TOP ACTIVATIONS
MAX = 2.305

former Luxembourg premier Jean - Cla ude Jun cker , she
Brennan Center filed an am icus brief calling for the Court
all age groups . Every parent loves to see their kids
Ma hea k au .
After spending a decade in Guantanamo Bay , Kh adr was
or rell y Animation of tra ject ory from 24 October
k ula ho ā man a p ū ke
utilities face a major logistical hurdle in replacing fuel oil :
Law yers for the former Guantanamo Bay detainee cons ented Thursday
sequence in which one woman crou ches on the floor while
to accept the transfer of Guantanamo Bay detainees who have been
obligation to fight climate disturbance and reiterated Berlin
first commercial test for the Zika virus will become available to
take the reins at the Commission in her negotiations with European
he grants freedom to a crou ching slave . That tens
that same mandate has a loophole that could guarantee fossil fuel
shi was involved in irregular siph oning activities , so they
rigorous testing to meet MIL STD 810 G standards , guaranteeing
pil ina ā ina a
. The one kilomet re to go mark was

MIN ACTIVATIONS
MIN = -2.145

cold est gym I have known , more like a freezer
platform er on Xbox Live Indie Games . Needs to be
even without AA ( I dunno an 8 k or 16
the California High School Exit Exam since its 2006 debut would
to a Jud as Priest concert in Land over , Maryland
held Wednesday on $ 500 bond , and it was unknown
arin gas in a Tokyo subway , killing 12 people and
figure than His Majesty King Carl XVI Gust af himself hauled
pl ines , run for Shia and Sunni Muslims , have
idae ). IV . Mult if acet ed study of the
Democratic presidential nominee Hillary Clinton Hillary Diane Rodham Clinton Sanders :
election matchup between Donald Trump Donald John Trump House committee believes
With an economy roughly the size of Spain s
was dealt to the Pittsburgh Penguins in the summer of 2015
problem . If I were Shia , I d
right ? Leave Shia alone , guys . You
has repeatedly criticized President Trump Donald John Trump House committee believes
healthcare , and retain a pension .
out but let me know if anyone does this project
went through the LA X security line with Marilyn Manson ,"

INTERVAL 1.192 - 2.305
CONTAINS 0.290%

. But as with every new toy , there are some
case or the child is transgender , society inst ills in
and the specifics are different here , the approach feels worn
is created and the archived file is uploaded to it .
take effective action on climate change considering the amount of money

INTERVAL 0.080 - 1.192
CONTAINS 40.580%

forces in the R SI also fought against the Allies including
memor anda intended to help minority communities , as well as
O pin ion ( by Jesse Smith )
if you re an emanc ip ated American woman
or spons or spons or

INTERVAL -1.032 - 0.080
CONTAINS 58.398%

was the one that just kind of haunted all of us
V ivid Audio -- and their lowest - priced models cost
what the shop s security system recorded during the
it is discreet . It ref r ains from prose ly
in employment , qualify for benefits , access education and healthcare

INTERVAL -2.145 - -1.032
CONTAINS 0.732%

accordingly . <|endoftext|> Story highlights Police chief vows wanted suspect "
Indeed , this idea of what it means to truly be
Mark Ham ill , best known for playing Luke Skywalker in
on average . In Mid western counties with high mortality rates
и а м
Token former
Token ID1966
Feature activation+1.26e+00

Pos logit contributions
+0.121
eteenth+0.112
ORK+0.106
glers+0.105
IGHTS+0.104
Neg logit contributions
 spoiler-0.090
 dilig-0.085
 spoilers-0.084
emale-0.083
adium-0.079
Token Luxembourg
Token ID31864
Feature activation+1.59e+00

Pos logit contributions
+3.632
eteenth+3.325
glers+3.152
ORK+3.132
IGHTS+3.093
Neg logit contributions
 spoiler-3.549
 dilig-3.528
emale-3.453
 spoilers-3.367
adium-3.273
Token premier
Token ID18256
Feature activation-7.70e-01

Pos logit contributions
+5.071
eteenth+4.658
ORK+4.400
IGHTS+4.342
glers+4.314
Neg logit contributions
 spoiler-4.117
 dilig-3.947
 spoilers-3.936
emale-3.815
adium-3.693
Token Jean
Token ID11320
Feature activation+4.51e-02

Pos logit contributions
 spoiler+2.402
 spoilers+2.257
 dilig+2.249
emale+2.113
 volunt+2.092
Neg logit contributions
-2.174
eteenth-1.992
ORK-1.847
glers-1.812
IGHTS-1.800
Token-
Token ID12
Feature activation-1.52e-01

Pos logit contributions
+0.123
eteenth+0.112
ORK+0.104
IGHTS+0.101
glers+0.101
Neg logit contributions
 spoiler-0.144
 dilig-0.138
 spoilers-0.137
emale-0.134
adium-0.129
TokenCla
Token ID47404
Feature activation+2.30e+00

Pos logit contributions
 spoiler+0.793
 dilig+0.770
 spoilers+0.768
emale+0.757
adium+0.743
Neg logit contributions
-0.105
eteenth-0.067
ORK-0.040
glers-0.034
IGHTS-0.031
Tokenude
Token ID2507
Feature activation+2.86e-02

Pos logit contributions
+4.801
eteenth+4.642
ORK+4.276
ters+4.252
č+4.171
Neg logit contributions
 spoiler-8.173
 dilig-8.040
 spoilers-7.878
 tremend-7.817
emale-7.706
Token Jun
Token ID7653
Feature activation+1.45e+00

Pos logit contributions
+0.071
eteenth+0.064
ORK+0.058
glers+0.058
IGHTS+0.057
Neg logit contributions
 spoiler-0.099
 spoilers-0.095
 dilig-0.094
emale-0.091
adium-0.089
Tokencker
Token ID15280
Feature activation+1.39e+00

Pos logit contributions
+1.778
eteenth+1.591
ORK+1.319
č+1.177
ters+1.144
Neg logit contributions
 spoiler-6.684
 dilig-6.568
 spoilers-6.530
emale-6.492
 tremend-6.353
Token,
Token ID11
Feature activation+1.98e-01

Pos logit contributions
+4.029
eteenth+3.671
č+3.408
glers+3.403
ters+3.400
Neg logit contributions
 spoiler-3.935
 dilig-3.879
emale-3.820
 spoilers-3.743
adium-3.653
Token she
Token ID673
Feature activation+2.27e-02

Pos logit contributions
+0.644
eteenth+0.595
ORK+0.561
glers+0.551
IGHTS+0.550
Neg logit contributions
 spoiler-0.520
 dilig-0.498
 spoilers-0.489
emale-0.485
adium-0.461
Token Brennan
Token ID26577
Feature activation+7.90e-01

Pos logit contributions
+0.638
eteenth+0.585
ORK+0.548
glers+0.536
IGHTS+0.535
Neg logit contributions
 spoiler-0.620
 dilig-0.593
 spoilers-0.586
emale-0.577
adium-0.555
Token Center
Token ID3337
Feature activation+2.35e-01

Pos logit contributions
+2.595
eteenth+2.387
ORK+2.254
IGHTS+2.213
glers+2.198
Neg logit contributions
 spoiler-2.041
 dilig-1.972
emale-1.931
 spoilers-1.916
adium-1.829
Token filed
Token ID5717
Feature activation+1.04e+00

Pos logit contributions
+0.780
eteenth+0.718
ORK+0.677
glers+0.666
IGHTS+0.664
Neg logit contributions
 spoiler-0.607
 dilig-0.579
 spoilers-0.570
emale-0.562
adium-0.536
Token an
Token ID281
Feature activation+6.82e-01

Pos logit contributions
+3.062
eteenth+2.840
ORK+2.629
IGHTS+2.571
glers+2.539
Neg logit contributions
 spoiler-3.013
 dilig-2.894
emale-2.850
 spoilers-2.841
adium-2.751
Token am
Token ID716
Feature activation+4.15e-01

Pos logit contributions
+2.078
eteenth+1.912
ORK+1.784
IGHTS+1.749
glers+1.717
Neg logit contributions
 spoiler-1.947
 dilig-1.861
 spoilers-1.838
emale-1.818
adium-1.751
Tokenicus
Token ID24552
Feature activation+2.19e+00

Pos logit contributions
+0.888
eteenth+0.794
ORK+0.728
glers+0.691
IGHTS+0.688
Neg logit contributions
 spoiler-1.564
 spoilers-1.505
 dilig-1.502
emale-1.475
 volunt-1.424
Token brief
Token ID4506
Feature activation+7.24e-01

Pos logit contributions
+6.359
eteenth+6.015
ORK+5.635
IGHTS+5.425
č+5.323
Neg logit contributions
 spoiler-5.894
emale-5.815
 dilig-5.784
 spoilers-5.713
adium-5.467
Token calling
Token ID4585
Feature activation-3.21e-01

Pos logit contributions
+2.229
eteenth+2.039
ORK+1.917
IGHTS+1.872
glers+1.853
Neg logit contributions
 spoiler-2.038
 dilig-1.953
 spoilers-1.935
emale-1.909
adium-1.820
Token for
Token ID329
Feature activation+3.46e-01

Pos logit contributions
 spoiler+0.859
 dilig+0.814
 spoilers+0.808
emale+0.788
adium+0.755
Neg logit contributions
-1.042
eteenth-0.961
ORK-0.905
glers-0.887
IGHTS-0.886
Token the
Token ID262
Feature activation+1.91e-02

Pos logit contributions
+1.077
eteenth+0.997
ORK+0.932
IGHTS+0.914
glers+0.911
Neg logit contributions
 spoiler-0.956
 dilig-0.912
emale-0.901
 spoilers-0.898
adium-0.857
Token Court
Token ID3078
Feature activation+1.35e+00

Pos logit contributions
+0.056
eteenth+0.051
ORK+0.048
glers+0.047
IGHTS+0.047
Neg logit contributions
 spoiler-0.057
 dilig-0.055
 spoilers-0.054
emale-0.053
adium-0.051
Token all
Token ID477
Feature activation+2.04e-01

Pos logit contributions
+0.398
eteenth+0.369
ORK+0.351
glers+0.344
IGHTS+0.344
Neg logit contributions
 spoiler-0.280
 dilig-0.267
 spoilers-0.262
emale-0.258
adium-0.245
Token age
Token ID2479
Feature activation-3.84e-02

Pos logit contributions
+0.782
eteenth+0.731
ORK+0.695
IGHTS+0.685
glers+0.683
Neg logit contributions
 spoiler-0.419
 dilig-0.394
 spoilers-0.387
emale-0.378
adium-0.359
Token groups
Token ID2628
Feature activation+1.31e-01

Pos logit contributions
 spoiler+0.107
 dilig+0.101
 spoilers+0.100
emale+0.099
adium+0.095
Neg logit contributions
-0.121
eteenth-0.111
ORK-0.105
IGHTS-0.103
glers-0.103
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
+0.412
eteenth+0.378
ORK+0.357
glers+0.351
IGHTS+0.350
Neg logit contributions
 spoiler-0.362
 dilig-0.346
 spoilers-0.340
emale-0.336
adium-0.320
TokenEvery
Token ID6109
Feature activation-3.32e-01

Pos logit contributions
 spoiler+0.496
 dilig+0.469
 spoilers+0.467
emale+0.454
adium+0.437
Neg logit contributions
-0.560
eteenth-0.515
ORK-0.483
glers-0.474
IGHTS-0.473
Token parent
Token ID2560
Feature activation+2.13e+00

Pos logit contributions
 spoiler+0.984
 dilig+0.937
 spoilers+0.931
emale+0.908
adium+0.875
Neg logit contributions
-0.985
eteenth-0.900
ORK-0.843
glers-0.825
IGHTS-0.823
Token loves
Token ID10408
Feature activation+8.95e-01

Pos logit contributions
+6.097
eteenth+5.607
ters+5.354
IGHTS+5.251
ORK+5.236
Neg logit contributions
 dilig-5.659
 spoiler-5.656
emale-5.615
 spoilers-5.260
adium-5.253
Token to
Token ID284
Feature activation+6.10e-01

Pos logit contributions
+2.586
eteenth+2.386
ORK+2.262
glers+2.243
IGHTS+2.206
Neg logit contributions
 spoiler-2.577
 dilig-2.518
emale-2.499
 spoilers-2.395
adium-2.346
Token see
Token ID766
Feature activation-1.24e-01

Pos logit contributions
+1.981
eteenth+1.831
ORK+1.735
glers+1.721
IGHTS+1.707
Neg logit contributions
 spoiler-1.560
 dilig-1.521
emale-1.487
 spoilers-1.471
adium-1.408
Token their
Token ID511
Feature activation-1.83e-01

Pos logit contributions
 spoiler+0.327
 dilig+0.313
 spoilers+0.305
emale+0.304
adium+0.290
Neg logit contributions
-0.407
eteenth-0.376
ORK-0.356
glers-0.350
IGHTS-0.349
Token kids
Token ID3988
Feature activation+3.81e-01

Pos logit contributions
 spoiler+0.461
 dilig+0.439
 spoilers+0.432
emale+0.424
adium+0.405
Neg logit contributions
-0.618
eteenth-0.573
ORK-0.542
glers-0.531
IGHTS-0.531
Token Ma
Token ID6669
Feature activation+3.82e-01

Pos logit contributions
 spoiler+0.159
 dilig+0.151
 spoilers+0.150
emale+0.147
adium+0.141
Neg logit contributions
-0.164
eteenth-0.150
ORK-0.141
glers-0.138
IGHTS-0.137
Tokenhea
Token ID21632
Feature activation+8.39e-01

Pos logit contributions
+1.135
eteenth+1.038
ORK+0.969
glers+0.945
IGHTS+0.943
Neg logit contributions
 spoiler-1.126
 dilig-1.080
 spoilers-1.065
emale-1.042
adium-1.002
Token
Token ID220
Feature activation-4.76e-02

Pos logit contributions
+2.616
eteenth+2.387
ORK+2.235
IGHTS+2.177
glers+2.168
Neg logit contributions
 spoiler-2.334
 dilig-2.238
 spoilers-2.187
emale-2.162
adium-2.070
Token
Token ID134
Feature activation+3.87e-01

Pos logit contributions
 spoiler+0.153
 dilig+0.147
 spoilers+0.146
emale+0.143
adium+0.138
Neg logit contributions
-0.129
eteenth-0.117
ORK-0.109
glers-0.106
IGHTS-0.106
Token
Token ID119
Feature activation+3.17e-01

Pos logit contributions
+0.612
eteenth+0.516
ORK+0.440
glers+0.424
IGHTS+0.421
Neg logit contributions
 spoiler-1.689
 dilig-1.639
 spoilers-1.628
emale-1.602
adium-1.561
Token
Token ID128
Feature activation+2.05e+00

Pos logit contributions
+0.998
eteenth+0.922
ORK+0.861
glers+0.845
IGHTS+0.844
Neg logit contributions
 spoiler-0.884
 dilig-0.841
 spoilers-0.835
emale-0.801
 volunt-0.772
Token
Token ID222
Feature activation+6.09e-01

Pos logit contributions
+5.372
eteenth+4.875
ORK+4.337
glers+4.300
IGHTS+4.160
Neg logit contributions
 spoiler-6.604
 spoilers-6.327
 dilig-6.314
emale-6.187
 lockout-5.952
Tokenk
Token ID74
Feature activation-1.10e-01

Pos logit contributions
+1.638
eteenth+1.479
ORK+1.369
glers+1.342
IGHTS+1.326
Neg logit contributions
 spoiler-1.973
 dilig-1.890
 spoilers-1.878
emale-1.829
adium-1.769
Tokenau
Token ID559
Feature activation+3.95e-01

Pos logit contributions
 spoiler+0.327
 dilig+0.312
 spoilers+0.310
emale+0.302
adium+0.291
Neg logit contributions
-0.325
eteenth-0.297
ORK-0.277
glers-0.272
IGHTS-0.271
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
+1.177
eteenth+1.074
ORK+1.001
glers+0.982
IGHTS+0.973
Neg logit contributions
 spoiler-1.162
 dilig-1.109
 spoilers-1.097
emale-1.073
adium-1.034
Token
Token ID198
Feature activation+1.42e-01

Pos logit contributions
+0.479
eteenth+0.438
ORK+0.410
IGHTS+0.400
glers+0.400
Neg logit contributions
 spoiler-0.453
 dilig-0.433
 spoilers-0.428
emale-0.418
adium-0.402
Token After
Token ID2293
Feature activation-6.21e-01

Pos logit contributions
 spoiler+0.364
 dilig+0.349
 spoilers+0.343
emale+0.337
 tremend+0.324
Neg logit contributions
-0.360
eteenth-0.328
ORK-0.308
IGHTS-0.302
glers-0.302
Token spending
Token ID4581
Feature activation+7.35e-01

Pos logit contributions
 spoiler+1.733
 dilig+1.640
 spoilers+1.637
emale+1.582
adium+1.527
Neg logit contributions
-1.950
eteenth-1.795
ORK-1.683
glers-1.651
IGHTS-1.646
Token a
Token ID257
Feature activation-4.78e-01

Pos logit contributions
+2.070
eteenth+1.920
ORK+1.758
glers+1.740
IGHTS+1.728
Neg logit contributions
 spoiler-2.178
 dilig-2.158
emale-2.111
 spoilers-2.067
 tremend-1.996
Token decade
Token ID5707
Feature activation+5.22e-02

Pos logit contributions
 spoiler+1.449
 dilig+1.376
 spoilers+1.368
emale+1.334
adium+1.286
Neg logit contributions
-1.391
eteenth-1.266
ORK-1.187
glers-1.158
IGHTS-1.157
Token in
Token ID287
Feature activation-4.95e-01

Pos logit contributions
+0.152
eteenth+0.139
ORK+0.130
IGHTS+0.127
glers+0.127
Neg logit contributions
 spoiler-0.155
 dilig-0.150
 spoilers-0.148
emale-0.147
adium-0.140
Token Guantanamo
Token ID34378
Feature activation+2.00e+00

Pos logit contributions
 spoiler+1.299
 spoilers+1.212
 dilig+1.207
emale+1.159
 volunt+1.128
Neg logit contributions
-1.642
eteenth-1.520
ORK-1.435
glers-1.407
IGHTS-1.404
Token Bay
Token ID4696
Feature activation+3.87e-01

Pos logit contributions
+5.210
eteenth+4.637
ORK+4.303
IGHTS+4.286
č+4.274
Neg logit contributions
 dilig-6.016
 spoiler-5.981
emale-5.858
 spoilers-5.783
 tremend-5.749
Token,
Token ID11
Feature activation-6.04e-02

Pos logit contributions
+1.183
eteenth+1.079
ORK+1.016
glers+1.002
IGHTS+0.999
Neg logit contributions
 spoiler-1.091
 dilig-1.055
 spoilers-1.035
emale-1.030
 tremend-0.987
Token Kh
Token ID5311
Feature activation-1.81e-01

Pos logit contributions
 spoiler+0.169
 dilig+0.161
 spoilers+0.160
emale+0.157
adium+0.150
Neg logit contributions
-0.189
eteenth-0.173
ORK-0.163
glers-0.159
IGHTS-0.159
Tokenadr
Token ID41909
Feature activation+5.36e-01

Pos logit contributions
 spoiler+0.538
 dilig+0.513
 spoilers+0.509
emale+0.497
adium+0.478
Neg logit contributions
-0.537
eteenth-0.492
ORK-0.460
glers-0.450
IGHTS-0.449
Token was
Token ID373
Feature activation-4.45e-01

Pos logit contributions
+1.605
eteenth+1.454
ORK+1.360
IGHTS+1.355
glers+1.349
Neg logit contributions
 spoiler-1.545
 dilig-1.501
 spoilers-1.470
emale-1.464
adium-1.390
Tokenor
Token ID273
Feature activation+6.57e-01

Pos logit contributions
+0.600
eteenth+0.546
ORK+0.511
IGHTS+0.499
glers+0.498
Neg logit contributions
 spoiler-0.651
 dilig-0.624
 spoilers-0.615
emale-0.604
 volunt-0.581
Tokenrell
Token ID11252
Feature activation+4.15e-01

Pos logit contributions
+1.849
eteenth+1.687
ORK+1.563
glers+1.546
IGHTS+1.513
Neg logit contributions
 spoiler-2.021
 dilig-1.958
 spoilers-1.911
emale-1.885
 tremend-1.812
Tokeny
Token ID88
Feature activation+1.68e-01

