TOP ACTIVATIONS
MAX = 9.133

players from using the fascinating Typh on neur om ods .
t just full of Typh on . There are also
to kill a tele pathic Typh on without hurting the mind
routes his final year at Ole Miss , he was successful
the institutional church , said Lauren Sand ler , author of
morning outside ," said volunteer Lauren Carter , who started organizing
T ina Ole ch owski , a Qu
performs " Sm ells Like Teen Spirit " in a bar
entitled Over coming Sexual Abuse or
a close examination of whether Ross testimony to the
. 2016 file photo shows Lauren Anderson , a staff attorney
sl ant , the former Rebels wide receiver made every route
ne re ) led by Aless andro Pav olini and the
successful in similar situations at Ole Miss . This
the first of 40 that Teen Mania is putting on between
, we will use the 2 test for each
Caps who struck first when Alex O ve ch kin scored
teacher overheard them talking about Alex ei Naval ny . The
WWE is still advertising that Les nar will face Randy Or
to the website owned by Alex Jones that propag ates conspiracy

MIN ACTIVATIONS
MIN = -10.070

parade during a ceremony South Sudan s first Independence
uba . South Sudan ese military parade during a
in J uba , South Sudan . ( Photo by Paula
by Osama bin Laden and Saddam Hussein . 1995
or chemical weapons by Osama bin Laden and Saddam Hussein .
the presidential guards of South Sudan s president ,
and are rejected by both Burma and neighbouring Bangladesh .
former President Barack Obama Barack Hussein Obama With low birth rate
The traditionally designed stone mug costs 16 euros ($ 18
. 2015 ). The hefty mug is em bl azon ed
euros . A Bav arian mug holds a full liter of
2 , 000 from the Brune i Currency and Monetary Board
infiltr ator from Syria carrying bin ocular s , explosives ,
the ob verse of the Brune i version is similar to
another , Abu Sin an bin M ih san , the
June 2007 , Singapore and Brune i celebrated the 40 th
While a decade ago a mug of beer cost 7 .
pas aurus rex in our debugger : 1 $
has the state title of Brune i in Latin script .[
Muslims , Kh all ad bin Su w aid was killed

INTERVAL 4.332 - 9.133
CONTAINS 0.678%

, Ms . Ole ch owski said .
they ." Pan sexual : Pan sexual people may
planet , but its special electric engine that maintains this altitude
West chester 1 hour ago Pretty simple Paul :
make mechanics for cycles of cards , we have to decide

INTERVAL -0.468 - 4.332
CONTAINS 66.575%

YP OWER . At MLG they did even better , best
forward a referendum on whether to exit the EU .
his page on Sh uffle Along s website .
a nightmare apartment broker on Broad City and once did cart
polit ic isation of his role in the run - up

INTERVAL -5.269 - -0.468
CONTAINS 32.514%

way I 'm building this ROM , moves / s bin
Catholic truth ought not only to teach the proficient , but
fact oring in Kim b rel s $ 34
have taken a form less distract ingly reminiscent of the American
as well as the rest of our allies across the globe

INTERVAL -10.070 - -5.269
CONTAINS 0.233%

, you have a hot bod . Let 's not pretend
ord inated campaign by Muslim nations against Sweden is not a
it should be part of Somalia , not Kenya . Ken
directly from the government of Haiti and would lose their profit
However , the new Haiti - V enezuel a alliance
Token players
Token ID1938
Feature activation+4.51e-01

Pos logit contributions
nces+0.247
tenance+0.238
reath+0.210
ned+0.208
 drown+0.201
Neg logit contributions
andro-0.323
agers-0.246
inyl-0.245
endale-0.236
tro-0.235
Token from
Token ID422
Feature activation-2.95e-01

Pos logit contributions
andro+0.461
agers+0.347
inyl+0.347
endale+0.333
tro+0.331
Neg logit contributions
nces-0.381
tenance-0.367
reath-0.327
ned-0.324
 drown-0.314
Token using
Token ID1262
Feature activation-3.50e+00

Pos logit contributions
nces+0.236
tenance+0.227
reath+0.201
ned+0.199
 drown+0.192
Neg logit contributions
andro-0.316
inyl-0.242
agers-0.241
endale-0.232
tro-0.231
Token the
Token ID262
Feature activation-5.10e-01

Pos logit contributions
nces+2.734
tenance+2.638
reath+2.353
ned+2.348
 drown+2.279
Neg logit contributions
andro-3.752
inyl-2.885
agers-2.852
endale-2.782
tro-2.739
Token fascinating
Token ID13899
Feature activation-1.43e+00

Pos logit contributions
nces+0.413
tenance+0.398
reath+0.354
ned+0.351
 drown+0.340
Neg logit contributions
andro-0.538
inyl-0.410
agers-0.409
endale-0.394
tro-0.391
Token Typh
Token ID27282
Feature activation+9.13e+00

Pos logit contributions
nces+1.177
tenance+1.133
reath+1.009
ned+1.007
 Shroud+0.974
Neg logit contributions
andro-1.490
inyl-1.135
agers-1.131
endale-1.086
tro-1.073
Tokenon
Token ID261
Feature activation+1.36e+00

Pos logit contributions
andro+8.576
inyl+6.411
agers+6.398
tro+6.308
endale+6.071
Neg logit contributions
nces-8.001
tenance-7.908
ned-6.914
reath-6.862
 drown-6.725
Token neur
Token ID11943
Feature activation-2.55e+00

Pos logit contributions
andro+1.440
inyl+1.095
agers+1.095
tro+1.053
endale+1.053
Neg logit contributions
nces-1.103
tenance-1.065
reath-0.941
ned-0.931
 drown-0.905
Tokenom
Token ID296
Feature activation-3.31e-01

Pos logit contributions
nces+2.155
tenance+2.083
reath+1.875
ned+1.855
 drown+1.797
Neg logit contributions
andro-2.590
inyl-1.942
agers-1.935
endale-1.873
tro-1.840
Tokenods
Token ID12978
Feature activation-1.21e+00

Pos logit contributions
nces+0.282
tenance+0.273
reath+0.245
ned+0.243
 drown+0.235
Neg logit contributions
andro-0.336
inyl-0.252
agers-0.251
endale-0.242
tro-0.240
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
nces+0.999
tenance+0.963
reath+0.860
ned+0.855
 drown+0.825
Neg logit contributions
andro-1.265
inyl-0.961
agers-0.957
endale-0.920
tro-0.911
Token
Token ID247
Feature activation+2.03e-01

Pos logit contributions
nces+0.261
tenance+0.252
reath+0.227
ned+0.225
 drown+0.218
Neg logit contributions
andro-0.294
inyl-0.220
agers-0.220
tro-0.210
endale-0.209
Tokent
Token ID83
Feature activation-1.91e+00

Pos logit contributions
andro+0.183
inyl+0.133
agers+0.132
endale+0.126
tro+0.124
Neg logit contributions
nces-0.196
tenance-0.190
reath-0.172
ned-0.172
 drown-0.167
Token just
Token ID655
Feature activation+1.15e+00

Pos logit contributions
nces+1.555
tenance+1.502
reath+1.339
ned+1.332
 drown+1.293
Neg logit contributions
andro-2.004
inyl-1.525
agers-1.517
endale-1.464
tro-1.453
Token full
Token ID1336
Feature activation+2.52e+00

Pos logit contributions
andro+1.188
agers+0.894
inyl+0.893
tro+0.855
endale+0.854
Neg logit contributions
nces-0.969
tenance-0.932
reath-0.828
ned-0.821
 drown-0.795
Token of
Token ID286
Feature activation-1.11e+00

Pos logit contributions
andro+2.504
agers+1.868
inyl+1.854
tro+1.787
endale+1.778
Neg logit contributions
nces-2.192
tenance-2.109
reath-1.887
ned-1.861
 drown-1.800
Token Typh
Token ID27282
Feature activation+8.79e+00

Pos logit contributions
nces+0.892
tenance+0.860
reath+0.764
ned+0.757
 drown+0.735
Neg logit contributions
andro-1.181
inyl-0.902
agers-0.899
endale-0.866
tro-0.860
Tokenon
Token ID261
Feature activation+1.75e+00

Pos logit contributions
andro+6.104
inyl+4.004
agers+3.959
tro+3.838
endale+3.729
Neg logit contributions
tenance-9.765
nces-9.729
ned-8.787
reath-8.756
 Shroud-8.621
Token.
Token ID13
Feature activation+1.93e-01

Pos logit contributions
andro+1.879
agers+1.438
inyl+1.435
tro+1.383
endale+1.375
Neg logit contributions
nces-1.379
tenance-1.338
reath-1.174
ned-1.156
 drown-1.122
Token There
Token ID1318
Feature activation+1.93e-01

Pos logit contributions
andro+0.186
inyl+0.137
agers+0.137
endale+0.131
tro+0.130
Neg logit contributions
nces-0.173
tenance-0.168
reath-0.151
ned-0.150
 drown-0.146
Token are
Token ID389
Feature activation+5.68e-01

Pos logit contributions
andro+0.192
inyl+0.143
agers+0.143
endale+0.137
tro+0.136
Neg logit contributions
nces-0.168
tenance-0.162
reath-0.145
ned-0.144
 drown-0.140
Token also
Token ID635
Feature activation-6.00e-01

Pos logit contributions
andro+0.585
inyl+0.442
agers+0.441
endale+0.424
tro+0.423
Neg logit contributions
nces-0.474
tenance-0.457
reath-0.408
ned-0.404
 drown-0.391
Token to
Token ID284
Feature activation-2.59e-01

Pos logit contributions
andro+0.126
agers+0.097
inyl+0.096
endale+0.093
tro+0.093
Neg logit contributions
nces-0.095
tenance-0.091
reath-0.081
ned-0.079
 Shroud-0.078
Token kill
Token ID1494
Feature activation-5.38e-01

Pos logit contributions
nces+0.193
tenance+0.185
reath+0.162
ned+0.159
 Shroud+0.153
Neg logit contributions
andro-0.290
inyl-0.225
agers-0.225
tro-0.217
endale-0.216
Token a
Token ID257
Feature activation+1.97e-01

Pos logit contributions
nces+0.440
tenance+0.424
reath+0.377
ned+0.373
 drown+0.361
Neg logit contributions
andro-0.565
agers-0.429
inyl-0.429
endale-0.412
tro-0.410
Token tele
Token ID5735
Feature activation+4.10e+00

Pos logit contributions
andro+0.214
inyl+0.164
agers+0.163
tro+0.158
endale+0.157
Neg logit contributions
nces-0.154
tenance-0.147
reath-0.131
ned-0.128
 drown-0.124
Tokenpathic
Token ID38829
Feature activation+9.07e-01

Pos logit contributions
andro+4.037
agers+2.994
inyl+2.993
tro+2.941
endale+2.879
Neg logit contributions
nces-3.578
tenance-3.409
reath-3.055
 drown-2.996
ned-2.984
Token Typh
Token ID27282
Feature activation+8.66e+00

Pos logit contributions
andro+0.988
agers+0.758
inyl+0.757
tro+0.732
endale+0.728
Neg logit contributions
nces-0.707
tenance-0.676
reath-0.597
ned-0.587
 drown-0.568
Tokenon
Token ID261
Feature activation+1.31e+00

Pos logit contributions
andro+6.260
inyl+4.103
tro+3.990
agers+3.981
endale+3.840
Neg logit contributions
nces-9.700
tenance-9.478
ned-8.500
reath-8.487
 Shroud-8.369
Token without
Token ID1231
Feature activation-1.07e+00

Pos logit contributions
andro+1.365
agers+1.034
inyl+1.032
tro+0.998
endale+0.989
Neg logit contributions
nces-1.080
tenance-1.038
reath-0.918
ned-0.901
 drown-0.879
Token hurting
Token ID21530
Feature activation+5.13e-01

Pos logit contributions
nces+0.838
tenance+0.808
reath+0.717
ned+0.711
 drown+0.689
Neg logit contributions
andro-1.152
inyl-0.881
agers-0.879
endale-0.847
tro-0.843
Token the
Token ID262
Feature activation-1.44e-01

Pos logit contributions
andro+0.545
agers+0.415
inyl+0.414
endale+0.399
tro+0.398
Neg logit contributions
nces-0.413
tenance-0.398
reath-0.353
ned-0.348
 drown-0.338
Token mind
Token ID2000
Feature activation+8.48e-01

Pos logit contributions
nces+0.114
tenance+0.110
reath+0.097
ned+0.096
 drown+0.093
Neg logit contributions
andro-0.155
agers-0.119
inyl-0.119
tro-0.114
endale-0.114
Token routes
Token ID11926
Feature activation+2.42e+00

Pos logit contributions
andro+0.508
agers+0.384
inyl+0.381
tro+0.367
endale+0.366
Neg logit contributions
nces-0.414
tenance-0.404
reath-0.358
ned-0.355
 drown-0.344
Token his
Token ID465
Feature activation+7.69e-01

Pos logit contributions
andro+2.373
inyl+1.774
agers+1.768
endale+1.693
tro+1.686
Neg logit contributions
nces-2.120
tenance-2.063
reath-1.842
ned-1.803
 drown-1.763
Token final
Token ID2457
Feature activation+3.14e+00

Pos logit contributions
andro+0.748
inyl+0.554
agers+0.553
endale+0.530
tro+0.527
Neg logit contributions
nces-0.687
tenance-0.665
reath-0.597
ned-0.591
 drown-0.575
Token year
Token ID614
Feature activation+1.24e-02

Pos logit contributions
andro+2.873
inyl+2.092
agers+2.085
endale+2.008
tro+1.987
Neg logit contributions
nces-2.948
tenance-2.873
reath-2.585
ned-2.542
 drown-2.482
Token at
Token ID379
Feature activation+1.87e+00

Pos logit contributions
andro+0.012
inyl+0.009
agers+0.009
endale+0.009
tro+0.009
Neg logit contributions
nces-0.011
tenance-0.010
reath-0.009
ned-0.009
 drown-0.009
Token Ole
Token ID30093
Feature activation+8.54e+00

Pos logit contributions
andro+1.932
inyl+1.463
agers+1.458
endale+1.407
tro+1.398
Neg logit contributions
nces-1.548
tenance-1.495
reath-1.328
ned-1.315
 drown-1.277
Token Miss
Token ID4544
Feature activation+4.15e+00

Pos logit contributions
andro+8.699
inyl+6.455
agers+6.452
endale+6.344
ager+6.207
Neg logit contributions
nces-7.210
tenance-6.981
reath-6.004
ned-5.966
 drown-5.918
Token,
Token ID11
Feature activation+1.39e-01

Pos logit contributions
andro+4.019
inyl+2.987
agers+2.965
endale+2.872
tro+2.827
Neg logit contributions
nces-3.686
tenance-3.569
reath-3.176
ned-3.130
 drown-3.075
Token he
Token ID339
Feature activation-4.57e-03

Pos logit contributions
andro+0.132
inyl+0.097
agers+0.097
endale+0.093
tro+0.092
Neg logit contributions
nces-0.126
tenance-0.122
reath-0.110
ned-0.110
 drown-0.107
Token was
Token ID373
Feature activation+5.40e-01

Pos logit contributions
nces+0.004
tenance+0.004
reath+0.003
ned+0.003
 drown+0.003
Neg logit contributions
andro-0.005
inyl-0.003
agers-0.003
endale-0.003
tro-0.003
Token successful
Token ID4388
Feature activation+6.57e-01

Pos logit contributions
andro+0.550
agers+0.414
inyl+0.414
endale+0.397
tro+0.395
Neg logit contributions
nces-0.458
tenance-0.443
reath-0.395
ned-0.391
 drown-0.380
Token the
Token ID262
Feature activation-5.65e-01

Pos logit contributions
nces+0.676
tenance+0.652
reath+0.583
ned+0.580
 drown+0.561
Neg logit contributions
andro-0.839
inyl-0.635
agers-0.632
endale-0.610
tro-0.606
Token institutional
Token ID15855
Feature activation+3.16e+00

Pos logit contributions
nces+0.487
tenance+0.471
reath+0.421
ned+0.419
 drown+0.406
Neg logit contributions
andro-0.567
inyl-0.425
agers-0.424
endale-0.407
tro-0.404
Token church
Token ID4928
Feature activation+1.79e+00

Pos logit contributions
andro+3.079
inyl+2.286
agers+2.286
tro+2.186
endale+2.186
Neg logit contributions
nces-2.785
tenance-2.675
reath-2.416
ned-2.369
 drown-2.303
Token,
Token ID11
Feature activation+1.54e-01

Pos logit contributions
andro+1.794
agers+1.344
inyl+1.343
endale+1.288
tro+1.282
Neg logit contributions
nces-1.544
tenance-1.491
reath-1.334
ned-1.318
 drown-1.283
Token said
Token ID531
Feature activation-7.27e-02

Pos logit contributions
andro+0.153
inyl+0.114
agers+0.114
endale+0.109
tro+0.109
Neg logit contributions
nces-0.135
tenance-0.130
reath-0.117
ned-0.116
 drown-0.113
Token Lauren
Token ID25672
Feature activation+8.44e+00

Pos logit contributions
nces+0.062
tenance+0.060
reath+0.053
ned+0.053
 drown+0.051
Neg logit contributions
andro-0.074
inyl-0.056
agers-0.055
endale-0.053
tro-0.053
Token Sand
Token ID3837
Feature activation+3.18e+00

Pos logit contributions
andro+8.147
agers+6.002
inyl+5.929
tro+5.771
endale+5.764
Neg logit contributions
nces-7.261
tenance-6.916
reath-6.178
 drown-6.026
ned-6.008
Tokenler
Token ID1754
Feature activation+6.81e-02

Pos logit contributions
andro+2.732
agers+1.927
inyl+1.921
endale+1.841
tro+1.823
Neg logit contributions
nces-3.197
tenance-3.109
reath-2.820
ned-2.804
 drown-2.744
Token,
Token ID11
Feature activation+2.51e-02

Pos logit contributions
andro+0.068
inyl+0.051
agers+0.051
endale+0.049
tro+0.049
Neg logit contributions
nces-0.059
tenance-0.057
reath-0.051
ned-0.050
 drown-0.049
Token author
Token ID1772
Feature activation-1.55e+00

Pos logit contributions
andro+0.027
inyl+0.020
agers+0.020
endale+0.019
tro+0.019
Neg logit contributions
nces-0.020
tenance-0.019
reath-0.017
ned-0.017
 drown-0.017
Token of
Token ID286
Feature activation-1.47e+00

Pos logit contributions
nces+1.270
tenance+1.225
reath+1.090
ned+1.081
 drown+1.048
Neg logit contributions
andro-1.619
inyl-1.231
agers-1.226
endale-1.179
tro-1.175
Token morning
Token ID3329
Feature activation-1.23e+00

Pos logit contributions
andro+0.142
inyl+0.107
agers+0.107
endale+0.102
tro+0.102
Neg logit contributions
nces-0.117
tenance-0.114
reath-0.101
ned-0.101
 drown-0.098
Token outside
Token ID2354
Feature activation-6.33e-01

Pos logit contributions
nces+1.041
tenance+1.007
reath+0.899
ned+0.894
 drown+0.866
Neg logit contributions
andro-1.261
inyl-0.950
agers-0.947
endale-0.909
tro-0.905
Token,"
Token ID553
Feature activation+3.72e-01

Pos logit contributions
nces+0.533
tenance+0.515
reath+0.460
ned+0.456
 drown+0.443
Neg logit contributions
andro-0.648
inyl-0.488
agers-0.487
endale-0.468
tro-0.466
Token said
Token ID531
Feature activation+8.25e-02

Pos logit contributions
andro+0.341
inyl+0.247
agers+0.246
endale+0.235
tro+0.234
Neg logit contributions
nces-0.353
tenance-0.343
reath-0.311
ned-0.309
 drown-0.300
Token volunteer
Token ID13904
Feature activation+1.69e+00

Pos logit contributions
andro+0.073
inyl+0.053
agers+0.052
endale+0.050
tro+0.050
Neg logit contributions
nces-0.080
tenance-0.078
reath-0.071
ned-0.071
 drown-0.069
Token Lauren
Token ID25672
Feature activation+8.39e+00

Pos logit contributions
andro+1.573
agers+1.145
inyl+1.143
endale+1.090
tro+1.088
Neg logit contributions
nces-1.593
tenance-1.537
reath-1.393
ned-1.374
 drown-1.341
Token Carter
Token ID10831
Feature activation-4.92e-01

Pos logit contributions
andro+6.540
agers+4.416
inyl+4.277
endale+4.210
ager+4.174
Neg logit contributions
nces-8.724
tenance-8.419
reath-7.700
ned-7.616
 drown-7.577
Token,
Token ID11
Feature activation+3.08e-01

Pos logit contributions
nces+0.416
tenance+0.401
reath+0.358
ned+0.355
 drown+0.345
Neg logit contributions
andro-0.502
inyl-0.378
agers-0.377
endale-0.362
tro-0.360
Token who
Token ID508
Feature activation+4.45e-01

Pos logit contributions
andro+0.327
inyl+0.249
agers+0.248
endale+0.239
tro+0.238
Neg logit contributions
nces-0.248
tenance-0.240
reath-0.213
ned-0.211
 drown-0.205
Token started
Token ID2067
Feature activation-1.27e-01

Pos logit contributions
andro+0.436
inyl+0.324
agers+0.323
endale+0.310
tro+0.308
Neg logit contributions
nces-0.395
tenance-0.382
reath-0.343
ned-0.338
 drown-0.329
Token organizing
Token ID16924
Feature activation+1.15e+00

Pos logit contributions
nces+0.108
tenance+0.105
reath+0.094
ned+0.093
 drown+0.090
Neg logit contributions
andro-0.128
inyl-0.096
agers-0.096
endale-0.092
tro-0.092
Token
Token ID251
Feature activation-3.39e-01

Pos logit contributions
nces+0.604
tenance+0.585
reath+0.527
ned+0.523
 drown+0.509
Neg logit contributions
andro-0.632
inyl-0.465
agers-0.465
endale-0.443
tro-0.442
Token
Token ID198
Feature activation-1.11e-01

Pos logit contributions
nces+0.291
tenance+0.282
reath+0.252
ned+0.251
 drown+0.243
Neg logit contributions
andro-0.341
inyl-0.256
agers-0.255
endale-0.245
tro-0.243
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
nces+0.095
tenance+0.093
ned+0.083
reath+0.083
 drown+0.080
Neg logit contributions
andro-0.112
inyl-0.084
agers-0.084
endale-0.080
tro-0.079
TokenT
Token ID51
Feature activation-8.88e-01

Pos logit contributions
nces+0.201
tenance+0.195
reath+0.174
ned+0.173
 drown+0.167
Neg logit contributions
andro-0.237
inyl-0.178
agers-0.178
endale-0.171
tro-0.169
Tokenina
Token ID1437
Feature activation-2.96e-01

Pos logit contributions
nces+0.767
tenance+0.742
reath+0.676
ned+0.670
 drown+0.639
Neg logit contributions
andro-0.877
inyl-0.651
agers-0.651
tro-0.623
endale-0.623
Token Ole
Token ID30093
Feature activation+8.37e+00

Pos logit contributions
nces+0.261
tenance+0.253
reath+0.227
ned+0.225
 drown+0.219
Neg logit contributions
andro-0.289
inyl-0.216
agers-0.215
endale-0.206
tro-0.205
Tokench
Token ID354
Feature activation-1.88e+00

Pos logit contributions
andro+8.642
agers+6.534
inyl+6.471
endale+6.342
ager+6.295
Neg logit contributions
nces-6.624
tenance-6.521
reath-5.678
 drown-5.615
ned-5.529
Tokenowski
Token ID12079
Feature activation+1.04e+00

