TOP ACTIVATIONS
MAX = 2.044

through the alleged victim , lured Mark over to a house
least . Some implanted devices can work very well
on May 25 . ( John McDonnell / The Washington Post
by REUTERS / John S omm ers II ) Ivanka Trump
that a good idea , especially a big one , requires
some respects and for some periods . By 1 , 000
against BJP MLA Narendra Me ht a s younger
CE 50 ( Ag reement number : 501 20 78 -
. <|endoftext|> E . S . Glover 's bird sey e
Massachusetts , the John J . Dug gan Middle School will
interviewing process : Interview preparation books are good ,
, for controlling thousands of RGB LEDs at video speeds .
classmates who wore small s omb rero hats to a te
Justice High School ( SO JO ), follows a similar mission
to clear the stack , followed by a return .
.: Boston police commissioner says number of fatalities is three ,
. Eng l . J . Med ., Peter Lur ie
lawyer during the George W . Bush administration , said there
in several initiatives . ( Nick Koz ak file photo for
find the email of a recru iter and send them a

MIN ACTIVATIONS
MIN = -2.673

Mer rick Garland to the Supreme Court . In March ,
s nomination to the Supreme Court . In brief ,
but related cases , the Supreme Court found that while the
elections . The Supreme Court s erroneous
just show up at the Supreme Court building and start working
filed . Whatever recon figured Supreme Court emerges after the November
on Aadhaar The Supreme Court of India has time
the first time that the Supreme Court was reported to hold
awareness about water scarcity , mis management and waste may pave
s , Judges of the supreme Court , and all other
stay while it asks the Supreme Court to hear its appeal
sound education ." Mis guided political effort
hash Gh ai , the Supreme Court today upheld the Bombay
the American economy and a Supreme Court remotely sympathetic to organized
elect justices on the Wisconsin supreme court majority that not only
all 50 states . The Supreme Court obviously didn 't want
. Whatever recon figured Supreme Court emerges after the November election
coincidence , natural occurrence or mis ident ification and the
compiling a list of possible Supreme Court nominees . It was
actions s ont enc ore obsc ures : les mut ins

INTERVAL 0.865 - 2.044
CONTAINS 1.689%

come in border cities , initially with the dispatch of tanks
bureau s many tech teams conduct its own investigation
then - Sea World CEO Jim At ch ison said in
( all pro - independence parties form a legislative majority of
promotional offers for programs that support The Nation s

INTERVAL -0.314 - 0.865
CONTAINS 78.722%

s a lot of anger , there s
s a brilliant writer . <|endoftext|> Another
inspired by the Three Fl oy ds - Half Ac re
Bel ieve me , Anna . If I want to get
the arguments against the comparison instead of , say , listing

INTERVAL -1.494 - -0.314
CONTAINS 19.547%

oad , April 18 th , 2017 Ko Do
water supply from the airport , however . The vast majority
real world projected onto their screen via their phone 's camera
Many states and individuals brought litigation against tobacco companies , which
, the brand army has rights to enter shops and business

INTERVAL -2.673 - -1.494
CONTAINS 0.042%

hash Gh ai , the Supreme Court today upheld the Bombay
of the state ," the bench said . The
Christmas in July " double - feature is July 26 and
s like if Vanilla Ice was slightly more gang ster
N . " special rapport eur " for the protection of
Token through
Token ID832
Feature activation-3.05e-01

Pos logit contributions
soever+2.111
 adversary+2.049
��+1.962
achine+1.908
anooga+1.840
Neg logit contributions
uid-2.973
-2.709
quote-2.598
í-2.489
 Ladies-2.406
Token the
Token ID262
Feature activation-7.63e-03

Pos logit contributions
uid+1.714
+1.531
quote+1.473
í+1.452
 Ladies+1.391
Neg logit contributions
soever-1.352
 adversary-1.302
��-1.280
achine-1.239
anooga-1.203
Token alleged
Token ID4260
Feature activation+5.47e-01

Pos logit contributions
uid+0.042
+0.038
quote+0.036
í+0.035
 Ladies+0.034
Neg logit contributions
soever-0.034
 adversary-0.034
��-0.032
achine-0.031
 Canaver-0.031
Token victim
Token ID3117
Feature activation-7.45e-02

Pos logit contributions
soever+2.256
 adversary+2.253
��+2.104
achine+2.004
 Canaver+1.971
Neg logit contributions
uid-3.203
-2.930
quote-2.755
í-2.683
 Ladies-2.572
Token,
Token ID11
Feature activation+4.87e-01

Pos logit contributions
uid+0.401
+0.358
quote+0.343
í+0.341
 Ladies+0.322
Neg logit contributions
soever-0.346
 adversary-0.334
��-0.329
achine-0.320
 Canaver-0.311
Token lured
Token ID41546
Feature activation+2.04e+00

Pos logit contributions
soever+2.086
 adversary+2.037
��+1.914
achine+1.887
anooga+1.841
Neg logit contributions
uid-2.765
-2.486
quote-2.381
í-2.293
 Ladies-2.211
Token Mark
Token ID2940
Feature activation+8.45e-01

Pos logit contributions
soever+7.823
 adversary+7.638
 intruder+6.957
��+6.894
achine+6.824
Neg logit contributions
uid-11.099
-10.214
quote-9.622
united-9.263
í-9.192
Token over
Token ID625
Feature activation+1.85e-01

Pos logit contributions
soever+3.320
 adversary+3.168
��+3.079
achine+3.016
anooga+2.899
Neg logit contributions
uid-5.057
-4.609
quote-4.419
í-4.288
 Ladies-4.165
Token to
Token ID284
Feature activation+3.12e-01

Pos logit contributions
soever+0.833
 adversary+0.804
��+0.790
achine+0.763
 Canaver+0.741
Neg logit contributions
uid-1.031
-0.920
quote-0.885
í-0.872
 Ladies-0.835
Token a
Token ID257
Feature activation+2.66e-01

Pos logit contributions
soever+1.357
 adversary+1.321
��+1.283
achine+1.250
 Canaver+1.207
Neg logit contributions
uid-1.756
-1.580
quote-1.512
í-1.480
 Ladies-1.420
Token house
Token ID2156
Feature activation+7.11e-01

Pos logit contributions
soever+1.087
 adversary+1.070
��+1.025
achine+0.992
anooga+0.968
Neg logit contributions
uid-1.566
-1.419
quote-1.348
í-1.325
 Ladies-1.263
Token least
Token ID1551
Feature activation+8.43e-01

Pos logit contributions
 adversary+0.885
soever+0.876
��+0.752
achine+0.716
 Canaver+0.649
Neg logit contributions
uid-3.643
-3.361
quote-3.230
í-3.166
united-3.088
Token.
Token ID13
Feature activation-4.48e-01

Pos logit contributions
soever+3.769
 adversary+3.648
��+3.581
achine+3.466
 Canaver+3.352
Neg logit contributions
uid-4.647
-4.156
quote-3.980
í-3.890
 Ladies-3.737
Token
Token ID564
Feature activation-4.67e-01

Pos logit contributions
uid+2.142
+1.881
quote+1.791
í+1.784
 Ladies+1.696
Neg logit contributions
soever-2.350
 adversary-2.317
��-2.265
achine-2.193
anooga-2.158
Token
Token ID250
Feature activation-2.24e-01

Pos logit contributions
uid+2.336
+2.062
quote+1.969
í+1.923
 Ladies+1.839
Neg logit contributions
soever-2.356
 adversary-2.289
��-2.252
achine-2.180
anooga-2.126
TokenSome
Token ID4366
Feature activation+4.67e-01

Pos logit contributions
uid+1.228
+1.098
quote+1.053
í+1.035
 Ladies+0.989
Neg logit contributions
soever-1.020
 adversary-0.989
��-0.967
achine-0.938
anooga-0.910
Token implanted
Token ID40740
Feature activation+2.03e+00

Pos logit contributions
soever+1.926
 adversary+1.875
��+1.811
achine+1.749
 Canaver+1.734
Neg logit contributions
uid-2.713
-2.459
quote-2.351
í-2.288
 Ladies-2.221
Token devices
Token ID4410
Feature activation+9.98e-01

Pos logit contributions
soever+8.127
 adversary+7.759
 Canaver+7.348
��+7.198
 decomp+7.050
Neg logit contributions
uid-10.641
-9.798
quote-9.404
united-8.784
í-8.728
Token can
Token ID460
Feature activation+4.61e-01

Pos logit contributions
soever+3.826
 adversary+3.685
achine+3.446
 Canaver+3.358
��+3.327
Neg logit contributions
uid-5.810
-5.406
quote-5.104
united-4.845
 Ladies-4.814
Token work
Token ID670
Feature activation+2.48e-03

Pos logit contributions
soever+1.851
 adversary+1.823
��+1.746
achine+1.728
anooga+1.643
Neg logit contributions
uid-2.707
-2.443
quote-2.356
í-2.262
 Ladies-2.240
Token very
Token ID845
Feature activation+5.06e-01

Pos logit contributions
soever+0.011
 adversary+0.010
��+0.010
achine+0.010
anooga+0.009
Neg logit contributions
uid-0.014
-0.013
quote-0.012
í-0.012
 Ladies-0.012
Token well
Token ID880
Feature activation+1.04e-01

Pos logit contributions
soever+1.852
 adversary+1.772
��+1.689
achine+1.657
 Canaver+1.589
Neg logit contributions
uid-3.233
-2.934
quote-2.831
í-2.760
 Ladies-2.677
Token on
Token ID319
Feature activation+1.77e-01

Pos logit contributions
soever+1.773
 adversary+1.714
��+1.666
achine+1.618
 Canaver+1.564
Neg logit contributions
uid-2.217
-1.983
quote-1.904
í-1.848
 Ladies-1.772
Token May
Token ID1737
Feature activation+4.91e-01

Pos logit contributions
soever+0.833
 adversary+0.811
��+0.788
achine+0.766
 Canaver+0.744
Neg logit contributions
uid-0.945
-0.843
quote-0.803
í-0.789
 Ladies-0.749
Token 25
Token ID1679
Feature activation-2.36e-01

Pos logit contributions
soever+1.756
 adversary+1.655
achine+1.519
 Canaver+1.517
��+1.488
Neg logit contributions
uid-3.118
-2.851
quote-2.679
í-2.588
united-2.579
Token.
Token ID13
Feature activation+3.33e-01

Pos logit contributions
uid+1.219
+1.085
quote+1.032
í+1.029
 Ladies+0.971
Neg logit contributions
soever-1.154
 adversary-1.113
��-1.092
achine-1.061
 Canaver-1.039
Token (
Token ID357
Feature activation+4.48e-01

Pos logit contributions
soever+1.687
 adversary+1.635
��+1.602
achine+1.564
 Canaver+1.522
Neg logit contributions
uid-1.648
-1.451
quote-1.381
í-1.349
 Ladies-1.283
TokenJohn
Token ID7554
Feature activation+1.97e+00

Pos logit contributions
soever+1.926
 adversary+1.860
��+1.819
achine+1.760
anooga+1.705
Neg logit contributions
uid-2.574
-2.313
quote-2.221
í-2.185
 Ladies-2.096
Token McDonnell
Token ID39441
Feature activation+4.79e-01

Pos logit contributions
 adversary+1.415
 Canaver+1.311
soever+1.283
achine+1.109
 McDonnell+0.965
Neg logit contributions
uid-16.478
-15.361
quote-14.596
united-14.239
nown-14.093
Token/
Token ID14
Feature activation+3.48e-01

Pos logit contributions
soever+1.829
 adversary+1.689
achine+1.611
 Canaver+1.599
��+1.562
Neg logit contributions
uid-2.920
-2.669
quote-2.502
í-2.419
united-2.397
TokenThe
Token ID464
Feature activation+5.26e-01

Pos logit contributions
soever+1.342
 adversary+1.270
��+1.214
achine+1.196
anooga+1.158
Neg logit contributions
uid-2.074
-1.852
quote-1.760
í-1.745
 Ladies-1.729
Token Washington
Token ID2669
Feature activation+6.90e-01

Pos logit contributions
soever+1.827
 adversary+1.791
achine+1.609
��+1.594
anooga+1.580
Neg logit contributions
uid-3.343
-3.058
quote-2.849
í-2.781
ú-2.672
Token Post
Token ID2947
Feature activation+6.55e-01

Pos logit contributions
soever+2.379
 adversary+2.299
 Canaver+2.087
achine+2.064
 weakness+2.004
Neg logit contributions
uid-4.367
-3.994
quote-3.653
í-3.589
united-3.514
Token by
Token ID416
Feature activation+3.04e-01

Pos logit contributions
soever+1.041
 adversary+1.006
��+0.977
achine+0.955
 Canaver+0.922
Neg logit contributions
uid-1.402
-1.264
quote-1.216
í-1.200
 Ladies-1.144
Token REUTERS
Token ID15862
Feature activation+5.63e-01

Pos logit contributions
soever+1.315
 adversary+1.274
��+1.245
achine+1.205
anooga+1.169
Neg logit contributions
uid-1.741
-1.562
quote-1.503
í-1.480
 Ladies-1.418
Token/
Token ID14
Feature activation+4.78e-01

Pos logit contributions
soever+2.508
 adversary+2.430
��+2.375
achine+2.297
anooga+2.242
Neg logit contributions
uid-3.162
-2.832
quote-2.727
í-2.675
 Ladies-2.568
TokenJohn
Token ID7554
Feature activation+1.55e+00

Pos logit contributions
soever+1.925
 adversary+1.838
��+1.811
achine+1.744
anooga+1.683
Neg logit contributions
uid-2.857
-2.581
quote-2.471
í-2.435
 Ladies-2.354
Token S
Token ID311
Feature activation+1.19e-01

Pos logit contributions
soever+6.795
��+6.403
 Canaver+6.303
 adversary+6.280
achine+6.219
Neg logit contributions
uid-7.948
-7.423
quote-6.910
í-6.421
united-6.398
Tokenomm
Token ID2002
Feature activation+1.92e+00

Pos logit contributions
soever+0.808
 adversary+0.791
��+0.779
achine+0.764
anooga+0.750
Neg logit contributions
uid-0.385
-0.314
quote-0.291
í-0.282
 Ladies-0.257
Tokeners
Token ID364
Feature activation+3.20e-01

Pos logit contributions
soever+6.102
achine+5.701
 adversary+5.515
anooga+5.189
��+4.944
Neg logit contributions
uid-11.649
-10.755
quote-10.375
united-10.190
 Ladies-9.784
Token II
Token ID2873
Feature activation+7.56e-01

Pos logit contributions
soever+1.239
 adversary+1.211
��+1.174
achine+1.123
anooga+1.098
Neg logit contributions
uid-1.982
-1.788
quote-1.726
í-1.708
 Ladies-1.643
Token)
Token ID8
Feature activation-1.62e-01

Pos logit contributions
soever+3.099
 adversary+2.988
��+2.919
achine+2.820
anooga+2.726
Neg logit contributions
uid-4.488
-4.048
quote-3.893
í-3.832
 Ladies-3.681
Token Ivanka
Token ID31002
Feature activation-7.33e-01

Pos logit contributions
uid+0.825
+0.731
quote+0.699
í+0.686
 Ladies+0.654
Neg logit contributions
soever-0.801
 adversary-0.778
��-0.764
achine-0.742
anooga-0.722
Token Trump
Token ID1301
Feature activation-1.70e-01

Pos logit contributions
uid+3.678
+3.337
í+3.304
quote+3.257
 Ladies+3.162
Neg logit contributions
soever-3.346
��-3.270
 adversary-3.268
achine-3.184
anooga-3.113
Token that
Token ID326
Feature activation-2.13e-01

Pos logit contributions
uid+1.511
+1.348
quote+1.291
í+1.271
 Ladies+1.216
Neg logit contributions
soever-1.301
 adversary-1.257
��-1.234
achine-1.198
anooga-1.164
Token a
Token ID257
Feature activation+2.69e-01

Pos logit contributions
uid+1.212
+1.089
quote+1.046
í+1.029
 Ladies+0.987
Neg logit contributions
soever-0.927
 adversary-0.895
��-0.879
achine-0.852
anooga-0.826
Token good
Token ID922
Feature activation+5.65e-01

Pos logit contributions
soever+1.121
 adversary+1.096
��+1.060
achine+1.016
anooga+0.987
Neg logit contributions
uid-1.571
-1.412
quote-1.357
í-1.333
 Ladies-1.279
Token idea
Token ID2126
Feature activation+5.73e-01

Pos logit contributions
soever+2.305
 adversary+2.295
��+2.178
achine+2.064
anooga+2.030
Neg logit contributions
uid-3.341
-3.012
quote-2.867
í-2.818
 Ladies-2.710
Token,
Token ID11
Feature activation+5.03e-01

Pos logit contributions
soever+2.220
 adversary+2.160
��+2.065
achine+1.987
anooga+1.924
Neg logit contributions
uid-3.513
-3.186
quote-3.062
í-2.979
 Ladies-2.898
Token especially
Token ID2592
Feature activation+1.90e+00

Pos logit contributions
soever+2.103
 adversary+2.059
��+1.945
achine+1.895
anooga+1.849
Neg logit contributions
uid-2.928
-2.649
quote-2.538
í-2.463
 Ladies-2.380
Token a
Token ID257
Feature activation+4.70e-01

Pos logit contributions
 adversary+6.891
soever+6.727
 weakness+5.911
 exemplary+5.856
achine+5.835
Neg logit contributions
uid-11.291
-10.109
quote-9.817
í-9.390
united-9.261
Token big
Token ID1263
Feature activation+7.33e-01

Pos logit contributions
soever+1.926
 adversary+1.899
��+1.799
achine+1.743
anooga+1.701
Neg logit contributions
uid-2.760
-2.486
quote-2.384
í-2.334
 Ladies-2.233
Token one
Token ID530
Feature activation+3.80e-01

Pos logit contributions
soever+2.880
 adversary+2.817
��+2.662
achine+2.578
anooga+2.529
Neg logit contributions
uid-4.425
-4.010
quote-3.843
í-3.761
 Ladies-3.637
Token,
Token ID11
Feature activation+8.31e-01

Pos logit contributions
soever+1.696
 adversary+1.639
��+1.606
achine+1.556
anooga+1.509
Neg logit contributions
uid-2.122
-1.900
quote-1.822
í-1.794
 Ladies-1.716
Token requires
Token ID4433
Feature activation+8.87e-01

Pos logit contributions
soever+2.991
 adversary+2.922
��+2.734
achine+2.647
anooga+2.563
Neg logit contributions
uid-5.247
-4.784
quote-4.613
í-4.428
 Ladies-4.344
Token some
Token ID617
Feature activation+5.01e-01

Pos logit contributions
uid+0.171
+0.153
quote+0.147
í+0.145
 Ladies+0.139
Neg logit contributions
soever-0.130
 adversary-0.125
��-0.123
achine-0.119
anooga-0.116
Token respects
Token ID19410
Feature activation+1.27e+00

Pos logit contributions
soever+1.886
 adversary+1.827
��+1.741
achine+1.693
 Canaver+1.630
Neg logit contributions
uid-3.145
-2.845
quote-2.736
í-2.686
 Ladies-2.591
Token and
Token ID290
Feature activation+6.12e-01

Pos logit contributions
soever+5.021
 adversary+4.799
��+4.562
achine+4.461
 Canaver+4.282
Neg logit contributions
uid-7.470
-6.618
quote-6.417
 Ladies-6.044
í-6.039
Token for
Token ID329
Feature activation+2.68e-01

Pos logit contributions
soever+2.522
 adversary+2.452
��+2.301
achine+2.250
 Canaver+2.205
Neg logit contributions
uid-3.632
-3.272
quote-3.124
í-3.051
 Ladies-2.946
Token some
Token ID617
Feature activation+9.26e-01

Pos logit contributions
soever+1.102
 adversary+1.067
��+1.034
achine+1.004
 Canaver+0.969
Neg logit contributions
uid-1.587
-1.438
quote-1.375
í-1.352
 Ladies-1.300
Token periods
Token ID9574
Feature activation+1.88e+00

Pos logit contributions
soever+3.830
 adversary+3.766
��+3.525
achine+3.434
 Canaver+3.321
Neg logit contributions
uid-5.378
-4.837
quote-4.640
í-4.505
 Ladies-4.344
Token.
Token ID13
Feature activation-2.62e-01

Pos logit contributions
soever+7.097
 adversary+6.797
achine+6.256
��+6.206
 Canaver+6.005
Neg logit contributions
uid-10.894
-9.681
quote-9.433
 Ladies-8.921
united-8.817
Token By
Token ID2750
Feature activation-1.58e-02

Pos logit contributions
uid+1.309
+1.155
quote+1.101
í+1.077
 Ladies+1.024
Neg logit contributions
soever-1.324
 adversary-1.283
��-1.257
achine-1.226
 Canaver-1.195
Token 1
Token ID352
Feature activation+1.06e-01

Pos logit contributions
uid+0.090
+0.081
quote+0.077
í+0.076
 Ladies+0.073
Neg logit contributions
soever-0.069
 adversary-0.066
��-0.065
achine-0.063
anooga-0.061
Token,
Token ID11
Feature activation-3.35e-01

Pos logit contributions
soever+0.629
 adversary+0.614
��+0.604
achine+0.590
 Canaver+0.576
Neg logit contributions
uid-0.437
-0.375
quote-0.355
í-0.344
 Ladies-0.324
Token000
Token ID830
Feature activation-4.57e-01

Pos logit contributions
uid+1.759
+1.569
quote+1.483
í+1.482
 Ladies+1.406
Neg logit contributions
soever-1.594
 adversary-1.553
��-1.516
achine-1.462
anooga-1.460
Token against
Token ID1028
Feature activation+3.21e-01

Pos logit contributions
soever+1.846
 adversary+1.815
��+1.711
achine+1.678
 Canaver+1.621
Neg logit contributions
uid-2.350
-2.094
quote-2.017
í-1.954
 Ladies-1.889
Token BJP
Token ID18317
Feature activation+3.06e-01

Pos logit contributions
soever+1.318
 adversary+1.278
��+1.229
achine+1.191
 Canaver+1.156
Neg logit contributions
uid-1.895
-1.720
quote-1.648
í-1.616
 Ladies-1.543
Token MLA
Token ID43265
Feature activation+2.63e-01

Pos logit contributions
soever+1.348
 adversary+1.308
��+1.253
achine+1.215
 Canaver+1.169
Neg logit contributions
uid-1.716
-1.541
quote-1.470
í-1.446
 Ladies-1.376
Token Narendra
Token ID28113
Feature activation+7.74e-01

Pos logit contributions
soever+1.164
 adversary+1.124
��+1.099
achine+1.064
 Canaver+1.032
Neg logit contributions
uid-1.476
-1.323
quote-1.269
í-1.247
 Ladies-1.193
Token Me
Token ID2185
Feature activation+8.21e-01

Pos logit contributions
soever+3.204
 adversary+3.011
��+2.929
achine+2.919
 Canaver+2.849
Neg logit contributions
uid-4.509
-4.108
quote-3.915
í-3.811
 Ladies-3.675
Tokenht
Token ID4352
Feature activation+1.86e+00

Pos logit contributions
soever+5.710
 adversary+5.575
achine+5.504
��+5.477
anooga+5.299
Neg logit contributions
uid-2.307
-2.022
quote-1.778
í-1.624
 Ladies-1.513
Tokena
Token ID64
Feature activation+5.75e-01

