TOP ACTIVATIONS
MAX = 0.879

particularly the non - w earing of the hijab or veil
of trou ser - w earing , eff em inate ,
widespread . AP Photo A man carries a dog
ired Equ ivalent Privacy ( WE P ) is a security
of trou ser - w earing , eff em inate ,
complied with the bank 's directions , the bank is pursuing
to 74 countries but the WHO has so far resisted lab
back . USA TODAY Sports But it
id wrote : Advertisement Advertisement
was governor . Advertisement Continue reading the main story
to see her in the flesh ," said Adrian L ister
and July . Advertisement Continue reading the main story
23 22 62 13 ( Photo 11 : SA UL LO
Kan ek o " H ame ko " Nor iy uki
cross fire . Advertisement Advertisement
edit ] Research directions [ edit ]
sites reported . Advertisement Continue reading the main story
the 2009 North American Pale ont ological Convention , the American
of Transportation . Advertisement If
and JPMorgan Chase was the subject of 20 , 057 .

MIN ACTIVATIONS
MIN = -0.825

. youtube . com / channel / UC _ K k
iff Tra x Reviewer : V the Happy L
so the Texans could off load his on erous contract .
= $ b mp | Select Width , Height } else
, I think Reviewer : B iz r Pix
be trying to influence our electoral process , influence who becomes
culture , he becomes rom antically entangled with a prec ocious
. Where Jack is g arr ulous and annoy ingly self
c v 2 . get Struct uring Element ( cv 2
the future ." <|endoftext|> M urd erer identified in 41 -
and night ! Rated 5 out of 5 by
c v 2 . get Struct uring Element ( cv 2
bike path ? A known factor we have an aging
's terrorist attacks in London left seven dead and 48 injured
Both users say they received notices from
for himself that he 's applied to the rest of the
m working on a little fir mer in texture .
sound system . Rated 5 out of 5 by
that Trump has indeed become electoral poison in the kind of
} -> " A ", { 1 , 14 } ->

INTERVAL 0.453 - 0.879
CONTAINS 0.233%

from approaching Mr . Ahmad ine jad as he arrived in
of a security guard 's ear with a hat chet at
million a year , after opting in for next season ,
gave Lear y his first LSD trip ] founded the Ag
is based on the K VM core kernel module , but

INTERVAL 0.027 - 0.453
CONTAINS 39.689%

umat oid arthritis . Trying to keep her on HIV medication
wants to try next . That includes their 70 , 000
for you on the other side . In fact , you
and sw agger , and they seemed afraid of nothing .
30 . Sc ann ell and Lt . Emil Rick ner

INTERVAL -0.399 - 0.027
CONTAINS 59.614%

nineteenth century . In L in vention de la
at reasonable listening volumes will make them excellent companions in the
Do use social media to make franchise - sh ifting
at a particular glacier is the longer - term position of
run , so we are basically ready . We will try

INTERVAL -0.825 - -0.399
CONTAINS 0.464%

Sheriff 's Office has been notified and is investigating . <|endoftext|>
's comment is astounding . Back handedly acknowledging that Kiev has
to be very quiet and acoustic , with lots of string
ial Name (' system . draw ing . im aging ')
Right eous Brothers singer Bill Med ley , whose brutal murder
Token particularly
Token ID3573
Feature activation+1.30e-01

Pos logit contributions
Narr+0.063
erker+0.063
guyen+0.061
stood+0.061
��+0.061
Neg logit contributions
 spons-0.073
 overboard-0.060
 slack-0.054
 conclud-0.053
 distingu-0.053
Token the
Token ID262
Feature activation+1.02e-01

Pos logit contributions
 spons+0.372
 overboard+0.308
 slack+0.272
 distingu+0.267
 conclud+0.264
Neg logit contributions
Narr-0.371
erker-0.355
guyen-0.354
��-0.347
stood-0.342
Token non
Token ID1729
Feature activation+1.86e-02

Pos logit contributions
 spons+0.302
 overboard+0.246
 slack+0.222
 distingu+0.215
 conclud+0.212
Neg logit contributions
Narr-0.281
erker-0.271
guyen-0.269
��-0.263
��-0.260
Token-
Token ID12
Feature activation+7.66e-03

Pos logit contributions
 spons+0.067
 overboard+0.058
 slack+0.052
 distingu+0.052
 conclud+0.052
Neg logit contributions
Narr-0.038
erker-0.036
guyen-0.036
��-0.035
stood-0.035
Tokenw
Token ID86
Feature activation+1.01e-01

Pos logit contributions
 spons+0.024
 overboard+0.020
 slack+0.018
 distingu+0.017
anova+0.017
Neg logit contributions
Narr-0.019
��-0.019
guyen-0.018
erker-0.018
��-0.018
Tokenearing
Token ID6648
Feature activation+8.79e-01

Pos logit contributions
 spons+0.356
 overboard+0.303
 slack+0.271
 distingu+0.266
 conclud+0.264
Neg logit contributions
Narr-0.216
��-0.211
��-0.209
guyen-0.208
MQ-0.198
Token of
Token ID286
Feature activation+8.67e-02

Pos logit contributions
 spons+2.412
 overboard+1.979
 slack+1.724
 distingu+1.649
 conclud+1.575
Neg logit contributions
Narr-2.573
guyen-2.535
erker-2.514
��-2.474
��-2.437
Token the
Token ID262
Feature activation+2.87e-02

Pos logit contributions
 spons+0.235
 overboard+0.191
 slack+0.169
 distingu+0.163
 conclud+0.156
Neg logit contributions
Narr-0.261
guyen-0.253
��-0.250
erker-0.246
MQ-0.241
Token hijab
Token ID48492
Feature activation-1.86e-01

Pos logit contributions
 spons+0.077
 overboard+0.063
 slack+0.055
 distingu+0.053
 conclud+0.051
Neg logit contributions
Narr-0.087
guyen-0.084
��-0.083
erker-0.082
stood-0.081
Token or
Token ID393
Feature activation+5.82e-02

Pos logit contributions
Narr+0.486
guyen+0.474
erker+0.462
��+0.460
stood+0.448
Neg logit contributions
 spons-0.583
 overboard-0.487
 slack-0.435
 distingu-0.423
 conclud-0.421
Token veil
Token ID30615
Feature activation+1.58e-02

Pos logit contributions
 spons+0.163
 overboard+0.134
 slack+0.119
 distingu+0.115
 conclud+0.113
Neg logit contributions
Narr-0.171
guyen-0.163
��-0.161
erker-0.160
stood-0.157
Token of
Token ID286
Feature activation+6.16e-02

Pos logit contributions
 spons+0.609
 overboard+0.501
 slack+0.440
 conclud+0.427
 distingu+0.426
Neg logit contributions
Narr-0.628
guyen-0.622
erker-0.603
��-0.597
��-0.591
Token trou
Token ID4057
Feature activation+1.16e-01

Pos logit contributions
 spons+0.182
 overboard+0.151
 slack+0.137
 distingu+0.130
 conclud+0.127
Neg logit contributions
Narr-0.169
guyen-0.163
erker-0.160
��-0.157
��-0.157
Tokenser
Token ID2655
Feature activation+2.44e-01

Pos logit contributions
 spons+0.339
 overboard+0.273
anova+0.247
 slack+0.243
 distingu+0.235
Neg logit contributions
Narr-0.321
��-0.316
��-0.315
MQ-0.310
erker-0.307
Token-
Token ID12
Feature activation+6.46e-02

Pos logit contributions
 spons+0.770
 overboard+0.644
 slack+0.580
 distingu+0.560
 conclud+0.548
Neg logit contributions
Narr-0.619
guyen-0.595
erker-0.584
��-0.578
��-0.576
Tokenw
Token ID86
Feature activation+6.17e-02

Pos logit contributions
 spons+0.192
 overboard+0.159
 slack+0.139
anova+0.136
 distingu+0.133
Neg logit contributions
Narr-0.174
guyen-0.171
��-0.169
��-0.168
erker-0.165
Tokenearing
Token ID6648
Feature activation+8.45e-01

Pos logit contributions
 spons+0.230
 overboard+0.195
 slack+0.181
razil+0.178
 distingu+0.173
Neg logit contributions
Narr-0.123
��-0.117
��-0.114
MQ-0.110
guyen-0.108
Token,
Token ID11
Feature activation+5.88e-02

Pos logit contributions
 spons+2.454
 overboard+2.035
 slack+1.859
 distingu+1.766
 conclud+1.681
Neg logit contributions
Narr-2.329
guyen-2.272
erker-2.227
��-2.201
��-2.172
Token eff
Token ID914
Feature activation+3.90e-02

Pos logit contributions
 spons+0.168
 overboard+0.141
 slack+0.126
 distingu+0.120
 conclud+0.117
Neg logit contributions
Narr-0.167
guyen-0.160
erker-0.159
��-0.157
��-0.156
Tokenem
Token ID368
Feature activation+3.22e-01

Pos logit contributions
 spons+0.106
 overboard+0.085
 slack+0.076
anova+0.073
 distingu+0.073
Neg logit contributions
Narr-0.116
��-0.111
��-0.111
guyen-0.111
MQ-0.108
Tokeninate
Token ID4559
Feature activation+1.72e-01

Pos logit contributions
 spons+0.742
 overboard+0.601
 slack+0.509
 distingu+0.483
razil+0.472
Neg logit contributions
Narr-1.070
guyen-1.029
��-1.027
erker-1.009
��-1.009
Token,
Token ID11
Feature activation+5.06e-02

Pos logit contributions
 spons+0.500
 overboard+0.415
 slack+0.372
 distingu+0.358
 conclud+0.347
Neg logit contributions
Narr-0.478
guyen-0.462
erker-0.454
��-0.445
��-0.445
Token widespread
Token ID10095
Feature activation+1.04e-01

Pos logit contributions
 spons+0.086
 overboard+0.074
 slack+0.067
 distingu+0.064
 conclud+0.061
Neg logit contributions
Narr-0.078
guyen-0.075
erker-0.075
��-0.074
��-0.073
Token.
Token ID13
Feature activation-1.58e-03

Pos logit contributions
 spons+0.301
 overboard+0.256
 slack+0.230
 conclud+0.219
 distingu+0.214
Neg logit contributions
Narr-0.283
guyen-0.279
��-0.276
erker-0.272
��-0.267
Token
Token ID198
Feature activation-3.77e-03

Pos logit contributions
guyen+0.004
erker+0.004
Narr+0.004
��+0.004
��+0.004
Neg logit contributions
 spons-0.004
 overboard-0.004
 slack-0.003
 Tycoon-0.003
 conclud-0.003
Token
Token ID198
Feature activation-4.51e-03

Pos logit contributions
Narr+0.009
guyen+0.009
erker+0.009
��+0.009
��+0.009
Neg logit contributions
 spons-0.011
 overboard-0.010
 slack-0.009
 conclud-0.008
 distingu-0.008
TokenAP
Token ID2969
Feature activation+8.34e-02

Pos logit contributions
erker+0.011
guyen+0.011
��+0.011
��+0.011
Narr+0.011
Neg logit contributions
 spons-0.013
 overboard-0.011
 slack-0.010
anova-0.010
razil-0.010
Token Photo
Token ID5555
Feature activation+8.36e-01

Pos logit contributions
 spons+0.242
 overboard+0.204
 slack+0.184
 conclud+0.182
 distingu+0.178
Neg logit contributions
Narr-0.216
stood-0.212
��-0.211
guyen-0.211
erker-0.210
Token A
Token ID317
Feature activation+2.27e-01

Pos logit contributions
 spons+2.546
 overboard+2.132
 slack+1.931
 Tycoon+1.891
 conclud+1.852
Neg logit contributions
Narr-2.070
erker-2.008
��-1.978
guyen-1.968
stood-1.947
Token man
Token ID582
Feature activation-3.72e-02

Pos logit contributions
 spons+0.636
 overboard+0.528
 slack+0.489
 distingu+0.459
 conclud+0.448
Neg logit contributions
Narr-0.631
��-0.605
erker-0.601
guyen-0.590
��-0.586
Token carries
Token ID10732
Feature activation+1.94e-01

Pos logit contributions
Narr+0.108
guyen+0.104
��+0.103
erker+0.102
��+0.100
Neg logit contributions
 spons-0.104
 overboard-0.089
 slack-0.077
 distingu-0.075
 conclud-0.073
Token a
Token ID257
Feature activation+1.52e-02

Pos logit contributions
 spons+0.564
 overboard+0.497
 slack+0.444
 distingu+0.411
 ashore+0.406
Neg logit contributions
Narr-0.523
��-0.520
erker-0.510
guyen-0.503
��-0.501
Token dog
Token ID3290
Feature activation+6.34e-02

Pos logit contributions
 spons+0.042
 overboard+0.035
 slack+0.032
 distingu+0.029
 conclud+0.028
Neg logit contributions
Narr-0.044
��-0.043
erker-0.043
guyen-0.042
��-0.042
Tokenired
Token ID1202
Feature activation+2.55e-01

Pos logit contributions
 spons+0.301
 overboard+0.254
 slack+0.228
 conclud+0.222
anova+0.220
Neg logit contributions
Narr-0.231
��-0.222
��-0.220
stood-0.216
guyen-0.212
Token Equ
Token ID7889
Feature activation+3.61e-01

Pos logit contributions
 spons+0.783
 overboard+0.653
 slack+0.580
 conclud+0.568
 Tycoon+0.568
Neg logit contributions
Narr-0.648
erker-0.625
��-0.622
guyen-0.622
��-0.612
Tokenivalent
Token ID29540
Feature activation+8.13e-02

Pos logit contributions
 spons+1.064
 overboard+0.878
 slack+0.794
anova+0.779
 distingu+0.776
Neg logit contributions
Narr-0.946
��-0.918
��-0.905
MQ-0.888
erker-0.887
Token Privacy
Token ID16777
Feature activation-1.42e-01

Pos logit contributions
 spons+0.247
 overboard+0.205
 slack+0.189
 distingu+0.180
 conclud+0.179
Neg logit contributions
Narr-0.210
guyen-0.205
erker-0.204
��-0.201
stood-0.199
Token (
Token ID357
Feature activation-3.49e-02

Pos logit contributions
Narr+0.372
guyen+0.360
erker+0.355
��+0.343
��+0.342
Neg logit contributions
 spons-0.428
 overboard-0.361
 slack-0.323
 distingu-0.311
 Tycoon-0.308
TokenWE
Token ID8845
Feature activation+8.30e-01

Pos logit contributions
Narr+0.076
erker+0.074
guyen+0.073
stood+0.070
��+0.070
Neg logit contributions
 spons-0.118
 overboard-0.099
 slack-0.091
 distingu-0.090
 conclud-0.090
TokenP
Token ID47
Feature activation+1.87e-02

Pos logit contributions
 spons+2.575
 overboard+2.147
 slack+1.904
 distingu+1.898
 conclud+1.870
Neg logit contributions
Narr-2.087
guyen-1.984
stood-1.925
erker-1.916
��-1.891
Token)
Token ID8
Feature activation+4.65e-02

Pos logit contributions
 spons+0.056
 overboard+0.047
 slack+0.041
 distingu+0.040
 conclud+0.039
Neg logit contributions
Narr-0.051
erker-0.048
guyen-0.047
��-0.047
stood-0.046
Token is
Token ID318
Feature activation+8.60e-02

Pos logit contributions
 spons+0.134
 overboard+0.111
 slack+0.099
 distingu+0.096
 conclud+0.094
Neg logit contributions
Narr-0.131
guyen-0.125
erker-0.125
��-0.120
stood-0.120
Token a
Token ID257
Feature activation+6.84e-02

Pos logit contributions
 spons+0.262
 overboard+0.222
 slack+0.200
 distingu+0.192
 conclud+0.187
Neg logit contributions
Narr-0.224
erker-0.216
guyen-0.216
stood-0.209
��-0.208
Token security
Token ID2324
Feature activation+1.55e-01

Pos logit contributions
 spons+0.195
 overboard+0.160
 slack+0.144
 distingu+0.140
 conclud+0.137
Neg logit contributions
Narr-0.195
erker-0.187
guyen-0.186
��-0.181
stood-0.180
Token of
Token ID286
Feature activation+8.32e-02

Pos logit contributions
 spons+0.458
 overboard+0.380
 conclud+0.345
 distingu+0.342
 slack+0.339
Neg logit contributions
Narr-0.381
erker-0.355
guyen-0.353
stood-0.351
MQ-0.344
Token trou
Token ID4057
Feature activation+9.14e-02

Pos logit contributions
 spons+0.212
 overboard+0.167
 slack+0.150
 distingu+0.141
 conclud+0.139
Neg logit contributions
Narr-0.268
guyen-0.256
erker-0.253
��-0.251
MQ-0.250
Tokenser
Token ID2655
Feature activation+1.79e-01

Pos logit contributions
 spons+0.269
 overboard+0.223
 conclud+0.198
 slack+0.198
 distingu+0.196
Neg logit contributions
Narr-0.247
guyen-0.234
erker-0.233
stood-0.229
��-0.227
Token-
Token ID12
Feature activation+1.93e-01

Pos logit contributions
 spons+0.645
 overboard+0.557
 slack+0.505
 distingu+0.479
 conclud+0.477
Neg logit contributions
Narr-0.375
guyen-0.358
erker-0.352
��-0.350
��-0.350
Tokenw
Token ID86
Feature activation+1.04e-01

Pos logit contributions
 spons+0.676
 overboard+0.579
 slack+0.526
 conclud+0.520
 distingu+0.517
Neg logit contributions
Narr-0.413
guyen-0.386
erker-0.383
��-0.374
stood-0.373
Tokenearing
Token ID6648
Feature activation+8.27e-01

Pos logit contributions
 spons+0.485
 overboard+0.432
 conclud+0.410
 distingu+0.406
 slack+0.404
Neg logit contributions
Narr-0.102
erker-0.090
guyen-0.088
stood-0.084
MQ-0.079
Token,
Token ID11
Feature activation+1.30e-01

Pos logit contributions
 spons+2.528
 overboard+2.142
 slack+1.932
 conclud+1.874
 distingu+1.865
Neg logit contributions
Narr-2.095
guyen-2.019
erker-1.997
stood-1.927
��-1.920
Token eff
Token ID914
Feature activation+3.51e-02

Pos logit contributions
 spons+0.406
 overboard+0.339
 conclud+0.304
 slack+0.304
 distingu+0.302
Neg logit contributions
Narr-0.325
guyen-0.305
erker-0.305
stood-0.300
��-0.296
Tokenem
Token ID368
Feature activation+3.41e-01

Pos logit contributions
 spons+0.100
 overboard+0.082
 conclud+0.073
 slack+0.073
 distingu+0.072
Neg logit contributions
Narr-0.098
erker-0.094
guyen-0.093
stood-0.092
��-0.090
Tokeninate
Token ID4559
Feature activation+1.88e-01

Pos logit contributions
 spons+0.946
 overboard+0.773
 slack+0.680
 conclud+0.676
 distingu+0.670
Neg logit contributions
Narr-0.983
guyen-0.932
erker-0.931
stood-0.915
��-0.909
Token,
Token ID11
Feature activation+1.10e-01

Pos logit contributions
 spons+0.636
 overboard+0.544
 slack+0.492
 conclud+0.482
 distingu+0.480
Neg logit contributions
Narr-0.426
guyen-0.402
erker-0.399
��-0.390
stood-0.389
Token complied
Token ID35413
Feature activation-2.00e-01

Pos logit contributions
Narr+0.028
guyen+0.027
erker+0.027
��+0.026
��+0.026
Neg logit contributions
 spons-0.028
 overboard-0.023
 slack-0.021
 distingu-0.020
 conclud-0.020
Token with
Token ID351
Feature activation-1.56e-02

Pos logit contributions
Narr+0.648
guyen+0.629
erker+0.623
��+0.607
stood+0.601
Neg logit contributions
 spons-0.488
 overboard-0.387
 slack-0.352
 conclud-0.336
 distingu-0.332
Token the
Token ID262
Feature activation+1.73e-02

Pos logit contributions
Narr+0.044
erker+0.042
guyen+0.042
��+0.041
��+0.041
Neg logit contributions
 spons-0.044
 overboard-0.036
 slack-0.033
 conclud-0.031
 distingu-0.031
Token bank
Token ID3331
Feature activation-1.60e-03

Pos logit contributions
 spons+0.052
 overboard+0.044
 slack+0.040
 conclud+0.038
 distingu+0.038
Neg logit contributions
Narr-0.046
erker-0.045
guyen-0.044
��-0.042
��-0.042
Token's
Token ID338
Feature activation-1.30e-02

Pos logit contributions
Narr+0.005
erker+0.004
guyen+0.004
��+0.004
stood+0.004
Neg logit contributions
 spons-0.005
 overboard-0.004
 slack-0.003
 conclud-0.003
 distingu-0.003
Token directions
Token ID11678
Feature activation+8.27e-01

Pos logit contributions
Narr+0.035
erker+0.033
guyen+0.033
��+0.032
��+0.032
Neg logit contributions
 spons-0.039
 overboard-0.032
 slack-0.030
 conclud-0.029
 distingu-0.028
Token,
Token ID11
Feature activation+7.67e-02

Pos logit contributions
 spons+2.301
 overboard+1.984
 slack+1.725
 distingu+1.635
 ashore+1.605
Neg logit contributions
Narr-2.344
guyen-2.298
erker-2.297
��-2.221
��-2.194
Token the
Token ID262
Feature activation+5.83e-02

Pos logit contributions
 spons+0.236
 overboard+0.196
 slack+0.176
 conclud+0.171
 distingu+0.170
Neg logit contributions
Narr-0.204
erker-0.195
guyen-0.192
��-0.189
��-0.188
Token bank
Token ID3331
Feature activation-1.61e-02

Pos logit contributions
 spons+0.173
 overboard+0.141
 slack+0.129
 distingu+0.122
 conclud+0.121
Neg logit contributions
Narr-0.161
erker-0.155
guyen-0.153
��-0.150
��-0.149
Token is
Token ID318
Feature activation-1.43e-02

Pos logit contributions
Narr+0.046
guyen+0.044
erker+0.044
��+0.043
��+0.043
Neg logit contributions
 spons-0.045
 overboard-0.037
 slack-0.033
 conclud-0.032
 distingu-0.032
Token pursuing
Token ID15461
Feature activation-1.54e-01

Pos logit contributions
Narr+0.041
guyen+0.039
erker+0.039
��+0.038
��+0.038
Neg logit contributions
 spons-0.041
 overboard-0.034
 slack-0.030
 conclud-0.029
 distingu-0.029
Token to
Token ID284
Feature activation-2.83e-02

Pos logit contributions
Narr+0.070
guyen+0.067
erker+0.067
��+0.066
��+0.066
Neg logit contributions
 spons-0.070
 overboard-0.059
 slack-0.052
 distingu-0.050
 conclud-0.049
Token 74
Token ID8915
Feature activation-1.16e-01

Pos logit contributions
Narr+0.078
erker+0.073
guyen+0.073
��+0.073
��+0.071
Neg logit contributions
 spons-0.083
 overboard-0.070
 slack-0.062
 distingu-0.060
 conclud-0.060
Token countries
Token ID2678
Feature activation+2.28e-02

Pos logit contributions
Narr+0.291
erker+0.274
guyen+0.268
stood+0.262
��+0.261
Neg logit contributions
 spons-0.375
 overboard-0.315
 slack-0.284
 distingu-0.277
 conclud-0.276
Token but
Token ID475
Feature activation+1.49e-01

Pos logit contributions
 spons+0.065
 overboard+0.055
 slack+0.049
 conclud+0.047
 distingu+0.046
Neg logit contributions
Narr-0.064
guyen-0.062
erker-0.061
��-0.060
��-0.060
Token the
Token ID262
Feature activation+1.62e-01

Pos logit contributions
 spons+0.428
 overboard+0.355
 slack+0.321
 conclud+0.308
 distingu+0.307
Neg logit contributions
Narr-0.423
erker-0.402
��-0.395
guyen-0.393
��-0.389
Token WHO
Token ID19494
Feature activation+8.00e-01

Pos logit contributions
 spons+0.481
 overboard+0.394
 slack+0.369
 distingu+0.343
 conclud+0.339
Neg logit contributions
Narr-0.445
erker-0.425
guyen-0.414
��-0.411
��-0.409
Token has
Token ID468
Feature activation+1.51e-01

Pos logit contributions
 spons+2.047
 overboard+1.667
 slack+1.475
 conclud+1.465
 distingu+1.432
Neg logit contributions
Narr-2.439
erker-2.347
��-2.333
guyen-2.327
��-2.298
Token so
Token ID523
Feature activation+1.79e-01