Pos logit contributions
nces+1.721
tenance+1.670
reath+1.521
ned+1.510
 drown+1.459
Neg logit contributions
andro-1.764
agers-1.301
inyl-1.299
endale-1.233
tro-1.223
Token,
Token ID11
Feature activation+2.77e-01

Pos logit contributions
andro+1.063
inyl+0.799
agers+0.798
endale+0.768
tro+0.761
Neg logit contributions
nces-0.880
tenance-0.851
reath-0.757
ned-0.749
 drown-0.727
Token a
Token ID257
Feature activation-2.68e-03

Pos logit contributions
andro+0.292
inyl+0.222
agers+0.221
endale+0.213
tro+0.212
Neg logit contributions
nces-0.225
tenance-0.217
reath-0.193
ned-0.191
 drown-0.185
Token Qu
Token ID2264
Feature activation-3.79e+00

Pos logit contributions
nces+0.002
tenance+0.002
reath+0.002
ned+0.002
 drown+0.002
Neg logit contributions
andro-0.003
inyl-0.002
agers-0.002
endale-0.002
tro-0.002
Token performs
Token ID17706
Feature activation-1.93e+00

Pos logit contributions
nces+0.631
tenance+0.607
reath+0.537
ned+0.532
 drown+0.515
Neg logit contributions
andro-0.880
inyl-0.676
agers-0.675
endale-0.651
tro-0.647
Token "
Token ID366
Feature activation+1.58e+00

Pos logit contributions
nces+1.618
tenance+1.538
reath+1.388
ned+1.380
 drown+1.345
Neg logit contributions
andro-1.988
inyl-1.506
agers-1.505
endale-1.445
tro-1.434
TokenSm
Token ID7556
Feature activation-1.73e+00

Pos logit contributions
andro+1.514
inyl+1.112
agers+1.112
endale+1.064
tro+1.063
Neg logit contributions
nces-1.430
tenance-1.383
reath-1.244
ned-1.232
 drown-1.203
Tokenells
Token ID19187
Feature activation+1.90e+00

Pos logit contributions
nces+1.435
tenance+1.382
reath+1.246
ned+1.235
 drown+1.186
Neg logit contributions
andro-1.775
inyl-1.338
agers-1.335
tro-1.280
endale-1.279
Token Like
Token ID4525
Feature activation-4.08e-01

Pos logit contributions
andro+1.754
inyl+1.272
agers+1.270
endale+1.217
tro+1.205
Neg logit contributions
nces-1.791
tenance-1.742
reath-1.566
ned-1.550
 drown-1.508
Token Teen
Token ID21432
Feature activation+8.34e+00

Pos logit contributions
nces+0.373
tenance+0.362
reath+0.328
ned+0.326
 drown+0.318
Neg logit contributions
andro-0.386
inyl-0.284
agers-0.282
endale-0.272
tro-0.269
Token Spirit
Token ID7710
Feature activation+2.97e+00

Pos logit contributions
andro+8.270
agers+6.550
ager+6.229
inyl+6.154
endale+5.875
Neg logit contributions
nces-7.224
tenance-6.853
reath-6.044
ned-5.970
selage-5.777
Token"
Token ID1
Feature activation+5.70e-01

Pos logit contributions
andro+2.902
inyl+2.172
agers+2.153
endale+2.071
tro+2.061
Neg logit contributions
nces-2.622
tenance-2.525
reath-2.268
ned-2.230
 drown-2.184
Token in
Token ID287
Feature activation+3.19e-01

Pos logit contributions
andro+0.580
inyl+0.437
agers+0.435
endale+0.418
tro+0.417
Neg logit contributions
nces-0.484
tenance-0.468
reath-0.417
ned-0.414
 drown-0.401
Token a
Token ID257
Feature activation+1.22e-01

Pos logit contributions
andro+0.322
inyl+0.241
agers+0.241
endale+0.231
tro+0.230
Neg logit contributions
nces-0.273
tenance-0.264
reath-0.236
ned-0.234
 drown-0.227
Token bar
Token ID2318
Feature activation+3.35e-01

Pos logit contributions
andro+0.129
inyl+0.099
agers+0.098
endale+0.095
tro+0.094
Neg logit contributions
nces-0.099
tenance-0.095
reath-0.085
ned-0.084
 drown-0.081
Token entitled
Token ID9080
Feature activation+3.27e+00

Pos logit contributions
andro+0.201
inyl+0.151
agers+0.151
endale+0.144
tro+0.144
Neg logit contributions
nces-0.169
tenance-0.163
reath-0.146
ned-0.145
 drown-0.141
Token
Token ID564
Feature activation+9.96e-01

Pos logit contributions
andro+3.350
inyl+2.541
agers+2.521
tro+2.426
endale+2.413
Neg logit contributions
nces-2.705
tenance-2.612
reath-2.325
ned-2.279
 drown-2.244
Token
Token ID250
Feature activation+2.45e-01

Pos logit contributions
andro+0.949
inyl+0.697
agers+0.695
endale+0.666
tro+0.661
Neg logit contributions
nces-0.910
tenance-0.882
reath-0.795
ned-0.788
 drown-0.767
TokenOver
Token ID5886
Feature activation+1.95e+00

Pos logit contributions
andro+0.243
inyl+0.181
agers+0.181
endale+0.173
tro+0.173
Neg logit contributions
nces-0.214
tenance-0.206
reath-0.185
ned-0.183
 drown-0.178
Tokencoming
Token ID4976
Feature activation-4.89e-01

Pos logit contributions
andro+1.918
agers+1.434
inyl+1.432
endale+1.368
tro+1.367
Neg logit contributions
nces-1.702
tenance-1.647
reath-1.470
ned-1.461
 drown-1.425
Token Sexual
Token ID19536
Feature activation+8.33e+00

Pos logit contributions
nces+0.404
tenance+0.390
reath+0.348
ned+0.345
 drown+0.334
Neg logit contributions
andro-0.508
inyl-0.385
agers-0.384
endale-0.370
tro-0.367
Token Abuse
Token ID24221
Feature activation+1.23e+00

Pos logit contributions
andro+7.828
agers+5.783
inyl+5.664
tro+5.487
ager+5.449
Neg logit contributions
nces-7.555
tenance-7.252
reath-6.560
ned-6.312
 drown-6.276
Token
Token ID447
Feature activation+1.37e-01

Pos logit contributions
andro+1.377
inyl+1.066
agers+1.065
endale+1.027
tro+1.022
Neg logit contributions
nces-0.921
tenance-0.886
reath-0.778
ned-0.770
 drown-0.744
Token
Token ID251
Feature activation+5.64e-01

Pos logit contributions
andro+0.133
inyl+0.098
agers+0.098
endale+0.094
tro+0.094
Neg logit contributions
nces-0.123
tenance-0.119
reath-0.107
ned-0.106
 drown-0.103
Token or
Token ID393
Feature activation-1.02e+00

Pos logit contributions
andro+0.572
inyl+0.430
agers+0.429
endale+0.412
tro+0.410
Neg logit contributions
nces-0.480
tenance-0.464
reath-0.414
ned-0.411
 drown-0.399
Token
Token ID564
Feature activation+1.13e+00

Pos logit contributions
nces+0.808
tenance+0.777
reath+0.690
ned+0.683
 drown+0.661
Neg logit contributions
andro-1.100
inyl-0.842
agers-0.841
endale-0.810
tro-0.806
Token a
Token ID257
Feature activation+5.91e-02

Pos logit contributions
nces+0.452
tenance+0.434
reath+0.381
ned+0.377
 drown+0.364
Neg logit contributions
andro-0.680
inyl-0.527
agers-0.526
endale-0.508
tro-0.505
Token close
Token ID1969
Feature activation+2.74e+00

Pos logit contributions
andro+0.061
inyl+0.046
agers+0.046
endale+0.044
tro+0.044
Neg logit contributions
nces-0.049
tenance-0.048
reath-0.042
ned-0.042
 drown-0.041
Token examination
Token ID12452
Feature activation-8.40e-01

Pos logit contributions
andro+2.771
inyl+2.086
agers+2.078
endale+2.005
tro+1.989
Neg logit contributions
nces-2.332
tenance-2.242
reath-2.009
ned-1.976
 drown-1.926
Token of
Token ID286
Feature activation-9.77e-01

Pos logit contributions
nces+0.696
tenance+0.671
reath+0.598
ned+0.592
 drown+0.575
Neg logit contributions
andro-0.872
inyl-0.660
agers-0.659
endale-0.634
tro-0.630
Token whether
Token ID1771
Feature activation-2.71e-01

Pos logit contributions
nces+0.828
tenance+0.798
reath+0.717
ned+0.713
 drown+0.692
Neg logit contributions
andro-0.994
inyl-0.747
agers-0.745
endale-0.717
tro-0.711
Token Ross
Token ID9847
Feature activation+8.31e+00

Pos logit contributions
nces+0.233
tenance+0.225
reath+0.202
ned+0.201
 drown+0.195
Neg logit contributions
andro-0.272
inyl-0.204
agers-0.203
endale-0.195
tro-0.194
Token
Token ID447
Feature activation-1.01e-01

Pos logit contributions
andro+7.957
agers+5.736
inyl+5.715
endale+5.616
tro+5.412
Neg logit contributions
nces-7.469
tenance-7.148
reath-6.269
ned-6.167
 Shroud-5.976
Token
Token ID247
Feature activation+8.21e-01

Pos logit contributions
nces+0.078
tenance+0.075
reath+0.066
ned+0.066
 drown+0.063
Neg logit contributions
andro-0.110
agers-0.086
inyl-0.086
tro-0.082
endale-0.082
Token testimony
Token ID9709
Feature activation+5.29e-01

Pos logit contributions
andro+0.543
inyl+0.337
agers+0.335
endale+0.310
tro+0.306
Neg logit contributions
nces-0.989
tenance-0.966
reath-0.894
ned-0.890
 drown-0.871
Token to
Token ID284
Feature activation-2.70e-01

Pos logit contributions
andro+0.525
inyl+0.392
agers+0.391
endale+0.375
tro+0.373
Neg logit contributions
nces-0.462
tenance-0.446
reath-0.400
ned-0.398
 drown-0.386
Token the
Token ID262
Feature activation-9.71e-02

Pos logit contributions
nces+0.216
tenance+0.208
reath+0.185
ned+0.183
 drown+0.178
Neg logit contributions
andro-0.288
inyl-0.220
agers-0.219
endale-0.211
tro-0.210
Token.
Token ID13
Feature activation-9.74e-01

Pos logit contributions
nces+0.018
tenance+0.017
reath+0.015
ned+0.015
 drown+0.015
Neg logit contributions
andro-0.021
inyl-0.016
agers-0.016
endale-0.015
tro-0.015
Token 2016
Token ID1584
Feature activation+1.96e+00

Pos logit contributions
nces+0.863
tenance+0.842
ned+0.755
reath+0.754
 Shroud+0.729
Neg logit contributions
andro-0.950
inyl-0.706
agers-0.701
endale-0.673
tro-0.668
Token file
Token ID2393
Feature activation-5.60e-01

Pos logit contributions
andro+2.130
inyl+1.639
agers+1.634
endale+1.578
tro+1.572
Neg logit contributions
nces-1.523
tenance-1.462
reath-1.293
ned-1.277
 drown-1.237
Token photo
Token ID4590
Feature activation+1.15e+00

Pos logit contributions
nces+0.399
tenance+0.383
reath+0.334
ned+0.330
 drown+0.318
Neg logit contributions
andro-0.646
inyl-0.504
agers-0.504
endale-0.487
tro-0.484
Token shows
Token ID2523
Feature activation+1.11e+00

Pos logit contributions
andro+1.172
agers+0.885
inyl+0.883
endale+0.848
tro+0.842
Neg logit contributions
nces-0.980
tenance-0.946
reath-0.844
ned-0.836
 drown-0.810
Token Lauren
Token ID25672
Feature activation+8.30e+00

Pos logit contributions
andro+1.130
agers+0.850
inyl+0.849
endale+0.815
tro+0.811
Neg logit contributions
nces-0.945
tenance-0.913
reath-0.816
ned-0.809
 drown-0.784
Token Anderson
Token ID9918
Feature activation+7.94e-01

Pos logit contributions
andro+8.221
agers+6.096
inyl+5.988
endale+5.852
ager+5.829
Neg logit contributions
nces-6.925
tenance-6.652
reath-5.896
ned-5.768
 drown-5.725
Token,
Token ID11
Feature activation-1.81e-01

Pos logit contributions
andro+0.814
inyl+0.614
agers+0.613
endale+0.590
tro+0.585
Neg logit contributions
nces-0.667
tenance-0.644
reath-0.575
ned-0.570
 drown-0.552
Token a
Token ID257
Feature activation-2.98e-01

Pos logit contributions
nces+0.155
tenance+0.150
reath+0.134
ned+0.133
 drown+0.130
Neg logit contributions
andro-0.182
inyl-0.137
agers-0.136
endale-0.131
tro-0.130
Token staff
Token ID3085
Feature activation+1.25e+00

Pos logit contributions
nces+0.246
tenance+0.238
reath+0.211
ned+0.210
 drown+0.204
Neg logit contributions
andro-0.311
inyl-0.235
agers-0.235
endale-0.226
tro-0.225
Token attorney
Token ID6136
Feature activation+1.30e+00

Pos logit contributions
andro+1.192
inyl+0.876
agers+0.875
endale+0.836
tro+0.832
Neg logit contributions
nces-1.143
tenance-1.107
reath-0.998
ned-0.990
 drown-0.963
Token sl
Token ID1017
Feature activation+2.04e+00

Pos logit contributions
nces+0.466
tenance+0.449
reath+0.400
ned+0.396
 drown+0.384
Neg logit contributions
andro-0.582
inyl-0.440
agers-0.439
endale-0.422
tro-0.420
Tokenant
Token ID415
Feature activation+3.85e+00

Pos logit contributions
andro+1.496
inyl+0.989
agers+0.980
endale+0.923
ager+0.910
Neg logit contributions
nces-2.336
tenance-2.261
reath-2.067
ned-2.058
 Shroud-2.019
Token,
Token ID11
Feature activation-3.83e-02

Pos logit contributions
andro+3.762
agers+2.786
inyl+2.776
tro+2.683
endale+2.683
Neg logit contributions
nces-3.441
tenance-3.234
reath-2.865
ned-2.827
 drown-2.773
Token the
Token ID262
Feature activation-6.35e-01

Pos logit contributions
nces+0.034
tenance+0.033
reath+0.030
ned+0.029
 drown+0.029
Neg logit contributions
andro-0.037
inyl-0.028
agers-0.028
endale-0.027
tro-0.026
Token former
Token ID1966
Feature activation-9.36e-01

Pos logit contributions
nces+0.527
tenance+0.509
reath+0.454
ned+0.450
 drown+0.437
Neg logit contributions
andro-0.658
inyl-0.498
agers-0.497
endale-0.478
tro-0.475
Token Rebels
Token ID36069
Feature activation+8.21e+00

Pos logit contributions
nces+0.776
tenance+0.749
reath+0.669
ned+0.666
 drown+0.647
Neg logit contributions
andro-0.969
inyl-0.734
agers-0.730
endale-0.705
tro-0.698
Token wide
Token ID3094
Feature activation+2.83e+00

Pos logit contributions
andro+8.303
agers+6.246
inyl+6.168
tro+6.087
ager+5.983
Neg logit contributions
nces-6.679
tenance-6.452
reath-5.584
ned-5.388
 drown-5.366
Token receiver
Token ID9733
Feature activation+1.72e+00

Pos logit contributions
andro+3.175
agers+2.459
inyl+2.449
tro+2.371
endale+2.359
Neg logit contributions
nces-2.126
tenance-2.003
reath-1.756
ned-1.711
 drown-1.679
Token made
Token ID925
Feature activation-8.16e-01

Pos logit contributions
andro+1.726
agers+1.300
inyl+1.297
tro+1.240
endale+1.239
Neg logit contributions
nces-1.475
tenance-1.428
reath-1.268
ned-1.246
 Shroud-1.211
Token every
Token ID790
Feature activation-2.93e-01

Pos logit contributions
nces+0.678
tenance+0.656
reath+0.582
ned+0.577
 drown+0.560
Neg logit contributions
andro-0.844
agers-0.638
inyl-0.638
endale-0.612
tro-0.609
Token route
Token ID6339
Feature activation+3.10e+00

Pos logit contributions
nces+0.237
tenance+0.227
reath+0.202
ned+0.199
 drown+0.193
Neg logit contributions
andro-0.311
inyl-0.237
agers-0.236
endale-0.228
tro-0.227
Token ne
Token ID497
Feature activation+1.38e+00

Pos logit contributions
andro+0.529
inyl+0.397
agers+0.396
endale+0.380
tro+0.377
Neg logit contributions
nces-0.455
tenance-0.439
reath-0.393
ned-0.390
 drown-0.378
Tokenre
Token ID260
Feature activation-8.41e-01

Pos logit contributions
andro+1.332
inyl+0.985
agers+0.983
endale+0.942
tro+0.933
Neg logit contributions
nces-1.243
tenance-1.202
reath-1.081
ned-1.075
 drown-1.044
Token)
Token ID8
Feature activation-5.51e-01

Pos logit contributions
nces+0.739
tenance+0.712
reath+0.638
ned+0.638
 drown+0.616
Neg logit contributions
andro-0.828
agers-0.619
inyl-0.618
endale-0.593
tro-0.585
Token led
Token ID2957
Feature activation-3.56e+00

Pos logit contributions
nces+0.487
tenance+0.472
reath+0.425
ned+0.423
 drown+0.411
Neg logit contributions
andro-0.538
inyl-0.400
agers-0.399
endale-0.381
tro-0.378
Token by
Token ID416
Feature activation+5.36e-01

Pos logit contributions
nces+2.944
tenance+2.856
reath+2.563
ned+2.561
 drown+2.460
Neg logit contributions
andro-3.629
inyl-2.750
agers-2.749
endale-2.622
ager-2.593
Token Aless
Token ID47319
Feature activation+8.20e+00

Pos logit contributions
andro+0.557
inyl+0.422
agers+0.421
endale+0.405
tro+0.403
Neg logit contributions
nces-0.443
tenance-0.428
reath-0.381
ned-0.377
 drown-0.366
Tokenandro
Token ID28092
Feature activation+4.62e+00

Pos logit contributions
andro+5.641
inyl+3.151
agers+3.124
endale+2.938
tro+2.935
Neg logit contributions
nces-9.856
tenance-9.702
reath-8.895
ned-8.824
 drown-8.736
Token Pav
Token ID24081
Feature activation+4.06e+00

Pos logit contributions
andro+4.450
agers+3.235
inyl+3.233
tro+3.107
endale+3.084
Neg logit contributions
nces-4.147
tenance-4.022
reath-3.631
ned-3.563
 drown-3.476
Tokenolini
Token ID43232
Feature activation+1.62e+00

Pos logit contributions
andro+3.909
inyl+2.877
agers+2.869
endale+2.768
tro+2.747
Neg logit contributions
nces-3.650
tenance-3.559
reath-3.170
ned-3.134
 Shroud-3.098
Token and
Token ID290
Feature activation-4.38e-01

Pos logit contributions
andro+1.589
inyl+1.177
agers+1.176
endale+1.130
tro+1.124
Neg logit contributions
nces-1.440
tenance-1.392
reath-1.248
ned-1.235
 drown-1.201
Token the
Token ID262
Feature activation-2.76e-01

Pos logit contributions
nces+0.376
tenance+0.364
reath+0.326
ned+0.324
 drown+0.314
Neg logit contributions
andro-0.439
inyl-0.331
agers-0.330
endale-0.316
tro-0.314
Token successful
Token ID4388
Feature activation+8.98e-01

Pos logit contributions
andro+2.995
agers+2.253
inyl+2.222
tro+2.147
ager+2.141
Neg logit contributions
nces-2.522
tenance-2.438
reath-2.176
ned-2.132
 drown-2.073
Token in
Token ID287
Feature activation+5.78e-01

Pos logit contributions
andro+0.891
inyl+0.667
agers+0.666
endale+0.639
tro+0.635
Neg logit contributions
nces-0.783
tenance-0.757
reath-0.678
ned-0.668
 drown-0.649
Token similar
Token ID2092
Feature activation+4.66e-01

Pos logit contributions
andro+0.607
inyl+0.463
agers+0.462
tro+0.443
endale+0.443
Neg logit contributions
nces-0.471
tenance-0.456
reath-0.404
ned-0.397
 drown-0.385
Token situations
Token ID7445
Feature activation+1.86e-01

Pos logit contributions
andro+0.492
agers+0.374
inyl+0.374
endale+0.359
tro+0.358
Neg logit contributions
nces-0.376
tenance-0.363
reath-0.323
ned-0.317
 drown-0.308
Token at
Token ID379
Feature activation+2.07e+00

Pos logit contributions
andro+0.188
inyl+0.142
agers+0.141
endale+0.136
tro+0.135
Neg logit contributions
nces-0.158
tenance-0.153
reath-0.137
ned-0.135
 drown-0.131
Token Ole
Token ID30093
Feature activation+8.18e+00

Pos logit contributions
andro+2.092
inyl+1.572
agers+1.565
endale+1.515
tro+1.501
Neg logit contributions
nces-1.758
tenance-1.715
reath-1.519
ned-1.499
 drown-1.457
Token Miss
Token ID4544
Feature activation+4.26e+00

Pos logit contributions
andro+8.051
inyl+5.944
agers+5.916
endale+5.852
ager+5.696
Neg logit contributions
nces-7.072
tenance-6.762
reath-5.956
 drown-5.853
ned-5.706
Token.
Token ID13
Feature activation-5.24e-02

Pos logit contributions
andro+4.135
inyl+3.060
agers+3.056
endale+2.962
tro+2.903
Neg logit contributions
nces-3.756
tenance-3.655
reath-3.246
ned-3.190
 drown-3.142
Token
Token ID198
Feature activation+1.71e-01

Pos logit contributions
nces+0.048
tenance+0.046
reath+0.042
ned+0.042
 drown+0.040
Neg logit contributions
andro-0.050
inyl-0.037
agers-0.037
endale-0.035
tro-0.035
Token
Token ID198
Feature activation-4.99e-02

Pos logit contributions
andro+0.170
inyl+0.127
agers+0.126
endale+0.121
tro+0.120
Neg logit contributions
nces-0.148
tenance-0.144
reath-0.129
ned-0.129
 drown-0.124
TokenThis
Token ID1212
Feature activation+1.54e+00

Pos logit contributions
nces+0.045
tenance+0.043
reath+0.039
ned+0.039
 drown+0.038
Neg logit contributions
andro-0.048
inyl-0.036
agers-0.036
endale-0.034
tro-0.034
Token the
Token ID262
Feature activation-3.75e-01

Pos logit contributions
andro+0.788
inyl+0.597
agers+0.596
endale+0.572
tro+0.570
Neg logit contributions
nces-0.630
tenance-0.608
reath-0.542
ned-0.537
 drown-0.520
Token first
Token ID717
Feature activation-2.39e-01

Pos logit contributions
nces+0.311
tenance+0.300
reath+0.268
ned+0.266
 drown+0.258
Neg logit contributions
andro-0.388
inyl-0.293
agers-0.293
endale-0.281
tro-0.280
Token of
Token ID286
Feature activation-1.32e+00

