TOP ACTIVATIONS
MAX = 2.060

brother ." President Rodrigo Duterte had nothing but kind
2016 . 01 . 29 "] [ Round " 11 "]
. Future Hall of Fame slug ger Stan Mus ial ,
m going to have to paraph rase here that the
Kills , Will y Moon sacked * Low ratings
exact mechanism that triggered the stream of incorrect data . They
ijk a an Z ee "] [ Date " 2016 .
Big Bang Theory CBS Amy Poe hler Parks and Recreation NBC
"] [ Round " 11 "] [ White " Ab as
24 11 S . Shepherd Today : Tor chy 's
, <|endoftext|> The urge to binge on streaming Netflix television and
[ who plays Mr . Poe ] sings really well .
on driving related skills . Springfield , VA : US Department
ov , N ij at "] [ Black " Ant ip
create an initialization file with | : mk vim rc |
able to direct more light reflected by the scaff old into
" which can come from stroke , head trauma or other
of her Dec . 6 runoff against Rep . Bill Cassidy
baking that also contains baking soda ( it s
panels is composed of combust ible plastic material . A sample

MIN ACTIVATIONS
MIN = -2.293

did not issue the total Loving v . Virginia victory that
will be the equivalent of Loving v . Virginia , which
outright ban on wearing the hijab . Sad ain
- w earing of the hijab or veil ,
acing inter p ares and supra - national nature of the
trip worsh ipping Lenin and Trotsky , around whom all history
intellig ents ia resisted en masse letting itself be travers ed
its national debt to a level that the market thinks is
making at the state court level , where 95 percent of
M akh nov ists , Trotsky ists par rot the line
Nigel Farage : " Lord Hes elt ine fears what the
47 ] < k link ttp > lol m 2 k
talk about pass porting of the financial
childhood , and a " Girl " side , for the
devoid of social content . Trotsky ism is a religion trip
When a lady politely declines to dance with you
prime minister should take Mr Hes elt ine 's comments "
ap = arg parse . Arg ument Parser () ap .
akh no against Lenin and Trotsky , for worldwide
. government worked with Exxon Mobil and Chevron , the two

INTERVAL 0.971 - 2.060
CONTAINS 0.385%

Temple Address : Sector 20 , J Road ,
boards offer help with beating alcohol or avoiding d eng ue
Say y af . Dr Abdullah has been publicly generous about
a total to thumb your nose at , and his advanced
rest is history . <|endoftext|> About This Game Choose

INTERVAL -0.117 - 0.971
CONTAINS 70.504%

ine Page and Ma ureen St ap leton , particularly ,
version unlocks more effects and frames ) [ Home page ]
said . " I don 't know how guys on either
C ultural If you 're not tempted
page layout templates are gone . If you open a document

INTERVAL -1.205 - -0.117
CONTAINS 28.999%

Batman . On the other hand , it still might have
ach , a fuel supplier which is connected to Priv at
s take a moment to discuss some of the
her " Last Will and Testament ": I leave
for it first came about when L . A . attorney

INTERVAL -2.293 - -1.205
CONTAINS 0.112%

refunds work ); CSV ( BIP 68 / B IP 112
app data _ full v ) { // Time component const
OF TRAN SM ISSION /// ---------------------------------------------------------------- ---------------------------------------------------------------- ------------------------ -- /// L
including items from the Imperial Hotel in Tokyo and Wright
d ans la corporation . Apr è s une tentative inf
Token brother
Token ID3956
Feature activation-4.81e-01

Pos logit contributions
 Lauder+0.011
 Loving+0.010
 Sioux+0.010
 Hots+0.009
 Subtle+0.009
Neg logit contributions
obar-0.012
rane-0.012
minist-0.011
oba-0.011
ega-0.010
Token."
Token ID526
Feature activation+3.45e-01

Pos logit contributions
 Lauder+0.857
 Loving+0.780
 Sioux+0.771
 Hots+0.724
 Subtle+0.713
Neg logit contributions
obar-0.836
rane-0.807
minist-0.738
oba-0.723
ega-0.713
Token
Token ID198
Feature activation+1.05e-01

Pos logit contributions
obar+0.642
rane+0.617
minist+0.570
oba+0.561
ega+0.556
Neg logit contributions
 Lauder-0.560
 Loving-0.504
 Sioux-0.499
 Hots-0.467
 Subtle-0.455
Token
Token ID198
Feature activation+6.35e-02

Pos logit contributions
obar+0.191
rane+0.184
minist+0.169
oba+0.167
ega+0.164
Neg logit contributions
 Lauder-0.179
 Loving-0.159
 Sioux-0.159
 Hots-0.148
 Subtle-0.146
TokenPresident
Token ID10364
Feature activation+8.36e-02

Pos logit contributions
obar+0.102
rane+0.098
minist+0.089
oba+0.087
ega+0.086
Neg logit contributions
 Lauder-0.122
 Loving-0.112
 Sioux-0.111
 Hots-0.104
 Subtle-0.103
Token Rodrigo
Token ID46198
Feature activation+2.06e+00

Pos logit contributions
obar+0.121
rane+0.115
minist+0.104
oba+0.101
ega+0.099
Neg logit contributions
 Lauder-0.173
 Loving-0.160
 Sioux-0.159
 Hots-0.150
 Subtle-0.148
Token Duterte
Token ID25763
Feature activation+1.38e+00

Pos logit contributions
obar+2.467
rane+2.227
oba+1.976
minist+1.946
ega+1.856
Neg logit contributions
 Lauder-4.687
 Sioux-4.367
 Loving-4.315
 Hots-4.160
 Subtle-4.120
Token had
Token ID550
Feature activation+2.44e-01

Pos logit contributions
obar+2.494
rane+2.380
ega+2.208
minist+2.188
oba+2.152
Neg logit contributions
 Lauder-2.284
 Loving-2.074
 Sioux-2.056
 Subtle-1.926
 Hots-1.860
Token nothing
Token ID2147
Feature activation-8.97e-02

Pos logit contributions
obar+0.460
rane+0.442
minist+0.408
ega+0.403
oba+0.402
Neg logit contributions
 Lauder-0.394
 Loving-0.358
 Sioux-0.350
 Subtle-0.327
 Hots-0.324
Token but
Token ID475
Feature activation-9.97e-02

Pos logit contributions
 Lauder+0.159
 Loving+0.144
 Sioux+0.143
 Hots+0.134
 Subtle+0.132
Neg logit contributions
obar-0.157
rane-0.151
minist-0.139
oba-0.136
ega-0.134
Token kind
Token ID1611
Feature activation-1.63e-01

Pos logit contributions
 Lauder+0.186
 Loving+0.168
 Sioux+0.166
 Hots+0.158
 Subtle+0.157
Neg logit contributions
obar-0.164
rane-0.157
minist-0.144
oba-0.142
ega-0.140
Token2016
Token ID5304
Feature activation-5.40e-01

Pos logit contributions
 Lauder+0.137
 Loving+0.126
 Sioux+0.125
 Hots+0.116
 Sikh+0.115
Neg logit contributions
obar-0.124
rane-0.119
minist-0.109
oba-0.107
ega-0.105
Token.
Token ID13
Feature activation-3.84e-02

Pos logit contributions
 Lauder+0.949
 Loving+0.848
 Sioux+0.839
 Hots+0.781
 Subtle+0.774
Neg logit contributions
obar-0.954
rane-0.926
minist-0.847
oba-0.836
ega-0.821
Token01
Token ID486
Feature activation+6.37e-02

Pos logit contributions
 Lauder+0.076
 Loving+0.069
 Sioux+0.069
 Hots+0.065
 Sikh+0.064
Neg logit contributions
obar-0.058
rane-0.056
minist-0.051
oba-0.050
ega-0.049
Token.
Token ID13
Feature activation+5.19e-02

Pos logit contributions
obar+0.108
rane+0.104
minist+0.094
oba+0.094
ega+0.092
Neg logit contributions
 Lauder-0.117
 Sioux-0.104
 Loving-0.103
 Hots-0.096
 Subtle-0.096
Token29
Token ID1959
Feature activation+1.07e-02

Pos logit contributions
obar+0.084
rane+0.082
minist+0.075
oba+0.072
ega+0.071
Neg logit contributions
 Lauder-0.098
 Loving-0.089
 Sioux-0.088
 Hots-0.083
 Sikh-0.081
Token"]
Token ID8973
Feature activation+1.75e+00

Pos logit contributions
obar+0.012
rane+0.012
minist+0.010
oba+0.010
ega+0.010
Neg logit contributions
 Lauder-0.025
 Loving-0.023
 Sioux-0.023
 Subtle-0.022
 Sikh-0.022
Token [
Token ID685
Feature activation+2.04e-01

Pos logit contributions
obar+2.562
rane+2.546
ega+2.291
oba+2.229
minist+2.200
Neg logit contributions
 Lauder-3.489
 Sioux-3.036
 Loving-3.016
etooth-2.928
 Sikh-2.804
TokenRound
Token ID22685
Feature activation-3.53e-01

Pos logit contributions
obar+0.263
rane+0.250
minist+0.222
oba+0.217
ega+0.215
Neg logit contributions
 Lauder-0.452
 Loving-0.419
 Sioux-0.415
 Hots-0.392
 Subtle-0.391
Token "
Token ID366
Feature activation+3.19e-03

Pos logit contributions
 Lauder+0.407
 Loving+0.352
 Sioux+0.351
 Subtle+0.311
 Sikh+0.301
Neg logit contributions
obar-0.826
rane-0.806
oba-0.749
minist-0.748
ega-0.741
Token11
Token ID1157
Feature activation-2.77e-01

Pos logit contributions
obar+0.006
rane+0.006
minist+0.005
oba+0.005
ega+0.005
Neg logit contributions
 Lauder-0.005
 Loving-0.005
 Sioux-0.005
 Hots-0.005
 Subtle-0.005
Token"]
Token ID8973
Feature activation+1.59e+00

Pos logit contributions
 Lauder+0.529
 Loving+0.485
 Sioux+0.479
 Hots+0.451
 Subtle+0.444
Neg logit contributions
obar-0.447
rane-0.430
minist-0.391
oba-0.383
ega-0.377
Token.
Token ID13
Feature activation+1.04e-01

Pos logit contributions
 Lauder+0.089
 Loving+0.080
 Sioux+0.078
 Subtle+0.073
 Hots+0.072
Neg logit contributions
obar-0.101
rane-0.097
minist-0.090
oba-0.088
ega-0.087
Token Future
Token ID10898
Feature activation+6.24e-01

Pos logit contributions
obar+0.187
rane+0.177
minist+0.165
oba+0.162
ega+0.160
Neg logit contributions
 Lauder-0.171
 Loving-0.151
 Sioux-0.150
 Hots-0.138
 Sikh-0.138
Token Hall
Token ID4789
Feature activation+8.54e-01

Pos logit contributions
obar+1.109
rane+1.063
minist+0.984
oba+0.970
ega+0.945
Neg logit contributions
 Lauder-1.060
 Loving-0.954
 Sioux-0.945
 Subtle-0.887
 Hots-0.882
Token of
Token ID286
Feature activation-5.66e-02

Pos logit contributions
obar+1.801
rane+1.743
minist+1.628
oba+1.599
ega+1.581
Neg logit contributions
 Lauder-1.199
 Loving-1.060
 Sioux-1.038
 Hots-0.951
 Sikh-0.932
Token Fame
Token ID18864
Feature activation+1.24e-01

Pos logit contributions
 Lauder+0.098
 Loving+0.089
 Sioux+0.088
 Hots+0.083
 Subtle+0.081
Neg logit contributions
obar-0.101
rane-0.097
minist-0.089
oba-0.088
ega-0.086
Token slug
Token ID31065
Feature activation+1.68e+00

Pos logit contributions
obar+0.222
rane+0.215
minist+0.199
oba+0.194
ega+0.191
Neg logit contributions
 Lauder-0.212
 Loving-0.192
 Sioux-0.187
 Hots-0.175
 Subtle-0.174
Tokenger
Token ID1362
Feature activation-4.84e-02

Pos logit contributions
obar+2.542
rane+2.421
minist+2.241
oba+2.110
anders+2.008
Neg logit contributions
 Lauder-3.374
 Loving-3.046
 Sioux-2.959
 Sikh-2.845
 Subtle-2.811
Token Stan
Token ID7299
Feature activation-6.09e-02

Pos logit contributions
 Lauder+0.078
 Loving+0.071
 Sioux+0.069
 Hots+0.064
 Subtle+0.064
Neg logit contributions
obar-0.091
rane-0.088
minist-0.081
oba-0.079
ega-0.079
Token Mus
Token ID2629
Feature activation-2.05e-01

Pos logit contributions
 Lauder+0.091
 Sioux+0.082
 Loving+0.081
 Hots+0.076
 Subtle+0.074
Neg logit contributions
obar-0.121
rane-0.116
oba-0.107
minist-0.107
ega-0.105
Tokenial
Token ID498
Feature activation-1.38e-01

Pos logit contributions
 Lauder+0.491
 Loving+0.454
 Sioux+0.450
 Hots+0.430
 Subtle+0.427
Neg logit contributions
obar-0.237
rane-0.226
minist-0.193
oba-0.187
ega-0.182
Token,
Token ID11
Feature activation+2.29e-02

Pos logit contributions
 Lauder+0.217
 Loving+0.195
 Sioux+0.193
 Subtle+0.178
 Hots+0.177
Neg logit contributions
obar-0.269
rane-0.257
minist-0.237
oba-0.234
ega-0.234
Tokenm
Token ID76
Feature activation+5.64e-01

Pos logit contributions
obar+0.027
rane+0.027
minist+0.025
oba+0.024
ega+0.023
Neg logit contributions
 Lauder-0.028
 Loving-0.025
 Sioux-0.025
 Hots-0.024
 Subtle-0.023
Token going
Token ID1016
Feature activation+1.05e-01

Pos logit contributions
obar+1.010
rane+0.961
minist+0.897
oba+0.870
ega+0.854
Neg logit contributions
 Lauder-0.983
 Loving-0.868
 Sioux-0.867
 Hots-0.815
 Subtle-0.811
Token to
Token ID284
Feature activation+1.19e-01

Pos logit contributions
obar+0.213
rane+0.207
minist+0.192
oba+0.188
ega+0.186
Neg logit contributions
 Lauder-0.157
 Loving-0.140
 Sioux-0.138
 Hots-0.127
 Sikh-0.125
Token have
Token ID423
Feature activation+1.35e-01

Pos logit contributions
obar+0.198
rane+0.191
minist+0.175
oba+0.171
ega+0.169
Neg logit contributions
 Lauder-0.217
 Loving-0.196
 Sioux-0.193
 Hots-0.182
 Subtle-0.181
Token to
Token ID284
Feature activation+1.22e-01

Pos logit contributions
obar+0.257
rane+0.247
minist+0.229
oba+0.223
ega+0.222
Neg logit contributions
 Lauder-0.215
 Loving-0.192
 Sioux-0.189
 Hots-0.177
 Subtle-0.176
Token paraph
Token ID38624
Feature activation+1.67e+00

Pos logit contributions
obar+0.200
rane+0.193
minist+0.175
oba+0.173
ega+0.169
Neg logit contributions
 Lauder-0.230
 Loving-0.209
 Sioux-0.205
 Hots-0.194
 Subtle-0.192
Tokenrase
Token ID22789
Feature activation-3.68e-01

Pos logit contributions
obar+3.091
rane+3.025
oba+2.704
ega+2.682
minist+2.677
Neg logit contributions
 Lauder-2.896
 Loving-2.600
 Sioux-2.589
 Hots-2.400
 Sikh-2.346
Token here
Token ID994
Feature activation+5.56e-01

Pos logit contributions
 Lauder+0.590
 Loving+0.529
 Sioux+0.522
 Hots+0.486
 Subtle+0.477
Neg logit contributions
obar-0.702
rane-0.679
minist-0.632
oba-0.613
ega-0.608
Token
Token ID851
Feature activation-2.12e-01

Pos logit contributions
obar+1.069
rane+1.026
minist+0.964
oba+0.933
ega+0.918
Neg logit contributions
 Lauder-0.881
 Loving-0.785
 Sioux-0.772
 Hots-0.723
 Subtle-0.707
Token that
Token ID326
Feature activation-9.10e-02

Pos logit contributions
 Lauder+0.345
 Loving+0.309
 Sioux+0.306
 Hots+0.287
 Subtle+0.279
Neg logit contributions
obar-0.398
rane-0.382
minist-0.355
oba-0.345
ega-0.342
Token the
Token ID262
Feature activation-4.28e-02

Pos logit contributions
 Lauder+0.146
 Loving+0.131
 Sioux+0.130
 Hots+0.121
 Subtle+0.120
Neg logit contributions
obar-0.172
rane-0.165
minist-0.153
oba-0.149
ega-0.149
Token Kills
Token ID23478
Feature activation-3.34e-01

Pos logit contributions
 Lauder+0.819
 Loving+0.735
 Sioux+0.726
 Hots+0.674
 Subtle+0.660
Neg logit contributions
obar-1.040
rane-1.010
minist-0.927
oba-0.916
ega-0.906
Token,
Token ID11
Feature activation+3.20e-02

Pos logit contributions
 Lauder+0.546
 Loving+0.489
 Sioux+0.485
 Hots+0.450
 Subtle+0.442
Neg logit contributions
obar-0.634
rane-0.615
minist-0.562
oba-0.556
ega-0.548
Token Will
Token ID2561
Feature activation+4.52e-04

Pos logit contributions
obar+0.061
rane+0.059
minist+0.054
oba+0.053
ega+0.053
Neg logit contributions
 Lauder-0.051
 Loving-0.046
 Sioux-0.045
 Hots-0.042
 Subtle-0.041
Tokeny
Token ID88
Feature activation+8.92e-02

Pos logit contributions
obar+0.001
rane+0.001
minist+0.001
oba+0.001
ega+0.001
Neg logit contributions
 Lauder-0.001
 Loving-0.001
 Sioux-0.001
 Hots-0.001
 Subtle-0.001
Token Moon
Token ID6869
Feature activation+2.08e-01

Pos logit contributions
obar+0.176
rane+0.171
minist+0.157
oba+0.155
ega+0.153
Neg logit contributions
 Lauder-0.136
 Loving-0.121
 Sioux-0.120
 Hots-0.111
 Subtle-0.110
Token sacked
Token ID32564
Feature activation+1.63e+00

Pos logit contributions
obar+0.400
rane+0.388
minist+0.358
oba+0.349
ega+0.348
Neg logit contributions
 Lauder-0.331
 Loving-0.297
 Sioux-0.293
 Hots-0.272
 Subtle-0.268
Token
Token ID198
Feature activation-1.84e-01

Pos logit contributions
obar+2.923
rane+2.843
minist+2.619
ega+2.555
oba+2.540
Neg logit contributions
 Lauder-2.699
 Loving-2.431
 Sioux-2.413
 Hots-2.255
 Subtle-2.208
Token
Token ID198
Feature activation-1.69e-01

Pos logit contributions
 Lauder+0.316
 Loving+0.280
 Sioux+0.279
 Hots+0.258
 Subtle+0.256
Neg logit contributions
obar-0.335
rane-0.324
minist-0.298
oba-0.292
ega-0.287
Token*
Token ID9
Feature activation-9.89e-02

Pos logit contributions
 Lauder+0.236
 Loving+0.210
 Sioux+0.206
 Hots+0.189
 Subtle+0.185
Neg logit contributions
obar-0.358
rane-0.348
minist-0.324
oba-0.318
ega-0.314
Token Low
Token ID7754
Feature activation-6.97e-01

Pos logit contributions
 Lauder+0.160
 Loving+0.143
 Sioux+0.142
 Hots+0.132
 Sikh+0.129
Neg logit contributions
obar-0.186
rane-0.180
minist-0.166
oba-0.163
ega-0.161
Token ratings
Token ID10109
Feature activation+4.99e-01

Pos logit contributions
 Lauder+1.176
 Loving+1.065
 Sioux+1.049
 Hots+0.979
 Subtle+0.960
Neg logit contributions
obar-1.281
rane-1.241
minist-1.141
oba-1.118
ega-1.101
Token exact
Token ID2748
Feature activation+8.62e-01

Pos logit contributions
obar+0.560
rane+0.548
minist+0.504
oba+0.489
ega+0.480
Neg logit contributions
 Lauder-0.488
 Loving-0.438
 Sioux-0.428
 Hots-0.397
 Subtle-0.397
Token mechanism
Token ID9030
Feature activation+5.26e-01

Pos logit contributions
obar+1.580
rane+1.555
minist+1.421
oba+1.375
ega+1.357
Neg logit contributions
 Lauder-1.430
 Loving-1.281
 Sioux-1.248
 Subtle-1.172
 Hots-1.160
Token that
Token ID326
Feature activation+3.07e-01

Pos logit contributions
obar+0.972
rane+0.954
minist+0.867
oba+0.847
ega+0.833
Neg logit contributions
 Lauder-0.869
 Loving-0.776
 Sioux-0.768
 Hots-0.714
 Subtle-0.708
Token triggered
Token ID13973
Feature activation+1.46e-02

Pos logit contributions
obar+0.601
rane+0.589
minist+0.538
oba+0.525
ega+0.522
Neg logit contributions
 Lauder-0.476
 Loving-0.427
 Sioux-0.414
 Subtle-0.382
 Hots-0.381
Token the
Token ID262
Feature activation+1.93e-01

Pos logit contributions
obar+0.028
rane+0.027
minist+0.025
oba+0.025
ega+0.024
Neg logit contributions
 Lauder-0.023
 Loving-0.021
 Sioux-0.021
 Hots-0.019
 Subtle-0.019
Token stream
Token ID4269
Feature activation+1.62e+00

Pos logit contributions
obar+0.348
rane+0.340
minist+0.311
oba+0.303
ega+0.297
Neg logit contributions
 Lauder-0.331
 Loving-0.298
 Sioux-0.293
 Hots-0.274
 Subtle-0.270
Token of
Token ID286
Feature activation+1.78e-01

Pos logit contributions
obar+3.358
rane+3.244
minist+3.034
oba+2.959
ega+2.920
Neg logit contributions
 Lauder-2.340
 Loving-2.092
 Sioux-2.036
 Hots-1.903
 Subtle-1.848
Token incorrect
Token ID11491
Feature activation-3.17e-01

Pos logit contributions
obar+0.305
rane+0.294
minist+0.269
oba+0.261
ega+0.257
Neg logit contributions
 Lauder-0.323
 Loving-0.292
 Sioux-0.287
 Hots-0.270
 Subtle-0.267
Token data
Token ID1366
Feature activation+3.77e-01

Pos logit contributions
 Lauder+0.583
 Loving+0.531
 Sioux+0.524
 Hots+0.492
 Subtle+0.486
Neg logit contributions
obar-0.535
rane-0.517
minist-0.469
oba-0.459
ega-0.450
Token.
Token ID13
Feature activation+6.73e-02

Pos logit contributions
obar+0.682
rane+0.660
minist+0.611
oba+0.593
ega+0.585
Neg logit contributions
 Lauder-0.644
 Loving-0.583
 Sioux-0.574
 Hots-0.536
 Subtle-0.531
Token They
Token ID1119
Feature activation+2.48e-01

Pos logit contributions
obar+0.128
rane+0.124
minist+0.114
oba+0.113
ega+0.110
Neg logit contributions
 Lauder-0.107
 Loving-0.096
 Sioux-0.095
 Hots-0.088
 Sikh-0.086
Tokenijk
Token ID45961
Feature activation-4.70e-02

Pos logit contributions
 Lauder+0.220
 Loving+0.201
 Sioux+0.196
 Hots+0.184
 Subtle+0.183
Neg logit contributions
obar-0.217
rane-0.210
minist-0.191
oba-0.189
ega-0.186
Token a
Token ID257
Feature activation+1.90e-01

Pos logit contributions
 Lauder+0.073
 Loving+0.065
 Sioux+0.064
 Sikh+0.058
 Hots+0.058
Neg logit contributions
obar-0.094
rane-0.090
minist-0.083
oba-0.082
ega-0.082
Tokenan
Token ID272
Feature activation+5.99e-01

Pos logit contributions
obar+0.305
rane+0.293
minist+0.264
oba+0.260
ega+0.257
Neg logit contributions
 Lauder-0.367
 Loving-0.336
 Sioux-0.331
 Hots-0.312
 Sikh-0.308
Token Z
Token ID1168
Feature activation-3.36e-01

Pos logit contributions
obar+0.892
rane+0.850
oba+0.747
ega+0.746
minist+0.740
Neg logit contributions
 Lauder-1.212
 Loving-1.122
 Sioux-1.119
 Sikh-1.041
 Hots-1.036
Tokenee
Token ID1453
Feature activation+1.47e-01

Pos logit contributions
 Lauder+0.515
 Loving+0.464
 Sioux+0.455
 Sikh+0.419
 Hots+0.417
Neg logit contributions
obar-0.686
rane-0.665
minist-0.614
oba-0.612
ega-0.603
Token"]
Token ID8973
Feature activation+1.62e+00

Pos logit contributions
obar+0.268
rane+0.260
minist+0.236
oba+0.235
ega+0.231
Neg logit contributions
 Lauder-0.245
 Loving-0.224
 Sioux-0.223
 Hots-0.206
 Sikh-0.204
Token [
Token ID685
Feature activation+1.39e-01

