TOP ACTIVATIONS
MAX = 22.025

v 2 # construct the argument parse and parse the arguments
parse the arguments ap = arg parse . Arg ument Parser
44 412 59 70 ; th om asc ook . com
n umpy as np import arg parse import im utils import
44 800 8 014 ; th om asc ook sign ature
x . x . x . 139 10 64 659 x
http :// www . ch ucky e ager . org
A spokesman said : " Th ur rock Council is following
- February 9 , 2010 R ipe for M ST 3
Michael Matthews ( R ab ob ank Cycling Team ) s
the Sh river Award , please download the Sh river Award
R upp e Award , please download the R upp e
= v ars ( ap . parse _ args ()) #
ue ld ner , B . A ., Ross , S
f unt p ère , cr é ateur origin el du
/ F raction ( b , c , d ) C
still exists . Ch ick ens also have communications
an auction in the US now understood to be topping $
= c v 2 . im read ( image Path )
71 231 4 691 ; th om son . co .

MIN ACTIVATIONS
MIN = -17.854

music box , involving the entire palm opl ant ar surfaces
/ init or / s bin / init , or you
. They pepp ered Bob ro vs ky with 19 shots
of God from above the seven heavens . 6
= ( m D ensity + ambient D ensity ) *
the atmosphere , where incoming and outgoing flux es are identical
dir ' option to " c :\ tmp ". Only a
on Facebook Share this comment on Twitter NY T
group at week 4 vs the sham ta V NS group
: 45 ) to take full control of the game .
been retail ing gossip . D vor ak and Brah ms
Advertisement Continue reading the main story Some teenagers
") is an autos omal dominant ker at oder ma of
head , and must roll to avoid following the commands in
to a cl ojure . l ibraries table .
on Facebook Share this comment on Twitter NY T
Advertisement Continue reading the main story
Advertisement Continue reading the main story When it
can be used across a wide range of temperatures . But
ic ), which carries a maximum penalty of 10 years imprisonment

INTERVAL 12.055 - 22.025
CONTAINS 0.071%

American economy and a Supreme Court remotely sympathetic to organized labor
( it -> vec () -> z () == 0 .
My ers , D . ( 2007 ). Psychology :
rely on stored body fat for fuel . You will always
. The high court had also directed Gh ai

INTERVAL 2.086 - 12.055
CONTAINS 24.935%

Bo a Vista , Cape Ver de , from £ 9
visitors ' locker room with the Chicago Blackhawks .
He iko Ma as , an " attack on our democracy
at a time . The Chiefs play Ping - P ong
a perceptual shift and B AM ! What you were seeking

INTERVAL -7.884 - 2.086
CONTAINS 73.972%

why , in an era of political lies and Brexit bias
t leave you rolling your eyes , as they still feel
address . Please re - enter . You must select a
people live there . Many rely entirely on rain or imported
in minutes . From M iley Cyrus phot ob omb ing

INTERVAL -17.854 - -7.884
CONTAINS 1.021%

. However , gender non con forming ( G NC )
in Buenos Aires in May 2010 . His pen
report investigating Protective Edge , the commission of inquiry treated the
Stephan opol ous will be in Boston on Tuesday morning for
as here , to ( 1 g ) 1
Tokenv
Token ID85
Feature activation+6.26e+00

Pos logit contributions
jad+4.750
estial+4.358
cious+4.220
cape+4.197
orem+4.185
Neg logit contributions
 Psychiat-6.412
 Amend-5.803
yne-5.619
ANK-5.410
nee-5.250
Token2
Token ID17
Feature activation+4.51e+00

Pos logit contributions
 Psychiat+3.952
yne+3.477
nee+3.366
ight+3.234
ANK+3.171
Neg logit contributions
jad-5.415
estial-5.377
 missionary-5.055
cious-5.025
orem-4.951
Token #
Token ID1303
Feature activation+1.05e+01

Pos logit contributions
 Psychiat+2.161
yne+1.753
 Amend+1.645
ight+1.571
nee+1.559
Neg logit contributions
jad-4.717
estial-4.688
 Unloaded-4.470
cious-4.443
orem-4.370
Token construct
Token ID5678
Feature activation+4.21e+00

Pos logit contributions
 Psychiat+7.434
 Amend+6.571
yne+6.547
ANK+6.256
ight+6.222
Neg logit contributions
jad-7.861
estial-7.822
cious-7.423
 Unloaded-7.295
cape-6.974
Token the
Token ID262
Feature activation+1.68e+00

Pos logit contributions
 Psychiat+2.887
yne+2.559
 Amend+2.435
nee+2.386
ight+2.352
Neg logit contributions
jad-3.573
estial-3.472
cious-3.266
orem-3.250
 Unloaded-3.247
Token argument
Token ID4578
Feature activation+2.20e+01

Pos logit contributions
 Psychiat+1.465
yne+1.315
 Amend+1.276
nee+1.253
ANK+1.231
Neg logit contributions
jad-1.139
estial-1.095
cious-1.027
 Unloaded-1.024
orem-1.012
Token parse
Token ID21136
Feature activation+9.17e+00

Pos logit contributions
 Psychiat+7.647
yne+6.134
 Amend+6.129
parse+5.849
nee+5.419
Neg logit contributions
jad-21.130
estial-21.067
cious-19.778
 Unloaded-19.223
 missionary-18.522
Token and
Token ID290
Feature activation+1.30e+01

Pos logit contributions
 Psychiat+5.283
yne+4.711
nee+4.405
 Amend+4.252
ight+4.215
Neg logit contributions
jad-8.316
estial-8.316
orem-7.627
cious-7.565
 missionary-7.460
Token parse
Token ID21136
Feature activation+5.43e+00

Pos logit contributions
 Psychiat+4.367
yne+3.600
 Amend+3.166
nee+2.993
ight+2.690
Neg logit contributions
jad-14.653
estial-14.468
cious-13.968
 Unloaded-13.688
orem-13.278
Token the
Token ID262
Feature activation-6.62e-01

Pos logit contributions
 Psychiat+3.507
yne+3.148
 Amend+2.925
nee+2.911
ight+2.865
Neg logit contributions
jad-4.738
estial-4.638
orem-4.346
cious-4.314
 Unloaded-4.278
Token arguments
Token ID7159
Feature activation+9.72e+00

Pos logit contributions
jad+0.485
estial+0.460
 Unloaded+0.440
orem+0.435
cious+0.434
Neg logit contributions
 Psychiat-0.548
yne-0.488
 Amend-0.469
nee-0.460
ANK-0.447
Token parse
Token ID21136
Feature activation+5.43e+00

Pos logit contributions
 Psychiat+4.367
yne+3.600
 Amend+3.166
nee+2.993
ight+2.690
Neg logit contributions
jad-14.653
estial-14.468
cious-13.968
 Unloaded-13.688
orem-13.278
Token the
Token ID262
Feature activation-6.62e-01

Pos logit contributions
 Psychiat+3.507
yne+3.148
 Amend+2.925
nee+2.911
ight+2.865
Neg logit contributions
jad-4.738
estial-4.638
orem-4.346
cious-4.314
 Unloaded-4.278
Token arguments
Token ID7159
Feature activation+9.72e+00

Pos logit contributions
jad+0.485
estial+0.460
 Unloaded+0.440
orem+0.435
cious+0.434
Neg logit contributions
 Psychiat-0.548
yne-0.488
 Amend-0.469
nee-0.460
ANK-0.447
Token ap
Token ID2471
Feature activation+2.28e+00

Pos logit contributions
 Psychiat+5.366
yne+4.609
 Amend+4.536
nee+4.190
ANK+4.178
Neg logit contributions
jad-8.959
estial-8.864
cious-8.493
 Unloaded-8.374
orem-8.086
Token =
Token ID796
Feature activation+1.84e+00

Pos logit contributions
 Psychiat+1.567
yne+1.367
 Amend+1.287
nee+1.284
ight+1.243
Neg logit contributions
jad-1.954
estial-1.902
cious-1.797
 Unloaded-1.789
orem-1.780
Token arg
Token ID1822
Feature activation+2.01e+01

Pos logit contributions
 Psychiat+1.486
yne+1.325
 Amend+1.277
nee+1.246
ANK+1.219
Neg logit contributions
jad-1.370
estial-1.322
cious-1.245
 Unloaded-1.240
orem-1.230
Tokenparse
Token ID29572
Feature activation+4.60e+00

Pos logit contributions
yne+4.647
parse+4.598
 Psychiat+4.185
nee+3.717
anche+3.094
Neg logit contributions
jad-21.973
estial-21.588
 missionary-21.318
 oun-20.447
 Unloaded-20.358
Token.
Token ID13
Feature activation+4.52e+00

Pos logit contributions
 Psychiat+3.050
yne+2.651
nee+2.510
 Amend+2.494
ANK+2.422
Neg logit contributions
jad-4.022
estial-3.966
orem-3.713
cious-3.699
 Unloaded-3.648
TokenArg
Token ID28100
Feature activation+2.49e+00

Pos logit contributions
 Psychiat+2.304
yne+1.869
 Amend+1.823
nee+1.768
ANK+1.765
Neg logit contributions
jad-4.631
estial-4.564
cious-4.387
orem-4.334
 missionary-4.319
Tokenument
Token ID1713
Feature activation+1.51e+01

Pos logit contributions
 Psychiat+1.840
yne+1.635
 Amend+1.553
nee+1.550
ight+1.509
Neg logit contributions
jad-1.995
estial-1.911
 Unloaded-1.828
cious-1.819
orem-1.798
TokenParser
Token ID46677
Feature activation+4.76e+00

Pos logit contributions
 Psychiat+4.052
yne+3.128
nee+2.866
ANK+2.468
 Amend+2.135
Neg logit contributions
jad-17.643
estial-17.294
cious-16.613
 missionary-16.576
jriwal-16.344
Token44
Token ID2598
Feature activation+4.75e+00

Pos logit contributions
jad+3.406
estial+3.246
 Unloaded+3.096
cious+3.077
orem+3.071
Neg logit contributions
 Psychiat-3.345
yne-2.963
 Amend-2.841
nee-2.778
ANK-2.698
Token 412
Token ID42215
Feature activation-4.24e+00

Pos logit contributions
 Psychiat+3.459
yne+3.037
 Amend+2.904
nee+2.835
ight+2.747
Neg logit contributions
jad-3.855
estial-3.746
orem-3.541
 Unloaded-3.519
cious-3.502
Token 59
Token ID7863
Feature activation-9.57e-01

Pos logit contributions
jad+3.091
estial+2.914
 Unloaded+2.826
cious+2.764
orem+2.761
Neg logit contributions
 Psychiat-3.446
yne-3.096
 Amend-2.950
nee-2.895
ANK-2.829
Token70
Token ID2154
Feature activation+1.14e+00

Pos logit contributions
jad+0.807
estial+0.774
 Unloaded+0.742
cious+0.736
orem+0.735
Neg logit contributions
 Psychiat-0.683
yne-0.599
 Amend-0.571
nee-0.557
ANK-0.541
Token;
Token ID26
Feature activation+2.04e+00

Pos logit contributions
 Psychiat+0.850
yne+0.757
 Amend+0.720
nee+0.705
ight+0.686
Neg logit contributions
jad-0.920
estial-0.889
 Unloaded-0.848
cious-0.843
orem-0.842
Token th
Token ID294
Feature activation+2.00e+01

Pos logit contributions
 Psychiat+1.521
yne+1.355
 Amend+1.292
nee+1.262
ight+1.235
Neg logit contributions
jad-1.620
estial-1.558
 Unloaded-1.498
cious-1.476
orem-1.470
Tokenom
Token ID296
Feature activation+5.54e+00

Pos logit contributions
 Psychiat+12.485
yne+12.236
ight+11.999
icol+11.790
inks+11.755
Neg logit contributions
 Unloaded-11.883
 missionary-11.835
jad-11.770
estial-11.214
 Starg-10.894
Tokenasc
Token ID3372
Feature activation+5.78e+00

Pos logit contributions
 Psychiat+5.090
yne+4.717
ight+4.564
anche+4.549
nee+4.517
Neg logit contributions
jad-3.153
estial-2.990
 Unloaded-2.888
 missionary-2.869
cious-2.743
Tokenook
Token ID566
Feature activation+4.62e-01

Pos logit contributions
 Psychiat+3.668
yne+3.287
nee+3.180
ight+3.053
anche+2.996
Neg logit contributions
jad-5.043
estial-4.956
 Unloaded-4.680
 missionary-4.663
orem-4.591
Token.
Token ID13
Feature activation+4.15e+00

Pos logit contributions
 Psychiat+0.405
yne+0.366
 Amend+0.351
nee+0.349
ight+0.342
Neg logit contributions
jad-0.307
estial-0.295
 Unloaded-0.281
orem-0.274
cious-0.273
Tokencom
Token ID785
Feature activation+8.90e-01

Pos logit contributions
 Psychiat+3.562
yne+3.270
nee+3.096
 Amend+3.048
ight+3.021
Neg logit contributions
jad-2.732
estial-2.641
 Unloaded-2.528
 missionary-2.451
orem-2.447
Token n
Token ID299
Feature activation-1.39e+00

Pos logit contributions
jad+3.032
estial+2.846
 Unloaded+2.712
orem+2.710
cious+2.692
Neg logit contributions
 Psychiat-4.230
yne-3.802
 Amend-3.689
nee-3.593
ANK-3.567
Tokenumpy
Token ID32152
Feature activation+6.76e+00

Pos logit contributions
jad+0.976
estial+0.921
 Unloaded+0.878
orem+0.873
cious+0.870
Neg logit contributions
 Psychiat-1.194
yne-1.062
 Amend-1.050
nee-1.007
ANK-0.991
Token as
Token ID355
Feature activation-1.39e+00

Pos logit contributions
 Psychiat+3.536
yne+3.150
nee+2.891
ANK+2.802
anche+2.741
Neg logit contributions
jad-6.546
estial-6.488
orem-6.094
cious-6.082
 missionary-6.000
Token np
Token ID45941
Feature activation+8.76e-01

Pos logit contributions
jad+1.202
estial+1.153
 Unloaded+1.114
orem+1.103
cious+1.101
Neg logit contributions
 Psychiat-0.949
yne-0.823
 Amend-0.796
nee-0.768
ANK-0.752
Token import
Token ID1330
Feature activation-4.34e+00

Pos logit contributions
 Psychiat+0.656
yne+0.574
 Amend+0.550
nee+0.540
ANK+0.525
Neg logit contributions
jad-0.704
estial-0.688
 Unloaded-0.643
cious-0.643
orem-0.640
Token arg
Token ID1822
Feature activation+1.92e+01

Pos logit contributions
jad+2.911
estial+2.711
 Unloaded+2.624
orem+2.592
cious+2.566
Neg logit contributions
 Psychiat-3.839
yne-3.428
 Amend-3.300
nee-3.243
ANK-3.145
Tokenparse
Token ID29572
Feature activation+8.57e+00

Pos logit contributions
yne+4.046
parse+3.765
 Psychiat+3.639
nee+3.394
anche+2.673
Neg logit contributions
jad-21.868
estial-21.318
 missionary-20.874
 Unloaded-20.074
cious-19.962
Token import
Token ID1330
Feature activation-3.25e+00

Pos logit contributions
 Psychiat+5.235
yne+4.448
nee+4.302
 Amend+4.242
ight+4.124
Neg logit contributions
estial-7.644
jad-7.398
cious-7.004
orem-6.967
 Unloaded-6.830
Token im
Token ID545
Feature activation+5.66e+00

Pos logit contributions
jad+2.351
estial+2.200
 Unloaded+2.135
orem+2.112
cious+2.102
Neg logit contributions
 Psychiat-2.682
yne-2.427
 Amend-2.307
nee-2.257
ANK-2.223
Tokenutils
Token ID26791
Feature activation+4.83e+00

Pos logit contributions
 Psychiat+5.285
yne+4.913
nee+4.735
ight+4.610
anche+4.602
Neg logit contributions
jad-3.270
estial-3.154
 missionary-2.898
 Unloaded-2.896
orem-2.892
Token import
Token ID1330
Feature activation-1.45e+00

Pos logit contributions
 Psychiat+3.336
yne+2.839
 Amend+2.760
nee+2.691
ight+2.656
Neg logit contributions
jad-4.067
estial-4.045
cious-3.756
orem-3.746
 Unloaded-3.713
Token44
Token ID2598
Feature activation+5.70e+00

Pos logit contributions
jad+2.641
estial+2.520
 Unloaded+2.421
cious+2.391
orem+2.388
Neg logit contributions
 Psychiat-2.422
yne-2.144
 Amend-2.050
nee-1.986
ANK-1.934
Token 800
Token ID10460
Feature activation-5.14e+00

Pos logit contributions
 Psychiat+3.932
yne+3.418
 Amend+3.241
nee+3.173
ANK+3.088
Neg logit contributions
jad-4.838
estial-4.681
cious-4.414
orem-4.411
 Unloaded-4.401
Token 8
Token ID807
Feature activation-5.43e-01

Pos logit contributions
jad+3.800
estial+3.585
 Unloaded+3.485
orem+3.398
cious+3.379
Neg logit contributions
 Psychiat-4.090
yne-3.682
 Amend-3.505
nee-3.434
anche-3.375
Token014
Token ID28645
Feature activation+3.95e+00

Pos logit contributions
jad+0.455
estial+0.437
 Unloaded+0.418
cious+0.415
orem+0.415
Neg logit contributions
 Psychiat-0.391
yne-0.343
 Amend-0.328
nee-0.320
ANK-0.311
Token;
Token ID26
Feature activation+1.71e+00

Pos logit contributions
 Psychiat+2.907
yne+2.582
 Amend+2.470
nee+2.403
ight+2.362
Neg logit contributions
jad-3.149
estial-3.079
cious-2.905
 Unloaded-2.902
orem-2.882
Token th
Token ID294
Feature activation+1.91e+01

Pos logit contributions
 Psychiat+1.317
yne+1.177
 Amend+1.123
nee+1.102
ight+1.077
Neg logit contributions
jad-1.320
estial-1.269
 Unloaded-1.216
cious-1.196
orem-1.190
Tokenom
Token ID296
Feature activation+9.28e+00

Pos logit contributions
 Psychiat+13.516
yne+13.160
ight+13.096
inks+12.715
icol+12.543
Neg logit contributions
jad-10.359
 missionary-10.155
 Unloaded-10.102
estial-9.850
 Starg-9.426
Tokenasc
Token ID3372
Feature activation+6.35e+00

Pos logit contributions
 Psychiat+7.134
yne+6.560
ight+6.434
nee+6.372
anche+6.290
Neg logit contributions
jad-6.228
estial-6.004
 Unloaded-5.849
 missionary-5.826
orem-5.554
Tokenook
Token ID566
Feature activation+1.32e+00

Pos logit contributions
 Psychiat+4.425
yne+4.045
nee+3.830
ight+3.809
anche+3.693
Neg logit contributions
jad-5.033
estial-4.885
 Unloaded-4.770
 missionary-4.705
cious-4.526
Tokensign
Token ID12683
Feature activation+5.44e-01

Pos logit contributions
 Psychiat+1.011
yne+0.900
nee+0.857
 Amend+0.855
ight+0.842
Neg logit contributions
jad-1.012
estial-0.979
 Unloaded-0.941
orem-0.914
 missionary-0.911
Tokenature
Token ID1300
Feature activation+3.13e+00

Pos logit contributions
 Psychiat+0.543
yne+0.495
 Amend+0.479
nee+0.472
ight+0.464
Neg logit contributions
jad-0.304
estial-0.286
 Unloaded-0.268
cious-0.263
orem-0.261
Token x
Token ID2124
Feature activation+1.08e+00

Pos logit contributions
 Psychiat+3.528
yne+2.600
 Amend+2.500
nee+2.439
ight+2.243
Neg logit contributions
estial-10.342
jad-10.219
cious-9.783
orem-9.642
 Unloaded-9.547
Token.
Token ID13
Feature activation+8.05e+00

Pos logit contributions
 Psychiat+0.793
yne+0.699
 Amend+0.666
nee+0.654
ANK+0.635
Neg logit contributions
jad-0.887
estial-0.854
 Unloaded-0.813
cious-0.808
orem-0.807
Tokenx
Token ID87
Feature activation+3.97e+00

Pos logit contributions
 Psychiat+3.463
yne+3.093
nee+2.870
ight+2.694
 Amend+2.504
Neg logit contributions
estial-8.416
jad-8.358
 missionary-8.039
 Unloaded-7.956
orem-7.897
Token.
Token ID13
Feature activation+1.27e+01

Pos logit contributions
 Psychiat+2.692
yne+2.368
nee+2.230
 Amend+2.214
ight+2.153
Neg logit contributions
jad-3.419
estial-3.355
orem-3.152
 Unloaded-3.147
cious-3.134
Tokenx
Token ID87
Feature activation+1.23e+01

Pos logit contributions
 Psychiat+4.300
yne+4.006
nee+3.869
ight+3.575
 Amend+2.928
Neg logit contributions
estial-13.475
jad-13.137
 missionary-13.097
 oun-12.963
jriwal-12.701
Token.
Token ID13
Feature activation+1.85e+01

Pos logit contributions
 Psychiat+6.172
yne+5.324
nee+5.231
ight+5.001
ANK+4.828
Neg logit contributions
estial-11.421
jad-11.144
 missionary-10.780
regor-10.760
 oun-10.693
Token139
Token ID20219
Feature activation+2.97e+00

Pos logit contributions
 Psychiat+7.657
nee+6.636
yne+6.142
ight+5.860
ANK+5.847
Neg logit contributions
estial-16.701
regor-16.446
jad-15.960
orem-15.846
 missionary-15.805
Token 10
Token ID838
Feature activation-4.65e+00

Pos logit contributions
 Psychiat+2.249
yne+1.953
 Amend+1.905
nee+1.837
ight+1.782
Neg logit contributions
jad-2.400
estial-2.326
cious-2.181
 Unloaded-2.169
orem-2.168
Token64
Token ID2414
Feature activation-1.54e+00

Pos logit contributions
jad+3.636
estial+3.460
 Unloaded+3.358
cious+3.274
orem+3.258
Neg logit contributions
 Psychiat-3.497
yne-3.143
 Amend-2.995
nee-2.859
anche-2.828
Token659
Token ID36445
Feature activation+9.42e+00

Pos logit contributions
jad+1.332
estial+1.279
 Unloaded+1.227
cious+1.218
orem+1.216
Neg logit contributions
 Psychiat-1.067
yne-0.931
 Amend-0.887
nee-0.864
ANK-0.838
Token x
Token ID2124
Feature activation+5.15e-01

Pos logit contributions
 Psychiat+3.610
yne+2.714
 Amend+2.572
nee+2.511
ight+2.271
Neg logit contributions
estial-10.620
jad-10.481
cious-10.050
orem-9.907
 Unloaded-9.795
Token
Token ID251
Feature activation-3.20e+00

Pos logit contributions
 Psychiat+1.309
yne+1.171
 Amend+1.121
nee+1.091
ANK+1.071
Neg logit contributions
jad-1.260
estial-1.208
 Unloaded-1.152
orem-1.133
cious-1.133
Token http
Token ID2638
Feature activation+1.26e+00

Pos logit contributions
jad+2.462
estial+2.356
 Unloaded+2.250
orem+2.230
cious+2.227
Neg logit contributions
 Psychiat-2.499
yne-2.221
 Amend-2.134
nee-2.081
ANK-2.027
Token://
Token ID1378
Feature activation-2.61e+00

Pos logit contributions
 Psychiat+1.106
yne+0.996
 Amend+0.958
nee+0.945
ANK+0.924
Neg logit contributions
jad-0.857
estial-0.821
 Unloaded-0.770
orem-0.769
cious-0.766
Tokenwww
Token ID2503
Feature activation-4.02e+00

Pos logit contributions
jad+1.758
estial+1.661
 Unloaded+1.570
cious+1.561
orem+1.552
Neg logit contributions
 Psychiat-2.312
yne-2.072
 Amend-2.013
nee-1.955
ANK-1.918
Token.
Token ID13
Feature activation+1.24e+00

Pos logit contributions
jad+2.932
estial+2.700
 Unloaded+2.664
cious+2.610
orem+2.568
Neg logit contributions
 Psychiat-3.306
yne-2.939
 Amend-2.872
anche-2.728
nee-2.706
Tokench
Token ID354
Feature activation+1.84e+01

Pos logit contributions
 Psychiat+0.866
yne+0.765
 Amend+0.717
nee+0.714
ight+0.690
Neg logit contributions
jad-1.053
estial-1.016
 Unloaded-0.977
orem-0.969
cious-0.965
Tokenucky
Token ID5309
Feature activation-4.70e-01

Pos logit contributions
yne+10.636
 Psychiat+10.462
ank+9.943
nee+9.855
alky+9.678
Neg logit contributions
 missionary-13.188
jad-13.045
 Unloaded-12.678
estial-12.452
cious-12.050
Tokene
Token ID68
Feature activation-1.23e+00