Pos logit contributions
nces+0.197
tenance+0.191
reath+0.170
ned+0.168
 drown+0.163
Neg logit contributions
andro-0.248
inyl-0.188
agers-0.188
endale-0.180
tro-0.179
Token 40
Token ID2319
Feature activation+2.07e+00

Pos logit contributions
nces+1.007
tenance+0.971
reath+0.859
ned+0.854
 drown+0.823
Neg logit contributions
andro-1.451
inyl-1.124
agers-1.116
endale-1.081
tro-1.074
Token that
Token ID326
Feature activation+2.00e+00

Pos logit contributions
andro+2.148
inyl+1.633
agers+1.626
endale+1.563
tro+1.562
Neg logit contributions
nces-1.713
tenance-1.655
reath-1.461
ned-1.442
 drown-1.400
Token Teen
Token ID21432
Feature activation+8.15e+00

Pos logit contributions
andro+1.945
inyl+1.444
agers+1.439
endale+1.382
tro+1.371
Neg logit contributions
nces-1.774
tenance-1.721
reath-1.543
ned-1.524
 drown-1.480
Token Mania
Token ID49755
Feature activation+1.00e+00

Pos logit contributions
andro+8.016
agers+6.272
ager+5.882
inyl+5.866
endale+5.669
Neg logit contributions
nces-6.971
tenance-6.779
reath-5.943
ned-5.718
selage-5.696
Token is
Token ID318
Feature activation+1.48e+00

Pos logit contributions
andro+1.043
inyl+0.789
agers+0.789
endale+0.758
tro+0.754
Neg logit contributions
nces-0.833
tenance-0.804
reath-0.715
ned-0.708
 drown-0.687
Token putting
Token ID5137
Feature activation+4.55e-01

Pos logit contributions
andro+1.603
inyl+1.230
agers+1.230
endale+1.183
tro+1.178
Neg logit contributions
nces-1.158
tenance-1.114
reath-0.985
ned-0.974
 drown-0.942
Token on
Token ID319
Feature activation+2.15e+00

Pos logit contributions
andro+0.465
inyl+0.350
agers+0.350
endale+0.336
tro+0.335
Neg logit contributions
nces-0.385
tenance-0.371
reath-0.331
ned-0.328
 drown-0.318
Token between
Token ID1022
Feature activation+5.88e-01

Pos logit contributions
andro+2.148
inyl+1.607
agers+1.601
tro+1.536
endale+1.536
Neg logit contributions
nces-1.860
tenance-1.792
reath-1.601
ned-1.577
 drown-1.540
Token,
Token ID11
Feature activation+4.32e-01

Pos logit contributions
nces+1.332
tenance+1.285
ned+1.153
reath+1.142
 drown+1.107
Neg logit contributions
andro-1.705
agers-1.290
inyl-1.286
endale-1.233
tro-1.228
Token we
Token ID356
Feature activation+3.31e-01

Pos logit contributions
andro+0.410
inyl+0.301
agers+0.300
endale+0.287
tro+0.285
Neg logit contributions
nces-0.397
tenance-0.384
reath-0.347
ned-0.344
 drown-0.335
Token will
Token ID481
Feature activation+4.21e-01

Pos logit contributions
andro+0.372
inyl+0.289
agers+0.289
endale+0.278
tro+0.277
Neg logit contributions
nces-0.245
tenance-0.235
reath-0.206
ned-0.203
 drown-0.195
Token use
Token ID779
Feature activation-3.83e+00

Pos logit contributions
andro+0.454
inyl+0.349
agers+0.347
endale+0.334
tro+0.333
Neg logit contributions
nces-0.333
tenance-0.321
reath-0.284
ned-0.280
 Shroud-0.270
Token the
Token ID262
Feature activation-4.13e-01

Pos logit contributions
nces+3.147
tenance+3.014
reath+2.711
ned+2.708
 drown+2.636
Neg logit contributions
andro-3.961
inyl-2.993
agers-2.988
endale-2.874
tro-2.843
Token
Token ID18074
Feature activation+8.14e+00

Pos logit contributions
nces+0.349
tenance+0.336
reath+0.301
ned+0.298
 drown+0.290
Neg logit contributions
andro-0.421
inyl-0.317
agers-0.317
endale-0.304
tro-0.302
Token
Token ID229
Feature activation+2.21e+00

Pos logit contributions
andro+5.770
agers+3.697
inyl+3.687
endale+3.627
ager+3.383
Neg logit contributions
nces-9.070
tenance-9.002
reath-8.174
ned-8.129
 Shroud-8.067
Token2
Token ID17
Feature activation-3.07e-01

Pos logit contributions
andro+2.226
agers+1.669
inyl+1.661
endale+1.617
ager+1.588
Neg logit contributions
nces-1.880
tenance-1.844
reath-1.615
ned-1.587
 Shroud-1.564
Token test
Token ID1332
Feature activation-5.13e-01

Pos logit contributions
nces+0.223
tenance+0.214
reath+0.187
ned+0.185
 drown+0.179
Neg logit contributions
andro-0.349
inyl-0.272
agers-0.272
endale-0.262
tro-0.261
Token for
Token ID329
Feature activation+1.96e-02

Pos logit contributions
nces+0.414
tenance+0.400
reath+0.355
ned+0.352
 drown+0.341
Neg logit contributions
andro-0.542
inyl-0.413
agers-0.412
endale-0.397
tro-0.394
Token each
Token ID1123
Feature activation-1.05e+00

Pos logit contributions
andro+0.020
inyl+0.015
agers+0.015
endale+0.014
tro+0.014
Neg logit contributions
nces-0.017
tenance-0.016
reath-0.014
ned-0.014
 drown-0.014
Token Caps
Token ID23534
Feature activation+1.58e+00

Pos logit contributions
nces+0.456
tenance+0.440
reath+0.393
ned+0.391
 drown+0.379
Neg logit contributions
andro-0.556
inyl-0.420
agers-0.418
endale-0.403
tro-0.400
Token who
Token ID508
Feature activation+4.47e-01

Pos logit contributions
andro+1.638
agers+1.242
inyl+1.239
endale+1.192
tro+1.187
Neg logit contributions
nces-1.306
tenance-1.257
reath-1.119
ned-1.104
 drown-1.073
Token struck
Token ID7425
Feature activation-8.01e-01

Pos logit contributions
andro+0.431
inyl+0.318
agers+0.318
endale+0.304
tro+0.302
Neg logit contributions
nces-0.403
tenance-0.390
reath-0.351
ned-0.349
 drown-0.339
Token first
Token ID717
Feature activation-2.67e-02

Pos logit contributions
nces+0.670
tenance+0.648
ned+0.579
reath+0.579
 drown+0.561
Neg logit contributions
andro-0.820
inyl-0.621
agers-0.617
endale-0.595
tro-0.590
Token when
Token ID618
Feature activation-8.68e-01

Pos logit contributions
nces+0.023
tenance+0.022
reath+0.020
ned+0.019
 drown+0.019
Neg logit contributions
andro-0.027
inyl-0.020
agers-0.020
endale-0.020
tro-0.019
Token Alex
Token ID4422
Feature activation+8.11e+00

Pos logit contributions
nces+0.770
tenance+0.747
ned+0.671
reath+0.668
 drown+0.649
Neg logit contributions
andro-0.843
inyl-0.630
agers-0.625
endale-0.601
tro-0.596
Token O
Token ID440
Feature activation+4.08e-01

Pos logit contributions
andro+8.106
agers+5.980
inyl+5.830
endale+5.702
tro+5.688
Neg logit contributions
nces-7.087
tenance-6.654
reath-6.006
ned-5.908
 Shroud-5.713
Tokenve
Token ID303
Feature activation+3.05e+00

Pos logit contributions
andro+0.464
inyl+0.363
agers+0.361
endale+0.351
tro+0.346
Neg logit contributions
nces-0.295
tenance-0.284
reath-0.247
ned-0.245
 drown-0.235
Tokench
Token ID354
Feature activation-2.41e+00

Pos logit contributions
andro+2.837
inyl+2.065
agers+2.052
tro+1.979
endale+1.968
Neg logit contributions
nces-2.901
tenance-2.797
ned-2.499
reath-2.489
 drown-2.418
Tokenkin
Token ID5116
Feature activation+1.20e-01

Pos logit contributions
nces+1.752
tenance+1.684
ned+1.474
reath+1.469
 drown+1.407
Neg logit contributions
andro-2.739
agers-2.127
inyl-2.124
endale-2.047
tro-2.023
Token scored
Token ID7781
Feature activation-8.05e-01

Pos logit contributions
andro+0.122
inyl+0.092
agers+0.091
endale+0.088
tro+0.087
Neg logit contributions
nces-0.102
tenance-0.099
reath-0.088
ned-0.088
 drown-0.085
Token teacher
Token ID4701
Feature activation-2.45e-01

Pos logit contributions
andro+0.408
inyl+0.311
agers+0.311
endale+0.300
tro+0.299
Neg logit contributions
nces-0.306
tenance-0.293
reath-0.261
ned-0.258
 drown-0.249
Token overheard
Token ID48255
Feature activation-2.70e+00

Pos logit contributions
nces+0.199
tenance+0.191
reath+0.170
ned+0.168
 drown+0.163
Neg logit contributions
andro-0.260
inyl-0.198
agers-0.198
endale-0.190
tro-0.189
Token them
Token ID606
Feature activation-5.38e-03

Pos logit contributions
nces+2.041
tenance+1.947
ned+1.722
reath+1.721
 drown+1.667
Neg logit contributions
andro-2.974
inyl-2.311
agers-2.297
endale-2.228
tro-2.214
Token talking
Token ID3375
Feature activation-1.85e+00

Pos logit contributions
nces+0.004
tenance+0.004
reath+0.003
ned+0.003
 Shroud+0.003
Neg logit contributions
andro-0.006
inyl-0.005
agers-0.005
endale-0.005
tro-0.005
Token about
Token ID546
Feature activation+1.53e+00

Pos logit contributions
nces+1.562
tenance+1.511
ned+1.349
reath+1.347
 drown+1.311
Neg logit contributions
andro-1.884
inyl-1.422
agers-1.418
endale-1.366
tro-1.354
Token Alex
Token ID4422
Feature activation+8.10e+00

Pos logit contributions
andro+1.576
inyl+1.190
agers+1.190
tro+1.133
endale+1.133
Neg logit contributions
nces-1.282
tenance-1.243
reath-1.102
ned-1.084
 Shroud-1.045
Tokenei
Token ID20295
Feature activation-1.08e+00

Pos logit contributions
andro+6.261
agers+4.112
inyl+4.092
endale+3.936
tro+3.897
Neg logit contributions
nces-8.789
tenance-8.531
ned-7.792
reath-7.786
 Shroud-7.467
Token Naval
Token ID20818
Feature activation+1.07e+00

Pos logit contributions
nces+0.850
tenance+0.817
reath+0.720
ned+0.718
 drown+0.697
Neg logit contributions
andro-1.165
inyl-0.900
agers-0.894
endale-0.861
tro-0.855
Tokenny
Token ID3281
Feature activation+2.32e+00

Pos logit contributions
andro+1.332
agers+1.064
inyl+1.064
endale+1.030
tro+1.028
Neg logit contributions
nces-0.662
tenance-0.631
reath-0.535
ned-0.528
 drown-0.506
Token.
Token ID13
Feature activation+3.79e-02

Pos logit contributions
andro+2.495
inyl+1.906
agers+1.905
endale+1.843
tro+1.831
Neg logit contributions
nces-1.834
tenance-1.771
reath-1.561
ned-1.544
 drown-1.490
Token The
Token ID383
Feature activation+3.85e-01

Pos logit contributions
andro+0.037
inyl+0.028
agers+0.028
endale+0.026
tro+0.026
Neg logit contributions
nces-0.033
tenance-0.032
reath-0.029
ned-0.029
 drown-0.028
Token WWE
Token ID15247
Feature activation+1.11e+00

Pos logit contributions
andro+0.496
inyl+0.345
agers+0.344
endale+0.326
tro+0.323
Neg logit contributions
nces-0.627
tenance-0.610
reath-0.557
ned-0.554
 drown-0.541
Token is
Token ID318
Feature activation+1.67e+00

Pos logit contributions
andro+1.183
agers+0.903
inyl+0.902
endale+0.866
tro+0.866
Neg logit contributions
nces-0.897
tenance-0.864
reath-0.763
ned-0.755
 drown-0.733
Token still
Token ID991
Feature activation+3.18e+00

Pos logit contributions
andro+1.773
inyl+1.352
agers+1.350
endale+1.298
tro+1.293
Neg logit contributions
nces-1.350
tenance-1.301
reath-1.154
ned-1.143
 drown-1.107
Token advertising
Token ID8560
Feature activation+8.28e-01

Pos logit contributions
andro+3.430
inyl+2.635
agers+2.629
tro+2.530
endale+2.523
Neg logit contributions
nces-2.486
tenance-2.391
reath-2.113
ned-2.081
 drown-2.010
Token that
Token ID326
Feature activation+1.90e+00

Pos logit contributions
andro+0.810
inyl+0.600
agers+0.599
endale+0.574
tro+0.572
Neg logit contributions
nces-0.735
tenance-0.712
reath-0.639
ned-0.632
 drown-0.615
Token Les
Token ID11732
Feature activation+8.06e+00

Pos logit contributions
andro+1.675
inyl+1.196
agers+1.193
endale+1.135
tro+1.129
Neg logit contributions
nces-1.867
tenance-1.812
reath-1.648
ned-1.633
 drown-1.593
Tokennar
Token ID23955
Feature activation+2.34e+00

Pos logit contributions
andro+7.854
agers+5.715
inyl+5.712
tro+5.545
endale+5.440
Neg logit contributions
nces-7.117
tenance-6.882
reath-6.144
 Shroud-5.966
 drown-5.932
Token will
Token ID481
Feature activation+1.32e+00

Pos logit contributions
andro+2.438
inyl+1.847
agers+1.836
endale+1.768
tro+1.758
Neg logit contributions
nces-1.929
tenance-1.853
reath-1.645
ned-1.625
 Shroud-1.571
Token face
Token ID1986
Feature activation-5.71e-01

Pos logit contributions
andro+1.416
inyl+1.084
agers+1.081
endale+1.041
tro+1.036
Neg logit contributions
nces-1.041
tenance-1.000
reath-0.888
ned-0.877
 drown-0.846
Token Randy
Token ID21248
Feature activation+2.60e+00

Pos logit contributions
nces+0.496
tenance+0.479
reath+0.429
ned+0.428
 drown+0.415
Neg logit contributions
andro-0.568
inyl-0.426
agers-0.425
endale-0.408
tro-0.404
Token Or
Token ID1471
Feature activation+1.39e+00

Pos logit contributions
andro+2.199
agers+1.569
inyl+1.515
tro+1.480
ager+1.470
Neg logit contributions
nces-2.668
tenance-2.562
reath-2.350
ned-2.291
 drown-2.230
Token to
Token ID284
Feature activation-2.37e-01

Pos logit contributions
nces+1.404
tenance+1.374
ned+1.198
reath+1.193
 drown+1.140
Neg logit contributions
andro-2.304
inyl-1.817
agers-1.798
endale-1.732
tro-1.710
Token the
Token ID262
Feature activation-3.92e-01

Pos logit contributions
nces+0.199
tenance+0.192
reath+0.171
ned+0.170
 drown+0.165
Neg logit contributions
andro-0.243
inyl-0.183
agers-0.183
endale-0.176
tro-0.175
Token website
Token ID3052
Feature activation-2.83e+00

Pos logit contributions
nces+0.317
tenance+0.306
reath+0.272
ned+0.270
 drown+0.261
Neg logit contributions
andro-0.415
inyl-0.316
agers-0.315
endale-0.303
tro-0.301
Token owned
Token ID6898
Feature activation+2.59e+00

Pos logit contributions
nces+2.269
tenance+2.196
ned+1.956
reath+1.940
 Shroud+1.888
Neg logit contributions
andro-2.995
inyl-2.274
agers-2.264
endale-2.190
tro-2.163
Token by
Token ID416
Feature activation+5.45e-01

Pos logit contributions
andro+2.469
agers+1.822
inyl+1.818
endale+1.736
tro+1.719
Neg logit contributions
nces-2.345
tenance-2.267
reath-2.036
ned-2.004
 drown-1.976
Token Alex
Token ID4422
Feature activation+8.06e+00

Pos logit contributions
andro+0.555
inyl+0.417
agers+0.417
endale+0.400
tro+0.398
Neg logit contributions
nces-0.462
tenance-0.446
reath-0.399
ned-0.395
 drown-0.383
Token Jones
Token ID5437
Feature activation+4.54e+00

Pos logit contributions
andro+8.127
inyl+5.985
agers+5.906
endale+5.807
tro+5.748
Neg logit contributions
nces-6.862
tenance-6.601
reath-5.912
ned-5.817
 drown-5.553
Token that
Token ID326
Feature activation+1.79e+00

Pos logit contributions
andro+4.443
agers+3.282
inyl+3.263
endale+3.156
tro+3.135
Neg logit contributions
nces-4.017
tenance-3.857
reath-3.461
ned-3.408
 drown-3.316
Token propag
Token ID8928
Feature activation+5.48e-01

Pos logit contributions
andro+1.825
inyl+1.381
agers+1.377
endale+1.324
tro+1.317
Neg logit contributions
nces-1.494
tenance-1.449
reath-1.292
ned-1.261
 drown-1.221
Tokenates
Token ID689
Feature activation+1.61e-01

Pos logit contributions
andro+0.587
agers+0.448
inyl+0.448
endale+0.431
tro+0.428
Neg logit contributions
nces-0.434
tenance-0.421
reath-0.371
ned-0.367
 drown-0.356
Token conspiracy
Token ID10086
Feature activation+2.67e+00

Pos logit contributions
andro+0.176
inyl+0.135
agers+0.135
endale+0.130
tro+0.130
Neg logit contributions
nces-0.124
tenance-0.119
reath-0.105
ned-0.104
 drown-0.101
Token parade
Token ID16134
Feature activation+3.67e+00

Pos logit contributions
nces+0.164
tenance+0.158
reath+0.140
ned+0.139
 drown+0.135
Neg logit contributions
andro-0.211
inyl-0.160
agers-0.160
endale-0.154
tro-0.153
Token during
Token ID1141
Feature activation-3.60e+00

Pos logit contributions
andro+3.712
agers+2.814
inyl+2.774
tro+2.712
endale+2.685
Neg logit contributions
nces-3.080
tenance-2.965
reath-2.655
ned-2.596
 Shroud-2.509
Token a
Token ID257
Feature activation-6.06e-02

Pos logit contributions
nces+2.926
tenance+2.824
reath+2.537
ned+2.514
 drown+2.431
Neg logit contributions
andro-3.750
inyl-2.844
agers-2.839
endale-2.734
tro-2.687
Token ceremony
Token ID10542
Feature activation+8.23e-01

Pos logit contributions
nces+0.046
tenance+0.044
reath+0.038
ned+0.038
 drown+0.037
Neg logit contributions
andro-0.068
inyl-0.052
agers-0.052
endale-0.050
tro-0.050
Token South
Token ID2520
Feature activation-2.02e+00

Pos logit contributions
andro+0.843
inyl+0.636
agers+0.635
endale+0.612
tro+0.610
Neg logit contributions
nces-0.692
tenance-0.666
reath-0.594
ned-0.588
 drown-0.571
Token Sudan
Token ID19610
Feature activation-1.01e+01

Pos logit contributions
nces+1.311
tenance+1.253
reath+1.077
ned+1.066
 drown+1.022
Neg logit contributions
andro-2.448
inyl-1.941
agers-1.937
endale-1.876
tro-1.868
Token
Token ID447
Feature activation-3.52e-01

Pos logit contributions
nces+7.390
tenance+7.136
ned+6.576
reath+6.509
 Shroud+6.223
Neg logit contributions
andro-10.464
inyl-8.055
agers-7.993
endale-7.625
ager-7.556
Token
Token ID247
Feature activation+2.19e-01

Pos logit contributions
nces+0.232
tenance+0.220
reath+0.192
ned+0.190
 drown+0.180
Neg logit contributions
andro-0.423
inyl-0.335
agers-0.334
tro-0.323
endale-0.322
Tokens
Token ID82
Feature activation-7.49e-01

Pos logit contributions
andro+0.142
inyl+0.087
agers+0.087
endale+0.080
tro+0.079
Neg logit contributions
nces-0.266
tenance-0.260
reath-0.241
ned-0.240
 drown-0.235
Token first
Token ID717
Feature activation-6.81e-01

Pos logit contributions
nces+0.540
tenance+0.518
reath+0.453
ned+0.447
 drown+0.432
Neg logit contributions
andro-0.858
inyl-0.669
agers-0.668
endale-0.646
tro-0.644
Token Independence
Token ID20153
Feature activation+1.74e+00

Pos logit contributions
nces+0.522
tenance+0.502
reath+0.442
ned+0.438
 drown+0.423
Neg logit contributions
andro-0.750
inyl-0.578
agers-0.577
endale-0.557
tro-0.554
Tokenuba
Token ID22013
Feature activation-7.01e+00

Pos logit contributions
nces+0.674
tenance+0.616
reath+0.576
ned+0.571
bug+0.533
Neg logit contributions
andro-1.141
inyl-0.911
agers-0.876
endale-0.864
tro-0.860
Token.
Token ID13
Feature activation-7.29e-01

Pos logit contributions
nces+5.346
tenance+5.220
reath+4.671
ned+4.634
 Shroud+4.418
Neg logit contributions
andro-7.402
agers-5.700
inyl-5.685
tro-5.394
endale-5.372
Token
Token ID198
Feature activation-5.50e-01

Pos logit contributions
nces+0.632
tenance+0.613
reath+0.548
ned+0.545
 Shroud+0.527
Neg logit contributions
andro-0.728
inyl-0.545
agers-0.544
endale-0.521
tro-0.515
Token
Token ID198
Feature activation-6.21e-01

Pos logit contributions
nces+0.466
tenance+0.457
ned+0.409
reath+0.407
 drown+0.390
Neg logit contributions
andro-0.555
inyl-0.418
agers-0.415
endale-0.399
tro-0.393
TokenSouth
Token ID14942
Feature activation-3.10e+00

Pos logit contributions
nces+0.549
tenance+0.532
reath+0.478
ned+0.477
 drown+0.458
Neg logit contributions
andro-0.607
inyl-0.453
agers-0.450
endale-0.432
tro-0.426
Token Sudan
Token ID19610
Feature activation-9.99e+00

Pos logit contributions
nces+1.967
tenance+1.882
reath+1.610
ned+1.600
 drown+1.535
Neg logit contributions
andro-3.809
inyl-3.027
agers-3.014
endale-2.928
tro-2.904
Tokenese
Token ID2771
Feature activation-2.61e+00

Pos logit contributions
nces+7.083
tenance+6.956
reath+6.297
ned+6.293
 drown+5.969
Neg logit contributions
andro-10.548
inyl-8.192
agers-8.085
endale-7.712
ager-7.619
Token military
Token ID2422
Feature activation-2.01e-01

Pos logit contributions
nces+1.947
tenance+1.870
reath+1.645
ned+1.638
 drown+1.582
Neg logit contributions
andro-2.914
inyl-2.265
agers-2.250
endale-2.178
tro-2.148
Token parade
Token ID16134
Feature activation+3.67e+00

Pos logit contributions
nces+0.164
tenance+0.158
reath+0.140
ned+0.139
 drown+0.135
Neg logit contributions
andro-0.211
inyl-0.160
agers-0.160
endale-0.154
tro-0.153
Token during
Token ID1141
Feature activation-3.60e+00

