TOP ACTIVATIONS
MAX = 2.012

via phone . " My first instinct after [ the first
possible , in the old Naval Air Station in South We
Superman # 1 , the first superhero to have his own
Summer season . First announced in 2013 , a
, now the tide has turned again , and the brewing
aware of what has been going on the last few weeks
being able to express their First Amendment rights .
Watch Outside First Presidential Debate , 24 Arrest
ula could not keep her balance and slipped . She fell
ond rl í k , pal ek . <|endoftext|>
So what made you guys go with Hunt ress ?
centre of the debate , seems to me like an unnecessary
It 's pretty strange your first time back , especially if
the way we train our first responders ! Des
However , now the tide has turned again , and
but if you have a child that is older they should
Here , in July in Paw t ucket , such moments
me so excited about this comic is that it transitions between
designated protest area in the first place . Martin said :
day . I just wish he

MIN ACTIVATIONS
MIN = -2.214

said he hoped that Ike a and others would consider compens
'd be happy to talk more but I 'd rather have
just one of many companies that benefited from the use of
way , they argue , Williams could have received government research
hoped that Ike a and others would consider compens ating former
. MOR PH _ BL ACK H AT , rect K
was iconic ( more on that later ), but he couldn
, 3 ), 0 ) black hat = c v 2
ED Israel has long pursued the physical , political
Virginia undergrad who served 18 months behind bars in the her
was just one of many companies that benefited from the use
oz illa still has a long way to go with mobile
had to lie , and tell him , " I 'll
. Like Apple s original iPhone and Tesla Motors
The report concluded that Ike a managers were aware of the
{ white } at least one blank character (< Space >
you ? While AT & T 's powerhouse FISA lobbyist Charlie
heat to low and cook f rit ters on each side
possible that mobile - device makers , some of which are
I 'd be happy to talk more but I 'd rather

INTERVAL 0.956 - 2.012
CONTAINS 0.917%

. Much of the first - floor lab space is under
prevent their production and stockp iling and abolish them completely once
description of them holding each other and shaking with
If that is what your aim is , why are we
d 3 p W X w pr

INTERVAL -0.101 - 0.956
CONTAINS 60.517%

ate Gu ests have been arrested for our right to hear
by whom there was no renewal of the fierce crackdown
Unknown Sources . Otherwise , you will not be
14 days from Friday in a bid to contain the virus
@ s unt imes . com <|endoftext|> Nintendo fans desperate to

INTERVAL -1.157 - -0.101
CONTAINS 38.345%

ian C . York added in her argument that filtering systems
Jama al Charles also participated in 11 - on - 11
south of Jerusalem to Heb ron , bis ect ing the
in jail . But the authorities have been unable to silence
the marijuana issue will face a greater burden of proof than

INTERVAL -2.214 - -1.157
CONTAINS 0.221%

doctrine as briefly and clearly as the matter itself may allow
California - based Total Call Mobile of fraud ul ently enroll
more top - end spark le and superb neutrality , the
but said Moscow had a long way to go to prove
of this : Success like Blackburn 's , aided by Jack
Token via
Token ID2884
Feature activation-2.78e-01

Pos logit contributions
hooting+0.571
HUD+0.563
advertisement+0.518
boarding+0.493
icide+0.480
Neg logit contributions
amins-0.664
ysis-0.628
-0.619
Thumbnail-0.592
-0.581
Token phone
Token ID3072
Feature activation+1.00e-01

Pos logit contributions
hooting+2.093
HUD+2.059
advertisement+1.901
boarding+1.803
icide+1.755
Neg logit contributions
amins-2.673
ysis-2.510
-2.480
Thumbnail-2.355
-2.325
Token.
Token ID13
Feature activation+2.79e-01

Pos logit contributions
amins+0.933
ysis+0.882
+0.879
Thumbnail+0.832
+0.824
Neg logit contributions
hooting-0.787
HUD-0.778
advertisement-0.707
boarding-0.675
icide-0.657
Token "
Token ID366
Feature activation+5.90e-01

Pos logit contributions
amins+2.252
+2.142
ysis+2.134
Thumbnail+1.996
+1.969
Neg logit contributions
hooting-2.485
HUD-2.469
advertisement-2.241
boarding-2.169
icide-2.127
TokenMy
Token ID3666
Feature activation+1.06e+00

Pos logit contributions
amins+5.191
+5.045
ysis+4.900
Thumbnail+4.789
+4.611
Neg logit contributions
hooting-4.762
HUD-4.526
advertisement-4.058
icide-4.000
boarding-3.997
Token first
Token ID717
Feature activation+2.01e+00

Pos logit contributions
amins+7.898
ysis+7.725
+7.638
uty+7.096
 ever+7.012
Neg logit contributions
HUD-8.980
hooting-8.942
advertisement-8.078
boarding-7.611
icide-7.488
Token instinct
Token ID13311
Feature activation+1.33e+00

Pos logit contributions
 ever+13.614
ysis+12.836
+12.615
amins+12.524
antam+11.869
Neg logit contributions
HUD-15.033
hooting-14.563
bees-12.453
advertisement-12.391
horn-12.355
Token after
Token ID706
Feature activation+6.64e-01

Pos logit contributions
amins+8.042
ysis+7.846
+7.654
 ever+7.582
+7.361
Neg logit contributions
HUD-12.478
hooting-11.898
advertisement-10.821
icide-10.307
boarding-10.215
Token [
Token ID685
Feature activation+1.78e-01

Pos logit contributions
amins+5.345
ysis+5.144
+5.028
Thumbnail+4.731
+4.697
Neg logit contributions
HUD-5.678
hooting-5.589
advertisement-5.122
horn-4.845
boarding-4.791
Tokenthe
Token ID1169
Feature activation+7.53e-01

Pos logit contributions
amins+1.694
ysis+1.612
+1.605
Thumbnail+1.521
+1.504
Neg logit contributions
hooting-1.344
HUD-1.333
advertisement-1.203
boarding-1.144
icide-1.116
Token first
Token ID717
Feature activation+1.69e+00

Pos logit contributions
amins+6.223
+6.003
ysis+5.921
uty+5.490
Thumbnail+5.477
Neg logit contributions
HUD-6.247
hooting-6.216
advertisement-5.569
boarding-5.379
horn-5.342
Token possible
Token ID1744
Feature activation+3.79e-02

Pos logit contributions
hooting+1.928
HUD+1.830
advertisement+1.631
boarding+1.556
horn+1.506
Neg logit contributions
amins-3.459
ysis-3.300
-3.259
-3.181
-3.169
Token,
Token ID11
Feature activation+1.12e-01

Pos logit contributions
amins+0.386
ysis+0.369
+0.367
Thumbnail+0.349
+0.346
Neg logit contributions
hooting-0.260
HUD-0.259
advertisement-0.231
boarding-0.218
icide-0.212
Tokenin
Token ID259
Feature activation-3.78e-02

Pos logit contributions
amins+0.975
ysis+0.922
+0.917
Thumbnail+0.864
+0.854
Neg logit contributions
hooting-0.945
HUD-0.939
advertisement-0.857
boarding-0.820
icide-0.801
Token the
Token ID262
Feature activation+4.36e-01

Pos logit contributions
hooting+0.310
HUD+0.307
advertisement+0.279
boarding+0.269
icide+0.261
Neg logit contributions
amins-0.338
ysis-0.319
-0.317
Thumbnail-0.299
-0.296
Token old
Token ID1468
Feature activation+1.64e+00

Pos logit contributions
amins+3.391
+3.222
ysis+3.222
Thumbnail+3.017
+2.962
Neg logit contributions
hooting-3.990
HUD-3.960
advertisement-3.655
boarding-3.480
icide-3.427
Token Naval
Token ID20818
Feature activation+1.93e+00

Pos logit contributions
+9.887
amins+9.655
endor+9.267
ysis+9.042
Thumbnail+9.009
Neg logit contributions
HUD-14.381
hooting-14.183
advertisement-12.782
icide-12.305
bees-12.057
Token Air
Token ID3701
Feature activation+1.68e+00

Pos logit contributions
amins+9.049
+8.764
ysis+8.200
endor+7.877
 ever+7.827
Neg logit contributions
hooting-18.422
HUD-18.006
advertisement-17.115
 confession-15.930
boarding-15.879
Token Station
Token ID9327
Feature activation+2.10e-01

Pos logit contributions
+4.283
amins+4.163
ysis+3.791
endor+3.224
uty+3.069
Neg logit contributions
HUD-21.142
hooting-20.674
advertisement-20.192
icide-19.091
boarding-18.478
Token in
Token ID287
Feature activation-2.38e-03

Pos logit contributions
amins+1.774
ysis+1.676
+1.669
Thumbnail+1.569
+1.549
Neg logit contributions
hooting-1.822
HUD-1.810
advertisement-1.656
boarding-1.585
icide-1.552
Token South
Token ID2520
Feature activation-4.13e-01

Pos logit contributions
hooting+0.017
HUD+0.017
advertisement+0.015
boarding+0.014
icide+0.014
Neg logit contributions
amins-0.023
ysis-0.022
-0.022
Thumbnail-0.021
-0.021
Token We
Token ID775
Feature activation-8.10e-02

Pos logit contributions
hooting+3.117
HUD+3.045
advertisement+2.774
boarding+2.635
icide+2.580
Neg logit contributions
amins-3.909
ysis-3.741
-3.741
Thumbnail-3.519
-3.487
Token Superman
Token ID14951
Feature activation+3.21e-01

Pos logit contributions
amins+4.735
+4.509
ysis+4.490
+4.219
+4.208
Neg logit contributions
hooting-4.275
HUD-4.242
advertisement-3.843
boarding-3.604
icide-3.530
Token #
Token ID1303
Feature activation+9.56e-02

Pos logit contributions
amins+2.853
ysis+2.699
+2.696
Thumbnail+2.544
+2.515
Neg logit contributions
hooting-2.614
HUD-2.597
advertisement-2.349
boarding-2.236
icide-2.182
Token1
Token ID16
Feature activation+6.20e-01

Pos logit contributions
amins+0.979
ysis+0.933
+0.925
Thumbnail+0.883
+0.874
Neg logit contributions
HUD-0.656
hooting-0.656
advertisement-0.585
boarding-0.553
icide-0.536
Token,
Token ID11
Feature activation+1.06e+00

Pos logit contributions
amins+5.279
+5.027
ysis+4.990
Thumbnail+4.715
+4.648
Neg logit contributions
HUD-5.155
hooting-5.125
advertisement-4.583
boarding-4.351
icide-4.268
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
amins+8.148
+7.881
ysis+7.587
Thumbnail+7.302
endor+7.266
Neg logit contributions
HUD-8.924
hooting-8.831
advertisement-7.933
boarding-7.441
horn-7.284
Token first
Token ID717
Feature activation+1.90e+00

Pos logit contributions
amins+8.598
+8.247
ysis+7.973
 ever+7.639
Thumbnail+7.582
Neg logit contributions
HUD-8.724
hooting-8.565
advertisement-7.793
boarding-7.284
horn-7.223
Token superhero
Token ID17343
Feature activation+8.99e-01

Pos logit contributions
 ever+12.785
amins+12.248
ysis+11.850
+11.822
+11.234
Neg logit contributions
HUD-14.627
hooting-14.365
advertisement-12.948
bees-12.314
horn-12.138
Token to
Token ID284
Feature activation+8.30e-01

Pos logit contributions
amins+6.916
+6.446
ysis+6.424
Thumbnail+6.023
 ever+5.999
Neg logit contributions
HUD-7.975
hooting-7.828
advertisement-7.051
boarding-6.771
horn-6.685
Token have
Token ID423
Feature activation+1.07e+00

Pos logit contributions
amins+6.178
ysis+5.913
+5.847
 ever+5.660
endor+5.455
Neg logit contributions
HUD-7.543
hooting-7.312
advertisement-6.807
boarding-6.411
horn-6.243
Token his
Token ID465
Feature activation+7.87e-01

Pos logit contributions
amins+8.282
ysis+8.083
+8.013
 ever+7.884
+7.490
Neg logit contributions
hooting-8.925
HUD-8.884
advertisement-8.067
boarding-7.401
horn-7.368
Token own
Token ID898
Feature activation+9.14e-01

Pos logit contributions
amins+6.123
+5.854
ysis+5.824
Thumbnail+5.437
+5.370
Neg logit contributions
hooting-6.977
HUD-6.893
advertisement-6.341
boarding-6.029
horn-5.897
Token Summer
Token ID10216
Feature activation+1.03e-01

Pos logit contributions
amins+0.377
ysis+0.359
+0.355
Thumbnail+0.338
+0.335
Neg logit contributions
hooting-0.306
HUD-0.301
advertisement-0.274
boarding-0.263
icide-0.254
Token season
Token ID1622
Feature activation-4.05e-01

Pos logit contributions
amins+0.934
ysis+0.884
+0.878
Thumbnail+0.834
+0.822
Neg logit contributions
hooting-0.827
HUD-0.821
advertisement-0.747
boarding-0.717
icide-0.695
Token.
Token ID13
Feature activation+1.71e-01

Pos logit contributions
hooting+3.260
HUD+3.200
advertisement+2.937
boarding+2.883
icide+2.789
Neg logit contributions
amins-3.573
ysis-3.375
-3.352
Thumbnail-3.209
-3.182
Token
Token ID198
Feature activation+3.08e-02

Pos logit contributions
amins+1.505
ysis+1.426
+1.420
Thumbnail+1.339
+1.322
Neg logit contributions
hooting-1.418
HUD-1.408
advertisement-1.282
boarding-1.225
icide-1.198
Token
Token ID198
Feature activation+3.80e-01

Pos logit contributions
amins+0.289
ysis+0.275
+0.272
Thumbnail+0.258
+0.256
Neg logit contributions
hooting-0.238
HUD-0.237
advertisement-0.215
boarding-0.204
icide-0.199
TokenFirst
Token ID5962
Feature activation+1.90e+00

Pos logit contributions
amins+3.300
+3.133
ysis+3.111
Thumbnail+2.956
+2.892
Neg logit contributions
hooting-3.191
HUD-3.124
advertisement-2.843
boarding-2.732
icide-2.698
Token announced
Token ID3414
Feature activation+1.73e-01

Pos logit contributions
amins+14.351
+13.812
 ever+13.360
ysis+13.038
+12.985
Neg logit contributions
hooting-13.419
HUD-13.372
advertisement-12.236
icide-11.012
boarding-10.881
Token in
Token ID287
Feature activation+2.83e-02

Pos logit contributions
amins+1.477
ysis+1.397
+1.390
Thumbnail+1.310
+1.295
Neg logit contributions
hooting-1.485
HUD-1.477
advertisement-1.350
boarding-1.295
icide-1.264
Token 2013
Token ID2211
Feature activation+1.06e-03

Pos logit contributions
amins+0.256
ysis+0.244
+0.241
Thumbnail+0.229
+0.226
Neg logit contributions
hooting-0.227
HUD-0.225
advertisement-0.204
boarding-0.197
icide-0.192
Token,
Token ID11
Feature activation+7.53e-01

Pos logit contributions
amins+0.011
ysis+0.010
+0.010
Thumbnail+0.009
+0.009
Neg logit contributions
hooting-0.008
HUD-0.008
advertisement-0.007
boarding-0.006
icide-0.006
Token a
Token ID257
Feature activation+4.11e-01

Pos logit contributions
amins+5.634
+5.311
ysis+5.232
+4.882
Thumbnail+4.878
Neg logit contributions
hooting-6.996
HUD-6.866
advertisement-6.299
boarding-5.984
icide-5.963
Token,
Token ID11
Feature activation+3.13e-01

Pos logit contributions
hooting+0.294
HUD+0.292
advertisement+0.262
boarding+0.248
icide+0.242
Neg logit contributions
amins-0.401
ysis-0.383
-0.381
Thumbnail-0.362
-0.358
Token now
Token ID783
Feature activation+3.68e-01

Pos logit contributions
amins+2.663
ysis+2.513
+2.500
Thumbnail+2.346
+2.324
Neg logit contributions
hooting-2.678
HUD-2.666
advertisement-2.437
boarding-2.321
icide-2.279
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
amins+3.000
ysis+2.828
+2.798
Thumbnail+2.627
+2.601
Neg logit contributions
hooting-3.251
HUD-3.249
advertisement-2.989
boarding-2.830
icide-2.792
Token tide
Token ID20013
Feature activation+1.79e+00

Pos logit contributions
amins+0.107
ysis+0.101
+0.101
Thumbnail+0.095
+0.093
Neg logit contributions
hooting-0.111
HUD-0.110
advertisement-0.101
boarding-0.097
icide-0.095
Token has
Token ID468
Feature activation+1.04e+00

Pos logit contributions
amins+11.116
ysis+10.777
+10.065
 ever+9.999
+9.426
Neg logit contributions
HUD-15.344
hooting-15.078
advertisement-14.302
icide-13.445
laughter-12.879
Token turned
Token ID2900
Feature activation+1.90e+00

Pos logit contributions
amins+6.962
ysis+6.885
+6.742
 ever+6.407
+6.319
Neg logit contributions
HUD-9.903
hooting-9.742
advertisement-9.081
icide-8.541
boarding-8.378
Token again
Token ID757
Feature activation+7.86e-01

Pos logit contributions
amins+11.493
ysis+11.124
 ever+11.101
+10.572
 submar+10.129
Neg logit contributions
HUD-15.932
hooting-15.257
advertisement-14.866
icide-13.610
laughter-13.222
Token,
Token ID11
Feature activation+6.26e-01

Pos logit contributions
amins+6.444
ysis+6.140
+6.085
Thumbnail+5.661
uty+5.627
Neg logit contributions
HUD-6.585
hooting-6.502
advertisement-6.090
icide-5.581
boarding-5.516
Token and
Token ID290
Feature activation+6.57e-01

Pos logit contributions
amins+4.817
ysis+4.539
+4.516
Thumbnail+4.203
+4.138
Neg logit contributions
HUD-5.741
hooting-5.727
advertisement-5.259
boarding-4.992
icide-4.927
Token the
Token ID262
Feature activation+2.98e-01

Pos logit contributions
amins+5.459
ysis+5.127
+5.065
+4.757
+4.731
Neg logit contributions
HUD-5.585
hooting-5.541
advertisement-5.119
boarding-4.771
icide-4.730
Token brewing
Token ID21778
Feature activation+2.87e-01

Pos logit contributions
amins+2.512
ysis+2.374
+2.362
Thumbnail+2.210
+2.191
Neg logit contributions
hooting-2.571
HUD-2.562
advertisement-2.342
boarding-2.234
icide-2.190
Token aware
Token ID3910
Feature activation-1.21e-01

Pos logit contributions
hooting+4.319
HUD+4.156
advertisement+3.751
boarding+3.742
horn+3.523
Neg logit contributions
amins-5.323
-5.130
ysis-5.069
Thumbnail-4.819
isine-4.728
Token of
Token ID286
Feature activation-1.43e-01

Pos logit contributions
hooting+0.942
HUD+0.931
advertisement+0.845
boarding+0.807
icide+0.788
Neg logit contributions
amins-1.123
ysis-1.070
-1.063
Thumbnail-1.014
-0.996
Token what
Token ID644
Feature activation-1.53e-01

Pos logit contributions
hooting+1.192
HUD+1.177
advertisement+1.078
boarding+1.029
icide+1.004
Neg logit contributions
amins-1.246
ysis-1.183
-1.170
Thumbnail-1.116
-1.090
Token has
Token ID468
Feature activation+4.00e-01

Pos logit contributions
hooting+1.329
HUD+1.307
advertisement+1.206
boarding+1.162
icide+1.140
Neg logit contributions
amins-1.279
ysis-1.221
-1.202
Thumbnail-1.148
-1.121
Token been
Token ID587
Feature activation+8.07e-01

Pos logit contributions
amins+2.965
+2.783
ysis+2.780
Thumbnail+2.583
+2.567
Neg logit contributions
HUD-3.808
hooting-3.791
advertisement-3.490
boarding-3.353
icide-3.295
Token going
Token ID1016
Feature activation+1.88e+00

Pos logit contributions
amins+6.046
+5.671
ysis+5.535
+5.334
Thumbnail+5.266
Neg logit contributions
HUD-7.308
hooting-7.138
advertisement-6.660
boarding-6.281
icide-6.280
Token on
Token ID319
Feature activation+4.60e-01

Pos logit contributions
amins+8.915
 ever+8.184
uty+7.891
+7.808
+7.722
Neg logit contributions
HUD-18.407
hooting-17.876
advertisement-17.064
boarding-15.904
icide-15.875
Token the
Token ID262
Feature activation-3.04e-02

Pos logit contributions
amins+3.952
+3.738
ysis+3.716
Thumbnail+3.501
+3.464
Neg logit contributions
HUD-3.822
hooting-3.796
advertisement-3.462
boarding-3.289
icide-3.228
Token last
Token ID938
Feature activation+6.75e-01

Pos logit contributions
hooting+0.243
HUD+0.240
advertisement+0.218
boarding+0.209
icide+0.203
Neg logit contributions
amins-0.276
ysis-0.263
-0.260
Thumbnail-0.248
-0.244
Token few
Token ID1178
Feature activation-4.12e-02

Pos logit contributions
amins+5.655
+5.328
ysis+5.300
+5.019
+4.943
Neg logit contributions
hooting-5.610
HUD-5.590
advertisement-5.096
boarding-4.826
horn-4.729
Token weeks
Token ID2745
Feature activation+5.92e-02

Pos logit contributions
hooting+0.416
HUD+0.411
advertisement+0.380
boarding+0.369
icide+0.362
Neg logit contributions
amins-0.289
ysis-0.271
-0.268
Thumbnail-0.252
-0.244
Token being
Token ID852
Feature activation+1.21e-01

Pos logit contributions
amins+2.631
ysis+2.484
+2.469
Thumbnail+2.307
+2.294
Neg logit contributions
HUD-2.993
hooting-2.970
advertisement-2.732
boarding-2.595
icide-2.574
Token able
Token ID1498
Feature activation+2.57e-01

Pos logit contributions
amins+1.038
ysis+0.983
+0.979
Thumbnail+0.921
+0.910
Neg logit contributions
hooting-1.032
HUD-1.025
advertisement-0.936
boarding-0.894
icide-0.877
Token to
Token ID284
Feature activation+5.78e-01

Pos logit contributions
amins+2.181
ysis+2.063
+2.057
Thumbnail+1.932
+1.910
Neg logit contributions
hooting-2.196
HUD-2.188
advertisement-1.999
boarding-1.902
icide-1.868
Token express
Token ID4911
Feature activation+5.92e-01

Pos logit contributions
amins+4.257
ysis+4.034
+4.024
 sidx+3.702
+3.698
Neg logit contributions
HUD-5.429
hooting-5.333
advertisement-4.940
boarding-4.680
icide-4.660
Token their
Token ID511
Feature activation+4.80e-01

Pos logit contributions
amins+4.619
ysis+4.366
+4.350
Thumbnail+4.058
+4.029
Neg logit contributions
hooting-5.313
HUD-5.306
advertisement-4.850
boarding-4.615
icide-4.593
Token First
Token ID3274
Feature activation+1.85e+00

Pos logit contributions
amins+3.294
ysis+3.108
+3.088
Thumbnail+2.847
+2.819
Neg logit contributions
hooting-4.824
HUD-4.803
advertisement-4.434
boarding-4.256
icide-4.218
Token Amendment
Token ID8441
Feature activation+1.39e+00

Pos logit contributions
amins+8.370
+7.501
+7.291
ysis+7.212
+6.953
Neg logit contributions
hooting-19.179
HUD-19.092
advertisement-17.736
icide-17.047
boarding-16.697
Token rights
Token ID2489
Feature activation+5.50e-01

Pos logit contributions
amins+7.954
+7.493
ysis+7.463
+7.151
uty+7.052
Neg logit contributions
HUD-13.699
hooting-13.391
advertisement-12.194
icide-11.897
boarding-11.876
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
amins+4.596
ysis+4.347
+4.326
Thumbnail+4.055
+4.032
Neg logit contributions
HUD-4.684
hooting-4.630
advertisement-4.238
boarding-4.030
icide-3.986
Token
Token ID198
Feature activation+9.50e-02

