TOP ACTIVATIONS
MAX = 10.930

has repeatedly criticized President Trump Donald John Trump House committee believes
against former President Barack Obama Barack Hussein Obama With low birth
election matchup between Donald Trump Donald John Trump House committee believes
with Republican nominee Donald Trump Donald John Trump House committee believes
Washington Examiner , Donald Trump Donald John Trump READ : Cohen
President Trump Donald John Trump House committee believes it has evidence
© K elli ( fl ickr : brow nd og _
Donald Trump Donald John Trump House committee believes it has evidence
Donald Trump Donald John Trump House committee believes it has evidence
During these two ch or uses starting at about 1
regrets , and what would you have liked to have done
repeatedly criticized President Trump Donald John Trump House committee believes it
all its power and grand eur , is fragile . Its
in IM for the sake of putting something in the
= Table [ { Keys [ search Space ][ [ i
ist ling or just ch or uses of hey
matchup between Donald Trump Donald John Trump House committee believes it
ub ges hig Rice / CBC ) Insp ired
However , this year is different because beside marking the end
Examiner , Donald Trump Donald John Trump READ : Cohen testimony

MIN ACTIVATIONS
MIN = -9.756

If all that wasn 't enough , the Yet i himself
explained . Next Page > <|endoftext|> Late in
if all of this not enough , the events also create
co . uk / business / analysis / why - aut
breach notifications is not nearly enough . There is a gathering
things they can 't get enough of . But as any
as if that wasn 't enough to tick le God 's
that s not enough fortune telling , there are
, just outside of present - day Baghdad , Iraq .
ground . com / 2016 / 09 / 08 / the
that s not enough , Da um Games have
uk / business / analysis / why - aut om ation
However , this is barely enough for any realistic optimism .
of Sciences . Explore further : New Insight Into
. uk / in coming / article 35 79 23 12
legraph . co . uk / business / analysis / why
45 287 119 8 ; adventure company . co . uk
ee pl inks / 2016 / 06 / t att oo
bur . org / 2015 / 08 / 11 / e
Size () ; for ( size _ t u Part icle

INTERVAL 5.759 - 10.930
CONTAINS 0.028%

former President Barack Obama Barack Hussein Obama With low birth rate
" f aint yells for help on the roadway from the
smooth ie d are I say it ever ?
Donald Trump Donald John Trump House committee believes it has evidence
all during these two ch or uses , but a regret

INTERVAL 0.587 - 5.759
CONTAINS 34.384%

filed against Wells Fargo which is accused of directing minority
dialogue (" Hey , Ker mit !" and " Yeah !
people don 't know who the Koch brothers are ."
signal pand emic imminent . Phase 6 : Virus spreads to
: Cho osing Life after an U nexpected P ren atal

INTERVAL -4.584 - 0.587
CONTAINS 65.297%

that this is what we must expect , but such will
Crit ique : Three of us did the full
PR and supporter liaison manager at Newcastle United , said :
tenants couldn t afford the rent when their subsidy
it became " a source of much amusement , laughing and

INTERVAL -9.756 - -4.584
CONTAINS 0.291%

attract you ? - January 15 , 2010 Que er magnet
2015 2017 ) [ edit ] 2015
The delayed Cy gn us mission comes
per cent , chances are pretty good that you found yourself
dummy will go a long way . We can only hope
Token has
Token ID468
Feature activation+1.72e+00

Pos logit contributions
�士+0.437
+0.431
Moh+0.420
Austral+0.418
ouf+0.393
Neg logit contributions
channelAvailability-0.497
estinal-0.418
 emanc-0.385
 virginity-0.372
ufact-0.371
Token repeatedly
Token ID7830
Feature activation-5.22e-01

Pos logit contributions
�士+1.247
+1.225
Moh+1.201
Austral+1.194
ouf+1.119
Neg logit contributions
channelAvailability-1.481
estinal-1.252
 emanc-1.145
ufact-1.112
 virginity-1.109
Token criticized
Token ID12318
Feature activation+1.02e+00

Pos logit contributions
channelAvailability+0.449
estinal+0.382
 emanc+0.357
 virginity+0.344
ufact+0.339
Neg logit contributions
�士-0.381
-0.370
Austral-0.362
Moh-0.362
ouf-0.339
Token President
Token ID1992
Feature activation-1.30e+00

Pos logit contributions
�士+0.720
+0.702
Moh+0.687
Austral+0.684
ouf+0.640
Neg logit contributions
channelAvailability-0.910
estinal-0.774
 emanc-0.719
 virginity-0.694
ufact-0.692
Token Trump
Token ID1301
Feature activation-1.16e+00

Pos logit contributions
channelAvailability+1.202
estinal+1.040
 emanc+0.976
 virginity+0.946
ufact+0.933
Neg logit contributions
�士-0.860
-0.831
Austral-0.810
Moh-0.806
ouf-0.753
Token Donald
Token ID3759
Feature activation+1.09e+01

Pos logit contributions
channelAvailability+0.931
estinal+0.781
 emanc+0.729
 virginity+0.701
ufact+0.689
Neg logit contributions
�士-0.909
-0.883
Austral-0.866
Moh-0.862
ouf-0.811
Token John
Token ID1757
Feature activation+7.42e+00

Pos logit contributions
Moh+5.442
Austral+5.378
lection+5.143
 McGr+4.941
�士+4.939
Neg logit contributions
channelAvailability-10.965
estinal-10.036
ufact-9.441
 emanc-9.379
 unlaw-9.092
Token Trump
Token ID1301
Feature activation+4.49e+00

Pos logit contributions
�士+3.122
+3.029
Moh+2.991
Austral+2.779
729+2.775
Neg logit contributions
channelAvailability-8.377
estinal-7.367
 emanc-7.032
 mathemat-7.010
ufact-6.989
TokenHouse
Token ID18102
Feature activation+8.97e+00

Pos logit contributions
�士+2.401
Moh+2.365
Austral+2.332
+2.256
Carter+2.126
Neg logit contributions
channelAvailability-4.687
estinal-4.126
 emanc-3.912
ufact-3.878
 virginity-3.821
Token committee
Token ID5583
Feature activation+5.04e+00

Pos logit contributions
�士+5.840
Moh+5.565
+5.204
729+5.125
lection+5.114
Neg logit contributions
channelAvailability-8.343
estinal-6.570
ufact-6.270
 mathemat-6.268
 emanc-6.251
Token believes
Token ID5804
Feature activation+3.43e+00

Pos logit contributions
�士+3.517
+3.312
Moh+3.298
Austral+3.267
729+3.188
Neg logit contributions
channelAvailability-4.499
estinal-3.802
ufact-3.536
 emanc-3.504
 virginity-3.453
Token against
Token ID1028
Feature activation-2.23e-01

Pos logit contributions
channelAvailability+0.295
estinal+0.248
 emanc+0.230
 virginity+0.222
ufact+0.219
Neg logit contributions
�士-0.272
-0.265
Moh-0.260
Austral-0.259
ouf-0.244
Token former
Token ID1966
Feature activation+8.03e-01

Pos logit contributions
channelAvailability+0.186
estinal+0.156
 emanc+0.144
 virginity+0.139
ufact+0.139
Neg logit contributions
�士-0.169
-0.165
Moh-0.162
Austral-0.162
ouf-0.152
Token President
Token ID1992
Feature activation-1.30e+00

Pos logit contributions
�士+0.574
+0.559
Moh+0.548
Austral+0.547
ouf+0.512
Neg logit contributions
channelAvailability-0.704
estinal-0.598
 emanc-0.550
ufact-0.538
 virginity-0.531
Token Barack
Token ID8732
Feature activation+6.42e-01

Pos logit contributions
channelAvailability+1.186
estinal+1.020
 emanc+0.957
 virginity+0.929
ufact+0.912
Neg logit contributions
�士-0.884
-0.853
Austral-0.834
Moh-0.829
ouf-0.779
Token Obama
Token ID2486
Feature activation-1.56e+00

Pos logit contributions
�士+0.460
+0.451
Moh+0.443
Austral+0.441
ouf+0.412
Neg logit contributions
channelAvailability-0.559
estinal-0.477
 emanc-0.442
 virginity-0.427
ufact-0.424
Token Barack
Token ID8732
Feature activation+9.70e+00

Pos logit contributions
channelAvailability+1.292
estinal+1.085
 emanc+1.017
 virginity+0.986
ufact+0.965
Neg logit contributions
�士-1.187
-1.133
Moh-1.119
Austral-1.119
ouf-1.054
Token Hussein
Token ID22983
Feature activation+5.98e+00

Pos logit contributions
Moh+3.548
Austral+3.202
�士+2.978
Lay+2.936
Carter+2.921
Neg logit contributions
channelAvailability-11.471
estinal-10.688
 emanc-9.805
ufact-9.798
 virginity-9.467
Token Obama
Token ID2486
Feature activation+3.60e+00

Pos logit contributions
Moh+3.501
Austral+3.489
�士+3.458
+3.414
Carter+3.242
Neg logit contributions
channelAvailability-5.761
estinal-5.071
 mathemat-4.621
 emanc-4.601
 virginity-4.517
TokenWith
Token ID3152
Feature activation+2.62e+00

Pos logit contributions
�士+2.068
Moh+2.014
Austral+2.010
+1.992
Carter+1.827
Neg logit contributions
channelAvailability-3.616
estinal-3.145
 emanc-2.968
ufact-2.897
 virginity-2.891
Token low
Token ID1877
Feature activation+3.25e+00

Pos logit contributions
�士+2.108
+2.060
Moh+2.019
Austral+2.016
ouf+1.902
Neg logit contributions
channelAvailability-2.056
estinal-1.713
 emanc-1.579
 virginity-1.518
ufact-1.502
Token birth
Token ID4082
Feature activation+4.78e-01

Pos logit contributions
+2.412
�士+2.314
Austral+2.288
Moh+2.242
ع+2.163
Neg logit contributions
channelAvailability-2.709
estinal-2.212
ufact-2.106
 mathemat-2.088
 emanc-2.063
Token election
Token ID3071
Feature activation-2.35e+00

Pos logit contributions
channelAvailability+0.154
estinal+0.128
 emanc+0.119
 virginity+0.114
ufact+0.109
Neg logit contributions
�士-0.170
-0.167
Moh-0.162
Austral-0.162
ouf-0.153
Token matchup
Token ID18406
Feature activation-1.68e+00

Pos logit contributions
channelAvailability+1.892
estinal+1.588
 emanc+1.480
 virginity+1.431
ufact+1.380
Neg logit contributions
�士-1.847
-1.794
Austral-1.758
Moh-1.754
ouf-1.652
Token between
Token ID1022
Feature activation+2.11e+00

Pos logit contributions
channelAvailability+1.316
estinal+1.093
 emanc+1.012
 virginity+0.974
ufact+0.954
Neg logit contributions
�士-1.368
-1.328
Austral-1.301
Moh-1.301
ouf-1.228
Token Donald
Token ID3759
Feature activation+3.45e-01

Pos logit contributions
�士+1.559
+1.529
Moh+1.497
Austral+1.488
lection+1.396
Neg logit contributions
channelAvailability-1.780
estinal-1.507
 emanc-1.386
ufact-1.343
 virginity-1.337
Token Trump
Token ID1301
Feature activation-1.23e+00

Pos logit contributions
�士+0.205
+0.199
Austral+0.193
Moh+0.193
ouf+0.178
Neg logit contributions
channelAvailability-0.344
estinal-0.298
 emanc-0.281
 virginity-0.273
ufact-0.271
Token Donald
Token ID3759
Feature activation+9.54e+00

Pos logit contributions
channelAvailability+0.986
estinal+0.822
 emanc+0.763
 virginity+0.735
ufact+0.722
Neg logit contributions
�士-0.969
-0.948
Austral-0.931
Moh-0.930
ouf-0.877
Token John
Token ID1757
Feature activation+7.22e+00

Pos logit contributions
Moh+5.112
Austral+5.014
lection+4.860
�士+4.749
Canada+4.629
Neg logit contributions
channelAvailability-9.340
estinal-8.472
 emanc-7.924
ufact-7.862
 virginity-7.583
Token Trump
Token ID1301
Feature activation+3.48e+00

Pos logit contributions
+2.934
�士+2.912
Moh+2.899
Austral+2.696
Carter+2.676
Neg logit contributions
channelAvailability-8.109
estinal-7.199
 mathemat-6.852
ufact-6.805
 emanc-6.796
TokenHouse
Token ID18102
Feature activation+8.46e+00

Pos logit contributions
�士+1.833
Moh+1.790
Austral+1.764
+1.727
Carter+1.609
Neg logit contributions
channelAvailability-3.668
estinal-3.226
 emanc-3.049
ufact-3.008
 virginity-2.965
Token committee
Token ID5583
Feature activation+5.28e+00

Pos logit contributions
�士+5.532
Moh+5.287
+5.124
729+5.004
Carter+4.907
Neg logit contributions
channelAvailability-7.699
estinal-6.169
 mathemat-5.961
ufact-5.808
 emanc-5.807
Token believes
Token ID5804
Feature activation+3.28e+00

Pos logit contributions
�士+3.549
Moh+3.297
+3.292
Austral+3.260
729+3.237
Neg logit contributions
channelAvailability-4.848
estinal-4.101
ufact-3.825
 emanc-3.785
 virginity-3.694
Token with
Token ID351
Feature activation+8.94e-02

Pos logit contributions
channelAvailability+1.799
estinal+1.510
 emanc+1.412
 virginity+1.362
ufact+1.330
Neg logit contributions
�士-1.679
-1.625
Austral-1.596
Moh-1.594
ouf-1.501
Token Republican
Token ID3415
Feature activation+3.80e-03

Pos logit contributions
�士+0.063
+0.062
Moh+0.061
Austral+0.060
ouf+0.056
Neg logit contributions
channelAvailability-0.079
estinal-0.067
 emanc-0.062
 virginity-0.060
ufact-0.060
Token nominee
Token ID10429
Feature activation+9.79e-01

Pos logit contributions
�士+0.003
+0.003
Moh+0.003
Austral+0.003
ouf+0.002
Neg logit contributions
channelAvailability-0.003
estinal-0.003
 emanc-0.003
 virginity-0.003
ufact-0.003
Token Donald
Token ID3759
Feature activation+2.35e+00

Pos logit contributions
�士+0.596
+0.577
Moh+0.562
Austral+0.561
ouf+0.519
Neg logit contributions
channelAvailability-0.962
estinal-0.833
 emanc-0.783
 virginity-0.761
ufact-0.753
Token Trump
Token ID1301
Feature activation-1.25e-01

Pos logit contributions
�士+1.349
+1.311
Moh+1.275
Austral+1.270
ouf+1.168
Neg logit contributions
channelAvailability-2.395
estinal-2.088
 emanc-1.967
 virginity-1.912
ufact-1.896
Token Donald
Token ID3759
Feature activation+9.51e+00

Pos logit contributions
channelAvailability+0.122
estinal+0.106
 emanc+0.100
 virginity+0.097
ufact+0.096
Neg logit contributions
�士-0.077
-0.075
Austral-0.073
Moh-0.073
ouf-0.067
Token John
Token ID1757
Feature activation+7.09e+00

Pos logit contributions
Moh+5.070
Austral+5.019
lection+4.841
�士+4.727
 McGr+4.594
Neg logit contributions
channelAvailability-9.370
estinal-8.466
ufact-7.876
 emanc-7.860
 mathemat-7.672
Token Trump
Token ID1301
Feature activation+3.18e+00

Pos logit contributions
+3.000
�士+2.960
Moh+2.931
Austral+2.759
Carter+2.717
Neg logit contributions
channelAvailability-7.906
estinal-6.981
ufact-6.642
 mathemat-6.616
 emanc-6.594
TokenHouse
Token ID18102
Feature activation+8.46e+00

Pos logit contributions
�士+1.676
Moh+1.620
Austral+1.604
+1.588
Carter+1.450
Neg logit contributions
channelAvailability-3.372
estinal-2.963
 emanc-2.802
ufact-2.746
 virginity-2.725
Token committee
Token ID5583
Feature activation+5.24e+00

Pos logit contributions
�士+5.520
Moh+5.232
+5.096
729+4.911
Carter+4.852
Neg logit contributions
channelAvailability-7.717
estinal-6.164
 mathemat-6.012
 emanc-5.903
ufact-5.846
Token believes
Token ID5804
Feature activation+3.06e+00

Pos logit contributions
�士+3.620
Moh+3.364
+3.364
Austral+3.314
lection+3.249
Neg logit contributions
channelAvailability-4.695
estinal-3.978
ufact-3.726
 emanc-3.657
 virginity-3.620
Token Washington
Token ID2669
Feature activation+1.95e+00

Pos logit contributions
channelAvailability+1.109
estinal+0.944
 emanc+0.885
 virginity+0.855
ufact+0.839
Neg logit contributions
�士-0.911
-0.884
Moh-0.861
Austral-0.861
ouf-0.807
Token Examiner
Token ID35855
Feature activation+2.04e+00

Pos logit contributions
�士+1.381
+1.350
Moh+1.326
Austral+1.308
ouf+1.227
Neg logit contributions
channelAvailability-1.729
estinal-1.460
 emanc-1.360
 virginity-1.313
ufact-1.304
Token,
Token ID11
Feature activation+7.67e-01

Pos logit contributions
�士+1.447
+1.412
Moh+1.379
Austral+1.373
ouf+1.291
Neg logit contributions
channelAvailability-1.797
estinal-1.526
 emanc-1.418
 virginity-1.371
ufact-1.360
Token Donald
Token ID3759
Feature activation+3.55e-01

Pos logit contributions
�士+0.552
+0.537
Moh+0.525
Austral+0.525
ouf+0.492
Neg logit contributions
channelAvailability-0.668
estinal-0.567
 emanc-0.529
 virginity-0.512
ufact-0.505
Token Trump
Token ID1301
Feature activation-1.40e+00

Pos logit contributions
�士+0.211
+0.206
Austral+0.200
Moh+0.199
ouf+0.184
Neg logit contributions
channelAvailability-0.351
estinal-0.305
 emanc-0.287
 virginity-0.279
ufact-0.276
Token Donald
Token ID3759
Feature activation+9.19e+00

Pos logit contributions
channelAvailability+1.208
estinal+1.031
 emanc+0.978
 virginity+0.940
ufact+0.925
Neg logit contributions
�士-0.999
-0.973
Austral-0.956
Moh-0.953
ouf-0.888
Token John
Token ID1757
Feature activation+7.11e+00

Pos logit contributions
Moh+4.950
Austral+4.886
lection+4.689
�士+4.627
+4.439
Neg logit contributions
channelAvailability-9.084
estinal-8.210
 emanc-7.680
 mathemat-7.623
ufact-7.605
Token Trump
Token ID1301
Feature activation+3.35e+00

Pos logit contributions
�士+2.843
+2.841
Moh+2.767
Austral+2.559
729+2.554
Neg logit contributions
channelAvailability-8.115
estinal-7.135
 mathemat-6.862
ufact-6.827
 emanc-6.797
TokenREAD
Token ID15675
Feature activation+4.34e+00

Pos logit contributions
�士+1.847
Moh+1.795
Austral+1.774
+1.749
Carter+1.611
Neg logit contributions
channelAvailability-3.471
estinal-3.040
 emanc-2.868
ufact-2.824
 virginity-2.797
Token:
Token ID25
Feature activation+9.27e-01

Pos logit contributions
+3.461
�士+3.429
Moh+3.386
Austral+3.354
lection+3.227
Neg logit contributions
channelAvailability-3.448
estinal-2.846
 emanc-2.604
 mathemat-2.518
 virginity-2.483
Token Cohen
Token ID17154
Feature activation+7.23e-01

Pos logit contributions
�士+0.627
+0.615
Austral+0.597
Moh+0.596
ouf+0.556
Neg logit contributions
channelAvailability-0.848
estinal-0.727
 emanc-0.680
 virginity-0.657
ufact-0.653
Token President
Token ID1992
Feature activation-1.30e+00

Pos logit contributions
�士+0.720
+0.702
Moh+0.687
Austral+0.684
ouf+0.640
Neg logit contributions
channelAvailability-0.910
estinal-0.774
 emanc-0.719
 virginity-0.694
ufact-0.692
Token Trump
Token ID1301
Feature activation-1.16e+00

Pos logit contributions
channelAvailability+1.202
estinal+1.040
 emanc+0.976
 virginity+0.946
ufact+0.933
Neg logit contributions
�士-0.860
-0.831
Austral-0.810
Moh-0.806
ouf-0.753
Token Donald
Token ID3759
Feature activation+1.09e+01

Pos logit contributions
channelAvailability+0.931
estinal+0.781
 emanc+0.729
 virginity+0.701
ufact+0.689
Neg logit contributions
�士-0.909
-0.883
Austral-0.866
Moh-0.862
ouf-0.811
Token John
Token ID1757
Feature activation+7.42e+00

Pos logit contributions
Moh+5.442
Austral+5.378
lection+5.143
 McGr+4.941
�士+4.939
Neg logit contributions
channelAvailability-10.965
estinal-10.036
ufact-9.441
 emanc-9.379
 unlaw-9.092
Token Trump
Token ID1301
Feature activation+4.49e+00

Pos logit contributions
�士+3.122
+3.029
Moh+2.991
Austral+2.779
729+2.775
Neg logit contributions
channelAvailability-8.377
estinal-7.367
 emanc-7.032
 mathemat-7.010
ufact-6.989
TokenHouse
Token ID18102
Feature activation+8.97e+00

Pos logit contributions
�士+2.401
Moh+2.365
Austral+2.332
+2.256
Carter+2.126
Neg logit contributions
channelAvailability-4.687
estinal-4.126
 emanc-3.912
ufact-3.878
 virginity-3.821
Token committee
Token ID5583
Feature activation+5.04e+00

Pos logit contributions
�士+5.840
Moh+5.565
+5.204
729+5.125
lection+5.114
Neg logit contributions
channelAvailability-8.343
estinal-6.570
ufact-6.270
 mathemat-6.268
 emanc-6.251
Token believes
Token ID5804
Feature activation+3.43e+00

Pos logit contributions
�士+3.517
+3.312
Moh+3.298
Austral+3.267
729+3.188
Neg logit contributions
channelAvailability-4.499
estinal-3.802
ufact-3.536
 emanc-3.504
 virginity-3.453
Token it
Token ID340
Feature activation+1.45e+00

Pos logit contributions
�士+2.005
+1.970
Moh+1.882
Austral+1.839
lection+1.755
Neg logit contributions
channelAvailability-3.456
estinal-2.963
ufact-2.858
 mathemat-2.812
 emanc-2.712
Token has
Token ID468
Feature activation+8.59e-01

Pos logit contributions
�士+0.980
+0.970
Moh+0.929
Austral+0.917
ouf+0.868
Neg logit contributions
channelAvailability-1.336
estinal-1.141
 emanc-1.048
ufact-1.026
 virginity-1.019
Token evidence
Token ID2370
Feature activation+2.02e+00

Pos logit contributions
�士+0.691
+0.674
Moh+0.661
Austral+0.661
ouf+0.623
Neg logit contributions
channelAvailability-0.677
estinal-0.564
 emanc-0.522
 virginity-0.502
ufact-0.494
Token ©
Token ID10673
Feature activation+4.58e-01

Pos logit contributions
�士+1.408
+1.395
Moh+1.354
Austral+1.345
ouf+1.265
Neg logit contributions
channelAvailability-1.680
estinal-1.423
 emanc-1.305
 virginity-1.262
ufact-1.260
TokenK
Token ID42
Feature activation-1.21e+00

Pos logit contributions
�士+0.310
+0.302
Moh+0.295
Austral+0.295
ouf+0.275
Neg logit contributions
channelAvailability-0.418
estinal-0.357
 emanc-0.334
 virginity-0.323
ufact-0.320
Tokenelli
Token ID23225
Feature activation-1.86e-01

Pos logit contributions
channelAvailability+1.157
estinal+1.004
 emanc+0.936
 virginity+0.908
ufact+0.904
Neg logit contributions
�士-0.775
-0.746
Moh-0.723
Austral-0.722
ouf-0.665
Token (
Token ID357
Feature activation+2.20e+00

Pos logit contributions
channelAvailability+0.163
estinal+0.138
 emanc+0.129
 virginity+0.124
ufact+0.123
Neg logit contributions
�士-0.133
-0.130
Moh-0.127
Austral-0.127
ouf-0.119
Tokenfl
Token ID2704
Feature activation+3.47e-01

Pos logit contributions
�士+1.389
+1.357
Moh+1.325
Austral+1.321
ouf+1.222
Neg logit contributions
channelAvailability-2.110
estinal-1.825
 emanc-1.708
 virginity-1.659
ufact-1.644
Tokenickr
Token ID18994
Feature activation+8.60e+00

Pos logit contributions
�士+0.235
+0.229
Moh+0.224
Austral+0.223
ouf+0.209
Neg logit contributions
channelAvailability-0.316
estinal-0.271
 emanc-0.253
 virginity-0.245
ufact-0.243
Token:
Token ID25
Feature activation+2.63e+00