Pos logit contributions
soever+6.745
achine+6.738
 adversary+6.665
��+6.270
anooga+6.163
Neg logit contributions
uid-9.899
-9.843
quote-8.846
 Ladies-8.678
united-8.484
Token
Token ID447
Feature activation+5.60e-01

Pos logit contributions
soever+2.402
 adversary+2.321
��+2.260
achine+2.181
 Canaver+2.096
Neg logit contributions
uid-3.325
-3.003
quote-2.883
í-2.799
 Ladies-2.705
Token
Token ID247
Feature activation+2.98e-01

Pos logit contributions
soever+1.969
��+1.883
 adversary+1.883
achine+1.758
anooga+1.694
Neg logit contributions
uid-3.632
-3.312
quote-3.220
í-3.130
 Ladies-3.057
Tokens
Token ID82
Feature activation+1.73e-01

Pos logit contributions
soever+1.317
 adversary+1.274
��+1.242
achine+1.205
anooga+1.163
Neg logit contributions
uid-1.663
-1.493
quote-1.432
í-1.401
 Ladies-1.350
Token younger
Token ID7099
Feature activation-1.17e-01

Pos logit contributions
soever+0.771
 adversary+0.748
��+0.727
achine+0.705
 Canaver+0.682
Neg logit contributions
uid-0.968
-0.869
quote-0.831
í-0.817
 Ladies-0.781
Token CE
Token ID18671
Feature activation+3.69e-01

Pos logit contributions
soever+0.398
 adversary+0.385
��+0.376
achine+0.366
 Canaver+0.354
Neg logit contributions
uid-0.476
-0.427
quote-0.408
í-0.399
 Ladies-0.383
Token50
Token ID1120
Feature activation+9.51e-01

Pos logit contributions
soever+1.691
 adversary+1.644
��+1.599
achine+1.558
anooga+1.508
Neg logit contributions
uid-2.000
-1.796
quote-1.711
í-1.675
 Ladies-1.605
Token (
Token ID357
Feature activation+3.56e-01

Pos logit contributions
soever+4.142
 adversary+4.030
��+3.901
achine+3.832
 Canaver+3.718
Neg logit contributions
uid-5.167
-4.675
quote-4.459
í-4.325
 Ladies-4.160
TokenAg
Token ID10262
Feature activation+7.82e-01

Pos logit contributions
soever+1.736
 adversary+1.682
��+1.646
achine+1.611
 Canaver+1.560
Neg logit contributions
uid-1.817
-1.619
quote-1.534
í-1.508
 Ladies-1.448
Tokenreement
Token ID10237
Feature activation+5.56e-01

Pos logit contributions
soever+3.960
 adversary+3.854
��+3.772
achine+3.723
anooga+3.615
Neg logit contributions
uid-3.777
-3.432
quote-3.201
í-3.072
 Ladies-2.986
Token number
Token ID1271
Feature activation+1.84e+00

Pos logit contributions
soever+2.536
 adversary+2.466
��+2.394
achine+2.338
anooga+2.249
Neg logit contributions
uid-2.952
-2.713
quote-2.545
í-2.463
 Ladies-2.374
Token:
Token ID25
Feature activation+5.49e-01

Pos logit contributions
soever+7.974
 adversary+7.633
achine+7.154
��+7.092
 Canaver+7.075
Neg logit contributions
uid-9.046
-8.511
quote-7.726
united-7.409
í-7.375
Token 501
Token ID24555
Feature activation-2.46e-01

Pos logit contributions
soever+2.486
 adversary+2.411
��+2.333
achine+2.287
 Canaver+2.226
Neg logit contributions
uid-2.955
-2.684
quote-2.533
í-2.471
 Ladies-2.370
Token20
Token ID1238
Feature activation-5.49e-01

Pos logit contributions
uid+1.341
+1.193
quote+1.146
í+1.131
 Ladies+1.080
Neg logit contributions
soever-1.133
 adversary-1.094
��-1.070
achine-1.034
anooga-1.020
Token78
Token ID3695
Feature activation-6.77e-01

Pos logit contributions
uid+3.042
+2.706
quote+2.602
í+2.579
 Ladies+2.467
Neg logit contributions
soever-2.480
 adversary-2.378
��-2.356
anooga-2.249
achine-2.236
Token-
Token ID12
Feature activation-1.37e-02

Pos logit contributions
uid+3.823
+3.394
quote+3.276
í+3.258
 Ladies+3.103
Neg logit contributions
soever-2.966
 adversary-2.839
��-2.816
anooga-2.683
achine-2.658
Token.
Token ID13
Feature activation+8.06e-03

Pos logit contributions
uid+1.190
+1.066
quote+1.022
í+1.007
 Ladies+0.963
Neg logit contributions
soever-0.951
 adversary-0.920
��-0.903
achine-0.874
anooga-0.848
Token<|endoftext|>
Token ID50256
Feature activation+4.69e-01

Pos logit contributions
soever+0.041
 adversary+0.040
��+0.039
achine+0.038
anooga+0.037
Neg logit contributions
uid-0.040
-0.035
quote-0.033
í-0.033
 Ladies-0.031
TokenE
Token ID36
Feature activation+1.81e-01

Pos logit contributions
soever+2.159
 adversary+2.084
��+2.046
achine+1.987
anooga+1.930
Neg logit contributions
uid-2.509
-2.245
quote-2.126
í-2.104
 Ladies-2.025
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
soever+0.964
 adversary+0.938
��+0.921
achine+0.897
anooga+0.875
Neg logit contributions
uid-0.856
-0.750
quote-0.713
í-0.698
 Ladies-0.662
TokenS
Token ID50
Feature activation+1.07e-01

Pos logit contributions
soever+4.326
 adversary+4.197
��+4.072
achine+3.969
 Canaver+3.865
Neg logit contributions
uid-5.725
-5.140
quote-4.913
í-4.808
united-4.588
Token.
Token ID13
Feature activation+1.82e+00

Pos logit contributions
soever+0.520
 adversary+0.509
��+0.499
achine+0.478
anooga+0.468
Neg logit contributions
uid-0.558
-0.490
quote-0.469
í-0.467
 Ladies-0.439
Token Glover
Token ID43487
Feature activation+1.52e-02

Pos logit contributions
soever+7.856
 adversary+7.835
achine+7.554
��+7.505
 Canaver+7.330
Neg logit contributions
uid-9.326
-8.283
quote-7.885
í-7.616
united-7.349
Token's
Token ID338
Feature activation+1.37e-01

Pos logit contributions
soever+0.069
 adversary+0.067
��+0.065
achine+0.063
anooga+0.061
Neg logit contributions
uid-0.084
-0.075
quote-0.072
í-0.071
 Ladies-0.068
Token bird
Token ID6512
Feature activation+3.47e-01

Pos logit contributions
soever+0.627
 adversary+0.607
��+0.595
achine+0.577
anooga+0.560
Neg logit contributions
uid-0.745
-0.665
quote-0.637
í-0.626
 Ladies-0.599
Tokensey
Token ID4397
Feature activation+5.24e-01

Pos logit contributions
soever+1.581
 adversary+1.533
��+1.497
achine+1.453
anooga+1.410
Neg logit contributions
uid-1.900
-1.699
quote-1.626
í-1.597
 Ladies-1.529
Tokene
Token ID68
Feature activation+8.18e-02

Pos logit contributions
soever+2.566
 adversary+2.488
��+2.431
achine+2.370
 Canaver+2.298
Neg logit contributions
uid-2.690
-2.394
quote-2.281
í-2.236
 Ladies-2.133
Token Massachusetts
Token ID10140
Feature activation-9.93e-01

Pos logit contributions
uid+0.874
+0.779
quote+0.747
í+0.733
 Ladies+0.702
Neg logit contributions
soever-0.758
 adversary-0.732
��-0.718
achine-0.696
anooga-0.676
Token,
Token ID11
Feature activation-1.69e-01

Pos logit contributions
uid+4.898
+4.485
í+4.201
quote+4.185
 Ladies+4.030
Neg logit contributions
soever-4.745
��-4.689
 adversary-4.636
achine-4.439
 Canaver-4.414
Token the
Token ID262
Feature activation+1.03e-02

Pos logit contributions
uid+0.963
+0.865
quote+0.830
í+0.817
 Ladies+0.783
Neg logit contributions
soever-0.734
 adversary-0.709
��-0.693
achine-0.671
anooga-0.650
Token John
Token ID1757
Feature activation+9.25e-01

Pos logit contributions
soever+0.046
 adversary+0.045
��+0.043
achine+0.042
anooga+0.041
Neg logit contributions
uid-0.057
-0.051
quote-0.049
í-0.048
 Ladies-0.046
Token J
Token ID449
Feature activation+1.30e+00

Pos logit contributions
soever+4.234
 adversary+4.091
��+3.973
achine+3.920
anooga+3.774
Neg logit contributions
uid-5.016
-4.447
quote-4.275
í-4.151
 Ladies-3.959
Token.
Token ID13
Feature activation+1.81e+00

Pos logit contributions
soever+5.468
 adversary+5.340
��+5.168
achine+5.141
anooga+4.953
Neg logit contributions
uid-7.053
-6.587
quote-6.242
í-5.987
 Ladies-5.810
Token Dug
Token ID27436
Feature activation+1.29e+00

Pos logit contributions
soever+7.414
 adversary+7.316
achine+7.115
��+6.921
 Canaver+6.816
Neg logit contributions
uid-9.801
-8.717
quote-8.455
í-7.999
 Ladies-7.727
Tokengan
Token ID1030
Feature activation+6.84e-02

Pos logit contributions
soever+8.107
 adversary+7.792
achine+7.637
��+7.508
anooga+7.456
Neg logit contributions
uid-3.965
-3.935
quote-3.481
í-3.178
 Ladies-3.128
Token Middle
Token ID6046
Feature activation-9.39e-01

Pos logit contributions
soever+0.339
 adversary+0.329
��+0.324
achine+0.314
anooga+0.306
Neg logit contributions
uid-0.347
-0.307
quote-0.293
í-0.288
 Ladies-0.275
Token School
Token ID3961
Feature activation+1.99e-03

Pos logit contributions
uid+3.829
+3.261
quote+3.138
í+3.126
 Ladies+3.036
Neg logit contributions
soever-5.310
 adversary-5.159
��-5.136
 Canaver-5.032
achine-5.021
Token will
Token ID481
Feature activation-2.27e-01

Pos logit contributions
soever+0.009
 adversary+0.009
��+0.009
achine+0.008
anooga+0.008
Neg logit contributions
uid-0.011
-0.010
quote-0.009
í-0.009
 Ladies-0.009
Token interviewing
Token ID31481
Feature activation+1.02e+00

Pos logit contributions
uid+2.133
+1.928
quote+1.872
í+1.848
 Ladies+1.771
Neg logit contributions
soever-1.419
 adversary-1.356
��-1.329
achine-1.286
 Canaver-1.252
Token process
Token ID1429
Feature activation+3.60e-01

Pos logit contributions
soever+3.988
 adversary+3.885
��+3.687
achine+3.629
 Canaver+3.488
Neg logit contributions
uid-6.087
-5.504
quote-5.223
í-5.079
united-4.922
Token:
Token ID25
Feature activation+1.08e-01

Pos logit contributions
soever+1.619
 adversary+1.565
��+1.531
achine+1.487
anooga+1.443
Neg logit contributions
uid-1.993
-1.783
quote-1.707
í-1.677
 Ladies-1.606
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
soever+0.554
 adversary+0.537
��+0.528
achine+0.513
 Canaver+0.501
Neg logit contributions
uid-0.528
-0.465
quote-0.445
í-0.436
 Ladies-0.415
Token
Token ID198
Feature activation+3.38e-02

Pos logit contributions
uid+0.550
+0.495
quote+0.465
í+0.450
 Ladies+0.441
Neg logit contributions
soever-0.458
 adversary-0.444
achine-0.429
��-0.413
 Canaver-0.407
TokenInterview
Token ID39945
Feature activation+1.80e+00

Pos logit contributions
soever+0.157
 adversary+0.152
��+0.149
achine+0.145
 Canaver+0.141
Neg logit contributions
uid-0.183
-0.163
quote-0.156
í-0.153
 Ladies-0.146
Token preparation
Token ID11824
Feature activation+3.14e-01

Pos logit contributions
 adversary+7.519
soever+7.500
��+7.163
achine+7.012
anooga+7.006
Neg logit contributions
uid-9.437
-8.626
quote-7.845
í-7.803
united-7.609
Token books
Token ID3835
Feature activation+1.03e-01

Pos logit contributions
soever+1.212
 adversary+1.174
��+1.130
achine+1.100
anooga+1.055
Neg logit contributions
uid-1.935
-1.763
quote-1.683
í-1.655
 Ladies-1.596
Token are
Token ID389
Feature activation-1.08e-02

Pos logit contributions
soever+0.449
 adversary+0.435
��+0.423
achine+0.412
anooga+0.397
Neg logit contributions
uid-0.583
-0.526
quote-0.502
í-0.492
 Ladies-0.473
Token good
Token ID922
Feature activation-7.37e-02

Pos logit contributions
uid+0.064
+0.057
quote+0.055
í+0.054
 Ladies+0.052
Neg logit contributions
soever-0.045
 adversary-0.043
��-0.042
achine-0.041
 Canaver-0.039
Token,
Token ID11
Feature activation+2.76e-01

Pos logit contributions
uid+0.415
+0.372
quote+0.356
í+0.351
 Ladies+0.336
Neg logit contributions
soever-0.325
 adversary-0.314
��-0.308
achine-0.298
anooga-0.289
Token,
Token ID11
Feature activation+3.36e-01

Pos logit contributions
uid+1.280
+1.143
quote+1.100
í+1.083
 Ladies+1.038
Neg logit contributions
soever-1.015
 adversary-0.972
��-0.953
achine-0.919
anooga-0.904
Token for
Token ID329
Feature activation+5.08e-01

Pos logit contributions
soever+1.363
 adversary+1.326
��+1.289
achine+1.252
 Canaver+1.204
Neg logit contributions
uid-1.995
-1.802
quote-1.734
í-1.699
 Ladies-1.630
Token controlling
Token ID12755
Feature activation+4.73e-01

Pos logit contributions
soever+1.926
 adversary+1.891
��+1.824
achine+1.773
 Canaver+1.695
Neg logit contributions
uid-3.129
-2.857
quote-2.728
í-2.684
 Ladies-2.566
Token thousands
Token ID4138
Feature activation+1.28e-01

Pos logit contributions
soever+1.960
 adversary+1.915
��+1.839
achine+1.807
 Canaver+1.737
Neg logit contributions
uid-2.761
-2.509
quote-2.393
í-2.354
 Ladies-2.244
Token of
Token ID286
Feature activation-7.02e-01

Pos logit contributions
soever+0.614
 adversary+0.593
��+0.586
achine+0.561
 Canaver+0.553
Neg logit contributions
uid-0.675
-0.598
quote-0.569
í-0.563
 Ladies-0.532
Token RGB
Token ID25228
Feature activation+1.80e+00

Pos logit contributions
uid+4.087
+3.639
quote+3.534
í+3.495
 Ladies+3.385
Neg logit contributions
soever-2.924
��-2.778
 adversary-2.746
achine-2.616
anooga-2.596
Token LEDs
Token ID33697
Feature activation+1.13e+00

Pos logit contributions
soever+6.150
 adversary+6.021
achine+5.915
��+5.615
 decomp+5.389
Neg logit contributions
uid-10.729
-10.013
quote-9.516
í-9.112
united-8.869
Token at
Token ID379
Feature activation+3.07e-01

Pos logit contributions
soever+4.484
 adversary+4.292
achine+4.183
��+4.008
 Canaver+3.866
Neg logit contributions
uid-6.450
-5.957
quote-5.721
í-5.469
 Ladies-5.333
Token video
Token ID2008
Feature activation+2.98e-01

Pos logit contributions
soever+1.298
 adversary+1.263
��+1.227
achine+1.191
 Canaver+1.150
Neg logit contributions
uid-1.776
-1.604
quote-1.537
í-1.506
 Ladies-1.446
Token speeds
Token ID12055
Feature activation+5.13e-01

Pos logit contributions
soever+1.243
 adversary+1.197
��+1.172
achine+1.131
anooga+1.095
Neg logit contributions
uid-1.752
-1.577
quote-1.518
í-1.495
 Ladies-1.433
Token.
Token ID13
Feature activation+3.06e-01

Pos logit contributions
soever+2.150
 adversary+2.081
��+2.011
achine+1.966
 Canaver+1.877
Neg logit contributions
uid-2.968
-2.699
quote-2.571
í-2.514
 Ladies-2.425
Token classmates
Token ID28999
Feature activation+1.19e-01

Pos logit contributions
uid+0.176
+0.158
quote+0.152
í+0.150
 Ladies+0.144
Neg logit contributions
soever-0.129
 adversary-0.124
��-0.123
achine-0.118
anooga-0.115
Token who
Token ID508
Feature activation+5.08e-01

Pos logit contributions
soever+0.514
 adversary+0.496
��+0.482
achine+0.468
 Canaver+0.452
Neg logit contributions
uid-0.682
-0.611
quote-0.588
í-0.573
 Ladies-0.554
Token wore
Token ID12408
Feature activation+1.03e-02

Pos logit contributions
soever+2.298
 adversary+2.219
��+2.087
achine+2.070
 Canaver+2.011
Neg logit contributions
uid-2.796
-2.495
quote-2.380
í-2.288
 Ladies-2.241
Token small
Token ID1402
Feature activation+2.84e-01

Pos logit contributions
soever+0.046
 adversary+0.044
��+0.043
achine+0.042
anooga+0.041
Neg logit contributions
uid-0.058
-0.052
quote-0.050
í-0.049
 Ladies-0.047
Token s
Token ID264
Feature activation-9.74e-01

Pos logit contributions
soever+1.249
 adversary+1.212
��+1.184
achine+1.147
anooga+1.111
Neg logit contributions
uid-1.598
-1.431
quote-1.371
í-1.348
 Ladies-1.289
Tokenomb
Token ID2381
Feature activation+1.80e+00

Pos logit contributions
uid+5.237
+4.540
í+4.495
quote+4.426
 Ladies+4.189
Neg logit contributions
soever-4.497
 adversary-4.427
��-4.322
anooga-4.160
achine-4.095
Tokenrero
Token ID34785
Feature activation-1.83e-01

Pos logit contributions
soever+7.663
 adversary+7.309
achine+7.069
��+6.862
anooga+6.690
Neg logit contributions
uid-8.940
-8.583
quote-7.662
 Ladies-7.391
í-7.344
Token hats
Token ID23910
Feature activation-1.86e-01

Pos logit contributions
uid+0.960
+0.856
quote+0.819
í+0.811
 Ladies+0.773
Neg logit contributions
soever-0.872
 adversary-0.843
��-0.832
achine-0.807
anooga-0.786
Token to
Token ID284
Feature activation+2.17e-01

Pos logit contributions
uid+1.032
+0.924
quote+0.885
í+0.873
 Ladies+0.834
Neg logit contributions
soever-0.835
 adversary-0.808
��-0.793
achine-0.767
anooga-0.745
Token a
Token ID257
Feature activation+2.60e-02

Pos logit contributions
soever+0.966
 adversary+0.942
��+0.915
achine+0.889
 Canaver+0.858
Neg logit contributions
uid-1.206
-1.081
quote-1.033
í-1.012
 Ladies-0.968
Token te
Token ID573
Feature activation+8.42e-01

Pos logit contributions
soever+0.118
 adversary+0.115
��+0.112
achine+0.109
anooga+0.105
Neg logit contributions
uid-0.142
-0.127
quote-0.121
í-0.119
 Ladies-0.114
Token Justice
Token ID4796
Feature activation+2.72e-02

Pos logit contributions
uid+0.257
+0.232
quote+0.219
í+0.219
 Ladies+0.211
Neg logit contributions
soever-0.220
 adversary-0.211
��-0.209
achine-0.199
 Canaver-0.194
Token High
Token ID3334
Feature activation-2.31e-01

Pos logit contributions
soever+0.131
 adversary+0.126
��+0.124
achine+0.120
anooga+0.117
Neg logit contributions
uid-0.143
-0.127
quote-0.121
í-0.119
 Ladies-0.114
Token School
Token ID3961
Feature activation+4.65e-02

Pos logit contributions
uid+1.079
+0.935
quote+0.900
í+0.881
 Ladies+0.843
Neg logit contributions
soever-1.241
 adversary-1.202
��-1.181
achine-1.157
 Canaver-1.130
Token (
Token ID357
Feature activation+6.74e-01

Pos logit contributions
soever+0.204
 adversary+0.197
��+0.192
achine+0.187
anooga+0.181
Neg logit contributions
uid-0.263
-0.236
quote-0.226
í-0.222
 Ladies-0.213
TokenSO
Token ID15821
Feature activation+8.73e-01

Pos logit contributions
soever+3.037
 adversary+2.947
��+2.889
achine+2.835
anooga+2.738
Neg logit contributions
uid-3.640
-3.225
quote-3.084
í-3.047
 Ladies-2.932
TokenJO
Token ID45006
Feature activation+1.79e+00

Pos logit contributions
soever+3.120
 adversary+3.041
��+2.924
achine+2.881
anooga+2.748
Neg logit contributions
uid-5.520
-4.993
quote-4.835
í-4.728
 Ladies-4.546
Token),
Token ID828
Feature activation+5.37e-01

Pos logit contributions
 adversary+5.548
soever+5.424
��+5.220
achine+5.151
anooga+4.780
Neg logit contributions
uid-11.400
-10.308
quote-10.073
í-9.704
united-9.323
Token follows
Token ID5679
Feature activation+1.23e+00

Pos logit contributions
soever+2.200
 adversary+2.163
��+2.071
achine+2.035
anooga+1.959
Neg logit contributions
uid-3.110
-2.824
quote-2.709
í-2.639
 Ladies-2.501
Token a
Token ID257
Feature activation+4.88e-01

Pos logit contributions
soever+4.988
 adversary+4.894
��+4.671
achine+4.623
 Canaver+4.402
Neg logit contributions
uid-6.929
-6.335
quote-6.023
í-5.894
 Ladies-5.590
Token similar
Token ID2092
Feature activation+4.00e-01

Pos logit contributions
soever+1.983
 adversary+1.960
��+1.874
achine+1.816
 Canaver+1.757
Neg logit contributions
uid-2.867
-2.580
quote-2.466
í-2.420
 Ladies-2.309
Token mission
Token ID4365
Feature activation-3.76e-01

Pos logit contributions
soever+1.548
 adversary+1.525
��+1.445
achine+1.403
 Canaver+1.356
Neg logit contributions
uid-2.460
-2.228
quote-2.127
í-2.088
 Ladies-2.005
Token to
Token ID284
Feature activation+1.39e-01

Pos logit contributions
soever+1.199
 adversary+1.170
��+1.122
achine+1.101
 Canaver+1.057
Neg logit contributions
uid-1.655
-1.510
quote-1.434
í-1.410
 Ladies-1.362
Token clear
Token ID1598
Feature activation+1.58e-01

Pos logit contributions
soever+0.599
 adversary+0.595
��+0.559
achine+0.555
 Canaver+0.532
Neg logit contributions
uid-0.783
-0.712
quote-0.671
í-0.659
 Ladies-0.638
Token the
Token ID262
Feature activation+3.82e-01

