H2.9 top features

Top feature 0 in H2.9: (feature 21398)

TOP ACTIVATIONS
MAX = 2.514

is
Token is
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.437
to
Token to
Feature activation+2.514
respond
Token respond
Feature activation+1.868
,
Token,
Feature activation+0.311
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
G
Token G
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.443
was
Token was
Feature activation+2.292
hearing
Token hearing
Feature activation+1.513
an
Token an
Feature activation+0.762
appeal
Token appeal
Feature activation+0.130
filed
Token filed
Feature activation+0.321
by
Token by
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.274
concluded
Token concluded
Feature activation+2.175
the
Token the
Feature activation+1.137
state
Token state
Feature activation+1.029
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
was
Token was
Feature activation+0.000
flawed
Token flawed
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
court
Token court
Feature activation+0.507
can
Token can
Feature activation+2.081
dismiss
Token dismiss
Feature activation+1.913
the
Token the
Feature activation+0.242
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
uphold
Token uphold
Feature activation+0.151
Ļ
TokenĻ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.455
found
Token found
Feature activation+2.039
Wild
Token Wild
Feature activation+0.705
ers
Tokeners
Feature activation+0.000
not
Token not
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.548
found
Token found
Feature activation+1.991
the
Token the
Feature activation+1.084
mother
Token mother
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.298
found
Token found
Feature activation+1.978
the
Token the
Feature activation+1.225
argument
Token argument
Feature activation+0.584
intriguing
Token intriguing
Feature activation+0.000
enough
Token enough
Feature activation+0.000
that
Token that
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
This
TokenThis
Feature activation+0.000
court
Token court
Feature activation+0.000
has
Token has
Feature activation+1.925
found
Token found
Feature activation+1.671
that
Token that
Feature activation+0.143
Carter
Token Carter
Feature activation+0.000
's
Token's
Feature activation+0.000
actions
Token actions
Feature activation+0.000
flawed
Token flawed
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
court
Token court
Feature activation+0.507
can
Token can
Feature activation+2.081
dismiss
Token dismiss
Feature activation+1.913
the
Token the
Feature activation+0.242
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
uphold
Token uphold
Feature activation+0.151
the
Token the
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.437
to
Token to
Feature activation+2.514
respond
Token respond
Feature activation+1.868
,
Token,
Feature activation+0.311
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
G
Token G
Feature activation+0.000
orman
Tokenorman
Feature activation+0.000
was
Token was
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.367
to
Token to
Feature activation+1.858
administ
Token administ
Feature activation+1.099
rate
Tokenrate
Feature activation+0.345
the
Token the
Feature activation+0.491
settlement
Token settlement
Feature activation+0.132
,
Token,
Feature activation+0.019
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.544
ordered
Token ordered
Feature activation+1.829
ambassador
Token ambassador
Feature activation+0.466
Dan
Token Dan
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
le
Tokenle
Feature activation+0.000
M
Token M
Feature activation+0.000
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.000
Under
Token Under
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.382
's
Token's
Feature activation+1.816
interpretation
Token interpretation
Feature activation+0.553
of
Token of
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
law
Token law
Feature activation+0.000
,
Token,
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
High
TokenHigh
Feature activation+0.000
Court
Token Court
Feature activation+0.572
R
Token R
Feature activation+1.789
uling
Tokenuling
Feature activation+0.874
Ċ
TokenĊ
Feature activation+0.145
Ċ
TokenĊ
Feature activation+0.029
S
TokenS
Feature activation+0.000
oci
Tokenoci
Feature activation+0.000
women
Token women
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.099
goes
Token goes
Feature activation+1.783
along
Token along
Feature activation+1.015
,
Token,
Feature activation+0.419
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
is
Token is
Feature activation+0.000
ambiguous
Token ambiguous
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.390
said
Token said
Feature activation+1.777
.
Token.
Feature activation+0.921
It
Token It
Feature activation+0.277
has
Token has
Feature activation+0.450
80
Token 80
Feature activation+0.159
different
Token different
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
court
Token court
Feature activation+0.000
,
Token,
Feature activation+1.713
lawyers
Token lawyers
Feature activation+0.032
representing
Token representing
Feature activation+0.000
Er
Token Er
Feature activation+0.000
de
Tokende
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
agan
Tokenagan
Feature activation+0.000
will
Token will
Feature activation+0.000
face
Token face
Feature activation+0.000
court
Token court
Feature activation+0.000
on
Token on
Feature activation+1.492
the
Token the
Feature activation+1.701
criminal
Token criminal
Feature activation+0.811
charges
Token charges
Feature activation+0.000
in
Token in
Feature activation+0.000
relation
Token relation
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
This
TokenThis
Feature activation+0.000
court
Token court
Feature activation+0.000
has
Token has
Feature activation+1.925
found
Token found
Feature activation+1.671
that
Token that
Feature activation+0.143
Carter
Token Carter
Feature activation+0.000
's
Token's
Feature activation+0.000
actions
Token actions
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.321
ruled
Token ruled
Feature activation+1.654
that
Token that
Feature activation+0.119
was
Token was
Feature activation+0.582
wrong
Token wrong
Feature activation+0.176
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

Top DFA by src position
MAX = 3.642

it
Token it
Feature activation+0.080
Top resid features:
is
Token is
Feature activation+0.030
Top resid features:
up
Token up
Feature activation+0.116
Top resid features:
to
Token to
Feature activation-0.042
Top resid features:
the
Token the
Feature activation+0.168
Top resid features:
court
Token court
Feature activation+3.642
Top resid features:
to
Token to
Feature activation+0.042
Top resid features:
respond
Token respond
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
said
Token said
Feature activation+0.037
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
The
TokenThe
Feature activation+0.209
Top resid features:
court
Token court
Feature activation+3.146
Top resid features:
was
Token was
Feature activation+0.107
Top resid features:
hearing
Token hearing
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
appeal
Token appeal
Feature activation+0.000
Top resid features:
filed
Token filed
Feature activation+0.000
Top resid features:
movement
Token movement
Feature activation+0.035
Top resid features:
.
Token.
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
The
TokenThe
Feature activation+0.192
Top resid features:
court
Token court
Feature activation+3.603
Top resid features:
concluded
Token concluded
Feature activation-0.013
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
state
Token state
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
maintained
Token maintained
Feature activation+0.003
Top resid features:
was
Token was
Feature activation+0.031
Top resid features:
flawed
Token flawed
Feature activation+0.030
Top resid features:
.
Token.
Feature activation+0.071
Top resid features:
The
Token The
Feature activation+0.259
Top resid features:
court
Token court
Feature activation+3.293
Top resid features:
can
Token can
Feature activation+0.154
Top resid features:
dismiss
Token dismiss
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
cases
Token cases
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.013
Top resid features:
Ļ
TokenĻ
Feature activation-0.017
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.038
Top resid features:
The
TokenThe
Feature activation+0.129
Top resid features:
court
Token court
Feature activation+3.160
Top resid features:
found
Token found
Feature activation-0.009
Top resid features:
Wild
Token Wild
Feature activation+0.000
Top resid features:
ers
Tokeners
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
guilty
Token guilty
Feature activation+0.000
Top resid features:
father
Token father
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.039
Top resid features:
The
TokenThe
Feature activation+0.136
Top resid features:
court
Token court
Feature activation+2.943
Top resid features:
found
Token found
Feature activation+0.010
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
mother
Token mother
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
charged
Token charged
Feature activation+0.010
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
However
Token However
Feature activation+0.049
Top resid features:
,
Token,
Feature activation+0.014
Top resid features:
the
Token the
Feature activation+0.167
Top resid features:
court
Token court
Feature activation+2.963
Top resid features:
found
Token found
Feature activation+0.087
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
argument
Token argument
Feature activation+0.000
Top resid features:
intriguing
Token intriguing
Feature activation+0.000
Top resid features:
enough
Token enough
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
"
Token"
Feature activation-0.036
Top resid features:
This
TokenThis
Feature activation+0.221
Top resid features:
court
Token court
Feature activation+3.128
Top resid features:
has
Token has
Feature activation+0.019
Top resid features:
found
Token found
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Carter
Token Carter
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
maintained
Token maintained
Feature activation+0.004
Top resid features:
was
Token was
Feature activation+0.029
Top resid features:
flawed
Token flawed
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
The
Token The
Feature activation+0.202
Top resid features:
court
Token court
Feature activation+2.931
Top resid features:
can
Token can
Feature activation+0.267
Top resid features:
dismiss
Token dismiss
Feature activation+0.123
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
cases
Token cases
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.088
Top resid features:
is
Token is
Feature activation+0.038
Top resid features:
up
Token up
Feature activation+0.097
Top resid features:
to
Token to
Feature activation-0.029
Top resid features:
the
Token the
Feature activation+0.135
Top resid features:
court
Token court
Feature activation+2.768
Top resid features:
to
Token to
Feature activation+0.135
Top resid features:
respond
Token respond
Feature activation+0.057
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.039
Top resid features:
was
Token was
Feature activation+0.035
Top resid features:
appointed
Token appointed
Feature activation+0.123
Top resid features:
by
Token by
Feature activation+0.090
Top resid features:
the
Token the
Feature activation+0.184
Top resid features:
court
Token court
Feature activation+2.771
Top resid features:
to
Token to
Feature activation+0.080
Top resid features:
administ
Token administ
Feature activation+0.000
Top resid features:
rate
Tokenrate
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
settlement
Token settlement
Feature activation+0.000
Top resid features:
decision
Token decision
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
Ċ
TokenĊ
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.041
Top resid features:
The
TokenThe
Feature activation+0.238
Top resid features:
court
Token court
Feature activation+2.603
Top resid features:
ordered
Token ordered
Feature activation+0.139
Top resid features:
ambassador
Token ambassador
Feature activation+0.000
Top resid features:
Dan
Token Dan
Feature activation+0.000
Top resid features:
ie
Tokenie
Feature activation+0.000
Top resid features:
le
Tokenle
Feature activation+0.000
Top resid features:
seven
Token seven
Feature activation+0.050
Top resid features:
men
Token men
Feature activation+0.020
Top resid features:
.
Token.
Feature activation+0.030
Top resid features:
Under
Token Under
Feature activation-0.092
Top resid features:
the
Token the
Feature activation+0.143
Top resid features:
court
Token court
Feature activation+3.007
Top resid features:
's
Token's
Feature activation+0.036
Top resid features:
interpretation
Token interpretation
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Islamic
Token Islamic
Feature activation+0.000
Top resid features:
law
Token law
Feature activation+0.000
Top resid features:
neighborhoods
Token neighborhoods
Feature activation-0.036
Top resid features:
.
Token.
Feature activation+0.012
Top resid features:
Ċ
TokenĊ
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation+0.055
Top resid features:
High
TokenHigh
Feature activation+0.029
Top resid features:
Court
Token Court
Feature activation+3.026
Top resid features:
R
Token R
Feature activation+0.097
Top resid features:
uling
Tokenuling
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation+0.000
Top resid features:
benefit
Token benefit
Feature activation+0.016
Top resid features:
women
Token women
Feature activation-0.026
Top resid features:
.
Token.
Feature activation+0.040
Top resid features:
If
Token If
Feature activation+0.028
Top resid features:
the
Token the
Feature activation+0.153
Top resid features:
court
Token court
Feature activation+2.879
Top resid features:
goes
Token goes
Feature activation+0.068
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
could
Token could
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.007
Top resid features:
is
Token is
Feature activation+0.033
Top resid features:
ambiguous
Token ambiguous
Feature activation-0.036
Top resid features:
,
Token,
Feature activation-0.017
Top resid features:
the
Token the
Feature activation+0.218
Top resid features:
court
Token court
Feature activation+2.709
Top resid features:
said
Token said
Feature activation+0.227
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
It
Token It
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
80
Token 80
Feature activation+0.000
Top resid features:
victims
Token victims
Feature activation+0.017
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.066
Top resid features:
Ċ
TokenĊ
Feature activation+0.065
Top resid features:
In
TokenIn
Feature activation+0.090
Top resid features:
court
Token court
Feature activation+2.867
Top resid features:
,
Token,
Feature activation+0.082
Top resid features:
lawyers
Token lawyers
Feature activation+0.000
Top resid features:
representing
Token representing
Feature activation+0.000
Top resid features:
Er
Token Er
Feature activation+0.000
Top resid features:
de
Tokende
Feature activation+0.000
Top resid features:
Fl
TokenFl
Feature activation+0.031
Top resid features:
an
Tokenan
Feature activation+0.008
Top resid features:
agan
Tokenagan
Feature activation-0.034
Top resid features:
will
Token will
Feature activation+0.015
Top resid features:
face
Token face
Feature activation+0.048
Top resid features:
court
Token court
Feature activation+2.615
Top resid features:
on
Token on
Feature activation+0.333
Top resid features:
the
Token the
Feature activation+0.099
Top resid features:
criminal
Token criminal
Feature activation+0.000
Top resid features:
charges
Token charges
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
"
Token"
Feature activation-0.031
Top resid features:
This
TokenThis
Feature activation+0.127
Top resid features:
court
Token court
Feature activation+2.848
Top resid features:
has
Token has
Feature activation+0.057
Top resid features:
found
Token found
Feature activation+0.070
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
Carter
Token Carter
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.013
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
The
TokenThe
Feature activation+0.202
Top resid features:
court
Token court
Feature activation+2.645
Top resid features:
ruled
Token ruled
Feature activation-0.013
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
wrong
Token wrong
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.07

Head 2: 0.06

Head 3: 0.06

Head 4: 0.05

Head 5: 0.10

Head 6: 0.03

Head 7: 0.04

Head 8: 0.05

Head 9: 0.38

Head 10: 0.08

Head 11: 0.03

Positive logits

orney1.58

subpoena1.58

jurisdiction1.51

Judicial1.46

tribunal1.45

adjud1.42

�醒1.40

subpoen1.40

Audit1.39

Appeals1.38

Lawyers1.37

Judge1.34

rulings1.34

ORDER1.34

examiner1.34

jury1.33

Holder1.31

mbudsman1.31

Honour1.30

idav1.28

Negative logits

tsun-1.52

Pacific-1.44

seaw-1.33

essel-1.26

glide-1.24

scenery-1.23

Atl-1.23

fade-1.22

ocean-1.19

volcanic-1.18

volcan-1.17

flakes-1.17

iceberg-1.16

Wonders-1.12

auri-1.12

Moon-1.12

vanish-1.10

spac-1.10

destinations-1.10

uns-1.09

INTERVAL 2.263 - 2.514
CONTAINS 0.000%

is
Token is
Feature activation+0.000
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.437
to
Token to
Feature activation+2.514
respond
Token respond
Feature activation+1.868
,
Token,
Feature activation+0.311
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
G
Token G
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.443
was
Token was
Feature activation+2.292
hearing
Token hearing
Feature activation+1.513
an
Token an
Feature activation+0.762
appeal
Token appeal
Feature activation+0.130
filed
Token filed
Feature activation+0.321
by
Token by
Feature activation+0.000

INTERVAL 2.011 - 2.263
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.274
concluded
Token concluded
Feature activation+2.175
the
Token the
Feature activation+1.137
state
Token state
Feature activation+1.029
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.455
found
Token found
Feature activation+2.039
Wild
Token Wild
Feature activation+0.705
ers
Tokeners
Feature activation+0.000
not
Token not
Feature activation+0.000
guilty
Token guilty
Feature activation+0.000
of
Token of
Feature activation+0.000
was
Token was
Feature activation+0.000
flawed
Token flawed
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
court
Token court
Feature activation+0.507
can
Token can
Feature activation+2.081
dismiss
Token dismiss
Feature activation+1.913
the
Token the
Feature activation+0.242
cases
Token cases
Feature activation+0.000
,
Token,
Feature activation+0.000
uphold
Token uphold
Feature activation+0.151

INTERVAL 1.760 - 2.011
CONTAINS 0.001%

up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.437
to
Token to
Feature activation+2.514
respond
Token respond
Feature activation+1.868
,
Token,
Feature activation+0.311
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
G
Token G
Feature activation+0.000
orman
Tokenorman
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
This
TokenThis
Feature activation+0.000
court
Token court
Feature activation+0.000
has
Token has
Feature activation+1.925
found
Token found
Feature activation+1.671
that
Token that
Feature activation+0.143
Carter
Token Carter
Feature activation+0.000
's
Token's
Feature activation+0.000
actions
Token actions
Feature activation+0.000
men
Token men
Feature activation+0.000
.
Token.
Feature activation+0.000
Under
Token Under
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.382
's
Token's
Feature activation+1.816
interpretation
Token interpretation
Feature activation+0.553
of
Token of
Feature activation+0.000
Islamic
Token Islamic
Feature activation+0.000
law
Token law
Feature activation+0.000
,
Token,
Feature activation+0.000
women
Token women
Feature activation+0.000
.
Token.
Feature activation+0.000
If
Token If
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.099
goes
Token goes
Feature activation+1.783
along
Token along
Feature activation+1.015
,
Token,
Feature activation+0.419
it
Token it
Feature activation+0.000
could
Token could
Feature activation+0.000
have
Token have
Feature activation+0.000
was
Token was
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.367
to
Token to
Feature activation+1.858
administ
Token administ
Feature activation+1.099
rate
Tokenrate
Feature activation+0.345
the
Token the
Feature activation+0.491
settlement
Token settlement
Feature activation+0.132
,
Token,
Feature activation+0.019

INTERVAL 1.508 - 1.760
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
11
Token11
Feature activation+0.000
The
Token The
Feature activation+0.000
court
Token court
Feature activation+0.418
heard
Token heard
Feature activation+1.587
L
Token L
Feature activation+0.330
avin
Tokenavin
Feature activation+0.000
ia
Tokenia
Feature activation+0.000
has
Token has
Feature activation+0.000
battled
Token battled
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
An
TokenAn
Feature activation+0.000
Athens
Token Athens
Feature activation+0.000
court
Token court
Feature activation+0.000
on
Token on
Feature activation+1.114
Wednesday
Token Wednesday
Feature activation+1.619
acquitted
Token acquitted
Feature activation+1.081
anarchist
Token anarchist
Feature activation+0.000
Cost
Token Cost
Feature activation+0.000
as
Tokenas
Feature activation+0.000
Sak
Token Sak
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
This
TokenThis
Feature activation+0.000
court
Token court
Feature activation+0.000
has
Token has
Feature activation+1.925
found
Token found
Feature activation+1.671
that
Token that
Feature activation+0.143
Carter
Token Carter
Feature activation+0.000
's
Token's
Feature activation+0.000
actions
Token actions
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
court
Token court
Feature activation+0.000
,
Token,
Feature activation+1.713
lawyers
Token lawyers
Feature activation+0.032
representing
Token representing
Feature activation+0.000
Er
Token Er
Feature activation+0.000
de
Tokende
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.321
ruled
Token ruled
Feature activation+1.654
that
Token that
Feature activation+0.119
was
Token was
Feature activation+0.582
wrong
Token wrong
Feature activation+0.176
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.257 - 1.508
CONTAINS 0.003%

'll
Token'll
Feature activation+0.000
go
Token go
Feature activation+0.000
to
Token to
Feature activation+0.000
court
Token court
Feature activation+0.000
and
Token and
Feature activation+1.129
I
Token I
Feature activation+1.283
'll
Token'll
Feature activation+0.673
sit
Token sit
Feature activation+0.487
there
Token there
Feature activation+0.000
and
Token and
Feature activation+0.000
drink
Token drink
Feature activation+0.000
at
Token at
Feature activation+0.000
Dublin
Token Dublin
Feature activation+0.000
Circuit
Token Circuit
Feature activation+0.000
Criminal
Token Criminal
Feature activation+0.000
Court
Token Court
Feature activation+0.000
collapsed
Token collapsed
Feature activation+1.295
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.025
charges
Token charges
Feature activation+0.000
were
Token were
Feature activation+0.000
withdrawn
Token withdrawn
Feature activation+0.000
standing
Token standing
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.000
in
Token in
Feature activation+1.342
the
Token the
Feature activation+1.351
public
Token public
Feature activation+0.791
âĢ
TokenâĢ
Feature activation+0.023
Ļ
TokenĻ
Feature activation+0.052
s
Tokens
Feature activation+0.000
mind
Token mind
Feature activation+0.000
for
Token for
Feature activation+0.000
discrimination
Token discrimination
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
court
Token court
Feature activation+0.153
said
Token said
Feature activation+1.477
Oklahoma
Token Oklahoma
Feature activation+0.085
hasn
Token hasn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
would
Token would
Feature activation+0.000
get
Token get
Feature activation+0.000
off
Token off
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.145
as
Token as
Feature activation+1.497
soon
Token soon
Feature activation+0.494
as
Token as
Feature activation+0.000
possible
Token possible
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.006 - 1.257
CONTAINS 0.006%

trust
Token trust
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.932
âĢ
TokenâĢ
Feature activation+1.134
Ļ
TokenĻ
Feature activation+1.192
s
Tokens
Feature activation+0.000
own
Token own
Feature activation+1.004
integrity
Token integrity
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Victoria
Token Victoria
Feature activation+0.000
only
Token only
Feature activation+0.000
asked
Token asked
Feature activation+0.000
her
Token her
Feature activation+0.000
court
Token court
Feature activation+0.000
for
Token for
Feature activation+1.122
three
Token three
Feature activation+1.041
years
Token years
Feature activation+0.666
of
Token of
Feature activation+0.000
g
Token g
Feature activation+0.149
oth
Tokenoth
Feature activation+0.207
.
Token.
Feature activation+0.000
How
Token How
Feature activation+0.000
can
Token can
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.000
determine
Token determine
Feature activation+1.196
what
Token what
Feature activation+0.249
the
Token the
Feature activation+0.414
boy
Token boy
Feature activation+0.000
really
Token really
Feature activation+0.000
wants
Token wants
Feature activation+0.000
up
Token up
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.322
of
Token of
Feature activation+0.735
law
Token law
Feature activation+1.151
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
CM
Token CM
Feature activation+0.000
March
Token March
Feature activation+0.000
before
Token before
Feature activation+0.000
any
Token any
Feature activation+0.000
disciplinary
Token disciplinary
Feature activation+0.000
court
Token court
Feature activation+0.000
to
Token to
Feature activation+1.069
explain
Token explain
Feature activation+0.729
to
Token to
Feature activation+0.000
me
Token me
Feature activation+0.000
exactly
Token exactly
Feature activation+0.000
what
Token what
Feature activation+0.000

INTERVAL 0.754 - 1.006
CONTAINS 0.008%

She
TokenShe
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.049
âĢ
TokenâĢ
Feature activation+0.470
Ļ
TokenĻ
Feature activation+0.882
s
Tokens
Feature activation+0.000
decision
Token decision
Feature activation+0.000
could
Token could
Feature activation+0.007
lead
Token lead
Feature activation+0.145
to
Token to
Feature activation+0.000
her
Token her
Feature activation+0.000
lengthy
Token lengthy
Feature activation+0.000
court
Token court
Feature activation+0.000
battle
Token battle
Feature activation+0.197
to
Token to
Feature activation+0.844
return
Token return
Feature activation+0.897
to
Token to
Feature activation+0.000
her
Token her
Feature activation+0.000
position
Token position
Feature activation+0.000
.
Token.
Feature activation+0.000
There
Token There
Feature activation+0.000
the
Token the
Feature activation+0.000
results
Token results
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
,
Token,
Feature activation+1.110
where
Token where
Feature activation+0.939
she
Token she
Feature activation+0.199
will
Token will
Feature activation+0.000
be
Token be
Feature activation+0.000
forced
Token forced
Feature activation+0.000
to
Token to
Feature activation+0.000
nothing
Token nothing
Feature activation+0.000
upcoming
Token upcoming
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.170
d
Token d
Feature activation+0.961
ocket
Tokenocket
Feature activation+0.541
for
Token for
Feature activation+0.017
the
Token the
Feature activation+0.219
three
Token three
Feature activation+0.163
.
Token.
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.932
âĢ
TokenâĢ
Feature activation+1.134
Ļ
TokenĻ
Feature activation+1.192
s
Tokens
Feature activation+0.000
own
Token own
Feature activation+1.004
integrity
Token integrity
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
logic
Token logic
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.503 - 0.754
CONTAINS 0.014%

Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
court
Token court
Feature activation+0.415
's
Token's
Feature activation+1.263
decision
Token decision
Feature activation+0.742
once
Token once
Feature activation+0.689
again
Token again
Feature activation+0.000
confirms
Token confirms
Feature activation+0.069
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
appeared
Token appeared
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
briefly
Token briefly
Feature activation+1.399
on
Token on
Feature activation+0.896
Tuesday
Token Tuesday
Feature activation+0.535
,
Token,
Feature activation+0.110
November
Token November
Feature activation+0.000
28
Token 28
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
.
Token.
Feature activation+0.000
released
Token released
Feature activation+0.000
pursuant
Token pursuant
Feature activation+0.000
to
Token to
Feature activation+0.000
court
Token court
Feature activation+0.640
order
Token order
Feature activation+0.401
due
Token due
Feature activation+0.748
to
Token to
Feature activation+0.495
Z
Token Z
Feature activation+0.073
adv
Tokenadv
Feature activation+0.028
yd
Tokenyd
Feature activation+0.000
as
Tokenas
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
District
Token District
Feature activation+0.000
Court
Token Court
Feature activation+0.000
in
Token in
Feature activation+0.635
Manhattan
Token Manhattan
Feature activation+0.585
,
Token ,
Feature activation+0.033
an
Token an
Feature activation+0.000
S
Token S
Feature activation+0.000
.
Token.
Feature activation+0.000
same
Token same
Feature activation+0.000
test
Token test
Feature activation+0.000
the
Token the
Feature activation+0.000
high
Token high
Feature activation+0.000
court
Token court
Feature activation+0.243
used
Token used
Feature activation+0.514
to
Token to
Feature activation+0.479
invalid
Token invalid
Feature activation+0.000
ate
Tokenate
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.251 - 0.503
CONTAINS 0.023%

can
Token can
Feature activation+0.000
the
Token the
Feature activation+0.000
court
Token court
Feature activation+0.000
determine
Token determine
Feature activation+1.196
what
Token what
Feature activation+0.249
the
Token the
Feature activation+0.414
boy
Token boy
Feature activation+0.000
really
Token really
Feature activation+0.000
wants
Token wants
Feature activation+0.000
?
Token?
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
-
Token-
Feature activation+0.000
world
Tokenworld
Feature activation+0.000
y
Tokeny
Feature activation+0.000
"
Token"
Feature activation+0.000
court
Token court
Feature activation+0.000
formal
Token formal
Feature activation+0.494
ities
Tokenities
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Lord
Token Lord
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Arkansas
Token Arkansas
Feature activation+0.000
to
Token to
Feature activation+0.000
seek
Token seek
Feature activation+0.000
court
Token court
Feature activation+0.000
action
Token action
Feature activation+0.000
to
Token to
Feature activation+0.254
collect
Token collect
Feature activation+0.698
the
Token the
Feature activation+0.000
tax
Token tax
Feature activation+0.000
revenue
Token revenue
Feature activation+0.000
from
Token from
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.151
at
Token at
Feature activation+1.286
a
Token a
Feature activation+1.651
later
Token later
Feature activation+0.928
date
Token date
Feature activation+0.352
.
Token.
Feature activation+0.000
Another
TokenAnother
Feature activation+0.000
student
Token student
Feature activation+0.000
was
Token was
Feature activation+0.000
also
Token also
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
City
Token City
Feature activation+0.000
in
Token in
Feature activation+0.000
court
Token court
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.379
but
Token but
Feature activation+0.120
,
Token,
Feature activation+0.379
like
Token like
Feature activation+0.000
all
Token all
Feature activation+0.000
good
Token good
Feature activation+0.000

INTERVAL 0.000 - 0.251
CONTAINS 99.944%

s
Tokens
Feature activation+0.000
ability
Token ability
Feature activation+0.000
to
Token to
Feature activation+0.000
create
Token create
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
life
Tokenlife
Feature activation+0.000
like
Token like
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
tension
Token tension
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
party
Token party
Feature activation+0.000
-
Token-
Feature activation+0.000
style
Tokenstyle
Feature activation+0.000
bus
Token bus
Feature activation+0.000
and
Token and
Feature activation+0.000
there
Token there
Feature activation+0.000
was
Token was
Feature activation+0.000
a
Token a
Feature activation+0.000
stri
Token stri
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
no
Token no
Feature activation+0.000
point
Token point
Feature activation+0.000
in
Token in
Feature activation+0.000
trying
Token trying
Feature activation+0.000
.
Token.
Feature activation+0.000
No
Token No
Feature activation+0.000
point
Token point
Feature activation+0.000
in
Token in
Feature activation+0.000
Railway
Token Railway
Feature activation+0.000
Children
Token Children
Feature activation+0.000
(
Token (
Feature activation+0.000
1970
Token1970
Feature activation+0.000
)
Token)
Feature activation+0.000
and
Token and
Feature activation+0.000
The
Token The
Feature activation+0.000
Go
Token Go
Feature activation+0.000
-
Token-
Feature activation+0.000
Between
TokenBetween
Feature activation+0.000
(
Token (
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
board
Token board
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
he
Token he
Feature activation+0.000
has
Token has
Feature activation+0.000
voted
Token voted
Feature activation+0.000
to
Token to
Feature activation+0.000
weaken
Token weaken
Feature activation+0.000
some
Token some
Feature activation+0.000
environmental
Token environmental
Feature activation+0.000
regulations
Token regulations
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 1 in H2.9: (feature 24315)

TOP ACTIVATIONS
MAX = 2.429

Rosen
Token Rosen
Feature activation+0.000
has
Token has
Feature activation+0.000
advised
Token advised
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.089
to
Token to
Feature activation+2.429
throw
Token throw
Feature activation+1.093
out
Token out
Feature activation+0.291
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
playbook
Token playbook
Feature activation+0.000
Sh
Token Sh
Feature activation+0.000
afer
Tokenafer
Feature activation+0.000
argue
Token argue
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
should
Token should
Feature activation+2.378
ignore
Token ignore
Feature activation+1.599
President
Token President
Feature activation+0.059
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
K
Token K
Feature activation+0.000
essel
Tokenessel
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
media
Token media
Feature activation+0.081
just
Token just
Feature activation+2.196
gives
Token gives
Feature activation+1.726
it
Token it
Feature activation+0.444
to
Token to
Feature activation+0.161
him
Token him
Feature activation+0.000
for
Token for
Feature activation+0.000
massacres
Token massacres
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.136
to
Token to
Feature activation+2.171
show
Token show
Feature activation+1.785
him
Token him
Feature activation+0.459
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
familiar
Token familiar
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.078
have
Token have
Feature activation+1.712
an
Token an
Feature activation+2.066
inherent
Token inherent
Feature activation+1.676
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000
entirely
Token entirely
Feature activation+0.000
expected
Token expected
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
media
Token media
Feature activation+0.263
suddenly
Token suddenly
Feature activation+2.023
painted
Token painted
Feature activation+1.302
her
Token her
Feature activation+0.479
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
evil
Token evil
Feature activation+0.000
in
Token in
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.583
,
Token,
Feature activation+2.016
and
Token and
Feature activation+1.477
academ
Token academ
Feature activation+0.623
e
Tokene
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.207
yesterday
Token yesterday
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.459
showed
Token showed
Feature activation+1.961
up
Token up
Feature activation+0.844
Ċ
TokenĊ
Feature activation+0.028
Ċ
TokenĊ
Feature activation+0.046
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
ave
Tokenave
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.116
,
Token,
Feature activation+1.961
including
Token including
Feature activation+1.363
Stephen
Token Stephen
Feature activation+0.030
A
Token A
Feature activation+0.000
.
Token.
Feature activation+0.000
Smith
Token Smith
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
To
TokenTo
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.483
he
Token he
Feature activation+1.893
was
Token was
Feature activation+0.941
,
Token,
Feature activation+0.579
but
Token but
Feature activation+0.000
behind
Token behind
Feature activation+0.000
the
Token the
Feature activation+0.000
spot
Token spot
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
and
Token and
Feature activation+1.605
powerful
Token powerful
Feature activation+1.862
politicians
Token politicians
Feature activation+0.000
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
she
Token she
Feature activation+0.000
ing
Tokening
Feature activation+0.000
skepticism
Token skepticism
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.387
âĢĶ
Token âĢĶ
Feature activation+1.830
including
Token including
Feature activation+1.573
commentators
Token commentators
Feature activation+0.277
âĢĶ
Token âĢĶ
Feature activation+0.067
simply
Token simply
Feature activation+0.088
reported
Token reported
Feature activation+0.000
ett
Tokenett
Feature activation+0.000
as
Tokenas
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.236
and
Token and
Feature activation+1.829
political
Token political
Feature activation+1.134
establishment
Token establishment
Feature activation+0.194
and
Token and
Feature activation+0.205
who
Token who
Feature activation+0.139
is
Token is
Feature activation+0.042
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.136
to
Token to
Feature activation+2.171
show
Token show
Feature activation+1.785
him
Token him
Feature activation+0.459
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
's
Token's
Feature activation+0.000
has
Token has
Feature activation+0.000
used
Token used
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.259
and
Token and
Feature activation+1.768
fiery
Token fiery
Feature activation+1.275
rhetoric
Token rhetoric
Feature activation+0.028
to
Token to
Feature activation+0.109
tell
Token tell
Feature activation+0.389
his
Token his
Feature activation+0.000
and
Token and
Feature activation+0.000
maintained
Token maintained
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.223
in
Token in
Feature activation+1.750
a
Token a
Feature activation+1.457
successful
Token successful
Feature activation+1.092
effort
Token effort
Feature activation+0.000
to
Token to
Feature activation+0.000
defeat
Token defeat
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.674
and
Token and
Feature activation+1.749
technology
Token technology
Feature activation+1.147
industries
Token industries
Feature activation+0.278
are
Token are
Feature activation+0.105
urgently
Token urgently
Feature activation+0.096
searching
Token searching
Feature activation+0.000
importantly
Token importantly
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.422
is
Token is
Feature activation+1.747
completely
Token completely
Feature activation+1.374
turning
Token turning
Feature activation+0.896
a
Token a
Feature activation+0.166
blind
Token blind
Feature activation+0.232
eye
Token eye
Feature activation+0.000
last
Token last
Feature activation+0.000
weekend
Token weekend
Feature activation+0.000
the
Token the
Feature activation+0.000
liberal
Token liberal
Feature activation+0.000
media
Token media
Feature activation+0.000
tried
Token tried
Feature activation+1.742
to
Token to
Feature activation+1.607
hit
Token hit
Feature activation+0.665
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
with
Token with
Feature activation+0.000
essel
Tokenessel
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
media
Token media
Feature activation+0.081
just
Token just
Feature activation+2.196
gives
Token gives
Feature activation+1.726
it
Token it
Feature activation+0.444
to
Token to
Feature activation+0.161
him
Token him
Feature activation+0.000
for
Token for
Feature activation+0.000
no
Token no
Feature activation+0.000