Pos logit contributions
+1.252
eteenth+1.145
ORK+1.076
IGHTS+1.057
glers+1.043
Neg logit contributions
 spoiler-1.191
 dilig-1.155
 spoilers-1.125
emale-1.106
 volunt-1.062
Token Animation
Token ID23535
Feature activation+3.00e-01

Pos logit contributions
+0.502
eteenth+0.458
ORK+0.431
IGHTS+0.422
glers+0.420
Neg logit contributions
 spoiler-0.491
 dilig-0.471
 spoilers-0.464
emale-0.455
adium-0.437
Token of
Token ID286
Feature activation+3.51e-01

Pos logit contributions
+0.903
eteenth+0.825
ORK+0.775
IGHTS+0.760
glers+0.757
Neg logit contributions
 spoiler-0.866
 dilig-0.836
 spoilers-0.819
emale-0.807
adium-0.775
Tokentra
Token ID9535
Feature activation+1.96e+00

Pos logit contributions
+1.084
eteenth+0.993
ORK+0.938
glers+0.918
IGHTS+0.918
Neg logit contributions
 spoiler-0.980
 dilig-0.943
 spoilers-0.922
emale-0.910
adium-0.873
Tokenject
Token ID752
Feature activation+1.14e+00

Pos logit contributions
+5.290
eteenth+4.857
IGHTS+4.475
ORK+4.434
glers+4.398
Neg logit contributions
 spoiler-5.919
 dilig-5.695
 spoilers-5.586
emale-5.548
 lockout-5.379
Tokenory
Token ID652
Feature activation+6.31e-01

Pos logit contributions
+4.139
eteenth+3.872
ORK+3.694
IGHTS+3.623
glers+3.594
Neg logit contributions
 spoiler-2.438
 dilig-2.363
 spoilers-2.267
emale-2.187
 tremend-2.153
Token from
Token ID422
Feature activation+4.57e-01

Pos logit contributions
+1.931
eteenth+1.767
ORK+1.665
IGHTS+1.624
glers+1.620
Neg logit contributions
 spoiler-1.778
 dilig-1.716
 spoilers-1.675
emale-1.656
adium-1.584
Token 24
Token ID1987
Feature activation+5.79e-01

Pos logit contributions
+1.394
eteenth+1.276
ORK+1.201
IGHTS+1.174
glers+1.169
Neg logit contributions
 spoiler-1.296
 dilig-1.246
 spoilers-1.224
emale-1.205
adium-1.155
Token October
Token ID3267
Feature activation+3.26e-01

Pos logit contributions
+1.598
eteenth+1.453
ORK+1.355
IGHTS+1.324
glers+1.319
Neg logit contributions
 spoiler-1.827
 dilig-1.754
 spoilers-1.728
emale-1.701
adium-1.635
Token k
Token ID479
Feature activation-4.20e-01

Pos logit contributions
+1.172
eteenth+1.072
ORK+0.999
glers+0.977
IGHTS+0.972
Neg logit contributions
 spoiler-1.259
 dilig-1.203
 spoilers-1.194
emale-1.166
adium-1.124
Tokenula
Token ID4712
Feature activation+5.78e-01

Pos logit contributions
 spoiler+1.288
 dilig+1.229
 spoilers+1.221
emale+1.193
adium+1.150
Neg logit contributions
-1.204
eteenth-1.098
ORK-1.025
glers-1.002
IGHTS-1.000
Token ho
Token ID8169
Feature activation+2.49e-01

Pos logit contributions
+1.774
eteenth+1.632
ORK+1.526
glers+1.484
IGHTS+1.481
Neg logit contributions
 spoiler-1.629
 dilig-1.552
 spoilers-1.539
emale-1.502
adium-1.445
Token
Token ID134
Feature activation+1.25e+00

Pos logit contributions
+0.767
eteenth+0.706
ORK+0.660
IGHTS+0.644
glers+0.642
Neg logit contributions
 spoiler-0.708
 dilig-0.675
 spoilers-0.669
emale-0.650
adium-0.626
Token
Token ID119
Feature activation+8.68e-01

Pos logit contributions
+2.592
eteenth+2.291
ORK+1.993
IGHTS+1.934
glers+1.933
Neg logit contributions
 spoiler-4.834
 spoilers-4.643
 dilig-4.615
emale-4.548
adium-4.407
Tokenā
Token ID10235
Feature activation+1.93e+00

Pos logit contributions
+2.609
eteenth+2.401
ORK+2.230
glers+2.175
IGHTS+2.172
Neg logit contributions
 spoiler-2.525
 dilig-2.396
 spoilers-2.387
emale-2.294
 lockout-2.216
Tokenman
Token ID805
Feature activation+3.61e-01

Pos logit contributions
+5.282
eteenth+4.785
č+4.421
ORK+4.397
glers+4.321
Neg logit contributions
 spoiler-5.874
 dilig-5.610
 spoilers-5.593
emale-5.449
adium-5.302
Tokena
Token ID64
Feature activation+6.92e-01

Pos logit contributions
+1.104
eteenth+1.015
ORK+0.944
glers+0.924
IGHTS+0.921
Neg logit contributions
 spoiler-1.027
 dilig-0.981
 spoilers-0.971
emale-0.947
adium-0.914
Token p
Token ID279
Feature activation-4.38e-01

Pos logit contributions
+2.122
eteenth+1.955
ORK+1.819
IGHTS+1.771
č+1.764
Neg logit contributions
 spoiler-1.950
 dilig-1.854
 spoilers-1.840
emale-1.797
adium-1.734
Tokenū
Token ID20317
Feature activation+1.43e+00

Pos logit contributions
 spoiler+1.282
 dilig+1.221
 spoilers+1.212
emale+1.184
adium+1.140
Neg logit contributions
-1.311
eteenth-1.200
ORK-1.124
glers-1.100
IGHTS-1.098
Token ke
Token ID885
Feature activation-2.73e-01

Pos logit contributions
+3.786
eteenth+3.454
ORK+3.158
glers+3.130
č+3.128
Neg logit contributions
 spoiler-4.543
 dilig-4.349
 spoilers-4.328
emale-4.217
adium-4.083
Token utilities
Token ID20081
Feature activation-3.54e-01

Pos logit contributions
 spoiler+0.727
 dilig+0.691
 spoilers+0.686
emale+0.669
adium+0.642
Neg logit contributions
-0.830
eteenth-0.763
ORK-0.718
glers-0.703
IGHTS-0.702
Token face
Token ID1986
Feature activation-2.06e-01

Pos logit contributions
 spoiler+0.909
 dilig+0.860
 spoilers+0.852
emale+0.830
adium+0.794
Neg logit contributions
-1.187
eteenth-1.097
ORK-1.036
glers-1.017
IGHTS-1.016
Token a
Token ID257
Feature activation+1.53e-01

Pos logit contributions
 spoiler+0.561
 dilig+0.531
 spoilers+0.528
emale+0.512
adium+0.493
Neg logit contributions
-0.660
eteenth-0.608
ORK-0.572
glers-0.560
IGHTS-0.560
Token major
Token ID1688
Feature activation-1.69e-01

Pos logit contributions
+0.492
eteenth+0.455
ORK+0.428
glers+0.421
IGHTS+0.419
Neg logit contributions
 spoiler-0.408
 dilig-0.391
 spoilers-0.387
emale-0.380
adium-0.364
Token logistical
Token ID41088
Feature activation+6.18e-01

Pos logit contributions
 spoiler+0.466
 dilig+0.445
 spoilers+0.440
emale+0.431
adium+0.413
Neg logit contributions
-0.534
eteenth-0.492
ORK-0.462
glers-0.453
IGHTS-0.452
Token hurdle
Token ID36633
Feature activation+1.93e+00

Pos logit contributions
+1.816
eteenth+1.656
ORK+1.552
glers+1.526
IGHTS+1.515
Neg logit contributions
 spoiler-1.770
 dilig-1.741
emale-1.715
 spoilers-1.692
adium-1.617
Token in
Token ID287
Feature activation+1.98e-01

Pos logit contributions
+5.417
eteenth+4.884
glers+4.634
ORK+4.562
ters+4.558
Neg logit contributions
 spoiler-5.550
emale-5.525
 dilig-5.432
 spoilers-5.287
 tremend-5.113
Token replacing
Token ID13586
Feature activation-1.42e-01

Pos logit contributions
+0.598
eteenth+0.548
ORK+0.514
glers+0.505
IGHTS+0.502
Neg logit contributions
 spoiler-0.571
 dilig-0.546
 spoilers-0.540
emale-0.533
adium-0.508
Token fuel
Token ID5252
Feature activation+2.91e-01

Pos logit contributions
 spoiler+0.374
 dilig+0.354
 spoilers+0.351
emale+0.344
adium+0.328
Neg logit contributions
-0.465
eteenth-0.429
ORK-0.405
glers-0.397
IGHTS-0.396
Token oil
Token ID3056
Feature activation-7.38e-02

Pos logit contributions
+0.872
eteenth+0.793
ORK+0.748
IGHTS+0.733
glers+0.731
Neg logit contributions
 spoiler-0.837
 dilig-0.806
emale-0.796
 spoilers-0.790
 tremend-0.749
Token:
Token ID25
Feature activation+5.00e-01

Pos logit contributions
 spoiler+0.208
 dilig+0.199
 spoilers+0.197
emale+0.195
adium+0.185
Neg logit contributions
-0.227
eteenth-0.209
ORK-0.196
glers-0.192
IGHTS-0.192
TokenLaw
Token ID16966
Feature activation+3.45e-01

Pos logit contributions
+0.550
eteenth+0.499
ORK+0.467
IGHTS+0.456
glers+0.455
Neg logit contributions
 spoiler-0.608
 dilig-0.584
 spoilers-0.576
emale-0.564
adium-0.543
Tokenyers
Token ID21200
Feature activation+1.46e-01

Pos logit contributions
+0.732
eteenth+0.646
ORK+0.594
glers+0.577
IGHTS+0.574
Neg logit contributions
 spoiler-1.301
 dilig-1.261
 spoilers-1.241
emale-1.226
adium-1.194
Token for
Token ID329
Feature activation+9.08e-06

Pos logit contributions
+0.480
eteenth+0.442
ORK+0.419
IGHTS+0.411
glers+0.410
Neg logit contributions
 spoiler-0.382
 dilig-0.364
 spoilers-0.360
emale-0.354
adium-0.337
Token the
Token ID262
Feature activation+5.47e-03

Feature not active on prev token;
no predictions were affected.
Token former
Token ID1966
Feature activation+7.63e-01

Pos logit contributions
+0.017
eteenth+0.016
ORK+0.015
glers+0.015
IGHTS+0.015
Neg logit contributions
 spoiler-0.015
 dilig-0.014
 spoilers-0.014
emale-0.014
adium-0.013
Token Guantanamo
Token ID34378
Feature activation+1.93e+00

Pos logit contributions
+2.173
eteenth+1.978
ORK+1.849
IGHTS+1.835
glers+1.829
Neg logit contributions
 spoiler-2.252
 dilig-2.228
emale-2.158
 spoilers-2.150
 tremend-2.067
Token Bay
Token ID4696
Feature activation+5.64e-01

Pos logit contributions
+4.884
eteenth+4.421
glers+4.069
IGHTS+4.054
 Arri+4.026
Neg logit contributions
 dilig-5.960
 spoiler-5.864
emale-5.788
 tremend-5.731
 spoilers-5.679
Token detainee
Token ID49436
Feature activation+6.03e-01

Pos logit contributions
+2.017
eteenth+1.870
IGHTS+1.766
glers+1.760
ORK+1.750
Neg logit contributions
 spoiler-1.253
 dilig-1.229
emale-1.183
 spoilers-1.175
 tremend-1.129
Token cons
Token ID762
Feature activation-2.64e-01

Pos logit contributions
+1.935
eteenth+1.776
ORK+1.676
IGHTS+1.673
glers+1.665
Neg logit contributions
 spoiler-1.578
 dilig-1.544
 spoilers-1.497
emale-1.492
 tremend-1.425
Tokenented
Token ID4714
Feature activation-9.02e-02

Pos logit contributions
 spoiler+0.605
 dilig+0.568
 spoilers+0.564
emale+0.546
adium+0.518
Neg logit contributions
-0.957
eteenth-0.890
ORK-0.845
glers-0.832
IGHTS-0.830
Token Thursday
Token ID3635
Feature activation-5.57e-01

Pos logit contributions
 spoiler+0.268
 dilig+0.256
 spoilers+0.253
emale+0.249
adium+0.239
Neg logit contributions
-0.266
eteenth-0.243
ORK-0.228
glers-0.223
IGHTS-0.222
Token sequence
Token ID8379
Feature activation-2.29e-01

Pos logit contributions
 spoiler+0.741
 dilig+0.708
 spoilers+0.700
emale+0.685
adium+0.659
Neg logit contributions
-0.864
eteenth-0.796
ORK-0.749
glers-0.735
IGHTS-0.732
Token in
Token ID287
Feature activation-2.29e-01

Pos logit contributions
 spoiler+0.574
 dilig+0.545
 spoilers+0.538
emale+0.525
adium+0.502
Neg logit contributions
-0.780
eteenth-0.722
ORK-0.682
glers-0.668
IGHTS-0.668
Token which
Token ID543
Feature activation-3.94e-01

Pos logit contributions
 spoiler+0.582
 dilig+0.553
 spoilers+0.546
emale+0.532
adium+0.508
Neg logit contributions
-0.773
eteenth-0.715
ORK-0.673
glers-0.661
IGHTS-0.660
Token one
Token ID530
Feature activation-1.51e-01

Pos logit contributions
 spoiler+1.060
 dilig+1.007
 spoilers+0.997
emale+0.973
adium+0.934
Neg logit contributions
-1.274
eteenth-1.174
ORK-1.107
glers-1.085
IGHTS-1.083
Token woman
Token ID2415
Feature activation+3.28e-01

Pos logit contributions
 spoiler+0.387
 dilig+0.368
 spoilers+0.364
emale+0.355
adium+0.340
Neg logit contributions
-0.505
eteenth-0.468
ORK-0.441
glers-0.433
IGHTS-0.432
Token crou
Token ID33838
Feature activation+1.91e+00

Pos logit contributions
+1.086
eteenth+1.007
ORK+0.943
glers+0.935
IGHTS+0.932
Neg logit contributions
 spoiler-0.839
 dilig-0.806
 spoilers-0.787
emale-0.778
adium-0.748
Tokenches
Token ID2052
Feature activation+8.89e-01

Pos logit contributions
+4.384
eteenth+4.105
ters+3.925
glers+3.758
drops+3.721
Neg logit contributions
 spoiler-6.624
 dilig-6.449
 spoilers-6.299
emale-6.247
 tremend-6.124
Token on
Token ID319
Feature activation+1.33e-01

Pos logit contributions
+2.559
eteenth+2.364
ORK+2.171
IGHTS+2.158
glers+2.149
Neg logit contributions
 spoiler-2.592
 dilig-2.520
emale-2.482
 spoilers-2.473
adium-2.380
Token the
Token ID262
Feature activation-9.33e-02

Pos logit contributions
+0.412
eteenth+0.378
ORK+0.356
glers+0.349
IGHTS+0.349
Neg logit contributions
 spoiler-0.370
 dilig-0.357
 spoilers-0.349
emale-0.346
adium-0.332
Token floor
Token ID4314
Feature activation-2.73e-01

Pos logit contributions
 spoiler+0.297
 dilig+0.283
 spoilers+0.282
emale+0.275
adium+0.266
Neg logit contributions
-0.257
eteenth-0.233
ORK-0.217
glers-0.212
IGHTS-0.211
Token while
Token ID981
Feature activation-4.10e-01

Pos logit contributions
 spoiler+0.754
 dilig+0.712
 spoilers+0.709
emale+0.687
adium+0.661
Neg logit contributions
-0.867
eteenth-0.796
ORK-0.751
glers-0.735
IGHTS-0.734
Token to
Token ID284
Feature activation-2.01e-01

Pos logit contributions
+1.063
eteenth+0.974
ORK+0.915
glers+0.902
IGHTS+0.896
Neg logit contributions
 spoiler-0.964
 dilig-0.920
 spoilers-0.911
emale-0.908
adium-0.858
Token accept
Token ID2453
Feature activation+1.63e-01

Pos logit contributions
 spoiler+0.528
 dilig+0.499
 spoilers+0.496
emale+0.481
adium+0.462
Neg logit contributions
-0.666
eteenth-0.615
ORK-0.580
glers-0.568
IGHTS-0.568
Token the
Token ID262
Feature activation-2.09e-01

Pos logit contributions
+0.510
eteenth+0.472
ORK+0.444
glers+0.438
IGHTS+0.433
Neg logit contributions
 spoiler-0.449
 dilig-0.430
 spoilers-0.420
emale-0.420
adium-0.399
Token transfer
Token ID4351
Feature activation-3.06e-01

Pos logit contributions
 spoiler+0.563
 dilig+0.533
 spoilers+0.530
emale+0.515
adium+0.494
Neg logit contributions
-0.675
eteenth-0.622
ORK-0.586
glers-0.574
IGHTS-0.573
Token of
Token ID286
Feature activation+3.91e-02

Pos logit contributions
 spoiler+0.748
 dilig+0.705
 spoilers+0.699
emale+0.677
adium+0.648
Neg logit contributions
-1.066
eteenth-0.989
ORK-0.934
IGHTS-0.918
glers-0.918
Token Guantanamo
Token ID34378
Feature activation+1.91e+00

Pos logit contributions
+0.115
eteenth+0.105
ORK+0.098
glers+0.096
IGHTS+0.096
Neg logit contributions
 spoiler-0.117
 dilig-0.111
 spoilers-0.110
emale-0.108
adium-0.104
Token Bay
Token ID4696
Feature activation+3.98e-01

Pos logit contributions
+4.953
eteenth+4.538
ORK+4.247
IGHTS+4.213
glers+4.201
Neg logit contributions
 spoiler-5.659
emale-5.585
 dilig-5.581
 tremend-5.365
 spoilers-5.357
Token detainees
Token ID25027
Feature activation+3.73e-01

Pos logit contributions
+1.276
eteenth+1.175
ORK+1.101
glers+1.097
IGHTS+1.095
Neg logit contributions
 spoiler-1.048
 dilig-1.005
emale-0.986
 spoilers-0.983
 tremend-0.936
Token who
Token ID508
Feature activation+3.56e-01

Pos logit contributions
+1.180
eteenth+1.084
ORK+1.022
glers+1.004
IGHTS+1.002
Neg logit contributions
 spoiler-1.021
 dilig-0.972
 spoilers-0.962
emale-0.950
adium-0.901
Token have
Token ID423
Feature activation+3.28e-01

Pos logit contributions
+1.179
eteenth+1.092
ORK+1.037
glers+1.029
IGHTS+1.022
Neg logit contributions
 spoiler-0.909
 dilig-0.877
 spoilers-0.854
emale-0.843
adium-0.808
Token been
Token ID587
Feature activation-2.80e-01

Pos logit contributions
+1.030
eteenth+0.949
ORK+0.893
glers+0.880
IGHTS+0.875
Neg logit contributions
 spoiler-0.901
 dilig-0.866
emale-0.846
 spoilers-0.846
adium-0.805
Token obligation
Token ID12990
Feature activation+2.83e-01

Pos logit contributions
+0.492
eteenth+0.458
ORK+0.433
IGHTS+0.426
glers+0.425
Neg logit contributions
 spoiler-0.323
 dilig-0.308
 spoilers-0.303
emale-0.300
adium-0.282
Token
Token ID447
Feature activation-1.26e-02

Pos logit contributions
+0.813
eteenth+0.737
ORK+0.688
IGHTS+0.673
glers+0.670
Neg logit contributions
 spoiler-0.856
 dilig-0.825
 spoilers-0.815
emale-0.807
adium-0.770
Token
Token ID251
Feature activation-2.06e-01

Pos logit contributions
 spoiler+0.046
 dilig+0.044
 spoilers+0.044
emale+0.043
adium+0.041
Neg logit contributions
-0.029
eteenth-0.026
ORK-0.024
glers-0.023
IGHTS-0.023
Token to
Token ID284
Feature activation+1.77e-01

Pos logit contributions
 spoiler+0.566
 dilig+0.539
 spoilers+0.535
emale+0.521
adium+0.499
Neg logit contributions
-0.654
eteenth-0.601
ORK-0.565
glers-0.553
IGHTS-0.552
Token fight
Token ID1907
Feature activation+5.58e-01

