TOP ACTIVATIONS
MAX = 1.350

The rising practice of qu ack ery and sectarian medicine fractured
possession and possession of drug parap hern alia . It
had said , " How cum nobody just does simple stories
a little - known hedge fund manager who crossed Goldman
. When Trump named his vice presidential pick , Gov .
with sect arians and qu acks could not support an influx
the office said in a draft Strategic Plan released last week
been trained to navigate a wheelchair through a maze and have
Read more about Sud h ir Ch oud h
speeches . Newsletter Sign Up Continue reading the main
, broadcast , rewritten or redistributed .) <|endoftext|> New castle United
be chosen as Romney 's vice presidential candidate .
, Ma urer and Qu ack en bush , to Triple
the country knew who the Koch brothers are . With 25
years . <|endoftext|> Image copyright AFP The Bank of
Chicago Bears have blocked outside linebackers coach Clint Hur tt from
Indiana . <|endoftext|> The Bengals signed kicker Jonathan Brown , far
. <|endoftext|> Media playback is unsupported on your device Media caption
solve the Pittsburgh Penguins expansion draft problem ? If you believe
is able to meet its deficit targets , given that a

MIN ACTIVATIONS
MIN = -1.261

d ong province turns redd ish brown after the water was
atics and over 90 000 rounds of blank ammunition . "
ongoing violations and increase in settlement expansion . A shift has
would drive nearly nine hours round trip in a day to
stated that the Ministry of Internal Affairs also expressed its willingness
a service pistol and 15 rounds of ammunition that disappeared last
found a ' p reg nant ' T . re x
01 . 29 "] [ Round " 11 "] [ White
her departure time carefully . Either she gets on the London
Ay at ollah Ali Kham enei , warned that the day
Lew said . Neither action will extend the Oct
in both official languages . Neither language takes precedence over the
Pupp ies stole the Sad Pupp ies brand as one
between sovereign Israel and the settlements in the territories ended up
other team , his team fight tim ings are going to
success ". L ever , like Gibbs , was
" j okes " about Internal Revenue Service audits to the
is part of the Virtual Console service , which brings you
a super - p reg nant Ann al ise knowing
choking Jennifer Lawrence , was round ly criticized for showing excessive

INTERVAL 0.697 - 1.350
CONTAINS 0.250%

and all the til ap ia fil lets are the same
ings head [ who gave Lear y his first LSD trip
from his boss Hood a despite the fact that it is
Boston ( pictured ), the Latin Academy , some areas in
pick in the 2015 NBA draft by the Philadelphia 76 ers

INTERVAL 0.044 - 0.697
CONTAINS 36.914%

video of your owner dancing in the locker room , because
What has the universe got to do with it ?
bullying , dominance , and victim ization during the transition from
Un locked BIOS , Digital P WM Controller , and Enhanced
of factors means it 's closed . And the only numbers

INTERVAL -0.608 - 0.044
CONTAINS 62.233%

Metroid speed run race , from Awesome Games Done Quick 2014
to give third driver Bruno S enna some time in the
AAA games , and you all know that the Nintendo booth
had wrought , and on the labor that I
placing figures . Lastly , I tint ed around

INTERVAL -1.261 - -0.608
CONTAINS 0.602%

sorts in a blow out victory . In 2014 , Texas
path , 4 ) = '. cl j ' OR RIGHT
however , and his preseason teased us with previews of greatness
that life is meaningless . . . The only thing that
used . He sometimes shot in the afternoon ,
Token The
Token ID383
Feature activation-1.20e-01

Pos logit contributions
 confir+0.301
 contro+0.288
 discharge+0.281
 corpor+0.277
 Jude+0.277
Neg logit contributions
acs-0.302
 Gravity-0.294
assic-0.293
ikhail-0.292
Tokens-0.286
Token rising
Token ID7396
Feature activation+1.23e-02

Pos logit contributions
 confir+0.190
 contro+0.180
 discharge+0.175
 corpor+0.172
 Jude+0.172
Neg logit contributions
acs-0.236
 Gravity-0.231
assic-0.229
ikhail-0.229
Tokens-0.225
Token practice
Token ID3357
Feature activation-3.51e-02

Pos logit contributions
acs+0.026
 Gravity+0.025
assic+0.025
ikhail+0.025
Tokens+0.024
Neg logit contributions
 confir-0.018
 contro-0.017
 discharge-0.016
 Jude-0.016
 corpor-0.016
Token of
Token ID286
Feature activation-2.07e-02

Pos logit contributions
 confir+0.049
 contro+0.046
 discharge+0.045
 corpor+0.044
 Jude+0.044
Neg logit contributions
acs-0.075
 Gravity-0.073
assic-0.073
ikhail-0.073
Tokens-0.072
Token qu
Token ID627
Feature activation-1.07e-01

Pos logit contributions
 confir+0.032
 contro+0.030
 discharge+0.029
 Jude+0.029
 corpor+0.029
Neg logit contributions
acs-0.041
 Gravity-0.041
assic-0.040
ikhail-0.040
Tokens-0.039
Tokenack
Token ID441
Feature activation+1.35e+00

Pos logit contributions
 confir+0.217
 contro+0.208
 discharge+0.203
 corpor+0.201
 Jude+0.201
Neg logit contributions
acs-0.161
 Gravity-0.156
assic-0.156
ikhail-0.155
Tokens-0.151
Tokenery
Token ID1924
Feature activation+2.10e-01

Pos logit contributions
acs+2.573
 Gravity+2.501
assic+2.486
ikhail+2.471
Tokens+2.443
Neg logit contributions
 confir-2.190
 contro-2.064
 discharge-2.023
 Jude-1.986
 cumulative-1.982
Token and
Token ID290
Feature activation-3.33e-02

Pos logit contributions
acs+0.394
 Gravity+0.385
assic+0.383
ikhail+0.382
Tokens+0.374
Neg logit contributions
 confir-0.348
 contro-0.332
 discharge-0.323
 corpor-0.319
 Jude-0.318
Token sectarian
Token ID28005
Feature activation-3.71e-01

Pos logit contributions
 confir+0.054
 contro+0.051
 discharge+0.050
 corpor+0.049
 Jude+0.049
Neg logit contributions
acs-0.064
 Gravity-0.063
assic-0.062
ikhail-0.062
Tokens-0.061
Token medicine
Token ID9007
Feature activation+1.74e-01

Pos logit contributions
 confir+0.610
 contro+0.580
 discharge+0.564
 corpor+0.557
 Jude+0.556
Neg logit contributions
acs-0.703
 Gravity-0.688
assic-0.684
ikhail-0.682
Tokens-0.670
Token fractured
Token ID34051
Feature activation+3.53e-01

Pos logit contributions
acs+0.322
 Gravity+0.315
assic+0.313
ikhail+0.312
Tokens+0.306
Neg logit contributions
 confir-0.295
 contro-0.280
 discharge-0.273
 corpor-0.270
 Jude-0.269
Token possession
Token ID7797
Feature activation+1.02e+00

Pos logit contributions
acs+0.329
 Gravity+0.321
assic+0.320
ikhail+0.319
Tokens+0.313
Neg logit contributions
 confir-0.302
 contro-0.288
 discharge-0.280
 corpor-0.277
 Jude-0.276
Token and
Token ID290
Feature activation+1.85e-01

Pos logit contributions
acs+1.905
 Gravity+1.855
assic+1.842
ikhail+1.830
Tokens+1.789
Neg logit contributions
 confir-1.684
 contro-1.589
 Jude-1.527
 discharge-1.527
 corpor-1.521
Token possession
Token ID7797
Feature activation+9.03e-01

Pos logit contributions
acs+0.350
 Gravity+0.345
assic+0.340
ikhail+0.339
Tokens+0.331
Neg logit contributions
 confir-0.303
 contro-0.286
 discharge-0.275
 Jude-0.275
 corpor-0.272
Token of
Token ID286
Feature activation+2.38e-01

Pos logit contributions
acs+1.833
 Gravity+1.785
assic+1.770
ikhail+1.761
Tokens+1.733
Neg logit contributions
 confir-1.362
 contro-1.280
 discharge-1.233
 Jude-1.231
 corpor-1.222
Token drug
Token ID2563
Feature activation+2.07e-01

Pos logit contributions
acs+0.464
 Gravity+0.455
assic+0.448
ikhail+0.446
Tokens+0.441
Neg logit contributions
 confir-0.380
 contro-0.357
 discharge-0.347
 Jude-0.344
 corpor-0.340
Token parap
Token ID41406
Feature activation+1.35e+00

Pos logit contributions
acs+0.402
 Gravity+0.393
assic+0.391
ikhail+0.390
Tokens+0.383
Neg logit contributions
 confir-0.329
 contro-0.313
 discharge-0.304
 corpor-0.300
 Jude-0.299
Tokenhern
Token ID2881
Feature activation+3.18e-01

Pos logit contributions
acs+1.952
 Gravity+1.849
ikhail+1.831
assic+1.818
ochem+1.792
Neg logit contributions
 confir-2.938
 contro-2.748
 corpor-2.663
 Jude-2.662
 discharge-2.656
Tokenalia
Token ID9752
Feature activation+6.57e-01

Pos logit contributions
acs+0.738
 Gravity+0.726
assic+0.723
ikhail+0.722
Tokens+0.711
Neg logit contributions
 confir-0.385
 contro-0.360
 discharge-0.348
 corpor-0.341
 Jude-0.340
Token.
Token ID13
Feature activation+2.13e-01

Pos logit contributions
acs+1.276
 Gravity+1.247
ikhail+1.233
assic+1.228
Tokens+1.208
Neg logit contributions
 confir-1.047
 contro-0.979
 discharge-0.949
 Jude-0.948
 corpor-0.940
Token It
Token ID632
Feature activation+6.91e-02

Pos logit contributions
acs+0.428
 Gravity+0.423
assic+0.414
ikhail+0.414
Tokens+0.408
Neg logit contributions
 confir-0.333
 contro-0.312
 discharge-0.302
 corpor-0.297
 cumulative-0.296
Token
Token ID447
Feature activation+2.34e-01

Pos logit contributions
acs+0.120
 Gravity+0.118
assic+0.117
ikhail+0.116
Tokens+0.114
Neg logit contributions
 confir-0.124
 contro-0.119
 discharge-0.116
 corpor-0.115
 Jude-0.114
Token had
Token ID550
Feature activation+2.40e-01

Pos logit contributions
acs+0.069
 Gravity+0.068
assic+0.067
ikhail+0.067
Tokens+0.066
Neg logit contributions
 confir-0.062
 contro-0.059
 discharge-0.058
 corpor-0.057
 Jude-0.057
Token said
Token ID531
Feature activation-5.59e-02

Pos logit contributions
acs+0.459
 Gravity+0.450
assic+0.447
ikhail+0.445
Tokens+0.437
Neg logit contributions
 confir-0.391
 contro-0.372
 discharge-0.362
 corpor-0.357
 Jude-0.356
Token,
Token ID11
Feature activation-2.84e-02

Pos logit contributions
 confir+0.086
 contro+0.082
 discharge+0.079
 corpor+0.078
 Jude+0.078
Neg logit contributions
acs-0.112
 Gravity-0.110
assic-0.109
ikhail-0.109
Tokens-0.107
Token "
Token ID366
Feature activation-8.17e-02

Pos logit contributions
 confir+0.040
 contro+0.038
 discharge+0.037
 corpor+0.036
 Jude+0.036
Neg logit contributions
acs-0.060
 Gravity-0.059
assic-0.059
ikhail-0.059
Tokens-0.058
TokenHow
Token ID2437
Feature activation-7.00e-02

Pos logit contributions
 confir+0.150
 contro+0.144
 discharge+0.141
 corpor+0.139
 Jude+0.139
Neg logit contributions
acs-0.139
 Gravity-0.135
assic-0.135
ikhail-0.134
Tokens-0.131
Tokencum
Token ID36340
Feature activation+1.27e+00

Pos logit contributions
 confir+0.118
 contro+0.112
 discharge+0.109
 corpor+0.108
 Jude+0.107
Neg logit contributions
acs-0.130
 Gravity-0.127
assic-0.127
ikhail-0.126
Tokens-0.124
Token nobody
Token ID8168
Feature activation-7.79e-02

Pos logit contributions
acs+2.467
 Gravity+2.406
assic+2.379
ikhail+2.373
ochem+2.308
Neg logit contributions
 confir-2.014
 contro-1.904
 discharge-1.846
 Jude-1.819
 corpor-1.819
Token just
Token ID655
Feature activation+1.00e-01

Pos logit contributions
 confir+0.131
 contro+0.123
 discharge+0.121
 corpor+0.119
 Jude+0.119
Neg logit contributions
acs-0.145
 Gravity-0.143
assic-0.141
ikhail-0.140
Tokens-0.137
Token does
Token ID857
Feature activation-1.09e-01

Pos logit contributions
acs+0.189
 Gravity+0.186
assic+0.184
ikhail+0.182
Tokens+0.179
Neg logit contributions
 confir-0.166
 contro-0.157
 discharge-0.154
 corpor-0.152
 Jude-0.151
Token simple
Token ID2829
Feature activation+2.03e-01

Pos logit contributions
 confir+0.168
 contro+0.159
 discharge+0.155
 corpor+0.152
 Jude+0.152
Neg logit contributions
acs-0.218
 Gravity-0.213
assic-0.212
ikhail-0.212
Tokens-0.208
Token stories
Token ID3923
Feature activation+1.56e-01

Pos logit contributions
acs+0.362
 Gravity+0.355
assic+0.352
ikhail+0.351
Tokens+0.344
Neg logit contributions
 confir-0.358
 contro-0.341
 discharge-0.333
 corpor-0.328
 Jude-0.328
Token a
Token ID257
Feature activation-1.47e-02

Pos logit contributions
 confir+0.126
 contro+0.120
 discharge+0.117
 corpor+0.115
 Jude+0.115
Neg logit contributions
acs-0.140
 Gravity-0.137
assic-0.136
ikhail-0.136
Tokens-0.133
Token little
Token ID1310
Feature activation+6.18e-02

Pos logit contributions
 confir+0.023
 contro+0.022
 discharge+0.021
 Jude+0.021
 corpor+0.021
Neg logit contributions
acs-0.029
 Gravity-0.028
ikhail-0.028
assic-0.028
Tokens-0.027
Token-
Token ID12
Feature activation-6.56e-02

Pos logit contributions
acs+0.114
 Gravity+0.111
assic+0.111
ikhail+0.110
Tokens+0.108
Neg logit contributions
 confir-0.105
 contro-0.100
 discharge-0.097
 corpor-0.096
 Jude-0.096
Tokenknown
Token ID4002
Feature activation-4.95e-01

Pos logit contributions
 confir+0.099
 contro+0.093
 discharge+0.091
 Jude+0.089
 corpor+0.089
Neg logit contributions
acs-0.135
 Gravity-0.130
assic-0.130
ikhail-0.130
Tokens-0.128
Token hedge
Token ID19859
Feature activation+4.17e-01

Pos logit contributions
 confir+0.816
 contro+0.780
 discharge+0.759
 corpor+0.752
 Jude+0.747
Neg logit contributions
acs-0.936
 Gravity-0.914
assic-0.912
ikhail-0.908
Tokens-0.891
Token fund
Token ID1814
Feature activation+1.17e+00

Pos logit contributions
acs+0.678
 Gravity+0.661
assic+0.657
ikhail+0.655
Tokens+0.640
Neg logit contributions
 confir-0.799
 contro-0.765
 discharge-0.749
 corpor-0.741
 Jude-0.738
Token manager
Token ID4706
Feature activation+4.56e-01

Pos logit contributions
acs+2.369
 Gravity+2.327
ikhail+2.322
assic+2.297
ochem+2.253
Neg logit contributions
 confir-1.741
 contro-1.641
 discharge-1.577
 Jude-1.573
 cumulative-1.551
Token who
Token ID508
Feature activation-2.12e-01

Pos logit contributions
acs+0.915
 Gravity+0.897
ikhail+0.890
assic+0.887
Tokens+0.870
Neg logit contributions
 confir-0.701
 contro-0.660
 discharge-0.643
 Jude-0.632
 corpor-0.629
Token crossed
Token ID12606
Feature activation+5.45e-01

Pos logit contributions
 confir+0.379
 contro+0.364
 discharge+0.355
 corpor+0.352
 Jude+0.350
Neg logit contributions
acs-0.370
 Gravity-0.361
assic-0.360
ikhail-0.360
Tokens-0.352
Token Goldman
Token ID18740
Feature activation+3.02e-01

Pos logit contributions
acs+1.062
 Gravity+1.039
assic+1.034
ikhail+1.031
Tokens+1.012
Neg logit contributions
 confir-0.867
 contro-0.825
 discharge-0.803
 corpor-0.792
 Jude-0.789
Token
Token ID447
Feature activation+3.70e-02

Pos logit contributions
acs+0.555
 Gravity+0.543
assic+0.540
ikhail+0.538
Tokens+0.528
Neg logit contributions
 confir-0.513
 contro-0.489
 discharge-0.476
 corpor-0.470
 Jude-0.469
Token.
Token ID13
Feature activation+1.24e-02

Pos logit contributions
 confir+0.028
 contro+0.026
 discharge+0.026
 corpor+0.025
 Jude+0.025
Neg logit contributions
acs-0.035
 Gravity-0.034
assic-0.034
ikhail-0.034
Tokens-0.033
Token When
Token ID1649
Feature activation+1.57e-01

Pos logit contributions
acs+0.022
 Gravity+0.021
assic+0.021
ikhail+0.021
Tokens+0.021
Neg logit contributions
 confir-0.022
 contro-0.021
 discharge-0.021
 corpor-0.020
 cumulative-0.020
Token Trump
Token ID1301
Feature activation+4.67e-03

Pos logit contributions
acs+0.301
 Gravity+0.295
assic+0.292
ikhail+0.292
Tokens+0.287
Neg logit contributions
 confir-0.253
 contro-0.241
 discharge-0.234
 corpor-0.231
 Jude-0.230
Token named
Token ID3706
Feature activation+4.54e-02

Pos logit contributions
acs+0.009
 Gravity+0.009
ikhail+0.009
assic+0.009
Tokens+0.008
Neg logit contributions
 confir-0.008
 contro-0.007
 discharge-0.007
 corpor-0.007
 Jude-0.007
Token his
Token ID465
Feature activation+1.81e-01

Pos logit contributions
acs+0.078
 Gravity+0.076
assic+0.076
ikhail+0.076
Tokens+0.074
Neg logit contributions
 confir-0.082
 contro-0.079
 discharge-0.077
 corpor-0.076
 Jude-0.076
Token vice
Token ID7927
Feature activation+1.16e+00

Pos logit contributions
acs+0.355
 Gravity+0.349
assic+0.345
ikhail+0.345
Tokens+0.338
Neg logit contributions
 confir-0.287
 contro-0.272
 discharge-0.264
 corpor-0.260
 Jude-0.260
Token presidential
Token ID4787
Feature activation+3.11e-01

Pos logit contributions
acs+1.795
 Gravity+1.739
assic+1.727
ikhail+1.723
Tokens+1.682
Neg logit contributions
 confir-2.310
 contro-2.220
 discharge-2.166
 Jude-2.136
 corpor-2.135
Token pick
Token ID2298
Feature activation+1.94e-02

Pos logit contributions
acs+0.586
 Gravity+0.575
ikhail+0.572
assic+0.572
Tokens+0.560
Neg logit contributions
 confir-0.509
 contro-0.481
 discharge-0.465
 Jude-0.461
 corpor-0.461
Token,
Token ID11
Feature activation-5.80e-02

Pos logit contributions
acs+0.037
 Gravity+0.037
assic+0.036
ikhail+0.036
Tokens+0.036
Neg logit contributions
 confir-0.031
 contro-0.030
 discharge-0.029
 corpor-0.029
 Jude-0.028
Token Gov
Token ID10964
Feature activation-1.01e-01

Pos logit contributions
 confir+0.109
 contro+0.104
 discharge+0.102
 corpor+0.100
 Jude+0.100
Neg logit contributions
acs-0.096
 Gravity-0.094
assic-0.093
ikhail-0.093
Tokens-0.091
Token.
Token ID13
Feature activation-5.20e-02

Pos logit contributions
 confir+0.145
 contro+0.137
 discharge+0.133
 corpor+0.131
 Jude+0.131
Neg logit contributions
acs-0.211
 Gravity-0.207
assic-0.206
ikhail-0.205
Tokens-0.202
Token with
Token ID351
Feature activation-7.12e-03

Pos logit contributions
 confir+0.139
 contro+0.133
 discharge+0.129
 corpor+0.128
 Jude+0.127
Neg logit contributions
acs-0.155
 Gravity-0.152
assic-0.151
ikhail-0.151
Tokens-0.148
Token sect
Token ID15951
Feature activation-4.61e-01

Pos logit contributions
 confir+0.012
 contro+0.011
 discharge+0.011
 Jude+0.011
 corpor+0.011
Neg logit contributions
acs-0.013
 Gravity-0.013
assic-0.013
ikhail-0.013
Tokens-0.013
Tokenarians
Token ID13517
Feature activation-1.16e-01

Pos logit contributions
 confir+0.867
 contro+0.838
 discharge+0.817
 corpor+0.812
 Jude+0.808
Neg logit contributions
acs-0.753
 Gravity-0.741
assic-0.735
ikhail-0.734
Tokens-0.717
Token and
Token ID290
Feature activation-3.85e-02

Pos logit contributions
 confir+0.194
 contro+0.186
 discharge+0.181
 corpor+0.179
 Jude+0.177
Neg logit contributions
acs-0.216
 Gravity-0.212
assic-0.211
ikhail-0.211
Tokens-0.207
Token qu
Token ID627
Feature activation-1.18e-01

Pos logit contributions
 confir+0.064
 contro+0.061
 discharge+0.059
 corpor+0.059
 Jude+0.059
Neg logit contributions
acs-0.072
 Gravity-0.071
assic-0.070
ikhail-0.070
Tokens-0.069
Tokenacks
Token ID4595
Feature activation+1.12e+00

Pos logit contributions
 confir+0.247
 contro+0.238
 discharge+0.234
 corpor+0.231
 Jude+0.231
Neg logit contributions
acs-0.169
 Gravity-0.164
assic-0.163
ikhail-0.163
Tokens-0.158
Token could
Token ID714
Feature activation-1.03e-01

Pos logit contributions
acs+2.086
 Gravity+2.026
assic+2.018
ikhail+2.009
Tokens+1.964
Neg logit contributions
 confir-1.888
 contro-1.783
 discharge-1.745
 Jude-1.723
 cumulative-1.717
Token not
Token ID407
Feature activation+4.56e-02

Pos logit contributions
 confir+0.173
 contro+0.165
 discharge+0.161
 corpor+0.159
 Jude+0.159
Neg logit contributions
acs-0.192
 Gravity-0.188
assic-0.187
ikhail-0.186
Tokens-0.183
Token support
Token ID1104
Feature activation+8.62e-03

Pos logit contributions
acs+0.082
 Gravity+0.080
assic+0.079
ikhail+0.079
Tokens+0.077
Neg logit contributions
 confir-0.080
 contro-0.076
 discharge-0.074
 corpor-0.073
 Jude-0.073
Token an
Token ID281
Feature activation+3.16e-01

Pos logit contributions
acs+0.016
 Gravity+0.016
assic+0.015
ikhail+0.015
Tokens+0.015
Neg logit contributions
 confir-0.015
 contro-0.014
 discharge-0.014
 corpor-0.013
 Jude-0.013
Token influx
Token ID25065
Feature activation-4.57e-01

Pos logit contributions
acs+0.592
 Gravity+0.578
assic+0.576
ikhail+0.573
Tokens+0.562
Neg logit contributions
 confir-0.527
 contro-0.499
 discharge-0.487
 corpor-0.480
 Jude-0.480
Token the
Token ID262
Feature activation-8.94e-02

Pos logit contributions
acs+0.065
 Gravity+0.063
assic+0.063
ikhail+0.062
Tokens+0.062
Neg logit contributions
 confir-0.050
 contro-0.048
 discharge-0.046
 corpor-0.046
 Jude-0.046
Token office
Token ID2607
Feature activation+1.03e-02

Pos logit contributions
 confir+0.113
 contro+0.105
 discharge+0.100
 Jude+0.099
 corpor+0.099
Neg logit contributions
acs-0.204
 Gravity-0.201
assic-0.198
ikhail-0.197
Tokens-0.194
Token said
Token ID531
Feature activation-3.52e-02

Pos logit contributions
acs+0.020
 Gravity+0.020
assic+0.020
ikhail+0.020
Tokens+0.019
Neg logit contributions
 confir-0.016
 contro-0.015
 discharge-0.015
 Jude-0.015
 corpor-0.015
Token in
Token ID287
Feature activation-6.16e-02

Pos logit contributions
 confir+0.051
 contro+0.048
 discharge+0.046
 Jude+0.046
 corpor+0.046
Neg logit contributions
acs-0.074
 Gravity-0.072
assic-0.071
ikhail-0.071
Tokens-0.070
Token a
Token ID257
Feature activation-1.18e-01

Pos logit contributions
 confir+0.100
 contro+0.095
 discharge+0.092
 corpor+0.091
 Jude+0.091
Neg logit contributions
acs-0.118
 Gravity-0.116
assic-0.115
ikhail-0.114
Tokens-0.112
Token draft
Token ID4538
Feature activation+1.12e+00

Pos logit contributions
 confir+0.185
 contro+0.175
 corpor+0.167
 discharge+0.166
 Jude+0.166
Neg logit contributions
acs-0.231
 Gravity-0.229
ikhail-0.224
assic-0.223
Tokens-0.219
Token Strategic
Token ID24999
Feature activation+2.11e-01

Pos logit contributions
 Gravity+2.323
acs+2.311
assic+2.253
ikhail+2.229
Tokens+2.217
Neg logit contributions
 confir-1.573
 contro-1.491
 Jude-1.408
 corpor-1.406
 discharge-1.365
Token Plan
Token ID5224
Feature activation-3.60e-01