Pos logit contributions
jad+0.377
estial+0.361
 Unloaded+0.346
cious+0.342
orem+0.342
Neg logit contributions
 Psychiat-0.353
yne-0.315
 Amend-0.298
nee-0.294
ight-0.285
Tokenager
Token ID3536
Feature activation-1.89e-01

Pos logit contributions
jad+0.926
estial+0.885
 Unloaded+0.842
cious+0.835
orem+0.834
Neg logit contributions
 Psychiat-0.989
yne-0.881
 Amend-0.845
nee-0.828
ANK-0.807
Token.
Token ID13
Feature activation-4.03e+00

Pos logit contributions
jad+0.154
estial+0.148
 Unloaded+0.142
cious+0.140
orem+0.140
Neg logit contributions
 Psychiat-0.140
yne-0.124
 Amend-0.117
nee-0.116
ANK-0.112
Tokenorg
Token ID2398
Feature activation-4.80e+00

Pos logit contributions
jad+2.395
estial+2.240
 Unloaded+2.103
cious+2.095
orem+2.076
Neg logit contributions
 Psychiat-3.886
yne-3.493
 Amend-3.429
nee-3.303
ANK-3.279
TokenA
Token ID32
Feature activation-2.21e+00

Pos logit contributions
 Psychiat+2.689
yne+2.385
ANK+2.256
nee+2.248
 Amend+2.220
Neg logit contributions
jad-3.058
estial-2.950
 Unloaded-2.836
orem-2.831
 missionary-2.796
Token spokesman
Token ID6523
Feature activation+2.83e-01

Pos logit contributions
jad+1.674
estial+1.599
 Unloaded+1.522
cious+1.510
orem+1.507
Neg logit contributions
 Psychiat-1.769
yne-1.573
 Amend-1.511
nee-1.479
ANK-1.442
Token said
Token ID531
Feature activation+3.35e+00

Pos logit contributions
 Psychiat+0.195
yne+0.171
 Amend+0.161
nee+0.156
ight+0.154
Neg logit contributions
jad-0.245
estial-0.237
 Unloaded-0.227
cious-0.225
orem-0.225
Token:
Token ID25
Feature activation+2.90e+00

Pos logit contributions
 Psychiat+2.441
yne+2.165
 Amend+2.090
ight+1.982
nee+1.942
Neg logit contributions
jad-2.767
estial-2.641
 Unloaded-2.533
orem-2.525
cious-2.485
Token "
Token ID366
Feature activation+3.22e+00

Pos logit contributions
 Psychiat+2.037
yne+1.766
 Amend+1.691
nee+1.658
ight+1.595
Neg logit contributions
jad-2.486
estial-2.411
orem-2.280
cious-2.275
 Unloaded-2.266
TokenTh
Token ID817
Feature activation+1.79e+01

Pos logit contributions
 Psychiat+2.339
yne+2.052
 Amend+1.968
nee+1.934
ANK+1.915
Neg logit contributions
jad-2.657
estial-2.551
orem-2.455
 Unloaded-2.439
cious-2.399
Tokenur
Token ID333
Feature activation+1.18e+01

Pos logit contributions
yne+8.254
 Psychiat+7.799
ight+7.304
nee+6.624
rone+6.557
Neg logit contributions
jad-15.804
 Unloaded-15.661
estial-14.945
 missionary-14.914
cape-14.527
Tokenrock
Token ID10823
Feature activation-4.77e+00

Pos logit contributions
 Psychiat+3.723
yne+3.274
nee+2.952
ight+2.704
ank+2.644
Neg logit contributions
jad-13.106
estial-12.986
 missionary-12.616
orem-12.466
 Unloaded-12.409
Token Council
Token ID4281
Feature activation-8.77e-01

Pos logit contributions
jad+3.342
estial+3.182
 Unloaded+3.056
cious+3.018
orem+2.989
Neg logit contributions
 Psychiat-3.984
yne-3.546
 Amend-3.410
nee-3.373
ANK-3.306
Token is
Token ID318
Feature activation+6.08e+00

Pos logit contributions
jad+0.686
estial+0.656
 Unloaded+0.624
cious+0.619
orem+0.618
Neg logit contributions
 Psychiat-0.683
yne-0.605
 Amend-0.581
nee-0.566
ANK-0.551
Token following
Token ID1708
Feature activation+9.88e+00

Pos logit contributions
 Psychiat+4.099
yne+3.625
 Amend+3.490
nee+3.350
ight+3.233
Neg logit contributions
jad-5.191
estial-5.015
orem-4.820
 Unloaded-4.771
cious-4.645
Token -
Token ID532
Feature activation+6.21e-01

Pos logit contributions
jad+0.057
estial+0.055
 Unloaded+0.052
cious+0.051
orem+0.051
Neg logit contributions
 Psychiat-0.055
yne-0.048
 Amend-0.046
nee-0.045
ANK-0.044
Token February
Token ID3945
Feature activation-1.90e+00

Pos logit contributions
 Psychiat+0.383
yne+0.328
 Amend+0.314
nee+0.304
ANK+0.294
Neg logit contributions
jad-0.582
estial-0.564
 Unloaded-0.540
cious-0.538
orem-0.536
Token 9
Token ID860
Feature activation-6.57e-01

Pos logit contributions
jad+1.241
estial+1.142
 Unloaded+1.109
cious+1.084
orem+1.074
Neg logit contributions
 Psychiat-1.698
yne-1.556
 Amend-1.496
nee-1.461
ANK-1.431
Token,
Token ID11
Feature activation+7.12e+00

Pos logit contributions
jad+0.527
estial+0.500
 Unloaded+0.482
cious+0.477
orem+0.474
Neg logit contributions
 Psychiat-0.497
yne-0.437
 Amend-0.421
nee-0.407
ANK-0.395
Token 2010
Token ID3050
Feature activation-4.16e+00

Pos logit contributions
 Psychiat+4.401
yne+3.800
 Amend+3.498
nee+3.474
ANK+3.411
Neg logit contributions
estial-6.561
jad-6.539
orem-6.103
cious-6.059
 Unloaded-5.957
TokenR
Token ID49
Feature activation+1.75e+01

Pos logit contributions
jad+3.542
estial+3.315
 Unloaded+3.246
cious+3.224
orem+3.209
Neg logit contributions
 Psychiat-2.870
yne-2.499
 Amend-2.442
anche-2.261
nee-2.253
Tokenipe
Token ID3757
Feature activation+4.23e+00

Pos logit contributions
yne+5.311
ight+5.260
nee+5.196
 Psychiat+5.077
anche+4.681
Neg logit contributions
 missionary-17.648
estial-17.600
 Unloaded-17.341
jad-17.282
cious-16.537
Token for
Token ID329
Feature activation-2.00e+00

Pos logit contributions
 Psychiat+2.884
yne+2.519
 Amend+2.376
nee+2.328
ight+2.297
Neg logit contributions
jad-3.605
estial-3.554
 Unloaded-3.391
orem-3.384
cious-3.337
Token M
Token ID337
Feature activation-8.28e+00

Pos logit contributions
jad+1.555
estial+1.483
 Unloaded+1.422
cious+1.409
orem+1.404
Neg logit contributions
 Psychiat-1.545
yne-1.374
 Amend-1.314
nee-1.288
ANK-1.250
TokenST
Token ID2257
Feature activation-2.79e+00

Pos logit contributions
jad+3.742
estial+3.405
 Unloaded+3.271
cious+3.119
cape+3.058
Neg logit contributions
 Psychiat-8.835
yne-8.063
 Amend-8.029
nee-7.551
agons-7.392
Token3
Token ID18
Feature activation-8.09e+00

Pos logit contributions
jad+2.053
estial+1.918
 Unloaded+1.860
cious+1.825
orem+1.820
Neg logit contributions
 Psychiat-2.305
yne-2.032
 Amend-1.983
nee-1.898
anche-1.843
Token Michael
Token ID3899
Feature activation-2.67e+00

Pos logit contributions
jad+4.105
estial+3.887
 Unloaded+3.756
cious+3.728
orem+3.699
Neg logit contributions
 Psychiat-3.814
yne-3.379
 Amend-3.164
nee-3.159
anche-3.082
Token Matthews
Token ID22233
Feature activation-3.57e+00

Pos logit contributions
jad+2.009
estial+1.911
orem+1.825
 Unloaded+1.820
cious+1.801
Neg logit contributions
 Psychiat-2.121
yne-1.885
 Amend-1.818
nee-1.775
ANK-1.749
Token (
Token ID357
Feature activation-2.58e+00

Pos logit contributions
jad+2.681
estial+2.513
 Unloaded+2.421
cious+2.388
orem+2.383
Neg logit contributions
 Psychiat-2.872
yne-2.509
 Amend-2.428
nee-2.408
ANK-2.346
TokenR
Token ID49
Feature activation+7.54e-01

Pos logit contributions
jad+2.148
estial+2.051
 Unloaded+1.977
cious+1.960
orem+1.938
Neg logit contributions
 Psychiat-1.860
yne-1.620
 Amend-1.549
nee-1.492
anche-1.466
Tokenab
Token ID397
Feature activation+4.71e+00

Pos logit contributions
 Psychiat+0.534
yne+0.478
 Amend+0.449
nee+0.443
ANK+0.434
Neg logit contributions
jad-0.633
estial-0.605
 Unloaded-0.588
cious-0.581
orem-0.576
Tokenob
Token ID672
Feature activation+1.75e+01

Pos logit contributions
 Psychiat+2.541
yne+2.193
nee+2.011
 Amend+1.938
ight+1.912
Neg logit contributions
jad-4.670
estial-4.588
 Unloaded-4.366
cious-4.358
orem-4.342
Tokenank
Token ID962
Feature activation+8.32e+00

Pos logit contributions
ank+3.768
ANK+3.145
 Psychiat+2.965
yne+2.807
nee+2.397
Neg logit contributions
estial-20.957
jad-20.617
orem-20.048
 missionary-19.689
cious-19.251
Token Cycling
Token ID25550
Feature activation-7.41e-01

Pos logit contributions
 Psychiat+5.539
yne+4.922
 Amend+4.709
nee+4.486
ight+4.394
Neg logit contributions
jad-6.998
estial-6.865
orem-6.555
cious-6.437
 Unloaded-6.282
Token Team
Token ID4816
Feature activation+1.22e-01

Pos logit contributions
jad+0.561
estial+0.531
 Unloaded+0.512
cious+0.504
orem+0.503
Neg logit contributions
 Psychiat-0.591
yne-0.526
 Amend-0.504
nee-0.494
ANK-0.482
Token)
Token ID8
Feature activation-1.13e+01

Pos logit contributions
 Psychiat+0.090
yne+0.079
 Amend+0.076
nee+0.074
ANK+0.072
Neg logit contributions
jad-0.100
estial-0.095
 Unloaded-0.092
cious-0.091
orem-0.091
Token s
Token ID264
Feature activation-7.64e-01

Pos logit contributions
jad+5.234
estial+4.937
 Unloaded+4.655
cious+4.502
orem+4.424
Neg logit contributions
 Psychiat-11.204
yne-10.111
nee-9.952
anche-9.764
ANK-9.654
Token the
Token ID262
Feature activation-4.81e-02

Pos logit contributions
 Psychiat+1.382
yne+1.221
 Amend+1.166
nee+1.130
ight+1.107
Neg logit contributions
jad-1.531
estial-1.470
 Unloaded-1.404
orem-1.387
cious-1.385
Token Sh
Token ID911
Feature activation+4.04e+00

Pos logit contributions
jad+0.036
estial+0.034
 Unloaded+0.032
cious+0.032
orem+0.032
Neg logit contributions
 Psychiat-0.039
yne-0.035
 Amend-0.034
nee-0.033
ight-0.032
Tokenriver
Token ID38291
Feature activation-9.39e-01

Pos logit contributions
 Psychiat+2.119
yne+1.846
nee+1.749
ight+1.666
 Amend+1.632
Neg logit contributions
jad-3.990
estial-3.952
 Unloaded-3.781
cious-3.749
 missionary-3.717
Token Award
Token ID11289
Feature activation+1.43e+00

Pos logit contributions
jad+0.903
estial+0.872
 Unloaded+0.839
cious+0.833
orem+0.832
Neg logit contributions
 Psychiat-0.561
yne-0.477
 Amend-0.451
nee-0.437
ANK-0.421
Token,
Token ID11
Feature activation+3.56e+00

Pos logit contributions
 Psychiat+0.989
yne+0.863
 Amend+0.824
nee+0.800
ANK+0.781
Neg logit contributions
jad-1.229
estial-1.182
 Unloaded-1.132
cious-1.121
orem-1.117
Token please
Token ID3387
Feature activation+1.74e+01

Pos logit contributions
 Psychiat+2.713
yne+2.417
 Amend+2.349
nee+2.267
ANK+2.234
Neg logit contributions
jad-2.766
estial-2.687
cious-2.518
 Unloaded-2.503
orem-2.502
Token download
Token ID4321
Feature activation+6.62e+00

Pos logit contributions
 Psychiat+7.084
yne+6.524
 Amend+6.011
nee+5.993
ANK+5.569
Neg logit contributions
estial-15.943
jad-15.486
cious-15.002
 Unloaded-14.939
orem-14.441
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
 Psychiat+4.325
yne+3.913
 Amend+3.657
nee+3.485
ight+3.461
Neg logit contributions
jad-5.661
estial-5.495
orem-5.230
 Unloaded-5.208
cious-5.173
Token Sh
Token ID911
Feature activation+2.94e+00

Pos logit contributions
jad+0.751
estial+0.715
 Unloaded+0.676
cious+0.672
orem+0.670
Neg logit contributions
 Psychiat-0.882
yne-0.789
 Amend-0.761
nee-0.743
ANK-0.726
Tokenriver
Token ID38291
Feature activation-5.89e-01

Pos logit contributions
 Psychiat+1.603
yne+1.390
nee+1.303
 Amend+1.249
ight+1.241
Neg logit contributions
jad-2.881
estial-2.824
 Unloaded-2.713
cious-2.686
 missionary-2.663
Token Award
Token ID11289
Feature activation-5.65e-01

Pos logit contributions
jad+0.573
estial+0.554
 Unloaded+0.532
cious+0.530
orem+0.529
Neg logit contributions
 Psychiat-0.345
yne-0.292
 Amend-0.276
nee-0.267
ANK-0.257
Token R
Token ID371
Feature activation+1.17e+00

Pos logit contributions
 Psychiat+4.649
yne+3.965
 Amend+3.725
nee+3.650
ight+3.486
Neg logit contributions
jad-8.121
estial-8.014
 Unloaded-7.696
cious-7.610
cape-7.449
Tokenupp
Token ID7211
Feature activation+4.16e+00

Pos logit contributions
 Psychiat+0.905
yne+0.808
 Amend+0.764
nee+0.762
ANK+0.739
Neg logit contributions
jad-0.906
estial-0.871
 Unloaded-0.829
cious-0.824
orem-0.817
Tokene
Token ID68
Feature activation+3.65e+00

Pos logit contributions
 Psychiat+3.007
yne+2.750
nee+2.615
 Amend+2.538
ight+2.505
Neg logit contributions
jad-3.364
estial-3.249
 Unloaded-3.096
cious-3.050
orem-3.023
Token Award
Token ID11289
Feature activation+4.87e+00

Pos logit contributions
 Psychiat+1.974
yne+1.645
 Amend+1.559
nee+1.517
ANK+1.452
Neg logit contributions
jad-3.656
estial-3.575
 Unloaded-3.425
cious-3.413
orem-3.368
Token,
Token ID11
Feature activation+4.25e+00

Pos logit contributions
 Psychiat+3.137
yne+2.754
 Amend+2.618
nee+2.576
ANK+2.493
Neg logit contributions
jad-4.288
estial-4.152
 Unloaded-3.975
cious-3.943
orem-3.892
Token please
Token ID3387
Feature activation+1.74e+01

Pos logit contributions
 Psychiat+3.187
yne+2.850
 Amend+2.769
nee+2.675
ANK+2.637
Neg logit contributions
jad-3.325
estial-3.233
cious-3.028
 Unloaded-3.012
orem-3.008
Token download
Token ID4321
Feature activation+9.73e+00

Pos logit contributions
 Psychiat+7.140
yne+6.621
 Amend+6.070
nee+6.042
ANK+5.596
Neg logit contributions
estial-15.754
jad-15.496
 Unloaded-14.950
cious-14.942
orem-14.374
Token the
Token ID262
Feature activation+6.97e+00

Pos logit contributions
 Psychiat+5.856
yne+5.380
 Amend+4.992
nee+4.738
ight+4.712
Neg logit contributions
jad-8.461
estial-8.148
cious-7.773
 Unloaded-7.738
orem-7.717
Token R
Token ID371
Feature activation+1.82e+00

Pos logit contributions
 Psychiat+4.225
yne+3.660
 Amend+3.509
nee+3.370
ight+3.245
Neg logit contributions
jad-6.365
estial-6.146
cious-5.916
 Unloaded-5.806
orem-5.721
Tokenupp
Token ID7211
Feature activation+4.05e+00

Pos logit contributions
 Psychiat+1.397
yne+1.251
nee+1.182
 Amend+1.177
ight+1.144
Neg logit contributions
jad-1.428
estial-1.373
 Unloaded-1.307
cious-1.300
orem-1.289
Tokene
Token ID68
Feature activation+1.33e+00

Pos logit contributions
 Psychiat+2.938
yne+2.686
nee+2.550
 Amend+2.493
ight+2.464
Neg logit contributions
jad-3.252
estial-3.136
 Unloaded-2.988
cious-2.944
orem-2.926
Token =
Token ID796
Feature activation-2.24e+00

Pos logit contributions
 Psychiat+2.808
yne+2.445
nee+2.301
 Amend+2.238
ight+2.233
Neg logit contributions
jad-3.863
estial-3.795
cious-3.562
 missionary-3.548
orem-3.530
Token v
Token ID410
Feature activation+1.10e+00

Pos logit contributions
jad+1.588
estial+1.507
 Unloaded+1.447
orem+1.426
cious+1.417
Neg logit contributions
 Psychiat-1.884
yne-1.686
 Amend-1.625
nee-1.599
ANK-1.569
Tokenars
Token ID945
Feature activation+4.69e+00

Pos logit contributions
 Psychiat+1.119
yne+1.025
 Amend+0.986
nee+0.976
ANK+0.957
Neg logit contributions
jad-0.593
estial-0.558
 Unloaded-0.518
cious-0.512
orem-0.511
Token(
Token ID7
Feature activation+4.85e+00

Pos logit contributions
 Psychiat+2.924
yne+2.535
nee+2.370
 Amend+2.326
ANK+2.277
Neg logit contributions
jad-4.295
estial-4.211
orem-3.996
cious-3.960
 Unloaded-3.948
Tokenap
Token ID499
Feature activation+1.74e+00

Pos logit contributions
 Psychiat+2.851
yne+2.531
nee+2.375
 Amend+2.299
anche+2.286
Neg logit contributions
jad-4.443
estial-4.409
 Unloaded-4.211
cious-4.183
 missionary-4.172
Token.
Token ID13
Feature activation+1.74e+01

Pos logit contributions
 Psychiat+1.254
yne+1.102
 Amend+1.044
nee+1.036
ANK+1.003
Neg logit contributions
jad-1.448
estial-1.399
 Unloaded-1.324
orem-1.321
cious-1.320
Tokenparse
Token ID29572
Feature activation+8.43e+00

Pos logit contributions
 Psychiat+3.124
parse+3.122
yne+2.985
nee+2.653
ight+1.807
Neg logit contributions
estial-20.358
jad-19.946
 missionary-19.941
 Unloaded-19.360
cious-18.669
Token_
Token ID62
Feature activation-2.60e+00

Pos logit contributions
 Psychiat+4.563
yne+4.002
nee+3.925
ANK+3.685
 Amend+3.541
Neg logit contributions
estial-7.943
jad-7.892
 missionary-7.469
orem-7.446
cious-7.434
Tokenargs
Token ID22046
Feature activation+6.36e+00

Pos logit contributions
jad+1.376
estial+1.252
 Unloaded+1.180
orem+1.166
cious+1.165
Neg logit contributions
 Psychiat-2.708
yne-2.444
 Amend-2.407
nee-2.325
ANK-2.281
Token())
Token ID28955
Feature activation+1.37e+00

Pos logit contributions
 Psychiat+3.610
yne+3.185
nee+3.058
ight+2.817
 Amend+2.810
Neg logit contributions
jad-5.974
estial-5.850
orem-5.611
 missionary-5.566
cious-5.534
Token #
Token ID1303
Feature activation+1.17e+01

Pos logit contributions
 Psychiat+0.590
yne+0.473
 Amend+0.433
nee+0.406
ight+0.394
Neg logit contributions
jad-1.536
estial-1.501
 Unloaded-1.443
cious-1.437
orem-1.423
Tokenue
Token ID518
Feature activation-2.15e+00

Pos logit contributions
jad+4.130
estial+3.924
orem+3.759
cious+3.715
 Unloaded+3.705
Neg logit contributions
 Psychiat-3.596
yne-3.098
 Amend-2.990
nee-2.859
ANK-2.839
Tokenld
Token ID335
Feature activation-2.76e-02

Pos logit contributions
jad+1.715
estial+1.635
 Unloaded+1.553
cious+1.552
orem+1.546
Neg logit contributions
 Psychiat-1.635
yne-1.434
 Amend-1.381
nee-1.339
ANK-1.321
Tokenner
Token ID1008
Feature activation+7.75e+00

Pos logit contributions
jad+0.022
estial+0.021
 Unloaded+0.020
cious+0.020
orem+0.020
Neg logit contributions
 Psychiat-0.021
yne-0.019
 Amend-0.018
nee-0.018
ight-0.017
Token,
Token ID11
Feature activation+1.01e+01

Pos logit contributions
 Psychiat+4.644
yne+4.137
nee+3.905
 Amend+3.818
ight+3.718
Neg logit contributions
estial-6.844
jad-6.799
 Unloaded-6.565
cious-6.497
 missionary-6.396
Token B
Token ID347
Feature activation+9.23e+00

Pos logit contributions
 Psychiat+5.898
 Amend+4.880
yne+4.841
nee+4.692
 Lob+4.418
Neg logit contributions
estial-9.290
jad-9.178
jriwal-8.733
orem-8.679
cious-8.598
Token.
Token ID13
Feature activation+1.73e+01

Pos logit contributions
 Psychiat+5.449
yne+4.831
nee+4.596
ight+4.447
 Amend+4.380
Neg logit contributions
jad-8.018
estial-7.881
 Unloaded-7.739
cape-7.583
cious-7.539
Token A
Token ID317
Feature activation+6.14e+00

Pos logit contributions
 Psychiat+8.782
 Amend+6.771
nee+6.598
yne+6.478
 Lob+6.382
Neg logit contributions
estial-15.909
jriwal-15.731
jad-15.250
wcs-14.802
orem-14.710
Token.,
Token ID1539
Feature activation-3.24e+00

Pos logit contributions
 Psychiat+3.852
yne+3.366
nee+3.122
 Amend+3.082
ight+3.039
Neg logit contributions
jad-5.437
estial-5.278
 Unloaded-5.124
cious-5.026
orem-5.000
Token Ross
Token ID9847
Feature activation-5.48e-01

Pos logit contributions
jad+2.624
estial+2.498
 Unloaded+2.401
cious+2.381
orem+2.375
Neg logit contributions
 Psychiat-2.407
yne-2.131
 Amend-2.015
nee-1.982
ANK-1.944
Token,
Token ID11
Feature activation+8.65e+00

Pos logit contributions
jad+0.447
estial+0.430
 Unloaded+0.412
cious+0.406
orem+0.405
Neg logit contributions
 Psychiat-0.406
yne-0.359
 Amend-0.342
nee-0.336
ight-0.326
Token S
Token ID311
Feature activation+6.35e+00

Pos logit contributions
 Psychiat+5.255
yne+4.344
 Amend+4.342
nee+4.195
 Lob+3.916
Neg logit contributions
estial-7.891
jad-7.867
orem-7.385
jriwal-7.362
cious-7.326
Tokenf
Token ID69
Feature activation+5.48e+00

Pos logit contributions
 Psychiat+6.942
yne+6.292
nee+6.096
 Amend+5.789
ight+5.783
Neg logit contributions
jad-6.380
 Unloaded-6.335
estial-6.248
 missionary-6.081
orem-5.907
Tokenunt
Token ID2797
Feature activation+5.34e+00

Pos logit contributions
 Psychiat+4.399
yne+4.021
nee+3.779
ight+3.766
anche+3.740
Neg logit contributions
jad-3.931
estial-3.762
 Unloaded-3.689
 missionary-3.598
cious-3.503
Token p
Token ID279
Feature activation+2.42e+00

Pos logit contributions
 Psychiat+3.853
yne+3.410
 Amend+3.239
nee+3.203
ight+3.083
Neg logit contributions
jad-4.335
estial-4.157
 Unloaded-4.033
cious-3.958
orem-3.813
Tokenère
Token ID35979
Feature activation+6.40e+00