Pos logit contributions
 spons+0.427
 overboard+0.354
 slack+0.321
 conclud+0.310
 distingu+0.308
Neg logit contributions
Narr-0.426
guyen-0.411
erker-0.408
��-0.401
��-0.400
Token far
Token ID1290
Feature activation+5.06e-03

Pos logit contributions
 spons+0.463
 overboard+0.384
 slack+0.342
 distingu+0.327
 conclud+0.326
Neg logit contributions
Narr-0.542
guyen-0.525
erker-0.522
��-0.511
��-0.507
Token resisted
Token ID26643
Feature activation+8.88e-02

Pos logit contributions
 spons+0.015
 overboard+0.013
 slack+0.011
 conclud+0.011
 distingu+0.011
Neg logit contributions
Narr-0.014
guyen-0.013
erker-0.013
��-0.013
��-0.013
Token lab
Token ID2248
Feature activation+6.57e-01

Pos logit contributions
 spons+0.253
 overboard+0.208
 slack+0.187
 conclud+0.183
 distingu+0.182
Neg logit contributions
Narr-0.254
erker-0.241
guyen-0.241
��-0.236
stood-0.233
Token back
Token ID736
Feature activation-1.56e-01

Pos logit contributions
 spons+0.240
 overboard+0.204
 slack+0.183
 conclud+0.174
 distingu+0.173
Neg logit contributions
Narr-0.213
guyen-0.207
erker-0.203
��-0.201
��-0.200
Token.
Token ID13
Feature activation+5.44e-03

Pos logit contributions
Narr+0.409
guyen+0.401
erker+0.392
��+0.390
��+0.384
Neg logit contributions
 spons-0.474
 overboard-0.404
 slack-0.362
 conclud-0.348
 distingu-0.340
Token
Token ID198
Feature activation+2.04e-02

Pos logit contributions
 spons+0.016
 overboard+0.013
 slack+0.012
 conclud+0.011
 Tycoon+0.011
Neg logit contributions
Narr-0.014
guyen-0.014
erker-0.014
��-0.014
��-0.013
Token
Token ID198
Feature activation+4.09e-02

Pos logit contributions
 spons+0.066
 overboard+0.056
 conclud+0.050
 slack+0.050
 distingu+0.050
Neg logit contributions
Narr-0.049
guyen-0.046
erker-0.046
stood-0.045
��-0.045
TokenUSA
Token ID14053
Feature activation+1.83e-01

Pos logit contributions
 spons+0.121
 overboard+0.101
 slack+0.092
anova+0.092
razil+0.089
Neg logit contributions
guyen-0.100
erker-0.099
��-0.097
��-0.096
Narr-0.094
Token TODAY
Token ID20092
Feature activation+7.86e-01

Pos logit contributions
 spons+0.379
 overboard+0.288
 slack+0.247
 conclud+0.236
 Tycoon+0.223
Neg logit contributions
Narr-0.657
erker-0.630
guyen-0.622
stood-0.622
��-0.607
Token Sports
Token ID7092
Feature activation+4.50e-01

Pos logit contributions
 spons+2.509
 overboard+2.087
 conclud+1.922
 slack+1.904
 distingu+1.868
Neg logit contributions
Narr-1.871
guyen-1.758
stood-1.752
erker-1.750
��-1.749
Token
Token ID198
Feature activation+6.79e-02

Pos logit contributions
 spons+1.252
 overboard+0.999
 conclud+0.925
 slack+0.907
 distingu+0.896
Neg logit contributions
Narr-1.267
guyen-1.208
��-1.204
��-1.192
erker-1.165
Token
Token ID198
Feature activation+8.09e-02

Pos logit contributions
 spons+0.222
 overboard+0.187
 conclud+0.169
 distingu+0.168
 slack+0.168
Neg logit contributions
Narr-0.163
erker-0.152
guyen-0.152
stood-0.150
MQ-0.148
TokenBut
Token ID1537
Feature activation+3.82e-02

Pos logit contributions
 spons+0.247
 overboard+0.206
anova+0.188
 slack+0.187
razil+0.186
Neg logit contributions
guyen-0.191
erker-0.190
Narr-0.185
��-0.183
��-0.182
Token it
Token ID340
Feature activation+8.41e-02

Pos logit contributions
 spons+0.116
 overboard+0.097
 slack+0.087
 conclud+0.085
 distingu+0.084
Neg logit contributions
Narr-0.100
guyen-0.095
erker-0.095
��-0.093
stood-0.092
Tokenid
Token ID312
Feature activation+2.92e-02

Pos logit contributions
 spons+0.194
 overboard+0.165
 slack+0.150
 conclud+0.149
 distingu+0.148
Neg logit contributions
Narr-0.129
guyen-0.120
erker-0.120
stood-0.117
��-0.116
Token wrote
Token ID2630
Feature activation-8.79e-02

Pos logit contributions
 spons+0.078
 overboard+0.064
 slack+0.056
 conclud+0.055
 distingu+0.055
Neg logit contributions
Narr-0.087
guyen-0.084
��-0.083
erker-0.082
��-0.081
Token:
Token ID25
Feature activation-1.26e-01

Pos logit contributions
Narr+0.264
erker+0.256
guyen+0.256
stood+0.248
��+0.247
Neg logit contributions
 spons-0.231
 overboard-0.191
 slack-0.167
 distingu-0.164
 conclud-0.162
Token
Token ID198
Feature activation-3.57e-02

Pos logit contributions
Narr+0.299
erker+0.289
guyen+0.286
��+0.276
��+0.274
Neg logit contributions
 spons-0.409
 overboard-0.340
 slack-0.315
 distingu-0.308
 conclud-0.306
Token
Token ID198
Feature activation-7.96e-03

Pos logit contributions
Narr+0.087
guyen+0.081
erker+0.081
stood+0.080
��+0.079
Neg logit contributions
 spons-0.115
 overboard-0.097
 slack-0.087
 conclud-0.087
 distingu-0.087
TokenAdvertisement
Token ID4723
Feature activation+7.86e-01

Pos logit contributions
guyen+0.019
erker+0.019
Narr+0.018
��+0.018
��+0.018
Neg logit contributions
 spons-0.025
 overboard-0.021
 slack-0.019
anova-0.018
 distingu-0.018
Token
Token ID198
Feature activation+1.97e-02

Pos logit contributions
 spons+2.111
 overboard+1.736
 slack+1.603
 Tycoon+1.478
razil+1.440
Neg logit contributions
��-2.175
Narr-2.167
guyen-2.156
��-2.152
erker-2.137
Token
Token ID198
Feature activation+5.58e-02

Pos logit contributions
 spons+0.064
 overboard+0.054
 conclud+0.049
 distingu+0.049
 slack+0.049
Neg logit contributions
Narr-0.047
erker-0.044
guyen-0.044
stood-0.043
MQ-0.043
TokenAdvertisement
Token ID4723
Feature activation+6.28e-01

Pos logit contributions
 spons+0.157
 overboard+0.132
 slack+0.118
anova+0.113
 distingu+0.111
Neg logit contributions
��-0.146
guyen-0.145
erker-0.145
Narr-0.142
��-0.141
Token
Token ID198
Feature activation-3.46e-02

Pos logit contributions
 spons+1.853
 overboard+1.560
 slack+1.417
anova+1.323
 conclud+1.321
Neg logit contributions
Narr-1.620
guyen-1.580
��-1.563
erker-1.552
��-1.547
Token
Token ID198
Feature activation+1.55e-02

Pos logit contributions
Narr+0.082
erker+0.077
guyen+0.076
stood+0.076
MQ+0.074
Neg logit contributions
 spons-0.114
 overboard-0.096
 conclud-0.088
 distingu-0.087
 slack-0.086
Token was
Token ID373
Feature activation+6.02e-02

Pos logit contributions
Narr+0.092
erker+0.089
guyen+0.088
��+0.086
��+0.084
Neg logit contributions
 spons-0.101
 overboard-0.087
 slack-0.078
 distingu-0.074
 conclud-0.073
Token governor
Token ID8153
Feature activation+3.83e-01

Pos logit contributions
 spons+0.180
 overboard+0.152
 slack+0.137
 distingu+0.131
 conclud+0.130
Neg logit contributions
Narr-0.160
erker-0.153
guyen-0.153
��-0.151
��-0.150
Token.
Token ID13
Feature activation+7.74e-02

Pos logit contributions
 spons+1.094
 overboard+0.905
 slack+0.822
 conclud+0.796
 Tycoon+0.746
Neg logit contributions
Narr-1.067
guyen-1.047
erker-1.041
��-1.008
stood-1.006
Token
Token ID198
Feature activation+3.48e-02

Pos logit contributions
 spons+0.209
 overboard+0.173
 slack+0.162
 Tycoon+0.155
anova+0.149
Neg logit contributions
Narr-0.215
erker-0.213
guyen-0.213
��-0.208
��-0.205
Token
Token ID198
Feature activation+4.41e-02

Pos logit contributions
 spons+0.113
 overboard+0.095
 conclud+0.086
 slack+0.085
 distingu+0.085
Neg logit contributions
Narr-0.084
erker-0.078
guyen-0.078
stood-0.077
��-0.076
TokenAdvertisement
Token ID4723
Feature activation+7.85e-01

Pos logit contributions
 spons+0.117
 overboard+0.098
 slack+0.089
anova+0.087
 Tycoon+0.082
Neg logit contributions
guyen-0.121
erker-0.120
��-0.117
��-0.115
Narr-0.113
Token Continue
Token ID10054
Feature activation+2.91e-01

Pos logit contributions
 spons+2.127
 overboard+1.732
 slack+1.543
 distingu+1.453
 conclud+1.435
Neg logit contributions
Narr-2.257
guyen-2.187
erker-2.179
��-2.167
stood-2.156
Token reading
Token ID3555
Feature activation+4.96e-02

Pos logit contributions
 spons+0.987
 overboard+0.841
 slack+0.764
 conclud+0.753
 distingu+0.749
Neg logit contributions
Narr-0.657
guyen-0.616
erker-0.611
��-0.597
stood-0.597
Token the
Token ID262
Feature activation+6.03e-02

Pos logit contributions
 spons+0.154
 overboard+0.129
 slack+0.116
 conclud+0.114
 distingu+0.113
Neg logit contributions
Narr-0.126
guyen-0.119
erker-0.118
��-0.116
stood-0.116
Token main
Token ID1388
Feature activation-8.18e-03

Pos logit contributions
 spons+0.164
 overboard+0.133
 slack+0.116
 conclud+0.116
 distingu+0.115
Neg logit contributions
Narr-0.177
guyen-0.168
erker-0.168
stood-0.165
��-0.164
Token story
Token ID1621
Feature activation-3.22e-01

Pos logit contributions
Narr+0.019
guyen+0.018
erker+0.018
��+0.018
stood+0.018
Neg logit contributions
 spons-0.027
 overboard-0.023
 slack-0.020
 conclud-0.020
 distingu-0.020
Token to
Token ID284
Feature activation-1.49e-01

Pos logit contributions
 spons+0.140
 overboard+0.119
 slack+0.105
 conclud+0.102
 distingu+0.101
Neg logit contributions
Narr-0.123
guyen-0.120
��-0.118
erker-0.118
MQ-0.115
Token see
Token ID766
Feature activation-1.41e-01

Pos logit contributions
Narr+0.419
guyen+0.401
erker+0.398
��+0.391
stood+0.390
Neg logit contributions
 spons-0.428
 overboard-0.353
 slack-0.315
 conclud-0.307
 distingu-0.306
Token her
Token ID607
Feature activation-6.28e-02

Pos logit contributions
Narr+0.370
erker+0.353
guyen+0.352
��+0.348
��+0.344
Neg logit contributions
 spons-0.427
 overboard-0.361
 slack-0.324
 distingu-0.311
 conclud-0.310
Token in
Token ID287
Feature activation-8.54e-02

Pos logit contributions
Narr+0.177
guyen+0.170
��+0.168
erker+0.168
��+0.165
Neg logit contributions
 spons-0.178
 overboard-0.149
 slack-0.133
 distingu-0.129
 conclud-0.128
Token the
Token ID262
Feature activation-3.93e-02

Pos logit contributions
Narr+0.229
guyen+0.223
��+0.216
erker+0.216
��+0.215
Neg logit contributions
 spons-0.255
 overboard-0.212
 slack-0.195
 conclud-0.182
 distingu-0.181
Token flesh
Token ID11222
Feature activation+7.82e-01

Pos logit contributions
Narr+0.116
guyen+0.111
erker+0.110
��+0.109
MQ+0.108
Neg logit contributions
 spons-0.107
 overboard-0.087
 slack-0.080
 distingu-0.074
 conclud-0.074
Token,"
Token ID553
Feature activation-3.84e-02

Pos logit contributions
 spons+2.228
 overboard+1.894
 slack+1.700
 conclud+1.610
 distingu+1.589
Neg logit contributions
Narr-2.135
guyen-2.098
��-2.073
MQ-2.021
��-2.006
Token said
Token ID531
Feature activation-2.18e-02

Pos logit contributions
Narr+0.112
erker+0.107
��+0.107
guyen+0.106
��+0.106
Neg logit contributions
 spons-0.104
 overboard-0.085
 slack-0.076
 distingu-0.074
 conclud-0.074
Token Adrian
Token ID21462
Feature activation+1.34e-01

Pos logit contributions
Narr+0.056
erker+0.053
��+0.053
guyen+0.052
stood+0.052
Neg logit contributions
 spons-0.068
 overboard-0.056
 slack-0.051
 distingu-0.050
 conclud-0.049
Token L
Token ID406
Feature activation-1.07e-01

Pos logit contributions
 spons+0.417
 overboard+0.350
 slack+0.325
 Tycoon+0.316
anova+0.311
Neg logit contributions
Narr-0.326
erker-0.305
guyen-0.303
��-0.302
stood-0.301
Tokenister
Token ID1694
Feature activation-1.38e-02

Pos logit contributions
Narr+0.286
��+0.268
MQ+0.260
��+0.260
guyen+0.259
Neg logit contributions
 spons-0.322
 overboard-0.266
 slack-0.238
uana-0.236
anova-0.235
Token and
Token ID290
Feature activation+7.26e-02

Pos logit contributions
 spons+0.485
 overboard+0.411
 slack+0.368
 conclud+0.360
 distingu+0.349
Neg logit contributions
Narr-0.413
guyen-0.404
��-0.396
erker-0.391
stood-0.383
Token July
Token ID2901
Feature activation+1.72e-01

Pos logit contributions
 spons+0.212
 overboard+0.176
 slack+0.159
 conclud+0.155
 distingu+0.153
Neg logit contributions
Narr-0.197
erker-0.189
guyen-0.188
��-0.186
stood-0.180
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
 spons+0.527
 overboard+0.447
 slack+0.403
 conclud+0.393
 distingu+0.382
Neg logit contributions
Narr-0.445
guyen-0.438
��-0.426
erker-0.422
��-0.409
Token
Token ID198
Feature activation+1.41e-01

Pos logit contributions
 spons+0.307
 overboard+0.256
 slack+0.238
 Tycoon+0.224
anova+0.220
Neg logit contributions
Narr-0.316
guyen-0.311
erker-0.308
��-0.308
��-0.301
Token
Token ID198
Feature activation+1.24e-01

Pos logit contributions
 spons+0.454
 overboard+0.382
 slack+0.343
 conclud+0.343
 distingu+0.340
Neg logit contributions
Narr-0.341
guyen-0.320
erker-0.319
stood-0.313
��-0.310
TokenAdvertisement
Token ID4723
Feature activation+7.76e-01

Pos logit contributions
 spons+0.346
 overboard+0.292
 slack+0.262
anova+0.256
razil+0.243
Neg logit contributions
guyen-0.327
erker-0.325
��-0.323
Narr-0.315
��-0.314
Token Continue
Token ID10054
Feature activation+3.57e-01

Pos logit contributions
 spons+2.248
 overboard+1.865
 slack+1.660
 conclud+1.619
 distingu+1.606
Neg logit contributions
Narr-2.115
guyen-2.015
erker-2.009
��-1.976
stood-1.967
Token reading
Token ID3555
Feature activation+2.57e-02

Pos logit contributions
 spons+1.204
 overboard+1.028
 slack+0.933
 conclud+0.915
 distingu+0.910
Neg logit contributions
Narr-0.811
guyen-0.761
erker-0.755
��-0.740
stood-0.736
Token the
Token ID262
Feature activation+7.03e-02

Pos logit contributions
 spons+0.082
 overboard+0.069
 slack+0.062
 conclud+0.061
 distingu+0.061
Neg logit contributions
Narr-0.064
guyen-0.060
erker-0.060
stood-0.059
��-0.058
Token main
Token ID1388
Feature activation-9.65e-02

Pos logit contributions
 spons+0.195
 overboard+0.158
 conclud+0.141
 distingu+0.139
 slack+0.138
Neg logit contributions
Narr-0.203
erker-0.192
guyen-0.192
stood-0.189
MQ-0.187
Token story
Token ID1621
Feature activation-3.04e-01

Pos logit contributions
Narr+0.221
erker+0.206
guyen+0.205
stood+0.201
��+0.197
Neg logit contributions
 spons-0.326
 overboard-0.276
 conclud-0.252
 distingu-0.249
 slack-0.249
Token23
Token ID1954
Feature activation+8.81e-02

Pos logit contributions
 spons+0.390
 overboard+0.328
 slack+0.298
 conclud+0.292
 distingu+0.291
Neg logit contributions
Narr-0.298
guyen-0.287
erker-0.285
��-0.280
stood-0.280
Token22
Token ID1828
Feature activation+9.24e-02

Pos logit contributions
 spons+0.276
 overboard+0.232
 slack+0.211
 conclud+0.206
 distingu+0.206
Neg logit contributions
Narr-0.215
erker-0.207
guyen-0.206
��-0.202
stood-0.202
Token62
Token ID5237
Feature activation+1.69e-01

Pos logit contributions
 spons+0.292
 overboard+0.247
 slack+0.225
 conclud+0.219
 distingu+0.219
Neg logit contributions
Narr-0.223
guyen-0.214
erker-0.214
stood-0.209
��-0.209
Token13
Token ID1485
Feature activation+4.37e-02

Pos logit contributions
 spons+0.509
 overboard+0.433
 slack+0.395
 distingu+0.377
 conclud+0.374
Neg logit contributions
Narr-0.422
guyen-0.414
erker-0.412
��-0.402
��-0.401
Token (
Token ID357
Feature activation-1.61e-02

Pos logit contributions
 spons+0.135
 overboard+0.116
 slack+0.106
 distingu+0.102
 conclud+0.101
Neg logit contributions
Narr-0.106
erker-0.103
guyen-0.102
��-0.101
stood-0.101
TokenPhoto
Token ID6191
Feature activation+7.70e-01

Pos logit contributions
Narr+0.041
guyen+0.039
erker+0.038
��+0.038
stood+0.038
Neg logit contributions
 spons-0.050
 overboard-0.042
 slack-0.038
 conclud-0.037
 distingu-0.037
Token11
Token ID1157
Feature activation+1.31e-01

Pos logit contributions
 spons+1.557
 overboard+1.181
 slack+1.036
 conclud+0.958
 distingu+0.930
Neg logit contributions
Narr-2.736
guyen-2.636
erker-2.635
��-2.602
stood-2.598
Token:
Token ID25
Feature activation-1.27e-02

Pos logit contributions
 spons+0.398
 overboard+0.338
 slack+0.305
 distingu+0.291
 conclud+0.289
Neg logit contributions
Narr-0.330
guyen-0.318
stood-0.318
erker-0.316
��-0.316
Token SA
Token ID14719
Feature activation+4.18e-02

Pos logit contributions
Narr+0.032
��+0.030
guyen+0.030
erker+0.030
stood+0.029
Neg logit contributions
 spons-0.040
 overboard-0.033
 slack-0.031
 conclud-0.030
 distingu-0.029
TokenUL
Token ID6239
Feature activation+1.57e-01

Pos logit contributions
 spons+0.154
 overboard+0.132
 slack+0.122
 distingu+0.118
 conclud+0.118
Neg logit contributions
Narr-0.082
erker-0.075
��-0.074
guyen-0.074
stood-0.074
Token LO
Token ID17579
Feature activation+2.12e-01

Pos logit contributions
 spons+0.406
 overboard+0.341
 slack+0.303
 conclud+0.291
 distingu+0.287
Neg logit contributions
Narr-0.468
guyen-0.450
erker-0.448
stood-0.441
��-0.436
Token Kan
Token ID14248
Feature activation+8.30e-02

Pos logit contributions
Narr+0.395
erker+0.373
guyen+0.371
��+0.369
MQ+0.361
Neg logit contributions
 spons-0.460
 overboard-0.387
 slack-0.350
 distingu-0.335
 Tycoon-0.331
Tokenek
Token ID988
Feature activation+3.52e-01

Pos logit contributions
 spons+0.258
 overboard+0.215
 slack+0.195
anova+0.186
 distingu+0.186
Neg logit contributions
Narr-0.211
��-0.200
guyen-0.195
��-0.194
erker-0.193
Tokeno
Token ID78
Feature activation+1.83e-02

Pos logit contributions
 spons+1.120
 overboard+0.944
 slack+0.850
 distingu+0.821
anova+0.820
Neg logit contributions
Narr-0.859
erker-0.798
guyen-0.792
��-0.786
MQ-0.785
Token "
Token ID366
Feature activation+1.90e-01

Pos logit contributions
 spons+0.052
 overboard+0.043
 slack+0.039
 distingu+0.037
 conclud+0.037
Neg logit contributions
Narr-0.050
erker-0.049
guyen-0.048
��-0.048
stood-0.047
TokenH
Token ID39
Feature activation+1.63e-01

Pos logit contributions
 spons+0.646
 overboard+0.544
 slack+0.499
anova+0.495
uana+0.481
Neg logit contributions
Narr-0.395
��-0.390
guyen-0.380
erker-0.379
��-0.368
Tokename
Token ID480
Feature activation+7.62e-01

Pos logit contributions
 spons+0.509
 overboard+0.419
 slack+0.378
razil+0.371
uana+0.370
Neg logit contributions
Narr-0.405
��-0.391
erker-0.375
guyen-0.374
��-0.374
Tokenko
Token ID7204
Feature activation-4.95e-02

Pos logit contributions
 spons+2.438
 overboard+2.116
 slack+1.885
 distingu+1.814
 conclud+1.800
Neg logit contributions
Narr-1.758
��-1.720
guyen-1.663
erker-1.661
��-1.661
Token"
Token ID1
Feature activation-7.09e-02

Pos logit contributions
Narr+0.119
erker+0.113
��+0.112
guyen+0.112
stood+0.109
Neg logit contributions
 spons-0.159
 overboard-0.136
 slack-0.122
 conclud-0.120
 distingu-0.118
Token Nor
Token ID5414
Feature activation+4.82e-01

Pos logit contributions
Narr+0.180
erker+0.175
guyen+0.172
��+0.170
��+0.168
Neg logit contributions
 spons-0.214
 overboard-0.182
 slack-0.165
 conclud-0.157
 Tycoon-0.157
Tokeniy
Token ID7745
Feature activation-1.18e-01

Pos logit contributions
 spons+1.413
 overboard+1.167
 slack+1.036
anova+1.009
 conclud+0.998
Neg logit contributions
Narr-1.324
��-1.238
guyen-1.222
��-1.222
erker-1.221
Tokenuki
Token ID11308
Feature activation+3.17e-02

Pos logit contributions
Narr+0.286
guyen+0.267
��+0.266
erker+0.265
��+0.260
Neg logit contributions
 spons-0.379
 overboard-0.324
 slack-0.289
anova-0.285
 distingu-0.283
Token cross
Token ID3272
Feature activation-2.20e-01

Pos logit contributions
Narr+0.684
guyen+0.671
erker+0.652
��+0.649
stood+0.646
Neg logit contributions
 spons-0.779
 overboard-0.656
 slack-0.603
 conclud-0.579
 distingu-0.571
Tokenfire
Token ID6495
Feature activation-5.28e-01

Pos logit contributions
Narr+0.502
guyen+0.477
erker+0.473
stood+0.472
��+0.468
Neg logit contributions
 spons-0.751
 overboard-0.642
 slack-0.594
 distingu-0.574
 conclud-0.573
Token.
Token ID13
Feature activation-2.47e-02

Pos logit contributions
Narr+1.401
guyen+1.399
��+1.333
erker+1.329
��+1.327
Neg logit contributions
 spons-1.596
 overboard-1.360
 slack-1.231
 conclud-1.162
 distingu-1.157
Token
Token ID198
Feature activation+1.64e-02

