TOP ACTIVATIONS
MAX = 0.535

special ties : " stru ggle and sacrifice ." SO JO
natural mix of wild ed ibles . This requires you to
to use cannabis . Ed ibles , vapor izers
problem , further Russian inc ursions , would bring the crisis
offer plans with higher deduct ibles and out - of -
story 's one of persever ance , that 's for sure
your questions about the barn acles . <|endoftext|> From the very
guaranteed minimum income ( G MI ). Block chain
Paul Sol man : Ed ibles , at least back in
ork ery 41 ), De vers . Sl ov
. The General Assembly of Bow do in students
legislation in the 2013 General Assembly Session to i ) prohibit
paired with " Del iver ance " on Aug . 9
Just about the key w ording of potions .
the age of the Rob ber Bar ons of the late
{ turn : self . clone (), pieces : self .
premiums , doubling of deduct ibles , and narrowing provider networks
055 complaints filed against Wells Fargo which is accused of
using prostitutes and possessing B ibles . North Koreans
originally headlined " Int ang ibles have helped Patriots ' Malcolm

MIN ACTIVATIONS
MIN = -0.528

slap down against the conf lation of sovereign Israel with the
musical accents playing in the background , Survivor memor abilia throughout
plant aris ," " P unct ate ker at oder ma
ma ," and " P unct ate por oker at osis
plant aris ," " P unct ate ker at oder ma
ma ," and " P unct ate por oker at osis
own political baggage ? With background checks and confirmation hearings ,
to the mountain in the background . In front of it
bo also had a soccer background .
the visit of B ourn emouth to The Hawth orns .
Ambassador Sand erson ab et ted U . S . interests
dark regions on a light background gray = c v 2
microwave be ep in the background as he squee zes in
and flying from B ourn emouth on December 22 .
s the Sex Pist ols follows . This
as a symbol of Az eri identity , dub bing it
nightclub scenes playing in the background might help add life to
of the finest intuitive mathematic ians I have met . He
the personal intervention of Ecuador ian president Core a . Assange
3 - amine to sy late ( E 250 8 ),

INTERVAL 0.269 - 0.535
CONTAINS 0.339%

of day Mem ories of racing in the fog
hard and you couldn 't fault anybody . They showed character
NATO . A l uke warm response from the United States
the list in the Gob ber Tinker , Wrong Eye &
for the latest version of Libre Office and I wanted to

INTERVAL 0.003 - 0.269
CONTAINS 47.112%

have gotten ourselves around on foot , vehicle or bicycle ,
credit would not be easily forthcoming . The banks already take
I apply the same basic concept to my fruit and nut
read well ; it usually doesn t work .
I want to collaborate with each artist . » And his

INTERVAL -0.262 - 0.003
CONTAINS 52.229%

recently reached the level of kissing . For Stella , she
coaches and media and ACC Fresh man of the year .
t pick a better place to do it than a city
is almost here and we ve got an
text ] any text or empty Example : /* vim :

INTERVAL -0.528 - -0.262
CONTAINS 0.320%

analyzing how Phil adel ph ians speak , Fisher explains .
, stating the plan lacked transparency in the selection of the
gave the legs a good wake up call . Mid -
if you look across this room , you ll
until the arrival location is part of the search space .
Token special
Token ID2041
Feature activation-3.82e-02

Pos logit contributions
cius+0.078
unct+0.067
lation+0.064
late+0.061
 Theodore+0.061
Neg logit contributions
 Palest-0.075
ggle-0.073
adium-0.072
 gib-0.069
DER-0.069
Tokenties
Token ID4278
Feature activation-2.46e-03

Pos logit contributions
cius+0.026
unct+0.023
lation+0.022
 Theodore+0.021
late+0.021
Neg logit contributions
 Palest-0.026
ggle-0.025
adium-0.025
 gib-0.024
DER-0.024
Token:
Token ID25
Feature activation+3.38e-02

Pos logit contributions
cius+0.002
unct+0.002
lation+0.002
late+0.002
 Theodore+0.002
Neg logit contributions
 Palest-0.001
ggle-0.001
adium-0.001
 gib-0.001
DER-0.001
Token "
Token ID366
Feature activation-7.89e-02

Pos logit contributions
 Palest+0.023
ggle+0.022
adium+0.022
 gib+0.021
DER+0.021
Neg logit contributions
cius-0.024
unct-0.020
lation-0.019
late-0.018
 Theodore-0.018
Tokenstru
Token ID19554
Feature activation-5.75e-02

Pos logit contributions
cius+0.056
unct+0.048
lation+0.046
late+0.044
 Theodore+0.044
Neg logit contributions
 Palest-0.052
ggle-0.050
adium-0.050
 gib-0.048
verson-0.048
Tokenggle
Token ID16444
Feature activation+5.35e-01

Pos logit contributions
cius+0.073
unct+0.067
lation+0.065
late+0.064
 Theodore+0.064
Neg logit contributions
 Palest-0.006
adium-0.005
ggle-0.004
 gib-0.003
DER-0.003
Token and
Token ID290
Feature activation+1.60e-02

Pos logit contributions
 Palest+0.352
ggle+0.342
adium+0.338
 gib+0.326
DER+0.323
Neg logit contributions
cius-0.380
unct-0.326
lation-0.313
late-0.299
 Theodore-0.297
Token sacrifice
Token ID11728
Feature activation+2.79e-02

Pos logit contributions
 Palest+0.011
ggle+0.010
adium+0.010
 gib+0.010
DER+0.010
Neg logit contributions
cius-0.011
unct-0.010
lation-0.009
late-0.009
 Theodore-0.009
Token."
Token ID526
Feature activation+5.57e-02

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.016
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.022
unct-0.019
lation-0.018
late-0.017
 Theodore-0.017
Token SO
Token ID12809
Feature activation+5.31e-02

Pos logit contributions
 Palest+0.038
ggle+0.037
adium+0.036
 gib+0.035
DER+0.035
Neg logit contributions
cius-0.038
unct-0.033
lation-0.032
late-0.030
 Theodore-0.030
TokenJO
Token ID45006
Feature activation-1.26e-02

Pos logit contributions
 Palest+0.033
ggle+0.032
adium+0.032
 gib+0.031
verson+0.030
Neg logit contributions
cius-0.039
unct-0.034
lation-0.033
late-0.032
 Theodore-0.032
Token natural
Token ID3288
Feature activation+1.46e-01

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.005
DER-0.005
Token mix
Token ID5022
Feature activation-8.52e-03

Pos logit contributions
 Palest+0.092
ggle+0.089
adium+0.089
 gib+0.085
verson+0.084
Neg logit contributions
cius-0.108
unct-0.093
lation-0.090
late-0.086
 Theodore-0.085
Token of
Token ID286
Feature activation+2.11e-02

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.005
DER-0.005
Token wild
Token ID4295
Feature activation+8.56e-03

Pos logit contributions
 Palest+0.015
ggle+0.014
adium+0.014
 gib+0.014
DER+0.013
Neg logit contributions
cius-0.014
unct-0.012
lation-0.012
late-0.011
 Theodore-0.011
Token ed
Token ID1225
Feature activation-9.46e-03

Pos logit contributions
 Palest+0.006
ggle+0.006
adium+0.006
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.005
 Theodore-0.005
Tokenibles
Token ID18764
Feature activation+5.24e-01

Pos logit contributions
cius+0.011
unct+0.010
lation+0.010
late+0.010
 Theodore+0.009
Neg logit contributions
 Palest-0.002
ggle-0.002
adium-0.002
 gib-0.002
verson-0.001
Token.
Token ID13
Feature activation+1.83e-02

Pos logit contributions
 Palest+0.332
ggle+0.322
adium+0.319
 gib+0.308
DER+0.305
Neg logit contributions
cius-0.384
unct-0.331
lation-0.318
late-0.305
 Theodore-0.303
Token This
Token ID770
Feature activation+5.40e-03

Pos logit contributions
 Palest+0.013
ggle+0.012
adium+0.012
 gib+0.012
DER+0.012
Neg logit contributions
cius-0.012
unct-0.011
lation-0.010
late-0.010
 Theodore-0.010
Token requires
Token ID4433
Feature activation-9.68e-02

Pos logit contributions
 Palest+0.004
ggle+0.003
adium+0.003
 gib+0.003
DER+0.003
Neg logit contributions
cius-0.004
unct-0.003
lation-0.003
late-0.003
 Theodore-0.003
Token you
Token ID345
Feature activation-3.12e-02

Pos logit contributions
cius+0.069
unct+0.059
lation+0.057
late+0.054
 Theodore+0.054
Neg logit contributions
 Palest-0.064
ggle-0.062
adium-0.061
 gib-0.059
DER-0.058
Token to
Token ID284
Feature activation+1.26e-02

Pos logit contributions
cius+0.025
unct+0.022
lation+0.021
late+0.020
 Theodore+0.020
Neg logit contributions
 Palest-0.018
ggle-0.017
adium-0.017
 gib-0.016
DER-0.016
Token to
Token ID284
Feature activation+1.45e-02

Pos logit contributions
 Palest+0.054
ggle+0.052
adium+0.051
 gib+0.049
verson+0.049
Neg logit contributions
cius-0.063
unct-0.054
lation-0.053
late-0.050
 Theodore-0.050
Token use
Token ID779
Feature activation+9.82e-02

Pos logit contributions
 Palest+0.009
ggle+0.009
adium+0.008
 gib+0.008
DER+0.008
Neg logit contributions
cius-0.011
unct-0.010
lation-0.009
late-0.009
 Theodore-0.009
Token cannabis
Token ID9499
Feature activation+2.41e-02

Pos logit contributions
 Palest+0.065
ggle+0.064
adium+0.063
 gib+0.061
DER+0.060
Neg logit contributions
cius-0.069
unct-0.059
lation-0.057
late-0.054
 Theodore-0.054
Token.
Token ID13
Feature activation+2.27e-03

Pos logit contributions
 Palest+0.015
ggle+0.015
adium+0.015
 gib+0.014
DER+0.014
Neg logit contributions
cius-0.018
unct-0.015
lation-0.015
late-0.014
 Theodore-0.014
Token Ed
Token ID1717
Feature activation+9.63e-02

Pos logit contributions
 Palest+0.002
ggle+0.002
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.002
unct-0.001
lation-0.001
late-0.001
 Theodore-0.001
Tokenibles
Token ID18764
Feature activation+5.00e-01

Pos logit contributions
 Palest+0.028
ggle+0.026
adium+0.026
 gib+0.023
verson+0.023
Neg logit contributions
cius-0.104
unct-0.094
lation-0.092
late-0.089
 Theodore-0.089
Token,
Token ID11
Feature activation-1.51e-03

Pos logit contributions
 Palest+0.317
ggle+0.307
adium+0.305
 gib+0.294
DER+0.291
Neg logit contributions
cius-0.366
unct-0.316
lation-0.303
late-0.291
 Theodore-0.289
Token vapor
Token ID20199
Feature activation-3.69e-02

Pos logit contributions
cius+0.001
unct+0.001
lation+0.001
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.001
ggle-0.001
adium-0.001
 gib-0.001
DER-0.001
Tokenizers
Token ID11341
Feature activation-1.48e-01

Pos logit contributions
cius+0.020
unct+0.016
lation+0.016
late+0.015
 Theodore+0.015
Neg logit contributions
 Palest-0.030
ggle-0.030
adium-0.029
 gib-0.028
verson-0.028
Token
Token ID1399
Feature activation+1.30e-01

Pos logit contributions
cius+0.108
unct+0.093
lation+0.089
late+0.085
 Theodore+0.085
Neg logit contributions
 Palest-0.095
ggle-0.092
adium-0.092
 gib-0.088
DER-0.087
Token
Token ID198
Feature activation+5.86e-02

Pos logit contributions
 Palest+0.089
ggle+0.087
adium+0.086
 gib+0.083
DER+0.082
Neg logit contributions
cius-0.088
unct-0.075
lation-0.072
late-0.069
 Theodore-0.068
Token problem
Token ID1917
Feature activation+1.62e-02

Pos logit contributions
 Palest+0.055
ggle+0.053
adium+0.053
 gib+0.051
DER+0.051
Neg logit contributions
cius-0.064
unct-0.055
lation-0.053
late-0.051
 Theodore-0.051
Token,
Token ID11
Feature activation+5.99e-03

Pos logit contributions
 Palest+0.010
ggle+0.010
adium+0.010
 gib+0.010
DER+0.009
Neg logit contributions
cius-0.012
unct-0.010
lation-0.010
late-0.009
 Theodore-0.009
Token further
Token ID2252
Feature activation+1.28e-01

Pos logit contributions
 Palest+0.004
ggle+0.004
adium+0.004
 gib+0.004
DER+0.004
Neg logit contributions
cius-0.004
unct-0.004
lation-0.003
late-0.003
 Theodore-0.003
Token Russian
Token ID3394
Feature activation+9.11e-03

Pos logit contributions
 Palest+0.080
ggle+0.077
adium+0.077
 gib+0.074
DER+0.073
Neg logit contributions
cius-0.095
unct-0.082
lation-0.079
late-0.076
 Theodore-0.075
Token inc
Token ID753
Feature activation+5.60e-02

Pos logit contributions
 Palest+0.006
ggle+0.006
adium+0.006
 gib+0.006
DER+0.006
Neg logit contributions
cius-0.006
unct-0.006
lation-0.005
late-0.005
 Theodore-0.005
Tokenursions
Token ID42394
Feature activation+4.91e-01

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.015
 gib+0.014
DER+0.014
Neg logit contributions
cius-0.060
unct-0.054
lation-0.053
late-0.052
 Theodore-0.051
Token,
Token ID11
Feature activation+1.13e-02

Pos logit contributions
 Palest+0.320
ggle+0.310
adium+0.307
 gib+0.296
DER+0.294
Neg logit contributions
cius-0.352
unct-0.303
lation-0.291
late-0.278
 Theodore-0.276
Token would
Token ID561
Feature activation+4.26e-02

Pos logit contributions
 Palest+0.007
ggle+0.007
adium+0.007
 gib+0.007
DER+0.007
Neg logit contributions
cius-0.008
unct-0.007
lation-0.007
late-0.007
 Theodore-0.007
Token bring
Token ID2222
Feature activation+3.25e-03

Pos logit contributions
 Palest+0.028
ggle+0.028
adium+0.027
 gib+0.026
DER+0.026
Neg logit contributions
cius-0.030
unct-0.026
lation-0.025
late-0.023
 Theodore-0.023
Token the
Token ID262
Feature activation+4.10e-02

Pos logit contributions
 Palest+0.002
ggle+0.002
adium+0.002
 gib+0.002
DER+0.002
Neg logit contributions
cius-0.002
unct-0.002
lation-0.002
late-0.002
 Theodore-0.002
Token crisis
Token ID4902
Feature activation-4.77e-02

Pos logit contributions
 Palest+0.027
ggle+0.026
adium+0.026
 gib+0.025
DER+0.025
Neg logit contributions
cius-0.029
unct-0.025
lation-0.024
late-0.023
 Theodore-0.023
Token offer
Token ID2897
Feature activation+3.84e-02

Pos logit contributions
 Palest+0.014
ggle+0.014
adium+0.014
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.018
unct-0.015
lation-0.015
late-0.014
 Theodore-0.014
Token plans
Token ID3352
Feature activation+2.66e-02

Pos logit contributions
 Palest+0.025
ggle+0.024
adium+0.024
 gib+0.023
DER+0.023
Neg logit contributions
cius-0.028
unct-0.024
lation-0.023
late-0.022
 Theodore-0.022
Token with
Token ID351
Feature activation-3.91e-02

Pos logit contributions
 Palest+0.018
ggle+0.017
adium+0.017
 gib+0.016
DER+0.016
Neg logit contributions
cius-0.018
unct-0.016
lation-0.015
late-0.015
 Theodore-0.014
Token higher
Token ID2440
Feature activation+6.58e-02

Pos logit contributions
cius+0.028
unct+0.024
lation+0.023
late+0.022
 Theodore+0.022
Neg logit contributions
 Palest-0.026
ggle-0.025
adium-0.025
 gib-0.024
DER-0.023
Token deduct
Token ID18777
Feature activation-7.22e-02

Pos logit contributions
 Palest+0.046
ggle+0.045
adium+0.045
 gib+0.043
DER+0.043
Neg logit contributions
cius-0.044
unct-0.037
lation-0.035
late-0.034
 Theodore-0.034
Tokenibles
Token ID18764
Feature activation+4.72e-01

Pos logit contributions
cius+0.083
unct+0.077
lation+0.075
late+0.073
 Theodore+0.073
Neg logit contributions
 Palest-0.016
ggle-0.013
adium-0.012
 gib-0.011
DER-0.011
Token and
Token ID290
Feature activation+1.82e-02

Pos logit contributions
 Palest+0.304
ggle+0.295
adium+0.292
 gib+0.281
DER+0.279
Neg logit contributions
cius-0.342
unct-0.294
lation-0.283
late-0.271
 Theodore-0.269
Token out
Token ID503
Feature activation-9.93e-03

Pos logit contributions
 Palest+0.011
ggle+0.011
adium+0.011
 gib+0.010
DER+0.010
Neg logit contributions
cius-0.014
unct-0.012
lation-0.012
late-0.011
 Theodore-0.011
Token-
Token ID12
Feature activation-1.24e-02

Pos logit contributions
cius+0.007
unct+0.006
lation+0.006
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.007
ggle-0.007
adium-0.007
 gib-0.006
DER-0.006
Tokenof
Token ID1659
Feature activation-1.46e-01

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.010
ggle-0.010
adium-0.010
 gib-0.010
DER-0.010
Token-
Token ID12
Feature activation-7.42e-03

Pos logit contributions
cius+0.096
unct+0.082
lation+0.079
late+0.075
 Theodore+0.074
Neg logit contributions
 Palest-0.104
ggle-0.100
adium-0.098
 gib-0.095
DER-0.094
Token story
Token ID1621
Feature activation+2.32e-01

Pos logit contributions
 Palest+0.058
ggle+0.056
adium+0.056
DER+0.053
 gib+0.053
Neg logit contributions
cius-0.058
unct-0.050
lation-0.048
late-0.046
 Theodore-0.046
Token's
Token ID338
Feature activation+4.03e-02

Pos logit contributions
 Palest+0.150
ggle+0.144
adium+0.143
 gib+0.137
DER+0.137
Neg logit contributions
cius-0.168
unct-0.145
lation-0.139
late-0.133
 Theodore-0.132
Token one
Token ID530
Feature activation-3.21e-02

Pos logit contributions
 Palest+0.026
ggle+0.025
adium+0.025
 gib+0.024
DER+0.024
Neg logit contributions
cius-0.029
unct-0.025
lation-0.024
late-0.023
 Theodore-0.023
Token of
Token ID286
Feature activation+5.46e-02

Pos logit contributions
cius+0.023
unct+0.020
lation+0.019
late+0.019
 Theodore+0.018
Neg logit contributions
 Palest-0.021
ggle-0.020
adium-0.020
 gib-0.019
DER-0.019
Token persever
Token ID45712
Feature activation-1.05e-01

Pos logit contributions
 Palest+0.037
ggle+0.036
adium+0.036
 gib+0.034
DER+0.034
Neg logit contributions
cius-0.037
unct-0.032
lation-0.031
late-0.029
 Theodore-0.029
Tokenance
Token ID590
Feature activation+4.65e-01

Pos logit contributions
cius+0.115
unct+0.105
lation+0.103
late+0.100
 Theodore+0.099
Neg logit contributions
 Palest-0.030
ggle-0.026
adium-0.026
 gib-0.024
DER-0.024
Token,
Token ID11
Feature activation+1.95e-02

Pos logit contributions
 Palest+0.295
ggle+0.284
adium+0.283
 gib+0.271
DER+0.270
Neg logit contributions
cius-0.341
unct-0.293
lation-0.283
late-0.271
 Theodore-0.270
Token that
Token ID326
Feature activation+8.10e-03

Pos logit contributions
 Palest+0.014
ggle+0.013
adium+0.013
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.013
unct-0.011
lation-0.011
late-0.010
 Theodore-0.010
Token's
Token ID338
Feature activation+3.05e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.004
 Theodore-0.004
Token for
Token ID329
Feature activation+1.34e-02

Pos logit contributions
 Palest+0.019
ggle+0.019
adium+0.018
 gib+0.018
DER+0.018
Neg logit contributions
cius-0.022
unct-0.019
lation-0.019
late-0.018
 Theodore-0.018
Token sure
Token ID1654
Feature activation+2.95e-02

Pos logit contributions
 Palest+0.008
ggle+0.008
adium+0.008
verson+0.008
 gib+0.008
Neg logit contributions
cius-0.010
unct-0.009
lation-0.008
late-0.008
 Theodore-0.008
Token your
Token ID534
Feature activation+3.44e-03

Pos logit contributions
 Palest+0.156
ggle+0.151
adium+0.150
 gib+0.143
DER+0.142
Neg logit contributions
cius-0.199
unct-0.173
lation-0.166
late-0.160
 Theodore-0.159
Token questions
Token ID2683
Feature activation+1.74e-01

Pos logit contributions
 Palest+0.001
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.003
unct-0.003
lation-0.003
late-0.003
 Theodore-0.003
Token about
Token ID546
Feature activation-4.00e-02

Pos logit contributions
 Palest+0.113
ggle+0.110
adium+0.109
 gib+0.104
DER+0.104
Neg logit contributions
cius-0.125
unct-0.107
lation-0.103
late-0.099
 Theodore-0.098
Token the
Token ID262
Feature activation+5.18e-03

Pos logit contributions
cius+0.028
unct+0.024
lation+0.023
late+0.022
 Theodore+0.022
Neg logit contributions
 Palest-0.026
ggle-0.026
adium-0.025
 gib-0.024
DER-0.024
Token barn
Token ID25203
Feature activation+5.62e-02

Pos logit contributions
 Palest+0.003
ggle+0.003
adium+0.003
 gib+0.003
DER+0.003
Neg logit contributions
cius-0.004
unct-0.003
lation-0.003
late-0.003
 Theodore-0.003
Tokenacles
Token ID9928
Feature activation+4.61e-01

Pos logit contributions
 Palest+0.033
ggle+0.032
adium+0.032
 gib+0.031
DER+0.030
Neg logit contributions
cius-0.043
unct-0.038
lation-0.036
late-0.035
 Theodore-0.035
Token.
Token ID13
Feature activation+8.61e-03

Pos logit contributions
 Palest+0.295
ggle+0.286
adium+0.283
 gib+0.273
DER+0.271
Neg logit contributions
cius-0.335
unct-0.289
lation-0.278
late-0.266
 Theodore-0.264
Token<|endoftext|>
Token ID50256
Feature activation+7.27e-03

Pos logit contributions
 Palest+0.006
ggle+0.006
adium+0.006
 gib+0.006
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.005
 Theodore-0.005
TokenFrom
Token ID4863
Feature activation-3.90e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
verson+0.005
Neg logit contributions
cius-0.005
unct-0.004
lation-0.004
late-0.004
 Theodore-0.004
Token the
Token ID262
Feature activation+3.26e-02