Pos logit contributions
 Psychiat+2.012
yne+1.824
nee+1.723
 Amend+1.706
anche+1.690
Neg logit contributions
jad-1.714
estial-1.658
 Unloaded-1.589
cious-1.549
 missionary-1.534
Token,
Token ID11
Feature activation+5.37e+00

Pos logit contributions
 Psychiat+4.819
yne+4.218
nee+4.074
 Amend+4.041
ANK+3.821
Neg logit contributions
jad-4.891
estial-4.746
 Unloaded-4.568
cious-4.471
orem-4.418
Token cr
Token ID1067
Feature activation+1.70e+01

Pos logit contributions
 Psychiat+4.098
yne+3.569
nee+3.452
 Amend+3.424
ANK+3.256
Neg logit contributions
jad-4.140
estial-4.012
 Unloaded-3.847
cious-3.742
orem-3.727
Tokené
Token ID2634
Feature activation+5.53e+00

Pos logit contributions
 Psychiat+9.059
anche+8.919
yne+8.333
ight+8.193
nee+7.912
Neg logit contributions
jad-13.488
 Unloaded-12.917
 missionary-12.734
estial-12.509
wcs-11.998
Tokenateur
Token ID15093
Feature activation+1.04e+01

Pos logit contributions
 Psychiat+4.202
yne+3.743
nee+3.588
 Amend+3.477
ight+3.434
Neg logit contributions
jad-4.226
estial-3.964
 Unloaded-3.953
orem-3.760
cious-3.754
Token origin
Token ID8159
Feature activation+7.22e-01

Pos logit contributions
 Psychiat+7.618
yne+6.579
nee+6.407
 Amend+6.334
ight+6.006
Neg logit contributions
jad-7.727
estial-7.532
 Unloaded-7.394
cious-6.988
orem-6.894
Tokenel
Token ID417
Feature activation+3.45e+00

Pos logit contributions
 Psychiat+0.514
yne+0.452
 Amend+0.428
nee+0.422
ANK+0.407
Neg logit contributions
jad-0.610
estial-0.587
 Unloaded-0.563
cious-0.557
orem-0.554
Token du
Token ID7043
Feature activation+2.45e+00

Pos logit contributions
 Psychiat+2.536
yne+2.216
 Amend+2.123
nee+2.092
ight+2.017
Neg logit contributions
jad-2.824
estial-2.682
 Unloaded-2.622
cious-2.558
orem-2.525
Token/
Token ID14
Feature activation+7.16e-01

Pos logit contributions
jad+0.001
estial+0.001
 Unloaded+0.001
orem+0.001
cious+0.001
Neg logit contributions
 Psychiat-0.001
yne-0.001
 Amend-0.001
nee-0.001
ANK-0.001
TokenF
Token ID37
Feature activation+2.70e+00

Pos logit contributions
 Psychiat+0.570
yne+0.507
 Amend+0.485
nee+0.477
ANK+0.466
Neg logit contributions
jad-0.547
estial-0.521
 Unloaded-0.498
cious-0.491
orem-0.490
Tokenraction
Token ID7861
Feature activation-2.91e-01

Pos logit contributions
 Psychiat+2.086
yne+1.876
 Amend+1.760
nee+1.734
ANK+1.706
Neg logit contributions
jad-2.103
estial-1.990
 Unloaded-1.944
orem-1.895
cious-1.886
Token (
Token ID357
Feature activation+1.72e+00

Pos logit contributions
jad+0.232
estial+0.221
 Unloaded+0.211
cious+0.210
orem+0.209
Neg logit contributions
 Psychiat-0.221
yne-0.196
 Amend-0.188
nee-0.183
ANK-0.178
Tokenb
Token ID65
Feature activation+4.37e+00

Pos logit contributions
 Psychiat+1.290
yne+1.147
 Amend+1.093
nee+1.086
ANK+1.056
Neg logit contributions
jad-1.375
estial-1.322
 Unloaded-1.264
cious-1.249
orem-1.245
Token,
Token ID11
Feature activation+1.69e+01

Pos logit contributions
 Psychiat+2.851
yne+2.495
 Amend+2.392
nee+2.342
ANK+2.286
Neg logit contributions
jad-3.840
estial-3.697
 Unloaded-3.555
cious-3.512
orem-3.487
Tokenc
Token ID66
Feature activation-1.81e+00

Pos logit contributions
 Psychiat+8.780
yne+8.054
nee+7.717
 Amend+7.173
anche+7.166
Neg logit contributions
jad-14.051
estial-13.624
 Unloaded-12.644
cious-12.590
orem-12.467
Token,
Token ID11
Feature activation+2.87e+00

Pos logit contributions
jad+1.494
estial+1.433
 Unloaded+1.371
cious+1.361
orem+1.358
Neg logit contributions
 Psychiat-1.319
yne-1.160
 Amend-1.108
nee-1.082
ANK-1.051
Tokend
Token ID67
Feature activation+7.20e-01

Pos logit contributions
 Psychiat+1.898
yne+1.675
 Amend+1.564
nee+1.554
ight+1.498
Neg logit contributions
jad-2.508
estial-2.438
 Unloaded-2.336
cious-2.298
orem-2.296
Token)
Token ID8
Feature activation-1.35e+00

Pos logit contributions
 Psychiat+0.505
yne+0.445
 Amend+0.426
nee+0.415
ANK+0.403
Neg logit contributions
jad-0.612
estial-0.588
 Unloaded-0.564
cious-0.559
orem-0.557
Token C
Token ID327
Feature activation-6.51e+00

Pos logit contributions
jad+1.084
estial+1.037
 Unloaded+0.991
cious+0.983
orem+0.981
Neg logit contributions
 Psychiat-1.014
yne-0.895
 Amend-0.857
nee-0.837
ANK-0.814
Token still
Token ID991
Feature activation-2.98e+00

Pos logit contributions
jad+3.268
estial+3.104
 Unloaded+2.996
orem+2.946
cious+2.928
Neg logit contributions
 Psychiat-3.459
yne-3.080
 Amend-2.963
nee-2.861
ANK-2.817
Token exists
Token ID7160
Feature activation-1.62e+00

Pos logit contributions
jad+2.256
estial+2.157
 Unloaded+2.056
orem+2.032
cious+2.030
Neg logit contributions
 Psychiat-2.371
yne-2.118
 Amend-2.026
nee-1.967
ANK-1.935
Token.
Token ID13
Feature activation+3.51e+00

Pos logit contributions
jad+1.296
estial+1.239
 Unloaded+1.185
cious+1.175
orem+1.173
Neg logit contributions
 Psychiat-1.226
yne-1.083
 Amend-1.037
nee-1.012
ANK-0.985
Token
Token ID198
Feature activation-6.61e-01

Pos logit contributions
 Psychiat+2.652
yne+2.239
 Amend+2.221
nee+2.129
ANK+2.077
Neg logit contributions
jad-2.843
estial-2.777
cious-2.603
orem-2.575
 Unloaded-2.540
Token
Token ID198
Feature activation+4.96e+00

Pos logit contributions
jad+0.515
estial+0.488
 Unloaded+0.471
cious+0.465
orem+0.463
Neg logit contributions
 Psychiat-0.514
yne-0.456
 Amend-0.438
nee-0.424
ANK-0.415
TokenCh
Token ID1925
Feature activation+1.67e+01

Pos logit contributions
 Psychiat+3.744
yne+3.307
nee+3.187
ANK+3.181
 Amend+3.110
Neg logit contributions
jad-3.820
estial-3.736
 Unloaded-3.524
 missionary-3.504
orem-3.481
Tokenick
Token ID624
Feature activation+4.57e+00

Pos logit contributions
yne+4.665
 Psychiat+4.428
inks+4.068
ight+3.978
agons+3.822
Neg logit contributions
 missionary-17.213
jad-17.058
estial-17.056
 Unloaded-17.029
cious-16.465
Tokenens
Token ID641
Feature activation-1.69e+00

Pos logit contributions
 Psychiat+3.903
yne+3.508
 Amend+3.372
nee+3.321
ight+3.243
Neg logit contributions
jad-3.124
estial-3.002
orem-2.843
 Unloaded-2.833
cious-2.789
Token also
Token ID635
Feature activation-2.64e+00

Pos logit contributions
jad+1.313
estial+1.250
 Unloaded+1.197
cious+1.187
orem+1.185
Neg logit contributions
 Psychiat-1.318
yne-1.173
 Amend-1.123
nee-1.098
ANK-1.071
Token have
Token ID423
Feature activation-1.52e+00

Pos logit contributions
jad+2.014
estial+1.911
 Unloaded+1.831
cious+1.817
orem+1.812
Neg logit contributions
 Psychiat-2.078
yne-1.859
 Amend-1.780
nee-1.727
ANK-1.698
Token communications
Token ID8062
Feature activation+1.13e+00

Pos logit contributions
jad+1.201
estial+1.149
 Unloaded+1.097
cious+1.088
orem+1.087
Neg logit contributions
 Psychiat-1.161
yne-1.029
 Amend-0.985
nee-0.964
ANK-0.938
Token an
Token ID281
Feature activation+9.84e+00

Pos logit contributions
 Psychiat+4.379
yne+3.818
 Amend+3.634
nee+3.592
anche+3.538
Neg logit contributions
jad-5.284
estial-5.125
 Unloaded-4.800
orem-4.767
cious-4.751
Token auction
Token ID14389
Feature activation+6.99e+00

Pos logit contributions
 Psychiat+6.887
yne+6.148
 Amend+6.046
nee+6.015
anche+5.966
Neg logit contributions
jad-7.825
estial-7.645
cious-7.114
cape-6.831
orem-6.783
Token in
Token ID287
Feature activation+4.19e+00

Pos logit contributions
 Psychiat+4.858
yne+4.329
 Amend+4.097
nee+4.058
ight+4.007
Neg logit contributions
jad-5.710
estial-5.570
 Unloaded-5.264
cious-5.214
orem-5.172
Token the
Token ID262
Feature activation+3.94e+00

Pos logit contributions
 Psychiat+3.042
yne+2.667
 Amend+2.606
nee+2.531
ight+2.488
Neg logit contributions
jad-3.446
estial-3.332
orem-3.099
 Unloaded-3.098
cious-3.081
Token US
Token ID1294
Feature activation+1.35e+01

Pos logit contributions
 Psychiat+3.014
yne+2.663
 Amend+2.563
nee+2.475
ANK+2.441
Neg logit contributions
jad-3.110
estial-2.967
 Unloaded-2.791
cious-2.782
orem-2.770
Token now
Token ID783
Feature activation+1.66e+01

Pos logit contributions
 Psychiat+8.237
yne+7.348
ight+7.058
nee+6.822
 Amend+6.820
Neg logit contributions
estial-10.680
jad-10.675
orem-9.907
 Unloaded-9.777
cious-9.743
Token understood
Token ID7247
Feature activation+9.62e+00

Pos logit contributions
 Psychiat+9.139
yne+8.582
ight+7.942
anche+7.842
nee+7.756
Neg logit contributions
estial-13.022
jad-12.894
orem-12.176
cious-11.995
 Unloaded-11.956
Token to
Token ID284
Feature activation+1.12e+01

Pos logit contributions
 Psychiat+5.624
yne+4.985
 Amend+4.684
nee+4.655
ANK+4.562
Neg logit contributions
jad-8.434
estial-8.290
orem-7.924
cious-7.720
 missionary-7.649
Token be
Token ID307
Feature activation+1.40e+01

Pos logit contributions
 Psychiat+6.918
yne+6.369
nee+5.897
 Amend+5.836
anche+5.805
Neg logit contributions
jad-9.236
estial-9.154
cious-8.729
 Unloaded-8.527
orem-8.383
Token topping
Token ID34366
Feature activation+6.55e+00

Pos logit contributions
 Psychiat+8.225
yne+7.429
 Amend+6.966
ANK+6.861
anche+6.840
Neg logit contributions
jad-11.367
estial-11.342
orem-10.558
cious-10.339
 Unloaded-10.300
Token $
Token ID720
Feature activation+3.34e+00

Pos logit contributions
 Psychiat+4.512
yne+3.917
 Amend+3.736
ANK+3.651
nee+3.644
Neg logit contributions
jad-5.534
estial-5.296
orem-5.032
 Unloaded-4.951
cious-4.912
Token =
Token ID796
Feature activation-1.77e+00

Pos logit contributions
 Psychiat+3.222
yne+2.778
nee+2.638
 Amend+2.582
ANK+2.571
Neg logit contributions
jad-4.418
estial-4.331
orem-4.079
cious-4.065
 missionary-4.039
Token c
Token ID269
Feature activation-5.85e+00

Pos logit contributions
jad+1.388
estial+1.313
 Unloaded+1.275
cious+1.251
orem+1.248
Neg logit contributions
 Psychiat-1.372
yne-1.216
 Amend-1.161
nee-1.141
ANK-1.114
Tokenv
Token ID85
Feature activation+3.87e+00

Pos logit contributions
jad+4.006
estial+3.686
cious+3.528
 Unloaded+3.504
orem+3.502
Neg logit contributions
 Psychiat-5.109
 Amend-4.548
yne-4.507
ANK-4.271
nee-4.203
Token2
Token ID17
Feature activation+4.20e-01

Pos logit contributions
 Psychiat+2.641
yne+2.329
nee+2.235
 Amend+2.164
ight+2.130
Neg logit contributions
jad-3.261
estial-3.199
cious-2.999
 Unloaded-2.994
orem-2.994
Token.
Token ID13
Feature activation+1.91e+00

Pos logit contributions
 Psychiat+0.314
yne+0.277
 Amend+0.265
nee+0.259
ANK+0.252
Neg logit contributions
jad-0.340
estial-0.326
 Unloaded-0.311
cious-0.309
orem-0.308
Tokenim
Token ID320
Feature activation+1.65e+01

Pos logit contributions
 Psychiat+1.248
yne+1.097
nee+1.028
 Amend+1.021
ight+0.987
Neg logit contributions
jad-1.705
estial-1.644
 Unloaded-1.577
cious-1.556
orem-1.550
Tokenread
Token ID961
Feature activation+5.07e+00

Pos logit contributions
yne+3.226
 Psychiat+3.140
nee+3.075
ight+2.684
anche+2.105
Neg logit contributions
estial-18.961
jad-18.593
 missionary-18.511
 Unloaded-17.810
orem-17.783
Token(
Token ID7
Feature activation+5.72e-01

Pos logit contributions
 Psychiat+3.070
yne+2.649
nee+2.528
 Amend+2.435
ANK+2.423
Neg logit contributions
jad-4.690
estial-4.619
orem-4.380
cious-4.339
 Unloaded-4.324
Tokenimage
Token ID9060
Feature activation+1.09e+00

Pos logit contributions
 Psychiat+0.260
yne+0.211
 Amend+0.192
nee+0.188
ANK+0.177
Neg logit contributions
jad-0.628
estial-0.610
 Unloaded-0.590
cious-0.586
orem-0.585
TokenPath
Token ID15235
Feature activation-1.68e+00

Pos logit contributions
 Psychiat+0.999
yne+0.904
 Amend+0.872
nee+0.858
ANK+0.839
Neg logit contributions
jad-0.694
estial-0.657
 Unloaded-0.618
cious-0.613
orem-0.613
Token)
Token ID8
Feature activation-2.63e+00

Pos logit contributions
jad+1.345
estial+1.274
 Unloaded+1.243
cious+1.216
orem+1.212
Neg logit contributions
 Psychiat-1.279
yne-1.124
 Amend-1.081
nee-1.043
ANK-1.018
Token71
Token ID4869
Feature activation+5.52e-01

Pos logit contributions
jad+0.616
estial+0.595
 Unloaded+0.572
cious+0.569
orem+0.568
Neg logit contributions
 Psychiat-0.386
yne-0.330
 Amend-0.311
nee-0.302
ANK-0.291
Token 231
Token ID34598
Feature activation-4.24e+00

Pos logit contributions
 Psychiat+0.404
yne+0.356
 Amend+0.340
nee+0.332
ANK+0.322
Neg logit contributions
jad-0.455
estial-0.439
 Unloaded-0.418
orem-0.415
cious-0.414
Token 4
Token ID604
Feature activation+1.04e+00

Pos logit contributions
jad+3.124
estial+2.963
 Unloaded+2.846
cious+2.815
orem+2.809
Neg logit contributions
 Psychiat-3.406
yne-3.042
 Amend-2.911
nee-2.862
ANK-2.781
Token691
Token ID49541
Feature activation+2.41e+00

Pos logit contributions
 Psychiat+0.706
yne+0.609
 Amend+0.582
nee+0.571
ANK+0.555
Neg logit contributions
jad-0.905
estial-0.877
cious-0.836
 Unloaded-0.835
orem-0.834
Token;
Token ID26
Feature activation-6.80e-01

Pos logit contributions
 Psychiat+1.774
yne+1.583
 Amend+1.506
nee+1.471
ight+1.440
Neg logit contributions
jad-1.926
estial-1.879
 Unloaded-1.774
orem-1.769
cious-1.766
Token th
Token ID294
Feature activation+1.64e+01

Pos logit contributions
jad+0.565
estial+0.543
 Unloaded+0.522
cious+0.516
orem+0.516
Neg logit contributions
 Psychiat-0.491
yne-0.434
 Amend-0.412
nee-0.403
ight-0.391
Tokenom
Token ID296
Feature activation+2.53e+00

Pos logit contributions
yne+8.016
 Psychiat+7.806
ight+7.490
nee+7.309
icol+7.177
Neg logit contributions
 missionary-13.347
jad-13.196
 Unloaded-12.988
estial-12.874
cious-12.216
Tokenson
Token ID1559
Feature activation+9.30e-01

Pos logit contributions
 Psychiat+2.467
yne+2.302
nee+2.198
ight+2.173
 Amend+2.167
Neg logit contributions
jad-1.378
estial-1.324
 Unloaded-1.234
 missionary-1.211
orem-1.203
Token.
Token ID13
Feature activation+2.56e+00

Pos logit contributions
 Psychiat+0.678
yne+0.602
 Amend+0.569
nee+0.564
ight+0.550
Neg logit contributions
jad-0.759
estial-0.733
 Unloaded-0.704
orem-0.691
cious-0.689
Tokenco
Token ID1073
Feature activation-8.70e+00

Pos logit contributions
 Psychiat+2.277
yne+2.094
nee+1.987
 Amend+1.974
ight+1.941
Neg logit contributions
jad-1.616
estial-1.567
 Unloaded-1.492
orem-1.456
 missionary-1.431
Token.
Token ID13
Feature activation-9.87e+00

Pos logit contributions
jad+5.717
 Unloaded+5.154
estial+5.111
cious+5.064
orem+4.875
Neg logit contributions
 Psychiat-7.465
 Amend-6.591
yne-6.509
anche-6.123
nee-6.074
Token music
Token ID2647
Feature activation-5.79e+00

Pos logit contributions
jad+6.033
estial+5.759
cious+5.537
 missionary+5.504
orem+5.494
Neg logit contributions
 Psychiat-6.027
yne-5.327
 Amend-5.203
nee-4.984
ANK-4.949
Token box
Token ID3091
Feature activation-4.39e+00

Pos logit contributions
jad+4.483
estial+4.222
cious+4.098
 Unloaded+3.995
orem+3.992
Neg logit contributions
 Psychiat-4.487
yne-3.941
 Amend-3.810
nee-3.688
ANK-3.631
Token,
Token ID11
Feature activation-6.08e+00

Pos logit contributions
jad+3.424
estial+3.268
cious+3.129
 Unloaded+3.116
orem+3.073
Neg logit contributions
 Psychiat-3.368
yne-2.978
 Amend-2.861
nee-2.795
ANK-2.733
Token involving
Token ID7411
Feature activation-9.53e+00

Pos logit contributions
jad+4.594
estial+4.345
 Unloaded+4.200
cious+4.161
 missionary+4.132
Neg logit contributions
 Psychiat-4.740
yne-4.196
 Amend-4.000
nee-3.924
ANK-3.864
Token the
Token ID262
Feature activation-1.05e+01

Pos logit contributions
jad+6.962
estial+6.570
 missionary+6.475
 Unloaded+6.352
cious+6.287
Neg logit contributions
 Psychiat-7.275
yne-6.360
 Amend-6.092
nee-5.958
anche-5.906
Token entire
Token ID2104
Feature activation-1.79e+01

Pos logit contributions
jad+7.659
estial+7.142
 missionary+7.089
orem+6.967
 Unloaded+6.895
Neg logit contributions
 Psychiat-8.028
yne-7.083
 Amend-6.731
anche-6.591
nee-6.573
Token palm
Token ID18057
Feature activation-1.19e+01

Pos logit contributions
jad+10.775
 missionary+10.546
estial+10.423
orem+10.023
cious+9.977
Neg logit contributions
 Psychiat-13.341
yne-11.758
anche-11.547
 Amend-11.249
ANK-11.185
Tokenopl
Token ID20106
Feature activation-7.46e+00

Pos logit contributions
jad+8.727
estial+8.578
cape+8.095
cious+8.051
 Unloaded+7.996
Neg logit contributions
 Psychiat-8.712
yne-7.566
 Amend-7.448
ANK-7.005
nee-6.995
Tokenant
Token ID415
Feature activation-6.42e+00

Pos logit contributions
jad+5.218
estial+5.204
cious+4.875
orem+4.867
 Unloaded+4.811
Neg logit contributions
 Psychiat-6.052
 Amend-5.289
yne-5.222
nee-4.952
ANK-4.837
Tokenar
Token ID283
Feature activation-7.96e+00

Pos logit contributions
jad+4.618
estial+4.471
cious+4.211
 Unloaded+4.187
orem+4.180
Neg logit contributions
 Psychiat-5.286
yne-4.643
 Amend-4.543
nee-4.396
ANK-4.305
Token surfaces
Token ID16649
Feature activation-6.24e+00

Pos logit contributions
jad+6.013
estial+5.786
cious+5.534
 Unloaded+5.474
 missionary+5.468
Neg logit contributions
 Psychiat-6.060
yne-5.274
 Amend-5.094
nee-4.925
ANK-4.898
Token /
Token ID1220
Feature activation-7.06e+00

Pos logit contributions
jad+1.181
estial+1.130
 Unloaded+1.081
cious+1.072
orem+1.069
Neg logit contributions
 Psychiat-1.119
yne-0.989
 Amend-0.944
nee-0.924
ANK-0.899
Tokeninit
Token ID15003
Feature activation-6.52e+00

Pos logit contributions
jad+5.080
estial+4.824
cious+4.661
 Unloaded+4.637
orem+4.537
Neg logit contributions
 Psychiat-5.766
yne-5.095
 Amend-4.873
nee-4.710
ight-4.616
Token or
Token ID393
Feature activation-1.62e+00

Pos logit contributions
jad+4.801
estial+4.586
 Unloaded+4.390
cious+4.386
orem+4.311
Neg logit contributions
 Psychiat-5.203
yne-4.565
 Amend-4.401
nee-4.253
ANK-4.141
Token /
Token ID1220
Feature activation-5.22e+00

Pos logit contributions
jad+1.388
estial+1.332
 Unloaded+1.278
cious+1.268
orem+1.266
Neg logit contributions
 Psychiat-1.141
yne-0.998
 Amend-0.951
nee-0.927
ANK-0.900
Tokens
Token ID82
Feature activation-5.20e+00

Pos logit contributions
jad+3.852
estial+3.645
cious+3.505
 Unloaded+3.491
orem+3.445
Neg logit contributions
 Psychiat-4.254
yne-3.746
 Amend-3.621
nee-3.477
ANK-3.414
Tokenbin
Token ID8800
Feature activation-1.78e+01

Pos logit contributions
jad+2.418
estial+2.206
cious+2.097
 Unloaded+2.057
orem+2.032
Neg logit contributions
 Psychiat-5.618
yne-5.112
 Amend-5.001
nee-4.815
ANK-4.795
Token/
Token ID14
Feature activation-4.35e+00

Pos logit contributions
jad+10.059
estial+9.606
 Unloaded+9.518
cape+9.497
cious+9.395
Neg logit contributions
 Psychiat-13.993
yne-12.451
 Amend-11.788
nee-11.397
ANK-11.124
Tokeninit
Token ID15003
Feature activation-3.58e+00

Pos logit contributions
jad+3.966
estial+3.803
 Unloaded+3.668
cious+3.656
orem+3.632
Neg logit contributions
 Psychiat-2.796
yne-2.381
 Amend-2.264
nee-2.169
ANK-2.099
Token,
Token ID11
Feature activation-3.62e+00

Pos logit contributions
jad+2.725
estial+2.599
 Unloaded+2.487
cious+2.471
orem+2.457
Neg logit contributions
 Psychiat-2.845
yne-2.512
 Amend-2.418
nee-2.348
ANK-2.293
Token or
Token ID393
Feature activation+1.41e+00

Pos logit contributions
jad+2.683
estial+2.550
 Unloaded+2.465
cious+2.450
orem+2.417
Neg logit contributions
 Psychiat-2.917
yne-2.589
 Amend-2.473
nee-2.439
ANK-2.366
Token you
Token ID345
Feature activation+4.78e-01