Pos logit contributions
Narr+0.066
guyen+0.066
erker+0.065
��+0.065
��+0.063
Neg logit contributions
 spons-0.069
 overboard-0.058
 slack-0.054
 Tycoon-0.051
 conclud-0.050
Token
Token ID198
Feature activation+2.09e-02

Pos logit contributions
 spons+0.054
 overboard+0.045
 conclud+0.041
 distingu+0.041
 slack+0.041
Neg logit contributions
Narr-0.039
erker-0.037
guyen-0.036
stood-0.036
MQ-0.035
TokenAdvertisement
Token ID4723
Feature activation+7.61e-01

Pos logit contributions
 spons+0.060
 overboard+0.051
 slack+0.046
anova+0.044
 Tycoon+0.042
Neg logit contributions
guyen-0.054
erker-0.053
��-0.052
Narr-0.052
��-0.051
Token
Token ID198
Feature activation+1.12e-01

Pos logit contributions
 spons+1.997
 overboard+1.635
 slack+1.464
 Tycoon+1.354
 distingu+1.334
Neg logit contributions
Narr-2.185
guyen-2.139
erker-2.137
��-2.128
stood-2.126
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
 spons+0.363
 overboard+0.306
 conclud+0.276
 slack+0.275
 distingu+0.274
Neg logit contributions
Narr-0.270
erker-0.252
guyen-0.251
stood-0.247
��-0.244
TokenAdvertisement
Token ID4723
Feature activation+6.48e-01

Pos logit contributions
 spons+0.412
 overboard+0.355
 slack+0.319
anova+0.302
 Tycoon+0.295
Neg logit contributions
guyen-0.365
erker-0.363
��-0.355
Narr-0.354
��-0.347
Token
Token ID198
Feature activation+4.82e-02

Pos logit contributions
 spons+1.996
 overboard+1.685
 slack+1.516
 conclud+1.462
 distingu+1.453
Neg logit contributions
Narr-1.626
guyen-1.558
erker-1.542
��-1.529
��-1.510
Token
Token ID198
Feature activation+9.98e-02

Pos logit contributions
 spons+0.158
 overboard+0.133
 conclud+0.120
 distingu+0.119
 slack+0.119
Neg logit contributions
Narr-0.116
erker-0.108
guyen-0.108
stood-0.106
MQ-0.104
Token edit
Token ID4370
Feature activation-7.24e-02

Pos logit contributions
Narr+0.497
erker+0.465
stood+0.464
guyen+0.462
MQ+0.453
Neg logit contributions
 spons-0.493
 overboard-0.398
 conclud-0.365
 distingu-0.362
 slack-0.351
Token ]
Token ID2361
Feature activation-5.69e-02

Pos logit contributions
Narr+0.185
erker+0.170
stood+0.170
guyen+0.168
MQ+0.166
Neg logit contributions
 spons-0.230
 overboard-0.190
 conclud-0.176
 distingu-0.175
 slack-0.168
Token
Token ID198
Feature activation-3.01e-02

Pos logit contributions
Narr+0.155
��+0.153
��+0.151
guyen+0.150
erker+0.150
Neg logit contributions
 spons-0.157
 overboard-0.134
 slack-0.119
 Tycoon-0.113
anova-0.113
Token
Token ID198
Feature activation+2.52e-02

Pos logit contributions
Narr+0.072
erker+0.067
guyen+0.067
stood+0.066
MQ+0.065
Neg logit contributions
 spons-0.099
 overboard-0.083
 conclud-0.075
 distingu-0.075
 slack-0.075
TokenResearch
Token ID25104
Feature activation+1.48e-01

Pos logit contributions
 spons+0.080
 overboard+0.068
 slack+0.060
anova+0.059
 distingu+0.059
Neg logit contributions
erker-0.058
guyen-0.057
��-0.056
��-0.056
Narr-0.056
Token directions
Token ID11678
Feature activation+7.60e-01

Pos logit contributions
 spons+0.425
 overboard+0.352
 slack+0.313
 conclud+0.312
 distingu+0.306
Neg logit contributions
Narr-0.406
erker-0.406
guyen-0.396
stood-0.388
��-0.386
Token [
Token ID685
Feature activation-9.26e-02

Pos logit contributions
 spons+2.323
 overboard+2.001
 slack+1.758
 distingu+1.729
 conclud+1.713
Neg logit contributions
Narr-1.930
erker-1.882
guyen-1.874
stood-1.807
��-1.801
Token edit
Token ID4370
Feature activation-7.16e-03

Pos logit contributions
Narr+0.267
erker+0.251
guyen+0.250
stood+0.249
MQ+0.244
Neg logit contributions
 spons-0.259
 overboard-0.209
 conclud-0.190
 distingu-0.189
 slack-0.185
Token ]
Token ID2361
Feature activation+6.88e-03

Pos logit contributions
Narr+0.018
erker+0.017
stood+0.017
guyen+0.017
MQ+0.017
Neg logit contributions
 spons-0.023
 overboard-0.019
 conclud-0.017
 distingu-0.017
 slack-0.017
Token
Token ID198
Feature activation+8.63e-03

Pos logit contributions
 spons+0.020
 overboard+0.017
 slack+0.015
 conclud+0.015
 distingu+0.014
Neg logit contributions
Narr-0.019
erker-0.018
stood-0.018
guyen-0.018
��-0.018
Token
Token ID198
Feature activation+5.84e-02

Pos logit contributions
 spons+0.028
 overboard+0.024
 conclud+0.021
 slack+0.021
 distingu+0.021
Neg logit contributions
Narr-0.021
guyen-0.019
erker-0.019
stood-0.019
��-0.019
Token sites
Token ID5043
Feature activation-6.37e-02

Pos logit contributions
 spons+0.603
 overboard+0.496
 slack+0.476
 conclud+0.439
 distingu+0.429
Neg logit contributions
Narr-0.512
erker-0.488
��-0.486
guyen-0.483
��-0.475
Token reported
Token ID2098
Feature activation+2.14e-03

Pos logit contributions
Narr+0.168
guyen+0.161
erker+0.157
��+0.156
��+0.156
Neg logit contributions
 spons-0.192
 overboard-0.161
 slack-0.148
 conclud-0.144
 distingu-0.140
Token.
Token ID13
Feature activation+8.30e-02

Pos logit contributions
 spons+0.007
 overboard+0.006
 slack+0.005
 conclud+0.005
 distingu+0.005
Neg logit contributions
Narr-0.005
guyen-0.005
erker-0.005
stood-0.005
��-0.005
Token
Token ID198
Feature activation+9.81e-03

Pos logit contributions
 spons+0.223
 overboard+0.186
 slack+0.172
 Tycoon+0.163
anova+0.162
Neg logit contributions
Narr-0.232
guyen-0.229
erker-0.225
��-0.223
��-0.220
Token
Token ID198
Feature activation+9.50e-03

Pos logit contributions
 spons+0.032
 overboard+0.027
 conclud+0.024
 slack+0.024
 distingu+0.024
Neg logit contributions
Narr-0.024
erker-0.022
guyen-0.022
stood-0.022
��-0.021
TokenAdvertisement
Token ID4723
Feature activation+7.58e-01

Pos logit contributions
 spons+0.027
 overboard+0.022
 slack+0.020
anova+0.020
 distingu+0.019
Neg logit contributions
guyen-0.025
erker-0.025
��-0.024
Narr-0.024
��-0.024
Token Continue
Token ID10054
Feature activation+4.20e-01

Pos logit contributions
 spons+1.972
 overboard+1.602
 slack+1.424
 distingu+1.291
 conclud+1.272
Neg logit contributions
Narr-2.252
��-2.194
erker-2.182
guyen-2.180
stood-2.159
Token reading
Token ID3555
Feature activation+7.29e-02

Pos logit contributions
 spons+1.425
 overboard+1.215
 slack+1.103
 conclud+1.088
 distingu+1.081
Neg logit contributions
Narr-0.946
guyen-0.887
erker-0.880
��-0.859
stood-0.859
Token the
Token ID262
Feature activation+8.14e-02

Pos logit contributions
 spons+0.227
 overboard+0.191
 slack+0.172
 conclud+0.168
 distingu+0.167
Neg logit contributions
Narr-0.184
guyen-0.174
erker-0.173
��-0.169
stood-0.169
Token main
Token ID1388
Feature activation-5.62e-02

Pos logit contributions
 spons+0.224
 overboard+0.182
 conclud+0.161
 distingu+0.159
 slack+0.159
Neg logit contributions
Narr-0.237
erker-0.225
guyen-0.224
stood-0.221
��-0.218
Token story
Token ID1621
Feature activation-2.83e-01

Pos logit contributions
Narr+0.132
guyen+0.124
erker+0.123
stood+0.121
��+0.120
Neg logit contributions
 spons-0.186
 overboard-0.157
 slack-0.142
 conclud-0.141
 distingu-0.140
Token the
Token ID262
Feature activation+4.00e-02

Pos logit contributions
 spons+0.083
 overboard+0.069
 slack+0.062
 distingu+0.060
 conclud+0.060
Neg logit contributions
Narr-0.081
erker-0.076
guyen-0.075
��-0.075
MQ-0.073
Token 2009
Token ID3717
Feature activation-1.62e-02

Pos logit contributions
 spons+0.123
 overboard+0.102
 slack+0.093
 distingu+0.090
 conclud+0.089
Neg logit contributions
Narr-0.105
erker-0.099
guyen-0.099
��-0.097
stood-0.096
Token North
Token ID2258
Feature activation-1.98e-02

Pos logit contributions
Narr+0.040
guyen+0.038
erker+0.038
stood+0.037
��+0.036
Neg logit contributions
 spons-0.053
 overboard-0.044
 slack-0.041
 distingu-0.039
 conclud-0.039
Token American
Token ID1605
Feature activation-2.03e-01

Pos logit contributions
Narr+0.052
guyen+0.051
MQ+0.051
erker+0.050
stood+0.049
Neg logit contributions
 spons-0.059
 overboard-0.049
 slack-0.043
 distingu-0.042
 conclud-0.041
Token Pale
Token ID21706
Feature activation-3.17e-02

Pos logit contributions
Narr+0.457
guyen+0.448
erker+0.444
stood+0.421
��+0.416
Neg logit contributions
 spons-0.694
 overboard-0.591
 slack-0.540
 distingu-0.527
 conclud-0.522
Tokenont
Token ID756
Feature activation+7.47e-01

Pos logit contributions
Narr+0.084
guyen+0.080
MQ+0.078
��+0.078
stood+0.078
Neg logit contributions
 spons-0.093
 overboard-0.079
 slack-0.069
anova-0.067
 distingu-0.067
Tokenological
Token ID2770
Feature activation-9.69e-02

Pos logit contributions
 spons+1.795
 overboard+1.423
 slack+1.255
anova+1.204
 Tycoon+1.159
Neg logit contributions
Narr-2.331
��-2.288
MQ-2.230
guyen-2.224
��-2.204
Token Convention
Token ID11680
Feature activation+4.49e-01

Pos logit contributions
Narr+0.269
erker+0.260
guyen+0.259
stood+0.255
��+0.252
Neg logit contributions
 spons-0.274
 overboard-0.229
 slack-0.202
 distingu-0.198
 conclud-0.196
Token,
Token ID11
Feature activation+4.83e-02

Pos logit contributions
 spons+1.375
 overboard+1.163
 slack+1.022
 conclud+1.012
 distingu+0.983
Neg logit contributions
Narr-1.175
guyen-1.126
erker-1.117
stood-1.106
��-1.085
Token the
Token ID262
Feature activation+5.28e-02

Pos logit contributions
 spons+0.151
 overboard+0.127
 slack+0.113
 conclud+0.110
 distingu+0.110
Neg logit contributions
Narr-0.124
erker-0.118
guyen-0.117
��-0.115
stood-0.115
Token American
Token ID1605
Feature activation-2.77e-01

Pos logit contributions
 spons+0.165
 overboard+0.137
 slack+0.124
 distingu+0.120
 conclud+0.120
Neg logit contributions
Narr-0.136
guyen-0.129
erker-0.129
��-0.125
stood-0.125
Token of
Token ID286
Feature activation+4.97e-02

Pos logit contributions
 spons+0.171
 overboard+0.142
 slack+0.127
 conclud+0.126
 distingu+0.125
Neg logit contributions
Narr-0.152
guyen-0.144
erker-0.143
stood-0.141
��-0.140
Token Transportation
Token ID15198
Feature activation-7.48e-02

Pos logit contributions
 spons+0.158
 overboard+0.134
 slack+0.122
 distingu+0.117
 Tycoon+0.115
Neg logit contributions
Narr-0.121
erker-0.117
��-0.113
��-0.112
guyen-0.112
Token.
Token ID13
Feature activation+2.58e-02

Pos logit contributions
Narr+0.201
guyen+0.194
erker+0.193
��+0.190
��+0.189
Neg logit contributions
 spons-0.222
 overboard-0.189
 slack-0.167
 conclud-0.162
 distingu-0.159
Token
Token ID198
Feature activation-4.36e-02

Pos logit contributions
 spons+0.071
 overboard+0.059
 slack+0.054
 Tycoon+0.052
 conclud+0.050
Neg logit contributions
Narr-0.071
erker-0.070
guyen-0.070
��-0.069
��-0.068
Token
Token ID198
Feature activation-7.22e-02

Pos logit contributions
Narr+0.105
erker+0.097
guyen+0.097
stood+0.096
MQ+0.095
Neg logit contributions
 spons-0.142
 overboard-0.120
 conclud-0.109
 distingu-0.108
 slack-0.108
TokenAdvertisement
Token ID4723
Feature activation+7.35e-01

Pos logit contributions
erker+0.183
guyen+0.180
��+0.179
��+0.177
Narr+0.173
Neg logit contributions
 spons-0.209
 overboard-0.178
 slack-0.156
anova-0.154
razil-0.150
Token
Token ID198
Feature activation+4.06e-02

Pos logit contributions
 spons+1.948
 overboard+1.548
 slack+1.426
 conclud+1.339
 distingu+1.333
Neg logit contributions
Narr-2.107
stood-2.060
��-2.034
erker-2.031
guyen-2.012
Token
Token ID198
Feature activation+7.54e-02

Pos logit contributions
 spons+0.132
 overboard+0.111
 conclud+0.101
 slack+0.100
 distingu+0.100
Neg logit contributions
Narr-0.098
erker-0.091
guyen-0.091
stood-0.090
��-0.088
Token
Token ID447
Feature activation+1.70e-01

Pos logit contributions
 spons+0.214
 overboard+0.182
 slack+0.162
anova+0.159
razil+0.154
Neg logit contributions
erker-0.192
guyen-0.190
��-0.189
��-0.187
Narr-0.182
Token
Token ID250
Feature activation+5.38e-02

Pos logit contributions
 spons+0.530
 overboard+0.442
 slack+0.406
 distingu+0.388
 conclud+0.387
Neg logit contributions
Narr-0.423
guyen-0.404
stood-0.402
erker-0.401
ingen-0.379
TokenIf
Token ID1532
Feature activation+1.93e-01

Pos logit contributions
 spons+0.164
 overboard+0.137
 slack+0.126
 conclud+0.121
 distingu+0.119
Neg logit contributions
Narr-0.136
guyen-0.132
erker-0.131
��-0.130
��-0.127
Token and
Token ID290
Feature activation+1.13e-01

Pos logit contributions
 spons+0.276
 overboard+0.225
 slack+0.203
 conclud+0.197
 distingu+0.195
Neg logit contributions
Narr-0.303
erker-0.295
guyen-0.290
��-0.283
stood-0.283
Token JPMorgan
Token ID43318
Feature activation-1.15e-01

Pos logit contributions
 spons+0.330
 overboard+0.271
 slack+0.249
 conclud+0.241
 distingu+0.240
Neg logit contributions
Narr-0.307
erker-0.295
guyen-0.294
��-0.283
��-0.280
Token Chase
Token ID16346
Feature activation-1.80e-01

Pos logit contributions
Narr+0.302
erker+0.285
guyen+0.284
��+0.275
��+0.274
Neg logit contributions
 spons-0.353
 overboard-0.292
 slack-0.268
 conclud-0.262
 distingu-0.261
Token was
Token ID373
Feature activation+1.76e-01

Pos logit contributions
Narr+0.548
erker+0.522
guyen+0.521
��+0.515
��+0.509
Neg logit contributions
 spons-0.477
 overboard-0.384
 slack-0.342
 conclud-0.329
 distingu-0.324
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
 spons+0.525
 overboard+0.435
 slack+0.390
 conclud+0.380
 distingu+0.376
Neg logit contributions
Narr-0.477
guyen-0.454
erker-0.452
��-0.443
��-0.439
Token subject
Token ID2426
Feature activation+7.35e-01

Pos logit contributions
 spons+0.427
 overboard+0.352
 slack+0.321
 distingu+0.309
 conclud+0.308
Neg logit contributions
Narr-0.367
guyen-0.349
erker-0.346
��-0.339
��-0.336
Token of
Token ID286
Feature activation+8.59e-02

Pos logit contributions
 spons+1.907
 overboard+1.505
 slack+1.372
 conclud+1.336
 distingu+1.325
Neg logit contributions
Narr-2.198
guyen-2.104
erker-2.091
MQ-2.065
stood-2.050
Token 20
Token ID1160
Feature activation+1.20e-01

Pos logit contributions
 spons+0.269
 overboard+0.226
 slack+0.204
 conclud+0.199
 distingu+0.197
Neg logit contributions
Narr-0.218
erker-0.206
guyen-0.206
��-0.202
��-0.199
Token,
Token ID11
Feature activation+1.99e-01

Pos logit contributions
 spons+0.370
 overboard+0.308
 slack+0.281
 conclud+0.275
 distingu+0.271
Neg logit contributions
Narr-0.311
guyen-0.294
erker-0.289
stood-0.285
��-0.279
Token057
Token ID43526
Feature activation-5.71e-03

Pos logit contributions
 spons+0.595
 overboard+0.495
 conclud+0.449
 slack+0.446
 distingu+0.437
Neg logit contributions
Narr-0.519
erker-0.487
guyen-0.483
��-0.480
stood-0.476
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
Narr+0.015
guyen+0.014
erker+0.014
��+0.014
stood+0.014
Neg logit contributions
 spons-0.017
 overboard-0.015
 slack-0.013
 conclud-0.013
 distingu-0.013
Token.
Token ID13
Feature activation-2.79e-01

Pos logit contributions
 spons+0.359
 overboard+0.305
 slack+0.276
 conclud+0.275
 distingu+0.273
Neg logit contributions
Narr-0.243
guyen-0.228
erker-0.227
stood-0.222
��-0.221
Tokenyoutube
Token ID11604
Feature activation-5.12e-01

Pos logit contributions
Narr+0.673
��+0.644
guyen+0.637
��+0.624
erker+0.616
Neg logit contributions
 spons-0.917
 overboard-0.767
 slack-0.701
anova-0.670
 distingu-0.666
Token.
Token ID13
Feature activation-2.02e-01

Pos logit contributions
Narr+1.104
erker+1.009
stood+1.001
guyen+0.995
MQ+0.979
Neg logit contributions
 spons-1.814
 overboard-1.542
 conclud-1.446
 distingu-1.427
 slack-1.391
Tokencom
Token ID785
Feature activation+4.71e-02

Pos logit contributions
Narr+0.544
erker+0.513
stood+0.510
guyen+0.508
MQ+0.498
Neg logit contributions
 spons-0.601
 overboard-0.495
 conclud-0.460
 distingu-0.449
 slack-0.437
Token/
Token ID14
Feature activation-5.26e-02

Pos logit contributions
 spons+0.150
 overboard+0.127
 slack+0.117
 distingu+0.110
 conclud+0.109
Neg logit contributions
Narr-0.116
guyen-0.111
erker-0.109
��-0.108
stood-0.107
Tokenchannel
Token ID17620
Feature activation-8.25e-01

Pos logit contributions
Narr+0.103
��+0.099
guyen+0.098
erker+0.097
��+0.094
Neg logit contributions
 spons-0.194
 overboard-0.167
 slack-0.150
 distingu-0.147
anova-0.146
Token/
Token ID14
Feature activation-3.24e-03

Pos logit contributions
Narr+1.551
stood+1.361
erker+1.360
MQ+1.347
guyen+1.309
Neg logit contributions
 spons-3.190
 overboard-2.724
 conclud-2.634
 distingu-2.603
 conduc-2.481
TokenUC
Token ID9598
Feature activation+4.90e-02

Pos logit contributions
Narr+0.007
guyen+0.007
erker+0.007
��+0.007
��+0.007
Neg logit contributions
 spons-0.011
 overboard-0.009
 slack-0.008
 distingu-0.008
anova-0.008
Token_
Token ID62
Feature activation+3.06e-01

Pos logit contributions
 spons+0.162
 overboard+0.138
 slack+0.123
 distingu+0.121
anova+0.120
Neg logit contributions
Narr-0.111
��-0.105
erker-0.104
guyen-0.104
stood-0.103
TokenK
Token ID42
Feature activation+9.29e-02

Pos logit contributions
 spons+1.011
 overboard+0.859
 slack+0.768
anova+0.757
 distingu+0.749
Neg logit contributions
Narr-0.684
��-0.656
erker-0.642
guyen-0.640
stood-0.635
Tokenk
Token ID74
Feature activation+5.02e-02

Pos logit contributions
 spons+0.310
 overboard+0.262
 slack+0.235
anova+0.230
 distingu+0.230
Neg logit contributions
Narr-0.208
��-0.199
guyen-0.194
erker-0.194
stood-0.192
Tokeniff
Token ID733
Feature activation+1.26e-01

Pos logit contributions
Narr+0.228
erker+0.213
guyen+0.212
stood+0.208
MQ+0.206
Neg logit contributions
 spons-0.348
 overboard-0.296
 conclud-0.275
 distingu-0.270
 slack-0.269
TokenTra
Token ID15721
Feature activation-1.98e-01

Pos logit contributions
 spons+0.490
 overboard+0.427
 slack+0.394
 conclud+0.382
 distingu+0.381
Neg logit contributions
Narr-0.216
guyen-0.204
erker-0.201
��-0.198
stood-0.195
Tokenx
Token ID87
Feature activation-1.68e-01

Pos logit contributions
Narr+0.369
erker+0.340
guyen+0.336
stood+0.332
MQ+0.324
Neg logit contributions
 spons-0.754
 overboard-0.652
 conclud-0.606
 distingu-0.600
 slack-0.597
Token
Token ID198
Feature activation-7.88e-02

Pos logit contributions
Narr+0.461
guyen+0.450
erker+0.444
��+0.441
��+0.437
Neg logit contributions
 spons-0.480
 overboard-0.399
 slack-0.353
 distingu-0.344
 conclud-0.342
Token
Token ID198
Feature activation-8.09e-02

Pos logit contributions
Narr+0.190
erker+0.178
guyen+0.178
stood+0.175
��+0.172
Neg logit contributions
 spons-0.256
 overboard-0.216
 conclud-0.194
 slack-0.194
 distingu-0.193
TokenReviewer
Token ID35407
Feature activation-7.98e-01

Pos logit contributions
Narr+0.205
��+0.203
guyen+0.203
erker+0.202
��+0.198
Neg logit contributions
 spons-0.239
 overboard-0.199
 slack-0.177
anova-0.170
 distingu-0.168
Token:
Token ID25
Feature activation+1.70e-01

Pos logit contributions
Narr+1.908
stood+1.755
erker+1.745
MQ+1.732
guyen+1.715
Neg logit contributions
 spons-2.665
 overboard-2.205
 conclud-2.124
 distingu-2.091
 slack-1.961
Token V
Token ID569
Feature activation+6.19e-02

Pos logit contributions
 spons+0.527
 overboard+0.439
 slack+0.403
 distingu+0.386
 conclud+0.379
Neg logit contributions
Narr-0.446
erker-0.422
guyen-0.419
��-0.413
��-0.408
Tokenthe
Token ID1169
Feature activation+8.37e-02

Pos logit contributions
 spons+0.202
 overboard+0.169
 slack+0.153
 distingu+0.149
anova+0.149
Neg logit contributions
Narr-0.146
guyen-0.138
��-0.137
stood-0.135
erker-0.135
TokenHappy
Token ID25082
Feature activation+6.06e-02

Pos logit contributions
 spons+0.285
 overboard+0.241
 slack+0.219
 distingu+0.217
 conclud+0.214
Neg logit contributions
Narr-0.179
��-0.170
erker-0.169
guyen-0.168
stood-0.165
TokenL
Token ID43
Feature activation+3.47e-02

