TOP ACTIVATIONS
MAX = 18.174

x . x . x . 151 103 30 29 x
x . x . x . 153 11 75 163 x
x . x . x . 150 110 81 12 x
x . x . x . 152 101 8 604 x
000 mph ( 720 , 000 km / h ). Even
, and explore the world with kindred spirits .
ALL PERSON EL UPDATE : 0 555 z MO HA W
x . x . x . 103 105 49 36 x
84 million miles ( 940 million km ) by ­ ­
go over some basic dos and don 't s , using
x . x . x . 149 110 22 26 x
x . x . x . 102 113 44 17 x
x . x . x . 154 109 77 39 x
604 x . x . x . 153 11 75 163
x . x . x . 132 10 86 213 x
x . x . x . 131 111 58 91 x
x . x . x . 155 10 384 38 x
teams , along with all int ram ural activities , including
x . x . x . 172 100 79 72 x
x . x . x . 171 102 30 86 x

MIN ACTIVATIONS
MIN = -15.571

. T RE AS URE HUN TER
D P ART IS . Faith .
F LECT _ CLASS _ ST ART () above is the
TI P ART IS . Pen ance
large reservoir of M . le p ra e and may
107 P / Wilson Har rington . The
= c v 2 . morphology Ex ( gray , c
T RE AS URE HUN TER 2007
E mpire . FIN DE TRAN SM ISSION /// <|endoftext|> Our
S U PP LE MENT UM T ER TI
21 O & A - WOR ST OF - Penn J
. Old gift be arer setting box underneath roughly (
AC T RE AS URE HUN TER
Railroad Company , 118 U . S . 39 4 (
lesbian spouses . Cre ighton University in Omaha ,
My c ob acter ium le p ra e .[ 116
of the vagina and restricts path ogen growth . A
ε ρ ε ι
about as dangerous as could be , and certainly will look
the body s natural shifts between sympathetic (

INTERVAL 9.738 - 18.174
CONTAINS 0.046%

golden brown . These are lightly fried and not deep fried
170 x . x . x . 149 110 22 26
Read More About Dw ark adh ish Temple Here
proven oil reserves : 140 billion barrels ), Obama pedd led
x . x . x . 154 109 77 39 x

INTERVAL 1.302 - 9.738
CONTAINS 29.800%

ials / Deb ate Op in ions expressed in USA TODAY
makes a great case for the N 64 as the New
the life of me remember anything that preceded Alfred o 's
oral and anthrop omorphic div in ities became unacceptable to the
one caveat . Yes , his cabinet represents several core Canadian

INTERVAL -7.134 - 1.302
CONTAINS 69.672%

set of two 7 - bar LED panels ( 5 cm
pioneering lingu ist William Lab ov told City Paper in
ro Cub ans ( bl acks and mul att os
toe - to - toe with the world s
had been set at 22 , 500 students .

INTERVAL -15.571 - -7.134
CONTAINS 0.481%

much as $ 2 million .) The private school she attended
or call 0 207 7 82 4 368 <|endoftext|> To all
, so caveat empt or .) Another of Moore
two parties . Prep aring for independence : 1961
highlight her support for free trade , but also the concerns
Token x
Token ID2124
Feature activation-2.11e+00

Pos logit contributions
 Weld+1.851
ationally+1.800
ammy+1.757
netflix+1.694
ittle+1.692
Neg logit contributions
eret-2.019
cano-1.914
hell-1.838
 voic-1.801
 bras-1.780
Token.
Token ID13
Feature activation+2.82e+00

Pos logit contributions
eret+1.390
cano+1.285
hell+1.268
 voic+1.218
 bras+1.209
Neg logit contributions
 Weld-1.599
ationally-1.580
ammy-1.566
ittle-1.507
netflix-1.506
Tokenx
Token ID87
Feature activation+3.51e+00

Pos logit contributions
ationally+1.421
 Weld+1.412
ammy+1.367
netflix+1.319
ittle+1.306
Neg logit contributions
eret-2.507
cano-2.406
 voic-2.362
 bras-2.347
hell-2.311
Token.
Token ID13
Feature activation+7.35e+00

Pos logit contributions
 Weld+2.318
ationally+2.262
ammy+2.185
netflix+2.138
ittle+2.119
Neg logit contributions
eret-2.624
cano-2.494
 voic-2.406
 bras-2.374
hell-2.361
Tokenx
Token ID87
Feature activation+1.07e+01

Pos logit contributions
ationally+3.123
 Weld+3.000
ammy+2.955
netflix+2.869
gans+2.866
Neg logit contributions
eret-6.824
 voic-6.693
 bras-6.661
cano-6.626
 notor-6.479
Token.
Token ID13
Feature activation+1.82e+01

Pos logit contributions
 Weld+5.767
ationally+5.402
ammy+5.267
gans+5.166
ittle+5.118
Neg logit contributions
eret-8.586
 notor-8.425
 voic-8.289
cano-8.243
 bras-8.108
Token151
Token ID24309
Feature activation-1.58e+00

Pos logit contributions
 Weld+5.288
uld+4.409
ammy+4.247
gans+4.201
ationally+4.154
Neg logit contributions
eret-18.081
 voic-17.346
 bras-17.171
cano-17.026
 Xperia-16.841
Token 103
Token ID15349
Feature activation-7.07e+00

Pos logit contributions
eret+1.125
cano+1.054
hell+1.035
 voic+1.008
 bras+0.997
Neg logit contributions
 Weld-1.112
ationally-1.101
ammy-1.085
ittle-1.046
netflix-1.044
Token30
Token ID1270
Feature activation-1.19e+00

Pos logit contributions
eret+4.282
hell+3.963
cano+3.858
tes+3.727
 bras+3.707
Neg logit contributions
ationally-5.555
ammy-5.531
 Weld-5.421
ittle-5.253
netflix-5.213
Token29
Token ID1959
Feature activation-1.01e+00

Pos logit contributions
eret+0.799
cano+0.743
hell+0.729
 voic+0.705
 bras+0.699
Neg logit contributions
 Weld-0.889
ationally-0.878
ammy-0.867
ittle-0.836
netflix-0.836
Token x
Token ID2124
Feature activation-4.01e+00

Pos logit contributions
eret+0.682
cano+0.634
hell+0.621
 voic+0.604
 bras+0.599
Neg logit contributions
 Weld-0.748
ationally-0.739
ammy-0.728
netflix-0.704
ittle-0.703
Token x
Token ID2124
Feature activation-3.04e+00

Pos logit contributions
eret+0.884
cano+0.819
hell+0.804
 voic+0.783
 bras+0.776
Neg logit contributions
 Weld-0.978
ationally-0.965
ammy-0.953
netflix-0.920
ittle-0.919
Token.
Token ID13
Feature activation+2.37e-01

Pos logit contributions
eret+1.950
cano+1.791
hell+1.782
 voic+1.694
 bras+1.683
Neg logit contributions
 Weld-2.349
ationally-2.327
ammy-2.315
ittle-2.225
netflix-2.220
Tokenx
Token ID87
Feature activation+3.77e+00

Pos logit contributions
 Weld+0.132
ationally+0.131
ammy+0.127
netflix+0.122
ittle+0.122
Neg logit contributions
eret-0.203
cano-0.193
hell-0.188
 voic-0.186
 bras-0.185
Token.
Token ID13
Feature activation+9.88e+00

Pos logit contributions
 Weld+2.475
ationally+2.413
ammy+2.332
netflix+2.276
ittle+2.260
Neg logit contributions
eret-2.829
cano-2.695
 voic-2.598
 bras-2.567
hell-2.546
Tokenx
Token ID87
Feature activation+1.37e+01

Pos logit contributions
ationally+3.847
ammy+3.740
 Weld+3.737
gans+3.534
ittle+3.516
Neg logit contributions
 bras-9.153
eret-9.116
 voic-9.109
 notor-9.023
 contrace-8.943
Token.
Token ID13
Feature activation+1.68e+01

Pos logit contributions
 Weld+6.696
ationally+6.205
ammy+6.130
^^^^+6.080
ittle+6.080
Neg logit contributions
 notor-11.254
eret-10.784
 contrace-10.779
 voic-10.570
 bras-10.544
Token153
Token ID21395
Feature activation-1.84e+00

Pos logit contributions
 Weld+6.240
ittle+5.968
ammy+5.851
ationally+5.655
uld+5.631
Neg logit contributions
eret-14.358
 bras-14.258
cano-13.913
 Instr-13.846
 notor-13.825
Token 11
Token ID1367
Feature activation+1.66e+00

Pos logit contributions
eret+1.302
cano+1.219
hell+1.200
 voic+1.170
 bras+1.157
Neg logit contributions
 Weld-1.291
ationally-1.282
ammy-1.265
ittle-1.217
netflix-1.214
Token75
Token ID2425
Feature activation-3.19e-01

Pos logit contributions
 Weld+1.194
ationally+1.165
ammy+1.144
netflix+1.110
ittle+1.105
Neg logit contributions
eret-1.161
cano-1.090
hell-1.054
 voic-1.039
 bras-1.028
Token163
Token ID24136
Feature activation-8.57e-02

Pos logit contributions
eret+0.232
cano+0.217
hell+0.212
 voic+0.207
 bras+0.205
Neg logit contributions
 Weld-0.222
ationally-0.218
ammy-0.215
netflix-0.207
ittle-0.207
Token x
Token ID2124
Feature activation-2.26e+00

Pos logit contributions
eret+0.060
cano+0.056
hell+0.054
 voic+0.053
 bras+0.052
Neg logit contributions
 Weld-0.062
ationally-0.061
ammy-0.060
netflix-0.058
ittle-0.058
Token x
Token ID2124
Feature activation-1.55e+00

Pos logit contributions
 Weld+1.065
ationally+1.040
ammy+1.018
netflix+0.985
ittle+0.983
Neg logit contributions
eret-1.096
cano-1.032
hell-0.997
 voic-0.975
 bras-0.965
Token.
Token ID13
Feature activation+1.71e+00

Pos logit contributions
eret+1.039
cano+0.964
hell+0.946
 voic+0.915
 bras+0.907
Neg logit contributions
 Weld-1.166
ationally-1.151
ammy-1.138
ittle-1.096
netflix-1.096
Tokenx
Token ID87
Feature activation+2.96e+00

Pos logit contributions
 Weld+0.903
ationally+0.899
ammy+0.871
netflix+0.839
ittle+0.832
Neg logit contributions
eret-1.498
cano-1.431
 voic-1.394
 bras-1.385
hell-1.384
Token.
Token ID13
Feature activation+6.60e+00

Pos logit contributions
 Weld+1.986
ationally+1.941
ammy+1.879
netflix+1.833
ittle+1.821
Neg logit contributions
eret-2.188
cano-2.077
 voic-1.998
 bras-1.975
hell-1.974
Tokenx
Token ID87
Feature activation+9.44e+00

Pos logit contributions
ationally+2.892
 Weld+2.812
ammy+2.746
netflix+2.661
gans+2.645
Neg logit contributions
eret-6.096
 voic-5.941
cano-5.911
 bras-5.910
 notor-5.702
Token.
Token ID13
Feature activation+1.57e+01

Pos logit contributions
 Weld+5.142
ationally+4.858
ammy+4.681
ittle+4.588
gans+4.562
Neg logit contributions
eret-7.600
 notor-7.423
cano-7.366
 voic-7.319
 bras-7.160
Token150
Token ID8628
Feature activation-7.01e-01

Pos logit contributions
 Weld+5.078
ittle+5.017
ammy+4.842
vard+4.482
ationally+4.436
Neg logit contributions
eret-14.618
 voic-14.532
 bras-14.068
cano-14.058
 notor-13.802
Token 110
Token ID9796
Feature activation+3.11e+00

Pos logit contributions
eret+0.498
cano+0.466
hell+0.456
 voic+0.445
 bras+0.440
Neg logit contributions
 Weld-0.495
ationally-0.489
ammy-0.482
ittle-0.464
netflix-0.464
Token81
Token ID6659
Feature activation-6.13e+00

Pos logit contributions
 Weld+2.163
ationally+2.106
ammy+2.055
netflix+2.013
gans+1.997
Neg logit contributions
eret-2.236
cano-2.100
 voic-2.017
hell-1.996
 bras-1.985
Token12
Token ID1065
Feature activation+2.73e+00

Pos logit contributions
eret+3.853
hell+3.529
cano+3.500
 bras+3.366
tes+3.340
Neg logit contributions
ationally-4.711
ammy-4.674
 Weld-4.638
netflix-4.517
ittle-4.444
Token x
Token ID2124
Feature activation-2.11e+00

Pos logit contributions
 Weld+1.851
ationally+1.800
ammy+1.757
netflix+1.694
ittle+1.692
Neg logit contributions
eret-2.019
cano-1.914
hell-1.838
 voic-1.801
 bras-1.780
Token x
Token ID2124
Feature activation-4.01e+00

Pos logit contributions
eret+0.682
cano+0.634
hell+0.621
 voic+0.604
 bras+0.599
Neg logit contributions
 Weld-0.748
ationally-0.739
ammy-0.728
netflix-0.704
ittle-0.703
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
eret+2.487
hell+2.275
cano+2.262
 voic+2.132
 bras+2.121
Neg logit contributions
 Weld-3.169
ationally-3.146
ammy-3.145
ittle-3.015
netflix-3.001
Tokenx
Token ID87
Feature activation-6.84e-01

Pos logit contributions
eret+1.108
cano+1.044
hell+1.029
 voic+0.999
 bras+0.991
Neg logit contributions
 Weld-0.782
ationally-0.764
ammy-0.751
ittle-0.717
netflix-0.716
Token.
Token ID13
Feature activation+4.30e+00

Pos logit contributions
eret+0.466
cano+0.434
hell+0.424
 voic+0.413
 bras+0.409
Neg logit contributions
 Weld-0.506
ationally-0.498
ammy-0.491
netflix-0.474
ittle-0.474
Tokenx
Token ID87
Feature activation+5.42e+00

Pos logit contributions
ationally+2.063
 Weld+2.048
ammy+1.971
netflix+1.907
ittle+1.887
Neg logit contributions
eret-3.894
cano-3.751
 voic-3.722
 bras-3.693
hell-3.576
Token.
Token ID13
Feature activation+1.55e+01

Pos logit contributions
 Weld+3.434
ationally+3.321
ammy+3.221
ittle+3.125
netflix+3.113
Neg logit contributions
eret-4.109
cano-3.935
 voic-3.859
 bras-3.816
hell-3.698
Token152
Token ID17827
Feature activation-1.38e+00

Pos logit contributions
 Weld+6.739
ammy+6.435
ationally+6.134
ittle+5.956
uld+5.853
Neg logit contributions
 bras-12.841
eret-12.593
 voic-12.522
 notor-12.514
 contrace-12.420
Token 101
Token ID8949
Feature activation-5.72e-01

Pos logit contributions
eret+0.976
cano+0.913
hell+0.896
 voic+0.874
 bras+0.865
Neg logit contributions
 Weld-0.972
ationally-0.961
ammy-0.949
ittle-0.912
netflix-0.911
Token8
Token ID23
Feature activation-1.21e+00

Pos logit contributions
eret+0.395
cano+0.369
hell+0.360
 voic+0.351
 bras+0.348
Neg logit contributions
 Weld-0.418
ationally-0.411
ammy-0.405
netflix-0.391
ittle-0.391
Token604
Token ID31916
Feature activation-1.31e+00

Pos logit contributions
eret+0.868
cano+0.810
hell+0.795
 voic+0.769
 bras+0.763
Neg logit contributions
 Weld-0.847
ationally-0.836
ammy-0.827
ittle-0.792
netflix-0.791
Token x
Token ID2124
Feature activation-3.04e+00

Pos logit contributions
eret+0.884
cano+0.819
hell+0.804
 voic+0.783
 bras+0.776
Neg logit contributions
 Weld-0.978
ationally-0.965
ammy-0.953
netflix-0.920
ittle-0.919
Token000
Token ID830
Feature activation+7.02e+00

Pos logit contributions
 Weld+1.166
ationally+1.142
ammy+1.116
netflix+1.080
ittle+1.078
Neg logit contributions
eret-1.448
cano-1.362
hell-1.334
 voic-1.308
 bras-1.296
Token mph
Token ID16462
Feature activation-8.43e-01

Pos logit contributions
 Weld+2.994
ationally+2.827
ammy+2.631
ittle+2.614
netflix+2.463
Neg logit contributions
eret-6.805
cano-6.595
hell-6.441
 voic-6.259
 bras-6.185
Token (
Token ID357
Feature activation+3.82e+00

Pos logit contributions
eret+0.526
cano+0.487
hell+0.476
 voic+0.461
 bras+0.456
Neg logit contributions
 Weld-0.670
ationally-0.662
ammy-0.657
netflix-0.634
ittle-0.630
Token720
Token ID23906
Feature activation+6.09e+00

Pos logit contributions
 Weld+2.437
ationally+2.377
ammy+2.315
netflix+2.272
ittle+2.270
Neg logit contributions
eret-2.953
cano-2.776
hell-2.674
 voic-2.672
 bras-2.652
Token,
Token ID11
Feature activation+2.75e+00

Pos logit contributions
 Weld+3.886
ationally+3.710
ammy+3.622
ittle+3.552
netflix+3.510
Neg logit contributions
eret-4.684
cano-4.401
hell-4.323
 voic-4.207
 bras-4.100
Token000
Token ID830
Feature activation+1.54e+01

Pos logit contributions
 Weld+1.652
ationally+1.613
ammy+1.569
netflix+1.534
ittle+1.517
Neg logit contributions
eret-2.236
cano-2.111
hell-2.061
 voic-2.034
 bras-2.016
Token km
Token ID10571
Feature activation-2.81e-01

Pos logit contributions
 Weld+3.222
ationally+2.779
ittle+2.431
 kcal+2.413
 km+2.328
Neg logit contributions
eret-16.413
cano-15.827
hell-15.709
 voic-15.323
olesc-15.218
Token/
Token ID14
Feature activation+2.00e+00

Pos logit contributions
eret+0.227
cano+0.215
hell+0.210
 voic+0.206
 bras+0.204
Neg logit contributions
 Weld-0.171
ationally-0.168
ammy-0.165
netflix-0.158
ittle-0.158
Tokenh
Token ID71
Feature activation-2.03e+00

Pos logit contributions
 Weld+1.437
ationally+1.426
ammy+1.395
ittle+1.360
netflix+1.352
Neg logit contributions
eret-1.389
cano-1.292
hell-1.250
 voic-1.250
 bras-1.235
Token).
Token ID737
Feature activation-1.69e+00

Pos logit contributions
eret+1.296
cano+1.207
hell+1.176
 voic+1.143
 bras+1.137
Neg logit contributions
 Weld-1.570
ationally-1.551
ammy-1.543
netflix-1.492
ittle-1.478
Token Even
Token ID3412
Feature activation-4.73e-01

Pos logit contributions
eret+1.189
cano+1.104
hell+1.091
 voic+1.054
 bras+1.050
Neg logit contributions
 Weld-1.198
ationally-1.197
ammy-1.190
netflix-1.141
ittle-1.139
Token,
Token ID11
Feature activation-1.72e+00

Pos logit contributions
 Weld+2.187
ationally+2.105
ammy+2.047
netflix+1.995
ittle+1.976
Neg logit contributions
eret-2.625
cano-2.482
 voic-2.380
hell-2.354
 bras-2.349
Token and
Token ID290
Feature activation+1.70e+00

Pos logit contributions
eret+1.183
cano+1.100
hell+1.083
 voic+1.050
 bras+1.042
Neg logit contributions
 Weld-1.257
ationally-1.238
ammy-1.227
ittle-1.180
netflix-1.177
Token explore
Token ID7301
Feature activation+6.79e-01

Pos logit contributions
ationally+1.033
 Weld+1.024
ammy+0.983
netflix+0.957
ittle+0.954
Neg logit contributions
eret-1.383
cano-1.297
hell-1.272
 voic-1.241
 bras-1.231
Token the
Token ID262
Feature activation+1.96e-01

Pos logit contributions
 Weld+0.480
ationally+0.473
ammy+0.460
netflix+0.445
ittle+0.445
Neg logit contributions
eret-0.484
cano-0.455
hell-0.440
 voic-0.430
 bras-0.429
Token world
Token ID995
Feature activation-2.54e+00

Pos logit contributions
 Weld+0.154
ationally+0.153
ammy+0.150
netflix+0.145
ittle+0.145
Neg logit contributions
eret-0.125
cano-0.115
hell-0.112
 voic-0.108
 bras-0.108
Token with
Token ID351
Feature activation+1.52e+01

Pos logit contributions
eret+1.597
cano+1.474
hell+1.458
 voic+1.403
 bras+1.394
Neg logit contributions
 Weld-1.983
ationally-1.957
ammy-1.944
netflix-1.872
ittle-1.870
Token kindred
Token ID46449
Feature activation+2.20e+00

Pos logit contributions
 Weld+4.130
ationally+3.528
ammy+3.013
^^^^+2.915
netflix+2.849
Neg logit contributions
eret-16.394
cano-15.427
zek-14.722
butt-14.582
hell-14.399
Token spirits
Token ID13747
Feature activation+2.06e+00

Pos logit contributions
 Weld+1.729
ationally+1.691
ammy+1.673
ittle+1.620
netflix+1.617
Neg logit contributions
eret-1.404
cano-1.297
hell-1.252
 voic-1.199
 bras-1.196
Token.
Token ID13
Feature activation-3.11e+00

Pos logit contributions
 Weld+1.402
ationally+1.366
ammy+1.333
netflix+1.299
ittle+1.284
Neg logit contributions
eret-1.522
cano-1.432
 voic-1.373
hell-1.365
 bras-1.357
Token
Token ID198
Feature activation-3.59e+00

Pos logit contributions
eret+2.189
cano+2.035
hell+2.027
 voic+1.948
 bras+1.935
Neg logit contributions
 Weld-2.197
ationally-2.186
ammy-2.162
ittle-2.074
netflix-2.069
Token
Token ID198
Feature activation-2.27e+00

Pos logit contributions
eret+2.464
hell+2.286
cano+2.285
 voic+2.177
 bras+2.164
Neg logit contributions
 Weld-2.595
ationally-2.568
ammy-2.559
ittle-2.455
netflix-2.443
Token ALL
Token ID11096
Feature activation+5.79e+00

Pos logit contributions
eret+0.468
cano+0.435
hell+0.427
 voic+0.418
 bras+0.413
Neg logit contributions
 Weld-0.505
ationally-0.500
ammy-0.493
netflix-0.476
ittle-0.476
Token PERSON
Token ID46740
Feature activation-5.67e+00

Pos logit contributions
 Weld+3.998
ationally+3.800
ammy+3.729
ittle+3.644
gans+3.584
Neg logit contributions
eret-4.177
cano-3.937
hell-3.816
 bras-3.664
 voic-3.621
TokenEL
Token ID3698
Feature activation-1.00e+01

Pos logit contributions
eret+4.257
hell+3.960
cano+3.866
 voic+3.785
 bras+3.689
Neg logit contributions
 Weld-3.662
ammy-3.660
ationally-3.660
netflix-3.473
ittle-3.457
Token UPDATE
Token ID35717
Feature activation+1.89e+00

Pos logit contributions
eret+5.297
 voic+4.902
cano+4.879
hell+4.827
 bras+4.515
Neg logit contributions
ationally-8.214
ammy-8.131
 Weld-7.849
netflix-7.826
ittle-7.798
Token:
Token ID25
Feature activation+3.93e+00

Pos logit contributions
 Weld+1.281
ationally+1.250
ammy+1.225
netflix+1.187
ittle+1.181
Neg logit contributions
eret-1.413
cano-1.326
hell-1.294
 voic-1.260
 bras-1.248
Token 0
Token ID657
Feature activation+1.48e+01

Pos logit contributions
 Weld+3.098
ationally+2.975
ammy+2.912
netflix+2.860
ittle+2.850
Neg logit contributions
eret-2.507
cano-2.342
hell-2.259
 bras-2.160
 voic-2.136
Token555
Token ID31046
Feature activation+1.32e+00

Pos logit contributions
 Weld+8.393
ationally+7.155
^^^^+7.096
 Petersen+6.926
ittle+6.851
Neg logit contributions
eret-11.350
cano-10.848
 bras-10.463
hell-10.267
olesc-10.018
Tokenz
Token ID89
Feature activation-2.89e+00