Pos logit contributions
acs+0.362
 Gravity+0.360
assic+0.349
ikhail+0.347
Tokens+0.345
Neg logit contributions
 confir-0.385
 contro-0.366
 corpor-0.350
 discharge-0.349
 cumulative-0.346
Token released
Token ID2716
Feature activation+7.10e-02

Pos logit contributions
 confir+0.547
 contro+0.520
 discharge+0.501
 corpor+0.496
 Jude+0.496
Neg logit contributions
acs-0.728
 Gravity-0.714
assic-0.708
ikhail-0.706
Tokens-0.695
Token last
Token ID938
Feature activation-3.86e-01

Pos logit contributions
acs+0.149
 Gravity+0.146
assic+0.144
ikhail+0.144
Tokens+0.142
Neg logit contributions
 confir-0.103
 contro-0.097
 discharge-0.094
 corpor-0.092
 Jude-0.092
Token week
Token ID1285
Feature activation-5.95e-02

Pos logit contributions
 confir+0.548
 contro+0.518
 discharge+0.503
 corpor+0.495
 Jude+0.493
Neg logit contributions
acs-0.818
 Gravity-0.801
assic-0.799
ikhail-0.798
Tokens-0.783
Token been
Token ID587
Feature activation-1.14e-01

Pos logit contributions
 confir+0.062
 contro+0.057
 discharge+0.056
 Jude+0.056
 corpor+0.055
Neg logit contributions
acs-0.072
 Gravity-0.071
assic-0.070
ikhail-0.070
Tokens-0.068
Token trained
Token ID8776
Feature activation-4.61e-02

Pos logit contributions
 confir+0.156
 contro+0.145
 discharge+0.141
 Jude+0.139
 cumulative+0.138
Neg logit contributions
acs-0.246
 Gravity-0.242
assic-0.239
ikhail-0.238
Tokens-0.234
Token to
Token ID284
Feature activation-9.42e-02

Pos logit contributions
 confir+0.071
 contro+0.067
 discharge+0.066
 Jude+0.065
 corpor+0.064
Neg logit contributions
acs-0.092
 Gravity-0.090
assic-0.089
ikhail-0.089
Tokens-0.088
Token navigate
Token ID16500
Feature activation+1.74e-01

Pos logit contributions
 confir+0.144
 contro+0.134
 discharge+0.130
 Jude+0.130
 corpor+0.129
Neg logit contributions
acs-0.190
 Gravity-0.187
assic-0.184
ikhail-0.183
Tokens-0.180
Token a
Token ID257
Feature activation-1.04e-01

Pos logit contributions
acs+0.335
 Gravity+0.329
ikhail+0.322
assic+0.322
Tokens+0.318
Neg logit contributions
 confir-0.284
 contro-0.264
 discharge-0.258
 Jude-0.255
 corpor-0.253
Token wheelchair
Token ID27181
Feature activation+1.11e+00

Pos logit contributions
 confir+0.157
 contro+0.146
 discharge+0.142
 Jude+0.141
 corpor+0.139
Neg logit contributions
acs-0.212
 Gravity-0.209
ikhail-0.206
assic-0.205
 Mov-0.201
Token through
Token ID832
Feature activation-1.78e-01

Pos logit contributions
acs+2.093
 Gravity+2.051
ikhail+1.999
assic+1.978
Tokens+1.966
Neg logit contributions
 confir-1.853
 contro-1.689
 Jude-1.668
 cumulative-1.652
 discharge-1.648
Token a
Token ID257
Feature activation-8.30e-02

Pos logit contributions
 confir+0.286
 contro+0.269
 discharge+0.262
 corpor+0.258
 Jude+0.258
Neg logit contributions
acs-0.344
 Gravity-0.339
assic-0.334
ikhail-0.334
Tokens-0.328
Token maze
Token ID31237
Feature activation+1.69e-01

Pos logit contributions
 confir+0.125
 contro+0.116
 discharge+0.113
 Jude+0.112
 corpor+0.112
Neg logit contributions
acs-0.168
 Gravity-0.166
assic-0.163
ikhail-0.163
 Mov-0.160
Token and
Token ID290
Feature activation-3.52e-02

Pos logit contributions
acs+0.330
 Gravity+0.324
ikhail+0.319
assic+0.318
Tokens+0.312
Neg logit contributions
 confir-0.270
 contro-0.251
 discharge-0.245
 Jude-0.244
 corpor-0.241
Token have
Token ID423
Feature activation-4.33e-02

Pos logit contributions
 confir+0.055
 contro+0.051
 discharge+0.050
 Jude+0.050
 corpor+0.049
Neg logit contributions
acs-0.070
 Gravity-0.069
assic-0.068
ikhail-0.067
Tokens-0.066
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
acs+0.336
 Gravity+0.331
ikhail+0.327
assic+0.327
Tokens+0.322
Neg logit contributions
 confir-0.221
 contro-0.207
 discharge-0.201
 corpor-0.197
 cumulative-0.195
Token
Token ID198
Feature activation+9.46e-02

Pos logit contributions
acs+0.327
 Gravity+0.321
ikhail+0.316
assic+0.315
Tokens+0.315
Neg logit contributions
 confir-0.201
 contro-0.179
 discharge-0.173
 corpor-0.171
 cumulative-0.169
TokenRead
Token ID5569
Feature activation+2.42e-01

Pos logit contributions
acs+0.163
 Gravity+0.160
assic+0.159
ikhail+0.158
Tokens+0.154
Neg logit contributions
 confir-0.171
 contro-0.164
 discharge-0.160
 corpor-0.158
 Jude-0.158
Token more
Token ID517
Feature activation+5.38e-02

Pos logit contributions
acs+0.438
 Gravity+0.428
assic+0.425
ikhail+0.425
Tokens+0.416
Neg logit contributions
 confir-0.420
 contro-0.400
 discharge-0.390
 corpor-0.385
 Jude-0.384
Token about
Token ID546
Feature activation+1.09e-01

Pos logit contributions
acs+0.111
 Gravity+0.109
assic+0.108
ikhail+0.108
Tokens+0.106
Neg logit contributions
 confir-0.079
 contro-0.075
 discharge-0.073
 corpor-0.072
 Jude-0.071
Token Sud
Token ID14818
Feature activation+1.11e+00

Pos logit contributions
acs+0.194
 Gravity+0.191
assic+0.189
ikhail+0.189
Tokens+0.184
Neg logit contributions
 confir-0.193
 contro-0.184
 discharge-0.180
 corpor-0.177
 Jude-0.177
Tokenh
Token ID71
Feature activation+8.89e-02

Pos logit contributions
acs+1.839
 Gravity+1.789
ikhail+1.782
assic+1.781
Tokens+1.726
Neg logit contributions
 confir-2.085
 contro-1.996
 discharge-1.944
 corpor-1.925
 Jude-1.913
Tokenir
Token ID343
Feature activation-3.43e-01

Pos logit contributions
acs+0.161
 Gravity+0.157
assic+0.156
ikhail+0.156
Tokens+0.153
Neg logit contributions
 confir-0.153
 contro-0.147
 discharge-0.143
 corpor-0.141
 Jude-0.141
Token Ch
Token ID609
Feature activation+2.90e-01

Pos logit contributions
 confir+0.571
 contro+0.544
 discharge+0.530
 corpor+0.524
 Jude+0.522
Neg logit contributions
acs-0.643
 Gravity-0.629
assic-0.627
ikhail-0.625
Tokens-0.614
Tokenoud
Token ID2778
Feature activation-4.84e-02

Pos logit contributions
acs+0.514
 Gravity+0.499
assic+0.499
ikhail+0.498
Tokens+0.486
Neg logit contributions
 confir-0.518
 contro-0.492
 discharge-0.480
 corpor-0.475
 Jude-0.473
Tokenh
Token ID71
Feature activation+1.12e-01

Pos logit contributions
 confir+0.091
 contro+0.086
 discharge+0.084
 corpor+0.084
 Jude+0.083
Neg logit contributions
acs-0.082
 Gravity-0.079
assic-0.079
ikhail-0.079
Tokens-0.077
Token speeches
Token ID18138
Feature activation+1.01e-01

Pos logit contributions
acs+0.257
 Gravity+0.252
assic+0.251
ikhail+0.250
Tokens+0.246
Neg logit contributions
 confir-0.196
 contro-0.186
 discharge-0.180
 corpor-0.178
 Jude-0.177
Token.
Token ID13
Feature activation-6.79e-02

Pos logit contributions
acs+0.204
 Gravity+0.200
assic+0.198
ikhail+0.198
Tokens+0.194
Neg logit contributions
 confir-0.153
 contro-0.145
 discharge-0.140
 corpor-0.138
 Jude-0.138
Token
Token ID198
Feature activation+1.60e-02

Pos logit contributions
 confir+0.087
 contro+0.082
 discharge+0.079
 corpor+0.078
 Jude+0.077
Neg logit contributions
acs-0.153
 Gravity-0.151
assic-0.150
ikhail-0.150
Tokens-0.147
Token
Token ID198
Feature activation-3.10e-03

Pos logit contributions
acs+0.036
 Gravity+0.036
ikhail+0.035
assic+0.035
Tokens+0.035
Neg logit contributions
 confir-0.022
 contro-0.019
 discharge-0.019
 corpor-0.019
 cumulative-0.018
TokenNewsletter
Token ID33031
Feature activation+2.18e-01

Pos logit contributions
 confir+0.005
 contro+0.005
 discharge+0.005
 corpor+0.005
 Jude+0.005
Neg logit contributions
acs-0.006
 Gravity-0.006
assic-0.006
ikhail-0.006
Tokens-0.006
Token Sign
Token ID5865
Feature activation+1.10e+00

Pos logit contributions
acs+0.411
 Gravity+0.404
ikhail+0.398
assic+0.395
Tokens+0.389
Neg logit contributions
 confir-0.368
 contro-0.344
 discharge-0.337
 corpor-0.331
 cumulative-0.330
Token Up
Token ID3205
Feature activation+1.00e-01

Pos logit contributions
acs+0.899
 Gravity+0.859
ikhail+0.812
assic+0.808
Tokens+0.794
Neg logit contributions
 confir-3.063
 contro-2.927
 discharge-2.885
 corpor-2.859
 cumulative-2.840
Token Continue
Token ID10054
Feature activation+4.79e-01

Pos logit contributions
acs+0.120
 Gravity+0.118
ikhail+0.115
assic+0.114
Tokens+0.112
Neg logit contributions
 confir-0.236
 contro-0.226
 discharge-0.221
 corpor-0.221
 cumulative-0.219
Token reading
Token ID3555
Feature activation+3.96e-02

Pos logit contributions
acs+0.685
 Gravity+0.675
ikhail+0.653
assic+0.653
Tokens+0.635
Neg logit contributions
 confir-1.020
 contro-0.955
 discharge-0.937
 corpor-0.934
 Jude-0.926
Token the
Token ID262
Feature activation-1.23e-02

Pos logit contributions
acs+0.079
 Gravity+0.078
ikhail+0.077
assic+0.077
Tokens+0.076
Neg logit contributions
 confir-0.063
 contro-0.058
 discharge-0.056
 corpor-0.055
 Jude-0.055
Token main
Token ID1388
Feature activation+3.58e-01

Pos logit contributions
 confir+0.019
 contro+0.018
 discharge+0.017
 corpor+0.017
 Jude+0.017
Neg logit contributions
acs-0.025
 Gravity-0.024
assic-0.024
ikhail-0.024
Tokens-0.024
Token,
Token ID11
Feature activation+9.24e-02

Pos logit contributions
acs+0.271
 Gravity+0.265
assic+0.263
ikhail+0.263
Tokens+0.258
Neg logit contributions
 confir-0.226
 contro-0.214
 discharge-0.209
 corpor-0.206
 Jude-0.205
Token broadcast
Token ID7025
Feature activation+2.06e-01

Pos logit contributions
acs+0.176
 Gravity+0.173
ikhail+0.169
assic+0.167
Bro+0.166
Neg logit contributions
 confir-0.153
 contro-0.137
 Jude-0.137
 cumulative-0.133
 discharge-0.132
Token,
Token ID11
Feature activation+1.10e-01

Pos logit contributions
acs+0.403
 Gravity+0.394
assic+0.392
ikhail+0.392
Tokens+0.384
Neg logit contributions
 confir-0.325
 contro-0.310
 discharge-0.302
 corpor-0.298
 Jude-0.297
Token rewritten
Token ID30101
Feature activation-3.36e-01

Pos logit contributions
acs+0.235
 Gravity+0.233
ikhail+0.230
assic+0.229
Tokens+0.225
Neg logit contributions
 confir-0.154
 contro-0.141
 discharge-0.136
 Jude-0.135
 cumulative-0.133
Token or
Token ID393
Feature activation+9.21e-02

Pos logit contributions
 confir+0.502
 contro+0.486
 discharge+0.474
 corpor+0.468
 cumulative+0.461
Neg logit contributions
acs-0.675
 Gravity-0.664
ikhail-0.662
assic-0.662
Tokens-0.650
Token redistributed
Token ID38913
Feature activation+1.09e+00

Pos logit contributions
acs+0.131
 Gravity+0.128
assic+0.126
ikhail+0.125
Tokens+0.123
Neg logit contributions
 confir-0.196
 contro-0.187
 discharge-0.183
 Jude-0.181
 corpor-0.180
Token.)
Token ID2014
Feature activation+2.55e-01

Pos logit contributions
acs+1.929
 Gravity+1.876
ikhail+1.858
assic+1.849
ochem+1.805
Neg logit contributions
 confir-1.934
 contro-1.825
 discharge-1.777
 corpor-1.756
 Jude-1.755
Token<|endoftext|>
Token ID50256
Feature activation+2.25e-04

Pos logit contributions
acs+0.554
 Gravity+0.543
assic+0.541
ikhail+0.540
Tokens+0.531
Neg logit contributions
 confir-0.348
 contro-0.328
 discharge-0.317
 corpor-0.312
 Jude-0.311
TokenNew
Token ID3791
Feature activation+2.50e-01

Pos logit contributions
acs+0.000
 Gravity+0.000
assic+0.000
ikhail+0.000
Tokens+0.000
Neg logit contributions
 confir-0.000
 contro-0.000
 discharge-0.000
 corpor-0.000
 Jude-0.000
Tokencastle
Token ID18676
Feature activation-1.97e-01

Pos logit contributions
acs+0.402
 Gravity+0.391
assic+0.389
ikhail+0.388
Tokens+0.379
Neg logit contributions
 confir-0.484
 contro-0.464
 discharge-0.454
 corpor-0.449
 Jude-0.448
Token United
Token ID1578
Feature activation+3.64e-01

Pos logit contributions
 confir+0.357
 contro+0.341
 discharge+0.333
 corpor+0.329
 Jude+0.328
Neg logit contributions
acs-0.342
 Gravity-0.334
assic-0.332
ikhail-0.331
Tokens-0.324
Token be
Token ID307
Feature activation+9.48e-02

Pos logit contributions
 confir+0.271
 contro+0.257
 discharge+0.249
 corpor+0.247
 Jude+0.247
Neg logit contributions
acs-0.329
 Gravity-0.322
assic-0.319
ikhail-0.318
Tokens-0.313
Token chosen
Token ID7147
Feature activation+2.25e-02

Pos logit contributions
acs+0.187
 Gravity+0.183
assic+0.182
ikhail+0.181
Tokens+0.178
Neg logit contributions
 confir-0.148
 contro-0.140
 discharge-0.137
 corpor-0.135
 Jude-0.134
Token as
Token ID355
Feature activation-1.98e-01

Pos logit contributions
acs+0.045
 Gravity+0.044
assic+0.044
ikhail+0.044
Tokens+0.043
Neg logit contributions
 confir-0.035
 contro-0.033
 discharge-0.032
 corpor-0.032
 Jude-0.031
Token Romney
Token ID8431
Feature activation-1.85e-02

Pos logit contributions
 confir+0.314
 contro+0.299
 discharge+0.291
 corpor+0.287
 Jude+0.286
Neg logit contributions
acs-0.386
 Gravity-0.378
assic-0.377
ikhail-0.376
Tokens-0.368
Token's
Token ID338
Feature activation-1.71e-01

Pos logit contributions
 confir+0.032
 contro+0.031
 discharge+0.030
 corpor+0.029
 Jude+0.029
Neg logit contributions
acs-0.034
 Gravity-0.033
assic-0.033
ikhail-0.033
Tokens-0.032
Token vice
Token ID7927
Feature activation+1.08e+00

Pos logit contributions
 confir+0.304
 contro+0.290
 discharge+0.283
 corpor+0.279
 Jude+0.279
Neg logit contributions
acs-0.302
 Gravity-0.296
assic-0.293
ikhail-0.293
Tokens-0.287
Token presidential
Token ID4787
Feature activation+3.35e-01

Pos logit contributions
acs+1.555
 Gravity+1.506
assic+1.486
ikhail+1.483
Tokens+1.441
Neg logit contributions
 confir-2.252
 contro-2.159
 discharge-2.106
 corpor-2.081
 Jude-2.081
Token candidate
Token ID4540
Feature activation+1.75e-01

Pos logit contributions
acs+0.611
 Gravity+0.601
assic+0.595
ikhail+0.593
Tokens+0.582
Neg logit contributions
 confir-0.570
 contro-0.538
 discharge-0.519
 Jude-0.516
 corpor-0.516
Token.
Token ID13
Feature activation-3.12e-02

Pos logit contributions
acs+0.350
 Gravity+0.344
ikhail+0.340
assic+0.339
Tokens+0.334
Neg logit contributions
 confir-0.270
 contro-0.254
 discharge-0.247
 corpor-0.244
 Jude-0.242
Token
Token ID198
Feature activation-1.65e-02

Pos logit contributions
 confir+0.044
 contro+0.041
 discharge+0.040
 corpor+0.039
 Jude+0.039
Neg logit contributions
acs-0.067
 Gravity-0.066
assic-0.065
ikhail-0.065
Tokens-0.064
Token
Token ID198
Feature activation-4.34e-02

Pos logit contributions
 confir+0.022
 contro+0.020
 discharge+0.019
 corpor+0.019
 cumulative+0.019
Neg logit contributions
acs-0.037
 Gravity-0.037
ikhail-0.036
assic-0.036
Tokens-0.036
Token,
Token ID11
Feature activation-5.89e-02

Pos logit contributions
 confir+0.309
 contro+0.292
 discharge+0.285
 corpor+0.281
 Jude+0.280
Neg logit contributions
acs-0.397
 Gravity-0.388
assic-0.386
ikhail-0.386
Tokens-0.378
Token Ma
Token ID6669
Feature activation+3.23e-01

Pos logit contributions
 confir+0.102
 contro+0.096
 discharge+0.095
 corpor+0.093
 Jude+0.093
Neg logit contributions
acs-0.106
 Gravity-0.104
ikhail-0.103
assic-0.103
Tokens-0.100
Tokenurer
Token ID15051
Feature activation+2.27e-01

Pos logit contributions
acs+0.604
 Gravity+0.591
assic+0.588
ikhail+0.586
Tokens+0.575
Neg logit contributions
 confir-0.541
 contro-0.515
 discharge-0.502
 corpor-0.495
 Jude-0.494
Token and
Token ID290
Feature activation-6.37e-02

Pos logit contributions
acs+0.435
 Gravity+0.426
assic+0.423
ikhail+0.422
Tokens+0.414
Neg logit contributions
 confir-0.368
 contro-0.349
 discharge-0.340
 corpor-0.336
 Jude-0.335
Token Qu
Token ID2264
Feature activation-2.28e-01

Pos logit contributions
 confir+0.098
 contro+0.093
 discharge+0.090
 corpor+0.089
 Jude+0.089
Neg logit contributions
acs-0.127
 Gravity-0.125
ikhail-0.124
assic-0.123
Tokens-0.121
Tokenack
Token ID441
Feature activation+1.08e+00

Pos logit contributions
 confir+0.452
 contro+0.438
 discharge+0.430
 corpor+0.424
 Jude+0.423
Neg logit contributions
acs-0.348
 Gravity-0.342
assic-0.337
ikhail-0.337
Tokens-0.331
Tokenen
Token ID268
Feature activation-4.49e-02

Pos logit contributions
acs+1.530
assic+1.462
 Gravity+1.455
ikhail+1.439
ochem+1.403
Neg logit contributions
 confir-2.345
 contro-2.209
 discharge-2.152
 Jude-2.140
 corpor-2.137
Tokenbush
Token ID50231
Feature activation-3.96e-01

Pos logit contributions
 confir+0.059
 contro+0.054
 discharge+0.052
 corpor+0.052
 Jude+0.051
Neg logit contributions
acs-0.102
 Gravity-0.099
assic-0.099
ikhail-0.099
Tokens-0.097
Token,
Token ID11
Feature activation+6.91e-02

Pos logit contributions
 confir+0.621
 contro+0.590
 discharge+0.573
 corpor+0.566
 Jude+0.564
Neg logit contributions
acs-0.780
 Gravity-0.764
assic-0.760
ikhail-0.759
Tokens-0.745
Token to
Token ID284
Feature activation-5.06e-02

Pos logit contributions
acs+0.135
 Gravity+0.133
ikhail+0.131
assic+0.131
Tokens+0.128
Neg logit contributions
 confir-0.110
 contro-0.103
 discharge-0.101
 corpor-0.099
 Jude-0.099
Token Triple
Token ID19817
Feature activation+1.57e-02

Pos logit contributions
 confir+0.082
 contro+0.078
 discharge+0.076
 Jude+0.075
 corpor+0.075
Neg logit contributions
acs-0.096
 Gravity-0.095
assic-0.094
ikhail-0.094
Tokens-0.092
Token the
Token ID262
Feature activation-1.65e-03

Pos logit contributions
 confir+0.023
 contro+0.022
 discharge+0.021
 corpor+0.021
 Jude+0.021
Neg logit contributions
acs-0.028
assic-0.027
 Gravity-0.027
ikhail-0.027
Tokens-0.027
Token country
Token ID1499
Feature activation+2.03e-01

Pos logit contributions
 confir+0.003
 contro+0.002
 discharge+0.002
 corpor+0.002
 Jude+0.002
Neg logit contributions
acs-0.003
 Gravity-0.003
assic-0.003
ikhail-0.003
Tokens-0.003
Token knew
Token ID2993
Feature activation-1.40e-01

Pos logit contributions
acs+0.349
 Gravity+0.341
assic+0.337
ikhail+0.334
Tokens+0.328
Neg logit contributions
 confir-0.370
 contro-0.350
 discharge-0.343
 Jude-0.338
 corpor-0.338
Token who
Token ID508
Feature activation-2.03e-01

Pos logit contributions
 confir+0.211
 contro+0.200
 discharge+0.194
 corpor+0.191
 Jude+0.191
Neg logit contributions
acs-0.284
 Gravity-0.278
assic-0.277
ikhail-0.276
Tokens-0.271
Token the
Token ID262
Feature activation-2.12e-02

Pos logit contributions
 confir+0.311
 contro+0.296
 discharge+0.287
 corpor+0.284
 Jude+0.283
Neg logit contributions
acs-0.408
 Gravity-0.399
assic-0.398
ikhail-0.397
Tokens-0.390
Token Koch
Token ID17009
Feature activation+1.07e+00

Pos logit contributions
 confir+0.029
 contro+0.027
 discharge+0.026
 corpor+0.026
 Jude+0.026
Neg logit contributions
acs-0.046
 Gravity-0.045
assic-0.045
ikhail-0.045
Tokens-0.044
Token brothers
Token ID9397
Feature activation+6.77e-01

Pos logit contributions
acs+2.257
 Gravity+2.206
ikhail+2.187
assic+2.185
Tokens+2.147
Neg logit contributions
 confir-1.537
 contro-1.440
 discharge-1.400
 Jude-1.373
 corpor-1.370
Token are
Token ID389
Feature activation-3.32e-02

Pos logit contributions
acs+1.445
 Gravity+1.411
assic+1.401
ikhail+1.400
Tokens+1.378
Neg logit contributions
 confir-0.957
 contro-0.889
 discharge-0.860
 cumulative-0.848
 Jude-0.847
Token.
Token ID13
Feature activation+9.09e-03

Pos logit contributions
 confir+0.050
 contro+0.048
 discharge+0.046
 corpor+0.046
 Jude+0.046
Neg logit contributions
acs-0.067
 Gravity-0.066
assic-0.066
ikhail-0.065
Tokens-0.064
Token With
Token ID2080
Feature activation-1.85e-01

Pos logit contributions
acs+0.016
 Gravity+0.016
assic+0.016
ikhail+0.016
Tokens+0.016
Neg logit contributions
 confir-0.016
 contro-0.015
 discharge-0.015
 corpor-0.015
 cumulative-0.014
Token 25
Token ID1679
Feature activation-2.67e-02

Pos logit contributions
 confir+0.309
 contro+0.296
 discharge+0.288
 corpor+0.285
 Jude+0.284
Neg logit contributions
acs-0.346
 Gravity-0.338
assic-0.338
ikhail-0.337
Tokens-0.330
Token years
Token ID812
Feature activation+1.24e-01

Pos logit contributions
 confir+0.149
 contro+0.144
 discharge+0.141
 cumulative+0.139
 Jude+0.139
Neg logit contributions
acs-0.118
 Gravity-0.114
ikhail-0.113
assic-0.113
Tokens-0.111
Token.
Token ID13
Feature activation+7.60e-02

Pos logit contributions
acs+0.251
 Gravity+0.247
assic+0.245
ikhail+0.245
Tokens+0.240
Neg logit contributions
 confir-0.186
 contro-0.176
 discharge-0.171
 corpor-0.169
 Jude-0.168
Token<|endoftext|>
Token ID50256
Feature activation+8.02e-02