Pos logit contributions
rane+2.328
obar+2.323
ega+2.059
minist+2.045
oba+2.035
Neg logit contributions
 Lauder-3.339
 Sioux-2.842
 Loving-2.792
etooth-2.713
cks-2.612
TokenDate
Token ID10430
Feature activation-2.07e-01

Pos logit contributions
obar+0.209
rane+0.203
minist+0.185
oba+0.180
ega+0.175
Neg logit contributions
 Lauder-0.276
 Loving-0.255
 Sioux-0.253
 Hots-0.236
 Subtle-0.235
Token "
Token ID366
Feature activation-7.43e-02

Pos logit contributions
 Lauder+0.229
 Loving+0.191
 Sioux+0.191
 Sikh+0.164
 Subtle+0.163
Neg logit contributions
obar-0.495
rane-0.487
oba-0.453
minist-0.450
ega-0.446
Token2016
Token ID5304
Feature activation-5.40e-01

Pos logit contributions
 Lauder+0.137
 Loving+0.126
 Sioux+0.125
 Hots+0.116
 Sikh+0.115
Neg logit contributions
obar-0.124
rane-0.119
minist-0.109
oba-0.107
ega-0.105
Token.
Token ID13
Feature activation-3.84e-02

Pos logit contributions
 Lauder+0.949
 Loving+0.848
 Sioux+0.839
 Hots+0.781
 Subtle+0.774
Neg logit contributions
obar-0.954
rane-0.926
minist-0.847
oba-0.836
ega-0.821
Token Big
Token ID4403
Feature activation+4.42e-02

Pos logit contributions
obar+0.139
rane+0.135
minist+0.124
oba+0.123
ega+0.120
Neg logit contributions
 Lauder-0.108
 Loving-0.096
 Sioux-0.095
 Hots-0.088
 Sikh-0.086
Token Bang
Token ID9801
Feature activation+6.54e-01

Pos logit contributions
obar+0.062
rane+0.058
minist+0.053
oba+0.051
ega+0.050
Neg logit contributions
 Lauder-0.094
 Loving-0.088
 Sioux-0.087
 Hots-0.083
 Subtle-0.081
Token Theory
Token ID17003
Feature activation+1.31e-02

Pos logit contributions
obar+1.369
rane+1.343
minist+1.239
oba+1.236
ega+1.216
Neg logit contributions
 Lauder-0.912
 Loving-0.775
 Sioux-0.743
 Hots-0.717
 Subtle-0.695
Token CBS
Token ID11133
Feature activation-1.27e-01

Pos logit contributions
obar+0.025
rane+0.024
minist+0.022
oba+0.022
ega+0.022
Neg logit contributions
 Lauder-0.021
 Loving-0.018
 Sioux-0.018
 Hots-0.017
 Subtle-0.016
Token Amy
Token ID14235
Feature activation-1.02e-01

Pos logit contributions
 Lauder+0.207
 Loving+0.185
 Sioux+0.182
 Hots+0.171
 Subtle+0.168
Neg logit contributions
obar-0.238
rane-0.231
minist-0.212
oba-0.208
ega-0.206
Token Poe
Token ID34815
Feature activation+1.60e+00

Pos logit contributions
 Lauder+0.219
 Loving+0.201
 Sioux+0.199
 Hots+0.189
 Subtle+0.187
Neg logit contributions
obar-0.138
rane-0.133
minist-0.116
oba-0.114
ega-0.113
Tokenhler
Token ID49737
Feature activation+4.89e-01

Pos logit contributions
obar+2.477
rane+2.363
minist+2.098
oba+2.046
ega+2.040
Neg logit contributions
 Lauder-3.159
 Loving-2.907
 Sioux-2.876
 Hots-2.713
 Subtle-2.684
Token Parks
Token ID20604
Feature activation+3.78e-01

Pos logit contributions
obar+0.932
rane+0.908
minist+0.834
oba+0.817
ega+0.815
Neg logit contributions
 Lauder-0.760
 Loving-0.661
 Sioux-0.650
 Hots-0.615
 Subtle-0.602
Token and
Token ID290
Feature activation-1.43e-01

Pos logit contributions
obar+0.711
rane+0.694
minist+0.637
oba+0.624
ega+0.617
Neg logit contributions
 Lauder-0.619
 Loving-0.547
 Sioux-0.544
 Hots-0.506
 Subtle-0.493
Token Recreation
Token ID34285
Feature activation-1.85e-01

Pos logit contributions
 Lauder+0.199
 Loving+0.173
 Sioux+0.171
 Hots+0.157
 Sikh+0.153
Neg logit contributions
obar-0.306
rane-0.298
minist-0.277
oba-0.271
ega-0.268
Token NBC
Token ID9716
Feature activation-2.63e-01

Pos logit contributions
 Lauder+0.286
 Loving+0.253
 Sioux+0.248
 Hots+0.232
 Subtle+0.228
Neg logit contributions
obar-0.359
rane-0.349
minist-0.323
oba-0.316
ega-0.314
Token"]
Token ID8973
Feature activation+1.75e+00

Pos logit contributions
obar+0.012
rane+0.012
minist+0.010
oba+0.010
ega+0.010
Neg logit contributions
 Lauder-0.025
 Loving-0.023
 Sioux-0.023
 Subtle-0.022
 Sikh-0.022
Token [
Token ID685
Feature activation+2.04e-01

Pos logit contributions
obar+2.562
rane+2.546
ega+2.291
oba+2.229
minist+2.200
Neg logit contributions
 Lauder-3.489
 Sioux-3.036
 Loving-3.016
etooth-2.928
 Sikh-2.804
TokenRound
Token ID22685
Feature activation-3.53e-01

Pos logit contributions
obar+0.263
rane+0.250
minist+0.222
oba+0.217
ega+0.215
Neg logit contributions
 Lauder-0.452
 Loving-0.419
 Sioux-0.415
 Hots-0.392
 Subtle-0.391
Token "
Token ID366
Feature activation+3.19e-03

Pos logit contributions
 Lauder+0.407
 Loving+0.352
 Sioux+0.351
 Subtle+0.311
 Sikh+0.301
Neg logit contributions
obar-0.826
rane-0.806
oba-0.749
minist-0.748
ega-0.741
Token11
Token ID1157
Feature activation-2.77e-01

Pos logit contributions
obar+0.006
rane+0.006
minist+0.005
oba+0.005
ega+0.005
Neg logit contributions
 Lauder-0.005
 Loving-0.005
 Sioux-0.005
 Hots-0.005
 Subtle-0.005
Token"]
Token ID8973
Feature activation+1.59e+00

Pos logit contributions
 Lauder+0.529
 Loving+0.485
 Sioux+0.479
 Hots+0.451
 Subtle+0.444
Neg logit contributions
obar-0.447
rane-0.430
minist-0.391
oba-0.383
ega-0.377
Token [
Token ID685
Feature activation+1.78e-01

Pos logit contributions
obar+2.418
rane+2.342
ega+2.095
oba+2.058
minist+2.057
Neg logit contributions
 Lauder-3.103
 Sioux-2.728
 Loving-2.715
 Hots-2.554
 Sikh-2.524
TokenWhite
Token ID12256
Feature activation-2.10e-01

Pos logit contributions
obar+0.326
rane+0.315
minist+0.291
oba+0.284
ega+0.279
Neg logit contributions
 Lauder-0.301
 Loving-0.273
 Sioux-0.269
 Hots-0.251
 Subtle-0.247
Token "
Token ID366
Feature activation+6.13e-03

Pos logit contributions
 Lauder+0.238
 Loving+0.205
 Sioux+0.198
 Subtle+0.185
 Sikh+0.180
Neg logit contributions
obar-0.504
rane-0.479
oba-0.456
ega-0.447
minist-0.444
TokenAb
Token ID4826
Feature activation+1.05e-01

Pos logit contributions
obar+0.011
rane+0.010
minist+0.010
oba+0.009
ega+0.009
Neg logit contributions
 Lauder-0.011
 Loving-0.010
 Sioux-0.010
 Hots-0.009
 Subtle-0.009
Tokenas
Token ID292
Feature activation+3.57e-01

Pos logit contributions
obar+0.172
rane+0.165
minist+0.149
oba+0.147
ega+0.145
Neg logit contributions
 Lauder-0.201
 Loving-0.183
 Sioux-0.182
 Hots-0.171
 Sikh-0.168
Token
Token ID198
Feature activation-8.41e-02

Pos logit contributions
 Lauder+0.187
 Loving+0.165
 Sioux+0.165
 Hots+0.153
 Subtle+0.152
Neg logit contributions
obar-0.194
rane-0.187
minist-0.172
oba-0.169
ega-0.166
Token24
Token ID1731
Feature activation-1.70e-01

Pos logit contributions
 Lauder+0.147
 Loving+0.133
 Sioux+0.132
 Hots+0.123
 Subtle+0.121
Neg logit contributions
obar-0.149
rane-0.144
minist-0.132
oba-0.129
ega-0.127
Token11
Token ID1157
Feature activation-9.59e-02

Pos logit contributions
 Lauder+0.299
 Loving+0.272
 Sioux+0.267
 Hots+0.252
 Subtle+0.247
Neg logit contributions
obar-0.295
rane-0.284
minist-0.259
oba-0.253
ega-0.252
Token S
Token ID311
Feature activation-3.38e-01

Pos logit contributions
 Lauder+0.144
 Loving+0.129
 Sioux+0.127
 Hots+0.118
 Subtle+0.116
Neg logit contributions
obar-0.189
rane-0.184
minist-0.170
oba-0.167
ega-0.166
Token.
Token ID13
Feature activation-1.79e-01

Pos logit contributions
 Lauder+0.564
 Loving+0.513
 Sioux+0.504
 Hots+0.477
 Subtle+0.467
Neg logit contributions
obar-0.626
rane-0.602
minist-0.556
oba-0.549
ega-0.535
Token Shepherd
Token ID30890
Feature activation+1.58e+00

Pos logit contributions
 Lauder+0.274
 Loving+0.245
 Sioux+0.241
 Hots+0.225
 Subtle+0.221
Neg logit contributions
obar-0.353
rane-0.342
minist-0.316
oba-0.311
ega-0.307
Token Today
Token ID6288
Feature activation+3.26e-01

Pos logit contributions
obar+2.782
rane+2.652
minist+2.448
oba+2.444
ega+2.412
Neg logit contributions
 Lauder-2.789
 Loving-2.440
 Sioux-2.426
 Subtle-2.286
 Hots-2.283
Token:
Token ID25
Feature activation-2.42e-01

Pos logit contributions
obar+0.586
rane+0.564
minist+0.515
oba+0.511
ega+0.505
Neg logit contributions
 Lauder-0.556
 Loving-0.487
 Sioux-0.486
 Hots-0.452
 Subtle-0.446
Token Tor
Token ID4022
Feature activation+3.32e-01

Pos logit contributions
 Lauder+0.376
 Loving+0.335
 Sioux+0.329
 Hots+0.307
 Subtle+0.301
Neg logit contributions
obar-0.470
rane-0.456
minist-0.419
oba-0.415
ega-0.409
Tokenchy
Token ID29658
Feature activation-5.56e-01

Pos logit contributions
obar+0.546
rane+0.528
minist+0.478
oba+0.470
ega+0.459
Neg logit contributions
 Lauder-0.625
 Loving-0.573
 Sioux-0.569
 Hots-0.535
 Subtle-0.527
Token's
Token ID338
Feature activation-1.07e-01

Pos logit contributions
 Lauder+0.890
 Loving+0.799
 Sioux+0.788
 Hots+0.731
 Subtle+0.719
Neg logit contributions
obar-1.071
rane-1.037
minist-0.956
oba-0.941
ega-0.925
Token,
Token ID11
Feature activation-5.18e-02

Pos logit contributions
 Lauder+0.793
 Loving+0.712
 Sioux+0.706
 Hots+0.656
 Subtle+0.646
Neg logit contributions
obar-0.909
rane-0.875
minist-0.810
oba-0.796
ega-0.780
Token<|endoftext|>
Token ID50256
Feature activation-1.62e-01

Pos logit contributions
 Lauder+0.094
 Loving+0.085
 Sioux+0.084
 Hots+0.079
 Subtle+0.078
Neg logit contributions
obar-0.088
rane-0.084
minist-0.077
oba-0.075
ega-0.074
TokenThe
Token ID464
Feature activation-2.70e-01

Pos logit contributions
 Lauder+0.309
 Loving+0.282
 Sioux+0.279
 Hots+0.263
 Subtle+0.258
Neg logit contributions
obar-0.265
rane-0.254
minist-0.232
oba-0.226
ega-0.222
Token urge
Token ID14960
Feature activation+4.77e-02

Pos logit contributions
 Lauder+0.433
 Loving+0.390
 Sioux+0.383
 Hots+0.357
 Subtle+0.349
Neg logit contributions
obar-0.515
rane-0.499
minist-0.461
oba-0.453
ega-0.445
Token to
Token ID284
Feature activation-2.93e-01

Pos logit contributions
obar+0.093
rane+0.090
minist+0.084
oba+0.082
ega+0.081
Neg logit contributions
 Lauder-0.074
 Loving-0.067
 Sioux-0.066
 Hots-0.061
 Subtle-0.060
Token binge
Token ID34735
Feature activation+1.56e+00

Pos logit contributions
 Lauder+0.534
 Loving+0.485
 Sioux+0.477
 Hots+0.448
 Subtle+0.441
Neg logit contributions
obar-0.500
rane-0.483
minist-0.440
oba-0.432
ega-0.424
Token on
Token ID319
Feature activation-1.12e-01

Pos logit contributions
obar+2.756
rane+2.688
minist+2.460
ega+2.420
oba+2.417
Neg logit contributions
 Lauder-2.686
 Loving-2.412
 Sioux-2.349
 Hots-2.210
 Subtle-2.197
Token streaming
Token ID11305
Feature activation+9.78e-01

Pos logit contributions
 Lauder+0.185
 Loving+0.167
 Sioux+0.163
 Hots+0.153
 Subtle+0.151
Neg logit contributions
obar-0.208
rane-0.202
minist-0.185
oba-0.182
ega-0.180
Token Netflix
Token ID12074
Feature activation+1.05e-01

Pos logit contributions
obar+1.654
rane+1.582
minist+1.439
ega+1.408
oba+1.406
Neg logit contributions
 Lauder-1.767
 Loving-1.614
 Sioux-1.557
 Subtle-1.451
 Hots-1.441
Token television
Token ID5581
Feature activation+6.63e-01

Pos logit contributions
obar+0.196
rane+0.190
minist+0.175
oba+0.171
ega+0.170
Neg logit contributions
 Lauder-0.173
 Loving-0.156
 Sioux-0.152
 Sikh-0.140
 Subtle-0.139
Token and
Token ID290
Feature activation-2.47e-01

Pos logit contributions
obar+1.203
rane+1.178
minist+1.085
ega+1.049
oba+1.045
Neg logit contributions
 Lauder-1.108
 Loving-1.004
 Sioux-0.977
 Subtle-0.897
 Sikh-0.895
Token [
Token ID685
Feature activation-3.34e-01

Pos logit contributions
obar+0.838
rane+0.813
minist+0.742
ega+0.732
oba+0.728
Neg logit contributions
 Lauder-0.731
 Loving-0.650
 Sioux-0.642
 Hots-0.596
 Subtle-0.590
Tokenwho
Token ID8727
Feature activation+7.27e-01

Pos logit contributions
 Lauder+0.613
 Loving+0.558
 Sioux+0.551
 Hots+0.518
 Subtle+0.510
Neg logit contributions
obar-0.565
rane-0.545
minist-0.500
oba-0.486
ega-0.477
Token plays
Token ID5341
Feature activation+2.61e-02

Pos logit contributions
obar+1.356
rane+1.312
minist+1.203
oba+1.180
ega+1.171
Neg logit contributions
 Lauder-1.207
 Loving-1.068
 Sioux-1.051
 Hots-0.980
 Subtle-0.973
Token Mr
Token ID1770
Feature activation-4.09e-01

Pos logit contributions
obar+0.050
rane+0.048
minist+0.044
oba+0.044
ega+0.043
Neg logit contributions
 Lauder-0.042
 Loving-0.037
 Sioux-0.037
 Hots-0.034
 Sikh-0.034
Token.
Token ID13
Feature activation-2.62e-01

Pos logit contributions
 Lauder+0.665
 Loving+0.601
 Sioux+0.593
 Hots+0.552
 Subtle+0.541
Neg logit contributions
obar-0.778
rane-0.751
minist-0.695
oba-0.678
ega-0.671
Token Poe
Token ID34815
Feature activation+1.54e+00

Pos logit contributions
 Lauder+0.409
 Loving+0.366
 Sioux+0.362
 Hots+0.336
 Sikh+0.330
Neg logit contributions
obar-0.506
rane-0.490
minist-0.452
oba-0.445
ega-0.437
Token]
Token ID60
Feature activation+2.50e-01

Pos logit contributions
obar+2.812
rane+2.636
minist+2.442
oba+2.410
ega+2.389
Neg logit contributions
 Lauder-2.577
 Loving-2.329
 Sioux-2.304
 Subtle-2.142
 Hots-2.123
Token sings
Token ID33041
Feature activation-4.78e-01

Pos logit contributions
obar+0.471
rane+0.456
minist+0.417
oba+0.408
ega+0.407
Neg logit contributions
 Lauder-0.410
 Loving-0.366
 Sioux-0.360
 Hots-0.335
 Subtle-0.332
Token really
Token ID1107
Feature activation-5.26e-01

Pos logit contributions
 Lauder+0.771
 Loving+0.690
 Sioux+0.673
 Hots+0.628
 Sikh+0.618
Neg logit contributions
obar-0.913
rane-0.882
minist-0.816
oba-0.799
ega-0.790
Token well
Token ID880
Feature activation-9.17e-03

Pos logit contributions
 Lauder+0.852
 Loving+0.763
 Sioux+0.740
 Hots+0.692
 Subtle+0.678
Neg logit contributions
obar-1.002
rane-0.964
minist-0.897
oba-0.873
ega-0.868
Token.
Token ID13
Feature activation-8.60e-02

Pos logit contributions
 Lauder+0.015
 Loving+0.014
 Sioux+0.014
 Hots+0.013
 Subtle+0.013
Neg logit contributions
obar-0.017
rane-0.016
minist-0.015
oba-0.015
ega-0.015
Token on
Token ID319
Feature activation+5.83e-02

Pos logit contributions
obar+2.204
rane+2.084
minist+1.956
ega+1.872
oba+1.871
Neg logit contributions
 Lauder-1.899
 Sioux-1.715
 Loving-1.711
 Hots-1.559
 Subtle-1.554
Token driving
Token ID5059
Feature activation+1.28e-02

Pos logit contributions
obar+0.102
rane+0.099
minist+0.091
oba+0.088
ega+0.087
Neg logit contributions
 Lauder-0.104
 Loving-0.094
 Sioux-0.092
 Hots-0.087
 Subtle-0.085
Token related
Token ID3519
Feature activation-3.20e-01

Pos logit contributions
obar+0.023
rane+0.022
minist+0.020
oba+0.020
ega+0.020
Neg logit contributions
 Lauder-0.022
 Loving-0.020
 Sioux-0.020
 Hots-0.019
 Subtle-0.018
Token skills
Token ID4678
Feature activation+1.10e-01

Pos logit contributions
 Lauder+0.604
 Loving+0.550
 Sioux+0.540
 Hots+0.511
 Subtle+0.501
Neg logit contributions
obar-0.526
rane-0.511
minist-0.466
oba-0.451
ega-0.444
Token.
Token ID13
Feature activation-1.13e-01

Pos logit contributions
obar+0.202
rane+0.197
minist+0.180
oba+0.177
ega+0.173
Neg logit contributions
 Lauder-0.186
 Loving-0.167
 Sioux-0.165
 Hots-0.153
 Subtle-0.151
Token Springfield
Token ID27874
Feature activation+1.54e+00

Pos logit contributions
 Lauder+0.175
 Loving+0.155
 Sioux+0.153
 Hots+0.142
 Sikh+0.138
Neg logit contributions
obar-0.219
rane-0.215
minist-0.196
oba-0.192
ega-0.189
Token,
Token ID11
Feature activation-7.45e-03

Pos logit contributions
obar+2.841
rane+2.757
minist+2.519
oba+2.478
ega+2.455
Neg logit contributions
 Lauder-2.548
 Loving-2.293
 Sioux-2.239
 Hots-2.105
 Subtle-2.062
Token VA
Token ID13753
Feature activation+6.73e-01

Pos logit contributions
 Lauder+0.010
 Loving+0.009
 Sioux+0.009
 Hots+0.008
 Subtle+0.008
Neg logit contributions
obar-0.016
rane-0.015
minist-0.014
oba-0.014
ega-0.014
Token:
Token ID25
Feature activation-2.68e-01

Pos logit contributions
obar+1.197
rane+1.156
minist+1.060
oba+1.038
ega+1.025
Neg logit contributions
 Lauder-1.155
 Loving-1.041
 Sioux-1.020
 Hots-0.949
 Subtle-0.937
Token US
Token ID1294
Feature activation+1.17e-01

Pos logit contributions
 Lauder+0.361
 Loving+0.317
 Sioux+0.312
 Hots+0.286
 Subtle+0.278
Neg logit contributions
obar-0.575
rane-0.563
minist-0.522
oba-0.512
ega-0.506
Token Department
Token ID2732
Feature activation+3.51e-01

Pos logit contributions
obar+0.202
rane+0.197
minist+0.181
oba+0.175
ega+0.172
Neg logit contributions
 Lauder-0.210
 Loving-0.189
 Sioux-0.187
 Hots-0.176
 Subtle-0.173
Tokenov
Token ID709
Feature activation-9.47e-02

Pos logit contributions
obar+0.618
rane+0.590
oba+0.534
minist+0.531
ega+0.519
Neg logit contributions
 Lauder-0.640
 Loving-0.586
 Sioux-0.582
 Hots-0.550
 Subtle-0.540
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
 Lauder+0.162
 Loving+0.146
 Sioux+0.145
 Hots+0.135
 Subtle+0.134
Neg logit contributions
obar-0.172
rane-0.166
minist-0.152
oba-0.151
ega-0.149
Token N
Token ID399
Feature activation-6.74e-01

Pos logit contributions
obar+0.460
rane+0.440
minist+0.404
oba+0.402
ega+0.399
Neg logit contributions
 Lauder-0.381
 Loving-0.342
 Sioux-0.339
 Hots-0.310
 Subtle-0.309
Tokenij
Token ID2926
Feature activation+7.29e-02

Pos logit contributions
 Lauder+1.243
 Loving+1.135
 Sioux+1.126
 Hots+1.051
 Subtle+1.040
Neg logit contributions
obar-1.139
rane-1.101
minist-0.998
oba-0.986
ega-0.967
Tokenat
Token ID265
Feature activation+3.50e-02

Pos logit contributions
obar+0.128
rane+0.123
oba+0.111
minist+0.111
ega+0.109
Neg logit contributions
 Lauder-0.133
 Loving-0.120
 Sioux-0.119
 Subtle-0.112
 Hots-0.111
Token"]
Token ID8973
Feature activation+1.53e+00

Pos logit contributions
obar+0.052
rane+0.050
oba+0.045
minist+0.044
ega+0.044
Neg logit contributions
 Lauder-0.071
 Sioux-0.065
 Loving-0.065
 Hots-0.061
 Subtle-0.061
Token [
Token ID685
Feature activation+1.80e-01

Pos logit contributions
obar+2.391
rane+2.323
oba+2.085
ega+2.044
minist+2.036
Neg logit contributions
 Lauder-2.878
 Sioux-2.564
 Loving-2.537
 Hots-2.388
 Subtle-2.355
TokenBlack
Token ID9915
Feature activation-9.76e-01

Pos logit contributions
obar+0.367
rane+0.355
minist+0.326
oba+0.325
ega+0.318
Neg logit contributions
 Lauder-0.265
 Loving-0.240
 Sioux-0.236
 Hots-0.216
 Subtle-0.213
Token "
Token ID366
Feature activation-1.74e-02

Pos logit contributions
 Lauder+1.037
 Loving+0.857
 Sioux+0.842
 Hots+0.716
 Sikh+0.715
Neg logit contributions
obar-2.422
rane-2.356
minist-2.202
oba-2.191
ega-2.164
TokenAnt
Token ID13217
Feature activation-1.56e-01

Pos logit contributions
 Lauder+0.031
 Loving+0.028
 Sioux+0.028
 Hots+0.026
 Subtle+0.026
Neg logit contributions
obar-0.030
rane-0.029
minist-0.027
oba-0.026
ega-0.026
Tokenip
Token ID541
Feature activation-6.24e-01

Pos logit contributions
 Lauder+0.281
 Loving+0.256
 Sioux+0.254
 Hots+0.237
 Subtle+0.235
Neg logit contributions
obar-0.271
rane-0.264
minist-0.237
oba-0.236
ega-0.233
Token create
Token ID2251
Feature activation-2.22e-01

Pos logit contributions
 Lauder+0.809
 Loving+0.736
 Sioux+0.726
 Hots+0.677
 Subtle+0.668
Neg logit contributions
obar-0.784
rane-0.755
minist-0.692
oba-0.677
ega-0.664
Token an
Token ID281
Feature activation-2.25e-01

Pos logit contributions
 Lauder+0.371
 Loving+0.335
 Sioux+0.333
 Hots+0.305
 Sikh+0.301
Neg logit contributions
obar-0.410
rane-0.394
minist-0.365
oba-0.354
ega-0.350
Token initialization
Token ID37588
Feature activation+4.21e-01