Pos logit contributions
 spons+0.202
 overboard+0.173
 slack+0.156
 distingu+0.152
 conclud+0.152
Neg logit contributions
Narr-0.132
��-0.130
guyen-0.127
erker-0.126
stood-0.125
Token so
Token ID523
Feature activation+1.90e-01

Pos logit contributions
Narr+0.246
erker+0.235
guyen+0.233
��+0.231
stood+0.228
Neg logit contributions
 spons-0.235
 overboard-0.199
 slack-0.174
 conclud-0.165
 distingu-0.163
Token the
Token ID262
Feature activation-9.40e-03

Pos logit contributions
 spons+0.540
 overboard+0.439
 slack+0.398
 conclud+0.374
 Tycoon+0.373
Neg logit contributions
Narr-0.538
erker-0.520
guyen-0.514
��-0.501
��-0.499
Token Texans
Token ID21012
Feature activation+7.88e-03

Pos logit contributions
Narr+0.026
erker+0.024
guyen+0.024
��+0.024
��+0.023
Neg logit contributions
 spons-0.029
 overboard-0.023
 slack-0.021
 conclud-0.020
 distingu-0.020
Token could
Token ID714
Feature activation+3.88e-02

Pos logit contributions
 spons+0.020
 overboard+0.016
 slack+0.014
 conclud+0.013
 distingu+0.013
Neg logit contributions
Narr-0.025
guyen-0.024
erker-0.023
��-0.023
��-0.023
Token off
Token ID572
Feature activation-3.15e-01

Pos logit contributions
 spons+0.109
 overboard+0.090
 slack+0.080
 conclud+0.078
 distingu+0.078
Neg logit contributions
Narr-0.111
guyen-0.105
erker-0.104
stood-0.103
��-0.103
Tokenload
Token ID2220
Feature activation-7.66e-01

Pos logit contributions
Narr+0.617
erker+0.570
stood+0.558
guyen+0.548
��+0.546
Neg logit contributions
 spons-1.193
 overboard-1.027
 slack-0.958
 distingu-0.923
 conclud-0.921
Token his
Token ID465
Feature activation-1.40e-01

Pos logit contributions
Narr+2.003
erker+1.925
guyen+1.888
��+1.862
MQ+1.827
Neg logit contributions
 spons-2.361
 overboard-1.994
 slack-1.812
 distingu-1.733
 conclud-1.726
Token on
Token ID319
Feature activation-7.38e-02

Pos logit contributions
Narr+0.387
erker+0.368
guyen+0.360
��+0.358
��+0.354
Neg logit contributions
 spons-0.421
 overboard-0.353
 slack-0.319
 distingu-0.300
 conclud-0.292
Tokenerous
Token ID48411
Feature activation+4.33e-03

Pos logit contributions
Narr+0.173
erker+0.158
��+0.157
stood+0.153
��+0.152
Neg logit contributions
 spons-0.249
 overboard-0.217
 slack-0.200
 distingu-0.189
 conclud-0.184
Token contract
Token ID2775
Feature activation-3.26e-01

Pos logit contributions
 spons+0.013
 overboard+0.011
 slack+0.010
 distingu+0.010
 conclud+0.009
Neg logit contributions
Narr-0.012
erker-0.011
guyen-0.011
��-0.011
��-0.010
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
Narr+0.898
erker+0.861
guyen+0.853
��+0.849
stood+0.823
Neg logit contributions
 spons-0.974
 overboard-0.826
 slack-0.735
 conclud-0.701
 distingu-0.696
Token =
Token ID796
Feature activation-1.49e-02

Pos logit contributions
Narr+0.518
��+0.495
guyen+0.490
erker+0.490
��+0.478
Neg logit contributions
 spons-0.789
 overboard-0.668
 slack-0.606
 distingu-0.605
 conclud-0.592
Token $
Token ID720
Feature activation+1.38e-01

Pos logit contributions
Narr+0.040
erker+0.038
guyen+0.038
��+0.036
stood+0.036
Neg logit contributions
 spons-0.045
 overboard-0.037
 slack-0.035
 distingu-0.033
 conclud-0.032
Tokenb
Token ID65
Feature activation+3.44e-02

Pos logit contributions
 spons+0.454
 overboard+0.377
 slack+0.345
anova+0.335
 distingu+0.331
Neg logit contributions
Narr-0.311
guyen-0.307
��-0.305
erker-0.302
��-0.289
Tokenmp
Token ID3149
Feature activation-2.50e-01

Pos logit contributions
 spons+0.124
 overboard+0.107
 conclud+0.100
 distingu+0.098
 slack+0.098
Neg logit contributions
Narr-0.071
erker-0.066
guyen-0.065
stood-0.064
MQ-0.063
Token |
Token ID930
Feature activation-4.00e-01

Pos logit contributions
Narr+0.653
erker+0.624
guyen+0.620
��+0.610
stood+0.596
Neg logit contributions
 spons-0.760
 overboard-0.634
 slack-0.584
 distingu-0.570
 conclud-0.564
Token Select
Token ID9683
Feature activation-7.63e-01

Pos logit contributions
Narr+1.097
erker+1.056
guyen+1.046
��+1.025
stood+1.016
Neg logit contributions
 spons-1.166
 overboard-0.974
 slack-0.896
 distingu-0.867
 conclud-0.836
Token Width
Token ID38807
Feature activation-5.06e-02

Pos logit contributions
Narr+1.674
guyen+1.625
erker+1.600
��+1.555
MQ+1.541
Neg logit contributions
 spons-2.610
 overboard-2.218
 slack-2.066
 distingu-2.027
 conclud-1.985
Token,
Token ID11
Feature activation-1.70e-01

Pos logit contributions
Narr+0.131
erker+0.127
guyen+0.126
��+0.123
stood+0.122
Neg logit contributions
 spons-0.151
 overboard-0.126
 slack-0.117
 distingu-0.113
 conclud-0.109
TokenHeight
Token ID23106
Feature activation-1.26e-01

Pos logit contributions
Narr+0.496
erker+0.491
guyen+0.487
��+0.484
stood+0.478
Neg logit contributions
 spons-0.446
 overboard-0.361
 slack-0.334
 distingu-0.318
 Tycoon-0.309
Token }
Token ID1782
Feature activation+8.89e-02

Pos logit contributions
Narr+0.319
erker+0.309
guyen+0.305
��+0.299
stood+0.295
Neg logit contributions
 spons-0.387
 overboard-0.327
 slack-0.303
 distingu-0.294
 conclud-0.286
Token else
Token ID2073
Feature activation-2.38e-01

Pos logit contributions
 spons+0.241
 overboard+0.199
 slack+0.183
 distingu+0.173
 conclud+0.172
Neg logit contributions
Narr-0.260
guyen-0.248
erker-0.248
��-0.244
stood-0.242
Token,
Token ID11
Feature activation-6.36e-02

Pos logit contributions
 spons+0.262
 overboard+0.224
 slack+0.202
 conclud+0.195
 distingu+0.194
Neg logit contributions
Narr-0.187
guyen-0.179
erker-0.176
��-0.175
��-0.172
Token I
Token ID314
Feature activation+5.50e-02

Pos logit contributions
Narr+0.180
erker+0.167
guyen+0.167
��+0.166
stood+0.165
Neg logit contributions
 spons-0.183
 overboard-0.153
 slack-0.136
 conclud-0.131
 distingu-0.131
Token think
Token ID892
Feature activation-1.11e-01

Pos logit contributions
 spons+0.169
 overboard+0.141
 conclud+0.127
 distingu+0.126
 slack+0.126
Neg logit contributions
Narr-0.141
erker-0.133
guyen-0.132
stood-0.130
MQ-0.128
Token
Token ID198
Feature activation-8.32e-02

Pos logit contributions
Narr+0.311
guyen+0.293
erker+0.293
��+0.287
��+0.284
Neg logit contributions
 spons-0.322
 overboard-0.266
 slack-0.238
 distingu-0.233
 conclud-0.232
Token
Token ID198
Feature activation-5.94e-02

Pos logit contributions
Narr+0.198
erker+0.185
guyen+0.184
stood+0.182
MQ+0.179
Neg logit contributions
 spons-0.274
 overboard-0.231
 conclud-0.210
 distingu-0.208
 slack-0.207
TokenReviewer
Token ID35407
Feature activation-7.57e-01

Pos logit contributions
Narr+0.153
guyen+0.151
erker+0.149
��+0.149
��+0.144
Neg logit contributions
 spons-0.176
 overboard-0.145
 slack-0.130
 distingu-0.124
anova-0.123
Token:
Token ID25
Feature activation+7.91e-02

Pos logit contributions
Narr+1.821
stood+1.672
erker+1.665
MQ+1.654
guyen+1.637
Neg logit contributions
 spons-2.520
 overboard-2.082
 conclud-1.998
 distingu-1.970
 slack-1.851
Token B
Token ID347
Feature activation+2.65e-01

Pos logit contributions
 spons+0.247
 overboard+0.206
 slack+0.189
 distingu+0.181
 conclud+0.178
Neg logit contributions
Narr-0.206
erker-0.195
guyen-0.194
��-0.191
��-0.188
Tokeniz
Token ID528
Feature activation-4.51e-02

Pos logit contributions
 spons+0.861
 overboard+0.733
 slack+0.655
 distingu+0.639
razil+0.633
Neg logit contributions
Narr-0.617
��-0.585
guyen-0.579
stood-0.573
erker-0.573
Tokenr
Token ID81
Feature activation+8.54e-02

Pos logit contributions
Narr+0.104
��+0.100
guyen+0.099
erker+0.097
stood+0.097
Neg logit contributions
 spons-0.148
 overboard-0.125
 slack-0.113
anova-0.111
 conclud-0.110
Token Pix
Token ID21642
Feature activation+3.86e-02

Pos logit contributions
 spons+0.280
 overboard+0.238
 slack+0.212
 conclud+0.210
 distingu+0.208
Neg logit contributions
Narr-0.196
��-0.192
guyen-0.186
erker-0.186
stood-0.184
Token be
Token ID307
Feature activation+1.55e-01

Pos logit contributions
Narr+0.010
guyen+0.010
erker+0.009
��+0.009
stood+0.009
Neg logit contributions
 spons-0.009
 overboard-0.007
 slack-0.007
 distingu-0.006
 conclud-0.006
Token trying
Token ID2111
Feature activation-2.54e-01

Pos logit contributions
 spons+0.441
 overboard+0.364
 slack+0.326
 distingu+0.309
 conclud+0.306
Neg logit contributions
Narr-0.439
guyen-0.431
erker-0.421
��-0.416
stood-0.410
Token to
Token ID284
Feature activation-1.20e-01

Pos logit contributions
Narr+0.674
guyen+0.642
erker+0.641
stood+0.632
MQ+0.625
Neg logit contributions
 spons-0.764
 overboard-0.654
 slack-0.583
 conclud-0.570
 distingu-0.565
Token influence
Token ID4588
Feature activation-1.83e-01

Pos logit contributions
Narr+0.344
guyen+0.330
erker+0.327
��+0.323
stood+0.322
Neg logit contributions
 spons-0.341
 overboard-0.281
 slack-0.252
 distingu-0.241
 conclud-0.240
Token our
Token ID674
Feature activation-3.26e-02

Pos logit contributions
Narr+0.489
erker+0.483
guyen+0.483
��+0.468
��+0.467
Neg logit contributions
 spons-0.534
 overboard-0.459
 slack-0.412
 conclud-0.390
 distingu-0.389
Token electoral
Token ID13901
Feature activation-7.51e-01

Pos logit contributions
Narr+0.071
erker+0.070
guyen+0.069
��+0.066
stood+0.066
Neg logit contributions
 spons-0.113
 overboard-0.097
 slack-0.089
 distingu-0.086
 conclud-0.085
Token process
Token ID1429
Feature activation-2.22e-01

Pos logit contributions
Narr+2.422
erker+2.385
guyen+2.351
��+2.311
��+2.285
Neg logit contributions
 spons-1.840
 overboard-1.489
 slack-1.299
 conclud-1.228
 distingu-1.219
Token,
Token ID11
Feature activation-2.79e-02

Pos logit contributions
Narr+0.572
guyen+0.556
��+0.544
erker+0.541
��+0.532
Neg logit contributions
 spons-0.685
 overboard-0.588
 slack-0.525
 conclud-0.513
 distingu-0.505
Token influence
Token ID4588
Feature activation-4.19e-02

Pos logit contributions
Narr+0.074
erker+0.071
guyen+0.071
��+0.069
stood+0.068
Neg logit contributions
 spons-0.084
 overboard-0.071
 slack-0.063
 conclud-0.061
 distingu-0.061
Token who
Token ID508
Feature activation-1.31e-01

Pos logit contributions
Narr+0.112
guyen+0.109
erker+0.109
��+0.107
��+0.106
Neg logit contributions
 spons-0.124
 overboard-0.106
 slack-0.094
 distingu-0.091
 conclud-0.090
Token becomes
Token ID4329
Feature activation-4.13e-01

Pos logit contributions
Narr+0.362
guyen+0.358
erker+0.355
��+0.349
��+0.349
Neg logit contributions
 spons-0.377
 overboard-0.314
 slack-0.277
 distingu-0.269
 conclud-0.263
Token culture
Token ID3968
Feature activation-2.24e-01

Pos logit contributions
Narr+1.056
erker+1.007
guyen+1.002
��+0.985
��+0.977
Neg logit contributions
 spons-1.193
 overboard-0.995
 slack-0.902
 conclud-0.861
 distingu-0.855
Token,
Token ID11
Feature activation+6.94e-02

Pos logit contributions
Narr+0.578
guyen+0.559
erker+0.545
��+0.537
stood+0.536
Neg logit contributions
 spons-0.691
 overboard-0.581
 slack-0.524
 conclud-0.519
 distingu-0.510
Token he
Token ID339
Feature activation-2.76e-03

Pos logit contributions
 spons+0.231
 overboard+0.200
 slack+0.180
 conclud+0.175
 distingu+0.174
Neg logit contributions
Narr-0.156
erker-0.154
guyen-0.150
��-0.149
stood-0.147
Token becomes
Token ID4329
Feature activation-3.21e-01

Pos logit contributions
Narr+0.008
guyen+0.007
erker+0.007
��+0.007
stood+0.007
Neg logit contributions
 spons-0.008
 overboard-0.007
 slack-0.006
 conclud-0.006
 distingu-0.006
Token rom
Token ID9267
Feature activation-2.20e-01

Pos logit contributions
Narr+0.863
guyen+0.841
erker+0.833
��+0.817
MQ+0.809
Neg logit contributions
 spons-0.947
 overboard-0.796
 slack-0.718
 distingu-0.692
 conclud-0.674
Tokenantically
Token ID31589
Feature activation-7.46e-01

Pos logit contributions
Narr+0.503
guyen+0.495
��+0.484
MQ+0.484
��+0.483
Neg logit contributions
 spons-0.719
 overboard-0.613
 slack-0.569
anova-0.545
 distingu-0.544
Token entangled
Token ID47446
Feature activation-1.30e-01

Pos logit contributions
Narr+1.931
guyen+1.850
erker+1.820
��+1.814
stood+1.795
Neg logit contributions
 spons-2.302
 overboard-1.944
 slack-1.755
 distingu-1.701
 conclud-1.695
Token with
Token ID351
Feature activation-1.73e-01

Pos logit contributions
Narr+0.404
guyen+0.396
erker+0.388
��+0.386
stood+0.383
Neg logit contributions
 spons-0.324
 overboard-0.270
 slack-0.232
 conclud-0.223
 distingu-0.218
Token a
Token ID257
Feature activation-1.07e-02

Pos logit contributions
Narr+0.454
erker+0.441
guyen+0.432
��+0.431
MQ+0.429
Neg logit contributions
 spons-0.515
 overboard-0.433
 slack-0.396
 distingu-0.379
 conclud-0.373
Token prec
Token ID3718
Feature activation-3.09e-02

Pos logit contributions
Narr+0.030
erker+0.029
��+0.029
guyen+0.028
��+0.028
Neg logit contributions
 spons-0.031
 overboard-0.025
 slack-0.023
 distingu-0.022
 conclud-0.021
Tokenocious
Token ID32346
Feature activation-1.25e-01

Pos logit contributions
Narr+0.095
��+0.093
��+0.093
guyen+0.091
stood+0.090
Neg logit contributions
 spons-0.078
 overboard-0.062
 slack-0.055
anova-0.053
razil-0.052
Token.
Token ID13
Feature activation+3.96e-03

Pos logit contributions
Narr+0.368
guyen+0.357
erker+0.344
��+0.342
MQ+0.339
Neg logit contributions
 spons-0.432
 overboard-0.367
 slack-0.331
 distingu-0.318
 conclud-0.314
Token Where
Token ID6350
Feature activation-2.39e-01

Pos logit contributions
 spons+0.012
 overboard+0.010
 slack+0.009
 distingu+0.008
 conclud+0.008
Neg logit contributions
Narr-0.010
guyen-0.010
erker-0.010
��-0.010
��-0.010
Token Jack
Token ID3619
Feature activation-2.39e-01

Pos logit contributions
Narr+0.610
guyen+0.582
erker+0.575
MQ+0.558
stood+0.556
Neg logit contributions
 spons-0.744
 overboard-0.627
 slack-0.565
 distingu-0.546
 conclud-0.543
Token is
Token ID318
Feature activation-4.74e-02

Pos logit contributions
Narr+0.693
guyen+0.663
erker+0.659
��+0.641
stood+0.639
Neg logit contributions
 spons-0.663
 overboard-0.548
 slack-0.492
 distingu-0.474
 conclud-0.463
Token g
Token ID308
Feature activation-2.50e-01

Pos logit contributions
Narr+0.130
guyen+0.125
erker+0.124
��+0.122
��+0.121
Neg logit contributions
 spons-0.140
 overboard-0.118
 slack-0.107
 distingu-0.102
 conclud-0.098
Tokenarr
Token ID3258
Feature activation-7.37e-01

Pos logit contributions
Narr+0.689
��+0.649
guyen+0.647
��+0.643
MQ+0.641
Neg logit contributions
 spons-0.729
 overboard-0.610
 slack-0.538
anova-0.510
 distingu-0.507
Tokenulous
Token ID6985
Feature activation-2.27e-01

Pos logit contributions
Narr+2.310
guyen+2.212
��+2.211
erker+2.186
��+2.174
Neg logit contributions
 spons-1.907
 overboard-1.547
 slack-1.323
 distingu-1.302
 conclud-1.287
Token and
Token ID290
Feature activation+3.60e-02

Pos logit contributions
Narr+0.612
guyen+0.596
erker+0.583
��+0.575
MQ+0.571
Neg logit contributions
 spons-0.668
 overboard-0.577
 slack-0.515
 distingu-0.486
 conclud-0.477
Token annoy
Token ID10072
Feature activation+8.68e-02

Pos logit contributions
 spons+0.102
 overboard+0.087
 slack+0.078
 distingu+0.074
 conclud+0.073
Neg logit contributions
Narr-0.102
guyen-0.098
erker-0.098
��-0.096
��-0.095
Tokeningly
Token ID4420
Feature activation-4.18e-02

Pos logit contributions
 spons+0.375
 overboard+0.338
 slack+0.320
 distingu+0.303
anova+0.303
Neg logit contributions
Narr-0.114
guyen-0.107
erker-0.101
��-0.099
MQ-0.096
Token self
Token ID2116
Feature activation-1.81e-01

Pos logit contributions
Narr+0.119
guyen+0.115
erker+0.114
��+0.113
��+0.111
Neg logit contributions
 spons-0.118
 overboard-0.101
 slack-0.091
 distingu-0.085
 conclud-0.084
Token c
Token ID269
Feature activation-6.29e-02

Pos logit contributions
 spons+0.348
 overboard+0.279
 slack+0.260
 conclud+0.251
 distingu+0.251
Neg logit contributions
Narr-0.314
guyen-0.297
erker-0.296
��-0.290
stood-0.289
Tokenv
Token ID85
Feature activation-3.17e-01

Pos logit contributions
Narr+0.116
erker+0.107
guyen+0.106
stood+0.105
MQ+0.101
Neg logit contributions
 spons-0.241
 overboard-0.208
 conclud-0.194
 distingu-0.192
 slack-0.191
Token2
Token ID17
Feature activation+3.56e-03

Pos logit contributions
Narr+0.754
erker+0.703
guyen+0.699
stood+0.692
MQ+0.680
Neg logit contributions
 spons-1.043
 overboard-0.879
 conclud-0.798
 distingu-0.792
 slack-0.790
Token.
Token ID13
Feature activation+4.96e-02

Pos logit contributions
 spons+0.012
 overboard+0.010
 conclud+0.009
 slack+0.009
 distingu+0.009
Neg logit contributions
Narr-0.008
erker-0.007
guyen-0.007
stood-0.007
��-0.007
Tokenget
Token ID1136
Feature activation-6.42e-02

Pos logit contributions
 spons+0.148
 overboard+0.118
 slack+0.109
anova+0.106
 conclud+0.106
Neg logit contributions
Narr-0.130
guyen-0.126
erker-0.125
��-0.122
stood-0.120
TokenStruct
Token ID44909
Feature activation-7.22e-01

Pos logit contributions
guyen+0.108
erker+0.106
Narr+0.101
��+0.098
��+0.097
Neg logit contributions
 spons-0.245
 overboard-0.211
 slack-0.197
anova-0.196
razil-0.194
Tokenuring
Token ID870
Feature activation-3.45e-01

Pos logit contributions
Narr+1.416
erker+1.293
stood+1.286
guyen+1.260
MQ+1.227
Neg logit contributions
 spons-2.673
 overboard-2.312
 conclud-2.176
 distingu-2.140
 slack-2.110
TokenElement
Token ID20180
Feature activation-6.69e-02

Pos logit contributions
Narr+0.355
guyen+0.327
erker+0.317
��+0.300
stood+0.298
Neg logit contributions
 spons-1.570
 overboard-1.401
 slack-1.311
 conclud-1.290
 distingu-1.288
Token(
Token ID7
Feature activation+2.63e-01

Pos logit contributions
Narr+0.106
guyen+0.098
erker+0.097
��+0.094
stood+0.093
Neg logit contributions
 spons-0.270
 overboard-0.236
 slack-0.219
 conclud-0.216
 distingu-0.214
Tokencv
Token ID33967
Feature activation-1.62e-01

Pos logit contributions
 spons+0.931
 overboard+0.780
 slack+0.716
 conclud+0.710
 distingu+0.707
Neg logit contributions
Narr-0.551
erker-0.516
��-0.513
guyen-0.509
��-0.487
Token2
Token ID17
Feature activation+5.15e-02

Pos logit contributions
Narr+0.390
erker+0.364
guyen+0.363
stood+0.358
��+0.352
Neg logit contributions
 spons-0.527
 overboard-0.444
 conclud-0.401
 slack-0.399
 distingu-0.398
Token the
Token ID262
Feature activation-5.54e-02

Pos logit contributions
Narr+0.077
erker+0.074
guyen+0.073
��+0.072
MQ+0.072
Neg logit contributions
 spons-0.076
 overboard-0.063
 slack-0.058
 distingu-0.053
 conclud-0.051
Token future
Token ID2003
Feature activation-2.54e-02

Pos logit contributions
Narr+0.159
guyen+0.155
erker+0.154
��+0.153
��+0.152
Neg logit contributions
 spons-0.155
 overboard-0.129
 slack-0.119
 distingu-0.108
 conclud-0.107
Token."
Token ID526
Feature activation-7.01e-02

Pos logit contributions
Narr+0.068
guyen+0.068
erker+0.066
MQ+0.066
��+0.066
Neg logit contributions
 spons-0.075
 overboard-0.065
 slack-0.057
 distingu-0.053
 conclud-0.053
Token<|endoftext|>
Token ID50256
Feature activation+7.69e-02

Pos logit contributions
Narr+0.195
erker+0.183
guyen+0.182
stood+0.180
��+0.179
Neg logit contributions
 spons-0.201
 overboard-0.165
 slack-0.151
 conclud-0.147
 distingu-0.145
TokenM
Token ID44
Feature activation-6.15e-02

Pos logit contributions
 spons+0.233
 overboard+0.200
anova+0.177
 slack+0.176
razil+0.170
Neg logit contributions
guyen-0.183
erker-0.182
��-0.179
��-0.176
Narr-0.176
Tokenurd
Token ID2799
Feature activation-7.18e-01

Pos logit contributions
Narr+0.144
��+0.140
stood+0.138
��+0.135
erker+0.132
Neg logit contributions
 spons-0.200
 overboard-0.168
anova-0.151
 slack-0.150
 distingu-0.149
Tokenerer
Token ID11882
Feature activation-4.45e-02