Pos logit contributions
acs+0.154
 Gravity+0.152
assic+0.150
ikhail+0.150
Tokens+0.147
Neg logit contributions
 confir-0.116
 contro-0.109
 discharge-0.106
 corpor-0.104
 cumulative-0.103
TokenImage
Token ID5159
Feature activation+4.93e-01

Pos logit contributions
acs+0.136
 Gravity+0.133
assic+0.133
ikhail+0.132
Tokens+0.129
Neg logit contributions
 confir-0.147
 contro-0.141
 discharge-0.137
 corpor-0.136
 Jude-0.136
Token copyright
Token ID6634
Feature activation+2.18e-01

Pos logit contributions
acs+0.582
 Gravity+0.563
assic+0.557
ikhail+0.556
Tokens+0.537
Neg logit contributions
 confir-1.160
 contro-1.121
 discharge-1.101
 corpor-1.090
 Jude-1.088
Token AFP
Token ID8916
Feature activation+1.06e+00

Pos logit contributions
acs+0.406
 Gravity+0.400
assic+0.396
ikhail+0.394
Tokens+0.386
Neg logit contributions
 confir-0.366
 contro-0.347
 discharge-0.339
 corpor-0.333
 cumulative-0.331
Token
Token ID198
Feature activation+1.76e-01

Pos logit contributions
acs+1.666
 Gravity+1.623
ikhail+1.609
assic+1.604
Tokens+1.562
Neg logit contributions
 confir-2.102
 contro-2.017
 discharge-1.971
 corpor-1.942
 cumulative-1.940
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
acs+0.396
 Gravity+0.391
ikhail+0.385
assic+0.384
Tokens+0.382
Neg logit contributions
 confir-0.237
 contro-0.213
 discharge-0.206
 corpor-0.202
 cumulative-0.201
TokenThe
Token ID464
Feature activation-9.02e-02

Pos logit contributions
acs+0.184
 Gravity+0.179
assic+0.178
ikhail+0.178
Tokens+0.173
Neg logit contributions
 confir-0.208
 contro-0.199
 discharge-0.195
 corpor-0.193
 Jude-0.193
Token Bank
Token ID5018
Feature activation-5.10e-03

Pos logit contributions
 confir+0.157
 contro+0.150
 discharge+0.146
 corpor+0.145
 Jude+0.144
Neg logit contributions
acs-0.162
 Gravity-0.158
assic-0.158
ikhail-0.157
Tokens-0.154
Token of
Token ID286
Feature activation+1.33e-02

Pos logit contributions
 confir+0.007
 contro+0.007
 discharge+0.007
 corpor+0.006
 Jude+0.006
Neg logit contributions
acs-0.011
 Gravity-0.011
assic-0.011
ikhail-0.011
Tokens-0.010
Token Chicago
Token ID4842
Feature activation-6.12e-02

Pos logit contributions
 confir+0.281
 contro+0.268
 discharge+0.262
 corpor+0.259
 Jude+0.258
Neg logit contributions
acs-0.304
 Gravity-0.297
assic-0.296
ikhail-0.295
Tokens-0.289
Token Bears
Token ID15682
Feature activation-2.67e-01

Pos logit contributions
 confir+0.105
 contro+0.101
 discharge+0.098
 corpor+0.097
 Jude+0.097
Neg logit contributions
acs-0.111
 Gravity-0.108
ikhail-0.108
assic-0.108
Tokens-0.106
Token have
Token ID423
Feature activation-3.30e-02

Pos logit contributions
 confir+0.409
 contro+0.388
 discharge+0.377
 corpor+0.372
 Jude+0.372
Neg logit contributions
acs-0.535
 Gravity-0.524
assic-0.519
ikhail-0.518
Tokens-0.510
Token blocked
Token ID10226
Feature activation+1.66e-01

Pos logit contributions
 confir+0.051
 contro+0.048
 discharge+0.047
 corpor+0.046
 Jude+0.046
Neg logit contributions
acs-0.066
 Gravity-0.065
assic-0.064
ikhail-0.064
Tokens-0.063
Token outside
Token ID2354
Feature activation+8.13e-02

Pos logit contributions
acs+0.314
 Gravity+0.309
assic+0.305
ikhail+0.305
Tokens+0.299
Neg logit contributions
 confir-0.273
 contro-0.259
 discharge-0.251
 corpor-0.248
 Jude-0.248
Token linebackers
Token ID43081
Feature activation+1.06e+00

Pos logit contributions
acs+0.164
 Gravity+0.161
assic+0.160
ikhail+0.160
Tokens+0.157
Neg logit contributions
 confir-0.124
 contro-0.117
 discharge-0.114
 corpor-0.113
 Jude-0.112
Token coach
Token ID3985
Feature activation+4.84e-01

Pos logit contributions
acs+1.952
 Gravity+1.921
ikhail+1.889
assic+1.869
 Mov+1.848
Neg logit contributions
 confir-1.795
 contro-1.710
 discharge-1.646
 corpor-1.621
 cumulative-1.616
Token Clint
Token ID21549
Feature activation+6.77e-02

Pos logit contributions
acs+0.836
 Gravity+0.821
assic+0.809
ikhail+0.809
Tokens+0.788
Neg logit contributions
 confir-0.881
 contro-0.837
 discharge-0.816
 corpor-0.805
 cumulative-0.802
Token Hur
Token ID10077
Feature activation-1.12e-01

Pos logit contributions
acs+0.119
 Gravity+0.116
assic+0.115
ikhail+0.115
Tokens+0.112
Neg logit contributions
 confir-0.122
 contro-0.116
 discharge-0.113
 corpor-0.111
 cumulative-0.111
Tokentt
Token ID926
Feature activation-4.83e-02

Pos logit contributions
 confir+0.202
 contro+0.194
 discharge+0.190
 corpor+0.187
 Jude+0.187
Neg logit contributions
acs-0.192
 Gravity-0.189
assic-0.188
ikhail-0.187
Tokens-0.183
Token from
Token ID422
Feature activation-1.89e-01

Pos logit contributions
 confir+0.075
 contro+0.072
 discharge+0.070
 corpor+0.069
 Jude+0.068
Neg logit contributions
acs-0.096
 Gravity-0.094
assic-0.093
ikhail-0.093
Tokens-0.091
Token Indiana
Token ID10278
Feature activation+1.38e-01

Pos logit contributions
 confir+0.204
 contro+0.197
 discharge+0.192
 Jude+0.191
 corpor+0.190
Neg logit contributions
acs-0.186
assic-0.181
 Gravity-0.180
ikhail-0.180
Tokens-0.176
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
acs+0.288
 Gravity+0.282
assic+0.281
ikhail+0.280
Tokens+0.275
Neg logit contributions
 confir-0.201
 contro-0.190
 discharge-0.184
 corpor-0.181
 Jude-0.181
Token<|endoftext|>
Token ID50256
Feature activation-1.48e-01

Pos logit contributions
acs+0.229
 Gravity+0.225
assic+0.223
ikhail+0.223
Tokens+0.219
Neg logit contributions
 confir-0.170
 contro-0.161
 discharge-0.157
 corpor-0.154
 Jude-0.154
TokenThe
Token ID464
Feature activation-1.50e-01

Pos logit contributions
 confir+0.269
 contro+0.258
 discharge+0.252
 corpor+0.249
 Jude+0.249
Neg logit contributions
acs-0.251
 Gravity-0.246
assic-0.244
ikhail-0.244
Tokens-0.237
Token Bengals
Token ID24037
Feature activation-6.11e-02

Pos logit contributions
 confir+0.254
 contro+0.243
 discharge+0.237
 corpor+0.234
 Jude+0.233
Neg logit contributions
acs-0.276
 Gravity-0.270
assic-0.268
ikhail-0.268
Tokens-0.263
Token signed
Token ID4488
Feature activation+1.06e+00

Pos logit contributions
 confir+0.094
 contro+0.089
 discharge+0.087
 corpor+0.086
 Jude+0.086
Neg logit contributions
acs-0.122
 Gravity-0.119
assic-0.118
ikhail-0.118
Tokens-0.116
Token kicker
Token ID38297
Feature activation+2.26e-01

Pos logit contributions
acs+2.008
 Gravity+1.994
ikhail+1.955
assic+1.944
 Mov+1.917
Neg logit contributions
 confir-1.711
 contro-1.586
 discharge-1.559
 corpor-1.525
 Jude-1.523
Token Jonathan
Token ID11232
Feature activation-5.97e-01

Pos logit contributions
acs+0.400
 Gravity+0.392
ikhail+0.387
assic+0.387
Tokens+0.377
Neg logit contributions
 confir-0.403
 contro-0.382
 discharge-0.372
 corpor-0.367
 cumulative-0.366
Token Brown
Token ID4373
Feature activation-6.90e-01

Pos logit contributions
 confir+1.010
 contro+0.973
 discharge+0.951
 Jude+0.944
 corpor+0.944
Neg logit contributions
acs-1.084
assic-1.060
ikhail-1.057
 Gravity-1.055
Tokens-1.037
Token,
Token ID11
Feature activation-4.17e-02

Pos logit contributions
 confir+1.069
 contro+1.014
 discharge+0.985
 corpor+0.972
 Jude+0.969
Neg logit contributions
acs-1.376
 Gravity-1.347
assic-1.341
ikhail-1.338
Tokens-1.313
Token far
Token ID1290
Feature activation+3.49e-01

Pos logit contributions
 confir+0.065
 contro+0.061
 discharge+0.059
 Jude+0.058
 corpor+0.058
Neg logit contributions
acs-0.083
 Gravity-0.081
ikhail-0.080
assic-0.080
Tokens-0.078
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
acs+0.035
assic+0.035
 Gravity+0.035
ikhail+0.034
Tokens+0.034
Neg logit contributions
 confir-0.026
 contro-0.025
 discharge-0.024
 corpor-0.024
 Jude-0.024
Token<|endoftext|>
Token ID50256
Feature activation-4.45e-02

Pos logit contributions
acs+0.255
 Gravity+0.250
assic+0.249
ikhail+0.249
Tokens+0.244
Neg logit contributions
 confir-0.162
 contro-0.153
 discharge-0.148
 Jude-0.146
 corpor-0.146
TokenMedia
Token ID13152
Feature activation-1.40e-02

Pos logit contributions
 confir+0.081
 contro+0.078
 discharge+0.076
 corpor+0.075
 Jude+0.075
Neg logit contributions
acs-0.076
 Gravity-0.074
assic-0.073
ikhail-0.073
Tokens-0.071
Token playback
Token ID16388
Feature activation+5.39e-01

Pos logit contributions
 confir+0.021
 contro+0.020
 discharge+0.019
 corpor+0.019
 Jude+0.019
Neg logit contributions
acs-0.029
 Gravity-0.028
assic-0.028
ikhail-0.028
Tokens-0.027
Token is
Token ID318
Feature activation+1.49e-01

Pos logit contributions
acs+0.959
 Gravity+0.948
assic+0.940
ikhail+0.934
Tokens+0.910
Neg logit contributions
 confir-0.964
 contro-0.896
 discharge-0.878
 corpor-0.865
 cumulative-0.860
Token unsupported
Token ID24222
Feature activation+1.05e+00

Pos logit contributions
acs+0.182
ikhail+0.175
assic+0.175
 Gravity+0.174
Tokens+0.170
Neg logit contributions
 confir-0.343
 contro-0.334
 discharge-0.326
 corpor-0.325
 Jude-0.324
Token on
Token ID319
Feature activation+1.56e-01

Pos logit contributions
acs+1.754
 Gravity+1.753
ikhail+1.692
assic+1.685
Tokens+1.665
Neg logit contributions
 confir-2.003
 contro-1.841
 discharge-1.809
 corpor-1.786
 Jude-1.782
Token your
Token ID534
Feature activation+3.59e-01

Pos logit contributions
acs+0.275
 Gravity+0.273
assic+0.268
ikhail+0.267
Tokens+0.261
Neg logit contributions
 confir-0.280
 contro-0.261
 discharge-0.255
 Jude-0.253
 corpor-0.252
Token device
Token ID3335
Feature activation+5.85e-01

Pos logit contributions
acs+0.789
 Gravity+0.787
ikhail+0.775
assic+0.773
 Mov+0.760
Neg logit contributions
 confir-0.485
 contro-0.436
 discharge-0.425
 Jude-0.423
 corpor-0.415
Token Media
Token ID6343
Feature activation+3.12e-02

Pos logit contributions
acs+1.064
 Gravity+1.063
ikhail+1.029
assic+1.025
 Mov+1.010
Neg logit contributions
 confir-1.024
 contro-0.949
 discharge-0.931
 corpor-0.920
 cumulative-0.914
Token caption
Token ID8305
Feature activation+7.42e-01

Pos logit contributions
acs+0.031
 Gravity+0.030
assic+0.030
ikhail+0.030
Tokens+0.028
Neg logit contributions
 confir-0.079
 contro-0.077
 discharge-0.075
 corpor-0.075
 Jude-0.075
Token solve
Token ID8494
Feature activation+2.70e-01

Pos logit contributions
 confir+0.458
 contro+0.435
 discharge+0.422
 corpor+0.417
 Jude+0.416
Neg logit contributions
acs-0.560
 Gravity-0.549
assic-0.544
ikhail-0.542
Tokens-0.533
Token the
Token ID262
Feature activation+2.94e-02

Pos logit contributions
acs+0.506
 Gravity+0.498
assic+0.491
ikhail+0.491
Tokens+0.480
Neg logit contributions
 confir-0.449
 contro-0.426
 discharge-0.415
 corpor-0.409
 Jude-0.408
Token Pittsburgh
Token ID12767
Feature activation+3.91e-01

Pos logit contributions
acs+0.053
 Gravity+0.052
assic+0.052
ikhail+0.051
Tokens+0.050
Neg logit contributions
 confir-0.051
 contro-0.048
 discharge-0.047
 corpor-0.047
 Jude-0.047
Token Penguins
Token ID29755
Feature activation-1.36e-02

Pos logit contributions
acs+0.574
 Gravity+0.559
ikhail+0.552
assic+0.551
Tokens+0.535
Neg logit contributions
 confir-0.813
 contro-0.778
 discharge-0.762
 corpor-0.757
 Jude-0.753
Token expansion
Token ID7118
Feature activation+5.50e-02

Pos logit contributions
 confir+0.022
 contro+0.021
 discharge+0.021
 corpor+0.020
 Jude+0.020
Neg logit contributions
acs-0.026
 Gravity-0.025
ikhail-0.025
assic-0.025
Tokens-0.024
Token draft
Token ID4538
Feature activation+1.05e+00

Pos logit contributions
acs+0.116
 Gravity+0.115
ikhail+0.113
assic+0.113
Tokens+0.111
Neg logit contributions
 confir-0.079
 contro-0.073
 discharge-0.070
 corpor-0.070
 Jude-0.070
Token problem
Token ID1917
Feature activation-1.24e-01

Pos logit contributions
acs+2.066
 Gravity+2.063
assic+2.027
ikhail+2.019
Tokens+1.977
Neg logit contributions
 confir-1.637
 contro-1.511
 discharge-1.462
 Jude-1.444
 corpor-1.442
Token?
Token ID30
Feature activation-1.38e-02

Pos logit contributions
 confir+0.206
 contro+0.196
 discharge+0.191
 corpor+0.188
 Jude+0.188
Neg logit contributions
acs-0.234
 Gravity-0.229
assic-0.228
ikhail-0.227
Tokens-0.223
Token If
Token ID1002
Feature activation-6.67e-02

Pos logit contributions
 confir+0.022
 contro+0.020
 discharge+0.020
 corpor+0.020
 cumulative+0.019
Neg logit contributions
acs-0.028
 Gravity-0.027
ikhail-0.027
assic-0.027
Tokens-0.026
Token you
Token ID345
Feature activation-2.01e-02

Pos logit contributions
 confir+0.124
 contro+0.119
 discharge+0.116
 corpor+0.115
 Jude+0.114
Neg logit contributions
acs-0.112
 Gravity-0.110
ikhail-0.108
assic-0.108
Tokens-0.106
Token believe
Token ID1975
Feature activation-2.23e-01

Pos logit contributions
 confir+0.033
 contro+0.031
 discharge+0.030
 Jude+0.030
 corpor+0.030
Neg logit contributions
acs-0.038
 Gravity-0.038
assic-0.037
ikhail-0.037
Tokens-0.036
Token is
Token ID318
Feature activation+7.15e-02

Pos logit contributions
acs+0.135
 Gravity+0.131
assic+0.131
ikhail+0.130
Tokens+0.128
Neg logit contributions
 confir-0.121
 contro-0.115
 discharge-0.112
 Jude-0.111
 corpor-0.111
Token able
Token ID1498
Feature activation+2.20e-01

Pos logit contributions
acs+0.136
 Gravity+0.133
assic+0.132
ikhail+0.131
Tokens+0.129
Neg logit contributions
 confir-0.117
 contro-0.111
 discharge-0.108
 Jude-0.107
 corpor-0.106
Token to
Token ID284
Feature activation+1.16e-01

Pos logit contributions
acs+0.456
 Gravity+0.447
assic+0.445
ikhail+0.444
Tokens+0.436
Neg logit contributions
 confir-0.324
 contro-0.306
 discharge-0.297
 corpor-0.293
 Jude-0.292
Token meet
Token ID1826
Feature activation-3.62e-03

Pos logit contributions
acs+0.221
 Gravity+0.216
assic+0.213
ikhail+0.212
Tokens+0.210
Neg logit contributions
 confir-0.190
 contro-0.179
 Jude-0.174
 discharge-0.173
 corpor-0.173
Token its
Token ID663
Feature activation+8.53e-02

Pos logit contributions
 confir+0.006
 contro+0.005
 discharge+0.005
 corpor+0.005
 Jude+0.005
Neg logit contributions
acs-0.007
 Gravity-0.007
assic-0.007
ikhail-0.007
Tokens-0.007
Token deficit
Token ID11807
Feature activation+1.04e+00

Pos logit contributions
acs+0.156
 Gravity+0.154
assic+0.152
ikhail+0.151
Tokens+0.149
Neg logit contributions
 confir-0.146
 contro-0.138
 discharge-0.134
 Jude-0.133
 corpor-0.132
Token targets
Token ID6670
Feature activation-2.84e-01

Pos logit contributions
acs+2.278
 Gravity+2.232
assic+2.194
ikhail+2.188
Tokens+2.170
Neg logit contributions
 confir-1.409
 contro-1.302
 Jude-1.260
 corpor-1.250
 discharge-1.242
Token,
Token ID11
Feature activation+1.13e-02

Pos logit contributions
 confir+0.441
 contro+0.419
 discharge+0.407
 corpor+0.401
 Jude+0.400
Neg logit contributions
acs-0.563
 Gravity-0.551
assic-0.548
ikhail-0.547
Tokens-0.537
Token given
Token ID1813
Feature activation+1.75e-03

Pos logit contributions
acs+0.023
 Gravity+0.022
assic+0.022
ikhail+0.022
Tokens+0.022
Neg logit contributions
 confir-0.017
 contro-0.016
 discharge-0.016
 corpor-0.016
 Jude-0.016
Token that
Token ID326
Feature activation+6.06e-02

Pos logit contributions
acs+0.003
 Gravity+0.003
ikhail+0.003
assic+0.003
Tokens+0.003
Neg logit contributions
 confir-0.003
 contro-0.003
 discharge-0.003
 corpor-0.003
 Jude-0.003
Token a
Token ID257
Feature activation-5.11e-02

Pos logit contributions
acs+0.118
 Gravity+0.115
assic+0.114
ikhail+0.113
Tokens+0.112
Neg logit contributions
 confir-0.097
 contro-0.091
 discharge-0.089
 Jude-0.088
 corpor-0.087
Tokend
Token ID67
Feature activation+1.87e-01

Pos logit contributions
acs+0.397
assic+0.385
 Gravity+0.384
ikhail+0.381
Tokens+0.372
Neg logit contributions
 confir-0.401
 contro-0.382
 discharge-0.371
 corpor-0.366
 cumulative-0.366
Tokenong
Token ID506
Feature activation+1.92e-01

Pos logit contributions
acs+0.283
assic+0.273
 Gravity+0.273
ikhail+0.271
Tokens+0.260
Neg logit contributions
 confir-0.387
 contro-0.370
 discharge-0.361
 corpor-0.358
 Jude-0.357
Token province
Token ID8473
Feature activation-2.06e-01

Pos logit contributions
acs+0.410
 Gravity+0.403
assic+0.401
ikhail+0.397
Tokens+0.390
Neg logit contributions
 confir-0.269
 contro-0.254
 discharge-0.245
 corpor-0.241
 Jude-0.240
Token turns
Token ID4962
Feature activation+1.14e-01

Pos logit contributions
 confir+0.341
 contro+0.325
 discharge+0.316
 corpor+0.312
 Jude+0.311
Neg logit contributions
acs-0.389
 Gravity-0.380
assic-0.379
ikhail-0.378
Tokens-0.370
Token redd
Token ID14688
Feature activation-5.77e-01

Pos logit contributions
acs+0.225
 Gravity+0.222
assic+0.219
ikhail+0.218
Tokens+0.214
Neg logit contributions
 confir-0.180
 contro-0.169
 discharge-0.164
 corpor-0.162
 Jude-0.161
Tokenish
Token ID680
Feature activation-1.26e+00

Pos logit contributions
 confir+0.583
 contro+0.543
 discharge+0.527
 Jude+0.508
 corpor+0.507
Neg logit contributions
acs-1.449
 Gravity-1.432
assic-1.423
ikhail-1.419
Tokens-1.401
Token brown
Token ID7586
Feature activation-1.67e-01

Pos logit contributions
 confir+1.926
 contro+1.880
 discharge+1.855
 corpor+1.801
 Jude+1.797
Neg logit contributions
acs-2.486
 Gravity-2.436
assic-2.432
ikhail-2.429
Tokens-2.370
Token after
Token ID706
Feature activation-1.06e-01

Pos logit contributions
 confir+0.261
 contro+0.248
 discharge+0.241
 corpor+0.238
 Jude+0.237
Neg logit contributions
acs-0.330
 Gravity-0.323
assic-0.321
ikhail-0.320
Tokens-0.314
Token the
Token ID262
Feature activation-1.61e-01

Pos logit contributions
 confir+0.170
 contro+0.162
 discharge+0.157
 corpor+0.155
 Jude+0.155
Neg logit contributions
acs-0.206
 Gravity-0.202
assic-0.201
ikhail-0.200
Tokens-0.196
Token water
Token ID1660
Feature activation-1.95e-01

Pos logit contributions
 confir+0.259
 contro+0.246
 discharge+0.239
 corpor+0.236
 Jude+0.235
Neg logit contributions
acs-0.313
 Gravity-0.306
assic-0.305
ikhail-0.304
Tokens-0.298
Token was
Token ID373
Feature activation-4.05e-02

Pos logit contributions
 confir+0.326
 contro+0.312
 discharge+0.307
 corpor+0.301
 cumulative+0.299
Neg logit contributions
acs-0.363
 Gravity-0.354
ikhail-0.353
assic-0.352
Tokens-0.347
Tokenatics
Token ID23372
Feature activation-5.86e-01

Pos logit contributions
acs+0.081
 Gravity+0.079
assic+0.079
ikhail+0.078
Tokens+0.077
Neg logit contributions
 confir-0.115
 contro-0.111
 discharge-0.108
 corpor-0.107
 Jude-0.107
Token and
Token ID290
Feature activation+2.36e-02

Pos logit contributions
 confir+0.883
 contro+0.837
 discharge+0.813
 corpor+0.801
 Jude+0.799
Neg logit contributions
acs-1.192
 Gravity-1.167
assic-1.162
ikhail-1.159
Tokens-1.138
Token over
Token ID625
Feature activation+9.75e-02

Pos logit contributions
acs+0.045
 Gravity+0.044
assic+0.044
ikhail+0.044
Tokens+0.043
Neg logit contributions
 confir-0.038
 contro-0.036
 discharge-0.035
 corpor-0.035
 Jude-0.035
Token 90
Token ID4101
Feature activation-2.61e-01

Pos logit contributions
acs+0.190
 Gravity+0.187
assic+0.185
ikhail+0.185
Tokens+0.182
Neg logit contributions
 confir-0.155
 contro-0.147
 discharge-0.143
 corpor-0.141
 Jude-0.140
Token 000
Token ID12877
Feature activation-5.93e-01

Pos logit contributions
 confir+0.424
 contro+0.401
 discharge+0.391
 Jude+0.386
 corpor+0.386
Neg logit contributions
acs-0.498
 Gravity-0.489
assic-0.484
ikhail-0.482
Tokens-0.473
Token rounds
Token ID9196
Feature activation-1.24e+00

Pos logit contributions
 confir+0.901
 contro+0.853
 discharge+0.829
 corpor+0.817
 Jude+0.815
Neg logit contributions
acs-1.197
 Gravity-1.173
assic-1.167
ikhail-1.164
Tokens-1.143
Token of
Token ID286
Feature activation-1.17e-01

Pos logit contributions
 confir+1.678
 contro+1.603
 discharge+1.552
 cumulative+1.519
 corpor+1.510
Neg logit contributions
acs-2.697
assic-2.647
 Gravity-2.645
ikhail-2.640
Tokens-2.594
Token blank
Token ID9178
Feature activation+2.72e-01

Pos logit contributions
 confir+0.171
 contro+0.158
 discharge+0.154
 Jude+0.153
 corpor+0.152
Neg logit contributions
acs-0.243
 Gravity-0.242
assic-0.237
ikhail-0.236
Tokens-0.233
Token ammunition
Token ID14271
Feature activation-7.70e-03

Pos logit contributions
acs+0.573
 Gravity+0.566
assic+0.561
ikhail+0.559
Tokens+0.551
Neg logit contributions
 confir-0.391
 contro-0.363
 discharge-0.350
 corpor-0.348
 Jude-0.348
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
 confir+0.012
 contro+0.011
 discharge+0.011
 corpor+0.011
 Jude+0.011
Neg logit contributions
acs-0.015
 Gravity-0.015
assic-0.015
ikhail-0.015
Tokens-0.015
Token "
Token ID366
Feature activation-6.63e-02