Pos logit contributions
amins+1.324
ysis+1.258
+1.251
Thumbnail+1.182
+1.168
Neg logit contributions
hooting-1.149
HUD-1.141
advertisement-1.035
boarding-0.985
icide-0.962
Token
Token ID198
Feature activation+4.97e-01

Pos logit contributions
amins+0.878
ysis+0.834
+0.830
Thumbnail+0.784
+0.777
Neg logit contributions
hooting-0.746
HUD-0.741
advertisement-0.673
boarding-0.640
icide-0.624
Token
Token ID198
Feature activation+4.41e-01

Pos logit contributions
amins+0.953
ysis+0.905
+0.901
Thumbnail+0.852
+0.843
Neg logit contributions
hooting-0.820
HUD-0.814
advertisement-0.739
boarding-0.703
icide-0.687
TokenWatch
Token ID10723
Feature activation-2.50e-01

Pos logit contributions
amins+3.867
+3.678
ysis+3.643
Thumbnail+3.508
+3.409
Neg logit contributions
hooting-3.627
HUD-3.551
advertisement-3.223
boarding-3.114
icide-3.082
Token
Token ID564
Feature activation+7.53e-01

Pos logit contributions
hooting+1.972
HUD+1.955
advertisement+1.804
boarding+1.704
horn+1.687
Neg logit contributions
amins-2.300
ysis-2.178
-2.144
Thumbnail-2.009
 sidx-2.005
Token
Token ID250
Feature activation+1.93e-01

Pos logit contributions
amins+3.866
+3.771
+3.713
+3.690
ysis+3.597
Neg logit contributions
hooting-8.635
HUD-8.491
advertisement-7.777
boarding-7.674
icide-7.665
TokenOutside
Token ID30815
Feature activation+9.35e-02

Pos logit contributions
amins+1.750
ysis+1.661
+1.654
Thumbnail+1.563
+1.544
Neg logit contributions
hooting-1.550
HUD-1.539
advertisement-1.397
boarding-1.332
icide-1.302
Token First
Token ID3274
Feature activation+1.85e+00

Pos logit contributions
amins+0.797
ysis+0.753
+0.750
Thumbnail+0.706
+0.696
Neg logit contributions
hooting-0.802
HUD-0.798
advertisement-0.729
boarding-0.697
icide-0.680
Token Presidential
Token ID17471
Feature activation+8.33e-01

Pos logit contributions
amins+14.017
+12.819
ysis+12.761
+12.436
+12.343
Neg logit contributions
hooting-13.435
HUD-12.907
advertisement-12.193
icide-11.440
boarding-10.958
Token Debate
Token ID41029
Feature activation+1.75e-01

Pos logit contributions
amins+5.078
ysis+4.876
+4.612
Thumbnail+4.374
+4.328
Neg logit contributions
HUD-8.613
hooting-8.597
advertisement-7.983
icide-7.607
boarding-7.564
Token,
Token ID11
Feature activation+5.14e-01

Pos logit contributions
amins+1.506
ysis+1.426
+1.420
Thumbnail+1.337
+1.319
Neg logit contributions
hooting-1.485
HUD-1.474
advertisement-1.348
boarding-1.288
icide-1.258
Token 24
Token ID1987
Feature activation+7.89e-01

Pos logit contributions
amins+4.419
ysis+4.174
+4.172
Thumbnail+3.933
+3.903
Neg logit contributions
hooting-4.261
HUD-4.212
advertisement-3.842
boarding-3.680
icide-3.618
Token Arrest
Token ID35080
Feature activation-6.40e-02

Pos logit contributions
amins+6.163
+5.811
ysis+5.752
+5.388
Thumbnail+5.375
Neg logit contributions
HUD-6.934
hooting-6.934
advertisement-6.404
boarding-6.070
icide-6.025
Tokenula
Token ID4712
Feature activation+4.29e-01

Pos logit contributions
amins+1.293
ysis+1.223
+1.221
Thumbnail+1.152
+1.138
Neg logit contributions
hooting-1.234
HUD-1.222
advertisement-1.120
boarding-1.067
icide-1.047
Token could
Token ID714
Feature activation-1.99e-01

Pos logit contributions
amins+4.005
ysis+3.807
+3.791
+3.578
Thumbnail+3.570
Neg logit contributions
HUD-3.242
hooting-3.229
advertisement-2.940
boarding-2.753
icide-2.667
Token not
Token ID407
Feature activation+9.81e-03

Pos logit contributions
hooting+1.724
HUD+1.670
advertisement+1.567
boarding+1.472
icide+1.453
Neg logit contributions
amins-1.688
-1.587
ysis-1.567
Thumbnail-1.507
-1.466
Token keep
Token ID1394
Feature activation+4.86e-01

Pos logit contributions
amins+0.082
+0.078
ysis+0.077
Thumbnail+0.074
+0.072
Neg logit contributions
hooting-0.086
HUD-0.084
advertisement-0.078
boarding-0.075
icide-0.073
Token her
Token ID607
Feature activation+8.13e-01

Pos logit contributions
amins+3.864
ysis+3.661
+3.654
Thumbnail+3.367
+3.357
Neg logit contributions
HUD-4.345
hooting-4.341
advertisement-3.960
boarding-3.755
icide-3.719
Token balance
Token ID5236
Feature activation+1.84e+00

Pos logit contributions
amins+6.359
ysis+6.163
+5.970
uty+5.589
Thumbnail+5.571
Neg logit contributions
hooting-7.126
HUD-7.097
advertisement-6.447
boarding-6.048
icide-5.999
Token and
Token ID290
Feature activation+1.07e+00

Pos logit contributions
amins+10.783
 ever+10.709
ysis+10.448
+9.806
uty+9.677
Neg logit contributions
HUD-16.027
hooting-14.754
advertisement-14.237
laughter-13.055
icide-12.980
Token slipped
Token ID18859
Feature activation+5.43e-01

Pos logit contributions
amins+9.030
ysis+8.557
+8.550
 submar+8.302
 ever+8.251
Neg logit contributions
HUD-8.111
hooting-7.910
advertisement-7.401
boarding-6.777
icide-6.664
Token.
Token ID13
Feature activation+2.57e-01

Pos logit contributions
amins+4.358
ysis+4.177
+4.137
uty+3.839
Thumbnail+3.837
Neg logit contributions
HUD-4.754
hooting-4.647
advertisement-4.312
boarding-4.011
icide-3.981
Token She
Token ID1375
Feature activation+5.08e-01

Pos logit contributions
amins+2.181
ysis+2.062
+2.053
Thumbnail+1.931
+1.906
Neg logit contributions
hooting-2.218
HUD-2.201
advertisement-2.013
boarding-1.926
icide-1.887
Token fell
Token ID3214
Feature activation+7.37e-01

Pos logit contributions
amins+4.453
ysis+4.240
+4.196
Thumbnail+3.942
uty+3.937
Neg logit contributions
HUD-4.109
hooting-4.006
advertisement-3.709
boarding-3.467
icide-3.395
Tokenond
Token ID623
Feature activation+4.06e-03

Pos logit contributions
amins+1.845
ysis+1.746
+1.735
Thumbnail+1.631
+1.614
Neg logit contributions
hooting-1.856
HUD-1.842
advertisement-1.686
boarding-1.611
icide-1.576
Tokenrl
Token ID45895
Feature activation+8.99e-01

Pos logit contributions
amins+0.035
ysis+0.033
+0.033
Thumbnail+0.031
+0.030
Neg logit contributions
hooting-0.035
HUD-0.034
advertisement-0.031
boarding-0.030
icide-0.029
Tokení
Token ID8836
Feature activation+7.94e-01

Pos logit contributions
amins+5.902
ysis+5.673
+5.487
uty+5.286
isine+5.067
Neg logit contributions
hooting-8.731
HUD-8.682
advertisement-8.153
boarding-7.757
horn-7.571
Tokenk
Token ID74
Feature activation+5.30e-02

Pos logit contributions
amins+6.428
ysis+6.172
+6.062
+5.786
uty+5.785
Neg logit contributions
hooting-6.534
HUD-6.491
advertisement-5.991
boarding-5.544
icide-5.454
Token,
Token ID11
Feature activation+1.93e-01

Pos logit contributions
amins+0.524
ysis+0.499
+0.497
Thumbnail+0.472
+0.468
Neg logit contributions
hooting-0.382
HUD-0.378
advertisement-0.341
boarding-0.322
icide-0.313
Token
Token ID25370
Feature activation+1.84e+00

Pos logit contributions
amins+1.722
ysis+1.634
+1.627
Thumbnail+1.534
+1.517
Neg logit contributions
hooting-1.572
HUD-1.559
advertisement-1.419
boarding-1.353
icide-1.324
Token
Token ID254
Feature activation+9.45e-01

Pos logit contributions
+8.826
+8.123
amins+6.878
ysis+6.703
+6.461
Neg logit contributions
hooting-19.902
HUD-18.991
advertisement-18.437
boarding-17.808
icide-17.572
Tokenpal
Token ID18596
Feature activation+7.41e-01

Pos logit contributions
amins+8.593
ysis+8.216
+8.050
uty+7.727
+7.680
Neg logit contributions
hooting-6.849
HUD-6.768
advertisement-6.208
boarding-5.832
icide-5.658
Tokenek
Token ID988
Feature activation+4.31e-01

Pos logit contributions
amins+6.443
ysis+6.167
+6.009
uty+5.760
+5.652
Neg logit contributions
hooting-5.899
HUD-5.879
advertisement-5.394
boarding-5.071
icide-4.870
Token.
Token ID13
Feature activation-2.93e-01

Pos logit contributions
amins+4.063
ysis+3.861
+3.849
uty+3.631
Thumbnail+3.627
Neg logit contributions
hooting-3.226
HUD-3.197
advertisement-2.922
boarding-2.751
icide-2.683
Token<|endoftext|>
Token ID50256
Feature activation-1.14e-01

Pos logit contributions
hooting+2.361
HUD+2.343
advertisement+2.122
boarding+2.026
icide+1.988
Neg logit contributions
amins-2.641
ysis-2.502
-2.495
Thumbnail-2.350
-2.321
Token So
Token ID1406
Feature activation-2.54e-01

Pos logit contributions
amins+3.987
+3.776
ysis+3.771
Thumbnail+3.541
+3.474
Neg logit contributions
hooting-4.370
HUD-4.294
advertisement-3.942
boarding-3.786
icide-3.723
Token what
Token ID644
Feature activation+5.20e-01

Pos logit contributions
hooting+2.096
HUD+2.093
advertisement+1.871
boarding+1.833
icide+1.800
Neg logit contributions
amins-2.224
ysis-2.116
-2.104
Thumbnail-1.987
-1.948
Token made
Token ID925
Feature activation-4.05e-03

Pos logit contributions
amins+4.026
ysis+3.763
+3.743
Thumbnail+3.490
+3.487
Neg logit contributions
HUD-4.740
hooting-4.719
advertisement-4.363
boarding-4.109
icide-4.024
Token you
Token ID345
Feature activation+8.05e-01

Pos logit contributions
hooting+0.034
HUD+0.033
advertisement+0.030
boarding+0.029
icide+0.029
Neg logit contributions
amins-0.036
ysis-0.034
-0.034
Thumbnail-0.032
-0.031
Token guys
Token ID3730
Feature activation+8.45e-01

Pos logit contributions
amins+5.549
ysis+5.366
+5.256
Thumbnail+4.923
 ever+4.916
Neg logit contributions
HUD-7.669
hooting-7.538
advertisement-7.154
boarding-6.545
bees-6.456
Token go
Token ID467
Feature activation+1.82e+00

Pos logit contributions
amins+5.732
ysis+5.522
+5.343
 ever+5.097
Thumbnail+5.010
Neg logit contributions
HUD-8.015
hooting-7.936
advertisement-7.556
boarding-6.902
icide-6.861
Token with
Token ID351
Feature activation+7.07e-01

Pos logit contributions
amins+11.701
+11.214
ysis+11.127
 ever+10.933
Thumbnail+10.492
Neg logit contributions
HUD-14.779
hooting-14.334
advertisement-14.140
icide-12.526
bees-12.362
Token Hunt
Token ID12937
Feature activation+7.71e-02

Pos logit contributions
amins+5.953
ysis+5.735
+5.719
+5.340
Thumbnail+5.339
Neg logit contributions
hooting-5.667
HUD-5.664
advertisement-5.211
boarding-4.792
icide-4.743
Tokenress
Token ID601
Feature activation+8.82e-01

Pos logit contributions
amins+0.495
ysis+0.459
+0.453
Thumbnail+0.419
+0.408
Neg logit contributions
hooting-0.824
HUD-0.820
advertisement-0.760
boarding-0.738
icide-0.728
Token?
Token ID30
Feature activation+2.51e-01

Pos logit contributions
amins+6.535
+6.311
ysis+6.276
Thumbnail+5.875
endor+5.796
Neg logit contributions
hooting-7.817
HUD-7.722
advertisement-7.105
boarding-6.726
icide-6.531
Token
Token ID198
Feature activation-3.07e-01

Pos logit contributions
amins+2.168
ysis+2.055
+2.047
Thumbnail+1.933
+1.901
Neg logit contributions
hooting-2.105
HUD-2.086
advertisement-1.907
boarding-1.822
icide-1.782
Token centre
Token ID7372
Feature activation+1.51e-01

Pos logit contributions
amins+3.425
ysis+3.241
+3.222
Thumbnail+3.035
+2.993
Neg logit contributions
hooting-3.801
HUD-3.773
advertisement-3.444
boarding-3.295
icide-3.221
Token of
Token ID286
Feature activation+2.95e-01

Pos logit contributions
amins+1.319
ysis+1.249
+1.244
Thumbnail+1.173
+1.157
Neg logit contributions
hooting-1.266
HUD-1.256
advertisement-1.145
boarding-1.096
icide-1.072
Token the
Token ID262
Feature activation-2.30e-01

Pos logit contributions
amins+2.426
ysis+2.287
+2.278
Thumbnail+2.141
+2.113
Neg logit contributions
hooting-2.605
HUD-2.588
advertisement-2.371
boarding-2.267
icide-2.226
Token debate
Token ID4384
Feature activation+5.32e-01

Pos logit contributions
hooting+1.931
HUD+1.918
advertisement+1.764
boarding+1.698
horn+1.648
Neg logit contributions
amins-1.958
ysis-1.888
-1.860
Thumbnail-1.750
-1.731
Token,
Token ID11
Feature activation+8.48e-01

Pos logit contributions
amins+4.455
ysis+4.239
+4.174
Thumbnail+3.913
uty+3.890
Neg logit contributions
HUD-4.538
hooting-4.492
advertisement-4.083
boarding-3.863
icide-3.801
Token seems
Token ID2331
Feature activation+1.80e+00

Pos logit contributions
amins+6.530
ysis+6.189
+6.004
 submar+5.682
+5.672
Neg logit contributions
HUD-7.419
hooting-7.414
advertisement-6.673
boarding-6.400
horn-6.255
Token to
Token ID284
Feature activation+5.42e-01

Pos logit contributions
amins+10.750
 ever+10.730
ysis+9.886
+9.754
+9.699
Neg logit contributions
HUD-15.167
hooting-14.951
advertisement-13.754
boarding-13.303
horn-12.470
Token me
Token ID502
Feature activation+1.70e+00

Pos logit contributions
amins+5.298
ysis+5.125
+5.117
+4.819
Thumbnail+4.804
Neg logit contributions
HUD-3.776
hooting-3.726
advertisement-3.350
boarding-3.170
icide-3.012
Token like
Token ID588
Feature activation+8.37e-01

Pos logit contributions
amins+10.569
 ever+10.061
ysis+9.670
+9.544
 submar+9.544
Neg logit contributions
HUD-14.503
hooting-14.273
advertisement-12.949
boarding-12.738
horn-11.941
Token an
Token ID281
Feature activation+1.54e+00

Pos logit contributions
amins+6.477
ysis+6.071
+5.935
 submar+5.674
+5.674
Neg logit contributions
HUD-7.338
hooting-7.193
advertisement-6.578
boarding-6.163
horn-6.051
Token unnecessary
Token ID13114
Feature activation+4.08e-01

Pos logit contributions
amins+8.523
 ever+7.669
ysis+7.362
+7.146
uty+6.968
Neg logit contributions
HUD-15.536
hooting-15.428
advertisement-13.647
boarding-13.506
bees-13.276
TokenIt
Token ID1026
Feature activation+5.32e-01

Pos logit contributions
amins+5.900
+5.740
ysis+5.567
Thumbnail+5.562
+5.287
Neg logit contributions
hooting-5.922
HUD-5.552
icide-5.039
advertisement-5.029
boarding-4.943
Token's
Token ID338
Feature activation+2.94e-01

Pos logit contributions
amins+3.929
ysis+3.672
+3.625
Thumbnail+3.385
+3.331
Neg logit contributions
HUD-5.110
hooting-4.994
advertisement-4.630
boarding-4.380
icide-4.320
Token pretty
Token ID2495
Feature activation+1.94e-01

Pos logit contributions
amins+2.507
ysis+2.378
+2.365
Thumbnail+2.227
+2.199
Neg logit contributions
hooting-2.483
HUD-2.481
advertisement-2.253
boarding-2.153
icide-2.119
Token strange
Token ID6283
Feature activation+1.03e-01

Pos logit contributions
amins+1.703
ysis+1.615
+1.608
Thumbnail+1.516
+1.499
Neg logit contributions
hooting-1.598
HUD-1.588
advertisement-1.445
boarding-1.379
icide-1.351
Token your
Token ID534
Feature activation+5.46e-01

Pos logit contributions
amins+0.923
ysis+0.874
+0.874
Thumbnail+0.823
+0.812
Neg logit contributions
hooting-0.844
HUD-0.835
advertisement-0.762
boarding-0.729
icide-0.711
Token first
Token ID717
Feature activation+1.80e+00

Pos logit contributions
amins+4.553
ysis+4.324
+4.264
Thumbnail+4.083
+3.962
Neg logit contributions
HUD-4.638
hooting-4.625
advertisement-4.197
boarding-4.008
icide-3.943
Token time
Token ID640
Feature activation+3.42e-01

Pos logit contributions
 ever+11.705
amins+11.656
ysis+11.464
Thumbnail+10.935
+10.853
Neg logit contributions
HUD-14.605
hooting-14.164
advertisement-12.396
bees-12.317
icide-12.028
Token back
Token ID736
Feature activation+2.31e-01

Pos logit contributions
amins+2.879
ysis+2.734
+2.693
Thumbnail+2.560
+2.517
Neg logit contributions
HUD-2.930
hooting-2.908
advertisement-2.645
boarding-2.509
icide-2.491
Token,
Token ID11
Feature activation+9.58e-02

Pos logit contributions
amins+1.959
ysis+1.853
+1.841
Thumbnail+1.736
+1.711
Neg logit contributions
hooting-1.986
HUD-1.979
advertisement-1.807
boarding-1.719
icide-1.692
Token especially
Token ID2592
Feature activation+4.41e-02

Pos logit contributions
amins+0.850
ysis+0.804
+0.804
Thumbnail+0.756
+0.747
Neg logit contributions
hooting-0.789
HUD-0.783
advertisement-0.715
boarding-0.682
icide-0.667
Token if
Token ID611
Feature activation+6.69e-01

Pos logit contributions
amins+0.370
ysis+0.349
+0.349
Thumbnail+0.326
+0.323
Neg logit contributions
hooting-0.385
HUD-0.381
advertisement-0.350
boarding-0.336
icide-0.327
Token the
Token ID262
Feature activation+1.37e-01

Pos logit contributions
amins+6.402
ysis+6.126
+5.948
Thumbnail+5.644
 submar+5.617
Neg logit contributions
HUD-7.296
hooting-7.226
advertisement-6.609
horn-6.255
boarding-6.202
Token way
Token ID835
Feature activation+4.45e-01

Pos logit contributions
amins+1.427
ysis+1.363
+1.358
Thumbnail+1.295
+1.281
Neg logit contributions
hooting-0.918
HUD-0.910
advertisement-0.810
boarding-0.765
icide-0.742
Token we
Token ID356
Feature activation+6.45e-01

Pos logit contributions
amins+3.614
ysis+3.436
+3.347
Thumbnail+3.160
+3.105
Neg logit contributions
hooting-3.914
HUD-3.913
advertisement-3.578
boarding-3.384
horn-3.351
Token train
Token ID4512
Feature activation+1.18e+00

Pos logit contributions
amins+4.570
ysis+4.375
+4.209
+3.970
uty+3.957
Neg logit contributions
HUD-6.169
hooting-6.112
advertisement-5.657
boarding-5.398
horn-5.382
Token our
Token ID674
Feature activation+6.21e-01

Pos logit contributions
amins+9.121
ysis+8.791
+8.091
 submar+8.083
 ever+8.044
Neg logit contributions
HUD-9.951
hooting-9.490
advertisement-8.852
horn-8.227
icide-8.193
Token first
Token ID717
Feature activation+1.80e+00

Pos logit contributions
amins+4.513
ysis+4.280
+4.167
Thumbnail+3.858
+3.836
Neg logit contributions
hooting-5.963
HUD-5.946
advertisement-5.478
boarding-5.202
horn-5.138
Token responders
Token ID33339
Feature activation+7.33e-01

Pos logit contributions
amins+12.662
ysis+11.980
 ever+11.395
+11.049
uty+10.651
Neg logit contributions
HUD-14.573
hooting-14.181
advertisement-13.643
boarding-11.982
horn-11.924
Token!
Token ID0
Feature activation+5.98e-02

Pos logit contributions
amins+5.838
ysis+5.655
+5.445
uty+5.178
 ever+5.106
Neg logit contributions
HUD-6.326
hooting-6.054
advertisement-5.722
boarding-5.305
horn-5.284
Token
Token ID198
Feature activation-4.63e-02

Pos logit contributions
amins+0.530
ysis+0.501
+0.499
Thumbnail+0.470
+0.467
Neg logit contributions
hooting-0.492
HUD-0.491
advertisement-0.447
boarding-0.426
icide-0.415
Token
Token ID198
Feature activation+1.26e-02

Pos logit contributions
HUD+0.346
hooting+0.345
advertisement+0.314
boarding+0.296
horn+0.289
Neg logit contributions
amins-0.447
ysis-0.426
-0.420
-0.399
-0.398
TokenDes
Token ID5960
Feature activation-8.63e-01

Pos logit contributions
amins+0.112
ysis+0.106
+0.104
+0.098
 sidx+0.098
Neg logit contributions
HUD-0.105
hooting-0.103
advertisement-0.096
boarding-0.090
horn-0.087
Token
Token ID198
Feature activation-3.40e-02

Pos logit contributions
amins+3.146
+3.003
ysis+2.976
Thumbnail+2.832
uty+2.758
Neg logit contributions
hooting-3.166
HUD-3.112
advertisement-2.816
boarding-2.713
icide-2.674
TokenHowever
Token ID4864
Feature activation-4.07e-02

Pos logit contributions
HUD+0.280
hooting+0.275
advertisement+0.257
boarding+0.240
horn+0.236
Neg logit contributions
amins-0.303
ysis-0.289
-0.283
 sidx-0.267
-0.266
Token,
Token ID11
Feature activation+3.13e-01

Pos logit contributions
hooting+0.294
HUD+0.292
advertisement+0.262
boarding+0.248
icide+0.242
Neg logit contributions
amins-0.401
ysis-0.383
-0.381
Thumbnail-0.362
-0.358
Token now
Token ID783
Feature activation+3.68e-01

Pos logit contributions
amins+2.663
ysis+2.513
+2.500
Thumbnail+2.346
+2.324
Neg logit contributions
hooting-2.678
HUD-2.666
advertisement-2.437
boarding-2.321
icide-2.279
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
amins+3.000
ysis+2.828
+2.798
Thumbnail+2.627
+2.601
Neg logit contributions
hooting-3.251
HUD-3.249
advertisement-2.989
boarding-2.830
icide-2.792
Token tide
Token ID20013
Feature activation+1.79e+00