Top DFA by src position
MAX = 3.541

Professor
TokenProfessor
Feature activation-0.080
Top resid features:
Rosen
Token Rosen
Feature activation+0.014
Top resid features:
has
Token has
Feature activation-0.019
Top resid features:
advised
Token advised
Feature activation+0.304
Top resid features:
the
Token the
Feature activation+0.285
Top resid features:
media
Token media
Feature activation+3.456
Top resid features:
to
Token to
Feature activation-0.119
Top resid features:
throw
Token throw
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
old
Token old
Feature activation+0.000
Top resid features:
Jack
Token Jack
Feature activation-0.024
Top resid features:
Sh
Token Sh
Feature activation+0.004
Top resid features:
afer
Tokenafer
Feature activation-0.004
Top resid features:
argue
Token argue
Feature activation-0.014
Top resid features:
the
Token the
Feature activation+0.299
Top resid features:
media
Token media
Feature activation+3.459
Top resid features:
should
Token should
Feature activation+0.002
Top resid features:
ignore
Token ignore
Feature activation+0.000
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
elect
Tokenelect
Feature activation+0.000
Top resid features:
Phil
Token Phil
Feature activation-0.053
Top resid features:
K
Token K
Feature activation-0.033
Top resid features:
essel
Tokenessel
Feature activation-0.033
Top resid features:
.
Token.
Feature activation+0.067
Top resid features:
The
Token The
Feature activation+0.168
Top resid features:
media
Token media
Feature activation+3.541
Top resid features:
just
Token just
Feature activation-0.037
Top resid features:
gives
Token gives
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.002
Top resid features:
massacres
Token massacres
Feature activation+0.043
Top resid features:
and
Token and
Feature activation-0.037
Top resid features:
asked
Token asked
Feature activation+0.194
Top resid features:
the
Token the
Feature activation+0.233
Top resid features:
media
Token media
Feature activation+3.142
Top resid features:
to
Token to
Feature activation-0.098
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
aren
Token aren
Feature activation-0.033
Top resid features:
't
Token't
Feature activation-0.008
Top resid features:
familiar
Token familiar
Feature activation-0.044
Top resid features:
with
Token with
Feature activation-0.104
Top resid features:
the
Token the
Feature activation+0.077
Top resid features:
media
Token media
Feature activation+3.227
Top resid features:
have
Token have
Feature activation+0.390
Top resid features:
an
Token an
Feature activation-0.004
Top resid features:
inherent
Token inherent
Feature activation+0.000
Top resid features:
suspicion
Token suspicion
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
were
Token were
Feature activation-0.041
Top resid features:
entirely
Token entirely
Feature activation-0.016
Top resid features:
expected
Token expected
Feature activation+0.011
Top resid features:
.
Token.
Feature activation+0.201
Top resid features:
The
Token The
Feature activation+0.186
Top resid features:
media
Token media
Feature activation+3.209
Top resid features:
suddenly
Token suddenly
Feature activation-0.099
Top resid features:
painted
Token painted
Feature activation+0.000
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
members
Token members
Feature activation-0.033
Top resid features:
in
Token in
Feature activation-0.030
Top resid features:
government
Token government
Feature activation+0.065
Top resid features:
,
Token,
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.290
Top resid features:
media
Token media
Feature activation+3.044
Top resid features:
,
Token,
Feature activation+0.084
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
academ
Token academ
Feature activation+0.000
Top resid features:
e
Tokene
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
reporters
Token reporters
Feature activation+0.063
Top resid features:
yesterday
Token yesterday
Feature activation-0.034
Top resid features:
,
Token,
Feature activation+0.061
Top resid features:
and
Token and
Feature activation-0.075
Top resid features:
the
Token the
Feature activation+0.230
Top resid features:
media
Token media
Feature activation+2.934
Top resid features:
showed
Token showed
Feature activation+0.055
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
g
Tokeng
Feature activation-0.012
Top resid features:
ave
Tokenave
Feature activation-0.010
Top resid features:
âĢ
TokenâĢ
Feature activation+0.037
Top resid features:
Ŀ
TokenĿ
Feature activation-0.024
Top resid features:
the
Token the
Feature activation+0.343
Top resid features:
media
Token media
Feature activation+2.992
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
Stephen
Token Stephen
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.009
Top resid features:
"
Token"
Feature activation-0.047
Top resid features:
To
TokenTo
Feature activation-0.111
Top resid features:
the
Token the
Feature activation+0.272
Top resid features:
media
Token media
Feature activation+3.084
Top resid features:
he
Token he
Feature activation+0.011
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
but
Token but
Feature activation+0.000
Top resid features:
behind
Token behind
Feature activation+0.000
Top resid features:
on
Token on
Feature activation-0.043
Top resid features:
the
Token the
Feature activation+0.009
Top resid features:
spot
Token spot
Feature activation-0.068
Top resid features:
with
Token with
Feature activation-0.065
Top resid features:
the
Token the
Feature activation+0.159
Top resid features:
media
Token media
Feature activation+3.142
Top resid features:
and
Token and
Feature activation+0.008
Top resid features:
powerful
Token powerful
Feature activation+0.017
Top resid features:
politicians
Token politicians
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
inc
Tokeninc
Feature activation-0.042
Top resid features:
ing
Tokening
Feature activation-0.039
Top resid features:
skepticism
Token skepticism
Feature activation+0.035
Top resid features:
,
Token,
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.298
Top resid features:
media
Token media
Feature activation+2.927
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.044
Top resid features:
including
Token including
Feature activation+0.000
Top resid features:
commentators
Token commentators
Feature activation+0.000
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.000
Top resid features:
simply
Token simply
Feature activation+0.000
Top resid features:
vend
Token vend
Feature activation+0.048
Top resid features:
ett
Tokenett
Feature activation-0.042
Top resid features:
as
Tokenas
Feature activation+0.020
Top resid features:
by
Token by
Feature activation+0.007
Top resid features:
the
Token the
Feature activation+0.216
Top resid features:
media
Token media
Feature activation+2.906
Top resid features:
and
Token and
Feature activation-0.052
Top resid features:
political
Token political
Feature activation+0.000
Top resid features:
establishment
Token establishment
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
massacres
Token massacres
Feature activation+0.030
Top resid features:
and
Token and
Feature activation-0.012
Top resid features:
asked
Token asked
Feature activation+0.017
Top resid features:
the
Token the
Feature activation+0.163
Top resid features:
media
Token media
Feature activation+2.705
Top resid features:
to
Token to
Feature activation-0.043
Top resid features:
show
Token show
Feature activation+0.158
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Abbas
Token Abbas
Feature activation+0.030
Top resid features:
has
Token has
Feature activation-0.047
Top resid features:
used
Token used
Feature activation-0.003
Top resid features:
both
Token both
Feature activation+0.373
Top resid features:
the
Token the
Feature activation+0.121
Top resid features:
media
Token media
Feature activation+2.737
Top resid features:
and
Token and
Feature activation-0.080
Top resid features:
fiery
Token fiery
Feature activation+0.000
Top resid features:
rhetoric
Token rhetoric
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
tell
Token tell
Feature activation+0.000
Top resid features:
ists
Tokenists
Feature activation+0.008
Top resid features:
and
Token and
Feature activation-0.053
Top resid features:
maintained
Token maintained
Feature activation+0.119
Top resid features:
by
Token by
Feature activation-0.092
Top resid features:
the
Token the
Feature activation+0.300
Top resid features:
media
Token media
Feature activation+2.764
Top resid features:
in
Token in
Feature activation-0.072
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
successful
Token successful
Feature activation+0.000
Top resid features:
effort
Token effort
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
become
Token become
Feature activation-0.063
Top resid features:
a
Token a
Feature activation-0.022
Top resid features:
problem
Token problem
Feature activation+0.008
Top resid features:
that
Token that
Feature activation+0.111
Top resid features:
the
Token the
Feature activation+0.218
Top resid features:
media
Token media
Feature activation+2.929
Top resid features:
and
Token and
Feature activation-0.081
Top resid features:
technology
Token technology
Feature activation+0.000
Top resid features:
industries
Token industries
Feature activation+0.000
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
urgently
Token urgently
Feature activation+0.000
Top resid features:
most
Token most
Feature activation-0.005
Top resid features:
importantly
Token importantly
Feature activation-0.009
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
how
Token how
Feature activation+0.054
Top resid features:
the
Token the
Feature activation+0.127
Top resid features:
media
Token media
Feature activation+3.022
Top resid features:
is
Token is
Feature activation-0.045
Top resid features:
completely
Token completely
Feature activation+0.000
Top resid features:
turning
Token turning
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
blind
Token blind
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation-0.018
Top resid features:
last
Token last
Feature activation-0.047
Top resid features:
weekend
Token weekend
Feature activation-0.029
Top resid features:
the
Token the
Feature activation+0.161
Top resid features:
liberal
Token liberal
Feature activation+0.223
Top resid features:
media
Token media
Feature activation+2.831
Top resid features:
tried
Token tried
Feature activation+0.078
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
hit
Token hit
Feature activation+0.000
Top resid features:
Donald
Token Donald
Feature activation+0.000
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
Phil
Token Phil
Feature activation-0.027
Top resid features:
K
Token K
Feature activation-0.016
Top resid features:
essel
Tokenessel
Feature activation-0.039
Top resid features:
.
Token.
Feature activation+0.081
Top resid features:
The
Token The
Feature activation+0.123
Top resid features:
media
Token media
Feature activation+2.860
Top resid features:
just
Token just
Feature activation+0.110
Top resid features:
gives
Token gives
Feature activation-0.003
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.07

Head 3: 0.07

Head 4: 0.04

Head 5: 0.09

Head 6: 0.05

Head 7: 0.03

Head 8: 0.05

Head 9: 0.38

Head 10: 0.08

Head 11: 0.05

Positive logits

atters1.36

Limbaugh1.34

moderates1.33

Hannity1.26

telev1.25

Spears1.25

sensit1.25

boycot1.24

Anthem1.23

pundits1.23

anchors1.21

phia1.19

Morsi1.17

casters1.15

lete1.15

sponsors1.15

scandals1.15

headlines1.15

saturated1.14

satur1.13

Negative logits

uana-1.31

vised-1.21

abase-1.20

tein-1.19

Solitaire-1.19

onel-1.17

EStreamFrame-1.17

gmaxwell-1.16

selage-1.16

rontal-1.15

dfx-1.15

onga-1.15

agonal-1.13

.$-1.13

ussian-1.13

Reward-1.11

Mobility-1.11

rox-1.10

_-_-1.10

Maximum-1.09

INTERVAL 2.186 - 2.429
CONTAINS 0.000%

Sh
Token Sh
Feature activation+0.000
afer
Tokenafer
Feature activation+0.000
argue
Token argue
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
should
Token should
Feature activation+2.378
ignore
Token ignore
Feature activation+1.599
President
Token President
Feature activation+0.059
-
Token-
Feature activation+0.000
elect
Tokenelect
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Rosen
Token Rosen
Feature activation+0.000
has
Token has
Feature activation+0.000
advised
Token advised
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.089
to
Token to
Feature activation+2.429
throw
Token throw
Feature activation+1.093
out
Token out
Feature activation+0.291
the
Token the
Feature activation+0.000
old
Token old
Feature activation+0.000
playbook
Token playbook
Feature activation+0.000
K
Token K
Feature activation+0.000
essel
Tokenessel
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
media
Token media
Feature activation+0.081
just
Token just
Feature activation+2.196
gives
Token gives
Feature activation+1.726
it
Token it
Feature activation+0.444
to
Token to
Feature activation+0.161
him
Token him
Feature activation+0.000
for
Token for
Feature activation+0.000

INTERVAL 1.944 - 2.186
CONTAINS 0.001%

entirely
Token entirely
Feature activation+0.000
expected
Token expected
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
media
Token media
Feature activation+0.263
suddenly
Token suddenly
Feature activation+2.023
painted
Token painted
Feature activation+1.302
her
Token her
Feature activation+0.479
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
evil
Token evil
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.459
showed
Token showed
Feature activation+1.961
up
Token up
Feature activation+0.844
Ċ
TokenĊ
Feature activation+0.028
Ċ
TokenĊ
Feature activation+0.046
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
in
Token in
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.583
,
Token,
Feature activation+2.016
and
Token and
Feature activation+1.477
academ
Token academ
Feature activation+0.623
e
Tokene
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.207
massacres
Token massacres
Feature activation+0.000
and
Token and
Feature activation+0.000
asked
Token asked
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.136
to
Token to
Feature activation+2.171
show
Token show
Feature activation+1.785
him
Token him
Feature activation+0.459
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
familiar
Token familiar
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.078
have
Token have
Feature activation+1.712
an
Token an
Feature activation+2.066
inherent
Token inherent
Feature activation+1.676
suspicion
Token suspicion
Feature activation+0.000
of
Token of
Feature activation+0.000
being
Token being
Feature activation+0.000
recorded
Token recorded
Feature activation+0.000

INTERVAL 1.701 - 1.944
CONTAINS 0.002%

has
Token has
Feature activation+0.000
used
Token used
Feature activation+0.000
both
Token both
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.259
and
Token and
Feature activation+1.768
fiery
Token fiery
Feature activation+1.275
rhetoric
Token rhetoric
Feature activation+0.028
to
Token to
Feature activation+0.109
tell
Token tell
Feature activation+0.389
his
Token his
Feature activation+0.000
said
Token said
Feature activation+0.000
they
Token they
Feature activation+0.000
believed
Token believed
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
was
Token was
Feature activation+1.724
biased
Token biased
Feature activation+1.151
against
Token against
Feature activation+0.348
Trump
Token Trump
Feature activation+0.248
.
Token.
Feature activation+0.000
Numbers
Token Numbers
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
To
TokenTo
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.483
he
Token he
Feature activation+1.893
was
Token was
Feature activation+0.941
,
Token,
Feature activation+0.579
but
Token but
Feature activation+0.000
behind
Token behind
Feature activation+0.000
the
Token the
Feature activation+0.000
a
Token a
Feature activation+0.000
problem
Token problem
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.674
and
Token and
Feature activation+1.749
technology
Token technology
Feature activation+1.147
industries
Token industries
Feature activation+0.278
are
Token are
Feature activation+0.105
urgently
Token urgently
Feature activation+0.096
searching
Token searching
Feature activation+0.000
ett
Tokenett
Feature activation+0.000
as
Tokenas
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.236
and
Token and
Feature activation+1.829
political
Token political
Feature activation+1.134
establishment
Token establishment
Feature activation+0.194
and
Token and
Feature activation+0.205
who
Token who
Feature activation+0.139
is
Token is
Feature activation+0.042

INTERVAL 1.458 - 1.701
CONTAINS 0.002%

yet
Token yet
Feature activation+0.000
made
Token made
Feature activation+0.000
comment
Token comment
Feature activation+0.000
to
Token to
Feature activation+0.000
media
Token media
Feature activation+0.000
about
Token about
Feature activation+1.533
the
Token the
Feature activation+1.191
tweet
Token tweet
Feature activation+0.383
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
right
Token right
Feature activation+0.000
wing
Token wing
Feature activation+0.000
media
Token media
Feature activation+0.000
to
Token to
Feature activation+1.608
avoid
Token avoid
Feature activation+1.384
a
Token a
Feature activation+0.782
primary
Token primary
Feature activation+0.405
challenge
Token challenge
Feature activation+0.000
will
Token will
Feature activation+0.000
the
Token the
Feature activation+0.000
situation
Token situation
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.109
,
Token,
Feature activation+1.687
and
Token and
Feature activation+1.119
how
Token how
Feature activation+0.295
his
Token his
Feature activation+0.068
public
Token public
Feature activation+0.000
image
Token image
Feature activation+0.000
and
Tokenand
Feature activation+0.000
]
Token]
Feature activation+0.000
the
Token the
Feature activation+0.000
US
Token US
Feature activation+0.000
media
Token media
Feature activation+0.218
falsely
Token falsely
Feature activation+1.669
accused
Token accused
Feature activation+1.090
China
Token China
Feature activation+0.498
of
Token of
Feature activation+0.000
using
Token using
Feature activation+0.050
Operation
Token Operation
Feature activation+0.000
skepticism
Token skepticism
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.387
âĢĶ
Token âĢĶ
Feature activation+1.830
including
Token including
Feature activation+1.573
commentators
Token commentators
Feature activation+0.277
âĢĶ
Token âĢĶ
Feature activation+0.067
simply
Token simply
Feature activation+0.088
reported
Token reported
Feature activation+0.000
that
Token that
Feature activation+0.000

INTERVAL 1.215 - 1.458
CONTAINS 0.004%

aro
Tokenaro
Feature activation+0.000
told
Token told
Feature activation+0.000
local
Token local
Feature activation+0.000
media
Token media
Feature activation+0.000
the
Token the
Feature activation+1.207
plane
Token plane
Feature activation+1.280
crashed
Token crashed
Feature activation+0.000
while
Token while
Feature activation+0.000
attempting
Token attempting
Feature activation+0.000
to
Token to
Feature activation+0.000
return
Token return
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Dutch
Token Dutch
Feature activation+0.000
media
Token media
Feature activation+0.000
have
Token have
Feature activation+0.769
described
Token described
Feature activation+1.416
them
Token them
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
About
TokenAbout
Feature activation+0.000
,
Token,
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.422
is
Token is
Feature activation+1.747
completely
Token completely
Feature activation+1.374
turning
Token turning
Feature activation+0.896
a
Token a
Feature activation+0.166
blind
Token blind
Feature activation+0.232
eye
Token eye
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
corporate
Token corporate
Feature activation+0.000
media
Token media
Feature activation+0.202
are
Token are
Feature activation+1.232
again
Token again
Feature activation+0.763
rolling
Token rolling
Feature activation+1.236
out
Token out
Feature activation+0.000
their
Token their
Feature activation+0.000
tired
Token tired
Feature activation+0.000
arguments
Token arguments
Feature activation+0.000
about
Token about
Feature activation+0.000
dubbed
Token dubbed
Feature activation+0.000
by
Token by
Feature activation+0.000
fans
Token fans
Feature activation+0.000
and
Token and
Feature activation+0.000
media
Token media
Feature activation+0.118
as
Token as
Feature activation+1.359
the
Token the
Feature activation+1.170
"
Token "
Feature activation+1.031
Mir
TokenMir
Feature activation+0.088
acle
Tokenacle
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 0.972 - 1.215
CONTAINS 0.004%

referred
Token referred
Feature activation+0.000
to
Token to
Feature activation+0.000
in
Token in
Feature activation+0.000
media
Token media
Feature activation+0.129
,
Token,
Feature activation+1.203
for
Token for
Feature activation+1.015
example
Token example
Feature activation+0.521
by
Token by
Feature activation+0.000
es
Token es
Feature activation+0.000
y
Tokeny
Feature activation+0.000
ria
Tokenria
Feature activation+0.000
new
Token new
Feature activation+0.000
industry
Token industry
Feature activation+0.000
of
Token of
Feature activation+0.000
print
Token print
Feature activation+0.000
media
Token media
Feature activation+0.010
and
Token and
Feature activation+1.067
books
Token books
Feature activation+0.820
.
Token.
Feature activation+0.000
Millions
Token Millions
Feature activation+0.000
are
Token are
Feature activation+0.000
already
Token already
Feature activation+0.000
Complex
Token Complex
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.275
and
Token and
Feature activation+1.276
the
Token the
Feature activation+1.147
installation
Token installation
Feature activation+0.769
of
Token of
Feature activation+0.023
institutional
Token institutional
Feature activation+0.000
ized
Tokenized
Feature activation+0.000
slavery
Token slavery
Feature activation+0.000
they
Token they
Feature activation+0.000
believed
Token believed
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.000
was
Token was
Feature activation+1.724
biased
Token biased
Feature activation+1.151
against
Token against
Feature activation+0.348
Trump
Token Trump
Feature activation+0.248
.
Token.
Feature activation+0.000
Numbers
Token Numbers
Feature activation+0.000
like
Token like
Feature activation+0.000
as
Tokenas
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.236
and
Token and
Feature activation+1.829
political
Token political
Feature activation+1.134
establishment
Token establishment
Feature activation+0.194
and
Token and
Feature activation+0.205
who
Token who
Feature activation+0.139
is
Token is
Feature activation+0.042
backed
Token backed
Feature activation+0.000

INTERVAL 0.729 - 0.972
CONTAINS 0.004%

the
Token the
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+1.496
the
Token the
Feature activation+1.078
confused
Token confused
Feature activation+0.970
independents
Token independents
Feature activation+0.388
,
Token,
Feature activation+0.084
and
Token and
Feature activation+0.000
most
Token most
Feature activation+0.000
of
Token of
Feature activation+0.000
published
Token published
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
media
Token media
Feature activation+0.000
,
Token,
Feature activation+0.895
explores
Token explores
Feature activation+0.222
claims
Token claims
Feature activation+0.000
made
Token made
Feature activation+0.000
by
Token by
Feature activation+0.000
some
Token some
Feature activation+0.000
the
Token the
Feature activation+0.000
recall
Token recall
Feature activation+0.000
.
Token.
Feature activation+0.000
Media
Token Media
Feature activation+0.377
campaigns
Token campaigns
Feature activation+0.381
will
Token will
Feature activation+0.877
be
Token be
Feature activation+1.194
launched
Token launched
Feature activation+0.720
fraught
Token fraught
Feature activation+0.085
with
Token with
Feature activation+0.000
lies
Token lies
Feature activation+0.000
l
Token l
Feature activation+0.000
uv
Tokenuv
Feature activation+0.000
v
Tokenv
Feature activation+0.000
ie
Tokenie
Feature activation+0.000
media
Token media
Feature activation+0.000
here
Token here
Feature activation+0.753
;
Token;
Feature activation+0.082
Channel
Token Channel
Feature activation+0.000
4
Token 4
Feature activation+0.000
and
Token and
Feature activation+0.000
The
Token The
Feature activation+0.000
the
Token the
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
media
Token media
Feature activation+0.091
is
Token is
Feature activation+1.285
obsess
Token obsess
Feature activation+0.781
ively
Tokenively
Feature activation+0.864
compiling
Token compiling
Feature activation+0.484
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.486 - 0.729
CONTAINS 0.010%

enthal
Tokenenthal
Feature activation+0.000
Delete
Token Delete
Feature activation+0.000
Edit
Token Edit
Feature activation+0.000
embedded
Token embedded
Feature activation+0.000
media
Token media
Feature activation+0.000
in
Token in
Feature activation+0.589
the
Token the
Feature activation+0.368
Files
Token Files
Feature activation+0.074
Tab
Token Tab
Feature activation+0.000
and
Token and
Feature activation+0.000
re
Token re
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
media
Token media
Feature activation+0.305
are
Token are
Feature activation+1.385
in
Token in
Feature activation+1.111
on
Token on
Feature activation+0.740
the
Token the
Feature activation+0.605
game
Token game
Feature activation+0.000
of
Token of
Feature activation+0.000
deceit
Token deceit
Feature activation+0.000
about
Token about
Feature activation+0.000
America
Token America
Feature activation+0.000
,
Token,
Feature activation+0.000
Arab
Token Arab
Feature activation+0.000
media
Token media
Feature activation+0.000
outlets
Token outlets
Feature activation+0.000
reported
Token reported
Feature activation+0.511
that
Token that
Feature activation+0.669
Israeli
Token Israeli
Feature activation+0.022
forces
Token forces
Feature activation+0.000
launched
Token launched
Feature activation+0.000
a
Token a
Feature activation+0.000
missile
Token missile
Feature activation+0.000
to
Token to
Feature activation+0.000
more
Token more
Feature activation+0.000
Canadian
Token Canadian
Feature activation+0.000
media
Token media
Feature activation+0.000
coverage
Token coverage
Feature activation+0.454
and
Token and
Feature activation+0.714
eventually
Token eventually
Feature activation+0.163
the
Token the
Feature activation+0.000
attention
Token attention
Feature activation+0.000
of
Token of
Feature activation+0.255
the
Token the
Feature activation+0.000
first
Token first
Feature activation+0.000
major
Token major
Feature activation+0.000
mainstream
Token mainstream
Feature activation+0.000
media
Token media
Feature activation+0.000
coverage
Token coverage
Feature activation+0.424
was
Token was
Feature activation+0.555
in
Token in
Feature activation+0.268
The
Token The
Feature activation+0.249
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+0.000

INTERVAL 0.243 - 0.486
CONTAINS 0.016%

Internet
Token Internet
Feature activation+0.000
and
Token and
Feature activation+0.000
social
Token social
Feature activation+0.000
media
Token media
Feature activation+0.000
by
Token by
Feature activation+0.088
our
Token our
Feature activation+0.291
side
Token side
Feature activation+0.004
,
Token,
Feature activation+0.000
it
Token it
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
,
Token,
Feature activation+0.000
media
Token media
Feature activation+0.042
and
Token and
Feature activation+1.055
non
Token non
Feature activation+1.227
-
Token-
Feature activation+1.010
governmental
Tokengovernmental
Feature activation+0.358
organisations
Token organisations
Feature activation+0.000
(
Token (
Feature activation+0.000
NG
TokenNG
Feature activation+0.000
Os
TokenOs
Feature activation+0.000
).
Token).
Feature activation+0.000
see
Token see
Feature activation+0.000
themselves
Token themselves
Feature activation+0.000
represented
Token represented
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
media
Token media
Feature activation+0.278
.
Token.
Feature activation+0.251
Wong
Token Wong
Feature activation+0.000
Fu
Token Fu
Feature activation+0.000
produces
Token produces
Feature activation+0.000
character
Token character
Feature activation+0.000
the
Token the
Feature activation+0.000
Press
Token Press
Feature activation+0.000
for
Token for
Feature activation+0.000
propaganda
Token propaganda
Feature activation+0.184
to
Token to
Feature activation+0.225
control
Token control
Feature activation+0.394
all
Token all
Feature activation+0.000
outlets
Token outlets
Feature activation+0.000
of
Token of
Feature activation+0.000
public
Token public
Feature activation+0.000
information
Token information
Feature activation+0.000
will
Token will
Feature activation+0.000
surface
Token surface
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
MSM
Token MSM
Feature activation+0.000
this
Token this
Feature activation+0.344
year
Token year
Feature activation+0.360
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
will
Token will
Feature activation+0.000

INTERVAL 0.000 - 0.243
CONTAINS 99.957%

of
Token of
Feature activation+0.000
psy
Token psy
Feature activation+0.000
b
Tokenb
Feature activation+0.000
ient
Tokenient
Feature activation+0.000
,
Token,
Feature activation+0.000
psy
Token psy
Feature activation+0.000
bass
Tokenbass
Feature activation+0.000
and
Token and
Feature activation+0.000
psy
Token psy
Feature activation+0.000
d
Tokend
Feature activation+0.000
ub
Tokenub
Feature activation+0.000
high
Token high
Feature activation+0.000
school
Token school
Feature activation+0.000
,
Token,
Feature activation+0.000
Casey
Token Casey
Feature activation+0.000
and
Token and
Feature activation+0.000
Miller
Token Miller
Feature activation+0.000
are
Token are
Feature activation+0.000
both
Token both
Feature activation+0.000
over
Token over
Feature activation+0.000
21
Token 21
Feature activation+0.000
and
Token and
Feature activation+0.000
ech
Tokenech
Feature activation+0.000
which
Token which
Feature activation+0.000
will
Token will
Feature activation+0.000
consume
Token consume
Feature activation+0.000
trees
Token trees
Feature activation+0.000
,
Token,
Feature activation+0.000
grass
Token grass
Feature activation+0.000
,
Token,
Feature activation+0.000
flowers
Token flowers
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
Wars
Token Wars
Feature activation+0.000
shirts
Token shirts
Feature activation+0.000
and
Token and
Feature activation+0.000
superhero
Token superhero
Feature activation+0.000
underwear
Token underwear
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Supp
Token Supp
Feature activation+0.000
lied
Tokenlied
Feature activation+0.000
)
Token )
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
want
Token want
Feature activation+0.000
to
Token to
Feature activation+0.000
expose
Token expose
Feature activation+0.000
his
Token his
Feature activation+0.000
2
Token 2
Feature activation+0.000
-
Token-
Feature activation+0.000
month
Tokenmonth
Feature activation+0.000
-
Token-
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 2 in H2.9: (feature 22897)

TOP ACTIVATIONS
MAX = 1.936

:
Token:
Feature activation+0.000
It
Token It
Feature activation+0.000
allows
Token allows
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.242
secretly
Token secretly
Feature activation+1.936
to
Token to
Feature activation+0.841
track
Token track
Feature activation+0.874
who
Token who
Feature activation+0.406
a
Token a
Feature activation+0.000
target
Token target
Feature activation+0.000
out
Token out
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
and
Token and
Feature activation+0.847
its
Token its
Feature activation+1.934
proxies
Token proxies
Feature activation+0.810
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
stock
Token stock
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.276
's
Token's
Feature activation+1.569
interest
Token interest
Feature activation+1.882
to
Token to
Feature activation+0.173
get
Token get
Feature activation+0.436
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
in
Token in
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.000
on
Token on
Feature activation+1.155
Thursday
Token Thursday
Feature activation+1.840
decided
Token decided
Feature activation+0.765
to
Token to
Feature activation+0.013
sue
Token sue
Feature activation+0.252
Pakistan
Token Pakistan
Feature activation+0.000
Te
Token Te
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
had
Token had
Feature activation+1.408
created
Token created
Feature activation+1.759
a
Token a
Feature activation+0.414
"
Token "
Feature activation+0.303
financial
Tokenfinancial
Feature activation+0.000
climate
Token climate
Feature activation+0.000
that
Token that
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.000
responded
Token responded
Feature activation+1.722
by
Token by
Feature activation+0.438
ignoring
Token ignoring
Feature activation+0.580
the
Token the
Feature activation+0.000
High
Token High
Feature activation+0.000
Court
Token Court
Feature activation+0.000
's
Token's
Feature activation+0.000
how
Token how
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
is
Token is
Feature activation+1.485
behaving
Token behaving
Feature activation+1.696
in
Token in
Feature activation+0.072
its
Token its
Feature activation+1.074
handling
Token handling
Feature activation+0.247
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.000
's
Token's
Feature activation+1.223
new
Token new
Feature activation+1.689
guide
Token guide
Feature activation+0.527
includes
Token includes
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
believes
Token believes
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.321
can
Token can
Feature activation+1.687
closely
Token closely
Feature activation+1.274
monitor
Token monitor
Feature activation+0.679
every
Token every
Feature activation+0.000
individual
Token individual
Feature activation+0.000
entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
message
Token message
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.007
is
Token is
Feature activation+1.687
trying
Token trying
Feature activation+1.469
to
Token to
Feature activation+0.685
look
Token look
Feature activation+0.815
after
Token after
Feature activation+0.000
children
Token children
Feature activation+0.000
[
Token [
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
]
Token]
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.500
should
Token should
Feature activation+1.620
not
Token not
Feature activation+1.262
force
Token force
Feature activation+1.200
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
essential
Token essential
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Government
Token Government
Feature activation+0.361
has
Token has
Feature activation+1.365
an
Token an
Feature activation+1.613
opportunity
Token opportunity
Feature activation+1.150
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.232
more
Token more
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
still
Token still
Feature activation+1.579
hasn
Token hasn
Feature activation+0.918
âĢ
TokenâĢ
Feature activation+0.508
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.044
followed
Token followed
Feature activation+0.239
it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.276
's
Token's
Feature activation+1.569
interest
Token interest
Feature activation+1.882
to
Token to
Feature activation+0.173
get
Token get
Feature activation+0.436
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
says
Token says
Feature activation+1.560
it
Token it
Feature activation+0.976
is
Token is
Feature activation+0.545
still
Token still
Feature activation+0.000
on
Token on
Feature activation+0.000
track
Token track
Feature activation+0.000
E
TokenE
Feature activation+0.000
by
Tokenby
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
needs
Token needs
Feature activation+1.558
to
Token to
Feature activation+0.775
address
Token address
Feature activation+0.883
"
Token "
Feature activation+0.000
deep
Tokendeep
Feature activation+0.000
and
Token and
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
.
Token.
Feature activation+0.000
"
Token "
Feature activation+0.000
Government
TokenGovernment
Feature activation+0.000
's
Token's
Feature activation+0.742
job
Token job
Feature activation+1.556
is
Token is
Feature activation+0.242
not
Token not
Feature activation+0.044
to
Token to
Feature activation+0.000
keep
Token keep
Feature activation+0.000
bureaucrats
Token bureaucrats
Feature activation+0.000
I
Token I
Feature activation+0.000
hope
Token hope
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
will
Token will
Feature activation+1.415
diss
Token diss
Feature activation+1.553
ociate
Tokenociate
Feature activation+1.089
from
Token from
Feature activation+0.027
them
Token them
Feature activation+0.000
,
Token,
Feature activation+0.000
otherwise
Token otherwise
Feature activation+0.000
that
Token that
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.380
is
Token is
Feature activation+1.512
intervening
Token intervening
Feature activation+1.530
in
Token in
Feature activation+0.277
one
Token one
Feature activation+0.220
area
Token area
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
saying
Token saying
Feature activation+0.000
that
Token that
Feature activation+0.000
since
Token since
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.380
is
Token is
Feature activation+1.512
intervening
Token intervening
Feature activation+1.530
in
Token in
Feature activation+0.277
one
Token one
Feature activation+0.220
area
Token area
Feature activation+0.000
,
Token,
Feature activation+0.000

Top DFA by src position
MAX = 2.593

Ŀ
TokenĿ
Feature activation+0.013
Top resid features:
:
Token:
Feature activation+0.046
Top resid features:
It
Token It
Feature activation+0.065
Top resid features:
allows
Token allows
Feature activation+0.242
Top resid features:
the
Token the
Feature activation+0.008
Top resid features:
government
Token government
Feature activation+2.559
Top resid features:
secretly
Token secretly
Feature activation+0.111
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
track
Token track
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
information
Token information
Feature activation+0.013
Top resid features:
coming
Token coming
Feature activation+0.058
Top resid features:
out
Token out
Feature activation+0.040
Top resid features:
from
Token from
Feature activation+0.042
Top resid features:
the
Token the
Feature activation+0.083
Top resid features:
government
Token government
Feature activation+2.338
Top resid features:
and
Token and
Feature activation+0.231
Top resid features:
its
Token its
Feature activation+0.133
Top resid features:
proxies
Token proxies
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.050
Top resid features:
it
Token it
Feature activation+0.033
Top resid features:
's
Token's
Feature activation+0.047
Top resid features:
in
Token in
Feature activation-0.036
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
government
Token government
Feature activation+2.183
Top resid features:
's
Token's
Feature activation+0.512
Top resid features:
interest
Token interest
Feature activation+0.105
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
AB
TokenAB
Feature activation+0.022
Top resid features:
AD
TokenAD
Feature activation+0.035
Top resid features:
:
Token:
Feature activation+0.073
Top resid features:
The
Token The
Feature activation+0.008
Top resid features:
federal
Token federal
Feature activation+0.516
Top resid features:
government
Token government
Feature activation+1.896
Top resid features:
on
Token on
Feature activation+0.245
Top resid features:
Thursday
Token Thursday
Feature activation+0.156
Top resid features:
decided
Token decided
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
sue
Token sue
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.028
Top resid features:
Burn
Token Burn
Feature activation+0.005
Top resid features:
ham
Tokenham
Feature activation+0.013
Top resid features:
said
Token said
Feature activation+0.129
Top resid features:
the
Token the
Feature activation+0.101
Top resid features:
government
Token government
Feature activation+2.390
Top resid features:
had
Token had
Feature activation+0.157
Top resid features:
created
Token created
Feature activation+0.105
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
financial
Tokenfinancial
Feature activation+0.000
Top resid features:
Icelandic
Token Icelandic
Feature activation+0.046
Top resid features:
.)
Token.)
Feature activation+0.020
Top resid features:
Ċ
TokenĊ
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
The
TokenThe
Feature activation-0.035
Top resid features:
government
Token government
Feature activation+2.593
Top resid features:
responded
Token responded
Feature activation+0.118
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
ignoring
Token ignoring
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
High
Token High
Feature activation+0.000
Top resid features:
-
Token -
Feature activation+0.073
Top resid features:
that
Token that
Feature activation+0.038
Top resid features:
's
Token's
Feature activation+0.008
Top resid features:
how
Token how
Feature activation+0.212
Top resid features:
the
Token the
Feature activation-0.062
Top resid features:
government
Token government
Feature activation+2.468
Top resid features:
is
Token is
Feature activation+0.123
Top resid features:
behaving
Token behaving
Feature activation+0.047
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
its
Token its
Feature activation+0.000
Top resid features:
handling
Token handling
Feature activation+0.000
Top resid features:
graduating
Token graduating
Feature activation+0.002
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.023
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
The
TokenThe
Feature activation-0.023
Top resid features:
government
Token government
Feature activation+2.213
Top resid features:
's
Token's
Feature activation+0.315
Top resid features:
new
Token new
Feature activation+0.113
Top resid features:
guide
Token guide
Feature activation+0.000
Top resid features:
includes
Token includes
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
Donald
TokenDonald
Feature activation+0.030
Top resid features:
Trump
Token Trump
Feature activation+0.076
Top resid features:
believes
Token believes
Feature activation+0.091
Top resid features:
that
Token that
Feature activation+0.129
Top resid features:
the
Token the
Feature activation+0.104
Top resid features:
government
Token government
Feature activation+2.413
Top resid features:
can
Token can
Feature activation+0.097
Top resid features:
closely
Token closely
Feature activation+0.000
Top resid features:
monitor
Token monitor
Feature activation+0.000
Top resid features:
every
Token every
Feature activation+0.000
Top resid features:
individual
Token individual
Feature activation+0.000
Top resid features:
sending
Token sending
Feature activation+0.090
Top resid features:
the
Token the
Feature activation+0.022
Top resid features:
message
Token message
Feature activation-0.036
Top resid features:
that
Token that
Feature activation+0.166
Top resid features:
the
Token the
Feature activation+0.105
Top resid features:
government
Token government
Feature activation+2.255
Top resid features:
is
Token is
Feature activation+0.120
Top resid features:
trying
Token trying
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
look
Token look
Feature activation+0.000
Top resid features:
after
Token after
Feature activation+0.000
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.090
Top resid features:
[
Token [
Feature activation+0.145
Top resid features:
but
Tokenbut
Feature activation+0.108
Top resid features:
]
Token]
Feature activation+0.025
Top resid features:
the
Token the
Feature activation+0.069
Top resid features:
government
Token government
Feature activation+2.209
Top resid features:
should
Token should
Feature activation+0.075
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
force
Token force
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
will
Tokenwill
Feature activation+0.018
Top resid features:
be
Token be
Feature activation+0.025
Top resid features:
essential
Token essential
Feature activation+0.061
Top resid features:
.
Token.
Feature activation+0.032
Top resid features:
The
Token The
Feature activation+0.064
Top resid features:
Government
Token Government
Feature activation+2.108
Top resid features:
has
Token has
Feature activation+0.207
Top resid features:
an
Token an
Feature activation+0.109
Top resid features:
opportunity
Token opportunity
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.044
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation+0.018
Top resid features:
But
TokenBut
Feature activation-0.092
Top resid features:
the
Token the
Feature activation-0.019
Top resid features:
government
Token government
Feature activation+2.495
Top resid features:
still
Token still
Feature activation+0.100
Top resid features:
hasn
Token hasn
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.073
Top resid features:
it
Token it
Feature activation+0.076
Top resid features:
's
Token's
Feature activation+0.017
Top resid features:
in
Token in
Feature activation+0.174
Top resid features:
the
Token the
Feature activation+0.106
Top resid features:
government
Token government
Feature activation+2.109
Top resid features:
's
Token's
Feature activation+0.128
Top resid features:
interest
Token interest
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.007
Top resid features:
Ċ
TokenĊ
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
But
TokenBut
Feature activation+0.085
Top resid features:
the
Token the
Feature activation+0.017
Top resid features:
government
Token government
Feature activation+2.353
Top resid features:
says
Token says
Feature activation+0.159
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
still
Token still
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.031
Top resid features:
E
TokenE
Feature activation-0.011
Top resid features:
by
Tokenby
Feature activation+0.056
Top resid features:
said
Token said
Feature activation+0.147
Top resid features:
the
Token the
Feature activation+0.026
Top resid features:
government
Token government
Feature activation+2.377
Top resid features:
needs
Token needs
Feature activation+0.131
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
address
Token address
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
deep
Tokendeep
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.045
Top resid features:
said
Token said
Feature activation+0.045
Top resid features:
Tuesday
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:
Government
TokenGovernment
Feature activation+2.001
Top resid features:
's
Token's
Feature activation+0.194
Top resid features:
job
Token job
Feature activation+0.107
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
not
Token not
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.048
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
I
Token I
Feature activation+0.004
Top resid features:
hope
Token hope
Feature activation+0.243
Top resid features:
the
Token the
Feature activation+0.116
Top resid features:
government
Token government
Feature activation+1.882
Top resid features:
will
Token will
Feature activation+0.200
Top resid features:
diss
Token diss
Feature activation+0.050
Top resid features:
ociate
Tokenociate
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
them
Token them
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.018
Top resid features:
saying
Token saying
Feature activation+0.051
Top resid features:
that
Token that
Feature activation+0.058
Top resid features:
since
Token since
Feature activation+0.104
Top resid features:
the
Token the
Feature activation+0.096
Top resid features:
government
Token government
Feature activation+2.130
Top resid features:
is
Token is
Feature activation+0.310
Top resid features:
intervening
Token intervening
Feature activation-0.023
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
area
Token area
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.015
Top resid features:
saying
Token saying
Feature activation+0.053
Top resid features:
that
Token that
Feature activation+0.084
Top resid features:
since
Token since
Feature activation+0.254
Top resid features:
the
Token the
Feature activation+0.046
Top resid features:
government
Token government
Feature activation+2.115
Top resid features:
is
Token is
Feature activation+0.137
Top resid features:
intervening
Token intervening
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
area
Token area
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.05