Pos logit contributions
+4.983
�士+4.774
Moh+4.769
Austral+4.683
ouf+4.359
Neg logit contributions
channelAvailability-8.381
estinal-7.342
 emanc-6.633
 virginity-6.513
ufact-6.444
Token brow
Token ID4772
Feature activation-2.46e+00

Pos logit contributions
�士+1.918
+1.880
Moh+1.839
Austral+1.831
ouf+1.719
Neg logit contributions
channelAvailability-2.258
estinal-1.914
 emanc-1.766
 virginity-1.708
ufact-1.692
Tokennd
Token ID358
Feature activation-3.58e-01

Pos logit contributions
channelAvailability+2.312
estinal+2.008
 emanc+1.884
 virginity+1.829
ufact+1.810
Neg logit contributions
�士-1.583
-1.511
Austral-1.486
Moh-1.472
ouf-1.353
Tokenog
Token ID519
Feature activation-3.34e+00

Pos logit contributions
channelAvailability+0.340
estinal+0.294
 emanc+0.275
 virginity+0.267
ufact+0.265
Neg logit contributions
�士-0.230
-0.222
Austral-0.216
Moh-0.216
ouf-0.199
Token_
Token ID62
Feature activation-7.29e-01

Pos logit contributions
channelAvailability+3.088
estinal+2.667
 emanc+2.501
 virginity+2.432
ufact+2.430
Neg logit contributions
�士-2.186
-2.090
Austral-2.046
Moh-2.025
ouf-1.870
Token Donald
Token ID3759
Feature activation+2.35e+00

Pos logit contributions
�士+0.596
+0.577
Moh+0.562
Austral+0.561
ouf+0.519
Neg logit contributions
channelAvailability-0.962
estinal-0.833
 emanc-0.783
 virginity-0.761
ufact-0.753
Token Trump
Token ID1301
Feature activation-1.25e-01

Pos logit contributions
�士+1.349
+1.311
Moh+1.275
Austral+1.270
ouf+1.168
Neg logit contributions
channelAvailability-2.395
estinal-2.088
 emanc-1.967
 virginity-1.912
ufact-1.896
Token Donald
Token ID3759
Feature activation+9.51e+00

Pos logit contributions
channelAvailability+0.122
estinal+0.106
 emanc+0.100
 virginity+0.097
ufact+0.096
Neg logit contributions
�士-0.077
-0.075
Austral-0.073
Moh-0.073
ouf-0.067
Token John
Token ID1757
Feature activation+7.09e+00

Pos logit contributions
Moh+5.070
Austral+5.019
lection+4.841
�士+4.727
 McGr+4.594
Neg logit contributions
channelAvailability-9.370
estinal-8.466
ufact-7.876
 emanc-7.860
 mathemat-7.672
Token Trump
Token ID1301
Feature activation+3.18e+00

Pos logit contributions
+3.000
�士+2.960
Moh+2.931
Austral+2.759
Carter+2.717
Neg logit contributions
channelAvailability-7.906
estinal-6.981
ufact-6.642
 mathemat-6.616
 emanc-6.594
TokenHouse
Token ID18102
Feature activation+8.46e+00

Pos logit contributions
�士+1.676
Moh+1.620
Austral+1.604
+1.588
Carter+1.450
Neg logit contributions
channelAvailability-3.372
estinal-2.963
 emanc-2.802
ufact-2.746
 virginity-2.725
Token committee
Token ID5583
Feature activation+5.24e+00

Pos logit contributions
�士+5.520
Moh+5.232
+5.096
729+4.911
Carter+4.852
Neg logit contributions
channelAvailability-7.717
estinal-6.164
 mathemat-6.012
 emanc-5.903
ufact-5.846
Token believes
Token ID5804
Feature activation+3.06e+00

Pos logit contributions
�士+3.620
Moh+3.364
+3.364
Austral+3.314
lection+3.249
Neg logit contributions
channelAvailability-4.695
estinal-3.978
ufact-3.726
 emanc-3.657
 virginity-3.620
Token it
Token ID340
Feature activation+1.39e+00

Pos logit contributions
�士+1.906
+1.874
Moh+1.782
Austral+1.748
lection+1.653
Neg logit contributions
channelAvailability-2.975
estinal-2.566
ufact-2.408
 mathemat-2.387
 emanc-2.354
Token has
Token ID468
Feature activation+7.82e-01

Pos logit contributions
�士+0.956
+0.938
Moh+0.898
Austral+0.888
ouf+0.840
Neg logit contributions
channelAvailability-1.263
estinal-1.079
 emanc-0.989
ufact-0.976
 virginity-0.966
Token evidence
Token ID2370
Feature activation+1.57e+00

Pos logit contributions
�士+0.624
+0.610
Moh+0.597
Austral+0.597
ouf+0.563
Neg logit contributions
channelAvailability-0.620
estinal-0.517
 emanc-0.478
 virginity-0.460
ufact-0.454
Token Donald
Token ID3759
Feature activation+3.45e-01

Pos logit contributions
�士+1.559
+1.529
Moh+1.497
Austral+1.488
lection+1.396
Neg logit contributions
channelAvailability-1.780
estinal-1.507
 emanc-1.386
ufact-1.343
 virginity-1.337
Token Trump
Token ID1301
Feature activation-1.23e+00

Pos logit contributions
�士+0.205
+0.199
Austral+0.193
Moh+0.193
ouf+0.178
Neg logit contributions
channelAvailability-0.344
estinal-0.298
 emanc-0.281
 virginity-0.273
ufact-0.271
Token Donald
Token ID3759
Feature activation+9.54e+00

Pos logit contributions
channelAvailability+0.986
estinal+0.822
 emanc+0.763
 virginity+0.735
ufact+0.722
Neg logit contributions
�士-0.969
-0.948
Austral-0.931
Moh-0.930
ouf-0.877
Token John
Token ID1757
Feature activation+7.22e+00

Pos logit contributions
Moh+5.112
Austral+5.014
lection+4.860
�士+4.749
Canada+4.629
Neg logit contributions
channelAvailability-9.340
estinal-8.472
 emanc-7.924
ufact-7.862
 virginity-7.583
Token Trump
Token ID1301
Feature activation+3.48e+00

Pos logit contributions
+2.934
�士+2.912
Moh+2.899
Austral+2.696
Carter+2.676
Neg logit contributions
channelAvailability-8.109
estinal-7.199
 mathemat-6.852
ufact-6.805
 emanc-6.796
TokenHouse
Token ID18102
Feature activation+8.46e+00

Pos logit contributions
�士+1.833
Moh+1.790
Austral+1.764
+1.727
Carter+1.609
Neg logit contributions
channelAvailability-3.668
estinal-3.226
 emanc-3.049
ufact-3.008
 virginity-2.965
Token committee
Token ID5583
Feature activation+5.28e+00

Pos logit contributions
�士+5.532
Moh+5.287
+5.124
729+5.004
Carter+4.907
Neg logit contributions
channelAvailability-7.699
estinal-6.169
 mathemat-5.961
ufact-5.808
 emanc-5.807
Token believes
Token ID5804
Feature activation+3.28e+00

Pos logit contributions
�士+3.549
Moh+3.297
+3.292
Austral+3.260
729+3.237
Neg logit contributions
channelAvailability-4.848
estinal-4.101
ufact-3.825
 emanc-3.785
 virginity-3.694
Token it
Token ID340
Feature activation+1.54e+00

Pos logit contributions
�士+1.816
+1.751
Moh+1.689
Austral+1.632
ONY+1.562
Neg logit contributions
channelAvailability-3.402
estinal-2.963
 mathemat-2.821
ufact-2.820
 emanc-2.719
Token has
Token ID468
Feature activation+1.33e+00

Pos logit contributions
�士+1.067
+1.053
Moh+1.008
Austral+0.993
ouf+0.941
Neg logit contributions
channelAvailability-1.391
estinal-1.191
 emanc-1.078
ufact-1.068
 mathemat-1.054
Token evidence
Token ID2370
Feature activation+2.30e+00

Pos logit contributions
�士+1.037
+1.016
Moh+0.995
Austral+0.990
ouf+0.933
Neg logit contributions
channelAvailability-1.081
estinal-0.903
 emanc-0.824
 virginity-0.799
ufact-0.794
Token
Token ID250
Feature activation+1.68e+00

Pos logit contributions
�士+0.765
+0.743
Moh+0.723
Austral+0.722
ouf+0.672
Neg logit contributions
channelAvailability-1.072
estinal-0.920
 emanc-0.862
 virginity-0.835
ufact-0.828
TokenDuring
Token ID7191
Feature activation+7.80e-01

Pos logit contributions
�士+0.955
+0.931
Moh+0.907
Austral+0.905
ouf+0.829
Neg logit contributions
channelAvailability-1.709
estinal-1.490
 emanc-1.402
 virginity-1.366
ufact-1.355
Token these
Token ID777
Feature activation-8.05e-01

Pos logit contributions
�士+0.575
+0.561
Moh+0.549
Austral+0.548
ouf+0.514
Neg logit contributions
channelAvailability-0.666
estinal-0.563
 emanc-0.524
 virginity-0.506
ufact-0.500
Token two
Token ID734
Feature activation-8.19e-01

Pos logit contributions
channelAvailability+0.692
estinal+0.585
 emanc+0.555
 virginity+0.532
ufact+0.518
Neg logit contributions
�士-0.584
-0.569
Moh-0.555
Austral-0.555
ouf-0.523
Token ch
Token ID442
Feature activation+2.73e+00

Pos logit contributions
channelAvailability+0.667
estinal+0.559
 emanc+0.530
 virginity+0.504
ufact+0.490
Neg logit contributions
�士-0.635
-0.615
Moh-0.601
Austral-0.600
ouf-0.569
Tokenor
Token ID273
Feature activation+7.81e+00

Pos logit contributions
�士+1.263
+1.231
Moh+1.193
Austral+1.191
ouf+1.083
Neg logit contributions
channelAvailability-3.075
estinal-2.689
 emanc-2.554
 virginity-2.499
ufact-2.466
Tokenuses
Token ID2664
Feature activation+1.84e+00

Pos logit contributions
+1.933
Austral+1.900
�士+1.830
Moh+1.790
lection+1.723
Neg logit contributions
channelAvailability-10.343
estinal-8.898
 emanc-8.590
 virginity-8.469
ufact-8.457
Token starting
Token ID3599
Feature activation+3.71e+00

Pos logit contributions
�士+1.305
+1.279
Moh+1.245
Austral+1.242
ouf+1.162
Neg logit contributions
channelAvailability-1.626
estinal-1.382
 emanc-1.280
 virginity-1.239
ufact-1.234
Token at
Token ID379
Feature activation+2.09e+00

Pos logit contributions
�士+2.636
+2.609
Moh+2.542
Austral+2.533
lection+2.371
Neg logit contributions
channelAvailability-3.230
estinal-2.754
 emanc-2.522
ufact-2.453
 virginity-2.450
Token about
Token ID546
Feature activation+2.10e+00

Pos logit contributions
�士+1.468
+1.444
Moh+1.404
Austral+1.398
ouf+1.311
Neg logit contributions
channelAvailability-1.858
estinal-1.587
 emanc-1.464
 virginity-1.421
ufact-1.415
Token 1
Token ID352
Feature activation+8.78e-01

Pos logit contributions
�士+1.475
+1.451
Moh+1.411
Austral+1.408
ouf+1.317
Neg logit contributions
channelAvailability-1.868
estinal-1.596
 emanc-1.473
 virginity-1.428
ufact-1.421
Token regrets
Token ID30090
Feature activation+1.77e-02

Pos logit contributions
�士+1.293
+1.265
Moh+1.237
Austral+1.232
ouf+1.156
Neg logit contributions
channelAvailability-1.511
estinal-1.276
 emanc-1.181
 virginity-1.141
ufact-1.134
Token,
Token ID11
Feature activation+2.22e-01

Pos logit contributions
�士+0.012
+0.012
Moh+0.012
Austral+0.012
ouf+0.011
Neg logit contributions
channelAvailability-0.016
estinal-0.014
 emanc-0.013
 virginity-0.012
ufact-0.012
Token and
Token ID290
Feature activation-6.20e-02

Pos logit contributions
�士+0.167
+0.163
Moh+0.160
Austral+0.159
ouf+0.150
Neg logit contributions
channelAvailability-0.186
estinal-0.157
 emanc-0.146
 virginity-0.140
ufact-0.139
Token what
Token ID644
Feature activation-1.46e+00

Pos logit contributions
channelAvailability+0.053
estinal+0.045
 emanc+0.042
 virginity+0.041
ufact+0.040
Neg logit contributions
�士-0.045
-0.044
Moh-0.043
Austral-0.043
ouf-0.040
Token would
Token ID561
Feature activation+2.57e+00

Pos logit contributions
channelAvailability+1.227
estinal+1.033
 emanc+0.972
 virginity+0.935
ufact+0.915
Neg logit contributions
�士-1.094
-1.059
Moh-1.040
Austral-1.039
ouf-0.980
Token you
Token ID345
Feature activation+7.60e+00

Pos logit contributions
�士+1.950
+1.903
Austral+1.864
Moh+1.863
ONY+1.739
Neg logit contributions
channelAvailability-2.133
estinal-1.794
 emanc-1.653
 virginity-1.599
ufact-1.593
Token have
Token ID423
Feature activation+5.85e+00

Pos logit contributions
+4.459
Moh+4.207
�士+4.140
Austral+4.072
MO+3.865
Neg logit contributions
channelAvailability-7.545
estinal-6.428
ufact-5.956
 emanc-5.830
 mathemat-5.764
Token liked
Token ID8288
Feature activation+2.95e+00

Pos logit contributions
+3.297
�士+3.280
Moh+3.218
Austral+3.166
ouf+2.921
Neg logit contributions
channelAvailability-5.825
estinal-5.073
 emanc-4.662
 virginity-4.593
ufact-4.568
Token to
Token ID284
Feature activation+1.18e+00

Pos logit contributions
�士+1.888
+1.839
Moh+1.787
Austral+1.777
ouf+1.652
Neg logit contributions
channelAvailability-2.805
estinal-2.420
 emanc-2.261
 virginity-2.198
ufact-2.177
Token have
Token ID423
Feature activation+2.19e+00

Pos logit contributions
�士+0.742
+0.724
Moh+0.705
Austral+0.703
ouf+0.652
Neg logit contributions
channelAvailability-1.130
estinal-0.972
 emanc-0.909
 virginity-0.884
ufact-0.878
Token done
Token ID1760
Feature activation+6.31e-01

Pos logit contributions
�士+1.347
+1.331
Moh+1.296
Austral+1.290
ouf+1.193
Neg logit contributions
channelAvailability-2.116
estinal-1.816
 emanc-1.680
 virginity-1.652
ufact-1.633
Token repeatedly
Token ID7830
Feature activation-5.22e-01

Pos logit contributions
�士+1.247
+1.225
Moh+1.201
Austral+1.194
ouf+1.119
Neg logit contributions
channelAvailability-1.481
estinal-1.252
 emanc-1.145
ufact-1.112
 virginity-1.109
Token criticized
Token ID12318
Feature activation+1.02e+00

Pos logit contributions
channelAvailability+0.449
estinal+0.382
 emanc+0.357
 virginity+0.344
ufact+0.339
Neg logit contributions
�士-0.381
-0.370
Austral-0.362
Moh-0.362
ouf-0.339
Token President
Token ID1992
Feature activation-1.30e+00

Pos logit contributions
�士+0.720
+0.702
Moh+0.687
Austral+0.684
ouf+0.640
Neg logit contributions
channelAvailability-0.910
estinal-0.774
 emanc-0.719
 virginity-0.694
ufact-0.692
Token Trump
Token ID1301
Feature activation-1.16e+00

Pos logit contributions
channelAvailability+1.202
estinal+1.040
 emanc+0.976
 virginity+0.946
ufact+0.933
Neg logit contributions
�士-0.860
-0.831
Austral-0.810
Moh-0.806
ouf-0.753
Token Donald
Token ID3759
Feature activation+1.09e+01

Pos logit contributions
channelAvailability+0.931
estinal+0.781
 emanc+0.729
 virginity+0.701
ufact+0.689
Neg logit contributions
�士-0.909
-0.883
Austral-0.866
Moh-0.862
ouf-0.811
Token John
Token ID1757
Feature activation+7.42e+00

Pos logit contributions
Moh+5.442
Austral+5.378
lection+5.143
 McGr+4.941
�士+4.939
Neg logit contributions
channelAvailability-10.965
estinal-10.036
ufact-9.441
 emanc-9.379
 unlaw-9.092
Token Trump
Token ID1301
Feature activation+4.49e+00

Pos logit contributions
�士+3.122
+3.029
Moh+2.991
Austral+2.779
729+2.775
Neg logit contributions
channelAvailability-8.377
estinal-7.367
 emanc-7.032
 mathemat-7.010
ufact-6.989
TokenHouse
Token ID18102
Feature activation+8.97e+00

Pos logit contributions
�士+2.401
Moh+2.365
Austral+2.332
+2.256
Carter+2.126
Neg logit contributions
channelAvailability-4.687
estinal-4.126
 emanc-3.912
ufact-3.878
 virginity-3.821
Token committee
Token ID5583
Feature activation+5.04e+00

Pos logit contributions
�士+5.840
Moh+5.565
+5.204
729+5.125
lection+5.114
Neg logit contributions
channelAvailability-8.343
estinal-6.570
ufact-6.270
 mathemat-6.268
 emanc-6.251
Token believes
Token ID5804
Feature activation+3.43e+00

Pos logit contributions
�士+3.517
+3.312
Moh+3.298
Austral+3.267
729+3.188
Neg logit contributions
channelAvailability-4.499
estinal-3.802
ufact-3.536
 emanc-3.504
 virginity-3.453
Token it
Token ID340
Feature activation+1.45e+00

Pos logit contributions
�士+2.005
+1.970
Moh+1.882
Austral+1.839
lection+1.755
Neg logit contributions
channelAvailability-3.456
estinal-2.963
ufact-2.858
 mathemat-2.812
 emanc-2.712
Token all
Token ID477
Feature activation+3.68e+00

Pos logit contributions
�士+0.672
+0.655
Moh+0.639
Austral+0.638
ouf+0.596
Neg logit contributions
channelAvailability-0.863
estinal-0.736
 emanc-0.687
 virginity-0.665
ufact-0.658
Token its
Token ID663
Feature activation+4.59e+00

Pos logit contributions
�士+2.651
+2.574
Austral+2.502
Moh+2.497
lection+2.339
Neg logit contributions
channelAvailability-3.212
estinal-2.740
 emanc-2.509
 virginity-2.448
ufact-2.424
Token power
Token ID1176
Feature activation+3.36e+00

Pos logit contributions
�士+3.355
+3.296
Moh+3.198
Austral+3.196
lection+2.999
Neg logit contributions
channelAvailability-3.913
estinal-3.321
 emanc-3.000
ufact-2.943
 virginity-2.916
Token and
Token ID290
Feature activation+2.73e+00

Pos logit contributions
�士+2.424
+2.369
Moh+2.315
Austral+2.306
ouf+2.160
Neg logit contributions
channelAvailability-2.920
estinal-2.476
 emanc-2.295
 virginity-2.224
ufact-2.202
Token grand
Token ID4490
Feature activation+3.47e+00

Pos logit contributions
�士+2.092
+2.054
Moh+2.001
Austral+1.999
lection+1.879
Neg logit contributions
channelAvailability-2.235
estinal-1.881
 emanc-1.717
ufact-1.660
 virginity-1.657
Tokeneur
Token ID23365
Feature activation+7.32e+00

Pos logit contributions
�士+2.163
+2.098
Moh+2.039
Austral+2.037
ouf+1.885
Neg logit contributions
channelAvailability-3.370
estinal-2.902
 emanc-2.702
 virginity-2.633
ufact-2.631
Token,
Token ID11
Feature activation+2.85e-01

Pos logit contributions
�士+4.725
+4.655
Moh+4.463
Austral+4.408
lection+4.170
Neg logit contributions
channelAvailability-6.744
estinal-5.766
 emanc-5.276
 virginity-5.139
ufact-5.115
Token is
Token ID318
Feature activation+1.26e+00

Pos logit contributions
�士+0.227
+0.221
Moh+0.217
Austral+0.216
ouf+0.204
Neg logit contributions
channelAvailability-0.226
estinal-0.189
 emanc-0.175
 virginity-0.168
ufact-0.166
Token fragile
Token ID21049
Feature activation+2.07e+00

Pos logit contributions
�士+0.965
+0.945
Moh+0.924
Austral+0.922
ouf+0.867
Neg logit contributions
channelAvailability-1.037
estinal-0.871
 emanc-0.801
 virginity-0.772
ufact-0.767
Token.
Token ID13
Feature activation+1.83e+00

Pos logit contributions
+1.433
�士+1.425
Moh+1.381
Austral+1.369
lection+1.292
Neg logit contributions
channelAvailability-1.843
estinal-1.563
 emanc-1.436
 virginity-1.386
ufact-1.381
Token Its
Token ID6363
Feature activation+8.69e-01

Pos logit contributions
�士+1.437
+1.406
Moh+1.376
Austral+1.373
ouf+1.293
Neg logit contributions
channelAvailability-1.476
estinal-1.237
 emanc-1.143
 virginity-1.099
ufact-1.087
Token in
Token ID287
Feature activation+2.61e+00

Pos logit contributions
�士+2.773
+2.749
Austral+2.692
Moh+2.687
ouf+2.525
Neg logit contributions
channelAvailability-3.437
estinal-2.939
 emanc-2.678
ufact-2.594
 virginity-2.593
Token IM
Token ID8959
Feature activation+4.20e-01

Pos logit contributions
�士+1.934
+1.908
Austral+1.863
Moh+1.859
ouf+1.745
Neg logit contributions
channelAvailability-2.208
estinal-1.867
 emanc-1.713
 virginity-1.661
ufact-1.655
Token
Token ID1906
Feature activation+6.80e-01

Pos logit contributions
�士+0.274
+0.268
Moh+0.261
Austral+0.260
ouf+0.242
Neg logit contributions
channelAvailability-0.392
estinal-0.338
 emanc-0.316
 virginity-0.306
ufact-0.303
Token for
Token ID329
Feature activation-1.59e-01

Pos logit contributions
�士+0.409
+0.397
Moh+0.386
Austral+0.386
ouf+0.356
Neg logit contributions
channelAvailability-0.673
estinal-0.584
 emanc-0.549
 virginity-0.534
ufact-0.528
Token the
Token ID262
Feature activation+5.70e-01

Pos logit contributions
channelAvailability+0.133
estinal+0.112
 emanc+0.105
 virginity+0.101
ufact+0.100
Neg logit contributions
�士-0.119
-0.116
Moh-0.114
Austral-0.113
ouf-0.107
Token sake
Token ID11060
Feature activation+7.32e+00

Pos logit contributions
�士+0.429
+0.419
Moh+0.409
Austral+0.409
ouf+0.384
Neg logit contributions
channelAvailability-0.477
estinal-0.403
 emanc-0.373
 virginity-0.360
ufact-0.356
Token of
Token ID286
Feature activation+1.51e+00

Pos logit contributions
+4.024
Moh+3.807
Austral+3.766
�士+3.596
729+3.561
Neg logit contributions
channelAvailability-7.203
estinal-6.455
ufact-6.048
 mathemat-5.999
 emanc-5.848
Token putting
Token ID5137
Feature activation-1.06e+00

Pos logit contributions
�士+1.210
+1.187
Austral+1.162
Moh+1.161
ouf+1.096
Neg logit contributions
channelAvailability-1.192
estinal-0.991
 emanc-0.903
 virginity-0.869
ufact-0.868
Token something
Token ID1223
Feature activation-1.59e+00

Pos logit contributions
channelAvailability+0.878
estinal+0.737
 emanc+0.687
 virginity+0.663
ufact+0.650
Neg logit contributions
�士-0.809
-0.784
Moh-0.770
Austral-0.767
ouf-0.722
Token in
Token ID287
Feature activation-5.30e-01

Pos logit contributions
channelAvailability+1.331
estinal+1.118
 emanc+1.043
 virginity+1.006
ufact+0.987
Neg logit contributions
�士-1.203
-1.164
Moh-1.145
Austral-1.141
ouf-1.074
Token the
Token ID262
Feature activation-1.95e-01

Pos logit contributions
channelAvailability+0.439
estinal+0.369
 emanc+0.342
 virginity+0.330
ufact+0.326
Neg logit contributions
�士-0.406
-0.396
Moh-0.387
Austral-0.387
ouf-0.364
Token =
Token ID796
Feature activation-2.62e-03

Pos logit contributions
channelAvailability+1.310
estinal+1.123
 emanc+1.042
 virginity+1.006
ufact+0.996
Neg logit contributions
�士-1.048
-1.005
Moh-0.975
Austral-0.973
ouf-0.909
Token Table
Token ID8655
Feature activation-1.27e+00

Pos logit contributions
channelAvailability+0.002
estinal+0.002
 emanc+0.002
 virginity+0.002
ufact+0.002
Neg logit contributions
�士-0.002
-0.002
Moh-0.002
Austral-0.002
ouf-0.002
Token[
Token ID58
Feature activation+3.32e+00