Pos logit contributions
 Psychiat+1.047
yne+0.923
 Amend+0.892
nee+0.862
ight+0.840
Neg logit contributions
jad-1.144
estial-1.103
 Unloaded-1.045
cious-1.038
orem-1.035
Token.
Token ID13
Feature activation-1.92e+00

Pos logit contributions
jad+1.796
estial+1.710
 Unloaded+1.640
cious+1.625
orem+1.619
Neg logit contributions
 Psychiat-1.685
yne-1.487
 Amend-1.422
nee-1.388
ANK-1.351
Token They
Token ID1119
Feature activation-1.94e+00

Pos logit contributions
jad+1.459
estial+1.388
 Unloaded+1.330
cious+1.315
orem+1.310
Neg logit contributions
 Psychiat-1.532
yne-1.368
 Amend-1.305
nee-1.281
ANK-1.249
Token pepp
Token ID49038
Feature activation-5.03e+00

Pos logit contributions
jad+1.552
estial+1.483
 Unloaded+1.418
cious+1.406
orem+1.403
Neg logit contributions
 Psychiat-1.474
yne-1.301
 Amend-1.246
nee-1.215
ANK-1.184
Tokenered
Token ID1068
Feature activation+9.62e-02

Pos logit contributions
jad+3.931
estial+3.763
cious+3.594
 Unloaded+3.570
orem+3.557
Neg logit contributions
 Psychiat-3.877
 Amend-3.279
yne-3.256
ANK-3.136
nee-3.132
Token Bob
Token ID5811
Feature activation-2.59e+00

Pos logit contributions
 Psychiat+0.077
yne+0.069
 Amend+0.066
nee+0.065
ight+0.063
Neg logit contributions
jad-0.072
estial-0.070
 Unloaded-0.066
orem-0.066
cious-0.065
Tokenro
Token ID305
Feature activation-1.72e+01

Pos logit contributions
jad+2.221
estial+2.123
 Unloaded+2.033
orem+2.025
cious+2.017
Neg logit contributions
 Psychiat-1.812
yne-1.575
 Amend-1.505
nee-1.459
ANK-1.424
Tokenvs
Token ID14259
Feature activation-9.03e+00

Pos logit contributions
jad+7.356
estial+6.109
 Unloaded+6.030
cious+6.018
cape+5.307
Neg logit contributions
 Psychiat-16.853
 Amend-15.368
yne-15.058
ANK-14.962
nee-14.473
Tokenky
Token ID2584
Feature activation-3.87e+00

Pos logit contributions
jad+4.943
estial+4.410
cious+4.384
 Unloaded+4.025
orem+4.003
Neg logit contributions
 Psychiat-8.919
 Amend-8.063
yne-7.744
ANK-7.411
anche-7.323
Token with
Token ID351
Feature activation-5.53e+00

Pos logit contributions
jad+3.075
estial+2.913
 Unloaded+2.796
cious+2.785
orem+2.761
Neg logit contributions
 Psychiat-2.962
yne-2.574
 Amend-2.490
nee-2.400
ANK-2.367
Token 19
Token ID678
Feature activation-6.70e-01

Pos logit contributions
jad+4.198
estial+3.961
cious+3.823
 Unloaded+3.779
 missionary+3.758
Neg logit contributions
 Psychiat-4.338
yne-3.796
 Amend-3.639
nee-3.576
ANK-3.545
Token shots
Token ID6934
Feature activation+2.07e+00

Pos logit contributions
jad+0.561
estial+0.540
 Unloaded+0.517
cious+0.511
orem+0.510
Neg logit contributions
 Psychiat-0.482
yne-0.424
 Amend-0.404
nee-0.395
ight-0.383
Token of
Token ID286
Feature activation-7.10e+00

Pos logit contributions
jad+3.554
estial+3.402
 Unloaded+3.199
cious+3.192
orem+3.185
Neg logit contributions
 Psychiat-3.511
yne-3.108
 Amend-2.993
nee-2.893
ANK-2.839
Token God
Token ID1793
Feature activation+2.46e-01

Pos logit contributions
jad+4.286
estial+4.054
orem+3.776
 Unloaded+3.734
cious+3.727
Neg logit contributions
 Psychiat-6.499
yne-5.940
 Amend-5.692
nee-5.688
ANK-5.489
Token from
Token ID422
Feature activation-5.43e+00

Pos logit contributions
 Psychiat+0.189
yne+0.168
 Amend+0.160
nee+0.157
ight+0.153
Neg logit contributions
jad-0.194
estial-0.185
 Unloaded-0.178
cious-0.177
orem-0.176
Token above
Token ID2029
Feature activation-4.47e+00

Pos logit contributions
jad+4.521
estial+4.380
 Unloaded+4.126
orem+4.089
cious+4.076
Neg logit contributions
 Psychiat-3.864
yne-3.374
 Amend-3.236
nee-3.136
ANK-3.069
Token the
Token ID262
Feature activation-6.53e+00

Pos logit contributions
jad+3.341
estial+3.208
 Unloaded+3.021
cious+3.016
orem+2.991
Neg logit contributions
 Psychiat-3.588
yne-3.186
 Amend-3.071
nee-3.013
ANK-2.915
Token seven
Token ID3598
Feature activation-1.71e+01

Pos logit contributions
jad+3.867
estial+3.680
cious+3.416
 Unloaded+3.355
orem+3.257
Neg logit contributions
 Psychiat-6.223
yne-5.685
 Amend-5.542
nee-5.356
ANK-5.282
Token heavens
Token ID27636
Feature activation-1.52e+00

Pos logit contributions
estial+6.555
jad+6.218
cious+5.326
 missionary+5.309
cape+5.203
Neg logit contributions
 Psychiat-17.314
yne-16.156
 Amend-15.781
nee-15.263
ANK-15.221
Token.
Token ID13
Feature activation+3.98e-01

Pos logit contributions
jad+1.254
estial+1.202
 Unloaded+1.150
cious+1.143
orem+1.140
Neg logit contributions
 Psychiat-1.107
yne-0.973
 Amend-0.929
nee-0.907
ANK-0.882
Token
Token ID447
Feature activation-2.89e+00

Pos logit contributions
 Psychiat+0.304
yne+0.267
 Amend+0.258
nee+0.252
ANK+0.245
Neg logit contributions
jad-0.316
estial-0.304
 Unloaded-0.289
cious-0.287
orem-0.287
Token
Token ID251
Feature activation-6.98e-01

Pos logit contributions
jad+2.290
estial+2.192
 Unloaded+2.095
cious+2.083
orem+2.076
Neg logit contributions
 Psychiat-2.201
yne-1.945
 Amend-1.859
nee-1.822
ANK-1.770
Token6
Token ID21
Feature activation-5.57e+00

Pos logit contributions
jad+0.552
estial+0.530
 Unloaded+0.504
cious+0.501
orem+0.500
Neg logit contributions
 Psychiat-0.536
yne-0.473
 Amend-0.455
nee-0.444
ANK-0.433
Token =
Token ID796
Feature activation-1.36e+01

Pos logit contributions
jad+4.397
estial+4.173
 Unloaded+3.994
orem+3.975
cious+3.955
Neg logit contributions
 Psychiat-4.337
yne-3.764
 Amend-3.693
nee-3.566
ANK-3.494
Token (
Token ID357
Feature activation-1.32e+01

Pos logit contributions
jad+9.090
 Unloaded+8.610
estial+8.515
orem+8.284
cious+8.197
Neg logit contributions
 Psychiat-10.217
yne-9.417
nee-8.948
 Amend-8.860
ANK-8.603
Token m
Token ID285
Feature activation-5.20e+00

Pos logit contributions
jad+8.851
estial+8.260
 Unloaded+8.001
cious+7.971
cape+7.814
Neg logit contributions
 Psychiat-10.155
yne-9.163
 Amend-9.038
nee-8.558
ANK-8.379
TokenD
Token ID35
Feature activation-5.24e+00

Pos logit contributions
jad+4.158
estial+3.935
 Unloaded+3.777
cious+3.755
orem+3.700
Neg logit contributions
 Psychiat-3.905
yne-3.458
 Amend-3.335
nee-3.211
ANK-3.136
Tokenensity
Token ID6377
Feature activation-7.91e+00

Pos logit contributions
jad+5.133
estial+4.899
 Unloaded+4.779
cious+4.765
orem+4.697
Neg logit contributions
 Psychiat-2.931
 Amend-2.352
yne-2.349
nee-2.169
ANK-2.145
Token +
Token ID1343
Feature activation-1.70e+01

Pos logit contributions
jad+5.882
estial+5.550
 Unloaded+5.414
cious+5.269
cape+5.239
Neg logit contributions
 Psychiat-6.100
yne-5.287
 Amend-5.190
nee-4.954
anche-4.873
Token ambient
Token ID25237
Feature activation+1.88e+00

Pos logit contributions
jad+10.420
 Unloaded+9.704
estial+9.555
cious+9.121
 missionary+9.111
Neg logit contributions
 Psychiat-12.662
yne-11.665
nee-11.283
 Amend-11.190
ANK-10.796
TokenD
Token ID35
Feature activation+1.16e-01

Pos logit contributions
 Psychiat+1.344
yne+1.192
 Amend+1.120
nee+1.108
ight+1.079
Neg logit contributions
jad-1.563
estial-1.503
 Unloaded-1.440
orem-1.428
cious-1.424
Tokenensity
Token ID6377
Feature activation-8.19e+00

Pos logit contributions
 Psychiat+0.060
yne+0.049
 Amend+0.047
nee+0.045
ANK+0.043
Neg logit contributions
jad-0.121
estial-0.117
 Unloaded-0.113
cious-0.112
orem-0.112
Token )
Token ID1267
Feature activation-8.05e+00

Pos logit contributions
jad+4.996
estial+4.583
 Unloaded+4.401
orem+4.340
cious+4.286
Neg logit contributions
 Psychiat-7.463
yne-6.625
 Amend-6.463
nee-6.272
anche-6.181
Token *
Token ID1635
Feature activation-1.48e+01

Pos logit contributions
jad+6.082
estial+5.682
 Unloaded+5.427
orem+5.391
cious+5.277
Neg logit contributions
 Psychiat-6.204
yne-5.424
 Amend-5.270
nee-5.082
ANK-4.962
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
 Psychiat+0.809
yne+0.714
 Amend+0.685
nee+0.669
ight+0.650
Neg logit contributions
jad-0.877
estial-0.838
 Unloaded-0.801
orem-0.792
cious-0.792
Token atmosphere
Token ID8137
Feature activation+6.95e+00

Pos logit contributions
 Psychiat+1.054
yne+0.935
 Amend+0.897
nee+0.875
ANK+0.850
Neg logit contributions
jad-1.118
estial-1.066
 Unloaded-1.020
cious-1.006
orem-1.004
Token,
Token ID11
Feature activation+1.65e+00

Pos logit contributions
 Psychiat+4.468
yne+3.947
 Amend+3.733
ight+3.698
nee+3.696
Neg logit contributions
jad-5.928
estial-5.710
 Unloaded-5.475
orem-5.474
cious-5.433
Token where
Token ID810
Feature activation+3.81e+00

Pos logit contributions
 Psychiat+1.235
yne+1.089
 Amend+1.044
nee+1.023
ight+0.999
Neg logit contributions
jad-1.332
estial-1.278
 Unloaded-1.212
orem-1.209
cious-1.209
Token incoming
Token ID15619
Feature activation+1.49e+00

Pos logit contributions
 Psychiat+2.716
yne+2.426
 Amend+2.311
nee+2.264
ight+2.222
Neg logit contributions
jad-3.136
estial-2.998
 Unloaded-2.881
cious-2.848
orem-2.837
Token and
Token ID290
Feature activation-1.69e+01

Pos logit contributions
 Psychiat+1.101
yne+0.972
 Amend+0.933
nee+0.910
ight+0.886
Neg logit contributions
jad-1.205
estial-1.157
 Unloaded-1.101
orem-1.098
cious-1.092
Token outgoing
Token ID28181
Feature activation+9.70e-01

Pos logit contributions
jad+9.111
orem+8.588
 Unloaded+8.561
estial+8.390
 missionary+8.335
Neg logit contributions
 Psychiat-14.254
yne-12.555
nee-11.952
 Amend-11.802
ANK-11.630
Token flux
Token ID28462
Feature activation-7.81e-01

Pos logit contributions
 Psychiat+0.745
yne+0.661
 Amend+0.634
nee+0.620
ight+0.602
Neg logit contributions
jad-0.763
estial-0.732
 Unloaded-0.696
orem-0.692
cious-0.691
Tokenes
Token ID274
Feature activation+5.17e+00

Pos logit contributions
jad+0.673
estial+0.646
 Unloaded+0.620
cious+0.615
orem+0.614
Neg logit contributions
 Psychiat-0.544
yne-0.475
 Amend-0.453
nee-0.441
ANK-0.428
Token are
Token ID389
Feature activation+1.15e+00

Pos logit contributions
 Psychiat+3.717
yne+3.287
 Amend+3.165
nee+3.075
ight+3.068
Neg logit contributions
jad-4.170
estial-4.082
cious-3.840
 Unloaded-3.820
orem-3.790
Token identical
Token ID10411
Feature activation+2.25e+00

Pos logit contributions
 Psychiat+0.879
yne+0.778
 Amend+0.745
nee+0.727
ight+0.707
Neg logit contributions
jad-0.908
estial-0.874
 Unloaded-0.830
cious-0.824
orem-0.823
Tokendir
Token ID15908
Feature activation-7.43e+00

Pos logit contributions
jad+4.817
estial+4.542
 Unloaded+4.354
orem+4.340
cape+4.325
Neg logit contributions
 Psychiat-4.841
yne-4.259
 Amend-4.111
nee-3.948
ANK-3.846
Token'
Token ID6
Feature activation-4.57e+00

Pos logit contributions
jad+4.707
estial+4.556
 Unloaded+4.253
orem+4.247
cape+4.205
Neg logit contributions
 Psychiat-6.588
yne-5.968
 Amend-5.781
nee-5.629
ANK-5.449
Token option
Token ID3038
Feature activation-4.37e+00

Pos logit contributions
jad+3.464
estial+3.277
 Unloaded+3.188
orem+3.112
cious+3.111
Neg logit contributions
 Psychiat-3.603
yne-3.189
 Amend-3.078
nee-2.986
ANK-2.899
Token to
Token ID284
Feature activation-5.14e+00

Pos logit contributions
jad+3.346
estial+3.181
 Unloaded+3.088
orem+3.036
cious+3.026
Neg logit contributions
 Psychiat-3.397
yne-3.017
 Amend-2.892
nee-2.820
ANK-2.754
Token "
Token ID366
Feature activation-7.03e+00

Pos logit contributions
jad+4.032
estial+3.840
 Unloaded+3.735
orem+3.677
cious+3.655
Neg logit contributions
 Psychiat-3.859
yne-3.429
 Amend-3.240
nee-3.184
ANK-3.101
Tokenc
Token ID66
Feature activation-1.68e+01

Pos logit contributions
jad+5.793
estial+5.500
 Unloaded+5.312
orem+5.282
cape+5.280
Neg logit contributions
 Psychiat-4.980
yne-4.357
 Amend-4.175
nee-4.010
ANK-3.868
Token:\
Token ID7479
Feature activation-7.11e+00

Pos logit contributions
jad+9.975
estial+9.597
cape+9.251
orem+9.239
 Unloaded+9.238
Neg logit contributions
 Psychiat-12.988
yne-11.676
 Amend-11.550
nee-10.939
anche-10.486
Tokentmp
Token ID22065
Feature activation-9.79e+00

Pos logit contributions
jad+4.496
estial+4.209
 Unloaded+4.006
orem+3.971
cious+3.951
Neg logit contributions
 Psychiat-6.366
yne-5.708
 Amend-5.574
nee-5.422
ANK-5.281
Token".
Token ID1911
Feature activation-1.57e+00

Pos logit contributions
jad+6.535
estial+6.224
 Unloaded+6.043
orem+5.951
cape+5.838
Neg logit contributions
 Psychiat-8.088
yne-7.259
 Amend-7.013
nee-6.784
ANK-6.627
Token Only
Token ID5514
Feature activation-2.13e+00

Pos logit contributions
jad+1.176
estial+1.121
 Unloaded+1.071
orem+1.060
cious+1.060
Neg logit contributions
 Psychiat-1.261
yne-1.123
 Amend-1.077
nee-1.055
ANK-1.029
Token a
Token ID257
Feature activation+1.23e+00

Pos logit contributions
jad+1.673
estial+1.597
 Unloaded+1.532
orem+1.515
cious+1.515
Neg logit contributions
 Psychiat-1.647
yne-1.458
 Amend-1.395
nee-1.368
ANK-1.330
Token on
Token ID319
Feature activation-5.99e+00

Pos logit contributions
jad+3.300
 Unloaded+3.017
estial+3.009
orem+2.967
cious+2.932
Neg logit contributions
 Psychiat-4.215
yne-3.813
 Amend-3.690
nee-3.546
ANK-3.500
Token Facebook
Token ID3203
Feature activation-3.93e+00

Pos logit contributions
jad+4.282
 Unloaded+3.886
estial+3.771
cious+3.761
orem+3.665
Neg logit contributions
 Psychiat-4.846
yne-4.423
 Amend-4.200
anche-4.062
nee-4.018
Token Share
Token ID8734
Feature activation-1.55e+00

Pos logit contributions
jad+3.038
estial+2.820
 Unloaded+2.759
orem+2.740
cious+2.736
Neg logit contributions
 Psychiat-2.997
yne-2.730
 Amend-2.539
nee-2.507
ANK-2.453
Token this
Token ID428
Feature activation-4.88e+00

Pos logit contributions
jad+1.133
estial+1.070
 Unloaded+1.019
cious+1.011
orem+1.006
Neg logit contributions
 Psychiat-1.279
yne-1.140
 Amend-1.099
nee-1.071
ANK-1.050
Token comment
Token ID2912
Feature activation-5.16e+00

Pos logit contributions
jad+3.037
estial+2.727
 Unloaded+2.647
orem+2.611
cious+2.610
Neg logit contributions
 Psychiat-4.570
yne-4.119
 Amend-3.994
nee-3.868
ANK-3.813
Token on
Token ID319
Feature activation-1.67e+01

Pos logit contributions
jad+3.480
 Unloaded+3.177
estial+3.172
orem+3.113
cious+3.080
Neg logit contributions
 Psychiat-4.450
yne-4.011
 Amend-3.892
nee-3.737
ANK-3.679
Token Twitter
Token ID3009
Feature activation-5.70e+00

Pos logit contributions
jad+6.537
 Unloaded+5.696
 Starg+4.933
mith+4.797
orem+4.781
Neg logit contributions
 Psychiat-16.247
yne-16.218
anche-15.261
anches-14.855
 Amend-14.589
Token
Token ID198
Feature activation-3.12e+00

Pos logit contributions
jad+4.320
estial+4.042
 Unloaded+3.913
cious+3.878
orem+3.858
Neg logit contributions
 Psychiat-4.445
yne-3.988
 Amend-3.783
nee-3.734
ANK-3.625
Token
Token ID198
Feature activation+2.36e+00

Pos logit contributions
jad+2.304
estial+2.138
 Unloaded+2.098
cious+2.068
orem+2.028
Neg logit contributions
 Psychiat-2.534
yne-2.270
 Amend-2.175
nee-2.094
anche-2.080
TokenNY
Token ID12805
Feature activation+9.85e+00

Pos logit contributions
 Psychiat+1.875
yne+1.688
 Amend+1.604
nee+1.594
ANK+1.580
Neg logit contributions
jad-1.745
estial-1.691
 Unloaded-1.618
orem-1.614
cious-1.577
TokenT
Token ID51
Feature activation+1.94e+00

Pos logit contributions
 Psychiat+3.660
ANK+2.788
yne+2.745
 Amend+2.665
nee+2.583
Neg logit contributions
jad-10.819
estial-10.806
orem-10.459
 missionary-10.267
 Unloaded-10.241
Token group
Token ID1448
Feature activation-4.05e+00

Pos logit contributions
jad+6.365
estial+5.649
orem+5.547
 Unloaded+5.542
 missionary+5.524
Neg logit contributions
 Psychiat-7.848
yne-7.004
 Amend-6.787
nee-6.704
ANK-6.477
Token at
Token ID379
Feature activation-8.82e+00

Pos logit contributions
jad+3.197
estial+3.009
 Unloaded+2.893
orem+2.878
cious+2.869
Neg logit contributions
 Psychiat-3.078
yne-2.709
 Amend-2.616
nee-2.544
ANK-2.491
Token week
Token ID1285
Feature activation-5.01e+00

Pos logit contributions
jad+6.335
estial+5.783
 missionary+5.537
 Unloaded+5.531
orem+5.528
Neg logit contributions
 Psychiat-7.143
yne-6.402
 Amend-6.105
ANK-5.945
nee-5.935
Token 4
Token ID604
Feature activation-4.32e+00

Pos logit contributions
jad+3.461
estial+3.248
 Unloaded+3.123
orem+3.094
cious+3.092
Neg logit contributions
 Psychiat-4.265
yne-3.795
 Amend-3.664
nee-3.576
ANK-3.520
Token vs
Token ID3691
Feature activation-9.76e+00

Pos logit contributions
jad+3.227
estial+3.008
 Unloaded+2.893
orem+2.874
cious+2.862
Neg logit contributions
 Psychiat-3.459
yne-3.089
 Amend-2.982
nee-2.897
ANK-2.832
Token the
Token ID262
Feature activation-1.64e+01

Pos logit contributions
jad+6.884
estial+6.342
orem+6.289
cious+6.176
 Unloaded+6.150
Neg logit contributions
 Psychiat-7.705
yne-6.896
 Amend-6.705
nee-6.537
ANK-6.409
Token sham
Token ID23565
Feature activation-8.41e+00

Pos logit contributions
jad+8.736
orem+8.070
 missionary+8.018
cious+7.691
estial+7.683
Neg logit contributions
 Psychiat-13.429
yne-12.696
nee-11.960
ANK-11.909
 Amend-11.861
Token ta
Token ID20486
Feature activation-5.99e+00

Pos logit contributions
jad+6.116
estial+5.703
 Unloaded+5.519
orem+5.473
cious+5.450
Neg logit contributions
 Psychiat-6.561
yne-5.851
 Amend-5.633
nee-5.481
ANK-5.386
TokenV
Token ID53
Feature activation-7.45e+00

Pos logit contributions
jad+4.795
estial+4.469
 Unloaded+4.450
orem+4.344
cious+4.325
Neg logit contributions
 Psychiat-4.353
yne-3.846
 Amend-3.741
nee-3.471
anche-3.467
TokenNS
Token ID8035
Feature activation-1.29e+01

Pos logit contributions
jad+4.952
estial+4.514
cious+4.455
 Unloaded+4.425
orem+4.302
Neg logit contributions
 Psychiat-6.381
 Amend-5.792
yne-5.466
nee-5.183
ANK-5.130
Token group
Token ID1448
Feature activation-5.60e+00

Pos logit contributions
jad+7.843
 missionary+6.836
orem+6.810
estial+6.798
 Unloaded+6.625
Neg logit contributions
 Psychiat-10.908
yne-9.830
 Amend-9.526
nee-9.478
ANK-9.086
Token:
Token ID25
Feature activation-1.78e+00

Pos logit contributions
jad+2.499
estial+2.297
 Unloaded+2.238
cious+2.227
cape+2.180
Neg logit contributions
 Psychiat-2.748
yne-2.481
 Amend-2.370
nee-2.272
anche-2.266
Token45
Token ID2231
Feature activation+1.07e+00

Pos logit contributions
jad+1.508
estial+1.432
 Unloaded+1.385
cious+1.371
orem+1.366
Neg logit contributions
 Psychiat-1.249
yne-1.107
 Amend-1.046
nee-1.010
anche-0.991
Token)
Token ID8
Feature activation-2.16e+00

Pos logit contributions
 Psychiat+0.724
yne+0.637
 Amend+0.605
nee+0.596
ANK+0.575
Neg logit contributions
jad-0.935
estial-0.912
 Unloaded-0.871
orem-0.862
cious-0.860
Token to
Token ID284
Feature activation-7.81e+00

Pos logit contributions
jad+1.733
estial+1.655
 Unloaded+1.585
cious+1.572
orem+1.567
Neg logit contributions
 Psychiat-1.636
yne-1.444
 Amend-1.383
nee-1.349
ANK-1.315
Token take
Token ID1011
Feature activation-6.82e+00

Pos logit contributions
jad+5.838
estial+5.269
 Unloaded+5.227
 missionary+5.184
orem+5.152
Neg logit contributions
 Psychiat-6.126
yne-5.413
 Amend-5.050
nee-4.997
ANK-4.914
Token full
Token ID1336
Feature activation-1.63e+01