Pos logit contributions
 confir+0.021
 contro+0.020
 discharge+0.020
 corpor+0.019
 Jude+0.019
Neg logit contributions
acs-0.024
 Gravity-0.024
assic-0.024
ikhail-0.024
Tokens-0.023
Token ongoing
Token ID7044
Feature activation-1.63e-01

Pos logit contributions
 confir+0.164
 contro+0.154
 discharge+0.150
 corpor+0.148
 cumulative+0.146
Neg logit contributions
acs-0.199
 Gravity-0.196
assic-0.194
ikhail-0.194
Tokens-0.190
Token violations
Token ID11734
Feature activation-3.61e-01

Pos logit contributions
 confir+0.236
 contro+0.221
 discharge+0.214
 corpor+0.210
 Jude+0.208
Neg logit contributions
acs-0.341
 Gravity-0.335
assic-0.332
ikhail-0.332
Tokens-0.326
Token and
Token ID290
Feature activation-9.64e-02

Pos logit contributions
 confir+0.514
 contro+0.486
 discharge+0.472
 corpor+0.464
 Jude+0.463
Neg logit contributions
acs-0.763
 Gravity-0.748
assic-0.745
ikhail-0.743
Tokens-0.730
Token increase
Token ID2620
Feature activation-2.39e-01

Pos logit contributions
 confir+0.154
 contro+0.145
 discharge+0.141
 corpor+0.139
 Jude+0.139
Neg logit contributions
acs-0.187
 Gravity-0.184
assic-0.182
ikhail-0.182
Tokens-0.178
Token in
Token ID287
Feature activation-5.89e-02

Pos logit contributions
 confir+0.374
 contro+0.352
 discharge+0.343
 corpor+0.337
 Jude+0.334
Neg logit contributions
acs-0.473
 Gravity-0.465
ikhail-0.460
assic-0.459
Tokens-0.450
Token settlement
Token ID9443
Feature activation-1.23e+00

Pos logit contributions
 confir+0.095
 contro+0.089
 discharge+0.087
 corpor+0.086
 Jude+0.085
Neg logit contributions
acs-0.113
 Gravity-0.111
ikhail-0.110
assic-0.110
Tokens-0.108
Token expansion
Token ID7118
Feature activation-2.61e-01

Pos logit contributions
 confir+1.944
 contro+1.859
 discharge+1.815
 corpor+1.790
 Jude+1.781
Neg logit contributions
acs-2.418
 Gravity-2.364
assic-2.362
ikhail-2.362
Tokens-2.313
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
 confir+0.399
 contro+0.377
 discharge+0.366
 corpor+0.362
 Jude+0.360
Neg logit contributions
acs-0.527
 Gravity-0.516
ikhail-0.512
assic-0.512
Tokens-0.502
Token A
Token ID317
Feature activation-1.49e-01

Pos logit contributions
 confir+0.025
 contro+0.024
 discharge+0.023
 corpor+0.023
 Jude+0.023
Neg logit contributions
acs-0.024
 Gravity-0.023
assic-0.023
ikhail-0.023
Tokens-0.022
Token shift
Token ID6482
Feature activation-4.60e-01

Pos logit contributions
 confir+0.223
 contro+0.210
 discharge+0.204
 corpor+0.201
 Jude+0.200
Neg logit contributions
acs-0.302
 Gravity-0.297
ikhail-0.295
assic-0.294
Tokens-0.288
Token has
Token ID468
Feature activation-7.15e-02

Pos logit contributions
 confir+0.679
 contro+0.642
 discharge+0.623
 corpor+0.614
 Jude+0.612
Neg logit contributions
acs-0.950
 Gravity-0.931
assic-0.927
ikhail-0.925
Tokens-0.908
Token would
Token ID561
Feature activation-1.72e-01

Pos logit contributions
 confir+0.261
 contro+0.247
 discharge+0.240
 corpor+0.237
 Jude+0.236
Neg logit contributions
acs-0.325
 Gravity-0.319
assic-0.316
ikhail-0.315
Tokens-0.310
Token drive
Token ID3708
Feature activation+6.57e-02

Pos logit contributions
 confir+0.275
 contro+0.261
 discharge+0.255
 corpor+0.251
 Jude+0.250
Neg logit contributions
acs-0.334
 Gravity-0.327
assic-0.326
ikhail-0.325
Tokens-0.319
Token nearly
Token ID3016
Feature activation+7.80e-02

Pos logit contributions
acs+0.127
 Gravity+0.125
assic+0.124
ikhail+0.123
Tokens+0.121
Neg logit contributions
 confir-0.106
 contro-0.100
 discharge-0.097
 corpor-0.096
 Jude-0.096
Token nine
Token ID5193
Feature activation-2.18e-01

Pos logit contributions
acs+0.148
 Gravity+0.146
assic+0.144
ikhail+0.143
Tokens+0.141
Neg logit contributions
 confir-0.128
 contro-0.121
 discharge-0.118
 corpor-0.116
 Jude-0.116
Token hours
Token ID2250
Feature activation+5.15e-02

Pos logit contributions
 confir+0.432
 contro+0.416
 discharge+0.408
 corpor+0.403
 Jude+0.402
Neg logit contributions
acs-0.339
 Gravity-0.330
assic-0.328
ikhail-0.328
Tokens-0.319
Token round
Token ID2835
Feature activation-1.21e+00

Pos logit contributions
acs+0.102
 Gravity+0.100
assic+0.099
ikhail+0.099
Tokens+0.098
Neg logit contributions
 confir-0.080
 contro-0.076
 discharge-0.073
 corpor-0.073
 Jude-0.072
Token trip
Token ID5296
Feature activation-1.27e-01

Pos logit contributions
 confir+1.853
 contro+1.783
 discharge+1.761
 Jude+1.730
 cumulative+1.723
Neg logit contributions
acs-2.384
ikhail-2.330
assic-2.327
 Gravity-2.306
Tokens-2.273
Token in
Token ID287
Feature activation-6.00e-03

Pos logit contributions
 confir+0.193
 contro+0.183
 discharge+0.177
 corpor+0.175
 Jude+0.174
Neg logit contributions
acs-0.255
 Gravity-0.250
assic-0.249
ikhail-0.248
Tokens-0.244
Token a
Token ID257
Feature activation-1.33e-01

Pos logit contributions
 confir+0.010
 contro+0.010
 discharge+0.010
 corpor+0.009
 Jude+0.009
Neg logit contributions
acs-0.011
 Gravity-0.011
assic-0.011
ikhail-0.011
Tokens-0.010
Token day
Token ID1110
Feature activation+4.11e-02

Pos logit contributions
 confir+0.221
 contro+0.208
 discharge+0.203
 corpor+0.200
 Jude+0.199
Neg logit contributions
acs-0.250
 Gravity-0.248
assic-0.242
ikhail-0.241
 Mov-0.237
Token to
Token ID284
Feature activation-1.03e-01

Pos logit contributions
acs+0.082
 Gravity+0.080
ikhail+0.079
assic+0.079
Tokens+0.078
Neg logit contributions
 confir-0.064
 contro-0.061
 discharge-0.059
 Jude-0.058
 corpor-0.058
Token stated
Token ID5081
Feature activation+1.31e-01

Pos logit contributions
acs+0.538
 Gravity+0.528
ikhail+0.523
assic+0.523
Tokens+0.512
Neg logit contributions
 confir-0.437
 contro-0.416
 discharge-0.406
 corpor-0.400
 Jude-0.398
Token that
Token ID326
Feature activation-1.31e-01

Pos logit contributions
acs+0.256
 Gravity+0.251
assic+0.249
ikhail+0.249
Tokens+0.244
Neg logit contributions
 confir-0.207
 contro-0.197
 discharge-0.191
 corpor-0.188
 Jude-0.188
Token the
Token ID262
Feature activation-3.98e-02

Pos logit contributions
 confir+0.206
 contro+0.195
 discharge+0.189
 corpor+0.186
 Jude+0.186
Neg logit contributions
acs-0.258
 Gravity-0.254
ikhail-0.251
assic-0.251
Tokens-0.247
Token Ministry
Token ID9475
Feature activation+6.89e-02

Pos logit contributions
 confir+0.060
 contro+0.057
 discharge+0.055
 corpor+0.054
 Jude+0.054
Neg logit contributions
acs-0.080
 Gravity-0.079
ikhail-0.078
assic-0.078
Tokens-0.076
Token of
Token ID286
Feature activation-1.21e-01

Pos logit contributions
acs+0.137
 Gravity+0.135
assic+0.133
ikhail+0.133
Tokens+0.131
Neg logit contributions
 confir-0.106
 contro-0.100
 discharge-0.097
 corpor-0.096
 Jude-0.096
Token Internal
Token ID18628
Feature activation-1.20e+00

Pos logit contributions
 confir+0.177
 contro+0.167
 discharge+0.162
 corpor+0.159
 cumulative+0.158
Neg logit contributions
acs-0.250
 Gravity-0.246
assic-0.244
ikhail-0.244
Tokens-0.239
Token Affairs
Token ID10665
Feature activation-3.71e-01

Pos logit contributions
 confir+2.053
 contro+1.974
 discharge+1.936
 Jude+1.924
 corpor+1.906
Neg logit contributions
acs-2.163
assic-2.121
ikhail-2.100
 Gravity-2.099
Tokens-2.067
Token also
Token ID635
Feature activation+1.02e-01

Pos logit contributions
 confir+0.605
 contro+0.576
 discharge+0.560
 corpor+0.553
 Jude+0.551
Neg logit contributions
acs-0.707
 Gravity-0.693
assic-0.687
ikhail-0.685
Tokens-0.672
Token expressed
Token ID6241
Feature activation+8.33e-02

Pos logit contributions
acs+0.189
 Gravity+0.185
assic+0.182
ikhail+0.181
Tokens+0.178
Neg logit contributions
 confir-0.169
 contro-0.161
 discharge-0.157
 Jude-0.155
 cumulative-0.155
Token its
Token ID663
Feature activation-1.46e-01

Pos logit contributions
acs+0.160
 Gravity+0.157
ikhail+0.155
assic+0.155
Tokens+0.152
Neg logit contributions
 confir-0.135
 contro-0.128
 discharge-0.124
 corpor-0.122
 Jude-0.122
Token willingness
Token ID16826
Feature activation+2.06e-01

Pos logit contributions
 confir+0.236
 contro+0.224
 discharge+0.217
 corpor+0.214
 Jude+0.214
Neg logit contributions
acs-0.282
 Gravity-0.277
assic-0.275
ikhail-0.274
Tokens-0.269
Token a
Token ID257
Feature activation-5.46e-02

Pos logit contributions
 confir+0.205
 contro+0.195
 discharge+0.190
 corpor+0.188
 Jude+0.187
Neg logit contributions
acs-0.239
 Gravity-0.233
assic-0.232
ikhail-0.232
Tokens-0.227
Token service
Token ID2139
Feature activation+6.09e-01

Pos logit contributions
 confir+0.092
 contro+0.088
 discharge+0.085
 corpor+0.084
 Jude+0.084
Neg logit contributions
acs-0.101
 Gravity-0.099
assic-0.098
ikhail-0.098
Tokens-0.096
Token pistol
Token ID16790
Feature activation-4.57e-02

Pos logit contributions
acs+1.106
 Gravity+1.080
assic+1.074
ikhail+1.067
Tokens+1.046
Neg logit contributions
 confir-1.047
 contro-0.997
 discharge-0.966
 Jude-0.957
 cumulative-0.955
Token and
Token ID290
Feature activation+5.14e-02

Pos logit contributions
 confir+0.074
 contro+0.070
 discharge+0.068
 corpor+0.067
 Jude+0.067
Neg logit contributions
acs-0.088
 Gravity-0.086
assic-0.085
ikhail-0.085
Tokens-0.084
Token 15
Token ID1315
Feature activation-2.42e-01

Pos logit contributions
acs+0.102
 Gravity+0.101
assic+0.099
ikhail+0.099
Tokens+0.097
Neg logit contributions
 confir-0.079
 contro-0.075
 discharge-0.072
 Jude-0.071
 cumulative-0.071
Token rounds
Token ID9196
Feature activation-1.19e+00

Pos logit contributions
 confir+0.413
 contro+0.394
 discharge+0.384
 corpor+0.379
 Jude+0.378
Neg logit contributions
acs-0.445
 Gravity-0.434
assic-0.432
ikhail-0.431
Tokens-0.423
Token of
Token ID286
Feature activation-7.32e-03

Pos logit contributions
 confir+1.609
 contro+1.532
 discharge+1.492
 cumulative+1.456
 corpor+1.455
Neg logit contributions
acs-2.596
 Gravity-2.547
assic-2.540
ikhail-2.527
Tokens-2.491
Token ammunition
Token ID14271
Feature activation+1.76e-02

Pos logit contributions
 confir+0.011
 contro+0.010
 discharge+0.009
 Jude+0.009
 corpor+0.009
Neg logit contributions
acs-0.015
 Gravity-0.015
assic-0.015
ikhail-0.015
 Mov-0.015
Token that
Token ID326
Feature activation+1.31e-01

Pos logit contributions
acs+0.033
 Gravity+0.033
ikhail+0.032
assic+0.032
Tokens+0.031
Neg logit contributions
 confir-0.029
 contro-0.027
 discharge-0.026
 Jude-0.026
 corpor-0.026
Token disappeared
Token ID12120
Feature activation+8.01e-02

Pos logit contributions
acs+0.235
 Gravity+0.230
assic+0.229
ikhail+0.228
Tokens+0.223
Neg logit contributions
 confir-0.229
 contro-0.218
 discharge-0.213
 corpor-0.210
 Jude-0.210
Token last
Token ID938
Feature activation-2.88e-01

Pos logit contributions
acs+0.161
 Gravity+0.158
assic+0.157
ikhail+0.157
Tokens+0.154
Neg logit contributions
 confir-0.122
 contro-0.115
 discharge-0.112
 corpor-0.110
 Jude-0.110
Token found
Token ID1043
Feature activation-3.78e-01

Pos logit contributions
 confir+0.094
 contro+0.089
 discharge+0.087
 corpor+0.085
 Jude+0.085
Neg logit contributions
acs-0.132
 Gravity-0.129
assic-0.129
ikhail-0.129
Tokens-0.126
Token a
Token ID257
Feature activation+1.91e-02

Pos logit contributions
 confir+0.598
 contro+0.572
 discharge+0.556
 corpor+0.550
 Jude+0.546
Neg logit contributions
acs-0.739
assic-0.719
 Gravity-0.719
ikhail-0.718
Tokens-0.705
Token '
Token ID705
Feature activation-6.00e-01

Pos logit contributions
acs+0.039
 Gravity+0.038
assic+0.038
ikhail+0.038
Tokens+0.037
Neg logit contributions
 confir-0.029
 contro-0.027
 discharge-0.026
 corpor-0.026
 Jude-0.026
Tokenp
Token ID79
Feature activation+5.40e-01

Pos logit contributions
 confir+0.982
 contro+0.935
 discharge+0.910
 corpor+0.899
 Jude+0.896
Neg logit contributions
acs-1.140
 Gravity-1.115
assic-1.109
ikhail-1.107
Tokens-1.085
Tokenreg
Token ID2301
Feature activation-9.87e-02

Pos logit contributions
acs+1.000
 Gravity+0.974
assic+0.973
ikhail+0.969
Tokens+0.947
Neg logit contributions
 confir-0.917
 contro-0.872
 discharge-0.847
 corpor-0.837
 Jude-0.836
Tokennant
Token ID22057
Feature activation-1.19e+00

Pos logit contributions
 confir+0.165
 contro+0.158
 discharge+0.156
 corpor+0.155
 Jude+0.154
Neg logit contributions
acs-0.180
 Gravity-0.178
ikhail-0.176
Tokens-0.174
assic-0.173
Token'
Token ID6
Feature activation-4.15e-01

Pos logit contributions
 confir+1.935
 contro+1.856
 discharge+1.825
 corpor+1.794
 Jude+1.787
Neg logit contributions
acs-2.263
ikhail-2.195
assic-2.191
 Gravity-2.190
Tokens-2.159
Token T
Token ID309
Feature activation-6.74e-02

Pos logit contributions
 confir+0.712
 contro+0.681
 discharge+0.665
 corpor+0.657
 Jude+0.655
Neg logit contributions
acs-0.756
 Gravity-0.735
assic-0.733
ikhail-0.732
Tokens-0.719
Token.
Token ID13
Feature activation+1.37e-01

Pos logit contributions
 confir+0.099
 contro+0.095
 discharge+0.092
 corpor+0.091
 Jude+0.090
Neg logit contributions
acs-0.138
 Gravity-0.136
ikhail-0.134
assic-0.134
Tokens-0.133
Token re
Token ID302
Feature activation+5.87e-02

Pos logit contributions
acs+0.290
assic+0.284
 Gravity+0.284
ikhail+0.283
Tokens+0.276
Neg logit contributions
 confir-0.195
 contro-0.184
 discharge-0.178
 corpor-0.175
 Jude-0.175
Tokenx
Token ID87
Feature activation-1.59e-01

Pos logit contributions
acs+0.106
assic+0.103
 Gravity+0.103
ikhail+0.103
Tokens+0.100
Neg logit contributions
 confir-0.103
 contro-0.097
 discharge-0.095
 corpor-0.094
 Jude-0.094
Token01
Token ID486
Feature activation-9.33e-02

Pos logit contributions
 confir+0.281
 contro+0.271
 discharge+0.264
 Jude+0.262
 corpor+0.261
Neg logit contributions
acs-0.320
assic-0.314
 Gravity-0.313
ikhail-0.312
Tokens-0.304
Token.
Token ID13
Feature activation-2.24e-01

Pos logit contributions
 confir+0.133
 contro+0.127
 discharge+0.123
 corpor+0.121
 Jude+0.121
Neg logit contributions
acs-0.196
 Gravity-0.192
assic-0.192
ikhail-0.191
Tokens-0.187
Token29
Token ID1959
Feature activation-2.65e-02

Pos logit contributions
 confir+0.358
 contro+0.345
 discharge+0.336
 Jude+0.333
 corpor+0.332
Neg logit contributions
acs-0.428
assic-0.419
 Gravity-0.418
ikhail-0.417
Tokens-0.406
Token"]
Token ID8973
Feature activation-6.04e-02

Pos logit contributions
 confir+0.063
 contro+0.062
 discharge+0.060
 Jude+0.060
 corpor+0.060
Neg logit contributions
acs-0.030
assic-0.029
 Gravity-0.029
ikhail-0.029
Tokens-0.028
Token [
Token ID685
Feature activation+6.56e-01

Pos logit contributions
 confir+0.120
 contro+0.117
 discharge+0.114
 Jude+0.114
 corpor+0.113
Neg logit contributions
acs-0.092
assic-0.090
 Gravity-0.089
ikhail-0.089
Tokens-0.086
TokenRound
Token ID22685
Feature activation-1.18e+00

Pos logit contributions
 Gravity+1.508
acs+1.505
Tokens+1.496
ikhail+1.482
Bro+1.475
Neg logit contributions
 confir-0.829
 contro-0.750
 discharge-0.732
 cumulative-0.696
 corpor-0.685
Token "
Token ID366
Feature activation+1.56e-01

Pos logit contributions
 confir+1.593
 contro+1.524
 discharge+1.477
 Jude+1.471
 corpor+1.467
Neg logit contributions
acs-2.596
 Gravity-2.510
assic-2.505
ikhail-2.502
Tokens-2.444
Token11
Token ID1157
Feature activation+5.53e-02

Pos logit contributions
acs+0.296
 Gravity+0.290
assic+0.288
ikhail+0.288
Tokens+0.282
Neg logit contributions
 confir-0.257
 contro-0.244
 discharge-0.238
 corpor-0.235
 Jude-0.234
Token"]
Token ID8973
Feature activation+5.28e-02

Pos logit contributions
acs+0.094
 Gravity+0.092
assic+0.092
ikhail+0.091
Tokens+0.089
Neg logit contributions
 confir-0.101
 contro-0.097
 discharge-0.095
 corpor-0.094
 Jude-0.094
Token [
Token ID685
Feature activation+6.99e-01

Pos logit contributions
acs+0.077
 Gravity+0.075
assic+0.074
ikhail+0.074
Tokens+0.072
Neg logit contributions
 confir-0.111
 contro-0.106
 discharge-0.104
 corpor-0.103
 Jude-0.102
TokenWhite
Token ID12256
Feature activation-6.72e-01

Pos logit contributions
acs+1.546
 Gravity+1.526
ikhail+1.512
assic+1.506
Tokens+1.501
Neg logit contributions
 confir-0.931
 contro-0.870
 discharge-0.843
 corpor-0.815
 Jude-0.813
Token her
Token ID607
Feature activation-2.55e-01

Pos logit contributions
 confir+0.155
 contro+0.146
 discharge+0.142
 corpor+0.140
 Jude+0.140
Neg logit contributions
acs-0.201
 Gravity-0.197
assic-0.195
ikhail-0.195
Tokens-0.191
Token departure
Token ID12928
Feature activation-3.37e-01

Pos logit contributions
 confir+0.414
 contro+0.395
 discharge+0.385
 corpor+0.380
 Jude+0.378
Neg logit contributions
acs-0.488
 Gravity-0.477
assic-0.476
ikhail-0.474
Tokens-0.465
Token time
Token ID640
Feature activation+2.37e-02

Pos logit contributions
 confir+0.515
 contro+0.492
 discharge+0.478
 corpor+0.472
 Jude+0.469
Neg logit contributions
acs-0.678
 Gravity-0.661
assic-0.661
ikhail-0.659
Tokens-0.645
Token carefully
Token ID7773
Feature activation-8.13e-02

Pos logit contributions
acs+0.044
 Gravity+0.043
assic+0.043
ikhail+0.043
Tokens+0.042
Neg logit contributions
 confir-0.040
 contro-0.038
 discharge-0.037
 Jude-0.036
 corpor-0.036
Token.
Token ID13
Feature activation-1.85e-02

Pos logit contributions
 confir+0.123
 contro+0.116
 discharge+0.113
 corpor+0.111
 Jude+0.111
Neg logit contributions
acs-0.165
 Gravity-0.162
assic-0.161
ikhail-0.160
Tokens-0.157
Token Either
Token ID15467
Feature activation-1.17e+00

Pos logit contributions
 confir+0.030
 contro+0.028
 discharge+0.027
 corpor+0.027
 cumulative+0.027
Neg logit contributions
acs-0.036
 Gravity-0.035
ikhail-0.035
assic-0.035
Tokens-0.034
Token she
Token ID673
Feature activation-2.38e-01

Pos logit contributions
 confir+1.638
 contro+1.551
 discharge+1.514
 corpor+1.486
 Jude+1.480
Neg logit contributions
acs-2.511
assic-2.452
 Gravity-2.452
ikhail-2.448
Tokens-2.404
Token gets
Token ID3011
Feature activation-2.17e-01

Pos logit contributions
 confir+0.405
 contro+0.384
 discharge+0.374
 Jude+0.370
 corpor+0.370
Neg logit contributions
acs-0.439
 Gravity-0.428
assic-0.425
ikhail-0.423
Tokens-0.415
Token on
Token ID319
Feature activation-1.20e-01

Pos logit contributions
 confir+0.357
 contro+0.339
 discharge+0.330
 corpor+0.326
 Jude+0.325
Neg logit contributions
acs-0.410
 Gravity-0.401
assic-0.399
ikhail-0.398
Tokens-0.391
Token the
Token ID262
Feature activation-9.06e-02

Pos logit contributions
 confir+0.192
 contro+0.182
 discharge+0.177
 corpor+0.175
 Jude+0.174
Neg logit contributions
acs-0.234
 Gravity-0.229
assic-0.227
ikhail-0.227
Tokens-0.223
Token London
Token ID3576
Feature activation-1.41e-01

Pos logit contributions
 confir+0.141
 contro+0.134
 discharge+0.130
 corpor+0.129
 Jude+0.128
Neg logit contributions
acs-0.179
 Gravity-0.176
assic-0.175
ikhail-0.174
Tokens-0.171
Token Ay
Token ID13709
Feature activation-1.70e-01

Pos logit contributions
 confir+0.065
 contro+0.063
 discharge+0.061
 corpor+0.060
 Jude+0.060
Neg logit contributions
acs-0.063
ikhail-0.061
 Gravity-0.061
assic-0.060
Tokens-0.059
Tokenat
Token ID265
Feature activation-1.31e-01

Pos logit contributions
 confir+0.325
 contro+0.314
 discharge+0.306
 corpor+0.303
 Jude+0.303
Neg logit contributions
acs-0.273
 Gravity-0.270
assic-0.266
ikhail-0.264
Tokens-0.260
Tokenollah
Token ID17999
Feature activation-5.44e-01

Pos logit contributions
 confir+0.178
 contro+0.166
 discharge+0.161
 corpor+0.159
 Jude+0.158
Neg logit contributions
acs-0.286
 Gravity-0.280
assic-0.279
ikhail-0.278
Tokens-0.273
Token Ali
Token ID12104
Feature activation-4.35e-01

Pos logit contributions
 confir+0.522
 contro+0.479
 discharge+0.458
 Jude+0.454
 corpor+0.450
Neg logit contributions
acs-1.402
 Gravity-1.383
assic-1.382
ikhail-1.371
Tokens-1.358
Token Kham
Token ID45159
Feature activation-4.73e-01

Pos logit contributions
 confir+0.709
 contro+0.669
 discharge+0.652
 corpor+0.644
 cumulative+0.640
Neg logit contributions
acs-0.839
 Gravity-0.819
assic-0.814
ikhail-0.813
Tokens-0.794
Tokenenei
Token ID46009
Feature activation-1.16e+00

Pos logit contributions
 confir+0.883
 contro+0.851
 discharge+0.830
 corpor+0.822
 Jude+0.820
Neg logit contributions
acs-0.786
 Gravity-0.769
assic-0.763
ikhail-0.760
Tokens-0.745
Token,
Token ID11
Feature activation+2.46e-02