Pos logit contributions
cius+0.027
unct+0.023
lation+0.022
 Theodore+0.022
late+0.022
Neg logit contributions
 Palest-0.026
ggle-0.025
adium-0.025
 gib-0.024
verson-0.024
Token very
Token ID845
Feature activation+5.48e-02

Pos logit contributions
 Palest+0.021
ggle+0.021
adium+0.020
 gib+0.020
DER+0.019
Neg logit contributions
cius-0.023
unct-0.020
lation-0.019
late-0.019
 Theodore-0.018
Token guaranteed
Token ID11462
Feature activation-4.38e-02

Pos logit contributions
 Palest+0.032
ggle+0.031
adium+0.031
 gib+0.029
DER+0.029
Neg logit contributions
cius-0.034
unct-0.029
lation-0.028
late-0.026
 Theodore-0.026
Token minimum
Token ID5288
Feature activation+3.45e-02

Pos logit contributions
cius+0.031
unct+0.026
lation+0.025
late+0.024
 Theodore+0.024
Neg logit contributions
 Palest-0.029
ggle-0.028
adium-0.028
DER-0.027
verson-0.027
Token income
Token ID3739
Feature activation+6.71e-02

Pos logit contributions
 Palest+0.023
ggle+0.022
adium+0.022
 gib+0.021
DER+0.021
Neg logit contributions
cius-0.024
unct-0.020
lation-0.020
late-0.019
 Theodore-0.019
Token (
Token ID357
Feature activation+8.54e-03

Pos logit contributions
 Palest+0.043
ggle+0.042
adium+0.042
 gib+0.040
DER+0.040
Neg logit contributions
cius-0.048
unct-0.041
lation-0.040
late-0.038
 Theodore-0.038
TokenG
Token ID38
Feature activation-1.55e-02

Pos logit contributions
 Palest+0.006
ggle+0.006
adium+0.006
 gib+0.005
verson+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.005
 Theodore-0.005
TokenMI
Token ID8895
Feature activation+4.60e-01

Pos logit contributions
cius+0.012
unct+0.011
lation+0.010
late+0.010
 Theodore+0.010
Neg logit contributions
 Palest-0.009
ggle-0.009
adium-0.008
 gib-0.008
verson-0.008
Token).
Token ID737
Feature activation+7.75e-02

Pos logit contributions
 Palest+0.284
ggle+0.275
adium+0.272
 gib+0.261
DER+0.260
Neg logit contributions
cius-0.347
unct-0.300
lation-0.287
late-0.277
 Theodore-0.275
Token
Token ID198
Feature activation+8.31e-02

Pos logit contributions
 Palest+0.052
ggle+0.051
adium+0.050
 gib+0.049
DER+0.048
Neg logit contributions
cius-0.054
unct-0.046
lation-0.044
late-0.042
 Theodore-0.042
Token
Token ID198
Feature activation+7.03e-02

Pos logit contributions
 Palest+0.059
ggle+0.056
adium+0.055
 gib+0.054
verson+0.053
Neg logit contributions
cius-0.056
unct-0.048
lation-0.046
late-0.044
 Theodore-0.044
TokenBlock
Token ID12235
Feature activation+7.70e-02

Pos logit contributions
 Palest+0.050
ggle+0.049
adium+0.048
 gib+0.047
verson+0.046
Neg logit contributions
cius-0.046
unct-0.039
lation-0.038
late-0.036
 Theodore-0.035
Tokenchain
Token ID7983
Feature activation+1.10e-01

Pos logit contributions
 Palest+0.037
ggle+0.036
adium+0.035
 gib+0.033
DER+0.033
Neg logit contributions
cius-0.068
unct-0.060
lation-0.059
late-0.057
 Theodore-0.056
TokenPaul
Token ID12041
Feature activation+4.67e-02

Pos logit contributions
 Palest+0.029
ggle+0.028
adium+0.028
 gib+0.027
DER+0.027
Neg logit contributions
cius-0.027
unct-0.023
lation-0.022
late-0.021
 Theodore-0.021
Token Sol
Token ID4294
Feature activation-3.52e-02

Pos logit contributions
 Palest+0.032
ggle+0.031
adium+0.031
 gib+0.030
verson+0.029
Neg logit contributions
cius-0.032
unct-0.027
lation-0.026
 Theodore-0.025
late-0.025
Tokenman
Token ID805
Feature activation+9.92e-02

Pos logit contributions
cius+0.027
unct+0.023
lation+0.023
late+0.022
 Theodore+0.021
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.020
 gib-0.020
DER-0.019
Token:
Token ID25
Feature activation+3.30e-02

Pos logit contributions
 Palest+0.062
ggle+0.059
adium+0.058
 gib+0.056
DER+0.055
Neg logit contributions
cius-0.075
unct-0.065
lation-0.063
late-0.061
 Theodore-0.060
Token Ed
Token ID1717
Feature activation+6.87e-02

Pos logit contributions
 Palest+0.023
ggle+0.022
adium+0.022
 gib+0.021
verson+0.021
Neg logit contributions
cius-0.023
unct-0.019
lation-0.018
 Theodore-0.018
late-0.018
Tokenibles
Token ID18764
Feature activation+4.56e-01

Pos logit contributions
 Palest+0.012
ggle+0.011
adium+0.010
 gib+0.009
verson+0.008
Neg logit contributions
cius-0.082
unct-0.075
lation-0.073
late-0.072
 Theodore-0.071
Token,
Token ID11
Feature activation+2.12e-03

Pos logit contributions
 Palest+0.311
ggle+0.302
adium+0.299
 gib+0.289
DER+0.286
Neg logit contributions
cius-0.313
unct-0.268
lation-0.256
late-0.245
 Theodore-0.243
Token at
Token ID379
Feature activation+2.49e-02

Pos logit contributions
 Palest+0.001
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.001
unct-0.001
lation-0.001
late-0.001
 Theodore-0.001
Token least
Token ID1551
Feature activation-1.88e-02

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.016
 gib+0.016
DER+0.015
Neg logit contributions
cius-0.017
unct-0.015
lation-0.014
late-0.014
 Theodore-0.014
Token back
Token ID736
Feature activation+6.17e-02

Pos logit contributions
cius+0.013
unct+0.011
lation+0.011
late+0.011
 Theodore+0.010
Neg logit contributions
 Palest-0.012
ggle-0.012
adium-0.012
 gib-0.011
DER-0.011
Token in
Token ID287
Feature activation-3.10e-02

Pos logit contributions
 Palest+0.044
ggle+0.043
adium+0.043
 gib+0.041
DER+0.041
Neg logit contributions
cius-0.040
unct-0.034
lation-0.032
late-0.031
 Theodore-0.031
Tokenork
Token ID967
Feature activation+1.34e-01

Pos logit contributions
 Palest+0.021
ggle+0.021
adium+0.020
 gib+0.020
DER+0.020
Neg logit contributions
cius-0.024
unct-0.021
lation-0.020
late-0.020
 Theodore-0.019
Tokenery
Token ID1924
Feature activation+1.77e-01

Pos logit contributions
 Palest+0.087
ggle+0.084
adium+0.083
 gib+0.080
DER+0.080
Neg logit contributions
cius-0.096
unct-0.083
lation-0.080
late-0.076
 Theodore-0.076
Token 41
Token ID6073
Feature activation+1.15e-01

Pos logit contributions
 Palest+0.109
ggle+0.106
adium+0.105
 gib+0.101
DER+0.100
Neg logit contributions
cius-0.133
unct-0.115
lation-0.111
late-0.107
 Theodore-0.106
Token),
Token ID828
Feature activation+7.85e-02

Pos logit contributions
 Palest+0.074
ggle+0.072
adium+0.071
 gib+0.068
DER+0.068
Neg logit contributions
cius-0.083
unct-0.071
lation-0.068
late-0.065
 Theodore-0.065
Token De
Token ID1024
Feature activation+2.15e-01

Pos logit contributions
 Palest+0.052
ggle+0.051
adium+0.050
 gib+0.048
DER+0.048
Neg logit contributions
cius-0.055
unct-0.047
lation-0.046
late-0.044
 Theodore-0.044
Tokenvers
Token ID690
Feature activation+4.55e-01

Pos logit contributions
 Palest+0.135
ggle+0.131
adium+0.129
 gib+0.124
DER+0.123
Neg logit contributions
cius-0.159
unct-0.137
lation-0.132
late-0.127
 Theodore-0.126
Token.
Token ID13
Feature activation+8.44e-02

Pos logit contributions
 Palest+0.299
ggle+0.290
adium+0.287
 gib+0.278
DER+0.276
Neg logit contributions
cius-0.323
unct-0.277
lation-0.266
late-0.253
 Theodore-0.253
Token
Token ID198
Feature activation+7.79e-02

Pos logit contributions
 Palest+0.056
ggle+0.054
adium+0.054
 gib+0.052
DER+0.051
Neg logit contributions
cius-0.060
unct-0.051
lation-0.049
late-0.047
 Theodore-0.047
Token
Token ID198
Feature activation+5.81e-02

Pos logit contributions
 Palest+0.055
ggle+0.053
adium+0.052
 gib+0.051
verson+0.050
Neg logit contributions
cius-0.052
unct-0.045
lation-0.043
late-0.041
 Theodore-0.041
TokenSl
Token ID11122
Feature activation-1.21e-02

Pos logit contributions
 Palest+0.039
ggle+0.038
adium+0.038
 gib+0.037
verson+0.036
Neg logit contributions
cius-0.040
unct-0.034
lation-0.033
late-0.032
 Theodore-0.031
Tokenov
Token ID709
Feature activation-1.08e-01

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.005
 Theodore+0.004
Neg logit contributions
 Palest-0.010
ggle-0.010
adium-0.010
 gib-0.010
DER-0.010
Token.
Token ID13
Feature activation+7.83e-03

Pos logit contributions
 Palest+0.110
ggle+0.107
adium+0.106
 gib+0.102
DER+0.101
Neg logit contributions
cius-0.119
unct-0.102
lation-0.098
late-0.094
 Theodore-0.093
Token
Token ID198
Feature activation+1.72e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.005
unct-0.005
lation-0.004
late-0.004
 Theodore-0.004
Token
Token ID198
Feature activation+1.26e-02

Pos logit contributions
 Palest+0.012
ggle+0.012
adium+0.011
 gib+0.011
verson+0.011
Neg logit contributions
cius-0.012
unct-0.010
lation-0.009
late-0.009
 Theodore-0.009
TokenThe
Token ID464
Feature activation+4.39e-02

Pos logit contributions
 Palest+0.009
ggle+0.009
adium+0.009
 gib+0.008
verson+0.008
Neg logit contributions
cius-0.008
unct-0.007
lation-0.007
late-0.007
 Theodore-0.006
Token General
Token ID3611
Feature activation-8.44e-02

Pos logit contributions
 Palest+0.028
ggle+0.027
adium+0.027
 gib+0.025
verson+0.025
Neg logit contributions
cius-0.032
unct-0.028
lation-0.027
late-0.026
 Theodore-0.026
Token Assembly
Token ID10006
Feature activation+4.52e-01

Pos logit contributions
cius+0.059
unct+0.050
lation+0.048
late+0.046
 Theodore+0.046
Neg logit contributions
 Palest-0.057
ggle-0.055
adium-0.055
 gib-0.053
DER-0.052
Token of
Token ID286
Feature activation+2.84e-02

Pos logit contributions
 Palest+0.292
ggle+0.284
adium+0.280
 gib+0.270
DER+0.268
Neg logit contributions
cius-0.327
unct-0.281
lation-0.270
late-0.259
 Theodore-0.257
Token Bow
Token ID9740
Feature activation-2.62e-01

Pos logit contributions
 Palest+0.020
ggle+0.019
adium+0.019
 gib+0.018
DER+0.018
Neg logit contributions
cius-0.019
unct-0.016
lation-0.016
late-0.015
 Theodore-0.015
Tokendo
Token ID4598
Feature activation+2.08e-01

Pos logit contributions
cius+0.243
unct+0.215
lation+0.208
late+0.203
 Theodore+0.200
Neg logit contributions
 Palest-0.123
adium-0.112
ggle-0.111
 gib-0.107
DER-0.103
Tokenin
Token ID259
Feature activation-3.12e-02

Pos logit contributions
 Palest+0.163
ggle+0.157
adium+0.156
 gib+0.152
DER+0.150
Neg logit contributions
cius-0.123
unct-0.102
lation-0.097
late-0.092
 Theodore-0.090
Token students
Token ID2444
Feature activation+3.93e-02

Pos logit contributions
cius+0.024
unct+0.020
lation+0.020
late+0.019
 Theodore+0.019
Neg logit contributions
 Palest-0.019
ggle-0.019
adium-0.018
 gib-0.018
DER-0.018
Token legislation
Token ID5520
Feature activation-1.81e-01

Pos logit contributions
cius+0.024
unct+0.020
lation+0.019
late+0.018
 Theodore+0.018
Neg logit contributions
 Palest-0.031
ggle-0.030
adium-0.030
 gib-0.029
DER-0.029
Token in
Token ID287
Feature activation+2.08e-02

Pos logit contributions
cius+0.133
unct+0.115
lation+0.111
 Theodore+0.107
late+0.106
Neg logit contributions
 Palest-0.113
ggle-0.110
adium-0.110
 gib-0.105
DER-0.104
Token the
Token ID262
Feature activation+4.24e-02

Pos logit contributions
 Palest+0.014
ggle+0.014
adium+0.014
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.014
unct-0.012
lation-0.012
late-0.011
 Theodore-0.011
Token 2013
Token ID2211
Feature activation+3.14e-02

Pos logit contributions
 Palest+0.026
ggle+0.025
adium+0.025
 gib+0.024
DER+0.024
Neg logit contributions
cius-0.032
unct-0.028
lation-0.027
late-0.026
 Theodore-0.026
Token General
Token ID3611
Feature activation-7.95e-02

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.016
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.026
unct-0.023
lation-0.022
late-0.021
 Theodore-0.021
Token Assembly
Token ID10006
Feature activation+4.48e-01

Pos logit contributions
cius+0.096
unct+0.089
lation+0.087
 Theodore+0.085
late+0.085
Neg logit contributions
 Palest-0.012
ggle-0.011
adium-0.009
 gib-0.008
DER-0.008
Token Session
Token ID23575
Feature activation+5.05e-02

Pos logit contributions
 Palest+0.277
ggle+0.269
adium+0.266
 gib+0.256
DER+0.253
Neg logit contributions
cius-0.335
unct-0.290
lation-0.280
late-0.269
 Theodore-0.268
Token to
Token ID284
Feature activation+1.41e-04

Pos logit contributions
 Palest+0.031
ggle+0.030
adium+0.030
 gib+0.029
DER+0.029
Neg logit contributions
cius-0.038
unct-0.033
lation-0.032
late-0.030
 Theodore-0.030
Token i
Token ID1312
Feature activation+7.17e-02

Pos logit contributions
 Palest+0.000
ggle+0.000
adium+0.000
 gib+0.000
DER+0.000
Neg logit contributions
cius-0.000
unct-0.000
lation-0.000
late-0.000
 Theodore-0.000
Token)
Token ID8
Feature activation+6.68e-02

Pos logit contributions
 Palest+0.045
ggle+0.044
adium+0.043
 gib+0.042
DER+0.041
Neg logit contributions
cius-0.053
unct-0.046
lation-0.044
late-0.042
 Theodore-0.042
Token prohibit
Token ID20767
Feature activation+5.57e-03

Pos logit contributions
 Palest+0.044
ggle+0.043
adium+0.042
 gib+0.041
DER+0.041
Neg logit contributions
cius-0.047
unct-0.040
lation-0.039
late-0.037
 Theodore-0.037
Token paired
Token ID20312
Feature activation+3.04e-02

Pos logit contributions
 Palest+0.031
ggle+0.030
adium+0.030
 gib+0.029
DER+0.029
Neg logit contributions
cius-0.031
unct-0.026
lation-0.025
late-0.024
 Theodore-0.024
Token with
Token ID351
Feature activation-3.81e-02

Pos logit contributions
 Palest+0.023
ggle+0.022
adium+0.022
DER+0.021
 gib+0.021
Neg logit contributions
cius-0.019
unct-0.016
lation-0.015
late-0.014
 Theodore-0.014
Token "
Token ID366
Feature activation-3.48e-02

Pos logit contributions
cius+0.026
unct+0.023
lation+0.022
late+0.021
 Theodore+0.021
Neg logit contributions
 Palest-0.026
ggle-0.025
adium-0.025
 gib-0.024
DER-0.024
TokenDel
Token ID13856
Feature activation+6.35e-02

Pos logit contributions
cius+0.023
unct+0.020
lation+0.019
late+0.018
 Theodore+0.018
Neg logit contributions
 Palest-0.025
ggle-0.024
adium-0.024
 gib-0.023
verson-0.023
Tokeniver
Token ID1428
Feature activation+1.23e-01

Pos logit contributions
 Palest+0.042
ggle+0.041
adium+0.040
 gib+0.039
DER+0.039
Neg logit contributions
cius-0.045
unct-0.038
lation-0.037
late-0.035
 Theodore-0.035
Tokenance
Token ID590
Feature activation+4.48e-01

Pos logit contributions
 Palest+0.048
ggle+0.045
adium+0.045
 gib+0.042
DER+0.041
Neg logit contributions
cius-0.120
unct-0.108
lation-0.105
late-0.102
 Theodore-0.101
Token"
Token ID1
Feature activation+2.48e-02

Pos logit contributions
 Palest+0.251
ggle+0.242
adium+0.240
 gib+0.229
DER+0.227
Neg logit contributions
cius-0.362
unct-0.316
lation-0.306
late-0.294
 Theodore-0.292
Token on
Token ID319
Feature activation-1.21e-02

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.016
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.017
unct-0.015
lation-0.014
late-0.014
 Theodore-0.013
Token Aug
Token ID2447
Feature activation+1.34e-01

Pos logit contributions
cius+0.009
unct+0.008
lation+0.007
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.008
ggle-0.008
adium-0.008
 gib-0.007
DER-0.007
Token.
Token ID13
Feature activation-3.89e-02

Pos logit contributions
 Palest+0.088
ggle+0.085
adium+0.083
 gib+0.081
DER+0.079
Neg logit contributions
cius-0.096
unct-0.084
lation-0.080
late-0.077
 Theodore-0.076
Token 9
Token ID860
Feature activation+8.05e-02

Pos logit contributions
cius+0.029
unct+0.025
lation+0.024
late+0.024
 Theodore+0.024
Neg logit contributions
 Palest-0.024
ggle-0.023
adium-0.023
 gib-0.022
verson-0.022
Token Just
Token ID2329
Feature activation+1.74e-02

Pos logit contributions
 Palest+0.030
ggle+0.029
adium+0.029
 gib+0.028
verson+0.028
Neg logit contributions
cius-0.030
unct-0.026
lation-0.025
 Theodore-0.024
late-0.024
Token about
Token ID546
Feature activation+1.02e-04

Pos logit contributions
 Palest+0.011
ggle+0.011
adium+0.011
 gib+0.010
DER+0.010
Neg logit contributions
cius-0.013
unct-0.011
lation-0.010
late-0.010
 Theodore-0.010
Token the
Token ID262
Feature activation+1.14e-02

Pos logit contributions
 Palest+0.000
ggle+0.000
adium+0.000
DER+0.000
verson+0.000
Neg logit contributions
cius-0.000
unct-0.000
lation-0.000
late-0.000
 Theodore-0.000
Token key
Token ID1994
Feature activation-6.55e-02

Pos logit contributions
 Palest+0.007
ggle+0.007
adium+0.007
DER+0.007
 gib+0.007
Neg logit contributions
cius-0.008
unct-0.007
lation-0.007
late-0.007
 Theodore-0.007
Tokenw
Token ID86
Feature activation-7.36e-02

Pos logit contributions
cius+0.049
unct+0.042
lation+0.041
late+0.039
 Theodore+0.039
Neg logit contributions
 Palest-0.041
ggle-0.039
adium-0.039
DER-0.037
 gib-0.037
Tokenording
Token ID1284
Feature activation+4.45e-01

Pos logit contributions
cius+0.083
unct+0.076
lation+0.074
late+0.072
 Theodore+0.071
Neg logit contributions
 Palest-0.018
ggle-0.016
adium-0.016
 gib-0.014
DER-0.014
Token of
Token ID286
Feature activation-8.01e-03

Pos logit contributions
 Palest+0.283
ggle+0.274
adium+0.271
 gib+0.261
DER+0.259
Neg logit contributions
cius-0.327
unct-0.282
lation-0.271
late-0.259
 Theodore-0.258
Token potions
Token ID28074
Feature activation-1.59e-01

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.004
 Theodore+0.004
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.005
DER-0.005
Token.
Token ID13
Feature activation+3.39e-02

Pos logit contributions
cius+0.112
unct+0.096
lation+0.092
late+0.088
 Theodore+0.087
Neg logit contributions
 Palest-0.106
ggle-0.102
adium-0.101
 gib-0.098
DER-0.097
Token
Token ID198
Feature activation+3.79e-02

Pos logit contributions
 Palest+0.023
ggle+0.022
adium+0.022
 gib+0.021
DER+0.021
Neg logit contributions
cius-0.024
unct-0.020
lation-0.019
late-0.019
 Theodore-0.018
Token
Token ID198
Feature activation+3.70e-02

Pos logit contributions
 Palest+0.027
ggle+0.026
adium+0.025
 gib+0.025
verson+0.024
Neg logit contributions
cius-0.025
unct-0.022
lation-0.021
late-0.020
 Theodore-0.020
Token the
Token ID262
Feature activation-9.26e-03

Pos logit contributions
 Palest+0.069
ggle+0.067
adium+0.066
 gib+0.064
DER+0.064
Neg logit contributions
cius-0.070
unct-0.060
lation-0.058
late-0.055
 Theodore-0.055
Token age
Token ID2479
Feature activation+9.91e-02

Pos logit contributions
cius+0.007
unct+0.006
lation+0.005
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.006
ggle-0.006
adium-0.006
 gib-0.006
DER-0.006
Token of
Token ID286
Feature activation-1.06e-02

Pos logit contributions
 Palest+0.066
ggle+0.063
adium+0.063
DER+0.060
 gib+0.060
Neg logit contributions
cius-0.070
unct-0.060
lation-0.058
 Theodore-0.056
late-0.056
Token the
Token ID262
Feature activation+6.57e-03

Pos logit contributions
cius+0.007
unct+0.006
lation+0.006
late+0.006
 Theodore+0.006
Neg logit contributions
 Palest-0.007
ggle-0.007
adium-0.007
 gib-0.007
DER-0.007
Token Rob
Token ID3851
Feature activation-4.48e-02

Pos logit contributions
 Palest+0.004
ggle+0.004
adium+0.004
DER+0.004
verson+0.004
Neg logit contributions
cius-0.005
unct-0.004
lation-0.004
 Theodore-0.004
late-0.004
Tokenber
Token ID527
Feature activation+4.44e-01