Pos logit contributions
channelAvailability+0.961
estinal+0.801
 emanc+0.734
 virginity+0.702
ufact+0.693
Neg logit contributions
�士-1.053
-1.026
Austral-0.999
Moh-0.998
ouf-0.947
Token {
Token ID1391
Feature activation+1.74e+00

Pos logit contributions
�士+2.335
+2.294
Moh+2.273
Austral+2.257
lection+2.120
Neg logit contributions
channelAvailability-2.892
estinal-2.457
 emanc-2.288
 virginity-2.232
ufact-2.196
Token Keys
Token ID26363
Feature activation-7.17e-01

Pos logit contributions
�士+1.246
+1.220
Moh+1.202
Austral+1.198
ouf+1.122
Neg logit contributions
channelAvailability-1.512
estinal-1.284
 emanc-1.198
 virginity-1.161
ufact-1.142
Token[
Token ID58
Feature activation+7.24e+00

Pos logit contributions
channelAvailability+0.558
estinal+0.466
 emanc+0.429
 virginity+0.412
ufact+0.406
Neg logit contributions
�士-0.582
-0.567
Austral-0.556
Moh-0.555
ouf-0.525
Tokensearch
Token ID12947
Feature activation+9.61e-01

Pos logit contributions
�士+4.370
Moh+4.323
+4.314
Austral+4.260
lection+3.988
Neg logit contributions
channelAvailability-6.704
estinal-5.802
 emanc-5.478
 virginity-5.329
ufact-5.296
TokenSpace
Token ID14106
Feature activation-1.75e+00

Pos logit contributions
�士+0.492
+0.477
Moh+0.462
Austral+0.462
ouf+0.418
Neg logit contributions
channelAvailability-1.035
estinal-0.909
 emanc-0.861
 virginity-0.838
ufact-0.832
Token][
Token ID7131
Feature activation-5.61e-01

Pos logit contributions
channelAvailability+1.411
estinal+1.188
 emanc+1.097
 virginity+1.062
ufact+1.042
Neg logit contributions
�士-1.375
-1.330
Moh-1.299
Austral-1.298
ouf-1.220
Token[
Token ID58
Feature activation+2.54e+00

Pos logit contributions
channelAvailability+0.483
estinal+0.409
 emanc+0.380
 virginity+0.367
ufact+0.363
Neg logit contributions
�士-0.411
-0.400
Moh-0.391
Austral-0.390
ouf-0.366
Tokeni
Token ID72
Feature activation-2.31e+00

Pos logit contributions
�士+1.806
+1.785
Moh+1.756
Austral+1.754
ouf+1.638
Neg logit contributions
channelAvailability-2.193
estinal-1.860
 emanc-1.741
 virginity-1.691
ufact-1.659
Tokenist
Token ID396
Feature activation+1.40e+00

Pos logit contributions
�士+1.301
+1.279
Austral+1.248
Moh+1.245
lection+1.152
Neg logit contributions
channelAvailability-2.590
estinal-2.234
 emanc-2.117
 virginity-2.071
ufact-2.039
Tokenling
Token ID1359
Feature activation+1.68e+00

Pos logit contributions
�士+0.735
+0.713
Moh+0.691
Austral+0.687
ouf+0.630
Neg logit contributions
channelAvailability-1.498
estinal-1.306
 emanc-1.237
 virginity-1.201
ufact-1.195
Token or
Token ID393
Feature activation+1.19e+00

Pos logit contributions
�士+1.090
+1.082
Moh+1.050
Austral+1.047
ouf+0.974
Neg logit contributions
channelAvailability-1.570
estinal-1.345
 emanc-1.248
ufact-1.209
 virginity-1.207
Token just
Token ID655
Feature activation-1.80e+00

Pos logit contributions
�士+0.908
+0.892
Moh+0.872
Austral+0.867
ouf+0.817
Neg logit contributions
channelAvailability-0.986
estinal-0.828
 emanc-0.760
 virginity-0.733
ufact-0.732
Token ch
Token ID442
Feature activation+1.53e+00

Pos logit contributions
channelAvailability+1.290
estinal+1.058
 emanc+0.977
 virginity+0.939
ufact+0.908
Neg logit contributions
�士-1.573
-1.529
Moh-1.502
Austral-1.499
ouf-1.420
Tokenor
Token ID273
Feature activation+7.24e+00

Pos logit contributions
�士+0.890
+0.875
Moh+0.857
Austral+0.855
ouf+0.799
Neg logit contributions
channelAvailability-1.548
estinal-1.322
 emanc-1.251
 virginity-1.221
ufact-1.202
Tokenuses
Token ID2664
Feature activation+9.32e-01

Pos logit contributions
�士+3.212
+3.210
Austral+3.101
Moh+3.072
lection+2.941
Neg logit contributions
channelAvailability-8.151
estinal-6.947
 emanc-6.601
ufact-6.503
 virginity-6.469
Token of
Token ID286
Feature activation+9.96e-01

Pos logit contributions
�士+0.654
+0.644
Moh+0.625
Austral+0.624
ouf+0.585
Neg logit contributions
channelAvailability-0.826
estinal-0.702
 emanc-0.651
 virginity-0.631
ufact-0.626
Token
Token ID564
Feature activation-2.27e+00

Pos logit contributions
�士+0.723
+0.713
Moh+0.695
Austral+0.691
lection+0.649
Neg logit contributions
channelAvailability-0.860
estinal-0.725
 emanc-0.667
ufact-0.646
 virginity-0.643
Token
Token ID250
Feature activation-2.07e+00

Pos logit contributions
channelAvailability+2.130
estinal+1.836
 emanc+1.715
 virginity+1.675
ufact+1.647
Neg logit contributions
�士-1.417
Austral-1.384
-1.382
Moh-1.372
ouf-1.280
Tokenhey
Token ID20342
Feature activation+7.80e-01

Pos logit contributions
channelAvailability+1.989
estinal+1.714
 emanc+1.612
 virginity+1.565
ufact+1.549
Neg logit contributions
�士-1.300
-1.236
Moh-1.212
Austral-1.212
ouf-1.126
Token matchup
Token ID18406
Feature activation-1.68e+00

Pos logit contributions
channelAvailability+1.892
estinal+1.588
 emanc+1.480
 virginity+1.431
ufact+1.380
Neg logit contributions
�士-1.847
-1.794
Austral-1.758
Moh-1.754
ouf-1.652
Token between
Token ID1022
Feature activation+2.11e+00

Pos logit contributions
channelAvailability+1.316
estinal+1.093
 emanc+1.012
 virginity+0.974
ufact+0.954
Neg logit contributions
�士-1.368
-1.328
Austral-1.301
Moh-1.301
ouf-1.228
Token Donald
Token ID3759
Feature activation+3.45e-01

Pos logit contributions
�士+1.559
+1.529
Moh+1.497
Austral+1.488
lection+1.396
Neg logit contributions
channelAvailability-1.780
estinal-1.507
 emanc-1.386
ufact-1.343
 virginity-1.337
Token Trump
Token ID1301
Feature activation-1.23e+00

Pos logit contributions
�士+0.205
+0.199
Austral+0.193
Moh+0.193
ouf+0.178
Neg logit contributions
channelAvailability-0.344
estinal-0.298
 emanc-0.281
 virginity-0.273
ufact-0.271
Token Donald
Token ID3759
Feature activation+9.54e+00

Pos logit contributions
channelAvailability+0.986
estinal+0.822
 emanc+0.763
 virginity+0.735
ufact+0.722
Neg logit contributions
�士-0.969
-0.948
Austral-0.931
Moh-0.930
ouf-0.877
Token John
Token ID1757
Feature activation+7.22e+00

Pos logit contributions
Moh+5.112
Austral+5.014
lection+4.860
�士+4.749
Canada+4.629
Neg logit contributions
channelAvailability-9.340
estinal-8.472
 emanc-7.924
ufact-7.862
 virginity-7.583
Token Trump
Token ID1301
Feature activation+3.48e+00

Pos logit contributions
+2.934
�士+2.912
Moh+2.899
Austral+2.696
Carter+2.676
Neg logit contributions
channelAvailability-8.109
estinal-7.199
 mathemat-6.852
ufact-6.805
 emanc-6.796
TokenHouse
Token ID18102
Feature activation+8.46e+00

Pos logit contributions
�士+1.833
Moh+1.790
Austral+1.764
+1.727
Carter+1.609
Neg logit contributions
channelAvailability-3.668
estinal-3.226
 emanc-3.049
ufact-3.008
 virginity-2.965
Token committee
Token ID5583
Feature activation+5.28e+00

Pos logit contributions
�士+5.532
Moh+5.287
+5.124
729+5.004
Carter+4.907
Neg logit contributions
channelAvailability-7.699
estinal-6.169
 mathemat-5.961
ufact-5.808
 emanc-5.807
Token believes
Token ID5804
Feature activation+3.28e+00

Pos logit contributions
�士+3.549
Moh+3.297
+3.292
Austral+3.260
729+3.237
Neg logit contributions
channelAvailability-4.848
estinal-4.101
ufact-3.825
 emanc-3.785
 virginity-3.694
Token it
Token ID340
Feature activation+1.54e+00

Pos logit contributions
�士+1.816
+1.751
Moh+1.689
Austral+1.632
ONY+1.562
Neg logit contributions
channelAvailability-3.402
estinal-2.963
 mathemat-2.821
ufact-2.820
 emanc-2.719
Tokenub
Token ID549
Feature activation-3.20e+00

Pos logit contributions
�士+1.220
+1.213
Moh+1.199
Austral+1.189
ouf+1.140
Neg logit contributions
channelAvailability-1.110
estinal-0.909
 emanc-0.846
 virginity-0.807
ufact-0.795
Tokenges
Token ID3212
Feature activation+1.55e+00

Pos logit contributions
channelAvailability+2.742
estinal+2.342
 emanc+2.162
 virginity+2.102
ufact+2.050
Neg logit contributions
�士-2.387
-2.261
Austral-2.201
Moh-2.183
ONY-2.057
Tokenhig
Token ID25196
Feature activation-1.97e+00

Pos logit contributions
�士+1.272
+1.263
Moh+1.248
Austral+1.241
ouf+1.183
Neg logit contributions
channelAvailability-1.164
estinal-0.958
 emanc-0.885
 virginity-0.847
ufact-0.837
Token Rice
Token ID13823
Feature activation+2.51e+00

Pos logit contributions
channelAvailability+1.866
estinal+1.602
 emanc+1.500
 virginity+1.465
ufact+1.435
Neg logit contributions
�士-1.275
-1.211
Austral-1.193
Moh-1.184
ouf-1.103
Token/
Token ID14
Feature activation+1.68e+00

Pos logit contributions
+1.846
�士+1.821
Moh+1.819
Austral+1.811
ouf+1.695
Neg logit contributions
channelAvailability-2.098
estinal-1.797
 emanc-1.655
ufact-1.607
 mathemat-1.594
TokenCBC
Token ID29208
Feature activation+7.21e+00

Pos logit contributions
�士+0.841
+0.822
Moh+0.799
Austral+0.796
ouf+0.718
Neg logit contributions
channelAvailability-1.817
estinal-1.606
 emanc-1.522
 virginity-1.482
ufact-1.471
Token)
Token ID8
Feature activation+2.32e+00

Pos logit contributions
�士+3.926
Moh+3.846
+3.832
Austral+3.663
Canada+3.463
Neg logit contributions
channelAvailability-7.219
estinal-6.372
 emanc-5.991
ufact-5.786
 virginity-5.777
Token
Token ID198
Feature activation+7.88e-01

Pos logit contributions
�士+1.735
+1.699
Moh+1.662
Austral+1.658
ouf+1.557
Neg logit contributions
channelAvailability-1.963
estinal-1.655
 emanc-1.534
 virginity-1.478
ufact-1.463
Token
Token ID198
Feature activation+5.71e-01

Pos logit contributions
�士+0.662
+0.653
Moh+0.641
Austral+0.639
ouf+0.605
Neg logit contributions
channelAvailability-0.587
estinal-0.485
 emanc-0.445
 virginity-0.426
ufact-0.422
TokenInsp
Token ID41502
Feature activation+5.30e-01

Pos logit contributions
�士+0.308
+0.290
Austral+0.275
Moh+0.274
ouf+0.256
Neg logit contributions
channelAvailability-0.603
estinal-0.525
 emanc-0.496
 virginity-0.484
ufact-0.476
Tokenired
Token ID1202
Feature activation+3.94e-01

Pos logit contributions
�士+0.187
+0.177
Moh+0.169
Austral+0.168
ouf+0.146
Neg logit contributions
channelAvailability-0.657
estinal-0.586
 emanc-0.559
 virginity-0.548
ufact-0.543
Token However
Token ID2102
Feature activation+3.18e+00

Pos logit contributions
�士+1.981
+1.956
Moh+1.920
Austral+1.916
729+1.787
Neg logit contributions
channelAvailability-2.180
estinal-1.848
 emanc-1.709
ufact-1.633
 virginity-1.632
Token,
Token ID11
Feature activation+3.39e+00

Pos logit contributions
�士+2.218
+2.180
Moh+2.129
Austral+2.117
ouf+1.985
Neg logit contributions
channelAvailability-2.828
estinal-2.395
 emanc-2.221
ufact-2.148
 virginity-2.145
Token this
Token ID428
Feature activation+2.21e+00

Pos logit contributions
�士+2.403
+2.385
Moh+2.346
Austral+2.334
lection+2.188
Neg logit contributions
channelAvailability-2.940
estinal-2.480
 emanc-2.259
ufact-2.225
 virginity-2.177
Token year
Token ID614
Feature activation+1.06e+00

Pos logit contributions
�士+1.674
+1.651
Moh+1.618
Austral+1.610
lection+1.520
Neg logit contributions
channelAvailability-1.833
estinal-1.535
 emanc-1.402
ufact-1.366
 virginity-1.355
Token is
Token ID318
Feature activation+3.79e+00

Pos logit contributions
�士+0.774
+0.756
Moh+0.741
Austral+0.740
ouf+0.692
Neg logit contributions
channelAvailability-0.918
estinal-0.776
 emanc-0.717
 virginity-0.692
ufact-0.690
Token different
Token ID1180
Feature activation+7.16e+00

Pos logit contributions
�士+2.733
+2.717
Austral+2.660
Moh+2.659
lection+2.505
Neg logit contributions
channelAvailability-3.208
estinal-2.706
 emanc-2.446
ufact-2.387
 virginity-2.371
Token because
Token ID780
Feature activation+1.34e+00

Pos logit contributions
+4.506
Moh+4.346
Austral+4.227
�士+4.194
lection+4.076
Neg logit contributions
channelAvailability-6.544
estinal-5.637
 emanc-5.091
 virginity-5.023
ufact-4.993
Token beside
Token ID13970
Feature activation-1.18e+00

Pos logit contributions
�士+0.956
+0.938
Moh+0.918
Austral+0.915
ouf+0.856
Neg logit contributions
channelAvailability-1.177
estinal-0.997
 emanc-0.923
 virginity-0.892
ufact-0.891
Token marking
Token ID18730
Feature activation+2.47e+00

Pos logit contributions
channelAvailability+0.987
estinal+0.832
 emanc+0.782
 virginity+0.756
ufact+0.738
Neg logit contributions
�士-0.889
-0.863
Austral-0.842
Moh-0.841
ouf-0.794
Token the
Token ID262
Feature activation+1.92e+00

Pos logit contributions
�士+1.734
+1.702
Moh+1.667
Austral+1.666
ouf+1.550
Neg logit contributions
channelAvailability-2.187
estinal-1.862
 emanc-1.713
ufact-1.660
 virginity-1.657
Token end
Token ID886
Feature activation+1.04e+00

Pos logit contributions
�士+1.453
+1.423
Moh+1.401
Austral+1.400
lection+1.308
Neg logit contributions
channelAvailability-1.595
estinal-1.343
 emanc-1.220
ufact-1.194
 virginity-1.179
Token Examiner
Token ID35855
Feature activation+2.04e+00

Pos logit contributions
�士+1.381
+1.350
Moh+1.326
Austral+1.308
ouf+1.227
Neg logit contributions
channelAvailability-1.729
estinal-1.460
 emanc-1.360
 virginity-1.313
ufact-1.304
Token,
Token ID11
Feature activation+7.67e-01

Pos logit contributions
�士+1.447
+1.412
Moh+1.379
Austral+1.373
ouf+1.291
Neg logit contributions
channelAvailability-1.797
estinal-1.526
 emanc-1.418
 virginity-1.371
ufact-1.360
Token Donald
Token ID3759
Feature activation+3.55e-01

Pos logit contributions
�士+0.552
+0.537
Moh+0.525
Austral+0.525
ouf+0.492
Neg logit contributions
channelAvailability-0.668
estinal-0.567
 emanc-0.529
 virginity-0.512
ufact-0.505
Token Trump
Token ID1301
Feature activation-1.40e+00

Pos logit contributions
�士+0.211
+0.206
Austral+0.200
Moh+0.199
ouf+0.184
Neg logit contributions
channelAvailability-0.351
estinal-0.305
 emanc-0.287
 virginity-0.279
ufact-0.276
Token Donald
Token ID3759
Feature activation+9.19e+00

Pos logit contributions
channelAvailability+1.208
estinal+1.031
 emanc+0.978
 virginity+0.940
ufact+0.925
Neg logit contributions
�士-0.999
-0.973
Austral-0.956
Moh-0.953
ouf-0.888
Token John
Token ID1757
Feature activation+7.11e+00

Pos logit contributions
Moh+4.950
Austral+4.886
lection+4.689
�士+4.627
+4.439
Neg logit contributions
channelAvailability-9.084
estinal-8.210
 emanc-7.680
 mathemat-7.623
ufact-7.605
Token Trump
Token ID1301
Feature activation+3.35e+00

Pos logit contributions
�士+2.843
+2.841
Moh+2.767
Austral+2.559
729+2.554
Neg logit contributions
channelAvailability-8.115
estinal-7.135
 mathemat-6.862
ufact-6.827
 emanc-6.797
TokenREAD
Token ID15675
Feature activation+4.34e+00

Pos logit contributions
�士+1.847
Moh+1.795
Austral+1.774
+1.749
Carter+1.611
Neg logit contributions
channelAvailability-3.471
estinal-3.040
 emanc-2.868
ufact-2.824
 virginity-2.797
Token:
Token ID25
Feature activation+9.27e-01

Pos logit contributions
+3.461
�士+3.429
Moh+3.386
Austral+3.354
lection+3.227
Neg logit contributions
channelAvailability-3.448
estinal-2.846
 emanc-2.604
 mathemat-2.518
 virginity-2.483
Token Cohen
Token ID17154
Feature activation+7.23e-01

Pos logit contributions
�士+0.627
+0.615
Austral+0.597
Moh+0.596
ouf+0.556
Neg logit contributions
channelAvailability-0.848
estinal-0.727
 emanc-0.680
 virginity-0.657
ufact-0.653
Token testimony
Token ID9709
Feature activation+2.86e+00

Pos logit contributions
�士+0.559
+0.546
Moh+0.534
Austral+0.533
ouf+0.502
Neg logit contributions
channelAvailability-0.591
estinal-0.496
 emanc-0.459
 virginity-0.443
ufact-0.438
TokenIf
Token ID1532
Feature activation-7.98e-01

Pos logit contributions
�士+1.639
+1.615
Moh+1.592
Austral+1.575
ouf+1.439
Neg logit contributions
channelAvailability-2.851
estinal-2.496
 emanc-2.352
 virginity-2.285
ufact-2.278
Token all
Token ID477
Feature activation+8.33e-01

Pos logit contributions
channelAvailability+0.673
estinal+0.569
 emanc+0.533
 virginity+0.516
ufact+0.505
Neg logit contributions
�士-0.594
-0.577
Austral-0.566
Moh-0.564
ouf-0.530
Token that
Token ID326
Feature activation+7.38e-01

Pos logit contributions
�士+0.606
+0.592
Moh+0.579
Austral+0.578
ouf+0.542
Neg logit contributions
channelAvailability-0.721
estinal-0.611
 emanc-0.565
 virginity-0.547
ufact-0.543
Token wasn
Token ID2492
Feature activation-1.82e+00

Pos logit contributions
�士+0.572
+0.559
Moh+0.548
Austral+0.547
ouf+0.515
Neg logit contributions
channelAvailability-0.603
estinal-0.505
 emanc-0.465
 virginity-0.448
ufact-0.444
Token't
Token ID470
Feature activation-4.89e+00

Pos logit contributions
channelAvailability+1.661
estinal+1.385
 emanc+1.305
 virginity+1.275
ufact+1.232
Neg logit contributions
�士-1.273
-1.184
Austral-1.139
Moh-1.137
ouf-1.075
Token enough
Token ID1576
Feature activation-9.76e+00

Pos logit contributions
channelAvailability+3.788
estinal+3.168
 emanc+3.017
 virginity+2.872
ufact+2.792
Neg logit contributions
�士-3.923
-3.751
Austral-3.689
Moh-3.675
ouf-3.475
Token,
Token ID11
Feature activation-2.87e+00

Pos logit contributions
channelAvailability+6.930
estinal+5.797
 emanc+5.559
 virginity+5.397
ufact+5.091
Neg logit contributions
�士-7.693
Austral-7.439
-7.262
Moh-7.235
ONY-6.910
Token the
Token ID262
Feature activation-9.62e-01

Pos logit contributions
channelAvailability+2.377
estinal+2.011
 emanc+1.898
 virginity+1.844
ufact+1.775
Neg logit contributions
�士-2.132
-2.057
Austral-2.042
Moh-2.018
ouf-1.908
Token Yet
Token ID6430
Feature activation-2.95e+00

Pos logit contributions
channelAvailability+0.783
estinal+0.658
 emanc+0.611
 virginity+0.591
ufact+0.580
Neg logit contributions
�士-0.743
-0.724
Austral-0.711
Moh-0.709
ouf-0.667
Tokeni
Token ID72
Feature activation-3.04e+00

Pos logit contributions
channelAvailability+2.230
estinal+1.884
 emanc+1.732
 virginity+1.648
ufact+1.641
Neg logit contributions
�士-2.439
-2.327
Austral-2.313
Moh-2.295
729-2.154
Token himself
Token ID2241
Feature activation+2.22e-01

Pos logit contributions
channelAvailability+2.482
estinal+2.121
 emanc+1.987
 virginity+1.917
ufact+1.866
Neg logit contributions
�士-2.281
-2.200
Austral-2.173
Moh-2.149
lection-2.012
Token explained
Token ID4893
Feature activation-1.06e+00

Pos logit contributions
channelAvailability+1.592
estinal+1.349
 emanc+1.272
 virginity+1.212
ufact+1.173
Neg logit contributions
�士-1.576
-1.519
Austral-1.494
Moh-1.489
ouf-1.403
Token.
Token ID13
Feature activation+6.06e-01

Pos logit contributions
channelAvailability+0.893
estinal+0.754
 emanc+0.701
 virginity+0.677
ufact+0.667
Neg logit contributions
�士-0.789
-0.767
Moh-0.751
Austral-0.750
ouf-0.705
Token
Token ID198
Feature activation-3.23e-01

Pos logit contributions
�士+0.472
+0.461
Moh+0.452
Austral+0.451
ouf+0.425
Neg logit contributions
channelAvailability-0.492
estinal-0.412
 emanc-0.381
 virginity-0.368
ufact-0.363
Token
Token ID198
Feature activation-4.61e-01

Pos logit contributions
channelAvailability+0.233
estinal+0.187
 emanc+0.171
 virginity+0.164
ufact+0.160
Neg logit contributions
�士-0.284
-0.274
Austral-0.267
Moh-0.267
ouf-0.255
TokenNext
Token ID10019
Feature activation-9.66e-01

Pos logit contributions
channelAvailability+0.455
estinal+0.392
 emanc+0.368
 virginity+0.358
ufact+0.352
Neg logit contributions
�士-0.281
-0.271
Austral-0.261
Moh-0.260
ouf-0.243
Token Page
Token ID7873
Feature activation-9.67e+00

Pos logit contributions
channelAvailability+0.808
estinal+0.682
 emanc+0.633
 virginity+0.611
ufact+0.602
Neg logit contributions
�士-0.729
-0.710
Moh-0.695
Austral-0.695
ouf-0.652
Token
Token ID851
Feature activation-2.99e+00

Pos logit contributions
channelAvailability+6.747
estinal+5.460
 emanc+5.158
 virginity+5.005
ufact+4.840
Neg logit contributions
�士-8.019
Austral-7.411
-7.396
Moh-7.316
ouf-7.079
Token>
Token ID29
Feature activation-2.90e+00

Pos logit contributions
channelAvailability+2.580
estinal+2.173
 emanc+2.040
 virginity+1.984
ufact+1.956
Neg logit contributions
�士-2.140
-2.065
Austral-2.030
Moh-2.025
ouf-1.899
Token<|endoftext|>
Token ID50256
Feature activation-5.12e-01