Pos logit contributions
andro+3.712
agers+2.814
inyl+2.774
tro+2.712
endale+2.685
Neg logit contributions
nces-3.080
tenance-2.965
reath-2.655
ned-2.596
 Shroud-2.509
Token a
Token ID257
Feature activation-6.06e-02

Pos logit contributions
nces+2.926
tenance+2.824
reath+2.537
ned+2.514
 drown+2.431
Neg logit contributions
andro-3.750
inyl-2.844
agers-2.839
endale-2.734
tro-2.687
Token in
Token ID287
Feature activation+8.47e-02

Pos logit contributions
andro+0.376
inyl+0.282
agers+0.281
endale+0.271
tro+0.269
Neg logit contributions
nces-0.323
tenance-0.312
reath-0.279
ned-0.277
 drown-0.269
Token J
Token ID449
Feature activation-1.38e+00

Pos logit contributions
andro+0.083
inyl+0.062
agers+0.062
endale+0.059
tro+0.059
Neg logit contributions
nces-0.075
tenance-0.073
reath-0.065
ned-0.065
 drown-0.063
Tokenuba
Token ID22013
Feature activation-7.54e+00

Pos logit contributions
nces+0.974
tenance+0.925
reath+0.841
ned+0.832
bug+0.786
Neg logit contributions
andro-1.552
inyl-1.226
agers-1.198
endale-1.170
tro-1.167
Token,
Token ID11
Feature activation-1.21e-01

Pos logit contributions
nces+5.612
tenance+5.527
reath+4.958
ned+4.909
 Shroud+4.711
Neg logit contributions
andro-8.024
agers-6.158
inyl-6.143
tro-5.813
endale-5.797
Token South
Token ID2520
Feature activation-2.32e+00

Pos logit contributions
nces+0.101
tenance+0.097
reath+0.087
ned+0.086
 drown+0.084
Neg logit contributions
andro-0.124
inyl-0.094
agers-0.094
endale-0.090
tro-0.089
Token Sudan
Token ID19610
Feature activation-9.99e+00

Pos logit contributions
nces+1.427
tenance+1.367
reath+1.168
ned+1.164
 drown+1.120
Neg logit contributions
andro-2.864
inyl-2.286
agers-2.270
endale-2.211
tro-2.195
Token.
Token ID13
Feature activation-7.26e-01

Pos logit contributions
nces+7.033
tenance+7.027
ned+6.305
reath+6.268
 Shroud+5.994
Neg logit contributions
andro-10.589
inyl-8.160
agers-8.095
endale-7.705
tro-7.602
Token (
Token ID357
Feature activation-1.38e-01

Pos logit contributions
nces+0.618
tenance+0.598
reath+0.535
ned+0.530
 drown+0.514
Neg logit contributions
andro-0.736
inyl-0.553
agers-0.552
endale-0.529
tro-0.525
TokenPhoto
Token ID6191
Feature activation+1.04e+00

Pos logit contributions
nces+0.129
tenance+0.125
reath+0.113
ned+0.112
 drown+0.109
Neg logit contributions
andro-0.129
inyl-0.094
agers-0.094
endale-0.090
tro-0.089
Token by
Token ID416
Feature activation+3.44e-01

Pos logit contributions
andro+1.045
inyl+0.784
agers+0.783
endale+0.751
tro+0.749
Neg logit contributions
nces-0.895
tenance-0.866
reath-0.773
ned-0.764
 drown-0.745
Token Paula
Token ID36025
Feature activation+2.26e+00

Pos logit contributions
andro+0.350
inyl+0.263
agers+0.263
endale+0.252
tro+0.251
Neg logit contributions
nces-0.291
tenance-0.281
reath-0.251
ned-0.249
 drown-0.241
Token by
Token ID416
Feature activation+9.24e-01

Pos logit contributions
nces+1.575
tenance+1.527
ned+1.372
reath+1.366
 drown+1.320
Neg logit contributions
andro-1.935
inyl-1.457
agers-1.455
endale-1.399
tro-1.390
Token Osama
Token ID29236
Feature activation-6.43e+00

Pos logit contributions
andro+0.966
agers+0.733
inyl+0.730
endale+0.703
tro+0.702
Neg logit contributions
nces-0.759
tenance-0.732
reath-0.647
ned-0.636
 drown-0.621
Token bin
Token ID9874
Feature activation-9.69e+00

Pos logit contributions
tenance+2.696
nces+2.684
ned+2.237
reath+2.193
 Shroud+2.078
Neg logit contributions
andro-8.797
inyl-7.292
agers-7.203
endale-7.102
tro-7.069
Token Laden
Token ID19402
Feature activation-6.60e+00

Pos logit contributions
nces+1.560
tenance+1.458
ned+1.137
reath+0.742
 Laden+0.710
Neg logit contributions
andro-15.487
inyl-13.288
agers-13.131
endale-13.058
tro-12.901
Token and
Token ID290
Feature activation-7.33e-01

Pos logit contributions
nces+4.878
tenance+4.786
ned+4.304
reath+4.228
 drown+4.099
Neg logit contributions
andro-7.028
inyl-5.468
agers-5.354
tro-5.209
endale-5.200
Token Saddam
Token ID24277
Feature activation-9.94e+00

Pos logit contributions
nces+0.580
tenance+0.559
reath+0.495
ned+0.491
 drown+0.475
Neg logit contributions
andro-0.788
inyl-0.603
agers-0.602
endale-0.580
tro-0.577
Token Hussein
Token ID22983
Feature activation-7.74e+00

Pos logit contributions
nces+3.351
tenance+3.335
ned+2.632
reath+2.573
 Shroud+2.367
Neg logit contributions
andro-14.266
inyl-11.877
agers-11.742
endale-11.495
tro-11.468
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
nces+5.708
tenance+5.595
ned+5.036
reath+4.992
 drown+4.774
Neg logit contributions
andro-8.174
inyl-6.361
agers-6.254
tro-6.045
endale-6.025
Token
Token ID198
Feature activation-2.28e-01

Pos logit contributions
nces+0.164
tenance+0.159
reath+0.143
ned+0.141
 drown+0.138
Neg logit contributions
andro-0.184
inyl-0.137
agers-0.137
endale-0.131
tro-0.130
Token
Token ID198
Feature activation-3.92e-01

Pos logit contributions
nces+0.195
tenance+0.190
ned+0.170
reath+0.170
 drown+0.163
Neg logit contributions
andro-0.230
inyl-0.173
agers-0.172
endale-0.165
tro-0.163
Token1995
Token ID21908
Feature activation+5.43e-01

Pos logit contributions
nces+0.357
tenance+0.346
reath+0.311
ned+0.310
 drown+0.300
Neg logit contributions
andro-0.374
inyl-0.276
agers-0.275
endale-0.263
tro-0.261
Token or
Token ID393
Feature activation-7.00e-01

Pos logit contributions
nces+0.329
tenance+0.318
reath+0.282
ned+0.280
 drown+0.272
Neg logit contributions
andro-0.433
inyl-0.330
agers-0.328
endale-0.316
tro-0.314
Token chemical
Token ID5931
Feature activation-1.55e+00

Pos logit contributions
nces+0.512
tenance+0.492
reath+0.432
ned+0.428
 drown+0.413
Neg logit contributions
andro-0.793
inyl-0.617
agers-0.616
endale-0.595
tro-0.592
Token weapons
Token ID3777
Feature activation-1.89e+00

Pos logit contributions
nces+1.212
tenance+1.173
reath+1.041
ned+1.038
 drown+1.006
Neg logit contributions
andro-1.671
inyl-1.279
agers-1.274
endale-1.231
tro-1.221
Token by
Token ID416
Feature activation+9.24e-01

Pos logit contributions
nces+1.575
tenance+1.527
ned+1.372
reath+1.366
 drown+1.320
Neg logit contributions
andro-1.935
inyl-1.457
agers-1.455
endale-1.399
tro-1.390
Token Osama
Token ID29236
Feature activation-6.43e+00

Pos logit contributions
andro+0.966
agers+0.733
inyl+0.730
endale+0.703
tro+0.702
Neg logit contributions
nces-0.759
tenance-0.732
reath-0.647
ned-0.636
 drown-0.621
Token bin
Token ID9874
Feature activation-9.69e+00

Pos logit contributions
tenance+2.696
nces+2.684
ned+2.237
reath+2.193
 Shroud+2.078
Neg logit contributions
andro-8.797
inyl-7.292
agers-7.203
endale-7.102
tro-7.069
Token Laden
Token ID19402
Feature activation-6.60e+00

Pos logit contributions
nces+1.560
tenance+1.458
ned+1.137
reath+0.742
 Laden+0.710
Neg logit contributions
andro-15.487
inyl-13.288
agers-13.131
endale-13.058
tro-12.901
Token and
Token ID290
Feature activation-7.33e-01

Pos logit contributions
nces+4.878
tenance+4.786
ned+4.304
reath+4.228
 drown+4.099
Neg logit contributions
andro-7.028
inyl-5.468
agers-5.354
tro-5.209
endale-5.200
Token Saddam
Token ID24277
Feature activation-9.94e+00

Pos logit contributions
nces+0.580
tenance+0.559
reath+0.495
ned+0.491
 drown+0.475
Neg logit contributions
andro-0.788
inyl-0.603
agers-0.602
endale-0.580
tro-0.577
Token Hussein
Token ID22983
Feature activation-7.74e+00

Pos logit contributions
nces+3.351
tenance+3.335
ned+2.632
reath+2.573
 Shroud+2.367
Neg logit contributions
andro-14.266
inyl-11.877
agers-11.742
endale-11.495
tro-11.468
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
nces+5.708
tenance+5.595
ned+5.036
reath+4.992
 drown+4.774
Neg logit contributions
andro-8.174
inyl-6.361
agers-6.254
tro-6.045
endale-6.025
Token the
Token ID262
Feature activation-4.15e-01

Pos logit contributions
andro+0.192
inyl+0.146
agers+0.146
endale+0.140
tro+0.139
Neg logit contributions
nces-0.151
tenance-0.146
reath-0.130
ned-0.129
 drown-0.125
Token presidential
Token ID4787
Feature activation-2.13e+00

Pos logit contributions
nces+0.331
tenance+0.319
reath+0.283
ned+0.280
 drown+0.271
Neg logit contributions
andro-0.444
inyl-0.339
agers-0.339
endale-0.326
tro-0.324
Token guards
Token ID10942
Feature activation+1.22e+00

Pos logit contributions
nces+1.684
tenance+1.633
reath+1.447
ned+1.439
 drown+1.387
Neg logit contributions
andro-2.270
inyl-1.737
agers-1.728
endale-1.669
tro-1.646
Token of
Token ID286
Feature activation-1.54e+00

Pos logit contributions
andro+1.255
agers+0.945
inyl+0.944
endale+0.907
tro+0.902
Neg logit contributions
nces-1.032
tenance-0.995
reath-0.889
ned-0.880
 drown-0.855
Token South
Token ID2520
Feature activation-1.14e+00

Pos logit contributions
nces+1.216
tenance+1.172
reath+1.039
ned+1.032
 drown+0.996
Neg logit contributions
andro-1.658
inyl-1.272
agers-1.266
endale-1.220
tro-1.211
Token Sudan
Token ID19610
Feature activation-9.55e+00

Pos logit contributions
nces+0.748
tenance+0.715
reath+0.616
ned+0.609
 drown+0.585
Neg logit contributions
andro-1.377
inyl-1.090
agers-1.088
endale-1.054
tro-1.049
Token
Token ID447
Feature activation-3.47e-01

Pos logit contributions
nces+6.211
tenance+6.132
reath+5.480
ned+5.471
 Shroud+5.137
Neg logit contributions
andro-10.711
inyl-8.503
agers-8.344
tro-8.006
endale-8.002
Token
Token ID247
Feature activation+4.25e-01

Pos logit contributions
nces+0.273
tenance+0.262
reath+0.233
ned+0.230
 Shroud+0.221
Neg logit contributions
andro-0.374
inyl-0.287
agers-0.287
tro-0.276
endale-0.274
Tokens
Token ID82
Feature activation-7.14e-01

Pos logit contributions
andro+0.426
inyl+0.319
agers+0.318
endale+0.306
tro+0.305
Neg logit contributions
nces-0.367
tenance-0.354
reath-0.317
ned-0.314
 drown-0.306
Token president
Token ID1893
Feature activation-4.05e+00

Pos logit contributions
nces+0.574
tenance+0.553
reath+0.491
ned+0.484
 drown+0.471
Neg logit contributions
andro-0.759
inyl-0.579
agers-0.579
endale-0.557
tro-0.554
Token,
Token ID11
Feature activation-3.46e-01

Pos logit contributions
nces+3.317
tenance+3.171
ned+2.856
reath+2.852
 Shroud+2.741
Neg logit contributions
andro-4.175
inyl-3.179
agers-3.133
endale-3.025
tro-3.012
Token and
Token ID290
Feature activation-4.67e-01

Pos logit contributions
andro+0.467
inyl+0.352
agers+0.350
endale+0.336
tro+0.334
Neg logit contributions
nces-0.395
tenance-0.381
reath-0.342
ned-0.341
 drown-0.330
Token are
Token ID389
Feature activation+9.33e-02

Pos logit contributions
nces+0.386
tenance+0.373
reath+0.332
ned+0.330
 drown+0.320
Neg logit contributions
andro-0.486
inyl-0.368
agers-0.367
endale-0.353
tro-0.351
Token rejected
Token ID8606
Feature activation-1.31e+00

Pos logit contributions
andro+0.095
inyl+0.072
agers+0.072
endale+0.069
tro+0.068
Neg logit contributions
nces-0.079
tenance-0.076
reath-0.068
ned-0.067
 drown-0.065
Token by
Token ID416
Feature activation+9.40e-01

Pos logit contributions
nces+1.126
tenance+1.082
reath+0.981
ned+0.980
 drown+0.942
Neg logit contributions
andro-1.314
inyl-0.987
agers-0.979
tro-0.938
endale-0.937
Token both
Token ID1111
Feature activation-1.65e+00

Pos logit contributions
andro+0.946
agers+0.712
inyl+0.708
endale+0.682
tro+0.676
Neg logit contributions
nces-0.805
tenance-0.779
reath-0.695
ned-0.684
 drown-0.668
Token Burma
Token ID40306
Feature activation-9.45e+00

Pos logit contributions
nces+1.344
tenance+1.292
ned+1.165
reath+1.160
 drown+1.118
Neg logit contributions
andro-1.733
inyl-1.319
agers-1.313
tro-1.259
endale-1.259
Token and
Token ID290
Feature activation-7.13e-01

Pos logit contributions
nces+6.617
tenance+6.344
reath+5.758
ned+5.734
 Shroud+5.442
Neg logit contributions
andro-10.300
inyl-8.089
agers-7.971
tro-7.674
endale-7.656
Token neighbouring
Token ID29272
Feature activation-4.97e+00

Pos logit contributions
nces+0.505
tenance+0.485
reath+0.425
ned+0.422
 drown+0.405
Neg logit contributions
andro-0.824
inyl-0.646
agers-0.643
endale-0.620
tro-0.619
Token Bangladesh
Token ID19483
Feature activation-6.17e+00

Pos logit contributions
nces+2.904
tenance+2.831
ned+2.499
reath+2.459
 drown+2.351
Neg logit contributions
andro-6.126
inyl-4.966
agers-4.874
endale-4.748
tro-4.736
Token.
Token ID13
Feature activation-1.84e-01

Pos logit contributions
nces+4.751
tenance+4.567
ned+4.177
reath+4.138
 drown+3.911
Neg logit contributions
andro-6.435
inyl-5.019
agers-4.927
endale-4.738
tro-4.722
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
nces+0.161
tenance+0.156
reath+0.139
ned+0.139
 drown+0.134
Neg logit contributions
andro-0.182
inyl-0.136
agers-0.136
endale-0.130
tro-0.129
Token former
Token ID1966
Feature activation-4.27e-01

Pos logit contributions
andro+1.770
agers+1.334
inyl+1.331
endale+1.284
tro+1.278
Neg logit contributions
nces-1.422
tenance-1.378
reath-1.221
ned-1.200
 drown-1.167
Token President
Token ID1992
Feature activation-2.99e+00

Pos logit contributions
nces+0.313
tenance+0.301
reath+0.263
ned+0.261
 drown+0.252
Neg logit contributions
andro-0.483
inyl-0.376
agers-0.375
endale-0.362
tro-0.361
Token Barack
Token ID8732
Feature activation-5.40e+00

Pos logit contributions
nces+2.098
tenance+2.020
ned+1.779
reath+1.775
 drown+1.696
Neg logit contributions
andro-3.400
inyl-2.685
agers-2.664
endale-2.594
tro-2.578
Token Obama
Token ID2486
Feature activation-4.44e+00

Pos logit contributions
nces+3.464
tenance+3.443
ned+3.027
reath+2.998
 Shroud+2.875
Neg logit contributions
andro-6.225
inyl-5.030
agers-4.979
endale-4.812
tro-4.791
Token Barack
Token ID8732
Feature activation-6.04e+00

Pos logit contributions
nces+3.518
tenance+3.395
reath+3.052
ned+3.033
 drown+2.953
Neg logit contributions
andro-4.622
agers-3.557
inyl-3.554
tro-3.399
endale-3.381
Token Hussein
Token ID22983
Feature activation-9.34e+00

Pos logit contributions
nces+1.180
tenance+1.134
ned+0.720
reath+0.597
 Shroud+0.427
Neg logit contributions
andro-9.762
inyl-8.348
agers-8.289
tro-8.168
endale-8.065
Token Obama
Token ID2486
Feature activation-4.81e+00

Pos logit contributions
tenance+5.327
nces+5.113
reath+4.925
ned+4.479
 drown+4.325
Neg logit contributions
andro-11.161
inyl-9.005
agers-8.859
tro-8.702
endale-8.583
TokenWith
Token ID3152
Feature activation+1.05e+00

Pos logit contributions
nces+3.868
tenance+3.814
reath+3.493
ned+3.405
 drown+3.307
Neg logit contributions
andro-4.823
inyl-3.695
agers-3.639
endale-3.522
tro-3.494
Token low
Token ID1877
Feature activation+2.48e-01

Pos logit contributions
andro+1.102
inyl+0.842
agers+0.837
endale+0.811
tro+0.802
Neg logit contributions
nces-0.857
tenance-0.827
reath-0.732
ned-0.730
 drown-0.700
Token birth
Token ID4082
Feature activation-1.37e+00

Pos logit contributions
andro+0.252
agers+0.191
inyl+0.190
endale+0.182
tro+0.180
Neg logit contributions
nces-0.210
tenance-0.204
reath-0.182
ned-0.181
 drown-0.177
Token rate
Token ID2494
Feature activation+2.09e-01

Pos logit contributions
nces+0.998
tenance+0.954
ned+0.848
reath+0.844
 drown+0.815
Neg logit contributions
andro-1.541
inyl-1.198
agers-1.197
endale-1.159
tro-1.147
Token
Token ID198
Feature activation-5.08e-01

Pos logit contributions
nces+0.303
tenance+0.298
ned+0.267
reath+0.264
 Shroud+0.253
Neg logit contributions
andro-0.363
inyl-0.274
agers-0.272
endale-0.262
tro-0.258
TokenThe
Token ID464
Feature activation-7.14e-01

Pos logit contributions
nces+0.454
tenance+0.443
reath+0.398
ned+0.398
 drown+0.381
Neg logit contributions
andro-0.489
inyl-0.364
agers-0.361
endale-0.347
tro-0.342
Token traditionally
Token ID16083
Feature activation+1.02e+00

Pos logit contributions
nces+0.570
tenance+0.551
reath+0.491
ned+0.487
 drown+0.471
Neg logit contributions
andro-0.758
inyl-0.578
agers-0.577
endale-0.557
tro-0.552
Token designed
Token ID3562
Feature activation-2.02e+00

Pos logit contributions
andro+1.047
inyl+0.788
agers+0.788
endale+0.755
tro+0.752
Neg logit contributions
nces-0.865
tenance-0.835
reath-0.745
ned-0.737
 drown-0.716
Token stone
Token ID7815
Feature activation+2.11e+00

Pos logit contributions
nces+1.592
tenance+1.543
reath+1.375
ned+1.368
 drown+1.322
Neg logit contributions
andro-2.156
inyl-1.655
agers-1.646
endale-1.595
tro-1.579
Token mug
Token ID25152
Feature activation-9.30e+00

Pos logit contributions
andro+2.274
agers+1.739
inyl+1.733
tro+1.671
endale+1.666
Neg logit contributions
nces-1.682
tenance-1.609
reath-1.410
ned-1.392
 drown-1.352
Token costs
Token ID3484
Feature activation-3.54e-01

Pos logit contributions
nces+6.882
tenance+6.772
ned+6.233
reath+6.170
 drown+6.026
Neg logit contributions
andro-9.544
inyl-7.288
agers-7.217
endale-7.054
tro-6.838
Token 16
Token ID1467
Feature activation+3.09e-01

Pos logit contributions
nces+0.331
tenance+0.321
reath+0.291
ned+0.290
 drown+0.281
Neg logit contributions
andro-0.328
inyl-0.240
agers-0.238
endale-0.228
tro-0.226
Token euros
Token ID21138
Feature activation+1.29e+00

Pos logit contributions
andro+0.310
inyl+0.232
agers+0.232
endale+0.222
tro+0.222
Neg logit contributions
nces-0.266
tenance-0.257
reath-0.230
ned-0.227
 drown-0.221
Token ($
Token ID7198
Feature activation+7.86e-01

Pos logit contributions
andro+1.263
inyl+0.937
agers+0.935
endale+0.898
tro+0.894
Neg logit contributions
nces-1.149
tenance-1.112
reath-0.995
ned-0.981
 drown-0.959
Token18
Token ID1507
Feature activation-5.41e-01

Pos logit contributions
andro+0.750
inyl+0.550
agers+0.550
endale+0.525
tro+0.524
Neg logit contributions
nces-0.720
tenance-0.693
reath-0.626
ned-0.619
 drown-0.606
Token.
Token ID13
Feature activation-6.47e-01

Pos logit contributions
andro+1.074
agers+0.806
inyl+0.800
endale+0.771
tro+0.770
Neg logit contributions
nces-0.907
tenance-0.870
reath-0.781
ned-0.771
 drown-0.759
Token2015
Token ID4626
Feature activation+2.12e-01

Pos logit contributions
nces+0.550
tenance+0.533
reath+0.477
ned+0.473
 drown+0.458
Neg logit contributions
andro-0.656
inyl-0.494
agers-0.493
endale-0.473
tro-0.470
Token).
Token ID737
Feature activation-9.44e-01

Pos logit contributions
andro+0.238
inyl+0.184
agers+0.184
endale+0.178
tro+0.176
Neg logit contributions
nces-0.158
tenance-0.152
reath-0.133
ned-0.132
 drown-0.128
Token The
Token ID383
Feature activation+2.34e-02

Pos logit contributions
nces+0.808
tenance+0.792
reath+0.707
ned+0.705
 Shroud+0.684
Neg logit contributions
andro-0.942
inyl-0.707
agers-0.706
endale-0.678
tro-0.669
Token hefty
Token ID29784
Feature activation+3.40e+00

Pos logit contributions
andro+0.024
inyl+0.018
agers+0.018
endale+0.017
tro+0.017
Neg logit contributions
nces-0.020
tenance-0.019
reath-0.017
ned-0.017
 drown-0.017
Token mug
Token ID25152
Feature activation-9.24e+00