Pos logit contributions
cius+0.039
unct+0.035
lation+0.034
late+0.033
 Theodore+0.032
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.021
DER-0.020
 gib-0.020
Token Bar
Token ID2409
Feature activation+4.52e-02

Pos logit contributions
 Palest+0.263
ggle+0.255
adium+0.249
 gib+0.241
DER+0.239
Neg logit contributions
cius-0.344
unct-0.299
lation-0.287
late-0.276
 Theodore-0.272
Tokenons
Token ID684
Feature activation+8.20e-03

Pos logit contributions
 Palest+0.030
ggle+0.029
adium+0.029
 gib+0.028
DER+0.028
Neg logit contributions
cius-0.031
unct-0.027
lation-0.026
late-0.025
 Theodore-0.024
Token of
Token ID286
Feature activation-1.27e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.005
 Theodore-0.005
Token the
Token ID262
Feature activation+2.05e-03

Pos logit contributions
cius+0.009
unct+0.007
lation+0.007
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.009
ggle-0.008
adium-0.008
 gib-0.008
DER-0.008
Token late
Token ID2739
Feature activation+2.23e-02

Pos logit contributions
 Palest+0.001
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.001
unct-0.001
lation-0.001
late-0.001
 Theodore-0.001
Token {
Token ID1391
Feature activation+7.67e-02

Pos logit contributions
cius+0.050
unct+0.042
lation+0.040
late+0.038
 Theodore+0.037
Neg logit contributions
 Palest-0.058
ggle-0.057
adium-0.056
 gib-0.054
DER-0.054
Token turn
Token ID1210
Feature activation+6.25e-03

Pos logit contributions
 Palest+0.051
ggle+0.050
adium+0.049
 gib+0.047
DER+0.047
Neg logit contributions
cius-0.054
unct-0.046
lation-0.044
late-0.042
 Theodore-0.042
Token :
Token ID1058
Feature activation-1.34e-01

Pos logit contributions
 Palest+0.005
ggle+0.004
adium+0.004
 gib+0.004
DER+0.004
Neg logit contributions
cius-0.004
unct-0.003
lation-0.003
late-0.003
 Theodore-0.003
Token self
Token ID2116
Feature activation+1.06e-01

Pos logit contributions
cius+0.094
unct+0.081
lation+0.077
late+0.074
 Theodore+0.074
Neg logit contributions
 Palest-0.089
ggle-0.086
adium-0.086
 gib-0.082
DER-0.082
Token.
Token ID764
Feature activation-1.07e-01

Pos logit contributions
 Palest+0.088
ggle+0.086
adium+0.086
 gib+0.083
DER+0.083
Neg logit contributions
cius-0.056
unct-0.045
lation-0.043
late-0.040
 Theodore-0.040
Tokenclone
Token ID21018
Feature activation+4.41e-01

Pos logit contributions
cius+0.080
unct+0.069
lation+0.067
late+0.064
 Theodore+0.064
Neg logit contributions
 Palest-0.066
ggle-0.064
adium-0.063
 gib-0.061
DER-0.060
Token (),
Token ID29994
Feature activation-7.50e-02

Pos logit contributions
 Palest+0.325
ggle+0.317
adium+0.314
 gib+0.304
DER+0.302
Neg logit contributions
cius-0.277
unct-0.233
lation-0.222
late-0.210
 Theodore-0.209
Token pieces
Token ID5207
Feature activation+2.26e-01

Pos logit contributions
cius+0.058
unct+0.050
lation+0.048
late+0.047
 Theodore+0.046
Neg logit contributions
 Palest-0.045
ggle-0.043
adium-0.043
 gib-0.041
DER-0.041
Token :
Token ID1058
Feature activation-1.57e-01

Pos logit contributions
 Palest+0.193
ggle+0.188
adium+0.187
 gib+0.182
DER+0.181
Neg logit contributions
cius-0.116
unct-0.093
lation-0.087
 Theodore-0.081
late-0.081
Token self
Token ID2116
Feature activation+8.15e-02

Pos logit contributions
cius+0.111
unct+0.095
lation+0.091
late+0.088
 Theodore+0.087
Neg logit contributions
 Palest-0.104
ggle-0.101
adium-0.100
 gib-0.096
DER-0.096
Token.
Token ID764
Feature activation-9.95e-02

Pos logit contributions
 Palest+0.064
ggle+0.063
adium+0.063
 gib+0.061
verson+0.061
Neg logit contributions
cius-0.046
unct-0.038
lation-0.036
 Theodore-0.034
late-0.033
Token premiums
Token ID21884
Feature activation-1.48e-01

Pos logit contributions
cius+0.009
unct+0.008
lation+0.008
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.009
ggle-0.009
adium-0.009
 gib-0.008
DER-0.008
Token,
Token ID11
Feature activation-4.51e-03

Pos logit contributions
cius+0.105
unct+0.090
lation+0.087
late+0.083
 Theodore+0.082
Neg logit contributions
 Palest-0.097
ggle-0.094
adium-0.093
 gib-0.089
DER-0.089
Token doubling
Token ID26862
Feature activation-9.55e-02

Pos logit contributions
cius+0.003
unct+0.003
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.003
ggle-0.003
adium-0.003
 gib-0.003
DER-0.003
Token of
Token ID286
Feature activation+2.76e-02

Pos logit contributions
cius+0.071
unct+0.061
lation+0.059
late+0.056
 Theodore+0.056
Neg logit contributions
 Palest-0.060
ggle-0.058
adium-0.057
 gib-0.055
DER-0.055
Token deduct
Token ID18777
Feature activation-6.15e-02

Pos logit contributions
 Palest+0.018
ggle+0.018
adium+0.018
 gib+0.017
DER+0.017
Neg logit contributions
cius-0.019
unct-0.017
lation-0.016
late-0.015
 Theodore-0.015
Tokenibles
Token ID18764
Feature activation+4.40e-01

Pos logit contributions
cius+0.072
unct+0.066
lation+0.065
late+0.063
 Theodore+0.062
Neg logit contributions
 Palest-0.012
ggle-0.011
adium-0.010
 gib-0.009
DER-0.009
Token,
Token ID11
Feature activation-3.85e-03

Pos logit contributions
 Palest+0.281
ggle+0.273
adium+0.270
 gib+0.260
DER+0.258
Neg logit contributions
cius-0.321
unct-0.277
lation-0.266
late-0.255
 Theodore-0.253
Token and
Token ID290
Feature activation-2.86e-02

Pos logit contributions
cius+0.003
unct+0.002
lation+0.002
late+0.002
 Theodore+0.002
Neg logit contributions
 Palest-0.002
ggle-0.002
adium-0.002
 gib-0.002
DER-0.002
Token narrowing
Token ID46426
Feature activation-9.49e-02

Pos logit contributions
cius+0.020
unct+0.018
lation+0.017
late+0.016
 Theodore+0.016
Neg logit contributions
 Palest-0.019
ggle-0.018
adium-0.018
 gib-0.017
DER-0.017
Token provider
Token ID10131
Feature activation-3.41e-02

Pos logit contributions
cius+0.070
unct+0.060
lation+0.058
late+0.056
 Theodore+0.055
Neg logit contributions
 Palest-0.060
ggle-0.058
adium-0.057
 gib-0.055
DER-0.055
Token networks
Token ID7686
Feature activation-2.87e-02

Pos logit contributions
cius+0.025
unct+0.022
lation+0.021
late+0.020
 Theodore+0.020
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.021
 gib-0.020
DER-0.020
Token055
Token ID47838
Feature activation+6.06e-02

Pos logit contributions
 Palest+0.009
ggle+0.008
adium+0.008
 gib+0.008
DER+0.008
Neg logit contributions
cius-0.010
unct-0.009
lation-0.009
late-0.008
 Theodore-0.008
Token complaints
Token ID9687
Feature activation-1.09e-01

Pos logit contributions
 Palest+0.043
ggle+0.042
adium+0.042
 gib+0.040
DER+0.040
Neg logit contributions
cius-0.040
unct-0.034
lation-0.032
late-0.031
 Theodore-0.031
Token filed
Token ID5717
Feature activation+2.91e-02

Pos logit contributions
cius+0.078
unct+0.067
lation+0.065
late+0.062
 Theodore+0.062
Neg logit contributions
 Palest-0.070
ggle-0.069
adium-0.068
 gib-0.065
DER-0.065
Token against
Token ID1028
Feature activation-1.38e-01

Pos logit contributions
 Palest+0.020
ggle+0.019
adium+0.019
 gib+0.018
DER+0.018
Neg logit contributions
cius-0.020
unct-0.017
lation-0.016
late-0.016
 Theodore-0.015
Token Wells
Token ID18292
Feature activation-1.17e-01

Pos logit contributions
cius+0.106
unct+0.092
lation+0.088
late+0.085
 Theodore+0.084
Neg logit contributions
 Palest-0.084
ggle-0.081
adium-0.080
 gib-0.077
DER-0.076
Token Fargo
Token ID28125
Feature activation+4.38e-01

Pos logit contributions
cius+0.132
unct+0.120
lation+0.117
late+0.115
 Theodore+0.114
Neg logit contributions
 Palest-0.029
ggle-0.027
adium-0.026
 gib-0.023
DER-0.022
Token
Token ID960
Feature activation+2.08e-01

Pos logit contributions
 Palest+0.280
ggle+0.271
adium+0.269
 gib+0.259
DER+0.257
Neg logit contributions
cius-0.320
unct-0.276
lation-0.265
late-0.253
 Theodore-0.252
Tokenwhich
Token ID4758
Feature activation+4.23e-06

Pos logit contributions
 Palest+0.143
ggle+0.138
adium+0.137
 gib+0.132
DER+0.130
Neg logit contributions
cius-0.142
unct-0.121
lation-0.116
late-0.112
 Theodore-0.110
Token is
Token ID318
Feature activation+6.78e-02

Feature not active on prev token;
no predictions were affected.
Token accused
Token ID5371
Feature activation+1.57e-01

Pos logit contributions
 Palest+0.045
ggle+0.043
adium+0.043
 gib+0.041
DER+0.041
Neg logit contributions
cius-0.048
unct-0.041
lation-0.039
late-0.038
 Theodore-0.038
Token of
Token ID286
Feature activation+3.26e-02

Pos logit contributions
 Palest+0.097
ggle+0.094
adium+0.093
 gib+0.090
DER+0.089
Neg logit contributions
cius-0.118
unct-0.102
lation-0.098
late-0.094
 Theodore-0.093
Token using
Token ID1262
Feature activation+1.59e-02

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.005
DER-0.005
Token prostitutes
Token ID32159
Feature activation-1.40e-01

Pos logit contributions
 Palest+0.010
ggle+0.010
adium+0.010
DER+0.010
verson+0.010
Neg logit contributions
cius-0.011
unct-0.010
lation-0.009
late-0.009
 Theodore-0.009
Token and
Token ID290
Feature activation-6.23e-03

Pos logit contributions
cius+0.103
unct+0.089
lation+0.086
late+0.082
 Theodore+0.082
Neg logit contributions
 Palest-0.088
ggle-0.085
adium-0.084
 gib-0.081
DER-0.080
Token possessing
Token ID25566
Feature activation+5.88e-02

Pos logit contributions
cius+0.005
unct+0.004
lation+0.004
 Theodore+0.004
late+0.004
Neg logit contributions
 Palest-0.004
ggle-0.004
adium-0.004
DER-0.004
verson-0.004
Token B
Token ID347
Feature activation-1.15e-02

Pos logit contributions
 Palest+0.038
ggle+0.037
adium+0.037
DER+0.035
verson+0.035
Neg logit contributions
cius-0.042
unct-0.036
lation-0.035
late-0.033
 Theodore-0.033
Tokenibles
Token ID18764
Feature activation+4.38e-01

Pos logit contributions
cius+0.014
unct+0.012
lation+0.012
late+0.012
 Theodore+0.012
Neg logit contributions
 Palest-0.002
ggle-0.002
adium-0.002
 gib-0.002
verson-0.002
Token.
Token ID13
Feature activation+2.35e-03

Pos logit contributions
 Palest+0.273
ggle+0.263
adium+0.261
 gib+0.252
DER+0.249
Neg logit contributions
cius-0.326
unct-0.283
lation-0.271
late-0.259
 Theodore-0.258
Token
Token ID198
Feature activation+7.90e-03

Pos logit contributions
 Palest+0.002
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.002
unct-0.001
lation-0.001
late-0.001
 Theodore-0.001
Token
Token ID198
Feature activation+1.14e-02

Pos logit contributions
 Palest+0.006
ggle+0.005
adium+0.005
 gib+0.005
verson+0.005
Neg logit contributions
cius-0.005
unct-0.005
lation-0.004
late-0.004
 Theodore-0.004
TokenNorth
Token ID14157
Feature activation+1.44e-01

Pos logit contributions
 Palest+0.008
ggle+0.008
adium+0.008
 gib+0.008
verson+0.007
Neg logit contributions
cius-0.008
unct-0.006
lation-0.006
late-0.006
 Theodore-0.006
Token Koreans
Token ID25999
Feature activation-6.98e-03

Pos logit contributions
 Palest+0.099
ggle+0.096
adium+0.095
 gib+0.092
DER+0.091
Neg logit contributions
cius-0.098
unct-0.084
lation-0.080
late-0.077
 Theodore-0.076
Token originally
Token ID6198
Feature activation+7.42e-02

Pos logit contributions
cius+0.060
unct+0.052
lation+0.050
late+0.048
 Theodore+0.047
Neg logit contributions
 Palest-0.053
ggle-0.052
adium-0.051
 gib-0.049
DER-0.049
Token headlined
Token ID46958
Feature activation+1.05e-01

Pos logit contributions
 Palest+0.057
ggle+0.056
adium+0.055
 gib+0.053
DER+0.053
Neg logit contributions
cius-0.045
unct-0.037
lation-0.035
late-0.033
 Theodore-0.033
Token "
Token ID366
Feature activation-9.44e-02

Pos logit contributions
 Palest+0.068
ggle+0.066
adium+0.066
 gib+0.063
DER+0.063
Neg logit contributions
cius-0.075
unct-0.064
lation-0.062
late-0.059
 Theodore-0.059
TokenInt
Token ID5317
Feature activation-3.22e-02

Pos logit contributions
cius+0.063
unct+0.053
lation+0.051
late+0.049
 Theodore+0.048
Neg logit contributions
 Palest-0.066
ggle-0.065
adium-0.064
 gib-0.062
verson-0.061
Tokenang
Token ID648
Feature activation+1.89e-02

Pos logit contributions
cius+0.024
unct+0.021
lation+0.020
late+0.019
 Theodore+0.019
Neg logit contributions
 Palest-0.020
ggle-0.020
adium-0.019
 gib-0.019
DER-0.019
Tokenibles
Token ID18764
Feature activation+4.34e-01

Pos logit contributions
 Palest+0.003
ggle+0.003
adium+0.003
 gib+0.002
DER+0.002
Neg logit contributions
cius-0.022
unct-0.021
lation-0.020
late-0.020
 Theodore-0.020
Token have
Token ID423
Feature activation-1.08e-01

Pos logit contributions
 Palest+0.277
ggle+0.269
adium+0.266
 gib+0.256
DER+0.254
Neg logit contributions
cius-0.317
unct-0.273
lation-0.262
late-0.251
 Theodore-0.250
Token helped
Token ID4193
Feature activation-2.28e-02

Pos logit contributions
cius+0.073
unct+0.062
lation+0.059
late+0.057
 Theodore+0.056
Neg logit contributions
 Palest-0.075
ggle-0.072
adium-0.072
 gib-0.069
DER-0.069
Token Patriots
Token ID13104
Feature activation-1.62e-02

Pos logit contributions
cius+0.015
unct+0.013
lation+0.013
late+0.012
 Theodore+0.012
Neg logit contributions
 Palest-0.016
ggle-0.015
adium-0.015
 gib-0.015
DER-0.014
Token'
Token ID6
Feature activation-8.12e-02

Pos logit contributions
cius+0.012
unct+0.010
lation+0.010
late+0.009
 Theodore+0.009
Neg logit contributions
 Palest-0.011
ggle-0.010
adium-0.010
 gib-0.010
DER-0.010
Token Malcolm
Token ID20002
Feature activation+2.56e-01

Pos logit contributions
cius+0.057
unct+0.049
lation+0.047
late+0.045
 Theodore+0.045
Neg logit contributions
 Palest-0.054
ggle-0.052
adium-0.052
 gib-0.050
DER-0.049
Token slap
Token ID23905
Feature activation-1.24e-02

Pos logit contributions
cius+0.074
unct+0.063
lation+0.061
late+0.058
 Theodore+0.058
Neg logit contributions
 Palest-0.065
ggle-0.063
adium-0.062
 gib-0.060
DER-0.059
Tokendown
Token ID2902
Feature activation+2.47e-01

Pos logit contributions
cius+0.009
unct+0.007
lation+0.007
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.008
ggle-0.008
adium-0.008
 gib-0.008
DER-0.008
Token against
Token ID1028
Feature activation-1.25e-01

Pos logit contributions
 Palest+0.166
ggle+0.161
adium+0.160
 gib+0.154
DER+0.153
Neg logit contributions
cius-0.172
unct-0.147
lation-0.141
late-0.135
 Theodore-0.134
Token the
Token ID262
Feature activation+3.06e-02

Pos logit contributions
cius+0.086
unct+0.073
lation+0.070
late+0.067
 Theodore+0.066
Neg logit contributions
 Palest-0.085
ggle-0.083
adium-0.082
 gib-0.079
DER-0.079
Token conf
Token ID1013
Feature activation+3.09e-02

Pos logit contributions
 Palest+0.021
ggle+0.020
adium+0.020
 gib+0.019
DER+0.019
Neg logit contributions
cius-0.021
unct-0.018
lation-0.017
late-0.017
 Theodore-0.016
Tokenlation
Token ID7592
Feature activation-5.28e-01

Pos logit contributions
 Palest+0.025
ggle+0.024
adium+0.024
 gib+0.023
verson+0.023
Neg logit contributions
cius-0.017
unct-0.014
lation-0.013
 Theodore-0.013
late-0.013
Token of
Token ID286
Feature activation+4.53e-02

Pos logit contributions
cius+0.382
unct+0.328
lation+0.315
late+0.302
 Theodore+0.300
Neg logit contributions
 Palest-0.341
ggle-0.330
adium-0.327
 gib-0.315
DER-0.312
Token sovereign
Token ID18901
Feature activation-1.25e-01

Pos logit contributions
 Palest+0.028
ggle+0.028
adium+0.027
 gib+0.026
DER+0.026
Neg logit contributions
cius-0.033
unct-0.029
lation-0.028
late-0.027
 Theodore-0.027
Token Israel
Token ID2692
Feature activation-5.58e-02

Pos logit contributions
cius+0.094
unct+0.081
lation+0.079
 Theodore+0.076
late+0.075
Neg logit contributions
 Palest-0.075
ggle-0.075
adium-0.074
 gib-0.070
DER-0.070
Token with
Token ID351
Feature activation-5.72e-03

Pos logit contributions
cius+0.038
unct+0.032
lation+0.031
late+0.029
 Theodore+0.029
Neg logit contributions
 Palest-0.039
ggle-0.038
adium-0.037
 gib-0.036
DER-0.036
Token the
Token ID262
Feature activation+4.30e-02

Pos logit contributions
cius+0.004
unct+0.004
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.004
ggle-0.004
adium-0.004
 gib-0.003
DER-0.003
Token musical
Token ID10530
Feature activation+4.27e-02

Pos logit contributions
 Palest+0.132
ggle+0.128
adium+0.126
 gib+0.122
DER+0.121
Neg logit contributions
cius-0.151
unct-0.130
lation-0.125
late-0.120
 Theodore-0.119
Token accents
Token ID39271
Feature activation+1.23e-01

Pos logit contributions
 Palest+0.026
ggle+0.025
adium+0.025
 gib+0.024
DER+0.023
Neg logit contributions
cius-0.033
unct-0.028
lation-0.027
late-0.026
 Theodore-0.026
Token playing
Token ID2712
Feature activation-3.67e-02

Pos logit contributions
 Palest+0.080
ggle+0.078
adium+0.077
 gib+0.074
DER+0.074
Neg logit contributions
cius-0.088
unct-0.076
lation-0.073
late-0.070
 Theodore-0.069
Token in
Token ID287
Feature activation-3.01e-02

Pos logit contributions
cius+0.026
unct+0.022
lation+0.021
late+0.020
 Theodore+0.020
Neg logit contributions
 Palest-0.025
ggle-0.024
adium-0.024
 gib-0.023
DER-0.023
Token the
Token ID262
Feature activation-1.07e-02

Pos logit contributions
cius+0.022
unct+0.018
lation+0.018
late+0.017
 Theodore+0.017
Neg logit contributions
 Palest-0.020
ggle-0.019
adium-0.019
 gib-0.018
DER-0.018
Token background
Token ID4469
Feature activation-4.89e-01

Pos logit contributions
cius+0.004
unct+0.002
lation+0.002
late+0.002
 Theodore+0.002
Neg logit contributions
 Palest-0.011
ggle-0.011
adium-0.011
 gib-0.011
DER-0.011
Token,
Token ID11
Feature activation-1.87e-02

Pos logit contributions
cius+0.353
unct+0.304
lation+0.292
late+0.280
 Theodore+0.278
Neg logit contributions
 Palest-0.316
ggle-0.306
adium-0.304
 gib-0.292
DER-0.290
Token Survivor
Token ID23740
Feature activation+2.06e-01

Pos logit contributions
cius+0.013
unct+0.012
lation+0.011
late+0.011
 Theodore+0.011
Neg logit contributions
 Palest-0.012
ggle-0.012
adium-0.012
 gib-0.011
DER-0.011
Token memor
Token ID16181
Feature activation+1.33e-01

Pos logit contributions
 Palest+0.131
ggle+0.127
adium+0.126
 gib+0.121
DER+0.120
Neg logit contributions
cius-0.151
unct-0.130
lation-0.125
late-0.120
 Theodore-0.119
Tokenabilia
Token ID48249
Feature activation+2.24e-02

Pos logit contributions
 Palest+0.086
ggle+0.083
adium+0.082
 gib+0.078
DER+0.078
Neg logit contributions
cius-0.097
unct-0.083
lation-0.080
late-0.077
 Theodore-0.076
Token throughout
Token ID3690
Feature activation-5.34e-02

Pos logit contributions
 Palest+0.015
ggle+0.014
adium+0.014
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.016
unct-0.014
lation-0.013
late-0.013
 Theodore-0.013
Token plant
Token ID4618
Feature activation-1.56e-01

Pos logit contributions
cius+0.014
unct+0.011
lation+0.010
late+0.010
 Theodore+0.009
Neg logit contributions
 Palest-0.025
ggle-0.024
adium-0.024
DER-0.023
verson-0.023
Tokenaris
Token ID20066
Feature activation+4.18e-02