Pos logit contributions
 Weld+1.268
ationally+1.257
ammy+1.243
netflix+1.218
ittle+1.208
Neg logit contributions
eret-0.600
cano-0.544
hell-0.507
 voic-0.504
 bras-0.493
Token MO
Token ID13070
Feature activation-6.01e+00

Pos logit contributions
eret+1.808
cano+1.679
hell+1.652
 voic+1.609
 bras+1.590
Neg logit contributions
ationally-2.262
 Weld-2.239
ammy-2.222
ittle-2.157
netflix-2.141
TokenHA
Token ID7801
Feature activation+1.24e+00

Pos logit contributions
eret+3.977
hell+3.727
cano+3.687
 voic+3.570
 bras+3.529
Neg logit contributions
 Weld-4.321
ationally-4.321
ammy-4.320
netflix-4.126
ittle-4.101
TokenW
Token ID54
Feature activation-5.50e-01

Pos logit contributions
 Weld+0.913
ationally+0.892
ammy+0.879
netflix+0.850
ittle+0.849
Neg logit contributions
eret-0.853
cano-0.797
hell-0.775
 voic-0.756
 bras-0.747
Token x
Token ID2124
Feature activation-2.24e+00

Pos logit contributions
eret+0.758
cano+0.704
hell+0.690
 voic+0.672
 bras+0.666
Neg logit contributions
 Weld-0.836
ationally-0.827
ammy-0.816
netflix-0.788
ittle-0.787
Token.
Token ID13
Feature activation+9.37e-01

Pos logit contributions
eret+1.473
cano+1.362
hell+1.344
 voic+1.290
 bras+1.280
Neg logit contributions
 Weld-1.707
ationally-1.687
ammy-1.671
ittle-1.609
netflix-1.609
Tokenx
Token ID87
Feature activation+2.23e+00

Pos logit contributions
 Weld+0.508
ationally+0.503
ammy+0.490
netflix+0.470
ittle+0.468
Neg logit contributions
eret-0.813
cano-0.774
hell-0.752
 voic-0.751
 bras-0.746
Token.
Token ID13
Feature activation+5.52e+00

Pos logit contributions
 Weld+1.523
ationally+1.492
ammy+1.452
netflix+1.411
ittle+1.402
Neg logit contributions
eret-1.626
cano-1.539
 voic-1.477
hell-1.468
 bras-1.461
Tokenx
Token ID87
Feature activation+8.70e+00

Pos logit contributions
ationally+2.510
 Weld+2.455
ammy+2.418
netflix+2.332
gans+2.292
Neg logit contributions
eret-5.055
cano-4.882
 voic-4.881
 bras-4.861
hell-4.630
Token.
Token ID13
Feature activation+1.45e+01

Pos logit contributions
 Weld+4.823
ationally+4.675
ammy+4.448
^^^^+4.415
gans+4.381
Neg logit contributions
eret-6.974
 notor-6.707
cano-6.657
 voic-6.584
 bras-6.530
Token103
Token ID15197
Feature activation-3.02e+00

Pos logit contributions
ationally+3.021
netflix+2.435
^^^^+2.358
ammy+2.349
gans+2.083
Neg logit contributions
eret-15.860
 bras-15.167
cano-15.109
 voic-15.048
olesc-14.823
Token 105
Token ID13343
Feature activation-3.38e+00

Pos logit contributions
eret+1.996
cano+1.853
hell+1.834
 voic+1.786
 bras+1.761
Neg logit contributions
 Weld-2.237
ationally-2.228
ammy-2.209
ittle-2.129
netflix-2.115
Token49
Token ID2920
Feature activation-4.07e+00

Pos logit contributions
eret+2.136
cano+1.965
hell+1.957
 voic+1.856
 bras+1.854
Neg logit contributions
 Weld-2.629
ationally-2.622
ammy-2.590
ittle-2.494
netflix-2.485
Token36
Token ID2623
Feature activation+3.10e+00

Pos logit contributions
eret+2.568
hell+2.392
cano+2.361
 voic+2.238
 bras+2.229
Neg logit contributions
ationally-3.131
 Weld-3.116
ammy-3.102
netflix-2.992
ittle-2.983
Token x
Token ID2124
Feature activation-1.80e+00

Pos logit contributions
 Weld+2.100
ationally+2.025
ammy+1.976
netflix+1.910
ittle+1.908
Neg logit contributions
eret-2.300
cano-2.184
hell-2.097
 voic-2.048
 bras-2.026
Token84
Token ID5705
Feature activation+1.19e+00

Pos logit contributions
eret+0.863
cano+0.805
hell+0.787
 voic+0.769
 bras+0.761
Neg logit contributions
 Weld-0.821
ationally-0.805
ammy-0.794
netflix-0.770
ittle-0.767
Token million
Token ID1510
Feature activation+9.91e+00

Pos logit contributions
 Weld+0.803
ationally+0.790
ammy+0.777
netflix+0.748
ittle+0.747
Neg logit contributions
eret-0.886
cano-0.832
hell-0.814
 voic-0.793
 bras-0.787
Token miles
Token ID4608
Feature activation+5.72e-01

Pos logit contributions
 Weld+5.147
ationally+5.000
ammy+4.657
ittle+4.597
netflix+4.491
Neg logit contributions
eret-8.254
cano-8.179
hell-7.783
 voic-7.547
 bras-7.421
Token (
Token ID357
Feature activation+5.58e+00

Pos logit contributions
 Weld+0.451
ationally+0.445
ammy+0.438
netflix+0.425
ittle+0.424
Neg logit contributions
eret-0.361
cano-0.334
hell-0.325
 voic-0.316
 bras-0.313
Token940
Token ID46899
Feature activation+6.11e+00

Pos logit contributions
ammy+2.941
 Weld+2.937
ationally+2.908
ittle+2.848
netflix+2.778
Neg logit contributions
eret-4.704
cano-4.536
hell-4.461
 voic-4.390
 bras-4.332
Token million
Token ID1510
Feature activation+1.45e+01

Pos logit contributions
 Weld+3.588
ationally+3.455
ammy+3.429
ittle+3.303
gans+3.271
Neg logit contributions
eret-4.983
cano-4.724
hell-4.616
tes-4.400
 voic-4.353
Token km
Token ID10571
Feature activation+2.84e+00

Pos logit contributions
 Weld+2.111
ationally+1.933
gans+1.384
netflix+1.369
ittle+1.269
Neg logit contributions
eret-16.688
cano-16.053
hell-15.784
 voic-15.489
zek-15.321
Token)
Token ID8
Feature activation+1.55e+00

Pos logit contributions
 Weld+1.691
ationally+1.671
ammy+1.622
ittle+1.570
netflix+1.563
Neg logit contributions
eret-2.323
cano-2.177
hell-2.137
 voic-2.094
 bras-2.079
Token by
Token ID416
Feature activation-5.34e+00

Pos logit contributions
 Weld+1.214
ationally+1.202
ammy+1.177
ittle+1.142
netflix+1.141
Neg logit contributions
eret-0.980
cano-0.911
hell-0.881
 voic-0.861
 bras-0.852
Token­
Token ID3907
Feature activation+4.33e+00

Pos logit contributions
eret+3.277
cano+2.987
hell+2.958
 voic+2.875
 bras+2.870
Neg logit contributions
 Weld-4.219
ammy-4.201
ationally-4.165
netflix-4.029
ittle-3.971
Token­
Token ID3907
Feature activation+4.06e+00

Pos logit contributions
 Weld+3.159
ationally+3.103
ammy+3.011
ittle+2.984
netflix+2.921
Neg logit contributions
eret-2.926
cano-2.757
hell-2.634
 voic-2.630
 bras-2.614
Token go
Token ID467
Feature activation-7.82e-01

Pos logit contributions
eret+0.195
cano+0.182
hell+0.177
 voic+0.173
 bras+0.171
Neg logit contributions
 Weld-0.209
ationally-0.206
ammy-0.203
netflix-0.196
ittle-0.196
Token over
Token ID625
Feature activation-1.98e+00

Pos logit contributions
eret+0.519
cano+0.482
hell+0.472
 voic+0.461
 bras+0.455
Neg logit contributions
 Weld-0.589
ationally-0.581
ammy-0.573
netflix-0.554
ittle-0.552
Token some
Token ID617
Feature activation-2.68e+00

Pos logit contributions
eret+1.349
cano+1.248
hell+1.230
 voic+1.214
 bras+1.200
Neg logit contributions
 Weld-1.429
ationally-1.420
ammy-1.409
ittle-1.360
netflix-1.357
Token basic
Token ID4096
Feature activation-7.70e-01

Pos logit contributions
eret+1.726
cano+1.612
hell+1.576
 voic+1.569
 bras+1.540
Neg logit contributions
 Weld-2.032
ationally-2.015
ammy-2.007
netflix-1.943
ittle-1.941
Token dos
Token ID23430
Feature activation-2.74e+00

Pos logit contributions
eret+0.510
cano+0.472
hell+0.462
 voic+0.457
 bras+0.448
Neg logit contributions
 Weld-0.579
ationally-0.574
ammy-0.567
netflix-0.549
ittle-0.548
Token and
Token ID290
Feature activation+1.45e+01

Pos logit contributions
eret+1.822
cano+1.663
hell+1.654
 voic+1.598
 bras+1.591
Neg logit contributions
 Weld-2.059
ationally-2.036
ammy-2.011
netflix-1.935
ittle-1.930
Token don
Token ID836
Feature activation+7.29e+00

Pos logit contributions
 Weld+6.329
gans+5.799
ammy+5.487
onds+5.462
 dwarves+5.252
Neg logit contributions
cano-12.515
eret-12.120
hell-11.367
AppData-11.342
olesc-11.232
Token't
Token ID470
Feature activation+4.86e+00

Pos logit contributions
 Weld+4.999
ationally+4.833
ammy+4.764
netflix+4.741
ittle+4.719
Neg logit contributions
eret-4.856
cano-4.789
hell-4.537
 voic-4.496
 bras-4.345
Tokens
Token ID82
Feature activation-1.28e-01

Pos logit contributions
 Weld+4.163
ationally+4.094
ammy+4.016
ittle+3.931
netflix+3.860
Neg logit contributions
eret-2.603
cano-2.438
hell-2.404
 bras-2.155
 voic-2.154
Token,
Token ID11
Feature activation-2.47e-01

Pos logit contributions
eret+0.087
cano+0.081
hell+0.080
 voic+0.077
 bras+0.077
Neg logit contributions
 Weld-0.095
ationally-0.094
ammy-0.092
netflix-0.089
ittle-0.089
Token using
Token ID1262
Feature activation+4.73e-01

Pos logit contributions
eret+0.171
cano+0.160
hell+0.156
 voic+0.153
 bras+0.151
Neg logit contributions
 Weld-0.179
ationally-0.176
ammy-0.174
netflix-0.168
ittle-0.168
Token x
Token ID2124
Feature activation-1.34e+00

Pos logit contributions
eret+0.215
cano+0.200
hell+0.195
 voic+0.190
 bras+0.189
Neg logit contributions
 Weld-0.227
ationally-0.223
ammy-0.220
netflix-0.212
ittle-0.212
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
eret+0.904
cano+0.840
hell+0.823
 voic+0.798
 bras+0.791
Neg logit contributions
 Weld-0.997
ationally-0.983
ammy-0.970
netflix-0.936
ittle-0.936
Tokenx
Token ID87
Feature activation+3.43e+00

Pos logit contributions
 Weld+0.584
ationally+0.580
ammy+0.564
netflix+0.542
ittle+0.538
Neg logit contributions
eret-0.943
cano-0.898
 voic-0.873
hell-0.871
 bras-0.867
Token.
Token ID13
Feature activation+7.97e+00

Pos logit contributions
 Weld+2.265
ationally+2.210
ammy+2.136
netflix+2.086
ittle+2.071
Neg logit contributions
eret-2.564
cano-2.441
 voic-2.349
 bras-2.324
hell-2.312
Tokenx
Token ID87
Feature activation+9.77e+00

Pos logit contributions
ationally+3.317
 Weld+3.209
ammy+3.179
gans+3.038
netflix+3.028
Neg logit contributions
eret-7.376
 voic-7.267
 bras-7.259
cano-7.198
 notor-7.048
Token.
Token ID13
Feature activation+1.44e+01

Pos logit contributions
 Weld+5.309
ationally+4.967
ammy+4.824
^^^^+4.780
ittle+4.761
Neg logit contributions
eret-7.827
 notor-7.579
cano-7.575
 voic-7.484
 bras-7.403
Token149
Token ID19442
Feature activation-2.31e+00

Pos logit contributions
 Weld+4.422
ittle+4.373
ammy+4.003
^^^^+3.980
ationally+3.933
Neg logit contributions
eret-14.082
cano-13.656
 voic-13.214
 bras-13.173
hell-13.150
Token 110
Token ID9796
Feature activation+3.59e+00

Pos logit contributions
eret+1.616
cano+1.512
hell+1.489
 voic+1.449
 bras+1.428
Neg logit contributions
 Weld-1.637
ationally-1.633
ammy-1.610
ittle-1.554
netflix-1.545
Token22
Token ID1828
Feature activation+3.08e+00

Pos logit contributions
 Weld+2.450
ationally+2.378
ammy+2.316
netflix+2.264
gans+2.248
Neg logit contributions
eret-2.611
cano-2.455
 voic-2.358
hell-2.350
 bras-2.319
Token26
Token ID2075
Feature activation+1.52e+00

Pos logit contributions
 Weld+2.171
ationally+2.097
ammy+2.043
netflix+1.987
ittle+1.982
Neg logit contributions
eret-2.225
cano-2.093
 voic-1.987
hell-1.985
 bras-1.960
Token x
Token ID2124
Feature activation-1.55e+00

Pos logit contributions
 Weld+1.065
ationally+1.040
ammy+1.018
netflix+0.985
ittle+0.983
Neg logit contributions
eret-1.096
cano-1.032
hell-0.997
 voic-0.975
 bras-0.965
Token x
Token ID2124
Feature activation-1.46e+00

Pos logit contributions
 Weld+0.799
ationally+0.781
ammy+0.767
netflix+0.741
ittle+0.740
Neg logit contributions
eret-0.795
cano-0.747
hell-0.724
 voic-0.707
 bras-0.699
Token.
Token ID13
Feature activation+1.59e+00

Pos logit contributions
eret+0.982
cano+0.913
hell+0.895
 voic+0.866
 bras+0.859
Neg logit contributions
 Weld-1.094
ationally-1.079
ammy-1.065
netflix-1.027
ittle-1.027
Tokenx
Token ID87
Feature activation+3.63e+00

Pos logit contributions
 Weld+0.840
ationally+0.836
ammy+0.813
netflix+0.782
ittle+0.774
Neg logit contributions
eret-1.391
cano-1.327
 voic-1.295
 bras-1.286
hell-1.284
Token.
Token ID13
Feature activation+7.21e+00

Pos logit contributions
 Weld+2.379
ationally+2.332
ammy+2.261
netflix+2.204
ittle+2.178
Neg logit contributions
eret-2.715
cano-2.583
 voic-2.502
 bras-2.473
hell-2.437
Tokenx
Token ID87
Feature activation+1.15e+01

Pos logit contributions
ationally+3.090
 Weld+2.989
ammy+2.979
netflix+2.870
gans+2.818
Neg logit contributions
eret-6.684
 voic-6.539
 bras-6.502
cano-6.455
 notor-6.259
Token.
Token ID13
Feature activation+1.44e+01

Pos logit contributions
 Weld+5.771
ationally+5.600
^^^^+5.424
ammy+5.317
gans+5.286
Neg logit contributions
 notor-9.480
eret-9.401
 voic-9.048
 contrace-8.982
 bras-8.949
Token102
Token ID15377
Feature activation-1.75e+00

Pos logit contributions
ationally+3.801
 Weld+3.768
^^^^+3.569
ammy+3.548
gans+3.287
Neg logit contributions
eret-14.737
 bras-14.242
 voic-14.205
olesc-13.883
cano-13.665
Token 113
Token ID17318
Feature activation-5.21e-01

Pos logit contributions
eret+1.173
cano+1.091
hell+1.074
 voic+1.046
 bras+1.032
Neg logit contributions
 Weld-1.300
ationally-1.289
ammy-1.276
ittle-1.229
netflix-1.227
Token44
Token ID2598
Feature activation-3.10e+00

Pos logit contributions
eret+0.354
cano+0.330
hell+0.322
 voic+0.314
 bras+0.311
Neg logit contributions
 Weld-0.385
ationally-0.379
ammy-0.374
netflix-0.361
ittle-0.361
Token17
Token ID1558
Feature activation-1.12e+00

Pos logit contributions
eret+1.985
hell+1.839
cano+1.835
 voic+1.745
 bras+1.735
Neg logit contributions
 Weld-2.363
ationally-2.361
ammy-2.337
netflix-2.254
ittle-2.248
Token x
Token ID2124
Feature activation-2.24e+00

Pos logit contributions
eret+0.758
cano+0.704
hell+0.690
 voic+0.672
 bras+0.666
Neg logit contributions
 Weld-0.836
ationally-0.827
ammy-0.816
netflix-0.788
ittle-0.787
Token x
Token ID2124
Feature activation-2.26e+00

Pos logit contributions
eret+0.060
cano+0.056
hell+0.054
 voic+0.053
 bras+0.052
Neg logit contributions
 Weld-0.062
ationally-0.061
ammy-0.060
netflix-0.058
ittle-0.058
Token.
Token ID13
Feature activation+3.35e-01

Pos logit contributions
eret+1.487
cano+1.374
hell+1.357
 voic+1.302
 bras+1.292
Neg logit contributions
 Weld-1.722
ationally-1.703
ammy-1.687
ittle-1.624
netflix-1.622
Tokenx
Token ID87
Feature activation+2.30e+00

Pos logit contributions
 Weld+0.186
ationally+0.183
ammy+0.179
netflix+0.172
ittle+0.171
Neg logit contributions
eret-0.288
cano-0.273
hell-0.266
 voic-0.264
 bras-0.262
Token.
Token ID13
Feature activation+4.97e+00

Pos logit contributions
 Weld+1.565
ationally+1.530
ammy+1.489
netflix+1.451
ittle+1.441
Neg logit contributions
eret-1.681
cano-1.590
 voic-1.525
hell-1.516
 bras-1.508
Tokenx
Token ID87
Feature activation+7.50e+00

Pos logit contributions
ationally+2.320
 Weld+2.284
ammy+2.233
netflix+2.157
ittle+2.115
Neg logit contributions
eret-4.519
cano-4.356
 voic-4.335
 bras-4.318
hell-4.139
Token.
Token ID13
Feature activation+1.43e+01

Pos logit contributions
 Weld+4.332
ationally+4.099
ammy+3.992
ittle+3.866
gans+3.859
Neg logit contributions
eret-5.918
cano-5.741
 notor-5.654
 voic-5.603
 bras-5.597
Token154
Token ID21526
Feature activation-3.09e+00

Pos logit contributions
 Weld+5.632
ammy+5.334
ationally+5.310
ittle+5.277
uld+4.845
Neg logit contributions
 bras-12.148
eret-11.905
cano-11.881
 notor-11.752
 contrace-11.738
Token 109
Token ID16003
Feature activation-1.46e+00

Pos logit contributions
eret+2.099
cano+1.971
hell+1.947
 voic+1.896
 bras+1.866
Neg logit contributions
 Weld-2.217
ationally-2.215
ammy-2.191
ittle-2.114
netflix-2.097
Token77
Token ID3324
Feature activation-8.76e-01

Pos logit contributions
eret+0.984
cano+0.915
hell+0.899
 voic+0.868
 bras+0.861
Neg logit contributions
 Weld-1.091
ationally-1.079
ammy-1.064
ittle-1.026
netflix-1.025
Token39
Token ID2670
Feature activation-4.38e-01

Pos logit contributions
eret+0.587
cano+0.546
hell+0.536
 voic+0.519
 bras+0.514
Neg logit contributions
 Weld-0.654
ationally-0.646
ammy-0.638
netflix-0.615
ittle-0.615
Token x
Token ID2124
Feature activation-2.66e+00

Pos logit contributions
eret+0.301
cano+0.281
hell+0.274
 voic+0.267
 bras+0.265
Neg logit contributions
 Weld-0.321
ationally-0.316
ammy-0.311
netflix-0.300
ittle-0.300
Token604
Token ID31916
Feature activation-1.31e+00

Pos logit contributions
eret+0.868
cano+0.810
hell+0.795
 voic+0.769
 bras+0.763
Neg logit contributions
 Weld-0.847
ationally-0.836
ammy-0.827
ittle-0.792
netflix-0.791
Token x
Token ID2124
Feature activation-3.04e+00

Pos logit contributions
eret+0.884
cano+0.819
hell+0.804
 voic+0.783
 bras+0.776
Neg logit contributions
 Weld-0.978
ationally-0.965
ammy-0.953
netflix-0.920
ittle-0.919
Token.
Token ID13
Feature activation+2.37e-01

Pos logit contributions
eret+1.950
cano+1.791
hell+1.782
 voic+1.694
 bras+1.683
Neg logit contributions
 Weld-2.349
ationally-2.327
ammy-2.315
ittle-2.225
netflix-2.220
Tokenx
Token ID87
Feature activation+3.77e+00

Pos logit contributions
 Weld+0.132
ationally+0.131
ammy+0.127
netflix+0.122
ittle+0.122
Neg logit contributions
eret-0.203
cano-0.193
hell-0.188
 voic-0.186
 bras-0.185
Token.
Token ID13
Feature activation+9.88e+00

Pos logit contributions
 Weld+2.475
ationally+2.413
ammy+2.332
netflix+2.276
ittle+2.260
Neg logit contributions
eret-2.829
cano-2.695
 voic-2.598
 bras-2.567
hell-2.546
Tokenx
Token ID87
Feature activation+1.37e+01

Pos logit contributions
ationally+3.847
ammy+3.740
 Weld+3.737
gans+3.534
ittle+3.516
Neg logit contributions
 bras-9.153
eret-9.116
 voic-9.109
 notor-9.023
 contrace-8.943
Token.
Token ID13
Feature activation+1.68e+01

Pos logit contributions
 Weld+6.696
ationally+6.205
ammy+6.130
^^^^+6.080
ittle+6.080
Neg logit contributions
 notor-11.254
eret-10.784
 contrace-10.779
 voic-10.570
 bras-10.544
Token153
Token ID21395
Feature activation-1.84e+00

Pos logit contributions
 Weld+6.240
ittle+5.968
ammy+5.851
ationally+5.655
uld+5.631
Neg logit contributions
eret-14.358
 bras-14.258
cano-13.913
 Instr-13.846
 notor-13.825
Token 11
Token ID1367
Feature activation+1.66e+00

Pos logit contributions
eret+1.302
cano+1.219
hell+1.200
 voic+1.170
 bras+1.157
Neg logit contributions
 Weld-1.291
ationally-1.282
ammy-1.265
ittle-1.217
netflix-1.214
Token75
Token ID2425
Feature activation-3.19e-01

Pos logit contributions
 Weld+1.194
ationally+1.165
ammy+1.144
netflix+1.110
ittle+1.105
Neg logit contributions
eret-1.161
cano-1.090
hell-1.054
 voic-1.039
 bras-1.028
Token163
Token ID24136
Feature activation-8.57e-02

Pos logit contributions
eret+0.232
cano+0.217
hell+0.212
 voic+0.207
 bras+0.205
Neg logit contributions
 Weld-0.222
ationally-0.218
ammy-0.215
netflix-0.207
ittle-0.207
Token x
Token ID2124
Feature activation-2.80e+00

Pos logit contributions
eret+0.464
cano+0.433
hell+0.423
 voic+0.412
 bras+0.408
Neg logit contributions
 Weld-0.496
ationally-0.489
ammy-0.482
netflix-0.465
ittle-0.465
Token.
Token ID13
Feature activation+1.27e+00

Pos logit contributions
eret+1.811
cano+1.667
hell+1.655
 voic+1.576
 bras+1.565
Neg logit contributions
 Weld-2.157
ationally-2.134
ammy-2.121
ittle-2.038
netflix-2.035
Tokenx
Token ID87
Feature activation+3.53e+00

Pos logit contributions
 Weld+0.680
ationally+0.676
ammy+0.657
netflix+0.631
ittle+0.627
Neg logit contributions
eret-1.112
cano-1.060
 voic-1.032
hell-1.027
 bras-1.025
Token.
Token ID13
Feature activation+7.07e+00