Pos logit contributions
jad+4.976
estial+4.719
 Unloaded+4.557
cious+4.534
orem+4.451
Neg logit contributions
 Psychiat-5.498
yne-4.921
 Amend-4.670
nee-4.628
ANK-4.477
Token control
Token ID1630
Feature activation-4.54e+00

Pos logit contributions
jad+7.955
estial+7.511
cious+7.437
 missionary+7.233
orem+7.132
Neg logit contributions
 Psychiat-14.813
yne-13.723
 Amend-13.023
nee-12.867
ANK-12.674
Token of
Token ID286
Feature activation-4.77e+00

Pos logit contributions
jad+3.518
estial+3.332
 Unloaded+3.213
cious+3.186
orem+3.162
Neg logit contributions
 Psychiat-3.514
yne-3.103
 Amend-2.966
nee-2.902
ANK-2.832
Token the
Token ID262
Feature activation-7.10e-01

Pos logit contributions
jad+3.550
estial+3.337
 Unloaded+3.222
cious+3.204
orem+3.168
Neg logit contributions
 Psychiat-3.849
yne-3.427
 Amend-3.262
nee-3.236
ANK-3.145
Token game
Token ID983
Feature activation-8.31e-01

Pos logit contributions
jad+0.531
estial+0.510
 Unloaded+0.484
orem+0.479
cious+0.478
Neg logit contributions
 Psychiat-0.573
yne-0.509
 Amend-0.491
nee-0.479
ight-0.467
Token.
Token ID13
Feature activation-4.53e+00

Pos logit contributions
jad+0.678
estial+0.652
 Unloaded+0.622
orem+0.618
cious+0.617
Neg logit contributions
 Psychiat-0.615
yne-0.542
 Amend-0.517
nee-0.506
ANK-0.492
Token been
Token ID587
Feature activation-2.09e+00

Pos logit contributions
jad+3.741
estial+3.533
 Unloaded+3.403
cious+3.346
orem+3.343
Neg logit contributions
 Psychiat-3.308
yne-2.914
 Amend-2.772
nee-2.720
ANK-2.660
Token retail
Token ID6308
Feature activation-8.53e+00

Pos logit contributions
jad+1.703
estial+1.627
 Unloaded+1.558
cious+1.545
orem+1.541
Neg logit contributions
 Psychiat-1.543
yne-1.362
 Amend-1.298
nee-1.268
ANK-1.234
Tokening
Token ID278
Feature activation-6.01e+00

Pos logit contributions
jad+6.254
estial+5.824
 missionary+5.573
cious+5.536
 Unloaded+5.507
Neg logit contributions
 Psychiat-6.553
yne-5.963
 Amend-5.704
nee-5.621
ANK-5.494
Token gossip
Token ID30914
Feature activation-2.28e+00

Pos logit contributions
jad+4.501
estial+4.246
 Unloaded+4.052
cious+4.047
 missionary+3.993
Neg logit contributions
 Psychiat-4.745
yne-4.228
nee-4.011
 Amend-3.993
ANK-3.880
Token.
Token ID13
Feature activation+1.81e+00

Pos logit contributions
jad+1.801
estial+1.718
 Unloaded+1.641
cious+1.631
orem+1.622
Neg logit contributions
 Psychiat-1.756
yne-1.553
 Amend-1.489
nee-1.455
ANK-1.418
Token D
Token ID360
Feature activation-1.63e+01

Pos logit contributions
 Psychiat+1.342
yne+1.145
 Amend+1.125
nee+1.078
ANK+1.048
Neg logit contributions
jad-1.498
estial-1.453
cious-1.373
 Unloaded-1.372
orem-1.369
Tokenvor
Token ID20867
Feature activation-1.02e+01

Pos logit contributions
jad+10.276
estial+9.593
orem+9.289
cious+9.007
 Unloaded+8.864
Neg logit contributions
 Psychiat-12.927
yne-11.178
 Amend-11.107
nee-10.299
ANK-10.072
Tokenak
Token ID461
Feature activation-6.62e-01

Pos logit contributions
jad+5.308
 Unloaded+4.559
estial+4.528
cious+4.422
orem+4.242
Neg logit contributions
 Psychiat-10.251
 Amend-9.202
yne-9.192
nee-8.582
ANK-8.412
Token and
Token ID290
Feature activation-6.73e+00

Pos logit contributions
jad+0.545
estial+0.523
 Unloaded+0.500
cious+0.497
orem+0.496
Neg logit contributions
 Psychiat-0.486
yne-0.427
 Amend-0.408
nee-0.399
ANK-0.387
Token Brah
Token ID36415
Feature activation+4.51e+00

Pos logit contributions
jad+4.889
estial+4.558
 Unloaded+4.391
orem+4.356
 missionary+4.333
Neg logit contributions
 Psychiat-5.346
yne-4.816
 Amend-4.556
nee-4.535
ANK-4.441
Tokenms
Token ID907
Feature activation+1.12e+00

Pos logit contributions
 Psychiat+3.649
yne+3.338
nee+3.201
 Amend+3.115
ight+3.062
Neg logit contributions
jad-3.192
estial-3.123
 Unloaded-2.957
orem-2.912
 missionary-2.891
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
jad+2.074
estial+1.924
 Unloaded+1.902
cious+1.860
orem+1.836
Neg logit contributions
 Psychiat-2.312
yne-2.081
 Amend-1.994
nee-1.907
anche-1.903
TokenAdvertisement
Token ID4723
Feature activation-7.80e+00

Pos logit contributions
jad+1.008
estial+0.959
 Unloaded+0.913
cious+0.905
orem+0.903
Neg logit contributions
 Psychiat-1.134
yne-1.013
 Amend-0.974
nee-0.952
ANK-0.929
Token Continue
Token ID10054
Feature activation-7.05e+00

Pos logit contributions
jad+5.014
estial+4.594
 Unloaded+4.511
orem+4.462
cious+4.397
Neg logit contributions
 Psychiat-6.843
yne-6.203
 Amend-5.878
nee-5.740
anche-5.676
Token reading
Token ID3555
Feature activation-3.19e+00

Pos logit contributions
jad+5.181
estial+4.740
cious+4.677
 Unloaded+4.667
 missionary+4.615
Neg logit contributions
 Psychiat-5.578
yne-4.897
 Amend-4.773
nee-4.598
ANK-4.517
Token the
Token ID262
Feature activation-8.17e+00

Pos logit contributions
jad+2.330
estial+2.187
 Unloaded+2.115
cious+2.105
orem+2.091
Neg logit contributions
 Psychiat-2.623
yne-2.331
 Amend-2.242
nee-2.185
ANK-2.133
Token main
Token ID1388
Feature activation-1.62e+01

Pos logit contributions
jad+4.493
orem+3.982
estial+3.960
 Unloaded+3.828
cious+3.791
Neg logit contributions
 Psychiat-8.050
yne-7.217
 Amend-7.022
nee-6.813
ANK-6.708
Token story
Token ID1621
Feature activation-9.13e+00

Pos logit contributions
jad+7.095
 missionary+6.028
cious+6.018
 Unloaded+5.916
cape+5.869
Neg logit contributions
 Psychiat-15.534
yne-14.239
 Amend-13.986
nee-13.409
ANK-13.039
Token
Token ID198
Feature activation-6.33e-01

Pos logit contributions
jad+5.525
 Unloaded+5.262
cious+4.906
cape+4.861
estial+4.828
Neg logit contributions
 Psychiat-7.713
yne-7.364
anche-6.905
 Amend-6.666
agons-6.551
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
jad+0.493
estial+0.467
 Unloaded+0.451
cious+0.445
orem+0.443
Neg logit contributions
 Psychiat-0.492
yne-0.438
 Amend-0.419
nee-0.407
ANK-0.398
TokenSome
Token ID4366
Feature activation-6.20e+00

Pos logit contributions
jad+1.024
estial+0.978
 Unloaded+0.932
cious+0.925
orem+0.923
Neg logit contributions
 Psychiat-1.062
yne-0.944
 Amend-0.905
nee-0.885
ANK-0.862
Token teenagers
Token ID17366
Feature activation-3.73e-01

Pos logit contributions
jad+4.841
estial+4.523
 Unloaded+4.350
cious+4.319
orem+4.299
Neg logit contributions
 Psychiat-4.724
yne-4.176
 Amend-4.016
nee-3.925
ANK-3.857
Token")
Token ID4943
Feature activation-4.92e+00

Pos logit contributions
jad+1.853
estial+1.756
 Unloaded+1.732
cious+1.686
cape+1.667
Neg logit contributions
 Psychiat-1.593
yne-1.399
 Amend-1.348
nee-1.285
ANK-1.268
Token is
Token ID318
Feature activation+4.11e+00

Pos logit contributions
jad+3.262
estial+3.020
 Unloaded+2.998
cious+2.867
orem+2.862
Neg logit contributions
 Psychiat-4.305
yne-3.859
 Amend-3.735
nee-3.639
anche-3.585
Token an
Token ID281
Feature activation-1.86e+00

Pos logit contributions
 Psychiat+2.637
yne+2.264
 Amend+2.168
nee+2.120
ANK+2.062
Neg logit contributions
jad-3.682
estial-3.613
cious-3.446
orem-3.432
 Unloaded-3.399
Token autos
Token ID44619
Feature activation-6.56e+00

Pos logit contributions
jad+0.907
estial+0.840
 Unloaded+0.784
cious+0.770
orem+0.768
Neg logit contributions
 Psychiat-1.994
yne-1.825
 Amend-1.776
nee-1.748
ANK-1.715
Tokenomal
Token ID18048
Feature activation-8.74e+00

Pos logit contributions
jad+2.884
estial+2.659
orem+2.498
cious+2.484
 Unloaded+2.427
Neg logit contributions
 Psychiat-7.237
 Amend-6.607
yne-6.332
ANK-6.253
nee-6.120
Token dominant
Token ID11410
Feature activation-1.62e+01

Pos logit contributions
jad+3.829
 missionary+3.186
 Unloaded+3.073
cious+3.058
estial+3.034
Neg logit contributions
 Psychiat-9.469
yne-8.604
 Amend-8.543
nee-8.188
ANK-8.092
Token ker
Token ID41927
Feature activation-4.15e+00

Pos logit contributions
jad+6.007
 missionary+4.906
 Unloaded+4.900
estial+4.818
cape+4.746
Neg logit contributions
 Psychiat-16.952
 Amend-15.068
yne-14.941
ANK-14.659
anche-14.579
Tokenat
Token ID265
Feature activation-4.14e+00

Pos logit contributions
jad+3.068
estial+2.857
cious+2.737
 Unloaded+2.737
orem+2.733
Neg logit contributions
 Psychiat-3.378
yne-2.979
 Amend-2.954
nee-2.767
ANK-2.761
Tokenoder
Token ID12342
Feature activation-8.57e+00

Pos logit contributions
jad+2.305
estial+2.135
orem+2.033
 Unloaded+2.022
cious+1.987
Neg logit contributions
 Psychiat-4.152
yne-3.686
 Amend-3.660
nee-3.526
ANK-3.517
Tokenma
Token ID2611
Feature activation-3.15e+00

Pos logit contributions
jad+4.058
estial+3.367
cious+3.340
orem+3.300
 Unloaded+3.271
Neg logit contributions
 Psychiat-9.199
 Amend-8.236
yne-8.164
ANK-7.929
anche-7.713
Token of
Token ID286
Feature activation-1.52e+00

Pos logit contributions
jad+2.408
estial+2.245
 Unloaded+2.201
cious+2.163
cape+2.118
Neg logit contributions
 Psychiat-2.482
yne-2.203
 Amend-2.129
nee-2.057
ANK-2.020
Token head
Token ID1182
Feature activation-9.23e-01

Pos logit contributions
 Psychiat+1.901
yne+1.649
 Amend+1.547
nee+1.537
ANK+1.487
Neg logit contributions
jad-2.721
estial-2.676
orem-2.554
 Unloaded-2.527
cious-2.511
Token,
Token ID11
Feature activation+2.12e+00

Pos logit contributions
jad+0.746
estial+0.710
 Unloaded+0.682
cious+0.676
orem+0.673
Neg logit contributions
 Psychiat-0.692
yne-0.611
 Amend-0.586
nee-0.568
ANK-0.552
Token and
Token ID290
Feature activation-6.08e+00

Pos logit contributions
 Psychiat+1.570
yne+1.388
 Amend+1.320
nee+1.300
ANK+1.262
Neg logit contributions
jad-1.731
estial-1.673
orem-1.581
 Unloaded-1.568
cious-1.566
Token must
Token ID1276
Feature activation-9.53e+00

Pos logit contributions
jad+4.533
estial+4.309
 Unloaded+4.252
cious+4.122
 missionary+4.115
Neg logit contributions
 Psychiat-4.754
yne-4.217
 Amend-4.033
nee-3.947
ANK-3.935
Token roll
Token ID4836
Feature activation-1.75e+00

Pos logit contributions
jad+3.589
estial+3.002
cious+2.909
 Unloaded+2.886
 missionary+2.881
Neg logit contributions
 Psychiat-10.583
yne-9.391
 Amend-9.388
ANK-9.059
nee-9.032
Token to
Token ID284
Feature activation-1.60e+01

Pos logit contributions
jad+1.370
estial+1.303
 Unloaded+1.253
cious+1.237
orem+1.231
Neg logit contributions
 Psychiat-1.350
yne-1.194
 Amend-1.146
nee-1.115
ANK-1.089
Token avoid
Token ID3368
Feature activation-8.53e+00

Pos logit contributions
jad+6.324
cape+6.088
 missionary+5.780
estial+5.762
cious+5.563
Neg logit contributions
 Psychiat-15.870
yne-14.717
ANK-14.175
netflix-13.587
 Amend-13.423
Token following
Token ID1708
Feature activation+5.34e+00

Pos logit contributions
jad+5.682
estial+5.033
 Unloaded+5.001
 missionary+4.898
cious+4.867
Neg logit contributions
 Psychiat-7.512
yne-6.630
 Amend-6.450
nee-6.198
ANK-6.162
Token the
Token ID262
Feature activation+4.11e-01

Pos logit contributions
 Psychiat+3.577
yne+3.168
 Amend+2.967
nee+2.941
ight+2.901
Neg logit contributions
jad-4.603
estial-4.505
orem-4.225
cious-4.190
 Unloaded-4.160
Token commands
Token ID9729
Feature activation-1.22e+00

Pos logit contributions
 Psychiat+0.299
yne+0.262
 Amend+0.251
nee+0.245
ANK+0.237
Neg logit contributions
jad-0.342
estial-0.327
 Unloaded-0.314
cious-0.311
orem-0.311
Token in
Token ID287
Feature activation-1.74e+00

Pos logit contributions
jad+0.908
estial+0.860
 Unloaded+0.829
cious+0.818
orem+0.813
Neg logit contributions
 Psychiat-0.996
yne-0.889
 Amend-0.857
nee-0.834
ANK-0.814
Token to
Token ID284
Feature activation-5.55e-01

Pos logit contributions
 Psychiat+1.940
yne+1.710
 Amend+1.617
nee+1.588
ANK+1.560
Neg logit contributions
jad-2.256
estial-2.170
cious-2.057
 Unloaded-2.049
orem-2.038
Token a
Token ID257
Feature activation-3.30e+00

Pos logit contributions
jad+0.424
estial+0.406
 Unloaded+0.385
cious+0.384
orem+0.382
Neg logit contributions
 Psychiat-0.442
yne-0.392
 Amend-0.376
nee-0.369
ANK-0.359
Token cl
Token ID537
Feature activation+2.67e+00

Pos logit contributions
jad+2.511
estial+2.387
 Unloaded+2.293
orem+2.259
cious+2.257
Neg logit contributions
 Psychiat-2.606
yne-2.319
 Amend-2.238
nee-2.181
ANK-2.123
Tokenojure
Token ID32511
Feature activation-5.22e+00

Pos logit contributions
 Psychiat+2.076
yne+1.883
nee+1.751
 Amend+1.750
ight+1.714
Neg logit contributions
jad-2.011
estial-1.941
 Unloaded-1.862
cious-1.846
orem-1.838
Token.
Token ID13
Feature activation-4.37e+00

Pos logit contributions
jad+3.917
estial+3.733
 Unloaded+3.551
orem+3.551
cious+3.549
Neg logit contributions
 Psychiat-4.150
yne-3.664
 Amend-3.523
nee-3.474
ANK-3.355
Tokenl
Token ID75
Feature activation-1.59e+01

Pos logit contributions
jad+2.617
estial+2.455
 Unloaded+2.315
cious+2.286
orem+2.281
Neg logit contributions
 Psychiat-4.163
yne-3.769
 Amend-3.654
nee-3.579
ANK-3.516
Tokenibraries
Token ID11127
Feature activation-1.01e+01

Pos logit contributions
jad+12.096
orem+11.550
estial+11.455
 Unloaded+10.773
cape+10.659
Neg logit contributions
 Psychiat-10.672
 Amend-9.371
yne-9.052
ANK-8.394
nee-8.228
Token table
Token ID3084
Feature activation-1.81e+00

Pos logit contributions
jad+6.304
estial+5.867
 Unloaded+5.738
orem+5.693
cious+5.619
Neg logit contributions
 Psychiat-8.661
yne-7.720
 Amend-7.499
nee-7.434
ANK-7.089
Token.
Token ID13
Feature activation+9.78e-01

Pos logit contributions
jad+1.440
estial+1.374
 Unloaded+1.318
cious+1.308
orem+1.304
Neg logit contributions
 Psychiat-1.385
yne-1.223
 Amend-1.171
nee-1.144
ANK-1.111
Token
Token ID198
Feature activation+3.46e+00

Pos logit contributions
 Psychiat+0.754
yne+0.665
 Amend+0.642
nee+0.622
ight+0.608
Neg logit contributions
jad-0.768
estial-0.741
 Unloaded-0.698
cious-0.696
orem-0.692
Token
Token ID198
Feature activation+7.53e+00

Pos logit contributions
 Psychiat+2.388
yne+2.079
nee+1.982
 Amend+1.979
ight+1.903
Neg logit contributions
jad-2.953
estial-2.892
orem-2.721
 Unloaded-2.708
cious-2.705
Token on
Token ID319
Feature activation-4.15e+00

Pos logit contributions
jad+3.122
estial+2.859
 Unloaded+2.859
orem+2.802
cious+2.775
Neg logit contributions
 Psychiat-3.943
yne-3.566
 Amend-3.443
nee-3.314
anche-3.268
Token Facebook
Token ID3203
Feature activation-2.47e+00

Pos logit contributions
jad+3.095
 Unloaded+2.811
estial+2.777
cious+2.735
orem+2.686
Neg logit contributions
 Psychiat-3.293
yne-2.975
 Amend-2.836
nee-2.729
anche-2.724
Token Share
Token ID8734
Feature activation-1.52e+00

Pos logit contributions
jad+1.986
estial+1.869
 Unloaded+1.814
orem+1.798
cious+1.798
Neg logit contributions
 Psychiat-1.835
yne-1.648
 Amend-1.546
nee-1.518
ANK-1.484
Token this
Token ID428
Feature activation-5.05e+00

Pos logit contributions
jad+1.110
estial+1.047
 Unloaded+0.999
cious+0.990
orem+0.984
Neg logit contributions
 Psychiat-1.262
yne-1.124
 Amend-1.085
nee-1.057
ANK-1.037
Token comment
Token ID2912
Feature activation-4.94e+00

Pos logit contributions
jad+3.129
estial+2.801
 Unloaded+2.725
orem+2.690
cious+2.686
Neg logit contributions
 Psychiat-4.730
yne-4.264
 Amend-4.138
nee-3.999
ANK-3.952
Token on
Token ID319
Feature activation-1.59e+01

Pos logit contributions
jad+3.339
 Unloaded+3.050
estial+3.048
orem+2.983
cious+2.956
Neg logit contributions
 Psychiat-4.256
yne-3.829
 Amend-3.715
nee-3.574
ANK-3.520
Token Twitter
Token ID3009
Feature activation-5.26e+00

Pos logit contributions
jad+6.498
 Unloaded+5.706
 Starg+4.913
orem+4.890
mith+4.886
Neg logit contributions
 Psychiat-15.484
yne-15.272
anche-14.329
anches-13.923
 Amend-13.889
Token
Token ID198
Feature activation-3.14e+00

Pos logit contributions
jad+3.997
estial+3.756
 Unloaded+3.628
cious+3.601
orem+3.580
Neg logit contributions
 Psychiat-4.114
yne-3.678
 Amend-3.504
nee-3.449
ANK-3.344
Token
Token ID198
Feature activation+1.72e+00

Pos logit contributions
jad+2.318
estial+2.152
 Unloaded+2.111
cious+2.081
orem+2.040
Neg logit contributions
 Psychiat-2.547
yne-2.279
 Amend-2.186
nee-2.104
anche-2.089
TokenNY
Token ID12805
Feature activation+1.03e+01

Pos logit contributions
 Psychiat+1.378
yne+1.239
 Amend+1.178
nee+1.170
ANK+1.156
Neg logit contributions
jad-1.264
estial-1.223
 Unloaded-1.168
orem-1.167
cious-1.140
TokenT
Token ID51
Feature activation+3.23e+00

Pos logit contributions
 Psychiat+3.773
ANK+2.842
yne+2.766
 Amend+2.700
nee+2.602
Neg logit contributions
estial-11.439
jad-11.394
orem-11.047
 missionary-10.844
cious-10.806
Token
Token ID198
Feature activation-7.36e-01

Pos logit contributions
jad+1.361
estial+1.274
 Unloaded+1.247
cious+1.225
orem+1.212
Neg logit contributions
 Psychiat-1.450
yne-1.298
 Amend-1.246
nee-1.196
anche-1.180
TokenAdvertisement
Token ID4723
Feature activation-8.03e+00

Pos logit contributions
jad+0.547
estial+0.524
 Unloaded+0.498
cious+0.494
orem+0.493
Neg logit contributions
 Psychiat-0.599
yne-0.534
 Amend-0.512
nee-0.503
ANK-0.491
Token Continue
Token ID10054
Feature activation-4.65e+00

Pos logit contributions
jad+4.892
 Unloaded+4.469
estial+4.399
orem+4.294
cious+4.188
Neg logit contributions
 Psychiat-7.180
yne-6.615
 Amend-6.139
nee-6.073
anche-5.989
Token reading
Token ID3555
Feature activation-3.61e+00

Pos logit contributions
jad+3.611
estial+3.336
 Unloaded+3.272
cious+3.267
orem+3.227
Neg logit contributions
 Psychiat-3.590
yne-3.149
 Amend-3.054
nee-2.944
ANK-2.886
Token the
Token ID262
Feature activation-1.12e+01

Pos logit contributions
jad+2.574
estial+2.389
 Unloaded+2.336
cious+2.318
orem+2.291
Neg logit contributions
 Psychiat-3.036
yne-2.701
 Amend-2.604
nee-2.521
anche-2.486
Token main
Token ID1388
Feature activation-1.59e+01

Pos logit contributions
jad+5.471
orem+4.690
 missionary+4.630
estial+4.603
cious+4.526
Neg logit contributions
 Psychiat-11.375
yne-10.189
 Amend-9.865
nee-9.618
ANK-9.512
Token story
Token ID1621
Feature activation-9.27e+00

Pos logit contributions
jad+6.957
 missionary+6.052
cious+5.919
 Unloaded+5.730
cape+5.693
Neg logit contributions
 Psychiat-15.477
yne-14.313
 Amend-13.929
nee-13.505
ANK-13.148
Token
Token ID198
Feature activation+1.65e-01

Pos logit contributions
jad+5.541
 Unloaded+5.275
cious+4.914
cape+4.889
estial+4.784
Neg logit contributions
 Psychiat-7.910
yne-7.552
anche-7.131
 Amend-6.901
agons-6.744
Token
Token ID198
Feature activation+3.55e-02

Pos logit contributions
 Psychiat+0.126
yne+0.112
 Amend+0.107
nee+0.104
ANK+0.102
Neg logit contributions
jad-0.131
estial-0.125
 Unloaded-0.120
cious-0.119
orem-0.118
Token
Token ID447
Feature activation-2.47e+00

Pos logit contributions
 Psychiat+0.028
yne+0.025
 Amend+0.024
nee+0.023
ANK+0.023
Neg logit contributions
jad-0.027
estial-0.026
 Unloaded-0.025
orem-0.025
cious-0.025
Token
Token ID250
Feature activation-1.71e+00

Pos logit contributions
jad+1.972
estial+1.886
 Unloaded+1.802
cious+1.791
orem+1.786
Neg logit contributions
 Psychiat-1.868
yne-1.650
 Amend-1.576
nee-1.543
ANK-1.496
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
jad+2.957
 Unloaded+2.720
estial+2.710
cious+2.644
orem+2.600
Neg logit contributions
 Psychiat-3.475
yne-3.148
 Amend-3.026
anche-2.894
nee-2.868
TokenAdvertisement
Token ID4723
Feature activation-8.40e+00

Pos logit contributions
jad+0.972
estial+0.924
 Unloaded+0.879
cious+0.871
orem+0.869
Neg logit contributions
 Psychiat-1.135
yne-1.016
 Amend-0.977
nee-0.955
ANK-0.932
Token Continue
Token ID10054
Feature activation-7.52e+00