Pos logit contributions
+0.573
eteenth+0.527
ORK+0.499
glers+0.490
IGHTS+0.488
Neg logit contributions
 spoiler-0.468
 dilig-0.447
 spoilers-0.442
emale-0.435
adium-0.414
Token climate
Token ID4258
Feature activation+1.88e+00

Pos logit contributions
+1.472
eteenth+1.333
ORK+1.238
glers+1.212
IGHTS+1.206
Neg logit contributions
 spoiler-1.809
 dilig-1.738
 spoilers-1.721
emale-1.712
adium-1.636
Token disturbance
Token ID30497
Feature activation-2.03e-01

Pos logit contributions
+3.638
eteenth+3.173
ORK+2.839
IGHTS+2.827
ters+2.815
Neg logit contributions
emale-6.971
 spoiler-6.898
 dilig-6.786
 spoilers-6.649
 tremend-6.544
Token and
Token ID290
Feature activation+2.10e-01

Pos logit contributions
 spoiler+0.552
 dilig+0.523
 spoilers+0.519
emale+0.504
adium+0.484
Neg logit contributions
-0.651
eteenth-0.600
ORK-0.564
glers-0.553
IGHTS-0.552
Token reiterated
Token ID27116
Feature activation+2.09e-01

Pos logit contributions
+0.663
eteenth+0.608
ORK+0.573
IGHTS+0.562
glers+0.561
Neg logit contributions
 spoiler-0.577
 dilig-0.552
 spoilers-0.545
emale-0.538
adium-0.513
Token Berlin
Token ID11307
Feature activation+1.83e-01

Pos logit contributions
+0.720
eteenth+0.664
ORK+0.632
glers+0.618
IGHTS+0.616
Neg logit contributions
 spoiler-0.514
 dilig-0.491
 spoilers-0.481
emale-0.475
adium-0.450
Token
Token ID447
Feature activation+2.39e-02

Pos logit contributions
+0.591
eteenth+0.545
ORK+0.512
glers+0.504
IGHTS+0.503
Neg logit contributions
 spoiler-0.489
 dilig-0.466
 spoilers-0.460
emale-0.451
adium-0.430
Token first
Token ID717
Feature activation+1.32e-01

Pos logit contributions
+0.091
eteenth+0.083
ORK+0.078
glers+0.076
IGHTS+0.076
Neg logit contributions
 spoiler-0.086
 dilig-0.082
 spoilers-0.081
emale-0.080
adium-0.076
Token commercial
Token ID5068
Feature activation+3.94e-01

Pos logit contributions
+0.408
eteenth+0.376
ORK+0.352
glers+0.348
IGHTS+0.345
Neg logit contributions
 spoiler-0.371
 dilig-0.356
 spoilers-0.350
emale-0.346
adium-0.330
Token test
Token ID1332
Feature activation+2.21e-01

Pos logit contributions
+1.166
eteenth+1.072
ORK+1.004
glers+0.998
IGHTS+0.986
Neg logit contributions
 spoiler-1.133
 dilig-1.099
 spoilers-1.068
emale-1.066
adium-1.016
Token for
Token ID329
Feature activation+1.71e-01

Pos logit contributions
+0.719
eteenth+0.666
ORK+0.631
glers+0.619
IGHTS+0.616
Neg logit contributions
 spoiler-0.582
 dilig-0.559
 spoilers-0.547
emale-0.539
adium-0.510
Token the
Token ID262
Feature activation+1.46e-01

Pos logit contributions
+0.474
eteenth+0.431
ORK+0.401
glers+0.395
IGHTS+0.391
Neg logit contributions
 spoiler-0.533
 dilig-0.513
 spoilers-0.505
emale-0.498
adium-0.478
Token Zika
Token ID30861
Feature activation+1.87e+00

Pos logit contributions
+0.411
eteenth+0.374
ORK+0.349
glers+0.341
IGHTS+0.340
Neg logit contributions
 spoiler-0.451
 dilig-0.433
 spoilers-0.428
emale-0.420
adium-0.404
Token virus
Token ID9471
Feature activation-9.70e-02

Pos logit contributions
+4.884
eteenth+4.408
ORK+4.188
glers+4.074
č+4.070
Neg logit contributions
 dilig-5.611
 spoiler-5.561
emale-5.502
 spoilers-5.295
 volunt-5.149
Token will
Token ID481
Feature activation+1.32e-02

Pos logit contributions
 spoiler+0.265
 dilig+0.250
 spoilers+0.249
emale+0.241
adium+0.232
Neg logit contributions
-0.311
eteenth-0.287
ORK-0.270
glers-0.264
IGHTS-0.264
Token become
Token ID1716
Feature activation+3.92e-01

Pos logit contributions
+0.042
eteenth+0.039
ORK+0.037
glers+0.036
IGHTS+0.036
Neg logit contributions
 spoiler-0.035
 dilig-0.034
 spoilers-0.033
emale-0.033
adium-0.031
Token available
Token ID1695
Feature activation+9.35e-02

Pos logit contributions
+1.311
eteenth+1.227
ORK+1.147
glers+1.133
IGHTS+1.132
Neg logit contributions
 spoiler-0.975
 dilig-0.933
emale-0.924
 spoilers-0.917
adium-0.866
Token to
Token ID284
Feature activation-1.57e-01

Pos logit contributions
+0.288
eteenth+0.265
ORK+0.248
glers+0.244
IGHTS+0.243
Neg logit contributions
 spoiler-0.264
 dilig-0.253
 spoilers-0.249
emale-0.245
adium-0.235
Token take
Token ID1011
Feature activation-5.52e-01

Pos logit contributions
 spoiler+0.305
 dilig+0.289
 spoilers+0.286
emale+0.279
adium+0.267
Neg logit contributions
-0.375
eteenth-0.346
ORK-0.326
glers-0.320
IGHTS-0.320
Token the
Token ID262
Feature activation-4.10e-02

Pos logit contributions
 spoiler+1.483
 dilig+1.404
 spoilers+1.394
emale+1.355
adium+1.301
Neg logit contributions
-1.794
eteenth-1.653
ORK-1.557
glers-1.527
IGHTS-1.524
Token reins
Token ID35627
Feature activation-7.57e-01

Pos logit contributions
 spoiler+0.120
 dilig+0.114
 spoilers+0.113
emale+0.110
adium+0.106
Neg logit contributions
-0.123
eteenth-0.113
ORK-0.106
glers-0.104
IGHTS-0.103
Token at
Token ID379
Feature activation-4.79e-01

Pos logit contributions
 spoiler+1.923
 dilig+1.802
 spoilers+1.788
emale+1.707
adium+1.649
Neg logit contributions
-2.586
eteenth-2.383
ORK-2.257
glers-2.211
IGHTS-2.209
Token the
Token ID262
Feature activation+1.17e-01

Pos logit contributions
 spoiler+1.249
 dilig+1.172
 spoilers+1.168
emale+1.126
adium+1.084
Neg logit contributions
-1.597
eteenth-1.473
ORK-1.386
IGHTS-1.361
glers-1.358
Token Commission
Token ID4513
Feature activation+1.86e+00

Pos logit contributions
+0.361
eteenth+0.332
ORK+0.311
glers+0.305
IGHTS+0.304
Neg logit contributions
 spoiler-0.334
 dilig-0.316
 spoilers-0.315
emale-0.305
adium-0.294
Token in
Token ID287
Feature activation-1.36e-01

Pos logit contributions
+5.292
eteenth+4.821
ORK+4.579
ters+4.453
č+4.393
Neg logit contributions
 spoiler-5.179
 dilig-5.095
emale-5.053
 spoilers-4.991
adium-4.860
Token her
Token ID607
Feature activation+3.51e-01

Pos logit contributions
 spoiler+0.381
 dilig+0.361
 spoilers+0.359
emale+0.348
adium+0.335
Neg logit contributions
-0.426
eteenth-0.391
ORK-0.367
glers-0.360
IGHTS-0.359
Token negotiations
Token ID9825
Feature activation+1.23e+00

Pos logit contributions
+1.045
eteenth+0.955
ORK+0.897
glers+0.876
IGHTS+0.873
Neg logit contributions
 spoiler-1.013
 dilig-0.975
 spoilers-0.961
emale-0.949
adium-0.914
Token with
Token ID351
Feature activation+3.55e-01

Pos logit contributions
+3.161
eteenth+2.823
ORK+2.672
ters+2.605
IGHTS+2.571
Neg logit contributions
 spoiler-3.921
 dilig-3.798
emale-3.789
 spoilers-3.762
adium-3.627
Token European
Token ID3427
Feature activation+3.27e-01

Pos logit contributions
+0.964
eteenth+0.879
ORK+0.824
glers+0.807
IGHTS+0.796
Neg logit contributions
 spoiler-1.116
 dilig-1.072
 spoilers-1.059
emale-1.055
adium-1.013
Token he
Token ID339
Feature activation-2.67e-02

Pos logit contributions
+0.806
eteenth+0.747
ORK+0.697
IGHTS+0.683
glers+0.683
Neg logit contributions
 spoiler-0.701
 dilig-0.670
 spoilers-0.662
emale-0.651
adium-0.623
Token grants
Token ID11455
Feature activation-2.49e-01

Pos logit contributions
 spoiler+0.070
 dilig+0.066
 spoilers+0.065
emale+0.064
adium+0.061
Neg logit contributions
-0.088
eteenth-0.082
ORK-0.077
glers-0.075
IGHTS-0.075
Token freedom
Token ID4925
Feature activation-8.58e-02

Pos logit contributions
 spoiler+0.705
 dilig+0.670
 spoilers+0.666
emale+0.648
adium+0.623
Neg logit contributions
-0.769
eteenth-0.706
ORK-0.663
glers-0.649
IGHTS-0.648
Token to
Token ID284
Feature activation-2.42e-01

Pos logit contributions
 spoiler+0.241
 dilig+0.230
 spoilers+0.226
emale+0.222
adium+0.214
Neg logit contributions
-0.266
eteenth-0.247
ORK-0.230
IGHTS-0.226
glers-0.225
Token a
Token ID257
Feature activation-4.28e-01

Pos logit contributions
 spoiler+0.725
 dilig+0.688
 spoilers+0.686
emale+0.667
 volunt+0.643
Neg logit contributions
-0.716
eteenth-0.650
ORK-0.610
glers-0.597
IGHTS-0.595
Token crou
Token ID33838
Feature activation+1.85e+00

Pos logit contributions
 spoiler+1.248
 dilig+1.179
 spoilers+1.172
emale+1.143
 volunt+1.102
Neg logit contributions
-1.300
eteenth-1.182
ORK-1.114
IGHTS-1.090
glers-1.087
Tokenching
Token ID10813
Feature activation+9.05e-01

Pos logit contributions
+3.265
eteenth+2.997
ters+2.613
glers+2.560
ORK+2.519
Neg logit contributions
 spoiler-7.399
 dilig-7.251
 spoilers-7.228
emale-6.945
 tremend-6.776
Token slave
Token ID11778
Feature activation+6.31e-01

Pos logit contributions
+2.519
eteenth+2.354
ORK+2.148
glers+2.129
IGHTS+2.098
Neg logit contributions
 spoiler-2.712
 dilig-2.661
 spoilers-2.599
emale-2.568
adium-2.486
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
+2.003
eteenth+1.887
ORK+1.739
glers+1.716
IGHTS+1.698
Neg logit contributions
 spoiler-1.693
 dilig-1.616
 spoilers-1.606
emale-1.553
adium-1.491
Token That
Token ID1320
Feature activation+5.47e-01

Pos logit contributions
+0.311
eteenth+0.285
ORK+0.268
glers+0.262
IGHTS+0.262
Neg logit contributions
 spoiler-0.282
 dilig-0.269
 spoilers-0.266
emale-0.260
adium-0.250
Token tens
Token ID11192
Feature activation+2.53e-02

Pos logit contributions
+1.746
eteenth+1.628
ORK+1.518
IGHTS+1.489
glers+1.486
Neg logit contributions
 spoiler-1.453
 dilig-1.405
 spoilers-1.372
emale-1.362
adium-1.298
Token that
Token ID326
Feature activation+1.38e-01

Pos logit contributions
+0.437
eteenth+0.402
ORK+0.379
glers+0.372
IGHTS+0.370
Neg logit contributions
 spoiler-0.383
 dilig-0.365
 spoilers-0.361
emale-0.355
adium-0.339
Token same
Token ID976
Feature activation+1.40e-02

Pos logit contributions
+0.470
eteenth+0.435
ORK+0.412
glers+0.404
IGHTS+0.403
Neg logit contributions
 spoiler-0.347
 dilig-0.330
 spoilers-0.326
emale-0.319
adium-0.304
Token mandate
Token ID14598
Feature activation-7.28e-01

Pos logit contributions
+0.045
eteenth+0.041
ORK+0.039
glers+0.038
IGHTS+0.038
Neg logit contributions
 spoiler-0.038
 dilig-0.036
 spoilers-0.036
emale-0.035
adium-0.033
Token has
Token ID468
Feature activation+2.52e-01

Pos logit contributions
 spoiler+1.820
 dilig+1.703
 spoilers+1.700
emale+1.633
adium+1.569
Neg logit contributions
-2.502
eteenth-2.320
ORK-2.198
IGHTS-2.147
glers-2.143
Token a
Token ID257
Feature activation+1.34e-01

Pos logit contributions
+0.773
eteenth+0.712
ORK+0.666
glers+0.655
IGHTS+0.650
Neg logit contributions
 spoiler-0.714
 dilig-0.682
 spoilers-0.675
emale-0.664
adium-0.635
Token loophole
Token ID35723
Feature activation+1.84e+00

Pos logit contributions
+0.417
eteenth+0.386
ORK+0.361
glers+0.355
IGHTS+0.352
Neg logit contributions
 spoiler-0.368
 dilig-0.354
 spoilers-0.351
emale-0.343
adium-0.329
Token that
Token ID326
Feature activation+3.65e-01

Pos logit contributions
+5.376
eteenth+4.949
ORK+4.588
glers+4.581
č+4.489
Neg logit contributions
 dilig-5.044
 spoiler-5.016
emale-4.846
 spoilers-4.819
 volunt-4.566
Token could
Token ID714
Feature activation+2.48e-01

Pos logit contributions
+1.208
eteenth+1.115
ORK+1.053
glers+1.049
IGHTS+1.037
Neg logit contributions
 spoiler-0.928
 dilig-0.891
 spoilers-0.869
emale-0.865
adium-0.824
Token guarantee
Token ID9149
Feature activation+1.62e-01

Pos logit contributions
+0.785
eteenth+0.722
ORK+0.679
glers+0.675
IGHTS+0.667
Neg logit contributions
 spoiler-0.666
 dilig-0.643
 spoilers-0.630
emale-0.623
adium-0.596
Token fossil
Token ID12584
Feature activation+6.66e-01

Pos logit contributions
+0.515
eteenth+0.475
ORK+0.447
glers+0.439
IGHTS+0.437
Neg logit contributions
 spoiler-0.438
 dilig-0.418
 spoilers-0.412
emale-0.407
adium-0.387
Token fuel
Token ID5252
Feature activation+6.49e-01

Pos logit contributions
+1.691
eteenth+1.510
ORK+1.388
IGHTS+1.375
glers+1.369
Neg logit contributions
 spoiler-2.195
 dilig-2.148
 spoilers-2.093
emale-2.085
 tremend-2.010
Tokenshi
Token ID44019
Feature activation-4.01e-01

Pos logit contributions
+0.164
eteenth+0.143
ORK+0.127
glers+0.122
IGHTS+0.122
Neg logit contributions
 spoiler-0.355
 dilig-0.344
 spoilers-0.341
emale-0.336
adium-0.326
Token was
Token ID373
Feature activation-3.51e-01

Pos logit contributions
 spoiler+1.106
 dilig+1.048
 spoilers+1.041
emale+1.011
adium+0.972
Neg logit contributions
-1.271
eteenth-1.169
ORK-1.101
glers-1.078
IGHTS-1.075
Token involved
Token ID2950
Feature activation+6.34e-01

Pos logit contributions
 spoiler+0.976
 dilig+0.919
 spoilers+0.917
emale+0.879
 volunt+0.852
Neg logit contributions
-1.119
eteenth-1.031
ORK-0.967
glers-0.947
IGHTS-0.942
Token in
Token ID287
Feature activation+1.41e-01

Pos logit contributions
+1.877
eteenth+1.705
ORK+1.598
glers+1.566
IGHTS+1.563
Neg logit contributions
 spoiler-1.851
 dilig-1.770
 spoilers-1.757
emale-1.747
adium-1.668
Token irregular
Token ID21388
Feature activation+9.33e-02

Pos logit contributions
+0.450
eteenth+0.414
ORK+0.390
glers+0.382
IGHTS+0.382
Neg logit contributions
 spoiler-0.384
 dilig-0.365
 spoilers-0.362
emale-0.355
adium-0.340
Token siph
Token ID44105
Feature activation+1.84e+00

Pos logit contributions
+0.309
eteenth+0.285
ORK+0.269
glers+0.264
IGHTS+0.264
Neg logit contributions
 spoiler-0.244
 dilig-0.231
 spoilers-0.229
emale-0.223
adium-0.213
Tokenoning
Token ID12484
Feature activation+4.20e-02

Pos logit contributions
+4.094
eteenth+3.787
glers+3.503
drops+3.409
mount+3.376
Neg logit contributions
 spoiler-6.325
 dilig-6.209
 spoilers-6.073
 tremend-6.063
emale-5.893
Token activities
Token ID4568
Feature activation+4.47e-03

Pos logit contributions
+0.139
eteenth+0.128
ORK+0.121
glers+0.119
IGHTS+0.119
Neg logit contributions
 spoiler-0.109
 dilig-0.103
 spoilers-0.102
emale-0.101
adium-0.096
Token,
Token ID11
Feature activation-8.74e-02

Pos logit contributions
+0.014
eteenth+0.013
ORK+0.012
glers+0.012
IGHTS+0.012
Neg logit contributions
 spoiler-0.013
 dilig-0.012
 spoilers-0.012
emale-0.012
adium-0.011
Token so
Token ID523
Feature activation+1.06e-01

Pos logit contributions
 spoiler+0.238
 dilig+0.225
 spoilers+0.224
emale+0.218
adium+0.209
Neg logit contributions
-0.280
eteenth-0.258
ORK-0.243
glers-0.238
IGHTS-0.238
Token they
Token ID484
Feature activation-4.48e-01

Pos logit contributions
+0.351
eteenth+0.323
ORK+0.306
glers+0.300
IGHTS+0.299
Neg logit contributions
 spoiler-0.276
 dilig-0.261
 spoilers-0.259
emale-0.254
adium-0.243
Token rigorous
Token ID22888
Feature activation+2.67e-01

Pos logit contributions
+2.105
eteenth+1.953
ORK+1.850
IGHTS+1.826
ters+1.806
Neg logit contributions
 spoiler-1.403
emale-1.356
 dilig-1.350
 spoilers-1.324
 volunt-1.270
Token testing
Token ID4856
Feature activation+3.90e-01

Pos logit contributions
+0.825
eteenth+0.754
ORK+0.704
IGHTS+0.693
glers+0.685
Neg logit contributions
 spoiler-0.736
 dilig-0.704
 spoilers-0.693
emale-0.692
 tremend-0.658
Token to
Token ID284
Feature activation-1.08e-01

Pos logit contributions
+1.177
eteenth+1.075
ORK+1.016
IGHTS+0.987
glers+0.986
Neg logit contributions
 spoiler-1.115
 dilig-1.067
 spoilers-1.058
emale-1.046
 volunt-0.991
Token meet
Token ID1826
Feature activation-8.07e-03

Pos logit contributions
 spoiler+0.295
 dilig+0.281
 spoilers+0.278
emale+0.272
adium+0.260
Neg logit contributions
-0.342
eteenth-0.315
ORK-0.297
glers-0.291
IGHTS-0.291
Token MIL
Token ID31515
Feature activation+8.96e-01

Pos logit contributions
 spoiler+0.021
 dilig+0.020
 spoilers+0.020
emale+0.020
adium+0.019
Neg logit contributions
-0.027
eteenth-0.024
ORK-0.023
IGHTS-0.023
glers-0.023
TokenSTD
Token ID32147
Feature activation+1.82e+00

