TOP ACTIVATIONS
MAX = 9.459

Perhaps with some apolog etic intent , the late
" I hope he apolog izes [ Tuesday ], to
states like Poland and the Balt ics , as well as
" He was really apolog etic about it , and
when she wandered into the cave on the Y uc atan
about to run out of fuel . Current estimates
seas had risen and the cave system had filled with water
energy in Australia , and coal cannot compete .
]. But not going to cave just c uz he sends
small fl aps and a fuel jet at one end .
suffered serious injuries in a rally crash last weekend . Michael
hybrids and electric cars , gas tax revenues are going to
has developed a culture of caution , and it 's being
rop ost ach , a fuel supplier which is connected to
Koch Industries , and other coal , oil , and gas
life ; a chance to escape the to il caused by
by the results of a straw poll conducted this weekend in
, f irmed up by gas and soon battery storage .
" I hope he apolog izes tomorrow ," Crow der
two different concepts from the arg uable king of curse ,

MIN ACTIVATIONS
MIN = -8.593

. With Josh Doct son finally becoming a force
I ve developed parad ig ms based on such
cancelled , besides serious damage inflicted on rail property . The
My favorites to use are Whole Al monds , P ec
network , C TO John Saw said yesterday .
the ecological damage the plantations inflicted on the islands .
Ste in suffered an open disl ocation of his finger and
Tampa s Jake Od or izz i , San
22 O & A - Tom Ret ired - 08 Election
Justin Williams Tom Wilson T .
reconstruction is done at the subt ape level . Don
- St all one - Tom Cruise Book - M unch
5 . Crystal Emb ry o 04 : 30
: 51 Crystal Emb ry o by Sing ,
of inquiry to investigate this mish ap . The March launch
/ " Crystal Emb ry o lives in a
the development and support for Koh a , recently formed an
Prec ise - Unt et hered , Dist ant
architecture , are deployed through multit en ant S aa S
Brain iac gives The Joker Imper vious so that if they

INTERVAL 4.946 - 9.459
CONTAINS 0.383%

at the Paris meeting , Fab ius said .
ia Bailey , a Capitol cafe cash ier , as she
director Bryan Singer during the press junk et , but ultimately
established a siege on the rebel - held portion of the
seismic testing for oil and gas in the north but dismissing

INTERVAL 0.433 - 4.946
CONTAINS 36.387%

ones seen in Wisconsin . Court rulings could be affected .
the Conservatives made with some improvements . Treasury Board president
ve lled Five days later , bed r agg
att acked and by 1 August reached the original border .[
," he noted Friday . " If they don 't want

INTERVAL -4.080 - 0.433
CONTAINS 62.334%

eding to the throne . The design is of the 1989
have convinced them that the cause of their problems is rooted
I BF wel ter weight title Read more True
Huff man of Houston , state police closed the meeting room
and be headed her . She said : I will not

INTERVAL -8.593 - -4.080
CONTAINS 0.896%

Assistant to report persons pretending to be from the
story of Am non and Tam ar , which is explicitly
their respective fields , this Manhattan Project would also be able
" I 'll Feel a Whole Lot Better " ( above
. But the Work it Y OW group runs
Token
Token ID198
Feature activation-2.86e-01

Pos logit contributions
+1.408
+1.189
Islam+1.137
poll+1.131
REL+1.117
Neg logit contributions
acht-1.729
 Parenthood-1.465
uscript-1.452
ield-1.438
estic-1.419
Token
Token ID198
Feature activation-4.38e-01

Pos logit contributions
acht+0.273
 Parenthood+0.231
ield+0.227
uscript+0.225
estic+0.222
Neg logit contributions
-0.233
-0.196
Islam-0.184
REL-0.183
poll-0.183
TokenPerhaps
Token ID13710
Feature activation-5.27e-02

Pos logit contributions
acht+0.421
 Parenthood+0.354
uscript+0.353
ield+0.349
estic+0.343
Neg logit contributions
-0.354
-0.298
poll-0.284
Islam-0.281
REL-0.279
Token with
Token ID351
Feature activation-7.16e-01

Pos logit contributions
acht+0.053
 Parenthood+0.045
uscript+0.045
ield+0.044
estic+0.044
Neg logit contributions
-0.040
-0.033
poll-0.032
Islam-0.032
REL-0.031
Token some
Token ID617
Feature activation+1.62e+00

Pos logit contributions
acht+0.732
 Parenthood+0.623
uscript+0.621
ield+0.613
estic+0.606
Neg logit contributions
-0.534
-0.443
poll-0.421
Islam-0.420
REL-0.416
Token apolog
Token ID8453
Feature activation+9.46e+00

Pos logit contributions
+1.240
+1.041
Islam+0.989
poll+0.986
REL+0.972
Neg logit contributions
acht-1.620
 Parenthood-1.377
uscript-1.367
ield-1.353
estic-1.336
Tokenetic
Token ID5139
Feature activation+2.78e+00

Pos logit contributions
+5.023
+3.963
Islam+3.698
poll+3.619
istas+3.452
Neg logit contributions
acht-11.229
 Parenthood-9.950
uscript-9.669
assium-9.632
ield-9.550
Token intent
Token ID6824
Feature activation-2.59e+00

Pos logit contributions
+2.101
+1.762
Islam+1.668
poll+1.664
REL+1.636
Neg logit contributions
acht-2.799
 Parenthood-2.387
uscript-2.371
ield-2.342
estic-2.316
Token,
Token ID11
Feature activation+1.04e-01

Pos logit contributions
acht+2.363
 Parenthood+1.971
uscript+1.960
ield+1.927
estic+1.907
Neg logit contributions
-2.218
-1.887
poll-1.804
Islam-1.788
REL-1.782
Token the
Token ID262
Feature activation+2.45e-01

Pos logit contributions
+0.082
+0.068
poll+0.065
Islam+0.065
REL+0.064
Neg logit contributions
acht-0.102
 Parenthood-0.087
uscript-0.086
ield-0.085
estic-0.084
Token late
Token ID2739
Feature activation+1.56e+00

Pos logit contributions
+0.196
+0.166
Islam+0.158
poll+0.158
REL+0.156
Neg logit contributions
acht-0.237
 Parenthood-0.200
uscript-0.199
ield-0.197
estic-0.194
Token
Token ID198
Feature activation+5.13e-01

Pos logit contributions
+0.620
+0.519
Islam+0.491
poll+0.489
REL+0.486
Neg logit contributions
acht-0.774
 Parenthood-0.658
uscript-0.646
ield-0.646
estic-0.635
Token"
Token ID1
Feature activation+7.48e-01

Pos logit contributions
+0.452
+0.388
poll+0.370
Islam+0.369
REL+0.366
Neg logit contributions
acht-0.454
 Parenthood-0.376
uscript-0.374
ield-0.371
estic-0.364
TokenI
Token ID40
Feature activation+2.55e+00

Pos logit contributions
+0.652
+0.559
poll+0.535
Islam+0.533
REL+0.527
Neg logit contributions
acht-0.670
 Parenthood-0.558
uscript-0.553
ield-0.547
estic-0.539
Token hope
Token ID2911
Feature activation+1.69e+00

Pos logit contributions
+1.767
+1.452
Islam+1.383
poll+1.373
REL+1.363
Neg logit contributions
acht-2.714
 Parenthood-2.344
uscript-2.324
ield-2.296
estic-2.272
Token he
Token ID339
Feature activation+9.19e-01

Pos logit contributions
+1.307
+1.098
Islam+1.047
poll+1.042
REL+1.025
Neg logit contributions
acht-1.684
 Parenthood-1.423
uscript-1.419
ield-1.405
estic-1.385
Token apolog
Token ID8453
Feature activation+8.90e+00

Pos logit contributions
+0.776
+0.662
Islam+0.633
poll+0.632
REL+0.624
Neg logit contributions
acht-0.850
 Parenthood-0.712
uscript-0.706
ield-0.698
estic-0.689
Tokenizes
Token ID4340
Feature activation+6.01e-01

Pos logit contributions
+5.155
+4.166
Islam+3.867
poll+3.756
istas+3.716
Neg logit contributions
acht-10.197
 Parenthood-8.935
everal-8.754
uscript-8.728
ocument-8.686
Token [
Token ID685
Feature activation+8.61e-01

Pos logit contributions
+0.499
+0.424
Islam+0.405
poll+0.404
REL+0.398
Neg logit contributions
acht-0.565
 Parenthood-0.474
uscript-0.471
ield-0.466
estic-0.460
TokenTuesday
Token ID26133
Feature activation+3.65e-01

Pos logit contributions
+0.684
+0.576
Islam+0.550
poll+0.549
REL+0.541
Neg logit contributions
acht-0.840
 Parenthood-0.711
uscript-0.706
ield-0.698
estic-0.689
Token],
Token ID4357
Feature activation-1.26e-01

Pos logit contributions
+0.318
+0.273
Islam+0.261
poll+0.261
REL+0.257
Neg logit contributions
acht-0.328
 Parenthood-0.273
uscript-0.271
ield-0.268
estic-0.264
Token to
Token ID284
Feature activation+2.86e-01

Pos logit contributions
acht+0.122
 Parenthood+0.103
uscript+0.102
ield+0.101
estic+0.100
Neg logit contributions
-0.101
-0.085
poll-0.081
Islam-0.081
REL-0.080
Token states
Token ID2585
Feature activation-3.00e+00

Pos logit contributions
acht+0.726
 Parenthood+0.625
uscript+0.620
ield+0.616
estic+0.608
Neg logit contributions
-0.451
-0.368
Islam-0.347
poll-0.347
REL-0.341
Token like
Token ID588
Feature activation+9.35e-01

Pos logit contributions
acht+2.647
 Parenthood+2.174
uscript+2.147
ield+2.139
estic+2.108
Neg logit contributions
-2.653
-2.286
poll-2.175
Islam-2.174
REL-2.163
Token Poland
Token ID12873
Feature activation-3.37e+00

Pos logit contributions
+0.742
+0.627
Islam+0.598
poll+0.596
REL+0.588
Neg logit contributions
acht-0.909
 Parenthood-0.769
uscript-0.768
ield-0.757
estic-0.750
Token and
Token ID290
Feature activation-2.95e-01

Pos logit contributions
acht+2.877
 Parenthood+2.356
uscript+2.321
ield+2.306
estic+2.273
Neg logit contributions
-3.060
-2.650
poll-2.541
Islam-2.535
REL-2.516
Token the
Token ID262
Feature activation+4.49e-01

Pos logit contributions
acht+0.271
 Parenthood+0.228
uscript+0.226
ield+0.223
estic+0.221
Neg logit contributions
-0.251
-0.214
Islam-0.205
poll-0.204
REL-0.202
Token Balt
Token ID9035
Feature activation+8.77e+00

Pos logit contributions
+0.409
+0.354
Islam+0.338
poll+0.338
REL+0.335
Neg logit contributions
acht-0.384
 Parenthood-0.318
uscript-0.317
ield-0.310
estic-0.307
Tokenics
Token ID873
Feature activation+4.66e-01

Pos logit contributions
+5.783
+4.723
poll+4.511
Islam+4.497
istas+4.351
Neg logit contributions
acht-9.140
 Parenthood-8.172
uscript-8.017
ield-7.836
everal-7.821
Token,
Token ID11
Feature activation+5.92e-01

Pos logit contributions
+0.416
+0.358
Islam+0.343
poll+0.343
REL+0.339
Neg logit contributions
acht-0.407
 Parenthood-0.338
uscript-0.336
ield-0.331
estic-0.326
Token as
Token ID355
Feature activation+4.91e-01

Pos logit contributions
+0.503
+0.429
Islam+0.410
poll+0.409
REL+0.404
Neg logit contributions
acht-0.546
 Parenthood-0.457
uscript-0.453
ield-0.448
estic-0.442
Token well
Token ID880
Feature activation+1.32e+00

Pos logit contributions
+0.387
+0.326
Islam+0.310
poll+0.310
REL+0.305
Neg logit contributions
acht-0.483
 Parenthood-0.409
uscript-0.406
ield-0.401
estic-0.396
Token as
Token ID355
Feature activation+6.10e-01

Pos logit contributions
+1.107
+0.943
Islam+0.902
poll+0.901
REL+0.887
Neg logit contributions
acht-1.222
 Parenthood-1.025
uscript-1.019
ield-1.005
estic-0.994
Token
Token ID198
Feature activation+6.88e-01

Pos logit contributions
+0.813
+0.682
Islam+0.644
poll+0.642
REL+0.637
Neg logit contributions
acht-1.021
 Parenthood-0.868
uscript-0.853
ield-0.852
estic-0.838
Token"
Token ID1
Feature activation+2.94e-01

Pos logit contributions
+0.563
+0.477
poll+0.453
Islam+0.453
REL+0.447
Neg logit contributions
acht-0.652
 Parenthood-0.549
uscript-0.544
ield-0.539
estic-0.531
TokenHe
Token ID1544
Feature activation-6.58e-02

Pos logit contributions
+0.247
+0.210
Islam+0.201
poll+0.201
REL+0.198
Neg logit contributions
acht-0.273
 Parenthood-0.229
uscript-0.227
ield-0.224
estic-0.221
Token was
Token ID373
Feature activation-2.21e+00

Pos logit contributions
acht+0.066
 Parenthood+0.056
uscript+0.056
ield+0.056
estic+0.055
Neg logit contributions
-0.050
-0.042
poll-0.040
Islam-0.040
REL-0.039
Token really
Token ID1107
Feature activation-2.20e+00

Pos logit contributions
acht+2.214
 Parenthood+1.885
uscript+1.868
ield+1.845
estic+1.835
Neg logit contributions
-1.694
-1.423
poll-1.345
Islam-1.344
REL-1.324
Token apolog
Token ID8453
Feature activation+8.67e+00

Pos logit contributions
acht+2.124
 Parenthood+1.792
uscript+1.768
ield+1.762
estic+1.743
Neg logit contributions
-1.754
-1.486
poll-1.413
Islam-1.410
REL-1.396
Tokenetic
Token ID5139
Feature activation+2.64e+00

Pos logit contributions
+3.387
+2.347
Islam+2.098
poll+2.021
ardless+1.930
Neg logit contributions
acht-11.465
 Parenthood-10.397
uscript-10.100
ocument-10.097
assium-10.091
Token about
Token ID546
Feature activation-7.01e-01

Pos logit contributions
+2.173
+1.845
Islam+1.761
poll+1.760
REL+1.731
Neg logit contributions
acht-2.472
 Parenthood-2.082
uscript-2.075
ield-2.051
assium-2.019
Token it
Token ID340
Feature activation-1.88e+00

Pos logit contributions
acht+0.721
 Parenthood+0.616
uscript+0.611
ield+0.605
estic+0.599
Neg logit contributions
-0.518
-0.430
Islam-0.408
poll-0.407
REL-0.402
Token,
Token ID11
Feature activation+6.28e-02

Pos logit contributions
acht+1.654
 Parenthood+1.370
uscript+1.357
ield+1.337
estic+1.325
Neg logit contributions
-1.665
-1.434
Islam-1.371
poll-1.370
REL-1.358
Token and
Token ID290
Feature activation+1.87e-01

Pos logit contributions
+0.050
+0.042
Islam+0.040
poll+0.040
REL+0.039
Neg logit contributions
acht-0.061
 Parenthood-0.052
uscript-0.051
ield-0.051
estic-0.050
Token when
Token ID618
Feature activation+2.62e+00

Pos logit contributions
+0.684
+0.588
poll+0.564
Islam+0.563
REL+0.556
Neg logit contributions
acht-0.685
 Parenthood-0.569
uscript-0.563
ield-0.558
estic-0.550
Token she
Token ID673
Feature activation+5.19e-01

Pos logit contributions
+2.083
+1.759
poll+1.684
Islam+1.684
REL+1.661
Neg logit contributions
acht-2.525
 Parenthood-2.120
uscript-2.113
ield-2.101
estic-2.068
Token wandered
Token ID36036
Feature activation+5.05e-01

Pos logit contributions
+0.436
+0.372
poll+0.355
Islam+0.355
REL+0.350
Neg logit contributions
acht-0.482
 Parenthood-0.404
uscript-0.400
ield-0.396
estic-0.391
Token into
Token ID656
Feature activation-6.92e-01

Pos logit contributions
+0.382
+0.319
Islam+0.304
poll+0.304
REL+0.300
Neg logit contributions
acht-0.510
 Parenthood-0.432
uscript-0.431
ield-0.427
estic-0.422
Token the
Token ID262
Feature activation-2.18e-02

Pos logit contributions
acht+0.679
 Parenthood+0.576
uscript+0.571
ield+0.564
estic+0.557
Neg logit contributions
-0.546
-0.460
Islam-0.437
poll-0.437
REL-0.431
Token cave
Token ID11527
Feature activation+8.53e+00

Pos logit contributions
acht+0.021
 Parenthood+0.018
uscript+0.018
ield+0.017
estic+0.017
Neg logit contributions
-0.017
-0.015
Islam-0.014
poll-0.014
REL-0.014
Token on
Token ID319
Feature activation+1.59e-01

Pos logit contributions
+6.683
+5.700
REL+5.453
Islam+5.417
poll+5.393
Neg logit contributions
acht-7.768
 Parenthood-6.607
uscript-6.476
ocument-6.437
ield-6.407
Token the
Token ID262
Feature activation+6.85e-02

Pos logit contributions
+0.131
+0.111
poll+0.106
Islam+0.106
REL+0.105
Neg logit contributions
acht-0.150
 Parenthood-0.126
uscript-0.125
ield-0.124
estic-0.122
Token Y
Token ID575
Feature activation-2.34e+00

Pos logit contributions
+0.058
+0.049
Islam+0.047
poll+0.047
REL+0.046
Neg logit contributions
acht-0.063
 Parenthood-0.053
uscript-0.053
ield-0.052
estic-0.051
Tokenuc
Token ID1229
Feature activation+1.00e+00

Pos logit contributions
acht+2.106
uscript+1.718
ield+1.711
 Parenthood+1.701
estic+1.665
Neg logit contributions
-2.065
-1.779
poll-1.701
Islam-1.693
REL-1.672
Tokenatan
Token ID39036
Feature activation+1.09e+00

Pos logit contributions
+0.947
+0.822
Islam+0.791
poll+0.790
REL+0.781
Neg logit contributions
acht-0.828
 Parenthood-0.678
uscript-0.671
ield-0.663
estic-0.652
Token about
Token ID546
Feature activation-9.06e-01

Pos logit contributions
acht+0.146
 Parenthood+0.124
uscript+0.123
ield+0.122
estic+0.120
Neg logit contributions
-0.111
-0.093
Islam-0.089
poll-0.088
REL-0.087
Token to
Token ID284
Feature activation-3.76e-01

Pos logit contributions
acht+0.805
 Parenthood+0.668
uscript+0.663
ield+0.655
estic+0.645
Neg logit contributions
-0.799
-0.686
poll-0.658
Islam-0.657
REL-0.649
Token run
Token ID1057
Feature activation+2.94e+00

Pos logit contributions
acht+0.375
 Parenthood+0.317
uscript+0.314
ield+0.313
estic+0.309
Neg logit contributions
-0.291
-0.244
Islam-0.232
poll-0.231
REL-0.228
Token out
Token ID503
Feature activation+7.56e-01

Pos logit contributions
+2.382
+2.019
poll+1.941
Islam+1.926
REL+1.886
Neg logit contributions
acht-2.795
uscript-2.362
ield-2.336
 Parenthood-2.334
ocument-2.295
Token of
Token ID286
Feature activation+1.12e+00

Pos logit contributions
+0.653
+0.558
Islam+0.534
poll+0.533
REL+0.527
Neg logit contributions
acht-0.686
 Parenthood-0.571
uscript-0.567
ield-0.561
estic-0.553
Token fuel
Token ID5252
Feature activation+8.41e+00

Pos logit contributions
+0.793
+0.654
Islam+0.619
poll+0.618
REL+0.609
Neg logit contributions
acht-1.186
 Parenthood-1.018
uscript-1.010
ield-1.001
estic-0.989
Token.
Token ID13
Feature activation+6.30e-01

Pos logit contributions
+6.727
+5.766
poll+5.571
REL+5.495
Islam+5.453
Neg logit contributions
acht-7.523
uscript-6.502
 Parenthood-6.329
ocument-6.289
estic-6.260
Token
Token ID198
Feature activation+8.07e-01

Pos logit contributions
+0.496
+0.417
Islam+0.398
poll+0.395
REL+0.391
Neg logit contributions
acht-0.617
 Parenthood-0.526
ield-0.515
uscript-0.514
estic-0.505
Token
Token ID198
Feature activation+3.94e-01

Pos logit contributions
+0.634
+0.531
Islam+0.502
poll+0.500
REL+0.496
Neg logit contributions
acht-0.796
 Parenthood-0.676
uscript-0.665
ield-0.664
estic-0.654
TokenCurrent
Token ID11297
Feature activation+8.05e-01

Pos logit contributions
+0.323
+0.274
Islam+0.260
poll+0.260
REL+0.257
Neg logit contributions
acht-0.375
 Parenthood-0.314
uscript-0.312
ield-0.310
estic-0.305
Token estimates
Token ID7746
Feature activation+5.20e-01

Pos logit contributions
+0.609
+0.510
poll+0.485
Islam+0.483
REL+0.476
Neg logit contributions
acht-0.815
 Parenthood-0.693
uscript-0.689
ield-0.679
estic-0.673
Token seas
Token ID21547
Feature activation+3.52e+00

Pos logit contributions
+0.538
+0.457
Islam+0.436
poll+0.436
REL+0.430
Neg logit contributions
acht-0.605
 Parenthood-0.508
uscript-0.504
ield-0.498
estic-0.492
Token had
Token ID550
Feature activation-1.85e+00

Pos logit contributions
+2.856
+2.420
poll+2.333
Islam+2.318
REL+2.282
Neg logit contributions
acht-3.323
 Parenthood-2.831
uscript-2.791
ield-2.748
estic-2.717
Token risen
Token ID17450
Feature activation-1.56e+00

Pos logit contributions
acht+1.826
 Parenthood+1.542
uscript+1.527
ield+1.514
estic+1.498
Neg logit contributions
-1.454
-1.224
Islam-1.168
poll-1.161
REL-1.151
Token and
Token ID290
Feature activation-1.64e-01

Pos logit contributions
acht+1.415
 Parenthood+1.176
uscript+1.166
ield+1.152
estic+1.137
Neg logit contributions
-1.351
-1.161
Islam-1.106
poll-1.104
REL-1.096
Token the
Token ID262
Feature activation+3.70e-01

Pos logit contributions
acht+0.163
 Parenthood+0.138
uscript+0.137
ield+0.136
estic+0.134
Neg logit contributions
-0.127
-0.107
Islam-0.101
poll-0.101
REL-0.100
Token cave
Token ID11527
Feature activation+8.38e+00

Pos logit contributions
+0.298
+0.252
poll+0.240
Islam+0.240
REL+0.236
Neg logit contributions
acht-0.357
 Parenthood-0.301
uscript-0.299
ield-0.296
estic-0.292
Token system
Token ID1080
Feature activation-1.82e+00