Pos logit contributions
amins+0.107
ysis+0.101
+0.101
Thumbnail+0.095
+0.093
Neg logit contributions
hooting-0.111
HUD-0.110
advertisement-0.101
boarding-0.097
icide-0.095
Token has
Token ID468
Feature activation+1.04e+00

Pos logit contributions
amins+11.116
ysis+10.777
+10.065
 ever+9.999
+9.426
Neg logit contributions
HUD-15.344
hooting-15.078
advertisement-14.302
icide-13.445
laughter-12.879
Token turned
Token ID2900
Feature activation+1.90e+00

Pos logit contributions
amins+6.962
ysis+6.885
+6.742
 ever+6.407
+6.319
Neg logit contributions
HUD-9.903
hooting-9.742
advertisement-9.081
icide-8.541
boarding-8.378
Token again
Token ID757
Feature activation+7.86e-01

Pos logit contributions
amins+11.493
ysis+11.124
 ever+11.101
+10.572
 submar+10.129
Neg logit contributions
HUD-15.932
hooting-15.257
advertisement-14.866
icide-13.610
laughter-13.222
Token,
Token ID11
Feature activation+6.26e-01

Pos logit contributions
amins+6.444
ysis+6.140
+6.085
Thumbnail+5.661
uty+5.627
Neg logit contributions
HUD-6.585
hooting-6.502
advertisement-6.090
icide-5.581
boarding-5.516
Token and
Token ID290
Feature activation+6.57e-01

Pos logit contributions
amins+4.817
ysis+4.539
+4.516
Thumbnail+4.203
+4.138
Neg logit contributions
HUD-5.741
hooting-5.727
advertisement-5.259
boarding-4.992
icide-4.927
Token but
Token ID475
Feature activation+5.17e-01

Pos logit contributions
hooting+0.528
HUD+0.518
advertisement+0.468
boarding+0.439
icide+0.426
Neg logit contributions
amins-0.825
-0.789
ysis-0.788
Thumbnail-0.751
-0.743
Token if
Token ID611
Feature activation+1.08e+00

Pos logit contributions
amins+4.180
ysis+3.924
+3.870
Thumbnail+3.633
+3.616
Neg logit contributions
HUD-4.566
hooting-4.553
advertisement-4.140
boarding-3.964
icide-3.910
Token you
Token ID345
Feature activation+1.16e+00

Pos logit contributions
amins+6.855
ysis+6.587
+6.330
 ever+6.045
+5.952
Neg logit contributions
HUD-10.485
hooting-10.293
advertisement-9.556
boarding-9.089
icide-9.080
Token have
Token ID423
Feature activation+8.94e-01

Pos logit contributions
amins+7.173
ysis+6.895
 ever+6.879
+6.649
+6.303
Neg logit contributions
HUD-11.278
hooting-10.818
advertisement-10.187
boarding-9.810
icide-9.538
Token a
Token ID257
Feature activation+7.16e-01

Pos logit contributions
amins+7.035
ysis+6.780
+6.637
 ever+6.279
Thumbnail+6.173
Neg logit contributions
HUD-7.647
hooting-7.534
advertisement-6.896
boarding-6.535
icide-6.441
Token child
Token ID1200
Feature activation+1.78e+00

Pos logit contributions
amins+5.962
ysis+5.787
+5.679
+5.344
+5.316
Neg logit contributions
HUD-5.902
hooting-5.789
advertisement-5.307
boarding-5.004
icide-4.941
Token that
Token ID326
Feature activation+7.60e-01

Pos logit contributions
amins+11.168
ysis+10.928
 ever+10.744
uty+10.422
+10.373
Neg logit contributions
HUD-14.970
hooting-13.617
advertisement-12.886
icide-11.896
laughter-11.840
Token is
Token ID318
Feature activation+6.89e-01

Pos logit contributions
amins+5.517
ysis+5.097
+5.011
+4.677
Thumbnail+4.676
Neg logit contributions
HUD-7.257
hooting-7.115
advertisement-6.611
boarding-6.298
icide-6.144
Token older
Token ID4697
Feature activation+9.37e-01

Pos logit contributions
amins+5.689
ysis+5.436
+5.346
uty+5.086
+5.077
Neg logit contributions
HUD-5.699
hooting-5.543
advertisement-5.154
icide-4.819
boarding-4.807
Token they
Token ID484
Feature activation+2.64e-01

Pos logit contributions
amins+8.083
ysis+7.548
+7.339
+6.993
 ever+6.971
Neg logit contributions
HUD-7.285
hooting-7.149
advertisement-6.662
horn-6.006
icide-5.929
Token should
Token ID815
Feature activation+4.09e-01

Pos logit contributions
amins+2.697
ysis+2.575
+2.557
Thumbnail+2.434
+2.418
Neg logit contributions
HUD-1.783
hooting-1.782
advertisement-1.588
boarding-1.494
icide-1.449
TokenHere
Token ID4342
Feature activation+7.04e-01

Pos logit contributions
amins+2.635
+2.499
ysis+2.489
Thumbnail+2.373
+2.325
Neg logit contributions
hooting-2.432
HUD-2.393
advertisement-2.164
boarding-2.087
icide-2.051
Token,
Token ID11
Feature activation+4.24e-01

Pos logit contributions
amins+5.027
+4.718
ysis+4.713
Thumbnail+4.422
+4.391
Neg logit contributions
HUD-6.681
hooting-6.641
advertisement-6.109
boarding-5.826
icide-5.781
Token in
Token ID287
Feature activation-2.32e-01

Pos logit contributions
amins+3.607
ysis+3.409
+3.399
Thumbnail+3.216
+3.173
Neg logit contributions
hooting-3.586
HUD-3.567
advertisement-3.244
boarding-3.106
icide-3.045
Token July
Token ID2901
Feature activation+2.91e-01

Pos logit contributions
hooting+1.860
HUD+1.822
advertisement+1.666
boarding+1.601
horn+1.541
Neg logit contributions
amins-2.110
ysis-2.005
-1.983
-1.864
Thumbnail-1.848
Token in
Token ID287
Feature activation+4.37e-01

Pos logit contributions
amins+2.743
ysis+2.619
+2.606
Thumbnail+2.481
+2.442
Neg logit contributions
hooting-2.196
HUD-2.181
advertisement-1.968
boarding-1.860
icide-1.831
Token Paw
Token ID35553
Feature activation+1.77e+00

Pos logit contributions
amins+3.783
ysis+3.579
+3.570
Thumbnail+3.383
uty+3.316
Neg logit contributions
HUD-3.593
hooting-3.586
advertisement-3.265
boarding-3.112
icide-3.066
Tokent
Token ID83
Feature activation+4.74e-01

Pos logit contributions
+9.887
amins+9.700
ysis+9.598
+9.403
endor+9.289
Neg logit contributions
HUD-15.068
hooting-14.651
advertisement-14.443
icide-13.207
bees-12.739
Tokenucket
Token ID38811
Feature activation+5.93e-01

Pos logit contributions
amins+1.914
ysis+1.676
+1.669
Thumbnail+1.510
uty+1.504
Neg logit contributions
hooting-6.116
HUD-6.092
advertisement-5.740
boarding-5.508
icide-5.409
Token,
Token ID11
Feature activation+1.12e+00

Pos logit contributions
amins+5.362
ysis+5.096
+5.058
Thumbnail+4.866
+4.819
Neg logit contributions
HUD-4.537
hooting-4.469
advertisement-4.095
boarding-3.864
icide-3.802
Token such
Token ID884
Feature activation+2.75e-01

Pos logit contributions
amins+9.044
ysis+8.518
+8.496
Thumbnail+8.148
 submar+8.091
Neg logit contributions
HUD-8.898
hooting-8.784
advertisement-8.070
horn-7.568
boarding-7.545
Token moments
Token ID7188
Feature activation+1.53e-01

Pos logit contributions
amins+2.345
ysis+2.223
+2.206
Thumbnail+2.083
+2.053
Neg logit contributions
hooting-2.337
HUD-2.330
advertisement-2.121
boarding-2.028
icide-1.987
Token me
Token ID502
Feature activation+5.15e-01

Pos logit contributions
amins+0.906
ysis+0.857
+0.853
Thumbnail+0.805
+0.793
Neg logit contributions
hooting-0.903
HUD-0.896
advertisement-0.820
boarding-0.784
icide-0.767
Token so
Token ID523
Feature activation+1.61e-01

Pos logit contributions
amins+4.390
ysis+4.213
+4.157
Thumbnail+3.930
+3.906
Neg logit contributions
HUD-4.265
hooting-4.244
advertisement-3.875
boarding-3.650
icide-3.602
Token excited
Token ID6568
Feature activation+1.34e+00

Pos logit contributions
amins+1.696
ysis+1.619
+1.614
Thumbnail+1.537
+1.520
Neg logit contributions
hooting-1.066
HUD-1.055
advertisement-0.936
boarding-0.884
icide-0.858
Token about
Token ID546
Feature activation+1.08e+00

Pos logit contributions
ysis+8.063
amins+8.036
+7.790
 ever+7.386
uty+7.108
Neg logit contributions
HUD-12.858
hooting-11.932
advertisement-11.157
boarding-10.558
icide-10.554
Token this
Token ID428
Feature activation+7.27e-01

Pos logit contributions
amins+7.430
+7.172
ysis+6.976
endor+6.542
+6.491
Neg logit contributions
HUD-9.792
hooting-9.686
advertisement-8.819
icide-8.500
boarding-8.461
Token comic
Token ID9048
Feature activation+1.77e+00

Pos logit contributions
amins+5.546
ysis+5.308
+5.285
Thumbnail+4.932
endor+4.813
Neg logit contributions
HUD-6.528
hooting-6.430
advertisement-5.785
boarding-5.580
horn-5.514
Token is
Token ID318
Feature activation-3.20e-02

Pos logit contributions
amins+10.565
ysis+10.387
+9.846
 ever+9.771
endor+9.332
Neg logit contributions
HUD-15.617
hooting-14.695
advertisement-12.869
bees-12.811
icide-12.573
Token that
Token ID326
Feature activation+2.40e-01

Pos logit contributions
hooting+0.274
HUD+0.272
advertisement+0.250
boarding+0.240
icide+0.233
Neg logit contributions
amins-0.273
ysis-0.258
-0.257
Thumbnail-0.242
-0.238
Token it
Token ID340
Feature activation+7.15e-01

Pos logit contributions
amins+2.083
ysis+1.972
+1.966
Thumbnail+1.850
+1.828
Neg logit contributions
hooting-2.010
HUD-1.997
advertisement-1.819
boarding-1.736
icide-1.702
Token transitions
Token ID27188
Feature activation+3.58e-01

Pos logit contributions
amins+5.106
+4.835
ysis+4.799
Thumbnail+4.416
endor+4.369
Neg logit contributions
HUD-6.907
hooting-6.759
advertisement-6.183
boarding-5.948
icide-5.848
Token between
Token ID1022
Feature activation+4.64e-01

Pos logit contributions
amins+3.143
ysis+2.980
+2.977
Thumbnail+2.790
+2.755
Neg logit contributions
hooting-2.941
HUD-2.931
advertisement-2.661
boarding-2.531
icide-2.475
Token designated
Token ID11032
Feature activation+4.38e-01

Pos logit contributions
amins+3.495
ysis+3.328
+3.289
Thumbnail+3.101
+3.059
Neg logit contributions
HUD-3.526
hooting-3.518
advertisement-3.202
boarding-3.055
icide-3.013
Token protest
Token ID5402
Feature activation+2.32e-01

Pos logit contributions
amins+3.574
ysis+3.445
+3.370
Thumbnail+3.162
+3.134
Neg logit contributions
HUD-3.787
hooting-3.775
advertisement-3.440
boarding-3.274
icide-3.256
Token area
Token ID1989
Feature activation-1.23e-01

Pos logit contributions
amins+1.694
ysis+1.587
+1.580
Thumbnail+1.469
+1.446
Neg logit contributions
hooting-2.263
HUD-2.249
advertisement-2.079
boarding-2.001
icide-1.966
Token in
Token ID287
Feature activation+6.83e-01

Pos logit contributions
hooting+0.970
HUD+0.948
advertisement+0.863
boarding+0.832
icide+0.814
Neg logit contributions
amins-1.138
-1.076
ysis-1.075
Thumbnail-1.019
-1.001
Token the
Token ID262
Feature activation+7.07e-01

Pos logit contributions
amins+5.627
ysis+5.387
+5.284
Thumbnail+5.000
endor+4.969
Neg logit contributions
HUD-5.710
hooting-5.684
advertisement-5.261
icide-4.871
boarding-4.863
Token first
Token ID717
Feature activation+1.76e+00

Pos logit contributions
amins+5.791
ysis+5.661
+5.486
Thumbnail+5.240
endor+5.153
Neg logit contributions
HUD-5.875
hooting-5.823
advertisement-5.363
boarding-5.066
icide-5.047
Token place
Token ID1295
Feature activation+5.12e-01

Pos logit contributions
amins+8.793
 ever+8.335
ysis+7.961
+7.466
+7.290
Neg logit contributions
HUD-17.284
hooting-16.733
advertisement-15.742
icide-15.313
laughter-14.858
Token.
Token ID13
Feature activation+5.86e-01

Pos logit contributions
amins+4.342
ysis+4.100
+4.090
Thumbnail+3.842
+3.833
Neg logit contributions
HUD-4.309
hooting-4.248
advertisement-3.899
boarding-3.694
icide-3.634
Token Martin
Token ID5780
Feature activation+4.17e-01

Pos logit contributions
amins+4.919
+4.716
ysis+4.681
Thumbnail+4.452
+4.370
Neg logit contributions
hooting-4.864
HUD-4.783
advertisement-4.372
boarding-4.199
icide-4.175
Token said
Token ID531
Feature activation+1.52e-01

Pos logit contributions
amins+3.741
ysis+3.569
+3.554
Thumbnail+3.337
+3.305
Neg logit contributions
hooting-3.328
HUD-3.298
advertisement-3.029
boarding-2.858
icide-2.785
Token:
Token ID25
Feature activation+6.89e-01

Pos logit contributions
amins+1.260
ysis+1.188
+1.185
Thumbnail+1.112
+1.097
Neg logit contributions
hooting-1.346
HUD-1.336
advertisement-1.225
boarding-1.175
icide-1.149
Token day
Token ID1110
Feature activation+2.75e-01

Pos logit contributions
hooting+0.957
HUD+0.938
advertisement+0.869
boarding+0.829
icide+0.804
Neg logit contributions
amins-1.011
ysis-0.951
-0.943
Thumbnail-0.896
-0.884
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
amins+2.532
ysis+2.409
+2.400
Thumbnail+2.268
+2.240
Neg logit contributions
hooting-2.154
HUD-2.141
advertisement-1.937
boarding-1.839
icide-1.803
Token
Token ID198
Feature activation+4.82e-02

Pos logit contributions
+9.873
amins+9.595
ysis+9.293
Thumbnail+9.096
+8.832
Neg logit contributions
hooting-11.966
HUD-11.797
advertisement-10.639
icide-10.597
boarding-10.444
Token
Token ID198
Feature activation+1.00e+00

Pos logit contributions
amins+0.453
ysis+0.430
+0.427
Thumbnail+0.403
+0.402
Neg logit contributions
hooting-0.371
HUD-0.369
advertisement-0.335
boarding-0.318
icide-0.309
Token
Token ID447
Feature activation-2.77e-01

Pos logit contributions
amins+7.689
+7.574
Thumbnail+7.316
ysis+7.260
+6.795
Neg logit contributions
hooting-8.634
HUD-8.223
icide-7.386
boarding-7.345
advertisement-7.329
Token
Token ID250
Feature activation+1.76e+00

Pos logit contributions
HUD+2.855
hooting+2.807
advertisement+2.668
boarding+2.536
horn+2.489
Neg logit contributions
amins-1.868
ysis-1.712
-1.679
 sidx-1.593
Thumbnail-1.569
TokenI
Token ID40
Feature activation+6.77e-01

Pos logit contributions
+13.042
amins+12.970
Thumbnail+12.758
ysis+12.218
+11.611
Neg logit contributions
hooting-12.662
HUD-11.442
icide-10.906
advertisement-10.319
boarding-10.269
Token just
Token ID655
Feature activation+2.15e-01

Pos logit contributions
amins+5.411
+5.141
ysis+5.132
Thumbnail+4.793
+4.774
Neg logit contributions
hooting-5.923
HUD-5.842
advertisement-5.446
boarding-5.113
icide-5.001
Token wish
Token ID4601
Feature activation+2.14e-01

Pos logit contributions
amins+1.810
ysis+1.714
+1.709
Thumbnail+1.603
+1.587
Neg logit contributions
hooting-1.852
HUD-1.838
advertisement-1.681
boarding-1.607
icide-1.574
Token he
Token ID339
Feature activation-4.45e-01

Pos logit contributions
amins+1.811
ysis+1.713
+1.706
Thumbnail+1.604
+1.582
Neg logit contributions
hooting-1.852
HUD-1.839
advertisement-1.682
boarding-1.609
icide-1.576
Token
Token ID447
Feature activation-4.02e-01

Pos logit contributions
hooting+3.056
HUD+2.947
advertisement+2.694
boarding+2.583
horn+2.487
Neg logit contributions
amins-4.430
-4.207
ysis-4.201
Thumbnail-4.070
uty-3.988
Token said
Token ID531
Feature activation-4.45e-01

Pos logit contributions
amins+0.298
ysis+0.282
+0.280
Thumbnail+0.264
+0.261
Neg logit contributions
hooting-0.296
HUD-0.293
advertisement-0.267
boarding-0.257
icide-0.252
Token he
Token ID339
Feature activation-1.37e-01

Pos logit contributions
HUD+3.625
hooting+3.612
advertisement+3.254
boarding+3.198
icide+3.094
Neg logit contributions
amins-3.936
-3.663
ysis-3.570
Thumbnail-3.460
-3.406
Token hoped
Token ID10719
Feature activation-7.12e-01

Pos logit contributions
hooting+1.116
HUD+1.092
advertisement+0.992
boarding+0.964
icide+0.945
Neg logit contributions
amins-1.232
-1.163
ysis-1.158
Thumbnail-1.098
-1.087
Token that
Token ID326
Feature activation-1.17e+00

Pos logit contributions
HUD+5.311
hooting+5.220
advertisement+4.658
boarding+4.533
icide+4.392
Neg logit contributions
amins-6.618
-6.099
ysis-6.063
Thumbnail-5.935
-5.853
Token Ike
Token ID34880
Feature activation-9.87e-01

Pos logit contributions
HUD+8.561
hooting+8.432
boarding+7.498
advertisement+7.387
 confession+7.233
Neg logit contributions
amins-10.242
-9.291
ysis-9.110
Thumbnail-9.098
-8.978
Tokena
Token ID64
Feature activation-2.21e+00

Pos logit contributions
HUD+3.771
hooting+3.759
advertisement+3.333
horn+2.884
bees+2.874
Neg logit contributions
amins-11.744
ysis-11.520
-11.452
-11.411
 submar-11.349
Token and
Token ID290
Feature activation-4.84e-01

Pos logit contributions
HUD+13.770
hooting+12.726
 confession+12.110
icide+11.740
boarding+11.739
Neg logit contributions
amins-15.697
-14.834
ysis-14.521
antam-14.171
 sidx-14.123
Token others
Token ID1854
Feature activation-1.87e+00

Pos logit contributions
hooting+3.768
HUD+3.764
advertisement+3.317
boarding+3.261
icide+3.169
Neg logit contributions
amins-4.426
-4.137
ysis-4.092
Thumbnail-3.965
-3.865
Token would
Token ID561
Feature activation-1.27e+00

Pos logit contributions
HUD+11.516
hooting+11.370
advertisement+9.658
 misled+9.587
boarding+9.552
Neg logit contributions
amins-16.120
-14.946
ysis-14.327
Thumbnail-14.213
antam-13.884
Token consider
Token ID2074
Feature activation-6.19e-01

Pos logit contributions
hooting+9.044
HUD+8.695
icide+7.901
advertisement+7.857
 confession+7.854
Neg logit contributions
amins-10.591
-9.712
ysis-9.677
Thumbnail-9.612
-9.392
Token compens
Token ID7144
Feature activation-9.86e-01

Pos logit contributions
hooting+4.772
HUD+4.671
advertisement+4.170
boarding+4.156
icide+3.986
Neg logit contributions
amins-5.622
-5.282
ysis-5.151
Thumbnail-5.046
-5.027
Token'd
Token ID1549
Feature activation-1.47e-01

Pos logit contributions
amins+0.640
ysis+0.600
+0.598
Thumbnail+0.558
+0.549
Neg logit contributions
hooting-0.807
HUD-0.802
advertisement-0.739
boarding-0.712
icide-0.699
Token be
Token ID307
Feature activation-3.01e-01

Pos logit contributions
hooting+1.288
HUD+1.272
advertisement+1.165
boarding+1.127
icide+1.106
Neg logit contributions
amins-1.221
ysis-1.152
-1.136
Thumbnail-1.085
-1.052
Token happy
Token ID3772
Feature activation-3.05e-01

Pos logit contributions
hooting+2.161
HUD+2.061
advertisement+1.848
boarding+1.822
horn+1.774
Neg logit contributions
amins-3.020
-2.838
ysis-2.829
Thumbnail-2.712
 sidx-2.696
Token to
Token ID284
Feature activation-7.34e-01

Pos logit contributions
hooting+2.505
HUD+2.461
advertisement+2.237
boarding+2.162
icide+2.116
Neg logit contributions
amins-2.711
ysis-2.567
-2.557
Thumbnail-2.418
-2.372
Token talk
Token ID1561
Feature activation-1.73e+00

Pos logit contributions
hooting+5.751
HUD+5.499
advertisement+4.966
boarding+4.891
icide+4.856
Neg logit contributions
amins-6.413
-5.987
ysis-5.954
Thumbnail-5.844
-5.690
Token more
Token ID517
Feature activation-2.04e+00

Pos logit contributions
hooting+9.809
icide+8.573
HUD+8.511
boarding+8.295
horn+8.071
Neg logit contributions
amins-15.737
-14.511
Thumbnail-14.198
ysis-14.057
 sidx-14.026
Token but
Token ID475
Feature activation-2.98e-01

Pos logit contributions
hooting+10.899
HUD+9.659
boarding+9.332
horn+9.069
icide+8.868
Neg logit contributions
amins-17.917
-16.817
Thumbnail-16.629
-16.352
ysis-16.199
Token I
Token ID314
Feature activation+4.54e-01

Pos logit contributions
HUD+2.226
hooting+2.224
advertisement+1.986
boarding+1.923
icide+1.853
Neg logit contributions
amins-2.818
ysis-2.691
-2.690
Thumbnail-2.575
-2.519
Token'd
Token ID1549
Feature activation+3.10e-01

Pos logit contributions
amins+3.128
ysis+2.967
+2.929
uty+2.722
+2.716
Neg logit contributions
hooting-4.476
HUD-4.462
advertisement-4.177
boarding-3.949
icide-3.878
Token rather
Token ID2138
Feature activation-8.45e-01

Pos logit contributions
amins+2.330
+2.190
ysis+2.188
+2.018
Thumbnail+2.016
Neg logit contributions
hooting-2.931
HUD-2.916
advertisement-2.697
boarding-2.575
icide-2.529
Token have
Token ID423
Feature activation-1.10e+00

Pos logit contributions
hooting+6.230
HUD+6.181
advertisement+5.594
boarding+5.348
horn+5.294
Neg logit contributions
amins-7.474
ysis-7.041
-6.912
Thumbnail-6.816
 sidx-6.628
Token just
Token ID655
Feature activation-8.97e-01

