H1.4 top features

Top feature 0 in H1.4: (feature 8703)

TOP ACTIVATIONS
MAX = 1.167

,
Token,
Feature activation+0.379
sneakers
Token sneakers
Feature activation+0.125
,
Token,
Feature activation+0.709
velvet
Token velvet
Feature activation+0.575
clothes
Token clothes
Feature activation+0.900
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820
clothes
Token clothes
Feature activation+0.900
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820
.
Token.
Feature activation+0.813
The
Token The
Feature activation+0.615
girls
Token girls
Feature activation+0.366
from
Token from
Feature activation+0.605
/
Token/
Feature activation+0.783
cl
Token cl
Feature activation+0.378
ippers
Tokenippers
Feature activation+0.148
,
Token,
Feature activation+0.802
brush
Token brush
Feature activation+0.143
,
Token,
Feature activation+0.921
etc
Token etc
Feature activation+0.401
.
Token.
Feature activation+0.571
You
Token You
Feature activation+0.226
need
Token need
Feature activation+0.000
to
Token to
Feature activation+0.131
glasses
Token glasses
Feature activation+0.000
,
Token,
Feature activation+0.379
sneakers
Token sneakers
Feature activation+0.125
,
Token,
Feature activation+0.709
velvet
Token velvet
Feature activation+0.575
clothes
Token clothes
Feature activation+0.900
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
rom
Tokenrom
Feature activation+0.271
bones
Tokenbones
Feature activation+0.385
,
Token,
Feature activation+0.814
French
Token French
Feature activation+0.471
horns
Token horns
Feature activation+0.342
,
Token,
Feature activation+0.854
s
Token s
Feature activation+0.573
ous
Tokenous
Feature activation+0.637
aph
Tokenaph
Feature activation+0.518
ones
Tokenones
Feature activation+0.560
,
Token,
Feature activation+0.725
d
Token d
Feature activation+0.209
yes
Tokenyes
Feature activation+0.092
,
Token,
Feature activation+0.296
acrylic
Token acrylic
Feature activation+0.165
yarn
Token yarn
Feature activation+0.400
,
Token,
Feature activation+0.847
and
Token and
Feature activation+0.684
machines
Token machines
Feature activation+0.315
were
Token were
Feature activation+0.475
being
Token being
Feature activation+0.343
used
Token used
Feature activation+0.153
,
Token,
Feature activation+0.701
white
Token white
Feature activation+0.277
pick
Token pick
Feature activation+0.373
et
Tokenet
Feature activation+0.488
fences
Token fences
Feature activation+0.489
and
Token and
Feature activation+0.842
expans
Token expans
Feature activation+0.440
es
Tokenes
Feature activation+0.491
of
Token of
Feature activation+0.680
bright
Token bright
Feature activation+0.198
green
Token green
Feature activation+0.197
dental
Token dental
Feature activation+0.000
clinic
Token clinic
Feature activation+0.000
,
Token,
Feature activation+0.333
hair
Token hair
Feature activation+0.086
salon
Token salon
Feature activation+0.089
,
Token,
Feature activation+0.835
and
Token and
Feature activation+0.646
hook
Token hook
Feature activation+0.187
ah
Tokenah
Feature activation+0.342
cafe
Token cafe
Feature activation+0.231
.
Token.
Feature activation+0.516
robe
Token robe
Feature activation+0.000
with
Token with
Feature activation+0.385
bag
Token bag
Feature activation+0.007
gy
Tokengy
Feature activation+0.519
sleeves
Token sleeves
Feature activation+0.000
,
Token,
Feature activation+0.820
and
Token and
Feature activation+0.678
a
Token a
Feature activation+0.453
hijab
Token hijab
Feature activation+0.252
,
Token,
Feature activation+0.525
or
Token or
Feature activation+0.455
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820
.
Token.
Feature activation+0.813
The
Token The
Feature activation+0.615
girls
Token girls
Feature activation+0.366
from
Token from
Feature activation+0.605
Friends
Token Friends
Feature activation+0.163
ets
Tokenets
Feature activation+0.360
,
Token,
Feature activation+0.741
t
Token t
Feature activation+0.459
rom
Tokenrom
Feature activation+0.271
bones
Tokenbones
Feature activation+0.385
,
Token,
Feature activation+0.814
French
Token French
Feature activation+0.471
horns
Token horns
Feature activation+0.342
,
Token,
Feature activation+0.854
s
Token s
Feature activation+0.573
ous
Tokenous
Feature activation+0.637
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820
.
Token.
Feature activation+0.813
The
Token The
Feature activation+0.615
girls
Token girls
Feature activation+0.366
from
Token from
Feature activation+0.605
Friends
Token Friends
Feature activation+0.163
kept
Token kept
Feature activation+0.203
tank
Token tank
Feature activation+0.348
tops
Token tops
Feature activation+0.305
,
Token,
Feature activation+0.804
and
Token and
Feature activation+0.652
flip
Token flip
Feature activation+0.131
-
Token-
Feature activation+0.807
fl
Tokenfl
Feature activation+0.465
ops
Tokenops
Feature activation+0.537
to
Token to
Feature activation+0.618
the
Token the
Feature activation+0.337
Holy
Token Holy
Feature activation+0.190
fluoride
Token fluoride
Feature activation+0.353
,
Token,
Feature activation+0.578
iron
Token iron
Feature activation+0.276
,
Token,
Feature activation+0.691
salt
Token salt
Feature activation+0.329
and
Token and
Feature activation+0.806
vitamins
Token vitamins
Feature activation+0.536
A
Token A
Feature activation+0.491
and
Token and
Feature activation+0.577
D
Token D
Feature activation+0.277
,
Token,
Feature activation+0.328
beach
Token beach
Feature activation+0.000
shorts
Token shorts
Feature activation+0.000
,
Token,
Feature activation+0.463
tank
Token tank
Feature activation+0.348
tops
Token tops
Feature activation+0.305
,
Token,
Feature activation+0.804
and
Token and
Feature activation+0.652
flip
Token flip
Feature activation+0.131
-
Token-
Feature activation+0.807
fl
Tokenfl
Feature activation+0.465
ops
Tokenops
Feature activation+0.537
,
Token,
Feature activation+0.536
scissors
Token scissors
Feature activation+0.246
/
Token/
Feature activation+0.783
cl
Token cl
Feature activation+0.378
ippers
Tokenippers
Feature activation+0.148
,
Token,
Feature activation+0.802
brush
Token brush
Feature activation+0.143
,
Token,
Feature activation+0.921
etc
Token etc
Feature activation+0.401
.
Token.
Feature activation+0.571
You
Token You
Feature activation+0.226
for
Token for
Feature activation+0.604
poker
Token poker
Feature activation+0.087
,
Token,
Feature activation+0.633
black
Token black
Feature activation+0.444
jack
Tokenjack
Feature activation+0.431
and
Token and
Feature activation+0.799
other
Token other
Feature activation+0.448
games
Token games
Feature activation+0.223
where
Token where
Feature activation+0.414
owners
Token owners
Feature activation+0.000
could
Token could
Feature activation+0.069
,
Token,
Feature activation+0.684
condition
Token condition
Feature activation+0.249
er
Tokener
Feature activation+0.261
,
Token,
Feature activation+0.536
scissors
Token scissors
Feature activation+0.246
/
Token/
Feature activation+0.783
cl
Token cl
Feature activation+0.378
ippers
Tokenippers
Feature activation+0.148
,
Token,
Feature activation+0.802
brush
Token brush
Feature activation+0.143
,
Token,
Feature activation+0.921
,
Token,
Feature activation+0.680
lithium
Token lithium
Feature activation+0.504
strips
Token strips
Feature activation+0.531
from
Token from
Feature activation+0.710
batteries
Token batteries
Feature activation+0.378
and
Token and
Feature activation+0.782
numerous
Token numerous
Feature activation+0.582
hyp
Token hyp
Feature activation+0.439
od
Tokenod
Feature activation+0.289
erm
Tokenerm
Feature activation+0.116
ic
Tokenic
Feature activation+0.181
as
Token as
Feature activation+0.454
well
Token well
Feature activation+0.143
as
Token as
Feature activation+0.380
yellow
Token yellow
Feature activation+0.156
skin
Token skin
Feature activation+0.149
and
Token and
Feature activation+0.777
eyes
Token eyes
Feature activation+0.112
,
Token,
Feature activation+0.727
and
Token and
Feature activation+0.715
anyone
Token anyone
Feature activation+0.284
experiencing
Token experiencing
Feature activation+0.000

Top DFA by src position
MAX = 0.528

's
Token's
Feature activation+0.009
Top resid features:
glasses
Token glasses
Feature activation+0.256
Top resid features:
,
Token,
Feature activation+0.102
Top resid features:
sneakers
Token sneakers
Feature activation+0.307
Top resid features:
,
Token,
Feature activation+0.100
Top resid features:
velvet
Token velvet
Feature activation+0.442
Top resid features:
clothes
Token clothes
Feature activation+0.389
Top resid features:
and
Token and
Feature activation+0.038
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Yankees
Token Yankees
Feature activation+0.000
Top resid features:
sheets
Token sheets
Feature activation+0.000
Top resid features:
velvet
Token velvet
Feature activation+0.256
Top resid features:
clothes
Token clothes
Feature activation+0.225
Top resid features:
and
Token and
Feature activation+0.028
Top resid features:
the
Token the
Feature activation-0.030
Top resid features:
Yankees
Token Yankees
Feature activation+0.111
Top resid features:
sheets
Token sheets
Feature activation+0.436
Top resid features:
and
Token and
Feature activation+0.035
Top resid features:
blankets
Token blankets
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:
girls
Token girls
Feature activation+0.000
Top resid features:
scissors
Token scissors
Feature activation+0.303
Top resid features:
/
Token/
Feature activation+0.035
Top resid features:
cl
Token cl
Feature activation+0.084
Top resid features:
ippers
Tokenippers
Feature activation+0.129
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
brush
Token brush
Feature activation+0.418
Top resid features:
,
Token,
Feature activation+0.051
Top resid features:
etc
Token etc
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
You
Token You
Feature activation+0.000
Top resid features:
need
Token need
Feature activation+0.000
Top resid features:
's
Token's
Feature activation+0.015
Top resid features:
glasses
Token glasses
Feature activation+0.214
Top resid features:
,
Token,
Feature activation+0.082
Top resid features:
sneakers
Token sneakers
Feature activation+0.322
Top resid features:
,
Token,
Feature activation+0.093
Top resid features:
velvet
Token velvet
Feature activation+0.506
Top resid features:
clothes
Token clothes
Feature activation+0.286
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Yankees
Token Yankees
Feature activation+0.000
Top resid features:
sheets
Token sheets
Feature activation+0.000
Top resid features:
t
Token t
Feature activation+0.083
Top resid features:
rom
Tokenrom
Feature activation+0.040
Top resid features:
bones
Tokenbones
Feature activation+0.204
Top resid features:
,
Token,
Feature activation+0.054
Top resid features:
French
Token French
Feature activation+0.053
Top resid features:
horns
Token horns
Feature activation+0.413
Top resid features:
,
Token,
Feature activation+0.078
Top resid features:
s
Token s
Feature activation+0.000
Top resid features:
ous
Tokenous
Feature activation+0.000
Top resid features:
aph
Tokenaph
Feature activation+0.000
Top resid features:
ones
Tokenones
Feature activation+0.000
Top resid features:
cheap
Token cheap
Feature activation+0.100
Top resid features:
chemical
Token chemical
Feature activation+0.106
Top resid features:
d
Token d
Feature activation+0.043
Top resid features:
yes
Tokenyes
Feature activation+0.098
Top resid features:
,
Token,
Feature activation+0.072
Top resid features:
acrylic
Token acrylic
Feature activation+0.434
Top resid features:
yarn
Token yarn
Feature activation+0.388
Top resid features:
,
Token,
Feature activation+0.077
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
machines
Token machines
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
trees
Token trees
Feature activation+0.149
Top resid features:
,
Token,
Feature activation+0.107
Top resid features:
white
Token white
Feature activation+0.201
Top resid features:
pick
Token pick
Feature activation+0.130
Top resid features:
et
Tokenet
Feature activation+0.068
Top resid features:
fences
Token fences
Feature activation+0.280
Top resid features:
and
Token and
Feature activation+0.047
Top resid features:
expans
Token expans
Feature activation+0.000
Top resid features:
es
Tokenes
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
bright
Token bright
Feature activation+0.000
Top resid features:
restaurant
Token restaurant
Feature activation+0.051
Top resid features:
,
Token,
Feature activation+0.086
Top resid features:
dental
Token dental
Feature activation+0.181
Top resid features:
clinic
Token clinic
Feature activation+0.044
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
hair
Token hair
Feature activation+0.528
Top resid features:
salon
Token salon
Feature activation+0.168
Top resid features:
,
Token,
Feature activation+0.095
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
hook
Token hook
Feature activation+0.000
Top resid features:
ah
Tokenah
Feature activation+0.000
Top resid features:
length
Tokenlength
Feature activation+0.057
Top resid features:
robe
Token robe
Feature activation+0.252
Top resid features:
with
Token with
Feature activation+0.046
Top resid features:
bag
Token bag
Feature activation+0.276
Top resid features:
gy
Tokengy
Feature activation+0.101
Top resid features:
sleeves
Token sleeves
Feature activation+0.347
Top resid features:
,
Token,
Feature activation+0.130
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
hijab
Token hijab
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
velvet
Token velvet
Feature activation+0.183
Top resid features:
clothes
Token clothes
Feature activation+0.144
Top resid features:
and
Token and
Feature activation+0.026
Top resid features:
the
Token the
Feature activation-0.018
Top resid features:
Yankees
Token Yankees
Feature activation+0.094
Top resid features:
sheets
Token sheets
Feature activation+0.393
Top resid features:
and
Token and
Feature activation+0.044
Top resid features:
blankets
Token blankets
Feature activation+0.249
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
girls
Token girls
Feature activation+0.000
Top resid features:
trump
Token trump
Feature activation+0.137
Top resid features:
ets
Tokenets
Feature activation+0.109
Top resid features:
,
Token,
Feature activation+0.057
Top resid features:
t
Token t
Feature activation+0.134
Top resid features:
rom
Tokenrom
Feature activation+0.067
Top resid features:
bones
Tokenbones
Feature activation+0.325
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
French
Token French
Feature activation+0.000
Top resid features:
horns
Token horns
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
s
Token s
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.022
Top resid features:
the
Token the
Feature activation-0.023
Top resid features:
Yankees
Token Yankees
Feature activation+0.070
Top resid features:
sheets
Token sheets
Feature activation+0.213
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
blankets
Token blankets
Feature activation+0.272
Top resid features:
.
Token.
Feature activation+0.154
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
girls
Token girls
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.000
Top resid features:
Friends
Token Friends
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.078
Top resid features:
tank
Token tank
Feature activation+0.222
Top resid features:
tops
Token tops
Feature activation+0.139
Top resid features:
,
Token,
Feature activation+0.105
Top resid features:
and
Token and
Feature activation+0.050
Top resid features:
flip
Token flip
Feature activation+0.417
Top resid features:
-
Token-
Feature activation+0.021
Top resid features:
fl
Tokenfl
Feature activation+0.000
Top resid features:
ops
Tokenops
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
fluoride
Token fluoride
Feature activation+0.128
Top resid features:
,
Token,
Feature activation+0.066
Top resid features:
iron
Token iron
Feature activation+0.207
Top resid features:
,
Token,
Feature activation+0.074
Top resid features:
salt
Token salt
Feature activation+0.364
Top resid features:
and
Token and
Feature activation+0.054
Top resid features:
vitamins
Token vitamins
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
D
Token D
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.005
Top resid features:
wear
Token wear
Feature activation+0.159
Top resid features:
beach
Token beach
Feature activation+0.111
Top resid features:
shorts
Token shorts
Feature activation+0.241
Top resid features:
,
Token,
Feature activation+0.117
Top resid features:
tank
Token tank
Feature activation+0.375
Top resid features:
tops
Token tops
Feature activation+0.208
Top resid features:
,
Token,
Feature activation+0.129
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
flip
Token flip
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
towel
Token towel
Feature activation+0.171
Top resid features:
,
Token,
Feature activation+0.048
Top resid features:
condition
Token condition
Feature activation+0.058
Top resid features:
er
Tokener
Feature activation+0.034
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
scissors
Token scissors
Feature activation+0.397
Top resid features:
/
Token/
Feature activation+0.053
Top resid features:
cl
Token cl
Feature activation+0.115
Top resid features:
ippers
Tokenippers
Feature activation+0.169
Top resid features:
,
Token,
Feature activation+0.063
Top resid features:
brush
Token brush
Feature activation+0.000
Top resid features:
machines
Token machines
Feature activation+0.106
Top resid features:
rigged
Token rigged
Feature activation+0.141
Top resid features:
for
Token for
Feature activation-0.009
Top resid features:
poker
Token poker
Feature activation+0.187
Top resid features:
,
Token,
Feature activation+0.126
Top resid features:
black
Token black
Feature activation+0.256
Top resid features:
jack
Tokenjack
Feature activation+0.152
Top resid features:
and
Token and
Feature activation+0.055
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
games
Token games
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
towel
Token towel
Feature activation+0.309
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
condition
Token condition
Feature activation+0.066
Top resid features:
er
Tokener
Feature activation+0.046
Top resid features:
,
Token,
Feature activation+0.079
Top resid features:
scissors
Token scissors
Feature activation+0.461
Top resid features:
/
Token/
Feature activation+0.082
Top resid features:
cl
Token cl
Feature activation+0.000
Top resid features:
ippers
Tokenippers
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
brush
Token brush
Feature activation+0.000
Top resid features:
tablets
Token tablets
Feature activation+0.164
Top resid features:
,
Token,
Feature activation+0.094
Top resid features:
lithium
Token lithium
Feature activation+0.179
Top resid features:
strips
Token strips
Feature activation+0.205
Top resid features:
from
Token from
Feature activation-0.053
Top resid features:
batteries
Token batteries
Feature activation+0.326
Top resid features:
and
Token and
Feature activation+0.059
Top resid features:
numerous
Token numerous
Feature activation+0.000
Top resid features:
hyp
Token hyp
Feature activation+0.000
Top resid features:
od
Tokenod
Feature activation+0.000
Top resid features:
erm
Tokenerm
Feature activation+0.000
Top resid features:
fever
Token fever
Feature activation+0.130
Top resid features:
as
Token as
Feature activation+0.005
Top resid features:
well
Token well
Feature activation+0.026
Top resid features:
as
Token as
Feature activation+0.010
Top resid features:
yellow
Token yellow
Feature activation+0.290
Top resid features:
skin
Token skin
Feature activation+0.358
Top resid features:
and
Token and
Feature activation+0.053
Top resid features:
eyes
Token eyes
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:
anyone
Token anyone
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.13

Head 1: 0.12

Head 2: 0.11

Head 3: 0.05

Head 4: 0.16

Head 5: 0.06

Head 6: 0.05

Head 7: 0.07

Head 8: 0.05

Head 9: 0.04

Head 10: 0.07

Head 11: 0.09

Positive logits

tubes1.67

needles1.55

nests1.54

crystals1.52

humid1.50

veins1.48

zers1.48

protr1.44

sculptures1.42

cages1.41

Blend1.41

filament1.40

dye1.39

blades1.39

powd1.38

cones1.38

brush1.38

adorned1.37

envelop1.37

cream1.36

Negative logits

Accountability-1.72

eve-1.56

ndum-1.53

uthor-1.44

appoint-1.37

Disclosure-1.36

ONSORED-1.33

cipled-1.33

EMBER-1.31

Payments-1.30

QB-1.28

Responsibility-1.28

Garrison-1.28

isSpecialOrderable-1.28

displayText-1.27

Parent-1.27

Equality-1.23

Salary-1.23

ETHOD-1.23

Equity-1.23

INTERVAL 1.050 - 1.167
CONTAINS 0.000%

,
Token,
Feature activation+0.379
sneakers
Token sneakers
Feature activation+0.125
,
Token,
Feature activation+0.709
velvet
Token velvet
Feature activation+0.575
clothes
Token clothes
Feature activation+0.900
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820

INTERVAL 0.934 - 1.050
CONTAINS 0.000%

clothes
Token clothes
Feature activation+0.900
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820
.
Token.
Feature activation+0.813
The
Token The
Feature activation+0.615
girls
Token girls
Feature activation+0.366
from
Token from
Feature activation+0.605

INTERVAL 0.817 - 0.934
CONTAINS 0.001%

,
Token,
Feature activation+0.701
white
Token white
Feature activation+0.277
pick
Token pick
Feature activation+0.373
et
Tokenet
Feature activation+0.488
fences
Token fences
Feature activation+0.489
and
Token and
Feature activation+0.842
expans
Token expans
Feature activation+0.440
es
Tokenes
Feature activation+0.491
of
Token of
Feature activation+0.680
bright
Token bright
Feature activation+0.198
green
Token green
Feature activation+0.197
rom
Tokenrom
Feature activation+0.271
bones
Tokenbones
Feature activation+0.385
,
Token,
Feature activation+0.814
French
Token French
Feature activation+0.471
horns
Token horns
Feature activation+0.342
,
Token,
Feature activation+0.854
s
Token s
Feature activation+0.573
ous
Tokenous
Feature activation+0.637
aph
Tokenaph
Feature activation+0.518
ones
Tokenones
Feature activation+0.560
,
Token,
Feature activation+0.725
robe
Token robe
Feature activation+0.000
with
Token with
Feature activation+0.385
bag
Token bag
Feature activation+0.007
gy
Tokengy
Feature activation+0.519
sleeves
Token sleeves
Feature activation+0.000
,
Token,
Feature activation+0.820
and
Token and
Feature activation+0.678
a
Token a
Feature activation+0.453
hijab
Token hijab
Feature activation+0.252
,
Token,
Feature activation+0.525
or
Token or
Feature activation+0.455
dental
Token dental
Feature activation+0.000
clinic
Token clinic
Feature activation+0.000
,
Token,
Feature activation+0.333
hair
Token hair
Feature activation+0.086
salon
Token salon
Feature activation+0.089
,
Token,
Feature activation+0.835
and
Token and
Feature activation+0.646
hook
Token hook
Feature activation+0.187
ah
Tokenah
Feature activation+0.342
cafe
Token cafe
Feature activation+0.231
.
Token.
Feature activation+0.516
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820
.
Token.
Feature activation+0.813
The
Token The
Feature activation+0.615
girls
Token girls
Feature activation+0.366
from
Token from
Feature activation+0.605
Friends
Token Friends
Feature activation+0.163

INTERVAL 0.700 - 0.817
CONTAINS 0.004%

George
Token George
Feature activation+0.000
's
Token's
Feature activation+0.000
glasses
Token glasses
Feature activation+0.000
,
Token,
Feature activation+0.379
sneakers
Token sneakers
Feature activation+0.125
,
Token,
Feature activation+0.709
velvet
Token velvet
Feature activation+0.575
clothes
Token clothes
Feature activation+0.900
and
Token and
Feature activation+1.167
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
yellow
Token yellow
Feature activation+0.156
skin
Token skin
Feature activation+0.149
and
Token and
Feature activation+0.777
eyes
Token eyes
Feature activation+0.112
,
Token,
Feature activation+0.727
and
Token and
Feature activation+0.715
anyone
Token anyone
Feature activation+0.284
experiencing
Token experiencing
Feature activation+0.000
these
Token these
Feature activation+0.000
symptoms
Token symptoms
Feature activation+0.000
are
Token are
Feature activation+0.000
flags
Token flags
Feature activation+0.000
,
Token,
Feature activation+0.025
wearing
Token wearing
Feature activation+0.000
black
Token black
Feature activation+0.000
clothing
Token clothing
Feature activation+0.079
,
Token,
Feature activation+0.707
and
Token and
Feature activation+0.526
black
Token black
Feature activation+0.208
band
Token band
Feature activation+0.492
anas
Tokenanas
Feature activation+0.593
and
Token and
Feature activation+0.662
black
Token black
Feature activation+0.208
band
Token band
Feature activation+0.492
anas
Tokenanas
Feature activation+0.593
and
Token and
Feature activation+0.662
masks
Token masks
Feature activation+0.205
,
Token,
Feature activation+0.731
police
Token police
Feature activation+0.435
said
Token said
Feature activation+0.213
.
Token.
Feature activation+0.113
Members
Token Members
Feature activation+0.048
of
Token of
Feature activation+0.085
the
Token the
Feature activation+0.737
Yankees
Token Yankees
Feature activation+0.462
sheets
Token sheets
Feature activation+0.528
and
Token and
Feature activation+1.041
blankets
Token blankets
Feature activation+0.820
.
Token.
Feature activation+0.813
The
Token The
Feature activation+0.615
girls
Token girls
Feature activation+0.366
from
Token from
Feature activation+0.605
Friends
Token Friends
Feature activation+0.163
kept
Token kept
Feature activation+0.203

INTERVAL 0.584 - 0.700
CONTAINS 0.008%

garden
Token garden
Feature activation+0.000
fork
Token fork
Feature activation+0.000
,
Token,
Feature activation+0.461
a
Token a
Feature activation+0.353
knife
Token knife
Feature activation+0.148
and
Token and
Feature activation+0.624
a
Token a
Feature activation+0.458
m
Token m
Feature activation+0.308
ache
Tokenache
Feature activation+0.035
te
Tokente
Feature activation+0.230
near
Token near
Feature activation+0.167
food
Token food
Feature activation+0.298
types
Token types
Feature activation+0.370
,
Token,
Feature activation+0.618
and
Token and
Feature activation+0.545
pear
Token pear
Feature activation+0.331
/
Token/
Feature activation+0.584
orange
Tokenorange
Feature activation+0.248
trees
Token trees
Feature activation+0.395
in
Token in
Feature activation+0.629
Marion
Token Marion
Feature activation+0.267
which
Token which
Feature activation+0.417
,
Token,
Feature activation+0.417
soccer
Token soccer
Feature activation+0.173
,
Token,
Feature activation+0.523
gymn
Token gymn
Feature activation+0.136
astics
Tokenastics
Feature activation+0.000
,
Token,
Feature activation+0.694
diving
Token diving
Feature activation+0.264
,
Token,
Feature activation+0.741
equ
Token equ
Feature activation+0.318
est
Tokenest
Feature activation+0.074
rian
Tokenrian
Feature activation+0.229
clip
Token clip
Feature activation+0.000
spray
Token spray
Feature activation+0.199
can
Token can
Feature activation+0.428
shotgun
Token shotgun
Feature activation+0.462
shell
Token shell
Feature activation+0.319
(
Token (
Feature activation+0.671
0
Token0
Feature activation+0.157
AP
Token AP
Feature activation+0.032
)
Token)
Feature activation+0.224
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
[
Token[
Feature activation+0.000
,
Token,
Feature activation+0.498
ro
Token ro
Feature activation+0.174
wing
Tokenwing
Feature activation+0.159
,
Token,
Feature activation+0.571
sailing
Token sailing
Feature activation+0.199
,
Token,
Feature activation+0.604
shooting
Token shooting
Feature activation+0.261
,
Token,
Feature activation+0.596
tennis
Token tennis
Feature activation+0.331
,
Token,
Feature activation+0.701
swimming
Token swimming
Feature activation+0.290

INTERVAL 0.467 - 0.584
CONTAINS 0.018%

ange
Tokenange
Feature activation+0.364
of
Token of
Feature activation+0.459
Middle
Token Middle
Feature activation+0.380
Eastern
Token Eastern
Feature activation+0.225
herbs
Token herbs
Feature activation+0.000
and
Token and
Feature activation+0.554
spices
Token spices
Feature activation+0.149
:
Token:
Feature activation+0.508
mint
Token mint
Feature activation+0.176
,
Token,
Feature activation+0.733
sum
Token sum
Feature activation+0.393
boats
Token boats
Feature activation+0.011
,
Token,
Feature activation+0.531
golf
Token golf
Feature activation+0.247
equipment
Token equipment
Feature activation+0.336
,
Token,
Feature activation+0.714
tennis
Token tennis
Feature activation+0.478
equipment
Token equipment
Feature activation+0.422
âĢĵ
Token âĢĵ
Feature activation+0.574
you
Token you
Feature activation+0.182
name
Token name
Feature activation+0.096
it
Token it
Feature activation+0.203
consists
Token consists
Feature activation+0.000
of
Token of
Feature activation+0.000
wooden
Token wooden
Feature activation+0.000
cab
Token cab
Feature activation+0.186
ins
Tokenins
Feature activation+0.479
and
Token and
Feature activation+0.561
a
Token a
Feature activation+0.310
few
Token few
Feature activation+0.176
less
Token less
Feature activation+0.056
sturdy
Token sturdy
Feature activation+0.000
buildings
Token buildings
Feature activation+0.089
est
Tokenest
Feature activation+0.074
rian
Tokenrian
Feature activation+0.229
,
Token,
Feature activation+0.498
ro
Token ro
Feature activation+0.174
wing
Tokenwing
Feature activation+0.159
,
Token,
Feature activation+0.571
sailing
Token sailing
Feature activation+0.199
,
Token,
Feature activation+0.604
shooting
Token shooting
Feature activation+0.261
,
Token,
Feature activation+0.596
tennis
Token tennis
Feature activation+0.331
machines
Token machines
Feature activation+0.000
,
Token,
Feature activation+0.567
and
Token and
Feature activation+0.431
computing
Token computing
Feature activation+0.202
engines
Token engines
Feature activation+0.312
at
Token at
Feature activation+0.508
the
Token the
Feature activation+0.253
size
Token size
Feature activation+0.000
of
Token of
Feature activation+0.320
individual
Token individual
Feature activation+0.040
molecules
Token molecules
Feature activation+0.097

INTERVAL 0.350 - 0.467
CONTAINS 0.044%

A
Token A
Feature activation+0.000
towel
Token towel
Feature activation+0.000
is
Token is
Feature activation+0.172
deform
Token deform
Feature activation+0.017
able
Tokenable
Feature activation+0.183
;
Token;
Feature activation+0.374
a
Token a
Feature activation+0.171
mug
Token mug
Feature activation+0.146
or
Token or
Feature activation+0.370
a
Token a
Feature activation+0.348
computer
Token computer
Feature activation+0.158
and
Token and
Feature activation+0.646
hook
Token hook
Feature activation+0.187
ah
Tokenah
Feature activation+0.342
cafe
Token cafe
Feature activation+0.231
.
Token.
Feature activation+0.516
On
Token On
Feature activation+0.381
the
Token the
Feature activation+0.113
north
Token north
Feature activation+0.000
side
Token side
Feature activation+0.000
,
Token,
Feature activation+0.229
a
Token a
Feature activation+0.057
feminists
Token feminists
Feature activation+0.000
stopped
Token stopped
Feature activation+0.000
shaving
Token shaving
Feature activation+0.000
their
Token their
Feature activation+0.000
legs
Token legs
Feature activation+0.000
and
Token and
Feature activation+0.411
abandoned
Token abandoned
Feature activation+0.031
their
Token their
Feature activation+0.023
babies
Token babies
Feature activation+0.000
at
Token at
Feature activation+0.257
day
Token day
Feature activation+0.012
with
Token with
Feature activation+0.284
7
Token 7
Feature activation+0.159
herbs
Token herbs
Feature activation+0.000
&
Token &
Feature activation+0.328
spices
Token spices
Feature activation+0.000
.
Token.
Feature activation+0.393
Ċ
TokenĊ
Feature activation+0.206
Ċ
TokenĊ
Feature activation+0.117
It
TokenIt
Feature activation+0.000
's
Token's
Feature activation+0.000
not
Token not
Feature activation+0.000
Transport
Token Transport
Feature activation+0.000
bus
Token bus
Feature activation+0.042
,
Token,
Feature activation+0.238
car
Token car
Feature activation+0.223
racing
Token racing
Feature activation+0.153
,
Token,
Feature activation+0.378
a
Token a
Feature activation+0.182
writing
Token writing
Feature activation+0.000
desk
Token desk
Feature activation+0.000
[
Token [
Feature activation+0.153
which
Tokenwhich
Feature activation+0.027

INTERVAL 0.233 - 0.350
CONTAINS 0.106%

a
Token a
Feature activation+0.000
fast
Token fast
Feature activation+0.000
moving
Token moving
Feature activation+0.000
cold
Token cold
Feature activation+0.000
front
Token front
Feature activation+0.028
,
Token,
Feature activation+0.260
continues
Token continues
Feature activation+0.000
into
Token into
Feature activation+0.000
Saturday
Token Saturday
Feature activation+0.000
evening
Token evening
Feature activation+0.000
from
Token from
Feature activation+0.000
cross
Token cross
Feature activation+0.000
on
Token on
Feature activation+0.000
his
Token his
Feature activation+0.000
upper
Token upper
Feature activation+0.000
arm
Token arm
Feature activation+0.000
,
Token,
Feature activation+0.273
entered
Token entered
Feature activation+0.000
the
Token the
Feature activation+0.015
restaurant
Token restaurant
Feature activation+0.000
from
Token from
Feature activation+0.000
a
Token a
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
He
TokenHe
Feature activation+0.000
is
Token is
Feature activation+0.000
undeniably
Token undeniably
Feature activation+0.000
athletic
Token athletic
Feature activation+0.000
and
Token and
Feature activation+0.269
makes
Token makes
Feature activation+0.000
things
Token things
Feature activation+0.000
look
Token look
Feature activation+0.000
easy
Token easy
Feature activation+0.000
on
Token on
Feature activation+0.000
string
Token string
Feature activation+0.000
of
Token of
Feature activation+0.260
special
Token special
Feature activation+0.009
versions
Token versions
Feature activation+0.089
designed
Token designed
Feature activation+0.103
to
Token to
Feature activation+0.241
mark
Token mark
Feature activation+0.012
the
Token the
Feature activation+0.093
Dodge
Token Dodge
Feature activation+0.000
's
Token's
Feature activation+0.035
25
Token 25
Feature activation+0.000
.
Token.
Feature activation+0.000
(
Token (
Feature activation+0.000
Disney
TokenDisney
Feature activation+0.000
routinely
Token routinely
Feature activation+0.000
susp
Token susp
Feature activation+0.000
ends
Tokenends
Feature activation+0.246
employees
Token employees
Feature activation+0.000
while
Token while
Feature activation+0.027
investigating
Token investigating
Feature activation+0.000
such
Token such
Feature activation+0.000
cases
Token cases
Feature activation+0.000

INTERVAL 0.117 - 0.233
CONTAINS 0.278%

les
Tokenles
Feature activation+0.000
with
Token with
Feature activation+0.000
the
Token the
Feature activation+0.000
new
Token new
Feature activation+0.000
mixer
Token mixer
Feature activation+0.000
,
Token,
Feature activation+0.183
or
Token or
Feature activation+0.089
Gran
Token Gran
Feature activation+0.000
th
Tokenth
Feature activation+0.000
am
Tokenam
Feature activation+0.000
fre
Token fre
Feature activation+0.000
heat
Token heat
Feature activation+0.000
waves
Token waves
Feature activation+0.171
,
Token,
Feature activation+0.306
water
Token water
Feature activation+0.139
is
Token is
Feature activation+0.178
less
Token less
Feature activation+0.137
effective
Token effective
Feature activation+0.000
as
Token as
Feature activation+0.139
a
Token a
Feature activation+0.000
cool
Token cool
Feature activation+0.000
ant
Tokenant
Feature activation+0.000
ing
Tokening
Feature activation+0.000
the
Token the
Feature activation+0.000
plaster
Token plaster
Feature activation+0.000
and
Token and
Feature activation+0.345
hurting
Token hurting
Feature activation+0.000
his
Token his
Feature activation+0.150
head
Token head
Feature activation+0.000
.
Token.
Feature activation+0.153
He
Token He
Feature activation+0.000
lay
Token lay
Feature activation+0.000
there
Token there
Feature activation+0.000
The
TokenThe
Feature activation+0.000
wage
Token wage
Feature activation+0.000
increases
Token increases
Feature activation+0.000
would
Token would
Feature activation+0.000
pump
Token pump
Feature activation+0.000
an
Token an
Feature activation+0.153
additional
Token additional
Feature activation+0.000
$
Token $
Feature activation+0.000
22
Token22
Feature activation+0.000
billion
Token billion
Feature activation+0.000
into
Token into
Feature activation+0.000
rye
Token rye
Feature activation+0.000
,
Token,
Feature activation+0.252
is
Token is
Feature activation+0.115
also
Token also
Feature activation+0.066
sort
Token sort
Feature activation+0.004
of
Token of
Feature activation+0.122
keeping
Token keeping
Feature activation+0.000
with
Token with
Feature activation+0.000
what
Token what
Feature activation+0.000
was
Token was
Feature activation+0.000
being
Token being
Feature activation+0.000

INTERVAL 0.000 - 0.117
CONTAINS 99.542%

Mark
Token Mark
Feature activation+0.000
Mc
Token Mc
Feature activation+0.000
All
TokenAll
Feature activation+0.000
ister
Tokenister
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
John
TokenJohn
Feature activation+0.000
Tory
Token Tory
Feature activation+0.000
by
Token by
Feature activation+0.000
a
Token a
Feature activation+0.000
process
Token process
Feature activation+0.000
which
Token which
Feature activation+0.000
neither
Token neither
Feature activation+0.000
they
Token they
Feature activation+0.000
nor
Token nor
Feature activation+0.000
we
Token we
Feature activation+0.000
could
Token could
Feature activation+0.000
successfully
Token successfully
Feature activation+0.000
control
Token control
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
what
Token what
Feature activation+0.000
happened
Token happened
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Sud
Token Sud
Feature activation+0.000
et
Tokenet
Feature activation+0.000
en
Tokenen
Feature activation+0.000
land
Tokenland
Feature activation+0.000
MAP
TokenMAP
Feature activation+0.000
K
TokenK
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
m
Token m
Feature activation+0.000
C
TokenC
Feature activation+0.000
herry
Tokenherry
Feature activation+0.000
-
Token-
Feature activation+0.000
positive
Tokenpositive
Feature activation+0.000
cells
Token cells
Feature activation+0.000
underneath
Token underneath
Feature activation+0.000
low
Token low
Feature activation+0.000
including
Token including
Feature activation+0.000
holidays
Token holidays
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
hourly
Token hourly
Feature activation+0.000
breakdown
Token breakdown
Feature activation+0.000
is
Token is
Feature activation+0.000
even
Token even
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 H1.4: (feature 15916)

TOP ACTIVATIONS
MAX = 0.285

.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
to
Token to
Feature activation+0.056
learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
with
Token with
Feature activation+0.000
a
Token a
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
[
Token[
Feature activation+0.000
This
TokenThis
Feature activation+0.000
paragraph
Token paragraph
Feature activation+0.169
is
Token is
Feature activation+0.000
obsolete
Token obsolete
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
expect
Token expect
Feature activation+0.000
to
Token to
Feature activation+0.056
learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
:
Token:
Feature activation+0.000
23
Token 23
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
**
Token **
Feature activation+0.000
Numbers
TokenNumbers
Feature activation+0.106
are
Token are
Feature activation+0.080
age
Token age
Feature activation+0.000
-
Token-
Feature activation+0.000
adjusted
Tokenadjusted
Feature activation+0.000
,
Token,
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
,
Token,
Feature activation+0.000
recently
Token recently
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.102
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
coming
Token coming
Feature activation+0.000
up
Token up
Feature activation+0.000
Years
Token Years
Feature activation+0.000
Ago
Token Ago
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
Articles
Token Articles
Feature activation+0.090
:
Token:
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
SAN
TokenSAN
Feature activation+0.000
J
Token J
Feature activation+0.000
OSE
TokenOSE
Feature activation+0.000
23
Token 23
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
**
Token **
Feature activation+0.000
Numbers
TokenNumbers
Feature activation+0.106
are
Token are
Feature activation+0.080
age
Token age
Feature activation+0.000
-
Token-
Feature activation+0.000
adjusted
Tokenadjusted
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
Lists
Token Lists
Feature activation+0.044
allows
Token allows
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+0.000
books
Token books
Feature activation+0.064
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.013
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
interested
Token interested
Feature activation+0.000
can
Token can
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
expect
Token expect
Feature activation+0.000
to
Token to
Feature activation+0.056
learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Amazon
TokenAmazon
Feature activation+0.000
Wish
Token Wish
Feature activation+0.000
Lists
Token Lists
Feature activation+0.044
allows
Token allows
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+0.000
books
Token books
Feature activation+0.064
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+0.000
books
Token books
Feature activation+0.064
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.013
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
interested
Token interested
Feature activation+0.000
in
Token in
Feature activation+0.000
to
Token to
Feature activation+0.000
ify
Tokenify
Feature activation+0.000
the
Token the
Feature activation+0.000
treaty
Token treaty
Feature activation+0.000
of
Token of
Feature activation+0.000
asc
Token asc
Feature activation+0.000
ension
Tokenension
Feature activation+0.010
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
country
Token country
Feature activation+0.000
joins
Token joins
Feature activation+0.000
the
Token the
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
A
Token A
Feature activation+0.000
quick
Token quick
Feature activation+0.000
overview
Token overview
Feature activation+0.000
of
Token of
Feature activation+0.006
the
Token the
Feature activation+0.000
syll
Token syll
Feature activation+0.001
abus
Tokenabus
Feature activation+0.000
,
Token,
Feature activation+0.000
course
Token course
Feature activation+0.000
A
Token A
Feature activation+0.000
quick
Token quick
Feature activation+0.000
overview
Token overview
Feature activation+0.000
of
Token of
Feature activation+0.006
the
Token the
Feature activation+0.000
syll
Token syll
Feature activation+0.001
abus
Tokenabus
Feature activation+0.000
,
Token,
Feature activation+0.000
course
Token course
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
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
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
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