Head 2: 0.06

Head 3: 0.08

Head 4: 0.03

Head 5: 0.10

Head 6: 0.04

Head 7: 0.04

Head 8: 0.04

Head 9: 0.38

Head 10: 0.08

Head 11: 0.04

Positive logits

appoint1.54

orses1.42

1.41

istries1.39

Brady1.34

�醒1.27

Regulations1.27

legisl1.27

funding1.26

verning1.25

instit1.24

ْ1.23

ablished1.23

Fiat1.23

sworn1.22

1.22

subsid1.21

Regulatory1.21

authorised1.21

itates1.20

Negative logits

occurrence-1.30

etimes-1.29

vortex-1.27

teammate-1.19

Interstitial-1.18

rament-1.18

ancest-1.15

poems-1.13

teammates-1.12

karma-1.12

immersion-1.12

trivia-1.11

ny-1.11

plex-1.10

misfortune-1.10

archetype-1.10

visualization-1.09

occurrences-1.09

rue-1.09

rano-1.07

INTERVAL 1.743 - 1.936
CONTAINS 0.001%

:
Token:
Feature activation+0.000
It
Token It
Feature activation+0.000
allows
Token allows
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.242
secretly
Token secretly
Feature activation+1.936
to
Token to
Feature activation+0.841
track
Token track
Feature activation+0.874
who
Token who
Feature activation+0.406
a
Token a
Feature activation+0.000
target
Token target
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.000
on
Token on
Feature activation+1.155
Thursday
Token Thursday
Feature activation+1.840
decided
Token decided
Feature activation+0.765
to
Token to
Feature activation+0.013
sue
Token sue
Feature activation+0.252
Pakistan
Token Pakistan
Feature activation+0.000
Te
Token Te
Feature activation+0.000
ham
Tokenham
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
had
Token had
Feature activation+1.408
created
Token created
Feature activation+1.759
a
Token a
Feature activation+0.414
"
Token "
Feature activation+0.303
financial
Tokenfinancial
Feature activation+0.000
climate
Token climate
Feature activation+0.000
that
Token that
Feature activation+0.000
out
Token out
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
and
Token and
Feature activation+0.847
its
Token its
Feature activation+1.934
proxies
Token proxies
Feature activation+0.810
that
Token that
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
stock
Token stock
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.276
's
Token's
Feature activation+1.569
interest
Token interest
Feature activation+1.882
to
Token to
Feature activation+0.173
get
Token get
Feature activation+0.436
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
in
Token in
Feature activation+0.000

INTERVAL 1.549 - 1.743
CONTAINS 0.001%

it
Token it
Feature activation+0.000
's
Token's
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.276
's
Token's
Feature activation+1.569
interest
Token interest
Feature activation+1.882
to
Token to
Feature activation+0.173
get
Token get
Feature activation+0.436
it
Token it
Feature activation+0.000
right
Token right
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.000
's
Token's
Feature activation+1.223
new
Token new
Feature activation+1.689
guide
Token guide
Feature activation+0.527
includes
Token includes
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
of
Token of
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.000
responded
Token responded
Feature activation+1.722
by
Token by
Feature activation+0.438
ignoring
Token ignoring
Feature activation+0.580
the
Token the
Feature activation+0.000
High
Token High
Feature activation+0.000
Court
Token Court
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
still
Token still
Feature activation+1.579
hasn
Token hasn
Feature activation+0.918
âĢ
TokenâĢ
Feature activation+0.508
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.044
followed
Token followed
Feature activation+0.239
E
TokenE
Feature activation+0.000
by
Tokenby
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
needs
Token needs
Feature activation+1.558
to
Token to
Feature activation+0.775
address
Token address
Feature activation+0.883
"
Token "
Feature activation+0.000
deep
Tokendeep
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.356 - 1.549
CONTAINS 0.004%

by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.000
for
Token for
Feature activation+0.713
the
Token the
Feature activation+1.375
Islamic
Token Islamic
Feature activation+0.545
State
Token State
Feature activation+0.000
in
Token in
Feature activation+0.000
Iraq
Token Iraq
Feature activation+0.000
and
Token and
Feature activation+0.000
gal
Tokengal
Feature activation+0.000
infection
Token infection
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
government
Token government
Feature activation+0.000
recommends
Token recommends
Feature activation+1.402
doctors
Token doctors
Feature activation+0.000
stop
Token stop
Feature activation+0.000
using
Token using
Feature activation+0.144
any
Token any
Feature activation+0.000
sterile
Token sterile
Feature activation+0.000
is
Token is
Feature activation+0.000
saying
Token saying
Feature activation+0.000
the
Token the
Feature activation+0.000
Government
Token Government
Feature activation+0.000
is
Token is
Feature activation+1.348
shooting
Token shooting
Feature activation+1.473
itself
Token itself
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
foot
Token foot
Feature activation+0.000
by
Token by
Feature activation+0.000
,
Token,
Feature activation+0.000
urges
Token urges
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.049
to
Token to
Feature activation+1.242
introduce
Token introduce
Feature activation+1.499
a
Token a
Feature activation+0.280
voluntary
Token voluntary
Feature activation+0.061
body
Token body
Feature activation+0.078
that
Token that
Feature activation+0.000
would
Token would
Feature activation+0.000
First
Token First
Feature activation+0.000
wants
Token wants
Feature activation+0.000
the
Token the
Feature activation+0.000
Government
Token Government
Feature activation+0.044
to
Token to
Feature activation+1.222
cover
Token cover
Feature activation+1.506
the
Token the
Feature activation+0.587
cost
Token cost
Feature activation+0.186
of
Token of
Feature activation+0.000
fees
Token fees
Feature activation+0.037
,
Token,
Feature activation+0.000

INTERVAL 1.162 - 1.356
CONTAINS 0.007%

December
Token December
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
gave
Token gave
Feature activation+1.300
the
Token the
Feature activation+1.281
green
Token green
Feature activation+1.118
light
Tokenlight
Feature activation+0.000
for
Token for
Feature activation+0.000
10
Token 10
Feature activation+0.000
post
Token post
Feature activation+0.000
is
Token is
Feature activation+0.000
important
Token important
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
know
Token know
Feature activation+1.267
the
Token the
Feature activation+0.949
purchaser
Token purchaser
Feature activation+0.007
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
government
Token government
Feature activation+0.000
is
Token is
Feature activation+1.429
not
Token not
Feature activation+1.252
going
Token going
Feature activation+0.930
to
Token to
Feature activation+0.274
be
Token be
Feature activation+0.030
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
]
Token]
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.500
should
Token should
Feature activation+1.620
not
Token not
Feature activation+1.262
force
Token force
Feature activation+1.200
them
Token them
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
it
Token it
Feature activation+0.000
,
Token,
Feature activation+0.000
attacks
Token attacks
Feature activation+0.000
aside
Token aside
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
has
Token has
Feature activation+1.179
little
Token little
Feature activation+0.717
interest
Token interest
Feature activation+0.826
in
Token in
Feature activation+0.000
breaking
Token breaking
Feature activation+0.328
up
Token up
Feature activation+0.000

INTERVAL 0.968 - 1.162
CONTAINS 0.009%

for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
while
Token while
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.183
was
Token was
Feature activation+1.158
immensely
Token immensely
Feature activation+1.386
rich
Token rich
Feature activation+0.310
,
Token,
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
given
Token given
Feature activation+0.000
the
Token the
Feature activation+0.000
radical
Token radical
Feature activation+0.000
Taliban
Token Taliban
Feature activation+0.000
government
Token government
Feature activation+0.000
in
Token in
Feature activation+0.375
Afghanistan
Token Afghanistan
Feature activation+1.044
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.125
rise
Token rise
Feature activation+0.000
of
Token of
Feature activation+0.000
al
Token al
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
should
Token should
Feature activation+1.472
be
Token be
Feature activation+1.446
in
Token in
Feature activation+1.033
charge
Token charge
Feature activation+0.419
of
Token of
Feature activation+0.000
your
Token your
Feature activation+0.054
life
Token life
Feature activation+0.000
in
Token in
Feature activation+0.000
alienated
Token alienated
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
government
Token government
Feature activation+0.057
that
Token that
Feature activation+0.497
is
Token is
Feature activation+1.048
not
Token not
Feature activation+0.296
above
Token above
Feature activation+0.000
questionable
Token questionable
Feature activation+0.000
tactics
Token tactics
Feature activation+0.000
.
Token.
Feature activation+0.000
is
Token is
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.012
just
Token just
Feature activation+1.292
wants
Token wants
Feature activation+1.132
to
Token to
Feature activation+0.686
know
Token know
Feature activation+0.441
how
Token how
Feature activation+0.234
its
Token its
Feature activation+0.000
programs
Token programs
Feature activation+0.000

INTERVAL 0.775 - 0.968
CONTAINS 0.011%

to
Token to
Feature activation+0.000
parents
Token parents
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
.
Token.
Feature activation+0.799
Ċ
TokenĊ
Feature activation+0.205
Ċ
TokenĊ
Feature activation+0.073
The
TokenThe
Feature activation+0.000
guide
Token guide
Feature activation+0.000
from
Token from
Feature activation+0.000
Brotherhood
Token Brotherhood
Feature activation+0.000
-
Token-
Feature activation+0.000
dominated
Tokendominated
Feature activation+0.000
government
Token government
Feature activation+0.000
of
Token of
Feature activation+0.000
Egyptian
Token Egyptian
Feature activation+0.877
President
Token President
Feature activation+0.000
Mohamed
Token Mohamed
Feature activation+0.000
Morsi
Token Morsi
Feature activation+0.000
has
Token has
Feature activation+0.000
for
Token for
Feature activation+0.000
brought
Token brought
Feature activation+0.000
in
Token in
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.921
head
Token head
Feature activation+1.160
off
Token off
Feature activation+0.000
a
Token a
Feature activation+0.000
bubble
Token bubble
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
led
Token led
Feature activation+0.170
by
Token by
Feature activation+0.350
its
Token its
Feature activation+0.823
leader
Token leader
Feature activation+0.000
,
Token,
Feature activation+0.000
Nikola
Token Nikola
Feature activation+0.000
Gr
Token Gr
Feature activation+0.000
ue
Tokenue
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
local
Token local
Feature activation+0.000
government
Token government
Feature activation+0.000
denies
Token denies
Feature activation+0.832
the
Token the
Feature activation+0.360
crackdown
Token crackdown
Feature activation+0.000
on
Token on
Feature activation+0.000
Christianity
Token Christianity
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.581 - 0.775
CONTAINS 0.017%

âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
government
Token government
Feature activation+0.056
âĢ
TokenâĢ
Feature activation+0.276
Ļ
TokenĻ
Feature activation+0.585
s
Tokens
Feature activation+0.353
sources
Token sources
Feature activation+0.011
and
Token and
Feature activation+0.000
methods
Token methods
Feature activation+0.000
are
Token are
Feature activation+0.000
autonomous
Token autonomous
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.747
the
Token the
Feature activation+0.625
E
Token E
Feature activation+0.244
Z
TokenZ
Feature activation+0.000
L
TokenL
Feature activation+0.000
N
TokenN
Feature activation+0.000
has
Token has
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Blair
Token Blair
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.646
which
Token which
Feature activation+0.734
dropped
Token dropped
Feature activation+0.422
the
Token the
Feature activation+0.000
requirement
Token requirement
Feature activation+0.000
for
Token for
Feature activation+0.000
foreign
Token foreign
Feature activation+0.000
with
Token with
Feature activation+0.000
too
Token too
Feature activation+0.000
much
Token much
Feature activation+0.000
government
Token government
Feature activation+0.000
and
Token and
Feature activation+0.136
too
Token too
Feature activation+0.658
much
Token much
Feature activation+0.121
debt
Token debt
Feature activation+0.000
;
Token;
Feature activation+0.000
his
Token his
Feature activation+0.000
supporters
Token supporters
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
Federal
Token Federal
Feature activation+0.000
Government
Token Government
Feature activation+0.000
to
Token to
Feature activation+0.392
the
Token the
Feature activation+0.594
Hob
Token Hob
Feature activation+0.000
art
Tokenart
Feature activation+0.000
-
Token-
Feature activation+0.000
based
Tokenbased
Feature activation+0.000
chocolate
Token chocolate
Feature activation+0.000

INTERVAL 0.387 - 0.581
CONTAINS 0.022%

in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
interim
Token interim
Feature activation+0.000
government
Token government
Feature activation+0.000
will
Token will
Feature activation+0.136
do
Token do
Feature activation+0.448
everything
Token everything
Feature activation+0.000
in
Token in
Feature activation+0.000
their
Token their
Feature activation+0.000
power
Token power
Feature activation+0.000
to
Token to
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Australian
Token Australian
Feature activation+0.000
Government
Token Government
Feature activation+0.000
has
Token has
Feature activation+0.785
very
Token very
Feature activation+0.797
low
Token low
Feature activation+0.553
gross
Token gross
Feature activation+0.000
debt
Token debt
Feature activation+0.000
that
Token that
Feature activation+0.000
is
Token is
Feature activation+0.000
easily
Token easily
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
federal
Token federal
Feature activation+0.000
government
Token government
Feature activation+0.000
and
Token and
Feature activation+0.337
to
Token to
Feature activation+0.538
local
Token local
Feature activation+0.036
law
Token law
Feature activation+0.000
enforcement
Token enforcement
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
However
Token However
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
estimates
Token estimates
Feature activation+0.551
up
Token up
Feature activation+0.000
to
Token to
Feature activation+0.000
one
Token one
Feature activation+0.000
million
Token million
Feature activation+0.000
women
Token women
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
says
Token says
Feature activation+1.283
,
Token,
Feature activation+0.728
it
Token it
Feature activation+0.492
must
Token must
Feature activation+0.000
confirm
Token confirm
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
expert
Token expert
Feature activation+0.000

INTERVAL 0.194 - 0.387
CONTAINS 0.035%

predicted
Token predicted
Feature activation+0.000
dystopian
Token dystopian
Feature activation+0.000
governments
Token governments
Feature activation+0.000
and
Token and
Feature activation+0.000
not
Token not
Feature activation+0.244
being
Token being
Feature activation+0.293
able
Token able
Feature activation+0.275
to
Token to
Feature activation+0.281
breathe
Token breathe
Feature activation+0.000
the
Token the
Feature activation+0.000
polluted
Token polluted
Feature activation+0.000
said
Token said
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.000
will
Token will
Feature activation+0.000
ask
Token ask
Feature activation+0.262
Congress
Token Congress
Feature activation+0.000
to
Token to
Feature activation+0.000
establish
Token establish
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
governments
Token governments
Feature activation+0.000
have
Token have
Feature activation+0.686
become
Token become
Feature activation+1.064
adept
Token adept
Feature activation+0.334
at
Token at
Feature activation+0.000
getting
Token getting
Feature activation+0.000
their
Token their
Feature activation+0.000
own
Token own
Feature activation+0.000
way
Token way
Feature activation+0.000
This
TokenThis
Feature activation+0.000
scheme
Token scheme
Feature activation+0.000
(
Token (
Feature activation+0.000
of
Tokenof
Feature activation+0.000
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.246
)
Token)
Feature activation+0.717
has
Token has
Feature activation+0.737
been
Token been
Feature activation+0.643
accepted
Token accepted
Feature activation+0.380
,"
Token,"
Feature activation+0.000
,
Token,
Feature activation+0.000
elections
Token elections
Feature activation+0.000
,
Token,
Feature activation+0.000
government
Token government
Feature activation+0.000
-
Token-
Feature activation+0.000
and
Tokenand
Feature activation+0.295
-
Token-
Feature activation+0.751
politics
Tokenpolitics
Feature activation+0.405
,
Token,
Feature activation+0.000
aust
Token aust
Feature activation+0.000
ral
Tokenral
Feature activation+0.000

INTERVAL 0.000 - 0.194
CONTAINS 99.894%

on
Token on
Feature activation+0.000
going
Token going
Feature activation+0.000
.
Token.
Feature activation+0.000
Det
Token Det
Feature activation+0.000
ailing
Tokenailing
Feature activation+0.000
the
Token the
Feature activation+0.000
lives
Token lives
Feature activation+0.000
of
Token of
Feature activation+0.000
people
Token people
Feature activation+0.000
trying
Token trying
Feature activation+0.000
to
Token to
Feature activation+0.000
search
Token search
Feature activation+0.000
engines
Token engines
Feature activation+0.000
"
Token "
Feature activation+0.000
over
Tokenover
Feature activation+0.000
whelming
Tokenwhelming
Feature activation+0.000
ly
Tokenly
Feature activation+0.000
"
Token"
Feature activation+0.000
direct
Token direct
Feature activation+0.000
music
Token music
Feature activation+0.000
fans
Token fans
Feature activation+0.000
to
Token to
Feature activation+0.000
factors
Token factors
Feature activation+0.000
all
Token all
Feature activation+0.000
contribute
Token contribute
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
fast
Token fast
Feature activation+0.000
-
Token-
Feature activation+0.000
progress
Tokenprogress
Feature activation+0.000
ing
Tokening
Feature activation+0.000
cancer
Token cancer
Feature activation+0.000
,"
Token,"
Feature activation+0.000
and
Token and
Feature activation+0.000
kind
Token kind
Feature activation+0.000
words
Token words
Feature activation+0.000
,"
Token,"
Feature activation+0.000
the
Token the
Feature activation+0.000
dad
Token dad
Feature activation+0.000
said
Token said
Feature activation+0.000
there
Token there
Feature activation+0.000
's
Token's
Feature activation+0.000
another
Token another
Feature activation+0.000
person
Token person
Feature activation+0.000
his
Token his
Feature activation+0.000
appointment
Token appointment
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Tokenbut
Feature activation+0.000
was
Token was
Feature activation+0.000
promoted
Token promoted
Feature activation+0.000
to
Token to
Feature activation+0.000
rear
Token rear
Feature activation+0.000
adm
Token adm
Feature activation+0.000
iral
Tokeniral
Feature activation+0.000
.
Token.
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 3 in H2.9: (feature 16770)

TOP ACTIVATIONS
MAX = 1.573

East
Token East
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.573
gone
Token gone
Feature activation+1.156
c
Token c
Feature activation+0.517
uck
Tokenuck
Feature activation+0.000
oo
Tokenoo
Feature activation+0.000
for
Token for
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.043
is
Token is
Feature activation+1.543
grounded
Token grounded
Feature activation+1.217
upon
Token upon
Feature activation+0.000
suffering
Token suffering
Feature activation+0.097
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
UK
Token UK
Feature activation+0.000
.
Token.
Feature activation+0.000
Unless
Token Unless
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
sees
Token sees
Feature activation+1.509
a
Token a
Feature activation+0.703
second
Token second
Feature activation+0.103
green
Token green
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
,
Token,
Feature activation+0.000
film
Token film
Feature activation+0.000
industry
Token industry
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.478
truly
Token truly
Feature activation+1.032
changed
Token changed
Feature activation+1.005
.
Token.
Feature activation+0.456
Entertainment
Token Entertainment
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
continues
Token continues
Feature activation+1.345
warming
Token warming
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
warming
Token warming
Feature activation+0.000
tends
Token tends
Feature activation+0.000
.
Token.
Feature activation+0.000
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
saw
Token saw
Feature activation+1.325
Ferguson
Token Ferguson
Feature activation+0.344
Police
Token Police
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.043
is
Token is
Feature activation+1.543
grounded
Token grounded
Feature activation+1.217
upon
Token upon
Feature activation+0.000
suffering
Token suffering
Feature activation+0.097
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
I
TokenI
Feature activation+0.000
)
Token)
Feature activation+0.000
--
Token --
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.154
risks
Token risks
Feature activation+1.208
disastrous
Token disastrous
Feature activation+0.357
income
Token income
Feature activation+0.000
drops
Token drops
Feature activation+0.000
,
Token,
Feature activation+0.000
ecological
Token ecological
Feature activation+0.000
India
Token India
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
World
TokenWorld
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.161
Ļ
TokenĻ
Feature activation+0.638
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
dreaded
Token dreaded
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
"
Token "
Feature activation+0.000
The
TokenThe
Feature activation+0.000
World
Token World
Feature activation+0.000
's
Token's
Feature activation+0.000
Most
Token Most
Feature activation+0.464
Dangerous
Token Dangerous
Feature activation+1.160
Geek
Token Geek
Feature activation+0.000
":
Token":
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.573
gone
Token gone
Feature activation+1.156
c
Token c
Feature activation+0.517
uck
Tokenuck
Feature activation+0.000
oo
Tokenoo
Feature activation+0.000
for
Token for
Feature activation+0.000
cold
Token cold
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
was
Token was
Feature activation+1.150
o
Token o
Feature activation+0.400
gling
Tokengling
Feature activation+0.142
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
time
Token time
Feature activation+0.000
/
Token /
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
is
Token is
Feature activation+1.133
spinning
Token spinning
Feature activation+0.807
slower
Token slower
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
mind
Token mind
Feature activation+0.000
which
Token which
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.172
confronts
Token confronts
Feature activation+1.080
global
Token global
Feature activation+0.015
warming
Token warming
Feature activation+0.000
,
Token,
Feature activation+0.000
fossil
Token fossil
Feature activation+0.000
fuel
Token fuel
Feature activation+0.000
to
Token to
Feature activation+0.000
believe
Token believe
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
is
Token is
Feature activation+1.045
real
Token real
Feature activation+0.821
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
/
Token/
Feature activation+0.000
Jason
TokenJason
Feature activation+0.000
Reed
Token Reed
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.037
no
Token no
Feature activation+0.902
crystal
Token crystal
Feature activation+0.000
ball
Token ball
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
industry
Token industry
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.478
truly
Token truly
Feature activation+1.032
changed
Token changed
Feature activation+1.005
.
Token.
Feature activation+0.456
Entertainment
Token Entertainment
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.478
truly
Token truly
Feature activation+1.032
changed
Token changed
Feature activation+1.005
.
Token.
Feature activation+0.456
Entertainment
Token Entertainment
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
drivers
Token drivers
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
prepares
Token prepares
Feature activation+1.003
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000
say
Token say
Feature activation+0.000
will
Token will
Feature activation+0.000
keep
Token keep
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
safe
Token safe
Feature activation+0.977
from
Token from
Feature activation+0.000
Iran
Token Iran
Feature activation+0.000
's
Token's
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
ambitions
Token ambitions
Feature activation+0.000

Top DFA by src position
MAX = 2.273

Middle
Token Middle
Feature activation-0.014
Top resid features:
East
Token East
Feature activation-0.022
Top resid features:
!
Token!
Feature activation-0.061
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.265
Top resid features:
The
TokenThe
Feature activation-0.041
Top resid features:
world
Token world
Feature activation+2.273
Top resid features:
has
Token has
Feature activation-0.021
Top resid features:
gone
Token gone
Feature activation+0.000
Top resid features:
c
Token c
Feature activation+0.000
Top resid features:
uck
Tokenuck
Feature activation+0.000
Top resid features:
oo
Tokenoo
Feature activation+0.000
Top resid features:
words
Token words
Feature activation-0.038
Top resid features:
:
Token:
Feature activation-0.081
Top resid features:
âĢ
Token âĢ
Feature activation-0.013
Top resid features:
ľ
Tokenľ
Feature activation-0.038
Top resid features:
The
TokenThe
Feature activation-0.012
Top resid features:
world
Token world
Feature activation+2.148
Top resid features:
is
Token is
Feature activation-0.050
Top resid features:
grounded
Token grounded
Feature activation+0.000
Top resid features:
upon
Token upon
Feature activation+0.000
Top resid features:
suffering
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:
UK
Token UK
Feature activation-0.018
Top resid features:
.
Token.
Feature activation-0.124
Top resid features:
Unless
Token Unless
Feature activation-0.035
Top resid features:
the
Token the
Feature activation+0.027
Top resid features:
world
Token world
Feature activation+2.031
Top resid features:
sees
Token sees
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
green
Token green
Feature activation+0.000
Top resid features:
revolution
Token revolution
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.030
Top resid features:
film
Token film
Feature activation+0.007
Top resid features:
industry
Token industry
Feature activation-0.015
Top resid features:
?
Token?
Feature activation-0.179
Top resid features:
The
Token The
Feature activation+0.025
Top resid features:
world
Token world
Feature activation+2.083
Top resid features:
has
Token has
Feature activation-0.017
Top resid features:
truly
Token truly
Feature activation+0.000
Top resid features:
changed
Token changed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Entertainment
Token Entertainment
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.095
Top resid features:
Ċ
TokenĊ
Feature activation-0.057
Top resid features:
Ċ
TokenĊ
Feature activation-0.082
Top resid features:
As
TokenAs
Feature activation+0.294
Top resid features:
the
Token the
Feature activation-0.115
Top resid features:
world
Token world
Feature activation+1.920
Top resid features:
continues
Token continues
Feature activation-0.140
Top resid features:
warming
Token warming
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
warming
Token warming
Feature activation+0.000
Top resid features:
Aug
Token Aug
Feature activation-0.092
Top resid features:
.
Token.
Feature activation-0.045
Top resid features:
15
Token 15
Feature activation-0.057
Top resid features:
,
Token,
Feature activation-0.134
Top resid features:
the
Token the
Feature activation-0.005
Top resid features:
world
Token world
Feature activation+1.944
Top resid features:
saw
Token saw
Feature activation+0.104
Top resid features:
Ferguson
Token Ferguson
Feature activation+0.000
Top resid features:
Police
Token Police
Feature activation+0.000
Top resid features:
Chief
Token Chief
Feature activation+0.000
Top resid features:
Thomas
Token Thomas
Feature activation+0.000
Top resid features:
words
Token words
Feature activation-0.035
Top resid features:
:
Token:
Feature activation-0.072
Top resid features:
âĢ
Token âĢ
Feature activation-0.011
Top resid features:
ľ
Tokenľ
Feature activation-0.022
Top resid features:
The
TokenThe
Feature activation+0.017
Top resid features:
world
Token world
Feature activation+1.800
Top resid features:
is
Token is
Feature activation-0.108
Top resid features:
grounded
Token grounded
Feature activation-0.049
Top resid features:
upon
Token upon
Feature activation+0.000
Top resid features:
suffering
Token suffering
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
UP
TokenUP
Feature activation+0.002
Top resid features:
I
TokenI
Feature activation-0.000
Top resid features:
)
Token)
Feature activation-0.053
Top resid features:
--
Token --
Feature activation-0.140
Top resid features:
The
Token The
Feature activation+0.080
Top resid features:
world
Token world
Feature activation+1.826
Top resid features:
risks
Token risks
Feature activation-0.187
Top resid features:
disastrous
Token disastrous
Feature activation+0.000
Top resid features:
income
Token income
Feature activation+0.000
Top resid features:
drops
Token drops
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.045
Top resid features:
India
Token India
Feature activation-0.034
Top resid features:
.
Token.
Feature activation-0.138
Top resid features:
Ċ
TokenĊ
Feature activation-0.062
Top resid features:
Ċ
TokenĊ
Feature activation-0.091
Top resid features:
World
TokenWorld
Feature activation+1.912
Top resid features:
âĢ
TokenâĢ
Feature activation-0.079
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
most
Token most
Feature activation+0.000
Top resid features:
dreaded
Token dreaded
Feature activation+0.000
Top resid features:
kel
Tokenkel
Feature activation-0.012
Top resid features:
aptly
Token aptly
Feature activation-0.010
Top resid features:
entitled
Token entitled
Feature activation-0.113
Top resid features:
"
Token "
Feature activation-0.024
Top resid features:
The
TokenThe
Feature activation-0.035
Top resid features:
World
Token World
Feature activation+1.644
Top resid features:
's
Token's
Feature activation-0.203
Top resid features:
Most
Token Most
Feature activation+0.336
Top resid features:
Dangerous
Token Dangerous
Feature activation-0.030
Top resid features:
Geek
Token Geek
Feature activation+0.000
Top resid features:
":
Token":
Feature activation+0.000
Top resid features:
Middle
Token Middle
Feature activation-0.009
Top resid features:
East
Token East
Feature activation-0.018
Top resid features:
!
Token!
Feature activation-0.037
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.215
Top resid features:
The
TokenThe
Feature activation+0.061
Top resid features:
world
Token world
Feature activation+1.879
Top resid features:
has
Token has
Feature activation-0.190
Top resid features:
gone
Token gone
Feature activation-0.098
Top resid features:
c
Token c
Feature activation+0.000
Top resid features:
uck
Tokenuck
Feature activation+0.000
Top resid features:
oo
Tokenoo
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.041
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.118
Top resid features:
While
TokenWhile
Feature activation+0.029
Top resid features:
yesterday
Token yesterday
Feature activation-0.159
Top resid features:
the
Token the
Feature activation-0.058
Top resid features:
world
Token world
Feature activation+1.804
Top resid features:
was
Token was
Feature activation-0.044
Top resid features:
o
Token o
Feature activation+0.000
Top resid features:
gling
Tokengling
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
over
Token over
Feature activation-0.117
Top resid features:
time
Token time
Feature activation-0.041
Top resid features:
/
Token /
Feature activation-0.216
Top resid features:
But
Token But
Feature activation-0.181
Top resid features:
the
Token the
Feature activation+0.004
Top resid features:
world
Token world
Feature activation+2.053
Top resid features:
is
Token is
Feature activation-0.062
Top resid features:
spinning
Token spinning
Feature activation+0.000
Top resid features:
slower
Token slower
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
my
Token my
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.058
Top resid features:
which
Token which
Feature activation-0.067
Top resid features:
,
Token,
Feature activation-0.155
Top resid features:
as
Token as
Feature activation+0.121
Top resid features:
the
Token the
Feature activation-0.067
Top resid features:
world
Token world
Feature activation+1.717
Top resid features:
confronts
Token confronts
Feature activation-0.021
Top resid features:
global
Token global
Feature activation+0.000
Top resid features:
warming
Token warming
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
fossil
Token fossil
Feature activation+0.000
Top resid features:
audience
Token audience
Feature activation+0.004
Top resid features:
to
Token to
Feature activation-0.067
Top resid features:
believe
Token believe
Feature activation-0.155
Top resid features:
that
Token that
Feature activation-0.189
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
world
Token world
Feature activation+1.886
Top resid features:
is
Token is
Feature activation-0.101
Top resid features:
real
Token real
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
they
Token they
Feature activation+0.000
Top resid features:
Reuters
Token Reuters
Feature activation-0.004
Top resid features:
/
Token/
Feature activation-0.133
Top resid features:
Jason
TokenJason
Feature activation-0.046
Top resid features:
Reed
Token Reed
Feature activation-0.075
Top resid features:
The
Token The
Feature activation-0.009
Top resid features:
world
Token world
Feature activation+1.765
Top resid features:
has
Token has
Feature activation-0.018
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
crystal
Token crystal
Feature activation+0.000
Top resid features:
ball
Token ball
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.026
Top resid features:
film
Token film
Feature activation-0.003
Top resid features:
industry
Token industry
Feature activation+0.000
Top resid features:
?
Token?
Feature activation-0.128
Top resid features:
The
Token The
Feature activation+0.037
Top resid features:
world
Token world
Feature activation+1.594
Top resid features:
has
Token has
Feature activation-0.104
Top resid features:
truly
Token truly
Feature activation-0.012
Top resid features:
changed
Token changed
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Entertainment
Token Entertainment
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
film
Token film
Feature activation+0.009
Top resid features:
industry
Token industry
Feature activation-0.002
Top resid features:
?
Token?
Feature activation-0.118
Top resid features:
The
Token The
Feature activation+0.027
Top resid features:
world
Token world
Feature activation+1.476
Top resid features:
has
Token has
Feature activation-0.061
Top resid features:
truly
Token truly
Feature activation+0.002
Top resid features:
changed
Token changed
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Entertainment
Token Entertainment
Feature activation+0.000
Top resid features:
bad
Token bad
Feature activation-0.016
Top resid features:
drivers
Token drivers
Feature activation-0.067
Top resid features:
.
Token.
Feature activation-0.221
Top resid features:
As
Token As
Feature activation+0.270
Top resid features:
the
Token the
Feature activation-0.054
Top resid features:
world
Token world
Feature activation+1.432
Top resid features:
prepares
Token prepares
Feature activation-0.024
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
coming
Token coming
Feature activation+0.000
Top resid features:
future
Token future
Feature activation+0.000
Top resid features:
supporters
Token supporters
Feature activation-0.058
Top resid features:
say
Token say
Feature activation-0.086
Top resid features:
will
Token will
Feature activation-0.068
Top resid features:
keep
Token keep
Feature activation-0.051
Top resid features:
the
Token the
Feature activation-0.039
Top resid features:
world
Token world
Feature activation+1.812
Top resid features:
safe
Token safe
Feature activation-0.133
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Iran
Token Iran
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
nuclear
Token nuclear
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.03

Head 2: 0.08

Head 3: 0.09

Head 4: 0.03

Head 5: 0.05

Head 6: 0.04

Head 7: 0.04

Head 8: 0.05

Head 9: 0.37

Head 10: 0.07

Head 11: 0.04

Positive logits

mite1.25

م1.25

Latter1.20

descended1.19

ゼウス1.16

civilisation1.15

Mormons1.14

Lens1.12

gra1.12

population1.12

Antarctica1.12

atcher1.12

envy1.11

Glac1.11

warming1.10

inhab1.09

Origin1.09

Mecca1.09

hesion1.08

upuncture1.08

Negative logits

incent-1.97

tein-1.71

oyal-1.66

weeney-1.47

sqor-1.46

anwhile-1.43

ullivan-1.41

sidx-1.40

principals-1.34

rompt-1.28

ussian-1.28

specify-1.27

ersen-1.26

additionally-1.24

BILITIES-1.24

instructional-1.22

WAR-1.22

vious-1.22

akov-1.21

uez-1.21

INTERVAL 1.416 - 1.573
CONTAINS 0.000%

film
Token film
Feature activation+0.000
industry
Token industry
Feature activation+0.000
?
Token?
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.478
truly
Token truly
Feature activation+1.032
changed
Token changed
Feature activation+1.005
.
Token.
Feature activation+0.456
Entertainment
Token Entertainment
Feature activation+0.000
is
Token is
Feature activation+0.000
UK
Token UK
Feature activation+0.000
.
Token.
Feature activation+0.000
Unless
Token Unless
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
sees
Token sees
Feature activation+1.509
a
Token a
Feature activation+0.703
second
Token second
Feature activation+0.103
green
Token green
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
,
Token,
Feature activation+0.000
East
Token East
Feature activation+0.000
!
Token!
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.573
gone
Token gone
Feature activation+1.156
c
Token c
Feature activation+0.517
uck
Tokenuck
Feature activation+0.000
oo
Tokenoo
Feature activation+0.000
for
Token for
Feature activation+0.000
:
Token:
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.043
is
Token is
Feature activation+1.543
grounded
Token grounded
Feature activation+1.217
upon
Token upon
Feature activation+0.000
suffering
Token suffering
Feature activation+0.097
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000

INTERVAL 1.258 - 1.416
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
continues
Token continues
Feature activation+1.345
warming
Token warming
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
warming
Token warming
Feature activation+0.000
tends
Token tends
Feature activation+0.000
.
Token.
Feature activation+0.000
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
saw
Token saw
Feature activation+1.325
Ferguson
Token Ferguson
Feature activation+0.344
Police
Token Police
Feature activation+0.000
Chief
Token Chief
Feature activation+0.000
Thomas
Token Thomas
Feature activation+0.000
Jackson
Token Jackson
Feature activation+0.000

INTERVAL 1.101 - 1.258
CONTAINS 0.001%

I
TokenI
Feature activation+0.000
)
Token)
Feature activation+0.000
--
Token --
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.154
risks
Token risks
Feature activation+1.208
disastrous
Token disastrous
Feature activation+0.357
income
Token income
Feature activation+0.000
drops
Token drops
Feature activation+0.000
,
Token,
Feature activation+0.000
ecological
Token ecological
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
While
TokenWhile
Feature activation+0.000
yesterday
Token yesterday
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
was
Token was
Feature activation+1.150
o
Token o
Feature activation+0.400
gling
Tokengling
Feature activation+0.142
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
iPhone
Token iPhone
Feature activation+0.000
time
Token time
Feature activation+0.000
/
Token /
Feature activation+0.000
But
Token But
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
is
Token is
Feature activation+1.133
spinning
Token spinning
Feature activation+0.807
slower
Token slower
Feature activation+0.000
in
Token in
Feature activation+0.000
my
Token my
Feature activation+0.000
mind
Token mind
Feature activation+0.000
India
Token India
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
World
TokenWorld
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.161
Ļ
TokenĻ
Feature activation+0.638
s
Tokens
Feature activation+0.000
most
Token most
Feature activation+0.000
dreaded
Token dreaded
Feature activation+0.000
terrorist
Token terrorist
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.043
is
Token is
Feature activation+1.543
grounded
Token grounded
Feature activation+1.217
upon
Token upon
Feature activation+0.000
suffering
Token suffering
Feature activation+0.097
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000

INTERVAL 0.944 - 1.101
CONTAINS 0.001%

Still
Token Still
Feature activation+0.000
,
Token,
Feature activation+0.000
neither
Token neither
Feature activation+0.000
world
Token world
Feature activation+0.000
of
Token of
Feature activation+0.043
performances
Token performances
Feature activation+0.953
hinted
Token hinted
Feature activation+0.000
at
Token at
Feature activation+0.000
a
Token a
Feature activation+0.000
blockbuster
Token blockbuster
Feature activation+0.000
-
Token-
Feature activation+0.000
ago
Token ago
Feature activation+0.000
and
Token and
Feature activation+0.000
tell
Token tell
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
we
Token we
Feature activation+0.952
need
Token need
Feature activation+0.393
your
Token your
Feature activation+0.319
capital
Token capital
Feature activation+0.011
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
to
Token to
Feature activation+0.000
believe
Token believe
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
is
Token is
Feature activation+1.045
real
Token real
Feature activation+0.821
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
/
Token/
Feature activation+0.000
Jason
TokenJason
Feature activation+0.000
Reed
Token Reed
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+1.037
no
Token no
Feature activation+0.902
crystal
Token crystal
Feature activation+0.000
ball
Token ball
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
drivers
Token drivers
Feature activation+0.000
.
Token.
Feature activation+0.000
As
Token As
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
prepares
Token prepares
Feature activation+1.003
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
coming
Token coming
Feature activation+0.000
future
Token future
Feature activation+0.000
of
Token of
Feature activation+0.000

INTERVAL 0.786 - 0.944
CONTAINS 0.002%

look
Token look
Feature activation+0.000
upon
Token upon
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.122
that
Token that
Feature activation+0.593
has
Token has
Feature activation+0.854
benefited
Token benefited
Feature activation+0.495
enormously
Token enormously
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
world
Token world
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
world
Token world
Feature activation+0.183
is
Token is
Feature activation+0.959
divided
Token divided
Feature activation+0.883
into
Token into
Feature activation+0.000
regions
Token regions
Feature activation+0.000
(
Token (
Feature activation+0.000
each
Tokeneach
Feature activation+0.000
town
Token town
Feature activation+0.000
1970
Token 1970
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
that
Token that
Feature activation+0.239
had
Token had
Feature activation+0.796
already
Token already
Feature activation+0.199
become
Token become
Feature activation+0.065
compl
Token compl
Feature activation+0.000
acent
Tokenacent
Feature activation+0.000
about
Token about
Feature activation+0.000
believe
Token believe
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
is
Token is
Feature activation+1.045
real
Token real
Feature activation+0.821
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
they
Token they
Feature activation+0.000
absolutely
Token absolutely
Feature activation+0.000
help
Token help
Feature activation+0.000
TR
TokenTR
Feature activation+0.000
ON
TokenON
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
has
Token has
Feature activation+0.874
demanded
Token demanded
Feature activation+0.164
that
Token that
Feature activation+0.000
female
Token female
Feature activation+0.000
hero
Token hero
Feature activation+0.000
ines
Tokenines
Feature activation+0.000