Pos logit contributions
+6.208
+5.238
Islam+5.025
poll+5.007
REL+4.949
Neg logit contributions
acht-8.062
 Parenthood-7.004
ocument-6.918
uscript-6.887
ield-6.771
Token had
Token ID550
Feature activation-2.08e+00

Pos logit contributions
acht+1.689
 Parenthood+1.403
uscript+1.391
ield+1.380
assium+1.367
Neg logit contributions
-1.527
-1.296
Islam-1.236
poll-1.232
REL-1.228
Token filled
Token ID5901
Feature activation-2.81e-01

Pos logit contributions
acht+1.970
 Parenthood+1.651
uscript+1.634
ield+1.626
estic+1.605
Neg logit contributions
-1.702
-1.444
Islam-1.379
poll-1.376
REL-1.365
Token with
Token ID351
Feature activation-5.04e-01

Pos logit contributions
acht+0.247
 Parenthood+0.205
uscript+0.202
ield+0.201
estic+0.198
Neg logit contributions
-0.252
-0.216
Islam-0.207
poll-0.207
REL-0.205
Token water
Token ID1660
Feature activation+2.10e+00

Pos logit contributions
acht+0.488
 Parenthood+0.412
uscript+0.409
ield+0.404
estic+0.400
Neg logit contributions
-0.403
-0.340
Islam-0.324
poll-0.322
REL-0.320
Token energy
Token ID2568
Feature activation+2.58e+00

Pos logit contributions
+1.458
+1.237
poll+1.177
Islam+1.173
REL+1.158
Neg logit contributions
acht-1.760
 Parenthood-1.485
uscript-1.482
ield-1.455
estic-1.436
Token in
Token ID287
Feature activation+3.97e-01

Pos logit contributions
+2.131
+1.813
poll+1.744
Islam+1.735
REL+1.716
Neg logit contributions
acht-2.416
uscript-2.029
 Parenthood-2.022
ield-1.987
ocument-1.959
Token Australia
Token ID4505
Feature activation-3.20e-02

Pos logit contributions
+0.301
+0.252
Islam+0.239
poll+0.238
REL+0.235
Neg logit contributions
acht-0.401
 Parenthood-0.342
uscript-0.339
ield-0.336
estic-0.332
Token,
Token ID11
Feature activation+7.02e-01

Pos logit contributions
acht+0.029
 Parenthood+0.024
uscript+0.024
ield+0.024
estic+0.023
Neg logit contributions
-0.027
-0.024
Islam-0.022
poll-0.022
REL-0.022
Token and
Token ID290
Feature activation+4.44e-01

Pos logit contributions
+0.589
+0.501
Islam+0.478
poll+0.476
REL+0.471
Neg logit contributions
acht-0.654
 Parenthood-0.549
uscript-0.541
ield-0.538
estic-0.531
Token coal
Token ID5655
Feature activation+8.37e+00

Pos logit contributions
+0.335
+0.280
Islam+0.265
poll+0.263
REL+0.260
Neg logit contributions
acht-0.451
 Parenthood-0.384
uscript-0.378
ield-0.377
estic-0.374
Token cannot
Token ID2314
Feature activation+2.25e+00

Pos logit contributions
+6.387
+5.339
poll+5.247
Islam+5.144
REL+5.085
Neg logit contributions
acht-7.916
uscript-6.956
 Parenthood-6.779
ocument-6.659
ield-6.621
Token compete
Token ID9320
Feature activation+1.90e+00

Pos logit contributions
+1.761
+1.481
Islam+1.408
poll+1.407
REL+1.387
Neg logit contributions
acht-2.220
 Parenthood-1.882
uscript-1.867
ield-1.849
estic-1.826
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
+1.701
+1.466
Islam+1.406
poll+1.405
REL+1.387
Neg logit contributions
acht-1.649
 Parenthood-1.363
uscript-1.355
ield-1.335
estic-1.317
Token
Token ID198
Feature activation+9.19e-01

Pos logit contributions
+0.850
+0.720
Islam+0.686
poll+0.685
REL+0.675
Neg logit contributions
acht-1.005
 Parenthood-0.849
uscript-0.840
ield-0.832
estic-0.821
Token
Token ID198
Feature activation+5.58e-01

Pos logit contributions
+0.713
+0.597
Islam+0.565
poll+0.564
REL+0.558
Neg logit contributions
acht-0.913
 Parenthood-0.775
uscript-0.765
ield-0.762
estic-0.750
Token].
Token ID4083
Feature activation+2.64e-01

Pos logit contributions
acht+4.148
 Parenthood+3.435
uscript+3.415
ield+3.368
estic+3.323
Neg logit contributions
-4.068
-3.506
Islam-3.376
REL-3.374
poll-3.318
Token But
Token ID887
Feature activation-8.19e-02

Pos logit contributions
+0.238
+0.205
Islam+0.197
poll+0.197
REL+0.195
Neg logit contributions
acht-0.230
 Parenthood-0.190
uscript-0.188
ield-0.186
estic-0.184
Token not
Token ID407
Feature activation+3.63e+00

Pos logit contributions
acht+0.079
 Parenthood+0.067
uscript+0.066
ield+0.066
estic+0.065
Neg logit contributions
-0.066
-0.055
Islam-0.053
poll-0.053
REL-0.052
Token going
Token ID1016
Feature activation-8.98e-01

Pos logit contributions
+2.708
+2.269
poll+2.167
Islam+2.154
REL+2.135
Neg logit contributions
acht-3.677
 Parenthood-3.131
uscript-3.108
ield-3.081
estic-3.043
Token to
Token ID284
Feature activation-4.78e-01

Pos logit contributions
acht+0.854
 Parenthood+0.719
uscript+0.712
ield+0.703
estic+0.696
Neg logit contributions
-0.735
-0.624
poll-0.594
Islam-0.594
REL-0.585
Token cave
Token ID11527
Feature activation+8.36e+00

Pos logit contributions
acht+0.505
 Parenthood+0.433
uscript+0.430
ield+0.425
estic+0.421
Neg logit contributions
-0.342
-0.282
Islam-0.267
poll-0.266
REL-0.261
Token just
Token ID655
Feature activation+1.74e+00

Pos logit contributions
+6.391
+5.400
Islam+5.246
poll+5.221
REL+5.059
Neg logit contributions
acht-7.750
uscript-6.645
 Parenthood-6.641
ield-6.550
assium-6.496
Token c
Token ID269
Feature activation+3.50e+00

Pos logit contributions
+1.267
+1.049
Islam+0.995
poll+0.994
REL+0.977
Neg logit contributions
acht-1.813
 Parenthood-1.554
uscript-1.543
ield-1.528
estic-1.510
Tokenuz
Token ID10277
Feature activation-2.78e-01

Pos logit contributions
+2.711
+2.273
Islam+2.178
poll+2.177
REL+2.127
Neg logit contributions
acht-3.431
 Parenthood-2.951
uscript-2.904
ield-2.860
assium-2.836
Token he
Token ID339
Feature activation+2.93e-01

Pos logit contributions
acht+0.267
 Parenthood+0.225
uscript+0.223
ield+0.221
estic+0.218
Neg logit contributions
-0.225
-0.190
Islam-0.181
poll-0.180
REL-0.179
Token sends
Token ID12800
Feature activation-8.79e-01

Pos logit contributions
+0.252
+0.215
Islam+0.206
poll+0.206
REL+0.203
Neg logit contributions
acht-0.267
 Parenthood-0.223
uscript-0.221
ield-0.219
estic-0.216
Token small
Token ID1402
Feature activation-8.16e-01

Pos logit contributions
+1.148
+0.975
poll+0.930
Islam+0.929
REL+0.917
Neg logit contributions
acht-1.327
 Parenthood-1.117
uscript-1.111
ield-1.093
estic-1.081
Token fl
Token ID781
Feature activation+2.88e+00

Pos logit contributions
acht+0.805
 Parenthood+0.682
uscript+0.674
ield+0.671
estic+0.662
Neg logit contributions
-0.639
-0.537
Islam-0.511
poll-0.510
REL-0.504
Tokenaps
Token ID1686
Feature activation-1.81e+00

Pos logit contributions
+3.145
+2.790
poll+2.712
Islam+2.710
REL+2.672
Neg logit contributions
acht-1.899
 Parenthood-1.520
uscript-1.465
ield-1.421
estic-1.400
Token and
Token ID290
Feature activation-4.90e-01

Pos logit contributions
acht+1.655
 Parenthood+1.376
uscript+1.360
ield+1.354
estic+1.339
Neg logit contributions
-1.547
-1.320
Islam-1.260
poll-1.255
REL-1.238
Token a
Token ID257
Feature activation+4.78e-01

Pos logit contributions
acht+0.488
 Parenthood+0.413
uscript+0.409
ield+0.407
estic+0.401
Neg logit contributions
-0.381
-0.320
Islam-0.304
poll-0.303
REL-0.298
Token fuel
Token ID5252
Feature activation+8.31e+00

Pos logit contributions
+0.379
+0.320
Islam+0.305
poll+0.304
REL+0.300
Neg logit contributions
acht-0.467
 Parenthood-0.395
uscript-0.392
ield-0.388
estic-0.383
Token jet
Token ID12644
Feature activation+2.70e+00

Pos logit contributions
+5.765
+4.793
poll+4.583
REL+4.503
Islam+4.430
Neg logit contributions
acht-8.505
uscript-7.420
 Parenthood-7.416
ocument-7.172
estic-7.140
Token at
Token ID379
Feature activation-2.21e+00

Pos logit contributions
+2.156
+1.825
poll+1.740
Islam+1.736
REL+1.726
Neg logit contributions
acht-2.589
 Parenthood-2.209
uscript-2.186
ield-2.147
estic-2.128
Token one
Token ID530
Feature activation-2.42e+00

Pos logit contributions
acht+2.192
 Parenthood+1.859
ield+1.831
uscript+1.830
assium+1.807
Neg logit contributions
-1.709
-1.427
Islam-1.366
poll-1.353
REL-1.337
Token end
Token ID886
Feature activation+2.00e+00

Pos logit contributions
acht+1.974
 Parenthood+1.606
ield+1.581
uscript+1.567
estic+1.544
Neg logit contributions
-2.319
-2.003
Islam-1.926
poll-1.914
REL-1.898
Token.
Token ID13
Feature activation+3.44e-05

Pos logit contributions
+1.760
+1.511
poll+1.449
Islam+1.444
REL+1.430
Neg logit contributions
acht-1.761
 Parenthood-1.474
uscript-1.457
ield-1.433
estic-1.415
Token suffered
Token ID6989
Feature activation-4.61e+00

Pos logit contributions
acht+0.025
 Parenthood+0.021
uscript+0.021
ield+0.021
estic+0.020
Neg logit contributions
-0.024
-0.020
Islam-0.019
poll-0.019
REL-0.019
Token serious
Token ID2726
Feature activation-1.41e+00

Pos logit contributions
acht+4.123
 Parenthood+3.439
ield+3.328
 Hots+3.321
estic+3.296
Neg logit contributions
-3.944
-3.323
Islam-3.200
poll-3.170
ardless-3.150
Token injuries
Token ID6821
Feature activation-3.25e+00

Pos logit contributions
acht+1.364
 Parenthood+1.151
uscript+1.134
ield+1.131
estic+1.116
Neg logit contributions
-1.136
-0.956
Islam-0.915
poll-0.909
REL-0.902
Token in
Token ID287
Feature activation-2.58e-01

Pos logit contributions
acht+2.817
 Parenthood+2.326
uscript+2.273
ield+2.271
estic+2.245
Neg logit contributions
-2.918
-2.515
Islam-2.414
poll-2.385
REL-2.369
Token a
Token ID257
Feature activation+4.52e-01

Pos logit contributions
acht+0.251
 Parenthood+0.212
uscript+0.211
ield+0.209
estic+0.206
Neg logit contributions
-0.205
-0.173
poll-0.165
Islam-0.165
REL-0.163
Token rally
Token ID7903
Feature activation+8.28e+00

Pos logit contributions
+0.386
+0.330
poll+0.315
Islam+0.314
REL+0.311
Neg logit contributions
acht-0.414
 Parenthood-0.346
uscript-0.344
ield-0.339
estic-0.335
Token crash
Token ID7014
Feature activation+2.22e+00

Pos logit contributions
+6.319
+5.457
poll+5.353
REL+5.234
Islam+5.150
Neg logit contributions
acht-7.580
uscript-6.685
 Parenthood-6.493
ocument-6.429
assium-6.418
Token last
Token ID938
Feature activation+2.03e-02

Pos logit contributions
+1.881
+1.615
poll+1.563
Islam+1.532
REL+1.531
Neg logit contributions
acht-2.013
uscript-1.692
 Parenthood-1.683
ield-1.652
estic-1.637
Token weekend
Token ID5041
Feature activation+1.65e+00

Pos logit contributions
+0.019
+0.016
poll+0.016
Islam+0.016
REL+0.016
Neg logit contributions
acht-0.017
 Parenthood-0.014
uscript-0.014
ield-0.014
estic-0.013
Token.
Token ID13
Feature activation+4.77e-01

Pos logit contributions
+1.470
+1.269
poll+1.224
Islam+1.212
REL+1.198
Neg logit contributions
acht-1.438
 Parenthood-1.200
uscript-1.193
ield-1.162
estic-1.155
Token Michael
Token ID3899
Feature activation+4.64e-01

Pos logit contributions
+0.389
+0.329
Islam+0.313
poll+0.312
REL+0.309
Neg logit contributions
acht-0.455
 Parenthood-0.384
uscript-0.379
ield-0.376
estic-0.370
Token hybrids
Token ID45456
Feature activation+3.75e+00

Pos logit contributions
acht+0.004
 Parenthood+0.004
uscript+0.004
ield+0.004
estic+0.004
Neg logit contributions
-0.003
-0.003
Islam-0.003
poll-0.003
REL-0.003
Token and
Token ID290
Feature activation-2.17e-01

Pos logit contributions
+3.196
+2.732
poll+2.613
Islam+2.595
REL+2.554
Neg logit contributions
acht-3.417
uscript-2.867
 Parenthood-2.852
ield-2.799
estic-2.764
Token electric
Token ID5186
Feature activation+4.71e+00

Pos logit contributions
acht+0.219
 Parenthood+0.185
uscript+0.183
ield+0.183
estic+0.180
Neg logit contributions
-0.166
-0.139
Islam-0.132
poll-0.131
REL-0.130
Token cars
Token ID5006
Feature activation+1.01e+00

Pos logit contributions
+2.864
+2.294
poll+2.139
Islam+2.090
REL+2.041
Neg logit contributions
acht-5.428
 Parenthood-4.746
uscript-4.738
ield-4.637
assium-4.620
Token,
Token ID11
Feature activation+6.26e-01

Pos logit contributions
+0.884
+0.759
poll+0.726
Islam+0.725
REL+0.715
Neg logit contributions
acht-0.902
 Parenthood-0.750
uscript-0.747
ield-0.736
estic-0.726
Token gas
Token ID3623
Feature activation+8.10e+00

Pos logit contributions
+0.501
+0.423
Islam+0.403
poll+0.402
REL+0.397
Neg logit contributions
acht-0.606
 Parenthood-0.513
uscript-0.508
ield-0.503
estic-0.497
Token tax
Token ID1687
Feature activation+3.51e+00

Pos logit contributions
+5.953
+4.999
poll+4.831
Islam+4.675
REL+4.629
Neg logit contributions
acht-8.095
uscript-7.024
 Parenthood-6.803
ield-6.707
ocument-6.706
Token revenues
Token ID13089
Feature activation-1.61e+00

Pos logit contributions
+2.832
+2.423
poll+2.301
Islam+2.289
REL+2.250
Neg logit contributions
acht-3.337
uscript-2.824
 Parenthood-2.802
ield-2.752
ocument-2.733
Token are
Token ID389
Feature activation+1.83e+00

Pos logit contributions
acht+1.564
 Parenthood+1.323
uscript+1.297
ield+1.290
estic+1.279
Neg logit contributions
-1.296
-1.096
Islam-1.042
poll-1.041
REL-1.034
Token going
Token ID1016
Feature activation-5.25e-01

Pos logit contributions
+0.965
+0.740
poll+0.681
Islam+0.679
REL+0.662
Neg logit contributions
acht-2.271
 Parenthood-1.992
uscript-1.987
ield-1.968
estic-1.950
Token to
Token ID284
Feature activation-1.14e-01

Pos logit contributions
acht+0.492
 Parenthood+0.414
uscript+0.409
ield+0.404
estic+0.401
Neg logit contributions
-0.437
-0.372
poll-0.357
Islam-0.355
REL-0.351
Token has
Token ID468
Feature activation-1.45e+00

Pos logit contributions
+1.102
+0.942
poll+0.902
Islam+0.901
REL+0.891
Neg logit contributions
acht-1.169
 Parenthood-0.973
uscript-0.969
ield-0.958
estic-0.945
Token developed
Token ID4166
Feature activation-1.10e+00

Pos logit contributions
acht+1.376
 Parenthood+1.158
uscript+1.141
ield+1.132
estic+1.117
Neg logit contributions
-1.190
-1.010
Islam-0.963
poll-0.958
REL-0.948
Token a
Token ID257
Feature activation+4.98e-01

Pos logit contributions
acht+1.065
 Parenthood+0.900
uscript+0.889
ield+0.883
estic+0.872
Neg logit contributions
-0.876
-0.740
Islam-0.706
poll-0.702
REL-0.693
Token culture
Token ID3968
Feature activation-6.43e-01

Pos logit contributions
+0.398
+0.337
poll+0.321
Islam+0.320
REL+0.316
Neg logit contributions
acht-0.482
 Parenthood-0.407
uscript-0.404
ield-0.400
estic-0.394
Token of
Token ID286
Feature activation+1.01e+00

Pos logit contributions
acht+0.640
 Parenthood+0.539
uscript+0.536
ield+0.531
estic+0.526
Neg logit contributions
-0.500
-0.419
poll-0.398
Islam-0.398
REL-0.393
Token caution
Token ID13041
Feature activation+8.07e+00

Pos logit contributions
+0.796
+0.669
Islam+0.637
poll+0.636
REL+0.627
Neg logit contributions
acht-0.996
 Parenthood-0.844
uscript-0.836
ield-0.828
estic-0.818
Token,
Token ID11
Feature activation+7.15e-01

Pos logit contributions
+6.100
+5.150
poll+4.978
Islam+4.944
zone+4.771
Neg logit contributions
acht-7.584
uscript-6.576
 Parenthood-6.553
ield-6.329
assium-6.329
Token and
Token ID290
Feature activation+4.46e-01

Pos logit contributions
+0.575
+0.485
Islam+0.462
poll+0.461
REL+0.455
Neg logit contributions
acht-0.693
 Parenthood-0.584
uscript-0.578
ield-0.573
estic-0.568
Token it
Token ID340
Feature activation-5.98e-01

Pos logit contributions
+0.344
+0.288
Islam+0.274
poll+0.273
REL+0.269
Neg logit contributions
acht-0.447
 Parenthood-0.380
uscript-0.376
ield-0.373
estic-0.368
Token's
Token ID338
Feature activation+1.34e+00

Pos logit contributions
acht+0.527
 Parenthood+0.436
uscript+0.432
ield+0.427
estic+0.421
Neg logit contributions
-0.532
-0.457
Islam-0.437
poll-0.437
REL-0.433
Token being
Token ID852
Feature activation+6.52e-01

Pos logit contributions
+1.042
+0.878
poll+0.835
Islam+0.833
REL+0.821
Neg logit contributions
acht-1.325
 Parenthood-1.121
uscript-1.119
ield-1.105
estic-1.091
Tokenrop
Token ID1773
Feature activation+1.56e+00

Pos logit contributions
+4.152
+3.706
poll+3.639
Islam+3.616
REL+3.567
Neg logit contributions
acht-2.128
 Parenthood-1.622
uscript-1.603
ield-1.546
ocument-1.506
Tokenost
Token ID455
Feature activation-7.61e-01

Pos logit contributions
+1.469
+1.275
poll+1.232
Islam+1.232
REL+1.211
Neg logit contributions
acht-1.286
 Parenthood-1.058
uscript-1.047
ield-1.028
estic-1.011
Tokenach
Token ID620
Feature activation-1.23e+00

Pos logit contributions
acht+0.398
 Parenthood+0.283
uscript+0.279
ield+0.272
estic+0.264
Neg logit contributions
-0.949
-0.854
Islam-0.830
poll-0.829
REL-0.823
Token,
Token ID11
Feature activation+4.31e-02

Pos logit contributions
acht+1.034
 Parenthood+0.848
uscript+0.838
ield+0.831
estic+0.817
Neg logit contributions
-1.141
-0.987
poll-0.948
Islam-0.947
REL-0.937
Token a
Token ID257
Feature activation+9.44e-01

Pos logit contributions
+0.035
+0.030
Islam+0.029
poll+0.029
REL+0.028
Neg logit contributions
acht-0.041
 Parenthood-0.034
uscript-0.034
ield-0.034
estic-0.033
Token fuel
Token ID5252
Feature activation+8.07e+00

Pos logit contributions
+0.781
+0.664
Islam+0.634
poll+0.634
REL+0.625
Neg logit contributions
acht-0.889
 Parenthood-0.746
uscript-0.741
ield-0.732
estic-0.723
Token supplier
Token ID22693
Feature activation+3.12e+00

Pos logit contributions
+5.715
+4.766
poll+4.630
REL+4.558
Islam+4.523
Neg logit contributions
acht-8.146
uscript-7.081
 Parenthood-7.018
assium-6.758
ocument-6.752
Token which
Token ID543
Feature activation-3.50e-01

Pos logit contributions
+2.521
+2.150
poll+2.047
Islam+2.046
REL+2.034
Neg logit contributions
acht-2.951
uscript-2.503
 Parenthood-2.477
ield-2.445
estic-2.419
Token is
Token ID318
Feature activation-3.39e-01

Pos logit contributions
acht+0.312
 Parenthood+0.260
uscript+0.257
ield+0.254
estic+0.251
Neg logit contributions
-0.307
-0.264
Islam-0.252
poll-0.252
REL-0.249
Token connected
Token ID5884
Feature activation-2.01e-01

Pos logit contributions
acht+0.327
 Parenthood+0.277
uscript+0.274
ield+0.271
estic+0.268
Neg logit contributions
-0.273
-0.231
Islam-0.220
poll-0.220
REL-0.216
Token to
Token ID284
Feature activation-8.11e-01

Pos logit contributions
acht+0.182
 Parenthood+0.152
uscript+0.151
ield+0.149
estic+0.147
Neg logit contributions
-0.173
-0.148
Islam-0.141
poll-0.141
REL-0.139
Token Koch
Token ID17009
Feature activation+5.99e-01

Pos logit contributions
+0.080
+0.067
poll+0.064
Islam+0.064
REL+0.063
Neg logit contributions
acht-0.101
 Parenthood-0.085
uscript-0.085
ield-0.084
estic-0.083
Token Industries
Token ID20171
Feature activation-2.10e+00

Pos logit contributions
+0.702
+0.629
Islam+0.609
poll+0.609
REL+0.604
Neg logit contributions
acht-0.359
 Parenthood-0.266
uscript-0.265
ield-0.258
estic-0.253
Token,
Token ID11
Feature activation+1.96e-02