Pos logit contributions
 confir+1.655
 contro+1.561
 discharge+1.496
 corpor+1.490
 Jude+1.486
Neg logit contributions
acs-2.441
 Gravity-2.414
assic-2.402
ikhail-2.394
Tokens-2.349
Token warned
Token ID7728
Feature activation-3.62e-01

Pos logit contributions
acs+0.047
 Gravity+0.046
assic+0.046
ikhail+0.046
Tokens+0.045
Neg logit contributions
 confir-0.040
 contro-0.038
 discharge-0.037
 corpor-0.037
 Jude-0.037
Token that
Token ID326
Feature activation-1.39e-01

Pos logit contributions
 confir+0.584
 contro+0.555
 discharge+0.541
 corpor+0.533
 Jude+0.531
Neg logit contributions
acs-0.697
 Gravity-0.682
assic-0.679
ikhail-0.677
Tokens-0.664
Token the
Token ID262
Feature activation-9.48e-02

Pos logit contributions
 confir+0.228
 contro+0.217
 discharge+0.211
 corpor+0.208
 Jude+0.207
Neg logit contributions
acs-0.263
 Gravity-0.258
assic-0.255
ikhail-0.255
Tokens-0.250
Token day
Token ID1110
Feature activation+1.83e-01

Pos logit contributions
 confir+0.162
 contro+0.154
 discharge+0.150
 corpor+0.148
 Jude+0.147
Neg logit contributions
acs-0.173
 Gravity-0.170
ikhail-0.168
assic-0.168
Tokens-0.164
Token Lew
Token ID8260
Feature activation+6.75e-01

Pos logit contributions
 confir+0.012
 contro+0.012
 discharge+0.011
 corpor+0.011
 Jude+0.011
Neg logit contributions
acs-0.012
 Gravity-0.011
assic-0.011
ikhail-0.011
Tokens-0.011
Token said
Token ID531
Feature activation+1.32e-01

Pos logit contributions
acs+1.161
 Gravity+1.132
assic+1.122
ikhail+1.118
Tokens+1.095
Neg logit contributions
 confir-1.225
 contro-1.172
 discharge-1.145
 corpor-1.129
 Jude-1.127
Token.
Token ID13
Feature activation-1.91e-02

Pos logit contributions
acs+0.270
 Gravity+0.265
assic+0.261
ikhail+0.261
Tokens+0.257
Neg logit contributions
 confir-0.198
 contro-0.186
 discharge-0.181
 corpor-0.178
 Jude-0.177
Token
Token ID198
Feature activation-6.42e-02

Pos logit contributions
 confir+0.026
 contro+0.024
 discharge+0.024
 Jude+0.023
 corpor+0.023
Neg logit contributions
acs-0.042
 Gravity-0.041
assic-0.041
ikhail-0.041
Tokens-0.040
Token
Token ID198
Feature activation-9.59e-02

Pos logit contributions
 confir+0.086
 contro+0.077
 discharge+0.075
 corpor+0.073
 cumulative+0.073
Neg logit contributions
acs-0.145
 Gravity-0.143
ikhail-0.141
assic-0.141
Tokens-0.140
TokenNeither
Token ID27270
Feature activation-1.15e+00

Pos logit contributions
 confir+0.173
 contro+0.168
 discharge+0.164
 Jude+0.162
 corpor+0.162
Neg logit contributions
acs-0.163
 Gravity-0.160
assic-0.159
ikhail-0.159
Tokens-0.153
Token action
Token ID2223
Feature activation+9.50e-02

Pos logit contributions
 confir+1.884
 contro+1.805
 discharge+1.766
 corpor+1.738
 cumulative+1.730
Neg logit contributions
acs-2.179
assic-2.139
ikhail-2.129
 Gravity-2.115
Tokens-2.094
Token will
Token ID481
Feature activation+4.94e-03

Pos logit contributions
acs+0.180
 Gravity+0.177
assic+0.175
ikhail+0.175
Tokens+0.171
Neg logit contributions
 confir-0.156
 contro-0.148
 discharge-0.144
 corpor-0.143
 Jude-0.142
Token extend
Token ID9117
Feature activation-1.23e-01

Pos logit contributions
acs+0.010
 Gravity+0.009
assic+0.009
ikhail+0.009
Tokens+0.009
Neg logit contributions
 confir-0.008
 contro-0.007
 discharge-0.007
 Jude-0.007
 corpor-0.007
Token the
Token ID262
Feature activation-6.32e-02

Pos logit contributions
 confir+0.193
 contro+0.184
 discharge+0.179
 corpor+0.176
 Jude+0.176
Neg logit contributions
acs-0.244
 Gravity-0.238
assic-0.238
ikhail-0.237
Tokens-0.232
Token Oct
Token ID2556
Feature activation-4.52e-01

Pos logit contributions
 confir+0.106
 contro+0.100
 discharge+0.097
 corpor+0.096
 Jude+0.096
Neg logit contributions
acs-0.118
 Gravity-0.116
assic-0.114
ikhail-0.114
Tokens-0.112
Token in
Token ID287
Feature activation-2.83e-03

Pos logit contributions
acs+0.349
 Gravity+0.342
assic+0.339
ikhail+0.338
Tokens+0.334
Neg logit contributions
 confir-0.281
 contro-0.266
 discharge-0.258
 Jude-0.254
 corpor-0.254
Token both
Token ID1111
Feature activation-6.44e-01

Pos logit contributions
 confir+0.004
 contro+0.004
 discharge+0.004
 corpor+0.004
 Jude+0.004
Neg logit contributions
acs-0.006
assic-0.005
 Gravity-0.005
ikhail-0.005
Tokens-0.005
Token official
Token ID1743
Feature activation-3.75e-02

Pos logit contributions
 confir+1.257
 contro+1.211
 discharge+1.184
 corpor+1.179
 Jude+1.172
Neg logit contributions
acs-1.018
assic-0.993
 Gravity-0.989
ikhail-0.987
Tokens-0.961
Token languages
Token ID8950
Feature activation+4.30e-02

Pos logit contributions
 confir+0.086
 contro+0.084
 discharge+0.082
 corpor+0.082
 Jude+0.081
Neg logit contributions
acs-0.046
assic-0.045
 Gravity-0.045
ikhail-0.044
Tokens-0.043
Token.
Token ID13
Feature activation-8.17e-02

Pos logit contributions
acs+0.085
 Gravity+0.083
assic+0.082
ikhail+0.082
Tokens+0.081
Neg logit contributions
 confir-0.068
 contro-0.064
 discharge-0.062
 corpor-0.062
 Jude-0.061
Token Neither
Token ID16126
Feature activation-1.14e+00

Pos logit contributions
 confir+0.136
 contro+0.129
 discharge+0.126
 corpor+0.124
 Jude+0.124
Neg logit contributions
acs-0.154
 Gravity-0.151
assic-0.150
ikhail-0.149
Tokens-0.146
Token language
Token ID3303
Feature activation-1.46e-01

Pos logit contributions
 confir+1.904
 contro+1.825
 discharge+1.771
 corpor+1.767
 Jude+1.741
Neg logit contributions
acs-2.114
assic-2.072
ikhail-2.070
 Gravity-2.061
Tokens-2.022
Token takes
Token ID2753
Feature activation-3.15e-01

Pos logit contributions
 confir+0.245
 contro+0.234
 discharge+0.228
 corpor+0.225
 Jude+0.225
Neg logit contributions
acs-0.270
 Gravity-0.264
assic-0.263
ikhail-0.262
Tokens-0.257
Token precedence
Token ID38177
Feature activation+6.25e-02

Pos logit contributions
 confir+0.526
 contro+0.499
 discharge+0.486
 Jude+0.479
 corpor+0.479
Neg logit contributions
acs-0.590
 Gravity-0.577
assic-0.573
ikhail-0.570
Tokens-0.560
Token over
Token ID625
Feature activation+1.54e-01

Pos logit contributions
acs+0.126
 Gravity+0.123
assic+0.122
ikhail+0.122
Tokens+0.120
Neg logit contributions
 confir-0.095
 contro-0.090
 discharge-0.088
 corpor-0.086
 Jude-0.086
Token the
Token ID262
Feature activation-6.37e-02

Pos logit contributions
acs+0.288
 Gravity+0.282
assic+0.280
ikhail+0.280
Tokens+0.274
Neg logit contributions
 confir-0.256
 contro-0.243
 discharge-0.237
 corpor-0.234
 Jude-0.233
Token Pupp
Token ID20926
Feature activation-8.53e-01

Pos logit contributions
acs+0.097
 Gravity+0.095
assic+0.094
ikhail+0.094
Tokens+0.092
Neg logit contributions
 confir-0.093
 contro-0.089
 discharge-0.086
 corpor-0.085
 Jude-0.085
Tokenies
Token ID444
Feature activation+6.32e-02

Pos logit contributions
 confir+1.548
 contro+1.516
 discharge+1.478
 corpor+1.464
 Jude+1.460
Neg logit contributions
acs-1.406
 Gravity-1.397
assic-1.382
ikhail-1.378
Tokens-1.347
Token stole
Token ID18240
Feature activation-1.99e-01

Pos logit contributions
acs+0.124
 Gravity+0.121
assic+0.120
ikhail+0.120
Tokens+0.118
Neg logit contributions
 confir-0.100
 contro-0.095
 discharge-0.093
 corpor-0.091
 Jude-0.091
Token the
Token ID262
Feature activation+1.69e-01

Pos logit contributions
 confir+0.321
 contro+0.306
 discharge+0.297
 corpor+0.293
 Jude+0.293
Neg logit contributions
acs-0.383
 Gravity-0.374
assic-0.373
ikhail-0.372
Tokens-0.365
Token Sad
Token ID14668
Feature activation+3.76e-01

Pos logit contributions
acs+0.331
 Gravity+0.325
assic+0.322
ikhail+0.321
Tokens+0.315
Neg logit contributions
 confir-0.269
 contro-0.254
 discharge-0.247
 corpor-0.244
 Jude-0.243
Token Pupp
Token ID20926
Feature activation-1.14e+00

Pos logit contributions
acs+0.666
 Gravity+0.651
assic+0.647
ikhail+0.646
Tokens+0.632
Neg logit contributions
 confir-0.664
 contro-0.635
 discharge-0.620
 corpor-0.613
 Jude-0.612
Tokenies
Token ID444
Feature activation+8.44e-02

Pos logit contributions
 confir+2.025
 contro+1.987
 discharge+1.939
 Jude+1.917
 corpor+1.916
Neg logit contributions
acs-1.893
 Gravity-1.886
ikhail-1.869
assic-1.866
Tokens-1.821
Token brand
Token ID4508
Feature activation+4.20e-01

Pos logit contributions
acs+0.166
 Gravity+0.162
assic+0.161
ikhail+0.161
Tokens+0.158
Neg logit contributions
 confir-0.133
 contro-0.126
 discharge-0.123
 corpor-0.121
 Jude-0.121
Token
Token ID960
Feature activation-9.09e-02

Pos logit contributions
acs+0.820
 Gravity+0.804
assic+0.794
ikhail+0.792
Tokens+0.783
Neg logit contributions
 confir-0.667
 contro-0.628
 discharge-0.613
 Jude-0.603
 corpor-0.602
Tokenas
Token ID292
Feature activation+7.33e-02

Pos logit contributions
 confir+0.148
 contro+0.141
 discharge+0.137
 corpor+0.135
 Jude+0.135
Neg logit contributions
acs-0.174
 Gravity-0.170
assic-0.169
ikhail-0.169
Tokens-0.166
Token one
Token ID530
Feature activation+2.51e-01

Pos logit contributions
acs+0.140
 Gravity+0.137
assic+0.136
ikhail+0.135
Tokens+0.133
Neg logit contributions
 confir-0.120
 contro-0.114
 discharge-0.111
 corpor-0.109
 Jude-0.109
Token between
Token ID1022
Feature activation+1.30e-01

Pos logit contributions
acs+0.373
 Gravity+0.365
assic+0.363
ikhail+0.362
Tokens+0.355
Neg logit contributions
 confir-0.318
 contro-0.303
 discharge-0.295
 corpor-0.291
 Jude-0.290
Token sovereign
Token ID18901
Feature activation+1.43e-01

Pos logit contributions
acs+0.253
 Gravity+0.249
ikhail+0.246
assic+0.246
Tokens+0.241
Neg logit contributions
 confir-0.208
 contro-0.195
 discharge-0.190
 corpor-0.187
 cumulative-0.186
Token Israel
Token ID2692
Feature activation-3.55e-01

Pos logit contributions
acs+0.271
 Gravity+0.265
assic+0.263
ikhail+0.262
Tokens+0.258
Neg logit contributions
 confir-0.236
 contro-0.224
 discharge-0.217
 corpor-0.214
 cumulative-0.213
Token and
Token ID290
Feature activation+1.40e-02

Pos logit contributions
 confir+0.548
 contro+0.522
 discharge+0.507
 corpor+0.501
 Jude+0.499
Neg logit contributions
acs-0.705
 Gravity-0.692
assic-0.690
ikhail-0.689
Tokens-0.675
Token the
Token ID262
Feature activation+2.77e-03

Pos logit contributions
acs+0.026
 Gravity+0.026
assic+0.026
ikhail+0.026
Tokens+0.025
Neg logit contributions
 confir-0.023
 contro-0.022
 discharge-0.021
 corpor-0.021
 cumulative-0.021
Token settlements
Token ID18573
Feature activation-1.13e+00

Pos logit contributions
acs+0.005
 Gravity+0.005
assic+0.004
ikhail+0.004
Tokens+0.004
Neg logit contributions
 confir-0.005
 contro-0.005
 discharge-0.005
 corpor-0.005
 cumulative-0.005
Token in
Token ID287
Feature activation-1.39e-02

Pos logit contributions
 confir+1.727
 contro+1.642
 discharge+1.600
 corpor+1.575
 Jude+1.569
Neg logit contributions
acs-2.259
 Gravity-2.223
ikhail-2.220
assic-2.214
Tokens-2.176
Token the
Token ID262
Feature activation-6.54e-02

Pos logit contributions
 confir+0.022
 contro+0.021
 discharge+0.021
 corpor+0.020
 cumulative+0.020
Neg logit contributions
acs-0.027
 Gravity-0.026
ikhail-0.026
assic-0.026
Tokens-0.025
Token territories
Token ID16771
Feature activation+5.56e-02

Pos logit contributions
 confir+0.127
 contro+0.122
 discharge+0.118
 corpor+0.117
 cumulative+0.117
Neg logit contributions
acs-0.104
 Gravity-0.102
assic-0.100
ikhail-0.100
Tokens-0.098
Token ended
Token ID4444
Feature activation+5.52e-01

Pos logit contributions
acs+0.113
 Gravity+0.111
assic+0.110
ikhail+0.110
Tokens+0.108
Neg logit contributions
 confir-0.084
 contro-0.079
 discharge-0.077
 corpor-0.076
 Jude-0.075
Token up
Token ID510
Feature activation+1.35e-01

Pos logit contributions
acs+0.958
 Gravity+0.935
assic+0.926
ikhail+0.926
Tokens+0.906
Neg logit contributions
 confir-1.000
 contro-0.950
 discharge-0.930
 corpor-0.917
 Jude-0.915
Token other
Token ID584
Feature activation+2.45e-02

Pos logit contributions
acs+0.003
 Gravity+0.003
assic+0.003
ikhail+0.003
Tokens+0.002
Neg logit contributions
 confir-0.002
 contro-0.002
 discharge-0.002
 corpor-0.002
 Jude-0.002
Token team
Token ID1074
Feature activation+3.33e-01

Pos logit contributions
acs+0.056
 Gravity+0.055
assic+0.054
ikhail+0.054
Tokens+0.053
Neg logit contributions
 confir-0.031
 contro-0.029
 discharge-0.028
 corpor-0.028
 Jude-0.028
Token,
Token ID11
Feature activation-9.55e-04

Pos logit contributions
acs+0.639
 Gravity+0.627
assic+0.620
ikhail+0.618
Tokens+0.607
Neg logit contributions
 confir-0.539
 contro-0.510
 discharge-0.497
 corpor-0.491
 Jude-0.490
Token his
Token ID465
Feature activation-3.28e-02

Pos logit contributions
 confir+0.002
 contro+0.001
 discharge+0.001
 corpor+0.001
 Jude+0.001
Neg logit contributions
acs-0.002
 Gravity-0.002
assic-0.002
ikhail-0.002
Tokens-0.002
Token team
Token ID1074
Feature activation+2.15e-01

Pos logit contributions
 confir+0.052
 contro+0.049
 discharge+0.048
 corpor+0.047
 Jude+0.047
Neg logit contributions
acs-0.065
 Gravity-0.063
assic-0.063
ikhail-0.063
Tokens-0.062
Tokenfight
Token ID15481
Feature activation-1.13e+00

Pos logit contributions
acs+0.406
 Gravity+0.397
assic+0.395
ikhail+0.394
Tokens+0.386
Neg logit contributions
 confir-0.356
 contro-0.339
 discharge-0.330
 corpor-0.326
 Jude-0.325
Token tim
Token ID4628
Feature activation-1.96e-01

Pos logit contributions
 confir+1.740
 contro+1.678
 discharge+1.641
 corpor+1.598
 cumulative+1.598
Neg logit contributions
acs-2.236
ikhail-2.189
assic-2.176
 Gravity-2.171
Tokens-2.133
Tokenings
Token ID654
Feature activation-2.50e-01

Pos logit contributions
 confir+0.268
 contro+0.253
 discharge+0.245
 corpor+0.240
 Jude+0.239
Neg logit contributions
acs-0.423
 Gravity-0.415
assic-0.414
ikhail-0.413
Tokens-0.407
Token are
Token ID389
Feature activation-1.06e-01

Pos logit contributions
 confir+0.371
 contro+0.352
 discharge+0.342
 corpor+0.336
 Jude+0.335
Neg logit contributions
acs-0.514
 Gravity-0.504
assic-0.502
ikhail-0.501
Tokens-0.492
Token going
Token ID1016
Feature activation-2.27e-01

Pos logit contributions
 confir+0.183
 contro+0.175
 discharge+0.170
 corpor+0.168
 Jude+0.168
Neg logit contributions
acs-0.191
 Gravity-0.186
assic-0.185
ikhail-0.185
Tokens-0.181
Token to
Token ID284
Feature activation-2.00e-02

Pos logit contributions
 confir+0.338
 contro+0.322
 discharge+0.311
 corpor+0.306
 Jude+0.306
Neg logit contributions
acs-0.464
 Gravity-0.454
assic-0.453
ikhail-0.452
Tokens-0.445
Token success
Token ID1943
Feature activation-3.25e-01

Pos logit contributions
acs+0.200
 Gravity+0.196
assic+0.195
ikhail+0.194
Tokens+0.191
Neg logit contributions
 confir-0.154
 contro-0.146
 discharge-0.142
 corpor-0.140
 Jude-0.140
Token".
Token ID1911
Feature activation-2.50e-01

Pos logit contributions
 confir+0.432
 contro+0.408
 discharge+0.394
 corpor+0.388
 Jude+0.386
Neg logit contributions
acs-0.717
 Gravity-0.703
assic-0.701
ikhail-0.700
Tokens-0.687
Token
Token ID198
Feature activation-1.60e-01

Pos logit contributions
 confir+0.309
 contro+0.289
 discharge+0.278
 corpor+0.273
 Jude+0.272
Neg logit contributions
acs-0.578
 Gravity-0.568
assic-0.564
ikhail-0.563
Tokens-0.555
Token
Token ID198
Feature activation-1.69e-01

Pos logit contributions
 confir+0.212
 contro+0.192
 discharge+0.185
 corpor+0.182
 cumulative+0.181
Neg logit contributions
acs-0.364
 Gravity-0.357
assic-0.353
ikhail-0.353
Tokens-0.350
TokenL
Token ID43
Feature activation-3.35e-02

Pos logit contributions
 confir+0.282
 contro+0.267
 discharge+0.260
 corpor+0.256
 Jude+0.256
Neg logit contributions
acs-0.320
 Gravity-0.313
assic-0.311
ikhail-0.310
Tokens-0.305
Tokenever
Token ID964
Feature activation-1.13e+00

Pos logit contributions
 confir+0.037
 contro+0.034
 discharge+0.032
 Jude+0.032
 corpor+0.032
Neg logit contributions
acs-0.083
assic-0.081
 Gravity-0.081
ikhail-0.081
Tokens-0.079
Token,
Token ID11
Feature activation-4.42e-02

Pos logit contributions
 confir+1.858
 contro+1.774
 discharge+1.723
 corpor+1.702
 cumulative+1.689
Neg logit contributions
acs-2.128
ikhail-2.080
assic-2.079
 Gravity-2.077
Tokens-2.038
Token like
Token ID588
Feature activation+1.37e-01

Pos logit contributions
 confir+0.067
 contro+0.063
 discharge+0.062
 Jude+0.061
 corpor+0.061
Neg logit contributions
acs-0.088
 Gravity-0.088
ikhail-0.085
assic-0.085
 Mov-0.084
Token Gibbs
Token ID41071
Feature activation+2.31e-01

Pos logit contributions
acs+0.313
 Gravity+0.309
assic+0.305
ikhail+0.305
Tokens+0.300
Neg logit contributions
 confir-0.171
 contro-0.159
 discharge-0.153
 corpor-0.151
 Jude-0.150
Token,
Token ID11
Feature activation-4.60e-02

Pos logit contributions
acs+0.443
 Gravity+0.433
assic+0.429
ikhail+0.429
Tokens+0.420
Neg logit contributions
 confir-0.375
 contro-0.355
 discharge-0.346
 corpor-0.342
 Jude-0.341
Token was
Token ID373
Feature activation-2.21e-01

Pos logit contributions
 confir+0.079
 contro+0.075
 discharge+0.074
 Jude+0.073
 corpor+0.073
Neg logit contributions
acs-0.083
 Gravity-0.082
assic-0.081
ikhail-0.080
Tokens-0.079
Token "
Token ID366
Feature activation-2.21e-03

Pos logit contributions
acs+0.072
 Gravity+0.070
assic+0.070
ikhail+0.070
Tokens+0.069
Neg logit contributions
 confir-0.059
 contro-0.056
 discharge-0.055
 corpor-0.054
 Jude-0.054
Tokenj
Token ID73
Feature activation+8.12e-02

Pos logit contributions
 confir+0.004
 contro+0.003
 discharge+0.003
 corpor+0.003
 Jude+0.003
Neg logit contributions
acs-0.004
 Gravity-0.004
assic-0.004
ikhail-0.004
Tokens-0.004
Tokenokes
Token ID3369
Feature activation+2.55e-01

Pos logit contributions
acs+0.134
 Gravity+0.131
assic+0.130
ikhail+0.130
Tokens+0.127
Neg logit contributions
 confir-0.153
 contro-0.147
 discharge-0.144
 corpor-0.142
 Jude-0.142
Token"
Token ID1
Feature activation-1.56e-01

Pos logit contributions
acs+0.524
 Gravity+0.513
assic+0.511
ikhail+0.509
Tokens+0.500
Neg logit contributions
 confir-0.379
 contro-0.358
 discharge-0.348
 corpor-0.342
 Jude-0.341
Token about
Token ID546
Feature activation+1.93e-01

Pos logit contributions
 confir+0.237
 contro+0.225
 discharge+0.218
 corpor+0.215
 Jude+0.215
Neg logit contributions
acs-0.316
 Gravity-0.310
assic-0.308
ikhail-0.307
Tokens-0.302
Token Internal
Token ID18628
Feature activation-1.12e+00

Pos logit contributions
acs+0.351
 Gravity+0.344
assic+0.341
ikhail+0.340
Tokens+0.333
Neg logit contributions
 confir-0.331
 contro-0.314
 discharge-0.306
 corpor-0.302
 Jude-0.302
Token Revenue
Token ID20197
Feature activation-3.17e-01

Pos logit contributions
 confir+1.281
 contro+1.256
 discharge+1.255
 Jude+1.253
 corpor+1.198
Neg logit contributions
acs-2.601
assic-2.583
Tokens-2.537
ikhail-2.520
 Gravity-2.503
Token Service
Token ID4809
Feature activation+2.59e-02

Pos logit contributions
 confir+0.343
 contro+0.318
 discharge+0.308
 corpor+0.300
 Jude+0.298
Neg logit contributions
acs-0.777
 Gravity-0.764
assic-0.762
ikhail-0.761
Tokens-0.750
Token audits
Token ID41973
Feature activation-3.86e-01

Pos logit contributions
acs+0.051
 Gravity+0.050
assic+0.050
ikhail+0.050
Tokens+0.049
Neg logit contributions
 confir-0.040
 contro-0.038
 discharge-0.036
 Jude-0.036
 corpor-0.036
Token to
Token ID284
Feature activation-4.78e-02

Pos logit contributions
 confir+0.574
 contro+0.544
 discharge+0.529
 corpor+0.521
 Jude+0.519
Neg logit contributions
acs-0.790
 Gravity-0.775
assic-0.771
ikhail-0.770
Tokens-0.756
Token the
Token ID262
Feature activation-4.52e-03

Pos logit contributions
 confir+0.078
 contro+0.075
 discharge+0.073
 corpor+0.072
 Jude+0.072
Neg logit contributions
acs-0.091
 Gravity-0.089
assic-0.088
ikhail-0.088
Tokens-0.087
Token is
Token ID318
Feature activation+4.61e-03

Pos logit contributions
 confir+0.438
 contro+0.418
 discharge+0.407
 corpor+0.402
 Jude+0.401
Neg logit contributions
acs-0.465
 Gravity-0.453
assic-0.452
ikhail-0.451
Tokens-0.442
Token part
Token ID636
Feature activation+1.05e-01