Pos logit contributions
soever+0.689
 adversary+0.670
��+0.651
achine+0.632
anooga+0.609
Neg logit contributions
uid-0.892
-0.807
quote-0.770
í-0.758
 Ladies-0.727
Token stack
Token ID8931
Feature activation-5.51e-02

Pos logit contributions
soever+1.471
 adversary+1.466
��+1.392
achine+1.338
 Canaver+1.279
Neg logit contributions
uid-2.324
-2.131
quote-2.019
í-2.000
 Ladies-1.924
Token,
Token ID11
Feature activation+3.55e-01

Pos logit contributions
uid+0.312
+0.282
quote+0.268
í+0.265
 Ladies+0.254
Neg logit contributions
soever-0.240
 adversary-0.233
��-0.227
achine-0.220
 Canaver-0.213
Token followed
Token ID3940
Feature activation+1.78e+00

Pos logit contributions
soever+1.409
 adversary+1.375
��+1.319
achine+1.284
 Canaver+1.235
Neg logit contributions
uid-2.128
-1.941
quote-1.851
í-1.815
 Ladies-1.754
Token by
Token ID416
Feature activation+1.09e+00

Pos logit contributions
soever+6.045
 adversary+5.802
��+5.581
achine+5.453
anooga+5.189
Neg logit contributions
uid-11.241
-10.439
quote-9.942
í-9.720
 Ladies-9.482
Token a
Token ID257
Feature activation+1.65e-01

Pos logit contributions
soever+4.439
 adversary+4.432
��+4.230
achine+4.038
 decomp+3.991
Neg logit contributions
uid-6.110
-5.620
quote-5.251
í-5.188
united-5.078
Token return
Token ID1441
Feature activation+4.32e-01

Pos logit contributions
soever+0.732
 adversary+0.713
��+0.696
achine+0.670
anooga+0.650
Neg logit contributions
uid-0.920
-0.828
quote-0.788
í-0.777
 Ladies-0.743
Token.
Token ID13
Feature activation+3.45e-01

Pos logit contributions
soever+1.756
 adversary+1.717
��+1.659
achine+1.591
anooga+1.529
Neg logit contributions
uid-2.529
-2.334
quote-2.189
í-2.176
 Ladies-2.089
Token
Token ID198
Feature activation+6.19e-02

Pos logit contributions
soever+1.678
 adversary+1.637
��+1.568
achine+1.532
 Canaver+1.503
Neg logit contributions
uid-1.741
-1.583
quote-1.457
í-1.450
united-1.384
Token.:
Token ID11207
Feature activation+7.28e-02

Pos logit contributions
soever+3.030
 adversary+2.944
��+2.900
achine+2.805
 Canaver+2.768
Neg logit contributions
uid-2.308
-1.995
quote-1.890
í-1.853
 Ladies-1.735
Token Boston
Token ID6182
Feature activation-1.33e-01

Pos logit contributions
soever+0.356
 adversary+0.345
��+0.338
achine+0.329
 Canaver+0.320
Neg logit contributions
uid-0.374
-0.331
quote-0.316
í-0.310
 Ladies-0.295
Token police
Token ID1644
Feature activation-2.06e-01

Pos logit contributions
uid+0.660
+0.586
quote+0.556
í+0.552
 Ladies+0.528
Neg logit contributions
soever-0.669
 adversary-0.648
��-0.640
achine-0.620
 Canaver-0.607
Token commissioner
Token ID16248
Feature activation+1.38e-01

Pos logit contributions
uid+1.114
+0.995
quote+0.952
í+0.931
 Ladies+0.893
Neg logit contributions
soever-0.951
 adversary-0.924
��-0.900
achine-0.875
anooga-0.849
Token says
Token ID1139
Feature activation+2.93e-01

Pos logit contributions
soever+0.625
 adversary+0.603
��+0.596
achine+0.575
anooga+0.561
Neg logit contributions
uid-0.764
-0.684
quote-0.653
í-0.649
 Ladies-0.623
Token number
Token ID1271
Feature activation+1.78e+00

Pos logit contributions
soever+1.219
 adversary+1.178
��+1.140
achine+1.101
 Canaver+1.070
Neg logit contributions
uid-1.722
-1.550
quote-1.489
í-1.458
 Ladies-1.403
Token of
Token ID286
Feature activation+1.18e-01

Pos logit contributions
soever+6.749
 adversary+6.720
��+6.153
 Canaver+5.970
anooga+5.960
Neg logit contributions
uid-10.242
-9.293
quote-9.003
í-8.599
 Ladies-8.500
Token fatalities
Token ID30091
Feature activation+4.22e-01

Pos logit contributions
soever+0.442
 adversary+0.426
��+0.413
achine+0.398
anooga+0.383
Neg logit contributions
uid-0.742
-0.674
quote-0.649
í-0.638
 Ladies-0.614
Token is
Token ID318
Feature activation+2.41e-01

Pos logit contributions
soever+1.630
 adversary+1.567
��+1.475
achine+1.447
 Canaver+1.403
Neg logit contributions
uid-2.612
-2.374
quote-2.285
í-2.220
 Ladies-2.153
Token three
Token ID1115
Feature activation+3.84e-01

Pos logit contributions
soever+1.019
 adversary+0.995
��+0.953
achine+0.928
 Canaver+0.902
Neg logit contributions
uid-1.390
-1.258
quote-1.204
í-1.173
 Ladies-1.129
Token,
Token ID11
Feature activation+3.35e-01

Pos logit contributions
soever+1.695
 adversary+1.642
��+1.604
achine+1.554
 Canaver+1.503
Neg logit contributions
uid-2.150
-1.928
quote-1.849
í-1.813
 Ladies-1.739
Token.
Token ID13
Feature activation+6.66e-01

Pos logit contributions
soever+1.630
 adversary+1.588
��+1.547
achine+1.525
anooga+1.467
Neg logit contributions
uid-1.666
-1.482
quote-1.431
í-1.372
 Ladies-1.319
Token Eng
Token ID1985
Feature activation+9.25e-01

Pos logit contributions
soever+3.228
 adversary+3.188
��+3.106
achine+3.073
 Canaver+2.953
Neg logit contributions
uid-3.368
-2.962
quote-2.846
í-2.756
 Ladies-2.633
Tokenl
Token ID75
Feature activation+1.45e+00

Pos logit contributions
soever+4.483
 adversary+4.338
��+4.016
 Canaver+3.966
achine+3.943
Neg logit contributions
uid-4.553
-4.255
quote-3.823
í-3.718
united-3.621
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
soever+5.053
 adversary+4.958
achine+4.357
 weakness+4.342
anooga+4.235
Neg logit contributions
uid-8.684
-8.230
quote-7.721
united-7.261
 Ladies-7.232
Token J
Token ID449
Feature activation+7.66e-01

Pos logit contributions
 adversary+3.242
soever+3.239
��+2.936
 Canaver+2.826
achine+2.824
Neg logit contributions
uid-7.646
-7.142
quote-6.863
í-6.543
united-6.449
Token.
Token ID13
Feature activation+1.78e+00

Pos logit contributions
 adversary+2.940
soever+2.909
achine+2.723
��+2.670
 Canaver+2.577
Neg logit contributions
uid-4.473
-4.166
quote-3.973
í-3.831
united-3.703
Token Med
Token ID2019
Feature activation+6.16e-01

Pos logit contributions
 adversary+5.475
soever+5.355
��+4.939
achine+4.612
 decomp+4.593
Neg logit contributions
uid-11.316
-10.373
quote-10.043
í-9.565
tta-9.338
Token.,
Token ID1539
Feature activation+5.48e-01

Pos logit contributions
soever+2.738
 adversary+2.647
��+2.589
achine+2.509
anooga+2.433
Neg logit contributions
uid-3.441
-3.084
quote-2.958
í-2.906
 Ladies-2.782
Token Peter
Token ID5613
Feature activation+8.38e-01

Pos logit contributions
soever+2.412
 adversary+2.342
��+2.266
achine+2.193
 Canaver+2.159
Neg logit contributions
uid-3.070
-2.755
quote-2.635
í-2.583
 Ladies-2.466
Token Lur
Token ID47851
Feature activation+7.31e-01

Pos logit contributions
soever+3.583
 adversary+3.446
��+3.377
achine+3.302
 Canaver+3.263
Neg logit contributions
uid-4.733
-4.291
quote-4.095
í-3.960
united-3.802
Tokenie
Token ID494
Feature activation+4.89e-01

Pos logit contributions
soever+3.775
 adversary+3.671
��+3.583
achine+3.545
anooga+3.426
Neg logit contributions
uid-3.373
-3.082
quote-2.860
í-2.687
 Ladies-2.658
Token lawyer
Token ID6853
Feature activation-2.81e-01

Pos logit contributions
soever+0.814
 adversary+0.779
��+0.772
achine+0.753
 Canaver+0.734
Neg logit contributions
uid-0.815
-0.718
quote-0.690
í-0.679
 Ladies-0.642
Token during
Token ID1141
Feature activation-7.82e-02

Pos logit contributions
uid+1.496
+1.335
í+1.277
quote+1.271
 Ladies+1.208
Neg logit contributions
soever-1.325
 adversary-1.256
��-1.248
achine-1.214
 Canaver-1.191
Token the
Token ID262
Feature activation+1.81e-01

Pos logit contributions
uid+0.422
+0.369
quote+0.360
í+0.355
 Ladies+0.339
Neg logit contributions
soever-0.366
 adversary-0.350
��-0.345
achine-0.336
 Canaver-0.329
Token George
Token ID4502
Feature activation+1.67e-01

Pos logit contributions
soever+0.722
 adversary+0.690
��+0.677
achine+0.653
anooga+0.632
Neg logit contributions
uid-1.098
-0.988
quote-0.955
í-0.941
 Ladies-0.906
Token W
Token ID370
Feature activation+4.13e-01

Pos logit contributions
soever+0.679
 adversary+0.651
��+0.641
achine+0.622
 Canaver+0.603
Neg logit contributions
uid-0.990
-0.892
quote-0.863
í-0.856
 Ladies-0.823
Token.
Token ID13
Feature activation+1.77e+00

Pos logit contributions
soever+1.644
 adversary+1.621
achine+1.515
��+1.479
anooga+1.431
Neg logit contributions
uid-2.398
-2.254
quote-2.088
í-2.006
 Ladies-1.985
Token Bush
Token ID5511
Feature activation+4.55e-03

Pos logit contributions
 adversary+2.891
soever+2.592
achine+2.388
 Canaver+2.252
 weakness+2.180
Neg logit contributions
uid-13.716
-12.728
quote-12.263
nown-11.666
role-11.605
Token administration
Token ID3662
Feature activation-5.68e-01

Pos logit contributions
soever+0.018
 adversary+0.017
��+0.017
achine+0.016
 Canaver+0.016
Neg logit contributions
uid-0.028
-0.025
quote-0.024
í-0.024
 Ladies-0.023
Token,
Token ID11
Feature activation+1.29e-01

Pos logit contributions
uid+2.865
+2.537
í+2.451
quote+2.404
 Ladies+2.294
Neg logit contributions
soever-2.837
��-2.676
 adversary-2.665
achine-2.581
 Canaver-2.573
Token said
Token ID531
Feature activation+1.76e-01

Pos logit contributions
soever+0.583
 adversary+0.563
��+0.553
achine+0.535
anooga+0.519
Neg logit contributions
uid-0.715
-0.639
quote-0.613
í-0.603
 Ladies-0.577
Token there
Token ID612
Feature activation+6.05e-02

Pos logit contributions
soever+0.783
 adversary+0.759
��+0.737
achine+0.711
 Canaver+0.694
Neg logit contributions
uid-0.987
-0.886
quote-0.843
í-0.829
 Ladies-0.793
Token in
Token ID287
Feature activation-1.40e-02

Pos logit contributions
soever+2.717
 adversary+2.640
��+2.590
achine+2.514
anooga+2.440
Neg logit contributions
uid-2.942
-2.628
quote-2.501
í-2.473
 Ladies-2.345
Token several
Token ID1811
Feature activation+1.89e-01

Pos logit contributions
uid+0.081
+0.073
quote+0.071
í+0.069
 Ladies+0.067
Neg logit contributions
soever-0.059
 adversary-0.057
��-0.056
achine-0.054
anooga-0.052
Token initiatives
Token ID15446
Feature activation+1.62e-01

Pos logit contributions
soever+0.789
 adversary+0.768
��+0.739
achine+0.717
 Canaver+0.693
Neg logit contributions
uid-1.105
-0.996
quote-0.954
í-0.937
 Ladies-0.897
Token.
Token ID13
Feature activation+3.15e-01

Pos logit contributions
soever+0.692
 adversary+0.670
��+0.649
achine+0.632
anooga+0.610
Neg logit contributions
uid-0.932
-0.836
quote-0.805
í-0.786
 Ladies-0.757
Token (
Token ID357
Feature activation+4.21e-01

Pos logit contributions
soever+1.596
 adversary+1.548
��+1.509
achine+1.482
 Canaver+1.435
Neg logit contributions
uid-1.561
-1.375
quote-1.309
í-1.277
 Ladies-1.215
Token Nick
Token ID8047
Feature activation+1.76e+00

Pos logit contributions
soever+1.919
 adversary+1.855
��+1.815
achine+1.763
 Canaver+1.709
Neg logit contributions
uid-2.306
-2.059
quote-1.972
í-1.938
 Ladies-1.854
Token Koz
Token ID40772
Feature activation-1.82e-01

Pos logit contributions
soever+7.022
achine+6.718
 Canaver+6.683
 adversary+6.589
��+6.415
Neg logit contributions
-9.327
uid-9.309
quote-8.072
 Ladies-7.626
í-7.490
Tokenak
Token ID461
Feature activation-1.92e-01

Pos logit contributions
uid+0.878
+0.748
quote+0.718
í+0.718
 Ladies+0.668
Neg logit contributions
soever-0.973
 adversary-0.942
��-0.937
achine-0.891
 Canaver-0.885
Token file
Token ID2393
Feature activation+1.43e-01

Pos logit contributions
uid+0.871
+0.746
quote+0.711
í+0.708
 Ladies+0.666
Neg logit contributions
soever-1.066
 adversary-1.037
��-1.025
achine-0.992
 Canaver-0.983
Token photo
Token ID4590
Feature activation-2.69e-01

Pos logit contributions
soever+0.618
 adversary+0.591
��+0.589
achine+0.565
 Canaver+0.553
Neg logit contributions
uid-0.822
-0.747
quote-0.720
í-0.704
 Ladies-0.676
Token for
Token ID329
Feature activation+1.79e-01

Pos logit contributions
uid+1.521
+1.382
quote+1.329
í+1.309
 Ladies+1.253
Neg logit contributions
soever-1.164
 adversary-1.124
��-1.109
achine-1.051
 Canaver-1.045
Token find
Token ID1064
Feature activation-4.56e-01

Pos logit contributions
uid+0.839
+0.754
quote+0.718
í+0.705
 Ladies+0.677
Neg logit contributions
soever-0.666
 adversary-0.644
��-0.625
achine-0.609
anooga-0.589
Token the
Token ID262
Feature activation-1.88e-01

Pos logit contributions
uid+2.535
+2.255
quote+2.192
í+2.160
 Ladies+2.066
Neg logit contributions
soever-2.031
 adversary-1.930
��-1.921
achine-1.856
 Canaver-1.813
Token email
Token ID3053
Feature activation-1.02e-01

Pos logit contributions
uid+1.100
+0.991
quote+0.953
í+0.938
 Ladies+0.901
Neg logit contributions
soever-0.786
 adversary-0.757
��-0.742
achine-0.717
anooga-0.693
Token of
Token ID286
Feature activation-3.85e-01

Pos logit contributions
uid+0.582
+0.523
quote+0.502
í+0.494
 Ladies+0.473
Neg logit contributions
soever-0.443
 adversary-0.428
��-0.418
achine-0.405
anooga-0.392
Token a
Token ID257
Feature activation-3.57e-01

Pos logit contributions
uid+2.123
+1.878
quote+1.827
í+1.790
 Ladies+1.712
Neg logit contributions
soever-1.748
 adversary-1.667
��-1.662
achine-1.603
anooga-1.555
Token recru
Token ID8921
Feature activation+1.75e+00

Pos logit contributions
uid+2.034
+1.823
quote+1.754
í+1.724
 Ladies+1.653
Neg logit contributions
soever-1.554
 adversary-1.497
��-1.469
achine-1.421
 Canaver-1.377
Tokeniter
Token ID2676
Feature activation+3.12e-01

Pos logit contributions
 adversary+6.658
soever+6.367
achine+6.356
anooga+6.119
 intruder+5.812
Neg logit contributions
uid-9.462
-8.823
 Ladies-7.995
quote-7.853
ーン-7.429
Token and
Token ID290
Feature activation-5.40e-02

Pos logit contributions
soever+1.284
 adversary+1.227
��+1.169
achine+1.157
anooga+1.109
Neg logit contributions
uid-1.849
-1.673
quote-1.585
í-1.546
 Ladies-1.508
Token send
Token ID3758
Feature activation-3.70e-01

Pos logit contributions
uid+0.293
+0.263
quote+0.248
í+0.243
 Ladies+0.234
Neg logit contributions
soever-0.249
 adversary-0.243
��-0.233
achine-0.228
 Canaver-0.221
Token them
Token ID606
Feature activation-2.85e-01

Pos logit contributions
uid+2.017
+1.788
quote+1.745
í+1.708
 Ladies+1.623
Neg logit contributions
soever-1.695
 adversary-1.633
��-1.627
achine-1.556
anooga-1.520
Token a
Token ID257
Feature activation-6.87e-01

Pos logit contributions
uid+1.602
+1.434
quote+1.390
í+1.361
 Ladies+1.302
Neg logit contributions
soever-1.255
 adversary-1.210
��-1.198
achine-1.148
anooga-1.119
Token Mer
Token ID4638
Feature activation+7.62e-02

Pos logit contributions
uid+1.697
+1.513
quote+1.456
í+1.435
 Ladies+1.375
Neg logit contributions
soever-1.387
 adversary-1.330
��-1.311
achine-1.269
anooga-1.235
Tokenrick
Token ID5557
Feature activation-3.33e-01

Pos logit contributions
soever+0.418
 adversary+0.409
��+0.400
achine+0.394
anooga+0.384
Neg logit contributions
uid-0.340
-0.301
quote-0.282
í-0.275
 Ladies-0.262
Token Garland
Token ID35466
Feature activation-7.62e-01

Pos logit contributions
uid+2.029
+1.827
quote+1.766
í+1.759
 Ladies+1.687
Neg logit contributions
soever-1.313
 adversary-1.252
��-1.236
achine-1.183
anooga-1.151
Token to
Token ID284
Feature activation-1.82e-01

Pos logit contributions
uid+4.087
+3.618
í+3.466
quote+3.463
 Ladies+3.268
Neg logit contributions
soever-3.532
 adversary-3.358
��-3.282
achine-3.272
anooga-3.168
Token the
Token ID262
Feature activation-6.07e-01

Pos logit contributions
uid+0.984
+0.877
quote+0.840
í+0.829
 Ladies+0.791
Neg logit contributions
soever-0.841
 adversary-0.809
��-0.795
achine-0.773
anooga-0.750
Token Supreme
Token ID5617
Feature activation-2.67e+00

Pos logit contributions
uid+2.612
+2.251
quote+2.138
í+2.094
 Ladies+1.977
Neg logit contributions
soever-3.475
 adversary-3.369
��-3.328
achine-3.248
anooga-3.176
Token Court
Token ID3078
Feature activation-2.00e+00

Pos logit contributions
uid+7.662
í+6.083
quote+5.977
 Ladies+5.569
+5.530
Neg logit contributions
��-17.651
soever-17.593
 adversary-16.677
achine-16.530
anooga-16.500
Token.
Token ID13
Feature activation+1.84e-01

Pos logit contributions
uid+9.135
+7.910
í+7.860
quote+7.579
 Ladies+7.197
Neg logit contributions
soever-9.771
��-9.230
achine-9.040
 Canaver-8.965
anooga-8.939
Token In
Token ID554
Feature activation-5.84e-02

Pos logit contributions
soever+0.896
 adversary+0.867
��+0.844
achine+0.830
 Canaver+0.830
Neg logit contributions
uid-0.930
-0.827
quote-0.777
í-0.752
united-0.723
Token March
Token ID2805
Feature activation+2.08e-01

Pos logit contributions
uid+0.315
+0.282
quote+0.268
í+0.263
 Ladies+0.252
Neg logit contributions
soever-0.270
 adversary-0.265
��-0.257
achine-0.251
 Canaver-0.244
Token,
Token ID11
Feature activation-2.00e-01

Pos logit contributions
soever+1.000
 adversary+0.975
��+0.952
achine+0.924
 Canaver+0.897
Neg logit contributions
uid-1.082
-0.963
quote-0.915
í-0.898
 Ladies-0.859
Token
Token ID247
Feature activation+3.58e-01

Pos logit contributions
soever+2.388
��+2.310
 adversary+2.299
achine+2.142
anooga+2.087
Neg logit contributions
uid-3.583
-3.251
quote-3.129
í-3.061
 Ladies-2.983
Tokens
Token ID82
Feature activation+1.55e-01

Pos logit contributions
soever+1.622
 adversary+1.572
��+1.528
achine+1.485
anooga+1.439
Neg logit contributions
uid-1.952
-1.743
quote-1.662
í-1.626
 Ladies-1.572
Token nomination
Token ID11872
Feature activation-9.42e-02

Pos logit contributions
soever+0.726
 adversary+0.707
��+0.687
achine+0.666
 Canaver+0.648
Neg logit contributions
uid-0.827
-0.740
quote-0.703
í-0.691
 Ladies-0.659
Token to
Token ID284
Feature activation-3.08e-01

Pos logit contributions
uid+0.515
+0.460
quote+0.440
í+0.436
 Ladies+0.413
Neg logit contributions
soever-0.433
 adversary-0.415
��-0.411
achine-0.397
 Canaver-0.386
Token the
Token ID262
Feature activation-6.14e-01

Pos logit contributions
uid+1.627
+1.443
quote+1.384
í+1.370
 Ladies+1.307
Neg logit contributions
soever-1.478
 adversary-1.408
��-1.392
achine-1.356
anooga-1.325
Token Supreme
Token ID5617
Feature activation-2.56e+00

Pos logit contributions
uid+2.307
+1.939
quote+1.831
í+1.792
 Ladies+1.681
Neg logit contributions
soever-3.854
 adversary-3.732
��-3.699
achine-3.616
anooga-3.553
Token Court
Token ID3078
Feature activation-1.83e+00

Pos logit contributions
uid+7.777
í+6.214
quote+6.068
+5.925
 Ladies+5.756
Neg logit contributions
soever-16.658
��-16.542
 adversary-15.772
achine-15.581
anooga-15.576
Token.
Token ID13
Feature activation+5.43e-02

Pos logit contributions
uid+8.536
+7.413
í+7.297
quote+7.104
 Ladies+6.744
Neg logit contributions
soever-8.811
��-8.497
 adversary-8.191
 Canaver-8.157
achine-8.151
Token In
Token ID554
Feature activation+1.33e-02

Pos logit contributions
soever+0.271
 adversary+0.262
��+0.257
achine+0.251
 Canaver+0.247
Neg logit contributions
uid-0.272
-0.241
quote-0.227
í-0.222
 Ladies-0.211
Token brief
Token ID4506
Feature activation+5.78e-01