INTERVAL 0.629 - 0.786
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Unless
Token Unless
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
sees
Token sees
Feature activation+1.509
a
Token a
Feature activation+0.703
second
Token second
Feature activation+0.103
green
Token green
Feature activation+0.000
revolution
Token revolution
Feature activation+0.000
,
Token,
Feature activation+0.000
some
Token some
Feature activation+0.000
the
Token the
Feature activation+0.000
nation
Token nation
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
forward
Token forward
Feature activation+0.675
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
believe
Token believe
Feature activation+0.000
Mitt
Token Mitt
Feature activation+0.000
Romney
Token Romney
Feature activation+0.000
you
Token you
Feature activation+0.000
are
Token are
Feature activation+0.000
making
Token making
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
a
Token a
Feature activation+0.692
better
Token better
Feature activation+0.886
place
Token place
Feature activation+0.903
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
i
Tokeni
Feature activation+0.000
has
Token has
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
at
Token at
Feature activation+0.591
his
Token his
Feature activation+0.775
feet
Token feet
Feature activation+0.284
,"
Token,"
Feature activation+0.000
S
Token S
Feature activation+0.000
oun
Tokenoun
Feature activation+0.000
ess
Tokeness
Feature activation+0.000
time
Token time
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
of
Token of
Feature activation+0.000
talking
Token talking
Feature activation+0.679
dinosaurs
Token dinosaurs
Feature activation+0.000
was
Token was
Feature activation+0.000
restricted
Token restricted
Feature activation+0.000
to
Token to
Feature activation+0.000
largely
Token largely
Feature activation+0.000

INTERVAL 0.472 - 0.629
CONTAINS 0.003%

âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.780
Ļ
TokenĻ
Feature activation+0.559
s
Tokens
Feature activation+0.000
gone
Token gone
Feature activation+0.000
crazy
Token crazy
Feature activation+0.114
!
Token!
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
rem
Tokenrem
Feature activation+0.000
ake
Tokenake
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
in
Token in
Feature activation+0.109
our
Token our
Feature activation+0.549
image
Token image
Feature activation+0.293
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
On
TokenOn
Feature activation+0.000
we
Token we
Feature activation+0.000
will
Token will
Feature activation+0.000
have
Token have
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
or
Token or
Feature activation+0.501
not
Token not
Feature activation+0.658
going
Token going
Feature activation+0.389
forward
Token forward
Feature activation+0.883
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ASH
TokenASH
Feature activation+0.000
:
Token:
Feature activation+0.000
The
Token The
Feature activation+0.000
earth
Token earth
Feature activation+0.000
has
Token has
Feature activation+0.214
experienced
Token experienced
Feature activation+0.517
much
Token much
Feature activation+0.000
higher
Token higher
Feature activation+0.000
carbon
Token carbon
Feature activation+0.000
dioxide
Token dioxide
Feature activation+0.000
levels
Token levels
Feature activation+0.000
upon
Token upon
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.122
that
Token that
Feature activation+0.593
has
Token has
Feature activation+0.854
benefited
Token benefited
Feature activation+0.495
enormously
Token enormously
Feature activation+0.000
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
international
Token international
Feature activation+0.000
order
Token order
Feature activation+0.000

INTERVAL 0.315 - 0.472
CONTAINS 0.006%

Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
think
Token think
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
still
Token still
Feature activation+0.398
exists
Token exists
Feature activation+0.600
/
Token/
Feature activation+0.000
Only
Token Only
Feature activation+0.000
this
Token this
Feature activation+0.000
room
Token room
Feature activation+0.000
;
Token;
Feature activation+0.000
print
Token print
Feature activation+0.000
"
Token "
Feature activation+0.000
Hello
TokenHello
Feature activation+0.000
world
Token world
Feature activation+0.000
";
Token";
Feature activation+0.356
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Per
TokenPer
Feature activation+0.000
l
Tokenl
Feature activation+0.000
scripts
Token scripts
Feature activation+0.000
the
Token the
Feature activation+0.000
eyes
Token eyes
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
will
Token will
Feature activation+0.391
be
Token be
Feature activation+0.102
following
Token following
Feature activation+0.135
our
Token our
Feature activation+0.000
leadership
Token leadership
Feature activation+0.000
in
Token in
Feature activation+0.000
s
Tokens
Feature activation+0.000
not
Token not
Feature activation+0.000
a
Token a
Feature activation+0.000
world
Token world
Feature activation+0.000
-
Token-
Feature activation+0.000
sh
Tokensh
Feature activation+0.326
attering
Tokenattering
Feature activation+0.446
revelation
Token revelation
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
if
Token if
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
as
Token as
Feature activation+0.193
it
Token it
Feature activation+0.356
is
Token is
Feature activation+0.084
:
Token:
Feature activation+0.000
as
Token as
Feature activation+0.000
imper
Token imper
Feature activation+0.000
manent
Tokenmanent
Feature activation+0.000

INTERVAL 0.157 - 0.315
CONTAINS 0.012%

ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
automotive
Token automotive
Feature activation+0.000
world
Token world
Feature activation+0.000
needed
Token needed
Feature activation+0.236
a
Token a
Feature activation+0.232
change
Token change
Feature activation+0.288
and
Token and
Feature activation+0.000
Tesla
Token Tesla
Feature activation+0.000
was
Token was
Feature activation+0.000
moving
Token moving
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
Our
TokenOur
Feature activation+0.000
country
Token country
Feature activation+0.000
deserves
Token deserves
Feature activation+0.159
better
Token better
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
became
Token became
Feature activation+0.000
one
Token one
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.265
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
wealthiest
Token wealthiest
Feature activation+0.000
and
Token and
Feature activation+0.000
most
Token most
Feature activation+0.000
bring
Token bring
Feature activation+0.000
the
Token the
Feature activation+0.000
whole
Token whole
Feature activation+0.000
world
Token world
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.192
all
Token all
Feature activation+0.007
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
people
Token people
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
state
Token state
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
world
Token world
Feature activation+0.000
is
Token is
Feature activation+0.161
showing
Token showing
Feature activation+0.512
some
Token some
Feature activation+0.000
eerie
Token eerie
Feature activation+0.000
similarities
Token similarities
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.000 - 0.157
CONTAINS 99.972%

cognitive
Token cognitive
Feature activation+0.000
performance
Token performance
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
a
Token a
Feature activation+0.000
bit
Token bit
Feature activation+0.000
like
Token like
Feature activation+0.000
leveraging
Token leveraging
Feature activation+0.000
a
Token a
Feature activation+0.000
large
Token large
Feature activation+0.000
study
Token study
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
body
Token body
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Two
TokenTwo
Feature activation+0.000
Rutgers
Token Rutgers
Feature activation+0.000
students
Token students
Feature activation+0.000
have
Token have
Feature activation+0.000
been
Token been
Feature activation+0.000
charged
Token charged
Feature activation+0.000
Delhi
Token Delhi
Feature activation+0.000
on
Token on
Feature activation+0.000
Tuesday
Token Tuesday
Feature activation+0.000
."
Token."
Feature activation+0.000
The
TokenThe
Feature activation+0.000
DG
Token DG
Feature activation+0.000
CA
TokenCA
Feature activation+0.000
grounded
Token grounded
Feature activation+0.000
the
Token the
Feature activation+0.000
pilot
Token pilot
Feature activation+0.000
on
Token on
Feature activation+0.000
election
Tokenelection
Feature activation+0.000
in
Token in
Feature activation+0.000
November
Token November
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
I
Token I
Feature activation+0.000
do
Token do
Feature activation+0.000
extraction
Token extraction
Feature activation+0.000
on
Token on
Feature activation+0.000
those
Token those
Feature activation+0.000
same
Token same
Feature activation+0.000
lands
Token lands
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
architects
Token architects
Feature activation+0.000
of
Token of
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 4 in H2.9: (feature 10260)

TOP ACTIVATIONS
MAX = 2.539

able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.000
in
Token in
Feature activation+2.365
contact
Token contact
Feature activation+1.839
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
source
Token source
Feature activation+0.000
,
Token,
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.673
said
Token said
Feature activation+2.168
the
Token the
Feature activation+1.305
Obama
Token Obama
Feature activation+0.670
administration
Token administration
Feature activation+0.010
was
Token was
Feature activation+0.000
alarmed
Token alarmed
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Times
Token Times
Feature activation+0.559
,
Token,
Feature activation+2.139
h
Token h
Feature activation+1.013
/
Token/
Feature activation+0.624
t
Tokent
Feature activation+0.000
CBS
Token CBS
Feature activation+0.000
Sports
Token Sports
Feature activation+0.000
full
Token full
Feature activation+0.000
story
Token story
Feature activation+0.000
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.359
and
Token and
Feature activation+2.101
The
Token The
Feature activation+1.584
Telegraph
Token Telegraph
Feature activation+0.855
.
Token.
Feature activation+0.730
Ċ
TokenĊ
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.000
The
Token The
Feature activation+0.000
aide
Token aide
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.634
the
Token the
Feature activation+2.099
publisher
Token publisher
Feature activation+1.553
will
Token will
Feature activation+0.000
receive
Token receive
Feature activation+0.000
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
reporting
Token reporting
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.148
also
Token also
Feature activation+2.096
has
Token has
Feature activation+1.416
been
Token been
Feature activation+1.000
unable
Token unable
Feature activation+0.348
to
Token to
Feature activation+0.000
locate
Token locate
Feature activation+0.455
i
Token i
Feature activation+0.000
ME
TokenME
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.387
,
Token,
Feature activation+2.009
maintains
Token maintains
Feature activation+0.794
that
Token that
Feature activation+0.495
his
Token his
Feature activation+0.266
sourcing
Token sourcing
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.360
that
Token that
Feature activation+1.944
he
Token he
Feature activation+1.030
âĢ
Token âĢ
Feature activation+0.287
ľ
Tokenľ
Feature activation+0.000
would
Tokenwould
Feature activation+0.000
hope
Token hope
Feature activation+0.000
was
Token was
Feature activation+0.000
published
Token published
Feature activation+0.000
in
Token in
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.266
on
Token on
Feature activation+1.863
7
Token 7
Feature activation+1.661
October
Token October
Feature activation+0.498
1915
Token 1915
Feature activation+0.061
confirming
Token confirming
Feature activation+0.000
the
Token the
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.000
in
Token in
Feature activation+2.365
contact
Token contact
Feature activation+1.839
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
source
Token source
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.893
âĢ
TokenâĢ
Feature activation+1.838
Ļ
TokenĻ
Feature activation+1.046
s
Tokens
Feature activation+0.784
reporting
Token reporting
Feature activation+1.144
is
Token is
Feature activation+0.000
accurate
Token accurate
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
criticizing
Token criticizing
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.085
over
Token over
Feature activation+1.810
this
Token this
Feature activation+1.060
;
Token;
Feature activation+0.330
stories
Token stories
Feature activation+0.261
get
Token get
Feature activation+0.000
rewritten
Token rewritten
Feature activation+0.000
©
Token ©
Feature activation+0.000
2019
Token 2019
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.676
LLC
Token LLC
Feature activation+0.734
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Let
TokenLet
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
©
Token ©
Feature activation+0.000
2019
Token 2019
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.676
LLC
Token LLC
Feature activation+0.779
.
Token.
Feature activation+0.000
Click
Token Click
Feature activation+0.040
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
published
Token published
Feature activation+0.000
in
Token in
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.266
on
Token on
Feature activation+1.863
7
Token 7
Feature activation+1.661
October
Token October
Feature activation+0.498
1915
Token 1915
Feature activation+0.061
confirming
Token confirming
Feature activation+0.000
the
Token the
Feature activation+0.000
known
Token known
Feature activation+0.000
©
Token ©
Feature activation+0.000
2019
Token 2019
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.614
LLC
Token LLC
Feature activation+0.660
.
Token.
Feature activation+0.000
Click
Token Click
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
story
Token story
Feature activation+0.000
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.359
and
Token and
Feature activation+2.101
The
Token The
Feature activation+1.584
Telegraph
Token Telegraph
Feature activation+0.855
.
Token.
Feature activation+0.730
Ċ
TokenĊ
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
aide
Token aide
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.634
the
Token the
Feature activation+2.099
publisher
Token publisher
Feature activation+1.553
will
Token will
Feature activation+0.000
receive
Token receive
Feature activation+0.000
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Moscow
Token Moscow
Feature activation+0.000
Times
Token Times
Feature activation+0.000
(@
Token (@
Feature activation+1.356
Moscow
TokenMoscow
Feature activation+0.349
Times
TokenTimes
Feature activation+0.000
)
Token)
Feature activation+1.541
May
Token May
Feature activation+0.794
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
©
Token ©
Feature activation+0.000
2019
Token 2019
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.540
LLC
Token LLC
Feature activation+0.575
.
Token.
Feature activation+0.000
Click
Token Click
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000

Top DFA by src position
MAX = 4.012

been
Token been
Feature activation-0.045
Top resid features:
able
Token able
Feature activation-0.021
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
put
Token put
Feature activation-0.402
Top resid features:
the
Token the
Feature activation+0.357
Top resid features:
Times
Token Times
Feature activation+4.012
Top resid features:
in
Token in
Feature activation+0.145
Top resid features:
contact
Token contact
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
either
Token either
Feature activation+0.000
Top resid features:
source
Token source
Feature activation+0.000
Top resid features:
Congress
Token Congress
Feature activation-0.006
Top resid features:
last
Token last
Feature activation+0.033
Top resid features:
month
Token month
Feature activation-0.034
Top resid features:
,
Token,
Feature activation+0.210
Top resid features:
the
Token the
Feature activation+0.184
Top resid features:
Times
Token Times
Feature activation+3.091
Top resid features:
said
Token said
Feature activation+0.048
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Obama
Token Obama
Feature activation+0.000
Top resid features:
administration
Token administration
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
."
Token."
Feature activation+0.051
Top resid features:
Ċ
TokenĊ
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
[
Token[
Feature activation+0.366
Top resid features:
The
TokenThe
Feature activation+0.079
Top resid features:
Times
Token Times
Feature activation+3.474
Top resid features:
,
Token,
Feature activation-0.024
Top resid features:
h
Token h
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
CBS
Token CBS
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.032
Top resid features:
full
Token full
Feature activation-0.072
Top resid features:
story
Token story
Feature activation+0.059
Top resid features:
at
Token at
Feature activation+0.141
Top resid features:
The
Token The
Feature activation+0.202
Top resid features:
Times
Token Times
Feature activation+3.375
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Telegraph
Token Telegraph
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.108
Top resid features:
The
Token The
Feature activation-0.022
Top resid features:
aide
Token aide
Feature activation+0.065
Top resid features:
told
Token told
Feature activation+0.005
Top resid features:
the
Token the
Feature activation+0.080
Top resid features:
Times
Token Times
Feature activation+3.213
Top resid features:
the
Token the
Feature activation+0.297
Top resid features:
publisher
Token publisher
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
receive
Token receive
Feature activation+0.000
Top resid features:
half
Token half
Feature activation+0.000
Top resid features:
extensive
Token extensive
Feature activation-0.059
Top resid features:
reporting
Token reporting
Feature activation-0.061
Top resid features:
efforts
Token efforts
Feature activation-0.131
Top resid features:
,
Token,
Feature activation+0.226
Top resid features:
The
Token The
Feature activation+0.169
Top resid features:
Times
Token Times
Feature activation+3.457
Top resid features:
also
Token also
Feature activation+0.133
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
unable
Token unable
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.021
Top resid features:
i
Token i
Feature activation+0.115
Top resid features:
ME
TokenME
Feature activation+0.067
Top resid features:
and
Token and
Feature activation+0.132
Top resid features:
the
Token the
Feature activation+0.337
Top resid features:
Times
Token Times
Feature activation+2.915
Top resid features:
,
Token,
Feature activation+0.095
Top resid features:
maintains
Token maintains
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
sourcing
Token sourcing
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.013
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
Trump
TokenTrump
Feature activation-0.036
Top resid features:
told
Token told
Feature activation-0.163
Top resid features:
the
Token the
Feature activation+0.257
Top resid features:
Times
Token Times
Feature activation+3.169
Top resid features:
that
Token that
Feature activation+0.332
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
would
Tokenwould
Feature activation+0.000
Top resid features:
notice
Token notice
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.043
Top resid features:
published
Token published
Feature activation+0.033
Top resid features:
in
Token in
Feature activation+0.205
Top resid features:
The
Token The
Feature activation+0.189
Top resid features:
Times
Token Times
Feature activation+2.984
Top resid features:
on
Token on
Feature activation+0.102
Top resid features:
7
Token 7
Feature activation+0.000
Top resid features:
October
Token October
Feature activation+0.000
Top resid features:
1915
Token 1915
Feature activation+0.000
Top resid features:
confirming
Token confirming
Feature activation+0.000
Top resid features:
been
Token been
Feature activation-0.003
Top resid features:
able
Token able
Feature activation-0.025
Top resid features:
to
Token to
Feature activation+0.017
Top resid features:
put
Token put
Feature activation-0.224
Top resid features:
the
Token the
Feature activation+0.196
Top resid features:
Times
Token Times
Feature activation+3.168
Top resid features:
in
Token in
Feature activation+0.561
Top resid features:
contact
Token contact
Feature activation-0.067
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
either
Token either
Feature activation+0.000
Top resid features:
source
Token source
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.001
Top resid features:
But
TokenBut
Feature activation-0.088
Top resid features:
if
Token if
Feature activation+0.257
Top resid features:
the
Token the
Feature activation+0.321
Top resid features:
Times
Token Times
Feature activation+3.076
Top resid features:
âĢ
TokenâĢ
Feature activation+0.147
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
reporting
Token reporting
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
particularly
Token particularly
Feature activation-0.031
Top resid features:
interested
Token interested
Feature activation-0.057
Top resid features:
in
Token in
Feature activation+0.034
Top resid features:
criticizing
Token criticizing
Feature activation+0.341
Top resid features:
the
Token the
Feature activation+0.301
Top resid features:
Times
Token Times
Feature activation+2.739
Top resid features:
over
Token over
Feature activation+0.054
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.000
Top resid features:
stories
Token stories
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
Copyright
TokenCopyright
Feature activation-0.129
Top resid features:
©
Token ©
Feature activation+0.097
Top resid features:
2019
Token 2019
Feature activation+0.038
Top resid features:
The
Token The
Feature activation+0.187
Top resid features:
Washington
Token Washington
Feature activation+0.150
Top resid features:
Times
Token Times
Feature activation+2.877
Top resid features:
,
Token,
Feature activation+0.129
Top resid features:
LLC
Token LLC
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
Let
TokenLet
Feature activation+0.000
Top resid features:
Copyright
TokenCopyright
Feature activation-0.107
Top resid features:
©
Token ©
Feature activation+0.127
Top resid features:
2019
Token 2019
Feature activation+0.060
Top resid features:
The
Token The
Feature activation+0.231
Top resid features:
Washington
Token Washington
Feature activation+0.118
Top resid features:
Times
Token Times
Feature activation+2.853
Top resid features:
,
Token,
Feature activation+0.125
Top resid features:
LLC
Token LLC
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Click
Token Click
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
notice
Token notice
Feature activation-0.010
Top resid features:
was
Token was
Feature activation+0.013
Top resid features:
published
Token published
Feature activation-0.045
Top resid features:
in
Token in
Feature activation+0.129
Top resid features:
The
Token The
Feature activation+0.081
Top resid features:
Times
Token Times
Feature activation+2.615
Top resid features:
on
Token on
Feature activation+0.560
Top resid features:
7
Token 7
Feature activation+0.051
Top resid features:
October
Token October
Feature activation+0.000
Top resid features:
1915
Token 1915
Feature activation+0.000
Top resid features:
confirming
Token confirming
Feature activation+0.000
Top resid features:
Copyright
TokenCopyright
Feature activation-0.099
Top resid features:
©
Token ©
Feature activation+0.071
Top resid features:
2019
Token 2019
Feature activation+0.062
Top resid features:
The
Token The
Feature activation+0.200
Top resid features:
Washington
Token Washington
Feature activation+0.143
Top resid features:
Times
Token Times
Feature activation+2.844
Top resid features:
,
Token,
Feature activation+0.148
Top resid features:
LLC
Token LLC
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Click
Token Click
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.005
Top resid features:
full
Token full
Feature activation-0.072
Top resid features:
story
Token story
Feature activation+0.059
Top resid features:
at
Token at
Feature activation+0.083
Top resid features:
The
Token The
Feature activation-0.002
Top resid features:
Times
Token Times
Feature activation+2.665
Top resid features:
and
Token and
Feature activation+0.381
Top resid features:
The
Token The
Feature activation+0.138
Top resid features:
Telegraph
Token Telegraph
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.088
Top resid features:
The
Token The
Feature activation-0.013
Top resid features:
aide
Token aide
Feature activation+0.070
Top resid features:
told
Token told
Feature activation+0.093
Top resid features:
the
Token the
Feature activation+0.157
Top resid features:
Times
Token Times
Feature activation+2.151
Top resid features:
the
Token the
Feature activation+0.597
Top resid features:
publisher
Token publisher
Feature activation+0.171
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
receive
Token receive
Feature activation+0.000
Top resid features:
half
Token half
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.006
Top resid features:
Moscow
Token Moscow
Feature activation+0.014
Top resid features:
Times
Token Times
Feature activation+0.589
Top resid features:
(@
Token (@
Feature activation+0.618
Top resid features:
Moscow
TokenMoscow
Feature activation+0.049
Top resid features:
Times
TokenTimes
Feature activation+1.716
Top resid features:
)
Token)
Feature activation+0.280
Top resid features:
May
Token May
Feature activation+0.000
Top resid features:
15
Token 15
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
2015
Token 2015
Feature activation+0.000
Top resid features:
Copyright
TokenCopyright
Feature activation-0.150
Top resid features:
©
Token ©
Feature activation+0.113
Top resid features:
2019
Token 2019
Feature activation+0.029
Top resid features:
The
Token The
Feature activation+0.166
Top resid features:
Washington
Token Washington
Feature activation+0.056
Top resid features:
Times
Token Times
Feature activation+2.927
Top resid features:
,
Token,
Feature activation+0.144
Top resid features:
LLC
Token LLC
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Click
Token Click
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.04

Head 1: 0.05

Head 2: 0.11

Head 3: 0.07

Head 4: 0.04

Head 5: 0.11

Head 6: 0.03

Head 7: 0.04

Head 8: 0.06

Head 9: 0.36

Head 10: 0.06

Head 11: 0.04

Positive logits

Britann1.46

BBC1.34

Journals1.34

hari1.32

Mysteries1.32

Journal1.32

Newsp1.31

Transcript1.30

Cust1.29

Parables1.29

Herald1.27

DragonMagazine1.26

Newsletter1.26

Faw1.26

Breaking1.25

arthed1.24

��1.22

Magazine1.22

camel1.20

Ltd1.19

Negative logits

disadvantage-1.31

gap-1.27

uphill-1.27

lear-1.26

capacity-1.26

advant-1.25

scal-1.23

inferior-1.20

detrim-1.18

backward-1.15

biologically-1.13

frac-1.12

Chaser-1.09

ptr-1.09

spacing-1.09

seat-1.07

relational-1.06

otropic-1.06

downside-1.06

scar-1.06

INTERVAL 2.286 - 2.539
CONTAINS 0.000%

able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.000
in
Token in
Feature activation+2.365
contact
Token contact
Feature activation+1.839
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
source
Token source
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 2.032 - 2.286
CONTAINS 0.001%

The
Token The
Feature activation+0.000
aide
Token aide
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.634
the
Token the
Feature activation+2.099
publisher
Token publisher
Feature activation+1.553
will
Token will
Feature activation+0.000
receive
Token receive
Feature activation+0.000
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
[
Token[
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Times
Token Times
Feature activation+0.559
,
Token,
Feature activation+2.139
h
Token h
Feature activation+1.013
/
Token/
Feature activation+0.624
t
Tokent
Feature activation+0.000
CBS
Token CBS
Feature activation+0.000
Sports
Token Sports
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.673
said
Token said
Feature activation+2.168
the
Token the
Feature activation+1.305
Obama
Token Obama
Feature activation+0.670
administration
Token administration
Feature activation+0.010
was
Token was
Feature activation+0.000
alarmed
Token alarmed
Feature activation+0.000
reporting
Token reporting
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.148
also
Token also
Feature activation+2.096
has
Token has
Feature activation+1.416
been
Token been
Feature activation+1.000
unable
Token unable
Feature activation+0.348
to
Token to
Feature activation+0.000
locate
Token locate
Feature activation+0.455
full
Token full
Feature activation+0.000
story
Token story
Feature activation+0.000
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.359
and
Token and
Feature activation+2.101
The
Token The
Feature activation+1.584
Telegraph
Token Telegraph
Feature activation+0.855
.
Token.
Feature activation+0.730
Ċ
TokenĊ
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 1.778 - 2.032
CONTAINS 0.001%

was
Token was
Feature activation+0.000
published
Token published
Feature activation+0.000
in
Token in
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.266
on
Token on
Feature activation+1.863
7
Token 7
Feature activation+1.661
October
Token October
Feature activation+0.498
1915
Token 1915
Feature activation+0.061
confirming
Token confirming
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
But
TokenBut
Feature activation+0.000
if
Token if
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.893
âĢ
TokenâĢ
Feature activation+1.838
Ļ
TokenĻ
Feature activation+1.046
s
Tokens
Feature activation+0.784
reporting
Token reporting
Feature activation+1.144
is
Token is
Feature activation+0.000
accurate
Token accurate
Feature activation+0.000
to
Token to
Feature activation+0.000
put
Token put
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.000
in
Token in
Feature activation+2.365
contact
Token contact
Feature activation+1.839
with
Token with
Feature activation+0.000
either
Token either
Feature activation+0.000
source
Token source
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
i
Token i
Feature activation+0.000
ME
TokenME
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.387
,
Token,
Feature activation+2.009
maintains
Token maintains
Feature activation+0.794
that
Token that
Feature activation+0.495
his
Token his
Feature activation+0.266
sourcing
Token sourcing
Feature activation+0.000
is
Token is
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.360
that
Token that
Feature activation+1.944
he
Token he
Feature activation+1.030
âĢ
Token âĢ
Feature activation+0.287
ľ
Tokenľ
Feature activation+0.000
would
Tokenwould
Feature activation+0.000
hope
Token hope
Feature activation+0.000

INTERVAL 1.524 - 1.778
CONTAINS 0.001%

©
Token ©
Feature activation+0.000
2019
Token 2019
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.614
LLC
Token LLC
Feature activation+0.660
.
Token.
Feature activation+0.000
Click
Token Click
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
Moscow
Token Moscow
Feature activation+0.000
Times
Token Times
Feature activation+0.000
(@
Token (@
Feature activation+1.356
Moscow
TokenMoscow
Feature activation+0.349
Times
TokenTimes
Feature activation+0.000
)
Token)
Feature activation+1.541
May
Token May
Feature activation+0.794
15
Token 15
Feature activation+0.000
,
Token,
Feature activation+0.000
2015
Token 2015
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
©
Token ©
Feature activation+0.000
2019
Token 2019
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.676
LLC
Token LLC
Feature activation+0.779
.
Token.
Feature activation+0.000
Click
Token Click
Feature activation+0.040
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
©
Token ©
Feature activation+0.000
2019
Token 2019
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.540
LLC
Token LLC
Feature activation+0.575
.
Token.
Feature activation+0.000
Click
Token Click
Feature activation+0.000
here
Token here
Feature activation+0.000
for
Token for
Feature activation+0.000
aide
Token aide
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.634
the
Token the
Feature activation+2.099
publisher
Token publisher
Feature activation+1.553
will
Token will
Feature activation+0.000
receive
Token receive
Feature activation+0.000
half
Token half
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 1.270 - 1.524
CONTAINS 0.001%

ough
Tokenough
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.053
he
Token he
Feature activation+1.389
did
Token did
Feature activation+0.576
not
Token not
Feature activation+0.106
want
Token want
Feature activation+0.154
to
Token to
Feature activation+0.151
go
Token go
Feature activation+0.000
Li
Token Li
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Global
Token Global
Feature activation+0.000
Times
Token Times
Feature activation+0.000
on
Token on
Feature activation+1.281
Wednesday
Token Wednesday
Feature activation+0.504
.
Token.
Feature activation+0.119
Ex
TokenEx
Feature activation+0.000
ternally
Tokenternally
Feature activation+0.000
,
Token,
Feature activation+0.000
efforts
Token efforts
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.148
also
Token also
Feature activation+2.096
has
Token has
Feature activation+1.416
been
Token been
Feature activation+1.000
unable
Token unable
Feature activation+0.348
to
Token to
Feature activation+0.000
locate
Token locate
Feature activation+0.455
or
Token or
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.636
of
Token of
Feature activation+1.009
India
Token India
Feature activation+1.404
Friday
Token Friday
Feature activation+0.474
.
Token.
Feature activation+0.174
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
Kejriwal
Token Kejriwal
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
New
TokenNew
Feature activation+0.000
Times
Token Times
Feature activation+0.000
:
Token:
Feature activation+1.417
You
Token You
Feature activation+0.450
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
toured
Token toured
Feature activation+0.000

INTERVAL 1.016 - 1.270
CONTAINS 0.002%

According
Token According
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Cap
Token Cap
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+1.244
Governor
Token Governor
Feature activation+0.115
Walker
Token Walker
Feature activation+0.000
and
Token and
Feature activation+0.000
his
Token his
Feature activation+0.000
allies
Token allies
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
the
Token the
Feature activation+0.000
Seattle
Token Seattle
Feature activation+0.000
Times
Token Times
Feature activation+0.000
reported
Token reported
Feature activation+1.183
.
Token.
Feature activation+0.090
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
©
Token©
Feature activation+0.000
Provided
Token Provided
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.360
that
Token that
Feature activation+1.944
he
Token he
Feature activation+1.030
âĢ
Token âĢ
Feature activation+0.287
ľ
Tokenľ
Feature activation+0.000
would
Tokenwould
Feature activation+0.000
hope
Token hope
Feature activation+0.000
that
Token that
Feature activation+0.000
editors
Token editors
Feature activation+0.000
have
Token have
Feature activation+0.000
concluded
Token concluded
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+1.023
cannot
Token cannot
Feature activation+1.019
v
Token v
Feature activation+0.830
ouch
Tokenouch
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Support
TokenSupport
Feature activation+0.000
Times
Token Times
Feature activation+0.000
of
Token of
Feature activation+0.671
San
Token San
Feature activation+1.080
Diego
Token Diego
Feature activation+0.563
's
Token's
Feature activation+0.000
growth
Token growth
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.762 - 1.016
CONTAINS 0.003%

in
Token in
Feature activation+0.000
The
Token The
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+0.299
,
Token,
Feature activation+0.836
under
Token under
Feature activation+0.463
the
Token the
Feature activation+0.053
headline
Token headline
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
the
Token the
Feature activation+0.000
Los
Token Los
Feature activation+0.000
Angeles
Token Angeles
Feature activation+0.000
Times
Token Times
Feature activation+0.000
,
Token,
Feature activation+0.948
describes
Token describes
Feature activation+0.922
border
Token border
Feature activation+0.000
officers
Token officers
Feature activation+0.000
shooting
Token shooting
Feature activation+0.000
at
Token at
Feature activation+0.000
moving
Token moving
Feature activation+0.000
ME
TokenME
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.387
,
Token,
Feature activation+2.009
maintains
Token maintains
Feature activation+0.794
that
Token that
Feature activation+0.495
his
Token his
Feature activation+0.266
sourcing
Token sourcing
Feature activation+0.000
is
Token is
Feature activation+0.000
all
Token all
Feature activation+0.000
Kejriwal
Token Kejriwal
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.636
of
Token of
Feature activation+1.009
India
Token India
Feature activation+1.404
Friday
Token Friday
Feature activation+0.474
.
Token.
Feature activation+0.174
Mr
Token Mr
Feature activation+0.000
.
Token.
Feature activation+0.000
at
Token at
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.359
and
Token and
Feature activation+2.101
The
Token The
Feature activation+1.584
Telegraph
Token Telegraph
Feature activation+0.855
.
Token.
Feature activation+0.730
Ċ
TokenĊ
Feature activation+0.049
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.508 - 0.762
CONTAINS 0.003%

for
Token for
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.725
including
Token including
Feature activation+1.196
paying
Token paying
Feature activation+0.740
close
Token close
Feature activation+0.000
attention
Token attention
Feature activation+0.000
to
Token to
Feature activation+0.000
visual
Token visual
Feature activation+0.000
integrity
Token integrity
Feature activation+0.000
in
Token in
Feature activation+0.000
The
Token The
Feature activation+0.000
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+0.000
saying
Token saying
Feature activation+0.538
that
Token that
Feature activation+0.000
large
Token large
Feature activation+0.000
segments
Token segments
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
ton
Tokenton
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.053
he
Token he
Feature activation+1.389
did
Token did
Feature activation+0.576
not
Token not
Feature activation+0.106
want
Token want
Feature activation+0.154
to
Token to
Feature activation+0.151
go
Token go
Feature activation+0.000
into
Token into
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Support
TokenSupport
Feature activation+0.000
Times
Token Times
Feature activation+0.000
of
Token of
Feature activation+0.671
San
Token San
Feature activation+1.080
Diego
Token Diego
Feature activation+0.563
's
Token's
Feature activation+0.000
growth
Token growth
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
with
Tokenwith
Feature activation+0.000
story
Token story
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
NY
Token NY
Feature activation+0.000
Times
TokenTimes
Feature activation+0.506
about
Token about
Feature activation+0.537
how
Token how
Feature activation+0.342
the
Token the
Feature activation+0.117
Strauss
Token Strauss
Feature activation+0.480
-
Token-
Feature activation+0.000
K
TokenK
Feature activation+0.000

INTERVAL 0.254 - 0.508
CONTAINS 0.005%

the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
Times
Token Times
Feature activation+0.356
(
Token (
Feature activation+1.415
via
Tokenvia
Feature activation+0.564
SW
Token SW
Feature activation+0.306
7
Token7
Feature activation+0.000
News
TokenNews
Feature activation+0.000
).
Token).
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
notice
Token notice
Feature activation+0.000
was
Token was
Feature activation+0.000
published
Token published
Feature activation+0.000
in
Token in
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.266
on
Token on
Feature activation+1.863
7
Token 7
Feature activation+1.661
October
Token October
Feature activation+0.498
1915
Token 1915
Feature activation+0.061
confirming
Token confirming
Feature activation+0.000
investigation
Token investigation
Feature activation+0.000
by
Token by
Feature activation+0.000
The
Token The
Feature activation+0.000
Times
Token Times
Feature activation+0.000
found
Token found
Feature activation+0.781
the
Token the
Feature activation+0.298
companies
Token companies
Feature activation+0.128
promoted
Token promoted
Feature activation+0.000
on
Token on
Feature activation+0.000
videos
Token videos
Feature activation+0.000
posted
Token posted
Feature activation+0.000
complex
Token complex
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
Journal
Token Journal
Feature activation+0.000
reported
Token reported
Feature activation+0.392
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
She
Token She
Feature activation+0.000
the
Token the
Feature activation+0.000
Times
Token Times
Feature activation+0.085
over
Token over
Feature activation+1.810
this
Token this
Feature activation+1.060
;
Token;
Feature activation+0.330
stories
Token stories
Feature activation+0.261
get
Token get
Feature activation+0.000
rewritten
Token rewritten
Feature activation+0.000
all
Token all
Feature activation+0.000
the
Token the
Feature activation+0.000
time
Token time
Feature activation+0.000

INTERVAL 0.000 - 0.254
CONTAINS 99.985%

EX
TokenEX
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
Click
Token Click
Feature activation+0.000
image
Token image
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
3
Token 3
Feature activation+0.000
D
TokenD
Feature activation+0.000
model
Token model
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
air
Tokenair
Feature activation+0.000
writes
Token writes
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
threat
Token threat
Feature activation+0.000
of
Token of
Feature activation+0.000
nuclear
Token nuclear
Feature activation+0.000
war
Token war
Feature activation+0.000
is
Token is
Feature activation+0.000
higher
Token higher
Feature activation+0.000
now
Token now
Feature activation+0.000
West
Token West
Feature activation+0.000
London
Token London
Feature activation+0.000
collaboration
Token collaboration
Feature activation+0.000
of
Token of
Feature activation+0.000
clinical
Token clinical
Feature activation+0.000
commission
Token commission
Feature activation+0.000
ing
Tokening
Feature activation+0.000
groups
Token groups
Feature activation+0.000
(
Token (
Feature activation+0.000
CC
TokenCC
Feature activation+0.000
G
TokenG
Feature activation+0.000
the
Token the
Feature activation+0.000
film
Token film
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
water
Token water
Feature activation+0.000
color
Tokencolor
Feature activation+0.000
-
Token-
Feature activation+0.000
esque
Tokenesque
Feature activation+0.000
color
Token color
Feature activation+0.000
palette
Token palette
Feature activation+0.000
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
she
Token she
Feature activation+0.000
needed
Token needed
Feature activation+0.000
help
Token help
Feature activation+0.000
and
Token and
Feature activation+0.000
needed
Token needed
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
taken
Token taken
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 5 in H2.9: (feature 7321)