Pos logit contributions
+2.309
eteenth+2.089
ORK+1.952
IGHTS+1.925
INS+1.828
Neg logit contributions
 spoiler-2.920
 dilig-2.859
emale-2.766
 spoilers-2.763
 tremend-2.720
Token810
Token ID40215
Feature activation+8.92e-02

Pos logit contributions
+4.578
eteenth+4.074
ORK+3.779
IGHTS+3.708
mount+3.625
Neg logit contributions
 spoiler-5.895
 dilig-5.801
emale-5.613
 tremend-5.593
 spoilers-5.590
TokenG
Token ID38
Feature activation+8.66e-01

Pos logit contributions
+0.255
eteenth+0.229
ORK+0.217
IGHTS+0.210
glers+0.209
Neg logit contributions
 spoiler-0.273
 dilig-0.260
 spoilers-0.258
emale-0.257
 tremend-0.245
Token standards
Token ID5423
Feature activation-3.90e-02

Pos logit contributions
+2.612
eteenth+2.354
ORK+2.234
IGHTS+2.185
glers+2.151
Neg logit contributions
 spoiler-2.458
 dilig-2.348
 spoilers-2.307
emale-2.301
 volunt-2.212
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
 spoiler+0.107
 dilig+0.101
 spoilers+0.101
emale+0.098
 volunt+0.094
Neg logit contributions
-0.124
eteenth-0.114
ORK-0.108
glers-0.105
IGHTS-0.105
Token guaranteeing
Token ID50156
Feature activation-3.88e-01

Pos logit contributions
+0.523
eteenth+0.476
ORK+0.449
IGHTS+0.439
glers+0.437
Neg logit contributions
 spoiler-0.516
 dilig-0.492
 spoilers-0.488
emale-0.480
 volunt-0.459
Token pil
Token ID5560
Feature activation+8.54e-03

Pos logit contributions
 spoiler+2.779
 dilig+2.637
 spoilers+2.626
emale+2.550
 volunt+2.468
Neg logit contributions
-2.963
eteenth-2.721
ORK-2.568
glers-2.526
IGHTS-2.511
Tokenina
Token ID1437
Feature activation+6.23e-01

Pos logit contributions
+0.025
eteenth+0.023
ORK+0.022
glers+0.021
IGHTS+0.021
Neg logit contributions
 spoiler-0.025
 dilig-0.024
 spoilers-0.024
emale-0.023
adium-0.022
Token
Token ID220
Feature activation+2.57e-02

Pos logit contributions
+1.936
eteenth+1.776
ORK+1.656
IGHTS+1.615
glers+1.606
Neg logit contributions
 spoiler-1.747
 dilig-1.665
 spoilers-1.645
emale-1.607
adium-1.547
Token
Token ID134
Feature activation+5.37e-01

Pos logit contributions
+0.070
eteenth+0.064
ORK+0.059
glers+0.058
IGHTS+0.058
Neg logit contributions
 spoiler-0.083
 dilig-0.079
 spoilers-0.079
emale-0.077
adium-0.074
Token
Token ID119
Feature activation+3.74e-01

Pos logit contributions
+0.834
eteenth+0.700
ORK+0.584
glers+0.573
IGHTS+0.563
Neg logit contributions
 spoiler-2.359
 dilig-2.279
 spoilers-2.276
emale-2.234
adium-2.179
Tokenā
Token ID10235
Feature activation+1.81e+00

Pos logit contributions
+1.156
eteenth+1.066
ORK+0.992
glers+0.973
IGHTS+0.970
Neg logit contributions
 spoiler-1.060
 dilig-1.011
 spoilers-1.003
emale-0.965
 volunt-0.929
Tokenina
Token ID1437
Feature activation+6.58e-01

Pos logit contributions
+4.992
eteenth+4.484
ORK+4.102
č+4.100
glers+4.093
Neg logit contributions
 spoiler-5.513
 dilig-5.287
 spoilers-5.259
emale-5.062
adium-4.927
Token a
Token ID257
Feature activation+3.77e-02

Pos logit contributions
+2.043
eteenth+1.866
ORK+1.741
IGHTS+1.703
glers+1.692
Neg logit contributions
 spoiler-1.839
 dilig-1.756
 spoilers-1.731
emale-1.698
adium-1.637
Token
Token ID220
Feature activation+4.42e-02

Pos logit contributions
+0.120
eteenth+0.111
ORK+0.104
glers+0.102
IGHTS+0.102
Neg logit contributions
 spoiler-0.103
 dilig-0.098
 spoilers-0.097
emale-0.094
adium-0.091
Token
Token ID134
Feature activation+6.64e-01

Pos logit contributions
+0.121
eteenth+0.110
ORK+0.102
glers+0.100
IGHTS+0.100
Neg logit contributions
 spoiler-0.141
 dilig-0.135
 spoilers-0.134
emale-0.131
adium-0.127
Token
Token ID119
Feature activation+2.77e-01

Pos logit contributions
+1.007
eteenth+0.846
ORK+0.697
glers+0.685
IGHTS+0.673
Neg logit contributions
 spoiler-2.936
 dilig-2.838
 spoilers-2.835
emale-2.781
adium-2.713
Token.
Token ID13
Feature activation+8.70e-03

Pos logit contributions
+1.910
eteenth+1.749
ORK+1.630
glers+1.613
IGHTS+1.603
Neg logit contributions
 spoiler-1.690
 dilig-1.622
 spoilers-1.601
emale-1.580
adium-1.512
Token
Token ID564
Feature activation+1.91e-02

Pos logit contributions
+0.027
eteenth+0.025
ORK+0.024
glers+0.023
IGHTS+0.023
Neg logit contributions
 spoiler-0.024
 dilig-0.023
 spoilers-0.023
emale-0.022
adium-0.021
Token
Token ID250
Feature activation-1.50e-01

Pos logit contributions
+0.052
eteenth+0.047
ORK+0.043
glers+0.042
IGHTS+0.042
Neg logit contributions
 spoiler-0.062
 dilig-0.059
 spoilers-0.059
emale-0.058
adium-0.055
TokenThe
Token ID464
Feature activation+1.04e-01

Pos logit contributions
 spoiler+0.457
 dilig+0.434
 spoilers+0.432
emale+0.422
adium+0.407
Neg logit contributions
-0.434
eteenth-0.397
ORK-0.370
glers-0.362
IGHTS-0.361
Token one
Token ID530
Feature activation+4.84e-02

Pos logit contributions
+0.328
eteenth+0.301
ORK+0.284
glers+0.278
IGHTS+0.277
Neg logit contributions
 spoiler-0.286
 dilig-0.273
 spoilers-0.270
emale-0.264
adium-0.253
Token kilomet
Token ID11866
Feature activation+1.81e+00

Pos logit contributions
+0.156
eteenth+0.144
ORK+0.135
glers+0.133
IGHTS+0.132
Neg logit contributions
 spoiler-0.130
 dilig-0.124
 spoilers-0.123
emale-0.121
adium-0.115
Tokenre
Token ID260
Feature activation+1.11e+00

Pos logit contributions
+4.566
eteenth+4.323
ORK+3.827
ters+3.794
glers+3.784
Neg logit contributions
 dilig-5.730
 spoiler-5.721
 spoilers-5.496
emale-5.431
 tremend-5.355
Token to
Token ID284
Feature activation+3.92e-01

Pos logit contributions
+3.364
eteenth+3.068
ORK+2.933
glers+2.891
IGHTS+2.828
Neg logit contributions
 spoiler-2.996
emale-2.969
 dilig-2.961
 spoilers-2.859
adium-2.793
Token go
Token ID467
Feature activation-5.82e-01

Pos logit contributions
+1.246
eteenth+1.144
ORK+1.081
glers+1.061
IGHTS+1.052
Neg logit contributions
 spoiler-1.065
 dilig-1.014
 spoilers-1.008
emale-0.993
adium-0.946
Token mark
Token ID1317
Feature activation-1.17e-02

Pos logit contributions
 spoiler+1.599
 dilig+1.504
 spoilers+1.499
emale+1.437
adium+1.398
Neg logit contributions
-1.863
eteenth-1.717
ORK-1.610
IGHTS-1.580
glers-1.573
Token was
Token ID373
Feature activation+1.31e-01

Pos logit contributions
 spoiler+0.033
 dilig+0.031
 spoilers+0.031
emale+0.030
adium+0.029
Neg logit contributions
-0.036
eteenth-0.033
ORK-0.031
glers-0.031
IGHTS-0.031
Token cold
Token ID4692
Feature activation-7.26e-02

Pos logit contributions
+0.645
eteenth+0.591
ORK+0.557
glers+0.546
IGHTS+0.544
Neg logit contributions
 spoiler-0.600
 dilig-0.574
 spoilers-0.567
emale-0.557
adium-0.532
Tokenest
Token ID395
Feature activation+9.09e-03

Pos logit contributions
 spoiler+0.208
 dilig+0.198
 spoilers+0.196
emale+0.191
adium+0.184
Neg logit contributions
-0.223
eteenth-0.204
ORK-0.192
glers-0.188
IGHTS-0.187
Token gym
Token ID11550
Feature activation+7.78e-01

Pos logit contributions
+0.029
eteenth+0.027
ORK+0.025
glers+0.024
IGHTS+0.024
Neg logit contributions
 spoiler-0.025
 dilig-0.024
 spoilers-0.024
emale-0.023
adium-0.022
Token I
Token ID314
Feature activation+1.28e-01

Pos logit contributions
+2.302
eteenth+2.105
ORK+1.989
glers+1.955
ters+1.937
Neg logit contributions
 spoiler-2.237
 dilig-2.180
emale-2.131
 spoilers-2.126
 volunt-1.989
Token have
Token ID423
Feature activation-4.95e-01

Pos logit contributions
+0.421
eteenth+0.388
ORK+0.366
IGHTS+0.360
glers+0.360
Neg logit contributions
 spoiler-0.335
 dilig-0.318
 spoilers-0.315
emale-0.308
adium-0.293
Token known
Token ID1900
Feature activation-2.14e+00

Pos logit contributions
 spoiler+1.521
 dilig+1.451
 spoilers+1.443
emale+1.402
adium+1.357
Neg logit contributions
-1.410
eteenth-1.288
ORK-1.200
glers-1.175
IGHTS-1.171
Token,
Token ID11
Feature activation-6.39e-02

Pos logit contributions
 spoiler+5.250
 spoilers+4.876
 dilig+4.846
emale+4.548
 lockout+4.540
Neg logit contributions
-7.142
eteenth-6.693
glers-6.236
ORK-6.177
IGHTS-6.167
Token more
Token ID517
Feature activation-3.62e-01

Pos logit contributions
 spoiler+0.177
 dilig+0.168
 spoilers+0.167
emale+0.163
adium+0.156
Neg logit contributions
-0.202
eteenth-0.186
ORK-0.175
glers-0.171
IGHTS-0.171
Token like
Token ID588
Feature activation-5.33e-01

Pos logit contributions
 spoiler+0.924
 dilig+0.873
 spoilers+0.866
emale+0.838
adium+0.804
Neg logit contributions
-1.220
eteenth-1.129
ORK-1.066
glers-1.046
IGHTS-1.044
Token a
Token ID257
Feature activation-1.32e-01

Pos logit contributions
 spoiler+1.446
 dilig+1.367
 spoilers+1.361
emale+1.311
adium+1.268
Neg logit contributions
-1.712
eteenth-1.583
ORK-1.486
glers-1.457
IGHTS-1.455
Token freezer
Token ID30967
Feature activation+2.09e-01

Pos logit contributions
 spoiler+0.372
 dilig+0.354
 spoilers+0.351
emale+0.344
adium+0.330
Neg logit contributions
-0.407
eteenth-0.374
ORK-0.351
glers-0.344
IGHTS-0.343
Token platform
Token ID3859
Feature activation-3.11e-01

Pos logit contributions
 spoiler+1.020
 dilig+0.966
 spoilers+0.960
emale+0.934
adium+0.897
Neg logit contributions
-1.184
eteenth-1.090
ORK-1.026
glers-1.004
IGHTS-1.003
Tokener
Token ID263
Feature activation-6.50e-01

Pos logit contributions
 spoiler+0.840
 dilig+0.798
 spoilers+0.791
emale+0.771
adium+0.739
Neg logit contributions
-1.002
eteenth-0.923
ORK-0.870
glers-0.853
IGHTS-0.851
Token on
Token ID319
Feature activation-1.30e-01

Pos logit contributions
 spoiler+1.736
 dilig+1.625
 spoilers+1.624
emale+1.573
adium+1.518
Neg logit contributions
-2.123
eteenth-1.965
ORK-1.848
IGHTS-1.810
glers-1.803
Token Xbox
Token ID9445
Feature activation-6.11e-01

Pos logit contributions
 spoiler+0.349
 dilig+0.334
 spoilers+0.329
emale+0.324
adium+0.309
Neg logit contributions
-0.422
eteenth-0.386
ORK-0.364
glers-0.359
IGHTS-0.358
Token Live
Token ID7547
Feature activation-7.37e-01

Pos logit contributions
 spoiler+1.740
 dilig+1.655
 spoilers+1.643
emale+1.603
adium+1.541
Neg logit contributions
-1.877
eteenth-1.726
ORK-1.618
glers-1.584
IGHTS-1.576
Token Indie
Token ID31527
Feature activation-2.12e+00

Pos logit contributions
 spoiler+1.890
 dilig+1.772
 spoilers+1.771
emale+1.718
adium+1.656
Neg logit contributions
-2.472
eteenth-2.294
ORK-2.162
glers-2.127
IGHTS-2.111
Token Games
Token ID5776
Feature activation-5.92e-02

Pos logit contributions
 spoiler+5.617
 spoilers+5.249
 dilig+5.232
emale+5.125
adium+4.987
Neg logit contributions
-6.673
eteenth-6.218
ORK-5.821
IGHTS-5.699
glers-5.661
Token.
Token ID13
Feature activation-4.15e-01

Pos logit contributions
 spoiler+0.159
 dilig+0.152
 spoilers+0.150
emale+0.146
adium+0.139
Neg logit contributions
-0.192
eteenth-0.176
ORK-0.166
IGHTS-0.163
glers-0.163
Token Needs
Token ID36557
Feature activation-9.62e-01

Pos logit contributions
 spoiler+1.157
 spoilers+1.090
 dilig+1.089
emale+1.057
adium+1.021
Neg logit contributions
-1.301
eteenth-1.200
ORK-1.124
glers-1.102
IGHTS-1.097
Token to
Token ID284
Feature activation-4.51e-01

Pos logit contributions
 spoiler+2.631
 spoilers+2.483
 dilig+2.470
emale+2.363
adium+2.292
Neg logit contributions
-3.080
eteenth-2.854
ORK-2.675
glers-2.611
IGHTS-2.610
Token be
Token ID307
Feature activation-4.65e-01

Pos logit contributions
 spoiler+1.193
 dilig+1.124
 spoilers+1.119
emale+1.084
adium+1.040
Neg logit contributions
-1.488
eteenth-1.376
ORK-1.296
IGHTS-1.267
glers-1.267
Token even
Token ID772
Feature activation-7.48e-01

Pos logit contributions
 spoiler+0.374
 dilig+0.355
 spoilers+0.352
emale+0.343
adium+0.329
Neg logit contributions
-0.434
eteenth-0.400
ORK-0.376
glers-0.369
IGHTS-0.368
Token without
Token ID1231
Feature activation+3.29e-01

Pos logit contributions
 spoiler+2.012
 dilig+1.894
 spoilers+1.887
emale+1.805
adium+1.749
Neg logit contributions
-2.436
eteenth-2.242
ORK-2.113
IGHTS-2.069
glers-2.067
Token AA
Token ID15923
Feature activation+2.94e-01

Pos logit contributions
+1.029
eteenth+0.942
ORK+0.891
IGHTS+0.872
glers+0.872
Neg logit contributions
 spoiler-0.901
 dilig-0.861
emale-0.849
 spoilers-0.846
adium-0.805
Token (
Token ID357
Feature activation-5.71e-02

Pos logit contributions
+0.926
eteenth+0.850
ORK+0.802
IGHTS+0.785
glers+0.785
Neg logit contributions
 spoiler-0.808
 dilig-0.772
 spoilers-0.762
emale-0.749
adium-0.718
TokenI
Token ID40
Feature activation-3.74e-02

Pos logit contributions
 spoiler+0.171
 dilig+0.162
 spoilers+0.161
emale+0.157
adium+0.152
Neg logit contributions
-0.168
eteenth-0.154
ORK-0.144
glers-0.141
IGHTS-0.140
Token dunno
Token ID50109
Feature activation-2.09e+00

Pos logit contributions
 spoiler+0.097
 dilig+0.091
 spoilers+0.091
emale+0.088
adium+0.085
Neg logit contributions
-0.125
eteenth-0.115
ORK-0.109
glers-0.107
IGHTS-0.106
Token an
Token ID281
Feature activation-1.52e-01

Pos logit contributions
 spoiler+5.133
 spoilers+4.816
 dilig+4.675
emale+4.368
 volunt+4.284
Neg logit contributions
-7.191
eteenth-6.663
ORK-6.316
IGHTS-6.191
glers-6.127
Token 8
Token ID807
Feature activation+5.98e-02

Pos logit contributions
 spoiler+0.431
 dilig+0.408
 spoilers+0.407
emale+0.395
adium+0.381
Neg logit contributions
-0.472
eteenth-0.434
ORK-0.408
glers-0.400
IGHTS-0.399
Tokenk
Token ID74
Feature activation-2.20e-01

Pos logit contributions
+0.154
eteenth+0.138
ORK+0.128
glers+0.125
IGHTS+0.124
Neg logit contributions
 spoiler-0.201
 dilig-0.193
 spoilers-0.191
emale-0.188
 volunt-0.181
Token or
Token ID393
Feature activation+1.48e-01

Pos logit contributions
 spoiler+0.637
 dilig+0.605
 spoilers+0.601
emale+0.586
adium+0.565
Neg logit contributions
-0.666
eteenth-0.611
ORK-0.573
glers-0.561
IGHTS-0.560
Token 16
Token ID1467
Feature activation+4.99e-01

Pos logit contributions
+0.460
eteenth+0.422
ORK+0.396
glers+0.388
IGHTS+0.388
Neg logit contributions
 spoiler-0.412
 dilig-0.393
 spoilers-0.389
emale-0.382
adium-0.365
Token the
Token ID262
Feature activation-2.41e-01

Pos logit contributions
+1.769
eteenth+1.640
ORK+1.525
IGHTS+1.492
glers+1.481
Neg logit contributions
 spoiler-1.582
 spoilers-1.493
 dilig-1.491
emale-1.453
adium-1.394
Token California
Token ID3442
Feature activation+4.03e-01

Pos logit contributions
 spoiler+0.704
 dilig+0.672
 spoilers+0.666
emale+0.652
adium+0.628
Neg logit contributions
-0.721
eteenth-0.660
ORK-0.617
glers-0.604
IGHTS-0.604
Token High
Token ID3334
Feature activation-3.75e-03

Pos logit contributions
+1.263
eteenth+1.170
ORK+1.100
IGHTS+1.076
glers+1.065
Neg logit contributions
 spoiler-1.107
 dilig-1.055
 spoilers-1.039
emale-1.028
 tremend-0.981
Token School
Token ID3961
Feature activation-2.38e-01

Pos logit contributions
 spoiler+0.010
 dilig+0.009
 spoilers+0.009
emale+0.009
adium+0.008
Neg logit contributions
-0.013
eteenth-0.012
ORK-0.011
glers-0.011
IGHTS-0.011
Token Exit
Token ID29739
Feature activation-1.06e+00

Pos logit contributions
 spoiler+0.647
 dilig+0.615
 spoilers+0.609
emale+0.597
adium+0.571
Neg logit contributions
-0.761
eteenth-0.700
ORK-0.658
glers-0.646
IGHTS-0.644
Token Exam
Token ID35909
Feature activation-2.05e+00

Pos logit contributions
 spoiler+2.989
 dilig+2.838
 spoilers+2.818
emale+2.744
adium+2.641
Neg logit contributions
-3.268
eteenth-3.000
ORK-2.820
glers-2.759
IGHTS-2.758
Token since
Token ID1201
Feature activation-5.83e-01

Pos logit contributions
 spoiler+5.315
 spoilers+4.896
 dilig+4.887
emale+4.665
 volunt+4.603
Neg logit contributions
-6.733
eteenth-6.167
ORK-5.846
IGHTS-5.661
glers-5.627
Token its
Token ID663
Feature activation+3.02e-01

