Token | is |
Feature activation | +0.000 |
Token | up |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.437 |
Token | to |
Feature activation | +2.514 |
Token | respond |
Feature activation | +1.868 |
Token | , |
Feature activation | +0.311 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | G |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.443 |
Token | was |
Feature activation | +2.292 |
Token | hearing |
Feature activation | +1.513 |
Token | an |
Feature activation | +0.762 |
Token | appeal |
Feature activation | +0.130 |
Token | filed |
Feature activation | +0.321 |
Token | by |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.274 |
Token | concluded |
Feature activation | +2.175 |
Token | the |
Feature activation | +1.137 |
Token | state |
Feature activation | +1.029 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | flawed |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.507 |
Token | can |
Feature activation | +2.081 |
Token | dismiss |
Feature activation | +1.913 |
Token | the |
Feature activation | +0.242 |
Token | cases |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | uphold |
Feature activation | +0.151 |
Token | Ļ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.455 |
Token | found |
Feature activation | +2.039 |
Token | Wild |
Feature activation | +0.705 |
Token | ers |
Feature activation | +0.000 |
Token | not |
Feature activation | +0.000 |
Token | guilty |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.548 |
Token | found |
Feature activation | +1.991 |
Token | the |
Feature activation | +1.084 |
Token | mother |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | However |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.298 |
Token | found |
Feature activation | +1.978 |
Token | the |
Feature activation | +1.225 |
Token | argument |
Feature activation | +0.584 |
Token | intriguing |
Feature activation | +0.000 |
Token | enough |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.925 |
Token | found |
Feature activation | +1.671 |
Token | that |
Feature activation | +0.143 |
Token | Carter |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | actions |
Feature activation | +0.000 |
Token | flawed |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.507 |
Token | can |
Feature activation | +2.081 |
Token | dismiss |
Feature activation | +1.913 |
Token | the |
Feature activation | +0.242 |
Token | cases |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | uphold |
Feature activation | +0.151 |
Token | the |
Feature activation | +0.000 |
Token | up |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.437 |
Token | to |
Feature activation | +2.514 |
Token | respond |
Feature activation | +1.868 |
Token | , |
Feature activation | +0.311 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | G |
Feature activation | +0.000 |
Token | orman |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | appointed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.367 |
Token | to |
Feature activation | +1.858 |
Token | administ |
Feature activation | +1.099 |
Token | rate |
Feature activation | +0.345 |
Token | the |
Feature activation | +0.491 |
Token | settlement |
Feature activation | +0.132 |
Token | , |
Feature activation | +0.019 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.544 |
Token | ordered |
Feature activation | +1.829 |
Token | ambassador |
Feature activation | +0.466 |
Token | Dan |
Feature activation | +0.000 |
Token | ie |
Feature activation | +0.000 |
Token | le |
Feature activation | +0.000 |
Token | M |
Feature activation | +0.000 |
Token | men |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Under |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.382 |
Token | 's |
Feature activation | +1.816 |
Token | interpretation |
Feature activation | +0.553 |
Token | of |
Feature activation | +0.000 |
Token | Islamic |
Feature activation | +0.000 |
Token | law |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | High |
Feature activation | +0.000 |
Token | Court |
Feature activation | +0.572 |
Token | R |
Feature activation | +1.789 |
Token | uling |
Feature activation | +0.874 |
Token | Ċ |
Feature activation | +0.145 |
Token | Ċ |
Feature activation | +0.029 |
Token | S |
Feature activation | +0.000 |
Token | oci |
Feature activation | +0.000 |
Token | women |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | If |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.099 |
Token | goes |
Feature activation | +1.783 |
Token | along |
Feature activation | +1.015 |
Token | , |
Feature activation | +0.419 |
Token | it |
Feature activation | +0.000 |
Token | could |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | ambiguous |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.390 |
Token | said |
Feature activation | +1.777 |
Token | . |
Feature activation | +0.921 |
Token | It |
Feature activation | +0.277 |
Token | has |
Feature activation | +0.450 |
Token | 80 |
Feature activation | +0.159 |
Token | different |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.713 |
Token | lawyers |
Feature activation | +0.032 |
Token | representing |
Feature activation | +0.000 |
Token | Er |
Feature activation | +0.000 |
Token | de |
Feature activation | +0.000 |
Token | ly |
Feature activation | +0.000 |
Token | agan |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | face |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | on |
Feature activation | +1.492 |
Token | the |
Feature activation | +1.701 |
Token | criminal |
Feature activation | +0.811 |
Token | charges |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | relation |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.925 |
Token | found |
Feature activation | +1.671 |
Token | that |
Feature activation | +0.143 |
Token | Carter |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | actions |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.321 |
Token | ruled |
Feature activation | +1.654 |
Token | that |
Feature activation | +0.119 |
Token | was |
Feature activation | +0.582 |
Token | wrong |
Feature activation | +0.176 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.080 |
Top resid features:
|
Token | is |
Feature activation | +0.030 |
Top resid features:
|
Token | up |
Feature activation | +0.116 |
Top resid features:
|
Token | to |
Feature activation | -0.042 |
Top resid features:
|
Token | the |
Feature activation | +0.168 |
Top resid features:
|
Token | court |
Feature activation | +3.642 |
Top resid features:
|
Token | to |
Feature activation | +0.042 |
Top resid features:
|
Token | respond |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ŀ |
Feature activation | +0.000 |
Top resid features:
|
Token | said |
Feature activation | +0.037 |
Top resid features:
|
Token | . |
Feature activation | +0.007 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.043 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.042 |
Top resid features:
|
Token | The |
Feature activation | +0.209 |
Top resid features:
|
Token | court |
Feature activation | +3.146 |
Top resid features:
|
Token | was |
Feature activation | +0.107 |
Top resid features:
|
Token | hearing |
Feature activation | +0.000 |
Top resid features:
|
Token | an |
Feature activation | +0.000 |
Top resid features:
|
Token | appeal |
Feature activation | +0.000 |
Top resid features:
|
Token | filed |
Feature activation | +0.000 |
Top resid features:
|
Token | movement |
Feature activation | +0.035 |
Top resid features:
|
Token | . |
Feature activation | -0.008 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.008 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.015 |
Top resid features:
|
Token | The |
Feature activation | +0.192 |
Top resid features:
|
Token | court |
Feature activation | +3.603 |
Top resid features:
|
Token | concluded |
Feature activation | -0.013 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | state |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ļ |
Feature activation | +0.000 |
Top resid features:
|
Token | maintained |
Feature activation | +0.003 |
Top resid features:
|
Token | was |
Feature activation | +0.031 |
Top resid features:
|
Token | flawed |
Feature activation | +0.030 |
Top resid features:
|
Token | . |
Feature activation | +0.071 |
Top resid features:
|
Token | The |
Feature activation | +0.259 |
Top resid features:
|
Token | court |
Feature activation | +3.293 |
Top resid features:
|
Token | can |
Feature activation | +0.154 |
Top resid features:
|
Token | dismiss |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | cases |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.013 |
Top resid features:
|
Token | Ļ |
Feature activation | -0.017 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.042 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.038 |
Top resid features:
|
Token | The |
Feature activation | +0.129 |
Top resid features:
|
Token | court |
Feature activation | +3.160 |
Top resid features:
|
Token | found |
Feature activation | -0.009 |
Top resid features:
|
Token | Wild |
Feature activation | +0.000 |
Top resid features:
|
Token | ers |
Feature activation | +0.000 |
Top resid features:
|
Token | not |
Feature activation | +0.000 |
Top resid features:
|
Token | guilty |
Feature activation | +0.000 |
Top resid features:
|
Token | father |
Feature activation | -0.015 |
Top resid features:
|
Token | . |
Feature activation | +0.057 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.046 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.039 |
Top resid features:
|
Token | The |
Feature activation | +0.136 |
Top resid features:
|
Token | court |
Feature activation | +2.943 |
Top resid features:
|
Token | found |
Feature activation | +0.010 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | mother |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ļ |
Feature activation | +0.000 |
Top resid features:
|
Token | charged |
Feature activation | +0.010 |
Top resid features:
|
Token | . |
Feature activation | +0.033 |
Top resid features:
|
Token | However |
Feature activation | +0.049 |
Top resid features:
|
Token | , |
Feature activation | +0.014 |
Top resid features:
|
Token | the |
Feature activation | +0.167 |
Top resid features:
|
Token | court |
Feature activation | +2.963 |
Top resid features:
|
Token | found |
Feature activation | +0.087 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | argument |
Feature activation | +0.000 |
Top resid features:
|
Token | intriguing |
Feature activation | +0.000 |
Top resid features:
|
Token | enough |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.003 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.028 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.027 |
Top resid features:
|
Token | " |
Feature activation | -0.036 |
Top resid features:
|
Token | This |
Feature activation | +0.221 |
Top resid features:
|
Token | court |
Feature activation | +3.128 |
Top resid features:
|
Token | has |
Feature activation | +0.019 |
Top resid features:
|
Token | found |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | Carter |
Feature activation | +0.000 |
Top resid features:
|
Token | 's |
Feature activation | +0.000 |
Top resid features:
|
Token | maintained |
Feature activation | +0.004 |
Top resid features:
|
Token | was |
Feature activation | +0.029 |
Top resid features:
|
Token | flawed |
Feature activation | -0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.020 |
Top resid features:
|
Token | The |
Feature activation | +0.202 |
Top resid features:
|
Token | court |
Feature activation | +2.931 |
Top resid features:
|
Token | can |
Feature activation | +0.267 |
Top resid features:
|
Token | dismiss |
Feature activation | +0.123 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | cases |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | +0.088 |
Top resid features:
|
Token | is |
Feature activation | +0.038 |
Top resid features:
|
Token | up |
Feature activation | +0.097 |
Top resid features:
|
Token | to |
Feature activation | -0.029 |
Top resid features:
|
Token | the |
Feature activation | +0.135 |
Top resid features:
|
Token | court |
Feature activation | +2.768 |
Top resid features:
|
Token | to |
Feature activation | +0.135 |
Top resid features:
|
Token | respond |
Feature activation | +0.057 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ŀ |
Feature activation | +0.000 |
Top resid features:
|
Token | who |
Feature activation | +0.039 |
Top resid features:
|
Token | was |
Feature activation | +0.035 |
Top resid features:
|
Token | appointed |
Feature activation | +0.123 |
Top resid features:
|
Token | by |
Feature activation | +0.090 |
Top resid features:
|
Token | the |
Feature activation | +0.184 |
Top resid features:
|
Token | court |
Feature activation | +2.771 |
Top resid features:
|
Token | to |
Feature activation | +0.080 |
Top resid features:
|
Token | administ |
Feature activation | +0.000 |
Top resid features:
|
Token | rate |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | settlement |
Feature activation | +0.000 |
Top resid features:
|
Token | decision |
Feature activation | +0.012 |
Top resid features:
|
Token | . |
Feature activation | +0.043 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.044 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.041 |
Top resid features:
|
Token | The |
Feature activation | +0.238 |
Top resid features:
|
Token | court |
Feature activation | +2.603 |
Top resid features:
|
Token | ordered |
Feature activation | +0.139 |
Top resid features:
|
Token | ambassador |
Feature activation | +0.000 |
Top resid features:
|
Token | Dan |
Feature activation | +0.000 |
Top resid features:
|
Token | ie |
Feature activation | +0.000 |
Top resid features:
|
Token | le |
Feature activation | +0.000 |
Top resid features:
|
Token | seven |
Feature activation | +0.050 |
Top resid features:
|
Token | men |
Feature activation | +0.020 |
Top resid features:
|
Token | . |
Feature activation | +0.030 |
Top resid features:
|
Token | Under |
Feature activation | -0.092 |
Top resid features:
|
Token | the |
Feature activation | +0.143 |
Top resid features:
|
Token | court |
Feature activation | +3.007 |
Top resid features:
|
Token | 's |
Feature activation | +0.036 |
Top resid features:
|
Token | interpretation |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | Islamic |
Feature activation | +0.000 |
Top resid features:
|
Token | law |
Feature activation | +0.000 |
Top resid features:
|
Token | neighborhoods |
Feature activation | -0.036 |
Top resid features:
|
Token | . |
Feature activation | +0.012 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.050 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.055 |
Top resid features:
|
Token | High |
Feature activation | +0.029 |
Top resid features:
|
Token | Court |
Feature activation | +3.026 |
Top resid features:
|
Token | R |
Feature activation | +0.097 |
Top resid features:
|
Token | uling |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | S |
Feature activation | +0.000 |
Top resid features:
|
Token | benefit |
Feature activation | +0.016 |
Top resid features:
|
Token | women |
Feature activation | -0.026 |
Top resid features:
|
Token | . |
Feature activation | +0.040 |
Top resid features:
|
Token | If |
Feature activation | +0.028 |
Top resid features:
|
Token | the |
Feature activation | +0.153 |
Top resid features:
|
Token | court |
Feature activation | +2.879 |
Top resid features:
|
Token | goes |
Feature activation | +0.068 |
Top resid features:
|
Token | along |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | could |
Feature activation | +0.000 |
Top resid features:
|
Token | Ŀ |
Feature activation | -0.007 |
Top resid features:
|
Token | is |
Feature activation | +0.033 |
Top resid features:
|
Token | ambiguous |
Feature activation | -0.036 |
Top resid features:
|
Token | , |
Feature activation | -0.017 |
Top resid features:
|
Token | the |
Feature activation | +0.218 |
Top resid features:
|
Token | court |
Feature activation | +2.709 |
Top resid features:
|
Token | said |
Feature activation | +0.227 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | It |
Feature activation | +0.000 |
Top resid features:
|
Token | has |
Feature activation | +0.000 |
Top resid features:
|
Token | 80 |
Feature activation | +0.000 |
Top resid features:
|
Token | victims |
Feature activation | +0.017 |
Top resid features:
|
Token | . |
Feature activation | +0.015 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.066 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.065 |
Top resid features:
|
Token | In |
Feature activation | +0.090 |
Top resid features:
|
Token | court |
Feature activation | +2.867 |
Top resid features:
|
Token | , |
Feature activation | +0.082 |
Top resid features:
|
Token | lawyers |
Feature activation | +0.000 |
Top resid features:
|
Token | representing |
Feature activation | +0.000 |
Top resid features:
|
Token | Er |
Feature activation | +0.000 |
Top resid features:
|
Token | de |
Feature activation | +0.000 |
Top resid features:
|
Token | Fl |
Feature activation | +0.031 |
Top resid features:
|
Token | an |
Feature activation | +0.008 |
Top resid features:
|
Token | agan |
Feature activation | -0.034 |
Top resid features:
|
Token | will |
Feature activation | +0.015 |
Top resid features:
|
Token | face |
Feature activation | +0.048 |
Top resid features:
|
Token | court |
Feature activation | +2.615 |
Top resid features:
|
Token | on |
Feature activation | +0.333 |
Top resid features:
|
Token | the |
Feature activation | +0.099 |
Top resid features:
|
Token | criminal |
Feature activation | +0.000 |
Top resid features:
|
Token | charges |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.007 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.032 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.030 |
Top resid features:
|
Token | " |
Feature activation | -0.031 |
Top resid features:
|
Token | This |
Feature activation | +0.127 |
Top resid features:
|
Token | court |
Feature activation | +2.848 |
Top resid features:
|
Token | has |
Feature activation | +0.057 |
Top resid features:
|
Token | found |
Feature activation | +0.070 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | Carter |
Feature activation | +0.000 |
Top resid features:
|
Token | 's |
Feature activation | +0.000 |
Top resid features:
|
Token | one |
Feature activation | +0.013 |
Top resid features:
|
Token | . |
Feature activation | +0.038 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.037 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.035 |
Top resid features:
|
Token | The |
Feature activation | +0.202 |
Top resid features:
|
Token | court |
Feature activation | +2.645 |
Top resid features:
|
Token | ruled |
Feature activation | -0.013 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | was |
Feature activation | +0.000 |
Top resid features:
|
Token | wrong |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | +0.000 |
Token | up |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.437 |
Token | to |
Feature activation | +2.514 |
Token | respond |
Feature activation | +1.868 |
Token | , |
Feature activation | +0.311 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | G |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.443 |
Token | was |
Feature activation | +2.292 |
Token | hearing |
Feature activation | +1.513 |
Token | an |
Feature activation | +0.762 |
Token | appeal |
Feature activation | +0.130 |
Token | filed |
Feature activation | +0.321 |
Token | by |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.274 |
Token | concluded |
Feature activation | +2.175 |
Token | the |
Feature activation | +1.137 |
Token | state |
Feature activation | +1.029 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.455 |
Token | found |
Feature activation | +2.039 |
Token | Wild |
Feature activation | +0.705 |
Token | ers |
Feature activation | +0.000 |
Token | not |
Feature activation | +0.000 |
Token | guilty |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | flawed |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.507 |
Token | can |
Feature activation | +2.081 |
Token | dismiss |
Feature activation | +1.913 |
Token | the |
Feature activation | +0.242 |
Token | cases |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | uphold |
Feature activation | +0.151 |
Token | up |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.437 |
Token | to |
Feature activation | +2.514 |
Token | respond |
Feature activation | +1.868 |
Token | , |
Feature activation | +0.311 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | G |
Feature activation | +0.000 |
Token | orman |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.925 |
Token | found |
Feature activation | +1.671 |
Token | that |
Feature activation | +0.143 |
Token | Carter |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | actions |
Feature activation | +0.000 |
Token | men |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Under |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.382 |
Token | 's |
Feature activation | +1.816 |
Token | interpretation |
Feature activation | +0.553 |
Token | of |
Feature activation | +0.000 |
Token | Islamic |
Feature activation | +0.000 |
Token | law |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | women |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | If |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.099 |
Token | goes |
Feature activation | +1.783 |
Token | along |
Feature activation | +1.015 |
Token | , |
Feature activation | +0.419 |
Token | it |
Feature activation | +0.000 |
Token | could |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | appointed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.367 |
Token | to |
Feature activation | +1.858 |
Token | administ |
Feature activation | +1.099 |
Token | rate |
Feature activation | +0.345 |
Token | the |
Feature activation | +0.491 |
Token | settlement |
Feature activation | +0.132 |
Token | , |
Feature activation | +0.019 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | 11 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.418 |
Token | heard |
Feature activation | +1.587 |
Token | L |
Feature activation | +0.330 |
Token | avin |
Feature activation | +0.000 |
Token | ia |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | battled |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | An |
Feature activation | +0.000 |
Token | Athens |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | on |
Feature activation | +1.114 |
Token | Wednesday |
Feature activation | +1.619 |
Token | acquitted |
Feature activation | +1.081 |
Token | anarchist |
Feature activation | +0.000 |
Token | Cost |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | Sak |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.925 |
Token | found |
Feature activation | +1.671 |
Token | that |
Feature activation | +0.143 |
Token | Carter |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | actions |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.713 |
Token | lawyers |
Feature activation | +0.032 |
Token | representing |
Feature activation | +0.000 |
Token | Er |
Feature activation | +0.000 |
Token | de |
Feature activation | +0.000 |
Token | ly |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.321 |
Token | ruled |
Feature activation | +1.654 |
Token | that |
Feature activation | +0.119 |
Token | was |
Feature activation | +0.582 |
Token | wrong |
Feature activation | +0.176 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | 'll |
Feature activation | +0.000 |
Token | go |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | and |
Feature activation | +1.129 |
Token | I |
Feature activation | +1.283 |
Token | 'll |
Feature activation | +0.673 |
Token | sit |
Feature activation | +0.487 |
Token | there |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | drink |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | Dublin |
Feature activation | +0.000 |
Token | Circuit |
Feature activation | +0.000 |
Token | Criminal |
Feature activation | +0.000 |
Token | Court |
Feature activation | +0.000 |
Token | collapsed |
Feature activation | +1.295 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.025 |
Token | charges |
Feature activation | +0.000 |
Token | were |
Feature activation | +0.000 |
Token | withdrawn |
Feature activation | +0.000 |
Token | standing |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | in |
Feature activation | +1.342 |
Token | the |
Feature activation | +1.351 |
Token | public |
Feature activation | +0.791 |
Token | âĢ |
Feature activation | +0.023 |
Token | Ļ |
Feature activation | +0.052 |
Token | s |
Feature activation | +0.000 |
Token | mind |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | discrimination |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.153 |
Token | said |
Feature activation | +1.477 |
Token | Oklahoma |
Feature activation | +0.085 |
Token | hasn |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | t |
Feature activation | +0.000 |
Token | would |
Feature activation | +0.000 |
Token | get |
Feature activation | +0.000 |
Token | off |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.145 |
Token | as |
Feature activation | +1.497 |
Token | soon |
Feature activation | +0.494 |
Token | as |
Feature activation | +0.000 |
Token | possible |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | trust |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.932 |
Token | âĢ |
Feature activation | +1.134 |
Token | Ļ |
Feature activation | +1.192 |
Token | s |
Feature activation | +0.000 |
Token | own |
Feature activation | +1.004 |
Token | integrity |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Victoria |
Feature activation | +0.000 |
Token | only |
Feature activation | +0.000 |
Token | asked |
Feature activation | +0.000 |
Token | her |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | for |
Feature activation | +1.122 |
Token | three |
Feature activation | +1.041 |
Token | years |
Feature activation | +0.666 |
Token | of |
Feature activation | +0.000 |
Token | g |
Feature activation | +0.149 |
Token | oth |
Feature activation | +0.207 |
Token | . |
Feature activation | +0.000 |
Token | How |
Feature activation | +0.000 |
Token | can |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | determine |
Feature activation | +1.196 |
Token | what |
Feature activation | +0.249 |
Token | the |
Feature activation | +0.414 |
Token | boy |
Feature activation | +0.000 |
Token | really |
Feature activation | +0.000 |
Token | wants |
Feature activation | +0.000 |
Token | up |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.322 |
Token | of |
Feature activation | +0.735 |
Token | law |
Feature activation | +1.151 |
Token | ." |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | CM |
Feature activation | +0.000 |
Token | March |
Feature activation | +0.000 |
Token | before |
Feature activation | +0.000 |
Token | any |
Feature activation | +0.000 |
Token | disciplinary |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | to |
Feature activation | +1.069 |
Token | explain |
Feature activation | +0.729 |
Token | to |
Feature activation | +0.000 |
Token | me |
Feature activation | +0.000 |
Token | exactly |
Feature activation | +0.000 |
Token | what |
Feature activation | +0.000 |
Token | She |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.049 |
Token | âĢ |
Feature activation | +0.470 |
Token | Ļ |
Feature activation | +0.882 |
Token | s |
Feature activation | +0.000 |
Token | decision |
Feature activation | +0.000 |
Token | could |
Feature activation | +0.007 |
Token | lead |
Feature activation | +0.145 |
Token | to |
Feature activation | +0.000 |
Token | her |
Feature activation | +0.000 |
Token | lengthy |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | battle |
Feature activation | +0.197 |
Token | to |
Feature activation | +0.844 |
Token | return |
Feature activation | +0.897 |
Token | to |
Feature activation | +0.000 |
Token | her |
Feature activation | +0.000 |
Token | position |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | There |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | results |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.110 |
Token | where |
Feature activation | +0.939 |
Token | she |
Feature activation | +0.199 |
Token | will |
Feature activation | +0.000 |
Token | be |
Feature activation | +0.000 |
Token | forced |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | nothing |
Feature activation | +0.000 |
Token | upcoming |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.170 |
Token | d |
Feature activation | +0.961 |
Token | ocket |
Feature activation | +0.541 |
Token | for |
Feature activation | +0.017 |
Token | the |
Feature activation | +0.219 |
Token | three |
Feature activation | +0.163 |
Token | . |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.932 |
Token | âĢ |
Feature activation | +1.134 |
Token | Ļ |
Feature activation | +1.192 |
Token | s |
Feature activation | +0.000 |
Token | own |
Feature activation | +1.004 |
Token | integrity |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | logic |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.415 |
Token | 's |
Feature activation | +1.263 |
Token | decision |
Feature activation | +0.742 |
Token | once |
Feature activation | +0.689 |
Token | again |
Feature activation | +0.000 |
Token | confirms |
Feature activation | +0.069 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | appeared |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | briefly |
Feature activation | +1.399 |
Token | on |
Feature activation | +0.896 |
Token | Tuesday |
Feature activation | +0.535 |
Token | , |
Feature activation | +0.110 |
Token | November |
Feature activation | +0.000 |
Token | 28 |
Feature activation | +0.000 |
Token | 2017 |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | released |
Feature activation | +0.000 |
Token | pursuant |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.640 |
Token | order |
Feature activation | +0.401 |
Token | due |
Feature activation | +0.748 |
Token | to |
Feature activation | +0.495 |
Token | Z |
Feature activation | +0.073 |
Token | adv |
Feature activation | +0.028 |
Token | yd |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Federal |
Feature activation | +0.000 |
Token | District |
Feature activation | +0.000 |
Token | Court |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.635 |
Token | Manhattan |
Feature activation | +0.585 |
Token | , |
Feature activation | +0.033 |
Token | an |
Feature activation | +0.000 |
Token | S |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | same |
Feature activation | +0.000 |
Token | test |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | high |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.243 |
Token | used |
Feature activation | +0.514 |
Token | to |
Feature activation | +0.479 |
Token | invalid |
Feature activation | +0.000 |
Token | ate |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | can |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | determine |
Feature activation | +1.196 |
Token | what |
Feature activation | +0.249 |
Token | the |
Feature activation | +0.414 |
Token | boy |
Feature activation | +0.000 |
Token | really |
Feature activation | +0.000 |
Token | wants |
Feature activation | +0.000 |
Token | ? |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | y |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | formal |
Feature activation | +0.494 |
Token | ities |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Lord |
Feature activation | +0.000 |
Token | Chief |
Feature activation | +0.000 |
Token | Arkansas |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | seek |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | action |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.254 |
Token | collect |
Feature activation | +0.698 |
Token | the |
Feature activation | +0.000 |
Token | tax |
Feature activation | +0.000 |
Token | revenue |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.151 |
Token | at |
Feature activation | +1.286 |
Token | a |
Feature activation | +1.651 |
Token | later |
Feature activation | +0.928 |
Token | date |
Feature activation | +0.352 |
Token | . |
Feature activation | +0.000 |
Token | Another |
Feature activation | +0.000 |
Token | student |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | also |
Feature activation | +0.000 |
Token | New |
Feature activation | +0.000 |
Token | York |
Feature activation | +0.000 |
Token | City |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | âĢĶ |
Feature activation | +0.379 |
Token | but |
Feature activation | +0.120 |
Token | , |
Feature activation | +0.379 |
Token | like |
Feature activation | +0.000 |
Token | all |
Feature activation | +0.000 |
Token | good |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | ability |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | create |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | life |
Feature activation | +0.000 |
Token | like |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | tension |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | party |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | style |
Feature activation | +0.000 |
Token | bus |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | there |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | stri |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | no |
Feature activation | +0.000 |
Token | point |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | trying |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | No |
Feature activation | +0.000 |
Token | point |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | Railway |
Feature activation | +0.000 |
Token | Children |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | 1970 |
Feature activation | +0.000 |
Token | ) |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Go |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | Between |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | board |
Feature activation | +0.000 |
Token | âĢĶ |
Feature activation | +0.000 |
Token | he |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | voted |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | weaken |
Feature activation | +0.000 |
Token | some |
Feature activation | +0.000 |
Token | environmental |
Feature activation | +0.000 |
Token | regulations |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Rosen |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | advised |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.089 |
Token | to |
Feature activation | +2.429 |
Token | throw |
Feature activation | +1.093 |
Token | out |
Feature activation | +0.291 |
Token | the |
Feature activation | +0.000 |
Token | old |
Feature activation | +0.000 |
Token | playbook |
Feature activation | +0.000 |
Token | Sh |
Feature activation | +0.000 |
Token | afer |
Feature activation | +0.000 |
Token | argue |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | should |
Feature activation | +2.378 |
Token | ignore |
Feature activation | +1.599 |
Token | President |
Feature activation | +0.059 |
Token | - |
Feature activation | +0.000 |
Token | elect |
Feature activation | +0.000 |
Token | Donald |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | essel |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.081 |
Token | just |
Feature activation | +2.196 |
Token | gives |
Feature activation | +1.726 |
Token | it |
Feature activation | +0.444 |
Token | to |
Feature activation | +0.161 |
Token | him |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | massacres |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | asked |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.136 |
Token | to |
Feature activation | +2.171 |
Token | show |
Feature activation | +1.785 |
Token | him |
Feature activation | +0.459 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | nation |
Feature activation | +0.000 |
Token | familiar |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.078 |
Token | have |
Feature activation | +1.712 |
Token | an |
Feature activation | +2.066 |
Token | inherent |
Feature activation | +1.676 |
Token | suspicion |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | being |
Feature activation | +0.000 |
Token | recorded |
Feature activation | +0.000 |
Token | entirely |
Feature activation | +0.000 |
Token | expected |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.263 |
Token | suddenly |
Feature activation | +2.023 |
Token | painted |
Feature activation | +1.302 |
Token | her |
Feature activation | +0.479 |
Token | as |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | evil |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.583 |
Token | , |
Feature activation | +2.016 |
Token | and |
Feature activation | +1.477 |
Token | academ |
Feature activation | +0.623 |
Token | e |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | been |
Feature activation | +0.207 |
Token | yesterday |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.459 |
Token | showed |
Feature activation | +1.961 |
Token | up |
Feature activation | +0.844 |
Token | Ċ |
Feature activation | +0.028 |
Token | Ċ |
Feature activation | +0.046 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | ave |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.116 |
Token | , |
Feature activation | +1.961 |
Token | including |
Feature activation | +1.363 |
Token | Stephen |
Feature activation | +0.030 |
Token | A |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Smith |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | To |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.483 |
Token | he |
Feature activation | +1.893 |
Token | was |
Feature activation | +0.941 |
Token | , |
Feature activation | +0.579 |
Token | but |
Feature activation | +0.000 |
Token | behind |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | spot |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | and |
Feature activation | +1.605 |
Token | powerful |
Feature activation | +1.862 |
Token | politicians |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | least |
Feature activation | +0.000 |
Token | she |
Feature activation | +0.000 |
Token | ing |
Feature activation | +0.000 |
Token | skepticism |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.387 |
Token | âĢĶ |
Feature activation | +1.830 |
Token | including |
Feature activation | +1.573 |
Token | commentators |
Feature activation | +0.277 |
Token | âĢĶ |
Feature activation | +0.067 |
Token | simply |
Feature activation | +0.088 |
Token | reported |
Feature activation | +0.000 |
Token | ett |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.236 |
Token | and |
Feature activation | +1.829 |
Token | political |
Feature activation | +1.134 |
Token | establishment |
Feature activation | +0.194 |
Token | and |
Feature activation | +0.205 |
Token | who |
Feature activation | +0.139 |
Token | is |
Feature activation | +0.042 |
Token | and |
Feature activation | +0.000 |
Token | asked |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.136 |
Token | to |
Feature activation | +2.171 |
Token | show |
Feature activation | +1.785 |
Token | him |
Feature activation | +0.459 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | nation |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | used |
Feature activation | +0.000 |
Token | both |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.259 |
Token | and |
Feature activation | +1.768 |
Token | fiery |
Feature activation | +1.275 |
Token | rhetoric |
Feature activation | +0.028 |
Token | to |
Feature activation | +0.109 |
Token | tell |
Feature activation | +0.389 |
Token | his |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | maintained |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.223 |
Token | in |
Feature activation | +1.750 |
Token | a |
Feature activation | +1.457 |
Token | successful |
Feature activation | +1.092 |
Token | effort |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | defeat |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | problem |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.674 |
Token | and |
Feature activation | +1.749 |
Token | technology |
Feature activation | +1.147 |
Token | industries |
Feature activation | +0.278 |
Token | are |
Feature activation | +0.105 |
Token | urgently |
Feature activation | +0.096 |
Token | searching |
Feature activation | +0.000 |
Token | importantly |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | how |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.422 |
Token | is |
Feature activation | +1.747 |
Token | completely |
Feature activation | +1.374 |
Token | turning |
Feature activation | +0.896 |
Token | a |
Feature activation | +0.166 |
Token | blind |
Feature activation | +0.232 |
Token | eye |
Feature activation | +0.000 |
Token | last |
Feature activation | +0.000 |
Token | weekend |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | liberal |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | tried |
Feature activation | +1.742 |
Token | to |
Feature activation | +1.607 |
Token | hit |
Feature activation | +0.665 |
Token | Donald |
Feature activation | +0.000 |
Token | Trump |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | essel |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.081 |
Token | just |
Feature activation | +2.196 |
Token | gives |
Feature activation | +1.726 |
Token | it |
Feature activation | +0.444 |
Token | to |
Feature activation | +0.161 |
Token | him |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | no |
Feature activation | +0.000 |
Token | Professor |
Feature activation | -0.080 |
Top resid features:
|
Token | Rosen |
Feature activation | +0.014 |
Top resid features:
|
Token | has |
Feature activation | -0.019 |
Top resid features:
|
Token | advised |
Feature activation | +0.304 |
Top resid features:
|
Token | the |
Feature activation | +0.285 |
Top resid features:
|
Token | media |
Feature activation | +3.456 |
Top resid features:
|
Token | to |
Feature activation | -0.119 |
Top resid features:
|
Token | throw |
Feature activation | +0.000 |
Top resid features:
|
Token | out |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | old |
Feature activation | +0.000 |
Top resid features:
|
Token | Jack |
Feature activation | -0.024 |
Top resid features:
|
Token | Sh |
Feature activation | +0.004 |
Top resid features:
|
Token | afer |
Feature activation | -0.004 |
Top resid features:
|
Token | argue |
Feature activation | -0.014 |
Top resid features:
|
Token | the |
Feature activation | +0.299 |
Top resid features:
|
Token | media |
Feature activation | +3.459 |
Top resid features:
|
Token | should |
Feature activation | +0.002 |
Top resid features:
|
Token | ignore |
Feature activation | +0.000 |
Top resid features:
|
Token | President |
Feature activation | +0.000 |
Top resid features:
|
Token | - |
Feature activation | +0.000 |
Top resid features:
|
Token | elect |
Feature activation | +0.000 |
Top resid features:
|
Token | Phil |
Feature activation | -0.053 |
Top resid features:
|
Token | K |
Feature activation | -0.033 |
Top resid features:
|
Token | essel |
Feature activation | -0.033 |
Top resid features:
|
Token | . |
Feature activation | +0.067 |
Top resid features:
|
Token | The |
Feature activation | +0.168 |
Top resid features:
|
Token | media |
Feature activation | +3.541 |
Top resid features:
|
Token | just |
Feature activation | -0.037 |
Top resid features:
|
Token | gives |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | him |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.002 |
Top resid features:
|
Token | massacres |
Feature activation | +0.043 |
Top resid features:
|
Token | and |
Feature activation | -0.037 |
Top resid features:
|
Token | asked |
Feature activation | +0.194 |
Top resid features:
|
Token | the |
Feature activation | +0.233 |
Top resid features:
|
Token | media |
Feature activation | +3.142 |
Top resid features:
|
Token | to |
Feature activation | -0.098 |
Top resid features:
|
Token | show |
Feature activation | +0.000 |
Top resid features:
|
Token | him |
Feature activation | +0.000 |
Top resid features:
|
Token | where |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | aren |
Feature activation | -0.033 |
Top resid features:
|
Token | 't |
Feature activation | -0.008 |
Top resid features:
|
Token | familiar |
Feature activation | -0.044 |
Top resid features:
|
Token | with |
Feature activation | -0.104 |
Top resid features:
|
Token | the |
Feature activation | +0.077 |
Top resid features:
|
Token | media |
Feature activation | +3.227 |
Top resid features:
|
Token | have |
Feature activation | +0.390 |
Top resid features:
|
Token | an |
Feature activation | -0.004 |
Top resid features:
|
Token | inherent |
Feature activation | +0.000 |
Top resid features:
|
Token | suspicion |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | were |
Feature activation | -0.041 |
Top resid features:
|
Token | entirely |
Feature activation | -0.016 |
Top resid features:
|
Token | expected |
Feature activation | +0.011 |
Top resid features:
|
Token | . |
Feature activation | +0.201 |
Top resid features:
|
Token | The |
Feature activation | +0.186 |
Top resid features:
|
Token | media |
Feature activation | +3.209 |
Top resid features:
|
Token | suddenly |
Feature activation | -0.099 |
Top resid features:
|
Token | painted |
Feature activation | +0.000 |
Top resid features:
|
Token | her |
Feature activation | +0.000 |
Top resid features:
|
Token | as |
Feature activation | +0.000 |
Top resid features:
|
Token | an |
Feature activation | +0.000 |
Top resid features:
|
Token | members |
Feature activation | -0.033 |
Top resid features:
|
Token | in |
Feature activation | -0.030 |
Top resid features:
|
Token | government |
Feature activation | +0.065 |
Top resid features:
|
Token | , |
Feature activation | +0.005 |
Top resid features:
|
Token | the |
Feature activation | +0.290 |
Top resid features:
|
Token | media |
Feature activation | +3.044 |
Top resid features:
|
Token | , |
Feature activation | +0.084 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | academ |
Feature activation | +0.000 |
Top resid features:
|
Token | e |
Feature activation | +0.000 |
Top resid features:
|
Token | have |
Feature activation | +0.000 |
Top resid features:
|
Token | reporters |
Feature activation | +0.063 |
Top resid features:
|
Token | yesterday |
Feature activation | -0.034 |
Top resid features:
|
Token | , |
Feature activation | +0.061 |
Top resid features:
|
Token | and |
Feature activation | -0.075 |
Top resid features:
|
Token | the |
Feature activation | +0.230 |
Top resid features:
|
Token | media |
Feature activation | +2.934 |
Top resid features:
|
Token | showed |
Feature activation | +0.055 |
Top resid features:
|
Token | up |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | g |
Feature activation | -0.012 |
Top resid features:
|
Token | ave |
Feature activation | -0.010 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.037 |
Top resid features:
|
Token | Ŀ |
Feature activation | -0.024 |
Top resid features:
|
Token | the |
Feature activation | +0.343 |
Top resid features:
|
Token | media |
Feature activation | +2.992 |
Top resid features:
|
Token | , |
Feature activation | -0.001 |
Top resid features:
|
Token | including |
Feature activation | +0.000 |
Top resid features:
|
Token | Stephen |
Feature activation | +0.000 |
Top resid features:
|
Token | A |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.005 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.009 |
Top resid features:
|
Token | " |
Feature activation | -0.047 |
Top resid features:
|
Token | To |
Feature activation | -0.111 |
Top resid features:
|
Token | the |
Feature activation | +0.272 |
Top resid features:
|
Token | media |
Feature activation | +3.084 |
Top resid features:
|
Token | he |
Feature activation | +0.011 |
Top resid features:
|
Token | was |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | but |
Feature activation | +0.000 |
Top resid features:
|
Token | behind |
Feature activation | +0.000 |
Top resid features:
|
Token | on |
Feature activation | -0.043 |
Top resid features:
|
Token | the |
Feature activation | +0.009 |
Top resid features:
|
Token | spot |
Feature activation | -0.068 |
Top resid features:
|
Token | with |
Feature activation | -0.065 |
Top resid features:
|
Token | the |
Feature activation | +0.159 |
Top resid features:
|
Token | media |
Feature activation | +3.142 |
Top resid features:
|
Token | and |
Feature activation | +0.008 |
Top resid features:
|
Token | powerful |
Feature activation | +0.017 |
Top resid features:
|
Token | politicians |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | at |
Feature activation | +0.000 |
Top resid features:
|
Token | inc |
Feature activation | -0.042 |
Top resid features:
|
Token | ing |
Feature activation | -0.039 |
Top resid features:
|
Token | skepticism |
Feature activation | +0.035 |
Top resid features:
|
Token | , |
Feature activation | +0.017 |
Top resid features:
|
Token | the |
Feature activation | +0.298 |
Top resid features:
|
Token | media |
Feature activation | +2.927 |
Top resid features:
|
Token | âĢĶ |
Feature activation | +0.044 |
Top resid features:
|
Token | including |
Feature activation | +0.000 |
Top resid features:
|
Token | commentators |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢĶ |
Feature activation | +0.000 |
Top resid features:
|
Token | simply |
Feature activation | +0.000 |
Top resid features:
|
Token | vend |
Feature activation | +0.048 |
Top resid features:
|
Token | ett |
Feature activation | -0.042 |
Top resid features:
|
Token | as |
Feature activation | +0.020 |
Top resid features:
|
Token | by |
Feature activation | +0.007 |
Top resid features:
|
Token | the |
Feature activation | +0.216 |
Top resid features:
|
Token | media |
Feature activation | +2.906 |
Top resid features:
|
Token | and |
Feature activation | -0.052 |
Top resid features:
|
Token | political |
Feature activation | +0.000 |
Top resid features:
|
Token | establishment |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | who |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | massacres |
Feature activation | +0.030 |
Top resid features:
|
Token | and |
Feature activation | -0.012 |
Top resid features:
|
Token | asked |
Feature activation | +0.017 |
Top resid features:
|
Token | the |
Feature activation | +0.163 |
Top resid features:
|
Token | media |
Feature activation | +2.705 |
Top resid features:
|
Token | to |
Feature activation | -0.043 |
Top resid features:
|
Token | show |
Feature activation | +0.158 |
Top resid features:
|
Token | him |
Feature activation | +0.000 |
Top resid features:
|
Token | where |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | Abbas |
Feature activation | +0.030 |
Top resid features:
|
Token | has |
Feature activation | -0.047 |
Top resid features:
|
Token | used |
Feature activation | -0.003 |
Top resid features:
|
Token | both |
Feature activation | +0.373 |
Top resid features:
|
Token | the |
Feature activation | +0.121 |
Top resid features:
|
Token | media |
Feature activation | +2.737 |
Top resid features:
|
Token | and |
Feature activation | -0.080 |
Top resid features:
|
Token | fiery |
Feature activation | +0.000 |
Top resid features:
|
Token | rhetoric |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | tell |
Feature activation | +0.000 |
Top resid features:
|
Token | ists |
Feature activation | +0.008 |
Top resid features:
|
Token | and |
Feature activation | -0.053 |
Top resid features:
|
Token | maintained |
Feature activation | +0.119 |
Top resid features:
|
Token | by |
Feature activation | -0.092 |
Top resid features:
|
Token | the |
Feature activation | +0.300 |
Top resid features:
|
Token | media |
Feature activation | +2.764 |
Top resid features:
|
Token | in |
Feature activation | -0.072 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | successful |
Feature activation | +0.000 |
Top resid features:
|
Token | effort |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | become |
Feature activation | -0.063 |
Top resid features:
|
Token | a |
Feature activation | -0.022 |
Top resid features:
|
Token | problem |
Feature activation | +0.008 |
Top resid features:
|
Token | that |
Feature activation | +0.111 |
Top resid features:
|
Token | the |
Feature activation | +0.218 |
Top resid features:
|
Token | media |
Feature activation | +2.929 |
Top resid features:
|
Token | and |
Feature activation | -0.081 |
Top resid features:
|
Token | technology |
Feature activation | +0.000 |
Top resid features:
|
Token | industries |
Feature activation | +0.000 |
Top resid features:
|
Token | are |
Feature activation | +0.000 |
Top resid features:
|
Token | urgently |
Feature activation | +0.000 |
Top resid features:
|
Token | most |
Feature activation | -0.005 |
Top resid features:
|
Token | importantly |
Feature activation | -0.009 |
Top resid features:
|
Token | , |
Feature activation | +0.040 |
Top resid features:
|
Token | how |
Feature activation | +0.054 |
Top resid features:
|
Token | the |
Feature activation | +0.127 |
Top resid features:
|
Token | media |
Feature activation | +3.022 |
Top resid features:
|
Token | is |
Feature activation | -0.045 |
Top resid features:
|
Token | completely |
Feature activation | +0.000 |
Top resid features:
|
Token | turning |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | blind |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢĵ |
Feature activation | -0.018 |
Top resid features:
|
Token | last |
Feature activation | -0.047 |
Top resid features:
|
Token | weekend |
Feature activation | -0.029 |
Top resid features:
|
Token | the |
Feature activation | +0.161 |
Top resid features:
|
Token | liberal |
Feature activation | +0.223 |
Top resid features:
|
Token | media |
Feature activation | +2.831 |
Top resid features:
|
Token | tried |
Feature activation | +0.078 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | hit |
Feature activation | +0.000 |
Top resid features:
|
Token | Donald |
Feature activation | +0.000 |
Top resid features:
|
Token | Trump |
Feature activation | +0.000 |
Top resid features:
|
Token | Phil |
Feature activation | -0.027 |
Top resid features:
|
Token | K |
Feature activation | -0.016 |
Top resid features:
|
Token | essel |
Feature activation | -0.039 |
Top resid features:
|
Token | . |
Feature activation | +0.081 |
Top resid features:
|
Token | The |
Feature activation | +0.123 |
Top resid features:
|
Token | media |
Feature activation | +2.860 |
Top resid features:
|
Token | just |
Feature activation | +0.110 |
Top resid features:
|
Token | gives |
Feature activation | -0.003 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | him |
Feature activation | +0.000 |
Top resid features:
|
Token | Sh |
Feature activation | +0.000 |
Token | afer |
Feature activation | +0.000 |
Token | argue |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | should |
Feature activation | +2.378 |
Token | ignore |
Feature activation | +1.599 |
Token | President |
Feature activation | +0.059 |
Token | - |
Feature activation | +0.000 |
Token | elect |
Feature activation | +0.000 |
Token | Donald |
Feature activation | +0.000 |
Token | Rosen |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | advised |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.089 |
Token | to |
Feature activation | +2.429 |
Token | throw |
Feature activation | +1.093 |
Token | out |
Feature activation | +0.291 |
Token | the |
Feature activation | +0.000 |
Token | old |
Feature activation | +0.000 |
Token | playbook |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | essel |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.081 |
Token | just |
Feature activation | +2.196 |
Token | gives |
Feature activation | +1.726 |
Token | it |
Feature activation | +0.444 |
Token | to |
Feature activation | +0.161 |
Token | him |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | entirely |
Feature activation | +0.000 |
Token | expected |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.263 |
Token | suddenly |
Feature activation | +2.023 |
Token | painted |
Feature activation | +1.302 |
Token | her |
Feature activation | +0.479 |
Token | as |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | evil |
Feature activation | +0.000 |
Token | yesterday |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.459 |
Token | showed |
Feature activation | +1.961 |
Token | up |
Feature activation | +0.844 |
Token | Ċ |
Feature activation | +0.028 |
Token | Ċ |
Feature activation | +0.046 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.583 |
Token | , |
Feature activation | +2.016 |
Token | and |
Feature activation | +1.477 |
Token | academ |
Feature activation | +0.623 |
Token | e |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | been |
Feature activation | +0.207 |
Token | massacres |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | asked |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.136 |
Token | to |
Feature activation | +2.171 |
Token | show |
Feature activation | +1.785 |
Token | him |
Feature activation | +0.459 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | nation |
Feature activation | +0.000 |
Token | familiar |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.078 |
Token | have |
Feature activation | +1.712 |
Token | an |
Feature activation | +2.066 |
Token | inherent |
Feature activation | +1.676 |
Token | suspicion |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | being |
Feature activation | +0.000 |
Token | recorded |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | used |
Feature activation | +0.000 |
Token | both |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.259 |
Token | and |
Feature activation | +1.768 |
Token | fiery |
Feature activation | +1.275 |
Token | rhetoric |
Feature activation | +0.028 |
Token | to |
Feature activation | +0.109 |
Token | tell |
Feature activation | +0.389 |
Token | his |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | they |
Feature activation | +0.000 |
Token | believed |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | was |
Feature activation | +1.724 |
Token | biased |
Feature activation | +1.151 |
Token | against |
Feature activation | +0.348 |
Token | Trump |
Feature activation | +0.248 |
Token | . |
Feature activation | +0.000 |
Token | Numbers |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | To |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.483 |
Token | he |
Feature activation | +1.893 |
Token | was |
Feature activation | +0.941 |
Token | , |
Feature activation | +0.579 |
Token | but |
Feature activation | +0.000 |
Token | behind |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | problem |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.674 |
Token | and |
Feature activation | +1.749 |
Token | technology |
Feature activation | +1.147 |
Token | industries |
Feature activation | +0.278 |
Token | are |
Feature activation | +0.105 |
Token | urgently |
Feature activation | +0.096 |
Token | searching |
Feature activation | +0.000 |
Token | ett |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.236 |
Token | and |
Feature activation | +1.829 |
Token | political |
Feature activation | +1.134 |
Token | establishment |
Feature activation | +0.194 |
Token | and |
Feature activation | +0.205 |
Token | who |
Feature activation | +0.139 |
Token | is |
Feature activation | +0.042 |
Token | yet |
Feature activation | +0.000 |
Token | made |
Feature activation | +0.000 |
Token | comment |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | about |
Feature activation | +1.533 |
Token | the |
Feature activation | +1.191 |
Token | tweet |
Feature activation | +0.383 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | right |
Feature activation | +0.000 |
Token | wing |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | to |
Feature activation | +1.608 |
Token | avoid |
Feature activation | +1.384 |
Token | a |
Feature activation | +0.782 |
Token | primary |
Feature activation | +0.405 |
Token | challenge |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | situation |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.109 |
Token | , |
Feature activation | +1.687 |
Token | and |
Feature activation | +1.119 |
Token | how |
Feature activation | +0.295 |
Token | his |
Feature activation | +0.068 |
Token | public |
Feature activation | +0.000 |
Token | image |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | ] |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | US |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.218 |
Token | falsely |
Feature activation | +1.669 |
Token | accused |
Feature activation | +1.090 |
Token | China |
Feature activation | +0.498 |
Token | of |
Feature activation | +0.000 |
Token | using |
Feature activation | +0.050 |
Token | Operation |
Feature activation | +0.000 |
Token | skepticism |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.387 |
Token | âĢĶ |
Feature activation | +1.830 |
Token | including |
Feature activation | +1.573 |
Token | commentators |
Feature activation | +0.277 |
Token | âĢĶ |
Feature activation | +0.067 |
Token | simply |
Feature activation | +0.088 |
Token | reported |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | aro |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | local |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | the |
Feature activation | +1.207 |
Token | plane |
Feature activation | +1.280 |
Token | crashed |
Feature activation | +0.000 |
Token | while |
Feature activation | +0.000 |
Token | attempting |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | return |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | Dutch |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.769 |
Token | described |
Feature activation | +1.416 |
Token | them |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | About |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | how |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.422 |
Token | is |
Feature activation | +1.747 |
Token | completely |
Feature activation | +1.374 |
Token | turning |
Feature activation | +0.896 |
Token | a |
Feature activation | +0.166 |
Token | blind |
Feature activation | +0.232 |
Token | eye |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | corporate |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.202 |
Token | are |
Feature activation | +1.232 |
Token | again |
Feature activation | +0.763 |
Token | rolling |
Feature activation | +1.236 |
Token | out |
Feature activation | +0.000 |
Token | their |
Feature activation | +0.000 |
Token | tired |
Feature activation | +0.000 |
Token | arguments |
Feature activation | +0.000 |
Token | about |
Feature activation | +0.000 |
Token | dubbed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | fans |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.118 |
Token | as |
Feature activation | +1.359 |
Token | the |
Feature activation | +1.170 |
Token | " |
Feature activation | +1.031 |
Token | Mir |
Feature activation | +0.088 |
Token | acle |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | referred |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.129 |
Token | , |
Feature activation | +1.203 |
Token | for |
Feature activation | +1.015 |
Token | example |
Feature activation | +0.521 |
Token | by |
Feature activation | +0.000 |
Token | es |
Feature activation | +0.000 |
Token | y |
Feature activation | +0.000 |
Token | ria |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | industry |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | print |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.010 |
Token | and |
Feature activation | +1.067 |
Token | books |
Feature activation | +0.820 |
Token | . |
Feature activation | +0.000 |
Token | Millions |
Feature activation | +0.000 |
Token | are |
Feature activation | +0.000 |
Token | already |
Feature activation | +0.000 |
Token | Complex |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.275 |
Token | and |
Feature activation | +1.276 |
Token | the |
Feature activation | +1.147 |
Token | installation |
Feature activation | +0.769 |
Token | of |
Feature activation | +0.023 |
Token | institutional |
Feature activation | +0.000 |
Token | ized |
Feature activation | +0.000 |
Token | slavery |
Feature activation | +0.000 |
Token | they |
Feature activation | +0.000 |
Token | believed |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | was |
Feature activation | +1.724 |
Token | biased |
Feature activation | +1.151 |
Token | against |
Feature activation | +0.348 |
Token | Trump |
Feature activation | +0.248 |
Token | . |
Feature activation | +0.000 |
Token | Numbers |
Feature activation | +0.000 |
Token | like |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.236 |
Token | and |
Feature activation | +1.829 |
Token | political |
Feature activation | +1.134 |
Token | establishment |
Feature activation | +0.194 |
Token | and |
Feature activation | +0.205 |
Token | who |
Feature activation | +0.139 |
Token | is |
Feature activation | +0.042 |
Token | backed |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | mainstream |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.496 |
Token | the |
Feature activation | +1.078 |
Token | confused |
Feature activation | +0.970 |
Token | independents |
Feature activation | +0.388 |
Token | , |
Feature activation | +0.084 |
Token | and |
Feature activation | +0.000 |
Token | most |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | published |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | mainstream |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.895 |
Token | explores |
Feature activation | +0.222 |
Token | claims |
Feature activation | +0.000 |
Token | made |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | some |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | recall |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Media |
Feature activation | +0.377 |
Token | campaigns |
Feature activation | +0.381 |
Token | will |
Feature activation | +0.877 |
Token | be |
Feature activation | +1.194 |
Token | launched |
Feature activation | +0.720 |
Token | fraught |
Feature activation | +0.085 |
Token | with |
Feature activation | +0.000 |
Token | lies |
Feature activation | +0.000 |
Token | l |
Feature activation | +0.000 |
Token | uv |
Feature activation | +0.000 |
Token | v |
Feature activation | +0.000 |
Token | ie |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | here |
Feature activation | +0.753 |
Token | ; |
Feature activation | +0.082 |
Token | Channel |
Feature activation | +0.000 |
Token | 4 |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | mainstream |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.091 |
Token | is |
Feature activation | +1.285 |
Token | obsess |
Feature activation | +0.781 |
Token | ively |
Feature activation | +0.864 |
Token | compiling |
Feature activation | +0.484 |
Token | it |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | enthal |
Feature activation | +0.000 |
Token | Delete |
Feature activation | +0.000 |
Token | Edit |
Feature activation | +0.000 |
Token | embedded |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.589 |
Token | the |
Feature activation | +0.368 |
Token | Files |
Feature activation | +0.074 |
Token | Tab |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | re |
Feature activation | +0.000 |
Token | mainstream |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.305 |
Token | are |
Feature activation | +1.385 |
Token | in |
Feature activation | +1.111 |
Token | on |
Feature activation | +0.740 |
Token | the |
Feature activation | +0.605 |
Token | game |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | deceit |
Feature activation | +0.000 |
Token | about |
Feature activation | +0.000 |
Token | America |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Arab |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | outlets |
Feature activation | +0.000 |
Token | reported |
Feature activation | +0.511 |
Token | that |
Feature activation | +0.669 |
Token | Israeli |
Feature activation | +0.022 |
Token | forces |
Feature activation | +0.000 |
Token | launched |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | missile |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | more |
Feature activation | +0.000 |
Token | Canadian |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | coverage |
Feature activation | +0.454 |
Token | and |
Feature activation | +0.714 |
Token | eventually |
Feature activation | +0.163 |
Token | the |
Feature activation | +0.000 |
Token | attention |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.255 |
Token | the |
Feature activation | +0.000 |
Token | first |
Feature activation | +0.000 |
Token | major |
Feature activation | +0.000 |
Token | mainstream |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | coverage |
Feature activation | +0.424 |
Token | was |
Feature activation | +0.555 |
Token | in |
Feature activation | +0.268 |
Token | The |
Feature activation | +0.249 |
Token | New |
Feature activation | +0.000 |
Token | York |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | Internet |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | social |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.088 |
Token | our |
Feature activation | +0.291 |
Token | side |
Feature activation | +0.004 |
Token | , |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.042 |
Token | and |
Feature activation | +1.055 |
Token | non |
Feature activation | +1.227 |
Token | - |
Feature activation | +1.010 |
Token | governmental |
Feature activation | +0.358 |
Token | organisations |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | NG |
Feature activation | +0.000 |
Token | Os |
Feature activation | +0.000 |
Token | ). |
Feature activation | +0.000 |
Token | see |
Feature activation | +0.000 |
Token | themselves |
Feature activation | +0.000 |
Token | represented |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | media |
Feature activation | +0.278 |
Token | . |
Feature activation | +0.251 |
Token | Wong |
Feature activation | +0.000 |
Token | Fu |
Feature activation | +0.000 |
Token | produces |
Feature activation | +0.000 |
Token | character |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Press |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | propaganda |
Feature activation | +0.184 |
Token | to |
Feature activation | +0.225 |
Token | control |
Feature activation | +0.394 |
Token | all |
Feature activation | +0.000 |
Token | outlets |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | public |
Feature activation | +0.000 |
Token | information |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | surface |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | MSM |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.344 |
Token | year |
Feature activation | +0.360 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | psy |
Feature activation | +0.000 |
Token | b |
Feature activation | +0.000 |
Token | ient |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | psy |
Feature activation | +0.000 |
Token | bass |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | psy |
Feature activation | +0.000 |
Token | d |
Feature activation | +0.000 |
Token | ub |
Feature activation | +0.000 |
Token | high |
Feature activation | +0.000 |
Token | school |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Casey |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | Miller |
Feature activation | +0.000 |
Token | are |
Feature activation | +0.000 |
Token | both |
Feature activation | +0.000 |
Token | over |
Feature activation | +0.000 |
Token | 21 |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | ech |
Feature activation | +0.000 |
Token | which |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | consume |
Feature activation | +0.000 |
Token | trees |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | grass |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | flowers |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | Wars |
Feature activation | +0.000 |
Token | shirts |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | superhero |
Feature activation | +0.000 |
Token | underwear |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | Supp |
Feature activation | +0.000 |
Token | lied |
Feature activation | +0.000 |
Token | ) |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | t |
Feature activation | +0.000 |
Token | want |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | expose |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | 2 |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | month |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | It |
Feature activation | +0.000 |
Token | allows |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.242 |
Token | secretly |
Feature activation | +1.936 |
Token | to |
Feature activation | +0.841 |
Token | track |
Feature activation | +0.874 |
Token | who |
Feature activation | +0.406 |
Token | a |
Feature activation | +0.000 |
Token | target |
Feature activation | +0.000 |
Token | out |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.847 |
Token | its |
Feature activation | +1.934 |
Token | proxies |
Feature activation | +0.810 |
Token | that |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | stock |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.276 |
Token | 's |
Feature activation | +1.569 |
Token | interest |
Feature activation | +1.882 |
Token | to |
Feature activation | +0.173 |
Token | get |
Feature activation | +0.436 |
Token | it |
Feature activation | +0.000 |
Token | right |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | federal |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | on |
Feature activation | +1.155 |
Token | Thursday |
Feature activation | +1.840 |
Token | decided |
Feature activation | +0.765 |
Token | to |
Feature activation | +0.013 |
Token | sue |
Feature activation | +0.252 |
Token | Pakistan |
Feature activation | +0.000 |
Token | Te |
Feature activation | +0.000 |
Token | ham |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | had |
Feature activation | +1.408 |
Token | created |
Feature activation | +1.759 |
Token | a |
Feature activation | +0.414 |
Token | " |
Feature activation | +0.303 |
Token | financial |
Feature activation | +0.000 |
Token | climate |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | .) |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | responded |
Feature activation | +1.722 |
Token | by |
Feature activation | +0.438 |
Token | ignoring |
Feature activation | +0.580 |
Token | the |
Feature activation | +0.000 |
Token | High |
Feature activation | +0.000 |
Token | Court |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | how |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.485 |
Token | behaving |
Feature activation | +1.696 |
Token | in |
Feature activation | +0.072 |
Token | its |
Feature activation | +1.074 |
Token | handling |
Feature activation | +0.247 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.223 |
Token | new |
Feature activation | +1.689 |
Token | guide |
Feature activation | +0.527 |
Token | includes |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | list |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | Trump |
Feature activation | +0.000 |
Token | believes |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.321 |
Token | can |
Feature activation | +1.687 |
Token | closely |
Feature activation | +1.274 |
Token | monitor |
Feature activation | +0.679 |
Token | every |
Feature activation | +0.000 |
Token | individual |
Feature activation | +0.000 |
Token | entering |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | message |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.007 |
Token | is |
Feature activation | +1.687 |
Token | trying |
Feature activation | +1.469 |
Token | to |
Feature activation | +0.685 |
Token | look |
Feature activation | +0.815 |
Token | after |
Feature activation | +0.000 |
Token | children |
Feature activation | +0.000 |
Token | [ |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | ] |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.500 |
Token | should |
Feature activation | +1.620 |
Token | not |
Feature activation | +1.262 |
Token | force |
Feature activation | +1.200 |
Token | them |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | do |
Feature activation | +0.000 |
Token | essential |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Government |
Feature activation | +0.361 |
Token | has |
Feature activation | +1.365 |
Token | an |
Feature activation | +1.613 |
Token | opportunity |
Feature activation | +1.150 |
Token | to |
Feature activation | +0.000 |
Token | do |
Feature activation | +0.232 |
Token | more |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | still |
Feature activation | +1.579 |
Token | hasn |
Feature activation | +0.918 |
Token | âĢ |
Feature activation | +0.508 |
Token | Ļ |
Feature activation | +0.000 |
Token | t |
Feature activation | +0.044 |
Token | followed |
Feature activation | +0.239 |
Token | it |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.276 |
Token | 's |
Feature activation | +1.569 |
Token | interest |
Feature activation | +1.882 |
Token | to |
Feature activation | +0.173 |
Token | get |
Feature activation | +0.436 |
Token | it |
Feature activation | +0.000 |
Token | right |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | says |
Feature activation | +1.560 |
Token | it |
Feature activation | +0.976 |
Token | is |
Feature activation | +0.545 |
Token | still |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | track |
Feature activation | +0.000 |
Token | E |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | needs |
Feature activation | +1.558 |
Token | to |
Feature activation | +0.775 |
Token | address |
Feature activation | +0.883 |
Token | " |
Feature activation | +0.000 |
Token | deep |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | Tuesday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | Government |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.742 |
Token | job |
Feature activation | +1.556 |
Token | is |
Feature activation | +0.242 |
Token | not |
Feature activation | +0.044 |
Token | to |
Feature activation | +0.000 |
Token | keep |
Feature activation | +0.000 |
Token | bureaucrats |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | hope |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | will |
Feature activation | +1.415 |
Token | diss |
Feature activation | +1.553 |
Token | ociate |
Feature activation | +1.089 |
Token | from |
Feature activation | +0.027 |
Token | them |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | otherwise |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | since |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.380 |
Token | is |
Feature activation | +1.512 |
Token | intervening |
Feature activation | +1.530 |
Token | in |
Feature activation | +0.277 |
Token | one |
Feature activation | +0.220 |
Token | area |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | saying |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | since |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.380 |
Token | is |
Feature activation | +1.512 |
Token | intervening |
Feature activation | +1.530 |
Token | in |
Feature activation | +0.277 |
Token | one |
Feature activation | +0.220 |
Token | area |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.013 |
Top resid features:
|
Token | : |
Feature activation | +0.046 |
Top resid features:
|
Token | It |
Feature activation | +0.065 |
Top resid features:
|
Token | allows |
Feature activation | +0.242 |
Top resid features:
|
Token | the |
Feature activation | +0.008 |
Top resid features:
|
Token | government |
Feature activation | +2.559 |
Top resid features:
|
Token | secretly |
Feature activation | +0.111 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | track |
Feature activation | +0.000 |
Top resid features:
|
Token | who |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | information |
Feature activation | +0.013 |
Top resid features:
|
Token | coming |
Feature activation | +0.058 |
Top resid features:
|
Token | out |
Feature activation | +0.040 |
Top resid features:
|
Token | from |
Feature activation | +0.042 |
Top resid features:
|
Token | the |
Feature activation | +0.083 |
Top resid features:
|
Token | government |
Feature activation | +2.338 |
Top resid features:
|
Token | and |
Feature activation | +0.231 |
Top resid features:
|
Token | its |
Feature activation | +0.133 |
Top resid features:
|
Token | proxies |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | has |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.050 |
Top resid features:
|
Token | it |
Feature activation | +0.033 |
Top resid features:
|
Token | 's |
Feature activation | +0.047 |
Top resid features:
|
Token | in |
Feature activation | -0.036 |
Top resid features:
|
Token | the |
Feature activation | +0.040 |
Top resid features:
|
Token | government |
Feature activation | +2.183 |
Top resid features:
|
Token | 's |
Feature activation | +0.512 |
Top resid features:
|
Token | interest |
Feature activation | +0.105 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | get |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | AB |
Feature activation | +0.022 |
Top resid features:
|
Token | AD |
Feature activation | +0.035 |
Top resid features:
|
Token | : |
Feature activation | +0.073 |
Top resid features:
|
Token | The |
Feature activation | +0.008 |
Top resid features:
|
Token | federal |
Feature activation | +0.516 |
Top resid features:
|
Token | government |
Feature activation | +1.896 |
Top resid features:
|
Token | on |
Feature activation | +0.245 |
Top resid features:
|
Token | Thursday |
Feature activation | +0.156 |
Top resid features:
|
Token | decided |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | sue |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | -0.028 |
Top resid features:
|
Token | Burn |
Feature activation | +0.005 |
Top resid features:
|
Token | ham |
Feature activation | +0.013 |
Top resid features:
|
Token | said |
Feature activation | +0.129 |
Top resid features:
|
Token | the |
Feature activation | +0.101 |
Top resid features:
|
Token | government |
Feature activation | +2.390 |
Top resid features:
|
Token | had |
Feature activation | +0.157 |
Top resid features:
|
Token | created |
Feature activation | +0.105 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | " |
Feature activation | +0.000 |
Top resid features:
|
Token | financial |
Feature activation | +0.000 |
Top resid features:
|
Token | Icelandic |
Feature activation | +0.046 |
Top resid features:
|
Token | .) |
Feature activation | +0.020 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.001 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.010 |
Top resid features:
|
Token | The |
Feature activation | -0.035 |
Top resid features:
|
Token | government |
Feature activation | +2.593 |
Top resid features:
|
Token | responded |
Feature activation | +0.118 |
Top resid features:
|
Token | by |
Feature activation | +0.000 |
Top resid features:
|
Token | ignoring |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | High |
Feature activation | +0.000 |
Top resid features:
|
Token | - |
Feature activation | +0.073 |
Top resid features:
|
Token | that |
Feature activation | +0.038 |
Top resid features:
|
Token | 's |
Feature activation | +0.008 |
Top resid features:
|
Token | how |
Feature activation | +0.212 |
Top resid features:
|
Token | the |
Feature activation | -0.062 |
Top resid features:
|
Token | government |
Feature activation | +2.468 |
Top resid features:
|
Token | is |
Feature activation | +0.123 |
Top resid features:
|
Token | behaving |
Feature activation | +0.047 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | its |
Feature activation | +0.000 |
Top resid features:
|
Token | handling |
Feature activation | +0.000 |
Top resid features:
|
Token | graduating |
Feature activation | +0.002 |
Top resid features:
|
Token | . |
Feature activation | +0.015 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.023 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.012 |
Top resid features:
|
Token | The |
Feature activation | -0.023 |
Top resid features:
|
Token | government |
Feature activation | +2.213 |
Top resid features:
|
Token | 's |
Feature activation | +0.315 |
Top resid features:
|
Token | new |
Feature activation | +0.113 |
Top resid features:
|
Token | guide |
Feature activation | +0.000 |
Top resid features:
|
Token | includes |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | Donald |
Feature activation | +0.030 |
Top resid features:
|
Token | Trump |
Feature activation | +0.076 |
Top resid features:
|
Token | believes |
Feature activation | +0.091 |
Top resid features:
|
Token | that |
Feature activation | +0.129 |
Top resid features:
|
Token | the |
Feature activation | +0.104 |
Top resid features:
|
Token | government |
Feature activation | +2.413 |
Top resid features:
|
Token | can |
Feature activation | +0.097 |
Top resid features:
|
Token | closely |
Feature activation | +0.000 |
Top resid features:
|
Token | monitor |
Feature activation | +0.000 |
Top resid features:
|
Token | every |
Feature activation | +0.000 |
Top resid features:
|
Token | individual |
Feature activation | +0.000 |
Top resid features:
|
Token | sending |
Feature activation | +0.090 |
Top resid features:
|
Token | the |
Feature activation | +0.022 |
Top resid features:
|
Token | message |
Feature activation | -0.036 |
Top resid features:
|
Token | that |
Feature activation | +0.166 |
Top resid features:
|
Token | the |
Feature activation | +0.105 |
Top resid features:
|
Token | government |
Feature activation | +2.255 |
Top resid features:
|
Token | is |
Feature activation | +0.120 |
Top resid features:
|
Token | trying |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | look |
Feature activation | +0.000 |
Top resid features:
|
Token | after |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ¦ |
Feature activation | +0.090 |
Top resid features:
|
Token | [ |
Feature activation | +0.145 |
Top resid features:
|
Token | but |
Feature activation | +0.108 |
Top resid features:
|
Token | ] |
Feature activation | +0.025 |
Top resid features:
|
Token | the |
Feature activation | +0.069 |
Top resid features:
|
Token | government |
Feature activation | +2.209 |
Top resid features:
|
Token | should |
Feature activation | +0.075 |
Top resid features:
|
Token | not |
Feature activation | +0.000 |
Top resid features:
|
Token | force |
Feature activation | +0.000 |
Top resid features:
|
Token | them |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | will |
Feature activation | +0.018 |
Top resid features:
|
Token | be |
Feature activation | +0.025 |
Top resid features:
|
Token | essential |
Feature activation | +0.061 |
Top resid features:
|
Token | . |
Feature activation | +0.032 |
Top resid features:
|
Token | The |
Feature activation | +0.064 |
Top resid features:
|
Token | Government |
Feature activation | +2.108 |
Top resid features:
|
Token | has |
Feature activation | +0.207 |
Top resid features:
|
Token | an |
Feature activation | +0.109 |
Top resid features:
|
Token | opportunity |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | do |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.044 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.009 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.018 |
Top resid features:
|
Token | But |
Feature activation | -0.092 |
Top resid features:
|
Token | the |
Feature activation | -0.019 |
Top resid features:
|
Token | government |
Feature activation | +2.495 |
Top resid features:
|
Token | still |
Feature activation | +0.100 |
Top resid features:
|
Token | hasn |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ļ |
Feature activation | +0.000 |
Top resid features:
|
Token | t |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.073 |
Top resid features:
|
Token | it |
Feature activation | +0.076 |
Top resid features:
|
Token | 's |
Feature activation | +0.017 |
Top resid features:
|
Token | in |
Feature activation | +0.174 |
Top resid features:
|
Token | the |
Feature activation | +0.106 |
Top resid features:
|
Token | government |
Feature activation | +2.109 |
Top resid features:
|
Token | 's |
Feature activation | +0.128 |
Top resid features:
|
Token | interest |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | get |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.007 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.015 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.007 |
Top resid features:
|
Token | But |
Feature activation | +0.085 |
Top resid features:
|
Token | the |
Feature activation | +0.017 |
Top resid features:
|
Token | government |
Feature activation | +2.353 |
Top resid features:
|
Token | says |
Feature activation | +0.159 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | +0.000 |
Top resid features:
|
Token | still |
Feature activation | +0.000 |