Pos logit contributions
andro+3.426
inyl+2.579
agers+2.563
tro+2.463
endale+2.447
Neg logit contributions
nces-2.933
tenance-2.819
reath-2.513
ned-2.468
 drown-2.405
Token is
Token ID318
Feature activation+1.08e+00

Pos logit contributions
nces+6.986
tenance+6.837
ned+6.377
reath+6.310
 drown+6.040
Neg logit contributions
andro-9.320
inyl-7.100
agers-7.083
endale-6.852
tro-6.586
Token em
Token ID795
Feature activation-2.14e+00

Pos logit contributions
andro+1.100
inyl+0.827
agers+0.825
endale+0.791
tro+0.790
Neg logit contributions
nces-0.922
tenance-0.890
reath-0.794
ned-0.785
 drown-0.762
Tokenbl
Token ID2436
Feature activation-5.13e+00

Pos logit contributions
nces+1.372
tenance+1.304
ned+1.139
reath+1.136
 Shroud+1.075
Neg logit contributions
andro-2.597
agers-2.070
inyl-2.061
endale-2.002
tro-1.978
Tokenazon
Token ID5168
Feature activation-7.03e-01

Pos logit contributions
nces+2.545
tenance+2.487
ned+2.153
reath+2.133
 Shroud+1.894
Neg logit contributions
andro-6.741
inyl-5.509
agers-5.508
endale-5.233
ager-5.219
Tokened
Token ID276
Feature activation+1.21e-01

Pos logit contributions
nces+0.819
tenance+0.801
ned+0.744
reath+0.741
 drown+0.721
Neg logit contributions
andro-0.490
inyl-0.312
agers-0.311
endale-0.291
tro-0.286
Token euros
Token ID21138
Feature activation+4.10e-01

Pos logit contributions
nces+0.884
tenance+0.851
reath+0.759
ned+0.755
 drown+0.730
Neg logit contributions
andro-1.120
inyl-0.850
agers-0.846
endale-0.815
tro-0.808
Token.
Token ID13
Feature activation-5.57e-01

Pos logit contributions
andro+0.412
inyl+0.308
agers+0.308
endale+0.296
tro+0.294
Neg logit contributions
nces-0.354
tenance-0.342
reath-0.306
ned-0.303
 drown-0.295
Token A
Token ID317
Feature activation-3.99e-01

Pos logit contributions
nces+0.486
tenance+0.474
reath+0.423
ned+0.422
 drown+0.408
Neg logit contributions
andro-0.551
inyl-0.411
agers-0.409
endale-0.393
tro-0.389
Token Bav
Token ID37313
Feature activation-2.76e+00

Pos logit contributions
nces+0.315
tenance+0.303
reath+0.269
ned+0.266
 drown+0.258
Neg logit contributions
andro-0.429
inyl-0.329
agers-0.328
endale-0.316
tro-0.315
Tokenarian
Token ID3699
Feature activation+6.64e-01

Pos logit contributions
nces+2.034
tenance+1.962
reath+1.737
ned+1.721
 drown+1.650
Neg logit contributions
andro-3.086
inyl-2.403
agers-2.391
endale-2.298
tro-2.278
Token mug
Token ID25152
Feature activation-9.09e+00

Pos logit contributions
andro+0.702
agers+0.535
inyl+0.535
endale+0.513
tro+0.512
Neg logit contributions
nces-0.539
tenance-0.518
reath-0.460
ned-0.454
 drown-0.440
Token holds
Token ID6622
Feature activation-1.12e-01

Pos logit contributions
nces+7.106
tenance+7.035
ned+6.448
reath+6.330
 drown+6.189
Neg logit contributions
andro-9.064
inyl-6.883
agers-6.617
endale-6.462
tro-6.379
Token a
Token ID257
Feature activation-4.28e-01

Pos logit contributions
nces+0.096
tenance+0.093
reath+0.083
ned+0.082
 drown+0.080
Neg logit contributions
andro-0.114
inyl-0.086
agers-0.085
endale-0.082
tro-0.081
Token full
Token ID1336
Feature activation+3.03e+00

Pos logit contributions
nces+0.358
tenance+0.346
reath+0.309
ned+0.306
 drown+0.297
Neg logit contributions
andro-0.441
inyl-0.333
agers-0.332
endale-0.319
tro-0.317
Token liter
Token ID4187
Feature activation-2.20e+00

Pos logit contributions
andro+2.985
agers+2.240
inyl+2.226
tro+2.132
endale+2.129
Neg logit contributions
nces-2.678
tenance-2.551
reath-2.286
ned-2.263
 drown-2.189
Token of
Token ID286
Feature activation-1.39e+00

Pos logit contributions
nces+1.780
tenance+1.723
reath+1.537
ned+1.532
 drown+1.481
Neg logit contributions
andro-2.317
inyl-1.762
agers-1.745
endale-1.691
tro-1.680
Token 2
Token ID362
Feature activation-4.44e-01

Pos logit contributions
nces+0.440
tenance+0.425
reath+0.382
ned+0.380
 drown+0.369
Neg logit contributions
andro-0.491
inyl-0.365
agers-0.364
endale-0.349
tro-0.347
Token,
Token ID11
Feature activation+4.13e-03

Pos logit contributions
nces+0.373
tenance+0.360
reath+0.321
ned+0.321
 drown+0.310
Neg logit contributions
andro-0.456
agers-0.344
inyl-0.344
endale-0.330
tro-0.326
Token000
Token ID830
Feature activation+1.27e+00

Pos logit contributions
andro+0.004
inyl+0.003
agers+0.003
endale+0.002
tro+0.002
Neg logit contributions
nces-0.004
tenance-0.004
reath-0.004
ned-0.004
 drown-0.003
Token from
Token ID422
Feature activation-6.25e-01

Pos logit contributions
andro+1.280
inyl+0.965
agers+0.958
tro+0.920
endale+0.920
Neg logit contributions
nces-1.083
tenance-1.050
reath-0.937
ned-0.925
 drown-0.898
Token the
Token ID262
Feature activation-3.35e-01

Pos logit contributions
nces+0.528
tenance+0.509
reath+0.455
ned+0.452
 drown+0.438
Neg logit contributions
andro-0.638
inyl-0.480
agers-0.480
endale-0.461
tro-0.458
Token Brune
Token ID46070
Feature activation-9.07e+00

Pos logit contributions
nces+0.259
tenance+0.249
reath+0.220
ned+0.218
 drown+0.211
Neg logit contributions
andro-0.365
inyl-0.281
agers-0.281
endale-0.270
tro-0.269
Tokeni
Token ID72
Feature activation-2.86e+00

Pos logit contributions
nces+8.047
tenance+8.010
ned+7.516
reath+7.467
selage+6.970
Neg logit contributions
andro-7.681
agers-5.509
inyl-5.487
endale-5.234
tro-5.226
Token Currency
Token ID20113
Feature activation-2.60e+00

Pos logit contributions
nces+2.182
tenance+2.099
ned+1.853
reath+1.848
 Shroud+1.784
Neg logit contributions
andro-3.126
agers-2.409
inyl-2.406
endale-2.333
tro-2.303
Token and
Token ID290
Feature activation-7.22e-01

Pos logit contributions
nces+1.909
tenance+1.835
ned+1.606
reath+1.602
 Shroud+1.544
Neg logit contributions
andro-2.923
agers-2.269
inyl-2.261
endale-2.191
tro-2.178
Token Monetary
Token ID34112
Feature activation-3.38e+00

Pos logit contributions
nces+0.565
tenance+0.545
reath+0.482
ned+0.477
 drown+0.462
Neg logit contributions
andro-0.781
inyl-0.599
agers-0.599
endale-0.577
tro-0.573
Token Board
Token ID5926
Feature activation-7.65e-02

Pos logit contributions
nces+2.448
tenance+2.381
ned+2.050
reath+2.044
 Shroud+1.989
Neg logit contributions
andro-3.793
inyl-2.967
agers-2.945
endale-2.868
tro-2.824
Token infiltr
Token ID21086
Feature activation-9.78e-02

Pos logit contributions
nces+1.506
tenance+1.460
reath+1.297
ned+1.289
 drown+1.249
Neg logit contributions
andro-2.089
inyl-1.602
agers-1.598
endale-1.536
tro-1.522
Tokenator
Token ID1352
Feature activation-2.95e-02

Pos logit contributions
nces+0.068
tenance+0.066
reath+0.057
ned+0.057
 drown+0.054
Neg logit contributions
andro-0.114
inyl-0.090
agers-0.089
endale-0.086
tro-0.085
Token from
Token ID422
Feature activation-3.53e-01

Pos logit contributions
nces+0.025
tenance+0.024
reath+0.022
ned+0.022
 drown+0.021
Neg logit contributions
andro-0.030
inyl-0.022
agers-0.022
endale-0.021
tro-0.021
Token Syria
Token ID4392
Feature activation-4.25e+00

Pos logit contributions
nces+0.298
tenance+0.289
reath+0.258
ned+0.256
 drown+0.249
Neg logit contributions
andro-0.360
inyl-0.271
agers-0.271
endale-0.259
tro-0.258
Token carrying
Token ID6872
Feature activation-7.09e-02

Pos logit contributions
nces+3.521
tenance+3.429
ned+3.122
reath+3.071
 drown+3.004
Neg logit contributions
andro-4.304
agers-3.235
inyl-3.227
endale-3.089
tro-3.063
Token bin
Token ID9874
Feature activation-9.06e+00

Pos logit contributions
nces+0.058
tenance+0.056
reath+0.050
ned+0.049
 drown+0.048
Neg logit contributions
andro-0.075
inyl-0.057
agers-0.057
endale-0.054
tro-0.054
Tokenocular
Token ID37320
Feature activation-3.55e+00

Pos logit contributions
nces+5.328
tenance+5.144
ned+4.869
reath+4.436
 Shroud+4.311
Neg logit contributions
andro-10.838
agers-8.549
inyl-8.517
endale-8.379
tro-8.206
Tokens
Token ID82
Feature activation-1.24e+00

Pos logit contributions
nces+4.014
tenance+3.965
ned+3.678
reath+3.611
 drown+3.585
Neg logit contributions
andro-2.563
inyl-1.633
agers-1.584
endale-1.537
tro-1.469
Token,
Token ID11
Feature activation+1.86e-01

Pos logit contributions
nces+1.056
tenance+1.021
reath+0.913
ned+0.910
 drown+0.882
Neg logit contributions
andro-1.261
inyl-0.947
agers-0.945
endale-0.908
tro-0.902
Token explosives
Token ID20732
Feature activation-1.23e+00

Pos logit contributions
andro+0.200
inyl+0.153
agers+0.153
endale+0.147
tro+0.147
Neg logit contributions
nces-0.147
tenance-0.142
reath-0.126
ned-0.125
 drown-0.121
Token,
Token ID11
Feature activation-1.36e-01

Pos logit contributions
nces+1.024
tenance+0.989
reath+0.883
ned+0.881
 drown+0.853
Neg logit contributions
andro-1.266
agers-0.953
inyl-0.950
endale-0.918
tro-0.908
Token the
Token ID262
Feature activation-7.34e-01

Pos logit contributions
nces+1.977
tenance+1.906
reath+1.713
ned+1.706
 drown+1.651
Neg logit contributions
andro-2.350
agers-1.763
inyl-1.755
endale-1.699
tro-1.682
Token ob
Token ID909
Feature activation-3.34e+00

Pos logit contributions
nces+0.574
tenance+0.554
reath+0.490
ned+0.486
 drown+0.470
Neg logit contributions
andro-0.795
inyl-0.610
agers-0.609
endale-0.587
tro-0.583
Tokenverse
Token ID4399
Feature activation-2.53e-01

Pos logit contributions
nces+2.068
tenance+1.974
ned+1.719
reath+1.713
 drown+1.583
Neg logit contributions
andro-4.097
agers-3.309
inyl-3.255
endale-3.155
ager-3.135
Token of
Token ID286
Feature activation-1.48e+00

Pos logit contributions
nces+0.212
tenance+0.205
reath+0.182
ned+0.181
 drown+0.175
Neg logit contributions
andro-0.260
inyl-0.196
agers-0.196
endale-0.188
tro-0.187
Token the
Token ID262
Feature activation-2.61e-01

Pos logit contributions
nces+1.269
tenance+1.228
reath+1.101
ned+1.094
 drown+1.059
Neg logit contributions
andro-1.497
inyl-1.122
agers-1.121
endale-1.077
tro-1.070
Token Brune
Token ID46070
Feature activation-9.00e+00

Pos logit contributions
nces+0.185
tenance+0.177
reath+0.154
ned+0.153
 drown+0.147
Neg logit contributions
andro-0.303
inyl-0.237
agers-0.236
endale-0.228
tro-0.227
Tokeni
Token ID72
Feature activation-3.05e+00

Pos logit contributions
tenance+7.718
nces+7.713
ned+7.495
reath+7.298
bug+6.816
Neg logit contributions
andro-7.799
agers-5.701
inyl-5.563
endale-5.394
tro-5.249
Token version
Token ID2196
Feature activation+9.26e-01

Pos logit contributions
nces+2.366
tenance+2.283
ned+2.043
reath+2.042
 Shroud+1.961
Neg logit contributions
andro-3.273
agers-2.519
inyl-2.499
endale-2.425
tro-2.404
Token is
Token ID318
Feature activation+1.41e+00

Pos logit contributions
andro+0.915
inyl+0.681
agers+0.680
endale+0.651
tro+0.647
Neg logit contributions
nces-0.814
tenance-0.788
reath-0.704
ned-0.698
 drown-0.676
Token similar
Token ID2092
Feature activation-2.62e-01

Pos logit contributions
andro+1.450
inyl+1.095
agers+1.092
endale+1.049
tro+1.044
Neg logit contributions
nces-1.184
tenance-1.142
reath-1.017
ned-1.006
 drown-0.975
Token to
Token ID284
Feature activation-1.50e-01

Pos logit contributions
nces+0.205
tenance+0.197
reath+0.175
ned+0.172
 drown+0.167
Neg logit contributions
andro-0.284
inyl-0.218
agers-0.218
endale-0.210
tro-0.209
Token another
Token ID1194
Feature activation-3.14e+00

Pos logit contributions
nces+0.158
tenance+0.153
reath+0.136
ned+0.136
 drown+0.132
Neg logit contributions
andro-0.189
inyl-0.143
agers-0.142
endale-0.137
tro-0.136
Token,
Token ID11
Feature activation+3.05e-01

Pos logit contributions
nces+2.532
tenance+2.442
ned+2.188
reath+2.175
 drown+2.125
Neg logit contributions
andro-3.303
inyl-2.522
agers-2.509
endale-2.424
tro-2.400
Token Abu
Token ID13098
Feature activation-4.19e+00

Pos logit contributions
andro+0.323
inyl+0.246
agers+0.246
endale+0.237
tro+0.235
Neg logit contributions
nces-0.246
tenance-0.237
reath-0.210
ned-0.208
 drown-0.202
Token Sin
Token ID10884
Feature activation+9.14e-01

Pos logit contributions
nces+3.313
tenance+3.215
ned+2.911
reath+2.861
 Shroud+2.765
Neg logit contributions
andro-4.379
inyl-3.347
agers-3.310
endale-3.231
tro-3.185
Tokenan
Token ID272
Feature activation-4.35e-01

Pos logit contributions
andro+0.922
inyl+0.691
agers+0.690
endale+0.662
tro+0.658
Neg logit contributions
nces-0.785
tenance-0.758
reath-0.678
ned-0.670
 drown-0.652
Token bin
Token ID9874
Feature activation-8.99e+00

Pos logit contributions
nces+0.344
tenance+0.331
reath+0.294
ned+0.292
 drown+0.282
Neg logit contributions
andro-0.467
inyl-0.357
agers-0.356
endale-0.344
tro-0.342
Token M
Token ID337
Feature activation+7.85e-03

Pos logit contributions
nces+6.690
tenance+6.552
ned+6.156
 Shroud+5.902
reath+5.812
Neg logit contributions
andro-9.223
inyl-7.047
agers-6.913
endale-6.888
tro-6.715
Tokenih
Token ID4449
Feature activation+1.43e+00

Pos logit contributions
andro+0.009
inyl+0.007
agers+0.007
endale+0.006
tro+0.006
Neg logit contributions
nces-0.006
tenance-0.006
reath-0.005
ned-0.005
 drown-0.005
Tokensan
Token ID12807
Feature activation-2.09e+00

Pos logit contributions
andro+1.348
inyl+0.986
agers+0.984
endale+0.940
tro+0.935
Neg logit contributions
nces-1.331
tenance-1.288
reath-1.162
ned-1.153
 drown-1.124
Token,
Token ID11
Feature activation+3.93e-02

Pos logit contributions
nces+1.717
tenance+1.668
ned+1.496
reath+1.490
 drown+1.440
Neg logit contributions
andro-2.153
inyl-1.631
agers-1.625
endale-1.570
tro-1.561
Token the
Token ID262
Feature activation-3.12e-01

Pos logit contributions
andro+0.039
inyl+0.029
agers+0.029
endale+0.028
tro+0.028
Neg logit contributions
nces-0.034
tenance-0.033
reath-0.030
ned-0.029
 drown-0.028
Token June
Token ID2795
Feature activation-3.97e-01

Pos logit contributions
nces+1.063
tenance+1.030
reath+0.917
ned+0.916
 drown+0.879
Neg logit contributions
andro-1.331
inyl-1.006
agers-1.002
endale-0.969
tro-0.958
Token 2007
Token ID4343
Feature activation-3.48e+00

Pos logit contributions
nces+0.344
tenance+0.333
reath+0.299
ned+0.297
 drown+0.288
Neg logit contributions
andro-0.396
inyl-0.296
agers-0.295
endale-0.283
tro-0.282
Token,
Token ID11
Feature activation+4.68e-01

Pos logit contributions
nces+2.816
tenance+2.734
reath+2.466
ned+2.463
 Shroud+2.348
Neg logit contributions
andro-3.607
inyl-2.739
agers-2.738
endale-2.636
tro-2.618
Token Singapore
Token ID12551
Feature activation-3.95e+00

Pos logit contributions
andro+0.474
inyl+0.356
agers+0.356
endale+0.341
tro+0.339
Neg logit contributions
nces-0.399
tenance-0.386
reath-0.345
ned-0.342
 drown-0.332
Token and
Token ID290
Feature activation-5.85e-01

Pos logit contributions
nces+3.075
tenance+2.971
ned+2.680
reath+2.654
 drown+2.564
Neg logit contributions
andro-4.208
agers-3.216
inyl-3.211
endale-3.103
tro-3.047
Token Brune
Token ID46070
Feature activation-8.96e+00

Pos logit contributions
nces+0.439
tenance+0.422
reath+0.371
ned+0.367
 drown+0.355
Neg logit contributions
andro-0.654
inyl-0.506
agers-0.505
endale-0.488
tro-0.485
Tokeni
Token ID72
Feature activation-3.14e+00

Pos logit contributions
nces+7.935
tenance+7.909
ned+7.399
reath+7.259
bug+6.920
Neg logit contributions
andro-7.605
agers-5.749
inyl-5.528
ager-5.254
endale-5.156
Token celebrated
Token ID13943
Feature activation-3.71e-01

Pos logit contributions
nces+2.629
tenance+2.568
ned+2.304
reath+2.302
 drown+2.225
Neg logit contributions
andro-3.164
agers-2.381
inyl-2.377
endale-2.293
tro-2.266
Token the
Token ID262
Feature activation-4.42e-01

Pos logit contributions
nces+0.319
tenance+0.307
reath+0.276
ned+0.274
 drown+0.266
Neg logit contributions
andro-0.373
inyl-0.280
agers-0.279
endale-0.269
tro-0.267
Token 40
Token ID2319
Feature activation+1.85e+00

Pos logit contributions
nces+0.428
tenance+0.416
reath+0.378
ned+0.375
 drown+0.366
Neg logit contributions
andro-0.396
inyl-0.286
agers-0.284
endale-0.272
tro-0.268
Tokenth
Token ID400
Feature activation-2.49e+00

Pos logit contributions
andro+1.747
inyl+1.283
agers+1.280
tro+1.224
endale+1.218
Neg logit contributions
nces-1.704
tenance-1.652
reath-1.480
ned-1.469
 drown-1.431
Token While
Token ID2893
Feature activation-1.93e+00

Pos logit contributions
nces+0.058
tenance+0.056
reath+0.050
ned+0.050
 drown+0.048
Neg logit contributions
andro-0.064
inyl-0.048
agers-0.048
endale-0.046
tro-0.045
Token a
Token ID257
Feature activation-5.70e-01

Pos logit contributions
nces+1.635
tenance+1.587
reath+1.423
ned+1.422
 drown+1.377
Neg logit contributions
andro-1.943
inyl-1.451
agers-1.439
endale-1.399
tro-1.384
Token decade
Token ID5707
Feature activation-3.34e+00

Pos logit contributions
nces+0.463
tenance+0.447
reath+0.397
ned+0.394
 drown+0.382
Neg logit contributions
andro-0.601
inyl-0.457
agers-0.456
endale-0.439
tro-0.437
Token ago
Token ID2084
Feature activation-1.39e+00

Pos logit contributions
nces+2.668
tenance+2.581
ned+2.311
reath+2.306
 drown+2.227
Neg logit contributions
andro-3.510
inyl-2.679
agers-2.655
endale-2.558
tro-2.548
Token a
Token ID257
Feature activation-5.55e-01

Pos logit contributions
nces+1.184
tenance+1.148
reath+1.033
ned+1.027
 drown+0.993
Neg logit contributions
andro-1.393
inyl-1.042
agers-1.034
endale-1.000
tro-0.993
Token mug
Token ID25152
Feature activation-8.93e+00

Pos logit contributions
nces+0.458
tenance+0.443
reath+0.395
ned+0.391
 drown+0.380
Neg logit contributions
andro-0.577
inyl-0.437
agers-0.436
endale-0.420
tro-0.417
Token of
Token ID286
Feature activation-1.81e+00

Pos logit contributions
tenance+6.734
nces+6.676
ned+6.208
reath+6.125
 drown+5.872
Neg logit contributions
andro-9.085
inyl-6.835
agers-6.670
endale-6.620
tro-6.414
Token beer
Token ID6099
Feature activation+2.07e+00

Pos logit contributions
nces+1.536
tenance+1.486
reath+1.335
ned+1.329
 drown+1.289
Neg logit contributions
andro-1.831
inyl-1.377
agers-1.367
endale-1.319
tro-1.307
Token cost
Token ID1575
Feature activation-1.33e+00

Pos logit contributions
andro+2.033
agers+1.523
inyl+1.523
endale+1.455
tro+1.450
Neg logit contributions
nces-1.822
tenance-1.757
reath-1.565
ned-1.546
 Shroud-1.504
Token 7
Token ID767
Feature activation-1.14e+00

Pos logit contributions
nces+1.147
tenance+1.109
ned+0.996
reath+0.996
 drown+0.965
Neg logit contributions
andro-1.326
inyl-0.991
agers-0.981
endale-0.947
tro-0.941
Token.
Token ID13
Feature activation-5.77e-01

Pos logit contributions
nces+0.970
tenance+0.936
reath+0.838
ned+0.835
 drown+0.808
Neg logit contributions
andro-1.163
inyl-0.875
agers-0.871
endale-0.840
tro-0.826
Tokenpas
Token ID44429
Feature activation+1.45e+00

Pos logit contributions
andro+2.225
inyl+1.664
agers+1.653
tro+1.591
endale+1.586
Neg logit contributions
nces-1.943
tenance-1.880
reath-1.688
ned-1.663
 drown-1.623
Tokenaurus
Token ID22302
Feature activation-2.11e+00