Pos logit contributions
 spoiler+1.681
 dilig+1.595
 spoilers+1.591
emale+1.538
adium+1.485
Neg logit contributions
-1.782
eteenth-1.634
ORK-1.531
glers-1.498
IGHTS-1.497
Token 2006
Token ID4793
Feature activation+4.57e-01

Pos logit contributions
+0.897
eteenth+0.827
ORK+0.772
glers+0.755
IGHTS+0.753
Neg logit contributions
 spoiler-0.869
 dilig-0.839
 spoilers-0.822
emale-0.815
adium-0.785
Token debut
Token ID8886
Feature activation-3.17e-01

Pos logit contributions
+1.502
eteenth+1.389
ORK+1.308
glers+1.289
IGHTS+1.270
Neg logit contributions
 spoiler-1.171
 dilig-1.126
 spoilers-1.099
emale-1.081
adium-1.037
Token would
Token ID561
Feature activation+3.13e-01

Pos logit contributions
 spoiler+0.847
 dilig+0.805
 spoilers+0.797
emale+0.777
adium+0.745
Neg logit contributions
-1.028
eteenth-0.949
ORK-0.892
glers-0.877
IGHTS-0.875
Token to
Token ID284
Feature activation-2.18e-01

Pos logit contributions
 spoiler+2.314
 dilig+2.178
 spoilers+2.170
emale+2.092
adium+2.033
Neg logit contributions
-2.631
eteenth-2.420
ORK-2.275
IGHTS-2.224
glers-2.220
Token a
Token ID257
Feature activation-2.77e-01

Pos logit contributions
 spoiler+0.627
 dilig+0.601
 spoilers+0.594
emale+0.583
adium+0.557
Neg logit contributions
-0.659
eteenth-0.604
ORK-0.567
glers-0.554
IGHTS-0.553
Token Jud
Token ID4794
Feature activation-2.63e-01

Pos logit contributions
 spoiler+0.753
 dilig+0.721
 spoilers+0.712
emale+0.699
adium+0.664
Neg logit contributions
-0.877
eteenth-0.812
ORK-0.763
glers-0.753
IGHTS-0.747
Tokenas
Token ID292
Feature activation+8.53e-01

Pos logit contributions
 spoiler+0.741
 dilig+0.713
 spoilers+0.701
emale+0.684
 volunt+0.656
Neg logit contributions
-0.808
eteenth-0.754
ORK-0.700
glers-0.695
IGHTS-0.689
Token Priest
Token ID20876
Feature activation+4.55e-02

Pos logit contributions
+2.543
eteenth+2.402
ORK+2.190
IGHTS+2.159
č+2.149
Neg logit contributions
 spoiler-2.409
 dilig-2.315
 spoilers-2.262
emale-2.234
adium-2.133
Token concert
Token ID10010
Feature activation-1.98e+00

Pos logit contributions
+0.158
eteenth+0.148
ORK+0.139
IGHTS+0.138
glers+0.137
Neg logit contributions
 spoiler-0.109
 dilig-0.104
 spoilers-0.102
emale-0.101
adium-0.094
Token in
Token ID287
Feature activation-3.59e-01

Pos logit contributions
 spoiler+5.118
 spoilers+4.740
 dilig+4.681
emale+4.455
adium+4.452
Neg logit contributions
-6.577
eteenth-6.032
ORK-5.690
glers-5.552
IGHTS-5.547
Token Land
Token ID6379
Feature activation-4.72e-02

Pos logit contributions
 spoiler+1.142
 dilig+1.090
 spoilers+1.084
emale+1.059
adium+1.024
Neg logit contributions
-0.987
eteenth-0.897
ORK-0.834
glers-0.815
IGHTS-0.813
Tokenover
Token ID2502
Feature activation+2.74e-01

Pos logit contributions
 spoiler+0.121
 dilig+0.116
 spoilers+0.114
emale+0.111
 volunt+0.106
Neg logit contributions
-0.157
eteenth-0.147
ORK-0.138
glers-0.135
IGHTS-0.134
Token,
Token ID11
Feature activation+1.38e-01

Pos logit contributions
+0.840
eteenth+0.772
ORK+0.724
IGHTS+0.713
glers+0.704
Neg logit contributions
 spoiler-0.773
 dilig-0.743
 spoilers-0.731
emale-0.722
adium-0.686
Token Maryland
Token ID10769
Feature activation-2.88e-01

Pos logit contributions
+0.330
eteenth+0.295
ORK+0.272
IGHTS+0.266
glers+0.264
Neg logit contributions
 spoiler-0.485
 dilig-0.468
 spoilers-0.464
emale-0.459
adium-0.442
Token held
Token ID2714
Feature activation-6.45e-01

Pos logit contributions
 spoiler+1.699
 dilig+1.565
 spoilers+1.556
emale+1.462
 volunt+1.415
Neg logit contributions
-3.418
eteenth-3.195
ORK-3.053
glers-3.004
IGHTS-2.980
Token Wednesday
Token ID3583
Feature activation-9.02e-01

Pos logit contributions
 spoiler+1.829
 dilig+1.727
 spoilers+1.718
emale+1.662
adium+1.610
Neg logit contributions
-2.001
eteenth-1.835
ORK-1.726
glers-1.684
IGHTS-1.681
Token on
Token ID319
Feature activation+1.78e-02

Pos logit contributions
 spoiler+2.580
 dilig+2.438
 spoilers+2.425
emale+2.332
 volunt+2.282
Neg logit contributions
-2.769
eteenth-2.521
ORK-2.391
IGHTS-2.325
glers-2.317
Token $
Token ID720
Feature activation-1.19e-01

Pos logit contributions
+0.057
eteenth+0.053
ORK+0.050
glers+0.049
IGHTS+0.049
Neg logit contributions
 spoiler-0.048
 dilig-0.046
 spoilers-0.045
emale-0.045
adium-0.042
Token500
Token ID4059
Feature activation-2.56e-01

Pos logit contributions
 spoiler+0.409
 spoilers+0.390
 dilig+0.388
emale+0.381
adium+0.372
Neg logit contributions
-0.295
eteenth-0.267
ORK-0.244
glers-0.239
IGHTS-0.237
Token bond
Token ID6314
Feature activation-1.98e+00

Pos logit contributions
 spoiler+0.699
 dilig+0.664
 spoilers+0.658
emale+0.648
adium+0.616
Neg logit contributions
-0.819
eteenth-0.753
ORK-0.709
IGHTS-0.694
glers-0.694
Token,
Token ID11
Feature activation-1.03e-01

Pos logit contributions
 spoiler+4.651
 dilig+4.289
 spoilers+4.257
adium+4.011
 volunt+4.007
Neg logit contributions
-6.870
eteenth-6.340
ORK-5.985
IGHTS-5.888
glers-5.839
Token and
Token ID290
Feature activation-7.73e-02

Pos logit contributions
 spoiler+0.280
 dilig+0.269
 spoilers+0.264
emale+0.261
adium+0.249
Neg logit contributions
-0.326
eteenth-0.300
ORK-0.283
glers-0.279
IGHTS-0.277
Token it
Token ID340
Feature activation-2.24e-01

Pos logit contributions
 spoiler+0.200
 dilig+0.191
 spoilers+0.188
emale+0.186
adium+0.178
Neg logit contributions
-0.256
eteenth-0.236
ORK-0.223
glers-0.220
IGHTS-0.219
Token was
Token ID373
Feature activation-3.35e-01

Pos logit contributions
 spoiler+0.636
 dilig+0.610
 spoilers+0.601
emale+0.593
adium+0.566
Neg logit contributions
-0.686
eteenth-0.630
ORK-0.588
glers-0.581
IGHTS-0.578
Token unknown
Token ID6439
Feature activation-9.46e-01

Pos logit contributions
 spoiler+0.961
 dilig+0.915
 spoilers+0.907
emale+0.886
adium+0.852
Neg logit contributions
-1.024
eteenth-0.939
ORK-0.881
glers-0.862
IGHTS-0.861
Tokenarin
Token ID17714
Feature activation+1.70e-01

Pos logit contributions
 spoiler+0.256
 dilig+0.245
 spoilers+0.242
emale+0.236
 volunt+0.226
Neg logit contributions
-0.256
eteenth-0.236
ORK-0.220
IGHTS-0.216
glers-0.214
Token gas
Token ID3623
Feature activation-1.11e-01

Pos logit contributions
+0.439
eteenth+0.392
ORK+0.360
IGHTS+0.354
glers+0.347
Neg logit contributions
 spoiler-0.561
 dilig-0.547
 spoilers-0.534
emale-0.534
 volunt-0.510
Token in
Token ID287
Feature activation-1.63e-01

Pos logit contributions
 spoiler+0.288
 dilig+0.274
 spoilers+0.271
emale+0.265
adium+0.252
Neg logit contributions
-0.368
eteenth-0.340
ORK-0.320
IGHTS-0.315
glers-0.314
Token a
Token ID257
Feature activation-2.15e-01

Pos logit contributions
 spoiler+0.467
 dilig+0.446
 spoilers+0.441
emale+0.432
adium+0.415
Neg logit contributions
-0.498
eteenth-0.456
ORK-0.428
glers-0.419
IGHTS-0.419
Token Tokyo
Token ID11790
Feature activation-7.33e-02

Pos logit contributions
 spoiler+0.611
 dilig+0.582
 spoilers+0.577
emale+0.563
adium+0.542
Neg logit contributions
-0.660
eteenth-0.606
ORK-0.568
glers-0.557
IGHTS-0.556
Token subway
Token ID19612
Feature activation-1.97e+00

Pos logit contributions
 spoiler+0.198
 dilig+0.189
 spoilers+0.187
emale+0.183
adium+0.175
Neg logit contributions
-0.234
eteenth-0.216
ORK-0.202
IGHTS-0.199
glers-0.198
Token,
Token ID11
Feature activation+1.14e-01

Pos logit contributions
 spoiler+4.974
 spoilers+4.616
 dilig+4.539
emale+4.251
 lockout+4.236
Neg logit contributions
-6.705
eteenth-6.230
ORK-5.883
glers-5.855
IGHTS-5.709
Token killing
Token ID5170
Feature activation-1.71e-01

Pos logit contributions
+0.323
eteenth+0.294
ORK+0.274
IGHTS+0.268
glers+0.268
Neg logit contributions
 spoiler-0.349
 dilig-0.334
 spoilers-0.331
emale-0.325
adium-0.313
Token 12
Token ID1105
Feature activation+1.53e-01

Pos logit contributions
 spoiler+0.517
 dilig+0.493
 spoilers+0.490
emale+0.478
adium+0.461
Neg logit contributions
-0.498
eteenth-0.455
ORK-0.425
glers-0.416
IGHTS-0.415
Token people
Token ID661
Feature activation-6.01e-01

Pos logit contributions
+0.506
eteenth+0.467
ORK+0.441
IGHTS+0.431
glers+0.430
Neg logit contributions
 spoiler-0.401
 dilig-0.380
 spoilers-0.375
emale-0.368
adium-0.354
Token and
Token ID290
Feature activation-4.53e-01

Pos logit contributions
 spoiler+1.574
 dilig+1.487
 spoilers+1.477
emale+1.426
adium+1.372
Neg logit contributions
-1.989
eteenth-1.836
ORK-1.733
glers-1.701
IGHTS-1.692
Token figure
Token ID3785
Feature activation+2.68e-01

Pos logit contributions
 spoiler+0.435
 dilig+0.414
 spoilers+0.410
emale+0.399
adium+0.383
Neg logit contributions
-0.529
eteenth-0.487
ORK-0.459
glers-0.451
IGHTS-0.450
Token than
Token ID621
Feature activation+4.83e-01

Pos logit contributions
+0.927
eteenth+0.852
ORK+0.801
glers+0.792
IGHTS+0.788
Neg logit contributions
 spoiler-0.661
 dilig-0.636
 spoilers-0.622
emale-0.611
adium-0.582
Token His
Token ID2399
Feature activation+2.69e-01

Pos logit contributions
+1.477
eteenth+1.348
ORK+1.267
glers+1.242
IGHTS+1.233
Neg logit contributions
 spoiler-1.352
 dilig-1.316
 spoilers-1.286
emale-1.270
adium-1.224
Token Majesty
Token ID25788
Feature activation-1.16e+00

Pos logit contributions
+0.723
eteenth+0.655
ORK+0.608
glers+0.594
IGHTS+0.593
Neg logit contributions
 spoiler-0.869
 dilig-0.831
 spoilers-0.826
emale-0.808
adium-0.781
Token King
Token ID2677
Feature activation-8.71e-01

Pos logit contributions
 spoiler+2.994
 dilig+2.816
 spoilers+2.809
emale+2.710
adium+2.593
Neg logit contributions
-3.895
eteenth-3.592
ORK-3.387
glers-3.341
IGHTS-3.319
Token Carl
Token ID8124
Feature activation-1.94e+00

Pos logit contributions
 spoiler+2.267
 dilig+2.147
 spoilers+2.128
emale+2.071
adium+1.982
Neg logit contributions
-2.895
eteenth-2.676
ORK-2.523
glers-2.475
IGHTS-2.471
Token XVI
Token ID49090
Feature activation-1.35e-01

Pos logit contributions
 spoiler+3.994
 spoilers+3.682
 dilig+3.675
emale+3.514
adium+3.373
Neg logit contributions
-7.441
eteenth-6.944
ORK-6.611
glers-6.547
IGHTS-6.487
Token Gust
Token ID26657
Feature activation-7.64e-01

Pos logit contributions
 spoiler+0.463
 dilig+0.445
 spoilers+0.442
emale+0.431
adium+0.417
Neg logit contributions
-0.337
eteenth-0.303
ORK-0.281
glers-0.272
IGHTS-0.271
Tokenaf
Token ID1878
Feature activation+6.96e-01

Pos logit contributions
 spoiler+1.801
 dilig+1.693
 spoilers+1.677
emale+1.624
 volunt+1.537
Neg logit contributions
-2.732
eteenth-2.544
ORK-2.408
glers-2.366
IGHTS-2.362
Token himself
Token ID2241
Feature activation+3.52e-01

Pos logit contributions
+2.280
eteenth+2.054
ORK+1.955
IGHTS+1.903
č+1.881
Neg logit contributions
 spoiler-1.811
 dilig-1.789
 spoilers-1.692
emale-1.676
adium-1.627
Token hauled
Token ID43423
Feature activation+6.64e-01

Pos logit contributions
+1.115
eteenth+1.019
ORK+0.956
IGHTS+0.940
glers+0.937
Neg logit contributions
 spoiler-0.968
 dilig-0.924
 spoilers-0.915
emale-0.902
adium-0.862
Tokenpl
Token ID489
Feature activation-7.37e-02

Pos logit contributions
 spoiler+0.667
 spoilers+0.640
 dilig+0.634
emale+0.628
adium+0.616
Neg logit contributions
-0.336
eteenth-0.292
ORK-0.267
IGHTS-0.255
glers-0.249
Tokenines
Token ID1127
Feature activation-4.85e-01

Pos logit contributions
 spoiler+0.200
 dilig+0.191
 spoilers+0.188
emale+0.182
 tremend+0.175
Neg logit contributions
-0.236
eteenth-0.219
ORK-0.205
IGHTS-0.203
glers-0.202
Token,
Token ID11
Feature activation-1.26e-01

Pos logit contributions
 spoiler+1.287
 dilig+1.215
 spoilers+1.208
emale+1.173
adium+1.126
Neg logit contributions
-1.586
eteenth-1.467
ORK-1.378
glers-1.354
IGHTS-1.350
Token run
Token ID1057
Feature activation-8.81e-01

Pos logit contributions
 spoiler+0.350
 dilig+0.333
 spoilers+0.330
emale+0.322
adium+0.309
Neg logit contributions
-0.396
eteenth-0.363
ORK-0.342
IGHTS-0.335
glers-0.335
Token for
Token ID329
Feature activation-2.65e-01

Pos logit contributions
 spoiler+2.306
 dilig+2.158
 spoilers+2.150
emale+2.089
adium+1.999
Neg logit contributions
-2.905
eteenth-2.700
ORK-2.530
IGHTS-2.489
glers-2.467
Token Shia
Token ID27424
Feature activation-1.93e+00

Pos logit contributions
 spoiler+0.728
 dilig+0.690
 spoilers+0.686
emale+0.668
adium+0.641
Neg logit contributions
-0.845
eteenth-0.777
ORK-0.732
glers-0.717
IGHTS-0.716
Token and
Token ID290
Feature activation-1.69e-02

Pos logit contributions
 spoiler+4.878
 spoilers+4.611
 dilig+4.577
emale+4.387
 volunt+4.331
Neg logit contributions
-6.332
eteenth-5.963
ORK-5.562
IGHTS-5.488
glers-5.476
Token Sunni
Token ID18592
Feature activation-1.53e+00

Pos logit contributions
 spoiler+0.045
 dilig+0.043
 spoilers+0.042
emale+0.041
adium+0.040
Neg logit contributions
-0.055
eteenth-0.050
ORK-0.048
IGHTS-0.047
glers-0.046
Token Muslims
Token ID7045
Feature activation-1.31e+00

Pos logit contributions
 spoiler+3.931
 spoilers+3.712
 dilig+3.655
emale+3.503
 volunt+3.454
Neg logit contributions
-5.056
eteenth-4.721
ORK-4.433
IGHTS-4.348
glers-4.340
Token,
Token ID11
Feature activation-1.02e-01

Pos logit contributions
 spoiler+3.317
 dilig+3.125
 spoilers+3.120
emale+3.010
 volunt+2.894
Neg logit contributions
-4.363
eteenth-4.086
ORK-3.837
IGHTS-3.751
glers-3.741
Token have
Token ID423
Feature activation+2.29e-01

Pos logit contributions
 spoiler+0.266
 dilig+0.252
 spoilers+0.250
emale+0.244
adium+0.233
Neg logit contributions
-0.336
eteenth-0.310
ORK-0.293
IGHTS-0.287
glers-0.287
Tokenidae
Token ID31718
Feature activation+3.86e-01

Pos logit contributions
 spoiler+1.815
 dilig+1.716
 spoilers+1.706
emale+1.672
adium+1.603
Neg logit contributions
-2.157
eteenth-1.982
ORK-1.874
IGHTS-1.840
glers-1.837
Token).
Token ID737
Feature activation+4.89e-02

Pos logit contributions
+0.947
eteenth+0.846
ORK+0.779
IGHTS+0.753
glers+0.751
Neg logit contributions
 spoiler-1.331
 dilig-1.282
 spoilers-1.271
emale-1.249
adium-1.214
Token IV
Token ID8363
Feature activation+1.31e-01

Pos logit contributions
+0.147
eteenth+0.135
ORK+0.127
IGHTS+0.124
glers+0.123
Neg logit contributions
 spoiler-0.142
 dilig-0.136
 spoilers-0.135
emale-0.132
adium-0.126
Token.
Token ID13
Feature activation+1.59e-01

Pos logit contributions
+0.405
eteenth+0.370
ORK+0.350
IGHTS+0.341
glers+0.334
Neg logit contributions
 spoiler-0.368
 dilig-0.355
 spoilers-0.347
emale-0.341
 volunt-0.328
Token Mult
Token ID7854
Feature activation+5.94e-02

Pos logit contributions
+0.473
eteenth+0.433
ORK+0.406
IGHTS+0.395
glers+0.394
Neg logit contributions
 spoiler-0.471
 dilig-0.452
 spoilers-0.446
emale-0.436
adium-0.419
Tokenif
Token ID361
Feature activation-1.92e+00

Pos logit contributions
+0.185
eteenth+0.173
ORK+0.159
IGHTS+0.156
glers+0.155
Neg logit contributions
 spoiler-0.167
 dilig-0.159
 spoilers-0.158
emale-0.151
 volunt-0.147
Tokenacet
Token ID23253
Feature activation-5.30e-01

Pos logit contributions
 spoiler+6.067
emale+6.001
 spoilers+5.680
 dilig+5.557
adium+5.554
Neg logit contributions
-5.284
eteenth-4.518
ORK-4.349
glers-4.317
IGHTS-4.206
Tokened
Token ID276
Feature activation-5.46e-01