Pos logit contributions
Narr+1.508
guyen+1.433
��+1.433
��+1.406
MQ+1.387
Neg logit contributions
 spons-2.608
 overboard-2.226
 slack-2.029
 distingu-1.988
 conclud-1.973
Token identified
Token ID5174
Feature activation-1.29e-01

Pos logit contributions
Narr+0.120
guyen+0.115
erker+0.114
��+0.114
stood+0.111
Neg logit contributions
 spons-0.131
 overboard-0.112
 slack-0.098
 distingu-0.095
 conclud-0.095
Token in
Token ID287
Feature activation+1.95e-01

Pos logit contributions
Narr+0.374
erker+0.356
��+0.356
guyen+0.354
��+0.346
Neg logit contributions
 spons-0.358
 overboard-0.303
 slack-0.264
 distingu-0.256
 conclud-0.255
Token 41
Token ID6073
Feature activation-6.47e-02

Pos logit contributions
 spons+0.562
 overboard+0.473
 slack+0.426
 distingu+0.402
 conclud+0.401
Neg logit contributions
Narr-0.542
guyen-0.510
��-0.507
erker-0.503
��-0.496
Token-
Token ID12
Feature activation-1.48e-01

Pos logit contributions
Narr+0.183
stood+0.173
guyen+0.173
erker+0.173
��+0.170
Neg logit contributions
 spons-0.182
 overboard-0.154
 slack-0.135
 distingu-0.129
 conclud-0.129
Token and
Token ID290
Feature activation+4.26e-02

Pos logit contributions
Narr+0.097
guyen+0.092
��+0.091
erker+0.091
��+0.089
Neg logit contributions
 spons-0.115
 overboard-0.097
 slack-0.088
 conclud-0.086
 distingu-0.084
Token night
Token ID1755
Feature activation-1.80e-01

Pos logit contributions
 spons+0.126
 overboard+0.105
 slack+0.094
 conclud+0.092
 distingu+0.091
Neg logit contributions
Narr-0.116
guyen-0.109
erker-0.109
��-0.108
stood-0.107
Token!
Token ID0
Feature activation-1.10e-01

Pos logit contributions
Narr+0.474
guyen+0.451
��+0.445
erker+0.445
MQ+0.435
Neg logit contributions
 spons-0.546
 overboard-0.459
 slack-0.414
 conclud-0.403
 distingu-0.394
Token
Token ID198
Feature activation-8.51e-02

Pos logit contributions
Narr+0.294
guyen+0.279
erker+0.279
��+0.275
stood+0.271
Neg logit contributions
 spons-0.329
 overboard-0.274
 slack-0.245
 conclud-0.240
 distingu-0.237
Token
Token ID198
Feature activation-6.91e-02

Pos logit contributions
Narr+0.205
erker+0.192
guyen+0.192
stood+0.189
��+0.186
Neg logit contributions
 spons-0.277
 overboard-0.233
 conclud-0.210
 slack-0.209
 distingu-0.208
TokenRated
Token ID15322
Feature activation-7.18e-01

Pos logit contributions
Narr+0.141
guyen+0.134
erker+0.133
��+0.130
stood+0.128
Neg logit contributions
 spons-0.245
 overboard-0.212
 slack-0.193
 conclud-0.188
 distingu-0.188
Token 5
Token ID642
Feature activation-7.34e-03

Pos logit contributions
Narr+1.905
erker+1.816
guyen+1.808
stood+1.767
��+1.759
Neg logit contributions
 spons-2.154
 overboard-1.819
 slack-1.628
 conclud-1.574
 distingu-1.574
Token out
Token ID503
Feature activation+9.40e-02

Pos logit contributions
Narr+0.018
guyen+0.017
erker+0.017
stood+0.016
��+0.016
Neg logit contributions
 spons-0.024
 overboard-0.020
 slack-0.018
 conclud-0.018
 distingu-0.018
Token of
Token ID286
Feature activation-9.51e-03

Pos logit contributions
 spons+0.284
 overboard+0.236
 conclud+0.211
 slack+0.210
 distingu+0.209
Neg logit contributions
Narr-0.248
guyen-0.233
erker-0.233
stood-0.229
��-0.227
Token 5
Token ID642
Feature activation-2.91e-03

Pos logit contributions
Narr+0.023
erker+0.022
guyen+0.022
stood+0.021
MQ+0.021
Neg logit contributions
 spons-0.031
 overboard-0.026
 conclud-0.023
 distingu-0.023
 slack-0.023
Token by
Token ID416
Feature activation+1.43e-01

Pos logit contributions
Narr+0.008
guyen+0.007
erker+0.007
stood+0.007
��+0.007
Neg logit contributions
 spons-0.009
 overboard-0.007
 slack-0.006
 conclud-0.006
 distingu-0.006
Token c
Token ID269
Feature activation-5.39e-02

Pos logit contributions
 spons+0.281
 overboard+0.228
 slack+0.210
 distingu+0.205
 conclud+0.202
Neg logit contributions
Narr-0.238
guyen-0.224
erker-0.224
stood-0.219
��-0.217
Tokenv
Token ID85
Feature activation-2.64e-01

Pos logit contributions
Narr+0.127
��+0.118
guyen+0.118
erker+0.118
��+0.116
Neg logit contributions
 spons-0.179
 overboard-0.148
 slack-0.135
 distingu-0.133
anova-0.133
Token2
Token ID17
Feature activation-2.19e-03

Pos logit contributions
Narr+0.735
guyen+0.712
erker+0.706
��+0.703
��+0.688
Neg logit contributions
 spons-0.733
 overboard-0.602
 slack-0.540
anova-0.519
razil-0.518
Token.
Token ID13
Feature activation+1.10e-01

Pos logit contributions
Narr+0.005
erker+0.005
guyen+0.005
stood+0.005
��+0.005
Neg logit contributions
 spons-0.007
 overboard-0.006
 slack-0.005
 distingu-0.005
 conclud-0.005
Tokenget
Token ID1136
Feature activation-2.70e-02

Pos logit contributions
 spons+0.362
 overboard+0.297
 slack+0.273
 distingu+0.269
anova+0.266
Neg logit contributions
Narr-0.258
guyen-0.245
erker-0.243
��-0.238
stood-0.237
TokenStruct
Token ID44909
Feature activation-7.10e-01

Pos logit contributions
Narr+0.063
erker+0.059
guyen+0.059
��+0.058
stood+0.057
Neg logit contributions
 spons-0.090
 overboard-0.073
 slack-0.067
anova-0.066
 distingu-0.065
Tokenuring
Token ID870
Feature activation-3.40e-01

Pos logit contributions
Narr+1.686
guyen+1.601
erker+1.570
MQ+1.555
stood+1.552
Neg logit contributions
 spons-2.335
 overboard-1.907
 slack-1.761
 distingu-1.756
anova-1.711
TokenElement
Token ID20180
Feature activation-5.98e-02

Pos logit contributions
guyen+0.699
Narr+0.693
erker+0.667
��+0.661
stood+0.656
Neg logit contributions
 spons-1.173
 overboard-0.991
 slack-0.920
 distingu-0.897
uana-0.894
Token(
Token ID7
Feature activation+2.61e-01

Pos logit contributions
Narr+0.117
guyen+0.111
erker+0.107
��+0.106
stood+0.106
Neg logit contributions
 spons-0.218
 overboard-0.185
 slack-0.172
 distingu-0.169
 conclud-0.166
Tokencv
Token ID33967
Feature activation-1.55e-01

Pos logit contributions
 spons+0.851
 overboard+0.703
 slack+0.634
 distingu+0.624
 conclud+0.612
Neg logit contributions
Narr-0.631
guyen-0.593
erker-0.590
��-0.582
��-0.570
Token2
Token ID17
Feature activation+2.58e-02

Pos logit contributions
Narr+0.421
guyen+0.407
��+0.406
erker+0.404
��+0.397
Neg logit contributions
 spons-0.442
 overboard-0.355
 slack-0.323
 distingu-0.314
anova-0.313
Token bike
Token ID7161
Feature activation+2.91e-02

Pos logit contributions
Narr+0.098
erker+0.093
��+0.092
guyen+0.091
stood+0.090
Neg logit contributions
 spons-0.104
 overboard-0.085
 slack-0.077
 distingu-0.075
 conclud-0.074
Token path
Token ID3108
Feature activation-3.82e-02

Pos logit contributions
 spons+0.083
 overboard+0.068
 slack+0.063
 distingu+0.059
 conclud+0.058
Neg logit contributions
Narr-0.082
erker-0.077
guyen-0.077
��-0.076
��-0.076
Token?
Token ID30
Feature activation-1.54e-01

Pos logit contributions
Narr+0.104
erker+0.100
guyen+0.099
��+0.098
stood+0.097
Neg logit contributions
 spons-0.114
 overboard-0.094
 slack-0.083
 distingu-0.082
 conclud-0.081
Token A
Token ID317
Feature activation+5.21e-02

Pos logit contributions
Narr+0.399
erker+0.382
guyen+0.376
��+0.371
stood+0.367
Neg logit contributions
 spons-0.472
 overboard-0.394
 slack-0.355
 distingu-0.344
 conclud-0.342
Token known
Token ID1900
Feature activation-1.14e-01

Pos logit contributions
 spons+0.153
 overboard+0.125
 slack+0.113
 distingu+0.109
 conclud+0.109
Neg logit contributions
Narr-0.143
erker-0.137
��-0.134
guyen-0.133
MQ-0.133
Token factor
Token ID5766
Feature activation-7.00e-01

Pos logit contributions
Narr+0.311
erker+0.296
��+0.291
guyen+0.290
MQ+0.283
Neg logit contributions
 spons-0.340
 overboard-0.279
 slack-0.256
 distingu-0.245
 conclud-0.236
Token
Token ID851
Feature activation+2.36e-01

Pos logit contributions
Narr+1.980
guyen+1.908
erker+1.892
��+1.862
stood+1.845
Neg logit contributions
 spons-2.016
 overboard-1.664
 slack-1.467
 distingu-1.439
 conclud-1.438
Token we
Token ID356
Feature activation-6.87e-02

Pos logit contributions
 spons+0.712
 overboard+0.592
 slack+0.538
 distingu+0.518
 conclud+0.518
Neg logit contributions
Narr-0.624
erker-0.601
guyen-0.580
��-0.578
��-0.577
Token have
Token ID423
Feature activation-4.30e-02

Pos logit contributions
Narr+0.196
guyen+0.187
erker+0.185
��+0.183
��+0.182
Neg logit contributions
 spons-0.194
 overboard-0.158
 slack-0.141
 distingu-0.137
 conclud-0.137
Token an
Token ID281
Feature activation+2.08e-02

Pos logit contributions
Narr+0.115
erker+0.111
guyen+0.108
��+0.108
��+0.107
Neg logit contributions
 spons-0.129
 overboard-0.108
 slack-0.097
 distingu-0.094
 conclud-0.092
Token aging
Token ID14736
Feature activation-1.95e-01

Pos logit contributions
 spons+0.063
 overboard+0.053
 slack+0.047
 distingu+0.046
 conclud+0.045
Neg logit contributions
Narr-0.056
erker-0.053
guyen-0.052
��-0.051
��-0.051
Token's
Token ID338
Feature activation-3.93e-01

Pos logit contributions
Narr+0.774
guyen+0.739
erker+0.736
��+0.728
stood+0.720
Neg logit contributions
 spons-0.744
 overboard-0.609
 slack-0.540
 conclud-0.537
 distingu-0.515
Token terrorist
Token ID7417
Feature activation-3.26e-01

Pos logit contributions
Narr+1.080
guyen+1.025
erker+1.014
��+1.002
��+0.986
Neg logit contributions
 spons-1.176
 overboard-0.974
 slack-0.878
 distingu-0.843
 conclud-0.841
Token attacks
Token ID3434
Feature activation-2.22e-01

Pos logit contributions
Narr+1.005
guyen+0.966
erker+0.953
��+0.945
stood+0.943
Neg logit contributions
 spons-0.844
 overboard-0.692
 slack-0.600
 distingu-0.579
 conclud-0.579
Token in
Token ID287
Feature activation-2.22e-01

Pos logit contributions
Narr+0.651
guyen+0.637
��+0.622
erker+0.617
stood+0.613
Neg logit contributions
 spons-0.596
 overboard-0.499
 slack-0.438
 conclud-0.428
 distingu-0.416
Token London
Token ID3576
Feature activation-2.35e-01

Pos logit contributions
Narr+0.685
guyen+0.656
erker+0.644
��+0.638
stood+0.633
Neg logit contributions
 spons-0.580
 overboard-0.468
 slack-0.414
 conclud-0.393
 distingu-0.390
Token left
Token ID1364
Feature activation-6.99e-01

Pos logit contributions
Narr+0.629
guyen+0.609
��+0.596
erker+0.592
stood+0.574
Neg logit contributions
 spons-0.703
 overboard-0.592
 slack-0.530
 conclud-0.516
 distingu-0.503
Token seven
Token ID3598
Feature activation-1.22e-01

Pos logit contributions
Narr+1.897
guyen+1.823
erker+1.802
��+1.776
MQ+1.749
Neg logit contributions
 spons-2.060
 overboard-1.736
 slack-1.542
 conclud-1.487
 distingu-1.483
Token dead
Token ID2636
Feature activation-1.76e-01

Pos logit contributions
Narr+0.304
guyen+0.296
erker+0.296
��+0.286
MQ+0.283
Neg logit contributions
 spons-0.377
 overboard-0.329
 slack-0.294
 distingu-0.284
 conclud-0.275
Token and
Token ID290
Feature activation-1.99e-01

Pos logit contributions
Narr+0.486
erker+0.476
guyen+0.474
��+0.466
stood+0.453
Neg logit contributions
 spons-0.494
 overboard-0.427
 slack-0.377
 conclud-0.359
 distingu-0.355
Token 48
Token ID4764
Feature activation-1.85e-01

Pos logit contributions
Narr+0.517
guyen+0.491
erker+0.489
��+0.485
stood+0.472
Neg logit contributions
 spons-0.607
 overboard-0.515
 slack-0.459
 conclud-0.449
 distingu-0.446
Token injured
Token ID6686
Feature activation-2.69e-01

Pos logit contributions
Narr+0.460
guyen+0.450
erker+0.436
��+0.429
stood+0.427
Neg logit contributions
 spons-0.574
 overboard-0.506
 slack-0.448
 distingu-0.429
 conclud-0.428
Token
Token ID447
Feature activation-1.79e-01

Pos logit contributions
Narr+0.185
guyen+0.182
erker+0.179
��+0.176
��+0.175
Neg logit contributions
 spons-0.241
 overboard-0.202
 slack-0.188
 conclud-0.179
 Tycoon-0.178
Token
Token ID251
Feature activation-9.19e-02

Pos logit contributions
Narr+0.402
guyen+0.380
erker+0.375
stood+0.374
MQ+0.356
Neg logit contributions
 spons-0.607
 overboard-0.516
 slack-0.472
 conclud-0.461
 distingu-0.454
Token
Token ID198
Feature activation+5.72e-03

Pos logit contributions
Narr+0.246
guyen+0.238
erker+0.235
��+0.233
��+0.233
Neg logit contributions
 spons-0.272
 overboard-0.223
 slack-0.204
 conclud-0.196
 distingu-0.193
Token
Token ID198
Feature activation+2.11e-02

Pos logit contributions
 spons+0.018
 overboard+0.016
 slack+0.014
 conclud+0.014
 distingu+0.014
Neg logit contributions
Narr-0.014
guyen-0.013
erker-0.013
stood-0.013
��-0.013
TokenBoth
Token ID10265
Feature activation-1.51e-01

Pos logit contributions
 spons+0.064
 overboard+0.054
 slack+0.049
anova+0.048
razil+0.047
Neg logit contributions
erker-0.050
guyen-0.050
��-0.050
Narr-0.049
��-0.049
Token users
Token ID2985
Feature activation-6.93e-01

Pos logit contributions
Narr+0.418
erker+0.397
guyen+0.396
��+0.390
��+0.390
Neg logit contributions
 spons-0.442
 overboard-0.360
 slack-0.327
 conclud-0.316
 distingu-0.315
Token say
Token ID910
Feature activation+6.62e-02

Pos logit contributions
Narr+1.948
guyen+1.848
erker+1.834
��+1.803
stood+1.803
Neg logit contributions
 spons-1.975
 overboard-1.629
 slack-1.445
 conclud-1.426
 distingu-1.413
Token they
Token ID484
Feature activation-5.16e-02

Pos logit contributions
 spons+0.185
 overboard+0.152
 slack+0.136
 conclud+0.129
 distingu+0.129
Neg logit contributions
Narr-0.194
erker-0.184
guyen-0.181
��-0.181
��-0.179
Token received
Token ID2722
Feature activation+1.93e-02

Pos logit contributions
Narr+0.145
guyen+0.137
erker+0.136
��+0.134
��+0.134
Neg logit contributions
 spons-0.148
 overboard-0.122
 slack-0.109
 conclud-0.107
 distingu-0.106
Token notices
Token ID19748
Feature activation+1.58e-02

Pos logit contributions
 spons+0.058
 overboard+0.048
 slack+0.044
 distingu+0.042
 conclud+0.041
Neg logit contributions
Narr-0.053
erker-0.050
guyen-0.050
��-0.049
��-0.048
Token from
Token ID422
Feature activation+1.37e-01

Pos logit contributions
 spons+0.043
 overboard+0.036
 slack+0.032
 conclud+0.030
 distingu+0.030
Neg logit contributions
Narr-0.047
guyen-0.045
erker-0.045
��-0.044
��-0.044
Token for
Token ID329
Feature activation-1.00e-01

Pos logit contributions
Narr+0.563
guyen+0.542
erker+0.529
��+0.523
��+0.523
Neg logit contributions
 spons-0.656
 overboard-0.557
 slack-0.498
 distingu-0.480
 conclud-0.479
Token himself
Token ID2241
Feature activation-1.87e-01

Pos logit contributions
Narr+0.259
guyen+0.248
erker+0.247
��+0.240
��+0.240
Neg logit contributions
 spons-0.308
 overboard-0.259
 slack-0.233
 distingu-0.226
 conclud-0.226
Token that
Token ID326
Feature activation-1.13e-01

Pos logit contributions
Narr+0.491
guyen+0.483
��+0.466
��+0.464
erker+0.463
Neg logit contributions
 spons-0.571
 overboard-0.489
 slack-0.433
 conclud-0.418
 distingu-0.418
Token he
Token ID339
Feature activation-1.72e-01

Pos logit contributions
Narr+0.308
guyen+0.295
erker+0.294
��+0.287
MQ+0.285
Neg logit contributions
 spons-0.333
 overboard-0.277
 slack-0.248
 distingu-0.242
 conclud-0.241
Token's
Token ID338
Feature activation-8.90e-02

Pos logit contributions
Narr+0.470
guyen+0.444
erker+0.443
stood+0.435
��+0.433
Neg logit contributions
 spons-0.503
 overboard-0.416
 slack-0.369
 conclud-0.366
 distingu-0.363
Token applied
Token ID5625
Feature activation-6.90e-01

Pos logit contributions
Narr+0.233
guyen+0.222
erker+0.221
��+0.215
stood+0.214
Neg logit contributions
 spons-0.270
 overboard-0.227
 slack-0.203
 distingu-0.199
 conclud-0.198
Token to
Token ID284
Feature activation+9.67e-03

Pos logit contributions
Narr+1.783
guyen+1.701
erker+1.684
��+1.655
MQ+1.647
Neg logit contributions
 spons-2.142
 overboard-1.826
 slack-1.628
 conclud-1.579
 distingu-1.577
Token the
Token ID262
Feature activation-2.97e-02

Pos logit contributions
 spons+0.028
 overboard+0.023
 slack+0.021
 conclud+0.021
 distingu+0.020
Neg logit contributions
Narr-0.026
erker-0.026
guyen-0.025
��-0.025
��-0.025
Token rest
Token ID1334
Feature activation-1.04e-01

Pos logit contributions
Narr+0.089
erker+0.085
guyen+0.085
��+0.083
��+0.083
Neg logit contributions
 spons-0.080
 overboard-0.065
 slack-0.058
 distingu-0.055
 conclud-0.055
Token of
Token ID286
Feature activation-1.16e-02

Pos logit contributions
Narr+0.311
guyen+0.302
��+0.300
erker+0.299
��+0.295
Neg logit contributions
 spons-0.275
 overboard-0.230
 slack-0.202
 conclud-0.181
razil-0.180
Token the
Token ID262
Feature activation+8.62e-02

Pos logit contributions
Narr+0.031
erker+0.031
guyen+0.030
��+0.030
��+0.029
Neg logit contributions
 spons-0.034
 overboard-0.028
 slack-0.026
 conclud-0.024
 distingu-0.024
Tokenm
Token ID76
Feature activation-8.70e-02

Pos logit contributions
Narr+0.193
guyen+0.179
erker+0.178
��+0.176
��+0.172
Neg logit contributions
 spons-0.299
 overboard-0.254
 slack-0.231
 conclud-0.228
 distingu-0.227
Token working
Token ID1762
Feature activation-6.15e-02

Pos logit contributions
Narr+0.245
guyen+0.234
erker+0.234
stood+0.230
��+0.229
Neg logit contributions
 spons-0.248
 overboard-0.207
 slack-0.184
 distingu-0.176
 conclud-0.175
Token on
Token ID319
Feature activation+1.06e-03

Pos logit contributions
Narr+0.181
guyen+0.176
erker+0.173
��+0.172
��+0.171
Neg logit contributions
 spons-0.165
 overboard-0.142
 slack-0.122
 conclud-0.116
 distingu-0.114
Token a
Token ID257
Feature activation-1.00e-01

Pos logit contributions
 spons+0.003
 overboard+0.003
 slack+0.002
 conclud+0.002
 distingu+0.002
Neg logit contributions
Narr-0.003
guyen-0.003
erker-0.003
��-0.003
��-0.003
Token little
Token ID1310
Feature activation-1.63e-01

Pos logit contributions
Narr+0.279
guyen+0.264
erker+0.261
��+0.261
��+0.259
Neg logit contributions
 spons-0.288
 overboard-0.243
 slack-0.217
 distingu-0.210
 conclud-0.205
Token fir
Token ID37979
Feature activation-6.85e-01

Pos logit contributions
Narr+0.458
guyen+0.438
erker+0.434
��+0.426
��+0.426
Neg logit contributions
 spons-0.466
 overboard-0.398
 slack-0.350
 distingu-0.337
 conclud-0.331
Tokenmer
Token ID647
Feature activation-5.15e-02

Pos logit contributions
Narr+1.592
guyen+1.480
��+1.468
stood+1.450
MQ+1.441
Neg logit contributions
 spons-2.325
 overboard-2.009
 slack-1.821
 conclud-1.765
 distingu-1.744
Token in
Token ID287
Feature activation-1.93e-02

Pos logit contributions
Narr+0.139
guyen+0.135
��+0.131
erker+0.131
��+0.131
Neg logit contributions
 spons-0.153
 overboard-0.131
 slack-0.116
 conclud-0.111
 distingu-0.111
Token texture
Token ID11743
Feature activation-1.32e-01

Pos logit contributions
Narr+0.054
guyen+0.052
��+0.051
erker+0.051
��+0.050
Neg logit contributions
 spons-0.057
 overboard-0.047
 slack-0.043
 conclud-0.041
 distingu-0.040
Token.
Token ID13
Feature activation-3.05e-02

Pos logit contributions
Narr+0.346
guyen+0.337
erker+0.329
��+0.329
��+0.326
Neg logit contributions
 spons-0.402
 overboard-0.341
 slack-0.303
 conclud-0.297
 distingu-0.290
Token
Token ID198
Feature activation-1.41e-01

Pos logit contributions
Narr+0.079
guyen+0.077
erker+0.076
��+0.075
��+0.074
Neg logit contributions
 spons-0.091
 overboard-0.077
 slack-0.070
 conclud-0.067
 distingu-0.067
Token sound
Token ID2128
Feature activation-1.75e-01

Pos logit contributions
Narr+0.162
erker+0.154
guyen+0.153
��+0.150
stood+0.149
Neg logit contributions
 spons-0.170
 overboard-0.141
 slack-0.128
 distingu-0.122
 conclud-0.122
Token system
Token ID1080
Feature activation-1.99e-01

Pos logit contributions
Narr+0.510
erker+0.483
guyen+0.481
��+0.473
��+0.468
Neg logit contributions
 spons-0.485
 overboard-0.399
 slack-0.358
 distingu-0.347
 conclud-0.344
Token.
Token ID13
Feature activation-3.29e-02