Pos logit contributions
acht+2.044
 Parenthood+1.743
uscript+1.711
ield+1.702
estic+1.682
Neg logit contributions
-1.657
-1.396
poll-1.332
Islam-1.329
REL-1.312
Token and
Token ID290
Feature activation-1.41e-01

Pos logit contributions
+0.017
+0.014
Islam+0.013
poll+0.013
REL+0.013
Neg logit contributions
acht-0.018
 Parenthood-0.015
uscript-0.015
ield-0.015
estic-0.015
Token other
Token ID584
Feature activation+6.39e-01

Pos logit contributions
acht+0.139
 Parenthood+0.118
uscript+0.117
ield+0.116
estic+0.114
Neg logit contributions
-0.111
-0.094
Islam-0.089
poll-0.089
REL-0.088
Token coal
Token ID5655
Feature activation+8.06e+00

Pos logit contributions
+0.498
+0.421
poll+0.401
Islam+0.399
REL+0.394
Neg logit contributions
acht-0.629
 Parenthood-0.532
uscript-0.532
ield-0.523
estic-0.517
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
+5.155
+4.188
poll+3.988
Islam+3.861
REL+3.853
Neg logit contributions
acht-8.765
uscript-7.749
 Parenthood-7.729
ocument-7.504
ield-7.433
Token oil
Token ID3056
Feature activation+2.16e+00

Pos logit contributions
+0.146
+0.122
Islam+0.117
REL+0.115
poll+0.115
Neg logit contributions
acht-0.177
 Parenthood-0.149
uscript-0.147
ield-0.147
estic-0.146
Token,
Token ID11
Feature activation+7.93e-02

Pos logit contributions
+1.995
+1.726
Islam+1.657
poll+1.655
REL+1.637
Neg logit contributions
acht-1.827
 Parenthood-1.501
uscript-1.486
ield-1.470
estic-1.448
Token and
Token ID290
Feature activation-6.78e-02

Pos logit contributions
+0.066
+0.056
Islam+0.054
REL+0.053
poll+0.053
Neg logit contributions
acht-0.074
 Parenthood-0.062
uscript-0.061
ield-0.061
estic-0.060
Token gas
Token ID3623
Feature activation+5.88e+00

Pos logit contributions
acht+0.071
 Parenthood+0.061
uscript+0.060
ield+0.060
estic+0.059
Neg logit contributions
-0.049
-0.040
Islam-0.038
poll-0.038
REL-0.038
Token life
Token ID1204
Feature activation-2.51e-01

Pos logit contributions
acht+1.218
 Parenthood+1.027
uscript+1.017
ield+1.010
estic+0.996
Neg logit contributions
-1.014
-0.856
Islam-0.818
poll-0.817
REL-0.805
Token;
Token ID26
Feature activation+7.85e-01

Pos logit contributions
acht+0.219
 Parenthood+0.181
uscript+0.179
ield+0.177
estic+0.175
Neg logit contributions
-0.225
-0.193
poll-0.185
Islam-0.185
REL-0.183
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
+0.618
+0.520
Islam+0.495
poll+0.494
REL+0.487
Neg logit contributions
acht-0.772
 Parenthood-0.653
uscript-0.648
ield-0.642
estic-0.633
Token chance
Token ID2863
Feature activation+1.68e+00

Pos logit contributions
+0.947
+0.795
poll+0.756
Islam+0.756
REL+0.745
Neg logit contributions
acht-1.207
 Parenthood-1.024
uscript-1.017
ield-1.006
estic-0.995
Token to
Token ID284
Feature activation+5.05e-01

Pos logit contributions
+1.359
+1.149
poll+1.093
Islam+1.090
REL+1.078
Neg logit contributions
acht-1.610
 Parenthood-1.362
uscript-1.348
ield-1.337
estic-1.320
Token escape
Token ID6654
Feature activation+8.03e+00

Pos logit contributions
+0.388
+0.326
Islam+0.310
poll+0.309
REL+0.305
Neg logit contributions
acht-0.505
 Parenthood-0.429
uscript-0.426
ield-0.421
estic-0.416
Token the
Token ID262
Feature activation+4.08e-01

Pos logit contributions
+5.616
+4.683
poll+4.483
Islam+4.386
REL+4.291
Neg logit contributions
acht-8.178
uscript-6.992
 Parenthood-6.957
ield-6.926
assium-6.871
Token to
Token ID284
Feature activation+2.67e-01

Pos logit contributions
+0.322
+0.272
Islam+0.258
poll+0.258
REL+0.255
Neg logit contributions
acht-0.400
 Parenthood-0.338
uscript-0.336
ield-0.332
estic-0.328
Tokenil
Token ID346
Feature activation+3.15e+00

Pos logit contributions
+0.240
+0.206
Islam+0.198
poll+0.197
REL+0.196
Neg logit contributions
acht-0.232
 Parenthood-0.192
uscript-0.190
ield-0.188
estic-0.186
Token caused
Token ID4073
Feature activation-2.72e+00

Pos logit contributions
+2.368
+1.975
poll+1.880
Islam+1.870
REL+1.836
Neg logit contributions
acht-3.181
 Parenthood-2.732
uscript-2.710
ield-2.668
estic-2.637
Token by
Token ID416
Feature activation+5.35e-01

Pos logit contributions
acht+2.237
 Parenthood+1.833
uscript+1.803
ield+1.787
estic+1.764
Neg logit contributions
-2.516
-2.195
poll-2.118
Islam-2.118
REL-2.093
Token by
Token ID416
Feature activation+8.65e-01

Pos logit contributions
+1.022
+0.880
Islam+0.843
poll+0.843
REL+0.833
Neg logit contributions
acht-0.994
 Parenthood-0.822
uscript-0.815
ield-0.806
estic-0.794
Token the
Token ID262
Feature activation-2.85e-02

Pos logit contributions
+0.669
+0.562
poll+0.535
Islam+0.534
REL+0.526
Neg logit contributions
acht-0.860
 Parenthood-0.730
uscript-0.725
ield-0.717
estic-0.709
Token results
Token ID2482
Feature activation-9.16e-01

Pos logit contributions
acht+0.028
 Parenthood+0.024
uscript+0.024
ield+0.024
estic+0.023
Neg logit contributions
-0.022
-0.018
Islam-0.018
poll-0.017
REL-0.017
Token of
Token ID286
Feature activation+9.18e-01

Pos logit contributions
acht+0.930
 Parenthood+0.791
uscript+0.782
ield+0.778
estic+0.769
Neg logit contributions
-0.695
-0.578
Islam-0.549
poll-0.540
REL-0.540
Token a
Token ID257
Feature activation+5.27e-01

Pos logit contributions
+0.726
+0.615
poll+0.589
Islam+0.583
REL+0.577
Neg logit contributions
acht-0.894
 Parenthood-0.753
uscript-0.751
ield-0.742
estic-0.734
Token straw
Token ID14787
Feature activation+8.03e+00

Pos logit contributions
+0.448
+0.383
poll+0.366
Islam+0.366
REL+0.361
Neg logit contributions
acht-0.485
 Parenthood-0.405
uscript-0.402
ield-0.397
estic-0.392
Token poll
Token ID3278
Feature activation+2.32e+00

Pos logit contributions
+1.788
poll+1.127
+0.921
 poll+0.675
Islam+0.585
Neg logit contributions
acht-12.150
uscript-10.924
ield-10.768
 Parenthood-10.737
assium-10.727
Token conducted
Token ID5952
Feature activation-4.53e+00

Pos logit contributions
+1.844
+1.580
poll+1.534
Islam+1.492
REL+1.477
Neg logit contributions
acht-2.224
 Parenthood-1.876
uscript-1.873
ield-1.844
ocument-1.825
Token this
Token ID428
Feature activation-1.64e+00

Pos logit contributions
acht+3.759
 Parenthood+3.136
uscript+3.048
ield+3.008
estic+2.983
Neg logit contributions
-4.164
-3.571
Islam-3.463
REL-3.411
poll-3.389
Token weekend
Token ID5041
Feature activation+1.21e+00

Pos logit contributions
acht+1.247
 Parenthood+1.011
uscript+0.992
ield+0.979
estic+0.963
Neg logit contributions
-1.648
-1.443
Islam-1.390
poll-1.379
REL-1.372
Token in
Token ID287
Feature activation-1.93e-01

Pos logit contributions
+1.026
+0.883
poll+0.851
Islam+0.840
REL+0.827
Neg logit contributions
acht-1.102
 Parenthood-0.920
uscript-0.917
ield-0.900
estic-0.889
Token,
Token ID11
Feature activation+2.20e-01

Pos logit contributions
+2.738
+2.324
Islam+2.240
poll+2.235
REL+2.216
Neg logit contributions
acht-3.070
uscript-2.607
 Parenthood-2.592
ield-2.542
assium-2.514
Token f
Token ID277
Feature activation+4.11e+00

Pos logit contributions
+0.179
+0.152
Islam+0.144
poll+0.144
REL+0.142
Neg logit contributions
acht-0.210
 Parenthood-0.177
uscript-0.175
ield-0.174
estic-0.172
Tokenirmed
Token ID15491
Feature activation-1.59e+00

Pos logit contributions
+3.032
+2.546
poll+2.418
Islam+2.412
REL+2.378
Neg logit contributions
acht-4.188
 Parenthood-3.601
uscript-3.557
ield-3.500
ocument-3.458
Token up
Token ID510
Feature activation+9.54e-01

Pos logit contributions
acht+1.538
 Parenthood+1.299
ield+1.285
uscript+1.277
estic+1.264
Neg logit contributions
-1.268
-1.072
Islam-1.026
poll-1.016
REL-1.007
Token by
Token ID416
Feature activation+1.44e+00

Pos logit contributions
+0.728
+0.609
poll+0.579
Islam+0.579
REL+0.570
Neg logit contributions
acht-0.960
 Parenthood-0.816
uscript-0.811
ield-0.801
estic-0.792
Token gas
Token ID3623
Feature activation+8.02e+00

Pos logit contributions
+1.109
+0.930
Islam+0.884
poll+0.883
REL+0.871
Neg logit contributions
acht-1.437
 Parenthood-1.221
uscript-1.212
ield-1.199
estic-1.185
Token and
Token ID290
Feature activation+2.09e-01

Pos logit contributions
+5.896
+4.959
poll+4.798
Islam+4.712
REL+4.700
Neg logit contributions
acht-7.931
uscript-6.889
 Parenthood-6.748
ield-6.575
ocument-6.534
Token soon
Token ID2582
Feature activation+1.55e+00

Pos logit contributions
+0.147
+0.120
Islam+0.113
poll+0.113
REL+0.111
Neg logit contributions
acht-0.224
 Parenthood-0.192
uscript-0.190
ield-0.189
estic-0.187
Token battery
Token ID6555
Feature activation+3.06e+00

Pos logit contributions
+1.214
+1.021
Islam+0.972
poll+0.971
REL+0.957
Neg logit contributions
acht-1.530
 Parenthood-1.295
uscript-1.284
ield-1.272
estic-1.258
Token storage
Token ID6143
Feature activation+3.45e+00

Pos logit contributions
+2.360
+1.987
poll+1.892
Islam+1.892
REL+1.869
Neg logit contributions
acht-3.037
 Parenthood-2.578
uscript-2.574
ield-2.528
estic-2.494
Token.
Token ID13
Feature activation+8.99e-01

Pos logit contributions
+3.020
+2.601
poll+2.503
Islam+2.499
REL+2.470
Neg logit contributions
acht-3.039
uscript-2.541
 Parenthood-2.527
ield-2.470
estic-2.436
Token
Token ID198
Feature activation+1.88e-01

Pos logit contributions
+0.389
+0.326
Islam+0.308
poll+0.306
REL+0.305
Neg logit contributions
acht-0.475
 Parenthood-0.403
ield-0.396
uscript-0.395
estic-0.389
Token"
Token ID1
Feature activation+3.08e-01

Pos logit contributions
+0.168
+0.145
poll+0.138
Islam+0.137
REL+0.137
Neg logit contributions
acht-0.164
 Parenthood-0.135
uscript-0.135
ield-0.134
estic-0.131
TokenI
Token ID40
Feature activation+2.16e+00

Pos logit contributions
+0.265
+0.227
poll+0.217
Islam+0.216
REL+0.214
Neg logit contributions
acht-0.280
 Parenthood-0.234
uscript-0.232
ield-0.229
estic-0.226
Token hope
Token ID2911
Feature activation+1.15e+00

Pos logit contributions
+1.370
+1.104
Islam+1.039
poll+1.035
REL+1.025
Neg logit contributions
acht-2.434
 Parenthood-2.119
uscript-2.102
ield-2.076
estic-2.056
Token he
Token ID339
Feature activation+5.44e-01

Pos logit contributions
+0.890
+0.749
Islam+0.712
poll+0.710
REL+0.699
Neg logit contributions
acht-1.151
 Parenthood-0.976
uscript-0.970
ield-0.960
estic-0.947
Token apolog
Token ID8453
Feature activation+7.98e+00

Pos logit contributions
+0.451
+0.383
Islam+0.365
poll+0.365
REL+0.360
Neg logit contributions
acht-0.512
 Parenthood-0.429
uscript-0.426
ield-0.421
estic-0.416
Tokenizes
Token ID4340
Feature activation-4.05e-02

Pos logit contributions
+4.689
+3.793
Islam+3.561
poll+3.467
istas+3.425
Neg logit contributions
acht-9.116
everal-7.945
 Parenthood-7.901
uscript-7.761
ocument-7.738
Token tomorrow
Token ID9439
Feature activation-1.53e+00

Pos logit contributions
acht+0.037
 Parenthood+0.031
uscript+0.030
ield+0.030
estic+0.030
Neg logit contributions
-0.035
-0.030
Islam-0.029
poll-0.029
REL-0.028
Token,"
Token ID553
Feature activation+1.41e+00

Pos logit contributions
acht+1.337
 Parenthood+1.107
uscript+1.094
ield+1.082
estic+1.066
Neg logit contributions
-1.366
-1.175
poll-1.126
Islam-1.126
REL-1.116
Token Crow
Token ID15502
Feature activation+3.90e-01

Pos logit contributions
+1.144
+0.968
Islam+0.924
poll+0.922
REL+0.911
Neg logit contributions
acht-1.350
 Parenthood-1.138
uscript-1.130
ield-1.118
estic-1.103
Tokender
Token ID1082
Feature activation+2.11e+00

Pos logit contributions
+0.356
+0.306
Islam+0.293
poll+0.291
REL+0.290
Neg logit contributions
acht-0.337
 Parenthood-0.276
ield-0.274
uscript-0.274
estic-0.268
Token two
Token ID734
Feature activation+2.77e-01

Pos logit contributions
+0.587
+0.501
poll+0.479
Islam+0.478
REL+0.472
Neg logit contributions
acht-0.647
 Parenthood-0.541
uscript-0.538
ield-0.531
estic-0.524
Token different
Token ID1180
Feature activation-6.08e-01

Pos logit contributions
+0.221
+0.187
Islam+0.178
poll+0.178
REL+0.176
Neg logit contributions
acht-0.268
 Parenthood-0.227
uscript-0.225
ield-0.223
estic-0.220
Token concepts
Token ID10838
Feature activation-1.44e+00

Pos logit contributions
acht+0.586
 Parenthood+0.495
uscript+0.490
ield+0.485
estic+0.480
Neg logit contributions
-0.489
-0.414
Islam-0.395
poll-0.395
REL-0.389
Token from
Token ID422
Feature activation+4.47e-01

Pos logit contributions
acht+1.239
 Parenthood+1.024
uscript+1.014
ield+1.000
estic+0.989
Neg logit contributions
-1.302
-1.120
poll-1.079
Islam-1.078
REL-1.065
Token the
Token ID262
Feature activation-1.67e-01

Pos logit contributions
+0.356
+0.300
Islam+0.285
poll+0.285
REL+0.281
Neg logit contributions
acht-0.435
 Parenthood-0.367
uscript-0.365
ield-0.362
estic-0.357
Token arg
Token ID1822
Feature activation+7.95e+00

Pos logit contributions
acht+0.152
 Parenthood+0.128
uscript+0.126
ield+0.125
estic+0.123
Neg logit contributions
-0.143
-0.122
Islam-0.117
poll-0.117
REL-0.115
Tokenuable
Token ID7153
Feature activation+2.65e-01

Pos logit contributions
+6.759
+5.831
poll+5.661
Islam+5.549
REL+5.545
Neg logit contributions
acht-6.870
 Parenthood-5.820
uscript-5.697
ield-5.617
assium-5.557
Token king
Token ID5822
Feature activation-1.15e+00

Pos logit contributions
+0.219
+0.186
poll+0.177
Islam+0.177
REL+0.175
Neg logit contributions
acht-0.249
 Parenthood-0.209
uscript-0.208
ield-0.206
estic-0.203
Token of
Token ID286
Feature activation+9.59e-01

Pos logit contributions
acht+1.155
 Parenthood+0.979
uscript+0.977
ield+0.965
estic+0.956
Neg logit contributions
-0.879
-0.734
Islam-0.698
poll-0.695
REL-0.691
Token curse
Token ID17328
Feature activation+1.41e+00

Pos logit contributions
+0.782
+0.663
Islam+0.632
poll+0.631
REL+0.622
Neg logit contributions
acht-0.915
 Parenthood-0.770
uscript-0.764
ield-0.756
estic-0.746
Token,
Token ID11
Feature activation+6.74e-02

Pos logit contributions
+1.191
+1.016
Islam+0.969
poll+0.969
REL+0.956
Neg logit contributions
acht-1.310
 Parenthood-1.098
uscript-1.090
ield-1.077
estic-1.062
Token.
Token ID13
Feature activation-5.73e-01

Pos logit contributions
acht+0.522
 Parenthood+0.422
uscript+0.418
ield+0.413
estic+0.406
Neg logit contributions
-0.626
-0.545
Islam-0.524
poll-0.523
REL-0.518
Token
Token ID198
Feature activation+2.36e-01

Pos logit contributions
acht+0.562
 Parenthood+0.476
uscript+0.471
ield+0.468
estic+0.462
Neg logit contributions
-0.451
-0.380
Islam-0.361
poll-0.358
REL-0.354
Token
Token ID198
Feature activation+5.28e-03

Pos logit contributions
+0.187
+0.156
Islam+0.148
poll+0.147
REL+0.146
Neg logit contributions
acht-0.231
 Parenthood-0.196
ield-0.192
uscript-0.192
estic-0.189
TokenWith
Token ID3152
Feature activation-1.62e+00

Pos logit contributions
+0.004
+0.004
Islam+0.003
poll+0.003
REL+0.003
Neg logit contributions
acht-0.005
 Parenthood-0.004
uscript-0.004
ield-0.004
estic-0.004
Token Josh
Token ID8518
Feature activation-3.20e+00

Pos logit contributions
acht+1.555
 Parenthood+1.319
uscript+1.301
ield+1.290
estic+1.272
Neg logit contributions
-1.305
-1.100
Islam-1.058
poll-1.049
REL-1.038
Token Doct
Token ID32155
Feature activation-8.59e+00

Pos logit contributions
acht+2.778
 Parenthood+2.297
ield+2.259
uscript+2.257
estic+2.214
Neg logit contributions
-2.861
-2.470
poll-2.374
Islam-2.367
REL-2.343
Tokenson
Token ID1559
Feature activation-1.42e+00

Pos logit contributions
acht+4.651
ield+3.557
estic+3.441
 Parenthood+3.288
uscript+3.213
Neg logit contributions
-10.341
-9.102
Islam-9.047
REL-8.863
ardless-8.682
Token finally
Token ID3443
Feature activation+1.84e+00

Pos logit contributions
acht+1.346
 Parenthood+1.133
uscript+1.124
ield+1.112
estic+1.098
Neg logit contributions
-1.160
-0.983
Islam-0.938
poll-0.936
REL-0.924
Token becoming
Token ID5033
Feature activation-9.85e-01

Pos logit contributions
+1.320
+1.101
poll+1.049
Islam+1.038
REL+1.023
Neg logit contributions
acht-1.919
uscript-1.635
 Parenthood-1.625
ield-1.612
ocument-1.595
Token a
Token ID257
Feature activation-5.04e-02

Pos logit contributions
acht+0.948
 Parenthood+0.803
uscript+0.793
ield+0.786
estic+0.776
Neg logit contributions
-0.793
-0.669
Islam-0.639
poll-0.638
REL-0.629
Token force
Token ID2700
Feature activation+6.64e-01

Pos logit contributions
acht+0.048
 Parenthood+0.041
uscript+0.040
ield+0.040
estic+0.039
Neg logit contributions
-0.041
-0.035
poll-0.033
Islam-0.033
REL-0.032
Token I
Token ID314
Feature activation+2.52e+00

Pos logit contributions
+0.068
+0.058
Islam+0.056
poll+0.055
REL+0.055
Neg logit contributions
acht-0.071
 Parenthood-0.059
uscript-0.059
ield-0.058
estic-0.057
Token
Token ID447
Feature activation+8.45e-01

Pos logit contributions
+1.802
+1.493
Islam+1.409
poll+1.399
REL+1.396
Neg logit contributions
acht-2.645
 Parenthood-2.275
uscript-2.248
ield-2.221
estic-2.202
Token
Token ID247
Feature activation-1.02e+00

Pos logit contributions
+0.839
+0.734
Islam+0.706
poll+0.706
REL+0.699
Neg logit contributions
acht-0.656
 Parenthood-0.529
uscript-0.524
ield-0.517
estic-0.508
Tokenve
Token ID303
Feature activation+3.91e-01

Pos logit contributions
acht+1.252
 Parenthood+1.095
uscript+1.093
ield+1.086
estic+1.074
Neg logit contributions
-0.550
-0.424
Islam-0.391
poll-0.390
REL-0.380
Token developed
Token ID4166
Feature activation-1.90e+00

Pos logit contributions
+0.313
+0.266
Islam+0.252
poll+0.252
REL+0.249
Neg logit contributions
acht-0.376
 Parenthood-0.319
uscript-0.316
ield-0.312
estic-0.308
Token parad
Token ID11497
Feature activation-8.51e+00

Pos logit contributions
acht+1.812
 Parenthood+1.522
uscript+1.506
ield+1.493
estic+1.470
Neg logit contributions
-1.559
-1.325
Islam-1.264
poll-1.261
REL-1.243
Tokenig
Token ID328
Feature activation+2.48e+00

Pos logit contributions
acht+6.604
estic+5.294
uscript+5.256
ield+5.223
ocument+5.148
Neg logit contributions
-8.259
-7.262
Islam-6.888
REL-6.874
poll-6.836
Tokenms
Token ID907
Feature activation-1.40e+00

Pos logit contributions
+2.388
+2.085
Islam+2.007
poll+2.003
REL+1.982
Neg logit contributions
acht-1.998
 Parenthood-1.627
uscript-1.606
ield-1.583
estic-1.556
Token based
Token ID1912
Feature activation+9.92e-01

Pos logit contributions
acht+1.331
 Parenthood+1.120
uscript+1.110
ield+1.099
estic+1.086
Neg logit contributions
-1.145
-0.971
poll-0.928
Islam-0.927
REL-0.916
Token on
Token ID319
Feature activation-1.61e-01