Pos logit contributions
hooting+5.659
HUD+5.635
advertisement+4.946
boarding+4.900
icide+4.785
Neg logit contributions
amins-6.861
-6.361
ysis-6.276
 sidx-6.075
Thumbnail-5.952
Token one
Token ID530
Feature activation-8.43e-01

Pos logit contributions
hooting+6.669
HUD+6.431
boarding+5.764
advertisement+5.669
icide+5.562
Neg logit contributions
amins-8.178
ysis-7.654
-7.636
 sidx-7.348
Thumbnail-7.144
Token of
Token ID286
Feature activation-4.49e-01

Pos logit contributions
hooting+5.865
HUD+5.814
advertisement+5.229
boarding+5.134
horn+4.939
Neg logit contributions
amins-8.277
-7.560
ysis-7.372
-7.098
isine-7.003
Token many
Token ID867
Feature activation-7.63e-01

Pos logit contributions
HUD+3.509
hooting+3.488
advertisement+3.124
boarding+3.021
icide+2.989
Neg logit contributions
amins-4.086
-3.865
ysis-3.807
Thumbnail-3.611
 sidx-3.557
Token companies
Token ID2706
Feature activation-1.84e+00

Pos logit contributions
hooting+6.017
HUD+6.009
advertisement+5.323
boarding+5.243
icide+5.051
Neg logit contributions
amins-6.714
-6.351
ysis-6.100
-5.794
Thumbnail-5.746
Token that
Token ID326
Feature activation-1.95e+00

Pos logit contributions
hooting+11.768
HUD+11.588
advertisement+9.940
 misled+9.907
boarding+9.823
Neg logit contributions
amins-15.510
-14.614
ysis-13.814
antam-13.434
Thumbnail-13.074
Token benefited
Token ID25050
Feature activation-1.47e+00

Pos logit contributions
HUD+12.302
hooting+12.252
 misled+11.371
icide+11.198
 confession+10.785
Neg logit contributions
amins-15.511
-14.022
ysis-13.998
Thumbnail-13.396
 sidx-12.915
Token from
Token ID422
Feature activation-5.64e-01

Pos logit contributions
HUD+8.400
hooting+8.255
icide+7.445
boarding+7.352
advertisement+7.230
Neg logit contributions
amins-14.031
-12.949
ysis-12.775
antam-12.136
-12.086
Token the
Token ID262
Feature activation-3.01e-01

Pos logit contributions
hooting+4.527
HUD+4.527
advertisement+4.140
boarding+4.076
icide+3.933
Neg logit contributions
amins-4.902
-4.583
ysis-4.492
Thumbnail-4.316
-4.246
Token use
Token ID779
Feature activation-3.55e-01

Pos logit contributions
hooting+2.564
HUD+2.532
advertisement+2.332
boarding+2.246
icide+2.217
Neg logit contributions
amins-2.542
-2.388
ysis-2.367
Thumbnail-2.248
-2.215
Token of
Token ID286
Feature activation-5.19e-02

Pos logit contributions
hooting+2.885
HUD+2.864
advertisement+2.620
boarding+2.515
icide+2.460
Neg logit contributions
amins-3.156
ysis-2.958
-2.951
Thumbnail-2.791
-2.743
Token way
Token ID835
Feature activation-1.22e-01

Pos logit contributions
amins+0.539
ysis+0.514
+0.513
Thumbnail+0.487
+0.481
Neg logit contributions
hooting-0.385
HUD-0.382
advertisement-0.342
boarding-0.324
icide-0.316
Token,
Token ID11
Feature activation-5.16e-01

Pos logit contributions
hooting+0.888
HUD+0.877
advertisement+0.787
boarding+0.751
icide+0.730
Neg logit contributions
amins-1.191
ysis-1.135
-1.132
Thumbnail-1.076
-1.059
Token they
Token ID484
Feature activation-7.38e-01

Pos logit contributions
HUD+4.105
hooting+4.036
advertisement+3.685
boarding+3.518
icide+3.439
Neg logit contributions
amins-4.510
ysis-4.324
-4.298
Thumbnail-4.153
 sidx-4.064
Token argue
Token ID7267
Feature activation-5.62e-01

Pos logit contributions
hooting+5.595
HUD+5.428
advertisement+4.895
boarding+4.726
icide+4.720
Neg logit contributions
amins-6.664
ysis-6.419
-6.241
Thumbnail-6.154
-5.852
Token,
Token ID11
Feature activation-5.57e-01

Pos logit contributions
hooting+3.738
HUD+3.717
advertisement+3.292
boarding+3.099
icide+3.011
Neg logit contributions
amins-5.724
ysis-5.473
-5.435
Thumbnail-5.209
-5.128
Token Williams
Token ID6484
Feature activation-1.88e+00

Pos logit contributions
HUD+4.458
hooting+4.379
advertisement+3.978
boarding+3.829
icide+3.736
Neg logit contributions
amins-4.811
-4.559
ysis-4.552
Thumbnail-4.418
 sidx-4.342
Token could
Token ID714
Feature activation-1.04e+00

Pos logit contributions
HUD+11.552
hooting+11.196
advertisement+10.072
might+9.808
boarding+9.771
Neg logit contributions
amins-14.680
ysis-14.529
-14.219
 sidx-14.138
Thumbnail-13.493
Token have
Token ID423
Feature activation-9.24e-01

Pos logit contributions
hooting+6.925
HUD+6.720
advertisement+5.909
icide+5.849
horn+5.702
Neg logit contributions
amins-9.759
ysis-9.277
-9.168
Thumbnail-8.900
-8.806
Token received
Token ID2722
Feature activation-8.81e-01

Pos logit contributions
hooting+6.386
HUD+6.175
advertisement+5.676
boarding+5.386
icide+5.328
Neg logit contributions
amins-8.757
ysis-8.132
-8.072
 sidx-7.894
uty-7.760
Token government
Token ID1230
Feature activation-4.97e-01

Pos logit contributions
HUD+6.944
hooting+6.789
advertisement+6.466
boarding+6.011
icide+5.889
Neg logit contributions
amins-7.359
-6.970
ysis-6.692
Thumbnail-6.688
 sidx-6.652
Token research
Token ID2267
Feature activation-2.09e-01

Pos logit contributions
HUD+3.929
hooting+3.872
advertisement+3.656
boarding+3.405
icide+3.299
Neg logit contributions
amins-4.457
-4.190
ysis-4.066
Thumbnail-3.981
 sidx-3.958
Token hoped
Token ID10719
Feature activation-7.12e-01

Pos logit contributions
hooting+1.116
HUD+1.092
advertisement+0.992
boarding+0.964
icide+0.945
Neg logit contributions
amins-1.232
-1.163
ysis-1.158
Thumbnail-1.098
-1.087
Token that
Token ID326
Feature activation-1.17e+00

Pos logit contributions
HUD+5.311
hooting+5.220
advertisement+4.658
boarding+4.533
icide+4.392
Neg logit contributions
amins-6.618
-6.099
ysis-6.063
Thumbnail-5.935
-5.853
Token Ike
Token ID34880
Feature activation-9.87e-01

Pos logit contributions
HUD+8.561
hooting+8.432
boarding+7.498
advertisement+7.387
 confession+7.233
Neg logit contributions
amins-10.242
-9.291
ysis-9.110
Thumbnail-9.098
-8.978
Tokena
Token ID64
Feature activation-2.21e+00

Pos logit contributions
HUD+3.771
hooting+3.759
advertisement+3.333
horn+2.884
bees+2.874
Neg logit contributions
amins-11.744
ysis-11.520
-11.452
-11.411
 submar-11.349
Token and
Token ID290
Feature activation-4.84e-01

Pos logit contributions
HUD+13.770
hooting+12.726
 confession+12.110
icide+11.740
boarding+11.739
Neg logit contributions
amins-15.697
-14.834
ysis-14.521
antam-14.171
 sidx-14.123
Token others
Token ID1854
Feature activation-1.87e+00

Pos logit contributions
hooting+3.768
HUD+3.764
advertisement+3.317
boarding+3.261
icide+3.169
Neg logit contributions
amins-4.426
-4.137
ysis-4.092
Thumbnail-3.965
-3.865
Token would
Token ID561
Feature activation-1.27e+00

Pos logit contributions
HUD+11.516
hooting+11.370
advertisement+9.658
 misled+9.587
boarding+9.552
Neg logit contributions
amins-16.120
-14.946
ysis-14.327
Thumbnail-14.213
antam-13.884
Token consider
Token ID2074
Feature activation-6.19e-01

Pos logit contributions
hooting+9.044
HUD+8.695
icide+7.901
advertisement+7.857
 confession+7.854
Neg logit contributions
amins-10.591
-9.712
ysis-9.677
Thumbnail-9.612
-9.392
Token compens
Token ID7144
Feature activation-9.86e-01

Pos logit contributions
hooting+4.772
HUD+4.671
advertisement+4.170
boarding+4.156
icide+3.986
Neg logit contributions
amins-5.622
-5.282
ysis-5.151
Thumbnail-5.046
-5.027
Tokenating
Token ID803
Feature activation-7.65e-01

Pos logit contributions
hooting+6.154
HUD+5.787
advertisement+5.061
boarding+5.018
icide+5.007
Neg logit contributions
-9.819
amins-9.680
ysis-9.346
Thumbnail-9.331
-9.297
Token former
Token ID1966
Feature activation-2.27e-01

Pos logit contributions
hooting+5.435
HUD+5.338
boarding+4.770
icide+4.651
advertisement+4.582
Neg logit contributions
amins-7.457
-6.811
Thumbnail-6.444
ysis-6.435
-6.291
Token.
Token ID764
Feature activation-5.55e-01

Pos logit contributions
HUD+2.189
hooting+2.162
advertisement+2.021
boarding+1.836
horn+1.803
Neg logit contributions
amins-3.363
ysis-3.188
-3.177
 submar-3.071
-3.047
Token MOR
Token ID35208
Feature activation-1.01e+00

Pos logit contributions
HUD+5.106
hooting+5.064
advertisement+4.669
boarding+4.475
icide+4.455
Neg logit contributions
amins-4.211
ysis-3.969
-3.962
Thumbnail-3.626
-3.618
TokenPH
Token ID11909
Feature activation-2.61e-01

Pos logit contributions
HUD+6.816
advertisement+5.987
hooting+5.973
horn+5.440
Phill+5.140
Neg logit contributions
amins-10.071
 submar-9.560
ysis-9.551
 sidx-9.434
��-9.357
Token_
Token ID62
Feature activation-9.59e-01

Pos logit contributions
HUD+1.820
hooting+1.746
advertisement+1.639
boarding+1.497
horn+1.460
Neg logit contributions
amins-2.665
ysis-2.519
-2.484
 submar-2.432
isine-2.373
TokenBL
Token ID9148
Feature activation-1.02e+00

Pos logit contributions
HUD+6.093
advertisement+4.919
hooting+4.651
horn+4.261
boarding+4.163
Neg logit contributions
amins-10.637
ysis-10.406
 submar-10.049
isine-9.874
-9.800
TokenACK
Token ID8120
Feature activation-1.86e+00

Pos logit contributions
HUD+7.598
hooting+6.403
advertisement+6.368
horn+5.673
boarding+5.287
Neg logit contributions
amins-9.994
ysis-9.499
 submar-9.454
-9.139
 sidx-9.057
TokenH
Token ID39
Feature activation-1.32e+00

Pos logit contributions
HUD+8.115
hooting+4.930
horn+4.397
advertisement+4.382
boarding+2.883
Neg logit contributions
 submar-22.547
amins-22.417
ysis-22.128
��-21.647
isine-21.613
TokenAT
Token ID1404
Feature activation-6.23e-01

Pos logit contributions
HUD+4.905
advertisement+4.220
hooting+3.336
horn+2.639
boarding+2.376
Neg logit contributions
amins-16.209
ysis-16.134
 submar-16.099
-15.753
��-15.671
Token,
Token ID837
Feature activation-3.54e-01

Pos logit contributions
HUD+2.402
hooting+2.264
advertisement+1.962
boarding+1.670
horn+1.604
Neg logit contributions
amins-8.194
ysis-7.859
-7.779
 submar-7.710
-7.561
Token rect
Token ID13621
Feature activation-1.48e-01

Pos logit contributions
hooting+1.933
HUD+1.930
advertisement+1.646
boarding+1.529
horn+1.490
Neg logit contributions
amins-4.089
-3.907
ysis-3.874
Thumbnail-3.695
-3.692
TokenK
Token ID42
Feature activation-1.22e-01

Pos logit contributions
HUD+0.989
hooting+0.950
advertisement+0.862
boarding+0.803
horn+0.781
Neg logit contributions
amins-1.557
ysis-1.486
-1.468
-1.414
-1.412
Token was
Token ID373
Feature activation+9.16e-01

Pos logit contributions
amins+2.103
ysis+1.994
+1.985
Thumbnail+1.873
+1.847
Neg logit contributions
hooting-2.013
HUD-2.000
advertisement-1.823
boarding-1.741
icide-1.706
Token iconic
Token ID14133
Feature activation+3.29e-01

Pos logit contributions
amins+7.498
ysis+7.068
+6.984
Thumbnail+6.730
+6.678
Neg logit contributions
hooting-7.525
HUD-7.457
advertisement-6.773
boarding-6.560
icide-6.360
Token (
Token ID357
Feature activation+2.48e-02

Pos logit contributions
amins+2.927
ysis+2.779
+2.762
Thumbnail+2.611
+2.574
Neg logit contributions
hooting-2.676
HUD-2.666
advertisement-2.408
boarding-2.301
icide-2.249
Tokenmore
Token ID3549
Feature activation-4.85e-01

Pos logit contributions
amins+0.219
ysis+0.209
+0.206
Thumbnail+0.193
+0.193
Neg logit contributions
HUD-0.204
hooting-0.204
advertisement-0.186
boarding-0.177
icide-0.172
Token on
Token ID319
Feature activation-6.42e-01

Pos logit contributions
HUD+4.180
hooting+4.112
advertisement+3.710
boarding+3.636
horn+3.554
Neg logit contributions
amins-3.928
-3.775
ysis-3.772
Thumbnail-3.486
endor-3.471
Token that
Token ID326
Feature activation-1.86e+00

Pos logit contributions
hooting+4.885
HUD+4.876
advertisement+4.593
boarding+4.194
icide+4.142
Neg logit contributions
amins-5.675
ysis-5.395
-5.337
-4.996
Thumbnail-4.985
Token later
Token ID1568
Feature activation-3.33e-01

Pos logit contributions
hooting+11.311
HUD+11.268
advertisement+10.462
horn+9.538
boarding+9.432
Neg logit contributions
amins-14.713
-13.870
ysis-13.868
isine-13.404
 sidx-13.390
Token),
Token ID828
Feature activation+1.75e-01

Pos logit contributions
hooting+2.858
HUD+2.796
advertisement+2.551
boarding+2.479
icide+2.430
Neg logit contributions
amins-2.762
-2.633
ysis-2.622
Thumbnail-2.486
-2.403
Token but
Token ID475
Feature activation+5.04e-01

Pos logit contributions
amins+1.702
ysis+1.621
+1.614
Thumbnail+1.531
+1.514
Neg logit contributions
hooting-1.282
HUD-1.270
advertisement-1.145
boarding-1.084
icide-1.058
Token he
Token ID339
Feature activation+4.12e-01

Pos logit contributions
amins+4.252
ysis+4.024
+4.006
Thumbnail+3.802
+3.754
Neg logit contributions
hooting-4.241
HUD-4.235
advertisement-3.853
boarding-3.692
icide-3.604
Token couldn
Token ID3521
Feature activation+4.51e-02

Pos logit contributions
amins+3.567
ysis+3.378
+3.373
Thumbnail+3.189
+3.136
Neg logit contributions
HUD-3.431
hooting-3.410
advertisement-3.127
boarding-2.956
icide-2.880
Token,
Token ID11
Feature activation-5.47e-01

Pos logit contributions
amins+0.580
ysis+0.552
+0.550
Thumbnail+0.520
+0.517
Neg logit contributions
hooting-0.448
HUD-0.443
advertisement-0.399
boarding-0.380
icide-0.370
Token 3
Token ID513
Feature activation-4.25e-03

Pos logit contributions
HUD+3.430
hooting+3.354
advertisement+2.947
boarding+2.796
icide+2.774
Neg logit contributions
amins-5.782
-5.488
ysis-5.449
Thumbnail-5.208
-5.179
Token),
Token ID828
Feature activation-8.01e-01

Pos logit contributions
hooting+0.038
HUD+0.038
advertisement+0.035
boarding+0.033
icide+0.033
Neg logit contributions
amins-0.035
ysis-0.033
-0.032
Thumbnail-0.030
-0.030
Token 0
Token ID657
Feature activation+1.20e-01

Pos logit contributions
HUD+5.739
hooting+5.592
advertisement+4.933
boarding+4.774
icide+4.724
Neg logit contributions
amins-7.542
-7.181
ysis-7.080
-6.663
-6.637
Token)
Token ID8
Feature activation-6.76e-01

Pos logit contributions
amins+1.040
ysis+0.983
+0.976
Thumbnail+0.922
+0.911
Neg logit contributions
hooting-1.019
HUD-1.008
advertisement-0.920
boarding-0.882
icide-0.860
Token black
Token ID2042
Feature activation-1.86e+00

Pos logit contributions
HUD+5.783
hooting+5.766
advertisement+5.206
boarding+5.090
icide+5.022
Neg logit contributions
amins-5.403
-5.179
ysis-4.966
-4.732
-4.704
Tokenhat
Token ID5183
Feature activation-8.83e-01

Pos logit contributions
HUD+13.308
hooting+13.087
horn+11.546
advertisement+11.225
boarding+11.211
Neg logit contributions
amins-14.126
-13.517
ysis-13.266
 submar-13.137
 sidx-13.034
Token =
Token ID796
Feature activation-2.15e-01

Pos logit contributions
HUD+5.291
hooting+5.062
advertisement+4.520
boarding+4.299
horn+4.077
Neg logit contributions
amins-9.331
-8.881
ysis-8.866
 submar-8.423
-8.418
Token c
Token ID269
Feature activation-2.45e-01

Pos logit contributions
hooting+1.644
HUD+1.640
advertisement+1.471
boarding+1.399
icide+1.373
Neg logit contributions
amins-2.018
ysis-1.908
-1.907
Thumbnail-1.798
-1.785
Tokenv
Token ID85
Feature activation+8.09e-01

Pos logit contributions
hooting+1.817
HUD+1.791
advertisement+1.621
boarding+1.548
horn+1.519
Neg logit contributions
amins-2.348
ysis-2.248
-2.238
-2.141
-2.135
Token2
Token ID17
Feature activation+5.97e-03

Pos logit contributions
amins+6.111
+5.976
ysis+5.701
Thumbnail+5.662
endor+5.476
Neg logit contributions
hooting-7.327
HUD-6.925
advertisement-6.318
icide-6.147
boarding-6.123
TokenED
Token ID1961
Feature activation-3.99e-01

Pos logit contributions
HUD+6.537
hooting+6.319
advertisement+5.606
boarding+5.412
icide+5.250
Neg logit contributions
amins-7.635
ysis-7.358
-7.127
Thumbnail-6.835
uty-6.724
Token
Token ID198
Feature activation-4.35e-01

Pos logit contributions
HUD+3.123
hooting+3.119
advertisement+2.776
boarding+2.679
icide+2.601
Neg logit contributions
amins-3.635
ysis-3.469
-3.454
Thumbnail-3.249
uty-3.188
Token
Token ID198
Feature activation-1.45e-01

Pos logit contributions
HUD+2.804
hooting+2.740
advertisement+2.558
boarding+2.360
horn+2.331
Neg logit contributions
amins-4.578
ysis-4.380
-4.275
 submar-4.257
-4.167
TokenIsrael
Token ID14040
Feature activation-3.61e-01

Pos logit contributions
HUD+1.222
hooting+1.181
advertisement+1.114
boarding+1.040
horn+1.012
Neg logit contributions
amins-1.279
ysis-1.219
-1.188
 sidx-1.134
-1.114
Token has
Token ID468
Feature activation-7.22e-01

Pos logit contributions
HUD+3.096
hooting+3.056
advertisement+2.760
icide+2.730
boarding+2.720
Neg logit contributions
amins-3.008
ysis-2.831
-2.814
Thumbnail-2.634
-2.609
Token long
Token ID890
Feature activation-1.85e+00

Pos logit contributions
HUD+5.503
hooting+5.424
advertisement+4.906
icide+4.825
boarding+4.783
Neg logit contributions
amins-6.539
ysis-6.029
-5.997
 sidx-5.683
Thumbnail-5.659
Token pursued
Token ID19189
Feature activation-7.60e-01

Pos logit contributions
hooting+10.885
HUD+10.568
boarding+9.936
icide+9.607
advertisement+9.170
Neg logit contributions
amins-15.968
ysis-14.613
-14.128
 sidx-13.760
Thumbnail-13.736
Token the
Token ID262
Feature activation-1.98e-01

Pos logit contributions
hooting+5.513
HUD+5.493
advertisement+4.960
icide+4.861
boarding+4.840
Neg logit contributions
amins-6.915
-6.589
ysis-6.461
Thumbnail-6.210
 sidx-6.131
Token physical
Token ID3518
Feature activation+2.36e-01

Pos logit contributions
hooting+1.627
HUD+1.619
advertisement+1.474
boarding+1.419
icide+1.407
Neg logit contributions
amins-1.729
-1.626
ysis-1.625
Thumbnail-1.538
-1.517
Token,
Token ID11
Feature activation-1.58e-01

Pos logit contributions
amins+2.201
ysis+2.103
+2.083
Thumbnail+1.972
+1.949
Neg logit contributions
hooting-1.826
HUD-1.813
advertisement-1.638
boarding-1.553
icide-1.515
Token political
Token ID1964
Feature activation-5.39e-01

Pos logit contributions
hooting+1.329
HUD+1.324
advertisement+1.213
boarding+1.157
icide+1.144
Neg logit contributions
amins-1.359
-1.278
ysis-1.278
Thumbnail-1.205
-1.192
Token Virginia
Token ID6025
Feature activation-1.77e-01

Pos logit contributions
HUD+4.203
hooting+4.191
advertisement+3.700
horn+3.556
boarding+3.490
Neg logit contributions
amins-7.742
-7.313
ysis-7.224
Thumbnail-7.207
isine-7.023
Token undergrad
Token ID43485
Feature activation+2.75e-01

Pos logit contributions
hooting+1.652
HUD+1.629
advertisement+1.486
boarding+1.452
icide+1.431
Neg logit contributions
amins-1.384
-1.311
ysis-1.289
Thumbnail-1.228
 sidx-1.194
Token who
Token ID508
Feature activation-2.40e-01

Pos logit contributions
amins+2.401
ysis+2.317
+2.288
Thumbnail+2.149
+2.140
Neg logit contributions
HUD-2.239
hooting-2.233
advertisement-2.047
boarding-1.924
horn-1.876
Token served
Token ID4983
Feature activation-3.05e-01

Pos logit contributions
hooting+1.900
HUD+1.850
advertisement+1.658
boarding+1.637
icide+1.612
Neg logit contributions
amins-2.221
-2.094
ysis-2.066
Thumbnail-1.972
-1.942
Token 18
Token ID1248
Feature activation-2.54e-01

Pos logit contributions
hooting+2.450
HUD+2.442
advertisement+2.224
boarding+2.157
icide+2.097
Neg logit contributions
amins-2.705
ysis-2.560
-2.559
Thumbnail-2.425
-2.406
Token months
Token ID1933
Feature activation-1.84e+00

Pos logit contributions
hooting+2.446
HUD+2.422
advertisement+2.252
boarding+2.212
icide+2.139
Neg logit contributions
amins-1.855
ysis-1.742
-1.741
Thumbnail-1.633
-1.594
Token behind
Token ID2157
Feature activation-5.53e-01

Pos logit contributions
hooting+9.577
HUD+9.109
boarding+8.933
advertisement+8.799
horn+8.472
Neg logit contributions
amins-16.938
-15.794
Thumbnail-15.736
ysis-15.594
-15.578
Token bars
Token ID9210
Feature activation-6.99e-01