Pos logit contributions
andro+1.495
inyl+1.128
agers+1.127
endale+1.082
tro+1.077
Neg logit contributions
nces-1.218
tenance-1.174
reath-1.047
ned-1.036
 drown-1.007
Tokenrex
Token ID21510
Feature activation-1.13e-01

Pos logit contributions
nces+1.732
tenance+1.683
reath+1.494
ned+1.482
 drown+1.433
Neg logit contributions
andro-2.191
inyl-1.672
agers-1.659
endale-1.596
tro-1.584
Token in
Token ID287
Feature activation+3.29e-01

Pos logit contributions
nces+0.094
tenance+0.092
reath+0.081
ned+0.081
 drown+0.078
Neg logit contributions
andro-0.116
inyl-0.088
agers-0.087
endale-0.084
tro-0.083
Token our
Token ID674
Feature activation+1.42e+00

Pos logit contributions
andro+0.338
inyl+0.255
agers+0.254
endale+0.245
tro+0.243
Neg logit contributions
nces-0.276
tenance-0.267
reath-0.238
ned-0.236
 drown-0.229
Token debugger
Token ID49518
Feature activation-8.91e+00

Pos logit contributions
andro+1.525
agers+1.163
inyl+1.162
endale+1.117
tro+1.116
Neg logit contributions
nces-1.125
tenance-1.077
reath-0.960
ned-0.946
 drown-0.914
Token:
Token ID25
Feature activation+3.46e-01

Pos logit contributions
tenance+6.524
nces+6.490
ned+5.785
reath+5.688
 drown+5.485
Neg logit contributions
andro-9.369
inyl-7.277
agers-7.162
endale-6.898
tro-6.861
Token
Token ID198
Feature activation-5.63e-01

Pos logit contributions
andro+0.347
inyl+0.260
agers+0.260
endale+0.249
tro+0.248
Neg logit contributions
nces-0.298
tenance-0.288
reath-0.258
ned-0.255
 drown-0.248
Token
Token ID198
Feature activation-6.47e-01

Pos logit contributions
nces+0.476
tenance+0.464
ned+0.415
reath+0.413
bug+0.395
Neg logit contributions
andro-0.566
inyl-0.429
agers-0.426
endale-0.408
tro-0.403
Token1
Token ID16
Feature activation-1.38e+00

Pos logit contributions
nces+0.560
tenance+0.542
reath+0.485
ned+0.483
 drown+0.466
Neg logit contributions
andro-0.644
inyl-0.483
agers-0.481
endale-0.462
tro-0.457
Token $
Token ID720
Feature activation+1.75e+00

Pos logit contributions
nces+1.125
tenance+1.087
reath+0.962
ned+0.961
 drown+0.928
Neg logit contributions
andro-1.443
inyl-1.097
agers-1.093
endale-1.056
tro-1.043
Token has
Token ID468
Feature activation+1.78e+00

Pos logit contributions
andro+0.909
inyl+0.674
agers+0.672
endale+0.643
tro+0.640
Neg logit contributions
nces-0.831
tenance-0.805
reath-0.721
ned-0.713
 drown-0.692
Token the
Token ID262
Feature activation-3.82e-01

Pos logit contributions
andro+1.871
inyl+1.426
agers+1.416
endale+1.361
tro+1.359
Neg logit contributions
nces-1.443
tenance-1.399
reath-1.236
ned-1.218
 drown-1.181
Token state
Token ID1181
Feature activation-1.44e+00

Pos logit contributions
nces+0.316
tenance+0.305
reath+0.272
ned+0.269
 drown+0.261
Neg logit contributions
andro-0.397
inyl-0.301
agers-0.300
endale-0.289
tro-0.287
Token title
Token ID3670
Feature activation+3.02e-02

Pos logit contributions
nces+1.090
tenance+1.052
reath+0.925
ned+0.918
 drown+0.887
Neg logit contributions
andro-1.592
agers-1.228
inyl-1.227
endale-1.185
tro-1.177
Token of
Token ID286
Feature activation-1.23e+00

Pos logit contributions
andro+0.031
inyl+0.023
agers+0.023
endale+0.022
tro+0.022
Neg logit contributions
nces-0.026
tenance-0.025
reath-0.022
ned-0.022
 drown-0.022
Token Brune
Token ID46070
Feature activation-8.79e+00

Pos logit contributions
nces+1.054
tenance+1.019
reath+0.914
ned+0.909
 drown+0.882
Neg logit contributions
andro-1.242
agers-0.931
inyl-0.930
endale-0.893
tro-0.886
Tokeni
Token ID72
Feature activation-3.11e+00

Pos logit contributions
nces+8.270
tenance+8.093
reath+7.572
ned+7.557
 Shroud+7.244
Neg logit contributions
andro-7.177
agers-5.213
inyl-5.018
endale-4.824
tro-4.765
Token in
Token ID287
Feature activation+5.70e-01

Pos logit contributions
nces+2.537
tenance+2.448
reath+2.206
ned+2.198
 drown+2.123
Neg logit contributions
andro-3.217
agers-2.452
inyl-2.422
endale-2.340
tro-2.328
Token Latin
Token ID9133
Feature activation-5.33e-01

Pos logit contributions
andro+0.604
inyl+0.460
agers+0.459
endale+0.442
tro+0.440
Neg logit contributions
nces-0.460
tenance-0.443
reath-0.393
ned-0.390
 drown-0.378
Token script
Token ID4226
Feature activation-7.67e-01

Pos logit contributions
nces+0.450
tenance+0.434
reath+0.389
ned+0.385
 drown+0.375
Neg logit contributions
andro-0.543
agers-0.409
inyl-0.409
endale-0.392
tro-0.390
Token.[
Token ID3693
Feature activation+1.46e+00

Pos logit contributions
nces+0.679
tenance+0.656
reath+0.590
ned+0.586
 drown+0.569
Neg logit contributions
andro-0.752
inyl-0.558
agers-0.558
endale-0.534
tro-0.532
Token Muslims
Token ID7045
Feature activation-1.14e+00

Pos logit contributions
nces+0.198
tenance+0.191
reath+0.170
ned+0.170
 drown+0.164
Neg logit contributions
andro-0.248
inyl-0.188
agers-0.187
endale-0.180
tro-0.179
Token,
Token ID11
Feature activation+2.70e-01

Pos logit contributions
nces+0.962
tenance+0.929
reath+0.833
ned+0.831
 drown+0.808
Neg logit contributions
andro-1.154
inyl-0.870
agers-0.867
endale-0.832
tro-0.828
Token Kh
Token ID5311
Feature activation-1.25e+00

Pos logit contributions
andro+0.288
inyl+0.220
agers+0.219
endale+0.211
tro+0.210
Neg logit contributions
nces-0.216
tenance-0.208
reath-0.185
ned-0.183
 drown-0.178
Tokenall
Token ID439
Feature activation+2.74e-01

Pos logit contributions
nces+1.006
tenance+0.971
reath+0.875
ned+0.869
 drown+0.832
Neg logit contributions
andro-1.300
inyl-0.993
agers-0.986
endale-0.950
tro-0.948
Tokenad
Token ID324
Feature activation-7.64e-01

Pos logit contributions
andro+0.281
inyl+0.212
agers+0.211
endale+0.203
tro+0.202
Neg logit contributions
nces-0.231
tenance-0.223
reath-0.199
ned-0.197
 drown-0.191
Token bin
Token ID9874
Feature activation-8.79e+00

Pos logit contributions
nces+0.611
tenance+0.589
reath+0.525
ned+0.521
 drown+0.504
Neg logit contributions
andro-0.812
inyl-0.620
agers-0.618
endale-0.596
tro-0.594
Token Su
Token ID1778
Feature activation+2.51e+00

Pos logit contributions
nces+6.574
tenance+6.430
ned+5.995
 Shroud+5.753
reath+5.736
Neg logit contributions
andro-8.998
inyl-6.911
agers-6.785
endale-6.728
tro-6.577
Tokenw
Token ID86
Feature activation-2.65e+00

Pos logit contributions
andro+2.413
inyl+1.772
agers+1.769
endale+1.695
tro+1.683
Neg logit contributions
nces-2.285
tenance-2.211
reath-1.977
ned-1.961
 drown-1.920
Tokenaid
Token ID1698
Feature activation-3.46e-01

Pos logit contributions
nces+1.792
tenance+1.709
reath+1.509
ned+1.496
 drown+1.415
Neg logit contributions
andro-3.113
inyl-2.464
agers-2.427
endale-2.380
tro-2.375
Token was
Token ID373
Feature activation+6.58e-01

Pos logit contributions
nces+0.290
tenance+0.280
reath+0.250
ned+0.249
 drown+0.241
Neg logit contributions
andro-0.355
inyl-0.268
agers-0.268
endale-0.257
tro-0.256
Token killed
Token ID2923
Feature activation-5.79e-01

Pos logit contributions
andro+0.687
inyl+0.522
agers+0.521
endale+0.500
tro+0.498
Neg logit contributions
nces-0.540
tenance-0.521
reath-0.464
ned-0.458
 drown-0.443
Token,
Token ID11
Feature activation-1.40e-01

Pos logit contributions
andro+1.303
inyl+0.978
agers+0.978
endale+0.939
tro+0.933
Neg logit contributions
nces-1.106
tenance-1.070
reath-0.953
ned-0.945
 Shroud-0.916
Token
Token ID447
Feature activation-5.68e-01

Pos logit contributions
nces+0.126
tenance+0.121
reath+0.109
ned+0.108
 drown+0.106
Neg logit contributions
andro-0.136
inyl-0.101
agers-0.100
endale-0.096
tro-0.095
Token
Token ID251
Feature activation-4.91e-02

Pos logit contributions
nces+0.463
tenance+0.446
reath+0.397
ned+0.392
 drown+0.381
Neg logit contributions
andro-0.597
agers-0.454
inyl-0.454
tro-0.436
endale-0.435
Token Ms
Token ID6997
Feature activation+1.26e+00

Pos logit contributions
nces+0.046
tenance+0.045
reath+0.040
ned+0.040
 drown+0.039
Neg logit contributions
andro-0.046
inyl-0.033
agers-0.033
endale-0.032
tro-0.031
Token.
Token ID13
Feature activation-3.54e-01

Pos logit contributions
andro+1.307
inyl+0.988
agers+0.987
endale+0.949
tro+0.940
Neg logit contributions
nces-1.042
tenance-1.005
reath-0.897
ned-0.893
 drown-0.860
Token Ole
Token ID30093
Feature activation+7.87e+00

Pos logit contributions
nces+0.280
tenance+0.270
reath+0.239
ned+0.237
 drown+0.230
Neg logit contributions
andro-0.379
agers-0.290
inyl-0.289
endale-0.279
tro-0.276
Tokench
Token ID354
Feature activation-2.05e+00

Pos logit contributions
andro+6.998
agers+5.005
inyl+4.995
tro+4.852
endale+4.821
Neg logit contributions
nces-7.393
tenance-7.203
 drown-6.429
reath-6.410
 Shroud-6.312
Tokenowski
Token ID12079
Feature activation+8.06e-01

Pos logit contributions
nces+1.949
tenance+1.894
ned+1.734
reath+1.729
 drown+1.652
Neg logit contributions
andro-1.853
agers-1.341
inyl-1.339
endale-1.272
tro-1.248
Token said
Token ID531
Feature activation+2.47e-01

Pos logit contributions
andro+0.757
agers+0.553
inyl+0.552
endale+0.527
tro+0.523
Neg logit contributions
nces-0.748
tenance-0.726
reath-0.654
ned-0.645
 drown-0.630
Token.
Token ID13
Feature activation+4.01e-02

Pos logit contributions
andro+0.248
inyl+0.186
agers+0.185
endale+0.178
tro+0.177
Neg logit contributions
nces-0.213
tenance-0.206
reath-0.184
ned-0.182
 drown-0.177
Token
Token ID198
Feature activation+1.07e-01

Pos logit contributions
andro+0.040
inyl+0.030
agers+0.030
endale+0.029
tro+0.028
Neg logit contributions
nces-0.035
tenance-0.034
reath-0.030
ned-0.030
 drown-0.029
Tokenthey
Token ID9930
Feature activation-4.13e-01

Pos logit contributions
andro+1.124
inyl+0.816
agers+0.814
endale+0.777
tro+0.773
Neg logit contributions
nces-1.155
tenance-1.120
reath-1.013
ned-1.005
 drown-0.980
Token."
Token ID526
Feature activation-3.37e-01

Pos logit contributions
nces+0.361
tenance+0.349
reath+0.313
ned+0.310
 drown+0.302
Neg logit contributions
andro-0.410
inyl-0.306
agers-0.305
endale-0.293
tro-0.291
Token
Token ID198
Feature activation-2.36e-01

Pos logit contributions
nces+0.296
tenance+0.287
reath+0.257
ned+0.256
 Shroud+0.248
Neg logit contributions
andro-0.330
inyl-0.247
agers-0.246
endale-0.237
tro-0.234
Token
Token ID198
Feature activation-3.88e-01

Pos logit contributions
nces+0.202
tenance+0.198
ned+0.177
reath+0.176
 drown+0.169
Neg logit contributions
andro-0.238
inyl-0.179
agers-0.178
endale-0.171
tro-0.169
TokenPan
Token ID15730
Feature activation-2.91e+00

Pos logit contributions
nces+0.362
tenance+0.353
reath+0.319
ned+0.319
 drown+0.306
Neg logit contributions
andro-0.358
inyl-0.263
agers-0.262
endale-0.252
tro-0.247
Tokensexual
Token ID18338
Feature activation+5.91e+00

Pos logit contributions
nces+2.718
tenance+2.657
ned+2.412
reath+2.389
 drown+2.316
Neg logit contributions
andro-2.662
inyl-1.937
agers-1.903
endale-1.856
tro-1.836
Token:
Token ID25
Feature activation+8.47e-01

Pos logit contributions
andro+5.586
agers+4.118
inyl+4.078
tro+3.882
ager+3.874
Neg logit contributions
nces-5.339
tenance-5.177
reath-4.664
ned-4.557
 drown-4.466
Token Pan
Token ID5961
Feature activation-2.72e+00

Pos logit contributions
andro+0.807
inyl+0.594
agers+0.592
endale+0.567
tro+0.563
Neg logit contributions
nces-0.773
tenance-0.749
reath-0.675
ned-0.670
 drown-0.652
Tokensexual
Token ID18338
Feature activation+5.42e+00

Pos logit contributions
nces+2.593
tenance+2.521
ned+2.288
reath+2.261
 drown+2.220
Neg logit contributions
andro-2.449
inyl-1.783
agers-1.749
endale-1.701
tro-1.662
Token people
Token ID661
Feature activation-3.57e-01

Pos logit contributions
andro+5.445
agers+4.114
inyl+4.077
tro+3.892
ager+3.859
Neg logit contributions
nces-4.602
tenance-4.430
reath-3.977
ned-3.841
 Shroud-3.778
Token may
Token ID743
Feature activation-9.69e-01

Pos logit contributions
nces+0.301
tenance+0.291
reath+0.259
ned+0.257
 drown+0.249
Neg logit contributions
andro-0.366
inyl-0.276
agers-0.276
endale-0.265
tro-0.263
Token planet
Token ID5440
Feature activation-2.19e+00

Pos logit contributions
nces+0.325
tenance+0.313
reath+0.273
ned+0.271
 drown+0.263
Neg logit contributions
andro-0.578
inyl-0.456
agers-0.455
endale-0.441
tro-0.438
Token,
Token ID11
Feature activation+3.27e-01

Pos logit contributions
nces+1.563
tenance+1.497
reath+1.312
ned+1.311
 drown+1.253
Neg logit contributions
andro-2.511
inyl-1.960
agers-1.952
endale-1.888
tro-1.880
Token but
Token ID475
Feature activation+1.17e+00

Pos logit contributions
andro+0.345
inyl+0.262
agers+0.261
endale+0.252
tro+0.250
Neg logit contributions
nces-0.266
tenance-0.257
reath-0.228
ned-0.226
 drown-0.219
Token its
Token ID663
Feature activation-8.56e-01

Pos logit contributions
andro+1.200
agers+0.905
inyl+0.904
endale+0.868
tro+0.864
Neg logit contributions
nces-0.984
tenance-0.950
reath-0.848
ned-0.838
 drown-0.813
Token special
Token ID2041
Feature activation+1.75e+00

Pos logit contributions
nces+0.689
tenance+0.665
reath+0.591
ned+0.588
 drown+0.570
Neg logit contributions
andro-0.907
inyl-0.693
agers-0.686
endale-0.664
tro-0.659
Token electric
Token ID5186
Feature activation+5.09e+00

Pos logit contributions
andro+1.840
agers+1.399
inyl+1.396
endale+1.343
tro+1.339
Neg logit contributions
nces-1.421
tenance-1.364
reath-1.215
ned-1.200
 drown-1.165
Token engine
Token ID3113
Feature activation-4.21e+00

Pos logit contributions
andro+5.719
agers+4.459
inyl+4.398
tro+4.315
ager+4.281
Neg logit contributions
nces-3.727
tenance-3.523
reath-3.071
ned-2.999
 drown-2.906
Token that
Token ID326
Feature activation+1.56e+00

Pos logit contributions
nces+3.333
tenance+3.192
ned+2.890
reath+2.842
 drown+2.819
Neg logit contributions
andro-4.456
inyl-3.427
agers-3.369
endale-3.292
tro-3.224
Token maintains
Token ID16047
Feature activation-5.97e-01

Pos logit contributions
andro+1.704
agers+1.311
inyl+1.310
endale+1.260
tro+1.256
Neg logit contributions
nces-1.210
tenance-1.171
reath-1.031
ned-1.016
 drown-0.979
Token this
Token ID428
Feature activation+1.38e+00

Pos logit contributions
nces+0.465
tenance+0.449
reath+0.397
ned+0.394
 drown+0.382
Neg logit contributions
andro-0.649
inyl-0.500
agers-0.496
endale-0.479
tro-0.477
Token altitude
Token ID20334
Feature activation-6.33e-02

Pos logit contributions
andro+1.427
inyl+1.078
agers+1.075
endale+1.032
tro+1.025
Neg logit contributions
nces-1.156
tenance-1.119
reath-0.998
ned-0.991
 drown-0.962
Token West
Token ID2688
Feature activation-5.87e-02

Pos logit contributions
andro+1.261
inyl+0.949
agers+0.948
endale+0.913
tro+0.907
Neg logit contributions
nces-1.034
tenance-0.999
reath-0.891
ned-0.881
 drown-0.857
Tokenchester
Token ID35983
Feature activation-3.42e+00

Pos logit contributions
nces+0.049
tenance+0.047
reath+0.042
ned+0.041
 drown+0.040
Neg logit contributions
andro-0.061
inyl-0.046
agers-0.046
endale-0.044
tro-0.044
Token 1
Token ID352
Feature activation-3.70e-01

Pos logit contributions
nces+2.851
tenance+2.761
ned+2.483
reath+2.479
 Shroud+2.399
Neg logit contributions
andro-3.466
agers-2.647
inyl-2.634
endale-2.506
ager-2.481
Token hour
Token ID1711
Feature activation-3.23e+00

Pos logit contributions
nces+0.330
tenance+0.321
reath+0.288
ned+0.286
 drown+0.278
Neg logit contributions
andro-0.360
inyl-0.268
agers-0.266
endale-0.254
tro-0.253
Token ago
Token ID2084
Feature activation-1.03e+00

Pos logit contributions
nces+2.456
tenance+2.360
ned+2.149
reath+2.078
 drown+1.994
Neg logit contributions
andro-3.509
inyl-2.729
agers-2.702
endale-2.574
tro-2.566
Token Pretty
Token ID20090
Feature activation+4.34e+00

Pos logit contributions
nces+0.879
tenance+0.850
reath+0.759
ned+0.756
 drown+0.733
Neg logit contributions
andro-1.039
inyl-0.780
agers-0.778
endale-0.746
tro-0.741
Token simple
Token ID2829
Feature activation-2.42e+00

Pos logit contributions
andro+4.416
agers+3.307
inyl+3.300
tro+3.185
endale+3.169
Neg logit contributions
nces-3.626
tenance-3.519
reath-3.157
ned-3.072
 drown-2.978
Token Paul
Token ID3362
Feature activation+5.06e+00

Pos logit contributions
nces+1.995
tenance+1.926
ned+1.723
reath+1.699
 drown+1.668
Neg logit contributions
andro-2.514
inyl-1.905
agers-1.894
endale-1.827
tro-1.796
Token:
Token ID25
Feature activation+3.54e-01

Pos logit contributions
andro+4.929
agers+3.655
inyl+3.647
tro+3.494
endale+3.474
Neg logit contributions
nces-4.472
tenance-4.336
reath-3.888
ned-3.841
 Shroud-3.711
Token
Token ID198
Feature activation-6.94e-01

Pos logit contributions
andro+0.365
inyl+0.276
agers+0.275
endale+0.265
tro+0.263
Neg logit contributions
nces-0.296
tenance-0.285
reath-0.255
ned-0.252
 drown-0.245
Token
Token ID198
Feature activation-7.78e-01

Pos logit contributions
nces+0.582
tenance+0.570
ned+0.511
reath+0.506
 Shroud+0.485
Neg logit contributions
andro-0.708
inyl-0.535
agers-0.531
endale-0.510
tro-0.503
Token make
Token ID787
Feature activation-2.16e+00

Pos logit contributions
andro+0.921
inyl+0.700
agers+0.696
endale+0.668
tro+0.665
Neg logit contributions
nces-0.744
tenance-0.718
reath-0.638
ned-0.629
 drown-0.609
Token mechanics
Token ID12933
Feature activation+6.55e-01

Pos logit contributions
nces+1.742
tenance+1.675
reath+1.496
ned+1.488
 drown+1.443
Neg logit contributions
andro-2.277
inyl-1.739
agers-1.728
endale-1.669
tro-1.655
Token for
Token ID329
Feature activation-2.38e-01

Pos logit contributions
andro+0.661
agers+0.495
inyl+0.495
endale+0.474
tro+0.473
Neg logit contributions
nces-0.562
tenance-0.543
reath-0.484
ned-0.479
 drown-0.465
Token cycles
Token ID16006
Feature activation-4.45e-01

Pos logit contributions
nces+0.194
tenance+0.187
reath+0.166
ned+0.164
 drown+0.159
Neg logit contributions
andro-0.249
agers-0.190
inyl-0.189
endale-0.182
tro-0.181
Token of
Token ID286
Feature activation-1.41e+00

Pos logit contributions
nces+0.385
tenance+0.372
reath+0.333
ned+0.331
 drown+0.321
Neg logit contributions
andro-0.445
inyl-0.333
agers-0.332
endale-0.319
tro-0.317
Token cards
Token ID4116
Feature activation+4.50e+00

Pos logit contributions
nces+1.138
tenance+1.096
reath+0.974
ned+0.966
 drown+0.937
Neg logit contributions
andro-1.494
inyl-1.138
agers-1.134
endale-1.094
tro-1.086
Token,
Token ID11
Feature activation+3.06e-01

Pos logit contributions
andro+4.252
inyl+3.141
agers+3.130
endale+3.015
tro+2.979
Neg logit contributions
nces-4.093
tenance-3.927
reath-3.514
ned-3.455
 Shroud-3.389
Token we
Token ID356
Feature activation+6.36e-01

Pos logit contributions
andro+0.283
inyl+0.206
agers+0.205
endale+0.197
tro+0.195
Neg logit contributions
nces-0.287
tenance-0.278
reath-0.252
ned-0.250
 drown-0.244
Token have
Token ID423
Feature activation+6.74e-01