Pos logit contributions
+0.843
+0.721
Islam+0.689
poll+0.688
REL+0.679
Neg logit contributions
acht-0.912
 Parenthood-0.762
uscript-0.756
ield-0.748
estic-0.738
Token such
Token ID884
Feature activation-1.38e+00

Pos logit contributions
acht+0.154
 Parenthood+0.130
uscript+0.129
ield+0.127
estic+0.126
Neg logit contributions
-0.132
-0.112
Islam-0.107
poll-0.106
REL-0.105
Token cancelled
Token ID16769
Feature activation-3.54e-01

Pos logit contributions
acht+0.813
 Parenthood+0.683
uscript+0.677
ield+0.670
estic+0.661
Neg logit contributions
-0.715
-0.607
Islam-0.580
poll-0.579
REL-0.572
Token,
Token ID11
Feature activation-2.53e-01

Pos logit contributions
acht+0.320
 Parenthood+0.267
uscript+0.263
ield+0.262
estic+0.258
Neg logit contributions
-0.306
-0.262
Islam-0.251
poll-0.250
REL-0.248
Token besides
Token ID13769
Feature activation-1.10e+00

Pos logit contributions
acht+0.242
 Parenthood+0.204
uscript+0.202
ield+0.201
estic+0.198
Neg logit contributions
-0.206
-0.174
Islam-0.166
poll-0.165
REL-0.164
Token serious
Token ID2726
Feature activation-1.08e+00

Pos logit contributions
acht+1.025
 Parenthood+0.859
uscript+0.849
ield+0.841
estic+0.830
Neg logit contributions
-0.926
-0.787
Islam-0.752
poll-0.748
REL-0.743
Token damage
Token ID2465
Feature activation-2.40e+00

Pos logit contributions
acht+1.060
 Parenthood+0.896
uscript+0.888
ield+0.881
estic+0.870
Neg logit contributions
-0.855
-0.719
Islam-0.686
poll-0.683
REL-0.679
Token inflicted
Token ID27010
Feature activation-8.51e+00

Pos logit contributions
acht+2.188
 Parenthood+1.804
ield+1.781
uscript+1.780
estic+1.763
Neg logit contributions
-2.053
-1.762
REL-1.672
Islam-1.670
poll-1.660
Token on
Token ID319
Feature activation-1.13e+00

Pos logit contributions
acht+6.802
 Parenthood+5.530
ield+5.400
 Hots+5.358
uscript+5.340
Neg logit contributions
-7.672
-6.665
REL-6.478
Islam-6.372
poll-6.302
Token rail
Token ID6787
Feature activation+4.87e+00

Pos logit contributions
acht+1.113
 Parenthood+0.944
uscript+0.935
ield+0.925
estic+0.914
Neg logit contributions
-0.887
-0.745
Islam-0.709
poll-0.706
REL-0.700
Token property
Token ID3119
Feature activation-9.03e-01

Pos logit contributions
+3.684
+3.100
poll+2.962
Islam+2.925
REL+2.870
Neg logit contributions
acht-4.834
 Parenthood-4.195
uscript-4.162
ield-4.051
assium-4.021
Token.
Token ID13
Feature activation+3.89e-01

Pos logit contributions
acht+0.789
 Parenthood+0.651
uscript+0.642
ield+0.641
estic+0.629
Neg logit contributions
-0.810
-0.697
Islam-0.667
poll-0.666
REL-0.660
Token The
Token ID383
Feature activation-2.52e-01

Pos logit contributions
+0.338
+0.290
Islam+0.278
poll+0.278
REL+0.274
Neg logit contributions
acht-0.350
 Parenthood-0.291
uscript-0.289
ield-0.285
estic-0.281
Token My
Token ID2011
Feature activation+1.45e+00

Pos logit contributions
acht+0.157
 Parenthood+0.132
uscript+0.130
ield+0.129
estic+0.127
Neg logit contributions
-0.146
-0.125
Islam-0.119
poll-0.119
REL-0.118
Token favorites
Token ID18852
Feature activation-3.09e-01

Pos logit contributions
+1.073
+0.894
Islam+0.846
poll+0.846
REL+0.832
Neg logit contributions
acht-1.499
 Parenthood-1.278
uscript-1.271
ield-1.257
estic-1.243
Token to
Token ID284
Feature activation-5.91e-01

Pos logit contributions
acht+0.279
 Parenthood+0.233
uscript+0.231
ield+0.228
estic+0.225
Neg logit contributions
-0.268
-0.229
Islam-0.219
poll-0.219
REL-0.216
Token use
Token ID779
Feature activation+5.66e-01

Pos logit contributions
acht+0.568
 Parenthood+0.480
uscript+0.474
ield+0.472
estic+0.465
Neg logit contributions
-0.478
-0.402
Islam-0.386
poll-0.385
REL-0.379
Token are
Token ID389
Feature activation+7.93e-01

Pos logit contributions
+0.477
+0.408
poll+0.390
Islam+0.389
REL+0.384
Neg logit contributions
acht-0.523
 Parenthood-0.437
uscript-0.435
ield-0.429
estic-0.423
Token Whole
Token ID23431
Feature activation-8.39e+00

Pos logit contributions
+0.637
+0.538
Islam+0.513
poll+0.512
REL+0.505
Neg logit contributions
acht-0.766
 Parenthood-0.647
uscript-0.642
ield-0.636
estic-0.627
Token Al
Token ID978
Feature activation+2.19e+00

Pos logit contributions
acht+7.448
 Parenthood+6.419
ield+6.192
estic+6.035
assium+6.017
Neg logit contributions
-6.950
-5.916
REL-5.648
poll-5.581
Islam-5.560
Tokenmonds
Token ID42620
Feature activation-4.34e+00

Pos logit contributions
+2.113
+1.843
Islam+1.774
poll+1.773
REL+1.751
Neg logit contributions
acht-1.748
 Parenthood-1.422
uscript-1.409
ield-1.383
estic-1.365
Token,
Token ID837
Feature activation-8.87e-01

Pos logit contributions
acht+3.690
 Parenthood+3.061
ield+3.001
uscript+2.964
estic+2.927
Neg logit contributions
-3.958
-3.418
Islam-3.272
poll-3.252
REL-3.231
Token P
Token ID350
Feature activation-1.34e+00

Pos logit contributions
acht+0.778
 Parenthood+0.647
uscript+0.638
ield+0.633
estic+0.623
Neg logit contributions
-0.789
-0.679
Islam-0.651
poll-0.649
REL-0.643
Tokenec
Token ID721
Feature activation+1.76e+00

Pos logit contributions
acht+1.223
ield+1.009
estic+1.005
uscript+1.005
 Parenthood+0.996
Neg logit contributions
-1.155
-0.986
poll-0.941
Islam-0.939
REL-0.919
Token network
Token ID3127
Feature activation+1.42e+00

Pos logit contributions
acht+0.521
 Parenthood+0.443
uscript+0.437
ield+0.435
estic+0.429
Neg logit contributions
-0.432
-0.365
Islam-0.348
poll-0.346
REL-0.343
Token,
Token ID11
Feature activation+3.00e-01

Pos logit contributions
+1.133
+0.957
Islam+0.911
poll+0.911
REL+0.898
Neg logit contributions
acht-1.373
 Parenthood-1.160
uscript-1.151
ield-1.139
estic-1.124
Token C
Token ID327
Feature activation+2.85e+00

Pos logit contributions
+0.234
+0.197
Islam+0.187
poll+0.187
REL+0.184
Neg logit contributions
acht-0.297
 Parenthood-0.252
uscript-0.249
ield-0.247
estic-0.244
TokenTO
Token ID10468
Feature activation-2.21e+00

Pos logit contributions
+2.322
+1.973
Islam+1.883
poll+1.880
REL+1.865
Neg logit contributions
acht-2.706
 Parenthood-2.286
uscript-2.264
ield-2.234
estic-2.203
Token John
Token ID1757
Feature activation-6.71e-02

Pos logit contributions
acht+2.143
 Parenthood+1.811
uscript+1.787
ield+1.778
estic+1.754
Neg logit contributions
-1.749
-1.467
Islam-1.406
poll-1.403
REL-1.386
Token Saw
Token ID19882
Feature activation-8.28e+00

Pos logit contributions
acht+0.061
 Parenthood+0.051
uscript+0.050
ield+0.050
estic+0.049
Neg logit contributions
-0.058
-0.050
Islam-0.048
poll-0.047
REL-0.047
Token said
Token ID531
Feature activation-1.07e+00

Pos logit contributions
acht+7.848
ield+6.623
estic+6.537
uscript+6.472
 Parenthood+6.459
Neg logit contributions
-6.456
-5.449
Islam-5.103
REL-5.028
poll-4.980
Token yesterday
Token ID7415
Feature activation-1.10e+00

Pos logit contributions
acht+0.949
 Parenthood+0.789
uscript+0.779
ield+0.774
estic+0.763
Neg logit contributions
-0.936
-0.804
Islam-0.769
poll-0.767
REL-0.757
Token.
Token ID13
Feature activation-3.03e-02

Pos logit contributions
acht+0.906
 Parenthood+0.738
uscript+0.731
ield+0.725
estic+0.713
Neg logit contributions
-1.035
-0.898
Islam-0.864
poll-0.861
REL-0.854
Token
Token ID198
Feature activation+8.97e-02

Pos logit contributions
acht+0.029
 Parenthood+0.024
uscript+0.024
ield+0.024
estic+0.024
Neg logit contributions
-0.025
-0.021
Islam-0.020
poll-0.020
REL-0.020
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
+0.071
+0.060
Islam+0.057
poll+0.056
REL+0.056
Neg logit contributions
acht-0.087
 Parenthood-0.074
ield-0.073
uscript-0.072
estic-0.071
Token the
Token ID262
Feature activation-2.90e-01

Pos logit contributions
+0.327
+0.273
poll+0.260
Islam+0.259
REL+0.255
Neg logit contributions
acht-0.431
 Parenthood-0.366
uscript-0.364
ield-0.360
estic-0.355
Token ecological
Token ID25047
Feature activation+2.73e+00

Pos logit contributions
acht+0.277
 Parenthood+0.233
uscript+0.232
ield+0.229
estic+0.226
Neg logit contributions
-0.236
-0.200
poll-0.191
Islam-0.191
REL-0.188
Token damage
Token ID2465
Feature activation-2.06e+00

Pos logit contributions
+2.144
+1.809
poll+1.722
Islam+1.711
REL+1.680
Neg logit contributions
acht-2.693
uscript-2.270
 Parenthood-2.265
ield-2.221
estic-2.206
Token the
Token ID262
Feature activation-4.71e-01

Pos logit contributions
acht+1.831
 Parenthood+1.513
ield+1.494
uscript+1.494
estic+1.477
Neg logit contributions
-1.811
-1.560
Islam-1.494
REL-1.478
poll-1.477
Token plantations
Token ID49441
Feature activation-7.78e-01

Pos logit contributions
acht+0.455
 Parenthood+0.384
uscript+0.381
ield+0.377
estic+0.372
Neg logit contributions
-0.380
-0.321
Islam-0.306
poll-0.306
REL-0.302
Token inflicted
Token ID27010
Feature activation-8.24e+00

Pos logit contributions
acht+0.722
 Parenthood+0.603
uscript+0.596
ield+0.592
estic+0.585
Neg logit contributions
-0.657
-0.560
Islam-0.534
poll-0.532
REL-0.527
Token on
Token ID319
Feature activation-1.32e+00

Pos logit contributions
acht+6.746
 Parenthood+5.630
ield+5.428
 Hots+5.406
estic+5.379
Neg logit contributions
-7.268
-6.310
Islam-6.047
REL-6.019
poll-5.905
Token the
Token ID262
Feature activation-3.38e-01

Pos logit contributions
acht+1.310
 Parenthood+1.112
uscript+1.103
ield+1.093
estic+1.083
Neg logit contributions
-1.016
-0.852
Islam-0.813
poll-0.803
REL-0.802
Token islands
Token ID14807
Feature activation-1.36e+00

Pos logit contributions
acht+0.326
 Parenthood+0.275
uscript+0.273
ield+0.270
estic+0.266
Neg logit contributions
-0.273
-0.231
poll-0.221
Islam-0.220
REL-0.216
Token.
Token ID13
Feature activation+7.94e-01

Pos logit contributions
acht+1.198
 Parenthood+0.992
uscript+0.982
ield+0.973
estic+0.960
Neg logit contributions
-1.210
-1.042
Islam-0.999
poll-0.996
REL-0.986
Token
Token ID198
Feature activation+1.05e+00

Pos logit contributions
+0.660
+0.561
Islam+0.536
poll+0.535
REL+0.528
Neg logit contributions
acht-0.746
 Parenthood-0.626
uscript-0.621
ield-0.614
estic-0.606
TokenSte
Token ID7447
Feature activation+6.43e-01

Pos logit contributions
+0.157
+0.130
Islam+0.123
poll+0.123
REL+0.121
Neg logit contributions
acht-0.229
 Parenthood-0.196
uscript-0.196
ield-0.193
estic-0.191
Tokenin
Token ID259
Feature activation+2.23e+00

Pos logit contributions
+0.453
+0.373
Islam+0.352
poll+0.352
REL+0.346
Neg logit contributions
acht-0.685
 Parenthood-0.589
uscript-0.585
ield-0.579
estic-0.573
Token suffered
Token ID6989
Feature activation-5.44e+00

Pos logit contributions
+1.815
+1.544
poll+1.468
Islam+1.468
REL+1.445
Neg logit contributions
acht-2.114
 Parenthood-1.798
uscript-1.783
ield-1.740
ocument-1.737
Token an
Token ID281
Feature activation-1.75e-01

Pos logit contributions
acht+4.837
 Parenthood+4.055
ield+3.972
estic+3.953
 Hots+3.942
Neg logit contributions
-4.606
-3.877
poll-3.775
Islam-3.747
REL-3.674
Token open
Token ID1280
Feature activation+2.87e+00

Pos logit contributions
acht+0.162
uscript+0.136
 Parenthood+0.135
ield+0.132
ocument+0.131
Neg logit contributions
-0.148
-0.128
Islam-0.122
poll-0.120
REL-0.119
Token disl
Token ID19621
Feature activation-8.22e+00

Pos logit contributions
+2.209
+1.860
Islam+1.752
poll+1.737
REL+1.736
Neg logit contributions
acht-2.847
uscript-2.442
 Parenthood-2.435
ield-2.364
ocument-2.335
Tokenocation
Token ID5040
Feature activation-1.94e+00

Pos logit contributions
acht+7.099
ield+5.808
estic+5.641
uscript+5.514
assium+5.483
Neg logit contributions
-7.455
-6.310
REL-6.069
poll-5.991
Islam-5.891
Token of
Token ID286
Feature activation+2.90e-01

Pos logit contributions
acht+1.872
 Parenthood+1.574
uscript+1.558
ield+1.551
estic+1.536
Neg logit contributions
-1.549
-1.307
poll-1.248
Islam-1.247
REL-1.228
Token his
Token ID465
Feature activation+3.53e-01

Pos logit contributions
+0.222
+0.186
Islam+0.176
poll+0.176
REL+0.173
Neg logit contributions
acht-0.291
 Parenthood-0.248
uscript-0.246
ield-0.244
estic-0.240
Token finger
Token ID7660
Feature activation-1.26e+00

Pos logit contributions
+0.274
+0.231
Islam+0.219
poll+0.219
REL+0.216
Neg logit contributions
acht-0.350
 Parenthood-0.296
uscript-0.296
ield-0.291
estic-0.287
Token and
Token ID290
Feature activation-5.36e-01

Pos logit contributions
acht+1.158
 Parenthood+0.970
uscript+0.964
ield+0.950
estic+0.937
Neg logit contributions
-1.065
-0.908
poll-0.868
Islam-0.867
REL-0.857
Token Tampa
Token ID15528
Feature activation-3.25e+00

Pos logit contributions
+0.274
+0.232
poll+0.221
Islam+0.221
REL+0.218
Neg logit contributions
acht-0.325
 Parenthood-0.274
uscript-0.272
ield-0.269
estic-0.266
Token
Token ID447
Feature activation+2.17e-01

Pos logit contributions
acht+2.927
 Parenthood+2.433
ield+2.403
uscript+2.398
estic+2.356
Neg logit contributions
-2.795
-2.392
Islam-2.305
poll-2.303
REL-2.263
Token
Token ID247
Feature activation-1.49e+00

Pos logit contributions
+0.215
+0.188
Islam+0.181
poll+0.181
REL+0.179
Neg logit contributions
acht-0.169
 Parenthood-0.136
uscript-0.135
ield-0.133
estic-0.131
Tokens
Token ID82
Feature activation+1.31e+00

Pos logit contributions
acht+1.467
 Parenthood+1.242
uscript+1.232
ield+1.226
estic+1.210
Neg logit contributions
-1.159
-0.975
Islam-0.933
poll-0.926
REL-0.919
Token Jake
Token ID14757
Feature activation+3.75e-01

Pos logit contributions
+1.010
+0.848
poll+0.806
Islam+0.804
REL+0.793
Neg logit contributions
acht-1.304
 Parenthood-1.106
uscript-1.100
ield-1.086
estic-1.075
Token Od
Token ID10529
Feature activation-8.18e+00

Pos logit contributions
+0.334
+0.287
Islam+0.275
poll+0.275
REL+0.271
Neg logit contributions
acht-0.329
 Parenthood-0.273
uscript-0.271
ield-0.268
estic-0.264
Tokenor
Token ID273
Feature activation-1.75e+00

Pos logit contributions
acht+8.850
ield+7.685
uscript+7.501
 Parenthood+7.461
assium+7.457
Neg logit contributions
-5.722
-4.584
poll-4.205
Islam-4.153
REL-4.119
Tokenizz
Token ID6457
Feature activation-3.19e+00

Pos logit contributions
acht+1.110
 Parenthood+0.827
ield+0.819
uscript+0.816
estic+0.791
Neg logit contributions
-1.985
-1.770
Islam-1.711
poll-1.703
REL-1.696
Tokeni
Token ID72
Feature activation+1.88e+00

Pos logit contributions
acht+2.947
 Parenthood+2.460
uscript+2.442
ield+2.412
estic+2.383
Neg logit contributions
-2.704
-2.304
Islam-2.207
poll-2.202
REL-2.175
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
+1.684
+1.448
Islam+1.384
poll+1.383
REL+1.369
Neg logit contributions
acht-1.630
 Parenthood-1.351
uscript-1.342
ield-1.321
estic-1.311
Token San
Token ID2986
Feature activation-2.78e+00

Pos logit contributions
acht+0.124
 Parenthood+0.104
uscript+0.103
ield+0.102
estic+0.100
Neg logit contributions
-0.110
-0.094
Islam-0.089
poll-0.089
REL-0.088
Token22
Token ID1828
Feature activation+2.61e+00

Pos logit contributions
+1.272
+1.058
Islam+1.002
poll+1.002
REL+0.986
Neg logit contributions
acht-1.775
 Parenthood-1.515
uscript-1.505
ield-1.490
estic-1.473
Token O
Token ID440
Feature activation-2.63e+00

Pos logit contributions
+2.653
+2.343
poll+2.289
Islam+2.273
REL+2.234
Neg logit contributions
acht-1.944
uscript-1.560
everal-1.532
ield-1.517
 Parenthood-1.509
Token&
Token ID5
Feature activation-1.14e+00

Pos logit contributions
acht+1.981
 Parenthood+1.572
ield+1.546
uscript+1.521
estic+1.503
Neg logit contributions
-2.655
-2.333
Islam-2.225
poll-2.224
ardless-2.215
TokenA
Token ID32
Feature activation-5.57e-01

Pos logit contributions
acht+1.029
 Parenthood+0.863
ield+0.844
uscript+0.843
estic+0.828
Neg logit contributions
-0.979
-0.837
poll-0.796
Islam-0.793
REL-0.784
Token-
Token ID12
Feature activation-6.71e-01

Pos logit contributions
acht+0.584
 Parenthood+0.505
ield+0.494
uscript+0.492
estic+0.486
Neg logit contributions
-0.398
-0.327
Islam-0.307
poll-0.306
REL-0.304
TokenTom
Token ID13787
Feature activation-8.17e+00

Pos logit contributions
acht+0.624
 Parenthood+0.525
uscript+0.518
ield+0.514
estic+0.506
Neg logit contributions
-0.561
-0.479
Islam-0.455
poll-0.455
REL-0.449
Token Ret
Token ID4990
Feature activation-4.02e-01

Pos logit contributions
acht+7.005
 Parenthood+5.739
ield+5.636
uscript+5.626
estic+5.586
Neg logit contributions
-7.153
-6.204
Islam-5.992
REL-5.923
poll-5.857
Tokenired
Token ID1202
Feature activation-8.51e-01

Pos logit contributions
acht+0.313
 Parenthood+0.252
uscript+0.250
ield+0.246
estic+0.242
Neg logit contributions
-0.398
-0.348
Islam-0.336
poll-0.335
REL-0.332
Token-
Token ID12
Feature activation-6.85e-01

Pos logit contributions
acht+0.870
 Parenthood+0.743
uscript+0.737
ield+0.730
estic+0.720
Neg logit contributions
-0.636
-0.530
Islam-0.501
poll-0.501
REL-0.495
Token08
Token ID2919
Feature activation+1.56e-01

Pos logit contributions
acht+0.635
 Parenthood+0.533
uscript+0.527
ield+0.522
estic+0.514
Neg logit contributions
-0.575
-0.490
poll-0.466
Islam-0.466
REL-0.460
Token Election
Token ID14219
Feature activation+2.70e-01

Pos logit contributions
+0.138
+0.118
poll+0.114
Islam+0.113
REL+0.111
Neg logit contributions
acht-0.139
 Parenthood-0.115
uscript-0.115
ield-0.113
estic-0.111
Token
Token ID198
Feature activation-1.12e+00

Pos logit contributions
acht+1.041
 Parenthood+0.886
ield+0.866
uscript+0.854
estic+0.844
Neg logit contributions
-0.899
-0.753
Islam-0.711
poll-0.707
REL-0.704
TokenJustin
Token ID33229
Feature activation-5.20e+00

Pos logit contributions
acht+1.049
 Parenthood+0.877
uscript+0.868
ield+0.864
estic+0.847
Neg logit contributions
-0.934
-0.793
poll-0.754
Islam-0.752
REL-0.740
Token Williams
Token ID6484
Feature activation-1.96e+00

Pos logit contributions
acht+5.110
ield+4.265
 Parenthood+4.252
uscript+4.242
estic+4.215
Neg logit contributions
-3.965
-3.361
poll-3.216
Islam-3.206
REL-3.125
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
acht+1.783
 Parenthood+1.494
uscript+1.472
ield+1.462
estic+1.435
Neg logit contributions
-1.675
-1.429
poll-1.367
Islam-1.367
REL-1.345
Token
Token ID198
Feature activation-1.26e+00

Pos logit contributions
acht+1.181
 Parenthood+1.002
ield+0.980
uscript+0.967
estic+0.955
Neg logit contributions
-1.029
-0.862
Islam-0.813
poll-0.807
REL-0.807
TokenTom
Token ID13787
Feature activation-8.12e+00

Pos logit contributions
acht+1.200
 Parenthood+1.010
uscript+0.997
ield+0.994
estic+0.976
Neg logit contributions
-1.022
-0.863
poll-0.818
Islam-0.816
REL-0.803
Token Wilson
Token ID8127
Feature activation-1.90e+00