Pos logit contributions
jad+5.090
 Unloaded+4.630
estial+4.608
orem+4.577
cious+4.460
Neg logit contributions
 Psychiat-7.530
yne-6.922
 Amend-6.538
nee-6.313
ANK-6.280
Token reading
Token ID3555
Feature activation-3.74e+00

Pos logit contributions
jad+5.410
estial+4.963
cious+4.909
 Unloaded+4.901
cape+4.848
Neg logit contributions
 Psychiat-6.005
yne-5.291
 Amend-5.125
nee-4.962
ANK-4.858
Token the
Token ID262
Feature activation-8.02e+00

Pos logit contributions
jad+2.680
estial+2.509
 Unloaded+2.435
cious+2.423
orem+2.410
Neg logit contributions
 Psychiat-3.113
yne-2.770
 Amend-2.664
nee-2.591
anche-2.537
Token main
Token ID1388
Feature activation-1.57e+01

Pos logit contributions
jad+4.404
orem+3.958
estial+3.943
 Unloaded+3.779
cious+3.761
Neg logit contributions
 Psychiat-7.876
yne-7.055
 Amend-6.851
nee-6.662
ANK-6.573
Token story
Token ID1621
Feature activation-8.63e+00

Pos logit contributions
jad+7.003
 missionary+6.043
cious+5.967
 Unloaded+5.896
cape+5.887
Neg logit contributions
 Psychiat-15.058
yne-13.843
 Amend-13.530
nee-13.042
ANK-12.730
Token
Token ID198
Feature activation-5.72e-01

Pos logit contributions
jad+5.271
 Unloaded+5.016
cious+4.682
cape+4.661
estial+4.613
Neg logit contributions
 Psychiat-7.306
yne-6.963
anche-6.542
 Amend-6.355
agons-6.201
Token
Token ID198
Feature activation+2.45e-01

Pos logit contributions
jad+0.446
estial+0.423
 Unloaded+0.409
cious+0.404
orem+0.402
Neg logit contributions
 Psychiat-0.444
yne-0.395
 Amend-0.378
nee-0.367
ANK-0.359
TokenWhen
Token ID2215
Feature activation+2.63e+00

Pos logit contributions
 Psychiat+0.188
yne+0.167
 Amend+0.159
nee+0.157
ANK+0.154
Neg logit contributions
jad-0.192
estial-0.185
 Unloaded-0.176
orem-0.175
cious-0.175
Token it
Token ID340
Feature activation-3.51e+00

Pos logit contributions
 Psychiat+1.958
yne+1.711
 Amend+1.650
nee+1.583
ight+1.572
Neg logit contributions
jad-2.121
estial-2.056
 Unloaded-1.939
orem-1.925
cious-1.920
Token can
Token ID460
Feature activation-3.07e+00

Pos logit contributions
 Psychiat+0.343
yne+0.306
 Amend+0.292
nee+0.287
ight+0.279
Neg logit contributions
jad-0.354
estial-0.339
 Unloaded-0.324
cious-0.321
orem-0.320
Token be
Token ID307
Feature activation-3.03e+00

Pos logit contributions
jad+2.315
estial+2.200
 Unloaded+2.098
orem+2.089
cious+2.085
Neg logit contributions
 Psychiat-2.455
yne-2.154
 Amend-2.088
nee-2.015
ANK-1.985
Token used
Token ID973
Feature activation+3.79e-01

Pos logit contributions
jad+2.334
estial+2.213
 Unloaded+2.137
cious+2.111
orem+2.098
Neg logit contributions
 Psychiat-2.372
yne-2.085
 Amend-2.008
nee-1.951
ANK-1.908
Token across
Token ID1973
Feature activation-3.70e+00

Pos logit contributions
 Psychiat+0.271
yne+0.242
 Amend+0.227
nee+0.226
ight+0.218
Neg logit contributions
jad-0.317
estial-0.307
orem-0.291
cious-0.291
 Unloaded-0.290
Token a
Token ID257
Feature activation-4.10e+00

Pos logit contributions
jad+2.840
estial+2.699
 Unloaded+2.592
cious+2.564
orem+2.549
Neg logit contributions
 Psychiat-2.906
yne-2.548
 Amend-2.451
nee-2.376
ANK-2.333
Token wide
Token ID3094
Feature activation-1.57e+01

Pos logit contributions
jad+3.434
estial+3.275
 Unloaded+3.161
cious+3.128
orem+3.088
Neg logit contributions
 Psychiat-2.928
yne-2.543
 Amend-2.462
nee-2.353
ANK-2.324
Token range
Token ID2837
Feature activation-2.35e+00

Pos logit contributions
jad+9.056
estial+8.494
 missionary+8.417
 Unloaded+8.175
cious+8.055
Neg logit contributions
 Psychiat-13.090
yne-11.329
 Amend-11.103
ANK-10.824
nee-10.584
Token of
Token ID286
Feature activation-4.37e+00

Pos logit contributions
jad+1.883
estial+1.794
 Unloaded+1.725
cious+1.707
orem+1.699
Neg logit contributions
 Psychiat-1.774
yne-1.555
 Amend-1.498
nee-1.456
ANK-1.419
Token temperatures
Token ID10101
Feature activation+3.09e-01

Pos logit contributions
jad+3.357
estial+3.182
 Unloaded+3.054
cious+3.024
orem+3.016
Neg logit contributions
 Psychiat-3.416
yne-2.986
 Amend-2.882
nee-2.807
ANK-2.737
Token.
Token ID13
Feature activation-2.32e+00

Pos logit contributions
 Psychiat+0.228
yne+0.203
 Amend+0.193
nee+0.189
ight+0.184
Neg logit contributions
jad-0.251
estial-0.242
 Unloaded-0.230
orem-0.230
cious-0.228
Token But
Token ID887
Feature activation+1.03e+00

Pos logit contributions
jad+1.766
estial+1.680
 Unloaded+1.616
orem+1.592
cious+1.591
Neg logit contributions
 Psychiat-1.840
yne-1.637
 Amend-1.564
nee-1.533
ANK-1.497
Tokenic
Token ID291
Feature activation-2.17e-01

Pos logit contributions
jad+0.987
estial+0.947
 Unloaded+0.907
cious+0.902
orem+0.900
Neg logit contributions
 Psychiat-0.809
yne-0.706
 Amend-0.673
nee-0.657
ANK-0.637
Token),
Token ID828
Feature activation+3.63e-01

Pos logit contributions
jad+0.175
estial+0.168
 Unloaded+0.160
orem+0.159
cious+0.159
Neg logit contributions
 Psychiat-0.162
yne-0.143
 Amend-0.137
nee-0.134
ANK-0.130
Token which
Token ID543
Feature activation+1.64e+00

Pos logit contributions
 Psychiat+0.281
yne+0.248
 Amend+0.240
nee+0.233
ANK+0.227
Neg logit contributions
jad-0.286
estial-0.274
 Unloaded-0.259
orem-0.258
cious-0.258
Token carries
Token ID10732
Feature activation-2.87e+00

Pos logit contributions
 Psychiat+1.182
yne+1.034
 Amend+1.008
nee+0.970
ight+0.942
Neg logit contributions
jad-1.356
estial-1.306
cious-1.241
 Unloaded-1.238
orem-1.235
Token a
Token ID257
Feature activation-3.67e+00

Pos logit contributions
jad+2.280
estial+2.179
 Unloaded+2.083
cious+2.061
orem+2.055
Neg logit contributions
 Psychiat-2.193
yne-1.940
 Amend-1.850
nee-1.812
ANK-1.769
Token maximum
Token ID5415
Feature activation-1.55e+01

Pos logit contributions
jad+3.303
estial+3.165
 Unloaded+3.054
cious+3.021
orem+3.017
Neg logit contributions
 Psychiat-2.396
yne-2.081
 Amend-1.962
nee-1.909
ANK-1.873
Token penalty
Token ID7389
Feature activation-2.06e-01

Pos logit contributions
jad+8.574
 Unloaded+7.597
estial+7.555
 missionary+7.363
cious+7.249
Neg logit contributions
 Psychiat-13.536
yne-12.060
ANK-11.545
 Amend-11.475
nee-11.286
Token of
Token ID286
Feature activation-9.48e+00

Pos logit contributions
jad+0.172
estial+0.165
 Unloaded+0.158
cious+0.157
orem+0.157
Neg logit contributions
 Psychiat-0.148
yne-0.131
 Amend-0.125
nee-0.122
ANK-0.118
Token 10
Token ID838
Feature activation-9.85e+00

Pos logit contributions
jad+6.167
 Unloaded+5.720
 missionary+5.652
estial+5.603
cious+5.447
Neg logit contributions
 Psychiat-7.792
yne-7.197
 Amend-6.765
ANK-6.606
nee-6.546
Token years
Token ID812
Feature activation-1.01e+01

Pos logit contributions
jad+6.613
estial+6.141
 Unloaded+5.969
cious+5.941
orem+5.858
Neg logit contributions
 Psychiat-8.015
yne-7.284
 Amend-7.004
ANK-6.752
nee-6.720
Token imprisonment
Token ID16510
Feature activation+8.10e-01

Pos logit contributions
jad+6.554
estial+5.975
 Unloaded+5.891
 missionary+5.759
cious+5.639
Neg logit contributions
 Psychiat-8.499
yne-7.843
 Amend-7.411
nee-7.221
ANK-7.106
Token American
Token ID1605
Feature activation+2.64e+00

Pos logit contributions
 Psychiat+0.156
yne+0.138
 Amend+0.133
nee+0.129
ANK+0.126
Neg logit contributions
jad-0.155
estial-0.148
 Unloaded-0.141
cious-0.140
orem-0.139
Token economy
Token ID3773
Feature activation-2.45e+00

Pos logit contributions
 Psychiat+1.980
yne+1.706
 Amend+1.671
nee+1.628
ight+1.576
Neg logit contributions
jad-2.140
estial-2.036
 Unloaded-1.951
orem-1.937
cious-1.935
Token and
Token ID290
Feature activation-1.76e+00

Pos logit contributions
jad+1.975
estial+1.892
 Unloaded+1.809
cious+1.794
orem+1.789
Neg logit contributions
 Psychiat-1.839
yne-1.621
 Amend-1.549
nee-1.516
ANK-1.468
Token a
Token ID257
Feature activation+1.89e-01

Pos logit contributions
jad+1.383
estial+1.322
 Unloaded+1.263
cious+1.252
orem+1.250
Neg logit contributions
 Psychiat-1.359
yne-1.204
 Amend-1.152
nee-1.129
ANK-1.097
Token Supreme
Token ID5617
Feature activation+1.56e+00

Pos logit contributions
 Psychiat+0.141
yne+0.124
 Amend+0.119
nee+0.116
ight+0.113
Neg logit contributions
jad-0.153
estial-0.147
 Unloaded-0.140
orem-0.140
cious-0.139
Token Court
Token ID3078
Feature activation+1.34e+01

Pos logit contributions
 Psychiat+1.513
yne+1.370
 Amend+1.333
nee+1.307
ANK+1.273
Neg logit contributions
jad-0.926
estial-0.879
 Unloaded-0.812
cious-0.810
orem-0.808
Token remotely
Token ID19863
Feature activation+1.91e+00

Pos logit contributions
 Psychiat+8.687
 Amend+7.241
ight+7.088
yne+7.061
nee+6.914
Neg logit contributions
estial-10.597
jad-10.568
orem-10.107
 Unloaded-9.775
regor-9.577
Token sympathetic
Token ID22335
Feature activation+6.75e+00

Pos logit contributions
 Psychiat+1.349
yne+1.166
 Amend+1.139
nee+1.099
ight+1.081
Neg logit contributions
jad-1.611
estial-1.542
 Unloaded-1.482
orem-1.475
cious-1.469
Token to
Token ID284
Feature activation+2.87e+00

Pos logit contributions
 Psychiat+4.325
yne+3.753
nee+3.595
 Amend+3.570
ight+3.421
Neg logit contributions
jad-5.810
estial-5.687
 Unloaded-5.544
cious-5.444
orem-5.396
Token organized
Token ID8389
Feature activation+3.81e+00

Pos logit contributions
 Psychiat+2.118
yne+1.837
 Amend+1.809
nee+1.730
ight+1.707
Neg logit contributions
jad-2.324
estial-2.257
 Unloaded-2.146
cious-2.132
orem-2.114
Token labor
Token ID4827
Feature activation+6.00e-01

Pos logit contributions
 Psychiat+2.612
yne+2.261
 Amend+2.182
nee+2.107
ight+2.059
Neg logit contributions
jad-3.312
estial-3.172
 Unloaded-3.045
cious-3.018
orem-3.016
Token(
Token ID7
Feature activation-3.33e+00

Pos logit contributions
 Psychiat+0.392
yne+0.342
 Amend+0.325
nee+0.316
ANK+0.309
Neg logit contributions
jad-0.512
estial-0.493
 Unloaded-0.473
orem-0.468
cious-0.468
Tokenit
Token ID270
Feature activation-6.35e+00

Pos logit contributions
jad+3.388
estial+3.258
 Unloaded+3.151
cious+3.151
orem+3.133
Neg logit contributions
 Psychiat-1.791
yne-1.495
 Amend-1.412
nee-1.346
ANK-1.289
Token->
Token ID3784
Feature activation+4.00e+00

Pos logit contributions
jad+3.517
 Unloaded+3.184
estial+3.174
cape+3.047
cious+3.012
Neg logit contributions
 Psychiat-6.205
yne-5.625
 Amend-5.561
anche-5.286
ANK-5.196
Tokenvec
Token ID35138
Feature activation-6.30e+00

Pos logit contributions
 Psychiat+3.136
yne+2.878
nee+2.693
 Amend+2.639
ight+2.629
Neg logit contributions
jad-2.965
estial-2.875
 Unloaded-2.739
 missionary-2.657
orem-2.649
Token()
Token ID3419
Feature activation-9.42e+00

Pos logit contributions
jad+3.431
 Unloaded+3.081
estial+3.018
cious+2.857
orem+2.841
Neg logit contributions
 Psychiat-6.356
yne-5.732
 Amend-5.711
nee-5.330
anche-5.320
Token->
Token ID3784
Feature activation+1.43e+01

Pos logit contributions
jad+4.525
 Unloaded+4.304
cape+4.017
estial+3.947
cious+3.823
Neg logit contributions
 Psychiat-9.326
yne-8.698
 Amend-8.444
anche-8.277
nee-7.956
Tokenz
Token ID89
Feature activation-4.15e+00

Pos logit contributions
yne+8.449
 Psychiat+8.442
nee+7.828
ight+7.738
anche+7.207
Neg logit contributions
estial-10.895
jad-10.771
 missionary-10.314
 Unloaded-10.213
orem-9.897
Token()
Token ID3419
Feature activation-5.91e+00

Pos logit contributions
jad+2.428
estial+2.235
 Unloaded+2.195
orem+2.092
cious+2.087
Neg logit contributions
 Psychiat-4.024
yne-3.644
 Amend-3.586
nee-3.396
ANK-3.343
Token ==
Token ID6624
Feature activation-5.74e+00

Pos logit contributions
jad+2.841
 Unloaded+2.734
estial+2.532
cape+2.442
orem+2.375
Neg logit contributions
 Psychiat-6.108
yne-5.662
 Amend-5.476
anche-5.318
nee-5.276
Token 0
Token ID657
Feature activation-2.77e+00

Pos logit contributions
jad+3.344
 Unloaded+3.070
estial+3.068
cious+2.930
orem+2.904
Neg logit contributions
 Psychiat-5.443
yne-4.929
 Amend-4.819
nee-4.714
ANK-4.566
Token.
Token ID13
Feature activation-3.79e+00

Pos logit contributions
jad+2.090
estial+1.955
 Unloaded+1.919
cious+1.879
orem+1.858
Neg logit contributions
 Psychiat-2.214
yne-1.966
 Amend-1.913
nee-1.820
anche-1.797
Token
Token ID198
Feature activation+8.84e-01

Pos logit contributions
jad+1.183
estial+1.112
 Unloaded+1.078
cious+1.066
orem+1.058
Neg logit contributions
 Psychiat-1.224
yne-1.092
 Amend-1.044
nee-1.009
anche-0.994
TokenMy
Token ID3666
Feature activation-5.12e-01

Pos logit contributions
 Psychiat+0.638
yne+0.563
 Amend+0.534
nee+0.533
ANK+0.515
Neg logit contributions
jad-0.734
estial-0.708
 Unloaded-0.681
cious-0.670
orem-0.669
Tokeners
Token ID364
Feature activation+5.95e+00

Pos logit contributions
jad+0.388
estial+0.371
 Unloaded+0.353
cious+0.350
orem+0.349
Neg logit contributions
 Psychiat-0.409
yne-0.364
 Amend-0.349
nee-0.342
ANK-0.333
Token,
Token ID11
Feature activation+6.24e+00

Pos logit contributions
 Psychiat+3.913
yne+3.449
 Amend+3.240
nee+3.204
ight+3.181
Neg logit contributions
jad-5.071
estial-4.987
 Unloaded-4.824
orem-4.698
cious-4.695
Token D
Token ID360
Feature activation+2.31e+00

Pos logit contributions
 Psychiat+4.018
yne+3.381
 Amend+3.329
nee+3.217
ANK+3.048
Neg logit contributions
jad-5.597
estial-5.573
orem-5.235
cious-5.193
 Unloaded-5.116
Token.
Token ID13
Feature activation+1.26e+01

Pos logit contributions
 Psychiat+1.598
yne+1.414
 Amend+1.327
nee+1.316
ight+1.268
Neg logit contributions
jad-1.962
estial-1.899
 Unloaded-1.830
cious-1.806
orem-1.792
Token (
Token ID357
Feature activation-8.79e-01

Pos logit contributions
 Psychiat+7.110
yne+5.588
 Amend+5.556
nee+5.493
 Lob+5.161
Neg logit contributions
estial-11.721
jad-11.345
jriwal-11.193
orem-10.854
wcs-10.729
Token 2007
Token ID4343
Feature activation+2.45e+00

Pos logit contributions
jad+0.613
estial+0.583
 Unloaded+0.553
cious+0.548
orem+0.546
Neg logit contributions
 Psychiat-0.756
yne-0.679
 Amend-0.653
nee-0.640
ANK-0.626
Token ).
Token ID6739
Feature activation+9.84e-01

Pos logit contributions
 Psychiat+1.971
yne+1.744
 Amend+1.682
nee+1.653
ANK+1.598
Neg logit contributions
jad-1.825
estial-1.763
 Unloaded-1.662
cious-1.662
orem-1.658
Token Psychology
Token ID18430
Feature activation-6.14e-01

Pos logit contributions
 Psychiat+0.760
yne+0.657
 Amend+0.640
nee+0.620
ANK+0.601
Neg logit contributions
jad-0.782
estial-0.757
cious-0.713
orem-0.711
 Unloaded-0.711
Token:
Token ID25
Feature activation+7.83e-01

Pos logit contributions
jad+0.503
estial+0.483
 Unloaded+0.460
cious+0.457
orem+0.457
Neg logit contributions
 Psychiat-0.456
yne-0.401
 Amend-0.383
nee-0.374
ANK-0.363
Token rely
Token ID8814
Feature activation-8.16e-01

Pos logit contributions
 Psychiat+4.845
yne+4.309
 Amend+4.002
nee+3.934
ight+3.926
Neg logit contributions
estial-6.895
jad-6.888
 Unloaded-6.532
cious-6.426
orem-6.249
Token on
Token ID319
Feature activation+8.11e+00

Pos logit contributions
jad+0.624
estial+0.596
 Unloaded+0.568
cious+0.564
orem+0.563
Neg logit contributions
 Psychiat-0.646
yne-0.574
 Amend-0.551
nee-0.539
ANK-0.525
Token stored
Token ID8574
Feature activation+4.97e+00

Pos logit contributions
 Psychiat+5.097
yne+4.480
 Amend+4.192
ight+4.015
nee+3.993
Neg logit contributions
jad-7.160
estial-7.046
 Unloaded-6.607
cious-6.561
orem-6.482
Token body
Token ID1767
Feature activation+5.36e+00

Pos logit contributions
 Psychiat+3.014
yne+2.656
 Amend+2.460
nee+2.396
ight+2.364
Neg logit contributions
jad-4.615
estial-4.477
 Unloaded-4.288
orem-4.235
cious-4.212
Token fat
Token ID3735
Feature activation+3.67e+00

Pos logit contributions
 Psychiat+2.959
yne+2.542
 Amend+2.336
nee+2.311
ANK+2.276
Neg logit contributions
jad-5.200
estial-5.085
 Unloaded-4.860
orem-4.849
cious-4.778
Token for
Token ID329
Feature activation+1.21e+01

Pos logit contributions
 Psychiat+2.508
yne+2.219
 Amend+2.060
ight+2.041
nee+2.029
Neg logit contributions
jad-3.126
estial-3.048
 Unloaded-2.885
cious-2.869
orem-2.856
Token fuel
Token ID5252
Feature activation+8.29e+00

Pos logit contributions
 Psychiat+5.714
yne+5.031
ight+4.585
 Amend+4.402
ANK+4.270
Neg logit contributions
estial-11.645
jad-11.645
cious-10.898
 Unloaded-10.872
orem-10.683
Token.
Token ID13
Feature activation+7.58e+00

Pos logit contributions
 Psychiat+5.097
yne+4.556
ight+4.219
ANK+4.151
anche+4.103
Neg logit contributions
jad-7.163
estial-7.069
cious-6.653
 Unloaded-6.640
orem-6.536
Token You
Token ID921
Feature activation+7.69e+00

Pos logit contributions
 Psychiat+5.200
 Amend+4.313
yne+4.271
nee+4.041
ight+3.956
Neg logit contributions
jad-6.411
estial-6.351
cious-5.983
 Unloaded-5.837
orem-5.800
Token will
Token ID481
Feature activation+2.89e+00

Pos logit contributions
 Psychiat+4.997
yne+4.440
 Amend+4.249
nee+4.212
ight+4.125
Neg logit contributions
jad-6.443
estial-6.376
 Unloaded-6.148
cious-5.960
orem-5.945
Token always
Token ID1464
Feature activation+3.56e+00

Pos logit contributions
 Psychiat+2.101
yne+1.861
 Amend+1.789
nee+1.763
ight+1.710
Neg logit contributions
jad-2.347
estial-2.291
 Unloaded-2.185
cious-2.153
orem-2.127
Token.
Token ID13
Feature activation+4.22e+00

Pos logit contributions
 Psychiat+0.057
yne+0.051
 Amend+0.048
nee+0.047
ANK+0.046
Neg logit contributions
jad-0.063
estial-0.060
 Unloaded-0.057
cious-0.057
orem-0.057
Token
Token ID198
Feature activation+2.81e+00

Pos logit contributions
 Psychiat+3.058
yne+2.633
 Amend+2.589
nee+2.454
ight+2.412
Neg logit contributions
jad-3.437
estial-3.375
orem-3.155
 Unloaded-3.128
cious-3.124
Token
Token ID198
Feature activation+3.29e+00

Pos logit contributions
 Psychiat+2.000
yne+1.745
 Amend+1.668
nee+1.654
ANK+1.594
Neg logit contributions
jad-2.348
estial-2.295
orem-2.164
 Unloaded-2.157
cious-2.153
TokenThe
Token ID464
Feature activation+8.14e+00

Pos logit contributions
 Psychiat+2.431
yne+2.135
 Amend+2.043
nee+2.028
ANK+2.015
Neg logit contributions
jad-2.613
estial-2.567
 Unloaded-2.432
orem-2.418
 missionary-2.395
Token high
Token ID1029
Feature activation+1.04e+00

Pos logit contributions
 Psychiat+5.569
yne+4.922
 Amend+4.738
nee+4.506
ANK+4.454
Neg logit contributions
jad-6.612
estial-6.534
cious-6.025
 Unloaded-6.020
orem-6.004
Token court
Token ID2184
Feature activation+1.33e+01

Pos logit contributions
 Psychiat+0.783
yne+0.691
 Amend+0.664
nee+0.650
ANK+0.631
Neg logit contributions
jad-0.827
estial-0.798
 Unloaded-0.760
orem-0.758
cious-0.755
Token had
Token ID550
Feature activation+1.05e+01

Pos logit contributions
 Psychiat+7.016
 Amend+6.127
yne+5.925
anche+5.721
ight+5.575
Neg logit contributions
estial-11.907
jad-11.538
orem-11.147
cious-10.984
 Unloaded-10.843
Token also
Token ID635
Feature activation+9.28e+00

Pos logit contributions
 Psychiat+6.060
yne+5.275
 Amend+5.275
ight+4.917
nee+4.906
Neg logit contributions
estial-9.207
jad-9.013
orem-8.570
cious-8.422
 Unloaded-8.314
Token directed
Token ID7924
Feature activation+1.19e+00