Top DFA by src position
MAX = 1.291

.
Token.
Feature activation+0.194
Top resid features:
Some
Token Some
Feature activation+0.171
Top resid features:
course
Token course
Feature activation+0.239
Top resid features:
terminology
Token terminology
Feature activation+0.459
Top resid features:
is
Token is
Feature activation+0.391
Top resid features:
covered
Token covered
Feature activation+0.632
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
with
Token with
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:
|
Token |
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.125
Top resid features:
learn
Token learn
Feature activation+0.257
Top resid features:
.
Token.
Feature activation+0.234
Top resid features:
Some
Token Some
Feature activation+0.225
Top resid features:
course
Token course
Feature activation+0.332
Top resid features:
terminology
Token terminology
Feature activation+1.097
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
covered
Token covered
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
learn
Token learn
Feature activation+0.247
Top resid features:
.
Token.
Feature activation+0.207
Top resid features:
Some
Token Some
Feature activation+0.236
Top resid features:
course
Token course
Feature activation+0.283
Top resid features:
terminology
Token terminology
Feature activation+0.476
Top resid features:
is
Token is
Feature activation+0.771
Top resid features:
covered
Token covered
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
with
Token with
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:
?
Token?
Feature activation+0.108
Top resid features:
Ċ
TokenĊ
Feature activation+0.234
Top resid features:
Ċ
TokenĊ
Feature activation+0.243
Top resid features:
[
Token[
Feature activation+0.537
Top resid features:
This
TokenThis
Feature activation+0.664
Top resid features:
paragraph
Token paragraph
Feature activation+0.979
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
obsolete
Token obsolete
Feature activation+0.000
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+0.214
Top resid features:
expect
Token expect
Feature activation+0.238
Top resid features:
to
Token to
Feature activation+0.138
Top resid features:
learn
Token learn
Feature activation+0.305
Top resid features:
.
Token.
Feature activation+0.287
Top resid features:
Some
Token Some
Feature activation+0.758
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
terminology
Token terminology
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
covered
Token covered
Feature activation+0.000
Top resid features:
along
Token along
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.033
Top resid features:
23
Token 23
Feature activation+0.234
Top resid features:
.
Token.
Feature activation+0.055
Top resid features:
1
Token1
Feature activation+0.109
Top resid features:
**
Token **
Feature activation+0.922
Top resid features:
Numbers
TokenNumbers
Feature activation+1.150
Top resid features:
are
Token are
Feature activation+0.000
Top resid features:
age
Token age
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
adjusted
Tokenadjusted
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.386
Top resid features:
So
TokenSo
Feature activation+0.292
Top resid features:
,
Token,
Feature activation+0.220
Top resid features:
recently
Token recently
Feature activation+0.177
Top resid features:
I
Token I
Feature activation+0.156
Top resid features:
âĢ
TokenâĢ
Feature activation+0.754
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
ve
Tokenve
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
coming
Token coming
Feature activation+0.000
Top resid features:
up
Token up
Feature activation+0.000
Top resid features:
20
Token 20
Feature activation+0.142
Top resid features:
Years
Token Years
Feature activation+0.136
Top resid features:
Ago
Token Ago
Feature activation+0.104
Top resid features:
Ċ
TokenĊ
Feature activation+0.215
Top resid features:
Ċ
TokenĊ
Feature activation+0.238
Top resid features:
Related
TokenRelated
Feature activation+1.281
Top resid features:
Articles
Token Articles
Feature activation+0.819
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Top resid features:
SAN
TokenSAN
Feature activation+0.000
Top resid features:
J
Token J
Feature activation+0.000
Top resid features:
:
Token:
Feature activation+0.007
Top resid features:
23
Token 23
Feature activation+0.205
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
1
Token1
Feature activation+0.087
Top resid features:
**
Token **
Feature activation+0.791
Top resid features:
Numbers
TokenNumbers
Feature activation+1.056
Top resid features:
are
Token are
Feature activation+0.877
Top resid features:
age
Token age
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
adjusted
Tokenadjusted
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Lists
Token Lists
Feature activation+0.323
Top resid features:
allows
Token allows
Feature activation+0.222
Top resid features:
you
Token you
Feature activation+0.033
Top resid features:
to
Token to
Feature activation+0.127
Top resid features:
add
Token add
Feature activation+0.392
Top resid features:
books
Token books
Feature activation+1.001
Top resid features:
you
Token you
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:
re
Tokenre
Feature activation+0.000
Top resid features:
interested
Token interested
Feature activation+0.000
Top resid features:
can
Token can
Feature activation+0.114
Top resid features:
|
Token |
Feature activation+0.239
Top resid features:
|
Token |
Feature activation+0.262
Top resid features:
|
Token |
Feature activation+0.278
Top resid features:
expect
Token expect
Feature activation+0.643
Top resid features:
to
Token to
Feature activation+0.648
Top resid features:
learn
Token learn
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Some
Token Some
Feature activation+0.000
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
terminology
Token terminology
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.213
Top resid features:
Ċ
TokenĊ
Feature activation+0.250
Top resid features:
Ċ
TokenĊ
Feature activation+0.275
Top resid features:
Amazon
TokenAmazon
Feature activation+0.365
Top resid features:
Wish
Token Wish
Feature activation+0.359
Top resid features:
Lists
Token Lists
Feature activation+0.738
Top resid features:
allows
Token allows
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
add
Token add
Feature activation+0.000
Top resid features:
books
Token books
Feature activation+0.000
Top resid features:
Some
Token Some
Feature activation+0.221
Top resid features:
course
Token course
Feature activation+0.233
Top resid features:
terminology
Token terminology
Feature activation+0.352
Top resid features:
is
Token is
Feature activation+0.256
Top resid features:
covered
Token covered
Feature activation+0.203
Top resid features:
along
Token along
Feature activation+0.496
Top resid features:
with
Token with
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:
|
Token |
Feature activation+0.000
Top resid features:
|
Token |
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.051
Top resid features:
to
Token to
Feature activation+0.103
Top resid features:
add
Token add
Feature activation+0.356
Top resid features:
books
Token books
Feature activation+0.368
Top resid features:
you
Token you
Feature activation+0.032
Top resid features:
âĢ
TokenâĢ
Feature activation+0.620
Top resid features:
Ļ
TokenĻ
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.000
Top resid features:
interested
Token interested
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
rat
Token rat
Feature activation+0.223
Top resid features:
ify
Tokenify
Feature activation+0.039
Top resid features:
the
Token the
Feature activation+0.086
Top resid features:
treaty
Token treaty
Feature activation+0.390
Top resid features:
of
Token of
Feature activation+0.204
Top resid features:
asc
Token asc
Feature activation+1.291
Top resid features:
ension
Tokenension
Feature activation+0.278
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
country
Token country
Feature activation+0.000
Top resid features:
joins
Token joins
Feature activation+0.000
Top resid features:
|
Token |
Feature activation+0.212
Top resid features:
|
Token |
Feature activation+0.226
Top resid features:
A
Token A
Feature activation+0.249
Top resid features:
quick
Token quick
Feature activation+0.185
Top resid features:
overview
Token overview
Feature activation+0.464
Top resid features:
of
Token of
Feature activation+0.656
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
syll
Token syll
Feature activation+0.000
Top resid features:
abus
Tokenabus
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
course
Token course
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.188
Top resid features:
quick
Token quick
Feature activation+0.137
Top resid features:
overview
Token overview
Feature activation+0.315
Top resid features:
of
Token of
Feature activation+0.325
Top resid features:
the
Token the
Feature activation+0.285
Top resid features:
syll
Token syll
Feature activation+0.627
Top resid features:
abus
Tokenabus
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
course
Token course
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.783
Top resid features:
rik
Tokenrik
Feature activation-0.225
Top resid features:
ar
Tokenar
Feature activation-0.053
Top resid features:
said
Token said
Feature activation+0.150
Top resid features:
Saturday
Token Saturday
Feature activation+0.078
Top resid features:
.
Token.
Feature activation+0.191
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.688
Top resid features:
rik
Tokenrik
Feature activation-0.189
Top resid features:
ar
Tokenar
Feature activation-0.051
Top resid features:
said
Token said
Feature activation+0.126
Top resid features:
Saturday
Token Saturday
Feature activation+0.123
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.575
Top resid features:
rik
Tokenrik
Feature activation-0.158
Top resid features:
ar
Tokenar
Feature activation-0.044
Top resid features:
said
Token said
Feature activation+0.098
Top resid features:
Saturday
Token Saturday
Feature activation+0.108
Top resid features:
.
Token.
Feature activation-0.009
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.12

Head 2: 0.08

Head 3: 0.06

Head 4: 0.15

Head 5: 0.07

Head 6: 0.07

Head 7: 0.10

Head 8: 0.08

Head 9: 0.05

Head 10: 0.05

Head 11: 0.08

Positive logits

apologise1.67

Chronicle1.56

chron1.52

azeera1.47

aunder1.47

rumours1.47

lette1.46

Hare1.44

transcript1.43

Spoiler1.43

surname1.42

disclaimer1.40

agher1.40

ocaust1.39

apology1.37

Zeit1.35

agna1.34

pseudonym1.34

confir1.33

ransom1.31

Negative logits

NetMessage-1.67

isolation-1.54

alin-1.44

)].-1.44

&&-1.41

nect-1.39

-1.38

FIG-1.37

Goal-1.35

Pros-1.33

oglu-1.33

Components-1.33

Compat-1.33

oving-1.32

onents-1.32

NYSE-1.32

outer-1.30

quartered-1.30

adj-1.30

coli-1.29

INTERVAL 0.257 - 0.285
CONTAINS 0.000%

.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000

INTERVAL 0.228 - 0.257
CONTAINS 0.000%

INTERVAL 0.200 - 0.228
CONTAINS 0.000%

to
Token to
Feature activation+0.056
learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000

INTERVAL 0.171 - 0.200
CONTAINS 0.000%

learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
|
Token |
Feature activation+0.000

INTERVAL 0.143 - 0.171
CONTAINS 0.000%

?
Token?
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
paragraph
Token paragraph
Feature activation+0.169
is
Token is
Feature activation+0.000
obsolete
Token obsolete
Feature activation+0.000
:]
Token:]
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.114 - 0.143
CONTAINS 0.000%

|
Token |
Feature activation+0.000
expect
Token expect
Feature activation+0.000
to
Token to
Feature activation+0.056
learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
is
Token is
Feature activation+0.173
covered
Token covered
Feature activation+0.285
along
Token along
Feature activation+0.014

INTERVAL 0.086 - 0.114
CONTAINS 0.000%

Years
Token Years
Feature activation+0.000
Ago
Token Ago
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Related
TokenRelated
Feature activation+0.000
Articles
Token Articles
Feature activation+0.090
:
Token:
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
SAN
TokenSAN
Feature activation+0.000
J
Token J
Feature activation+0.000
OSE
TokenOSE
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
So
TokenSo
Feature activation+0.000
,
Token,
Feature activation+0.000
recently
Token recently
Feature activation+0.000
I
Token I
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.102
Ļ
TokenĻ
Feature activation+0.000
ve
Tokenve
Feature activation+0.000
been
Token been
Feature activation+0.000
coming
Token coming
Feature activation+0.000
up
Token up
Feature activation+0.000
:
Token:
Feature activation+0.000
23
Token 23
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
**
Token **
Feature activation+0.000
Numbers
TokenNumbers
Feature activation+0.106
are
Token are
Feature activation+0.080
age
Token age
Feature activation+0.000
-
Token-
Feature activation+0.000
adjusted
Tokenadjusted
Feature activation+0.000
,
Token,
Feature activation+0.000

INTERVAL 0.057 - 0.086
CONTAINS 0.000%

Lists
Token Lists
Feature activation+0.044
allows
Token allows
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+0.000
books
Token books
Feature activation+0.064
you
Token you
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.013
Ļ
TokenĻ
Feature activation+0.000
re
Tokenre
Feature activation+0.000
interested
Token interested
Feature activation+0.000
23
Token 23
Feature activation+0.000
.
Token.
Feature activation+0.000
1
Token1
Feature activation+0.000
**
Token **
Feature activation+0.000
Numbers
TokenNumbers
Feature activation+0.106
are
Token are
Feature activation+0.080
age
Token age
Feature activation+0.000
-
Token-
Feature activation+0.000
adjusted
Tokenadjusted
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000

INTERVAL 0.029 - 0.057
CONTAINS 0.000%

can
Token can
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
|
Token |
Feature activation+0.000
expect
Token expect
Feature activation+0.000
to
Token to
Feature activation+0.056
learn
Token learn
Feature activation+0.000
.
Token.
Feature activation+0.000
Some
Token Some
Feature activation+0.121
course
Token course
Feature activation+0.000
terminology
Token terminology
Feature activation+0.219
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Amazon
TokenAmazon
Feature activation+0.000
Wish
Token Wish
Feature activation+0.000
Lists
Token Lists
Feature activation+0.044
allows
Token allows
Feature activation+0.000
you
Token you
Feature activation+0.000
to
Token to
Feature activation+0.000
add
Token add
Feature activation+0.000
books
Token books
Feature activation+0.064

INTERVAL 0.000 - 0.029
CONTAINS 99.999%

500
Token500
Feature activation+0.000
blood
Token blood
Feature activation+0.000
samples
Token samples
Feature activation+0.000
it
Token it
Feature activation+0.000
has
Token has
Feature activation+0.000
examined
Token examined
Feature activation+0.000
since
Token since
Feature activation+0.000
last
Token last
Feature activation+0.000
July
Token July
Feature activation+0.000
re
Token re
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
young
Token young
Feature activation+0.000
band
Token band
Feature activation+0.000
's
Token's
Feature activation+0.000
first
Token first
Feature activation+0.000
single
Token single
Feature activation+0.000
Sw
Token Sw
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
&
Token &
Feature activation+0.000
Steve
Token Steve
Feature activation+0.000
Clarke
Token Clarke
Feature activation+0.000
to
Token to
Feature activation+0.000
draw
Token draw
Feature activation+0.000
Wolves
Token Wolves
Feature activation+0.000
'
Token'
Feature activation+0.000
defence
Token defence
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
position
Token position
Feature activation+0.000
Ãĥ
TokenÃĥ
Feature activation+0.000
-
Token-
Feature activation+0.000
Pro
TokenPro
Feature activation+0.000
l
Tokenl
Feature activation+0.000
iferation
Tokeniferation
Feature activation+0.000
Treaty
Token Treaty
Feature activation+0.000
,
Token,
Feature activation+0.000
as
Token as
Feature activation+0.000
it
Token it
Feature activation+0.000
applies
Token applies
Feature activation+0.000
to
Token to
Feature activation+0.000
this
Token this
Feature activation+0.000
and
Token and
Feature activation+0.000
buy
Token buy
Feature activation+0.000
,
Token,
Feature activation+0.000
say
Token say
Feature activation+0.000
,
Token,
Feature activation+0.000
two
Token two
Feature activation+0.000
thousand
Token thousand
Feature activation+0.000
dollars
Token dollars
Feature activation+0.000
worth
Token worth
Feature activation+0.000
of
Token of
Feature activation+0.000
fireworks
Token fireworks
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 H1.4: (feature 12418)

TOP ACTIVATIONS
MAX = 1.086

Blessing
Token Blessing
Feature activation+0.287
and
Token and
Feature activation+0.450
Deborah
Token Deborah
Feature activation+0.312
Zoe
Token Zoe
Feature activation+0.513
Lau
Token Lau
Feature activation+0.906
fer
Tokenfer
Feature activation+1.086
.
Token.
Feature activation+0.791
Pulitzer
Token Pulitzer
Feature activation+0.624
winner
Token winner
Feature activation+0.653
Qu
Token Qu
Feature activation+0.533
i
Tokeni
Feature activation+0.654
,
Token,
Feature activation+0.326
Nick
Token Nick
Feature activation+0.254
and
Token and
Feature activation+0.712
Tom
Token Tom
Feature activation+0.461
Te
Token Te
Feature activation+0.557
ves
Tokenves
Feature activation+1.051
âĢĵ
Token âĢĵ
Feature activation+0.744
Ċ
TokenĊ
Feature activation+0.560
Ċ
TokenĊ
Feature activation+0.483
Family
TokenFamily
Feature activation+0.301
of
Token of
Feature activation+0.398
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000
Stan
Token Stan
Feature activation+0.210
Monte
Token Monte
Feature activation+0.384
ith
Tokenith
Feature activation+0.576
likes
Token likes
Feature activation+0.972
to
Token to
Feature activation+0.688
say
Token say
Feature activation+0.505
as
Token as
Feature activation+0.399
he
Token he
Feature activation+0.309
starts
Token starts
Feature activation+0.300
Mart
TokenMart
Feature activation+0.523
ino
Tokenino
Feature activation+0.520
,
Token,
Feature activation+0.787
Bryan
Token Bryan
Feature activation+0.570
Kon
Token Kon
Feature activation+0.515
iet
Tokeniet
Feature activation+0.963
z
Tokenz
Feature activation+0.748
ko
Tokenko
Feature activation+0.831
and
Token and
Feature activation+0.987
all
Token all
Feature activation+0.900
the
Token the
Feature activation+0.675
Warren
Token Warren
Feature activation+0.044
Elizabeth
Token Elizabeth
Feature activation+0.401
Ann
Token Ann
Feature activation+0.677
Warren
Token Warren
Feature activation+0.717
Sanders
TokenSanders
Feature activation+0.863
:
Token:
Feature activation+0.955
'
Token '
Feature activation+0.579
Damn
TokenDamn
Feature activation+0.121
right
Token right
Feature activation+0.350
'
Token'
Feature activation+0.320
I
Token I
Feature activation+0.106
murdered
Token murdered
Feature activation+0.241
Dr
Token Dr
Feature activation+0.134
.
Token.
Feature activation+0.053
John
Token John
Feature activation+0.284
Britt
Token Britt
Feature activation+0.499
on
Tokenon
Feature activation+0.932
at
Token at
Feature activation+0.854
an
Token an
Feature activation+0.651
abortion
Token abortion
Feature activation+0.444
clinic
Token clinic
Feature activation+0.396
in
Token in
Feature activation+0.373
House
Token House
Feature activation+0.422
Counsel
Token Counsel
Feature activation+0.509
Neil
Token Neil
Feature activation+0.613
Egg
Token Egg
Feature activation+0.660
l
Tokenl
Feature activation+0.829
eston
Tokeneston
Feature activation+0.931
.
Token.
Feature activation+0.593
Ċ
TokenĊ
Feature activation+0.323
Ċ
TokenĊ
Feature activation+0.256
But
TokenBut
Feature activation+0.122
Republicans
Token Republicans
Feature activation+0.000
aren
Tokenaren
Feature activation+0.563
/
Token /
Feature activation+0.478
AP
Token AP
Feature activation+0.427
Dwight
Token Dwight
Feature activation+0.251
Chandler
Token Chandler
Feature activation+0.425
walks
Token walks
Feature activation+0.928
through
Token through
Feature activation+0.836
his
Token his
Feature activation+0.549
flood
Token flood
Feature activation+0.532
-
Token-
Feature activation+0.488
dam
Tokendam
Feature activation+0.267
Dou
Token Dou
Feature activation+0.488
glass
Tokenglass
Feature activation+0.487
and
Token and
Feature activation+0.552
Dean
Token Dean
Feature activation+0.601
Musk
Token Musk
Feature activation+0.586
ett
Tokenett
Feature activation+0.927
.
Token.
Feature activation+0.689
Ċ
TokenĊ
Feature activation+0.365
Ċ
TokenĊ
Feature activation+0.308
In
TokenIn
Feature activation+0.245
his
Token his
Feature activation+0.178
Lee
Token Lee
Feature activation+0.000
Blessing
Token Blessing
Feature activation+0.287
and
Token and
Feature activation+0.450
Deborah
Token Deborah
Feature activation+0.312
Zoe
Token Zoe
Feature activation+0.513
Lau
Token Lau
Feature activation+0.906
fer
Tokenfer
Feature activation+1.086
.
Token.
Feature activation+0.791
Pulitzer
Token Pulitzer
Feature activation+0.624
winner
Token winner
Feature activation+0.653
Qu
Token Qu
Feature activation+0.533
Dennis
Token Dennis
Feature activation+0.000
and
Token and
Feature activation+0.467
Julia
Token Julia
Feature activation+0.268
Karl
Token Karl
Feature activation+0.691
sson
Tokensson
Feature activation+0.650
.
Token.
Feature activation+0.882
Ċ
TokenĊ
Feature activation+0.461
Ċ
TokenĊ
Feature activation+0.372
Track
TokenTrack
Feature activation+0.220
5
Token 5
Feature activation+0.327
features
Token features
Feature activation+0.187
and
Token and
Feature activation+0.426
Amanda
Token Amanda
Feature activation+0.307
Joyce
Token Joyce
Feature activation+0.598
Hale
Token Hale
Feature activation+0.719
,
Token,
Feature activation+0.790
28
Token 28
Feature activation+0.880
,
Token,
Feature activation+0.579
were
Token were
Feature activation+0.689
all
Token all
Feature activation+0.409
taken
Token taken
Feature activation+0.359
into
Token into
Feature activation+0.274
Rog
Token Rog
Feature activation+0.154
gio
Tokengio
Feature activation+0.327
and
Token and
Feature activation+0.545
Thomas
Token Thomas
Feature activation+0.444
Jos
Token Jos
Feature activation+0.553
ce
Tokence
Feature activation+0.874
lyn
Tokenlyn
Feature activation+0.862
,
Token,
Feature activation+0.706
who
Token who
Feature activation+0.689
received
Token received
Feature activation+0.514
an
Token an
Feature activation+0.381
Jim
Token Jim
Feature activation+0.026
Clark
Token Clark
Feature activation+0.064
,
Token,
Feature activation+0.493
Jack
Token Jack
Feature activation+0.314
Br
Token Br
Feature activation+0.611
ab
Tokenab
Feature activation+0.867
ham
Tokenham
Feature activation+0.698
,
Token,
Feature activation+0.568
Jo
Token Jo
Feature activation+0.440
S
Token S
Feature activation+0.501
iff
Tokeniff
Feature activation+0.599
McDonald
Token McDonald
Feature activation+0.387
,
Token,
Feature activation+0.455
Eric
Token Eric
Feature activation+0.356
Horn
Token Horn
Feature activation+0.564
ick
Tokenick
Feature activation+0.775
,
Token,
Feature activation+0.863
and
Token and
Feature activation+0.752
Peter
Token Peter
Feature activation+0.555
R
Token R
Feature activation+0.727
utt
Tokenutt
Feature activation+0.781
ga
Tokenga
Feature activation+0.634
Elizabeth
Token Elizabeth
Feature activation+0.000
Warren
Token Warren
Feature activation+0.044
Elizabeth
Token Elizabeth
Feature activation+0.401
Ann
Token Ann
Feature activation+0.677
Warren
Token Warren
Feature activation+0.717
Sanders
TokenSanders
Feature activation+0.863
:
Token:
Feature activation+0.955
'
Token '
Feature activation+0.579
Damn
TokenDamn
Feature activation+0.121
right
Token right
Feature activation+0.350
'
Token'
Feature activation+0.320
gio
Tokengio
Feature activation+0.327
and
Token and
Feature activation+0.545
Thomas
Token Thomas
Feature activation+0.444
Jos
Token Jos
Feature activation+0.553
ce
Tokence
Feature activation+0.874
lyn
Tokenlyn
Feature activation+0.862
,
Token,
Feature activation+0.706
who
Token who
Feature activation+0.689
received
Token received
Feature activation+0.514
an
Token an
Feature activation+0.381
exclusive
Token exclusive
Feature activation+0.406
Dr
Token Dr
Feature activation+0.134
.
Token.
Feature activation+0.053
John
Token John
Feature activation+0.284
Britt
Token Britt
Feature activation+0.499
on
Tokenon
Feature activation+0.932
at
Token at
Feature activation+0.854
an
Token an
Feature activation+0.651
abortion
Token abortion
Feature activation+0.444
clinic
Token clinic
Feature activation+0.396
in
Token in
Feature activation+0.373
Florida
Token Florida
Feature activation+0.164
quite
Token quite
Feature activation+0.000
matter
Token matter
Feature activation+0.000
.
Token.
Feature activation+0.000
David
Token David
Feature activation+0.023
Roberts
Token Roberts
Feature activation+0.288
cast
Token cast
Feature activation+0.849
it
Token it
Feature activation+0.448
color
Token color
Feature activation+0.229
fully
Tokenfully
Feature activation+0.361
in
Token in
Feature activation+0.273
his
Token his
Feature activation+0.222
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Richard
TokenRichard
Feature activation+0.089
William
Token William
Feature activation+0.304
Whe
Token Whe
Feature activation+0.671
aton
Tokenaton
Feature activation+0.848
III
Token III
Feature activation+0.542
(
Token (
Feature activation+0.742
born
Tokenborn
Feature activation+0.646
29
Token 29
Feature activation+0.523
July
Token July
Feature activation+0.406

Top DFA by src position
MAX = 0.777

Ludwig
Token Ludwig
Feature activation+0.113
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
Lee
Token Lee
Feature activation+0.171
Top resid features:
Blessing
Token Blessing
Feature activation+0.141
Top resid features:
and
Token and
Feature activation+0.042
Top resid features:
Deborah
Token Deborah
Feature activation+0.517
Top resid features:
Zoe
Token Zoe
Feature activation+0.350
Top resid features:
Lau
Token Lau
Feature activation+0.223
Top resid features:
fer
Tokenfer
Feature activation+0.212
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Pulitzer
Token Pulitzer
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.045
Top resid features:
Tommy
Token Tommy
Feature activation+0.270
Top resid features:
,
Token,
Feature activation+0.062
Top resid features:
Nick
Token Nick
Feature activation+0.406
Top resid features:
and
Token and
Feature activation+0.065
Top resid features:
Tom
Token Tom
Feature activation+0.443
Top resid features:
Te
Token Te
Feature activation+0.130
Top resid features:
ves
Tokenves
Feature activation+0.182
Top resid features:
âĢĵ
Token âĢĵ
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+0.047
Top resid features:
just
Token just
Feature activation+0.050
Top resid features:
as
Token as
Feature activation+0.046
Top resid features:
Dr
Token Dr
Feature activation+0.152
Top resid features:
.
Token.
Feature activation+0.043
Top resid features:
Stan
Token Stan
Feature activation+0.559
Top resid features:
Monte
Token Monte
Feature activation+0.349
Top resid features:
ith
Tokenith
Feature activation+0.201
Top resid features:
likes
Token likes
Feature activation+0.097
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
say
Token say
Feature activation+0.000
Top resid features:
Dante
Token Dante
Feature activation+0.238
Top resid features:
Di
Token Di
Feature activation+0.111
Top resid features:
Mart
TokenMart
Feature activation+0.098
Top resid features:
ino
Tokenino
Feature activation+0.114
Top resid features:
,
Token,
Feature activation+0.090
Top resid features:
Bryan
Token Bryan
Feature activation+0.401
Top resid features:
Kon
Token Kon
Feature activation+0.246
Top resid features:
iet
Tokeniet
Feature activation+0.087
Top resid features:
z
Tokenz
Feature activation+0.000
Top resid features:
ko
Tokenko
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.231
Top resid features:
Warren
Token Warren
Feature activation+0.170
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.248
Top resid features:
Ann
Token Ann
Feature activation+0.267
Top resid features:
Warren
Token Warren
Feature activation+0.218
Top resid features:
Sanders
TokenSanders
Feature activation+0.383
Top resid features:
:
Token:
Feature activation+0.129
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
Damn
TokenDamn
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
Paul
Token Paul
Feature activation+0.170
Top resid features:
Hill
Token Hill
Feature activation+0.142
Top resid features:
murdered
Token murdered
Feature activation+0.079
Top resid features:
Dr
Token Dr
Feature activation+0.157
Top resid features:
.
Token.
Feature activation+0.062
Top resid features:
John
Token John
Feature activation+0.606
Top resid features:
Britt
Token Britt
Feature activation+0.183
Top resid features:
on
Tokenon
Feature activation+0.181
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
abortion
Token abortion
Feature activation+0.000
Top resid features:
Comey
Token Comey
Feature activation+0.124
Top resid features:
and
Token and
Feature activation+0.036
Top resid features:
White
Token White
Feature activation+0.085
Top resid features:
House
Token House
Feature activation+0.037
Top resid features:
Counsel
Token Counsel
Feature activation+0.111
Top resid features:
Neil
Token Neil
Feature activation+0.457
Top resid features:
Egg
Token Egg
Feature activation+0.160
Top resid features:
l
Tokenl
Feature activation+0.061
Top resid features:
eston
Tokeneston
Feature activation+0.222
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
De
Token De
Feature activation+0.117
Top resid features:
aren
Tokenaren
Feature activation+0.114
Top resid features:
/
Token /
Feature activation+0.083
Top resid features:
AP
Token AP
Feature activation+0.090
Top resid features:
Dwight
Token Dwight
Feature activation+0.328
Top resid features:
Chandler
Token Chandler
Feature activation+0.481
Top resid features:
walks
Token walks
Feature activation+0.083
Top resid features:
through
Token through
Feature activation+0.000
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
flood
Token flood
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.043
Top resid features:
Steve
Token Steve
Feature activation+0.312
Top resid features:
Dou
Token Dou
Feature activation+0.117
Top resid features:
glass
Tokenglass
Feature activation+0.135
Top resid features:
and
Token and
Feature activation+0.065
Top resid features:
Dean
Token Dean
Feature activation+0.371
Top resid features:
Musk
Token Musk
Feature activation+0.256
Top resid features:
ett
Tokenett
Feature activation+0.151
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:
Ludwig
Token Ludwig
Feature activation+0.124
Top resid features:
,
Token,
Feature activation+0.038
Top resid features:
Lee
Token Lee
Feature activation+0.204
Top resid features:
Blessing
Token Blessing
Feature activation+0.137
Top resid features:
and
Token and
Feature activation+0.042
Top resid features:
Deborah
Token Deborah
Feature activation+0.461
Top resid features:
Zoe
Token Zoe
Feature activation+0.425
Top resid features:
Lau
Token Lau
Feature activation+0.177
Top resid features:
fer
Tokenfer
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Pulitzer
Token Pulitzer
Feature activation+0.000
Top resid features:
from
Token from
Feature activation+0.037
Top resid features:
Cathy
Token Cathy
Feature activation+0.249
Top resid features:
Dennis
Token Dennis
Feature activation+0.310
Top resid features:
and
Token and
Feature activation+0.055
Top resid features:
Julia
Token Julia
Feature activation+0.316
Top resid features:
Karl
Token Karl
Feature activation+0.354
Top resid features:
sson
Tokensson
Feature activation+0.271
Top resid features:
.
Token.
Feature activation+0.112
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Track
TokenTrack
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
36
Token 36
Feature activation+0.065
Top resid features:
,
Token,
Feature activation+0.031
Top resid features:
and
Token and
Feature activation+0.030
Top resid features:
Amanda
Token Amanda
Feature activation+0.323
Top resid features:
Joyce
Token Joyce
Feature activation+0.332
Top resid features:
Hale
Token Hale
Feature activation+0.254
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
28
Token 28
Feature activation+0.097
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
Editors
Token Editors
Feature activation+0.057
Top resid features:
Bill
Token Bill
Feature activation+0.230
Top resid features:
Rog
Token Rog
Feature activation+0.134
Top resid features:
gio
Tokengio
Feature activation+0.231
Top resid features:
and
Token and
Feature activation+0.047
Top resid features:
Thomas
Token Thomas
Feature activation+0.474
Top resid features:
Jos
Token Jos
Feature activation+0.229
Top resid features:
ce
Tokence
Feature activation+0.086
Top resid features:
lyn
Tokenlyn
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:
Hill
Token Hill
Feature activation+0.137
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
Jim
Token Jim
Feature activation+0.237
Top resid features:
Clark
Token Clark
Feature activation+0.314
Top resid features:
,
Token,
Feature activation+0.069
Top resid features:
Jack
Token Jack
Feature activation+0.410
Top resid features:
Br
Token Br
Feature activation+0.161
Top resid features:
ab
Tokenab
Feature activation+0.135
Top resid features:
ham
Tokenham
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Jo
Token Jo
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.039
Top resid features:
J
Token J
Feature activation+0.084
Top resid features:
iggs
Tokeniggs
Feature activation+0.141
Top resid features:
McDonald
Token McDonald
Feature activation+0.166
Top resid features:
,
Token,
Feature activation+0.055
Top resid features:
Eric
Token Eric
Feature activation+0.413
Top resid features:
Horn
Token Horn
Feature activation+0.316
Top resid features:
ick
Tokenick
Feature activation+0.150
Top resid features:
,
Token,
Feature activation+0.078
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Peter
Token Peter
Feature activation+0.000
Top resid features:
Sen
Token Sen
Feature activation+0.044
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.261
Top resid features:
Warren
Token Warren
Feature activation+0.180
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.275
Top resid features:
Ann
Token Ann
Feature activation+0.319
Top resid features:
Warren
Token Warren
Feature activation+0.226
Top resid features:
Sanders
TokenSanders
Feature activation+0.253
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
Damn
TokenDamn
Feature activation+0.000
Top resid features:
Editors
Token Editors
Feature activation+0.051
Top resid features:
Bill
Token Bill
Feature activation+0.206
Top resid features:
Rog
Token Rog
Feature activation+0.127
Top resid features:
gio
Tokengio
Feature activation+0.196
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
Thomas
Token Thomas
Feature activation+0.358
Top resid features:
Jos
Token Jos
Feature activation+0.241
Top resid features:
ce
Tokence
Feature activation+0.092
Top resid features:
lyn
Tokenlyn
Feature activation+0.191
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
Paul
Token Paul
Feature activation+0.182
Top resid features:
Hill
Token Hill
Feature activation+0.132
Top resid features:
murdered
Token murdered
Feature activation+0.069
Top resid features:
Dr
Token Dr
Feature activation+0.126
Top resid features:
.
Token.
Feature activation+0.037
Top resid features:
John
Token John
Feature activation+0.450
Top resid features:
Britt
Token Britt
Feature activation+0.339
Top resid features:
on
Tokenon
Feature activation+0.125
Top resid features:
at
Token at
Feature activation+0.108
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
abortion
Token abortion
Feature activation+0.000
Top resid features:
doesn
Token doesn
Feature activation+0.026
Top resid features:
't
Token't
Feature activation+0.010
Top resid features:
quite
Token quite
Feature activation+0.020
Top resid features:
matter
Token matter
Feature activation+0.045
Top resid features:
.
Token.
Feature activation+0.107
Top resid features:
David
Token David
Feature activation+0.777
Top resid features:
Roberts
Token Roberts
Feature activation+0.347
Top resid features:
cast
Token cast
Feature activation+0.139
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
color
Token color
Feature activation+0.000
Top resid features:
fully
Tokenfully
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.032
Top resid features:
PAX
Token PAX
Feature activation+0.124
Top resid features:
2007
Token 2007
Feature activation+0.067
Top resid features:
Ċ
TokenĊ
Feature activation+0.065
Top resid features:
Ċ
TokenĊ
Feature activation+0.070
Top resid features:
Richard
TokenRichard
Feature activation+0.482
Top resid features:
William
Token William
Feature activation+0.472
Top resid features:
Whe
Token Whe
Feature activation+0.130
Top resid features:
aton
Tokenaton
Feature activation+0.151
Top resid features:
III
Token III
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.18

Head 2: 0.14

Head 3: 0.08

Head 4: 0.15

Head 5: 0.03

Head 6: 0.03

Head 7: 0.07

Head 8: 0.06

Head 9: 0.04

Head 10: 0.08

Head 11: 0.07

Positive logits

ken1.69

herty1.63

eus1.62

ivas1.62

quez1.61

Jr1.55

axter1.54

Sr1.52

ourke1.51

cz1.51

itone1.50

owicz1.49

kson1.48

hner1.47

Vert1.44

1.44

pton1.43

leck1.43

Buzz1.41

LLP1.40

Negative logits

conformity-1.39

standings-1.34

ancial-1.32

polarization-1.31

favourable-1.29

indoors-1.27

bias-1.27

indexes-1.27

composition-1.27

determining-1.27

representation-1.25

fixture-1.24

varied-1.24

environment-1.24

variables-1.24

rpm-1.24

necessities-1.23

FIX-1.23

objective-1.22

equivalent-1.22

INTERVAL 0.977 - 1.086
CONTAINS 0.000%

,
Token,
Feature activation+0.326
Nick
Token Nick
Feature activation+0.254
and
Token and
Feature activation+0.712
Tom
Token Tom
Feature activation+0.461
Te
Token Te
Feature activation+0.557
ves
Tokenves
Feature activation+1.051
âĢĵ
Token âĢĵ
Feature activation+0.744
Ċ
TokenĊ
Feature activation+0.560
Ċ
TokenĊ
Feature activation+0.483
Family
TokenFamily
Feature activation+0.301
of
Token of
Feature activation+0.398
Blessing
Token Blessing
Feature activation+0.287
and
Token and
Feature activation+0.450
Deborah
Token Deborah
Feature activation+0.312
Zoe
Token Zoe
Feature activation+0.513
Lau
Token Lau
Feature activation+0.906
fer
Tokenfer
Feature activation+1.086
.
Token.
Feature activation+0.791
Pulitzer
Token Pulitzer
Feature activation+0.624
winner
Token winner
Feature activation+0.653
Qu
Token Qu
Feature activation+0.533
i
Tokeni
Feature activation+0.654

INTERVAL 0.869 - 0.977
CONTAINS 0.002%

Lee
Token Lee
Feature activation+0.000
Blessing
Token Blessing
Feature activation+0.287
and
Token and
Feature activation+0.450
Deborah
Token Deborah
Feature activation+0.312
Zoe
Token Zoe
Feature activation+0.513
Lau
Token Lau
Feature activation+0.906
fer
Tokenfer
Feature activation+1.086
.
Token.
Feature activation+0.791
Pulitzer
Token Pulitzer
Feature activation+0.624
winner
Token winner
Feature activation+0.653
Qu
Token Qu
Feature activation+0.533
Mart
TokenMart
Feature activation+0.523
ino
Tokenino
Feature activation+0.520
,
Token,
Feature activation+0.787
Bryan
Token Bryan
Feature activation+0.570
Kon
Token Kon
Feature activation+0.515
iet
Tokeniet
Feature activation+0.963
z
Tokenz
Feature activation+0.748
ko
Tokenko
Feature activation+0.831
and
Token and
Feature activation+0.987
all
Token all
Feature activation+0.900
the
Token the
Feature activation+0.675
House
Token House
Feature activation+0.422
Counsel
Token Counsel
Feature activation+0.509
Neil
Token Neil
Feature activation+0.613
Egg
Token Egg
Feature activation+0.660
l
Tokenl
Feature activation+0.829
eston
Tokeneston
Feature activation+0.931
.
Token.
Feature activation+0.593
Ċ
TokenĊ
Feature activation+0.323
Ċ
TokenĊ
Feature activation+0.256
But
TokenBut
Feature activation+0.122
Republicans
Token Republicans
Feature activation+0.000
aren
Tokenaren
Feature activation+0.563
/
Token /
Feature activation+0.478
AP
Token AP
Feature activation+0.427
Dwight
Token Dwight
Feature activation+0.251
Chandler
Token Chandler
Feature activation+0.425
walks
Token walks
Feature activation+0.928
through
Token through
Feature activation+0.836
his
Token his
Feature activation+0.549
flood
Token flood
Feature activation+0.532
-
Token-
Feature activation+0.488
dam
Tokendam
Feature activation+0.267
Rog
Token Rog
Feature activation+0.154
gio
Tokengio
Feature activation+0.327
and
Token and
Feature activation+0.545
Thomas
Token Thomas
Feature activation+0.444
Jos
Token Jos
Feature activation+0.553
ce
Tokence
Feature activation+0.874
lyn
Tokenlyn
Feature activation+0.862
,
Token,
Feature activation+0.706
who
Token who
Feature activation+0.689
received
Token received
Feature activation+0.514
an
Token an
Feature activation+0.381

INTERVAL 0.760 - 0.869
CONTAINS 0.005%

Sally
Token Sally
Feature activation+0.013
Qu
Token Qu
Feature activation+0.287
illian
Tokenillian
Feature activation+0.599
Yates
Token Yates
Feature activation+0.438
and
Token and
Feature activation+0.739
two
Token two
Feature activation+0.834
Assistant
Token Assistant
Feature activation+0.609
U
Token U
Feature activation+0.649
.
Token.
Feature activation+0.433
S
TokenS
Feature activation+0.458
.
Token.
Feature activation+0.257
Harry
Token Harry
Feature activation+0.000
Wilson
Token Wilson
Feature activation+0.005
,
Token,
Feature activation+0.265
Kevin
Token Kevin
Feature activation+0.123
Stewart
Token Stewart
Feature activation+0.395
,
Token,
Feature activation+0.785
Ryan
Token Ryan
Feature activation+0.544
Kent
Token Kent
Feature activation+0.642
,
Token,
Feature activation+0.942
She
Token She
Feature activation+0.614
yi
Tokenyi
Feature activation+0.655
R
Token R
Feature activation+0.000
avi
Tokenavi
Feature activation+0.000
and
Token and
Feature activation+0.043
Molly
Token Molly
Feature activation+0.069
Wei
Token Wei
Feature activation+0.164
taped
Token taped
Feature activation+0.771
two
Token two
Feature activation+0.671
sexual
Token sexual
Feature activation+0.441
encounters
Token encounters
Feature activation+0.441
.
Token.
Feature activation+0.252
Ċ
TokenĊ
Feature activation+0.075
and
Token and
Feature activation+0.111
Christopher
Token Christopher
Feature activation+0.072
Jon
Token Jon
Feature activation+0.284
Spr
Token Spr
Feature activation+0.624
ig
Tokenig
Feature activation+0.698
man
Tokenman
Feature activation+0.800
Ċ
TokenĊ
Feature activation+0.453
Ċ
TokenĊ
Feature activation+0.349
It
TokenIt
Feature activation+0.000
seems
Token seems
Feature activation+0.000
that
Token that
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Richard
TokenRichard
Feature activation+0.089
William
Token William
Feature activation+0.304
Whe
Token Whe
Feature activation+0.671
aton
Tokenaton
Feature activation+0.848
III
Token III
Feature activation+0.542
(
Token (
Feature activation+0.742
born
Tokenborn
Feature activation+0.646
29
Token 29
Feature activation+0.523
July
Token July
Feature activation+0.406

INTERVAL 0.652 - 0.760
CONTAINS 0.010%

Council
TokenCouncil
Feature activation+0.000
man
Tokenman
Feature activation+0.000
Dennis
Token Dennis
Feature activation+0.000
Robert
Token Robert
Feature activation+0.395
,
Token,
Feature activation+0.560
gathering
Token gathering
Feature activation+0.731
letters
Token letters
Feature activation+0.464
of
Token of
Feature activation+0.418
support
Token support
Feature activation+0.161
from
Token from
Feature activation+0.370
the
Token the
Feature activation+0.158
for
Token for
Feature activation+0.294
governor
Token governor
Feature activation+0.050
and
Token and
Feature activation+0.181
Jean
Token Jean
Feature activation+0.048
Sch
Token Sch
Feature activation+0.392
od
Tokenod
Feature activation+0.692
orf
Tokenorf
Feature activation+0.514
for
Token for
Feature activation+0.462
secretary
Token secretary
Feature activation+0.394
of
Token of
Feature activation+0.207
state
Token state
Feature activation+0.000
hart
Tokenhart
Feature activation+0.000
in
Token in
Feature activation+0.177
Irwin
Token Irwin
Feature activation+0.096
Allen
Token Allen
Feature activation+0.297
âĢ
TokenâĢ
Feature activation+0.617
Ļ
TokenĻ
Feature activation+0.654
s
Tokens
Feature activation+0.420
original
Token original
Feature activation+0.350
1965
Token 1965
Feature activation+0.414
-
Token-
Feature activation+0.320
1968
Token1968
Feature activation+0.368
.
Token.
Feature activation+0.000
Gen
Token Gen
Feature activation+0.000
.
Token.
Feature activation+0.000
Kenneth
Token Kenneth
Feature activation+0.032
Dahl
Token Dahl
Feature activation+0.482
interviewing
Token interviewing
Feature activation+0.749
the
Token the
Feature activation+0.537
sergeant
Token sergeant
Feature activation+0.470
in
Token in
Feature activation+0.426
Texas
Token Texas
Feature activation+0.361
in
Token in
Feature activation+0.380
âĢ
TokenâĢ
Feature activation+0.065
Ŀ
TokenĿ
Feature activation+0.075
Vaughan
Token Vaughan
Feature activation+0.087
councillor
Token councillor
Feature activation+0.235
James
Token James
Feature activation+0.461
Cameron
Token Cameron
Feature activation+0.723
told
Token told
Feature activation+0.691
the
Token the
Feature activation+0.545
Star
Token Star
Feature activation+0.398
in
Token in
Feature activation+0.535
March
Token March
Feature activation+0.351

INTERVAL 0.543 - 0.652
CONTAINS 0.024%

.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Senator
TokenSenator
Feature activation+0.000
David
Token David
Feature activation+0.168
Burns
Token Burns
Feature activation+0.552
,
Token,
Feature activation+0.658
R
Token R
Feature activation+0.472
-
Token-
Feature activation+0.548
Wh
TokenWh
Feature activation+0.373
iting
Tokeniting
Feature activation+0.491
Navy
Token Navy
Feature activation+0.000
Admiral
Token Admiral
Feature activation+0.000
William
Token William
Feature activation+0.210
Mc
Token Mc
Feature activation+0.521
Raven
TokenRaven
Feature activation+0.570
,
Token,
Feature activation+0.556
has
Token has
Feature activation+0.455
said
Token said
Feature activation+0.072
concealed
Token concealed
Feature activation+0.057
weapons
Token weapons
Feature activation+0.042
on
Token on
Feature activation+0.009
religious
Token religious
Feature activation+0.062
right
Token right
Feature activation+0.042
surrogate
Token surrogate
Feature activation+0.011
Jerry
Token Jerry
Feature activation+0.089
Fal
Token Fal
Feature activation+0.232
well
Tokenwell
Feature activation+0.545
and
Token and
Feature activation+0.448
went
Token went
Feature activation+0.333
after
Token after
Feature activation+0.210
John
Token John
Feature activation+0.188
McCain
Token McCain
Feature activation+0.290
ley
Tokenley
Feature activation+0.347
and
Token and
Feature activation+0.323
Bruce
Token Bruce
Feature activation+0.350
H
Token H
Feature activation+0.541
ines
Tokenines
Feature activation+0.747
train
Token train
Feature activation+0.616
us
Token us
Feature activation+0.484
as
Token as
Feature activation+0.428
Scient
Token Scient
Feature activation+0.349
ologists
Tokenologists
Feature activation+0.399
Ċ
TokenĊ
Feature activation+0.210
Arm
Token Arm
Feature activation+0.448
ia
Tokenia
Feature activation+0.601
,
Token,
Feature activation+0.559
Connor
Token Connor
Feature activation+0.448
Hel
Token Hel
Feature activation+0.363
le
Tokenle
Feature activation+0.593
buy
Tokenbuy
Feature activation+0.595
ck
Tokenck
Feature activation+0.530
.
Token.
Feature activation+0.414
The
Token The
Feature activation+0.300
Jets
Token Jets
Feature activation+0.024