Pos logit contributions
Narr+0.541
guyen+0.514
erker+0.505
��+0.499
MQ+0.492
Neg logit contributions
 spons-0.600
 overboard-0.499
 slack-0.447
 conclud-0.435
 distingu-0.431
Token
Token ID198
Feature activation-7.16e-02

Pos logit contributions
Narr+0.088
guyen+0.084
erker+0.084
��+0.082
stood+0.081
Neg logit contributions
 spons-0.097
 overboard-0.081
 slack-0.073
 conclud-0.070
 distingu-0.070
Token
Token ID198
Feature activation-2.42e-02

Pos logit contributions
Narr+0.172
erker+0.160
guyen+0.160
stood+0.158
MQ+0.155
Neg logit contributions
 spons-0.234
 overboard-0.197
 conclud-0.179
 distingu-0.177
 slack-0.177
TokenRated
Token ID15322
Feature activation-6.82e-01

Pos logit contributions
Narr+0.050
guyen+0.048
erker+0.047
��+0.046
��+0.046
Neg logit contributions
 spons-0.085
 overboard-0.073
 slack-0.067
 distingu-0.065
 conclud-0.065
Token 5
Token ID642
Feature activation+3.56e-02

Pos logit contributions
Narr+1.799
erker+1.715
guyen+1.707
stood+1.670
��+1.663
Neg logit contributions
 spons-2.056
 overboard-1.739
 slack-1.557
 conclud-1.506
 distingu-1.505
Token out
Token ID503
Feature activation+1.42e-01

Pos logit contributions
 spons+0.114
 overboard+0.096
 slack+0.086
 conclud+0.086
 distingu+0.085
Neg logit contributions
Narr-0.087
guyen-0.082
erker-0.081
stood-0.080
��-0.079
Token of
Token ID286
Feature activation+4.17e-02

Pos logit contributions
 spons+0.428
 overboard+0.355
 conclud+0.316
 slack+0.316
 distingu+0.314
Neg logit contributions
Narr-0.374
guyen-0.352
erker-0.352
stood-0.346
��-0.342
Token 5
Token ID642
Feature activation+2.70e-02

Pos logit contributions
 spons+0.133
 overboard+0.111
 slack+0.100
 conclud+0.100
 distingu+0.099
Neg logit contributions
Narr-0.103
guyen-0.097
erker-0.097
stood-0.095
��-0.094
Token by
Token ID416
Feature activation+1.89e-01

Pos logit contributions
 spons+0.080
 overboard+0.066
 slack+0.059
 conclud+0.058
 distingu+0.058
Neg logit contributions
Narr-0.073
guyen-0.069
erker-0.068
stood-0.067
��-0.067
Token that
Token ID326
Feature activation-5.29e-02

Pos logit contributions
 spons+0.063
 overboard+0.053
 slack+0.047
 conclud+0.044
 distingu+0.043
Neg logit contributions
Narr-0.066
guyen-0.064
erker-0.063
��-0.062
��-0.061
Token Trump
Token ID1301
Feature activation-2.06e-02

Pos logit contributions
Narr+0.143
guyen+0.137
erker+0.135
��+0.135
MQ+0.131
Neg logit contributions
 spons-0.159
 overboard-0.134
 slack-0.122
 conclud-0.115
 distingu-0.114
Token has
Token ID468
Feature activation-2.70e-02

Pos logit contributions
Narr+0.060
guyen+0.058
erker+0.057
��+0.057
stood+0.056
Neg logit contributions
 spons-0.057
 overboard-0.047
 slack-0.042
 conclud-0.040
 distingu-0.040
Token indeed
Token ID5600
Feature activation-1.01e-01

Pos logit contributions
Narr+0.074
guyen+0.071
erker+0.071
��+0.070
MQ+0.069
Neg logit contributions
 spons-0.079
 overboard-0.066
 slack-0.060
 distingu-0.057
 conclud-0.057
Token become
Token ID1716
Feature activation-2.40e-01

Pos logit contributions
Narr+0.275
guyen+0.264
erker+0.261
��+0.258
MQ+0.255
Neg logit contributions
 spons-0.298
 overboard-0.251
 slack-0.226
 distingu-0.215
 conclud-0.215
Token electoral
Token ID13901
Feature activation-6.82e-01

Pos logit contributions
Narr+0.646
guyen+0.624
erker+0.616
��+0.601
MQ+0.595
Neg logit contributions
 spons-0.718
 overboard-0.614
 slack-0.554
 distingu-0.521
 conclud-0.512
Token poison
Token ID8764
Feature activation-1.28e-01

Pos logit contributions
Narr+1.865
guyen+1.764
erker+1.759
��+1.734
��+1.713
Neg logit contributions
 spons-2.026
 overboard-1.691
 slack-1.526
 conclud-1.481
 distingu-1.468
Token in
Token ID287
Feature activation-6.18e-02

Pos logit contributions
Narr+0.350
guyen+0.339
��+0.328
stood+0.326
MQ+0.322
Neg logit contributions
 spons-0.375
 overboard-0.328
 slack-0.292
 distingu-0.271
 conclud-0.270
Token the
Token ID262
Feature activation-4.28e-02

Pos logit contributions
Narr+0.172
guyen+0.167
erker+0.162
��+0.161
MQ+0.159
Neg logit contributions
 spons-0.180
 overboard-0.149
 slack-0.137
 conclud-0.128
 distingu-0.126
Token kind
Token ID1611
Feature activation-1.03e-01

Pos logit contributions
Narr+0.110
guyen+0.106
��+0.104
erker+0.103
��+0.102
Neg logit contributions
 spons-0.133
 overboard-0.111
 slack-0.102
 distingu-0.096
 conclud-0.096
Token of
Token ID286
Feature activation-4.02e-02

Pos logit contributions
Narr+0.308
guyen+0.294
erker+0.294
��+0.285
stood+0.284
Neg logit contributions
 spons-0.276
 overboard-0.220
 slack-0.202
 distingu-0.190
 conclud-0.187
Token}
Token ID92
Feature activation-4.26e-02

Pos logit contributions
Narr+0.206
guyen+0.200
erker+0.193
��+0.191
stood+0.190
Neg logit contributions
 spons-0.278
 overboard-0.239
 slack-0.219
 conclud-0.214
 distingu-0.213
Token ->
Token ID4613
Feature activation-2.37e-01

Pos logit contributions
Narr+0.096
guyen+0.091
erker+0.089
stood+0.089
��+0.087
Neg logit contributions
 spons-0.144
 overboard-0.124
 slack-0.115
 distingu-0.111
 conclud-0.111
Token "
Token ID366
Feature activation-7.14e-02

Pos logit contributions
Narr+0.685
erker+0.655
guyen+0.653
stood+0.637
MQ+0.622
Neg logit contributions
 spons-0.664
 overboard-0.547
 slack-0.493
 distingu-0.476
 conclud-0.471
TokenA
Token ID32
Feature activation-2.64e-01

Pos logit contributions
Narr+0.165
guyen+0.160
erker+0.159
��+0.154
stood+0.152
Neg logit contributions
 spons-0.232
 overboard-0.199
 slack-0.179
anova-0.173
 conclud-0.172
Token",
Token ID1600
Feature activation-2.60e-01

Pos logit contributions
Narr+0.762
guyen+0.723
erker+0.723
stood+0.712
��+0.704
Neg logit contributions
 spons-0.728
 overboard-0.595
 slack-0.536
 conclud-0.524
 distingu-0.523
Token {
Token ID1391
Feature activation-6.80e-01

Pos logit contributions
Narr+0.852
erker+0.821
guyen+0.816
stood+0.803
MQ+0.788
Neg logit contributions
 spons-0.613
 overboard-0.495
 slack-0.437
 distingu-0.419
 conclud-0.418
Token1
Token ID16
Feature activation-2.31e-01

Pos logit contributions
Narr+1.772
guyen+1.713
erker+1.706
��+1.673
stood+1.650
Neg logit contributions
 spons-2.036
 overboard-1.717
 slack-1.536
 conclud-1.486
 distingu-1.475
Token,
Token ID11
Feature activation-2.29e-01

Pos logit contributions
Narr+0.513
guyen+0.481
erker+0.478
stood+0.467
��+0.466
Neg logit contributions
 spons-0.788
 overboard-0.673
 slack-0.610
 conclud-0.604
 distingu-0.600
Token 14
Token ID1478
Feature activation-8.30e-02

Pos logit contributions
Narr+0.612
erker+0.585
guyen+0.583
��+0.570
stood+0.567
Neg logit contributions
 spons-0.678
 overboard-0.569
 slack-0.512
 conclud-0.495
 distingu-0.491
Token}
Token ID92
Feature activation-4.43e-02

Pos logit contributions
Narr+0.194
guyen+0.186
erker+0.181
stood+0.178
��+0.177
Neg logit contributions
 spons-0.271
 overboard-0.231
 slack-0.215
 conclud-0.211
 distingu-0.211
Token ->
Token ID4613
Feature activation-1.81e-01

Pos logit contributions
Narr+0.086
guyen+0.084
stood+0.082
erker+0.080
��+0.078
Neg logit contributions
 spons-0.161
 overboard-0.140
 slack-0.132
 distingu-0.128
 conclud-0.125
Token from
Token ID422
Feature activation-9.68e-03

Pos logit contributions
 spons+0.647
 overboard+0.558
 slack+0.502
 distingu+0.465
 conclud+0.465
Neg logit contributions
Narr-0.653
guyen-0.633
��-0.633
erker-0.617
��-0.611
Token approaching
Token ID13885
Feature activation+1.52e-01

Pos logit contributions
Narr+0.029
erker+0.028
guyen+0.027
��+0.027
��+0.027
Neg logit contributions
 spons-0.026
 overboard-0.022
 slack-0.019
 distingu-0.019
 conclud-0.018
Token Mr
Token ID1770
Feature activation-9.37e-02

Pos logit contributions
 spons+0.435
 overboard+0.366
 slack+0.334
 distingu+0.322
 conclud+0.313
Neg logit contributions
Narr-0.417
guyen-0.404
erker-0.401
��-0.398
��-0.390
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
Narr+0.204
erker+0.187
stood+0.187
guyen+0.186
MQ+0.182
Neg logit contributions
 spons-0.330
 overboard-0.280
 conclud-0.260
 distingu-0.258
 slack-0.253
Token Ahmad
Token ID24152
Feature activation+4.48e-01

Pos logit contributions
 spons+0.482
 overboard+0.397
 slack+0.366
 distingu+0.345
 conclud+0.340
Neg logit contributions
Narr-0.500
erker-0.480
guyen-0.479
��-0.467
��-0.459
Tokenine
Token ID500
Feature activation+6.47e-01

Pos logit contributions
 spons+1.327
 overboard+1.126
 slack+1.022
 conclud+0.985
 distingu+0.984
Neg logit contributions
Narr-1.172
guyen-1.125
erker-1.122
��-1.105
��-1.079
Tokenjad
Token ID38442
Feature activation+5.89e-01

Pos logit contributions
 spons+1.568
 overboard+1.361
 slack+1.194
 conclud+1.092
 distingu+1.085
Neg logit contributions
Narr-1.978
erker-1.952
��-1.950
guyen-1.934
stood-1.871
Token as
Token ID355
Feature activation+5.24e-03

Pos logit contributions
 spons+1.627
 overboard+1.378
 slack+1.223
 conclud+1.189
 distingu+1.159
Neg logit contributions
Narr-1.673
��-1.621
erker-1.614
guyen-1.609
stood-1.557
Token he
Token ID339
Feature activation+3.43e-02

Pos logit contributions
 spons+0.015
 overboard+0.012
 slack+0.011
 distingu+0.010
 conclud+0.010
Neg logit contributions
Narr-0.015
erker-0.015
guyen-0.014
��-0.014
��-0.014
Token arrived
Token ID5284
Feature activation+1.46e-01

Pos logit contributions
 spons+0.094
 overboard+0.079
 slack+0.071
 distingu+0.067
 conclud+0.067
Neg logit contributions
Narr-0.100
guyen-0.097
erker-0.095
��-0.094
��-0.094
Token in
Token ID287
Feature activation+1.08e-01

Pos logit contributions
 spons+0.383
 overboard+0.323
 slack+0.281
 onstage+0.265
 ashore+0.264
Neg logit contributions
Narr-0.444
erker-0.433
guyen-0.433
��-0.426
��-0.422
Token of
Token ID286
Feature activation-4.71e-03

Pos logit contributions
Narr+0.364
erker+0.354
guyen+0.346
MQ+0.345
��+0.344
Neg logit contributions
 spons-0.326
 overboard-0.274
 slack-0.246
 distingu-0.232
 conclud-0.227
Token a
Token ID257
Feature activation+2.10e-02

Pos logit contributions
Narr+0.013
erker+0.012
guyen+0.012
MQ+0.012
��+0.012
Neg logit contributions
 spons-0.014
 overboard-0.012
 slack-0.010
 conclud-0.010
 distingu-0.010
Token security
Token ID2324
Feature activation+5.14e-02

Pos logit contributions
 spons+0.059
 overboard+0.049
 slack+0.044
 distingu+0.042
 conclud+0.041
Neg logit contributions
Narr-0.061
��-0.057
erker-0.057
guyen-0.057
��-0.056
Token guard
Token ID4860
Feature activation-6.46e-02

Pos logit contributions
 spons+0.146
 overboard+0.126
 slack+0.114
 distingu+0.106
 conclud+0.105
Neg logit contributions
Narr-0.145
��-0.139
guyen-0.137
��-0.137
MQ-0.136
Token's
Token ID338
Feature activation-4.03e-02

Pos logit contributions
Narr+0.189
��+0.178
guyen+0.176
stood+0.174
erker+0.174
Neg logit contributions
 spons-0.180
 overboard-0.154
 slack-0.135
 distingu-0.128
 conclud-0.128
Token ear
Token ID1027
Feature activation+4.70e-01

Pos logit contributions
Narr+0.120
erker+0.114
guyen+0.114
��+0.113
MQ+0.111
Neg logit contributions
 spons-0.109
 overboard-0.091
 slack-0.082
 distingu-0.077
 conclud-0.076
Token with
Token ID351
Feature activation-1.69e-02

Pos logit contributions
 spons+1.448
 overboard+1.265
 slack+1.148
 distingu+1.100
 conclud+1.063
Neg logit contributions
Narr-1.192
erker-1.152
guyen-1.148
��-1.129
stood-1.109
Token a
Token ID257
Feature activation+3.12e-03

Pos logit contributions
Narr+0.046
erker+0.043
guyen+0.042
MQ+0.042
��+0.042
Neg logit contributions
 spons-0.050
 overboard-0.044
 slack-0.041
 distingu-0.037
 conclud-0.037
Token hat
Token ID6877
Feature activation+3.17e-01

Pos logit contributions
 spons+0.009
 overboard+0.007
 slack+0.006
 distingu+0.006
 conclud+0.006
Neg logit contributions
Narr-0.009
guyen-0.009
erker-0.009
��-0.009
MQ-0.008
Tokenchet
Token ID20043
Feature activation-2.87e-01

Pos logit contributions
 spons+0.945
 overboard+0.812
 slack+0.720
 distingu+0.691
 conclud+0.689
Neg logit contributions
Narr-0.852
guyen-0.802
��-0.795
erker-0.790
stood-0.777
Token at
Token ID379
Feature activation-2.99e-02

Pos logit contributions
Narr+0.801
guyen+0.761
��+0.753
erker+0.751
stood+0.736
Neg logit contributions
 spons-0.832
 overboard-0.700
 slack-0.618
 conclud-0.599
 distingu-0.597
Token million
Token ID1510
Feature activation-1.07e-01

Pos logit contributions
Narr+0.505
erker+0.482
stood+0.459
guyen+0.452
��+0.443
Neg logit contributions
 spons-1.032
 overboard-0.896
 slack-0.828
 conclud-0.818
 distingu-0.812
Token a
Token ID257
Feature activation-1.09e-01

Pos logit contributions
Narr+0.291
��+0.280
guyen+0.278
erker+0.277
��+0.270
Neg logit contributions
 spons-0.317
 overboard-0.267
 slack-0.237
 conclud-0.225
 distingu-0.224
Token year
Token ID614
Feature activation-2.46e-02

Pos logit contributions
Narr+0.275
guyen+0.259
erker+0.258
��+0.253
stood+0.252
Neg logit contributions
 spons-0.339
 overboard-0.287
 slack-0.258
 distingu-0.250
 conclud-0.249
Token,
Token ID11
Feature activation-1.24e-01

Pos logit contributions
Narr+0.071
guyen+0.069
��+0.068
erker+0.068
��+0.066
Neg logit contributions
 spons-0.069
 overboard-0.058
 slack-0.052
 conclud-0.049
 distingu-0.049
Token after
Token ID706
Feature activation-1.70e-01

Pos logit contributions
Narr+0.336
erker+0.319
guyen+0.316
��+0.314
stood+0.307
Neg logit contributions
 spons-0.369
 overboard-0.308
 slack-0.276
 conclud-0.269
 distingu-0.266
Token opting
Token ID37529
Feature activation+5.20e-01

Pos logit contributions
Narr+0.486
erker+0.467
��+0.463
guyen+0.460
��+0.447
Neg logit contributions
 spons-0.486
 overboard-0.397
 slack-0.359
 conclud-0.345
 distingu-0.343
Token in
Token ID287
Feature activation-1.67e-01

Pos logit contributions
 spons+1.351
 overboard+1.225
 slack+1.011
 distingu+0.961
 onstage+0.951
Neg logit contributions
Narr-1.522
erker-1.489
��-1.458
guyen-1.457
stood-1.455
Token for
Token ID329
Feature activation-1.81e-01

Pos logit contributions
Narr+0.471
erker+0.445
��+0.443
guyen+0.440
��+0.438
Neg logit contributions
 spons-0.488
 overboard-0.415
 slack-0.365
 distingu-0.343
 conclud-0.339
Token next
Token ID1306
Feature activation-1.49e-02

Pos logit contributions
Narr+0.496
erker+0.471
��+0.464
guyen+0.463
��+0.452
Neg logit contributions
 spons-0.539
 overboard-0.447
 slack-0.414
 conclud-0.387
 distingu-0.384
Token season
Token ID1622
Feature activation-1.28e-01

Pos logit contributions
Narr+0.044
stood+0.042
erker+0.042
guyen+0.041
MQ+0.041
Neg logit contributions
 spons-0.041
 overboard-0.033
 slack-0.030
 distingu-0.028
 conclud-0.028
Token,
Token ID11
Feature activation-1.03e-01

Pos logit contributions
Narr+0.353
guyen+0.334
erker+0.333
��+0.330
��+0.323
Neg logit contributions
 spons-0.382
 overboard-0.325
 slack-0.292
 conclud-0.281
 distingu-0.272
Token gave
Token ID2921
Feature activation+1.49e-01

Pos logit contributions
 spons+0.188
 overboard+0.158
 slack+0.141
 distingu+0.137
 conclud+0.135
Neg logit contributions
Narr-0.174
guyen-0.167
erker-0.165
��-0.163
��-0.161
Token Lear
Token ID8010
Feature activation+2.75e-01

Pos logit contributions
 spons+0.424
 overboard+0.355
 slack+0.311
 distingu+0.302
 conclud+0.290
Neg logit contributions
Narr-0.417
erker-0.407
��-0.396
guyen-0.395
��-0.391
Tokeny
Token ID88
Feature activation+5.83e-02

Pos logit contributions
 spons+0.911
 overboard+0.804
 slack+0.722
 distingu+0.690
 conclud+0.688
Neg logit contributions
Narr-0.631
erker-0.594
guyen-0.588
��-0.584
stood-0.580
Token his
Token ID465
Feature activation+1.37e-01

Pos logit contributions
 spons+0.175
 overboard+0.148
 slack+0.134
 conclud+0.127
 distingu+0.127
Neg logit contributions
Narr-0.154
erker-0.147
guyen-0.146
��-0.144
��-0.143
Token first
Token ID717
Feature activation+9.85e-02

Pos logit contributions
 spons+0.388
 overboard+0.318
 slack+0.290
 distingu+0.275
 conclud+0.264
Neg logit contributions
Narr-0.393
erker-0.378
guyen-0.377
��-0.368
��-0.362
Token LSD
Token ID27483
Feature activation+5.38e-01

Pos logit contributions
 spons+0.277
 overboard+0.228
 slack+0.203
 distingu+0.196
 conclud+0.189
Neg logit contributions
Narr-0.284
erker-0.273
guyen-0.271
��-0.265
��-0.263
Token trip
Token ID5296
Feature activation-2.68e-02

Pos logit contributions
 spons+1.592
 overboard+1.361
 slack+1.193
 conclud+1.162
 distingu+1.148
Neg logit contributions
Narr-1.434
guyen-1.370
erker-1.369
��-1.360
��-1.340
Token]
Token ID60
Feature activation-2.78e-01

Pos logit contributions
Narr+0.073
guyen+0.071
erker+0.070
��+0.069
��+0.069
Neg logit contributions
 spons-0.077
 overboard-0.066
 slack-0.058
 conclud-0.057
 distingu-0.055
Token founded
Token ID9393
Feature activation-4.91e-02

Pos logit contributions
Narr+0.782
guyen+0.753
erker+0.746
��+0.736
��+0.730
Neg logit contributions
 spons-0.793
 overboard-0.656
 slack-0.583
 conclud-0.570
 distingu-0.567
Token the
Token ID262
Feature activation+4.13e-02

Pos logit contributions
Narr+0.134
erker+0.130
guyen+0.129
��+0.127
��+0.125
Neg logit contributions
 spons-0.144
 overboard-0.119
 slack-0.108
 distingu-0.103
 conclud-0.101
Token Ag
Token ID2449
Feature activation-2.02e-01

Pos logit contributions
 spons+0.125
 overboard+0.103
 slack+0.094
 distingu+0.091
 conclud+0.089
Neg logit contributions
Narr-0.110
guyen-0.105
erker-0.105
��-0.103
��-0.102
Token is
Token ID318
Feature activation+7.86e-02

Pos logit contributions
 spons+0.054
 overboard+0.044
 slack+0.039
 distingu+0.038
 conclud+0.038
Neg logit contributions
Narr-0.056
guyen-0.052
erker-0.052
��-0.052
��-0.051
Token based
Token ID1912
Feature activation-1.63e-01

Pos logit contributions
 spons+0.230
 overboard+0.190
 slack+0.170
 distingu+0.166
 conclud+0.165
Neg logit contributions
Narr-0.219
guyen-0.206
erker-0.206
��-0.203
stood-0.202
Token on
Token ID319
Feature activation+9.95e-02

Pos logit contributions
Narr+0.483
guyen+0.463
stood+0.458
erker+0.457
��+0.454
Neg logit contributions
 spons-0.446
 overboard-0.371
 slack-0.327
 distingu-0.319
 conclud-0.317
Token the
Token ID262
Feature activation-1.07e-03

Pos logit contributions
 spons+0.299
 overboard+0.245
 slack+0.228
 distingu+0.214
 conclud+0.212
Neg logit contributions
Narr-0.276
erker-0.256
guyen-0.256
��-0.249
stood-0.247
Token K
Token ID509
Feature activation+9.63e-02

Pos logit contributions
Narr+0.003
erker+0.003
guyen+0.003
��+0.003
stood+0.003
Neg logit contributions
 spons-0.003
 overboard-0.003
 slack-0.002
 distingu-0.002
 conclud-0.002
TokenVM
Token ID15996
Feature activation+4.63e-01

Pos logit contributions
 spons+0.300
 overboard+0.251
 slack+0.223
 distingu+0.222
anova+0.219
Neg logit contributions
Narr-0.242
��-0.229
guyen-0.227
erker-0.224
stood-0.219
Token core
Token ID4755
Feature activation+1.67e-01

Pos logit contributions
 spons+1.442
 overboard+1.206
 slack+1.099
 distingu+1.065
 conclud+1.031
Neg logit contributions
Narr-1.205
erker-1.113
guyen-1.096
��-1.087
stood-1.085
Token kernel
Token ID9720
Feature activation-1.25e-01

Pos logit contributions
 spons+0.513
 overboard+0.427
 slack+0.387
 distingu+0.377
 conclud+0.366
Neg logit contributions
Narr-0.444
erker-0.415
guyen-0.412
stood-0.400
��-0.399
Token module
Token ID8265
Feature activation+1.91e-01