Pos logit contributions
hooting+3.924
HUD+3.821
boarding+3.543
advertisement+3.469
icide+3.331
Neg logit contributions
amins-5.349
-5.070
ysis-4.942
Thumbnail-4.746
-4.740
Token in
Token ID287
Feature activation-1.07e-02

Pos logit contributions
hooting+5.015
HUD+4.688
advertisement+4.267
boarding+4.215
icide+4.088
Neg logit contributions
amins-6.867
-6.499
ysis-6.377
Thumbnail-6.095
-6.055
Token the
Token ID262
Feature activation+1.59e-01

Pos logit contributions
hooting+0.081
HUD+0.080
advertisement+0.072
boarding+0.069
icide+0.067
Neg logit contributions
amins-0.102
-0.097
ysis-0.096
Thumbnail-0.092
-0.091
Token her
Token ID607
Feature activation+5.96e-02

Pos logit contributions
amins+1.466
ysis+1.395
+1.387
Thumbnail+1.311
+1.294
Neg logit contributions
hooting-1.256
HUD-1.251
advertisement-1.132
boarding-1.075
icide-1.051
Token was
Token ID373
Feature activation-7.45e-01

Pos logit contributions
HUD+11.051
hooting+10.418
boarding+9.615
icide+9.606
 confession+9.542
Neg logit contributions
amins-13.525
-12.731
ysis-12.296
antam-11.717
 sidx-11.694
Token just
Token ID655
Feature activation-8.97e-01

Pos logit contributions
hooting+5.659
HUD+5.635
advertisement+4.946
boarding+4.900
icide+4.785
Neg logit contributions
amins-6.861
-6.361
ysis-6.276
 sidx-6.075
Thumbnail-5.952
Token one
Token ID530
Feature activation-8.43e-01

Pos logit contributions
hooting+6.669
HUD+6.431
boarding+5.764
advertisement+5.669
icide+5.562
Neg logit contributions
amins-8.178
ysis-7.654
-7.636
 sidx-7.348
Thumbnail-7.144
Token of
Token ID286
Feature activation-4.49e-01

Pos logit contributions
hooting+5.865
HUD+5.814
advertisement+5.229
boarding+5.134
horn+4.939
Neg logit contributions
amins-8.277
-7.560
ysis-7.372
-7.098
isine-7.003
Token many
Token ID867
Feature activation-7.63e-01

Pos logit contributions
HUD+3.509
hooting+3.488
advertisement+3.124
boarding+3.021
icide+2.989
Neg logit contributions
amins-4.086
-3.865
ysis-3.807
Thumbnail-3.611
 sidx-3.557
Token companies
Token ID2706
Feature activation-1.84e+00

Pos logit contributions
hooting+6.017
HUD+6.009
advertisement+5.323
boarding+5.243
icide+5.051
Neg logit contributions
amins-6.714
-6.351
ysis-6.100
-5.794
Thumbnail-5.746
Token that
Token ID326
Feature activation-1.95e+00

Pos logit contributions
hooting+11.768
HUD+11.588
advertisement+9.940
 misled+9.907
boarding+9.823
Neg logit contributions
amins-15.510
-14.614
ysis-13.814
antam-13.434
Thumbnail-13.074
Token benefited
Token ID25050
Feature activation-1.47e+00

Pos logit contributions
HUD+12.302
hooting+12.252
 misled+11.371
icide+11.198
 confession+10.785
Neg logit contributions
amins-15.511
-14.022
ysis-13.998
Thumbnail-13.396
 sidx-12.915
Token from
Token ID422
Feature activation-5.64e-01

Pos logit contributions
HUD+8.400
hooting+8.255
icide+7.445
boarding+7.352
advertisement+7.230
Neg logit contributions
amins-14.031
-12.949
ysis-12.775
antam-12.136
-12.086
Token the
Token ID262
Feature activation-3.01e-01

Pos logit contributions
hooting+4.527
HUD+4.527
advertisement+4.140
boarding+4.076
icide+3.933
Neg logit contributions
amins-4.902
-4.583
ysis-4.492
Thumbnail-4.316
-4.246
Token use
Token ID779
Feature activation-3.55e-01

Pos logit contributions
hooting+2.564
HUD+2.532
advertisement+2.332
boarding+2.246
icide+2.217
Neg logit contributions
amins-2.542
-2.388
ysis-2.367
Thumbnail-2.248
-2.215
Tokenoz
Token ID8590
Feature activation-6.24e-01

Pos logit contributions
hooting+5.773
HUD+5.620
advertisement+5.276
icide+5.195
horn+5.138
Neg logit contributions
amins-2.855
-2.624
ysis-2.518
Thumbnail-2.416
-2.396
Tokenilla
Token ID5049
Feature activation-5.04e-01

Pos logit contributions
hooting+4.112
HUD+3.912
advertisement+3.586
icide+3.481
boarding+3.437
Neg logit contributions
amins-6.175
ysis-6.013
-5.917
 sidx-5.784
-5.702
Token still
Token ID991
Feature activation-1.29e+00

Pos logit contributions
hooting+4.419
HUD+4.380
advertisement+3.998
boarding+3.847
icide+3.840
Neg logit contributions
amins-4.052
ysis-3.856
-3.809
-3.580
Thumbnail-3.524
Token has
Token ID468
Feature activation-7.78e-01

Pos logit contributions
hooting+9.762
HUD+8.907
icide+8.489
advertisement+8.430
boarding+8.422
Neg logit contributions
amins-10.587
ysis-10.208
-9.976
isine-9.478
Thumbnail-9.417
Token a
Token ID257
Feature activation-4.88e-01

Pos logit contributions
hooting+5.658
HUD+5.527
advertisement+5.114
boarding+4.921
icide+4.857
Neg logit contributions
amins-7.082
-6.716
ysis-6.649
Thumbnail-6.454
isine-6.378
Token long
Token ID890
Feature activation-1.83e+00

Pos logit contributions
hooting+4.033
HUD+3.970
advertisement+3.620
boarding+3.529
icide+3.408
Neg logit contributions
amins-4.228
-3.983
ysis-3.966
Thumbnail-3.754
 sidx-3.703
Token way
Token ID835
Feature activation-1.05e+00

Pos logit contributions
hooting+7.854
boarding+7.506
HUD+7.427
icide+6.341
horn+6.095
Neg logit contributions
ysis-18.163
amins-18.038
-17.892
 sidx-17.847
Thumbnail-17.111
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
hooting+7.045
HUD+6.579
boarding+6.121
advertisement+5.827
icide+5.762
Neg logit contributions
amins-10.098
-9.783
ysis-9.575
Thumbnail-9.193
 sidx-9.141
Token go
Token ID467
Feature activation-4.96e-01

Pos logit contributions
hooting+7.945
HUD+7.601
boarding+7.013
icide+6.975
advertisement+6.901
Neg logit contributions
amins-9.485
-9.145
ysis-8.746
-8.506
-8.366
Token with
Token ID351
Feature activation+8.47e-02

Pos logit contributions
hooting+3.692
HUD+3.571
advertisement+3.237
boarding+3.202
icide+3.084
Neg logit contributions
amins-4.672
-4.508
ysis-4.451
-4.212
Thumbnail-4.168
Token mobile
Token ID5175
Feature activation-2.48e-01

Pos logit contributions
amins+0.800
ysis+0.760
+0.757
Thumbnail+0.719
+0.710
Neg logit contributions
hooting-0.649
HUD-0.640
advertisement-0.582
boarding-0.554
icide-0.541
Token had
Token ID550
Feature activation-2.71e-01

Pos logit contributions
hooting+2.047
HUD+2.005
advertisement+1.806
boarding+1.761
icide+1.744
Neg logit contributions
amins-2.345
-2.220
ysis-2.216
Thumbnail-2.117
-2.063
Token to
Token ID284
Feature activation-4.28e-01

Pos logit contributions
hooting+2.092
HUD+2.066
advertisement+1.889
boarding+1.811
icide+1.790
Neg logit contributions
amins-2.518
-2.385
ysis-2.377
Thumbnail-2.279
-2.234
Token lie
Token ID6486
Feature activation-4.19e-01

Pos logit contributions
hooting+3.715
HUD+3.599
advertisement+3.363
boarding+3.263
icide+3.246
Neg logit contributions
amins-3.541
-3.355
ysis-3.300
Thumbnail-3.191
-3.145
Token,
Token ID11
Feature activation-3.11e-01

Pos logit contributions
hooting+3.468
HUD+3.354
advertisement+3.070
boarding+3.062
horn+2.992
Neg logit contributions
amins-3.714
-3.469
ysis-3.393
Thumbnail-3.332
-3.245
Token and
Token ID290
Feature activation-3.95e-01

Pos logit contributions
hooting+2.495
HUD+2.449
advertisement+2.263
boarding+2.178
icide+2.128
Neg logit contributions
amins-2.800
-2.651
ysis-2.614
Thumbnail-2.555
-2.461
Token tell
Token ID1560
Feature activation-1.81e+00

Pos logit contributions
hooting+3.181
HUD+3.124
advertisement+2.860
boarding+2.787
icide+2.698
Neg logit contributions
amins-3.502
-3.335
ysis-3.291
Thumbnail-3.207
 sidx-3.070
Token him
Token ID683
Feature activation-9.63e-01

Pos logit contributions
hooting+10.494
 confession+9.710
HUD+9.651
boarding+9.571
icide+9.228
Neg logit contributions
amins-15.371
Thumbnail-15.158
-14.715
 sidx-14.634
ysis-14.236
Token,
Token ID11
Feature activation-4.47e-01

Pos logit contributions
hooting+7.232
HUD+6.808
boarding+6.437
icide+6.294
 confession+6.225
Neg logit contributions
amins-8.263
-8.059
Thumbnail-7.865
ysis-7.665
 sidx-7.578
Token "
Token ID366
Feature activation-5.51e-01

Pos logit contributions
hooting+3.509
HUD+3.427
advertisement+3.194
icide+3.054
boarding+3.054
Neg logit contributions
amins-3.991
-3.810
ysis-3.710
Thumbnail-3.667
-3.546
TokenI
Token ID40
Feature activation-2.14e-01

Pos logit contributions
HUD+4.542
hooting+4.364
advertisement+4.173
boarding+3.919
horn+3.890
Neg logit contributions
amins-4.673
ysis-4.447
-4.389
 sidx-4.382
-4.157
Token'll
Token ID1183
Feature activation-6.79e-01

Pos logit contributions
hooting+1.971
HUD+1.966
advertisement+1.778
icide+1.738
boarding+1.735
Neg logit contributions
amins-1.681
ysis-1.574
-1.573
Thumbnail-1.497
-1.445
Token.
Token ID13
Feature activation+2.21e-01

Pos logit contributions
amins+0.095
ysis+0.090
+0.090
Thumbnail+0.085
+0.084
Neg logit contributions
hooting-0.094
HUD-0.093
advertisement-0.086
boarding-0.082
icide-0.080
Token Like
Token ID4525
Feature activation+1.14e-01

Pos logit contributions
amins+1.937
+1.832
ysis+1.832
Thumbnail+1.724
+1.701
Neg logit contributions
hooting-1.844
HUD-1.826
advertisement-1.662
boarding-1.591
icide-1.560
Token Apple
Token ID4196
Feature activation-1.01e+00

Pos logit contributions
amins+0.956
ysis+0.904
+0.898
Thumbnail+0.846
+0.833
Neg logit contributions
hooting-0.988
HUD-0.979
advertisement-0.897
boarding-0.859
icide-0.841
Token
Token ID447
Feature activation-2.19e-01

Pos logit contributions
hooting+7.156
HUD+7.155
advertisement+6.582
bees+6.331
boarding+6.272
Neg logit contributions
amins-8.911
ysis-8.640
-8.453
 sidx-8.114
Thumbnail-7.984
Token
Token ID247
Feature activation-1.03e+00

Pos logit contributions
HUD+2.119
hooting+2.089
advertisement+1.951
boarding+1.851
icide+1.813
Neg logit contributions
amins-1.622
ysis-1.517
-1.488
Thumbnail-1.407
 sidx-1.403
Tokens
Token ID82
Feature activation-1.80e+00

Pos logit contributions
hooting+5.684
HUD+5.638
advertisement+5.036
boarding+4.698
horn+4.656
Neg logit contributions
amins-10.818
ysis-10.459
-10.133
Thumbnail-9.963
 sidx-9.845
Token original
Token ID2656
Feature activation-7.52e-01

Pos logit contributions
hooting+12.361
HUD+11.780
advertisement+11.161
bees+10.673
 Lisp+10.534
Neg logit contributions
amins-13.206
ysis-13.080
-12.596
Thumbnail-11.872
uty-11.772
Token iPhone
Token ID7133
Feature activation-6.46e-01

Pos logit contributions
hooting+5.362
HUD+5.247
advertisement+4.798
boarding+4.559
icide+4.474
Neg logit contributions
amins-7.001
ysis-6.661
-6.583
Thumbnail-6.360
uty-6.240
Token and
Token ID290
Feature activation-3.07e-01

Pos logit contributions
hooting+4.190
HUD+4.118
advertisement+3.725
boarding+3.506
horn+3.383
Neg logit contributions
amins-6.589
-6.263
ysis-6.241
Thumbnail-5.942
uty-5.874
Token Tesla
Token ID11938
Feature activation-7.58e-01

Pos logit contributions
hooting+2.230
HUD+2.176
advertisement+1.985
boarding+1.869
icide+1.828
Neg logit contributions
amins-2.999
ysis-2.877
-2.823
Thumbnail-2.686
-2.668
Token Motors
Token ID19292
Feature activation-1.23e+00

Pos logit contributions
hooting+5.554
HUD+5.507
advertisement+4.934
boarding+4.681
horn+4.672
Neg logit contributions
amins-6.843
ysis-6.615
-6.449
Thumbnail-6.213
uty-6.115
Token The
Token ID383
Feature activation-3.47e-01

Pos logit contributions
HUD+1.204
hooting+1.177
advertisement+1.083
boarding+1.025
horn+1.002
Neg logit contributions
amins-1.293
ysis-1.215
-1.191
Thumbnail-1.129
-1.122
Token report
Token ID989
Feature activation+3.33e-01

Pos logit contributions
hooting+2.729
HUD+2.721
advertisement+2.431
boarding+2.390
icide+2.306
Neg logit contributions
amins-3.136
-2.950
ysis-2.929
Thumbnail-2.802
-2.762
Token concluded
Token ID8391
Feature activation+1.48e-01

Pos logit contributions
amins+2.792
ysis+2.661
+2.640
Thumbnail+2.494
+2.450
Neg logit contributions
hooting-2.844
HUD-2.843
advertisement-2.588
boarding-2.448
icide-2.401
Token that
Token ID326
Feature activation-5.71e-01

Pos logit contributions
amins+1.143
ysis+1.080
+1.073
Thumbnail+1.005
+0.987
Neg logit contributions
hooting-1.379
HUD-1.366
advertisement-1.262
boarding-1.206
icide-1.186
Token Ike
Token ID34880
Feature activation-1.04e+00

Pos logit contributions
HUD+4.509
hooting+4.481
advertisement+4.030
boarding+4.029
icide+3.871
Neg logit contributions
amins-5.150
-4.757
ysis-4.669
Thumbnail-4.550
-4.435
Tokena
Token ID64
Feature activation-1.77e+00

Pos logit contributions
hooting+3.978
HUD+3.974
advertisement+3.500
icide+3.178
horn+3.154
Neg logit contributions
amins-12.284
ysis-12.004
-11.976
-11.906
-11.762
Token managers
Token ID11663
Feature activation-1.39e+00

Pos logit contributions
HUD+11.958
hooting+11.186
icide+10.697
 misled+10.535
boarding+10.512
Neg logit contributions
amins-14.143
-13.452
ysis-12.736
 sidx-12.128
ablishment-12.065
Token were
Token ID547
Feature activation-7.43e-01

Pos logit contributions
hooting+9.376
HUD+9.087
icide+8.220
 misled+8.189
boarding+8.072
Neg logit contributions
amins-12.555
-11.743
ysis-11.415
Thumbnail-11.299
 sidx-10.565
Token aware
Token ID3910
Feature activation-5.50e-01

Pos logit contributions
hooting+5.364
HUD+5.363
advertisement+4.793
boarding+4.686
icide+4.566
Neg logit contributions
amins-7.079
-6.696
ysis-6.515
Thumbnail-6.197
 sidx-6.143
Token of
Token ID286
Feature activation-2.75e-01

Pos logit contributions
HUD+4.252
hooting+4.252
advertisement+3.840
boarding+3.732
icide+3.647
Neg logit contributions
amins-5.038
-4.719
ysis-4.657
Thumbnail-4.452
-4.425
Token the
Token ID262
Feature activation-1.00e-01

Pos logit contributions
hooting+2.213
HUD+2.194
advertisement+2.002
boarding+1.942
icide+1.880
Neg logit contributions
amins-2.482
-2.337
ysis-2.297
Thumbnail-2.210
-2.176
Token {
Token ID1391
Feature activation-1.32e+00

Pos logit contributions
hooting+0.988
HUD+0.982
advertisement+0.905
boarding+0.860
icide+0.848
Neg logit contributions
amins-1.027
ysis-0.968
-0.963
Thumbnail-0.904
-0.898
Tokenwhite
Token ID11186
Feature activation-6.61e-01

Pos logit contributions
hooting+7.252
HUD+7.222
advertisement+6.462
boarding+6.378
icide+6.156
Neg logit contributions
amins-13.296
ysis-12.711
-12.462
 sidx-12.233
-12.048
Token}
Token ID92
Feature activation-3.89e-01

Pos logit contributions
hooting+4.109
HUD+4.061
advertisement+3.604
boarding+3.471
icide+3.377
Neg logit contributions
amins-6.993
ysis-6.777
-6.591
Thumbnail-6.315
-6.202
Token at
Token ID379
Feature activation-6.93e-01

Pos logit contributions
hooting+3.157
HUD+3.125
advertisement+2.932
boarding+2.782
icide+2.730
Neg logit contributions
amins-3.382
-3.210
ysis-3.207
Thumbnail-3.033
-2.980
Token least
Token ID1551
Feature activation-1.29e+00

Pos logit contributions
hooting+3.880
HUD+3.678
advertisement+3.268
boarding+3.193
horn+3.142
Neg logit contributions
amins-7.482
-7.331
ysis-6.961
Thumbnail-6.895
-6.880
Token one
Token ID530
Feature activation-1.77e+00

Pos logit contributions
hooting+6.318
HUD+6.215
advertisement+5.662
boarding+5.307
icide+5.230
Neg logit contributions
amins-13.458
-13.066
ysis-12.743
Thumbnail-12.314
-12.211
Token blank
Token ID9178
Feature activation-3.54e-01

Pos logit contributions
hooting+9.744
HUD+9.733
advertisement+9.464
boarding+8.630
icide+8.511
Neg logit contributions
amins-16.510
-15.013
ysis-14.805
isine-14.269
-13.944
Token character
Token ID2095
Feature activation-5.54e-01

Pos logit contributions
hooting+2.911
HUD+2.837
advertisement+2.695
boarding+2.508
icide+2.498
Neg logit contributions
amins-3.137
ysis-2.927
-2.854
Thumbnail-2.733
 sidx-2.684
Token (<
Token ID38155
Feature activation-8.78e-01

Pos logit contributions
hooting+4.181
HUD+4.034
advertisement+3.803
icide+3.613
boarding+3.557
Neg logit contributions
amins-5.117
-4.839
ysis-4.781
-4.560
Thumbnail-4.544
TokenSpace
Token ID14106
Feature activation-4.84e-01

Pos logit contributions
HUD+6.189
hooting+5.910
advertisement+5.609
boarding+5.168
icide+5.158
Neg logit contributions
amins-8.312
ysis-7.918
-7.721
 sidx-7.525
isine-7.267
Token>
Token ID29
Feature activation-7.36e-01

Pos logit contributions
HUD+3.580
hooting+3.525
advertisement+3.269
horn+3.059
icide+3.008
Neg logit contributions
amins-4.518
ysis-4.354
-4.271
 submar-4.077
Thumbnail-4.077
Token you
Token ID345
Feature activation+3.49e-01

Pos logit contributions
amins+2.722
ysis+2.556
+2.528
Thumbnail+2.363
+2.340
Neg logit contributions
hooting-3.492
HUD-3.477
advertisement-3.178
boarding-3.073
icide-3.019
Token?
Token ID30
Feature activation-4.67e-01

Pos logit contributions
amins+2.438
ysis+2.291
+2.265
Thumbnail+2.110
+2.067
Neg logit contributions
hooting-3.488
HUD-3.483
advertisement-3.207
boarding-3.083
icide-3.036
Token While
Token ID2893
Feature activation-7.66e-01

Pos logit contributions
HUD+3.655
hooting+3.598
advertisement+3.365
boarding+3.131
horn+3.110
Neg logit contributions
amins-4.219
ysis-4.022
-3.998
isine-3.759
-3.752
Token AT
Token ID5161
Feature activation-8.74e-01

Pos logit contributions
hooting+5.504
HUD+5.458
advertisement+5.075
boarding+4.814
horn+4.636
Neg logit contributions
amins-6.990
-6.752
ysis-6.659
Thumbnail-6.296
-6.223
Token&
Token ID5
Feature activation-8.01e-01

Pos logit contributions
HUD+5.531
hooting+5.302
advertisement+4.903
boarding+4.504
horn+4.421
Neg logit contributions
amins-8.875
ysis-8.486
-8.455
 submar-8.306
isine-8.186
TokenT
Token ID51
Feature activation-1.76e+00

Pos logit contributions
HUD+4.517
hooting+3.871
advertisement+3.752
horn+3.274
boarding+3.244
Neg logit contributions
amins-9.126
ysis-8.767
 submar-8.661
-8.528
isine-8.468
Token's
Token ID338
Feature activation-7.99e-01

Pos logit contributions
HUD+11.498
hooting+11.167
advertisement+10.414
icide+10.304
boarding+10.133
Neg logit contributions
amins-13.490
-13.176
ysis-13.051
isine-12.460
-12.445
Token powerhouse
Token ID34886
Feature activation-4.76e-01

Pos logit contributions
hooting+6.233
HUD+6.228
advertisement+5.895
boarding+5.570
icide+5.439
Neg logit contributions
amins-6.772
-6.454
ysis-6.352
Thumbnail-6.120
-5.965
Token FISA
Token ID44073
Feature activation-3.87e-02

Pos logit contributions
HUD+3.640
hooting+3.634
advertisement+3.407
boarding+3.200
icide+3.112
Neg logit contributions
amins-4.325
ysis-4.119
-4.106
Thumbnail-3.904
-3.845
Token lobbyist
Token ID35196
Feature activation-5.77e-01

Pos logit contributions
hooting+0.298
HUD+0.295
advertisement+0.268
boarding+0.255
icide+0.249
Neg logit contributions
amins-0.364
ysis-0.345
-0.343
Thumbnail-0.325
-0.319
Token Charlie
Token ID11526
Feature activation+1.88e-01

Pos logit contributions
hooting+4.571
HUD+4.551
advertisement+4.174
boarding+4.083
icide+3.965
Neg logit contributions
amins-4.999
ysis-4.785
-4.663
Thumbnail-4.520
 sidx-4.404
Token heat
Token ID4894
Feature activation-7.32e-02

Pos logit contributions
hooting+0.083
HUD+0.082
advertisement+0.072
boarding+0.068
icide+0.067
Neg logit contributions
amins-0.143
-0.136
ysis-0.136
Thumbnail-0.130
-0.128
Token to
Token ID284
Feature activation-2.46e-01

Pos logit contributions
hooting+0.592
HUD+0.582
advertisement+0.527
boarding+0.508
icide+0.498
Neg logit contributions
amins-0.661
-0.626
ysis-0.625
Thumbnail-0.594
-0.583
Token low
Token ID1877
Feature activation-6.17e-03