INTERVAL 0.434 - 0.543
CONTAINS 0.051%

Matt
Token Matt
Feature activation+0.329
Lomb
Token Lomb
Feature activation+0.521
ardo
Tokenardo
Feature activation+0.655
on
Token on
Feature activation+0.812
Twitter
Token Twitter
Feature activation+0.615
@
Token @
Feature activation+0.523
Matt
TokenMatt
Feature activation+0.338
L
TokenL
Feature activation+0.401
omb
Tokenomb
Feature activation+0.596
ardo
Tokenardo
Feature activation+0.419
975
Token975
Feature activation+0.579
Ċ
TokenĊ
Feature activation+0.000
Senator
TokenSenator
Feature activation+0.000
David
Token David
Feature activation+0.168
Burns
Token Burns
Feature activation+0.552
,
Token,
Feature activation+0.658
R
Token R
Feature activation+0.472
-
Token-
Feature activation+0.548
Wh
TokenWh
Feature activation+0.373
iting
Tokeniting
Feature activation+0.491
,
Token,
Feature activation+0.352
serves
Token serves
Feature activation+0.490
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
Mark
Token Mark
Feature activation+0.000
Shapiro
Token Shapiro
Feature activation+0.296
âĢ
TokenâĢ
Feature activation+0.446
Ļ
TokenĻ
Feature activation+0.349
s
Tokens
Feature activation+0.346
comfort
Token comfort
Feature activation+0.277
zone
Token zone
Feature activation+0.185
by
Token by
Feature activation+0.240
oring
Tokenoring
Feature activation+0.182
,
Token,
Feature activation+0.141
J
Token J
Feature activation+0.020
iggs
Tokeniggs
Feature activation+0.114
McDonald
Token McDonald
Feature activation+0.387
,
Token,
Feature activation+0.455
Eric
Token Eric
Feature activation+0.356
Horn
Token Horn
Feature activation+0.564
ick
Tokenick
Feature activation+0.775
,
Token,
Feature activation+0.863
and
Token and
Feature activation+0.752
and
Token and
Feature activation+0.467
Julia
Token Julia
Feature activation+0.268
Karl
Token Karl
Feature activation+0.691
sson
Tokensson
Feature activation+0.650
.
Token.
Feature activation+0.882
Ċ
TokenĊ
Feature activation+0.461
Ċ
TokenĊ
Feature activation+0.372
Track
TokenTrack
Feature activation+0.220
5
Token 5
Feature activation+0.327
features
Token features
Feature activation+0.187
unc
Token unc
Feature activation+0.077

INTERVAL 0.326 - 0.434
CONTAINS 0.097%

Michael
TokenMichael
Feature activation+0.063
Mans
Token Mans
Feature activation+0.487
field
Tokenfield
Feature activation+0.281
,
Token,
Feature activation+0.383
curator
Token curator
Feature activation+0.520
of
Token of
Feature activation+0.371
film
Token film
Feature activation+0.343
and
Token and
Feature activation+0.226
media
Token media
Feature activation+0.168
arts
Token arts
Feature activation+0.106
at
Token at
Feature activation+0.165
:
Token:
Feature activation+0.000
Stephen
Token Stephen
Feature activation+0.000
A
Token A
Feature activation+0.063
.
Token.
Feature activation+0.091
Smith
Token Smith
Feature activation+0.282
-
Token -
Feature activation+0.345
Looks
Token Looks
Feature activation+0.157
like
Token like
Feature activation+0.181
the
Token the
Feature activation+0.116
family
Token family
Feature activation+0.000
member
Token member
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Jason
TokenJason
Feature activation+0.000
De
Token De
Feature activation+0.224
aren
Tokenaren
Feature activation+0.563
/
Token /
Feature activation+0.478
AP
Token AP
Feature activation+0.427
Dwight
Token Dwight
Feature activation+0.251
Chandler
Token Chandler
Feature activation+0.425
walks
Token walks
Feature activation+0.928
through
Token through
Feature activation+0.836
his
Token his
Feature activation+0.549
who
Token who
Feature activation+0.204
played
Token played
Feature activation+0.124
a
Token a
Feature activation+0.080
perfect
Token perfect
Feature activation+0.052
Robin
Token Robin
Feature activation+0.131
to
Token to
Feature activation+0.393
Bowman
Token Bowman
Feature activation+0.165
âĢ
TokenâĢ
Feature activation+0.353
Ļ
TokenĻ
Feature activation+0.364
s
Tokens
Feature activation+0.255
bat
Token bat
Feature activation+0.120
Scott
Token Scott
Feature activation+0.000
Hill
Token Hill
Feature activation+0.053
iard
Tokeniard
Feature activation+0.430
of
Token of
Feature activation+0.204
Mer
Token Mer
Feature activation+0.305
rim
Tokenrim
Feature activation+0.434
ack
Tokenack
Feature activation+0.381
,
Token,
Feature activation+0.150
the
Token the
Feature activation+0.158
state
Token state
Feature activation+0.000
's
Token's
Feature activation+0.000

INTERVAL 0.217 - 0.326
CONTAINS 0.193%

between
Token between
Feature activation+0.000
Cincinnati
Token Cincinnati
Feature activation+0.000
and
Token and
Feature activation+0.040
Dayton
Token Dayton
Feature activation+0.000
on
Token on
Feature activation+0.297
Interstate
Token Interstate
Feature activation+0.222
75
Token 75
Feature activation+0.231
,
Token,
Feature activation+0.035
where
Token where
Feature activation+0.151
his
Token his
Feature activation+0.090
grandparents
Token grandparents
Feature activation+0.000
expired
Token expired
Feature activation+0.000
in
Token in
Feature activation+0.000
2006
Token 2006
Feature activation+0.000
.
Token.
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
has
Token has
Feature activation+0.280
attempted
Token attempted
Feature activation+0.097
to
Token to
Feature activation+0.178
re
Token re
Feature activation+0.107
author
Tokenauthor
Feature activation+0.165
ize
Tokenize
Feature activation+0.000
Patrick
Token Patrick
Feature activation+0.156
M
Token M
Feature activation+0.288
.
Token.
Feature activation+0.322
H
Token H
Feature activation+0.210
oe
Tokenoe
Feature activation+0.343
y
Tokeny
Feature activation+0.325
,
Token,
Feature activation+0.349
Roy
Token Roy
Feature activation+0.011
R
Token R
Feature activation+0.198
itchie
Tokenitchie
Feature activation+0.304
,
Token,
Feature activation+0.428
Goal
Token Goal
Feature activation+0.000
keeper
Tokenkeeper
Feature activation+0.000
Josh
Token Josh
Feature activation+0.000
Ford
Token Ford
Feature activation+0.130
was
Token was
Feature activation+0.391
selected
Token selected
Feature activation+0.221
in
Token in
Feature activation+0.135
the
Token the
Feature activation+0.035
second
Token second
Feature activation+0.000
stage
Token stage
Feature activation+0.000
of
Token of
Feature activation+0.000
Reason
Token Reason
Feature activation+0.000
Ezra
Token Ezra
Feature activation+0.000
Miller
Token Miller
Feature activation+0.246
Is
Token Is
Feature activation+0.262
Exc
Token Exc
Feature activation+0.229
ited
Tokenited
Feature activation+0.309
For
Token For
Feature activation+0.236
Fantastic
Token Fantastic
Feature activation+0.140
Beasts
Token Beasts
Feature activation+0.114
and
Token and
Feature activation+0.240
Justice
Token Justice
Feature activation+0.020

INTERVAL 0.109 - 0.217
CONTAINS 0.391%

of
Token of
Feature activation+0.000
George
Token George
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
in
Token in
Feature activation+0.109
2008
Token 2008
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
after
Token after
Feature activation+0.000
W
Token W
Feature activation+0.000
had
Token had
Feature activation+0.000
y
Tokeny
Feature activation+0.482
Jr
Token Jr
Feature activation+0.299
.
Token.
Feature activation+0.284
told
Token told
Feature activation+0.378
Ey
Token Ey
Feature activation+0.076
ewitness
Tokenewitness
Feature activation+0.199
News
Token News
Feature activation+0.097
on
Token on
Feature activation+0.286
Thursday
Token Thursday
Feature activation+0.213
.
Token.
Feature activation+0.085
He
Token He
Feature activation+0.061
to
Token to
Feature activation+0.000
gain
Token gain
Feature activation+0.000
."
Token."
Feature activation+0.000
Alonso
Token Alonso
Feature activation+0.000
arrived
Token arrived
Feature activation+0.037
at
Token at
Feature activation+0.135
the
Token the
Feature activation+0.000
Yas
Token Yas
Feature activation+0.000
Marina
Token Marina
Feature activation+0.000
Circuit
Token Circuit
Feature activation+0.000
in
Token in
Feature activation+0.206
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ash
TokenAsh
Feature activation+0.000
lan
Tokenlan
Feature activation+0.078
said
Token said
Feature activation+0.301
this
Token this
Feature activation+0.176
was
Token was
Feature activation+0.089
one
Token one
Feature activation+0.076
of
Token of
Feature activation+0.042
their
Token their
Feature activation+0.000
biggest
Token biggest
Feature activation+0.000
YouTube
Token YouTube
Feature activation+0.051
with
Token with
Feature activation+0.243
hardcore
Token hardcore
Feature activation+0.155
porn
Token porn
Feature activation+0.094
;
Token;
Feature activation+0.069
taking
Token taking
Feature activation+0.169
down
Token down
Feature activation+0.055
gossip
Token gossip
Feature activation+0.022
blogs
Token blogs
Feature activation+0.059
;
Token;
Feature activation+0.000
vandal
Token vandal
Feature activation+0.000

INTERVAL 0.000 - 0.109
CONTAINS 99.228%

2007
Token 2007
Feature activation+0.000
Mand
Token Mand
Feature activation+0.000
ar
Tokenar
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
paid
Token paid
Feature activation+0.000
$
Token $
Feature activation+0.000
145
Token145
Feature activation+0.000
,
Token,
Feature activation+0.000
000
Token000
Feature activation+0.000
(£
Token (£
Feature activation+0.000
93
Token93
Feature activation+0.000
eno
Tokeneno
Feature activation+0.000
-
Token-
Feature activation+0.000
Sch
TokenSch
Feature activation+0.000
ultz
Tokenultz
Feature activation+0.000
Clinic
Token Clinic
Feature activation+0.000
in
Token in
Feature activation+0.000
Colorado
Token Colorado
Feature activation+0.000
that
Token that
Feature activation+0.000
performs
Token performs
Feature activation+0.000
a
Token a
Feature activation+0.000
nons
Token nons
Feature activation+0.000
appeal
Token appeal
Feature activation+0.000
the
Token the
Feature activation+0.000
ruling
Token ruling
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
amounts
Token amounts
Feature activation+0.000
awarded
Token awarded
Feature activation+0.000
in
Token in
Feature activation+0.000
this
Token this
Feature activation+0.000
case
Token case
Feature activation+0.000
radically
Token radically
Feature activation+0.000
been
Token been
Feature activation+0.000
ruled
Token ruled
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
skills
Token skills
Feature activation+0.000
camp
Token camp
Feature activation+0.000
beginning
Token beginning
Feature activation+0.000
on
Token on
Feature activation+0.000
May
Token May
Feature activation+0.000
28
Token 28
Feature activation+0.000
also
Token also
Feature activation+0.000
responded
Token responded
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
scene
Token scene
Feature activation+0.000
and
Token and
Feature activation+0.000
found
Token found
Feature activation+0.000
Stephanie
Token Stephanie
Feature activation+0.000
alive
Token alive
Feature activation+0.000
.
Token.
Feature activation+0.000
C
TokenC
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 H1.4: (feature 8982)

TOP ACTIVATIONS
MAX = 1.001

do
Tokendo
Feature activation+0.730
,
Token,
Feature activation+0.849
which
Token which
Feature activation+0.972
is
Token is
Feature activation+0.951
already
Token already
Feature activation+0.914
home
Token home
Feature activation+1.001
to
Token to
Feature activation+0.678
a
Token a
Feature activation+0.671
North
Token North
Feature activation+0.751
Korean
Token Korean
Feature activation+0.477
military
Token military
Feature activation+0.364
j
Tokenj
Feature activation+0.583
iv
Tokeniv
Feature activation+0.493
ar
Tokenar
Feature activation+0.531
,
Token,
Feature activation+0.720
El
Token El
Feature activation+0.894
iz
Tokeniz
Feature activation+0.989
ondo
Tokenondo
Feature activation+0.962
,
Token,
Feature activation+0.782
Rest
Token Rest
Feature activation+0.907
re
Tokenre
Feature activation+0.953
po
Tokenpo
Feature activation+0.780
age
Tokenage
Feature activation+0.572
Dou
Token Dou
Feature activation+0.705
rak
Tokenrak
Feature activation+0.685
u
Tokenu
Feature activation+0.586
,
Token,
Feature activation+0.969
and
Token and
Feature activation+0.987
Jou
Token Jou
Feature activation+0.952
ji
Tokenji
Feature activation+0.662
Nak
Token Nak
Feature activation+0.810
ata
Tokenata
Feature activation+0.756
as
Token as
Feature activation+0.789
j
Tokenj
Feature activation+0.507
ae
Tokenae
Feature activation+0.470
-
Token-
Feature activation+0.734
do
Tokendo
Feature activation+0.730
,
Token,
Feature activation+0.849
which
Token which
Feature activation+0.972
is
Token is
Feature activation+0.951
already
Token already
Feature activation+0.914
home
Token home
Feature activation+1.001
to
Token to
Feature activation+0.678
a
Token a
Feature activation+0.671
Ut
Token Ut
Feature activation+0.647
age
Tokenage
Feature activation+0.572
Dou
Token Dou
Feature activation+0.705
rak
Tokenrak
Feature activation+0.685
u
Tokenu
Feature activation+0.586
,
Token,
Feature activation+0.969
and
Token and
Feature activation+0.987
Jou
Token Jou
Feature activation+0.952
ji
Tokenji
Feature activation+0.662
Nak
Token Nak
Feature activation+0.810
ata
Tokenata
Feature activation+0.756
e
Tokene
Feature activation+0.499
Bain
Token Bain
Feature activation+0.551
imar
Tokenimar
Feature activation+0.539
ama
Tokenama
Feature activation+0.560
,
Token,
Feature activation+0.774
said
Token said
Feature activation+0.966
he
Token he
Feature activation+0.814
hoped
Token hoped
Feature activation+0.699
the
Token the
Feature activation+0.644
planned
Token planned
Feature activation+0.689
construction
Token construction
Feature activation+0.687
iv
Tokeniv
Feature activation+0.493
ar
Tokenar
Feature activation+0.531
,
Token,
Feature activation+0.720
El
Token El
Feature activation+0.894
iz
Tokeniz
Feature activation+0.989
ondo
Tokenondo
Feature activation+0.962
,
Token,
Feature activation+0.782
Rest
Token Rest
Feature activation+0.907
re
Tokenre
Feature activation+0.953
po
Tokenpo
Feature activation+0.780
,
Token,
Feature activation+0.662
ver
Token ver
Feature activation+0.779
l
Tokenl
Feature activation+0.828
ä
Tokenä
Feature activation+0.705
ng
Tokenng
Feature activation+0.577
ern
Tokenern
Feature activation+0.613
.
Token.
Feature activation+0.961
<|endoftext|>
Token<|endoftext|>
Feature activation+0.929
ADVERTISEMENT
TokenADVERTISEMENT
Feature activation+0.657
Ċ
TokenĊ
Feature activation+0.479
Ċ
TokenĊ
Feature activation+0.292
T
TokenT
Feature activation+0.247
inas
Tokeninas
Feature activation+0.000
J
Token J
Feature activation+0.263
urg
Tokenurg
Feature activation+0.472
ait
Tokenait
Feature activation+0.450
is
Tokenis
Feature activation+0.674
-
Token -
Feature activation+0.958
bass
Token bass
Feature activation+0.927
guitar
Token guitar
Feature activation+0.775
.
Token.
Feature activation+0.674
Ċ
TokenĊ
Feature activation+0.643
Ċ
TokenĊ
Feature activation+0.520
-
Token-
Feature activation+0.413
R
TokenR
Feature activation+0.477
iw
Tokeniw
Feature activation+0.394
al
Tokenal
Feature activation+0.322
).
Token).
Feature activation+0.806
After
Token After
Feature activation+0.956
25
Token 25
Feature activation+0.859
km
Tokenkm
Feature activation+0.824
of
Token of
Feature activation+0.665
racing
Token racing
Feature activation+0.806
their
Token their
Feature activation+0.623
El
Token El
Feature activation+0.894
iz
Tokeniz
Feature activation+0.989
ondo
Tokenondo
Feature activation+0.962
,
Token,
Feature activation+0.782
Rest
Token Rest
Feature activation+0.907
re
Tokenre
Feature activation+0.953
po
Tokenpo
Feature activation+0.780
,
Token,
Feature activation+0.662
Gent
Token Gent
Feature activation+0.872
ile
Tokenile
Feature activation+0.833
(
Token (
Feature activation+0.536
Dou
Token Dou
Feature activation+0.705
rak
Tokenrak
Feature activation+0.685
u
Tokenu
Feature activation+0.586
,
Token,
Feature activation+0.969
and
Token and
Feature activation+0.987
Jou
Token Jou
Feature activation+0.952
ji
Tokenji
Feature activation+0.662
Nak
Token Nak
Feature activation+0.810
ata
Tokenata
Feature activation+0.756
as
Token as
Feature activation+0.789
Narr
Token Narr
Feature activation+0.752
the
Token the
Feature activation+0.713
Me
Token Me
Feature activation+0.799
erg
Tokenerg
Feature activation+0.690
un
Tokenun
Feature activation+0.738
j
Tokenj
Feature activation+0.711
police
Token police
Feature activation+0.952
to
Token to
Feature activation+0.643
lodge
Token lodge
Feature activation+0.728
a
Token a
Feature activation+0.581
complaint
Token complaint
Feature activation+0.595
.
Token.
Feature activation+0.341
ae
Tokenae
Feature activation+0.470
-
Token-
Feature activation+0.734
do
Tokendo
Feature activation+0.730
,
Token,
Feature activation+0.849
which
Token which
Feature activation+0.972
is
Token is
Feature activation+0.951
already
Token already
Feature activation+0.914
home
Token home
Feature activation+1.001
to
Token to
Feature activation+0.678
a
Token a
Feature activation+0.671
North
Token North
Feature activation+0.751
S
Token S
Feature activation+0.000
riv
Tokenriv
Feature activation+0.000
ast
Tokenast
Feature activation+0.091
ava
Tokenava
Feature activation+0.359
,
Token,
Feature activation+0.723
he
Token he
Feature activation+0.949
directed
Token directed
Feature activation+0.870
the
Token the
Feature activation+0.713
Me
Token Me
Feature activation+0.799
erg
Tokenerg
Feature activation+0.690
un
Tokenun
Feature activation+0.738
inform
Token inform
Feature activation+0.766
at
Tokenat
Feature activation+0.775
iv
Tokeniv
Feature activation+0.659
n
Tokenn
Feature activation+0.635
og
Tokenog
Feature activation+0.584
program
Token program
Feature activation+0.943
a
Tokena
Feature activation+0.673
B
Token B
Feature activation+0.635
92
Token92
Feature activation+0.566
plate
Token plate
Feature activation+0.614
n
Token n
Feature activation+0.280
l
Tokenl
Feature activation+0.828
ä
Tokenä
Feature activation+0.705
ng
Tokenng
Feature activation+0.577
ern
Tokenern
Feature activation+0.613
.
Token.
Feature activation+0.961
<|endoftext|>
Token<|endoftext|>
Feature activation+0.929
ADVERTISEMENT
TokenADVERTISEMENT
Feature activation+0.657
Ċ
TokenĊ
Feature activation+0.479
Ċ
TokenĊ
Feature activation+0.292
T
TokenT
Feature activation+0.247
ennis
Tokenennis
Feature activation+0.123
J
Token J
Feature activation+0.263
urg
Tokenurg
Feature activation+0.472
ait
Tokenait
Feature activation+0.450
is
Tokenis
Feature activation+0.674
-
Token -
Feature activation+0.958
bass
Token bass
Feature activation+0.927
guitar
Token guitar
Feature activation+0.775
.
Token.
Feature activation+0.674
Ċ
TokenĊ
Feature activation+0.643
Ċ
TokenĊ
Feature activation+0.520
History
TokenHistory
Feature activation+0.405
ines
Tokenines
Feature activation+0.543
en
Token en
Feature activation+0.542
nu
Token nu
Feature activation+0.413
est
Tokenest
Feature activation+0.371
ras
Tokenras
Feature activation+0.397
âĢ¦
TokenâĢ¦
Feature activation+0.925
http
Token http
Feature activation+0.689
://
Token://
Feature activation+0.635
t
Tokent
Feature activation+0.694
.
Token.
Feature activation+0.557
co
Tokenco
Feature activation+0.479
exp
Token exp
Feature activation+0.553
onen
Tokenonen
Feature activation+0.593
cial
Tokencial
Feature activation+0.702
"
Token"
Feature activation+0.867
no
Token no
Feature activation+0.763
volume
Token volume
Feature activation+0.924
de
Token de
Feature activation+0.664
consult
Token consult
Feature activation+0.731
as
Tokenas
Feature activation+0.649
de
Token de
Feature activation+0.432
int
Token int
Feature activation+0.529

Top DFA by src position
MAX = 0.390

<|endoftext|>
Token<|endoftext|>
Feature activation+0.251
Top resid features:
on
Tokenon
Feature activation+0.145
Top resid features:
p
Tokenp
Feature activation+0.140
Top resid features:
ye
Tokenye
Feature activation+0.116
Top resid features:
ong
Tokenong
Feature activation+0.133
Top resid features:
-
Token-
Feature activation+0.056
Top resid features:
Men
Token Men
Feature activation+0.140
Top resid features:
j
Tokenj
Feature activation+0.176
Top resid features:
iv
Tokeniv
Feature activation+0.222
Top resid features:
ar
Tokenar
Feature activation+0.254
Top resid features:
,
Token,
Feature activation+0.158
Top resid features:
El
Token El
Feature activation+0.316
Top resid features:
iz
Tokeniz
Feature activation+0.209
Top resid features:
ondo
Tokenondo
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Rest
Token Rest
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.288
Top resid features:
ad
Tokenad
Feature activation+0.109
Top resid features:
Åį
TokenÅį
Feature activation+0.091
Top resid features:
,
Token,
Feature activation+0.052
Top resid features:
Ak
Token Ak
Feature activation+0.158
Top resid features:
iko
Tokeniko
Feature activation+0.166
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.269
Top resid features:
on
Tokenon
Feature activation+0.166
Top resid features:
p
Tokenp
Feature activation+0.150
Top resid features:
ye
Tokenye
Feature activation+0.121
Top resid features:
ong
Tokenong
Feature activation+0.139
Top resid features:
-
Token-
Feature activation+0.065
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.303
Top resid features:
ad
Tokenad
Feature activation+0.124
Top resid features:
Åį
TokenÅį
Feature activation+0.093
Top resid features:
,
Token,
Feature activation+0.068
Top resid features:
Ak
Token Ak
Feature activation+0.177
Top resid features:
iko
Tokeniko
Feature activation+0.170
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.301
Top resid features:
,
Token,
Feature activation+0.060
Top resid features:
J
Token J
Feature activation+0.163
Top resid features:
osa
Tokenosa
Feature activation+0.194
Top resid features:
ia
Tokenia
Feature activation+0.208
Top resid features:
V
Token V
Feature activation+0.195
Top resid features:
Men
Token Men
Feature activation+0.125
Top resid features:
j
Tokenj
Feature activation+0.162
Top resid features:
iv
Tokeniv
Feature activation+0.205
Top resid features:
ar
Tokenar
Feature activation+0.248
Top resid features:
,
Token,
Feature activation+0.145
Top resid features:
El
Token El
Feature activation+0.262
Top resid features:
iz
Tokeniz
Feature activation+0.147
Top resid features:
ondo
Tokenondo
Feature activation+0.200
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Rest
Token Rest
Feature activation+0.000
Top resid features:
re
Tokenre
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.316
Top resid features:
Ar
Token Ar
Feature activation+0.202
Top resid features:
be
Tokenbe
Feature activation+0.121
Top resid features:
its
Tokenits
Feature activation+0.138
Top resid features:
p
Tokenp
Feature activation+0.160
Top resid features:
ap
Tokenap
Feature activation+0.164
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.375
Top resid features:
G
TokenG
Feature activation+0.172
Top resid features:
ed
Tokened
Feature activation+0.168
Top resid features:
im
Tokenim
Feature activation+0.280
Top resid features:
inas
Tokeninas
Feature activation+0.234
Top resid features:
J
Token J
Feature activation+0.247
Top resid features:
ring
Tokenring
Feature activation+0.184
Top resid features:
-
Token-
Feature activation+0.098
Top resid features:
R
TokenR
Feature activation+0.184
Top resid features:
iw
Tokeniw
Feature activation+0.179
Top resid features:
al
Tokenal
Feature activation+0.231
Top resid features:
).
Token).
Feature activation+0.290
Top resid features:
After
Token After
Feature activation+0.195
Top resid features:
25
Token 25
Feature activation+0.000
Top resid features:
km
Tokenkm
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
racing
Token racing
Feature activation+0.000
Top resid features:
âĢ²
TokenâĢ²
Feature activation+0.004
Top resid features:
),
Token),
Feature activation+0.073
Top resid features:
Men
Token Men
Feature activation+0.101
Top resid features:
j
Tokenj
Feature activation+0.149
Top resid features:
iv
Tokeniv
Feature activation+0.186
Top resid features:
ar
Tokenar
Feature activation+0.231
Top resid features:
,
Token,
Feature activation+0.094
Top resid features:
El
Token El
Feature activation+0.192
Top resid features:
iz
Tokeniz
Feature activation+0.207
Top resid features:
ondo
Tokenondo
Feature activation+0.176
Top resid features:
,
Token,
Feature activation+0.128
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.198
Top resid features:
ad
Tokenad
Feature activation+0.153
Top resid features:
Åį
TokenÅį
Feature activation+0.111
Top resid features:
,
Token,
Feature activation+0.073
Top resid features:
Ak
Token Ak
Feature activation+0.154
Top resid features:
iko
Tokeniko
Feature activation+0.146
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.272
Top resid features:
Bri
Token Bri
Feature activation+0.122
Top resid features:
j
Tokenj
Feature activation+0.131
Top resid features:
esh
Tokenesh
Feature activation+0.133
Top resid features:
S
Token S
Feature activation+0.131
Top resid features:
riv
Tokenriv
Feature activation+0.166
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.253
Top resid features:
on
Tokenon
Feature activation+0.149
Top resid features:
p
Tokenp
Feature activation+0.152
Top resid features:
ye
Tokenye
Feature activation+0.121
Top resid features:
ong
Tokenong
Feature activation+0.138
Top resid features:
-
Token-
Feature activation+0.061
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.385
Top resid features:
Bri
Token Bri
Feature activation+0.164
Top resid features:
j
Tokenj
Feature activation+0.196
Top resid features:
esh
Tokenesh
Feature activation+0.228
Top resid features:
S
Token S
Feature activation+0.244
Top resid features:
riv
Tokenriv
Feature activation+0.226
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.259
Top resid features:
Mat
Token Mat
Feature activation+0.095
Top resid features:
i
Tokeni
Feature activation+0.097
Top resid features:
Äĩ
TokenÄĩ
Feature activation+0.104
Top resid features:
u
Tokenu
Feature activation+0.110
Top resid features:
,
Token,
Feature activation+0.064
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.326
Top resid features:
Ar
Token Ar
Feature activation+0.241
Top resid features:
be
Tokenbe
Feature activation+0.120
Top resid features:
its
Tokenits
Feature activation+0.123
Top resid features:
p
Tokenp
Feature activation+0.144
Top resid features:
ap
Tokenap
Feature activation+0.148
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.343
Top resid features:
G
TokenG
Feature activation+0.196
Top resid features:
ed
Tokened
Feature activation+0.155
Top resid features:
im
Tokenim
Feature activation+0.237
Top resid features:
inas
Tokeninas
Feature activation+0.266
Top resid features:
J
Token J
Feature activation+0.210
Top resid features:
ines
Tokenines
Feature activation+0.123
Top resid features:
en
Token en
Feature activation+0.104
Top resid features:
nu
Token nu
Feature activation+0.078
Top resid features:
est
Tokenest
Feature activation+0.142
Top resid features:
ras
Tokenras
Feature activation+0.161
Top resid features:
âĢ¦
TokenâĢ¦
Feature activation+0.390
Top resid features:
http
Token http
Feature activation+0.000
Top resid features:
://
Token://
Feature activation+0.000
Top resid features:
t
Tokent
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
co
Tokenco
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.254
Top resid features:
o
Tokeno
Feature activation+0.153
Top resid features:
que
Token que
Feature activation+0.058
Top resid features:
ch
Token ch
Feature activation+0.091
Top resid features:
am
Tokenam
Feature activation+0.119
Top resid features:
ou
Tokenou
Feature activation+0.132
Top resid features:

Decoder Weights Distribution

Head 0: 0.03

Head 1: 0.07

Head 2: 0.16

Head 3: 0.08

Head 4: 0.15

Head 5: 0.03

Head 6: 0.04

Head 7: 0.11

Head 8: 0.07

Head 9: 0.07

Head 10: 0.14

Head 11: 0.06

Positive logits

nen1.09

1.03

ragon1.00

fecture0.99

hai0.99

0.97

hu0.96

ğ0.95

ashtra0.95

;;;;;;;;;;;;0.94

0.93

ensis0.93

sch0.92

esan0.92

Elys0.91

Reincarnated0.91

geries0.90

ocese0.90

ドラゴン0.89

ivas0.89

Negative logits

increments-1.15

depends-1.08

cents-0.97

msec-0.93

alarms-0.89

suppose-0.89

deduct-0.89

deductible-0.88

ITNESS-0.87

subjective-0.84

millisec-0.84

subscriptions-0.84

changing-0.83

recip-0.81

healthier-0.80

compliant-0.80

depreciation-0.79

quotas-0.79

compliance-0.79

mindless-0.79

INTERVAL 0.901 - 1.001
CONTAINS 0.002%

Dou
Token Dou
Feature activation+0.705
rak
Tokenrak
Feature activation+0.685
u
Tokenu
Feature activation+0.586
,
Token,
Feature activation+0.969
and
Token and
Feature activation+0.987
Jou
Token Jou
Feature activation+0.952
ji
Tokenji
Feature activation+0.662
Nak
Token Nak
Feature activation+0.810
ata
Tokenata
Feature activation+0.756
as
Token as
Feature activation+0.789
Narr
Token Narr
Feature activation+0.752
Ut
Token Ut
Feature activation+0.647
age
Tokenage
Feature activation+0.572
Dou
Token Dou
Feature activation+0.705
rak
Tokenrak
Feature activation+0.685
u
Tokenu
Feature activation+0.586
,
Token,
Feature activation+0.969
and
Token and
Feature activation+0.987
Jou
Token Jou
Feature activation+0.952
ji
Tokenji
Feature activation+0.662
Nak
Token Nak
Feature activation+0.810
ata
Tokenata
Feature activation+0.756
ver
Token ver
Feature activation+0.779
l
Tokenl
Feature activation+0.828
ä
Tokenä
Feature activation+0.705
ng
Tokenng
Feature activation+0.577
ern
Tokenern
Feature activation+0.613
.
Token.
Feature activation+0.961
<|endoftext|>
Token<|endoftext|>
Feature activation+0.929
ADVERTISEMENT
TokenADVERTISEMENT
Feature activation+0.657
Ċ
TokenĊ
Feature activation+0.479
Ċ
TokenĊ
Feature activation+0.292
T
TokenT
Feature activation+0.247
inform
Token inform
Feature activation+0.766
at
Tokenat
Feature activation+0.775
iv
Tokeniv
Feature activation+0.659
n
Tokenn
Feature activation+0.635
og
Tokenog
Feature activation+0.584
program
Token program
Feature activation+0.943
a
Tokena
Feature activation+0.673
B
Token B
Feature activation+0.635
92
Token92
Feature activation+0.566
plate
Token plate
Feature activation+0.614
n
Token n
Feature activation+0.280
age
Tokenage
Feature activation+0.572
Dou
Token Dou
Feature activation+0.705
rak
Tokenrak
Feature activation+0.685
u
Tokenu
Feature activation+0.586
,
Token,
Feature activation+0.969
and
Token and
Feature activation+0.987
Jou
Token Jou
Feature activation+0.952
ji
Tokenji
Feature activation+0.662
Nak
Token Nak
Feature activation+0.810
ata
Tokenata
Feature activation+0.756
as
Token as
Feature activation+0.789

INTERVAL 0.801 - 0.901
CONTAINS 0.004%

au
Tokenau
Feature activation+0.392
ht
Tokenht
Feature activation+0.398
em
Tokenem
Feature activation+0.512
oc
Tokenoc
Feature activation+0.537
Bl
Token Bl
Feature activation+0.735
anco
Tokenanco
Feature activation+0.807
.
Token.
Feature activation+0.673
And
Token And
Feature activation+0.833
then
Token then
Feature activation+0.864
things
Token things
Feature activation+0.758
started
Token started
Feature activation+0.774
and
Token and
Feature activation+0.732
Bh
Token Bh
Feature activation+0.772
ak
Tokenak
Feature activation+0.656
kar
Tokenkar
Feature activation+0.594
51
Token 51
Feature activation+0.879
.
Token.
Feature activation+0.814
Ċ
TokenĊ
Feature activation+0.881
Ċ
TokenĊ
Feature activation+0.716
Instead
TokenInstead
Feature activation+0.757
of
Token of
Feature activation+0.679
ch
Token ch
Feature activation+0.766
Comp
Token Comp
Feature activation+0.524
o
Tokeno
Feature activation+0.526
am
Tokenam
Feature activation+0.607
or
Tokenor
Feature activation+0.619
would
Token would
Feature activation+0.879
feel
Token feel
Feature activation+0.816
differently
Token differently
Feature activation+0.664
if
Token if
Feature activation+0.626
organizations
Token organizations
Feature activation+0.654
,
Token,
Feature activation+0.485
like
Token like
Feature activation+0.407
Mot
Token Mot
Feature activation+0.000
so
Tokenso
Feature activation+0.000
en
Tokenen
Feature activation+0.235
eng
Tokeneng
Feature activation+0.438
would
Token would
Feature activation+0.827
surely
Token surely
Feature activation+0.802
find
Token find
Feature activation+0.780
that
Token that
Feature activation+0.758
without
Token without
Feature activation+0.679
Z
Token Z
Feature activation+0.716
uma
Tokenuma
Feature activation+0.669
audi
Tokenaudi
Feature activation+0.000
Mot
Token Mot
Feature activation+0.000
so
Tokenso
Feature activation+0.000
en
Tokenen
Feature activation+0.235
eng
Tokeneng
Feature activation+0.438
would
Token would
Feature activation+0.827
surely
Token surely
Feature activation+0.802
find
Token find
Feature activation+0.780
that
Token that
Feature activation+0.758
without
Token without
Feature activation+0.679
Z
Token Z
Feature activation+0.716

INTERVAL 0.701 - 0.801
CONTAINS 0.013%

i
Tokeni
Feature activation+0.671
&
Token &
Feature activation+0.776
Data
Token Data
Feature activation+0.778
,
Token,
Feature activation+0.771
and
Token and
Feature activation+0.746
A
Token A
Feature activation+0.795
isin
Tokenisin
Feature activation+0.670
AW
Token AW
Feature activation+0.634
.
Token.
Feature activation+0.602
Ċ
TokenĊ
Feature activation+0.645
Ċ
TokenĊ
Feature activation+0.503
Kar
Token Kar
Feature activation+0.000
ob
Tokenob
Feature activation+0.134
on
Tokenon
Feature activation+0.365
ik
Tokenik
Feature activation+0.387
for
Token for
Feature activation+0.616
some
Token some
Feature activation+0.792
tips
Token tips
Feature activation+0.697
on
Token on
Feature activation+0.668
navigating
Token navigating
Feature activation+0.577
Content
Token Content
Feature activation+0.686
ID
TokenID
Feature activation+0.552
ien
Tokenien
Feature activation+0.209
mal
Token mal
Feature activation+0.224
he
Tokenhe
Feature activation+0.267
ure
Tokenure
Feature activation+0.309
use
Tokenuse
Feature activation+0.458
pour
Token pour
Feature activation+0.701
av
Token av
Feature activation+0.431
oir
Tokenoir
Feature activation+0.508
dro
Token dro
Feature activation+0.402
it
Tokenit
Feature activation+0.545
a
Token a
Feature activation+0.570
Aw
Token Aw
Feature activation+0.482
ake
Tokenake
Feature activation+0.617
(
Token (
Feature activation+0.697
2000
Token2000
Feature activation+0.734
)
Token)
Feature activation+0.622
âĢĵ
Token âĢĵ
Feature activation+0.720
an
Token an
Feature activation+0.658
extraordinary
Token extraordinary
Feature activation+0.683
look
Token look
Feature activation+0.536
at
Token at
Feature activation+0.484
a
Token a
Feature activation+0.442
Ch
Token Ch
Feature activation+0.000
ish
Tokenish
Feature activation+0.138
ol
Tokenol
Feature activation+0.330
m
Tokenm
Feature activation+0.394
are
Token are
Feature activation+0.709
charged
Token charged
Feature activation+0.716
with
Token with
Feature activation+0.635
a
Token a
Feature activation+0.629
one
Token one
Feature activation+0.642
count
Token count
Feature activation+0.609
of
Token of
Feature activation+0.507

INTERVAL 0.601 - 0.701
CONTAINS 0.027%

are
Token are
Feature activation+0.709
charged
Token charged
Feature activation+0.716
with
Token with
Feature activation+0.635
a
Token a
Feature activation+0.629
one
Token one
Feature activation+0.642
count
Token count
Feature activation+0.609
of
Token of
Feature activation+0.507
wrong
Token wrong
Feature activation+0.469
fully
Tokenfully
Feature activation+0.367
obtaining
Token obtaining
Feature activation+0.475
public
Token public
Feature activation+0.461
with
Token with
Feature activation+0.385
L
Token L
Feature activation+0.527
ying
Tokenying
Feature activation+0.441
Aw
Token Aw
Feature activation+0.482
ake
Tokenake
Feature activation+0.617
(
Token (
Feature activation+0.697
2000
Token2000
Feature activation+0.734
)
Token)
Feature activation+0.622
âĢĵ
Token âĢĵ
Feature activation+0.720
an
Token an
Feature activation+0.658
extraordinary
Token extraordinary
Feature activation+0.683
arte
Tokenarte
Feature activation+0.494
,[
Token,[
Feature activation+0.687
17
Token17
Feature activation+0.654
]
Token]
Feature activation+0.723
a
Token a
Feature activation+0.698
.
Token.
Feature activation+0.652
k
Tokenk
Feature activation+0.738
.
Token.
Feature activation+0.570
a
Tokena
Feature activation+0.572
.
Token.
Feature activation+0.484
"
Token "
Feature activation+0.571
Robert
Token Robert
Feature activation+0.236
L
Token L
Feature activation+0.261
uss
Tokenuss
Feature activation+0.271
er
Tokener
Feature activation+0.231
,
Token,
Feature activation+0.385
chief
Token chief
Feature activation+0.642
designer
Token designer
Feature activation+0.516
and
Token and
Feature activation+0.296
technical
Token technical
Feature activation+0.366
director
Token director
Feature activation+0.341
at
Token at
Feature activation+0.197
est
Tokenest
Feature activation+0.371
ras
Tokenras
Feature activation+0.397
âĢ¦
TokenâĢ¦
Feature activation+0.925
http
Token http
Feature activation+0.689
://
Token://
Feature activation+0.635
t
Tokent
Feature activation+0.694
.
Token.
Feature activation+0.557
co
Tokenco
Feature activation+0.479
/
Token/
Feature activation+0.418
DT
TokenDT
Feature activation+0.267
ty
Tokenty
Feature activation+0.131

INTERVAL 0.501 - 0.601
CONTAINS 0.051%

N
TokenN
Feature activation+0.361
y
Tokeny
Feature activation+0.199
al
Tokenal
Feature activation+0.191
and
Tokenand
Feature activation+0.252
u
Tokenu
Feature activation+0.315
said
Token said
Feature activation+0.511
that
Token that
Feature activation+0.389
,
Token,
Feature activation+0.334
with
Token with
Feature activation+0.323
the
Token the
Feature activation+0.296
operation
Token operation
Feature activation+0.286
Sa
Token Sa
Feature activation+0.000
eed
Tokeneed
Feature activation+0.000
Sark
Token Sark
Feature activation+0.017
ar
Tokenar
Feature activation+0.148
,
Token,
Feature activation+0.458
head
Token head
Feature activation+0.539
of
Token of
Feature activation+0.457
Research
Token Research
Feature activation+0.545
Center
Token Center
Feature activation+0.513
for
Token for
Feature activation+0.396
Medical
Token Medical
Feature activation+0.495
Bay
Token Bay
Feature activation+0.383
in
Token in
Feature activation+0.328
Rio
Token Rio
Feature activation+0.453
de
Token de
Feature activation+0.461
Janeiro
Token Janeiro
Feature activation+0.401
âĢĵ
Token âĢĵ
Feature activation+0.593
home
Token home
Feature activation+0.615
of
Token of
Feature activation+0.347
the
Token the
Feature activation+0.341
swimming
Token swimming
Feature activation+0.423
and
Token and
Feature activation+0.153
-
Token-
Feature activation+0.238
T
TokenT
Feature activation+0.303
yl
Tokenyl
Feature activation+0.233
a
Tokena
Feature activation+0.285
,
Token,
Feature activation+0.397
recently
Token recently
Feature activation+0.535
a
Token a
Feature activation+0.515
Dud
Token Dud
Feature activation+0.412
amel
Tokenamel
Feature activation+0.062
Conduct
Token Conduct
Feature activation+0.277
ing
Tokening
Feature activation+0.040
ass
Tokenass
Feature activation+0.262
li
Tokenli
Feature activation+0.474
90
Token 90
Feature activation+0.614
âĢ²
TokenâĢ²
Feature activation+0.613
),
Token),
Feature activation+0.456
Men
Token Men
Feature activation+0.524
j
Tokenj
Feature activation+0.583
iv
Tokeniv
Feature activation+0.493
ar
Tokenar
Feature activation+0.531
,
Token,
Feature activation+0.720
El
Token El
Feature activation+0.894

INTERVAL 0.401 - 0.501
CONTAINS 0.097%

at
Tokenat
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
Gir
Token Gir
Feature activation+0.181
one
Tokenone
Feature activation+0.169
(
Token (
Feature activation+0.427
R
TokenR
Feature activation+0.462
)
Token)
Feature activation+0.552
and
Token and
Feature activation+0.448
Mass
Token Mass
Feature activation+0.489
imil
Tokenimil
Feature activation+0.470
iano
Tokeniano
Feature activation+0.420
he
Tokenhe
Feature activation+0.249
uss
Tokenuss
Feature activation+0.385
er
Tokener
Feature activation+0.577
-
Token-
Feature activation+0.558
S
TokenS
Feature activation+0.640
chn
Tokenchn
Feature activation+0.464
ar
Tokenar
Feature activation+0.515
ren
Tokenren
Feature activation+0.590
berger
Tokenberger
Feature activation+0.608
(
Token (
Feature activation+0.607
F
TokenF
Feature activation+0.586
int
Tokenint
Feature activation+0.000
ech
Tokenech
Feature activation+0.000
Valley
Token Valley
Feature activation+0.060
Viz
Token Viz
Feature activation+0.049
ag
Tokenag
Feature activation+0.206
is
Token is
Feature activation+0.406
being
Token being
Feature activation+0.429
attended
Token attended
Feature activation+0.477
by
Token by
Feature activation+0.352
regional
Token regional
Feature activation+0.407
and
Token and
Feature activation+0.158
on
Token on
Feature activation+0.604
homes
Token homes
Feature activation+0.670
,
Token,
Feature activation+0.454
then
Token then
Feature activation+0.556
retreat
Token retreat
Feature activation+0.572
âĢĵ
Token âĢĵ
Feature activation+0.477
but
Token but
Feature activation+0.470
alerts
Token alerts
Feature activation+0.373
still
Token still
Feature activation+0.233
in
Token in
Feature activation+0.167
place
Token place
Feature activation+0.075
á
Tokená
Feature activation+0.102
ve
Tokenve
Feature activation+0.214
a
Tokena
Feature activation+0.173
hosts
Token hosts
Feature activation+0.451
an
Token an
Feature activation+0.512
International
Token International
Feature activation+0.449
Jazz
Token Jazz
Feature activation+0.431
festival
Token festival
Feature activation+0.443
by
Token by
Feature activation+0.347
the
Token the
Feature activation+0.374
Mediterranean
Token Mediterranean
Feature activation+0.320