TOP ACTIVATIONS
MAX = 2.510

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.919
reported
Token reported
Feature activation+2.510
that
Token that
Feature activation+1.597
British
Token British
Feature activation+0.449
and
Token and
Feature activation+0.000
US
Token US
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
their
Token their
Feature activation+0.000
approval
Token approval
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.544
called
Token called
Feature activation+2.031
the
Token the
Feature activation+1.443
deal
Token deal
Feature activation+0.780
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
Oxford
Token Oxford
Feature activation+0.000
University
Token University
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.048
reports
Token reports
Feature activation+1.945
.
Token.
Feature activation+0.208
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
"
Token"
Feature activation+0.000
People
TokenPeople
Feature activation+0.000
in
Token in
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.448
reported
Token reported
Feature activation+1.930
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
During
TokenDuring
Feature activation+0.000
an
Token an
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
FT
Token FT
Feature activation+0.925
,
Token,
Feature activation+1.718
citing
Token citing
Feature activation+1.929
anonymous
Token anonymous
Feature activation+0.700
officials
Token officials
Feature activation+0.202
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
Davis
Token Davis
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.943
Express
Token Express
Feature activation+1.730
has
Token has
Feature activation+1.926
come
Token come
Feature activation+1.295
across
Token across
Feature activation+0.572
some
Token some
Feature activation+0.000
very
Token very
Feature activation+0.000
valuable
Token valuable
Feature activation+0.000
Speaking
Token Speaking
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Daily
Token Daily
Feature activation+0.118
Telegraph
Token Telegraph
Feature activation+0.806
,
Token,
Feature activation+1.815
Amanda
Token Amanda
Feature activation+1.114
Ross
Token Ross
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
runs
Token runs
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.286
contacted
Token contacted
Feature activation+1.809
more
Token more
Feature activation+0.727
than
Token than
Feature activation+0.503
a
Token a
Feature activation+0.050
dozen
Token dozen
Feature activation+0.000
people
Token people
Feature activation+0.000
major
Token major
Feature activation+0.000
operation
Token operation
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.217
reported
Token reported
Feature activation+1.762
that
Token that
Feature activation+0.919
at
Token at
Feature activation+0.438
least
Token least
Feature activation+0.000
eight
Token eight
Feature activation+0.000
police
Token police
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.943
Express
Token Express
Feature activation+1.730
has
Token has
Feature activation+1.926
come
Token come
Feature activation+1.295
across
Token across
Feature activation+0.572
some
Token some
Feature activation+0.000
very
Token very
Feature activation+0.000
of
Token of
Feature activation+0.000
Maryland
Token Maryland
Feature activation+0.000
,
Token,
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.572
reported
Token reported
Feature activation+1.727
.
Token.
Feature activation+0.636
That
Token That
Feature activation+0.019
led
Token led
Feature activation+0.000
to
Token to
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
FT
Token FT
Feature activation+0.925
,
Token,
Feature activation+1.718
citing
Token citing
Feature activation+1.929
anonymous
Token anonymous
Feature activation+0.700
officials
Token officials
Feature activation+0.202
,
Token,
Feature activation+0.000
said
Token said
Feature activation+0.000
and
Token and
Feature activation+0.000
shared
Token shared
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.496
,
Token,
Feature activation+1.717
urges
Token urges
Feature activation+0.807
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
introduce
Token introduce
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
8
Token8
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
The
Token The
Feature activation+0.000
Telegraph
Token Telegraph
Feature activation+0.959
(@
Token (@
Feature activation+1.600
Te
TokenTe
Feature activation+0.302
legraph
Tokenlegraph
Feature activation+0.059
)
Token)
Feature activation+0.706
August
Token August
Feature activation+0.238
4
Token 4
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.919
reported
Token reported
Feature activation+2.510
that
Token that
Feature activation+1.597
British
Token British
Feature activation+0.449
and
Token and
Feature activation+0.000
US
Token US
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000
agencies
Token agencies
Feature activation+0.000
regarding
Token regarding
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.562
Ŀ
TokenĿ
Feature activation+0.820
âĢĵ
Token âĢĵ
Feature activation+0.140
and
Token and
Feature activation+0.476
he
Token he
Feature activation+0.171
clearly
Token clearly
Feature activation+0.000
Russia
Token Russia
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.142
he
Token he
Feature activation+1.556
would
Token would
Feature activation+0.627
be
Token be
Feature activation+0.484
âĢ
Token âĢ
Feature activation+0.423
ľ
Tokenľ
Feature activation+0.000
more
Tokenmore
Feature activation+0.062
Channel
Token Channel
Feature activation+0.000
4
Token 4
Feature activation+0.000
and
Token and
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.598
.
Token.
Feature activation+1.525
Sophie
Token Sophie
Feature activation+1.127
Walker
Token Walker
Feature activation+0.000
called
Token called
Feature activation+0.000
me
Token me
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.459
watched
Token watched
Feature activation+1.497
as
Token as
Feature activation+0.218
Lock
Token Lock
Feature activation+0.542
ett
Tokenett
Feature activation+0.000
was
Token was
Feature activation+0.000
covered
Token covered
Feature activation+0.000
complex
Token complex
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Sun
Token Sun
Feature activation+0.000
Journal
Token Journal
Feature activation+0.454
reported
Token reported
Feature activation+1.496
.
Token.
Feature activation+0.636
Ċ
TokenĊ
Feature activation+0.059
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
She
Token She
Feature activation+0.083

Top DFA by src position
MAX = 3.655

contractor
Token contractor
Feature activation-0.031
Top resid features:
.
Token.
Feature activation+0.001
Top resid features:
Ċ
TokenĊ
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.042
Top resid features:
The
TokenThe
Feature activation+0.407
Top resid features:
Guardian
Token Guardian
Feature activation+3.655
Top resid features:
reported
Token reported
Feature activation-0.031
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
British
Token British
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
ed
Tokened
Feature activation-0.015
Top resid features:
their
Token their
Feature activation-0.007
Top resid features:
approval
Token approval
Feature activation-0.002
Top resid features:
.
Token.
Feature activation+0.053
Top resid features:
The
Token The
Feature activation+0.413
Top resid features:
Guardian
Token Guardian
Feature activation+3.157
Top resid features:
called
Token called
Feature activation+0.008
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
deal
Token deal
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.023
Top resid features:
Oxford
Token Oxford
Feature activation+0.025
Top resid features:
University
Token University
Feature activation-0.021
Top resid features:
,
Token,
Feature activation-0.054
Top resid features:
the
Token the
Feature activation+0.395
Top resid features:
Guardian
Token Guardian
Feature activation+3.121
Top resid features:
reports
Token reports
Feature activation-0.077
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
"
Token"
Feature activation+0.000
Top resid features:
State
Token State
Feature activation-0.010
Top resid features:
in
Token in
Feature activation-0.008
Top resid features:
Syria
Token Syria
Feature activation-0.007
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
the
Token the
Feature activation+0.317
Top resid features:
Guardian
Token Guardian
Feature activation+2.992
Top resid features:
reported
Token reported
Feature activation-0.015
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
During
TokenDuring
Feature activation+0.000
Top resid features:
affected
Token affected
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
Ċ
TokenĊ
Feature activation+0.010
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
The
TokenThe
Feature activation+0.347
Top resid features:
FT
Token FT
Feature activation+2.612
Top resid features:
,
Token,
Feature activation+0.192
Top resid features:
citing
Token citing
Feature activation-0.034
Top resid features:
anonymous
Token anonymous
Feature activation+0.000
Top resid features:
officials
Token officials
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
alt
Tokenalt
Feature activation-0.004
Top resid features:
of
Token of
Feature activation+0.006
Top resid features:
the
Token the
Feature activation-0.001
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.029
Top resid features:
The
TokenThe
Feature activation+0.310
Top resid features:
Guardian
Token Guardian
Feature activation+1.613
Top resid features:
Express
Token Express
Feature activation+1.352
Top resid features:
has
Token has
Feature activation+0.020
Top resid features:
come
Token come
Feature activation+0.000
Top resid features:
across
Token across
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
Speaking
Token Speaking
Feature activation+0.029
Top resid features:
to
Token to
Feature activation+0.023
Top resid features:
the
Token the
Feature activation+0.209
Top resid features:
Daily
Token Daily
Feature activation+0.793
Top resid features:
Telegraph
Token Telegraph
Feature activation+1.960
Top resid features:
,
Token,
Feature activation+0.111
Top resid features:
Amanda
Token Amanda
Feature activation+0.000
Top resid features:
Ross
Token Ross
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
atic
Tokenatic
Feature activation-0.035
Top resid features:
âĢ
TokenâĢ
Feature activation-0.037
Top resid features:
Ŀ
TokenĿ
Feature activation-0.038
Top resid features:
.
Token.
Feature activation+0.074
Top resid features:
The
Token The
Feature activation+0.321
Top resid features:
Guardian
Token Guardian
Feature activation+2.755
Top resid features:
contacted
Token contacted
Feature activation+0.246
Top resid features:
more
Token more
Feature activation+0.000
Top resid features:
than
Token than
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
dozen
Token dozen
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.001
Top resid features:
major
Token major
Feature activation-0.009
Top resid features:
operation
Token operation
Feature activation-0.040
Top resid features:
:
Token:
Feature activation-0.057
Top resid features:
the
Token the
Feature activation+0.293
Top resid features:
Guardian
Token Guardian
Feature activation+2.978
Top resid features:
reported
Token reported
Feature activation-0.049
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
least
Token least
Feature activation+0.000
Top resid features:
eight
Token eight
Feature activation+0.000
Top resid features:
alt
Tokenalt
Feature activation+0.005
Top resid features:
of
Token of
Feature activation+0.035
Top resid features:
the
Token the
Feature activation+0.100
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.126
Top resid features:
The
TokenThe
Feature activation+0.209
Top resid features:
Guardian
Token Guardian
Feature activation+2.386
Top resid features:
Express
Token Express
Feature activation+0.245
Top resid features:
has
Token has
Feature activation+0.000
Top resid features:
come
Token come
Feature activation+0.000
Top resid features:
across
Token across
Feature activation+0.000
Top resid features:
some
Token some
Feature activation+0.000
Top resid features:
University
Token University
Feature activation+0.025
Top resid features:
of
Token of
Feature activation-0.026
Top resid features:
Maryland
Token Maryland
Feature activation-0.034
Top resid features:
,
Token,
Feature activation+0.003
Top resid features:
The
Token The
Feature activation+0.258
Top resid features:
Guardian
Token Guardian
Feature activation+2.837
Top resid features:
reported
Token reported
Feature activation-0.049
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
That
Token That
Feature activation+0.000
Top resid features:
led
Token led
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
affected
Token affected
Feature activation+0.022
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.035
Top resid features:
The
TokenThe
Feature activation+0.460
Top resid features:
FT
Token FT
Feature activation+2.330
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
citing
Token citing
Feature activation+0.000
Top resid features:
anonymous
Token anonymous
Feature activation+0.000
Top resid features:
officials
Token officials
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Group
Token Group
Feature activation+0.005
Top resid features:
and
Token and
Feature activation-0.022
Top resid features:
shared
Token shared
Feature activation+0.053
Top resid features:
with
Token with
Feature activation+0.112
Top resid features:
the
Token the
Feature activation+0.254
Top resid features:
Guardian
Token Guardian
Feature activation+2.440
Top resid features:
,
Token,
Feature activation+0.059
Top resid features:
urges
Token urges
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
government
Token government
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
2
Token2
Feature activation-0.008
Top resid features:
oc
Tokenoc
Feature activation-0.027
Top resid features:
8
Token8
Feature activation-0.017
Top resid features:
âĢĶ
Token âĢĶ
Feature activation+0.072
Top resid features:
The
Token The
Feature activation+0.474
Top resid features:
Telegraph
Token Telegraph
Feature activation+2.437
Top resid features:
(@
Token (@
Feature activation+0.006
Top resid features:
Te
TokenTe
Feature activation+0.000
Top resid features:
legraph
Tokenlegraph
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
August
Token August
Feature activation+0.000
Top resid features:
contractor
Token contractor
Feature activation-0.029
Top resid features:
.
Token.
Feature activation+0.038
Top resid features:
Ċ
TokenĊ
Feature activation+0.022
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
The
TokenThe
Feature activation+0.298
Top resid features:
Guardian
Token Guardian
Feature activation+2.284
Top resid features:
reported
Token reported
Feature activation+0.300
Top resid features:
that
Token that
Feature activation+0.171
Top resid features:
British
Token British
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
US
Token US
Feature activation+0.000
Top resid features:
information
Token information
Feature activation+0.005
Top resid features:
regarding
Token regarding
Feature activation+0.005
Top resid features:
âĢ
Token âĢ
Feature activation+0.015
Top resid features:
ľ
Tokenľ
Feature activation-0.085
Top resid features:
The
TokenThe
Feature activation+0.372
Top resid features:
Guardian
Token Guardian
Feature activation+2.723
Top resid features:
âĢ
TokenâĢ
Feature activation-0.005
Top resid features:
Ŀ
TokenĿ
Feature activation+0.000
Top resid features:
âĢĵ
Token âĢĵ
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
in
Token in
Feature activation-0.005
Top resid features:
Russia
Token Russia
Feature activation-0.015
Top resid features:
,
Token,
Feature activation+0.010
Top resid features:
told
Token told
Feature activation+0.001
Top resid features:
the
Token the
Feature activation+0.416
Top resid features:
Guardian
Token Guardian
Feature activation+2.399
Top resid features:
he
Token he
Feature activation+0.120
Top resid features:
would
Token would
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
;
Token;
Feature activation+0.053
Top resid features:
Channel
Token Channel
Feature activation+0.093
Top resid features:
4
Token 4
Feature activation-0.022
Top resid features:
and
Token and
Feature activation+0.145
Top resid features:
The
Token The
Feature activation+0.295
Top resid features:
Guardian
Token Guardian
Feature activation+2.072
Top resid features:
.
Token.
Feature activation+0.242
Top resid features:
Sophie
Token Sophie
Feature activation+0.000
Top resid features:
Walker
Token Walker
Feature activation+0.000
Top resid features:
called
Token called
Feature activation+0.000
Top resid features:
me
Token me
Feature activation+0.000
Top resid features:
afterward
Token afterward
Feature activation-0.050
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
Ċ
TokenĊ
Feature activation+0.008
Top resid features:
The
TokenThe
Feature activation+0.245
Top resid features:
Guardian
Token Guardian
Feature activation+2.707
Top resid features:
watched
Token watched
Feature activation+0.081
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
Lock
Token Lock
Feature activation+0.000
Top resid features:
ett
Tokenett
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
tourism
Token tourism
Feature activation-0.006
Top resid features:
complex
Token complex
Feature activation-0.044
Top resid features:
,
Token,
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.308
Top resid features:
Sun
Token Sun
Feature activation+0.803
Top resid features:
Journal
Token Journal
Feature activation+1.812
Top resid features:
reported
Token reported
Feature activation-0.001
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.06

Head 2: 0.06

Head 3: 0.10

Head 4: 0.04

Head 5: 0.08

Head 6: 0.04

Head 7: 0.04

Head 8: 0.04

Head 9: 0.36

Head 10: 0.07

Head 11: 0.04

Positive logits

��1.67

Herald1.40

ournal1.38

Editorial1.38

Newsletter1.35

1.34

Pound1.31

regrets1.31

Expedition1.28

Breaking1.24

Journal1.24

archives1.23

1.22

editorial1.21

Ltd1.20

BBC1.20

Attribution1.19

Carbuncle1.19

Ur1.18

Archae1.18

Negative logits

capacity-1.29

uphill-1.28

gradient-1.26

lear-1.24

luster-1.21

rano-1.19

abiding-1.17

Takeru-1.16

icidal-1.16

biologically-1.16

advant-1.16

oret-1.13

payoff-1.12

alo-1.11

timer-1.11

gart-1.10

neighbor-1.10

ace-1.10

GGGGGGGG-1.09

aneous-1.09

INTERVAL 2.259 - 2.510
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.919
reported
Token reported
Feature activation+2.510
that
Token that
Feature activation+1.597
British
Token British
Feature activation+0.449
and
Token and
Feature activation+0.000
US
Token US
Feature activation+0.000
intelligence
Token intelligence
Feature activation+0.000

INTERVAL 2.008 - 2.259
CONTAINS 0.000%

their
Token their
Feature activation+0.000
approval
Token approval
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.544
called
Token called
Feature activation+2.031
the
Token the
Feature activation+1.443
deal
Token deal
Feature activation+0.780
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000

INTERVAL 1.757 - 2.008
CONTAINS 0.001%

major
Token major
Feature activation+0.000
operation
Token operation
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.217
reported
Token reported
Feature activation+1.762
that
Token that
Feature activation+0.919
at
Token at
Feature activation+0.438
least
Token least
Feature activation+0.000
eight
Token eight
Feature activation+0.000
police
Token police
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.286
contacted
Token contacted
Feature activation+1.809
more
Token more
Feature activation+0.727
than
Token than
Feature activation+0.503
a
Token a
Feature activation+0.050
dozen
Token dozen
Feature activation+0.000
people
Token people
Feature activation+0.000
Speaking
Token Speaking
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Daily
Token Daily
Feature activation+0.118
Telegraph
Token Telegraph
Feature activation+0.806
,
Token,
Feature activation+1.815
Amanda
Token Amanda
Feature activation+1.114
Ross
Token Ross
Feature activation+0.000
,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
runs
Token runs
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.943
Express
Token Express
Feature activation+1.730
has
Token has
Feature activation+1.926
come
Token come
Feature activation+1.295
across
Token across
Feature activation+0.572
some
Token some
Feature activation+0.000
very
Token very
Feature activation+0.000
valuable
Token valuable
Feature activation+0.000
in
Token in
Feature activation+0.000
Syria
Token Syria
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.448
reported
Token reported
Feature activation+1.930
.
Token.
Feature activation+0.598
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
During
TokenDuring
Feature activation+0.000
an
Token an
Feature activation+0.000

INTERVAL 1.506 - 1.757
CONTAINS 0.001%

Russia
Token Russia
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.142
he
Token he
Feature activation+1.556
would
Token would
Feature activation+0.627
be
Token be
Feature activation+0.484
âĢ
Token âĢ
Feature activation+0.423
ľ
Tokenľ
Feature activation+0.000
more
Tokenmore
Feature activation+0.062
regarding
Token regarding
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.562
Ŀ
TokenĿ
Feature activation+0.820
âĢĵ
Token âĢĵ
Feature activation+0.140
and
Token and
Feature activation+0.476
he
Token he
Feature activation+0.171
clearly
Token clearly
Feature activation+0.000
oc
Tokenoc
Feature activation+0.000
8
Token8
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
The
Token The
Feature activation+0.000
Telegraph
Token Telegraph
Feature activation+0.959
(@
Token (@
Feature activation+1.600
Te
TokenTe
Feature activation+0.302
legraph
Tokenlegraph
Feature activation+0.059
)
Token)
Feature activation+0.706
August
Token August
Feature activation+0.238
4
Token 4
Feature activation+0.000
Channel
Token Channel
Feature activation+0.000
4
Token 4
Feature activation+0.000
and
Token and
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.598
.
Token.
Feature activation+1.525
Sophie
Token Sophie
Feature activation+1.127
Walker
Token Walker
Feature activation+0.000
called
Token called
Feature activation+0.000
me
Token me
Feature activation+0.000
a
Token a
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.943
Express
Token Express
Feature activation+1.730
has
Token has
Feature activation+1.926
come
Token come
Feature activation+1.295
across
Token across
Feature activation+0.572
some
Token some
Feature activation+0.000
very
Token very
Feature activation+0.000

INTERVAL 1.255 - 1.506
CONTAINS 0.002%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.758
has
Token has
Feature activation+1.422
spoken
Token spoken
Feature activation+1.081
to
Token to
Feature activation+0.188
six
Token six
Feature activation+0.304
key
Token key
Feature activation+0.000
lawmakers
Token lawmakers
Feature activation+0.000
approval
Token approval
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.544
called
Token called
Feature activation+2.031
the
Token the
Feature activation+1.443
deal
Token deal
Feature activation+0.780
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
a
Tokena
Feature activation+0.000
victory
Token victory
Feature activation+0.000
downs
Token downs
Feature activation+0.000
ides
Tokenides
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.114
website
Token website
Feature activation+1.300
reported
Token reported
Feature activation+0.479
that
Token that
Feature activation+0.041
armed
Token armed
Feature activation+0.000
robbers
Token robbers
Feature activation+0.000
in
Token in
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Root
Token Root
Feature activation+0.030
reveals
Token reveals
Feature activation+1.262
that
Token that
Feature activation+0.524
in
Token in
Feature activation+0.218
2012
Token 2012
Feature activation+0.000
,
Token,
Feature activation+0.000
"
Token "
Feature activation+0.000
,"
Token,"
Feature activation+0.000
Zucker
Token Zucker
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.000
in
Token in
Feature activation+1.438
an
Token an
Feature activation+1.031
interview
Token interview
Feature activation+0.357
published
Token published
Feature activation+0.000
Sunday
Token Sunday
Feature activation+0.000
.
Token.
Feature activation+0.024

INTERVAL 1.004 - 1.255
CONTAINS 0.002%

anonymous
Token anonymous
Feature activation+0.000
,
Token,
Feature activation+0.000
told
Token told
Feature activation+0.000
the
Token the
Feature activation+0.000
Telegraph
Token Telegraph
Feature activation+0.188
:
Token:
Feature activation+1.169
'
Token '
Feature activation+0.761
I
TokenI
Feature activation+0.000
know
Token know
Feature activation+0.000
[
Token [
Feature activation+0.000
W
TokenW
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
to
Token to
Feature activation+0.000
The
Token The
Feature activation+0.000
Globe
Token Globe
Feature activation+0.364
that
Token that
Feature activation+1.188
the
Token the
Feature activation+1.086
government
Token government
Feature activation+0.335
is
Token is
Feature activation+0.000
planning
Token planning
Feature activation+0.000
to
Token to
Feature activation+0.000
release
Token release
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Intercept
Token Intercept
Feature activation+0.540
,
Token,
Feature activation+1.172
which
Token which
Feature activation+1.108
broke
Token broke
Feature activation+0.635
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Intercept
Token Intercept
Feature activation+0.540
,
Token,
Feature activation+1.172
which
Token which
Feature activation+1.108
broke
Token broke
Feature activation+0.635
the
Token the
Feature activation+0.000
story
Token story
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Post
Token Post
Feature activation+0.339
âĢ
TokenâĢ
Feature activation+1.054
Ļ
TokenĻ
Feature activation+1.164
s
Tokens
Feature activation+0.700
Aaron
Token Aaron
Feature activation+0.000
Blake
Token Blake
Feature activation+0.000
responds
Token responds
Feature activation+0.000

INTERVAL 0.753 - 1.004
CONTAINS 0.006%

alt
Tokenalt
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.943
Express
Token Express
Feature activation+1.730
has
Token has
Feature activation+1.926
come
Token come
Feature activation+1.295
across
Token across
Feature activation+0.572
some
Token some
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+1.562
Ŀ
TokenĿ
Feature activation+0.820
âĢĵ
Token âĢĵ
Feature activation+0.140
and
Token and
Feature activation+0.476
he
Token he
Feature activation+0.171
clearly
Token clearly
Feature activation+0.000
wants
Token wants
Feature activation+0.000
says
Token says
Feature activation+0.000
The
Token The
Feature activation+0.000
Verge
Token Verge
Feature activation+0.641
âĢ
TokenâĢ
Feature activation+0.984
Ļ
TokenĻ
Feature activation+0.889
s
Tokens
Feature activation+0.968
Russell
Token Russell
Feature activation+0.162
Br
Token Br
Feature activation+0.000
andom
Tokenandom
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
the
Token the
Feature activation+0.786
Daily
Token Daily
Feature activation+0.201
Mirror
Token Mirror
Feature activation+0.446
and
Token and
Feature activation+1.223
the
Token the
Feature activation+1.369
Sun
Token Sun
Feature activation+0.865
âĢĵ
Token âĢĵ
Feature activation+0.932
"
Token "
Feature activation+0.636
to
Tokento
Feature activation+0.176
do
Token do
Feature activation+0.098
what
Token what
Feature activation+0.000
shared
Token shared
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.496
,
Token,
Feature activation+1.717
urges
Token urges
Feature activation+0.807
the
Token the
Feature activation+0.000
government
Token government
Feature activation+0.000
to
Token to
Feature activation+0.000
introduce
Token introduce
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.502 - 0.753
CONTAINS 0.011%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
Wall
Token Wall
Feature activation+0.000
Street
Token Street
Feature activation+0.000
Journal
Token Journal
Feature activation+0.000
reported
Token reported
Feature activation+0.671
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Guardian
Token Guardian
Feature activation+0.459
watched
Token watched
Feature activation+1.497
as
Token as
Feature activation+0.218
Lock
Token Lock
Feature activation+0.542
ett
Tokenett
Feature activation+0.000
was
Token was
Feature activation+0.000
covered
Token covered
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
editor
Token editor
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Mirror
Token Mirror
Feature activation+0.358
Morgan
Token Morgan
Feature activation+0.574
,
Token,
Feature activation+0.346
48
Token 48
Feature activation+0.087
,
Token,
Feature activation+0.042
was
Token was
Feature activation+0.000
appointed
Token appointed
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
The
Token The
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Tribune
Token Tribune
Feature activation+0.598
.
Token.
Feature activation+0.705
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
his
Token his
Feature activation+0.000
short
Token short
Feature activation+0.000
,
Token,
Feature activation+0.000
according
Token according
Feature activation+0.000
to
Token to
Feature activation+0.000
The
Token The
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Tribune
Token Tribune
Feature activation+0.598
.
Token.
Feature activation+0.705
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
his
Token his
Feature activation+0.000

INTERVAL 0.251 - 0.502
CONTAINS 0.025%

,
Token,
Feature activation+0.000
who
Token who
Feature activation+0.000
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
Post
Token Post
Feature activation+0.000
and
Token and
Feature activation+0.441
Courier
Token Courier
Feature activation+1.306
in
Token in
Feature activation+0.805
Charleston
Token Charleston
Feature activation+0.476
,
Token,
Feature activation+0.000
S
Token S
Feature activation+0.000
an
Token an
Feature activation+0.000
interview
Token interview
Feature activation+0.000
with
Token with
Feature activation+0.000
The
Token The
Feature activation+0.000
News
Token News
Feature activation+0.139
-
Token-
Feature activation+0.362
G
TokenG
Feature activation+0.668
az
Tokenaz
Feature activation+0.357
ette
Tokenette
Feature activation+0.000
in
Token in
Feature activation+0.000
Champ
Token Champ
Feature activation+0.000
meantime
Token meantime
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
news
Token news
Feature activation+0.011
is
Token is
Feature activation+0.141
all
Token all
Feature activation+0.273
using
Token using
Feature activation+0.000
his
Token his
Feature activation+0.000
name
Token name
Feature activation+0.000
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
a
Token a
Feature activation+0.000
reporter
Token reporter
Feature activation+0.000
for
Token for
Feature activation+0.000
HuffPost
Token HuffPost
Feature activation+0.000
who
Token who
Feature activation+0.421
has
Token has
Feature activation+0.362
followed
Token followed
Feature activation+0.000
this
Token this
Feature activation+0.000
more
Token more
Feature activation+0.000
closely
Token closely
Feature activation+0.000
than
Token than
Feature activation+0.000
ri
Tokenri
Feature activation+0.000
yet
Tokenyet
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
News
Token News
Feature activation+0.000
during
Token during
Feature activation+0.184
a
Token a
Feature activation+0.470
meeting
Token meeting
Feature activation+0.077
on
Token on
Feature activation+0.000
Sept
Token Sept
Feature activation+0.000
.
Token.
Feature activation+0.000
17
Token 17
Feature activation+0.000

INTERVAL 0.000 - 0.251
CONTAINS 99.951%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
16
Token 16
Feature activation+0.000
,
Token,
Feature activation+0.000
New
Token New
Feature activation+0.000
Haven
Token Haven
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Prime
TokenPrime
Feature activation+0.000
16
Token 16
Feature activation+0.000
it
Token it
Feature activation+0.000
can
Token can
Feature activation+0.000
be
Token be
Feature activation+0.000
really
Token really
Feature activation+0.000
ostr
Token ostr
Feature activation+0.000
ac
Tokenac
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
,"
Token,"
Feature activation+0.000
said
Token said
Feature activation+0.000
Peter
Token Peter
Feature activation+0.000
He
Token He
Feature activation+0.000
we
Token we
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
d
Tokend
Feature activation+0.000
be
Token be
Feature activation+0.000
approaching
Token approaching
Feature activation+0.000
Memorial
Token Memorial
Feature activation+0.000
Day
Token Day
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
Baltimore
Token Baltimore
Feature activation+0.000
(
Token (
Feature activation+0.000
288
Token288
Feature activation+0.000
carries
Token carries
Feature activation+0.000
and
Token and
Feature activation+0.000
77
Token 77
Feature activation+0.000
catches
Token catches
Feature activation+0.000
),
Token),
Feature activation+0.000
he
Token he
Feature activation+0.000
averaged
Token averaged
Feature activation+0.000
24
Token 24
Feature activation+0.000
.
Token.
Feature activation+0.000
PC
Token PC
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
ll
Tokenll
Feature activation+0.000
be
Token be
Feature activation+0.000
able
Token able
Feature activation+0.000
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 6 in H2.9: (feature 9709)

TOP ACTIVATIONS
MAX = 2.151

is
Token is
Feature activation+0.000
evident
Token evident
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.706
is
Token is
Feature activation+2.151
going
Token going
Feature activation+1.149
through
Token through
Feature activation+1.420
increased
Token increased
Feature activation+0.458
crisis
Token crisis
Feature activation+0.000
of
Token of
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.556
dictate
Token dictate
Feature activation+2.081
the
Token the
Feature activation+0.654
rules
Token rules
Feature activation+0.846
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
it
Token it
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
West
Token West
Feature activation+0.422
âĢ
TokenâĢ
Feature activation+1.579
Ļ
TokenĻ
Feature activation+0.541
s
Tokens
Feature activation+0.000
experience
Token experience
Feature activation+0.138
shows
Token shows
Feature activation+0.000
(
Token (
Feature activation+0.000
a
Token a
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
's
Token's
Feature activation+1.545
resolution
Token resolution
Feature activation+1.307
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UN
Token UN
Feature activation+0.000
General
Token General
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
and
Token and
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.137
is
Token is
Feature activation+1.420
bombing
Token bombing
Feature activation+1.280
the
Token the
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.068
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.506
Fr
Token Fr
Feature activation+1.420
is
Tokenis
Feature activation+0.143
ian
Tokenian
Feature activation+0.000
language
Token language
Feature activation+0.000
spoken
Token spoken
Feature activation+0.000
in
Token in
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.706
is
Token is
Feature activation+2.151
going
Token going
Feature activation+1.149
through
Token through
Feature activation+1.420
increased
Token increased
Feature activation+0.458
crisis
Token crisis
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
's
Token's
Feature activation+1.545
resolution
Token resolution
Feature activation+1.307
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UN
Token UN
Feature activation+0.000
General
Token General
Feature activation+0.000
Assembly
Token Assembly
Feature activation+0.000
and
Token and
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.137
is
Token is
Feature activation+1.420
bombing
Token bombing
Feature activation+1.280
the
Token the
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.068
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
TV
Token TV
Feature activation+0.000
birth
Token birth
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
's
Token's
Feature activation+0.824
founding
Token founding
Feature activation+1.177
leader
Token leader
Feature activation+0.000
,
Token,
Feature activation+0.000
Kim
Token Kim
Feature activation+0.000
Il
Token Il
Feature activation+0.000
Sung
Token Sung
Feature activation+0.000
classic
Token classic
Feature activation+0.000
Journey
Token Journey
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.085
tales
Token tales
Feature activation+1.152
--
Token --
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
Chow
Token Chow
Feature activation+0.000
's
Token's
Feature activation+0.000
Journey
Token Journey
Feature activation+0.000
evident
Token evident
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.706
is
Token is
Feature activation+2.151
going
Token going
Feature activation+1.149
through
Token through
Feature activation+1.420
increased
Token increased
Feature activation+0.458
crisis
Token crisis
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
singles
Token singles
Feature activation+0.000
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
West
Token West
Feature activation+0.000
's
Token's
Feature activation+1.148
GOOD
Token GOOD
Feature activation+0.638
Fridays
Token Fridays
Feature activation+0.000
giveaways
Token giveaways
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
two
Token two
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
after
Token after
Feature activation+0.000
West
Token West
Feature activation+0.000
was
Token was
Feature activation+0.530
released
Token released
Feature activation+1.124
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
UCLA
Token UCLA
Feature activation+0.000
Medical
Token Medical
Feature activation+0.000
Center
Token Center
Feature activation+0.000
to
Token to
Feature activation+0.000
engage
Token engage
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.313
but
Token but
Feature activation+1.042
to
Token to
Feature activation+0.963
no
Token no
Feature activation+0.596
avail
Token avail
Feature activation+0.000
.
Token.
Feature activation+0.000
Stein
Token Stein
Feature activation+0.000
hospitalized
Token hospitalized
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.000
garnered
Token garnered
Feature activation+1.040
criticism
Token criticism
Feature activation+0.076
for
Token for
Feature activation+0.000
ending
Token ending
Feature activation+0.000
a
Token a
Feature activation+0.000
California
Token California
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
height
Token height
Feature activation+0.000
of
Token of
Feature activation+0.000
East
Token East
Feature activation+0.000
-
Token-
Feature activation+0.527
West
TokenWest
Feature activation+1.038
tensions
Token tensions
Feature activation+0.839
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.751
Germany
Token Germany
Feature activation+0.000
feared
Token feared
Feature activation+0.344
you
Token you
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
Old
Token Old
Feature activation+0.000
West
Token West
Feature activation+0.000
type
Token type
Feature activation+1.017
showdown
Token showdown
Feature activation+0.000
for
Token for
Feature activation+0.000
Cash
Token Cash
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Round
Token Round
Feature activation+0.000
13
Token 13
Feature activation+0.000
against
Token against
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.226
s
Tokens
Feature activation+0.990
Tigers
Token Tigers
Feature activation+0.545
.
Token.
Feature activation+0.000
Trent
Token Trent
Feature activation+0.000
Robinson
Token Robinson
Feature activation+0.000
confirmed
Token confirmed
Feature activation+0.000
engage
Token engage
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.313
but
Token but
Feature activation+1.042
to
Token to
Feature activation+0.963
no
Token no
Feature activation+0.596
avail
Token avail
Feature activation+0.000
.
Token.
Feature activation+0.000
Stein
Token Stein
Feature activation+0.000
meier
Tokenmeier
Feature activation+0.000

Top DFA by src position
MAX = 3.038

it
Token it
Feature activation+0.030
Top resid features:
is
Token is
Feature activation-0.025
Top resid features:
evident
Token evident
Feature activation-0.021
Top resid features:
that
Token that
Feature activation+0.074
Top resid features:
the
Token the
Feature activation+0.266
Top resid features:
West
Token West
Feature activation+3.038
Top resid features:
is
Token is
Feature activation+0.060
Top resid features:
going
Token going
Feature activation+0.000
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
increased
Token increased
Feature activation+0.000
Top resid features:
crisis
Token crisis
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.089
Top resid features:
won
Token won
Feature activation+0.007
Top resid features:
't
Token't
Feature activation+0.122
Top resid features:
let
Token let
Feature activation+0.095
Top resid features:
the
Token the
Feature activation+0.259
Top resid features:
West
Token West
Feature activation+2.783
Top resid features:
dictate
Token dictate
Feature activation-0.055
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
rules
Token rules
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
And
Token And
Feature activation+0.000
Top resid features:
dozen
Token dozen
Feature activation+0.012
Top resid features:
.
Token.
Feature activation+0.094
Top resid features:
Ċ
TokenĊ
Feature activation+0.089
Top resid features:
Ċ
TokenĊ
Feature activation+0.091
Top resid features:
As
TokenAs
Feature activation+0.268
Top resid features:
West
Token West
Feature activation+2.362
Top resid features:
âĢ
TokenâĢ
Feature activation-0.025
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
s
Tokens
Feature activation+0.000
Top resid features:
experience
Token experience
Feature activation+0.000
Top resid features:
shows
Token shows
Feature activation+0.000
Top resid features:
sponsored
Token sponsored
Feature activation+0.007
Top resid features:
a
Token a
Feature activation+0.118
Top resid features:
version
Token version
Feature activation-0.069
Top resid features:
of
Token of
Feature activation+0.197
Top resid features:
the
Token the
Feature activation+0.223
Top resid features:
West
Token West
Feature activation+2.338
Top resid features:
's
Token's
Feature activation+0.052
Top resid features:
resolution
Token resolution
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
UN
Token UN
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.022
Top resid features:
fighting
Token fighting
Feature activation-0.061
Top resid features:
and
Token and
Feature activation+0.120
Top resid features:
where
Token where
Feature activation+0.210
Top resid features:
the
Token the
Feature activation+0.170
Top resid features:
West
Token West
Feature activation+2.231
Top resid features:
is
Token is
Feature activation+0.014
Top resid features:
bombing
Token bombing
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
terrorists
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:
Germany
Token Germany
Feature activation-0.012
Top resid features:
,
Token,
Feature activation+0.145
Top resid features:
and
Token and
Feature activation+0.167
Top resid features:
the
Token the
Feature activation+0.246
Top resid features:
West
Token West
Feature activation+2.163
Top resid features:
Fr
Token Fr
Feature activation+0.044
Top resid features:
is
Tokenis
Feature activation+0.000
Top resid features:
ian
Tokenian
Feature activation+0.000
Top resid features:
language
Token language
Feature activation+0.000
Top resid features:
spoken
Token spoken
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.021
Top resid features:
is
Token is
Feature activation-0.021
Top resid features:
evident
Token evident
Feature activation-0.019
Top resid features:
that
Token that
Feature activation+0.055
Top resid features:
the
Token the
Feature activation+0.170
Top resid features:
West
Token West
Feature activation+2.121
Top resid features:
is
Token is
Feature activation+0.177
Top resid features:
going
Token going
Feature activation+0.050
Top resid features:
through
Token through
Feature activation+0.136
Top resid features:
increased
Token increased
Feature activation+0.000
Top resid features:
crisis
Token crisis
Feature activation+0.000
Top resid features:
sponsored
Token sponsored
Feature activation-0.028
Top resid features:
a
Token a
Feature activation+0.062
Top resid features:
version
Token version
Feature activation-0.037
Top resid features:
of
Token of
Feature activation+0.129
Top resid features:
the
Token the
Feature activation+0.211
Top resid features:
West
Token West
Feature activation+2.063
Top resid features:
's
Token's
Feature activation+0.133
Top resid features:
resolution
Token resolution
Feature activation-0.033
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
UN
Token UN
Feature activation+0.000
Top resid features:
is
Token is
Feature activation-0.001
Top resid features:
fighting
Token fighting
Feature activation-0.034
Top resid features:
and
Token and
Feature activation+0.082
Top resid features:
where
Token where
Feature activation+0.097
Top resid features:
the
Token the
Feature activation+0.211
Top resid features:
West
Token West
Feature activation+2.086
Top resid features:
is
Token is
Feature activation+0.198
Top resid features:
bombing
Token bombing
Feature activation-0.110
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
terrorists
Token terrorists
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.091
Top resid features:
the
Token the
Feature activation+0.042
Top resid features:
birth
Token birth
Feature activation-0.039
Top resid features:
of
Token of
Feature activation+0.159
Top resid features:
the
Token the
Feature activation+0.156
Top resid features:
North
Token North
Feature activation+1.865
Top resid features:
's
Token's
Feature activation+0.290
Top resid features:
founding
Token founding
Feature activation+0.074
Top resid features:
leader
Token leader
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Kim
Token Kim
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.002
Top resid features:
classic
Token classic
Feature activation+0.001
Top resid features:
Journey
Token Journey
Feature activation-0.029
Top resid features:
to
Token to
Feature activation+0.301
Top resid features:
the
Token the
Feature activation+0.279
Top resid features:
West
Token West
Feature activation+1.933
Top resid features:
tales
Token tales
Feature activation-0.103
Top resid features:
--
Token --
Feature activation+0.000
Top resid features:
Stephen
Token Stephen
Feature activation+0.000
Top resid features:
Chow
Token Chow
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.024
Top resid features:
is
Token is
Feature activation-0.032
Top resid features:
evident
Token evident
Feature activation-0.017
Top resid features:
that
Token that
Feature activation+0.094
Top resid features:
the
Token the
Feature activation+0.269
Top resid features:
West
Token West
Feature activation+1.983
Top resid features:
is
Token is
Feature activation+0.077
Top resid features:
going
Token going
Feature activation-0.040
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
increased
Token increased
Feature activation+0.000
Top resid features:
crisis
Token crisis
Feature activation+0.000
Top resid features:
promotional
Token promotional
Feature activation+0.021
Top resid features:
singles
Token singles
Feature activation-0.008
Top resid features:
as
Token as
Feature activation+0.094
Top resid features:
part
Token part
Feature activation-0.037
Top resid features:
of
Token of
Feature activation+0.165
Top resid features:
West
Token West
Feature activation+2.152
Top resid features:
's
Token's
Feature activation+0.098
Top resid features:
GOOD
Token GOOD
Feature activation+0.000
Top resid features:
Fridays
Token Fridays
Feature activation+0.000
Top resid features:
giveaways
Token giveaways
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
place
Token place
Feature activation-0.034
Top resid features:
nearly
Token nearly
Feature activation+0.024
Top resid features:
two
Token two
Feature activation+0.051
Top resid features:
weeks
Token weeks
Feature activation-0.060
Top resid features:
after
Token after
Feature activation+0.459
Top resid features:
West
Token West
Feature activation+1.742
Top resid features:
was
Token was
Feature activation+0.117
Top resid features:
released
Token released
Feature activation-0.018
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
UCLA
Token UCLA
Feature activation+0.000
Top resid features:
Putin
Token Putin
Feature activation+0.023
Top resid features:
to
Token to
Feature activation+0.054
Top resid features:
engage
Token engage
Feature activation+0.033
Top resid features:
with
Token with
Feature activation+0.082
Top resid features:
the
Token the
Feature activation+0.254
Top resid features:
West
Token West
Feature activation+1.765
Top resid features:
but
Token but
Feature activation+0.091
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
avail
Token avail
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.031
Top resid features:
hospitalized
Token hospitalized
Feature activation+0.007
Top resid features:
last
Token last
Feature activation+0.047
Top resid features:
month
Token month
Feature activation-0.112
Top resid features:
,
Token,
Feature activation+0.293
Top resid features:
West
Token West
Feature activation+2.109
Top resid features:
garnered
Token garnered
Feature activation+0.041
Top resid features:
criticism
Token criticism
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
ending
Token ending
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.206
Top resid features:
height
Token height
Feature activation-0.048
Top resid features:
of
Token of
Feature activation+0.221
Top resid features:
East
Token East
Feature activation+1.236
Top resid features:
-
Token-
Feature activation+0.460
Top resid features:
West
TokenWest
Feature activation+0.554
Top resid features:
tensions
Token tensions
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
West
Token West
Feature activation+0.000
Top resid features:
challenge
Token challenge
Feature activation+0.028
Top resid features:
you
Token you
Feature activation+0.035
Top resid features:
in
Token in
Feature activation+0.130
Top resid features:
a
Token a
Feature activation+0.212
Top resid features:
Old
Token Old
Feature activation+0.440
Top resid features:
West
Token West
Feature activation+1.619
Top resid features:
type
Token type
Feature activation-0.149
Top resid features:
showdown
Token showdown
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Cash
Token Cash
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.059
Top resid features:
Round
Token Round
Feature activation-0.017
Top resid features:
13
Token 13
Feature activation+0.117
Top resid features:
against
Token against
Feature activation+0.150
Top resid features:
the
Token the
Feature activation+0.222
Top resid features:
West
Token West
Feature activation+1.701
Top resid features:
s
Tokens
Feature activation+0.048
Top resid features:
Tigers
Token Tigers
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Trent
Token Trent
Feature activation+0.000
Top resid features:
Robinson
Token Robinson
Feature activation+0.000
Top resid features:
Putin
Token Putin
Feature activation+0.028
Top resid features:
to
Token to
Feature activation+0.021
Top resid features:
engage
Token engage
Feature activation+0.001
Top resid features:
with
Token with
Feature activation+0.044
Top resid features:
the
Token the
Feature activation+0.149
Top resid features:
West
Token West
Feature activation+1.606
Top resid features:
but
Token but
Feature activation+0.324
Top resid features:
to
Token to
Feature activation+0.162
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
avail
Token avail
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.04