Pos logit contributions
hooting+1.777
HUD+1.736
advertisement+1.555
boarding+1.487
icide+1.457
Neg logit contributions
amins-2.429
ysis-2.301
-2.298
Thumbnail-2.203
uty-2.147
Token and
Token ID290
Feature activation-7.32e-02

Pos logit contributions
hooting+0.048
HUD+0.047
advertisement+0.043
boarding+0.041
icide+0.040
Neg logit contributions
amins-0.058
ysis-0.055
-0.055
Thumbnail-0.052
-0.051
Token cook
Token ID4255
Feature activation-8.26e-01

Pos logit contributions
hooting+0.670
HUD+0.660
advertisement+0.607
boarding+0.584
icide+0.577
Neg logit contributions
amins-0.582
-0.547
ysis-0.546
Thumbnail-0.512
-0.499
Token f
Token ID277
Feature activation-1.76e+00

Pos logit contributions
hooting+6.060
HUD+5.808
advertisement+5.373
boarding+5.191
icide+5.043
Neg logit contributions
amins-7.594
-7.266
ysis-7.261
Thumbnail-6.877
uty-6.713
Tokenrit
Token ID799
Feature activation-3.49e-01

Pos logit contributions
hooting+7.734
HUD+7.400
advertisement+6.619
icide+6.517
boarding+6.249
Neg logit contributions
-17.381
ysis-16.795
 submar-16.410
-16.393
Thumbnail-16.145
Tokenters
Token ID1010
Feature activation-3.62e-01

Pos logit contributions
HUD+2.602
hooting+2.594
advertisement+2.317
boarding+2.253
icide+2.185
Neg logit contributions
amins-3.231
ysis-3.138
-3.109
-2.977
-2.973
Token on
Token ID319
Feature activation-5.73e-01

Pos logit contributions
hooting+2.862
HUD+2.779
advertisement+2.525
boarding+2.454
icide+2.377
Neg logit contributions
amins-3.318
-3.157
ysis-3.141
Thumbnail-3.020
-2.950
Token each
Token ID1123
Feature activation-8.33e-01

Pos logit contributions
hooting+4.673
HUD+4.621
boarding+4.171
advertisement+4.128
icide+4.038
Neg logit contributions
amins-4.977
-4.631
ysis-4.532
Thumbnail-4.438
 sidx-4.221
Token side
Token ID1735
Feature activation-1.18e-01

Pos logit contributions
hooting+6.431
HUD+5.957
advertisement+5.744
boarding+5.516
icide+5.319
Neg logit contributions
amins-7.584
-6.894
ysis-6.859
Thumbnail-6.523
-6.384
Token possible
Token ID1744
Feature activation-5.77e-01

Pos logit contributions
hooting+4.591
HUD+4.502
advertisement+4.094
boarding+3.883
horn+3.824
Neg logit contributions
amins-5.441
ysis-5.256
-5.052
Thumbnail-4.792
-4.789
Token that
Token ID326
Feature activation-4.87e-01

Pos logit contributions
HUD+4.647
hooting+4.622
advertisement+4.219
boarding+3.965
icide+3.895
Neg logit contributions
amins-4.971
ysis-4.699
-4.613
Thumbnail-4.452
-4.397
Token mobile
Token ID5175
Feature activation-4.59e-01

Pos logit contributions
HUD+3.699
hooting+3.698
advertisement+3.371
boarding+3.142
horn+3.075
Neg logit contributions
amins-4.487
ysis-4.208
-4.155
Thumbnail-4.044
-3.958
Token-
Token ID12
Feature activation-4.01e-01

Pos logit contributions
hooting+3.739
HUD+3.709
advertisement+3.429
boarding+3.329
icide+3.231
Neg logit contributions
amins-3.971
ysis-3.698
-3.695
Thumbnail-3.499
-3.494
Tokendevice
Token ID25202
Feature activation-1.73e-01

Pos logit contributions
hooting+3.020
HUD+3.017
advertisement+2.797
boarding+2.667
horn+2.577
Neg logit contributions
amins-3.812
ysis-3.609
-3.561
 sidx-3.387
-3.371
Token makers
Token ID14429
Feature activation-1.74e+00

Pos logit contributions
hooting+1.472
HUD+1.458
advertisement+1.346
boarding+1.292
icide+1.262
Neg logit contributions
amins-1.475
-1.390
ysis-1.380
Thumbnail-1.305
-1.295
Token,
Token ID11
Feature activation-4.34e-01

Pos logit contributions
hooting+12.090
HUD+11.468
advertisement+10.446
horn+9.988
 misled+9.889
Neg logit contributions
amins-13.897
ysis-12.978
-12.599
isine-12.429
Thumbnail-12.138
Token some
Token ID617
Feature activation-6.18e-01

Pos logit contributions
hooting+3.591
HUD+3.556
advertisement+3.270
boarding+3.090
horn+3.027
Neg logit contributions
amins-3.770
-3.545
ysis-3.506
-3.327
Thumbnail-3.307
Token of
Token ID286
Feature activation+3.49e-01

Pos logit contributions
hooting+4.743
HUD+4.653
advertisement+4.238
boarding+4.002
horn+3.926
Neg logit contributions
amins-5.671
ysis-5.287
-5.227
-5.018
Thumbnail-5.000
Token which
Token ID543
Feature activation-1.19e+00

Pos logit contributions
amins+2.054
+1.908
ysis+1.899
Thumbnail+1.730
+1.686
Neg logit contributions
hooting-3.863
HUD-3.839
advertisement-3.564
boarding-3.468
icide-3.419
Token are
Token ID389
Feature activation-1.05e+00

Pos logit contributions
hooting+9.112
HUD+8.936
advertisement+8.052
horn+7.842
icide+7.680
Neg logit contributions
amins-9.770
ysis-9.041
-8.829
Thumbnail-8.515
isine-8.482
TokenI
Token ID40
Feature activation+8.46e-02

Pos logit contributions
HUD+0.624
hooting+0.598
advertisement+0.561
boarding+0.517
horn+0.504
Neg logit contributions
amins-0.816
ysis-0.780
-0.762
 sidx-0.734
-0.723
Token'd
Token ID1549
Feature activation-1.47e-01

Pos logit contributions
amins+0.640
ysis+0.600
+0.598
Thumbnail+0.558
+0.549
Neg logit contributions
hooting-0.807
HUD-0.802
advertisement-0.739
boarding-0.712
icide-0.699
Token be
Token ID307
Feature activation-3.01e-01

Pos logit contributions
hooting+1.288
HUD+1.272
advertisement+1.165
boarding+1.127
icide+1.106
Neg logit contributions
amins-1.221
ysis-1.152
-1.136
Thumbnail-1.085
-1.052
Token happy
Token ID3772
Feature activation-3.05e-01

Pos logit contributions
hooting+2.161
HUD+2.061
advertisement+1.848
boarding+1.822
horn+1.774
Neg logit contributions
amins-3.020
-2.838
ysis-2.829
Thumbnail-2.712
 sidx-2.696
Token to
Token ID284
Feature activation-7.34e-01

Pos logit contributions
hooting+2.505
HUD+2.461
advertisement+2.237
boarding+2.162
icide+2.116
Neg logit contributions
amins-2.711
ysis-2.567
-2.557
Thumbnail-2.418
-2.372
Token talk
Token ID1561
Feature activation-1.73e+00

Pos logit contributions
hooting+5.751
HUD+5.499
advertisement+4.966
boarding+4.891
icide+4.856
Neg logit contributions
amins-6.413
-5.987
ysis-5.954
Thumbnail-5.844
-5.690
Token more
Token ID517
Feature activation-2.04e+00

Pos logit contributions
hooting+9.809
icide+8.573
HUD+8.511
boarding+8.295
horn+8.071
Neg logit contributions
amins-15.737
-14.511
Thumbnail-14.198
ysis-14.057
 sidx-14.026
Token but
Token ID475
Feature activation-2.98e-01

Pos logit contributions
hooting+10.899
HUD+9.659
boarding+9.332
horn+9.069
icide+8.868
Neg logit contributions
amins-17.917
-16.817
Thumbnail-16.629
-16.352
ysis-16.199
Token I
Token ID314
Feature activation+4.54e-01

Pos logit contributions
HUD+2.226
hooting+2.224
advertisement+1.986
boarding+1.923
icide+1.853
Neg logit contributions
amins-2.818
ysis-2.691
-2.690
Thumbnail-2.575
-2.519
Token'd
Token ID1549
Feature activation+3.10e-01

Pos logit contributions
amins+3.128
ysis+2.967
+2.929
uty+2.722
+2.716
Neg logit contributions
hooting-4.476
HUD-4.462
advertisement-4.177
boarding-3.949
icide-3.878
Token rather
Token ID2138
Feature activation-8.45e-01

Pos logit contributions
amins+2.330
+2.190
ysis+2.188
+2.018
Thumbnail+2.016
Neg logit contributions
hooting-2.931
HUD-2.916
advertisement-2.697
boarding-2.575
icide-2.529
Token.
Token ID13
Feature activation+1.77e-01

Pos logit contributions
amins+4.262
ysis+4.031
+3.999
Thumbnail+3.729
+3.685
Neg logit contributions
HUD-4.530
hooting-4.469
advertisement-4.059
boarding-3.855
icide-3.833
Token Much
Token ID13111
Feature activation-1.14e-01

Pos logit contributions
amins+1.573
ysis+1.492
+1.488
Thumbnail+1.402
+1.384
Neg logit contributions
hooting-1.450
HUD-1.435
advertisement-1.304
boarding-1.248
icide-1.222
Token of
Token ID286
Feature activation+2.94e-02

Pos logit contributions
hooting+0.969
HUD+0.966
advertisement+0.884
boarding+0.845
icide+0.824
Neg logit contributions
amins-0.980
ysis-0.924
-0.918
Thumbnail-0.870
-0.861
Token the
Token ID262
Feature activation+1.03e-01

Pos logit contributions
amins+0.258
ysis+0.245
+0.244
Thumbnail+0.231
+0.227
Neg logit contributions
hooting-0.244
HUD-0.242
advertisement-0.221
boarding-0.211
icide-0.206
Token first
Token ID717
Feature activation+1.21e+00

Pos logit contributions
amins+0.856
ysis+0.808
+0.804
Thumbnail+0.757
+0.746
Neg logit contributions
hooting-0.904
HUD-0.897
advertisement-0.822
boarding-0.787
icide-0.771
Token-
Token ID12
Feature activation+9.85e-01

Pos logit contributions
amins+9.178
ysis+8.722
+8.496
 ever+8.254
 submar+7.857
Neg logit contributions
hooting-10.073
HUD-9.938
advertisement-9.095
boarding-8.605
icide-8.505
Tokenfloor
Token ID28300
Feature activation-1.19e-01

Pos logit contributions
amins+9.521
+9.108
ysis+8.881
uty+8.556
endor+8.531
Neg logit contributions
hooting-6.368
HUD-6.282
advertisement-5.561
icide-5.209
boarding-5.206
Token lab
Token ID2248
Feature activation+2.09e-01

Pos logit contributions
hooting+1.021
HUD+1.009
advertisement+0.930
boarding+0.890
icide+0.866
Neg logit contributions
amins-1.022
-0.953
ysis-0.949
Thumbnail-0.905
-0.891
Token space
Token ID2272
Feature activation-4.41e-01

Pos logit contributions
amins+1.693
ysis+1.598
+1.590
Thumbnail+1.487
+1.470
Neg logit contributions
hooting-1.879
HUD-1.867
advertisement-1.711
boarding-1.640
icide-1.609
Token is
Token ID318
Feature activation-3.23e-01

Pos logit contributions
hooting+3.804
HUD+3.758
advertisement+3.480
boarding+3.322
horn+3.258
Neg logit contributions
amins-3.673
-3.435
ysis-3.425
Thumbnail-3.253
-3.190
Token under
Token ID739
Feature activation+1.10e-01

Pos logit contributions
HUD+2.621
hooting+2.608
advertisement+2.375
boarding+2.260
icide+2.218
Neg logit contributions
amins-2.894
ysis-2.687
-2.685
Thumbnail-2.555
uty-2.506
Token prevent
Token ID2948
Feature activation+6.53e-01

Pos logit contributions
amins+3.694
ysis+3.492
+3.465
Thumbnail+3.183
+3.150
Neg logit contributions
HUD-4.956
hooting-4.937
advertisement-4.580
boarding-4.393
horn-4.270
Token their
Token ID511
Feature activation+5.25e-01

Pos logit contributions
amins+5.022
ysis+4.828
+4.689
Thumbnail+4.363
 submar+4.363
Neg logit contributions
hooting-5.897
HUD-5.856
advertisement-5.400
boarding-5.114
horn-5.004
Token production
Token ID3227
Feature activation+5.38e-01

Pos logit contributions
amins+4.136
ysis+3.939
+3.887
Thumbnail+3.631
+3.612
Neg logit contributions
hooting-4.720
HUD-4.680
advertisement-4.315
boarding-4.102
horn-4.031
Token and
Token ID290
Feature activation+5.44e-01

Pos logit contributions
amins+4.573
ysis+4.380
+4.278
Thumbnail+3.987
+3.987
Neg logit contributions
HUD-4.549
hooting-4.541
advertisement-4.125
boarding-3.875
icide-3.805
Token stockp
Token ID29534
Feature activation+5.66e-01

Pos logit contributions
amins+4.061
ysis+3.857
+3.779
Thumbnail+3.520
+3.511
Neg logit contributions
hooting-5.087
HUD-5.051
advertisement-4.665
boarding-4.442
horn-4.374
Tokeniling
Token ID4386
Feature activation+9.77e-01

Pos logit contributions
amins+4.191
ysis+3.929
+3.790
uty+3.621
endor+3.578
Neg logit contributions
HUD-5.486
hooting-5.258
advertisement-4.957
boarding-4.787
horn-4.586
Token and
Token ID290
Feature activation+7.44e-01

Pos logit contributions
amins+7.395
ysis+7.013
+6.845
 ever+6.411
uty+6.272
Neg logit contributions
HUD-8.792
hooting-8.729
advertisement-7.870
boarding-7.454
icide-7.326
Token abolish
Token ID35531
Feature activation+1.04e+00

Pos logit contributions
amins+5.854
ysis+5.615
+5.460
+5.091
+5.080
Neg logit contributions
hooting-6.516
HUD-6.506
advertisement-5.958
boarding-5.625
horn-5.531
Token them
Token ID606
Feature activation+4.18e-01

Pos logit contributions
amins+7.485
ysis+7.231
+6.945
+6.513
+6.485
Neg logit contributions
HUD-9.519
hooting-9.468
advertisement-8.773
boarding-8.219
horn-8.098
Token completely
Token ID3190
Feature activation+4.69e-01

Pos logit contributions
amins+3.420
ysis+3.237
+3.199
Thumbnail+2.998
+2.966
Neg logit contributions
hooting-3.688
HUD-3.685
advertisement-3.373
boarding-3.207
icide-3.135
Token once
Token ID1752
Feature activation+3.58e-01

Pos logit contributions
amins+3.906
ysis+3.699
+3.646
Thumbnail+3.419
+3.393
Neg logit contributions
hooting-4.049
HUD-4.029
advertisement-3.691
boarding-3.484
icide-3.405
Token description
Token ID6764
Feature activation-1.05e-01

Pos logit contributions
amins+1.025
ysis+0.967
+0.963
Thumbnail+0.908
+0.894
Neg logit contributions
hooting-1.042
HUD-1.034
advertisement-0.947
boarding-0.906
icide-0.888
Token of
Token ID286
Feature activation-1.17e-01

Pos logit contributions
hooting+0.866
HUD+0.852
advertisement+0.793
boarding+0.752
horn+0.732
Neg logit contributions
amins-0.928
ysis-0.872
-0.866
Thumbnail-0.823
-0.809
Token them
Token ID606
Feature activation+5.70e-01

Pos logit contributions
hooting+0.946
HUD+0.934
advertisement+0.857
boarding+0.820
icide+0.801
Neg logit contributions
amins-1.055
ysis-0.999
-0.993
Thumbnail-0.946
-0.924
Token holding
Token ID4769
Feature activation+3.93e-01

Pos logit contributions
amins+4.685
+4.463
ysis+4.461
+4.140
Thumbnail+4.130
Neg logit contributions
HUD-4.861
hooting-4.817
advertisement-4.332
boarding-4.148
icide-4.127
Token each
Token ID1123
Feature activation+9.48e-02

Pos logit contributions
amins+2.928
ysis+2.824
+2.778
+2.565
Thumbnail+2.560
Neg logit contributions
HUD-3.688
hooting-3.679
advertisement-3.380
boarding-3.215
icide-3.169
Token other
Token ID584
Feature activation+1.12e+00

Pos logit contributions
amins+0.721
ysis+0.685
+0.682
+0.629
+0.629
Neg logit contributions
hooting-0.892
HUD-0.892
advertisement-0.812
boarding-0.783
icide-0.768
Token and
Token ID290
Feature activation+1.10e-01

Pos logit contributions
ysis+7.992
amins+7.991
+7.669
 ever+7.505
+7.208
Neg logit contributions
HUD-9.808
hooting-9.325
advertisement-8.625
icide-8.050
boarding-7.931
Token shaking
Token ID17275
Feature activation+6.82e-01

Pos logit contributions
amins+1.000
ysis+0.949
+0.945
Thumbnail+0.893
+0.882
Neg logit contributions
hooting-0.884
HUD-0.878
advertisement-0.797
boarding-0.759
icide-0.743
Token
Token ID564
Feature activation+4.48e-01

Pos logit contributions
amins+5.132
+5.023
ysis+5.017
+4.633
Thumbnail+4.600
Neg logit contributions
HUD-6.083
hooting-5.945
advertisement-5.508
icide-5.206
boarding-5.161
Token
Token ID250
Feature activation+2.93e-01

Pos logit contributions
amins+2.664
ysis+2.515
+2.510
+2.443
+2.440
Neg logit contributions
hooting-4.907
HUD-4.828
advertisement-4.482
boarding-4.394
icide-4.333
Tokenwith
Token ID4480
Feature activation+5.22e-01

Pos logit contributions
amins+2.660
ysis+2.531
+2.520
Thumbnail+2.374
+2.352
Neg logit contributions
hooting-2.335
HUD-2.320
advertisement-2.100
boarding-2.009
icide-1.963
Token If
Token ID1002
Feature activation+5.29e-01

Pos logit contributions
amins+2.238
ysis+2.112
+2.105
Thumbnail+1.976
+1.948
Neg logit contributions
hooting-2.398
HUD-2.364
advertisement-2.169
boarding-2.080
icide-2.042
Token that
Token ID326
Feature activation+5.80e-01

Pos logit contributions
amins+4.123
ysis+3.963
+3.854
Thumbnail+3.633
+3.624
Neg logit contributions
hooting-4.734
HUD-4.657
advertisement-4.331
boarding-4.087
icide-4.057
Token is
Token ID318
Feature activation+5.16e-01

Pos logit contributions
amins+4.270
ysis+4.077
+3.979
Thumbnail+3.759
+3.696
Neg logit contributions
HUD-5.411
hooting-5.365
advertisement-4.868
boarding-4.659
icide-4.613
Token what
Token ID644
Feature activation-3.99e-02

Pos logit contributions
amins+4.050
ysis+3.844
+3.816
+3.586
Thumbnail+3.583
Neg logit contributions
hooting-4.585
HUD-4.555
advertisement-4.212
boarding-3.984
icide-3.945
Token your
Token ID534
Feature activation+3.48e-01

Pos logit contributions
hooting+0.349
HUD+0.347
advertisement+0.317
boarding+0.306
icide+0.299
Neg logit contributions
amins-0.333
ysis-0.315
-0.314
Thumbnail-0.295
-0.290
Token aim
Token ID4031
Feature activation+1.35e+00

Pos logit contributions
amins+2.770
ysis+2.629
+2.608
Thumbnail+2.439
+2.415
Neg logit contributions
hooting-3.144
HUD-3.115
advertisement-2.858
boarding-2.733
icide-2.691
Token is
Token ID318
Feature activation+1.03e+00

Pos logit contributions
amins+6.657
ysis+6.106
+6.084
 ever+5.904
uty+5.651
Neg logit contributions
HUD-14.184
hooting-13.949
advertisement-12.701
icide-12.427
laughter-12.157
Token,
Token ID11
Feature activation+2.39e-01

Pos logit contributions
amins+7.949
ysis+7.458
+7.253
 ever+7.173
Thumbnail+7.052
Neg logit contributions
HUD-8.444
hooting-8.307
advertisement-7.624
boarding-7.063
horn-7.014
Token why
Token ID1521
Feature activation+8.73e-01

Pos logit contributions
amins+1.995
ysis+1.885
+1.874
Thumbnail+1.760
+1.738
Neg logit contributions
hooting-2.082
HUD-2.065
advertisement-1.894
boarding-1.810
icide-1.773
Token are
Token ID389
Feature activation+5.68e-01

Pos logit contributions
amins+6.194
ysis+5.754
+5.668
 ever+5.465
 submar+5.358
Neg logit contributions
HUD-8.048
hooting-8.041
advertisement-7.540
boarding-7.070
icide-6.951
Token we
Token ID356
Feature activation+9.04e-01

Pos logit contributions
amins+4.283
ysis+4.038
+3.975
Thumbnail+3.712
+3.708
Neg logit contributions
hooting-5.262
HUD-5.234
advertisement-4.878
boarding-4.636
icide-4.562
Tokend
Token ID67
Feature activation+1.24e+00

Pos logit contributions
amins+11.847
ysis+11.400
+11.186
uty+10.870
Thumbnail+10.668
Neg logit contributions
hooting-9.852
HUD-9.446
advertisement-8.916
boarding-8.585
icide-8.347
Token3
Token ID18
Feature activation+6.11e-01

Pos logit contributions
amins+10.526
ysis+10.186
+9.919
uty+9.605
Thumbnail+9.464
Neg logit contributions
hooting-8.839
HUD-8.452
advertisement-8.050
boarding-7.719
icide-7.459
Tokenp
Token ID79
Feature activation+1.16e+00

Pos logit contributions
amins+5.655
ysis+5.415
+5.344
Thumbnail+5.080
uty+5.050
Neg logit contributions
hooting-4.556
HUD-4.456
advertisement-4.104
boarding-3.909
icide-3.828
TokenW
Token ID54
Feature activation+7.63e-01

Pos logit contributions
amins+10.016
ysis+9.570
+9.377
uty+9.079
Thumbnail+8.974
Neg logit contributions
hooting-8.403
HUD-8.042
advertisement-7.603
boarding-7.334
icide-7.056
TokenX
Token ID55
Feature activation+6.38e-01

Pos logit contributions
amins+6.869
ysis+6.557
+6.491
Thumbnail+6.197
uty+6.159
Neg logit contributions
hooting-5.767
HUD-5.611
advertisement-5.161
boarding-4.980
icide-4.836
Tokenw
Token ID86
Feature activation+1.01e+00

Pos logit contributions
amins+5.862
ysis+5.601
+5.549
Thumbnail+5.276
uty+5.229
Neg logit contributions
hooting-4.806
HUD-4.694
advertisement-4.319
boarding-4.133
icide-4.027
Tokenpr
Token ID1050
Feature activation+7.11e-01

Pos logit contributions
amins+8.831
ysis+8.442
+8.296
uty+7.971
Thumbnail+7.957
Neg logit contributions
hooting-7.431
HUD-7.136
advertisement-6.727
boarding-6.455
icide-6.248
Token
Token ID851
Feature activation+2.96e-01

Pos logit contributions
amins+6.356
ysis+6.061
+6.038
Thumbnail+5.756
+5.658
Neg logit contributions
hooting-5.406
HUD-5.383
advertisement-5.024
boarding-4.721
icide-4.603
Token
Token ID12520
Feature activation+7.45e-01

Pos logit contributions
amins+2.650
ysis+2.524
+2.519
Thumbnail+2.365
+2.349
Neg logit contributions
hooting-2.371
HUD-2.360
advertisement-2.137
boarding-2.037
icide-1.995
Token
Token ID229
Feature activation+7.27e-01