INTERVAL 0.300 - 0.401
CONTAINS 0.161%

Emmanuel
Token Emmanuel
Feature activation+0.000
N
Token N
Feature activation+0.000
ch
Tokench
Feature activation+0.000
im
Tokenim
Feature activation+0.000
bi
Tokenbi
Feature activation+0.000
and
Token and
Feature activation+0.331
the
Token the
Feature activation+0.417
livestock
Token livestock
Feature activation+0.497
development
Token development
Feature activation+0.312
minister
Token minister
Feature activation+0.331
David
Token David
Feature activation+0.278
back
Token back
Feature activation+0.333
of
Token of
Feature activation+0.287
his
Token his
Feature activation+0.298
eyes
Token eyes
Feature activation+0.194
.
Token.
Feature activation+0.328
Ċ
TokenĊ
Feature activation+0.333
Ċ
TokenĊ
Feature activation+0.199
Police
TokenPolice
Feature activation+0.190
will
Token will
Feature activation+0.069
further
Token further
Feature activation+0.102
investigate
Token investigate
Feature activation+0.037
ine
Tokenine
Feature activation+0.000
ken
Tokenken
Feature activation+0.000
controls
Token controls
Feature activation+0.000
Alm
Token Alm
Feature activation+0.159
aza
Tokenaza
Feature activation+0.220
(
Token (
Feature activation+0.353
Arab
TokenArab
Feature activation+0.302
ic
Tokenic
Feature activation+0.222
for
Token for
Feature activation+0.254
âĢ
Token âĢ
Feature activation+0.439
ľ
Tokenľ
Feature activation+0.299
he
Token he
Feature activation+0.211
was
Token was
Feature activation+0.193
managing
Token managing
Feature activation+0.235
tens
Token tens
Feature activation+0.315
of
Token of
Feature activation+0.350
millions
Token millions
Feature activation+0.391
of
Token of
Feature activation+0.219
dollars
Token dollars
Feature activation+0.242
âĢ
TokenâĢ
Feature activation+0.117
Ļ
TokenĻ
Feature activation+0.008
worth
Token worth
Feature activation+0.063
R
Token R
Feature activation+0.528
oxy
Tokenoxy
Feature activation+0.411
Music
Token Music
Feature activation+0.580
-
Token -
Feature activation+0.454
Love
Token Love
Feature activation+0.464
Is
Token Is
Feature activation+0.394
The
Token The
Feature activation+0.305
Drug
Token Drug
Feature activation+0.284
Sean
Token Sean
Feature activation+0.112
Hayes
Token Hayes
Feature activation+0.000
&
Token &
Feature activation+0.000

INTERVAL 0.200 - 0.300
CONTAINS 0.289%

Trail
Token Trail
Feature activation+0.376
and
Token and
Feature activation+0.339
across
Token across
Feature activation+0.425
the
Token the
Feature activation+0.383
...
Token ...
Feature activation+0.499
more
Token more
Feature activation+0.238
Image
Token Image
Feature activation+0.268
1
Token 1
Feature activation+0.150
of
Token of
Feature activation+0.107
/
Token /
Feature activation+0.209
10
Token 10
Feature activation+0.032
erg
Tokenerg
Feature activation+0.078
uss
Tokenuss
Feature activation+0.180
on
Tokenon
Feature activation+0.065
and
Token and
Feature activation+0.113
John
Token John
Feature activation+0.321
Scott
Token Scott
Feature activation+0.233
make
Token make
Feature activation+0.162
up
Token up
Feature activation+0.099
the
Token the
Feature activation+0.067
top
Token top
Feature activation+0.083
five
Token five
Feature activation+0.045
,
Token,
Feature activation+0.237
in
Token in
Feature activation+0.242
the
Token the
Feature activation+0.241
same
Token same
Feature activation+0.209
manner
Token manner
Feature activation+0.164
they
Token they
Feature activation+0.212
pick
Token pick
Feature activation+0.178
a
Token a
Feature activation+0.105
flattering
Token flattering
Feature activation+0.100
hair
Token hair
Feature activation+0.000
style
Token style
Feature activation+0.000
s
Tokens
Feature activation+0.000
c
Token c
Feature activation+0.000
ela
Tokenela
Feature activation+0.000
,
Token,
Feature activation+0.079
il
Token il
Feature activation+0.162
a
Token a
Feature activation+0.229
l
Token l
Feature activation+0.186
u
Tokenu
Feature activation+0.278
des
Token des
Feature activation+0.296
g
Token g
Feature activation+0.367
ens
Tokenens
Feature activation+0.423
their
Token their
Feature activation+0.101
children
Token children
Feature activation+0.152
.
Token.
Feature activation+0.135
A
Token A
Feature activation+0.205
private
Token private
Feature activation+0.215
family
Token family
Feature activation+0.230
that
Token that
Feature activation+0.159
kept
Token kept
Feature activation+0.183
to
Token to
Feature activation+0.000
itself
Token itself
Feature activation+0.000
with
Token with
Feature activation+0.000

INTERVAL 0.100 - 0.200
CONTAINS 0.493%

major
Token major
Feature activation+0.112
junior
Token junior
Feature activation+0.058
rights
Token rights
Feature activation+0.126
before
Token before
Feature activation+0.185
the
Token the
Feature activation+0.198
January
Token January
Feature activation+0.171
trade
Token trade
Feature activation+0.212
deadline
Token deadline
Feature activation+0.153
last
Token last
Feature activation+0.051
season
Token season
Feature activation+0.000
.
Token.
Feature activation+0.000
agents
Token agents
Feature activation+0.217
suspected
Token suspected
Feature activation+0.221
of
Token of
Feature activation+0.091
being
Token being
Feature activation+0.130
under
Token under
Feature activation+0.161
the
Token the
Feature activation+0.173
influence
Token influence
Feature activation+0.238
while
Token while
Feature activation+0.064
striking
Token striking
Feature activation+0.095
a
Token a
Feature activation+0.000
White
Token White
Feature activation+0.000
care
Tokencare
Feature activation+0.277
âĢ
TokenâĢ
Feature activation+0.262
Ŀ
TokenĿ
Feature activation+0.006
,
Token,
Feature activation+0.203
cu
Token cu
Feature activation+0.089
ast
Token ast
Feature activation+0.157
a
Tokena
Feature activation+0.230
s
Token s
Feature activation+0.000
unt
Tokenunt
Feature activation+0.000
to
Token to
Feature activation+0.038
Å
TokenÅ
Feature activation+0.000
Ah
Token Ah
Feature activation+0.000
m
Tokenm
Feature activation+0.049
adi
Tokenadi
Feature activation+0.000
Muslims
Token Muslims
Feature activation+0.027
were
Token were
Feature activation+0.242
killed
Token killed
Feature activation+0.109
and
Token and
Feature activation+0.041
martial
Token martial
Feature activation+0.030
law
Token law
Feature activation+0.000
had
Token had
Feature activation+0.050
to
Token to
Feature activation+0.000
of
Token of
Feature activation+0.382
King
Token King
Feature activation+0.479
âĢ
TokenâĢ
Feature activation+0.530
Ļ
TokenĻ
Feature activation+0.351
s
Tokens
Feature activation+0.402
Landing
Token Landing
Feature activation+0.162
.
Token.
Feature activation+0.325
Ċ
TokenĊ
Feature activation+0.417
Ċ
TokenĊ
Feature activation+0.279
That
TokenThat
Feature activation+0.377
single
Token single
Feature activation+0.240

INTERVAL 0.000 - 0.100
CONTAINS 98.862%

and
Token and
Feature activation+0.000
placement
Token placement
Feature activation+0.000
of
Token of
Feature activation+0.000
meat
Token meat
Feature activation+0.000
in
Token in
Feature activation+0.000
your
Token your
Feature activation+0.000
suit
Token suit
Feature activation+0.000
cases
Tokencases
Feature activation+0.000
,"
Token,"
Feature activation+0.000
she
Token she
Feature activation+0.000
was
Token was
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
Can
TokenCan
Feature activation+0.000
you
Token you
Feature activation+0.000
imagine
Token imagine
Feature activation+0.000
the
Token the
Feature activation+0.000
reaction
Token reaction
Feature activation+0.000
if
Token if
Feature activation+0.000
we
Token we
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
.
Token.
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
sponsor
Token sponsor
Feature activation+0.000
Sen
Token Sen
Feature activation+0.000
.
Token.
Feature activation+0.000
Pat
Token Pat
Feature activation+0.000
To
Token To
Feature activation+0.000
ome
Tokenome
Feature activation+0.000
y
Tokeny
Feature activation+0.000
(
Token (
Feature activation+0.000
.
Token.
Feature activation+0.000
In
Token In
Feature activation+0.000
April
Token April
Feature activation+0.000
,
Token,
Feature activation+0.000
1915
Token 1915
Feature activation+0.000
,
Token,
Feature activation+0.000
he
Token he
Feature activation+0.000
was
Token was
Feature activation+0.000
dispatched
Token dispatched
Feature activation+0.000
to
Token to
Feature activation+0.000
take
Token take
Feature activation+0.000
about
Token about
Feature activation+0.000
being
Token being
Feature activation+0.000
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

BOTTOM ACTIVATIONS
MIN = 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
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
guidelines
Token guidelines
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
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
recommend
Token recommend
Feature activation+0.000
boss
Token boss
Feature activation+0.084
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
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
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
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
Feature activation+0.000
is
Token is
Feature activation+0.000
to
Token to
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.097
The
TokenThe
Feature activation+0.043
defence
Token defence
Feature activation+0.013
ministry
Token ministry
Feature activation+0.025
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+0.197
Ċ
TokenĊ
Feature activation+0.097
The
TokenThe
Feature activation+0.043
defence
Token defence
Feature activation+0.013
ministry
Token ministry
Feature activation+0.025
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
The
TokenThe
Feature activation+0.043
defence
Token defence
Feature activation+0.013
ministry
Token ministry
Feature activation+0.025
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+0.013
ministry
Token ministry
Feature activation+0.025
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
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+0.084
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
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+0.084
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
Defence
Token Defence
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+0.084
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+0.084
of
Token of
Feature activation+0.000
the
Token the
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+0.084
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
Organisation
Token Organisation
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+0.084
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
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.084
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
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
former
Token former
Feature activation+0.000
boss
Token boss
Feature activation+0.084
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
Organisation
Token Organisation
Feature activation+0.000
,
Token,
Feature activation+0.000
which
Token which
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+0.084
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
ministry
Token ministry
Feature activation+0.025
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
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

Top feature 4 in H1.4: (feature 6763)

TOP ACTIVATIONS
MAX = 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 DFA by src position
MAX = 0.690

atre
Tokenatre
Feature activation-0.158
Top resid features:
,
Token,
Feature activation-0.093
Top resid features:
a
Token a
Feature activation-0.057
Top resid features:
former
Token former
Feature activation-0.059
Top resid features:
boss
Token boss
Feature activation-0.171
Top resid features:
of
Token of
Feature activation+0.413
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Defence
Token Defence
Feature activation+0.000
Top resid features:
Research
Token Research
Feature activation+0.000
Top resid features:
&
Token &
Feature activation+0.000
Top resid features:
Development
Token Development
Feature activation+0.000
Top resid features:
A
Token A
Feature activation-0.220
Top resid features:
atre
Tokenatre
Feature activation-0.178
Top resid features:
,
Token,
Feature activation-0.136
Top resid features:
a
Token a
Feature activation-0.059
Top resid features:
former
Token former
Feature activation+0.012
Top resid features:
boss
Token boss
Feature activation+0.320
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Defence
Token Defence
Feature activation+0.000
Top resid features:
Research
Token Research
Feature activation+0.000
Top resid features:
&
Token &
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation-0.106
Top resid features:
.
Token.
Feature activation-0.106
Top resid features:
A
Token A
Feature activation-0.023
Top resid features:
atre
Tokenatre
Feature activation-0.187
Top resid features:
,
Token,
Feature activation-0.088
Top resid features:
a
Token a
Feature activation+0.308
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
boss
Token boss
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:
Defence
Token Defence
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.101
Top resid features:
A
Token A
Feature activation-0.199
Top resid features:
atre
Tokenatre
Feature activation-0.187
Top resid features:
,
Token,
Feature activation-0.129
Top resid features:
a
Token a
Feature activation+0.018
Top resid features:
former
Token former
Feature activation+0.690
Top resid features:
boss
Token boss
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:
Defence
Token Defence
Feature activation+0.000
Top resid features:
Research
Token Research
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.171
Top resid features:
rik
Tokenrik
Feature activation-0.053
Top resid features:
ar
Tokenar
Feature activation-0.140
Top resid features:
said
Token said
Feature activation-0.208
Top resid features:
Saturday
Token Saturday
Feature activation-0.239
Top resid features:
.
Token.
Feature activation+0.003
Top resid features:
Ċ
TokenĊ
Feature activation-0.279
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation-0.290
Top resid features:
rik
Tokenrik
Feature activation-0.077
Top resid features:
ar
Tokenar
Feature activation-0.165
Top resid features:
said
Token said
Feature activation-0.189
Top resid features:
Saturday
Token Saturday
Feature activation-0.258
Top resid features:
.
Token.
Feature activation+0.053
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:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.172
Top resid features:
Saturday
Token Saturday
Feature activation-0.195
Top resid features:
.
Token.
Feature activation-0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.265
Top resid features:
Ċ
TokenĊ
Feature activation-0.281
Top resid features:
The
TokenThe
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.178
Top resid features:
Saturday
Token Saturday
Feature activation-0.211
Top resid features:
.
Token.
Feature activation-0.065
Top resid features:
Ċ
TokenĊ
Feature activation-0.239
Top resid features:
Ċ
TokenĊ
Feature activation-0.269
Top resid features:
The
TokenThe
Feature activation+0.348
Top resid features:
defence
Token defence
Feature activation+0.000
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation-0.115
Top resid features:
headed
Token headed
Feature activation-0.180
Top resid features:
by
Token by
Feature activation-0.175
Top resid features:
V
Token V
Feature activation+0.016
Top resid features:
.
Token.
Feature activation-0.089
Top resid features:
K
TokenK
Feature activation+0.470
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.031
Top resid features:
Saturday
Token Saturday
Feature activation-0.075
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Ċ
TokenĊ
Feature activation-0.101
Top resid features:
Ċ
TokenĊ
Feature activation-0.111
Top resid features:
The
TokenThe
Feature activation+0.029
Top resid features:
defence
Token defence
Feature activation-0.089
Top resid features:
ministry
Token ministry
Feature activation-0.084
Top resid features:
committee
Token committee
Feature activation-0.041
Top resid features:
headed
Token headed
Feature activation-0.138
Top resid features:
by
Token by
Feature activation-0.062
Top resid features:
The
TokenThe
Feature activation-0.108
Top resid features:
defence
Token defence
Feature activation-0.136
Top resid features:
ministry
Token ministry
Feature activation-0.129
Top resid features:
committee
Token committee
Feature activation-0.111
Top resid features:
headed
Token headed
Feature activation-0.088
Top resid features:
by
Token by
Feature activation+0.571
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
defence
Token defence
Feature activation-0.138
Top resid features:
ministry
Token ministry
Feature activation-0.131
Top resid features:
committee
Token committee
Feature activation-0.129
Top resid features:
headed
Token headed
Feature activation-0.202
Top resid features:
by
Token by
Feature activation-0.146
Top resid features:
V
Token V
Feature activation+0.546
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
A
Token A
Feature activation+0.000
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
by
Token by
Feature activation-0.124
Top resid features:
V
Token V
Feature activation-0.120
Top resid features:
.
Token.
Feature activation-0.085
Top resid features:
K
TokenK
Feature activation-0.060
Top resid features:
.
Token.
Feature activation-0.121
Top resid features:
A
Token A
Feature activation+0.275
Top resid features:
atre
Tokenatre
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
boss
Token boss
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.029
Top resid features:
Saturday
Token Saturday
Feature activation-0.066
Top resid features:
.
Token.
Feature activation+0.016
Top resid features:
Ċ
TokenĊ
Feature activation-0.087
Top resid features:
Ċ
TokenĊ
Feature activation-0.095
Top resid features:
The
TokenThe
Feature activation+0.042
Top resid features:
defence
Token defence
Feature activation-0.082
Top resid features:
ministry
Token ministry
Feature activation-0.067
Top resid features:
committee
Token committee
Feature activation-0.038
Top resid features:
headed
Token headed
Feature activation-0.126
Top resid features:
by
Token by
Feature activation-0.046
Top resid features:
V
Token V
Feature activation-0.107
Top resid features:
.
Token.
Feature activation-0.086
Top resid features:
K
TokenK
Feature activation+0.021
Top resid features:
.
Token.
Feature activation-0.120
Top resid features:
A
Token A
Feature activation-0.257
Top resid features:
atre
Tokenatre
Feature activation+0.110
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
former
Token former
Feature activation+0.000
Top resid features:
boss
Token boss
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
said
Token said
Feature activation-0.015
Top resid features:
Saturday
Token Saturday
Feature activation-0.050
Top resid features:
.
Token.
Feature activation+0.019
Top resid features:
Ċ
TokenĊ
Feature activation-0.046
Top resid features:
Ċ
TokenĊ
Feature activation-0.050
Top resid features:
The
TokenThe
Feature activation+0.033
Top resid features:
defence
Token defence
Feature activation-0.077
Top resid features:
ministry
Token ministry
Feature activation-0.062
Top resid features:
committee
Token committee
Feature activation-0.045
Top resid features:
headed
Token headed
Feature activation-0.081
Top resid features:
by
Token by
Feature activation-0.010
Top resid features:
Ċ
TokenĊ
Feature activation-0.208
Top resid features:
The
TokenThe
Feature activation-0.106
Top resid features:
defence
Token defence
Feature activation-0.110
Top resid features:
ministry
Token ministry
Feature activation-0.128
Top resid features:
committee
Token committee
Feature activation-0.049
Top resid features:
headed
Token headed
Feature activation+0.342
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.198
Top resid features:
Ċ
TokenĊ
Feature activation-0.227
Top resid features:
The
TokenThe
Feature activation-0.106
Top resid features:
defence
Token defence
Feature activation-0.104
Top resid features:
ministry
Token ministry
Feature activation-0.073
Top resid features:
committee
Token committee
Feature activation+0.436
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
K
TokenK
Feature activation+0.000
Top resid features:
Saturday
Token Saturday
Feature activation-0.208
Top resid features:
.
Token.
Feature activation-0.061
Top resid features:
Ċ
TokenĊ
Feature activation-0.222
Top resid features:
Ċ
TokenĊ
Feature activation-0.260
Top resid features:
The
TokenThe
Feature activation-0.132
Top resid features:
defence
Token defence
Feature activation+0.606
Top resid features:
ministry
Token ministry
Feature activation+0.000
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.013
Top resid features:
Ċ
TokenĊ
Feature activation-0.212
Top resid features:
Ċ
TokenĊ
Feature activation-0.238
Top resid features:
The
TokenThe
Feature activation-0.119
Top resid features:
defence
Token defence
Feature activation-0.020
Top resid features:
ministry
Token ministry
Feature activation+0.345
Top resid features:
committee
Token committee
Feature activation+0.000
Top resid features:
headed
Token headed
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
V
Token V
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.06

Head 1: 0.09

Head 2: 0.15

Head 3: 0.06

Head 4: 0.14

Head 5: 0.06

Head 6: 0.06

Head 7: 0.07

Head 8: 0.06

Head 9: 0.06

Head 10: 0.11

Head 11: 0.07

Positive logits

"$:/1.11

>[1.07

bour1.00

vulgar0.98

sy0.98

migrants0.96

param0.96

principle0.96

ogeneity0.96

extant0.96

conson0.95

malice0.95

nic0.95

apologies0.95

spe0.94

lingu0.94

precedent0.94

fundamentally0.94

%);0.93

gener0.93

Negative logits

senal-1.39

andem-1.18

agle-1.17

Booster-1.04

wagon-1.04

TOP-1.03

proxy-1.02

zai-1.01

Wally-1.01

boost-1.01

Reverse-1.01

hawk-1.00

vest-0.99

EMENT-0.98

fest-0.98

yahoo-0.98

icer-0.98

cha-0.97

iosis-0.97

jer-0.97

INTERVAL 0.000 - 0.000
CONTAINS 100.000%

ctions
Tokenctions
Feature activation+0.000
like
Token like
Feature activation+0.000
fl
Token fl
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
seed
Token seed
Feature activation+0.000
hair
Token hair
Feature activation+0.000
gel
Token gel
Feature activation+0.000
(
Token (
Feature activation+0.000
it
Tokenit
Feature activation+0.000
gun
Token gun
Feature activation+0.000
ked
Tokenked
Feature activation+0.000
response
Token response
Feature activation+0.000
to
Token to
Feature activation+0.000
the
Token the
Feature activation+0.000
Dutch
Token Dutch
Feature activation+0.000
referendum
Token referendum
Feature activation+0.000
today
Token today
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
IG
TokenIG
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
T
Token T
Feature activation+0.000
Nashville
Token Nashville
Feature activation+0.000
is
Token is
Feature activation+0.000
the
Token the
Feature activation+0.000
coolest
Token coolest
Feature activation+0.000
city
Token city
Feature activation+0.000
in
Token in
Feature activation+0.000
America
Token America
Feature activation+0.000
.
Token.
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
chain
Token chain
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
which
Token which
Feature activation+0.000
has
Token has
Feature activation+0.000
10
Token 10
Feature activation+0.000
locations
Token locations
Feature activation+0.000
in
Token in
Feature activation+0.000
Southern
Token Southern
Feature activation+0.000
California
Token California
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.000
during
Token during
Feature activation+0.000
new
Token new
Feature activation+0.000
low
Token low
Feature activation+0.000
including
Token including
Feature activation+0.000
holidays
Token holidays
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
hourly
Token hourly
Feature activation+0.000
breakdown
Token breakdown
Feature activation+0.000
is
Token is
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 H1.4: (feature 2795)

TOP ACTIVATIONS
MAX = 0.932

y
Tokeny
Feature activation+0.000
and
Token and
Feature activation+0.931
M
Token M
Feature activation+0.226
amb
Tokenamb
Feature activation+0.139
alam
Tokenalam
Feature activation+0.000
and
Token and
Feature activation+0.932
other
Token other
Feature activation+0.478
western
Token western
Feature activation+0.054
parts
Token parts
Feature activation+0.048
of
Token of
Feature activation+0.389
the
Token the
Feature activation+0.277
et
Tokenet
Feature activation+0.000
,
Token,
Feature activation+0.711
Gu
Token Gu
Feature activation+0.160
ind
Tokenind
Feature activation+0.000
y
Tokeny
Feature activation+0.000
and
Token and
Feature activation+0.931
M
Token M
Feature activation+0.226
amb
Tokenamb
Feature activation+0.139
alam
Tokenalam
Feature activation+0.000
and
Token and
Feature activation+0.932
other
Token other
Feature activation+0.478
ets
Tokenets
Feature activation+0.168
ui
Tokenui
Feature activation+0.000
Shim
Token Shim
Feature activation+0.119
ash
Tokenash
Feature activation+0.015
ita
Tokenita
Feature activation+0.000
(
Token (
Feature activation+0.928
Yu
TokenYu
Feature activation+0.000
-
Token-
Feature activation+0.674
S
TokenS
Feature activation+0.274
ibu
Tokenibu
Feature activation+0.000
)
Token)
Feature activation+0.707
o
Tokeno
Feature activation+0.000
,
Token,
Feature activation+0.667
Pal
Token Pal
Feature activation+0.066
er
Tokener
Feature activation+0.132
mo
Tokenmo
Feature activation+0.127
,
Token,
Feature activation+0.801
Ud
Token Ud
Feature activation+0.000
inese
Tokeninese
Feature activation+0.000
,
Token,
Feature activation+0.742
and
Token and
Feature activation+0.663
Ver
Token Ver
Feature activation+0.020
Mik
Token Mik
Feature activation+0.000
ko
Tokenko
Feature activation+0.077
Kod
Token Kod
Feature activation+0.000
iso
Tokeniso
Feature activation+0.000
ja
Tokenja
Feature activation+0.000
,
Token,
Feature activation+0.797
founders
Token founders
Feature activation+0.232
of
Token of
Feature activation+0.547
âĢ
Token âĢ
Feature activation+0.115
ľ
Tokenľ
Feature activation+0.046
Cl
TokenCl
Feature activation+0.000
Patricia
Token Patricia
Feature activation+0.000
Laf
Token Laf
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
ll
Tokenll
Feature activation+0.029
ve
Tokenve
Feature activation+0.055
of
Token of
Feature activation+0.778
The
Token The
Feature activation+0.554
Tro
Token Tro
Feature activation+0.156
th
Tokenth
Feature activation+0.131
,
Token,
Feature activation+0.716
he
Token he
Feature activation+0.287
)
Token)
Feature activation+0.722
and
Token and
Feature activation+0.692
Sonia
Token Sonia
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
anche
Tokenanche
Feature activation+0.056
(
Token (
Feature activation+0.753
vo
Tokenvo
Feature activation+0.000
iced
Tokeniced
Feature activation+0.097
by
Token by
Feature activation+0.558
As
Token As
Feature activation+0.232
ami
Tokenami
Feature activation+0.000
er
Tokener
Feature activation+0.132
mo
Tokenmo
Feature activation+0.127
,
Token,
Feature activation+0.801
Ud
Token Ud
Feature activation+0.000
inese
Tokeninese
Feature activation+0.000
,
Token,
Feature activation+0.742
and
Token and
Feature activation+0.663
Ver
Token Ver
Feature activation+0.020
ona
Tokenona
Feature activation+0.000
.
Token.
Feature activation+0.586
Not
Token Not
Feature activation+0.344
the
Token the
Feature activation+0.390
B
Token B
Feature activation+0.074
aj
Tokenaj
Feature activation+0.000
aj
Tokenaj
Feature activation+0.000
s
Tokens
Feature activation+0.227
)
Token)
Feature activation+0.736
have
Token have
Feature activation+0.269
been
Token been
Feature activation+0.163
merged
Token merged
Feature activation+0.000
to
Token to
Feature activation+0.263
ensure
Token ensure
Feature activation+0.000
,
Token,
Feature activation+0.602
Jo
Token Jo
Feature activation+0.000
S
Token S
Feature activation+0.103
iff
Tokeniff
Feature activation+0.000
ert
Tokenert
Feature activation+0.000
,
Token,
Feature activation+0.729
J
Token J
Feature activation+0.193
oc
Tokenoc
Feature activation+0.000
hen
Tokenhen
Feature activation+0.190
R
Token R
Feature activation+0.371
ind
Tokenind
Feature activation+0.179
Moj
Token Moj
Feature activation+0.000
on
Tokenon
Feature activation+0.167
of
Token of
Feature activation+0.633
Chron
Token Chron
Feature activation+0.005
ode
Tokenode
Feature activation+0.000
,
Token,
Feature activation+0.727
the
Tokenthe
Feature activation+0.503
same
Token same
Feature activation+0.391
specialist
Token specialist
Feature activation+0.029
responsible
Token responsible
Feature activation+0.055
for
Token for
Feature activation+0.281
Pe
Token Pe
Feature activation+0.000
ñ
Tokenñ
Feature activation+0.000
ÃŃ
TokenÃŃ
Feature activation+0.000
sc
Tokensc
Feature activation+0.000
ola
Tokenola
Feature activation+0.082
,
Token,
Feature activation+0.727
Spain
Token Spain
Feature activation+0.149
set
Token set
Feature activation+0.166
where
Token where
Feature activation+0.233
all
Token all
Feature activation+0.223
Me
Token Me
Feature activation+0.000
11
Token 11
Feature activation+0.493
-
Token-
Feature activation+0.535
Mal
Token Mal
Feature activation+0.205
z
Tokenz
Feature activation+0.000
ieu
Tokenieu
Feature activation+0.110
,
Token,
Feature activation+0.725
10
Token 10
Feature activation+0.607
-
Token-
Feature activation+0.595
Trin
Token Trin
Feature activation+0.000
h
Tokenh
Feature activation+0.000
-
Token-
Feature activation+0.699
im
Tokenim
Feature activation+0.000
ni
Tokenni
Feature activation+0.000
K
Token K
Feature activation+0.011
any
Tokenany
Feature activation+0.000
oro
Tokenoro
Feature activation+0.000
and
Token and
Feature activation+0.722
founder
Token founder
Feature activation+0.130
and
Token and
Feature activation+0.482
Editor
Token Editor
Feature activation+0.000
-
Token-
Feature activation+0.259
in
Tokenin
Feature activation+0.000
by
Token by
Feature activation+0.477
Sa
Token Sa
Feature activation+0.000
ori
Tokenori
Feature activation+0.000
Hay
Token Hay
Feature activation+0.000
ami
Tokenami
Feature activation+0.000
)
Token)
Feature activation+0.722
and
Token and
Feature activation+0.692
Sonia
Token Sonia
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
anche
Tokenanche
Feature activation+0.056
(
Token (
Feature activation+0.753
ham
Tokenham
Feature activation+0.000
bra
Tokenbra
Feature activation+0.000
N
Token N
Feature activation+0.046
ie
Tokenie
Feature activation+0.000
vas
Tokenvas
Feature activation+0.043
,
Token,
Feature activation+0.721
of
Token of
Feature activation+0.712
Spain
Token Spain
Feature activation+0.293
,
Token,
Feature activation+0.539
were
Token were
Feature activation+0.156
also
Token also
Feature activation+0.034
B
TokenB
Feature activation+0.000
oun
Tokenoun
Feature activation+0.000
cy
Tokency
Feature activation+0.000
Ch
Token Ch
Feature activation+0.254
airs
Tokenairs
Feature activation+0.212
:
Token:
Feature activation+0.720
While
Token While
Feature activation+0.402
moms
Token moms
Feature activation+0.000
also
Token also
Feature activation+0.000
swear
Token swear
Feature activation+0.000
that
Token that
Feature activation+0.000
ve
Tokenve
Feature activation+0.055
of
Token of
Feature activation+0.778
The
Token The
Feature activation+0.554
Tro
Token Tro
Feature activation+0.156
th
Tokenth
Feature activation+0.131
,
Token,
Feature activation+0.716
he
Token he
Feature activation+0.287
submitted
Token submitted
Feature activation+0.135
a
Token a
Feature activation+0.261
second
Token second
Feature activation+0.063
application
Token application
Feature activation+0.000
al
Token al
Feature activation+0.000
-
Token-
Feature activation+0.273
Sh
TokenSh
Feature activation+0.000
amm
Tokenamm
Feature activation+0.000
ari
Tokenari
Feature activation+0.000
,
Token,
Feature activation+0.716
the
Token the
Feature activation+0.488
head
Token head
Feature activation+0.130
of
Token of
Feature activation+0.445
the
Token the
Feature activation+0.308
provincial
Token provincial
Feature activation+0.000
.
Token.
Feature activation+0.228
P
Token P
Feature activation+0.000
ochem
Tokenochem
Feature activation+0.000
uch
Tokenuch
Feature activation+0.000
ka
Tokenka
Feature activation+0.000
(
Token (
Feature activation+0.715
Russian
TokenRussian
Feature activation+0.043
)
Token)
Feature activation+0.453
Ċ
TokenĊ
Feature activation+0.277
Ċ
TokenĊ
Feature activation+0.167
5
Token5
Feature activation+0.000

Top DFA by src position
MAX = 0.427

y
Tokeny
Feature activation+0.134
Top resid features:
and
Token and
Feature activation+0.158
Top resid features:
M
Token M
Feature activation+0.135
Top resid features:
amb
Tokenamb
Feature activation+0.123
Top resid features:
alam
Tokenalam
Feature activation+0.186
Top resid features:
and
Token and
Feature activation+0.207
Top resid features:
other
Token other
Feature activation+0.000
Top resid features:
western
Token western
Feature activation+0.000
Top resid features:
parts
Token parts
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.218
Top resid features:
left
Token left
Feature activation+0.022
Top resid features:
Ad
Token Ad
Feature activation+0.030
Top resid features:
y
Tokeny
Feature activation+0.028
Top resid features:
ar
Tokenar
Feature activation+0.035
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
ets
Tokenets
Feature activation+0.136
Top resid features:
ui
Tokenui
Feature activation+0.146
Top resid features:
Shim
Token Shim
Feature activation+0.117
Top resid features:
ash
Tokenash
Feature activation+0.201
Top resid features:
ita
Tokenita
Feature activation+0.216
Top resid features:
(
Token (
Feature activation+0.427
Top resid features:
Yu
TokenYu
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
S
TokenS
Feature activation+0.000
Top resid features:
ibu
Tokenibu
Feature activation+0.000
Top resid features:
)
Token)
Feature activation+0.000
Top resid features:
o
Tokeno
Feature activation+0.142
Top resid features:
,
Token,
Feature activation+0.169
Top resid features:
Pal
Token Pal
Feature activation+0.143
Top resid features:
er
Tokener
Feature activation+0.159
Top resid features:
mo
Tokenmo
Feature activation+0.194
Top resid features:
,
Token,
Feature activation+0.224
Top resid features:
Ud
Token Ud
Feature activation+0.000
Top resid features:
inese
Tokeninese
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:
Ver
Token Ver
Feature activation+0.000
Top resid features:
Mik
Token Mik
Feature activation+0.135
Top resid features:
ko
Tokenko
Feature activation+0.118
Top resid features:
Kod
Token Kod
Feature activation+0.072
Top resid features:
iso
Tokeniso
Feature activation+0.164
Top resid features:
ja
Tokenja
Feature activation+0.191
Top resid features:
,
Token,
Feature activation+0.262
Top resid features:
founders
Token founders
Feature activation+0.000
Top resid features:
of
Token of
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:
Cl
TokenCl
Feature activation+0.000
Top resid features:
Patricia
Token Patricia
Feature activation+0.133
Top resid features:
Laf
Token Laf
Feature activation+0.118
Top resid features:
ay
Tokenay
Feature activation+0.161
Top resid features:
ll
Tokenll
Feature activation+0.130
Top resid features:
ve
Tokenve
Feature activation+0.192
Top resid features:
of
Token of
Feature activation+0.237
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Tro
Token Tro
Feature activation+0.000
Top resid features:
th
Tokenth
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
Kir
Token Kir
Feature activation+0.046
Top resid features:
ika
Tokenika
Feature activation+0.050
Top resid features:
T
Token T
Feature activation+0.029
Top resid features:
owa
Tokenowa
Feature activation+0.044
Top resid features:
Alma
Token Alma
Feature activation+0.065
Top resid features:
(
Token (
Feature activation+0.254
Top resid features:
vo
Tokenvo
Feature activation+0.057
Top resid features:
iced
Tokeniced
Feature activation+0.029
Top resid features:
by
Token by
Feature activation+0.035
Top resid features:
Sa
Token Sa
Feature activation+0.111
Top resid features:
ori
Tokenori
Feature activation+0.085
Top resid features:
er
Tokener
Feature activation+0.108
Top resid features:
mo
Tokenmo
Feature activation+0.128
Top resid features:
,
Token,
Feature activation+0.172
Top resid features:
Ud
Token Ud
Feature activation+0.114
Top resid features:
inese
Tokeninese
Feature activation+0.145
Top resid features:
,
Token,
Feature activation+0.235
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ver
Token Ver
Feature activation+0.000
Top resid features:
ona
Tokenona
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Not
Token Not
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.072
Top resid features:
B
Token B
Feature activation+0.098
Top resid features:
aj
Tokenaj
Feature activation+0.187
Top resid features:
aj
Tokenaj
Feature activation+0.181
Top resid features:
s
Tokens
Feature activation+0.123
Top resid features:
)
Token)
Feature activation+0.218
Top resid features:
have
Token have
Feature activation+0.000
Top resid features:
been
Token been
Feature activation+0.000
Top resid features:
merged
Token merged
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
ensure
Token ensure
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.151
Top resid features:
Jo
Token Jo
Feature activation+0.121
Top resid features:
S
Token S
Feature activation+0.084
Top resid features:
iff
Tokeniff
Feature activation+0.123
Top resid features:
ert
Tokenert
Feature activation+0.156
Top resid features:
,
Token,
Feature activation+0.248
Top resid features:
J
Token J
Feature activation+0.000
Top resid features:
oc
Tokenoc
Feature activation+0.000
Top resid features:
hen
Tokenhen
Feature activation+0.000
Top resid features:
R
Token R
Feature activation+0.000
Top resid features:
ind
Tokenind
Feature activation+0.000
Top resid features:
Moj
Token Moj
Feature activation+0.110
Top resid features:
on
Tokenon
Feature activation+0.138
Top resid features:
of
Token of
Feature activation+0.121
Top resid features:
Chron
Token Chron
Feature activation+0.097
Top resid features:
ode
Tokenode
Feature activation+0.157
Top resid features:
,
Token,
Feature activation+0.297
Top resid features:
the
Tokenthe
Feature activation+0.000
Top resid features:
same
Token same
Feature activation+0.000
Top resid features:
specialist
Token specialist
Feature activation+0.000
Top resid features:
responsible
Token responsible
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.000
Top resid features:
Pe
Token Pe
Feature activation+0.133
Top resid features:
ñ
Tokenñ
Feature activation+0.122
Top resid features:
ÃŃ
TokenÃŃ
Feature activation+0.174
Top resid features:
sc
Tokensc
Feature activation+0.128
Top resid features:
ola
Tokenola
Feature activation+0.204
Top resid features:
,
Token,
Feature activation+0.260
Top resid features:
Spain
Token Spain
Feature activation+0.000
Top resid features:
set
Token set
Feature activation+0.000
Top resid features:
where
Token where
Feature activation+0.000
Top resid features:
all
Token all
Feature activation+0.000
Top resid features:
Me
Token Me
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.107
Top resid features:
11
Token 11
Feature activation+0.016
Top resid features:
-
Token-
Feature activation+0.066
Top resid features:
Mal
Token Mal
Feature activation+0.175
Top resid features:
z
Tokenz
Feature activation+0.168
Top resid features:
ieu
Tokenieu
Feature activation+0.219
Top resid features:
,
Token,
Feature activation+0.178
Top resid features:
10
Token 10
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
Trin
Token Trin
Feature activation+0.000
Top resid features:
h
Tokenh
Feature activation+0.000
Top resid features:
Mus
Token Mus
Feature activation+0.110
Top resid features:
im
Tokenim
Feature activation+0.136
Top resid features:
ni
Tokenni
Feature activation+0.149
Top resid features:
K
Token K
Feature activation+0.141
Top resid features:
any
Tokenany
Feature activation+0.222
Top resid features:
oro
Tokenoro
Feature activation+0.235
Top resid features:
and
Token and
Feature activation+0.231
Top resid features:
founder
Token founder
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Editor
Token Editor
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
by
Token by
Feature activation+0.064
Top resid features:
Sa
Token Sa
Feature activation+0.170
Top resid features:
ori
Tokenori
Feature activation+0.135
Top resid features:
Hay
Token Hay
Feature activation+0.133
Top resid features:
ami
Tokenami
Feature activation+0.151
Top resid features:
)
Token)
Feature activation+0.252
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Sonia
Token Sonia
Feature activation+0.000
Top resid features:
Bl
Token Bl
Feature activation+0.000
Top resid features:
anche
Tokenanche
Feature activation+0.000
Top resid features:
(
Token (
Feature activation+0.000
Top resid features:
ham
Tokenham
Feature activation+0.129
Top resid features:
bra
Tokenbra
Feature activation+0.116
Top resid features:
N
Token N
Feature activation+0.109
Top resid features:
ie
Tokenie
Feature activation+0.189
Top resid features:
vas
Tokenvas
Feature activation+0.182
Top resid features:
,
Token,
Feature activation+0.230
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Spain
Token Spain
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
were
Token were
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
B
TokenB
Feature activation+0.105
Top resid features:
oun
Tokenoun
Feature activation+0.109
Top resid features:
cy
Tokency
Feature activation+0.128
Top resid features:
Ch
Token Ch
Feature activation+0.175
Top resid features:
airs
Tokenairs
Feature activation+0.188
Top resid features:
:
Token:
Feature activation+0.287
Top resid features:
While
Token While
Feature activation+0.000
Top resid features:
moms
Token moms
Feature activation+0.000
Top resid features:
also
Token also
Feature activation+0.000
Top resid features:
swear
Token swear
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
ve
Tokenve
Feature activation+0.103
Top resid features:
of
Token of
Feature activation+0.078
Top resid features:
The
Token The
Feature activation+0.128
Top resid features:
Tro
Token Tro
Feature activation+0.080
Top resid features:
th
Tokenth
Feature activation+0.139
Top resid features:
,
Token,
Feature activation+0.310
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
submitted
Token submitted
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
second
Token second
Feature activation+0.000
Top resid features:
application
Token application
Feature activation+0.000
Top resid features:
al
Token al
Feature activation+0.067
Top resid features:
-
Token-
Feature activation+0.083
Top resid features:
Sh
TokenSh
Feature activation+0.135
Top resid features:
amm
Tokenamm
Feature activation+0.125
Top resid features:
ari
Tokenari
Feature activation+0.235
Top resid features:
,
Token,
Feature activation+0.272
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
head
Token head
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:
provincial
Token provincial
Feature activation+0.000
Top resid features:
4
Token4
Feature activation+0.074
Top resid features:
.
Token.
Feature activation+0.087
Top resid features:
P
Token P
Feature activation+0.109
Top resid features:
ochem
Tokenochem
Feature activation+0.099
Top resid features:
uch
Tokenuch
Feature activation+0.247
Top resid features:
ka
Tokenka
Feature activation+0.305
Top resid features:
(
Token (
Feature activation+0.132
Top resid features:
Russian
TokenRussian
Feature activation+0.000
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:

Decoder Weights Distribution

Head 0: 0.08

Head 1: 0.14

Head 2: 0.13

Head 3: 0.06

Head 4: 0.14

Head 5: 0.07

Head 6: 0.04

Head 7: 0.07

Head 8: 0.04

Head 9: 0.03

Head 10: 0.07

Head 11: 0.12

Positive logits

LLP1.77

ivas1.76

Vaj1.71

fecture1.67

ryu1.65

Vert1.63

Vert1.58

tsky1.57

Beaut1.56

hots1.54

atars1.53

osa1.52

Unt1.52

SourceFile1.51

Sty1.49

ji1.48

��1.48

yi1.48

��1.47

Founder1.46

Negative logits

hindsight-1.53

increments-1.53

inarily-1.38

debugging-1.37

ditch-1.37

mistakes-1.35

rpm-1.35

FIX-1.33

deficit-1.33

faulty-1.32

blindly-1.30

stupid-1.28

appropriations-1.28

verbal-1.27

wiser-1.27

payoff-1.27

warnings-1.27

gasp-1.26

exemptions-1.26

deductions-1.26

INTERVAL 0.839 - 0.932
CONTAINS 0.000%

et
Tokenet
Feature activation+0.000
,
Token,
Feature activation+0.711
Gu
Token Gu
Feature activation+0.160
ind
Tokenind
Feature activation+0.000
y
Tokeny
Feature activation+0.000
and
Token and
Feature activation+0.931
M
Token M
Feature activation+0.226
amb
Tokenamb
Feature activation+0.139
alam
Tokenalam
Feature activation+0.000
and
Token and
Feature activation+0.932
other
Token other
Feature activation+0.478
y
Tokeny
Feature activation+0.000
and
Token and
Feature activation+0.931
M
Token M
Feature activation+0.226
amb
Tokenamb
Feature activation+0.139
alam
Tokenalam
Feature activation+0.000
and
Token and
Feature activation+0.932
other
Token other
Feature activation+0.478
western
Token western
Feature activation+0.054
parts
Token parts
Feature activation+0.048
of
Token of
Feature activation+0.389
the
Token the
Feature activation+0.277
ets
Tokenets
Feature activation+0.168
ui
Tokenui
Feature activation+0.000
Shim
Token Shim
Feature activation+0.119
ash
Tokenash
Feature activation+0.015
ita
Tokenita
Feature activation+0.000
(
Token (
Feature activation+0.928
Yu
TokenYu
Feature activation+0.000
-
Token-
Feature activation+0.674
S
TokenS
Feature activation+0.274
ibu
Tokenibu
Feature activation+0.000
)
Token)
Feature activation+0.707