Pos logit contributions
soever+0.058
 adversary+0.057
��+0.055
achine+0.054
 Canaver+0.052
Neg logit contributions
uid-0.075
-0.068
quote-0.065
í-0.064
 Ladies-0.061
Token,
Token ID11
Feature activation+3.82e-02

Pos logit contributions
soever+2.460
 adversary+2.397
��+2.339
achine+2.250
anooga+2.181
Neg logit contributions
uid-3.297
-2.954
quote-2.822
í-2.772
 Ladies-2.661
Token but
Token ID475
Feature activation+1.56e-01

Pos logit contributions
soever+0.031
 adversary+0.030
��+0.029
achine+0.028
 Canaver+0.027
Neg logit contributions
uid-0.050
-0.045
quote-0.044
í-0.043
 Ladies-0.041
Token related
Token ID3519
Feature activation+2.25e-01

Pos logit contributions
soever+0.609
 adversary+0.585
��+0.572
achine+0.551
anooga+0.532
Neg logit contributions
uid-0.954
-0.863
quote-0.831
í-0.818
 Ladies-0.787
Token cases
Token ID2663
Feature activation+4.43e-02

Pos logit contributions
soever+0.822
 adversary+0.807
��+0.759
achine+0.737
 Canaver+0.709
Neg logit contributions
uid-1.430
-1.300
quote-1.258
í-1.229
 Ladies-1.182
Token,
Token ID11
Feature activation-3.18e-02

Pos logit contributions
soever+0.199
 adversary+0.193
��+0.189
achine+0.183
anooga+0.177
Neg logit contributions
uid-0.245
-0.220
quote-0.210
í-0.207
 Ladies-0.198
Token the
Token ID262
Feature activation+1.87e-02

Pos logit contributions
uid+0.177
+0.158
quote+0.152
í+0.149
 Ladies+0.143
Neg logit contributions
soever-0.142
 adversary-0.137
��-0.135
achine-0.131
anooga-0.127
Token Supreme
Token ID5617
Feature activation-2.45e+00

Pos logit contributions
soever+0.091
 adversary+0.089
��+0.087
achine+0.084
 Canaver+0.082
Neg logit contributions
uid-0.097
-0.086
quote-0.082
í-0.080
 Ladies-0.076
Token Court
Token ID3078
Feature activation-1.45e+00

Pos logit contributions
uid+7.218
í+5.846
quote+5.509
 Ladies+5.391
+5.179
Neg logit contributions
��-16.124
soever-15.864
anooga-15.310
 adversary-15.023
achine-14.978
Token found
Token ID1043
Feature activation-1.53e-01

Pos logit contributions
uid+6.829
+5.829
í+5.819
quote+5.731
 Ladies+5.613
Neg logit contributions
soever-7.013
��-7.000
achine-6.777
 adversary-6.534
 Canaver-6.482
Token that
Token ID326
Feature activation+1.24e-01

Pos logit contributions
uid+0.872
+0.781
quote+0.758
í+0.745
 Ladies+0.716
Neg logit contributions
soever-0.655
 adversary-0.626
��-0.624
achine-0.605
anooga-0.587
Token while
Token ID981
Feature activation-1.28e-01

Pos logit contributions
soever+0.491
 adversary+0.472
��+0.462
achine+0.446
anooga+0.431
Neg logit contributions
uid-0.757
-0.685
quote-0.660
í-0.650
 Ladies-0.625
Token the
Token ID262
Feature activation+1.02e-01

Pos logit contributions
uid+0.741
+0.665
quote+0.643
í+0.634
 Ladies+0.608
Neg logit contributions
soever-0.535
 adversary-0.515
��-0.511
achine-0.492
anooga-0.480
Token elections
Token ID7024
Feature activation+6.23e-02

Pos logit contributions
uid+3.926
+3.548
quote+3.407
í+3.390
 Ladies+3.260
Neg logit contributions
soever-2.993
��-2.957
achine-2.849
 adversary-2.845
anooga-2.786
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
soever+0.290
 adversary+0.281
��+0.277
achine+0.268
anooga+0.261
Neg logit contributions
uid-0.334
-0.299
quote-0.285
í-0.282
 Ladies-0.268
Token
Token ID198
Feature activation+2.55e-01

Pos logit contributions
soever+0.618
 adversary+0.592
��+0.577
achine+0.567
 Canaver+0.557
Neg logit contributions
uid-0.637
-0.564
quote-0.534
í-0.518
united-0.491
Token
Token ID198
Feature activation+1.77e-01

Pos logit contributions
soever+1.027
 adversary+0.999
achine+0.974
 Canaver+0.916
 weakness+0.905
Neg logit contributions
uid-1.437
-1.300
quote-1.217
 Ladies-1.158
í-1.157
TokenThe
Token ID464
Feature activation+2.12e-01

Pos logit contributions
soever+0.808
 adversary+0.780
��+0.764
achine+0.740
anooga+0.720
Neg logit contributions
uid-0.963
-0.862
quote-0.822
í-0.809
 Ladies-0.778
Token Supreme
Token ID5617
Feature activation-2.42e+00

Pos logit contributions
soever+0.915
 adversary+0.904
��+0.865
achine+0.840
 Canaver+0.814
Neg logit contributions
uid-1.201
-1.084
quote-1.034
í-1.015
 Ladies-0.964
Token Court
Token ID3078
Feature activation-1.70e+00

Pos logit contributions
uid+7.506
í+6.079
quote+5.834
 Ladies+5.742
+5.726
Neg logit contributions
��-15.565
soever-15.394
 adversary-14.713
achine-14.598
anooga-14.592
Token
Token ID447
Feature activation+7.53e-02

Pos logit contributions
uid+9.269
í+8.091
+8.014
quote+7.880
 Ladies+7.717
Neg logit contributions
soever-6.956
��-6.939
achine-6.563
 adversary-6.386
anooga-6.312
Token
Token ID247
Feature activation-2.04e-01

Pos logit contributions
soever+0.379
 adversary+0.373
��+0.369
achine+0.348
 Canaver+0.341
Neg logit contributions
uid-0.366
-0.328
quote-0.315
í-0.299
 Ladies-0.295
Tokens
Token ID82
Feature activation-3.10e-01

Pos logit contributions
uid+1.141
+1.018
quote+0.978
í+0.967
 Ladies+0.920
Neg logit contributions
soever-0.906
 adversary-0.875
��-0.872
achine-0.834
 Canaver-0.813
Token erroneous
Token ID35366
Feature activation-8.92e-01

Pos logit contributions
uid+1.838
+1.655
quote+1.593
í+1.569
 Ladies+1.508
Neg logit contributions
soever-1.271
 adversary-1.222
��-1.199
achine-1.157
anooga-1.120
Token just
Token ID655
Feature activation-9.62e-01

Pos logit contributions
uid+3.839
+3.434
quote+3.303
í+3.296
 Ladies+3.113
Neg logit contributions
soever-3.084
��-2.984
 adversary-2.889
achine-2.791
anooga-2.784
Token show
Token ID905
Feature activation-7.08e-01

Pos logit contributions
uid+5.319
+4.673
í+4.557
quote+4.543
 Ladies+4.245
Neg logit contributions
soever-4.348
��-4.145
 adversary-4.104
achine-3.932
anooga-3.913
Token up
Token ID510
Feature activation-6.60e-01

Pos logit contributions
uid+4.008
+3.504
quote+3.402
í+3.364
 Ladies+3.226
Neg logit contributions
soever-3.111
��-2.954
 adversary-2.904
achine-2.824
anooga-2.785
Token at
Token ID379
Feature activation-5.02e-01

Pos logit contributions
uid+3.518
+3.138
í+2.998
quote+2.996
 Ladies+2.857
Neg logit contributions
soever-3.067
��-2.964
 adversary-2.936
achine-2.859
 Canaver-2.772
Token the
Token ID262
Feature activation-2.25e-01

Pos logit contributions
uid+2.696
+2.392
quote+2.318
í+2.293
 Ladies+2.207
Neg logit contributions
soever-2.326
��-2.223
 adversary-2.196
achine-2.142
anooga-2.078
Token Supreme
Token ID5617
Feature activation-2.41e+00

Pos logit contributions
uid+1.088
+0.957
quote+0.910
í+0.892
 Ladies+0.847
Neg logit contributions
soever-1.171
 adversary-1.139
��-1.117
achine-1.088
anooga-1.060
Token Court
Token ID3078
Feature activation-1.79e+00

Pos logit contributions
uid+7.346
í+5.827
quote+5.661
+5.565
 Ladies+5.472
Neg logit contributions
��-15.607
soever-15.561
 adversary-14.852
achine-14.804
anooga-14.686
Token building
Token ID2615
Feature activation-2.58e-01

Pos logit contributions
uid+9.252
+8.147
í+8.069
quote+7.932
 Ladies+7.737
Neg logit contributions
soever-7.908
��-7.722
achine-7.454
 adversary-7.275
anooga-7.216
Token and
Token ID290
Feature activation-3.28e-01

Pos logit contributions
uid+1.462
+1.312
quote+1.259
í+1.240
 Ladies+1.188
Neg logit contributions
soever-1.131
 adversary-1.092
��-1.073
achine-1.038
anooga-1.005
Token start
Token ID923
Feature activation+5.84e-02

Pos logit contributions
uid+1.787
+1.595
quote+1.529
í+1.504
 Ladies+1.439
Neg logit contributions
soever-1.507
 adversary-1.457
��-1.434
achine-1.388
anooga-1.350
Token working
Token ID1762
Feature activation-9.41e-01

Pos logit contributions
soever+0.252
 adversary+0.244
��+0.237
achine+0.230
 Canaver+0.223
Neg logit contributions
uid-0.334
-0.300
quote-0.288
í-0.283
 Ladies-0.271
Token filed
Token ID5717
Feature activation+2.13e-01

Pos logit contributions
uid+0.404
+0.358
quote+0.343
í+0.333
 Ladies+0.318
Neg logit contributions
soever-0.388
 adversary-0.379
��-0.367
achine-0.358
anooga-0.349
Token.
Token ID13
Feature activation+9.71e-02

Pos logit contributions
soever+0.954
 adversary+0.920
��+0.891
achine+0.869
anooga+0.843
Neg logit contributions
uid-1.184
-1.061
quote-1.021
í-0.995
 Ladies-0.958
Token Whatever
Token ID15935
Feature activation-2.01e-02

Pos logit contributions
soever+0.483
 adversary+0.465
��+0.454
achine+0.444
 Canaver+0.435
Neg logit contributions
uid-0.491
-0.436
quote-0.413
í-0.402
 Ladies-0.381
Token recon
Token ID8195
Feature activation-7.48e-01

Pos logit contributions
uid+0.114
+0.102
quote+0.098
í+0.097
 Ladies+0.093
Neg logit contributions
soever-0.088
 adversary-0.085
��-0.083
achine-0.080
anooga-0.078
Tokenfigured
Token ID46296
Feature activation-2.65e-01

Pos logit contributions
uid+2.937
+2.460
quote+2.352
í+2.335
 Ladies+2.123
Neg logit contributions
soever-4.559
��-4.385
 adversary-4.377
achine-4.294
 Canaver-4.216
Token Supreme
Token ID5617
Feature activation-2.33e+00

Pos logit contributions
uid+1.428
+1.272
quote+1.221
í+1.201
 Ladies+1.148
Neg logit contributions
soever-1.228
 adversary-1.185
��-1.168
achine-1.132
anooga-1.100
Token Court
Token ID3078
Feature activation-2.05e+00

Pos logit contributions
uid+7.294
í+5.813
+5.709
quote+5.671
 Ladies+5.411
Neg logit contributions
��-14.918
soever-14.870
 adversary-14.252
achine-14.136
anooga-14.096
Token emerges
Token ID25457
Feature activation-5.35e-02

Pos logit contributions
uid+10.583
í+9.461
+9.280
quote+8.940
 Ladies+8.634
Neg logit contributions
soever-8.483
��-8.356
achine-8.048
 Canaver-8.032
anooga-7.893
Token after
Token ID706
Feature activation+2.36e-01

Pos logit contributions
uid+0.305
+0.274
quote+0.263
í+0.259
 Ladies+0.248
Neg logit contributions
soever-0.231
 adversary-0.223
��-0.219
achine-0.212
anooga-0.205
Token the
Token ID262
Feature activation-2.70e-02

Pos logit contributions
soever+1.109
 adversary+1.077
��+1.045
achine+1.014
 Canaver+0.985
Neg logit contributions
uid-1.258
-1.126
quote-1.072
í-1.050
 Ladies-1.004
Token November
Token ID3389
Feature activation-1.78e-01

Pos logit contributions
uid+0.137
+0.122
quote+0.115
í+0.113
 Ladies+0.107
Neg logit contributions
soever-0.134
 adversary-0.131
��-0.127
achine-0.124
 Canaver-0.121
Token on
Token ID319
Feature activation+2.26e-01

Pos logit contributions
uid+2.120
+1.867
quote+1.796
í+1.774
 Ladies+1.691
Neg logit contributions
soever-1.950
 adversary-1.882
��-1.866
achine-1.810
anooga-1.769
Token Aadhaar
Token ID47727
Feature activation+2.20e-01

Pos logit contributions
soever+1.165
 adversary+1.138
��+1.108
achine+1.077
 Canaver+1.053
Neg logit contributions
uid-1.101
-0.973
quote-0.922
í-0.902
 Ladies-0.850
Token
Token ID198
Feature activation-1.51e-01

Pos logit contributions
soever+0.996
 adversary+0.961
��+0.930
achine+0.901
 Canaver+0.868
Neg logit contributions
uid-1.211
-1.091
quote-1.038
í-1.008
 Ladies-0.969
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
uid+0.711
+0.626
quote+0.597
í+0.585
 Ladies+0.556
Neg logit contributions
soever-0.806
 adversary-0.788
��-0.772
achine-0.749
 Canaver-0.736
TokenThe
Token ID464
Feature activation+1.31e-01

Pos logit contributions
uid+0.746
+0.665
quote+0.638
í+0.627
 Ladies+0.598
Neg logit contributions
soever-0.640
 adversary-0.621
��-0.608
achine-0.590
 Canaver-0.574
Token Supreme
Token ID5617
Feature activation-2.28e+00

Pos logit contributions
soever+0.730
 adversary+0.716
��+0.696
achine+0.680
 Canaver+0.663
Neg logit contributions
uid-0.583
-0.511
quote-0.482
í-0.469
 Ladies-0.439
Token Court
Token ID3078
Feature activation-1.40e+00

Pos logit contributions
uid+6.572
í+5.307
 Ladies+4.968
quote+4.945
+4.722
Neg logit contributions
��-15.048
soever-14.907
achine-14.360
anooga-14.298
 adversary-14.212
Token of
Token ID286
Feature activation-9.40e-01

Pos logit contributions
uid+7.749
í+6.659
+6.625
quote+6.567
 Ladies+6.453
Neg logit contributions
��-5.842
soever-5.814
achine-5.577
 adversary-5.523
anooga-5.433
Token India
Token ID3794
Feature activation-4.44e-01

Pos logit contributions
uid+3.512
+2.763
quote+2.720
í+2.701
 Ladies+2.552
Neg logit contributions
soever-5.871
��-5.703
 adversary-5.670
 Canaver-5.547
anooga-5.509
Token has
Token ID468
Feature activation-1.47e-01

Pos logit contributions
uid+2.664
+2.384
quote+2.305
í+2.283
 Ladies+2.195
Neg logit contributions
soever-1.779
 adversary-1.720
��-1.700
achine-1.634
anooga-1.590
Token time
Token ID640
Feature activation+2.94e-01

Pos logit contributions
uid+0.743
+0.658
quote+0.628
í+0.613
 Ladies+0.584
Neg logit contributions
soever-0.736
 adversary-0.714
��-0.694
achine-0.677
 Canaver-0.659
Token the
Token ID262
Feature activation-5.53e-01

Pos logit contributions
uid+3.154
+2.823
quote+2.748
í+2.727
 Ladies+2.605
Neg logit contributions
soever-2.599
��-2.502
 adversary-2.480
achine-2.424
anooga-2.335
Token first
Token ID717
Feature activation-3.26e-01

Pos logit contributions
uid+3.176
+2.832
quote+2.765
í+2.729
 Ladies+2.634
Neg logit contributions
soever-2.338
 adversary-2.216
��-2.207
achine-2.145
anooga-2.086
Token time
Token ID640
Feature activation-6.20e-01

Pos logit contributions
uid+1.892
+1.703
quote+1.641
í+1.616
 Ladies+1.553
Neg logit contributions
soever-1.373
 adversary-1.321
��-1.303
achine-1.260
anooga-1.219
Token that
Token ID326
Feature activation-3.97e-01

Pos logit contributions
uid+3.289
+2.957
quote+2.868
í+2.832
 Ladies+2.716
Neg logit contributions
soever-2.788
 adversary-2.723
��-2.714
achine-2.640
anooga-2.567
Token the
Token ID262
Feature activation-2.86e-01

Pos logit contributions
uid+2.149
+1.924
quote+1.867
í+1.837
 Ladies+1.763
Neg logit contributions
soever-1.782
 adversary-1.735
��-1.722
achine-1.673
 Canaver-1.626
Token Supreme
Token ID5617
Feature activation-2.21e+00

Pos logit contributions
uid+1.246
+1.079
quote+1.021
í+0.998
 Ladies+0.942
Neg logit contributions
soever-1.622
 adversary-1.579
��-1.553
achine-1.516
anooga-1.481
Token Court
Token ID3078
Feature activation-1.68e+00

Pos logit contributions
uid+6.745
í+5.457
quote+5.377
+5.241
 Ladies+5.117
Neg logit contributions
soever-14.319
��-14.316
 adversary-13.759
achine-13.528
anooga-13.420
Token was
Token ID373
Feature activation-8.72e-01

Pos logit contributions
uid+8.574
í+7.647
quote+7.583
+7.544
 Ladies+7.296
Neg logit contributions
��-7.230
soever-6.970
achine-6.914
 adversary-6.708
 Canaver-6.702
Token reported
Token ID2098
Feature activation-1.10e-02

Pos logit contributions
uid+4.567
+4.077
quote+3.923
í+3.897
 Ladies+3.704
Neg logit contributions
soever-4.052
��-3.936
 adversary-3.892
achine-3.792
anooga-3.688
Token to
Token ID284
Feature activation-1.86e-02

Pos logit contributions
uid+0.062
+0.056
quote+0.053
í+0.053
 Ladies+0.050
Neg logit contributions
soever-0.048
 adversary-0.046
��-0.045
achine-0.044
anooga-0.043
Token hold
Token ID1745
Feature activation-1.04e+00

Pos logit contributions
uid+0.108
+0.097
quote+0.093
í+0.092
 Ladies+0.088
Neg logit contributions
soever-0.079
 adversary-0.076
��-0.074
achine-0.072
anooga-0.069
Token awareness
Token ID9359
Feature activation-5.23e-01

Pos logit contributions
uid+3.615
+3.183
í+3.065
quote+3.029
 Ladies+2.876
Neg logit contributions
soever-3.359
��-3.225
 adversary-3.203
achine-3.109
 Canaver-3.045
Token about
Token ID546
Feature activation-4.60e-01

Pos logit contributions
uid+2.815
+2.523
í+2.403
quote+2.395
 Ladies+2.246
Neg logit contributions
soever-2.405
 adversary-2.315
��-2.292
achine-2.197
 Canaver-2.169
Token water
Token ID1660
Feature activation+1.17e-02

Pos logit contributions
uid+2.383
+2.119
quote+2.023
í+2.014
 Ladies+1.931
Neg logit contributions
soever-2.207
 adversary-2.110
��-2.107
achine-2.043
anooga-2.006
Token scarcity
Token ID35501
Feature activation-1.28e-01

Pos logit contributions
soever+0.048
 adversary+0.046
��+0.045
achine+0.043
anooga+0.042
Neg logit contributions
uid-0.070
-0.063
quote-0.060
í-0.059
 Ladies-0.057
Token,
Token ID11
Feature activation-4.09e-01

Pos logit contributions
uid+0.763
+0.689
quote+0.662
í+0.654
 Ladies+0.627
Neg logit contributions
soever-0.517
 adversary-0.498
��-0.488
achine-0.470
anooga-0.455
Token mis
Token ID2984
Feature activation-2.16e+00

Pos logit contributions
uid+2.335
+2.095
quote+2.006
í+1.997
 Ladies+1.900
Neg logit contributions
soever-1.747
��-1.687
 adversary-1.669
achine-1.609
anooga-1.578
Tokenmanagement
Token ID27604
Feature activation-3.94e-01

Pos logit contributions
uid+8.831
quote+7.575
í+7.482
+6.868
sell+6.742
Neg logit contributions
 adversary-11.526
��-11.446
soever-11.188
achine-11.053
 Canaver-11.013
Token and
Token ID290
Feature activation+5.62e-02

Pos logit contributions
uid+2.012
+1.808
í+1.754
quote+1.709
 Ladies+1.598
Neg logit contributions
soever-1.896
��-1.840
 adversary-1.808
achine-1.745
 Canaver-1.744
Token waste
Token ID7030
Feature activation-3.62e-01

Pos logit contributions
soever+0.234
 adversary+0.225
��+0.220
achine+0.213
anooga+0.206
Neg logit contributions
uid-0.330
-0.298
quote-0.286
í-0.282
 Ladies-0.270
Token may
Token ID743
Feature activation-4.98e-01

Pos logit contributions
uid+2.002
+1.779
quote+1.719
í+1.709
 Ladies+1.606
Neg logit contributions
soever-1.611
 adversary-1.567
��-1.532
achine-1.500
anooga-1.457
Token pave
Token ID23000
Feature activation-6.09e-01

Pos logit contributions
uid+2.772
+2.490
quote+2.382
í+2.372
 Ladies+2.236
Neg logit contributions
soever-2.234
��-2.137
 adversary-2.128
achine-2.023
anooga-1.994
Tokens
Token ID82
Feature activation-2.06e-01

Pos logit contributions
uid+4.706
í+3.993
+3.981
 Ladies+3.905
quote+3.884
Neg logit contributions
soever-4.350
 adversary-4.206
��-4.137
achine-4.061
 Canaver-4.038
Token,
Token ID11
Feature activation-3.12e-02

Pos logit contributions
uid+1.137
+1.016
quote+0.974
í+0.960
 Ladies+0.920
Neg logit contributions
soever-0.926
 adversary-0.897
��-0.879
achine-0.852
anooga-0.828
Token Judges
Token ID42495
Feature activation-9.31e-01

Pos logit contributions
uid+0.172
+0.155
quote+0.148
í+0.144
 Ladies+0.137
Neg logit contributions
soever-0.141
 adversary-0.136
��-0.133
achine-0.128
anooga-0.124
Token of
Token ID286
Feature activation-6.95e-01

Pos logit contributions
uid+4.682
+4.045
í+4.008
 Ladies+3.911
quote+3.909
Neg logit contributions
soever-4.386
 adversary-4.354
��-4.238
achine-4.148
 Canaver-4.143
Token the
Token ID262
Feature activation-5.59e-01

Pos logit contributions
uid+3.493
+2.964
í+2.937
quote+2.926
 Ladies+2.898
Neg logit contributions
soever-3.364
 adversary-3.270
��-3.251
achine-3.216
 Canaver-3.152
Token supreme
Token ID17700
Feature activation-2.14e+00