Head 2: 0.09

Head 3: 0.09

Head 4: 0.04

Head 5: 0.08

Head 6: 0.03

Head 7: 0.03

Head 8: 0.05

Head 9: 0.36

Head 10: 0.06

Head 11: 0.04

Positive logits

Ruins1.44

ibur1.38

1.37

1.36

Fell1.35

ּ1.34

izens1.34

arna1.33

1.32

aucuses1.29

Belg1.28

Summit1.27

istan1.23

Falls1.22

1.21

enburg1.20

istas1.19

chens1.19

ways1.19

atan1.18

Negative logits

oyal-1.46

execut-1.29

aughtered-1.28

��-1.27

extras-1.23

clipboard-1.23

TTL-1.22

��-1.20

rogram-1.18

named-1.17

expiration-1.15

receipt-1.15

Downloadha-1.14

ocious-1.12

grap-1.12

memos-1.11

assistant-1.10

depleted-1.10

memory-1.10

ongyang-1.09

INTERVAL 1.936 - 2.151
CONTAINS 0.000%

is
Token is
Feature activation+0.000
evident
Token evident
Feature activation+0.000
that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.706
is
Token is
Feature activation+2.151
going
Token going
Feature activation+1.149
through
Token through
Feature activation+1.420
increased
Token increased
Feature activation+0.458
crisis
Token crisis
Feature activation+0.000
of
Token of
Feature activation+0.000
won
Token won
Feature activation+0.000
't
Token't
Feature activation+0.000
let
Token let
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.556
dictate
Token dictate
Feature activation+2.081
the
Token the
Feature activation+0.654
rules
Token rules
Feature activation+0.846
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
it
Token it
Feature activation+0.000

INTERVAL 1.721 - 1.936
CONTAINS 0.000%

INTERVAL 1.506 - 1.721
CONTAINS 0.000%

a
Token a
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
's
Token's
Feature activation+1.545
resolution
Token resolution
Feature activation+1.307
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UN
Token UN
Feature activation+0.000
General
Token General
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
West
Token West
Feature activation+0.422
âĢ
TokenâĢ
Feature activation+1.579
Ļ
TokenĻ
Feature activation+0.541
s
Tokens
Feature activation+0.000
experience
Token experience
Feature activation+0.138
shows
Token shows
Feature activation+0.000
(
Token (
Feature activation+0.000

INTERVAL 1.291 - 1.506
CONTAINS 0.000%

that
Token that
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.706
is
Token is
Feature activation+2.151
going
Token going
Feature activation+1.149
through
Token through
Feature activation+1.420
increased
Token increased
Feature activation+0.458
crisis
Token crisis
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
version
Token version
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
's
Token's
Feature activation+1.545
resolution
Token resolution
Feature activation+1.307
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
UN
Token UN
Feature activation+0.000
General
Token General
Feature activation+0.000
Assembly
Token Assembly
Feature activation+0.000
Germany
Token Germany
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.506
Fr
Token Fr
Feature activation+1.420
is
Tokenis
Feature activation+0.143
ian
Tokenian
Feature activation+0.000
language
Token language
Feature activation+0.000
spoken
Token spoken
Feature activation+0.000
in
Token in
Feature activation+0.000
fighting
Token fighting
Feature activation+0.000
and
Token and
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.137
is
Token is
Feature activation+1.420
bombing
Token bombing
Feature activation+1.280
the
Token the
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.068
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000

INTERVAL 1.076 - 1.291
CONTAINS 0.001%

singles
Token singles
Feature activation+0.000
as
Token as
Feature activation+0.000
part
Token part
Feature activation+0.000
of
Token of
Feature activation+0.000
West
Token West
Feature activation+0.000
's
Token's
Feature activation+1.148
GOOD
Token GOOD
Feature activation+0.638
Fridays
Token Fridays
Feature activation+0.000
giveaways
Token giveaways
Feature activation+0.000
,
Token,
Feature activation+0.000
including
Token including
Feature activation+0.000
two
Token two
Feature activation+0.000
weeks
Token weeks
Feature activation+0.000
after
Token after
Feature activation+0.000
West
Token West
Feature activation+0.000
was
Token was
Feature activation+0.530
released
Token released
Feature activation+1.124
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
UCLA
Token UCLA
Feature activation+0.000
Medical
Token Medical
Feature activation+0.000
Center
Token Center
Feature activation+0.000
and
Token and
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.137
is
Token is
Feature activation+1.420
bombing
Token bombing
Feature activation+1.280
the
Token the
Feature activation+0.000
terrorists
Token terrorists
Feature activation+0.068
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
TV
Token TV
Feature activation+0.000
birth
Token birth
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
's
Token's
Feature activation+0.824
founding
Token founding
Feature activation+1.177
leader
Token leader
Feature activation+0.000
,
Token,
Feature activation+0.000
Kim
Token Kim
Feature activation+0.000
Il
Token Il
Feature activation+0.000
Sung
Token Sung
Feature activation+0.000
classic
Token classic
Feature activation+0.000
Journey
Token Journey
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.085
tales
Token tales
Feature activation+1.152
--
Token --
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
Chow
Token Chow
Feature activation+0.000
's
Token's
Feature activation+0.000
Journey
Token Journey
Feature activation+0.000

INTERVAL 0.861 - 1.076
CONTAINS 0.002%

hospitalized
Token hospitalized
Feature activation+0.000
last
Token last
Feature activation+0.000
month
Token month
Feature activation+0.000
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.000
garnered
Token garnered
Feature activation+1.040
criticism
Token criticism
Feature activation+0.076
for
Token for
Feature activation+0.000
ending
Token ending
Feature activation+0.000
a
Token a
Feature activation+0.000
California
Token California
Feature activation+0.000
Republicans
Token Republicans
Feature activation+0.000
took
Token took
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
South
Token South
Feature activation+0.000
following
Token following
Feature activation+0.952
the
Token the
Feature activation+0.370
civil
Token civil
Feature activation+0.139
rights
Token rights
Feature activation+0.000
movement
Token movement
Feature activation+0.000
.
Token.
Feature activation+0.000
Elijah
Token Elijah
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
at
Token at
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
Tigers
Token Tigers
Feature activation+0.902
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
suggest
Token suggest
Feature activation+0.000
it
Token it
Feature activation+0.000
may
Token may
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
height
Token height
Feature activation+0.000
of
Token of
Feature activation+0.000
East
Token East
Feature activation+0.000
-
Token-
Feature activation+0.527
West
TokenWest
Feature activation+1.038
tensions
Token tensions
Feature activation+0.839
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.751
Germany
Token Germany
Feature activation+0.000
feared
Token feared
Feature activation+0.344
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
web
Token web
Feature activation+0.000
.
Token.
Feature activation+0.000
West
Token West
Feature activation+0.293
and
Token and
Feature activation+0.912
Stone
Token Stone
Feature activation+0.571
quote
Token quote
Feature activation+0.220
New
Token New
Feature activation+0.000
York
Token York
Feature activation+0.000
Times
Token Times
Feature activation+0.000

INTERVAL 0.645 - 0.861
CONTAINS 0.004%

state
Token state
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
East
Token East
Feature activation+0.000
West
Token West
Feature activation+0.610
Link
Token Link
Feature activation+0.670
project
Token project
Feature activation+0.528
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
was
Token was
Feature activation+0.000
scrapped
Token scrapped
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢĵ
TokenâĢĵ
Feature activation+0.000
The
Token The
Feature activation+0.000
West
Token West
Feature activation+0.713
Euras
Token Euras
Feature activation+0.682
ian
Tokenian
Feature activation+0.005
ancestry
Token ancestry
Feature activation+0.000
of
Token of
Feature activation+0.000
South
Token South
Feature activation+0.000
Asians
Token Asians
Feature activation+0.000
sometimes
Token sometimes
Feature activation+0.000
called
Token called
Feature activation+0.000
Pentagon
Token Pentagon
Feature activation+0.000
East
Token East
Feature activation+0.000
,
Token,
Feature activation+0.356
a
Token a
Feature activation+0.727
force
Token force
Feature activation+0.088
of
Token of
Feature activation+0.000
7
Token 7
Feature activation+0.000
,
Token,
Feature activation+0.000
200
Token200
Feature activation+0.000
"
Token "
Feature activation+0.000
the
Tokenthe
Feature activation+0.000
East
Token East
Feature activation+0.000
Side
Token Side
Feature activation+0.436
âĢĶ
TokenâĢĶ
Feature activation+0.532
the
Tokenthe
Feature activation+0.752
elephant
Token elephant
Feature activation+0.167
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
room
Token room
Feature activation+0.000
here
Token here
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
West
Token West
Feature activation+0.166
Point
Token Point
Feature activation+0.076
remarks
Token remarks
Feature activation+0.695
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
meet
Token meet
Feature activation+0.000

INTERVAL 0.430 - 0.645
CONTAINS 0.007%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
area
Token area
Feature activation+0.000
.
Token.
Feature activation+0.000
North
Token North
Feature activation+0.000
to
Token to
Feature activation+0.581
the
Token the
Feature activation+0.829
Yuk
Token Yuk
Feature activation+0.000
on
Tokenon
Feature activation+0.000
and
Token and
Feature activation+0.000
east
Token east
Feature activation+0.000
the
Token the
Feature activation+0.000
industry
Token industry
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
Western
Token Western
Feature activation+0.000
import
Token import
Feature activation+0.602
.
Token.
Feature activation+0.000
And
Token And
Feature activation+0.000
that
Token that
Feature activation+0.000
,
Token,
Feature activation+0.000
Dick
Token Dick
Feature activation+0.000
but
Token but
Feature activation+0.542
if
Token if
Feature activation+0.084
West
Token West
Feature activation+0.601
Austin
Token Austin
Feature activation+0.078
and
Token and
Feature activation+0.000
its
Token its
Feature activation+0.617
accompanying
Token accompanying
Feature activation+0.000
suburbs
Token suburbs
Feature activation+0.000
have
Token have
Feature activation+0.000
long
Token long
Feature activation+0.000
been
Token been
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.706
is
Token is
Feature activation+2.151
going
Token going
Feature activation+1.149
through
Token through
Feature activation+1.420
increased
Token increased
Feature activation+0.458
crisis
Token crisis
Feature activation+0.000
of
Token of
Feature activation+0.000
its
Token its
Feature activation+0.000
cultural
Token cultural
Feature activation+0.000
divides
Token divides
Feature activation+0.000
better
Token better
Feature activation+0.000
ties
Token ties
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.277
.
Token.
Feature activation+0.569
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Would
TokenWould
Feature activation+0.000

INTERVAL 0.215 - 0.430
CONTAINS 0.012%

entering
Token entering
Feature activation+0.000
the
Token the
Feature activation+0.000
West
Token West
Feature activation+0.000
Bank
Token Bank
Feature activation+0.000
,
Token,
Feature activation+0.266
where
Token where
Feature activation+0.365
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
to
Token to
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
a
Token a
Feature activation+0.000
.
Token.
Feature activation+0.000
29
Token 29
Feature activation+0.000
,
Token,
Feature activation+0.000
West
Token West
Feature activation+0.034
past
Token past
Feature activation+0.804
ed
Tokened
Feature activation+0.386
the
Token the
Feature activation+0.070
text
Token text
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
story
Token story
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Upper
Token Upper
Feature activation+0.000
East
Token East
Feature activation+0.000
Side
Token Side
Feature activation+0.125
are
Token are
Feature activation+0.301
about
Token about
Feature activation+0.102
$
Token $
Feature activation+0.000
150
Token150
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
or
Token or
Feature activation+0.000
redef
Token redef
Feature activation+0.000
ine
Tokenine
Feature activation+0.000
a
Token a
Feature activation+0.000
Europe
Token Europe
Feature activation+0.000
that
Token that
Feature activation+0.220
protects
Token protects
Feature activation+0.000
".
Token".
Feature activation+0.000
This
Token This
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
chief
Token chief
Feature activation+0.000
officer
Token officer
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
North
Token North
Feature activation+0.000
West
Token West
Feature activation+0.428
London
Token London
Feature activation+0.000
collaboration
Token collaboration
Feature activation+0.402
of
Token of
Feature activation+0.000
clinical
Token clinical
Feature activation+0.000
commission
Token commission
Feature activation+0.000

INTERVAL 0.000 - 0.215
CONTAINS 99.974%

appear
Token appear
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
final
Token final
Feature activation+0.000
two
Token two
Feature activation+0.000
Avengers
Token Avengers
Feature activation+0.000
films
Token films
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
soon
Token soon
Feature activation+0.000
to
Token to
Feature activation+0.000
be
Token be
Feature activation+0.000
unt
Token unt
Feature activation+0.000
rust
Tokenrust
Feature activation+0.000
worthy
Tokenworthy
Feature activation+0.000
,
Token,
Feature activation+0.000
or
Token or
Feature activation+0.000
illegal
Token illegal
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
jurisdiction
Token jurisdiction
Feature activation+0.000
.
Token.
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
you
Token you
Feature activation+0.000
will
Token will
Feature activation+0.000
get
Token get
Feature activation+0.000
to
Token to
Feature activation+0.000
see
Token see
Feature activation+0.000
a
Token a
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
2009
Token 2009
Feature activation+0.000
Hal
Token Hal
Feature activation+0.000
,
Token,
Feature activation+0.000
then
Token then
Feature activation+0.000
in
Token in
Feature activation+0.000
mid
Token mid
Feature activation+0.000
f
Token f
Feature activation+0.000
.
Token.
Feature activation+0.000
Inc
Token Inc
Feature activation+0.000
itement
Tokenitement
Feature activation+0.000
to
Token to
Feature activation+0.000
hatred
Token hatred
Feature activation+0.000
based
Token based
Feature activation+0.000
on
Token on
Feature activation+0.000
sexual
Token sexual
Feature activation+0.000
orientation
Token orientation
Feature activation+0.000
is
Token is
Feature activation+0.000
only
Token only
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 7 in H2.9: (feature 9963)

TOP ACTIVATIONS
MAX = 2.557

is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
research
Token research
Feature activation+0.572
is
Token is
Feature activation+2.000
needed
Token needed
Feature activation+2.557
to
Token to
Feature activation+1.905
find
Token find
Feature activation+1.075
out
Token out
Feature activation+0.811
how
Token how
Feature activation+0.353
drastically
Token drastically
Feature activation+0.000
be
Token be
Feature activation+0.000
pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+0.193
showing
Token showing
Feature activation+2.467
that
Token that
Feature activation+0.945
people
Token people
Feature activation+0.269
eat
Token eat
Feature activation+0.000
better
Token better
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.146
is
Token is
Feature activation+1.683
needed
Token needed
Feature activation+2.307
before
Token before
Feature activation+0.862
the
Token the
Feature activation+0.003
next
Token next
Feature activation+0.000
diet
Token diet
Feature activation+0.000
cra
Token cra
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
research
Token research
Feature activation+0.000
could
Token could
Feature activation+2.210
also
Token also
Feature activation+1.719
have
Token have
Feature activation+1.516
implications
Token implications
Feature activation+0.870
for
Token for
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
s
Tokens
Feature activation+0.000
said
Token said
Feature activation+0.000
previous
Token previous
Feature activation+0.000
research
Token research
Feature activation+0.000
had
Token had
Feature activation+1.039
shown
Token shown
Feature activation+2.093
the
Token the
Feature activation+0.497
same
Token same
Feature activation+0.000
"
Token "
Feature activation+0.000
dec
Tokendec
Feature activation+0.000
arbon
Tokenarbon
Feature activation+0.000
it
Token it
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
research
Token research
Feature activation+0.572
is
Token is
Feature activation+2.000
needed
Token needed
Feature activation+2.557
to
Token to
Feature activation+1.905
find
Token find
Feature activation+1.075
out
Token out
Feature activation+0.811
how
Token how
Feature activation+0.353
first
Token first
Feature activation+0.000
seems
Token seems
Feature activation+0.000
.
Token.
Feature activation+0.000
Our
Token Our
Feature activation+0.000
research
Token research
Feature activation+0.184
shows
Token shows
Feature activation+1.984
that
Token that
Feature activation+0.641
only
Token only
Feature activation+0.000
12
Token 12
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
In
TokenIn
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+0.436
found
Token found
Feature activation+1.981
that
Token that
Feature activation+1.120
politics
Token politics
Feature activation+0.570
was
Token was
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
important
Token important
Feature activation+0.000
court
Token court
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Research
TokenResearch
Feature activation+0.000
shows
Token shows
Feature activation+1.974
a
Token a
Feature activation+0.774
child
Token child
Feature activation+0.461
convicted
Token convicted
Feature activation+0.000
of
Token of
Feature activation+0.000
a
Token a
Feature activation+0.000
there
Token there
Feature activation+0.000
.
Token.
Feature activation+0.000
Indeed
Token Indeed
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.143
shows
Token shows
Feature activation+1.970
that
Token that
Feature activation+1.135
,
Token,
Feature activation+0.503
especially
Token especially
Feature activation+0.000
for
Token for
Feature activation+0.000
recently
Token recently
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
research
Token research
Feature activation+0.287
isn
Token isn
Feature activation+1.896
't
Token't
Feature activation+1.952
ready
Token ready
Feature activation+1.233
for
Token for
Feature activation+0.116
prime
Token prime
Feature activation+0.000
time
Token time
Feature activation+0.000
yet
Token yet
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
As
TokenAs
Feature activation+0.000
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
research
Token research
Feature activation+0.338
supporting
Token supporting
Feature activation+1.932
advanced
Token advanced
Feature activation+1.336
reactor
Token reactor
Feature activation+0.000
technology
Token technology
Feature activation+0.000
,
Token,
Feature activation+0.000
Do
Token Do
Feature activation+0.000
relationships
Token relationships
Feature activation+0.000
.
Token.
Feature activation+0.000
Further
Token Further
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.265
suggests
Token suggests
Feature activation+1.932
that
Token that
Feature activation+1.217
bisexual
Token bisexual
Feature activation+0.000
individuals
Token individuals
Feature activation+0.000
who
Token who
Feature activation+0.000
do
Token do
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
research
Token research
Feature activation+0.572
is
Token is
Feature activation+2.000
needed
Token needed
Feature activation+2.557
to
Token to
Feature activation+1.905
find
Token find
Feature activation+1.075
out
Token out
Feature activation+0.811
how
Token how
Feature activation+0.353
drastically
Token drastically
Feature activation+0.000
the
Token the
Feature activation+0.000
I
TokenI
Feature activation+0.000
could
Token could
Feature activation+0.000
find
Token find
Feature activation+0.000
no
Token no
Feature activation+0.000
research
Token research
Feature activation+0.620
supporting
Token supporting
Feature activation+1.901
the
Token the
Feature activation+0.828
idea
Token idea
Feature activation+0.642
that
Token that
Feature activation+0.000
bisexual
Token bisexual
Feature activation+0.000
s
Tokens
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Instead
TokenInstead
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+0.392
focused
Token focused
Feature activation+1.901
on
Token on
Feature activation+1.196
the
Token the
Feature activation+0.487
quality
Token quality
Feature activation+0.013
of
Token of
Feature activation+0.000
father
Token father
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
research
Token research
Feature activation+0.287
isn
Token isn
Feature activation+1.896
't
Token't
Feature activation+1.952
ready
Token ready
Feature activation+1.233
for
Token for
Feature activation+0.116
prime
Token prime
Feature activation+0.000
time
Token time
Feature activation+0.000
well
Token well
Feature activation+0.000
established
Token established
Feature activation+0.000
,
Token,
Feature activation+0.000
however
Token however
Feature activation+0.000
research
Token research
Feature activation+0.367
examining
Token examining
Feature activation+1.847
the
Token the
Feature activation+0.605
behavioural
Token behavioural
Feature activation+0.512
effects
Token effects
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
body
Token body
Feature activation+0.000
of
Token of
Feature activation+0.000
academic
Token academic
Feature activation+0.000
research
Token research
Feature activation+0.000
that
Token that
Feature activation+0.575
supports
Token supports
Feature activation+1.840
the
Token the
Feature activation+0.212
conservative
Token conservative
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Further
TokenFurther
Feature activation+0.000
research
Token research
Feature activation+0.052
by
Token by
Feature activation+1.818
T
Token T
Feature activation+1.302
&
Token&
Feature activation+0.000
E
TokenE
Feature activation+0.000
shows
Token shows
Feature activation+1.757
the
Token the
Feature activation+0.000

Top DFA by src position
MAX = 3.605

away
Token away
Feature activation+0.005
Top resid features:
it
Token it
Feature activation+0.005
Top resid features:
is
Token is
Feature activation-0.050
Top resid features:
.
Token.
Feature activation-0.067
Top resid features:
More
Token More
Feature activation+0.079
Top resid features:
research
Token research
Feature activation+3.213
Top resid features:
is
Token is
Feature activation-0.203
Top resid features:
needed
Token needed
Feature activation-0.060
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
would
Token would
Feature activation-0.096
Top resid features:
be
Token be
Feature activation-0.055
Top resid features:
pointing
Token pointing
Feature activation-0.066
Top resid features:
to
Token to
Feature activation+0.011
Top resid features:
the
Token the
Feature activation-0.145
Top resid features:
research
Token research
Feature activation+3.605
Top resid features:
showing
Token showing
Feature activation-0.198
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
eat
Token eat
Feature activation+0.000
Top resid features:
better
Token better
Feature activation+0.000
Top resid features:
MAP
TokenMAP
Feature activation-0.011
Top resid features:
diet
Token diet
Feature activation-0.017
Top resid features:
,
Token,
Feature activation-0.073
Top resid features:
but
Token but
Feature activation-0.085
Top resid features:
more
Token more
Feature activation+0.092
Top resid features:
research
Token research
Feature activation+3.120
Top resid features:
is
Token is
Feature activation-0.162
Top resid features:
needed
Token needed
Feature activation-0.083
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
next
Token next
Feature activation+0.000
Top resid features:
cancers
Token cancers
Feature activation-0.037
Top resid features:
.
Token.
Feature activation-0.103
Top resid features:
Ċ
TokenĊ
Feature activation-0.030
Top resid features:
Ċ
TokenĊ
Feature activation-0.039
Top resid features:
The
TokenThe
Feature activation-0.040
Top resid features:
research
Token research
Feature activation+3.133
Top resid features:
could
Token could
Feature activation+0.012
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
implications
Token implications
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
D
TokenD
Feature activation-0.013
Top resid features:
odd
Tokenodd
Feature activation-0.019
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
said
Token said
Feature activation-0.101
Top resid features:
previous
Token previous
Feature activation+0.018
Top resid features:
research
Token research
Feature activation+3.134
Top resid features:
had
Token had
Feature activation-0.163
Top resid features:
shown
Token shown
Feature activation-0.235
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
same
Token same
Feature activation+0.000
Top resid features:
"
Token "
Feature activation+0.000
Top resid features:
away
Token away
Feature activation-0.008
Top resid features:
it
Token it
Feature activation-0.002
Top resid features:
is
Token is
Feature activation-0.049
Top resid features:
.
Token.
Feature activation-0.092
Top resid features:
More
Token More
Feature activation+0.186
Top resid features:
research
Token research
Feature activation+2.541
Top resid features:
is
Token is
Feature activation-0.159
Top resid features:
needed
Token needed
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
it
Token it
Feature activation-0.013
Top resid features:
first
Token first
Feature activation-0.014
Top resid features:
seems
Token seems
Feature activation-0.080
Top resid features:
.
Token.
Feature activation-0.136
Top resid features:
Our
Token Our
Feature activation-0.032
Top resid features:
research
Token research
Feature activation+2.931
Top resid features:
shows
Token shows
Feature activation-0.177
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
only
Token only
Feature activation+0.000
Top resid features:
12
Token 12
Feature activation+0.000
Top resid features:
%
Token%
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.004
Top resid features:
In
TokenIn
Feature activation+0.023
Top resid features:
fact
Token fact
Feature activation-0.017
Top resid features:
,
Token,
Feature activation-0.147
Top resid features:
the
Token the
Feature activation-0.084
Top resid features:
research
Token research
Feature activation+2.658
Top resid features:
found
Token found
Feature activation+0.015
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
politics
Token politics
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
particularly
Token particularly
Feature activation+0.000
Top resid features:
adult
Token adult
Feature activation-0.001
Top resid features:
court
Token court
Feature activation-0.019
Top resid features:
.
Token.
Feature activation-0.102
Top resid features:
Ċ
TokenĊ
Feature activation-0.094
Top resid features:
Ċ
TokenĊ
Feature activation-0.126
Top resid features:
Research
TokenResearch
Feature activation+3.136
Top resid features:
shows
Token shows
Feature activation-0.200
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
child
Token child
Feature activation+0.000
Top resid features:
convicted
Token convicted
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
one
Token one
Feature activation-0.031
Top resid features:
there
Token there
Feature activation-0.025
Top resid features:
.
Token.
Feature activation-0.091
Top resid features:
Indeed
Token Indeed
Feature activation-0.069
Top resid features:
,
Token,
Feature activation-0.255
Top resid features:
research
Token research
Feature activation+3.011
Top resid features:
shows
Token shows
Feature activation-0.136
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
especially
Token especially
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
says
Token says
Feature activation+0.005
Top resid features:
.
Token.
Feature activation-0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.009
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
The
TokenThe
Feature activation-0.114
Top resid features:
research
Token research
Feature activation+2.870
Top resid features:
isn
Token isn
Feature activation-0.112
Top resid features:
't
Token't
Feature activation-0.099
Top resid features:
ready
Token ready
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
prime
Token prime
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.024
Top resid features:
Ċ
TokenĊ
Feature activation+0.020
Top resid features:
As
TokenAs
Feature activation-0.055
Top resid features:
well
Token well
Feature activation+0.081
Top resid features:
as
Token as
Feature activation-0.129
Top resid features:
research
Token research
Feature activation+2.576
Top resid features:
supporting
Token supporting
Feature activation-0.064
Top resid features:
advanced
Token advanced
Feature activation+0.000
Top resid features:
reactor
Token reactor
Feature activation+0.000
Top resid features:
technology
Token technology
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
term
Tokenterm
Feature activation-0.006
Top resid features:
relationships
Token relationships
Feature activation-0.023
Top resid features:
.
Token.
Feature activation-0.080
Top resid features:
Further
Token Further
Feature activation+0.064
Top resid features:
,
Token,
Feature activation-0.223
Top resid features:
research
Token research
Feature activation+2.920
Top resid features:
suggests
Token suggests
Feature activation-0.141
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
bisexual
Token bisexual
Feature activation+0.000
Top resid features:
individuals
Token individuals
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
away
Token away
Feature activation-0.008
Top resid features:
it
Token it
Feature activation+0.003
Top resid features:
is
Token is
Feature activation-0.045
Top resid features:
.
Token.
Feature activation-0.018
Top resid features:
More
Token More
Feature activation+0.071
Top resid features:
research
Token research
Feature activation+2.643
Top resid features:
is
Token is
Feature activation-0.169
Top resid features:
needed
Token needed
Feature activation-0.209
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
find
Token find
Feature activation+0.000
Top resid features:
out
Token out
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
I
TokenI
Feature activation-0.015
Top resid features:
could
Token could
Feature activation+0.001
Top resid features:
find
Token find
Feature activation+0.004
Top resid features:
no
Token no
Feature activation-0.154
Top resid features:
research
Token research
Feature activation+2.619
Top resid features:
supporting
Token supporting
Feature activation-0.153
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
idea
Token idea
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
bisexual
Token bisexual
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.012
Top resid features:
Ċ
TokenĊ
Feature activation-0.002
Top resid features:
Instead
TokenInstead
Feature activation-0.164
Top resid features:
,
Token,
Feature activation-0.110
Top resid features:
the
Token the
Feature activation-0.043
Top resid features:
research
Token research
Feature activation+2.928
Top resid features:
focused
Token focused
Feature activation-0.118
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
quality
Token quality
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
says
Token says
Feature activation-0.003
Top resid features:
.
Token.
Feature activation-0.078
Top resid features:
Ċ
TokenĊ
Feature activation-0.005
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
The
TokenThe
Feature activation-0.130
Top resid features:
research
Token research
Feature activation+2.707
Top resid features:
isn
Token isn
Feature activation-0.000
Top resid features:
't
Token't
Feature activation+0.000
Top resid features:
ready
Token ready
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
prime
Token prime
Feature activation+0.000
Top resid features:
fairly
Token fairly
Feature activation-0.024
Top resid features:
well
Token well
Feature activation+0.014
Top resid features:
established
Token established
Feature activation-0.026
Top resid features:
,
Token,
Feature activation-0.173
Top resid features:
however
Token however
Feature activation-0.080
Top resid features:
research
Token research
Feature activation+2.878
Top resid features:
examining
Token examining
Feature activation-0.196
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
behavioural
Token behavioural
Feature activation+0.000
Top resid features:
effects
Token effects
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
a
Token a
Feature activation-0.019
Top resid features:
growing
Token growing
Feature activation+0.013
Top resid features:
body
Token body
Feature activation-0.056
Top resid features:
of
Token of
Feature activation+0.004
Top resid features:
academic
Token academic
Feature activation+0.202
Top resid features:
research
Token research
Feature activation+2.459
Top resid features:
that
Token that
Feature activation-0.215
Top resid features:
supports
Token supports
Feature activation-0.096
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
conservative
Token conservative
Feature activation+0.000
Top resid features:
view
Token view
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation-0.054
Top resid features:
Ŀ
TokenĿ
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.029
Top resid features:
Further
TokenFurther
Feature activation-0.150
Top resid features:
research
Token research
Feature activation+2.761
Top resid features:
by
Token by
Feature activation-0.044
Top resid features:
T
Token T
Feature activation+0.000
Top resid features:
&
Token&
Feature activation+0.000
Top resid features:
E
TokenE
Feature activation+0.000
Top resid features:
shows
Token shows
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.05

Head 1: 0.06

Head 2: 0.05

Head 3: 0.06

Head 4: 0.06

Head 5: 0.07

Head 6: 0.05

Head 7: 0.05

Head 8: 0.06

Head 9: 0.36

Head 10: 0.09

Head 11: 0.04

Positive logits

earcher1.66

enhagen1.56

research1.52

quantitative1.52

analys1.48

hypothes1.44

Quant1.41

STEM1.39

foc1.38

Quant1.38

ellen1.37

forecasting1.37

behavioural1.37

hypotheses1.37

neuroscience1.34

ractical1.34

correl1.33

quant1.33

ummies1.31

itatively1.31

Negative logits

ht-1.36

TY-1.33

voic-1.33

kiss-1.33

wings-1.32

tiles-1.26

kissed-1.26

bolt-1.22

vati-1.20

retaliate-1.19

tile-1.19

kisses-1.19

whine-1.18

mop-1.17

illes-1.16

tall-1.16

choke-1.15

externalActionCode-1.14

gro-1.14

awkward-1.13

INTERVAL 2.301 - 2.557
CONTAINS 0.000%

be
Token be
Feature activation+0.000
pointing
Token pointing
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+0.193
showing
Token showing
Feature activation+2.467
that
Token that
Feature activation+0.945
people
Token people
Feature activation+0.269
eat
Token eat
Feature activation+0.000
better
Token better
Feature activation+0.000
and
Token and
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.146
is
Token is
Feature activation+1.683
needed
Token needed
Feature activation+2.307
before
Token before
Feature activation+0.862
the
Token the
Feature activation+0.003
next
Token next
Feature activation+0.000
diet
Token diet
Feature activation+0.000
cra
Token cra
Feature activation+0.000
is
Token is
Feature activation+0.000
.
Token.
Feature activation+0.000
More
Token More
Feature activation+0.000
research
Token research
Feature activation+0.572
is
Token is
Feature activation+2.000
needed
Token needed
Feature activation+2.557
to
Token to
Feature activation+1.905
find
Token find
Feature activation+1.075
out
Token out
Feature activation+0.811
how
Token how
Feature activation+0.353
drastically
Token drastically
Feature activation+0.000

INTERVAL 2.046 - 2.301
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
research
Token research
Feature activation+0.000
could
Token could
Feature activation+2.210
also
Token also
Feature activation+1.719
have
Token have
Feature activation+1.516
implications
Token implications
Feature activation+0.870
for
Token for
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
s
Tokens
Feature activation+0.000
said
Token said
Feature activation+0.000
previous
Token previous
Feature activation+0.000
research
Token research
Feature activation+0.000
had
Token had
Feature activation+1.039
shown
Token shown
Feature activation+2.093
the
Token the
Feature activation+0.497
same
Token same
Feature activation+0.000
"
Token "
Feature activation+0.000
dec
Tokendec
Feature activation+0.000
arbon
Tokenarbon
Feature activation+0.000

INTERVAL 1.790 - 2.046
CONTAINS 0.002%

In
TokenIn
Feature activation+0.000
fact
Token fact
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+0.436
found
Token found
Feature activation+1.981
that
Token that
Feature activation+1.120
politics
Token politics
Feature activation+0.570
was
Token was
Feature activation+0.000
particularly
Token particularly
Feature activation+0.000
important
Token important
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
research
Token research
Feature activation+0.287
isn
Token isn
Feature activation+1.896
't
Token't
Feature activation+1.952
ready
Token ready
Feature activation+1.233
for
Token for
Feature activation+0.116
prime
Token prime
Feature activation+0.000
time
Token time
Feature activation+0.000
yet
Token yet
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
research
Token research
Feature activation+0.287
isn
Token isn
Feature activation+1.896
't
Token't
Feature activation+1.952
ready
Token ready
Feature activation+1.233
for
Token for
Feature activation+0.116
prime
Token prime
Feature activation+0.000
time
Token time
Feature activation+0.000
body
Token body
Feature activation+0.000
of
Token of
Feature activation+0.000
academic
Token academic
Feature activation+0.000
research
Token research
Feature activation+0.000
that
Token that
Feature activation+0.575
supports
Token supports
Feature activation+1.840
the
Token the
Feature activation+0.212
conservative
Token conservative
Feature activation+0.000
view
Token view
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Further
TokenFurther
Feature activation+0.000
research
Token research
Feature activation+0.052
by
Token by
Feature activation+1.818
T
Token T
Feature activation+1.302
&
Token&
Feature activation+0.000
E
TokenE
Feature activation+0.000
shows
Token shows
Feature activation+1.757
the
Token the
Feature activation+0.000