Pos logit contributions
andro+0.695
inyl+0.537
agers+0.536
endale+0.515
tro+0.513
Neg logit contributions
nces-0.490
tenance-0.472
reath-0.416
ned-0.411
 drown-0.396
Token to
Token ID284
Feature activation-5.86e-01

Pos logit contributions
andro+0.710
agers+0.540
inyl+0.540
endale+0.519
tro+0.517
Neg logit contributions
nces-0.547
tenance-0.529
reath-0.469
ned-0.463
 drown-0.448
Token decide
Token ID5409
Feature activation+1.09e+00

Pos logit contributions
nces+0.447
tenance+0.430
reath+0.380
ned+0.377
 drown+0.367
Neg logit contributions
andro-0.647
agers-0.497
inyl-0.497
endale-0.481
tro-0.476
TokenYP
Token ID48232
Feature activation-1.68e-01

Pos logit contributions
nces+3.692
tenance+3.617
reath+3.275
ned+3.217
 drown+3.093
Neg logit contributions
andro-4.789
inyl-3.648
agers-3.612
endale-3.495
tro-3.473
TokenOWER
Token ID36048
Feature activation-1.84e+00

Pos logit contributions
nces+0.049
tenance+0.045
reath+0.031
ned+0.030
 drown+0.027
Neg logit contributions
andro-0.263
inyl-0.221
agers-0.220
endale-0.215
tro-0.214
Token.
Token ID13
Feature activation-4.07e-01

Pos logit contributions
nces+1.522
tenance+1.473
reath+1.312
ned+1.305
 drown+1.258
Neg logit contributions
andro-1.913
inyl-1.446
agers-1.437
endale-1.386
tro-1.371
Token At
Token ID1629
Feature activation+2.28e+00

Pos logit contributions
nces+0.362
tenance+0.351
reath+0.315
ned+0.313
 drown+0.304
Neg logit contributions
andro-0.396
inyl-0.294
agers-0.293
endale-0.281
tro-0.279
Token MLG
Token ID48144
Feature activation-1.23e+00

Pos logit contributions
andro+2.328
agers+1.757
inyl+1.756
endale+1.688
tro+1.683
Neg logit contributions
nces-1.916
tenance-1.840
reath-1.648
ned-1.630
 drown-1.581
Token they
Token ID484
Feature activation+5.14e-01

Pos logit contributions
nces+1.084
tenance+1.049
reath+0.946
ned+0.938
 drown+0.912
Neg logit contributions
andro-1.215
inyl-0.903
agers-0.902
endale-0.860
tro-0.859
Token did
Token ID750
Feature activation-2.76e+00

Pos logit contributions
andro+0.501
inyl+0.371
agers+0.371
endale+0.355
tro+0.353
Neg logit contributions
nces-0.459
tenance-0.444
reath-0.399
ned-0.395
 drown-0.384
Token even
Token ID772
Feature activation+2.62e+00

Pos logit contributions
nces+2.212
tenance+2.134
reath+1.891
ned+1.884
 drown+1.840
Neg logit contributions
andro-2.920
inyl-2.239
agers-2.224
endale-2.152
tro-2.128
Token better
Token ID1365
Feature activation-1.93e+00

Pos logit contributions
andro+2.585
agers+1.925
inyl+1.919
tro+1.846
endale+1.841
Neg logit contributions
nces-2.288
tenance-2.223
reath-1.995
ned-1.963
 Shroud-1.911
Token,
Token ID11
Feature activation+1.77e-01

Pos logit contributions
nces+1.603
tenance+1.539
ned+1.368
reath+1.367
 drown+1.323
Neg logit contributions
andro-2.011
inyl-1.520
agers-1.513
endale-1.456
tro-1.444
Token best
Token ID1266
Feature activation-4.29e-01

Pos logit contributions
andro+0.182
inyl+0.137
agers+0.137
endale+0.132
tro+0.131
Neg logit contributions
nces-0.149
tenance-0.144
reath-0.129
ned-0.127
 drown-0.124
Token forward
Token ID2651
Feature activation+2.46e+00

Pos logit contributions
andro+0.419
inyl+0.317
agers+0.316
endale+0.304
tro+0.302
Neg logit contributions
nces-0.337
tenance-0.325
reath-0.290
ned-0.288
 drown-0.279
Token a
Token ID257
Feature activation+1.39e-01

Pos logit contributions
andro+2.454
agers+1.846
inyl+1.832
tro+1.774
endale+1.756
Neg logit contributions
nces-2.112
tenance-2.052
reath-1.810
ned-1.788
 Shroud-1.731
Token referendum
Token ID11467
Feature activation-1.25e-01

Pos logit contributions
andro+0.142
inyl+0.107
agers+0.107
endale+0.103
tro+0.102
Neg logit contributions
nces-0.117
tenance-0.113
reath-0.101
ned-0.100
 drown-0.097
Token on
Token ID319
Feature activation+1.78e+00

Pos logit contributions
nces+0.104
tenance+0.101
reath+0.090
ned+0.089
 drown+0.087
Neg logit contributions
andro-0.128
inyl-0.097
agers-0.096
endale-0.093
tro-0.092
Token whether
Token ID1771
Feature activation-2.72e-01

Pos logit contributions
andro+1.723
agers+1.288
inyl+1.281
tro+1.223
endale+1.220
Neg logit contributions
nces-1.586
tenance-1.531
reath-1.364
ned-1.352
 drown-1.312
Token to
Token ID284
Feature activation-3.51e-01

Pos logit contributions
nces+0.222
tenance+0.215
reath+0.192
ned+0.190
 drown+0.184
Neg logit contributions
andro-0.285
inyl-0.217
agers-0.216
endale-0.208
tro-0.206
Token exit
Token ID8420
Feature activation-2.26e+00

Pos logit contributions
nces+0.258
tenance+0.248
reath+0.217
ned+0.214
 drown+0.206
Neg logit contributions
andro-0.398
inyl-0.310
agers-0.309
endale-0.298
tro-0.297
Token the
Token ID262
Feature activation-3.39e-01

Pos logit contributions
nces+1.818
tenance+1.772
reath+1.594
ned+1.588
 drown+1.524
Neg logit contributions
andro-2.372
inyl-1.794
agers-1.793
endale-1.726
tro-1.701
Token EU
Token ID4576
Feature activation+1.30e+00

Pos logit contributions
nces+0.310
tenance+0.302
reath+0.273
ned+0.272
 drown+0.264
Neg logit contributions
andro-0.321
inyl-0.237
agers-0.233
endale-0.225
tro-0.221
Token.
Token ID13
Feature activation+4.29e-02

Pos logit contributions
andro+1.319
inyl+0.993
agers+0.991
endale+0.952
tro+0.947
Neg logit contributions
nces-1.099
tenance-1.061
reath-0.948
ned-0.939
 drown-0.912
Token
Token ID198
Feature activation+1.20e-01

Pos logit contributions
andro+0.042
inyl+0.032
agers+0.031
endale+0.030
tro+0.030
Neg logit contributions
nces-0.038
tenance-0.037
reath-0.033
ned-0.032
 drown-0.032
Token his
Token ID465
Feature activation+9.63e-01

Pos logit contributions
nces+0.013
tenance+0.013
reath+0.012
ned+0.011
 drown+0.011
Neg logit contributions
andro-0.016
inyl-0.012
agers-0.012
endale-0.012
tro-0.012
Token page
Token ID2443
Feature activation-3.67e-01

Pos logit contributions
andro+1.026
inyl+0.783
agers+0.781
endale+0.753
tro+0.748
Neg logit contributions
nces-0.769
tenance-0.743
reath-0.659
ned-0.654
 drown-0.634
Token on
Token ID319
Feature activation+1.77e+00

Pos logit contributions
nces+0.309
tenance+0.298
reath+0.266
ned+0.264
 drown+0.256
Neg logit contributions
andro-0.376
inyl-0.284
agers-0.283
endale-0.272
tro-0.270
Token Sh
Token ID911
Feature activation-2.01e+00

Pos logit contributions
andro+1.842
inyl+1.396
agers+1.393
endale+1.339
tro+1.332
Neg logit contributions
nces-1.462
tenance-1.411
reath-1.256
ned-1.245
 drown-1.207
Tokenuffle
Token ID18137
Feature activation-1.75e+00

Pos logit contributions
nces+0.981
tenance+0.918
reath+0.753
ned+0.743
 drown+0.679
Neg logit contributions
andro-2.752
agers-2.246
inyl-2.246
endale-2.183
tro-2.182
Token Along
Token ID17159
Feature activation+1.39e+00

Pos logit contributions
nces+1.699
tenance+1.648
reath+1.490
ned+1.485
 Shroud+1.442
Neg logit contributions
andro-1.562
inyl-1.124
agers-1.123
endale-1.066
tro-1.060
Token
Token ID447
Feature activation+2.37e-01

Pos logit contributions
andro+1.442
inyl+1.093
agers+1.090
endale+1.047
tro+1.044
Neg logit contributions
nces-1.150
tenance-1.108
reath-0.988
ned-0.978
 drown-0.950
Token
Token ID247
Feature activation+7.71e-01

Pos logit contributions
andro+0.242
inyl+0.182
agers+0.181
endale+0.174
tro+0.173
Neg logit contributions
nces-0.200
tenance-0.194
reath-0.173
ned-0.171
 drown-0.166
Tokens
Token ID82
Feature activation-6.34e-01

Pos logit contributions
andro+0.805
inyl+0.612
agers+0.611
endale+0.587
tro+0.583
Neg logit contributions
nces-0.633
tenance-0.612
reath-0.543
ned-0.539
 drown-0.521
Token website
Token ID3052
Feature activation-3.08e+00

Pos logit contributions
nces+0.490
tenance+0.477
reath+0.419
ned+0.417
 drown+0.401
Neg logit contributions
andro-0.687
agers-0.527
inyl-0.527
endale-0.509
tro-0.506
Token.
Token ID13
Feature activation-2.10e-01

Pos logit contributions
nces+2.472
tenance+2.399
reath+2.122
ned+2.106
 drown+2.025
Neg logit contributions
andro-3.247
agers-2.480
inyl-2.476
endale-2.377
tro-2.355
Token a
Token ID257
Feature activation-8.14e-02

Pos logit contributions
nces+0.854
tenance+0.821
reath+0.734
ned+0.732
 drown+0.710
Neg logit contributions
andro-1.050
inyl-0.794
agers-0.791
endale-0.760
tro-0.757
Token nightmare
Token ID17123
Feature activation-7.83e-01

Pos logit contributions
nces+0.066
tenance+0.063
reath+0.056
ned+0.056
 drown+0.054
Neg logit contributions
andro-0.086
inyl-0.066
agers-0.066
endale-0.063
tro-0.063
Token apartment
Token ID7962
Feature activation+1.95e+00

Pos logit contributions
nces+0.662
tenance+0.640
reath+0.572
ned+0.567
 drown+0.550
Neg logit contributions
andro-0.798
inyl-0.601
agers-0.600
endale-0.576
tro-0.573
Token broker
Token ID20426
Feature activation-8.53e-01

Pos logit contributions
andro+2.203
inyl+1.725
agers+1.713
endale+1.660
ager+1.651
Neg logit contributions
nces-1.447
tenance-1.363
reath-1.192
ned-1.158
 Shroud-1.127
Token on
Token ID319
Feature activation+1.97e+00

Pos logit contributions
nces+0.722
tenance+0.697
reath+0.623
ned+0.618
 drown+0.600
Neg logit contributions
andro-0.870
inyl-0.655
agers-0.653
endale-0.627
tro-0.624
Token Broad
Token ID9765
Feature activation-7.81e-02

Pos logit contributions
andro+2.031
inyl+1.534
agers+1.533
endale+1.472
tro+1.464
Neg logit contributions
nces-1.653
tenance-1.595
reath-1.422
ned-1.406
 drown-1.364
Token City
Token ID2254
Feature activation+1.67e+00

Pos logit contributions
nces+0.062
tenance+0.059
reath+0.052
ned+0.051
 drown+0.050
Neg logit contributions
andro-0.084
inyl-0.065
agers-0.065
endale-0.063
tro-0.062
Token and
Token ID290
Feature activation-6.56e-01

Pos logit contributions
andro+1.725
inyl+1.309
agers+1.306
endale+1.255
tro+1.248
Neg logit contributions
nces-1.389
tenance-1.345
reath-1.193
ned-1.177
 drown-1.144
Token once
Token ID1752
Feature activation-1.56e+00

Pos logit contributions
nces+0.564
tenance+0.545
reath+0.489
ned+0.487
 drown+0.473
Neg logit contributions
andro-0.658
inyl-0.492
agers-0.491
endale-0.470
tro-0.469
Token did
Token ID750
Feature activation-2.80e+00

Pos logit contributions
nces+1.327
tenance+1.281
ned+1.157
reath+1.150
 drown+1.123
Neg logit contributions
andro-1.576
agers-1.183
inyl-1.178
endale-1.131
tro-1.129
Token cart
Token ID6383
Feature activation+1.90e+00

Pos logit contributions
nces+2.256
tenance+2.167
reath+1.934
ned+1.926
 drown+1.883
Neg logit contributions
andro-2.934
agers-2.247
inyl-2.239
endale-2.145
tro-2.140
Tokenpolit
Token ID34470
Feature activation-1.40e+00

Pos logit contributions
andro+1.724
inyl+1.292
agers+1.291
endale+1.238
tro+1.232
Neg logit contributions
nces-1.477
tenance-1.427
reath-1.276
ned-1.266
 drown-1.229
Tokenic
Token ID291
Feature activation+1.04e+00

Pos logit contributions
nces+1.158
tenance+1.153
reath+1.043
ned+1.030
 drown+0.979
Neg logit contributions
andro-1.422
agers-1.064
inyl-1.057
endale-1.021
tro-0.996
Tokenisation
Token ID5612
Feature activation+6.32e-02

Pos logit contributions
andro+1.013
inyl+0.750
agers+0.747
endale+0.719
tro+0.712
Neg logit contributions
nces-0.929
tenance-0.902
reath-0.808
ned-0.806
 drown-0.781
Token of
Token ID286
Feature activation-1.02e+00

Pos logit contributions
andro+0.066
inyl+0.050
agers+0.050
endale+0.048
tro+0.048
Neg logit contributions
nces-0.052
tenance-0.050
reath-0.045
ned-0.044
 drown-0.043
Token his
Token ID465
Feature activation+8.64e-01

Pos logit contributions
nces+0.861
tenance+0.832
reath+0.745
ned+0.739
 drown+0.716
Neg logit contributions
andro-1.043
inyl-0.786
agers-0.780
endale-0.752
tro-0.746
Token role
Token ID2597
Feature activation+3.51e-01

Pos logit contributions
andro+0.900
inyl+0.682
agers+0.682
endale+0.656
tro+0.653
Neg logit contributions
nces-0.711
tenance-0.686
reath-0.609
ned-0.603
 drown-0.585
Token in
Token ID287
Feature activation+5.05e-03

Pos logit contributions
andro+0.342
inyl+0.254
agers+0.253
endale+0.243
tro+0.241
Neg logit contributions
nces-0.312
tenance-0.302
reath-0.271
ned-0.269
 drown-0.262
Token the
Token ID262
Feature activation-2.14e-01

Pos logit contributions
andro+0.005
inyl+0.004
agers+0.004
endale+0.004
tro+0.004
Neg logit contributions
nces-0.004
tenance-0.004
reath-0.004
ned-0.004
 drown-0.004
Token run
Token ID1057
Feature activation-1.16e+00

Pos logit contributions
nces+0.178
tenance+0.172
reath+0.153
ned+0.152
 drown+0.148
Neg logit contributions
andro-0.221
inyl-0.167
agers-0.166
endale-0.160
tro-0.159
Token-
Token ID12
Feature activation-7.53e-01

Pos logit contributions
nces+1.038
tenance+1.005
reath+0.904
ned+0.897
 drown+0.870
Neg logit contributions
andro-1.136
inyl-0.843
agers-0.839
endale-0.805
tro-0.800
Tokenup
Token ID929
Feature activation+2.18e+00

Pos logit contributions
nces+0.775
tenance+0.756
reath+0.690
ned+0.687
 drown+0.665
Neg logit contributions
andro-0.627
inyl-0.439
agers-0.434
endale-0.412
tro-0.408
Token way
Token ID835
Feature activation-2.56e-01

Pos logit contributions
andro+0.410
inyl+0.309
agers+0.308
endale+0.296
tro+0.295
Neg logit contributions
nces-0.337
tenance-0.324
reath-0.290
ned-0.286
 drown-0.278
Token I
Token ID314
Feature activation-4.45e-01

Pos logit contributions
nces+0.213
tenance+0.206
reath+0.183
ned+0.181
 drown+0.176
Neg logit contributions
andro-0.264
inyl-0.199
agers-0.199
endale-0.191
tro-0.191
Token'm
Token ID1101
Feature activation-7.75e-01

Pos logit contributions
nces+0.330
tenance+0.318
reath+0.279
ned+0.275
 drown+0.266
Neg logit contributions
andro-0.499
inyl-0.388
agers-0.387
endale-0.373
tro-0.372
Token building
Token ID2615
Feature activation-1.42e-01

Pos logit contributions
nces+0.590
tenance+0.568
reath+0.500
ned+0.499
 drown+0.483
Neg logit contributions
andro-0.849
inyl-0.656
agers-0.653
endale-0.632
tro-0.629
Token this
Token ID428
Feature activation+1.52e+00

Pos logit contributions
nces+0.120
tenance+0.116
reath+0.104
ned+0.102
 drown+0.099
Neg logit contributions
andro-0.145
agers-0.109
inyl-0.109
endale-0.105
tro-0.104
Token ROM
Token ID21224
Feature activation-8.05e-01

Pos logit contributions
andro+1.654
agers+1.270
inyl+1.268
tro+1.223
endale+1.218
Neg logit contributions
nces-1.190
tenance-1.131
reath-1.004
ned-0.984
 drown-0.950
Token,
Token ID11
Feature activation+2.09e-01

Pos logit contributions
nces+0.696
tenance+0.673
reath+0.603
ned+0.599
 drown+0.581
Neg logit contributions
andro-0.806
inyl-0.604
agers-0.601
endale-0.578
tro-0.574
Token moves
Token ID6100
Feature activation+3.00e+00

Pos logit contributions
andro+0.205
inyl+0.153
agers+0.152
endale+0.146
tro+0.145
Neg logit contributions
nces-0.185
tenance-0.179
reath-0.161
ned-0.160
 drown-0.155
Token /
Token ID1220
Feature activation+1.35e+00

Pos logit contributions
andro+2.972
inyl+2.200
agers+2.195
tro+2.105
endale+2.101
Neg logit contributions
nces-2.619
tenance-2.523
reath-2.266
ned-2.217
 drown-2.169
Tokens
Token ID82
Feature activation-5.32e-01

Pos logit contributions
andro+1.280
agers+0.934
inyl+0.932
tro+0.892
endale+0.890
Neg logit contributions
nces-1.250
tenance-1.208
reath-1.089
ned-1.079
 drown-1.054
Tokenbin
Token ID8800
Feature activation-7.26e+00

Pos logit contributions
nces+0.349
tenance+0.334
reath+0.288
ned+0.284
 drown+0.273
Neg logit contributions
andro-0.643
inyl-0.509
agers-0.508
endale-0.492
tro-0.490
Token Catholic
Token ID7835
Feature activation+3.11e+00

Pos logit contributions
nces+1.318
tenance+1.274
reath+1.138
ned+1.133
 drown+1.098
Neg logit contributions
andro-1.629
inyl-1.230
agers-1.225
endale-1.182
tro-1.173
Token truth
Token ID3872
Feature activation+1.08e+00

Pos logit contributions
andro+3.007
inyl+2.228
agers+2.223
endale+2.131
tro+2.118
Neg logit contributions
nces-2.773
tenance-2.667
reath-2.398
ned-2.370
 drown-2.301
Token ought
Token ID10783
Feature activation-1.62e+00

Pos logit contributions
andro+1.096
agers+0.823
inyl+0.822
endale+0.790
tro+0.785
Neg logit contributions
nces-0.920
tenance-0.889
reath-0.795
ned-0.786
 drown-0.763
Token not
Token ID407
Feature activation-1.86e+00

Pos logit contributions
nces+1.263
tenance+1.217
reath+1.075
ned+1.067
 drown+1.032
Neg logit contributions
andro-1.755
inyl-1.348
agers-1.343
endale-1.296
tro-1.288
Token only
Token ID691
Feature activation-9.27e-01

Pos logit contributions
nces+1.415
tenance+1.360
reath+1.200
ned+1.184
 drown+1.144
Neg logit contributions
andro-2.051
inyl-1.582
agers-1.581
endale-1.524
tro-1.517
Token to
Token ID284
Feature activation-7.34e-01

Pos logit contributions
nces+0.714
tenance+0.687
reath+0.607
ned+0.599
 drown+0.579
Neg logit contributions
andro-1.017
inyl-0.782
agers-0.782
endale-0.753
tro-0.750
Token teach
Token ID4545
Feature activation-3.69e-01

Pos logit contributions
nces+0.541
tenance+0.519
reath+0.455
ned+0.450
 drown+0.434
Neg logit contributions
andro-0.828
inyl-0.644
agers-0.643
endale-0.620
tro-0.618
Token the
Token ID262
Feature activation-3.88e-01

Pos logit contributions
nces+0.303
tenance+0.292
reath+0.260
ned+0.259
 drown+0.251
Neg logit contributions
andro-0.385
inyl-0.293
agers-0.292
endale-0.281
tro-0.279
Token proficient
Token ID39318
Feature activation-3.47e+00

Pos logit contributions
nces+0.326
tenance+0.315
reath+0.281
ned+0.278
 drown+0.270
Neg logit contributions
andro-0.398
inyl-0.301
agers-0.300
endale-0.288
tro-0.287
Token,
Token ID11
Feature activation+1.86e-01

Pos logit contributions
nces+2.882
tenance+2.790
ned+2.496
reath+2.478
 drown+2.402
Neg logit contributions
andro-3.548
inyl-2.704
agers-2.661
endale-2.578
tro-2.545
Token but
Token ID475
Feature activation+8.40e-01

Pos logit contributions
andro+0.178
inyl+0.131
agers+0.130
endale+0.125
tro+0.124
Neg logit contributions
nces-0.169
tenance-0.164
reath-0.148
ned-0.147
 drown-0.143
Token fact
Token ID1109
Feature activation+1.30e+00

Pos logit contributions
andro+2.143
agers+1.595
inyl+1.589
endale+1.520
tro+1.507
Neg logit contributions
nces-2.015
tenance-1.948
reath-1.752
ned-1.727
 drown-1.681
Tokenoring
Token ID3255
Feature activation-1.55e+00

Pos logit contributions
andro+1.392
inyl+1.066
agers+1.064
endale+1.025
tro+1.019
Neg logit contributions
nces-1.027
tenance-0.989
reath-0.876
ned-0.867
 drown-0.840
Token in
Token ID287
Feature activation+1.11e-01

Pos logit contributions
nces+1.296
tenance+1.255
reath+1.120
ned+1.119
 drown+1.083
Neg logit contributions
andro-1.597
inyl-1.205
agers-1.193
endale-1.151
tro-1.145
Token Kim
Token ID6502
Feature activation+1.47e+00

Pos logit contributions
andro+0.112
inyl+0.084
agers+0.084
endale+0.081
tro+0.080
Neg logit contributions
nces-0.095
tenance-0.092
reath-0.082
ned-0.082
 drown-0.079
Tokenb
Token ID65
Feature activation-3.23e+00