Pos logit contributions
channelAvailability+2.468
estinal+2.077
 emanc+1.948
 virginity+1.890
ufact+1.854
Neg logit contributions
�士-2.128
-2.034
Austral-2.014
Moh-2.002
ouf-1.885
TokenLate
Token ID26302
Feature activation+2.03e+00

Pos logit contributions
channelAvailability+0.511
estinal+0.440
 emanc+0.414
 virginity+0.403
ufact+0.396
Neg logit contributions
�士-0.306
-0.294
Moh-0.282
Austral-0.281
ouf-0.263
Token in
Token ID287
Feature activation+3.57e+00

Pos logit contributions
�士+1.545
+1.520
Moh+1.490
Austral+1.485
ouf+1.395
Neg logit contributions
channelAvailability-1.678
estinal-1.400
 emanc-1.291
ufact-1.248
 virginity-1.242
Token if
Token ID611
Feature activation-3.96e-01

Pos logit contributions
�士+0.041
+0.040
Moh+0.039
Austral+0.039
ouf+0.037
Neg logit contributions
channelAvailability-0.048
estinal-0.041
 emanc-0.038
 virginity-0.036
ufact-0.036
Token all
Token ID477
Feature activation+2.59e-01

Pos logit contributions
channelAvailability+0.340
estinal+0.288
 emanc+0.267
 virginity+0.258
ufact+0.256
Neg logit contributions
�士-0.290
-0.284
Moh-0.277
Austral-0.276
ouf-0.259
Token of
Token ID286
Feature activation-1.43e+00

Pos logit contributions
�士+0.191
+0.187
Moh+0.182
Austral+0.182
ouf+0.171
Neg logit contributions
channelAvailability-0.221
estinal-0.187
 emanc-0.173
 virginity-0.167
ufact-0.166
Token this
Token ID428
Feature activation-5.86e-01

Pos logit contributions
channelAvailability+1.117
estinal+0.925
 emanc+0.862
 virginity+0.833
ufact+0.811
Neg logit contributions
�士-1.154
-1.126
Moh-1.104
Austral-1.100
ouf-1.043
Token not
Token ID407
Feature activation-2.69e+00

Pos logit contributions
channelAvailability+0.481
estinal+0.404
 emanc+0.375
 virginity+0.362
ufact+0.357
Neg logit contributions
�士-0.451
-0.440
Moh-0.431
Austral-0.430
ouf-0.405
Token enough
Token ID1576
Feature activation-8.88e+00

Pos logit contributions
channelAvailability+2.091
estinal+1.740
 emanc+1.613
 virginity+1.544
ufact+1.522
Neg logit contributions
�士-2.176
-2.116
Moh-2.086
Austral-2.080
ouf-1.966
Token,
Token ID11
Feature activation-1.87e+00

Pos logit contributions
channelAvailability+6.582
estinal+5.534
 emanc+5.310
 virginity+5.041
ufact+4.822
Neg logit contributions
�士-7.072
Austral-6.537
Moh-6.504
-6.426
ouf-6.173
Token the
Token ID262
Feature activation-4.60e-01

Pos logit contributions
channelAvailability+1.575
estinal+1.327
 emanc+1.241
 virginity+1.197
ufact+1.174
Neg logit contributions
�士-1.399
-1.350
Moh-1.327
Austral-1.327
ouf-1.251
Token events
Token ID2995
Feature activation-1.26e+00

Pos logit contributions
channelAvailability+0.382
estinal+0.321
 emanc+0.298
 virginity+0.287
ufact+0.284
Neg logit contributions
�士-0.351
-0.342
Moh-0.335
Austral-0.334
ouf-0.315
Token also
Token ID635
Feature activation-6.42e-01

Pos logit contributions
channelAvailability+1.072
estinal+0.906
 emanc+0.845
 virginity+0.815
ufact+0.803
Neg logit contributions
�士-0.941
-0.912
Moh-0.894
Austral-0.893
ouf-0.839
Token create
Token ID2251
Feature activation-2.98e-01

Pos logit contributions
channelAvailability+0.568
estinal+0.485
 emanc+0.454
 virginity+0.439
ufact+0.432
Neg logit contributions
�士-0.454
-0.440
Moh-0.430
Austral-0.430
ouf-0.402
Tokenco
Token ID1073
Feature activation-8.44e-01

Pos logit contributions
channelAvailability+1.157
estinal+0.956
 emanc+0.883
 virginity+0.846
ufact+0.826
Neg logit contributions
�士-1.265
-1.207
Austral-1.182
Moh-1.174
ouf-1.109
Token.
Token ID13
Feature activation-2.87e-01

Pos logit contributions
channelAvailability+0.707
estinal+0.594
 emanc+0.551
 virginity+0.533
ufact+0.519
Neg logit contributions
�士-0.652
-0.614
Austral-0.599
Moh-0.597
ouf-0.563
Tokenuk
Token ID2724
Feature activation-2.15e+00

Pos logit contributions
channelAvailability+0.231
estinal+0.193
 emanc+0.179
 virginity+0.172
ufact+0.168
Neg logit contributions
�士-0.230
-0.219
Austral-0.215
Moh-0.214
ouf-0.201
Token/
Token ID14
Feature activation-7.48e+00

Pos logit contributions
channelAvailability+1.618
estinal+1.315
 emanc+1.210
 virginity+1.176
ufact+1.144
Neg logit contributions
�士-1.833
-1.726
Austral-1.693
Moh-1.687
ouf-1.607
Tokenbusiness
Token ID22680
Feature activation-2.58e+00

Pos logit contributions
channelAvailability+5.299
estinal+4.353
 emanc+4.102
ufact+3.849
 virginity+3.758
Neg logit contributions
�士-6.332
-6.088
Austral-5.853
Moh-5.808
ONY-5.581
Token/
Token ID14
Feature activation-8.79e+00

Pos logit contributions
channelAvailability+1.994
estinal+1.647
 emanc+1.516
 virginity+1.460
ufact+1.430
Neg logit contributions
�士-2.117
-2.050
Austral-1.998
Moh-1.991
ouf-1.882
Tokenanalysis
Token ID20930
Feature activation-7.14e-01

Pos logit contributions
channelAvailability+7.201
estinal+5.991
 emanc+5.764
ufact+5.547
chapter+5.320
Neg logit contributions
�士-6.327
-6.006
Austral-5.717
Moh-5.623
ONY-5.401
Token/
Token ID14
Feature activation-7.77e+00

Pos logit contributions
channelAvailability+0.574
estinal+0.480
 emanc+0.444
 virginity+0.427
ufact+0.422
Neg logit contributions
�士-0.561
-0.548
Moh-0.535
Austral-0.535
ouf-0.505
Tokenwhy
Token ID22850
Feature activation-1.31e+00

Pos logit contributions
channelAvailability+6.391
estinal+5.294
 emanc+5.112
ufact+4.795
 virginity+4.709
Neg logit contributions
�士-5.723
-5.291
Austral-5.067
Moh-5.000
Lay-4.787
Token-
Token ID12
Feature activation-1.63e+00

Pos logit contributions
channelAvailability+1.083
estinal+0.906
 emanc+0.846
 virginity+0.809
ufact+0.800
Neg logit contributions
�士-1.031
-0.986
Moh-0.960
Austral-0.955
ouf-0.900
Tokenaut
Token ID2306
Feature activation+7.10e-01

Pos logit contributions
channelAvailability+1.602
estinal+1.377
 emanc+1.306
ufact+1.256
 virginity+1.241
Neg logit contributions
�士-1.032
-0.969
Moh-0.924
Austral-0.914
ouf-0.842
Token breach
Token ID13694
Feature activation+2.57e-01

Pos logit contributions
�士+1.604
+1.569
Moh+1.540
Austral+1.538
ouf+1.448
Neg logit contributions
channelAvailability-1.606
estinal-1.340
 emanc-1.223
 virginity-1.174
ufact-1.169
Token notifications
Token ID19605
Feature activation-1.25e+00

Pos logit contributions
�士+0.226
+0.222
Austral+0.218
Moh+0.218
ouf+0.206
Neg logit contributions
channelAvailability-0.182
estinal-0.149
 emanc-0.134
 virginity-0.129
ufact-0.127
Token is
Token ID318
Feature activation+9.29e-02

Pos logit contributions
channelAvailability+1.029
estinal+0.865
 emanc+0.809
 virginity+0.776
ufact+0.764
Neg logit contributions
�士-0.970
-0.935
Moh-0.920
Austral-0.918
ouf-0.864
Token not
Token ID407
Feature activation+3.11e-01

Pos logit contributions
�士+0.070
+0.069
Austral+0.067
Moh+0.067
ouf+0.063
Neg logit contributions
channelAvailability-0.077
estinal-0.065
 emanc-0.060
 virginity-0.058
ufact-0.058
Token nearly
Token ID3016
Feature activation-2.25e-01

Pos logit contributions
�士+0.229
+0.225
Moh+0.220
Austral+0.219
ouf+0.206
Neg logit contributions
channelAvailability-0.264
estinal-0.224
 emanc-0.206
 virginity-0.200
ufact-0.198
Token enough
Token ID1576
Feature activation-8.39e+00

Pos logit contributions
channelAvailability+0.197
estinal+0.167
 emanc+0.155
 virginity+0.150
ufact+0.149
Neg logit contributions
�士-0.161
-0.157
Moh-0.153
Austral-0.153
ouf-0.143
Token.
Token ID13
Feature activation+6.82e-01

Pos logit contributions
channelAvailability+6.440
estinal+5.232
 emanc+5.167
 virginity+4.783
ufact+4.652
Neg logit contributions
�士-6.683
Moh-6.182
Austral-6.164
-6.072
ouf-5.791
Token There
Token ID1318
Feature activation+6.61e-01

Pos logit contributions
�士+0.522
+0.511
Moh+0.500
Austral+0.499
ouf+0.469
Neg logit contributions
channelAvailability-0.563
estinal-0.475
 emanc-0.439
 virginity-0.423
ufact-0.418
Token is
Token ID318
Feature activation+8.75e-01

Pos logit contributions
�士+0.487
+0.476
Moh+0.465
Austral+0.465
ouf+0.436
Neg logit contributions
channelAvailability-0.563
estinal-0.478
 emanc-0.442
 virginity-0.428
ufact-0.424
Token a
Token ID257
Feature activation+8.88e-01

Pos logit contributions
�士+0.661
+0.650
Austral+0.635
Moh+0.635
lection+0.595
Neg logit contributions
channelAvailability-0.726
estinal-0.613
 emanc-0.562
 virginity-0.544
ufact-0.541
Token gathering
Token ID11228
Feature activation-2.68e-02

Pos logit contributions
�士+0.658
+0.646
Moh+0.631
Austral+0.631
lection+0.593
Neg logit contributions
channelAvailability-0.751
estinal-0.634
 emanc-0.583
 virginity-0.566
ufact-0.562
Token things
Token ID1243
Feature activation-1.51e+00

Pos logit contributions
channelAvailability+0.324
estinal+0.271
 emanc+0.251
 virginity+0.242
ufact+0.238
Neg logit contributions
�士-0.319
-0.311
Moh-0.305
Austral-0.304
ouf-0.287
Token they
Token ID484
Feature activation-8.91e-01

Pos logit contributions
channelAvailability+1.283
estinal+1.080
 emanc+1.012
 virginity+0.981
ufact+0.951
Neg logit contributions
�士-1.133
-1.085
Moh-1.070
Austral-1.063
ouf-1.006
Token can
Token ID460
Feature activation-1.31e+00

Pos logit contributions
channelAvailability+0.738
estinal+0.627
 emanc+0.588
 virginity+0.567
ufact+0.549
Neg logit contributions
�士-0.684
-0.653
Moh-0.645
Austral-0.643
ouf-0.608
Token't
Token ID470
Feature activation-1.52e+00

Pos logit contributions
channelAvailability+1.135
estinal+0.975
 emanc+0.924
 virginity+0.888
ufact+0.860
Neg logit contributions
�士-0.958
-0.906
Austral-0.897
Moh-0.896
ouf-0.842
Token get
Token ID651
Feature activation-1.81e+00

Pos logit contributions
channelAvailability+1.257
estinal+1.071
 emanc+1.012
 virginity+0.971
ufact+0.938
Neg logit contributions
�士-1.169
-1.104
Moh-1.095
Austral-1.094
ouf-1.028
Token enough
Token ID1576
Feature activation-8.28e+00

Pos logit contributions
channelAvailability+1.582
estinal+1.336
 emanc+1.274
 virginity+1.228
ufact+1.195
Neg logit contributions
�士-1.329
-1.256
Moh-1.236
Austral-1.234
ouf-1.160
Token of
Token ID286
Feature activation-1.17e+00

Pos logit contributions
channelAvailability+6.435
estinal+5.476
 emanc+4.972
 virginity+4.921
 pills+4.625
Neg logit contributions
�士-6.438
Austral-6.164
Moh-6.092
-5.850
ouf-5.720
Token.
Token ID13
Feature activation+4.67e-01

Pos logit contributions
channelAvailability+0.988
estinal+0.836
 emanc+0.778
 virginity+0.754
ufact+0.742
Neg logit contributions
�士-0.869
-0.839
Moh-0.825
Austral-0.824
ouf-0.775
Token But
Token ID887
Feature activation+3.29e-02

Pos logit contributions
�士+0.356
+0.349
Moh+0.341
Austral+0.340
ouf+0.320
Neg logit contributions
channelAvailability-0.387
estinal-0.325
 emanc-0.301
 virginity-0.290
ufact-0.287
Token as
Token ID355
Feature activation+2.01e+00

Pos logit contributions
�士+0.024
+0.024
Moh+0.023
Austral+0.023
ouf+0.022
Neg logit contributions
channelAvailability-0.028
estinal-0.024
 emanc-0.022
 virginity-0.021
ufact-0.021
Token any
Token ID597
Feature activation+2.90e+00

Pos logit contributions
�士+1.476
+1.462
Moh+1.425
Austral+1.424
ouf+1.333
Neg logit contributions
channelAvailability-1.703
estinal-1.437
 emanc-1.323
 virginity-1.277
ufact-1.274
Token as
Token ID355
Feature activation-2.18e-01

Pos logit contributions
channelAvailability+1.193
estinal+1.013
 emanc+0.947
 virginity+0.915
ufact+0.893
Neg logit contributions
�士-1.059
-1.030
Austral-1.007
Moh-1.003
ouf-0.943
Token if
Token ID611
Feature activation-9.17e-02

Pos logit contributions
channelAvailability+0.185
estinal+0.157
 emanc+0.145
 virginity+0.140
ufact+0.139
Neg logit contributions
�士-0.161
-0.157
Moh-0.154
Austral-0.153
ouf-0.144
Token that
Token ID326
Feature activation-1.42e+00

Pos logit contributions
channelAvailability+0.080
estinal+0.068
 emanc+0.063
 virginity+0.060
ufact+0.060
Neg logit contributions
�士-0.066
-0.065
Moh-0.063
Austral-0.063
ouf-0.059
Token wasn
Token ID2492
Feature activation-3.65e+00

Pos logit contributions
channelAvailability+1.156
estinal+0.971
 emanc+0.901
 virginity+0.870
ufact+0.857
Neg logit contributions
�士-1.101
-1.073
Austral-1.050
Moh-1.050
ouf-0.989
Token't
Token ID470
Feature activation-5.62e+00

Pos logit contributions
channelAvailability+3.204
estinal+2.596
 emanc+2.434
 virginity+2.390
ufact+2.310
Neg logit contributions
�士-2.713
-2.432
Austral-2.372
Moh-2.358
ouf-2.268
Token enough
Token ID1576
Feature activation-8.26e+00

Pos logit contributions
channelAvailability+4.456
estinal+3.755
 emanc+3.522
 virginity+3.385
ufact+3.322
Neg logit contributions
�士-4.432
-4.230
Austral-4.185
Moh-4.172
ouf-3.938
Token to
Token ID284
Feature activation-2.03e+00

Pos logit contributions
channelAvailability+6.190
estinal+5.252
 emanc+4.876
 virginity+4.736
ufact+4.595
Neg logit contributions
�士-6.394
Austral-6.268
-6.233
Moh-6.182
ouf-5.869
Token tick
Token ID4378
Feature activation+5.60e-01

Pos logit contributions
channelAvailability+1.719
estinal+1.461
 emanc+1.373
 virginity+1.323
ufact+1.292
Neg logit contributions
�士-1.510
-1.450
Austral-1.425
Moh-1.424
ouf-1.338
Tokenle
Token ID293
Feature activation+1.14e-01

Pos logit contributions
�士+0.346
+0.337
Moh+0.328
Austral+0.327
ouf+0.302
Neg logit contributions
channelAvailability-0.545
estinal-0.471
 emanc-0.442
 virginity-0.428
ufact-0.427
Token God
Token ID1793
Feature activation-1.90e+00

Pos logit contributions
�士+0.085
+0.084
Moh+0.082
Austral+0.082
ouf+0.077
Neg logit contributions
channelAvailability-0.095
estinal-0.080
 emanc-0.074
 virginity-0.071
ufact-0.071
Token's
Token ID338
Feature activation-1.30e+00

Pos logit contributions
channelAvailability+1.615
estinal+1.370
 emanc+1.273
 virginity+1.231
ufact+1.210
Neg logit contributions
�士-1.409
-1.371
Austral-1.339
Moh-1.335
ouf-1.250
Token that
Token ID326
Feature activation-1.59e+00

Pos logit contributions
channelAvailability+1.839
estinal+1.587
 emanc+1.501
 virginity+1.462
ufact+1.425
Neg logit contributions
�士-1.214
-1.174
Austral-1.142
Moh-1.134
lection-1.050
Token
Token ID447
Feature activation-1.44e+00

Pos logit contributions
channelAvailability+1.215
estinal+1.009
 emanc+0.935
 virginity+0.901
ufact+0.878
Neg logit contributions
�士-1.307
-1.272
Austral-1.249
Moh-1.242
ouf-1.174
Token
Token ID247
Feature activation+5.12e-01

Pos logit contributions
channelAvailability+1.143
estinal+0.952
 emanc+0.873
 virginity+0.849
ufact+0.831
Neg logit contributions
�士-1.144
-1.119
Austral-1.103
Moh-1.099
ouf-1.037
Tokens
Token ID82
Feature activation-2.06e+00

Pos logit contributions
�士+0.325
+0.321
Moh+0.311
Austral+0.309
ouf+0.287
Neg logit contributions
channelAvailability-0.487
estinal-0.420
 emanc-0.394
 virginity-0.382
ufact-0.378
Token not
Token ID407
Feature activation-3.39e+00

Pos logit contributions
channelAvailability+1.681
estinal+1.401
 emanc+1.314
 virginity+1.274
ufact+1.244
Neg logit contributions
�士-1.589
-1.535
Austral-1.511
Moh-1.500
ouf-1.408
Token enough
Token ID1576
Feature activation-8.12e+00

Pos logit contributions
channelAvailability+2.683
estinal+2.238
 emanc+2.104
 virginity+2.020
ufact+1.962
Neg logit contributions
�士-2.685
-2.588
Austral-2.541
Moh-2.525
ONY-2.391
Token fortune
Token ID15807
Feature activation-3.56e-01

Pos logit contributions
channelAvailability+6.230
estinal+5.121
 emanc+4.945
 virginity+4.812
ufact+4.468
Neg logit contributions
�士-6.331
Austral-5.905
-5.843
Moh-5.773
ONY-5.585
Token telling
Token ID5149
Feature activation+1.17e+00

Pos logit contributions
channelAvailability+0.306
estinal+0.259
 emanc+0.241
 virginity+0.233
ufact+0.230
Neg logit contributions
�士-0.261
-0.254
Moh-0.248
Austral-0.248
ouf-0.233
Token,
Token ID11
Feature activation-1.73e+00

Pos logit contributions
�士+0.837
+0.821
Moh+0.802
Austral+0.799
ouf+0.749
Neg logit contributions
channelAvailability-1.029
estinal-0.874
 emanc-0.811
 virginity-0.784
ufact-0.779
Token there
Token ID612
Feature activation-1.40e+00

Pos logit contributions
channelAvailability+1.568
estinal+1.343
 emanc+1.259
 virginity+1.225
ufact+1.196
Neg logit contributions
�士-1.171
-1.134
Austral-1.107
Moh-1.103
ouf-1.030
Token are
Token ID389
Feature activation-3.44e+00

Pos logit contributions
channelAvailability+1.137
estinal+0.950
 emanc+0.881
 virginity+0.850
ufact+0.837
Neg logit contributions
�士-1.088
-1.059
Moh-1.038
Austral-1.036
ouf-0.978
Token,
Token ID11
Feature activation-7.74e-01

Pos logit contributions
channelAvailability+0.375
estinal+0.315
 emanc+0.292
 virginity+0.282
ufact+0.279
Neg logit contributions
�士-0.339
-0.332
Moh-0.324
Austral-0.324
ouf-0.305
Token just
Token ID655
Feature activation+5.45e-01

Pos logit contributions
channelAvailability+0.671
estinal+0.569
 emanc+0.531
 virginity+0.514
ufact+0.506
Neg logit contributions
�士-0.560
-0.546
Austral-0.533
Moh-0.533
ouf-0.499
Token outside
Token ID2354
Feature activation+7.53e-01

Pos logit contributions
�士+0.392
+0.382
Moh+0.373
Austral+0.373
ouf+0.349
Neg logit contributions
channelAvailability-0.475
estinal-0.403
 emanc-0.375
 virginity-0.363
ufact-0.359
Token of
Token ID286
Feature activation-2.19e+00

Pos logit contributions
�士+0.504
+0.493
Moh+0.481
Austral+0.479
ouf+0.448
Neg logit contributions
channelAvailability-0.696
estinal-0.594
 emanc-0.555
 virginity-0.537
ufact-0.534
Token present
Token ID1944
Feature activation-5.06e+00

Pos logit contributions
channelAvailability+1.986
estinal+1.709
 emanc+1.603
 virginity+1.561
ufact+1.526
Neg logit contributions
�士-1.481
-1.439
Austral-1.403
Moh-1.395
ouf-1.303
Token-
Token ID12
Feature activation-8.09e+00

Pos logit contributions
channelAvailability+3.794
estinal+3.241
 emanc+3.012
 virginity+2.927
ufact+2.835
Neg logit contributions
�士-4.021
-3.945
Austral-3.832
Moh-3.769
ONY-3.582
Tokenday
Token ID820
Feature activation-3.28e+00

Pos logit contributions
channelAvailability+6.929
estinal+5.885
 virginity+5.555
 emanc+5.508
ufact+5.165
Neg logit contributions
�士-5.716
-5.321
Austral-4.960
ONY-4.818
Moh-4.811
Token Baghdad
Token ID19761
Feature activation-6.99e-01

Pos logit contributions
channelAvailability+3.229
estinal+2.837
 emanc+2.688
 virginity+2.634
ufact+2.557
Neg logit contributions
�士-1.933
-1.867
Austral-1.803
Moh-1.776
ouf-1.652
Token,
Token ID11
Feature activation-4.10e-01

Pos logit contributions
channelAvailability+0.601
estinal+0.510
 emanc+0.475
 virginity+0.460
ufact+0.453
Neg logit contributions
�士-0.508
-0.496
Austral-0.486
Moh-0.484
ouf-0.454
Token Iraq
Token ID3908
Feature activation+1.82e+00

Pos logit contributions
channelAvailability+0.382
estinal+0.328
 emanc+0.308
 virginity+0.299
ufact+0.295
Neg logit contributions
�士-0.271
-0.264
Austral-0.256
Moh-0.256
ouf-0.238
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
�士+1.275
+1.246
Moh+1.217
Austral+1.203
ouf+1.133
Neg logit contributions
channelAvailability-1.626
estinal-1.384
 emanc-1.287
 virginity-1.247
ufact-1.237
Tokenground
Token ID2833
Feature activation-2.56e+00

Pos logit contributions
channelAvailability+1.765
estinal+1.490
 emanc+1.378
 virginity+1.331
ufact+1.323
Neg logit contributions
�士-1.629
-1.566
Austral-1.535
Moh-1.531
ouf-1.435
Token.
Token ID13
Feature activation+5.52e-01

Pos logit contributions
channelAvailability+2.120
estinal+1.791
 emanc+1.649
 virginity+1.598
ufact+1.586
Neg logit contributions
�士-1.944
-1.865
Austral-1.849
Moh-1.833
ouf-1.723
Tokencom
Token ID785
Feature activation+6.62e-01

Pos logit contributions
�士+0.391
+0.380
Moh+0.370
Austral+0.370
ouf+0.346
Neg logit contributions
channelAvailability-0.489
estinal-0.416
 emanc-0.388
 virginity-0.375
ufact-0.372
Token/
Token ID14
Feature activation-4.48e+00

Pos logit contributions
�士+0.514
+0.504
Moh+0.492
Austral+0.491
ouf+0.463
Neg logit contributions
channelAvailability-0.539
estinal-0.452
 emanc-0.418
 virginity-0.402
ufact-0.397
Token2016
Token ID5304
Feature activation-3.58e-01

Pos logit contributions
channelAvailability+4.247
estinal+3.615
 emanc+3.427
 virginity+3.310
ufact+3.282
Neg logit contributions
�士-2.882
-2.701
Austral-2.616
Moh-2.601
ouf-2.405
Token/
Token ID14
Feature activation-8.02e+00