Top resid features:
|
Token | on |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.031 |
Top resid features:
|
Token | E |
Feature activation | -0.011 |
Top resid features:
|
Token | by |
Feature activation | +0.056 |
Top resid features:
|
Token | said |
Feature activation | +0.147 |
Top resid features:
|
Token | the |
Feature activation | +0.026 |
Top resid features:
|
Token | government |
Feature activation | +2.377 |
Top resid features:
|
Token | needs |
Feature activation | +0.131 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | address |
Feature activation | +0.000 |
Top resid features:
|
Token | " |
Feature activation | +0.000 |
Top resid features:
|
Token | deep |
Feature activation | +0.000 |
Top resid features:
|
Token | he |
Feature activation | +0.045 |
Top resid features:
|
Token | said |
Feature activation | +0.045 |
Top resid features:
|
Token | Tuesday |
Feature activation | +0.014 |
Top resid features:
|
Token | . |
Feature activation | +0.011 |
Top resid features:
|
Token | " |
Feature activation | +0.048 |
Top resid features:
|
Token | Government |
Feature activation | +2.001 |
Top resid features:
|
Token | 's |
Feature activation | +0.194 |
Top resid features:
|
Token | job |
Feature activation | +0.107 |
Top resid features:
|
Token | is |
Feature activation | +0.000 |
Top resid features:
|
Token | not |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | them |
Feature activation | +0.048 |
Top resid features:
|
Token | . |
Feature activation | +0.019 |
Top resid features:
|
Token | I |
Feature activation | +0.004 |
Top resid features:
|
Token | hope |
Feature activation | +0.243 |
Top resid features:
|
Token | the |
Feature activation | +0.116 |
Top resid features:
|
Token | government |
Feature activation | +1.882 |
Top resid features:
|
Token | will |
Feature activation | +0.200 |
Top resid features:
|
Token | diss |
Feature activation | +0.050 |
Top resid features:
|
Token | ociate |
Feature activation | +0.000 |
Top resid features:
|
Token | from |
Feature activation | +0.000 |
Top resid features:
|
Token | them |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | +0.018 |
Top resid features:
|
Token | saying |
Feature activation | +0.051 |
Top resid features:
|
Token | that |
Feature activation | +0.058 |
Top resid features:
|
Token | since |
Feature activation | +0.104 |
Top resid features:
|
Token | the |
Feature activation | +0.096 |
Top resid features:
|
Token | government |
Feature activation | +2.130 |
Top resid features:
|
Token | is |
Feature activation | +0.310 |
Top resid features:
|
Token | intervening |
Feature activation | -0.023 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | one |
Feature activation | +0.000 |
Top resid features:
|
Token | area |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | +0.015 |
Top resid features:
|
Token | saying |
Feature activation | +0.053 |
Top resid features:
|
Token | that |
Feature activation | +0.084 |
Top resid features:
|
Token | since |
Feature activation | +0.254 |
Top resid features:
|
Token | the |
Feature activation | +0.046 |
Top resid features:
|
Token | government |
Feature activation | +2.115 |
Top resid features:
|
Token | is |
Feature activation | +0.137 |
Top resid features:
|
Token | intervening |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | one |
Feature activation | +0.000 |
Top resid features:
|
Token | area |
Feature activation | +0.000 |
Top resid features:
|
Token | : |
Feature activation | +0.000 |
Token | It |
Feature activation | +0.000 |
Token | allows |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.242 |
Token | secretly |
Feature activation | +1.936 |
Token | to |
Feature activation | +0.841 |
Token | track |
Feature activation | +0.874 |
Token | who |
Feature activation | +0.406 |
Token | a |
Feature activation | +0.000 |
Token | target |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | federal |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | on |
Feature activation | +1.155 |
Token | Thursday |
Feature activation | +1.840 |
Token | decided |
Feature activation | +0.765 |
Token | to |
Feature activation | +0.013 |
Token | sue |
Feature activation | +0.252 |
Token | Pakistan |
Feature activation | +0.000 |
Token | Te |
Feature activation | +0.000 |
Token | ham |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | had |
Feature activation | +1.408 |
Token | created |
Feature activation | +1.759 |
Token | a |
Feature activation | +0.414 |
Token | " |
Feature activation | +0.303 |
Token | financial |
Feature activation | +0.000 |
Token | climate |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | out |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.847 |
Token | its |
Feature activation | +1.934 |
Token | proxies |
Feature activation | +0.810 |
Token | that |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | stock |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.276 |
Token | 's |
Feature activation | +1.569 |
Token | interest |
Feature activation | +1.882 |
Token | to |
Feature activation | +0.173 |
Token | get |
Feature activation | +0.436 |
Token | it |
Feature activation | +0.000 |
Token | right |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.276 |
Token | 's |
Feature activation | +1.569 |
Token | interest |
Feature activation | +1.882 |
Token | to |
Feature activation | +0.173 |
Token | get |
Feature activation | +0.436 |
Token | it |
Feature activation | +0.000 |
Token | right |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.223 |
Token | new |
Feature activation | +1.689 |
Token | guide |
Feature activation | +0.527 |
Token | includes |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | list |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | .) |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | responded |
Feature activation | +1.722 |
Token | by |
Feature activation | +0.438 |
Token | ignoring |
Feature activation | +0.580 |
Token | the |
Feature activation | +0.000 |
Token | High |
Feature activation | +0.000 |
Token | Court |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | still |
Feature activation | +1.579 |
Token | hasn |
Feature activation | +0.918 |
Token | âĢ |
Feature activation | +0.508 |
Token | Ļ |
Feature activation | +0.000 |
Token | t |
Feature activation | +0.044 |
Token | followed |
Feature activation | +0.239 |
Token | E |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | needs |
Feature activation | +1.558 |
Token | to |
Feature activation | +0.775 |
Token | address |
Feature activation | +0.883 |
Token | " |
Feature activation | +0.000 |
Token | deep |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | federal |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.713 |
Token | the |
Feature activation | +1.375 |
Token | Islamic |
Feature activation | +0.545 |
Token | State |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | Iraq |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | gal |
Feature activation | +0.000 |
Token | infection |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | recommends |
Feature activation | +1.402 |
Token | doctors |
Feature activation | +0.000 |
Token | stop |
Feature activation | +0.000 |
Token | using |
Feature activation | +0.144 |
Token | any |
Feature activation | +0.000 |
Token | sterile |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | saying |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Government |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.348 |
Token | shooting |
Feature activation | +1.473 |
Token | itself |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | foot |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | urges |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.049 |
Token | to |
Feature activation | +1.242 |
Token | introduce |
Feature activation | +1.499 |
Token | a |
Feature activation | +0.280 |
Token | voluntary |
Feature activation | +0.061 |
Token | body |
Feature activation | +0.078 |
Token | that |
Feature activation | +0.000 |
Token | would |
Feature activation | +0.000 |
Token | First |
Feature activation | +0.000 |
Token | wants |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Government |
Feature activation | +0.044 |
Token | to |
Feature activation | +1.222 |
Token | cover |
Feature activation | +1.506 |
Token | the |
Feature activation | +0.587 |
Token | cost |
Feature activation | +0.186 |
Token | of |
Feature activation | +0.000 |
Token | fees |
Feature activation | +0.037 |
Token | , |
Feature activation | +0.000 |
Token | December |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | gave |
Feature activation | +1.300 |
Token | the |
Feature activation | +1.281 |
Token | green |
Feature activation | +1.118 |
Token | light |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | 10 |
Feature activation | +0.000 |
Token | post |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | important |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | know |
Feature activation | +1.267 |
Token | the |
Feature activation | +0.949 |
Token | purchaser |
Feature activation | +0.007 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.429 |
Token | not |
Feature activation | +1.252 |
Token | going |
Feature activation | +0.930 |
Token | to |
Feature activation | +0.274 |
Token | be |
Feature activation | +0.030 |
Token | able |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | ] |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.500 |
Token | should |
Feature activation | +1.620 |
Token | not |
Feature activation | +1.262 |
Token | force |
Feature activation | +1.200 |
Token | them |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | do |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | attacks |
Feature activation | +0.000 |
Token | aside |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.179 |
Token | little |
Feature activation | +0.717 |
Token | interest |
Feature activation | +0.826 |
Token | in |
Feature activation | +0.000 |
Token | breaking |
Feature activation | +0.328 |
Token | up |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | while |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.183 |
Token | was |
Feature activation | +1.158 |
Token | immensely |
Feature activation | +1.386 |
Token | rich |
Feature activation | +0.310 |
Token | , |
Feature activation | +0.000 |
Token | particularly |
Feature activation | +0.000 |
Token | given |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | radical |
Feature activation | +0.000 |
Token | Taliban |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.375 |
Token | Afghanistan |
Feature activation | +1.044 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.125 |
Token | rise |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | al |
Feature activation | +0.000 |
Token | think |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | should |
Feature activation | +1.472 |
Token | be |
Feature activation | +1.446 |
Token | in |
Feature activation | +1.033 |
Token | charge |
Feature activation | +0.419 |
Token | of |
Feature activation | +0.000 |
Token | your |
Feature activation | +0.054 |
Token | life |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | alienated |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.057 |
Token | that |
Feature activation | +0.497 |
Token | is |
Feature activation | +1.048 |
Token | not |
Feature activation | +0.296 |
Token | above |
Feature activation | +0.000 |
Token | questionable |
Feature activation | +0.000 |
Token | tactics |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.012 |
Token | just |
Feature activation | +1.292 |
Token | wants |
Feature activation | +1.132 |
Token | to |
Feature activation | +0.686 |
Token | know |
Feature activation | +0.441 |
Token | how |
Feature activation | +0.234 |
Token | its |
Feature activation | +0.000 |
Token | programs |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | parents |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.799 |
Token | Ċ |
Feature activation | +0.205 |
Token | Ċ |
Feature activation | +0.073 |
Token | The |
Feature activation | +0.000 |
Token | guide |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | Brotherhood |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | dominated |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | Egyptian |
Feature activation | +0.877 |
Token | President |
Feature activation | +0.000 |
Token | Mohamed |
Feature activation | +0.000 |
Token | Morsi |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | brought |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.921 |
Token | head |
Feature activation | +1.160 |
Token | off |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | bubble |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | led |
Feature activation | +0.170 |
Token | by |
Feature activation | +0.350 |
Token | its |
Feature activation | +0.823 |
Token | leader |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Nikola |
Feature activation | +0.000 |
Token | Gr |
Feature activation | +0.000 |
Token | ue |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | local |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | denies |
Feature activation | +0.832 |
Token | the |
Feature activation | +0.360 |
Token | crackdown |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | Christianity |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | Our |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.056 |
Token | âĢ |
Feature activation | +0.276 |
Token | Ļ |
Feature activation | +0.585 |
Token | s |
Feature activation | +0.353 |
Token | sources |
Feature activation | +0.011 |
Token | and |
Feature activation | +0.000 |
Token | methods |
Feature activation | +0.000 |
Token | are |
Feature activation | +0.000 |
Token | autonomous |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.747 |
Token | the |
Feature activation | +0.625 |
Token | E |
Feature activation | +0.244 |
Token | Z |
Feature activation | +0.000 |
Token | L |
Feature activation | +0.000 |
Token | N |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Blair |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.646 |
Token | which |
Feature activation | +0.734 |
Token | dropped |
Feature activation | +0.422 |
Token | the |
Feature activation | +0.000 |
Token | requirement |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | foreign |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | too |
Feature activation | +0.000 |
Token | much |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.136 |
Token | too |
Feature activation | +0.658 |
Token | much |
Feature activation | +0.121 |
Token | debt |
Feature activation | +0.000 |
Token | ; |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | supporters |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Federal |
Feature activation | +0.000 |
Token | Government |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.392 |
Token | the |
Feature activation | +0.594 |
Token | Hob |
Feature activation | +0.000 |
Token | art |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | based |
Feature activation | +0.000 |
Token | chocolate |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | interim |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.136 |
Token | do |
Feature activation | +0.448 |
Token | everything |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | their |
Feature activation | +0.000 |
Token | power |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Australian |
Feature activation | +0.000 |
Token | Government |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.785 |
Token | very |
Feature activation | +0.797 |
Token | low |
Feature activation | +0.553 |
Token | gross |
Feature activation | +0.000 |
Token | debt |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | easily |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | federal |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.337 |
Token | to |
Feature activation | +0.538 |
Token | local |
Feature activation | +0.036 |
Token | law |
Feature activation | +0.000 |
Token | enforcement |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | However |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | estimates |
Feature activation | +0.551 |
Token | up |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | one |
Feature activation | +0.000 |
Token | million |
Feature activation | +0.000 |
Token | women |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | says |
Feature activation | +1.283 |
Token | , |
Feature activation | +0.728 |
Token | it |
Feature activation | +0.492 |
Token | must |
Feature activation | +0.000 |
Token | confirm |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | expert |
Feature activation | +0.000 |
Token | predicted |
Feature activation | +0.000 |
Token | dystopian |
Feature activation | +0.000 |
Token | governments |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | not |
Feature activation | +0.244 |
Token | being |
Feature activation | +0.293 |
Token | able |
Feature activation | +0.275 |
Token | to |
Feature activation | +0.281 |
Token | breathe |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | polluted |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Obama |
Feature activation | +0.000 |
Token | administration |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | ask |
Feature activation | +0.262 |
Token | Congress |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | establish |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Our |
Feature activation | +0.000 |
Token | governments |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.686 |
Token | become |
Feature activation | +1.064 |
Token | adept |
Feature activation | +0.334 |
Token | at |
Feature activation | +0.000 |
Token | getting |
Feature activation | +0.000 |
Token | their |
Feature activation | +0.000 |
Token | own |
Feature activation | +0.000 |
Token | way |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | scheme |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.246 |
Token | ) |
Feature activation | +0.717 |
Token | has |
Feature activation | +0.737 |
Token | been |
Feature activation | +0.643 |
Token | accepted |
Feature activation | +0.380 |
Token | ," |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | elections |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.295 |
Token | - |
Feature activation | +0.751 |
Token | politics |
Feature activation | +0.405 |
Token | , |
Feature activation | +0.000 |
Token | aust |
Feature activation | +0.000 |
Token | ral |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | going |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Det |
Feature activation | +0.000 |
Token | ailing |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | lives |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | people |
Feature activation | +0.000 |
Token | trying |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | search |
Feature activation | +0.000 |
Token | engines |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | over |
Feature activation | +0.000 |
Token | whelming |
Feature activation | +0.000 |
Token | ly |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | direct |
Feature activation | +0.000 |
Token | music |
Feature activation | +0.000 |
Token | fans |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | factors |
Feature activation | +0.000 |
Token | all |
Feature activation | +0.000 |
Token | contribute |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | fast |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | progress |
Feature activation | +0.000 |
Token | ing |
Feature activation | +0.000 |
Token | cancer |
Feature activation | +0.000 |
Token | ," |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | kind |
Feature activation | +0.000 |
Token | words |
Feature activation | +0.000 |
Token | ," |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | dad |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | there |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | another |
Feature activation | +0.000 |
Token | person |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | appointment |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | promoted |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | rear |
Feature activation | +0.000 |
Token | adm |
Feature activation | +0.000 |
Token | iral |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | ! |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.573 |
Token | gone |
Feature activation | +1.156 |
Token | c |
Feature activation | +0.517 |
Token | uck |
Feature activation | +0.000 |
Token | oo |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.043 |
Token | is |
Feature activation | +1.543 |
Token | grounded |
Feature activation | +1.217 |
Token | upon |
Feature activation | +0.000 |
Token | suffering |
Feature activation | +0.097 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | UK |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Unless |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | sees |
Feature activation | +1.509 |
Token | a |
Feature activation | +0.703 |
Token | second |
Feature activation | +0.103 |
Token | green |
Feature activation | +0.000 |
Token | revolution |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | film |
Feature activation | +0.000 |
Token | industry |
Feature activation | +0.000 |
Token | ? |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.478 |
Token | truly |
Feature activation | +1.032 |
Token | changed |
Feature activation | +1.005 |
Token | . |
Feature activation | +0.456 |
Token | Entertainment |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | As |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | continues |
Feature activation | +1.345 |
Token | warming |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | warming |
Feature activation | +0.000 |
Token | tends |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | 15 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | saw |
Feature activation | +1.325 |
Token | Ferguson |
Feature activation | +0.344 |
Token | Police |
Feature activation | +0.000 |
Token | Chief |
Feature activation | +0.000 |
Token | Thomas |
Feature activation | +0.000 |
Token | Jackson |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.043 |
Token | is |
Feature activation | +1.543 |
Token | grounded |
Feature activation | +1.217 |
Token | upon |
Feature activation | +0.000 |
Token | suffering |
Feature activation | +0.097 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | ) |
Feature activation | +0.000 |
Token | -- |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.154 |
Token | risks |
Feature activation | +1.208 |
Token | disastrous |
Feature activation | +0.357 |
Token | income |
Feature activation | +0.000 |
Token | drops |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | ecological |
Feature activation | +0.000 |
Token | India |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | World |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +1.161 |
Token | Ļ |
Feature activation | +0.638 |
Token | s |
Feature activation | +0.000 |
Token | most |
Feature activation | +0.000 |
Token | dreaded |
Feature activation | +0.000 |
Token | terrorist |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | World |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | Most |
Feature activation | +0.464 |
Token | Dangerous |
Feature activation | +1.160 |
Token | Geek |
Feature activation | +0.000 |
Token | ": |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | ! |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.573 |
Token | gone |
Feature activation | +1.156 |
Token | c |
Feature activation | +0.517 |
Token | uck |
Feature activation | +0.000 |
Token | oo |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | cold |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | While |
Feature activation | +0.000 |
Token | yesterday |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | was |
Feature activation | +1.150 |
Token | o |
Feature activation | +0.400 |
Token | gling |
Feature activation | +0.142 |
Token | over |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | iPhone |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | / |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.133 |
Token | spinning |
Feature activation | +0.807 |
Token | slower |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | my |
Feature activation | +0.000 |
Token | mind |
Feature activation | +0.000 |
Token | which |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.172 |
Token | confronts |
Feature activation | +1.080 |
Token | global |
Feature activation | +0.015 |
Token | warming |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | fossil |
Feature activation | +0.000 |
Token | fuel |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | believe |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.045 |
Token | real |
Feature activation | +0.821 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | they |
Feature activation | +0.000 |
Token | absolutely |
Feature activation | +0.000 |
Token | / |
Feature activation | +0.000 |
Token | Jason |
Feature activation | +0.000 |
Token | Reed |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.037 |
Token | no |
Feature activation | +0.902 |
Token | crystal |
Feature activation | +0.000 |
Token | ball |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | see |
Feature activation | +0.000 |
Token | industry |
Feature activation | +0.000 |
Token | ? |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.478 |
Token | truly |
Feature activation | +1.032 |
Token | changed |
Feature activation | +1.005 |
Token | . |
Feature activation | +0.456 |
Token | Entertainment |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | ? |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.478 |
Token | truly |
Feature activation | +1.032 |
Token | changed |
Feature activation | +1.005 |
Token | . |
Feature activation | +0.456 |
Token | Entertainment |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | drivers |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | As |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | prepares |
Feature activation | +1.003 |
Token | for |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | coming |
Feature activation | +0.000 |
Token | future |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | say |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | keep |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | safe |
Feature activation | +0.977 |
Token | from |
Feature activation | +0.000 |
Token | Iran |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | nuclear |
Feature activation | +0.000 |
Token | ambitions |
Feature activation | +0.000 |
Token | Middle |
Feature activation | -0.014 |
Top resid features:
|
Token | East |
Feature activation | -0.022 |
Top resid features:
|
Token | ! |
Feature activation | -0.061 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.265 |
Top resid features:
|
Token | The |
Feature activation | -0.041 |
Top resid features:
|
Token | world |
Feature activation | +2.273 |
Top resid features:
|
Token | has |
Feature activation | -0.021 |
Top resid features:
|
Token | gone |
Feature activation | +0.000 |
Top resid features:
|
Token | c |
Feature activation | +0.000 |
Top resid features:
|
Token | uck |
Feature activation | +0.000 |
Top resid features:
|
Token | oo |
Feature activation | +0.000 |
Top resid features:
|
Token | words |
Feature activation | -0.038 |
Top resid features:
|
Token | : |
Feature activation | -0.081 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.013 |
Top resid features:
|
Token | ľ |
Feature activation | -0.038 |
Top resid features:
|
Token | The |
Feature activation | -0.012 |
Top resid features:
|
Token | world |
Feature activation | +2.148 |
Top resid features:
|
Token | is |
Feature activation | -0.050 |
Top resid features:
|
Token | grounded |
Feature activation | +0.000 |
Top resid features:
|
Token | upon |
Feature activation | +0.000 |
Top resid features:
|
Token | suffering |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | -0.044 |
Top resid features:
|
Token | UK |
Feature activation | -0.018 |
Top resid features:
|
Token | . |
Feature activation | -0.124 |
Top resid features:
|
Token | Unless |
Feature activation | -0.035 |
Top resid features:
|
Token | the |
Feature activation | +0.027 |
Top resid features:
|
Token | world |
Feature activation | +2.031 |
Top resid features:
|
Token | sees |
Feature activation | +0.007 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | second |
Feature activation | +0.000 |
Top resid features:
|
Token | green |
Feature activation | +0.000 |
Top resid features:
|
Token | revolution |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | -0.030 |
Token | film |
Feature activation | +0.007 |
Token | industry |
Feature activation | -0.015 |
Token | ? |
Feature activation | -0.179 |
Token | The |
Feature activation | +0.025 |
Token | world |
Feature activation | +2.083 |
Token | has |
Feature activation | -0.017 |
Token | truly |
Feature activation | +0.000 |
Token | changed |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Entertainment |
Feature activation | +0.000 |
Token | . |
Feature activation | -0.095 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.057 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.082 |
Top resid features:
|
Token | As |
Feature activation | +0.294 |
Top resid features:
|
Token | the |
Feature activation | -0.115 |
Top resid features:
|
Token | world |
Feature activation | +1.920 |
Top resid features:
|
Token | continues |
Feature activation | -0.140 |
Top resid features:
|
Token | warming |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | warming |
Feature activation | +0.000 |
Top resid features:
|
Token | Aug |
Feature activation | -0.092 |
Top resid features:
|
Token | . |
Feature activation | -0.045 |
Top resid features:
|
Token | 15 |
Feature activation | -0.057 |
Top resid features:
|
Token | , |
Feature activation | -0.134 |
Top resid features:
|
Token | the |
Feature activation | -0.005 |
Top resid features:
|
Token | world |
Feature activation | +1.944 |
Top resid features:
|
Token | saw |
Feature activation | +0.104 |
Top resid features:
|
Token | Ferguson |
Feature activation | +0.000 |
Top resid features:
|
Token | Police |
Feature activation | +0.000 |
Top resid features:
|
Token | Chief |
Feature activation | +0.000 |
Top resid features:
|
Token | Thomas |
Feature activation | +0.000 |
Top resid features:
|
Token | words |
Feature activation | -0.035 |
Top resid features:
|
Token | : |
Feature activation | -0.072 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.011 |
Top resid features:
|
Token | ľ |
Feature activation | -0.022 |
Top resid features:
|
Token | The |
Feature activation | +0.017 |
Top resid features:
|
Token | world |
Feature activation | +1.800 |
Top resid features:
|
Token | is |
Feature activation | -0.108 |
Top resid features:
|
Token | grounded |
Feature activation | -0.049 |
Top resid features:
|
Token | upon |
Feature activation | +0.000 |
Top resid features:
|
Token | suffering |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | UP |
Feature activation | +0.002 |
Top resid features:
|
Token | I |
Feature activation | -0.000 |
Top resid features:
|
Token | ) |
Feature activation | -0.053 |
Top resid features:
|
Token | -- |
Feature activation | -0.140 |
Top resid features:
|
Token | The |
Feature activation | +0.080 |
Top resid features:
|
Token | world |
Feature activation | +1.826 |
Top resid features:
|
Token | risks |
Feature activation | -0.187 |
Top resid features:
|
Token | disastrous |
Feature activation | +0.000 |
Top resid features:
|
Token | income |
Feature activation | +0.000 |
Top resid features:
|
Token | drops |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | -0.045 |
Top resid features:
|
Token | India |
Feature activation | -0.034 |
Top resid features:
|
Token | . |
Feature activation | -0.138 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.062 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.091 |
Top resid features:
|
Token | World |
Feature activation | +1.912 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.079 |
Top resid features:
|
Token | Ļ |
Feature activation | +0.000 |
Top resid features:
|
Token | s |
Feature activation | +0.000 |
Top resid features:
|
Token | most |
Feature activation | +0.000 |
Top resid features:
|
Token | dreaded |
Feature activation | +0.000 |
Top resid features:
|
Token | kel |
Feature activation | -0.012 |
Top resid features:
|
Token | aptly |
Feature activation | -0.010 |
Top resid features:
|
Token | entitled |
Feature activation | -0.113 |
Top resid features:
|
Token | " |
Feature activation | -0.024 |
Top resid features:
|
Token | The |
Feature activation | -0.035 |
Top resid features:
|
Token | World |
Feature activation | +1.644 |
Top resid features:
|
Token | 's |
Feature activation | -0.203 |
Top resid features:
|
Token | Most |
Feature activation | +0.336 |
Top resid features:
|
Token | Dangerous |
Feature activation | -0.030 |
Top resid features:
|
Token | Geek |
Feature activation | +0.000 |
Top resid features:
|
Token | ": |
Feature activation | +0.000 |
Top resid features:
|
Token | Middle |
Feature activation | -0.009 |
Top resid features:
|
Token | East |
Feature activation | -0.018 |
Top resid features:
|
Token | ! |
Feature activation | -0.037 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.215 |
Top resid features:
|
Token | The |
Feature activation | +0.061 |
Top resid features:
|
Token | world |
Feature activation | +1.879 |
Top resid features:
|
Token | has |
Feature activation | -0.190 |
Top resid features:
|
Token | gone |
Feature activation | -0.098 |
Top resid features:
|
Token | c |
Feature activation | +0.000 |
Top resid features:
|
Token | uck |
Feature activation | +0.000 |
Top resid features:
|
Token | oo |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | -0.041 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.118 |
Top resid features:
|
Token | While |
Feature activation | +0.029 |
Top resid features:
|
Token | yesterday |
Feature activation | -0.159 |
Top resid features:
|
Token | the |
Feature activation | -0.058 |
Top resid features:
|
Token | world |
Feature activation | +1.804 |
Top resid features:
|
Token | was |
Feature activation | -0.044 |
Top resid features:
|
Token | o |
Feature activation | +0.000 |
Top resid features:
|
Token | gling |
Feature activation | +0.000 |
Top resid features:
|
Token | over |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | over |
Feature activation | -0.117 |
Top resid features:
|
Token | time |
Feature activation | -0.041 |
Top resid features:
|
Token | / |
Feature activation | -0.216 |
Top resid features:
|
Token | But |
Feature activation | -0.181 |
Top resid features:
|
Token | the |
Feature activation | +0.004 |
Top resid features:
|
Token | world |
Feature activation | +2.053 |
Top resid features:
|
Token | is |
Feature activation | -0.062 |
Top resid features:
|
Token | spinning |
Feature activation | +0.000 |
Top resid features:
|
Token | slower |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | my |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | -0.058 |
Top resid features:
|
Token | which |
Feature activation | -0.067 |
Top resid features:
|
Token | , |
Feature activation | -0.155 |
Top resid features:
|
Token | as |
Feature activation | +0.121 |
Top resid features:
|
Token | the |
Feature activation | -0.067 |
Top resid features:
|
Token | world |
Feature activation | +1.717 |
Top resid features:
|
Token | confronts |
Feature activation | -0.021 |
Top resid features:
|
Token | global |
Feature activation | +0.000 |
Top resid features:
|
Token | warming |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | fossil |
Feature activation | +0.000 |
Top resid features:
|
Token | audience |
Feature activation | +0.004 |
Top resid features:
|
Token | to |
Feature activation | -0.067 |
Top resid features:
|
Token | believe |
Feature activation | -0.155 |
Top resid features:
|
Token | that |
Feature activation | -0.189 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | world |
Feature activation | +1.886 |
Top resid features:
|
Token | is |
Feature activation | -0.101 |
Top resid features:
|
Token | real |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | they |
Feature activation | +0.000 |
Top resid features:
|
Token | Reuters |
Feature activation | -0.004 |
Top resid features:
|
Token | / |
Feature activation | -0.133 |
Top resid features:
|
Token | Jason |
Feature activation | -0.046 |
Top resid features:
|
Token | Reed |
Feature activation | -0.075 |
Top resid features:
|
Token | The |
Feature activation | -0.009 |
Top resid features:
|
Token | world |
Feature activation | +1.765 |
Top resid features:
|
Token | has |
Feature activation | -0.018 |
Top resid features:
|
Token | no |
Feature activation | +0.000 |
Top resid features:
|
Token | crystal |
Feature activation | +0.000 |
Top resid features:
|
Token | ball |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | -0.026 |
Token | film |
Feature activation | -0.003 |
Token | industry |
Feature activation | +0.000 |
Token | ? |
Feature activation | -0.128 |
Token | The |
Feature activation | +0.037 |
Token | world |
Feature activation | +1.594 |
Token | has |
Feature activation | -0.104 |
Token | truly |
Feature activation | -0.012 |
Token | changed |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Entertainment |
Feature activation | +0.000 |
Token | the |
Feature activation | -0.018 |
Token | film |
Feature activation | +0.009 |
Token | industry |
Feature activation | -0.002 |
Token | ? |
Feature activation | -0.118 |
Token | The |
Feature activation | +0.027 |
Token | world |
Feature activation | +1.476 |
Token | has |
Feature activation | -0.061 |
Token | truly |
Feature activation | +0.002 |
Token | changed |
Feature activation | +0.019 |
Token | . |
Feature activation | +0.000 |
Token | Entertainment |
Feature activation | +0.000 |
Token | bad |
Feature activation | -0.016 |
Token | drivers |
Feature activation | -0.067 |
Token | . |
Feature activation | -0.221 |
Token | As |
Feature activation | +0.270 |
Token | the |
Feature activation | -0.054 |
Token | world |
Feature activation | +1.432 |
Token | prepares |
Feature activation | -0.024 |
Token | for |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | coming |
Feature activation | +0.000 |
Token | future |
Feature activation | +0.000 |
Token | supporters |
Feature activation | -0.058 |
Top resid features:
|
Token | say |
Feature activation | -0.086 |
Top resid features:
|
Token | will |
Feature activation | -0.068 |
Top resid features:
|
Token | keep |
Feature activation | -0.051 |
Top resid features:
|
Token | the |
Feature activation | -0.039 |
Top resid features:
|
Token | world |
Feature activation | +1.812 |
Top resid features:
|
Token | safe |
Feature activation | -0.133 |
Top resid features:
|
Token | from |
Feature activation | +0.000 |
Top resid features:
|
Token | Iran |
Feature activation | +0.000 |
Top resid features:
|
Token | 's |
Feature activation | +0.000 |
Top resid features:
|
Token | nuclear |
Feature activation | +0.000 |
Top resid features:
|
Token | film |
Feature activation | +0.000 |
Token | industry |
Feature activation | +0.000 |
Token | ? |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.478 |
Token | truly |
Feature activation | +1.032 |
Token | changed |
Feature activation | +1.005 |
Token | . |
Feature activation | +0.456 |
Token | Entertainment |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | UK |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Unless |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | sees |
Feature activation | +1.509 |
Token | a |
Feature activation | +0.703 |
Token | second |
Feature activation | +0.103 |
Token | green |
Feature activation | +0.000 |
Token | revolution |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | ! |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.573 |
Token | gone |
Feature activation | +1.156 |
Token | c |
Feature activation | +0.517 |
Token | uck |
Feature activation | +0.000 |
Token | oo |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.043 |
Token | is |
Feature activation | +1.543 |
Token | grounded |
Feature activation | +1.217 |
Token | upon |
Feature activation | +0.000 |
Token | suffering |
Feature activation | +0.097 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | As |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | continues |
Feature activation | +1.345 |
Token | warming |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | warming |
Feature activation | +0.000 |
Token | tends |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | 15 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | saw |
Feature activation | +1.325 |
Token | Ferguson |
Feature activation | +0.344 |
Token | Police |
Feature activation | +0.000 |
Token | Chief |
Feature activation | +0.000 |
Token | Thomas |
Feature activation | +0.000 |
Token | Jackson |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | ) |
Feature activation | +0.000 |
Token | -- |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.154 |
Token | risks |
Feature activation | +1.208 |
Token | disastrous |
Feature activation | +0.357 |
Token | income |
Feature activation | +0.000 |
Token | drops |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | ecological |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | While |
Feature activation | +0.000 |
Token | yesterday |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | was |
Feature activation | +1.150 |
Token | o |
Feature activation | +0.400 |
Token | gling |
Feature activation | +0.142 |
Token | over |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | iPhone |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | / |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.133 |
Token | spinning |
Feature activation | +0.807 |
Token | slower |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | my |
Feature activation | +0.000 |
Token | mind |
Feature activation | +0.000 |
Token | India |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | World |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +1.161 |
Token | Ļ |
Feature activation | +0.638 |
Token | s |
Feature activation | +0.000 |
Token | most |
Feature activation | +0.000 |
Token | dreaded |
Feature activation | +0.000 |
Token | terrorist |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.043 |
Token | is |
Feature activation | +1.543 |
Token | grounded |
Feature activation | +1.217 |
Token | upon |
Feature activation | +0.000 |
Token | suffering |
Feature activation | +0.097 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | Still |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | neither |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.043 |
Token | performances |
Feature activation | +0.953 |
Token | hinted |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | blockbuster |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | ago |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | tell |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | we |
Feature activation | +0.952 |
Token | need |
Feature activation | +0.393 |
Token | your |
Feature activation | +0.319 |
Token | capital |
Feature activation | +0.011 |
Token | , |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | believe |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.045 |
Token | real |
Feature activation | +0.821 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | they |
Feature activation | +0.000 |
Token | absolutely |
Feature activation | +0.000 |
Token | / |
Feature activation | +0.000 |
Token | Jason |
Feature activation | +0.000 |
Token | Reed |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +1.037 |
Token | no |
Feature activation | +0.902 |
Token | crystal |
Feature activation | +0.000 |
Token | ball |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | see |
Feature activation | +0.000 |
Token | drivers |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | As |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | prepares |
Feature activation | +1.003 |
Token | for |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | coming |
Feature activation | +0.000 |
Token | future |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | look |
Feature activation | +0.000 |
Token | upon |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.122 |
Token | that |