INTERVAL 0.746 - 0.839
CONTAINS 0.001%

o
Tokeno
Feature activation+0.000
,
Token,
Feature activation+0.667
Pal
Token Pal
Feature activation+0.066
er
Tokener
Feature activation+0.132
mo
Tokenmo
Feature activation+0.127
,
Token,
Feature activation+0.801
Ud
Token Ud
Feature activation+0.000
inese
Tokeninese
Feature activation+0.000
,
Token,
Feature activation+0.742
and
Token and
Feature activation+0.663
Ver
Token Ver
Feature activation+0.020
Mik
Token Mik
Feature activation+0.000
ko
Tokenko
Feature activation+0.077
Kod
Token Kod
Feature activation+0.000
iso
Tokeniso
Feature activation+0.000
ja
Tokenja
Feature activation+0.000
,
Token,
Feature activation+0.797
founders
Token founders
Feature activation+0.232
of
Token of
Feature activation+0.547
âĢ
Token âĢ
Feature activation+0.115
ľ
Tokenľ
Feature activation+0.046
Cl
TokenCl
Feature activation+0.000
Patricia
Token Patricia
Feature activation+0.000
Laf
Token Laf
Feature activation+0.000
ay
Tokenay
Feature activation+0.000
ll
Tokenll
Feature activation+0.029
ve
Tokenve
Feature activation+0.055
of
Token of
Feature activation+0.778
The
Token The
Feature activation+0.554
Tro
Token Tro
Feature activation+0.156
th
Tokenth
Feature activation+0.131
,
Token,
Feature activation+0.716
he
Token he
Feature activation+0.287
)
Token)
Feature activation+0.722
and
Token and
Feature activation+0.692
Sonia
Token Sonia
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
anche
Tokenanche
Feature activation+0.056
(
Token (
Feature activation+0.753
vo
Tokenvo
Feature activation+0.000
iced
Tokeniced
Feature activation+0.097
by
Token by
Feature activation+0.558
As
Token As
Feature activation+0.232
ami
Tokenami
Feature activation+0.000

INTERVAL 0.652 - 0.746
CONTAINS 0.004%

and
Token and
Feature activation+0.430
Tal
Token Tal
Feature activation+0.000
im
Tokenim
Feature activation+0.000
h
Tokenh
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
,
Token,
Feature activation+0.654
all
Token all
Feature activation+0.392
popular
Token popular
Feature activation+0.000
hang
Token hang
Feature activation+0.000
-
Token-
Feature activation+0.124
out
Tokenout
Feature activation+0.000
mo
Tokenmo
Feature activation+0.127
,
Token,
Feature activation+0.801
Ud
Token Ud
Feature activation+0.000
inese
Tokeninese
Feature activation+0.000
,
Token,
Feature activation+0.742
and
Token and
Feature activation+0.663
Ver
Token Ver
Feature activation+0.020
ona
Tokenona
Feature activation+0.000
.
Token.
Feature activation+0.586
Not
Token Not
Feature activation+0.344
great
Token great
Feature activation+0.111
Prince
Token Prince
Feature activation+0.000
F
Token F
Feature activation+0.000
um
Tokenum
Feature activation+0.000
ih
Tokenih
Feature activation+0.000
ito
Tokenito
Feature activation+0.000
,
Token,
Feature activation+0.700
whose
Token whose
Feature activation+0.358
official
Token official
Feature activation+0.000
title
Token title
Feature activation+0.000
is
Token is
Feature activation+0.055
Prince
Token Prince
Feature activation+0.000
Moj
Token Moj
Feature activation+0.000
on
Tokenon
Feature activation+0.167
of
Token of
Feature activation+0.633
Chron
Token Chron
Feature activation+0.005
ode
Tokenode
Feature activation+0.000
,
Token,
Feature activation+0.727
the
Tokenthe
Feature activation+0.503
same
Token same
Feature activation+0.391
specialist
Token specialist
Feature activation+0.029
responsible
Token responsible
Feature activation+0.055
for
Token for
Feature activation+0.281
Sa
Token Sa
Feature activation+0.000
ori
Tokenori
Feature activation+0.000
Hay
Token Hay
Feature activation+0.000
ami
Tokenami
Feature activation+0.000
)
Token)
Feature activation+0.722
and
Token and
Feature activation+0.692
Sonia
Token Sonia
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
anche
Tokenanche
Feature activation+0.056
(
Token (
Feature activation+0.753
vo
Tokenvo
Feature activation+0.000

INTERVAL 0.559 - 0.652
CONTAINS 0.007%

oth
Tokenoth
Feature activation+0.000
ings
Tokenings
Feature activation+0.046
,
Token,
Feature activation+0.520
MET
Token MET
Feature activation+0.066
Z
TokenZ
Feature activation+0.000
,
Token,
Feature activation+0.642
etc
Token etc
Feature activation+0.168
.,
Token.,
Feature activation+0.347
but
Token but
Feature activation+0.230
still
Token still
Feature activation+0.000
,
Token,
Feature activation+0.131
and
Token and
Feature activation+0.205
Ni
Token Ni
Feature activation+0.000
all
Tokenall
Feature activation+0.000
Mer
Token Mer
Feature activation+0.083
rigan
Tokenrigan
Feature activation+0.000
,
Token,
Feature activation+0.584
this
Token this
Feature activation+0.359
group
Token group
Feature activation+0.107
is
Token is
Feature activation+0.056
behind
Token behind
Feature activation+0.000
around
Token around
Feature activation+0.000
ille
Tokenille
Feature activation+0.000
Roy
Token Roy
Feature activation+0.000
bal
Tokenbal
Feature activation+0.000
All
Token All
Feature activation+0.269
ard
Tokenard
Feature activation+0.000
(
Token (
Feature activation+0.603
D
TokenD
Feature activation+0.000
-
Token-
Feature activation+0.384
Calif
TokenCalif
Feature activation+0.000
.)
Token.)
Feature activation+0.323
presented
Token presented
Feature activation+0.000
De
Token De
Feature activation+0.000
ir
Tokenir
Feature activation+0.000
E
Token E
Feature activation+0.000
zz
Tokenzz
Feature activation+0.000
or
Tokenor
Feature activation+0.282
.
Token.
Feature activation+0.616
Now
Token Now
Feature activation+0.274
,
Token,
Feature activation+0.346
government
Token government
Feature activation+0.000
forces
Token forces
Feature activation+0.000
are
Token are
Feature activation+0.000
Moh
Token Moh
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Bab
Token Bab
Feature activation+0.000
u
Tokenu
Feature activation+0.000
,
Token,
Feature activation+0.693
in
Token in
Feature activation+0.580
B
Token B
Feature activation+0.289
ollywood
Tokenollywood
Feature activation+0.213
as
Token as
Feature activation+0.506
Bul
Token Bul
Feature activation+0.000
andi
Tokenandi
Feature activation+0.000

INTERVAL 0.466 - 0.559
CONTAINS 0.014%

ist
Tokenist
Feature activation+0.000
party
Token party
Feature activation+0.000
D
Token D
Feature activation+0.000
ver
Tokenver
Feature activation+0.000
i
Tokeni
Feature activation+0.000
.
Token.
Feature activation+0.489
Ċ
TokenĊ
Feature activation+0.178
Ċ
TokenĊ
Feature activation+0.075
"
Token"
Feature activation+0.000
The
TokenThe
Feature activation+0.000
problem
Token problem
Feature activation+0.000
who
Token who
Feature activation+0.399
was
Token was
Feature activation+0.183
ch
Token ch
Feature activation+0.062
aper
Tokenaper
Feature activation+0.000
one
Tokenone
Feature activation+0.054
for
Token for
Feature activation+0.497
several
Token several
Feature activation+0.435
integrated
Token integrated
Feature activation+0.071
students
Token students
Feature activation+0.000
âĢĶ
Token âĢĶ
Feature activation+0.227
disabled
Token disabled
Feature activation+0.000
Bl
Token Bl
Feature activation+0.000
anche
Tokenanche
Feature activation+0.056
(
Token (
Feature activation+0.753
vo
Tokenvo
Feature activation+0.000
iced
Tokeniced
Feature activation+0.097
by
Token by
Feature activation+0.558
As
Token As
Feature activation+0.232
ami
Tokenami
Feature activation+0.000
Set
Token Set
Feature activation+0.133
o
Tokeno
Feature activation+0.000
).
Token).
Feature activation+0.723
P
Token P
Feature activation+0.000
aez
Tokenaez
Feature activation+0.000
V
Token V
Feature activation+0.000
ilar
Tokenilar
Feature activation+0.000
ó
Tokenó
Feature activation+0.000
)
Token)
Feature activation+0.478
van
Token van
Feature activation+0.000
a
Token a
Feature activation+0.063
P
Token P
Feature activation+0.000
c
Tokenc
Feature activation+0.000
io
Tokenio
Feature activation+0.000
ke
Tokenke
Feature activation+0.000
Le
Token Le
Feature activation+0.000
op
Tokenop
Feature activation+0.000
old
Tokenold
Feature activation+0.000
Wilhelm
Token Wilhelm
Feature activation+0.070
,
Token,
Feature activation+0.532
when
Token when
Feature activation+0.502
they
Token they
Feature activation+0.110
lost
Token lost
Feature activation+0.000
a
Token a
Feature activation+0.106
battle
Token battle
Feature activation+0.000

INTERVAL 0.373 - 0.466
CONTAINS 0.032%

as
Token as
Feature activation+0.000
Ralph
Token Ralph
Feature activation+0.000
B
Token B
Feature activation+0.000
ors
Tokenors
Feature activation+0.000
odi
Tokenodi
Feature activation+0.000
,
Token,
Feature activation+0.395
gained
Token gained
Feature activation+0.000
in
Token in
Feature activation+0.020
popularity
Token popularity
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
H
Token H
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
ik
Tokenik
Feature activation+0.000
Åį
TokenÅį
Feature activation+0.000
statue
Token statue
Feature activation+0.000
,
Token,
Feature activation+0.427
giving
Token giving
Feature activation+0.000
it
Token it
Feature activation+0.000
a
Token a
Feature activation+0.000
brand
Token brand
Feature activation+0.000
-
Token-
Feature activation+0.060
intent
Token intent
Feature activation+0.000
,
Token,
Feature activation+0.000
P
Token P
Feature activation+0.000
ach
Tokenach
Feature activation+0.000
uca
Tokenuca
Feature activation+0.000
and
Token and
Feature activation+0.419
Ch
Token Ch
Feature activation+0.000
ivas
Tokenivas
Feature activation+0.000
are
Token are
Feature activation+0.206
the
Token the
Feature activation+0.246
teams
Token teams
Feature activation+0.000
De
Token De
Feature activation+0.000
Te
Token Te
Feature activation+0.000
leg
Tokenleg
Feature activation+0.000
ra
Tokenra
Feature activation+0.000
af
Tokenaf
Feature activation+0.000
(
Token (
Feature activation+0.459
via
Tokenvia
Feature activation+0.000
Tu
Token Tu
Feature activation+0.000
aw
Tokenaw
Feature activation+0.000
)
Token)
Feature activation+0.517
that
Token that
Feature activation+0.296
ren
Tokenren
Feature activation+0.000
dra
Token dra
Feature activation+0.000
f
Tokenf
Feature activation+0.037
te
Tokente
Feature activation+0.000
e
Tokene
Feature activation+0.010
.
Token.
Feature activation+0.463
The
Token The
Feature activation+0.256
only
Token only
Feature activation+0.023
problem
Token problem
Feature activation+0.000
is
Token is
Feature activation+0.000
,
Token,
Feature activation+0.071

INTERVAL 0.280 - 0.373
CONTAINS 0.066%

IK
TokenIK
Feature activation+0.000
ES
TokenES
Feature activation+0.000
In
Token In
Feature activation+0.000
T
TokenT
Feature activation+0.000
v
Tokenv
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.344
Ċ
TokenĊ
Feature activation+0.232
29
Token29
Feature activation+0.000
.
Token.
Feature activation+0.099
20
Token 20
Feature activation+0.000
ohm
Tokenohm
Feature activation+0.000
,
Token,
Feature activation+0.231
the
Token the
Feature activation+0.182
Wa
Token Wa
Feature activation+0.000
itt
Tokenitt
Feature activation+0.000
Foundation
Token Foundation
Feature activation+0.000
,
Token,
Feature activation+0.372
the
Token the
Feature activation+0.287
James
Token James
Feature activation+0.000
B
Token B
Feature activation+0.000
.
Token.
Feature activation+0.269
Pend
Token Pend
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
aw
Tokenaw
Feature activation+0.000
ey
Tokeney
Feature activation+0.000
a
Tokena
Feature activation+0.000
square
Token square
Feature activation+0.000
in
Token in
Feature activation+0.326
Cairo
Token Cairo
Feature activation+0.000
treat
Token treat
Feature activation+0.000
their
Token their
Feature activation+0.000
women
Token women
Feature activation+0.000
-
Token-
Feature activation+0.000
dystopian
Token dystopian
Feature activation+0.000
classic
Token classic
Feature activation+0.037
Brave
Token Brave
Feature activation+0.000
New
Token New
Feature activation+0.076
World
Token World
Feature activation+0.000
,
Token,
Feature activation+0.312
where
Token where
Feature activation+0.228
"
Token "
Feature activation+0.133
feel
Tokenfeel
Feature activation+0.000
ies
Tokenies
Feature activation+0.000
"
Token"
Feature activation+0.069
,
Token,
Feature activation+0.245
forming
Token forming
Feature activation+0.000
a
Token a
Feature activation+0.000
U
Token U
Feature activation+0.000
ral
Tokenral
Feature activation+0.000
-
Token-
Feature activation+0.364
Al
TokenAl
Feature activation+0.038
ta
Tokenta
Feature activation+0.140
ic
Tokenic
Feature activation+0.068
macro
Token macro
Feature activation+0.182
-
Token-
Feature activation+0.466

INTERVAL 0.186 - 0.280
CONTAINS 0.132%

(@
Token (@
Feature activation+0.031
Larry
TokenLarry
Feature activation+0.000
AN
TokenAN
Feature activation+0.000
j
Tokenj
Feature activation+0.000
ax
Tokenax
Feature activation+0.000
)
Token)
Feature activation+0.210
April
Token April
Feature activation+0.000
5
Token 5
Feature activation+0.098
,
Token,
Feature activation+0.105
2017
Token 2017
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Be
Token Be
Feature activation+0.000
Sanskrit
Token Sanskrit
Feature activation+0.000
,
Token,
Feature activation+0.000
Pal
Token Pal
Feature activation+0.000
i
Tokeni
Feature activation+0.000
,
Token,
Feature activation+0.205
and
Token and
Feature activation+0.238
P
Token P
Feature activation+0.000
rak
Tokenrak
Feature activation+0.000
rit
Tokenrit
Feature activation+0.000
via
Token via
Feature activation+0.243
at
Token at
Feature activation+0.112
Vers
Token Vers
Feature activation+0.000
a
Tokena
Feature activation+0.000
illes
Tokenilles
Feature activation+0.067
.
Token.
Feature activation+0.343
I
Token I
Feature activation+0.198
love
Token love
Feature activation+0.000
this
Token this
Feature activation+0.001
costume
Token costume
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
cre
Tokencre
Feature activation+0.000
ep
Tokenep
Feature activation+0.000
y
Tokeny
Feature activation+0.000
,
Token,
Feature activation+0.269
rude
Token rude
Feature activation+0.000
,
Token,
Feature activation+0.154
and
Token and
Feature activation+0.183
obnoxious
Token obnoxious
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
van
Token van
Feature activation+0.000
die
Token die
Feature activation+0.000
ren
Tokenren
Feature activation+0.000
m
Tokenm
Feature activation+0.000
ish
Tokenish
Feature activation+0.000
and
Tokenand
Feature activation+0.189
eling
Tokeneling
Feature activation+0.030
-
Token -
Feature activation+0.530
w
Token w
Feature activation+0.000
erk
Tokenerk
Feature activation+0.000
ten
Tokenten
Feature activation+0.000

INTERVAL 0.093 - 0.186
CONTAINS 0.241%

âĢĵ
Token âĢĵ
Feature activation+0.563
bass
Token bass
Feature activation+0.096
guitar
Token guitar
Feature activation+0.059
,
Token,
Feature activation+0.248
Ċ
TokenĊ
Feature activation+0.236
Ċ
TokenĊ
Feature activation+0.148
D
TokenD
Feature activation+0.000
omas
Tokenomas
Feature activation+0.000
D
Token D
Feature activation+0.000
Ä
TokenÄ
Feature activation+0.000
Ĺ
TokenĹ
Feature activation+0.000
oba
Tokenoba
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
place
Token place
Feature activation+0.000
at
Token at
Feature activation+0.152
3
Token 3
Feature activation+0.101
pm
Token pm
Feature activation+0.000
.
Token.
Feature activation+0.067
Ċ
TokenĊ
Feature activation+0.077
Ċ
TokenĊ
Feature activation+0.004
release
Token release
Feature activation+0.000
packaged
Token packaged
Feature activation+0.000
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
game
Token game
Feature activation+0.000
,
Token,
Feature activation+0.100
as
Token as
Feature activation+0.078
well
Token well
Feature activation+0.000
as
Token as
Feature activation+0.000
a
Token a
Feature activation+0.000
new
Token new
Feature activation+0.000
A
Token A
Feature activation+0.000
Time
Token Time
Feature activation+0.000
To
Token To
Feature activation+0.000
Be
Token Be
Feature activation+0.000
Bare
Token Bare
Feature activation+0.000
ly
Tokenly
Feature activation+0.182
Alive
Token Alive
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
.
Token.
Feature activation+0.239
Released
Token Released
Feature activation+0.000
F
Token F
Feature activation+0.000
oust
Tokenoust
Feature activation+0.000
and
Token and
Feature activation+0.193
former
Token former
Feature activation+0.019
NASCAR
Token NASCAR
Feature activation+0.000
and
Token and
Feature activation+0.097
Formula
Token Formula
Feature activation+0.000
One
Token One
Feature activation+0.000
competitor
Token competitor
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
Speed
Token Speed
Feature activation+0.000

INTERVAL 0.000 - 0.093
CONTAINS 99.505%

Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
these
Token these
Feature activation+0.000
countries
Token countries
Feature activation+0.000
,
Token,
Feature activation+0.000
food
Token food
Feature activation+0.000
waste
Token waste
Feature activation+0.000
usually
Token usually
Feature activation+0.000
isn
Token isn
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
space
Token space
Feature activation+0.000
craft
Token craft
Feature activation+0.000
(
Token (
Feature activation+0.000
like
Tokenlike
Feature activation+0.000
the
Token the
Feature activation+0.000
ISS
Token ISS
Feature activation+0.000
)
Token)
Feature activation+0.000
are
Token are
Feature activation+0.000
obvious
Token obvious
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
No
TokenNo
Feature activation+0.000
,
Token,
Feature activation+0.000
don
Token don
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
t
Tokent
Feature activation+0.000
take
Token take
Feature activation+0.000
them
Token them
Feature activation+0.000
off
Token off
Feature activation+0.000
,
Token,
Feature activation+0.000
interim
Token interim
Feature activation+0.000
government
Token government
Feature activation+0.000
will
Token will
Feature activation+0.000
do
Token do
Feature activation+0.000
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
prevent
Token prevent
Feature activation+0.000
election
Token election
Feature activation+0.000
returns
Token returns
Feature activation+0.000
from
Token from
Feature activation+0.000
injury
Token injury
Feature activation+0.000
.
Token.
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
Tor
TokenTor
Feature activation+0.000
rance
Tokenrance
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
strict
Token strict
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 H1.4: (feature 20018)

TOP ACTIVATIONS
MAX = 1.128

Hillary
Token Hillary
Feature activation+0.196
Diane
Token Diane
Feature activation+0.327
Rodham
Token Rodham
Feature activation+0.459
Clinton
Token Clinton
Feature activation+0.520
Sanders
TokenSanders
Feature activation+0.863
:
Token:
Feature activation+1.128
'
Token '
Feature activation+0.675
I
TokenI
Feature activation+0.602
fully
Token fully
Feature activation+0.445
expect
Token expect
Feature activation+0.294
'
Token'
Feature activation+0.296
directives
Token directives
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
made
Token made
Feature activation+1.054
the
Token the
Feature activation+0.283
âĢ
Token âĢ
Feature activation+0.478
ľ
Tokenľ
Feature activation+0.058
three
Tokenthree
Feature activation+0.323
directives
Token directives
Feature activation+0.261
minute
Token minute
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
said
Token said
Feature activation+1.047
he
Token he
Feature activation+0.453
had
Token had
Feature activation+0.347
already
Token already
Feature activation+0.102
stepped
Token stepped
Feature activation+0.232
up
Token up
Feature activation+0.000
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
.
Token.
Feature activation+0.265
Obama
Token Obama
Feature activation+0.301
's
Token's
Feature activation+1.000
critics
Token critics
Feature activation+0.574
argue
Token argue
Feature activation+0.509
that
Token that
Feature activation+0.332
he
Token he
Feature activation+0.258
is
Token is
Feature activation+0.281
Act
Token Act
Feature activation+0.000
.
Token.
Feature activation+0.062
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.170
made
Token made
Feature activation+0.927
repeal
Token repeal
Feature activation+0.575
and
Token and
Feature activation+0.595
replace
Token replace
Feature activation+0.571
of
Token of
Feature activation+0.428
his
Token his
Feature activation+0.385
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
President
Token President
Feature activation+0.000
Donald
Token Donald
Feature activation+0.200
Trump
Token Trump
Feature activation+0.499
responded
Token responded
Feature activation+0.916
by
Token by
Feature activation+0.520
firing
Token firing
Feature activation+0.240
cruise
Token cruise
Feature activation+0.304
missiles
Token missiles
Feature activation+0.145
at
Token at
Feature activation+0.093
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.137
paid
Token paid
Feature activation+0.903
no
Token no
Feature activation+0.593
federal
Token federal
Feature activation+0.317
income
Token income
Feature activation+0.398
taxes
Token taxes
Feature activation+0.250
for
Token for
Feature activation+0.212
so
Token so
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
lost
Token lost
Feature activation+0.896
to
Token to
Feature activation+0.480
Republican
Token Republican
Feature activation+0.090
presidential
Token presidential
Feature activation+0.130
candidate
Token candidate
Feature activation+0.392
John
Token John
Feature activation+0.567
Republican
Token Republican
Feature activation+0.090
presidential
Token presidential
Feature activation+0.130
candidate
Token candidate
Feature activation+0.392
John
Token John
Feature activation+0.567
McCain
Token McCain
Feature activation+0.359
by
Token by
Feature activation+0.881
11
Token 11
Feature activation+0.533
percentage
Token percentage
Feature activation+0.465
points
Token points
Feature activation+0.507
and
Token and
Feature activation+0.334
close
Token close
Feature activation+0.224
want
Token want
Feature activation+0.435
to
Token to
Feature activation+0.332
see
Token see
Feature activation+0.305
President
Token President
Feature activation+0.095
Trump
Token Trump
Feature activation+0.274
irre
Token irre
Feature activation+0.875
par
Tokenpar
Feature activation+0.618
ably
Tokenably
Feature activation+0.651
damaged
Token damaged
Feature activation+0.546
so
Token so
Feature activation+0.403
they
Token they
Feature activation+0.210
.
Token.
Feature activation+0.031
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mrs
TokenMrs
Feature activation+0.035
Obama
Token Obama
Feature activation+0.000
's
Token's
Feature activation+0.868
remarks
Token remarks
Feature activation+0.683
come
Token come
Feature activation+0.586
within
Token within
Feature activation+0.513
hours
Token hours
Feature activation+0.318
of
Token of
Feature activation+0.187
Clinton
Token Clinton
Feature activation+0.000
Hillary
Token Hillary
Feature activation+0.196
Diane
Token Diane
Feature activation+0.327
Rodham
Token Rodham
Feature activation+0.459
Clinton
Token Clinton
Feature activation+0.520
Sanders
TokenSanders
Feature activation+0.863
:
Token:
Feature activation+1.128
'
Token '
Feature activation+0.675
I
TokenI
Feature activation+0.602
fully
Token fully
Feature activation+0.445
expect
Token expect
Feature activation+0.294
Clinton
Token Clinton
Feature activation+0.325
's
Token's
Feature activation+0.606
advantage
Token advantage
Feature activation+0.561
over
Token over
Feature activation+0.508
Trump
Token Trump
Feature activation+0.254
today
Token today
Feature activation+0.849
is
Token is
Feature activation+0.670
75
Token 75
Feature activation+0.469
-
Token-
Feature activation+0.314
15
Token15
Feature activation+0.134
,
Token,
Feature activation+0.085
President
Token President
Feature activation+0.000
-
Token-
Feature activation+0.092
elect
Tokenelect
Feature activation+0.000
Donald
Token Donald
Feature activation+0.097
Trump
Token Trump
Feature activation+0.305
gets
Token gets
Feature activation+0.846
into
Token into
Feature activation+0.490
office
Token office
Feature activation+0.346
Ċ
TokenĊ
Feature activation+0.303
Ċ
TokenĊ
Feature activation+0.242
U
TokenU
Feature activation+0.126
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
The
TokenThe
Feature activation+0.000
Obama
Token Obama
Feature activation+0.029
administration
Token administration
Feature activation+0.440
insisted
Token insisted
Feature activation+0.831
that
Token that
Feature activation+0.415
private
Token private
Feature activation+0.480
-
Token-
Feature activation+0.414
sector
Tokensector
Feature activation+0.254
creditors
Token creditors
Feature activation+0.339
10
Token 10
Feature activation+0.000
,
Token,
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
:
Token:
Feature activation+0.000
Trump
Token Trump
Feature activation+0.062
gives
Token gives
Feature activation+0.829
a
Token a
Feature activation+0.455
speech
Token speech
Feature activation+0.256
to
Token to
Feature activation+0.299
CP
Token CP
Feature activation+0.042
AC
TokenAC
Feature activation+0.083
Warren
Token Warren
Feature activation+0.000
Elizabeth
Token Elizabeth
Feature activation+0.079
Ann
Token Ann
Feature activation+0.197
Warren
Token Warren
Feature activation+0.125
Sanders
TokenSanders
Feature activation+0.625
:
Token:
Feature activation+0.826
'
Token '
Feature activation+0.382
Damn
TokenDamn
Feature activation+0.311
right
Token right
Feature activation+0.242
'
Token'
Feature activation+0.260
I
Token I
Feature activation+0.165
the
Token the
Feature activation+0.000
election
Token election
Feature activation+0.000
of
Token of
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.104
as
Token as
Feature activation+0.817
US
Token US
Feature activation+0.414
President
Token President
Feature activation+0.548
.
Token.
Feature activation+0.527
Ċ
TokenĊ
Feature activation+0.236
Ċ
TokenĊ
Feature activation+0.162
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
JUST
TokenJUST
Feature activation+0.000
WATCHED
Token WATCHED
Feature activation+0.000
Trump
Token Trump
Feature activation+0.362
gives
Token gives
Feature activation+0.799
tacit
Token tacit
Feature activation+0.325
approval
Token approval
Feature activation+0.333
to
Token to
Feature activation+0.284
Roy
Token Roy
Feature activation+0.182
Moore
Token Moore
Feature activation+0.079
/
Token/
Feature activation+0.193
Brian
TokenBrian
Feature activation+0.016
Snyder
Token Snyder
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.076
took
Token took
Feature activation+0.793
a
Token a
Feature activation+0.468
shot
Token shot
Feature activation+0.249
at
Token at
Feature activation+0.169
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000

Top DFA by src position
MAX = 1.584

Clinton
Token Clinton
Feature activation+0.191
Top resid features:
Hillary
Token Hillary
Feature activation+0.145
Top resid features:
Diane
Token Diane
Feature activation+0.112
Top resid features:
Rodham
Token Rodham
Feature activation+0.343
Top resid features:
Clinton
Token Clinton
Feature activation+0.339
Top resid features:
Sanders
TokenSanders
Feature activation+0.481
Top resid features:
:
Token:
Feature activation-0.039
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
fully
Token fully
Feature activation+0.000
Top resid features:
expect
Token expect
Feature activation+0.000
Top resid features:
three
Token three
Feature activation+0.004
Top resid features:
directives
Token directives
Feature activation+0.035
Top resid features:
.
Token.
Feature activation+0.075
Top resid features:
Ċ
TokenĊ
Feature activation+0.059
Top resid features:
Ċ
TokenĊ
Feature activation+0.068
Top resid features:
Obama
TokenObama
Feature activation+1.480
Top resid features:
made
Token made
Feature activation+0.039
Top resid features:
the
Token the
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:
three
Tokenthree
Feature activation+0.000
Top resid features:
per
Token per
Feature activation+0.013
Top resid features:
minute
Token minute
Feature activation+0.007
Top resid features:
.
Token.
Feature activation+0.041
Top resid features:
Ċ
TokenĊ
Feature activation+0.047
Top resid features:
Ċ
TokenĊ
Feature activation+0.058
Top resid features:
Obama
TokenObama
Feature activation+1.584
Top resid features:
said
Token said
Feature activation-0.031
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
already
Token already
Feature activation+0.000
Top resid features:
stepped
Token stepped
Feature activation+0.000
Top resid features:
George
Token George
Feature activation+0.080
Top resid features:
W
Token W
Feature activation+0.049
Top resid features:
.
Token.
Feature activation+0.028
Top resid features:
Bush
Token Bush
Feature activation+0.322
Top resid features:
.
Token.
Feature activation+0.111
Top resid features:
Obama
Token Obama
Feature activation+1.003
Top resid features:
's
Token's
Feature activation-0.027
Top resid features:
critics
Token critics
Feature activation+0.000
Top resid features:
argue
Token argue
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
Care
Token Care
Feature activation+0.031
Top resid features:
Act
Token Act
Feature activation+0.049
Top resid features:
.
Token.
Feature activation+0.033
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Ċ
TokenĊ
Feature activation+0.036
Top resid features:
Trump
TokenTrump
Feature activation+1.109
Top resid features:
made
Token made
Feature activation-0.022
Top resid features:
repeal
Token repeal
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
replace
Token replace
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
.
Token.
Feature activation-0.003
Top resid features:
S
TokenS
Feature activation+0.041
Top resid features:
.
Token.
Feature activation-0.005
Top resid features:
President
Token President
Feature activation+0.271
Top resid features:
Donald
Token Donald
Feature activation+0.304
Top resid features:
Trump
Token Trump
Feature activation+0.640
Top resid features:
responded
Token responded
Feature activation+0.018
Top resid features:
by
Token by
Feature activation+0.000
Top resid features:
firing
Token firing
Feature activation+0.000
Top resid features:
cruise
Token cruise
Feature activation+0.000
Top resid features:
missiles
Token missiles
Feature activation+0.000
Top resid features:
reported
Token reported
Feature activation+0.050
Top resid features:
:
Token:
Feature activation+0.035
Top resid features:
Ċ
TokenĊ
Feature activation+0.031
Top resid features:
Ċ
TokenĊ
Feature activation+0.030
Top resid features:
Donald
TokenDonald
Feature activation+0.446
Top resid features:
Trump
Token Trump
Feature activation+0.671
Top resid features:
paid
Token paid
Feature activation-0.068
Top resid features:
no
Token no
Feature activation+0.000
Top resid features:
federal
Token federal
Feature activation+0.000
Top resid features:
income
Token income
Feature activation+0.000
Top resid features:
taxes
Token taxes
Feature activation+0.000
Top resid features:
do
Token do
Feature activation+0.013
Top resid features:
so
Token so
Feature activation+0.010
Top resid features:
."
Token."
Feature activation+0.094
Top resid features:
Ċ
TokenĊ
Feature activation+0.046
Top resid features:
Ċ
TokenĊ
Feature activation+0.056
Top resid features:
Obama
TokenObama
Feature activation+1.273
Top resid features:
lost
Token lost
Feature activation+0.019
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Republican
Token Republican
Feature activation+0.000
Top resid features:
presidential
Token presidential
Feature activation+0.000
Top resid features:
candidate
Token candidate
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.038
Top resid features:
Republican
Token Republican
Feature activation+0.150
Top resid features:
presidential
Token presidential
Feature activation+0.154
Top resid features:
candidate
Token candidate
Feature activation+0.162
Top resid features:
John
Token John
Feature activation+0.142
Top resid features:
McCain
Token McCain
Feature activation+0.457
Top resid features:
by
Token by
Feature activation-0.070
Top resid features:
11
Token 11
Feature activation+0.000
Top resid features:
percentage
Token percentage
Feature activation+0.000
Top resid features:
points
Token points
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.047
Top resid features:
want
Token want
Feature activation+0.079
Top resid features:
to
Token to
Feature activation+0.028
Top resid features:
see
Token see
Feature activation+0.021
Top resid features:
President
Token President
Feature activation+0.222
Top resid features:
Trump
Token Trump
Feature activation+0.514
Top resid features:
irre
Token irre
Feature activation-0.012
Top resid features:
par
Tokenpar
Feature activation+0.000
Top resid features:
ably
Tokenably
Feature activation+0.000
Top resid features:
damaged
Token damaged
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
result
Token result
Feature activation+0.027
Top resid features:
.
Token.
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation+0.034
Top resid features:
Ċ
TokenĊ
Feature activation+0.038
Top resid features:
Mrs
TokenMrs
Feature activation+0.175
Top resid features:
Obama
Token Obama
Feature activation+0.944
Top resid features:
's
Token's
Feature activation-0.023
Top resid features:
remarks
Token remarks
Feature activation+0.000
Top resid features:
come
Token come
Feature activation+0.000
Top resid features:
within
Token within
Feature activation+0.000
Top resid features:
hours
Token hours
Feature activation+0.000
Top resid features:
where
Token where
Feature activation-0.007
Top resid features:
Hillary
Token Hillary
Feature activation+0.117
Top resid features:
Clinton
Token Clinton
Feature activation+0.128
Top resid features:
Hillary
Token Hillary
Feature activation+0.133
Top resid features:
Diane
Token Diane
Feature activation+0.233
Top resid features:
Rodham
Token Rodham
Feature activation+0.362
Top resid features:
Clinton
Token Clinton
Feature activation+0.278
Top resid features:
Sanders
TokenSanders
Feature activation+0.236
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
I
TokenI
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.064
Top resid features:
Clinton
Token Clinton
Feature activation+0.334
Top resid features:
's
Token's
Feature activation+0.001
Top resid features:
advantage
Token advantage
Feature activation-0.003
Top resid features:
over
Token over
Feature activation+0.052
Top resid features:
Trump
Token Trump
Feature activation+0.596
Top resid features:
today
Token today
Feature activation+0.016
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
75
Token 75
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
15
Token15
Feature activation+0.000
Top resid features:
as
Token as
Feature activation+0.008
Top resid features:
President
Token President
Feature activation+0.172
Top resid features:
-
Token-
Feature activation+0.027
Top resid features:
elect
Tokenelect
Feature activation+0.071
Top resid features:
Donald
Token Donald
Feature activation+0.332
Top resid features:
Trump
Token Trump
Feature activation+0.594
Top resid features:
gets
Token gets
Feature activation-0.016
Top resid features:
into
Token into
Feature activation+0.000
Top resid features:
office
Token office
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:
price
Token price
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.029
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
The
TokenThe
Feature activation-0.006
Top resid features:
Obama
Token Obama
Feature activation+0.821
Top resid features:
administration
Token administration
Feature activation+0.280
Top resid features:
insisted
Token insisted
Feature activation+0.041
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
private
Token private
Feature activation+0.000
Top resid features:
-
Token-
Feature activation+0.000
Top resid features:
February
TokenFebruary
Feature activation+0.041
Top resid features:
10
Token 10
Feature activation+0.007
Top resid features:
,
Token,
Feature activation+0.035
Top resid features:
2011
Token 2011
Feature activation+0.099
Top resid features:
:
Token:
Feature activation+0.062
Top resid features:
Trump
Token Trump
Feature activation+0.928
Top resid features:
gives
Token gives
Feature activation-0.032
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
speech
Token speech
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
CP
Token CP
Feature activation+0.000
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.078
Top resid features:
Warren
Token Warren
Feature activation+0.169
Top resid features:
Elizabeth
Token Elizabeth
Feature activation+0.114
Top resid features:
Ann
Token Ann
Feature activation+0.082
Top resid features:
Warren
Token Warren
Feature activation+0.242
Top resid features:
Sanders
TokenSanders
Feature activation+0.663
Top resid features:
:
Token:
Feature activation-0.010
Top resid features:
'
Token '
Feature activation+0.000
Top resid features:
Damn
TokenDamn
Feature activation+0.000
Top resid features:
right
Token right
Feature activation+0.000
Top resid features:
'
Token'
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.027
Top resid features:
the
Token the
Feature activation+0.011
Top resid features:
election
Token election
Feature activation+0.163
Top resid features:
of
Token of
Feature activation+0.019
Top resid features:
Donald
Token Donald
Feature activation+0.298
Top resid features:
Trump
Token Trump
Feature activation+0.642
Top resid features:
as
Token as
Feature activation-0.002
Top resid features:
US
Token US
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:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
moments
Token moments
Feature activation+0.050
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
Ċ
TokenĊ
Feature activation+0.027
Top resid features:
JUST
TokenJUST
Feature activation+0.061
Top resid features:
WATCHED
Token WATCHED
Feature activation+0.305
Top resid features:
Trump
Token Trump
Feature activation+0.823
Top resid features:
gives
Token gives
Feature activation-0.044
Top resid features:
tacit
Token tacit
Feature activation+0.000
Top resid features:
approval
Token approval
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
Roy
Token Roy
Feature activation+0.000
Top resid features:
REUTERS
Token REUTERS
Feature activation+0.069
Top resid features:
/
Token/
Feature activation+0.023
Top resid features:
Brian
TokenBrian
Feature activation+0.124
Top resid features:
Snyder
Token Snyder
Feature activation+0.177
Top resid features:
Donald
Token Donald
Feature activation+0.230
Top resid features:
Trump
Token Trump
Feature activation+0.486
Top resid features:
took
Token took
Feature activation-0.078
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
shot
Token shot
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
President
Token President
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.15

Head 2: 0.11

Head 3: 0.04

Head 4: 0.14

Head 5: 0.04

Head 6: 0.05

Head 7: 0.12

Head 8: 0.05

Head 9: 0.04

Head 10: 0.08

Head 11: 0.08

Positive logits

Obama1.60

himself1.59

Bush1.57

Schumer1.56

Pants1.54

veto1.51

Chuck1.51

unilateral1.47

pardon1.47

reelection1.46

Congress1.46

Romney1.44

Barack1.44

pard1.44

1.44

Reagan1.42

Truman1.42

pard1.42

Obama1.40

Chair1.38

Negative logits

ept-1.38

Imaging-1.38

angular-1.34

-1.28

fluid-1.28

juveniles-1.27

youngsters-1.27

-1.25

sic-1.23

biomark-1.23

php-1.22

oi-1.22

respectively-1.20

ormonal-1.20

medi-1.19

environments-1.19

Umb-1.19

samples-1.18

xa-1.18

oxy-1.18

INTERVAL 1.015 - 1.128
CONTAINS 0.000%

Hillary
Token Hillary
Feature activation+0.196
Diane
Token Diane
Feature activation+0.327
Rodham
Token Rodham
Feature activation+0.459
Clinton
Token Clinton
Feature activation+0.520
Sanders
TokenSanders
Feature activation+0.863
:
Token:
Feature activation+1.128
'
Token '
Feature activation+0.675
I
TokenI
Feature activation+0.602
fully
Token fully
Feature activation+0.445
expect
Token expect
Feature activation+0.294
'
Token'
Feature activation+0.296
minute
Token minute
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
said
Token said
Feature activation+1.047
he
Token he
Feature activation+0.453
had
Token had
Feature activation+0.347
already
Token already
Feature activation+0.102
stepped
Token stepped
Feature activation+0.232
up
Token up
Feature activation+0.000
directives
Token directives
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
made
Token made
Feature activation+1.054
the
Token the
Feature activation+0.283
âĢ
Token âĢ
Feature activation+0.478
ľ
Tokenľ
Feature activation+0.058
three
Tokenthree
Feature activation+0.323
directives
Token directives
Feature activation+0.261

INTERVAL 0.903 - 1.015
CONTAINS 0.000%

:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Donald
TokenDonald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.137
paid
Token paid
Feature activation+0.903
no
Token no
Feature activation+0.593
federal
Token federal
Feature activation+0.317
income
Token income
Feature activation+0.398
taxes
Token taxes
Feature activation+0.250
for
Token for
Feature activation+0.212
S
TokenS
Feature activation+0.000
.
Token.
Feature activation+0.000
President
Token President
Feature activation+0.000
Donald
Token Donald
Feature activation+0.200
Trump
Token Trump
Feature activation+0.499
responded
Token responded
Feature activation+0.916
by
Token by
Feature activation+0.520
firing
Token firing
Feature activation+0.240
cruise
Token cruise
Feature activation+0.304
missiles
Token missiles
Feature activation+0.145
at
Token at
Feature activation+0.093
W
Token W
Feature activation+0.000
.
Token.
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
.
Token.
Feature activation+0.265
Obama
Token Obama
Feature activation+0.301
's
Token's
Feature activation+1.000
critics
Token critics
Feature activation+0.574
argue
Token argue
Feature activation+0.509
that
Token that
Feature activation+0.332
he
Token he
Feature activation+0.258
is
Token is
Feature activation+0.281
Act
Token Act
Feature activation+0.000
.
Token.
Feature activation+0.062
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.170
made
Token made
Feature activation+0.927
repeal
Token repeal
Feature activation+0.575
and
Token and
Feature activation+0.595
replace
Token replace
Feature activation+0.571
of
Token of
Feature activation+0.428
his
Token his
Feature activation+0.385

INTERVAL 0.790 - 0.903
CONTAINS 0.002%

Warren
Token Warren
Feature activation+0.000
Elizabeth
Token Elizabeth
Feature activation+0.079
Ann
Token Ann
Feature activation+0.197
Warren
Token Warren
Feature activation+0.125
Sanders
TokenSanders
Feature activation+0.625
:
Token:
Feature activation+0.826
'
Token '
Feature activation+0.382
Damn
TokenDamn
Feature activation+0.311
right
Token right
Feature activation+0.242
'
Token'
Feature activation+0.260
I
Token I
Feature activation+0.165
Republican
Token Republican
Feature activation+0.090
presidential
Token presidential
Feature activation+0.130
candidate
Token candidate
Feature activation+0.392
John
Token John
Feature activation+0.567
McCain
Token McCain
Feature activation+0.359
by
Token by
Feature activation+0.881
11
Token 11
Feature activation+0.533
percentage
Token percentage
Feature activation+0.465
points
Token points
Feature activation+0.507
and
Token and
Feature activation+0.334
close
Token close
Feature activation+0.224
.
Token.
Feature activation+0.031
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Mrs
TokenMrs
Feature activation+0.035
Obama
Token Obama
Feature activation+0.000
's
Token's
Feature activation+0.868
remarks
Token remarks
Feature activation+0.683
come
Token come
Feature activation+0.586
within
Token within
Feature activation+0.513
hours
Token hours
Feature activation+0.318
of
Token of
Feature activation+0.187
/
Token/
Feature activation+0.193
Brian
TokenBrian
Feature activation+0.016
Snyder
Token Snyder
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.076
took
Token took
Feature activation+0.793
a
Token a
Feature activation+0.468
shot
Token shot
Feature activation+0.249
at
Token at
Feature activation+0.169
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
so
Token so
Feature activation+0.000
."
Token."
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
lost
Token lost
Feature activation+0.896
to
Token to
Feature activation+0.480
Republican
Token Republican
Feature activation+0.090
presidential
Token presidential
Feature activation+0.130
candidate
Token candidate
Feature activation+0.392
John
Token John
Feature activation+0.567

INTERVAL 0.677 - 0.790
CONTAINS 0.003%

ack
Tokenack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
,
Token,
Feature activation+0.225
Hillary
Token Hillary
Feature activation+0.361
Clinton
Token Clinton
Feature activation+0.306
and
Token and
Feature activation+0.748
Joe
Token Joe
Feature activation+0.555
Biden
Token Biden
Feature activation+0.336
âĢĶ
TokenâĢĶ
Feature activation+0.692
it
Tokenit
Feature activation+0.603
âĢ
TokenâĢ
Feature activation+0.367
President
Token President
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
Donald
Token Donald
Feature activation+0.197
John
Token John
Feature activation+0.365
Trump
Token Trump
Feature activation+0.341
House
TokenHouse
Feature activation+0.711
committee
Token committee
Feature activation+0.611
believes
Token believes
Feature activation+0.384
it
Token it
Feature activation+0.117
has
Token has
Feature activation+0.123
evidence
Token evidence
Feature activation+0.000
been
Token been
Feature activation+0.000
clearer
Token clearer
Feature activation+0.000
-
Token -
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
calls
Token calls
Feature activation+0.681
on
Token on
Feature activation+0.502
us
Token us
Feature activation+0.419
to
Token to
Feature activation+0.252
Believe
Token Believe
Feature activation+0.230
in
Token in
Feature activation+0.199
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+0.158
,
Token,
Feature activation+0.693
who
Token who
Feature activation+0.659
apologized
Token apologized
Feature activation+0.340
in
Token in
Feature activation+0.476
a
Token a
Feature activation+0.403
video
Token video
Feature activation+0.342
âĢ
TokenâĢ
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Clinton
TokenClinton
Feature activation+0.000
added
Token added
Feature activation+0.730
of
Token of
Feature activation+0.248
Perry
Token Perry
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.215
Ļ
TokenĻ
Feature activation+0.096
s
Tokens
Feature activation+0.195