Pos logit contributions
acht+7.674
ield+6.352
 Parenthood+6.337
estic+6.299
assium+6.179
Neg logit contributions
-6.329
-5.345
Islam-5.229
REL-5.198
poll-5.130
Token
Token ID198
Feature activation-1.52e+00

Pos logit contributions
acht+1.857
 Parenthood+1.575
uscript+1.556
ield+1.548
estic+1.522
Neg logit contributions
-1.501
-1.262
Islam-1.205
poll-1.203
REL-1.183
Token
Token ID198
Feature activation-1.46e+00

Pos logit contributions
acht+1.411
 Parenthood+1.192
ield+1.171
uscript+1.146
estic+1.141
Neg logit contributions
-1.277
-1.073
Islam-1.010
REL-1.003
ardless-0.998
TokenT
Token ID51
Feature activation-2.38e+00

Pos logit contributions
acht+1.388
 Parenthood+1.167
uscript+1.149
ield+1.148
estic+1.128
Neg logit contributions
-1.186
-1.001
poll-0.946
Islam-0.944
REL-0.932
Token.
Token ID13
Feature activation-2.02e+00

Pos logit contributions
acht+2.117
ield+1.721
 Parenthood+1.720
uscript+1.718
estic+1.713
Neg logit contributions
-2.106
-1.807
Islam-1.723
poll-1.722
REL-1.679
Token reconstruction
Token ID25056
Feature activation-3.24e-01

Pos logit contributions
acht+1.275
 Parenthood+1.095
uscript+1.083
ield+1.074
estic+1.060
Neg logit contributions
-0.887
-0.735
Islam-0.698
poll-0.689
REL-0.679
Token is
Token ID318
Feature activation-1.03e-01

Pos logit contributions
acht+0.298
 Parenthood+0.249
uscript+0.247
ield+0.244
estic+0.241
Neg logit contributions
-0.276
-0.236
Islam-0.225
poll-0.225
REL-0.222
Token done
Token ID1760
Feature activation-4.59e+00

Pos logit contributions
acht+0.095
 Parenthood+0.079
uscript+0.079
ield+0.078
estic+0.077
Neg logit contributions
-0.087
-0.074
poll-0.071
Islam-0.071
REL-0.070
Token at
Token ID379
Feature activation-2.09e+00

Pos logit contributions
acht+4.142
 Parenthood+3.477
uscript+3.415
ield+3.393
estic+3.346
Neg logit contributions
-3.933
-3.370
Islam-3.214
poll-3.191
REL-3.150
Token the
Token ID262
Feature activation-3.35e-01

Pos logit contributions
acht+2.024
 Parenthood+1.715
uscript+1.701
ield+1.683
estic+1.663
Neg logit contributions
-1.671
-1.408
Islam-1.346
poll-1.337
REL-1.320
Token subt
Token ID13284
Feature activation-8.03e+00

Pos logit contributions
acht+0.296
 Parenthood+0.245
uscript+0.243
ield+0.240
estic+0.237
Neg logit contributions
-0.297
-0.256
poll-0.245
Islam-0.245
REL-0.242
Tokenape
Token ID1758
Feature activation-1.52e+00

Pos logit contributions
acht+6.912
uscript+5.702
estic+5.692
ield+5.672
 Parenthood+5.543
Neg logit contributions
-7.234
-6.131
Islam-5.848
REL-5.740
poll-5.668
Token level
Token ID1241
Feature activation+4.92e-02

Pos logit contributions
acht+1.323
 Parenthood+1.096
uscript+1.084
ield+1.074
estic+1.059
Neg logit contributions
-1.365
-1.176
Islam-1.131
poll-1.127
REL-1.113
Token.
Token ID13
Feature activation+3.08e-01

Pos logit contributions
+0.045
+0.039
Islam+0.037
poll+0.037
REL+0.037
Neg logit contributions
acht-0.042
 Parenthood-0.035
uscript-0.035
ield-0.034
estic-0.034
Token Don
Token ID2094
Feature activation+1.55e+00

Pos logit contributions
+0.261
+0.223
poll+0.213
Islam+0.213
REL+0.210
Neg logit contributions
acht-0.284
 Parenthood-0.237
uscript-0.235
ield-0.233
estic-0.230
Token
Token ID447
Feature activation+1.02e+00

Pos logit contributions
+0.893
+0.701
Islam+0.651
poll+0.650
REL+0.636
Neg logit contributions
acht-1.843
 Parenthood-1.610
uscript-1.601
ield-1.587
estic-1.571
Token-
Token ID12
Feature activation-6.74e-01

Pos logit contributions
acht+2.880
 Parenthood+2.343
uscript+2.276
ield+2.249
estic+2.237
Neg logit contributions
-3.864
-3.383
REL-3.236
Islam-3.232
poll-3.229
TokenSt
Token ID1273
Feature activation-1.83e-01

Pos logit contributions
acht+0.621
 Parenthood+0.521
uscript+0.514
ield+0.510
estic+0.503
Neg logit contributions
-0.569
-0.485
poll-0.461
Islam-0.460
REL-0.455
Tokenall
Token ID439
Feature activation+2.06e+00

Pos logit contributions
acht+0.165
 Parenthood+0.137
uscript+0.136
ield+0.135
estic+0.133
Neg logit contributions
-0.160
-0.137
poll-0.131
Islam-0.131
REL-0.129
Tokenone
Token ID505
Feature activation-2.54e+00

Pos logit contributions
+1.777
+1.521
poll+1.464
Islam+1.463
REL+1.434
Neg logit contributions
acht-1.853
 Parenthood-1.537
uscript-1.534
ield-1.514
estic-1.490
Token-
Token ID12
Feature activation-5.65e-01

Pos logit contributions
acht+2.173
 Parenthood+1.803
uscript+1.769
ield+1.745
estic+1.724
Neg logit contributions
-2.317
-2.001
Islam-1.914
poll-1.909
REL-1.900
TokenTom
Token ID13787
Feature activation-7.93e+00

Pos logit contributions
acht+0.524
 Parenthood+0.440
uscript+0.435
ield+0.430
estic+0.424
Neg logit contributions
-0.476
-0.406
poll-0.386
Islam-0.385
REL-0.381
Token Cruise
Token ID29147
Feature activation+1.52e+00

Pos logit contributions
acht+6.949
 Parenthood+5.721
ield+5.618
uscript+5.596
estic+5.577
Neg logit contributions
-6.818
-5.880
Islam-5.684
REL-5.612
poll-5.542
Token Book
Token ID4897
Feature activation+4.36e-01

Pos logit contributions
+1.315
+1.127
poll+1.087
Islam+1.083
REL+1.063
Neg logit contributions
acht-1.373
 Parenthood-1.133
uscript-1.133
ield-1.125
estic-1.106
Token-
Token ID12
Feature activation-6.54e-01

Pos logit contributions
+0.367
+0.313
poll+0.299
Islam+0.299
REL+0.295
Neg logit contributions
acht-0.404
 Parenthood-0.339
uscript-0.336
ield-0.332
estic-0.328
TokenM
Token ID44
Feature activation-1.87e+00

Pos logit contributions
acht+0.603
 Parenthood+0.506
uscript+0.500
ield+0.495
estic+0.488
Neg logit contributions
-0.553
-0.472
poll-0.448
Islam-0.448
REL-0.443
Tokenunch
Token ID3316
Feature activation-2.33e+00

Pos logit contributions
acht+1.624
 Parenthood+1.329
uscript+1.324
ield+1.310
estic+1.299
Neg logit contributions
-1.694
-1.463
poll-1.392
Islam-1.391
REL-1.370
Token
Token ID198
Feature activation-8.79e-01

Pos logit contributions
acht+0.444
 Parenthood+0.376
uscript+0.373
ield+0.371
estic+0.365
Neg logit contributions
-0.351
-0.294
Islam-0.280
poll-0.278
REL-0.275
Token
Token ID198
Feature activation-1.06e+00

Pos logit contributions
acht+0.831
 Parenthood+0.701
ield+0.690
uscript+0.680
estic+0.676
Neg logit contributions
-0.724
-0.609
Islam-0.573
REL-0.569
poll-0.568
Token5
Token ID20
Feature activation-8.73e-01

Pos logit contributions
acht+1.003
 Parenthood+0.840
uscript+0.837
ield+0.830
estic+0.817
Neg logit contributions
-0.857
-0.729
Islam-0.692
poll-0.690
REL-0.681
Token.
Token ID13
Feature activation-1.75e+00

Pos logit contributions
acht+0.686
 Parenthood+0.558
ield+0.544
uscript+0.543
estic+0.532
Neg logit contributions
-0.858
-0.748
Islam-0.716
poll-0.714
REL-0.709
Token Crystal
Token ID12969
Feature activation-8.51e-02

Pos logit contributions
acht+1.460
 Parenthood+1.208
uscript+1.183
ield+1.168
estic+1.154
Neg logit contributions
-1.626
-1.407
Islam-1.354
poll-1.351
REL-1.338
Token Emb
Token ID13302
Feature activation-7.92e+00

Pos logit contributions
acht+0.070
 Parenthood+0.057
uscript+0.057
ield+0.056
estic+0.055
Neg logit contributions
-0.080
-0.070
poll-0.067
Islam-0.067
REL-0.066
Tokenry
Token ID563
Feature activation-1.29e+00

Pos logit contributions
acht+4.219
ield+3.107
 Parenthood+2.999
estic+2.933
uscript+2.925
Neg logit contributions
-9.809
-8.508
Islam-8.252
REL-8.195
poll-8.103
Tokeno
Token ID78
Feature activation+6.52e-01

Pos logit contributions
acht+1.236
 Parenthood+1.034
uscript+1.022
ield+1.018
estic+1.008
Neg logit contributions
-1.062
-0.896
Islam-0.854
poll-0.851
REL-0.849
Token 04
Token ID8702
Feature activation-2.34e-01

Pos logit contributions
+0.644
+0.565
poll+0.546
Islam+0.545
REL+0.539
Neg logit contributions
acht-0.506
 Parenthood-0.406
uscript-0.404
ield-0.399
estic-0.391
Token:
Token ID25
Feature activation-1.40e+00

Pos logit contributions
acht+0.181
 Parenthood+0.146
uscript+0.143
ield+0.142
estic+0.139
Neg logit contributions
-0.233
-0.203
Islam-0.195
poll-0.195
REL-0.194
Token30
Token ID1270
Feature activation+3.83e+00

Pos logit contributions
acht+1.322
 Parenthood+1.116
ield+1.095
uscript+1.094
estic+1.078
Neg logit contributions
-1.139
-0.965
Islam-0.908
poll-0.899
REL-0.898
Token:
Token ID25
Feature activation-1.39e+00

Pos logit contributions
+1.536
+1.341
poll+1.292
Islam+1.291
REL+1.274
Neg logit contributions
acht-1.274
 Parenthood-1.032
uscript-1.027
ield-1.010
estic-0.996
Token51
Token ID4349
Feature activation-4.06e-02

Pos logit contributions
acht+1.340
 Parenthood+1.136
ield+1.114
uscript+1.112
estic+1.097
Neg logit contributions
-1.113
-0.941
Islam-0.884
poll-0.874
REL-0.874
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
acht+0.041
 Parenthood+0.034
uscript+0.034
ield+0.034
estic+0.033
Neg logit contributions
-0.031
-0.026
Islam-0.025
poll-0.025
REL-0.025
Token
Token ID198
Feature activation-1.19e+00

Pos logit contributions
acht+0.991
 Parenthood+0.837
ield+0.824
uscript+0.810
estic+0.805
Neg logit contributions
-0.872
-0.733
Islam-0.690
REL-0.685
poll-0.682
TokenCrystal
Token ID43752
Feature activation+3.50e-01

Pos logit contributions
acht+1.046
 Parenthood+0.860
uscript+0.859
ield+0.853
estic+0.831
Neg logit contributions
-1.059
-0.909
Islam-0.867
poll-0.862
REL-0.852
Token Emb
Token ID13302
Feature activation-7.92e+00

Pos logit contributions
+0.319
+0.276
poll+0.265
Islam+0.264
REL+0.261
Neg logit contributions
acht-0.300
 Parenthood-0.247
uscript-0.245
ield-0.242
estic-0.239
Tokenry
Token ID563
Feature activation-1.52e+00

Pos logit contributions
acht+4.144
ield+3.072
 Parenthood+2.970
estic+2.882
uscript+2.879
Neg logit contributions
-9.823
-8.516
Islam-8.277
REL-8.222
poll-8.106
Tokeno
Token ID78
Feature activation+5.78e-01

Pos logit contributions
acht+1.428
 Parenthood+1.187
ield+1.174
uscript+1.169
estic+1.159
Neg logit contributions
-1.271
-1.074
Islam-1.021
REL-1.020
poll-1.016
Token by
Token ID416
Feature activation+1.32e-01

Pos logit contributions
+0.515
+0.445
poll+0.428
Islam+0.426
REL+0.422
Neg logit contributions
acht-0.503
 Parenthood-0.416
uscript-0.413
ield-0.407
estic-0.402
Token Sing
Token ID5573
Feature activation-3.99e+00

Pos logit contributions
+0.119
+0.102
poll+0.098
Islam+0.098
REL+0.097
Neg logit contributions
acht-0.115
 Parenthood-0.095
uscript-0.094
ield-0.093
estic-0.092
Token,
Token ID11
Feature activation-6.67e-01

Pos logit contributions
acht+3.254
 Parenthood+2.645
uscript+2.616
ield+2.600
estic+2.529
Neg logit contributions
-3.766
-3.279
poll-3.139
Islam-3.130
REL-3.124
Token of
Token ID286
Feature activation+8.56e-01

Pos logit contributions
+1.608
+1.351
poll+1.279
Islam+1.277
REL+1.264
Neg logit contributions
acht-2.133
 Parenthood-1.827
uscript-1.805
ield-1.786
estic-1.765
Token inquiry
Token ID12069
Feature activation+2.40e+00

Pos logit contributions
+0.551
+0.443
Islam+0.416
poll+0.414
REL+0.407
Neg logit contributions
acht-0.965
 Parenthood-0.835
uscript-0.830
ield-0.823
estic-0.815
Token to
Token ID284
Feature activation-5.01e-01

Pos logit contributions
+1.990
+1.697
poll+1.616
Islam+1.605
REL+1.595
Neg logit contributions
acht-2.240
 Parenthood-1.885
uscript-1.875
ield-1.850
estic-1.829
Token investigate
Token ID9161
Feature activation+6.50e-01

Pos logit contributions
acht+0.469
 Parenthood+0.394
uscript+0.390
ield+0.386
estic+0.381
Neg logit contributions
-0.418
-0.355
Islam-0.340
poll-0.339
REL-0.335
Token this
Token ID428
Feature activation-1.67e+00

Pos logit contributions
+0.536
+0.455
poll+0.434
Islam+0.433
REL+0.429
Neg logit contributions
acht-0.614
 Parenthood-0.516
uscript-0.513
ield-0.507
estic-0.500
Token mish
Token ID29406
Feature activation-7.86e+00

Pos logit contributions
acht+1.684
 Parenthood+1.433
uscript+1.421
ield+1.409
estic+1.391
Neg logit contributions
-1.272
-1.062
Islam-1.010
poll-1.008
REL-0.994
Tokenap
Token ID499
Feature activation-1.59e+00

Pos logit contributions
acht+6.045
ield+4.792
uscript+4.720
estic+4.592
 Parenthood+4.585
Neg logit contributions
-7.926
-6.893
Islam-6.604
poll-6.524
REL-6.517
Token.
Token ID13
Feature activation+7.94e-02

Pos logit contributions
acht+1.357
 Parenthood+1.117
uscript+1.107
ield+1.093
estic+1.079
Neg logit contributions
-1.449
-1.251
Islam-1.202
poll-1.200
REL-1.186
Token The
Token ID383
Feature activation-1.16e-01

Pos logit contributions
+0.073
+0.063
Islam+0.060
poll+0.060
REL+0.060
Neg logit contributions
acht-0.068
 Parenthood-0.056
uscript-0.055
ield-0.054
estic-0.054
Token March
Token ID2805
Feature activation+2.40e+00

Pos logit contributions
acht+0.112
 Parenthood+0.095
uscript+0.094
ield+0.093
estic+0.092
Neg logit contributions
-0.094
-0.079
Islam-0.075
poll-0.075
REL-0.074
Token launch
Token ID4219
Feature activation+5.69e+00

Pos logit contributions
+2.164
+1.875
poll+1.801
Islam+1.789
REL+1.765
Neg logit contributions
acht-2.060
uscript-1.699
 Parenthood-1.699
ield-1.665
assium-1.645
Token/
Token ID14
Feature activation+8.18e-01

Pos logit contributions
acht+2.312
ield+1.852
 Parenthood+1.843
uscript+1.827
estic+1.822
Neg logit contributions
-2.775
-2.396
Islam-2.329
REL-2.313
poll-2.312
Token
Token ID198
Feature activation+3.43e-01

Pos logit contributions
+0.633
+0.532
Islam+0.506
poll+0.504
REL+0.497
Neg logit contributions
acht-0.815
 Parenthood-0.691
uscript-0.686
ield-0.679
estic-0.671
Token
Token ID198
Feature activation+8.18e-02

Pos logit contributions
+0.275
+0.231
Islam+0.218
poll+0.217
REL+0.216
Neg logit contributions
acht-0.333
 Parenthood-0.281
ield-0.277
uscript-0.275
estic-0.272
Token"
Token ID1
Feature activation+1.84e-01

Pos logit contributions
+0.068
+0.058
Islam+0.056
poll+0.056
REL+0.055
Neg logit contributions
acht-0.076
 Parenthood-0.064
uscript-0.063
ield-0.063
estic-0.062
TokenCrystal
Token ID43752
Feature activation+1.00e+00

Pos logit contributions
+0.157
+0.134
Islam+0.128
poll+0.128
REL+0.126
Neg logit contributions
acht-0.169
 Parenthood-0.141
uscript-0.140
ield-0.138
estic-0.136
Token Emb
Token ID13302
Feature activation-7.84e+00

Pos logit contributions
+0.907
+0.784
poll+0.751
Islam+0.751
REL+0.739
Neg logit contributions
acht-0.859
 Parenthood-0.710
uscript-0.705
ield-0.695
estic-0.688
Tokenry
Token ID563
Feature activation-9.47e-01

Pos logit contributions
acht+4.216
ield+3.140
 Parenthood+3.000
uscript+2.951
estic+2.950
Neg logit contributions
-9.701
-8.459
Islam-8.099
REL-8.095
poll-7.978
Tokeno
Token ID78
Feature activation+8.59e-01

Pos logit contributions
acht+0.902
 Parenthood+0.752
uscript+0.745
ield+0.743
estic+0.734
Neg logit contributions
-0.781
-0.660
poll-0.627
Islam-0.626
REL-0.626
Token lives
Token ID3160
Feature activation-2.31e+00

Pos logit contributions
+0.726
+0.620
Islam+0.592
poll+0.590
REL+0.582
Neg logit contributions
acht-0.792
 Parenthood-0.663
uscript-0.658
ield-0.650
estic-0.645
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
acht+2.236
 Parenthood+1.886
uscript+1.869
ield+1.849
estic+1.824
Neg logit contributions
-1.846
-1.551
poll-1.488
Islam-1.478
REL-1.468
Token a
Token ID257
Feature activation+4.39e-01

Pos logit contributions
acht+0.179
 Parenthood+0.151
uscript+0.150
ield+0.149
estic+0.147
Neg logit contributions
-0.145
-0.122
Islam-0.116
poll-0.116
REL-0.115
Token the
Token ID262
Feature activation-4.58e-01

Pos logit contributions
acht+0.219
 Parenthood+0.186
uscript+0.184
ield+0.181
estic+0.180
Neg logit contributions
-0.181
-0.153
Islam-0.145
poll-0.145
REL-0.143
Token development
Token ID2478
Feature activation+1.34e+00

Pos logit contributions
acht+0.425
 Parenthood+0.358
uscript+0.354
ield+0.350
estic+0.345
Neg logit contributions
-0.385
-0.328
Islam-0.313
poll-0.313
REL-0.309
Token and
Token ID290
Feature activation-6.23e-01

Pos logit contributions
+0.963
+0.796
poll+0.753
Islam+0.752
REL+0.739
Neg logit contributions
acht-1.413
 Parenthood-1.210
uscript-1.201
ield-1.190
estic-1.177
Token support
Token ID1104
Feature activation+3.12e+00

Pos logit contributions
acht+0.661
 Parenthood+0.569
uscript+0.563
ield+0.560
estic+0.554
Neg logit contributions
-0.444
-0.364
poll-0.344
Islam-0.344
REL-0.338
Token for
Token ID329
Feature activation-4.42e-01

Pos logit contributions
+2.139
+1.755
Islam+1.657
poll+1.654
REL+1.626
Neg logit contributions
acht-3.362
 Parenthood-2.895
uscript-2.880
ield-2.847
estic-2.815
Token Koh
Token ID24754
Feature activation-7.83e+00

Pos logit contributions
acht+0.414
 Parenthood+0.349
uscript+0.345
ield+0.341
estic+0.337
Neg logit contributions
-0.368
-0.313
Islam-0.299
poll-0.299
REL-0.295
Tokena
Token ID64
Feature activation+1.48e+00

Pos logit contributions
acht+5.956
 Parenthood+4.724
ield+4.693
uscript+4.675
estic+4.611
Neg logit contributions
-7.712
-6.778
poll-6.353
REL-6.346
Islam-6.344
Token,
Token ID11
Feature activation+7.34e-02

Pos logit contributions
+1.347
+1.164
Islam+1.125
poll+1.113
REL+1.105
Neg logit contributions
acht-1.260
 Parenthood-1.035
uscript-1.033
ield-1.015
estic-1.005
Token recently
Token ID2904
Feature activation+4.86e-01

Pos logit contributions
+0.063
+0.053
Islam+0.051
poll+0.051
REL+0.050
Neg logit contributions
acht-0.067
 Parenthood-0.056
uscript-0.056
ield-0.055
estic-0.054
Token formed
Token ID7042
Feature activation+6.26e-01

Pos logit contributions
+0.406
+0.345
Islam+0.330
poll+0.330
REL+0.325
Neg logit contributions
acht-0.453
 Parenthood-0.380
uscript-0.377
ield-0.373
estic-0.368
Token an
Token ID281
Feature activation+9.44e-01

Pos logit contributions
+0.498
+0.421
Islam+0.400
poll+0.400
REL+0.395
Neg logit contributions
acht-0.609
 Parenthood-0.514
uscript-0.511
ield-0.505
estic-0.499
Token Prec
Token ID28737
Feature activation-3.24e+00

Pos logit contributions
acht+0.425
 Parenthood+0.348
uscript+0.345
ield+0.341
estic+0.336
Neg logit contributions
-0.472
-0.408
Islam-0.392
poll-0.392
REL-0.388
Tokenise
Token ID786
Feature activation-1.79e+00

Pos logit contributions
acht+2.776
 Parenthood+2.252
uscript+2.250
ield+2.236
estic+2.198
Neg logit contributions
-2.993
-2.596
Islam-2.475
poll-2.456
REL-2.452
Token
Token ID198
Feature activation-6.54e-01