Pos logit contributions
acs+0.009
 Gravity+0.009
assic+0.009
ikhail+0.009
Tokens+0.009
Neg logit contributions
 confir-0.007
 contro-0.007
 discharge-0.007
 corpor-0.006
 Jude-0.006
Token of
Token ID286
Feature activation-8.25e-02

Pos logit contributions
acs+0.217
 Gravity+0.212
assic+0.211
ikhail+0.211
Tokens+0.207
Neg logit contributions
 confir-0.154
 contro-0.145
 discharge-0.141
 corpor-0.139
 Jude-0.138
Token the
Token ID262
Feature activation-5.17e-02

Pos logit contributions
 confir+0.138
 contro+0.131
 discharge+0.128
 corpor+0.126
 Jude+0.126
Neg logit contributions
acs-0.154
 Gravity-0.150
assic-0.150
ikhail-0.150
Tokens-0.147
Token Virtual
Token ID15595
Feature activation-5.65e-01

Pos logit contributions
 confir+0.095
 contro+0.091
 discharge+0.089
 corpor+0.088
 Jude+0.088
Neg logit contributions
acs-0.088
 Gravity-0.086
assic-0.085
ikhail-0.085
Tokens-0.083
Token Console
Token ID24371
Feature activation-1.11e+00

Pos logit contributions
 confir+1.023
 contro+0.986
 Jude+0.959
 discharge+0.954
 cumulative+0.951
Neg logit contributions
acs-0.969
ikhail-0.939
assic-0.930
 Gravity-0.923
ochem-0.910
Token service
Token ID2139
Feature activation+1.02e-01

Pos logit contributions
 confir+1.030
 contro+0.953
 discharge+0.902
 corpor+0.881
 Jude+0.878
Neg logit contributions
acs-2.902
 Gravity-2.852
assic-2.846
ikhail-2.841
Tokens-2.798
Token,
Token ID11
Feature activation+2.08e-02

Pos logit contributions
acs+0.195
 Gravity+0.193
ikhail+0.189
assic+0.189
Tokens+0.186
Neg logit contributions
 confir-0.168
 contro-0.158
 discharge-0.154
 corpor-0.152
 Jude-0.151
Token which
Token ID543
Feature activation-5.93e-02

Pos logit contributions
acs+0.051
 Gravity+0.050
ikhail+0.050
assic+0.049
Tokens+0.049
Neg logit contributions
 confir-0.023
 contro-0.020
 discharge-0.020
 corpor-0.020
 Jude-0.019
Token brings
Token ID6774
Feature activation-3.77e-01

Pos logit contributions
 confir+0.088
 contro+0.083
 discharge+0.081
 corpor+0.080
 Jude+0.080
Neg logit contributions
acs-0.122
 Gravity-0.119
assic-0.119
ikhail-0.118
Tokens-0.116
Token you
Token ID345
Feature activation+7.31e-02

Pos logit contributions
 confir+0.629
 contro+0.593
 discharge+0.581
 corpor+0.572
 Jude+0.571
Neg logit contributions
acs-0.707
 Gravity-0.694
assic-0.691
ikhail-0.687
Tokens-0.672
Token a
Token ID257
Feature activation-1.30e-01

Pos logit contributions
 confir+0.272
 contro+0.259
 discharge+0.252
 corpor+0.248
 Jude+0.248
Neg logit contributions
acs-0.314
 Gravity-0.307
assic-0.305
ikhail-0.304
Tokens-0.298
Token super
Token ID2208
Feature activation+7.14e-01

Pos logit contributions
 confir+0.205
 contro+0.194
 discharge+0.189
 corpor+0.186
 Jude+0.186
Neg logit contributions
acs-0.252
 Gravity-0.248
assic-0.246
ikhail-0.246
Tokens-0.240
Token-
Token ID12
Feature activation+1.12e-01

Pos logit contributions
acs+1.300
 Gravity+1.270
assic+1.260
ikhail+1.259
Tokens+1.224
Neg logit contributions
 confir-1.228
 contro-1.165
 discharge-1.139
 Jude-1.123
 corpor-1.120
Tokenp
Token ID79
Feature activation+3.83e-01

Pos logit contributions
acs+0.206
 Gravity+0.201
assic+0.200
ikhail+0.199
Tokens+0.195
Neg logit contributions
 confir-0.190
 contro-0.181
 discharge-0.177
 corpor-0.174
 Jude-0.174
Tokenreg
Token ID2301
Feature activation-1.55e-01

Pos logit contributions
acs+0.681
 Gravity+0.660
assic+0.660
ikhail+0.657
Tokens+0.641
Neg logit contributions
 confir-0.680
 contro-0.648
 discharge-0.630
 corpor-0.623
 Jude-0.623
Tokennant
Token ID22057
Feature activation-1.11e+00

Pos logit contributions
 confir+0.265
 contro+0.252
 discharge+0.247
 corpor+0.245
 Jude+0.244
Neg logit contributions
acs-0.283
 Gravity-0.277
ikhail-0.274
assic-0.272
Tokens-0.272
Token Ann
Token ID5506
Feature activation+1.37e-01

Pos logit contributions
 confir+1.933
 contro+1.866
 discharge+1.820
 Jude+1.801
 corpor+1.801
Neg logit contributions
acs-1.984
assic-1.932
ikhail-1.928
 Gravity-1.915
Tokens-1.891
Tokenal
Token ID282
Feature activation-3.65e-01

Pos logit contributions
acs+0.383
 Gravity+0.377
assic+0.376
ikhail+0.376
Tokens+0.370
Neg logit contributions
 confir-0.101
 contro-0.090
 discharge-0.084
 corpor-0.081
 cumulative-0.080
Tokenise
Token ID786
Feature activation-3.14e-01

Pos logit contributions
 confir+0.572
 contro+0.539
 discharge+0.522
 corpor+0.517
 cumulative+0.514
Neg logit contributions
acs-0.724
 Gravity-0.708
assic-0.706
ikhail-0.705
Tokens-0.686
Token
Token ID851
Feature activation+1.65e-01

Pos logit contributions
 confir+0.488
 contro+0.464
 discharge+0.451
 corpor+0.445
 Jude+0.443
Neg logit contributions
acs-0.624
 Gravity-0.611
assic-0.609
ikhail-0.607
Tokens-0.596
Token knowing
Token ID6970
Feature activation+1.89e-01

Pos logit contributions
acs+0.317
 Gravity+0.311
assic+0.308
ikhail+0.307
Tokens+0.302
Neg logit contributions
 confir-0.268
 contro-0.254
 discharge-0.247
 corpor-0.244
 Jude-0.243
Token choking
Token ID39302
Feature activation-4.33e-01

Pos logit contributions
 confir+0.814
 contro+0.774
 discharge+0.757
 corpor+0.746
 Jude+0.744
Neg logit contributions
acs-1.019
assic-1.001
ikhail-0.999
 Gravity-0.995
Tokens-0.975
Token Jennifer
Token ID16348
Feature activation-2.51e-01

Pos logit contributions
 confir+0.761
 contro+0.731
 discharge+0.714
 Jude+0.709
 corpor+0.706
Neg logit contributions
acs-0.770
assic-0.747
ikhail-0.747
 Gravity-0.746
Tokens-0.732
Token Lawrence
Token ID13914
Feature activation-5.00e-01

Pos logit contributions
 confir+0.500
 contro+0.481
 discharge+0.471
 corpor+0.466
 Jude+0.465
Neg logit contributions
acs-0.387
 Gravity-0.376
assic-0.375
ikhail-0.374
Tokens-0.364
Token,
Token ID837
Feature activation-2.68e-01

Pos logit contributions
 confir+0.692
 contro+0.655
 discharge+0.634
 corpor+0.625
 Jude+0.622
Neg logit contributions
acs-1.074
 Gravity-1.054
ikhail-1.053
assic-1.051
Tokens-1.034
Token was
Token ID373
Feature activation-2.12e-01

Pos logit contributions
 confir+0.468
 contro+0.448
 discharge+0.436
 corpor+0.432
 Jude+0.430
Neg logit contributions
acs-0.482
 Gravity-0.469
assic-0.469
ikhail-0.468
Tokens-0.459
Token round
Token ID2835
Feature activation-1.10e+00

Pos logit contributions
 confir+0.368
 contro+0.352
 discharge+0.343
 corpor+0.339
 Jude+0.338
Neg logit contributions
acs-0.383
 Gravity-0.375
assic-0.373
ikhail-0.373
Tokens-0.365
Tokenly
Token ID306
Feature activation-6.44e-02

Pos logit contributions
 confir+2.157
 contro+2.111
 discharge+2.079
 corpor+2.071
 cumulative+2.050
Neg logit contributions
acs-1.684
ikhail-1.640
assic-1.623
Tokens-1.611
 Gravity-1.610
Token criticized
Token ID12318
Feature activation-1.08e-01

Pos logit contributions
 confir+0.108
 contro+0.103
 discharge+0.100
 corpor+0.099
 Jude+0.099
Neg logit contributions
acs-0.120
 Gravity-0.117
assic-0.116
ikhail-0.116
Tokens-0.114
Token for
Token ID329
Feature activation-1.63e-01

Pos logit contributions
 confir+0.166
 contro+0.157
 discharge+0.153
 corpor+0.150
 Jude+0.150
Neg logit contributions
acs-0.217
 Gravity-0.213
assic-0.212
ikhail-0.211
Tokens-0.207
Token showing
Token ID4478
Feature activation+1.01e-01

Pos logit contributions
 confir+0.254
 contro+0.241
 discharge+0.234
 corpor+0.231
 Jude+0.230
Neg logit contributions
acs-0.323
 Gravity-0.316
assic-0.314
ikhail-0.314
Tokens-0.308
Token excessive
Token ID13181
Feature activation-1.23e-01

Pos logit contributions
acs+0.185
assic+0.180
 Gravity+0.180
ikhail+0.180
Tokens+0.176
Neg logit contributions
 confir-0.171
 contro-0.163
 discharge-0.159
 Jude-0.158
 corpor-0.157
Token and
Token ID290
Feature activation-5.73e-02

Pos logit contributions
 confir+0.131
 contro+0.124
 discharge+0.121
 corpor+0.119
 Jude+0.119
Neg logit contributions
acs-0.159
 Gravity-0.156
assic-0.155
ikhail-0.155
Tokens-0.152
Token all
Token ID477
Feature activation-5.78e-02

Pos logit contributions
 confir+0.088
 contro+0.084
 discharge+0.081
 corpor+0.080
 Jude+0.080
Neg logit contributions
acs-0.115
 Gravity-0.112
assic-0.112
ikhail-0.112
Tokens-0.110
Token the
Token ID262
Feature activation-1.35e-02

Pos logit contributions
 confir+0.087
 contro+0.083
 discharge+0.080
 corpor+0.079
 Jude+0.079
Neg logit contributions
acs-0.117
 Gravity-0.115
assic-0.114
ikhail-0.114
Tokens-0.112
Token til
Token ID21502
Feature activation-5.67e-01

Pos logit contributions
 confir+0.024
 contro+0.023
 discharge+0.022
 corpor+0.022
 Jude+0.022
Neg logit contributions
acs-0.024
 Gravity-0.023
assic-0.023
ikhail-0.023
Tokens-0.023
Tokenap
Token ID499
Feature activation+3.32e-01

Pos logit contributions
 confir+0.862
 contro+0.831
 discharge+0.816
 corpor+0.797
 cumulative+0.793
Neg logit contributions
 Gravity-1.106
acs-1.094
ikhail-1.093
assic-1.082
Tokens-1.075
Tokenia
Token ID544
Feature activation+8.13e-01

Pos logit contributions
acs+0.593
 Gravity+0.584
assic+0.579
ikhail+0.578
Tokens+0.569
Neg logit contributions
 confir-0.577
 contro-0.553
 discharge-0.540
 corpor-0.533
 Jude-0.531
Token fil
Token ID1226
Feature activation+2.21e-02

Pos logit contributions
acs+1.554
 Gravity+1.516
assic+1.504
ikhail+1.500
Tokens+1.471
Neg logit contributions
 confir-1.328
 contro-1.257
 discharge-1.219
 Jude-1.211
 corpor-1.205
Tokenlets
Token ID5289
Feature activation+4.10e-01

Pos logit contributions
acs+0.055
 Gravity+0.054
assic+0.054
ikhail+0.054
Tokens+0.053
Neg logit contributions
 confir-0.023
 contro-0.021
 discharge-0.021
 corpor-0.020
 Jude-0.020
Token are
Token ID389
Feature activation-1.03e-02

Pos logit contributions
acs+0.835
 Gravity+0.819
assic+0.808
ikhail+0.806
Tokens+0.790
Neg logit contributions
 confir-0.620
 contro-0.582
 Jude-0.560
 discharge-0.560
 corpor-0.556
Token the
Token ID262
Feature activation+5.78e-02

Pos logit contributions
 confir+0.017
 contro+0.016
 discharge+0.015
 corpor+0.015
 Jude+0.015
Neg logit contributions
acs-0.020
 Gravity-0.019
assic-0.019
ikhail-0.019
Tokens-0.019
Token same
Token ID976
Feature activation+3.13e-01

Pos logit contributions
acs+0.114
 Gravity+0.111
assic+0.111
ikhail+0.110
Tokens+0.108
Neg logit contributions
 confir-0.091
 contro-0.087
 discharge-0.084
 corpor-0.083
 Jude-0.083
Tokenings
Token ID654
Feature activation-1.93e-02

Pos logit contributions
acs+0.615
assic+0.599
 Gravity+0.599
ikhail+0.593
Tokens+0.581
Neg logit contributions
 confir-0.500
 contro-0.474
 discharge-0.459
 corpor-0.453
 cumulative-0.451
Tokenhead
Token ID2256
Feature activation-2.60e-01

Pos logit contributions
 confir+0.037
 contro+0.035
 discharge+0.034
 corpor+0.034
 Jude+0.034
Neg logit contributions
acs-0.032
assic-0.031
ikhail-0.031
 Gravity-0.031
Tokens-0.030
Token [
Token ID685
Feature activation+5.78e-01

Pos logit contributions
 confir+0.432
 contro+0.413
 discharge+0.401
 corpor+0.397
 Jude+0.396
Neg logit contributions
acs-0.488
assic-0.477
ikhail-0.476
 Gravity-0.476
Tokens-0.467
Tokenwho
Token ID8727
Feature activation+8.12e-02

Pos logit contributions
acs+1.094
 Gravity+1.060
assic+1.056
ikhail+1.056
Tokens+1.039
Neg logit contributions
 confir-0.963
 contro-0.910
 discharge-0.889
 cumulative-0.871
 Jude-0.871
Token gave
Token ID2921
Feature activation+8.54e-02

Pos logit contributions
acs+0.125
 Gravity+0.121
assic+0.121
ikhail+0.121
Tokens+0.118
Neg logit contributions
 confir-0.162
 contro-0.156
 discharge-0.153
 corpor-0.152
 Jude-0.151
Token Lear
Token ID8010
Feature activation+7.18e-01

Pos logit contributions
acs+0.162
 Gravity+0.158
assic+0.158
ikhail+0.157
Tokens+0.154
Neg logit contributions
 confir-0.140
 contro-0.134
 discharge-0.130
 corpor-0.128
 Jude-0.128
Tokeny
Token ID88
Feature activation-1.87e-01

Pos logit contributions
acs+1.312
 Gravity+1.283
assic+1.273
ikhail+1.272
Tokens+1.242
Neg logit contributions
 confir-1.233
 contro-1.172
 discharge-1.145
 corpor-1.127
 Jude-1.125
Token his
Token ID465
Feature activation+1.76e-01

Pos logit contributions
 confir+0.313
 contro+0.300
 discharge+0.293
 corpor+0.289
 Jude+0.289
Neg logit contributions
acs-0.347
assic-0.338
 Gravity-0.338
ikhail-0.337
Tokens-0.332
Token first
Token ID717
Feature activation-9.30e-03

Pos logit contributions
acs+0.343
 Gravity+0.335
assic+0.335
ikhail+0.334
Tokens+0.328
Neg logit contributions
 confir-0.278
 contro-0.265
 discharge-0.259
 corpor-0.255
 Jude-0.255
Token LSD
Token ID27483
Feature activation+1.61e-01

Pos logit contributions
 confir+0.016
 contro+0.015
 discharge+0.015
 corpor+0.015
 Jude+0.015
Neg logit contributions
acs-0.017
 Gravity-0.016
assic-0.016
ikhail-0.016
Tokens-0.016
Token trip
Token ID5296
Feature activation+4.34e-02

Pos logit contributions
acs+0.278
 Gravity+0.271
assic+0.271
ikhail+0.269
Tokens+0.264
Neg logit contributions
 confir-0.293
 contro-0.281
 discharge-0.275
 corpor-0.271
 Jude-0.270
Token from
Token ID422
Feature activation-1.96e-02

Pos logit contributions
 confir+0.782
 contro+0.743
 discharge+0.723
 corpor+0.710
 Jude+0.708
Neg logit contributions
acs-1.061
 Gravity-1.039
assic-1.035
ikhail-1.032
Tokens-1.014
Token his
Token ID465
Feature activation+1.29e-01

Pos logit contributions
 confir+0.032
 contro+0.030
 discharge+0.029
 Jude+0.029
 cumulative+0.029
Neg logit contributions
acs-0.038
 Gravity-0.037
assic-0.036
ikhail-0.036
Tokens-0.036
Token boss
Token ID6478
Feature activation+1.27e-01

Pos logit contributions
acs+0.245
 Gravity+0.240
assic+0.237
ikhail+0.236
Tokens+0.232
Neg logit contributions
 confir-0.209
 contro-0.197
 discharge-0.191
 Jude-0.190
 corpor-0.189
Token Hood
Token ID17233
Feature activation-3.51e-01

Pos logit contributions
acs+0.242
 Gravity+0.237
assic+0.235
ikhail+0.234
Tokens+0.229
Neg logit contributions
 confir-0.207
 contro-0.197
 discharge-0.191
 Jude-0.188
 corpor-0.188
Tokena
Token ID64
Feature activation+1.73e-01

Pos logit contributions
 confir+0.563
 contro+0.536
 discharge+0.522
 corpor+0.515
 Jude+0.514
Neg logit contributions
acs-0.677
 Gravity-0.664
assic-0.661
ikhail-0.659
Tokens-0.647
Token despite
Token ID3805
Feature activation+7.50e-01

Pos logit contributions
acs+0.342
 Gravity+0.334
assic+0.333
ikhail+0.332
Tokens+0.325
Neg logit contributions
 confir-0.271
 contro-0.257
 discharge-0.250
 Jude-0.246
 corpor-0.246
Token the
Token ID262
Feature activation+5.99e-02

Pos logit contributions
acs+1.386
 Gravity+1.367
assic+1.341
ikhail+1.334
Tokens+1.313
Neg logit contributions
 confir-1.249
 contro-1.181
 discharge-1.145
 Jude-1.137
 corpor-1.129
Token fact
Token ID1109
Feature activation-1.91e-01

Pos logit contributions
acs+0.111
 Gravity+0.109
assic+0.107
ikhail+0.107
Tokens+0.105
Neg logit contributions
 confir-0.101
 contro-0.096
 discharge-0.093
 Jude-0.092
 corpor-0.092
Token that
Token ID326
Feature activation+6.29e-02

Pos logit contributions
 confir+0.305
 contro+0.290
 discharge+0.282
 corpor+0.278
 Jude+0.277
Neg logit contributions
acs-0.371
 Gravity-0.363
assic-0.361
ikhail-0.360
Tokens-0.353
Token it
Token ID340
Feature activation+2.13e-02

Pos logit contributions
acs+0.122
 Gravity+0.119
assic+0.118
ikhail+0.117
Tokens+0.115
Neg logit contributions
 confir-0.101
 contro-0.096
 discharge-0.093
 Jude-0.092
 corpor-0.091
Token is
Token ID318
Feature activation+5.62e-02

Pos logit contributions
acs+0.037
 Gravity+0.036
assic+0.036
ikhail+0.036
Tokens+0.035
Neg logit contributions
 confir-0.038
 contro-0.036
 discharge-0.036
 Jude-0.035
 corpor-0.035
Token Boston
Token ID6182
Feature activation+6.45e-02

Pos logit contributions
acs+0.043
assic+0.042
 Gravity+0.042
ikhail+0.042
Tokens+0.041
Neg logit contributions
 confir-0.052
 contro-0.050
 discharge-0.049
 Jude-0.049
 corpor-0.049
Token (
Token ID357
Feature activation-1.86e-01

Pos logit contributions
acs+0.125
 Gravity+0.122
assic+0.122
ikhail+0.122
Tokens+0.119
Neg logit contributions
 confir-0.103
 contro-0.098
 discharge-0.095
 corpor-0.094
 Jude-0.094
Tokenpictured
Token ID28852
Feature activation-3.72e-01

Pos logit contributions
 confir+0.307
 contro+0.292
 discharge+0.285
 corpor+0.281
 Jude+0.280
Neg logit contributions
acs-0.353
 Gravity-0.345
assic-0.343
ikhail-0.342
Tokens-0.336
Token),
Token ID828
Feature activation+1.29e-01

Pos logit contributions
 confir+0.605
 contro+0.579
 discharge+0.563
 corpor+0.556
 Jude+0.554
Neg logit contributions
acs-0.712
 Gravity-0.695
assic-0.692
ikhail-0.691
Tokens-0.677
Token the
Token ID262
Feature activation-3.31e-02

Pos logit contributions
acs+0.243
 Gravity+0.237
assic+0.236
ikhail+0.236
Tokens+0.231
Neg logit contributions
 confir-0.212
 contro-0.202
 discharge-0.197
 corpor-0.195
 Jude-0.194
Token Latin
Token ID9133
Feature activation+9.03e-01

Pos logit contributions
 confir+0.061
 contro+0.059
 discharge+0.057
 corpor+0.057
 Jude+0.057
Neg logit contributions
acs-0.056
 Gravity-0.054
assic-0.054
ikhail-0.054
Tokens-0.053
Token Academy
Token ID8581
Feature activation+7.51e-02

Pos logit contributions
acs+1.558
 Gravity+1.528
assic+1.510
ikhail+1.498
Tokens+1.464
Neg logit contributions
 confir-1.648
 contro-1.570
 discharge-1.533
 corpor-1.512
 cumulative-1.503
Token,
Token ID11
Feature activation+9.85e-02

Pos logit contributions
acs+0.147
 Gravity+0.144
assic+0.143
ikhail+0.143
Tokens+0.140
Neg logit contributions
 confir-0.119
 contro-0.113
 discharge-0.110
 corpor-0.108
 Jude-0.108
Token some
Token ID617
Feature activation-5.62e-02

Pos logit contributions
acs+0.184
 Gravity+0.180
assic+0.179
ikhail+0.179
Tokens+0.175
Neg logit contributions
 confir-0.164
 contro-0.157
 discharge-0.153
 corpor-0.151
 Jude-0.151
Token areas
Token ID3006
Feature activation+1.09e-02

Pos logit contributions
 confir+0.097
 contro+0.093
 discharge+0.091
 corpor+0.090
 Jude+0.089
Neg logit contributions
acs-0.102
 Gravity-0.099
assic-0.099
ikhail-0.099
Tokens-0.097
Token in
Token ID287
Feature activation+5.77e-02

Pos logit contributions
acs+0.022
 Gravity+0.022
assic+0.022
ikhail+0.022
Tokens+0.021
Neg logit contributions
 confir-0.016
 contro-0.015
 discharge-0.015
 corpor-0.015
 Jude-0.015
Token pick
Token ID2298
Feature activation+4.20e-01

Pos logit contributions
 confir+0.144
 contro+0.137
 discharge+0.133
 corpor+0.132
 Jude+0.131
Neg logit contributions
acs-0.176
 Gravity-0.172
assic-0.171
ikhail-0.171
Tokens-0.167
Token in
Token ID287
Feature activation+4.83e-02

Pos logit contributions
acs+0.854
 Gravity+0.839
assic+0.832
ikhail+0.832
Tokens+0.811
Neg logit contributions
 confir-0.636
 contro-0.596
 discharge-0.578
 corpor-0.573
 Jude-0.569
Token the
Token ID262
Feature activation+2.09e-02

Pos logit contributions
acs+0.098
 Gravity+0.096
assic+0.096
ikhail+0.095
Tokens+0.094
Neg logit contributions
 confir-0.073
 contro-0.069
 discharge-0.067
 corpor-0.066
 Jude-0.066
Token 2015
Token ID1853
Feature activation-2.34e-01

Pos logit contributions
acs+0.037
 Gravity+0.036
assic+0.036
ikhail+0.036
Tokens+0.035
Neg logit contributions
 confir-0.037
 contro-0.035
 discharge-0.035
 corpor-0.034
 Jude-0.034
Token NBA
Token ID7403
Feature activation+6.69e-02

Pos logit contributions
 confir+0.386
 contro+0.369
 discharge+0.359
 corpor+0.355
 Jude+0.354
Neg logit contributions
acs-0.440
 Gravity-0.430
assic-0.429
ikhail-0.428
Tokens-0.420
Token draft
Token ID4538
Feature activation+7.65e-01

Pos logit contributions
acs+0.142
 Gravity+0.140
assic+0.139
ikhail+0.139
Tokens+0.136
Neg logit contributions
 confir-0.095
 contro-0.089
 discharge-0.086
 corpor-0.085
 Jude-0.085
Token by
Token ID416
Feature activation-4.41e-02

Pos logit contributions
acs+1.427
 Gravity+1.409
assic+1.397
ikhail+1.396
Tokens+1.363
Neg logit contributions
 confir-1.272
 contro-1.198
 discharge-1.164
 corpor-1.157
 Jude-1.150
Token the
Token ID262
Feature activation-1.42e-02

Pos logit contributions
 confir+0.070
 contro+0.066
 discharge+0.064
 corpor+0.064
 Jude+0.063
Neg logit contributions
acs-0.086
 Gravity-0.085
ikhail-0.084
assic-0.084
Tokens-0.082
Token Philadelphia
Token ID8857
Feature activation+2.41e-02