Pos logit contributions
 Psychiat+5.716
yne+5.029
 Amend+5.000
nee+4.739
ight+4.645
Neg logit contributions
estial-7.897
jad-7.824
orem-7.426
cious-7.278
 Unloaded-7.178
Token Gh
Token ID11972
Feature activation+5.34e+00

Pos logit contributions
 Psychiat+0.913
yne+0.809
 Amend+0.782
nee+0.750
ANK+0.737
Neg logit contributions
jad-0.933
estial-0.901
 Unloaded-0.848
orem-0.847
cious-0.846
Tokenai
Token ID1872
Feature activation+2.63e+00

Pos logit contributions
 Psychiat+3.589
yne+3.241
nee+3.064
ight+2.960
 Amend+2.938
Neg logit contributions
estial-4.474
jad-4.438
 Unloaded-4.203
orem-4.173
cious-4.172
Token Bo
Token ID3248
Feature activation-2.47e+00

Pos logit contributions
 Psychiat+1.722
yne+1.516
 Amend+1.469
nee+1.421
ight+1.387
Neg logit contributions
jad-1.767
estial-1.708
 Unloaded-1.609
orem-1.601
cious-1.590
Tokena
Token ID64
Feature activation-1.37e+00

Pos logit contributions
jad+2.272
estial+2.179
 Unloaded+2.094
orem+2.083
cious+2.083
Neg logit contributions
 Psychiat-1.584
yne-1.359
 Amend-1.295
nee-1.255
ANK-1.219
Token Vista
Token ID25160
Feature activation+1.04e+00

Pos logit contributions
jad+1.061
estial+1.014
 Unloaded+0.967
cious+0.960
orem+0.958
Neg logit contributions
 Psychiat-1.071
yne-0.949
 Amend-0.910
nee-0.891
ANK-0.867
Token,
Token ID11
Feature activation+1.84e+00

Pos logit contributions
 Psychiat+0.767
yne+0.675
 Amend+0.643
nee+0.630
ight+0.614
Neg logit contributions
jad-0.849
estial-0.820
orem-0.774
 Unloaded-0.773
cious-0.770
Token Cape
Token ID15725
Feature activation+3.14e+00

Pos logit contributions
 Psychiat+1.396
yne+1.226
 Amend+1.182
nee+1.148
ight+1.123
Neg logit contributions
jad-1.472
estial-1.418
orem-1.332
 Unloaded-1.331
cious-1.325
Token Ver
Token ID4643
Feature activation+7.22e+00

Pos logit contributions
 Psychiat+2.413
yne+2.143
 Amend+2.065
nee+1.990
ight+1.944
Neg logit contributions
jad-2.449
estial-2.366
orem-2.247
 Unloaded-2.237
cious-2.219
Tokende
Token ID2934
Feature activation+3.27e+00

Pos logit contributions
 Psychiat+4.076
yne+3.405
nee+3.272
 Amend+3.113
anche+3.045
Neg logit contributions
jad-7.041
estial-6.956
 Unloaded-6.663
cious-6.549
cape-6.472
Token,
Token ID11
Feature activation-2.72e-01

Pos logit contributions
 Psychiat+2.374
yne+2.102
 Amend+1.983
nee+1.961
ight+1.905
Neg logit contributions
jad-2.694
estial-2.611
orem-2.468
 Unloaded-2.457
cious-2.427
Token from
Token ID422
Feature activation+4.22e+00

Pos logit contributions
jad+0.214
estial+0.205
 Unloaded+0.195
cious+0.193
orem+0.193
Neg logit contributions
 Psychiat-0.210
yne-0.186
 Amend-0.179
nee-0.174
ANK-0.170
Token £
Token ID4248
Feature activation+4.30e+00

Pos logit contributions
 Psychiat+2.760
yne+2.384
 Amend+2.259
nee+2.217
ight+2.133
Neg logit contributions
jad-3.773
estial-3.612
 Unloaded-3.429
orem-3.429
cious-3.362
Token9
Token ID24
Feature activation+2.29e+00

Pos logit contributions
 Psychiat+2.865
yne+2.474
nee+2.326
 Amend+2.314
ANK+2.269
Neg logit contributions
jad-3.725
estial-3.627
orem-3.474
 Unloaded-3.451
cious-3.441
Token visitors
Token ID9692
Feature activation-5.23e-02

Pos logit contributions
 Psychiat+0.652
yne+0.579
 Amend+0.561
nee+0.546
ight+0.532
Neg logit contributions
jad-0.578
estial-0.554
 Unloaded-0.523
cious-0.521
orem-0.518
Token'
Token ID6
Feature activation-3.37e+00

Pos logit contributions
jad+0.035
estial+0.033
 Unloaded+0.032
cious+0.031
orem+0.031
Neg logit contributions
 Psychiat-0.046
yne-0.042
 Amend-0.040
nee-0.039
ight-0.038
Token locker
Token ID17355
Feature activation-3.06e+00

Pos logit contributions
jad+2.043
estial+1.932
 Unloaded+1.825
orem+1.812
cious+1.806
Neg logit contributions
 Psychiat-3.169
yne-2.868
 Amend-2.767
nee-2.731
ANK-2.685
Token room
Token ID2119
Feature activation+3.23e-01

Pos logit contributions
jad+2.302
estial+2.186
 Unloaded+2.095
cious+2.081
orem+2.070
Neg logit contributions
 Psychiat-2.458
yne-2.174
 Amend-2.100
nee-2.061
ANK-2.002
Token with
Token ID351
Feature activation-1.11e+00

Pos logit contributions
 Psychiat+0.238
yne+0.209
 Amend+0.200
nee+0.195
ight+0.190
Neg logit contributions
jad-0.265
estial-0.255
 Unloaded-0.243
orem-0.242
cious-0.241
Token the
Token ID262
Feature activation+6.27e+00

Pos logit contributions
jad+0.889
estial+0.851
 Unloaded+0.813
cious+0.807
orem+0.806
Neg logit contributions
 Psychiat-0.835
yne-0.737
 Amend-0.705
nee-0.689
ANK-0.671
Token Chicago
Token ID4842
Feature activation+4.15e+00

Pos logit contributions
 Psychiat+4.810
yne+4.124
 Amend+4.110
nee+3.919
ight+3.874
Neg logit contributions
jad-4.771
estial-4.679
 Unloaded-4.435
cious-4.348
orem-4.301
Token Blackhawks
Token ID35663
Feature activation+6.56e+00

Pos logit contributions
 Psychiat+2.396
yne+1.982
 Amend+1.900
nee+1.826
ight+1.805
Neg logit contributions
jad-4.003
estial-3.910
cious-3.783
 Unloaded-3.746
orem-3.691
Token.
Token ID13
Feature activation+2.76e+00

Pos logit contributions
 Psychiat+4.640
yne+4.019
 Amend+3.828
nee+3.766
ight+3.735
Neg logit contributions
jad-5.333
estial-5.205
 Unloaded-5.007
orem-4.937
cious-4.897
Token
Token ID198
Feature activation-1.43e+00

Pos logit contributions
 Psychiat+2.016
 Amend+1.691
yne+1.688
nee+1.634
ANK+1.574
Neg logit contributions
jad-2.314
estial-2.264
orem-2.142
cious-2.127
 missionary-2.087
Token
Token ID198
Feature activation+5.28e+00

Pos logit contributions
jad+1.082
estial+1.016
 Unloaded+0.991
cious+0.976
orem+0.965
Neg logit contributions
 Psychiat-1.142
yne-1.016
 Amend-0.977
nee-0.939
anche-0.923
Token He
Token ID679
Feature activation+8.29e-03

Pos logit contributions
 Psychiat+4.998
 Amend+4.232
yne+4.071
nee+3.859
ight+3.856
Neg logit contributions
jad-6.213
estial-6.055
 Unloaded-5.712
orem-5.704
cious-5.592
Tokeniko
Token ID12125
Feature activation+1.62e+00

Pos logit contributions
 Psychiat+0.007
yne+0.006
 Amend+0.006
nee+0.005
ANK+0.005
Neg logit contributions
jad-0.006
estial-0.006
 Unloaded-0.006
cious-0.006
orem-0.006
Token Ma
Token ID6669
Feature activation-3.45e+00

Pos logit contributions
 Psychiat+1.373
 Amend+1.219
yne+1.208
nee+1.159
ight+1.135
Neg logit contributions
jad-1.151
estial-1.129
 Unloaded-1.041
cious-1.039
orem-1.035
Tokenas
Token ID292
Feature activation-2.99e+00

Pos logit contributions
jad+2.760
estial+2.601
 Unloaded+2.535
orem+2.522
cious+2.500
Neg logit contributions
 Psychiat-2.594
yne-2.267
 Amend-2.204
nee-2.129
ANK-2.074
Token,
Token ID11
Feature activation+2.45e+00

Pos logit contributions
jad+2.420
estial+2.307
 Unloaded+2.213
cious+2.196
orem+2.195
Neg logit contributions
 Psychiat-2.240
yne-1.976
 Amend-1.892
nee-1.843
ANK-1.797
Token an
Token ID281
Feature activation+6.60e+00

Pos logit contributions
 Psychiat+1.764
yne+1.532
 Amend+1.474
nee+1.438
ANK+1.400
Neg logit contributions
jad-2.043
estial-1.987
 Unloaded-1.877
orem-1.871
cious-1.860
Token "
Token ID366
Feature activation+5.20e+00

Pos logit contributions
 Psychiat+4.535
yne+3.968
 Amend+3.918
nee+3.737
ANK+3.671
Neg logit contributions
jad-5.552
estial-5.466
cious-5.107
 Unloaded-4.955
orem-4.909
Tokenattack
Token ID20358
Feature activation+5.38e-01

Pos logit contributions
 Psychiat+3.953
yne+3.617
nee+3.448
ANK+3.377
 Amend+3.377
Neg logit contributions
jad-3.893
estial-3.847
 Unloaded-3.602
cious-3.549
orem-3.518
Token on
Token ID319
Feature activation+2.36e+00

Pos logit contributions
 Psychiat+0.409
yne+0.360
 Amend+0.345
nee+0.339
ight+0.328
Neg logit contributions
jad-0.428
estial-0.412
 Unloaded-0.392
cious-0.389
orem-0.386
Token our
Token ID674
Feature activation+3.41e+00

Pos logit contributions
 Psychiat+1.716
yne+1.487
 Amend+1.451
nee+1.400
ight+1.361
Neg logit contributions
jad-1.955
estial-1.903
 Unloaded-1.799
cious-1.787
orem-1.770
Token democracy
Token ID7996
Feature activation+3.66e+00

Pos logit contributions
 Psychiat+2.429
yne+2.093
 Amend+2.038
nee+1.971
ight+1.920
Neg logit contributions
jad-2.861
estial-2.780
 Unloaded-2.635
cious-2.599
orem-2.589
Token at
Token ID379
Feature activation+1.94e+00

Pos logit contributions
 Psychiat+2.597
yne+2.298
nee+2.163
 Amend+2.139
ight+2.110
Neg logit contributions
jad-3.162
estial-3.090
 Unloaded-2.941
orem-2.926
cious-2.894
Token a
Token ID257
Feature activation-7.27e-01

Pos logit contributions
 Psychiat+1.356
yne+1.176
 Amend+1.137
nee+1.108
ANK+1.070
Neg logit contributions
jad-1.644
estial-1.601
 Unloaded-1.528
orem-1.524
cious-1.518
Token time
Token ID640
Feature activation+2.19e+00

Pos logit contributions
jad+0.512
estial+0.490
 Unloaded+0.464
orem+0.459
cious+0.459
Neg logit contributions
 Psychiat-0.620
yne-0.555
 Amend-0.533
nee-0.524
ANK-0.511
Token.
Token ID13
Feature activation+1.42e+00

Pos logit contributions
 Psychiat+1.542
yne+1.350
nee+1.272
 Amend+1.269
ight+1.235
Neg logit contributions
jad-1.837
estial-1.791
 Unloaded-1.713
orem-1.709
cious-1.685
Token The
Token ID383
Feature activation+2.79e-01

Pos logit contributions
 Psychiat+1.104
yne+0.958
 Amend+0.934
nee+0.908
ANK+0.879
Neg logit contributions
jad-1.122
estial-1.087
cious-1.025
orem-1.019
 Unloaded-1.017
Token Chiefs
Token ID18733
Feature activation+2.83e+00

Pos logit contributions
 Psychiat+0.214
yne+0.189
 Amend+0.181
nee+0.177
ANK+0.172
Neg logit contributions
jad-0.220
estial-0.211
 Unloaded-0.202
cious-0.200
orem-0.198
Token play
Token ID711
Feature activation-1.13e+00

Pos logit contributions
 Psychiat+2.131
yne+1.867
 Amend+1.785
nee+1.769
ight+1.722
Neg logit contributions
jad-2.250
estial-2.171
 Unloaded-2.078
cious-2.067
orem-2.056
Token Ping
Token ID34263
Feature activation+7.05e-01

Pos logit contributions
jad+0.891
estial+0.853
 Unloaded+0.814
cious+0.807
orem+0.806
Neg logit contributions
 Psychiat-0.870
yne-0.770
 Amend-0.738
nee-0.722
ANK-0.702
Token-
Token ID12
Feature activation+3.58e+00

Pos logit contributions
 Psychiat+0.498
yne+0.435
 Amend+0.413
nee+0.408
ANK+0.393
Neg logit contributions
jad-0.600
estial-0.578
 Unloaded-0.552
cious-0.548
orem-0.547
TokenP
Token ID47
Feature activation+3.27e+00

Pos logit contributions
 Psychiat+2.326
yne+1.971
 Amend+1.902
nee+1.899
ANK+1.815
Neg logit contributions
jad-3.218
estial-3.113
 Unloaded-2.984
orem-2.970
cious-2.944
Tokenong
Token ID506
Feature activation+3.33e+00

Pos logit contributions
 Psychiat+1.860
yne+1.605
ight+1.472
nee+1.464
 Amend+1.441
Neg logit contributions
jad-3.169
estial-3.042
 Unloaded-2.968
orem-2.933
cious-2.923
Token a
Token ID257
Feature activation+2.16e+00

Pos logit contributions
 Psychiat+3.372
yne+2.929
 Amend+2.850
nee+2.712
ight+2.698
Neg logit contributions
jad-3.915
estial-3.777
 Unloaded-3.591
orem-3.588
cious-3.539
Token perceptual
Token ID49615
Feature activation+7.72e+00

Pos logit contributions
 Psychiat+1.537
yne+1.325
 Amend+1.268
nee+1.241
ight+1.214
Neg logit contributions
jad-1.837
estial-1.758
 Unloaded-1.686
orem-1.674
cious-1.650
Token shift
Token ID6482
Feature activation+3.56e+00

Pos logit contributions
 Psychiat+5.335
yne+4.567
 Amend+4.454
nee+4.347
ight+4.257
Neg logit contributions
jad-6.456
estial-6.222
orem-5.884
 Unloaded-5.882
cious-5.726
Token and
Token ID290
Feature activation+1.20e+00

Pos logit contributions
 Psychiat+2.492
yne+2.163
 Amend+2.048
nee+2.038
ight+2.010
Neg logit contributions
jad-3.005
estial-2.909
 Unloaded-2.783
orem-2.771
cious-2.767
Token B
Token ID347
Feature activation+2.39e+00

Pos logit contributions
 Psychiat+0.903
yne+0.794
 Amend+0.764
nee+0.738
ight+0.725
Neg logit contributions
jad-0.967
estial-0.928
 Unloaded-0.885
orem-0.880
cious-0.876
TokenAM
Token ID2390
Feature activation+5.10e+00

Pos logit contributions
 Psychiat+1.825
yne+1.623
 Amend+1.551
nee+1.523
ANK+1.507
Neg logit contributions
jad-1.873
estial-1.805
 Unloaded-1.727
cious-1.708
orem-1.681
Token!
Token ID0
Feature activation+3.22e+00

Pos logit contributions
 Psychiat+3.572
yne+3.062
 Amend+2.943
nee+2.931
ANK+2.920
Neg logit contributions
jad-4.241
estial-4.106
 Unloaded-3.940
cious-3.887
orem-3.857
Token What
Token ID1867
Feature activation+4.49e+00

Pos logit contributions
 Psychiat+2.428
yne+2.111
 Amend+2.036
nee+1.981
ANK+1.955
Neg logit contributions
jad-2.573
estial-2.467
orem-2.330
 Unloaded-2.328
cious-2.316
Token you
Token ID345
Feature activation+7.43e+00

Pos logit contributions
 Psychiat+3.225
yne+2.769
 Amend+2.711
nee+2.609
ight+2.587
Neg logit contributions
jad-3.709
estial-3.602
 Unloaded-3.413
cious-3.368
orem-3.361
Token were
Token ID547
Feature activation+8.58e+00

Pos logit contributions
 Psychiat+5.206
yne+4.462
 Amend+4.352
ight+4.299
nee+4.255
Neg logit contributions
jad-6.028
estial-5.991
orem-5.535
 Unloaded-5.495
cious-5.474
Token seeking
Token ID6095
Feature activation+3.77e+00

Pos logit contributions
 Psychiat+5.400
yne+4.631
ight+4.457
 Amend+4.413
nee+4.366
Neg logit contributions
jad-7.405
estial-7.376
orem-6.935
 Unloaded-6.921
cious-6.728
Token why
Token ID1521
Feature activation-3.00e+00

Pos logit contributions
jad+2.940
estial+2.759
 Unloaded+2.663
cious+2.641
orem+2.634
Neg logit contributions
 Psychiat-3.146
yne-2.821
 Amend-2.698
nee-2.636
ANK-2.572
Token,
Token ID11
Feature activation-6.29e-01

Pos logit contributions
jad+2.331
estial+2.213
 Unloaded+2.126
cious+2.109
orem+2.103
Neg logit contributions
 Psychiat-2.313
yne-2.062
 Amend-1.970
nee-1.934
ANK-1.877
Token in
Token ID287
Feature activation-2.04e-01

Pos logit contributions
jad+0.514
estial+0.494
 Unloaded+0.470
orem+0.467
cious+0.467
Neg logit contributions
 Psychiat-0.467
yne-0.411
 Amend-0.393
nee-0.384
ANK-0.372
Token an
Token ID281
Feature activation+6.37e+00

Pos logit contributions
jad+0.165
estial+0.158
 Unloaded+0.151
cious+0.150
orem+0.150
Neg logit contributions
 Psychiat-0.153
yne-0.135
 Amend-0.129
nee-0.126
ANK-0.122
Token era
Token ID6980
Feature activation+1.11e+00

Pos logit contributions
 Psychiat+4.542
yne+3.940
 Amend+3.845
nee+3.752
ANK+3.679
Neg logit contributions
jad-5.248
estial-5.083
cious-4.801
orem-4.763
 Unloaded-4.675
Token of
Token ID286
Feature activation+7.93e-01

Pos logit contributions
 Psychiat+0.788
yne+0.685
 Amend+0.658
nee+0.644
ANK+0.625
Neg logit contributions
jad-0.933
estial-0.898
orem-0.860
 Unloaded-0.853
cious-0.848
Token political
Token ID1964
Feature activation+4.07e+00

Pos logit contributions
 Psychiat+0.593
yne+0.520
 Amend+0.500
nee+0.489
ANK+0.475
Neg logit contributions
jad-0.644
estial-0.618
 Unloaded-0.587
orem-0.586
cious-0.583
Token lies
Token ID7363
Feature activation+2.87e+00

Pos logit contributions
 Psychiat+2.872
yne+2.501
 Amend+2.395
nee+2.352
ANK+2.308
Neg logit contributions
jad-3.382
estial-3.310
orem-3.152
 Unloaded-3.119
cious-3.065
Token and
Token ID290
Feature activation+3.67e+00

Pos logit contributions
 Psychiat+2.011
yne+1.765
 Amend+1.677
nee+1.641
ight+1.633
Neg logit contributions
jad-2.400
estial-2.330
orem-2.232
 Unloaded-2.199
cious-2.175
Token Brexit
Token ID11435
Feature activation+2.55e+00

Pos logit contributions
 Psychiat+2.736
yne+2.378
 Amend+2.307
nee+2.238
ANK+2.199
Neg logit contributions
jad-2.938
estial-2.842
orem-2.725
 Unloaded-2.688
cious-2.674
Token bias
Token ID10690
Feature activation+1.93e-01

Pos logit contributions
 Psychiat+1.866
yne+1.630
 Amend+1.563
nee+1.540
ANK+1.507
Neg logit contributions
jad-2.071
estial-2.018
 Unloaded-1.915
orem-1.912
cious-1.886
Tokent
Token ID83
Feature activation+4.60e-01

Pos logit contributions
 Psychiat+1.008
yne+0.884
 Amend+0.833
nee+0.820
ight+0.796
Neg logit contributions
jad-1.323
estial-1.271
 Unloaded-1.219
orem-1.210
cious-1.208
Token leave
Token ID2666
Feature activation-5.28e+00

Pos logit contributions
 Psychiat+0.352
yne+0.314
 Amend+0.299
nee+0.296
ANK+0.286
Neg logit contributions
jad-0.361
estial-0.347
 Unloaded-0.330
cious-0.330
orem-0.326
Token you
Token ID345
Feature activation-8.00e+00

Pos logit contributions
jad+3.753
estial+3.489
 Unloaded+3.410
cious+3.331
 missionary+3.296
Neg logit contributions
 Psychiat-4.379
yne-3.923
 Amend-3.787
nee-3.688
ANK-3.603
Token rolling
Token ID10708
Feature activation-3.64e+00

Pos logit contributions
jad+5.739
estial+5.195
 Unloaded+5.145
 missionary+5.057
cious+5.032
Neg logit contributions
 Psychiat-6.487
yne-5.811
 Amend-5.662
nee-5.373
ANK-5.334
Token your
Token ID534
Feature activation-1.95e+00

Pos logit contributions
jad+2.833
estial+2.709
 Unloaded+2.563
cious+2.555
orem+2.527
Neg logit contributions
 Psychiat-2.818
yne-2.505
 Amend-2.388
nee-2.328
ANK-2.261
Token eyes
Token ID2951
Feature activation-3.57e+00

Pos logit contributions
jad+1.584
estial+1.515
 Unloaded+1.451
cious+1.442
orem+1.436
Neg logit contributions
 Psychiat-1.455
yne-1.285
 Amend-1.228
nee-1.200
ANK-1.167
Token,
Token ID11
Feature activation-2.73e+00

Pos logit contributions
jad+2.812
estial+2.684
 Unloaded+2.563
cious+2.556
orem+2.519
Neg logit contributions
 Psychiat-2.745
yne-2.416
 Amend-2.328
nee-2.250
ANK-2.211
Token as
Token ID355
Feature activation-1.18e-01

Pos logit contributions
jad+2.137
estial+2.034
 Unloaded+1.953
cious+1.935
orem+1.917
Neg logit contributions
 Psychiat-2.104
yne-1.862
 Amend-1.787
nee-1.745
ANK-1.701
Token they
Token ID484
Feature activation-3.77e+00

Pos logit contributions
jad+0.093
estial+0.089
 Unloaded+0.084
orem+0.084
cious+0.084
Neg logit contributions
 Psychiat-0.091
yne-0.081
 Amend-0.077
nee-0.075
ight-0.073
Token still
Token ID991
Feature activation-1.29e+00

Pos logit contributions
jad+2.885
estial+2.750
 Unloaded+2.627
cious+2.605
orem+2.592
Neg logit contributions
 Psychiat-2.983
yne-2.620
 Amend-2.543
nee-2.446
ANK-2.405
Token feel
Token ID1254
Feature activation-4.13e+00

Pos logit contributions
jad+0.993
estial+0.949
 Unloaded+0.905
cious+0.898
orem+0.896
Neg logit contributions
 Psychiat-1.021
yne-0.906
 Amend-0.870
nee-0.850
ANK-0.829
Token address
Token ID2209
Feature activation+1.13e+00

Pos logit contributions
 Psychiat+1.998
yne+1.703
 Amend+1.629
nee+1.565
ight+1.512
Neg logit contributions
jad-3.273
estial-3.192
 Unloaded-3.036
cious-3.032
orem-3.027
Token.
Token ID13
Feature activation+6.15e+00

Pos logit contributions
 Psychiat+0.842
yne+0.741
 Amend+0.709
nee+0.693
ANK+0.673
Neg logit contributions
jad-0.924
estial-0.886
 Unloaded-0.846
cious-0.840
orem-0.839
Token Please
Token ID4222
Feature activation+1.94e+00

Pos logit contributions
 Psychiat+4.360
 Amend+3.733
yne+3.579
ight+3.454
nee+3.394
Neg logit contributions
jad-5.192
estial-4.992
orem-4.726
cious-4.719
 Unloaded-4.669
Token re
Token ID302
Feature activation+4.15e+00

Pos logit contributions
 Psychiat+1.435
yne+1.273
 Amend+1.214
nee+1.186
ANK+1.154
Neg logit contributions
jad-1.574
estial-1.513
 Unloaded-1.445
cious-1.432
orem-1.431
Token-
Token ID12
Feature activation+5.87e+00