Pos logit contributions
uid+2.609
+2.256
quote+2.164
í+2.145
 Ladies+2.057
Neg logit contributions
soever-2.966
 adversary-2.877
��-2.858
achine-2.800
 Canaver-2.734
Token Court
Token ID3078
Feature activation-1.46e+00

Pos logit contributions
uid+7.097
í+5.951
 Ladies+5.848
+5.636
quote+5.484
Neg logit contributions
��-12.561
soever-12.495
 Canaver-12.268
achine-12.234
anooga-11.946
Token,
Token ID11
Feature activation-1.74e-01

Pos logit contributions
uid+6.741
+5.723
í+5.691
 Ladies+5.591
quote+5.508
Neg logit contributions
soever-7.005
��-6.945
 adversary-6.899
 Canaver-6.855
achine-6.782
Token and
Token ID290
Feature activation-3.08e-02

Pos logit contributions
uid+0.950
+0.846
quote+0.812
í+0.801
 Ladies+0.768
Neg logit contributions
soever-0.792
 adversary-0.766
��-0.752
achine-0.730
anooga-0.709
Token all
Token ID477
Feature activation-4.49e-01

Pos logit contributions
uid+0.186
+0.168
quote+0.162
í+0.158
 Ladies+0.150
Neg logit contributions
soever-0.124
 adversary-0.119
��-0.115
achine-0.110
 Canaver-0.107
Token other
Token ID584
Feature activation+4.67e-01

Pos logit contributions
uid+2.760
+2.493
quote+2.400
í+2.376
 Ladies+2.295
Neg logit contributions
soever-1.734
 adversary-1.673
��-1.638
achine-1.585
anooga-1.531
Token stay
Token ID2652
Feature activation+5.51e-01

Pos logit contributions
soever+1.377
 adversary+1.348
��+1.293
achine+1.253
 Canaver+1.205
Neg logit contributions
uid-1.927
-1.743
quote-1.663
í-1.640
 Ladies-1.567
Token while
Token ID981
Feature activation+1.33e-01

Pos logit contributions
soever+2.297
 adversary+2.230
��+2.115
achine+2.067
 Canaver+2.011
Neg logit contributions
uid-3.180
-2.881
quote-2.735
í-2.699
 Ladies-2.614
Token it
Token ID340
Feature activation+1.46e-01

Pos logit contributions
soever+0.605
 adversary+0.585
��+0.573
achine+0.556
anooga+0.540
Neg logit contributions
uid-0.731
-0.654
quote-0.626
í-0.616
 Ladies-0.589
Token asks
Token ID7893
Feature activation+4.92e-01

Pos logit contributions
soever+0.639
 adversary+0.624
��+0.597
achine+0.581
 Canaver+0.567
Neg logit contributions
uid-0.825
-0.739
quote-0.712
í-0.692
 Ladies-0.668
Token the
Token ID262
Feature activation+1.74e-01

Pos logit contributions
soever+2.146
 adversary+2.090
��+2.017
achine+1.958
 Canaver+1.893
Neg logit contributions
uid-2.784
-2.507
quote-2.392
í-2.350
 Ladies-2.247
Token Supreme
Token ID5617
Feature activation-2.13e+00

Pos logit contributions
soever+0.853
 adversary+0.835
��+0.810
achine+0.790
 Canaver+0.764
Neg logit contributions
uid-0.894
-0.797
quote-0.755
í-0.741
 Ladies-0.703
Token Court
Token ID3078
Feature activation-1.13e+00

Pos logit contributions
uid+6.558
í+5.213
quote+5.106
+4.885
 Ladies+4.876
Neg logit contributions
��-13.919
soever-13.778
anooga-13.221
 adversary-13.154
achine-12.991
Token to
Token ID284
Feature activation-3.45e-01

Pos logit contributions
uid+5.449
+4.692
í+4.631
quote+4.542
 Ladies+4.338
Neg logit contributions
soever-5.692
��-5.418
 adversary-5.263
achine-5.249
 Canaver-5.212
Token hear
Token ID3285
Feature activation-6.91e-02

Pos logit contributions
uid+1.865
+1.661
quote+1.596
í+1.571
 Ladies+1.498
Neg logit contributions
soever-1.599
 adversary-1.541
��-1.523
achine-1.469
anooga-1.437
Token its
Token ID663
Feature activation+3.94e-01

Pos logit contributions
uid+0.388
+0.346
quote+0.333
í+0.329
 Ladies+0.315
Neg logit contributions
soever-0.306
 adversary-0.293
��-0.290
achine-0.280
anooga-0.275
Token appeal
Token ID5198
Feature activation+2.08e-02

Pos logit contributions
soever+1.516
 adversary+1.511
��+1.405
achine+1.365
 Canaver+1.316
Neg logit contributions
uid-2.403
-2.204
quote-2.102
í-2.057
 Ladies-1.982
Token sound
Token ID2128
Feature activation-6.94e-03

Pos logit contributions
uid+2.527
+2.279
quote+2.211
í+2.181
 Ladies+2.105
Neg logit contributions
soever-1.725
 adversary-1.640
��-1.640
achine-1.582
 Canaver-1.531
Token education
Token ID3707
Feature activation+1.73e-01

Pos logit contributions
uid+0.041
+0.037
quote+0.036
í+0.035
 Ladies+0.034
Neg logit contributions
soever-0.028
 adversary-0.027
��-0.027
achine-0.026
 Canaver-0.025
Token."
Token ID526
Feature activation-6.73e-02

Pos logit contributions
soever+0.776
 adversary+0.750
��+0.736
achine+0.712
 Canaver+0.691
Neg logit contributions
uid-0.958
-0.857
quote-0.822
í-0.809
 Ladies-0.773
Token
Token ID198
Feature activation+9.63e-02

Pos logit contributions
uid+0.315
+0.276
quote+0.264
í+0.263
 Ladies+0.249
Neg logit contributions
soever-0.359
 adversary-0.352
��-0.347
achine-0.333
 Canaver-0.326
Token
Token ID198
Feature activation+1.33e-01

Pos logit contributions
soever+0.405
 adversary+0.396
achine+0.382
 Canaver+0.360
��+0.356
Neg logit contributions
uid-0.532
-0.483
quote-0.452
í-0.433
 Ladies-0.430
TokenMis
Token ID31281
Feature activation-2.08e+00

Pos logit contributions
soever+0.606
 adversary+0.586
��+0.573
achine+0.557
anooga+0.540
Neg logit contributions
uid-0.728
-0.650
quote-0.622
í-0.612
 Ladies-0.587
Tokenguided
Token ID23657
Feature activation-1.12e+00

Pos logit contributions
uid+9.755
quote+8.714
+8.062
í+8.052
sell+7.959
Neg logit contributions
soever-9.736
 adversary-9.663
��-9.627
 Canaver-9.082
achine-8.775
Token political
Token ID1964
Feature activation+9.63e-02

Pos logit contributions
uid+6.320
+5.695
quote+5.635
í+5.581
 Ladies+5.327
Neg logit contributions
soever-4.467
��-4.292
 adversary-4.157
achine-4.148
 Canaver-4.057
Token effort
Token ID3626
Feature activation-3.44e-01

Pos logit contributions
soever+0.380
 adversary+0.365
��+0.358
achine+0.344
anooga+0.332
Neg logit contributions
uid-0.587
-0.530
quote-0.511
í-0.504
 Ladies-0.484
Token
Token ID198
Feature activation-3.69e-01

Pos logit contributions
uid+1.564
+1.365
quote+1.293
í+1.271
 Ladies+1.195
Neg logit contributions
soever-1.895
��-1.812
 adversary-1.808
achine-1.737
 Canaver-1.725
Token
Token ID198
Feature activation-3.67e-01

Pos logit contributions
uid+1.916
+1.706
quote+1.615
í+1.570
 Ladies+1.518
Neg logit contributions
soever-1.763
 adversary-1.713
achine-1.641
��-1.628
 Canaver-1.587
Tokenhash
Token ID17831
Feature activation+7.60e-01

Pos logit contributions
soever+0.019
 adversary+0.018
��+0.018
achine+0.017
anooga+0.017
Neg logit contributions
uid-0.020
-0.017
quote-0.017
í-0.016
 Ladies-0.016
Token Gh
Token ID11972
Feature activation-2.68e-01

Pos logit contributions
soever+3.394
 adversary+3.270
��+3.217
achine+3.130
 Canaver+3.051
Neg logit contributions
uid-4.132
-3.749
quote-3.565
í-3.473
 Ladies-3.338
Tokenai
Token ID1872
Feature activation+6.53e-01

Pos logit contributions
uid+1.441
+1.243
quote+1.211
í+1.208
 Ladies+1.129
Neg logit contributions
soever-1.279
 adversary-1.238
��-1.227
achine-1.162
 Canaver-1.148
Token,
Token ID11
Feature activation+7.46e-02

Pos logit contributions
soever+3.194
 adversary+3.115
��+3.031
achine+2.956
anooga+2.853
Neg logit contributions
uid-3.287
-2.945
quote-2.778
í-2.704
 Ladies-2.603
Token the
Token ID262
Feature activation+2.44e-01

Pos logit contributions
soever+0.339
 adversary+0.328
��+0.322
achine+0.312
anooga+0.303
Neg logit contributions
uid-0.409
-0.366
quote-0.351
í-0.345
 Ladies-0.330
Token Supreme
Token ID5617
Feature activation-2.08e+00

Pos logit contributions
soever+1.123
 adversary+1.095
��+1.059
achine+1.032
 Canaver+1.000
Neg logit contributions
uid-1.325
-1.189
quote-1.134
í-1.113
 Ladies-1.056
Token Court
Token ID3078
Feature activation-1.40e+00

Pos logit contributions
uid+6.528
í+5.183
quote+5.014
 Ladies+4.988
+4.823
Neg logit contributions
soever-13.348
��-13.322
anooga-12.753
 adversary-12.725
achine-12.705
Token today
Token ID1909
Feature activation-2.83e-01

Pos logit contributions
uid+6.944
+5.923
quote+5.844
í+5.834
 Ladies+5.675
Neg logit contributions
��-6.521
soever-6.489
achine-6.239
 adversary-6.168
 Canaver-6.073
Token upheld
Token ID24816
Feature activation-4.94e-03

Pos logit contributions
uid+1.428
+1.263
quote+1.204
í+1.186
 Ladies+1.130
Neg logit contributions
soever-1.409
 adversary-1.368
��-1.353
achine-1.316
anooga-1.281
Token the
Token ID262
Feature activation+4.37e-01

Pos logit contributions
uid+0.028
+0.025
quote+0.024
í+0.023
 Ladies+0.023
Neg logit contributions
soever-0.022
 adversary-0.021
��-0.021
achine-0.020
anooga-0.020
Token Bombay
Token ID48918
Feature activation+2.59e-01

Pos logit contributions
soever+1.876
 adversary+1.836
��+1.752
achine+1.698
 Canaver+1.648
Neg logit contributions
uid-2.482
-2.251
quote-2.145
í-2.108
united-1.999
Token the
Token ID262
Feature activation+1.62e-01

Pos logit contributions
soever+0.796
 adversary+0.769
��+0.755
achine+0.730
anooga+0.707
Neg logit contributions
uid-0.993
-0.889
quote-0.853
í-0.840
 Ladies-0.804
Token American
Token ID1605
Feature activation-7.42e-06

Pos logit contributions
soever+0.697
 adversary+0.676
��+0.659
achine+0.639
anooga+0.619
Neg logit contributions
uid-0.929
-0.834
quote-0.800
í-0.786
 Ladies-0.753
Token economy
Token ID3773
Feature activation+9.15e-02

Feature not active on prev token;
no predictions were affected.
Token and
Token ID290
Feature activation+2.67e-01

Pos logit contributions
soever+0.425
 adversary+0.409
��+0.403
achine+0.389
 Canaver+0.386
Neg logit contributions
uid-0.495
-0.444
quote-0.422
í-0.422
 Ladies-0.399
Token a
Token ID257
Feature activation+3.64e-02

Pos logit contributions
soever+1.176
 adversary+1.138
��+1.102
achine+1.069
anooga+1.038
Neg logit contributions
uid-1.513
-1.350
quote-1.299
í-1.269
 Ladies-1.216
Token Supreme
Token ID5617
Feature activation-2.07e+00

Pos logit contributions
soever+0.156
 adversary+0.151
��+0.148
achine+0.143
anooga+0.138
Neg logit contributions
uid-0.210
-0.188
quote-0.181
í-0.178
 Ladies-0.170
Token Court
Token ID3078
Feature activation-1.57e+00

Pos logit contributions
uid+6.733
í+5.432
+5.347
quote+5.314
 Ladies+4.956
Neg logit contributions
soever-13.193
��-13.124
 adversary-12.646
achine-12.451
anooga-12.413
Token remotely
Token ID19863
Feature activation+4.00e-01

Pos logit contributions
uid+8.313
+7.320
í+7.294
quote+7.079
 Ladies+6.762
Neg logit contributions
soever-6.792
��-6.615
achine-6.353
 Canaver-6.301
anooga-6.175
Token sympathetic
Token ID22335
Feature activation-1.10e-01

Pos logit contributions
soever+1.524
 adversary+1.479
��+1.418
achine+1.362
 Canaver+1.315
Neg logit contributions
uid-2.494
-2.267
quote-2.166
í-2.130
 Ladies-2.056
Token to
Token ID284
Feature activation-8.35e-02

Pos logit contributions
uid+0.582
+0.518
í+0.496
quote+0.488
 Ladies+0.462
Neg logit contributions
soever-0.525
��-0.497
 adversary-0.497
achine-0.478
 Canaver-0.473
Token organized
Token ID8389
Feature activation+4.60e-01

Pos logit contributions
uid+0.458
+0.410
quote+0.393
í+0.387
 Ladies+0.371
Neg logit contributions
soever-0.380
 adversary-0.366
��-0.360
achine-0.349
anooga-0.339
Token elect
Token ID1742
Feature activation+1.62e-01

Pos logit contributions
uid+2.648
+2.374
quote+2.308
í+2.281
 Ladies+2.181
Neg logit contributions
soever-1.792
 adversary-1.694
��-1.690
achine-1.632
anooga-1.592
Token justices
Token ID27818
Feature activation-1.64e+00

Pos logit contributions
soever+0.691
 adversary+0.671
��+0.650
achine+0.628
anooga+0.608
Neg logit contributions
uid-0.939
-0.849
quote-0.812
í-0.797
 Ladies-0.764
Token on
Token ID319
Feature activation-6.41e-01

Pos logit contributions
uid+8.245
+7.269
í+7.155
quote+6.927
 Ladies+6.613
Neg logit contributions
soever-7.458
 adversary-7.102
��-7.099
achine-7.063
anooga-6.966
Token the
Token ID262
Feature activation-6.53e-01

Pos logit contributions
uid+3.502
+3.074
quote+2.987
í+2.978
 Ladies+2.870
Neg logit contributions
soever-2.880
��-2.747
 adversary-2.694
achine-2.659
anooga-2.619
Token Wisconsin
Token ID9279
Feature activation-9.61e-01

Pos logit contributions
uid+3.457
+3.053
quote+2.957
í+2.924
 Ladies+2.809
Neg logit contributions
soever-3.054
��-2.913
 adversary-2.907
achine-2.823
anooga-2.771
Token supreme
Token ID17700
Feature activation-2.07e+00

Pos logit contributions
uid+3.577
+3.003
í+2.890
quote+2.867
 Ladies+2.739
Neg logit contributions
soever-5.850
��-5.763
 adversary-5.646
achine-5.598
anooga-5.539
Token court
Token ID2184
Feature activation-1.76e+00

Pos logit contributions
uid+8.083
í+6.947
+6.932
quote+6.900
 Ladies+6.285
Neg logit contributions
��-11.325
soever-11.318
 Canaver-10.742
achine-10.705
anooga-10.581
Token majority
Token ID3741
Feature activation-7.79e-01

Pos logit contributions
uid+8.548
í+7.528
+7.460
quote+7.121
 Ladies+6.959
Neg logit contributions
soever-8.217
��-7.878
achine-7.697
 Canaver-7.682
 adversary-7.626
Token that
Token ID326
Feature activation-4.26e-01

Pos logit contributions
uid+4.082
+3.621
í+3.505
quote+3.455
 Ladies+3.259
Neg logit contributions
soever-3.661
��-3.482
 adversary-3.475
achine-3.417
 Canaver-3.348
Token not
Token ID407
Feature activation-2.64e-01

Pos logit contributions
uid+2.294
+2.042
quote+1.958
í+1.934
 Ladies+1.844
Neg logit contributions
soever-1.972
 adversary-1.909
��-1.881
achine-1.835
anooga-1.784
Token only
Token ID691
Feature activation-6.63e-01

Pos logit contributions
uid+1.638
+1.473
í+1.434
quote+1.433
 Ladies+1.354
Neg logit contributions
soever-1.002
 adversary-0.962
��-0.954
achine-0.907
 Canaver-0.880
Token all
Token ID477
Feature activation-1.09e-01

Pos logit contributions
uid+2.061
+1.854
quote+1.789
í+1.766
 Ladies+1.703
Neg logit contributions
soever-1.509
��-1.449
 adversary-1.447
achine-1.385
anooga-1.347
Token 50
Token ID2026
Feature activation+3.03e-01

Pos logit contributions
uid+0.576
+0.516
quote+0.492
í+0.486
 Ladies+0.464
Neg logit contributions
soever-0.513
 adversary-0.496
��-0.495
achine-0.480
 Canaver-0.466
Token states
Token ID2585
Feature activation+1.88e-01

Pos logit contributions
soever+1.453
 adversary+1.406
��+1.382
achine+1.344
 Canaver+1.307
Neg logit contributions
uid-1.592
-1.418
quote-1.352
í-1.333
 Ladies-1.267
Token.
Token ID13
Feature activation+3.09e-01

Pos logit contributions
soever+0.848
 adversary+0.819
��+0.798
achine+0.776
anooga+0.751
Neg logit contributions
uid-1.037
-0.927
quote-0.889
í-0.872
 Ladies-0.836
Token The
Token ID383
Feature activation+1.81e-01

Pos logit contributions
soever+1.480
 adversary+1.385
��+1.341
achine+1.341
 Canaver+1.339
Neg logit contributions
uid-1.613
-1.415
quote-1.329
í-1.290
united-1.242
Token Supreme
Token ID5617
Feature activation-2.07e+00

Pos logit contributions
soever+0.823
 adversary+0.816
��+0.779
achine+0.758
 Canaver+0.732
Neg logit contributions
uid-0.986
-0.881
quote-0.840
í-0.823
 Ladies-0.777
Token Court
Token ID3078
Feature activation-1.46e+00

Pos logit contributions
uid+6.712
í+5.353
+5.307
quote+5.233
 Ladies+4.983
Neg logit contributions
soever-13.303
��-13.243
 adversary-12.705
achine-12.580
anooga-12.421
Token obviously
Token ID6189
Feature activation+1.08e-01

Pos logit contributions
uid+7.595
+6.658
í+6.590
quote+6.553
 Ladies+6.323
Neg logit contributions
��-6.531
soever-6.389
achine-6.149
 adversary-5.995
anooga-5.921
Token didn
Token ID1422
Feature activation-7.94e-02

Pos logit contributions
soever+0.460
 adversary+0.448
��+0.420
achine+0.413
 Canaver+0.403
Neg logit contributions
uid-0.625
-0.562
quote-0.539
í-0.523
 Ladies-0.504
Token't
Token ID470
Feature activation+2.30e-01

Pos logit contributions
uid+0.408
+0.363
quote+0.337
 Ladies+0.326
í+0.317
Neg logit contributions
soever-0.372
 adversary-0.362
achine-0.349
 Canaver-0.337
��-0.333
Token want
Token ID765
Feature activation+3.70e-01

Pos logit contributions
soever+0.985
 adversary+0.971
achine+0.903
��+0.874
 decomp+0.856
Neg logit contributions
uid-1.303
-1.169
quote-1.116
í-1.075
 Ladies-1.059
Token.
Token ID13
Feature activation+9.71e-02

Pos logit contributions
soever+0.954
 adversary+0.920
��+0.891
achine+0.869
anooga+0.843
Neg logit contributions
uid-1.184
-1.061
quote-1.021
í-0.995
 Ladies-0.958
Token Whatever
Token ID15935
Feature activation-2.01e-02

Pos logit contributions
soever+0.483
 adversary+0.465
��+0.454
achine+0.444
 Canaver+0.435
Neg logit contributions
uid-0.491
-0.436
quote-0.413
í-0.402
 Ladies-0.381
Token recon
Token ID8195
Feature activation-7.48e-01

Pos logit contributions
uid+0.114
+0.102
quote+0.098
í+0.097
 Ladies+0.093
Neg logit contributions
soever-0.088
 adversary-0.085
��-0.083
achine-0.080
anooga-0.078
Tokenfigured
Token ID46296
Feature activation-2.65e-01

Pos logit contributions
uid+2.937
+2.460
quote+2.352
í+2.335
 Ladies+2.123
Neg logit contributions
soever-4.559
��-4.385
 adversary-4.377
achine-4.294
 Canaver-4.216
Token Supreme
Token ID5617
Feature activation-2.33e+00

Pos logit contributions
uid+1.428
+1.272
quote+1.221
í+1.201
 Ladies+1.148
Neg logit contributions
soever-1.228
 adversary-1.185
��-1.168
achine-1.132
anooga-1.100
Token Court
Token ID3078
Feature activation-2.05e+00

Pos logit contributions
uid+7.294
í+5.813
+5.709
quote+5.671
 Ladies+5.411
Neg logit contributions
��-14.918
soever-14.870
 adversary-14.252
achine-14.136
anooga-14.096
Token emerges
Token ID25457
Feature activation-5.35e-02

Pos logit contributions
uid+10.583
í+9.461
+9.280
quote+8.940
 Ladies+8.634
Neg logit contributions
soever-8.483
��-8.356
achine-8.048
 Canaver-8.032
anooga-7.893
Token after
Token ID706
Feature activation+2.36e-01

Pos logit contributions
uid+0.305
+0.274
quote+0.263
í+0.259
 Ladies+0.248
Neg logit contributions
soever-0.231
 adversary-0.223
��-0.219
achine-0.212
anooga-0.205
Token the
Token ID262
Feature activation-2.70e-02

Pos logit contributions
soever+1.109
 adversary+1.077
��+1.045
achine+1.014
 Canaver+0.985
Neg logit contributions
uid-1.258
-1.126
quote-1.072
í-1.050
 Ladies-1.004
Token November
Token ID3389
Feature activation-1.78e-01

Pos logit contributions
uid+0.137
+0.122
quote+0.115
í+0.113
 Ladies+0.107
Neg logit contributions
soever-0.134
 adversary-0.131
��-0.127
achine-0.124
 Canaver-0.121
Token election
Token ID3071
Feature activation-3.90e-02

Pos logit contributions
uid+0.946
+0.842
quote+0.806
í+0.792
 Ladies+0.756
Neg logit contributions
soever-0.840
 adversary-0.814
��-0.798
achine-0.775
anooga-0.753
Token coincidence
Token ID21083
Feature activation-9.61e-01

Pos logit contributions
uid+4.338
+3.874
quote+3.747
í+3.743
 Ladies+3.547
Neg logit contributions
soever-3.339
��-3.192
 adversary-3.187
achine-3.062
anooga-2.979
Token,
Token ID11
Feature activation-3.11e-01