Pos logit contributions
amins+3.892
+3.635
ysis+3.571
+3.547
+3.526
Neg logit contributions
hooting-8.537
HUD-8.413
advertisement-7.861
boarding-7.690
icide-7.596
Token
Token ID118
Feature activation+6.59e-01

Pos logit contributions
amins+4.054
+3.799
ysis+3.736
+3.717
+3.664
Neg logit contributions
hooting-8.024
HUD-7.965
advertisement-7.447
boarding-7.295
icide-7.225
Tokenate
Token ID378
Feature activation+1.74e-01

Pos logit contributions
amins+3.337
ysis+3.099
+3.087
uty+2.836
Thumbnail+2.824
Neg logit contributions
HUD-4.970
hooting-4.950
advertisement-4.568
boarding-4.407
icide-4.367
TokenGu
Token ID8205
Feature activation+4.31e-01

Pos logit contributions
amins+1.509
ysis+1.429
+1.423
Thumbnail+1.340
+1.323
Neg logit contributions
hooting-1.461
HUD-1.452
advertisement-1.324
boarding-1.266
icide-1.237
Tokenests
Token ID3558
Feature activation+4.19e-02

Pos logit contributions
amins+3.541
ysis+3.327
+3.283
+3.062
+3.055
Neg logit contributions
hooting-3.768
HUD-3.764
advertisement-3.463
boarding-3.301
horn-3.208
Token have
Token ID423
Feature activation+5.77e-01

Pos logit contributions
amins+0.361
ysis+0.341
+0.339
Thumbnail+0.318
+0.314
Neg logit contributions
hooting-0.357
HUD-0.355
advertisement-0.323
boarding-0.310
icide-0.303
Token been
Token ID587
Feature activation+3.61e-01

Pos logit contributions
amins+4.878
+4.666
ysis+4.635
+4.392
Thumbnail+4.366
Neg logit contributions
hooting-4.774
HUD-4.736
advertisement-4.352
boarding-4.072
icide-4.008
Token arrested
Token ID5169
Feature activation+6.14e-01

Pos logit contributions
amins+3.052
ysis+2.884
+2.883
+2.722
Thumbnail+2.709
Neg logit contributions
hooting-3.034
HUD-3.034
advertisement-2.784
boarding-2.611
icide-2.598
Token for
Token ID329
Feature activation+1.09e+00

Pos logit contributions
amins+5.001
ysis+4.760
+4.747
Thumbnail+4.443
+4.405
Neg logit contributions
HUD-5.264
hooting-5.190
advertisement-4.772
boarding-4.502
icide-4.455
Token our
Token ID674
Feature activation+9.22e-01

Pos logit contributions
amins+8.317
+7.942
ysis+7.829
+7.541
+7.530
Neg logit contributions
HUD-8.985
hooting-8.798
advertisement-8.080
icide-7.675
boarding-7.655
Token right
Token ID826
Feature activation+1.01e+00

Pos logit contributions
amins+7.283
ysis+6.865
+6.832
+6.445
+6.421
Neg logit contributions
hooting-7.786
HUD-7.774
advertisement-7.117
boarding-6.816
icide-6.645
Token to
Token ID284
Feature activation+9.91e-01

Pos logit contributions
amins+7.154
+6.922
ysis+6.721
+6.429
+6.287
Neg logit contributions
hooting-9.113
HUD-9.075
advertisement-8.211
boarding-7.861
icide-7.811
Token hear
Token ID3285
Feature activation-2.39e-01

Pos logit contributions
amins+6.718
+6.404
ysis+6.334
+5.951
+5.859
Neg logit contributions
HUD-9.279
hooting-9.174
advertisement-8.468
boarding-8.121
icide-8.062
Token by
Token ID416
Feature activation+1.62e-01

Pos logit contributions
amins+4.254
ysis+4.054
+4.037
Thumbnail+3.780
+3.741
Neg logit contributions
HUD-4.920
hooting-4.882
advertisement-4.536
boarding-4.277
icide-4.200
Token whom
Token ID4150
Feature activation+2.04e-01

Pos logit contributions
amins+1.306
ysis+1.232
+1.226
Thumbnail+1.150
+1.134
Neg logit contributions
hooting-1.456
HUD-1.446
advertisement-1.327
boarding-1.273
icide-1.248
Token
Token ID851
Feature activation+1.60e-01

Pos logit contributions
amins+1.911
ysis+1.823
+1.810
Thumbnail+1.716
+1.697
Neg logit contributions
hooting-1.563
HUD-1.553
advertisement-1.406
boarding-1.332
icide-1.298
Token there
Token ID612
Feature activation+1.66e-01

Pos logit contributions
amins+1.377
ysis+1.301
+1.297
Thumbnail+1.222
+1.205
Neg logit contributions
hooting-1.360
HUD-1.349
advertisement-1.232
boarding-1.179
icide-1.155
Token was
Token ID373
Feature activation+1.48e-01

Pos logit contributions
amins+1.344
ysis+1.273
+1.268
Thumbnail+1.187
+1.173
Neg logit contributions
hooting-1.487
HUD-1.484
advertisement-1.359
boarding-1.301
icide-1.277
Token no
Token ID645
Feature activation+4.47e-01

Pos logit contributions
amins+1.311
ysis+1.247
+1.241
Thumbnail+1.171
+1.155
Neg logit contributions
hooting-1.215
HUD-1.207
advertisement-1.097
boarding-1.048
icide-1.025
Token renewal
Token ID22901
Feature activation-2.24e-02

Pos logit contributions
amins+3.491
ysis+3.334
+3.310
Thumbnail+3.094
uty+3.056
Neg logit contributions
HUD-4.032
hooting-4.031
advertisement-3.694
boarding-3.538
icide-3.479
Token of
Token ID286
Feature activation+6.39e-01

Pos logit contributions
hooting+0.188
HUD+0.186
advertisement+0.171
boarding+0.163
icide+0.159
Neg logit contributions
amins-0.196
ysis-0.185
-0.184
Thumbnail-0.174
-0.171
Token the
Token ID262
Feature activation+2.16e-01

Pos logit contributions
amins+4.933
ysis+4.737
+4.707
uty+4.376
Thumbnail+4.362
Neg logit contributions
hooting-5.746
HUD-5.733
advertisement-5.265
boarding-4.976
icide-4.866
Token fierce
Token ID14800
Feature activation-3.69e-02

Pos logit contributions
amins+1.788
ysis+1.691
+1.683
Thumbnail+1.580
+1.559
Neg logit contributions
hooting-1.898
HUD-1.886
advertisement-1.727
boarding-1.654
icide-1.620
Token crackdown
Token ID22671
Feature activation+6.93e-01

Pos logit contributions
hooting+0.332
HUD+0.327
advertisement+0.304
boarding+0.291
icide+0.286
Neg logit contributions
amins-0.299
-0.279
ysis-0.279
Thumbnail-0.262
-0.258
TokenUnknown
Token ID20035
Feature activation+4.40e-01

Pos logit contributions
amins+6.797
+6.477
ysis+6.389
Thumbnail+6.151
+6.065
Neg logit contributions
hooting-6.340
HUD-6.162
advertisement-5.559
boarding-5.434
icide-5.332
Token Sources
Token ID26406
Feature activation-4.41e-01

Pos logit contributions
amins+3.859
+3.656
ysis+3.641
Thumbnail+3.461
+3.417
Neg logit contributions
hooting-3.601
HUD-3.555
advertisement-3.233
boarding-3.094
icide-3.023
Token.
Token ID13
Feature activation+1.07e-01

Pos logit contributions
hooting+3.423
HUD+3.354
advertisement+3.070
boarding+2.930
icide+2.838
Neg logit contributions
amins-3.985
ysis-3.856
-3.808
Thumbnail-3.565
-3.523
Token
Token ID447
Feature activation+3.72e-02

Pos logit contributions
amins+0.926
ysis+0.877
+0.873
Thumbnail+0.822
+0.811
Neg logit contributions
hooting-0.908
HUD-0.901
advertisement-0.823
boarding-0.786
icide-0.768
Token
Token ID247
Feature activation+2.96e-01

Pos logit contributions
amins+0.235
ysis+0.217
+0.216
Thumbnail+0.199
+0.194
Neg logit contributions
hooting-0.401
HUD-0.399
advertisement-0.372
boarding-0.359
icide-0.353
Token Otherwise
Token ID15323
Feature activation+8.17e-02

Pos logit contributions
amins+2.549
ysis+2.412
+2.402
Thumbnail+2.263
+2.233
Neg logit contributions
hooting-2.508
HUD-2.489
advertisement-2.270
boarding-2.173
icide-2.129
Token,
Token ID11
Feature activation+2.68e-01

Pos logit contributions
amins+0.792
ysis+0.754
+0.752
Thumbnail+0.713
+0.705
Neg logit contributions
hooting-0.602
HUD-0.597
advertisement-0.538
boarding-0.510
icide-0.498
Token you
Token ID345
Feature activation-3.07e-01

Pos logit contributions
amins+2.162
ysis+2.037
+2.031
Thumbnail+1.901
+1.874
Neg logit contributions
hooting-2.416
HUD-2.401
advertisement-2.205
boarding-2.114
icide-2.074
Token will
Token ID481
Feature activation-2.91e-01

Pos logit contributions
hooting+2.430
HUD+2.393
advertisement+2.135
boarding+2.054
icide+2.036
Neg logit contributions
amins-2.783
ysis-2.658
-2.592
Thumbnail-2.501
-2.444
Token not
Token ID407
Feature activation-3.09e-01

Pos logit contributions
hooting+2.427
HUD+2.392
advertisement+2.157
boarding+2.067
icide+2.040
Neg logit contributions
amins-2.531
ysis-2.407
-2.352
Thumbnail-2.247
-2.180
Token be
Token ID307
Feature activation-4.99e-01

Pos logit contributions
hooting+2.564
HUD+2.538
advertisement+2.292
boarding+2.197
icide+2.158
Neg logit contributions
amins-2.685
ysis-2.557
-2.532
Thumbnail-2.385
-2.352
Token 14
Token ID1478
Feature activation-4.83e-01

Pos logit contributions
hooting+2.862
HUD+2.786
advertisement+2.539
boarding+2.492
icide+2.410
Neg logit contributions
amins-3.289
-3.110
ysis-3.070
Thumbnail-2.993
 sidx-2.949
Token days
Token ID1528
Feature activation-3.45e-01

Pos logit contributions
hooting+4.860
HUD+4.697
advertisement+4.390
boarding+4.295
icide+4.211
Neg logit contributions
amins-3.316
ysis-3.076
-3.050
Thumbnail-2.930
 sidx-2.805
Token from
Token ID422
Feature activation-1.40e-01

Pos logit contributions
hooting+2.689
HUD+2.611
advertisement+2.347
boarding+2.312
icide+2.244
Neg logit contributions
amins-3.191
ysis-3.027
-3.010
Thumbnail-2.897
-2.835
Token Friday
Token ID3217
Feature activation-4.38e-01

Pos logit contributions
hooting+0.994
HUD+0.978
advertisement+0.883
boarding+0.845
icide+0.817
Neg logit contributions
amins-1.407
-1.331
ysis-1.330
Thumbnail-1.270
-1.252
Token in
Token ID287
Feature activation+2.91e-01

Pos logit contributions
hooting+3.249
HUD+3.206
advertisement+2.861
boarding+2.795
icide+2.718
Neg logit contributions
amins-4.192
ysis-3.947
-3.937
Thumbnail-3.787
-3.689
Token a
Token ID257
Feature activation+6.74e-03

Pos logit contributions
amins+2.508
ysis+2.380
+2.367
Thumbnail+2.220
+2.200
Neg logit contributions
hooting-2.433
HUD-2.433
advertisement-2.220
boarding-2.115
icide-2.068
Token bid
Token ID8406
Feature activation-2.23e-01

Pos logit contributions
amins+0.060
ysis+0.056
+0.056
Thumbnail+0.053
+0.052
Neg logit contributions
hooting-0.056
HUD-0.055
advertisement-0.050
boarding-0.048
icide-0.047
Token to
Token ID284
Feature activation-4.81e-01

Pos logit contributions
hooting+1.676
HUD+1.648
advertisement+1.483
boarding+1.417
icide+1.408
Neg logit contributions
amins-2.118
ysis-2.008
-1.976
Thumbnail-1.907
-1.875
Token contain
Token ID3994
Feature activation+1.54e-01

Pos logit contributions
hooting+4.278
HUD+4.071
advertisement+3.808
icide+3.667
boarding+3.595
Neg logit contributions
amins-3.887
-3.550
ysis-3.537
Thumbnail-3.483
-3.379
Token the
Token ID262
Feature activation+2.60e-01

Pos logit contributions
amins+1.343
ysis+1.269
+1.267
Thumbnail+1.195
+1.177
Neg logit contributions
hooting-1.284
HUD-1.271
advertisement-1.161
boarding-1.110
icide-1.086
Token virus
Token ID9471
Feature activation-5.49e-01

Pos logit contributions
amins+2.318
ysis+2.205
+2.192
Thumbnail+2.061
+2.045
Neg logit contributions
hooting-2.114
HUD-2.113
advertisement-1.910
boarding-1.824
icide-1.781
Token@
Token ID31
Feature activation+1.10e-01

Pos logit contributions
hooting+1.542
HUD+1.531
advertisement+1.388
boarding+1.307
horn+1.282
Neg logit contributions
amins-1.939
ysis-1.855
-1.853
Thumbnail-1.735
-1.719
Tokens
Token ID82
Feature activation+4.37e-01

Pos logit contributions
amins+0.993
ysis+0.944
+0.941
Thumbnail+0.888
+0.877
Neg logit contributions
hooting-0.893
HUD-0.887
advertisement-0.805
boarding-0.770
icide-0.753
Tokenunt
Token ID2797
Feature activation+4.66e-01

Pos logit contributions
amins+3.604
ysis+3.366
+3.326
Thumbnail+3.162
uty+3.109
Neg logit contributions
hooting-3.834
HUD-3.827
advertisement-3.508
boarding-3.376
icide-3.269
Tokenimes
Token ID999
Feature activation+4.08e-01

Pos logit contributions
amins+2.067
ysis+1.863
+1.786
uty+1.563
Thumbnail+1.554
Neg logit contributions
HUD-5.873
hooting-5.828
advertisement-5.491
boarding-5.348
icide-5.264
Token.
Token ID13
Feature activation+6.18e-02

Pos logit contributions
amins+3.536
ysis+3.357
+3.310
Thumbnail+3.130
+3.080
Neg logit contributions
HUD-3.410
hooting-3.386
advertisement-3.093
boarding-2.940
icide-2.889
Tokencom
Token ID785
Feature activation-3.01e-02

Pos logit contributions
amins+0.497
ysis+0.469
+0.467
Thumbnail+0.437
+0.431
Neg logit contributions
hooting-0.559
HUD-0.555
advertisement-0.509
boarding-0.489
icide-0.480
Token<|endoftext|>
Token ID50256
Feature activation-1.41e-01

Pos logit contributions
hooting+0.241
HUD+0.239
advertisement+0.216
boarding+0.207
icide+0.203
Neg logit contributions
amins-0.273
ysis-0.260
-0.259
Thumbnail-0.244
-0.241
TokenNintendo
Token ID32348
Feature activation-4.11e-01

Pos logit contributions
HUD+1.161
hooting+1.141
advertisement+1.069
boarding+1.000
horn+0.972
Neg logit contributions
amins-1.253
ysis-1.194
-1.172
 sidx-1.099
-1.096
Token fans
Token ID3296
Feature activation-4.69e-01

Pos logit contributions
hooting+3.399
HUD+3.365
advertisement+3.091
boarding+2.975
icide+2.964
Neg logit contributions
amins-3.498
ysis-3.365
-3.318
Thumbnail-3.152
-3.094
Token desperate
Token ID12111
Feature activation+1.43e-01

Pos logit contributions
hooting+3.972
HUD+3.838
advertisement+3.496
boarding+3.390
icide+3.357
Neg logit contributions
amins-4.050
-3.836
ysis-3.808
Thumbnail-3.657
-3.508
Token to
Token ID284
Feature activation-2.32e-01

Pos logit contributions
amins+1.256
ysis+1.191
+1.187
Thumbnail+1.117
+1.104
Neg logit contributions
hooting-1.188
HUD-1.185
advertisement-1.076
boarding-1.030
icide-1.004
Tokenian
Token ID666
Feature activation+1.64e-01

Pos logit contributions
amins+1.134
ysis+1.074
+1.070
Thumbnail+1.009
+0.996
Neg logit contributions
hooting-1.066
HUD-1.058
advertisement-0.964
boarding-0.920
icide-0.901
Token C
Token ID327
Feature activation-3.50e-01

Pos logit contributions
amins+1.471
ysis+1.396
+1.390
Thumbnail+1.311
+1.296
Neg logit contributions
hooting-1.326
HUD-1.316
advertisement-1.196
boarding-1.140
icide-1.115
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
hooting+3.117
HUD+3.031
advertisement+2.795
horn+2.712
boarding+2.707
Neg logit contributions
amins-2.823
-2.692
ysis-2.650
Thumbnail-2.562
-2.483
Token York
Token ID1971
Feature activation+6.22e-01

Pos logit contributions
hooting+1.128
HUD+1.121
advertisement+1.018
boarding+0.969
horn+0.950
Neg logit contributions
amins-1.254
ysis-1.183
-1.179
Thumbnail-1.125
-1.100
Token added
Token ID2087
Feature activation+1.75e-01

Pos logit contributions
amins+5.133
+4.862
ysis+4.796
+4.537
Thumbnail+4.527
Neg logit contributions
HUD-5.334
hooting-5.329
advertisement-4.860
boarding-4.617
icide-4.541
Token in
Token ID287
Feature activation-2.86e-01

Pos logit contributions
amins+1.433
ysis+1.350
+1.346
Thumbnail+1.263
+1.246
Neg logit contributions
hooting-1.562
HUD-1.551
advertisement-1.421
boarding-1.362
icide-1.337
Token her
Token ID607
Feature activation-5.16e-02

Pos logit contributions
hooting+2.144
HUD+2.079
advertisement+1.927
boarding+1.825
horn+1.768
Neg logit contributions
amins-2.740
ysis-2.620
-2.588
Thumbnail-2.456
-2.417
Token argument
Token ID4578
Feature activation+2.34e-01

Pos logit contributions
hooting+0.380
HUD+0.371
advertisement+0.340
boarding+0.323
icide+0.314
Neg logit contributions
amins-0.505
ysis-0.479
-0.476
Thumbnail-0.451
-0.446
Token that
Token ID326
Feature activation-4.72e-02

Pos logit contributions
amins+1.912
ysis+1.805
+1.799
Thumbnail+1.684
+1.664
Neg logit contributions
hooting-2.081
HUD-2.067
advertisement-1.890
boarding-1.812
icide-1.779
Token filtering
Token ID25431
Feature activation-4.05e-02

Pos logit contributions
hooting+0.396
HUD+0.394
advertisement+0.362
boarding+0.346
icide+0.337
Neg logit contributions
amins-0.412
ysis-0.387
-0.386
Thumbnail-0.365
-0.357
Token systems
Token ID3341
Feature activation-2.00e-01

Pos logit contributions
hooting+0.346
HUD+0.345
advertisement+0.317
boarding+0.305
icide+0.296
Neg logit contributions
amins-0.347
-0.324
ysis-0.323
Thumbnail-0.304
-0.300
Token Jama
Token ID21661
Feature activation-1.64e-01

Pos logit contributions
amins+1.958
ysis+1.861
+1.853
Thumbnail+1.753
+1.727
Neg logit contributions
hooting-1.779
HUD-1.761
advertisement-1.604
boarding-1.530
icide-1.497
Tokenal
Token ID282
Feature activation-6.98e-02

Pos logit contributions
hooting+1.380
HUD+1.356
advertisement+1.238
icide+1.199
boarding+1.173
Neg logit contributions
amins-1.401
-1.343
ysis-1.339
Thumbnail-1.269
 sidx-1.254
Token Charles
Token ID7516
Feature activation-1.76e-01

Pos logit contributions
hooting+0.518
HUD+0.515
advertisement+0.462
icide+0.442
boarding+0.433
Neg logit contributions
amins-0.675
-0.639
ysis-0.638
Thumbnail-0.606
-0.599
Token also
Token ID635
Feature activation-5.69e-01

Pos logit contributions
hooting+1.414
HUD+1.371
advertisement+1.240
boarding+1.189
horn+1.174
Neg logit contributions
amins-1.626
ysis-1.530
-1.527
Thumbnail-1.430
-1.421
Token participated
Token ID14888
Feature activation-2.47e-01

Pos logit contributions
hooting+4.279
HUD+3.955
advertisement+3.610
boarding+3.514
horn+3.473
Neg logit contributions
amins-5.456
-5.102
ysis-5.095
uty-4.820
Thumbnail-4.785
Token in
Token ID287
Feature activation-2.69e-01

Pos logit contributions
hooting+2.025
HUD+1.987
advertisement+1.804
boarding+1.733
horn+1.697
Neg logit contributions
amins-2.198
-2.076
ysis-2.074
Thumbnail-1.947
-1.934
Token 11
Token ID1367
Feature activation-2.90e-02

Pos logit contributions
hooting+2.135
HUD+2.075
advertisement+1.897
boarding+1.826
icide+1.783
Neg logit contributions
amins-2.431
-2.305
ysis-2.267
Thumbnail-2.161
endor-2.131
Token-
Token ID12
Feature activation-4.84e-01

Pos logit contributions
hooting+0.247
HUD+0.243
advertisement+0.222
boarding+0.214
icide+0.209
Neg logit contributions
amins-0.249
-0.235
ysis-0.233
Thumbnail-0.220
-0.218
Tokenon
Token ID261
Feature activation-2.44e-01

Pos logit contributions
hooting+3.839
HUD+3.749
advertisement+3.433
boarding+3.332
horn+3.286
Neg logit contributions
amins-4.194
-4.077
ysis-3.971
 sidx-3.886
Thumbnail-3.872
Token-
Token ID12
Feature activation-9.77e-01

Pos logit contributions
hooting+1.935
HUD+1.897
advertisement+1.754
boarding+1.698
horn+1.629
Neg logit contributions
amins-2.190
ysis-2.095
-2.074
Thumbnail-1.978
-1.975
Token11
Token ID1157
Feature activation-3.78e-01

Pos logit contributions
hooting+5.521
HUD+5.318
advertisement+4.728
boarding+4.528
horn+4.410
Neg logit contributions
amins-10.174
-10.157
ysis-10.084
-9.714
-9.683
Token south
Token ID5366
Feature activation-5.32e-01

Pos logit contributions
hooting+1.824
HUD+1.789
advertisement+1.634
boarding+1.551
icide+1.513
Neg logit contributions
amins-2.126
ysis-2.029
-2.006
Thumbnail-1.936
-1.887
Token of
Token ID286
Feature activation-1.21e-01

Pos logit contributions
hooting+3.973
HUD+3.831
boarding+3.470
advertisement+3.463
icide+3.324
Neg logit contributions
amins-4.997
ysis-4.740
-4.667
Thumbnail-4.564
-4.442
Token Jerusalem
Token ID10843
Feature activation+2.10e-01

Pos logit contributions
hooting+0.901
HUD+0.900
advertisement+0.803
boarding+0.775
icide+0.753
Neg logit contributions
amins-1.167
-1.108
ysis-1.105
Thumbnail-1.052
-1.033
Token to
Token ID284
Feature activation+1.72e-02

Pos logit contributions
amins+1.835
ysis+1.737
+1.731
Thumbnail+1.628
+1.610
Neg logit contributions
hooting-1.755
HUD-1.743
advertisement-1.589
boarding-1.518
icide-1.484
Token Heb
Token ID27030
Feature activation-1.94e-01

Pos logit contributions
amins+0.155
+0.147
ysis+0.147
Thumbnail+0.139
+0.136
Neg logit contributions
hooting-0.139
HUD-0.138
advertisement-0.125
boarding-0.120
icide-0.117
Tokenron
Token ID1313
Feature activation-4.43e-01