Feature activation | +0.593 |
Token | has |
Feature activation | +0.854 |
Token | benefited |
Feature activation | +0.495 |
Token | enormously |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | international |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.183 |
Token | is |
Feature activation | +0.959 |
Token | divided |
Feature activation | +0.883 |
Token | into |
Feature activation | +0.000 |
Token | regions |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | each |
Feature activation | +0.000 |
Token | town |
Feature activation | +0.000 |
Token | 1970 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.239 |
Token | had |
Feature activation | +0.796 |
Token | already |
Feature activation | +0.199 |
Token | become |
Feature activation | +0.065 |
Token | compl |
Feature activation | +0.000 |
Token | acent |
Feature activation | +0.000 |
Token | about |
Feature activation | +0.000 |
Token | believe |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.045 |
Token | real |
Feature activation | +0.821 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | they |
Feature activation | +0.000 |
Token | absolutely |
Feature activation | +0.000 |
Token | help |
Feature activation | +0.000 |
Token | TR |
Feature activation | +0.000 |
Token | ON |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.874 |
Token | demanded |
Feature activation | +0.164 |
Token | that |
Feature activation | +0.000 |
Token | female |
Feature activation | +0.000 |
Token | hero |
Feature activation | +0.000 |
Token | ines |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Unless |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | sees |
Feature activation | +1.509 |
Token | a |
Feature activation | +0.703 |
Token | second |
Feature activation | +0.103 |
Token | green |
Feature activation | +0.000 |
Token | revolution |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | some |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | nation |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | forward |
Feature activation | +0.675 |
Token | . |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | believe |
Feature activation | +0.000 |
Token | Mitt |
Feature activation | +0.000 |
Token | Romney |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | are |
Feature activation | +0.000 |
Token | making |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.692 |
Token | better |
Feature activation | +0.886 |
Token | place |
Feature activation | +0.903 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | i |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.591 |
Token | his |
Feature activation | +0.775 |
Token | feet |
Feature activation | +0.284 |
Token | ," |
Feature activation | +0.000 |
Token | S |
Feature activation | +0.000 |
Token | oun |
Feature activation | +0.000 |
Token | ess |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | talking |
Feature activation | +0.679 |
Token | dinosaurs |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | restricted |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | largely |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.780 |
Token | Ļ |
Feature activation | +0.559 |
Token | s |
Feature activation | +0.000 |
Token | gone |
Feature activation | +0.000 |
Token | crazy |
Feature activation | +0.114 |
Token | ! |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | rem |
Feature activation | +0.000 |
Token | ake |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.109 |
Token | our |
Feature activation | +0.549 |
Token | image |
Feature activation | +0.293 |
Token | ." |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | On |
Feature activation | +0.000 |
Token | we |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | or |
Feature activation | +0.501 |
Token | not |
Feature activation | +0.658 |
Token | going |
Feature activation | +0.389 |
Token | forward |
Feature activation | +0.883 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ASH |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | earth |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.214 |
Token | experienced |
Feature activation | +0.517 |
Token | much |
Feature activation | +0.000 |
Token | higher |
Feature activation | +0.000 |
Token | carbon |
Feature activation | +0.000 |
Token | dioxide |
Feature activation | +0.000 |
Token | levels |
Feature activation | +0.000 |
Token | upon |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.122 |
Token | that |
Feature activation | +0.593 |
Token | has |
Feature activation | +0.854 |
Token | benefited |
Feature activation | +0.495 |
Token | enormously |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | international |
Feature activation | +0.000 |
Token | order |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | t |
Feature activation | +0.000 |
Token | think |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | still |
Feature activation | +0.398 |
Token | exists |
Feature activation | +0.600 |
Token | / |
Feature activation | +0.000 |
Token | Only |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | room |
Feature activation | +0.000 |
Token | ; |
Feature activation | +0.000 |
Token | print |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | Hello |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | "; |
Feature activation | +0.356 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Per |
Feature activation | +0.000 |
Token | l |
Feature activation | +0.000 |
Token | scripts |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | eyes |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.391 |
Token | be |
Feature activation | +0.102 |
Token | following |
Feature activation | +0.135 |
Token | our |
Feature activation | +0.000 |
Token | leadership |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | not |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | sh |
Feature activation | +0.326 |
Token | attering |
Feature activation | +0.446 |
Token | revelation |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | if |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | see |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.193 |
Token | it |
Feature activation | +0.356 |
Token | is |
Feature activation | +0.084 |
Token | : |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | imper |
Feature activation | +0.000 |
Token | manent |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | automotive |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | needed |
Feature activation | +0.236 |
Token | a |
Feature activation | +0.232 |
Token | change |
Feature activation | +0.288 |
Token | and |
Feature activation | +0.000 |
Token | Tesla |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | moving |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | Our |
Feature activation | +0.000 |
Token | country |
Feature activation | +0.000 |
Token | deserves |
Feature activation | +0.159 |
Token | better |
Feature activation | +0.000 |
Token | ." |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Trump |
Feature activation | +0.000 |
Token | became |
Feature activation | +0.000 |
Token | one |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.265 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | wealthiest |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | most |
Feature activation | +0.000 |
Token | bring |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | whole |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.192 |
Token | all |
Feature activation | +0.007 |
Token | of |
Feature activation | +0.000 |
Token | its |
Feature activation | +0.000 |
Token | people |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | state |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | world |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.161 |
Token | showing |
Feature activation | +0.512 |
Token | some |
Feature activation | +0.000 |
Token | eerie |
Feature activation | +0.000 |
Token | similarities |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | cognitive |
Feature activation | +0.000 |
Token | performance |
Feature activation | +0.000 |
Token | âĢĵ |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | bit |
Feature activation | +0.000 |
Token | like |
Feature activation | +0.000 |
Token | leveraging |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | large |
Feature activation | +0.000 |
Token | study |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | body |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Two |
Feature activation | +0.000 |
Token | Rutgers |
Feature activation | +0.000 |
Token | students |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | been |
Feature activation | +0.000 |
Token | charged |
Feature activation | +0.000 |
Token | Delhi |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | Tuesday |
Feature activation | +0.000 |
Token | ." |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | DG |
Feature activation | +0.000 |
Token | CA |
Feature activation | +0.000 |
Token | grounded |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | pilot |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | election |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | November |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | do |
Feature activation | +0.000 |
Token | extraction |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | those |
Feature activation | +0.000 |
Token | same |
Feature activation | +0.000 |
Token | lands |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | architects |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | able |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | put |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | in |
Feature activation | +2.365 |
Token | contact |
Feature activation | +1.839 |
Token | with |
Feature activation | +0.000 |
Token | either |
Feature activation | +0.000 |
Token | source |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | last |
Feature activation | +0.000 |
Token | month |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.673 |
Token | said |
Feature activation | +2.168 |
Token | the |
Feature activation | +1.305 |
Token | Obama |
Feature activation | +0.670 |
Token | administration |
Feature activation | +0.010 |
Token | was |
Feature activation | +0.000 |
Token | alarmed |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | [ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.559 |
Token | , |
Feature activation | +2.139 |
Token | h |
Feature activation | +1.013 |
Token | / |
Feature activation | +0.624 |
Token | t |
Feature activation | +0.000 |
Token | CBS |
Feature activation | +0.000 |
Token | Sports |
Feature activation | +0.000 |
Token | full |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.359 |
Token | and |
Feature activation | +2.101 |
Token | The |
Feature activation | +1.584 |
Token | Telegraph |
Feature activation | +0.855 |
Token | . |
Feature activation | +0.730 |
Token | Ċ |
Feature activation | +0.049 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | aide |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.634 |
Token | the |
Feature activation | +2.099 |
Token | publisher |
Feature activation | +1.553 |
Token | will |
Feature activation | +0.000 |
Token | receive |
Feature activation | +0.000 |
Token | half |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | reporting |
Feature activation | +0.000 |
Token | efforts |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.148 |
Token | also |
Feature activation | +2.096 |
Token | has |
Feature activation | +1.416 |
Token | been |
Feature activation | +1.000 |
Token | unable |
Feature activation | +0.348 |
Token | to |
Feature activation | +0.000 |
Token | locate |
Feature activation | +0.455 |
Token | i |
Feature activation | +0.000 |
Token | ME |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.387 |
Token | , |
Feature activation | +2.009 |
Token | maintains |
Feature activation | +0.794 |
Token | that |
Feature activation | +0.495 |
Token | his |
Feature activation | +0.266 |
Token | sourcing |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Trump |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.360 |
Token | that |
Feature activation | +1.944 |
Token | he |
Feature activation | +1.030 |
Token | âĢ |
Feature activation | +0.287 |
Token | ľ |
Feature activation | +0.000 |
Token | would |
Feature activation | +0.000 |
Token | hope |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | published |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.266 |
Token | on |
Feature activation | +1.863 |
Token | 7 |
Feature activation | +1.661 |
Token | October |
Feature activation | +0.498 |
Token | 1915 |
Feature activation | +0.061 |
Token | confirming |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | put |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | in |
Feature activation | +2.365 |
Token | contact |
Feature activation | +1.839 |
Token | with |
Feature activation | +0.000 |
Token | either |
Feature activation | +0.000 |
Token | source |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | or |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | if |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.893 |
Token | âĢ |
Feature activation | +1.838 |
Token | Ļ |
Feature activation | +1.046 |
Token | s |
Feature activation | +0.784 |
Token | reporting |
Feature activation | +1.144 |
Token | is |
Feature activation | +0.000 |
Token | accurate |
Feature activation | +0.000 |
Token | interested |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | criticizing |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.085 |
Token | over |
Feature activation | +1.810 |
Token | this |
Feature activation | +1.060 |
Token | ; |
Feature activation | +0.330 |
Token | stories |
Feature activation | +0.261 |
Token | get |
Feature activation | +0.000 |
Token | rewritten |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | 2019 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.676 |
Token | LLC |
Feature activation | +0.734 |
Token | . |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | Let |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | 2019 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.676 |
Token | LLC |
Feature activation | +0.779 |
Token | . |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.040 |
Token | here |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | published |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.266 |
Token | on |
Feature activation | +1.863 |
Token | 7 |
Feature activation | +1.661 |
Token | October |
Feature activation | +0.498 |
Token | 1915 |
Feature activation | +0.061 |
Token | confirming |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | known |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | 2019 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.614 |
Token | LLC |
Feature activation | +0.660 |
Token | . |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.000 |
Token | here |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.359 |
Token | and |
Feature activation | +2.101 |
Token | The |
Feature activation | +1.584 |
Token | Telegraph |
Feature activation | +0.855 |
Token | . |
Feature activation | +0.730 |
Token | Ċ |
Feature activation | +0.049 |
Token | Ċ |
Feature activation | +0.000 |
Token | Related |
Feature activation | +0.000 |
Token | aide |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.634 |
Token | the |
Feature activation | +2.099 |
Token | publisher |
Feature activation | +1.553 |
Token | will |
Feature activation | +0.000 |
Token | receive |
Feature activation | +0.000 |
Token | half |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Moscow |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | (@ |
Feature activation | +1.356 |
Token | Moscow |
Feature activation | +0.349 |
Token | Times |
Feature activation | +0.000 |
Token | ) |
Feature activation | +1.541 |
Token | May |
Feature activation | +0.794 |
Token | 15 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | 2015 |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | 2019 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.540 |
Token | LLC |
Feature activation | +0.575 |
Token | . |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.000 |
Token | here |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | been |
Feature activation | -0.045 |
Top resid features:
|
Token | able |
Feature activation | -0.021 |
Top resid features:
|
Token | to |
Feature activation | +0.005 |
Top resid features:
|
Token | put |
Feature activation | -0.402 |
Top resid features:
|
Token | the |
Feature activation | +0.357 |
Top resid features:
|
Token | Times |
Feature activation | +4.012 |
Top resid features:
|
Token | in |
Feature activation | +0.145 |
Top resid features:
|
Token | contact |
Feature activation | +0.000 |
Top resid features:
|
Token | with |
Feature activation | +0.000 |
Top resid features:
|
Token | either |
Feature activation | +0.000 |
Top resid features:
|
Token | source |
Feature activation | +0.000 |
Top resid features:
|
Token | Congress |
Feature activation | -0.006 |
Top resid features:
|
Token | last |
Feature activation | +0.033 |
Top resid features:
|
Token | month |
Feature activation | -0.034 |
Top resid features:
|
Token | , |
Feature activation | +0.210 |
Top resid features:
|
Token | the |
Feature activation | +0.184 |
Top resid features:
|
Token | Times |
Feature activation | +3.091 |
Top resid features:
|
Token | said |
Feature activation | +0.048 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | Obama |
Feature activation | +0.000 |
Top resid features:
|
Token | administration |
Feature activation | +0.000 |
Top resid features:
|
Token | was |
Feature activation | +0.000 |
Top resid features:
|
Token | ." |
Feature activation | +0.051 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.019 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.027 |
Top resid features:
|
Token | [ |
Feature activation | +0.366 |
Top resid features:
|
Token | The |
Feature activation | +0.079 |
Top resid features:
|
Token | Times |
Feature activation | +3.474 |
Top resid features:
|
Token | , |
Feature activation | -0.024 |
Top resid features:
|
Token | h |
Feature activation | +0.000 |
Top resid features:
|
Token | / |
Feature activation | +0.000 |
Top resid features:
|
Token | t |
Feature activation | +0.000 |
Top resid features:
|
Token | CBS |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.032 |
Top resid features:
|
Token | full |
Feature activation | -0.072 |
Top resid features:
|
Token | story |
Feature activation | +0.059 |
Top resid features:
|
Token | at |
Feature activation | +0.141 |
Top resid features:
|
Token | The |
Feature activation | +0.202 |
Top resid features:
|
Token | Times |
Feature activation | +3.375 |
Top resid features:
|
Token | and |
Feature activation | +0.022 |
Top resid features:
|
Token | The |
Feature activation | +0.000 |
Top resid features:
|
Token | Telegraph |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.108 |
Top resid features:
|
Token | The |
Feature activation | -0.022 |
Top resid features:
|
Token | aide |
Feature activation | +0.065 |
Top resid features:
|
Token | told |
Feature activation | +0.005 |
Top resid features:
|
Token | the |
Feature activation | +0.080 |
Top resid features:
|
Token | Times |
Feature activation | +3.213 |
Top resid features:
|
Token | the |
Feature activation | +0.297 |
Top resid features:
|
Token | publisher |
Feature activation | +0.000 |
Top resid features:
|
Token | will |
Feature activation | +0.000 |
Top resid features:
|
Token | receive |
Feature activation | +0.000 |
Top resid features:
|
Token | half |
Feature activation | +0.000 |
Top resid features:
|
Token | extensive |
Feature activation | -0.059 |
Top resid features:
|
Token | reporting |
Feature activation | -0.061 |
Top resid features:
|
Token | efforts |
Feature activation | -0.131 |
Top resid features:
|
Token | , |
Feature activation | +0.226 |
Top resid features:
|
Token | The |
Feature activation | +0.169 |
Top resid features:
|
Token | Times |
Feature activation | +3.457 |
Top resid features:
|
Token | also |
Feature activation | +0.133 |
Top resid features:
|
Token | has |
Feature activation | +0.000 |
Top resid features:
|
Token | been |
Feature activation | +0.000 |
Top resid features:
|
Token | unable |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | by |
Feature activation | +0.021 |
Top resid features:
|
Token | i |
Feature activation | +0.115 |
Top resid features:
|
Token | ME |
Feature activation | +0.067 |
Top resid features:
|
Token | and |
Feature activation | +0.132 |
Top resid features:
|
Token | the |
Feature activation | +0.337 |
Top resid features:
|
Token | Times |
Feature activation | +2.915 |
Top resid features:
|
Token | , |
Feature activation | +0.095 |
Top resid features:
|
Token | maintains |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | his |
Feature activation | +0.000 |
Top resid features:
|
Token | sourcing |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.013 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.017 |
Top resid features:
|
Token | Trump |
Feature activation | -0.036 |
Top resid features:
|
Token | told |
Feature activation | -0.163 |
Top resid features:
|
Token | the |
Feature activation | +0.257 |
Top resid features:
|
Token | Times |
Feature activation | +3.169 |
Top resid features:
|
Token | that |
Feature activation | +0.332 |
Top resid features:
|
Token | he |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | ľ |
Feature activation | +0.000 |
Top resid features:
|
Token | would |
Feature activation | +0.000 |
Top resid features:
|
Token | notice |
Feature activation | +0.000 |
Top resid features:
|
Token | was |
Feature activation | +0.043 |
Top resid features:
|
Token | published |
Feature activation | +0.033 |
Top resid features:
|
Token | in |
Feature activation | +0.205 |
Top resid features:
|
Token | The |
Feature activation | +0.189 |
Top resid features:
|
Token | Times |
Feature activation | +2.984 |
Top resid features:
|
Token | on |
Feature activation | +0.102 |
Top resid features:
|
Token | 7 |
Feature activation | +0.000 |
Top resid features:
|
Token | October |
Feature activation | +0.000 |
Top resid features:
|
Token | 1915 |
Feature activation | +0.000 |
Top resid features:
|
Token | confirming |
Feature activation | +0.000 |
Top resid features:
|
Token | been |
Feature activation | -0.003 |
Top resid features:
|
Token | able |
Feature activation | -0.025 |
Top resid features:
|
Token | to |
Feature activation | +0.017 |
Top resid features:
|
Token | put |
Feature activation | -0.224 |
Top resid features:
|
Token | the |
Feature activation | +0.196 |
Top resid features:
|
Token | Times |
Feature activation | +3.168 |
Top resid features:
|
Token | in |
Feature activation | +0.561 |
Top resid features:
|
Token | contact |
Feature activation | -0.067 |
Top resid features:
|
Token | with |
Feature activation | +0.000 |
Top resid features:
|
Token | either |
Feature activation | +0.000 |
Top resid features:
|
Token | source |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.003 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.001 |
Top resid features:
|
Token | But |
Feature activation | -0.088 |
Top resid features:
|
Token | if |
Feature activation | +0.257 |
Top resid features:
|
Token | the |
Feature activation | +0.321 |
Top resid features:
|
Token | Times |
Feature activation | +3.076 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.147 |
Top resid features:
|
Token | Ļ |
Feature activation | +0.000 |
Top resid features:
|
Token | s |
Feature activation | +0.000 |
Top resid features:
|
Token | reporting |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | +0.000 |
Top resid features:
|
Token | particularly |
Feature activation | -0.031 |
Top resid features:
|
Token | interested |
Feature activation | -0.057 |
Top resid features:
|
Token | in |
Feature activation | +0.034 |
Top resid features:
|
Token | criticizing |
Feature activation | +0.341 |
Top resid features:
|
Token | the |
Feature activation | +0.301 |
Top resid features:
|
Token | Times |
Feature activation | +2.739 |
Top resid features:
|
Token | over |
Feature activation | +0.054 |
Top resid features:
|
Token | this |
Feature activation | +0.000 |
Top resid features:
|
Token | ; |
Feature activation | +0.000 |
Top resid features:
|
Token | stories |
Feature activation | +0.000 |
Top resid features:
|
Token | get |
Feature activation | +0.000 |
Top resid features:
|
Token | Copyright |
Feature activation | -0.129 |
Top resid features:
|
Token | © |
Feature activation | +0.097 |
Top resid features:
|
Token | 2019 |
Feature activation | +0.038 |
Top resid features:
|
Token | The |
Feature activation | +0.187 |
Top resid features:
|
Token | Washington |
Feature activation | +0.150 |
Top resid features:
|
Token | Times |
Feature activation | +2.877 |
Top resid features:
|
Token | , |
Feature activation | +0.129 |
Top resid features:
|
Token | LLC |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | +0.000 |
Top resid features:
|
Token | Let |
Feature activation | +0.000 |
Top resid features:
|
Token | Copyright |
Feature activation | -0.107 |
Top resid features:
|
Token | © |
Feature activation | +0.127 |
Top resid features:
|
Token | 2019 |
Feature activation | +0.060 |
Top resid features:
|
Token | The |
Feature activation | +0.231 |
Top resid features:
|
Token | Washington |
Feature activation | +0.118 |
Top resid features:
|
Token | Times |
Feature activation | +2.853 |
Top resid features:
|
Token | , |
Feature activation | +0.125 |
Top resid features:
|
Token | LLC |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Click |
Feature activation | +0.000 |
Top resid features:
|
Token | here |
Feature activation | +0.000 |
Top resid features:
|
Token | notice |
Feature activation | -0.010 |
Top resid features:
|
Token | was |
Feature activation | +0.013 |
Top resid features:
|
Token | published |
Feature activation | -0.045 |
Top resid features:
|
Token | in |
Feature activation | +0.129 |
Top resid features:
|
Token | The |
Feature activation | +0.081 |
Top resid features:
|
Token | Times |
Feature activation | +2.615 |
Top resid features:
|
Token | on |
Feature activation | +0.560 |
Top resid features:
|
Token | 7 |
Feature activation | +0.051 |
Top resid features:
|
Token | October |
Feature activation | +0.000 |
Top resid features:
|
Token | 1915 |
Feature activation | +0.000 |
Top resid features:
|
Token | confirming |
Feature activation | +0.000 |
Top resid features:
|
Token | Copyright |
Feature activation | -0.099 |
Top resid features:
|
Token | © |
Feature activation | +0.071 |
Top resid features:
|
Token | 2019 |
Feature activation | +0.062 |
Top resid features:
|
Token | The |
Feature activation | +0.200 |
Top resid features:
|
Token | Washington |
Feature activation | +0.143 |
Top resid features:
|
Token | Times |
Feature activation | +2.844 |
Top resid features:
|
Token | , |
Feature activation | +0.148 |
Top resid features:
|
Token | LLC |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Click |
Feature activation | +0.000 |
Top resid features:
|
Token | here |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.005 |
Top resid features:
|
Token | full |
Feature activation | -0.072 |
Top resid features:
|
Token | story |
Feature activation | +0.059 |
Top resid features:
|
Token | at |
Feature activation | +0.083 |
Top resid features:
|
Token | The |
Feature activation | -0.002 |
Top resid features:
|
Token | Times |
Feature activation | +2.665 |
Top resid features:
|
Token | and |
Feature activation | +0.381 |
Top resid features:
|
Token | The |
Feature activation | +0.138 |
Top resid features:
|
Token | Telegraph |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.088 |
Top resid features:
|
Token | The |
Feature activation | -0.013 |
Top resid features:
|
Token | aide |
Feature activation | +0.070 |
Top resid features:
|
Token | told |
Feature activation | +0.093 |
Top resid features:
|
Token | the |
Feature activation | +0.157 |
Top resid features:
|
Token | Times |
Feature activation | +2.151 |
Top resid features:
|
Token | the |
Feature activation | +0.597 |
Top resid features:
|
Token | publisher |
Feature activation | +0.171 |
Top resid features:
|
Token | will |
Feature activation | +0.000 |
Top resid features:
|
Token | receive |
Feature activation | +0.000 |
Top resid features:
|
Token | half |
Feature activation | +0.000 |
Top resid features:
|
Token | The |
Feature activation | +0.006 |
Top resid features:
|
Token | Moscow |
Feature activation | +0.014 |
Top resid features:
|
Token | Times |
Feature activation | +0.589 |
Top resid features:
|
Token | (@ |
Feature activation | +0.618 |
Top resid features:
|
Token | Moscow |
Feature activation | +0.049 |
Top resid features:
|
Token | Times |
Feature activation | +1.716 |
Top resid features:
|
Token | ) |
Feature activation | +0.280 |
Top resid features:
|
Token | May |
Feature activation | +0.000 |
Top resid features:
|
Token | 15 |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | 2015 |
Feature activation | +0.000 |
Top resid features:
|
Token | Copyright |
Feature activation | -0.150 |
Top resid features:
|
Token | © |
Feature activation | +0.113 |
Top resid features:
|
Token | 2019 |
Feature activation | +0.029 |
Top resid features:
|
Token | The |
Feature activation | +0.166 |
Top resid features:
|
Token | Washington |
Feature activation | +0.056 |
Top resid features:
|
Token | Times |
Feature activation | +2.927 |
Top resid features:
|
Token | , |
Feature activation | +0.144 |
Top resid features:
|
Token | LLC |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Click |
Feature activation | +0.000 |
Top resid features:
|
Token | here |
Feature activation | +0.000 |
Top resid features:
|
Token | able |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | put |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | in |
Feature activation | +2.365 |
Token | contact |
Feature activation | +1.839 |
Token | with |
Feature activation | +0.000 |
Token | either |
Feature activation | +0.000 |
Token | source |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | aide |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.634 |
Token | the |
Feature activation | +2.099 |
Token | publisher |
Feature activation | +1.553 |
Token | will |
Feature activation | +0.000 |
Token | receive |
Feature activation | +0.000 |
Token | half |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | [ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.559 |
Token | , |
Feature activation | +2.139 |
Token | h |
Feature activation | +1.013 |
Token | / |
Feature activation | +0.624 |
Token | t |
Feature activation | +0.000 |
Token | CBS |
Feature activation | +0.000 |
Token | Sports |
Feature activation | +0.000 |
Token | last |
Feature activation | +0.000 |
Token | month |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.673 |
Token | said |
Feature activation | +2.168 |
Token | the |
Feature activation | +1.305 |
Token | Obama |
Feature activation | +0.670 |
Token | administration |
Feature activation | +0.010 |
Token | was |
Feature activation | +0.000 |
Token | alarmed |
Feature activation | +0.000 |
Token | reporting |
Feature activation | +0.000 |
Token | efforts |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.148 |
Token | also |
Feature activation | +2.096 |
Token | has |
Feature activation | +1.416 |
Token | been |
Feature activation | +1.000 |
Token | unable |
Feature activation | +0.348 |
Token | to |
Feature activation | +0.000 |
Token | locate |
Feature activation | +0.455 |
Token | full |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.359 |
Token | and |
Feature activation | +2.101 |
Token | The |
Feature activation | +1.584 |
Token | Telegraph |
Feature activation | +0.855 |
Token | . |
Feature activation | +0.730 |
Token | Ċ |
Feature activation | +0.049 |
Token | Ċ |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | published |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.266 |
Token | on |
Feature activation | +1.863 |
Token | 7 |
Feature activation | +1.661 |
Token | October |
Feature activation | +0.498 |
Token | 1915 |
Feature activation | +0.061 |
Token | confirming |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | But |
Feature activation | +0.000 |
Token | if |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.893 |
Token | âĢ |
Feature activation | +1.838 |
Token | Ļ |
Feature activation | +1.046 |
Token | s |
Feature activation | +0.784 |
Token | reporting |
Feature activation | +1.144 |
Token | is |
Feature activation | +0.000 |
Token | accurate |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | put |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | in |
Feature activation | +2.365 |
Token | contact |
Feature activation | +1.839 |
Token | with |
Feature activation | +0.000 |
Token | either |
Feature activation | +0.000 |
Token | source |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | or |
Feature activation | +0.000 |
Token | i |
Feature activation | +0.000 |
Token | ME |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.387 |
Token | , |
Feature activation | +2.009 |
Token | maintains |
Feature activation | +0.794 |
Token | that |
Feature activation | +0.495 |
Token | his |
Feature activation | +0.266 |
Token | sourcing |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Trump |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.360 |
Token | that |
Feature activation | +1.944 |
Token | he |
Feature activation | +1.030 |
Token | âĢ |
Feature activation | +0.287 |
Token | ľ |
Feature activation | +0.000 |
Token | would |
Feature activation | +0.000 |
Token | hope |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | 2019 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.614 |
Token | LLC |
Feature activation | +0.660 |
Token | . |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.000 |
Token | here |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | Moscow |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | (@ |
Feature activation | +1.356 |
Token | Moscow |
Feature activation | +0.349 |
Token | Times |
Feature activation | +0.000 |
Token | ) |
Feature activation | +1.541 |
Token | May |
Feature activation | +0.794 |
Token | 15 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | 2015 |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | 2019 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.676 |
Token | LLC |
Feature activation | +0.779 |
Token | . |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.040 |
Token | here |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | 2019 |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.540 |
Token | LLC |
Feature activation | +0.575 |
Token | . |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.000 |
Token | here |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | aide |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.634 |
Token | the |
Feature activation | +2.099 |
Token | publisher |
Feature activation | +1.553 |
Token | will |
Feature activation | +0.000 |
Token | receive |
Feature activation | +0.000 |
Token | half |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | ough |
Feature activation | +0.000 |
Token | ton |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.053 |
Token | he |
Feature activation | +1.389 |
Token | did |
Feature activation | +0.576 |
Token | not |
Feature activation | +0.106 |
Token | want |
Feature activation | +0.154 |
Token | to |
Feature activation | +0.151 |
Token | go |
Feature activation | +0.000 |
Token | Li |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Global |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | on |
Feature activation | +1.281 |
Token | Wednesday |
Feature activation | +0.504 |
Token | . |
Feature activation | +0.119 |
Token | Ex |
Feature activation | +0.000 |
Token | ternally |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | efforts |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.148 |
Token | also |
Feature activation | +2.096 |
Token | has |
Feature activation | +1.416 |
Token | been |
Feature activation | +1.000 |
Token | unable |
Feature activation | +0.348 |
Token | to |
Feature activation | +0.000 |
Token | locate |
Feature activation | +0.455 |
Token | or |
Feature activation | +0.000 |
Token | wrote |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.636 |
Token | of |
Feature activation | +1.009 |
Token | India |
Feature activation | +1.404 |
Token | Friday |
Feature activation | +0.474 |
Token | . |
Feature activation | +0.174 |
Token | Mr |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Kejriwal |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | New |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | : |
Feature activation | +1.417 |
Token | You |
Feature activation | +0.450 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | ve |
Feature activation | +0.000 |
Token | toured |
Feature activation | +0.000 |
Token | According |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Cap |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.244 |
Token | Governor |
Feature activation | +0.115 |
Token | Walker |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | allies |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Seattle |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | reported |
Feature activation | +1.183 |
Token | . |
Feature activation | +0.090 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | © |
Feature activation | +0.000 |
Token | Provided |
Feature activation | +0.000 |
Token | Trump |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.360 |
Token | that |
Feature activation | +1.944 |
Token | he |
Feature activation | +1.030 |
Token | âĢ |
Feature activation | +0.287 |
Token | ľ |
Feature activation | +0.000 |
Token | would |
Feature activation | +0.000 |
Token | hope |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | editors |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | concluded |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +1.023 |
Token | cannot |
Feature activation | +1.019 |
Token | v |
Feature activation | +0.830 |
Token | ouch |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Support |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.671 |
Token | San |
Feature activation | +1.080 |
Token | Diego |
Feature activation | +0.563 |
Token | 's |
Feature activation | +0.000 |
Token | growth |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | New |
Feature activation | +0.000 |
Token | York |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.299 |
Token | , |
Feature activation | +0.836 |
Token | under |
Feature activation | +0.463 |
Token | the |
Feature activation | +0.053 |
Token | headline |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Los |
Feature activation | +0.000 |
Token | Angeles |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.948 |
Token | describes |
Feature activation | +0.922 |
Token | border |
Feature activation | +0.000 |
Token | officers |
Feature activation | +0.000 |
Token | shooting |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | moving |
Feature activation | +0.000 |
Token | ME |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.387 |
Token | , |
Feature activation | +2.009 |
Token | maintains |
Feature activation | +0.794 |
Token | that |
Feature activation | +0.495 |
Token | his |
Feature activation | +0.266 |
Token | sourcing |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | all |
Feature activation | +0.000 |
Token | Kejriwal |
Feature activation | +0.000 |
Token | wrote |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.636 |
Token | of |
Feature activation | +1.009 |
Token | India |
Feature activation | +1.404 |
Token | Friday |
Feature activation | +0.474 |
Token | . |
Feature activation | +0.174 |
Token | Mr |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.359 |
Token | and |
Feature activation | +2.101 |
Token | The |
Feature activation | +1.584 |
Token | Telegraph |
Feature activation | +0.855 |
Token | . |
Feature activation | +0.730 |
Token | Ċ |
Feature activation | +0.049 |
Token | Ċ |
Feature activation | +0.000 |
Token | Related |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | âĢĶ |
Feature activation | +0.725 |
Token | including |
Feature activation | +1.196 |
Token | paying |
Feature activation | +0.740 |
Token | close |
Feature activation | +0.000 |
Token | attention |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | visual |
Feature activation | +0.000 |
Token | integrity |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | New |
Feature activation | +0.000 |
Token | York |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | saying |
Feature activation | +0.538 |
Token | that |
Feature activation | +0.000 |
Token | large |
Feature activation | +0.000 |
Token | segments |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | ton |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.053 |
Token | he |
Feature activation | +1.389 |
Token | did |
Feature activation | +0.576 |
Token | not |
Feature activation | +0.106 |
Token | want |
Feature activation | +0.154 |
Token | to |
Feature activation | +0.151 |
Token | go |
Feature activation | +0.000 |
Token | into |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Support |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.671 |
Token | San |
Feature activation | +1.080 |
Token | Diego |
Feature activation | +0.563 |
Token | 's |
Feature activation | +0.000 |
Token | growth |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | NY |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.506 |
Token | about |
Feature activation | +0.537 |
Token | how |
Feature activation | +0.342 |
Token | the |
Feature activation | +0.117 |
Token | Strauss |
Feature activation | +0.480 |
Token | - |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Sun |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.356 |
Token | ( |
Feature activation | +1.415 |
Token | via |
Feature activation | +0.564 |
Token | SW |
Feature activation | +0.306 |
Token | 7 |
Feature activation | +0.000 |
Token | News |
Feature activation | +0.000 |
Token | ). |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | notice |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | published |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.266 |
Token | on |
Feature activation | +1.863 |
Token | 7 |
Feature activation | +1.661 |
Token | October |
Feature activation | +0.498 |
Token | 1915 |
Feature activation | +0.061 |
Token | confirming |
Feature activation | +0.000 |
Token | investigation |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | found |
Feature activation | +0.781 |
Token | the |
Feature activation | +0.298 |
Token | companies |
Feature activation | +0.128 |
Token | promoted |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | videos |
Feature activation | +0.000 |
Token | posted |
Feature activation | +0.000 |
Token | complex |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Sun |
Feature activation | +0.000 |
Token | Journal |
Feature activation | +0.000 |
Token | reported |
Feature activation | +0.392 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | She |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.085 |
Token | over |
Feature activation | +1.810 |
Token | this |
Feature activation | +1.060 |
Token | ; |
Feature activation | +0.330 |
Token | stories |
Feature activation | +0.261 |
Token | get |
Feature activation | +0.000 |
Token | rewritten |
Feature activation | +0.000 |
Token | all |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | EX |
Feature activation | +0.000 |
Token | âĢĵ |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.000 |
Token | image |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | 3 |
Feature activation | +0.000 |
Token | D |
Feature activation | +0.000 |
Token | model |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | air |
Feature activation | +0.000 |
Token | writes |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | threat |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | nuclear |
Feature activation | +0.000 |
Token | war |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | higher |
Feature activation | +0.000 |
Token | now |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | London |
Feature activation | +0.000 |
Token | collaboration |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | clinical |
Feature activation | +0.000 |
Token | commission |
Feature activation | +0.000 |