Pos logit contributions
uid+4.902
+4.332
í+4.191
quote+4.173
 Ladies+3.933
Neg logit contributions
soever-4.514
��-4.432
 adversary-4.413
achine-4.259
anooga-4.191
Token natural
Token ID3288
Feature activation-6.38e-01

Pos logit contributions
uid+1.643
+1.461
quote+1.399
í+1.378
 Ladies+1.313
Neg logit contributions
soever-1.480
 adversary-1.433
��-1.409
achine-1.367
anooga-1.329
Token occurrence
Token ID19810
Feature activation-2.22e-01

Pos logit contributions
uid+3.715
+3.370
quote+3.233
í+3.220
 Ladies+3.034
Neg logit contributions
soever-2.602
��-2.499
 adversary-2.457
achine-2.427
anooga-2.329
Token or
Token ID393
Feature activation-1.80e-01

Pos logit contributions
uid+1.198
+1.072
quote+1.031
í+1.021
 Ladies+0.966
Neg logit contributions
soever-1.013
 adversary-0.982
��-0.978
achine-0.940
anooga-0.919
Token mis
Token ID2984
Feature activation-2.05e+00

Pos logit contributions
uid+1.027
+0.923
quote+0.889
í+0.877
 Ladies+0.838
Neg logit contributions
soever-0.768
 adversary-0.740
��-0.734
achine-0.708
anooga-0.687
Tokenident
Token ID738
Feature activation-4.80e-01

Pos logit contributions
uid+8.533
quote+7.635
í+7.322
+6.922
united+6.558
Neg logit contributions
 adversary-10.541
soever-10.402
��-10.260
achine-10.193
anooga-9.932
Tokenification
Token ID2649
Feature activation-9.06e-01

Pos logit contributions
uid+3.035
+2.712
quote+2.654
í+2.641
 Ladies+2.510
Neg logit contributions
soever-1.791
 adversary-1.734
��-1.714
achine-1.623
anooga-1.579
Token and
Token ID290
Feature activation-3.15e-01

Pos logit contributions
uid+4.632
+4.090
í+3.971
quote+3.968
 Ladies+3.701
Neg logit contributions
soever-4.246
��-4.180
 adversary-4.129
achine-4.018
anooga-3.928
Token the
Token ID262
Feature activation-1.43e-01

Pos logit contributions
uid+1.754
+1.572
quote+1.513
í+1.493
 Ladies+1.424
Neg logit contributions
soever-1.391
 adversary-1.346
��-1.329
achine-1.286
anooga-1.250
Token
Token ID564
Feature activation-1.38e-01

Pos logit contributions
uid+0.843
+0.759
quote+0.730
í+0.719
 Ladies+0.690
Neg logit contributions
soever-0.592
 adversary-0.571
��-0.558
achine-0.539
anooga-0.522
Token compiling
Token ID33393
Feature activation-5.29e-01

Pos logit contributions
uid+0.406
+0.361
quote+0.350
í+0.344
 Ladies+0.331
Neg logit contributions
soever-0.323
��-0.307
 adversary-0.307
achine-0.294
anooga-0.287
Token a
Token ID257
Feature activation-4.31e-01

Pos logit contributions
uid+2.876
+2.547
quote+2.475
í+2.434
 Ladies+2.358
Neg logit contributions
soever-2.408
��-2.296
 adversary-2.262
achine-2.213
anooga-2.160
Token list
Token ID1351
Feature activation-9.41e-02

Pos logit contributions
uid+2.360
+2.112
quote+2.030
í+1.993
 Ladies+1.924
Neg logit contributions
soever-1.961
 adversary-1.865
��-1.860
achine-1.794
anooga-1.748
Token of
Token ID286
Feature activation-3.99e-01

Pos logit contributions
uid+0.499
+0.443
quote+0.425
í+0.418
 Ladies+0.395
Neg logit contributions
soever-0.450
 adversary-0.432
��-0.428
achine-0.412
anooga-0.404
Token possible
Token ID1744
Feature activation-5.19e-01

Pos logit contributions
uid+2.273
+2.030
quote+1.958
í+1.940
 Ladies+1.875
Neg logit contributions
soever-1.722
��-1.634
 adversary-1.618
achine-1.576
anooga-1.529
Token Supreme
Token ID5617
Feature activation-2.04e+00

Pos logit contributions
uid+2.961
+2.648
quote+2.580
í+2.525
 Ladies+2.462
Neg logit contributions
soever-2.211
��-2.098
 adversary-2.057
achine-2.030
anooga-1.965
Token Court
Token ID3078
Feature activation-1.90e+00

Pos logit contributions
uid+6.709
quote+5.355
í+5.355
+5.350
 Ladies+5.079
Neg logit contributions
��-12.910
soever-12.831
 adversary-12.466
achine-12.206
anooga-12.129
Token nominees
Token ID26456
Feature activation-7.49e-01

Pos logit contributions
uid+7.369
í+6.026
+5.946
quote+5.833
 Ladies+5.802
Neg logit contributions
��-10.599
soever-10.566
achine-10.313
anooga-10.017
 adversary-9.894
Token.
Token ID13
Feature activation-1.09e-01

Pos logit contributions
uid+3.921
+3.509
í+3.336
quote+3.336
 Ladies+3.179
Neg logit contributions
soever-3.468
��-3.411
 adversary-3.344
achine-3.273
anooga-3.180
Token It
Token ID632
Feature activation-1.24e-01

Pos logit contributions
uid+0.543
+0.479
quote+0.456
í+0.447
 Ladies+0.425
Neg logit contributions
soever-0.548
 adversary-0.532
��-0.521
achine-0.508
 Canaver-0.495
Token was
Token ID373
Feature activation-1.69e-01

Pos logit contributions
uid+0.677
+0.605
quote+0.579
í+0.569
 Ladies+0.545
Neg logit contributions
soever-0.564
 adversary-0.546
��-0.534
achine-0.518
anooga-0.503
Token actions
Token ID4028
Feature activation-1.08e+00

Pos logit contributions
uid+2.638
+2.331
quote+2.249
í+2.214
 Ladies+2.107
Neg logit contributions
soever-2.369
 adversary-2.281
��-2.260
achine-2.177
anooga-2.144
Token s
Token ID264
Feature activation-1.49e+00

Pos logit contributions
uid+5.664
+4.974
quote+4.834
í+4.793
 Ladies+4.520
Neg logit contributions
soever-5.057
��-4.873
 adversary-4.820
anooga-4.634
achine-4.617
Tokenont
Token ID756
Feature activation-1.86e-01

Pos logit contributions
uid+6.442
í+5.287
+5.155
quote+5.084
ú+4.737
Neg logit contributions
soever-8.281
��-8.269
 adversary-8.118
 Canaver-7.860
anooga-7.800
Token enc
Token ID2207
Feature activation-2.57e-01

Pos logit contributions
uid+0.995
+0.885
quote+0.849
í+0.835
 Ladies+0.797
Neg logit contributions
soever-0.870
 adversary-0.840
��-0.828
achine-0.801
anooga-0.780
Tokenore
Token ID382
Feature activation-5.02e-01

Pos logit contributions
uid+1.670
+1.498
quote+1.455
í+1.443
 Ladies+1.377
Neg logit contributions
soever-0.925
 adversary-0.887
��-0.874
achine-0.813
anooga-0.803
Token obsc
Token ID10666
Feature activation-2.03e+00

Pos logit contributions
uid+2.529
+2.217
quote+2.129
í+2.093
 Ladies+1.984
Neg logit contributions
soever-2.508
 adversary-2.434
��-2.397
achine-2.323
anooga-2.285
Tokenures
Token ID942
Feature activation-9.06e-01

Pos logit contributions
uid+9.910
í+8.349
quote+7.979
ú+7.923
+7.699
Neg logit contributions
��-10.065
soever-9.968
 adversary-9.862
 Canaver-9.091
anooga-8.967
Token :
Token ID1058
Feature activation-5.00e-01

Pos logit contributions
uid+4.538
+3.940
quote+3.842
í+3.795
 Ladies+3.558
Neg logit contributions
soever-4.478
 adversary-4.328
��-4.312
achine-4.145
anooga-4.137
Token les
Token ID10287
Feature activation-9.17e-01

Pos logit contributions
uid+2.641
+2.341
quote+2.273
í+2.227
 Ladies+2.124
Neg logit contributions
soever-2.369
 adversary-2.277
��-2.270
achine-2.164
anooga-2.139
Token mut
Token ID4517
Feature activation-6.59e-01

Pos logit contributions
uid+5.192
+4.620
quote+4.482
í+4.434
 Ladies+4.250
Neg logit contributions
soever-3.888
��-3.720
 adversary-3.643
anooga-3.544
achine-3.535
Tokenins
Token ID1040
Feature activation-9.57e-01

Pos logit contributions
uid+3.597
+3.072
í+3.039
quote+3.002
 Ladies+2.791
Neg logit contributions
soever-3.114
 adversary-3.018
��-3.001
achine-2.791
 Canaver-2.772
Token come
Token ID1282
Feature activation+3.41e-01

Pos logit contributions
soever+0.717
 adversary+0.694
��+0.674
achine+0.654
 Canaver+0.634
Neg logit contributions
uid-0.980
-0.878
quote-0.847
í-0.827
 Ladies-0.796
Token in
Token ID287
Feature activation-1.24e-01

Pos logit contributions
soever+1.480
 adversary+1.426
��+1.377
achine+1.352
anooga+1.302
Neg logit contributions
uid-1.945
-1.732
quote-1.679
í-1.636
 Ladies-1.571
Token border
Token ID4865
Feature activation+4.57e-01

Pos logit contributions
uid+0.684
+0.612
quote+0.586
í+0.578
 Ladies+0.555
Neg logit contributions
soever-0.555
 adversary-0.533
��-0.529
achine-0.507
anooga-0.497
Token cities
Token ID4736
Feature activation+3.89e-01

Pos logit contributions
soever+1.868
 adversary+1.822
��+1.735
achine+1.702
anooga+1.645
Neg logit contributions
uid-2.705
-2.436
quote-2.346
í-2.286
 Ladies-2.208
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
soever+1.747
 adversary+1.697
��+1.634
achine+1.600
 Canaver+1.543
Neg logit contributions
uid-2.157
-1.924
quote-1.852
í-1.799
 Ladies-1.735
Token initially
Token ID7317
Feature activation+1.03e+00

Pos logit contributions
uid+1.119
+1.005
quote+0.964
í+0.953
 Ladies+0.911
Neg logit contributions
soever-0.851
 adversary-0.819
��-0.807
achine-0.779
anooga-0.756
Token with
Token ID351
Feature activation-2.88e-01

Pos logit contributions
soever+4.222
 adversary+4.176
��+3.801
achine+3.800
anooga+3.657
Neg logit contributions
uid-5.935
-5.206
quote-5.099
í-4.858
 Ladies-4.732
Token the
Token ID262
Feature activation-1.67e-01

Pos logit contributions
uid+1.593
+1.426
quote+1.364
í+1.358
 Ladies+1.305
Neg logit contributions
soever-1.286
��-1.221
 adversary-1.217
achine-1.175
anooga-1.141
Token dispatch
Token ID27965
Feature activation-6.80e-01

Pos logit contributions
uid+0.979
+0.881
quote+0.849
í+0.837
 Ladies+0.805
Neg logit contributions
soever-0.702
 adversary-0.668
��-0.659
achine-0.637
 Canaver-0.615
Token of
Token ID286
Feature activation-4.32e-01

Pos logit contributions
uid+3.292
+2.874
í+2.804
quote+2.728
ú+2.518
Neg logit contributions
soever-3.522
 adversary-3.340
��-3.264
achine-3.164
 Canaver-3.104
Token tanks
Token ID11657
Feature activation+2.40e-01

Pos logit contributions
uid+2.525
+2.273
í+2.194
quote+2.180
 Ladies+2.100
Neg logit contributions
soever-1.796
��-1.682
 adversary-1.676
achine-1.623
anooga-1.574
Token bureau
Token ID10583
Feature activation-8.90e-01

Pos logit contributions
soever+0.079
 adversary+0.077
��+0.075
achine+0.072
anooga+0.070
Neg logit contributions
uid-0.101
-0.091
quote-0.087
í-0.085
 Ladies-0.081
Token
Token ID447
Feature activation-3.99e-01

Pos logit contributions
uid+4.202
+3.641
í+3.541
quote+3.454
 Ladies+3.259
Neg logit contributions
soever-4.652
 adversary-4.507
��-4.489
achine-4.416
 Canaver-4.276
Token
Token ID247
Feature activation-4.74e-01

Pos logit contributions
uid+1.822
+1.598
quote+1.521
í+1.474
 Ladies+1.404
Neg logit contributions
soever-2.172
 adversary-2.116
��-2.085
achine-2.016
anooga-1.970
Tokens
Token ID82
Feature activation-1.63e-01

Pos logit contributions
uid+2.624
+2.316
quote+2.235
í+2.235
 Ladies+2.095
Neg logit contributions
soever-2.138
 adversary-2.071
��-2.067
achine-1.985
 Canaver-1.927
Token many
Token ID867
Feature activation-1.92e-01

Pos logit contributions
uid+0.931
+0.839
quote+0.804
í+0.782
 Ladies+0.754
Neg logit contributions
soever-0.706
 adversary-0.685
��-0.660
achine-0.636
 Canaver-0.618
Token tech
Token ID7261
Feature activation+9.44e-01

Pos logit contributions
uid+1.097
+0.986
quote+0.946
í+0.928
 Ladies+0.891
Neg logit contributions
soever-0.831
 adversary-0.804
��-0.784
achine-0.757
anooga-0.734
Token teams
Token ID3466
Feature activation+3.69e-01

Pos logit contributions
soever+3.612
 adversary+3.555
��+3.274
anooga+3.151
achine+3.143
Neg logit contributions
uid-5.701
-5.209
quote-4.926
í-4.700
 Ladies-4.692
Token conduct
Token ID3189
Feature activation+2.19e-01

Pos logit contributions
soever+1.595
 adversary+1.554
achine+1.423
��+1.420
 Canaver+1.376
Neg logit contributions
uid-2.104
-1.899
quote-1.811
í-1.728
 Ladies-1.703
Token its
Token ID663
Feature activation+2.94e-01

Pos logit contributions
soever+0.902
 adversary+0.876
��+0.849
achine+0.817
 Canaver+0.791
Neg logit contributions
uid-1.295
-1.167
quote-1.122
í-1.100
 Ladies-1.063
Token own
Token ID898
Feature activation+3.81e-02

Pos logit contributions
soever+1.030
 adversary+1.004
��+0.943
achine+0.899
 Canaver+0.867
Neg logit contributions
uid-1.909
-1.741
quote-1.682
í-1.641
 Ladies-1.597
Token investigation
Token ID3645
Feature activation+8.93e-02

Pos logit contributions
soever+0.132
 adversary+0.126
��+0.122
achine+0.117
anooga+0.112
Neg logit contributions
uid-0.251
-0.228
quote-0.221
í-0.217
 Ladies-0.210
Token then
Token ID788
Feature activation+6.73e-01

Pos logit contributions
soever+1.395
 adversary+1.349
��+1.309
achine+1.261
 Canaver+1.243
Neg logit contributions
uid-1.803
-1.614
quote-1.539
í-1.496
 Ladies-1.455
Token-
Token ID12
Feature activation-2.44e-01

Pos logit contributions
soever+2.911
 adversary+2.823
��+2.699
achine+2.598
 Canaver+2.588
Neg logit contributions
uid-3.783
-3.380
quote-3.212
í-3.118
united-3.034
TokenSea
Token ID37567
Feature activation+5.18e-01

Pos logit contributions
uid+1.298
+1.152
quote+1.106
í+1.086
 Ladies+1.031
Neg logit contributions
soever-1.162
 adversary-1.121
��-1.104
achine-1.070
 Canaver-1.040
TokenWorld
Token ID10603
Feature activation-3.72e-01

Pos logit contributions
soever+2.295
 adversary+2.292
achine+2.175
��+2.145
anooga+2.079
Neg logit contributions
uid-2.776
-2.508
quote-2.400
í-2.302
 Ladies-2.214
Token CEO
Token ID6123
Feature activation+3.10e-01

Pos logit contributions
uid+1.842
+1.622
quote+1.549
í+1.526
 Ladies+1.448
Neg logit contributions
soever-1.898
 adversary-1.836
��-1.811
achine-1.760
anooga-1.711
Token Jim
Token ID5395
Feature activation+1.32e+00

Pos logit contributions
soever+1.347
 adversary+1.302
��+1.266
achine+1.229
 Canaver+1.198
Neg logit contributions
uid-1.759
-1.583
quote-1.517
í-1.484
 Ladies-1.419
Token At
Token ID1629
Feature activation+7.82e-01

Pos logit contributions
soever+5.612
 adversary+5.335
 Canaver+5.311
achine+5.231
��+5.193
Neg logit contributions
uid-7.015
-6.593
quote-6.140
united-5.714
í-5.692
Tokench
Token ID354
Feature activation+4.86e-01

Pos logit contributions
soever+3.308
 adversary+3.206
achine+3.109
��+3.034
anooga+2.932
Neg logit contributions
uid-4.333
-4.036
quote-3.798
í-3.612
 Ladies-3.593
Tokenison
Token ID1653
Feature activation-9.42e-02

Pos logit contributions
soever+1.983
 adversary+1.906
��+1.856
achine+1.814
anooga+1.740
Neg logit contributions
uid-2.881
-2.607
quote-2.501
í-2.447
 Ladies-2.365
Token said
Token ID531
Feature activation+5.41e-02

Pos logit contributions
uid+0.518
+0.463
quote+0.443
í+0.434
 Ladies+0.416
Neg logit contributions
soever-0.427
 adversary-0.414
��-0.404
achine-0.392
anooga-0.381
Token in
Token ID287
Feature activation+1.39e-01

Pos logit contributions
soever+0.242
 adversary+0.234
��+0.229
achine+0.221
 Canaver+0.215
Neg logit contributions
uid-0.301
-0.269
quote-0.258
í-0.253
 Ladies-0.243
Token (
Token ID357
Feature activation+1.64e-01

Pos logit contributions
uid+2.341
+2.075
í+2.010
quote+1.986
 Ladies+1.864
Neg logit contributions
soever-2.463
��-2.373
 adversary-2.360
achine-2.298
anooga-2.258
Tokenall
Token ID439
Feature activation-1.01e-01

Pos logit contributions
soever+0.738
 adversary+0.714
��+0.698
achine+0.677
anooga+0.656
Neg logit contributions
uid-0.912
-0.816
quote-0.782
í-0.768
 Ladies-0.738
Token pro
Token ID386
Feature activation+8.34e-03

Pos logit contributions
uid+0.576
+0.517
quote+0.497
í+0.492
 Ladies+0.468
Neg logit contributions
soever-0.436
 adversary-0.422
��-0.414
achine-0.400
anooga-0.389
Token-
Token ID12
Feature activation+1.01e+00

Pos logit contributions
soever+0.042
 adversary+0.041
��+0.041
 Canaver+0.040
achine+0.039
Neg logit contributions
uid-0.041
-0.037
í-0.035
quote-0.035
 Ladies-0.032
Tokenindependence
Token ID39894
Feature activation+1.12e+00

Pos logit contributions
soever+4.429
 adversary+4.259
��+4.060
achine+3.991
anooga+3.814
Neg logit contributions
uid-5.443
-4.910
quote-4.657
í-4.539
 Ladies-4.503
Token parties
Token ID4671
Feature activation+1.09e+00

Pos logit contributions
soever+4.320
 adversary+4.157
��+3.860
achine+3.769
 Canaver+3.545
Neg logit contributions
uid-6.814
-6.056
quote-5.851
í-5.525
united-5.491
Token form
Token ID1296
Feature activation+9.61e-02

Pos logit contributions
soever+4.563
 adversary+4.433
achine+4.072
��+3.934
 Canaver+3.906
Neg logit contributions
uid-6.213
-5.540
quote-5.276
 Ladies-4.949
í-4.944
Token a
Token ID257
Feature activation-3.36e-01

Pos logit contributions
soever+0.404
 adversary+0.390
��+0.381
achine+0.368
anooga+0.356
Neg logit contributions
uid-0.561
-0.505
quote-0.486
í-0.477
 Ladies-0.459
Token legislative
Token ID10828
Feature activation-1.53e-01

Pos logit contributions
uid+1.861
+1.671
quote+1.599
í+1.580
 Ladies+1.509
Neg logit contributions
soever-1.510
 adversary-1.454
��-1.431
achine-1.384
anooga-1.349
Token majority
Token ID3741
Feature activation-2.00e-01

Pos logit contributions
uid+0.895
+0.806
quote+0.775
í+0.763
 Ladies+0.732
Neg logit contributions
soever-0.636
 adversary-0.614
��-0.600
achine-0.580
anooga-0.561
Token of
Token ID286
Feature activation-5.27e-01

Pos logit contributions
uid+1.121
+1.005
quote+0.962
í+0.953
 Ladies+0.905
Neg logit contributions
soever-0.888
 adversary-0.855
��-0.845
achine-0.813
anooga-0.796
Token promotional
Token ID18767
Feature activation-8.22e-02

Pos logit contributions
uid+0.036
+0.033
quote+0.030
í+0.030
 Ladies+0.028
Neg logit contributions
soever-0.029
 adversary-0.029
achine-0.027
��-0.027
 Canaver-0.026
Token offers
Token ID4394
Feature activation-2.39e-01

Pos logit contributions
uid+0.526
+0.480
quote+0.459
í+0.452
 Ladies+0.431
Neg logit contributions
soever-0.297
 adversary-0.292
achine-0.273
��-0.270
 Canaver-0.257
Token for
Token ID329
Feature activation+3.65e-01

Pos logit contributions
uid+1.513
+1.374
quote+1.313
í+1.277
 Ladies+1.249
Neg logit contributions
soever-0.888
 adversary-0.853
achine-0.798
��-0.794
 Canaver-0.763
Token programs
Token ID4056
Feature activation+9.08e-01

Pos logit contributions
soever+1.050
 adversary+1.017
achine+0.893
 exemplary+0.882
��+0.861
Neg logit contributions
uid-2.597
-2.385
quote-2.305
í-2.232
tta-2.166
Token that
Token ID326
Feature activation+6.37e-01

Pos logit contributions
 adversary+2.469
soever+2.428
achine+2.211
 weakness+2.207
 decomp+2.176
Neg logit contributions
uid-6.201
-5.753
quote-5.328
 Ladies-5.271
í-5.052
Token support
Token ID1104
Feature activation+8.67e-01

Pos logit contributions
 adversary+2.157
soever+2.040
 weakness+1.840
 decomp+1.799
achine+1.797
Neg logit contributions
uid-4.116
-3.815
quote-3.562
 Ladies-3.402
                -3.359
Token The
Token ID383
Feature activation+7.20e-01

Pos logit contributions
 adversary+3.578
soever+3.575
��+3.376
achine+3.346
 exemplary+3.213
Neg logit contributions
uid-4.944
-4.379
quote-4.140
í-3.965
sell-3.810
Token Nation
Token ID8741
Feature activation+5.34e-01

Pos logit contributions
 adversary+2.509
soever+2.393
 weakness+2.134
achine+2.126
��+2.105
Neg logit contributions
uid-4.457
-4.165
quote-3.889
í-3.703
 Ladies-3.619
Token
Token ID447
Feature activation+8.15e-01