Pos logit contributions
cius+0.122
unct+0.107
lation+0.102
late+0.099
 Theodore+0.097
Neg logit contributions
 Palest-0.093
ggle-0.088
adium-0.087
 gib-0.085
DER-0.083
Token,"
Token ID553
Feature activation+7.95e-02

Pos logit contributions
 Palest+0.026
ggle+0.025
adium+0.025
 gib+0.024
DER+0.024
Neg logit contributions
cius-0.031
unct-0.027
lation-0.026
late-0.025
 Theodore-0.025
Token "
Token ID366
Feature activation-2.72e-02

Pos logit contributions
 Palest+0.056
ggle+0.055
adium+0.053
 gib+0.052
verson+0.051
Neg logit contributions
cius-0.053
unct-0.045
lation-0.043
late-0.042
 Theodore-0.041
TokenP
Token ID47
Feature activation+1.09e-01

Pos logit contributions
cius+0.020
unct+0.017
lation+0.016
late+0.016
 Theodore+0.016
Neg logit contributions
 Palest-0.018
ggle-0.017
adium-0.017
 gib-0.016
verson-0.016
Tokenunct
Token ID16260
Feature activation-4.83e-01

Pos logit contributions
 Palest+0.142
ggle+0.138
adium+0.137
 gib+0.136
DER+0.134
Neg logit contributions
cius-0.009
unct-0.000
lation+0.005
late+0.007
 Theodore+0.009
Tokenate
Token ID378
Feature activation-5.08e-02

Pos logit contributions
cius+0.311
unct+0.270
lation+0.254
late+0.247
 Theodore+0.237
Neg logit contributions
 Palest-0.358
ggle-0.337
adium-0.331
 gib-0.329
DER-0.323
Token ker
Token ID41927
Feature activation+1.21e-01

Pos logit contributions
cius+0.043
unct+0.039
lation+0.037
late+0.036
 Theodore+0.036
Neg logit contributions
 Palest-0.026
ggle-0.025
adium-0.025
DER-0.023
 gib-0.023
Tokenat
Token ID265
Feature activation-1.10e-01

Pos logit contributions
 Palest+0.097
ggle+0.091
adium+0.090
 gib+0.089
DER+0.087
Neg logit contributions
cius-0.071
unct-0.060
lation-0.058
late-0.056
 Theodore-0.053
Tokenoder
Token ID12342
Feature activation-5.08e-02

Pos logit contributions
cius+0.077
unct+0.066
lation+0.063
late+0.061
 Theodore+0.060
Neg logit contributions
 Palest-0.076
ggle-0.072
adium-0.071
 gib-0.069
verson-0.068
Tokenma
Token ID2611
Feature activation-7.51e-02

Pos logit contributions
cius+0.031
unct+0.025
lation+0.024
late+0.023
 Theodore+0.022
Neg logit contributions
 Palest-0.040
ggle-0.038
adium-0.037
 gib-0.037
DER-0.036
Tokenma
Token ID2611
Feature activation-7.51e-02

Pos logit contributions
cius+0.031
unct+0.025
lation+0.024
late+0.023
 Theodore+0.022
Neg logit contributions
 Palest-0.040
ggle-0.038
adium-0.037
 gib-0.037
DER-0.036
Token,"
Token ID553
Feature activation+5.28e-02

Pos logit contributions
cius+0.055
unct+0.048
lation+0.046
 Theodore+0.045
late+0.045
Neg logit contributions
 Palest-0.048
ggle-0.046
adium-0.046
 gib-0.043
DER-0.043
Token and
Token ID290
Feature activation+2.67e-03

Pos logit contributions
 Palest+0.036
ggle+0.035
adium+0.034
 gib+0.033
verson+0.033
Neg logit contributions
cius-0.036
unct-0.031
lation-0.030
late-0.029
 Theodore-0.029
Token "
Token ID366
Feature activation-2.51e-02

Pos logit contributions
 Palest+0.002
ggle+0.002
adium+0.002
DER+0.002
verson+0.002
Neg logit contributions
cius-0.002
unct-0.002
lation-0.001
late-0.001
 Theodore-0.001
TokenP
Token ID47
Feature activation+1.20e-01

Pos logit contributions
cius+0.018
unct+0.016
lation+0.015
late+0.015
 Theodore+0.015
Neg logit contributions
 Palest-0.016
ggle-0.015
adium-0.015
 gib-0.015
verson-0.014
Tokenunct
Token ID16260
Feature activation-4.83e-01

Pos logit contributions
 Palest+0.156
ggle+0.152
adium+0.151
 gib+0.150
DER+0.148
Neg logit contributions
cius-0.010
unct-0.000
lation+0.005
late+0.008
 Theodore+0.010
Tokenate
Token ID378
Feature activation-7.69e-02

Pos logit contributions
cius+0.310
unct+0.268
lation+0.254
late+0.247
 Theodore+0.236
Neg logit contributions
 Palest-0.359
ggle-0.337
adium-0.332
 gib-0.329
verson-0.325
Token por
Token ID16964
Feature activation+7.76e-02

Pos logit contributions
cius+0.064
unct+0.058
lation+0.055
late+0.054
 Theodore+0.053
Neg logit contributions
 Palest-0.041
ggle-0.039
adium-0.039
DER-0.036
 gib-0.036
Tokenoker
Token ID11020
Feature activation-1.17e-01

Pos logit contributions
 Palest+0.052
ggle+0.049
adium+0.049
 gib+0.047
DER+0.047
Neg logit contributions
cius-0.055
unct-0.047
lation-0.046
late-0.044
 Theodore-0.043
Tokenat
Token ID265
Feature activation-7.85e-02

Pos logit contributions
cius+0.069
unct+0.058
lation+0.056
late+0.054
 Theodore+0.051
Neg logit contributions
 Palest-0.093
ggle-0.088
 gib-0.086
adium-0.086
DER-0.084
Tokenosis
Token ID5958
Feature activation+2.13e-01

Pos logit contributions
cius+0.080
unct+0.072
lation+0.070
late+0.068
 Theodore+0.067
Neg logit contributions
 Palest-0.029
ggle-0.026
adium-0.025
 gib-0.025
DER-0.024
Token plant
Token ID4618
Feature activation-1.54e-01

Pos logit contributions
cius+0.015
unct+0.013
lation+0.013
late+0.012
 Theodore+0.012
Neg logit contributions
 Palest-0.014
ggle-0.013
adium-0.013
 gib-0.013
DER-0.013
Tokenaris
Token ID20066
Feature activation+5.06e-02

Pos logit contributions
cius+0.106
unct+0.090
lation+0.086
late+0.082
 Theodore+0.082
Neg logit contributions
 Palest-0.105
ggle-0.102
adium-0.101
 gib-0.097
DER-0.096
Token,"
Token ID553
Feature activation+6.16e-02

Pos logit contributions
 Palest+0.030
ggle+0.029
adium+0.028
 gib+0.027
DER+0.027
Neg logit contributions
cius-0.040
unct-0.035
lation-0.033
late-0.032
 Theodore-0.032
Token "
Token ID366
Feature activation-2.86e-02

Pos logit contributions
 Palest+0.040
ggle+0.039
adium+0.038
 gib+0.037
verson+0.037
Neg logit contributions
cius-0.044
unct-0.038
lation-0.037
late-0.035
 Theodore-0.035
TokenP
Token ID47
Feature activation+1.20e-01

Pos logit contributions
cius+0.021
unct+0.018
lation+0.017
late+0.017
 Theodore+0.017
Neg logit contributions
 Palest-0.018
ggle-0.018
adium-0.018
 gib-0.017
DER-0.017
Tokenunct
Token ID16260
Feature activation-4.79e-01

Pos logit contributions
 Palest+0.060
ggle+0.058
adium+0.057
 gib+0.054
DER+0.054
Neg logit contributions
cius-0.105
unct-0.093
lation-0.090
late-0.087
 Theodore-0.086
Tokenate
Token ID378
Feature activation-4.36e-02

Pos logit contributions
cius+0.361
unct+0.314
lation+0.301
late+0.290
 Theodore+0.287
Neg logit contributions
 Palest-0.294
ggle-0.284
adium-0.281
 gib-0.271
DER-0.269
Token ker
Token ID41927
Feature activation+1.67e-01

Pos logit contributions
cius+0.036
unct+0.031
lation+0.030
late+0.029
 Theodore+0.029
Neg logit contributions
 Palest-0.024
ggle-0.023
adium-0.023
 gib-0.022
DER-0.022
Tokenat
Token ID265
Feature activation-9.84e-02

Pos logit contributions
 Palest+0.121
ggle+0.118
adium+0.117
 gib+0.113
DER+0.112
Neg logit contributions
cius-0.107
unct-0.091
lation-0.087
late-0.083
 Theodore-0.082
Tokenoder
Token ID12342
Feature activation-2.64e-02

Pos logit contributions
cius+0.082
unct+0.072
lation+0.070
late+0.067
 Theodore+0.067
Neg logit contributions
 Palest-0.052
ggle-0.050
adium-0.050
 gib-0.047
DER-0.047
Tokenma
Token ID2611
Feature activation-7.84e-02

Pos logit contributions
cius+0.017
unct+0.014
lation+0.013
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.019
ggle-0.019
adium-0.019
 gib-0.018
DER-0.018
Tokenma
Token ID2611
Feature activation-7.84e-02

Pos logit contributions
cius+0.017
unct+0.014
lation+0.013
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.019
ggle-0.019
adium-0.019
 gib-0.018
DER-0.018
Token,"
Token ID553
Feature activation+5.06e-02

Pos logit contributions
cius+0.058
unct+0.050
lation+0.048
late+0.046
 Theodore+0.046
Neg logit contributions
 Palest-0.049
ggle-0.048
adium-0.047
 gib-0.045
DER-0.045
Token and
Token ID290
Feature activation+8.02e-03

Pos logit contributions
 Palest+0.033
ggle+0.032
adium+0.031
 gib+0.030
DER+0.030
Neg logit contributions
cius-0.037
unct-0.031
lation-0.030
late-0.029
 Theodore-0.029
Token "
Token ID366
Feature activation-1.89e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.004
 Theodore-0.004
TokenP
Token ID47
Feature activation+1.43e-01

Pos logit contributions
cius+0.014
unct+0.012
lation+0.011
late+0.011
 Theodore+0.011
Neg logit contributions
 Palest-0.012
ggle-0.012
adium-0.012
 gib-0.011
DER-0.011
Tokenunct
Token ID16260
Feature activation-4.74e-01

Pos logit contributions
 Palest+0.114
ggle+0.111
adium+0.110
 gib+0.107
DER+0.106
Neg logit contributions
cius-0.082
unct-0.068
lation-0.064
late-0.060
 Theodore-0.059
Tokenate
Token ID378
Feature activation-6.67e-02

Pos logit contributions
cius+0.329
unct+0.283
lation+0.270
late+0.259
 Theodore+0.256
Neg logit contributions
 Palest-0.319
ggle-0.309
adium-0.306
 gib-0.296
DER-0.294
Token por
Token ID16964
Feature activation+1.10e-01

Pos logit contributions
cius+0.056
unct+0.049
lation+0.047
late+0.046
 Theodore+0.045
Neg logit contributions
 Palest-0.036
ggle-0.034
adium-0.034
 gib-0.032
DER-0.032
Tokenoker
Token ID11020
Feature activation-9.62e-02

Pos logit contributions
 Palest+0.064
ggle+0.062
adium+0.061
 gib+0.059
DER+0.058
Neg logit contributions
cius-0.087
unct-0.076
lation-0.073
late-0.070
 Theodore-0.070
Tokenat
Token ID265
Feature activation-5.36e-02

Pos logit contributions
cius+0.064
unct+0.055
lation+0.052
late+0.050
 Theodore+0.049
Neg logit contributions
 Palest-0.067
ggle-0.065
adium-0.065
 gib-0.063
DER-0.062
Tokenosis
Token ID5958
Feature activation+2.32e-01

Pos logit contributions
cius+0.054
unct+0.049
lation+0.048
late+0.046
 Theodore+0.046
Neg logit contributions
 Palest-0.019
ggle-0.018
adium-0.018
 gib-0.016
DER-0.016
Token own
Token ID898
Feature activation-1.24e-01

Pos logit contributions
cius+0.004
unct+0.003
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.004
ggle-0.004
adium-0.004
 gib-0.004
DER-0.004
Token political
Token ID1964
Feature activation-2.49e-02

Pos logit contributions
cius+0.091
unct+0.079
lation+0.075
 Theodore+0.072
late+0.072
Neg logit contributions
 Palest-0.079
ggle-0.077
adium-0.076
DER-0.072
 gib-0.072
Token baggage
Token ID30466
Feature activation-7.08e-02

Pos logit contributions
cius+0.018
unct+0.015
lation+0.015
 Theodore+0.014
late+0.014
Neg logit contributions
 Palest-0.016
ggle-0.016
adium-0.016
verson-0.015
DER-0.015
Token?
Token ID30
Feature activation-7.29e-02

Pos logit contributions
cius+0.048
unct+0.041
lation+0.040
late+0.038
 Theodore+0.038
Neg logit contributions
 Palest-0.048
ggle-0.047
adium-0.046
 gib-0.045
DER-0.045
Token With
Token ID2080
Feature activation-6.41e-02

Pos logit contributions
cius+0.051
unct+0.044
lation+0.042
late+0.040
 Theodore+0.040
Neg logit contributions
 Palest-0.049
ggle-0.047
adium-0.047
 gib-0.045
DER-0.045
Token background
Token ID4469
Feature activation-4.70e-01

Pos logit contributions
cius+0.044
unct+0.038
lation+0.036
 Theodore+0.035
late+0.035
Neg logit contributions
 Palest-0.043
ggle-0.042
adium-0.042
 gib-0.040
DER-0.040
Token checks
Token ID8794
Feature activation-2.20e-01

Pos logit contributions
cius+0.327
unct+0.279
lation+0.268
late+0.255
 Theodore+0.255
Neg logit contributions
 Palest-0.317
ggle-0.308
adium-0.305
 gib-0.293
DER-0.292
Token and
Token ID290
Feature activation-8.62e-03

Pos logit contributions
cius+0.157
unct+0.135
lation+0.130
late+0.124
 Theodore+0.124
Neg logit contributions
 Palest-0.144
ggle-0.140
adium-0.138
 gib-0.133
DER-0.132
Token confirmation
Token ID12641
Feature activation-6.39e-03

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.006
ggle-0.006
adium-0.005
 gib-0.005
DER-0.005
Token hearings
Token ID18921
Feature activation-8.43e-02

Pos logit contributions
cius+0.005
unct+0.004
lation+0.004
 Theodore+0.004
late+0.004
Neg logit contributions
 Palest-0.004
ggle-0.004
adium-0.004
DER-0.004
 gib-0.004
Token,
Token ID11
Feature activation+1.61e-02

Pos logit contributions
cius+0.061
unct+0.052
lation+0.050
late+0.048
 Theodore+0.048
Neg logit contributions
 Palest-0.054
ggle-0.053
adium-0.052
 gib-0.050
DER-0.050
Token to
Token ID284
Feature activation-1.55e-02

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
 Theodore+0.005
late+0.005
Neg logit contributions
 Palest-0.006
ggle-0.006
adium-0.006
DER-0.005
 gib-0.005
Token the
Token ID262
Feature activation+8.02e-03

Pos logit contributions
cius+0.011
unct+0.009
lation+0.009
late+0.008
 Theodore+0.008
Neg logit contributions
 Palest-0.011
ggle-0.010
adium-0.010
 gib-0.010
DER-0.010
Token mountain
Token ID8598
Feature activation-7.44e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.005
 Theodore-0.005
Token in
Token ID287
Feature activation-4.34e-02

Pos logit contributions
cius+0.055
unct+0.047
lation+0.045
late+0.044
 Theodore+0.043
Neg logit contributions
 Palest-0.047
ggle-0.046
adium-0.045
 gib-0.044
DER-0.043
Token the
Token ID262
Feature activation+2.47e-02

Pos logit contributions
cius+0.034
unct+0.030
lation+0.029
late+0.028
 Theodore+0.028
Neg logit contributions
 Palest-0.025
ggle-0.024
adium-0.024
 gib-0.023
DER-0.023
Token background
Token ID4469
Feature activation-4.70e-01

Pos logit contributions
 Palest+0.019
ggle+0.018
adium+0.018
 gib+0.018
DER+0.018
Neg logit contributions
cius-0.015
unct-0.012
lation-0.012
late-0.011
 Theodore-0.011
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
cius+0.345
unct+0.297
lation+0.287
late+0.275
 Theodore+0.274
Neg logit contributions
 Palest-0.297
ggle-0.288
adium-0.286
 gib-0.273
DER-0.272
Token In
Token ID554
Feature activation-2.21e-05

Pos logit contributions
cius+0.009
unct+0.008
lation+0.008
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.009
ggle-0.009
adium-0.009
 gib-0.009
DER-0.009
Token front
Token ID2166
Feature activation+1.25e-01

Pos logit contributions
cius+0.000
unct+0.000
lation+0.000
late+0.000
 Theodore+0.000
Neg logit contributions
 Palest-0.000
ggle-0.000
adium-0.000
 gib-0.000
DER-0.000
Token of
Token ID286
Feature activation-6.02e-03

Pos logit contributions
 Palest+0.077
ggle+0.074
adium+0.073
 gib+0.071
verson+0.070
Neg logit contributions
cius-0.094
unct-0.081
lation-0.078
late-0.075
 Theodore-0.074
Token it
Token ID340
Feature activation+2.81e-02

Pos logit contributions
cius+0.003
unct+0.003
lation+0.003
 Theodore+0.003
late+0.003
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.004
DER-0.004
Tokenbo
Token ID2127
Feature activation+1.72e-01

Pos logit contributions
 Palest+0.024
ggle+0.023
adium+0.022
 gib+0.021
DER+0.021
Neg logit contributions
cius-0.038
unct-0.033
lation-0.032
late-0.031
 Theodore-0.031
Token also
Token ID635
Feature activation-5.11e-02

Pos logit contributions
 Palest+0.112
ggle+0.109
adium+0.108
 gib+0.104
DER+0.103
Neg logit contributions
cius-0.123
unct-0.105
lation-0.101
late-0.097
 Theodore-0.096
Token had
Token ID550
Feature activation+2.19e-02

Pos logit contributions
cius+0.037
unct+0.032
lation+0.031
 Theodore+0.029
late+0.029
Neg logit contributions
 Palest-0.033
ggle-0.032
adium-0.032
DER-0.030
 gib-0.030
Token a
Token ID257
Feature activation-1.06e-02

Pos logit contributions
 Palest+0.015
ggle+0.015
adium+0.014
 gib+0.014
DER+0.014
Neg logit contributions
cius-0.015
unct-0.013
lation-0.012
 Theodore-0.012
late-0.012
Token soccer
Token ID11783
Feature activation+1.60e-01

Pos logit contributions
cius+0.008
unct+0.007
lation+0.006
 Theodore+0.006
late+0.006
Neg logit contributions
 Palest-0.007
ggle-0.007
adium-0.007
 gib-0.006
DER-0.006
Token background
Token ID4469
Feature activation-4.69e-01

Pos logit contributions
 Palest+0.113
ggle+0.110
adium+0.109
 gib+0.105
DER+0.104
Neg logit contributions
cius-0.106
unct-0.090
lation-0.086
late-0.082
 Theodore-0.081
Token.
Token ID13
Feature activation-2.26e-03

Pos logit contributions
cius+0.341
unct+0.295
lation+0.284
late+0.272
 Theodore+0.270
Neg logit contributions
 Palest-0.299
ggle-0.290
adium-0.287
 gib-0.276
DER-0.274
Token
Token ID198
Feature activation-4.63e-04

Pos logit contributions
cius+0.002
unct+0.001
lation+0.001
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.002
ggle-0.001
adium-0.001
 gib-0.001
DER-0.001
Token
Token ID198
Feature activation+3.32e-04

Pos logit contributions
cius+0.000
unct+0.000
lation+0.000
late+0.000
 Theodore+0.000
Neg logit contributions
 Palest-0.000
ggle-0.000
adium-0.000
 gib-0.000
verson-0.000
Token
Token ID447
Feature activation-5.24e-02

Pos logit contributions
 Palest+0.000
ggle+0.000
adium+0.000
 gib+0.000
verson+0.000
Neg logit contributions
cius-0.000
unct-0.000
lation-0.000
late-0.000
 Theodore-0.000
Token
Token ID250
Feature activation+1.18e-02

Pos logit contributions
cius+0.038
unct+0.033
lation+0.032
late+0.031
 Theodore+0.030
Neg logit contributions
 Palest-0.033
ggle-0.032
adium-0.032
 gib-0.031
DER-0.030
Token the
Token ID262
Feature activation-1.57e-03

Pos logit contributions
cius+0.033
unct+0.028
lation+0.027
late+0.026
 Theodore+0.026
Neg logit contributions
 Palest-0.032
ggle-0.031
adium-0.031
 gib-0.030
verson-0.030
Token visit
Token ID3187
Feature activation-2.04e-02

Pos logit contributions
cius+0.001
unct+0.001
lation+0.001
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.001
ggle-0.001
adium-0.001
 gib-0.001
verson-0.001
Token of
Token ID286
Feature activation-1.86e-02

Pos logit contributions
cius+0.015
unct+0.013
lation+0.013
late+0.012
 Theodore+0.012
Neg logit contributions
 Palest-0.013
ggle-0.012
adium-0.012
 gib-0.012
DER-0.011
Token B
Token ID347
Feature activation-3.57e-02

Pos logit contributions
cius+0.013
unct+0.011
lation+0.011
late+0.010
 Theodore+0.010
Neg logit contributions
 Palest-0.012
ggle-0.012
adium-0.012
 gib-0.011
verson-0.011
Tokenourn
Token ID1798
Feature activation-1.64e-01

Pos logit contributions
cius+0.019
unct+0.016
lation+0.015
late+0.014
 Theodore+0.014
Neg logit contributions
 Palest-0.030
ggle-0.029
adium-0.029
 gib-0.028
DER-0.028
Tokenemouth
Token ID46880
Feature activation-4.65e-01

Pos logit contributions
cius+0.045
unct+0.027
lation+0.022
 Theodore+0.018
late+0.016
Neg logit contributions
 Palest-0.183
adium-0.180
ggle-0.178
 gib-0.174
DER-0.174
Token to
Token ID284
Feature activation-2.82e-03

Pos logit contributions
cius+0.326
unct+0.280
lation+0.270
late+0.259
 Theodore+0.258
Neg logit contributions
 Palest-0.306
ggle-0.297
adium-0.294
 gib-0.284
verson-0.281
Token The
Token ID383
Feature activation-4.27e-02

Pos logit contributions
cius+0.002
unct+0.002
lation+0.002
 Theodore+0.002
late+0.002
Neg logit contributions
 Palest-0.002
ggle-0.002
adium-0.002
 gib-0.002
DER-0.002
Token Hawth
Token ID41457
Feature activation+1.06e-01