Pos logit contributions
channelAvailability+0.285
estinal+0.237
 emanc+0.219
 virginity+0.211
ufact+0.208
Neg logit contributions
�士-0.285
-0.278
Moh-0.273
Austral-0.272
ouf-0.257
Token09
Token ID2931
Feature activation-1.89e+00

Pos logit contributions
channelAvailability+5.780
estinal+4.659
 emanc+4.443
 virginity+4.164
ufact+4.054
Neg logit contributions
�士-6.991
-6.248
Austral-6.113
Moh-6.027
ONY-5.796
Token/
Token ID14
Feature activation-5.16e+00

Pos logit contributions
channelAvailability+1.428
estinal+1.161
 emanc+1.078
 virginity+1.040
ufact+0.997
Neg logit contributions
�士-1.616
-1.517
Austral-1.483
Moh-1.478
ouf-1.413
Token08
Token ID2919
Feature activation-2.19e+00

Pos logit contributions
channelAvailability+4.330
estinal+3.691
 emanc+3.504
 virginity+3.354
ufact+3.266
Neg logit contributions
�士-3.856
-3.552
Austral-3.458
Moh-3.428
ONY-3.229
Token/
Token ID14
Feature activation-5.17e+00

Pos logit contributions
channelAvailability+1.673
estinal+1.374
 emanc+1.275
 virginity+1.224
ufact+1.194
Neg logit contributions
�士-1.835
-1.741
Austral-1.707
Moh-1.700
ouf-1.614
Tokenthe
Token ID1169
Feature activation-1.02e+00

Pos logit contributions
channelAvailability+4.602
estinal+3.937
 emanc+3.733
 virginity+3.574
ufact+3.514
Neg logit contributions
�士-3.578
-3.317
Austral-3.246
Moh-3.199
ONY-2.986
Token that
Token ID326
Feature activation-1.68e-01

Pos logit contributions
�士+0.173
+0.170
Moh+0.166
Austral+0.166
ouf+0.156
Neg logit contributions
channelAvailability-0.185
estinal-0.155
 emanc-0.143
 virginity-0.137
ufact-0.137
Token
Token ID447
Feature activation+1.46e-01

Pos logit contributions
channelAvailability+0.135
estinal+0.112
 emanc+0.103
ufact+0.099
 virginity+0.098
Neg logit contributions
�士-0.133
-0.131
Moh-0.128
Austral-0.127
ouf-0.120
Token
Token ID247
Feature activation+2.46e-01

Pos logit contributions
�士+0.073
+0.070
Austral+0.069
Moh+0.069
ouf+0.062
Neg logit contributions
channelAvailability-0.159
estinal-0.140
 emanc-0.132
 virginity-0.129
ufact-0.128
Tokens
Token ID82
Feature activation-1.46e+00

Pos logit contributions
�士+0.172
+0.171
Austral+0.165
Moh+0.165
ouf+0.154
Neg logit contributions
channelAvailability-0.218
estinal-0.186
 emanc-0.173
 virginity-0.168
ufact-0.166
Token not
Token ID407
Feature activation-2.74e+00

Pos logit contributions
channelAvailability+1.203
estinal+1.010
 emanc+0.940
 virginity+0.908
ufact+0.895
Neg logit contributions
�士-1.118
-1.081
Moh-1.064
Austral-1.063
ouf-0.999
Token enough
Token ID1576
Feature activation-7.78e+00

Pos logit contributions
channelAvailability+2.273
estinal+1.917
 emanc+1.795
 virginity+1.727
ufact+1.703
Neg logit contributions
�士-2.093
-2.006
Moh-1.980
Austral-1.977
ouf-1.858
Token,
Token ID11
Feature activation-1.23e+00

Pos logit contributions
channelAvailability+6.140
estinal+5.124
 emanc+4.890
 virginity+4.777
ufact+4.553
Neg logit contributions
�士-5.961
Moh-5.597
Austral-5.566
-5.451
ouf-5.233
Token Da
Token ID9637
Feature activation+3.51e-01

Pos logit contributions
channelAvailability+1.016
estinal+0.854
 emanc+0.792
 virginity+0.765
ufact+0.754
Neg logit contributions
�士-0.942
-0.918
Moh-0.899
Austral-0.898
ouf-0.844
Tokenum
Token ID388
Feature activation+2.73e+00

Pos logit contributions
�士+0.211
+0.204
Moh+0.198
Austral+0.198
ouf+0.182
Neg logit contributions
channelAvailability-0.347
estinal-0.301
 emanc-0.283
 virginity-0.276
ufact-0.273
Token Games
Token ID5776
Feature activation-1.74e+00

Pos logit contributions
�士+1.988
+1.947
Moh+1.910
Austral+1.894
ouf+1.810
Neg logit contributions
channelAvailability-2.351
estinal-1.972
 emanc-1.832
 virginity-1.758
ufact-1.752
Token have
Token ID423
Feature activation+8.02e-01

Pos logit contributions
channelAvailability+1.427
estinal+1.200
 emanc+1.119
 virginity+1.079
ufact+1.061
Neg logit contributions
�士-1.330
-1.285
Moh-1.265
Austral-1.264
ouf-1.188
Tokenuk
Token ID2724
Feature activation-2.15e+00

Pos logit contributions
channelAvailability+0.231
estinal+0.193
 emanc+0.179
 virginity+0.172
ufact+0.168
Neg logit contributions
�士-0.230
-0.219
Austral-0.215
Moh-0.214
ouf-0.201
Token/
Token ID14
Feature activation-7.48e+00

Pos logit contributions
channelAvailability+1.618
estinal+1.315
 emanc+1.210
 virginity+1.176
ufact+1.144
Neg logit contributions
�士-1.833
-1.726
Austral-1.693
Moh-1.687
ouf-1.607
Tokenbusiness
Token ID22680
Feature activation-2.58e+00

Pos logit contributions
channelAvailability+5.299
estinal+4.353
 emanc+4.102
ufact+3.849
 virginity+3.758
Neg logit contributions
�士-6.332
-6.088
Austral-5.853
Moh-5.808
ONY-5.581
Token/
Token ID14
Feature activation-8.79e+00

Pos logit contributions
channelAvailability+1.994
estinal+1.647
 emanc+1.516
 virginity+1.460
ufact+1.430
Neg logit contributions
�士-2.117
-2.050
Austral-1.998
Moh-1.991
ouf-1.882
Tokenanalysis
Token ID20930
Feature activation-7.14e-01

Pos logit contributions
channelAvailability+7.201
estinal+5.991
 emanc+5.764
ufact+5.547
chapter+5.320
Neg logit contributions
�士-6.327
-6.006
Austral-5.717
Moh-5.623
ONY-5.401
Token/
Token ID14
Feature activation-7.77e+00

Pos logit contributions
channelAvailability+0.574
estinal+0.480
 emanc+0.444
 virginity+0.427
ufact+0.422
Neg logit contributions
�士-0.561
-0.548
Moh-0.535
Austral-0.535
ouf-0.505
Tokenwhy
Token ID22850
Feature activation-1.31e+00

Pos logit contributions
channelAvailability+6.391
estinal+5.294
 emanc+5.112
ufact+4.795
 virginity+4.709
Neg logit contributions
�士-5.723
-5.291
Austral-5.067
Moh-5.000
Lay-4.787
Token-
Token ID12
Feature activation-1.63e+00

Pos logit contributions
channelAvailability+1.083
estinal+0.906
 emanc+0.846
 virginity+0.809
ufact+0.800
Neg logit contributions
�士-1.031
-0.986
Moh-0.960
Austral-0.955
ouf-0.900
Tokenaut
Token ID2306
Feature activation+7.10e-01

Pos logit contributions
channelAvailability+1.602
estinal+1.377
 emanc+1.306
ufact+1.256
 virginity+1.241
Neg logit contributions
�士-1.032
-0.969
Moh-0.924
Austral-0.914
ouf-0.842
Tokenom
Token ID296
Feature activation+6.38e+00

Pos logit contributions
�士+0.442
+0.426
Moh+0.413
Austral+0.412
ouf+0.379
Neg logit contributions
channelAvailability-0.691
estinal-0.599
 emanc-0.564
 virginity-0.546
ufact-0.545
Tokenation
Token ID341
Feature activation-1.64e-01

Pos logit contributions
Moh+4.808
�士+4.786
+4.735
Austral+4.690
lection+4.591
Neg logit contributions
channelAvailability-5.061
estinal-4.275
 emanc-3.817
 virginity-3.773
 mathemat-3.648
TokenHowever
Token ID4864
Feature activation-2.42e-01

Pos logit contributions
channelAvailability+0.282
estinal+0.242
 emanc+0.228
 virginity+0.221
ufact+0.218
Neg logit contributions
�士-0.175
-0.166
Austral-0.159
Moh-0.158
ouf-0.149
Token,
Token ID11
Feature activation-8.06e-02

Pos logit contributions
channelAvailability+0.205
estinal+0.174
 emanc+0.163
 virginity+0.157
ufact+0.155
Neg logit contributions
�士-0.179
-0.174
Austral-0.170
Moh-0.170
ouf-0.159
Token this
Token ID428
Feature activation-8.81e-01

Pos logit contributions
channelAvailability+0.068
estinal+0.057
 emanc+0.053
 virginity+0.051
ufact+0.050
Neg logit contributions
�士-0.061
-0.059
Moh-0.058
Austral-0.058
ouf-0.054
Token is
Token ID318
Feature activation+7.32e-01

Pos logit contributions
channelAvailability+0.732
estinal+0.618
 emanc+0.581
 virginity+0.559
ufact+0.549
Neg logit contributions
�士-0.672
-0.651
Austral-0.636
Moh-0.635
ouf-0.595
Token barely
Token ID8523
Feature activation-2.51e-01

Pos logit contributions
�士+0.573
+0.560
Moh+0.549
Austral+0.548
ouf+0.516
Neg logit contributions
channelAvailability-0.591
estinal-0.495
 emanc-0.456
 virginity-0.440
ufact-0.435
Token enough
Token ID1576
Feature activation-7.75e+00

Pos logit contributions
channelAvailability+0.213
estinal+0.180
 emanc+0.168
 virginity+0.162
ufact+0.160
Neg logit contributions
�士-0.186
-0.181
Moh-0.177
Austral-0.177
ouf-0.166
Token for
Token ID329
Feature activation-2.25e+00

Pos logit contributions
channelAvailability+6.199
estinal+5.179
 emanc+5.055
 virginity+4.772
ufact+4.615
Neg logit contributions
�士-6.001
Austral-5.555
-5.546
Moh-5.502
ouf-5.133
Token any
Token ID597
Feature activation-2.82e-01

Pos logit contributions
channelAvailability+1.871
estinal+1.576
 emanc+1.484
 virginity+1.426
ufact+1.408
Neg logit contributions
�士-1.706
-1.648
Austral-1.619
Moh-1.611
ouf-1.517
Token realistic
Token ID12653
Feature activation-7.37e-01

Pos logit contributions
channelAvailability+0.231
estinal+0.194
 emanc+0.180
 virginity+0.173
ufact+0.171
Neg logit contributions
�士-0.217
-0.212
Moh-0.208
Austral-0.207
ouf-0.195
Token optimism
Token ID24323
Feature activation-2.06e+00

Pos logit contributions
channelAvailability+0.597
estinal+0.500
 emanc+0.465
 virginity+0.447
ufact+0.441
Neg logit contributions
�士-0.577
-0.562
Moh-0.550
Austral-0.549
ouf-0.517
Token.
Token ID13
Feature activation-7.99e-01

Pos logit contributions
channelAvailability+1.729
estinal+1.457
 emanc+1.371
 virginity+1.315
ufact+1.298
Neg logit contributions
�士-1.542
-1.482
Austral-1.458
Moh-1.457
ouf-1.364
Token of
Token ID286
Feature activation+3.48e-01

Pos logit contributions
�士+0.022
+0.021
Moh+0.021
Austral+0.021
ouf+0.020
Neg logit contributions
channelAvailability-0.029
estinal-0.025
 emanc-0.023
 virginity-0.023
ufact-0.022
Token Sciences
Token ID13473
Feature activation-2.17e+00

Pos logit contributions
�士+0.218
+0.211
Moh+0.205
Austral+0.205
ouf+0.190
Neg logit contributions
channelAvailability-0.336
estinal-0.291
 emanc-0.273
 virginity-0.265
ufact-0.263
Token.
Token ID13
Feature activation-5.56e-01

Pos logit contributions
channelAvailability+1.821
estinal+1.537
 emanc+1.427
 virginity+1.369
ufact+1.348
Neg logit contributions
�士-1.640
-1.591
Moh-1.563
Austral-1.559
ouf-1.465
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
channelAvailability+0.428
estinal+0.354
 emanc+0.326
 virginity+0.314
ufact+0.309
Neg logit contributions
�士-0.458
-0.444
Moh-0.437
Austral-0.435
ouf-0.412
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
channelAvailability+0.872
estinal+0.689
 emanc+0.634
 virginity+0.609
ufact+0.580
Neg logit contributions
�士-1.152
-1.082
Austral-1.058
Moh-1.056
ouf-1.013
TokenExplore
Token ID35433
Feature activation-7.67e+00

Pos logit contributions
channelAvailability+1.092
estinal+0.946
 emanc+0.889
 virginity+0.863
ufact+0.851
Neg logit contributions
�士-0.637
-0.599
Moh-0.579
Austral-0.576
ouf-0.537
Token further
Token ID2252
Feature activation+1.04e+00

Pos logit contributions
channelAvailability+3.629
estinal+2.568
 emanc+2.313
 virginity+2.189
 severed+1.905
Neg logit contributions
�士-8.584
-8.018
Moh-7.912
Austral-7.882
ouf-7.646
Token:
Token ID25
Feature activation-1.84e-01

Pos logit contributions
�士+0.883
+0.880
Moh+0.862
Austral+0.861
ouf+0.813
Neg logit contributions
channelAvailability-0.761
estinal-0.629
 emanc-0.572
ufact-0.547
 virginity-0.547
Token New
Token ID968
Feature activation+2.28e+00

Pos logit contributions
channelAvailability+0.156
estinal+0.132
 emanc+0.123
 virginity+0.120
ufact+0.117
Neg logit contributions
�士-0.136
-0.132
Moh-0.129
Austral-0.128
ouf-0.121
Token Insight
Token ID39917
Feature activation-2.79e-01

Pos logit contributions
�士+1.647
+1.621
Austral+1.594
Moh+1.587
ouf+1.490
Neg logit contributions
channelAvailability-1.980
estinal-1.647
 emanc-1.515
ufact-1.479
 virginity-1.465
Token Into
Token ID20008
Feature activation-5.01e-01

Pos logit contributions
channelAvailability+0.252
estinal+0.215
 emanc+0.201
 virginity+0.195
ufact+0.193
Neg logit contributions
�士-0.192
-0.187
Moh-0.182
Austral-0.182
ouf-0.170
Token.
Token ID13
Feature activation+1.29e+00

Pos logit contributions
�士+0.515
+0.503
Moh+0.492
Austral+0.491
ouf+0.460
Neg logit contributions
channelAvailability-0.629
estinal-0.535
 emanc-0.498
 virginity-0.481
ufact-0.476
Tokenuk
Token ID2724
Feature activation-3.76e-01

Pos logit contributions
�士+0.939
+0.937
Moh+0.921
Austral+0.914
ouf+0.862
Neg logit contributions
channelAvailability-1.101
estinal-0.937
 emanc-0.871
 virginity-0.838
ufact-0.836
Token/
Token ID14
Feature activation-6.64e+00

Pos logit contributions
channelAvailability+0.297
estinal+0.246
 emanc+0.227
 virginity+0.220
ufact+0.216
Neg logit contributions
�士-0.303
-0.293
Austral-0.287
Moh-0.287
ouf-0.271
Tokenin
Token ID259
Feature activation-1.12e+00

Pos logit contributions
channelAvailability+5.477
estinal+4.616
 emanc+4.320
ufact+4.096
 virginity+4.091
Neg logit contributions
�士-4.910
-4.731
Austral-4.533
Moh-4.505
ONY-4.307
Tokencoming
Token ID4976
Feature activation+1.45e-01

Pos logit contributions
channelAvailability+0.878
estinal+0.736
 emanc+0.673
 virginity+0.649
ufact+0.643
Neg logit contributions
�士-0.910
-0.877
Moh-0.858
Austral-0.858
ouf-0.807
Token/
Token ID14
Feature activation-7.57e+00

Pos logit contributions
�士+0.112
+0.110
Moh+0.108
Austral+0.107
ouf+0.101
Neg logit contributions
channelAvailability-0.118
estinal-0.099
 emanc-0.092
 virginity-0.089
ufact-0.087
Tokenarticle
Token ID20205
Feature activation+5.85e-01

Pos logit contributions
channelAvailability+6.098
estinal+5.124
 emanc+4.914
ufact+4.610
chapter+4.499
Neg logit contributions
�士-5.645
-5.469
Austral-5.217
Moh-5.128
ouf-4.946
Token35
Token ID2327
Feature activation-3.52e-01

Pos logit contributions
�士+0.444
+0.434
Moh+0.425
Austral+0.424
ouf+0.399
Neg logit contributions
channelAvailability-0.487
estinal-0.410
 emanc-0.380
 virginity-0.367
ufact-0.362
Token79
Token ID3720
Feature activation+8.68e-01

Pos logit contributions
channelAvailability+0.420
estinal+0.370
 emanc+0.353
 virginity+0.346
ufact+0.345
Neg logit contributions
�士-0.142
-0.132
Austral-0.126
Moh-0.124
ouf-0.111
Token23
Token ID1954
Feature activation+5.99e-01

Pos logit contributions
�士+0.517
+0.500
Moh+0.484
Austral+0.484
ouf+0.446
Neg logit contributions
channelAvailability-0.865
estinal-0.749
 emanc-0.705
 virginity-0.686
ufact-0.680
Token12
Token ID1065
Feature activation+4.48e-01

Pos logit contributions
�士+0.425
+0.414
Moh+0.404
Austral+0.403
ouf+0.377
Neg logit contributions
channelAvailability-0.529
estinal-0.449
 emanc-0.419
 virginity-0.406
ufact-0.401
Tokenlegraph
Token ID16606
Feature activation-9.08e-01

Pos logit contributions
�士+0.367
+0.361
Moh+0.355
Austral+0.354
ouf+0.339
Neg logit contributions
channelAvailability-0.212
estinal-0.164
 emanc-0.145
 virginity-0.137
ufact-0.135
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
channelAvailability+0.738
estinal+0.605
 emanc+0.557
 virginity+0.544
ufact+0.526
Neg logit contributions
�士-0.746
-0.680
Austral-0.663
Moh-0.663
ouf-0.631
Tokenco
Token ID1073
Feature activation-8.44e-01

Pos logit contributions
channelAvailability+1.157
estinal+0.956
 emanc+0.883
 virginity+0.846
ufact+0.826
Neg logit contributions
�士-1.265
-1.207
Austral-1.182
Moh-1.174
ouf-1.109
Token.
Token ID13
Feature activation-2.87e-01

Pos logit contributions
channelAvailability+0.707
estinal+0.594
 emanc+0.551
 virginity+0.533
ufact+0.519
Neg logit contributions
�士-0.652
-0.614
Austral-0.599
Moh-0.597
ouf-0.563
Tokenuk
Token ID2724
Feature activation-2.15e+00

Pos logit contributions
channelAvailability+0.231
estinal+0.193
 emanc+0.179
 virginity+0.172
ufact+0.168
Neg logit contributions
�士-0.230
-0.219
Austral-0.215
Moh-0.214
ouf-0.201
Token/
Token ID14
Feature activation-7.48e+00

Pos logit contributions
channelAvailability+1.618
estinal+1.315
 emanc+1.210
 virginity+1.176
ufact+1.144
Neg logit contributions
�士-1.833
-1.726
Austral-1.693
Moh-1.687
ouf-1.607
Tokenbusiness
Token ID22680
Feature activation-2.58e+00

Pos logit contributions
channelAvailability+5.299
estinal+4.353
 emanc+4.102
ufact+3.849
 virginity+3.758
Neg logit contributions
�士-6.332
-6.088
Austral-5.853
Moh-5.808
ONY-5.581
Token/
Token ID14
Feature activation-8.79e+00

Pos logit contributions
channelAvailability+1.994
estinal+1.647
 emanc+1.516
 virginity+1.460
ufact+1.430
Neg logit contributions
�士-2.117
-2.050
Austral-1.998
Moh-1.991
ouf-1.882
Tokenanalysis
Token ID20930
Feature activation-7.14e-01

Pos logit contributions
channelAvailability+7.201
estinal+5.991
 emanc+5.764
ufact+5.547
chapter+5.320
Neg logit contributions
�士-6.327
-6.006
Austral-5.717
Moh-5.623
ONY-5.401
Token/
Token ID14
Feature activation-7.77e+00

Pos logit contributions
channelAvailability+0.574
estinal+0.480
 emanc+0.444
 virginity+0.427
ufact+0.422
Neg logit contributions
�士-0.561
-0.548
Moh-0.535
Austral-0.535
ouf-0.505
Tokenwhy
Token ID22850
Feature activation-1.31e+00

Pos logit contributions
channelAvailability+6.391
estinal+5.294
 emanc+5.112
ufact+4.795
 virginity+4.709
Neg logit contributions
�士-5.723
-5.291
Austral-5.067
Moh-5.000
Lay-4.787
Token45
Token ID2231
Feature activation+3.17e+00

Pos logit contributions
channelAvailability+1.369
estinal+1.149
 emanc+1.070
 virginity+1.036
ufact+1.023
Neg logit contributions
�士-1.186
-1.147
Moh-1.116
Austral-1.113
ouf-1.051
Token 287
Token ID38721
Feature activation+1.74e+00

Pos logit contributions
�士+1.779
+1.733
Moh+1.684
Austral+1.677
729+1.545
Neg logit contributions
channelAvailability-3.257
estinal-2.847
 emanc-2.669
 virginity-2.599
ufact-2.593
Token 119
Token ID15136
Feature activation+9.11e-01

Pos logit contributions
�士+1.009
+0.979
Moh+0.951
Austral+0.949
ouf+0.874
Neg logit contributions
channelAvailability-1.753
estinal-1.525
 emanc-1.436
 virginity-1.396
ufact-1.384
Token8
Token ID23
Feature activation+2.95e+00

Pos logit contributions
�士+0.641
+0.627
Moh+0.614
Austral+0.611
ouf+0.572
Neg logit contributions
channelAvailability-0.807
estinal-0.688
 emanc-0.640
 virginity-0.619
ufact-0.615
Token;
Token ID26
Feature activation+1.20e+00

Pos logit contributions
�士+1.955
+1.909
Moh+1.865
Austral+1.850
ouf+1.725
Neg logit contributions
channelAvailability-2.727
estinal-2.341
 emanc-2.189
 virginity-2.127
ufact-2.111
Token adventure
Token ID8855
Feature activation-7.46e+00

Pos logit contributions
�士+0.903
+0.882
Austral+0.862
Moh+0.862
ouf+0.810
Neg logit contributions
channelAvailability-1.007
estinal-0.852
 emanc-0.782
 virginity-0.759
ufact-0.751
Tokencompany
Token ID39722
Feature activation-3.15e+00

Pos logit contributions
channelAvailability+6.267
estinal+5.398
ufact+4.923
 emanc+4.921
 virginity+4.681
Neg logit contributions
�士-5.168
-5.026
Moh-4.886
Austral-4.793
ع-4.579
Token.
Token ID13
Feature activation+7.56e-01

Pos logit contributions
channelAvailability+2.576
estinal+2.171
 emanc+1.993
ufact+1.928
 virginity+1.920
Neg logit contributions
�士-2.418
-2.353
Moh-2.258
Austral-2.244
ouf-2.137
Tokenco
Token ID1073
Feature activation+1.89e+00

Pos logit contributions
�士+0.513
+0.500
Moh+0.489
Austral+0.488
ouf+0.455
Neg logit contributions
channelAvailability-0.688
estinal-0.589
 emanc-0.551
 virginity-0.533
ufact-0.527
Token.
Token ID13
Feature activation+1.18e+00

Pos logit contributions
+1.279
�士+1.272
Moh+1.254
Austral+1.247
lection+1.168
Neg logit contributions
channelAvailability-1.707
estinal-1.457
 emanc-1.361
 virginity-1.316
ufact-1.316
Tokenuk
Token ID2724
Feature activation+1.35e+00

Pos logit contributions
�士+0.856
+0.849
Moh+0.835
Austral+0.832
ouf+0.783
Neg logit contributions
channelAvailability-1.004
estinal-0.851
 emanc-0.791
 virginity-0.762
ufact-0.758
Tokenee
Token ID1453
Feature activation+3.02e-01

Pos logit contributions
�士+0.077
+0.075
Moh+0.073
Austral+0.073
ouf+0.068
Neg logit contributions
channelAvailability-0.124
estinal-0.107
 emanc-0.101
 virginity-0.098
ufact-0.097
Tokenpl
Token ID489
Feature activation-3.03e-01