INTERVAL 1.534 - 1.790
CONTAINS 0.002%

by
Token by
Feature activation+0.000
others
Token others
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
research
Token research
Feature activation+0.142
consisted
Token consisted
Feature activation+1.710
of
Token of
Feature activation+1.263
forcing
Token forcing
Feature activation+0.632
test
Token test
Feature activation+0.000
subjects
Token subjects
Feature activation+0.000
to
Token to
Feature activation+0.000
,
Token,
Feature activation+0.000
upbeat
Token upbeat
Feature activation+0.000
conversations
Token conversations
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.000
shows
Token shows
Feature activation+1.648
.
Token.
Feature activation+0.307
Seek
Token Seek
Feature activation+0.000
out
Token out
Feature activation+0.000
any
Token any
Feature activation+0.000
common
Token common
Feature activation+0.000
culmin
Token culmin
Feature activation+0.000
ates
Tokenates
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
research
Token research
Feature activation+0.100
indicating
Token indicating
Feature activation+1.738
that
Token that
Feature activation+0.820
the
Token the
Feature activation+0.213
convoluted
Token convoluted
Feature activation+0.000
squ
Token squ
Feature activation+0.000
ishy
Tokenishy
Feature activation+0.000
.
Token.
Feature activation+0.000
One
Token One
Feature activation+0.000
factor
Token factor
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.249
shows
Token shows
Feature activation+1.720
,
Token,
Feature activation+0.993
has
Token has
Feature activation+1.209
a
Token a
Feature activation+0.582
larger
Token larger
Feature activation+0.361
-
Token-
Feature activation+0.000
where
Token where
Feature activation+0.000
such
Token such
Feature activation+0.000
fundamental
Token fundamental
Feature activation+0.000
research
Token research
Feature activation+0.000
that
Token that
Feature activation+0.506
impacts
Token impacts
Feature activation+1.556
the
Token the
Feature activation+0.000
fields
Token fields
Feature activation+0.000
of
Token of
Feature activation+0.000
both
Token both
Feature activation+0.000
computing
Token computing
Feature activation+0.000

INTERVAL 1.278 - 1.534
CONTAINS 0.002%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
is
Token is
Feature activation+0.000
Research
Token Research
Feature activation+0.318
?
Token?
Feature activation+1.378
Ċ
TokenĊ
Feature activation+0.387
Ċ
TokenĊ
Feature activation+0.227
or
Tokenor
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
new
Token new
Feature activation+0.000
research
Token research
Feature activation+0.000
also
Token also
Feature activation+1.112
highlights
Token highlights
Feature activation+1.453
how
Token how
Feature activation+0.008
technology
Token technology
Feature activation+0.000
can
Token can
Feature activation+0.000
provide
Token provide
Feature activation+0.000
insight
Token insight
Feature activation+0.000
extensively
Token extensively
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
New
TokenNew
Feature activation+0.000
research
Token research
Feature activation+0.450
on
Token on
Feature activation+1.142
the
Token the
Feature activation+1.524
structure
Token structure
Feature activation+0.487
of
Token of
Feature activation+0.000
spider
Token spider
Feature activation+0.000
silk
Token silk
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Further
TokenFurther
Feature activation+0.000
research
Token research
Feature activation+0.052
by
Token by
Feature activation+1.818
T
Token T
Feature activation+1.302
&
Token&
Feature activation+0.000
E
TokenE
Feature activation+0.000
shows
Token shows
Feature activation+1.757
the
Token the
Feature activation+0.000
availability
Token availability
Feature activation+0.000
will
Token will
Feature activation+0.000
establish
Token establish
Feature activation+0.000
a
Token a
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
development
Token development
Feature activation+1.388
centre
Token centre
Feature activation+0.000
focusing
Token focusing
Feature activation+0.133
on
Token on
Feature activation+0.000
autonomous
Token autonomous
Feature activation+0.000
and
Token and
Feature activation+0.000

INTERVAL 1.023 - 1.278
CONTAINS 0.003%

The
TokenThe
Feature activation+0.000
growing
Token growing
Feature activation+0.000
field
Token field
Feature activation+0.000
of
Token of
Feature activation+0.000
research
Token research
Feature activation+0.554
on
Token on
Feature activation+1.193
bisexual
Token bisexual
Feature activation+0.266
ity
Tokenity
Feature activation+0.000
is
Token is
Feature activation+0.356
promising
Token promising
Feature activation+0.022
,
Token,
Feature activation+0.000
-
Token-
Feature activation+0.000
centered
Tokencentered
Feature activation+0.000
outcomes
Token outcomes
Feature activation+0.000
research
Token research
Feature activation+0.000
to
Token to
Feature activation+0.906
identify
Token identify
Feature activation+1.064
waste
Token waste
Feature activation+0.000
and
Token and
Feature activation+0.000
improve
Token improve
Feature activation+0.000
the
Token the
Feature activation+0.000
safety
Token safety
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
To
TokenTo
Feature activation+0.000
do
Token do
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+0.000
,
Token,
Feature activation+1.263
his
Token his
Feature activation+0.854
team
Token team
Feature activation+0.000
placed
Token placed
Feature activation+0.177
a
Token a
Feature activation+0.000
special
Token special
Feature activation+0.000
a
Token a
Feature activation+0.000
fake
Token fake
Feature activation+0.000
research
Token research
Feature activation+0.000
journal
Token journal
Feature activation+0.000
to
Token to
Feature activation+0.755
push
Token push
Feature activation+1.207
Mer
Token Mer
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
products
Token products
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
An
TokenAn
Feature activation+0.000
international
Token international
Feature activation+0.000
research
Token research
Feature activation+0.000
team
Token team
Feature activation+0.200
has
Token has
Feature activation+0.444
used
Token used
Feature activation+1.120
a
Token a
Feature activation+0.125
"
Token "
Feature activation+0.000
ther
Tokenther
Feature activation+0.000
mal
Tokenmal
Feature activation+0.000
met
Token met
Feature activation+0.000

INTERVAL 0.767 - 1.023
CONTAINS 0.005%

phrases
Token phrases
Feature activation+0.000
.
Token.
Feature activation+0.000
Body
Token Body
Feature activation+0.000
language
Token language
Feature activation+0.000
research
Token research
Feature activation+0.000
has
Token has
Feature activation+0.925
revealed
Token revealed
Feature activation+1.770
a
Token a
Feature activation+0.052
correlation
Token correlation
Feature activation+0.000
between
Token between
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
;
Token;
Feature activation+0.000
some
Token some
Feature activation+0.000
research
Token research
Feature activation+0.000
,
Token,
Feature activation+1.231
especially
Token especially
Feature activation+0.984
in
Token in
Feature activation+0.662
the
Token the
Feature activation+0.519
area
Token area
Feature activation+0.142
of
Token of
Feature activation+0.000
heart
Token heart
Feature activation+0.000
but
Token but
Feature activation+0.000
more
Token more
Feature activation+0.000
research
Token research
Feature activation+0.146
is
Token is
Feature activation+1.683
needed
Token needed
Feature activation+2.307
before
Token before
Feature activation+0.862
the
Token the
Feature activation+0.003
next
Token next
Feature activation+0.000
diet
Token diet
Feature activation+0.000
cra
Token cra
Feature activation+0.000
ze
Tokenze
Feature activation+0.000
to
Token to
Feature activation+0.000
locate
Token locate
Feature activation+0.000
a
Token a
Feature activation+0.000
research
Token research
Feature activation+0.000
and
Token and
Feature activation+0.000
development
Token development
Feature activation+1.018
centre
Token centre
Feature activation+0.000
in
Token in
Feature activation+0.000
Turk
Token Turk
Feature activation+0.000
u
Tokenu
Feature activation+0.000
is
Token is
Feature activation+0.000
A
TokenA
Feature activation+0.000
lot
Token lot
Feature activation+0.000
of
Token of
Feature activation+0.000
research
Token research
Feature activation+0.000
has
Token has
Feature activation+0.631
been
Token been
Feature activation+0.874
done
Token done
Feature activation+1.117
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
10
Token 10
Feature activation+0.000

INTERVAL 0.511 - 0.767
CONTAINS 0.008%

economic
Token economic
Feature activation+0.000
and
Token and
Feature activation+0.000
historical
Token historical
Feature activation+0.000
research
Token research
Feature activation+0.000
demonstrates
Token demonstrates
Feature activation+1.246
that
Token that
Feature activation+0.653
black
Token black
Feature activation+0.255
student
Token student
Feature activation+0.000
performance
Token performance
Feature activation+0.000
improves
Token improves
Feature activation+0.000
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
recent
Token recent
Feature activation+0.000
research
Token research
Feature activation+0.057
paper
Token paper
Feature activation+0.074
we
Token we
Feature activation+0.436
look
Token look
Feature activation+0.622
at
Token at
Feature activation+0.481
how
Token how
Feature activation+0.042
the
Token the
Feature activation+0.000
fiscal
Token fiscal
Feature activation+0.000
-
Token-
Feature activation+0.000
-
Token-
Feature activation+0.000
in
Tokenin
Feature activation+0.000
excuse
Token excuse
Feature activation+0.000
.
Token.
Feature activation+0.000
Research
Token Research
Feature activation+0.000
.
Token.
Feature activation+0.674
It
Token It
Feature activation+1.375
âĢ
TokenâĢ
Feature activation+0.184
Ļ
TokenĻ
Feature activation+0.105
s
Tokens
Feature activation+0.000
always
Token always
Feature activation+0.000
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
fake
Token fake
Feature activation+0.000
research
Token research
Feature activation+0.000
journal
Token journal
Feature activation+0.000
to
Token to
Feature activation+0.755
push
Token push
Feature activation+1.207
Mer
Token Mer
Feature activation+0.000
ck
Tokenck
Feature activation+0.000
products
Token products
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
growing
Token growing
Feature activation+0.000
field
Token field
Feature activation+0.000
of
Token of
Feature activation+0.000
research
Token research
Feature activation+0.554
on
Token on
Feature activation+1.193
bisexual
Token bisexual
Feature activation+0.266
ity
Tokenity
Feature activation+0.000
is
Token is
Feature activation+0.356
promising
Token promising
Feature activation+0.022

INTERVAL 0.256 - 0.511
CONTAINS 0.011%

body
Token body
Feature activation+0.000
weight
Token weight
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
studies
Token studies
Feature activation+0.000
looked
Token looked
Feature activation+0.280
at
Token at
Feature activation+0.000
people
Token people
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
An
TokenAn
Feature activation+0.000
international
Token international
Feature activation+0.000
research
Token research
Feature activation+0.000
team
Token team
Feature activation+0.200
has
Token has
Feature activation+0.444
used
Token used
Feature activation+1.120
a
Token a
Feature activation+0.125
"
Token "
Feature activation+0.000
ther
Tokenther
Feature activation+0.000
mal
Tokenmal
Feature activation+0.000
research
Token research
Feature activation+0.249
shows
Token shows
Feature activation+1.720
,
Token,
Feature activation+0.993
has
Token has
Feature activation+1.209
a
Token a
Feature activation+0.582
larger
Token larger
Feature activation+0.361
-
Token-
Feature activation+0.000
than
Tokenthan
Feature activation+0.000
-
Token-
Feature activation+0.000
expected
Tokenexpected
Feature activation+0.000
impact
Token impact
Feature activation+0.000
upbeat
Token upbeat
Feature activation+0.000
conversations
Token conversations
Feature activation+0.000
,
Token,
Feature activation+0.000
research
Token research
Feature activation+0.000
shows
Token shows
Feature activation+1.648
.
Token.
Feature activation+0.307
Seek
Token Seek
Feature activation+0.000
out
Token out
Feature activation+0.000
any
Token any
Feature activation+0.000
common
Token common
Feature activation+0.000
interests
Token interests
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
ashi
Tokenashi
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
research
Token research
Feature activation+0.000
team
Token team
Feature activation+0.477
said
Token said
Feature activation+0.429
"
Token "
Feature activation+0.241
We
TokenWe
Feature activation+0.000
first
Token first
Feature activation+0.000
discovered
Token discovered
Feature activation+0.000

INTERVAL 0.000 - 0.256
CONTAINS 99.968%

,
Token,
Feature activation+0.000
long
Token long
Feature activation+0.000
turnover
Token turnover
Feature activation+0.000
drives
Token drives
Feature activation+0.000
.
Token.
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Arch
Token Arch
Feature activation+0.000
on
Tokenon
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
of
Token of
Feature activation+0.000
miles
Token miles
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
city
Token city
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
aging
Token aging
Feature activation+0.000
sewer
Token sewer
Feature activation+0.000
and
Token and
Feature activation+0.000
any
Token any
Feature activation+0.000
organization
Token organization
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sil
TokenSil
Feature activation+0.000
icon
Tokenicon
Feature activation+0.000
Valley
Token Valley
Feature activation+0.000
's
Token's
Feature activation+0.000
war
Token war
Feature activation+0.000
for
Token for
Feature activation+0.000
YOU
Token YOU
Feature activation+0.000
ST
Token ST
Feature activation+0.000
UP
TokenUP
Feature activation+0.000
ID
TokenID
Feature activation+0.000
FUCK
Token FUCK
Feature activation+0.000
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
I
Token I
Feature activation+0.000
'm
Token'm
Feature activation+0.000
a
Token a
Feature activation+0.000
trans
Token trans
Feature activation+0.000
a
Token a
Feature activation+0.000
prag
Token prag
Feature activation+0.000
mat
Tokenmat
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
behind
Token behind
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
You
Token You
Feature activation+0.000
look
Token look
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.138
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 8 in H2.9: (feature 9965)

TOP ACTIVATIONS
MAX = 3.355

Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
separate
Token separate
Feature activation+0.000
article
Token article
Feature activation+0.023
released
Token released
Feature activation+3.294
on
Token on
Feature activation+0.078
Thursday
Token Thursday
Feature activation+0.067
,
Token,
Feature activation+0.000
Del
Token Del
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
where
Token where
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
article
Token article
Feature activation+0.471
does
Token does
Feature activation+2.578
it
Token it
Feature activation+1.041
acknowledge
Token acknowledge
Feature activation+0.978
that
Token that
Feature activation+0.000
an
Token an
Feature activation+0.000
egregious
Token egregious
Feature activation+0.000
you
Token you
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
article
Tokenarticle
Feature activation+0.364
by
Token by
Feature activation+2.528
Af
Token Af
Feature activation+0.617
ro
Tokenro
Feature activation+0.000
dit
Tokendit
Feature activation+0.000
i
Tokeni
Feature activation+0.000
K
Token K
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
article
Token article
Feature activation+0.068
last
Token last
Feature activation+2.450
year
Token year
Feature activation+2.273
,
Token,
Feature activation+0.598
written
Token written
Feature activation+0.635
before
Token before
Feature activation+0.000
NYPD
Token NYPD
Feature activation+0.000
because
Token because
Feature activation+0.000
you
Token you
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.000
was
Token was
Feature activation+2.386
originally
Token originally
Feature activation+1.916
published
Token published
Feature activation+1.230
on
Token on
Feature activation+0.000
August
Token August
Feature activation+0.000
21
Token 21
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.114
was
Token was
Feature activation+2.358
originally
Token originally
Feature activation+1.904
written
Token written
Feature activation+1.618
for
Token for
Feature activation+0.134
Science
Token Science
Feature activation+0.000
of
Token of
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
,
Token,
Feature activation+2.346
I
Token I
Feature activation+1.468
will
Token will
Feature activation+1.032
explain
Token explain
Feature activation+0.704
Goal
Token Goal
Feature activation+0.000
and
Token and
Feature activation+0.000
Laura
Token Laura
Feature activation+0.000
Miller
Token Miller
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
an
Token an
Feature activation+0.000
article
Token article
Feature activation+0.096
called
Token called
Feature activation+2.342
âĢ
Token âĢ
Feature activation+0.097
ľ
Tokenľ
Feature activation+0.000
In
TokenIn
Feature activation+0.085
Defense
Token Defense
Feature activation+0.000
of
Token of
Feature activation+0.000
From
Token From
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
article
Token article
Feature activation+0.068
last
Token last
Feature activation+2.450
year
Token year
Feature activation+2.273
,
Token,
Feature activation+0.598
written
Token written
Feature activation+0.635
before
Token before
Feature activation+0.000
NYPD
Token NYPD
Feature activation+0.000
officers
Token officers
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.000
was
Token was
Feature activation+2.256
first
Token first
Feature activation+1.816
written
Token written
Feature activation+1.280
by
Token by
Feature activation+0.033
Newsweek
Token Newsweek
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Egyptian
Token Egyptian
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
article
Token article
Feature activation+0.457
calls
Token calls
Feature activation+2.232
for
Token for
Feature activation+0.472
prison
Token prison
Feature activation+0.090
sentences
Token sentences
Feature activation+0.000
and
Token and
Feature activation+0.000
fines
Token fines
Feature activation+0.000
available
Token available
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.221
will
Token will
Feature activation+2.147
show
Token show
Feature activation+1.657
you
Token you
Feature activation+0.469
how
Token how
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
render
Token render
Feature activation+0.000
an
Token an
Feature activation+0.000
article
Token article
Feature activation+0.128
containing
Token containing
Feature activation+2.146
both
Token both
Feature activation+0.286
R
Token R
Feature activation+0.000
plots
Token plots
Feature activation+0.000
and
Token and
Feature activation+0.000
diagrams
Token diagrams
Feature activation+0.000
once
Token once
Feature activation+0.000
again
Token again
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.000
is
Token is
Feature activation+2.138
over
Token over
Feature activation+0.766
2
Token 2
Feature activation+0.433
years
Token years
Feature activation+0.895
old
Token old
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ed
TokenEd
Feature activation+0.000
note
Token note
Feature activation+0.000
:
Token:
Feature activation+0.000
This
Token This
Feature activation+0.000
article
Token article
Feature activation+0.000
was
Token was
Feature activation+2.121
updated
Token updated
Feature activation+1.495
on
Token on
Feature activation+0.000
March
Token March
Feature activation+0.000
2
Token 2
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.141
is
Token is
Feature activation+2.091
from
Token from
Feature activation+1.367
the
Token the
Feature activation+1.095
archive
Token archive
Feature activation+0.846
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
:
Token:
Feature activation+0.000
apple
Token apple
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.000
is
Token is
Feature activation+2.078
from
Token from
Feature activation+1.092
the
Token the
Feature activation+1.167
archive
Token archive
Feature activation+0.610
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
Washington
Token Washington
Feature activation+0.000
Post
Token Post
Feature activation+0.000
article
Token article
Feature activation+0.035
cast
Token cast
Feature activation+2.063
it
Token it
Feature activation+0.248
in
Token in
Feature activation+0.063
an
Token an
Feature activation+0.046
Orwell
Token Orwell
Feature activation+0.000
ian
Tokenian
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.000
is
Token is
Feature activation+2.042
from
Token from
Feature activation+1.256
the
Token the
Feature activation+0.882
archive
Token archive
Feature activation+0.506
of
Token of
Feature activation+0.000
our
Token our
Feature activation+0.000
8
Token8
Feature activation+0.000
].
Token].
Feature activation+0.000
In
Token In
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.229
,
Token,
Feature activation+2.033
based
Token based
Feature activation+1.818
on
Token on
Feature activation+0.719
a
Token a
Feature activation+0.244
talk
Token talk
Feature activation+0.098
given
Token given
Feature activation+0.000

Top DFA by src position
MAX = 5.468

<|endoftext|>
Token<|endoftext|>
Feature activation-0.126
Top resid features:
Ċ
TokenĊ
Feature activation-0.060
Top resid features:
In
TokenIn
Feature activation-0.052
Top resid features:
a
Token a
Feature activation+0.059
Top resid features:
separate
Token separate
Feature activation-0.096
Top resid features:
article
Token article
Feature activation+5.468
Top resid features:
released
Token released
Feature activation-0.117
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Thursday
Token Thursday
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Del
Token Del
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.031
Top resid features:
where
Token where
Feature activation-0.125
Top resid features:
in
Token in
Feature activation-0.155
Top resid features:
the
Token the
Feature activation-0.039
Top resid features:
article
Token article
Feature activation+4.768
Top resid features:
does
Token does
Feature activation-0.057
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
acknowledge
Token acknowledge
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
near
Token near
Feature activation+0.232
Top resid features:
you
Token you
Feature activation+0.027
Top resid features:
!
Token!
Feature activation+0.188
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.061
Top resid features:
article
Tokenarticle
Feature activation+3.939
Top resid features:
by
Token by
Feature activation-0.190
Top resid features:
Af
Token Af
Feature activation+0.000
Top resid features:
ro
Tokenro
Feature activation+0.000
Top resid features:
dit
Tokendit
Feature activation+0.000
Top resid features:
i
Tokeni
Feature activation+0.000
Top resid features:
crackdown
Token crackdown
Feature activation+0.046
Top resid features:
.
Token.
Feature activation+0.089
Top resid features:
From
Token From
Feature activation-0.064
Top resid features:
the
Token the
Feature activation-0.064
Top resid features:
same
Token same
Feature activation-0.138
Top resid features:
article
Token article
Feature activation+4.463
Top resid features:
last
Token last
Feature activation-0.044
Top resid features:
year
Token year
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
written
Token written
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
sandwich
Token sandwich
Feature activation+0.029
Top resid features:
because
Token because
Feature activation-0.025
Top resid features:
you
Token you
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.117
Top resid features:
This
TokenThis
Feature activation-0.489
Top resid features:
article
Token article
Feature activation+4.780
Top resid features:
was
Token was
Feature activation-0.050
Top resid features:
originally
Token originally
Feature activation+0.000
Top resid features:
published
Token published
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
August
Token August
Feature activation+0.000
Top resid features:
website
Token website
Feature activation+0.040
Top resid features:
.
Token.
Feature activation+0.068
Top resid features:
Ċ
TokenĊ
Feature activation+0.049
Top resid features:
Ċ
TokenĊ
Feature activation+0.060
Top resid features:
This
TokenThis
Feature activation-0.388
Top resid features:
article
Token article
Feature activation+4.398
Top resid features:
was
Token was
Feature activation-0.013
Top resid features:
originally
Token originally
Feature activation+0.000
Top resid features:
written
Token written
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Science
Token Science
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.055
Top resid features:
Ċ
TokenĊ
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation+0.017
Top resid features:
In
TokenIn
Feature activation-0.057
Top resid features:
this
Token this
Feature activation-0.079
Top resid features:
article
Token article
Feature activation+4.108
Top resid features:
,
Token,
Feature activation+0.203
Top resid features:
I
Token I
Feature activation+0.000
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
explain
Token explain
Feature activation+0.000
Top resid features:
Goal
Token Goal
Feature activation+0.000
Top resid features:
contributor
Token contributor
Feature activation+0.041
Top resid features:
Laura
Token Laura
Feature activation+0.007
Top resid features:
Miller
Token Miller
Feature activation+0.065
Top resid features:
wrote
Token wrote
Feature activation-0.219
Top resid features:
an
Token an
Feature activation+0.045
Top resid features:
article
Token article
Feature activation+4.214
Top resid features:
called
Token called
Feature activation-0.119
Top resid features:
âĢ
Token âĢ
Feature activation+0.000
Top resid features:
ľ
Tokenľ
Feature activation+0.000
Top resid features:
In
TokenIn
Feature activation+0.000
Top resid features:
Defense
Token Defense
Feature activation+0.000
Top resid features:
crackdown
Token crackdown
Feature activation+0.029
Top resid features:
.
Token.
Feature activation+0.090
Top resid features:
From
Token From
Feature activation+0.056
Top resid features:
the
Token the
Feature activation-0.044
Top resid features:
same
Token same
Feature activation-0.110
Top resid features:
article
Token article
Feature activation+4.191
Top resid features:
last
Token last
Feature activation-0.168
Top resid features:
year
Token year
Feature activation+0.096
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
written
Token written
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
Records
Token Records
Feature activation-0.144
Top resid features:
.
Token.
Feature activation+0.076
Top resid features:
Ċ
TokenĊ
Feature activation+0.037
Top resid features:
Ċ
TokenĊ
Feature activation+0.032
Top resid features:
This
TokenThis
Feature activation-0.439
Top resid features:
article
Token article
Feature activation+4.676
Top resid features:
was
Token was
Feature activation-0.016
Top resid features:
first
Token first
Feature activation+0.000
Top resid features:
written
Token written
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Newsweek
Token Newsweek
Feature activation+0.000
Top resid features:
the
Token the
Feature activation-0.017
Top resid features:
Egyptian
Token Egyptian
Feature activation-0.013
Top resid features:
Constitution
Token Constitution
Feature activation+0.077
Top resid features:
.
Token.
Feature activation+0.114
Top resid features:
The
Token The
Feature activation-0.059
Top resid features:
article
Token article
Feature activation+4.167
Top resid features:
calls
Token calls
Feature activation-0.160
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
prison
Token prison
Feature activation+0.000
Top resid features:
sentences
Token sentences
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
its
Token its
Feature activation-0.004
Top resid features:
available
Token available
Feature activation+0.013
Top resid features:
,
Token,
Feature activation+0.105
Top resid features:
and
Token and
Feature activation-0.043
Top resid features:
this
Token this
Feature activation-0.109
Top resid features:
article
Token article
Feature activation+3.998
Top resid features:
will
Token will
Feature activation-0.101
Top resid features:
show
Token show
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
how
Token how
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
composed
Token composed
Feature activation-0.033
Top resid features:
.
Token.
Feature activation+0.057
Top resid features:
To
Token To
Feature activation-0.099
Top resid features:
render
Token render
Feature activation-0.010
Top resid features:
an
Token an
Feature activation+0.115
Top resid features:
article
Token article
Feature activation+4.145
Top resid features:
containing
Token containing
Feature activation-0.070
Top resid features:
both
Token both
Feature activation+0.000
Top resid features:
R
Token R
Feature activation+0.000
Top resid features:
plots
Token plots
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
there
Token there
Feature activation-0.008
Top resid features:
once
Token once
Feature activation-0.058
Top resid features:
again
Token again
Feature activation-0.046
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.111
Top resid features:
This
TokenThis
Feature activation-0.511
Top resid features:
article
Token article
Feature activation+4.802
Top resid features:
is
Token is
Feature activation-0.047
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
2
Token 2
Feature activation+0.000
Top resid features:
years
Token years
Feature activation+0.000
Top resid features:
old
Token old
Feature activation+0.000
Top resid features:
[
Token[
Feature activation-0.028
Top resid features:
Ed
TokenEd
Feature activation+0.013
Top resid features:
note
Token note
Feature activation-0.057
Top resid features:
:
Token:
Feature activation+0.107
Top resid features:
This
Token This
Feature activation-0.547
Top resid features:
article
Token article
Feature activation+4.508
Top resid features:
was
Token was
Feature activation-0.023
Top resid features:
updated
Token updated
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
March
Token March
Feature activation+0.000
Top resid features:
2
Token 2
Feature activation+0.000
Top resid features:
carrier
Token carrier
Feature activation-0.003
Top resid features:
.
Token.
Feature activation+0.073
Top resid features:
Ċ
TokenĊ
Feature activation+0.021
Top resid features:
Ċ
TokenĊ
Feature activation+0.055
Top resid features:
This
TokenThis
Feature activation-0.376
Top resid features:
article
Token article
Feature activation+4.214
Top resid features:
is
Token is
Feature activation-0.023
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
archive
Token archive
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Companies
TokenCompanies
Feature activation+0.042
Top resid features:
:
Token:
Feature activation-0.009
Top resid features:
apple
Token apple
Feature activation+0.047
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.171
Top resid features:
This
TokenThis
Feature activation-0.528
Top resid features:
article
Token article
Feature activation+4.627
Top resid features:
is
Token is
Feature activation-0.046
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
archive
Token archive
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
scale
Token scale
Feature activation-0.000
Top resid features:
.
Token.
Feature activation+0.042
Top resid features:
The
Token The
Feature activation-0.071
Top resid features:
Washington
Token Washington
Feature activation+0.032
Top resid features:
Post
Token Post
Feature activation+0.503
Top resid features:
article
Token article
Feature activation+3.524
Top resid features:
cast
Token cast
Feature activation+0.033
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
Orwell
Token Orwell
Feature activation+0.000
Top resid features:
5
Token 5
Feature activation-0.035
Top resid features:
.
Token.
Feature activation+0.074
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.057
Top resid features:
This
TokenThis
Feature activation-0.365
Top resid features:
article
Token article
Feature activation+4.290
Top resid features:
is
Token is
Feature activation-0.025
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
archive
Token archive
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
[
Token [
Feature activation+0.013
Top resid features:
8
Token8
Feature activation-0.076
Top resid features:
].
Token].
Feature activation+0.184
Top resid features:
In
Token In
Feature activation-0.114
Top resid features:
this
Token this
Feature activation-0.075
Top resid features:
article
Token article
Feature activation+3.582
Top resid features:
,
Token,
Feature activation+0.149
Top resid features:
based
Token based
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
talk
Token talk
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.06

Head 2: 0.08

Head 3: 0.06

Head 4: 0.03

Head 5: 0.10

Head 6: 0.06

Head 7: 0.04

Head 8: 0.06

Head 9: 0.36

Head 10: 0.08

Head 11: 0.03

Positive logits

cyclopedia1.35

quoted1.34

headlined1.30

Column1.25

edited1.24

titled1.19

Paste1.18

summarizes1.16

editor1.15

icter1.14

ython1.14

Blog1.13

synd1.13

Blog1.12

itself1.12

journal1.10

articles1.10

odox1.10

1.09

circulated1.09

Negative logits

awoken-1.33

icent-1.24

neighbours-1.21

scl-1.13

wings-1.11

draining-1.10

ahime-1.09

joice-1.07

wagen-1.05

amaru-1.04

Darkness-1.04

Distance-1.04

esi-1.03

EEG-1.03

demons-1.03

onga-1.02

Rite-1.02

gren-1.02

neighbors-1.01

reckoning-0.99

INTERVAL 3.019 - 3.355
CONTAINS 0.000%

Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
a
Token a
Feature activation+0.000
separate
Token separate
Feature activation+0.000
article
Token article
Feature activation+0.023
released
Token released
Feature activation+3.294
on
Token on
Feature activation+0.078
Thursday
Token Thursday
Feature activation+0.067
,
Token,
Feature activation+0.000
Del
Token Del
Feature activation+0.000
ors
Tokenors
Feature activation+0.000

INTERVAL 2.684 - 3.019
CONTAINS 0.000%

INTERVAL 2.348 - 2.684
CONTAINS 0.001%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.114
was
Token was
Feature activation+2.358
originally
Token originally
Feature activation+1.904
written
Token written
Feature activation+1.618
for
Token for
Feature activation+0.134
Science
Token Science
Feature activation+0.000
of
Token of
Feature activation+0.000
you
Token you
Feature activation+0.000
!
Token!
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
article
Tokenarticle
Feature activation+0.364
by
Token by
Feature activation+2.528
Af
Token Af
Feature activation+0.617
ro
Tokenro
Feature activation+0.000
dit
Tokendit
Feature activation+0.000
i
Tokeni
Feature activation+0.000
K
Token K
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
where
Token where
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
article
Token article
Feature activation+0.471
does
Token does
Feature activation+2.578
it
Token it
Feature activation+1.041
acknowledge
Token acknowledge
Feature activation+0.978
that
Token that
Feature activation+0.000
an
Token an
Feature activation+0.000
egregious
Token egregious
Feature activation+0.000
because
Token because
Feature activation+0.000
you
Token you
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.000
was
Token was
Feature activation+2.386
originally
Token originally
Feature activation+1.916
published
Token published
Feature activation+1.230
on
Token on
Feature activation+0.000
August
Token August
Feature activation+0.000
21
Token 21
Feature activation+0.000
.
Token.
Feature activation+0.000
From
Token From
Feature activation+0.000
the
Token the
Feature activation+0.000
same
Token same
Feature activation+0.000
article
Token article
Feature activation+0.068
last
Token last
Feature activation+2.450
year
Token year
Feature activation+2.273
,
Token,
Feature activation+0.598
written
Token written
Feature activation+0.635
before
Token before
Feature activation+0.000
NYPD
Token NYPD
Feature activation+0.000

INTERVAL 2.013 - 2.348
CONTAINS 0.002%

8
Token8
Feature activation+0.000
].
Token].
Feature activation+0.000
In
Token In
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.229
,
Token,
Feature activation+2.033
based
Token based
Feature activation+1.818
on
Token on
Feature activation+0.719
a
Token a
Feature activation+0.244
talk
Token talk
Feature activation+0.098
given
Token given
Feature activation+0.000
Egyptian
Token Egyptian
Feature activation+0.000
Constitution
Token Constitution
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
article
Token article
Feature activation+0.457
calls
Token calls
Feature activation+2.232
for
Token for
Feature activation+0.472
prison
Token prison
Feature activation+0.090
sentences
Token sentences
Feature activation+0.000
and
Token and
Feature activation+0.000
fines
Token fines
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
,
Token,
Feature activation+2.346
I
Token I
Feature activation+1.468
will
Token will
Feature activation+1.032
explain
Token explain
Feature activation+0.704
Goal
Token Goal
Feature activation+0.000
and
Token and
Feature activation+0.000
Ed
TokenEd
Feature activation+0.000
note
Token note
Feature activation+0.000
:
Token:
Feature activation+0.000
This
Token This
Feature activation+0.000
article
Token article
Feature activation+0.000
was
Token was
Feature activation+2.121
updated
Token updated
Feature activation+1.495
on
Token on
Feature activation+0.000
March
Token March
Feature activation+0.000
2
Token 2
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
To
Token To
Feature activation+0.000
render
Token render
Feature activation+0.000
an
Token an
Feature activation+0.000
article
Token article
Feature activation+0.128
containing
Token containing
Feature activation+2.146
both
Token both
Feature activation+0.286
R
Token R
Feature activation+0.000
plots
Token plots
Feature activation+0.000
and
Token and
Feature activation+0.000
diagrams
Token diagrams
Feature activation+0.000

INTERVAL 1.677 - 2.013
CONTAINS 0.003%

in
Token in
Feature activation+0.000
India
Token India
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
article
Token article
Feature activation+0.048
was
Token was
Feature activation+1.960
hailed
Token hailed
Feature activation+1.252
as
Token as
Feature activation+0.000
reaff
Token reaff
Feature activation+0.149
irmation
Tokenirmation
Feature activation+0.000
of
Token of
Feature activation+0.000
chosen
Token chosen
Feature activation+0.000
to
Token to
Feature activation+0.000
focus
Token focus
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
on
Token on
Feature activation+1.700
trans
Token trans
Feature activation+0.526
women
Token women
Feature activation+0.000
only
Token only
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
,
Token,
Feature activation+0.000
but
Token but
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.018
I
Token I
Feature activation+1.766
'll
Token'll
Feature activation+1.710
just
Token just
Feature activation+0.469
show
Token show
Feature activation+0.566
some
Token some
Feature activation+0.065
of
Token of
Feature activation+0.000
om
Tokenom
Feature activation+0.000
ials
Tokenials
Feature activation+0.000
in
Token in
Feature activation+0.000
an
Token an
Feature activation+0.000
article
Token article
Feature activation+0.175
that
Token that
Feature activation+1.759
appeared
Token appeared
Feature activation+1.057
in
Token in
Feature activation+0.188
1980
Token 1980
Feature activation+0.128
.[
Token.[
Feature activation+0.000
4
Token4
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Newsweek
Token Newsweek
Feature activation+0.000
article
Token article
Feature activation+0.862
published
Token published
Feature activation+1.795
in
Token in
Feature activation+0.658
February
Token February
Feature activation+0.587
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000

INTERVAL 1.342 - 1.677
CONTAINS 0.004%

Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
,
Token,
Feature activation+2.346
I
Token I
Feature activation+1.468
will
Token will
Feature activation+1.032
explain
Token explain
Feature activation+0.704
Goal
Token Goal
Feature activation+0.000
and
Token and
Feature activation+0.000
Sales
Token Sales
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
article
Token article
Feature activation+0.114
was
Token was
Feature activation+2.358
originally
Token originally
Feature activation+1.904
written
Token written
Feature activation+1.618
for
Token for
Feature activation+0.134
Science
Token Science
Feature activation+0.000
of
Token of
Feature activation+0.000
Relations
Token Relations
Feature activation+0.000
hips
Tokenhips
Feature activation+0.000
issue
Token issue
Feature activation+0.000
has
Token has
Feature activation+0.000
a
Token a
Feature activation+0.000
great
Token great
Feature activation+0.000
article
Token article
Feature activation+0.000
,
Token,
Feature activation+1.535
"
Token "
Feature activation+0.075
At
TokenAt
Feature activation+0.000
the
Token the
Feature activation+0.000
Front
Token Front
Feature activation+0.000
",
Token",
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.221
will
Token will
Feature activation+2.147
show
Token show
Feature activation+1.657
you
Token you
Feature activation+0.469
how
Token how
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
,
Token,
Feature activation+0.000
you
Token you
Feature activation+0.000
'll
Token'll
Feature activation+0.000
find
Token find
Feature activation+0.000
articles
Token articles
Feature activation+0.047
that
Token that
Feature activation+1.353
are
Token are
Feature activation+1.330
lists
Token lists
Feature activation+0.215
of
Token of
Feature activation+0.000
things
Token things
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 1.006 - 1.342
CONTAINS 0.006%

the
Token the
Feature activation+0.000
most
Token most
Feature activation+0.000
popular
Token popular
Feature activation+0.000
articles
Token articles
Feature activation+0.057
in
Token in
Feature activation+0.559
recent
Token recent
Feature activation+1.011
months
Token months
Feature activation+0.000
is
Token is
Feature activation+0.000
a
Token a
Feature activation+0.000
list
Token list
Feature activation+0.000
.
Token.
Feature activation+0.000
a
Token a
Feature activation+0.000
law
Token law
Feature activation+0.000
review
Token review
Feature activation+0.000
article
Token article
Feature activation+0.000
around
Token around
Feature activation+0.661
that
Token that
Feature activation+1.071
time
Token time
Feature activation+0.880
.
Token.
Feature activation+0.000
That
Token That
Feature activation+0.000
translated
Token translated
Feature activation+0.000
into
Token into
Feature activation+0.000
look
Tokenlook
Feature activation+0.000
ed
Tokened
Feature activation+0.000
article
Token article
Feature activation+0.000
is
Token is
Feature activation+1.974
well
Token well
Feature activation+1.243
constructed
Token constructed
Feature activation+1.128
and
Token and
Feature activation+0.000
provides
Token provides
Feature activation+0.000
detail
Token detail
Feature activation+0.000
on
Token on
Feature activation+0.000
why
Token why
Feature activation+0.000
you
Token you
Feature activation+0.000
think
Token think
Feature activation+0.000
about
Token about
Feature activation+0.000
this
Token this
Feature activation+0.000
article
Token article
Feature activation+0.000
.
Token.
Feature activation+1.016
Submit
Token Submit
Feature activation+0.649
a
Token a
Feature activation+0.000
letter
Token letter
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
for
Token for
Feature activation+0.000
this
Token this
Feature activation+0.000
final
Token final
Feature activation+0.000
article
Token article
Feature activation+0.000
,
Token,
Feature activation+1.764
I
Token I
Feature activation+1.157
'd
Token'd
Feature activation+0.326
like
Token like
Feature activation+0.000
to
Token to
Feature activation+0.090
try
Token try
Feature activation+0.000
to
Token to
Feature activation+0.000