Pos logit contributions
cius+0.033
unct+0.028
lation+0.027
late+0.026
 Theodore+0.026
Neg logit contributions
 Palest-0.026
ggle-0.025
adium-0.024
 gib-0.024
verson-0.023
Tokenorns
Token ID19942
Feature activation-3.11e-03

Pos logit contributions
 Palest+0.055
adium+0.053
ggle+0.053
 gib+0.050
DER+0.050
Neg logit contributions
cius-0.090
unct-0.079
lation-0.076
late-0.074
 Theodore-0.074
Token.
Token ID13
Feature activation-2.67e-02

Pos logit contributions
cius+0.002
unct+0.002
lation+0.002
late+0.002
 Theodore+0.002
Neg logit contributions
 Palest-0.002
ggle-0.002
adium-0.002
 gib-0.002
DER-0.002
Token Ambassador
Token ID20656
Feature activation+8.90e-02

Pos logit contributions
cius+0.004
unct+0.004
lation+0.004
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.004
ggle-0.004
adium-0.004
 gib-0.004
DER-0.004
Token Sand
Token ID3837
Feature activation-4.16e-02

Pos logit contributions
 Palest+0.057
ggle+0.055
adium+0.054
 gib+0.052
DER+0.052
Neg logit contributions
cius-0.065
unct-0.056
lation-0.054
late-0.052
 Theodore-0.051
Tokenerson
Token ID882
Feature activation-7.89e-02

Pos logit contributions
cius+0.025
unct+0.021
lation+0.020
late+0.019
 Theodore+0.019
Neg logit contributions
 Palest-0.032
ggle-0.031
adium-0.030
 gib-0.030
DER-0.029
Token ab
Token ID450
Feature activation+3.21e-02

Pos logit contributions
cius+0.056
unct+0.048
lation+0.046
late+0.044
 Theodore+0.044
Neg logit contributions
 Palest-0.052
ggle-0.050
adium-0.050
 gib-0.047
DER-0.047
Tokenet
Token ID316
Feature activation-1.15e-02

Pos logit contributions
 Palest+0.021
ggle+0.020
adium+0.020
 gib+0.019
DER+0.019
Neg logit contributions
cius-0.023
unct-0.020
lation-0.019
late-0.018
 Theodore-0.018
Tokented
Token ID1513
Feature activation-4.61e-01

Pos logit contributions
cius+0.003
unct+0.002
lation+0.002
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.013
ggle-0.013
adium-0.012
 gib-0.012
DER-0.012
Token U
Token ID471
Feature activation+2.31e-02

Pos logit contributions
cius+0.322
unct+0.276
lation+0.264
late+0.253
 Theodore+0.251
Neg logit contributions
 Palest-0.309
ggle-0.300
adium-0.297
 gib-0.286
DER-0.284
Token.
Token ID13
Feature activation-1.88e-02

Pos logit contributions
 Palest+0.015
ggle+0.014
adium+0.014
 gib+0.014
verson+0.014
Neg logit contributions
cius-0.017
unct-0.014
lation-0.014
late-0.013
 Theodore-0.013
TokenS
Token ID50
Feature activation-5.63e-02

Pos logit contributions
cius+0.011
unct+0.009
lation+0.009
late+0.008
 Theodore+0.008
Neg logit contributions
 Palest-0.015
ggle-0.014
adium-0.014
 gib-0.014
verson-0.013
Token.
Token ID13
Feature activation-3.32e-02

Pos logit contributions
cius+0.041
unct+0.035
lation+0.033
late+0.032
 Theodore+0.032
Neg logit contributions
 Palest-0.037
ggle-0.035
adium-0.035
 gib-0.034
DER-0.034
Token interests
Token ID5353
Feature activation-1.15e-01

Pos logit contributions
cius+0.024
unct+0.021
lation+0.020
late+0.019
 Theodore+0.019
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.021
 gib-0.020
DER-0.020
Token dark
Token ID3223
Feature activation+1.26e-01

Pos logit contributions
 Palest+0.024
ggle+0.023
adium+0.023
 gib+0.022
DER+0.022
Neg logit contributions
cius-0.026
unct-0.022
lation-0.021
late-0.021
 Theodore-0.020
Token regions
Token ID7652
Feature activation-1.51e-01

Pos logit contributions
 Palest+0.076
ggle+0.074
adium+0.073
 gib+0.070
DER+0.070
Neg logit contributions
cius-0.097
unct-0.084
lation-0.081
late-0.078
 Theodore-0.077
Token on
Token ID319
Feature activation-6.78e-02

Pos logit contributions
cius+0.107
unct+0.091
lation+0.088
late+0.084
 Theodore+0.083
Neg logit contributions
 Palest-0.101
ggle-0.098
adium-0.097
 gib-0.093
DER-0.093
Token a
Token ID257
Feature activation-3.02e-02

Pos logit contributions
cius+0.048
unct+0.041
lation+0.039
late+0.038
 Theodore+0.037
Neg logit contributions
 Palest-0.045
ggle-0.043
adium-0.043
 gib-0.041
DER-0.041
Token light
Token ID1657
Feature activation+2.43e-01

Pos logit contributions
cius+0.023
unct+0.020
lation+0.019
late+0.018
 Theodore+0.018
Neg logit contributions
 Palest-0.019
ggle-0.018
adium-0.018
 gib-0.017
DER-0.017
Token background
Token ID4469
Feature activation-4.59e-01

Pos logit contributions
 Palest+0.160
ggle+0.156
adium+0.154
 gib+0.149
DER+0.148
Neg logit contributions
cius-0.171
unct-0.147
lation-0.141
late-0.135
 Theodore-0.134
Token gray
Token ID12768
Feature activation+9.71e-02

Pos logit contributions
cius+0.334
unct+0.287
lation+0.276
late+0.264
 Theodore+0.262
Neg logit contributions
 Palest-0.295
ggle-0.286
adium-0.283
 gib-0.272
DER-0.270
Token =
Token ID796
Feature activation+8.75e-02

Pos logit contributions
 Palest+0.058
ggle+0.056
adium+0.056
 gib+0.054
DER+0.053
Neg logit contributions
cius-0.074
unct-0.065
lation-0.062
late-0.060
 Theodore-0.060
Token c
Token ID269
Feature activation+3.22e-02

Pos logit contributions
 Palest+0.054
ggle+0.053
adium+0.052
 gib+0.050
DER+0.050
Neg logit contributions
cius-0.065
unct-0.056
lation-0.054
late-0.052
 Theodore-0.052
Tokenv
Token ID85
Feature activation+5.06e-02

Pos logit contributions
 Palest+0.021
ggle+0.019
adium+0.019
 gib+0.018
DER+0.018
Neg logit contributions
cius-0.024
unct-0.021
lation-0.020
late-0.020
 Theodore-0.019
Token2
Token ID17
Feature activation-4.90e-02

Pos logit contributions
 Palest+0.038
ggle+0.036
adium+0.036
 gib+0.035
verson+0.034
Neg logit contributions
cius-0.032
unct-0.027
lation-0.026
late-0.025
 Theodore-0.024
Token microwave
Token ID27000
Feature activation+1.21e-02

Pos logit contributions
cius+0.029
unct+0.025
lation+0.024
late+0.023
 Theodore+0.023
Neg logit contributions
 Palest-0.024
ggle-0.023
adium-0.023
 gib-0.022
DER-0.022
Token be
Token ID307
Feature activation-3.31e-02

Pos logit contributions
 Palest+0.007
ggle+0.007
adium+0.007
 gib+0.007
DER+0.007
Neg logit contributions
cius-0.009
unct-0.008
lation-0.008
late-0.007
 Theodore-0.007
Tokenep
Token ID538
Feature activation+6.45e-03

Pos logit contributions
cius+0.026
unct+0.023
lation+0.022
late+0.021
 Theodore+0.021
Neg logit contributions
 Palest-0.019
ggle-0.018
adium-0.018
 gib-0.017
DER-0.017
Token in
Token ID287
Feature activation-3.47e-02

Pos logit contributions
 Palest+0.004
ggle+0.004
adium+0.004
 gib+0.004
DER+0.004
Neg logit contributions
cius-0.005
unct-0.004
lation-0.004
late-0.004
 Theodore-0.004
Token the
Token ID262
Feature activation-1.30e-02

Pos logit contributions
cius+0.024
unct+0.020
lation+0.019
late+0.019
 Theodore+0.018
Neg logit contributions
 Palest-0.024
ggle-0.023
adium-0.023
 gib-0.022
DER-0.022
Token background
Token ID4469
Feature activation-4.54e-01

Pos logit contributions
cius+0.005
unct+0.004
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.013
ggle-0.012
adium-0.012
DER-0.012
 gib-0.012
Token as
Token ID355
Feature activation+3.92e-03

Pos logit contributions
cius+0.330
unct+0.284
lation+0.275
late+0.263
 Theodore+0.261
Neg logit contributions
 Palest-0.289
ggle-0.280
adium-0.279
 gib-0.266
DER-0.266
Token he
Token ID339
Feature activation-4.86e-02

Pos logit contributions
 Palest+0.003
ggle+0.003
adium+0.003
 gib+0.003
DER+0.003
Neg logit contributions
cius-0.003
unct-0.002
lation-0.002
late-0.002
 Theodore-0.002
Token squee
Token ID13170
Feature activation+3.37e-02

Pos logit contributions
cius+0.035
unct+0.030
lation+0.029
late+0.028
 Theodore+0.028
Neg logit contributions
 Palest-0.031
ggle-0.030
adium-0.030
DER-0.029
 gib-0.028
Tokenzes
Token ID12271
Feature activation-7.29e-04

Pos logit contributions
 Palest+0.024
adium+0.023
ggle+0.023
DER+0.022
 gib+0.022
Neg logit contributions
cius-0.023
unct-0.019
lation-0.019
late-0.018
 Theodore-0.018
Token in
Token ID287
Feature activation-9.92e-03

Pos logit contributions
cius+0.001
unct+0.000
lation+0.000
late+0.000
 Theodore+0.000
Neg logit contributions
 Palest-0.000
ggle-0.000
adium-0.000
 gib-0.000
DER-0.000
Token and
Token ID290
Feature activation+1.12e-02

Pos logit contributions
cius+0.019
unct+0.016
lation+0.016
late+0.015
 Theodore+0.015
Neg logit contributions
 Palest-0.020
ggle-0.019
adium-0.019
 gib-0.019
DER-0.018
Token flying
Token ID7348
Feature activation-3.18e-02

Pos logit contributions
 Palest+0.007
ggle+0.007
adium+0.007
 gib+0.007
DER+0.007
Neg logit contributions
cius-0.008
unct-0.007
lation-0.007
late-0.006
 Theodore-0.006
Token from
Token ID422
Feature activation-2.47e-02

Pos logit contributions
cius+0.022
unct+0.019
lation+0.018
late+0.018
 Theodore+0.018
Neg logit contributions
 Palest-0.021
ggle-0.020
adium-0.020
verson-0.019
 gib-0.019
Token B
Token ID347
Feature activation-3.07e-02

Pos logit contributions
cius+0.017
unct+0.015
lation+0.014
late+0.014
 Theodore+0.014
Neg logit contributions
 Palest-0.016
ggle-0.016
adium-0.016
 gib-0.015
DER-0.015
Tokenourn
Token ID1798
Feature activation-1.29e-01

Pos logit contributions
cius+0.020
unct+0.017
lation+0.017
late+0.016
 Theodore+0.016
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.021
 gib-0.020
DER-0.020
Tokenemouth
Token ID46880
Feature activation-4.50e-01

Pos logit contributions
cius+0.029
unct+0.016
lation+0.012
 Theodore+0.009
late+0.008
Neg logit contributions
 Palest-0.149
ggle-0.146
adium-0.146
 gib-0.142
DER-0.142
Token on
Token ID319
Feature activation+1.15e-02

Pos logit contributions
cius+0.334
unct+0.290
lation+0.279
late+0.270
 Theodore+0.267
Neg logit contributions
 Palest-0.280
ggle-0.272
adium-0.269
 gib-0.257
verson-0.256
Token December
Token ID3426
Feature activation+3.28e-02

Pos logit contributions
 Palest+0.007
ggle+0.007
adium+0.007
 gib+0.006
verson+0.006
Neg logit contributions
cius-0.009
unct-0.008
lation-0.007
late-0.007
 Theodore-0.007
Token 22
Token ID2534
Feature activation+2.19e-02

Pos logit contributions
 Palest+0.020
ggle+0.019
adium+0.019
 gib+0.018
verson+0.018
Neg logit contributions
cius-0.025
unct-0.022
lation-0.021
late-0.020
 Theodore-0.020
Token.
Token ID13
Feature activation+1.50e-03

Pos logit contributions
 Palest+0.014
ggle+0.013
adium+0.013
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.016
unct-0.014
lation-0.013
late-0.013
 Theodore-0.013
Token
Token ID198
Feature activation+2.47e-02

Pos logit contributions
 Palest+0.001
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.001
unct-0.001
lation-0.001
late-0.001
 Theodore-0.001
Token
Token ID247
Feature activation-5.41e-02

Pos logit contributions
cius+0.030
unct+0.026
lation+0.025
late+0.024
 Theodore+0.024
Neg logit contributions
 Palest-0.027
ggle-0.026
adium-0.026
 gib-0.025
DER-0.025
Tokens
Token ID82
Feature activation-4.34e-02

Pos logit contributions
cius+0.039
unct+0.034
lation+0.032
late+0.031
 Theodore+0.031
Neg logit contributions
 Palest-0.035
ggle-0.034
adium-0.034
 gib-0.032
DER-0.032
Token the
Token ID262
Feature activation-5.90e-02

Pos logit contributions
cius+0.030
unct+0.026
lation+0.025
late+0.024
 Theodore+0.024
Neg logit contributions
 Palest-0.029
ggle-0.028
adium-0.028
 gib-0.027
DER-0.027
Token Sex
Token ID14419
Feature activation-1.34e-01

Pos logit contributions
cius+0.043
unct+0.037
lation+0.036
late+0.035
 Theodore+0.034
Neg logit contributions
 Palest-0.037
ggle-0.036
adium-0.036
 gib-0.034
DER-0.034
Token Pist
Token ID18667
Feature activation-2.37e-01

Pos logit contributions
cius+0.095
unct+0.082
lation+0.079
late+0.075
 Theodore+0.075
Neg logit contributions
 Palest-0.088
ggle-0.085
adium-0.084
 gib-0.081
verson-0.080
Tokenols
Token ID10220
Feature activation-4.49e-01

Pos logit contributions
cius+0.076
unct+0.053
lation+0.045
 Theodore+0.041
��+0.039
Neg logit contributions
 Palest-0.244
ggle-0.244
adium-0.242
verson-0.236
acles-0.236
Token follows
Token ID5679
Feature activation+8.98e-03

Pos logit contributions
cius+0.325
unct+0.280
lation+0.269
late+0.258
 Theodore+0.256
Neg logit contributions
 Palest-0.289
ggle-0.282
adium-0.278
 gib-0.267
DER-0.265
Token.
Token ID13
Feature activation-4.94e-02

Pos logit contributions
 Palest+0.006
ggle+0.006
adium+0.006
 gib+0.006
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.005
 Theodore-0.005
Token
Token ID564
Feature activation+3.01e-02

Pos logit contributions
cius+0.034
unct+0.029
lation+0.028
late+0.027
 Theodore+0.027
Neg logit contributions
 Palest-0.033
ggle-0.033
adium-0.032
 gib-0.031
DER-0.031
Token
Token ID250
Feature activation+2.15e-04

Pos logit contributions
 Palest+0.018
ggle+0.018
adium+0.018
 gib+0.017
DER+0.017
Neg logit contributions
cius-0.023
unct-0.020
lation-0.019
late-0.018
 Theodore-0.018
TokenThis
Token ID1212
Feature activation-3.43e-03

Pos logit contributions
 Palest+0.000
ggle+0.000
adium+0.000
 gib+0.000
verson+0.000
Neg logit contributions
cius-0.000
unct-0.000
lation-0.000
late-0.000
 Theodore-0.000
Token as
Token ID355
Feature activation-5.38e-03

Pos logit contributions
cius+0.118
unct+0.101
lation+0.097
late+0.093
 Theodore+0.092
Neg logit contributions
 Palest-0.108
ggle-0.106
adium-0.104
 gib-0.100
DER-0.100
Token a
Token ID257
Feature activation-4.95e-02

Pos logit contributions
cius+0.004
unct+0.003
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.004
ggle-0.004
adium-0.004
 gib-0.003
DER-0.003
Token symbol
Token ID6194
Feature activation-4.69e-02

Pos logit contributions
cius+0.037
unct+0.032
lation+0.030
late+0.029
 Theodore+0.029
Neg logit contributions
 Palest-0.031
ggle-0.030
adium-0.030
 gib-0.029
DER-0.028
Token of
Token ID286
Feature activation+2.35e-02

Pos logit contributions
cius+0.035
unct+0.030
lation+0.029
late+0.028
 Theodore+0.027
Neg logit contributions
 Palest-0.030
ggle-0.029
adium-0.028
 gib-0.027
DER-0.027
Token Az
Token ID7578
Feature activation-1.16e-01

Pos logit contributions
 Palest+0.016
ggle+0.015
adium+0.015
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.016
unct-0.014
lation-0.013
late-0.013
 Theodore-0.013
Tokeneri
Token ID33442
Feature activation-4.49e-01

Pos logit contributions
cius+0.089
unct+0.078
lation+0.075
late+0.072
 Theodore+0.071
Neg logit contributions
 Palest-0.070
ggle-0.067
adium-0.067
 gib-0.064
DER-0.064
Token identity
Token ID5369
Feature activation+1.12e-01

Pos logit contributions
cius+0.320
unct+0.274
lation+0.264
late+0.253
 Theodore+0.252
Neg logit contributions
 Palest-0.294
ggle-0.286
adium-0.283
 gib-0.272
DER-0.271
Token,
Token ID11
Feature activation-2.93e-02

Pos logit contributions
 Palest+0.070
ggle+0.067
adium+0.067
 gib+0.064
DER+0.064
Neg logit contributions
cius-0.084
unct-0.072
lation-0.070
late-0.067
 Theodore-0.066
Token dub
Token ID10873
Feature activation+8.47e-02

Pos logit contributions
cius+0.021
unct+0.018
lation+0.017
late+0.017
 Theodore+0.016
Neg logit contributions
 Palest-0.019
ggle-0.019
adium-0.018
 gib-0.018
DER-0.018
Tokenbing
Token ID4623
Feature activation+8.60e-02

Pos logit contributions
 Palest+0.047
ggle+0.045
adium+0.044
 gib+0.042
DER+0.042
Neg logit contributions
cius-0.069
unct-0.061
lation-0.059
late-0.056
 Theodore-0.056
Token it
Token ID340
Feature activation-3.36e-02

Pos logit contributions
 Palest+0.056
ggle+0.054
adium+0.054
 gib+0.052
DER+0.051
Neg logit contributions
cius-0.062
unct-0.053
lation-0.051
late-0.048
 Theodore-0.048
Token nightclub
Token ID26617
Feature activation-4.32e-02

Pos logit contributions
cius+0.015
unct+0.013
lation+0.013
late+0.012
 Theodore+0.012
Neg logit contributions
 Palest-0.015
ggle-0.015
adium-0.015
 gib-0.014
DER-0.014
Token scenes
Token ID8188
Feature activation+1.07e-01

Pos logit contributions
cius+0.032
unct+0.027
lation+0.026
late+0.025
 Theodore+0.025
Neg logit contributions
 Palest-0.027
ggle-0.027
adium-0.026
 gib-0.025
verson-0.025
Token playing
Token ID2712
Feature activation-4.25e-02

Pos logit contributions
 Palest+0.071
ggle+0.069
adium+0.068
 gib+0.066
DER+0.065
Neg logit contributions
cius-0.075
unct-0.064
lation-0.062
late-0.059
 Theodore-0.059
Token in
Token ID287
Feature activation-2.36e-02

Pos logit contributions
cius+0.030
unct+0.026
lation+0.025
late+0.024
 Theodore+0.024
Neg logit contributions
 Palest-0.028
ggle-0.027
adium-0.027
 gib-0.026
DER-0.025
Token the
Token ID262
Feature activation+1.26e-02

Pos logit contributions
cius+0.017
unct+0.015
lation+0.014
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.015
ggle-0.015
adium-0.015
DER-0.014
 gib-0.014
Token background
Token ID4469
Feature activation-4.47e-01

Pos logit contributions
 Palest+0.013
ggle+0.013
adium+0.013
DER+0.013
 gib+0.013
Neg logit contributions
cius-0.004
unct-0.003
lation-0.002
late-0.002
 Theodore-0.002
Token might
Token ID1244
Feature activation-3.91e-02

Pos logit contributions
cius+0.309
unct+0.265
lation+0.255
late+0.243
 Theodore+0.242
Neg logit contributions
 Palest-0.301
ggle-0.292
adium-0.290
DER-0.277
 gib-0.277
Token help
Token ID1037
Feature activation-1.95e-02

Pos logit contributions
cius+0.027
unct+0.023
lation+0.022
late+0.021
 Theodore+0.021
Neg logit contributions
 Palest-0.026
ggle-0.026
adium-0.025
 gib-0.025
DER-0.024
Token add
Token ID751
Feature activation+3.76e-02

Pos logit contributions
cius+0.014
unct+0.012
lation+0.012
late+0.011
 Theodore+0.011
Neg logit contributions
 Palest-0.013
ggle-0.012
adium-0.012
 gib-0.012
DER-0.012
Token life
Token ID1204
Feature activation-3.31e-02

Pos logit contributions
 Palest+0.023
ggle+0.023
adium+0.022
 gib+0.021
DER+0.021
Neg logit contributions
cius-0.028
unct-0.024
lation-0.024
late-0.023
 Theodore-0.022
Token to
Token ID284
Feature activation+6.47e-03

Pos logit contributions
cius+0.026
unct+0.022
lation+0.022
late+0.021
 Theodore+0.021
Neg logit contributions
 Palest-0.020
ggle-0.019
adium-0.019
 gib-0.018
DER-0.018
Token of
Token ID286
Feature activation-6.74e-03

Pos logit contributions
cius+0.050
unct+0.043
lation+0.042
late+0.040
 Theodore+0.039
Neg logit contributions
 Palest-0.042
ggle-0.041
adium-0.041
 gib-0.039
DER-0.039
Token the
Token ID262
Feature activation-5.59e-02

Pos logit contributions
cius+0.005
unct+0.004
lation+0.004
late+0.004
 Theodore+0.004
Neg logit contributions
 Palest-0.005
ggle-0.004
adium-0.004
 gib-0.004
DER-0.004
Token finest
Token ID18822
Feature activation+8.06e-02