Pos logit contributions
 Weld+2.329
ationally+2.271
ammy+2.192
netflix+2.145
ittle+2.126
Neg logit contributions
eret-2.650
cano-2.519
 voic-2.423
 bras-2.397
hell-2.379
Tokenx
Token ID87
Feature activation+9.49e+00

Pos logit contributions
ationally+3.065
 Weld+2.955
ammy+2.901
netflix+2.813
gans+2.781
Neg logit contributions
eret-6.572
 voic-6.399
 bras-6.385
cano-6.369
 notor-6.140
Token.
Token ID13
Feature activation+1.33e+01

Pos logit contributions
 Weld+5.165
ationally+4.997
^^^^+4.767
ammy+4.684
netflix+4.579
Neg logit contributions
eret-7.703
 notor-7.476
cano-7.454
 voic-7.269
 bras-7.260
Token132
Token ID19924
Feature activation-1.89e+00

Pos logit contributions
ationally+5.470
 Weld+5.357
^^^^+5.133
ammy+5.046
ittle+4.778
Neg logit contributions
eret-11.813
cano-11.564
 bras-11.530
 contrace-11.266
 voic-11.230
Token 10
Token ID838
Feature activation-1.81e+00

Pos logit contributions
eret+1.269
cano+1.182
hell+1.161
 voic+1.129
 bras+1.117
Neg logit contributions
 Weld-1.396
ationally-1.383
ammy-1.366
netflix-1.316
ittle-1.316
Token86
Token ID4521
Feature activation-3.88e+00

Pos logit contributions
eret+1.208
cano+1.121
hell+1.102
 voic+1.064
 bras+1.056
Neg logit contributions
 Weld-1.362
ationally-1.347
ammy-1.331
ittle-1.283
netflix-1.282
Token213
Token ID26427
Feature activation+2.83e+00

Pos logit contributions
eret+2.749
cano+2.560
hell+2.526
 voic+2.421
 bras+2.416
Neg logit contributions
 Weld-2.690
ationally-2.681
ammy-2.669
ittle-2.535
netflix-2.520
Token x
Token ID2124
Feature activation-7.92e-01

Pos logit contributions
 Weld+1.901
ationally+1.853
ammy+1.807
netflix+1.749
ittle+1.748
Neg logit contributions
eret-2.093
cano-1.991
hell-1.913
 voic-1.863
 bras-1.846
Token x
Token ID2124
Feature activation-2.36e+00

Pos logit contributions
 Weld+0.694
ationally+0.679
ammy+0.667
netflix+0.644
ittle+0.644
Neg logit contributions
eret-0.690
cano-0.648
hell-0.628
 voic-0.613
 bras-0.606
Token.
Token ID13
Feature activation+8.63e-01

Pos logit contributions
eret+1.547
cano+1.430
hell+1.412
 voic+1.353
 bras+1.343
Neg logit contributions
 Weld-1.802
ationally-1.782
ammy-1.766
ittle-1.699
netflix-1.696
Tokenx
Token ID87
Feature activation+3.85e+00

Pos logit contributions
 Weld+0.470
ationally+0.465
ammy+0.453
netflix+0.435
ittle+0.433
Neg logit contributions
eret-0.747
cano-0.710
hell-0.690
 voic-0.689
 bras-0.685
Token.
Token ID13
Feature activation+6.91e+00

Pos logit contributions
 Weld+2.519
ationally+2.462
ammy+2.373
netflix+2.328
ittle+2.300
Neg logit contributions
eret-2.892
cano-2.758
 voic-2.655
 bras-2.628
hell-2.597
Tokenx
Token ID87
Feature activation+1.07e+01

Pos logit contributions
ationally+3.019
 Weld+2.941
ammy+2.870
netflix+2.779
gans+2.730
Neg logit contributions
eret-6.391
 voic-6.213
cano-6.194
 bras-6.193
 notor-5.936
Token.
Token ID13
Feature activation+1.32e+01

Pos logit contributions
 Weld+5.809
ationally+5.682
^^^^+5.313
ammy+5.264
netflix+5.250
Neg logit contributions
eret-8.527
cano-8.309
 notor-8.155
 voic-8.103
 bras-7.999
Token131
Token ID22042
Feature activation-3.15e+00

Pos logit contributions
ationally+6.032
 Weld+5.863
ammy+5.432
^^^^+5.252
uld+5.132
Neg logit contributions
eret-11.331
cano-11.312
 voic-10.882
 bras-10.851
olesc-10.345
Token 111
Token ID13374
Feature activation+4.92e+00

Pos logit contributions
eret+2.037
cano+1.893
hell+1.867
 voic+1.811
 bras+1.789
Neg logit contributions
 Weld-2.388
ationally-2.378
ammy-2.354
ittle-2.268
netflix-2.268
Token58
Token ID3365
Feature activation-9.88e-01

Pos logit contributions
 Weld+3.298
ationally+3.175
ammy+3.091
netflix+3.035
gans+3.021
Neg logit contributions
eret-3.603
cano-3.415
 voic-3.268
hell-3.214
 bras-3.213
Token91
Token ID6420
Feature activation-6.77e-01

Pos logit contributions
eret+0.664
cano+0.617
hell+0.607
 voic+0.587
 bras+0.582
Neg logit contributions
 Weld-0.735
ationally-0.727
ammy-0.717
netflix-0.692
ittle-0.691
Token x
Token ID2124
Feature activation-2.80e+00

Pos logit contributions
eret+0.464
cano+0.433
hell+0.423
 voic+0.412
 bras+0.408
Neg logit contributions
 Weld-0.496
ationally-0.489
ammy-0.482
netflix-0.465
ittle-0.465
Token x
Token ID2124
Feature activation-2.66e+00

Pos logit contributions
eret+0.301
cano+0.281
hell+0.274
 voic+0.267
 bras+0.265
Neg logit contributions
 Weld-0.321
ationally-0.316
ammy-0.311
netflix-0.300
ittle-0.300
Token.
Token ID13
Feature activation+4.61e-02

Pos logit contributions
eret+1.722
cano+1.586
hell+1.575
 voic+1.502
 bras+1.490
Neg logit contributions
 Weld-2.047
ationally-2.027
ammy-2.014
ittle-1.936
netflix-1.933
Tokenx
Token ID87
Feature activation+1.66e+00

Pos logit contributions
 Weld+0.026
ationally+0.026
ammy+0.025
netflix+0.024
ittle+0.024
Neg logit contributions
eret-0.039
cano-0.037
hell-0.036
 voic-0.036
 bras-0.036
Token.
Token ID13
Feature activation+4.80e+00

Pos logit contributions
 Weld+1.154
ationally+1.129
ammy+1.101
netflix+1.071
ittle+1.066
Neg logit contributions
eret-1.197
cano-1.129
hell-1.082
 voic-1.081
 bras-1.069
Tokenx
Token ID87
Feature activation+6.54e+00

Pos logit contributions
ationally+2.256
 Weld+2.218
ammy+2.159
netflix+2.087
gans+2.064
Neg logit contributions
eret-4.370
cano-4.210
 voic-4.193
 bras-4.167
hell-4.005
Token.
Token ID13
Feature activation+1.32e+01

Pos logit contributions
 Weld+3.945
ationally+3.752
ammy+3.640
gans+3.571
ittle+3.567
Neg logit contributions
eret-5.068
cano-4.911
 voic-4.754
 bras-4.737
 notor-4.666
Token155
Token ID18742
Feature activation+1.48e-01

Pos logit contributions
ittle+6.148
 Weld+5.806
vard+5.611
gans+5.589
ammy+5.477
Neg logit contributions
cano-10.768
 bras-10.507
eret-10.473
hell-10.375
 voic-10.171
Token 10
Token ID838
Feature activation-3.78e+00

Pos logit contributions
 Weld+0.103
ationally+0.101
ammy+0.100
netflix+0.096
ittle+0.096
Neg logit contributions
eret-0.107
cano-0.100
hell-0.098
 voic-0.096
 bras-0.095
Token384
Token ID22842
Feature activation-3.09e+00

Pos logit contributions
eret+2.444
cano+2.261
hell+2.243
 voic+2.134
 bras+2.127
Neg logit contributions
 Weld-2.871
ationally-2.854
ammy-2.837
ittle-2.721
netflix-2.717
Token38
Token ID2548
Feature activation+2.77e+00

Pos logit contributions
eret+1.964
cano+1.814
hell+1.809
 voic+1.724
 bras+1.716
Neg logit contributions
 Weld-2.386
ationally-2.378
ammy-2.359
netflix-2.268
ittle-2.265
Token x
Token ID2124
Feature activation-2.38e+00

Pos logit contributions
 Weld+1.882
ationally+1.829
ammy+1.781
netflix+1.724
ittle+1.722
Neg logit contributions
eret-2.053
cano-1.939
hell-1.864
 voic-1.823
 bras-1.805
Token teams
Token ID3466
Feature activation+1.63e+00

Pos logit contributions
 Weld+2.372
ationally+2.356
ammy+2.276
ittle+2.218
netflix+2.184
Neg logit contributions
eret-2.342
cano-2.168
hell-2.103
 voic-2.063
 bras-2.004
Token,
Token ID11
Feature activation+3.85e+00

Pos logit contributions
 Weld+1.170
ationally+1.148
ammy+1.131
ittle+1.092
netflix+1.085
Neg logit contributions
eret-1.159
cano-1.078
hell-1.044
 voic-1.023
 bras-1.013
Token along
Token ID1863
Feature activation+1.88e+00

Pos logit contributions
 Weld+2.679
ationally+2.606
ammy+2.533
ittle+2.451
netflix+2.429
Neg logit contributions
eret-2.852
cano-2.652
hell-2.561
 voic-2.468
 bras-2.432
Token with
Token ID351
Feature activation+1.99e+00

Pos logit contributions
 Weld+1.365
ationally+1.341
ammy+1.308
ittle+1.274
netflix+1.268
Neg logit contributions
eret-1.302
cano-1.215
hell-1.188
 voic-1.153
 bras-1.141
Token all
Token ID477
Feature activation+2.34e+00

Pos logit contributions
 Weld+1.395
ationally+1.365
ammy+1.334
ittle+1.289
netflix+1.283
Neg logit contributions
eret-1.448
cano-1.354
hell-1.320
 voic-1.281
 bras-1.261
Token int
Token ID493
Feature activation+1.31e+01

Pos logit contributions
 Weld+1.668
ationally+1.634
ammy+1.596
ittle+1.543
netflix+1.535
Neg logit contributions
eret-1.675
cano-1.560
hell-1.519
 voic-1.479
 bras-1.453
Tokenram
Token ID859
Feature activation+7.37e+00

Pos logit contributions
ationally+8.286
 Weld+8.286
ammy+7.996
ittle+7.905
netflix+7.570
Neg logit contributions
cano-8.788
eret-8.055
 voic-7.959
 bras-7.786
hell-7.665
Tokenural
Token ID1523
Feature activation+2.12e-01

Pos logit contributions
ationally+3.438
 Weld+3.271
ammy+3.210
ittle+2.964
netflix+2.906
Neg logit contributions
eret-6.886
cano-6.648
 voic-6.409
 bras-6.401
hell-6.381
Token activities
Token ID4568
Feature activation+2.45e+00

Pos logit contributions
 Weld+0.152
ationally+0.149
ammy+0.147
netflix+0.142
ittle+0.142
Neg logit contributions
eret-0.149
cano-0.139
hell-0.136
 voic-0.133
 bras-0.131
Token,
Token ID11
Feature activation+2.70e+00

Pos logit contributions
 Weld+1.737
ationally+1.704
ammy+1.662
ittle+1.614
netflix+1.602
Neg logit contributions
eret-1.753
cano-1.634
hell-1.583
 voic-1.553
 bras-1.529
Token including
Token ID1390
Feature activation+2.63e+00

Pos logit contributions
 Weld+1.907
ationally+1.860
ammy+1.818
ittle+1.766
netflix+1.752
Neg logit contributions
eret-1.945
cano-1.806
hell-1.761
 voic-1.703
 bras-1.680
Token x
Token ID2124
Feature activation-2.99e+00

Pos logit contributions
eret+1.012
cano+0.940
hell+0.921
 voic+0.896
 bras+0.888
Neg logit contributions
 Weld-1.111
ationally-1.097
ammy-1.082
ittle-1.044
netflix-1.044
Token.
Token ID13
Feature activation-2.83e-01

Pos logit contributions
eret+1.914
cano+1.756
hell+1.748
 voic+1.662
 bras+1.651
Neg logit contributions
 Weld-2.311
ationally-2.290
ammy-2.280
ittle-2.189
netflix-2.184
Tokenx
Token ID87
Feature activation+1.55e-01

Pos logit contributions
eret+0.240
cano+0.228
hell+0.223
 voic+0.219
 bras+0.218
Neg logit contributions
 Weld-0.161
ationally-0.158
ammy-0.155
netflix-0.148
ittle-0.148
Token.
Token ID13
Feature activation+4.58e+00

Pos logit contributions
 Weld+0.112
ationally+0.110
ammy+0.108
netflix+0.105
ittle+0.105
Neg logit contributions
eret-0.108
cano-0.101
hell-0.098
 voic-0.096
 bras-0.095
Tokenx
Token ID87
Feature activation+3.36e+00

Pos logit contributions
ationally+2.176
 Weld+2.142
ammy+2.086
netflix+2.008
gans+1.995
Neg logit contributions
eret-4.160
cano-4.010
 voic-3.979
 bras-3.957
hell-3.817
Token.
Token ID13
Feature activation+1.30e+01

Pos logit contributions
 Weld+2.224
ationally+2.171
ammy+2.113
netflix+2.050
ittle+2.036
Neg logit contributions
eret-2.515
cano-2.380
 voic-2.299
 bras-2.274
hell-2.262
Token172
Token ID23628
Feature activation-3.01e-01

Pos logit contributions
ammy+5.909
ationally+5.777
^^^^+5.745
uld+5.565
 Weld+5.511
Neg logit contributions
eret-11.149
 bras-10.446
 voic-10.435
 contrace-10.263
cano-10.013
Token 100
Token ID1802
Feature activation-7.02e-01

Pos logit contributions
eret+0.219
cano+0.205
hell+0.201
 voic+0.196
 bras+0.194
Neg logit contributions
 Weld-0.208
ationally-0.205
ammy-0.202
netflix-0.195
ittle-0.194
Token79
Token ID3720
Feature activation-4.88e+00

Pos logit contributions
eret+0.483
cano+0.451
hell+0.440
 voic+0.429
 bras+0.425
Neg logit contributions
 Weld-0.514
ationally-0.506
ammy-0.499
netflix-0.481
ittle-0.481
Token72
Token ID4761
Feature activation-6.20e-01

Pos logit contributions
eret+3.039
hell+2.833
cano+2.798
tes+2.637
 voic+2.629
Neg logit contributions
ationally-3.777
ammy-3.753
 Weld-3.750
ittle-3.597
netflix-3.584
Token x
Token ID2124
Feature activation-1.10e+00

Pos logit contributions
eret+0.424
cano+0.395
hell+0.386
 voic+0.376
 bras+0.372
Neg logit contributions
 Weld-0.456
ationally-0.449
ammy-0.443
netflix-0.427
ittle-0.427
Token x
Token ID2124
Feature activation-1.75e+00

Pos logit contributions
eret+0.023
cano+0.022
hell+0.021
 voic+0.021
 bras+0.021
Neg logit contributions
 Weld-0.025
ationally-0.024
ammy-0.024
netflix-0.023
ittle-0.023
Token.
Token ID13
Feature activation+1.84e+00

Pos logit contributions
eret+1.164
cano+1.078
hell+1.061
 voic+1.023
 bras+1.015
Neg logit contributions
 Weld-1.318
ationally-1.301
ammy-1.287
ittle-1.240
netflix-1.239
Tokenx
Token ID87
Feature activation+2.02e+00

Pos logit contributions
 Weld+0.962
ationally+0.960
ammy+0.930
netflix+0.894
ittle+0.888
Neg logit contributions
eret-1.616
cano-1.542
 voic-1.506
 bras-1.497
hell-1.490
Token.
Token ID13
Feature activation+5.88e+00

Pos logit contributions
 Weld+1.389
ationally+1.362
ammy+1.325
netflix+1.292
ittle+1.283
Neg logit contributions
eret-1.464
cano-1.382
 voic-1.328
hell-1.321
 bras-1.312
Tokenx
Token ID87
Feature activation+4.30e+00

Pos logit contributions
ationally+2.638
 Weld+2.566
ammy+2.509
netflix+2.435
gans+2.433
Neg logit contributions
eret-5.416
 voic-5.241
cano-5.229
 bras-5.204
 notor-4.996
Token.
Token ID13
Feature activation+1.30e+01

Pos logit contributions
 Weld+2.785
ationally+2.715
ammy+2.634
netflix+2.572
gans+2.551
Neg logit contributions
eret-3.258
cano-3.086
 voic-2.999
 bras-2.958
hell-2.914
Token171
Token ID27192
Feature activation-7.11e-01

Pos logit contributions
uld+4.339
ationally+4.288
gans+4.283
ammy+4.234
 Weld+4.098
Neg logit contributions
eret-13.154
cano-12.116
 voic-12.101
 bras-12.000
 Xperia-11.606
Token 102
Token ID15143
Feature activation-2.77e+00

Pos logit contributions
eret+0.524
cano+0.491
hell+0.481
 voic+0.470
 bras+0.465
Neg logit contributions
 Weld-0.484
ationally-0.477
ammy-0.470
netflix-0.452
ittle-0.452
Token30
Token ID1270
Feature activation-2.37e+00

Pos logit contributions
eret+1.908
cano+1.767
hell+1.748
 voic+1.686
 bras+1.683
Neg logit contributions
 Weld-2.000
ationally-1.989
ammy-1.968
ittle-1.882
netflix-1.880
Token86
Token ID4521
Feature activation-1.50e+00

Pos logit contributions
eret+1.528
cano+1.414
hell+1.409
 voic+1.341
 bras+1.332
Neg logit contributions
 Weld-1.811
ationally-1.798
ammy-1.783
ittle-1.718
netflix-1.714
Token x
Token ID2124
Feature activation-2.99e+00

Pos logit contributions
eret+1.012
cano+0.940
hell+0.921
 voic+0.896
 bras+0.888
Neg logit contributions
 Weld-1.111
ationally-1.097
ammy-1.082
ittle-1.044
netflix-1.044
Token.
Token ID13
Feature activation-4.39e-01

Pos logit contributions
eret+2.695
cano+2.522
hell+2.473
 bras+2.357
 voic+2.349
Neg logit contributions
 Weld-3.321
ationally-3.279
ammy-3.276
netflix-3.174
ittle-3.158
Token
Token ID198
Feature activation-2.24e+00

Pos logit contributions
eret+0.318
cano+0.297
hell+0.291
 voic+0.283
 bras+0.281
Neg logit contributions
 Weld-0.305
ationally-0.301
ammy-0.296
ittle-0.285
netflix-0.285
Token
Token ID198
Feature activation-2.44e+00

Pos logit contributions
eret+1.581
cano+1.468
hell+1.459
 voic+1.402
 bras+1.392
Neg logit contributions
 Weld-1.590
ationally-1.573
ammy-1.557
ittle-1.495
netflix-1.493
TokenT
Token ID51
Feature activation+2.51e+00

Pos logit contributions
eret+1.690
hell+1.580
cano+1.576
 voic+1.496
 bras+1.485
Neg logit contributions
 Weld-1.751
ationally-1.723
ammy-1.699
ittle-1.648
netflix-1.632
TokenRE
Token ID2200
Feature activation-7.69e+00

Pos logit contributions
 Weld+1.723
ationally+1.700
ammy+1.676
ittle+1.613
netflix+1.592
Neg logit contributions
eret-1.826
cano-1.730
hell-1.676
 voic-1.646
 bras-1.628
TokenAS
Token ID1921
Feature activation-1.56e+01

Pos logit contributions
eret+4.160
cano+3.699
hell+3.674
 voic+3.518
 bras+3.500
Neg logit contributions
ammy-6.492
 Weld-6.366
ationally-6.303
netflix-6.289
ittle-6.254
TokenURE
Token ID11335
Feature activation-7.51e+00

Pos logit contributions
eret+8.960
hell+8.725
cano+7.797
zek+7.559
 voic+7.444
Neg logit contributions
ammy-10.755
 Weld-10.666
netflix-10.543
ationally-10.370
gans-10.328
Token HUN
Token ID41041
Feature activation-1.37e+01

Pos logit contributions
eret+3.834
hell+3.700
cano+3.541
 voic+3.417
 bras+3.363
Neg logit contributions
ationally-6.362
ammy-6.328
 Weld-6.213
ittle-6.191
netflix-6.175
TokenTER
Token ID5781
Feature activation-5.99e+00

Pos logit contributions
eret+5.903
hell+5.575
tes+5.407
cano+5.140
butt+5.012
Neg logit contributions
ammy-12.268
ationally-11.900
ittle-11.501
netflix-11.480
 Weld-11.243
Token
Token ID198
Feature activation-3.57e+00

Pos logit contributions
eret+3.879
hell+3.653
cano+3.595
 voic+3.503
 bras+3.492
Neg logit contributions
ationally-4.372
 Weld-4.370
ammy-4.340
ittle-4.202
netflix-4.138
Token
Token ID198
Feature activation-4.80e+00

Pos logit contributions
eret+2.423
hell+2.247
cano+2.234
 voic+2.130
 bras+2.116
Neg logit contributions
 Weld-2.609
ationally-2.590
ammy-2.575
ittle-2.469
netflix-2.458
TokenD
Token ID35
Feature activation-4.55e+00

Pos logit contributions
eret+7.289
hell+6.766
cano+6.747
 bras+6.463
tes+6.446
Neg logit contributions
ammy-7.246
ationally-7.242
 Weld-7.140
netflix-7.002
ittle-6.931
Token
Token ID127
Feature activation-6.17e+00

Pos logit contributions
eret+4.229
cano+3.973
hell+3.943
 voic+3.848
 bras+3.844
Neg logit contributions
 Weld-2.155
ationally-2.132
ammy-2.109
netflix-2.024
ittle-1.998
Token
Token ID228
Feature activation-7.03e+00

Pos logit contributions
eret+5.750
cano+5.471
hell+5.459
 voic+5.319
 bras+5.300
Neg logit contributions
ationally-2.771
 Weld-2.708
ammy-2.642
netflix-2.593
ittle-2.576
Token P
Token ID350
Feature activation-1.06e+01

Pos logit contributions
eret+4.369
hell+4.019
cano+4.015
 voic+3.885
 bras+3.882
Neg logit contributions
ammy-5.352
ationally-5.340
 Weld-5.272
netflix-5.133
ittle-5.094
Token ART
Token ID24278
Feature activation-1.16e+01

Pos logit contributions
eret+6.160
hell+5.766
 bras+5.573
cano+5.541
 voic+5.534
Neg logit contributions
ationally-8.058
ammy-8.045
netflix-7.923
 Weld-7.811
ittle-7.722
TokenIS
Token ID1797
Feature activation-1.52e+01

Pos logit contributions
eret+7.474
hell+6.724
cano+6.536
 bras+6.498
 voic+6.421
Neg logit contributions
ammy-8.132
ationally-8.064
 Weld-7.897
netflix-7.691
ittle-7.587
Token.
Token ID764
Feature activation-8.72e+00

Pos logit contributions
eret+8.151
hell+7.584
 bras+7.115
cano+7.080
 voic+7.054
Neg logit contributions
ammy-11.573
ationally-11.319
 Weld-11.050
netflix-10.910
ittle-10.902
Token
Token ID198
Feature activation-4.68e+00

Pos logit contributions
eret+5.601
hell+5.078
cano+5.051
 bras+4.856
 voic+4.845
Neg logit contributions
ationally-6.408
 Weld-6.373
ammy-6.332
netflix-6.198
ittle-6.063
Token
Token ID198
Feature activation-4.02e+00

Pos logit contributions
eret+3.061
hell+2.858
cano+2.800
 voic+2.673
tes+2.662
Neg logit contributions
ationally-3.497
 Weld-3.490
ammy-3.477
ittle-3.327
netflix-3.315
TokenFaith
Token ID45536
Feature activation-1.30e+00

Pos logit contributions
eret+2.486
hell+2.325
cano+2.306
 voic+2.169
 bras+2.141
Neg logit contributions
 Weld-3.194
ationally-3.144
ammy-3.106
netflix-3.001
ittle-2.992
Token.
Token ID13
Feature activation-2.80e+00