Token | ing |
Feature activation | +0.000 |
Token | groups |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | CC |
Feature activation | +0.000 |
Token | G |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | film |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | water |
Feature activation | +0.000 |
Token | color |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | esque |
Feature activation | +0.000 |
Token | color |
Feature activation | +0.000 |
Token | palette |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | she |
Feature activation | +0.000 |
Token | needed |
Feature activation | +0.000 |
Token | help |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | needed |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | be |
Feature activation | +0.000 |
Token | taken |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.919 |
Token | reported |
Feature activation | +2.510 |
Token | that |
Feature activation | +1.597 |
Token | British |
Feature activation | +0.449 |
Token | and |
Feature activation | +0.000 |
Token | US |
Feature activation | +0.000 |
Token | intelligence |
Feature activation | +0.000 |
Token | their |
Feature activation | +0.000 |
Token | approval |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.544 |
Token | called |
Feature activation | +2.031 |
Token | the |
Feature activation | +1.443 |
Token | deal |
Feature activation | +0.780 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | Oxford |
Feature activation | +0.000 |
Token | University |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.048 |
Token | reports |
Feature activation | +1.945 |
Token | . |
Feature activation | +0.208 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | People |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | Syria |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.448 |
Token | reported |
Feature activation | +1.930 |
Token | . |
Feature activation | +0.598 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | During |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | FT |
Feature activation | +0.925 |
Token | , |
Feature activation | +1.718 |
Token | citing |
Feature activation | +1.929 |
Token | anonymous |
Feature activation | +0.700 |
Token | officials |
Feature activation | +0.202 |
Token | , |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Davis |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.943 |
Token | Express |
Feature activation | +1.730 |
Token | has |
Feature activation | +1.926 |
Token | come |
Feature activation | +1.295 |
Token | across |
Feature activation | +0.572 |
Token | some |
Feature activation | +0.000 |
Token | very |
Feature activation | +0.000 |
Token | valuable |
Feature activation | +0.000 |
Token | Speaking |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Daily |
Feature activation | +0.118 |
Token | Telegraph |
Feature activation | +0.806 |
Token | , |
Feature activation | +1.815 |
Token | Amanda |
Feature activation | +1.114 |
Token | Ross |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | who |
Feature activation | +0.000 |
Token | runs |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.286 |
Token | contacted |
Feature activation | +1.809 |
Token | more |
Feature activation | +0.727 |
Token | than |
Feature activation | +0.503 |
Token | a |
Feature activation | +0.050 |
Token | dozen |
Feature activation | +0.000 |
Token | people |
Feature activation | +0.000 |
Token | major |
Feature activation | +0.000 |
Token | operation |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.217 |
Token | reported |
Feature activation | +1.762 |
Token | that |
Feature activation | +0.919 |
Token | at |
Feature activation | +0.438 |
Token | least |
Feature activation | +0.000 |
Token | eight |
Feature activation | +0.000 |
Token | police |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.943 |
Token | Express |
Feature activation | +1.730 |
Token | has |
Feature activation | +1.926 |
Token | come |
Feature activation | +1.295 |
Token | across |
Feature activation | +0.572 |
Token | some |
Feature activation | +0.000 |
Token | very |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | Maryland |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.572 |
Token | reported |
Feature activation | +1.727 |
Token | . |
Feature activation | +0.636 |
Token | That |
Feature activation | +0.019 |
Token | led |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | FT |
Feature activation | +0.925 |
Token | , |
Feature activation | +1.718 |
Token | citing |
Feature activation | +1.929 |
Token | anonymous |
Feature activation | +0.700 |
Token | officials |
Feature activation | +0.202 |
Token | , |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | shared |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.496 |
Token | , |
Feature activation | +1.717 |
Token | urges |
Feature activation | +0.807 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | introduce |
Feature activation | +0.000 |
Token | oc |
Feature activation | +0.000 |
Token | 8 |
Feature activation | +0.000 |
Token | âĢĶ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Telegraph |
Feature activation | +0.959 |
Token | (@ |
Feature activation | +1.600 |
Token | Te |
Feature activation | +0.302 |
Token | legraph |
Feature activation | +0.059 |
Token | ) |
Feature activation | +0.706 |
Token | August |
Feature activation | +0.238 |
Token | 4 |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.919 |
Token | reported |
Feature activation | +2.510 |
Token | that |
Feature activation | +1.597 |
Token | British |
Feature activation | +0.449 |
Token | and |
Feature activation | +0.000 |
Token | US |
Feature activation | +0.000 |
Token | intelligence |
Feature activation | +0.000 |
Token | agencies |
Feature activation | +0.000 |
Token | regarding |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +1.562 |
Token | Ŀ |
Feature activation | +0.820 |
Token | âĢĵ |
Feature activation | +0.140 |
Token | and |
Feature activation | +0.476 |
Token | he |
Feature activation | +0.171 |
Token | clearly |
Feature activation | +0.000 |
Token | Russia |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.142 |
Token | he |
Feature activation | +1.556 |
Token | would |
Feature activation | +0.627 |
Token | be |
Feature activation | +0.484 |
Token | âĢ |
Feature activation | +0.423 |
Token | ľ |
Feature activation | +0.000 |
Token | more |
Feature activation | +0.062 |
Token | Channel |
Feature activation | +0.000 |
Token | 4 |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.598 |
Token | . |
Feature activation | +1.525 |
Token | Sophie |
Feature activation | +1.127 |
Token | Walker |
Feature activation | +0.000 |
Token | called |
Feature activation | +0.000 |
Token | me |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.459 |
Token | watched |
Feature activation | +1.497 |
Token | as |
Feature activation | +0.218 |
Token | Lock |
Feature activation | +0.542 |
Token | ett |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | covered |
Feature activation | +0.000 |
Token | complex |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Sun |
Feature activation | +0.000 |
Token | Journal |
Feature activation | +0.454 |
Token | reported |
Feature activation | +1.496 |
Token | . |
Feature activation | +0.636 |
Token | Ċ |
Feature activation | +0.059 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | She |
Feature activation | +0.083 |
Token | contractor |
Feature activation | -0.031 |
Top resid features:
|
Token | . |
Feature activation | +0.001 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.029 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.042 |
Top resid features:
|
Token | The |
Feature activation | +0.407 |
Top resid features:
|
Token | Guardian |
Feature activation | +3.655 |
Top resid features:
|
Token | reported |
Feature activation | -0.031 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | British |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | US |
Feature activation | +0.000 |
Top resid features:
|
Token | ed |
Feature activation | -0.015 |
Top resid features:
|
Token | their |
Feature activation | -0.007 |
Top resid features:
|
Token | approval |
Feature activation | -0.002 |
Top resid features:
|
Token | . |
Feature activation | +0.053 |
Top resid features:
|
Token | The |
Feature activation | +0.413 |
Top resid features:
|
Token | Guardian |
Feature activation | +3.157 |
Top resid features:
|
Token | called |
Feature activation | +0.008 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | deal |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | ľ |
Feature activation | +0.000 |
Top resid features:
|
Token | at |
Feature activation | +0.023 |
Top resid features:
|
Token | Oxford |
Feature activation | +0.025 |
Top resid features:
|
Token | University |
Feature activation | -0.021 |
Top resid features:
|
Token | , |
Feature activation | -0.054 |
Top resid features:
|
Token | the |
Feature activation | +0.395 |
Top resid features:
|
Token | Guardian |
Feature activation | +3.121 |
Top resid features:
|
Token | reports |
Feature activation | -0.077 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | " |
Feature activation | +0.000 |
Top resid features:
|
Token | State |
Feature activation | -0.010 |
Top resid features:
|
Token | in |
Feature activation | -0.008 |
Top resid features:
|
Token | Syria |
Feature activation | -0.007 |
Top resid features:
|
Token | , |
Feature activation | +0.031 |
Top resid features:
|
Token | the |
Feature activation | +0.317 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.992 |
Top resid features:
|
Token | reported |
Feature activation | -0.015 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | During |
Feature activation | +0.000 |
Top resid features:
|
Token | affected |
Feature activation | +0.012 |
Top resid features:
|
Token | . |
Feature activation | +0.042 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.010 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.004 |
Top resid features:
|
Token | The |
Feature activation | +0.347 |
Top resid features:
|
Token | FT |
Feature activation | +2.612 |
Top resid features:
|
Token | , |
Feature activation | +0.192 |
Top resid features:
|
Token | citing |
Feature activation | -0.034 |
Top resid features:
|
Token | anonymous |
Feature activation | +0.000 |
Top resid features:
|
Token | officials |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | alt |
Feature activation | -0.004 |
Top resid features:
|
Token | of |
Feature activation | +0.006 |
Top resid features:
|
Token | the |
Feature activation | -0.001 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | +0.029 |
Top resid features:
|
Token | The |
Feature activation | +0.310 |
Top resid features:
|
Token | Guardian |
Feature activation | +1.613 |
Top resid features:
|
Token | Express |
Feature activation | +1.352 |
Top resid features:
|
Token | has |
Feature activation | +0.020 |
Top resid features:
|
Token | come |
Feature activation | +0.000 |
Top resid features:
|
Token | across |
Feature activation | +0.000 |
Top resid features:
|
Token | some |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.065 |
Top resid features:
|
Token | Speaking |
Feature activation | +0.029 |
Top resid features:
|
Token | to |
Feature activation | +0.023 |
Top resid features:
|
Token | the |
Feature activation | +0.209 |
Top resid features:
|
Token | Daily |
Feature activation | +0.793 |
Top resid features:
|
Token | Telegraph |
Feature activation | +1.960 |
Top resid features:
|
Token | , |
Feature activation | +0.111 |
Top resid features:
|
Token | Amanda |
Feature activation | +0.000 |
Top resid features:
|
Token | Ross |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | who |
Feature activation | +0.000 |
Top resid features:
|
Token | atic |
Feature activation | -0.035 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.037 |
Top resid features:
|
Token | Ŀ |
Feature activation | -0.038 |
Top resid features:
|
Token | . |
Feature activation | +0.074 |
Top resid features:
|
Token | The |
Feature activation | +0.321 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.755 |
Top resid features:
|
Token | contacted |
Feature activation | +0.246 |
Top resid features:
|
Token | more |
Feature activation | +0.000 |
Top resid features:
|
Token | than |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | dozen |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | +0.001 |
Top resid features:
|
Token | major |
Feature activation | -0.009 |
Top resid features:
|
Token | operation |
Feature activation | -0.040 |
Top resid features:
|
Token | : |
Feature activation | -0.057 |
Top resid features:
|
Token | the |
Feature activation | +0.293 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.978 |
Top resid features:
|
Token | reported |
Feature activation | -0.049 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | at |
Feature activation | +0.000 |
Top resid features:
|
Token | least |
Feature activation | +0.000 |
Top resid features:
|
Token | eight |
Feature activation | +0.000 |
Top resid features:
|
Token | alt |
Feature activation | +0.005 |
Top resid features:
|
Token | of |
Feature activation | +0.035 |
Top resid features:
|
Token | the |
Feature activation | +0.100 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | +0.126 |
Top resid features:
|
Token | The |
Feature activation | +0.209 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.386 |
Top resid features:
|
Token | Express |
Feature activation | +0.245 |
Top resid features:
|
Token | has |
Feature activation | +0.000 |
Top resid features:
|
Token | come |
Feature activation | +0.000 |
Top resid features:
|
Token | across |
Feature activation | +0.000 |
Top resid features:
|
Token | some |
Feature activation | +0.000 |
Top resid features:
|
Token | University |
Feature activation | +0.025 |
Top resid features:
|
Token | of |
Feature activation | -0.026 |
Top resid features:
|
Token | Maryland |
Feature activation | -0.034 |
Top resid features:
|
Token | , |
Feature activation | +0.003 |
Top resid features:
|
Token | The |
Feature activation | +0.258 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.837 |
Top resid features:
|
Token | reported |
Feature activation | -0.049 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | That |
Feature activation | +0.000 |
Top resid features:
|
Token | led |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | affected |
Feature activation | +0.022 |
Top resid features:
|
Token | . |
Feature activation | +0.029 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.037 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.035 |
Top resid features:
|
Token | The |
Feature activation | +0.460 |
Top resid features:
|
Token | FT |
Feature activation | +2.330 |
Top resid features:
|
Token | , |
Feature activation | +0.090 |
Top resid features:
|
Token | citing |
Feature activation | +0.000 |
Top resid features:
|
Token | anonymous |
Feature activation | +0.000 |
Top resid features:
|
Token | officials |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | Group |
Feature activation | +0.005 |
Top resid features:
|
Token | and |
Feature activation | -0.022 |
Top resid features:
|
Token | shared |
Feature activation | +0.053 |
Top resid features:
|
Token | with |
Feature activation | +0.112 |
Top resid features:
|
Token | the |
Feature activation | +0.254 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.440 |
Top resid features:
|
Token | , |
Feature activation | +0.059 |
Top resid features:
|
Token | urges |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | government |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | 2 |
Feature activation | -0.008 |
Top resid features:
|
Token | oc |
Feature activation | -0.027 |
Top resid features:
|
Token | 8 |
Feature activation | -0.017 |
Top resid features:
|
Token | âĢĶ |
Feature activation | +0.072 |
Top resid features:
|
Token | The |
Feature activation | +0.474 |
Top resid features:
|
Token | Telegraph |
Feature activation | +2.437 |
Top resid features:
|
Token | (@ |
Feature activation | +0.006 |
Top resid features:
|
Token | Te |
Feature activation | +0.000 |
Top resid features:
|
Token | legraph |
Feature activation | +0.000 |
Top resid features:
|
Token | ) |
Feature activation | +0.000 |
Top resid features:
|
Token | August |
Feature activation | +0.000 |
Top resid features:
|
Token | contractor |
Feature activation | -0.029 |
Top resid features:
|
Token | . |
Feature activation | +0.038 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.022 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.031 |
Top resid features:
|
Token | The |
Feature activation | +0.298 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.284 |
Top resid features:
|
Token | reported |
Feature activation | +0.300 |
Top resid features:
|
Token | that |
Feature activation | +0.171 |
Top resid features:
|
Token | British |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | US |
Feature activation | +0.000 |
Top resid features:
|
Token | information |
Feature activation | +0.005 |
Top resid features:
|
Token | regarding |
Feature activation | +0.005 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.015 |
Top resid features:
|
Token | ľ |
Feature activation | -0.085 |
Top resid features:
|
Token | The |
Feature activation | +0.372 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.723 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.005 |
Top resid features:
|
Token | Ŀ |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢĵ |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | he |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | -0.005 |
Top resid features:
|
Token | Russia |
Feature activation | -0.015 |
Top resid features:
|
Token | , |
Feature activation | +0.010 |
Top resid features:
|
Token | told |
Feature activation | +0.001 |
Top resid features:
|
Token | the |
Feature activation | +0.416 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.399 |
Top resid features:
|
Token | he |
Feature activation | +0.120 |
Top resid features:
|
Token | would |
Feature activation | +0.000 |
Top resid features:
|
Token | be |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | ľ |
Feature activation | +0.000 |
Top resid features:
|
Token | ; |
Feature activation | +0.053 |
Top resid features:
|
Token | Channel |
Feature activation | +0.093 |
Top resid features:
|
Token | 4 |
Feature activation | -0.022 |
Top resid features:
|
Token | and |
Feature activation | +0.145 |
Top resid features:
|
Token | The |
Feature activation | +0.295 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.072 |
Top resid features:
|
Token | . |
Feature activation | +0.242 |
Top resid features:
|
Token | Sophie |
Feature activation | +0.000 |
Top resid features:
|
Token | Walker |
Feature activation | +0.000 |
Top resid features:
|
Token | called |
Feature activation | +0.000 |
Top resid features:
|
Token | me |
Feature activation | +0.000 |
Top resid features:
|
Token | afterward |
Feature activation | -0.050 |
Top resid features:
|
Token | . |
Feature activation | +0.033 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.008 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.008 |
Top resid features:
|
Token | The |
Feature activation | +0.245 |
Top resid features:
|
Token | Guardian |
Feature activation | +2.707 |
Top resid features:
|
Token | watched |
Feature activation | +0.081 |
Top resid features:
|
Token | as |
Feature activation | +0.000 |
Top resid features:
|
Token | Lock |
Feature activation | +0.000 |
Top resid features:
|
Token | ett |
Feature activation | +0.000 |
Top resid features:
|
Token | was |
Feature activation | +0.000 |
Top resid features:
|
Token | tourism |
Feature activation | -0.006 |
Top resid features:
|
Token | complex |
Feature activation | -0.044 |
Top resid features:
|
Token | , |
Feature activation | +0.027 |
Top resid features:
|
Token | the |
Feature activation | +0.308 |
Top resid features:
|
Token | Sun |
Feature activation | +0.803 |
Top resid features:
|
Token | Journal |
Feature activation | +1.812 |
Top resid features:
|
Token | reported |
Feature activation | -0.001 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | The |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.919 |
Token | reported |
Feature activation | +2.510 |
Token | that |
Feature activation | +1.597 |
Token | British |
Feature activation | +0.449 |
Token | and |
Feature activation | +0.000 |
Token | US |
Feature activation | +0.000 |
Token | intelligence |
Feature activation | +0.000 |
Token | their |
Feature activation | +0.000 |
Token | approval |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.544 |
Token | called |
Feature activation | +2.031 |
Token | the |
Feature activation | +1.443 |
Token | deal |
Feature activation | +0.780 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | major |
Feature activation | +0.000 |
Token | operation |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.217 |
Token | reported |
Feature activation | +1.762 |
Token | that |
Feature activation | +0.919 |
Token | at |
Feature activation | +0.438 |
Token | least |
Feature activation | +0.000 |
Token | eight |
Feature activation | +0.000 |
Token | police |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.286 |
Token | contacted |
Feature activation | +1.809 |
Token | more |
Feature activation | +0.727 |
Token | than |
Feature activation | +0.503 |
Token | a |
Feature activation | +0.050 |
Token | dozen |
Feature activation | +0.000 |
Token | people |
Feature activation | +0.000 |
Token | Speaking |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Daily |
Feature activation | +0.118 |
Token | Telegraph |
Feature activation | +0.806 |
Token | , |
Feature activation | +1.815 |
Token | Amanda |
Feature activation | +1.114 |
Token | Ross |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | who |
Feature activation | +0.000 |
Token | runs |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.943 |
Token | Express |
Feature activation | +1.730 |
Token | has |
Feature activation | +1.926 |
Token | come |
Feature activation | +1.295 |
Token | across |
Feature activation | +0.572 |
Token | some |
Feature activation | +0.000 |
Token | very |
Feature activation | +0.000 |
Token | valuable |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | Syria |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.448 |
Token | reported |
Feature activation | +1.930 |
Token | . |
Feature activation | +0.598 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | During |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | Russia |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.142 |
Token | he |
Feature activation | +1.556 |
Token | would |
Feature activation | +0.627 |
Token | be |
Feature activation | +0.484 |
Token | âĢ |
Feature activation | +0.423 |
Token | ľ |
Feature activation | +0.000 |
Token | more |
Feature activation | +0.062 |
Token | regarding |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +1.562 |
Token | Ŀ |
Feature activation | +0.820 |
Token | âĢĵ |
Feature activation | +0.140 |
Token | and |
Feature activation | +0.476 |
Token | he |
Feature activation | +0.171 |
Token | clearly |
Feature activation | +0.000 |
Token | oc |
Feature activation | +0.000 |
Token | 8 |
Feature activation | +0.000 |
Token | âĢĶ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Telegraph |
Feature activation | +0.959 |
Token | (@ |
Feature activation | +1.600 |
Token | Te |
Feature activation | +0.302 |
Token | legraph |
Feature activation | +0.059 |
Token | ) |
Feature activation | +0.706 |
Token | August |
Feature activation | +0.238 |
Token | 4 |
Feature activation | +0.000 |
Token | Channel |
Feature activation | +0.000 |
Token | 4 |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.598 |
Token | . |
Feature activation | +1.525 |
Token | Sophie |
Feature activation | +1.127 |
Token | Walker |
Feature activation | +0.000 |
Token | called |
Feature activation | +0.000 |
Token | me |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.943 |
Token | Express |
Feature activation | +1.730 |
Token | has |
Feature activation | +1.926 |
Token | come |
Feature activation | +1.295 |
Token | across |
Feature activation | +0.572 |
Token | some |
Feature activation | +0.000 |
Token | very |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.758 |
Token | has |
Feature activation | +1.422 |
Token | spoken |
Feature activation | +1.081 |
Token | to |
Feature activation | +0.188 |
Token | six |
Feature activation | +0.304 |
Token | key |
Feature activation | +0.000 |
Token | lawmakers |
Feature activation | +0.000 |
Token | approval |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.544 |
Token | called |
Feature activation | +2.031 |
Token | the |
Feature activation | +1.443 |
Token | deal |
Feature activation | +0.780 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | victory |
Feature activation | +0.000 |
Token | downs |
Feature activation | +0.000 |
Token | ides |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.114 |
Token | website |
Feature activation | +1.300 |
Token | reported |
Feature activation | +0.479 |
Token | that |
Feature activation | +0.041 |
Token | armed |
Feature activation | +0.000 |
Token | robbers |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Root |
Feature activation | +0.030 |
Token | reveals |
Feature activation | +1.262 |
Token | that |
Feature activation | +0.524 |
Token | in |
Feature activation | +0.218 |
Token | 2012 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | ," |
Feature activation | +0.000 |
Token | Zucker |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.000 |
Token | in |
Feature activation | +1.438 |
Token | an |
Feature activation | +1.031 |
Token | interview |
Feature activation | +0.357 |
Token | published |
Feature activation | +0.000 |
Token | Sunday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.024 |
Token | anonymous |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Telegraph |
Feature activation | +0.188 |
Token | : |
Feature activation | +1.169 |
Token | ' |
Feature activation | +0.761 |
Token | I |
Feature activation | +0.000 |
Token | know |
Feature activation | +0.000 |
Token | [ |
Feature activation | +0.000 |
Token | W |
Feature activation | +0.000 |
Token | confirmed |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Globe |
Feature activation | +0.364 |
Token | that |
Feature activation | +1.188 |
Token | the |
Feature activation | +1.086 |
Token | government |
Feature activation | +0.335 |
Token | is |
Feature activation | +0.000 |
Token | planning |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | release |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Intercept |
Feature activation | +0.540 |
Token | , |
Feature activation | +1.172 |
Token | which |
Feature activation | +1.108 |
Token | broke |
Feature activation | +0.635 |
Token | the |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Intercept |
Feature activation | +0.540 |
Token | , |
Feature activation | +1.172 |
Token | which |
Feature activation | +1.108 |
Token | broke |
Feature activation | +0.635 |
Token | the |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Post |
Feature activation | +0.339 |
Token | âĢ |
Feature activation | +1.054 |
Token | Ļ |
Feature activation | +1.164 |
Token | s |
Feature activation | +0.700 |
Token | Aaron |
Feature activation | +0.000 |
Token | Blake |
Feature activation | +0.000 |
Token | responds |
Feature activation | +0.000 |
Token | alt |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.943 |
Token | Express |
Feature activation | +1.730 |
Token | has |
Feature activation | +1.926 |
Token | come |
Feature activation | +1.295 |
Token | across |
Feature activation | +0.572 |
Token | some |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +1.562 |
Token | Ŀ |
Feature activation | +0.820 |
Token | âĢĵ |
Feature activation | +0.140 |
Token | and |
Feature activation | +0.476 |
Token | he |
Feature activation | +0.171 |
Token | clearly |
Feature activation | +0.000 |
Token | wants |
Feature activation | +0.000 |
Token | says |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Verge |
Feature activation | +0.641 |
Token | âĢ |
Feature activation | +0.984 |
Token | Ļ |
Feature activation | +0.889 |
Token | s |
Feature activation | +0.968 |
Token | Russell |
Feature activation | +0.162 |
Token | Br |
Feature activation | +0.000 |
Token | andom |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.786 |
Token | Daily |
Feature activation | +0.201 |
Token | Mirror |
Feature activation | +0.446 |
Token | and |
Feature activation | +1.223 |
Token | the |
Feature activation | +1.369 |
Token | Sun |
Feature activation | +0.865 |
Token | âĢĵ |
Feature activation | +0.932 |
Token | " |
Feature activation | +0.636 |
Token | to |
Feature activation | +0.176 |
Token | do |
Feature activation | +0.098 |
Token | what |
Feature activation | +0.000 |
Token | shared |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.496 |
Token | , |
Feature activation | +1.717 |
Token | urges |
Feature activation | +0.807 |
Token | the |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | introduce |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Wall |
Feature activation | +0.000 |
Token | Street |
Feature activation | +0.000 |
Token | Journal |
Feature activation | +0.000 |
Token | reported |
Feature activation | +0.671 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Guardian |
Feature activation | +0.459 |
Token | watched |
Feature activation | +1.497 |
Token | as |
Feature activation | +0.218 |
Token | Lock |
Feature activation | +0.542 |
Token | ett |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | covered |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | editor |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Daily |
Feature activation | +0.000 |
Token | Mirror |
Feature activation | +0.358 |
Token | Morgan |
Feature activation | +0.574 |
Token | , |
Feature activation | +0.346 |
Token | 48 |
Feature activation | +0.087 |
Token | , |
Feature activation | +0.042 |
Token | was |
Feature activation | +0.000 |
Token | appointed |
Feature activation | +0.000 |
Token | according |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Star |
Feature activation | +0.000 |
Token | Tribune |
Feature activation | +0.598 |
Token | . |
Feature activation | +0.705 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | short |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | according |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Star |
Feature activation | +0.000 |
Token | Tribune |
Feature activation | +0.598 |
Token | . |
Feature activation | +0.705 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | who |
Feature activation | +0.000 |
Token | told |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Post |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.441 |
Token | Courier |
Feature activation | +1.306 |
Token | in |
Feature activation | +0.805 |
Token | Charleston |
Feature activation | +0.476 |
Token | , |
Feature activation | +0.000 |
Token | S |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | interview |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | News |
Feature activation | +0.139 |
Token | - |
Feature activation | +0.362 |
Token | G |
Feature activation | +0.668 |
Token | az |
Feature activation | +0.357 |
Token | ette |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | Champ |
Feature activation | +0.000 |
Token | meantime |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | news |
Feature activation | +0.011 |
Token | is |
Feature activation | +0.141 |
Token | all |
Feature activation | +0.273 |
Token | using |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | name |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | And |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | reporter |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | HuffPost |
Feature activation | +0.000 |
Token | who |
Feature activation | +0.421 |
Token | has |
Feature activation | +0.362 |
Token | followed |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | more |
Feature activation | +0.000 |
Token | closely |
Feature activation | +0.000 |
Token | than |
Feature activation | +0.000 |
Token | ri |
Feature activation | +0.000 |
Token | yet |
Feature activation | +0.000 |
Token | Daily |
Feature activation | +0.000 |
Token | News |
Feature activation | +0.000 |
Token | during |
Feature activation | +0.184 |
Token | a |
Feature activation | +0.470 |
Token | meeting |
Feature activation | +0.077 |
Token | on |
Feature activation | +0.000 |
Token | Sept |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | 17 |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Prime |
Feature activation | +0.000 |
Token | 16 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | New |
Feature activation | +0.000 |
Token | Haven |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Prime |
Feature activation | +0.000 |
Token | 16 |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | can |
Feature activation | +0.000 |
Token | be |
Feature activation | +0.000 |
Token | really |
Feature activation | +0.000 |
Token | ostr |
Feature activation | +0.000 |
Token | ac |
Feature activation | +0.000 |
Token | izing |
Feature activation | +0.000 |
Token | ," |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Peter |
Feature activation | +0.000 |
Token | He |
Feature activation | +0.000 |
Token | we |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | d |
Feature activation | +0.000 |
Token | be |
Feature activation | +0.000 |
Token | approaching |
Feature activation | +0.000 |
Token | Memorial |
Feature activation | +0.000 |
Token | Day |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Baltimore |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | 288 |
Feature activation | +0.000 |
Token | carries |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | 77 |
Feature activation | +0.000 |
Token | catches |
Feature activation | +0.000 |
Token | ), |
Feature activation | +0.000 |
Token | he |
Feature activation | +0.000 |
Token | averaged |
Feature activation | +0.000 |
Token | 24 |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | PC |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | ll |
Feature activation | +0.000 |
Token | be |
Feature activation | +0.000 |
Token | able |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | play |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | evident |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.706 |
Token | is |
Feature activation | +2.151 |
Token | going |
Feature activation | +1.149 |
Token | through |
Feature activation | +1.420 |
Token | increased |
Feature activation | +0.458 |
Token | crisis |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | won |
Feature activation | +0.000 |
Token | 't |
Feature activation | +0.000 |
Token | let |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.556 |
Token | dictate |
Feature activation | +2.081 |
Token | the |
Feature activation | +0.654 |
Token | rules |
Feature activation | +0.846 |
Token | . |
Feature activation | +0.000 |
Token | And |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | As |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.422 |
Token | âĢ |
Feature activation | +1.579 |
Token | Ļ |
Feature activation | +0.541 |
Token | s |
Feature activation | +0.000 |
Token | experience |
Feature activation | +0.138 |
Token | shows |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | version |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.545 |
Token | resolution |
Feature activation | +1.307 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | UN |
Feature activation | +0.000 |
Token | General |
Feature activation | +0.000 |
Token | fighting |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.137 |
Token | is |
Feature activation | +1.420 |
Token | bombing |
Feature activation | +1.280 |
Token | the |
Feature activation | +0.000 |
Token | terrorists |
Feature activation | +0.068 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Germany |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.506 |
Token | Fr |
Feature activation | +1.420 |
Token | is |
Feature activation | +0.143 |
Token | ian |
Feature activation | +0.000 |
Token | language |
Feature activation | +0.000 |
Token | spoken |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.706 |
Token | is |
Feature activation | +2.151 |
Token | going |
Feature activation | +1.149 |
Token | through |
Feature activation | +1.420 |
Token | increased |
Feature activation | +0.458 |
Token | crisis |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | its |
Feature activation | +0.000 |
Token | cultural |
Feature activation | +0.000 |
Token | version |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.545 |
Token | resolution |
Feature activation | +1.307 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | UN |
Feature activation | +0.000 |
Token | General |
Feature activation | +0.000 |
Token | Assembly |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.137 |
Token | is |
Feature activation | +1.420 |
Token | bombing |
Feature activation | +1.280 |
Token | the |
Feature activation | +0.000 |
Token | terrorists |
Feature activation | +0.068 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | TV |
Feature activation | +0.000 |
Token | birth |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | North |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.824 |
Token | founding |
Feature activation | +1.177 |
Token | leader |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Kim |
Feature activation | +0.000 |
Token | Il |
Feature activation | +0.000 |
Token | Sung |
Feature activation | +0.000 |
Token | classic |
Feature activation | +0.000 |
Token | Journey |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.085 |
Token | tales |
Feature activation | +1.152 |
Token | -- |
Feature activation | +0.000 |
Token | Stephen |
Feature activation | +0.000 |
Token | Chow |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | Journey |
Feature activation | +0.000 |
Token | evident |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.706 |
Token | is |
Feature activation | +2.151 |
Token | going |
Feature activation | +1.149 |
Token | through |
Feature activation | +1.420 |
Token | increased |
Feature activation | +0.458 |
Token | crisis |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | its |
Feature activation | +0.000 |
Token | singles |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | part |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.148 |
Token | GOOD |
Feature activation | +0.638 |
Token | Fridays |
Feature activation | +0.000 |
Token | giveaways |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | including |
Feature activation | +0.000 |
Token | two |
Feature activation | +0.000 |
Token | weeks |
Feature activation | +0.000 |
Token | after |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.530 |
Token | released |
Feature activation | +1.124 |
Token | from |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | UCLA |
Feature activation | +0.000 |
Token | Medical |
Feature activation | +0.000 |
Token | Center |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | engage |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.313 |
Token | but |
Feature activation | +1.042 |
Token | to |
Feature activation | +0.963 |
Token | no |
Feature activation | +0.596 |
Token | avail |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Stein |
Feature activation | +0.000 |
Token | hospitalized |
Feature activation | +0.000 |
Token | last |
Feature activation | +0.000 |
Token | month |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | garnered |
Feature activation | +1.040 |
Token | criticism |
Feature activation | +0.076 |
Token | for |
Feature activation | +0.000 |
Token | ending |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | California |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | height |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.527 |
Token | West |
Feature activation | +1.038 |
Token | tensions |
Feature activation | +0.839 |
Token | , |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.751 |
Token | Germany |
Feature activation | +0.000 |
Token | feared |
Feature activation | +0.344 |
Token | you |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | Old |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | type |
Feature activation | +1.017 |
Token | showdown |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | Cash |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Round |
Feature activation | +0.000 |
Token | 13 |
Feature activation | +0.000 |
Token | against |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.226 |
Token | s |
Feature activation | +0.990 |
Token | Tigers |
Feature activation | +0.545 |
Token | . |
Feature activation | +0.000 |
Token | Trent |
Feature activation | +0.000 |
Token | Robinson |
Feature activation | +0.000 |
Token | confirmed |
Feature activation | +0.000 |
Token | engage |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.313 |
Token | but |
Feature activation | +1.042 |
Token | to |
Feature activation | +0.963 |
Token | no |
Feature activation | +0.596 |
Token | avail |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Stein |
Feature activation | +0.000 |
Token | meier |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.030 |
Top resid features:
|
Token | is |
Feature activation | -0.025 |
Top resid features:
|
Token | evident |
Feature activation | -0.021 |
Top resid features:
|
Token | that |
Feature activation | +0.074 |
Top resid features:
|
Token | the |
Feature activation | +0.266 |
Top resid features:
|
Token | West |
Feature activation | +3.038 |
Top resid features:
|
Token | is |
Feature activation | +0.060 |
Top resid features:
|
Token | going |
Feature activation | +0.000 |
Top resid features:
|
Token | through |
Feature activation | +0.000 |
Top resid features:
|
Token | increased |
Feature activation | +0.000 |
Top resid features:
|
Token | crisis |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.089 |
Top resid features:
|
Token | won |
Feature activation | +0.007 |
Top resid features:
|
Token | 't |
Feature activation | +0.122 |
Top resid features:
|
Token | let |
Feature activation | +0.095 |
Top resid features:
|
Token | the |
Feature activation | +0.259 |
Top resid features:
|
Token | West |
Feature activation | +2.783 |
Top resid features:
|
Token | dictate |
Feature activation | -0.055 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | rules |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | And |
Feature activation | +0.000 |
Top resid features:
|
Token | dozen |
Feature activation | +0.012 |
Top resid features:
|
Token | . |
Feature activation | +0.094 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.089 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.091 |
Top resid features:
|
Token | As |
Feature activation | +0.268 |
Top resid features:
|
Token | West |
Feature activation | +2.362 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.025 |
Top resid features:
|
Token | Ļ |
Feature activation | +0.000 |
Top resid features:
|
Token | s |
Feature activation | +0.000 |
Top resid features:
|
Token | experience |
Feature activation | +0.000 |
Top resid features:
|
Token | shows |
Feature activation | +0.000 |
Top resid features:
|
Token | sponsored |
Feature activation | +0.007 |
Top resid features:
|
Token | a |
Feature activation | +0.118 |
Top resid features:
|
Token | version |
Feature activation | -0.069 |
Top resid features:
|
Token | of |
Feature activation | +0.197 |
Top resid features:
|
Token | the |
Feature activation | +0.223 |
Top resid features:
|
Token | West |
Feature activation | +2.338 |
Top resid features:
|
Token | 's |
Feature activation | +0.052 |
Top resid features:
|
Token | resolution |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | UN |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | -0.022 |
Top resid features:
|
Token | fighting |
Feature activation | -0.061 |
Top resid features:
|
Token | and |
Feature activation | +0.120 |
Top resid features:
|
Token | where |
Feature activation | +0.210 |
Top resid features:
|
Token | the |
Feature activation | +0.170 |
Top resid features:
|
Token | West |
Feature activation | +2.231 |
Top resid features:
|
Token | is |
Feature activation | +0.014 |
Top resid features:
|
Token | bombing |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | terrorists |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.079 |