Pos logit contributions
cius+0.039
unct+0.034
lation+0.032
 Theodore+0.031
late+0.031
Neg logit contributions
 Palest-0.037
ggle-0.036
adium-0.036
 gib-0.034
DER-0.034
Token intuitive
Token ID19933
Feature activation-4.92e-02

Pos logit contributions
 Palest+0.050
ggle+0.049
adium+0.048
 gib+0.046
DER+0.046
Neg logit contributions
cius-0.060
unct-0.052
lation-0.050
late-0.048
 Theodore-0.048
Token mathematic
Token ID33161
Feature activation-6.75e-02

Pos logit contributions
cius+0.036
unct+0.031
lation+0.030
late+0.029
 Theodore+0.029
Neg logit contributions
 Palest-0.031
ggle-0.030
adium-0.030
 gib-0.029
DER-0.028
Tokenians
Token ID1547
Feature activation-4.46e-01

Pos logit contributions
cius+0.019
unct+0.013
lation+0.011
late+0.009
 Theodore+0.009
Neg logit contributions
 Palest-0.073
ggle-0.072
adium-0.071
 gib-0.070
DER-0.069
Token I
Token ID314
Feature activation-7.24e-02

Pos logit contributions
cius+0.311
unct+0.264
lation+0.253
 Theodore+0.244
late+0.243
Neg logit contributions
 Palest-0.301
ggle-0.293
adium-0.290
 gib-0.278
DER-0.277
Token have
Token ID423
Feature activation-1.31e-01

Pos logit contributions
cius+0.049
unct+0.041
lation+0.039
late+0.038
 Theodore+0.037
Neg logit contributions
 Palest-0.051
ggle-0.049
adium-0.049
 gib-0.047
DER-0.047
Token met
Token ID1138
Feature activation-1.03e-01

Pos logit contributions
cius+0.094
unct+0.081
lation+0.078
late+0.075
 Theodore+0.074
Neg logit contributions
 Palest-0.085
ggle-0.082
adium-0.081
 gib-0.078
DER-0.078
Token.
Token ID13
Feature activation-8.84e-02

Pos logit contributions
cius+0.074
unct+0.064
lation+0.061
late+0.059
 Theodore+0.059
Neg logit contributions
 Palest-0.066
ggle-0.064
adium-0.064
 gib-0.061
DER-0.061
Token He
Token ID679
Feature activation-3.10e-02

Pos logit contributions
cius+0.060
unct+0.051
lation+0.049
late+0.047
 Theodore+0.047
Neg logit contributions
 Palest-0.060
ggle-0.059
adium-0.058
 gib-0.056
verson-0.056
Token the
Token ID262
Feature activation-7.43e-03

Pos logit contributions
cius+0.046
unct+0.039
lation+0.038
late+0.036
 Theodore+0.036
Neg logit contributions
 Palest-0.046
ggle-0.045
adium-0.045
 gib-0.043
DER-0.043
Token personal
Token ID2614
Feature activation+6.86e-02

Pos logit contributions
cius+0.005
unct+0.005
lation+0.004
late+0.004
 Theodore+0.004
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.004
DER-0.004
Token intervention
Token ID9572
Feature activation+5.26e-02

Pos logit contributions
 Palest+0.046
ggle+0.045
adium+0.044
DER+0.042
 gib+0.042
Neg logit contributions
cius-0.048
unct-0.041
lation-0.039
 Theodore-0.038
late-0.038
Token of
Token ID286
Feature activation+1.21e-02

Pos logit contributions
 Palest+0.032
ggle+0.031
adium+0.031
 gib+0.030
verson+0.029
Neg logit contributions
cius-0.040
unct-0.035
lation-0.033
late-0.032
 Theodore-0.031
Token Ecuador
Token ID25794
Feature activation+7.10e-02

Pos logit contributions
 Palest+0.008
ggle+0.008
adium+0.008
 gib+0.008
DER+0.008
Neg logit contributions
cius-0.008
unct-0.007
lation-0.007
late-0.006
 Theodore-0.006
Tokenian
Token ID666
Feature activation-4.45e-01

Pos logit contributions
 Palest+0.053
ggle+0.052
adium+0.051
 gib+0.050
DER+0.050
Neg logit contributions
cius-0.044
unct-0.037
lation-0.035
late-0.033
 Theodore-0.033
Token president
Token ID1893
Feature activation-1.29e-01

Pos logit contributions
cius+0.322
unct+0.275
lation+0.265
late+0.255
 Theodore+0.255
Neg logit contributions
 Palest-0.287
ggle-0.280
adium-0.277
 gib-0.264
verson-0.264
Token Core
Token ID7231
Feature activation-1.51e-01

Pos logit contributions
cius+0.084
unct+0.071
lation+0.068
late+0.065
 Theodore+0.063
Neg logit contributions
 Palest-0.093
ggle-0.090
adium-0.089
 gib-0.086
verson-0.085
Tokena
Token ID64
Feature activation-1.48e-01

Pos logit contributions
cius+0.090
unct+0.074
lation+0.072
late+0.068
 Theodore+0.067
Neg logit contributions
 Palest-0.117
ggle-0.114
adium-0.113
 gib-0.109
DER-0.109
Token.
Token ID13
Feature activation+2.18e-03

Pos logit contributions
cius+0.107
unct+0.093
lation+0.089
 Theodore+0.088
late+0.087
Neg logit contributions
 Palest-0.092
ggle-0.092
adium-0.091
DER-0.087
verson-0.087
Token Assange
Token ID21882
Feature activation-1.58e-03

Pos logit contributions
 Palest+0.001
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.001
unct-0.001
lation-0.001
late-0.001
 Theodore-0.001
Token3
Token ID18
Feature activation-1.09e-01

Pos logit contributions
 Palest+0.029
ggle+0.028
adium+0.028
 gib+0.027
DER+0.026
Neg logit contributions
cius-0.026
unct-0.022
lation-0.021
late-0.020
 Theodore-0.019
Token-
Token ID12
Feature activation+2.98e-02

Pos logit contributions
cius+0.076
unct+0.065
lation+0.063
late+0.060
 Theodore+0.060
Neg logit contributions
 Palest-0.072
ggle-0.070
adium-0.070
 gib-0.067
DER-0.067
Tokenamine
Token ID9862
Feature activation+2.41e-02

Pos logit contributions
 Palest+0.022
ggle+0.022
adium+0.022
 gib+0.021
DER+0.021
Neg logit contributions
cius-0.018
unct-0.015
lation-0.015
late-0.014
 Theodore-0.014
Token to
Token ID284
Feature activation-2.12e-03

Pos logit contributions
 Palest+0.016
ggle+0.016
adium+0.016
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.017
unct-0.014
lation-0.014
late-0.013
 Theodore-0.013
Tokensy
Token ID1837
Feature activation-9.61e-03

Pos logit contributions
cius+0.002
unct+0.001
lation+0.001
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.001
ggle-0.001
adium-0.001
 gib-0.001
DER-0.001
Tokenlate
Token ID17660
Feature activation-4.44e-01

Pos logit contributions
cius+0.007
unct+0.006
lation+0.006
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.006
ggle-0.006
adium-0.006
 gib-0.006
DER-0.006
Token (
Token ID357
Feature activation-4.69e-02

Pos logit contributions
cius+0.311
unct+0.266
lation+0.256
late+0.244
 Theodore+0.243
Neg logit contributions
 Palest-0.297
ggle-0.288
adium-0.285
 gib-0.275
DER-0.273
TokenE
Token ID36
Feature activation-1.33e-02

Pos logit contributions
cius+0.034
unct+0.029
lation+0.028
late+0.027
 Theodore+0.026
Neg logit contributions
 Palest-0.031
ggle-0.030
adium-0.029
 gib-0.028
DER-0.028
Token250
Token ID9031
Feature activation-6.73e-02

Pos logit contributions
cius+0.010
unct+0.008
lation+0.008
late+0.008
 Theodore+0.008
Neg logit contributions
 Palest-0.009
ggle-0.008
adium-0.008
 gib-0.008
DER-0.008
Token8
Token ID23
Feature activation-2.38e-02

Pos logit contributions
cius+0.048
unct+0.041
lation+0.039
late+0.037
 Theodore+0.037
Neg logit contributions
 Palest-0.045
ggle-0.043
adium-0.043
 gib-0.041
DER-0.041
Token),
Token ID828
Feature activation+2.08e-02

Pos logit contributions
cius+0.017
unct+0.015
lation+0.014
late+0.014
 Theodore+0.014
Neg logit contributions
 Palest-0.015
ggle-0.015
adium-0.015
 gib-0.014
DER-0.014
Token of
Token ID286
Feature activation+2.57e-02

Pos logit contributions
cius+0.095
unct+0.082
lation+0.078
late+0.075
 Theodore+0.075
Neg logit contributions
 Palest-0.087
ggle-0.085
adium-0.084
 gib-0.081
DER-0.080
Token day
Token ID1110
Feature activation-1.28e-01

Pos logit contributions
 Palest+0.020
ggle+0.019
adium+0.019
 gib+0.019
verson+0.019
Neg logit contributions
cius-0.015
unct-0.012
lation-0.012
late-0.011
 Theodore-0.011
Token
Token ID198
Feature activation+3.26e-02

Pos logit contributions
cius+0.091
unct+0.079
lation+0.075
late+0.072
 Theodore+0.072
Neg logit contributions
 Palest-0.083
ggle-0.081
adium-0.080
 gib-0.077
DER-0.077
Token
Token ID198
Feature activation+2.34e-02

Pos logit contributions
 Palest+0.023
ggle+0.022
adium+0.022
 gib+0.021
verson+0.021
Neg logit contributions
cius-0.022
unct-0.019
lation-0.018
late-0.018
 Theodore-0.017
TokenMem
Token ID13579
Feature activation+1.13e-01

Pos logit contributions
 Palest+0.016
ggle+0.016
adium+0.016
 gib+0.015
verson+0.015
Neg logit contributions
cius-0.016
unct-0.013
lation-0.013
late-0.012
 Theodore-0.012
Tokenories
Token ID1749
Feature activation+3.34e-01

Pos logit contributions
 Palest+0.067
ggle+0.064
adium+0.064
 gib+0.061
DER+0.061
Neg logit contributions
cius-0.087
unct-0.076
lation-0.073
late-0.071
 Theodore-0.070
Token of
Token ID286
Feature activation+7.79e-03

Pos logit contributions
 Palest+0.219
ggle+0.212
adium+0.210
 gib+0.202
DER+0.201
Neg logit contributions
cius-0.238
unct-0.204
lation-0.196
late-0.188
 Theodore-0.186
Token racing
Token ID11717
Feature activation-1.84e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.005
unct-0.005
lation-0.005
late-0.004
 Theodore-0.004
Token in
Token ID287
Feature activation-3.96e-04

Pos logit contributions
cius+0.013
unct+0.011
lation+0.011
late+0.010
 Theodore+0.010
Neg logit contributions
 Palest-0.012
ggle-0.012
adium-0.012
 gib-0.011
DER-0.011
Token the
Token ID262
Feature activation+4.29e-03

Pos logit contributions
cius+0.000
unct+0.000
lation+0.000
late+0.000
 Theodore+0.000
Neg logit contributions
 Palest-0.000
ggle-0.000
adium-0.000
 gib-0.000
DER-0.000
Token fog
Token ID19558
Feature activation-2.13e-02

Pos logit contributions
 Palest+0.003
ggle+0.003
adium+0.003
 gib+0.003
DER+0.003
Neg logit contributions
cius-0.003
unct-0.003
lation-0.002
late-0.002
 Theodore-0.002
Token hard
Token ID1327
Feature activation+2.83e-03

Pos logit contributions
 Palest+0.062
ggle+0.060
adium+0.060
 gib+0.057
DER+0.057
Neg logit contributions
cius-0.081
unct-0.070
lation-0.068
late-0.065
 Theodore-0.065
Token and
Token ID290
Feature activation+8.23e-03

Pos logit contributions
 Palest+0.002
ggle+0.002
adium+0.002
 gib+0.002
DER+0.002
Neg logit contributions
cius-0.002
unct-0.002
lation-0.002
late-0.002
 Theodore-0.002
Token you
Token ID345
Feature activation-8.63e-03

Pos logit contributions
 Palest+0.006
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.004
 Theodore-0.004
Token couldn
Token ID3521
Feature activation+7.12e-02

Pos logit contributions
cius+0.006
unct+0.005
lation+0.005
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.006
ggle-0.006
adium-0.006
 gib-0.005
DER-0.005
Token't
Token ID470
Feature activation+1.82e-02

Pos logit contributions
 Palest+0.048
ggle+0.046
adium+0.046
 gib+0.044
verson+0.044
Neg logit contributions
cius-0.050
unct-0.043
lation-0.041
late-0.039
 Theodore-0.039
Token fault
Token ID8046
Feature activation+2.94e-01

Pos logit contributions
 Palest+0.012
adium+0.012
ggle+0.011
DER+0.011
 gib+0.011
Neg logit contributions
cius-0.013
unct-0.011
lation-0.011
late-0.010
 Theodore-0.010
Token anybody
Token ID9599
Feature activation+1.84e-02

Pos logit contributions
 Palest+0.208
ggle+0.201
adium+0.200
 gib+0.193
DER+0.192
Neg logit contributions
cius-0.196
unct-0.166
lation-0.159
late-0.151
 Theodore-0.149
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
 Palest+0.012
ggle+0.011
adium+0.011
 gib+0.011
DER+0.011
Neg logit contributions
cius-0.013
unct-0.012
lation-0.011
late-0.011
 Theodore-0.011
Token They
Token ID1119
Feature activation+4.09e-02

Pos logit contributions
 Palest+0.007
ggle+0.007
adium+0.007
 gib+0.007
DER+0.007
Neg logit contributions
cius-0.007
unct-0.006
lation-0.006
late-0.006
 Theodore-0.006
Token showed
Token ID3751
Feature activation+2.10e-02

Pos logit contributions
 Palest+0.027
ggle+0.026
adium+0.026
 gib+0.025
DER+0.025
Neg logit contributions
cius-0.029
unct-0.025
lation-0.024
late-0.023
 Theodore-0.023
Token character
Token ID2095
Feature activation-7.16e-02

Pos logit contributions
 Palest+0.014
ggle+0.013
adium+0.013
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.015
unct-0.013
lation-0.012
late-0.012
 Theodore-0.012
Token NATO
Token ID11332
Feature activation+1.30e-01

Pos logit contributions
 Palest+0.012
ggle+0.012
adium+0.012
 gib+0.011
DER+0.011
Neg logit contributions
cius-0.012
unct-0.010
lation-0.010
late-0.009
 Theodore-0.009
Token.
Token ID13
Feature activation-2.00e-03

Pos logit contributions
 Palest+0.086
ggle+0.084
adium+0.083
 gib+0.080
DER+0.079
Neg logit contributions
cius-0.091
unct-0.078
lation-0.075
late-0.071
 Theodore-0.071
Token A
Token ID317
Feature activation-3.57e-02

Pos logit contributions
cius+0.001
unct+0.001
lation+0.001
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.001
ggle-0.001
adium-0.001
 gib-0.001
DER-0.001
Token l
Token ID300
Feature activation+9.28e-03

Pos logit contributions
cius+0.026
unct+0.022
lation+0.021
late+0.020
 Theodore+0.020
Neg logit contributions
 Palest-0.023
ggle-0.022
adium-0.022
 gib-0.021
DER-0.021
Tokenuke
Token ID4649
Feature activation+4.45e-02

Pos logit contributions
 Palest+0.006
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.007
unct-0.006
lation-0.006
late-0.006
 Theodore-0.006
Tokenwarm
Token ID31975
Feature activation+2.91e-01

Pos logit contributions
 Palest+0.012
ggle+0.011
adium+0.011
 gib+0.010
DER+0.010
Neg logit contributions
cius-0.049
unct-0.044
lation-0.043
late-0.042
 Theodore-0.042
Token response
Token ID2882
Feature activation+3.48e-02

Pos logit contributions
 Palest+0.187
ggle+0.181
adium+0.179
 gib+0.172
DER+0.171
Neg logit contributions
cius-0.211
unct-0.181
lation-0.175
late-0.167
 Theodore-0.166
Token from
Token ID422
Feature activation-4.68e-02

Pos logit contributions
 Palest+0.024
ggle+0.023
adium+0.023
 gib+0.022
DER+0.022
Neg logit contributions
cius-0.024
unct-0.020
lation-0.019
late-0.018
 Theodore-0.018
Token the
Token ID262
Feature activation+2.38e-02

Pos logit contributions
cius+0.030
unct+0.025
lation+0.024
late+0.023
 Theodore+0.023
Neg logit contributions
 Palest-0.034
ggle-0.033
adium-0.033
 gib-0.032
DER-0.032
Token United
Token ID1578
Feature activation-6.54e-03

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.016
 gib+0.016
DER+0.015
Neg logit contributions
cius-0.016
unct-0.013
lation-0.013
late-0.012
 Theodore-0.012
Token States
Token ID1829
Feature activation-7.42e-02

Pos logit contributions
cius+0.004
unct+0.004
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.004
 gib-0.004
DER-0.004
Token the
Token ID262
Feature activation-2.34e-02

Pos logit contributions
 Palest+0.011
ggle+0.011
adium+0.011
 gib+0.011
DER+0.010
Neg logit contributions
cius-0.011
unct-0.010
lation-0.009
late-0.009
 Theodore-0.009
Token list
Token ID1351
Feature activation-1.22e-01

Pos logit contributions
cius+0.019
unct+0.017
lation+0.016
late+0.016
 Theodore+0.016
Neg logit contributions
 Palest-0.013
ggle-0.012
adium-0.012
verson-0.012
DER-0.012
Token in
Token ID287
Feature activation-4.31e-02

Pos logit contributions
cius+0.089
unct+0.076
lation+0.074
late+0.071
 Theodore+0.070
Neg logit contributions
 Palest-0.078
ggle-0.076
adium-0.075
 gib-0.072
DER-0.072
Token the
Token ID262
Feature activation-5.07e-03

Pos logit contributions
cius+0.031
unct+0.026
lation+0.025
late+0.024
 Theodore+0.024
Neg logit contributions
 Palest-0.028
ggle-0.027
adium-0.027
 gib-0.026
DER-0.026
Token Gob
Token ID16909
Feature activation-1.54e-01

Pos logit contributions
cius+0.004
unct+0.003
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.003
ggle-0.003
adium-0.003
 gib-0.003
verson-0.003
Tokenber
Token ID527
Feature activation+3.37e-01

Pos logit contributions
cius+0.109
unct+0.094
lation+0.090
late+0.086
 Theodore+0.085
Neg logit contributions
 Palest-0.101
ggle-0.098
adium-0.097
 gib-0.094
DER-0.093
Token Tinker
Token ID46316
Feature activation-6.25e-02

Pos logit contributions
 Palest+0.221
ggle+0.215
adium+0.213
 gib+0.205
DER+0.203
Neg logit contributions
cius-0.240
unct-0.205
lation-0.197
late-0.188
 Theodore-0.187
Token,
Token ID11
Feature activation-5.13e-02

Pos logit contributions
cius+0.044
unct+0.038
lation+0.037
late+0.035
 Theodore+0.035
Neg logit contributions
 Palest-0.041
ggle-0.040
adium-0.039
 gib-0.038
DER-0.038
Token Wrong
Token ID28843
Feature activation-2.23e-01

Pos logit contributions
cius+0.037
unct+0.032
lation+0.030
late+0.029
 Theodore+0.029
Neg logit contributions
 Palest-0.033
ggle-0.032
adium-0.032
 gib-0.031
DER-0.031
Token Eye
Token ID14144
Feature activation+1.56e-01

Pos logit contributions
cius+0.161
unct+0.138
lation+0.133
late+0.127
 Theodore+0.126
Neg logit contributions
 Palest-0.145
ggle-0.141
adium-0.139
 gib-0.134
DER-0.133
Token &
Token ID1222
Feature activation+5.89e-02

Pos logit contributions
 Palest+0.101
ggle+0.098
adium+0.097
 gib+0.094
DER+0.093
Neg logit contributions
cius-0.113
unct-0.097
lation-0.093
late-0.089
 Theodore-0.089
Token for
Token ID329
Feature activation+2.80e-02

Pos logit contributions
cius+0.007
unct+0.006
lation+0.006
late+0.005
 Theodore+0.005
Neg logit contributions
 Palest-0.007
ggle-0.007
adium-0.007
DER-0.006
 gib-0.006
Token the
Token ID262
Feature activation+2.62e-02

Pos logit contributions
 Palest+0.018
ggle+0.017
adium+0.017
 gib+0.016
verson+0.016
Neg logit contributions
cius-0.020
unct-0.018
lation-0.017
late-0.016
 Theodore-0.016
Token latest
Token ID3452
Feature activation-6.48e-02

Pos logit contributions
 Palest+0.016
ggle+0.016
adium+0.016
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.019
unct-0.017
lation-0.016
late-0.016
 Theodore-0.015
Token version
Token ID2196
Feature activation+3.93e-02

Pos logit contributions
cius+0.050
unct+0.044
lation+0.042
late+0.041
 Theodore+0.041
Neg logit contributions
 Palest-0.038
ggle-0.037
adium-0.037
DER-0.035
verson-0.035
Token of
Token ID286
Feature activation+7.33e-03

Pos logit contributions
 Palest+0.024
ggle+0.024
adium+0.023
 gib+0.023
DER+0.022
Neg logit contributions
cius-0.029
unct-0.025
lation-0.024
late-0.023
 Theodore-0.023
Token Libre
Token ID44384
Feature activation+3.43e-01

Pos logit contributions
 Palest+0.005
ggle+0.004
adium+0.004
 gib+0.004
DER+0.004
Neg logit contributions
cius-0.005
unct-0.005
lation-0.005
late-0.004
 Theodore-0.004
TokenOffice
Token ID27743
Feature activation-2.29e-02

Pos logit contributions
 Palest+0.232
ggle+0.226
adium+0.224
 gib+0.217
DER+0.215
Neg logit contributions
cius-0.236
unct-0.201
lation-0.193
 Theodore-0.183
late-0.182
Token and
Token ID290
Feature activation+4.84e-03

Pos logit contributions
cius+0.017
unct+0.014
lation+0.014
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.015
ggle-0.014
adium-0.014
 gib-0.014
DER-0.014
Token I
Token ID314
Feature activation+1.80e-02

Pos logit contributions
 Palest+0.003
ggle+0.003
adium+0.003
 gib+0.003
DER+0.003
Neg logit contributions
cius-0.004
unct-0.003
lation-0.003
late-0.003
 Theodore-0.003
Token wanted
Token ID2227
Feature activation+4.21e-02

Pos logit contributions
 Palest+0.012
ggle+0.012
adium+0.012
 gib+0.011
DER+0.011
Neg logit contributions
cius-0.013
unct-0.011
lation-0.010
late-0.010
 Theodore-0.010
Token to
Token ID284
Feature activation-6.75e-03