Pos logit contributions
 Lauder+0.368
 Loving+0.331
 Sioux+0.330
 Hots+0.298
 Sikh+0.298
Neg logit contributions
obar-0.431
rane-0.411
minist-0.377
oba-0.367
ega-0.365
Token file
Token ID2393
Feature activation-1.77e-01

Pos logit contributions
obar+0.623
rane+0.588
minist+0.531
oba+0.514
ega+0.505
Neg logit contributions
 Lauder-0.858
 Loving-0.796
 Sioux-0.786
 Hots-0.738
 Subtle-0.730
Token with
Token ID351
Feature activation+7.28e-02

Pos logit contributions
 Lauder+0.285
 Loving+0.257
 Sioux+0.255
 Hots+0.235
 Sikh+0.232
Neg logit contributions
obar-0.338
rane-0.325
minist-0.302
oba-0.295
ega-0.289
Token |
Token ID930
Feature activation+1.52e+00

Pos logit contributions
obar+0.137
rane+0.131
minist+0.122
oba+0.119
ega+0.117
Neg logit contributions
 Lauder-0.120
 Loving-0.108
 Sioux-0.107
 Hots-0.099
 Sikh-0.098
Token:
Token ID25
Feature activation-8.47e-02

Pos logit contributions
obar+2.709
rane+2.584
minist+2.387
oba+2.316
ega+2.277
Neg logit contributions
 Lauder-2.665
 Loving-2.403
 Sioux-2.398
 Hots-2.209
 Sikh-2.192
Tokenmk
Token ID28015
Feature activation-5.92e-01

Pos logit contributions
 Lauder+0.161
 Loving+0.148
 Sioux+0.146
 Hots+0.137
 Subtle+0.135
Neg logit contributions
obar-0.137
rane-0.132
minist-0.120
oba-0.117
ega-0.115
Tokenvim
Token ID31124
Feature activation-5.78e-01

Pos logit contributions
 Lauder+1.235
 Loving+1.142
 Sioux+1.129
 Hots+1.070
 Subtle+1.054
Neg logit contributions
obar-0.848
rane-0.813
minist-0.729
oba-0.708
ega-0.693
Tokenrc
Token ID6015
Feature activation-3.51e-01

Pos logit contributions
 Lauder+1.018
 Loving+0.928
 Sioux+0.916
 Hots+0.858
 Subtle+0.842
Neg logit contributions
obar-1.015
rane-0.981
minist-0.899
oba-0.879
ega-0.864
Token|
Token ID91
Feature activation+7.93e-01

Pos logit contributions
 Lauder+0.614
 Loving+0.558
 Sioux+0.552
 Hots+0.516
 Subtle+0.506
Neg logit contributions
obar-0.624
rane-0.602
minist-0.554
oba-0.541
ega-0.531
Token able
Token ID1498
Feature activation+3.57e-02

Pos logit contributions
 Lauder+0.101
 Loving+0.091
 Sioux+0.089
 Hots+0.083
 Subtle+0.082
Neg logit contributions
obar-0.135
rane-0.131
minist-0.122
oba-0.119
ega-0.117
Token to
Token ID284
Feature activation-3.55e-02

Pos logit contributions
obar+0.067
rane+0.065
minist+0.060
oba+0.059
ega+0.058
Neg logit contributions
 Lauder-0.059
 Loving-0.053
 Sioux-0.052
 Hots-0.048
 Subtle-0.048
Token direct
Token ID1277
Feature activation+2.83e-01

Pos logit contributions
 Lauder+0.068
 Loving+0.062
 Sioux+0.061
 Hots+0.057
 Subtle+0.057
Neg logit contributions
obar-0.058
rane-0.056
minist-0.051
oba-0.050
ega-0.049
Token more
Token ID517
Feature activation+9.09e-02

Pos logit contributions
obar+0.499
rane+0.481
minist+0.445
oba+0.436
ega+0.427
Neg logit contributions
 Lauder-0.493
 Loving-0.448
 Sioux-0.442
 Hots-0.412
 Subtle-0.410
Token light
Token ID1657
Feature activation-2.00e-01

Pos logit contributions
obar+0.174
rane+0.170
minist+0.157
oba+0.153
ega+0.150
Neg logit contributions
 Lauder-0.146
 Loving-0.131
 Sioux-0.129
 Hots-0.120
 Subtle-0.118
Token reflected
Token ID12548
Feature activation+1.52e+00

Pos logit contributions
 Lauder+0.339
 Loving+0.308
 Sioux+0.304
 Hots+0.282
 Subtle+0.279
Neg logit contributions
obar-0.367
rane-0.354
minist-0.328
oba-0.319
ega-0.316
Token by
Token ID416
Feature activation+7.07e-02

Pos logit contributions
obar+2.714
rane+2.606
minist+2.464
oba+2.367
ega+2.338
Neg logit contributions
 Lauder-2.566
 Loving-2.358
 Sioux-2.298
 Subtle-2.179
 Hots-2.148
Token the
Token ID262
Feature activation+7.56e-03

Pos logit contributions
obar+0.129
rane+0.125
minist+0.115
oba+0.113
ega+0.111
Neg logit contributions
 Lauder-0.118
 Loving-0.108
 Sioux-0.106
 Hots-0.099
 Subtle-0.098
Token scaff
Token ID41498
Feature activation-8.36e-01

Pos logit contributions
obar+0.013
rane+0.012
minist+0.011
oba+0.011
ega+0.011
Neg logit contributions
 Lauder-0.013
 Loving-0.013
 Sioux-0.012
 Hots-0.011
 Subtle-0.011
Tokenold
Token ID727
Feature activation+1.28e-02

Pos logit contributions
 Lauder+1.640
 Loving+1.507
 Sioux+1.492
 Hots+1.408
 Subtle+1.385
Neg logit contributions
obar-1.308
rane-1.258
minist-1.138
oba-1.110
ega-1.088
Token into
Token ID656
Feature activation-4.58e-01

Pos logit contributions
obar+0.023
rane+0.022
minist+0.021
oba+0.020
ega+0.020
Neg logit contributions
 Lauder-0.022
 Loving-0.020
 Sioux-0.020
 Hots-0.018
 Subtle-0.018
Token "
Token ID366
Feature activation+6.19e-02

Pos logit contributions
obar+0.085
rane+0.082
minist+0.077
oba+0.075
ega+0.074
Neg logit contributions
 Lauder-0.051
 Loving-0.045
 Sioux-0.045
 Hots-0.041
 Subtle-0.040
Tokenwhich
Token ID4758
Feature activation+1.16e-01

Pos logit contributions
obar+0.096
rane+0.092
minist+0.084
oba+0.081
ega+0.079
Neg logit contributions
 Lauder-0.123
 Loving-0.113
 Sioux-0.112
 Hots-0.106
 Subtle-0.104
Token can
Token ID460
Feature activation-1.91e-01

Pos logit contributions
obar+0.209
rane+0.203
minist+0.185
oba+0.182
ega+0.181
Neg logit contributions
 Lauder-0.197
 Loving-0.178
 Sioux-0.174
 Hots-0.163
 Subtle-0.162
Token come
Token ID1282
Feature activation+8.56e-01

Pos logit contributions
 Lauder+0.357
 Loving+0.325
 Sioux+0.318
 Hots+0.299
 Subtle+0.295
Neg logit contributions
obar-0.319
rane-0.307
minist-0.276
oba-0.276
ega-0.272
Token from
Token ID422
Feature activation-2.22e-01

Pos logit contributions
obar+1.630
rane+1.554
minist+1.448
ega+1.424
oba+1.419
Neg logit contributions
 Lauder-1.387
 Loving-1.233
 Sioux-1.218
 Subtle-1.137
 Hots-1.126
Token stroke
Token ID14000
Feature activation+1.52e+00

Pos logit contributions
 Lauder+0.356
 Loving+0.318
 Sioux+0.315
 Hots+0.293
 Subtle+0.287
Neg logit contributions
obar-0.424
rane-0.411
minist-0.380
oba-0.372
ega-0.367
Token,
Token ID11
Feature activation+1.66e-01

Pos logit contributions
obar+2.626
rane+2.531
minist+2.331
oba+2.306
ega+2.293
Neg logit contributions
 Lauder-2.681
 Loving-2.413
 Sioux-2.384
 Hots-2.249
 Subtle-2.192
Token head
Token ID1182
Feature activation+2.81e-01

Pos logit contributions
obar+0.298
rane+0.286
minist+0.262
oba+0.256
ega+0.253
Neg logit contributions
 Lauder-0.287
 Loving-0.258
 Sioux-0.255
 Hots-0.241
 Subtle-0.237
Token trauma
Token ID14649
Feature activation+6.18e-01

Pos logit contributions
obar+0.520
rane+0.499
minist+0.460
oba+0.456
ega+0.447
Neg logit contributions
 Lauder-0.476
 Loving-0.424
 Sioux-0.423
 Hots-0.397
 Subtle-0.388
Token or
Token ID393
Feature activation+9.07e-03

Pos logit contributions
obar+1.125
rane+1.080
minist+0.996
oba+0.981
ega+0.977
Neg logit contributions
 Lauder-1.044
 Loving-0.942
 Sioux-0.931
 Hots-0.872
 Subtle-0.860
Token other
Token ID584
Feature activation-3.54e-01

Pos logit contributions
obar+0.017
rane+0.016
minist+0.015
oba+0.015
ega+0.014
Neg logit contributions
 Lauder-0.015
 Loving-0.013
 Sioux-0.013
 Hots-0.013
 Subtle-0.012
Token of
Token ID286
Feature activation-6.31e-02

Pos logit contributions
obar+0.055
rane+0.054
minist+0.050
oba+0.049
ega+0.048
Neg logit contributions
 Lauder-0.038
 Loving-0.034
 Sioux-0.033
 Hots-0.031
 Subtle-0.030
Token her
Token ID607
Feature activation-4.20e-01

Pos logit contributions
 Lauder+0.105
 Loving+0.095
 Sioux+0.094
 Hots+0.088
 Subtle+0.086
Neg logit contributions
obar-0.117
rane-0.113
minist-0.104
oba-0.102
ega-0.100
Token Dec
Token ID4280
Feature activation+2.54e-01

Pos logit contributions
 Lauder+0.744
 Loving+0.675
 Sioux+0.662
 Hots+0.627
 Subtle+0.616
Neg logit contributions
obar-0.732
rane-0.710
minist-0.648
oba-0.636
ega-0.627
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
obar+0.443
rane+0.433
oba+0.389
minist+0.388
ega+0.377
Neg logit contributions
 Lauder-0.455
 Loving-0.409
 Sioux-0.406
 Hots-0.385
 Subtle-0.375
Token 6
Token ID718
Feature activation-1.26e-01

Pos logit contributions
obar+0.229
rane+0.224
minist+0.204
oba+0.202
ega+0.199
Neg logit contributions
 Lauder-0.207
 Loving-0.184
 Sioux-0.182
 Hots-0.171
 Subtle-0.166
Token runoff
Token ID37536
Feature activation+1.52e+00

Pos logit contributions
 Lauder+0.229
 Loving+0.208
 Sioux+0.205
 Hots+0.193
 Subtle+0.190
Neg logit contributions
obar-0.213
rane-0.206
minist-0.187
oba-0.185
ega-0.182
Token against
Token ID1028
Feature activation+9.51e-03

Pos logit contributions
obar+2.556
rane+2.480
ega+2.249
minist+2.236
oba+2.233
Neg logit contributions
 Lauder-2.750
 Loving-2.458
 Sioux-2.377
 Hots-2.290
 Subtle-2.282
Token Rep
Token ID1432
Feature activation+1.07e-01

Pos logit contributions
obar+0.017
rane+0.016
minist+0.015
oba+0.015
ega+0.015
Neg logit contributions
 Lauder-0.016
 Loving-0.015
 Sioux-0.015
 Hots-0.014
 Subtle-0.013
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
obar+0.187
rane+0.182
minist+0.165
oba+0.163
ega+0.160
Neg logit contributions
 Lauder-0.189
 Loving-0.170
 Sioux-0.168
 Hots-0.158
 Subtle-0.157
Token Bill
Token ID3941
Feature activation-5.64e-01

Pos logit contributions
 Lauder+0.200
 Loving+0.181
 Sioux+0.178
 Hots+0.166
 Subtle+0.165
Neg logit contributions
obar-0.229
rane-0.222
minist-0.202
oba-0.200
ega-0.199
Token Cassidy
Token ID41373
Feature activation-4.69e-01

Pos logit contributions
 Lauder+0.869
 Loving+0.769
 Sioux+0.758
 Hots+0.712
 Subtle+0.699
Neg logit contributions
obar-1.098
rane-1.085
oba-0.974
minist-0.968
ega-0.966
Token baking
Token ID16871
Feature activation-1.62e-01

Pos logit contributions
obar+0.290
rane+0.280
minist+0.255
oba+0.251
ega+0.245
Neg logit contributions
 Lauder-0.326
 Loving-0.295
 Sioux-0.292
 Hots-0.276
 Subtle-0.272
Token that
Token ID326
Feature activation+3.11e-01

Pos logit contributions
 Lauder+0.275
 Loving+0.248
 Sioux+0.244
 Hots+0.228
 Subtle+0.223
Neg logit contributions
obar-0.296
rane-0.284
minist-0.264
oba-0.257
ega-0.252
Token also
Token ID635
Feature activation+4.88e-01

Pos logit contributions
obar+0.583
rane+0.561
minist+0.517
oba+0.510
ega+0.497
Neg logit contributions
 Lauder-0.508
 Loving-0.460
 Sioux-0.447
 Hots-0.419
 Subtle-0.410
Token contains
Token ID4909
Feature activation+8.04e-01

Pos logit contributions
obar+0.878
rane+0.855
minist+0.782
oba+0.776
ega+0.765
Neg logit contributions
 Lauder-0.831
 Loving-0.748
 Sioux-0.728
 Hots-0.679
 Subtle-0.672
Token baking
Token ID16871
Feature activation-2.70e-02

Pos logit contributions
obar+1.489
rane+1.434
oba+1.336
minist+1.306
ega+1.288
Neg logit contributions
 Lauder-1.318
 Loving-1.179
 Sioux-1.149
 Hots-1.085
 Subtle-1.051
Token soda
Token ID20584
Feature activation+1.52e+00

Pos logit contributions
 Lauder+0.047
 Loving+0.042
 Sioux+0.041
 Hots+0.039
 Sikh+0.038
Neg logit contributions
obar-0.049
rane-0.047
oba-0.043
minist-0.043
ega-0.041
Token (
Token ID357
Feature activation+7.17e-02

Pos logit contributions
obar+2.685
rane+2.570
oba+2.377
minist+2.371
ega+2.320
Neg logit contributions
 Lauder-2.639
 Loving-2.339
 Sioux-2.329
 Hots-2.160
 Sikh-2.128
Tokenit
Token ID270
Feature activation-3.75e-02

Pos logit contributions
obar+0.126
rane+0.121
minist+0.111
oba+0.110
ega+0.107
Neg logit contributions
 Lauder-0.128
 Loving-0.116
 Sioux-0.115
 Hots-0.107
 Subtle-0.106
Token
Token ID447
Feature activation-1.64e-01

Pos logit contributions
 Lauder+0.061
 Loving+0.055
 Sioux+0.054
 Hots+0.050
 Subtle+0.049
Neg logit contributions
obar-0.072
rane-0.069
minist-0.064
oba-0.063
ega-0.062
Token
Token ID247
Feature activation+9.58e-02

Pos logit contributions
 Lauder+0.305
 Sioux+0.279
 Loving+0.272
 Hots+0.258
 Sikh+0.251
Neg logit contributions
obar-0.273
rane-0.263
minist-0.238
oba-0.230
ega-0.229
Tokens
Token ID82
Feature activation+8.96e-04

Pos logit contributions
obar+0.182
rane+0.179
minist+0.167
oba+0.162
ega+0.161
Neg logit contributions
 Lauder-0.156
 Loving-0.136
 Sioux-0.135
 Hots-0.125
 Subtle-0.123
Token panels
Token ID13043
Feature activation+7.04e-01

Pos logit contributions
obar+0.351
rane+0.342
minist+0.312
oba+0.305
ega+0.302
Neg logit contributions
 Lauder-0.321
 Loving-0.292
 Sioux-0.289
 Subtle-0.268
 Hots-0.266
Token is
Token ID318
Feature activation+1.60e-01

Pos logit contributions
obar+1.252
rane+1.214
minist+1.102
oba+1.097
ega+1.089
Neg logit contributions
 Lauder-1.208
 Loving-1.093
 Sioux-1.078
 Hots-0.993
 Subtle-0.989
Token composed
Token ID13160
Feature activation+5.87e-02

Pos logit contributions
obar+0.315
rane+0.303
oba+0.276
minist+0.276
ega+0.269
Neg logit contributions
 Lauder-0.250
 Loving-0.226
 Sioux-0.218
 Subtle-0.205
 Hots-0.203
Token of
Token ID286
Feature activation+1.79e-01

Pos logit contributions
obar+0.130
rane+0.127
minist+0.119
oba+0.116
ega+0.115
Neg logit contributions
 Lauder-0.077
 Loving-0.067
 Sioux-0.066
 Hots-0.060
 Sikh-0.059
Token combust
Token ID27500
Feature activation-6.66e-01

Pos logit contributions
obar+0.331
rane+0.320
minist+0.291
oba+0.289
ega+0.283
Neg logit contributions
 Lauder-0.296
 Loving-0.268
 Sioux-0.263
 Hots-0.247
 Subtle-0.245
Tokenible
Token ID856
Feature activation+1.52e+00

Pos logit contributions
 Lauder+0.998
 Loving+0.892
 Sioux+0.876
 Hots+0.806
 Subtle+0.799
Neg logit contributions
obar-1.357
rane-1.314
minist-1.216
oba-1.202
ega-1.181
Token plastic
Token ID7309
Feature activation+4.21e-01

Pos logit contributions
obar+2.561
rane+2.477
oba+2.203
minist+2.165
ega+2.133
Neg logit contributions
 Lauder-2.727
 Loving-2.461
 Sioux-2.362
 Subtle-2.306
 Hots-2.273
Token material
Token ID2587
Feature activation+3.58e-01

Pos logit contributions
obar+0.760
rane+0.734
oba+0.659
minist+0.653
ega+0.652
Neg logit contributions
 Lauder-0.727
 Loving-0.650
 Sioux-0.644
 Hots-0.601
 Subtle-0.601
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
obar+0.650
rane+0.630
minist+0.572
oba+0.566
ega+0.560
Neg logit contributions
 Lauder-0.613
 Loving-0.547
 Sioux-0.543
 Hots-0.501
 Subtle-0.501
Token A
Token ID317
Feature activation+5.20e-01

Pos logit contributions
obar+0.323
rane+0.310
minist+0.285
oba+0.284
ega+0.276
Neg logit contributions
 Lauder-0.276
 Loving-0.248
 Sioux-0.245
 Hots-0.223
 Sikh-0.221
Token sample
Token ID6291
Feature activation-4.60e-01

Pos logit contributions
obar+0.953
rane+0.924
minist+0.848
oba+0.842
ega+0.816
Neg logit contributions
 Lauder-0.866
 Loving-0.791
 Sioux-0.780
 Subtle-0.722
 Hots-0.720
Token did
Token ID750
Feature activation+4.63e-01

Pos logit contributions
 Lauder+0.134
 Loving+0.120
 Sioux+0.119
 Hots+0.111
 Subtle+0.111
Neg logit contributions
obar-0.132
rane-0.127
minist-0.116
oba-0.114
ega-0.113
Token not
Token ID407
Feature activation-3.34e-02

Pos logit contributions
obar+0.818
rane+0.791
minist+0.724
oba+0.716
ega+0.704
Neg logit contributions
 Lauder-0.814
 Loving-0.724
 Sioux-0.719
 Hots-0.672
 Subtle-0.665
Token issue
Token ID2071
Feature activation-8.66e-01

Pos logit contributions
 Lauder+0.062
 Sioux+0.055
 Loving+0.055
 Hots+0.051
 Subtle+0.051
Neg logit contributions
obar-0.057
rane-0.055
minist-0.050
oba-0.049
ega-0.048
Token the
Token ID262
Feature activation-9.21e-03

Pos logit contributions
 Lauder+1.369
 Loving+1.220
 Sioux+1.213
 Hots+1.129
 Subtle+1.107
Neg logit contributions
obar-1.676
rane-1.626
minist-1.503
oba-1.475
ega-1.449
Token total
Token ID2472
Feature activation-4.26e-01

Pos logit contributions
 Lauder+0.014
 Sioux+0.012
 Loving+0.012
 Hots+0.012
 Subtle+0.011
Neg logit contributions
obar-0.018
rane-0.017
minist-0.016
oba-0.016
ega-0.015
Token Loving
Token ID39202
Feature activation-2.29e+00

Pos logit contributions
 Lauder+0.700
 Sioux+0.615
 Loving+0.613
 Hots+0.578
 Subtle+0.568
Neg logit contributions
obar-0.799
rane-0.776
minist-0.714
oba-0.705
ega-0.686
Token v
Token ID410
Feature activation-8.07e-01

Pos logit contributions
 Lauder+3.637
 Loving+3.343
 Sioux+3.286
 Hots+3.037
 Sikh+2.964
Neg logit contributions
obar-4.406
rane-4.271
minist-3.954
oba-3.853
ega-3.782
Token.
Token ID13
Feature activation-1.58e-01

Pos logit contributions
 Lauder+1.404
 Loving+1.238
 Sioux+1.233
 Hots+1.160
 Subtle+1.149
Neg logit contributions
obar-1.450
rane-1.403
minist-1.284
oba-1.262
ega-1.236
Token Virginia
Token ID6025
Feature activation-9.07e-02

Pos logit contributions
 Lauder+0.180
 Sioux+0.148
 Loving+0.148
 Hots+0.132
 Sikh+0.129
Neg logit contributions
obar-0.380
rane-0.368
minist-0.344
oba-0.344
ega-0.337
Token victory
Token ID5373
Feature activation+1.55e-01

Pos logit contributions
 Lauder+0.163
 Sioux+0.142
 Loving+0.140
 Hots+0.134
 Subtle+0.134
Neg logit contributions
obar-0.155
rane-0.149
oba-0.135
minist-0.135
ega-0.132
Token that
Token ID326
Feature activation+1.91e-02

Pos logit contributions
obar+0.274
rane+0.265
minist+0.243
oba+0.240
ega+0.237
Neg logit contributions
 Lauder-0.269
 Sioux-0.237
 Loving-0.234
 Hots-0.223
 Subtle-0.222
Token will
Token ID481
Feature activation-1.13e-01

Pos logit contributions
obar+0.473
rane+0.455
minist+0.420
ega+0.409
oba+0.408
Neg logit contributions
 Lauder-0.464
 Loving-0.416
 Sioux-0.411
 Hots-0.387
 Subtle-0.386
Token be
Token ID307
Feature activation-1.76e-01

Pos logit contributions
 Lauder+0.205
 Loving+0.187
 Sioux+0.183
 Hots+0.172
 Subtle+0.171
Neg logit contributions
obar-0.194
rane-0.185
minist-0.170
oba-0.167
ega-0.165
Token the
Token ID262
Feature activation-9.71e-02

Pos logit contributions
 Lauder+0.278
 Loving+0.245
 Sioux+0.242
 Subtle+0.227
 Hots+0.226
Neg logit contributions
obar-0.342
rane-0.325
minist-0.303
ega-0.296
oba-0.295
Token equivalent
Token ID7548
Feature activation-6.40e-01

Pos logit contributions
 Lauder+0.173
 Loving+0.155
 Sioux+0.154
 Hots+0.145
 Subtle+0.143
Neg logit contributions
obar-0.168
rane-0.161
minist-0.148
oba-0.144
ega-0.142
Token of
Token ID286
Feature activation-2.40e-02

Pos logit contributions
 Lauder+0.803
 Loving+0.709
 Sioux+0.695
 Hots+0.620
 Ku+0.613
Neg logit contributions
obar-1.440
rane-1.409
minist-1.318
oba-1.298
ega-1.269
Token Loving
Token ID39202
Feature activation-2.20e+00

Pos logit contributions
 Lauder+0.037
 Sioux+0.033
 Loving+0.032
 Hots+0.030
 Subtle+0.030
Neg logit contributions
obar-0.047
rane-0.045
minist-0.042
oba-0.041
ega-0.040
Token v
Token ID410
Feature activation-9.21e-01

Pos logit contributions
 Lauder+2.576
 Loving+2.298
 Sioux+2.229
 Hots+2.006
 Sikh+1.929
Neg logit contributions
obar-5.114
rane-5.008
minist-4.698
oba-4.604
ega-4.527
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
 Lauder+1.595
 Loving+1.412
 Sioux+1.407
 Hots+1.320
 Subtle+1.299
Neg logit contributions
obar-1.647
rane-1.595
minist-1.453
oba-1.433
ega-1.411
Token Virginia
Token ID6025
Feature activation-1.14e-01

Pos logit contributions
 Lauder+0.277
 Sioux+0.228
 Loving+0.225
 Hots+0.208
 Sikh+0.201
Neg logit contributions
obar-0.563
rane-0.546
minist-0.509
oba-0.508
ega-0.502
Token,
Token ID11
Feature activation-7.90e-02

Pos logit contributions
 Lauder+0.189
 Sioux+0.166
 Loving+0.165
 Subtle+0.154
 Hots+0.154
Neg logit contributions
obar-0.213
rane-0.203
minist-0.188
oba-0.185
ega-0.184
Token which
Token ID543
Feature activation-2.41e-01