Pos logit contributions
andro+1.292
inyl+0.920
agers+0.919
endale+0.874
tro+0.869
Neg logit contributions
nces-1.449
tenance-1.405
reath-1.277
ned-1.266
 drown-1.237
Tokenrel
Token ID2411
Feature activation-1.18e+00

Pos logit contributions
nces+2.187
tenance+2.129
reath+1.877
ned+1.870
 drown+1.752
Neg logit contributions
andro-3.769
agers-2.959
inyl-2.952
endale-2.847
tro-2.818
Token
Token ID447
Feature activation+3.89e-01

Pos logit contributions
nces+0.935
tenance+0.905
reath+0.799
ned+0.796
 drown+0.772
Neg logit contributions
andro-1.273
inyl-0.974
agers-0.967
endale-0.932
tro-0.930
Token
Token ID247
Feature activation+6.29e-01

Pos logit contributions
andro+0.461
inyl+0.364
agers+0.363
tro+0.351
endale+0.350
Neg logit contributions
nces-0.264
tenance-0.252
reath-0.219
ned-0.216
 drown-0.208
Tokens
Token ID82
Feature activation-2.88e-01

Pos logit contributions
andro+0.417
inyl+0.260
agers+0.258
endale+0.239
tro+0.236
Neg logit contributions
nces-0.756
tenance-0.738
reath-0.683
ned-0.679
 drown-0.665
Token $
Token ID720
Feature activation+1.91e+00

Pos logit contributions
nces+0.256
tenance+0.248
reath+0.223
ned+0.222
 drown+0.216
Neg logit contributions
andro-0.280
inyl-0.208
agers-0.206
endale-0.199
tro-0.197
Token34
Token ID2682
Feature activation+5.79e-01

Pos logit contributions
andro+1.829
agers+1.346
inyl+1.346
endale+1.287
tro+1.284
Neg logit contributions
nces-1.738
tenance-1.673
reath-1.510
ned-1.492
 drown-1.464
Token have
Token ID423
Feature activation+8.72e-01

Pos logit contributions
nces+0.318
tenance+0.306
reath+0.270
ned+0.268
 drown+0.260
Neg logit contributions
andro-0.449
inyl-0.345
agers-0.344
endale-0.332
tro-0.330
Token taken
Token ID2077
Feature activation-7.21e-01

Pos logit contributions
andro+0.834
inyl+0.615
agers+0.613
endale+0.587
tro+0.583
Neg logit contributions
nces-0.792
tenance-0.767
reath-0.691
ned-0.686
 drown-0.668
Token a
Token ID257
Feature activation+1.33e-01

Pos logit contributions
nces+0.577
tenance+0.556
reath+0.495
ned+0.492
 drown+0.477
Neg logit contributions
andro-0.765
inyl-0.584
agers-0.581
endale-0.562
tro-0.559
Token form
Token ID1296
Feature activation+4.68e-01

Pos logit contributions
andro+0.139
inyl+0.105
agers+0.105
endale+0.101
tro+0.101
Neg logit contributions
nces-0.109
tenance-0.106
reath-0.094
ned-0.093
 drown-0.090
Token less
Token ID1342
Feature activation-1.12e+00

Pos logit contributions
andro+0.476
inyl+0.358
agers+0.358
endale+0.343
tro+0.341
Neg logit contributions
nces-0.398
tenance-0.384
reath-0.343
ned-0.340
 drown-0.330
Token distract
Token ID11786
Feature activation-5.09e+00

Pos logit contributions
nces+0.911
tenance+0.882
reath+0.785
ned+0.782
 drown+0.758
Neg logit contributions
andro-1.174
inyl-0.894
agers-0.889
endale-0.855
tro-0.851
Tokeningly
Token ID4420
Feature activation+7.54e-01

Pos logit contributions
nces+3.897
tenance+3.732
reath+3.347
ned+3.333
 drown+3.161
Neg logit contributions
andro-5.481
inyl-4.280
agers-4.239
endale-4.050
tro-4.010
Token reminiscent
Token ID24960
Feature activation-5.46e-01

Pos logit contributions
andro+0.794
agers+0.603
inyl+0.602
endale+0.579
tro+0.577
Neg logit contributions
nces-0.613
tenance-0.591
reath-0.525
ned-0.518
 drown-0.503
Token of
Token ID286
Feature activation-1.26e+00

Pos logit contributions
nces+0.458
tenance+0.444
reath+0.396
ned+0.391
 drown+0.380
Neg logit contributions
andro-0.560
agers-0.422
inyl-0.421
endale-0.405
tro-0.404
Token the
Token ID262
Feature activation-2.08e-01

Pos logit contributions
nces+1.063
tenance+1.026
reath+0.918
ned+0.913
 drown+0.886
Neg logit contributions
andro-1.284
inyl-0.968
agers-0.965
endale-0.929
tro-0.924
Token American
Token ID1605
Feature activation-1.02e+00

Pos logit contributions
nces+0.173
tenance+0.167
reath+0.149
ned+0.147
 drown+0.143
Neg logit contributions
andro-0.215
inyl-0.162
agers-0.162
endale-0.156
tro-0.155
Token as
Token ID355
Feature activation-8.70e-01

Pos logit contributions
andro+0.462
inyl+0.352
agers+0.352
endale+0.338
tro+0.337
Neg logit contributions
nces-0.350
tenance-0.337
reath-0.299
ned-0.297
 drown-0.287
Token well
Token ID880
Feature activation+3.79e-01

Pos logit contributions
nces+0.696
tenance+0.670
reath+0.595
ned+0.591
 drown+0.574
Neg logit contributions
andro-0.928
inyl-0.708
agers-0.706
endale-0.680
tro-0.675
Token as
Token ID355
Feature activation-1.13e+00

Pos logit contributions
andro+0.334
inyl+0.240
agers+0.239
endale+0.228
tro+0.226
Neg logit contributions
nces-0.373
tenance-0.362
reath-0.327
ned-0.325
 drown-0.317
Token the
Token ID262
Feature activation-2.92e-01

Pos logit contributions
nces+0.919
tenance+0.887
reath+0.788
ned+0.781
 drown+0.756
Neg logit contributions
andro-1.182
inyl-0.899
agers-0.897
endale-0.863
tro-0.859
Token rest
Token ID1334
Feature activation-3.66e+00

Pos logit contributions
nces+0.242
tenance+0.235
reath+0.209
ned+0.207
 drown+0.201
Neg logit contributions
andro-0.301
inyl-0.228
agers-0.227
endale-0.219
tro-0.217
Token of
Token ID286
Feature activation-1.19e+00

Pos logit contributions
nces+2.740
tenance+2.665
ned+2.362
reath+2.330
 drown+2.242
Neg logit contributions
andro-4.010
inyl-3.123
agers-3.074
endale-2.979
tro-2.942
Token our
Token ID674
Feature activation+1.73e+00

Pos logit contributions
nces+1.018
tenance+0.987
reath+0.884
ned+0.877
 drown+0.851
Neg logit contributions
andro-1.197
inyl-0.899
agers-0.895
endale-0.862
tro-0.853
Token allies
Token ID7681
Feature activation-1.68e+00

Pos logit contributions
andro+1.803
agers+1.366
inyl+1.366
endale+1.312
tro+1.310
Neg logit contributions
nces-1.421
tenance-1.368
reath-1.219
ned-1.204
 drown-1.170
Token across
Token ID1973
Feature activation+2.19e+00

Pos logit contributions
nces+1.367
tenance+1.327
reath+1.180
ned+1.177
 drown+1.140
Neg logit contributions
andro-1.757
inyl-1.338
agers-1.333
endale-1.280
tro-1.269
Token the
Token ID262
Feature activation-7.42e-02

Pos logit contributions
andro+2.124
inyl+1.577
agers+1.576
endale+1.504
tro+1.501
Neg logit contributions
nces-1.960
tenance-1.886
reath-1.693
ned-1.679
 drown-1.635
Token globe
Token ID13342
Feature activation-5.83e+00

Pos logit contributions
nces+0.061
tenance+0.059
reath+0.053
ned+0.053
 drown+0.051
Neg logit contributions
andro-0.077
inyl-0.058
agers-0.058
endale-0.056
tro-0.055
Token,
Token ID11
Feature activation+2.06e-01

Pos logit contributions
nces+0.267
tenance+0.257
reath+0.230
ned+0.230
 drown+0.222
Neg logit contributions
andro-0.324
inyl-0.245
agers-0.244
endale-0.235
tro-0.233
Token you
Token ID345
Feature activation-2.23e+00

Pos logit contributions
andro+0.208
inyl+0.156
agers+0.156
endale+0.150
tro+0.149
Neg logit contributions
nces-0.177
tenance-0.171
reath-0.153
ned-0.152
 drown-0.148
Token have
Token ID423
Feature activation+5.45e-01

Pos logit contributions
nces+1.778
tenance+1.715
reath+1.518
ned+1.517
 drown+1.475
Neg logit contributions
andro-2.376
inyl-1.820
agers-1.805
endale-1.745
tro-1.731
Token a
Token ID257
Feature activation-1.18e-01

Pos logit contributions
andro+0.562
inyl+0.425
agers+0.424
endale+0.407
tro+0.406
Neg logit contributions
nces-0.456
tenance-0.440
reath-0.392
ned-0.388
 drown-0.376
Token hot
Token ID3024
Feature activation+2.06e-01

Pos logit contributions
nces+0.097
tenance+0.094
reath+0.083
ned+0.083
 drown+0.080
Neg logit contributions
andro-0.124
inyl-0.094
agers-0.094
endale-0.090
tro-0.090
Token bod
Token ID16429
Feature activation-5.79e+00

Pos logit contributions
andro+0.219
inyl+0.167
agers+0.167
endale+0.161
tro+0.160
Neg logit contributions
nces-0.166
tenance-0.160
reath-0.142
ned-0.141
 drown-0.136
Token.
Token ID13
Feature activation+7.10e-02

Pos logit contributions
nces+4.556
tenance+4.477
ned+4.033
reath+3.995
 drown+3.800
Neg logit contributions
andro-6.026
agers-4.617
inyl-4.595
endale-4.411
tro-4.380
Token Let
Token ID3914
Feature activation+1.00e+00

Pos logit contributions
andro+0.070
inyl+0.052
agers+0.052
endale+0.050
tro+0.050
Neg logit contributions
nces-0.062
tenance-0.060
reath-0.054
ned-0.054
 drown-0.052
Token's
Token ID338
Feature activation+6.60e-01

Pos logit contributions
andro+1.123
agers+0.872
inyl+0.868
tro+0.838
endale+0.837
Neg logit contributions
nces-0.744
tenance-0.716
reath-0.632
ned-0.616
 drown-0.597
Token not
Token ID407
Feature activation-1.80e+00

Pos logit contributions
andro+0.725
inyl+0.560
agers+0.559
endale+0.537
tro+0.536
Neg logit contributions
nces-0.507
tenance-0.487
reath-0.430
ned-0.423
 drown-0.407
Token pretend
Token ID16614
Feature activation-1.28e+00

Pos logit contributions
nces+1.307
tenance+1.256
reath+1.100
ned+1.092
 drown+1.059
Neg logit contributions
andro-2.039
inyl-1.585
agers-1.583
endale-1.532
tro-1.521
Tokenord
Token ID585
Feature activation+1.04e+00

Pos logit contributions
nces+0.601
tenance+0.584
reath+0.527
ned+0.525
 drown+0.508
Neg logit contributions
andro-0.614
inyl-0.449
agers-0.448
endale-0.429
tro-0.425
Tokeninated
Token ID3898
Feature activation-1.22e+00

Pos logit contributions
andro+1.181
inyl+0.919
agers+0.918
endale+0.887
tro+0.884
Neg logit contributions
nces-0.752
tenance-0.724
reath-0.634
ned-0.628
 drown-0.604
Token campaign
Token ID1923
Feature activation+1.16e+00

Pos logit contributions
nces+0.981
tenance+0.949
reath+0.842
ned+0.838
 drown+0.812
Neg logit contributions
andro-1.293
inyl-0.984
agers-0.983
endale-0.945
tro-0.938
Token by
Token ID416
Feature activation+7.93e-01

Pos logit contributions
andro+1.149
inyl+0.860
agers+0.859
endale+0.825
tro+0.823
Neg logit contributions
nces-1.006
tenance-0.970
reath-0.866
ned-0.856
 drown-0.831
Token Muslim
Token ID3765
Feature activation-1.48e+00

Pos logit contributions
andro+0.784
inyl+0.586
agers+0.585
endale+0.561
tro+0.559
Neg logit contributions
nces-0.694
tenance-0.671
reath-0.601
ned-0.594
 drown-0.577
Token nations
Token ID7027
Feature activation-5.67e+00

Pos logit contributions
nces+1.268
tenance+1.229
reath+1.102
ned+1.099
 drown+1.067
Neg logit contributions
andro-1.474
inyl-1.105
agers-1.102
endale-1.058
tro-1.049
Token against
Token ID1028
Feature activation+1.66e+00

Pos logit contributions
nces+4.579
tenance+4.390
ned+4.019
reath+3.961
 drown+3.895
Neg logit contributions
andro-5.811
agers-4.407
inyl-4.399
endale-4.216
tro-4.179
Token Sweden
Token ID10710
Feature activation+1.13e+00

Pos logit contributions
andro+1.745
inyl+1.324
agers+1.323
endale+1.268
tro+1.266
Neg logit contributions
nces-1.365
tenance-1.315
reath-1.164
ned-1.142
 drown-1.106
Token is
Token ID318
Feature activation+1.64e+00

Pos logit contributions
andro+1.146
inyl+0.865
agers+0.862
endale+0.829
tro+0.825
Neg logit contributions
nces-0.961
tenance-0.925
reath-0.824
ned-0.812
 Shroud-0.789
Token not
Token ID407
Feature activation-1.41e+00

Pos logit contributions
andro+1.661
inyl+1.250
agers+1.248
endale+1.197
tro+1.191
Neg logit contributions
nces-1.392
tenance-1.346
reath-1.203
ned-1.189
 drown-1.152
Token a
Token ID257
Feature activation-2.90e-01

Pos logit contributions
nces+1.180
tenance+1.140
reath+1.015
ned+1.013
 drown+0.984
Neg logit contributions
andro-1.444
inyl-1.090
agers-1.089
endale-1.048
tro-1.038
Token it
Token ID340
Feature activation-7.20e-01

Pos logit contributions
andro+1.160
inyl+0.877
agers+0.873
endale+0.840
tro+0.835
Neg logit contributions
nces-0.947
tenance-0.915
reath-0.818
ned-0.813
 drown-0.788
Token should
Token ID815
Feature activation-4.26e-01

Pos logit contributions
nces+0.660
tenance+0.639
reath+0.580
ned+0.579
 drown+0.561
Neg logit contributions
andro-0.679
inyl-0.500
agers-0.497
endale-0.475
tro-0.474
Token be
Token ID307
Feature activation-6.76e-02

Pos logit contributions
nces+0.322
tenance+0.310
reath+0.272
ned+0.270
 drown+0.261
Neg logit contributions
andro-0.473
inyl-0.366
agers-0.365
endale-0.352
tro-0.351
Token part
Token ID636
Feature activation+1.84e-01

Pos logit contributions
nces+0.058
tenance+0.057
reath+0.051
ned+0.050
 drown+0.049
Neg logit contributions
andro-0.068
inyl-0.051
agers-0.050
endale-0.048
tro-0.048
Token of
Token ID286
Feature activation-1.24e+00

Pos logit contributions
andro+0.195
inyl+0.149
agers+0.149
endale+0.143
tro+0.142
Neg logit contributions
nces-0.148
tenance-0.143
reath-0.127
ned-0.127
 drown-0.122
Token Somalia
Token ID23918
Feature activation-7.04e+00

Pos logit contributions
nces+0.976
tenance+0.944
reath+0.841
ned+0.835
 drown+0.802
Neg logit contributions
andro-1.332
inyl-1.023
agers-1.017
endale-0.983
tro-0.975
Token,
Token ID11
Feature activation+4.17e-01

Pos logit contributions
nces+5.254
tenance+5.191
ned+4.708
reath+4.609
 drown+4.463
Neg logit contributions
andro-7.391
inyl-5.725
agers-5.724
endale-5.449
tro-5.436
Token not
Token ID407
Feature activation-1.84e+00

Pos logit contributions
andro+0.419
inyl+0.314
agers+0.313
endale+0.301
tro+0.299
Neg logit contributions
nces-0.359
tenance-0.347
reath-0.310
ned-0.307
 drown-0.298
Token Kenya
Token ID21506
Feature activation-8.00e+00

Pos logit contributions
nces+1.447
tenance+1.399
reath+1.242
ned+1.234
 drown+1.198
Neg logit contributions
andro-1.983
inyl-1.519
agers-1.518
endale-1.457
tro-1.453
Token.
Token ID13
Feature activation-7.21e-02

Pos logit contributions
nces+5.749
tenance+5.645
ned+5.133
reath+5.063
 drown+4.890
Neg logit contributions
andro-8.485
inyl-6.589
agers-6.566
tro-6.332
endale-6.256
Token Ken
Token ID7148
Feature activation-4.25e+00

Pos logit contributions
nces+0.061
tenance+0.059
reath+0.052
ned+0.052
 drown+0.050
Neg logit contributions
andro-0.074
inyl-0.056
agers-0.056
endale-0.053
tro-0.053
Token directly
Token ID3264
Feature activation+1.40e+00

Pos logit contributions
nces+1.785
tenance+1.733
ned+1.565
reath+1.558
 drown+1.492
Neg logit contributions
andro-2.374
agers-1.810
inyl-1.808
endale-1.729
tro-1.726
Token from
Token ID422
Feature activation-2.30e-02

Pos logit contributions
andro+1.427
inyl+1.075
agers+1.071
endale+1.029
tro+1.024
Neg logit contributions
nces-1.190
tenance-1.149
reath-1.025
ned-1.015
 drown-0.986
Token the
Token ID262
Feature activation-2.12e-01

Pos logit contributions
nces+0.018
tenance+0.018
reath+0.016
ned+0.016
 drown+0.015
Neg logit contributions
andro-0.024
inyl-0.019
agers-0.019
endale-0.018
tro-0.018
Token government
Token ID1230
Feature activation-1.29e+00

Pos logit contributions
nces+0.164
tenance+0.159
reath+0.140
ned+0.139
 drown+0.135
Neg logit contributions
andro-0.231
inyl-0.177
agers-0.177
endale-0.171
tro-0.169
Token of
Token ID286
Feature activation-1.29e+00

Pos logit contributions
nces+1.050
tenance+1.020
reath+0.908
ned+0.905
 drown+0.876
Neg logit contributions
andro-1.345
inyl-1.020
agers-1.013
endale-0.978
tro-0.971
Token Haiti
Token ID25051
Feature activation-5.36e+00

Pos logit contributions
nces+0.992
tenance+0.959
reath+0.848
ned+0.839
 drown+0.811
Neg logit contributions
andro-1.405
inyl-1.083
agers-1.078
endale-1.040
tro-1.033
Token and
Token ID290
Feature activation-3.95e-01

Pos logit contributions
nces+4.160
tenance+4.114
ned+3.692
reath+3.650
 drown+3.552
Neg logit contributions
andro-5.596
inyl-4.256
agers-4.248
endale-4.088
tro-4.063
Token would
Token ID561
Feature activation+1.80e-01

Pos logit contributions
nces+0.318
tenance+0.306
reath+0.272
ned+0.269
 drown+0.261
Neg logit contributions
andro-0.419
inyl-0.320
agers-0.319
endale-0.307
tro-0.306
Token lose
Token ID4425
Feature activation+3.01e-01

Pos logit contributions
andro+0.194
inyl+0.149
agers+0.148
endale+0.143
tro+0.142
Neg logit contributions
nces-0.143
tenance-0.137
reath-0.121
ned-0.119
 Shroud-0.115
Token their
Token ID511
Feature activation+5.69e-01

Pos logit contributions
andro+0.318
inyl+0.242
agers+0.241
endale+0.232
tro+0.231
Neg logit contributions
nces-0.243
tenance-0.235
reath-0.209
ned-0.208
 drown-0.201
Token profit
Token ID7630
Feature activation-3.14e-02

Pos logit contributions
andro+0.585
inyl+0.441
agers+0.441
endale+0.423
tro+0.421
Neg logit contributions
nces-0.476
tenance-0.460
reath-0.410
ned-0.407
 drown-0.395
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
andro+0.054
inyl+0.040
agers+0.040
endale+0.038
tro+0.038
Neg logit contributions
nces-0.047
tenance-0.046
reath-0.041
ned-0.041
 drown-0.039
TokenHowever
Token ID4864
Feature activation-4.43e-01

Pos logit contributions
nces+0.149
tenance+0.145
reath+0.130
ned+0.129
 drown+0.125
Neg logit contributions
andro-0.158
inyl-0.117
agers-0.116
endale-0.112
tro-0.111
Token,
Token ID11
Feature activation+2.70e-01

Pos logit contributions
nces+0.382
tenance+0.369
reath+0.330
ned+0.328
 drown+0.318
Neg logit contributions
andro-0.444
inyl-0.332
agers-0.332
endale-0.318
tro-0.316
Token the
Token ID262
Feature activation-5.76e-01

Pos logit contributions
andro+0.275
inyl+0.207
agers+0.207
endale+0.198
tro+0.197
Neg logit contributions
nces-0.229
tenance-0.221
reath-0.197
ned-0.196
 drown-0.190
Token new
Token ID649
Feature activation+1.69e+00

Pos logit contributions
nces+0.462
tenance+0.447
reath+0.397
ned+0.394
 drown+0.381
Neg logit contributions
andro-0.611
inyl-0.467
agers-0.464
endale-0.448
tro-0.444
Token Haiti
Token ID25051
Feature activation-6.17e+00

Pos logit contributions
andro+1.849
agers+1.424
inyl+1.421
tro+1.369
endale+1.366
Neg logit contributions
nces-1.296
tenance-1.241
reath-1.094
ned-1.082
 drown-1.049
Token-
Token ID12
Feature activation-5.52e-01

Pos logit contributions
nces+4.760
tenance+4.635
ned+4.194
reath+4.190
 drown+4.001
Neg logit contributions
andro-6.459
inyl-4.966
agers-4.907
endale-4.797
tro-4.642
TokenV
Token ID53
Feature activation+1.49e+00

Pos logit contributions
nces+0.483
tenance+0.468
reath+0.420
ned+0.417
 drown+0.404
Neg logit contributions
andro-0.547
inyl-0.408
agers-0.407
endale-0.390
tro-0.387
Tokenenezuel
Token ID12596
Feature activation-3.88e+00

Pos logit contributions
andro+1.486
agers+1.106
inyl+1.106
endale+1.064
tro+1.052
Neg logit contributions
nces-1.278
tenance-1.237
reath-1.116
ned-1.110
 drown-1.070
Tokena
Token ID64
Feature activation-2.19e+00

Pos logit contributions
nces+3.910
tenance+3.865
reath+3.572
ned+3.527
 Shroud+3.436
Neg logit contributions
andro-3.147
agers-2.214
inyl-2.189
endale-2.098
tro-2.059
Token alliance
Token ID12801
Feature activation+3.08e+00

Pos logit contributions
nces+2.022
tenance+1.992
reath+1.799
ned+1.798
 drown+1.739
Neg logit contributions
andro-2.027
inyl-1.484
agers-1.472
endale-1.418
tro-1.386