Pos logit contributions
acht+1.674
 Parenthood+1.407
uscript+1.386
ield+1.379
estic+1.358
Neg logit contributions
-1.494
-1.275
Islam-1.218
poll-1.216
REL-1.196
Token
Token ID198
Feature activation-8.65e-01

Pos logit contributions
acht+0.620
 Parenthood+0.525
ield+0.516
uscript+0.509
estic+0.505
Neg logit contributions
-0.537
-0.451
Islam-0.425
REL-0.421
poll-0.421
Token-
Token ID12
Feature activation-1.18e-01

Pos logit contributions
acht+0.864
 Parenthood+0.737
uscript+0.726
ield+0.725
estic+0.711
Neg logit contributions
-0.659
-0.551
poll-0.521
Islam-0.519
REL-0.509
Token Unt
Token ID26970
Feature activation-7.81e+00

Pos logit contributions
acht+0.098
 Parenthood+0.080
uscript+0.080
ield+0.079
estic+0.077
Neg logit contributions
-0.111
-0.096
Islam-0.092
poll-0.092
REL-0.091
Tokenet
Token ID316
Feature activation+6.85e-01

Pos logit contributions
acht+6.913
estic+5.697
ield+5.685
uscript+5.607
ocument+5.563
Neg logit contributions
-6.870
-5.958
Islam-5.483
REL-5.379
poll-5.315
Tokenhered
Token ID6083
Feature activation-4.38e+00

Pos logit contributions
+0.634
+0.549
poll+0.529
Islam+0.527
REL+0.526
Neg logit contributions
acht-0.573
 Parenthood-0.473
uscript-0.470
ield-0.459
ocument-0.453
Token,
Token ID11
Feature activation-8.16e-01

Pos logit contributions
acht+3.630
 Parenthood+3.036
uscript+2.934
ield+2.919
estic+2.881
Neg logit contributions
-4.001
-3.490
poll-3.361
Islam-3.350
REL-3.273
Token Dist
Token ID4307
Feature activation-2.72e+00

Pos logit contributions
acht+0.688
 Parenthood+0.566
uscript+0.560
ield+0.554
estic+0.545
Neg logit contributions
-0.756
-0.655
Islam-0.628
poll-0.628
REL-0.620
Tokenant
Token ID415
Feature activation-1.49e+00

Pos logit contributions
acht+2.165
 Parenthood+1.736
ield+1.728
uscript+1.717
estic+1.703
Neg logit contributions
-2.660
-2.320
Islam-2.213
poll-2.199
REL-2.188
Token architecture
Token ID10959
Feature activation-1.68e+00

Pos logit contributions
acht+2.265
 Parenthood+1.930
uscript+1.899
ield+1.890
estic+1.856
Neg logit contributions
-1.856
-1.562
Islam-1.496
poll-1.486
REL-1.468
Token,
Token ID11
Feature activation-4.27e-02

Pos logit contributions
acht+1.659
 Parenthood+1.406
uscript+1.395
ield+1.383
ocument+1.364
Neg logit contributions
-1.311
-1.103
poll-1.052
Islam-1.044
REL-1.028
Token are
Token ID389
Feature activation+2.06e+00

Pos logit contributions
acht+0.042
 Parenthood+0.035
uscript+0.035
ield+0.035
estic+0.034
Neg logit contributions
-0.034
-0.028
Islam-0.027
poll-0.027
REL-0.027
Token deployed
Token ID12380
Feature activation-1.51e+00

Pos logit contributions
+1.680
+1.429
poll+1.357
Islam+1.356
REL+1.349
Neg logit contributions
acht-1.951
 Parenthood-1.647
uscript-1.628
ield-1.601
assium-1.589
Token through
Token ID832
Feature activation-5.82e-01

Pos logit contributions
acht+1.362
 Parenthood+1.136
uscript+1.125
ield+1.114
estic+1.098
Neg logit contributions
-1.307
-1.118
Islam-1.070
poll-1.069
REL-1.056
Token multit
Token ID41785
Feature activation-7.70e+00

Pos logit contributions
acht+0.560
 Parenthood+0.473
uscript+0.469
ield+0.465
estic+0.458
Neg logit contributions
-0.470
-0.397
Islam-0.378
poll-0.377
REL-0.372
Tokenen
Token ID268
Feature activation+1.88e+00

Pos logit contributions
acht+5.968
ield+4.899
uscript+4.872
estic+4.744
assium+4.697
Neg logit contributions
-7.546
-6.501
Islam-6.244
poll-6.117
REL-6.046
Tokenant
Token ID415
Feature activation-8.59e-01

Pos logit contributions
+1.478
+1.253
poll+1.188
Islam+1.185
REL+1.164
Neg logit contributions
acht-1.832
 Parenthood-1.559
uscript-1.541
ield-1.517
estic-1.508
Token S
Token ID311
Feature activation-6.56e-01

Pos logit contributions
acht+0.873
 Parenthood+0.745
uscript+0.738
ield+0.733
estic+0.722
Neg logit contributions
-0.647
-0.539
Islam-0.513
poll-0.511
REL-0.504
Tokenaa
Token ID7252
Feature activation-6.52e-02

Pos logit contributions
acht+0.640
 Parenthood+0.539
uscript+0.536
ield+0.533
estic+0.525
Neg logit contributions
-0.522
-0.440
Islam-0.419
poll-0.418
REL-0.411
TokenS
Token ID50
Feature activation-2.24e-01

Pos logit contributions
acht+0.060
 Parenthood+0.050
uscript+0.049
ield+0.049
estic+0.048
Neg logit contributions
-0.056
-0.048
Islam-0.045
poll-0.045
REL-0.045
TokenBrain
Token ID44687
Feature activation-9.63e-01

Pos logit contributions
acht+0.477
 Parenthood+0.399
uscript+0.396
ield+0.392
estic+0.386
Neg logit contributions
-0.436
-0.372
poll-0.355
Islam-0.355
REL-0.350
Tokeniac
Token ID9607
Feature activation+7.23e-01

Pos logit contributions
acht+0.948
 Parenthood+0.803
uscript+0.796
ield+0.787
estic+0.777
Neg logit contributions
-0.756
-0.636
poll-0.606
Islam-0.605
REL-0.596
Token gives
Token ID3607
Feature activation-9.42e-01

Pos logit contributions
+0.644
+0.555
Islam+0.530
poll+0.530
REL+0.523
Neg logit contributions
acht-0.634
 Parenthood-0.526
uscript-0.521
ield-0.515
estic-0.509
Token The
Token ID383
Feature activation-1.61e+00

Pos logit contributions
acht+0.937
 Parenthood+0.797
uscript+0.790
ield+0.780
estic+0.771
Neg logit contributions
-0.726
-0.609
Islam-0.581
poll-0.580
REL-0.572
Token Joker
Token ID23582
Feature activation-1.49e+00

Pos logit contributions
acht+1.144
 Parenthood+0.905
uscript+0.891
ield+0.879
estic+0.861
Neg logit contributions
-1.710
-1.509
Islam-1.457
poll-1.456
REL-1.444
Token Imper
Token ID28185
Feature activation-7.70e+00

Pos logit contributions
acht+1.393
 Parenthood+1.172
uscript+1.158
ield+1.146
estic+1.131
Neg logit contributions
-1.238
-1.052
poll-1.006
Islam-1.006
REL-0.993
Tokenvious
Token ID1442
Feature activation-3.63e+00

Pos logit contributions
acht+6.945
 Parenthood+5.795
ield+5.742
uscript+5.688
estic+5.651
Neg logit contributions
-6.341
-5.367
poll-5.203
Islam-5.167
REL-5.146
Token so
Token ID523
Feature activation-2.17e+00

Pos logit contributions
acht+3.187
 Parenthood+2.687
uscript+2.631
ield+2.617
estic+2.576
Neg logit contributions
-3.150
-2.700
poll-2.607
Islam-2.605
REL-2.572
Token that
Token ID326
Feature activation-1.63e-03

Pos logit contributions
acht+2.018
 Parenthood+1.698
uscript+1.676
ield+1.671
estic+1.639
Neg logit contributions
-1.801
-1.531
Islam-1.470
poll-1.465
REL-1.453
Token if
Token ID611
Feature activation+1.66e+00

Pos logit contributions
acht+0.002
 Parenthood+0.001
uscript+0.001
ield+0.001
estic+0.001
Neg logit contributions
-0.001
-0.001
Islam-0.001
poll-0.001
REL-0.001
Token they
Token ID484
Feature activation+1.79e+00

Pos logit contributions
+1.255
+1.050
poll+0.994
Islam+0.994
REL+0.979
Neg logit contributions
acht-1.683
 Parenthood-1.429
uscript-1.423
ield-1.406
estic-1.391
Token at
Token ID379
Feature activation-2.08e+00

Pos logit contributions
acht+1.879
 Parenthood+1.555
uscript+1.539
ield+1.528
estic+1.503
Neg logit contributions
-1.862
-1.597
Islam-1.532
poll-1.531
REL-1.513
Token the
Token ID262
Feature activation-2.68e-01

Pos logit contributions
acht+2.053
 Parenthood+1.735
uscript+1.714
ield+1.704
estic+1.686
Neg logit contributions
-1.626
-1.362
Islam-1.302
poll-1.289
REL-1.280
Token Paris
Token ID6342
Feature activation+2.83e-01

Pos logit contributions
acht+0.267
 Parenthood+0.227
uscript+0.225
ield+0.224
estic+0.221
Neg logit contributions
-0.206
-0.173
Islam-0.164
poll-0.163
REL-0.161
Token meeting
Token ID3249
Feature activation+6.93e-02

Pos logit contributions
+0.172
+0.136
Islam+0.127
poll+0.127
REL+0.124
Neg logit contributions
acht-0.329
 Parenthood-0.287
uscript-0.284
ield-0.283
estic-0.281
Token,
Token ID11
Feature activation+5.30e-01

Pos logit contributions
+0.064
+0.055
Islam+0.053
poll+0.053
REL+0.052
Neg logit contributions
acht-0.059
 Parenthood-0.048
uscript-0.048
ield-0.047
estic-0.047
Token Fab
Token ID14236
Feature activation+5.81e+00

Pos logit contributions
+0.432
+0.366
Islam+0.348
poll+0.348
REL+0.344
Neg logit contributions
acht-0.506
 Parenthood-0.426
uscript-0.422
ield-0.419
estic-0.413
Tokenius
Token ID3754
Feature activation+3.92e-01

Pos logit contributions
+2.802
+2.161
poll+1.981
Islam+1.968
REL+1.868
Neg logit contributions
acht-7.251
 Parenthood-6.430
uscript-6.416
everal-6.349
ocument-6.302
Token said
Token ID531
Feature activation-4.36e-01

Pos logit contributions
+0.269
+0.220
Islam+0.207
poll+0.207
REL+0.204
Neg logit contributions
acht-0.425
 Parenthood-0.366
uscript-0.363
ield-0.360
estic-0.356
Token.
Token ID13
Feature activation+5.31e-01

Pos logit contributions
acht+0.353
 Parenthood+0.286
uscript+0.282
ield+0.281
estic+0.276
Neg logit contributions
-0.419
-0.365
poll-0.349
Islam-0.349
REL-0.346
Token
Token ID198
Feature activation+8.70e-01

Pos logit contributions
+0.422
+0.356
poll+0.338
Islam+0.338
REL+0.334
Neg logit contributions
acht-0.515
 Parenthood-0.437
uscript-0.431
ield-0.428
estic-0.422
Token
Token ID198
Feature activation+5.47e-01

Pos logit contributions
+0.683
+0.572
Islam+0.541
poll+0.539
REL+0.535
Neg logit contributions
acht-0.859
 Parenthood-0.730
uscript-0.718
ield-0.716
estic-0.705
Tokenia
Token ID544
Feature activation+3.13e-01

Pos logit contributions
+0.143
+0.121
poll+0.116
Islam+0.115
REL+0.114
Neg logit contributions
acht-0.171
 Parenthood-0.144
uscript-0.143
ield-0.142
estic-0.140
Token Bailey
Token ID20330
Feature activation-7.98e-01

Pos logit contributions
+0.270
+0.232
Islam+0.222
poll+0.221
REL+0.219
Neg logit contributions
acht-0.283
 Parenthood-0.236
uscript-0.235
ield-0.231
estic-0.228
Token,
Token ID11
Feature activation+1.84e-01

Pos logit contributions
acht+0.702
 Parenthood+0.582
uscript+0.575
ield+0.571
estic+0.561
Neg logit contributions
-0.710
-0.611
Islam-0.587
poll-0.585
REL-0.579
Token a
Token ID257
Feature activation+1.04e+00

Pos logit contributions
+0.154
+0.131
Islam+0.125
poll+0.125
REL+0.124
Neg logit contributions
acht-0.172
 Parenthood-0.144
uscript-0.143
ield-0.141
estic-0.139
Token Capitol
Token ID13241
Feature activation+1.34e+00

Pos logit contributions
+0.851
+0.723
poll+0.692
Islam+0.687
REL+0.678
Neg logit contributions
acht-0.983
 Parenthood-0.825
uscript-0.821
ield-0.812
estic-0.799
Token cafe
Token ID26725
Feature activation+5.85e+00

Pos logit contributions
+1.187
+1.021
Islam+0.978
poll+0.978
REL+0.966
Neg logit contributions
acht-1.177
 Parenthood-0.976
uscript-0.968
ield-0.957
estic-0.943
Token cash
Token ID5003
Feature activation+3.94e+00

Pos logit contributions
+4.904
+4.230
poll+3.964
Islam+3.942
REL+3.858
Neg logit contributions
acht-5.269
uscript-4.468
 Parenthood-4.441
assium-4.312
ield-4.299
Tokenier
Token ID959
Feature activation-7.23e-01

Pos logit contributions
+3.032
+2.544
poll+2.439
Islam+2.426
REL+2.382
Neg logit contributions
acht-3.904
 Parenthood-3.326
uscript-3.305
ield-3.246
estic-3.206
Token,
Token ID11
Feature activation+3.05e-01

Pos logit contributions
acht+0.625
 Parenthood+0.515
uscript+0.510
ield+0.505
estic+0.497
Neg logit contributions
-0.655
-0.564
Islam-0.542
poll-0.541
REL-0.536
Token as
Token ID355
Feature activation+4.75e-01

Pos logit contributions
+0.269
+0.231
poll+0.221
Islam+0.221
REL+0.218
Neg logit contributions
acht-0.271
 Parenthood-0.225
uscript-0.224
ield-0.221
estic-0.218
Token she
Token ID673
Feature activation+7.93e-01

Pos logit contributions
+0.388
+0.328
Islam+0.313
poll+0.311
REL+0.308
Neg logit contributions
acht-0.454
 Parenthood-0.384
uscript-0.380
ield-0.376
estic-0.372
Token director
Token ID3437
Feature activation+2.38e+00

Pos logit contributions
+1.128
+0.948
Islam+0.901
poll+0.901
REL+0.888
Neg logit contributions
acht-1.438
 Parenthood-1.218
uscript-1.210
ield-1.198
estic-1.183
Token Bryan
Token ID17857
Feature activation+1.88e+00

Pos logit contributions
+1.931
+1.635
Islam+1.557
poll+1.557
REL+1.535
Neg logit contributions
acht-2.281
 Parenthood-1.917
uscript-1.906
ield-1.887
estic-1.860
Token Singer
Token ID28755
Feature activation-5.27e-01

Pos logit contributions
+1.627
+1.394
Islam+1.333
poll+1.332
REL+1.316
Neg logit contributions
acht-1.694
 Parenthood-1.411
uscript-1.400
ield-1.384
estic-1.364
Token during
Token ID1141
Feature activation-3.05e+00

Pos logit contributions
acht+0.484
 Parenthood+0.405
uscript+0.401
ield+0.397
estic+0.391
Neg logit contributions
-0.449
-0.383
Islam-0.366
poll-0.366
REL-0.362
Token the
Token ID262
Feature activation-6.07e-02

Pos logit contributions
acht+2.917
 Parenthood+2.514
uscript+2.448
ield+2.429
estic+2.397
Neg logit contributions
-2.432
-2.039
Islam-1.969
poll-1.949
REL-1.920
Token press
Token ID1803
Feature activation+5.96e+00

Pos logit contributions
acht+0.058
 Parenthood+0.049
uscript+0.049
ield+0.048
estic+0.048
Neg logit contributions
-0.049
-0.041
Islam-0.040
poll-0.039
REL-0.039
Token junk
Token ID18556
Feature activation-2.49e+00

Pos logit contributions
+3.729
+3.051
poll+2.861
Islam+2.809
REL+2.766
Neg logit contributions
acht-6.652
 Parenthood-5.838
uscript-5.830
ield-5.696
assium-5.678
Tokenet
Token ID316
Feature activation+7.70e-01

Pos logit contributions
acht+1.975
uscript+1.571
 Parenthood+1.564
ield+1.561
estic+1.550
Neg logit contributions
-2.431
-2.107
Islam-2.051
REL-2.047
poll-2.009
Token,
Token ID837
Feature activation-1.10e-01

Pos logit contributions
+0.697
+0.602
Islam+0.577
poll+0.577
REL+0.570
Neg logit contributions
acht-0.665
 Parenthood-0.549
uscript-0.545
ield-0.537
estic-0.530
Token but
Token ID475
Feature activation+1.59e+00

Pos logit contributions
acht+0.103
 Parenthood+0.087
uscript+0.086
ield+0.085
estic+0.084
Neg logit contributions
-0.091
-0.077
Islam-0.074
poll-0.073
REL-0.072
Token ultimately
Token ID6165
Feature activation+1.58e+00

Pos logit contributions
+1.191
+0.997
poll+0.944
Islam+0.942
REL+0.929
Neg logit contributions
acht-1.618
 Parenthood-1.373
uscript-1.370
ield-1.356
estic-1.339
Tokenestablished
Token ID27718
Feature activation-5.13e-01

Pos logit contributions
+0.796
+0.670
poll+0.641
Islam+0.641
REL+0.627
Neg logit contributions
acht-0.985
 Parenthood-0.838
uscript-0.828
ield-0.819
estic-0.811
Token a
Token ID257
Feature activation+6.66e-01

Pos logit contributions
acht+0.527
 Parenthood+0.451
uscript+0.446
ield+0.443
estic+0.436
Neg logit contributions
-0.379
-0.316
poll-0.298
Islam-0.298
REL-0.295
Token siege
Token ID20690
Feature activation+7.33e+00

Pos logit contributions
+0.511
+0.429
poll+0.406
Islam+0.406
REL+0.401
Neg logit contributions
acht-0.668
 Parenthood-0.568
uscript-0.563
ield-0.558
estic-0.551
Token on
Token ID319
Feature activation+2.49e-01

Pos logit contributions
+5.556
+4.608
Islam+4.413
poll+4.352
zone+4.312
Neg logit contributions
acht-7.263
uscript-6.212
 Parenthood-6.155
estic-6.036
ield-5.999
Token the
Token ID262
Feature activation+9.86e-02

Pos logit contributions
+0.180
+0.150
Islam+0.141
poll+0.141
REL+0.139
Neg logit contributions
acht-0.259
 Parenthood-0.222
uscript-0.220
ield-0.218
estic-0.216
Token rebel
Token ID14034
Feature activation+5.71e+00

Pos logit contributions
+0.071
+0.059
poll+0.056
Islam+0.056
REL+0.055
Neg logit contributions
acht-0.103
 Parenthood-0.089
uscript-0.088
ield-0.087
estic-0.086
Token-
Token ID12
Feature activation+6.78e-01

Pos logit contributions
+3.635
+2.940
Islam+2.828
poll+2.727
REL+2.688
Neg logit contributions
acht-6.337
uscript-5.466
 Parenthood-5.459
ocument-5.371
ield-5.365
Tokenheld
Token ID10217
Feature activation+1.64e-01

Pos logit contributions
+0.454
+0.370
Islam+0.348
poll+0.347
REL+0.342
Neg logit contributions
acht-0.745
 Parenthood-0.643
uscript-0.639
ield-0.634
estic-0.626
Token portion
Token ID6903
Feature activation-2.26e+00

Pos logit contributions
+0.120
+0.100
Islam+0.095
poll+0.095
REL+0.093
Neg logit contributions
acht-0.169
 Parenthood-0.144
uscript-0.144
ield-0.142
estic-0.140
Token of
Token ID286
Feature activation+1.23e+00

Pos logit contributions
acht+2.305
 Parenthood+1.954
uscript+1.943
ield+1.930
ocument+1.903
Neg logit contributions
-1.659
-1.389
poll-1.327
Islam-1.303
REL-1.301
Token the
Token ID262
Feature activation+6.39e-02

Pos logit contributions
+0.890
+0.737
Islam+0.698
poll+0.696
REL+0.683
Neg logit contributions
acht-1.294
 Parenthood-1.108
uscript-1.102
ield-1.090
estic-1.079
Token seismic
Token ID37463
Feature activation+1.12e+00

Pos logit contributions
acht+1.584
 Parenthood+1.353
uscript+1.331
ield+1.319
estic+1.310
Neg logit contributions
-1.271
-1.061
Islam-1.008
poll-0.997
REL-0.992
Token testing
Token ID4856
Feature activation-4.91e-01

Pos logit contributions
+0.879
+0.742
poll+0.706
Islam+0.705
REL+0.695
Neg logit contributions
acht-1.101
 Parenthood-0.933
uscript-0.928
ield-0.915
estic-0.904
Token for
Token ID329
Feature activation-5.80e-01

Pos logit contributions
acht+0.460
 Parenthood+0.387
uscript+0.382
ield+0.379
estic+0.374
Neg logit contributions
-0.410
-0.349
Islam-0.332
poll-0.331
REL-0.328
Token oil
Token ID3056
Feature activation+2.06e+00

Pos logit contributions
acht+0.565
 Parenthood+0.478
uscript+0.473
ield+0.469
estic+0.463
Neg logit contributions
-0.461
-0.388
Islam-0.370
poll-0.368
REL-0.364
Token and
Token ID290
Feature activation-2.97e-02

Pos logit contributions
+1.699
+1.443
poll+1.380
Islam+1.379
REL+1.359
Neg logit contributions
acht-1.943
 Parenthood-1.636
uscript-1.626
ield-1.603
estic-1.583
Token gas
Token ID3623
Feature activation+5.75e+00

Pos logit contributions
acht+0.033
 Parenthood+0.028
uscript+0.028
ield+0.028
estic+0.027
Neg logit contributions
-0.020
-0.016
Islam-0.015
poll-0.015
REL-0.015
Token in
Token ID287
Feature activation+5.02e-01

Pos logit contributions
+4.169
+3.549
poll+3.457
Islam+3.382
REL+3.368
Neg logit contributions
acht-5.681
uscript-4.958
 Parenthood-4.875
ield-4.796
ocument-4.720
Token the
Token ID262
Feature activation+4.33e-01

Pos logit contributions
+0.383
+0.321
Islam+0.305
poll+0.304
REL+0.300
Neg logit contributions
acht-0.505
 Parenthood-0.429
uscript-0.426
ield-0.422
estic-0.417
Token north
Token ID5093
Feature activation-2.95e-01