Pos logit contributions
 Lauder+0.134
 Sioux+0.118
 Loving+0.116
 Hots+0.110
 Subtle+0.109
Neg logit contributions
obar-0.146
rane-0.138
minist-0.126
oba-0.124
ega-0.124
Token outright
Token ID15828
Feature activation-5.46e-01

Pos logit contributions
 Lauder+0.076
 Loving+0.068
 Sioux+0.067
 Hots+0.063
 Subtle+0.062
Neg logit contributions
obar-0.097
rane-0.095
minist-0.086
oba-0.085
ega-0.083
Token ban
Token ID3958
Feature activation-4.34e-01

Pos logit contributions
 Lauder+0.948
 Loving+0.861
 Sioux+0.849
 Hots+0.801
 Subtle+0.797
Neg logit contributions
obar-0.961
rane-0.940
minist-0.857
oba-0.846
ega-0.825
Token on
Token ID319
Feature activation-1.82e-02

Pos logit contributions
 Lauder+0.692
 Loving+0.620
 Sioux+0.614
 Hots+0.571
 Subtle+0.562
Neg logit contributions
obar-0.841
rane-0.811
minist-0.754
oba-0.735
ega-0.728
Token wearing
Token ID5762
Feature activation-5.12e-01

Pos logit contributions
 Lauder+0.029
 Loving+0.026
 Sioux+0.025
 Hots+0.024
 Subtle+0.024
Neg logit contributions
obar-0.035
rane-0.034
minist-0.032
oba-0.031
ega-0.030
Token the
Token ID262
Feature activation+9.33e-03

Pos logit contributions
 Lauder+0.792
 Loving+0.715
 Sioux+0.698
 Hots+0.653
 Subtle+0.648
Neg logit contributions
obar-1.005
rane-0.968
minist-0.902
oba-0.879
ega-0.871
Token hijab
Token ID48492
Feature activation-1.93e+00

Pos logit contributions
obar+0.022
rane+0.021
minist+0.020
oba+0.020
ega+0.020
Neg logit contributions
 Lauder-0.011
 Loving-0.009
 Sioux-0.009
 Hots-0.008
 Subtle-0.008
Token.
Token ID13
Feature activation+3.23e-01

Pos logit contributions
 Lauder+2.983
 Loving+2.691
 Sioux+2.643
 Hots+2.458
 Sikh+2.431
Neg logit contributions
obar-3.775
rane-3.665
minist-3.387
oba-3.316
ega-3.261
Token
Token ID198
Feature activation+3.58e-01

Pos logit contributions
obar+0.595
rane+0.572
minist+0.529
oba+0.524
ega+0.516
Neg logit contributions
 Lauder-0.526
 Sioux-0.469
 Loving-0.469
 Hots-0.434
 Subtle-0.426
Token
Token ID198
Feature activation+3.22e-01

Pos logit contributions
obar+0.632
rane+0.606
minist+0.558
oba+0.551
ega+0.539
Neg logit contributions
 Lauder-0.633
 Sioux-0.557
 Loving-0.555
 Hots-0.517
 Subtle-0.513
TokenSad
Token ID26699
Feature activation+3.43e-02

Pos logit contributions
obar+0.510
rane+0.490
minist+0.449
oba+0.436
ega+0.425
Neg logit contributions
 Lauder-0.627
 Loving-0.574
 Sioux-0.570
 Hots-0.536
 Subtle-0.529
Tokenain
Token ID391
Feature activation+8.32e-02

Pos logit contributions
obar+0.060
rane+0.058
minist+0.053
oba+0.052
ega+0.052
Neg logit contributions
 Lauder-0.061
 Loving-0.055
 Sioux-0.055
 Hots-0.052
 Subtle-0.051
Token-
Token ID12
Feature activation+3.48e-02

Pos logit contributions
 Lauder+0.414
 Loving+0.370
 Sioux+0.363
 Hots+0.333
 Sikh+0.327
Neg logit contributions
obar-0.601
rane-0.583
minist-0.542
oba-0.532
ega-0.525
Tokenw
Token ID86
Feature activation+3.41e-01

Pos logit contributions
obar+0.059
rane+0.058
minist+0.054
oba+0.052
ega+0.051
Neg logit contributions
 Lauder-0.063
 Loving-0.057
 Sioux-0.057
 Hots-0.054
 Subtle-0.052
Tokenearing
Token ID6648
Feature activation+6.24e-02

Pos logit contributions
obar+0.672
rane+0.649
minist+0.606
oba+0.595
ega+0.585
Neg logit contributions
 Lauder-0.540
 Loving-0.476
 Sioux-0.468
 Hots-0.440
 Subtle-0.434
Token of
Token ID286
Feature activation+1.62e-01

Pos logit contributions
obar+0.127
rane+0.123
minist+0.117
oba+0.113
ega+0.111
Neg logit contributions
 Lauder-0.091
 Loving-0.081
 Sioux-0.079
 Hots-0.074
 Subtle-0.072
Token the
Token ID262
Feature activation+1.40e-01

Pos logit contributions
obar+0.314
rane+0.302
minist+0.283
oba+0.273
ega+0.273
Neg logit contributions
 Lauder-0.252
 Loving-0.227
 Sioux-0.223
 Hots-0.208
 Subtle-0.204
Token hijab
Token ID48492
Feature activation-1.76e+00

Pos logit contributions
obar+0.341
rane+0.331
minist+0.315
oba+0.308
ega+0.308
Neg logit contributions
 Lauder-0.145
 Loving-0.124
 Sioux-0.119
 Hots-0.106
 Subtle-0.103
Token or
Token ID393
Feature activation-2.19e-02

Pos logit contributions
 Lauder+2.736
 Loving+2.467
 Sioux+2.425
 Hots+2.256
 Sikh+2.216
Neg logit contributions
obar-3.449
rane-3.343
minist-3.092
oba-3.030
ega-2.984
Token veil
Token ID30615
Feature activation-5.76e-01

Pos logit contributions
 Lauder+0.033
 Loving+0.029
 Sioux+0.029
 Hots+0.026
 Subtle+0.026
Neg logit contributions
obar-0.044
rane-0.043
minist-0.040
oba-0.039
ega-0.039
Token,
Token ID11
Feature activation+2.46e-01

Pos logit contributions
 Lauder+0.940
 Loving+0.843
 Sioux+0.837
 Hots+0.776
 Subtle+0.759
Neg logit contributions
obar-1.089
rane-1.052
minist-0.974
oba-0.952
ega-0.938
Token
Token ID447
Feature activation-8.96e-02

Pos logit contributions
obar+0.458
rane+0.442
minist+0.410
oba+0.399
ega+0.389
Neg logit contributions
 Lauder-0.408
 Sioux-0.363
 Loving-0.361
 Hots-0.338
 Subtle-0.329
Token
Token ID251
Feature activation+1.38e-01

Pos logit contributions
 Lauder+0.146
 Loving+0.131
 Sioux+0.130
 Hots+0.120
 Sikh+0.118
Neg logit contributions
obar-0.171
rane-0.164
minist-0.151
oba-0.149
ega-0.146
Tokenacing
Token ID4092
Feature activation-3.32e-02

Pos logit contributions
obar+0.303
rane+0.289
minist+0.258
oba+0.250
ega+0.244
Neg logit contributions
 Lauder-0.488
 Loving-0.453
 Sioux-0.448
 Hots-0.426
 Subtle-0.420
Token inter
Token ID987
Feature activation-2.12e-01

Pos logit contributions
 Lauder+0.055
 Loving+0.050
 Sioux+0.049
 Hots+0.046
 Subtle+0.045
Neg logit contributions
obar-0.061
rane-0.059
minist-0.054
oba-0.053
ega-0.053
Token p
Token ID279
Feature activation+4.08e-01

Pos logit contributions
 Lauder+0.363
 Loving+0.327
 Sioux+0.324
 Hots+0.303
 Sikh+0.297
Neg logit contributions
obar-0.383
rane-0.375
minist-0.349
oba-0.333
ega-0.330
Tokenares
Token ID3565
Feature activation-2.36e-01

Pos logit contributions
obar+0.802
rane+0.770
minist+0.707
oba+0.699
ega+0.691
Neg logit contributions
 Lauder-0.647
 Loving-0.576
 Sioux-0.573
 Hots-0.530
 Sikh-0.525
Token and
Token ID290
Feature activation-2.05e-03

Pos logit contributions
 Lauder+0.440
 Loving+0.403
 Sioux+0.399
 Hots+0.374
 Sikh+0.368
Neg logit contributions
obar-0.390
rane-0.377
minist-0.346
oba-0.334
ega-0.329
Token supra
Token ID28614
Feature activation-1.76e+00

Pos logit contributions
 Lauder+0.003
 Loving+0.003
 Sioux+0.003
 Hots+0.003
 Subtle+0.003
Neg logit contributions
obar-0.004
rane-0.004
minist-0.004
oba-0.003
ega-0.003
Token-
Token ID12
Feature activation+3.95e-02

Pos logit contributions
 Lauder+2.723
 Loving+2.445
 Sioux+2.409
 Hots+2.232
 Subtle+2.184
Neg logit contributions
obar-3.474
rane-3.369
minist-3.121
oba-3.057
ega-3.013
Tokennational
Token ID14648
Feature activation-4.36e-01

Pos logit contributions
obar+0.071
rane+0.069
minist+0.064
oba+0.062
ega+0.061
Neg logit contributions
 Lauder-0.068
 Loving-0.061
 Sioux-0.061
 Hots-0.057
 Subtle-0.056
Token nature
Token ID3450
Feature activation+3.20e-01

Pos logit contributions
 Lauder+0.697
 Loving+0.631
 Sioux+0.621
 Hots+0.576
 Subtle+0.568
Neg logit contributions
obar-0.833
rane-0.807
minist-0.748
oba-0.730
ega-0.722
Token of
Token ID286
Feature activation+2.57e-02

Pos logit contributions
obar+0.699
rane+0.679
minist+0.634
oba+0.623
ega+0.615
Neg logit contributions
 Lauder-0.427
 Loving-0.377
 Sioux-0.370
 Hots-0.338
 Subtle-0.329
Token the
Token ID262
Feature activation+4.71e-02

Pos logit contributions
obar+0.049
rane+0.047
minist+0.044
oba+0.043
ega+0.042
Neg logit contributions
 Lauder-0.041
 Loving-0.037
 Sioux-0.037
 Hots-0.034
 Subtle-0.034
Token trip
Token ID5296
Feature activation-1.07e-01

Pos logit contributions
 Lauder+0.544
 Loving+0.486
 Sioux+0.481
 Hots+0.445
 Subtle+0.440
Neg logit contributions
obar-0.645
rane-0.618
minist-0.578
oba-0.562
ega-0.556
Token worsh
Token ID26511
Feature activation-1.52e+00

Pos logit contributions
 Lauder+0.175
 Loving+0.156
 Sioux+0.154
 Hots+0.144
 Subtle+0.141
Neg logit contributions
obar-0.205
rane-0.197
minist-0.185
oba-0.179
ega-0.177
Tokenipping
Token ID4501
Feature activation-5.66e-01

Pos logit contributions
 Lauder+2.937
 Loving+2.720
 Sioux+2.683
 Hots+2.533
 Sikh+2.487
Neg logit contributions
obar-2.351
rane-2.268
minist-2.028
oba-1.998
ega-1.970
Token Lenin
Token ID22899
Feature activation-6.56e-01

Pos logit contributions
 Lauder+0.889
 Loving+0.793
 Sioux+0.780
 Hots+0.726
 Subtle+0.712
Neg logit contributions
obar-1.108
rane-1.071
minist-1.000
oba-0.971
ega-0.956
Token and
Token ID290
Feature activation+9.34e-02

Pos logit contributions
 Lauder+1.028
 Loving+0.923
 Sioux+0.908
 Hots+0.838
 Subtle+0.828
Neg logit contributions
obar-1.287
rane-1.243
minist-1.156
oba-1.131
ega-1.113
Token Trotsky
Token ID32706
Feature activation-1.75e+00

Pos logit contributions
obar+0.195
rane+0.189
minist+0.178
oba+0.173
ega+0.170
Neg logit contributions
 Lauder-0.131
 Loving-0.114
 Sioux-0.113
 Subtle-0.104
 Hots-0.104
Token,
Token ID11
Feature activation+2.13e-01

Pos logit contributions
 Lauder+2.484
 Loving+2.208
 Sioux+2.175
 Hots+2.006
 Subtle+1.948
Neg logit contributions
obar-3.676
rane-3.575
minist-3.319
oba-3.259
ega-3.219
Token around
Token ID1088
Feature activation-4.22e-01

Pos logit contributions
obar+0.411
rane+0.393
minist+0.369
oba+0.356
ega+0.350
Neg logit contributions
 Lauder-0.339
 Loving-0.302
 Sioux-0.298
 Hots-0.276
 Subtle-0.276
Token whom
Token ID4150
Feature activation+7.80e-02

Pos logit contributions
 Lauder+0.694
 Loving+0.625
 Sioux+0.616
 Hots+0.575
 Subtle+0.566
Neg logit contributions
obar-0.794
rane-0.767
minist-0.711
oba-0.691
ega-0.678
Token all
Token ID477
Feature activation+2.74e-01

Pos logit contributions
obar+0.152
rane+0.148
minist+0.138
oba+0.134
ega+0.131
Neg logit contributions
 Lauder-0.120
 Loving-0.107
 Sioux-0.105
 Hots-0.098
 Subtle-0.097
Token history
Token ID2106
Feature activation+1.26e-01

Pos logit contributions
obar+0.516
rane+0.503
minist+0.467
oba+0.455
ega+0.442
Neg logit contributions
 Lauder-0.444
 Loving-0.396
 Sioux-0.391
 Hots-0.365
 Subtle-0.356
Token intellig
Token ID10878
Feature activation-6.12e-01

Pos logit contributions
 Lauder+0.528
 Loving+0.477
 Sioux+0.464
 Hots+0.430
 Subtle+0.426
Neg logit contributions
obar-0.657
rane-0.637
minist-0.596
oba-0.581
ega-0.571
Tokenents
Token ID658
Feature activation+1.15e-02

Pos logit contributions
 Lauder+0.832
 Loving+0.738
 Sioux+0.724
 Hots+0.662
 Subtle+0.646
Neg logit contributions
obar-1.324
rane-1.288
minist-1.203
oba-1.180
ega-1.164
Tokenia
Token ID544
Feature activation-1.56e-01

Pos logit contributions
obar+0.016
rane+0.016
minist+0.014
oba+0.013
ega+0.013
Neg logit contributions
 Lauder-0.025
 Loving-0.023
 Sioux-0.022
 Hots-0.021
 Subtle-0.021
Token resisted
Token ID26643
Feature activation-9.74e-02

Pos logit contributions
 Lauder+0.243
 Loving+0.220
 Sioux+0.214
 Hots+0.199
 Subtle+0.197
Neg logit contributions
obar-0.307
rane-0.298
minist-0.277
oba-0.270
ega-0.267
Token en
Token ID551
Feature activation+3.18e-02

Pos logit contributions
 Lauder+0.158
 Loving+0.143
 Sioux+0.141
 Hots+0.131
 Subtle+0.128
Neg logit contributions
obar-0.185
rane-0.179
minist-0.167
oba-0.162
ega-0.160
Token masse
Token ID41869
Feature activation-1.74e+00

Pos logit contributions
obar+0.057
rane+0.056
minist+0.051
oba+0.050
ega+0.049
Neg logit contributions
 Lauder-0.054
 Loving-0.049
 Sioux-0.049
 Hots-0.046
 Subtle-0.045
Token letting
Token ID9616
Feature activation+6.14e-01

Pos logit contributions
 Lauder+2.749
 Loving+2.476
 Sioux+2.440
 Hots+2.268
 Subtle+2.218
Neg logit contributions
obar-3.372
rane-3.273
minist-3.019
oba-2.962
ega-2.917
Token itself
Token ID2346
Feature activation+2.10e-01

Pos logit contributions
obar+1.084
rane+1.046
minist+0.962
oba+0.945
ega+0.918
Neg logit contributions
 Lauder-1.062
 Loving-0.974
 Sioux-0.959
 Hots-0.894
 Subtle-0.879
Token be
Token ID307
Feature activation-1.54e-01

Pos logit contributions
obar+0.361
rane+0.347
minist+0.317
oba+0.314
ega+0.309
Neg logit contributions
 Lauder-0.380
 Loving-0.348
 Sioux-0.341
 Hots-0.319
 Subtle-0.317
Token travers
Token ID33038
Feature activation+8.24e-01

Pos logit contributions
 Lauder+0.246
 Loving+0.222
 Sioux+0.218
 Hots+0.201
 Subtle+0.199
Neg logit contributions
obar-0.300
rane-0.286
minist-0.265
oba-0.263
ega-0.259
Tokened
Token ID276
Feature activation+2.59e-01

Pos logit contributions
obar+1.127
rane+1.077
minist+0.971
oba+0.925
ega+0.908
Neg logit contributions
 Lauder-1.790
 Loving-1.643
 Sioux-1.631
 Hots-1.558
 Subtle-1.534
Token its
Token ID663
Feature activation-1.67e-01

Pos logit contributions
 Lauder+0.450
 Loving+0.409
 Sioux+0.403
 Hots+0.376
 Subtle+0.370
Neg logit contributions
obar-0.457
rane-0.442
minist-0.407
oba-0.397
ega-0.389
Token national
Token ID2260
Feature activation-8.13e-02

Pos logit contributions
 Lauder+0.288
 Loving+0.261
 Sioux+0.257
 Hots+0.239
 Subtle+0.235
Neg logit contributions
obar-0.302
rane-0.293
minist-0.269
oba-0.264
ega-0.257
Token debt
Token ID5057
Feature activation-2.22e-01

Pos logit contributions
 Lauder+0.136
 Loving+0.123
 Sioux+0.121
 Hots+0.113
 Subtle+0.111
Neg logit contributions
obar-0.150
rane-0.146
minist-0.134
oba-0.131
ega-0.129
Token to
Token ID284
Feature activation-2.94e-02

Pos logit contributions
 Lauder+0.359
 Loving+0.326
 Sioux+0.319
 Hots+0.295
 Subtle+0.291
Neg logit contributions
obar-0.422
rane-0.406
minist-0.379
oba-0.370
ega-0.363
Token a
Token ID257
Feature activation-7.57e-02

Pos logit contributions
 Lauder+0.051
 Loving+0.046
 Sioux+0.045
 Hots+0.042
 Subtle+0.041
Neg logit contributions
obar-0.053
rane-0.052
minist-0.047
oba-0.047
ega-0.046
Token level
Token ID1241
Feature activation-1.74e+00

Pos logit contributions
 Lauder+0.131
 Loving+0.119
 Sioux+0.117
 Hots+0.109
 Subtle+0.107
Neg logit contributions
obar-0.135
rane-0.131
minist-0.119
oba-0.119
ega-0.115
Token that
Token ID326
Feature activation+2.08e-01

Pos logit contributions
 Lauder+2.813
 Loving+2.539
 Sioux+2.503
 Hots+2.327
 Subtle+2.281
Neg logit contributions
obar-3.315
rane-3.210
minist-2.965
oba-2.904
ega-2.858
Token the
Token ID262
Feature activation-8.23e-02

Pos logit contributions
obar+0.378
rane+0.364
minist+0.335
oba+0.326
ega+0.322
Neg logit contributions
 Lauder-0.352
 Loving-0.321
 Sioux-0.309
 Subtle-0.291
 Hots-0.286
Token market
Token ID1910
Feature activation+3.75e-01

Pos logit contributions
 Lauder+0.139
 Loving+0.126
 Sioux+0.124
 Hots+0.116
 Subtle+0.114
Neg logit contributions
obar-0.150
rane-0.146
minist-0.134
oba-0.131
ega-0.128
Token thinks
Token ID6834
Feature activation-2.31e-01

Pos logit contributions
obar+0.706
rane+0.682
minist+0.627
ega+0.613
oba+0.606
Neg logit contributions
 Lauder-0.618
 Loving-0.560
 Sioux-0.542
 Subtle-0.515
 Hots-0.506
Token is
Token ID318
Feature activation-3.95e-03

Pos logit contributions
 Lauder+0.384
 Loving+0.348
 Sioux+0.340
 Hots+0.315
 Subtle+0.313
Neg logit contributions
obar-0.429
rane-0.417
minist-0.384
oba-0.375
ega-0.370
Tokenmaking
Token ID8601
Feature activation-4.09e-01

Pos logit contributions
obar+0.112
rane+0.109
minist+0.103
oba+0.101
ega+0.100
Neg logit contributions
 Lauder-0.064
 Loving-0.055
 Sioux-0.054
 Hots-0.050
 Subtle-0.049
Token at
Token ID379
Feature activation+1.87e-01

Pos logit contributions
 Lauder+0.675
 Loving+0.607
 Sioux+0.598
 Hots+0.558
 Subtle+0.547
Neg logit contributions
obar-0.767
rane-0.743
minist-0.691
oba-0.671
ega-0.662
Token the
Token ID262
Feature activation-3.21e-02

Pos logit contributions
obar+0.347
rane+0.335
minist+0.312
oba+0.302
ega+0.297
Neg logit contributions
 Lauder-0.312
 Loving-0.276
 Sioux-0.274
 Hots-0.256
 Sikh-0.250
Token state
Token ID1181
Feature activation-2.02e-01

Pos logit contributions
 Lauder+0.055
 Loving+0.049
 Sioux+0.048
 Hots+0.045
 Subtle+0.045
Neg logit contributions
obar-0.057
rane-0.056
minist-0.052
oba-0.050
ega-0.049
Token court
Token ID2184
Feature activation+3.28e-01

Pos logit contributions
 Lauder+0.351
 Loving+0.317
 Sioux+0.313
 Hots+0.294
 Subtle+0.291
Neg logit contributions
obar-0.359
rane-0.346
minist-0.319
oba-0.310
ega-0.306
Token level
Token ID1241
Feature activation-1.69e+00

Pos logit contributions
obar+0.507
rane+0.485
minist+0.443
oba+0.425
ega+0.419
Neg logit contributions
 Lauder-0.642
 Loving-0.594
 Sioux-0.580
 Hots-0.551
 Subtle-0.545
Token,
Token ID11
Feature activation+2.91e-02

Pos logit contributions
 Lauder+2.682
 Loving+2.427
 Sioux+2.393
 Hots+2.225
 Sikh+2.178
Neg logit contributions
obar-3.249
rane-3.150
minist-2.899
oba-2.854
ega-2.806
Token where
Token ID810
Feature activation+2.76e-01

Pos logit contributions
obar+0.053
rane+0.051
minist+0.047
oba+0.046
ega+0.046
Neg logit contributions
 Lauder-0.049
 Loving-0.044
 Sioux-0.043
 Hots-0.040
 Subtle-0.040
Token 95
Token ID6957
Feature activation+3.21e-01

Pos logit contributions
obar+0.480
rane+0.465
minist+0.428
oba+0.415
ega+0.409
Neg logit contributions
 Lauder-0.486
 Loving-0.440
 Sioux-0.433
 Hots-0.412
 Subtle-0.402
Token percent
Token ID1411
Feature activation+2.15e-01

Pos logit contributions
obar+0.618
rane+0.598
minist+0.553
oba+0.540
ega+0.531
Neg logit contributions
 Lauder-0.510
 Loving-0.451
 Sioux-0.443
 Hots-0.419
 Subtle-0.410
Token of
Token ID286
Feature activation+5.13e-02

Pos logit contributions
obar+0.475
rane+0.461
minist+0.431
oba+0.424
ega+0.418
Neg logit contributions
 Lauder-0.282
 Loving-0.248
 Sioux-0.245
 Hots-0.222
 Sikh-0.216
Token M
Token ID337
Feature activation-4.35e-01

Pos logit contributions
 Lauder+0.196
 Loving+0.172
 Sioux+0.169
 Hots+0.157
 Subtle+0.155
Neg logit contributions
obar-0.272
rane-0.266
minist-0.247
oba-0.244
ega-0.235
Tokenakh
Token ID11322
Feature activation-3.06e-02

Pos logit contributions
 Lauder+0.839
 Loving+0.761
 Sioux+0.751
 Hots+0.716
 Subtle+0.713
Neg logit contributions
obar-0.707
rane-0.678
minist-0.614
oba-0.611
ega-0.587
Tokennov
Token ID37302
Feature activation-1.21e+00

Pos logit contributions
 Lauder+0.053
 Loving+0.048
 Sioux+0.048
 Hots+0.045
 Subtle+0.044
Neg logit contributions
obar-0.055
rane-0.053
minist-0.049
oba-0.048
ega-0.047
Tokenists
Token ID1023
Feature activation-5.67e-02

Pos logit contributions
 Lauder+1.491
 Loving+1.301
 Sioux+1.278
 Hots+1.154
 Subtle+1.121
Neg logit contributions
obar-2.782
rane-2.709
minist-2.536
oba-2.495
ega-2.465
Token,
Token ID11
Feature activation-4.93e-03

Pos logit contributions
 Lauder+0.091
 Loving+0.082
 Sioux+0.081
 Hots+0.075
 Subtle+0.074
Neg logit contributions
obar-0.108
rane-0.105
minist-0.097
oba-0.095
ega-0.094
Token Trotsky
Token ID32706
Feature activation-1.69e+00