Pos logit contributions
 Psychiat+2.624
yne+2.291
nee+2.128
 Amend+2.093
ight+2.082
Neg logit contributions
jad-3.764
estial-3.672
 Unloaded-3.490
cious-3.474
orem-3.463
Tokenenter
Token ID9255
Feature activation-1.20e+00

Pos logit contributions
 Psychiat+4.609
yne+4.170
nee+3.972
ight+3.909
 Amend+3.832
Neg logit contributions
jad-4.284
estial-4.149
 Unloaded-3.967
cious-3.882
orem-3.854
Token.
Token ID13
Feature activation-2.04e+00

Pos logit contributions
jad+0.937
estial+0.888
 Unloaded+0.854
cious+0.849
orem+0.837
Neg logit contributions
 Psychiat-0.935
yne-0.826
 Amend-0.799
nee-0.773
ANK-0.755
Token You
Token ID921
Feature activation+6.26e-01

Pos logit contributions
jad+1.337
estial+1.263
 Unloaded+1.205
cious+1.185
orem+1.180
Neg logit contributions
 Psychiat-1.830
yne-1.667
 Amend-1.597
nee-1.568
ANK-1.534
Token must
Token ID1276
Feature activation-3.04e+00

Pos logit contributions
 Psychiat+0.422
yne+0.367
 Amend+0.349
nee+0.340
ANK+0.329
Neg logit contributions
jad-0.552
estial-0.531
 Unloaded-0.509
cious-0.506
orem-0.505
Token select
Token ID2922
Feature activation+2.50e+00

Pos logit contributions
jad+3.191
estial+3.036
 Unloaded+2.981
cious+2.968
orem+2.932
Neg logit contributions
 Psychiat-1.527
yne-1.235
 Amend-1.167
nee-1.154
ANK-1.081
Token a
Token ID257
Feature activation-2.39e-01

Pos logit contributions
 Psychiat+1.793
yne+1.565
 Amend+1.502
nee+1.468
ANK+1.418
Neg logit contributions
jad-2.095
estial-2.022
orem-1.919
 Unloaded-1.918
cious-1.914
Token people
Token ID661
Feature activation+3.81e+00

Pos logit contributions
 Psychiat+0.975
yne+0.853
 Amend+0.816
nee+0.790
ight+0.775
Neg logit contributions
jad-1.132
estial-1.084
 Unloaded-1.038
orem-1.031
cious-1.030
Token live
Token ID2107
Feature activation-1.79e-01

Pos logit contributions
 Psychiat+2.725
yne+2.412
 Amend+2.277
ight+2.261
nee+2.250
Neg logit contributions
jad-3.110
estial-3.002
 Unloaded-2.856
orem-2.851
cious-2.835
Token there
Token ID612
Feature activation+3.20e+00

Pos logit contributions
jad+0.143
estial+0.138
 Unloaded+0.132
cious+0.131
orem+0.131
Neg logit contributions
 Psychiat-0.135
yne-0.120
 Amend-0.114
nee-0.112
ight-0.109
Token.
Token ID13
Feature activation-8.62e-01

Pos logit contributions
 Psychiat+2.243
yne+1.987
 Amend+1.848
nee+1.839
ight+1.818
Neg logit contributions
jad-2.672
estial-2.589
 Unloaded-2.494
orem-2.458
cious-2.456
Token Many
Token ID4650
Feature activation-2.04e+00

Pos logit contributions
jad+0.673
estial+0.644
 Unloaded+0.614
cious+0.610
orem+0.609
Neg logit contributions
 Psychiat-0.669
yne-0.593
 Amend-0.568
nee-0.556
ANK-0.541
Token rely
Token ID8814
Feature activation-2.12e+00

Pos logit contributions
jad+1.600
estial+1.524
 Unloaded+1.458
cious+1.447
orem+1.445
Neg logit contributions
 Psychiat-1.578
yne-1.398
 Amend-1.339
nee-1.313
ANK-1.278
Token entirely
Token ID5000
Feature activation-5.05e+00

Pos logit contributions
jad+1.645
estial+1.572
 Unloaded+1.500
cious+1.488
orem+1.486
Neg logit contributions
 Psychiat-1.663
yne-1.474
 Amend-1.414
nee-1.383
ANK-1.347
Token on
Token ID319
Feature activation-1.73e+00

Pos logit contributions
jad+3.670
estial+3.515
 Unloaded+3.349
cious+3.323
orem+3.321
Neg logit contributions
 Psychiat-4.168
yne-3.646
 Amend-3.576
nee-3.462
ANK-3.390
Token rain
Token ID6290
Feature activation+8.01e-01

Pos logit contributions
jad+1.376
estial+1.317
 Unloaded+1.257
cious+1.248
orem+1.245
Neg logit contributions
 Psychiat-1.318
yne-1.164
 Amend-1.114
nee-1.090
ANK-1.061
Token or
Token ID393
Feature activation+1.26e+00

Pos logit contributions
 Psychiat+0.558
yne+0.491
 Amend+0.464
nee+0.455
ight+0.446
Neg logit contributions
jad-0.686
estial-0.661
 Unloaded-0.631
orem-0.626
cious-0.623
Token imported
Token ID17392
Feature activation+6.73e-01

Pos logit contributions
 Psychiat+0.938
yne+0.836
 Amend+0.787
nee+0.775
ight+0.756
Neg logit contributions
jad-1.024
estial-0.985
 Unloaded-0.939
orem-0.931
cious-0.923
Token in
Token ID287
Feature activation-2.22e+00

Pos logit contributions
 Psychiat+1.592
yne+1.396
 Amend+1.328
nee+1.311
ight+1.280
Neg logit contributions
jad-1.943
estial-1.892
orem-1.811
 Unloaded-1.800
cious-1.790
Token minutes
Token ID2431
Feature activation+2.79e+00

Pos logit contributions
jad+1.729
estial+1.649
 Unloaded+1.577
cious+1.563
orem+1.554
Neg logit contributions
 Psychiat-1.727
yne-1.535
 Amend-1.463
nee-1.433
ANK-1.398
Token.
Token ID13
Feature activation+6.97e-01

Pos logit contributions
 Psychiat+1.882
yne+1.645
 Amend+1.569
nee+1.539
ight+1.523
Neg logit contributions
jad-2.420
estial-2.346
orem-2.248
 Unloaded-2.238
cious-2.209
Token From
Token ID3574
Feature activation+1.38e-01

Pos logit contributions
 Psychiat+0.539
yne+0.469
 Amend+0.457
nee+0.442
ANK+0.431
Neg logit contributions
jad-0.552
estial-0.532
orem-0.502
cious-0.501
 Unloaded-0.500
Token M
Token ID337
Feature activation-1.25e+00

Pos logit contributions
 Psychiat+0.105
yne+0.093
 Amend+0.089
nee+0.087
ANK+0.085
Neg logit contributions
jad-0.111
estial-0.106
 Unloaded-0.101
orem-0.100
cious-0.100
Tokeniley
Token ID9618
Feature activation-1.80e+00

Pos logit contributions
jad+1.051
estial+1.009
 Unloaded+0.966
cious+0.959
orem+0.957
Neg logit contributions
 Psychiat-0.895
yne-0.785
 Amend-0.749
nee-0.731
ANK-0.710
Token Cyrus
Token ID34305
Feature activation+2.36e-01

Pos logit contributions
jad+1.744
estial+1.678
 Unloaded+1.622
cious+1.614
orem+1.603
Neg logit contributions
 Psychiat-1.051
yne-0.894
 Amend-0.838
nee-0.810
ANK-0.787
Token phot
Token ID2825
Feature activation+4.11e-01

Pos logit contributions
 Psychiat+0.175
yne+0.154
 Amend+0.147
nee+0.144
ight+0.140
Neg logit contributions
jad-0.192
estial-0.185
 Unloaded-0.176
orem-0.176
cious-0.175
Tokenob
Token ID672
Feature activation+1.24e+01

Pos logit contributions
 Psychiat+0.381
yne+0.346
 Amend+0.332
nee+0.328
ight+0.321
Neg logit contributions
jad-0.258
estial-0.244
 Unloaded-0.230
cious-0.227
orem-0.227
Tokenomb
Token ID2381
Feature activation+8.30e+00

Pos logit contributions
 Psychiat+5.128
yne+4.402
ight+4.001
nee+3.981
ank+3.830
Neg logit contributions
jad-12.563
estial-12.487
 missionary-12.296
 Unloaded-12.155
orem-11.778
Tokening
Token ID278
Feature activation+2.22e+00

Pos logit contributions
 Psychiat+5.547
yne+4.841
nee+4.616
 Amend+4.516
ight+4.466
Neg logit contributions
jad-6.857
estial-6.622
orem-6.386
cious-6.229
 Unloaded-6.202
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
 Psychiat+0.601
yne+0.526
 Amend+0.504
nee+0.494
ight+0.480
Neg logit contributions
jad-0.672
estial-0.648
 Unloaded-0.615
orem-0.614
cious-0.611
Token However
Token ID2102
Feature activation+1.44e+00

Pos logit contributions
jad+0.824
estial+0.786
 Unloaded+0.752
cious+0.745
orem+0.743
Neg logit contributions
 Psychiat-0.830
yne-0.740
 Amend-0.707
nee-0.693
ANK-0.675
Token,
Token ID11
Feature activation+2.98e+00

Pos logit contributions
 Psychiat+1.027
yne+0.902
 Amend+0.857
nee+0.835
ight+0.814
Neg logit contributions
jad-1.215
estial-1.171
 Unloaded-1.122
orem-1.109
cious-1.108
Token gender
Token ID5279
Feature activation-2.60e+00

Pos logit contributions
 Psychiat+2.221
yne+1.925
 Amend+1.849
nee+1.780
ight+1.762
Neg logit contributions
jad-2.424
estial-2.368
 Unloaded-2.230
orem-2.220
cious-2.213
Token non
Token ID1729
Feature activation-1.02e+00

Pos logit contributions
jad+1.730
estial+1.627
 Unloaded+1.544
cious+1.540
orem+1.517
Neg logit contributions
 Psychiat-2.304
yne-2.073
 Amend-2.009
nee-1.969
ANK-1.924
Tokencon
Token ID1102
Feature activation-1.20e+01

Pos logit contributions
jad+0.962
estial+0.929
 Unloaded+0.895
cious+0.887
orem+0.887
Neg logit contributions
 Psychiat-0.624
yne-0.535
 Amend-0.504
nee-0.491
ANK-0.472
Tokenforming
Token ID15464
Feature activation-2.26e+00

Pos logit contributions
jad+8.040
cious+7.707
estial+7.485
cape+7.135
 Unloaded+7.013
Neg logit contributions
 Psychiat-9.871
yne-8.836
 Amend-8.630
ANK-8.452
nee-8.083
Token (
Token ID357
Feature activation-4.64e+00

Pos logit contributions
jad+1.850
estial+1.768
 Unloaded+1.693
cious+1.685
orem+1.674
Neg logit contributions
 Psychiat-1.659
yne-1.464
 Amend-1.403
nee-1.371
ANK-1.334
TokenG
Token ID38
Feature activation-1.10e+01

Pos logit contributions
jad+3.865
estial+3.647
cious+3.521
 Unloaded+3.504
orem+3.490
Neg logit contributions
 Psychiat-3.312
yne-2.889
 Amend-2.811
nee-2.674
ight-2.612
TokenNC
Token ID7792
Feature activation-7.65e+00

Pos logit contributions
jad+5.432
estial+5.041
cious+4.728
 Unloaded+4.643
orem+4.613
Neg logit contributions
 Psychiat-10.732
 Amend-9.450
yne-9.101
ight-8.919
 Lob-8.808
Token)
Token ID8
Feature activation-4.65e+00

Pos logit contributions
jad+5.571
estial+5.219
cious+5.051
 Unloaded+5.010
orem+4.903
Neg logit contributions
 Psychiat-6.011
yne-5.287
 Amend-5.148
nee-4.975
ANK-4.927
Token in
Token ID287
Feature activation-1.92e+00

Pos logit contributions
 Psychiat+0.266
yne+0.236
 Amend+0.226
nee+0.221
ANK+0.215
Neg logit contributions
jad-0.266
estial-0.256
 Unloaded-0.241
orem-0.240
cious-0.239
Token Buenos
Token ID46210
Feature activation+3.75e+00

Pos logit contributions
jad+1.545
estial+1.478
 Unloaded+1.414
cious+1.403
orem+1.400
Neg logit contributions
 Psychiat-1.446
yne-1.277
 Amend-1.221
nee-1.193
ANK-1.161
Token Aires
Token ID44692
Feature activation-3.22e+00

Pos logit contributions
 Psychiat+1.489
yne+1.155
 Amend+1.065
nee+1.031
ight+0.951
Neg logit contributions
jad-4.299
estial-4.238
orem-4.075
 Unloaded-4.067
cious-4.051
Token in
Token ID287
Feature activation-3.85e-01

Pos logit contributions
jad+2.404
estial+2.285
 Unloaded+2.189
cious+2.170
orem+2.161
Neg logit contributions
 Psychiat-2.604
yne-2.322
 Amend-2.226
nee-2.183
ANK-2.124
Token May
Token ID1737
Feature activation-8.49e+00

Pos logit contributions
jad+0.332
estial+0.321
 Unloaded+0.305
orem+0.304
cious+0.303
Neg logit contributions
 Psychiat-0.268
yne-0.233
 Amend-0.224
nee-0.217
ANK-0.211
Token 2010
Token ID3050
Feature activation-9.89e+00

Pos logit contributions
jad+5.697
 Unloaded+5.205
estial+5.090
cious+5.046
 missionary+4.971
Neg logit contributions
 Psychiat-7.235
yne-6.553
 Amend-6.186
nee-6.121
ANK-5.935
Token.
Token ID13
Feature activation-2.02e+00

Pos logit contributions
jad+6.564
estial+6.069
cious+5.936
 Unloaded+5.933
 missionary+5.773
Neg logit contributions
 Psychiat-8.300
yne-7.421
 Amend-7.132
nee-6.931
anche-6.823
Token
Token ID198
Feature activation-4.60e+00

Pos logit contributions
jad+1.587
estial+1.515
 Unloaded+1.452
cious+1.438
orem+1.432
Neg logit contributions
 Psychiat-1.558
yne-1.385
 Amend-1.322
nee-1.294
ANK-1.260
Token
Token ID198
Feature activation-4.68e+00

Pos logit contributions
jad+3.195
 Unloaded+2.912
estial+2.899
cious+2.838
orem+2.786
Neg logit contributions
 Psychiat-3.885
yne-3.494
 Amend-3.378
anche-3.229
nee-3.185
TokenHis
Token ID6653
Feature activation-4.50e-02

Pos logit contributions
jad+3.275
estial+3.073
cious+2.929
 Unloaded+2.910
orem+2.863
Neg logit contributions
 Psychiat-3.996
yne-3.576
 Amend-3.471
nee-3.306
anche-3.263
Token pen
Token ID3112
Feature activation-4.69e-01

Pos logit contributions
jad+0.035
estial+0.034
 Unloaded+0.032
cious+0.032
orem+0.032
Neg logit contributions
 Psychiat-0.035
yne-0.031
 Amend-0.030
nee-0.029
ight-0.028
Token report
Token ID989
Feature activation-4.58e+00

Pos logit contributions
 Psychiat+1.622
yne+1.444
 Amend+1.381
nee+1.355
ight+1.331
Neg logit contributions
jad-1.557
estial-1.498
 Unloaded-1.413
orem-1.406
cious-1.402
Token investigating
Token ID10240
Feature activation-1.03e+01

Pos logit contributions
jad+3.554
estial+3.357
 Unloaded+3.262
cious+3.210
orem+3.205
Neg logit contributions
 Psychiat-3.516
yne-3.156
 Amend-2.992
nee-2.930
ANK-2.853
Token Protective
Token ID45004
Feature activation-2.54e+00

Pos logit contributions
jad+6.849
estial+6.342
 Unloaded+6.268
 missionary+6.203
cious+6.100
Neg logit contributions
 Psychiat-8.439
yne-7.641
 Amend-7.316
nee-7.216
ANK-6.972
Token Edge
Token ID13113
Feature activation-3.20e+00

Pos logit contributions
jad+2.320
 Unloaded+2.245
estial+2.191
cious+2.155
orem+2.105
Neg logit contributions
 Psychiat-1.578
yne-1.349
 Amend-1.253
nee-1.215
ANK-1.206
Token,
Token ID11
Feature activation-5.54e+00

Pos logit contributions
jad+2.557
estial+2.438
 Unloaded+2.354
cious+2.321
orem+2.320
Neg logit contributions
 Psychiat-2.412
yne-2.136
 Amend-2.039
nee-1.990
ANK-1.933
Token the
Token ID262
Feature activation-7.95e+00

Pos logit contributions
jad+4.073
estial+3.869
 Unloaded+3.778
cious+3.723
orem+3.643
Neg logit contributions
 Psychiat-4.381
yne-3.963
 Amend-3.776
nee-3.708
ANK-3.575
Token commission
Token ID5810
Feature activation-1.57e+00

Pos logit contributions
jad+5.696
 Unloaded+5.332
estial+5.327
cious+5.196
orem+5.189
Neg logit contributions
 Psychiat-6.264
yne-5.689
 Amend-5.412
nee-5.292
ANK-5.182
Token of
Token ID286
Feature activation-4.04e+00

Pos logit contributions
jad+1.275
estial+1.220
 Unloaded+1.168
cious+1.159
orem+1.157
Neg logit contributions
 Psychiat-1.172
yne-1.034
 Amend-0.989
nee-0.965
ANK-0.939
Token inquiry
Token ID12069
Feature activation+2.11e+00

Pos logit contributions
jad+2.414
estial+2.286
 Unloaded+2.170
cious+2.162
orem+2.145
Neg logit contributions
 Psychiat-3.795
yne-3.473
 Amend-3.335
nee-3.296
ANK-3.217
Token treated
Token ID5716
Feature activation-7.06e+00

Pos logit contributions
 Psychiat+1.522
yne+1.328
 Amend+1.276
nee+1.241
ight+1.213
Neg logit contributions
jad-1.759
estial-1.704
 Unloaded-1.604
cious-1.602
orem-1.600
Token the
Token ID262
Feature activation-6.91e+00

Pos logit contributions
jad+4.994
estial+4.682
 Unloaded+4.589
cious+4.467
 missionary+4.421
Neg logit contributions
 Psychiat-5.773
yne-5.187
 Amend-4.979
nee-4.834
ANK-4.720
Token Stephan
Token ID20800
Feature activation-5.09e+00

Pos logit contributions
jad+3.318
estial+3.117
 Unloaded+2.991
cious+2.952
orem+2.941
Neg logit contributions
 Psychiat-3.594
yne-3.230
 Amend-3.077
nee-3.014
ANK-2.952
Tokenopol
Token ID39704
Feature activation-7.25e+00

Pos logit contributions
jad+3.003
estial+2.741
 Unloaded+2.657
cious+2.635
orem+2.580
Neg logit contributions
 Psychiat-4.874
yne-4.320
 Amend-4.286
nee-4.081
ANK-4.033
Tokenous
Token ID516
Feature activation-1.05e+00

Pos logit contributions
jad+3.705
estial+3.332
orem+3.154
cious+3.136
 Unloaded+3.060
Neg logit contributions
 Psychiat-7.389
yne-6.787
 Amend-6.644
nee-6.429
ANK-6.379
Token will
Token ID481
Feature activation-3.16e+00

Pos logit contributions
jad+0.850
estial+0.816
 Unloaded+0.780
cious+0.774
orem+0.772
Neg logit contributions
 Psychiat-0.781
yne-0.689
 Amend-0.658
nee-0.643
ANK-0.625
Token be
Token ID307
Feature activation-1.51e+00

Pos logit contributions
jad+2.453
estial+2.301
orem+2.208
 Unloaded+2.202
cious+2.173
Neg logit contributions
 Psychiat-2.464
yne-2.180
 Amend-2.088
nee-2.022
ANK-2.000
Token in
Token ID287
Feature activation-8.93e+00

Pos logit contributions
jad+1.201
estial+1.147
 Unloaded+1.097
cious+1.087
orem+1.085
Neg logit contributions
 Psychiat-1.149
yne-1.016
 Amend-0.972
nee-0.951
ANK-0.926
Token Boston
Token ID6182
Feature activation-4.65e+00

Pos logit contributions
jad+6.587
estial+5.975
 Unloaded+5.890
 missionary+5.777
cious+5.715
Neg logit contributions
 Psychiat-6.990
yne-6.404
nee-5.949
ANK-5.854
 Amend-5.852
Token on
Token ID319
Feature activation-6.73e+00

Pos logit contributions
jad+3.645
estial+3.430
 Unloaded+3.280
cious+3.240
orem+3.214
Neg logit contributions
 Psychiat-3.582
yne-3.173
 Amend-3.051
nee-2.987
ANK-2.920
Token Tuesday
Token ID3431
Feature activation-3.17e+00

Pos logit contributions
jad+4.851
estial+4.554
 Unloaded+4.419
 missionary+4.361
cious+4.350
Neg logit contributions
 Psychiat-5.345
yne-4.842
nee-4.542
 Amend-4.515
ight-4.406
Token morning
Token ID3329
Feature activation-3.32e+00

Pos logit contributions
jad+2.452
estial+2.326
 Unloaded+2.224
cious+2.202
orem+2.190
Neg logit contributions
 Psychiat-2.483
yne-2.204
 Amend-2.111
nee-2.061
ANK-2.014
Token for
Token ID329
Feature activation+3.76e-02

Pos logit contributions
jad+2.640
estial+2.497
 Unloaded+2.389
cious+2.363
orem+2.358
Neg logit contributions
 Psychiat-2.535
yne-2.246
 Amend-2.148
nee-2.104
ANK-2.048
Token as
Token ID355
Feature activation-1.06e-01

Pos logit contributions
jad+1.887
estial+1.795
 Unloaded+1.717
cious+1.707
orem+1.703
Neg logit contributions
 Psychiat-1.848
yne-1.624
 Amend-1.564
nee-1.520
ANK-1.484
Token here
Token ID994
Feature activation+2.89e+00

Pos logit contributions
jad+0.086
estial+0.082
 Unloaded+0.079
cious+0.078
orem+0.078
Neg logit contributions
 Psychiat-0.080
yne-0.070
 Amend-0.067
nee-0.066
ANK-0.064
Token,
Token ID11
Feature activation-1.90e+00

Pos logit contributions
 Psychiat+2.074
yne+1.819
 Amend+1.739
nee+1.736
ight+1.685
Neg logit contributions
jad-2.374
estial-2.308
 Unloaded-2.178
cious-2.168
orem-2.147
Token to
Token ID284
Feature activation-2.19e+00

Pos logit contributions
jad+1.504
estial+1.435
 Unloaded+1.377
orem+1.362
cious+1.360
Neg logit contributions
 Psychiat-1.447
yne-1.279
 Amend-1.224
nee-1.195
ANK-1.164
Token (
Token ID357
Feature activation-6.68e-01

Pos logit contributions
jad+1.675
estial+1.588
 Unloaded+1.524
orem+1.515
cious+1.505
Neg logit contributions
 Psychiat-1.733
yne-1.540
 Amend-1.470
nee-1.435
ANK-1.403
Token1
Token ID16
Feature activation-8.02e+00

Pos logit contributions
jad+0.560
estial+0.538
 Unloaded+0.515
cious+0.511
orem+0.510
Neg logit contributions
 Psychiat-0.480
yne-0.422
 Amend-0.402
nee-0.393
ANK-0.382
Token
Token ID784
Feature activation-9.27e-01

Pos logit contributions
jad+5.943
estial+5.564
 Unloaded+5.332
orem+5.331
cious+5.263
Neg logit contributions
 Psychiat-6.246
yne-5.526
 Amend-5.286
nee-5.125
anche-5.095
Token g
Token ID308
Feature activation-7.07e+00

Pos logit contributions
jad+0.775
estial+0.743
 Unloaded+0.712
cious+0.706
orem+0.705
Neg logit contributions
 Psychiat-0.669
yne-0.587
 Amend-0.560
nee-0.547
ANK-0.531
Token)
Token ID8
Feature activation-4.12e+00

Pos logit contributions
jad+5.458
estial+5.129
 Unloaded+4.952
orem+4.904
cious+4.808
Neg logit contributions
 Psychiat-5.420
yne-4.665
 Amend-4.546
nee-4.359
anche-4.270
Token
Token ID1906
Feature activation+4.36e-01

Pos logit contributions
jad+3.267
estial+3.101
 Unloaded+3.000
orem+2.972
cious+2.944
Neg logit contributions
 Psychiat-3.128
yne-2.732
 Amend-2.642
nee-2.553
ANK-2.483
Token1
Token ID16
Feature activation-4.67e+00

Pos logit contributions
 Psychiat+0.318
yne+0.282
 Amend+0.267
nee+0.263
ANK+0.256
Neg logit contributions
jad-0.359
estial-0.346
 Unloaded-0.330
cious-0.328
orem-0.326