Pos logit contributions
+0.337
+0.284
Islam+0.270
poll+0.269
REL+0.266
Neg logit contributions
acht-0.429
 Parenthood-0.364
uscript-0.361
ield-0.358
estic-0.353
Token but
Token ID475
Feature activation+1.49e+00

Pos logit contributions
acht+0.290
 Parenthood+0.242
uscript+0.241
ield+0.239
estic+0.236
Neg logit contributions
-0.233
-0.198
Islam-0.187
poll-0.186
REL-0.183
Token dismissing
Token ID37514
Feature activation+4.40e+00

Pos logit contributions
+1.064
+0.880
Islam+0.832
poll+0.831
REL+0.818
Neg logit contributions
acht-1.566
 Parenthood-1.342
uscript-1.334
ield-1.320
estic-1.305
Token ones
Token ID3392
Feature activation-2.33e+00

Pos logit contributions
acht+0.049
 Parenthood+0.042
uscript+0.041
ield+0.041
estic+0.040
Neg logit contributions
-0.041
-0.035
Islam-0.033
poll-0.033
REL-0.033
Token seen
Token ID1775
Feature activation-2.43e+00

Pos logit contributions
acht+2.198
 Parenthood+1.847
uscript+1.823
ield+1.811
estic+1.784
Neg logit contributions
-1.931
-1.640
Islam-1.572
poll-1.554
REL-1.544
Token in
Token ID287
Feature activation+2.58e-01

Pos logit contributions
acht+2.147
 Parenthood+1.788
uscript+1.758
ield+1.745
estic+1.721
Neg logit contributions
-2.139
-1.835
Islam-1.757
poll-1.746
REL-1.738
Token Wisconsin
Token ID9279
Feature activation-2.44e+00

Pos logit contributions
+0.208
+0.176
poll+0.168
Islam+0.168
REL+0.166
Neg logit contributions
acht-0.248
 Parenthood-0.209
uscript-0.207
ield-0.205
estic-0.203
Token.
Token ID13
Feature activation+6.06e-01

Pos logit contributions
acht+2.058
 Parenthood+1.692
uscript+1.671
ield+1.657
estic+1.627
Neg logit contributions
-2.260
-1.961
Islam-1.884
poll-1.870
REL-1.857
Token Court
Token ID3078
Feature activation+2.38e+00

Pos logit contributions
+0.533
+0.458
Islam+0.438
poll+0.438
REL+0.432
Neg logit contributions
acht-0.540
 Parenthood-0.448
uscript-0.445
ield-0.439
estic-0.433
Token rulings
Token ID31532
Feature activation-2.16e+00

Pos logit contributions
+1.765
+1.470
poll+1.407
Islam+1.387
REL+1.374
Neg logit contributions
acht-2.429
 Parenthood-2.074
uscript-2.058
ield-2.027
ocument-2.021
Token could
Token ID714
Feature activation-7.85e-01

Pos logit contributions
acht+2.042
 Parenthood+1.712
uscript+1.686
ield+1.679
estic+1.661
Neg logit contributions
-1.780
-1.515
Islam-1.442
poll-1.433
REL-1.418
Token be
Token ID307
Feature activation+2.37e+00

Pos logit contributions
acht+0.762
 Parenthood+0.641
ield+0.634
uscript+0.634
estic+0.627
Neg logit contributions
-0.627
-0.528
Islam-0.503
poll-0.501
REL-0.496
Token affected
Token ID5676
Feature activation-5.51e+00

Pos logit contributions
+1.866
+1.582
poll+1.516
Islam+1.506
REL+1.486
Neg logit contributions
acht-2.302
 Parenthood-1.953
uscript-1.939
ield-1.912
estic-1.897
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
acht+4.705
 Parenthood+3.932
uscript+3.820
ield+3.817
estic+3.739
Neg logit contributions
-4.870
-4.207
Islam-4.037
poll-4.009
REL-3.989
Token the
Token ID262
Feature activation-4.57e-01

Pos logit contributions
acht+0.741
 Parenthood+0.613
uscript+0.607
ield+0.600
estic+0.592
Neg logit contributions
-0.771
-0.665
Islam-0.637
poll-0.637
REL-0.629
Token Conservatives
Token ID17897
Feature activation-2.46e+00

Pos logit contributions
acht+0.528
 Parenthood+0.460
uscript+0.456
ield+0.452
estic+0.448
Neg logit contributions
-0.280
-0.224
Islam-0.209
poll-0.208
REL-0.204
Token made
Token ID925
Feature activation-2.74e+00

Pos logit contributions
acht+2.391
 Parenthood+2.013
uscript+1.998
ield+1.981
estic+1.963
Neg logit contributions
-1.944
-1.642
Islam-1.565
poll-1.555
REL-1.540
Token
Token ID851
Feature activation-1.14e+00

Pos logit contributions
acht+2.368
 Parenthood+1.965
uscript+1.927
ield+1.913
estic+1.897
Neg logit contributions
-2.460
-2.122
poll-2.031
Islam-2.030
REL-2.001
Token with
Token ID351
Feature activation-6.81e-01

Pos logit contributions
acht+1.132
 Parenthood+0.963
uscript+0.952
ield+0.943
estic+0.934
Neg logit contributions
-0.884
-0.743
Islam-0.704
poll-0.702
REL-0.694
Token some
Token ID617
Feature activation+1.54e+00

Pos logit contributions
acht+0.663
 Parenthood+0.563
uscript+0.557
ield+0.551
estic+0.545
Neg logit contributions
-0.539
-0.455
Islam-0.434
poll-0.431
REL-0.427
Token improvements
Token ID8561
Feature activation-2.87e+00

Pos logit contributions
+1.202
+1.012
poll+0.963
Islam+0.960
REL+0.948
Neg logit contributions
acht-1.522
 Parenthood-1.289
uscript-1.281
ield-1.265
estic-1.249
Token.
Token ID13
Feature activation+4.62e-01

Pos logit contributions
acht+2.455
 Parenthood+2.036
uscript+2.010
ield+1.988
estic+1.979
Neg logit contributions
-2.590
-2.244
poll-2.142
Islam-2.142
REL-2.125
Token Treasury
Token ID13419
Feature activation-1.75e+00

Pos logit contributions
+0.377
+0.320
Islam+0.305
poll+0.304
REL+0.300
Neg logit contributions
acht-0.438
 Parenthood-0.371
uscript-0.365
ield-0.362
estic-0.357
Token Board
Token ID5926
Feature activation+7.29e-01

Pos logit contributions
acht+1.335
 Parenthood+1.082
ield+1.051
uscript+1.049
estic+1.032
Neg logit contributions
-1.758
-1.527
Islam-1.485
poll-1.476
REL-1.456
Token president
Token ID1893
Feature activation-2.74e-01

Pos logit contributions
+0.593
+0.501
Islam+0.480
poll+0.480
REL+0.472
Neg logit contributions
acht-0.695
 Parenthood-0.589
uscript-0.581
ield-0.576
estic-0.569
Tokenve
Token ID303
Feature activation-2.60e-01

Pos logit contributions
+0.461
+0.361
poll+0.339
Islam+0.336
REL+0.331
Neg logit contributions
acht-0.904
uscript-0.795
 Parenthood-0.793
assium-0.775
estic-0.772
Tokenlled
Token ID3353
Feature activation+5.40e-01

Pos logit contributions
acht+0.270
 Parenthood+0.231
uscript+0.231
ield+0.224
estic+0.224
Neg logit contributions
-0.189
-0.156
Islam-0.149
poll-0.149
REL-0.146
Token
Token ID198
Feature activation-7.05e-02

Pos logit contributions
+0.480
+0.413
Islam+0.395
poll+0.395
REL+0.391
Neg logit contributions
acht-0.475
 Parenthood-0.393
uscript-0.392
ield-0.387
estic-0.381
Token
Token ID198
Feature activation-3.50e-01

Pos logit contributions
acht+0.068
 Parenthood+0.058
ield+0.057
uscript+0.056
estic+0.056
Neg logit contributions
-0.057
-0.048
Islam-0.045
poll-0.045
REL-0.044
TokenFive
Token ID20029
Feature activation-2.46e+00

Pos logit contributions
acht+0.330
 Parenthood+0.276
uscript+0.274
ield+0.272
estic+0.268
Neg logit contributions
-0.290
-0.246
poll-0.234
Islam-0.234
REL-0.231
Token days
Token ID1528
Feature activation+1.14e+00

Pos logit contributions
acht+2.368
 Parenthood+2.007
uscript+1.980
ield+1.974
estic+1.935
Neg logit contributions
-1.955
-1.654
Islam-1.583
poll-1.580
REL-1.558
Token later
Token ID1568
Feature activation+9.32e-01

Pos logit contributions
+0.948
+0.808
Islam+0.773
poll+0.773
REL+0.762
Neg logit contributions
acht-1.057
 Parenthood-0.886
uscript-0.881
ield-0.871
estic-0.861
Token,
Token ID11
Feature activation+1.46e-01

Pos logit contributions
+0.824
+0.709
Islam+0.679
poll+0.679
REL+0.672
Neg logit contributions
acht-0.820
 Parenthood-0.681
uscript-0.678
ield-0.670
estic-0.660
Token bed
Token ID3996
Feature activation+8.24e-01

Pos logit contributions
+0.120
+0.102
poll+0.097
Islam+0.097
REL+0.096
Neg logit contributions
acht-0.138
 Parenthood-0.116
uscript-0.116
ield-0.114
estic-0.113
Tokenr
Token ID81
Feature activation+2.28e+00

Pos logit contributions
+0.756
+0.654
Islam+0.627
poll+0.627
REL+0.620
Neg logit contributions
acht-0.702
 Parenthood-0.578
uscript-0.572
ield-0.565
estic-0.557
Tokenagg
Token ID9460
Feature activation+3.67e+00

Pos logit contributions
+1.327
+1.025
poll+0.977
Islam+0.971
REL+0.949
Neg logit contributions
acht-2.684
 Parenthood-2.365
uscript-2.355
ield-2.313
assium-2.298
Tokenatt
Token ID1078
Feature activation-2.56e+00

Pos logit contributions
+2.823
+2.361
poll+2.256
Islam+2.249
REL+2.183
Neg logit contributions
acht-3.907
 Parenthood-3.342
uscript-3.320
ield-3.252
estic-3.230
Tokenacked
Token ID6021
Feature activation-2.43e+00

Pos logit contributions
acht+2.070
 Parenthood+1.663
uscript+1.663
ield+1.650
estic+1.620
Neg logit contributions
-2.469
-2.152
Islam-2.060
poll-2.052
REL-2.041
Token and
Token ID290
Feature activation-6.47e-01

Pos logit contributions
acht+2.250
 Parenthood+1.893
uscript+1.863
ield+1.847
estic+1.821
Neg logit contributions
-2.039
-1.735
poll-1.653
Islam-1.650
REL-1.636
Token by
Token ID416
Feature activation+1.01e+00

Pos logit contributions
acht+0.626
 Parenthood+0.528
uscript+0.524
ield+0.519
estic+0.512
Neg logit contributions
-0.519
-0.439
Islam-0.418
poll-0.417
REL-0.412
Token 1
Token ID352
Feature activation-5.45e-01

Pos logit contributions
+0.916
+0.794
poll+0.764
Islam+0.761
REL+0.749
Neg logit contributions
acht-0.860
 Parenthood-0.710
uscript-0.707
ield-0.700
estic-0.687
Token August
Token ID2932
Feature activation+1.68e+00

Pos logit contributions
acht+0.504
 Parenthood+0.423
uscript+0.419
ield+0.415
estic+0.408
Neg logit contributions
-0.460
-0.392
Islam-0.374
poll-0.374
REL-0.370
Token reached
Token ID4251
Feature activation-2.13e+00

Pos logit contributions
+1.363
+1.152
Islam+1.104
poll+1.099
REL+1.081
Neg logit contributions
acht-1.603
 Parenthood-1.351
uscript-1.350
ield-1.328
estic-1.313
Token the
Token ID262
Feature activation-2.10e-01

Pos logit contributions
acht+2.083
 Parenthood+1.764
uscript+1.738
ield+1.725
estic+1.700
Neg logit contributions
-1.676
-1.412
poll-1.344
Islam-1.337
REL-1.326
Token original
Token ID2656
Feature activation+1.16e+00

Pos logit contributions
acht+0.207
 Parenthood+0.175
uscript+0.173
ield+0.172
estic+0.169
Neg logit contributions
-0.166
-0.139
poll-0.133
Islam-0.133
REL-0.131
Token border
Token ID4865
Feature activation+3.76e+00

Pos logit contributions
+0.873
+0.728
Islam+0.691
poll+0.689
REL+0.676
Neg logit contributions
acht-1.182
 Parenthood-1.008
uscript-1.000
ield-0.989
estic-0.978
Token.[
Token ID3693
Feature activation+3.62e-01

Pos logit contributions
+2.975
+2.533
Islam+2.408
poll+2.390
REL+2.360
Neg logit contributions
acht-3.631
 Parenthood-3.109
uscript-3.060
estic-3.005
ield-3.003
Token,"
Token ID553
Feature activation+1.57e+00

Pos logit contributions
+1.081
+0.915
poll+0.881
Islam+0.875
REL+0.862
Neg logit contributions
acht-1.239
 Parenthood-1.039
uscript-1.037
ield-1.026
assium-1.008
Token he
Token ID339
Feature activation+1.94e+00

Pos logit contributions
+1.154
+0.960
poll+0.910
Islam+0.909
REL+0.894
Neg logit contributions
acht-1.614
 Parenthood-1.377
uscript-1.370
ield-1.356
estic-1.339
Token noted
Token ID4367
Feature activation-1.54e+00

Pos logit contributions
+1.285
+1.044
Islam+0.981
poll+0.981
REL+0.963
Neg logit contributions
acht-2.145
 Parenthood-1.854
uscript-1.841
ield-1.824
estic-1.805
Token Friday
Token ID3217
Feature activation+1.63e+00

Pos logit contributions
acht+1.278
 Parenthood+1.046
uscript+1.031
ield+1.021
estic+1.006
Neg logit contributions
-1.443
-1.253
Islam-1.199
poll-1.194
REL-1.185
Token.
Token ID13
Feature activation+4.22e-01

Pos logit contributions
+1.497
+1.295
poll+1.245
Islam+1.245
REL+1.227
Neg logit contributions
acht-1.386
 Parenthood-1.143
uscript-1.136
ield-1.118
estic-1.103
Token "
Token ID366
Feature activation+4.53e-01

Pos logit contributions
+0.344
+0.292
Islam+0.277
poll+0.276
REL+0.274
Neg logit contributions
acht-0.401
 Parenthood-0.340
uscript-0.335
ield-0.332
estic-0.328
TokenIf
Token ID1532
Feature activation+1.29e+00

Pos logit contributions
+0.368
+0.312
Islam+0.297
poll+0.297
REL+0.293
Neg logit contributions
acht-0.434
 Parenthood-0.366
uscript-0.363
ield-0.359
estic-0.354
Token they
Token ID484
Feature activation+2.03e+00

Pos logit contributions
+0.906
+0.747
poll+0.707
Islam+0.706
REL+0.693
Neg logit contributions
acht-1.374
 Parenthood-1.179
uscript-1.173
ield-1.162
estic-1.148
Token don
Token ID836
Feature activation+2.57e+00

Pos logit contributions
+1.537
+1.288
poll+1.230
Islam+1.228
REL+1.208
Neg logit contributions
acht-2.036
 Parenthood-1.739
uscript-1.721
ield-1.705
estic-1.680
Token't
Token ID470
Feature activation+3.54e+00

Pos logit contributions
+1.650
+1.333
Islam+1.252
poll+1.252
REL+1.225
Neg logit contributions
acht-2.900
 Parenthood-2.512
uscript-2.503
ield-2.474
estic-2.449
Token want
Token ID765
Feature activation+1.85e+00

Pos logit contributions
+2.315
+1.883
poll+1.801
Islam+1.791
REL+1.758
Neg logit contributions
acht-3.897
 Parenthood-3.394
uscript-3.371
ield-3.317
assium-3.288
Tokeneding
Token ID8228
Feature activation+5.15e-01

Pos logit contributions
+1.127
+0.973
poll+0.934
Islam+0.933
REL+0.916
Neg logit contributions
acht-1.107
 Parenthood-0.925
uscript-0.910
ield-0.895
estic-0.885
Token to
Token ID284
Feature activation-8.13e-01

Pos logit contributions
+0.425
+0.361
Islam+0.344
poll+0.344
REL+0.340
Neg logit contributions
acht-0.486
 Parenthood-0.408
uscript-0.406
ield-0.401
estic-0.396
Token the
Token ID262
Feature activation-4.15e-01

Pos logit contributions
acht+0.808
 Parenthood+0.689
uscript+0.682
ield+0.673
estic+0.666
Neg logit contributions
-0.630
-0.526
poll-0.498
REL-0.495
Islam-0.495
Token throne
Token ID19262
Feature activation+1.60e+00

Pos logit contributions
acht+0.402
 Parenthood+0.340
uscript+0.336
ield+0.332
estic+0.328
Neg logit contributions
-0.333
-0.280
poll-0.267
Islam-0.267
REL-0.264
Token.
Token ID13
Feature activation+9.98e-03

Pos logit contributions
+1.261
+1.072
poll+1.024
Islam+1.021
REL+0.997
Neg logit contributions
acht-1.552
 Parenthood-1.319
uscript-1.304
ield-1.288
estic-1.274
Token The
Token ID383
Feature activation-4.98e-01

Pos logit contributions
+0.009
+0.008
Islam+0.007
poll+0.007
REL+0.007
Neg logit contributions
acht-0.009
 Parenthood-0.007
uscript-0.007
ield-0.007
estic-0.007
Token design
Token ID1486
Feature activation-8.92e-01

Pos logit contributions
acht+0.486
 Parenthood+0.411
uscript+0.408
ield+0.403
estic+0.398
Neg logit contributions
-0.395
-0.332
Islam-0.317
poll-0.317
REL-0.312
Token is
Token ID318
Feature activation-3.50e-01

Pos logit contributions
acht+0.825
 Parenthood+0.690
uscript+0.686
ield+0.678
estic+0.667
Neg logit contributions
-0.753
-0.643
poll-0.614
Islam-0.613
REL-0.605
Token of
Token ID286
Feature activation+7.56e-01

Pos logit contributions
acht+0.336
 Parenthood+0.284
uscript+0.282
ield+0.279
estic+0.275
Neg logit contributions
-0.282
-0.239
Islam-0.227
poll-0.227
REL-0.224
Token the
Token ID262
Feature activation-2.38e-01

Pos logit contributions
+0.594
+0.502
Islam+0.476
poll+0.476
REL+0.469
Neg logit contributions
acht-0.742
 Parenthood-0.628
uscript-0.623
ield-0.618
estic-0.610
Token 1989
Token ID11104
Feature activation-1.93e-01

Pos logit contributions
acht+0.216
 Parenthood+0.180
uscript+0.179
ield+0.177
estic+0.175
Neg logit contributions
-0.205
-0.175
Islam-0.168
poll-0.168
REL-0.165
Token have
Token ID423
Feature activation+1.21e+00

Pos logit contributions
acht+0.206
 Parenthood+0.175
uscript+0.174
ield+0.173
estic+0.171
Neg logit contributions
-0.146
-0.121
Islam-0.114
poll-0.114
REL-0.113
Token convinced
Token ID9431
Feature activation+2.92e+00

Pos logit contributions
+0.967
+0.815
Islam+0.779
poll+0.778
REL+0.765
Neg logit contributions
acht-1.172
 Parenthood-0.993
uscript-0.987
ield-0.976
estic-0.962
Token them
Token ID606
Feature activation+9.03e-01

Pos logit contributions
+2.236
+1.869
poll+1.795
Islam+1.780
REL+1.746
Neg logit contributions
acht-2.916
 Parenthood-2.487
uscript-2.473
ield-2.448
assium-2.410
Token that
Token ID326
Feature activation+5.96e-01

Pos logit contributions
+0.683
+0.570
Islam+0.544
poll+0.544
REL+0.533
Neg logit contributions
acht-0.913
 Parenthood-0.779
uscript-0.774
ield-0.766
estic-0.754
Token the
Token ID262
Feature activation+3.23e-02

Pos logit contributions
+0.446
+0.372
Islam+0.352
poll+0.351
REL+0.347
Neg logit contributions
acht-0.609
 Parenthood-0.520
uscript-0.515
ield-0.510
estic-0.504
Token cause
Token ID2728
Feature activation+2.55e-01

Pos logit contributions
+0.024
+0.020
Islam+0.019
poll+0.019
REL+0.019
Neg logit contributions
acht-0.033
 Parenthood-0.028
uscript-0.028
ield-0.028
estic-0.028
Token of
Token ID286
Feature activation+1.21e+00

Pos logit contributions
+0.208
+0.177
Islam+0.168
poll+0.168
REL+0.166
Neg logit contributions
acht-0.243
 Parenthood-0.204
uscript-0.202
ield-0.200
estic-0.198
Token their
Token ID511
Feature activation+2.35e+00

Pos logit contributions
+0.930
+0.779
Islam+0.740
poll+0.740
REL+0.729
Neg logit contributions
acht-1.219
 Parenthood-1.036
uscript-1.030
ield-1.019
estic-1.005
Token problems
Token ID2761
Feature activation-1.45e+00

Pos logit contributions
+1.717
+1.425
Islam+1.349
poll+1.349
REL+1.325
Neg logit contributions
acht-2.442
 Parenthood-2.087
uscript-2.083
ield-2.057
estic-2.030
Token is
Token ID318
Feature activation-1.82e-01

Pos logit contributions
acht+1.253
 Parenthood+1.032
uscript+1.018
ield+1.007
estic+0.996
Neg logit contributions
-1.315
-1.135
poll-1.083
Islam-1.082
REL-1.075
Token rooted
Token ID19459
Feature activation-2.17e-01

Pos logit contributions
acht+0.178
 Parenthood+0.151
uscript+0.149
ield+0.148
estic+0.146
Neg logit contributions
-0.144
-0.122
Islam-0.115
poll-0.115
REL-0.114
Token I
Token ID314
Feature activation+1.81e+00

Pos logit contributions
+0.876
+0.745
Islam+0.710
poll+0.708
REL+0.701
Neg logit contributions
acht-0.987
 Parenthood-0.829
uscript-0.823
ield-0.814
estic-0.803
TokenBF
Token ID29499
Feature activation+3.15e+00

Pos logit contributions
+0.988
+0.765
poll+0.706
Islam+0.706
REL+0.686
Neg logit contributions
acht-2.213
 Parenthood-1.937
uscript-1.927
ield-1.913
estic-1.894
Token wel
Token ID5029
Feature activation+8.96e-01

Pos logit contributions
+2.853
+2.456
Islam+2.339
poll+2.339
REL+2.334
Neg logit contributions
acht-2.714
 Parenthood-2.240
uscript-2.226
ield-2.189
assium-2.176
Tokenter
Token ID353
Feature activation-4.49e-01

Pos logit contributions
+0.773
+0.660
Islam+0.632
poll+0.632
REL+0.624
Neg logit contributions
acht-0.814
 Parenthood-0.678
uscript-0.672
ield-0.667
estic-0.656
Tokenweight
Token ID6551
Feature activation-2.54e+00