Top resid features:
|
Token | Germany |
Feature activation | -0.012 |
Top resid features:
|
Token | , |
Feature activation | +0.145 |
Top resid features:
|
Token | and |
Feature activation | +0.167 |
Top resid features:
|
Token | the |
Feature activation | +0.246 |
Top resid features:
|
Token | West |
Feature activation | +2.163 |
Top resid features:
|
Token | Fr |
Feature activation | +0.044 |
Top resid features:
|
Token | is |
Feature activation | +0.000 |
Top resid features:
|
Token | ian |
Feature activation | +0.000 |
Top resid features:
|
Token | language |
Feature activation | +0.000 |
Top resid features:
|
Token | spoken |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | +0.021 |
Top resid features:
|
Token | is |
Feature activation | -0.021 |
Top resid features:
|
Token | evident |
Feature activation | -0.019 |
Top resid features:
|
Token | that |
Feature activation | +0.055 |
Top resid features:
|
Token | the |
Feature activation | +0.170 |
Top resid features:
|
Token | West |
Feature activation | +2.121 |
Top resid features:
|
Token | is |
Feature activation | +0.177 |
Top resid features:
|
Token | going |
Feature activation | +0.050 |
Top resid features:
|
Token | through |
Feature activation | +0.136 |
Top resid features:
|
Token | increased |
Feature activation | +0.000 |
Top resid features:
|
Token | crisis |
Feature activation | +0.000 |
Top resid features:
|
Token | sponsored |
Feature activation | -0.028 |
Top resid features:
|
Token | a |
Feature activation | +0.062 |
Top resid features:
|
Token | version |
Feature activation | -0.037 |
Top resid features:
|
Token | of |
Feature activation | +0.129 |
Top resid features:
|
Token | the |
Feature activation | +0.211 |
Top resid features:
|
Token | West |
Feature activation | +2.063 |
Top resid features:
|
Token | 's |
Feature activation | +0.133 |
Top resid features:
|
Token | resolution |
Feature activation | -0.033 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | UN |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | -0.001 |
Top resid features:
|
Token | fighting |
Feature activation | -0.034 |
Top resid features:
|
Token | and |
Feature activation | +0.082 |
Top resid features:
|
Token | where |
Feature activation | +0.097 |
Top resid features:
|
Token | the |
Feature activation | +0.211 |
Top resid features:
|
Token | West |
Feature activation | +2.086 |
Top resid features:
|
Token | is |
Feature activation | +0.198 |
Top resid features:
|
Token | bombing |
Feature activation | -0.110 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | terrorists |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.091 |
Top resid features:
|
Token | the |
Feature activation | +0.042 |
Top resid features:
|
Token | birth |
Feature activation | -0.039 |
Top resid features:
|
Token | of |
Feature activation | +0.159 |
Top resid features:
|
Token | the |
Feature activation | +0.156 |
Top resid features:
|
Token | North |
Feature activation | +1.865 |
Top resid features:
|
Token | 's |
Feature activation | +0.290 |
Top resid features:
|
Token | founding |
Feature activation | +0.074 |
Top resid features:
|
Token | leader |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | Kim |
Feature activation | +0.000 |
Top resid features:
|
Token | 's |
Feature activation | +0.002 |
Top resid features:
|
Token | classic |
Feature activation | +0.001 |
Top resid features:
|
Token | Journey |
Feature activation | -0.029 |
Top resid features:
|
Token | to |
Feature activation | +0.301 |
Top resid features:
|
Token | the |
Feature activation | +0.279 |
Top resid features:
|
Token | West |
Feature activation | +1.933 |
Top resid features:
|
Token | tales |
Feature activation | -0.103 |
Top resid features:
|
Token | -- |
Feature activation | +0.000 |
Top resid features:
|
Token | Stephen |
Feature activation | +0.000 |
Top resid features:
|
Token | Chow |
Feature activation | +0.000 |
Top resid features:
|
Token | 's |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | +0.024 |
Top resid features:
|
Token | is |
Feature activation | -0.032 |
Top resid features:
|
Token | evident |
Feature activation | -0.017 |
Top resid features:
|
Token | that |
Feature activation | +0.094 |
Top resid features:
|
Token | the |
Feature activation | +0.269 |
Top resid features:
|
Token | West |
Feature activation | +1.983 |
Top resid features:
|
Token | is |
Feature activation | +0.077 |
Top resid features:
|
Token | going |
Feature activation | -0.040 |
Top resid features:
|
Token | through |
Feature activation | +0.000 |
Top resid features:
|
Token | increased |
Feature activation | +0.000 |
Top resid features:
|
Token | crisis |
Feature activation | +0.000 |
Top resid features:
|
Token | promotional |
Feature activation | +0.021 |
Top resid features:
|
Token | singles |
Feature activation | -0.008 |
Top resid features:
|
Token | as |
Feature activation | +0.094 |
Top resid features:
|
Token | part |
Feature activation | -0.037 |
Top resid features:
|
Token | of |
Feature activation | +0.165 |
Top resid features:
|
Token | West |
Feature activation | +2.152 |
Top resid features:
|
Token | 's |
Feature activation | +0.098 |
Top resid features:
|
Token | GOOD |
Feature activation | +0.000 |
Top resid features:
|
Token | Fridays |
Feature activation | +0.000 |
Top resid features:
|
Token | giveaways |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | place |
Feature activation | -0.034 |
Top resid features:
|
Token | nearly |
Feature activation | +0.024 |
Top resid features:
|
Token | two |
Feature activation | +0.051 |
Top resid features:
|
Token | weeks |
Feature activation | -0.060 |
Top resid features:
|
Token | after |
Feature activation | +0.459 |
Top resid features:
|
Token | West |
Feature activation | +1.742 |
Top resid features:
|
Token | was |
Feature activation | +0.117 |
Top resid features:
|
Token | released |
Feature activation | -0.018 |
Top resid features:
|
Token | from |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | UCLA |
Feature activation | +0.000 |
Top resid features:
|
Token | Putin |
Feature activation | +0.023 |
Top resid features:
|
Token | to |
Feature activation | +0.054 |
Top resid features:
|
Token | engage |
Feature activation | +0.033 |
Top resid features:
|
Token | with |
Feature activation | +0.082 |
Top resid features:
|
Token | the |
Feature activation | +0.254 |
Top resid features:
|
Token | West |
Feature activation | +1.765 |
Top resid features:
|
Token | but |
Feature activation | +0.091 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | no |
Feature activation | +0.000 |
Top resid features:
|
Token | avail |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | was |
Feature activation | +0.031 |
Top resid features:
|
Token | hospitalized |
Feature activation | +0.007 |
Top resid features:
|
Token | last |
Feature activation | +0.047 |
Top resid features:
|
Token | month |
Feature activation | -0.112 |
Top resid features:
|
Token | , |
Feature activation | +0.293 |
Top resid features:
|
Token | West |
Feature activation | +2.109 |
Top resid features:
|
Token | garnered |
Feature activation | +0.041 |
Top resid features:
|
Token | criticism |
Feature activation | +0.000 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | ending |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | +0.206 |
Top resid features:
|
Token | height |
Feature activation | -0.048 |
Top resid features:
|
Token | of |
Feature activation | +0.221 |
Top resid features:
|
Token | East |
Feature activation | +1.236 |
Top resid features:
|
Token | - |
Feature activation | +0.460 |
Top resid features:
|
Token | West |
Feature activation | +0.554 |
Top resid features:
|
Token | tensions |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | West |
Feature activation | +0.000 |
Top resid features:
|
Token | challenge |
Feature activation | +0.028 |
Top resid features:
|
Token | you |
Feature activation | +0.035 |
Top resid features:
|
Token | in |
Feature activation | +0.130 |
Top resid features:
|
Token | a |
Feature activation | +0.212 |
Top resid features:
|
Token | Old |
Feature activation | +0.440 |
Top resid features:
|
Token | West |
Feature activation | +1.619 |
Top resid features:
|
Token | type |
Feature activation | -0.149 |
Top resid features:
|
Token | showdown |
Feature activation | +0.000 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | Cash |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | +0.059 |
Top resid features:
|
Token | Round |
Feature activation | -0.017 |
Top resid features:
|
Token | 13 |
Feature activation | +0.117 |
Top resid features:
|
Token | against |
Feature activation | +0.150 |
Top resid features:
|
Token | the |
Feature activation | +0.222 |
Top resid features:
|
Token | West |
Feature activation | +1.701 |
Top resid features:
|
Token | s |
Feature activation | +0.048 |
Top resid features:
|
Token | Tigers |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | Trent |
Feature activation | +0.000 |
Top resid features:
|
Token | Robinson |
Feature activation | +0.000 |
Top resid features:
|
Token | Putin |
Feature activation | +0.028 |
Top resid features:
|
Token | to |
Feature activation | +0.021 |
Top resid features:
|
Token | engage |
Feature activation | +0.001 |
Top resid features:
|
Token | with |
Feature activation | +0.044 |
Top resid features:
|
Token | the |
Feature activation | +0.149 |
Top resid features:
|
Token | West |
Feature activation | +1.606 |
Top resid features:
|
Token | but |
Feature activation | +0.324 |
Top resid features:
|
Token | to |
Feature activation | +0.162 |
Top resid features:
|
Token | no |
Feature activation | +0.000 |
Top resid features:
|
Token | avail |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | +0.000 |
Token | evident |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.706 |
Token | is |
Feature activation | +2.151 |
Token | going |
Feature activation | +1.149 |
Token | through |
Feature activation | +1.420 |
Token | increased |
Feature activation | +0.458 |
Token | crisis |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | won |
Feature activation | +0.000 |
Token | 't |
Feature activation | +0.000 |
Token | let |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.556 |
Token | dictate |
Feature activation | +2.081 |
Token | the |
Feature activation | +0.654 |
Token | rules |
Feature activation | +0.846 |
Token | . |
Feature activation | +0.000 |
Token | And |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | version |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.545 |
Token | resolution |
Feature activation | +1.307 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | UN |
Feature activation | +0.000 |
Token | General |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | As |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.422 |
Token | âĢ |
Feature activation | +1.579 |
Token | Ļ |
Feature activation | +0.541 |
Token | s |
Feature activation | +0.000 |
Token | experience |
Feature activation | +0.138 |
Token | shows |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.706 |
Token | is |
Feature activation | +2.151 |
Token | going |
Feature activation | +1.149 |
Token | through |
Feature activation | +1.420 |
Token | increased |
Feature activation | +0.458 |
Token | crisis |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | its |
Feature activation | +0.000 |
Token | cultural |
Feature activation | +0.000 |
Token | version |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.545 |
Token | resolution |
Feature activation | +1.307 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | UN |
Feature activation | +0.000 |
Token | General |
Feature activation | +0.000 |
Token | Assembly |
Feature activation | +0.000 |
Token | Germany |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.506 |
Token | Fr |
Feature activation | +1.420 |
Token | is |
Feature activation | +0.143 |
Token | ian |
Feature activation | +0.000 |
Token | language |
Feature activation | +0.000 |
Token | spoken |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | fighting |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.137 |
Token | is |
Feature activation | +1.420 |
Token | bombing |
Feature activation | +1.280 |
Token | the |
Feature activation | +0.000 |
Token | terrorists |
Feature activation | +0.068 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | singles |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | part |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | 's |
Feature activation | +1.148 |
Token | GOOD |
Feature activation | +0.638 |
Token | Fridays |
Feature activation | +0.000 |
Token | giveaways |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | including |
Feature activation | +0.000 |
Token | two |
Feature activation | +0.000 |
Token | weeks |
Feature activation | +0.000 |
Token | after |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.530 |
Token | released |
Feature activation | +1.124 |
Token | from |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | UCLA |
Feature activation | +0.000 |
Token | Medical |
Feature activation | +0.000 |
Token | Center |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.137 |
Token | is |
Feature activation | +1.420 |
Token | bombing |
Feature activation | +1.280 |
Token | the |
Feature activation | +0.000 |
Token | terrorists |
Feature activation | +0.068 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | TV |
Feature activation | +0.000 |
Token | birth |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | North |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.824 |
Token | founding |
Feature activation | +1.177 |
Token | leader |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Kim |
Feature activation | +0.000 |
Token | Il |
Feature activation | +0.000 |
Token | Sung |
Feature activation | +0.000 |
Token | classic |
Feature activation | +0.000 |
Token | Journey |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.085 |
Token | tales |
Feature activation | +1.152 |
Token | -- |
Feature activation | +0.000 |
Token | Stephen |
Feature activation | +0.000 |
Token | Chow |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | Journey |
Feature activation | +0.000 |
Token | hospitalized |
Feature activation | +0.000 |
Token | last |
Feature activation | +0.000 |
Token | month |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | garnered |
Feature activation | +1.040 |
Token | criticism |
Feature activation | +0.076 |
Token | for |
Feature activation | +0.000 |
Token | ending |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | California |
Feature activation | +0.000 |
Token | Republicans |
Feature activation | +0.000 |
Token | took |
Feature activation | +0.000 |
Token | over |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | South |
Feature activation | +0.000 |
Token | following |
Feature activation | +0.952 |
Token | the |
Feature activation | +0.370 |
Token | civil |
Feature activation | +0.139 |
Token | rights |
Feature activation | +0.000 |
Token | movement |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Elijah |
Feature activation | +0.000 |
Token | Taylor |
Feature activation | +0.000 |
Token | at |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | Tigers |
Feature activation | +0.902 |
Token | . |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | suggest |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | may |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | height |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.527 |
Token | West |
Feature activation | +1.038 |
Token | tensions |
Feature activation | +0.839 |
Token | , |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.751 |
Token | Germany |
Feature activation | +0.000 |
Token | feared |
Feature activation | +0.344 |
Token | on |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | web |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.293 |
Token | and |
Feature activation | +0.912 |
Token | Stone |
Feature activation | +0.571 |
Token | quote |
Feature activation | +0.220 |
Token | New |
Feature activation | +0.000 |
Token | York |
Feature activation | +0.000 |
Token | Times |
Feature activation | +0.000 |
Token | state |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.610 |
Token | Link |
Feature activation | +0.670 |
Token | project |
Feature activation | +0.528 |
Token | , |
Feature activation | +0.000 |
Token | which |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | scrapped |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | âĢĵ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.713 |
Token | Euras |
Feature activation | +0.682 |
Token | ian |
Feature activation | +0.005 |
Token | ancestry |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | South |
Feature activation | +0.000 |
Token | Asians |
Feature activation | +0.000 |
Token | sometimes |
Feature activation | +0.000 |
Token | called |
Feature activation | +0.000 |
Token | Pentagon |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.356 |
Token | a |
Feature activation | +0.727 |
Token | force |
Feature activation | +0.088 |
Token | of |
Feature activation | +0.000 |
Token | 7 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | 200 |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | Side |
Feature activation | +0.436 |
Token | âĢĶ |
Feature activation | +0.532 |
Token | the |
Feature activation | +0.752 |
Token | elephant |
Feature activation | +0.167 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | room |
Feature activation | +0.000 |
Token | here |
Feature activation | +0.000 |
Token | based |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.166 |
Token | Point |
Feature activation | +0.076 |
Token | remarks |
Feature activation | +0.695 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | To |
Feature activation | +0.000 |
Token | meet |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | area |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | North |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.581 |
Token | the |
Feature activation | +0.829 |
Token | Yuk |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | east |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | industry |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | Western |
Feature activation | +0.000 |
Token | import |
Feature activation | +0.602 |
Token | . |
Feature activation | +0.000 |
Token | And |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Dick |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.542 |
Token | if |
Feature activation | +0.084 |
Token | West |
Feature activation | +0.601 |
Token | Austin |
Feature activation | +0.078 |
Token | and |
Feature activation | +0.000 |
Token | its |
Feature activation | +0.617 |
Token | accompanying |
Feature activation | +0.000 |
Token | suburbs |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | long |
Feature activation | +0.000 |
Token | been |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.706 |
Token | is |
Feature activation | +2.151 |
Token | going |
Feature activation | +1.149 |
Token | through |
Feature activation | +1.420 |
Token | increased |
Feature activation | +0.458 |
Token | crisis |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | its |
Feature activation | +0.000 |
Token | cultural |
Feature activation | +0.000 |
Token | divides |
Feature activation | +0.000 |
Token | better |
Feature activation | +0.000 |
Token | ties |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.277 |
Token | . |
Feature activation | +0.569 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | ľ |
Feature activation | +0.000 |
Token | Would |
Feature activation | +0.000 |
Token | entering |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.000 |
Token | Bank |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.266 |
Token | where |
Feature activation | +0.365 |
Token | he |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | deliver |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | 29 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.034 |
Token | past |
Feature activation | +0.804 |
Token | ed |
Feature activation | +0.386 |
Token | the |
Feature activation | +0.070 |
Token | text |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Upper |
Feature activation | +0.000 |
Token | East |
Feature activation | +0.000 |
Token | Side |
Feature activation | +0.125 |
Token | are |
Feature activation | +0.301 |
Token | about |
Feature activation | +0.102 |
Token | $ |
Feature activation | +0.000 |
Token | 150 |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | 000 |
Feature activation | +0.000 |
Token | or |
Feature activation | +0.000 |
Token | redef |
Feature activation | +0.000 |
Token | ine |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | Europe |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.220 |
Token | protects |
Feature activation | +0.000 |
Token | ". |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | he |
Feature activation | +0.000 |
Token | chief |
Feature activation | +0.000 |
Token | officer |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | North |
Feature activation | +0.000 |
Token | West |
Feature activation | +0.428 |
Token | London |
Feature activation | +0.000 |
Token | collaboration |
Feature activation | +0.402 |
Token | of |
Feature activation | +0.000 |
Token | clinical |
Feature activation | +0.000 |
Token | commission |
Feature activation | +0.000 |
Token | appear |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | final |
Feature activation | +0.000 |
Token | two |
Feature activation | +0.000 |
Token | Avengers |
Feature activation | +0.000 |
Token | films |
Feature activation | +0.000 |
Token | âĢĵ |
Feature activation | +0.000 |
Token | soon |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | be |
Feature activation | +0.000 |
Token | unt |
Feature activation | +0.000 |
Token | rust |
Feature activation | +0.000 |
Token | worthy |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | or |
Feature activation | +0.000 |
Token | illegal |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | your |
Feature activation | +0.000 |
Token | jurisdiction |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ad |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | So |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | get |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | see |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | lot |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | 2009 |
Feature activation | +0.000 |
Token | Hal |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | then |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | mid |
Feature activation | +0.000 |
Token | f |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Inc |
Feature activation | +0.000 |
Token | itement |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | hatred |
Feature activation | +0.000 |
Token | based |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | sexual |
Feature activation | +0.000 |
Token | orientation |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | only |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | More |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.572 |
Token | is |
Feature activation | +2.000 |
Token | needed |
Feature activation | +2.557 |
Token | to |
Feature activation | +1.905 |
Token | find |
Feature activation | +1.075 |
Token | out |
Feature activation | +0.811 |
Token | how |
Feature activation | +0.353 |
Token | drastically |
Feature activation | +0.000 |
Token | be |
Feature activation | +0.000 |
Token | pointing |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.193 |
Token | showing |
Feature activation | +2.467 |
Token | that |
Feature activation | +0.945 |
Token | people |
Feature activation | +0.269 |
Token | eat |
Feature activation | +0.000 |
Token | better |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | more |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.146 |
Token | is |
Feature activation | +1.683 |
Token | needed |
Feature activation | +2.307 |
Token | before |
Feature activation | +0.862 |
Token | the |
Feature activation | +0.003 |
Token | next |
Feature activation | +0.000 |
Token | diet |
Feature activation | +0.000 |
Token | cra |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | could |
Feature activation | +2.210 |
Token | also |
Feature activation | +1.719 |
Token | have |
Feature activation | +1.516 |
Token | implications |
Feature activation | +0.870 |
Token | for |
Feature activation | +0.000 |
Token | understanding |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | previous |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | had |
Feature activation | +1.039 |
Token | shown |
Feature activation | +2.093 |
Token | the |
Feature activation | +0.497 |
Token | same |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | dec |
Feature activation | +0.000 |
Token | arbon |
Feature activation | +0.000 |
Token | it |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | More |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.572 |
Token | is |
Feature activation | +2.000 |
Token | needed |
Feature activation | +2.557 |
Token | to |
Feature activation | +1.905 |
Token | find |
Feature activation | +1.075 |
Token | out |
Feature activation | +0.811 |
Token | how |
Feature activation | +0.353 |
Token | first |
Feature activation | +0.000 |
Token | seems |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Our |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.184 |
Token | shows |
Feature activation | +1.984 |
Token | that |
Feature activation | +0.641 |
Token | only |
Feature activation | +0.000 |
Token | 12 |
Feature activation | +0.000 |
Token | % |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | fact |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.436 |
Token | found |
Feature activation | +1.981 |
Token | that |
Feature activation | +1.120 |
Token | politics |
Feature activation | +0.570 |
Token | was |
Feature activation | +0.000 |
Token | particularly |
Feature activation | +0.000 |
Token | important |
Feature activation | +0.000 |
Token | court |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | shows |
Feature activation | +1.974 |
Token | a |
Feature activation | +0.774 |
Token | child |
Feature activation | +0.461 |
Token | convicted |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | there |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Indeed |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.143 |
Token | shows |
Feature activation | +1.970 |
Token | that |
Feature activation | +1.135 |
Token | , |
Feature activation | +0.503 |
Token | especially |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | recently |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.287 |
Token | isn |
Feature activation | +1.896 |
Token | 't |
Feature activation | +1.952 |
Token | ready |
Feature activation | +1.233 |
Token | for |
Feature activation | +0.116 |
Token | prime |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | yet |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | As |
Feature activation | +0.000 |
Token | well |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.338 |
Token | supporting |
Feature activation | +1.932 |
Token | advanced |
Feature activation | +1.336 |
Token | reactor |
Feature activation | +0.000 |
Token | technology |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Do |
Feature activation | +0.000 |
Token | relationships |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Further |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.265 |
Token | suggests |
Feature activation | +1.932 |
Token | that |
Feature activation | +1.217 |
Token | bisexual |
Feature activation | +0.000 |
Token | individuals |
Feature activation | +0.000 |
Token | who |
Feature activation | +0.000 |
Token | do |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | More |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.572 |
Token | is |
Feature activation | +2.000 |
Token | needed |
Feature activation | +2.557 |
Token | to |
Feature activation | +1.905 |
Token | find |
Feature activation | +1.075 |
Token | out |
Feature activation | +0.811 |
Token | how |
Feature activation | +0.353 |
Token | drastically |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | could |
Feature activation | +0.000 |
Token | find |
Feature activation | +0.000 |
Token | no |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.620 |
Token | supporting |
Feature activation | +1.901 |
Token | the |
Feature activation | +0.828 |
Token | idea |
Feature activation | +0.642 |
Token | that |
Feature activation | +0.000 |
Token | bisexual |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Instead |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.392 |
Token | focused |
Feature activation | +1.901 |
Token | on |
Feature activation | +1.196 |
Token | the |
Feature activation | +0.487 |
Token | quality |
Feature activation | +0.013 |
Token | of |
Feature activation | +0.000 |
Token | father |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.287 |
Token | isn |
Feature activation | +1.896 |
Token | 't |
Feature activation | +1.952 |
Token | ready |
Feature activation | +1.233 |
Token | for |
Feature activation | +0.116 |
Token | prime |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | well |
Feature activation | +0.000 |
Token | established |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | however |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.367 |
Token | examining |
Feature activation | +1.847 |
Token | the |
Feature activation | +0.605 |
Token | behavioural |
Feature activation | +0.512 |
Token | effects |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | body |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | academic |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.575 |
Token | supports |
Feature activation | +1.840 |
Token | the |
Feature activation | +0.212 |
Token | conservative |
Feature activation | +0.000 |
Token | view |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Further |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.052 |
Token | by |
Feature activation | +1.818 |
Token | T |
Feature activation | +1.302 |
Token | & |
Feature activation | +0.000 |
Token | E |
Feature activation | +0.000 |
Token | shows |
Feature activation | +1.757 |
Token | the |
Feature activation | +0.000 |
Token | away |
Feature activation | +0.005 |
Top resid features:
|
Token | it |
Feature activation | +0.005 |
Top resid features:
|
Token | is |
Feature activation | -0.050 |
Top resid features:
|
Token | . |
Feature activation | -0.067 |
Top resid features:
|
Token | More |
Feature activation | +0.079 |
Top resid features:
|
Token | research |
Feature activation | +3.213 |
Top resid features:
|
Token | is |
Feature activation | -0.203 |
Top resid features:
|
Token | needed |
Feature activation | -0.060 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | find |
Feature activation | +0.000 |
Top resid features:
|
Token | out |
Feature activation | +0.000 |
Top resid features:
|
Token | would |
Feature activation | -0.096 |
Top resid features:
|
Token | be |
Feature activation | -0.055 |
Top resid features:
|
Token | pointing |
Feature activation | -0.066 |
Top resid features:
|
Token | to |
Feature activation | +0.011 |
Top resid features:
|
Token | the |
Feature activation | -0.145 |
Top resid features:
|
Token | research |
Feature activation | +3.605 |
Top resid features:
|
Token | showing |
Feature activation | -0.198 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | people |
Feature activation | +0.000 |
Top resid features:
|
Token | eat |
Feature activation | +0.000 |
Top resid features:
|
Token | better |
Feature activation | +0.000 |
Top resid features:
|
Token | MAP |
Feature activation | -0.011 |
Top resid features:
|
Token | diet |
Feature activation | -0.017 |
Top resid features:
|
Token | , |
Feature activation | -0.073 |
Top resid features:
|
Token | but |
Feature activation | -0.085 |
Top resid features:
|
Token | more |
Feature activation | +0.092 |
Top resid features:
|
Token | research |
Feature activation | +3.120 |
Top resid features:
|
Token | is |
Feature activation | -0.162 |
Top resid features:
|
Token | needed |
Feature activation | -0.083 |
Top resid features:
|
Token | before |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | next |
Feature activation | +0.000 |
Top resid features:
|
Token | cancers |
Feature activation | -0.037 |
Top resid features:
|
Token | . |
Feature activation | -0.103 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.030 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.039 |
Top resid features:
|
Token | The |
Feature activation | -0.040 |
Top resid features:
|
Token | research |
Feature activation | +3.133 |
Top resid features:
|
Token | could |
Feature activation | +0.012 |
Top resid features:
|
Token | also |
Feature activation | +0.000 |
Top resid features:
|
Token | have |
Feature activation | +0.000 |
Top resid features:
|
Token | implications |
Feature activation | +0.000 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | D |
Feature activation | -0.013 |
Top resid features:
|
Token | odd |
Feature activation | -0.019 |
Top resid features:
|
Token | s |
Feature activation | -0.005 |
Top resid features:
|
Token | said |
Feature activation | -0.101 |
Top resid features:
|
Token | previous |
Feature activation | +0.018 |
Top resid features:
|
Token | research |
Feature activation | +3.134 |
Top resid features:
|
Token | had |
Feature activation | -0.163 |
Top resid features:
|
Token | shown |
Feature activation | -0.235 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | same |
Feature activation | +0.000 |
Top resid features:
|
Token | " |
Feature activation | +0.000 |
Top resid features:
|
Token | away |
Feature activation | -0.008 |
Top resid features:
|
Token | it |
Feature activation | -0.002 |
Top resid features:
|
Token | is |
Feature activation | -0.049 |
Top resid features:
|
Token | . |
Feature activation | -0.092 |
Top resid features:
|
Token | More |
Feature activation | +0.186 |
Top resid features:
|
Token | research |
Feature activation | +2.541 |
Top resid features:
|
Token | is |
Feature activation | -0.159 |
Top resid features:
|
Token | needed |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | find |
Feature activation | +0.000 |
Top resid features:
|
Token | out |
Feature activation | +0.000 |
Top resid features:
|
Token | it |
Feature activation | -0.013 |
Top resid features:
|
Token | first |
Feature activation | -0.014 |
Top resid features:
|
Token | seems |
Feature activation | -0.080 |
Top resid features:
|
Token | . |
Feature activation | -0.136 |
Top resid features:
|
Token | Our |
Feature activation | -0.032 |
Top resid features:
|
Token | research |
Feature activation | +2.931 |
Top resid features:
|
Token | shows |
Feature activation | -0.177 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | only |
Feature activation | +0.000 |
Top resid features:
|
Token | 12 |
Feature activation | +0.000 |
Top resid features:
|
Token | % |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.004 |
Top resid features:
|
Token | In |
Feature activation | +0.023 |
Top resid features:
|
Token | fact |
Feature activation | -0.017 |
Top resid features:
|
Token | , |
Feature activation | -0.147 |
Top resid features:
|
Token | the |
Feature activation | -0.084 |
Top resid features:
|
Token | research |
Feature activation | +2.658 |
Top resid features:
|
Token | found |
Feature activation | +0.015 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | politics |
Feature activation | +0.000 |
Top resid features:
|
Token | was |
Feature activation | +0.000 |
Top resid features:
|
Token | particularly |
Feature activation | +0.000 |
Top resid features:
|
Token | adult |
Feature activation | -0.001 |
Top resid features:
|
Token | court |
Feature activation | -0.019 |
Top resid features:
|
Token | . |
Feature activation | -0.102 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.094 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.126 |
Top resid features:
|
Token | Research |
Feature activation | +3.136 |
Top resid features:
|
Token | shows |
Feature activation | -0.200 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | child |
Feature activation | +0.000 |
Top resid features:
|
Token | convicted |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | one |
Feature activation | -0.031 |
Top resid features:
|
Token | there |
Feature activation | -0.025 |
Top resid features:
|
Token | . |
Feature activation | -0.091 |
Top resid features:
|
Token | Indeed |
Feature activation | -0.069 |
Top resid features:
|
Token | , |
Feature activation | -0.255 |
Top resid features:
|
Token | research |
Feature activation | +3.011 |
Top resid features:
|
Token | shows |
Feature activation | -0.136 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | especially |
Feature activation | +0.000 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | says |
Feature activation | +0.005 |
Top resid features:
|
Token | . |
Feature activation | -0.049 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.009 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.005 |
Top resid features:
|
Token | The |
Feature activation | -0.114 |
Top resid features:
|
Token | research |
Feature activation | +2.870 |
Top resid features:
|
Token | isn |
Feature activation | -0.112 |
Top resid features:
|
Token | 't |
Feature activation | -0.099 |
Top resid features:
|
Token | ready |
Feature activation | +0.000 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | prime |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.024 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.020 |
Top resid features:
|
Token | As |
Feature activation | -0.055 |
Top resid features:
|
Token | well |
Feature activation | +0.081 |
Top resid features:
|
Token | as |
Feature activation | -0.129 |
Top resid features:
|
Token | research |
Feature activation | +2.576 |
Top resid features:
|
Token | supporting |
Feature activation | -0.064 |
Top resid features:
|
Token | advanced |
Feature activation | +0.000 |
Top resid features:
|
Token | reactor |
Feature activation | +0.000 |
Top resid features:
|
Token | technology |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | term |
Feature activation | -0.006 |
Top resid features:
|
Token | relationships |
Feature activation | -0.023 |
Top resid features:
|
Token | . |
Feature activation | -0.080 |
Top resid features:
|
Token | Further |
Feature activation | +0.064 |
Top resid features:
|
Token | , |
Feature activation | -0.223 |
Top resid features:
|
Token | research |
Feature activation | +2.920 |
Top resid features:
|
Token | suggests |
Feature activation | -0.141 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | bisexual |
Feature activation | +0.000 |
Top resid features:
|
Token | individuals |
Feature activation | +0.000 |
Top resid features:
|
Token | who |
Feature activation | +0.000 |
Top resid features:
|
Token | away |
Feature activation | -0.008 |
Top resid features:
|
Token | it |
Feature activation | +0.003 |
Top resid features:
|
Token | is |
Feature activation | -0.045 |
Top resid features:
|
Token | . |
Feature activation | -0.018 |
Top resid features:
|
Token | More |
Feature activation | +0.071 |
Top resid features:
|
Token | research |
Feature activation | +2.643 |
Top resid features:
|
Token | is |
Feature activation | -0.169 |
Top resid features:
|
Token | needed |
Feature activation | -0.209 |
Top resid features:
|
Token | to |
Feature activation | +0.005 |
Top resid features:
|
Token | find |
Feature activation | +0.000 |
Top resid features:
|
Token | out |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.030 |
Top resid features:
|
Token | I |
Feature activation | -0.015 |
Top resid features:
|
Token | could |
Feature activation | +0.001 |
Top resid features:
|
Token | find |
Feature activation | +0.004 |
Top resid features:
|
Token | no |
Feature activation | -0.154 |
Top resid features:
|
Token | research |
Feature activation | +2.619 |
Top resid features:
|
Token | supporting |
Feature activation | -0.153 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | idea |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | bisexual |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.012 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.002 |
Top resid features:
|
Token | Instead |
Feature activation | -0.164 |
Top resid features:
|
Token | , |
Feature activation | -0.110 |
Top resid features:
|
Token | the |
Feature activation | -0.043 |
Top resid features:
|
Token | research |
Feature activation | +2.928 |
Top resid features:
|
Token | focused |
Feature activation | -0.118 |
Top resid features:
|
Token | on |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | quality |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | says |
Feature activation | -0.003 |
Top resid features:
|
Token | . |
Feature activation | -0.078 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.005 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.026 |
Top resid features:
|
Token | The |
Feature activation | -0.130 |
Top resid features:
|
Token | research |
Feature activation | +2.707 |
Top resid features:
|
Token | isn |
Feature activation | -0.000 |
Top resid features:
|
Token | 't |
Feature activation | +0.000 |
Top resid features:
|
Token | ready |
Feature activation | +0.000 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | prime |
Feature activation | +0.000 |
Top resid features:
|
Token | fairly |
Feature activation | -0.024 |
Top resid features:
|
Token | well |
Feature activation | +0.014 |
Top resid features:
|
Token | established |
Feature activation | -0.026 |
Top resid features:
|
Token | , |
Feature activation | -0.173 |
Top resid features:
|
Token | however |
Feature activation | -0.080 |
Top resid features:
|
Token | research |
Feature activation | +2.878 |
Top resid features:
|
Token | examining |
Feature activation | -0.196 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | behavioural |
Feature activation | +0.000 |
Top resid features:
|
Token | effects |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | -0.019 |
Top resid features:
|
Token | growing |
Feature activation | +0.013 |
Top resid features:
|
Token | body |
Feature activation | -0.056 |
Top resid features:
|
Token | of |
Feature activation | +0.004 |
Top resid features:
|
Token | academic |
Feature activation | +0.202 |
Top resid features:
|
Token | research |
Feature activation | +2.459 |
Top resid features:
|
Token | that |
Feature activation | -0.215 |
Top resid features:
|
Token | supports |
Feature activation | -0.096 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | conservative |
Feature activation | +0.000 |
Top resid features:
|
Token | view |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.054 |
Top resid features:
|
Token | Ŀ |
Feature activation | +0.016 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.029 |
Top resid features:
|
Token | Further |
Feature activation | -0.150 |
Top resid features:
|
Token | research |
Feature activation | +2.761 |
Top resid features:
|
Token | by |
Feature activation | -0.044 |
Top resid features:
|
Token | T |
Feature activation | +0.000 |
Top resid features:
|
Token | & |
Feature activation | +0.000 |
Top resid features:
|
Token | E |
Feature activation | +0.000 |
Top resid features:
|
Token | shows |
Feature activation | +0.000 |
Top resid features:
|
Token | be |
Feature activation | +0.000 |
Token | pointing |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.193 |
Token | showing |
Feature activation | +2.467 |
Token | that |
Feature activation | +0.945 |
Token | people |
Feature activation | +0.269 |
Token | eat |
Feature activation | +0.000 |
Token | better |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | more |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.146 |
Token | is |
Feature activation | +1.683 |
Token | needed |
Feature activation | +2.307 |
Token | before |
Feature activation | +0.862 |
Token | the |
Feature activation | +0.003 |
Token | next |
Feature activation | +0.000 |
Token | diet |
Feature activation | +0.000 |
Token | cra |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | More |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.572 |
Token | is |
Feature activation | +2.000 |
Token | needed |
Feature activation | +2.557 |
Token | to |
Feature activation | +1.905 |
Token | find |
Feature activation | +1.075 |
Token | out |
Feature activation | +0.811 |
Token | how |