Pos logit contributions
Narr+0.327
guyen+0.304
erker+0.303
stood+0.296
��+0.296
Neg logit contributions
 spons-0.389
 overboard-0.325
 slack-0.293
 distingu-0.285
 conclud-0.281
Token,
Token ID11
Feature activation+1.25e-02

Pos logit contributions
 spons+0.592
 overboard+0.490
 slack+0.447
 distingu+0.430
 conclud+0.423
Neg logit contributions
Narr-0.512
guyen-0.474
erker-0.472
stood-0.459
��-0.459
Token but
Token ID475
Feature activation+3.87e-02

Pos logit contributions
 spons+0.038
 overboard+0.031
 slack+0.028
 conclud+0.027
 distingu+0.027
Neg logit contributions
Narr-0.034
erker-0.032
guyen-0.032
stood-0.031
��-0.031
Tokenumat
Token ID27798
Feature activation-6.01e-01

Pos logit contributions
Narr+0.162
erker+0.155
guyen+0.153
��+0.152
MQ+0.151
Neg logit contributions
 spons-0.156
 overboard-0.126
 slack-0.114
 distingu-0.110
razil-0.109
Tokenoid
Token ID1868
Feature activation-1.03e-01

Pos logit contributions
Narr+2.174
guyen+2.111
MQ+2.063
��+2.059
erker+2.054
Neg logit contributions
 spons-1.241
 overboard-0.926
 slack-0.801
 distingu-0.729
 conclud-0.714
Token arthritis
Token ID37954
Feature activation-1.72e-01

Pos logit contributions
Narr+0.316
guyen+0.308
erker+0.300
MQ+0.295
��+0.295
Neg logit contributions
 spons-0.270
 overboard-0.216
 slack-0.197
 distingu-0.186
 conclud-0.182
Token.
Token ID13
Feature activation-8.40e-04

Pos logit contributions
Narr+0.458
guyen+0.439
erker+0.437
��+0.434
��+0.424
Neg logit contributions
 spons-0.516
 overboard-0.427
 slack-0.387
 conclud-0.375
 distingu-0.372
Token Trying
Token ID31165
Feature activation-2.76e-02

Pos logit contributions
Narr+0.002
erker+0.002
guyen+0.002
��+0.002
��+0.002
Neg logit contributions
 spons-0.002
 overboard-0.002
 slack-0.002
 conclud-0.002
 Tycoon-0.002
Token to
Token ID284
Feature activation+4.76e-02

Pos logit contributions
Narr+0.074
erker+0.070
guyen+0.069
stood+0.068
MQ+0.067
Neg logit contributions
 spons-0.082
 overboard-0.071
 slack-0.062
 distingu-0.061
 conclud-0.061
Token keep
Token ID1394
Feature activation+1.70e-01

Pos logit contributions
 spons+0.138
 overboard+0.114
 slack+0.101
 conclud+0.100
 distingu+0.099
Neg logit contributions
Narr-0.132
guyen-0.125
erker-0.125
stood-0.122
��-0.122
Token her
Token ID607
Feature activation-8.21e-03

Pos logit contributions
 spons+0.498
 overboard+0.416
 slack+0.377
 distingu+0.361
 conclud+0.355
Neg logit contributions
Narr-0.468
erker-0.449
guyen-0.444
��-0.439
��-0.436
Token on
Token ID319
Feature activation-3.92e-02

Pos logit contributions
Narr+0.023
erker+0.022
guyen+0.022
��+0.022
��+0.022
Neg logit contributions
 spons-0.023
 overboard-0.019
 slack-0.017
 distingu-0.017
 conclud-0.016
Token HIV
Token ID10498
Feature activation-1.49e-01

Pos logit contributions
Narr+0.111
erker+0.105
��+0.105
guyen+0.104
��+0.104
Neg logit contributions
 spons-0.114
 overboard-0.092
 slack-0.086
 distingu-0.083
 conclud-0.080
Token medication
Token ID14103
Feature activation-1.96e-01

Pos logit contributions
Narr+0.380
guyen+0.355
erker+0.355
��+0.350
��+0.348
Neg logit contributions
 spons-0.471
 overboard-0.396
 slack-0.363
 distingu-0.345
 conclud-0.344
Token wants
Token ID3382
Feature activation-5.78e-02

Pos logit contributions
 spons+1.071
 overboard+0.880
 slack+0.775
 conclud+0.754
 distingu+0.751
Neg logit contributions
Narr-1.106
guyen-1.053
erker-1.047
stood-1.029
��-1.028
Token to
Token ID284
Feature activation-7.35e-03

Pos logit contributions
Narr+0.151
guyen+0.148
erker+0.145
��+0.141
��+0.141
Neg logit contributions
 spons-0.177
 overboard-0.150
 slack-0.132
 distingu-0.128
 conclud-0.125
Token try
Token ID1949
Feature activation-2.37e-03

Pos logit contributions
Narr+0.021
guyen+0.020
erker+0.019
stood+0.019
��+0.019
Neg logit contributions
 spons-0.021
 overboard-0.017
 slack-0.016
 distingu-0.015
 conclud-0.015
Token next
Token ID1306
Feature activation+4.34e-02

Pos logit contributions
Narr+0.006
guyen+0.006
erker+0.006
��+0.006
stood+0.006
Neg logit contributions
 spons-0.007
 overboard-0.006
 slack-0.005
 conclud-0.005
 distingu-0.005
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
 spons+0.131
 overboard+0.111
 slack+0.099
 distingu+0.095
 conclud+0.094
Neg logit contributions
Narr-0.115
guyen-0.112
��-0.109
��-0.109
stood-0.109
Token That
Token ID1320
Feature activation+3.10e-02

Pos logit contributions
 spons+0.354
 overboard+0.298
 slack+0.270
 Tycoon+0.257
 distingu+0.256
Neg logit contributions
Narr-0.327
guyen-0.317
erker-0.314
��-0.309
��-0.308
Token includes
Token ID3407
Feature activation+9.43e-02

Pos logit contributions
 spons+0.088
 overboard+0.074
 slack+0.065
 distingu+0.063
 conclud+0.063
Neg logit contributions
Narr-0.088
guyen-0.083
��-0.083
erker-0.083
��-0.083
Token their
Token ID511
Feature activation+6.13e-02

Pos logit contributions
 spons+0.277
 overboard+0.231
 slack+0.207
 distingu+0.199
 conclud+0.198
Neg logit contributions
Narr-0.261
erker-0.248
guyen-0.248
��-0.244
��-0.242
Token 70
Token ID4317
Feature activation-4.26e-02

Pos logit contributions
 spons+0.177
 overboard+0.146
 slack+0.131
 distingu+0.125
 conclud+0.125
Neg logit contributions
Narr-0.172
erker-0.165
guyen-0.164
��-0.162
��-0.162
Token,
Token ID11
Feature activation+5.81e-02

Pos logit contributions
Narr+0.092
erker+0.088
guyen+0.085
stood+0.083
��+0.082
Neg logit contributions
 spons-0.150
 overboard-0.128
 slack-0.117
 conclud-0.114
 distingu-0.114
Token000
Token ID830
Feature activation-6.46e-02

Pos logit contributions
 spons+0.183
 overboard+0.156
 slack+0.141
 conclud+0.138
 distingu+0.135
Neg logit contributions
Narr-0.144
guyen-0.134
erker-0.134
��-0.134
stood-0.130
Token for
Token ID329
Feature activation+2.46e-01

Pos logit contributions
 spons+0.289
 overboard+0.242
 slack+0.217
 distingu+0.202
 conclud+0.199
Neg logit contributions
Narr-0.280
guyen-0.271
��-0.271
erker-0.267
��-0.267
Token you
Token ID345
Feature activation-3.50e-02

Pos logit contributions
 spons+0.733
 overboard+0.606
 slack+0.567
 distingu+0.525
 conclud+0.513
Neg logit contributions
Narr-0.660
erker-0.638
��-0.630
guyen-0.630
��-0.620
Token on
Token ID319
Feature activation+1.69e-01

Pos logit contributions
Narr+0.094
guyen+0.092
��+0.091
��+0.090
erker+0.089
Neg logit contributions
 spons-0.105
 overboard-0.089
 slack-0.080
 conclud-0.075
 distingu-0.075
Token the
Token ID262
Feature activation+1.44e-02

Pos logit contributions
 spons+0.468
 overboard+0.382
 slack+0.359
 distingu+0.330
 conclud+0.323
Neg logit contributions
Narr-0.493
erker-0.468
guyen-0.468
��-0.461
��-0.456
Token other
Token ID584
Feature activation+1.81e-02

Pos logit contributions
 spons+0.041
 overboard+0.033
 slack+0.031
 distingu+0.029
 conclud+0.028
Neg logit contributions
Narr-0.042
guyen-0.039
erker-0.039
��-0.039
stood-0.038
Token side
Token ID1735
Feature activation+3.82e-01

Pos logit contributions
 spons+0.048
 overboard+0.039
 slack+0.036
 distingu+0.032
 conclud+0.032
Neg logit contributions
Narr-0.056
��-0.053
guyen-0.053
erker-0.052
��-0.051
Token.
Token ID13
Feature activation-8.01e-03

Pos logit contributions
 spons+1.047
 overboard+0.878
 slack+0.788
 conclud+0.733
 distingu+0.709
Neg logit contributions
Narr-1.120
guyen-1.098
��-1.072
��-1.070
erker-1.068
Token In
Token ID554
Feature activation+2.00e-02

Pos logit contributions
Narr+0.021
guyen+0.020
erker+0.020
��+0.019
stood+0.019
Neg logit contributions
 spons-0.024
 overboard-0.020
 slack-0.018
 conclud-0.018
 distingu-0.018
Token fact
Token ID1109
Feature activation+1.46e-01

Pos logit contributions
 spons+0.060
 overboard+0.049
 slack+0.045
 distingu+0.043
 conclud+0.042
Neg logit contributions
Narr-0.054
guyen-0.052
erker-0.051
��-0.050
��-0.050
Token,
Token ID11
Feature activation-4.94e-02

Pos logit contributions
 spons+0.468
 overboard+0.395
 slack+0.361
 distingu+0.352
 conclud+0.352
Neg logit contributions
Narr-0.359
guyen-0.337
erker-0.335
stood-0.331
MQ-0.323
Token you
Token ID345
Feature activation-6.50e-02

Pos logit contributions
Narr+0.131
erker+0.124
guyen+0.124
��+0.122
stood+0.121
Neg logit contributions
 spons-0.149
 overboard-0.125
 slack-0.112
 distingu-0.109
 conclud-0.108
Token and
Token ID290
Feature activation+1.89e-02

Pos logit contributions
 spons+0.078
 overboard+0.065
 slack+0.059
 distingu+0.057
 conclud+0.056
Neg logit contributions
Narr-0.074
guyen-0.072
erker-0.072
��-0.070
MQ-0.069
Token sw
Token ID1509
Feature activation-1.36e-01

Pos logit contributions
 spons+0.055
 overboard+0.046
 slack+0.042
 distingu+0.041
 conclud+0.040
Neg logit contributions
Narr-0.051
erker-0.050
guyen-0.049
��-0.049
MQ-0.048
Tokenagger
Token ID7928
Feature activation-1.28e-01

Pos logit contributions
Narr+0.251
��+0.234
MQ+0.231
��+0.227
guyen+0.224
Neg logit contributions
 spons-0.519
 overboard-0.443
 slack-0.412
 distingu-0.403
anova-0.399
Token,
Token ID11
Feature activation+1.17e-01

Pos logit contributions
Narr+0.340
guyen+0.331
erker+0.326
��+0.319
MQ+0.317
Neg logit contributions
 spons-0.385
 overboard-0.324
 slack-0.292
 distingu-0.283
 conclud-0.280
Token and
Token ID290
Feature activation+4.75e-02

Pos logit contributions
 spons+0.352
 overboard+0.294
 slack+0.268
 distingu+0.262
 conclud+0.260
Neg logit contributions
Narr-0.307
erker-0.296
guyen-0.296
MQ-0.288
��-0.287
Token they
Token ID484
Feature activation+1.07e-01

Pos logit contributions
 spons+0.142
 overboard+0.119
 slack+0.108
 distingu+0.106
 conclud+0.105
Neg logit contributions
Narr-0.125
erker-0.121
guyen-0.120
��-0.117
��-0.117
Token seemed
Token ID3947
Feature activation+4.64e-02

Pos logit contributions
 spons+0.317
 overboard+0.262
 slack+0.241
 distingu+0.234
 conclud+0.230
Neg logit contributions
Narr-0.287
guyen-0.280
��-0.272
��-0.272
erker-0.271
Token afraid
Token ID7787
Feature activation-7.44e-04

Pos logit contributions
 spons+0.139
 overboard+0.117
 slack+0.106
 distingu+0.101
 conclud+0.099
Neg logit contributions
Narr-0.124
guyen-0.121
erker-0.120
��-0.116
MQ-0.116
Token of
Token ID286
Feature activation+1.45e-02

Pos logit contributions
Narr+0.002
erker+0.002
guyen+0.002
MQ+0.002
��+0.002
Neg logit contributions
 spons-0.002
 overboard-0.002
 slack-0.002
 distingu-0.002
 conclud-0.002
Token nothing
Token ID2147
Feature activation-5.77e-02

Pos logit contributions
 spons+0.044
 overboard+0.037
 slack+0.034
 distingu+0.033
 conclud+0.032
Neg logit contributions
Narr-0.038
erker-0.036
guyen-0.036
��-0.035
MQ-0.035
Token.
Token ID13
Feature activation+5.29e-02

Pos logit contributions
Narr+0.148
guyen+0.144
erker+0.141
stood+0.138
��+0.138
Neg logit contributions
 spons-0.177
 overboard-0.150
 slack-0.135
 distingu-0.131
 conclud-0.130
Token 30
Token ID1542
Feature activation-5.32e-02

Pos logit contributions
 spons+0.243
 overboard+0.202
 slack+0.182
 distingu+0.173
 conclud+0.172
Neg logit contributions
Narr-0.213
erker-0.204
guyen-0.201
��-0.200
��-0.197
Token.
Token ID13
Feature activation+8.86e-02

Pos logit contributions
Narr+0.142
guyen+0.136
erker+0.135
��+0.134
stood+0.132
Neg logit contributions
 spons-0.161
 overboard-0.134
 slack-0.122
 conclud-0.116
 distingu-0.116
Token Sc
Token ID1446
Feature activation-4.10e-02

Pos logit contributions
 spons+0.247
 overboard+0.205
 slack+0.190
 Tycoon+0.180
 distingu+0.178
Neg logit contributions
Narr-0.238
erker-0.237
guyen-0.237
��-0.231
��-0.229
Tokenann
Token ID1236
Feature activation+5.39e-02

Pos logit contributions
Narr+0.108
erker+0.102
guyen+0.101
stood+0.100
��+0.098
Neg logit contributions
 spons-0.124
 overboard-0.103
 conclud-0.094
 distingu-0.092
 slack-0.092
Tokenell
Token ID695
Feature activation+1.07e-02

Pos logit contributions
 spons+0.181
 overboard+0.154
 slack+0.140
 conclud+0.138
 distingu+0.137
Neg logit contributions
Narr-0.123
guyen-0.115
erker-0.114
stood-0.112
��-0.112
Token and
Token ID290
Feature activation+5.13e-02

Pos logit contributions
 spons+0.031
 overboard+0.026
 slack+0.024
 distingu+0.022
 conclud+0.022
Neg logit contributions
Narr-0.029
guyen-0.029
erker-0.028
��-0.028
��-0.027
Token Lt
Token ID19090
Feature activation-3.52e-01

Pos logit contributions
 spons+0.151
 overboard+0.124
 slack+0.113
 distingu+0.109
 conclud+0.106
Neg logit contributions
Narr-0.138
erker-0.134
��-0.132
guyen-0.131
��-0.130
Token.
Token ID13
Feature activation+2.75e-01

Pos logit contributions
Narr+0.931
guyen+0.897
erker+0.888
MQ+0.887
��+0.886
Neg logit contributions
 spons-1.036
 overboard-0.862
 slack-0.772
anova-0.750
 distingu-0.749
Token Emil
Token ID44272
Feature activation+2.67e-01

Pos logit contributions
 spons+0.836
 overboard+0.705
 slack+0.643
 Tycoon+0.626
 distingu+0.618
Neg logit contributions
erker-0.675
Narr-0.674
guyen-0.660
��-0.649
��-0.646
Token Rick
Token ID8759
Feature activation+6.25e-02

Pos logit contributions
 spons+0.766
 overboard+0.639
 slack+0.578
 distingu+0.553
 conclud+0.549
Neg logit contributions
Narr-0.713
erker-0.683
guyen-0.680
MQ-0.673
��-0.668
Tokenner
Token ID1008
Feature activation+3.75e-02

Pos logit contributions
 spons+0.192
 overboard+0.160
 slack+0.141
 distingu+0.138
 conclud+0.138
Neg logit contributions
Narr-0.165
guyen-0.155
��-0.152
erker-0.150
MQ-0.150
Token nineteenth
Token ID29666
Feature activation-3.27e-01

Pos logit contributions
 spons+0.068
 overboard+0.055
 slack+0.050
 distingu+0.048
 conclud+0.048
Neg logit contributions
Narr-0.063
guyen-0.061
erker-0.060
MQ-0.059
��-0.059
Token century
Token ID4289
Feature activation-2.55e-01

Pos logit contributions
Narr+0.912
erker+0.887
guyen+0.878
stood+0.867
��+0.862
Neg logit contributions
 spons-0.944
 overboard-0.782
 slack-0.705
 conclud-0.674
 distingu-0.665
Token.
Token ID13
Feature activation-9.35e-02

Pos logit contributions
Narr+0.654
guyen+0.635
erker+0.624
��+0.615
��+0.609
Neg logit contributions
 spons-0.791
 overboard-0.666
 slack-0.600
 conclud-0.584
 distingu-0.582
Token In
Token ID554
Feature activation-3.74e-02

Pos logit contributions
Narr+0.249
guyen+0.247
erker+0.245
��+0.238
��+0.238
Neg logit contributions
 spons-0.266
 overboard-0.222
 slack-0.202
 conclud-0.194
 Tycoon-0.191
Token L
Token ID406
Feature activation-9.14e-02

Pos logit contributions
Narr+0.100
guyen+0.096
erker+0.095
��+0.093
MQ+0.093
Neg logit contributions
 spons-0.112
 overboard-0.092
 slack-0.083
 conclud-0.081
 distingu-0.080
Token
Token ID447
Feature activation-1.52e-01

Pos logit contributions
Narr+0.234
guyen+0.222
��+0.220
stood+0.219
erker+0.215
Neg logit contributions
 spons-0.281
 overboard-0.234
 slack-0.208
uana-0.206
 conclud-0.205
Token
Token ID247
Feature activation-1.41e-01

Pos logit contributions
Narr+0.370
stood+0.344
guyen+0.342
erker+0.341
MQ+0.338
Neg logit contributions
 spons-0.488
 overboard-0.408
 slack-0.368
 conclud-0.363
 distingu-0.358
Tokenin
Token ID259
Feature activation+3.51e-02

Pos logit contributions
Narr+0.318
guyen+0.303
��+0.303
��+0.302
erker+0.299
Neg logit contributions
 spons-0.470
 overboard-0.396
 slack-0.355
 conclud-0.350
anova-0.349
Tokenvention
Token ID4018
Feature activation+2.09e-01

Pos logit contributions
 spons+0.113
 overboard+0.094
 slack+0.086
 conclud+0.084
 distingu+0.083
Neg logit contributions
Narr-0.085
guyen-0.081
erker-0.080
��-0.079
��-0.078
Token de
Token ID390
Feature activation-1.51e-01

Pos logit contributions
 spons+0.642
 overboard+0.532
 slack+0.474
 conclud+0.468
 distingu+0.465
Neg logit contributions
Narr-0.538
guyen-0.528
erker-0.518
��-0.503
stood-0.502
Token la
Token ID8591
Feature activation-9.75e-03

Pos logit contributions
Narr+0.392
erker+0.379
guyen+0.372
��+0.366
stood+0.364
Neg logit contributions
 spons-0.468
 overboard-0.381
 distingu-0.346
 slack-0.345
 conclud-0.338
Token at
Token ID379
Feature activation+1.23e-01

Pos logit contributions
Narr+0.228
guyen+0.220
erker+0.217
MQ+0.213
��+0.213
Neg logit contributions
 spons-0.234
 overboard-0.192
 slack-0.173
 conclud-0.169
 distingu-0.168
Token reasonable
Token ID6397
Feature activation+3.43e-02

Pos logit contributions
 spons+0.360
 overboard+0.300
 slack+0.272
 conclud+0.254
 distingu+0.253
Neg logit contributions
Narr-0.342
guyen-0.324
erker-0.318
��-0.317
��-0.314
Token listening
Token ID8680
Feature activation-3.69e-01

Pos logit contributions
 spons+0.105
 overboard+0.089
 slack+0.081
 distingu+0.077
 conclud+0.077
Neg logit contributions
Narr-0.089
guyen-0.085
erker-0.084
��-0.083
stood-0.081
Token volumes
Token ID15343
Feature activation-3.26e-01

Pos logit contributions
Narr+1.110
guyen+1.071
erker+1.064
��+1.035
stood+1.033
Neg logit contributions
 spons-0.998
 overboard-0.812
 slack-0.731
 distingu-0.694
 conclud-0.690
Token will
Token ID481
Feature activation-1.43e-01

Pos logit contributions
Narr+0.933
guyen+0.899
erker+0.880
��+0.870
stood+0.859
Neg logit contributions
 spons-0.919
 overboard-0.756
 slack-0.676
 conclud-0.661
 distingu-0.659
Token make
Token ID787
Feature activation-1.74e-01

Pos logit contributions
Narr+0.398
guyen+0.383
erker+0.376
��+0.372
stood+0.370
Neg logit contributions
 spons-0.414
 overboard-0.343
 slack-0.308
 distingu-0.298
 conclud-0.298
Token them
Token ID606
Feature activation-2.12e-01

Pos logit contributions
Narr+0.454
guyen+0.436
erker+0.434
��+0.426
��+0.420
Neg logit contributions
 spons-0.534
 overboard-0.443
 slack-0.406
 distingu-0.391
 conclud-0.390
Token excellent
Token ID6275
Feature activation-1.81e-01

Pos logit contributions
Narr+0.567
guyen+0.544
erker+0.540
��+0.535
��+0.529
Neg logit contributions
 spons-0.635
 overboard-0.528
 slack-0.476
 distingu-0.467
 conclud-0.461
Token companions
Token ID19429
Feature activation-1.66e-01

Pos logit contributions
Narr+0.537
guyen+0.516
erker+0.515
��+0.502
stood+0.499
Neg logit contributions
 spons-0.498
 overboard-0.401
 slack-0.361
 distingu-0.354
 conclud-0.349
Token in
Token ID287
Feature activation-5.34e-02

Pos logit contributions
Narr+0.465
guyen+0.458
��+0.443
erker+0.441
��+0.439
Neg logit contributions
 spons-0.473
 overboard-0.399
 slack-0.357
 distingu-0.338
 conclud-0.335
Token the
Token ID262
Feature activation-6.69e-02

Pos logit contributions
Narr+0.154
guyen+0.148
erker+0.146
��+0.145
��+0.144
Neg logit contributions
 spons-0.151
 overboard-0.122
 slack-0.112
 conclud-0.106
 distingu-0.105
Token
Token ID198
Feature activation-9.37e-02

Pos logit contributions
Narr+0.285
erker+0.264
guyen+0.262
stood+0.261
MQ+0.257
Neg logit contributions
 spons-0.404
 overboard-0.340
 conclud-0.314
 distingu-0.310
 slack-0.305
TokenDo
Token ID5211
Feature activation+4.29e-02

Pos logit contributions
guyen+0.215
erker+0.214
��+0.208
Narr+0.207
��+0.205
Neg logit contributions
 spons-0.297
 overboard-0.255
 slack-0.231
anova-0.223
 distingu-0.217
Token use
Token ID779
Feature activation+3.87e-03

Pos logit contributions
 spons+0.118
 overboard+0.098
 slack+0.089
 distingu+0.085
 conclud+0.084
Neg logit contributions
Narr-0.123
stood-0.119
guyen-0.119
erker-0.119
��-0.117
Token social
Token ID1919
Feature activation+5.36e-02

Pos logit contributions
 spons+0.010
 overboard+0.008
 slack+0.008
 distingu+0.007
 conclud+0.007
Neg logit contributions
Narr-0.012
erker-0.011
guyen-0.011
MQ-0.011
��-0.011
Token media
Token ID2056
Feature activation+4.79e-01