Pos logit contributions
acht+0.515
 Parenthood+0.448
uscript+0.444
ield+0.442
estic+0.436
Neg logit contributions
-0.280
-0.224
Islam-0.209
poll-0.209
REL-0.205
Token title
Token ID3670
Feature activation-5.32e-01

Pos logit contributions
acht+2.246
 Parenthood+1.864
uscript+1.864
ield+1.847
 Wonderful+1.800
Neg logit contributions
-2.205
-1.883
Islam-1.824
poll-1.822
REL-1.771
Token Read
Token ID4149
Feature activation-1.15e+00

Pos logit contributions
acht+0.493
 Parenthood+0.415
uscript+0.410
ield+0.407
estic+0.400
Neg logit contributions
-0.447
-0.380
Islam-0.364
poll-0.364
REL-0.358
Token more
Token ID517
Feature activation-6.52e-01

Pos logit contributions
acht+1.124
 Parenthood+0.952
uscript+0.947
ield+0.938
estic+0.921
Neg logit contributions
-0.902
-0.760
Islam-0.721
poll-0.716
REL-0.713
Token
Token ID198
Feature activation+2.72e-01

Pos logit contributions
acht+0.627
 Parenthood+0.532
ield+0.519
uscript+0.518
estic+0.508
Neg logit contributions
-0.528
-0.443
Islam-0.417
poll-0.415
REL-0.413
Token
Token ID198
Feature activation+2.26e-02

Pos logit contributions
+0.216
+0.182
Islam+0.171
poll+0.170
REL+0.170
Neg logit contributions
acht-0.264
 Parenthood-0.225
ield-0.220
uscript-0.220
estic-0.216
TokenTrue
Token ID17821
Feature activation-1.54e+00

Pos logit contributions
+0.019
+0.016
poll+0.015
Islam+0.015
REL+0.015
Neg logit contributions
acht-0.021
 Parenthood-0.018
uscript-0.018
ield-0.018
estic-0.017
Token Huff
Token ID14721
Feature activation-4.37e+00

Pos logit contributions
+3.811
+3.268
Islam+3.123
poll+3.111
REL+3.061
Neg logit contributions
acht-3.843
uscript-3.180
 Parenthood-3.179
ield-3.117
assium-3.085
Tokenman
Token ID805
Feature activation-1.33e+00

Pos logit contributions
acht+3.881
ield+3.239
uscript+3.168
 Parenthood+3.136
estic+3.063
Neg logit contributions
-3.914
-3.317
Islam-3.141
REL-3.129
poll-3.098
Token of
Token ID286
Feature activation+1.29e+00

Pos logit contributions
acht+1.098
 Parenthood+0.888
uscript+0.886
ield+0.878
estic+0.859
Neg logit contributions
-1.269
-1.102
Islam-1.057
poll-1.052
REL-1.044
Token Houston
Token ID6995
Feature activation-1.62e+00

Pos logit contributions
+1.090
+0.931
poll+0.889
Islam+0.889
REL+0.875
Neg logit contributions
acht-1.187
 Parenthood-0.989
uscript-0.985
ield-0.973
estic-0.961
Token,
Token ID11
Feature activation+4.68e-02

Pos logit contributions
acht+1.324
 Parenthood+1.085
uscript+1.067
ield+1.061
estic+1.044
Neg logit contributions
-1.535
-1.337
Islam-1.280
poll-1.279
REL-1.269
Token state
Token ID1181
Feature activation-2.90e-01

Pos logit contributions
+0.037
+0.031
Islam+0.030
poll+0.029
REL+0.029
Neg logit contributions
acht-0.046
 Parenthood-0.039
uscript-0.039
ield-0.038
estic-0.038
Token police
Token ID1644
Feature activation+2.42e-01

Pos logit contributions
acht+0.262
 Parenthood+0.218
uscript+0.216
ield+0.214
estic+0.211
Neg logit contributions
-0.252
-0.216
Islam-0.206
poll-0.206
REL-0.204
Token closed
Token ID4838
Feature activation-1.62e-01

Pos logit contributions
+0.195
+0.164
poll+0.156
Islam+0.156
REL+0.154
Neg logit contributions
acht-0.233
 Parenthood-0.197
uscript-0.195
ield-0.193
estic-0.191
Token the
Token ID262
Feature activation-2.66e-01

Pos logit contributions
acht+0.160
 Parenthood+0.136
uscript+0.134
ield+0.133
estic+0.132
Neg logit contributions
-0.127
-0.106
Islam-0.101
poll-0.101
REL-0.100
Token meeting
Token ID3249
Feature activation-1.48e-01

Pos logit contributions
acht+0.286
 Parenthood+0.247
uscript+0.245
ield+0.243
estic+0.240
Neg logit contributions
-0.185
-0.151
Islam-0.143
poll-0.142
REL-0.141
Token room
Token ID2119
Feature activation+4.16e-01

Pos logit contributions
acht+0.133
 Parenthood+0.111
uscript+0.110
ield+0.108
estic+0.107
Neg logit contributions
-0.129
-0.110
Islam-0.105
poll-0.105
REL-0.104
Token and
Token ID290
Feature activation-9.28e-01

Pos logit contributions
acht+0.202
 Parenthood+0.171
uscript+0.169
ield+0.167
estic+0.165
Neg logit contributions
-0.171
-0.145
Islam-0.138
poll-0.138
REL-0.136
Token be
Token ID307
Feature activation+1.92e+00

Pos logit contributions
acht+0.918
 Parenthood+0.778
uscript+0.770
ield+0.766
estic+0.754
Neg logit contributions
-0.725
-0.609
poll-0.578
Islam-0.578
REL-0.570
Tokenheaded
Token ID15353
Feature activation-1.90e+00

Pos logit contributions
+1.831
+1.591
poll+1.535
Islam+1.533
REL+1.510
Neg logit contributions
acht-1.555
 Parenthood-1.276
uscript-1.269
ield-1.233
ocument-1.223
Token her
Token ID607
Feature activation+2.93e-02

Pos logit contributions
acht+1.756
 Parenthood+1.471
uscript+1.453
ield+1.441
estic+1.424
Neg logit contributions
-1.603
-1.370
poll-1.304
Islam-1.298
REL-1.290
Token.
Token ID13
Feature activation-7.32e-03

Pos logit contributions
+0.026
+0.023
Islam+0.022
poll+0.022
REL+0.021
Neg logit contributions
acht-0.026
 Parenthood-0.021
uscript-0.021
ield-0.021
estic-0.020
Token She
Token ID1375
Feature activation-6.65e-01

Pos logit contributions
acht+0.006
 Parenthood+0.005
uscript+0.005
ield+0.005
estic+0.005
Neg logit contributions
-0.007
-0.006
poll-0.005
Islam-0.005
REL-0.005
Token said
Token ID531
Feature activation-1.79e+00

Pos logit contributions
acht+0.672
 Parenthood+0.571
uscript+0.568
ield+0.563
estic+0.556
Neg logit contributions
-0.504
-0.422
poll-0.399
Islam-0.399
REL-0.394
Token:
Token ID25
Feature activation-7.17e-01

Pos logit contributions
acht+1.424
 Parenthood+1.153
uscript+1.142
ield+1.125
estic+1.109
Neg logit contributions
-1.740
-1.522
poll-1.462
Islam-1.455
REL-1.444
Token I
Token ID314
Feature activation+1.90e+00

Pos logit contributions
acht+0.622
 Parenthood+0.515
uscript+0.509
ield+0.504
estic+0.496
Neg logit contributions
-0.647
-0.558
poll-0.534
Islam-0.534
REL-0.528
Token will
Token ID481
Feature activation-2.06e+00

Pos logit contributions
+1.410
+1.172
Islam+1.128
poll+1.120
REL+1.107
Neg logit contributions
acht-1.939
 Parenthood-1.657
uscript-1.645
ield-1.623
estic-1.608
Token not
Token ID407
Feature activation+3.70e+00

Pos logit contributions
acht+2.009
 Parenthood+1.694
uscript+1.677
ield+1.675
estic+1.655
Neg logit contributions
-1.643
-1.389
poll-1.304
Islam-1.296
REL-1.283
Token Assistant
Token ID15286
Feature activation-2.61e+00

Pos logit contributions
acht+1.824
 Parenthood+1.489
uscript+1.488
ield+1.462
estic+1.439
Neg logit contributions
-2.044
-1.762
poll-1.700
Islam-1.693
REL-1.682
Token
Token ID447
Feature activation+1.75e-01

Pos logit contributions
acht+2.579
 Parenthood+2.184
uscript+2.183
ield+2.152
estic+2.129
Neg logit contributions
-2.012
-1.674
Islam-1.609
poll-1.608
REL-1.589
Token
Token ID251
Feature activation-8.55e-02

Pos logit contributions
+0.161
+0.140
Islam+0.134
poll+0.134
REL+0.132
Neg logit contributions
acht-0.149
 Parenthood-0.122
uscript-0.121
ield-0.120
estic-0.118
Token to
Token ID284
Feature activation-1.15e+00

Pos logit contributions
acht+0.081
 Parenthood+0.069
uscript+0.068
ield+0.067
estic+0.066
Neg logit contributions
-0.070
-0.059
Islam-0.056
poll-0.056
REL-0.056
Token report
Token ID989
Feature activation+1.38e-01

Pos logit contributions
acht+1.181
 Parenthood+1.006
uscript+1.001
ield+0.991
estic+0.978
Neg logit contributions
-0.855
-0.711
poll-0.676
Islam-0.675
REL-0.665
Token persons
Token ID6506
Feature activation-4.32e+00

Pos logit contributions
+0.100
+0.083
Islam+0.078
poll+0.078
REL+0.077
Neg logit contributions
acht-0.145
 Parenthood-0.124
uscript-0.123
ield-0.122
estic-0.120
Token pretending
Token ID23662
Feature activation-7.24e-01

Pos logit contributions
acht+3.959
uscript+3.270
 Parenthood+3.269
estic+3.210
ield+3.204
Neg logit contributions
-3.651
-3.103
Islam-2.977
poll-2.969
REL-2.961
Token to
Token ID284
Feature activation-1.04e+00

Pos logit contributions
acht+0.681
 Parenthood+0.571
uscript+0.567
ield+0.560
estic+0.554
Neg logit contributions
-0.600
-0.510
poll-0.487
Islam-0.487
REL-0.482
Token be
Token ID307
Feature activation+1.74e+00

Pos logit contributions
acht+1.022
 Parenthood+0.864
uscript+0.856
ield+0.851
estic+0.846
Neg logit contributions
-0.817
-0.688
Islam-0.655
poll-0.655
REL-0.643
Token from
Token ID422
Feature activation+2.37e-01

Pos logit contributions
+1.359
+1.146
poll+1.087
Islam+1.086
REL+1.073
Neg logit contributions
acht-1.708
 Parenthood-1.447
uscript-1.437
ield-1.425
estic-1.402
Token the
Token ID262
Feature activation-5.58e-01

Pos logit contributions
+0.182
+0.153
Islam+0.145
poll+0.145
REL+0.143
Neg logit contributions
acht-0.236
 Parenthood-0.201
uscript-0.200
ield-0.197
estic-0.195
Token story
Token ID1621
Feature activation-4.24e-01

Pos logit contributions
acht+0.238
 Parenthood+0.201
uscript+0.199
ield+0.197
estic+0.194
Neg logit contributions
-0.202
-0.171
Islam-0.163
poll-0.163
REL-0.161
Token of
Token ID286
Feature activation+3.44e-01

Pos logit contributions
acht+0.449
 Parenthood+0.384
uscript+0.382
ield+0.378
estic+0.374
Neg logit contributions
-0.302
-0.249
poll-0.236
Islam-0.236
REL-0.232
Token Am
Token ID1703
Feature activation-1.13e+00

Pos logit contributions
+0.284
+0.242
Islam+0.231
poll+0.230
REL+0.227
Neg logit contributions
acht-0.324
 Parenthood-0.272
uscript-0.270
ield-0.267
estic-0.264
Tokennon
Token ID13159
Feature activation+6.11e-01

Pos logit contributions
acht+1.093
 Parenthood+0.911
uscript+0.910
ield+0.902
estic+0.895
Neg logit contributions
-0.923
-0.778
Islam-0.743
poll-0.733
REL-0.730
Token and
Token ID290
Feature activation-9.78e-01

Pos logit contributions
+0.549
+0.473
poll+0.453
Islam+0.453
REL+0.447
Neg logit contributions
acht-0.531
 Parenthood-0.441
uscript-0.436
ield-0.431
estic-0.424
Token Tam
Token ID11552
Feature activation-4.92e+00

Pos logit contributions
acht+0.907
 Parenthood+0.761
uscript+0.753
ield+0.745
estic+0.736
Neg logit contributions
-0.823
-0.701
Islam-0.669
poll-0.668
REL-0.660
Tokenar
Token ID283
Feature activation+1.81e-01

Pos logit contributions
acht+4.553
uscript+3.759
ield+3.739
 Parenthood+3.732
estic+3.704
Neg logit contributions
-4.123
-3.469
Islam-3.332
poll-3.298
REL-3.276
Token,
Token ID11
Feature activation-4.46e-01

Pos logit contributions
+0.163
+0.141
poll+0.135
Islam+0.135
REL+0.133
Neg logit contributions
acht-0.156
 Parenthood-0.130
uscript-0.128
ield-0.127
estic-0.125
Token which
Token ID543
Feature activation-3.24e-01

Pos logit contributions
acht+0.418
 Parenthood+0.351
uscript+0.348
ield+0.344
estic+0.340
Neg logit contributions
-0.371
-0.315
Islam-0.301
poll-0.301
REL-0.297
Token is
Token ID318
Feature activation-3.37e-01

Pos logit contributions
acht+0.299
 Parenthood+0.250
uscript+0.249
ield+0.246
estic+0.243
Neg logit contributions
-0.273
-0.233
Islam-0.223
poll-0.223
REL-0.220
Token explicitly
Token ID11777
Feature activation+9.54e-01

Pos logit contributions
acht+0.330
 Parenthood+0.280
uscript+0.277
ield+0.275
estic+0.271
Neg logit contributions
-0.266
-0.225
Islam-0.214
poll-0.214
REL-0.211
Token their
Token ID511
Feature activation+3.07e+00

Pos logit contributions
+1.464
+1.229
poll+1.170
Islam+1.169
REL+1.150
Neg logit contributions
acht-1.893
 Parenthood-1.603
uscript-1.596
ield-1.579
estic-1.557
Token respective
Token ID11756
Feature activation-1.43e+00

Pos logit contributions
+2.334
+1.956
poll+1.871
Islam+1.849
REL+1.836
Neg logit contributions
acht-3.076
uscript-2.610
 Parenthood-2.608
ield-2.558
assium-2.557
Token fields
Token ID7032
Feature activation+1.70e+00

Pos logit contributions
acht+1.420
 Parenthood+1.208
uscript+1.195
ield+1.190
estic+1.173
Neg logit contributions
-1.105
-0.928
Islam-0.884
poll-0.879
REL-0.868
Token,
Token ID11
Feature activation+3.83e-01

Pos logit contributions
+1.426
+1.214
Islam+1.160
poll+1.160
REL+1.142
Neg logit contributions
acht-1.579
 Parenthood-1.324
uscript-1.314
ield-1.301
estic-1.278
Token this
Token ID428
Feature activation-5.74e-01

Pos logit contributions
+0.302
+0.255
Islam+0.242
poll+0.242
REL+0.239
Neg logit contributions
acht-0.375
 Parenthood-0.317
uscript-0.315
ield-0.312
estic-0.308
Token Manhattan
Token ID13458
Feature activation-5.35e+00

Pos logit contributions
acht+0.553
 Parenthood+0.467
uscript+0.463
ield+0.458
estic+0.452
Neg logit contributions
-0.464
-0.392
Islam-0.373
poll-0.373
REL-0.368
Token Project
Token ID4935
Feature activation-2.83e+00

Pos logit contributions
acht+4.677
 Parenthood+3.841
uscript+3.789
ield+3.771
 Hots+3.713
Neg logit contributions
-4.749
-4.079
Islam-3.904
poll-3.887
REL-3.861
Token would
Token ID561
Feature activation-1.90e+00

Pos logit contributions
acht+2.650
 Parenthood+2.231
uscript+2.211
ield+2.185
estic+2.152
Neg logit contributions
-2.364
-2.004
Islam-1.913
poll-1.913
REL-1.882
Token also
Token ID635
Feature activation+2.16e+00

Pos logit contributions
acht+1.860
 Parenthood+1.569
uscript+1.553
ield+1.549
estic+1.529
Neg logit contributions
-1.505
-1.270
poll-1.205
Islam-1.204
REL-1.187
Token be
Token ID307
Feature activation+2.66e+00

Pos logit contributions
+1.646
+1.380
Islam+1.316
poll+1.309
REL+1.293
Neg logit contributions
acht-2.153
 Parenthood-1.833
uscript-1.827
ield-1.793
assium-1.780
Token able
Token ID1498
Feature activation-6.30e-01

Pos logit contributions
+2.082
+1.754
Islam+1.673
poll+1.671
REL+1.653
Neg logit contributions
acht-2.580
 Parenthood-2.192
uscript-2.182
ield-2.143
estic-2.135
Token "
Token ID366
Feature activation-3.12e-01

Pos logit contributions
+0.883
+0.750
poll+0.714
Islam+0.712
REL+0.702
Neg logit contributions
acht-1.042
uscript-0.875
 Parenthood-0.874
ield-0.863
estic-0.852
TokenI
Token ID40
Feature activation+1.29e+00

Pos logit contributions
acht+0.283
 Parenthood+0.237
uscript+0.234
ield+0.232
estic+0.229
Neg logit contributions
-0.268
-0.229
poll-0.219
Islam-0.218
REL-0.216
Token'll
Token ID1183
Feature activation-2.06e+00

Pos logit contributions
+0.931
+0.770
poll+0.729
Islam+0.729
REL+0.722
Neg logit contributions
acht-1.347
 Parenthood-1.152
uscript-1.144
ield-1.133
estic-1.121
Token Feel
Token ID18571
Feature activation-1.84e+00

Pos logit contributions
acht+1.425
 Parenthood+1.128
uscript+1.099
ield+1.097
estic+1.069
Neg logit contributions
-2.220
-1.968
poll-1.891
Islam-1.891
REL-1.869
Token a
Token ID257
Feature activation+2.53e-02

Pos logit contributions
acht+1.726
 Parenthood+1.470
uscript+1.443
ield+1.429
estic+1.405
Neg logit contributions
-1.519
-1.291
Islam-1.225
poll-1.220
REL-1.206
Token Whole
Token ID23431
Feature activation-7.30e+00

Pos logit contributions
+0.020
+0.017
poll+0.016
Islam+0.016
REL+0.016
Neg logit contributions
acht-0.025
uscript-0.021
 Parenthood-0.021
ield-0.021
estic-0.020
Token Lot
Token ID15099
Feature activation-1.39e+00

Pos logit contributions
acht+4.156
 Parenthood+3.352
 Wonderful+3.080
 Hots+3.018
uscript+2.939
Neg logit contributions
-8.523
-7.574
Islam-7.379
poll-7.334
REL-7.255
Token Better
Token ID11625
Feature activation-4.36e+00

Pos logit contributions
acht+1.200
 Parenthood+1.000
uscript+0.982
ield+0.970
estic+0.956
Neg logit contributions
-1.254
-1.082
Islam-1.037
poll-1.035
REL-1.024
Token"
Token ID1
Feature activation+4.76e-01

Pos logit contributions
acht+3.599
 Parenthood+2.936
uscript+2.917
ield+2.873
 Wonderful+2.819
Neg logit contributions
-4.095
-3.525
REL-3.363
poll-3.362
Islam-3.362
Token (
Token ID357
Feature activation-6.14e-01

Pos logit contributions
+0.422
+0.363
poll+0.349
Islam+0.348
REL+0.344
Neg logit contributions
acht-0.419
 Parenthood-0.347
uscript-0.345
ield-0.341
estic-0.336
Tokenabove
Token ID29370
Feature activation-1.62e+00

Pos logit contributions
acht+0.609
 Parenthood+0.516
uscript+0.512
ield+0.507
estic+0.500
Neg logit contributions
-0.478
-0.402
Islam-0.381
poll-0.380
REL-0.375
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
+1.178
+1.015
poll+0.977
Islam+0.975
REL+0.964
Neg logit contributions
acht-1.099
uscript-0.908
 Parenthood-0.906
ield-0.887
estic-0.875
Token
Token ID198
Feature activation+9.72e-01

Pos logit contributions
+0.398
+0.337
Islam+0.321
poll+0.321
REL+0.317
Neg logit contributions
acht-0.461
 Parenthood-0.390
uscript-0.384
ield-0.382
estic-0.377
Token
Token ID198
Feature activation+6.11e-01

Pos logit contributions
+0.764
+0.640
Islam+0.605
poll+0.603
REL+0.598
Neg logit contributions
acht-0.959
 Parenthood-0.814
uscript-0.801
ield-0.800
estic-0.787
TokenBut
Token ID1537
Feature activation+1.03e+00

Pos logit contributions
+0.500
+0.424
Islam+0.403
poll+0.403
REL+0.398
Neg logit contributions
acht-0.580
 Parenthood-0.488
uscript-0.484
ield-0.480
estic-0.473
Token the
Token ID262
Feature activation+5.57e-01

Pos logit contributions
+0.785
+0.657
poll+0.624
Islam+0.624
REL+0.614
Neg logit contributions
acht-1.034
 Parenthood-0.878
uscript-0.874
ield-0.864
estic-0.853
Token Work
Token ID5521
Feature activation-4.41e+00

Pos logit contributions
+0.444
+0.374
poll+0.356
Islam+0.356
REL+0.351
Neg logit contributions
acht-0.544
 Parenthood-0.457
uscript-0.457
ield-0.450
estic-0.444
Token it
Token ID340
Feature activation-1.47e+00

Pos logit contributions
acht+4.182
 Parenthood+3.582
uscript+3.488
ield+3.476
assium+3.424
Neg logit contributions
-3.516
-2.939
REL-2.803
poll-2.797
Islam-2.782
Token Y
Token ID575
Feature activation-2.36e+00

Pos logit contributions
acht+1.131
 Parenthood+0.917
uscript+0.901
ield+0.892
estic+0.874
Neg logit contributions
-1.473
-1.287
poll-1.240
Islam-1.239
REL-1.225
TokenOW
Token ID3913
Feature activation-3.05e+00

Pos logit contributions
acht+2.531
ield+2.158
 Parenthood+2.155
uscript+2.144
estic+2.115
Neg logit contributions
-1.678
-1.379
poll-1.286
Islam-1.286
REL-1.262
Token group
Token ID1448
Feature activation+1.38e+00

Pos logit contributions
acht+3.088
 Parenthood+2.645
ield+2.611
uscript+2.593
estic+2.557
Neg logit contributions
-2.286
-1.907
Islam-1.809
poll-1.803
REL-1.772
Token runs
Token ID4539
Feature activation+9.18e-01

Pos logit contributions
+1.148
+0.979
Islam+0.935
poll+0.934
REL+0.921
Neg logit contributions
acht-1.292
 Parenthood-1.083
uscript-1.079
ield-1.062
estic-1.052