Pos logit contributions
 Lauder+0.008
 Loving+0.007
 Sioux+0.007
 Hots+0.006
 Subtle+0.006
Neg logit contributions
obar-0.010
rane-0.009
minist-0.009
oba-0.008
ega-0.008
Tokenists
Token ID1023
Feature activation-4.79e-02

Pos logit contributions
 Lauder+2.574
 Loving+2.307
 Sioux+2.274
 Hots+2.106
 Subtle+2.057
Neg logit contributions
obar-3.374
rane-3.274
minist-3.032
oba-2.976
ega-2.932
Token par
Token ID1582
Feature activation-7.71e-02

Pos logit contributions
 Lauder+0.081
 Loving+0.073
 Sioux+0.072
 Hots+0.067
 Subtle+0.066
Neg logit contributions
obar-0.087
rane-0.084
minist-0.078
oba-0.076
ega-0.075
Tokenrot
Token ID10599
Feature activation+9.98e-02

Pos logit contributions
 Lauder+0.170
 Loving+0.158
 Sioux+0.157
 Hots+0.149
 Subtle+0.147
Neg logit contributions
obar-0.101
rane-0.096
minist-0.085
oba-0.083
ega-0.081
Token the
Token ID262
Feature activation+6.41e-03

Pos logit contributions
obar+0.192
rane+0.186
minist+0.175
oba+0.169
ega+0.166
Neg logit contributions
 Lauder-0.158
 Loving-0.142
 Sioux-0.139
 Hots-0.129
 Subtle-0.127
Token line
Token ID1627
Feature activation-6.88e-01

Pos logit contributions
obar+0.012
rane+0.012
minist+0.011
oba+0.011
ega+0.011
Neg logit contributions
 Lauder-0.010
 Loving-0.009
 Sioux-0.009
 Hots-0.008
 Subtle-0.008
Token Nigel
Token ID28772
Feature activation+3.52e-01

Pos logit contributions
obar+1.229
rane+1.190
minist+1.086
oba+1.084
ega+1.071
Neg logit contributions
 Lauder-1.015
 Loving-0.900
 Sioux-0.889
 Hots-0.823
 Subtle-0.812
Token Farage
Token ID33904
Feature activation-2.11e-01

Pos logit contributions
obar+0.523
rane+0.505
minist+0.444
oba+0.437
ega+0.428
Neg logit contributions
 Lauder-0.708
 Loving-0.648
 Sioux-0.645
 Hots-0.611
 Subtle-0.607
Token:
Token ID25
Feature activation-8.62e-02

Pos logit contributions
 Lauder+0.345
 Loving+0.311
 Sioux+0.308
 Subtle+0.284
 Hots+0.284
Neg logit contributions
obar-0.395
rane-0.384
minist-0.352
oba-0.345
ega-0.344
Token "
Token ID366
Feature activation-2.99e-01

Pos logit contributions
 Lauder+0.097
 Loving+0.083
 Sioux+0.082
 Hots+0.073
 Subtle+0.070
Neg logit contributions
obar-0.205
rane-0.200
minist-0.187
oba-0.185
ega-0.183
TokenLord
Token ID22438
Feature activation-5.67e-01

Pos logit contributions
 Lauder+0.577
 Loving+0.527
 Sioux+0.523
 Hots+0.491
 Subtle+0.484
Neg logit contributions
obar-0.477
rane-0.460
minist-0.420
oba-0.408
ega-0.399
Token Hes
Token ID44773
Feature activation-1.69e+00

Pos logit contributions
 Lauder+0.911
 Loving+0.824
 Sioux+0.815
 Hots+0.755
 Subtle+0.746
Neg logit contributions
obar-1.072
rane-1.046
minist-0.956
oba-0.943
ega-0.936
Tokenelt
Token ID2120
Feature activation-7.08e-01

Pos logit contributions
 Lauder+2.292
 Loving+2.054
 Sioux+1.981
 Hots+1.852
 Sikh+1.790
Neg logit contributions
obar-3.561
rane-3.471
minist-3.248
oba-3.164
ega-3.111
Tokenine
Token ID500
Feature activation-1.57e-01

Pos logit contributions
 Lauder+1.103
 Loving+0.999
 Sioux+0.992
 Hots+0.926
 Subtle+0.909
Neg logit contributions
obar-1.382
rane-1.359
minist-1.240
oba-1.215
ega-1.206
Token fears
Token ID10251
Feature activation-2.39e-01

Pos logit contributions
 Lauder+0.255
 Loving+0.230
 Sioux+0.228
 Hots+0.210
 Subtle+0.209
Neg logit contributions
obar-0.296
rane-0.287
minist-0.265
oba-0.259
ega-0.258
Token what
Token ID644
Feature activation-5.72e-01

Pos logit contributions
 Lauder+0.375
 Loving+0.339
 Sioux+0.334
 Hots+0.308
 Subtle+0.305
Neg logit contributions
obar-0.461
rane-0.448
minist-0.413
oba-0.403
ega-0.400
Token the
Token ID262
Feature activation-7.78e-02

Pos logit contributions
 Lauder+0.936
 Loving+0.847
 Sioux+0.834
 Hots+0.776
 Subtle+0.767
Neg logit contributions
obar-1.072
rane-1.039
minist-0.955
oba-0.935
ega-0.923
Token47
Token ID2857
Feature activation+6.62e-02

Pos logit contributions
 Lauder+0.301
 Loving+0.267
 Sioux+0.262
 Hots+0.240
 Subtle+0.234
Neg logit contributions
obar-0.473
rane-0.459
minist-0.429
oba-0.421
ega-0.415
Token]
Token ID60
Feature activation+3.38e-01

Pos logit contributions
obar+0.112
rane+0.108
minist+0.098
oba+0.096
ega+0.095
Neg logit contributions
 Lauder-0.122
 Sioux-0.109
 Loving-0.109
 Hots-0.101
 Subtle-0.101
Token <
Token ID1279
Feature activation+7.85e-01

Pos logit contributions
obar+0.701
rane+0.683
minist+0.634
oba+0.623
ega+0.614
Neg logit contributions
 Lauder-0.488
 Loving-0.435
 Sioux-0.428
 Hots-0.394
 Subtle-0.385
Tokenk
Token ID74
Feature activation+5.96e-02

Pos logit contributions
obar+1.372
rane+1.323
minist+1.224
oba+1.187
ega+1.159
Neg logit contributions
 Lauder-1.406
 Loving-1.280
 Sioux-1.267
 Hots-1.183
 Subtle-1.164
Tokenlink
Token ID8726
Feature activation+3.87e-01

Pos logit contributions
obar+0.101
rane+0.097
minist+0.089
oba+0.087
ega+0.085
Neg logit contributions
 Lauder-0.110
 Loving-0.101
 Sioux-0.100
 Hots-0.093
 Subtle-0.092
Tokenttp
Token ID29281
Feature activation-1.68e+00

Pos logit contributions
obar+0.696
rane+0.672
minist+0.618
oba+0.607
ega+0.596
Neg logit contributions
 Lauder-0.675
 Loving-0.609
 Sioux-0.606
 Hots-0.563
 Sikh-0.555
Token>
Token ID29
Feature activation-1.32e-01

Pos logit contributions
 Lauder+2.709
 Loving+2.469
 Sioux+2.418
 Hots+2.266
 Subtle+2.222
Neg logit contributions
obar-3.128
rane-3.036
minist-2.792
oba-2.729
ega-2.683
Token lol
Token ID19462
Feature activation-3.07e-01

Pos logit contributions
 Lauder+0.223
 Loving+0.200
 Sioux+0.199
 Hots+0.184
 Subtle+0.181
Neg logit contributions
obar-0.243
rane-0.234
minist-0.216
oba-0.212
ega-0.208
Token m
Token ID285
Feature activation+1.26e-01

Pos logit contributions
 Lauder+0.519
 Loving+0.470
 Sioux+0.464
 Hots+0.433
 Subtle+0.425
Neg logit contributions
obar-0.562
rane-0.544
minist-0.501
oba-0.490
ega-0.482
Token2
Token ID17
Feature activation+3.09e-02

Pos logit contributions
obar+0.237
rane+0.229
minist+0.210
oba+0.208
ega+0.203
Neg logit contributions
 Lauder-0.212
 Sioux-0.191
 Loving-0.191
 Hots-0.175
 Subtle-0.174
Tokenk
Token ID74
Feature activation+1.91e-01

Pos logit contributions
obar+0.069
rane+0.068
minist+0.063
oba+0.063
ega+0.061
Neg logit contributions
 Lauder-0.041
 Sioux-0.035
 Loving-0.035
 Hots-0.031
 Subtle-0.031
Token talk
Token ID1561
Feature activation+1.84e-02

Pos logit contributions
 Lauder+0.320
 Loving+0.293
 Sioux+0.290
 Hots+0.274
 Subtle+0.270
Neg logit contributions
obar-0.268
rane-0.261
minist-0.237
oba-0.229
ega-0.226
Token about
Token ID546
Feature activation-2.80e-01

Pos logit contributions
obar+0.038
rane+0.037
minist+0.034
oba+0.033
ega+0.033
Neg logit contributions
 Lauder-0.027
 Loving-0.024
 Sioux-0.024
 Hots-0.022
 Subtle-0.022
Token
Token ID564
Feature activation-4.82e-02

Pos logit contributions
 Lauder+0.460
 Loving+0.415
 Sioux+0.412
 Hots+0.380
 Subtle+0.376
Neg logit contributions
obar-0.524
rane-0.509
minist-0.470
oba-0.457
ega-0.452
Token
Token ID246
Feature activation+1.23e-01

Pos logit contributions
 Lauder+0.086
 Sioux+0.079
 Loving+0.078
 Hots+0.072
 Subtle+0.072
Neg logit contributions
obar-0.084
rane-0.081
minist-0.074
oba-0.072
ega-0.070
Tokenpass
Token ID6603
Feature activation+2.14e-01

Pos logit contributions
obar+0.217
rane+0.210
minist+0.195
oba+0.189
ega+0.185
Neg logit contributions
 Lauder-0.217
 Loving-0.197
 Sioux-0.196
 Hots-0.182
 Subtle-0.180
Tokenporting
Token ID26527
Feature activation-1.67e+00

Pos logit contributions
obar+0.378
rane+0.363
minist+0.335
oba+0.329
ega+0.324
Neg logit contributions
 Lauder-0.376
 Loving-0.339
 Sioux-0.338
 Hots-0.316
 Subtle-0.311
Token
Token ID447
Feature activation-7.15e-02

Pos logit contributions
 Lauder+2.570
 Loving+2.310
 Sioux+2.268
 Hots+2.111
 Sikh+2.074
Neg logit contributions
obar-3.276
rane-3.185
minist-2.930
oba-2.886
ega-2.840
Token
Token ID247
Feature activation-1.07e-01

Pos logit contributions
 Lauder+0.126
 Loving+0.114
 Sioux+0.113
 Hots+0.104
 Subtle+0.103
Neg logit contributions
obar-0.127
rane-0.122
minist-0.112
oba-0.110
ega-0.108
Token of
Token ID286
Feature activation-7.44e-02

Pos logit contributions
 Lauder+0.179
 Loving+0.161
 Sioux+0.159
 Hots+0.148
 Subtle+0.146
Neg logit contributions
obar-0.198
rane-0.192
minist-0.178
oba-0.173
ega-0.170
Token the
Token ID262
Feature activation-5.13e-02

Pos logit contributions
 Lauder+0.126
 Loving+0.114
 Sioux+0.113
 Hots+0.105
 Subtle+0.104
Neg logit contributions
obar-0.136
rane-0.132
minist-0.122
oba-0.118
ega-0.117
Token financial
Token ID3176
Feature activation+2.75e-01

Pos logit contributions
 Lauder+0.085
 Loving+0.077
 Sioux+0.076
 Hots+0.071
 Subtle+0.070
Neg logit contributions
obar-0.095
rane-0.092
minist-0.085
oba-0.083
ega-0.082
Token childhood
Token ID9963
Feature activation+3.14e-01

Pos logit contributions
obar+0.022
rane+0.021
minist+0.019
oba+0.019
ega+0.019
Neg logit contributions
 Lauder-0.019
 Loving-0.017
 Sioux-0.017
 Hots-0.016
 Subtle-0.016
Token,
Token ID11
Feature activation+7.45e-02

Pos logit contributions
obar+0.584
rane+0.564
minist+0.524
oba+0.508
ega+0.502
Neg logit contributions
 Lauder-0.518
 Loving-0.462
 Sioux-0.460
 Hots-0.428
 Subtle-0.424
Token and
Token ID290
Feature activation+9.02e-02

Pos logit contributions
obar+0.143
rane+0.137
minist+0.126
oba+0.124
ega+0.121
Neg logit contributions
 Lauder-0.121
 Loving-0.107
 Sioux-0.107
 Hots-0.099
 Subtle-0.097
Token a
Token ID257
Feature activation+9.44e-02

Pos logit contributions
obar+0.184
rane+0.178
minist+0.165
oba+0.162
ega+0.159
Neg logit contributions
 Lauder-0.134
 Loving-0.119
 Sioux-0.117
 Hots-0.109
 Sikh-0.106
Token "
Token ID366
Feature activation+5.55e-02

Pos logit contributions
obar+0.226
rane+0.220
minist+0.207
oba+0.204
ega+0.201
Neg logit contributions
 Lauder-0.106
 Loving-0.089
 Sioux-0.088
 Hots-0.080
 Subtle-0.077
TokenGirl
Token ID24151
Feature activation-1.66e+00

Pos logit contributions
obar+0.100
rane+0.097
minist+0.090
oba+0.088
ega+0.086
Neg logit contributions
 Lauder-0.095
 Loving-0.085
 Sioux-0.085
 Hots-0.079
 Subtle-0.078
Token"
Token ID1
Feature activation-6.94e-01

Pos logit contributions
 Lauder+2.793
 Loving+2.607
 Sioux+2.537
 Hots+2.362
 Sikh+2.302
Neg logit contributions
obar-2.990
rane-2.891
minist-2.684
oba-2.610
ega-2.536
Token side
Token ID1735
Feature activation-3.73e-01

Pos logit contributions
 Lauder+1.156
 Loving+1.050
 Sioux+1.036
 Hots+0.964
 Sikh+0.945
Neg logit contributions
obar-1.285
rane-1.245
minist-1.146
oba-1.122
ega-1.103
Token,
Token ID11
Feature activation+8.13e-02

Pos logit contributions
 Lauder+0.606
 Loving+0.545
 Sioux+0.538
 Hots+0.501
 Subtle+0.492
Neg logit contributions
obar-0.709
rane-0.686
minist-0.633
oba-0.620
ega-0.612
Token for
Token ID329
Feature activation+1.02e-01

Pos logit contributions
obar+0.148
rane+0.142
minist+0.131
oba+0.127
ega+0.127
Neg logit contributions
 Lauder-0.139
 Loving-0.124
 Sioux-0.123
 Hots-0.115
 Subtle-0.115
Token the
Token ID262
Feature activation+5.79e-02

Pos logit contributions
obar+0.185
rane+0.179
minist+0.165
oba+0.161
ega+0.158
Neg logit contributions
 Lauder-0.172
 Loving-0.155
 Sioux-0.154
 Hots-0.145
 Sikh-0.142
Token devoid
Token ID34065
Feature activation+1.38e-01

Pos logit contributions
 Lauder+0.610
 Loving+0.547
 Sioux+0.539
 Hots+0.501
 Subtle+0.497
Neg logit contributions
obar-0.706
rane-0.680
minist-0.637
oba-0.616
ega-0.608
Token of
Token ID286
Feature activation+2.31e-01

Pos logit contributions
obar+0.300
rane+0.292
minist+0.272
oba+0.268
ega+0.264
Neg logit contributions
 Lauder-0.184
 Loving-0.163
 Sioux-0.160
 Hots-0.146
 Subtle-0.142
Token social
Token ID1919
Feature activation+6.25e-02

Pos logit contributions
obar+0.425
rane+0.413
minist+0.384
oba+0.375
ega+0.368
Neg logit contributions
 Lauder-0.381
 Loving-0.338
 Sioux-0.336
 Hots-0.317
 Subtle-0.308
Token content
Token ID2695
Feature activation-2.51e-01

Pos logit contributions
obar+0.110
rane+0.106
minist+0.098
oba+0.096
ega+0.094
Neg logit contributions
 Lauder-0.110
 Loving-0.099
 Sioux-0.098
 Hots-0.092
 Subtle-0.091
Token.
Token ID13
Feature activation+7.65e-02

Pos logit contributions
 Lauder+0.412
 Loving+0.370
 Sioux+0.368
 Hots+0.343
 Subtle+0.335
Neg logit contributions
obar-0.474
rane-0.458
minist-0.425
oba-0.415
ega-0.407
Token Trotsky
Token ID32706
Feature activation-1.66e+00

Pos logit contributions
obar+0.141
rane+0.136
minist+0.126
oba+0.124
ega+0.121
Neg logit contributions
 Lauder-0.124
 Sioux-0.109
 Loving-0.109
 Hots-0.101
 Sikh-0.099
Tokenism
Token ID1042
Feature activation+2.08e-01

Pos logit contributions
 Lauder+2.435
 Loving+2.174
 Sioux+2.138
 Hots+1.969
 Subtle+1.928
Neg logit contributions
obar-3.414
rane-3.313
minist-3.082
oba-3.021
ega-2.978
Token is
Token ID318
Feature activation+1.66e-01

Pos logit contributions
obar+0.388
rane+0.374
minist+0.349
oba+0.340
ega+0.337
Neg logit contributions
 Lauder-0.342
 Loving-0.309
 Sioux-0.303
 Hots-0.279
 Subtle-0.278
Token a
Token ID257
Feature activation+6.87e-02

Pos logit contributions
obar+0.323
rane+0.310
minist+0.292
oba+0.283
ega+0.277
Neg logit contributions
 Lauder-0.262
 Loving-0.236
 Sioux-0.230
 Hots-0.214
 Subtle-0.210
Token religion
Token ID5737
Feature activation-3.35e-01

Pos logit contributions
obar+0.131
rane+0.127
minist+0.119
oba+0.116
ega+0.114
Neg logit contributions
 Lauder-0.110
 Loving-0.098
 Sioux-0.096
 Hots-0.090
 Subtle-0.089
Token trip
Token ID5296
Feature activation-1.07e-01

Pos logit contributions
 Lauder+0.544
 Loving+0.486
 Sioux+0.481
 Hots+0.445
 Subtle+0.440
Neg logit contributions
obar-0.645
rane-0.618
minist-0.578
oba-0.562
ega-0.556
Token
Token ID447
Feature activation+6.60e-02

Pos logit contributions
 Lauder+0.229
 Loving+0.204
 Sioux+0.200
 Hots+0.184
 Subtle+0.180
Neg logit contributions
obar-0.344
rane-0.334
minist-0.311
oba-0.305
ega-0.301
Token
Token ID250
Feature activation-1.15e-01

Pos logit contributions
obar+0.112
rane+0.106
minist+0.096
oba+0.096
ega+0.093
Neg logit contributions
 Lauder-0.122
 Sioux-0.112
 Loving-0.109
 Hots-0.102
 Sikh-0.101
TokenWhen
Token ID2215
Feature activation-6.40e-01

Pos logit contributions
 Lauder+0.229
 Loving+0.209
 Sioux+0.209
 Hots+0.196
 Sikh+0.193
Neg logit contributions
obar-0.175
rane-0.169
minist-0.154
oba-0.150
ega-0.146
Token a
Token ID257
Feature activation-1.80e-01

Pos logit contributions
 Lauder+1.017
 Loving+0.909
 Sioux+0.907
 Hots+0.837
 Subtle+0.823
Neg logit contributions
obar-1.235
rane-1.197
minist-1.106
oba-1.084
ega-1.070
Token lady
Token ID10846
Feature activation-8.32e-01

Pos logit contributions
 Lauder+0.249
 Loving+0.218
 Sioux+0.217
 Hots+0.198
 Subtle+0.193
Neg logit contributions
obar-0.380
rane-0.369
minist-0.347
oba-0.342
ega-0.336
Token politely
Token ID34313
Feature activation-1.66e+00

Pos logit contributions
 Lauder+1.348
 Loving+1.212
 Sioux+1.204
 Hots+1.108
 Subtle+1.099
Neg logit contributions
obar-1.583
rane-1.535
minist-1.419
oba-1.387
ega-1.375
Token declines
Token ID24459
Feature activation-2.99e-01

Pos logit contributions
 Lauder+2.620
 Loving+2.351
 Sioux+2.325
 Hots+2.150
 Subtle+2.116
Neg logit contributions
obar-3.228
rane-3.127
minist-2.895
oba-2.839
ega-2.803
Token to
Token ID284
Feature activation-1.16e-01

Pos logit contributions
 Lauder+0.476
 Loving+0.423
 Sioux+0.421
 Hots+0.390
 Subtle+0.382
Neg logit contributions
obar-0.577
rane-0.556
minist-0.516
ega-0.505
oba-0.505
Token dance
Token ID9280
Feature activation-9.86e-01

Pos logit contributions
 Lauder+0.213
 Loving+0.194
 Sioux+0.192
 Hots+0.179
 Subtle+0.178
Neg logit contributions
obar-0.194
rane-0.187
minist-0.170
oba-0.168
ega-0.165
Token with
Token ID351
Feature activation-1.34e-01

Pos logit contributions
 Lauder+1.590
 Loving+1.432
 Sioux+1.411
 Hots+1.309
 Subtle+1.289
Neg logit contributions
obar-1.886
rane-1.822
minist-1.687
oba-1.650
ega-1.630
Token you
Token ID345
Feature activation-7.27e-02

Pos logit contributions
 Lauder+0.218
 Loving+0.196
 Sioux+0.194
 Hots+0.179
 Subtle+0.177
Neg logit contributions
obar-0.253
rane-0.244
minist-0.224
oba-0.221
ega-0.218
Token prime
Token ID6994
Feature activation+1.60e-01

Pos logit contributions
 Lauder+0.238
 Loving+0.217
 Sioux+0.213
 Hots+0.199
 Subtle+0.198
Neg logit contributions
obar-0.238
rane-0.233
minist-0.213
oba-0.208
ega-0.205
Token minister
Token ID5342
Feature activation+9.44e-02

Pos logit contributions
obar+0.222
rane+0.211
minist+0.197
oba+0.186
ega+0.182
Neg logit contributions
 Lauder-0.337
 Loving-0.311
 Sioux-0.310
 Subtle-0.293
 Hots-0.293
Token should
Token ID815
Feature activation+9.10e-01

Pos logit contributions
obar+0.175
rane+0.169
minist+0.154
oba+0.152
ega+0.152
Neg logit contributions
 Lauder-0.155
 Loving-0.140
 Sioux-0.139
 Subtle-0.130
 Hots-0.126
Token take
Token ID1011
Feature activation+1.19e-01

Pos logit contributions
obar+1.594
rane+1.552
oba+1.408
minist+1.407
ega+1.394
Neg logit contributions
 Lauder-1.621
 Loving-1.458
 Sioux-1.435
 Subtle-1.336
 Hots-1.319
Token Mr
Token ID1770
Feature activation-5.83e-01

Pos logit contributions
obar+0.218
rane+0.212
minist+0.195
ega+0.191
oba+0.191
Neg logit contributions
 Lauder-0.199
 Loving-0.178
 Sioux-0.176
 Hots-0.164
 Subtle-0.162
Token Hes
Token ID44773
Feature activation-1.66e+00

Pos logit contributions
 Lauder+0.830
 Loving+0.737
 Sioux+0.727
 Hots+0.667
 Subtle+0.652
Neg logit contributions
obar-1.223
rane-1.190
minist-1.105
oba-1.086
ega-1.072
Tokenelt
Token ID2120
Feature activation-5.56e-01

Pos logit contributions
 Lauder+2.104
 Loving+1.844
 Sioux+1.808
 Hots+1.643
 Subtle+1.598
Neg logit contributions
obar-3.731
rane-3.631
minist-3.396
oba-3.339
ega-3.296
Tokenine
Token ID500
Feature activation-1.80e-01

Pos logit contributions
 Lauder+0.879
 Loving+0.791
 Sioux+0.785
 Hots+0.732
 Subtle+0.715
Neg logit contributions
obar-1.084
rane-1.063
minist-0.975
oba-0.958
ega-0.953
Token's
Token ID338
Feature activation-4.29e-02

Pos logit contributions
 Lauder+0.297
 Loving+0.269
 Sioux+0.263
 Hots+0.244
 Subtle+0.243
Neg logit contributions
obar-0.340
rane-0.328
minist-0.303
oba-0.297
ega-0.295
Token comments
Token ID3651
Feature activation-5.03e-01

Pos logit contributions
 Lauder+0.084
 Loving+0.076
 Sioux+0.075
 Hots+0.071
 Subtle+0.070
Neg logit contributions
obar-0.067
rane-0.065
minist-0.059
oba-0.058
ega-0.056
Token "
Token ID366
Feature activation-1.84e-01

Pos logit contributions
 Lauder+0.787
 Loving+0.702
 Sioux+0.694
 Hots+0.640
 Subtle+0.634
Neg logit contributions
obar-0.988
rane-0.954
minist-0.884
oba-0.867
ega-0.858
Token ap
Token ID2471
Feature activation-2.60e-01

Pos logit contributions
 Lauder+0.570
 Loving+0.516
 Sioux+0.509
 Hots+0.476
 Subtle+0.464
Neg logit contributions
obar-0.617
rane-0.594
minist-0.546
oba-0.534
ega-0.527
Token =
Token ID796
Feature activation-4.56e-01