Pos logit contributions
�士+0.090
+0.085
Moh+0.081
Austral+0.081
ouf+0.067
Neg logit contributions
channelAvailability-0.390
estinal-0.350
 emanc-0.334
 virginity-0.328
ufact-0.325
Tokeninks
Token ID2973
Feature activation-6.62e-01

Pos logit contributions
channelAvailability+0.256
estinal+0.220
 emanc+0.204
 virginity+0.196
ufact+0.196
Neg logit contributions
�士-0.226
-0.216
Austral-0.210
Moh-0.210
ouf-0.196
Token/
Token ID14
Feature activation-4.18e+00

Pos logit contributions
channelAvailability+0.532
estinal+0.445
 emanc+0.412
 virginity+0.396
ufact+0.393
Neg logit contributions
�士-0.522
-0.508
Moh-0.498
Austral-0.498
ouf-0.469
Token2016
Token ID5304
Feature activation+4.84e-01

Pos logit contributions
channelAvailability+3.989
estinal+3.387
 emanc+3.241
ufact+3.110
 virginity+3.109
Neg logit contributions
�士-2.657
-2.499
Moh-2.415
Austral-2.405
ouf-2.223
Token/
Token ID14
Feature activation-7.45e+00

Pos logit contributions
�士+0.380
+0.371
Moh+0.363
Austral+0.363
ouf+0.342
Neg logit contributions
channelAvailability-0.391
estinal-0.327
 emanc-0.302
 virginity-0.291
ufact-0.288
Token06
Token ID3312
Feature activation-2.71e+00

Pos logit contributions
channelAvailability+5.598
estinal+4.561
 emanc+4.392
 virginity+4.100
ufact+4.010
Neg logit contributions
�士-6.176
-5.641
Austral-5.447
Moh-5.392
ONY-5.185
Token/
Token ID14
Feature activation-4.06e+00

Pos logit contributions
channelAvailability+2.051
estinal+1.664
 emanc+1.540
 virginity+1.482
ufact+1.437
Neg logit contributions
�士-2.323
-2.183
Austral-2.131
Moh-2.128
ouf-2.029
Tokent
Token ID83
Feature activation+6.27e-01

Pos logit contributions
channelAvailability+3.658
estinal+3.113
 emanc+2.972
 virginity+2.859
ufact+2.828
Neg logit contributions
�士-2.789
-2.618
Austral-2.526
Moh-2.522
ONY-2.354
Tokenatt
Token ID1078
Feature activation+3.15e+00

Pos logit contributions
�士+0.338
+0.329
Moh+0.322
Austral+0.321
ouf+0.297
Neg logit contributions
channelAvailability-0.658
estinal-0.574
 emanc-0.541
 virginity-0.528
ufact-0.522
Tokenoo
Token ID2238
Feature activation+6.93e-01

Pos logit contributions
+1.212
�士+1.212
Moh+1.162
Austral+1.147
ouf+1.077
Neg logit contributions
channelAvailability-3.734
estinal-3.300
 emanc-3.154
 virginity-3.105
 mathemat-3.042
Tokenbur
Token ID6236
Feature activation-4.60e-01

Pos logit contributions
�士+0.414
+0.408
Moh+0.401
Austral+0.399
ouf+0.378
Neg logit contributions
channelAvailability-0.438
estinal-0.367
 emanc-0.340
 virginity-0.329
ufact-0.322
Token.
Token ID13
Feature activation+2.33e+00

Pos logit contributions
channelAvailability+0.412
estinal+0.353
 emanc+0.329
 virginity+0.318
ufact+0.316
Neg logit contributions
�士-0.319
-0.310
Austral-0.303
Moh-0.302
ouf-0.281
Tokenorg
Token ID2398
Feature activation+1.15e+00

Pos logit contributions
�士+1.441
+1.405
Moh+1.379
Austral+1.364
ouf+1.274
Neg logit contributions
channelAvailability-2.240
estinal-1.947
 emanc-1.825
 virginity-1.778
ufact-1.754
Token/
Token ID14
Feature activation-3.34e+00

Pos logit contributions
�士+0.881
+0.868
Moh+0.846
Austral+0.842
ouf+0.793
Neg logit contributions
channelAvailability-0.954
estinal-0.803
 emanc-0.743
 virginity-0.715
ufact-0.708
Token2015
Token ID4626
Feature activation-1.33e-01

Pos logit contributions
channelAvailability+3.158
estinal+2.702
 emanc+2.542
 virginity+2.451
ufact+2.432
Neg logit contributions
�士-2.150
-2.058
Austral-1.993
Moh-1.986
ouf-1.846
Token/
Token ID14
Feature activation-7.35e+00

Pos logit contributions
channelAvailability+0.106
estinal+0.089
 emanc+0.082
 virginity+0.079
ufact+0.078
Neg logit contributions
�士-0.105
-0.103
Moh-0.101
Austral-0.101
ouf-0.095
Token08
Token ID2919
Feature activation-1.78e+00

Pos logit contributions
channelAvailability+5.363
estinal+4.320
 emanc+4.054
 virginity+3.832
ufact+3.739
Neg logit contributions
�士-6.318
-5.803
Austral-5.619
Moh-5.563
ONY-5.304
Token/
Token ID14
Feature activation-5.09e+00

Pos logit contributions
channelAvailability+1.361
estinal+1.108
 emanc+1.026
 virginity+0.989
ufact+0.953
Neg logit contributions
�士-1.505
-1.422
Austral-1.385
Moh-1.383
ouf-1.320
Token11
Token ID1157
Feature activation-5.00e-01

Pos logit contributions
channelAvailability+4.127
estinal+3.473
 emanc+3.277
 virginity+3.139
ufact+3.038
Neg logit contributions
�士-3.998
-3.716
Austral-3.576
Moh-3.558
ONY-3.370
Token/
Token ID14
Feature activation-4.73e+00

Pos logit contributions
channelAvailability+0.401
estinal+0.335
 emanc+0.309
 virginity+0.298
ufact+0.294
Neg logit contributions
�士-0.395
-0.386
Moh-0.378
Austral-0.377
ouf-0.356
Tokene
Token ID68
Feature activation-1.02e+00

Pos logit contributions
channelAvailability+4.496
estinal+3.859
 emanc+3.643
 virginity+3.522
ufact+3.442
Neg logit contributions
�士-3.027
-2.836
Austral-2.733
Moh-2.711
ONY-2.514
TokenSize
Token ID10699
Feature activation-3.61e+00

Pos logit contributions
channelAvailability+1.321
estinal+1.140
 emanc+1.068
 virginity+1.038
ufact+1.024
Neg logit contributions
�士-0.855
-0.826
Moh-0.800
Austral-0.795
ouf-0.744
Token()
Token ID3419
Feature activation-1.36e-01

Pos logit contributions
channelAvailability+3.216
estinal+2.769
 emanc+2.584
 virginity+2.469
ufact+2.437
Neg logit contributions
�士-2.519
-2.359
Moh-2.316
Austral-2.306
ouf-2.172
Token ;
Token ID2162
Feature activation+7.38e-01

Pos logit contributions
channelAvailability+0.132
estinal+0.114
 emanc+0.107
 virginity+0.104
ufact+0.103
Neg logit contributions
�士-0.084
-0.082
Moh-0.080
Austral-0.080
ouf-0.074
Token for
Token ID329
Feature activation-6.85e-01

Pos logit contributions
�士+0.532
+0.524
Moh+0.509
Austral+0.507
ouf+0.483
Neg logit contributions
channelAvailability-0.640
estinal-0.538
 emanc-0.495
 virginity-0.482
ufact-0.480
Token(
Token ID7
Feature activation+1.08e+00

Pos logit contributions
channelAvailability+0.520
estinal+0.430
 emanc+0.395
 virginity+0.379
ufact+0.374
Neg logit contributions
�士-0.569
-0.557
Moh-0.546
Austral-0.545
ouf-0.516
Token size
Token ID2546
Feature activation-7.30e+00

Pos logit contributions
�士+0.770
+0.761
Moh+0.742
Austral+0.734
lection+0.700
Neg logit contributions
channelAvailability-0.936
estinal-0.793
 emanc-0.740
 virginity-0.720
ufact-0.713
Token_
Token ID62
Feature activation-3.23e+00

Pos logit contributions
channelAvailability+5.139
estinal+4.130
 emanc+3.681
 virginity+3.631
ufact+3.315
Neg logit contributions
�士-6.648
-6.070
Moh-5.955
Austral-5.927
ONY-5.621
Tokent
Token ID83
Feature activation-4.77e+00

Pos logit contributions
channelAvailability+2.943
estinal+2.503
 emanc+2.330
 virginity+2.262
ufact+2.202
Neg logit contributions
�士-2.256
-2.112
Moh-2.052
Austral-2.046
ONY-1.904
Token u
Token ID334
Feature activation-4.88e+00

Pos logit contributions
channelAvailability+3.601
estinal+3.004
 emanc+2.757
 virginity+2.658
ufact+2.567
Neg logit contributions
�士-3.964
-3.802
Austral-3.787
Moh-3.773
ONY-3.543
TokenPart
Token ID7841
Feature activation-2.58e+00

Pos logit contributions
channelAvailability+4.641
estinal+4.024
 emanc+3.760
 virginity+3.634
ufact+3.577
Neg logit contributions
�士-3.104
-2.912
Moh-2.863
Austral-2.858
ouf-2.658
Tokenicle
Token ID1548
Feature activation-7.41e-01

Pos logit contributions
channelAvailability+2.179
estinal+1.842
 emanc+1.697
 virginity+1.643
ufact+1.622
Neg logit contributions
�士-1.949
-1.882
Moh-1.839
Austral-1.838
ouf-1.720
Token former
Token ID1966
Feature activation+8.03e-01

Pos logit contributions
channelAvailability+0.186
estinal+0.156
 emanc+0.144
 virginity+0.139
ufact+0.139
Neg logit contributions
�士-0.169
-0.165
Moh-0.162
Austral-0.162
ouf-0.152
Token President
Token ID1992
Feature activation-1.30e+00

Pos logit contributions
�士+0.574
+0.559
Moh+0.548
Austral+0.547
ouf+0.512
Neg logit contributions
channelAvailability-0.704
estinal-0.598
 emanc-0.550
ufact-0.538
 virginity-0.531
Token Barack
Token ID8732
Feature activation+6.42e-01

Pos logit contributions
channelAvailability+1.186
estinal+1.020
 emanc+0.957
 virginity+0.929
ufact+0.912
Neg logit contributions
�士-0.884
-0.853
Austral-0.834
Moh-0.829
ouf-0.779
Token Obama
Token ID2486
Feature activation-1.56e+00

Pos logit contributions
�士+0.460
+0.451
Moh+0.443
Austral+0.441
ouf+0.412
Neg logit contributions
channelAvailability-0.559
estinal-0.477
 emanc-0.442
 virginity-0.427
ufact-0.424
Token Barack
Token ID8732
Feature activation+9.70e+00

Pos logit contributions
channelAvailability+1.292
estinal+1.085
 emanc+1.017
 virginity+0.986
ufact+0.965
Neg logit contributions
�士-1.187
-1.133
Moh-1.119
Austral-1.119
ouf-1.054
Token Hussein
Token ID22983
Feature activation+5.98e+00

Pos logit contributions
Moh+3.548
Austral+3.202
�士+2.978
Lay+2.936
Carter+2.921
Neg logit contributions
channelAvailability-11.471
estinal-10.688
 emanc-9.805
ufact-9.798
 virginity-9.467
Token Obama
Token ID2486
Feature activation+3.60e+00

Pos logit contributions
Moh+3.501
Austral+3.489
�士+3.458
+3.414
Carter+3.242
Neg logit contributions
channelAvailability-5.761
estinal-5.071
 mathemat-4.621
 emanc-4.601
 virginity-4.517
TokenWith
Token ID3152
Feature activation+2.62e+00

Pos logit contributions
�士+2.068
Moh+2.014
Austral+2.010
+1.992
Carter+1.827
Neg logit contributions
channelAvailability-3.616
estinal-3.145
 emanc-2.968
ufact-2.897
 virginity-2.891
Token low
Token ID1877
Feature activation+3.25e+00

Pos logit contributions
�士+2.108
+2.060
Moh+2.019
Austral+2.016
ouf+1.902
Neg logit contributions
channelAvailability-2.056
estinal-1.713
 emanc-1.579
 virginity-1.518
ufact-1.502
Token birth
Token ID4082
Feature activation+4.78e-01

Pos logit contributions
+2.412
�士+2.314
Austral+2.288
Moh+2.242
ع+2.163
Neg logit contributions
channelAvailability-2.709
estinal-2.212
ufact-2.106
 mathemat-2.088
 emanc-2.063
Token rate
Token ID2494
Feature activation+1.14e+00

Pos logit contributions
�士+0.353
+0.345
Moh+0.337
Austral+0.337
ouf+0.316
Neg logit contributions
channelAvailability-0.408
estinal-0.344
 emanc-0.320
 virginity-0.309
ufact-0.306
Token "
Token ID366
Feature activation-1.02e-01

Pos logit contributions
channelAvailability+1.387
estinal+1.172
 emanc+1.095
 virginity+1.059
ufact+1.034
Neg logit contributions
�士-1.255
-1.218
Austral-1.197
Moh-1.187
ouf-1.129
Tokenf
Token ID69
Feature activation+1.54e+00

Pos logit contributions
channelAvailability+0.098
estinal+0.084
 emanc+0.079
 virginity+0.077
ufact+0.076
Neg logit contributions
�士-0.064
-0.062
Austral-0.060
Moh-0.060
ouf-0.056
Tokenaint
Token ID2913
Feature activation+4.06e+00

Pos logit contributions
�士+1.031
+1.010
Moh+0.988
Austral+0.984
ouf+0.922
Neg logit contributions
channelAvailability-1.422
estinal-1.210
 emanc-1.137
 virginity-1.101
ufact-1.087
Token yells
Token ID42675
Feature activation+1.36e+00

Pos logit contributions
�士+3.177
+3.116
Moh+3.077
Austral+3.056
lection+2.882
Neg logit contributions
channelAvailability-3.287
estinal-2.705
 emanc-2.462
ufact-2.384
 virginity-2.384
Token for
Token ID329
Feature activation+1.24e+00

Pos logit contributions
�士+0.894
+0.874
Moh+0.851
Austral+0.847
ouf+0.791
Neg logit contributions
channelAvailability-1.273
estinal-1.092
 emanc-1.016
 virginity-0.989
ufact-0.979
Token help
Token ID1037
Feature activation+5.86e+00

Pos logit contributions
�士+1.148
+1.126
Moh+1.110
Austral+1.107
ouf+1.052
Neg logit contributions
channelAvailability-0.815
estinal-0.659
 emanc-0.582
ufact-0.556
 virginity-0.554
Token on
Token ID319
Feature activation+1.47e+00

Pos logit contributions
+3.441
�士+3.361
Moh+3.310
Austral+3.250
lection+3.089
Neg logit contributions
channelAvailability-5.747
estinal-4.987
 emanc-4.567
 virginity-4.515
ufact-4.452
Token the
Token ID262
Feature activation+1.54e+00

Pos logit contributions
�士+1.047
+1.021
Moh+0.999
Austral+0.995
ouf+0.933
Neg logit contributions
channelAvailability-1.288
estinal-1.096
 emanc-1.016
 virginity-0.984
ufact-0.979
Token roadway
Token ID35852
Feature activation+1.78e+00

Pos logit contributions
�士+1.118
+1.094
Moh+1.071
Austral+1.064
ouf+1.002
Neg logit contributions
channelAvailability-1.328
estinal-1.125
 emanc-1.034
 virginity-1.002
ufact-1.000
Token from
Token ID422
Feature activation+5.78e-01

Pos logit contributions
�士+1.180
+1.161
Moh+1.128
Austral+1.123
ouf+1.052
Neg logit contributions
channelAvailability-1.636
estinal-1.403
 emanc-1.299
 virginity-1.265
ufact-1.255
Token the
Token ID262
Feature activation+7.03e-01

Pos logit contributions
�士+0.431
+0.422
Moh+0.413
Austral+0.412
ouf+0.386
Neg logit contributions
channelAvailability-0.487
estinal-0.413
 emanc-0.381
 virginity-0.368
ufact-0.366
Token smooth
Token ID7209
Feature activation-1.39e+00

Pos logit contributions
channelAvailability+1.137
estinal+0.960
 emanc+0.896
 virginity+0.865
ufact+0.844
Neg logit contributions
�士-1.079
-1.038
Austral-1.025
Moh-1.020
ouf-0.961
Tokenie
Token ID494
Feature activation-1.48e+00

Pos logit contributions
channelAvailability+1.175
estinal+1.002
 emanc+0.937
 virginity+0.905
ufact+0.888
Neg logit contributions
�士-1.005
-0.974
Austral-0.966
Moh-0.953
ouf-0.895
Token
Token ID960
Feature activation-2.23e+00

Pos logit contributions
channelAvailability+1.219
estinal+1.027
 emanc+0.966
 virginity+0.935
ufact+0.917
Neg logit contributions
�士-1.127
-1.071
Austral-1.064
Moh-1.061
ouf-0.995
Tokend
Token ID67
Feature activation+1.76e-01

Pos logit contributions
channelAvailability+2.150
estinal+1.847
 emanc+1.741
 virginity+1.690
ufact+1.673
Neg logit contributions
�士-1.387
-1.317
Austral-1.277
Moh-1.275
lection-1.189
Tokenare
Token ID533
Feature activation+4.85e+00

Pos logit contributions
�士+0.110
+0.107
Moh+0.104
Austral+0.104
ouf+0.097
Neg logit contributions
channelAvailability-0.170
estinal-0.146
 emanc-0.137
 virginity-0.133
ufact-0.132
Token I
Token ID314
Feature activation+7.07e+00

Pos logit contributions
+3.017
�士+2.968
Moh+2.832
Austral+2.824
lection+2.662
Neg logit contributions
channelAvailability-4.659
estinal-4.054
 emanc-3.723
ufact-3.621
 virginity-3.595
Token say
Token ID910
Feature activation+8.29e-01

Pos logit contributions
+3.926
�士+3.696
Moh+3.639
Austral+3.513
lection+3.376
Neg logit contributions
channelAvailability-7.241
estinal-6.285
ufact-5.740
 emanc-5.721
 virginity-5.654
Token it
Token ID340
Feature activation-2.33e-01

Pos logit contributions
�士+0.630
+0.613
Moh+0.601
Austral+0.600
ouf+0.564
Neg logit contributions
channelAvailability-0.689
estinal-0.580
 emanc-0.540
 virginity-0.520
ufact-0.513
Token
Token ID960
Feature activation-6.76e-01

Pos logit contributions
channelAvailability+0.202
estinal+0.171
 emanc+0.161
 virginity+0.155
ufact+0.153
Neg logit contributions
�士-0.168
-0.162
Moh-0.160
Austral-0.159
ouf-0.150
Tokenever
Token ID964
Feature activation-2.26e+00

Pos logit contributions
channelAvailability+0.668
estinal+0.577
 emanc+0.544
 virginity+0.529
ufact+0.523
Neg logit contributions
�士-0.408
-0.389
Austral-0.377
Moh-0.376
ouf-0.349
Token?
Token ID30
Feature activation-1.48e+00

Pos logit contributions
channelAvailability+1.889
estinal+1.598
 emanc+1.498
 virginity+1.441
ufact+1.435
Neg logit contributions
�士-1.708
-1.622
Austral-1.612
Moh-1.603
ouf-1.503
Token Donald
Token ID3759
Feature activation+2.35e+00

Pos logit contributions
�士+0.596
+0.577
Moh+0.562
Austral+0.561
ouf+0.519
Neg logit contributions
channelAvailability-0.962
estinal-0.833
 emanc-0.783
 virginity-0.761
ufact-0.753
Token Trump
Token ID1301
Feature activation-1.25e-01

Pos logit contributions
�士+1.349
+1.311
Moh+1.275
Austral+1.270
ouf+1.168
Neg logit contributions
channelAvailability-2.395
estinal-2.088
 emanc-1.967
 virginity-1.912
ufact-1.896
Token Donald
Token ID3759
Feature activation+9.51e+00

Pos logit contributions
channelAvailability+0.122
estinal+0.106
 emanc+0.100
 virginity+0.097
ufact+0.096
Neg logit contributions
�士-0.077
-0.075
Austral-0.073
Moh-0.073
ouf-0.067
Token John
Token ID1757
Feature activation+7.09e+00

Pos logit contributions
Moh+5.070
Austral+5.019
lection+4.841
�士+4.727
 McGr+4.594
Neg logit contributions
channelAvailability-9.370
estinal-8.466
ufact-7.876
 emanc-7.860
 mathemat-7.672
Token Trump
Token ID1301
Feature activation+3.18e+00

Pos logit contributions
+3.000
�士+2.960
Moh+2.931
Austral+2.759
Carter+2.717
Neg logit contributions
channelAvailability-7.906
estinal-6.981
ufact-6.642
 mathemat-6.616
 emanc-6.594
TokenHouse
Token ID18102
Feature activation+8.46e+00

Pos logit contributions
�士+1.676
Moh+1.620
Austral+1.604
+1.588
Carter+1.450
Neg logit contributions
channelAvailability-3.372
estinal-2.963
 emanc-2.802
ufact-2.746
 virginity-2.725
Token committee
Token ID5583
Feature activation+5.24e+00

Pos logit contributions
�士+5.520
Moh+5.232
+5.096
729+4.911
Carter+4.852
Neg logit contributions
channelAvailability-7.717
estinal-6.164
 mathemat-6.012
 emanc-5.903
ufact-5.846
Token believes
Token ID5804
Feature activation+3.06e+00

Pos logit contributions
�士+3.620
Moh+3.364
+3.364
Austral+3.314
lection+3.249
Neg logit contributions
channelAvailability-4.695
estinal-3.978
ufact-3.726
 emanc-3.657
 virginity-3.620
Token it
Token ID340
Feature activation+1.39e+00

Pos logit contributions
�士+1.906
+1.874
Moh+1.782
Austral+1.748
lection+1.653
Neg logit contributions
channelAvailability-2.975
estinal-2.566
ufact-2.408
 mathemat-2.387
 emanc-2.354
Token has
Token ID468
Feature activation+7.82e-01

Pos logit contributions
�士+0.956
+0.938
Moh+0.898
Austral+0.888
ouf+0.840
Neg logit contributions
channelAvailability-1.263
estinal-1.079
 emanc-0.989
ufact-0.976
 virginity-0.966
Token evidence
Token ID2370
Feature activation+1.57e+00

Pos logit contributions
�士+0.624
+0.610
Moh+0.597
Austral+0.597
ouf+0.563
Neg logit contributions
channelAvailability-0.620
estinal-0.517
 emanc-0.478
 virginity-0.460
ufact-0.454
Token all
Token ID477
Feature activation+3.30e+00

Pos logit contributions
�士+0.487
+0.474
Moh+0.463
Austral+0.462
ouf+0.433
Neg logit contributions
channelAvailability-0.613
estinal-0.522
 emanc-0.487
 virginity-0.471
ufact-0.466
Token during
Token ID1141
Feature activation+7.03e-01

Pos logit contributions
�士+2.232
+2.230
Moh+2.140
Austral+2.134
lection+2.002
Neg logit contributions
channelAvailability-2.974
estinal-2.545
 emanc-2.351
 virginity-2.293
ufact-2.279
Token these
Token ID777
Feature activation-1.15e+00

Pos logit contributions
�士+0.518
+0.504
Moh+0.494
Austral+0.494
ouf+0.463
Neg logit contributions
channelAvailability-0.601
estinal-0.508
 emanc-0.474
 virginity-0.458
ufact-0.451
Token two
Token ID734
Feature activation-8.04e-01

Pos logit contributions
channelAvailability+1.033
estinal+0.881
 emanc+0.841
 virginity+0.806
ufact+0.792
Neg logit contributions
�士-0.786
-0.760
Moh-0.742
Austral-0.741
ouf-0.697
Token ch
Token ID442
Feature activation+2.23e+00

Pos logit contributions
channelAvailability+0.717
estinal+0.611
 emanc+0.579
 virginity+0.556
ufact+0.547
Neg logit contributions
�士-0.564
-0.543
Moh-0.533
Austral-0.531
ouf-0.500
Tokenor
Token ID273
Feature activation+6.67e+00

Pos logit contributions
+0.983
�士+0.974
Austral+0.952
Moh+0.946
lection+0.862
Neg logit contributions
channelAvailability-2.534
estinal-2.219
 emanc-2.118
 virginity-2.072
 mathemat-2.051
Tokenuses
Token ID2664
Feature activation+1.28e+00

Pos logit contributions
+1.255
Austral+1.242
Moh+1.234
lection+1.169
lections+1.117
Neg logit contributions
channelAvailability-9.092
estinal-7.919
 emanc-7.798
 mathemat-7.768
 virginity-7.642
Token,
Token ID11
Feature activation+1.93e+00