INTERVAL 0.564 - 0.677
CONTAINS 0.009%

.
Token.
Feature activation+0.062
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Trump
TokenTrump
Feature activation+0.170
made
Token made
Feature activation+0.927
repeal
Token repeal
Feature activation+0.575
and
Token and
Feature activation+0.595
replace
Token replace
Feature activation+0.571
of
Token of
Feature activation+0.428
his
Token his
Feature activation+0.385
predecessor
Token predecessor
Feature activation+0.279
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
George
TokenGeorge
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
made
Token made
Feature activation+0.610
a
Token a
Feature activation+0.241
mistake
Token mistake
Feature activation+0.065
,
Token,
Feature activation+0.048
we
Token we
Feature activation+0.076
can
Token can
Feature activation+0.000
see
Token see
Feature activation+0.305
President
Token President
Feature activation+0.095
Trump
Token Trump
Feature activation+0.274
irre
Token irre
Feature activation+0.875
par
Tokenpar
Feature activation+0.618
ably
Tokenably
Feature activation+0.651
damaged
Token damaged
Feature activation+0.546
so
Token so
Feature activation+0.403
they
Token they
Feature activation+0.210
can
Token can
Feature activation+0.162
run
Token run
Feature activation+0.052
.
Token.
Feature activation+0.000
Bush
Token Bush
Feature activation+0.000
and
Token and
Feature activation+0.231
Bill
Token Bill
Feature activation+0.158
Clinton
Token Clinton
Feature activation+0.055
in
Token in
Feature activation+0.625
the
Token the
Feature activation+0.418
first
Token first
Feature activation+0.360
town
Token town
Feature activation+0.242
hall
Token hall
Feature activation+0.213
debate
Token debate
Feature activation+0.327
her
Token her
Feature activation+0.358
own
Token own
Feature activation+0.321
speech
Token speech
Feature activation+0.222
attacking
Token attacking
Feature activation+0.326
Trump
Token Trump
Feature activation+0.073
on
Token on
Feature activation+0.630
his
Token his
Feature activation+0.541
business
Token business
Feature activation+0.569
record
Token record
Feature activation+0.474
,
Token,
Feature activation+0.289
foreign
Token foreign
Feature activation+0.103

INTERVAL 0.451 - 0.564
CONTAINS 0.019%

against
Token against
Feature activation+0.000
President
Token President
Feature activation+0.000
Barack
Token Barack
Feature activation+0.000
Obama
Token Obama
Feature activation+0.121
on
Token on
Feature activation+0.537
a
Token a
Feature activation+0.461
national
Token national
Feature activation+0.111
security
Token security
Feature activation+0.107
issue
Token issue
Feature activation+0.184
.
Token.
Feature activation+0.091
And
Token And
Feature activation+0.000
McCarthy
Token McCarthy
Feature activation+0.000
Kevin
Token Kevin
Feature activation+0.122
Owen
Token Owen
Feature activation+0.225
McCarthy
Token McCarthy
Feature activation+0.224
Steve
TokenSteve
Feature activation+0.490
King
Token King
Feature activation+0.461
says
Token says
Feature activation+0.451
he
Token he
Feature activation+0.196
will
Token will
Feature activation+0.000
run
Token run
Feature activation+0.022
again
Token again
Feature activation+0.112
clearer
Token clearer
Feature activation+0.000
-
Token -
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
calls
Token calls
Feature activation+0.681
on
Token on
Feature activation+0.502
us
Token us
Feature activation+0.419
to
Token to
Feature activation+0.252
Believe
Token Believe
Feature activation+0.230
in
Token in
Feature activation+0.199
America
Token America
Feature activation+0.000
once
Token once
Feature activation+0.080
.
Token.
Feature activation+0.000
Mrs
Token Mrs
Feature activation+0.016
.
Token.
Feature activation+0.000
Cheney
Token Cheney
Feature activation+0.000
served
Token served
Feature activation+0.549
spinach
Token spinach
Feature activation+0.253
.
Token.
Feature activation+0.042
But
Token But
Feature activation+0.000
I
Token I
Feature activation+0.000
don
Token don
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
administration
Token administration
Feature activation+0.247
.
Token.
Feature activation+0.460
House
Token House
Feature activation+0.275
Republicans
Token Republicans
Feature activation+0.258
won
Token won
Feature activation+0.521
the
Token the
Feature activation+0.481
lawsuit
Token lawsuit
Feature activation+0.266
,
Token,
Feature activation+0.186
which
Token which
Feature activation+0.100
was
Token was
Feature activation+0.000

INTERVAL 0.338 - 0.451
CONTAINS 0.034%

said
Token said
Feature activation+0.002
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Obama
TokenObama
Feature activation+0.000
also
Token also
Feature activation+0.220
sought
Token sought
Feature activation+0.390
to
Token to
Feature activation+0.000
tamp
Token tamp
Feature activation+0.040
down
Token down
Feature activation+0.000
the
Token the
Feature activation+0.000
spect
Token spect
Feature activation+0.000
all
Tokenall
Feature activation+0.000
strom
Tokenstrom
Feature activation+0.000
praised
Token praised
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.000
before
Token before
Feature activation+0.350
he
Token he
Feature activation+0.241
offered
Token offered
Feature activation+0.270
a
Token a
Feature activation+0.191
take
Token take
Feature activation+0.083
down
Token down
Feature activation+0.000
Ĵ
TokenĴ
Feature activation+0.636
s
Tokens
Feature activation+0.567
anti
Token anti
Feature activation+0.374
-
Token-
Feature activation+0.249
establishment
Tokenestablishment
Feature activation+0.055
sounding
Token sounding
Feature activation+0.390
rhetoric
Token rhetoric
Feature activation+0.266
scares
Token scares
Feature activation+0.484
them
Token them
Feature activation+0.426
,
Token,
Feature activation+0.208
especially
Token especially
Feature activation+0.176
is
Token is
Feature activation+0.000
no
Token no
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.184
2
Token 2
Feature activation+0.631
.
Token.
Feature activation+0.377
0
Token0
Feature activation+0.404
!]
Token!]
Feature activation+0.264
Ċ
TokenĊ
Feature activation+0.129
Ċ
TokenĊ
Feature activation+0.089
At
TokenAt
Feature activation+0.060
poster
Token poster
Feature activation+0.000
?
Token?
Feature activation+0.000
Senator
Token Senator
Feature activation+0.000
Obama
Token Obama
Feature activation+0.030
shrugged
Token shrugged
Feature activation+0.656
and
Token and
Feature activation+0.397
said
Token said
Feature activation+0.370
he
Token he
Feature activation+0.261
had
Token had
Feature activation+0.144
"
Token "
Feature activation+0.154
no
Tokenno
Feature activation+0.001

INTERVAL 0.226 - 0.338
CONTAINS 0.071%

originated
Token originated
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Obama
Token Obama
Feature activation+0.000
Administration
Token Administration
Feature activation+0.117
which
Token which
Feature activation+0.297
,
Token,
Feature activation+0.000
at
Token at
Feature activation+0.000
least
Token least
Feature activation+0.000
since
Token since
Feature activation+0.000
2011
Token 2011
Feature activation+0.000
tough
Token tough
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
,
Token,
Feature activation+0.292
appearing
Token appearing
Feature activation+0.200
at
Token at
Feature activation+0.111
the
Token the
Feature activation+0.000
Greens
Token Greens
Feature activation+0.000
boro
Tokenboro
Feature activation+0.000
Donald
Token Donald
Feature activation+0.000
Trump
Token Trump
Feature activation+0.098
not
Token not
Feature activation+0.612
paying
Token paying
Feature activation+0.455
taxes
Token taxes
Feature activation+0.168
two
Token two
Feature activation+0.324
years
Token years
Feature activation+0.124
âĢ¦
TokenâĢ¦
Feature activation+0.166
Back
Token Back
Feature activation+0.103
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
Clinton
Token Clinton
Feature activation+0.000
and
Token and
Feature activation+0.230
the
Token the
Feature activation+0.131
State
Token State
Feature activation+0.000
Department
Token Department
Feature activation+0.000
play
Token play
Feature activation+0.239
?
Token?
Feature activation+0.067
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Daniel
TokenDaniel
Feature activation+0.000
Mah
Token Mah
Feature activation+0.000
of
Token of
Feature activation+0.490
spinning
Token spinning
Feature activation+0.348
conspiracy
Token conspiracy
Feature activation+0.173
theories
Token theories
Feature activation+0.323
to
Token to
Feature activation+0.308
keep
Token keep
Feature activation+0.250
his
Token his
Feature activation+0.186
campaign
Token campaign
Feature activation+0.191
afloat
Token afloat
Feature activation+0.130
.
Token.
Feature activation+0.117
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.113 - 0.226
CONTAINS 0.146%

sarc
Token sarc
Feature activation+0.000
asm
Tokenasm
Feature activation+0.000
,
Token,
Feature activation+0.000
Limbaugh
Token Limbaugh
Feature activation+0.000
would
Token would
Feature activation+0.157
have
Token have
Feature activation+0.123
been
Token been
Feature activation+0.052
calling
Token calling
Feature activation+0.000
for
Token for
Feature activation+0.000
a
Token a
Feature activation+0.000
return
Token return
Feature activation+0.000
ozy
Tokenozy
Feature activation+0.130
has
Token has
Feature activation+0.255
taken
Token taken
Feature activation+0.210
his
Token his
Feature activation+0.190
country
Token country
Feature activation+0.132
back
Token back
Feature activation+0.135
into
Token into
Feature activation+0.000
the
Token the
Feature activation+0.000
Atlantic
Token Atlantic
Feature activation+0.000
fold
Token fold
Feature activation+0.000
It
Token It
Feature activation+0.000
.
Token.
Feature activation+0.000
Keith
Token Keith
Feature activation+0.000
Ellison
Token Ellison
Feature activation+0.112
(
Token (
Feature activation+0.258
D
TokenD
Feature activation+0.262
-
Token-
Feature activation+0.196
MN
TokenMN
Feature activation+0.091
)
Token)
Feature activation+0.000
was
Token was
Feature activation+0.186
recently
Token recently
Feature activation+0.024
called
Token called
Feature activation+0.229
his
Token his
Feature activation+0.123
allies
Token allies
Feature activation+0.000
in
Token in
Feature activation+0.163
the
Token the
Feature activation+0.056
current
Token current
Feature activation+0.030
inter
Token inter
Feature activation+0.129
-
Token-
Feature activation+0.000
agency
Tokenagency
Feature activation+0.000
debate
Token debate
Feature activation+0.072
do
Token do
Feature activation+0.114
not
Token not
Feature activation+0.044
Obamacare
Token Obamacare
Feature activation+0.239
would
Token would
Feature activation+0.491
reduce
Token reduce
Feature activation+0.269
the
Token the
Feature activation+0.235
deficit
Token deficit
Feature activation+0.099
by
Token by
Feature activation+0.129
$
Token $
Feature activation+0.091
100
Token100
Feature activation+0.000
billion
Token billion
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000

INTERVAL 0.000 - 0.113
CONTAINS 99.716%

,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
last
Token last
Feature activation+0.000
ten
Token ten
Feature activation+0.000
years
Token years
Feature activation+0.000
have
Token have
Feature activation+0.000
seen
Token seen
Feature activation+0.000
an
Token an
Feature activation+0.000
explosion
Token explosion
Feature activation+0.000
of
Token of
Feature activation+0.000
thoughtful
Token thoughtful
Feature activation+0.000
),
Token),
Feature activation+0.000
founded
Token founded
Feature activation+0.000
by
Token by
Feature activation+0.000
Paul
Token Paul
Feature activation+0.000
E
Token E
Feature activation+0.000
lam
Tokenlam
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
USA
Token USA
Feature activation+0.000
,
Token,
Feature activation+0.000
is
Token is
Feature activation+0.000
duty
Token duty
Feature activation+0.000
as
Token as
Feature activation+0.000
an
Token an
Feature activation+0.000
Army
Token Army
Feature activation+0.000
Journal
Token Journal
Feature activation+0.000
ist
Tokenist
Feature activation+0.000
.
Token.
Feature activation+0.000
The
Token The
Feature activation+0.000
paper
Token paper
Feature activation+0.000
I
Token I
Feature activation+0.000
worked
Token worked
Feature activation+0.000
wrote
Token wrote
Feature activation+0.000
HR
Token HR
Feature activation+0.000
W
TokenW
Feature activation+0.000
senior
Token senior
Feature activation+0.000
researcher
Token researcher
Feature activation+0.000
Amanda
Token Amanda
Feature activation+0.000
Kl
Token Kl
Feature activation+0.000
asing
Tokenasing
Feature activation+0.000
in
Token in
Feature activation+0.000
a
Token a
Feature activation+0.000
report
Token report
Feature activation+0.000
of
Token of
Feature activation+0.000
conference
Token conference
Feature activation+0.000
play
Token play
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
100
Token100
Feature activation+0.000
%
Token%
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
12
Token 12
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 H1.4: (feature 23125)

TOP ACTIVATIONS
MAX = 1.132

Bill
Token Bill
Feature activation+0.644
ingham
Tokeningham
Feature activation+0.731
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
and
Token and
Feature activation+0.811
Ed
Token Ed
Feature activation+0.475
Arm
Token Arm
Feature activation+0.624
br
Tokenbr
Feature activation+0.604
Lewis
Token Lewis
Feature activation+0.379
Walters
Token Walters
Feature activation+0.549
and
Token and
Feature activation+0.787
Chris
Token Chris
Feature activation+0.706
Dawson
Token Dawson
Feature activation+0.504
amongst
Token amongst
Feature activation+1.099
a
Token a
Feature activation+0.822
crop
Token crop
Feature activation+0.667
of
Token of
Feature activation+0.690
outstanding
Token outstanding
Feature activation+0.545
young
Token young
Feature activation+0.420
ingham
Tokeningham
Feature activation+0.731
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
and
Token and
Feature activation+0.811
Ed
Token Ed
Feature activation+0.475
Arm
Token Arm
Feature activation+0.624
br
Tokenbr
Feature activation+0.604
ister
Tokenister
Feature activation+0.621
Logan
Token Logan
Feature activation+0.040
Taylor
Token Taylor
Feature activation+0.126
and
Token and
Feature activation+0.502
Ronnie
Token Ronnie
Feature activation+0.190
Gideon
Token Gideon
Feature activation+0.266
each
Token each
Feature activation+0.870
knocked
Token knocked
Feature activation+0.634
in
Token in
Feature activation+0.436
two
Token two
Feature activation+0.441
runs
Token runs
Feature activation+0.343
to
Token to
Feature activation+0.156
Walters
Token Walters
Feature activation+0.549
and
Token and
Feature activation+0.787
Chris
Token Chris
Feature activation+0.706
Dawson
Token Dawson
Feature activation+0.504
amongst
Token amongst
Feature activation+1.099
a
Token a
Feature activation+0.822
crop
Token crop
Feature activation+0.667
of
Token of
Feature activation+0.690
outstanding
Token outstanding
Feature activation+0.545
young
Token young
Feature activation+0.420
players
Token players
Feature activation+0.253
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
and
Token and
Feature activation+0.811
Ed
Token Ed
Feature activation+0.475
Arm
Token Arm
Feature activation+0.624
br
Tokenbr
Feature activation+0.604
ister
Tokenister
Feature activation+0.621
.
Token.
Feature activation+0.633
Jones
Token Jones
Feature activation+0.059
and
Token and
Feature activation+0.265
Mary
Token Mary
Feature activation+0.204
Louise
Token Louise
Feature activation+0.243
Parker
Token Parker
Feature activation+0.499
as
Token as
Feature activation+0.807
women
Token women
Feature activation+0.464
âĢ
TokenâĢ
Feature activation+0.328
Ļ
TokenĻ
Feature activation+0.209
s
Tokens
Feature activation+0.237
rights
Token rights
Feature activation+0.246
James
Token James
Feature activation+0.354
Wilson
Token Wilson
Feature activation+0.463
,
Token,
Feature activation+0.643
Nick
Token Nick
Feature activation+0.356
Powell
Token Powell
Feature activation+0.527
and
Token and
Feature activation+0.807
Patrick
Token Patrick
Feature activation+0.573
McN
Token McN
Feature activation+0.662
air
Tokenair
Feature activation+0.629
,
Token,
Feature activation+0.636
but
Token but
Feature activation+0.655
Jack
Token Jack
Feature activation+0.438
Bill
Token Bill
Feature activation+0.644
ingham
Tokeningham
Feature activation+0.731
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
and
Token and
Feature activation+0.811
Ed
Token Ed
Feature activation+0.475
Arm
Token Arm
Feature activation+0.624
vin
Tokenvin
Feature activation+0.473
Phillips
Token Phillips
Feature activation+0.289
,
Token,
Feature activation+0.638
Lewis
Token Lewis
Feature activation+0.379
Walters
Token Walters
Feature activation+0.549
and
Token and
Feature activation+0.787
Chris
Token Chris
Feature activation+0.706
Dawson
Token Dawson
Feature activation+0.504
amongst
Token amongst
Feature activation+1.099
a
Token a
Feature activation+0.822
crop
Token crop
Feature activation+0.667
John
Token John
Feature activation+0.276
Edward
Token Edward
Feature activation+0.243
,
Token,
Feature activation+0.603
John
Token John
Feature activation+0.400
Holland
Token Holland
Feature activation+0.335
and
Token and
Feature activation+0.782
James
Token James
Feature activation+0.364
Van
Token Van
Feature activation+0.699
Pra
Token Pra
Feature activation+0.690
agh
Tokenagh
Feature activation+0.654
,
Token,
Feature activation+0.652
smith
Tokensmith
Feature activation+0.367
and
Token and
Feature activation+0.541
Johnny
Token Johnny
Feature activation+0.461
Bans
Token Bans
Feature activation+0.522
field
Tokenfield
Feature activation+0.733
as
Token as
Feature activation+0.769
two
Token two
Feature activation+0.595
returning
Token returning
Feature activation+0.508
1
Token 1
Feature activation+0.392
st
Tokenst
Feature activation+0.359
-
Token-
Feature activation+0.235
Alec
Token Alec
Feature activation+0.036
Martinez
Token Martinez
Feature activation+0.118
and
Token and
Feature activation+0.652
Justin
Token Justin
Feature activation+0.536
Williams
Token Williams
Feature activation+0.413
.
Token.
Feature activation+0.758
After
Token After
Feature activation+0.535
finding
Token finding
Feature activation+0.416
out
Token out
Feature activation+0.336
that
Token that
Feature activation+0.277
the
Token the
Feature activation+0.129
Michael
Token Michael
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.041
and
Token and
Feature activation+0.390
John
Token John
Feature activation+0.297
Pearson
Token Pearson
Feature activation+0.423
comic
Token comic
Feature activation+0.757
,
Token,
Feature activation+0.389
with
Token with
Feature activation+0.434
work
Token work
Feature activation+0.407
from
Token from
Feature activation+0.396
Steve
Token Steve
Feature activation+0.237
Jim
Token Jim
Feature activation+0.301
Clark
Token Clark
Feature activation+0.217
,
Token,
Feature activation+0.549
Jack
Token Jack
Feature activation+0.378
Br
Token Br
Feature activation+0.536
ab
Tokenab
Feature activation+0.740
ham
Tokenham
Feature activation+0.516
,
Token,
Feature activation+0.471
Jo
Token Jo
Feature activation+0.227
S
Token S
Feature activation+0.230
iff
Tokeniff
Feature activation+0.291
Jer
Token Jer
Feature activation+0.275
m
Tokenm
Feature activation+0.324
aine
Tokenaine
Feature activation+0.314
Jen
Token Jen
Feature activation+0.280
as
Tokenas
Feature activation+0.533
potential
Token potential
Feature activation+0.739
make
Token make
Feature activation+0.650
weights
Tokenweights
Feature activation+0.340
in
Token in
Feature activation+0.367
a
Token a
Feature activation+0.229
deal
Token deal
Feature activation+0.150
High
Token High
Feature activation+0.523
smith
Tokensmith
Feature activation+0.367
and
Token and
Feature activation+0.541
Johnny
Token Johnny
Feature activation+0.461
Bans
Token Bans
Feature activation+0.522
field
Tokenfield
Feature activation+0.733
as
Token as
Feature activation+0.769
two
Token two
Feature activation+0.595
returning
Token returning
Feature activation+0.508
1
Token 1
Feature activation+0.392
st
Tokenst
Feature activation+0.359
on
Tokenon
Feature activation+0.467
imo
Tokenimo
Feature activation+0.459
for
Token for
Feature activation+0.571
Jack
Token Jack
Feature activation+0.438
Bill
Token Bill
Feature activation+0.644
ingham
Tokeningham
Feature activation+0.731
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
del
Tokendel
Feature activation+0.197
in
Tokenin
Feature activation+0.219
and
Token and
Feature activation+0.275
Margaret
Token Margaret
Feature activation+0.256
Lewis
Token Lewis
Feature activation+0.414
show
Token show
Feature activation+0.728
,
Token,
Feature activation+0.490
the
Token the
Feature activation+0.423
disappearance
Token disappearance
Feature activation+0.286
of
Token of
Feature activation+0.290
much
Token much
Feature activation+0.145
Aff
Token Aff
Feature activation+0.172
leck
Tokenleck
Feature activation+0.295
and
Token and
Feature activation+0.453
Alan
Token Alan
Feature activation+0.423
Ar
Token Ar
Feature activation+0.432
kin
Tokenkin
Feature activation+0.710
will
Token will
Feature activation+0.663
get
Token get
Feature activation+0.483
recognized
Token recognized
Feature activation+0.279
in
Token in
Feature activation+0.241
the
Token the
Feature activation+0.204

Top DFA by src position
MAX = 0.467

Jack
Token Jack
Feature activation+0.150
Top resid features:
Bill
Token Bill
Feature activation+0.135
Top resid features:
ingham
Tokeningham
Feature activation+0.085
Top resid features:
.
Token.
Feature activation+0.076
Top resid features:
Dennis
Token Dennis
Feature activation+0.377
Top resid features:
Mickey
Token Mickey
Feature activation+0.444
Top resid features:
came
Token came
Feature activation+0.004
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ed
Token Ed
Feature activation+0.000
Top resid features:
Arm
Token Arm
Feature activation+0.000
Top resid features:
Phillips
Token Phillips
Feature activation+0.131
Top resid features:
,
Token,
Feature activation+0.023
Top resid features:
Lewis
Token Lewis
Feature activation+0.169
Top resid features:
Walters
Token Walters
Feature activation+0.185
Top resid features:
and
Token and
Feature activation+0.054
Top resid features:
Chris
Token Chris
Feature activation+0.372
Top resid features:
Dawson
Token Dawson
Feature activation+0.274
Top resid features:
amongst
Token amongst
Feature activation+0.069
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
crop
Token crop
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Jack
Token Jack
Feature activation+0.141
Top resid features:
Bill
Token Bill
Feature activation+0.129
Top resid features:
ingham
Tokeningham
Feature activation+0.082
Top resid features:
.
Token.
Feature activation+0.065
Top resid features:
Dennis
Token Dennis
Feature activation+0.314
Top resid features:
Mickey
Token Mickey
Feature activation+0.403
Top resid features:
came
Token came
Feature activation+0.022
Top resid features:
over
Token over
Feature activation-0.015
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ed
Token Ed
Feature activation+0.000
Top resid features:
Arm
Token Arm
Feature activation+0.000
Top resid features:
,
Token ,
Feature activation+0.039
Top resid features:
Logan
Token Logan
Feature activation+0.191
Top resid features:
Taylor
Token Taylor
Feature activation+0.184
Top resid features:
and
Token and
Feature activation+0.060
Top resid features:
Ronnie
Token Ronnie
Feature activation+0.285
Top resid features:
Gideon
Token Gideon
Feature activation+0.408
Top resid features:
each
Token each
Feature activation+0.031
Top resid features:
knocked
Token knocked
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
runs
Token runs
Feature activation+0.000
Top resid features:
Phillips
Token Phillips
Feature activation+0.133
Top resid features:
,
Token,
Feature activation+0.020
Top resid features:
Lewis
Token Lewis
Feature activation+0.152
Top resid features:
Walters
Token Walters
Feature activation+0.159
Top resid features:
and
Token and
Feature activation+0.032
Top resid features:
Chris
Token Chris
Feature activation+0.284
Top resid features:
Dawson
Token Dawson
Feature activation+0.264
Top resid features:
amongst
Token amongst
Feature activation+0.038
Top resid features:
a
Token a
Feature activation+0.016
Top resid features:
crop
Token crop
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
Jack
Token Jack
Feature activation+0.144
Top resid features:
Bill
Token Bill
Feature activation+0.124
Top resid features:
ingham
Tokeningham
Feature activation+0.078
Top resid features:
.
Token.
Feature activation+0.063
Top resid features:
Dennis
Token Dennis
Feature activation+0.276
Top resid features:
Mickey
Token Mickey
Feature activation+0.310
Top resid features:
came
Token came
Feature activation+0.028
Top resid features:
over
Token over
Feature activation+0.016
Top resid features:
and
Token and
Feature activation+0.069
Top resid features:
Ed
Token Ed
Feature activation+0.000
Top resid features:
Arm
Token Arm
Feature activation+0.000
Top resid features:
ve
Tokenve
Feature activation+0.036
Top resid features:
Jones
Token Jones
Feature activation+0.168
Top resid features:
and
Token and
Feature activation+0.072
Top resid features:
Mary
Token Mary
Feature activation+0.287
Top resid features:
Louise
Token Louise
Feature activation+0.290
Top resid features:
Parker
Token Parker
Feature activation+0.297
Top resid features:
as
Token as
Feature activation+0.066
Top resid features:
women
Token women
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:
s
Tokens
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.009
Top resid features:
James
Token James
Feature activation+0.181
Top resid features:
Wilson
Token Wilson
Feature activation+0.188
Top resid features:
,
Token,
Feature activation-0.001
Top resid features:
Nick
Token Nick
Feature activation+0.262
Top resid features:
Powell
Token Powell
Feature activation+0.269
Top resid features:
and
Token and
Feature activation+0.039
Top resid features:
Patrick
Token Patrick
Feature activation+0.000
Top resid features:
McN
Token McN
Feature activation+0.000
Top resid features:
air
Tokenair
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
for
Token for
Feature activation+0.032
Top resid features:
Jack
Token Jack
Feature activation+0.162
Top resid features:
Bill
Token Bill
Feature activation+0.144
Top resid features:
ingham
Tokeningham
Feature activation+0.112
Top resid features:
.
Token.
Feature activation+0.061
Top resid features:
Dennis
Token Dennis
Feature activation+0.365
Top resid features:
Mickey
Token Mickey
Feature activation+0.139
Top resid features:
came
Token came
Feature activation+0.000
Top resid features:
over
Token over
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Ed
Token Ed
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.286
Top resid features:
pay
Token pay
Feature activation+0.008
Top resid features:
a
Token a
Feature activation-0.005
Top resid features:
special
Token special
Feature activation+0.002
Top resid features:
tribute
Token tribute
Feature activation+0.006
Top resid features:
to
Token to
Feature activation+0.003
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.281
Top resid features:
the
Token the
Feature activation-0.007
Top resid features:
hope
Token hope
Feature activation+0.008
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
contacting
Token contacting
Feature activation+0.007
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.285
Top resid features:
longer
Token longer
Feature activation+0.004
Top resid features:
have
Token have
Feature activation+0.005
Top resid features:
a
Token a
Feature activation-0.004
Top resid features:
coach
Token coach
Feature activation+0.003
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
A
TokenA
Feature activation+0.019
Top resid features:
.
Token.
Feature activation+0.015
Top resid features:
Kings
Token Kings
Feature activation+0.113
Top resid features:
players
Token players
Feature activation+0.053
Top resid features:
Alec
Token Alec
Feature activation+0.278
Top resid features:
Martinez
Token Martinez
Feature activation+0.205
Top resid features:
and
Token and
Feature activation+0.042
Top resid features:
Justin
Token Justin
Feature activation+0.252
Top resid features:
Williams
Token Williams
Feature activation+0.258
Top resid features:
.
Token.
Feature activation+0.052
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.283
Top resid features:
s
Tokens
Feature activation-0.005
Top resid features:
future
Token future
Feature activation+0.001
Top resid features:
,
Token,
Feature activation-0.005
Top resid features:
teased
Token teased
Feature activation+0.008
Top resid features:
on
Token on
Feature activation+0.002
Top resid features:
Hill
Token Hill
Feature activation+0.131
Top resid features:
,
Token,
Feature activation+0.008
Top resid features:
Jim
Token Jim
Feature activation+0.182
Top resid features:
Clark
Token Clark
Feature activation+0.247
Top resid features:
,
Token,
Feature activation-0.013
Top resid features:
Jack
Token Jack
Feature activation+0.293
Top resid features:
Br
Token Br
Feature activation+0.079
Top resid features:
ab
Tokenab
Feature activation+0.052
Top resid features:
ham
Tokenham
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Jo
Token Jo
Feature activation+0.000
Top resid features:
Bentley
Token Bentley
Feature activation+0.152
Top resid features:
or
Token or
Feature activation+0.003
Top resid features:
Jer
Token Jer
Feature activation+0.164
Top resid features:
m
Tokenm
Feature activation+0.008
Top resid features:
aine
Tokenaine
Feature activation+0.088
Top resid features:
Jen
Token Jen
Feature activation+0.318
Top resid features:
as
Tokenas
Feature activation+0.047
Top resid features:
potential
Token potential
Feature activation+0.035
Top resid features:
make
Token make
Feature activation+0.000
Top resid features:
weights
Tokenweights
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.046
Top resid features:
James
Token James
Feature activation+0.184
Top resid features:
High
Token High
Feature activation+0.063
Top resid features:
smith
Tokensmith
Feature activation+0.117
Top resid features:
and
Token and
Feature activation+0.035
Top resid features:
Johnny
Token Johnny
Feature activation+0.327
Top resid features:
Bans
Token Bans
Feature activation+0.126
Top resid features:
field
Tokenfield
Feature activation+0.141
Top resid features:
as
Token as
Feature activation+0.000
Top resid features:
two
Token two
Feature activation+0.000
Top resid features:
returning
Token returning
Feature activation+0.000
Top resid features:
esar
Tokenesar
Feature activation+0.107
Top resid features:
Ger
Token Ger
Feature activation+0.110
Top resid features:
on
Tokenon
Feature activation+0.048
Top resid features:
imo
Tokenimo
Feature activation+0.103
Top resid features:
for
Token for
Feature activation+0.026
Top resid features:
Jack
Token Jack
Feature activation+0.314
Top resid features:
Bill
Token Bill
Feature activation+0.312
Top resid features:
ingham
Tokeningham
Feature activation+0.023
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
Dennis
Token Dennis
Feature activation+0.000
Top resid features:
Mickey
Token Mickey
Feature activation+0.000
Top resid features:
Wer
Token Wer
Feature activation+0.095
Top resid features:
del
Tokendel
Feature activation+0.052
Top resid features:
in
Tokenin
Feature activation+0.050
Top resid features:
and
Token and
Feature activation+0.045
Top resid features:
Margaret
Token Margaret
Feature activation+0.313
Top resid features:
Lewis
Token Lewis
Feature activation+0.357
Top resid features:
show
Token show
Feature activation+0.075
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
disappearance
Token disappearance
Feature activation+0.000
Top resid features:
of
Token of
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.029
Top resid features:
Ben
Token Ben
Feature activation+0.184
Top resid features:
Aff
Token Aff
Feature activation+0.057
Top resid features:
leck
Tokenleck
Feature activation+0.121
Top resid features:
and
Token and
Feature activation+0.024
Top resid features:
Alan
Token Alan
Feature activation+0.467
Top resid features:
Ar
Token Ar
Feature activation+0.043
Top resid features:
kin
Tokenkin
Feature activation+0.125
Top resid features:
will
Token will
Feature activation+0.000
Top resid features:
get
Token get
Feature activation+0.000
Top resid features:
recognized
Token recognized
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.09

Head 1: 0.18

Head 2: 0.12

Head 3: 0.05

Head 4: 0.14

Head 5: 0.03

Head 6: 0.02

Head 7: 0.09

Head 8: 0.04

Head 9: 0.03

Head 10: 0.13

Head 11: 0.07

Positive logits

ken1.98

itone1.87

tein1.80

quez1.74

ourke1.74

QC1.73

eus1.70

pton1.68

Jr1.67

herty1.67

ivas1.63

himself1.62

hner1.60

Quan1.60

cz1.57

Sr1.57

1.57

nick1.56

bart1.56

igl1.55

Negative logits

ancial-1.65

conformity-1.53

indoors-1.44

excluding-1.43

consumers-1.39

FIX-1.38

polarization-1.36

divided-1.35

representation-1.35

varied-1.33

standings-1.32

favourable-1.31

composition-1.31

compliant-1.30

unfavorable-1.29

incompatible-1.29

objective-1.28

overnight-1.28

organs-1.26

indexes-1.26

INTERVAL 1.019 - 1.132
CONTAINS 0.000%

Lewis
Token Lewis
Feature activation+0.379
Walters
Token Walters
Feature activation+0.549
and
Token and
Feature activation+0.787
Chris
Token Chris
Feature activation+0.706
Dawson
Token Dawson
Feature activation+0.504
amongst
Token amongst
Feature activation+1.099
a
Token a
Feature activation+0.822
crop
Token crop
Feature activation+0.667
of
Token of
Feature activation+0.690
outstanding
Token outstanding
Feature activation+0.545
young
Token young
Feature activation+0.420
Bill
Token Bill
Feature activation+0.644
ingham
Tokeningham
Feature activation+0.731
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
and
Token and
Feature activation+0.811
Ed
Token Ed
Feature activation+0.475
Arm
Token Arm
Feature activation+0.624
br
Tokenbr
Feature activation+0.604

INTERVAL 0.906 - 1.019
CONTAINS 0.000%

ingham
Tokeningham
Feature activation+0.731
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
and
Token and
Feature activation+0.811
Ed
Token Ed
Feature activation+0.475
Arm
Token Arm
Feature activation+0.624
br
Tokenbr
Feature activation+0.604
ister
Tokenister
Feature activation+0.621

INTERVAL 0.793 - 0.906
CONTAINS 0.001%

Jones
Token Jones
Feature activation+0.059
and
Token and
Feature activation+0.265
Mary
Token Mary
Feature activation+0.204
Louise
Token Louise
Feature activation+0.243
Parker
Token Parker
Feature activation+0.499
as
Token as
Feature activation+0.807
women
Token women
Feature activation+0.464
âĢ
TokenâĢ
Feature activation+0.328
Ļ
TokenĻ
Feature activation+0.209
s
Tokens
Feature activation+0.237
rights
Token rights
Feature activation+0.246
Logan
Token Logan
Feature activation+0.040
Taylor
Token Taylor
Feature activation+0.126
and
Token and
Feature activation+0.502
Ronnie
Token Ronnie
Feature activation+0.190
Gideon
Token Gideon
Feature activation+0.266
each
Token each
Feature activation+0.870
knocked
Token knocked
Feature activation+0.634
in
Token in
Feature activation+0.436
two
Token two
Feature activation+0.441
runs
Token runs
Feature activation+0.343
to
Token to
Feature activation+0.156
Walters
Token Walters
Feature activation+0.549
and
Token and
Feature activation+0.787
Chris
Token Chris
Feature activation+0.706
Dawson
Token Dawson
Feature activation+0.504
amongst
Token amongst
Feature activation+1.099
a
Token a
Feature activation+0.822
crop
Token crop
Feature activation+0.667
of
Token of
Feature activation+0.690
outstanding
Token outstanding
Feature activation+0.545
young
Token young
Feature activation+0.420
players
Token players
Feature activation+0.253
.
Token.
Feature activation+0.677
Dennis
Token Dennis
Feature activation+0.511
Mickey
Token Mickey
Feature activation+0.789
came
Token came
Feature activation+1.132
over
Token over
Feature activation+0.953
and
Token and
Feature activation+0.811
Ed
Token Ed
Feature activation+0.475
Arm
Token Arm
Feature activation+0.624
br
Tokenbr
Feature activation+0.604
ister
Tokenister
Feature activation+0.621
.
Token.
Feature activation+0.633
James
Token James
Feature activation+0.354
Wilson
Token Wilson
Feature activation+0.463
,
Token,
Feature activation+0.643
Nick
Token Nick
Feature activation+0.356
Powell
Token Powell
Feature activation+0.527
and
Token and
Feature activation+0.807
Patrick
Token Patrick
Feature activation+0.573
McN
Token McN
Feature activation+0.662
air
Tokenair
Feature activation+0.629
,
Token,
Feature activation+0.636
but
Token but
Feature activation+0.655

INTERVAL 0.679 - 0.793
CONTAINS 0.002%

As
TokenAs
Feature activation+0.001
Claire
Token Claire
Feature activation+0.000
Cain
Token Cain
Feature activation+0.236
Miller
Token Miller
Feature activation+0.451
wrote
Token wrote
Feature activation+0.647
at
Token at
Feature activation+0.680
the
Token the
Feature activation+0.500
Ups
Token Ups
Feature activation+0.360
hot
Tokenhot
Feature activation+0.466
,
Token,
Feature activation+0.351
the
Token the
Feature activation+0.342
ha
Tokenha
Feature activation+0.037
Ald
Token Ald
Feature activation+0.172
erman
Tokenerman
Feature activation+0.179
Aaron
Token Aaron
Feature activation+0.366
Perry
Token Perry
Feature activation+0.541
and
Token and
Feature activation+0.700
friends
Token friends
Feature activation+0.674
(
Token (
Feature activation+0.511
one
Tokenone
Feature activation+0.193
who
Token who
Feature activation+0.284
appears
Token appears
Feature activation+0.152
Michael
Token Michael
Feature activation+0.000
Johnson
Token Johnson
Feature activation+0.041
and
Token and
Feature activation+0.390
John
Token John
Feature activation+0.297
Pearson
Token Pearson
Feature activation+0.423
comic
Token comic
Feature activation+0.757
,
Token,
Feature activation+0.389
with
Token with
Feature activation+0.434
work
Token work
Feature activation+0.407
from
Token from
Feature activation+0.396
Steve
Token Steve
Feature activation+0.237
Phillips
Token Phillips
Feature activation+0.289
,
Token,
Feature activation+0.638
Lewis
Token Lewis
Feature activation+0.379
Walters
Token Walters
Feature activation+0.549
and
Token and
Feature activation+0.787
Chris
Token Chris
Feature activation+0.706
Dawson
Token Dawson
Feature activation+0.504
amongst
Token amongst
Feature activation+1.099
a
Token a
Feature activation+0.822
crop
Token crop
Feature activation+0.667
of
Token of
Feature activation+0.690
John
Token John
Feature activation+0.276
Edward
Token Edward
Feature activation+0.243
,
Token,
Feature activation+0.603
John
Token John
Feature activation+0.400
Holland
Token Holland
Feature activation+0.335
and
Token and
Feature activation+0.782
James
Token James
Feature activation+0.364
Van
Token Van
Feature activation+0.699
Pra
Token Pra
Feature activation+0.690
agh
Tokenagh
Feature activation+0.654
,
Token,
Feature activation+0.652

INTERVAL 0.566 - 0.679
CONTAINS 0.006%

ab
Tokenab
Feature activation+0.282
oni
Tokenoni
Feature activation+0.215
&
Token &
Feature activation+0.504
Whit
Token Whit
Feature activation+0.227
mer
Tokenmer
Feature activation+0.461
discuss
Token discuss
Feature activation+0.625
Adam
Token Adam
Feature activation+0.328
Page
Token Page
Feature activation+0.522
turning
Token turning
Feature activation+0.620
on
Token on
Feature activation+0.525
Whit
Token Whit
Feature activation+0.182
,
Token,
Feature activation+0.643
Nick
Token Nick
Feature activation+0.356
Powell
Token Powell
Feature activation+0.527
and
Token and
Feature activation+0.807
Patrick
Token Patrick
Feature activation+0.573
McN
Token McN
Feature activation+0.662
air
Tokenair
Feature activation+0.629
,
Token,
Feature activation+0.636
but
Token but
Feature activation+0.655
these
Token these
Feature activation+0.562
players
Token players
Feature activation+0.331
leck
Tokenleck
Feature activation+0.295
and
Token and
Feature activation+0.453
Alan
Token Alan
Feature activation+0.423
Ar
Token Ar
Feature activation+0.432
kin
Tokenkin
Feature activation+0.710
will
Token will
Feature activation+0.663
get
Token get
Feature activation+0.483
recognized
Token recognized
Feature activation+0.279
in
Token in
Feature activation+0.241
the
Token the
Feature activation+0.204
process
Token process
Feature activation+0.160
Holland
Token Holland
Feature activation+0.335
and
Token and
Feature activation+0.782
James
Token James
Feature activation+0.364
Van
Token Van
Feature activation+0.699
Pra
Token Pra
Feature activation+0.690
agh
Tokenagh
Feature activation+0.654
,
Token,
Feature activation+0.652
select
Token select
Feature activation+0.654
individuals
Token individuals
Feature activation+0.574
from
Token from
Feature activation+0.624
their
Token their
Feature activation+0.427
Hamilton
Token Hamilton
Feature activation+0.189
's
Token's
Feature activation+0.380
Brandon
Token Brandon
Feature activation+0.198
Victor
Token Victor
Feature activation+0.119
Dixon
Token Dixon
Feature activation+0.324
.
Token.
Feature activation+0.591
All
Token All
Feature activation+0.384
five
Token five
Feature activation+0.312
stand
Token stand
Feature activation+0.270
together
Token together
Feature activation+0.218
holding
Token holding
Feature activation+0.119

INTERVAL 0.453 - 0.566
CONTAINS 0.015%

ade
Tokenade
Feature activation+0.093
and
Token and
Feature activation+0.264
Jonathan
Token Jonathan
Feature activation+0.142
Joseph
Token Joseph
Feature activation+0.089
will
Token will
Feature activation+0.597
travel
Token travel
Feature activation+0.565
and
Token and
Feature activation+0.350
this
Token this
Feature activation+0.317
gives
Token gives
Feature activation+0.197
Jones
Token Jones
Feature activation+0.000
a
Token a
Feature activation+0.168
,
Token,
Feature activation+0.505
and
Token and
Feature activation+0.528
Elizabeth
Token Elizabeth
Feature activation+0.264
Cron
Token Cron
Feature activation+0.455
in
Tokenin
Feature activation+0.488
.
Token.
Feature activation+0.467
We
Token We
Feature activation+0.355
are
Token are
Feature activation+0.306
a
Token a
Feature activation+0.267
group
Token group
Feature activation+0.160
of
Token of
Feature activation+0.251
Jr
Token Jr
Feature activation+0.092
and
Token and
Feature activation+0.315
Samuel
Token Samuel
Feature activation+0.193
L
Token L
Feature activation+0.182
Jackson
Token Jackson
Feature activation+0.198
are
Token are
Feature activation+0.521
among
Token among
Feature activation+0.366
the
Token the
Feature activation+0.232
stars
Token stars
Feature activation+0.235
said
Token said
Feature activation+0.205
to
Token to
Feature activation+0.027
Randy
Token Randy
Feature activation+0.067
Fleming
Token Fleming
Feature activation+0.327
,
Token,
Feature activation+0.461
a
Token a
Feature activation+0.511
man
Token man
Feature activation+0.379
who
Token who
Feature activation+0.456
sustained
Token sustained
Feature activation+0.337
permanent
Token permanent
Feature activation+0.267
injuries
Token injuries
Feature activation+0.192
when
Token when
Feature activation+0.184
he
Token he
Feature activation+0.097
Pierce
Token Pierce
Feature activation+0.326
,
Token,
Feature activation+0.505
and
Token and
Feature activation+0.528
Elizabeth
Token Elizabeth
Feature activation+0.264
Cron
Token Cron
Feature activation+0.455
in
Tokenin
Feature activation+0.488
.
Token.
Feature activation+0.467
We
Token We
Feature activation+0.355
are
Token are
Feature activation+0.306
a
Token a
Feature activation+0.267
group
Token group
Feature activation+0.160