Pos logit contributions
eret+0.845
cano+0.785
hell+0.765
 voic+0.745
 bras+0.738
Neg logit contributions
 Weld-0.996
ationally-0.981
ammy-0.966
netflix-0.935
ittle-0.935
TokenF
Token ID37
Feature activation+2.16e+00

Pos logit contributions
eret+0.636
cano+0.593
hell+0.580
 voic+0.565
 bras+0.557
Neg logit contributions
 Weld-0.675
ationally-0.662
ammy-0.655
netflix-0.634
ittle-0.627
TokenLECT
Token ID16779
Feature activation-4.11e+00

Pos logit contributions
 Weld+1.682
ationally+1.661
ammy+1.623
ittle+1.607
netflix+1.570
Neg logit contributions
eret-1.365
cano-1.294
hell-1.238
 voic-1.219
 bras-1.203
Token_
Token ID62
Feature activation-4.93e+00

Pos logit contributions
eret+2.614
cano+2.424
hell+2.393
 voic+2.334
 bras+2.318
Neg logit contributions
 Weld-3.156
ammy-3.112
ationally-3.091
ittle-2.977
netflix-2.966
TokenCLASS
Token ID31631
Feature activation-7.97e+00

Pos logit contributions
eret+3.173
hell+2.970
cano+2.963
 voic+2.797
tes+2.786
Neg logit contributions
 Weld-3.758
ationally-3.656
ammy-3.608
ittle-3.504
netflix-3.449
Token_
Token ID62
Feature activation-1.21e+01

Pos logit contributions
eret+4.469
cano+4.143
hell+4.121
 voic+3.971
 bras+3.949
Neg logit contributions
 Weld-6.393
ammy-6.370
ationally-6.326
ittle-6.090
netflix-6.070
TokenST
Token ID2257
Feature activation-1.51e+01

Pos logit contributions
eret+6.810
hell+6.649
cano+6.392
tes+6.218
shut+6.065
Neg logit contributions
 Weld-9.183
ammy-9.014
ationally-8.927
ittle-8.635
gans-8.348
TokenART
Token ID7227
Feature activation-1.01e+00

Pos logit contributions
eret+9.863
hell+9.322
OFF+8.900
tes+8.656
butt+8.593
Neg logit contributions
ammy-9.562
 Weld-9.496
ationally-9.466
ittle-9.327
netflix-9.266
Token()
Token ID3419
Feature activation-1.63e+00

Pos logit contributions
eret+0.695
cano+0.649
hell+0.634
 voic+0.617
 bras+0.612
Neg logit contributions
 Weld-0.739
ationally-0.728
ammy-0.719
netflix-0.695
ittle-0.692
Token above
Token ID2029
Feature activation-3.04e+00

Pos logit contributions
eret+1.127
cano+1.051
hell+1.029
 voic+1.002
 bras+0.992
Neg logit contributions
 Weld-1.181
ationally-1.165
ammy-1.150
netflix-1.112
ittle-1.103
Token is
Token ID318
Feature activation-1.78e+00

Pos logit contributions
eret+2.087
cano+1.948
hell+1.904
 voic+1.862
 bras+1.845
Neg logit contributions
 Weld-2.202
ationally-2.179
ammy-2.160
netflix-2.096
ittle-2.062
Token the
Token ID262
Feature activation-4.90e+00

Pos logit contributions
eret+1.222
cano+1.137
hell+1.113
 voic+1.087
 bras+1.076
Neg logit contributions
 Weld-1.300
ationally-1.280
ammy-1.267
netflix-1.225
ittle-1.217
TokenTI
Token ID25621
Feature activation-4.58e+00

Pos logit contributions
eret+6.075
cano+5.445
tes+5.369
hell+5.365
 voic+5.243
Neg logit contributions
ammy-7.340
ationally-7.172
 Weld-7.067
netflix-7.016
ittle-6.750
Token
Token ID127
Feature activation-6.51e+00

Pos logit contributions
eret+2.903
cano+2.645
hell+2.639
 voic+2.544
 bras+2.527
Neg logit contributions
ationally-3.531
 Weld-3.528
ammy-3.518
netflix-3.381
ittle-3.373
Token
Token ID228
Feature activation-6.62e+00

Pos logit contributions
eret+6.024
cano+5.729
hell+5.728
 voic+5.579
 bras+5.547
Neg logit contributions
ationally-3.034
ammy-2.888
 Weld-2.879
netflix-2.803
ittle-2.793
Token P
Token ID350
Feature activation-9.69e+00

Pos logit contributions
eret+4.152
cano+3.828
hell+3.827
 voic+3.704
 bras+3.671
Neg logit contributions
ammy-5.039
ationally-5.011
 Weld-4.963
netflix-4.828
ittle-4.778
Token ART
Token ID24278
Feature activation-1.23e+01

Pos logit contributions
eret+4.680
hell+4.217
cano+4.082
 bras+4.045
 voic+4.009
Neg logit contributions
ationally-8.480
ammy-8.420
netflix-8.288
 Weld-8.282
ittle-8.149
TokenIS
Token ID1797
Feature activation-1.43e+01

Pos logit contributions
eret+7.489
hell+6.640
 bras+6.487
cano+6.481
 voic+6.361
Neg logit contributions
ammy-9.016
ationally-8.906
 Weld-8.655
netflix-8.443
ittle-8.411
Token.
Token ID764
Feature activation-8.28e+00

Pos logit contributions
eret+6.496
hell+5.790
cano+5.495
 bras+5.379
 voic+5.343
Neg logit contributions
ammy-12.224
ationally-12.027
 Weld-11.830
ittle-11.622
netflix-11.599
Token
Token ID198
Feature activation-4.28e+00

Pos logit contributions
eret+5.299
cano+4.777
hell+4.766
 bras+4.578
 voic+4.561
Neg logit contributions
ationally-6.135
 Weld-6.117
ammy-6.037
netflix-5.915
ittle-5.833
Token
Token ID198
Feature activation-4.14e+00

Pos logit contributions
eret+2.832
hell+2.636
cano+2.592
 voic+2.474
 bras+2.460
Neg logit contributions
 Weld-3.171
ationally-3.170
ammy-3.150
ittle-3.016
netflix-3.009
TokenPen
Token ID25553
Feature activation-6.19e+00

Pos logit contributions
eret+2.577
hell+2.389
cano+2.389
 voic+2.245
 bras+2.221
Neg logit contributions
 Weld-3.282
ationally-3.228
ammy-3.185
netflix-3.090
ittle-3.068
Tokenance
Token ID590
Feature activation-3.08e+00

Pos logit contributions
eret+4.706
cano+4.288
hell+4.284
 voic+4.050
 bras+4.001
Neg logit contributions
 Weld-4.050
ammy-3.948
ationally-3.905
netflix-3.759
ittle-3.726
Token large
Token ID1588
Feature activation+1.14e+00

Pos logit contributions
 Weld+0.404
ationally+0.397
ammy+0.390
ittle+0.376
netflix+0.375
Neg logit contributions
eret-0.452
cano-0.426
hell-0.415
 voic-0.404
 bras-0.401
Token reservoir
Token ID22115
Feature activation+3.24e-02

Pos logit contributions
 Weld+0.688
ationally+0.675
ammy+0.662
netflix+0.635
ittle+0.634
Neg logit contributions
eret-0.933
cano-0.881
hell-0.863
 voic-0.843
 bras-0.837
Token of
Token ID286
Feature activation-1.69e+00

Pos logit contributions
 Weld+0.025
ationally+0.024
ammy+0.024
netflix+0.023
ittle+0.023
Neg logit contributions
eret-0.021
cano-0.020
hell-0.019
 voic-0.019
 bras-0.019
Token M
Token ID337
Feature activation-5.24e-01

Pos logit contributions
eret+1.149
cano+1.068
hell+1.046
 voic+1.021
 bras+1.014
Neg logit contributions
 Weld-1.245
ationally-1.227
ammy-1.216
netflix-1.172
ittle-1.165
Token.
Token ID13
Feature activation-2.93e+00

Pos logit contributions
eret+0.376
cano+0.352
hell+0.344
 voic+0.336
 bras+0.333
Neg logit contributions
 Weld-0.368
ationally-0.362
ammy-0.356
ittle-0.343
netflix-0.343
Token le
Token ID443
Feature activation-1.42e+01

Pos logit contributions
eret+2.140
cano+2.004
hell+1.962
 bras+1.935
 voic+1.922
Neg logit contributions
 Weld-2.017
ationally-1.978
ammy-1.978
netflix-1.875
ittle-1.871
Tokenp
Token ID79
Feature activation-1.12e+01

Pos logit contributions
cano+7.309
eret+7.167
hell+6.717
zek+6.483
tes+6.307
Neg logit contributions
 Weld-11.532
ammy-10.968
ationally-10.957
netflix-10.816
^^^^-10.528
Tokenra
Token ID430
Feature activation-2.11e+00

Pos logit contributions
eret+5.820
cano+5.456
hell+5.294
 bras+4.998
tes+4.962
Neg logit contributions
 Weld-9.340
ammy-9.296
ationally-9.287
ittle-8.853
 Municip-8.776
Tokene
Token ID68
Feature activation-9.28e+00

Pos logit contributions
eret+1.505
cano+1.400
hell+1.375
 voic+1.327
 bras+1.325
Neg logit contributions
 Weld-1.493
ationally-1.468
ammy-1.454
netflix-1.397
ittle-1.393
Token and
Token ID290
Feature activation-3.15e+00

Pos logit contributions
eret+5.713
hell+5.350
cano+5.325
 bras+5.111
 voic+5.032
Neg logit contributions
ammy-7.026
 Weld-6.982
ationally-6.934
netflix-6.537
ittle-6.490
Token may
Token ID743
Feature activation-2.17e+00

Pos logit contributions
eret+2.152
cano+2.011
hell+1.970
 bras+1.924
 voic+1.917
Neg logit contributions
 Weld-2.293
ationally-2.271
ammy-2.243
netflix-2.165
ittle-2.132
Token 107
Token ID16226
Feature activation-4.18e+00

Pos logit contributions
eret+2.108
cano+1.967
hell+1.934
 voic+1.876
 bras+1.874
Neg logit contributions
ammy-2.744
ationally-2.739
 Weld-2.735
netflix-2.632
ittle-2.622
TokenP
Token ID47
Feature activation-5.24e-01

Pos logit contributions
eret+2.762
cano+2.616
hell+2.574
 voic+2.473
 bras+2.443
Neg logit contributions
 Weld-3.047
ationally-3.014
ammy-3.013
netflix-2.929
ittle-2.869
Token/
Token ID14
Feature activation-1.01e+00

Pos logit contributions
eret+0.419
cano+0.396
hell+0.389
 voic+0.379
 bras+0.376
Neg logit contributions
 Weld-0.320
ationally-0.317
ammy-0.313
netflix-0.302
ittle-0.299
TokenWilson
Token ID37349
Feature activation-6.78e+00

Pos logit contributions
eret+0.756
cano+0.711
hell+0.701
 voic+0.677
 bras+0.674
Neg logit contributions
 Weld-0.670
ationally-0.663
ammy-0.654
ittle-0.628
netflix-0.627
Token
Token ID1906
Feature activation-9.65e+00

Pos logit contributions
eret+4.450
cano+4.115
hell+4.098
 voic+3.929
 bras+3.915
Neg logit contributions
ationally-4.859
ammy-4.822
 Weld-4.754
netflix-4.722
ittle-4.604
TokenHar
Token ID13587
Feature activation-1.41e+01

Pos logit contributions
eret+5.066
hell+4.754
cano+4.574
tes+4.376
 voic+4.352
Neg logit contributions
ationally-7.900
ammy-7.791
 Weld-7.767
netflix-7.453
gans-7.452
Tokenrington
Token ID24833
Feature activation+2.41e+00

Pos logit contributions
eret+6.634
cano+6.275
hell+6.187
zek+5.750
butt+5.703
Neg logit contributions
 Weld-11.925
ammy-11.874
ationally-11.703
 Municip-11.259
netflix-10.957
Token.
Token ID13
Feature activation+5.80e-01

Pos logit contributions
 Weld+1.708
ationally+1.671
ammy+1.632
ittle+1.577
netflix+1.573
Neg logit contributions
eret-1.711
cano-1.596
hell-1.551
 voic-1.528
 bras-1.506
Token
Token ID198
Feature activation-1.82e+00

Pos logit contributions
 Weld+0.418
ationally+0.408
ammy+0.401
ittle+0.388
netflix+0.388
Neg logit contributions
eret-0.409
cano-0.382
hell-0.372
 voic-0.363
 bras-0.360
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
eret+1.301
cano+1.211
hell+1.196
 voic+1.157
 bras+1.147
Neg logit contributions
 Weld-1.278
ationally-1.263
ammy-1.249
ittle-1.200
netflix-1.198
TokenThe
Token ID464
Feature activation+7.32e-01

Pos logit contributions
eret+0.888
cano+0.827
hell+0.817
 voic+0.780
 bras+0.776
Neg logit contributions
 Weld-1.016
ationally-1.000
ammy-0.990
ittle-0.950
netflix-0.950
Token =
Token ID796
Feature activation+1.47e+00

Pos logit contributions
eret+3.441
hell+3.105
cano+3.101
 bras+2.963
 voic+2.942
Neg logit contributions
ationally-4.033
 Weld-4.024
ammy-3.991
ittle-3.772
netflix-3.748
Token c
Token ID269
Feature activation+2.80e+00

Pos logit contributions
 Weld+1.077
ationally+1.054
ammy+1.025
netflix+1.000
ittle+0.998
Neg logit contributions
eret-1.015
cano-0.945
hell-0.916
 voic-0.891
 bras-0.878
Tokenv
Token ID85
Feature activation+5.67e+00

Pos logit contributions
 Weld+2.042
ationally+2.027
ammy+1.989
netflix+1.934
ittle+1.934
Neg logit contributions
eret-1.892
cano-1.759
 bras-1.718
 voic-1.714
hell-1.674
Token2
Token ID17
Feature activation-1.11e+00

Pos logit contributions
 Weld+3.544
ationally+3.408
netflix+3.277
ammy+3.250
gans+3.250
Neg logit contributions
eret-4.347
cano-4.104
 voic-4.063
 bras-3.966
 notor-3.911
Token.
Token ID764
Feature activation-3.69e+00

Pos logit contributions
eret+0.473
cano+0.423
hell+0.405
 voic+0.388
 bras+0.381
Neg logit contributions
 Weld-1.100
ationally-1.087
ammy-1.074
netflix-1.048
ittle-1.047
Token morphology
Token ID46320
Feature activation-1.39e+01

Pos logit contributions
eret+2.115
cano+1.966
hell+1.901
 voic+1.874
 bras+1.850
Neg logit contributions
 Weld-3.080
ationally-3.032
ammy-2.989
ittle-2.944
netflix-2.940
TokenEx
Token ID3109
Feature activation-5.22e+00

Pos logit contributions
eret+3.380
hell+3.154
cano+2.645
 voic+2.552
AppData+2.383
Neg logit contributions
ammy-14.847
ationally-14.627
ittle-14.615
netflix-14.240
 Weld-14.050
Token (
Token ID357
Feature activation+2.28e+00

Pos logit contributions
eret+2.823
hell+2.589
cano+2.534
 voic+2.408
 bras+2.395
Neg logit contributions
 Weld-4.462
ationally-4.448
ammy-4.448
ittle-4.259
netflix-4.241
Token gray
Token ID12768
Feature activation+2.87e+00

Pos logit contributions
 Weld+1.086
ationally+1.053
ammy+1.010
ittle+0.982
netflix+0.969
Neg logit contributions
eret-2.152
cano-2.057
hell-1.999
 voic-1.952
 bras-1.942
Token,
Token ID837
Feature activation-2.64e+00

Pos logit contributions
 Weld+2.342
ationally+2.268
ammy+2.231
netflix+2.216
ittle+2.199
Neg logit contributions
eret-1.732
cano-1.630
hell-1.529
 voic-1.512
 bras-1.494
Token c
Token ID269
Feature activation+5.31e+00

Pos logit contributions
eret+1.624
cano+1.499
hell+1.470
 voic+1.434
 bras+1.421
Neg logit contributions
 Weld-2.104
ationally-2.082
ammy-2.076
ittle-1.993
netflix-1.991
Token
Token ID198
Feature activation-2.44e+00

Pos logit contributions
eret+1.581
cano+1.468
hell+1.459
 voic+1.402
 bras+1.392
Neg logit contributions
 Weld-1.590
ationally-1.573
ammy-1.557
ittle-1.495
netflix-1.493
TokenT
Token ID51
Feature activation+2.51e+00

Pos logit contributions
eret+1.690
hell+1.580
cano+1.576
 voic+1.496
 bras+1.485
Neg logit contributions
 Weld-1.751
ationally-1.723
ammy-1.699
ittle-1.648
netflix-1.632
TokenRE
Token ID2200
Feature activation-7.69e+00

Pos logit contributions
 Weld+1.723
ationally+1.700
ammy+1.676
ittle+1.613
netflix+1.592
Neg logit contributions
eret-1.826
cano-1.730
hell-1.676
 voic-1.646
 bras-1.628
TokenAS
Token ID1921
Feature activation-1.56e+01

Pos logit contributions
eret+4.160
cano+3.699
hell+3.674
 voic+3.518
 bras+3.500
Neg logit contributions
ammy-6.492
 Weld-6.366
ationally-6.303
netflix-6.289
ittle-6.254
TokenURE
Token ID11335
Feature activation-7.51e+00

Pos logit contributions
eret+8.960
hell+8.725
cano+7.797
zek+7.559
 voic+7.444
Neg logit contributions
ammy-10.755
 Weld-10.666
netflix-10.543
ationally-10.370
gans-10.328
Token HUN
Token ID41041
Feature activation-1.37e+01

Pos logit contributions
eret+3.834
hell+3.700
cano+3.541
 voic+3.417
 bras+3.363
Neg logit contributions
ationally-6.362
ammy-6.328
 Weld-6.213
ittle-6.191
netflix-6.175
TokenTER
Token ID5781
Feature activation-5.99e+00

Pos logit contributions
eret+5.903
hell+5.575
tes+5.407
cano+5.140
butt+5.012
Neg logit contributions
ammy-12.268
ationally-11.900
ittle-11.501
netflix-11.480
 Weld-11.243
Token
Token ID198
Feature activation-3.57e+00

Pos logit contributions
eret+3.879
hell+3.653
cano+3.595
 voic+3.503
 bras+3.492
Neg logit contributions
ationally-4.372
 Weld-4.370
ammy-4.340
ittle-4.202
netflix-4.138
Token
Token ID198
Feature activation-4.80e+00

Pos logit contributions
eret+2.423
hell+2.247
cano+2.234
 voic+2.130
 bras+2.116
Neg logit contributions
 Weld-2.609
ationally-2.590
ammy-2.575
ittle-2.469
netflix-2.458
Token2007
Token ID12726
Feature activation-6.32e-01

Pos logit contributions
eret+2.979
hell+2.768
cano+2.752
 bras+2.570
 voic+2.569
Neg logit contributions
 Weld-3.754
ationally-3.685
ammy-3.640
ittle-3.547
netflix-3.512
Token
Token ID198
Feature activation-1.75e+00

Pos logit contributions
eret+0.452
cano+0.421
hell+0.413
 voic+0.402
 bras+0.398
Neg logit contributions
 Weld-0.445
ationally-0.438
ammy-0.432
ittle-0.417
netflix-0.416
TokenE
Token ID36
Feature activation-6.87e+00

Pos logit contributions
eret+2.325
cano+2.183
hell+2.144
 voic+2.057
 bras+2.033
Neg logit contributions
 Weld-2.500
ationally-2.423
ammy-2.375
netflix-2.337
ittle-2.312
Tokenmpire
Token ID35386
Feature activation+7.78e-01

Pos logit contributions
eret+4.680
cano+4.379
tes+4.265
hell+4.234
 voic+4.067
Neg logit contributions
 Weld-4.951
ationally-4.794
ammy-4.765
netflix-4.672
ittle-4.532
Token.
Token ID13
Feature activation-3.15e+00

Pos logit contributions
 Weld+0.559
ationally+0.550
ammy+0.542
netflix+0.522
ittle+0.521
Neg logit contributions
eret-0.545
cano-0.508
hell-0.496
 voic-0.483
 bras-0.477
TokenFIN
Token ID20032
Feature activation-5.57e+00

Pos logit contributions
eret+2.233
cano+2.073
hell+2.037
 voic+1.996
 bras+1.980
Neg logit contributions
 Weld-2.219
ationally-2.212
ammy-2.193
netflix-2.106
ittle-2.096
Token DE
Token ID5550
Feature activation-5.45e+00

Pos logit contributions
eret+3.523
cano+3.224
hell+3.183
 voic+3.107
 bras+3.078
Neg logit contributions
 Weld-4.221
ammy-4.170
ationally-4.131
netflix-4.041
ittle-3.991
Token TRAN
Token ID48213
Feature activation-1.37e+01

Pos logit contributions
eret+3.653
cano+3.362
hell+3.315
 voic+3.262
 bras+3.250
Neg logit contributions
ationally-3.977
 Weld-3.965
ammy-3.947
netflix-3.802
ittle-3.798
TokenSM
Token ID12310
Feature activation+2.52e+00

Pos logit contributions
eret+6.280
cano+5.478
 voic+5.432
hell+5.375
 bras+5.367
Neg logit contributions
 Weld-11.565
ammy-11.508
ationally-11.418
ittle-11.142
netflix-10.870
TokenISSION
Token ID40373
Feature activation-1.68e+00

Pos logit contributions
 Weld+1.485
ationally+1.451
ammy+1.402
ittle+1.363
netflix+1.352
Neg logit contributions
eret-2.079
cano-1.974
hell-1.918
 voic-1.887
 bras-1.882
Token ///
Token ID34013
Feature activation+8.74e-01

Pos logit contributions
eret+1.370
cano+1.284
hell+1.263
 voic+1.239
 bras+1.231
Neg logit contributions
 Weld-1.017
ationally-1.002
ammy-0.989
netflix-0.945
ittle-0.942
Token<|endoftext|>
Token ID50256
Feature activation+3.84e+00

Pos logit contributions
 Weld+0.503
ationally+0.495
ammy+0.484
netflix+0.463
ittle+0.462
Neg logit contributions
eret-0.736
cano-0.696
hell-0.682
 voic-0.669
 bras-0.663
TokenOur
Token ID5122
Feature activation+1.49e+00

Pos logit contributions
 Weld+2.744
ationally+2.728
ammy+2.672
netflix+2.641
ittle+2.585
Neg logit contributions
eret-2.639
cano-2.469
 voic-2.364
 bras-2.345
hell-2.339
TokenS
Token ID50
Feature activation-6.66e+00

Pos logit contributions
eret+1.510
cano+1.400
hell+1.381
 voic+1.328
 bras+1.312
Neg logit contributions
 Weld-1.681
ationally-1.656
ammy-1.638
netflix-1.584
ittle-1.574
Token U
Token ID471
Feature activation-5.84e+00

Pos logit contributions
eret+4.267
cano+3.892
hell+3.886
 voic+3.724
 bras+3.680
Neg logit contributions
 Weld-5.021
ationally-4.989
ammy-4.981
netflix-4.867
ittle-4.752
TokenPP
Token ID10246
Feature activation-4.56e+00

Pos logit contributions
eret+4.237
cano+3.911
hell+3.894
tes+3.739
 bras+3.731
Neg logit contributions
ammy-3.890
ationally-3.888
 Weld-3.873
netflix-3.749
ittle-3.706
TokenLE
Token ID2538
Feature activation-5.98e+00

Pos logit contributions
eret+2.984
hell+2.707
cano+2.704
 voic+2.595
 bras+2.577
Neg logit contributions
ationally-3.449
ammy-3.425
 Weld-3.419
netflix-3.312
ittle-3.272
TokenMENT
Token ID10979
Feature activation-4.81e+00

Pos logit contributions
eret+3.956
cano+3.640
hell+3.633
 bras+3.495
 voic+3.494
Neg logit contributions
ationally-4.380
ammy-4.360
 Weld-4.357
netflix-4.243
ittle-4.152
TokenUM
Token ID5883
Feature activation-1.35e+01

Pos logit contributions
eret+3.087
cano+2.807
hell+2.803
 voic+2.714
 bras+2.687
Neg logit contributions
 Weld-3.658
ammy-3.617
ationally-3.612
netflix-3.503
ittle-3.477
Token T
Token ID309
Feature activation-5.35e+00