Pos logit contributions
 spoiler+0.742
 dilig+0.661
 spoilers+0.655
emale+0.621
adium+0.568
Neg logit contributions
-2.400
eteenth-2.268
ORK-2.176
glers-2.153
IGHTS-2.148
Token study
Token ID2050
Feature activation-1.91e-01

Pos logit contributions
 spoiler+1.552
 spoilers+1.469
 dilig+1.464
emale+1.422
adium+1.370
Neg logit contributions
-1.686
eteenth-1.555
ORK-1.456
glers-1.432
IGHTS-1.429
Token of
Token ID286
Feature activation-1.73e-01

Pos logit contributions
 spoiler+0.489
 dilig+0.464
 spoilers+0.459
emale+0.447
adium+0.427
Neg logit contributions
-0.639
eteenth-0.591
ORK-0.558
glers-0.547
IGHTS-0.546
Token the
Token ID262
Feature activation-9.59e-02

Pos logit contributions
 spoiler+0.488
 dilig+0.464
 spoilers+0.460
emale+0.449
adium+0.431
Neg logit contributions
-0.539
eteenth-0.495
ORK-0.465
glers-0.456
IGHTS-0.455
TokenDemocratic
Token ID33939
Feature activation-7.45e-01

Pos logit contributions
+2.246
eteenth+2.015
ORK+1.902
IGHTS+1.851
glers+1.826
Neg logit contributions
 spoiler-2.735
 dilig-2.678
 spoilers-2.597
emale-2.571
 tremend-2.500
Token presidential
Token ID4787
Feature activation-3.78e-01

Pos logit contributions
 spoiler+2.562
 spoilers+2.438
 dilig+2.423
emale+2.346
 volunt+2.284
Neg logit contributions
-1.877
eteenth-1.684
ORK-1.556
glers-1.526
IGHTS-1.503
Token nominee
Token ID10429
Feature activation-4.55e-01

Pos logit contributions
 spoiler+1.152
 dilig+1.092
 spoilers+1.089
emale+1.058
adium+1.022
Neg logit contributions
-1.095
eteenth-0.998
ORK-0.934
glers-0.912
IGHTS-0.909
Token Hillary
Token ID5073
Feature activation-9.34e-01

Pos logit contributions
 spoiler+1.569
 dilig+1.508
 spoilers+1.498
emale+1.470
adium+1.422
Neg logit contributions
-1.122
eteenth-1.008
ORK-0.928
glers-0.904
IGHTS-0.901
Token Clinton
Token ID2605
Feature activation-2.13e-01

Pos logit contributions
 spoiler+3.311
 spoilers+3.156
 dilig+3.131
emale+3.059
adium+2.984
Neg logit contributions
-2.250
eteenth-2.006
ORK-1.838
IGHTS-1.789
glers-1.776
Token Hillary
Token ID5073
Feature activation-1.91e+00

Pos logit contributions
 spoiler+0.559
 dilig+0.529
 spoilers+0.525
emale+0.511
adium+0.489
Neg logit contributions
-0.701
eteenth-0.647
ORK-0.610
glers-0.598
IGHTS-0.597
Token Diane
Token ID26542
Feature activation-1.46e+00

Pos logit contributions
 spoiler+3.205
emale+2.832
 spoilers+2.809
 dilig+2.705
adium+2.608
Neg logit contributions
-8.038
eteenth-7.618
ORK-7.200
IGHTS-7.081
glers-6.970
Token Rodham
Token ID41848
Feature activation-4.99e-01

Pos logit contributions
 spoiler+3.696
 spoilers+3.444
emale+3.369
 dilig+3.344
adium+3.241
Neg logit contributions
-4.825
eteenth-4.503
ORK-4.275
IGHTS-4.122
glers-4.078
Token Clinton
Token ID2605
Feature activation-6.97e-01

Pos logit contributions
 spoiler+1.789
 spoilers+1.708
 dilig+1.704
emale+1.666
adium+1.626
Neg logit contributions
-1.175
eteenth-1.053
ORK-0.960
IGHTS-0.930
glers-0.924
TokenSanders
Token ID26747
Feature activation-2.40e-01

Pos logit contributions
 spoiler+2.685
 spoilers+2.575
 dilig+2.551
emale+2.511
adium+2.460
Neg logit contributions
-1.431
eteenth-1.272
ORK-1.138
glers-1.113
IGHTS-1.095
Token:
Token ID25
Feature activation-4.93e-01

Pos logit contributions
 spoiler+0.600
 spoilers+0.564
 dilig+0.558
emale+0.538
adium+0.517
Neg logit contributions
-0.829
eteenth-0.770
ORK-0.725
glers-0.717
IGHTS-0.708
Token election
Token ID3071
Feature activation-7.93e-01

Pos logit contributions
 spoiler+3.089
 spoilers+2.896
 dilig+2.887
emale+2.787
adium+2.686
Neg logit contributions
-3.800
eteenth-3.500
ORK-3.305
glers-3.263
IGHTS-3.249
Token matchup
Token ID18406
Feature activation-5.98e-01

Pos logit contributions
 spoiler+2.154
 spoilers+2.007
 dilig+1.990
emale+1.925
adium+1.851
Neg logit contributions
-2.595
eteenth-2.385
ORK-2.255
glers-2.210
IGHTS-2.209
Token between
Token ID1022
Feature activation-4.11e-01

Pos logit contributions
 spoiler+1.794
 spoilers+1.691
 dilig+1.687
emale+1.633
adium+1.579
Neg logit contributions
-1.771
eteenth-1.612
ORK-1.510
glers-1.482
IGHTS-1.476
Token Donald
Token ID3759
Feature activation-7.39e-01

Pos logit contributions
 spoiler+1.366
 dilig+1.313
 spoilers+1.302
emale+1.278
adium+1.237
Neg logit contributions
-1.065
eteenth-0.962
ORK-0.891
glers-0.867
IGHTS-0.866
Token Trump
Token ID1301
Feature activation-2.34e-01

Pos logit contributions
 spoiler+2.785
 dilig+2.689
 spoilers+2.668
emale+2.624
adium+2.550
Neg logit contributions
-1.592
eteenth-1.410
ORK-1.281
IGHTS-1.238
glers-1.238
Token Donald
Token ID3759
Feature activation-1.88e+00

Pos logit contributions
 spoiler+0.669
 dilig+0.639
 spoilers+0.633
emale+0.620
adium+0.596
Neg logit contributions
-0.714
eteenth-0.656
ORK-0.614
glers-0.601
IGHTS-0.601
Token John
Token ID1757
Feature activation-6.97e-01

Pos logit contributions
 spoiler+4.587
 spoilers+4.219
emale+4.137
 lockout+4.031
 dilig+4.004
Neg logit contributions
-6.513
eteenth-5.993
glers-5.592
ORK-5.582
IGHTS-5.517
Token Trump
Token ID1301
Feature activation-6.82e-01

Pos logit contributions
 spoiler+2.452
 spoilers+2.323
 dilig+2.228
emale+2.199
adium+2.180
Neg logit contributions
-1.717
eteenth-1.538
ORK-1.408
IGHTS-1.349
glers-1.330
TokenHouse
Token ID18102
Feature activation+5.91e-01

Pos logit contributions
 spoiler+2.486
 spoilers+2.377
 dilig+2.358
emale+2.316
adium+2.259
Neg logit contributions
-1.544
eteenth-1.380
ORK-1.245
glers-1.231
IGHTS-1.203
Token committee
Token ID5583
Feature activation+6.61e-02

Pos logit contributions
+1.379
eteenth+1.231
ORK+1.127
glers+1.094
IGHTS+1.089
Neg logit contributions
 spoiler-2.133
 spoilers-2.049
 dilig-2.043
emale-1.996
adium-1.937
Token believes
Token ID5804
Feature activation-8.53e-02

Pos logit contributions
+0.257
eteenth+0.240
ORK+0.229
IGHTS+0.225
glers+0.225
Neg logit contributions
 spoiler-0.132
 dilig-0.124
 spoilers-0.121
emale-0.119
adium-0.113
Token With
Token ID2080
Feature activation+2.84e-01

Pos logit contributions
 spoiler+0.276
 dilig+0.263
 spoilers+0.260
emale+0.254
adium+0.244
Neg logit contributions
-0.299
eteenth-0.274
ORK-0.257
glers-0.252
IGHTS-0.252
Token an
Token ID281
Feature activation+2.84e-02

Pos logit contributions
+0.914
eteenth+0.843
ORK+0.795
glers+0.782
IGHTS+0.775
Neg logit contributions
 spoiler-0.756
 dilig-0.728
 spoilers-0.708
emale-0.704
adium-0.671
Token economy
Token ID3773
Feature activation-6.01e-01

Pos logit contributions
+0.090
eteenth+0.083
ORK+0.078
glers+0.076
IGHTS+0.076
Neg logit contributions
 spoiler-0.078
 dilig-0.074
 spoilers-0.074
emale-0.072
adium-0.069
Token roughly
Token ID7323
Feature activation-4.83e-01

Pos logit contributions
 spoiler+1.533
 dilig+1.432
 spoilers+1.428
emale+1.372
 volunt+1.321
Neg logit contributions
-2.038
eteenth-1.889
ORK-1.781
IGHTS-1.751
glers-1.747
Token the
Token ID262
Feature activation-3.90e-01

Pos logit contributions
 spoiler+1.371
 dilig+1.297
 spoilers+1.291
emale+1.254
adium+1.207
Neg logit contributions
-1.497
eteenth-1.372
ORK-1.289
glers-1.263
IGHTS-1.258
Token size
Token ID2546
Feature activation-1.88e+00

Pos logit contributions
 spoiler+1.073
 dilig+1.016
 spoilers+1.010
emale+0.982
adium+0.944
Neg logit contributions
-1.238
eteenth-1.138
ORK-1.071
glers-1.051
IGHTS-1.048
Token of
Token ID286
Feature activation-5.79e-01

Pos logit contributions
 spoiler+4.169
 dilig+3.838
 spoilers+3.828
emale+3.572
 volunt+3.499
Neg logit contributions
-6.883
eteenth-6.390
ORK-6.033
glers-5.998
IGHTS-5.993
Token Spain
Token ID8602
Feature activation-1.00e+00

Pos logit contributions
 spoiler+1.720
 dilig+1.638
 spoilers+1.627
emale+1.588
adium+1.530
Neg logit contributions
-1.714
eteenth-1.567
ORK-1.467
glers-1.435
IGHTS-1.432
Token
Token ID447
Feature activation-5.30e-01

Pos logit contributions
 spoiler+2.718
 dilig+2.562
 spoilers+2.551
emale+2.464
adium+2.379
Neg logit contributions
-3.209
eteenth-2.952
ORK-2.779
glers-2.738
IGHTS-2.726
Token
Token ID247
Feature activation-1.72e-01

Pos logit contributions
 spoiler+1.750
 spoilers+1.655
 dilig+1.651
emale+1.607
adium+1.577
Neg logit contributions
-1.384
eteenth-1.241
ORK-1.158
glers-1.134
IGHTS-1.134
Tokens
Token ID82
Feature activation-1.83e-01

Pos logit contributions
 spoiler+0.477
 dilig+0.453
 spoilers+0.450
emale+0.439
adium+0.420
Neg logit contributions
-0.539
eteenth-0.497
ORK-0.466
glers-0.458
IGHTS-0.455
Token was
Token ID373
Feature activation-4.11e-01

Pos logit contributions
 spoiler+2.045
 spoilers+1.919
 dilig+1.905
emale+1.843
adium+1.771
Neg logit contributions
-2.486
eteenth-2.290
ORK-2.169
glers-2.115
IGHTS-2.106
Token dealt
Token ID11829
Feature activation+1.39e-01

Pos logit contributions
 spoiler+1.148
 dilig+1.083
 spoilers+1.079
emale+1.041
adium+1.003
Neg logit contributions
-1.295
eteenth-1.189
ORK-1.120
glers-1.098
IGHTS-1.095
Token to
Token ID284
Feature activation+1.09e-01

Pos logit contributions
+0.437
eteenth+0.400
ORK+0.378
glers+0.369
IGHTS+0.369
Neg logit contributions
 spoiler-0.387
 dilig-0.369
 spoilers-0.365
emale-0.359
adium-0.345
Token the
Token ID262
Feature activation+4.00e-02

Pos logit contributions
+0.318
eteenth+0.287
ORK+0.271
glers+0.266
IGHTS+0.264
Neg logit contributions
 spoiler-0.327
 dilig-0.315
 spoilers-0.310
emale-0.307
adium-0.294
Token Pittsburgh
Token ID12767
Feature activation-8.38e-01

Pos logit contributions
+0.103
eteenth+0.092
ORK+0.086
glers+0.084
IGHTS+0.083
Neg logit contributions
 spoiler-0.134
 dilig-0.129
 spoilers-0.127
emale-0.126
adium-0.121
Token Penguins
Token ID29755
Feature activation-1.87e+00

Pos logit contributions
 spoiler+2.325
 dilig+2.213
 spoilers+2.190
emale+2.141
adium+2.051
Neg logit contributions
-2.637
eteenth-2.423
ORK-2.282
glers-2.235
IGHTS-2.229
Token in
Token ID287
Feature activation-3.33e-01

Pos logit contributions
 spoiler+4.663
 spoilers+4.322
 dilig+4.244
emale+4.114
 lockout+4.024
Neg logit contributions
-6.305
eteenth-5.889
ORK-5.510
glers-5.410
IGHTS-5.403
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
 spoiler+0.940
 dilig+0.896
 spoilers+0.888
emale+0.869
adium+0.833
Neg logit contributions
-1.028
eteenth-0.945
ORK-0.887
glers-0.869
IGHTS-0.867
Token summer
Token ID3931
Feature activation-2.78e-01

Pos logit contributions
 spoiler+0.035
 dilig+0.034
 spoilers+0.033
emale+0.033
adium+0.032
Neg logit contributions
-0.039
eteenth-0.036
ORK-0.034
glers-0.033
IGHTS-0.033
Token of
Token ID286
Feature activation+3.47e-01

Pos logit contributions
 spoiler+0.708
 dilig+0.680
 spoilers+0.667
emale+0.655
adium+0.624
Neg logit contributions
-0.934
eteenth-0.860
ORK-0.816
glers-0.801
IGHTS-0.795
Token 2015
Token ID1853
Feature activation-1.27e-01

Pos logit contributions
+0.957
eteenth+0.867
ORK+0.811
glers+0.792
IGHTS+0.790
Neg logit contributions
 spoiler-1.081
 dilig-1.058
 spoilers-1.030
emale-1.025
 tremend-0.986
Token problem
Token ID1917
Feature activation+2.95e-01

Pos logit contributions
+0.015
eteenth+0.014
ORK+0.013
glers+0.013
IGHTS+0.013
Neg logit contributions
 spoiler-0.013
 dilig-0.012
 spoilers-0.012
emale-0.012
adium-0.011
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
+0.948
eteenth+0.874
ORK+0.818
glers+0.804
IGHTS+0.801
Neg logit contributions
 spoiler-0.788
 dilig-0.759
 spoilers-0.744
emale-0.739
adium-0.698
Token If
Token ID1002
Feature activation-1.17e-02

Pos logit contributions
 spoiler+0.422
 dilig+0.402
 spoilers+0.397
emale+0.388
adium+0.372
Neg logit contributions
-0.487
eteenth-0.448
ORK-0.422
glers-0.413
IGHTS-0.413
Token I
Token ID314
Feature activation-1.84e-01

Pos logit contributions
 spoiler+0.031
 dilig+0.029
 spoilers+0.029
emale+0.028
adium+0.027
Neg logit contributions
-0.039
eteenth-0.036
ORK-0.034
glers-0.033
IGHTS-0.033
Token were
Token ID547
Feature activation-1.24e+00

Pos logit contributions
 spoiler+0.491
 dilig+0.460
 spoilers+0.460
emale+0.445
adium+0.428
Neg logit contributions
-0.604
eteenth-0.558
ORK-0.526
glers-0.514
IGHTS-0.513
Token Shia
Token ID27424
Feature activation-1.86e+00

Pos logit contributions
 spoiler+3.243
 spoilers+3.044
 dilig+3.002
emale+2.868
adium+2.792
Neg logit contributions
-4.116
eteenth-3.854
ORK-3.639
glers-3.550
IGHTS-3.530
Token,
Token ID11
Feature activation-2.85e-01

Pos logit contributions
 spoiler+5.095
 spoilers+4.828
 dilig+4.822
emale+4.635
 volunt+4.484
Neg logit contributions
-5.768
eteenth-5.398
ORK-5.037
glers-4.949
IGHTS-4.881
Token I
Token ID314
Feature activation-4.56e-02

Pos logit contributions
 spoiler+0.735
 dilig+0.703
 spoilers+0.689
emale+0.680
adium+0.649
Neg logit contributions
-0.948
eteenth-0.874
ORK-0.825
glers-0.812
IGHTS-0.810
Token
Token ID447
Feature activation-5.14e-01

Pos logit contributions
 spoiler+0.122
 dilig+0.116
 spoilers+0.115
emale+0.112
adium+0.107
Neg logit contributions
-0.148
eteenth-0.137
ORK-0.129
glers-0.126
IGHTS-0.126
Token
Token ID247
Feature activation-3.99e-01

Pos logit contributions
 spoiler+1.742
 dilig+1.667
 spoilers+1.658
emale+1.624
adium+1.571
Neg logit contributions
-1.304
eteenth-1.172
ORK-1.085
glers-1.057
IGHTS-1.055
Tokend
Token ID67
Feature activation-6.22e-01

Pos logit contributions
 spoiler+1.236
 dilig+1.182
 spoilers+1.173
emale+1.148
adium+1.107
Neg logit contributions
-1.125
eteenth-1.023
ORK-0.958
glers-0.935
IGHTS-0.932
Token right
Token ID826
Feature activation+2.99e-01

Pos logit contributions
 spoiler+0.020
 dilig+0.020
 spoilers+0.019
emale+0.019
adium+0.018
Neg logit contributions
-0.025
eteenth-0.023
ORK-0.022
IGHTS-0.021
glers-0.021
Token?
Token ID30
Feature activation-8.77e-02

Pos logit contributions
+0.855
eteenth+0.772
ORK+0.729
IGHTS+0.713
glers+0.703
Neg logit contributions
 spoiler-0.896
 dilig-0.861
emale-0.852
 spoilers-0.848
adium-0.826
Token
Token ID198
Feature activation-4.20e-01

Pos logit contributions
 spoiler+0.259
 dilig+0.249
 spoilers+0.245
emale+0.241
adium+0.231
Neg logit contributions
-0.260
eteenth-0.237
ORK-0.223
IGHTS-0.218
glers-0.218
Token
Token ID198
Feature activation-5.09e-01

Pos logit contributions
 spoiler+1.249
 spoilers+1.180
 dilig+1.139
emale+1.114
adium+1.114
Neg logit contributions
-1.245
eteenth-1.145
ORK-1.065
glers-1.040
IGHTS-1.036
TokenLeave
Token ID35087
Feature activation+6.26e-02

Pos logit contributions
 spoiler+1.516
 spoilers+1.434
 dilig+1.418
emale+1.391
adium+1.354
Neg logit contributions
-1.485
eteenth-1.365
ORK-1.268
glers-1.249
IGHTS-1.235
Token Shia
Token ID27424
Feature activation-1.86e+00

Pos logit contributions
+0.205
eteenth+0.189
ORK+0.180
IGHTS+0.176
glers+0.176
Neg logit contributions
 spoiler-0.161
 dilig-0.156
emale-0.152
 spoilers-0.151
adium-0.144
Token alone
Token ID3436
Feature activation+4.97e-01

Pos logit contributions
 spoiler+5.094
 spoilers+4.758
 dilig+4.651
emale+4.493
 volunt+4.379
Neg logit contributions
-5.781
eteenth-5.394
ORK-5.046
glers-5.022
IGHTS-4.855
Token,
Token ID11
Feature activation-2.00e-01

Pos logit contributions
+1.540
eteenth+1.410
ORK+1.325
IGHTS+1.297
glers+1.297
Neg logit contributions
 spoiler-1.372
 dilig-1.325
emale-1.300
 spoilers-1.298
adium-1.234
Token guys
Token ID3730
Feature activation-6.69e-02

Pos logit contributions
 spoiler+0.525
 dilig+0.504
 spoilers+0.494
emale+0.488
adium+0.467
Neg logit contributions
-0.653
eteenth-0.600
ORK-0.568
IGHTS-0.557
glers-0.557
Token.
Token ID13
Feature activation-1.42e-01