Pos logit contributions
�士+0.899
+0.878
Moh+0.856
Austral+0.855
ouf+0.800
Neg logit contributions
channelAvailability-1.130
estinal-0.961
 emanc-0.896
 virginity-0.867
ufact-0.858
Token but
Token ID475
Feature activation+2.69e+00

Pos logit contributions
�士+1.342
+1.315
Moh+1.282
Austral+1.280
ouf+1.195
Neg logit contributions
channelAvailability-1.723
estinal-1.477
 emanc-1.364
 virginity-1.325
ufact-1.318
Token a
Token ID257
Feature activation+1.50e+00

Pos logit contributions
�士+1.662
+1.614
Moh+1.573
Austral+1.567
ouf+1.452
Neg logit contributions
channelAvailability-2.617
estinal-2.258
 emanc-2.108
 virginity-2.052
ufact-2.042
Token regret
Token ID13721
Feature activation+1.46e+00

Pos logit contributions
�士+1.121
+1.097
Moh+1.074
Austral+1.071
ouf+1.007
Neg logit contributions
channelAvailability-1.258
estinal-1.059
 emanc-0.977
 virginity-0.944
ufact-0.940
Token filed
Token ID5717
Feature activation-1.25e+00

Pos logit contributions
�士+0.764
+0.752
Moh+0.737
Austral+0.727
ouf+0.686
Neg logit contributions
channelAvailability-0.878
estinal-0.742
 emanc-0.681
 virginity-0.663
ufact-0.656
Token against
Token ID1028
Feature activation-1.12e+00

Pos logit contributions
channelAvailability+1.027
estinal+0.862
 emanc+0.801
 virginity+0.772
ufact+0.762
Neg logit contributions
�士-0.962
-0.934
Austral-0.915
Moh-0.914
ouf-0.862
Token Wells
Token ID18292
Feature activation+3.80e-01

Pos logit contributions
channelAvailability+0.904
estinal+0.756
 emanc+0.703
 virginity+0.677
ufact+0.668
Neg logit contributions
�士-0.875
-0.851
Austral-0.834
Moh-0.833
ouf-0.786
Token Fargo
Token ID28125
Feature activation-7.09e-01

Pos logit contributions
�士+0.225
+0.218
Moh+0.212
Austral+0.212
ouf+0.196
Neg logit contributions
channelAvailability-0.379
estinal-0.329
 emanc-0.310
 virginity-0.301
ufact-0.298
Token
Token ID960
Feature activation-1.44e-01

Pos logit contributions
channelAvailability+0.598
estinal+0.505
 emanc+0.469
 virginity+0.453
ufact+0.448
Neg logit contributions
�士-0.530
-0.516
Moh-0.505
Austral-0.505
ouf-0.474
Tokenwhich
Token ID4758
Feature activation+1.63e+00

Pos logit contributions
channelAvailability+0.136
estinal+0.116
 emanc+0.109
 virginity+0.106
ufact+0.104
Neg logit contributions
�士-0.094
-0.090
Austral-0.087
Moh-0.087
ouf-0.082
Token is
Token ID318
Feature activation+3.19e+00

Pos logit contributions
�士+1.168
+1.149
Moh+1.120
Austral+1.111
ouf+1.046
Neg logit contributions
channelAvailability-1.418
estinal-1.197
 emanc-1.103
ufact-1.070
 virginity-1.068
Token accused
Token ID5371
Feature activation+7.34e-01

Pos logit contributions
�士+2.203
+2.177
Moh+2.126
Austral+2.104
729+1.980
Neg logit contributions
channelAvailability-2.828
estinal-2.416
 emanc-2.200
 virginity-2.155
ufact-2.138
Token of
Token ID286
Feature activation+2.09e+00

Pos logit contributions
�士+0.492
+0.479
Moh+0.467
Austral+0.464
ouf+0.432
Neg logit contributions
channelAvailability-0.676
estinal-0.579
 emanc-0.541
 virginity-0.524
ufact-0.520
Token directing
Token ID21024
Feature activation-1.45e+00

Pos logit contributions
�士+1.575
+1.542
Moh+1.516
Austral+1.505
729+1.410
Neg logit contributions
channelAvailability-1.747
estinal-1.467
 emanc-1.328
 virginity-1.287
ufact-1.286
Token minority
Token ID9137
Feature activation-4.41e+00

Pos logit contributions
channelAvailability+1.249
estinal+1.059
 emanc+0.995
 virginity+0.961
ufact+0.944
Neg logit contributions
�士-1.049
-1.020
Moh-0.993
Austral-0.993
ouf-0.935
Token dialogue
Token ID10721
Feature activation+2.22e-01

Pos logit contributions
�士+1.007
+0.989
Moh+0.971
Austral+0.966
lection+0.912
Neg logit contributions
channelAvailability-1.027
estinal-0.856
 emanc-0.779
ufact-0.752
 virginity-0.751
Token ("
Token ID5855
Feature activation+2.40e-01

Pos logit contributions
�士+0.168
+0.166
Moh+0.161
Austral+0.161
ouf+0.151
Neg logit contributions
channelAvailability-0.185
estinal-0.156
 emanc-0.143
 virginity-0.138
ufact-0.138
TokenHey
Token ID10814
Feature activation+2.92e+00

Pos logit contributions
�士+0.143
+0.139
Moh+0.135
Austral+0.134
ouf+0.124
Neg logit contributions
channelAvailability-0.239
estinal-0.207
 emanc-0.195
 virginity-0.190
ufact-0.188
Token,
Token ID11
Feature activation+4.10e+00

Pos logit contributions
�士+2.046
+2.014
Moh+1.966
Austral+1.955
ouf+1.834
Neg logit contributions
channelAvailability-2.586
estinal-2.196
 emanc-2.033
ufact-1.979
 virginity-1.961
Token Ker
Token ID17337
Feature activation+1.57e+00

Pos logit contributions
�士+2.852
+2.834
Moh+2.764
Austral+2.742
ouf+2.577
Neg logit contributions
channelAvailability-3.599
estinal-3.051
 emanc-2.782
ufact-2.756
 virginity-2.685
Tokenmit
Token ID2781
Feature activation+1.93e+00

Pos logit contributions
+0.815
�士+0.807
Moh+0.791
Austral+0.786
ouf+0.729
Neg logit contributions
channelAvailability-1.659
estinal-1.451
 emanc-1.373
ufact-1.332
 virginity-1.328
Token!"
Token ID2474
Feature activation+7.30e-01

Pos logit contributions
�士+1.350
+1.325
Moh+1.291
Austral+1.286
ouf+1.205
Neg logit contributions
channelAvailability-1.720
estinal-1.465
 emanc-1.362
 virginity-1.317
ufact-1.311
Token and
Token ID290
Feature activation+5.47e-01

Pos logit contributions
�士+0.480
+0.468
Moh+0.456
Austral+0.454
ouf+0.424
Neg logit contributions
channelAvailability-0.680
estinal-0.585
 emanc-0.547
 virginity-0.530
ufact-0.526
Token "
Token ID366
Feature activation+1.94e+00

Pos logit contributions
�士+0.367
+0.357
Moh+0.348
Austral+0.347
ouf+0.324
Neg logit contributions
channelAvailability-0.504
estinal-0.432
 emanc-0.404
 virginity-0.391
ufact-0.388
TokenYeah
Token ID10995
Feature activation+1.41e+00

Pos logit contributions
�士+1.154
+1.124
Moh+1.098
Austral+1.095
ouf+1.007
Neg logit contributions
channelAvailability-1.925
estinal-1.673
 emanc-1.574
 virginity-1.528
ufact-1.518
Token!
Token ID0
Feature activation+1.87e-01

Pos logit contributions
�士+0.991
+0.968
Moh+0.944
Austral+0.942
ouf+0.881
Neg logit contributions
channelAvailability-1.254
estinal-1.068
 emanc-0.995
 virginity-0.963
ufact-0.954
Token people
Token ID661
Feature activation+3.71e-01

Pos logit contributions
channelAvailability+1.368
estinal+1.155
 emanc+1.083
 virginity+1.047
ufact+1.010
Neg logit contributions
�士-1.262
-1.227
Moh-1.196
Austral-1.191
ouf-1.124
Token don
Token ID836
Feature activation+3.36e-01

Pos logit contributions
�士+0.271
+0.266
Moh+0.260
Austral+0.260
ouf+0.244
Neg logit contributions
channelAvailability-0.318
estinal-0.268
 emanc-0.248
 virginity-0.240
ufact-0.239
Token't
Token ID470
Feature activation-1.39e+00

Pos logit contributions
�士+0.211
+0.205
Moh+0.200
Austral+0.199
ouf+0.185
Neg logit contributions
channelAvailability-0.324
estinal-0.279
 emanc-0.262
 virginity-0.255
ufact-0.252
Token know
Token ID760
Feature activation+3.09e-01

Pos logit contributions
channelAvailability+1.126
estinal+0.955
 emanc+0.898
 virginity+0.860
ufact+0.825
Neg logit contributions
�士-1.095
-1.043
Austral-1.029
Moh-1.025
ouf-0.963
Token who
Token ID508
Feature activation+6.87e-01

Pos logit contributions
�士+0.216
+0.211
Moh+0.206
Austral+0.205
ouf+0.192
Neg logit contributions
channelAvailability-0.275
estinal-0.235
 emanc-0.219
 virginity-0.212
ufact-0.210
Token the
Token ID262
Feature activation+1.86e+00

Pos logit contributions
�士+0.494
+0.483
Moh+0.474
Austral+0.472
ouf+0.443
Neg logit contributions
channelAvailability-0.596
estinal-0.506
 emanc-0.468
 virginity-0.454
ufact-0.452
Token Koch
Token ID17009
Feature activation+1.38e-01

Pos logit contributions
�士+1.477
+1.441
Moh+1.418
Austral+1.414
ouf+1.332
Neg logit contributions
channelAvailability-1.474
estinal-1.235
 emanc-1.125
ufact-1.094
 virginity-1.088
Token brothers
Token ID9397
Feature activation-4.70e-01

Pos logit contributions
�士+0.091
+0.088
Moh+0.086
Austral+0.086
ouf+0.080
Neg logit contributions
channelAvailability-0.129
estinal-0.111
 emanc-0.104
 virginity-0.100
ufact-0.099
Token are
Token ID389
Feature activation+1.07e+00

Pos logit contributions
channelAvailability+0.388
estinal+0.326
 emanc+0.303
 virginity+0.292
ufact+0.287
Neg logit contributions
�士-0.361
-0.351
Moh-0.344
Austral-0.343
ouf-0.323
Token."
Token ID526
Feature activation+3.06e-01

Pos logit contributions
�士+0.738
+0.726
Moh+0.710
Austral+0.708
ouf+0.661
Neg logit contributions
channelAvailability-0.958
estinal-0.818
 emanc-0.761
 virginity-0.740
ufact-0.733
Token
Token ID198
Feature activation+2.75e-01

Pos logit contributions
�士+0.253
+0.248
Moh+0.243
Austral+0.243
ouf+0.229
Neg logit contributions
channelAvailability-0.234
estinal-0.194
 emanc-0.178
 virginity-0.171
ufact-0.169
Token signal
Token ID6737
Feature activation-1.58e-01

Pos logit contributions
�士+1.330
+1.302
Moh+1.272
Austral+1.272
ouf+1.193
Neg logit contributions
channelAvailability-1.496
estinal-1.258
 emanc-1.168
 virginity-1.128
ufact-1.115
Token pand
Token ID19798
Feature activation+4.34e+00

Pos logit contributions
channelAvailability+0.141
estinal+0.120
 emanc+0.112
 virginity+0.108
ufact+0.107
Neg logit contributions
�士-0.111
-0.108
Moh-0.105
Austral-0.105
ouf-0.098
Tokenemic
Token ID5314
Feature activation+3.48e-01

Pos logit contributions
+1.308
�士+1.304
Moh+1.241
Austral+1.222
lection+1.051
Neg logit contributions
channelAvailability-5.531
estinal-4.907
 emanc-4.709
 virginity-4.639
ufact-4.578
Token imminent
Token ID21161
Feature activation-1.80e+00

Pos logit contributions
�士+0.263
+0.260
Moh+0.254
Austral+0.254
ouf+0.238
Neg logit contributions
channelAvailability-0.288
estinal-0.241
 emanc-0.223
 virginity-0.215
ufact-0.214
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
channelAvailability+1.500
estinal+1.279
 emanc+1.187
 virginity+1.150
ufact+1.126
Neg logit contributions
�士-1.358
-1.298
Moh-1.274
Austral-1.274
ouf-1.202
Token Phase
Token ID18983
Feature activation+1.74e+00

Pos logit contributions
channelAvailability+0.861
estinal+0.729
 emanc+0.676
 virginity+0.657
ufact+0.648
Neg logit contributions
�士-0.757
-0.731
Moh-0.715
Austral-0.714
ouf-0.675
Token 6
Token ID718
Feature activation-1.08e+00

Pos logit contributions
�士+1.044
+1.019
Moh+0.989
Austral+0.985
ouf+0.911
Neg logit contributions
channelAvailability-1.728
estinal-1.495
 emanc-1.408
 virginity-1.368
ufact-1.358
Token:
Token ID25
Feature activation-3.91e-01

Pos logit contributions
channelAvailability+0.767
estinal+0.626
 emanc+0.569
 virginity+0.545
ufact+0.538
Neg logit contributions
�士-0.957
-0.934
Moh-0.919
Austral-0.918
ouf-0.873
Token Virus
Token ID40584
Feature activation+1.36e+00

Pos logit contributions
channelAvailability+0.347
estinal+0.297
 emanc+0.276
 virginity+0.268
ufact+0.265
Neg logit contributions
�士-0.275
-0.266
Moh-0.260
Austral-0.259
ouf-0.244
Token spreads
Token ID26779
Feature activation-5.37e-01

Pos logit contributions
�士+1.030
+1.020
Austral+1.002
Moh+1.001
ouf+0.936
Neg logit contributions
channelAvailability-1.122
estinal-0.938
 emanc-0.861
 virginity-0.833
ufact-0.831
Token to
Token ID284
Feature activation-2.95e-01

Pos logit contributions
channelAvailability+0.477
estinal+0.406
 emanc+0.378
 virginity+0.366
ufact+0.363
Neg logit contributions
�士-0.375
-0.368
Moh-0.359
Austral-0.359
ouf-0.335
Token:
Token ID25
Feature activation-4.47e-01

Pos logit contributions
�士+0.338
+0.328
Moh+0.320
Austral+0.319
ouf+0.298
Neg logit contributions
channelAvailability-0.456
estinal-0.391
 emanc-0.366
 virginity-0.355
ufact-0.351
Token Cho
Token ID10031
Feature activation+1.45e+00

Pos logit contributions
channelAvailability+0.377
estinal+0.318
 emanc+0.298
 virginity+0.289
ufact+0.284
Neg logit contributions
�士-0.333
-0.322
Moh-0.316
Austral-0.316
ouf-0.297
Tokenosing
Token ID2752
Feature activation+9.68e-01

Pos logit contributions
�士+1.171
+1.149
Moh+1.134
Austral+1.129
lection+1.075
Neg logit contributions
channelAvailability-1.131
estinal-0.925
 emanc-0.854
 virginity-0.822
ufact-0.802
Token Life
Token ID5155
Feature activation+5.06e-01

Pos logit contributions
�士+0.705
+0.690
Moh+0.675
Austral+0.673
ouf+0.631
Neg logit contributions
channelAvailability-0.835
estinal-0.706
 emanc-0.656
 virginity-0.632
ufact-0.628
Token after
Token ID706
Feature activation+1.61e-01

Pos logit contributions
�士+0.358
+0.349
Moh+0.341
Austral+0.340
ouf+0.318
Neg logit contributions
channelAvailability-0.448
estinal-0.381
 emanc-0.355
 virginity-0.343
ufact-0.339
Token an
Token ID281
Feature activation+1.00e+00

Pos logit contributions
�士+0.119
+0.116
Moh+0.113
Austral+0.113
ouf+0.106
Neg logit contributions
channelAvailability-0.138
estinal-0.117
 emanc-0.108
 virginity-0.105
ufact-0.103
Token U
Token ID471
Feature activation-7.95e-02

Pos logit contributions
�士+0.695
+0.678
Moh+0.662
Austral+0.660
ouf+0.617
Neg logit contributions
channelAvailability-0.902
estinal-0.769
 emanc-0.718
 virginity-0.696
ufact-0.688
Tokennexpected
Token ID42072
Feature activation-5.28e-01

Pos logit contributions
channelAvailability+0.073
estinal+0.063
 emanc+0.058
 virginity+0.057
ufact+0.056
Neg logit contributions
�士-0.054
-0.052
Austral-0.051
Moh-0.051
ouf-0.047
Token P
Token ID350
Feature activation+2.18e+00

Pos logit contributions
channelAvailability+0.434
estinal+0.365
 emanc+0.338
 virginity+0.326
ufact+0.321
Neg logit contributions
�士-0.408
-0.396
Austral-0.389
Moh-0.388
ouf-0.366
Tokenren
Token ID918
Feature activation+2.44e+00

Pos logit contributions
�士+1.412
+1.396
Moh+1.366
Austral+1.358
lection+1.281
Neg logit contributions
channelAvailability-2.044
estinal-1.731
 emanc-1.636
 virginity-1.591
ufact-1.570
Tokenatal
Token ID10254
Feature activation+2.36e+00

Pos logit contributions
�士+1.349
+1.306
Moh+1.267
Austral+1.264
ouf+1.159
Neg logit contributions
channelAvailability-2.534
estinal-2.212
 emanc-2.088
 virginity-2.033
ufact-2.014
Token that
Token ID326
Feature activation-6.65e-01

Pos logit contributions
�士+0.634
+0.624
Moh+0.609
Austral+0.608
ouf+0.570
Neg logit contributions
channelAvailability-0.780
estinal-0.661
 emanc-0.609
 virginity-0.592
ufact-0.588
Token this
Token ID428
Feature activation-7.86e-01

Pos logit contributions
channelAvailability+0.554
estinal+0.466
 emanc+0.434
 virginity+0.419
ufact+0.413
Neg logit contributions
�士-0.505
-0.492
Moh-0.480
Austral-0.480
ouf-0.451
Token is
Token ID318
Feature activation-6.15e-01

Pos logit contributions
channelAvailability+0.666
estinal+0.563
 emanc+0.525
 virginity+0.506
ufact+0.499
Neg logit contributions
�士-0.586
-0.570
Austral-0.557
Moh-0.557
ouf-0.521
Token what
Token ID644
Feature activation+4.23e-02

Pos logit contributions
channelAvailability+0.514
estinal+0.432
 emanc+0.402
 virginity+0.388
ufact+0.383
Neg logit contributions
�士-0.466
-0.455
Moh-0.445
Austral-0.444
ouf-0.417
Token we
Token ID356
Feature activation-8.39e-01

Pos logit contributions
�士+0.032
+0.031
Moh+0.031
Austral+0.031
ouf+0.029
Neg logit contributions
channelAvailability-0.035
estinal-0.030
 emanc-0.027
 virginity-0.026
ufact-0.026
Token must
Token ID1276
Feature activation-2.95e+00

Pos logit contributions
channelAvailability+0.735
estinal+0.627
 emanc+0.590
 virginity+0.567
ufact+0.557
Neg logit contributions
�士-0.604
-0.583
Moh-0.569
Austral-0.568
ouf-0.534
Token expect
Token ID1607
Feature activation-5.31e-01

Pos logit contributions
channelAvailability+2.508
estinal+2.168
 emanc+2.079
 virginity+1.973
ufact+1.884
Neg logit contributions
�士-2.196
-2.065
Moh-2.025
Austral-2.025
ouf-1.894
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
channelAvailability+0.481
estinal+0.412
 emanc+0.386
 virginity+0.373
ufact+0.368
Neg logit contributions
�士-0.365
-0.352
Austral-0.345
Moh-0.344
ouf-0.322
Token but
Token ID475
Feature activation+6.30e-01

Pos logit contributions
channelAvailability+0.983
estinal+0.831
 emanc+0.777
 virginity+0.749
ufact+0.738
Neg logit contributions
�士-0.845
-0.822
Moh-0.803
Austral-0.802
ouf-0.753
Token such
Token ID884
Feature activation-2.28e+00

Pos logit contributions
�士+0.458
+0.450
Moh+0.441
Austral+0.440
ouf+0.412
Neg logit contributions
channelAvailability-0.541
estinal-0.458
 emanc-0.422
 virginity-0.409
ufact-0.408
Token will
Token ID481
Feature activation-1.40e+00

Pos logit contributions
channelAvailability+1.812
estinal+1.530
 emanc+1.453
 virginity+1.388
ufact+1.346
Neg logit contributions
�士-1.803
-1.747
Moh-1.697
Austral-1.695
ouf-1.601
Token
Token ID198
Feature activation-1.10e+00

Pos logit contributions
channelAvailability+1.384
estinal+1.137
 emanc+1.036
 virginity+0.989
ufact+0.967
Neg logit contributions
�士-1.680
-1.626
Austral-1.620
Moh-1.608
ouf-1.534
Token
Token ID198
Feature activation-8.55e-01

Pos logit contributions
channelAvailability+0.778
estinal+0.620
 emanc+0.568
 virginity+0.545
ufact+0.526
Neg logit contributions
�士-0.989
-0.942
Austral-0.921
Moh-0.921
ouf-0.882
TokenCrit
Token ID18559
Feature activation-3.01e-01

Pos logit contributions
channelAvailability+1.033
estinal+0.913
 emanc+0.866
 virginity+0.849
ufact+0.839
Neg logit contributions
�士-0.331
-0.303
Moh-0.287
Austral-0.287
ouf-0.261
Tokenique
Token ID2350
Feature activation-1.64e+00

Pos logit contributions
channelAvailability+0.313
estinal+0.273
 emanc+0.256
 virginity+0.250
ufact+0.247
Neg logit contributions
�士-0.172
-0.158
Austral-0.155
Moh-0.153
ouf-0.140
Token:
Token ID25
Feature activation-3.13e-01

Pos logit contributions
channelAvailability+1.135
estinal+0.904
 emanc+0.827
 virginity+0.793
ufact+0.767
Neg logit contributions
�士-1.503
-1.440
Austral-1.414
Moh-1.408
ouf-1.346
Token Three
Token ID7683
Feature activation-4.50e-01

Pos logit contributions
channelAvailability+0.264
estinal+0.222
 emanc+0.207
 virginity+0.200
ufact+0.197
Neg logit contributions
�士-0.235
-0.228
Austral-0.223
Moh-0.223
ouf-0.209
Token of
Token ID286
Feature activation-2.28e-01

Pos logit contributions
channelAvailability+0.379
estinal+0.320
 emanc+0.298
 virginity+0.288
ufact+0.283
Neg logit contributions
�士-0.336
-0.327
Austral-0.320
Moh-0.320
ouf-0.301
Token us
Token ID514
Feature activation+1.66e-02

Pos logit contributions
channelAvailability+0.189
estinal+0.159
 emanc+0.148
 virginity+0.143
ufact+0.140
Neg logit contributions
�士-0.175
-0.169
Austral-0.166
Moh-0.166
ouf-0.156
Token did
Token ID750
Feature activation-1.63e+00

Pos logit contributions
�士+0.011
+0.011
Moh+0.011
Austral+0.011
ouf+0.010
Neg logit contributions
channelAvailability-0.015
estinal-0.013
 emanc-0.012
 virginity-0.011
ufact-0.011
Token the
Token ID262
Feature activation+5.20e-01

Pos logit contributions
channelAvailability+1.373
estinal+1.163
 emanc+1.083
 virginity+1.048
ufact+1.025
Neg logit contributions
�士-1.220
-1.184
Austral-1.162
Moh-1.159
ouf-1.090
Token full
Token ID1336
Feature activation+2.16e-02

Pos logit contributions
�士+0.383
+0.374
Moh+0.366
Austral+0.365
ouf+0.343
Neg logit contributions
channelAvailability-0.444
estinal-0.375
 emanc-0.348
 virginity-0.337
ufact-0.333
Token PR
Token ID4810
Feature activation-1.35e+00

Pos logit contributions
�士+0.152
+0.148
Austral+0.145
Moh+0.145
ouf+0.136
Neg logit contributions
channelAvailability-0.173
estinal-0.145
 emanc-0.136
 virginity-0.131
ufact-0.129
Token and
Token ID290
Feature activation-2.54e+00

Pos logit contributions
channelAvailability+1.115
estinal+0.940
 emanc+0.872
 virginity+0.840
ufact+0.827
Neg logit contributions
�士-1.028
-1.002
Austral-0.984
Moh-0.979
ouf-0.925
Token supporter
Token ID15525
Feature activation+6.62e-01

Pos logit contributions
channelAvailability+2.163
estinal+1.821
 emanc+1.720
 virginity+1.662
ufact+1.626
Neg logit contributions
�士-1.840
-1.772
Austral-1.754
Moh-1.741
ouf-1.640
Token liaison
Token ID43176
Feature activation-4.62e-01

Pos logit contributions
�士+0.526
+0.514
Moh+0.504
Austral+0.503
ouf+0.474
Neg logit contributions
channelAvailability-0.527
estinal-0.440
 emanc-0.406
 virginity-0.391
ufact-0.386
Token manager
Token ID4706
Feature activation-2.00e+00