Pos logit contributions
 Lauder+0.425
 Loving+0.381
 Sioux+0.377
 Hots+0.350
 Subtle+0.343
Neg logit contributions
obar-0.498
rane-0.480
minist-0.442
oba-0.435
ega-0.430
Token arg
Token ID1822
Feature activation-9.18e-01

Pos logit contributions
 Lauder+0.822
 Loving+0.746
 Sioux+0.740
 Hots+0.688
 Subtle+0.676
Neg logit contributions
obar-0.787
rane-0.759
minist-0.692
oba-0.679
ega-0.669
Tokenparse
Token ID29572
Feature activation-3.66e-01

Pos logit contributions
 Lauder+2.017
 Loving+1.870
 Sioux+1.856
 Hots+1.761
 Subtle+1.734
Neg logit contributions
obar-1.226
rane-1.172
minist-1.042
oba-1.010
ega-0.986
Token.
Token ID13
Feature activation-2.67e-01

Pos logit contributions
 Lauder+0.607
 Loving+0.549
 Sioux+0.540
 Hots+0.501
 Subtle+0.494
Neg logit contributions
obar-0.688
rane-0.665
minist-0.611
oba-0.599
ega-0.597
TokenArg
Token ID28100
Feature activation-1.66e+00

Pos logit contributions
 Lauder+0.381
 Loving+0.338
 Sioux+0.333
 Hots+0.306
 Subtle+0.299
Neg logit contributions
obar-0.560
rane-0.544
minist-0.506
oba-0.497
ega-0.490
Tokenument
Token ID1713
Feature activation-4.72e-01

Pos logit contributions
 Lauder+2.510
 Loving+2.240
 Sioux+2.197
 Hots+2.028
 Sikh+1.992
Neg logit contributions
obar-3.277
rane-3.195
minist-2.957
oba-2.911
ega-2.863
TokenParser
Token ID46677
Feature activation-7.51e-01

Pos logit contributions
 Lauder+0.985
 Loving+0.911
 Sioux+0.901
 Hots+0.854
 Subtle+0.841
Neg logit contributions
obar-0.677
rane-0.649
minist-0.582
oba-0.566
ega-0.554
Token()
Token ID3419
Feature activation-9.16e-01

Pos logit contributions
 Lauder+1.449
 Loving+1.331
 Sioux+1.316
 Hots+1.239
 Subtle+1.220
Neg logit contributions
obar-1.196
rane-1.151
minist-1.045
oba-1.017
ega-1.001
Token ap
Token ID2471
Feature activation-3.02e-01

Pos logit contributions
 Lauder+1.364
 Loving+1.219
 Sioux+1.200
 Hots+1.108
 Subtle+1.084
Neg logit contributions
obar-1.864
rane-1.808
minist-1.678
oba-1.647
ega-1.623
Token.
Token ID13
Feature activation-1.59e-01

Pos logit contributions
 Lauder+0.519
 Loving+0.469
 Sioux+0.463
 Hots+0.432
 Subtle+0.425
Neg logit contributions
obar-0.550
rane-0.530
minist-0.488
oba-0.477
ega-0.471
Tokenakh
Token ID11322
Feature activation+6.13e-02

Pos logit contributions
 Lauder+0.403
 Loving+0.372
 Sioux+0.369
 Hots+0.351
 Subtle+0.349
Neg logit contributions
obar-0.229
rane-0.215
minist-0.189
oba-0.187
ega-0.178
Tokenno
Token ID3919
Feature activation-2.95e-01

Pos logit contributions
obar+0.111
rane+0.107
minist+0.098
oba+0.097
ega+0.094
Neg logit contributions
 Lauder-0.107
 Loving-0.096
 Sioux-0.096
 Hots-0.090
 Sikh-0.088
Token against
Token ID1028
Feature activation+1.29e-01

Pos logit contributions
 Lauder+0.471
 Loving+0.424
 Sioux+0.415
 Hots+0.385
 Subtle+0.383
Neg logit contributions
obar-0.568
rane-0.547
minist-0.509
oba-0.497
ega-0.489
Token Lenin
Token ID22899
Feature activation-5.32e-01

Pos logit contributions
obar+0.254
rane+0.245
minist+0.229
oba+0.225
ega+0.221
Neg logit contributions
 Lauder-0.198
 Loving-0.178
 Sioux-0.173
 Hots-0.160
 Subtle-0.160
Token and
Token ID290
Feature activation-6.97e-02

Pos logit contributions
 Lauder+0.801
 Loving+0.717
 Sioux+0.703
 Hots+0.648
 Subtle+0.640
Neg logit contributions
obar-1.075
rane-1.039
minist-0.969
oba-0.948
ega-0.934
Token Trotsky
Token ID32706
Feature activation-1.64e+00

Pos logit contributions
 Lauder+0.090
 Loving+0.079
 Sioux+0.077
 Subtle+0.070
 Hots+0.069
Neg logit contributions
obar-0.154
rane-0.150
minist-0.141
oba-0.138
ega-0.136
Token,
Token ID11
Feature activation-1.70e-02

Pos logit contributions
 Lauder+2.589
 Loving+2.331
 Sioux+2.298
 Hots+2.134
 Subtle+2.087
Neg logit contributions
obar-3.199
rane-3.101
minist-2.869
oba-2.810
ega-2.768
Token
Token ID198
Feature activation-2.75e-01

Pos logit contributions
 Lauder+0.027
 Loving+0.024
 Sioux+0.023
 Hots+0.022
 Subtle+0.022
Neg logit contributions
obar-0.033
rane-0.032
minist-0.030
oba-0.029
ega-0.028
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 Lauder+0.477
 Loving+0.421
 Sioux+0.420
 Hots+0.392
 Subtle+0.387
Neg logit contributions
obar-0.495
rane-0.479
minist-0.441
oba-0.432
ega-0.424
Tokenfor
Token ID1640
Feature activation+2.54e-01

Pos logit contributions
 Lauder+0.437
 Loving+0.397
 Sioux+0.392
 Hots+0.367
 Subtle+0.362
Neg logit contributions
obar-0.435
rane-0.420
minist-0.388
oba-0.376
ega-0.369
Token worldwide
Token ID8688
Feature activation-6.59e-01

Pos logit contributions
obar+0.493
rane+0.474
minist+0.443
oba+0.432
ega+0.423
Neg logit contributions
 Lauder-0.401
 Loving-0.356
 Sioux-0.355
 Hots-0.328
 Subtle-0.324
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
obar+0.934
rane+0.902
minist+0.833
oba+0.813
ega+0.800
Neg logit contributions
 Lauder-0.876
 Loving-0.797
 Sioux-0.784
 Hots-0.733
 Subtle-0.722
Token government
Token ID1230
Feature activation+2.68e-01

Pos logit contributions
obar+0.273
rane+0.262
minist+0.246
oba+0.238
ega+0.234
Neg logit contributions
 Lauder-0.219
 Loving-0.198
 Sioux-0.193
 Subtle-0.178
 Hots-0.178
Token worked
Token ID3111
Feature activation-1.84e-01

Pos logit contributions
obar+0.524
rane+0.503
minist+0.470
oba+0.459
ega+0.451
Neg logit contributions
 Lauder-0.415
 Loving-0.381
 Sioux-0.369
 Subtle-0.342
 Hots-0.337
Token with
Token ID351
Feature activation+3.03e-02

Pos logit contributions
 Lauder+0.299
 Loving+0.270
 Sioux+0.265
 Hots+0.246
 Subtle+0.245
Neg logit contributions
obar-0.349
rane-0.335
minist-0.314
oba-0.303
ega-0.300
Token Exxon
Token ID27879
Feature activation-6.49e-01

Pos logit contributions
obar+0.063
rane+0.060
minist+0.057
oba+0.056
ega+0.055
Neg logit contributions
 Lauder-0.044
 Loving-0.039
 Sioux-0.038
 Hots-0.035
 Subtle-0.035
TokenMobil
Token ID47100
Feature activation-1.64e+00

Pos logit contributions
 Lauder+0.916
 Loving+0.817
 Sioux+0.800
 Hots+0.735
 Subtle+0.721
Neg logit contributions
obar-1.372
rane-1.327
minist-1.239
oba-1.216
ega-1.197
Token and
Token ID290
Feature activation+1.30e-02

Pos logit contributions
 Lauder+2.492
 Loving+2.230
 Sioux+2.204
 Hots+2.039
 Subtle+1.988
Neg logit contributions
obar-3.287
rane-3.194
minist-2.955
oba-2.902
ega-2.859
Token Chevron
Token ID50083
Feature activation-3.92e-01

Pos logit contributions
obar+0.025
rane+0.024
minist+0.023
oba+0.022
ega+0.022
Neg logit contributions
 Lauder-0.020
 Loving-0.018
 Sioux-0.018
 Hots-0.017
 Subtle-0.017
Token,
Token ID11
Feature activation+1.20e-01

Pos logit contributions
 Lauder+0.614
 Loving+0.555
 Sioux+0.540
 Hots+0.499
 Sikh+0.497
Neg logit contributions
obar-0.769
rane-0.742
minist-0.690
oba-0.674
ega-0.664
Token the
Token ID262
Feature activation+9.93e-02

Pos logit contributions
obar+0.228
rane+0.218
minist+0.204
oba+0.197
ega+0.195
Neg logit contributions
 Lauder-0.194
 Loving-0.177
 Sioux-0.173
 Subtle-0.160
 Hots-0.160
Token two
Token ID734
Feature activation+3.21e-01

Pos logit contributions
obar+0.186
rane+0.179
minist+0.166
oba+0.163
ega+0.160
Neg logit contributions
 Lauder-0.160
 Loving-0.147
 Sioux-0.142
 Hots-0.133
 Subtle-0.133
Token Temple
Token ID10857
Feature activation-3.64e-01

Pos logit contributions
obar+0.726
rane+0.704
minist+0.657
oba+0.645
ega+0.635
Neg logit contributions
 Lauder-0.537
 Loving-0.476
 Sioux-0.469
 Hots-0.434
 Subtle-0.423
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
 Lauder+0.551
 Loving+0.496
 Sioux+0.488
 Hots+0.452
 Sikh+0.445
Neg logit contributions
obar-0.729
rane-0.707
minist-0.655
oba-0.643
ega-0.632
Token
Token ID198
Feature activation-1.12e-01

Pos logit contributions
 Lauder+0.223
 Loving+0.197
 Sioux+0.197
 Hots+0.182
 Subtle+0.181
Neg logit contributions
obar-0.235
rane-0.228
minist-0.209
oba-0.206
ega-0.202
TokenAddress
Token ID20231
Feature activation-2.88e-01

Pos logit contributions
 Lauder+0.221
 Loving+0.201
 Sioux+0.200
 Hots+0.186
 Subtle+0.185
Neg logit contributions
obar-0.173
rane-0.168
minist-0.151
oba-0.148
ega-0.145
Token:
Token ID25
Feature activation-2.13e-01

Pos logit contributions
 Lauder+0.482
 Loving+0.428
 Sioux+0.426
 Hots+0.394
 Subtle+0.388
Neg logit contributions
obar-0.533
rane-0.514
minist-0.473
oba-0.466
ega-0.459
Token Sector
Token ID25892
Feature activation+1.08e+00

Pos logit contributions
 Lauder+0.327
 Loving+0.293
 Sioux+0.287
 Hots+0.268
 Subtle+0.263
Neg logit contributions
obar-0.421
rane-0.407
minist-0.374
oba-0.371
ega-0.367
Token 20
Token ID1160
Feature activation+2.15e-02

Pos logit contributions
obar+2.046
rane+1.980
oba+1.794
minist+1.778
ega+1.776
Neg logit contributions
 Lauder-1.729
 Loving-1.557
 Sioux-1.526
 Hots-1.429
 Subtle-1.392
Token,
Token ID11
Feature activation+7.06e-03

Pos logit contributions
obar+0.040
rane+0.039
minist+0.036
oba+0.035
ega+0.035
Neg logit contributions
 Lauder-0.035
 Loving-0.032
 Sioux-0.031
 Hots-0.029
 Subtle-0.029
TokenJ
Token ID41
Feature activation-3.56e-01

Pos logit contributions
obar+0.014
rane+0.014
minist+0.012
oba+0.012
ega+0.012
Neg logit contributions
 Lauder-0.011
 Loving-0.010
 Sioux-0.009
 Hots-0.009
 Subtle-0.009
Token Road
Token ID5567
Feature activation+1.33e-01

Pos logit contributions
 Lauder+0.662
 Loving+0.602
 Sioux+0.595
 Hots+0.564
 Subtle+0.552
Neg logit contributions
obar-0.603
rane-0.579
minist-0.523
oba-0.517
ega-0.510
Token,
Token ID11
Feature activation+1.73e-03

Pos logit contributions
obar+0.254
rane+0.246
minist+0.227
oba+0.223
ega+0.220
Neg logit contributions
 Lauder-0.217
 Loving-0.195
 Sioux-0.192
 Hots-0.179
 Subtle-0.175
Tokenboards
Token ID12821
Feature activation+1.39e-01

Pos logit contributions
 Lauder+0.597
 Loving+0.539
 Sioux+0.535
 Hots+0.499
 Subtle+0.490
Neg logit contributions
obar-0.667
rane-0.644
minist-0.593
oba-0.582
ega-0.572
Token offer
Token ID2897
Feature activation+3.22e-02

Pos logit contributions
obar+0.248
rane+0.239
minist+0.220
ega+0.215
oba+0.215
Neg logit contributions
 Lauder-0.238
 Loving-0.216
 Sioux-0.214
 Hots-0.198
 Subtle-0.197
Token help
Token ID1037
Feature activation+7.72e-02

Pos logit contributions
obar+0.061
rane+0.059
minist+0.055
oba+0.053
ega+0.053
Neg logit contributions
 Lauder-0.052
 Loving-0.047
 Sioux-0.046
 Hots-0.043
 Subtle-0.043
Token with
Token ID351
Feature activation-1.62e-01

Pos logit contributions
obar+0.144
rane+0.140
minist+0.131
oba+0.126
ega+0.125
Neg logit contributions
 Lauder-0.127
 Loving-0.115
 Sioux-0.114
 Hots-0.105
 Subtle-0.105
Token beating
Token ID11226
Feature activation-5.11e-01

Pos logit contributions
 Lauder+0.275
 Loving+0.249
 Sioux+0.246
 Subtle+0.229
 Hots+0.229
Neg logit contributions
obar-0.293
rane-0.284
minist-0.263
oba-0.255
ega-0.251
Token alcohol
Token ID5548
Feature activation+1.10e+00

Pos logit contributions
 Lauder+0.832
 Loving+0.748
 Sioux+0.738
 Hots+0.687
 Subtle+0.681
Neg logit contributions
obar-0.969
rane-0.934
minist-0.864
oba-0.844
ega-0.832
Token or
Token ID393
Feature activation-2.02e-01

Pos logit contributions
obar+2.028
rane+1.925
minist+1.805
oba+1.771
ega+1.747
Neg logit contributions
 Lauder-1.829
 Loving-1.656
 Sioux-1.652
 Subtle-1.513
 Hots-1.508
Token avoiding
Token ID14928
Feature activation+8.72e-01

Pos logit contributions
 Lauder+0.322
 Loving+0.290
 Sioux+0.288
 Hots+0.267
 Subtle+0.264
Neg logit contributions
obar-0.387
rane-0.374
minist-0.346
oba-0.338
ega-0.333
Token d
Token ID288
Feature activation-1.40e-01

Pos logit contributions
obar+1.610
rane+1.542
minist+1.448
oba+1.386
ega+1.375
Neg logit contributions
 Lauder-1.433
 Loving-1.282
 Sioux-1.267
 Subtle-1.195
 Hots-1.194
Tokeneng
Token ID1516
Feature activation-2.39e-01

Pos logit contributions
 Lauder+0.254
 Loving+0.231
 Sioux+0.229
 Hots+0.215
 Subtle+0.212
Neg logit contributions
obar-0.240
rane-0.231
minist-0.212
oba-0.207
ega-0.203
Tokenue
Token ID518
Feature activation+2.68e-01

Pos logit contributions
 Lauder+0.333
 Loving+0.296
 Sioux+0.291
 Hots+0.267
 Subtle+0.261
Neg logit contributions
obar-0.510
rane-0.496
minist-0.461
oba-0.453
ega-0.447
Token Say
Token ID13816
Feature activation-3.44e-02

Pos logit contributions
 Lauder+0.004
 Loving+0.004
 Sioux+0.004
 Hots+0.003
 Subtle+0.003
Neg logit contributions
obar-0.005
rane-0.005
minist-0.004
oba-0.004
ega-0.004
Tokeny
Token ID88
Feature activation+1.39e-01

Pos logit contributions
 Lauder+0.057
 Loving+0.052
 Sioux+0.051
 Hots+0.047
 Subtle+0.047
Neg logit contributions
obar-0.065
rane-0.063
minist-0.058
oba-0.057
ega-0.056
Tokenaf
Token ID1878
Feature activation-4.21e-01

Pos logit contributions
obar+0.258
rane+0.249
minist+0.226
oba+0.225
ega+0.222
Neg logit contributions
 Lauder-0.237
 Loving-0.211
 Sioux-0.210
 Hots-0.195
 Subtle-0.193
Token.
Token ID13
Feature activation+1.01e-01

Pos logit contributions
 Lauder+0.668
 Loving+0.602
 Sioux+0.593
 Hots+0.550
 Subtle+0.540
Neg logit contributions
obar-0.814
rane-0.790
minist-0.728
oba-0.716
ega-0.705
Token Dr
Token ID1583
Feature activation+3.57e-01

Pos logit contributions
obar+0.180
rane+0.175
minist+0.159
oba+0.158
ega+0.155
Neg logit contributions
 Lauder-0.170
 Loving-0.154
 Sioux-0.152
 Hots-0.142
 Subtle-0.139
Token Abdullah
Token ID26804
Feature activation+1.04e+00

Pos logit contributions
obar+0.650
rane+0.629
minist+0.576
oba+0.567
ega+0.556
Neg logit contributions
 Lauder-0.606
 Loving-0.549
 Sioux-0.543
 Hots-0.506
 Subtle-0.498
Token has
Token ID468
Feature activation+9.47e-02

Pos logit contributions
obar+1.882
rane+1.822
minist+1.647
ega+1.633
oba+1.631
Neg logit contributions
 Lauder-1.738
 Loving-1.575
 Sioux-1.549
 Subtle-1.444
 Hots-1.417
Token been
Token ID587
Feature activation-2.45e-01

Pos logit contributions
obar+0.178
rane+0.173
minist+0.158
oba+0.156
ega+0.155
Neg logit contributions
 Lauder-0.154
 Loving-0.139
 Sioux-0.136
 Subtle-0.126
 Hots-0.125
Token publicly
Token ID7271
Feature activation-2.66e-01

Pos logit contributions
 Lauder+0.393
 Loving+0.353
 Sioux+0.348
 Subtle+0.324
 Hots+0.321
Neg logit contributions
obar-0.471
rane-0.454
minist-0.416
oba-0.409
ega-0.406
Token generous
Token ID14431
Feature activation+6.99e-01

Pos logit contributions
 Lauder+0.411
 Loving+0.367
 Sioux+0.367
 Subtle+0.339
 Hots+0.337
Neg logit contributions
obar-0.521
rane-0.505
minist-0.465
oba-0.459
ega-0.457
Token about
Token ID546
Feature activation-5.09e-02

Pos logit contributions
obar+1.305
rane+1.255
minist+1.166
ega+1.135
oba+1.128
Neg logit contributions
 Lauder-1.150
 Loving-1.029
 Sioux-1.023
 Subtle-0.954
 Hots-0.946
Token a
Token ID257
Feature activation-1.08e-01

Pos logit contributions
obar+0.291
rane+0.279
minist+0.258
oba+0.256
ega+0.250
Neg logit contributions
 Lauder-0.238
 Loving-0.211
 Sioux-0.208
 Hots-0.194
 Subtle-0.191
Token total
Token ID2472
Feature activation-4.55e-01

Pos logit contributions
 Lauder+0.195
 Loving+0.175
 Sioux+0.173
 Hots+0.162
 Subtle+0.160
Neg logit contributions
obar-0.186
rane-0.180
minist-0.164
oba-0.164
ega-0.158
Token to
Token ID284
Feature activation-1.96e-03

Pos logit contributions
 Lauder+0.759
 Loving+0.684
 Sioux+0.678
 Hots+0.629
 Subtle+0.619
Neg logit contributions
obar-0.843
rane-0.816
minist-0.750
oba-0.740
ega-0.721
Token thumb
Token ID15683
Feature activation-5.06e-01

Pos logit contributions
 Lauder+0.003
 Loving+0.003
 Sioux+0.003
 Hots+0.003
 Subtle+0.003
Neg logit contributions
obar-0.003
rane-0.003
minist-0.003
oba-0.003
ega-0.003
Token your
Token ID534
Feature activation+1.57e-01

Pos logit contributions
 Lauder+0.798
 Loving+0.719
 Sioux+0.709
 Hots+0.658
 Subtle+0.644
Neg logit contributions
obar-0.983
rane-0.954
minist-0.882
oba-0.864
ega-0.852
Token nose
Token ID9686
Feature activation+1.06e+00

Pos logit contributions
obar+0.243
rane+0.230
minist+0.210
oba+0.205
ega+0.199
Neg logit contributions
 Lauder-0.314
 Loving-0.286
 Sioux-0.279
 Hots-0.265
 Subtle-0.263
Token at
Token ID379
Feature activation+3.04e-01

Pos logit contributions
obar+2.009
rane+1.901
minist+1.788
oba+1.756
ega+1.721
Neg logit contributions
 Lauder-1.731
 Loving-1.567
 Sioux-1.537
 Hots-1.429
 Subtle-1.412
Token,
Token ID11
Feature activation+3.45e-02

Pos logit contributions
obar+0.552
rane+0.533
minist+0.495
oba+0.480
ega+0.474
Neg logit contributions
 Lauder-0.517
 Loving-0.466
 Sioux-0.457
 Hots-0.428
 Subtle-0.422
Token and
Token ID290
Feature activation-8.85e-02

Pos logit contributions
obar+0.054
rane+0.051
minist+0.047
oba+0.045
ega+0.044
Neg logit contributions
 Lauder-0.068
 Loving-0.062
 Sioux-0.061
 Hots-0.057
 Subtle-0.057
Token his
Token ID465
Feature activation-1.31e-01

Pos logit contributions
 Lauder+0.152
 Loving+0.137
 Sioux+0.134
 Hots+0.126
 Sikh+0.124
Neg logit contributions
obar-0.159
rane-0.154
minist-0.141
oba-0.138
ega-0.136
Token advanced
Token ID6190
Feature activation-3.35e-01

Pos logit contributions
 Lauder+0.224
 Loving+0.202
 Sioux+0.196
 Hots+0.185
 Subtle+0.182
Neg logit contributions
obar-0.237
rane-0.229
minist-0.210
oba-0.206
ega-0.200
Token rest
Token ID1334
Feature activation-2.60e-01

Pos logit contributions
 Lauder+0.021
 Loving+0.018
 Sioux+0.018
 Hots+0.017
 Subtle+0.017
Neg logit contributions
obar-0.026
rane-0.026
minist-0.024
oba-0.023
ega-0.023
Token is
Token ID318
Feature activation+1.62e-01

Pos logit contributions
 Lauder+0.334
 Loving+0.290
 Sioux+0.285
 Hots+0.257
 Subtle+0.251
Neg logit contributions
obar-0.586
rane-0.567
minist-0.534
oba-0.522
ega-0.515
Token history
Token ID2106
Feature activation+5.60e-01

Pos logit contributions
obar+0.248
rane+0.239
minist+0.214
oba+0.209
ega+0.206
Neg logit contributions
 Lauder-0.320
 Loving-0.293
 Sioux-0.288
 Hots-0.275
 Subtle-0.272
Token.
Token ID13
Feature activation+1.62e-01

Pos logit contributions
obar+1.014
rane+0.974
minist+0.903
oba+0.884
ega+0.874
Neg logit contributions
 Lauder-0.950
 Loving-0.858
 Sioux-0.842
 Hots-0.795
 Subtle-0.786
Token<|endoftext|>
Token ID50256
Feature activation+2.77e-01

Pos logit contributions
obar+0.300
rane+0.287
minist+0.262
oba+0.262
ega+0.258
Neg logit contributions
 Lauder-0.264
 Loving-0.235
 Sioux-0.234
 Hots-0.218
 Subtle-0.216
TokenAbout
Token ID8585
Feature activation+1.01e+00

Pos logit contributions
obar+0.453
rane+0.434
minist+0.397
oba+0.387
ega+0.379
Neg logit contributions
 Lauder-0.529
 Loving-0.482
 Sioux-0.478
 Hots-0.449
 Subtle-0.441
Token This
Token ID770
Feature activation+4.26e-01

Pos logit contributions
obar+1.903
rane+1.835
oba+1.671
minist+1.661
ega+1.643
Neg logit contributions
 Lauder-1.614
 Loving-1.440
 Sioux-1.430
 Hots-1.318
 Sikh-1.287
Token Game
Token ID3776
Feature activation+2.90e-01

Pos logit contributions
obar+0.698
rane+0.674
minist+0.607
oba+0.599
ega+0.590
Neg logit contributions
 Lauder-0.795
 Sioux-0.722
 Loving-0.719
 Hots-0.665
 Sikh-0.657
Token
Token ID198
Feature activation-6.71e-02