Pos logit contributions
 confir+0.027
 contro+0.026
 discharge+0.025
 corpor+0.025
 Jude+0.025
Neg logit contributions
acs-0.024
 Gravity-0.023
assic-0.023
ikhail-0.023
Tokens-0.022
Token 76
Token ID8684
Feature activation-1.42e-01

Pos logit contributions
acs+0.046
 Gravity+0.045
ikhail+0.044
assic+0.044
Tokens+0.044
Neg logit contributions
 confir-0.040
 contro-0.038
 discharge-0.037
 corpor-0.036
 Jude-0.036
Tokeners
Token ID364
Feature activation+2.49e-01

Pos logit contributions
 confir+0.277
 contro+0.264
 discharge+0.258
 corpor+0.256
 Jude+0.255
Neg logit contributions
acs-0.227
 Gravity-0.220
assic-0.219
ikhail-0.218
Tokens-0.213
Token video
Token ID2008
Feature activation-3.34e-01

Pos logit contributions
acs+0.802
 Gravity+0.793
assic+0.781
ikhail+0.777
Tokens+0.766
Neg logit contributions
 confir-0.709
 contro-0.666
 discharge-0.651
 Jude-0.642
 corpor-0.640
Token of
Token ID286
Feature activation+8.03e-02

Pos logit contributions
 confir+0.546
 contro+0.520
 discharge+0.506
 corpor+0.499
 Jude+0.498
Neg logit contributions
acs-0.636
 Gravity-0.622
assic-0.619
ikhail-0.617
Tokens-0.605
Token your
Token ID534
Feature activation+1.35e-02

Pos logit contributions
acs+0.145
 Gravity+0.143
assic+0.141
ikhail+0.141
Tokens+0.138
Neg logit contributions
 confir-0.139
 contro-0.132
 discharge-0.128
 corpor-0.127
 Jude-0.127
Token owner
Token ID4870
Feature activation+9.31e-02

Pos logit contributions
acs+0.026
 Gravity+0.025
assic+0.025
ikhail+0.025
Tokens+0.025
Neg logit contributions
 confir-0.022
 contro-0.021
 discharge-0.020
 Jude-0.020
 corpor-0.020
Token dancing
Token ID15360
Feature activation-7.23e-02

Pos logit contributions
acs+0.172
 Gravity+0.168
assic+0.167
ikhail+0.166
Tokens+0.164
Neg logit contributions
 confir-0.157
 contro-0.150
 discharge-0.146
 corpor-0.144
 Jude-0.144
Token in
Token ID287
Feature activation+5.66e-02

Pos logit contributions
 confir+0.118
 contro+0.112
 discharge+0.109
 corpor+0.108
 Jude+0.107
Neg logit contributions
acs-0.138
 Gravity-0.135
assic-0.134
ikhail-0.134
Tokens-0.131
Token the
Token ID262
Feature activation-4.12e-02

Pos logit contributions
acs+0.108
 Gravity+0.106
assic+0.105
ikhail+0.105
Tokens+0.103
Neg logit contributions
 confir-0.092
 contro-0.088
 discharge-0.085
 corpor-0.084
 Jude-0.084
Token locker
Token ID17355
Feature activation+1.59e-01

Pos logit contributions
 confir+0.067
 contro+0.064
 discharge+0.062
 corpor+0.061
 Jude+0.061
Neg logit contributions
acs-0.079
 Gravity-0.077
assic-0.077
ikhail-0.076
Tokens-0.075
Token room
Token ID2119
Feature activation+1.40e-01

Pos logit contributions
acs+0.295
 Gravity+0.287
assic+0.285
ikhail+0.284
Tokens+0.278
Neg logit contributions
 confir-0.270
 contro-0.257
 discharge-0.249
 Jude-0.247
 corpor-0.247
Token,
Token ID11
Feature activation-5.57e-02

Pos logit contributions
acs+0.272
 Gravity+0.267
assic+0.264
ikhail+0.264
Tokens+0.259
Neg logit contributions
 confir-0.222
 contro-0.210
 discharge-0.204
 corpor-0.201
 Jude-0.201
Token because
Token ID780
Feature activation+2.09e-01

Pos logit contributions
 confir+0.092
 contro+0.088
 discharge+0.085
 corpor+0.084
 Jude+0.084
Neg logit contributions
acs-0.105
 Gravity-0.103
assic-0.102
ikhail-0.102
Tokens-0.100
Token
Token ID250
Feature activation+9.46e-02

Pos logit contributions
 confir+0.161
 contro+0.154
 discharge+0.151
 corpor+0.150
 Jude+0.149
Neg logit contributions
acs-0.125
 Gravity-0.121
assic-0.121
ikhail-0.120
Tokens-0.117
TokenWhat
Token ID2061
Feature activation+2.59e-01

Pos logit contributions
acs+0.165
 Gravity+0.160
assic+0.160
ikhail+0.160
Tokens+0.156
Neg logit contributions
 confir-0.169
 contro-0.162
 discharge-0.158
 Jude-0.157
 corpor-0.157
Token has
Token ID468
Feature activation+1.20e-01

Pos logit contributions
acs+0.484
 Gravity+0.474
assic+0.471
ikhail+0.470
Tokens+0.460
Neg logit contributions
 confir-0.433
 contro-0.413
 discharge-0.402
 corpor-0.397
 Jude-0.395
Token the
Token ID262
Feature activation+1.47e-01

Pos logit contributions
acs+0.230
 Gravity+0.226
assic+0.224
ikhail+0.223
Tokens+0.219
Neg logit contributions
 confir-0.195
 contro-0.185
 discharge-0.181
 corpor-0.178
 Jude-0.177
Token universe
Token ID6881
Feature activation+1.12e-01

Pos logit contributions
acs+0.287
 Gravity+0.281
assic+0.279
ikhail+0.278
Tokens+0.272
Neg logit contributions
 confir-0.233
 contro-0.220
 discharge-0.215
 corpor-0.211
 Jude-0.210
Token got
Token ID1392
Feature activation+2.18e-01

Pos logit contributions
acs+0.215
 Gravity+0.212
assic+0.208
ikhail+0.208
Tokens+0.204
Neg logit contributions
 confir-0.181
 contro-0.171
 discharge-0.167
 corpor-0.164
 Jude-0.164
Token to
Token ID284
Feature activation+6.44e-02

Pos logit contributions
acs+0.440
 Gravity+0.432
assic+0.429
ikhail+0.428
Tokens+0.421
Neg logit contributions
 confir-0.332
 contro-0.313
 discharge-0.305
 corpor-0.300
 Jude-0.300
Token do
Token ID466
Feature activation+6.56e-02

Pos logit contributions
acs+0.117
 Gravity+0.114
assic+0.114
ikhail+0.114
Tokens+0.111
Neg logit contributions
 confir-0.111
 contro-0.106
 discharge-0.103
 corpor-0.102
 Jude-0.102
Token with
Token ID351
Feature activation+9.25e-02

Pos logit contributions
acs+0.119
 Gravity+0.116
assic+0.116
ikhail+0.116
Tokens+0.113
Neg logit contributions
 confir-0.113
 contro-0.108
 discharge-0.105
 corpor-0.105
 Jude-0.104
Token it
Token ID340
Feature activation+1.10e-01

Pos logit contributions
acs+0.167
 Gravity+0.162
assic+0.162
ikhail+0.162
Tokens+0.158
Neg logit contributions
 confir-0.161
 contro-0.154
 discharge-0.150
 corpor-0.148
 Jude-0.148
Token?
Token ID30
Feature activation+5.94e-02

Pos logit contributions
acs+0.209
 Gravity+0.203
assic+0.203
ikhail+0.203
Tokens+0.199
Neg logit contributions
 confir-0.182
 contro-0.174
 discharge-0.169
 corpor-0.167
 Jude-0.166
Token bullying
Token ID20714
Feature activation-1.75e-01

Pos logit contributions
acs+0.198
 Gravity+0.194
assic+0.192
ikhail+0.192
Tokens+0.188
Neg logit contributions
 confir-0.149
 contro-0.139
 discharge-0.135
 Jude-0.133
 corpor-0.132
Token,
Token ID11
Feature activation+1.87e-01

Pos logit contributions
 confir+0.258
 contro+0.240
 discharge+0.232
 Jude+0.231
 corpor+0.229
Neg logit contributions
acs-0.365
 Gravity-0.357
assic-0.354
ikhail-0.353
Tokens-0.347
Token dominance
Token ID18648
Feature activation-2.88e-01

Pos logit contributions
acs+0.372
 Gravity+0.365
assic+0.360
ikhail+0.358
Tokens+0.353
Neg logit contributions
 confir-0.290
 contro-0.269
 discharge-0.262
 Jude-0.260
 cumulative-0.255
Token,
Token ID11
Feature activation+1.84e-01

Pos logit contributions
 confir+0.458
 contro+0.437
 discharge+0.425
 corpor+0.420
 Jude+0.417
Neg logit contributions
acs-0.561
 Gravity-0.550
assic-0.547
ikhail-0.546
Tokens-0.536
Token and
Token ID290
Feature activation+1.24e-01

Pos logit contributions
acs+0.346
 Gravity+0.339
assic+0.336
ikhail+0.335
Tokens+0.328
Neg logit contributions
 confir-0.307
 contro-0.288
 discharge-0.281
 Jude-0.278
 corpor-0.275
Token victim
Token ID3117
Feature activation+2.61e-01

Pos logit contributions
acs+0.249
 Gravity+0.245
assic+0.241
ikhail+0.241
Tokens+0.237
Neg logit contributions
 confir-0.188
 contro-0.174
 discharge-0.170
 Jude-0.169
 corpor-0.166
Tokenization
Token ID1634
Feature activation-3.45e-01

Pos logit contributions
acs+0.598
 Gravity+0.585
assic+0.581
ikhail+0.578
Tokens+0.569
Neg logit contributions
 confir-0.327
 contro-0.303
 discharge-0.290
 Jude-0.289
 corpor-0.286
Token during
Token ID1141
Feature activation+1.15e-01

Pos logit contributions
 confir+0.486
 contro+0.455
 discharge+0.440
 Jude+0.434
 corpor+0.434
Neg logit contributions
acs-0.738
 Gravity-0.722
ikhail-0.716
assic-0.716
Tokens-0.703
Token the
Token ID262
Feature activation+2.68e-02

Pos logit contributions
acs+0.216
 Gravity+0.213
ikhail+0.210
assic+0.210
Tokens+0.205
Neg logit contributions
 confir-0.193
 contro-0.181
 discharge-0.175
 Jude-0.174
 corpor-0.173
Token transition
Token ID6801
Feature activation+1.78e-01

Pos logit contributions
acs+0.051
 Gravity+0.050
assic+0.049
ikhail+0.049
Tokens+0.048
Neg logit contributions
 confir-0.045
 contro-0.042
 discharge-0.040
 Jude-0.040
 corpor-0.040
Token from
Token ID422
Feature activation-3.45e-02

Pos logit contributions
acs+0.361
 Gravity+0.353
assic+0.351
ikhail+0.350
Tokens+0.343
Neg logit contributions
 confir-0.271
 contro-0.254
 discharge-0.245
 Jude-0.243
 corpor-0.242
Token Un
Token ID791
Feature activation-2.44e-01

Pos logit contributions
acs+0.495
 Gravity+0.485
assic+0.480
ikhail+0.479
Tokens+0.469
Neg logit contributions
 confir-0.470
 contro-0.447
 discharge-0.437
 corpor-0.432
 Jude-0.432
Tokenlocked
Token ID24162
Feature activation+3.04e-02

Pos logit contributions
 confir+0.444
 contro+0.423
 discharge+0.413
 corpor+0.409
 Jude+0.408
Neg logit contributions
acs-0.422
 Gravity-0.411
assic-0.408
ikhail-0.407
Tokens-0.399
Token BIOS
Token ID27553
Feature activation+2.32e-01

Pos logit contributions
acs+0.059
 Gravity+0.058
assic+0.058
ikhail+0.057
Tokens+0.056
Neg logit contributions
 confir-0.049
 contro-0.046
 discharge-0.045
 corpor-0.044
 Jude-0.044
Token,
Token ID11
Feature activation-2.39e-03

Pos logit contributions
acs+0.449
 Gravity+0.442
assic+0.435
ikhail+0.434
Tokens+0.429
Neg logit contributions
 confir-0.369
 contro-0.349
 discharge-0.340
 Jude-0.338
 corpor-0.338
Token Digital
Token ID10231
Feature activation-6.50e-01

Pos logit contributions
 confir+0.004
 contro+0.004
 discharge+0.004
 corpor+0.004
 Jude+0.004
Neg logit contributions
acs-0.005
 Gravity-0.004
assic-0.004
ikhail-0.004
Tokens-0.004
TokenP
Token ID47
Feature activation+3.27e-01

Pos logit contributions
 confir+1.182
 contro+1.133
 discharge+1.104
 corpor+1.089
 Jude+1.088
Neg logit contributions
acs-1.119
assic-1.087
ikhail-1.086
 Gravity-1.085
Tokens-1.052
TokenWM
Token ID22117
Feature activation+1.32e-01

Pos logit contributions
acs+0.614
 Gravity+0.600
assic+0.597
ikhail+0.595
Tokens+0.584
Neg logit contributions
 confir-0.546
 contro-0.519
 discharge-0.505
 corpor-0.500
 Jude-0.498
Token Controller
Token ID22741
Feature activation+2.79e-01

Pos logit contributions
acs+0.250
 Gravity+0.245
assic+0.242
ikhail+0.241
Tokens+0.238
Neg logit contributions
 confir-0.216
 contro-0.204
 discharge-0.199
 corpor-0.198
 Jude-0.198
Token,
Token ID11
Feature activation-2.73e-02

Pos logit contributions
acs+0.533
 Gravity+0.523
assic+0.516
ikhail+0.516
Tokens+0.508
Neg logit contributions
 confir-0.453
 contro-0.428
 discharge-0.418
 Jude-0.414
 corpor-0.414
Token and
Token ID290
Feature activation-8.66e-02

Pos logit contributions
 confir+0.047
 contro+0.044
 discharge+0.043
 corpor+0.043
 Jude+0.043
Neg logit contributions
acs-0.050
 Gravity-0.049
assic-0.048
ikhail-0.048
Tokens-0.047
Token Enhanced
Token ID22104
Feature activation-5.99e-01

Pos logit contributions
 confir+0.148
 contro+0.141
 discharge+0.137
 corpor+0.136
 Jude+0.136
Neg logit contributions
acs-0.158
 Gravity-0.155
assic-0.154
ikhail-0.153
Tokens-0.150
Token of
Token ID286
Feature activation+1.03e-01

Pos logit contributions
acs+0.896
 Gravity+0.880
assic+0.874
ikhail+0.870
Tokens+0.856
Neg logit contributions
 confir-0.624
 contro-0.586
 discharge-0.569
 corpor-0.561
 Jude-0.560
Token factors
Token ID5087
Feature activation-3.47e-01

Pos logit contributions
acs+0.181
 Gravity+0.177
assic+0.175
ikhail+0.175
Tokens+0.172
Neg logit contributions
 confir-0.184
 contro-0.175
 discharge-0.171
 corpor-0.169
 Jude-0.168
Token means
Token ID1724
Feature activation+2.53e-01

Pos logit contributions
 confir+0.416
 contro+0.389
 discharge+0.374
 corpor+0.367
 Jude+0.366
Neg logit contributions
acs-0.811
 Gravity-0.797
assic-0.794
ikhail-0.792
Tokens-0.780
Token it
Token ID340
Feature activation+1.04e-01

Pos logit contributions
acs+0.521
 Gravity+0.513
assic+0.506
ikhail+0.506
Tokens+0.498
Neg logit contributions
 confir-0.375
 contro-0.351
 discharge-0.340
 corpor-0.337
 Jude-0.336
Token's
Token ID338
Feature activation+1.83e-01

Pos logit contributions
acs+0.187
 Gravity+0.183
assic+0.182
ikhail+0.182
Tokens+0.178
Neg logit contributions
 confir-0.180
 contro-0.172
 discharge-0.167
 corpor-0.165
 Jude-0.165
Token closed
Token ID4838
Feature activation+1.24e-01

Pos logit contributions
acs+0.348
 Gravity+0.341
assic+0.337
ikhail+0.336
Tokens+0.331
Neg logit contributions
 confir-0.301
 contro-0.283
 discharge-0.276
 corpor-0.273
 Jude-0.272
Token.
Token ID13
Feature activation+6.69e-02

Pos logit contributions
acs+0.253
 Gravity+0.249
assic+0.247
ikhail+0.247
Tokens+0.242
Neg logit contributions
 confir-0.186
 contro-0.175
 discharge-0.170
 corpor-0.168
 Jude-0.167
Token And
Token ID843
Feature activation+4.90e-02

Pos logit contributions
acs+0.129
 Gravity+0.128
ikhail+0.125
assic+0.125
Tokens+0.124
Neg logit contributions
 confir-0.109
 contro-0.103
 discharge-0.100
 corpor-0.099
 cumulative-0.098
Token the
Token ID262
Feature activation+8.69e-02

Pos logit contributions
acs+0.086
 Gravity+0.085
assic+0.083
ikhail+0.083
Tokens+0.082
Neg logit contributions
 confir-0.087
 contro-0.082
 discharge-0.081
 corpor-0.079
 Jude-0.079
Token only
Token ID691
Feature activation-6.06e-02

Pos logit contributions
acs+0.168
 Gravity+0.165
assic+0.163
ikhail+0.163
Tokens+0.160
Neg logit contributions
 confir-0.140
 contro-0.132
 discharge-0.129
 corpor-0.127
 Jude-0.127
Token numbers
Token ID3146
Feature activation+1.53e-01

Pos logit contributions
 confir+0.093
 contro+0.088
 discharge+0.085
 corpor+0.084
 Jude+0.084
Neg logit contributions
acs-0.121
 Gravity-0.119
assic-0.118
ikhail-0.118
Tokens-0.116
Token Metroid
Token ID45430
Feature activation+6.52e-01

Pos logit contributions
acs+0.552
 Gravity+0.537
assic+0.535
ikhail+0.534
Tokens+0.522
Neg logit contributions
 confir-0.630
 contro-0.605
 discharge-0.592
 corpor-0.585
 Jude-0.585
Token speed
Token ID2866
Feature activation-1.38e-02

Pos logit contributions
acs+1.295
 Gravity+1.282
assic+1.261
ikhail+1.251
Tokens+1.228
Neg logit contributions
 confir-1.010
 contro-0.949
 discharge-0.924
 Jude-0.918
 corpor-0.916
Tokenrun
Token ID5143
Feature activation-3.81e-01

Pos logit contributions
 confir+0.025
 contro+0.024
 discharge+0.024
 corpor+0.024
 Jude+0.023
Neg logit contributions
acs-0.023
 Gravity-0.023
assic-0.023
ikhail-0.023
Tokens-0.022
Token race
Token ID3234
Feature activation-2.62e-01

Pos logit contributions
 confir+0.597
 contro+0.567
 discharge+0.552
 corpor+0.544
 Jude+0.542
Neg logit contributions
acs-0.751
 Gravity-0.734
assic-0.732
ikhail-0.730
Tokens-0.716
Token,
Token ID11
Feature activation+2.90e-02

Pos logit contributions
 confir+0.403
 contro+0.382
 discharge+0.371
 corpor+0.366
 Jude+0.365
Neg logit contributions
acs-0.523
 Gravity-0.513
assic-0.510
ikhail-0.509
Tokens-0.499
Token from
Token ID422
Feature activation-1.52e-01

Pos logit contributions
acs+0.056
 Gravity+0.055
assic+0.055
ikhail+0.055
Tokens+0.054
Neg logit contributions
 confir-0.047
 contro-0.044
 discharge-0.043
 corpor-0.042
 Jude-0.042
Token Awesome
Token ID25020
Feature activation+1.11e-01

Pos logit contributions
 confir+0.256
 contro+0.243
 discharge+0.237
 corpor+0.234
 Jude+0.233
Neg logit contributions
acs-0.281
 Gravity-0.276
assic-0.273
ikhail-0.273
Tokens-0.267
Token Games
Token ID5776
Feature activation-9.87e-02

Pos logit contributions
acs+0.191
 Gravity+0.186
assic+0.185
ikhail+0.185
Tokens+0.180
Neg logit contributions
 confir-0.203
 contro-0.194
 discharge-0.190
 corpor-0.187
 Jude-0.187
Token Done
Token ID24429
Feature activation+1.06e-01

Pos logit contributions
 confir+0.149
 contro+0.141
 discharge+0.137
 corpor+0.135
 Jude+0.134
Neg logit contributions
acs-0.201
 Gravity-0.197
assic-0.196
ikhail-0.195
Tokens-0.192
Token Quick
Token ID12029
Feature activation+2.08e-01

Pos logit contributions
acs+0.184
 Gravity+0.180
assic+0.178
ikhail+0.178
Tokens+0.174
Neg logit contributions
 confir-0.190
 contro-0.181
 discharge-0.177
 corpor-0.175
 Jude-0.174
Token 2014
Token ID1946
Feature activation+2.63e-01

Pos logit contributions
acs+0.413
 Gravity+0.407
assic+0.401
ikhail+0.399
Tokens+0.393
Neg logit contributions
 confir-0.324
 contro-0.306
 discharge-0.298
 corpor-0.293
 Jude-0.292
Token to
Token ID284
Feature activation-1.04e-01

Pos logit contributions
 confir+0.878
 contro+0.821
 discharge+0.798
 corpor+0.788
 Jude+0.782
Neg logit contributions
acs-1.305
 Gravity-1.273
assic-1.272
ikhail-1.265
Tokens-1.247
Token give
Token ID1577
Feature activation-5.13e-02

Pos logit contributions
 confir+0.161
 contro+0.152
 discharge+0.148
 Jude+0.147
 corpor+0.146
Neg logit contributions
acs-0.205
 Gravity-0.202
assic-0.200
ikhail-0.199
Tokens-0.196
Token third
Token ID2368
Feature activation-7.88e-02

Pos logit contributions
 confir+0.090
 contro+0.086
 discharge+0.084
 corpor+0.082
 Jude+0.082
Neg logit contributions
acs-0.092
 Gravity-0.090
assic-0.089
ikhail-0.089
Tokens-0.087
Token driver
Token ID4639
Feature activation+4.79e-01

Pos logit contributions
 confir+0.128
 contro+0.121
 discharge+0.118
 corpor+0.117
 Jude+0.116
Neg logit contributions
acs-0.151
 Gravity-0.148
assic-0.147
ikhail-0.147
Tokens-0.144
Token Bruno
Token ID31045
Feature activation+3.96e-01

Pos logit contributions
acs+0.777
 Gravity+0.764
ikhail+0.749
assic+0.748
 Mov+0.728
Neg logit contributions
 confir-0.917
 contro-0.875
 discharge-0.860
 corpor-0.845
 cumulative-0.843
Token S
Token ID311
Feature activation+1.82e-02

Pos logit contributions
acs+0.676
 Gravity+0.659
assic+0.657
ikhail+0.655
Tokens+0.640
Neg logit contributions
 confir-0.725
 contro-0.694
 discharge-0.678
 corpor-0.670
 Jude-0.669
Tokenenna
Token ID13713
Feature activation-7.28e-02

Pos logit contributions
acs+0.037
 Gravity+0.036
assic+0.036
ikhail+0.036
Tokens+0.035
Neg logit contributions
 confir-0.027
 contro-0.026
 discharge-0.025
 corpor-0.025
 Jude-0.025
Token some
Token ID617
Feature activation-8.58e-03

Pos logit contributions
 confir+0.118
 contro+0.112
 discharge+0.109
 corpor+0.107
 Jude+0.107
Neg logit contributions
acs-0.140
 Gravity-0.137
assic-0.136
ikhail-0.136
Tokens-0.133
Token time
Token ID640
Feature activation+1.01e-01

Pos logit contributions
 confir+0.013
 contro+0.013
 discharge+0.012
 corpor+0.012
 Jude+0.012
Neg logit contributions
acs-0.017
 Gravity-0.017
assic-0.017
ikhail-0.016
Tokens-0.016
Token in
Token ID287
Feature activation-1.80e-02

Pos logit contributions
acs+0.187
 Gravity+0.183
assic+0.182
ikhail+0.181
Tokens+0.177
Neg logit contributions
 confir-0.170
 contro-0.161
 discharge-0.157
 corpor-0.156
 Jude-0.155
Token the
Token ID262
Feature activation-3.13e-02

Pos logit contributions
 confir+0.028
 contro+0.027
 discharge+0.026
 corpor+0.026
 Jude+0.026
Neg logit contributions
acs-0.035
 Gravity-0.035
assic-0.034
ikhail-0.034
Tokens-0.034
Token AAA
Token ID25734
Feature activation+2.70e-01

Pos logit contributions
acs+0.098
 Gravity+0.096
assic+0.096
ikhail+0.095
Tokens+0.093
Neg logit contributions
 confir-0.094
 contro-0.089
 discharge-0.087
 corpor-0.086
 Jude-0.086
Token games
Token ID1830
Feature activation-1.41e-01

Pos logit contributions
acs+0.483
 Gravity+0.473
assic+0.469
ikhail+0.466
Tokens+0.459
Neg logit contributions
 confir-0.472
 contro-0.449
 discharge-0.438
 Jude-0.432
 corpor-0.432
Token,
Token ID11
Feature activation+7.70e-02

Pos logit contributions
 confir+0.220
 contro+0.210
 discharge+0.205
 corpor+0.202
 Jude+0.201
Neg logit contributions
acs-0.277
ikhail-0.271
assic-0.271
 Gravity-0.270
Tokens-0.265
Token and
Token ID290
Feature activation+6.67e-02

Pos logit contributions
acs+0.144
 Gravity+0.141
assic+0.141
ikhail+0.140
Tokens+0.137
Neg logit contributions
 confir-0.128
 contro-0.122
 discharge-0.119
 corpor-0.117
 Jude-0.117
Token you
Token ID345
Feature activation+2.05e-02