Pos logit contributions
eret+7.606
hell+7.073
 bras+6.835
 voic+6.813
cano+6.750
Neg logit contributions
ammy-10.151
ationally-10.001
netflix-9.919
 Weld-9.669
ittle-9.561
Token ER
Token ID13793
Feature activation-9.81e+00

Pos logit contributions
eret+3.401
cano+3.061
hell+3.055
 voic+2.955
 bras+2.937
Neg logit contributions
ationally-4.102
 Weld-4.087
ammy-4.082
netflix-3.990
ittle-3.888
TokenTI
Token ID25621
Feature activation-4.58e+00

Pos logit contributions
eret+6.075
cano+5.445
tes+5.369
hell+5.365
 voic+5.243
Neg logit contributions
ammy-7.340
ationally-7.172
 Weld-7.067
netflix-7.016
ittle-6.750
Token
Token ID127
Feature activation-6.51e+00

Pos logit contributions
eret+2.903
cano+2.645
hell+2.639
 voic+2.544
 bras+2.527
Neg logit contributions
ationally-3.531
 Weld-3.528
ammy-3.518
netflix-3.381
ittle-3.373
Token
Token ID228
Feature activation-6.62e+00

Pos logit contributions
eret+6.024
cano+5.729
hell+5.728
 voic+5.579
 bras+5.547
Neg logit contributions
ationally-3.034
ammy-2.888
 Weld-2.879
netflix-2.803
ittle-2.793
Token21
Token ID2481
Feature activation-2.86e+00

Pos logit contributions
 Weld+2.591
ationally+2.548
ammy+2.488
netflix+2.422
ittle+2.408
Neg logit contributions
eret-2.347
cano-2.181
 voic-2.103
hell-2.099
 bras-2.033
Token O
Token ID440
Feature activation+1.46e+00

Pos logit contributions
eret+1.972
cano+1.828
hell+1.814
 voic+1.765
 bras+1.743
Neg logit contributions
ationally-2.048
 Weld-2.041
ammy-2.018
ittle-1.950
netflix-1.937
Token&
Token ID5
Feature activation-1.92e+00

Pos logit contributions
 Weld+0.776
ationally+0.763
ammy+0.743
netflix+0.708
ittle+0.707
Neg logit contributions
eret-1.287
cano-1.225
hell-1.186
 voic-1.176
 bras-1.170
TokenA
Token ID32
Feature activation-3.64e+00

Pos logit contributions
eret+1.124
cano+1.037
hell+1.019
 voic+0.975
 bras+0.964
Neg logit contributions
 Weld-1.591
ationally-1.569
ammy-1.555
netflix-1.510
ittle-1.509
Token-
Token ID12
Feature activation-6.46e+00

Pos logit contributions
eret+2.342
hell+2.166
cano+2.154
 voic+2.057
 bras+2.036
Neg logit contributions
ationally-2.768
 Weld-2.768
ammy-2.750
ittle-2.659
netflix-2.634
TokenWOR
Token ID45359
Feature activation-1.32e+01

Pos logit contributions
eret+4.279
hell+4.160
cano+4.012
 voic+3.901
 bras+3.829
Neg logit contributions
 Weld-4.562
ationally-4.536
ammy-4.418
ittle-4.297
netflix-4.224
TokenST
Token ID2257
Feature activation-8.42e+00

Pos logit contributions
eret+5.388
hell+5.079
cano+4.856
tes+4.788
 voic+4.510
Neg logit contributions
ammy-12.054
netflix-11.699
ationally-11.664
 Weld-11.543
enhagen-11.302
Token OF
Token ID3963
Feature activation-8.14e+00

Pos logit contributions
eret+4.312
 voic+3.956
hell+3.935
cano+3.923
 bras+3.770
Neg logit contributions
ationally-7.048
 Weld-6.947
ammy-6.936
ittle-6.835
netflix-6.791
Token-
Token ID12
Feature activation-5.13e+00

Pos logit contributions
eret+4.821
hell+4.462
 voic+4.416
cano+4.410
 bras+4.298
Neg logit contributions
ationally-6.190
 Weld-6.080
ittle-6.072
ammy-6.049
netflix-5.942
TokenPenn
Token ID39899
Feature activation-1.96e+00

Pos logit contributions
eret+3.677
hell+3.532
cano+3.444
 voic+3.340
 bras+3.277
Neg logit contributions
 Weld-3.434
ationally-3.403
ammy-3.309
ittle-3.221
netflix-3.150
Token J
Token ID449
Feature activation-3.90e+00

Pos logit contributions
eret+1.407
cano+1.309
hell+1.291
 voic+1.256
 bras+1.238
Neg logit contributions
 Weld-1.371
ationally-1.357
ammy-1.328
netflix-1.297
ittle-1.286
Token.
Token ID13
Feature activation-2.64e+00

Pos logit contributions
 Weld+1.762
ationally+1.712
ammy+1.671
netflix+1.621
ittle+1.607
Neg logit contributions
eret-1.868
cano-1.752
hell-1.690
 voic-1.679
 bras-1.665
Token Old
Token ID5706
Feature activation+4.69e+00

Pos logit contributions
eret+1.982
cano+1.864
hell+1.822
 voic+1.771
 bras+1.755
Neg logit contributions
ationally-1.736
 Weld-1.714
ammy-1.699
netflix-1.651
ittle-1.642
Token gift
Token ID6979
Feature activation-3.22e+00

Pos logit contributions
 Weld+3.089
ationally+3.019
ammy+2.973
ittle+2.877
netflix+2.834
Neg logit contributions
eret-3.473
cano-3.303
hell-3.227
 voic-3.118
 bras-3.107
Token
Token ID1906
Feature activation-6.23e+00

Pos logit contributions
eret+2.307
cano+2.162
hell+2.098
 voic+2.043
 bras+2.032
Neg logit contributions
 Weld-2.243
ationally-2.217
ammy-2.164
netflix-2.123
ittle-2.101
Tokenbe
Token ID1350
Feature activation+1.18e-01

Pos logit contributions
eret+3.547
cano+3.246
hell+3.215
tes+2.981
 voic+2.938
Neg logit contributions
 Weld-5.330
ationally-5.183
ammy-5.056
netflix-4.924
ittle-4.919
Tokenarer
Token ID11258
Feature activation-1.31e+01

Pos logit contributions
 Weld+0.099
ationally+0.098
ammy+0.097
ittle+0.094
netflix+0.094
Neg logit contributions
eret-0.068
cano-0.063
hell-0.061
 voic-0.060
 bras-0.059
Token setting
Token ID4634
Feature activation-1.66e+00

Pos logit contributions
eret+4.629
 voic+3.641
cano+3.325
hell+3.310
tes+3.171
Neg logit contributions
ammy-13.003
ationally-12.857
 Weld-12.772
ittle-12.724
netflix-12.678
Token box
Token ID3091
Feature activation-7.90e+00

Pos logit contributions
eret+1.305
cano+1.223
hell+1.204
 voic+1.176
 bras+1.167
Neg logit contributions
 Weld-1.052
ationally-1.039
ammy-1.022
netflix-0.977
ittle-0.974
Token underneath
Token ID14638
Feature activation+1.37e+00

Pos logit contributions
eret+4.545
cano+4.235
hell+4.098
 bras+3.916
 voic+3.895
Neg logit contributions
 Weld-6.348
ationally-6.273
ammy-6.199
gans-5.993
netflix-5.983
Token roughly
Token ID7323
Feature activation-5.11e+00

Pos logit contributions
ationally+1.066
 Weld+1.060
ammy+1.020
ittle+1.003
netflix+0.986
Neg logit contributions
eret-0.871
cano-0.809
hell-0.801
 voic-0.777
 bras-0.760
Token (
Token ID357
Feature activation-9.89e-01

Pos logit contributions
eret+2.867
cano+2.658
hell+2.578
 voic+2.500
 bras+2.470
Neg logit contributions
 Weld-4.244
ammy-4.220
ationally-4.218
ittle-4.030
netflix-4.030
TokenAC
Token ID2246
Feature activation-1.56e+00

Pos logit contributions
 Weld+3.651
ationally+3.617
ammy+3.475
netflix+3.388
ittle+3.357
Neg logit contributions
eret-4.082
cano-3.864
hell-3.685
 bras-3.625
 voic-3.608
Token
Token ID198
Feature activation+9.71e-01

Pos logit contributions
eret+1.098
cano+1.025
hell+1.011
 voic+0.983
 bras+0.972
Neg logit contributions
 Weld-1.112
ationally-1.097
ammy-1.086
ittle-1.045
netflix-1.043
Token
Token ID198
Feature activation+4.34e+00

Pos logit contributions
 Weld+0.626
ationally+0.612
ammy+0.596
netflix+0.580
ittle+0.575
Neg logit contributions
eret-0.752
cano-0.711
hell-0.685
 voic-0.679
 bras-0.672
TokenT
Token ID51
Feature activation+2.16e+00

Pos logit contributions
 Weld+3.089
ationally+3.069
ammy+3.015
netflix+2.955
ittle+2.905
Neg logit contributions
eret-2.991
cano-2.774
 voic-2.671
 bras-2.639
hell-2.638
TokenRE
Token ID2200
Feature activation-5.85e+00

Pos logit contributions
 Weld+1.511
ationally+1.496
ammy+1.473
ittle+1.420
netflix+1.403
Neg logit contributions
eret-1.543
cano-1.458
hell-1.417
 voic-1.388
 bras-1.374
TokenAS
Token ID1921
Feature activation-1.30e+01

Pos logit contributions
eret+3.780
cano+3.468
hell+3.439
 voic+3.340
 bras+3.322
Neg logit contributions
 Weld-4.350
ammy-4.339
ationally-4.249
netflix-4.205
ittle-4.180
TokenURE
Token ID11335
Feature activation-1.45e+00

Pos logit contributions
eret+7.621
hell+7.611
cano+7.107
 voic+6.844
zek+6.814
Neg logit contributions
ammy-9.372
netflix-9.048
 Weld-8.816
ittle-8.793
ationally-8.653
Token HUN
Token ID41041
Feature activation-8.81e+00

Pos logit contributions
eret+0.973
cano+0.909
hell+0.891
 voic+0.868
 bras+0.861
Neg logit contributions
 Weld-1.073
ationally-1.059
ammy-1.051
ittle-1.013
netflix-1.013
TokenTER
Token ID5781
Feature activation-2.03e+00

Pos logit contributions
eret+5.079
cano+4.674
hell+4.658
tes+4.564
 voic+4.526
Neg logit contributions
ationally-6.897
ammy-6.844
 Weld-6.723
netflix-6.552
ittle-6.535
Token
Token ID198
Feature activation+2.00e+00

Pos logit contributions
eret+1.417
cano+1.324
hell+1.304
 voic+1.271
 bras+1.260
Neg logit contributions
 Weld-1.454
ationally-1.440
ammy-1.422
ittle-1.370
netflix-1.367
Token
Token ID198
Feature activation+2.66e+00

Pos logit contributions
 Weld+1.245
ationally+1.209
ammy+1.174
netflix+1.144
ittle+1.133
Neg logit contributions
eret-1.586
cano-1.508
 voic-1.440
hell-1.439
 bras-1.426
Token Railroad
Token ID36289
Feature activation-2.78e+00

Pos logit contributions
eret+3.306
hell+3.106
cano+3.092
 voic+3.009
 bras+2.981
Neg logit contributions
ammy-2.460
 Weld-2.436
ationally-2.436
ittle-2.361
netflix-2.329
Token Company
Token ID5834
Feature activation-4.16e+00

Pos logit contributions
eret+1.899
cano+1.769
hell+1.751
 voic+1.689
 bras+1.686
Neg logit contributions
 Weld-2.001
ationally-1.996
ammy-1.970
ittle-1.902
netflix-1.902
Token,
Token ID11
Feature activation-2.29e+00

Pos logit contributions
eret+2.788
cano+2.584
hell+2.539
 voic+2.465
 bras+2.452
Neg logit contributions
 Weld-3.031
ammy-3.019
ationally-3.015
ittle-2.900
netflix-2.887
Token 118
Token ID19035
Feature activation+1.77e+00

Pos logit contributions
eret+1.515
cano+1.396
hell+1.378
 voic+1.349
 bras+1.331
Neg logit contributions
 Weld-1.713
ationally-1.697
ammy-1.696
ittle-1.621
netflix-1.614
Token U
Token ID471
Feature activation-8.18e+00

Pos logit contributions
 Weld+1.246
ationally+1.223
ammy+1.197
netflix+1.150
ittle+1.147
Neg logit contributions
eret-1.274
cano-1.199
hell-1.167
 voic-1.141
 bras-1.128
Token.
Token ID13
Feature activation-1.30e+01

Pos logit contributions
eret+4.466
hell+4.104
cano+3.979
tes+3.911
 bras+3.680
Neg logit contributions
ammy-6.818
ationally-6.742
 Weld-6.695
ittle-6.615
netflix-6.474
TokenS
Token ID50
Feature activation-7.86e+00

Pos logit contributions
eret+3.991
hell+3.392
tes+3.347
cano+3.266
 bras+3.114
Neg logit contributions
ammy-13.034
ittle-12.755
netflix-12.715
ationally-12.685
gans-12.574
Token.
Token ID13
Feature activation-4.69e+00

Pos logit contributions
eret+4.395
hell+4.043
cano+3.948
tes+3.733
 bras+3.682
Neg logit contributions
ammy-6.436
ationally-6.391
 Weld-6.328
ittle-6.209
netflix-6.170
Token 39
Token ID5014
Feature activation-5.21e+00

Pos logit contributions
eret+2.791
cano+2.586
hell+2.556
 bras+2.444
 voic+2.437
Neg logit contributions
ammy-3.745
 Weld-3.733
ationally-3.729
ittle-3.585
netflix-3.566
Token4
Token ID19
Feature activation-5.81e+00

Pos logit contributions
eret+3.187
hell+2.912
cano+2.910
 voic+2.789
 bras+2.769
Neg logit contributions
ammy-4.069
ationally-4.067
 Weld-4.049
ittle-3.918
netflix-3.917
Token (
Token ID357
Feature activation-5.23e+00

Pos logit contributions
eret+3.537
hell+3.175
cano+3.106
 voic+3.028
 bras+3.013
Neg logit contributions
ammy-4.613
ationally-4.539
 Weld-4.525
ittle-4.442
netflix-4.358
Token lesbian
Token ID17834
Feature activation-1.92e+00

Pos logit contributions
 Weld+2.110
ationally+2.084
ammy+2.028
ittle+1.955
gans+1.927
Neg logit contributions
eret-2.394
cano-2.315
hell-2.199
 voic-2.144
 bras-2.129
Token spouses
Token ID30250
Feature activation+3.71e-01

Pos logit contributions
eret+1.269
cano+1.175
hell+1.149
 voic+1.122
 bras+1.111
Neg logit contributions
 Weld-1.461
ationally-1.441
ammy-1.426
netflix-1.378
ittle-1.373
Token.
Token ID13
Feature activation-5.29e-01

Pos logit contributions
 Weld+0.278
ationally+0.274
ammy+0.270
netflix+0.261
ittle+0.261
Neg logit contributions
eret-0.248
cano-0.231
hell-0.225
 voic-0.219
 bras-0.217
Token
Token ID198
Feature activation+5.43e-01

Pos logit contributions
eret+0.386
cano+0.361
hell+0.353
 voic+0.345
 bras+0.342
Neg logit contributions
 Weld-0.366
ationally-0.360
ammy-0.354
netflix-0.341
ittle-0.341
Token
Token ID198
Feature activation-3.52e-01

Pos logit contributions
 Weld+0.355
ationally+0.348
ammy+0.340
netflix+0.329
ittle+0.328
Neg logit contributions
eret-0.416
cano-0.393
hell-0.380
 voic-0.375
 bras-0.372
TokenCre
Token ID12443
Feature activation-1.28e+01

Pos logit contributions
eret+0.234
cano+0.217
hell+0.213
 voic+0.206
 bras+0.204
Neg logit contributions
 Weld-0.266
ationally-0.262
ammy-0.258
netflix-0.249
ittle-0.249
Tokenighton
Token ID42993
Feature activation+1.18e+00

Pos logit contributions
eret+9.066
cano+8.194
hell+8.173
tes+7.981
zek+7.664
Neg logit contributions
 Weld-8.622
ammy-8.035
netflix-7.745
ittle-7.563
 Municip-7.553
Token University
Token ID2059
Feature activation-1.63e+00

Pos logit contributions
 Weld+0.885
ationally+0.867
ammy+0.846
ittle+0.820
netflix+0.815
Neg logit contributions
eret-0.791
cano-0.738
hell-0.715
 voic-0.701
 bras-0.693
Token in
Token ID287
Feature activation-1.48e+00

Pos logit contributions
eret+1.140
cano+1.064
hell+1.044
 voic+1.013
 bras+1.005
Neg logit contributions
 Weld-1.167
ationally-1.150
ammy-1.142
netflix-1.108
ittle-1.099
Token Omaha
Token ID37053
Feature activation-1.27e-01

Pos logit contributions
eret+1.089
cano+1.020
hell+0.998
 voic+0.974
 bras+0.966
Neg logit contributions
 Weld-1.007
ationally-0.991
ammy-0.975
netflix-0.940
ittle-0.938
Token,
Token ID11
Feature activation+2.77e+00

Pos logit contributions
eret+0.092
cano+0.086
hell+0.084
 voic+0.082
 bras+0.081
Neg logit contributions
 Weld-0.089
ationally-0.088
ammy-0.086
netflix-0.083
ittle-0.083
Token My
Token ID2011
Feature activation+1.83e+00

Pos logit contributions
 Weld+0.480
ationally+0.471
ammy+0.460
ittle+0.449
netflix+0.447
Neg logit contributions
eret-0.481
cano-0.453
hell-0.441
 voic-0.427
 bras-0.422
Tokenc
Token ID66
Feature activation-2.33e+00

Pos logit contributions
 Weld+1.424
ationally+1.403
ammy+1.383
netflix+1.339
ittle+1.338
Neg logit contributions
eret-1.169
cano-1.086
hell-1.055
 voic-1.033
 bras-1.017
Tokenob
Token ID672
Feature activation-1.74e+00

Pos logit contributions
eret+1.343
cano+1.227
hell+1.206
 voic+1.165
 bras+1.159
Neg logit contributions
 Weld-1.962
ationally-1.930
ammy-1.922
netflix-1.856
ittle-1.854
Tokenacter
Token ID7321
Feature activation-7.45e+00

Pos logit contributions
eret+0.887
cano+0.799
hell+0.781
 voic+0.733
 bras+0.724
Neg logit contributions
 Weld-1.601
ationally-1.564
ammy-1.553
netflix-1.508
ittle-1.499
Tokenium
Token ID1505
Feature activation-5.48e+00

Pos logit contributions
eret+2.101
hell+1.776
 bras+1.757
 voic+1.667
cano+1.620
Neg logit contributions
ammy-8.214
ationally-8.111
 Weld-8.096
netflix-7.934
ittle-7.821
Token le
Token ID443
Feature activation-1.28e+01

Pos logit contributions
eret+3.488
 bras+3.273
cano+3.232
hell+3.223
 voic+3.175
Neg logit contributions
ammy-4.166
 Weld-4.110
ationally-4.072
netflix-3.940
ittle-3.919
Tokenp
Token ID79
Feature activation-8.13e+00

Pos logit contributions
eret+7.104
cano+6.972
hell+6.600
zek+6.250
 voic+6.202
Neg logit contributions
 Weld-9.829
ationally-9.603
netflix-9.485
ammy-9.452
^^^^-9.038
Tokenra
Token ID430
Feature activation-3.15e+00

Pos logit contributions
eret+4.916
hell+4.647
cano+4.570
tes+4.290
sett+4.270
Neg logit contributions
 Weld-6.267
ationally-6.233
ammy-6.115
netflix-5.993
^^^^-5.910
Tokene
Token ID68
Feature activation-8.55e+00

Pos logit contributions
eret+2.279
cano+2.126
hell+2.090
 voic+2.020
 bras+2.011
Neg logit contributions
 Weld-2.200
ationally-2.157
ammy-2.126
netflix-2.053
ittle-2.049
Token.[
Token ID3693
Feature activation+2.04e+00

Pos logit contributions
eret+5.634
cano+5.225
hell+5.211
 bras+5.004
 voic+4.963
Neg logit contributions
 Weld-6.271
ationally-6.164
ammy-6.159
netflix-5.839
ittle-5.817
Token116
Token ID18298
Feature activation-1.57e+00

Pos logit contributions
 Weld+1.269
ationally+1.250
ammy+1.227
netflix+1.178
ittle+1.177
Neg logit contributions
eret-1.622
cano-1.525
hell-1.484
 voic-1.465
 bras-1.456
Token of
Token ID286
Feature activation+1.17e-01

Pos logit contributions
 Weld+0.855
ationally+0.842
ammy+0.824
ittle+0.802
netflix+0.798
Neg logit contributions
eret-0.779
cano-0.723
hell-0.706
 voic-0.689
 bras-0.682
Token the
Token ID262
Feature activation-1.10e+00

Pos logit contributions
 Weld+0.086
ationally+0.085
ammy+0.083
ittle+0.081
netflix+0.081
Neg logit contributions
eret-0.080
cano-0.075
hell-0.072
 voic-0.070
 bras-0.069
Token vagina
Token ID26150
Feature activation-1.11e+00

Pos logit contributions
eret+0.655
cano+0.604
hell+0.588
 voic+0.570
 bras+0.565
Neg logit contributions
 Weld-0.906
ationally-0.894
ammy-0.882
netflix-0.856
ittle-0.854
Token and
Token ID290
Feature activation-3.09e+00

Pos logit contributions
eret+0.770
cano+0.718
hell+0.703
 voic+0.684
 bras+0.679
Neg logit contributions
 Weld-0.810
ationally-0.798
ammy-0.788
netflix-0.761
ittle-0.758
Token restricts
Token ID47075
Feature activation-2.80e+00

Pos logit contributions
eret+2.003
cano+1.856
hell+1.812
 voic+1.772
 bras+1.771
Neg logit contributions
 Weld-2.371
ationally-2.353
ammy-2.325
netflix-2.254
ittle-2.228
Token path
Token ID3108
Feature activation-1.26e+01

Pos logit contributions
eret+1.839
cano+1.697
hell+1.662
 voic+1.624
 bras+1.614
Neg logit contributions
 Weld-2.125
ationally-2.105
ammy-2.082
netflix-2.009
ittle-1.995
Tokenogen
Token ID6644
Feature activation-3.44e+00

Pos logit contributions
eret+7.239
hell+6.813
cano+6.627
 voic+6.374
tes+6.336
Neg logit contributions
ammy-9.709
 Weld-9.529
ationally-9.345
netflix-9.307
gerald-8.972
Token growth
Token ID3349
Feature activation-6.16e+00

Pos logit contributions
eret+2.348
cano+2.180
hell+2.164
 voic+2.102
 bras+2.073
Neg logit contributions
 Weld-2.504
ationally-2.469
ammy-2.467
netflix-2.371
ittle-2.345
Token.
Token ID13
Feature activation-3.13e+00

Pos logit contributions
eret+3.823
hell+3.552
cano+3.552
 bras+3.398
 voic+3.352
Neg logit contributions
 Weld-4.761
ammy-4.757
ationally-4.669
netflix-4.595
ittle-4.470
Token A
Token ID317
Feature activation-2.51e+00

Pos logit contributions
eret+2.220
cano+2.060
hell+2.037
 bras+1.973
 voic+1.972
Neg logit contributions
ationally-2.190
 Weld-2.181
ammy-2.167
netflix-2.087
ittle-2.074
Token
Token ID564
Feature activation-2.10e+00

Pos logit contributions
eret+1.775
cano+1.648
hell+1.622
 voic+1.584
 bras+1.574
Neg logit contributions
 Weld-1.786
ationally-1.756
ammy-1.735
netflix-1.672
ittle-1.666
Token
Token ID18074
Feature activation-2.77e+00

Pos logit contributions
eret+1.823
cano+1.684
hell+1.650
 voic+1.612
 bras+1.588
Neg logit contributions
 Weld-2.177
ationally-2.158
ammy-2.135
netflix-2.071
ittle-2.055
Token
Token ID228
Feature activation-9.06e-01