Pos logit contributions
HUD+1.666
hooting+1.666
advertisement+1.511
boarding+1.477
icide+1.449
Neg logit contributions
amins-1.633
ysis-1.545
-1.539
Thumbnail-1.446
-1.421
Token,
Token ID11
Feature activation-4.63e-01

Pos logit contributions
HUD+3.162
hooting+3.142
advertisement+2.822
boarding+2.728
icide+2.652
Neg logit contributions
amins-4.204
ysis-4.028
-4.027
Thumbnail-3.845
-3.750
Token bis
Token ID47457
Feature activation-3.26e-02

Pos logit contributions
HUD+3.573
hooting+3.559
advertisement+3.247
boarding+3.123
icide+3.081
Neg logit contributions
amins-4.153
ysis-3.973
-3.960
Thumbnail-3.806
-3.724
Tokenect
Token ID478
Feature activation-1.24e-01

Pos logit contributions
hooting+0.318
HUD+0.314
advertisement+0.290
boarding+0.279
icide+0.275
Neg logit contributions
amins-0.239
ysis-0.226
-0.226
Thumbnail-0.210
-0.207
Tokening
Token ID278
Feature activation+5.23e-02

Pos logit contributions
hooting+0.869
HUD+0.855
advertisement+0.767
boarding+0.736
icide+0.712
Neg logit contributions
amins-1.252
-1.195
ysis-1.181
Thumbnail-1.138
-1.113
Token the
Token ID262
Feature activation-8.51e-02

Pos logit contributions
amins+0.467
ysis+0.441
+0.441
Thumbnail+0.417
+0.410
Neg logit contributions
hooting-0.426
HUD-0.424
advertisement-0.385
boarding-0.369
icide-0.361
Token in
Token ID287
Feature activation-5.03e-02

Pos logit contributions
hooting+3.900
HUD+3.750
boarding+3.348
advertisement+3.344
icide+3.201
Neg logit contributions
amins-4.748
-4.433
ysis-4.331
Thumbnail-4.219
 sidx-4.124
Token jail
Token ID7356
Feature activation-4.78e-02

Pos logit contributions
hooting+0.391
HUD+0.384
advertisement+0.346
boarding+0.335
icide+0.327
Neg logit contributions
amins-0.473
-0.447
ysis-0.444
Thumbnail-0.422
-0.414
Token.
Token ID13
Feature activation-2.47e-02

Pos logit contributions
hooting+0.380
HUD+0.371
advertisement+0.339
boarding+0.326
icide+0.317
Neg logit contributions
amins-0.442
-0.417
ysis-0.415
Thumbnail-0.394
-0.389
Token But
Token ID887
Feature activation+5.16e-01

Pos logit contributions
hooting+0.194
HUD+0.193
advertisement+0.175
boarding+0.167
icide+0.163
Neg logit contributions
amins-0.228
ysis-0.216
-0.214
Thumbnail-0.203
-0.201
Token the
Token ID262
Feature activation+4.48e-01

Pos logit contributions
amins+4.296
ysis+4.145
+4.058
Thumbnail+3.823
uty+3.770
Neg logit contributions
hooting-4.400
HUD-4.370
advertisement-3.987
boarding-3.796
icide-3.693
Token authorities
Token ID4773
Feature activation-3.54e-01

Pos logit contributions
amins+3.590
ysis+3.422
+3.376
Thumbnail+3.160
uty+3.108
Neg logit contributions
HUD-4.013
hooting-4.012
advertisement-3.649
boarding-3.491
icide-3.414
Token have
Token ID423
Feature activation-2.12e-01

Pos logit contributions
hooting+2.841
HUD+2.743
advertisement+2.485
boarding+2.422
icide+2.379
Neg logit contributions
amins-3.241
-3.027
ysis-3.005
Thumbnail-2.866
-2.813
Token been
Token ID587
Feature activation+1.76e-01

Pos logit contributions
hooting+1.711
HUD+1.667
advertisement+1.526
boarding+1.474
icide+1.444
Neg logit contributions
amins-1.933
-1.797
ysis-1.792
Thumbnail-1.693
 sidx-1.685
Token unable
Token ID5906
Feature activation-1.38e-01

Pos logit contributions
amins+1.556
ysis+1.476
+1.470
Thumbnail+1.387
+1.369
Neg logit contributions
hooting-1.450
HUD-1.440
advertisement-1.311
boarding-1.251
icide-1.224
Token to
Token ID284
Feature activation+1.12e-01

Pos logit contributions
hooting+1.088
HUD+1.049
advertisement+0.961
boarding+0.926
icide+0.908
Neg logit contributions
amins-1.290
-1.208
ysis-1.200
Thumbnail-1.158
-1.136
Token silence
Token ID9550
Feature activation+5.36e-01

Pos logit contributions
amins+0.874
ysis+0.818
+0.816
Thumbnail+0.766
+0.754
Neg logit contributions
hooting-1.036
HUD-1.025
advertisement-0.945
boarding-0.909
icide-0.893
Token the
Token ID262
Feature activation+5.19e-01

Pos logit contributions
hooting+0.539
HUD+0.533
advertisement+0.479
boarding+0.453
icide+0.441
Neg logit contributions
amins-0.756
ysis-0.720
-0.717
Thumbnail-0.682
-0.673
Token marijuana
Token ID5727
Feature activation+4.40e-01

Pos logit contributions
amins+4.260
ysis+4.069
+4.042
Thumbnail+3.773
+3.751
Neg logit contributions
hooting-4.483
HUD-4.462
advertisement-4.039
boarding-3.866
icide-3.823
Token issue
Token ID2071
Feature activation-5.54e-01

Pos logit contributions
amins+3.787
ysis+3.562
+3.545
Thumbnail+3.334
+3.295
Neg logit contributions
hooting-3.705
HUD-3.677
advertisement-3.329
boarding-3.175
icide-3.110
Token will
Token ID481
Feature activation-4.95e-01

Pos logit contributions
hooting+4.606
HUD+4.487
advertisement+4.149
boarding+3.988
horn+3.888
Neg logit contributions
amins-4.789
ysis-4.497
-4.464
Thumbnail-4.247
-4.219
Token face
Token ID1986
Feature activation-9.22e-02

Pos logit contributions
hooting+4.136
HUD+3.936
advertisement+3.612
icide+3.457
boarding+3.447
Neg logit contributions
amins-4.279
ysis-4.032
-3.966
Thumbnail-3.839
-3.747
Token a
Token ID257
Feature activation-1.13e-01

Pos logit contributions
hooting+0.744
HUD+0.739
advertisement+0.674
boarding+0.642
icide+0.626
Neg logit contributions
amins-0.834
-0.783
ysis-0.778
Thumbnail-0.743
-0.731
Token greater
Token ID3744
Feature activation+1.33e-02

Pos logit contributions
hooting+0.971
HUD+0.962
advertisement+0.875
boarding+0.844
icide+0.822
Neg logit contributions
amins-0.967
-0.904
ysis-0.904
Thumbnail-0.856
-0.841
Token burden
Token ID10538
Feature activation-2.17e-01

Pos logit contributions
amins+0.114
+0.107
ysis+0.106
Thumbnail+0.101
+0.100
Neg logit contributions
hooting-0.114
HUD-0.114
advertisement-0.104
boarding-0.100
icide-0.098
Token of
Token ID286
Feature activation+1.45e-01

Pos logit contributions
hooting+1.716
HUD+1.696
advertisement+1.542
boarding+1.486
horn+1.438
Neg logit contributions
amins-1.983
ysis-1.874
-1.864
Thumbnail-1.773
-1.758
Token proof
Token ID6617
Feature activation-8.20e-01

Pos logit contributions
amins+1.267
ysis+1.200
+1.196
Thumbnail+1.127
+1.113
Neg logit contributions
hooting-1.206
HUD-1.197
advertisement-1.091
boarding-1.043
icide-1.020
Token than
Token ID621
Feature activation+2.14e-01

Pos logit contributions
hooting+6.099
HUD+5.893
advertisement+5.426
boarding+5.314
icide+5.048
Neg logit contributions
amins-7.328
ysis-6.788
-6.787
Thumbnail-6.630
-6.514
Token doctrine
Token ID13115
Feature activation-3.26e-01

Pos logit contributions
amins+3.464
ysis+3.304
+3.256
Thumbnail+3.010
+3.003
Neg logit contributions
HUD-4.422
hooting-4.408
advertisement-4.041
boarding-3.909
icide-3.799
Token as
Token ID355
Feature activation-1.33e-01

Pos logit contributions
hooting+2.326
HUD+2.285
advertisement+2.111
boarding+1.973
icide+1.935
Neg logit contributions
amins-3.203
-3.031
ysis-3.007
Thumbnail-2.900
-2.838
Token briefly
Token ID11589
Feature activation-4.49e-01

Pos logit contributions
hooting+1.087
HUD+1.074
advertisement+0.981
boarding+0.934
icide+0.923
Neg logit contributions
amins-1.178
ysis-1.116
-1.113
Thumbnail-1.053
 sidx-1.025
Token and
Token ID290
Feature activation-6.64e-01

Pos logit contributions
hooting+3.629
HUD+3.497
advertisement+3.222
boarding+3.092
icide+3.051
Neg logit contributions
amins-4.015
-3.778
ysis-3.732
Thumbnail-3.564
-3.496
Token clearly
Token ID4084
Feature activation-5.91e-01

Pos logit contributions
hooting+4.972
HUD+4.894
advertisement+4.481
boarding+4.218
icide+4.151
Neg logit contributions
amins-6.018
-5.700
ysis-5.679
Thumbnail-5.392
-5.285
Token as
Token ID355
Feature activation-1.20e+00

Pos logit contributions
hooting+4.531
HUD+4.348
advertisement+4.022
boarding+3.850
icide+3.719
Neg logit contributions
amins-5.429
-5.086
ysis-5.032
Thumbnail-4.848
-4.728
Token the
Token ID262
Feature activation-5.33e-01

Pos logit contributions
hooting+8.138
HUD+7.602
icide+6.781
boarding+6.719
 confession+6.711
Neg logit contributions
amins-10.657
-10.235
ysis-10.131
Thumbnail-10.107
 sidx-9.493
Token matter
Token ID2300
Feature activation-7.94e-01

Pos logit contributions
hooting+4.364
HUD+4.224
advertisement+3.909
boarding+3.720
 confession+3.710
Neg logit contributions
amins-4.527
-4.272
ysis-4.267
Thumbnail-4.127
-3.962
Token itself
Token ID2346
Feature activation-7.55e-01

Pos logit contributions
hooting+5.878
HUD+5.456
advertisement+5.145
boarding+5.087
horn+4.967
Neg logit contributions
amins-7.040
-6.861
ysis-6.759
Thumbnail-6.614
 sidx-6.466
Token may
Token ID743
Feature activation-5.14e-01

Pos logit contributions
hooting+5.559
HUD+5.270
advertisement+4.994
boarding+4.704
horn+4.637
Neg logit contributions
amins-6.841
-6.582
ysis-6.442
Thumbnail-6.331
-6.082
Token allow
Token ID1249
Feature activation-8.72e-01

Pos logit contributions
hooting+4.504
HUD+4.325
advertisement+4.029
boarding+3.904
horn+3.820
Neg logit contributions
amins-4.182
-3.986
ysis-3.939
Thumbnail-3.731
-3.650
Token California
Token ID3442
Feature activation-6.53e-01

Pos logit contributions
hooting+4.831
HUD+4.742
advertisement+4.395
boarding+4.148
icide+4.120
Neg logit contributions
amins-5.512
-5.228
ysis-4.999
Thumbnail-4.921
 sidx-4.801
Token-
Token ID12
Feature activation-3.07e-01

Pos logit contributions
HUD+4.989
hooting+4.868
advertisement+4.447
icide+4.267
boarding+4.235
Neg logit contributions
amins-6.051
-5.622
ysis-5.444
Thumbnail-5.277
 sidx-5.250
Tokenbased
Token ID3106
Feature activation-1.03e+00

Pos logit contributions
HUD+2.163
hooting+2.120
advertisement+1.960
boarding+1.803
horn+1.765
Neg logit contributions
amins-3.093
ysis-2.956
-2.884
 sidx-2.805
Thumbnail-2.766
Token Total
Token ID7472
Feature activation-2.42e-01

Pos logit contributions
hooting+7.903
HUD+7.848
advertisement+7.057
boarding+6.914
icide+6.834
Neg logit contributions
amins-8.646
-8.260
Thumbnail-7.817
ysis-7.806
 sidx-7.532
Token Call
Token ID4889
Feature activation-4.53e-01

Pos logit contributions
HUD+1.917
hooting+1.907
advertisement+1.718
icide+1.667
boarding+1.651
Neg logit contributions
amins-2.211
-2.082
ysis-2.060
Thumbnail-1.945
 sidx-1.929
Token Mobile
Token ID12173
Feature activation-1.32e+00

Pos logit contributions
hooting+3.856
HUD+3.805
advertisement+3.459
icide+3.385
boarding+3.365
Neg logit contributions
amins-3.810
-3.570
ysis-3.510
Thumbnail-3.382
 sidx-3.316
Token of
Token ID286
Feature activation-8.47e-01

Pos logit contributions
HUD+8.368
hooting+8.298
advertisement+7.278
icide+7.037
horn+7.010
Neg logit contributions
amins-12.471
-11.574
ysis-11.415
 sidx-10.957
Thumbnail-10.853
Token fraud
Token ID7394
Feature activation-2.21e-01

Pos logit contributions
hooting+5.954
HUD+5.827
advertisement+5.348
icide+5.106
boarding+5.078
Neg logit contributions
amins-7.941
-7.628
ysis-7.396
Thumbnail-7.094
-6.985
Tokenul
Token ID377
Feature activation-1.58e-02

Pos logit contributions
hooting+1.836
HUD+1.796
advertisement+1.629
boarding+1.571
icide+1.560
Neg logit contributions
amins-1.965
ysis-1.855
-1.853
Thumbnail-1.755
-1.716
Tokenently
Token ID1473
Feature activation-4.93e-01

Pos logit contributions
hooting+0.111
HUD+0.110
advertisement+0.099
boarding+0.093
icide+0.091
Neg logit contributions
amins-0.159
-0.152
ysis-0.151
Thumbnail-0.144
-0.143
Token enroll
Token ID14627
Feature activation-3.10e-01

Pos logit contributions
hooting+3.878
HUD+3.784
advertisement+3.428
boarding+3.367
icide+3.213
Neg logit contributions
amins-4.539
-4.322
ysis-4.280
Thumbnail-4.051
-4.011
Token more
Token ID517
Feature activation-1.21e+00

Pos logit contributions
hooting+1.580
HUD+1.557
advertisement+1.406
boarding+1.345
horn+1.323
Neg logit contributions
amins-1.902
ysis-1.812
-1.808
Thumbnail-1.707
-1.688
Token top
Token ID1353
Feature activation-8.68e-02

Pos logit contributions
hooting+9.030
HUD+9.021
horn+7.799
advertisement+7.781
boarding+7.692
Neg logit contributions
amins-10.099
-9.678
ysis-9.582
Thumbnail-9.053
-8.929
Token-
Token ID12
Feature activation-5.06e-01

Pos logit contributions
hooting+0.770
HUD+0.762
advertisement+0.701
boarding+0.672
icide+0.660
Neg logit contributions
amins-0.713
ysis-0.677
-0.676
Thumbnail-0.637
-0.621
Tokenend
Token ID437
Feature activation-7.87e-01

Pos logit contributions
hooting+3.725
HUD+3.649
advertisement+3.401
boarding+3.207
horn+3.199
Neg logit contributions
amins-4.784
ysis-4.647
-4.640
Thumbnail-4.396
-4.386
Token spark
Token ID9009
Feature activation-9.13e-01

Pos logit contributions
hooting+5.461
HUD+5.276
advertisement+4.755
boarding+4.615
horn+4.557
Neg logit contributions
amins-7.406
-7.211
ysis-7.119
Thumbnail-6.843
-6.723
Tokenle
Token ID293
Feature activation-1.22e+00

Pos logit contributions
hooting+6.254
HUD+6.044
horn+5.347
boarding+5.227
advertisement+5.155
Neg logit contributions
amins-8.681
-8.256
ysis-8.165
Thumbnail-7.933
-7.675
Token and
Token ID290
Feature activation-8.25e-01

Pos logit contributions
hooting+8.211
HUD+7.854
advertisement+7.022
boarding+6.964
horn+6.830
Neg logit contributions
amins-11.101
-10.593
ysis-10.452
Thumbnail-10.073
-9.925
Token superb
Token ID21840
Feature activation-5.94e-01

Pos logit contributions
hooting+6.510
HUD+6.379
advertisement+5.867
boarding+5.555
horn+5.521
Neg logit contributions
amins-7.023
-6.688
ysis-6.598
Thumbnail-6.211
isine-6.153
Token neutrality
Token ID20723
Feature activation+4.54e-03

Pos logit contributions
hooting+4.801
HUD+4.604
advertisement+4.296
boarding+4.072
horn+4.033
Neg logit contributions
amins-5.147
-4.871
ysis-4.809
Thumbnail-4.652
 sidx-4.509
Token,
Token ID11
Feature activation-4.73e-01

Pos logit contributions
amins+0.043
+0.041
ysis+0.041
Thumbnail+0.039
+0.038
Neg logit contributions
hooting-0.035
HUD-0.034
advertisement-0.031
boarding-0.029
icide-0.029
Token the
Token ID262
Feature activation-3.85e-01

Pos logit contributions
hooting+3.783
HUD+3.751
advertisement+3.407
boarding+3.253
horn+3.192
Neg logit contributions
amins-4.142
ysis-3.992
-3.970
Thumbnail-3.787
-3.692
Token but
Token ID475
Feature activation+4.60e-02

Pos logit contributions
amins+3.065
ysis+2.913
+2.907
Thumbnail+2.732
+2.707
Neg logit contributions
hooting-2.996
HUD-2.977
advertisement-2.722
boarding-2.586
icide-2.540
Token said
Token ID531
Feature activation+1.12e-01

Pos logit contributions
amins+0.404
ysis+0.382
+0.382
Thumbnail+0.360
+0.354
Neg logit contributions
hooting-0.383
HUD-0.380
advertisement-0.345
boarding-0.332
icide-0.324
Token Moscow
Token ID9070
Feature activation-9.16e-01

Pos logit contributions
amins+0.933
+0.878
ysis+0.877
Thumbnail+0.824
+0.813
Neg logit contributions
hooting-0.990
HUD-0.984
advertisement-0.900
boarding-0.867
icide-0.848
Token had
Token ID550
Feature activation-7.24e-01

Pos logit contributions
HUD+6.285
hooting+6.247
boarding+5.609
icide+5.482
advertisement+5.423
Neg logit contributions
amins-8.386
-7.881
ysis-7.807
Thumbnail-7.442
-7.344
Token a
Token ID257
Feature activation-5.12e-02

Pos logit contributions
hooting+5.328
HUD+5.325
advertisement+4.863
boarding+4.742
icide+4.687
Neg logit contributions
amins-6.649
-6.125
ysis-5.997
Thumbnail-5.796
 sidx-5.712
Token long
Token ID890
Feature activation-1.55e+00

Pos logit contributions
hooting+0.431
HUD+0.427
advertisement+0.390
boarding+0.374
icide+0.366
Neg logit contributions
amins-0.445
ysis-0.417
-0.417
Thumbnail-0.393
-0.387
Token way
Token ID835
Feature activation-1.06e+00

Pos logit contributions
HUD+8.599
hooting+8.561
boarding+8.415
icide+7.513
 confession+7.375
Neg logit contributions
amins-13.994
ysis-13.649
-13.240
Thumbnail-13.028
 sidx-12.967
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
hooting+6.838
HUD+6.474
boarding+5.941
advertisement+5.573
icide+5.535
Neg logit contributions
amins-10.386
-9.890
ysis-9.694
Thumbnail-9.428
 sidx-9.304
Token go
Token ID467
Feature activation-2.38e-01

Pos logit contributions
hooting+7.468
HUD+7.219
boarding+6.666
icide+6.638
advertisement+6.483
Neg logit contributions
amins-8.880
-8.484
ysis-8.132
-7.798
-7.726
Token to
Token ID284
Feature activation-8.30e-01

Pos logit contributions
hooting+1.814
HUD+1.763
advertisement+1.579
boarding+1.575
icide+1.522
Neg logit contributions
amins-2.237
ysis-2.119
-2.117
Thumbnail-1.987
-1.981
Token prove
Token ID5879
Feature activation-5.73e-01

Pos logit contributions
hooting+6.490
HUD+6.331
advertisement+5.665
boarding+5.632
icide+5.591
Neg logit contributions
amins-7.074
-6.509
ysis-6.379
-6.191
Thumbnail-6.171
Token of
Token ID286
Feature activation-3.44e-01

Pos logit contributions
hooting+7.674
HUD+7.561
advertisement+6.915
boarding+6.731
bees+6.566
Neg logit contributions
amins-8.089
-7.735
ysis-7.547
Thumbnail-7.219
isine-7.108
Token this
Token ID428
Feature activation-9.37e-01

Pos logit contributions
hooting+2.833
HUD+2.783
advertisement+2.572
boarding+2.456
icide+2.419
Neg logit contributions
amins-3.008
ysis-2.836
-2.831
Thumbnail-2.668
-2.594
Token:
Token ID25
Feature activation-5.73e-01

Pos logit contributions
hooting+7.335
HUD+7.149
advertisement+6.645
icide+6.356
boarding+6.313
Neg logit contributions
amins-7.905
ysis-7.487
-7.400
Thumbnail-6.847
uty-6.786
Token Success
Token ID16282
Feature activation-4.55e-01

Pos logit contributions
hooting+4.437
HUD+4.379
advertisement+3.988
boarding+3.821
icide+3.802
Neg logit contributions
amins-5.161
ysis-4.860
-4.857
Thumbnail-4.642
isine-4.468
Token like
Token ID588
Feature activation-3.48e-01

Pos logit contributions
hooting+3.499
HUD+3.495
advertisement+3.126
boarding+3.037
icide+2.953
Neg logit contributions
amins-4.158
ysis-3.969
-3.888
Thumbnail-3.690
uty-3.638
Token Blackburn
Token ID42603
Feature activation-1.19e+00

Pos logit contributions
hooting+2.759
HUD+2.691
advertisement+2.483
boarding+2.399
icide+2.350
Neg logit contributions
amins-3.161
-2.963
ysis-2.937
Thumbnail-2.830
 sidx-2.756
Token's
Token ID338
Feature activation-8.95e-01

Pos logit contributions
hooting+8.660
HUD+8.617
advertisement+7.424
icide+7.396
horn+7.327
Neg logit contributions
amins-10.614
ysis-9.834
-9.707
isine-8.989
 sidx-8.971
Token,
Token ID11
Feature activation-2.03e-01

Pos logit contributions
hooting+6.561
HUD+6.362
advertisement+5.874
icide+5.552
boarding+5.545
Neg logit contributions
amins-8.120
-7.559
ysis-7.357
Thumbnail-7.280
endor-7.053
Token aided
Token ID28310
Feature activation-5.58e-01

Pos logit contributions
hooting+1.673
HUD+1.644
advertisement+1.507
boarding+1.435
icide+1.423
Neg logit contributions
amins-1.818
ysis-1.707
-1.701
Thumbnail-1.618
-1.577
Token by
Token ID416
Feature activation-7.24e-01

Pos logit contributions
hooting+3.817
HUD+3.670
advertisement+3.222
boarding+3.130
icide+3.106
Neg logit contributions
amins-5.638
ysis-5.347
-5.300
-5.056
Thumbnail-4.999
Token Jack
Token ID3619
Feature activation-1.31e-01

Pos logit contributions
hooting+5.475
HUD+5.374
advertisement+4.969
boarding+4.705
icide+4.662
Neg logit contributions
amins-6.491
-6.126
ysis-6.058
Thumbnail-5.866
endor-5.724