INTERVAL 0.340 - 0.453
CONTAINS 0.047%

Edward
Token Edward
Feature activation+0.243
,
Token,
Feature activation+0.603
John
Token John
Feature activation+0.400
Holland
Token Holland
Feature activation+0.335
and
Token and
Feature activation+0.782
James
Token James
Feature activation+0.364
Van
Token Van
Feature activation+0.699
Pra
Token Pra
Feature activation+0.690
agh
Tokenagh
Feature activation+0.654
,
Token,
Feature activation+0.652
select
Token select
Feature activation+0.654
Ivan
Token Ivan
Feature activation+0.000
ov
Tokenov
Feature activation+0.135
.
Token.
Feature activation+0.183
Sandra
Token Sandra
Feature activation+0.000
Ivan
Token Ivan
Feature activation+0.168
ov
Tokenov
Feature activation+0.426
is
Token is
Feature activation+0.463
from
Token from
Feature activation+0.496
New
Token New
Feature activation+0.246
Zealand
Token Zealand
Feature activation+0.112
with
Token with
Feature activation+0.340
Ed
Token Ed
Feature activation+0.067
el
Tokenel
Feature activation+0.148
mann
Tokenmann
Feature activation+0.214
who
Token who
Feature activation+0.373
heard
Token heard
Feature activation+0.356
this
Token this
Feature activation+0.356
one
Token one
Feature activation+0.374
all
Token all
Feature activation+0.283
the
Token the
Feature activation+0.254
way
Token way
Feature activation+0.094
from
Token from
Feature activation+0.146
Hume
Token Hume
Feature activation+0.000
,
Token,
Feature activation+0.272
Adam
Token Adam
Feature activation+0.139
Smith
Token Smith
Feature activation+0.092
,
Token,
Feature activation+0.386
and
Token and
Feature activation+0.395
Sir
Token Sir
Feature activation+0.221
James
Token James
Feature activation+0.216
Ste
Token Ste
Feature activation+0.315
uart
Tokenuart
Feature activation+0.463
had
Token had
Feature activation+0.524
St
Token St
Feature activation+0.000
.
Token.
Feature activation+0.000
John
Token John
Feature activation+0.000
Mand
Token Mand
Feature activation+0.000
el
Tokenel
Feature activation+0.097
handles
Token handles
Feature activation+0.365
it
Token it
Feature activation+0.098
with
Token with
Feature activation+0.000
a
Token a
Feature activation+0.000
light
Token light
Feature activation+0.000
touch
Token touch
Feature activation+0.000

INTERVAL 0.226 - 0.340
CONTAINS 0.140%

Photo
TokenPhoto
Feature activation+0.000
by
Token by
Feature activation+0.000
Doug
Token Doug
Feature activation+0.000
Mac
Token Mac
Feature activation+0.000
Cash
TokenCash
Feature activation+0.000
/
Token /
Feature activation+0.238
N
Token N
Feature activation+0.000
OL
TokenOL
Feature activation+0.000
A
TokenA
Feature activation+0.000
.
Token.
Feature activation+0.000
com
Tokencom
Feature activation+0.015
Ċ
TokenĊ
Feature activation+0.102
Ċ
TokenĊ
Feature activation+0.058
Follow
TokenFollow
Feature activation+0.000
Samantha
Token Samantha
Feature activation+0.006
on
Token on
Feature activation+0.418
Twitter
Token Twitter
Feature activation+0.249
or
Token or
Feature activation+0.302
visit
Token visit
Feature activation+0.236
her
Token her
Feature activation+0.000
website
Token website
Feature activation+0.031
.
Token.
Feature activation+0.027
quarterback
Token quarterback
Feature activation+0.181
Matt
Token Matt
Feature activation+0.167
Ryan
Token Ryan
Feature activation+0.140
.
Token.
Feature activation+0.344
Well
Token Well
Feature activation+0.166
,
Token,
Feature activation+0.257
he
Token he
Feature activation+0.114
tagged
Token tagged
Feature activation+0.144
him
Token him
Feature activation+0.007
down
Token down
Feature activation+0.073
,
Token,
Feature activation+0.000
Nathan
Token Nathan
Feature activation+0.000
Clifford
Token Clifford
Feature activation+0.108
paid
Token paid
Feature activation+0.536
a
Token a
Feature activation+0.429
visit
Token visit
Feature activation+0.403
to
Token to
Feature activation+0.255
the
Token the
Feature activation+0.116
school
Token school
Feature activation+0.097
and
Token and
Feature activation+0.000
addressed
Token addressed
Feature activation+0.082
the
Token the
Feature activation+0.000
McM
Token McM
Feature activation+0.007
ill
Tokenill
Feature activation+0.174
an
Tokenan
Feature activation+0.287
,
Token,
Feature activation+0.247
neither
Token neither
Feature activation+0.282
of
Token of
Feature activation+0.244
whom
Token whom
Feature activation+0.160
has
Token has
Feature activation+0.095
worked
Token worked
Feature activation+0.068
an
Token an
Feature activation+0.000
event
Token event
Feature activation+0.067

INTERVAL 0.113 - 0.226
CONTAINS 0.348%

former
Token former
Feature activation+0.304
communications
Token communications
Feature activation+0.185
director
Token director
Feature activation+0.119
Mike
Token Mike
Feature activation+0.006
Dub
Token Dub
Feature activation+0.097
ke
Tokenke
Feature activation+0.148
âĢĶ
Token âĢĶ
Feature activation+0.198
are
Token are
Feature activation+0.085
helping
Token helping
Feature activation+0.000
coordinate
Token coordinate
Feature activation+0.000
the
Token the
Feature activation+0.000
enthal
Tokenenthal
Feature activation+0.220
Delete
Token Delete
Feature activation+0.274
Edit
Token Edit
Feature activation+0.384
embedded
Token embedded
Feature activation+0.245
media
Token media
Feature activation+0.234
in
Token in
Feature activation+0.209
the
Token the
Feature activation+0.155
Files
Token Files
Feature activation+0.032
Tab
Token Tab
Feature activation+0.061
and
Token and
Feature activation+0.144
re
Token re
Feature activation+0.168
of
Token of
Feature activation+0.290
the
Token the
Feature activation+0.220
US
Token US
Feature activation+0.098
delegation
Token delegation
Feature activation+0.000
dealing
Token dealing
Feature activation+0.049
with
Token with
Feature activation+0.142
WC
Token WC
Feature activation+0.000
IT
TokenIT
Feature activation+0.000
:
Token:
Feature activation+0.103
Okay
TokenOkay
Feature activation+0.000
,
Token,
Feature activation+0.000
Wednesday
Token Wednesday
Feature activation+0.000
,
Token,
Feature activation+0.000
she
Token she
Feature activation+0.000
said
Token said
Feature activation+0.000
Oliver
Token Oliver
Feature activation+0.000
-
Token-
Feature activation+0.149
Mach
TokenMach
Feature activation+0.000
ado
Tokenado
Feature activation+0.000
did
Token did
Feature activation+0.095
a
Token a
Feature activation+0.080
good
Token good
Feature activation+0.027
Posted
Token Posted
Feature activation+0.000
by
Token by
Feature activation+0.000
George
Token George
Feature activation+0.000
Moss
Token Moss
Feature activation+0.000
on
Token on
Feature activation+0.324
Tuesday
Token Tuesday
Feature activation+0.195
,
Token,
Feature activation+0.127
June
Token June
Feature activation+0.143
23
Token 23
Feature activation+0.050
,
Token,
Feature activation+0.000
2015
Token 2015
Feature activation+0.000

INTERVAL 0.000 - 0.113
CONTAINS 99.442%

on
Token on
Feature activation+0.000
their
Token their
Feature activation+0.000
move
Token move
Feature activation+0.000
for
Token for
Feature activation+0.000
Lac
Token Lac
Feature activation+0.000
az
Tokenaz
Feature activation+0.000
ette
Tokenette
Feature activation+0.000
,
Token,
Feature activation+0.000
whom
Token whom
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
-
Token-
Feature activation+0.000
<|endoftext|>
Token<|endoftext|>
Feature activation+0.000
farming
Token farming
Feature activation+0.000
,
Token,
Feature activation+0.000
etc
Token etc
Feature activation+0.000
,
Token,
Feature activation+0.000
the
Token the
Feature activation+0.000
cost
Token cost
Feature activation+0.000
efficiency
Token efficiency
Feature activation+0.000
side
Token side
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
after
Token after
Feature activation+0.000
10
Token 10
Feature activation+0.000
years
Token years
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
OECD
Token OECD
Feature activation+0.000
average
Token average
Feature activation+0.000
is
Token is
Feature activation+0.000
26
Token 26
Feature activation+0.000
years
Token years
Feature activation+0.000
of
Token of
Feature activation+0.000
businesses
Token businesses
Feature activation+0.000
priced
Token priced
Feature activation+0.000
out
Token out
Feature activation+0.000
of
Token of
Feature activation+0.000
the
Token the
Feature activation+0.000
region
Token region
Feature activation+0.000
,
Token,
Feature activation+0.000
this
Token this
Feature activation+0.000
is
Token is
Feature activation+0.000
an
Token an
Feature activation+0.000
why
Token why
Feature activation+0.000
.
Token.
Feature activation+0.000
It
Token It
Feature activation+0.000
does
Token does
Feature activation+0.000
not
Token not
Feature activation+0.000
take
Token take
Feature activation+0.000
a
Token a
Feature activation+0.000
keen
Token keen
Feature activation+0.000
political
Token political
Feature activation+0.000
mind
Token mind
Feature activation+0.000
to
Token to
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 8 in H1.4: (feature 18366)

TOP ACTIVATIONS
MAX = 1.011

campaign
Token campaign
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
Ni
Token Ni
Feature activation+0.000
elson
Tokenelson
Feature activation+0.000
expressed
Token expressed
Feature activation+1.011
disappointment
Token disappointment
Feature activation+0.719
in
Token in
Feature activation+0.329
that
Token that
Feature activation+0.233
rationale
Token rationale
Feature activation+0.194
,
Token,
Feature activation+0.000
Ja
Token Ja
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
Pod
Token Pod
Feature activation+0.168
kan
Tokenkan
Feature activation+0.171
owicz
Tokenowicz
Feature activation+0.252
told
Token told
Feature activation+0.950
the
Token the
Feature activation+0.532
BBC
Token BBC
Feature activation+0.255
he
Token he
Feature activation+0.534
was
Token was
Feature activation+0.187
at
Token at
Feature activation+0.207
.
Token.
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
Levin
Token Levin
Feature activation+0.185
told
Token told
Feature activation+0.885
his
Token his
Feature activation+0.555
troops
Token troops
Feature activation+0.039
before
Token before
Feature activation+0.279
the
Token the
Feature activation+0.000
operation
Token operation
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sam
TokenSam
Feature activation+0.000
u
Tokenu
Feature activation+0.000
elson
Tokenelson
Feature activation+0.000
acknowledges
Token acknowledges
Feature activation+0.827
there
Token there
Feature activation+0.357
is
Token is
Feature activation+0.474
a
Token a
Feature activation+0.208
debate
Token debate
Feature activation+0.058
to
Token to
Feature activation+0.000
.
Token.
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
De
Token De
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
orio
Tokenorio
Feature activation+0.000
joined
Token joined
Feature activation+0.825
Fifa
Token Fifa
Feature activation+0.000
on
Token on
Feature activation+0.234
14
Token 14
Feature activation+0.009
September
Token September
Feature activation+0.010
2011
Token 2011
Feature activation+0.000
Ŀ
TokenĿ
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Wein
Token Wein
Feature activation+0.000
berger
Tokenberger
Feature activation+0.000
wrote
Token wrote
Feature activation+0.818
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
its
Token its
Feature activation+0.000
Election
Token Election
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
Chair
Token Chair
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
Buchanan
Token Buchanan
Feature activation+0.000
spoke
Token spoke
Feature activation+0.807
with
Token with
Feature activation+0.689
The
Token The
Feature activation+0.178
Tenn
Token Tenn
Feature activation+0.058
esse
Tokenesse
Feature activation+0.000
an
Tokenan
Feature activation+0.000
School
Token School
Feature activation+0.000
Principal
Token Principal
Feature activation+0.000
Charles
Token Charles
Feature activation+0.000
Ab
Token Ab
Feature activation+0.000
ba
Tokenba
Feature activation+0.000
sent
Token sent
Feature activation+0.773
a
Token a
Feature activation+0.349
letter
Token letter
Feature activation+0.150
to
Token to
Feature activation+0.000
parents
Token parents
Feature activation+0.000
pointing
Token pointing
Feature activation+0.200
On
TokenOn
Feature activation+0.000
bond
Token bond
Feature activation+0.000
:
Token:
Feature activation+0.000
Blake
Token Blake
Feature activation+0.000
Ferguson
Token Ferguson
Feature activation+0.000
leaves
Token leaves
Feature activation+0.770
the
Token the
Feature activation+0.183
Sutherland
Token Sutherland
Feature activation+0.000
Local
Token Local
Feature activation+0.020
Court
Token Court
Feature activation+0.000
on
Token on
Feature activation+0.124
okes
Tokenokes
Feature activation+0.000
woman
Tokenwoman
Feature activation+0.027
Jennifer
Token Jennifer
Feature activation+0.049
Young
Token Young
Feature activation+0.012
blood
Tokenblood
Feature activation+0.359
told
Token told
Feature activation+0.769
FP
Token FP
Feature activation+0.039
that
Token that
Feature activation+0.342
the
Token the
Feature activation+0.083
acting
Token acting
Feature activation+0.069
director
Token director
Feature activation+0.021
School
Token School
Feature activation+0.000
professor
Token professor
Feature activation+0.000
Ber
Token Ber
Feature activation+0.000
it
Tokenit
Feature activation+0.000
Berger
Token Berger
Feature activation+0.000
uttered
Token uttered
Feature activation+0.767
this
Token this
Feature activation+0.351
one
Token one
Feature activation+0.319
on
Token on
Feature activation+0.178
the
Token the
Feature activation+0.082
MSNBC
Token MSNBC
Feature activation+0.000
aine
Tokenaine
Feature activation+0.000
Keen
Token Keen
Feature activation+0.000
an
Tokenan
Feature activation+0.000
Beng
Token Beng
Feature activation+0.000
ts
Tokents
Feature activation+0.000
presented
Token presented
Feature activation+0.764
her
Token her
Feature activation+0.424
annual
Token annual
Feature activation+0.218
report
Token report
Feature activation+0.325
at
Token at
Feature activation+0.185
the
Token the
Feature activation+0.047
Hind
Token Hind
Feature activation+0.000
s
Tokens
Feature activation+0.000
Sheriff
Token Sheriff
Feature activation+0.000
Victor
Token Victor
Feature activation+0.000
Mason
Token Mason
Feature activation+0.000
announced
Token announced
Feature activation+0.753
that
Token that
Feature activation+0.354
he
Token he
Feature activation+0.295
and
Token and
Feature activation+0.000
the
Token the
Feature activation+0.000
Morton
Token Morton
Feature activation+0.000
feed
Tokenfeed
Feature activation+0.000
's
Token's
Feature activation+0.066
Ari
Token Ari
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
Lange
Token Lange
Feature activation+0.000
interviewed
Token interviewed
Feature activation+0.734
several
Token several
Feature activation+0.643
sex
Token sex
Feature activation+0.155
workers
Token workers
Feature activation+0.249
who
Token who
Feature activation+0.141
had
Token had
Feature activation+0.162
Director
Token Director
Feature activation+0.000
Dr
Token Dr
Feature activation+0.000
.
Token.
Feature activation+0.000
Francis
Token Francis
Feature activation+0.000
Collins
Token Collins
Feature activation+0.000
described
Token described
Feature activation+0.731
the
Token the
Feature activation+0.002
agreement
Token agreement
Feature activation+0.000
covering
Token covering
Feature activation+0.000
these
Token these
Feature activation+0.000
so
Token so
Feature activation+0.000
ters
Tokenters
Feature activation+0.000
fan
Token fan
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
Rush
Token Rush
Feature activation+0.000
ton
Tokenton
Feature activation+0.136
persuaded
Token persuaded
Feature activation+0.725
him
Token him
Feature activation+0.341
to
Token to
Feature activation+0.010
pack
Token pack
Feature activation+0.207
it
Token it
Feature activation+0.118
.
Token.
Feature activation+0.000
photo
Tokenphoto
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ryan
TokenRyan
Feature activation+0.000
Bundy
Token Bundy
Feature activation+0.000
takes
Token takes
Feature activation+0.723
a
Token a
Feature activation+0.259
phone
Token phone
Feature activation+0.255
call
Token call
Feature activation+0.189
by
Token by
Feature activation+0.011
the
Token the
Feature activation+0.000
ide
Tokenide
Feature activation+0.243
h
Tokenh
Feature activation+0.234
of
Token of
Feature activation+0.101
Kemp
Token Kemp
Feature activation+0.097
Klein
Token Klein
Feature activation+0.218
says
Token says
Feature activation+0.721
the
Token the
Feature activation+0.343
case
Token case
Feature activation+0.323
leaves
Token leaves
Feature activation+0.256
you
Token you
Feature activation+0.223
wondering
Token wondering
Feature activation+0.205
manager
Token manager
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
Ni
Token Ni
Feature activation+0.000
elson
Tokenelson
Feature activation+0.000
expressed
Token expressed
Feature activation+1.011
disappointment
Token disappointment
Feature activation+0.719
in
Token in
Feature activation+0.329
that
Token that
Feature activation+0.233
rationale
Token rationale
Feature activation+0.194
,
Token,
Feature activation+0.000
stating
Token stating
Feature activation+0.232
with
Token with
Feature activation+0.000
Padres
Token Padres
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Andy
Token Andy
Feature activation+0.000
Green
Token Green
Feature activation+0.000
discussing
Token discussing
Feature activation+0.716
it
Token it
Feature activation+0.478
:
Token:
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
H
TokenH
Feature activation+0.000

Top DFA by src position
MAX = 0.476

campaign
Token campaign
Feature activation+0.013
Top resid features:
manager
Token manager
Feature activation+0.032
Top resid features:
Ron
Token Ron
Feature activation+0.242
Top resid features:
Ni
Token Ni
Feature activation+0.169
Top resid features:
elson
Tokenelson
Feature activation+0.231
Top resid features:
expressed
Token expressed
Feature activation+0.465
Top resid features:
disappointment
Token disappointment
Feature activation+0.000
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
rationale
Token rationale
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Ja
Token Ja
Feature activation+0.189
Top resid features:
ison
Tokenison
Feature activation+0.135
Top resid features:
Pod
Token Pod
Feature activation+0.137
Top resid features:
kan
Tokenkan
Feature activation+0.151
Top resid features:
owicz
Tokenowicz
Feature activation+0.216
Top resid features:
told
Token told
Feature activation+0.351
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
BBC
Token BBC
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
was
Token was
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
Dr
Token Dr
Feature activation+0.053
Top resid features:
.
Token.
Feature activation-0.011
Top resid features:
L
Token L
Feature activation+0.049
Top resid features:
.
Token.
Feature activation-0.012
Top resid features:
Scott
Token Scott
Feature activation+0.430
Top resid features:
Levin
Token Levin
Feature activation+0.448
Top resid features:
told
Token told
Feature activation+0.297
Top resid features:
his
Token his
Feature activation+0.000
Top resid features:
troops
Token troops
Feature activation+0.000
Top resid features:
before
Token before
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.028
Top resid features:
Ċ
TokenĊ
Feature activation+0.026
Top resid features:
Sam
TokenSam
Feature activation+0.354
Top resid features:
u
Tokenu
Feature activation+0.090
Top resid features:
elson
Tokenelson
Feature activation+0.252
Top resid features:
acknowledges
Token acknowledges
Feature activation+0.399
Top resid features:
there
Token there
Feature activation+0.000
Top resid features:
is
Token is
Feature activation+0.000
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
debate
Token debate
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.101
Top resid features:
Mr
Token Mr
Feature activation+0.128
Top resid features:
De
Token De
Feature activation+0.101
Top resid features:
Greg
Token Greg
Feature activation+0.262
Top resid features:
orio
Tokenorio
Feature activation+0.227
Top resid features:
joined
Token joined
Feature activation+0.295
Top resid features:
Fifa
Token Fifa
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
14
Token 14
Feature activation+0.000
Top resid features:
September
Token September
Feature activation+0.000
Top resid features:
2011
Token 2011
Feature activation+0.000
Top resid features:
,
Token,
Feature activation-0.012
Top resid features:
âĢ
TokenâĢ
Feature activation-0.010
Top resid features:
Ŀ
TokenĿ
Feature activation+0.024
Top resid features:
Ms
Token Ms
Feature activation+0.079
Top resid features:
.
Token.
Feature activation-0.019
Top resid features:
Wein
Token Wein
Feature activation+0.397
Top resid features:
berger
Tokenberger
Feature activation+0.262
Top resid features:
wrote
Token wrote
Feature activation+0.293
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:
Election
Token Election
Feature activation-0.008
Top resid features:
Commission
Token Commission
Feature activation+0.006
Top resid features:
Chair
Token Chair
Feature activation+0.069
Top resid features:
Ron
Token Ron
Feature activation+0.265
Top resid features:
Buchanan
Token Buchanan
Feature activation+0.179
Top resid features:
spoke
Token spoke
Feature activation+0.389
Top resid features:
with
Token with
Feature activation+0.000
Top resid features:
The
Token The
Feature activation+0.000
Top resid features:
Tenn
Token Tenn
Feature activation+0.000
Top resid features:
esse
Tokenesse
Feature activation+0.000
Top resid features:
an
Tokenan
Feature activation+0.000
Top resid features:
School
Token School
Feature activation+0.007
Top resid features:
Principal
Token Principal
Feature activation+0.058
Top resid features:
Charles
Token Charles
Feature activation+0.204
Top resid features:
Ab
Token Ab
Feature activation+0.130
Top resid features:
ba
Tokenba
Feature activation+0.160
Top resid features:
sent
Token sent
Feature activation+0.358
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
letter
Token letter
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
parents
Token parents
Feature activation+0.000
Top resid features:
pointing
Token pointing
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation-0.008
Top resid features:
Ċ
TokenĊ
Feature activation-0.007
Top resid features:
On
TokenOn
Feature activation+0.030
Top resid features:
bond
Token bond
Feature activation+0.065
Top resid features:
:
Token:
Feature activation+0.083
Top resid features:
Blake
Token Blake
Feature activation+0.440
Top resid features:
Ferguson
Token Ferguson
Feature activation+0.347
Top resid features:
leaves
Token leaves
Feature activation+0.181
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Sutherland
Token Sutherland
Feature activation+0.000
Top resid features:
Local
Token Local
Feature activation+0.000
Top resid features:
okes
Tokenokes
Feature activation+0.058
Top resid features:
woman
Tokenwoman
Feature activation+0.073
Top resid features:
Jennifer
Token Jennifer
Feature activation+0.249
Top resid features:
Young
Token Young
Feature activation+0.163
Top resid features:
blood
Tokenblood
Feature activation+0.053
Top resid features:
told
Token told
Feature activation+0.315
Top resid features:
FP
Token FP
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
acting
Token acting
Feature activation+0.000
Top resid features:
director
Token director
Feature activation+0.000
Top resid features:
School
Token School
Feature activation-0.016
Top resid features:
professor
Token professor
Feature activation+0.021
Top resid features:
Ber
Token Ber
Feature activation+0.234
Top resid features:
it
Tokenit
Feature activation+0.033
Top resid features:
Berger
Token Berger
Feature activation+0.337
Top resid features:
uttered
Token uttered
Feature activation+0.409
Top resid features:
this
Token this
Feature activation+0.000
Top resid features:
one
Token one
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
MSNBC
Token MSNBC
Feature activation+0.000
Top resid features:
aine
Tokenaine
Feature activation+0.116
Top resid features:
Keen
Token Keen
Feature activation+0.229
Top resid features:
an
Tokenan
Feature activation+0.099
Top resid features:
Beng
Token Beng
Feature activation+0.216
Top resid features:
ts
Tokents
Feature activation+0.044
Top resid features:
presented
Token presented
Feature activation+0.356
Top resid features:
her
Token her
Feature activation+0.000
Top resid features:
annual
Token annual
Feature activation+0.000
Top resid features:
report
Token report
Feature activation+0.000
Top resid features:
at
Token at
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Hind
Token Hind
Feature activation+0.101
Top resid features:
s
Tokens
Feature activation+0.001
Top resid features:
Sheriff
Token Sheriff
Feature activation+0.079
Top resid features:
Victor
Token Victor
Feature activation+0.149
Top resid features:
Mason
Token Mason
Feature activation+0.190
Top resid features:
announced
Token announced
Feature activation+0.442
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
he
Token he
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
Morton
Token Morton
Feature activation+0.000
Top resid features:
feed
Tokenfeed
Feature activation+0.038
Top resid features:
's
Token's
Feature activation-0.034
Top resid features:
Ari
Token Ari
Feature activation+0.157
Top resid features:
ane
Tokenane
Feature activation+0.080
Top resid features:
Lange
Token Lange
Feature activation+0.301
Top resid features:
interviewed
Token interviewed
Feature activation+0.358
Top resid features:
several
Token several
Feature activation+0.000
Top resid features:
sex
Token sex
Feature activation+0.000
Top resid features:
workers
Token workers
Feature activation+0.000
Top resid features:
who
Token who
Feature activation+0.000
Top resid features:
had
Token had
Feature activation+0.000
Top resid features:
Director
Token Director
Feature activation+0.030
Top resid features:
Dr
Token Dr
Feature activation+0.052
Top resid features:
.
Token.
Feature activation-0.028
Top resid features:
Francis
Token Francis
Feature activation+0.364
Top resid features:
Collins
Token Collins
Feature activation+0.242
Top resid features:
described
Token described
Feature activation+0.446
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
agreement
Token agreement
Feature activation+0.000
Top resid features:
covering
Token covering
Feature activation+0.000
Top resid features:
these
Token these
Feature activation+0.000
Top resid features:
so
Token so
Feature activation+0.000
Top resid features:
ters
Tokenters
Feature activation+0.008
Top resid features:
fan
Token fan
Feature activation+0.038
Top resid features:
Andrew
Token Andrew
Feature activation+0.336
Top resid features:
Rush
Token Rush
Feature activation+0.174
Top resid features:
ton
Tokenton
Feature activation+0.156
Top resid features:
persuaded
Token persuaded
Feature activation+0.344
Top resid features:
him
Token him
Feature activation+0.000
Top resid features:
to
Token to
Feature activation+0.000
Top resid features:
pack
Token pack
Feature activation+0.000
Top resid features:
it
Token it
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
ven
Tokenven
Feature activation+0.017
Top resid features:
s
Tokens
Feature activation-0.002
Top resid features:
photo
Tokenphoto
Feature activation+0.062
Top resid features:
Ċ
TokenĊ
Feature activation+0.083
Top resid features:
Ċ
TokenĊ
Feature activation+0.100
Top resid features:
Ryan
TokenRyan
Feature activation+0.476
Top resid features:
Bundy
Token Bundy
Feature activation+0.206
Top resid features:
takes
Token takes
Feature activation+0.146
Top resid features:
a
Token a
Feature activation+0.000
Top resid features:
phone
Token phone
Feature activation+0.000
Top resid features:
call
Token call
Feature activation+0.000
Top resid features:
aw
Tokenaw
Feature activation+0.046
Top resid features:
ide
Tokenide
Feature activation+0.040
Top resid features:
h
Tokenh
Feature activation+0.036
Top resid features:
of
Token of
Feature activation+0.045
Top resid features:
Kemp
Token Kemp
Feature activation+0.218
Top resid features:
Klein
Token Klein
Feature activation+0.235
Top resid features:
says
Token says
Feature activation+0.143
Top resid features:
the
Token the
Feature activation+0.000
Top resid features:
case
Token case
Feature activation+0.000
Top resid features:
leaves
Token leaves
Feature activation+0.000
Top resid features:
you
Token you
Feature activation+0.000
Top resid features:
manager
Token manager
Feature activation+0.022
Top resid features:
Ron
Token Ron
Feature activation+0.177
Top resid features:
Ni
Token Ni
Feature activation+0.136
Top resid features:
elson
Tokenelson
Feature activation+0.174
Top resid features:
expressed
Token expressed
Feature activation+0.245
Top resid features:
disappointment
Token disappointment
Feature activation+0.281
Top resid features:
in
Token in
Feature activation+0.000
Top resid features:
that
Token that
Feature activation+0.000
Top resid features:
rationale
Token rationale
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
stating
Token stating
Feature activation+0.000
Top resid features:
with
Token with
Feature activation+0.037
Top resid features:
Padres
Token Padres
Feature activation+0.103
Top resid features:
manager
Token manager
Feature activation+0.065
Top resid features:
Andy
Token Andy
Feature activation+0.365
Top resid features:
Green
Token Green
Feature activation+0.149
Top resid features:
discussing
Token discussing
Feature activation+0.381
Top resid features:
it
Token it
Feature activation+0.000
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:
H
TokenH
Feature activation+0.000
Top resid features:

Decoder Weights Distribution

Head 0: 0.07

Head 1: 0.17

Head 2: 0.12

Head 3: 0.04

Head 4: 0.14

Head 5: 0.07

Head 6: 0.04

Head 7: 0.08

Head 8: 0.04

Head 9: 0.03

Head 10: 0.08

Head 11: 0.13

Positive logits

itone1.82

himself1.61

herty1.61

eus1.57

orem1.53

ivas1.53

SourceFile1.50

jon1.48

his1.43

ourke1.42

sch1.41

quez1.41

Himself1.39

ragon1.39

iere1.35

1.34

ken1.34

herself1.33

Es1.31

Izan1.30

Negative logits

viz-1.46

mismatch-1.42

gratification-1.41

ancial-1.35

magnification-1.34

FIX-1.33

>)-1.33

equivalent-1.33

shells-1.30

urgical-1.28

filled-1.28

calculation-1.26

'."-1.26

ablishment-1.25

bias-1.25

indoors-1.25

autical-1.24

conformity-1.23

ependent-1.22

>.-1.21

INTERVAL 0.910 - 1.011
CONTAINS 0.000%

campaign
Token campaign
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
Ni
Token Ni
Feature activation+0.000
elson
Tokenelson
Feature activation+0.000
expressed
Token expressed
Feature activation+1.011
disappointment
Token disappointment
Feature activation+0.719
in
Token in
Feature activation+0.329
that
Token that
Feature activation+0.233
rationale
Token rationale
Feature activation+0.194
,
Token,
Feature activation+0.000
Ja
Token Ja
Feature activation+0.000
ison
Tokenison
Feature activation+0.000
Pod
Token Pod
Feature activation+0.168
kan
Tokenkan
Feature activation+0.171
owicz
Tokenowicz
Feature activation+0.252
told
Token told
Feature activation+0.950
the
Token the
Feature activation+0.532
BBC
Token BBC
Feature activation+0.255
he
Token he
Feature activation+0.534
was
Token was
Feature activation+0.187
at
Token at
Feature activation+0.207

INTERVAL 0.809 - 0.910
CONTAINS 0.000%

Ŀ
TokenĿ
Feature activation+0.000
Ms
Token Ms
Feature activation+0.000
.
Token.
Feature activation+0.000
Wein
Token Wein
Feature activation+0.000
berger
Tokenberger
Feature activation+0.000
wrote
Token wrote
Feature activation+0.818
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
In
TokenIn
Feature activation+0.000
its
Token its
Feature activation+0.000
.
Token.
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
De
Token De
Feature activation+0.000
Greg
Token Greg
Feature activation+0.000
orio
Tokenorio
Feature activation+0.000
joined
Token joined
Feature activation+0.825
Fifa
Token Fifa
Feature activation+0.000
on
Token on
Feature activation+0.234
14
Token 14
Feature activation+0.009
September
Token September
Feature activation+0.010
2011
Token 2011
Feature activation+0.000
.
Token.
Feature activation+0.000
L
Token L
Feature activation+0.000
.
Token.
Feature activation+0.000
Scott
Token Scott
Feature activation+0.000
Levin
Token Levin
Feature activation+0.185
told
Token told
Feature activation+0.885
his
Token his
Feature activation+0.555
troops
Token troops
Feature activation+0.039
before
Token before
Feature activation+0.279
the
Token the
Feature activation+0.000
operation
Token operation
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Sam
TokenSam
Feature activation+0.000
u
Tokenu
Feature activation+0.000
elson
Tokenelson
Feature activation+0.000
acknowledges
Token acknowledges
Feature activation+0.827
there
Token there
Feature activation+0.357
is
Token is
Feature activation+0.474
a
Token a
Feature activation+0.208
debate
Token debate
Feature activation+0.058
to
Token to
Feature activation+0.000

INTERVAL 0.708 - 0.809
CONTAINS 0.002%

photo
Tokenphoto
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ryan
TokenRyan
Feature activation+0.000
Bundy
Token Bundy
Feature activation+0.000
takes
Token takes
Feature activation+0.723
a
Token a
Feature activation+0.259
phone
Token phone
Feature activation+0.255
call
Token call
Feature activation+0.189
by
Token by
Feature activation+0.011
the
Token the
Feature activation+0.000
feed
Tokenfeed
Feature activation+0.000
's
Token's
Feature activation+0.066
Ari
Token Ari
Feature activation+0.000
ane
Tokenane
Feature activation+0.000
Lange
Token Lange
Feature activation+0.000
interviewed
Token interviewed
Feature activation+0.734
several
Token several
Feature activation+0.643
sex
Token sex
Feature activation+0.155
workers
Token workers
Feature activation+0.249
who
Token who
Feature activation+0.141
had
Token had
Feature activation+0.162
ters
Tokenters
Feature activation+0.000
fan
Token fan
Feature activation+0.000
Andrew
Token Andrew
Feature activation+0.000
Rush
Token Rush
Feature activation+0.000
ton
Tokenton
Feature activation+0.136
persuaded
Token persuaded
Feature activation+0.725
him
Token him
Feature activation+0.341
to
Token to
Feature activation+0.010
pack
Token pack
Feature activation+0.207
it
Token it
Feature activation+0.118
.
Token.
Feature activation+0.000
manager
Token manager
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
Ni
Token Ni
Feature activation+0.000
elson
Tokenelson
Feature activation+0.000
expressed
Token expressed
Feature activation+1.011
disappointment
Token disappointment
Feature activation+0.719
in
Token in
Feature activation+0.329
that
Token that
Feature activation+0.233
rationale
Token rationale
Feature activation+0.194
,
Token,
Feature activation+0.000
stating
Token stating
Feature activation+0.232
Election
Token Election
Feature activation+0.000
Commission
Token Commission
Feature activation+0.000
Chair
Token Chair
Feature activation+0.000
Ron
Token Ron
Feature activation+0.000
Buchanan
Token Buchanan
Feature activation+0.000
spoke
Token spoke
Feature activation+0.807
with
Token with
Feature activation+0.689
The
Token The
Feature activation+0.178
Tenn
Token Tenn
Feature activation+0.058
esse
Tokenesse
Feature activation+0.000
an
Tokenan
Feature activation+0.000

INTERVAL 0.607 - 0.708
CONTAINS 0.005%

Ċ
TokenĊ
Feature activation+0.000
Bitcoin
TokenBitcoin
Feature activation+0.000
expert
Token expert
Feature activation+0.000
Graham
Token Graham
Feature activation+0.000
Williams
Token Williams
Feature activation+0.000
said
Token said
Feature activation+0.639
more
Token more
Feature activation+0.304
and
Token and
Feature activation+0.000
more
Token more
Feature activation+0.114
people
Token people
Feature activation+0.000
are
Token are
Feature activation+0.000
BC
TokenBC
Feature activation+0.000
R
TokenR
Feature activation+0.000
Treasurer
Token Treasurer
Feature activation+0.000
David
Token David
Feature activation+0.021
Craig
Token Craig
Feature activation+0.177
said
Token said
Feature activation+0.663
an
Token an
Feature activation+0.154
anonymous
Token anonymous
Feature activation+0.217
donor
Token donor
Feature activation+0.202
who
Token who
Feature activation+0.000
financed
Token financed
Feature activation+0.020
Judge
Token Judge
Feature activation+0.000
Leonard
Token Leonard
Feature activation+0.000
I
Token I
Feature activation+0.055
.
Token.
Feature activation+0.000
Shapiro
Token Shapiro
Feature activation+0.124
granted
Token granted
Feature activation+0.686
Obama
Token Obama
Feature activation+0.371
legal
Token legal
Feature activation+0.617
residency
Token residency
Feature activation+0.397
based
Token based
Feature activation+0.514
on
Token on
Feature activation+0.218
of
Token of
Feature activation+0.000
Miss
Token Miss
Feature activation+0.000
Jean
Token Jean
Feature activation+0.000
Bro
Token Bro
Feature activation+0.000
die
Tokendie
Feature activation+0.000
ends
Token ends
Feature activation+0.697
up
Token up
Feature activation+0.417
as
Token as
Feature activation+0.265
Sister
Token Sister
Feature activation+0.000
Helena
Token Helena
Feature activation+0.000
,
Token,
Feature activation+0.000
er
Tokener
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Andrew
TokenAndrew
Feature activation+0.000
wrote
Token wrote
Feature activation+0.615
an
Token an
Feature activation+0.126
article
Token article
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
g
Token g
Feature activation+0.000

INTERVAL 0.506 - 0.607
CONTAINS 0.010%

businessman
Token businessman
Feature activation+0.211
Neil
Token Neil
Feature activation+0.015
Hey
Token Hey
Feature activation+0.000
wood
Tokenwood
Feature activation+0.026
,
Token,
Feature activation+0.222
pictured
Token pictured
Feature activation+0.526
here
Token here
Feature activation+0.508
in
Token in
Feature activation+0.076
an
Token an
Feature activation+0.097
und
Token und
Feature activation+0.000
ated
Tokenated
Feature activation+0.000
Stadium
Token Stadium
Feature activation+0.000
after
Token after
Feature activation+0.122
Brian
Token Brian
Feature activation+0.000
Williams
Token Williams
Feature activation+0.000
up
Token up
Feature activation+0.388
ended
Tokenended
Feature activation+0.568
John
Token John
Feature activation+0.000
H
Token H
Feature activation+0.000
ark
Tokenark
Feature activation+0.239
es
Tokenes
Feature activation+0.263
in
Token in
Feature activation+0.194
but
Token but
Feature activation+0.000
bureau
Token bureau
Feature activation+0.000
director
Token director
Feature activation+0.000
James
Token James
Feature activation+0.000
Comey
Token Comey
Feature activation+0.000
gave
Token gave
Feature activation+0.558
her
Token her
Feature activation+0.246
a
Token a
Feature activation+0.168
tongue
Token tongue
Feature activation+0.009
-
Token-
Feature activation+0.000
l
Tokenl
Feature activation+0.000
2
Token 2
Feature activation+0.000
%.
Token%.
Feature activation+0.000
David
Token David
Feature activation+0.000
Beck
Token Beck
Feature activation+0.000
worth
Tokenworth
Feature activation+0.000
suggests
Token suggests
Feature activation+0.517
it
Token it
Feature activation+0.286
is
Token is
Feature activation+0.000
actually
Token actually
Feature activation+0.000
the
Token the
Feature activation+0.000
range
Token range
Feature activation+0.000
John
Token John
Feature activation+0.000
Piper
Token Piper
Feature activation+0.000
and
Token and
Feature activation+0.000
Justin
Token Justin
Feature activation+0.000
Taylor
Token Taylor
Feature activation+0.000
failed
Token failed
Feature activation+0.569
to
Token to
Feature activation+0.060
realize
Token realize
Feature activation+0.453
is
Token is
Feature activation+0.136
that
Token that
Feature activation+0.000
we
Token we
Feature activation+0.003

INTERVAL 0.405 - 0.506
CONTAINS 0.024%

C
Token C
Feature activation+0.000
Naz
Token Naz
Feature activation+0.037
r
Tokenr
Feature activation+0.000
Mohammed
Token Mohammed
Feature activation+0.010
was
Token was
Feature activation+0.421
preparing
Token preparing
Feature activation+0.460
for
Token for
Feature activation+0.230
the
Token the
Feature activation+0.075
second
Token second
Feature activation+0.183
half
Token half
Feature activation+0.000
when
Token when
Feature activation+0.000
I
Token I
Feature activation+0.000
hit
Token hit
Feature activation+0.075
Chris
Token Chris
Feature activation+0.000
Tra
Token Tra
Feature activation+0.000
eger
Tokeneger
Feature activation+0.000
levels
Token levels
Feature activation+0.486
of
Token of
Feature activation+0.116
optimism
Token optimism
Feature activation+0.215
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
December
TokenDecember
Feature activation+0.000
,
Token,
Feature activation+0.000
Vog
Token Vog
Feature activation+0.000
els
Tokenels
Feature activation+0.000
ong
Tokenong
Feature activation+0.000
signed
Token signed
Feature activation+0.411
a
Token a
Feature activation+0.137
$
Token $
Feature activation+0.029
2
Token2
Feature activation+0.000
million
Token million
Feature activation+0.000
contract
Token contract
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
seventh
Token seventh
Feature activation+0.000
.
Token.
Feature activation+0.000
Moss
Token Moss
Feature activation+0.000
drew
Token drew
Feature activation+0.428
a
Token a
Feature activation+0.061
lead
Token lead
Feature activation+0.100
off
Tokenoff
Feature activation+0.247
walk
Token walk
Feature activation+0.163
and
Token and
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Pl
TokenPl
Feature activation+0.000
o
Tokeno
Feature activation+0.000
etz
Tokenetz
Feature activation+0.000
suggests
Token suggests
Feature activation+0.431
that
Token that
Feature activation+0.045
Lei
Token Lei
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000

INTERVAL 0.303 - 0.405
CONTAINS 0.055%

cabinet
Token cabinet
Feature activation+0.000
minister
Token minister
Feature activation+0.000
Bill
Token Bill
Feature activation+0.000
Bennett
Token Bennett
Feature activation+0.000
told
Token told
Feature activation+0.362
me
Token me
Feature activation+0.354
.
Token.
Feature activation+0.000
âĢ
Token âĢ
Feature activation+0.000
ľ
Tokenľ
Feature activation+0.000
Unfortunately
TokenUnfortunately
Feature activation+0.000
,
Token,
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Star
Token Star
Feature activation+0.000
Online
Token Online
Feature activation+0.000
revealed
Token revealed
Feature activation+0.090
Ivanka
Token Ivanka
Feature activation+0.000
was
Token was
Feature activation+0.353
the
Token the
Feature activation+0.060
First
Token First
Feature activation+0.000
Daughter
Token Daughter
Feature activation+0.000
everyone
Token everyone
Feature activation+0.268
wants
Token wants
Feature activation+0.142
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ms
TokenMs
Feature activation+0.104
Fowler
Token Fowler
Feature activation+0.000
said
Token said
Feature activation+0.315
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
It
TokenIt
Feature activation+0.000
was
Token was
Feature activation+0.000
pretty
Token pretty
Feature activation+0.000
reserved
Token reserved
Feature activation+0.001
Led
Token Led
Feature activation+0.000
ward
Tokenward
Feature activation+0.000
Spencer
Token Spencer
Feature activation+0.000
,
Token,
Feature activation+0.000
accused
Token accused
Feature activation+0.390
of
Token of
Feature activation+0.075
burg
Token burg
Feature activation+0.000
lar
Tokenlar
Feature activation+0.000
izing
Tokenizing
Feature activation+0.000
Texas
Token Texas
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Lib
TokenLib
Feature activation+0.039
re
Tokenre
Feature activation+0.000
Office
TokenOffice
Feature activation+0.000
would
Token would
Feature activation+0.319
have
Token have
Feature activation+0.057
been
Token been
Feature activation+0.077
the
Token the
Feature activation+0.000
better
Token better
Feature activation+0.038
choice
Token choice
Feature activation+0.000

INTERVAL 0.202 - 0.303
CONTAINS 0.108%

General
Token General
Feature activation+0.000
Eric
Token Eric
Feature activation+0.000
Holder
Token Holder
Feature activation+0.000
told
Token told
Feature activation+0.640
an
Token an
Feature activation+0.294
audience
Token audience
Feature activation+0.292
at
Token at
Feature activation+0.123
Northwestern
Token Northwestern
Feature activation+0.000
University
Token University
Feature activation+0.000
Law
Token Law
Feature activation+0.000
School
Token School
Feature activation+0.000
ter
Tokenter
Feature activation+0.000
)
Token)
Feature activation+0.000
Brad
Token Brad
Feature activation+0.000
Wing
Token Wing
Feature activation+0.000
stuck
Token stuck
Feature activation+0.502
one
Token one
Feature activation+0.253
a
Token a
Feature activation+0.083
yard
Token yard
Feature activation+0.051
from
Token from
Feature activation+0.000
the
Token the
Feature activation+0.000
sideline
Token sideline
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
work
Token work
Feature activation+0.428
in
Token in
Feature activation+0.000
science
Token science
Feature activation+0.000
ranges
Token ranges
Feature activation+0.225
from
Token from
Feature activation+0.000
teaching
Token teaching
Feature activation+0.000
and
Token and
Feature activation+0.000
research
Token research
Feature activation+0.000
into
Token into
Feature activation+0.000
Ale
TokenAle
Feature activation+0.000
k
Tokenk
Feature activation+0.000
sey
Tokensey
Feature activation+0.000
P
Token P
Feature activation+0.000
.'
Token.'
Feature activation+0.000
said
Token said
Feature activation+0.266
:
Token:
Feature activation+0.000
'
Token '
Feature activation+0.000
Thank
TokenThank
Feature activation+0.000
God
Token God
Feature activation+0.000
,
Token,
Feature activation+0.000
B
Token B
Feature activation+0.000
aug
Tokenaug
Feature activation+0.000
her
Tokenher
Feature activation+0.211
said
Token said
Feature activation+0.443
,
Token,
Feature activation+0.000
adding
Token adding
Feature activation+0.261
that
Token that
Feature activation+0.000
his
Token his
Feature activation+0.000
initial
Token initial
Feature activation+0.001
skepticism
Token skepticism
Feature activation+0.000
about
Token about
Feature activation+0.014