Pos logit contributions
 adversary+2.198
soever+2.172
achine+1.975
 weakness+1.934
 intruder+1.912
Neg logit contributions
uid-3.004
-2.728
quote-2.579
 Ladies-2.449
united-2.409
Token
Token ID247
Feature activation+3.92e-02

Pos logit contributions
soever+3.616
 adversary+3.611
��+3.422
achine+3.247
anooga+3.203
Neg logit contributions
uid-4.077
-3.785
quote-3.651
 Ladies-3.480
united-3.422
Tokens
Token ID82
Feature activation+5.33e-01

Pos logit contributions
soever+0.138
 adversary+0.132
achine+0.126
��+0.117
 Canaver+0.117
Neg logit contributions
uid-0.245
-0.222
quote-0.213
 Ladies-0.206
í-0.202
Token
Token ID247
Feature activation-3.14e-01

Pos logit contributions
soever+1.275
��+1.244
 adversary+1.244
achine+1.157
anooga+1.132
Neg logit contributions
uid-1.272
-1.128
quote-1.108
í-1.037
united-1.018
Tokens
Token ID82
Feature activation+2.02e-01

Pos logit contributions
uid+1.583
+1.401
quote+1.327
í+1.320
 Ladies+1.245
Neg logit contributions
soever-1.566
 adversary-1.523
��-1.495
achine-1.458
anooga-1.423
Token a
Token ID257
Feature activation+1.52e-01

Pos logit contributions
soever+0.852
 adversary+0.823
��+0.801
achine+0.777
 Canaver+0.752
Neg logit contributions
uid-1.178
-1.057
quote-1.018
í-0.996
 Ladies-0.960
Token lot
Token ID1256
Feature activation+4.84e-01

Pos logit contributions
soever+0.635
 adversary+0.616
��+0.598
achine+0.578
anooga+0.559
Neg logit contributions
uid-0.885
-0.793
quote-0.762
í-0.748
 Ladies-0.717
Token of
Token ID286
Feature activation+1.97e-01

Pos logit contributions
soever+2.100
 adversary+2.038
��+1.987
achine+1.928
 Canaver+1.868
Neg logit contributions
uid-2.733
-2.452
quote-2.351
í-2.303
 Ladies-2.221
Token anger
Token ID8993
Feature activation+3.69e-01

Pos logit contributions
soever+0.802
 adversary+0.784
��+0.752
achine+0.731
 Canaver+0.708
Neg logit contributions
uid-1.177
-1.063
quote-1.015
í-0.998
 Ladies-0.960
Token,
Token ID11
Feature activation+2.22e-01

Pos logit contributions
soever+1.608
 adversary+1.551
��+1.498
achine+1.481
anooga+1.419
Neg logit contributions
uid-2.090
-1.868
quote-1.786
í-1.746
 Ladies-1.696
Token there
Token ID612
Feature activation+1.07e-01

Pos logit contributions
soever+0.934
 adversary+0.902
��+0.871
achine+0.847
 Canaver+0.818
Neg logit contributions
uid-1.297
-1.171
quote-1.119
í-1.094
 Ladies-1.056
Token
Token ID447
Feature activation+3.33e-01

Pos logit contributions
soever+0.499
 adversary+0.484
��+0.475
achine+0.461
 Canaver+0.447
Neg logit contributions
uid-0.574
-0.512
quote-0.490
í-0.483
 Ladies-0.460
Token
Token ID247
Feature activation-2.19e-01

Pos logit contributions
soever+1.664
��+1.626
 adversary+1.625
achine+1.519
 Canaver+1.489
Neg logit contributions
uid-1.630
-1.441
quote-1.412
í-1.332
 Ladies-1.292
Tokens
Token ID82
Feature activation+3.92e-01

Pos logit contributions
uid+1.204
+1.076
quote+1.028
í+1.025
 Ladies+0.968
Neg logit contributions
soever-0.989
 adversary-0.964
��-0.951
achine-0.917
anooga-0.894
Token
Token ID447
Feature activation+8.98e-02

Pos logit contributions
uid+0.443
+0.400
quote+0.383
í+0.382
 Ladies+0.362
Neg logit contributions
soever-0.321
 adversary-0.310
��-0.305
achine-0.294
 Canaver-0.285
Token
Token ID247
Feature activation-5.05e-01

Pos logit contributions
soever+0.461
 adversary+0.447
��+0.442
achine+0.418
anooga+0.409
Neg logit contributions
uid-0.434
-0.385
quote-0.371
í-0.351
united-0.342
Tokens
Token ID82
Feature activation-3.45e-02

Pos logit contributions
uid+2.783
+2.482
quote+2.380
í+2.377
 Ladies+2.235
Neg logit contributions
soever-2.282
 adversary-2.223
��-2.212
achine-2.103
anooga-2.066
Token a
Token ID257
Feature activation-3.87e-01

Pos logit contributions
uid+0.201
+0.180
quote+0.173
í+0.170
 Ladies+0.164
Neg logit contributions
soever-0.146
 adversary-0.141
��-0.138
achine-0.133
anooga-0.129
Token brilliant
Token ID10457
Feature activation-8.43e-02

Pos logit contributions
uid+2.257
+2.043
quote+1.962
í+1.941
 Ladies+1.865
Neg logit contributions
soever-1.620
 adversary-1.546
��-1.534
achine-1.478
anooga-1.434
Token writer
Token ID6260
Feature activation-7.77e-02

Pos logit contributions
uid+0.519
+0.469
quote+0.451
í+0.444
 Ladies+0.428
Neg logit contributions
soever-0.328
 adversary-0.316
��-0.307
achine-0.296
anooga-0.286
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
uid+0.420
+0.376
quote+0.359
í+0.356
 Ladies+0.338
Neg logit contributions
soever-0.359
 adversary-0.348
��-0.344
achine-0.332
 Canaver-0.323
Token
Token ID447
Feature activation+2.94e-02

Pos logit contributions
uid+0.636
+0.562
quote+0.536
í+0.526
 Ladies+0.500
Neg logit contributions
soever-0.652
 adversary-0.634
��-0.622
achine-0.605
anooga-0.589
Token
Token ID251
Feature activation+2.40e-02

Pos logit contributions
soever+0.153
 adversary+0.149
��+0.146
achine+0.143
anooga+0.139
Neg logit contributions
uid-0.142
-0.125
quote-0.119
í-0.117
 Ladies-0.111
Token<|endoftext|>
Token ID50256
Feature activation+5.73e-01

Pos logit contributions
soever+0.123
 adversary+0.119
��+0.117
achine+0.114
anooga+0.111
Neg logit contributions
uid-0.119
-0.105
quote-0.100
í-0.098
 Ladies-0.093
TokenAnother
Token ID6610
Feature activation-4.57e-01

Pos logit contributions
soever+2.628
 adversary+2.532
��+2.489
achine+2.419
anooga+2.349
Neg logit contributions
uid-3.055
-2.735
quote-2.580
í-2.559
 Ladies-2.470
Token inspired
Token ID7867
Feature activation+6.61e-01

Pos logit contributions
soever+3.486
 adversary+3.412
��+3.255
achine+3.169
anooga+3.028
Neg logit contributions
uid-4.455
-4.024
quote-3.845
í-3.731
 Ladies-3.581
Token by
Token ID416
Feature activation+2.14e-01

Pos logit contributions
soever+2.747
 adversary+2.681
��+2.525
achine+2.469
anooga+2.369
Neg logit contributions
uid-3.869
-3.491
quote-3.314
í-3.264
united-3.113
Token the
Token ID262
Feature activation-1.47e-01

Pos logit contributions
soever+0.962
 adversary+0.935
��+0.908
achine+0.883
 Canaver+0.856
Neg logit contributions
uid-1.187
-1.064
quote-1.014
í-0.997
 Ladies-0.951
Token Three
Token ID7683
Feature activation+6.89e-03

Pos logit contributions
uid+0.825
+0.737
quote+0.712
í+0.700
 Ladies+0.673
Neg logit contributions
soever-0.654
 adversary-0.628
��-0.621
achine-0.599
anooga-0.582
Token Fl
Token ID1610
Feature activation-5.73e-01

Pos logit contributions
soever+0.031
 adversary+0.030
��+0.029
achine+0.029
anooga+0.028
Neg logit contributions
uid-0.038
-0.034
quote-0.033
í-0.032
 Ladies-0.031
Tokenoy
Token ID726
Feature activation+9.03e-02

Pos logit contributions
uid+2.704
+2.205
í+2.152
quote+2.146
 Ladies+1.986
Neg logit contributions
soever-3.172
 adversary-3.110
��-3.061
achine-2.919
 Canaver-2.906
Tokends
Token ID9310
Feature activation+2.01e-02

Pos logit contributions
soever+0.397
 adversary+0.384
��+0.377
achine+0.365
 Canaver+0.355
Neg logit contributions
uid-0.512
-0.457
quote-0.440
í-0.435
 Ladies-0.416
Token-
Token ID12
Feature activation+4.49e-02

Pos logit contributions
soever+0.091
 adversary+0.088
��+0.086
achine+0.084
anooga+0.081
Neg logit contributions
uid-0.111
-0.099
quote-0.095
í-0.093
 Ladies-0.089
TokenHalf
Token ID31305
Feature activation-6.98e-01

Pos logit contributions
soever+0.223
 adversary+0.216
��+0.212
achine+0.206
anooga+0.201
Neg logit contributions
uid-0.228
-0.201
quote-0.192
í-0.189
 Ladies-0.180
Token Ac
Token ID4013
Feature activation-3.17e-01

Pos logit contributions
uid+3.554
+3.127
quote+3.039
í+2.983
 Ladies+2.899
Neg logit contributions
soever-3.367
 adversary-3.298
��-3.263
achine-3.131
 Canaver-3.091
Tokenre
Token ID260
Feature activation-2.95e-01

Pos logit contributions
uid+1.465
+1.246
quote+1.186
í+1.180
 Ladies+1.087
Neg logit contributions
soever-1.747
 adversary-1.696
��-1.690
achine-1.616
 Canaver-1.612
TokenBel
Token ID12193
Feature activation-7.12e-01

Pos logit contributions
uid+0.396
+0.353
quote+0.337
í+0.331
 Ladies+0.317
Neg logit contributions
soever-0.353
 adversary-0.341
��-0.334
achine-0.325
anooga-0.316
Tokenieve
Token ID12311
Feature activation+4.12e-02

Pos logit contributions
uid+2.467
+2.006
í+1.976
quote+1.933
 Ladies+1.748
Neg logit contributions
soever-4.676
 adversary-4.578
��-4.549
achine-4.352
 Canaver-4.311
Token me
Token ID502
Feature activation+7.19e-02

Pos logit contributions
soever+0.174
 adversary+0.169
��+0.166
achine+0.160
anooga+0.156
Neg logit contributions
uid-0.239
-0.214
quote-0.207
í-0.205
 Ladies-0.196
Token,
Token ID11
Feature activation+4.48e-02

Pos logit contributions
soever+0.332
 adversary+0.322
��+0.317
achine+0.306
anooga+0.298
Neg logit contributions
uid-0.389
-0.348
quote-0.333
í-0.328
 Ladies-0.315
Token Anna
Token ID11735
Feature activation-8.23e-02

Pos logit contributions
soever+0.207
 adversary+0.200
��+0.193
achine+0.189
 Canaver+0.184
Neg logit contributions
uid-0.244
-0.217
quote-0.208
í-0.202
 Ladies-0.192
Token.
Token ID13
Feature activation+9.94e-02

Pos logit contributions
uid+0.427
+0.382
quote+0.364
í+0.364
 Ladies+0.348
Neg logit contributions
soever-0.395
 adversary-0.384
��-0.380
achine-0.369
 Canaver-0.358
Token If
Token ID1002
Feature activation+1.03e-01

Pos logit contributions
soever+0.466
 adversary+0.441
��+0.425
achine+0.425
 Canaver+0.419
Neg logit contributions
uid-0.537
-0.471
quote-0.449
í-0.432
united-0.417
Token I
Token ID314
Feature activation+3.25e-02

Pos logit contributions
soever+0.455
 adversary+0.440
��+0.430
achine+0.417
anooga+0.404
Neg logit contributions
uid-0.577
-0.516
quote-0.495
í-0.487
 Ladies-0.466
Token want
Token ID765
Feature activation+4.22e-01

Pos logit contributions
soever+0.144
 adversary+0.142
achine+0.132
��+0.131
 Canaver+0.127
Neg logit contributions
uid-0.180
-0.162
quote-0.154
í-0.148
 Ladies-0.144
Token to
Token ID284
Feature activation+6.44e-01

Pos logit contributions
soever+1.862
 adversary+1.799
��+1.762
achine+1.704
anooga+1.654
Neg logit contributions
uid-2.377
-2.132
quote-2.044
í-2.013
 Ladies-1.929
Token get
Token ID651
Feature activation+4.05e-01

Pos logit contributions
soever+2.550
 adversary+2.521
achine+2.345
��+2.296
 decomp+2.245
Neg logit contributions
uid-3.815
-3.421
quote-3.272
í-3.163
united-3.076
Token the
Token ID262
Feature activation-1.82e-01

Pos logit contributions
uid+2.195
+1.968
quote+1.894
í+1.860
 Ladies+1.780
Neg logit contributions
soever-1.783
 adversary-1.718
��-1.687
achine-1.638
anooga-1.591
Token arguments
Token ID7159
Feature activation-1.75e-01

Pos logit contributions
uid+1.077
+0.970
quote+0.930
í+0.917
 Ladies+0.879
Neg logit contributions
soever-0.747
 adversary-0.724
��-0.704
achine-0.679
 Canaver-0.658
Token against
Token ID1028
Feature activation+3.99e-01

Pos logit contributions
uid+0.981
+0.879
quote+0.843
í+0.830
 Ladies+0.794
Neg logit contributions
soever-0.773
 adversary-0.748
��-0.732
achine-0.709
anooga-0.687
Token the
Token ID262
Feature activation+8.24e-03

Pos logit contributions
soever+2.066
 adversary+2.019
��+1.962
achine+1.916
 Canaver+1.880
Neg logit contributions
uid-1.928
-1.689
quote-1.595
í-1.567
 Ladies-1.480
Token comparison
Token ID7208
Feature activation-2.43e-01

Pos logit contributions
soever+0.038
 adversary+0.037
��+0.036
achine+0.035
 Canaver+0.034
Neg logit contributions
uid-0.045
-0.040
quote-0.038
í-0.038
 Ladies-0.036
Token instead
Token ID2427
Feature activation+4.16e-01

Pos logit contributions
uid+1.347
+1.210
quote+1.157
í+1.142
 Ladies+1.092
Neg logit contributions
soever-1.092
 adversary-1.053
��-1.037
achine-1.002
 Canaver-0.973
Token of
Token ID286
Feature activation+4.78e-01

Pos logit contributions
soever+1.958
 adversary+1.890
��+1.853
achine+1.800
 Canaver+1.748
Neg logit contributions
uid-2.235
-1.996
quote-1.909
í-1.881
 Ladies-1.794
Token,
Token ID11
Feature activation-5.70e-01

Pos logit contributions
soever+2.040
 adversary+1.996
��+1.905
achine+1.844
 Canaver+1.799
Neg logit contributions
uid-2.754
-2.446
quote-2.336
í-2.299
united-2.199
Token say
Token ID910
Feature activation+1.95e-01

Pos logit contributions
uid+2.790
+2.443
quote+2.349
í+2.323
 Ladies+2.217
Neg logit contributions
soever-2.929
 adversary-2.818
��-2.796
achine-2.711
anooga-2.641
Token,
Token ID11
Feature activation+5.45e-02

Pos logit contributions
soever+0.755
 adversary+0.733
achine+0.685
��+0.679
 Canaver+0.664
Neg logit contributions
uid-1.188
-1.071
quote-1.016
í-0.986
united-0.968
Token listing
Token ID13487
Feature activation+9.85e-02

Pos logit contributions
soever+0.240
 adversary+0.233
��+0.227
achine+0.220
 Canaver+0.213
Neg logit contributions
uid-0.308
-0.275
quote-0.264
í-0.260
 Ladies-0.248
Tokenoad
Token ID1170
Feature activation+6.92e-01

Pos logit contributions
uid+0.086
+0.074
quote+0.071
í+0.070
 Ladies+0.066
Neg logit contributions
soever-0.102
 adversary-0.099
��-0.098
achine-0.095
 Canaver-0.093
Token,
Token ID11
Feature activation+2.22e-01

Pos logit contributions
soever+3.349
 adversary+3.250
��+3.188
achine+3.127
anooga+3.010
Neg logit contributions
uid-3.530
-3.126
quote-2.953
í-2.923
 Ladies-2.770
Token April
Token ID3035
Feature activation+5.14e-01

Pos logit contributions
soever+1.064
 adversary+1.041
��+1.014
achine+0.985
 Canaver+0.957
Neg logit contributions
uid-1.157
-1.021
quote-0.979
í-0.962
 Ladies-0.910
Token 18
Token ID1248
Feature activation-9.00e-01

Pos logit contributions
soever+2.560
 adversary+2.501
��+2.363
achine+2.348
 Canaver+2.267
Neg logit contributions
uid-2.574
-2.284
quote-2.091
í-2.034
united-1.959
Tokenth
Token ID400
Feature activation-1.32e+00

Pos logit contributions
uid+4.215
+3.700
quote+3.614
í+3.503
 Ladies+3.290
Neg logit contributions
soever-4.739
 adversary-4.572
��-4.541
achine-4.367
anooga-4.337
Token,
Token ID11
Feature activation-6.14e-01

Pos logit contributions
uid+6.185
+5.575
quote+5.457
í+5.263
 Ladies+5.096
Neg logit contributions
soever-6.640
��-6.340
 adversary-6.283
 Canaver-6.138
achine-6.075
Token 2017
Token ID2177
Feature activation-1.93e-01

Pos logit contributions
uid+2.291
+1.944
quote+1.832
í+1.785
 Ladies+1.673
Neg logit contributions
soever-3.852
 adversary-3.754
��-3.723
achine-3.628
anooga-3.568
Token
Token ID198
Feature activation-2.39e-02

Pos logit contributions
uid+0.922
+0.817
quote+0.780
í+0.765
 Ladies+0.727
Neg logit contributions
soever-1.011
 adversary-0.987
��-0.969
achine-0.943
anooga-0.923
Token
Token ID198
Feature activation-1.14e-01

Pos logit contributions
uid+0.130
+0.118
quote+0.110
í+0.106
 Ladies+0.104
Neg logit contributions
soever-0.104
 adversary-0.101
achine-0.098
 Canaver-0.093
��-0.093
TokenKo
Token ID48735
Feature activation+1.10e+00

Pos logit contributions
uid+0.626
+0.558
quote+0.538
í+0.527
 Ladies+0.498
Neg logit contributions
soever-0.525
 adversary-0.509
��-0.498
achine-0.481
 Canaver-0.472
TokenDo
Token ID5211
Feature activation+5.34e-01

Pos logit contributions
soever+5.123
 adversary+5.000
��+4.875
achine+4.851
anooga+4.673
Neg logit contributions
uid-5.703
-5.018
quote-4.823
í-4.653
 Ladies-4.529
Token water
Token ID1660
Feature activation-1.14e-01

Pos logit contributions
soever+0.184
 adversary+0.177
��+0.173
achine+0.167
anooga+0.161
Neg logit contributions
uid-0.271
-0.245
quote-0.235
í-0.232
 Ladies-0.223
Token supply
Token ID5127
Feature activation-2.45e-01

Pos logit contributions
uid+0.662
+0.595
quote+0.571
í+0.562
 Ladies+0.539
Neg logit contributions
soever-0.486
 adversary-0.470
��-0.459
achine-0.444
anooga-0.430
Token from
Token ID422
Feature activation-4.16e-01

Pos logit contributions
uid+1.333
+1.191
quote+1.143
í+1.132
 Ladies+1.075
Neg logit contributions
soever-1.114
 adversary-1.081
��-1.070
achine-1.031
anooga-1.004
Token the
Token ID262
Feature activation-5.32e-01

Pos logit contributions
uid+2.281
+2.033
quote+1.956
í+1.941
 Ladies+1.856
Neg logit contributions
soever-1.871
 adversary-1.807
��-1.780
achine-1.735
anooga-1.684
Token airport
Token ID9003
Feature activation-9.17e-01

Pos logit contributions
uid+2.928
+2.610
quote+2.515
í+2.494
 Ladies+2.398
Neg logit contributions
soever-2.369
 adversary-2.281
��-2.255
achine-2.189
anooga-2.134
Token,
Token ID11
Feature activation-3.70e-01

Pos logit contributions
uid+4.507
+3.936
í+3.904
quote+3.842
 Ladies+3.607
Neg logit contributions
soever-4.406
��-4.347
 adversary-4.326
achine-4.191
 Canaver-4.157
Token however
Token ID2158
Feature activation+4.58e-01

Pos logit contributions
uid+2.100
+1.883
quote+1.802
í+1.798
 Ladies+1.709
Neg logit contributions
soever-1.599
 adversary-1.549
��-1.529
achine-1.478
anooga-1.436
Token.
Token ID13
Feature activation-2.67e-01

Pos logit contributions
soever+2.149
 adversary+2.085
��+2.041
achine+1.987
anooga+1.928
Neg logit contributions
uid-2.452
-2.186
quote-2.092
í-2.062
 Ladies-1.965
Token The
Token ID383
Feature activation+1.33e-02

Pos logit contributions
uid+1.345
+1.187
quote+1.132
í+1.106
 Ladies+1.054
Neg logit contributions
soever-1.338
 adversary-1.294
��-1.268
achine-1.235
 Canaver-1.207
Token vast
Token ID5909
Feature activation-4.32e-01

Pos logit contributions
soever+0.052
 adversary+0.050
��+0.048
achine+0.046
anooga+0.045
Neg logit contributions
uid-0.082
-0.074
quote-0.071
í-0.070
 Ladies-0.067
Token majority
Token ID3741
Feature activation-5.44e-01

Pos logit contributions
uid+2.211
+1.957
quote+1.864
í+1.849
 Ladies+1.756
Neg logit contributions
soever-2.121
 adversary-2.033
��-2.005
achine-1.953
 Canaver-1.915
Token real
Token ID1103
Feature activation-2.12e-01

Pos logit contributions
uid+0.637
+0.574
quote+0.551
í+0.543
 Ladies+0.522
Neg logit contributions
soever-0.458
 adversary-0.441
��-0.432
achine-0.417
anooga-0.404
Token world
Token ID995
Feature activation-1.05e-01

Pos logit contributions
uid+1.219
+1.094
quote+1.056
í+1.047
 Ladies+1.004
Neg logit contributions
soever-0.908
��-0.861
 adversary-0.860
achine-0.824
 Canaver-0.803
Token projected
Token ID13301
Feature activation-4.80e-01

Pos logit contributions
uid+0.599
+0.538
quote+0.516
í+0.508
 Ladies+0.487
Neg logit contributions
soever-0.454
 adversary-0.438
��-0.430
achine-0.416
anooga-0.403
Token onto
Token ID4291
Feature activation-4.98e-01

Pos logit contributions
uid+2.495
+2.222
quote+2.134
í+2.105
 Ladies+2.007
Neg logit contributions
soever-2.297
��-2.236
 adversary-2.197
achine-2.117
anooga-2.078
Token their
Token ID511
Feature activation-1.95e-01