Pos logit contributions
channelAvailability+0.361
estinal+0.302
 emanc+0.279
 virginity+0.268
ufact+0.265
Neg logit contributions
�士-0.372
-0.363
Austral-0.356
Moh-0.355
ouf-0.335
Token at
Token ID379
Feature activation-8.16e-01

Pos logit contributions
channelAvailability+1.614
estinal+1.349
 emanc+1.263
 virginity+1.215
ufact+1.195
Neg logit contributions
�士-1.555
-1.504
Austral-1.486
Moh-1.472
ouf-1.387
Token Newcastle
Token ID22410
Feature activation-2.72e+00

Pos logit contributions
channelAvailability+0.700
estinal+0.593
 emanc+0.551
 virginity+0.533
ufact+0.526
Neg logit contributions
�士-0.598
-0.583
Moh-0.570
Austral-0.569
ouf-0.534
Token United
Token ID1578
Feature activation-3.55e+00

Pos logit contributions
channelAvailability+2.621
estinal+2.259
 emanc+2.140
 virginity+2.072
ufact+2.049
Neg logit contributions
�士-1.660
-1.611
Austral-1.576
Moh-1.566
ouf-1.457
Token,
Token ID11
Feature activation-1.05e+00

Pos logit contributions
channelAvailability+2.851
estinal+2.370
 emanc+2.249
 virginity+2.167
ufact+2.125
Neg logit contributions
�士-2.731
-2.635
Austral-2.581
Moh-2.570
ouf-2.441
Token said
Token ID531
Feature activation-2.93e+00

Pos logit contributions
channelAvailability+0.905
estinal+0.767
 emanc+0.725
 virginity+0.699
ufact+0.689
Neg logit contributions
�士-0.760
-0.731
Austral-0.720
Moh-0.719
ouf-0.671
Token:
Token ID25
Feature activation-3.02e+00

Pos logit contributions
channelAvailability+1.942
estinal+1.570
 emanc+1.454
 virginity+1.382
ufact+1.355
Neg logit contributions
�士-2.677
-2.604
Austral-2.563
Moh-2.547
ouf-2.427
Token tenants
Token ID21445
Feature activation-2.78e-01

Pos logit contributions
channelAvailability+0.414
estinal+0.334
 emanc+0.306
 virginity+0.291
ufact+0.286
Neg logit contributions
�士-0.548
-0.537
Austral-0.527
Moh-0.526
ouf-0.500
Token couldn
Token ID3521
Feature activation-1.94e+00

Pos logit contributions
channelAvailability+0.245
estinal+0.208
 emanc+0.194
 virginity+0.188
ufact+0.186
Neg logit contributions
�士-0.197
-0.192
Moh-0.187
Austral-0.187
ouf-0.175
Token
Token ID447
Feature activation+9.97e-01

Pos logit contributions
channelAvailability+1.744
estinal+1.452
 emanc+1.366
 virginity+1.331
ufact+1.301
Neg logit contributions
�士-1.374
-1.267
Austral-1.242
Moh-1.237
ouf-1.179
Token
Token ID247
Feature activation+9.58e-02

Pos logit contributions
�士+0.653
+0.633
Moh+0.616
Austral+0.613
ouf+0.572
Neg logit contributions
channelAvailability-0.936
estinal-0.805
 emanc-0.756
 virginity-0.731
ufact-0.725
Tokent
Token ID83
Feature activation-1.98e+00

Pos logit contributions
�士+0.062
+0.060
Moh+0.058
Austral+0.058
ouf+0.054
Neg logit contributions
channelAvailability-0.091
estinal-0.078
 emanc-0.073
 virginity-0.071
ufact-0.070
Token afford
Token ID5368
Feature activation-1.48e+00

Pos logit contributions
channelAvailability+1.859
estinal+1.611
 emanc+1.544
 virginity+1.480
ufact+1.447
Neg logit contributions
�士-1.288
-1.219
Austral-1.212
Moh-1.200
ouf-1.111
Token the
Token ID262
Feature activation-1.71e-02

Pos logit contributions
channelAvailability+1.269
estinal+1.073
 emanc+1.009
 virginity+0.971
ufact+0.962
Neg logit contributions
�士-1.087
-1.055
Austral-1.043
Moh-1.033
ouf-0.970
Token rent
Token ID5602
Feature activation+1.18e+00

Pos logit contributions
channelAvailability+0.012
estinal+0.010
 emanc+0.009
 virginity+0.009
ufact+0.009
Neg logit contributions
�士-0.015
-0.015
Moh-0.014
Austral-0.014
ouf-0.014
Token when
Token ID618
Feature activation-2.00e+00

Pos logit contributions
�士+0.836
+0.822
Moh+0.801
Austral+0.796
ouf+0.747
Neg logit contributions
channelAvailability-1.045
estinal-0.888
 emanc-0.823
 virginity-0.800
ufact-0.791
Token their
Token ID511
Feature activation-6.10e-01

Pos logit contributions
channelAvailability+1.722
estinal+1.447
 emanc+1.367
 virginity+1.306
ufact+1.295
Neg logit contributions
�士-1.464
-1.418
Austral-1.401
Moh-1.386
ouf-1.305
Token subsidy
Token ID28646
Feature activation-1.62e+00

Pos logit contributions
channelAvailability+0.423
estinal+0.342
 emanc+0.314
 virginity+0.299
ufact+0.293
Neg logit contributions
�士-0.549
-0.535
Austral-0.526
Moh-0.525
ouf-0.500
Token it
Token ID340
Feature activation-1.86e-01

Pos logit contributions
channelAvailability+1.775
estinal+1.511
 emanc+1.422
 virginity+1.373
ufact+1.350
Neg logit contributions
�士-1.398
-1.358
Austral-1.328
Moh-1.316
ouf-1.235
Token became
Token ID2627
Feature activation+1.08e+00

Pos logit contributions
channelAvailability+0.170
estinal+0.145
 emanc+0.135
 virginity+0.132
ufact+0.130
Neg logit contributions
�士-0.126
-0.123
Moh-0.120
Austral-0.120
ouf-0.111
Token "
Token ID366
Feature activation-9.67e-02

Pos logit contributions
�士+0.886
+0.871
Moh+0.856
Austral+0.852
ouf+0.807
Neg logit contributions
channelAvailability-0.826
estinal-0.689
 emanc-0.624
ufact-0.605
 virginity-0.602
Tokena
Token ID64
Feature activation+1.12e+00

Pos logit contributions
channelAvailability+0.090
estinal+0.077
 emanc+0.072
 virginity+0.070
ufact+0.069
Neg logit contributions
�士-0.064
-0.062
Moh-0.061
Austral-0.061
ouf-0.056
Token source
Token ID2723
Feature activation-2.06e+00

Pos logit contributions
�士+0.871
+0.853
Moh+0.836
Austral+0.832
ouf+0.786
Neg logit contributions
channelAvailability-0.911
estinal-0.764
 emanc-0.704
 virginity-0.677
ufact-0.674
Token of
Token ID286
Feature activation-2.50e+00

Pos logit contributions
channelAvailability+1.790
estinal+1.520
 emanc+1.415
 virginity+1.377
ufact+1.341
Neg logit contributions
�士-1.473
-1.423
Austral-1.412
Moh-1.394
ouf-1.304
Token much
Token ID881
Feature activation-4.05e-01

Pos logit contributions
channelAvailability+2.039
estinal+1.714
 emanc+1.607
 virginity+1.552
ufact+1.499
Neg logit contributions
�士-1.935
-1.872
Austral-1.838
Moh-1.831
ouf-1.726
Token amusement
Token ID30184
Feature activation-3.75e+00

Pos logit contributions
channelAvailability+0.328
estinal+0.275
 emanc+0.255
 virginity+0.246
ufact+0.241
Neg logit contributions
�士-0.317
-0.308
Moh-0.302
Austral-0.302
ouf-0.285
Token,
Token ID11
Feature activation-3.26e+00

Pos logit contributions
channelAvailability+3.175
estinal+2.704
 emanc+2.536
 virginity+2.443
ufact+2.387
Neg logit contributions
�士-2.758
-2.637
Austral-2.610
Moh-2.584
ouf-2.435
Token laughing
Token ID14376
Feature activation-5.41e+00

Pos logit contributions
channelAvailability+2.589
estinal+2.162
 emanc+2.037
 virginity+1.968
ufact+1.880
Neg logit contributions
�士-2.586
-2.513
Austral-2.454
Moh-2.442
ouf-2.332
Token and
Token ID290
Feature activation-2.97e+00

Pos logit contributions
channelAvailability+4.104
estinal+3.395
 emanc+3.215
 virginity+3.129
ufact+2.918
Neg logit contributions
�士-4.416
-4.268
Austral-4.209
Moh-4.161
ouf-3.997
Token attract
Token ID4729
Feature activation-3.64e+00

Pos logit contributions
�士+1.355
+1.339
Moh+1.307
Austral+1.303
ouf+1.219
Neg logit contributions
channelAvailability-1.776
estinal-1.510
 emanc-1.395
ufact-1.358
 virginity-1.355
Token you
Token ID345
Feature activation+3.38e-01

Pos logit contributions
channelAvailability+2.808
estinal+2.319
 emanc+2.199
 virginity+2.126
ufact+2.001
Neg logit contributions
�士-2.997
-2.892
Moh-2.814
Austral-2.809
ouf-2.663
Token?
Token ID30
Feature activation-9.35e-01

Pos logit contributions
�士+0.244
+0.238
Moh+0.232
Austral+0.232
ouf+0.217
Neg logit contributions
channelAvailability-0.294
estinal-0.250
 emanc-0.233
 virginity-0.225
ufact-0.223
Token -
Token ID532
Feature activation-2.28e+00

Pos logit contributions
channelAvailability+0.747
estinal+0.621
 emanc+0.575
 virginity+0.558
ufact+0.544
Neg logit contributions
�士-0.742
-0.719
Moh-0.704
Austral-0.703
ouf-0.666
Token January
Token ID3269
Feature activation-1.57e+00

Pos logit contributions
channelAvailability+1.773
estinal+1.464
 emanc+1.357
 virginity+1.312
ufact+1.273
Neg logit contributions
�士-1.877
-1.808
Austral-1.770
Moh-1.767
ouf-1.663
Token 15
Token ID1315
Feature activation-4.88e+00

Pos logit contributions
channelAvailability+1.450
estinal+1.237
 emanc+1.164
 virginity+1.134
ufact+1.097
Neg logit contributions
�士-1.072
-1.018
Austral-0.995
Moh-0.986
ouf-0.927
Token,
Token ID11
Feature activation-1.39e+00

Pos logit contributions
channelAvailability+3.654
estinal+2.879
 emanc+2.686
 virginity+2.610
 bondage+2.440
Neg logit contributions
�士-4.385
-3.823
Austral-3.712
Moh-3.645
ouf-3.569
Token 2010
Token ID3050
Feature activation-7.44e-01

Pos logit contributions
channelAvailability+1.577
estinal+1.373
 emanc+1.315
 virginity+1.289
ufact+1.246
Neg logit contributions
�士-0.667
-0.593
Austral-0.588
Moh-0.574
ouf-0.520
TokenQue
Token ID15681
Feature activation-1.12e+00

Pos logit contributions
channelAvailability+0.964
estinal+0.863
 emanc+0.824
 virginity+0.807
ufact+0.798
Neg logit contributions
�士-0.227
-0.206
Austral-0.192
Moh-0.192
ouf-0.161
Tokener
Token ID263
Feature activation-7.52e-01

Pos logit contributions
channelAvailability+1.041
estinal+0.902
 emanc+0.845
 virginity+0.818
ufact+0.793
Neg logit contributions
�士-0.759
-0.704
Austral-0.681
Moh-0.681
ONY-0.630
Token magnet
Token ID19972
Feature activation-4.44e+00

Pos logit contributions
channelAvailability+0.619
estinal+0.520
 emanc+0.481
 virginity+0.464
ufact+0.460
Neg logit contributions
�士-0.575
-0.564
Moh-0.552
Austral-0.551
ouf-0.518
Token2015
Token ID4626
Feature activation-1.67e-01

Pos logit contributions
�士+0.152
+0.146
Austral+0.140
Moh+0.139
ouf+0.129
Neg logit contributions
channelAvailability-0.286
estinal-0.248
 emanc-0.236
 virginity-0.229
ufact-0.225
Token
Token ID1906
Feature activation-3.39e+00

Pos logit contributions
channelAvailability+0.139
estinal+0.117
 emanc+0.109
 virginity+0.105
ufact+0.103
Neg logit contributions
�士-0.127
-0.122
Austral-0.120
Moh-0.120
ouf-0.113
Token2017
Token ID5539
Feature activation-4.41e-01

Pos logit contributions
channelAvailability+2.522
estinal+2.057
 emanc+1.905
 virginity+1.820
ufact+1.776
Neg logit contributions
�士-2.864
-2.761
Austral-2.700
Moh-2.682
ouf-2.578
Token)
Token ID8
Feature activation-1.12e+00

Pos logit contributions
channelAvailability+0.410
estinal+0.353
 emanc+0.332
 virginity+0.321
ufact+0.317
Neg logit contributions
�士-0.290
-0.280
Austral-0.275
Moh-0.273
ouf-0.253
Token [
Token ID685
Feature activation+2.07e+00

Pos logit contributions
channelAvailability+0.779
estinal+0.633
 emanc+0.580
 virginity+0.552
ufact+0.542
Neg logit contributions
�士-0.999
-0.975
Austral-0.957
Moh-0.957
ouf-0.907
Token edit
Token ID4370
Feature activation-4.84e+00

Pos logit contributions
�士+0.537
+0.536
Moh+0.522
Austral+0.511
729+0.425
Neg logit contributions
channelAvailability-2.691
estinal-2.447
 emanc-2.340
ufact-2.310
 mathemat-2.285
Token ]
Token ID2361
Feature activation-1.31e+00

Pos logit contributions
channelAvailability+2.468
estinal+1.670
 emanc+1.504
 virginity+1.435
chapter+1.253
Neg logit contributions
�士-5.367
-5.008
Austral-4.917
Moh-4.910
ouf-4.785
Token
Token ID198
Feature activation+5.68e-01

Pos logit contributions
channelAvailability+0.904
estinal+0.710
 emanc+0.648
 virginity+0.627
ufact+0.600
Neg logit contributions
�士-1.206
-1.148
Moh-1.117
Austral-1.114
ouf-1.068
Token
Token ID198
Feature activation+4.30e-01

Pos logit contributions
�士+0.487
+0.475
Moh+0.466
Austral+0.465
ouf+0.441
Neg logit contributions
channelAvailability-0.418
estinal-0.342
 emanc-0.314
 virginity-0.301
ufact-0.296
Token2015
Token ID4626
Feature activation+5.54e-01

Pos logit contributions
�士+0.271
+0.261
Moh+0.253
Austral+0.253
ouf+0.236
Neg logit contributions
channelAvailability-0.415
estinal-0.357
 emanc-0.335
 virginity-0.325
ufact-0.321
Token
Token ID1906
Feature activation-1.28e+00

Pos logit contributions
�士+0.414
+0.406
Moh+0.396
Austral+0.395
ouf+0.372
Neg logit contributions
channelAvailability-0.468
estinal-0.393
 emanc-0.364
 virginity-0.353
ufact-0.349
Token
Token ID447
Feature activation+5.23e-01

Pos logit contributions
�士+0.574
+0.560
Moh+0.546
Austral+0.545
ouf+0.510
Neg logit contributions
channelAvailability-0.719
estinal-0.612
 emanc-0.571
 virginity-0.552
ufact-0.546
Token
Token ID251
Feature activation+6.26e-01

Pos logit contributions
�士+0.339
+0.329
Moh+0.319
Austral+0.318
ouf+0.296
Neg logit contributions
channelAvailability-0.494
estinal-0.426
 emanc-0.400
 virginity-0.387
ufact-0.384
Token
Token ID198
Feature activation+1.42e-01

Pos logit contributions
�士+0.521
+0.511
Moh+0.501
Austral+0.500
ouf+0.473
Neg logit contributions
channelAvailability-0.474
estinal-0.392
 emanc-0.360
 virginity-0.346
ufact-0.341
Token
Token ID198
Feature activation-3.42e-01

Pos logit contributions
�士+0.125
+0.120
Austral+0.118
Moh+0.118
ouf+0.112
Neg logit contributions
channelAvailability-0.103
estinal-0.083
 emanc-0.076
 virginity-0.073
ufact-0.071
TokenThe
Token ID464
Feature activation+2.65e-01

Pos logit contributions
channelAvailability+0.337
estinal+0.291
 emanc+0.273
 virginity+0.266
ufact+0.262
Neg logit contributions
�士-0.209
-0.201
Austral-0.194
Moh-0.194
ouf-0.180
Token delayed
Token ID11038
Feature activation-4.85e+00

Pos logit contributions
�士+0.192
+0.188
Moh+0.183
Austral+0.183
ouf+0.172
Neg logit contributions
channelAvailability-0.229
estinal-0.194
 emanc-0.180
 virginity-0.174
ufact-0.173
Token Cy
Token ID5934
Feature activation+1.54e+00

Pos logit contributions
channelAvailability+3.879
estinal+3.262
 emanc+3.101
 virginity+3.041
ufact+2.911
Neg logit contributions
�士-3.753
-3.564
Moh-3.513
Austral-3.496
ouf-3.307
Tokengn
Token ID4593
Feature activation+6.52e-01

Pos logit contributions
�士+0.924
+0.907
Moh+0.887
Austral+0.884
ouf+0.818
Neg logit contributions
channelAvailability-1.512
estinal-1.311
 emanc-1.233
 virginity-1.198
ufact-1.190
Tokenus
Token ID385
Feature activation-3.81e-01

Pos logit contributions
+0.422
�士+0.422
Moh+0.412
Austral+0.411
ouf+0.385
Neg logit contributions
channelAvailability-0.605
estinal-0.520
 emanc-0.488
 virginity-0.471
ufact-0.470
Token mission
Token ID4365
Feature activation-2.33e+00

Pos logit contributions
channelAvailability+0.316
estinal+0.266
 emanc+0.247
 virginity+0.239
ufact+0.235
Neg logit contributions
�士-0.291
-0.283
Moh-0.277
Austral-0.277
ouf-0.260
Token comes
Token ID2058
Feature activation-7.35e-01

Pos logit contributions
channelAvailability+1.878
estinal+1.573
 emanc+1.471
 virginity+1.419
ufact+1.396
Neg logit contributions
�士-1.840
-1.761
Austral-1.735
Moh-1.732
ouf-1.640
Token per
Token ID583
Feature activation-7.83e-01

Pos logit contributions
�士+0.069
+0.068
Moh+0.066
Austral+0.066
ouf+0.062
Neg logit contributions
channelAvailability-0.084
estinal-0.071
 emanc-0.066
 virginity-0.064
ufact-0.063
Token cent
Token ID1247
Feature activation-1.21e+00

Pos logit contributions
channelAvailability+0.680
estinal+0.579
 emanc+0.540
 virginity+0.523
ufact+0.515
Neg logit contributions
�士-0.563
-0.545
Moh-0.537
Austral-0.535
ouf-0.501
Token,
Token ID11
Feature activation-8.69e-01

Pos logit contributions
channelAvailability+1.041
estinal+0.884
 emanc+0.829
 virginity+0.805
ufact+0.783
Neg logit contributions
�士-0.874
-0.837
Moh-0.830
Austral-0.822
ouf-0.772
Token chances
Token ID8395
Feature activation-3.60e+00

Pos logit contributions
channelAvailability+0.707
estinal+0.592
 emanc+0.551
 virginity+0.532
ufact+0.521
Neg logit contributions
�士-0.676
-0.655
Moh-0.645
Austral-0.642
ouf-0.606
Token are
Token ID389
Feature activation-4.58e+00

Pos logit contributions
channelAvailability+2.832
estinal+2.367
 emanc+2.181
 virginity+2.113
ufact+2.028
Neg logit contributions
�士-2.878
-2.769
Moh-2.743
Austral-2.727
ouf-2.603
Token pretty
Token ID2495
Feature activation-4.67e+00

Pos logit contributions
channelAvailability+3.462
estinal+2.895
 emanc+2.689
 virginity+2.629
ufact+2.477
Neg logit contributions
�士-3.743
-3.590
Moh-3.588
Austral-3.541
ouf-3.373
Token good
Token ID922
Feature activation-1.67e+00

Pos logit contributions
channelAvailability+3.214
estinal+2.686
 emanc+2.473
 virginity+2.374
ufact+2.204
Neg logit contributions
�士-4.086
-3.932
Moh-3.908
Austral-3.898
ouf-3.772
Token that
Token ID326
Feature activation-1.81e+00

Pos logit contributions
channelAvailability+1.363
estinal+1.144
 emanc+1.063
 virginity+1.030
ufact+1.006
Neg logit contributions
�士-1.288
-1.248
Moh-1.228
Austral-1.221
ouf-1.154
Token you
Token ID345
Feature activation-1.13e+00

Pos logit contributions
channelAvailability+1.415
estinal+1.182
 emanc+1.099
 virginity+1.062
ufact+1.029
Neg logit contributions
�士-1.455
-1.404
Moh-1.386
Austral-1.380
ouf-1.308
Token found
Token ID1043
Feature activation-1.39e+00

Pos logit contributions
channelAvailability+1.000
estinal+0.852
 emanc+0.797
 virginity+0.771
ufact+0.761
Neg logit contributions
�士-0.792
-0.764
Moh-0.751
Austral-0.748
ouf-0.701
Token yourself
Token ID3511
Feature activation+1.50e+00

Pos logit contributions
channelAvailability+1.145
estinal+0.962
 emanc+0.897
 virginity+0.866
ufact+0.847
Neg logit contributions
�士-1.066
-1.035
Moh-1.015
Austral-1.012
ouf-0.954
Token dummy
Token ID31548
Feature activation+2.04e+00

Pos logit contributions
�士+1.866
+1.825
Moh+1.778
Austral+1.768
ouf+1.664
Neg logit contributions
channelAvailability-2.335
estinal-1.979
 emanc-1.813
ufact-1.765
 virginity-1.747
Token will
Token ID481
Feature activation-1.18e+00

Pos logit contributions
�士+1.549
+1.532
Moh+1.490
Austral+1.485
lection+1.401
Neg logit contributions
channelAvailability-1.685
estinal-1.410
 emanc-1.277
ufact-1.238
 virginity-1.231
Token go
Token ID467
Feature activation-1.17e-02

Pos logit contributions
channelAvailability+1.004
estinal+0.853
 emanc+0.802
 virginity+0.772
ufact+0.754
Neg logit contributions
�士-0.876
-0.848
Moh-0.831
Austral-0.829
ouf-0.780
Token a
Token ID257
Feature activation-3.35e+00

Pos logit contributions
channelAvailability+0.011
estinal+0.009
 emanc+0.009
 virginity+0.008
ufact+0.008
Neg logit contributions
�士-0.008
-0.008
Moh-0.008
Austral-0.008
ouf-0.007
Token long
Token ID890
Feature activation-8.44e-01

Pos logit contributions
channelAvailability+2.605
estinal+2.166
 emanc+2.020
 virginity+1.942
ufact+1.901
Neg logit contributions
�士-2.720
-2.641
Austral-2.596
Moh-2.580
ouf-2.460
Token way
Token ID835
Feature activation-4.90e+00

Pos logit contributions
channelAvailability+0.536
estinal+0.422
 emanc+0.375
 virginity+0.358
ufact+0.355
Neg logit contributions
�士-0.807
-0.792
Moh-0.782
Austral-0.778
lection-0.741
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
channelAvailability+4.244
estinal+3.600
 emanc+3.460
 virginity+3.309
ufact+3.215
Neg logit contributions
�士-3.560
-3.331
Austral-3.303
Moh-3.299
ouf-3.140
Token We
Token ID775
Feature activation-2.31e-01

Pos logit contributions
channelAvailability+0.121
estinal+0.102
 emanc+0.094
 virginity+0.091
ufact+0.090
Neg logit contributions
�士-0.115
-0.112
Moh-0.110
Austral-0.110
ouf-0.104
Token can
Token ID460
Feature activation+7.18e-01

Pos logit contributions
channelAvailability+0.203
estinal+0.172
 emanc+0.161
 virginity+0.156
ufact+0.153
Neg logit contributions
�士-0.165
-0.161
Moh-0.157
Austral-0.157
ouf-0.147
Token only
Token ID691
Feature activation+8.94e-01

Pos logit contributions
�士+0.499
+0.488
Moh+0.476
Austral+0.475
ouf+0.444
Neg logit contributions
channelAvailability-0.644
estinal-0.548
 emanc-0.510
 virginity-0.494
ufact-0.490
Token hope
Token ID2911
Feature activation-1.85e+00

Pos logit contributions
�士+0.688
+0.680
Moh+0.663
Austral+0.661
ouf+0.624
Neg logit contributions
channelAvailability-0.732
estinal-0.609
 emanc-0.561
 virginity-0.542
ufact-0.540