Pos logit contributions
 Palest+0.024
ggle+0.023
adium+0.023
 gib+0.022
DER+0.021
Neg logit contributions
cius-0.034
unct-0.030
lation-0.029
late-0.028
 Theodore-0.027
Token have
Token ID423
Feature activation-1.30e-02

Pos logit contributions
cius+0.016
unct+0.013
lation+0.013
late+0.012
 Theodore+0.012
Neg logit contributions
 Palest-0.016
ggle-0.015
adium-0.015
 gib-0.015
DER-0.015
Token gotten
Token ID7891
Feature activation-7.25e-03

Pos logit contributions
cius+0.009
unct+0.008
lation+0.008
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.008
ggle-0.008
adium-0.008
 gib-0.008
DER-0.008
Token ourselves
Token ID6731
Feature activation-2.96e-02

Pos logit contributions
cius+0.005
unct+0.004
lation+0.004
late+0.004
 Theodore+0.004
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.004
DER-0.004
Token around
Token ID1088
Feature activation+4.79e-02

Pos logit contributions
cius+0.021
unct+0.018
lation+0.017
late+0.016
 Theodore+0.016
Neg logit contributions
 Palest-0.020
ggle-0.019
adium-0.019
 gib-0.018
DER-0.018
Token on
Token ID319
Feature activation+1.83e-04

Pos logit contributions
 Palest+0.031
ggle+0.030
adium+0.030
 gib+0.029
DER+0.029
Neg logit contributions
cius-0.034
unct-0.029
lation-0.028
late-0.027
 Theodore-0.027
Token foot
Token ID2366
Feature activation+1.84e-01

Pos logit contributions
 Palest+0.000
ggle+0.000
adium+0.000
 gib+0.000
DER+0.000
Neg logit contributions
cius-0.000
unct-0.000
lation-0.000
 Theodore-0.000
late-0.000
Token,
Token ID11
Feature activation+7.51e-03

Pos logit contributions
 Palest+0.118
ggle+0.115
adium+0.114
 gib+0.109
DER+0.108
Neg logit contributions
cius-0.133
unct-0.115
lation-0.110
late-0.105
 Theodore-0.105
Token vehicle
Token ID4038
Feature activation-1.38e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.005
unct-0.005
lation-0.004
late-0.004
 Theodore-0.004
Token or
Token ID393
Feature activation+9.37e-03

Pos logit contributions
cius+0.010
unct+0.008
lation+0.008
 Theodore+0.008
late+0.008
Neg logit contributions
 Palest-0.009
ggle-0.009
adium-0.009
 gib-0.008
DER-0.008
Token bicycle
Token ID17026
Feature activation+3.81e-02

Pos logit contributions
 Palest+0.006
ggle+0.006
adium+0.006
 gib+0.006
DER+0.006
Neg logit contributions
cius-0.007
unct-0.006
lation-0.006
late-0.005
 Theodore-0.005
Token,
Token ID11
Feature activation+1.65e-02

Pos logit contributions
 Palest+0.024
ggle+0.024
adium+0.023
 gib+0.023
verson+0.022
Neg logit contributions
cius-0.028
unct-0.024
lation-0.023
 Theodore-0.022
late-0.022
Token credit
Token ID3884
Feature activation-1.94e-01

Pos logit contributions
 Palest+0.008
ggle+0.008
adium+0.008
 gib+0.008
DER+0.007
Neg logit contributions
cius-0.009
unct-0.008
lation-0.007
late-0.007
 Theodore-0.007
Token would
Token ID561
Feature activation-3.92e-02

Pos logit contributions
cius+0.133
unct+0.114
lation+0.110
late+0.104
 Theodore+0.103
Neg logit contributions
 Palest-0.132
ggle-0.129
adium-0.127
 gib-0.122
verson-0.122
Token not
Token ID407
Feature activation-1.77e-02

Pos logit contributions
cius+0.028
unct+0.024
lation+0.023
late+0.022
 Theodore+0.022
Neg logit contributions
 Palest-0.026
ggle-0.025
adium-0.025
 gib-0.024
DER-0.024
Token be
Token ID307
Feature activation+8.17e-03

Pos logit contributions
cius+0.013
unct+0.011
lation+0.011
late+0.010
 Theodore+0.010
Neg logit contributions
 Palest-0.012
ggle-0.011
adium-0.011
DER-0.011
 gib-0.011
Token easily
Token ID3538
Feature activation-4.61e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
DER+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.005
 Theodore-0.005
Token forthcoming
Token ID21220
Feature activation+1.41e-01

Pos logit contributions
cius+0.033
unct+0.028
lation+0.027
late+0.026
 Theodore+0.026
Neg logit contributions
 Palest-0.030
ggle-0.029
adium-0.029
 gib-0.028
DER-0.028
Token.
Token ID13
Feature activation-7.21e-03

Pos logit contributions
 Palest+0.091
ggle+0.089
adium+0.088
 gib+0.084
DER+0.084
Neg logit contributions
cius-0.101
unct-0.087
lation-0.084
late-0.080
 Theodore-0.080
Token The
Token ID383
Feature activation-1.61e-02

Pos logit contributions
cius+0.005
unct+0.004
lation+0.004
late+0.004
 Theodore+0.004
Neg logit contributions
 Palest-0.005
ggle-0.005
adium-0.005
 gib-0.004
DER-0.004
Token banks
Token ID6341
Feature activation+1.48e-01

Pos logit contributions
cius+0.012
unct+0.010
lation+0.010
late+0.009
 Theodore+0.009
Neg logit contributions
 Palest-0.010
ggle-0.010
adium-0.010
 gib-0.009
DER-0.009
Token already
Token ID1541
Feature activation+5.57e-02

Pos logit contributions
 Palest+0.105
ggle+0.102
adium+0.101
 gib+0.098
DER+0.097
Neg logit contributions
cius-0.097
unct-0.083
lation-0.079
late-0.075
 Theodore-0.074
Token take
Token ID1011
Feature activation+5.14e-02

Pos logit contributions
 Palest+0.037
ggle+0.036
adium+0.036
 gib+0.034
DER+0.034
Neg logit contributions
cius-0.039
unct-0.033
lation-0.032
late-0.031
 Theodore-0.030
Token I
Token ID314
Feature activation-1.59e-02

Pos logit contributions
cius+0.020
unct+0.017
lation+0.016
late+0.015
 Theodore+0.015
Neg logit contributions
 Palest-0.020
ggle-0.020
adium-0.020
 gib-0.019
DER-0.019
Token apply
Token ID4174
Feature activation+2.24e-02

Pos logit contributions
cius+0.011
unct+0.010
lation+0.009
late+0.009
 Theodore+0.009
Neg logit contributions
 Palest-0.011
ggle-0.010
adium-0.010
 gib-0.010
DER-0.010
Token the
Token ID262
Feature activation-4.22e-02

Pos logit contributions
 Palest+0.015
ggle+0.014
adium+0.014
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.016
unct-0.014
lation-0.013
late-0.013
 Theodore-0.013
Token same
Token ID976
Feature activation-3.13e-02

Pos logit contributions
cius+0.029
unct+0.025
lation+0.024
late+0.023
 Theodore+0.023
Neg logit contributions
 Palest-0.029
ggle-0.028
adium-0.027
 gib-0.026
DER-0.026
Token basic
Token ID4096
Feature activation-1.58e-01

Pos logit contributions
cius+0.022
unct+0.019
lation+0.018
late+0.017
 Theodore+0.017
Neg logit contributions
 Palest-0.021
ggle-0.020
adium-0.020
 gib-0.019
DER-0.019
Token concept
Token ID3721
Feature activation+1.56e-02

Pos logit contributions
cius+0.111
unct+0.095
lation+0.091
late+0.087
 Theodore+0.087
Neg logit contributions
 Palest-0.105
ggle-0.102
adium-0.101
 gib-0.097
DER-0.097
Token to
Token ID284
Feature activation-3.12e-02

Pos logit contributions
 Palest+0.009
ggle+0.009
adium+0.009
 gib+0.009
verson+0.009
Neg logit contributions
cius-0.012
unct-0.010
lation-0.010
late-0.010
 Theodore-0.010
Token my
Token ID616
Feature activation+2.43e-02

Pos logit contributions
cius+0.023
unct+0.019
lation+0.019
late+0.018
 Theodore+0.018
Neg logit contributions
 Palest-0.020
ggle-0.020
adium-0.019
 gib-0.019
DER-0.019
Token fruit
Token ID8234
Feature activation-7.63e-02

Pos logit contributions
 Palest+0.016
ggle+0.016
adium+0.016
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.017
unct-0.015
lation-0.014
late-0.013
 Theodore-0.013
Token and
Token ID290
Feature activation-2.12e-02

Pos logit contributions
cius+0.056
unct+0.048
lation+0.047
late+0.045
 Theodore+0.044
Neg logit contributions
 Palest-0.048
ggle-0.047
adium-0.046
 gib-0.044
verson-0.044
Token nut
Token ID6701
Feature activation+3.46e-02

Pos logit contributions
cius+0.014
unct+0.012
lation+0.011
late+0.011
 Theodore+0.011
Neg logit contributions
 Palest-0.015
ggle-0.015
adium-0.015
 gib-0.014
DER-0.014
Tokenread
Token ID961
Feature activation-7.11e-02

Pos logit contributions
cius+0.003
unct+0.002
lation+0.002
late+0.002
 Theodore+0.002
Neg logit contributions
 Palest-0.003
ggle-0.003
adium-0.003
 gib-0.003
DER-0.003
Tokenwell
Token ID4053
Feature activation-1.71e-01

Pos logit contributions
cius+0.042
unct+0.035
lation+0.033
late+0.031
 Theodore+0.030
Neg logit contributions
 Palest-0.056
ggle-0.054
adium-0.054
 gib-0.052
DER-0.052
Token;
Token ID26
Feature activation+4.78e-02

Pos logit contributions
cius+0.125
unct+0.108
lation+0.104
late+0.099
 Theodore+0.099
Neg logit contributions
 Palest-0.109
ggle-0.106
adium-0.105
 gib-0.101
DER-0.100
Token it
Token ID340
Feature activation+7.93e-03

Pos logit contributions
 Palest+0.032
ggle+0.031
adium+0.031
 gib+0.030
DER+0.029
Neg logit contributions
cius-0.034
unct-0.029
lation-0.028
late-0.026
 Theodore-0.026
Token usually
Token ID3221
Feature activation-8.74e-02

Pos logit contributions
 Palest+0.005
ggle+0.005
adium+0.005
 gib+0.005
verson+0.005
Neg logit contributions
cius-0.006
unct-0.005
lation-0.005
late-0.004
 Theodore-0.004
Token doesn
Token ID1595
Feature activation+6.52e-02

Pos logit contributions
cius+0.066
unct+0.057
lation+0.055
late+0.053
 Theodore+0.053
Neg logit contributions
 Palest-0.054
ggle-0.052
adium-0.051
 gib-0.049
DER-0.049
Token
Token ID447
Feature activation-2.50e-02

Pos logit contributions
 Palest+0.045
ggle+0.044
adium+0.044
 gib+0.042
DER+0.042
Neg logit contributions
cius-0.044
unct-0.037
lation-0.036
late-0.034
 Theodore-0.034
Token
Token ID247
Feature activation-2.54e-02

Pos logit contributions
cius+0.017
unct+0.014
lation+0.013
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.018
ggle-0.017
adium-0.017
 gib-0.017
DER-0.016
Tokent
Token ID83
Feature activation+1.09e-02

Pos logit contributions
cius+0.020
unct+0.017
lation+0.016
late+0.016
 Theodore+0.016
Neg logit contributions
 Palest-0.015
ggle-0.015
adium-0.014
 gib-0.014
DER-0.014
Token work
Token ID670
Feature activation-3.38e-02

Pos logit contributions
 Palest+0.007
ggle+0.007
adium+0.007
 gib+0.007
DER+0.007
Neg logit contributions
cius-0.008
unct-0.007
lation-0.006
late-0.006
 Theodore-0.006
Token.
Token ID13
Feature activation-4.21e-02

Pos logit contributions
cius+0.024
unct+0.021
lation+0.020
late+0.019
 Theodore+0.019
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.021
 gib-0.020
DER-0.020
Token I
Token ID314
Feature activation+4.88e-02

Pos logit contributions
 Palest+0.018
ggle+0.018
adium+0.018
 gib+0.017
DER+0.017
Neg logit contributions
cius-0.018
unct-0.015
lation-0.014
 Theodore-0.014
late-0.014
Token want
Token ID765
Feature activation-4.51e-02

Pos logit contributions
 Palest+0.033
ggle+0.032
adium+0.031
 gib+0.030
DER+0.030
Neg logit contributions
cius-0.034
unct-0.029
lation-0.028
late-0.027
 Theodore-0.027
Token to
Token ID284
Feature activation+6.81e-03

Pos logit contributions
cius+0.035
unct+0.030
lation+0.029
late+0.028
 Theodore+0.028
Neg logit contributions
 Palest-0.027
ggle-0.026
adium-0.026
 gib-0.025
DER-0.025
Token collaborate
Token ID30081
Feature activation+6.84e-02

Pos logit contributions
 Palest+0.004
ggle+0.004
adium+0.004
DER+0.004
 gib+0.004
Neg logit contributions
cius-0.005
unct-0.004
lation-0.004
late-0.004
 Theodore-0.004
Token with
Token ID351
Feature activation-6.80e-02

Pos logit contributions
 Palest+0.048
ggle+0.046
adium+0.046
 gib+0.044
DER+0.044
Neg logit contributions
cius-0.046
unct-0.039
lation-0.037
late-0.036
 Theodore-0.035
Token each
Token ID1123
Feature activation+9.16e-02

Pos logit contributions
cius+0.046
unct+0.039
lation+0.037
late+0.036
 Theodore+0.036
Neg logit contributions
 Palest-0.047
ggle-0.046
adium-0.045
 gib-0.044
DER-0.043
Token artist
Token ID6802
Feature activation+4.94e-02

Pos logit contributions
 Palest+0.048
ggle+0.047
adium+0.046
 gib+0.044
DER+0.044
Neg logit contributions
cius-0.077
unct-0.068
lation-0.065
late-0.063
 Theodore-0.063
Token.
Token ID13
Feature activation+2.33e-02

Pos logit contributions
 Palest+0.032
ggle+0.031
adium+0.031
 gib+0.030
DER+0.029
Neg logit contributions
cius-0.036
unct-0.031
lation-0.029
late-0.028
 Theodore-0.028
Token »
Token ID13355
Feature activation-6.02e-02

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.016
 gib+0.016
DER+0.016
Neg logit contributions
cius-0.015
unct-0.013
lation-0.012
late-0.011
 Theodore-0.011
Token And
Token ID843
Feature activation-5.38e-02

Pos logit contributions
cius+0.040
unct+0.034
lation+0.032
late+0.031
 Theodore+0.031
Neg logit contributions
 Palest-0.043
ggle-0.041
adium-0.041
 gib-0.040
DER-0.039
Token his
Token ID465
Feature activation-1.28e-02

Pos logit contributions
cius+0.036
unct+0.031
lation+0.030
late+0.028
 Theodore+0.028
Neg logit contributions
 Palest-0.037
ggle-0.036
adium-0.036
 gib-0.035
DER-0.034
Token recently
Token ID2904
Feature activation+7.60e-02

Pos logit contributions
 Palest+0.011
ggle+0.011
adium+0.011
 gib+0.010
DER+0.010
Neg logit contributions
cius-0.012
unct-0.011
lation-0.010
late-0.010
 Theodore-0.010
Token reached
Token ID4251
Feature activation+7.09e-02

Pos logit contributions
 Palest+0.051
ggle+0.050
adium+0.049
 gib+0.048
DER+0.047
Neg logit contributions
cius-0.053
unct-0.045
lation-0.043
late-0.041
 Theodore-0.041
Token the
Token ID262
Feature activation-4.68e-03

Pos logit contributions
 Palest+0.049
ggle+0.047
adium+0.047
DER+0.045
 gib+0.045
Neg logit contributions
cius-0.048
unct-0.041
lation-0.040
 Theodore-0.038
late-0.038
Token level
Token ID1241
Feature activation+1.10e-01

Pos logit contributions
cius+0.003
unct+0.003
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.003
ggle-0.003
adium-0.003
DER-0.003
 gib-0.003
Token of
Token ID286
Feature activation-5.22e-03

Pos logit contributions
 Palest+0.070
ggle+0.068
adium+0.067
 gib+0.065
DER+0.064
Neg logit contributions
cius-0.080
unct-0.069
lation-0.066
late-0.063
 Theodore-0.063
Token kissing
Token ID25847
Feature activation-1.35e-01

Pos logit contributions
cius+0.004
unct+0.003
lation+0.003
 Theodore+0.003
late+0.003
Neg logit contributions
 Palest-0.003
ggle-0.003
adium-0.003
DER-0.003
 gib-0.003
Token.
Token ID13
Feature activation-2.00e-02

Pos logit contributions
cius+0.096
unct+0.082
lation+0.080
 Theodore+0.077
late+0.076
Neg logit contributions
 Palest-0.089
ggle-0.086
adium-0.086
DER-0.081
verson-0.081
Token For
Token ID1114
Feature activation+6.60e-02

Pos logit contributions
cius+0.014
unct+0.012
lation+0.011
 Theodore+0.011
late+0.011
Neg logit contributions
 Palest-0.014
ggle-0.013
adium-0.013
 gib-0.013
DER-0.013
Token Stella
Token ID45856
Feature activation-1.12e-01

Pos logit contributions
 Palest+0.043
ggle+0.042
adium+0.041
 gib+0.040
DER+0.039
Neg logit contributions
cius-0.047
unct-0.041
lation-0.039
late-0.038
 Theodore-0.038
Token,
Token ID11
Feature activation-1.06e-02

Pos logit contributions
cius+0.080
unct+0.069
lation+0.066
late+0.064
 Theodore+0.063
Neg logit contributions
 Palest-0.072
ggle-0.070
adium-0.069
 gib-0.067
DER-0.066
Token she
Token ID673
Feature activation+1.35e-02

Pos logit contributions
cius+0.007
unct+0.006
lation+0.006
late+0.006
 Theodore+0.006
Neg logit contributions
 Palest-0.007
ggle-0.007
adium-0.007
 gib-0.006
DER-0.006
Token coaches
Token ID11070
Feature activation+2.04e-02

Pos logit contributions
 Palest+0.035
ggle+0.034
adium+0.034
 gib+0.033
DER+0.032
Neg logit contributions
cius-0.031
unct-0.026
lation-0.025
late-0.023
 Theodore-0.023
Token and
Token ID290
Feature activation-2.47e-02

Pos logit contributions
 Palest+0.013
ggle+0.013
adium+0.012
 gib+0.012
verson+0.012
Neg logit contributions
cius-0.015
unct-0.013
lation-0.012
late-0.012
 Theodore-0.012
Token media
Token ID2056
Feature activation-1.13e-01

Pos logit contributions
cius+0.017
unct+0.015
lation+0.014
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.017
ggle-0.016
adium-0.016
 gib-0.016
DER-0.015
Token and
Token ID290
Feature activation-2.50e-02

Pos logit contributions
cius+0.076
unct+0.065
lation+0.062
late+0.059
 Theodore+0.059
Neg logit contributions
 Palest-0.079
ggle-0.076
adium-0.076
 gib-0.073
DER-0.073
Token ACC
Token ID15859
Feature activation+2.26e-02

Pos logit contributions
cius+0.017
unct+0.015
lation+0.014
late+0.014
 Theodore+0.013
Neg logit contributions
 Palest-0.017
ggle-0.016
adium-0.016
 gib-0.016
DER-0.016
Token Fresh
Token ID20138
Feature activation-1.82e-01

Pos logit contributions
 Palest+0.016
ggle+0.016
adium+0.015
 gib+0.015
DER+0.015
Neg logit contributions
cius-0.015
unct-0.013
lation-0.012
late-0.012
 Theodore-0.011
Tokenman
Token ID805
Feature activation+1.46e-01

Pos logit contributions
cius+0.144
unct+0.125
lation+0.121
late+0.117
 Theodore+0.116
Neg logit contributions
 Palest-0.105
ggle-0.102
adium-0.101
 gib-0.097
DER-0.096
Token of
Token ID286
Feature activation-1.43e-02

Pos logit contributions
 Palest+0.088
ggle+0.085
adium+0.085
 gib+0.081
verson+0.080
Neg logit contributions
cius-0.112
unct-0.097
lation-0.093
late-0.089
 Theodore-0.088
Token the
Token ID262
Feature activation-2.03e-02

Pos logit contributions
cius+0.009
unct+0.008
lation+0.008
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.010
ggle-0.010
adium-0.010
 gib-0.009
DER-0.009
Token year
Token ID614
Feature activation-7.50e-02

Pos logit contributions
cius+0.015
unct+0.013
lation+0.012
late+0.012
 Theodore+0.012
Neg logit contributions
 Palest-0.013
ggle-0.012
adium-0.012
 gib-0.012
DER-0.012
Token.
Token ID13
Feature activation-3.60e-02

Pos logit contributions
cius+0.051
unct+0.044
lation+0.042
late+0.040
 Theodore+0.039
Neg logit contributions
 Palest-0.051
ggle-0.050
adium-0.049
 gib-0.048
verson-0.047
Tokent
Token ID83
Feature activation-5.42e-03

Pos logit contributions
cius+0.046
unct+0.040
lation+0.038
late+0.037
 Theodore+0.037
Neg logit contributions
 Palest-0.034
ggle-0.033
adium-0.033
 gib-0.032
DER-0.031
Token pick
Token ID2298
Feature activation-1.25e-01

Pos logit contributions
cius+0.004
unct+0.003
lation+0.003
late+0.003
 Theodore+0.003
Neg logit contributions
 Palest-0.003
ggle-0.003
adium-0.003
 gib-0.003
DER-0.003
Token a
Token ID257
Feature activation-2.10e-03

Pos logit contributions
cius+0.088
unct+0.075
lation+0.072
late+0.069
 Theodore+0.068
Neg logit contributions
 Palest-0.083
ggle-0.081
adium-0.080
 gib-0.077
DER-0.077
Token better
Token ID1365
Feature activation-6.53e-02

Pos logit contributions
cius+0.001
unct+0.001
lation+0.001
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.001
ggle-0.001
adium-0.001
 gib-0.001
DER-0.001
Token place
Token ID1295
Feature activation+1.01e-02

Pos logit contributions
cius+0.047
unct+0.040
lation+0.039
late+0.037
 Theodore+0.037
Neg logit contributions
 Palest-0.043
ggle-0.041
adium-0.041
 gib-0.039
DER-0.039
Token to
Token ID284
Feature activation-1.22e-02

Pos logit contributions
 Palest+0.006
ggle+0.006
adium+0.006
 gib+0.006
DER+0.006
Neg logit contributions
cius-0.008
unct-0.007
lation-0.006
late-0.006
 Theodore-0.006
Token do
Token ID466
Feature activation+8.11e-02