INTERVAL 0.101 - 0.202
CONTAINS 0.254%

went
Token went
Feature activation+0.146
0
Token 0
Feature activation+0.000
-
Token-
Feature activation+0.000
2
Token2
Feature activation+0.000
while
Token while
Feature activation+0.000
completing
Token completing
Feature activation+0.124
just
Token just
Feature activation+0.000
59
Token 59
Feature activation+0.000
percent
Token percent
Feature activation+0.000
of
Token of
Feature activation+0.000
his
Token his
Feature activation+0.000
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Her
TokenHer
Feature activation+0.000
feet
Token feet
Feature activation+0.000
slipped
Token slipped
Feature activation+0.109
on
Token on
Feature activation+0.000
the
Token the
Feature activation+0.000
run
Token run
Feature activation+0.027
gs
Tokengs
Feature activation+0.000
of
Token of
Feature activation+0.000
Ll
Token Ll
Feature activation+0.000
ore
Tokenore
Feature activation+0.000
nt
Tokennt
Feature activation+0.000
e
Tokene
Feature activation+0.000
scored
Token scored
Feature activation+0.235
against
Token against
Feature activation+0.169
his
Token his
Feature activation+0.024
former
Token former
Feature activation+0.000
club
Token club
Feature activation+0.000
Juventus
Token Juventus
Feature activation+0.000
to
Token to
Feature activation+0.000
decided
Token decided
Feature activation+0.075
to
Token to
Feature activation+0.000
consider
Token consider
Feature activation+0.093
Off
Token Off
Feature activation+0.000
Broadway
Token Broadway
Feature activation+0.000
eligible
Token eligible
Feature activation+0.192
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
trophy
Token trophy
Feature activation+0.000
,
Token,
Feature activation+0.000
too
Token too
Feature activation+0.000
,
Token,
Feature activation+0.000
L
Token L
Feature activation+0.000
ét
Tokenét
Feature activation+0.000
our
Tokenour
Feature activation+0.000
neau
Tokenneau
Feature activation+0.000
said
Token said
Feature activation+0.115
.
Token.
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
(
Token(
Feature activation+0.000
G
TokenG
Feature activation+0.000

INTERVAL 0.000 - 0.101
CONTAINS 99.542%

devastating
Token devastating
Feature activation+0.000
impact
Token impact
Feature activation+0.000
on
Token on
Feature activation+0.000
an
Token an
Feature activation+0.000
enemy
Token enemy
Feature activation+0.000
.
Token.
Feature activation+0.000
HA
Token HA
Feature activation+0.000
ARP
TokenARP
Feature activation+0.000
can
Token can
Feature activation+0.000
deliver
Token deliver
Feature activation+0.000
millions
Token millions
Feature activation+0.000
âĢ
TokenâĢ
Feature activation+0.000
Ļ
TokenĻ
Feature activation+0.000
s
Tokens
Feature activation+0.000
a
Token a
Feature activation+0.000
thing
Token thing
Feature activation+0.000
that
Token that
Feature activation+0.000
can
Token can
Feature activation+0.000
intro
Token intro
Feature activation+0.000
spect
Tokenspect
Feature activation+0.000
your
Token your
Feature activation+0.000
database
Token database
Feature activation+0.000
fing
Token fing
Feature activation+0.000
ern
Tokenern
Feature activation+0.000
ail
Tokenail
Feature activation+0.000
cl
Token cl
Feature activation+0.000
ipp
Tokenipp
Feature activation+0.000
ings
Tokenings
Feature activation+0.000
.
Token.
Feature activation+0.000
Not
Token Not
Feature activation+0.000
only
Token only
Feature activation+0.000
are
Token are
Feature activation+0.000
a
Token a
Feature activation+0.000
in
Token in
Feature activation+0.000
2012
Token 2012
Feature activation+0.000
âĢĵ
Token âĢĵ
Feature activation+0.000
planned
Token planned
Feature activation+0.000
to
Token to
Feature activation+0.000
do
Token do
Feature activation+0.000
a
Token a
Feature activation+0.000
Richard
Token Richard
Feature activation+0.000
III
Token III
Feature activation+0.000
that
Token that
Feature activation+0.000
riff
Token riff
Feature activation+0.000
sublime
Token sublime
Feature activation+0.000
shades
Token shades
Feature activation+0.000
of
Token of
Feature activation+0.000
cel
Token cel
Feature activation+0.000
ery
Tokenery
Feature activation+0.000
green
Token green
Feature activation+0.000
,
Token,
Feature activation+0.000
and
Token and
Feature activation+0.000
c
Token c
Feature activation+0.000
uffed
Tokenuffed
Feature activation+0.000
or
Token or
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 H1.4: (feature 2448)

TOP ACTIVATIONS
MAX = 1.218

:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
.
Token.
Feature activation+0.855
php
Tokenphp
Feature activation+0.783
on
Token on
Feature activation+0.895
line
Token line
Feature activation+0.910
16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
idden
Tokenidden
Feature activation+0.723
and
Token and
Feature activation+0.815
unc
Token unc
Feature activation+0.797
redited
Tokenredited
Feature activation+0.922
vocals
Token vocals
Feature activation+1.017
from
Token from
Feature activation+1.127
Cathy
Token Cathy
Feature activation+0.908
Dennis
Token Dennis
Feature activation+0.745
and
Token and
Feature activation+0.644
Julia
Token Julia
Feature activation+0.664
Karl
Token Karl
Feature activation+0.577
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
/
Token/
Feature activation+1.023
www
Tokenwww
Feature activation+1.168
root
Tokenroot
Feature activation+1.182
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
/
Token/
Feature activation+1.023
line
Token line
Feature activation+0.910
16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
.
Token.
Feature activation+0.816
H
Token H
Feature activation+0.930
oe
Tokenoe
Feature activation+0.860
y
Tokeny
Feature activation+0.950
,
Token,
Feature activation+0.835
Roy
Token Roy
Feature activation+1.089
R
Token R
Feature activation+0.995
itchie
Tokenitchie
Feature activation+1.027
,
Token,
Feature activation+0.926
and
Token and
Feature activation+0.872
the
Token the
Feature activation+0.852
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
/
Token/
Feature activation+1.023
www
Tokenwww
Feature activation+1.168
16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
Bram
Token Bram
Feature activation+0.921
ley
Tokenley
Feature activation+0.809
,
Token,
Feature activation+0.760
Marc
Token Marc
Feature activation+0.943
Urban
Token Urban
Feature activation+1.034
o
Tokeno
Feature activation+1.074
,
Token,
Feature activation+0.848
Patrick
Token Patrick
Feature activation+1.054
M
Token M
Feature activation+1.073
.
Token.
Feature activation+0.816
H
Token H
Feature activation+0.930
Marc
Token Marc
Feature activation+0.943
Urban
Token Urban
Feature activation+1.034
o
Tokeno
Feature activation+1.074
,
Token,
Feature activation+0.848
Patrick
Token Patrick
Feature activation+1.054
M
Token M
Feature activation+1.073
.
Token.
Feature activation+0.816
H
Token H
Feature activation+0.930
oe
Tokenoe
Feature activation+0.860
y
Tokeny
Feature activation+0.950
,
Token,
Feature activation+0.835
55
Token55
Feature activation+0.741
Inspired
Token Inspired
Feature activation+1.043
Sub
Token Sub
Feature activation+0.804
sc
Tokensc
Feature activation+0.849
riber
Tokenriber
Feature activation+0.946
Reward
Token Reward
Feature activation+1.069
Ċ
TokenĊ
Feature activation+0.618
Ċ
TokenĊ
Feature activation+0.416
New
TokenNew
Feature activation+0.530
Cart
Token Cart
Feature activation+0.440
el
Tokenel
Feature activation+0.129
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
/
Token/
Feature activation+1.023
www
Tokenwww
Feature activation+1.168
root
Tokenroot
Feature activation+1.182
/
Token/
Feature activation+1.050
,
Token,
Feature activation+0.760
Marc
Token Marc
Feature activation+0.943
Urban
Token Urban
Feature activation+1.034
o
Tokeno
Feature activation+1.074
,
Token,
Feature activation+0.848
Patrick
Token Patrick
Feature activation+1.054
M
Token M
Feature activation+1.073
.
Token.
Feature activation+0.816
H
Token H
Feature activation+0.930
oe
Tokenoe
Feature activation+0.860
y
Tokeny
Feature activation+0.950
on
Token on
Feature activation+0.895
line
Token line
Feature activation+0.910
16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
ization
Tokenization
Feature activation+0.699
-
Token -
Feature activation+0.681
HK
Token HK
Feature activation+0.668
-
Token-
Feature activation+0.677
55
Token55
Feature activation+0.741
Inspired
Token Inspired
Feature activation+1.043
Sub
Token Sub
Feature activation+0.804
sc
Tokensc
Feature activation+0.849
riber
Tokenriber
Feature activation+0.946
Reward
Token Reward
Feature activation+1.069
Ċ
TokenĊ
Feature activation+0.618
Mark
Token Mark
Feature activation+0.826
Bram
Token Bram
Feature activation+0.921
ley
Tokenley
Feature activation+0.809
,
Token,
Feature activation+0.760
Marc
Token Marc
Feature activation+0.943
Urban
Token Urban
Feature activation+1.034
o
Tokeno
Feature activation+1.074
,
Token,
Feature activation+0.848
Patrick
Token Patrick
Feature activation+1.054
M
Token M
Feature activation+1.073
.
Token.
Feature activation+0.816
Sv
Token Sv
Feature activation+0.695
idden
Tokenidden
Feature activation+0.723
and
Token and
Feature activation+0.815
unc
Token unc
Feature activation+0.797
redited
Tokenredited
Feature activation+0.922
vocals
Token vocals
Feature activation+1.017
from
Token from
Feature activation+1.127
Cathy
Token Cathy
Feature activation+0.908
Dennis
Token Dennis
Feature activation+0.745
and
Token and
Feature activation+0.644
Julia
Token Julia
Feature activation+0.664

Top DFA by src position
MAX = 0.270

16
Token 16
Feature activation+0.073
Top resid features:
Warning
Token Warning
Feature activation+0.123
Top resid features:
:
Token:
Feature activation+0.076
Top resid features:
impl
Token impl
Feature activation+0.108
Top resid features:
ode
Tokenode
Feature activation+0.111
Top resid features:
():
Token():
Feature activation+0.233
Top resid features:
Argument
Token Argument
Feature activation+0.208
Top resid features:
must
Token must
Feature activation+0.089
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
array
Token array
Feature activation+0.000
Top resid features:
16
Token 16
Feature activation+0.072
Top resid features:
Warning
Token Warning
Feature activation+0.104
Top resid features:
:
Token:
Feature activation+0.074
Top resid features:
impl
Token impl
Feature activation+0.100
Top resid features:
ode
Tokenode
Feature activation+0.108
Top resid features:
():
Token():
Feature activation+0.204
Top resid features:
Argument
Token Argument
Feature activation+0.176
Top resid features:
must
Token must
Feature activation+0.173
Top resid features:
be
Token be
Feature activation-0.002
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
array
Token array
Feature activation+0.000
Top resid features:
comm
Tokencomm
Feature activation+0.059
Top resid features:
end
Tokenend
Feature activation+0.103
Top resid features:
.
Token.
Feature activation+0.046
Top resid features:
php
Tokenphp
Feature activation+0.114
Top resid features:
on
Token on
Feature activation+0.136
Top resid features:
line
Token line
Feature activation+0.194
Top resid features:
16
Token 16
Feature activation+0.181
Top resid features:
Warning
Token Warning
Feature activation+0.058
Top resid features:
:
Token:
Feature activation+0.000
Top resid features:
impl
Token impl
Feature activation+0.000
Top resid features:
ode
Tokenode
Feature activation+0.000
Top resid features:
16
Token 16
Feature activation+0.078
Top resid features:
Warning
Token Warning
Feature activation+0.148
Top resid features:
:
Token:
Feature activation+0.070
Top resid features:
impl
Token impl
Feature activation+0.129
Top resid features:
ode
Tokenode
Feature activation+0.129
Top resid features:
():
Token():
Feature activation+0.245
Top resid features:
Argument
Token Argument
Feature activation+0.046
Top resid features:
must
Token must
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
an
Token an
Feature activation+0.000
Top resid features:
array
Token array
Feature activation+0.000
Top resid features:
Sv
Token Sv
Feature activation+0.114
Top resid features:
idden
Tokenidden
Feature activation+0.086
Top resid features:
and
Token and
Feature activation+0.122
Top resid features:
unc
Token unc
Feature activation+0.107
Top resid features:
redited
Tokenredited
Feature activation+0.136
Top resid features:
vocals
Token vocals
Feature activation+0.252
Top resid features:
from
Token from
Feature activation+0.113
Top resid features:
Cathy
Token Cathy
Feature activation+0.000
Top resid features:
Dennis
Token Dennis
Feature activation+0.000
Top resid features:
and
Token and
Feature activation+0.000
Top resid features:
Julia
Token Julia
Feature activation+0.000
Top resid features:
():
Token():
Feature activation+0.127
Top resid features:
Argument
Token Argument
Feature activation+0.127
Top resid features:
must
Token must
Feature activation+0.111
Top resid features:
be
Token be
Feature activation+0.070
Top resid features:
an
Token an
Feature activation+0.102
Top resid features:
array
Token array
Feature activation+0.179
Top resid features:
in
Token in
Feature activation+0.016
Top resid features:
/
Token /
Feature activation+0.000
Top resid features:
www
Tokenwww
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
www
Tokenwww
Feature activation+0.000
Top resid features:
16
Token 16
Feature activation+0.069
Top resid features:
Warning
Token Warning
Feature activation+0.085
Top resid features:
:
Token:
Feature activation+0.063
Top resid features:
impl
Token impl
Feature activation+0.089
Top resid features:
ode
Tokenode
Feature activation+0.097
Top resid features:
():
Token():
Feature activation+0.164
Top resid features:
Argument
Token Argument
Feature activation+0.150
Top resid features:
must
Token must
Feature activation+0.133
Top resid features:
be
Token be
Feature activation+0.089
Top resid features:
an
Token an
Feature activation+0.040
Top resid features:
array
Token array
Feature activation+0.000
Top resid features:
on
Token on
Feature activation+0.060
Top resid features:
line
Token line
Feature activation+0.117
Top resid features:
16
Token 16
Feature activation+0.122
Top resid features:
Warning
Token Warning
Feature activation+0.175
Top resid features:
:
Token:
Feature activation+0.095
Top resid features:
impl
Token impl
Feature activation+0.224
Top resid features:
ode
Tokenode
Feature activation-0.067
Top resid features:
():
Token():
Feature activation+0.000
Top resid features:
Argument
Token Argument
Feature activation+0.000
Top resid features:
must
Token must
Feature activation+0.000
Top resid features:
be
Token be
Feature activation+0.000
Top resid features:
M
Token M
Feature activation+0.090
Top resid features:
.
Token.
Feature activation+0.035
Top resid features:
H
Token H
Feature activation+0.112
Top resid features:
oe
Tokenoe
Feature activation+0.099
Top resid features:
y
Tokeny
Feature activation+0.086
Top resid features:
,
Token,
Feature activation+0.186
Top resid features:
Roy
Token Roy
Feature activation-0.027
Top resid features:
R
Token R
Feature activation+0.000
Top resid features:
itchie
Tokenitchie
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:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.143
Top resid features:
_
Token_
Feature activation+0.029
Top resid features:
comm
Tokencomm
Feature activation+0.015
Top resid features:
end
Tokenend
Feature activation+0.032
Top resid features:
.
Token.
Feature activation+0.036
Top resid features:
php
Tokenphp
Feature activation+0.033
Top resid features:
.
Token.
Feature activation+0.026
Top resid features:
php
Tokenphp
Feature activation+0.062
Top resid features:
on
Token on
Feature activation+0.066
Top resid features:
line
Token line
Feature activation+0.093
Top resid features:
16
Token 16
Feature activation+0.105
Top resid features:
Warning
Token Warning
Feature activation+0.191
Top resid features:
:
Token:
Feature activation+0.099
Top resid features:
impl
Token impl
Feature activation+0.165
Top resid features:
ode
Tokenode
Feature activation+0.136
Top resid features:
():
Token():
Feature activation+0.057
Top resid features:
Argument
Token Argument
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.197
Top resid features:
Le
Token Le
Feature activation+0.029
Top resid features:
pp
Tokenpp
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.037
Top resid features:
Mark
Token Mark
Feature activation+0.027
Top resid features:
Bram
Token Bram
Feature activation+0.029
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.188
Top resid features:
Le
Token Le
Feature activation+0.031
Top resid features:
pp
Tokenpp
Feature activation+0.026
Top resid features:
,
Token,
Feature activation+0.040
Top resid features:
Mark
Token Mark
Feature activation+0.028
Top resid features:
Bram
Token Bram
Feature activation+0.032
Top resid features:
-
Token-
Feature activation+0.061
Top resid features:
55
Token55
Feature activation+0.085
Top resid features:
Inspired
Token Inspired
Feature activation+0.152
Top resid features:
Sub
Token Sub
Feature activation+0.116
Top resid features:
sc
Tokensc
Feature activation+0.131
Top resid features:
riber
Tokenriber
Feature activation+0.270
Top resid features:
Reward
Token Reward
Feature activation+0.036
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
Ċ
TokenĊ
Feature activation+0.000
Top resid features:
New
TokenNew
Feature activation+0.000
Top resid features:
Cart
Token Cart
Feature activation+0.000
Top resid features:
():
Token():
Feature activation+0.127
Top resid features:
Argument
Token Argument
Feature activation+0.128
Top resid features:
must
Token must
Feature activation+0.092
Top resid features:
be
Token be
Feature activation+0.055
Top resid features:
an
Token an
Feature activation+0.076
Top resid features:
array
Token array
Feature activation+0.162
Top resid features:
in
Token in
Feature activation+0.063
Top resid features:
/
Token /
Feature activation+0.052
Top resid features:
www
Tokenwww
Feature activation+0.000
Top resid features:
/
Token/
Feature activation+0.000
Top resid features:
www
Tokenwww
Feature activation+0.000
Top resid features:
ley
Tokenley
Feature activation+0.077
Top resid features:
,
Token,
Feature activation+0.103
Top resid features:
Marc
Token Marc
Feature activation+0.133
Top resid features:
Urban
Token Urban
Feature activation+0.137
Top resid features:
o
Tokeno
Feature activation+0.082
Top resid features:
,
Token,
Feature activation+0.195
Top resid features:
Patrick
Token Patrick
Feature activation-0.029
Top resid features:
M
Token M
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.000
Top resid features:
H
Token H
Feature activation+0.000
Top resid features:
oe
Tokenoe
Feature activation+0.000
Top resid features:
.
Token.
Feature activation+0.020
Top resid features:
php
Tokenphp
Feature activation+0.077
Top resid features:
on
Token on
Feature activation+0.072
Top resid features:
line
Token line
Feature activation+0.128
Top resid features:
16
Token 16
Feature activation+0.111
Top resid features:
Warning
Token Warning
Feature activation+0.192
Top resid features:
:
Token:
Feature activation+0.130
Top resid features:
impl
Token impl
Feature activation+0.034
Top resid features:
ode
Tokenode
Feature activation+0.000
Top resid features:
():
Token():
Feature activation+0.000
Top resid features:
Argument
Token Argument
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.168
Top resid features:
-
Token-
Feature activation+0.022
Top resid features:
55
Token55
Feature activation+0.027
Top resid features:
's
Token's
Feature activation+0.034
Top resid features:
Helmet
Token Helmet
Feature activation+0.041
Top resid features:
Sub
Token Sub
Feature activation+0.030
Top resid features:
,
Token,
Feature activation+0.083
Top resid features:
Mark
Token Mark
Feature activation+0.136
Top resid features:
Bram
Token Bram
Feature activation+0.115
Top resid features:
ley
Tokenley
Feature activation+0.094
Top resid features:
,
Token,
Feature activation+0.163
Top resid features:
Marc
Token Marc
Feature activation+0.196
Top resid features:
Urban
Token Urban
Feature activation-0.023
Top resid features:
o
Tokeno
Feature activation+0.000
Top resid features:
,
Token,
Feature activation+0.000
Top resid features:
Patrick
Token Patrick
Feature activation+0.000
Top resid features:
M
Token M
Feature activation+0.000
Top resid features:
<|endoftext|>
Token<|endoftext|>
Feature activation+0.222
Top resid features:
Ċ
TokenĊ
Feature activation+0.023
Top resid features:
Notes
TokenNotes
Feature activation+0.024
Top resid features:
[
Token[
Feature activation+0.027
Top resid features:
11
Token11
Feature activation+0.018
Top resid features:
]
Token]
Feature activation+0.022
Top resid features:

Decoder Weights Distribution

Head 0: 0.10

Head 1: 0.12

Head 2: 0.12

Head 3: 0.06

Head 4: 0.14

Head 5: 0.08

Head 6: 0.04

Head 7: 0.09

Head 8: 0.07

Head 9: 0.05

Head 10: 0.06

Head 11: 0.07

Positive logits

MSN1.78

untarily1.55

arser1.45

イト1.43

atum1.41

1.41

":[1.40

Includes1.38

Verse1.38

Condition1.38

SourceFile1.37

uxe1.36

ucer1.35

OTAL1.34

"}1.34

leans1.33

1.32

zsche1.32

ramid1.32

"},"1.30

Negative logits

sporting-1.40

calendars-1.35

skepticism-1.32

questioning-1.26

tire-1.25

doubt-1.18

dissent-1.15

bashing-1.15

optimism-1.14

recruiting-1.14

distrust-1.14

tut-1.13

praise-1.13

skeptical-1.13

criticism-1.12

suspicion-1.11

criticisms-1.09

haven-1.09

spirited-1.08

BlackBerry-1.08

INTERVAL 1.096 - 1.218
CONTAINS 0.001%

impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
/
Token/
Feature activation+1.023
www
Tokenwww
Feature activation+1.168
root
Tokenroot
Feature activation+1.182
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
line
Token line
Feature activation+0.910
16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103

INTERVAL 0.974 - 1.096
CONTAINS 0.002%

16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
Argument
Token Argument
Feature activation+1.139
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
.
Token.
Feature activation+0.816
H
Token H
Feature activation+0.930
oe
Tokenoe
Feature activation+0.860
y
Tokeny
Feature activation+0.950
,
Token,
Feature activation+0.835
Roy
Token Roy
Feature activation+1.089
R
Token R
Feature activation+0.995
itchie
Tokenitchie
Feature activation+1.027
,
Token,
Feature activation+0.926
and
Token and
Feature activation+0.872
the
Token the
Feature activation+0.852
must
Token must
Feature activation+1.218
be
Token be
Feature activation+1.198
an
Token an
Feature activation+1.103
array
Token array
Feature activation+1.083
in
Token in
Feature activation+1.107
/
Token /
Feature activation+1.066
www
Tokenwww
Feature activation+1.163
/
Token/
Feature activation+1.023
www
Tokenwww
Feature activation+1.168
root
Tokenroot
Feature activation+1.182
/
Token/
Feature activation+1.050
end
Tokenend
Feature activation+0.778
.
Token.
Feature activation+0.855
php
Tokenphp
Feature activation+0.783
on
Token on
Feature activation+0.895
line
Token line
Feature activation+0.910
16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
impl
Token impl
Feature activation+1.044
ode
Tokenode
Feature activation+1.100
():
Token():
Feature activation+1.078
ization
Tokenization
Feature activation+0.699
-
Token -
Feature activation+0.681
HK
Token HK
Feature activation+0.668
-
Token-
Feature activation+0.677
55
Token55
Feature activation+0.741
Inspired
Token Inspired
Feature activation+1.043
Sub
Token Sub
Feature activation+0.804
sc
Tokensc
Feature activation+0.849
riber
Tokenriber
Feature activation+0.946
Reward
Token Reward
Feature activation+1.069
Ċ
TokenĊ
Feature activation+0.618

INTERVAL 0.852 - 0.974
CONTAINS 0.005%

Wars
Token Wars
Feature activation+0.470
:
Token:
Feature activation+0.561
The
Token The
Feature activation+0.598
Empire
Token Empire
Feature activation+0.563
Strikes
Token Strikes
Feature activation+0.615
Back
Token Back
Feature activation+0.882
,
Token,
Feature activation+0.735
Star
Token Star
Feature activation+0.742
Wars
Token Wars
Feature activation+0.699
:
Token:
Feature activation+0.764
Return
Token Return
Feature activation+0.813
5
Token 5
Feature activation+0.408
features
Token features
Feature activation+0.636
unc
Token unc
Feature activation+0.617
redited
Tokenredited
Feature activation+0.705
production
Token production
Feature activation+0.890
from
Token from
Feature activation+0.898
Sv
Token Sv
Feature activation+0.714
idden
Tokenidden
Feature activation+0.767
and
Token and
Feature activation+0.841
unc
Token unc
Feature activation+0.809
redited
Tokenredited
Feature activation+0.918
Track
TokenTrack
Feature activation+0.449
5
Token 5
Feature activation+0.408
features
Token features
Feature activation+0.636
unc
Token unc
Feature activation+0.617
redited
Tokenredited
Feature activation+0.705
production
Token production
Feature activation+0.890
from
Token from
Feature activation+0.898
Sv
Token Sv
Feature activation+0.714
idden
Tokenidden
Feature activation+0.767
and
Token and
Feature activation+0.841
unc
Token unc
Feature activation+0.809
resisting
Token resisting
Feature activation+0.719
arrest
Token arrest
Feature activation+0.738
and
Token and
Feature activation+0.717
weapons
Token weapons
Feature activation+0.741
violations
Token violations
Feature activation+0.761
charges
Token charges
Feature activation+0.858
.
Token.
Feature activation+0.670
Image
Token Image
Feature activation+0.712
9
Token 9
Feature activation+0.615
of
Token of
Feature activation+0.762
9
Token 9
Feature activation+0.600
bone
Tokenbone
Feature activation+0.771
3
Token3
Feature activation+0.927
)
Token)
Feature activation+0.889
July
Token July
Feature activation+0.995
20
Token 20
Feature activation+0.949
,
Token,
Feature activation+0.890
2016
Token 2016
Feature activation+0.986
Ċ
TokenĊ
Feature activation+0.632
Ċ
TokenĊ
Feature activation+0.521
As
TokenAs
Feature activation+0.509
players
Token players
Feature activation+0.587

INTERVAL 0.731 - 0.852
CONTAINS 0.010%

wait
Token wait
Feature activation+0.472
...
Token...
Feature activation+0.493
Discuss
Token Discuss
Feature activation+0.686
Card
Token Card
Feature activation+0.711
Rate
Token Rate
Feature activation+0.661
this
Token this
Feature activation+0.802
item
Token item
Feature activation+0.697
:
Token:
Feature activation+0.739
1
Token 1
Feature activation+0.731
.
Token.
Feature activation+0.613
00
Token00
Feature activation+0.608
with
Token with
Feature activation+0.620
fun
Token fun
Feature activation+0.762
color
Token color
Feature activation+0.661
g
Token g
Feature activation+0.673
els
Tokenels
Feature activation+0.622
in
Token in
Feature activation+0.747
blue
Token blue
Feature activation+0.688
,
Token,
Feature activation+0.716
red
Token red
Feature activation+0.756
,
Token,
Feature activation+0.711
purple
Token purple
Feature activation+0.734
block
Tokenblock
Feature activation+0.921
_
Token_
Feature activation+0.925
comm
Tokencomm
Feature activation+1.006
end
Tokenend
Feature activation+0.778
.
Token.
Feature activation+0.855
php
Tokenphp
Feature activation+0.783
on
Token on
Feature activation+0.895
line
Token line
Feature activation+0.910
16
Token 16
Feature activation+1.014
Warning
Token Warning
Feature activation+1.181
:
Token:
Feature activation+0.980
The
Token The
Feature activation+0.598
Empire
Token Empire
Feature activation+0.563
Strikes
Token Strikes
Feature activation+0.615
Back
Token Back
Feature activation+0.882
,
Token,
Feature activation+0.735
Star
Token Star
Feature activation+0.742
Wars
Token Wars
Feature activation+0.699
:
Token:
Feature activation+0.764
Return
Token Return
Feature activation+0.813
of
Token of
Feature activation+0.723
the
Token the
Feature activation+0.729
s
Tokens
Feature activation+0.676
car
Token car
Feature activation+0.674
out
Token out
Feature activation+0.865
of
Token of
Feature activation+0.740
the
Token the
Feature activation+0.689
snow
Token snow
Feature activation+0.732
.
Token.
Feature activation+0.655
Ċ
TokenĊ
Feature activation+0.604
Ċ
TokenĊ
Feature activation+0.571
More
TokenMore
Feature activation+0.636
than
Token than
Feature activation+0.625

INTERVAL 0.609 - 0.731
CONTAINS 0.016%

/
Token /
Feature activation+0.458
www
Tokenwww
Feature activation+0.612
/
Token/
Feature activation+0.528
www
Tokenwww
Feature activation+0.705
root
Tokenroot
Feature activation+0.742
/
Token/
Feature activation+0.660
default
Tokendefault
Feature activation+0.770
/
Token/
Feature activation+0.750
modules
Tokenmodules
Feature activation+0.845
/
Token/
Feature activation+0.744
article
Tokenarticle
Feature activation+1.003
blasted
Token blasted
Feature activation+0.456
media
Token media
Feature activation+0.512
reporting
Token reporting
Feature activation+0.575
and
Token and
Feature activation+0.496
skepticism
Token skepticism
Feature activation+0.564
on
Token on
Feature activation+0.611
his
Token his
Feature activation+0.574
Wednesday
Token Wednesday
Feature activation+0.602
tease
Token tease
Feature activation+0.657
.
Token.
Feature activation+0.602
Ċ
TokenĊ
Feature activation+0.431
and
Token and
Feature activation+0.496
skepticism
Token skepticism
Feature activation+0.564
on
Token on
Feature activation+0.611
his
Token his
Feature activation+0.574
Wednesday
Token Wednesday
Feature activation+0.602
tease
Token tease
Feature activation+0.657
.
Token.
Feature activation+0.602
Ċ
TokenĊ
Feature activation+0.431
Ċ
TokenĊ
Feature activation+0.373
The
TokenThe
Feature activation+0.263
Clark
Token Clark
Feature activation+0.190
word
Token word
Feature activation+0.599
'
Token '
Feature activation+0.685
class
Tokenclass
Feature activation+0.573
'
Token'
Feature activation+0.706
as
Token as
Feature activation+0.780
a
Token a
Feature activation+0.704
variable
Token variable
Feature activation+0.695
name
Token name
Feature activation+0.743
..
Token..
Feature activation+0.763
Ċ
TokenĊ
Feature activation+0.508
Ċ
TokenĊ
Feature activation+0.392
't
Token't
Feature activation+0.391
g
Token g
Feature activation+0.176
âĢ¦
TokenâĢ¦
Feature activation+0.456
Free
Token Free
Feature activation+0.532
View
Token View
Feature activation+0.554
in
Token in
Feature activation+0.721
iTunes
Token iTunes
Feature activation+0.450
Ċ
TokenĊ
Feature activation+0.544
Ċ
TokenĊ
Feature activation+0.480
35
Token35
Feature activation+0.155
Clean
Token Clean
Feature activation+0.380

INTERVAL 0.487 - 0.609
CONTAINS 0.027%

from
Token from
Feature activation+1.127
Cathy
Token Cathy
Feature activation+0.908
Dennis
Token Dennis
Feature activation+0.745
and
Token and
Feature activation+0.644
Julia
Token Julia
Feature activation+0.664
Karl
Token Karl
Feature activation+0.577
sson
Tokensson
Feature activation+0.483
.
Token.
Feature activation+0.439
Ċ
TokenĊ
Feature activation+0.379
Ċ
TokenĊ
Feature activation+0.353
Track
TokenTrack
Feature activation+0.449
âĢĶ
Token âĢĶ
Feature activation+0.155
Donald
Token Donald
Feature activation+0.260
J
Token J
Feature activation+0.300
.
Token.
Feature activation+0.254
Trump
Token Trump
Feature activation+0.381
(@
Token (@
Feature activation+0.510
realDonaldTrump
TokenrealDonaldTrump
Feature activation+0.653
)
Token)
Feature activation+0.599
August
Token August
Feature activation+0.666
26
Token 26
Feature activation+0.649
,
Token,
Feature activation+0.611
Ċ
TokenĊ
Feature activation+0.146
Ċ
TokenĊ
Feature activation+0.125
Track
TokenTrack
Feature activation+0.261
4
Token 4
Feature activation+0.218
features
Token features
Feature activation+0.465
unc
Token unc
Feature activation+0.506
redited
Tokenredited
Feature activation+0.597
production
Token production
Feature activation+0.802
from
Token from
Feature activation+0.845
Sv
Token Sv
Feature activation+0.695
idden
Tokenidden
Feature activation+0.723
anni
Tokenanni
Feature activation+0.075
(
Token (
Feature activation+0.205
ca
Tokenca
Feature activation+0.119
ution
Tokenution
Feature activation+0.280
;
Token;
Feature activation+0.386
reckless
Token reckless
Feature activation+0.573
foul
Token foul
Feature activation+0.526
)
Token)
Feature activation+0.444
118
Token 118
Feature activation+0.215
Ċ
TokenĊ
Feature activation+0.204
Ċ
TokenĊ
Feature activation+0.154
Key
Token Key
Feature activation+0.684
Beach
Token Beach
Feature activation+0.769
!
Token!
Feature activation+0.771
Additionally
Token Additionally
Feature activation+0.590
,
Token,
Feature activation+0.520
you
Token you
Feature activation+0.586
get
Token get
Feature activation+0.509
a
Token a
Feature activation+0.423
small
Token small
Feature activation+0.435
pitch
Token pitch
Feature activation+0.408
of
Token of
Feature activation+0.274

INTERVAL 0.365 - 0.487
CONTAINS 0.048%

the
Token the
Feature activation+0.232
art
Token art
Feature activation+0.370
of
Token of
Feature activation+0.285
sc
Token sc
Feature activation+0.319
rying
Tokenrying
Feature activation+0.202
with
Token with
Feature activation+0.429
a
Token a
Feature activation+0.375
mirror
Token mirror
Feature activation+0.339
or
Token or
Feature activation+0.390
a
Token a
Feature activation+0.372
crystal
Token crystal
Feature activation+0.292
!
Token!
Feature activation+0.183
Follow
Token Follow
Feature activation+0.326
me
Token me
Feature activation+0.359
on
Token on
Feature activation+0.380
Twitter
Token Twitter
Feature activation+0.431
@
Token @
Feature activation+0.470
ed
Tokened
Feature activation+0.456
ward
Tokenward
Feature activation+0.392
ian
Tokenian
Feature activation+0.443
_
Token_
Feature activation+0.559
era
Tokenera
Feature activation+0.615
f
Tokenf
Feature activation+0.233
\/
Token\/
Feature activation+0.127
H
TokenH
Feature activation+0.206
ang
Tokenang
Feature activation+0.284
-
Token-
Feature activation+0.338
Someone
TokenSomeone
Feature activation+0.473
-
Token-
Feature activation+0.550
in
Tokenin
Feature activation+0.669
-
Token-
Feature activation+0.530
Red
TokenRed
Feature activation+0.644
-
Token-
Feature activation+0.640
ih
Tokenih
Feature activation+0.313
aj
Tokenaj
Feature activation+0.443
l
Tokenl
Feature activation+0.378
ovic
Tokenovic
Feature activation+0.472
a
Token a
Feature activation+0.423
dream
Token dream
Feature activation+0.436
start
Token start
Feature activation+0.420
to
Token to
Feature activation+0.280
life
Token life
Feature activation+0.200
in
Token in
Feature activation+0.185
Gen
Token Gen
Feature activation+0.146
:
Token:
Feature activation+0.447
True
Token True
Feature activation+0.656
Draco
Token Draco
Feature activation+0.789
Metal
Token Metal
Feature activation+0.580
Koz
Token Koz
Feature activation+0.491
mo
Tokenmo
Feature activation+0.385
âĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.588
âĢĶâĢĶâĢĶâĢĶ
TokenâĢĶâĢĶâĢĶâĢĶ
Feature activation+0.688
âĢĶ-
TokenâĢĶ-
Feature activation+0.760
4
Token4
Feature activation+0.572
th
Tokenth
Feature activation+0.565

INTERVAL 0.244 - 0.365
CONTAINS 0.106%

Mount
Token Mount
Feature activation+0.344
aint
Tokenaint
Feature activation+0.297
ops
Tokenops
Feature activation+0.438
-
Token -
Feature activation+0.367
Bad
Token Bad
Feature activation+0.424
Bo
Token Bo
Feature activation+0.329
ogie
Tokenogie
Feature activation+0.160
Ball
Token Ball
Feature activation+0.279
in
Tokenin
Feature activation+0.242
'
Token'
Feature activation+0.319
bonus
Token bonus
Feature activation+0.316
start
Tokenstart
Feature activation+0.150
"
Token"
Feature activation+0.179
class
Token class
Feature activation+0.063
="
Token="
Feature activation+0.257
cd
Tokencd
Feature activation+0.037
-
Token-
Feature activation+0.247
btn
Tokenbtn
Feature activation+0.282
">
Token">
Feature activation+0.325
Start
TokenStart
Feature activation+0.180
Token
Feature activation+0.333
a
Tokena
Feature activation+0.149
paint
Token paint
Feature activation+0.435
ball
Tokenball
Feature activation+0.532
gun
Token gun
Feature activation+0.472
can
Token can
Feature activation+0.384
shoot
Token shoot
Feature activation+0.389
up
Token up
Feature activation+0.274
to
Token to
Feature activation+0.163
11
Token 11
Feature activation+0.075
balls
Token balls
Feature activation+0.205
per
Token per
Feature activation+0.051
second
Token second
Feature activation+0.123
the
Token the
Feature activation+0.000
ability
Token ability
Feature activation+0.000
of
Token of
Feature activation+0.083
Te
Token Te
Feature activation+0.079
emo
Tokenemo
Feature activation+0.000
in
Token in
Feature activation+0.282
which
Token which
Feature activation+0.219
Te
Token Te
Feature activation+0.229
emo
Tokenemo
Feature activation+0.001
blind
Token blind
Feature activation+0.317
the
Token the
Feature activation+0.387
-
Token -
Feature activation+0.000
Sylv
Token Sylv
Feature activation+0.059
ain
Tokenain
Feature activation+0.121
Marg
Token Marg
Feature activation+0.190
aine
Tokenaine
Feature activation+0.253
-
Token -
Feature activation+0.260
13
Token 13
Feature activation+0.201
-
Token -
Feature activation+0.149
Bro
Token Bro
Feature activation+0.198
oms
Tokenoms
Feature activation+0.051
Ċ
TokenĊ
Feature activation+0.000

INTERVAL 0.122 - 0.244
CONTAINS 0.298%

In
Token In
Feature activation+0.000
1935
Token 1935
Feature activation+0.000
Vol
Token Vol
Feature activation+0.000
iva
Tokeniva
Feature activation+0.115
tried
Token tried
Feature activation+0.106
to
Token to
Feature activation+0.170
revive
Token revive
Feature activation+0.000
the
Token the
Feature activation+0.018
flag
Token flag
Feature activation+0.000
ging
Tokenging
Feature activation+0.000
fortunes
Token fortunes
Feature activation+0.000
minor
Token minor
Feature activation+0.000
flies
Token flies
Feature activation+0.000
frequently
Token frequently
Feature activation+0.000
.[
Token.[
Feature activation+0.216
4
Token4
Feature activation+0.269
][
Token][
Feature activation+0.220
6
Token6
Feature activation+0.007
]
Token]
Feature activation+0.110
Ċ
TokenĊ
Feature activation+0.000
Ċ
TokenĊ
Feature activation+0.000
Ec
TokenEc
Feature activation+0.000
agn
Tokenagn
Feature activation+0.000
é
Tokené
Feature activation+0.000
in
Token in
Feature activation+0.089
2003
Token 2003
Feature activation+0.078
(
Token (
Feature activation+0.089
also
Tokenalso
Feature activation+0.186
a
Token a
Feature activation+0.021
closer
Token closer
Feature activation+0.146
).
Token).
Feature activation+0.029
A
Token A
Feature activation+0.017
total
Token total
Feature activation+0.000
by
Token by
Feature activation+0.000
punching
Token punching
Feature activation+0.000
and
Token and
Feature activation+0.010
kicking
Token kicking
Feature activation+0.033
him
Token him
Feature activation+0.147
and
Token and
Feature activation+0.146
stamp
Token stamp
Feature activation+0.076
ing
Tokening
Feature activation+0.039
on
Token on
Feature activation+0.039
his
Token his
Feature activation+0.006
head
Token head
Feature activation+0.055
Se
Token Se
Feature activation+0.000
ism
Tokenism
Feature activation+0.000
ic
Tokenic
Feature activation+0.000
Slam
Token Slam
Feature activation+0.000
,
Token,
Feature activation+0.043
etc
Token etc
Feature activation+0.173
.
Token.
Feature activation+0.031
New
Token New
Feature activation+0.200
Sets
Token Sets
Feature activation+0.210
:
Token :
Feature activation+0.028
Monk
Token Monk
Feature activation+0.027

INTERVAL 0.000 - 0.122
CONTAINS 99.486%

simple
Token simple
Feature activation+0.000
App
Token App
Feature activation+0.000
Ind
TokenInd
Feature activation+0.000
icator
Tokenicator
Feature activation+0.000
that
Token that
Feature activation+0.000
makes
Token makes
Feature activation+0.000
it
Token it
Feature activation+0.000
easy
Token easy
Feature activation+0.000
to
Token to
Feature activation+0.000
switch
Token switch
Feature activation+0.000
between
Token between
Feature activation+0.000
re
Tokenre
Feature activation+0.000
covering
Token covering
Feature activation+0.000
.
Token.
Feature activation+0.000
Whilst
Token Whilst
Feature activation+0.000
there
Token there
Feature activation+0.000
you
Token you
Feature activation+0.000
can
Token can
Feature activation+0.000
join
Token join
Feature activation+0.000
in
Token in
Feature activation+0.000
the
Token the
Feature activation+0.000
conversations
Token conversations
Feature activation+0.000
the
Token the
Feature activation+0.000
AFP
Token AFP
Feature activation+0.000
told
Token told
Feature activation+0.000
The
Token The
Feature activation+0.000
Daily
Token Daily
Feature activation+0.000
Mercury
Token Mercury
Feature activation+0.000
that
Token that
Feature activation+0.000
when
Token when
Feature activation+0.000
Mr
Token Mr
Feature activation+0.000
Turner
Token Turner
Feature activation+0.000
was
Token was
Feature activation+0.000
the
Token the
Feature activation+0.000
cue
Token cue
Feature activation+0.000
for
Token for
Feature activation+0.000
the
Token the
Feature activation+0.000
travelling
Token travelling
Feature activation+0.000
support
Token support
Feature activation+0.000
to
Token to
Feature activation+0.000
start
Token start
Feature activation+0.000
their
Token their
Feature activation+0.000
party
Token party
Feature activation+0.000
and
Token and
Feature activation+0.000
.
Token.
Feature activation+0.000
Stim
Token Stim
Feature activation+0.000
ul
Tokenul
Feature activation+0.000
ants
Tokenants
Feature activation+0.000
,
Token,
Feature activation+0.000
like
Token like
Feature activation+0.000
Ad
Token Ad
Feature activation+0.000
der
Tokender
Feature activation+0.000
all
Tokenall
Feature activation+0.000
and
Token and
Feature activation+0.000
R
Token R
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