Pos logit contributions
acs+0.124
 Gravity+0.123
assic+0.121
ikhail+0.120
Tokens+0.119
Neg logit contributions
 confir-0.112
 contro-0.106
 discharge-0.103
 corpor-0.101
 Jude-0.101
Token all
Token ID477
Feature activation+2.29e-02

Pos logit contributions
acs+0.041
 Gravity+0.040
assic+0.040
ikhail+0.040
Tokens+0.039
Neg logit contributions
 confir-0.031
 contro-0.030
 discharge-0.029
 corpor-0.029
 Jude-0.028
Token know
Token ID760
Feature activation-1.88e-01

Pos logit contributions
acs+0.046
 Gravity+0.046
assic+0.045
ikhail+0.045
Tokens+0.044
Neg logit contributions
 confir-0.035
 contro-0.033
 discharge-0.032
 corpor-0.031
 Jude-0.031
Token that
Token ID326
Feature activation+2.65e-02

Pos logit contributions
 confir+0.317
 contro+0.300
 discharge+0.292
 corpor+0.288
 Jude+0.287
Neg logit contributions
acs-0.349
 Gravity-0.344
assic-0.340
ikhail-0.338
Tokens-0.334
Token the
Token ID262
Feature activation+4.86e-03

Pos logit contributions
acs+0.050
 Gravity+0.049
assic+0.049
ikhail+0.049
Tokens+0.048
Neg logit contributions
 confir-0.044
 contro-0.041
 discharge-0.040
 corpor-0.040
 Jude-0.040
Token Nintendo
Token ID9714
Feature activation-5.48e-01

Pos logit contributions
acs+0.009
 Gravity+0.009
assic+0.009
ikhail+0.009
Tokens+0.009
Neg logit contributions
 confir-0.008
 contro-0.008
 discharge-0.008
 corpor-0.007
 Jude-0.007
Token booth
Token ID18600
Feature activation-1.05e-01

Pos logit contributions
 confir+0.911
 contro+0.872
 discharge+0.848
 corpor+0.838
 Jude+0.834
Neg logit contributions
acs-1.027
ikhail-1.004
assic-1.002
 Gravity-1.001
Tokens-0.977
Token had
Token ID550
Feature activation+2.12e-01

Pos logit contributions
 confir+0.822
 contro+0.777
 discharge+0.754
 corpor+0.748
 Jude+0.746
Neg logit contributions
acs-1.024
 Gravity-1.002
assic-0.993
ikhail-0.991
Tokens-0.971
Token wrought
Token ID38733
Feature activation-3.26e-01

Pos logit contributions
acs+0.415
 Gravity+0.408
ikhail+0.394
assic+0.394
 Mov+0.390
Neg logit contributions
 confir-0.332
 contro-0.308
 discharge-0.302
 corpor-0.301
 Jude-0.300
Token,
Token ID11
Feature activation-3.27e-02

Pos logit contributions
 confir+0.513
 contro+0.480
 discharge+0.469
 corpor+0.462
 Jude+0.462
Neg logit contributions
acs-0.644
 Gravity-0.632
ikhail-0.621
assic-0.621
Tokens-0.612
Token
Token ID198
Feature activation+2.28e-01

Pos logit contributions
 confir+0.042
 contro+0.040
 discharge+0.038
 corpor+0.038
 Jude+0.038
Neg logit contributions
acs-0.073
 Gravity-0.072
assic-0.072
ikhail-0.071
Tokens-0.070
Token
Token ID198
Feature activation+8.28e-02

Pos logit contributions
acs+0.508
 Gravity+0.500
ikhail+0.489
Tokens+0.489
assic+0.488
Neg logit contributions
 confir-0.322
 contro-0.284
 discharge-0.275
 corpor-0.271
 cumulative-0.268
Tokenand
Token ID392
Feature activation-1.95e-02

Pos logit contributions
acs+0.154
 Gravity+0.150
assic+0.149
ikhail+0.149
Tokens+0.146
Neg logit contributions
 confir-0.140
 contro-0.133
 discharge-0.130
 corpor-0.128
 Jude-0.128
Token on
Token ID319
Feature activation-1.23e-01

Pos logit contributions
 confir+0.032
 contro+0.030
 discharge+0.029
 corpor+0.029
 Jude+0.029
Neg logit contributions
acs-0.037
 Gravity-0.037
ikhail-0.036
assic-0.036
Tokens-0.036
Token the
Token ID262
Feature activation-1.14e-01

Pos logit contributions
 confir+0.215
 contro+0.205
 discharge+0.200
 corpor+0.197
 Jude+0.197
Neg logit contributions
acs-0.221
 Gravity-0.216
assic-0.214
ikhail-0.214
Tokens-0.210
Token labor
Token ID4827
Feature activation-5.74e-01

Pos logit contributions
 confir+0.194
 contro+0.185
 discharge+0.180
 corpor+0.178
 Jude+0.178
Neg logit contributions
acs-0.211
 Gravity-0.206
assic-0.204
ikhail-0.204
Tokens-0.200
Token that
Token ID326
Feature activation+4.95e-02

Pos logit contributions
 confir+0.825
 contro+0.787
 discharge+0.766
 corpor+0.752
 Jude+0.748
Neg logit contributions
acs-1.195
 Gravity-1.175
assic-1.173
ikhail-1.172
Tokens-1.151
Token I
Token ID314
Feature activation-2.94e-02

Pos logit contributions
acs+0.092
 Gravity+0.090
assic+0.089
ikhail+0.089
Tokens+0.087
Neg logit contributions
 confir-0.084
 contro-0.079
 discharge-0.077
 corpor-0.076
 Jude-0.076
Token placing
Token ID12560
Feature activation+7.19e-02

Pos logit contributions
 confir+0.036
 contro+0.034
 discharge+0.033
 corpor+0.033
 Jude+0.033
Neg logit contributions
acs-0.038
 Gravity-0.038
assic-0.037
ikhail-0.037
Tokens-0.037
Token figures
Token ID5538
Feature activation-1.54e-01

Pos logit contributions
acs+0.118
 Gravity+0.115
assic+0.114
ikhail+0.113
Tokens+0.111
Neg logit contributions
 confir-0.137
 contro-0.130
 discharge-0.128
 corpor-0.126
 Jude-0.126
Token.
Token ID13
Feature activation-3.70e-02

Pos logit contributions
 confir+0.238
 contro+0.227
 discharge+0.220
 corpor+0.217
 Jude+0.216
Neg logit contributions
acs-0.308
 Gravity-0.301
assic-0.300
ikhail-0.300
Tokens-0.294
Token
Token ID198
Feature activation-1.87e-02

Pos logit contributions
 confir+0.055
 contro+0.052
 discharge+0.050
 corpor+0.049
 Jude+0.049
Neg logit contributions
acs-0.076
 Gravity-0.075
assic-0.074
ikhail-0.074
Tokens-0.073
Token
Token ID198
Feature activation-3.56e-02

Pos logit contributions
 confir+0.025
 contro+0.023
 discharge+0.022
 corpor+0.021
 cumulative+0.021
Neg logit contributions
acs-0.042
 Gravity-0.042
assic-0.041
ikhail-0.041
Tokens-0.041
TokenLastly
Token ID37511
Feature activation-2.45e-01

Pos logit contributions
 confir+0.066
 contro+0.064
 discharge+0.062
 corpor+0.061
 Jude+0.061
Neg logit contributions
acs-0.060
 Gravity-0.058
assic-0.058
ikhail-0.058
Tokens-0.056
Token,
Token ID11
Feature activation-1.24e-02

Pos logit contributions
 confir+0.390
 contro+0.371
 discharge+0.361
 corpor+0.356
 Jude+0.355
Neg logit contributions
acs-0.476
 Gravity-0.466
assic-0.464
ikhail-0.463
Tokens-0.454
Token I
Token ID314
Feature activation-3.98e-02

Pos logit contributions
 confir+0.020
 contro+0.019
 discharge+0.019
 corpor+0.018
 Jude+0.018
Neg logit contributions
acs-0.024
 Gravity-0.023
assic-0.023
ikhail-0.023
Tokens-0.023
Token tint
Token ID34791
Feature activation-4.31e-01

Pos logit contributions
 confir+0.060
 contro+0.057
 discharge+0.056
 corpor+0.055
 Jude+0.055
Neg logit contributions
acs-0.080
 Gravity-0.079
assic-0.078
ikhail-0.078
Tokens-0.077
Tokened
Token ID276
Feature activation+6.11e-02

Pos logit contributions
 confir+0.721
 contro+0.690
 discharge+0.673
 corpor+0.663
 Jude+0.663
Neg logit contributions
acs-0.803
assic-0.783
 Gravity-0.782
ikhail-0.780
Tokens-0.765
Token around
Token ID1088
Feature activation-3.12e-01

Pos logit contributions
acs+0.119
 Gravity+0.117
assic+0.116
ikhail+0.116
Tokens+0.113
Neg logit contributions
 confir-0.097
 contro-0.092
 discharge-0.090
 corpor-0.089
 Jude-0.088
Token sorts
Token ID10524
Feature activation-1.11e-01

Pos logit contributions
 confir+0.158
 contro+0.150
 discharge+0.146
 corpor+0.144
 Jude+0.143
Neg logit contributions
acs-0.189
 Gravity-0.185
assic-0.184
ikhail-0.183
Tokens-0.180
Token in
Token ID287
Feature activation-4.75e-02

Pos logit contributions
 confir+0.175
 contro+0.164
 discharge+0.160
 corpor+0.157
 Jude+0.157
Neg logit contributions
acs-0.220
 Gravity-0.216
assic-0.214
ikhail-0.213
Tokens-0.210
Token a
Token ID257
Feature activation-1.66e-01

Pos logit contributions
 confir+0.077
 contro+0.073
 discharge+0.071
 corpor+0.070
 Jude+0.070
Neg logit contributions
acs-0.091
 Gravity-0.089
assic-0.089
ikhail-0.089
Tokens-0.087
Token blow
Token ID6611
Feature activation-1.84e-01

Pos logit contributions
 confir+0.250
 contro+0.233
 discharge+0.226
 corpor+0.224
 Jude+0.223
Neg logit contributions
acs-0.340
 Gravity-0.336
assic-0.331
ikhail-0.330
Tokens-0.324
Tokenout
Token ID448
Feature activation+2.62e-02

Pos logit contributions
 confir+0.232
 contro+0.217
 discharge+0.209
 corpor+0.206
 Jude+0.205
Neg logit contributions
acs-0.418
 Gravity-0.410
assic-0.408
ikhail-0.408
Tokens-0.400
Token victory
Token ID5373
Feature activation-6.41e-01

Pos logit contributions
acs+0.061
 Gravity+0.060
assic+0.059
ikhail+0.059
Tokens+0.058
Neg logit contributions
 confir-0.032
 contro-0.030
 Jude-0.028
 discharge-0.028
 corpor-0.028
Token.
Token ID13
Feature activation+2.53e-02

Pos logit contributions
 confir+1.015
 contro+0.960
 discharge+0.932
 corpor+0.921
 Jude+0.918
Neg logit contributions
acs-1.259
 Gravity-1.232
assic-1.221
ikhail-1.220
Tokens-1.198
Token In
Token ID554
Feature activation+6.30e-02

Pos logit contributions
acs+0.048
 Gravity+0.048
assic+0.047
ikhail+0.047
Tokens+0.046
Neg logit contributions
 confir-0.042
 contro-0.039
 discharge-0.038
 corpor-0.038
 cumulative-0.038
Token 2014
Token ID1946
Feature activation+2.03e-01

Pos logit contributions
acs+0.118
 Gravity+0.115
assic+0.115
ikhail+0.115
Tokens+0.112
Neg logit contributions
 confir-0.105
 contro-0.100
 discharge-0.097
 corpor-0.096
 Jude-0.096
Token,
Token ID11
Feature activation+2.36e-02

Pos logit contributions
acs+0.396
 Gravity+0.387
assic+0.386
ikhail+0.385
Tokens+0.377
Neg logit contributions
 confir-0.324
 contro-0.308
 discharge-0.300
 corpor-0.296
 Jude-0.295
Token Texas
Token ID3936
Feature activation-3.07e-01

Pos logit contributions
acs+0.047
 Gravity+0.046
assic+0.046
ikhail+0.046
Tokens+0.045
Neg logit contributions
 confir-0.037
 contro-0.035
 discharge-0.034
 corpor-0.033
 Jude-0.033
Token path
Token ID3108
Feature activation+2.17e-01

Pos logit contributions
acs+0.839
 Gravity+0.825
assic+0.817
ikhail+0.812
Tokens+0.802
Neg logit contributions
 confir-0.636
 contro-0.605
 discharge-0.586
 Jude-0.578
 corpor-0.574
Token,
Token ID837
Feature activation+1.10e-01

Pos logit contributions
acs+0.452
 Gravity+0.444
ikhail+0.440
assic+0.439
Tokens+0.435
Neg logit contributions
 confir-0.316
 contro-0.298
 discharge-0.290
 Jude-0.284
 corpor-0.284
Token 4
Token ID604
Feature activation-1.94e-01

Pos logit contributions
acs+0.218
 Gravity+0.214
assic+0.212
ikhail+0.211
Tokens+0.207
Neg logit contributions
 confir-0.174
 contro-0.164
 discharge-0.159
 Jude-0.157
 corpor-0.156
Token )
Token ID1267
Feature activation-4.05e-02

Pos logit contributions
 confir+0.230
 contro+0.214
 discharge+0.206
 Jude+0.202
 corpor+0.202
Neg logit contributions
acs-0.458
 Gravity-0.449
assic-0.447
ikhail-0.446
Tokens-0.440
Token =
Token ID796
Feature activation+4.98e-01

Pos logit contributions
 confir+0.068
 contro+0.065
 discharge+0.063
 corpor+0.062
 Jude+0.062
Neg logit contributions
acs-0.075
 Gravity-0.074
assic-0.073
ikhail-0.073
Tokens-0.072
Token '.
Token ID45302
Feature activation-6.30e-01

Pos logit contributions
acs+1.007
 Gravity+0.991
assic+0.977
ikhail+0.972
Tokens+0.962
Neg logit contributions
 confir-0.753
 contro-0.713
 discharge-0.688
 Jude-0.679
 corpor-0.675
Tokencl
Token ID565
Feature activation+3.91e-01

Pos logit contributions
 confir+1.037
 contro+0.988
 discharge+0.961
 corpor+0.948
 Jude+0.947
Neg logit contributions
acs-1.194
 Gravity-1.166
assic-1.161
ikhail-1.158
Tokens-1.135
Tokenj
Token ID73
Feature activation-1.39e-01

Pos logit contributions
acs+0.726
assic+0.704
ikhail+0.698
 Gravity+0.697
Tokens+0.683
Neg logit contributions
 confir-0.669
 contro-0.635
 discharge-0.616
 corpor-0.610
 Jude-0.607
Token'
Token ID6
Feature activation-1.15e-01

Pos logit contributions
 confir+0.220
 contro+0.209
 discharge+0.203
 corpor+0.200
 Jude+0.200
Neg logit contributions
acs-0.273
 Gravity-0.267
assic-0.265
ikhail-0.264
Tokens-0.260
Token OR
Token ID6375
Feature activation+1.09e-01

Pos logit contributions
 confir+0.178
 contro+0.168
 discharge+0.163
 corpor+0.160
 Jude+0.160
Neg logit contributions
acs-0.231
 Gravity-0.227
assic-0.224
ikhail-0.223
Tokens-0.220
Token RIGHT
Token ID33621
Feature activation-4.34e-01

Pos logit contributions
acs+0.215
 Gravity+0.211
assic+0.208
ikhail+0.208
Tokens+0.205
Neg logit contributions
 confir-0.171
 contro-0.162
 discharge-0.157
 corpor-0.155
 Jude-0.154
Token however
Token ID2158
Feature activation+5.57e-01

Pos logit contributions
 confir+0.091
 contro+0.087
 discharge+0.084
 corpor+0.083
 Jude+0.083
Neg logit contributions
acs-0.107
 Gravity-0.105
assic-0.104
ikhail-0.104
Tokens-0.102
Token,
Token ID11
Feature activation-5.17e-02

Pos logit contributions
acs+1.089
 Gravity+1.073
ikhail+1.059
assic+1.054
Tokens+1.042
Neg logit contributions
 confir-0.879
 contro-0.829
 discharge-0.811
 Jude-0.798
 corpor-0.796
Token and
Token ID290
Feature activation-9.66e-02

Pos logit contributions
 confir+0.082
 contro+0.078
 discharge+0.076
 corpor+0.075
 Jude+0.075
Neg logit contributions
acs-0.100
 Gravity-0.098
assic-0.098
ikhail-0.098
Tokens-0.096
Token his
Token ID465
Feature activation+1.67e-01

Pos logit contributions
 confir+0.154
 contro+0.146
 discharge+0.142
 corpor+0.140
 Jude+0.140
Neg logit contributions
acs-0.188
 Gravity-0.185
ikhail-0.183
assic-0.183
Tokens-0.179
Token preseason
Token ID18913
Feature activation+4.73e-01

Pos logit contributions
acs+0.336
 Gravity+0.330
assic+0.328
ikhail+0.327
Tokens+0.321
Neg logit contributions
 confir-0.255
 contro-0.240
 discharge-0.233
 corpor-0.231
 Jude-0.230
Token teased
Token ID35380
Feature activation-6.63e-01

Pos logit contributions
acs+0.923
 Gravity+0.904
ikhail+0.892
assic+0.890
Tokens+0.875
Neg logit contributions
 confir-0.748
 contro-0.708
 discharge-0.684
 corpor-0.683
 Jude-0.682
Token us
Token ID514
Feature activation-1.31e-01

Pos logit contributions
 confir+1.094
 contro+1.045
 discharge+1.017
 corpor+1.003
 cumulative+1.002
Neg logit contributions
acs-1.258
assic-1.228
 Gravity-1.221
ikhail-1.217
Tokens-1.193
Token with
Token ID351
Feature activation-8.38e-02

Pos logit contributions
 confir+0.220
 contro+0.209
 discharge+0.204
 corpor+0.201
 Jude+0.201
Neg logit contributions
acs-0.244
 Gravity-0.238
assic-0.237
ikhail-0.236
Tokens-0.232
Token previews
Token ID41418
Feature activation-3.19e-01

Pos logit contributions
 confir+0.139
 contro+0.133
 discharge+0.129
 corpor+0.128
 Jude+0.127
Neg logit contributions
acs-0.157
 Gravity-0.154
assic-0.153
ikhail-0.153
Tokens-0.150
Token of
Token ID286
Feature activation-5.41e-02

Pos logit contributions
 confir+0.456
 contro+0.431
 discharge+0.418
 corpor+0.411
 Jude+0.410
Neg logit contributions
acs-0.672
 Gravity-0.659
assic-0.656
ikhail-0.654
Tokens-0.643
Token greatness
Token ID27951
Feature activation+1.34e-01

Pos logit contributions
 confir+0.094
 contro+0.090
 discharge+0.088
 corpor+0.087
 Jude+0.087
Neg logit contributions
acs-0.097
 Gravity-0.095
assic-0.094
ikhail-0.094
Tokens-0.092
Token that
Token ID326
Feature activation-1.02e-01

Pos logit contributions
 confir+0.218
 contro+0.206
 discharge+0.201
 corpor+0.198
 Jude+0.198
Neg logit contributions
acs-0.239
 Gravity-0.235
assic-0.232
ikhail-0.231
Tokens-0.227
Token life
Token ID1204
Feature activation-1.19e-01

Pos logit contributions
 confir+0.167
 contro+0.158
 discharge+0.153
 corpor+0.151
 Jude+0.150
Neg logit contributions
acs-0.194
 Gravity-0.191
assic-0.188
ikhail-0.188
Tokens-0.185
Token is
Token ID318
Feature activation-9.74e-02

Pos logit contributions
 confir+0.217
 contro+0.207
 discharge+0.202
 corpor+0.200
 Jude+0.200
Neg logit contributions
acs-0.204
 Gravity-0.199
assic-0.197
ikhail-0.197
Tokens-0.193
Token meaningless
Token ID24513
Feature activation+1.41e-01

Pos logit contributions
 confir+0.167
 contro+0.156
 discharge+0.153
 Jude+0.151
 corpor+0.151
Neg logit contributions
acs-0.178
 Gravity-0.175
assic-0.171
ikhail-0.171
Tokens-0.169
Token.
Token ID764
Feature activation-7.81e-01

Pos logit contributions
acs+0.272
 Gravity+0.268
ikhail+0.263
assic+0.263
Tokens+0.260
Neg logit contributions
 confir-0.228
 contro-0.214
 discharge-0.208
 Jude-0.206
 corpor-0.205
Token.
Token ID764
Feature activation-6.61e-01

Pos logit contributions
 confir+1.221
 contro+1.177
 discharge+1.142
 Jude+1.136
 corpor+1.128
Neg logit contributions
acs-1.520
assic-1.494
ikhail-1.481
 Gravity-1.470
Tokens-1.448
Token.
Token ID764
Feature activation-6.20e-01

Pos logit contributions
 confir+0.598
 contro+0.553
 discharge+0.523
 corpor+0.512
 Jude+0.509
Neg logit contributions
acs-1.734
assic-1.705
 Gravity-1.704
ikhail-1.699
Tokens-1.675
Token The
Token ID383
Feature activation-2.36e-02

Pos logit contributions
 confir+1.024
 contro+0.982
 discharge+0.955
 corpor+0.942
 Jude+0.941
Neg logit contributions
acs-1.166
assic-1.140
ikhail-1.133
 Gravity-1.132
Tokens-1.110
Token only
Token ID691
Feature activation-1.09e-01

Pos logit contributions
 confir+0.037
 contro+0.035
 discharge+0.034
 corpor+0.034
 Jude+0.034
Neg logit contributions
acs-0.046
 Gravity-0.045
assic-0.045
ikhail-0.045
Tokens-0.044
Token thing
Token ID1517
Feature activation+6.26e-02

Pos logit contributions
 confir+0.162
 contro+0.151
 discharge+0.147
 corpor+0.145
 Jude+0.145
Neg logit contributions
acs-0.223
 Gravity-0.219
assic-0.216
ikhail-0.216
Tokens-0.213
Token that
Token ID326
Feature activation+5.92e-02

Pos logit contributions
acs+0.121
 Gravity+0.119
ikhail+0.116
assic+0.116
Tokens+0.114
Neg logit contributions
 confir-0.101
 contro-0.094
 discharge-0.092
 Jude-0.091
 corpor-0.091
Tokenused
Token ID1484
Feature activation-5.99e-02

Pos logit contributions
 confir+0.101
 contro+0.097
 discharge+0.094
 Jude+0.093
 corpor+0.093
Neg logit contributions
acs-0.181
 Gravity-0.180
assic-0.179
ikhail-0.177
Tokens-0.176
Token.
Token ID13
Feature activation+3.90e-02

Pos logit contributions
 confir+0.091
 contro+0.087
 discharge+0.084
 corpor+0.083
 Jude+0.083
Neg logit contributions
acs-0.121
 Gravity-0.118
assic-0.118
ikhail-0.118
Tokens-0.115
Token
Token ID447
Feature activation+9.00e-02

Pos logit contributions
acs+0.070
 Gravity+0.069
assic+0.068
ikhail+0.068
Tokens+0.067
Neg logit contributions
 confir-0.068
 contro-0.065
 discharge-0.063
 corpor-0.062
 Jude-0.062
Token
Token ID251
Feature activation+4.98e-02

Pos logit contributions
acs+0.151
 Gravity+0.148
assic+0.146
ikhail+0.146
Tokens+0.143
Neg logit contributions
 confir-0.167
 contro-0.160
 discharge-0.156
 corpor-0.155
 Jude-0.154
Token He
Token ID679
Feature activation+1.48e-01

Pos logit contributions
acs+0.090
 Gravity+0.088
assic+0.088
ikhail+0.088
Tokens+0.086
Neg logit contributions
 confir-0.086
 contro-0.082
 discharge-0.080
 corpor-0.079
 Jude-0.079
Token sometimes
Token ID3360
Feature activation-6.35e-01

Pos logit contributions
acs+0.280
 Gravity+0.274
assic+0.273
ikhail+0.272
Tokens+0.267
Neg logit contributions
 confir-0.245
 contro-0.233
 discharge-0.227
 corpor-0.224
 Jude-0.223
Token shot
Token ID2823
Feature activation+2.03e-01

Pos logit contributions
 confir+1.007
 contro+0.960
 discharge+0.933
 corpor+0.921
 Jude+0.916
Neg logit contributions
acs-1.238
 Gravity-1.211
assic-1.207
ikhail-1.207
Tokens-1.183
Token in
Token ID287
Feature activation+1.32e-01

Pos logit contributions
acs+0.375
 Gravity+0.368
assic+0.364
ikhail+0.364
Tokens+0.357
Neg logit contributions
 confir-0.342
 contro-0.325
 discharge-0.316
 Jude-0.312
 corpor-0.312
Token the
Token ID262
Feature activation+3.95e-02

Pos logit contributions
acs+0.255
 Gravity+0.250
assic+0.249
ikhail+0.248
Tokens+0.243
Neg logit contributions
 confir-0.213
 contro-0.203
 discharge-0.197
 corpor-0.195
 Jude-0.194
Token afternoon
Token ID6672
Feature activation+3.71e-02

Pos logit contributions
acs+0.076
 Gravity+0.074
assic+0.074
ikhail+0.073
Tokens+0.072
Neg logit contributions
 confir-0.064
 contro-0.061
 discharge-0.060
 corpor-0.059
 Jude-0.059
Token,
Token ID11
Feature activation-7.75e-03

Pos logit contributions
acs+0.071
 Gravity+0.070
assic+0.069
ikhail+0.069
Tokens+0.068
Neg logit contributions
 confir-0.060
 contro-0.057
 discharge-0.055
 corpor-0.055
 Jude-0.054