Pos logit contributions
cius+0.009
unct+0.008
lation+0.007
late+0.007
 Theodore+0.007
Neg logit contributions
 Palest-0.008
ggle-0.008
adium-0.008
DER-0.007
 gib-0.007
Token it
Token ID340
Feature activation-1.31e-02

Pos logit contributions
 Palest+0.053
ggle+0.051
adium+0.051
 gib+0.049
DER+0.049
Neg logit contributions
cius-0.057
unct-0.049
lation-0.048
late-0.046
 Theodore-0.046
Token than
Token ID621
Feature activation-2.61e-02

Pos logit contributions
cius+0.010
unct+0.008
lation+0.008
late+0.008
 Theodore+0.007
Neg logit contributions
 Palest-0.008
ggle-0.008
adium-0.008
 gib-0.008
DER-0.008
Token a
Token ID257
Feature activation-2.31e-02

Pos logit contributions
cius+0.017
unct+0.015
lation+0.014
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.018
ggle-0.018
adium-0.018
 gib-0.017
DER-0.017
Token city
Token ID1748
Feature activation-3.13e-02

Pos logit contributions
cius+0.016
unct+0.014
lation+0.013
late+0.013
 Theodore+0.013
Neg logit contributions
 Palest-0.015
ggle-0.015
adium-0.015
 gib-0.014
DER-0.014
Token is
Token ID318
Feature activation+4.88e-02

Pos logit contributions
 Palest+0.074
ggle+0.072
adium+0.071
 gib+0.068
DER+0.068
Neg logit contributions
cius-0.081
unct-0.070
lation-0.067
late-0.064
 Theodore-0.064
Token almost
Token ID2048
Feature activation-4.95e-02

Pos logit contributions
 Palest+0.032
ggle+0.031
adium+0.030
 gib+0.029
DER+0.029
Neg logit contributions
cius-0.035
unct-0.030
lation-0.029
late-0.028
 Theodore-0.028
Token here
Token ID994
Feature activation+1.13e-01

Pos logit contributions
cius+0.038
unct+0.033
lation+0.032
late+0.031
 Theodore+0.031
Neg logit contributions
 Palest-0.029
ggle-0.028
adium-0.028
 gib-0.027
DER-0.027
Token
Token ID784
Feature activation+2.29e-03

Pos logit contributions
 Palest+0.072
ggle+0.070
adium+0.069
 gib+0.066
DER+0.066
Neg logit contributions
cius-0.082
unct-0.071
lation-0.068
late-0.065
 Theodore-0.065
Token and
Token ID290
Feature activation+1.97e-02

Pos logit contributions
 Palest+0.001
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.002
unct-0.001
lation-0.001
late-0.001
 Theodore-0.001
Token we
Token ID356
Feature activation-1.51e-02

Pos logit contributions
 Palest+0.013
ggle+0.013
adium+0.013
 gib+0.012
DER+0.012
Neg logit contributions
cius-0.014
unct-0.012
lation-0.011
late-0.011
 Theodore-0.011
Token
Token ID447
Feature activation-1.82e-02

Pos logit contributions
cius+0.011
unct+0.009
lation+0.009
late+0.008
 Theodore+0.008
Neg logit contributions
 Palest-0.010
ggle-0.010
adium-0.010
 gib-0.009
DER-0.009
Token
Token ID247
Feature activation+3.62e-02

Pos logit contributions
cius+0.013
unct+0.012
lation+0.011
late+0.011
 Theodore+0.011
Neg logit contributions
 Palest-0.012
adium-0.011
ggle-0.011
 gib-0.011
DER-0.010
Tokenve
Token ID303
Feature activation+5.19e-02

Pos logit contributions
 Palest+0.026
ggle+0.025
adium+0.025
 gib+0.024
DER+0.024
Neg logit contributions
cius-0.024
unct-0.020
lation-0.019
late-0.018
 Theodore-0.018
Token got
Token ID1392
Feature activation-3.14e-02

Pos logit contributions
 Palest+0.035
ggle+0.034
adium+0.033
 gib+0.032
DER+0.032
Neg logit contributions
cius-0.036
unct-0.031
lation-0.030
late-0.028
 Theodore-0.028
Token an
Token ID281
Feature activation+1.76e-02

Pos logit contributions
cius+0.022
unct+0.019
lation+0.018
late+0.018
 Theodore+0.017
Neg logit contributions
 Palest-0.021
ggle-0.020
adium-0.020
 gib-0.019
DER-0.019
Tokentext
Token ID5239
Feature activation+8.03e-02

Pos logit contributions
 Palest+0.031
ggle+0.030
adium+0.030
 gib+0.029
DER+0.028
Neg logit contributions
cius-0.040
unct-0.035
lation-0.034
late-0.032
 Theodore-0.032
Token]
Token ID60
Feature activation-4.57e-02

Pos logit contributions
 Palest+0.057
ggle+0.055
adium+0.055
 gib+0.053
DER+0.053
Neg logit contributions
cius-0.053
unct-0.044
lation-0.042
 Theodore-0.040
late-0.040
Token any
Token ID597
Feature activation+2.64e-02

Pos logit contributions
cius+0.034
unct+0.029
lation+0.028
late+0.027
 Theodore+0.027
Neg logit contributions
 Palest-0.029
ggle-0.028
adium-0.028
 gib-0.026
DER-0.026
Token text
Token ID2420
Feature activation-1.54e-01

Pos logit contributions
 Palest+0.019
ggle+0.019
adium+0.019
 gib+0.018
DER+0.018
Neg logit contributions
cius-0.017
unct-0.014
lation-0.013
late-0.013
 Theodore-0.013
Token or
Token ID393
Feature activation+3.16e-02

Pos logit contributions
cius+0.115
unct+0.100
lation+0.096
late+0.092
 Theodore+0.091
Neg logit contributions
 Palest-0.095
ggle-0.092
adium-0.091
 gib-0.088
DER-0.087
Token empty
Token ID6565
Feature activation-1.19e-01

Pos logit contributions
 Palest+0.023
ggle+0.022
adium+0.022
 gib+0.021
DER+0.021
Neg logit contributions
cius-0.020
unct-0.017
lation-0.016
late-0.016
 Theodore-0.015
Token Example
Token ID17934
Feature activation-1.30e-02

Pos logit contributions
cius+0.084
unct+0.072
lation+0.069
late+0.066
 Theodore+0.065
Neg logit contributions
 Palest-0.079
ggle-0.076
adium-0.076
 gib-0.073
DER-0.072
Token:
Token ID25
Feature activation+2.56e-02

Pos logit contributions
cius+0.011
unct+0.009
lation+0.009
late+0.009
 Theodore+0.009
Neg logit contributions
 Palest-0.007
ggle-0.007
adium-0.007
 gib-0.007
DER-0.006
Token /*
Token ID11900
Feature activation-1.59e-01

Pos logit contributions
 Palest+0.014
ggle+0.014
adium+0.013
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.021
unct-0.018
lation-0.018
late-0.017
 Theodore-0.017
Token vim
Token ID43907
Feature activation+8.27e-02

Pos logit contributions
cius+0.115
unct+0.098
lation+0.095
late+0.091
 Theodore+0.090
Neg logit contributions
 Palest-0.103
ggle-0.100
adium-0.099
 gib-0.096
DER-0.095
Token:
Token ID25
Feature activation+1.67e-02

Pos logit contributions
 Palest+0.047
ggle+0.046
adium+0.045
 gib+0.044
DER+0.043
Neg logit contributions
cius-0.066
unct-0.057
lation-0.055
late-0.053
 Theodore-0.053
Token analyzing
Token ID22712
Feature activation+7.01e-02

Pos logit contributions
 Palest+0.040
ggle+0.039
adium+0.038
 gib+0.036
DER+0.036
Neg logit contributions
cius-0.045
unct-0.039
lation-0.037
late-0.036
 Theodore-0.035
Token how
Token ID703
Feature activation+3.63e-02

Pos logit contributions
 Palest+0.045
ggle+0.043
adium+0.043
DER+0.041
 gib+0.041
Neg logit contributions
cius-0.051
unct-0.044
lation-0.042
late-0.041
 Theodore-0.040
Token Phil
Token ID4543
Feature activation+6.00e-02

Pos logit contributions
 Palest+0.023
ggle+0.023
adium+0.023
DER+0.022
 gib+0.021
Neg logit contributions
cius-0.026
unct-0.022
lation-0.022
late-0.021
 Theodore-0.021
Tokenadel
Token ID6959
Feature activation+1.92e-01

Pos logit contributions
 Palest+0.037
ggle+0.035
adium+0.035
 gib+0.033
DER+0.033
Neg logit contributions
cius-0.046
unct-0.040
lation-0.038
late-0.037
 Theodore-0.036
Tokenph
Token ID746
Feature activation+1.68e-01

Pos logit contributions
 Palest+0.106
ggle+0.100
adium+0.098
DER+0.095
 gib+0.094
Neg logit contributions
cius-0.158
unct-0.140
lation-0.135
late-0.131
 Theodore-0.127
Tokenians
Token ID1547
Feature activation-2.80e-01

Pos logit contributions
 Palest+0.181
ggle+0.178
adium+0.177
 gib+0.173
DER+0.172
Neg logit contributions
cius-0.048
unct-0.031
lation-0.027
late-0.023
 Theodore-0.022
Token speak
Token ID2740
Feature activation+3.15e-02

Pos logit contributions
cius+0.209
unct+0.181
lation+0.174
late+0.167
 Theodore+0.166
Neg logit contributions
 Palest-0.175
ggle-0.168
adium-0.167
DER-0.159
 gib-0.158
Token,
Token ID11
Feature activation+1.94e-02

Pos logit contributions
 Palest+0.020
ggle+0.019
adium+0.019
DER+0.018
 gib+0.018
Neg logit contributions
cius-0.023
unct-0.020
lation-0.019
late-0.018
 Theodore-0.018
Token Fisher
Token ID14388
Feature activation-7.04e-02

Pos logit contributions
 Palest+0.013
ggle+0.013
adium+0.013
 gib+0.012
DER+0.012
Neg logit contributions
cius-0.013
unct-0.011
lation-0.011
late-0.010
 Theodore-0.010
Token explains
Token ID6688
Feature activation-1.13e-01

Pos logit contributions
cius+0.051
unct+0.044
lation+0.042
late+0.040
 Theodore+0.040
Neg logit contributions
 Palest-0.046
ggle-0.044
adium-0.044
 gib-0.042
DER-0.042
Token.
Token ID13
Feature activation+1.43e-02

Pos logit contributions
cius+0.086
unct+0.074
lation+0.071
late+0.069
 Theodore+0.068
Neg logit contributions
 Palest-0.069
ggle-0.067
adium-0.066
 gib-0.063
DER-0.063
Token,
Token ID11
Feature activation+2.38e-03

Pos logit contributions
 Palest+0.026
ggle+0.025
adium+0.025
 gib+0.024
DER+0.024
Neg logit contributions
cius-0.028
unct-0.024
lation-0.023
late-0.022
 Theodore-0.022
Token stating
Token ID12316
Feature activation+1.07e-01

Pos logit contributions
 Palest+0.001
ggle+0.001
adium+0.001
 gib+0.001
DER+0.001
Neg logit contributions
cius-0.002
unct-0.002
lation-0.002
late-0.001
 Theodore-0.001
Token the
Token ID262
Feature activation-1.91e-03

Pos logit contributions
 Palest+0.065
ggle+0.063
adium+0.062
 gib+0.060
DER+0.059
Neg logit contributions
cius-0.082
unct-0.071
lation-0.068
late-0.065
 Theodore-0.065
Token plan
Token ID1410
Feature activation+6.32e-03

Pos logit contributions
cius+0.001
unct+0.001
lation+0.001
late+0.001
 Theodore+0.001
Neg logit contributions
 Palest-0.001
ggle-0.001
adium-0.001
 gib-0.001
DER-0.001
Token lacked
Token ID19989
Feature activation+1.92e-01

Pos logit contributions
 Palest+0.004
ggle+0.004
adium+0.004
 gib+0.004
DER+0.004
Neg logit contributions
cius-0.004
unct-0.004
lation-0.004
late-0.003
 Theodore-0.003
Token transparency
Token ID13902
Feature activation-2.83e-01

Pos logit contributions
 Palest+0.130
ggle+0.126
adium+0.125
 gib+0.121
DER+0.120
Neg logit contributions
cius-0.133
unct-0.114
lation-0.109
late-0.104
 Theodore-0.103
Token in
Token ID287
Feature activation-3.28e-02

Pos logit contributions
cius+0.206
unct+0.177
lation+0.170
late+0.163
 Theodore+0.162
Neg logit contributions
 Palest-0.181
ggle-0.176
adium-0.174
 gib-0.167
DER-0.166
Token the
Token ID262
Feature activation+2.19e-02

Pos logit contributions
cius+0.024
unct+0.020
lation+0.019
late+0.019
 Theodore+0.019
Neg logit contributions
 Palest-0.021
ggle-0.021
adium-0.020
 gib-0.020
DER-0.020
Token selection
Token ID6356
Feature activation-8.55e-02

Pos logit contributions
 Palest+0.014
ggle+0.014
adium+0.014
 gib+0.013
DER+0.013
Neg logit contributions
cius-0.016
unct-0.014
lation-0.013
late-0.012
 Theodore-0.012
Token of
Token ID286
Feature activation+2.56e-02

Pos logit contributions
cius+0.059
unct+0.050
lation+0.048
late+0.046
 Theodore+0.045
Neg logit contributions
 Palest-0.058
ggle-0.057
adium-0.056
 gib-0.054
DER-0.054
Token the
Token ID262
Feature activation+2.88e-02

Pos logit contributions
 Palest+0.017
ggle+0.016
adium+0.016
 gib+0.016
DER+0.015
Neg logit contributions
cius-0.018
unct-0.016
lation-0.015
late-0.014
 Theodore-0.014
Token gave
Token ID2921
Feature activation-2.96e-02

Pos logit contributions
cius+0.022
unct+0.019
lation+0.018
late+0.017
 Theodore+0.017
Neg logit contributions
 Palest-0.021
ggle-0.021
adium-0.021
 gib-0.020
DER-0.020
Token the
Token ID262
Feature activation-1.04e-02

Pos logit contributions
cius+0.019
unct+0.016
lation+0.015
late+0.014
 Theodore+0.014
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.021
 gib-0.020
DER-0.020
Token legs
Token ID7405
Feature activation+1.08e-01

Pos logit contributions
cius+0.008
unct+0.007
lation+0.006
late+0.006
 Theodore+0.006
Neg logit contributions
 Palest-0.007
ggle-0.006
adium-0.006
DER-0.006
verson-0.006
Token a
Token ID257
Feature activation-4.05e-02

Pos logit contributions
 Palest+0.074
ggle+0.071
adium+0.071
 gib+0.068
DER+0.068
Neg logit contributions
cius-0.073
unct-0.063
lation-0.060
late-0.058
 Theodore-0.057
Token good
Token ID922
Feature activation+1.48e-01

Pos logit contributions
cius+0.031
unct+0.027
lation+0.026
late+0.025
 Theodore+0.025
Neg logit contributions
 Palest-0.025
adium-0.024
ggle-0.024
DER-0.023
 gib-0.022
Token wake
Token ID7765
Feature activation-2.65e-01

Pos logit contributions
 Palest+0.096
ggle+0.093
adium+0.092
DER+0.088
 gib+0.088
Neg logit contributions
cius-0.107
unct-0.092
lation-0.088
late-0.085
 Theodore-0.084
Token up
Token ID510
Feature activation-2.71e-02

Pos logit contributions
cius+0.177
unct+0.150
lation+0.144
late+0.137
 Theodore+0.136
Neg logit contributions
 Palest-0.187
ggle-0.181
adium-0.180
 gib-0.173
DER-0.172
Token call
Token ID869
Feature activation+8.63e-02

Pos logit contributions
cius+0.019
unct+0.016
lation+0.016
late+0.015
 Theodore+0.015
Neg logit contributions
 Palest-0.018
adium-0.017
ggle-0.017
DER-0.017
verson-0.017
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
 Palest+0.056
ggle+0.054
adium+0.054
 gib+0.051
DER+0.051
Neg logit contributions
cius-0.062
unct-0.054
lation-0.052
late-0.050
 Theodore-0.049
Token Mid
Token ID7215
Feature activation-1.52e-01

Pos logit contributions
cius+0.010
unct+0.009
lation+0.008
late+0.008
 Theodore+0.008
Neg logit contributions
 Palest-0.011
ggle-0.011
adium-0.011
 gib-0.010
DER-0.010
Token-
Token ID12
Feature activation-4.83e-02

Pos logit contributions
cius+0.103
unct+0.088
lation+0.084
late+0.080
 Theodore+0.079
Neg logit contributions
 Palest-0.105
ggle-0.102
adium-0.101
 gib-0.098
DER-0.097
Token if
Token ID611
Feature activation-4.14e-02

Pos logit contributions
 Palest+0.025
ggle+0.025
adium+0.024
 gib+0.023
DER+0.023
Neg logit contributions
cius-0.027
unct-0.023
lation-0.022
late-0.021
 Theodore-0.021
Token you
Token ID345
Feature activation-2.87e-02

Pos logit contributions
cius+0.029
unct+0.024
lation+0.023
late+0.022
 Theodore+0.022
Neg logit contributions
 Palest-0.028
ggle-0.027
adium-0.027
 gib-0.026
DER-0.026
Token look
Token ID804
Feature activation-3.64e-02

Pos logit contributions
cius+0.020
unct+0.017
lation+0.016
late+0.016
 Theodore+0.015
Neg logit contributions
 Palest-0.020
ggle-0.019
adium-0.019
 gib-0.018
DER-0.018
Token across
Token ID1973
Feature activation-5.38e-02

Pos logit contributions
cius+0.026
unct+0.022
lation+0.022
late+0.021
 Theodore+0.021
Neg logit contributions
 Palest-0.024
ggle-0.023
adium-0.023
 gib-0.022
DER-0.022
Token this
Token ID428
Feature activation+1.07e-02

Pos logit contributions
cius+0.038
unct+0.032
lation+0.031
late+0.029
 Theodore+0.029
Neg logit contributions
 Palest-0.036
ggle-0.035
adium-0.035
 gib-0.033
DER-0.033
Token room
Token ID2119
Feature activation-2.96e-01

Pos logit contributions
 Palest+0.008
ggle+0.007
adium+0.007
 gib+0.007
DER+0.007
Neg logit contributions
cius-0.007
unct-0.006
lation-0.006
late-0.005
 Theodore-0.005
Token,
Token ID11
Feature activation-2.29e-02

Pos logit contributions
cius+0.210
unct+0.180
lation+0.173
late+0.166
 Theodore+0.165
Neg logit contributions
 Palest-0.196
ggle-0.190
adium-0.187
 gib-0.181
DER-0.180
Token you
Token ID345
Feature activation-2.63e-02

Pos logit contributions
cius+0.016
unct+0.014
lation+0.013
late+0.013
 Theodore+0.012
Neg logit contributions
 Palest-0.015
ggle-0.015
adium-0.015
 gib-0.014
DER-0.014
Token
Token ID447
Feature activation-4.09e-03

Pos logit contributions
cius+0.018
unct+0.016
lation+0.015
late+0.014
 Theodore+0.014
Neg logit contributions
 Palest-0.018
ggle-0.017
adium-0.017
 gib-0.016
DER-0.016
Token
Token ID247
Feature activation-4.02e-02

Pos logit contributions
cius+0.003
unct+0.002
lation+0.002
late+0.002
 Theodore+0.002
Neg logit contributions
 Palest-0.003
adium-0.003
ggle-0.003
 gib-0.003
DER-0.003
Tokenll
Token ID297
Feature activation-7.41e-02

Pos logit contributions
cius+0.027
unct+0.023
lation+0.022
late+0.021
 Theodore+0.021
Neg logit contributions
 Palest-0.028
ggle-0.027
adium-0.027
 gib-0.026
DER-0.026
Token until
Token ID1566
Feature activation-1.05e-02

Pos logit contributions
cius+0.011
unct+0.010
lation+0.009
late+0.009
 Theodore+0.009
Neg logit contributions
 Palest-0.009
ggle-0.009
adium-0.009
 gib-0.008
DER-0.008
Token the
Token ID262
Feature activation-5.18e-02

Pos logit contributions
cius+0.007
unct+0.006
lation+0.006
late+0.006
 Theodore+0.006
Neg logit contributions
 Palest-0.007
ggle-0.007
adium-0.007
 gib-0.006
DER-0.006
Token arrival
Token ID10325
Feature activation+1.20e-01

Pos logit contributions
cius+0.039
unct+0.034
lation+0.033
late+0.032
 Theodore+0.032
Neg logit contributions
 Palest-0.031
ggle-0.030
adium-0.030
 gib-0.028
DER-0.028
Token location
Token ID4067
Feature activation-1.02e-01

Pos logit contributions
 Palest+0.077
ggle+0.075
adium+0.074
 gib+0.071
DER+0.071
Neg logit contributions
cius-0.087
unct-0.075
lation-0.072
late-0.069
 Theodore-0.069
Token is
Token ID318
Feature activation-3.47e-02

Pos logit contributions
cius+0.077
unct+0.066
lation+0.064
late+0.061
 Theodore+0.061
Neg logit contributions
 Palest-0.064
ggle-0.062
adium-0.061
 gib-0.058
DER-0.058
Token part
Token ID636
Feature activation-2.68e-01

Pos logit contributions
cius+0.025
unct+0.022
lation+0.021
late+0.020
 Theodore+0.020
Neg logit contributions
 Palest-0.022
ggle-0.021
adium-0.021
 gib-0.020
DER-0.020
Token of
Token ID286
Feature activation-6.69e-02

Pos logit contributions
cius+0.202
unct+0.175
lation+0.168
late+0.161
 Theodore+0.161
Neg logit contributions
 Palest-0.164
ggle-0.159
adium-0.157
 gib-0.152
verson-0.149
Token the
Token ID262
Feature activation-5.41e-02

Pos logit contributions
cius+0.046
unct+0.039
lation+0.038
late+0.036
 Theodore+0.036
Neg logit contributions
 Palest-0.045
ggle-0.044
adium-0.044
 gib-0.042
DER-0.042
Token search
Token ID2989
Feature activation-1.39e-01

Pos logit contributions
cius+0.038
unct+0.032
lation+0.031
late+0.030
 Theodore+0.029
Neg logit contributions
 Palest-0.036
ggle-0.035
adium-0.035
 gib-0.033
DER-0.033
Token space
Token ID2272
Feature activation+3.76e-02

Pos logit contributions
cius+0.111
unct+0.098
lation+0.094
late+0.091
 Theodore+0.090
Neg logit contributions
 Palest-0.078
ggle-0.076
adium-0.075
 gib-0.071
DER-0.071
Token.
Token ID13
Feature activation-5.36e-02

Pos logit contributions
 Palest+0.024
ggle+0.023
adium+0.023
 gib+0.022
DER+0.022
Neg logit contributions
cius-0.027
unct-0.024
lation-0.023
late-0.022
 Theodore-0.022