Pos logit contributions
eret+2.042
cano+1.894
hell+1.877
 voic+1.829
 bras+1.803
Neg logit contributions
 Weld-1.881
ationally-1.855
ammy-1.834
netflix-1.776
ittle-1.759
Token
Token ID138
Feature activation-1.52e+00

Pos logit contributions
eret+0.520
cano+0.479
hell+0.465
 voic+0.450
 bras+0.445
Neg logit contributions
 Weld-0.766
ationally-0.756
ammy-0.746
netflix-0.724
ittle-0.724
Token
Token ID116
Feature activation-2.99e+00

Pos logit contributions
eret+1.066
cano+0.996
hell+0.975
 voic+0.950
 bras+0.943
Neg logit contributions
 Weld-1.085
ationally-1.069
ammy-1.058
netflix-1.024
ittle-1.019
Tokenε
Token ID30950
Feature activation-5.10e+00

Pos logit contributions
eret+1.631
cano+1.478
hell+1.455
 voic+1.400
 bras+1.377
Neg logit contributions
 Weld-2.610
ationally-2.574
ammy-2.553
netflix-2.489
ittle-2.472
Token
Token ID45495
Feature activation-1.26e+01

Pos logit contributions
eret+2.756
cano+2.487
hell+2.464
 voic+2.356
 bras+2.320
Neg logit contributions
 Weld-4.412
ationally-4.364
ammy-4.343
netflix-4.254
ittle-4.192
Token
Token ID115
Feature activation-5.99e+00

Pos logit contributions
eret+8.523
hell+7.912
cano+7.873
 bras+7.872
tes+7.870
Neg logit contributions
ammy-8.253
ationally-8.118
netflix-8.080
 Weld-7.987
ittle-7.404
Tokenρ
Token ID33643
Feature activation-6.58e+00

Pos logit contributions
eret+3.370
hell+3.038
cano+3.020
 voic+2.951
 bras+2.917
Neg logit contributions
 Weld-4.992
ammy-4.945
ationally-4.940
netflix-4.824
ittle-4.742
Tokenε
Token ID30950
Feature activation-4.98e+00

Pos logit contributions
eret+3.925
cano+3.562
hell+3.559
 voic+3.504
 bras+3.446
Neg logit contributions
 Weld-5.233
ammy-5.208
ationally-5.193
netflix-5.050
ittle-4.959
Tokenι
Token ID29945
Feature activation-6.75e+00

Pos logit contributions
eret+2.764
cano+2.504
hell+2.477
 voic+2.387
 bras+2.350
Neg logit contributions
 Weld-4.226
ammy-4.191
ationally-4.189
netflix-4.081
ittle-4.024
Token
Token ID7377
Feature activation-1.33e+00

Pos logit contributions
eret+3.603
cano+3.266
hell+3.256
 voic+3.172
 bras+3.108
Neg logit contributions
 Weld-5.775
ammy-5.755
ationally-5.740
netflix-5.581
ittle-5.466
Token about
Token ID546
Feature activation-2.96e+00

Pos logit contributions
eret+3.096
cano+2.872
hell+2.863
 voic+2.814
 bras+2.791
Neg logit contributions
 Weld-3.180
ationally-3.175
ammy-3.149
netflix-3.011
ittle-2.991
Token as
Token ID355
Feature activation-3.82e+00

Pos logit contributions
eret+1.980
cano+1.837
hell+1.826
 voic+1.779
 bras+1.767
Neg logit contributions
 Weld-2.187
ationally-2.164
ammy-2.146
netflix-2.075
ittle-2.045
Token dangerous
Token ID4923
Feature activation+1.89e+00

Pos logit contributions
eret+2.695
cano+2.524
hell+2.467
 voic+2.439
 bras+2.424
Neg logit contributions
 Weld-2.658
ationally-2.649
ammy-2.593
ittle-2.510
netflix-2.509
Token as
Token ID355
Feature activation-4.83e+00

Pos logit contributions
 Weld+1.138
ationally+1.106
ammy+1.084
netflix+1.041
ittle+1.040
Neg logit contributions
eret-1.554
cano-1.463
hell-1.428
 voic-1.401
 bras-1.386
Token could
Token ID714
Feature activation-8.55e+00

Pos logit contributions
eret+3.291
cano+3.086
hell+3.032
 voic+2.996
 bras+2.974
Neg logit contributions
ationally-3.430
ammy-3.388
 Weld-3.382
ittle-3.263
netflix-3.231
Token be
Token ID307
Feature activation-1.25e+01

Pos logit contributions
eret+4.858
hell+4.432
cano+4.389
 bras+4.265
 voic+4.203
Neg logit contributions
 Weld-6.861
ammy-6.851
ationally-6.556
ittle-6.473
netflix-6.382
Token,
Token ID11
Feature activation-2.00e+00

Pos logit contributions
eret+6.821
hell+6.413
 bras+6.379
 voic+6.319
cano+6.274
Neg logit contributions
ammy-9.564
ationally-9.451
netflix-9.068
 Weld-9.065
ittle-8.994
Token and
Token ID290
Feature activation-3.37e+00

Pos logit contributions
eret+1.402
cano+1.315
hell+1.288
 voic+1.260
 bras+1.252
Neg logit contributions
 Weld-1.414
ationally-1.408
ammy-1.393
ittle-1.336
netflix-1.336
Token certainly
Token ID3729
Feature activation-2.39e+00

Pos logit contributions
eret+2.289
cano+2.136
hell+2.100
 voic+2.069
 bras+2.047
Neg logit contributions
ationally-2.429
ammy-2.406
 Weld-2.404
netflix-2.308
ittle-2.302
Token will
Token ID481
Feature activation-1.38e+00

Pos logit contributions
eret+1.618
cano+1.511
hell+1.481
 voic+1.461
 bras+1.453
Neg logit contributions
ationally-1.744
 Weld-1.734
ammy-1.707
ittle-1.646
netflix-1.645
Token look
Token ID804
Feature activation-5.49e+00

Pos logit contributions
eret+0.925
cano+0.858
hell+0.839
 voic+0.822
 bras+0.813
Neg logit contributions
 Weld-1.036
ationally-1.021
ammy-1.005
netflix-0.971
ittle-0.967
Token the
Token ID262
Feature activation+1.15e+00

Pos logit contributions
eret+0.962
cano+0.900
hell+0.881
 voic+0.861
 bras+0.854
Neg logit contributions
 Weld-0.876
ationally-0.860
ammy-0.848
netflix-0.817
ittle-0.813
Token body
Token ID1767
Feature activation-3.60e+00

Pos logit contributions
 Weld+0.804
ationally+0.792
ammy+0.781
ittle+0.752
netflix+0.748
Neg logit contributions
eret-0.823
cano-0.771
hell-0.753
 voic-0.731
 bras-0.725
Token
Token ID447
Feature activation-7.48e-01

Pos logit contributions
eret+2.601
cano+2.436
hell+2.383
 voic+2.322
 bras+2.308
Neg logit contributions
 Weld-2.496
ationally-2.423
ammy-2.403
netflix-2.321
ittle-2.292
Token
Token ID247
Feature activation+3.09e-01

Pos logit contributions
eret+0.517
cano+0.482
hell+0.471
 voic+0.459
 bras+0.454
Neg logit contributions
 Weld-0.544
ationally-0.536
ammy-0.529
netflix-0.511
ittle-0.509
Tokens
Token ID82
Feature activation-1.69e+00

Pos logit contributions
 Weld+0.285
ationally+0.282
ammy+0.278
ittle+0.271
netflix+0.271
Neg logit contributions
eret-0.154
cano-0.139
hell-0.135
 voic-0.130
 bras-0.129
Token natural
Token ID3288
Feature activation-1.24e+01

Pos logit contributions
eret+1.265
cano+1.187
hell+1.162
 voic+1.136
 bras+1.129
Neg logit contributions
 Weld-1.129
ationally-1.106
ammy-1.091
netflix-1.053
ittle-1.048
Token shifts
Token ID15381
Feature activation-4.72e-01

Pos logit contributions
eret+7.819
 voic+7.163
cano+7.148
 bras+7.067
hell+6.996
Neg logit contributions
 Weld-8.661
ammy-8.567
ationally-8.388
netflix-8.199
ittle-7.978
Token between
Token ID1022
Feature activation-1.92e+00

Pos logit contributions
eret+0.326
cano+0.303
hell+0.297
 voic+0.288
 bras+0.286
Neg logit contributions
 Weld-0.345
ationally-0.339
ammy-0.335
netflix-0.323
ittle-0.322
Token sympathetic
Token ID22335
Feature activation-1.39e-01

Pos logit contributions
eret+1.352
cano+1.260
hell+1.233
 voic+1.204
 bras+1.195
Neg logit contributions
 Weld-1.370
ationally-1.348
ammy-1.330
netflix-1.285
ittle-1.280
Token (
Token ID357
Feature activation+2.30e+00

Pos logit contributions
eret+0.098
cano+0.091
hell+0.089
 voic+0.087
 bras+0.086
Neg logit contributions
 Weld-0.099
ationally-0.097
ammy-0.096
netflix-0.093
ittle-0.092
Token
Token ID447
Feature activation+9.83e-01

Pos logit contributions
 Weld+1.741
ationally+1.738
ammy+1.716
ittle+1.667
netflix+1.666
Neg logit contributions
eret-1.476
cano-1.382
hell-1.323
 voic-1.319
 bras-1.313
Token golden
Token ID10861
Feature activation+7.62e+00

Pos logit contributions
 Weld+4.346
ationally+4.251
ittle+4.085
ammy+3.990
netflix+3.893
Neg logit contributions
eret-5.364
cano-4.951
hell-4.807
 voic-4.662
zek-4.612
Token brown
Token ID7586
Feature activation+4.95e+00

Pos logit contributions
 Weld+4.353
ationally+4.154
ittle+4.063
ammy+4.025
netflix+3.850
Neg logit contributions
eret-6.327
cano-5.976
hell-5.751
 bras-5.660
 voic-5.609
Token.
Token ID13
Feature activation+5.24e+00

Pos logit contributions
 Weld+3.411
ationally+3.330
ammy+3.228
ittle+3.200
netflix+3.144
Neg logit contributions
eret-3.569
cano-3.343
hell-3.252
 voic-3.155
 bras-3.123
Token These
Token ID2312
Feature activation-8.50e-01

Pos logit contributions
 Weld+3.543
ationally+3.295
ammy+3.242
ittle+3.180
netflix+3.130
Neg logit contributions
eret-3.977
cano-3.694
hell-3.609
 voic-3.560
 bras-3.467
Token are
Token ID389
Feature activation+2.95e+00

Pos logit contributions
eret+0.614
cano+0.576
hell+0.564
 voic+0.552
 bras+0.547
Neg logit contributions
 Weld-0.591
ationally-0.584
ammy-0.575
netflix-0.554
ittle-0.550
Token lightly
Token ID15376
Feature activation+9.85e+00

Pos logit contributions
 Weld+2.054
ationally+2.009
ammy+1.978
ittle+1.916
netflix+1.891
Neg logit contributions
eret-2.145
cano-1.983
hell-1.944
 voic-1.875
 bras-1.862
Token fried
Token ID23018
Feature activation+5.45e+00

Pos logit contributions
 Weld+5.868
ittle+5.620
ationally+5.595
ammy+5.513
netflix+5.305
Neg logit contributions
eret-7.797
cano-7.318
hell-6.966
zek-6.624
 voic-6.621
Token and
Token ID290
Feature activation+6.86e+00

Pos logit contributions
 Weld+3.704
ationally+3.577
ammy+3.492
ittle+3.422
netflix+3.377
Neg logit contributions
eret-3.992
cano-3.728
hell-3.587
 voic-3.497
tes-3.436
Token not
Token ID407
Feature activation+7.14e+00

Pos logit contributions
 Weld+4.492
ationally+4.317
ammy+4.278
ittle+4.226
netflix+4.101
Neg logit contributions
eret-5.150
cano-4.763
hell-4.655
 bras-4.444
 voic-4.435
Token deep
Token ID2769
Feature activation+9.71e+00

Pos logit contributions
ationally+4.426
 Weld+4.426
ammy+4.248
ittle+4.224
netflix+4.062
Neg logit contributions
eret-5.588
cano-5.240
hell-5.035
 bras-4.879
 voic-4.864
Token fried
Token ID23018
Feature activation+5.05e+00

Pos logit contributions
 Weld+4.631
ationally+4.549
ammy+4.380
ittle+4.139
netflix+4.103
Neg logit contributions
eret-8.644
cano-8.146
hell-7.977
tes-7.845
 voic-7.771
Token170
Token ID17279
Feature activation-3.11e-01

Pos logit contributions
eret+2.592
cano+2.409
hell+2.375
 voic+2.302
 bras+2.298
Neg logit contributions
 Weld-2.522
ationally-2.505
ammy-2.496
ittle-2.365
netflix-2.364
Token x
Token ID2124
Feature activation-1.34e+00

Pos logit contributions
eret+0.215
cano+0.200
hell+0.195
 voic+0.190
 bras+0.189
Neg logit contributions
 Weld-0.227
ationally-0.223
ammy-0.220
netflix-0.212
ittle-0.212
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
eret+0.904
cano+0.840
hell+0.823
 voic+0.798
 bras+0.791
Neg logit contributions
 Weld-0.997
ationally-0.983
ammy-0.970
netflix-0.936
ittle-0.936
Tokenx
Token ID87
Feature activation+3.43e+00

Pos logit contributions
 Weld+0.584
ationally+0.580
ammy+0.564
netflix+0.542
ittle+0.538
Neg logit contributions
eret-0.943
cano-0.898
 voic-0.873
hell-0.871
 bras-0.867
Token.
Token ID13
Feature activation+7.97e+00

Pos logit contributions
 Weld+2.265
ationally+2.210
ammy+2.136
netflix+2.086
ittle+2.071
Neg logit contributions
eret-2.564
cano-2.441
 voic-2.349
 bras-2.324
hell-2.312
Tokenx
Token ID87
Feature activation+9.77e+00

Pos logit contributions
ationally+3.317
 Weld+3.209
ammy+3.179
gans+3.038
netflix+3.028
Neg logit contributions
eret-7.376
 voic-7.267
 bras-7.259
cano-7.198
 notor-7.048
Token.
Token ID13
Feature activation+1.44e+01

Pos logit contributions
 Weld+5.309
ationally+4.967
ammy+4.824
^^^^+4.780
ittle+4.761
Neg logit contributions
eret-7.827
 notor-7.579
cano-7.575
 voic-7.484
 bras-7.403
Token149
Token ID19442
Feature activation-2.31e+00

Pos logit contributions
 Weld+4.422
ittle+4.373
ammy+4.003
^^^^+3.980
ationally+3.933
Neg logit contributions
eret-14.082
cano-13.656
 voic-13.214
 bras-13.173
hell-13.150
Token 110
Token ID9796
Feature activation+3.59e+00

Pos logit contributions
eret+1.616
cano+1.512
hell+1.489
 voic+1.449
 bras+1.428
Neg logit contributions
 Weld-1.637
ationally-1.633
ammy-1.610
ittle-1.554
netflix-1.545
Token22
Token ID1828
Feature activation+3.08e+00

Pos logit contributions
 Weld+2.450
ationally+2.378
ammy+2.316
netflix+2.264
gans+2.248
Neg logit contributions
eret-2.611
cano-2.455
 voic-2.358
hell-2.350
 bras-2.319
Token26
Token ID2075
Feature activation+1.52e+00

Pos logit contributions
 Weld+2.171
ationally+2.097
ammy+2.043
netflix+1.987
ittle+1.982
Neg logit contributions
eret-2.225
cano-2.093
 voic-1.987
hell-1.985
 bras-1.960
Token
Token ID198
Feature activation-9.47e-01

Pos logit contributions
eret+0.276
cano+0.259
hell+0.252
 voic+0.247
 bras+0.245
Neg logit contributions
 Weld-0.248
ationally-0.243
ammy-0.239
netflix-0.230
ittle-0.230
TokenRead
Token ID5569
Feature activation-1.96e+00

Pos logit contributions
eret+0.574
cano+0.530
hell+0.518
 voic+0.500
 bras+0.495
Neg logit contributions
 Weld-0.770
ationally-0.760
ammy-0.751
ittle-0.726
netflix-0.726
Token More
Token ID3125
Feature activation+5.18e+00

Pos logit contributions
eret+1.304
cano+1.208
hell+1.191
 voic+1.150
 bras+1.141
Neg logit contributions
 Weld-1.455
ationally-1.450
ammy-1.438
netflix-1.383
ittle-1.381
Token About
Token ID7994
Feature activation+8.20e+00

Pos logit contributions
 Weld+3.596
ationally+3.400
ammy+3.317
gans+3.188
ittle+3.160
Neg logit contributions
eret-3.826
cano-3.518
hell-3.443
 voic-3.408
 bras-3.361
Token Dw
Token ID19113
Feature activation+6.59e+00

Pos logit contributions
 Weld+5.057
ationally+4.565
ammy+4.362
 Municip+4.280
gans+4.270
Neg logit contributions
eret-6.595
cano-6.104
 voic-6.075
hell-6.028
 bras-5.879
Tokenark
Token ID668
Feature activation+9.93e+00

Pos logit contributions
ationally+3.199
ammy+3.122
 Weld+3.122
netflix+2.970
ittle+2.929
Neg logit contributions
eret-5.795
 voic-5.612
cano-5.558
hell-5.453
 bras-5.433
Tokenadh
Token ID24411
Feature activation-4.70e-01

Pos logit contributions
ammy+5.589
ationally+5.431
ittle+5.131
 Weld+5.093
arta+4.866
Neg logit contributions
eret-7.847
 bras-7.547
 voic-7.520
cano-7.513
hell-7.226
Tokenish
Token ID680
Feature activation-3.81e+00

Pos logit contributions
eret+0.320
cano+0.298
hell+0.291
 voic+0.283
 bras+0.281
Neg logit contributions
 Weld-0.347
ationally-0.342
ammy-0.337
ittle-0.325
netflix-0.325
Token Temple
Token ID10857
Feature activation-6.32e+00

Pos logit contributions
eret+1.663
cano+1.469
hell+1.432
 voic+1.330
 bras+1.315
Neg logit contributions
ationally-3.722
 Weld-3.710
ammy-3.666
netflix-3.607
ittle-3.586
Token Here
Token ID3423
Feature activation+6.62e-01

Pos logit contributions
eret+3.142
hell+2.856
cano+2.782
 bras+2.550
tes+2.530
Neg logit contributions
ationally-5.631
ammy-5.609
 Weld-5.528
netflix-5.458
ittle-5.413
Token
Token ID198
Feature activation+7.19e-01

Pos logit contributions
 Weld+0.451
ationally+0.443
ammy+0.436
netflix+0.420
ittle+0.420
Neg logit contributions
eret-0.490
cano-0.459
hell-0.448
 voic-0.438
 bras-0.435
Tokenproven
Token ID42874
Feature activation-1.46e+00

Pos logit contributions
eret+3.350
hell+3.156
cano+3.134
tes+2.934
 voic+2.931
Neg logit contributions
 Weld-4.040
ationally-3.901
ammy-3.832
ittle-3.773
netflix-3.694
Token oil
Token ID3056
Feature activation-6.76e+00

Pos logit contributions
eret+1.170
cano+1.101
hell+1.082
 voic+1.063
 bras+1.053
Neg logit contributions
 Weld-0.898
ationally-0.885
ammy-0.874
netflix-0.839
ittle-0.837
Token reserves
Token ID14072
Feature activation-5.35e+00

Pos logit contributions
eret+3.114
cano+2.860
hell+2.705
 voic+2.662
 bras+2.647
Neg logit contributions
 Weld-6.238
ationally-6.180
ammy-6.159
netflix-6.023
ittle-5.997
Token:
Token ID25
Feature activation-3.65e+00

Pos logit contributions
eret+3.436
cano+3.262
hell+3.204
 voic+3.071
 bras+3.050
Neg logit contributions
 Weld-4.004
ationally-3.934
ammy-3.875
ittle-3.773
netflix-3.757
Token 140
Token ID12713
Feature activation-2.28e+00

Pos logit contributions
eret+2.074
cano+1.934
hell+1.888
 voic+1.837
 bras+1.804
Neg logit contributions
 Weld-3.027
ationally-3.008
ammy-2.985
netflix-2.888
ittle-2.886
Token billion
Token ID2997
Feature activation+9.77e+00

Pos logit contributions
eret+1.593
cano+1.490
hell+1.461
 voic+1.426
 bras+1.419
Neg logit contributions
 Weld-1.635
ationally-1.614
ammy-1.586
netflix-1.554
ittle-1.533
Token barrels
Token ID17907
Feature activation-6.09e+00

Pos logit contributions
 Weld+4.124
ationally+3.825
ammy+3.539
ittle+3.401
netflix+3.378
Neg logit contributions
eret-9.225
cano-8.899
hell-8.611
zek-8.439
 voic-8.419
Token),
Token ID828
Feature activation-7.90e+00

Pos logit contributions
eret+3.702
cano+3.515
hell+3.436
 bras+3.328
 voic+3.327
Neg logit contributions
 Weld-4.666
ationally-4.662
ammy-4.616
netflix-4.490
ittle-4.433
Token Obama
Token ID2486
Feature activation+1.28e+00

Pos logit contributions
eret+4.577
hell+4.158
cano+4.060
 voic+4.046
 bras+3.915
Neg logit contributions
ammy-6.191
ationally-6.129
 Weld-6.097
netflix-5.983
ittle-5.952
Token pedd
Token ID36145
Feature activation-4.13e+00

Pos logit contributions
 Weld+0.848
ationally+0.833
ammy+0.813
netflix+0.785
ittle+0.784
Neg logit contributions
eret-0.977
cano-0.916
hell-0.894
 voic-0.872
 bras-0.866
Tokenled
Token ID992
Feature activation+7.99e-01

Pos logit contributions
eret+2.749
cano+2.534
hell+2.505
 bras+2.385
 voic+2.382
Neg logit contributions
 Weld-3.085
ationally-3.025
ammy-3.006
netflix-2.923
ittle-2.868
Token x
Token ID2124
Feature activation-2.26e+00

Pos logit contributions
eret+0.060
cano+0.056
hell+0.054
 voic+0.053
 bras+0.052
Neg logit contributions
 Weld-0.062
ationally-0.061
ammy-0.060
netflix-0.058
ittle-0.058
Token.
Token ID13
Feature activation+3.35e-01

Pos logit contributions
eret+1.487
cano+1.374
hell+1.357
 voic+1.302
 bras+1.292
Neg logit contributions
 Weld-1.722
ationally-1.703
ammy-1.687
ittle-1.624
netflix-1.622
Tokenx
Token ID87
Feature activation+2.30e+00

Pos logit contributions
 Weld+0.186
ationally+0.183
ammy+0.179
netflix+0.172
ittle+0.171
Neg logit contributions
eret-0.288
cano-0.273
hell-0.266
 voic-0.264
 bras-0.262
Token.
Token ID13
Feature activation+4.97e+00

Pos logit contributions
 Weld+1.565
ationally+1.530
ammy+1.489
netflix+1.451
ittle+1.441
Neg logit contributions
eret-1.681
cano-1.590
 voic-1.525
hell-1.516
 bras-1.508
Tokenx
Token ID87
Feature activation+7.50e+00

Pos logit contributions
ationally+2.320
 Weld+2.284
ammy+2.233
netflix+2.157
ittle+2.115
Neg logit contributions
eret-4.519
cano-4.356
 voic-4.335
 bras-4.318
hell-4.139
Token.
Token ID13
Feature activation+1.43e+01

Pos logit contributions
 Weld+4.332
ationally+4.099
ammy+3.992
ittle+3.866
gans+3.859
Neg logit contributions
eret-5.918
cano-5.741
 notor-5.654
 voic-5.603
 bras-5.597
Token154
Token ID21526
Feature activation-3.09e+00

Pos logit contributions
 Weld+5.632
ammy+5.334
ationally+5.310
ittle+5.277
uld+4.845
Neg logit contributions
 bras-12.148
eret-11.905
cano-11.881
 notor-11.752
 contrace-11.738
Token 109
Token ID16003
Feature activation-1.46e+00

Pos logit contributions
eret+2.099
cano+1.971
hell+1.947
 voic+1.896
 bras+1.866
Neg logit contributions
 Weld-2.217
ationally-2.215
ammy-2.191
ittle-2.114
netflix-2.097
Token77
Token ID3324
Feature activation-8.76e-01