Pos logit contributions
 spoiler+0.181
 dilig+0.172
 spoilers+0.170
emale+0.167
adium+0.161
Neg logit contributions
-0.215
eteenth-0.198
ORK-0.186
glers-0.182
IGHTS-0.182
Token You
Token ID921
Feature activation-2.57e-01

Pos logit contributions
 spoiler+0.397
 dilig+0.378
 spoilers+0.374
emale+0.365
adium+0.351
Neg logit contributions
-0.444
eteenth-0.408
ORK-0.383
glers-0.376
IGHTS-0.375
Token has
Token ID468
Feature activation+1.01e-01

Pos logit contributions
+0.538
eteenth+0.497
ORK+0.467
glers+0.460
IGHTS+0.459
Neg logit contributions
 spoiler-0.443
 dilig-0.424
 spoilers-0.417
emale-0.412
adium-0.393
Token repeatedly
Token ID7830
Feature activation+1.08e-01

Pos logit contributions
+0.325
eteenth+0.300
ORK+0.282
glers+0.276
IGHTS+0.276
Neg logit contributions
 spoiler-0.272
 dilig-0.259
 spoilers-0.256
emale-0.253
adium-0.241
Token criticized
Token ID12318
Feature activation-7.87e-01

Pos logit contributions
+0.347
eteenth+0.321
ORK+0.301
glers+0.296
IGHTS+0.296
Neg logit contributions
 spoiler-0.288
 dilig-0.275
 spoilers-0.271
emale-0.268
adium-0.256
Token President
Token ID1992
Feature activation+4.09e-01

Pos logit contributions
 spoiler+2.676
 spoilers+2.551
 dilig+2.539
emale+2.465
 volunt+2.399
Neg logit contributions
-2.011
eteenth-1.798
ORK-1.662
glers-1.625
IGHTS-1.620
Token Trump
Token ID1301
Feature activation-2.98e-01

Pos logit contributions
+0.845
eteenth+0.763
ORK+0.683
IGHTS+0.658
glers+0.655
Neg logit contributions
 spoiler-1.550
 dilig-1.511
 spoilers-1.486
emale-1.472
adium-1.431
Token Donald
Token ID3759
Feature activation-1.84e+00

Pos logit contributions
 spoiler+0.780
 dilig+0.735
 spoilers+0.732
emale+0.709
adium+0.680
Neg logit contributions
-0.987
eteenth-0.911
ORK-0.860
glers-0.843
IGHTS-0.841
Token John
Token ID1757
Feature activation-8.16e-01

Pos logit contributions
 spoiler+4.564
 spoilers+4.203
emale+4.110
 dilig+4.077
 lockout+3.959
Neg logit contributions
-6.281
eteenth-5.809
ORK-5.378
glers-5.355
IGHTS-5.339
Token Trump
Token ID1301
Feature activation-6.48e-01

Pos logit contributions
 spoiler+2.847
 spoilers+2.691
 dilig+2.568
emale+2.526
 lockout+2.501
Neg logit contributions
-2.056
eteenth-1.831
ORK-1.672
IGHTS-1.598
glers-1.588
TokenHouse
Token ID18102
Feature activation+5.52e-01

Pos logit contributions
 spoiler+2.328
 spoilers+2.224
 dilig+2.204
emale+2.167
adium+2.116
Neg logit contributions
-1.492
eteenth-1.339
ORK-1.202
glers-1.192
IGHTS-1.163
Token committee
Token ID5583
Feature activation+3.86e-01

Pos logit contributions
+1.256
eteenth+1.117
ORK+1.021
glers+0.990
IGHTS+0.987
Neg logit contributions
 spoiler-2.017
 dilig-1.938
 spoilers-1.931
emale-1.891
adium-1.835
Token believes
Token ID5804
Feature activation-1.76e-01

Pos logit contributions
+1.492
eteenth+1.392
ORK+1.335
IGHTS+1.314
glers+1.308
Neg logit contributions
 spoiler-0.773
 dilig-0.734
 spoilers-0.709
emale-0.704
adium-0.671
Token healthcare
Token ID11409
Feature activation-6.85e-01

Pos logit contributions
 spoiler+0.560
 dilig+0.530
 spoilers+0.526
emale+0.512
adium+0.490
Neg logit contributions
-0.704
eteenth-0.650
ORK-0.613
glers-0.601
IGHTS-0.600
Token,
Token ID11
Feature activation+1.99e-02

Pos logit contributions
 spoiler+1.810
 dilig+1.716
 spoilers+1.704
emale+1.643
 volunt+1.585
Neg logit contributions
-2.244
eteenth-2.071
ORK-1.948
glers-1.919
IGHTS-1.908
Token and
Token ID290
Feature activation+2.56e-01

Pos logit contributions
+0.065
eteenth+0.060
ORK+0.056
glers+0.055
IGHTS+0.055
Neg logit contributions
 spoiler-0.053
 dilig-0.050
 spoilers-0.050
emale-0.049
adium-0.046
Token retain
Token ID12377
Feature activation-3.09e-01

Pos logit contributions
+0.839
eteenth+0.772
ORK+0.730
glers+0.718
IGHTS+0.717
Neg logit contributions
 spoiler-0.669
 dilig-0.635
 spoilers-0.628
emale-0.615
adium-0.589
Token a
Token ID257
Feature activation-3.59e-01

Pos logit contributions
 spoiler+0.822
 dilig+0.778
 spoilers+0.772
emale+0.749
adium+0.719
Neg logit contributions
-1.009
eteenth-0.930
ORK-0.877
glers-0.860
IGHTS-0.857
Token pension
Token ID13553
Feature activation-1.84e+00

Pos logit contributions
 spoiler+0.985
 dilig+0.932
 spoilers+0.923
emale+0.899
adium+0.863
Neg logit contributions
-1.145
eteenth-1.052
ORK-0.991
glers-0.972
IGHTS-0.968
Token.
Token ID13
Feature activation-4.00e-01

Pos logit contributions
 spoiler+4.546
 dilig+4.212
 spoilers+4.177
emale+4.045
 volunt+3.925
Neg logit contributions
-6.261
eteenth-5.777
glers-5.439
ORK-5.437
IGHTS-5.364
Token
Token ID198
Feature activation-5.78e-02

Pos logit contributions
 spoiler+1.200
 dilig+1.140
 spoilers+1.138
emale+1.109
adium+1.072
Neg logit contributions
-1.167
eteenth-1.069
ORK-0.997
glers-0.975
IGHTS-0.971
Token
Token ID198
Feature activation-9.11e-02

Pos logit contributions
 spoiler+0.174
 spoilers+0.165
 dilig+0.161
emale+0.157
adium+0.156
Neg logit contributions
-0.169
eteenth-0.155
ORK-0.145
glers-0.141
IGHTS-0.141
Token
Token ID447
Feature activation+2.31e-02

Pos logit contributions
 spoiler+0.282
 spoilers+0.268
 dilig+0.268
emale+0.261
adium+0.253
Neg logit contributions
-0.256
eteenth-0.234
ORK-0.217
glers-0.213
IGHTS-0.211
Token
Token ID250
Feature activation-1.34e-03

Pos logit contributions
+0.059
eteenth+0.054
ORK+0.050
IGHTS+0.048
glers+0.048
Neg logit contributions
 spoiler-0.077
 dilig-0.074
 spoilers-0.074
emale-0.073
adium-0.070
Token out
Token ID503
Feature activation+3.59e-02

Pos logit contributions
 spoiler+2.930
 spoilers+2.746
 dilig+2.729
emale+2.615
adium+2.516
Neg logit contributions
-3.805
eteenth-3.509
ORK-3.331
glers-3.257
IGHTS-3.256
Token
Token ID1399
Feature activation-6.36e-01

Pos logit contributions
+0.114
eteenth+0.105
ORK+0.099
glers+0.097
IGHTS+0.097
Neg logit contributions
 spoiler-0.097
 dilig-0.093
 spoilers-0.091
emale-0.091
adium-0.087
Tokenbut
Token ID4360
Feature activation-3.02e-01

Pos logit contributions
 spoiler+1.793
 dilig+1.692
 spoilers+1.690
emale+1.639
adium+1.580
Neg logit contributions
-1.980
eteenth-1.819
ORK-1.705
glers-1.673
IGHTS-1.668
Token let
Token ID1309
Feature activation-5.31e-02

Pos logit contributions
 spoiler+0.771
 dilig+0.735
 spoilers+0.724
emale+0.711
adium+0.680
Neg logit contributions
-1.010
eteenth-0.934
ORK-0.882
glers-0.867
IGHTS-0.865
Token me
Token ID502
Feature activation-4.41e-01

Pos logit contributions
 spoiler+0.125
 dilig+0.121
emale+0.118
 spoilers+0.117
adium+0.111
Neg logit contributions
-0.186
eteenth-0.172
ORK-0.164
glers-0.162
IGHTS-0.161
Token know
Token ID760
Feature activation-1.84e+00

Pos logit contributions
 spoiler+1.089
 dilig+1.023
 spoilers+1.017
emale+0.982
adium+0.940
Neg logit contributions
-1.530
eteenth-1.419
ORK-1.343
glers-1.317
IGHTS-1.314
Token if
Token ID611
Feature activation-6.64e-01

Pos logit contributions
 spoiler+4.124
 spoilers+3.846
 dilig+3.747
emale+3.454
 volunt+3.359
Neg logit contributions
-6.748
eteenth-6.285
ORK-5.961
glers-5.887
IGHTS-5.801
Token anyone
Token ID2687
Feature activation-2.83e-01

Pos logit contributions
 spoiler+1.673
 dilig+1.570
 spoilers+1.569
emale+1.506
adium+1.442
Neg logit contributions
-2.275
eteenth-2.105
ORK-1.986
glers-1.950
IGHTS-1.949
Token does
Token ID857
Feature activation+4.75e-01

Pos logit contributions
 spoiler+0.740
 dilig+0.699
 spoilers+0.695
emale+0.674
adium+0.646
Neg logit contributions
-0.940
eteenth-0.868
ORK-0.820
glers-0.803
IGHTS-0.802
Token this
Token ID428
Feature activation-3.76e-02

Pos logit contributions
+1.462
eteenth+1.340
ORK+1.272
glers+1.245
IGHTS+1.237
Neg logit contributions
 spoiler-1.301
 dilig-1.269
emale-1.244
 spoilers-1.224
adium-1.194
Token project
Token ID1628
Feature activation-1.87e-01

Pos logit contributions
 spoiler+0.102
 dilig+0.097
 spoilers+0.096
emale+0.095
adium+0.091
Neg logit contributions
-0.120
eteenth-0.110
ORK-0.104
glers-0.102
IGHTS-0.102
Token went
Token ID1816
Feature activation-7.69e-01

Pos logit contributions
 spoiler+0.015
 dilig+0.014
 spoilers+0.014
emale+0.014
adium+0.013
Neg logit contributions
-0.018
eteenth-0.017
ORK-0.016
glers-0.015
IGHTS-0.015
Token through
Token ID832
Feature activation-3.01e-01

Pos logit contributions
 spoiler+2.110
 dilig+1.985
 spoilers+1.981
emale+1.909
adium+1.849
Neg logit contributions
-2.465
eteenth-2.263
ORK-2.131
glers-2.086
IGHTS-2.079
Token the
Token ID262
Feature activation-1.97e-01

Pos logit contributions
 spoiler+0.784
 dilig+0.744
 spoilers+0.735
emale+0.719
adium+0.687
Neg logit contributions
-0.996
eteenth-0.919
ORK-0.869
glers-0.852
IGHTS-0.851
Token LA
Token ID9131
Feature activation+6.05e-01

Pos logit contributions
 spoiler+0.524
 dilig+0.498
 spoilers+0.493
emale+0.483
adium+0.461
Neg logit contributions
-0.642
eteenth-0.592
ORK-0.558
glers-0.548
IGHTS-0.547
TokenX
Token ID55
Feature activation-3.64e-01

Pos logit contributions
+1.725
eteenth+1.575
ORK+1.480
IGHTS+1.466
glers+1.440
Neg logit contributions
 spoiler-1.812
 dilig-1.748
 spoilers-1.712
emale-1.703
 volunt-1.626
Token security
Token ID2324
Feature activation-1.83e+00

Pos logit contributions
 spoiler+0.937
 dilig+0.890
 spoilers+0.879
emale+0.858
adium+0.820
Neg logit contributions
-1.214
eteenth-1.122
ORK-1.061
IGHTS-1.041
glers-1.041
Token line
Token ID1627
Feature activation-2.99e-02

Pos logit contributions
 spoiler+4.619
 spoilers+4.330
 dilig+4.272
 lockout+4.017
emale+3.995
Neg logit contributions
-6.262
eteenth-5.786
ORK-5.469
glers-5.335
IGHTS-5.326
Token with
Token ID351
Feature activation-3.32e-01

Pos logit contributions
 spoiler+0.085
 dilig+0.081
 spoilers+0.080
emale+0.078
adium+0.075
Neg logit contributions
-0.092
eteenth-0.085
ORK-0.079
glers-0.078
IGHTS-0.078
Token Marilyn
Token ID40769
Feature activation-5.81e-01

Pos logit contributions
 spoiler+0.846
 dilig+0.803
 spoilers+0.791
emale+0.775
adium+0.741
Neg logit contributions
-1.117
eteenth-1.030
ORK-0.975
glers-0.957
IGHTS-0.955
Token Manson
Token ID41645
Feature activation-8.33e-01

Pos logit contributions
 spoiler+1.490
 dilig+1.405
 spoilers+1.397
emale+1.355
adium+1.299
Neg logit contributions
-1.954
eteenth-1.808
ORK-1.706
glers-1.673
IGHTS-1.670
Token,"
Token ID553
Feature activation+2.30e-01

Pos logit contributions
 spoiler+2.359
 spoilers+2.225
 dilig+2.218
emale+2.136
adium+2.072
Neg logit contributions
-2.590
eteenth-2.372
ORK-2.233
glers-2.175
IGHTS-2.165
Token.
Token ID13
Feature activation+5.84e-01

Pos logit contributions
+2.090
eteenth+1.905
ORK+1.792
glers+1.763
IGHTS+1.757
Neg logit contributions
 spoiler-1.835
 dilig-1.805
emale-1.743
 spoilers-1.732
 tremend-1.706
Token But
Token ID887
Feature activation+2.86e-01

Pos logit contributions
+2.008
eteenth+1.846
ORK+1.777
glers+1.754
IGHTS+1.747
Neg logit contributions
 spoiler-1.438
 dilig-1.375
 spoilers-1.336
emale-1.335
 tremend-1.265
Token as
Token ID355
Feature activation+7.80e-01

Pos logit contributions
+0.906
eteenth+0.833
ORK+0.783
glers+0.768
IGHTS+0.766
Neg logit contributions
 spoiler-0.790
 dilig-0.750
 spoilers-0.745
emale-0.726
adium-0.697
Token with
Token ID351
Feature activation-1.83e-02

Pos logit contributions
+2.092
eteenth+1.886
ORK+1.759
glers+1.730
IGHTS+1.715
Neg logit contributions
 spoiler-2.464
 dilig-2.440
emale-2.395
 spoilers-2.348
 tremend-2.322
Token every
Token ID790
Feature activation+1.19e-01

Pos logit contributions
 spoiler+0.042
 dilig+0.040
 spoilers+0.040
emale+0.038
adium+0.036
Neg logit contributions
-0.066
eteenth-0.061
ORK-0.058
glers-0.057
IGHTS-0.057
Token new
Token ID649
Feature activation+1.34e+00

Pos logit contributions
+0.290
eteenth+0.261
ORK+0.240
glers+0.234
IGHTS+0.233
Neg logit contributions
 spoiler-0.415
 dilig-0.401
 spoilers-0.396
emale-0.391
adium-0.377
Token toy
Token ID13373
Feature activation+1.25e+00

Pos logit contributions
+3.231
eteenth+2.977
ORK+2.781
glers+2.642
ters+2.607
Neg logit contributions
 dilig-4.427
emale-4.393
 spoiler-4.321
 tremend-4.220
 spoilers-4.172
Token,
Token ID11
Feature activation+6.82e-01

Pos logit contributions
+3.528
eteenth+3.117
glers+2.968
ORK+2.967
ters+2.933
Neg logit contributions
 dilig-3.880
 tremend-3.822
emale-3.746
 spoiler-3.717
 spoilers-3.509
Token there
Token ID612
Feature activation+1.01e+00

Pos logit contributions
+2.229
eteenth+2.056
ORK+1.953
IGHTS+1.907
glers+1.904
Neg logit contributions
 spoiler-1.746
 dilig-1.728
emale-1.710
 tremend-1.640
 spoilers-1.622
Token are
Token ID389
Feature activation+1.85e-01

Pos logit contributions
+3.262
eteenth+2.971
glers+2.840
drops+2.799
ters+2.793
Neg logit contributions
 dilig-2.632
 spoiler-2.604
 tremend-2.550
emale-2.533
 spoilers-2.408
Token some
Token ID617
Feature activation+3.30e-01

Pos logit contributions
+0.565
eteenth+0.521
ORK+0.489
IGHTS+0.477
glers+0.474
Neg logit contributions
 spoiler-0.535
 spoilers-0.509
 dilig-0.500
emale-0.482
adium-0.468
Token case
Token ID1339
Feature activation+3.59e-01

Pos logit contributions
 spoiler+1.249
 spoilers+1.179
 dilig+1.177
emale+1.151
 volunt+1.107
Neg logit contributions
-1.261
eteenth-1.153
ORK-1.078
glers-1.053
IGHTS-1.051
Token or
Token ID393
Feature activation-6.77e-02

Pos logit contributions
+1.141
eteenth+1.051
ORK+0.989
glers+0.971
IGHTS+0.968
Neg logit contributions
 spoiler-0.975
 dilig-0.938
 spoilers-0.916
emale-0.900
adium-0.869
Token the
Token ID262
Feature activation-2.73e-01

Pos logit contributions
 spoiler+0.192
 dilig+0.183
 spoilers+0.181
emale+0.177
adium+0.170
Neg logit contributions
-0.209
eteenth-0.192
ORK-0.180
glers-0.176
IGHTS-0.176
Token child
Token ID1200
Feature activation+2.34e-01

Pos logit contributions
 spoiler+0.813
 dilig+0.769
 spoilers+0.768
emale+0.748
adium+0.720
Neg logit contributions
-0.810
eteenth-0.741
ORK-0.693
glers-0.678
IGHTS-0.677
Token is
Token ID318
Feature activation+2.36e-01

Pos logit contributions
+0.782
eteenth+0.724
ORK+0.681
glers+0.674
IGHTS+0.672
Neg logit contributions
 spoiler-0.597
 dilig-0.569
 spoilers-0.559
emale-0.550
adium-0.526
Token transgender
Token ID10637
Feature activation+1.41e+00

Pos logit contributions
+0.731
eteenth+0.673
ORK+0.631
IGHTS+0.619
glers+0.619
Neg logit contributions
 spoiler-0.661
 dilig-0.632
 spoilers-0.624
emale-0.611
adium-0.588
Token,
Token ID11
Feature activation-2.38e-02

Pos logit contributions
+4.374
eteenth+4.008
glers+3.822
ORK+3.752
ters+3.749
Neg logit contributions
 spoiler-3.783
 dilig-3.732
 spoilers-3.480
emale-3.451
adium-3.393
Token society
Token ID3592
Feature activation-4.82e-02

Pos logit contributions
 spoiler+0.062
 dilig+0.059
 spoilers+0.058
emale+0.057
adium+0.055
Neg logit contributions
-0.078
eteenth-0.073
ORK-0.068
glers-0.067
IGHTS-0.067
Token inst
Token ID916
Feature activation+3.98e-01

Pos logit contributions
 spoiler+0.125
 dilig+0.118
 spoilers+0.118
emale+0.114
adium+0.109
Neg logit contributions
-0.160
eteenth-0.148
ORK-0.140
glers-0.137
IGHTS-0.137
Tokenills
Token ID2171
Feature activation+4.23e-01

Pos logit contributions
+1.156
eteenth+1.064
ORK+0.990
glers+0.979
IGHTS+0.972
Neg logit contributions
 spoiler-1.196
 dilig-1.145
 spoilers-1.128
emale-1.097
 volunt-1.065
Token in
Token ID287
Feature activation+9.11e-02