Feature activation | +0.353 |
Token | drastically |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | could |
Feature activation | +2.210 |
Token | also |
Feature activation | +1.719 |
Token | have |
Feature activation | +1.516 |
Token | implications |
Feature activation | +0.870 |
Token | for |
Feature activation | +0.000 |
Token | understanding |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | previous |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | had |
Feature activation | +1.039 |
Token | shown |
Feature activation | +2.093 |
Token | the |
Feature activation | +0.497 |
Token | same |
Feature activation | +0.000 |
Token | " |
Feature activation | +0.000 |
Token | dec |
Feature activation | +0.000 |
Token | arbon |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | fact |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.436 |
Token | found |
Feature activation | +1.981 |
Token | that |
Feature activation | +1.120 |
Token | politics |
Feature activation | +0.570 |
Token | was |
Feature activation | +0.000 |
Token | particularly |
Feature activation | +0.000 |
Token | important |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.287 |
Token | isn |
Feature activation | +1.896 |
Token | 't |
Feature activation | +1.952 |
Token | ready |
Feature activation | +1.233 |
Token | for |
Feature activation | +0.116 |
Token | prime |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | yet |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.287 |
Token | isn |
Feature activation | +1.896 |
Token | 't |
Feature activation | +1.952 |
Token | ready |
Feature activation | +1.233 |
Token | for |
Feature activation | +0.116 |
Token | prime |
Feature activation | +0.000 |
Token | time |
Feature activation | +0.000 |
Token | body |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | academic |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.575 |
Token | supports |
Feature activation | +1.840 |
Token | the |
Feature activation | +0.212 |
Token | conservative |
Feature activation | +0.000 |
Token | view |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Further |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.052 |
Token | by |
Feature activation | +1.818 |
Token | T |
Feature activation | +1.302 |
Token | & |
Feature activation | +0.000 |
Token | E |
Feature activation | +0.000 |
Token | shows |
Feature activation | +1.757 |
Token | the |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | others |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.142 |
Token | consisted |
Feature activation | +1.710 |
Token | of |
Feature activation | +1.263 |
Token | forcing |
Feature activation | +0.632 |
Token | test |
Feature activation | +0.000 |
Token | subjects |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | upbeat |
Feature activation | +0.000 |
Token | conversations |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | shows |
Feature activation | +1.648 |
Token | . |
Feature activation | +0.307 |
Token | Seek |
Feature activation | +0.000 |
Token | out |
Feature activation | +0.000 |
Token | any |
Feature activation | +0.000 |
Token | common |
Feature activation | +0.000 |
Token | culmin |
Feature activation | +0.000 |
Token | ates |
Feature activation | +0.000 |
Token | years |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.100 |
Token | indicating |
Feature activation | +1.738 |
Token | that |
Feature activation | +0.820 |
Token | the |
Feature activation | +0.213 |
Token | convoluted |
Feature activation | +0.000 |
Token | squ |
Feature activation | +0.000 |
Token | ishy |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | One |
Feature activation | +0.000 |
Token | factor |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.249 |
Token | shows |
Feature activation | +1.720 |
Token | , |
Feature activation | +0.993 |
Token | has |
Feature activation | +1.209 |
Token | a |
Feature activation | +0.582 |
Token | larger |
Feature activation | +0.361 |
Token | - |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | such |
Feature activation | +0.000 |
Token | fundamental |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.506 |
Token | impacts |
Feature activation | +1.556 |
Token | the |
Feature activation | +0.000 |
Token | fields |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | both |
Feature activation | +0.000 |
Token | computing |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | What |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.318 |
Token | ? |
Feature activation | +1.378 |
Token | Ċ |
Feature activation | +0.387 |
Token | Ċ |
Feature activation | +0.227 |
Token | or |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | also |
Feature activation | +1.112 |
Token | highlights |
Feature activation | +1.453 |
Token | how |
Feature activation | +0.008 |
Token | technology |
Feature activation | +0.000 |
Token | can |
Feature activation | +0.000 |
Token | provide |
Feature activation | +0.000 |
Token | insight |
Feature activation | +0.000 |
Token | extensively |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | New |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.450 |
Token | on |
Feature activation | +1.142 |
Token | the |
Feature activation | +1.524 |
Token | structure |
Feature activation | +0.487 |
Token | of |
Feature activation | +0.000 |
Token | spider |
Feature activation | +0.000 |
Token | silk |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Further |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.052 |
Token | by |
Feature activation | +1.818 |
Token | T |
Feature activation | +1.302 |
Token | & |
Feature activation | +0.000 |
Token | E |
Feature activation | +0.000 |
Token | shows |
Feature activation | +1.757 |
Token | the |
Feature activation | +0.000 |
Token | availability |
Feature activation | +0.000 |
Token | will |
Feature activation | +0.000 |
Token | establish |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | development |
Feature activation | +1.388 |
Token | centre |
Feature activation | +0.000 |
Token | focusing |
Feature activation | +0.133 |
Token | on |
Feature activation | +0.000 |
Token | autonomous |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | growing |
Feature activation | +0.000 |
Token | field |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.554 |
Token | on |
Feature activation | +1.193 |
Token | bisexual |
Feature activation | +0.266 |
Token | ity |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.356 |
Token | promising |
Feature activation | +0.022 |
Token | , |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | centered |
Feature activation | +0.000 |
Token | outcomes |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.906 |
Token | identify |
Feature activation | +1.064 |
Token | waste |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | improve |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | safety |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | To |
Feature activation | +0.000 |
Token | do |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.263 |
Token | his |
Feature activation | +0.854 |
Token | team |
Feature activation | +0.000 |
Token | placed |
Feature activation | +0.177 |
Token | a |
Feature activation | +0.000 |
Token | special |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | fake |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | journal |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.755 |
Token | push |
Feature activation | +1.207 |
Token | Mer |
Feature activation | +0.000 |
Token | ck |
Feature activation | +0.000 |
Token | products |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | An |
Feature activation | +0.000 |
Token | international |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | team |
Feature activation | +0.200 |
Token | has |
Feature activation | +0.444 |
Token | used |
Feature activation | +1.120 |
Token | a |
Feature activation | +0.125 |
Token | " |
Feature activation | +0.000 |
Token | ther |
Feature activation | +0.000 |
Token | mal |
Feature activation | +0.000 |
Token | met |
Feature activation | +0.000 |
Token | phrases |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Body |
Feature activation | +0.000 |
Token | language |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.925 |
Token | revealed |
Feature activation | +1.770 |
Token | a |
Feature activation | +0.052 |
Token | correlation |
Feature activation | +0.000 |
Token | between |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | thing |
Feature activation | +0.000 |
Token | ; |
Feature activation | +0.000 |
Token | some |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.231 |
Token | especially |
Feature activation | +0.984 |
Token | in |
Feature activation | +0.662 |
Token | the |
Feature activation | +0.519 |
Token | area |
Feature activation | +0.142 |
Token | of |
Feature activation | +0.000 |
Token | heart |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | more |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.146 |
Token | is |
Feature activation | +1.683 |
Token | needed |
Feature activation | +2.307 |
Token | before |
Feature activation | +0.862 |
Token | the |
Feature activation | +0.003 |
Token | next |
Feature activation | +0.000 |
Token | diet |
Feature activation | +0.000 |
Token | cra |
Feature activation | +0.000 |
Token | ze |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | locate |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | development |
Feature activation | +1.018 |
Token | centre |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | Turk |
Feature activation | +0.000 |
Token | u |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | lot |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.631 |
Token | been |
Feature activation | +0.874 |
Token | done |
Feature activation | +1.117 |
Token | over |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | last |
Feature activation | +0.000 |
Token | 10 |
Feature activation | +0.000 |
Token | economic |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | historical |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | demonstrates |
Feature activation | +1.246 |
Token | that |
Feature activation | +0.653 |
Token | black |
Feature activation | +0.255 |
Token | student |
Feature activation | +0.000 |
Token | performance |
Feature activation | +0.000 |
Token | improves |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | recent |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.057 |
Token | paper |
Feature activation | +0.074 |
Token | we |
Feature activation | +0.436 |
Token | look |
Feature activation | +0.622 |
Token | at |
Feature activation | +0.481 |
Token | how |
Feature activation | +0.042 |
Token | the |
Feature activation | +0.000 |
Token | fiscal |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | excuse |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.674 |
Token | It |
Feature activation | +1.375 |
Token | âĢ |
Feature activation | +0.184 |
Token | Ļ |
Feature activation | +0.105 |
Token | s |
Feature activation | +0.000 |
Token | always |
Feature activation | +0.000 |
Token | creating |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | fake |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | journal |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.755 |
Token | push |
Feature activation | +1.207 |
Token | Mer |
Feature activation | +0.000 |
Token | ck |
Feature activation | +0.000 |
Token | products |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | growing |
Feature activation | +0.000 |
Token | field |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.554 |
Token | on |
Feature activation | +1.193 |
Token | bisexual |
Feature activation | +0.266 |
Token | ity |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.356 |
Token | promising |
Feature activation | +0.022 |
Token | body |
Feature activation | +0.000 |
Token | weight |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | studies |
Feature activation | +0.000 |
Token | looked |
Feature activation | +0.280 |
Token | at |
Feature activation | +0.000 |
Token | people |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | An |
Feature activation | +0.000 |
Token | international |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | team |
Feature activation | +0.200 |
Token | has |
Feature activation | +0.444 |
Token | used |
Feature activation | +1.120 |
Token | a |
Feature activation | +0.125 |
Token | " |
Feature activation | +0.000 |
Token | ther |
Feature activation | +0.000 |
Token | mal |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.249 |
Token | shows |
Feature activation | +1.720 |
Token | , |
Feature activation | +0.993 |
Token | has |
Feature activation | +1.209 |
Token | a |
Feature activation | +0.582 |
Token | larger |
Feature activation | +0.361 |
Token | - |
Feature activation | +0.000 |
Token | than |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | expected |
Feature activation | +0.000 |
Token | impact |
Feature activation | +0.000 |
Token | upbeat |
Feature activation | +0.000 |
Token | conversations |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | shows |
Feature activation | +1.648 |
Token | . |
Feature activation | +0.307 |
Token | Seek |
Feature activation | +0.000 |
Token | out |
Feature activation | +0.000 |
Token | any |
Feature activation | +0.000 |
Token | common |
Feature activation | +0.000 |
Token | interests |
Feature activation | +0.000 |
Token | ay |
Feature activation | +0.000 |
Token | ashi |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | research |
Feature activation | +0.000 |
Token | team |
Feature activation | +0.477 |
Token | said |
Feature activation | +0.429 |
Token | " |
Feature activation | +0.241 |
Token | We |
Feature activation | +0.000 |
Token | first |
Feature activation | +0.000 |
Token | discovered |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | long |
Feature activation | +0.000 |
Token | turnover |
Feature activation | +0.000 |
Token | drives |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Arch |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | miles |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | city |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | aging |
Feature activation | +0.000 |
Token | sewer |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | any |
Feature activation | +0.000 |
Token | organization |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Sil |
Feature activation | +0.000 |
Token | icon |
Feature activation | +0.000 |
Token | Valley |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | war |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | YOU |
Feature activation | +0.000 |
Token | ST |
Feature activation | +0.000 |
Token | UP |
Feature activation | +0.000 |
Token | ID |
Feature activation | +0.000 |
Token | FUCK |
Feature activation | +0.000 |
Token | S |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | 'm |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | trans |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | prag |
Feature activation | +0.000 |
Token | mat |
Feature activation | +0.000 |
Token | ism |
Feature activation | +0.000 |
Token | behind |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | You |
Feature activation | +0.000 |
Token | look |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.138 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | separate |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.023 |
Token | released |
Feature activation | +3.294 |
Token | on |
Feature activation | +0.078 |
Token | Thursday |
Feature activation | +0.067 |
Token | , |
Feature activation | +0.000 |
Token | Del |
Feature activation | +0.000 |
Token | ors |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.471 |
Token | does |
Feature activation | +2.578 |
Token | it |
Feature activation | +1.041 |
Token | acknowledge |
Feature activation | +0.978 |
Token | that |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | egregious |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | ! |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.364 |
Token | by |
Feature activation | +2.528 |
Token | Af |
Feature activation | +0.617 |
Token | ro |
Feature activation | +0.000 |
Token | dit |
Feature activation | +0.000 |
Token | i |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | From |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | same |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.068 |
Token | last |
Feature activation | +2.450 |
Token | year |
Feature activation | +2.273 |
Token | , |
Feature activation | +0.598 |
Token | written |
Feature activation | +0.635 |
Token | before |
Feature activation | +0.000 |
Token | NYPD |
Feature activation | +0.000 |
Token | because |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | was |
Feature activation | +2.386 |
Token | originally |
Feature activation | +1.916 |
Token | published |
Feature activation | +1.230 |
Token | on |
Feature activation | +0.000 |
Token | August |
Feature activation | +0.000 |
Token | 21 |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.114 |
Token | was |
Feature activation | +2.358 |
Token | originally |
Feature activation | +1.904 |
Token | written |
Feature activation | +1.618 |
Token | for |
Feature activation | +0.134 |
Token | Science |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | , |
Feature activation | +2.346 |
Token | I |
Feature activation | +1.468 |
Token | will |
Feature activation | +1.032 |
Token | explain |
Feature activation | +0.704 |
Token | Goal |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | Laura |
Feature activation | +0.000 |
Token | Miller |
Feature activation | +0.000 |
Token | wrote |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.096 |
Token | called |
Feature activation | +2.342 |
Token | âĢ |
Feature activation | +0.097 |
Token | ľ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.085 |
Token | Defense |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | From |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | same |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.068 |
Token | last |
Feature activation | +2.450 |
Token | year |
Feature activation | +2.273 |
Token | , |
Feature activation | +0.598 |
Token | written |
Feature activation | +0.635 |
Token | before |
Feature activation | +0.000 |
Token | NYPD |
Feature activation | +0.000 |
Token | officers |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | was |
Feature activation | +2.256 |
Token | first |
Feature activation | +1.816 |
Token | written |
Feature activation | +1.280 |
Token | by |
Feature activation | +0.033 |
Token | Newsweek |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Egyptian |
Feature activation | +0.000 |
Token | Constitution |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.457 |
Token | calls |
Feature activation | +2.232 |
Token | for |
Feature activation | +0.472 |
Token | prison |
Feature activation | +0.090 |
Token | sentences |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | fines |
Feature activation | +0.000 |
Token | available |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.221 |
Token | will |
Feature activation | +2.147 |
Token | show |
Feature activation | +1.657 |
Token | you |
Feature activation | +0.469 |
Token | how |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | To |
Feature activation | +0.000 |
Token | render |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.128 |
Token | containing |
Feature activation | +2.146 |
Token | both |
Feature activation | +0.286 |
Token | R |
Feature activation | +0.000 |
Token | plots |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | diagrams |
Feature activation | +0.000 |
Token | once |
Feature activation | +0.000 |
Token | again |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | is |
Feature activation | +2.138 |
Token | over |
Feature activation | +0.766 |
Token | 2 |
Feature activation | +0.433 |
Token | years |
Feature activation | +0.895 |
Token | old |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ed |
Feature activation | +0.000 |
Token | note |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | was |
Feature activation | +2.121 |
Token | updated |
Feature activation | +1.495 |
Token | on |
Feature activation | +0.000 |
Token | March |
Feature activation | +0.000 |
Token | 2 |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.141 |
Token | is |
Feature activation | +2.091 |
Token | from |
Feature activation | +1.367 |
Token | the |
Feature activation | +1.095 |
Token | archive |
Feature activation | +0.846 |
Token | of |
Feature activation | +0.000 |
Token | our |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | apple |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | is |
Feature activation | +2.078 |
Token | from |
Feature activation | +1.092 |
Token | the |
Feature activation | +1.167 |
Token | archive |
Feature activation | +0.610 |
Token | of |
Feature activation | +0.000 |
Token | our |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | Washington |
Feature activation | +0.000 |
Token | Post |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.035 |
Token | cast |
Feature activation | +2.063 |
Token | it |
Feature activation | +0.248 |
Token | in |
Feature activation | +0.063 |
Token | an |
Feature activation | +0.046 |
Token | Orwell |
Feature activation | +0.000 |
Token | ian |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | is |
Feature activation | +2.042 |
Token | from |
Feature activation | +1.256 |
Token | the |
Feature activation | +0.882 |
Token | archive |
Feature activation | +0.506 |
Token | of |
Feature activation | +0.000 |
Token | our |
Feature activation | +0.000 |
Token | 8 |
Feature activation | +0.000 |
Token | ]. |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.229 |
Token | , |
Feature activation | +2.033 |
Token | based |
Feature activation | +1.818 |
Token | on |
Feature activation | +0.719 |
Token | a |
Feature activation | +0.244 |
Token | talk |
Feature activation | +0.098 |
Token | given |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | -0.126 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.060 |
Top resid features:
|
Token | In |
Feature activation | -0.052 |
Top resid features:
|
Token | a |
Feature activation | +0.059 |
Top resid features:
|
Token | separate |
Feature activation | -0.096 |
Top resid features:
|
Token | article |
Feature activation | +5.468 |
Top resid features:
|
Token | released |
Feature activation | -0.117 |
Top resid features:
|
Token | on |
Feature activation | +0.000 |
Top resid features:
|
Token | Thursday |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | Del |
Feature activation | +0.000 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.031 |
Top resid features:
|
Token | where |
Feature activation | -0.125 |
Top resid features:
|
Token | in |
Feature activation | -0.155 |
Top resid features:
|
Token | the |
Feature activation | -0.039 |
Top resid features:
|
Token | article |
Feature activation | +4.768 |
Top resid features:
|
Token | does |
Feature activation | -0.057 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | acknowledge |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | an |
Feature activation | +0.000 |
Top resid features:
|
Token | near |
Feature activation | +0.232 |
Top resid features:
|
Token | you |
Feature activation | +0.027 |
Top resid features:
|
Token | ! |
Feature activation | +0.188 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.059 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.061 |
Top resid features:
|
Token | article |
Feature activation | +3.939 |
Top resid features:
|
Token | by |
Feature activation | -0.190 |
Top resid features:
|
Token | Af |
Feature activation | +0.000 |
Top resid features:
|
Token | ro |
Feature activation | +0.000 |
Top resid features:
|
Token | dit |
Feature activation | +0.000 |
Top resid features:
|
Token | i |
Feature activation | +0.000 |
Top resid features:
|
Token | crackdown |
Feature activation | +0.046 |
Top resid features:
|
Token | . |
Feature activation | +0.089 |
Top resid features:
|
Token | From |
Feature activation | -0.064 |
Top resid features:
|
Token | the |
Feature activation | -0.064 |
Top resid features:
|
Token | same |
Feature activation | -0.138 |
Top resid features:
|
Token | article |
Feature activation | +4.463 |
Top resid features:
|
Token | last |
Feature activation | -0.044 |
Top resid features:
|
Token | year |
Feature activation | +0.000 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | written |
Feature activation | +0.000 |
Top resid features:
|
Token | before |
Feature activation | +0.000 |
Top resid features:
|
Token | sandwich |
Feature activation | +0.029 |
Top resid features:
|
Token | because |
Feature activation | -0.025 |
Top resid features:
|
Token | you |
Feature activation | +0.005 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.117 |
Top resid features:
|
Token | This |
Feature activation | -0.489 |
Top resid features:
|
Token | article |
Feature activation | +4.780 |
Top resid features:
|
Token | was |
Feature activation | -0.050 |
Top resid features:
|
Token | originally |
Feature activation | +0.000 |
Top resid features:
|
Token | published |
Feature activation | +0.000 |
Top resid features:
|
Token | on |
Feature activation | +0.000 |
Top resid features:
|
Token | August |
Feature activation | +0.000 |
Top resid features:
|
Token | website |
Feature activation | +0.040 |
Top resid features:
|
Token | . |
Feature activation | +0.068 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.049 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.060 |
Top resid features:
|
Token | This |
Feature activation | -0.388 |
Top resid features:
|
Token | article |
Feature activation | +4.398 |
Top resid features:
|
Token | was |
Feature activation | -0.013 |
Top resid features:
|
Token | originally |
Feature activation | +0.000 |
Top resid features:
|
Token | written |
Feature activation | +0.000 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | Science |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.055 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.015 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.017 |
Top resid features:
|
Token | In |
Feature activation | -0.057 |
Top resid features:
|
Token | this |
Feature activation | -0.079 |
Top resid features:
|
Token | article |
Feature activation | +4.108 |
Top resid features:
|
Token | , |
Feature activation | +0.203 |
Top resid features:
|
Token | I |
Feature activation | +0.000 |
Top resid features:
|
Token | will |
Feature activation | +0.000 |
Top resid features:
|
Token | explain |
Feature activation | +0.000 |
Top resid features:
|
Token | Goal |
Feature activation | +0.000 |
Top resid features:
|
Token | contributor |
Feature activation | +0.041 |
Top resid features:
|
Token | Laura |
Feature activation | +0.007 |
Top resid features:
|
Token | Miller |
Feature activation | +0.065 |
Top resid features:
|
Token | wrote |
Feature activation | -0.219 |
Top resid features:
|
Token | an |
Feature activation | +0.045 |
Top resid features:
|
Token | article |
Feature activation | +4.214 |
Top resid features:
|
Token | called |
Feature activation | -0.119 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | ľ |
Feature activation | +0.000 |
Top resid features:
|
Token | In |
Feature activation | +0.000 |
Top resid features:
|
Token | Defense |
Feature activation | +0.000 |
Top resid features:
|
Token | crackdown |
Feature activation | +0.029 |
Top resid features:
|
Token | . |
Feature activation | +0.090 |
Top resid features:
|
Token | From |
Feature activation | +0.056 |
Top resid features:
|
Token | the |
Feature activation | -0.044 |
Top resid features:
|
Token | same |
Feature activation | -0.110 |
Top resid features:
|
Token | article |
Feature activation | +4.191 |
Top resid features:
|
Token | last |
Feature activation | -0.168 |
Top resid features:
|
Token | year |
Feature activation | +0.096 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | written |
Feature activation | +0.000 |
Top resid features:
|
Token | before |
Feature activation | +0.000 |
Top resid features:
|
Token | Records |
Feature activation | -0.144 |
Top resid features:
|
Token | . |
Feature activation | +0.076 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.037 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.032 |
Top resid features:
|
Token | This |
Feature activation | -0.439 |
Top resid features:
|
Token | article |
Feature activation | +4.676 |
Top resid features:
|
Token | was |
Feature activation | -0.016 |
Top resid features:
|
Token | first |
Feature activation | +0.000 |
Top resid features:
|
Token | written |
Feature activation | +0.000 |
Top resid features:
|
Token | by |
Feature activation | +0.000 |
Top resid features:
|
Token | Newsweek |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | -0.017 |
Top resid features:
|
Token | Egyptian |
Feature activation | -0.013 |
Top resid features:
|
Token | Constitution |
Feature activation | +0.077 |
Top resid features:
|
Token | . |
Feature activation | +0.114 |
Top resid features:
|
Token | The |
Feature activation | -0.059 |
Top resid features:
|
Token | article |
Feature activation | +4.167 |
Top resid features:
|
Token | calls |
Feature activation | -0.160 |
Top resid features:
|
Token | for |
Feature activation | +0.000 |
Top resid features:
|
Token | prison |
Feature activation | +0.000 |
Top resid features:
|
Token | sentences |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | its |
Feature activation | -0.004 |
Top resid features:
|
Token | available |
Feature activation | +0.013 |
Top resid features:
|
Token | , |
Feature activation | +0.105 |
Top resid features:
|
Token | and |
Feature activation | -0.043 |
Top resid features:
|
Token | this |
Feature activation | -0.109 |
Top resid features:
|
Token | article |
Feature activation | +3.998 |
Top resid features:
|
Token | will |
Feature activation | -0.101 |
Top resid features:
|
Token | show |
Feature activation | +0.000 |
Top resid features:
|
Token | you |
Feature activation | +0.000 |
Top resid features:
|
Token | how |
Feature activation | +0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.000 |
Top resid features:
|
Token | composed |
Feature activation | -0.033 |
Top resid features:
|
Token | . |
Feature activation | +0.057 |
Top resid features:
|
Token | To |
Feature activation | -0.099 |
Top resid features:
|
Token | render |
Feature activation | -0.010 |
Top resid features:
|
Token | an |
Feature activation | +0.115 |
Top resid features:
|
Token | article |
Feature activation | +4.145 |
Top resid features:
|
Token | containing |
Feature activation | -0.070 |
Top resid features:
|
Token | both |
Feature activation | +0.000 |
Top resid features:
|
Token | R |
Feature activation | +0.000 |
Top resid features:
|
Token | plots |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | there |
Feature activation | -0.008 |
Top resid features:
|
Token | once |
Feature activation | -0.058 |
Top resid features:
|
Token | again |
Feature activation | -0.046 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.111 |
Top resid features:
|
Token | This |
Feature activation | -0.511 |
Top resid features:
|
Token | article |
Feature activation | +4.802 |
Top resid features:
|
Token | is |
Feature activation | -0.047 |
Top resid features:
|
Token | over |
Feature activation | +0.000 |
Top resid features:
|
Token | 2 |
Feature activation | +0.000 |
Top resid features:
|
Token | years |
Feature activation | +0.000 |
Top resid features:
|
Token | old |
Feature activation | +0.000 |
Top resid features:
|
Token | [ |
Feature activation | -0.028 |
Top resid features:
|
Token | Ed |
Feature activation | +0.013 |
Top resid features:
|
Token | note |
Feature activation | -0.057 |
Top resid features:
|
Token | : |
Feature activation | +0.107 |
Top resid features:
|
Token | This |
Feature activation | -0.547 |
Top resid features:
|
Token | article |
Feature activation | +4.508 |
Top resid features:
|
Token | was |
Feature activation | -0.023 |
Top resid features:
|
Token | updated |
Feature activation | +0.000 |
Top resid features:
|
Token | on |
Feature activation | +0.000 |
Top resid features:
|
Token | March |
Feature activation | +0.000 |
Top resid features:
|
Token | 2 |
Feature activation | +0.000 |
Top resid features:
|
Token | carrier |
Feature activation | -0.003 |
Top resid features:
|
Token | . |
Feature activation | +0.073 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.021 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.055 |
Top resid features:
|
Token | This |
Feature activation | -0.376 |
Top resid features:
|
Token | article |
Feature activation | +4.214 |
Top resid features:
|
Token | is |
Feature activation | -0.023 |
Top resid features:
|
Token | from |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | archive |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | Companies |
Feature activation | +0.042 |
Top resid features:
|
Token | : |
Feature activation | -0.009 |
Top resid features:
|
Token | apple |
Feature activation | +0.047 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.171 |
Top resid features:
|
Token | This |
Feature activation | -0.528 |
Top resid features:
|
Token | article |
Feature activation | +4.627 |
Top resid features:
|
Token | is |
Feature activation | -0.046 |
Top resid features:
|
Token | from |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | archive |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | scale |
Feature activation | -0.000 |
Top resid features:
|
Token | . |
Feature activation | +0.042 |
Top resid features:
|
Token | The |
Feature activation | -0.071 |
Top resid features:
|
Token | Washington |
Feature activation | +0.032 |
Top resid features:
|
Token | Post |
Feature activation | +0.503 |
Top resid features:
|
Token | article |
Feature activation | +3.524 |
Top resid features:
|
Token | cast |
Feature activation | +0.033 |
Top resid features:
|
Token | it |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | an |
Feature activation | +0.000 |
Top resid features:
|
Token | Orwell |
Feature activation | +0.000 |
Top resid features:
|
Token | 5 |
Feature activation | -0.035 |
Top resid features:
|
Token | . |
Feature activation | +0.074 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.026 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.057 |
Top resid features:
|
Token | This |
Feature activation | -0.365 |
Top resid features:
|
Token | article |
Feature activation | +4.290 |
Top resid features:
|
Token | is |
Feature activation | -0.025 |
Top resid features:
|
Token | from |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | archive |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | [ |
Feature activation | +0.013 |
Top resid features:
|
Token | 8 |
Feature activation | -0.076 |
Top resid features:
|
Token | ]. |
Feature activation | +0.184 |
Top resid features:
|
Token | In |
Feature activation | -0.114 |
Top resid features:
|
Token | this |
Feature activation | -0.075 |
Top resid features:
|
Token | article |
Feature activation | +3.582 |
Top resid features:
|
Token | , |
Feature activation | +0.149 |
Top resid features:
|
Token | based |
Feature activation | +0.000 |
Top resid features:
|
Token | on |
Feature activation | +0.000 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | talk |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | separate |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.023 |
Token | released |
Feature activation | +3.294 |
Token | on |
Feature activation | +0.078 |
Token | Thursday |
Feature activation | +0.067 |
Token | , |
Feature activation | +0.000 |
Token | Del |
Feature activation | +0.000 |
Token | ors |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.114 |
Token | was |
Feature activation | +2.358 |
Token | originally |
Feature activation | +1.904 |
Token | written |
Feature activation | +1.618 |
Token | for |
Feature activation | +0.134 |
Token | Science |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | ! |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.364 |
Token | by |
Feature activation | +2.528 |
Token | Af |
Feature activation | +0.617 |
Token | ro |
Feature activation | +0.000 |
Token | dit |
Feature activation | +0.000 |
Token | i |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.471 |
Token | does |
Feature activation | +2.578 |
Token | it |
Feature activation | +1.041 |
Token | acknowledge |
Feature activation | +0.978 |
Token | that |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | egregious |
Feature activation | +0.000 |
Token | because |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | was |
Feature activation | +2.386 |
Token | originally |
Feature activation | +1.916 |
Token | published |
Feature activation | +1.230 |
Token | on |
Feature activation | +0.000 |
Token | August |
Feature activation | +0.000 |
Token | 21 |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | From |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | same |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.068 |
Token | last |
Feature activation | +2.450 |
Token | year |
Feature activation | +2.273 |
Token | , |
Feature activation | +0.598 |
Token | written |
Feature activation | +0.635 |
Token | before |
Feature activation | +0.000 |
Token | NYPD |
Feature activation | +0.000 |
Token | 8 |
Feature activation | +0.000 |
Token | ]. |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.229 |
Token | , |
Feature activation | +2.033 |
Token | based |
Feature activation | +1.818 |
Token | on |
Feature activation | +0.719 |
Token | a |
Feature activation | +0.244 |
Token | talk |
Feature activation | +0.098 |
Token | given |
Feature activation | +0.000 |
Token | Egyptian |
Feature activation | +0.000 |
Token | Constitution |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.457 |
Token | calls |
Feature activation | +2.232 |
Token | for |
Feature activation | +0.472 |
Token | prison |
Feature activation | +0.090 |
Token | sentences |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | fines |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | , |
Feature activation | +2.346 |
Token | I |
Feature activation | +1.468 |
Token | will |
Feature activation | +1.032 |
Token | explain |
Feature activation | +0.704 |
Token | Goal |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | Ed |
Feature activation | +0.000 |
Token | note |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | was |
Feature activation | +2.121 |
Token | updated |
Feature activation | +1.495 |
Token | on |
Feature activation | +0.000 |
Token | March |
Feature activation | +0.000 |
Token | 2 |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | To |
Feature activation | +0.000 |
Token | render |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.128 |
Token | containing |
Feature activation | +2.146 |
Token | both |
Feature activation | +0.286 |
Token | R |
Feature activation | +0.000 |
Token | plots |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | diagrams |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | India |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.048 |
Token | was |
Feature activation | +1.960 |
Token | hailed |
Feature activation | +1.252 |
Token | as |
Feature activation | +0.000 |
Token | reaff |
Feature activation | +0.149 |
Token | irmation |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | chosen |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | focus |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | on |
Feature activation | +1.700 |
Token | trans |
Feature activation | +0.526 |
Token | women |
Feature activation | +0.000 |
Token | only |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | but |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.018 |
Token | I |
Feature activation | +1.766 |
Token | 'll |
Feature activation | +1.710 |
Token | just |
Feature activation | +0.469 |
Token | show |
Feature activation | +0.566 |
Token | some |
Feature activation | +0.065 |
Token | of |
Feature activation | +0.000 |
Token | om |
Feature activation | +0.000 |
Token | ials |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.175 |
Token | that |
Feature activation | +1.759 |
Token | appeared |
Feature activation | +1.057 |
Token | in |
Feature activation | +0.188 |
Token | 1980 |
Feature activation | +0.128 |
Token | .[ |
Feature activation | +0.000 |
Token | 4 |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | Newsweek |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.862 |
Token | published |
Feature activation | +1.795 |
Token | in |
Feature activation | +0.658 |
Token | February |
Feature activation | +0.587 |
Token | of |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | year |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | , |
Feature activation | +2.346 |
Token | I |
Feature activation | +1.468 |
Token | will |
Feature activation | +1.032 |
Token | explain |
Feature activation | +0.704 |
Token | Goal |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | Sales |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.114 |
Token | was |
Feature activation | +2.358 |
Token | originally |
Feature activation | +1.904 |
Token | written |
Feature activation | +1.618 |
Token | for |
Feature activation | +0.134 |
Token | Science |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | Relations |
Feature activation | +0.000 |
Token | hips |
Feature activation | +0.000 |
Token | issue |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | great |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.535 |
Token | " |
Feature activation | +0.075 |
Token | At |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Front |
Feature activation | +0.000 |
Token | ", |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.221 |
Token | will |
Feature activation | +2.147 |
Token | show |
Feature activation | +1.657 |
Token | you |
Feature activation | +0.469 |
Token | how |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | 'll |
Feature activation | +0.000 |
Token | find |
Feature activation | +0.000 |
Token | articles |
Feature activation | +0.047 |
Token | that |
Feature activation | +1.353 |
Token | are |
Feature activation | +1.330 |
Token | lists |
Feature activation | +0.215 |
Token | of |
Feature activation | +0.000 |
Token | things |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | most |
Feature activation | +0.000 |
Token | popular |
Feature activation | +0.000 |
Token | articles |
Feature activation | +0.057 |
Token | in |
Feature activation | +0.559 |
Token | recent |
Feature activation | +1.011 |
Token | months |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | list |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | law |
Feature activation | +0.000 |
Token | review |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | around |
Feature activation | +0.661 |
Token | that |
Feature activation | +1.071 |
Token | time |
Feature activation | +0.880 |
Token | . |
Feature activation | +0.000 |
Token | That |
Feature activation | +0.000 |
Token | translated |
Feature activation | +0.000 |
Token | into |
Feature activation | +0.000 |
Token | look |
Feature activation | +0.000 |
Token | ed |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | is |
Feature activation | +1.974 |
Token | well |
Feature activation | +1.243 |
Token | constructed |
Feature activation | +1.128 |
Token | and |
Feature activation | +0.000 |
Token | provides |
Feature activation | +0.000 |
Token | detail |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | why |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | think |
Feature activation | +0.000 |
Token | about |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | . |
Feature activation | +1.016 |
Token | Submit |
Feature activation | +0.649 |
Token | a |
Feature activation | +0.000 |
Token | letter |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | final |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | , |
Feature activation | +1.764 |
Token | I |
Feature activation | +1.157 |
Token | 'd |
Feature activation | +0.326 |
Token | like |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.090 |
Token | try |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | racist |
Feature activation | +0.000 |
Token | American |
Feature activation | +0.000 |
Token | Renaissance |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.000 |
Token | to |
Feature activation | +1.536 |
Token | his |
Feature activation | +0.695 |
Token | website |