INTERVAL 0.671 - 1.006
CONTAINS 0.009%

racist
Token racist
Feature activation+0.000
American
Token American
Feature activation+0.000
Renaissance
Token Renaissance
Feature activation+0.000
article
Token article
Feature activation+0.000
to
Token to
Feature activation+1.536
his
Token his
Feature activation+0.695
website
Token website
Feature activation+0.336
before
Token before
Feature activation+0.000
Dave
Token Dave
Feature activation+0.000
Ag
Token Ag
Feature activation+0.000
ema
Tokenema
Feature activation+0.000
in
Token in
Feature activation+0.000
newspapers
Token newspapers
Feature activation+0.000
and
Token and
Feature activation+0.000
articles
Token articles
Feature activation+0.000
doesn
Token doesn
Feature activation+0.669
't
Token't
Feature activation+0.938
harm
Token harm
Feature activation+0.000
standard
Token standard
Feature activation+0.000
Arabic
Token Arabic
Feature activation+0.000
and
Token and
Feature activation+0.000
that
Token that
Feature activation+0.000
write
Token write
Feature activation+0.000
an
Token an
Feature activation+0.000
entire
Token entire
Feature activation+0.000
article
Token article
Feature activation+0.261
on
Token on
Feature activation+0.681
the
Token the
Feature activation+0.888
promise
Token promise
Feature activation+0.225
and
Token and
Feature activation+0.000
peril
Token peril
Feature activation+0.000
of
Token of
Feature activation+0.000
OK
Token OK
Feature activation+0.000
New
TokenNew
Feature activation+0.000
sp
Tokensp
Feature activation+0.000
aper
Tokenaper
Feature activation+0.000
articles
Token articles
Feature activation+0.000
from
Token from
Feature activation+0.237
the
Token the
Feature activation+0.867
period
Token period
Feature activation+0.333
reported
Token reported
Feature activation+0.000
strange
Token strange
Feature activation+0.000
rituals
Token rituals
Feature activation+0.000
including
Token including
Feature activation+0.000
relevant
Token relevant
Feature activation+0.000
to
Token to
Feature activation+0.000
an
Token an
Feature activation+0.000
article
Token article
Feature activation+0.159
about
Token about
Feature activation+0.678
the
Token the
Feature activation+0.862
future
Token future
Feature activation+0.352
of
Token of
Feature activation+0.000
EVE
Token EVE
Feature activation+0.000
Online
Token Online
Feature activation+0.000
?
Token?
Feature activation+0.000

INTERVAL 0.335 - 0.671
CONTAINS 0.012%

of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
article
Token article
Feature activation+0.004
and
Token and
Feature activation+1.647
the
Token the
Feature activation+0.873
possible
Token possible
Feature activation+0.592
match
Token match
Feature activation+0.000
with
Token with
Feature activation+0.000
copied
Token copied
Feature activation+0.000
text
Token text
Feature activation+0.000
highlighted
Token highlighted
Feature activation+0.000
criticized
Token criticized
Feature activation+0.000
the
Token the
Feature activation+0.000
draft
Token draft
Feature activation+0.000
's
Token's
Feature activation+0.000
Article
Token Article
Feature activation+0.000
12
Token 12
Feature activation+0.472
,
Token,
Feature activation+1.034
which
Token which
Feature activation+1.065
specifically
Token specifically
Feature activation+0.418
addresses
Token addresses
Feature activation+0.274
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
A
TokenA
Feature activation+0.000
Newsweek
Token Newsweek
Feature activation+0.000
article
Token article
Feature activation+0.862
published
Token published
Feature activation+1.795
in
Token in
Feature activation+0.658
February
Token February
Feature activation+0.587
of
Token of
Feature activation+0.000
this
Token this
Feature activation+0.000
year
Token year
Feature activation+0.000
outlined
Token outlined
Feature activation+0.000
appiness
Tokenappiness
Feature activation+0.000
over
Token over
Feature activation+0.000
some
Token some
Feature activation+0.000
articles
Token articles
Feature activation+0.000
by
Token by
Feature activation+0.880
Mr
Token Mr
Feature activation+0.369
.
Token.
Feature activation+0.000
Nord
Token Nord
Feature activation+0.000
land
Tokenland
Feature activation+0.000
from
Token from
Feature activation+0.000
November
Token November
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
piece
Token piece
Feature activation+0.000
was
Token was
Feature activation+0.468
originally
Token originally
Feature activation+0.213
published
Token published
Feature activation+0.173
in
Token in
Feature activation+0.000
2017
Token 2017
Feature activation+0.000
.
Token.
Feature activation+0.000

INTERVAL 0.000 - 0.335
CONTAINS 99.965%

ridiculed
Token ridiculed
Feature activation+0.000
by
Token by
Feature activation+0.000
the
Token the
Feature activation+0.000
tech
Token tech
Feature activation+0.000
industry
Token industry
Feature activation+0.000
for
Token for
Feature activation+0.000
not
Token not
Feature activation+0.000
understanding
Token understanding
Feature activation+0.000
the
Token the
Feature activation+0.000
technologies
Token technologies
Feature activation+0.000
she
Token she
Feature activation+0.000
that
Token that
Feature activation+0.000
Bart
Token Bart
Feature activation+0.000
lett
Tokenlett
Feature activation+0.000
had
Token had
Feature activation+0.000
helped
Token helped
Feature activation+0.000
create
Token create
Feature activation+0.000
the
Token the
Feature activation+0.000
pear
Token pear
Feature activation+0.000
variety
Token variety
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Executive
Token Executive
Feature activation+0.000
Branch
Token Branch
Feature activation+0.000
and
Token and
Feature activation+0.000
place
Token place
Feature activation+0.000
this
Token this
Feature activation+0.000
information
Token information
Feature activation+0.000
on
Token on
Feature activation+0.000
its
Token its
Feature activation+0.000
website
Token website
Feature activation+0.000
only
Token only
Feature activation+0.000
received
Token received
Feature activation+0.000
his
Token his
Feature activation+0.000
first
Token first
Feature activation+0.000
booking
Token booking
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
third
Token third
Feature activation+0.000
minute
Token minute
Feature activation+0.000
of
Token of
Feature activation+0.000
injury
Token injury
Feature activation+0.000
interpreted
Token interpreted
Feature activation+0.000
as
Token as
Feature activation+0.000
running
Token running
Feature activation+0.000
(
Token (
Feature activation+0.000
mostly
Tokenmostly
Feature activation+0.000
)
Token)
Feature activation+0.000
from
Token from
Feature activation+0.000
money
Token money
Feature activation+0.000
to
Token to
Feature activation+0.000
output
Token output
Feature activation+0.000
and
Token and
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000

Top feature 9 in H2.9: (feature 11880)

TOP ACTIVATIONS
MAX = 3.054

have
Token have
Feature activation+0.000
you
Token you
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
video
Token video
Feature activation+0.862
will
Token will
Feature activation+3.054
start
Token start
Feature activation+2.942
in
Token in
Feature activation+1.247
8
Token 8
Feature activation+0.329
Cancel
Token Cancel
Feature activation+1.127
Ċ
TokenĊ
Feature activation+0.000
you
Token you
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
video
Token video
Feature activation+0.862
will
Token will
Feature activation+3.054
start
Token start
Feature activation+2.942
in
Token in
Feature activation+1.247
8
Token 8
Feature activation+0.329
Cancel
Token Cancel
Feature activation+1.127
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
That
TokenThat
Feature activation+0.000
's
Token's
Feature activation+0.000
how
Token how
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.717
begins
Token begins
Feature activation+2.825
on
Token on
Feature activation+1.325
Time
Token Time
Feature activation+0.550
Magazine
Token Magazine
Feature activation+0.000
's
Token's
Feature activation+0.000
website
Token website
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
video
Token video
Feature activation+0.092
is
Token is
Feature activation+2.399
from
Token from
Feature activation+1.740
MSNBC
Token MSNBC
Feature activation+0.592
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+0.000
racist
Token racist
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
video
Token video
Feature activation+0.468
shows
Token shows
Feature activation+2.371
Weinstein
Token Weinstein
Feature activation+1.288
attempting
Token attempting
Feature activation+0.399
to
Token to
Feature activation+0.059
respond
Token respond
Feature activation+0.171
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.495
,
Token,
Feature activation+2.286
F
Token F
Feature activation+1.253
oval
Tokenoval
Feature activation+0.463
is
Token is
Feature activation+0.000
heard
Token heard
Feature activation+0.033
saying
Token saying
Feature activation+0.154
can
Token can
Feature activation+0.000
watch
Token watch
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.519
that
Token that
Feature activation+1.934
shows
Token shows
Feature activation+2.262
a
Token a
Feature activation+0.626
docking
Token docking
Feature activation+0.581
here
Token here
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
about
Token about
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
video
Token video
Feature activation+0.534
was
Token was
Feature activation+2.261
getting
Token getting
Feature activation+1.728
thousands
Token thousands
Feature activation+0.154
of
Token of
Feature activation+0.000
views
Token views
Feature activation+0.006
a
Token a
Feature activation+0.000
rolling
Token rolling
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
video
Token video
Feature activation+0.212
introducing
Token introducing
Feature activation+2.177
people
Token people
Feature activation+0.786
to
Token to
Feature activation+0.000
somebody
Token somebody
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Vancouver
Token Vancouver
Feature activation+0.000
location
Token location
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
video
Token video
Feature activation+0.595
was
Token was
Feature activation+2.125
captured
Token captured
Feature activation+1.818
and
Token and
Feature activation+0.697
later
Token later
Feature activation+0.622
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.279
as
Token as
Feature activation+2.097
part
Token part
Feature activation+2.080
of
Token of
Feature activation+0.088
the
Token the
Feature activation+0.230
National
Token National
Feature activation+0.000
Labor
Token Labor
Feature activation+0.000
speeds
Token speeds
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.523
above
Token above
Feature activation+2.095
,
Token,
Feature activation+1.179
the
Token the
Feature activation+1.106
team
Token team
Feature activation+0.402
at
Token at
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
can
Token can
Feature activation+0.000
understand
Token understand
Feature activation+0.000
why
Token why
Feature activation+0.000
this
Token this
Feature activation+0.000
video
Token video
Feature activation+0.080
was
Token was
Feature activation+2.093
so
Token so
Feature activation+0.929
popular
Token popular
Feature activation+0.765
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
turn
Token turn
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.279
as
Token as
Feature activation+2.097
part
Token part
Feature activation+2.080
of
Token of
Feature activation+0.088
the
Token the
Feature activation+0.230
National
Token National
Feature activation+0.000
Labor
Token Labor
Feature activation+0.000
Relations
Token Relations
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
video
Token video
Feature activation+0.320
,
Token,
Feature activation+1.992
published
Token published
Feature activation+2.076
by
Token by
Feature activation+0.349
Buzz
Token Buzz
Feature activation+0.000
feed
Tokenfeed
Feature activation+0.000
News
Token News
Feature activation+0.000
as
Token as
Feature activation+0.000
2005
Token 2005
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.422
,
Token,
Feature activation+2.062
Trump
Token Trump
Feature activation+0.764
can
Token can
Feature activation+0.018
be
Token be
Feature activation+0.000
heard
Token heard
Feature activation+0.000
making
Token making
Feature activation+0.000
December
Token December
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
shocking
Token shocking
Feature activation+0.000
video
Token video
Feature activation+0.000
emerged
Token emerged
Feature activation+2.046
of
Token of
Feature activation+0.034
Syrian
Token Syrian
Feature activation+0.483
rebels
Token rebels
Feature activation+0.228
testing
Token testing
Feature activation+0.000
what
Token what
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
This
Token This
Feature activation+0.000
video
Token video
Feature activation+0.042
demonstrates
Token demonstrates
Feature activation+2.026
mathematical
Token mathematical
Feature activation+0.197
proof
Token proof
Feature activation+0.000
that
Token that
Feature activation+0.000
absence
Token absence
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
video
Token video
Feature activation+0.320
,
Token,
Feature activation+1.992
published
Token published
Feature activation+2.076
by
Token by
Feature activation+0.349
Buzz
Token Buzz
Feature activation+0.000
feed
Tokenfeed
Feature activation+0.000
News
Token News
Feature activation+0.000
In
TokenIn
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.192
promoting
Token promoting
Feature activation+1.958
a
Token a
Feature activation+1.227
book
Token book
Feature activation+0.133
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.000
active
Token active
Feature activation+0.000

Top DFA by src position
MAX = 3.271

How
TokenHow
Feature activation-0.004
Top resid features:
have
Token have
Feature activation+0.009
Top resid features:
you
Token you
Feature activation+0.018
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.134
Top resid features:
The
TokenThe
Feature activation-0.038
Top resid features:
video
Token video
Feature activation+3.271
Top resid features:
will
Token will
Feature activation+0.020
Top resid features:
start
Token start
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
Cancel
Token Cancel
Feature activation+0.000
Top resid features:
How
TokenHow
Feature activation+0.045
Top resid features:
have
Token have
Feature activation+0.026
Top resid features:
you
Token you
Feature activation+0.005
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.103
Top resid features:
The
TokenThe
Feature activation-0.019
Top resid features:
video
Token video
Feature activation+3.114
Top resid features:
will
Token will
Feature activation+0.027
Top resid features:
start
Token start
Feature activation-0.053
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
8
Token 8
Feature activation+0.000
Top resid features:
Cancel
Token Cancel
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.026
Top resid features:
That
TokenThat
Feature activation-0.049
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
how
Token how
Feature activation+0.062
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
video
Token video
Feature activation+3.186
Top resid features:
begins
Token begins
Feature activation-0.105
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
Time
Token Time
Feature activation+0.000
Top resid features:
Magazine
Token Magazine
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.000
Top resid features:
concluded
Token concluded
Feature activation+0.019
Top resid features:
.
Token.
Feature activation-0.014
Top resid features:
Ċ
TokenĊ
Feature activation-0.057
Top resid features:
Ċ
TokenĊ
Feature activation-0.083
Top resid features:
This
TokenThis
Feature activation-0.091
Top resid features:
video
Token video
Feature activation+2.729
Top resid features:
is
Token is
Feature activation-0.022
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
MSNBC
Token MSNBC
Feature activation+0.000
Top resid features:
âĢ
TokenâĢ
Feature activation+0.000
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
remarks
Token remarks
Feature activation+0.041
Top resid features:
as
Token as
Feature activation-0.039
Top resid features:
racist
Token racist
Feature activation-0.006
Top resid features:
.
Token.
Feature activation-0.086
Top resid features:
A
Token A
Feature activation-0.056
Top resid features:
video
Token video
Feature activation+2.650
Top resid features:
shows
Token shows
Feature activation-0.009
Top resid features:
Weinstein
Token Weinstein
Feature activation+0.000
Top resid features:
attempting
Token attempting
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
respond
Token respond
Feature activation+0.000
Top resid features:
Ŀ
TokenĿ
Feature activation-0.042
Top resid features:
Ċ
TokenĊ
Feature activation-0.051
Top resid features:
Ċ
TokenĊ
Feature activation-0.074
Top resid features:
In
TokenIn
Feature activation+0.034
Top resid features:
the
Token the
Feature activation+0.088
Top resid features:
video
Token video
Feature activation+2.744
Top resid features:
,
Token,
Feature activation-0.048
Top resid features:
F
Token F
Feature activation+0.000
Top resid features:
oval
Tokenoval
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
heard
Token heard
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.002
Top resid features:
You
TokenYou
Feature activation-0.037
Top resid features:
can
Token can
Feature activation+0.057
Top resid features:
watch
Token watch
Feature activation+0.059
Top resid features:
a
Token a
Feature activation+0.005
Top resid features:
video
Token video
Feature activation+2.549
Top resid features:
that
Token that
Feature activation-0.197
Top resid features:
shows
Token shows
Feature activation-0.018
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
docking
Token docking
Feature activation+0.000
Top resid features:
here
Token here
Feature activation+0.000
Top resid features:
something
Token something
Feature activation+0.010
Top resid features:
about
Token about
Feature activation+0.043
Top resid features:
this
Token this
Feature activation+0.007
Top resid features:
.
Token.
Feature activation-0.095
Top resid features:
The
Token The
Feature activation-0.108
Top resid features:
video
Token video
Feature activation+2.451
Top resid features:
was
Token was
Feature activation-0.007
Top resid features:
getting
Token getting
Feature activation+0.000
Top resid features:
thousands
Token thousands
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
views
Token views
Feature activation+0.000
Top resid features:
are
Token are
Feature activation-0.016
Top resid features:
rolling
Token rolling
Feature activation-0.056
Top resid features:
out
Token out
Feature activation-0.030
Top resid features:
a
Token a
Feature activation+0.002
Top resid features:
new
Token new
Feature activation-0.067
Top resid features:
video
Token video
Feature activation+2.556
Top resid features:
introducing
Token introducing
Feature activation-0.056
Top resid features:
people
Token people
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
somebody
Token somebody
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
downtown
Token downtown
Feature activation-0.010
Top resid features:
Vancouver
Token Vancouver
Feature activation-0.000
Top resid features:
location
Token location
Feature activation-0.020
Top resid features:
.
Token.
Feature activation-0.075
Top resid features:
The
Token The
Feature activation-0.105
Top resid features:
video
Token video
Feature activation+2.422
Top resid features:
was
Token was
Feature activation+0.020
Top resid features:
captured
Token captured
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
later
Token later
Feature activation+0.000
Top resid features:
re
Token re
Feature activation+0.000
Top resid features:
compelled
Token compelled
Feature activation-0.028
Top resid features:
to
Token to
Feature activation-0.018
Top resid features:
turn
Token turn
Feature activation-0.101
Top resid features:
over
Token over
Feature activation-0.051
Top resid features:
the
Token the
Feature activation-0.117
Top resid features:
video
Token video
Feature activation+2.785
Top resid features:
as
Token as
Feature activation-0.095
Top resid features:
part
Token part
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
National
Token National
Feature activation+0.000
Top resid features:
high
Token high
Feature activation+0.002
Top resid features:
speeds
Token speeds
Feature activation+0.012
Top resid features:
.
Token.
Feature activation-0.031
Top resid features:
In
Token In
Feature activation-0.073
Top resid features:
the
Token the
Feature activation+0.040
Top resid features:
video
Token video
Feature activation+2.419
Top resid features:
above
Token above
Feature activation-0.017
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
team
Token team
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
One
Token One
Feature activation-0.091
Top resid features:
can
Token can
Feature activation+0.042
Top resid features:
understand
Token understand
Feature activation+0.046
Top resid features:
why
Token why
Feature activation-0.124
Top resid features:
this
Token this
Feature activation-0.049
Top resid features:
video
Token video
Feature activation+2.448
Top resid features:
was
Token was
Feature activation+0.001
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
popular
Token popular
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
compelled
Token compelled
Feature activation-0.014
Top resid features:
to
Token to
Feature activation-0.024
Top resid features:
turn
Token turn
Feature activation-0.102
Top resid features:
over
Token over
Feature activation-0.038
Top resid features:
the
Token the
Feature activation-0.052
Top resid features:
video
Token video
Feature activation+2.681
Top resid features:
as
Token as
Feature activation-0.078
Top resid features:
part
Token part
Feature activation-0.030
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
National
Token National
Feature activation+0.000
Top resid features:
salute
Token salute
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.049
Top resid features:
Ċ
TokenĊ
Feature activation-0.065
Top resid features:
The
TokenThe
Feature activation-0.013
Top resid features:
video
Token video
Feature activation+2.596
Top resid features:
,
Token,
Feature activation-0.158
Top resid features:
published
Token published
Feature activation-0.120
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Buzz
Token Buzz
Feature activation+0.000
Top resid features:
feed
Tokenfeed
Feature activation+0.000
Top resid features:
from
Token from
Feature activation-0.017
Top resid features:
2005
Token 2005
Feature activation-0.054
Top resid features:
.
Token.
Feature activation-0.048
Top resid features:
In
Token In
Feature activation-0.049
Top resid features:
the
Token the
Feature activation+0.025
Top resid features:
video
Token video
Feature activation+2.227
Top resid features:
,
Token,
Feature activation-0.049
Top resid features:
Trump
Token Trump
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
heard
Token heard
Feature activation+0.000
Top resid features:
In
TokenIn
Feature activation-0.044
Top resid features:
December
Token December
Feature activation-0.020
Top resid features:
,
Token,
Feature activation-0.007
Top resid features:
a
Token a
Feature activation+0.024
Top resid features:
shocking
Token shocking
Feature activation-0.115
Top resid features:
video
Token video
Feature activation+2.591
Top resid features:
emerged
Token emerged
Feature activation-0.140
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Syrian
Token Syrian
Feature activation+0.000
Top resid features:
rebels
Token rebels
Feature activation+0.000
Top resid features:
testing
Token testing
Feature activation+0.000
Top resid features:
H
Token H
Feature activation-0.013
Top resid features:
.
Token.
Feature activation-0.032
Top resid features:
âĢ
TokenâĢ
Feature activation-0.013
Top resid features:
Ŀ
TokenĿ
Feature activation-0.028
Top resid features:
This
Token This
Feature activation-0.183
Top resid features:
video
Token video
Feature activation+2.603
Top resid features:
demonstrates
Token demonstrates
Feature activation-0.088
Top resid features:
mathematical
Token mathematical
Feature activation+0.000
Top resid features:
proof
Token proof
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
absence
Token absence
Feature activation+0.000
Top resid features:
salute
Token salute
Feature activation-0.021
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.063
Top resid features:
Ċ
TokenĊ
Feature activation-0.096
Top resid features:
The
TokenThe
Feature activation-0.028
Top resid features:
video
Token video
Feature activation+2.406
Top resid features:
,
Token,
Feature activation-0.101
Top resid features:
published
Token published
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
Buzz
Token Buzz
Feature activation+0.000
Top resid features:
feed
Tokenfeed
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.041
Top resid features:
In
TokenIn
Feature activation-0.027
Top resid features:
June
Token June
Feature activation-0.047
Top resid features:
,
Token,
Feature activation-0.004
Top resid features:
a
Token a
Feature activation-0.008
Top resid features:
video
Token video
Feature activation+2.372
Top resid features:
promoting
Token promoting
Feature activation-0.132
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
book
Token book
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.05

Head 2: 0.06

Head 3: 0.05

Head 4: 0.04

Head 5: 0.09

Head 6: 0.05

Head 7: 0.05

Head 8: 0.05

Head 9: 0.35

Head 10: 0.09

Head 11: 0.03

Positive logits

Videos1.39

videos1.36

Whats1.36

WhatsApp1.34

Youtube1.32

guiActiveUn1.32

outube1.31

1.28

Palin1.28

Snapchat1.27

umbnails1.26

circulated1.26

YouTube1.26

upload1.25

YouTube1.25

Instagram1.24

ideos1.23

Hannity1.23

GoPro1.22

clips1.22

Negative logits

ahime-2.03

reckoning-1.31

heit-1.29

Chosen-1.23

Ending-1.23

ieri-1.21

quartered-1.20

soType-1.19

urion-1.18

_>-1.18

chance-1.17

imi-1.16

cipled-1.15

nexus-1.14

joice-1.13

appointed-1.11

uneasy-1.11

comprom-1.10

withdrawn-1.10

Pact-1.10

INTERVAL 2.749 - 3.054
CONTAINS 0.000%

That
TokenThat
Feature activation+0.000
's
Token's
Feature activation+0.000
how
Token how
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.717
begins
Token begins
Feature activation+2.825
on
Token on
Feature activation+1.325
Time
Token Time
Feature activation+0.550
Magazine
Token Magazine
Feature activation+0.000
's
Token's
Feature activation+0.000
website
Token website
Feature activation+0.000
have
Token have
Feature activation+0.000
you
Token you
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
video
Token video
Feature activation+0.862
will
Token will
Feature activation+3.054
start
Token start
Feature activation+2.942
in
Token in
Feature activation+1.247
8
Token 8
Feature activation+0.329
Cancel
Token Cancel
Feature activation+1.127
Ċ
TokenĊ
Feature activation+0.000
you
Token you
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
The
TokenThe
Feature activation+0.000
video
Token video
Feature activation+0.862
will
Token will
Feature activation+3.054
start
Token start
Feature activation+2.942
in
Token in
Feature activation+1.247
8
Token 8
Feature activation+0.329
Cancel
Token Cancel
Feature activation+1.127
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 2.443 - 2.749
CONTAINS 0.000%

INTERVAL 2.138 - 2.443
CONTAINS 0.001%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.495
,
Token,
Feature activation+2.286
F
Token F
Feature activation+1.253
oval
Tokenoval
Feature activation+0.463
is
Token is
Feature activation+0.000
heard
Token heard
Feature activation+0.033
saying
Token saying
Feature activation+0.154
rolling
Token rolling
Feature activation+0.000
out
Token out
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
video
Token video
Feature activation+0.212
introducing
Token introducing
Feature activation+2.177
people
Token people
Feature activation+0.786
to
Token to
Feature activation+0.000
somebody
Token somebody
Feature activation+0.000
that
Token that
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
can
Token can
Feature activation+0.000
watch
Token watch
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.519
that
Token that
Feature activation+1.934
shows
Token shows
Feature activation+2.262
a
Token a
Feature activation+0.626
docking
Token docking
Feature activation+0.581
here
Token here
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
video
Token video
Feature activation+0.092
is
Token is
Feature activation+2.399
from
Token from
Feature activation+1.740
MSNBC
Token MSNBC
Feature activation+0.592
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
as
Token as
Feature activation+0.000
racist
Token racist
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
video
Token video
Feature activation+0.468
shows
Token shows
Feature activation+2.371
Weinstein
Token Weinstein
Feature activation+1.288
attempting
Token attempting
Feature activation+0.399
to
Token to
Feature activation+0.059
respond
Token respond
Feature activation+0.171
to
Token to
Feature activation+0.000

INTERVAL 1.832 - 2.138
CONTAINS 0.002%

You
TokenYou
Feature activation+0.000
can
Token can
Feature activation+0.000
watch
Token watch
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.519
that
Token that
Feature activation+1.934
shows
Token shows
Feature activation+2.262
a
Token a
Feature activation+0.626
docking
Token docking
Feature activation+0.581
here
Token here
Feature activation+0.000
.)
Token.)
Feature activation+0.000
Warning
TokenWarning
Feature activation+0.000
:
Token:
Feature activation+0.000
the
Token the
Feature activation+0.000
following
Token following
Feature activation+0.000
video
Token video
Feature activation+0.316
contains
Token contains
Feature activation+1.956
graphic
Token graphic
Feature activation+0.764
content
Token content
Feature activation+0.617
of
Token of
Feature activation+0.303
a
Token a
Feature activation+0.691
violent
Token violent
Feature activation+0.280
Vancouver
Token Vancouver
Feature activation+0.000
location
Token location
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
video
Token video
Feature activation+0.595
was
Token was
Feature activation+2.125
captured
Token captured
Feature activation+1.818
and
Token and
Feature activation+0.697
later
Token later
Feature activation+0.622
re
Token re
Feature activation+0.000
-
Token-
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
video
Token video
Feature activation+0.320
,
Token,
Feature activation+1.992
published
Token published
Feature activation+2.076
by
Token by
Feature activation+0.349
Buzz
Token Buzz
Feature activation+0.000
feed
Tokenfeed
Feature activation+0.000
News
Token News
Feature activation+0.000
to
Token to
Feature activation+0.000
turn
Token turn
Feature activation+0.000
over
Token over
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.279
as
Token as
Feature activation+2.097
part
Token part
Feature activation+2.080
of
Token of
Feature activation+0.088
the
Token the
Feature activation+0.230
National
Token National
Feature activation+0.000
Labor
Token Labor
Feature activation+0.000

INTERVAL 1.527 - 1.832
CONTAINS 0.003%

in
Token in
Feature activation+0.000
action
Token action
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.300
below
Token below
Feature activation+1.568
:
Token:
Feature activation+0.215
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
*
Token*
Feature activation+0.000
This
Token This
Feature activation+0.000
this
Token this
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
video
Token video
Feature activation+0.534
was
Token was
Feature activation+2.261
getting
Token getting
Feature activation+1.728
thousands
Token thousands
Feature activation+0.154
of
Token of
Feature activation+0.000
views
Token views
Feature activation+0.006
a
Token a
Feature activation+0.000
day
Token day
Feature activation+0.000
the
Token the
Feature activation+0.000
fore
Token fore
Feature activation+0.000
thought
Tokenthought
Feature activation+0.000
to
Token to
Feature activation+0.000
video
Token video
Feature activation+0.000
the
Token the
Feature activation+1.758
rat
Token rat
Feature activation+1.595
climbing
Token climbing
Feature activation+0.549
on
Token on
Feature activation+0.000
student
Token student
Feature activation+0.000
desks
Token desks
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
video
Token video
Feature activation+0.065
documents
Token documents
Feature activation+1.669
nearly
Token nearly
Feature activation+0.667
everything
Token everything
Feature activation+0.808
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Crow
Token Crow
Feature activation+0.000
ot
Tokenot
Feature activation+0.000
says
Token says
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.122
posted
Token posted
Feature activation+1.702
on
Token on
Feature activation+0.568
Per
Token Per
Feature activation+0.446
ot
Tokenot
Feature activation+0.000
Ch
TokenCh
Feature activation+0.000
arts
Tokenarts
Feature activation+0.000

INTERVAL 1.222 - 1.527
CONTAINS 0.005%

is
Token is
Feature activation+0.000
Youtube
Token Youtube
Feature activation+0.000
video
Token video
Feature activation+0.143
of
Token of
Feature activation+0.000
the
Token the
Feature activation+1.142
main
Token main
Feature activation+1.470
part
Token part
Feature activation+1.212
of
Token of
Feature activation+0.141
the
Token the
Feature activation+0.000
confrontation
Token confrontation
Feature activation+0.000
.
Token.
Feature activation+0.000
June
Token June
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.192
promoting
Token promoting
Feature activation+1.958
a
Token a
Feature activation+1.227
book
Token book
Feature activation+0.133
by
Token by
Feature activation+0.000
an
Token an
Feature activation+0.000
active
Token active
Feature activation+0.000
-
Token-
Feature activation+0.000
with
Token with
Feature activation+0.000
11
Token 11
Feature activation+0.000
hours
Token hours
Feature activation+0.000
of
Token of
Feature activation+0.000
video
Token video
Feature activation+0.461
statements
Token statements
Feature activation+1.231
and
Token and
Feature activation+0.283
more
Token more
Feature activation+0.865
than
Token than
Feature activation+0.242
180
Token 180
Feature activation+0.264
exhibits
Token exhibits
Feature activation+0.157
,
Token,
Feature activation+0.000
had
Token had
Feature activation+0.000
posted
Token posted
Feature activation+0.000
a
Token a
Feature activation+0.000
video
Token video
Feature activation+0.488
with
Token with
Feature activation+1.361
her
Token her
Feature activation+1.155
Indian
Token Indian
Feature activation+0.246
-
Token-
Feature activation+0.000
origin
Tokenorigin
Feature activation+0.000
Swedish
Token Swedish
Feature activation+0.000
racist
Token racist
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
video
Token video
Feature activation+0.468
shows
Token shows
Feature activation+2.371
Weinstein
Token Weinstein
Feature activation+1.288
attempting
Token attempting
Feature activation+0.399
to
Token to
Feature activation+0.059
respond
Token respond
Feature activation+0.171
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000

INTERVAL 0.916 - 1.222
CONTAINS 0.008%

already
Token already
Feature activation+0.000
released
Token released
Feature activation+0.000
videos
Token videos
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.882
show
Token show
Feature activation+1.043
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
This
TokenThis
Feature activation+0.000
is
Token is
Feature activation+0.000
said
Token said
Feature activation+0.000
in
Token in
Feature activation+0.000
her
Token her
Feature activation+0.000
announcement
Token announcement
Feature activation+0.000
video
Token video
Feature activation+0.024
.
Token.
Feature activation+1.060
"
Token "
Feature activation+0.000
Because
TokenBecause
Feature activation+0.000
when
Token when
Feature activation+0.031
families
Token families
Feature activation+0.000
are
Token are
Feature activation+0.000
ness
Tokenness
Feature activation+0.000
sprites
Token sprites
Feature activation+0.000
where
Token where
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.431
processor
Token processor
Feature activation+1.122
does
Token does
Feature activation+0.379
all
Token all
Feature activation+0.212
the
Token the
Feature activation+0.282
work
Token work
Feature activation+0.000
.
Token.
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.523
above
Token above
Feature activation+2.095
,
Token,
Feature activation+1.179
the
Token the
Feature activation+1.106
team
Token team
Feature activation+0.402
at
Token at
Feature activation+0.000
Civil
Token Civil
Feature activation+0.000
Maps
Token Maps
Feature activation+0.000
a
Token a
Feature activation+0.000
link
Token link
Feature activation+0.000
to
Token to
Feature activation+0.000
her
Token her
Feature activation+0.000
video
Token video
Feature activation+0.262
,
Token,
Feature activation+1.158
writing
Token writing
Feature activation+0.889
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
What
TokenWhat
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.611 - 0.916
CONTAINS 0.013%

-
Token-
Feature activation+0.000
shot
Tokenshot
Feature activation+0.000
video
Token video
Feature activation+0.183
is
Token is
Feature activation+1.325
the
Token the
Feature activation+1.321
latest
Token latest
Feature activation+0.854
in
Token in
Feature activation+0.513
a
Token a
Feature activation+0.492
parade
Token parade
Feature activation+0.057
of
Token of
Feature activation+0.000
PR
Token PR
Feature activation+0.000
ed
Tokened
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.000
were
Token were
Feature activation+1.075
unimaginable
Token unimaginable
Feature activation+0.621
.
Token.
Feature activation+0.000
Though
Token Though
Feature activation+0.000
the
Token the
Feature activation+0.000
comments
Token comments
Feature activation+0.000
have
Token have
Feature activation+0.000
came
Token came
Feature activation+0.364
along
Token along
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.001
videos
Token videos
Feature activation+0.088
were
Token were
Feature activation+0.845
passed
Token passed
Feature activation+0.805
around
Token around
Feature activation+0.380
through
Token through
Feature activation+0.229
download
Token download
Feature activation+0.000
links
Token links
Feature activation+0.000
on
Token on
Feature activation+0.000
The
Token The
Feature activation+0.000
video
Token video
Feature activation+0.501
has
Token has
Feature activation+1.845
been
Token been
Feature activation+1.957
widely
Token widely
Feature activation+1.256
condemned
Token condemned
Feature activation+0.735
by
Token by
Feature activation+0.000
Secretary
Token Secretary
Feature activation+0.000
of
Token of
Feature activation+0.000
State
Token State
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Video
TokenVideo
Feature activation+0.017
Loading
Token Loading
Feature activation+0.000
Video
Token Video
Feature activation+0.279
Un
Token Un
Feature activation+1.256
available
Tokenavailable
Feature activation+0.884
Click
Token Click
Feature activation+0.318
to
Token to
Feature activation+0.000
play
Token play
Feature activation+0.153
Tap
Token Tap
Feature activation+0.333
to
Token to
Feature activation+0.000

INTERVAL 0.305 - 0.611
CONTAINS 0.028%

Click
TokenClick
Feature activation+0.000
through
Token through
Feature activation+0.000
the
Token the
Feature activation+0.000
slideshow
Token slideshow
Feature activation+0.000
to
Token to
Feature activation+0.070
see
Token see
Feature activation+0.405
the
Token the
Feature activation+0.000
full
Token full
Feature activation+0.000
season
Token season
Feature activation+0.000
22
Token 22
Feature activation+0.000
lineup
Token lineup
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
From
TokenFrom
Feature activation+0.000
Video
Token Video
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.493
Ċ
TokenĊ
Feature activation+0.354
The
TokenThe
Feature activation+0.293
running
Token running
Feature activation+0.027
play
Token play
Feature activation+0.000
above
Token above
Feature activation+0.000
has
Token has
Feature activation+0.000
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
video
Token video
Feature activation+0.000
over
Token over
Feature activation+1.260
the
Token the
Feature activation+1.031
course
Token course
Feature activation+0.378
of
Token of
Feature activation+0.000
creating
Token creating
Feature activation+0.000
a
Token a
Feature activation+0.000
story
Token story
Feature activation+0.000
board
Tokenboard
Feature activation+0.000
publicly
Token publicly
Feature activation+0.000
available
Token available
Feature activation+0.000
aerial
Token aerial
Feature activation+0.000
photos
Token photos
Feature activation+0.000
and
Token and
Feature activation+0.000
video
Token video
Feature activation+0.334
.
Token.
Feature activation+0.831
If
Token If
Feature activation+0.055
a
Token a
Feature activation+0.000
shark
Token shark
Feature activation+0.000
is
Token is
Feature activation+0.000
Pa
Token Pa
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
transformed
Token transformed
Feature activation+0.000
video
Token video
Feature activation+0.000
into
Token into
Feature activation+1.027
a
Token a
Feature activation+0.532
medium
Token medium
Feature activation+0.000
for
Token for
Feature activation+0.000
art
Token art
Feature activation+0.000
âĢĶ
TokenâĢĶ
Feature activation+0.000
man
Tokenman
Feature activation+0.000

INTERVAL 0.000 - 0.305
CONTAINS 99.940%

up
Token up
Feature activation+0.000
all
Token all
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
money
Token money
Feature activation+0.000
owed
Token owed
Feature activation+0.000
by
Token by
Feature activation+0.000
all
Token all
Feature activation+0.000
levels
Token levels
Feature activation+0.000
of
Token of
Feature activation+0.000
government
Token government
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
product
Token product
Feature activation+0.000
...
Token ...
Feature activation+0.000
we
Token we
Feature activation+0.000
believe
Token believe
Feature activation+0.000
our
Token our
Feature activation+0.000
device
Token device
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
eject
Token eject
Feature activation+0.000
.
Token.
Feature activation+0.000
Earlier
Token Earlier
Feature activation+0.000
that
Token that
Feature activation+0.000
day
Token day
Feature activation+0.000
another
Token another
Feature activation+0.000
Su
Token Su
Feature activation+0.000
-
Token-
Feature activation+0.000
25
Token25
Feature activation+0.000
was
Token was
Feature activation+0.000
hit
Token hit
Feature activation+0.000
's
Token's
Feature activation+0.000
friend
Token friend
Feature activation+0.000
who
Token who
Feature activation+0.000
offered
Token offered
Feature activation+0.000
the
Token the
Feature activation+0.000
huge
Token huge
Feature activation+0.000
sum
Token sum
Feature activation+0.000
to
Token to
Feature activation+0.000
his
Token his
Feature activation+0.000
affiliate
Token affiliate
Feature activation+0.000
in
Token in
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
m
Tokenm
Feature activation+0.000
currently
Token currently
Feature activation+0.000
lim
Token lim
Feature activation+0.000
ping
Tokenping
Feature activation+0.000
along
Token along
Feature activation+0.000
in
Token in
Feature activation+0.000

BOTTOM ACTIVATIONS
MIN = 0.000

atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
Development
Token Development
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
&
Token &
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
Feature activation+0.000
Research
Token Research
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
rik
Tokenrik
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
said
Token said
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
A
Token A
Feature activation+0.000
atre
Tokenatre
Feature activation+0.000
,
Token,
Feature activation+0.000
a
Token a
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
K
TokenK
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
defence
Token defence
Feature activation+0.000
ministry
Token ministry
Feature activation+0.000
committee
Token committee
Feature activation+0.000
headed
Token headed
Feature activation+0.000
by
Token by
Feature activation+0.000
V
Token V
Feature activation+0.000
.
Token.
Feature activation+0.000