Pos logit contributions
uid+2.630
+2.347
quote+2.260
í+2.246
 Ladies+2.147
Neg logit contributions
soever-2.325
��-2.227
 adversary-2.221
achine-2.146
anooga-2.092
Token screen
Token ID3159
Feature activation-3.29e-01

Pos logit contributions
uid+1.045
+0.931
quote+0.892
í+0.879
 Ladies+0.840
Neg logit contributions
soever-0.913
 adversary-0.881
��-0.869
achine-0.844
anooga-0.819
Token via
Token ID2884
Feature activation-7.17e-01

Pos logit contributions
uid+1.755
+1.552
quote+1.496
í+1.475
 Ladies+1.404
Neg logit contributions
soever-1.539
 adversary-1.494
��-1.488
achine-1.427
 Canaver-1.397
Token their
Token ID511
Feature activation-5.40e-01

Pos logit contributions
uid+3.843
+3.410
quote+3.302
í+3.277
 Ladies+3.153
Neg logit contributions
soever-3.267
��-3.100
 adversary-3.093
achine-3.006
anooga-2.940
Token phone
Token ID3072
Feature activation-4.65e-01

Pos logit contributions
uid+2.771
+2.439
quote+2.347
í+2.325
 Ladies+2.218
Neg logit contributions
soever-2.634
 adversary-2.524
��-2.509
achine-2.450
anooga-2.381
Token's
Token ID338
Feature activation-9.88e-02

Pos logit contributions
uid+2.419
+2.120
quote+2.052
í+2.033
 Ladies+1.919
Neg logit contributions
soever-2.222
 adversary-2.158
��-2.153
achine-2.073
anooga-2.040
Token camera
Token ID4676
Feature activation-1.37e-01

Pos logit contributions
uid+0.569
+0.513
quote+0.491
í+0.482
 Ladies+0.462
Neg logit contributions
soever-0.424
 adversary-0.410
��-0.399
achine-0.386
 Canaver-0.373
Token Many
Token ID4650
Feature activation-1.91e-01

Pos logit contributions
soever+0.101
 adversary+0.098
��+0.096
achine+0.093
anooga+0.091
Neg logit contributions
uid-0.096
-0.084
quote-0.080
í-0.079
 Ladies-0.075
Token states
Token ID2585
Feature activation+8.05e-02

Pos logit contributions
uid+1.128
+1.016
quote+0.978
í+0.963
 Ladies+0.925
Neg logit contributions
soever-0.793
 adversary-0.764
��-0.748
achine-0.723
anooga-0.699
Token and
Token ID290
Feature activation+6.46e-02

Pos logit contributions
soever+0.347
 adversary+0.338
��+0.320
achine+0.316
 Canaver+0.304
Neg logit contributions
uid-0.459
-0.414
quote-0.395
í-0.385
 Ladies-0.373
Token individuals
Token ID3925
Feature activation+1.67e-01

Pos logit contributions
soever+0.282
 adversary+0.272
��+0.266
achine+0.258
anooga+0.250
Neg logit contributions
uid-0.367
-0.330
quote-0.316
í-0.311
 Ladies-0.298
Token brought
Token ID3181
Feature activation+1.19e-01

Pos logit contributions
soever+0.723
 adversary+0.704
��+0.660
achine+0.657
 Canaver+0.632
Neg logit contributions
uid-0.949
-0.855
quote-0.815
í-0.793
 Ladies-0.770
Token litigation
Token ID19284
Feature activation-4.69e-01

Pos logit contributions
soever+0.448
 adversary+0.432
��+0.417
achine+0.403
 Canaver+0.388
Neg logit contributions
uid-0.749
-0.680
quote-0.656
í-0.646
 Ladies-0.621
Token against
Token ID1028
Feature activation-7.37e-02

Pos logit contributions
uid+2.457
+2.190
quote+2.083
í+2.079
 Ladies+1.968
Neg logit contributions
soever-2.227
��-2.160
 adversary-2.129
achine-2.062
anooga-2.028
Token tobacco
Token ID11219
Feature activation-1.06e+00

Pos logit contributions
uid+0.400
+0.355
quote+0.344
í+0.338
 Ladies+0.325
Neg logit contributions
soever-0.337
 adversary-0.325
��-0.322
achine-0.313
anooga-0.304
Token companies
Token ID2706
Feature activation-1.76e-01

Pos logit contributions
uid+5.568
quote+4.907
+4.898
í+4.893
 Ladies+4.606
Neg logit contributions
soever-4.780
��-4.565
 adversary-4.494
achine-4.370
 Canaver-4.285
Token,
Token ID11
Feature activation-1.57e-01

Pos logit contributions
uid+0.995
+0.892
quote+0.857
í+0.844
 Ladies+0.808
Neg logit contributions
soever-0.766
 adversary-0.740
��-0.727
achine-0.703
anooga-0.682
Token which
Token ID543
Feature activation+1.58e-01

Pos logit contributions
uid+0.935
+0.842
quote+0.811
í+0.800
 Ladies+0.769
Neg logit contributions
soever-0.637
 adversary-0.612
��-0.601
achine-0.579
anooga-0.561
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
uid+0.928
+0.827
quote+0.796
í+0.788
 Ladies+0.754
Neg logit contributions
soever-0.772
 adversary-0.746
��-0.736
achine-0.713
anooga-0.693
Token the
Token ID262
Feature activation-9.42e-03

Pos logit contributions
uid+1.057
+0.949
quote+0.913
í+0.899
 Ladies+0.862
Neg logit contributions
soever-0.793
 adversary-0.766
��-0.751
achine-0.728
anooga-0.705
Token brand
Token ID4508
Feature activation-7.58e-01

Pos logit contributions
uid+0.052
+0.047
quote+0.045
í+0.044
 Ladies+0.042
Neg logit contributions
soever-0.042
 adversary-0.041
��-0.040
achine-0.038
 Canaver-0.037
Token army
Token ID5428
Feature activation+1.74e-02

Pos logit contributions
uid+4.252
+3.790
quote+3.696
í+3.657
 Ladies+3.495
Neg logit contributions
soever-3.203
��-3.126
 adversary-3.078
achine-2.972
anooga-2.889
Token has
Token ID468
Feature activation+1.33e-02

Pos logit contributions
soever+0.068
 adversary+0.065
��+0.063
achine+0.061
anooga+0.059
Neg logit contributions
uid-0.107
-0.097
quote-0.093
í-0.091
 Ladies-0.088
Token rights
Token ID2489
Feature activation-3.46e-01

Pos logit contributions
soever+0.057
 adversary+0.055
��+0.054
achine+0.052
anooga+0.051
Neg logit contributions
uid-0.076
-0.068
quote-0.065
í-0.064
 Ladies-0.062
Token to
Token ID284
Feature activation-3.34e-01

Pos logit contributions
uid+1.833
+1.629
quote+1.571
í+1.564
 Ladies+1.473
Neg logit contributions
soever-1.603
��-1.556
 adversary-1.549
achine-1.499
anooga-1.477
Token enter
Token ID3802
Feature activation+7.65e-01

Pos logit contributions
uid+1.852
+1.654
quote+1.596
í+1.574
 Ladies+1.508
Neg logit contributions
soever-1.489
 adversary-1.434
��-1.422
achine-1.375
anooga-1.345
Token shops
Token ID12437
Feature activation-1.62e-01

Pos logit contributions
soever+3.262
 adversary+3.127
��+2.908
achine+2.811
anooga+2.745
Neg logit contributions
uid-4.456
-4.024
quote-3.810
í-3.694
 Ladies-3.542
Token and
Token ID290
Feature activation-5.86e-02

Pos logit contributions
uid+0.937
+0.844
quote+0.808
í+0.791
 Ladies+0.761
Neg logit contributions
soever-0.695
 adversary-0.668
��-0.647
achine-0.629
anooga-0.607
Token business
Token ID1597
Feature activation-5.92e-02

Pos logit contributions
uid+0.317
+0.284
quote+0.270
í+0.264
 Ladies+0.253
Neg logit contributions
soever-0.274
 adversary-0.264
��-0.256
achine-0.249
anooga-0.241
Tokenhash
Token ID17831
Feature activation+7.60e-01

Pos logit contributions
soever+0.019
 adversary+0.018
��+0.018
achine+0.017
anooga+0.017
Neg logit contributions
uid-0.020
-0.017
quote-0.017
í-0.016
 Ladies-0.016
Token Gh
Token ID11972
Feature activation-2.68e-01

Pos logit contributions
soever+3.394
 adversary+3.270
��+3.217
achine+3.130
 Canaver+3.051
Neg logit contributions
uid-4.132
-3.749
quote-3.565
í-3.473
 Ladies-3.338
Tokenai
Token ID1872
Feature activation+6.53e-01

Pos logit contributions
uid+1.441
+1.243
quote+1.211
í+1.208
 Ladies+1.129
Neg logit contributions
soever-1.279
 adversary-1.238
��-1.227
achine-1.162
 Canaver-1.148
Token,
Token ID11
Feature activation+7.46e-02

Pos logit contributions
soever+3.194
 adversary+3.115
��+3.031
achine+2.956
anooga+2.853
Neg logit contributions
uid-3.287
-2.945
quote-2.778
í-2.704
 Ladies-2.603
Token the
Token ID262
Feature activation+2.44e-01

Pos logit contributions
soever+0.339
 adversary+0.328
��+0.322
achine+0.312
anooga+0.303
Neg logit contributions
uid-0.409
-0.366
quote-0.351
í-0.345
 Ladies-0.330
Token Supreme
Token ID5617
Feature activation-2.08e+00

Pos logit contributions
soever+1.123
 adversary+1.095
��+1.059
achine+1.032
 Canaver+1.000
Neg logit contributions
uid-1.325
-1.189
quote-1.134
í-1.113
 Ladies-1.056
Token Court
Token ID3078
Feature activation-1.40e+00

Pos logit contributions
uid+6.528
í+5.183
quote+5.014
 Ladies+4.988
+4.823
Neg logit contributions
soever-13.348
��-13.322
anooga-12.753
 adversary-12.725
achine-12.705
Token today
Token ID1909
Feature activation-2.83e-01

Pos logit contributions
uid+6.944
+5.923
quote+5.844
í+5.834
 Ladies+5.675
Neg logit contributions
��-6.521
soever-6.489
achine-6.239
 adversary-6.168
 Canaver-6.073
Token upheld
Token ID24816
Feature activation-4.94e-03

Pos logit contributions
uid+1.428
+1.263
quote+1.204
í+1.186
 Ladies+1.130
Neg logit contributions
soever-1.409
 adversary-1.368
��-1.353
achine-1.316
anooga-1.281
Token the
Token ID262
Feature activation+4.37e-01

Pos logit contributions
uid+0.028
+0.025
quote+0.024
í+0.023
 Ladies+0.023
Neg logit contributions
soever-0.022
 adversary-0.021
��-0.021
achine-0.020
anooga-0.020
Token Bombay
Token ID48918
Feature activation+2.59e-01

Pos logit contributions
soever+1.876
 adversary+1.836
��+1.752
achine+1.698
 Canaver+1.648
Neg logit contributions
uid-2.482
-2.251
quote-2.145
í-2.108
united-1.999
Token of
Token ID286
Feature activation-7.90e-03

Pos logit contributions
soever+0.192
 adversary+0.185
��+0.181
achine+0.176
anooga+0.170
Neg logit contributions
uid-0.236
-0.212
quote-0.203
í-0.199
 Ladies-0.191
Token the
Token ID262
Feature activation-6.99e-02

Pos logit contributions
uid+0.045
+0.040
quote+0.038
í+0.038
 Ladies+0.036
Neg logit contributions
soever-0.035
 adversary-0.034
��-0.033
achine-0.032
anooga-0.031
Token state
Token ID1181
Feature activation-5.46e-01

Pos logit contributions
uid+0.384
+0.344
quote+0.330
í+0.324
 Ladies+0.310
Neg logit contributions
soever-0.317
 adversary-0.307
��-0.300
achine-0.291
anooga-0.282
Token,"
Token ID553
Feature activation-3.71e-01

Pos logit contributions
uid+2.923
+2.567
quote+2.485
í+2.469
 Ladies+2.328
Neg logit contributions
soever-2.508
��-2.462
 adversary-2.421
achine-2.352
 Canaver-2.320
Token the
Token ID262
Feature activation-1.80e-01

Pos logit contributions
uid+1.963
+1.731
quote+1.675
í+1.648
 Ladies+1.585
Neg logit contributions
soever-1.730
 adversary-1.673
��-1.661
achine-1.631
 Canaver-1.581
Token bench
Token ID7624
Feature activation-1.61e+00

Pos logit contributions
uid+0.955
+0.843
quote+0.816
í+0.800
 Ladies+0.770
Neg logit contributions
soever-0.850
 adversary-0.815
��-0.808
achine-0.789
anooga-0.767
Token said
Token ID531
Feature activation-4.47e-01

Pos logit contributions
uid+6.950
quote+5.902
+5.834
í+5.753
 Ladies+5.442
Neg logit contributions
achine-8.404
��-8.268
soever-8.264
 Canaver-8.007
 adversary-7.995
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
uid+2.293
+2.002
quote+1.957
í+1.915
 Ladies+1.828
Neg logit contributions
soever-2.150
 adversary-2.075
��-2.061
achine-2.046
anooga-1.977
Token
Token ID198
Feature activation-6.76e-02

Pos logit contributions
uid+0.490
+0.429
quote+0.414
í+0.406
 Ladies+0.386
Neg logit contributions
soever-0.528
 adversary-0.516
��-0.505
achine-0.492
anooga-0.481
Token
Token ID198
Feature activation+4.63e-03

Pos logit contributions
uid+0.367
+0.330
quote+0.309
í+0.300
 Ladies+0.292
Neg logit contributions
soever-0.298
 adversary-0.288
achine-0.277
��-0.267
 Canaver-0.266
TokenThe
Token ID464
Feature activation+2.06e-01

Pos logit contributions
soever+0.021
 adversary+0.020
��+0.020
achine+0.019
anooga+0.019
Neg logit contributions
uid-0.026
-0.023
quote-0.022
í-0.022
 Ladies-0.021
TokenChristmas
Token ID44614
Feature activation+3.83e-01

Pos logit contributions
soever+1.867
 adversary+1.814
��+1.775
achine+1.728
anooga+1.676
Neg logit contributions
uid-2.157
-1.927
quote-1.839
í-1.814
 Ladies-1.733
Token in
Token ID287
Feature activation-4.27e-02

Pos logit contributions
soever+1.797
 adversary+1.754
��+1.680
achine+1.665
 Canaver+1.605
Neg logit contributions
uid-2.037
-1.826
quote-1.734
í-1.684
united-1.585
Token July
Token ID2901
Feature activation+1.62e-01

Pos logit contributions
uid+0.223
+0.198
quote+0.189
í+0.186
 Ladies+0.177
Neg logit contributions
soever-0.206
 adversary-0.199
��-0.196
achine-0.190
anooga-0.185
Token"
Token ID1
Feature activation+2.54e-02

Pos logit contributions
soever+0.648
 adversary+0.625
��+0.608
achine+0.588
anooga+0.568
Neg logit contributions
uid-0.978
-0.884
quote-0.849
í-0.836
 Ladies-0.802
Token double
Token ID4274
Feature activation-7.99e-01

Pos logit contributions
soever+0.107
 adversary+0.104
��+0.101
achine+0.098
anooga+0.095
Neg logit contributions
uid-0.147
-0.132
quote-0.127
í-0.125
 Ladies-0.119
Token-
Token ID12
Feature activation-1.60e+00

Pos logit contributions
uid+4.212
+3.672
quote+3.587
í+3.539
 Ladies+3.381
Neg logit contributions
soever-3.771
��-3.598
 adversary-3.565
achine-3.508
 Canaver-3.410
Tokenfeature
Token ID30053
Feature activation-5.15e-01

Pos logit contributions
uid+7.516
quote+6.253
í+6.037
sell+5.891
+5.806
Neg logit contributions
soever-8.378
 adversary-8.114
��-8.012
 Canaver-7.719
achine-7.603
Token is
Token ID318
Feature activation-4.97e-01

Pos logit contributions
uid+2.941
+2.635
quote+2.539
í+2.511
 Ladies+2.415
Neg logit contributions
soever-2.222
 adversary-2.114
��-2.094
achine-2.018
anooga-1.958
Token July
Token ID2901
Feature activation-4.04e-01

Pos logit contributions
uid+2.684
+2.410
quote+2.298
í+2.273
 Ladies+2.187
Neg logit contributions
soever-2.291
 adversary-2.197
��-2.189
achine-2.111
anooga-2.053
Token 26
Token ID2608
Feature activation-1.12e+00

Pos logit contributions
uid+2.410
+2.174
quote+2.092
í+2.060
 Ladies+1.979
Neg logit contributions
soever-1.648
 adversary-1.588
��-1.553
achine-1.499
anooga-1.450
Token and
Token ID290
Feature activation-1.57e-01

Pos logit contributions
uid+5.606
+4.969
quote+4.826
í+4.763
 Ladies+4.564
Neg logit contributions
soever-5.412
��-5.199
 adversary-5.119
achine-4.929
anooga-4.888
Token
Token ID247
Feature activation+1.04e-01

Pos logit contributions
soever+1.063
��+1.024
 adversary+1.022
achine+0.960
 Canaver+0.941
Neg logit contributions
uid-1.063
-0.950
quote-0.913
í-0.881
 Ladies-0.848
Tokens
Token ID82
Feature activation+1.65e-01

Pos logit contributions
soever+0.447
 adversary+0.429
��+0.419
achine+0.407
anooga+0.393
Neg logit contributions
uid-0.595
-0.535
quote-0.513
í-0.504
 Ladies-0.484
Token like
Token ID588
Feature activation+2.38e-01

Pos logit contributions
soever+0.697
 adversary+0.675
��+0.652
achine+0.636
 Canaver+0.618
Neg logit contributions
uid-0.960
-0.860
quote-0.826
í-0.803
 Ladies-0.773
Token if
Token ID611
Feature activation+1.82e-01

Pos logit contributions
soever+1.033
 adversary+0.996
��+0.967
achine+0.934
 Canaver+0.914
Neg logit contributions
uid-1.367
-1.212
quote-1.161
í-1.138
 Ladies-1.090
Token Vanilla
Token ID33897
Feature activation-1.28e+00

Pos logit contributions
soever+0.801
 adversary+0.769
��+0.747
achine+0.728
 Canaver+0.708
Neg logit contributions
uid-1.032
-0.915
quote-0.877
í-0.859
 Ladies-0.823
Token Ice
Token ID6663
Feature activation-1.77e+00

Pos logit contributions
uid+4.421
+3.734
í+3.622
 Ladies+3.602
quote+3.602
Neg logit contributions
soever-8.062
��-8.013
 adversary-7.793
anooga-7.665
achine-7.572
Token was
Token ID373
Feature activation-3.31e-01

Pos logit contributions
uid+8.990
+8.208
í+7.913
quote+7.843
 Ladies+7.503
Neg logit contributions
soever-7.778
��-7.668
 adversary-7.553
achine-7.286
anooga-7.187
Token slightly
Token ID4622
Feature activation-5.34e-01

Pos logit contributions
uid+1.879
+1.686
quote+1.618
í+1.592
 Ladies+1.526
Neg logit contributions
soever-1.441
 adversary-1.393
��-1.362
achine-1.319
anooga-1.278
Token more
Token ID517
Feature activation-6.41e-01

Pos logit contributions
uid+3.195
+2.881
quote+2.785
í+2.738
 Ladies+2.627
Neg logit contributions
soever-2.154
 adversary-2.074
��-2.042
achine-1.970
anooga-1.917
Token gang
Token ID7706
Feature activation-4.32e-01

Pos logit contributions
uid+3.546
+3.168
quote+3.060
í+3.009
 Ladies+2.878
Neg logit contributions
soever-2.856
 adversary-2.756
��-2.735
achine-2.637
anooga-2.570
Tokenster
Token ID1706
Feature activation-6.19e-01

Pos logit contributions
uid+1.870
+1.601
quote+1.518
í+1.496
 Ladies+1.400
Neg logit contributions
soever-2.472
 adversary-2.391
��-2.389
achine-2.302
 Canaver-2.270
TokenN
Token ID45
Feature activation-8.17e-01

Pos logit contributions
uid+2.864
+2.550
quote+2.473
í+2.459
 Ladies+2.320
Neg logit contributions
soever-2.202
 adversary-1.969
��-1.943
achine-1.909
 Canaver-1.906
Token.
Token ID13
Feature activation-5.68e-01

Pos logit contributions
uid+3.647
í+3.040
+3.018
quote+2.862
 Ladies+2.733
Neg logit contributions
soever-4.563
��-4.410
 adversary-4.310
 Canaver-4.284
achine-4.256
Token "
Token ID366
Feature activation+2.57e-01

Pos logit contributions
uid+3.288
+2.936
quote+2.830
í+2.818
 Ladies+2.705
Neg logit contributions
soever-2.424
 adversary-2.283
��-2.282
achine-2.204
 Canaver-2.153
Tokenspecial
Token ID20887
Feature activation-3.57e-01

Pos logit contributions
soever+1.241
 adversary+1.211
��+1.176
achine+1.145
anooga+1.116
Neg logit contributions
uid-1.314
-1.178
quote-1.117
í-1.096
 Ladies-1.054
Token rapport
Token ID49498
Feature activation-2.71e-01

Pos logit contributions
uid+2.052
+1.822
quote+1.767
í+1.755
 Ladies+1.680
Neg logit contributions
soever-1.536
��-1.457
 adversary-1.455
achine-1.393
 Canaver-1.367
Tokeneur
Token ID23365
Feature activation-1.50e+00

Pos logit contributions
uid+1.517
+1.345
quote+1.290
í+1.284
 Ladies+1.217
Neg logit contributions
soever-1.223
 adversary-1.162
��-1.148
achine-1.109
 Canaver-1.085
Token"
Token ID1
Feature activation-8.15e-01

Pos logit contributions
uid+6.921
í+6.091
+6.020
quote+5.855
 Ladies+5.537
Neg logit contributions
soever-7.368
��-7.118
 adversary-6.691
achine-6.602
 Canaver-6.565
Token for
Token ID329
Feature activation-4.92e-01

Pos logit contributions
uid+4.134
+3.640
í+3.524
quote+3.511
 Ladies+3.330
Neg logit contributions
soever-3.963
��-3.816
 adversary-3.691
achine-3.612
anooga-3.550
Token the
Token ID262
Feature activation-1.17e-01

Pos logit contributions
uid+2.760
+2.458
quote+2.370
í+2.347
 Ladies+2.257
Neg logit contributions
soever-2.157
��-2.071
 adversary-2.054
achine-1.991
anooga-1.950
Token protection
Token ID4800
Feature activation-5.37e-01

Pos logit contributions
uid+0.682
+0.615
quote+0.591
í+0.581
 Ladies+0.556
Neg logit contributions
soever-0.489
 adversary-0.474
��-0.461
achine-0.446
anooga-0.431
Token of
Token ID286
Feature activation-1.58e-01

Pos logit contributions
uid+2.563
+2.302
í+2.151
quote+2.146
 Ladies+1.992
Neg logit contributions
soever-2.788
��-2.672
 adversary-2.633
 Canaver-2.547
achine-2.544