Pos logit contributions
 spons+0.148
 overboard+0.121
 slack+0.106
 conclud+0.105
 distingu+0.104
Neg logit contributions
Narr-0.155
guyen-0.147
erker-0.147
stood-0.145
��-0.144
Token to
Token ID284
Feature activation+1.18e-02

Pos logit contributions
 spons+1.389
 overboard+1.167
 slack+1.057
 distingu+0.989
 conclud+0.974
Neg logit contributions
Narr-1.330
��-1.269
��-1.267
guyen-1.266
stood-1.254
Token make
Token ID787
Feature activation-1.52e-02

Pos logit contributions
 spons+0.032
 overboard+0.026
 slack+0.023
 distingu+0.022
 conclud+0.022
Neg logit contributions
Narr-0.036
guyen-0.035
erker-0.034
��-0.034
��-0.033
Token franchise
Token ID8663
Feature activation+1.58e-01

Pos logit contributions
Narr+0.041
guyen+0.039
erker+0.039
��+0.039
��+0.038
Neg logit contributions
 spons-0.045
 overboard-0.038
 slack-0.034
 distingu-0.032
 conclud-0.032
Token-
Token ID12
Feature activation+1.16e-01

Pos logit contributions
 spons+0.466
 overboard+0.378
 slack+0.345
 conclud+0.336
 distingu+0.329
Neg logit contributions
Narr-0.434
guyen-0.417
erker-0.413
��-0.407
��-0.405
Tokensh
Token ID1477
Feature activation+1.83e-01

Pos logit contributions
 spons+0.380
 overboard+0.319
 slack+0.287
anova+0.281
 distingu+0.278
Neg logit contributions
Narr-0.273
guyen-0.269
erker-0.265
��-0.265
��-0.260
Tokenifting
Token ID13309
Feature activation+3.67e-01

Pos logit contributions
 spons+0.542
 overboard+0.453
 slack+0.395
 Tycoon+0.388
razil+0.385
Neg logit contributions
Narr-0.493
��-0.470
guyen-0.459
MQ-0.459
��-0.453
Token at
Token ID379
Feature activation-2.24e-01

Pos logit contributions
 spons+0.225
 overboard+0.187
 slack+0.163
 distingu+0.155
 conclud+0.150
Neg logit contributions
Narr-0.271
guyen-0.266
erker-0.259
MQ-0.254
��-0.254
Token a
Token ID257
Feature activation-2.01e-01

Pos logit contributions
Narr+0.636
guyen+0.618
��+0.600
��+0.596
erker+0.592
Neg logit contributions
 spons-0.631
 overboard-0.519
 slack-0.486
 distingu-0.446
 conclud-0.444
Token particular
Token ID1948
Feature activation-1.27e-01

Pos logit contributions
Narr+0.603
guyen+0.577
erker+0.568
��+0.564
��+0.559
Neg logit contributions
 spons-0.534
 overboard-0.435
 slack-0.398
 distingu-0.383
 conclud-0.371
Token glacier
Token ID44539
Feature activation+6.57e-02

Pos logit contributions
Narr+0.336
guyen+0.323
erker+0.315
��+0.312
��+0.309
Neg logit contributions
 spons-0.387
 overboard-0.323
 slack-0.298
 distingu-0.286
 conclud-0.277
Token is
Token ID318
Feature activation-1.47e-01

Pos logit contributions
 spons+0.171
 overboard+0.137
 slack+0.124
 distingu+0.115
 conclud+0.114
Neg logit contributions
Narr-0.206
guyen-0.199
��-0.194
��-0.193
erker-0.193
Token the
Token ID262
Feature activation-4.74e-02

Pos logit contributions
Narr+0.423
guyen+0.400
erker+0.397
��+0.395
��+0.389
Neg logit contributions
 spons-0.420
 overboard-0.348
 slack-0.320
 distingu-0.299
 conclud-0.298
Token longer
Token ID2392
Feature activation-1.70e-01

Pos logit contributions
Narr+0.125
guyen+0.119
erker+0.118
��+0.117
��+0.115
Neg logit contributions
 spons-0.148
 overboard-0.123
 slack-0.115
 distingu-0.107
 conclud-0.105
Token-
Token ID12
Feature activation-1.02e-01

Pos logit contributions
Narr+0.441
guyen+0.437
erker+0.423
��+0.418
MQ+0.414
Neg logit contributions
 spons-0.513
 overboard-0.437
 slack-0.403
 distingu-0.383
 conclud-0.367
Tokenterm
Token ID4354
Feature activation+6.88e-03

Pos logit contributions
Narr+0.210
guyen+0.210
erker+0.200
��+0.199
��+0.197
Neg logit contributions
 spons-0.364
 overboard-0.314
 slack-0.292
 distingu-0.282
anova-0.274
Token position
Token ID2292
Feature activation-2.27e-02

Pos logit contributions
 spons+0.021
 overboard+0.017
 slack+0.016
 distingu+0.015
 conclud+0.015
Neg logit contributions
Narr-0.018
guyen-0.018
erker-0.018
��-0.017
��-0.017
Token of
Token ID286
Feature activation+3.82e-02

Pos logit contributions
Narr+0.067
guyen+0.066
erker+0.065
MQ+0.064
��+0.064
Neg logit contributions
 spons-0.060
 overboard-0.050
 slack-0.045
 distingu-0.042
 conclud-0.041
Token run
Token ID1057
Feature activation+1.85e-01

Pos logit contributions
Narr+0.972
guyen+0.922
erker+0.915
��+0.913
MQ+0.894
Neg logit contributions
 spons-0.824
 overboard-0.672
 slack-0.611
 distingu-0.574
 conclud-0.562
Token,
Token ID11
Feature activation-8.71e-02

Pos logit contributions
 spons+0.539
 overboard+0.457
 slack+0.412
 conclud+0.388
 distingu+0.387
Neg logit contributions
Narr-0.502
guyen-0.494
��-0.482
��-0.482
erker-0.479
Token so
Token ID523
Feature activation-1.96e-03

Pos logit contributions
Narr+0.236
erker+0.225
guyen+0.224
��+0.219
��+0.219
Neg logit contributions
 spons-0.257
 overboard-0.214
 slack-0.194
 conclud-0.186
 distingu-0.185
Token we
Token ID356
Feature activation-7.43e-02

Pos logit contributions
Narr+0.005
erker+0.005
guyen+0.005
��+0.005
��+0.005
Neg logit contributions
 spons-0.006
 overboard-0.005
 slack-0.005
 conclud-0.004
 distingu-0.004
Token are
Token ID389
Feature activation-6.62e-02

Pos logit contributions
Narr+0.200
guyen+0.190
erker+0.189
stood+0.185
��+0.185
Neg logit contributions
 spons-0.220
 overboard-0.182
 slack-0.162
 conclud-0.161
 distingu-0.159
Token basically
Token ID6209
Feature activation-1.11e-01

Pos logit contributions
Narr+0.182
guyen+0.173
erker+0.173
��+0.169
stood+0.167
Neg logit contributions
 spons-0.193
 overboard-0.160
 slack-0.143
 conclud-0.140
 distingu-0.139
Token ready
Token ID3492
Feature activation+1.31e-02

Pos logit contributions
Narr+0.300
guyen+0.285
erker+0.284
��+0.278
stood+0.276
Neg logit contributions
 spons-0.326
 overboard-0.271
 slack-0.242
 conclud-0.237
 distingu-0.236
Token.
Token ID13
Feature activation-4.25e-02

Pos logit contributions
 spons+0.038
 overboard+0.032
 slack+0.029
 conclud+0.027
 distingu+0.027
Neg logit contributions
Narr-0.036
guyen-0.035
erker-0.035
��-0.034
��-0.034
Token We
Token ID775
Feature activation-8.43e-02

Pos logit contributions
Narr+0.110
guyen+0.105
erker+0.104
��+0.102
��+0.101
Neg logit contributions
 spons-0.129
 overboard-0.108
 slack-0.098
 conclud-0.094
 distingu-0.093
Token will
Token ID481
Feature activation+8.02e-02

Pos logit contributions
Narr+0.238
guyen+0.225
erker+0.223
��+0.220
��+0.219
Neg logit contributions
 spons-0.240
 overboard-0.198
 slack-0.177
 conclud-0.173
 distingu-0.172
Token try
Token ID1949
Feature activation+1.15e-02

Pos logit contributions
 spons+0.234
 overboard+0.193
 slack+0.174
 conclud+0.169
 distingu+0.167
Neg logit contributions
Narr-0.222
guyen-0.211
erker-0.208
stood-0.205
��-0.205
Token Sheriff
Token ID12874
Feature activation-5.44e-02

Pos logit contributions
Narr+0.303
erker+0.295
guyen+0.287
��+0.285
stood+0.280
Neg logit contributions
 spons-0.352
 overboard-0.298
 slack-0.269
 conclud-0.263
 distingu-0.262
Token's
Token ID338
Feature activation+4.08e-02

Pos logit contributions
Narr+0.155
erker+0.149
guyen+0.148
��+0.145
��+0.144
Neg logit contributions
 spons-0.153
 overboard-0.127
 slack-0.113
 conclud-0.112
 distingu-0.111
Token Office
Token ID4452
Feature activation-8.43e-02

Pos logit contributions
 spons+0.132
 overboard+0.114
 slack+0.104
 distingu+0.103
 conclud+0.103
Neg logit contributions
Narr-0.096
erker-0.094
guyen-0.092
��-0.092
��-0.089
Token has
Token ID468
Feature activation-1.54e-02

Pos logit contributions
Narr+0.252
guyen+0.243
erker+0.240
��+0.237
��+0.237
Neg logit contributions
 spons-0.225
 overboard-0.184
 slack-0.162
 conclud-0.161
 distingu-0.158
Token been
Token ID587
Feature activation+1.34e-02

Pos logit contributions
Narr+0.043
guyen+0.041
erker+0.041
��+0.041
��+0.040
Neg logit contributions
 spons-0.044
 overboard-0.037
 slack-0.033
 conclud-0.032
 distingu-0.032
Token notified
Token ID17600
Feature activation-4.09e-01

Pos logit contributions
 spons+0.038
 overboard+0.032
 slack+0.029
 conclud+0.027
 distingu+0.027
Neg logit contributions
Narr-0.038
guyen-0.037
erker-0.036
��-0.036
stood-0.035
Token and
Token ID290
Feature activation-4.14e-02

Pos logit contributions
Narr+1.139
guyen+1.090
erker+1.090
��+1.056
stood+1.046
Neg logit contributions
 spons-1.192
 overboard-0.995
 slack-0.883
 conclud-0.854
 distingu-0.841
Token is
Token ID318
Feature activation-5.71e-02

Pos logit contributions
Narr+0.114
guyen+0.108
erker+0.107
��+0.105
��+0.104
Neg logit contributions
 spons-0.121
 overboard-0.100
 slack-0.089
 conclud-0.088
 distingu-0.087
Token investigating
Token ID10240
Feature activation-2.23e-01

Pos logit contributions
Narr+0.151
guyen+0.144
erker+0.143
��+0.140
stood+0.140
Neg logit contributions
 spons-0.173
 overboard-0.144
 slack-0.130
 conclud-0.127
 distingu-0.126
Token.
Token ID13
Feature activation-9.00e-03

Pos logit contributions
Narr+0.589
erker+0.564
guyen+0.559
��+0.552
stood+0.547
Neg logit contributions
 spons-0.677
 overboard-0.572
 slack-0.515
 conclud-0.499
 distingu-0.494
Token<|endoftext|>
Token ID50256
Feature activation+6.51e-02

Pos logit contributions
Narr+0.024
guyen+0.024
erker+0.023
��+0.023
��+0.023
Neg logit contributions
 spons-0.026
 overboard-0.022
 slack-0.019
 conclud-0.019
 Tycoon-0.018
Token's
Token ID338
Feature activation-6.11e-02

Pos logit contributions
 spons+0.396
 overboard+0.339
 slack+0.298
 conclud+0.283
 distingu+0.278
Neg logit contributions
Narr-0.412
guyen-0.394
��-0.393
erker-0.391
stood-0.380
Token comment
Token ID2912
Feature activation-3.00e-01

Pos logit contributions
Narr+0.172
guyen+0.164
erker+0.163
��+0.161
stood+0.159
Neg logit contributions
 spons-0.174
 overboard-0.145
 slack-0.129
 conclud-0.123
 distingu-0.123
Token is
Token ID318
Feature activation-1.87e-02

Pos logit contributions
Narr+0.903
guyen+0.865
erker+0.847
��+0.847
MQ+0.839
Neg logit contributions
 spons-0.804
 overboard-0.668
 slack-0.593
 distingu-0.562
 conclud-0.562
Token astounding
Token ID34328
Feature activation+6.06e-02

Pos logit contributions
Narr+0.053
guyen+0.051
erker+0.050
��+0.050
MQ+0.050
Neg logit contributions
 spons-0.054
 overboard-0.045
 slack-0.040
 distingu-0.038
 conclud-0.038
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
 spons+0.181
 overboard+0.155
 slack+0.139
 conclud+0.133
 distingu+0.132
Neg logit contributions
Narr-0.161
guyen-0.156
��-0.155
erker-0.152
MQ-0.151
Token Back
Token ID5157
Feature activation-4.21e-01

Pos logit contributions
Narr+0.300
guyen+0.289
erker+0.289
��+0.284
stood+0.279
Neg logit contributions
 spons-0.338
 overboard-0.283
 slack-0.256
 conclud-0.246
 distingu-0.244
Tokenhandedly
Token ID43919
Feature activation-1.81e-01

Pos logit contributions
Narr+1.218
guyen+1.169
��+1.165
erker+1.159
��+1.137
Neg logit contributions
 spons-1.171
 overboard-0.971
 slack-0.844
 conclud-0.820
 distingu-0.814
Token acknowledging
Token ID25937
Feature activation+2.35e-01

Pos logit contributions
Narr+0.511
guyen+0.496
erker+0.489
��+0.486
stood+0.473
Neg logit contributions
 spons-0.516
 overboard-0.432
 slack-0.382
 conclud-0.373
 distingu-0.370
Token that
Token ID326
Feature activation-2.79e-02

Pos logit contributions
 spons+0.667
 overboard+0.555
 slack+0.495
 conclud+0.462
 distingu+0.458
Neg logit contributions
Narr-0.670
erker-0.641
guyen-0.630
��-0.629
��-0.618
Token Kiev
Token ID22761
Feature activation-1.88e-02

Pos logit contributions
Narr+0.077
erker+0.073
guyen+0.073
��+0.072
��+0.071
Neg logit contributions
 spons-0.082
 overboard-0.069
 slack-0.061
 conclud-0.058
 distingu-0.058
Token has
Token ID468
Feature activation+5.08e-02

Pos logit contributions
Narr+0.055
guyen+0.053
erker+0.052
��+0.052
��+0.051
Neg logit contributions
 spons-0.052
 overboard-0.042
 slack-0.037
 conclud-0.036
 distingu-0.036
Token to
Token ID284
Feature activation-4.44e-02

Pos logit contributions
Narr+0.266
guyen+0.258
erker+0.257
stood+0.256
��+0.251
Neg logit contributions
 spons-0.287
 overboard-0.255
 slack-0.221
 conclud-0.208
 distingu-0.205
Token be
Token ID307
Feature activation-7.58e-02

Pos logit contributions
Narr+0.119
guyen+0.118
��+0.113
MQ+0.112
��+0.112
Neg logit contributions
 spons-0.132
 overboard-0.112
 slack-0.102
 distingu-0.097
 conclud-0.097
Token very
Token ID845
Feature activation+5.39e-02

Pos logit contributions
Narr+0.206
guyen+0.199
erker+0.195
��+0.193
MQ+0.193
Neg logit contributions
 spons-0.222
 overboard-0.188
 slack-0.168
 distingu-0.162
 conclud-0.159
Token quiet
Token ID5897
Feature activation-2.80e-01

Pos logit contributions
 spons+0.154
 overboard+0.132
 slack+0.117
 distingu+0.113
 conclud+0.110
Neg logit contributions
Narr-0.149
guyen-0.145
erker-0.142
MQ-0.140
��-0.140
Token and
Token ID290
Feature activation-4.17e-02

Pos logit contributions
Narr+0.723
guyen+0.711
��+0.689
erker+0.687
��+0.686
Neg logit contributions
 spons-0.847
 overboard-0.727
 slack-0.652
 distingu-0.624
 conclud-0.620
Token acoustic
Token ID26071
Feature activation-5.24e-01

Pos logit contributions
Narr+0.115
guyen+0.113
erker+0.111
��+0.109
��+0.109
Neg logit contributions
 spons-0.118
 overboard-0.101
 slack-0.092
 distingu-0.087
 conclud-0.086
Token,
Token ID11
Feature activation-6.14e-02

Pos logit contributions
Narr+1.364
guyen+1.342
erker+1.306
��+1.297
��+1.297
Neg logit contributions
 spons-1.585
 overboard-1.356
 slack-1.224
 distingu-1.172
 conclud-1.164
Token with
Token ID351
Feature activation-8.28e-02

Pos logit contributions
Narr+0.171
guyen+0.166
erker+0.164
��+0.162
��+0.162
Neg logit contributions
 spons-0.174
 overboard-0.147
 slack-0.132
 distingu-0.125
 conclud-0.125
Token lots
Token ID6041
Feature activation+6.52e-02

Pos logit contributions
Narr+0.227
erker+0.220
guyen+0.220
��+0.217
��+0.213
Neg logit contributions
 spons-0.240
 overboard-0.201
 slack-0.184
 distingu-0.172
 conclud-0.169
Token of
Token ID286
Feature activation-6.97e-03

Pos logit contributions
 spons+0.172
 overboard+0.142
 slack+0.126
 distingu+0.118
 conclud+0.117
Neg logit contributions
Narr-0.196
guyen-0.192
erker-0.191
��-0.189
MQ-0.188
Token string
Token ID4731
Feature activation-6.21e-02

Pos logit contributions
Narr+0.021
guyen+0.020
erker+0.020
��+0.020
��+0.020
Neg logit contributions
 spons-0.018
 overboard-0.015
 slack-0.014
 distingu-0.013
 conclud-0.012
Tokenial
Token ID498
Feature activation-3.02e-01

Pos logit contributions
Narr+0.573
guyen+0.562
erker+0.552
��+0.529
stood+0.525
Neg logit contributions
 spons-0.868
 overboard-0.752
 slack-0.691
 distingu-0.674
anova-0.654
TokenName
Token ID5376
Feature activation-6.29e-02

Pos logit contributions
guyen+0.627
Narr+0.623
erker+0.618
stood+0.602
��+0.594
Neg logit contributions
 spons-1.043
 overboard-0.899
 slack-0.834
 distingu-0.817
 conclud-0.806
Token('
Token ID10786
Feature activation+7.48e-03

Pos logit contributions
Narr+0.136
guyen+0.132
erker+0.131
stood+0.126
��+0.124
Neg logit contributions
 spons-0.214
 overboard-0.184
 slack-0.172
 distingu-0.166
 conclud-0.164
Tokensystem
Token ID10057
Feature activation-3.95e-01

Pos logit contributions
 spons+0.025
 overboard+0.021
 slack+0.019
anova+0.019
 distingu+0.019
Neg logit contributions
Narr-0.017
erker-0.016
guyen-0.016
��-0.016
stood-0.015
Token.
Token ID13
Feature activation-5.54e-02

Pos logit contributions
Narr+0.988
��+0.937
erker+0.926
guyen+0.922
stood+0.901
Neg logit contributions
 spons-1.247
 overboard-1.047
 slack-0.975
 conclud-0.940
 distingu-0.936
Tokendraw
Token ID19334
Feature activation-4.33e-01

Pos logit contributions
Narr+0.152
erker+0.144
��+0.142
guyen+0.142
MQ+0.138
Neg logit contributions
 spons-0.160
 overboard-0.131
 slack-0.116
anova-0.113
 distingu-0.113
Tokening
Token ID278
Feature activation-2.86e-01

Pos logit contributions
Narr+1.045
��+1.011
guyen+1.009
stood+0.976
erker+0.971
Neg logit contributions
 spons-1.379
 overboard-1.152
 slack-1.056
anova-1.022
 distingu-1.022
Token.
Token ID13
Feature activation+9.31e-03

Pos logit contributions
Narr+0.714
��+0.686
guyen+0.680
erker+0.673
stood+0.658
Neg logit contributions
 spons-0.894
 overboard-0.747
 slack-0.683
 distingu-0.658
anova-0.649
Tokenim
Token ID320
Feature activation-2.25e-01

Pos logit contributions
 spons+0.030
 overboard+0.025
 slack+0.023
anova+0.022
 distingu+0.022
Neg logit contributions
Narr-0.022
erker-0.021
guyen-0.021
��-0.021
stood-0.020
Tokenaging
Token ID3039
Feature activation-2.28e-01

Pos logit contributions
Narr+0.546
��+0.541
��+0.515
guyen+0.509
stood+0.504
Neg logit contributions
 spons-0.722
 overboard-0.603
 slack-0.539
 distingu-0.533
anova-0.529
Token')
Token ID11537
Feature activation+1.19e-01

Pos logit contributions
Narr+0.571
��+0.549
guyen+0.546
erker+0.540
stood+0.532
Neg logit contributions
 spons-0.702
 overboard-0.584
 slack-0.537
 distingu-0.521
anova-0.517
Token Right
Token ID6498
Feature activation+8.20e-02

Pos logit contributions
 spons+0.086
 overboard+0.073
 slack+0.065
 conclud+0.063
 distingu+0.063
Neg logit contributions
Narr-0.073
erker-0.070
��-0.069
guyen-0.068
MQ-0.068
Tokeneous
Token ID15303
Feature activation+1.60e-01

Pos logit contributions
 spons+0.268
 overboard+0.224
 slack+0.201
 distingu+0.195
 conclud+0.191
Neg logit contributions
Narr-0.200
��-0.194
guyen-0.190
erker-0.189
stood-0.185
Token Brothers
Token ID16055
Feature activation+3.06e-02

Pos logit contributions
 spons+0.498
 overboard+0.418
 slack+0.371
 Tycoon+0.362
 distingu+0.358
Neg logit contributions
Narr-0.406
guyen-0.389
��-0.387
erker-0.383
stood-0.374
Token singer
Token ID14015
Feature activation+9.63e-02

Pos logit contributions
 spons+0.089
 overboard+0.074
 slack+0.066
 conclud+0.063
 distingu+0.063
Neg logit contributions
Narr-0.085
guyen-0.081
��-0.080
erker-0.080
��-0.079
Token Bill
Token ID3941
Feature activation+5.00e-02

Pos logit contributions
 spons+0.283
 overboard+0.237
 slack+0.214
 Tycoon+0.201
 distingu+0.201
Neg logit contributions
Narr-0.260
erker-0.249
guyen-0.247
��-0.244
MQ-0.239
Token Med
Token ID2019
Feature activation-5.53e-01

Pos logit contributions
 spons+0.156
 overboard+0.129
 slack+0.117
anova+0.114
 distingu+0.111
Neg logit contributions
Narr-0.128
MQ-0.120
guyen-0.119
erker-0.119
stood-0.119
Tokenley
Token ID1636
Feature activation+2.24e-01

Pos logit contributions
Narr+1.232
��+1.132
guyen+1.105
��+1.103
erker+1.087
Neg logit contributions
 spons-1.948
 overboard-1.681
 slack-1.512
 conclud-1.470
 distingu-1.470
Token,
Token ID11
Feature activation+7.07e-02

Pos logit contributions
 spons+0.663
 overboard+0.568
 slack+0.499
 conclud+0.487
 distingu+0.470
Neg logit contributions
Narr-0.597
guyen-0.568
��-0.566
erker-0.564
stood-0.551
Token whose
Token ID3025
Feature activation+8.91e-04

Pos logit contributions
 spons+0.216
 overboard+0.186
 slack+0.163
 conclud+0.159
 distingu+0.158
Neg logit contributions
Narr-0.182
erker-0.175
��-0.174
guyen-0.172
��-0.168
Token brutal
Token ID12399
Feature activation+6.24e-02

Pos logit contributions
 spons+0.002
 overboard+0.002
 slack+0.002
 distingu+0.002
 conclud+0.002
Neg logit contributions
Narr-0.003
erker-0.002
guyen-0.002
��-0.002
stood-0.002
Token murder
Token ID5123
Feature activation-3.17e-03

Pos logit contributions
 spons+0.156
 overboard+0.128
 slack+0.110
 conclud+0.105
 distingu+0.105
Neg logit contributions
Narr-0.196
guyen-0.188
erker-0.186
��-0.184
stood-0.183