Pos logit contributions
eret+0.984
cano+0.915
hell+0.899
 voic+0.868
 bras+0.861
Neg logit contributions
 Weld-1.091
ationally-1.079
ammy-1.064
ittle-1.026
netflix-1.025
Token39
Token ID2670
Feature activation-4.38e-01

Pos logit contributions
eret+0.587
cano+0.546
hell+0.536
 voic+0.519
 bras+0.514
Neg logit contributions
 Weld-0.654
ationally-0.646
ammy-0.638
netflix-0.615
ittle-0.615
Token x
Token ID2124
Feature activation-2.66e+00

Pos logit contributions
eret+0.301
cano+0.281
hell+0.274
 voic+0.267
 bras+0.265
Neg logit contributions
 Weld-0.321
ationally-0.316
ammy-0.311
netflix-0.300
ittle-0.300
Tokenials
Token ID8231
Feature activation+3.59e+00

Pos logit contributions
eret+0.617
cano+0.554
hell+0.537
 voic+0.518
 bras+0.506
Neg logit contributions
 Weld-1.232
ationally-1.218
ammy-1.207
netflix-1.175
ittle-1.174
Token/
Token ID14
Feature activation+5.49e-01

Pos logit contributions
 Weld+2.519
ationally+2.468
ammy+2.427
ittle+2.341
netflix+2.336
Neg logit contributions
eret-2.564
cano-2.414
hell-2.323
 bras-2.263
 voic-2.247
TokenDeb
Token ID16587
Feature activation+1.45e-01

Pos logit contributions
 Weld+0.404
ationally+0.398
ammy+0.391
netflix+0.377
ittle+0.377
Neg logit contributions
eret-0.376
cano-0.351
hell-0.341
 bras-0.332
 voic-0.331
Tokenate
Token ID378
Feature activation+3.00e+00

Pos logit contributions
 Weld+0.103
ationally+0.101
ammy+0.099
netflix+0.096
ittle+0.095
Neg logit contributions
eret-0.103
cano-0.096
hell-0.094
 voic-0.091
 bras-0.091
Token Op
Token ID8670
Feature activation+1.93e+00

Pos logit contributions
 Weld+2.158
ationally+2.108
ammy+2.055
ittle+1.986
netflix+1.969
Neg logit contributions
eret-2.117
cano-1.983
hell-1.925
 bras-1.854
 voic-1.847
Tokenin
Token ID259
Feature activation+5.12e+00

Pos logit contributions
 Weld+1.229
ationally+1.208
ammy+1.181
ittle+1.134
netflix+1.123
Neg logit contributions
eret-1.517
cano-1.437
hell-1.394
 voic-1.356
 bras-1.352
Tokenions
Token ID507
Feature activation+2.22e+00

Pos logit contributions
 Weld+2.246
ationally+2.188
ammy+2.059
ittle+2.033
netflix+1.931
Neg logit contributions
eret-4.948
cano-4.740
 bras-4.561
hell-4.555
 voic-4.506
Token expressed
Token ID6241
Feature activation-6.86e-01

Pos logit contributions
 Weld+1.591
ationally+1.561
ammy+1.522
ittle+1.472
netflix+1.463
Neg logit contributions
eret-1.581
cano-1.477
hell-1.431
 bras-1.384
 voic-1.384
Token in
Token ID287
Feature activation-2.54e+00

Pos logit contributions
eret+0.440
cano+0.408
hell+0.399
 voic+0.388
 bras+0.382
Neg logit contributions
 Weld-0.534
ationally-0.525
ammy-0.519
netflix-0.503
ittle-0.501
Token USA
Token ID4916
Feature activation+1.51e+00

Pos logit contributions
eret+1.750
cano+1.615
hell+1.584
 voic+1.562
 bras+1.535
Neg logit contributions
 Weld-1.847
ationally-1.827
ammy-1.807
netflix-1.757
ittle-1.736
Token TODAY
Token ID20092
Feature activation-3.33e+00

Pos logit contributions
 Weld+1.164
ationally+1.148
ammy+1.125
ittle+1.095
netflix+1.085
Neg logit contributions
eret-0.978
cano-0.908
hell-0.886
 voic-0.857
 bras-0.853
Token makes
Token ID1838
Feature activation-3.96e-01

Pos logit contributions
eret+2.498
cano+2.342
hell+2.303
 voic+2.243
 bras+2.230
Neg logit contributions
 Weld-2.673
ationally-2.640
ammy-2.606
netflix-2.535
ittle-2.496
Token a
Token ID257
Feature activation+6.43e-01

Pos logit contributions
eret+0.268
cano+0.250
hell+0.244
 voic+0.237
 bras+0.235
Neg logit contributions
 Weld-0.294
ationally-0.290
ammy-0.285
netflix-0.276
ittle-0.275
Token great
Token ID1049
Feature activation-3.47e+00

Pos logit contributions
 Weld+0.442
ationally+0.433
ammy+0.426
netflix+0.411
ittle+0.409
Neg logit contributions
eret-0.472
cano-0.446
hell-0.432
 voic-0.420
 bras-0.418
Token case
Token ID1339
Feature activation-2.36e+00

Pos logit contributions
eret+2.496
cano+2.325
hell+2.282
 voic+2.275
 bras+2.207
Neg logit contributions
ationally-2.365
 Weld-2.362
ammy-2.324
netflix-2.256
ittle-2.248
Token for
Token ID329
Feature activation+1.93e-01

Pos logit contributions
eret+1.443
cano+1.331
hell+1.294
 voic+1.266
 bras+1.238
Neg logit contributions
 Weld-1.899
ationally-1.871
ammy-1.851
netflix-1.796
ittle-1.785
Token the
Token ID262
Feature activation+2.13e+00

Pos logit contributions
 Weld+0.139
ationally+0.136
ammy+0.134
netflix+0.130
ittle+0.130
Neg logit contributions
eret-0.135
cano-0.126
hell-0.123
 voic-0.120
 bras-0.119
Token N
Token ID399
Feature activation+3.60e-01

Pos logit contributions
 Weld+1.490
ationally+1.454
ammy+1.445
ittle+1.378
netflix+1.376
Neg logit contributions
eret-1.538
cano-1.430
hell-1.403
 voic-1.349
 bras-1.346
Token64
Token ID2414
Feature activation-1.56e+00

Pos logit contributions
 Weld+0.302
ationally+0.298
ammy+0.294
netflix+0.285
ittle+0.285
Neg logit contributions
eret-0.210
cano-0.193
hell-0.188
 voic-0.182
 bras-0.180
Token as
Token ID355
Feature activation+3.87e+00

Pos logit contributions
eret+1.119
cano+1.052
hell+1.028
 voic+1.005
 bras+0.992
Neg logit contributions
 Weld-1.090
ationally-1.078
ammy-1.057
netflix-1.029
ittle-1.021
Token the
Token ID262
Feature activation+4.37e-01

Pos logit contributions
 Weld+2.672
ationally+2.603
ammy+2.567
netflix+2.459
ittle+2.453
Neg logit contributions
eret-2.815
cano-2.650
hell-2.584
 voic-2.492
 bras-2.489
Token New
Token ID968
Feature activation+1.65e+00

Pos logit contributions
 Weld+0.299
ationally+0.294
ammy+0.289
netflix+0.278
ittle+0.277
Neg logit contributions
eret-0.323
cano-0.302
hell-0.296
 voic-0.287
 bras-0.285
Token the
Token ID262
Feature activation-3.24e+00

Pos logit contributions
eret+2.322
cano+2.162
hell+2.118
 voic+2.045
 bras+2.036
Neg logit contributions
 Weld-2.720
ationally-2.688
ammy-2.676
netflix-2.581
ittle-2.579
Token life
Token ID1204
Feature activation-5.80e+00

Pos logit contributions
eret+1.813
hell+1.644
cano+1.643
 voic+1.595
 bras+1.580
Neg logit contributions
 Weld-2.754
ationally-2.726
ammy-2.712
ittle-2.629
netflix-2.610
Token of
Token ID286
Feature activation-1.30e+00

Pos logit contributions
eret+3.312
cano+3.100
hell+3.029
 bras+2.930
 voic+2.879
Neg logit contributions
 Weld-4.773
ammy-4.681
ationally-4.675
ittle-4.506
netflix-4.501
Token me
Token ID502
Feature activation-1.69e+00

Pos logit contributions
eret+0.804
cano+0.743
hell+0.726
 voic+0.707
 bras+0.701
Neg logit contributions
 Weld-1.036
ationally-1.022
ammy-1.014
netflix-0.980
ittle-0.978
Token remember
Token ID3505
Feature activation+3.09e+00

Pos logit contributions
eret+1.061
cano+0.985
hell+0.963
 voic+0.938
 bras+0.929
Neg logit contributions
 Weld-1.328
ationally-1.302
ammy-1.296
netflix-1.257
ittle-1.244
Token anything
Token ID1997
Feature activation+4.36e+00

Pos logit contributions
 Weld+2.262
ationally+2.203
ammy+2.157
ittle+2.077
netflix+2.076
Neg logit contributions
eret-2.148
cano-2.028
hell-1.946
 voic-1.884
 bras-1.853
Token that
Token ID326
Feature activation+4.23e+00

Pos logit contributions
 Weld+3.054
ationally+2.980
ammy+2.910
ittle+2.842
netflix+2.799
Neg logit contributions
eret-3.156
cano-2.938
hell-2.814
 voic-2.719
 bras-2.710
Token preceded
Token ID27165
Feature activation+2.81e+00

Pos logit contributions
 Weld+2.830
ationally+2.725
ammy+2.678
ittle+2.597
netflix+2.563
Neg logit contributions
eret-3.197
cano-2.991
hell-2.910
 voic-2.805
 bras-2.781
Token Alfred
Token ID22044
Feature activation-2.46e+00

Pos logit contributions
 Weld+1.953
ationally+1.907
ammy+1.875
ittle+1.811
netflix+1.807
Neg logit contributions
eret-2.043
cano-1.908
hell-1.864
 voic-1.813
 bras-1.790
Tokeno
Token ID78
Feature activation+1.40e+00

Pos logit contributions
eret+1.161
cano+1.043
hell+1.010
 voic+0.957
 bras+0.943
Neg logit contributions
 Weld-2.332
ationally-2.307
ammy-2.280
netflix-2.226
ittle-2.217
Token's
Token ID338
Feature activation+5.35e+00

Pos logit contributions
 Weld+0.892
ationally+0.874
ammy+0.858
netflix+0.824
ittle+0.823
Neg logit contributions
eret-1.094
cano-1.029
hell-1.009
 voic-0.985
 bras-0.976
Tokenoral
Token ID6864
Feature activation-1.43e-01

Pos logit contributions
eret+0.958
cano+0.894
hell+0.875
 voic+0.851
 bras+0.840
Neg logit contributions
 Weld-0.935
ationally-0.919
ammy-0.905
netflix-0.878
ittle-0.866
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
eret+0.096
cano+0.089
hell+0.087
 voic+0.085
 bras+0.084
Neg logit contributions
 Weld-0.108
ationally-0.106
ammy-0.104
netflix-0.101
ittle-0.101
Token anthrop
Token ID17911
Feature activation-4.41e+00

Pos logit contributions
 Weld+0.933
ationally+0.920
ammy+0.902
ittle+0.872
netflix+0.869
Neg logit contributions
eret-0.962
cano-0.899
hell-0.875
 voic-0.848
 bras-0.845
Tokenomorphic
Token ID46374
Feature activation-1.31e+00

Pos logit contributions
eret+2.333
cano+2.133
hell+2.121
 voic+1.983
zek+1.914
Neg logit contributions
 Weld-3.874
ammy-3.741
ationally-3.735
netflix-3.639
ittle-3.618
Token div
Token ID2659
Feature activation+3.79e+00

Pos logit contributions
eret+0.881
cano+0.822
hell+0.804
 voic+0.785
 bras+0.777
Neg logit contributions
 Weld-0.979
ationally-0.966
ammy-0.952
netflix-0.923
ittle-0.918
Tokenin
Token ID259
Feature activation+3.90e+00

Pos logit contributions
 Weld+2.606
ationally+2.574
ammy+2.532
ittle+2.450
netflix+2.395
Neg logit contributions
eret-2.757
cano-2.577
hell-2.497
 voic-2.469
 bras-2.450
Tokenities
Token ID871
Feature activation+1.43e+00

Pos logit contributions
ationally+0.812
 Weld+0.791
ammy+0.731
ittle+0.642
netflix+0.586
Neg logit contributions
eret-4.665
cano-4.521
hell-4.418
 bras-4.411
 voic-4.394
Token became
Token ID2627
Feature activation-1.36e+00

Pos logit contributions
 Weld+0.951
ationally+0.933
ammy+0.914
ittle+0.880
netflix+0.880
Neg logit contributions
eret-1.078
cano-1.008
hell-0.982
 voic-0.960
 bras-0.952
Token unacceptable
Token ID18010
Feature activation-1.55e+00

Pos logit contributions
eret+0.969
cano+0.908
hell+0.887
 voic+0.870
 bras+0.860
Neg logit contributions
 Weld-0.957
ationally-0.942
ammy-0.932
netflix-0.899
ittle-0.896
Token to
Token ID284
Feature activation+2.05e+00

Pos logit contributions
eret+1.069
cano+0.998
hell+0.977
 voic+0.953
 bras+0.945
Neg logit contributions
 Weld-1.131
ationally-1.112
ammy-1.103
netflix-1.062
ittle-1.059
Token the
Token ID262
Feature activation+8.46e-01

Pos logit contributions
 Weld+1.434
ationally+1.411
ammy+1.373
ittle+1.333
netflix+1.312
Neg logit contributions
eret-1.480
cano-1.387
hell-1.348
 voic-1.302
 bras-1.287
Token one
Token ID530
Feature activation+4.60e+00

Pos logit contributions
 Weld+2.610
ationally+2.538
ammy+2.433
ittle+2.392
netflix+2.352
Neg logit contributions
eret-2.906
cano-2.739
hell-2.647
 voic-2.525
tes-2.505
Token caveat
Token ID36531
Feature activation+4.15e+00

Pos logit contributions
 Weld+3.251
ationally+3.218
ammy+3.083
ittle+3.030
netflix+2.986
Neg logit contributions
eret-3.285
cano-3.052
hell-2.946
 bras-2.801
zek-2.765
Token.
Token ID13
Feature activation+2.38e+00

Pos logit contributions
 Weld+2.804
ationally+2.750
ammy+2.678
ittle+2.590
netflix+2.581
Neg logit contributions
eret-3.083
cano-2.893
hell-2.801
 voic-2.713
 bras-2.704
Token Yes
Token ID3363
Feature activation+3.70e-02

Pos logit contributions
 Weld+1.625
ationally+1.556
ammy+1.524
netflix+1.477
ittle+1.471
Neg logit contributions
eret-1.776
cano-1.679
hell-1.615
 voic-1.579
 bras-1.562
Token,
Token ID11
Feature activation+2.43e+00

Pos logit contributions
 Weld+0.027
ationally+0.026
ammy+0.026
netflix+0.025
ittle+0.025
Neg logit contributions
eret-0.026
cano-0.024
hell-0.024
 voic-0.023
 bras-0.023
Token his
Token ID465
Feature activation+2.01e+00

Pos logit contributions
 Weld+1.693
ationally+1.660
ammy+1.612
ittle+1.565
netflix+1.552
Neg logit contributions
eret-1.770
cano-1.673
hell-1.614
 voic-1.553
 bras-1.536
Token cabinet
Token ID13447
Feature activation-6.35e-01

Pos logit contributions
 Weld+1.370
ationally+1.345
ammy+1.324
ittle+1.268
netflix+1.261
Neg logit contributions
eret-1.483
cano-1.393
hell-1.355
 voic-1.311
 bras-1.298
Token represents
Token ID6870
Feature activation-6.64e-01

Pos logit contributions
eret+0.435
cano+0.406
hell+0.396
 voic+0.386
 bras+0.382
Neg logit contributions
 Weld-0.466
ationally-0.459
ammy-0.452
netflix-0.437
ittle-0.436
Token several
Token ID1811
Feature activation-2.81e+00

Pos logit contributions
eret+0.458
cano+0.427
hell+0.418
 voic+0.408
 bras+0.404
Neg logit contributions
 Weld-0.484
ationally-0.477
ammy-0.470
netflix-0.454
ittle-0.454
Token core
Token ID4755
Feature activation+3.51e-01

Pos logit contributions
eret+1.904
cano+1.762
hell+1.731
 voic+1.724
 bras+1.701
Neg logit contributions
 Weld-2.048
ammy-2.010
ationally-2.005
netflix-1.954
ittle-1.937
Token Canadian
Token ID5398
Feature activation-2.74e+00

Pos logit contributions
 Weld+0.241
ationally+0.237
ammy+0.233
netflix+0.225
ittle+0.224
Neg logit contributions
eret-0.258
cano-0.242
hell-0.237
 voic-0.231
 bras-0.229
Token set
Token ID900
Feature activation-1.84e+00

Pos logit contributions
eret+2.665
cano+2.451
hell+2.427
 voic+2.424
 bras+2.369
Neg logit contributions
 Weld-2.600
ationally-2.591
ammy-2.572
netflix-2.468
ittle-2.446
Token of
Token ID286
Feature activation-5.00e+00

Pos logit contributions
eret+1.192
cano+1.104
hell+1.078
 voic+1.050
 bras+1.035
Neg logit contributions
 Weld-1.421
ationally-1.400
ammy-1.383
netflix-1.335
ittle-1.334
Token two
Token ID734
Feature activation-6.70e+00

Pos logit contributions
eret+3.439
cano+3.158
 voic+3.142
hell+3.105
 bras+3.092
Neg logit contributions
ationally-3.527
ammy-3.524
 Weld-3.520
netflix-3.394
ittle-3.358
Token 7
Token ID767
Feature activation+1.82e-01

Pos logit contributions
eret+4.634
 voic+4.285
cano+4.230
 bras+4.222
hell+4.215
Neg logit contributions
ationally-4.623
ammy-4.618
 Weld-4.578
netflix-4.427
ittle-4.378
Token-
Token ID12
Feature activation-1.58e+00

Pos logit contributions
 Weld+0.131
ationally+0.129
ammy+0.127
netflix+0.122
ittle+0.122
Neg logit contributions
eret-0.128
cano-0.120
hell-0.117
 voic-0.114
 bras-0.113
Tokenbar
Token ID5657
Feature activation-3.70e+00

Pos logit contributions
eret+1.081
cano+1.005
hell+0.989
 voic+0.955
 bras+0.946
Neg logit contributions
 Weld-1.168
ationally-1.146
ammy-1.133
netflix-1.096
ittle-1.090
Token LED
Token ID12365
Feature activation-6.95e-01

Pos logit contributions
eret+2.389
cano+2.225
hell+2.165
 voic+2.117
 bras+2.095
Neg logit contributions
 Weld-2.840
ationally-2.824
ammy-2.772
netflix-2.691
ittle-2.673
Token panels
Token ID13043
Feature activation-6.86e+00

Pos logit contributions
eret+0.428
cano+0.396
hell+0.386
 voic+0.375
 bras+0.371
Neg logit contributions
 Weld-0.558
ationally-0.550
ammy-0.543
netflix-0.526
ittle-0.526
Token (
Token ID357
Feature activation-1.76e+00

Pos logit contributions
eret+4.569
hell+4.328
cano+4.267
 voic+4.195
 bras+4.129
Neg logit contributions
ationally-4.868
 Weld-4.793
ammy-4.768
netflix-4.649
ittle-4.619
Token5
Token ID20
Feature activation-1.00e+00

Pos logit contributions
eret+1.202
cano+1.125
hell+1.104
 voic+1.063
 bras+1.055
Neg logit contributions
 Weld-1.288
ationally-1.269
ammy-1.250
netflix-1.206
ittle-1.206
Token cm
Token ID12067
Feature activation-2.37e+00

Pos logit contributions
eret+0.712
cano+0.665
hell+0.652
 voic+0.636
 bras+0.631
Neg logit contributions
 Weld-0.710
ationally-0.699
ammy-0.690
netflix-0.666
ittle-0.664
Token
Token ID251
Feature activation+2.47e+00

Pos logit contributions
eret+0.205
cano+0.192
hell+0.187
 voic+0.182
 bras+0.181
Neg logit contributions
 Weld-0.212
ationally-0.209
ammy-0.206
netflix-0.199
ittle-0.199
Token pioneering
Token ID36304
Feature activation-6.12e-02

Pos logit contributions
 Weld+1.740
ationally+1.720
ammy+1.682
ittle+1.623
netflix+1.616
Neg logit contributions
eret-1.774
cano-1.652
hell-1.600
 voic-1.551
 bras-1.548
Token lingu
Token ID20280
Feature activation-1.14e+00

Pos logit contributions
eret+0.043
cano+0.040
hell+0.039
 voic+0.038
 bras+0.038
Neg logit contributions
 Weld-0.044
ationally-0.043
ammy-0.043
ittle-0.041
netflix-0.041
Tokenist
Token ID396
Feature activation-9.48e-01

Pos logit contributions
eret+0.644
cano+0.588
hell+0.574
 voic+0.554
 bras+0.546
Neg logit contributions
 Weld-0.975
ationally-0.959
ammy-0.950
netflix-0.923
ittle-0.921
Token William
Token ID3977
Feature activation-1.99e+00

Pos logit contributions
eret+0.694
cano+0.649
hell+0.638
 voic+0.622
 bras+0.616
Neg logit contributions
 Weld-0.649
ationally-0.641
ammy-0.630
netflix-0.609
ittle-0.608
Token Lab
Token ID3498
Feature activation-5.77e-01

Pos logit contributions
eret+1.481
cano+1.382
hell+1.365
 voic+1.324
 bras+1.316
Neg logit contributions
 Weld-1.323
ationally-1.322
ammy-1.303
netflix-1.260
ittle-1.254
Tokenov
Token ID709
Feature activation+5.09e+00

Pos logit contributions
eret+0.394
cano+0.367
hell+0.358
 voic+0.349
 bras+0.346
Neg logit contributions
 Weld-0.425
ationally-0.419
ammy-0.413
netflix-0.399
ittle-0.398
Token told
Token ID1297
Feature activation-3.49e+00

Pos logit contributions
 Weld+3.616
ationally+3.584
ammy+3.461
ittle+3.388
netflix+3.307
Neg logit contributions
eret-3.552
cano-3.276
 voic-3.188
hell-3.173
 bras-3.098
Token City
Token ID2254
Feature activation+1.39e+00

Pos logit contributions
eret+2.385
cano+2.201
hell+2.180
 voic+2.139
 bras+2.101
Neg logit contributions
 Weld-2.513
ationally-2.482
ammy-2.471
netflix-2.407
ittle-2.367
Token Paper
Token ID14962
Feature activation-1.62e+00

Pos logit contributions
 Weld+1.013
ationally+0.994
ammy+0.973
ittle+0.944
netflix+0.935
Neg logit contributions
eret-0.955
cano-0.883
hell-0.859
 bras-0.846
 voic-0.842
Token in
Token ID287
Feature activation-2.79e+00

Pos logit contributions
eret+1.095
cano+1.019
hell+0.998
 voic+0.971
 bras+0.960
Neg logit contributions
 Weld-1.206
ationally-1.188
ammy-1.174
netflix-1.139
ittle-1.130
Tokenro
Token ID305
Feature activation+1.19e+00

Pos logit contributions
eret+0.988
cano+0.922
hell+0.903
 voic+0.878
 bras+0.871
Neg logit contributions
 Weld-1.003
ationally-0.988
ammy-0.972
netflix-0.937
ittle-0.936
Token
Token ID20977
Feature activation+2.49e+00

Pos logit contributions
 Weld+0.885
ationally+0.872
ammy+0.858
netflix+0.830
ittle+0.828
Neg logit contributions
eret-0.801
cano-0.745
hell-0.727
 voic-0.707
 bras-0.701
TokenCub
Token ID43632
Feature activation-3.80e+00

Pos logit contributions
 Weld+0.886
ationally+0.868
ammy+0.836
netflix+0.780
ittle+0.774
Neg logit contributions
eret-2.640
cano-2.517
hell-2.470
 voic-2.434
 bras-2.424
Tokenans
Token ID504
Feature activation-1.44e+00

Pos logit contributions
eret+2.395
cano+2.233
hell+2.167
 voic+2.097
tes+2.072
Neg logit contributions
 Weld-2.979
ationally-2.891
ammy-2.855
netflix-2.799
ittle-2.790
Token (
Token ID357
Feature activation-1.92e-01