Feature activation | +0.336 |
Token | before |
Feature activation | +0.000 |
Token | Dave |
Feature activation | +0.000 |
Token | Ag |
Feature activation | +0.000 |
Token | ema |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | newspapers |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | articles |
Feature activation | +0.000 |
Token | doesn |
Feature activation | +0.669 |
Token | 't |
Feature activation | +0.938 |
Token | harm |
Feature activation | +0.000 |
Token | standard |
Feature activation | +0.000 |
Token | Arabic |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | write |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | entire |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.261 |
Token | on |
Feature activation | +0.681 |
Token | the |
Feature activation | +0.888 |
Token | promise |
Feature activation | +0.225 |
Token | and |
Feature activation | +0.000 |
Token | peril |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | OK |
Feature activation | +0.000 |
Token | New |
Feature activation | +0.000 |
Token | sp |
Feature activation | +0.000 |
Token | aper |
Feature activation | +0.000 |
Token | articles |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.237 |
Token | the |
Feature activation | +0.867 |
Token | period |
Feature activation | +0.333 |
Token | reported |
Feature activation | +0.000 |
Token | strange |
Feature activation | +0.000 |
Token | rituals |
Feature activation | +0.000 |
Token | including |
Feature activation | +0.000 |
Token | relevant |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.159 |
Token | about |
Feature activation | +0.678 |
Token | the |
Feature activation | +0.862 |
Token | future |
Feature activation | +0.352 |
Token | of |
Feature activation | +0.000 |
Token | EVE |
Feature activation | +0.000 |
Token | Online |
Feature activation | +0.000 |
Token | ? |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.004 |
Token | and |
Feature activation | +1.647 |
Token | the |
Feature activation | +0.873 |
Token | possible |
Feature activation | +0.592 |
Token | match |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | copied |
Feature activation | +0.000 |
Token | text |
Feature activation | +0.000 |
Token | highlighted |
Feature activation | +0.000 |
Token | criticized |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | draft |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | Article |
Feature activation | +0.000 |
Token | 12 |
Feature activation | +0.472 |
Token | , |
Feature activation | +1.034 |
Token | which |
Feature activation | +1.065 |
Token | specifically |
Feature activation | +0.418 |
Token | addresses |
Feature activation | +0.274 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | Newsweek |
Feature activation | +0.000 |
Token | article |
Feature activation | +0.862 |
Token | published |
Feature activation | +1.795 |
Token | in |
Feature activation | +0.658 |
Token | February |
Feature activation | +0.587 |
Token | of |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | year |
Feature activation | +0.000 |
Token | outlined |
Feature activation | +0.000 |
Token | appiness |
Feature activation | +0.000 |
Token | over |
Feature activation | +0.000 |
Token | some |
Feature activation | +0.000 |
Token | articles |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.880 |
Token | Mr |
Feature activation | +0.369 |
Token | . |
Feature activation | +0.000 |
Token | Nord |
Feature activation | +0.000 |
Token | land |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | November |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | piece |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.468 |
Token | originally |
Feature activation | +0.213 |
Token | published |
Feature activation | +0.173 |
Token | in |
Feature activation | +0.000 |
Token | 2017 |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | ridiculed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | tech |
Feature activation | +0.000 |
Token | industry |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | not |
Feature activation | +0.000 |
Token | understanding |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | technologies |
Feature activation | +0.000 |
Token | she |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | Bart |
Feature activation | +0.000 |
Token | lett |
Feature activation | +0.000 |
Token | had |
Feature activation | +0.000 |
Token | helped |
Feature activation | +0.000 |
Token | create |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | pear |
Feature activation | +0.000 |
Token | variety |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Executive |
Feature activation | +0.000 |
Token | Branch |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | place |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | information |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | its |
Feature activation | +0.000 |
Token | website |
Feature activation | +0.000 |
Token | only |
Feature activation | +0.000 |
Token | received |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | first |
Feature activation | +0.000 |
Token | booking |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | third |
Feature activation | +0.000 |
Token | minute |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | injury |
Feature activation | +0.000 |
Token | interpreted |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | running |
Feature activation | +0.000 |
Token | ( |
Feature activation | +0.000 |
Token | mostly |
Feature activation | +0.000 |
Token | ) |
Feature activation | +0.000 |
Token | from |
Feature activation | +0.000 |
Token | money |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | output |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.862 |
Token | will |
Feature activation | +3.054 |
Token | start |
Feature activation | +2.942 |
Token | in |
Feature activation | +1.247 |
Token | 8 |
Feature activation | +0.329 |
Token | Cancel |
Feature activation | +1.127 |
Token | Ċ |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.862 |
Token | will |
Feature activation | +3.054 |
Token | start |
Feature activation | +2.942 |
Token | in |
Feature activation | +1.247 |
Token | 8 |
Feature activation | +0.329 |
Token | Cancel |
Feature activation | +1.127 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | That |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | how |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.717 |
Token | begins |
Feature activation | +2.825 |
Token | on |
Feature activation | +1.325 |
Token | Time |
Feature activation | +0.550 |
Token | Magazine |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | website |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.092 |
Token | is |
Feature activation | +2.399 |
Token | from |
Feature activation | +1.740 |
Token | MSNBC |
Feature activation | +0.592 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | racist |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.468 |
Token | shows |
Feature activation | +2.371 |
Token | Weinstein |
Feature activation | +1.288 |
Token | attempting |
Feature activation | +0.399 |
Token | to |
Feature activation | +0.059 |
Token | respond |
Feature activation | +0.171 |
Token | to |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.495 |
Token | , |
Feature activation | +2.286 |
Token | F |
Feature activation | +1.253 |
Token | oval |
Feature activation | +0.463 |
Token | is |
Feature activation | +0.000 |
Token | heard |
Feature activation | +0.033 |
Token | saying |
Feature activation | +0.154 |
Token | can |
Feature activation | +0.000 |
Token | watch |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.519 |
Token | that |
Feature activation | +1.934 |
Token | shows |
Feature activation | +2.262 |
Token | a |
Feature activation | +0.626 |
Token | docking |
Feature activation | +0.581 |
Token | here |
Feature activation | +0.000 |
Token | .) |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | about |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.534 |
Token | was |
Feature activation | +2.261 |
Token | getting |
Feature activation | +1.728 |
Token | thousands |
Feature activation | +0.154 |
Token | of |
Feature activation | +0.000 |
Token | views |
Feature activation | +0.006 |
Token | a |
Feature activation | +0.000 |
Token | rolling |
Feature activation | +0.000 |
Token | out |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.212 |
Token | introducing |
Feature activation | +2.177 |
Token | people |
Feature activation | +0.786 |
Token | to |
Feature activation | +0.000 |
Token | somebody |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Vancouver |
Feature activation | +0.000 |
Token | location |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.595 |
Token | was |
Feature activation | +2.125 |
Token | captured |
Feature activation | +1.818 |
Token | and |
Feature activation | +0.697 |
Token | later |
Feature activation | +0.622 |
Token | re |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | turn |
Feature activation | +0.000 |
Token | over |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.279 |
Token | as |
Feature activation | +2.097 |
Token | part |
Feature activation | +2.080 |
Token | of |
Feature activation | +0.088 |
Token | the |
Feature activation | +0.230 |
Token | National |
Feature activation | +0.000 |
Token | Labor |
Feature activation | +0.000 |
Token | speeds |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.523 |
Token | above |
Feature activation | +2.095 |
Token | , |
Feature activation | +1.179 |
Token | the |
Feature activation | +1.106 |
Token | team |
Feature activation | +0.402 |
Token | at |
Feature activation | +0.000 |
Token | Civil |
Feature activation | +0.000 |
Token | can |
Feature activation | +0.000 |
Token | understand |
Feature activation | +0.000 |
Token | why |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.080 |
Token | was |
Feature activation | +2.093 |
Token | so |
Feature activation | +0.929 |
Token | popular |
Feature activation | +0.765 |
Token | : |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | turn |
Feature activation | +0.000 |
Token | over |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.279 |
Token | as |
Feature activation | +2.097 |
Token | part |
Feature activation | +2.080 |
Token | of |
Feature activation | +0.088 |
Token | the |
Feature activation | +0.230 |
Token | National |
Feature activation | +0.000 |
Token | Labor |
Feature activation | +0.000 |
Token | Relations |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.320 |
Token | , |
Feature activation | +1.992 |
Token | published |
Feature activation | +2.076 |
Token | by |
Feature activation | +0.349 |
Token | Buzz |
Feature activation | +0.000 |
Token | feed |
Feature activation | +0.000 |
Token | News |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | 2005 |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.422 |
Token | , |
Feature activation | +2.062 |
Token | Trump |
Feature activation | +0.764 |
Token | can |
Feature activation | +0.018 |
Token | be |
Feature activation | +0.000 |
Token | heard |
Feature activation | +0.000 |
Token | making |
Feature activation | +0.000 |
Token | December |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | shocking |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.000 |
Token | emerged |
Feature activation | +2.046 |
Token | of |
Feature activation | +0.034 |
Token | Syrian |
Feature activation | +0.483 |
Token | rebels |
Feature activation | +0.228 |
Token | testing |
Feature activation | +0.000 |
Token | what |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ŀ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.042 |
Token | demonstrates |
Feature activation | +2.026 |
Token | mathematical |
Feature activation | +0.197 |
Token | proof |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | absence |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.320 |
Token | , |
Feature activation | +1.992 |
Token | published |
Feature activation | +2.076 |
Token | by |
Feature activation | +0.349 |
Token | Buzz |
Feature activation | +0.000 |
Token | feed |
Feature activation | +0.000 |
Token | News |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | June |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.192 |
Token | promoting |
Feature activation | +1.958 |
Token | a |
Feature activation | +1.227 |
Token | book |
Feature activation | +0.133 |
Token | by |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | active |
Feature activation | +0.000 |
Token | How |
Feature activation | -0.004 |
Top resid features:
|
Token | have |
Feature activation | +0.009 |
Top resid features:
|
Token | you |
Feature activation | +0.018 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.134 |
Top resid features:
|
Token | The |
Feature activation | -0.038 |
Top resid features:
|
Token | video |
Feature activation | +3.271 |
Top resid features:
|
Token | will |
Feature activation | +0.020 |
Top resid features:
|
Token | start |
Feature activation | +0.000 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | 8 |
Feature activation | +0.000 |
Top resid features:
|
Token | Cancel |
Feature activation | +0.000 |
Top resid features:
|
Token | How |
Feature activation | +0.045 |
Top resid features:
|
Token | have |
Feature activation | +0.026 |
Top resid features:
|
Token | you |
Feature activation | +0.005 |
Top resid features:
|
Token | <|endoftext|> |
Feature activation | -0.103 |
Top resid features:
|
Token | The |
Feature activation | -0.019 |
Top resid features:
|
Token | video |
Feature activation | +3.114 |
Top resid features:
|
Token | will |
Feature activation | +0.027 |
Top resid features:
|
Token | start |
Feature activation | -0.053 |
Top resid features:
|
Token | in |
Feature activation | +0.000 |
Top resid features:
|
Token | 8 |
Feature activation | +0.000 |
Top resid features:
|
Token | Cancel |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.026 |
Top resid features:
|
Token | That |
Feature activation | -0.049 |
Top resid features:
|
Token | 's |
Feature activation | +0.000 |
Top resid features:
|
Token | how |
Feature activation | +0.062 |
Top resid features:
|
Token | a |
Feature activation | +0.005 |
Top resid features:
|
Token | video |
Feature activation | +3.186 |
Top resid features:
|
Token | begins |
Feature activation | -0.105 |
Top resid features:
|
Token | on |
Feature activation | +0.000 |
Top resid features:
|
Token | Time |
Feature activation | +0.000 |
Top resid features:
|
Token | Magazine |
Feature activation | +0.000 |
Top resid features:
|
Token | 's |
Feature activation | +0.000 |
Top resid features:
|
Token | concluded |
Feature activation | +0.019 |
Top resid features:
|
Token | . |
Feature activation | -0.014 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.057 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.083 |
Top resid features:
|
Token | This |
Feature activation | -0.091 |
Top resid features:
|
Token | video |
Feature activation | +2.729 |
Top resid features:
|
Token | is |
Feature activation | -0.022 |
Top resid features:
|
Token | from |
Feature activation | +0.000 |
Top resid features:
|
Token | MSNBC |
Feature activation | +0.000 |
Top resid features:
|
Token | âĢ |
Feature activation | +0.000 |
Top resid features:
|
Token | Ļ |
Feature activation | +0.000 |
Top resid features:
|
Token | remarks |
Feature activation | +0.041 |
Top resid features:
|
Token | as |
Feature activation | -0.039 |
Top resid features:
|
Token | racist |
Feature activation | -0.006 |
Top resid features:
|
Token | . |
Feature activation | -0.086 |
Top resid features:
|
Token | A |
Feature activation | -0.056 |
Top resid features:
|
Token | video |
Feature activation | +2.650 |
Top resid features:
|
Token | shows |
Feature activation | -0.009 |
Top resid features:
|
Token | Weinstein |
Feature activation | +0.000 |
Top resid features:
|
Token | attempting |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | respond |
Feature activation | +0.000 |
Top resid features:
|
Token | Ŀ |
Feature activation | -0.042 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.051 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.074 |
Top resid features:
|
Token | In |
Feature activation | +0.034 |
Top resid features:
|
Token | the |
Feature activation | +0.088 |
Top resid features:
|
Token | video |
Feature activation | +2.744 |
Top resid features:
|
Token | , |
Feature activation | -0.048 |
Top resid features:
|
Token | F |
Feature activation | +0.000 |
Top resid features:
|
Token | oval |
Feature activation | +0.000 |
Top resid features:
|
Token | is |
Feature activation | +0.000 |
Top resid features:
|
Token | heard |
Feature activation | +0.000 |
Top resid features:
|
Token | ( |
Feature activation | +0.002 |
Top resid features:
|
Token | You |
Feature activation | -0.037 |
Top resid features:
|
Token | can |
Feature activation | +0.057 |
Top resid features:
|
Token | watch |
Feature activation | +0.059 |
Top resid features:
|
Token | a |
Feature activation | +0.005 |
Top resid features:
|
Token | video |
Feature activation | +2.549 |
Top resid features:
|
Token | that |
Feature activation | -0.197 |
Top resid features:
|
Token | shows |
Feature activation | -0.018 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | docking |
Feature activation | +0.000 |
Top resid features:
|
Token | here |
Feature activation | +0.000 |
Top resid features:
|
Token | something |
Feature activation | +0.010 |
Top resid features:
|
Token | about |
Feature activation | +0.043 |
Top resid features:
|
Token | this |
Feature activation | +0.007 |
Top resid features:
|
Token | . |
Feature activation | -0.095 |
Top resid features:
|
Token | The |
Feature activation | -0.108 |
Top resid features:
|
Token | video |
Feature activation | +2.451 |
Top resid features:
|
Token | was |
Feature activation | -0.007 |
Top resid features:
|
Token | getting |
Feature activation | +0.000 |
Top resid features:
|
Token | thousands |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | views |
Feature activation | +0.000 |
Top resid features:
|
Token | are |
Feature activation | -0.016 |
Top resid features:
|
Token | rolling |
Feature activation | -0.056 |
Top resid features:
|
Token | out |
Feature activation | -0.030 |
Top resid features:
|
Token | a |
Feature activation | +0.002 |
Top resid features:
|
Token | new |
Feature activation | -0.067 |
Top resid features:
|
Token | video |
Feature activation | +2.556 |
Top resid features:
|
Token | introducing |
Feature activation | -0.056 |
Top resid features:
|
Token | people |
Feature activation | +0.000 |
Top resid features:
|
Token | to |
Feature activation | +0.000 |
Top resid features:
|
Token | somebody |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | downtown |
Feature activation | -0.010 |
Top resid features:
|
Token | Vancouver |
Feature activation | -0.000 |
Top resid features:
|
Token | location |
Feature activation | -0.020 |
Top resid features:
|
Token | . |
Feature activation | -0.075 |
Top resid features:
|
Token | The |
Feature activation | -0.105 |
Top resid features:
|
Token | video |
Feature activation | +2.422 |
Top resid features:
|
Token | was |
Feature activation | +0.020 |
Top resid features:
|
Token | captured |
Feature activation | +0.000 |
Top resid features:
|
Token | and |
Feature activation | +0.000 |
Top resid features:
|
Token | later |
Feature activation | +0.000 |
Top resid features:
|
Token | re |
Feature activation | +0.000 |
Top resid features:
|
Token | compelled |
Feature activation | -0.028 |
Top resid features:
|
Token | to |
Feature activation | -0.018 |
Top resid features:
|
Token | turn |
Feature activation | -0.101 |
Top resid features:
|
Token | over |
Feature activation | -0.051 |
Top resid features:
|
Token | the |
Feature activation | -0.117 |
Top resid features:
|
Token | video |
Feature activation | +2.785 |
Top resid features:
|
Token | as |
Feature activation | -0.095 |
Top resid features:
|
Token | part |
Feature activation | +0.000 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | National |
Feature activation | +0.000 |
Top resid features:
|
Token | high |
Feature activation | +0.002 |
Top resid features:
|
Token | speeds |
Feature activation | +0.012 |
Top resid features:
|
Token | . |
Feature activation | -0.031 |
Top resid features:
|
Token | In |
Feature activation | -0.073 |
Top resid features:
|
Token | the |
Feature activation | +0.040 |
Top resid features:
|
Token | video |
Feature activation | +2.419 |
Top resid features:
|
Token | above |
Feature activation | -0.017 |
Top resid features:
|
Token | , |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | team |
Feature activation | +0.000 |
Top resid features:
|
Token | at |
Feature activation | +0.000 |
Top resid features:
|
Token | One |
Feature activation | -0.091 |
Top resid features:
|
Token | can |
Feature activation | +0.042 |
Top resid features:
|
Token | understand |
Feature activation | +0.046 |
Top resid features:
|
Token | why |
Feature activation | -0.124 |
Top resid features:
|
Token | this |
Feature activation | -0.049 |
Top resid features:
|
Token | video |
Feature activation | +2.448 |
Top resid features:
|
Token | was |
Feature activation | +0.001 |
Top resid features:
|
Token | so |
Feature activation | +0.000 |
Top resid features:
|
Token | popular |
Feature activation | +0.000 |
Top resid features:
|
Token | : |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | +0.000 |
Top resid features:
|
Token | compelled |
Feature activation | -0.014 |
Top resid features:
|
Token | to |
Feature activation | -0.024 |
Top resid features:
|
Token | turn |
Feature activation | -0.102 |
Top resid features:
|
Token | over |
Feature activation | -0.038 |
Top resid features:
|
Token | the |
Feature activation | -0.052 |
Top resid features:
|
Token | video |
Feature activation | +2.681 |
Top resid features:
|
Token | as |
Feature activation | -0.078 |
Top resid features:
|
Token | part |
Feature activation | -0.030 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | the |
Feature activation | +0.000 |
Top resid features:
|
Token | National |
Feature activation | +0.000 |
Top resid features:
|
Token | salute |
Feature activation | -0.013 |
Top resid features:
|
Token | . |
Feature activation | -0.013 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.049 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.065 |
Top resid features:
|
Token | The |
Feature activation | -0.013 |
Top resid features:
|
Token | video |
Feature activation | +2.596 |
Top resid features:
|
Token | , |
Feature activation | -0.158 |
Top resid features:
|
Token | published |
Feature activation | -0.120 |
Top resid features:
|
Token | by |
Feature activation | +0.000 |
Top resid features:
|
Token | Buzz |
Feature activation | +0.000 |
Top resid features:
|
Token | feed |
Feature activation | +0.000 |
Top resid features:
|
Token | from |
Feature activation | -0.017 |
Top resid features:
|
Token | 2005 |
Feature activation | -0.054 |
Top resid features:
|
Token | . |
Feature activation | -0.048 |
Top resid features:
|
Token | In |
Feature activation | -0.049 |
Top resid features:
|
Token | the |
Feature activation | +0.025 |
Top resid features:
|
Token | video |
Feature activation | +2.227 |
Top resid features:
|
Token | , |
Feature activation | -0.049 |
Top resid features:
|
Token | Trump |
Feature activation | +0.000 |
Top resid features:
|
Token | can |
Feature activation | +0.000 |
Top resid features:
|
Token | be |
Feature activation | +0.000 |
Top resid features:
|
Token | heard |
Feature activation | +0.000 |
Top resid features:
|
Token | In |
Feature activation | -0.044 |
Top resid features:
|
Token | December |
Feature activation | -0.020 |
Top resid features:
|
Token | , |
Feature activation | -0.007 |
Top resid features:
|
Token | a |
Feature activation | +0.024 |
Top resid features:
|
Token | shocking |
Feature activation | -0.115 |
Top resid features:
|
Token | video |
Feature activation | +2.591 |
Top resid features:
|
Token | emerged |
Feature activation | -0.140 |
Top resid features:
|
Token | of |
Feature activation | +0.000 |
Top resid features:
|
Token | Syrian |
Feature activation | +0.000 |
Top resid features:
|
Token | rebels |
Feature activation | +0.000 |
Top resid features:
|
Token | testing |
Feature activation | +0.000 |
Top resid features:
|
Token | H |
Feature activation | -0.013 |
Top resid features:
|
Token | . |
Feature activation | -0.032 |
Top resid features:
|
Token | âĢ |
Feature activation | -0.013 |
Top resid features:
|
Token | Ŀ |
Feature activation | -0.028 |
Top resid features:
|
Token | This |
Feature activation | -0.183 |
Top resid features:
|
Token | video |
Feature activation | +2.603 |
Top resid features:
|
Token | demonstrates |
Feature activation | -0.088 |
Top resid features:
|
Token | mathematical |
Feature activation | +0.000 |
Top resid features:
|
Token | proof |
Feature activation | +0.000 |
Top resid features:
|
Token | that |
Feature activation | +0.000 |
Top resid features:
|
Token | absence |
Feature activation | +0.000 |
Top resid features:
|
Token | salute |
Feature activation | -0.021 |
Top resid features:
|
Token | . |
Feature activation | -0.015 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.063 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.096 |
Top resid features:
|
Token | The |
Feature activation | -0.028 |
Top resid features:
|
Token | video |
Feature activation | +2.406 |
Top resid features:
|
Token | , |
Feature activation | -0.101 |
Top resid features:
|
Token | published |
Feature activation | +0.000 |
Top resid features:
|
Token | by |
Feature activation | +0.000 |
Top resid features:
|
Token | Buzz |
Feature activation | +0.000 |
Top resid features:
|
Token | feed |
Feature activation | +0.000 |
Top resid features:
|
Token | Ċ |
Feature activation | -0.041 |
Top resid features:
|
Token | In |
Feature activation | -0.027 |
Top resid features:
|
Token | June |
Feature activation | -0.047 |
Top resid features:
|
Token | , |
Feature activation | -0.004 |
Top resid features:
|
Token | a |
Feature activation | -0.008 |
Top resid features:
|
Token | video |
Feature activation | +2.372 |
Top resid features:
|
Token | promoting |
Feature activation | -0.132 |
Top resid features:
|
Token | a |
Feature activation | +0.000 |
Top resid features:
|
Token | book |
Feature activation | +0.000 |
Top resid features:
|
Token | by |
Feature activation | +0.000 |
Top resid features:
|
Token | an |
Feature activation | +0.000 |
Top resid features:
|
Token | That |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | how |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.717 |
Token | begins |
Feature activation | +2.825 |
Token | on |
Feature activation | +1.325 |
Token | Time |
Feature activation | +0.550 |
Token | Magazine |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | website |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.862 |
Token | will |
Feature activation | +3.054 |
Token | start |
Feature activation | +2.942 |
Token | in |
Feature activation | +1.247 |
Token | 8 |
Feature activation | +0.329 |
Token | Cancel |
Feature activation | +1.127 |
Token | Ċ |
Feature activation | +0.000 |
Token | you |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.862 |
Token | will |
Feature activation | +3.054 |
Token | start |
Feature activation | +2.942 |
Token | in |
Feature activation | +1.247 |
Token | 8 |
Feature activation | +0.329 |
Token | Cancel |
Feature activation | +1.127 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.495 |
Token | , |
Feature activation | +2.286 |
Token | F |
Feature activation | +1.253 |
Token | oval |
Feature activation | +0.463 |
Token | is |
Feature activation | +0.000 |
Token | heard |
Feature activation | +0.033 |
Token | saying |
Feature activation | +0.154 |
Token | rolling |
Feature activation | +0.000 |
Token | out |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.212 |
Token | introducing |
Feature activation | +2.177 |
Token | people |
Feature activation | +0.786 |
Token | to |
Feature activation | +0.000 |
Token | somebody |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | can |
Feature activation | +0.000 |
Token | watch |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.519 |
Token | that |
Feature activation | +1.934 |
Token | shows |
Feature activation | +2.262 |
Token | a |
Feature activation | +0.626 |
Token | docking |
Feature activation | +0.581 |
Token | here |
Feature activation | +0.000 |
Token | .) |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.092 |
Token | is |
Feature activation | +2.399 |
Token | from |
Feature activation | +1.740 |
Token | MSNBC |
Feature activation | +0.592 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | s |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | racist |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.468 |
Token | shows |
Feature activation | +2.371 |
Token | Weinstein |
Feature activation | +1.288 |
Token | attempting |
Feature activation | +0.399 |
Token | to |
Feature activation | +0.059 |
Token | respond |
Feature activation | +0.171 |
Token | to |
Feature activation | +0.000 |
Token | You |
Feature activation | +0.000 |
Token | can |
Feature activation | +0.000 |
Token | watch |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.519 |
Token | that |
Feature activation | +1.934 |
Token | shows |
Feature activation | +2.262 |
Token | a |
Feature activation | +0.626 |
Token | docking |
Feature activation | +0.581 |
Token | here |
Feature activation | +0.000 |
Token | .) |
Feature activation | +0.000 |
Token | Warning |
Feature activation | +0.000 |
Token | : |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | following |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.316 |
Token | contains |
Feature activation | +1.956 |
Token | graphic |
Feature activation | +0.764 |
Token | content |
Feature activation | +0.617 |
Token | of |
Feature activation | +0.303 |
Token | a |
Feature activation | +0.691 |
Token | violent |
Feature activation | +0.280 |
Token | Vancouver |
Feature activation | +0.000 |
Token | location |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.595 |
Token | was |
Feature activation | +2.125 |
Token | captured |
Feature activation | +1.818 |
Token | and |
Feature activation | +0.697 |
Token | later |
Feature activation | +0.622 |
Token | re |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.320 |
Token | , |
Feature activation | +1.992 |
Token | published |
Feature activation | +2.076 |
Token | by |
Feature activation | +0.349 |
Token | Buzz |
Feature activation | +0.000 |
Token | feed |
Feature activation | +0.000 |
Token | News |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | turn |
Feature activation | +0.000 |
Token | over |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.279 |
Token | as |
Feature activation | +2.097 |
Token | part |
Feature activation | +2.080 |
Token | of |
Feature activation | +0.088 |
Token | the |
Feature activation | +0.230 |
Token | National |
Feature activation | +0.000 |
Token | Labor |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | action |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.300 |
Token | below |
Feature activation | +1.568 |
Token | : |
Feature activation | +0.215 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | * |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | this |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.534 |
Token | was |
Feature activation | +2.261 |
Token | getting |
Feature activation | +1.728 |
Token | thousands |
Feature activation | +0.154 |
Token | of |
Feature activation | +0.000 |
Token | views |
Feature activation | +0.006 |
Token | a |
Feature activation | +0.000 |
Token | day |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | fore |
Feature activation | +0.000 |
Token | thought |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.000 |
Token | the |
Feature activation | +1.758 |
Token | rat |
Feature activation | +1.595 |
Token | climbing |
Feature activation | +0.549 |
Token | on |
Feature activation | +0.000 |
Token | student |
Feature activation | +0.000 |
Token | desks |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.065 |
Token | documents |
Feature activation | +1.669 |
Token | nearly |
Feature activation | +0.667 |
Token | everything |
Feature activation | +0.808 |
Token | , |
Feature activation | +0.000 |
Token | as |
Feature activation | +0.000 |
Token | Crow |
Feature activation | +0.000 |
Token | ot |
Feature activation | +0.000 |
Token | says |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.122 |
Token | posted |
Feature activation | +1.702 |
Token | on |
Feature activation | +0.568 |
Token | Per |
Feature activation | +0.446 |
Token | ot |
Feature activation | +0.000 |
Token | Ch |
Feature activation | +0.000 |
Token | arts |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | Youtube |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.143 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +1.142 |
Token | main |
Feature activation | +1.470 |
Token | part |
Feature activation | +1.212 |
Token | of |
Feature activation | +0.141 |
Token | the |
Feature activation | +0.000 |
Token | confrontation |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | June |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.192 |
Token | promoting |
Feature activation | +1.958 |
Token | a |
Feature activation | +1.227 |
Token | book |
Feature activation | +0.133 |
Token | by |
Feature activation | +0.000 |
Token | an |
Feature activation | +0.000 |
Token | active |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | with |
Feature activation | +0.000 |
Token | 11 |
Feature activation | +0.000 |
Token | hours |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.461 |
Token | statements |
Feature activation | +1.231 |
Token | and |
Feature activation | +0.283 |
Token | more |
Feature activation | +0.865 |
Token | than |
Feature activation | +0.242 |
Token | 180 |
Feature activation | +0.264 |
Token | exhibits |
Feature activation | +0.157 |
Token | , |
Feature activation | +0.000 |
Token | had |
Feature activation | +0.000 |
Token | posted |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.488 |
Token | with |
Feature activation | +1.361 |
Token | her |
Feature activation | +1.155 |
Token | Indian |
Feature activation | +0.246 |
Token | - |
Feature activation | +0.000 |
Token | origin |
Feature activation | +0.000 |
Token | Swedish |
Feature activation | +0.000 |
Token | racist |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.468 |
Token | shows |
Feature activation | +2.371 |
Token | Weinstein |
Feature activation | +1.288 |
Token | attempting |
Feature activation | +0.399 |
Token | to |
Feature activation | +0.059 |
Token | respond |
Feature activation | +0.171 |
Token | to |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | already |
Feature activation | +0.000 |
Token | released |
Feature activation | +0.000 |
Token | videos |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.882 |
Token | show |
Feature activation | +1.043 |
Token | : |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | This |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | her |
Feature activation | +0.000 |
Token | announcement |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.024 |
Token | . |
Feature activation | +1.060 |
Token | " |
Feature activation | +0.000 |
Token | Because |
Feature activation | +0.000 |
Token | when |
Feature activation | +0.031 |
Token | families |
Feature activation | +0.000 |
Token | are |
Feature activation | +0.000 |
Token | ness |
Feature activation | +0.000 |
Token | sprites |
Feature activation | +0.000 |
Token | where |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.431 |
Token | processor |
Feature activation | +1.122 |
Token | does |
Feature activation | +0.379 |
Token | all |
Feature activation | +0.212 |
Token | the |
Feature activation | +0.282 |
Token | work |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | In |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.523 |
Token | above |
Feature activation | +2.095 |
Token | , |
Feature activation | +1.179 |
Token | the |
Feature activation | +1.106 |
Token | team |
Feature activation | +0.402 |
Token | at |
Feature activation | +0.000 |
Token | Civil |
Feature activation | +0.000 |
Token | Maps |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | link |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | her |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.262 |
Token | , |
Feature activation | +1.158 |
Token | writing |
Feature activation | +0.889 |
Token | : |
Feature activation | +0.000 |
Token | ' |
Feature activation | +0.000 |
Token | What |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | shot |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.183 |
Token | is |
Feature activation | +1.325 |
Token | the |
Feature activation | +1.321 |
Token | latest |
Feature activation | +0.854 |
Token | in |
Feature activation | +0.513 |
Token | a |
Feature activation | +0.492 |
Token | parade |
Feature activation | +0.057 |
Token | of |
Feature activation | +0.000 |
Token | PR |
Feature activation | +0.000 |
Token | ed |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.000 |
Token | were |
Feature activation | +1.075 |
Token | unimaginable |
Feature activation | +0.621 |
Token | . |
Feature activation | +0.000 |
Token | Though |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | comments |
Feature activation | +0.000 |
Token | have |
Feature activation | +0.000 |
Token | came |
Feature activation | +0.364 |
Token | along |
Feature activation | +0.000 |
Token | âĢĶ |
Feature activation | +0.001 |
Token | videos |
Feature activation | +0.088 |
Token | were |
Feature activation | +0.845 |
Token | passed |
Feature activation | +0.805 |
Token | around |
Feature activation | +0.380 |
Token | through |
Feature activation | +0.229 |
Token | download |
Feature activation | +0.000 |
Token | links |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.501 |
Token | has |
Feature activation | +1.845 |
Token | been |
Feature activation | +1.957 |
Token | widely |
Feature activation | +1.256 |
Token | condemned |
Feature activation | +0.735 |
Token | by |
Feature activation | +0.000 |
Token | Secretary |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | State |
Feature activation | +0.000 |
Token | Hillary |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Video |
Feature activation | +0.017 |
Token | Loading |
Feature activation | +0.000 |
Token | Video |
Feature activation | +0.279 |
Token | Un |
Feature activation | +1.256 |
Token | available |
Feature activation | +0.884 |
Token | Click |
Feature activation | +0.318 |
Token | to |
Feature activation | +0.000 |
Token | play |
Feature activation | +0.153 |
Token | Tap |
Feature activation | +0.333 |
Token | to |
Feature activation | +0.000 |
Token | Click |
Feature activation | +0.000 |
Token | through |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | slideshow |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.070 |
Token | see |
Feature activation | +0.405 |
Token | the |
Feature activation | +0.000 |
Token | full |
Feature activation | +0.000 |
Token | season |
Feature activation | +0.000 |
Token | 22 |
Feature activation | +0.000 |
Token | lineup |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | From |
Feature activation | +0.000 |
Token | Video |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.493 |
Token | Ċ |
Feature activation | +0.354 |
Token | The |
Feature activation | +0.293 |
Token | running |
Feature activation | +0.027 |
Token | play |
Feature activation | +0.000 |
Token | above |
Feature activation | +0.000 |
Token | has |
Feature activation | +0.000 |
Token | on |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.000 |
Token | over |
Feature activation | +1.260 |
Token | the |
Feature activation | +1.031 |
Token | course |
Feature activation | +0.378 |
Token | of |
Feature activation | +0.000 |
Token | creating |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | story |
Feature activation | +0.000 |
Token | board |
Feature activation | +0.000 |
Token | publicly |
Feature activation | +0.000 |
Token | available |
Feature activation | +0.000 |
Token | aerial |
Feature activation | +0.000 |
Token | photos |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.334 |
Token | . |
Feature activation | +0.831 |
Token | If |
Feature activation | +0.055 |
Token | a |
Feature activation | +0.000 |
Token | shark |
Feature activation | +0.000 |
Token | is |
Feature activation | +0.000 |
Token | Pa |
Feature activation | +0.000 |
Token | ik |
Feature activation | +0.000 |
Token | transformed |
Feature activation | +0.000 |
Token | video |
Feature activation | +0.000 |
Token | into |
Feature activation | +1.027 |
Token | a |
Feature activation | +0.532 |
Token | medium |
Feature activation | +0.000 |
Token | for |
Feature activation | +0.000 |
Token | art |
Feature activation | +0.000 |
Token | âĢĶ |
Feature activation | +0.000 |
Token | man |
Feature activation | +0.000 |
Token | up |
Feature activation | +0.000 |
Token | all |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | money |
Feature activation | +0.000 |
Token | owed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | all |
Feature activation | +0.000 |
Token | levels |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | government |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | new |
Feature activation | +0.000 |
Token | product |
Feature activation | +0.000 |
Token | ... |
Feature activation | +0.000 |
Token | we |
Feature activation | +0.000 |
Token | believe |
Feature activation | +0.000 |
Token | our |
Feature activation | +0.000 |
Token | device |
Feature activation | +0.000 |
Token | does |
Feature activation | +0.000 |
Token | not |
Feature activation | +0.000 |
Token | eject |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Earlier |
Feature activation | +0.000 |
Token | that |
Feature activation | +0.000 |
Token | day |
Feature activation | +0.000 |
Token | another |
Feature activation | +0.000 |
Token | Su |
Feature activation | +0.000 |
Token | - |
Feature activation | +0.000 |
Token | 25 |
Feature activation | +0.000 |
Token | was |
Feature activation | +0.000 |
Token | hit |
Feature activation | +0.000 |
Token | 's |
Feature activation | +0.000 |
Token | friend |
Feature activation | +0.000 |
Token | who |
Feature activation | +0.000 |
Token | offered |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | huge |
Feature activation | +0.000 |
Token | sum |
Feature activation | +0.000 |
Token | to |
Feature activation | +0.000 |
Token | his |
Feature activation | +0.000 |
Token | affiliate |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | and |
Feature activation | +0.000 |
Token | I |
Feature activation | +0.000 |
Token | âĢ |
Feature activation | +0.000 |
Token | Ļ |
Feature activation | +0.000 |
Token | m |
Feature activation | +0.000 |
Token | currently |
Feature activation | +0.000 |
Token | lim |
Feature activation | +0.000 |
Token | ping |
Feature activation | +0.000 |
Token | along |
Feature activation | +0.000 |
Token | in |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | Development |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | & |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Defence |
Feature activation | +0.000 |
Token | Research |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | <|endoftext|> |
Feature activation | +0.000 |
Token | rik |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | ar |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | said |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | A |
Feature activation | +0.000 |
Token | atre |
Feature activation | +0.000 |
Token | , |
Feature activation | +0.000 |
Token | a |
Feature activation | +0.000 |
Token | former |
Feature activation | +0.000 |
Token | boss |
Feature activation | +0.000 |
Token | of |
Feature activation | +0.000 |
Token | the |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | K |
Feature activation | +0.000 |
Token | Saturday |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | Ċ |
Feature activation | +0.000 |
Token | The |
Feature activation | +0.000 |
Token | defence |
Feature activation | +0.000 |
Token | ministry |
Feature activation | +0.000 |
Token | committee |
Feature activation | +0.000 |
Token | headed |
Feature activation | +0.000 |
Token | by |
Feature activation | +0.000 |
Token | V |
Feature activation | +0.000 |
Token | . |
Feature activation | +0.000 |