Pos logit contributions
obar+0.555
rane+0.537
minist+0.495
oba+0.489
ega+0.482
Neg logit contributions
 Lauder-0.462
 Loving-0.411
 Sioux-0.406
 Hots-0.377
 Sikh-0.370
Token
Token ID198
Feature activation-4.87e-02

Pos logit contributions
 Lauder+0.117
 Sioux+0.104
 Loving+0.103
 Hots+0.096
 Subtle+0.094
Neg logit contributions
obar-0.120
rane-0.116
minist-0.107
oba-0.105
ega-0.103
TokenChoose
Token ID31851
Feature activation+8.13e-02

Pos logit contributions
 Lauder+0.094
 Loving+0.086
 Sioux+0.085
 Hots+0.080
 Subtle+0.079
Neg logit contributions
obar-0.078
rane-0.075
minist-0.069
oba-0.067
ega-0.066
Tokenine
Token ID500
Feature activation-7.08e-01

Pos logit contributions
 Lauder+0.003
 Sioux+0.003
 Loving+0.003
 Hots+0.003
 Subtle+0.003
Neg logit contributions
obar-0.004
rane-0.004
minist-0.004
oba-0.004
ega-0.004
Token Page
Token ID7873
Feature activation+1.58e-01

Pos logit contributions
 Lauder+1.082
 Loving+0.971
 Sioux+0.961
 Hots+0.894
 Sikh+0.878
Neg logit contributions
obar-1.379
rane-1.336
minist-1.227
oba-1.219
ega-1.207
Token and
Token ID290
Feature activation-1.19e-01

Pos logit contributions
obar+0.311
rane+0.300
minist+0.277
oba+0.272
ega+0.272
Neg logit contributions
 Lauder-0.243
 Loving-0.216
 Sioux-0.213
 Hots-0.198
 Subtle-0.194
Token Ma
Token ID6669
Feature activation+5.35e-01

Pos logit contributions
 Lauder+0.189
 Loving+0.170
 Sioux+0.168
 Hots+0.157
 Subtle+0.155
Neg logit contributions
obar-0.224
rane-0.217
minist-0.199
oba-0.196
ega-0.194
Tokenureen
Token ID49851
Feature activation-2.65e-01

Pos logit contributions
obar+0.724
rane+0.689
minist+0.614
oba+0.601
ega+0.593
Neg logit contributions
 Lauder-1.152
 Loving-1.061
 Sioux-1.051
 Hots-1.012
 Sikh-0.996
Token St
Token ID520
Feature activation+4.55e-01

Pos logit contributions
 Lauder+0.424
 Loving+0.385
 Sioux+0.382
 Hots+0.357
 Subtle+0.350
Neg logit contributions
obar-0.496
rane-0.486
oba-0.440
minist-0.439
ega-0.431
Tokenap
Token ID499
Feature activation+1.27e-01

Pos logit contributions
obar+0.779
rane+0.755
minist+0.676
oba+0.668
ega+0.662
Neg logit contributions
 Lauder-0.826
 Loving-0.760
 Sioux-0.751
 Hots-0.708
 Subtle-0.699
Tokenleton
Token ID10565
Feature activation+6.30e-01

Pos logit contributions
obar+0.235
rane+0.229
minist+0.210
oba+0.207
ega+0.203
Neg logit contributions
 Lauder-0.212
 Loving-0.192
 Sioux-0.188
 Hots-0.177
 Subtle-0.175
Token,
Token ID11
Feature activation+6.88e-03

Pos logit contributions
obar+1.152
rane+1.110
minist+1.016
oba+1.003
ega+1.000
Neg logit contributions
 Lauder-1.039
 Loving-0.937
 Sioux-0.923
 Hots-0.850
 Sikh-0.849
Token particularly
Token ID3573
Feature activation-8.13e-02

Pos logit contributions
obar+0.013
rane+0.012
minist+0.011
oba+0.011
ega+0.011
Neg logit contributions
 Lauder-0.011
 Loving-0.010
 Sioux-0.010
 Hots-0.009
 Subtle-0.009
Token,
Token ID11
Feature activation-1.08e-01

Pos logit contributions
 Lauder+0.133
 Loving+0.119
 Sioux+0.118
 Hots+0.109
 Subtle+0.108
Neg logit contributions
obar-0.152
rane-0.147
minist-0.136
oba-0.133
ega-0.131
Token version
Token ID2196
Feature activation-5.63e-01

Pos logit contributions
obar+0.044
rane+0.043
minist+0.039
oba+0.038
ega+0.038
Neg logit contributions
 Lauder-0.044
 Loving-0.040
 Sioux-0.039
 Hots-0.036
 Subtle-0.036
Token unlocks
Token ID23872
Feature activation+3.15e-02

Pos logit contributions
 Lauder+0.991
 Loving+0.896
 Sioux+0.888
 Hots+0.826
 Subtle+0.813
Neg logit contributions
obar-0.998
rane-0.965
minist-0.881
oba-0.866
ega-0.851
Token more
Token ID517
Feature activation+6.78e-02

Pos logit contributions
obar+0.058
rane+0.057
minist+0.052
oba+0.051
ega+0.050
Neg logit contributions
 Lauder-0.052
 Loving-0.047
 Sioux-0.046
 Hots-0.043
 Sikh-0.042
Token effects
Token ID3048
Feature activation-3.92e-01

Pos logit contributions
obar+0.118
rane+0.115
minist+0.104
oba+0.102
ega+0.100
Neg logit contributions
 Lauder-0.121
 Loving-0.109
 Sioux-0.108
 Hots-0.101
 Sikh-0.099
Token and
Token ID290
Feature activation+8.94e-02

Pos logit contributions
 Lauder+0.685
 Loving+0.621
 Sioux+0.614
 Hots+0.574
 Subtle+0.564
Neg logit contributions
obar-0.698
rane-0.675
minist-0.619
oba-0.605
ega-0.595
Token frames
Token ID13431
Feature activation-7.22e-03

Pos logit contributions
obar+0.162
rane+0.157
minist+0.143
oba+0.140
ega+0.139
Neg logit contributions
 Lauder-0.152
 Loving-0.137
 Sioux-0.136
 Hots-0.127
 Sikh-0.124
Token)
Token ID8
Feature activation+1.62e-01

Pos logit contributions
 Lauder+0.013
 Loving+0.012
 Sioux+0.011
 Hots+0.011
 Sikh+0.010
Neg logit contributions
obar-0.013
rane-0.012
minist-0.011
oba-0.011
ega-0.011
Token [
Token ID685
Feature activation+1.43e-01

Pos logit contributions
obar+0.308
rane+0.299
minist+0.273
oba+0.270
ega+0.266
Neg logit contributions
 Lauder-0.260
 Loving-0.232
 Sioux-0.231
 Hots-0.214
 Sikh-0.210
TokenHome
Token ID16060
Feature activation+1.85e-01

Pos logit contributions
obar+0.241
rane+0.233
minist+0.212
oba+0.207
ega+0.204
Neg logit contributions
 Lauder-0.262
 Loving-0.238
 Sioux-0.235
 Hots-0.221
 Sikh-0.216
Tokenpage
Token ID7700
Feature activation+2.55e-01

Pos logit contributions
obar+0.328
rane+0.314
minist+0.290
oba+0.287
ega+0.278
Neg logit contributions
 Lauder-0.326
 Loving-0.292
 Sioux-0.290
 Hots-0.268
 Subtle-0.267
Token]
Token ID60
Feature activation+4.09e-01

Pos logit contributions
obar+0.452
rane+0.436
minist+0.396
oba+0.394
ega+0.387
Neg logit contributions
 Lauder-0.447
 Loving-0.399
 Sioux-0.396
 Hots-0.368
 Subtle-0.363
Token said
Token ID531
Feature activation+6.44e-01

Pos logit contributions
obar+1.010
rane+0.976
minist+0.899
oba+0.879
ega+0.867
Neg logit contributions
 Lauder-0.923
 Loving-0.836
 Sioux-0.824
 Hots-0.770
 Subtle-0.757
Token.
Token ID13
Feature activation+3.84e-01

Pos logit contributions
obar+1.145
rane+1.102
minist+1.010
oba+0.993
ega+0.979
Neg logit contributions
 Lauder-1.118
 Loving-1.013
 Sioux-0.997
 Hots-0.936
 Subtle-0.931
Token "
Token ID366
Feature activation+2.97e-01

Pos logit contributions
obar+0.992
rane+0.969
minist+0.915
oba+0.902
ega+0.892
Neg logit contributions
 Lauder-0.360
 Loving-0.300
 Sioux-0.292
 Hots-0.253
 Subtle-0.243
TokenI
Token ID40
Feature activation+2.39e-01

Pos logit contributions
obar+0.431
rane+0.415
minist+0.369
oba+0.363
ega+0.355
Neg logit contributions
 Lauder-0.611
 Loving-0.553
 Sioux-0.550
 Hots-0.522
 Sikh-0.514
Token don
Token ID836
Feature activation-5.46e-01

Pos logit contributions
obar+0.419
rane+0.406
minist+0.370
oba+0.370
ega+0.360
Neg logit contributions
 Lauder-0.422
 Loving-0.379
 Sioux-0.379
 Hots-0.350
 Subtle-0.348
Token't
Token ID470
Feature activation+8.42e-02

Pos logit contributions
 Lauder+1.006
 Loving+0.905
 Sioux+0.901
 Hots+0.842
 Subtle+0.830
Neg logit contributions
obar-0.925
rane-0.892
minist-0.814
oba-0.799
ega-0.784
Token know
Token ID760
Feature activation-3.60e-01

Pos logit contributions
obar+0.146
rane+0.140
minist+0.128
oba+0.127
ega+0.124
Neg logit contributions
 Lauder-0.153
 Loving-0.138
 Sioux-0.137
 Hots-0.127
 Subtle-0.126
Token how
Token ID703
Feature activation+1.97e-01

Pos logit contributions
 Lauder+0.626
 Loving+0.566
 Sioux+0.557
 Hots+0.523
 Subtle+0.519
Neg logit contributions
obar-0.635
rane-0.614
minist-0.560
oba-0.552
ega-0.543
Token guys
Token ID3730
Feature activation-1.57e-02

Pos logit contributions
obar+0.368
rane+0.358
minist+0.325
oba+0.321
ega+0.319
Neg logit contributions
 Lauder-0.321
 Loving-0.288
 Sioux-0.282
 Hots-0.266
 Subtle-0.261
Token on
Token ID319
Feature activation-4.90e-02

Pos logit contributions
 Lauder+0.027
 Loving+0.025
 Sioux+0.024
 Hots+0.023
 Subtle+0.022
Neg logit contributions
obar-0.028
rane-0.027
minist-0.024
oba-0.024
ega-0.024
Token either
Token ID2035
Feature activation+3.44e-01

Pos logit contributions
 Lauder+0.081
 Loving+0.073
 Sioux+0.072
 Hots+0.067
 Subtle+0.066
Neg logit contributions
obar-0.092
rane-0.088
minist-0.081
oba-0.080
ega-0.079
Token
Token ID198
Feature activation-9.36e-02

Pos logit contributions
 Lauder+0.153
 Loving+0.137
 Sioux+0.135
 Hots+0.124
 Sikh+0.123
Neg logit contributions
obar-0.177
rane-0.171
minist-0.158
oba-0.156
ega-0.152
Token
Token ID198
Feature activation-8.53e-02

Pos logit contributions
 Lauder+0.161
 Loving+0.143
 Sioux+0.142
 Hots+0.132
 Subtle+0.130
Neg logit contributions
obar-0.170
rane-0.164
minist-0.151
oba-0.148
ega-0.145
TokenC
Token ID34
Feature activation+3.98e-01

Pos logit contributions
 Lauder+0.158
 Loving+0.144
 Sioux+0.142
 Hots+0.133
 Subtle+0.132
Neg logit contributions
obar-0.143
rane-0.138
minist-0.126
oba-0.123
ega-0.120
Tokenultural
Token ID8596
Feature activation-1.89e-01

Pos logit contributions
obar+0.678
rane+0.647
minist+0.587
oba+0.583
ega+0.570
Neg logit contributions
 Lauder-0.738
 Loving-0.674
 Sioux-0.666
 Hots-0.627
 Subtle-0.616
Token
Token ID198
Feature activation-9.09e-02

Pos logit contributions
 Lauder+0.308
 Loving+0.277
 Sioux+0.274
 Hots+0.253
 Subtle+0.251
Neg logit contributions
obar-0.358
rane-0.345
minist-0.319
oba-0.313
ega-0.306
Token
Token ID198
Feature activation-7.42e-02

Pos logit contributions
 Lauder+0.157
 Loving+0.139
 Sioux+0.139
 Hots+0.129
 Subtle+0.128
Neg logit contributions
obar-0.164
rane-0.159
minist-0.146
oba-0.143
ega-0.140
TokenIf
Token ID1532
Feature activation-5.58e-02

Pos logit contributions
 Lauder+0.141
 Loving+0.129
 Sioux+0.128
 Hots+0.120
 Subtle+0.118
Neg logit contributions
obar-0.121
rane-0.116
minist-0.106
oba-0.103
ega-0.101
Token you
Token ID345
Feature activation-7.91e-02

Pos logit contributions
 Lauder+0.089
 Loving+0.080
 Sioux+0.079
 Hots+0.073
 Subtle+0.072
Neg logit contributions
obar-0.107
rane-0.104
minist-0.095
oba-0.094
ega-0.092
Token're
Token ID821
Feature activation-5.92e-02

Pos logit contributions
 Lauder+0.140
 Loving+0.126
 Sioux+0.126
 Hots+0.117
 Subtle+0.116
Neg logit contributions
obar-0.139
rane-0.135
minist-0.122
oba-0.121
ega-0.118
Token not
Token ID407
Feature activation-1.36e-01

Pos logit contributions
 Lauder+0.087
 Loving+0.077
 Sioux+0.076
 Subtle+0.070
 Hots+0.070
Neg logit contributions
obar-0.121
rane-0.118
minist-0.108
oba-0.106
ega-0.105
Token tempted
Token ID26194
Feature activation+2.15e-01

Pos logit contributions
 Lauder+0.214
 Loving+0.192
 Sioux+0.188
 Subtle+0.176
 Hots+0.176
Neg logit contributions
obar-0.265
rane-0.257
minist-0.235
oba-0.231
ega-0.228
Token page
Token ID2443
Feature activation+3.18e-03

Pos logit contributions
obar+0.188
rane+0.182
minist+0.166
oba+0.163
ega+0.160
Neg logit contributions
 Lauder-0.179
 Loving-0.160
 Sioux-0.159
 Hots-0.147
 Sikh-0.146
Token layout
Token ID12461
Feature activation+3.23e-01

Pos logit contributions
obar+0.005
rane+0.005
minist+0.005
oba+0.005
ega+0.005
Neg logit contributions
 Lauder-0.006
 Loving-0.005
 Sioux-0.005
 Hots-0.005
 Subtle-0.005
Token templates
Token ID24019
Feature activation+1.06e-03

Pos logit contributions
obar+0.554
rane+0.535
minist+0.490
oba+0.476
ega+0.468
Neg logit contributions
 Lauder-0.584
 Loving-0.522
 Sioux-0.518
 Hots-0.486
 Subtle-0.479
Token are
Token ID389
Feature activation+1.69e-01

Pos logit contributions
obar+0.002
rane+0.002
minist+0.002
oba+0.002
ega+0.002
Neg logit contributions
 Lauder-0.002
 Loving-0.002
 Sioux-0.002
 Hots-0.001
 Subtle-0.001
Token gone
Token ID3750
Feature activation+5.85e-01

Pos logit contributions
obar+0.306
rane+0.296
minist+0.268
oba+0.264
ega+0.260
Neg logit contributions
 Lauder-0.292
 Loving-0.263
 Sioux-0.259
 Hots-0.242
 Subtle-0.239
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
obar+1.063
rane+1.022
minist+0.942
oba+0.928
ega+0.913
Neg logit contributions
 Lauder-0.996
 Loving-0.899
 Sioux-0.886
 Hots-0.822
 Subtle-0.814
Token If
Token ID1002
Feature activation+8.79e-02

Pos logit contributions
obar+0.280
rane+0.270
minist+0.247
oba+0.243
ega+0.240
Neg logit contributions
 Lauder-0.250
 Loving-0.220
 Sioux-0.220
 Hots-0.201
 Sikh-0.200
Token you
Token ID345
Feature activation+1.20e-01

Pos logit contributions
obar+0.170
rane+0.165
minist+0.152
oba+0.149
ega+0.146
Neg logit contributions
 Lauder-0.140
 Loving-0.125
 Sioux-0.123
 Hots-0.114
 Sikh-0.112
Token open
Token ID1280
Feature activation-2.86e-02

Pos logit contributions
obar+0.214
rane+0.210
minist+0.190
oba+0.188
ega+0.182
Neg logit contributions
 Lauder-0.211
 Loving-0.188
 Sioux-0.187
 Hots-0.172
 Subtle-0.171
Token a
Token ID257
Feature activation+7.87e-02

Pos logit contributions
 Lauder+0.044
 Loving+0.039
 Sioux+0.038
 Hots+0.035
 Sikh+0.035
Neg logit contributions
obar-0.057
rane-0.055
minist-0.051
oba-0.050
ega-0.049
Token document
Token ID3188
Feature activation+3.87e-01

Pos logit contributions
obar+0.137
rane+0.132
minist+0.120
oba+0.118
ega+0.116
Neg logit contributions
 Lauder-0.141
 Loving-0.127
 Sioux-0.126
 Hots-0.117
 Sikh-0.115
Token Batman
Token ID9827
Feature activation-6.25e-01

Pos logit contributions
obar+0.171
rane+0.164
minist+0.151
oba+0.148
ega+0.147
Neg logit contributions
 Lauder-0.148
 Loving-0.134
 Sioux-0.132
 Hots-0.123
 Subtle-0.121
Token.
Token ID13
Feature activation-1.17e-01

Pos logit contributions
 Lauder+1.012
 Loving+0.906
 Sioux+0.897
 Hots+0.824
 Sikh+0.816
Neg logit contributions
obar-1.192
rane-1.151
minist-1.068
oba-1.044
ega-1.033
Token On
Token ID1550
Feature activation-1.21e-01

Pos logit contributions
 Lauder+0.199
 Sioux+0.178
 Loving+0.177
 Hots+0.165
 Sikh+0.160
Neg logit contributions
obar-0.209
rane-0.201
minist-0.184
oba-0.180
ega-0.180
Token the
Token ID262
Feature activation-7.91e-02

Pos logit contributions
 Lauder+0.204
 Sioux+0.182
 Loving+0.182
 Hots+0.169
 Subtle+0.166
Neg logit contributions
obar-0.225
rane-0.214
minist-0.198
oba-0.194
ega-0.189
Token other
Token ID584
Feature activation-7.16e-01

Pos logit contributions
 Lauder+0.142
 Sioux+0.128
 Loving+0.128
 Hots+0.119
 Subtle+0.117
Neg logit contributions
obar-0.136
rane-0.130
minist-0.120
oba-0.116
ega-0.115
Token hand
Token ID1021
Feature activation-2.07e-01

Pos logit contributions
 Lauder+1.405
 Loving+1.289
 Sioux+1.279
 Hots+1.211
 Subtle+1.187
Neg logit contributions
obar-1.120
rane-1.077
minist-0.971
oba-0.951
ega-0.922
Token,
Token ID11
Feature activation-1.62e-01

Pos logit contributions
 Lauder+0.331
 Loving+0.298
 Sioux+0.293
 Hots+0.273
 Subtle+0.267
Neg logit contributions
obar-0.399
rane-0.386
minist-0.357
oba-0.350
ega-0.344
Token it
Token ID340
Feature activation+1.92e-02

Pos logit contributions
 Lauder+0.254
 Loving+0.229
 Sioux+0.227
 Hots+0.211
 Subtle+0.205
Neg logit contributions
obar-0.314
rane-0.303
minist-0.278
ega-0.271
oba-0.270
Token still
Token ID991
Feature activation-8.31e-02

Pos logit contributions
obar+0.038
rane+0.037
minist+0.034
oba+0.034
ega+0.033
Neg logit contributions
 Lauder-0.029
 Loving-0.026
 Sioux-0.026
 Hots-0.023
 Subtle-0.023
Token might
Token ID1244
Feature activation+7.61e-02

Pos logit contributions
 Lauder+0.131
 Loving+0.117
 Sioux+0.115
 Subtle+0.106
 Hots+0.105
Neg logit contributions
obar-0.162
rane-0.156
minist-0.144
ega-0.142
oba-0.141
Token have
Token ID423
Feature activation+4.91e-02

Pos logit contributions
obar+0.132
rane+0.126
minist+0.115
oba+0.114
ega+0.113
Neg logit contributions
 Lauder-0.138
 Loving-0.125
 Sioux-0.123
 Hots-0.114
 Subtle-0.114
Tokenach
Token ID620
Feature activation+2.78e-01

Pos logit contributions
 Lauder+0.128
 Loving+0.118
 Sioux+0.116
 Subtle+0.110
 Hots+0.110
Neg logit contributions
obar-0.072
rane-0.068
minist-0.061
oba-0.060
ega-0.059
Token,
Token ID11
Feature activation-9.64e-03

Pos logit contributions
obar+0.519
rane+0.498
minist+0.464
oba+0.453
ega+0.442
Neg logit contributions
 Lauder-0.458
 Loving-0.419
 Sioux-0.406
 Subtle-0.380
 Hots-0.379
Token a
Token ID257
Feature activation-9.73e-02

Pos logit contributions
 Lauder+0.015
 Loving+0.014
 Sioux+0.013
 Subtle+0.012
 Hots+0.012
Neg logit contributions
obar-0.019
rane-0.018
minist-0.017
oba-0.016
ega-0.016
Token fuel
Token ID5252
Feature activation+2.64e-03

Pos logit contributions
 Lauder+0.163
 Loving+0.150
 Sioux+0.146
 Subtle+0.139
 Hots+0.137
Neg logit contributions
obar-0.177
rane-0.170
minist-0.158
oba-0.155
ega-0.151
Token supplier
Token ID22693
Feature activation-1.09e-01

Pos logit contributions
obar+0.005
rane+0.004
minist+0.004
oba+0.004
ega+0.004
Neg logit contributions
 Lauder-0.005
 Loving-0.004
 Sioux-0.004
 Hots-0.004
 Subtle-0.004
Token which
Token ID543
Feature activation-2.33e-01

Pos logit contributions
 Lauder+0.154
 Loving+0.138
 Sioux+0.134
 Subtle+0.125
 Hots+0.124
Neg logit contributions
obar-0.227
rane-0.219
minist-0.205
oba-0.200
ega-0.198
Token is
Token ID318
Feature activation+1.25e-01

Pos logit contributions
 Lauder+0.353
 Loving+0.321
 Sioux+0.312
 Subtle+0.289
 Hots+0.288
Neg logit contributions
obar-0.463
rane-0.448
minist-0.415
oba-0.410
ega-0.401
Token connected
Token ID5884
Feature activation-4.08e-01

Pos logit contributions
obar+0.268
rane+0.256
minist+0.241
oba+0.237
ega+0.234
Neg logit contributions
 Lauder-0.168
 Loving-0.152
 Sioux-0.147
 Subtle-0.138
 Hots-0.135
Token to
Token ID284
Feature activation+7.56e-02

Pos logit contributions
 Lauder+0.599
 Loving+0.530
 Sioux+0.527
 Hots+0.481
 Ku+0.472
Neg logit contributions
obar-0.840
rane-0.816
minist-0.755
oba-0.745
ega-0.731
Token Priv
Token ID9243
Feature activation+4.17e-01

Pos logit contributions
obar+0.163
rane+0.158
minist+0.148
oba+0.146
ega+0.143
Neg logit contributions
 Lauder-0.101
 Loving-0.090
 Sioux-0.088
 Hots-0.080
 Subtle-0.080
Tokenat
Token ID265
Feature activation+3.71e-02

Pos logit contributions
obar+0.845
rane+0.813
oba+0.751
minist+0.747
ega+0.729
Neg logit contributions
 Lauder-0.647
 Loving-0.578
 Sioux-0.570
 Sikh-0.517
 Subtle-0.516
Token
Token ID447
Feature activation+4.32e-02

Pos logit contributions
obar+1.414
rane+1.354
minist+1.243
oba+1.224
ega+1.202
Neg logit contributions
 Lauder-1.404
 Loving-1.272
 Sioux-1.257
 Hots-1.173
 Subtle-1.152
Token
Token ID247
Feature activation-8.23e-02

Pos logit contributions
obar+0.073
rane+0.071
minist+0.064
oba+0.062
ega+0.062
Neg logit contributions
 Lauder-0.079
 Sioux-0.073
 Loving-0.071
 Hots-0.067
 Subtle-0.065
Tokens
Token ID82
Feature activation-8.22e-02

Pos logit contributions
 Lauder+0.119
 Loving+0.106
 Sioux+0.105
 Hots+0.096
 Subtle+0.094
Neg logit contributions
obar-0.170
rane-0.165
minist-0.154
oba-0.151
ega-0.149
Token take
Token ID1011
Feature activation-5.88e-02

Pos logit contributions
 Lauder+0.153
 Loving+0.139
 Sioux+0.138
 Hots+0.128
 Subtle+0.127
Neg logit contributions
obar-0.137
rane-0.132
minist-0.120
oba-0.118
ega-0.116
Token a
Token ID257
Feature activation-4.16e-02