Pos logit contributions
eret+0.979
cano+0.913
hell+0.894
 voic+0.870
 bras+0.861
Neg logit contributions
 Weld-1.063
ationally-1.046
ammy-1.033
netflix-1.005
ittle-0.995
Tokenbl
Token ID2436
Feature activation-5.84e+00

Pos logit contributions
eret+0.128
cano+0.120
hell+0.117
 voic+0.114
 bras+0.112
Neg logit contributions
 Weld-0.144
ationally-0.142
ammy-0.140
netflix-0.135
ittle-0.135
Tokenacks
Token ID4595
Feature activation-1.59e+00

Pos logit contributions
eret+3.623
hell+3.287
cano+3.251
 voic+3.063
tes+3.032
Neg logit contributions
 Weld-4.680
ationally-4.466
netflix-4.402
ammy-4.356
gans-4.227
Token and
Token ID290
Feature activation+3.03e+00

Pos logit contributions
eret+1.090
cano+1.018
hell+0.997
 voic+0.971
 bras+0.959
Neg logit contributions
 Weld-1.162
ationally-1.144
ammy-1.129
netflix-1.092
ittle-1.083
Token mul
Token ID35971
Feature activation-2.57e+00

Pos logit contributions
 Weld+2.022
ationally+1.962
ammy+1.945
ittle+1.893
netflix+1.851
Neg logit contributions
eret-2.273
cano-2.146
hell-2.077
 voic-2.002
 bras-1.976
Tokenatt
Token ID1078
Feature activation-7.32e+00

Pos logit contributions
eret+1.667
hell+1.531
cano+1.531
 bras+1.453
 voic+1.447
Neg logit contributions
 Weld-1.958
ationally-1.933
ammy-1.903
netflix-1.861
ittle-1.826
Tokenos
Token ID418
Feature activation-2.56e+00

Pos logit contributions
eret+3.392
cano+3.046
hell+2.988
tes+2.820
 voic+2.757
Neg logit contributions
 Weld-6.902
ationally-6.817
ammy-6.703
ittle-6.472
netflix-6.441
Token toe
Token ID21189
Feature activation-6.27e+00

Pos logit contributions
 Weld+0.502
ationally+0.492
ammy+0.486
netflix+0.468
ittle+0.468
Neg logit contributions
eret-0.470
cano-0.439
hell-0.428
 voic-0.415
 bras-0.412
Token-
Token ID12
Feature activation-2.89e+00

Pos logit contributions
eret+3.766
cano+3.602
hell+3.580
 voic+3.461
 bras+3.384
Neg logit contributions
 Weld-4.783
ationally-4.777
ammy-4.747
ittle-4.655
netflix-4.537
Tokento
Token ID1462
Feature activation+1.58e+00

Pos logit contributions
eret+1.963
cano+1.850
hell+1.843
 voic+1.759
 bras+1.732
Neg logit contributions
 Weld-2.088
ationally-2.063
ammy-2.023
netflix-1.963
ittle-1.957
Token-
Token ID12
Feature activation-2.76e-01

Pos logit contributions
 Weld+1.062
ationally+1.048
ammy+1.032
ittle+0.997
netflix+0.996
Neg logit contributions
eret-1.163
cano-1.101
hell-1.060
 voic-1.047
 bras-1.047
Tokentoe
Token ID44579
Feature activation-3.81e+00

Pos logit contributions
eret+0.178
cano+0.165
hell+0.159
 voic+0.158
 bras+0.156
Neg logit contributions
 Weld-0.213
ationally-0.211
ammy-0.208
ittle-0.202
netflix-0.201
Token with
Token ID351
Feature activation+5.55e-01

Pos logit contributions
eret+2.416
cano+2.216
hell+2.205
 voic+2.136
 bras+2.121
Neg logit contributions
 Weld-2.934
ationally-2.922
ammy-2.876
netflix-2.811
ittle-2.791
Token the
Token ID262
Feature activation-9.21e-01

Pos logit contributions
 Weld+0.385
ationally+0.377
ammy+0.371
netflix+0.357
ittle+0.356
Neg logit contributions
eret-0.406
cano-0.380
hell-0.371
 voic-0.361
 bras-0.358
Token world
Token ID995
Feature activation-3.49e+00

Pos logit contributions
eret+0.644
cano+0.601
hell+0.587
 voic+0.571
 bras+0.566
Neg logit contributions
 Weld-0.665
ationally-0.655
ammy-0.644
netflix-0.621
ittle-0.621
Token
Token ID447
Feature activation-3.34e+00

Pos logit contributions
eret+2.450
cano+2.313
hell+2.280
 voic+2.230
 bras+2.216
Neg logit contributions
 Weld-2.435
ationally-2.395
ammy-2.379
netflix-2.331
ittle-2.301
Token
Token ID247
Feature activation-1.67e+00

Pos logit contributions
eret+2.166
cano+2.024
hell+1.982
 voic+1.907
 bras+1.885
Neg logit contributions
 Weld-2.538
ationally-2.510
ammy-2.491
netflix-2.416
ittle-2.388
Tokens
Token ID82
Feature activation+3.19e+00

Pos logit contributions
eret+0.981
cano+0.906
hell+0.883
 voic+0.852
 bras+0.842
Neg logit contributions
 Weld-1.380
ationally-1.357
ammy-1.347
netflix-1.308
ittle-1.302
Token had
Token ID550
Feature activation-1.20e+00

Pos logit contributions
 Weld+0.659
ationally+0.645
ammy+0.632
ittle+0.609
netflix+0.607
Neg logit contributions
eret-0.718
cano-0.676
hell-0.658
 voic-0.641
 bras-0.635
Token been
Token ID587
Feature activation-1.15e+00

Pos logit contributions
eret+0.835
cano+0.778
hell+0.761
 voic+0.744
 bras+0.737
Neg logit contributions
 Weld-0.870
ationally-0.858
ammy-0.847
netflix-0.817
ittle-0.815
Token set
Token ID900
Feature activation+8.92e-01

Pos logit contributions
eret+0.819
cano+0.767
hell+0.747
 voic+0.728
 bras+0.723
Neg logit contributions
 Weld-0.813
ationally-0.800
ammy-0.786
ittle-0.758
netflix-0.757
Token at
Token ID379
Feature activation-3.12e+00

Pos logit contributions
 Weld+0.629
ationally+0.621
ammy+0.607
ittle+0.587
netflix+0.584
Neg logit contributions
eret-0.635
cano-0.598
hell-0.582
 voic-0.566
 bras-0.565
Token 22
Token ID2534
Feature activation+3.43e+00

Pos logit contributions
eret+1.923
cano+1.772
hell+1.736
 voic+1.712
 bras+1.681
Neg logit contributions
 Weld-2.448
ationally-2.436
ammy-2.415
netflix-2.340
ittle-2.318
Token,
Token ID11
Feature activation+3.12e-01

Pos logit contributions
 Weld+2.339
ationally+2.281
ammy+2.233
ittle+2.161
gans+2.108
Neg logit contributions
eret-2.531
cano-2.399
hell-2.333
 voic-2.257
 bras-2.218
Token500
Token ID4059
Feature activation+1.67e+00

Pos logit contributions
 Weld+0.197
ationally+0.194
ammy+0.190
netflix+0.183
ittle+0.182
Neg logit contributions
eret-0.247
cano-0.232
hell-0.227
 voic-0.222
 bras-0.220
Token students
Token ID2444
Feature activation-1.59e+00

Pos logit contributions
 Weld+1.158
ationally+1.134
ammy+1.105
ittle+1.075
netflix+1.061
Neg logit contributions
eret-1.212
cano-1.150
hell-1.120
 voic-1.079
 bras-1.072
Token.
Token ID13
Feature activation-2.31e+00

Pos logit contributions
eret+1.069
cano+0.992
hell+0.972
 voic+0.945
 bras+0.935
Neg logit contributions
 Weld-1.189
ationally-1.173
ammy-1.158
netflix-1.121
ittle-1.116
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
eret+1.609
cano+1.489
hell+1.467
 voic+1.419
 bras+1.406
Neg logit contributions
ationally-1.639
 Weld-1.634
ammy-1.617
netflix-1.566
ittle-1.552
Token
Token ID198
Feature activation-1.53e+00

Pos logit contributions
eret+0.880
cano+0.822
hell+0.808
 voic+0.785
 bras+0.778
Neg logit contributions
 Weld-0.839
ationally-0.827
ammy-0.816
ittle-0.784
netflix-0.784
Token much
Token ID881
Feature activation+2.12e+00

Pos logit contributions
eret+2.161
cano+2.018
hell+1.966
 voic+1.910
 bras+1.898
Neg logit contributions
 Weld-2.971
ationally-2.931
ammy-2.900
netflix-2.827
gans-2.753
Token as
Token ID355
Feature activation-2.65e+00

Pos logit contributions
 Weld+1.218
ationally+1.193
ammy+1.159
ittle+1.112
netflix+1.105
Neg logit contributions
eret-1.806
cano-1.704
hell-1.659
 voic-1.637
 bras-1.616
Token $
Token ID720
Feature activation-1.70e+00

Pos logit contributions
eret+1.561
cano+1.433
hell+1.413
 voic+1.373
 bras+1.359
Neg logit contributions
 Weld-2.162
ationally-2.138
ammy-2.124
netflix-2.062
ittle-2.054
Token2
Token ID17
Feature activation-2.33e+00

Pos logit contributions
eret+1.177
cano+1.099
hell+1.087
 voic+1.044
 bras+1.037
Neg logit contributions
 Weld-1.223
ationally-1.210
ammy-1.198
netflix-1.149
ittle-1.148
Token million
Token ID1510
Feature activation+7.58e-02

Pos logit contributions
eret+1.591
cano+1.480
hell+1.456
 voic+1.428
 bras+1.420
Neg logit contributions
 Weld-1.696
ationally-1.685
ammy-1.656
netflix-1.618
ittle-1.601
Token.)
Token ID2014
Feature activation-7.70e+00

Pos logit contributions
 Weld+0.050
ationally+0.050
ammy+0.049
netflix+0.047
ittle+0.047
Neg logit contributions
eret-0.057
cano-0.054
hell-0.053
 voic-0.051
 bras-0.051
Token The
Token ID383
Feature activation-2.28e+00

Pos logit contributions
eret+4.941
hell+4.654
cano+4.477
 voic+4.432
 bras+4.388
Neg logit contributions
ationally-5.673
ammy-5.547
 Weld-5.439
ittle-5.344
netflix-5.307
Token private
Token ID2839
Feature activation+2.21e+00

Pos logit contributions
eret+1.395
cano+1.293
hell+1.261
 voic+1.232
 bras+1.216
Neg logit contributions
 Weld-1.830
ationally-1.814
ammy-1.786
netflix-1.734
ittle-1.733
Token school
Token ID1524
Feature activation-8.75e-01

Pos logit contributions
 Weld+1.455
ationally+1.419
ammy+1.394
ittle+1.342
netflix+1.334
Neg logit contributions
eret-1.676
cano-1.596
hell-1.546
 voic-1.501
 bras-1.495
Token she
Token ID673
Feature activation+4.67e+00

Pos logit contributions
eret+0.632
cano+0.591
hell+0.580
 voic+0.564
 bras+0.561
Neg logit contributions
 Weld-0.608
ationally-0.599
ammy-0.590
netflix-0.570
ittle-0.568
Token attended
Token ID9141
Feature activation+4.23e+00

Pos logit contributions
 Weld+2.865
ationally+2.844
ammy+2.757
ittle+2.683
netflix+2.614
Neg logit contributions
eret-3.686
cano-3.476
 voic-3.370
hell-3.347
 bras-3.270
Token or
Token ID393
Feature activation-6.17e+00

Pos logit contributions
 Weld+0.168
ationally+0.165
ammy+0.162
ittle+0.157
netflix+0.157
Neg logit contributions
eret-0.169
cano-0.157
hell-0.153
 bras-0.149
 voic-0.148
Token call
Token ID869
Feature activation-4.68e+00

Pos logit contributions
eret+3.659
cano+3.393
 voic+3.373
hell+3.342
 bras+3.159
Neg logit contributions
 Weld-5.034
ationally-4.871
ammy-4.847
ittle-4.724
netflix-4.546
Token 0
Token ID657
Feature activation-8.91e+00

Pos logit contributions
eret+2.289
cano+2.094
hell+2.060
 voic+2.034
tes+1.915
Neg logit contributions
 Weld-4.282
ationally-4.258
ammy-4.187
ittle-4.078
netflix-3.997
Token207
Token ID22745
Feature activation-6.88e+00

Pos logit contributions
eret+4.953
 voic+4.869
cano+4.641
hell+4.624
tes+4.579
Neg logit contributions
 Weld-7.329
ammy-6.890
ittle-6.884
gans-6.782
ationally-6.688
Token 7
Token ID767
Feature activation-5.71e+00

Pos logit contributions
eret+3.498
cano+3.299
hell+3.238
 voic+3.201
 bras+3.115
Neg logit contributions
 Weld-6.094
ationally-5.887
ammy-5.883
ittle-5.786
netflix-5.659
Token82
Token ID6469
Feature activation-7.63e+00

Pos logit contributions
eret+3.262
cano+3.164
 voic+3.048
hell+2.996
tes+2.903
Neg logit contributions
 Weld-4.593
ationally-4.545
ammy-4.531
ittle-4.453
netflix-4.392
Token 4
Token ID604
Feature activation-5.41e+00

Pos logit contributions
eret+3.018
cano+2.925
hell+2.720
 voic+2.639
 bras+2.573
Neg logit contributions
 Weld-7.244
ammy-7.236
ationally-7.219
ittle-7.044
netflix-6.887
Token368
Token ID27412
Feature activation-5.99e+00

Pos logit contributions
eret+3.482
cano+3.360
hell+3.214
 voic+3.174
tes+3.026
Neg logit contributions
 Weld-4.089
ationally-4.043
ittle-3.967
ammy-3.963
gans-3.840
Token<|endoftext|>
Token ID50256
Feature activation+3.15e+00

Pos logit contributions
eret+2.972
cano+2.955
 voic+2.877
hell+2.858
 bras+2.689
Neg logit contributions
 Weld-5.136
ationally-5.053
ammy-4.996
ittle-4.949
netflix-4.822
TokenTo
Token ID2514
Feature activation+8.47e-01

Pos logit contributions
 Weld+2.264
ationally+2.247
ammy+2.205
netflix+2.167
ittle+2.130
Neg logit contributions
eret-2.170
cano-2.026
 voic-1.940
hell-1.930
 bras-1.923
Token all
Token ID477
Feature activation-4.84e+00

Pos logit contributions
 Weld+0.614
ationally+0.605
ammy+0.595
ittle+0.574
netflix+0.574
Neg logit contributions
eret-0.589
cano-0.550
hell-0.537
 voic-0.522
 bras-0.518
Token,
Token ID11
Feature activation+2.21e+00

Pos logit contributions
 Weld+2.609
ationally+2.549
ammy+2.485
ittle+2.396
netflix+2.387
Neg logit contributions
eret-2.835
cano-2.649
hell-2.557
 voic-2.517
 bras-2.481
Token so
Token ID523
Feature activation-3.53e+00

Pos logit contributions
 Weld+1.547
ationally+1.513
ammy+1.473
ittle+1.430
netflix+1.425
Neg logit contributions
eret-1.595
cano-1.484
hell-1.437
 voic-1.401
 bras-1.386
Token caveat
Token ID36531
Feature activation+9.66e-01

Pos logit contributions
eret+2.438
cano+2.279
hell+2.253
 voic+2.191
 bras+2.181
Neg logit contributions
 Weld-2.512
ationally-2.494
ammy-2.482
netflix-2.396
ittle-2.380
Token empt
Token ID23909
Feature activation-5.16e+00

Pos logit contributions
 Weld+0.919
ationally+0.909
ammy+0.896
netflix+0.873
ittle+0.873
Neg logit contributions
eret-0.453
cano-0.409
hell-0.395
 voic-0.378
 bras-0.373
Tokenor
Token ID273
Feature activation-1.31e+00

Pos logit contributions
eret+2.678
hell+2.340
cano+2.339
 voic+2.218
 bras+2.160
Neg logit contributions
 Weld-4.674
ationally-4.605
ammy-4.510
netflix-4.497
ittle-4.408
Token.)
Token ID2014
Feature activation-8.00e+00

Pos logit contributions
eret+0.941
cano+0.881
hell+0.864
 voic+0.844
 bras+0.837
Neg logit contributions
 Weld-0.905
ationally-0.896
ammy-0.881
netflix-0.853
ittle-0.848
Token
Token ID198
Feature activation-1.19e+00

Pos logit contributions
eret+5.020
hell+4.743
cano+4.583
 voic+4.504
 bras+4.500
Neg logit contributions
ationally-5.928
ammy-5.907
netflix-5.781
ittle-5.754
 Weld-5.725
Token
Token ID198
Feature activation-4.99e+00

Pos logit contributions
eret+0.866
cano+0.810
hell+0.795
 voic+0.773
 bras+0.767
Neg logit contributions
 Weld-0.821
ationally-0.809
ammy-0.798
netflix-0.767
ittle-0.767
TokenAnother
Token ID6610
Feature activation-4.34e-01

Pos logit contributions
eret+3.199
hell+3.043
cano+2.975
tes+2.819
 voic+2.809
Neg logit contributions
 Weld-3.794
ationally-3.704
ammy-3.682
ittle-3.571
netflix-3.538
Token of
Token ID286
Feature activation+3.30e+00

Pos logit contributions
eret+0.302
cano+0.282
hell+0.276
 voic+0.269
 bras+0.266
Neg logit contributions
 Weld-0.313
ationally-0.309
ammy-0.304
netflix-0.294
ittle-0.294
Token Moore
Token ID8877
Feature activation-1.67e+00

Pos logit contributions
 Weld+2.350
ationally+2.292
ammy+2.257
netflix+2.155
ittle+2.135
Neg logit contributions
eret-2.339
cano-2.189
hell-2.110
 voic-2.067
 bras-2.037
Token two
Token ID734
Feature activation+3.54e+00

Pos logit contributions
 Weld+4.186
ationally+4.101
ammy+3.975
gans+3.824
netflix+3.812
Neg logit contributions
eret-5.332
cano-5.134
hell-4.925
zek-4.701
tes-4.681
Token parties
Token ID4671
Feature activation+6.79e-01

Pos logit contributions
 Weld+2.180
ationally+2.131
ammy+2.051
ittle+1.982
netflix+1.980
Neg logit contributions
eret-2.828
cano-2.690
hell-2.617
 voic-2.516
 bras-2.486
Token.
Token ID13
Feature activation+4.08e-01

Pos logit contributions
 Weld+0.486
ationally+0.476
ammy+0.468
ittle+0.453
netflix+0.452
Neg logit contributions
eret-0.479
cano-0.448
hell-0.435
 voic-0.425
 bras-0.422
Token
Token ID198
Feature activation-2.95e+00

Pos logit contributions
 Weld+0.286
ationally+0.280
ammy+0.275
netflix+0.265
ittle+0.265
Neg logit contributions
eret-0.294
cano-0.276
hell-0.269
 voic-0.262
 bras-0.260
Token
Token ID198
Feature activation-6.22e-02

Pos logit contributions
eret+2.020
hell+1.871
cano+1.862
 voic+1.786
 bras+1.772
Neg logit contributions
 Weld-2.136
ationally-2.113
ammy-2.111
ittle-2.029
netflix-2.006
TokenPrep
Token ID37534
Feature activation-7.80e+00

Pos logit contributions
eret+0.042
cano+0.039
hell+0.039
 voic+0.038
 bras+0.037
Neg logit contributions
 Weld-0.046
ationally-0.045
ammy-0.045
netflix-0.043
ittle-0.043
Tokenaring
Token ID1723
Feature activation+1.60e-01

Pos logit contributions
eret+4.606
cano+4.052
hell+3.993
 voic+3.901
 bras+3.797
Neg logit contributions
 Weld-6.224
ationally-6.096
ammy-6.007
netflix-5.983
ittle-5.922
Token for
Token ID329
Feature activation-1.13e+00

Pos logit contributions
 Weld+0.121
ationally+0.119
ammy+0.117
netflix+0.114
ittle+0.113
Neg logit contributions
eret-0.105
cano-0.098
hell-0.096
 voic-0.093
 bras-0.092
Token independence
Token ID10404
Feature activation-1.26e+00

Pos logit contributions
eret+0.786
cano+0.733
hell+0.717
 voic+0.700
 bras+0.693
Neg logit contributions
 Weld-0.819
ationally-0.810
ammy-0.798
netflix-0.770
ittle-0.770
Token:
Token ID25
Feature activation-4.94e-01

Pos logit contributions
eret+0.899
cano+0.839
hell+0.822
 voic+0.802
 bras+0.796
Neg logit contributions
 Weld-0.891
ationally-0.880
ammy-0.868
netflix-0.834
ittle-0.833
Token 1961
Token ID20510
Feature activation+1.48e+00

Pos logit contributions
eret+0.339
cano+0.315
hell+0.308
 voic+0.301
 bras+0.298
Neg logit contributions
 Weld-0.363
ationally-0.358
ammy-0.353
netflix-0.341
ittle-0.340
Token highlight
Token ID7238
Feature activation-1.45e+00

Pos logit contributions
eret+0.460
cano+0.429
hell+0.419
 voic+0.408
 bras+0.404
Neg logit contributions
 Weld-0.490
ationally-0.483
ammy-0.476
netflix-0.460
ittle-0.459
Token her
Token ID607
Feature activation+7.25e-01

Pos logit contributions
eret+0.999
cano+0.929
hell+0.910
 voic+0.893
 bras+0.884
Neg logit contributions
 Weld-1.050
ationally-1.036
ammy-1.025
netflix-0.991
ittle-0.987
Token support
Token ID1104
Feature activation+2.39e+00

Pos logit contributions
 Weld+0.521
ationally+0.512
ammy+0.504
ittle+0.485
netflix+0.485
Neg logit contributions
eret-0.511
cano-0.477
hell-0.465
 voic-0.452
 bras-0.448
Token for
Token ID329
Feature activation-2.54e-01

Pos logit contributions
 Weld+1.829
ationally+1.800
ammy+1.755
ittle+1.711
netflix+1.711
Neg logit contributions
eret-1.570
cano-1.461
hell-1.427
 voic-1.374
 bras-1.370
Token free
Token ID1479
Feature activation-1.90e+00

Pos logit contributions
eret+0.181
cano+0.170
hell+0.166
 voic+0.161
 bras+0.160
Neg logit contributions
 Weld-0.179
ationally-0.176
ammy-0.173
netflix-0.167
ittle-0.167
Token trade
Token ID3292
Feature activation-8.88e+00

Pos logit contributions
eret+1.246
cano+1.164
 voic+1.141
hell+1.133
 bras+1.125
Neg logit contributions
ammy-1.420
ationally-1.412
 Weld-1.410
netflix-1.352
ittle-1.349
Token,
Token ID11
Feature activation-4.00e-01

Pos logit contributions
eret+4.986
hell+4.644
cano+4.624
 voic+4.621
 bras+4.621
Neg logit contributions
ammy-7.056
ationally-7.005
 Weld-6.979
netflix-6.958
ittle-6.587
Token but
Token ID475
Feature activation-6.65e-01

Pos logit contributions
eret+0.283
cano+0.264
hell+0.258
 voic+0.251
 bras+0.249
Neg logit contributions
 Weld-0.286
ationally-0.282
ammy-0.277
netflix-0.268
ittle-0.267
Token also
Token ID635
Feature activation-1.78e+00

Pos logit contributions
eret+0.481
cano+0.449
hell+0.440
 voic+0.431
 bras+0.428
Neg logit contributions
 Weld-0.461
ationally-0.455
ammy-0.450
netflix-0.432
ittle-0.431
Token the
Token ID262
Feature activation+2.24e+00

Pos logit contributions
eret+1.211
cano+1.131
hell+1.109
 voic+1.092
 bras+1.080
Neg logit contributions
 Weld-1.295
ationally-1.281
ammy-1.271
netflix-1.222
ittle-1.214
Token concerns
Token ID4786
Feature activation-1.24e+00

Pos logit contributions
 Weld+1.538
ationally+1.503
ammy+1.487
ittle+1.424
netflix+1.412
Neg logit contributions
eret-1.659
cano-1.548
hell-1.508
 bras-1.448
 voic-1.445