Pos logit contributions
 Lauder+0.090
 Loving+0.080
 Sioux+0.080
 Hots+0.073
 Sikh+0.072
Neg logit contributions
obar-0.116
rane-0.113
minist-0.104
oba-0.103
ega-0.102
Token moment
Token ID2589
Feature activation-2.19e-01

Pos logit contributions
 Lauder+0.070
 Loving+0.062
 Sioux+0.062
 Hots+0.057
 Sikh+0.056
Neg logit contributions
obar-0.075
rane-0.074
minist-0.068
oba-0.067
ega-0.066
Token to
Token ID284
Feature activation-8.50e-02

Pos logit contributions
 Lauder+0.325
 Loving+0.291
 Sioux+0.287
 Hots+0.265
 Subtle+0.258
Neg logit contributions
obar-0.444
rane-0.431
minist-0.400
oba-0.392
ega-0.386
Token discuss
Token ID2112
Feature activation+1.26e-01

Pos logit contributions
 Lauder+0.161
 Loving+0.145
 Sioux+0.144
 Hots+0.134
 Subtle+0.133
Neg logit contributions
obar-0.139
rane-0.134
minist-0.122
oba-0.120
ega-0.118
Token some
Token ID617
Feature activation-5.41e-02

Pos logit contributions
obar+0.236
rane+0.230
minist+0.214
oba+0.206
ega+0.205
Neg logit contributions
 Lauder-0.205
 Loving-0.183
 Sioux-0.181
 Hots-0.169
 Sikh-0.165
Token of
Token ID286
Feature activation-1.42e-01

Pos logit contributions
 Lauder+0.079
 Loving+0.069
 Sioux+0.068
 Hots+0.063
 Subtle+0.061
Neg logit contributions
obar-0.111
rane-0.108
minist-0.100
oba-0.098
ega-0.097
Token the
Token ID262
Feature activation-4.51e-02

Pos logit contributions
 Lauder+0.233
 Loving+0.210
 Sioux+0.207
 Hots+0.193
 Sikh+0.189
Neg logit contributions
obar-0.266
rane-0.258
minist-0.238
oba-0.232
ega-0.229
Token her
Token ID607
Feature activation-4.31e-01

Pos logit contributions
 Lauder+0.482
 Loving+0.424
 Sioux+0.421
 Hots+0.393
 Subtle+0.387
Neg logit contributions
obar-0.603
rane-0.584
minist-0.539
oba-0.530
ega-0.522
Token "
Token ID366
Feature activation-7.05e-02

Pos logit contributions
 Lauder+0.736
 Loving+0.652
 Sioux+0.646
 Hots+0.608
 Subtle+0.599
Neg logit contributions
obar-0.784
rane-0.759
minist-0.699
oba-0.684
ega-0.672
TokenLast
Token ID5956
Feature activation+5.62e-02

Pos logit contributions
 Lauder+0.129
 Loving+0.117
 Sioux+0.116
 Hots+0.109
 Subtle+0.107
Neg logit contributions
obar-0.119
rane-0.115
minist-0.106
oba-0.103
ega-0.101
Token Will
Token ID2561
Feature activation-2.33e-01

Pos logit contributions
obar+0.108
rane+0.105
minist+0.097
oba+0.096
ega+0.095
Neg logit contributions
 Lauder-0.089
 Loving-0.078
 Sioux-0.077
 Hots-0.072
 Sikh-0.070
Token and
Token ID290
Feature activation-1.61e-01

Pos logit contributions
 Lauder+0.386
 Loving+0.342
 Sioux+0.340
 Hots+0.318
 Subtle+0.314
Neg logit contributions
obar-0.434
rane-0.420
minist-0.384
oba-0.381
ega-0.376
Token Testament
Token ID18318
Feature activation-2.37e-01

Pos logit contributions
 Lauder+0.176
 Loving+0.146
 Sioux+0.144
 Hots+0.129
 Subtle+0.124
Neg logit contributions
obar-0.391
rane-0.381
minist-0.358
oba-0.354
ega-0.350
Token":
Token ID1298
Feature activation+8.67e-02

Pos logit contributions
 Lauder+0.432
 Loving+0.387
 Sioux+0.385
 Hots+0.362
 Subtle+0.357
Neg logit contributions
obar-0.402
rane-0.387
minist-0.355
oba-0.348
ega-0.343
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
obar+0.197
rane+0.192
minist+0.180
oba+0.177
ega+0.175
Neg logit contributions
 Lauder-0.108
 Loving-0.091
 Sioux-0.091
 Hots-0.083
 Subtle-0.080
Token
Token ID198
Feature activation-8.50e-02

Pos logit contributions
 Lauder+0.231
 Sioux+0.202
 Loving+0.202
 Hots+0.189
 Subtle+0.186
Neg logit contributions
obar-0.236
rane-0.228
minist-0.209
oba-0.205
ega-0.201
TokenI
Token ID40
Feature activation+2.56e-01

Pos logit contributions
 Lauder+0.165
 Loving+0.150
 Sioux+0.149
 Hots+0.141
 Subtle+0.138
Neg logit contributions
obar-0.135
rane-0.131
minist-0.119
oba-0.116
ega-0.113
Token leave
Token ID2666
Feature activation-1.66e-01

Pos logit contributions
obar+0.456
rane+0.443
minist+0.408
oba+0.400
ega+0.393
Neg logit contributions
 Lauder-0.441
 Sioux-0.393
 Loving-0.393
 Hots-0.369
 Subtle-0.362
Token for
Token ID329
Feature activation-1.73e-02

Pos logit contributions
 Lauder+0.090
 Loving+0.081
 Sioux+0.080
 Hots+0.074
 Subtle+0.073
Neg logit contributions
obar-0.104
rane-0.101
minist-0.093
oba-0.091
ega-0.090
Token it
Token ID340
Feature activation+1.66e-02

Pos logit contributions
 Lauder+0.028
 Loving+0.025
 Sioux+0.025
 Hots+0.023
 Subtle+0.023
Neg logit contributions
obar-0.033
rane-0.032
minist-0.029
oba-0.029
ega-0.028
Token first
Token ID717
Feature activation+1.49e-01

Pos logit contributions
obar+0.032
rane+0.031
minist+0.029
oba+0.028
ega+0.028
Neg logit contributions
 Lauder-0.026
 Loving-0.024
 Sioux-0.023
 Hots-0.021
 Subtle-0.021
Token came
Token ID1625
Feature activation+4.06e-01

Pos logit contributions
obar+0.277
rane+0.267
minist+0.246
oba+0.243
ega+0.240
Neg logit contributions
 Lauder-0.246
 Loving-0.222
 Sioux-0.219
 Subtle-0.203
 Hots-0.201
Token about
Token ID546
Feature activation+8.85e-02

Pos logit contributions
obar+0.806
rane+0.776
minist+0.727
oba+0.710
ega+0.707
Neg logit contributions
 Lauder-0.621
 Loving-0.556
 Sioux-0.543
 Subtle-0.509
 Hots-0.505
Token when
Token ID618
Feature activation-4.13e-01

Pos logit contributions
obar+0.156
rane+0.152
minist+0.139
oba+0.135
ega+0.134
Neg logit contributions
 Lauder-0.154
 Loving-0.139
 Sioux-0.137
 Hots-0.129
 Subtle-0.128
Token L
Token ID406
Feature activation+1.59e-01

Pos logit contributions
 Lauder+0.695
 Loving+0.627
 Sioux+0.619
 Hots+0.579
 Subtle+0.571
Neg logit contributions
obar-0.760
rane-0.734
minist-0.677
oba-0.661
ega-0.650
Token.
Token ID13
Feature activation-7.77e-02

Pos logit contributions
obar+0.288
rane+0.276
minist+0.255
oba+0.251
ega+0.245
Neg logit contributions
 Lauder-0.274
 Loving-0.249
 Sioux-0.247
 Hots-0.231
 Subtle-0.230
TokenA
Token ID32
Feature activation+5.09e-01

Pos logit contributions
 Lauder+0.160
 Loving+0.147
 Sioux+0.146
 Hots+0.139
 Subtle+0.138
Neg logit contributions
obar-0.113
rane-0.107
minist-0.095
oba-0.094
ega-0.091
Token.
Token ID13
Feature activation-2.73e-02

Pos logit contributions
obar+0.861
rane+0.828
minist+0.759
oba+0.742
ega+0.725
Neg logit contributions
 Lauder-0.931
 Loving-0.851
 Sioux-0.837
 Hots-0.789
 Subtle-0.779
Token attorney
Token ID6136
Feature activation+2.74e-01

Pos logit contributions
 Lauder+0.047
 Loving+0.042
 Sioux+0.042
 Hots+0.039
 Subtle+0.039
Neg logit contributions
obar-0.049
rane-0.047
minist-0.044
oba-0.043
ega-0.041
Token refunds
Token ID36903
Feature activation-3.81e-01

Pos logit contributions
 Lauder+0.513
 Loving+0.460
 Sioux+0.458
 Hots+0.422
 Subtle+0.417
Neg logit contributions
obar-0.570
rane-0.555
minist-0.518
oba-0.499
ega-0.492
Token work
Token ID670
Feature activation-2.26e-01

Pos logit contributions
 Lauder+0.651
 Loving+0.589
 Sioux+0.583
 Hots+0.542
 Subtle+0.534
Neg logit contributions
obar-0.694
rane-0.671
minist-0.618
oba-0.604
ega-0.595
Token);
Token ID1776
Feature activation+3.26e-01

Pos logit contributions
 Lauder+0.379
 Loving+0.341
 Sioux+0.336
 Hots+0.312
 Subtle+0.308
Neg logit contributions
obar-0.420
rane-0.406
minist-0.376
oba-0.366
ega-0.361
Token CSV
Token ID44189
Feature activation-1.41e-01

Pos logit contributions
obar+0.597
rane+0.577
minist+0.536
oba+0.519
ega+0.505
Neg logit contributions
 Lauder-0.551
 Sioux-0.493
 Loving-0.490
 Sikh-0.451
 Hots-0.450
Token (
Token ID357
Feature activation-9.86e-02

Pos logit contributions
 Lauder+0.230
 Loving+0.206
 Sioux+0.204
 Hots+0.188
 Subtle+0.186
Neg logit contributions
obar-0.267
rane-0.259
minist-0.240
oba-0.234
ega-0.231
TokenBIP
Token ID47772
Feature activation-1.26e+00

Pos logit contributions
 Lauder+0.170
 Loving+0.152
 Sioux+0.151
 Hots+0.141
 Subtle+0.138
Neg logit contributions
obar-0.179
rane-0.174
minist-0.162
oba-0.157
ega-0.154
Token68
Token ID3104
Feature activation-1.25e-01

Pos logit contributions
 Lauder+2.235
 Loving+2.041
 Sioux+2.013
 Hots+1.889
 Subtle+1.853
Neg logit contributions
obar-2.188
rane-2.113
minist-1.934
oba-1.889
ega-1.855
Token /
Token ID1220
Feature activation+1.17e+00

Pos logit contributions
 Lauder+0.201
 Loving+0.179
 Sioux+0.176
 Hots+0.163
 Subtle+0.161
Neg logit contributions
obar-0.241
rane-0.235
minist-0.217
oba-0.212
ega-0.209
Token B
Token ID347
Feature activation-5.65e-01

Pos logit contributions
obar+2.276
rane+2.210
minist+2.060
oba+2.024
ega+1.974
Neg logit contributions
 Lauder-1.797
 Sioux-1.585
 Loving-1.558
 Hots-1.443
 Sikh-1.427
TokenIP
Token ID4061
Feature activation-5.52e-01

Pos logit contributions
 Lauder+0.628
 Loving+0.535
 Sioux+0.528
 Hots+0.468
 Subtle+0.456
Neg logit contributions
obar-1.363
rane-1.331
minist-1.254
oba-1.234
ega-1.216
Token112
Token ID14686
Feature activation-1.09e-01

Pos logit contributions
 Lauder+1.002
 Loving+0.909
 Sioux+0.901
 Hots+0.842
 Subtle+0.832
Neg logit contributions
obar-0.945
rane-0.910
minist-0.833
oba-0.819
ega-0.804
Token app
Token ID598
Feature activation-4.39e-01

Pos logit contributions
obar+0.039
rane+0.037
oba+0.034
ega+0.034
minist+0.034
Neg logit contributions
 Lauder-0.025
 Loving-0.022
 Sioux-0.022
 Hots-0.020
 Subtle-0.020
Tokendata
Token ID7890
Feature activation+3.93e-02

Pos logit contributions
 Lauder+1.025
 Loving+0.957
 Sioux+0.953
 Hots+0.906
 Subtle+0.895
Neg logit contributions
obar-0.538
rane-0.503
minist-0.439
oba-0.429
ega-0.415
Token _
Token ID4808
Feature activation-1.04e-01

Pos logit contributions
obar+0.080
rane+0.077
oba+0.071
minist+0.070
ega+0.070
Neg logit contributions
 Lauder-0.058
 Sioux-0.051
 Loving-0.051
 Hots-0.046
 Subtle-0.046
Token full
Token ID1336
Feature activation-1.08e+00

Pos logit contributions
 Lauder+0.197
 Sioux+0.178
 Loving+0.177
 Hots+0.166
 Subtle+0.163
Neg logit contributions
obar-0.170
rane-0.162
minist-0.146
ega-0.144
oba-0.144
Token v
Token ID410
Feature activation-3.49e-01

Pos logit contributions
 Lauder+1.384
 Loving+1.213
 Sioux+1.192
 Hots+1.093
 Subtle+1.052
Neg logit contributions
obar-2.441
rane-2.353
minist-2.189
oba-2.171
ega-2.146
Token )
Token ID1267
Feature activation-1.26e+00

Pos logit contributions
 Lauder+0.648
 Loving+0.590
 Sioux+0.585
 Hots+0.547
 Subtle+0.542
Neg logit contributions
obar-0.581
rane-0.557
minist-0.509
oba-0.500
ega-0.490
Token {
Token ID1391
Feature activation+9.39e-02

Pos logit contributions
 Lauder+2.360
 Loving+2.158
 Sioux+2.137
 Hots+2.008
 Subtle+1.976
Neg logit contributions
obar-2.065
rane-1.988
minist-1.803
oba-1.766
ega-1.732
Token //
Token ID3373
Feature activation-3.70e-01

Pos logit contributions
obar+0.167
rane+0.161
minist+0.148
oba+0.144
ega+0.142
Neg logit contributions
 Lauder-0.164
 Loving-0.149
 Sioux-0.148
 Hots-0.138
 Sikh-0.135
Token Time
Token ID3862
Feature activation-4.11e-01

Pos logit contributions
 Lauder+0.536
 Loving+0.478
 Sioux+0.466
 Hots+0.433
 Subtle+0.425
Neg logit contributions
obar-0.768
rane-0.749
minist-0.700
oba-0.679
ega-0.671
Token component
Token ID7515
Feature activation+3.85e-02

Pos logit contributions
 Lauder+0.816
 Loving+0.752
 Sioux+0.745
 Hots+0.711
 Subtle+0.695
Neg logit contributions
obar-0.632
rane-0.601
minist-0.552
oba-0.530
ega-0.522
Token const
Token ID1500
Feature activation-4.19e-01

Pos logit contributions
obar+0.094
rane+0.091
minist+0.086
oba+0.085
ega+0.084
Neg logit contributions
 Lauder-0.042
 Loving-0.035
 Sioux-0.034
 Hots-0.029
 Subtle-0.029
Token OF
Token ID3963
Feature activation+1.67e-01

Pos logit contributions
 Lauder+0.907
 Loving+0.809
 Sioux+0.797
 Hots+0.739
 Subtle+0.720
Neg logit contributions
obar-1.189
rane-1.159
minist-1.072
oba-1.051
ega-1.038
Token TRAN
Token ID48213
Feature activation+7.62e-01

Pos logit contributions
obar+0.315
rane+0.309
minist+0.285
oba+0.278
ega+0.276
Neg logit contributions
 Lauder-0.267
 Loving-0.238
 Sioux-0.234
 Hots-0.219
 Sikh-0.212
TokenSM
Token ID12310
Feature activation-3.32e-01

Pos logit contributions
obar+1.792
rane+1.766
minist+1.641
oba+1.610
ega+1.608
Neg logit contributions
 Lauder-0.870
 Loving-0.741
 Sioux-0.729
 Hots-0.656
 Sikh-0.631
TokenISSION
Token ID40373
Feature activation+1.58e-01

Pos logit contributions
 Lauder+0.525
 Loving+0.470
 Sioux+0.463
 Hots+0.431
 Subtle+0.421
Neg logit contributions
obar-0.641
rane-0.628
minist-0.576
oba-0.565
ega-0.563
Token ///
Token ID34013
Feature activation+2.20e-02

Pos logit contributions
obar+0.292
rane+0.283
minist+0.261
oba+0.256
ega+0.252
Neg logit contributions
 Lauder-0.263
 Loving-0.237
 Sioux-0.234
 Hots-0.219
 Subtle-0.213
Token----------------------------------------------------------------
Token ID10097
Feature activation-1.22e+00

Pos logit contributions
obar+0.041
rane+0.040
minist+0.037
oba+0.036
ega+0.036
Neg logit contributions
 Lauder-0.036
 Loving-0.033
 Sioux-0.032
 Hots-0.030
 Subtle-0.029
Token----------------------------------------------------------------
Token ID10097
Feature activation-1.13e+00

Pos logit contributions
 Lauder+2.102
 Loving+1.916
 Sioux+1.891
 Hots+1.768
 Subtle+1.735
Neg logit contributions
obar-2.173
rane-2.109
minist-1.937
oba-1.888
ega-1.853
Token------------------------
Token ID22369
Feature activation-3.03e-01

Pos logit contributions
 Lauder+1.929
 Loving+1.756
 Sioux+1.733
 Hots+1.618
 Subtle+1.590
Neg logit contributions
obar-2.037
rane-1.975
minist-1.814
oba-1.771
ega-1.740
Token--
Token ID438
Feature activation-3.94e-01

Pos logit contributions
 Lauder+0.498
 Loving+0.449
 Sioux+0.442
 Hots+0.412
 Subtle+0.403
Neg logit contributions
obar-0.572
rane-0.553
minist-0.510
oba-0.500
ega-0.493
Token///
Token ID20379
Feature activation-3.96e-01

Pos logit contributions
 Lauder+0.677
 Loving+0.612
 Sioux+0.605
 Hots+0.565
 Subtle+0.554
Neg logit contributions
obar-0.711
rane-0.688
minist-0.632
oba-0.619
ega-0.609
Token L
Token ID406
Feature activation-2.25e-01

Pos logit contributions
 Lauder+0.654
 Loving+0.589
 Sioux+0.581
 Hots+0.542
 Subtle+0.530
Neg logit contributions
obar-0.740
rane-0.718
minist-0.662
oba-0.648
ega-0.638
Token including
Token ID1390
Feature activation+3.09e-01

Pos logit contributions
obar+0.244
rane+0.234
minist+0.220
oba+0.210
ega+0.208
Neg logit contributions
 Lauder-0.228
 Loving-0.204
 Sioux-0.201
 Hots-0.190
 Subtle-0.189
Token items
Token ID3709
Feature activation+3.09e-01

Pos logit contributions
obar+0.589
rane+0.568
minist+0.528
oba+0.516
ega+0.504
Neg logit contributions
 Lauder-0.491
 Loving-0.440
 Sioux-0.434
 Hots-0.406
 Subtle-0.402
Token from
Token ID422
Feature activation-1.38e-01

Pos logit contributions
obar+0.602
rane+0.585
minist+0.541
oba+0.526
ega+0.525
Neg logit contributions
 Lauder-0.479
 Loving-0.423
 Sioux-0.420
 Hots-0.391
 Subtle-0.388
Token the
Token ID262
Feature activation+1.29e-01

Pos logit contributions
 Lauder+0.224
 Loving+0.201
 Sioux+0.198
 Hots+0.185
 Subtle+0.183
Neg logit contributions
obar-0.259
rane-0.251
minist-0.233
oba-0.228
ega-0.224
Token Imperial
Token ID11773
Feature activation+8.00e-01

Pos logit contributions
obar+0.253
rane+0.246
minist+0.228
oba+0.224
ega+0.219
Neg logit contributions
 Lauder-0.195
 Loving-0.173
 Sioux-0.171
 Hots-0.160
 Subtle-0.157
Token Hotel
Token ID12696
Feature activation-1.34e+00

Pos logit contributions
obar+1.554
rane+1.483
oba+1.375
minist+1.372
ega+1.330
Neg logit contributions
 Lauder-1.223
 Loving-1.090
 Sioux-1.069
 Subtle-0.984
 Hots-0.981
Token in
Token ID287
Feature activation+5.76e-02

Pos logit contributions
 Lauder+2.130
 Loving+1.916
 Sioux+1.885
 Hots+1.753
 Subtle+1.724
Neg logit contributions
obar-2.595
rane-2.516
minist-2.324
oba-2.280
ega-2.243
Token Tokyo
Token ID11790
Feature activation-9.51e-02

Pos logit contributions
obar+0.113
rane+0.110
minist+0.101
oba+0.101
ega+0.098
Neg logit contributions
 Lauder-0.086
 Loving-0.077
 Sioux-0.075
 Subtle-0.070
 Hots-0.070
Token and
Token ID290
Feature activation+4.05e-02

Pos logit contributions
 Lauder+0.157
 Loving+0.140
 Sioux+0.140
 Subtle+0.128
 Hots+0.128
Neg logit contributions
obar-0.178
rane-0.170
minist-0.157
oba-0.155
ega-0.153
Token Wright
Token ID12206
Feature activation+1.87e-01

Pos logit contributions
obar+0.078
rane+0.076
minist+0.070
oba+0.069
ega+0.067
Neg logit contributions
 Lauder-0.063
 Loving-0.057
 Sioux-0.056
 Hots-0.052
 Subtle-0.052
Token
Token ID447
Feature activation-2.44e-02

Pos logit contributions
obar+0.359
rane+0.345
minist+0.324
oba+0.316
ega+0.311
Neg logit contributions
 Lauder-0.293
 Loving-0.263
 Sioux-0.258
 Hots-0.239
 Subtle-0.238
Token d
Token ID288
Feature activation-2.04e-01

Pos logit contributions
obar+0.481
rane+0.470
minist+0.439
oba+0.426
ega+0.423
Neg logit contributions
 Lauder-0.362
 Loving-0.327
 Sioux-0.321
 Hots-0.297
 Sikh-0.290
Tokenans
Token ID504
Feature activation+4.29e-01

Pos logit contributions
 Lauder+0.446
 Loving+0.414
 Sioux+0.408
 Hots+0.388
 Subtle+0.384
Neg logit contributions
obar-0.274
rane-0.263
minist-0.234
oba-0.228
ega-0.221
Token la
Token ID8591
Feature activation-4.44e-01

Pos logit contributions
obar+0.853
rane+0.833
minist+0.788
oba+0.763
ega+0.754
Neg logit contributions
 Lauder-0.637
 Loving-0.575
 Sioux-0.562
 Hots-0.520
 Sikh-0.511
Token corporation
Token ID12017
Feature activation+3.50e-01

Pos logit contributions
 Lauder+0.725
 Loving+0.656
 Sioux+0.645
 Hots+0.602
 Subtle+0.590
Neg logit contributions
obar-0.838
rane-0.810
minist-0.751
oba-0.734
ega-0.722
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
obar+0.748
rane+0.733
minist+0.685
oba+0.669
ega+0.665
Neg logit contributions
 Lauder-0.472
 Loving-0.424
 Sioux-0.413
 Hots-0.379
 Subtle-0.369
TokenApr
Token ID13680
Feature activation-1.24e+00

Pos logit contributions
 Lauder+0.294
 Loving+0.265
 Sioux+0.262
 Hots+0.244
 Sikh+0.239
Neg logit contributions
obar-0.327
rane-0.319
minist-0.295
oba-0.286
ega-0.283
Tokenè
Token ID14064
Feature activation+3.42e-01

Pos logit contributions
 Lauder+2.368
 Loving+2.174
 Sioux+2.149
 Hots+2.025
 Subtle+1.990
Neg logit contributions
obar-1.985
rane-1.910
minist-1.734
oba-1.691
ega-1.664
Tokens
Token ID82
Feature activation+2.17e-02

Pos logit contributions
obar+0.684
rane+0.666
minist+0.623
oba+0.601
ega+0.594
Neg logit contributions
 Lauder-0.509
 Loving-0.462
 Sioux-0.456
 Hots-0.421
 Sikh-0.413
Token une
Token ID17809
Feature activation+1.88e-01

Pos logit contributions
obar+0.043
rane+0.042
minist+0.039
oba+0.038
ega+0.038
Neg logit contributions
 Lauder-0.033
 Loving-0.029
 Sioux-0.029
 Hots-0.027
 Subtle-0.026
Token tentative
Token ID38358
Feature activation+1.40e-02

Pos logit contributions
obar+0.355
rane+0.345
minist+0.323
oba+0.313
ega+0.308
Neg logit contributions
 Lauder-0.303
 Loving-0.276
 Sioux-0.270
 Hots-0.253
 Subtle-0.248
Token inf
Token ID1167
Feature activation+3.35e-01

Pos logit contributions
obar+0.028
rane+0.027
minist+0.026
oba+0.025
ega+0.025
Neg logit contributions
 Lauder-0.021
 Loving-0.019
 Sioux-0.019
 Hots-0.017
 Subtle-0.017