Pos logit contributions
+1.316
eteenth+1.214
ORK+1.144
IGHTS+1.120
glers+1.118
Neg logit contributions
 spoiler-1.164
 dilig-1.117
 spoilers-1.094
emale-1.089
adium-1.047
Token and
Token ID290
Feature activation+7.15e-02

Pos logit contributions
+1.097
eteenth+1.011
ORK+0.952
glers+0.940
IGHTS+0.936
Neg logit contributions
 spoiler-0.836
 dilig-0.806
 spoilers-0.781
emale-0.780
adium-0.739
Token the
Token ID262
Feature activation+1.74e-01

Pos logit contributions
+0.218
eteenth+0.199
ORK+0.187
glers+0.183
IGHTS+0.182
Neg logit contributions
 spoiler-0.204
 dilig-0.196
 spoilers-0.192
emale-0.190
adium-0.183
Token specifics
Token ID23514
Feature activation-6.86e-01

Pos logit contributions
+0.535
eteenth+0.489
ORK+0.458
glers+0.451
IGHTS+0.448
Neg logit contributions
 spoiler-0.492
 dilig-0.474
 spoilers-0.464
emale-0.460
adium-0.442
Token are
Token ID389
Feature activation+2.50e-04

Pos logit contributions
 spoiler+1.662
 dilig+1.553
 spoilers+1.553
emale+1.497
adium+1.429
Neg logit contributions
-2.402
eteenth-2.233
ORK-2.115
glers-2.074
IGHTS-2.064
Token different
Token ID1180
Feature activation+5.30e-02

Pos logit contributions
+0.001
eteenth+0.001
ORK+0.001
glers+0.001
IGHTS+0.001
Neg logit contributions
 spoiler-0.001
 dilig-0.001
 spoilers-0.001
emale-0.001
adium-0.001
Token here
Token ID994
Feature activation+1.31e+00

Pos logit contributions
+0.169
eteenth+0.155
ORK+0.146
glers+0.144
IGHTS+0.143
Neg logit contributions
 spoiler-0.144
 dilig-0.138
 spoilers-0.135
emale-0.133
adium-0.127
Token,
Token ID11
Feature activation-1.89e-02

Pos logit contributions
+3.888
eteenth+3.502
ORK+3.250
glers+3.233
IGHTS+3.191
Neg logit contributions
 spoiler-3.735
 dilig-3.621
 spoilers-3.541
emale-3.493
adium-3.351
Token the
Token ID262
Feature activation+4.04e-02

Pos logit contributions
 spoiler+0.049
 dilig+0.047
 spoilers+0.046
emale+0.045
adium+0.043
Neg logit contributions
-0.062
eteenth-0.057
ORK-0.054
glers-0.053
IGHTS-0.053
Token approach
Token ID3164
Feature activation+1.91e-02

Pos logit contributions
+0.129
eteenth+0.118
ORK+0.111
glers+0.109
IGHTS+0.109
Neg logit contributions
 spoiler-0.110
 dilig-0.105
 spoilers-0.103
emale-0.102
adium-0.098
Token feels
Token ID5300
Feature activation+1.36e+00

Pos logit contributions
+0.063
eteenth+0.058
ORK+0.055
glers+0.054
IGHTS+0.054
Neg logit contributions
 spoiler-0.050
 dilig-0.047
 spoilers-0.047
emale-0.046
adium-0.044
Token worn
Token ID12666
Feature activation+6.96e-01

Pos logit contributions
+4.042
eteenth+3.764
ORK+3.424
IGHTS+3.416
ters+3.386
Neg logit contributions
 spoiler-3.689
emale-3.612
 dilig-3.607
 spoilers-3.541
adium-3.450
Tokenis
Token ID271
Feature activation+8.08e-01

Pos logit contributions
+0.860
eteenth+0.780
ORK+0.735
glers+0.712
IGHTS+0.709
Neg logit contributions
 spoiler-0.922
 dilig-0.890
 spoilers-0.873
emale-0.863
adium-0.824
Token created
Token ID2727
Feature activation+7.65e-01

Pos logit contributions
+1.766
eteenth+1.549
ORK+1.416
glers+1.357
IGHTS+1.356
Neg logit contributions
 spoiler-2.992
 dilig-2.895
 spoilers-2.889
emale-2.887
 tremend-2.744
Token and
Token ID290
Feature activation+3.07e-01

Pos logit contributions
+2.221
eteenth+2.012
ORK+1.883
glers+1.858
IGHTS+1.837
Neg logit contributions
 spoiler-2.268
 dilig-2.242
emale-2.195
 spoilers-2.152
 tremend-2.146
Token the
Token ID262
Feature activation+3.52e-01

Pos logit contributions
+0.978
eteenth+0.897
ORK+0.848
glers+0.834
IGHTS+0.832
Neg logit contributions
 spoiler-0.827
 dilig-0.807
emale-0.791
 spoilers-0.779
 tremend-0.761
Token archived
Token ID33962
Feature activation+2.74e-01

Pos logit contributions
+1.362
eteenth+1.270
ORK+1.226
IGHTS+1.197
glers+1.191
Neg logit contributions
 spoiler-0.698
 dilig-0.664
emale-0.650
 spoilers-0.645
adium-0.592
Token file
Token ID2393
Feature activation+1.21e+00

Pos logit contributions
+0.784
eteenth+0.712
ORK+0.674
glers+0.657
IGHTS+0.654
Neg logit contributions
 spoiler-0.818
 dilig-0.804
emale-0.782
 spoilers-0.778
 tremend-0.753
Token is
Token ID318
Feature activation+7.75e-01

Pos logit contributions
+3.629
eteenth+3.261
ters+3.166
drops+3.095
IGHTS+3.093
Neg logit contributions
 tremend-3.432
emale-3.420
 dilig-3.403
 spoiler-3.252
 spoilers-3.066
Token uploaded
Token ID19144
Feature activation+1.30e+00

Pos logit contributions
+2.475
eteenth+2.299
ORK+2.157
glers+2.117
IGHTS+2.113
Neg logit contributions
 spoiler-2.026
 dilig-2.002
emale-1.989
 spoilers-1.915
 tremend-1.898
Token to
Token ID284
Feature activation+6.46e-01

Pos logit contributions
+3.568
eteenth+3.165
ters+3.002
ORK+2.995
glers+2.976
Neg logit contributions
 dilig-4.029
emale-4.010
 tremend-4.009
 spoiler-3.946
 spoilers-3.753
Token it
Token ID340
Feature activation+4.49e-01

Pos logit contributions
+2.042
eteenth+1.875
ORK+1.793
glers+1.744
ters+1.733
Neg logit contributions
 spoiler-1.716
 dilig-1.713
emale-1.692
 tremend-1.643
 spoilers-1.625
Token.
Token ID13
Feature activation+7.27e-01

Pos logit contributions
+1.426
eteenth+1.308
ORK+1.232
glers+1.209
IGHTS+1.206
Neg logit contributions
 spoiler-1.231
 dilig-1.208
emale-1.164
 spoilers-1.161
 tremend-1.136
Token take
Token ID1011
Feature activation-8.48e-01

Pos logit contributions
 spoiler+0.742
 dilig+0.697
 spoilers+0.693
emale+0.670
adium+0.642
Neg logit contributions
-1.004
eteenth-0.930
ORK-0.879
IGHTS-0.861
glers-0.861
Token effective
Token ID4050
Feature activation-4.76e-01

Pos logit contributions
 spoiler+2.332
 spoilers+2.196
 dilig+2.189
emale+2.104
 volunt+2.041
Neg logit contributions
-2.710
eteenth-2.484
ORK-2.334
glers-2.295
IGHTS-2.281
Token action
Token ID2223
Feature activation+3.23e-01

Pos logit contributions
 spoiler+1.127
 dilig+1.065
 spoilers+1.051
emale+1.025
adium+0.974
Neg logit contributions
-1.689
eteenth-1.569
ORK-1.487
glers-1.461
IGHTS-1.460
Token on
Token ID319
Feature activation+2.23e-01

Pos logit contributions
+0.987
eteenth+0.906
ORK+0.847
glers+0.830
IGHTS+0.829
Neg logit contributions
 spoiler-0.919
 dilig-0.879
 spoilers-0.871
emale-0.862
adium-0.820
Token climate
Token ID4258
Feature activation+1.43e+00

Pos logit contributions
+0.644
eteenth+0.588
ORK+0.551
glers+0.538
IGHTS+0.537
Neg logit contributions
 spoiler-0.676
 dilig-0.647
 spoilers-0.640
emale-0.629
adium-0.604
Token change
Token ID1487
Feature activation+1.47e+00

Pos logit contributions
+3.092
eteenth+2.773
ORK+2.538
IGHTS+2.486
glers+2.447
Neg logit contributions
 spoiler-5.112
emale-5.052
 dilig-4.986
 spoilers-4.887
 tremend-4.758
Token considering
Token ID6402
Feature activation-4.57e-02

Pos logit contributions
+4.353
eteenth+4.011
ORK+3.814
glers+3.691
IGHTS+3.685
Neg logit contributions
 spoiler-4.065
 dilig-3.970
emale-3.968
 spoilers-3.841
 tremend-3.730
Token the
Token ID262
Feature activation+1.07e-01

Pos logit contributions
 spoiler+0.114
 dilig+0.109
 spoilers+0.107
emale+0.105
adium+0.100
Neg logit contributions
-0.155
eteenth-0.144
ORK-0.137
glers-0.134
IGHTS-0.134
Token amount
Token ID2033
Feature activation-8.44e-01

Pos logit contributions
+0.321
eteenth+0.294
ORK+0.275
glers+0.270
IGHTS+0.269
Neg logit contributions
 spoiler-0.309
 dilig-0.296
 spoilers-0.292
emale-0.288
adium-0.276
Token of
Token ID286
Feature activation-3.03e-01

Pos logit contributions
 spoiler+2.024
 dilig+1.909
 spoilers+1.890
emale+1.822
adium+1.749
Neg logit contributions
-2.977
eteenth-2.765
ORK-2.615
glers-2.564
IGHTS-2.562
Token money
Token ID1637
Feature activation-3.26e-01

Pos logit contributions
 spoiler+0.841
 dilig+0.797
 spoilers+0.792
emale+0.771
adium+0.741
Neg logit contributions
-0.957
eteenth-0.880
ORK-0.828
glers-0.811
IGHTS-0.809
Token forces
Token ID3386
Feature activation+1.51e-01

Pos logit contributions
+0.581
eteenth+0.539
ORK+0.511
glers+0.503
IGHTS+0.501
Neg logit contributions
 spoiler-0.367
 dilig-0.349
 spoilers-0.342
emale-0.339
adium-0.318
Token in
Token ID287
Feature activation+2.72e-01

Pos logit contributions
+0.484
eteenth+0.446
ORK+0.421
glers+0.412
IGHTS+0.412
Neg logit contributions
 spoiler-0.407
 dilig-0.389
 spoilers-0.384
emale-0.376
adium-0.360
Token the
Token ID262
Feature activation+5.34e-01

Pos logit contributions
+0.778
eteenth+0.712
ORK+0.662
glers+0.653
IGHTS+0.644
Neg logit contributions
 spoiler-0.825
 dilig-0.793
 spoilers-0.784
emale-0.776
adium-0.739
Token R
Token ID371
Feature activation+2.37e-01

Pos logit contributions
+1.575
eteenth+1.440
ORK+1.350
glers+1.328
IGHTS+1.315
Neg logit contributions
 spoiler-1.535
 dilig-1.495
 spoilers-1.458
emale-1.453
adium-1.390
TokenSI
Token ID11584
Feature activation+4.25e-01

Pos logit contributions
+0.690
eteenth+0.630
ORK+0.589
glers+0.575
IGHTS+0.575
Neg logit contributions
 spoiler-0.716
 dilig-0.684
 spoilers-0.678
emale-0.663
adium-0.638
Token also
Token ID635
Feature activation+4.90e-01

Pos logit contributions
+1.358
eteenth+1.244
ORK+1.171
IGHTS+1.153
glers+1.153
Neg logit contributions
 spoiler-1.146
 dilig-1.096
 spoilers-1.081
emale-1.059
adium-1.015
Token fought
Token ID8350
Feature activation+7.25e-01

Pos logit contributions
+1.550
eteenth+1.430
ORK+1.341
glers+1.327
IGHTS+1.326
Neg logit contributions
 spoiler-1.324
 dilig-1.268
 spoilers-1.252
emale-1.231
adium-1.178
Token against
Token ID1028
Feature activation+7.64e-03

Pos logit contributions
+2.110
eteenth+1.940
ORK+1.804
glers+1.780
IGHTS+1.768
Neg logit contributions
 spoiler-2.090
emale-2.015
 dilig-2.007
 spoilers-1.986
adium-1.911
Token the
Token ID262
Feature activation+2.26e-01

Pos logit contributions
+0.025
eteenth+0.023
ORK+0.022
glers+0.021
IGHTS+0.021
Neg logit contributions
 spoiler-0.020
 dilig-0.019
 spoilers-0.019
emale-0.019
adium-0.018
Token Allies
Token ID32430
Feature activation-2.31e-01

Pos logit contributions
+0.717
eteenth+0.661
ORK+0.621
glers+0.616
IGHTS+0.609
Neg logit contributions
 spoiler-0.606
 dilig-0.583
emale-0.568
 spoilers-0.568
adium-0.541
Token including
Token ID1390
Feature activation-1.93e-01

Pos logit contributions
 spoiler+0.636
 dilig+0.603
 spoilers+0.599
emale+0.585
adium+0.561
Neg logit contributions
-0.730
eteenth-0.672
ORK-0.632
glers-0.620
IGHTS-0.618
Token memor
Token ID16181
Feature activation+1.65e+00

Pos logit contributions
+1.981
eteenth+1.839
ORK+1.745
glers+1.717
IGHTS+1.717
Neg logit contributions
 spoiler-1.214
 dilig-1.138
 spoilers-1.115
emale-1.114
adium-1.036
Tokenanda
Token ID5282
Feature activation+3.85e-01

Pos logit contributions
+3.932
eteenth+3.691
ters+3.355
sts+3.268
glers+3.210
Neg logit contributions
 spoiler-5.627
 dilig-5.500
 spoilers-5.369
 tremend-5.311
emale-5.256
Token intended
Token ID5292
Feature activation+5.74e-04

Pos logit contributions
+1.193
eteenth+1.088
ORK+1.020
glers+1.000
IGHTS+1.000
Neg logit contributions
 spoiler-1.087
 dilig-1.037
 spoilers-1.029
emale-1.014
adium-0.965
Token to
Token ID284
Feature activation+2.65e-01

Pos logit contributions
+0.002
eteenth+0.002
ORK+0.002
glers+0.002
IGHTS+0.002
Neg logit contributions
 spoiler-0.002
 dilig-0.002
 spoilers-0.002
emale-0.001
adium-0.001
Token help
Token ID1037
Feature activation+2.93e-01

Pos logit contributions
+0.873
eteenth+0.804
ORK+0.759
glers+0.748
IGHTS+0.747
Neg logit contributions
 spoiler-0.687
 dilig-0.655
 spoilers-0.648
emale-0.638
adium-0.608
Token minority
Token ID9137
Feature activation+7.31e-01

Pos logit contributions
+0.943
eteenth+0.869
ORK+0.817
glers+0.803
IGHTS+0.799
Neg logit contributions
 spoiler-0.785
 dilig-0.742
 spoilers-0.741
emale-0.726
adium-0.695
Token communities
Token ID5348
Feature activation-1.52e-01

Pos logit contributions
+2.681
eteenth+2.500
ORK+2.365
glers+2.335
IGHTS+2.328
Neg logit contributions
 spoiler-1.641
 dilig-1.529
 spoilers-1.515
emale-1.476
adium-1.389
Token,
Token ID11
Feature activation-3.97e-02

Pos logit contributions
 spoiler+0.408
 dilig+0.387
 spoilers+0.384
emale+0.373
adium+0.358
Neg logit contributions
-0.492
eteenth-0.454
ORK-0.428
glers-0.419
IGHTS-0.418
Token as
Token ID355
Feature activation+2.14e-01

Pos logit contributions
 spoiler+0.113
 dilig+0.107
 spoilers+0.106
emale+0.104
adium+0.100
Neg logit contributions
-0.122
eteenth-0.112
ORK-0.105
glers-0.103
IGHTS-0.103
Token well
Token ID880
Feature activation-4.24e-01

Pos logit contributions
+0.706
eteenth+0.656
ORK+0.617
glers+0.606
IGHTS+0.605
Neg logit contributions
 spoiler-0.554
 dilig-0.525
 spoilers-0.521
emale-0.515
adium-0.486
Token as
Token ID355
Feature activation+5.01e-01

Pos logit contributions
 spoiler+1.166
 dilig+1.106
 spoilers+1.098
emale+1.070
adium+1.027
Neg logit contributions
-1.346
eteenth-1.239
ORK-1.166
glers-1.142
IGHTS-1.140
Token
Token ID198
Feature activation-2.03e-01

Pos logit contributions
 spoiler+0.834
 spoilers+0.789
 dilig+0.758
adium+0.745
emale+0.742
Neg logit contributions
-0.840
eteenth-0.772
ORK-0.720
glers-0.701
IGHTS-0.701
TokenO
Token ID46
Feature activation-2.83e-01

Pos logit contributions
 spoiler+0.642
 dilig+0.612
 spoilers+0.610
emale+0.595
adium+0.576
Neg logit contributions
-0.559
eteenth-0.507
ORK-0.472
glers-0.461
IGHTS-0.460
Tokenpin
Token ID11635
Feature activation-6.33e-01

Pos logit contributions
 spoiler+0.888
 dilig+0.850
 spoilers+0.842
emale+0.825
adium+0.797
Neg logit contributions
-0.783
eteenth-0.713
ORK-0.667
glers-0.654
IGHTS-0.649
Tokenion
Token ID295
Feature activation-4.04e-01

Pos logit contributions
 spoiler+1.352
 dilig+1.261
 spoilers+1.252
emale+1.208
adium+1.147
Neg logit contributions
-2.397
eteenth-2.235
ORK-2.127
glers-2.093
IGHTS-2.089
Token (
Token ID357
Feature activation+3.92e-04

Pos logit contributions
 spoiler+1.140
 dilig+1.085
 spoilers+1.076
emale+1.051
adium+1.009
Neg logit contributions
-1.255
eteenth-1.153
ORK-1.083
glers-1.060
IGHTS-1.059
Tokenby
Token ID1525
Feature activation+1.26e-01

Pos logit contributions
+0.001
eteenth+0.001
ORK+0.001
glers+0.001
IGHTS+0.001
Neg logit contributions
 spoiler-0.001
 dilig-0.001
 spoilers-0.001
emale-0.001
adium-0.001
Token Jesse
Token ID18033
Feature activation-7.97e-01

Pos logit contributions
+0.385
eteenth+0.353
ORK+0.332
glers+0.325
IGHTS+0.323
Neg logit contributions
 spoiler-0.356
 dilig-0.341
 spoilers-0.336
emale-0.332
adium-0.318
Token Smith
Token ID4176
Feature activation+1.75e-01

Pos logit contributions
 spoiler+2.750
 dilig+2.626
 spoilers+2.623
emale+2.555
adium+2.483
Neg logit contributions
-1.965
eteenth-1.763
ORK-1.628
glers-1.583
IGHTS-1.578
Token)
Token ID8
Feature activation+4.68e-01

Pos logit contributions
+0.438
eteenth+0.394
ORK+0.364
glers+0.354
IGHTS+0.353
Neg logit contributions
 spoiler-0.593
 dilig-0.573
 spoilers-0.566
emale-0.558
adium-0.541
Token
Token ID198
Feature activation-1.96e-02

Pos logit contributions
+1.303
eteenth+1.195
ORK+1.111
glers+1.093
IGHTS+1.091
Neg logit contributions
 spoiler-1.445
 dilig-1.391
 spoilers-1.371
emale-1.359
adium-1.303
Token
Token ID198
Feature activation-6.57e-02

Pos logit contributions
 spoiler+0.060
 spoilers+0.057
 dilig+0.056
emale+0.055
adium+0.054
Neg logit contributions
-0.056
eteenth-0.052
ORK-0.048
glers-0.047
IGHTS-0.047
Token if
Token ID611
Feature activation-7.39e-02

Pos logit contributions
+0.420
eteenth+0.387
ORK+0.365
IGHTS+0.358
glers+0.357
Neg logit contributions
 spoiler-0.339
 dilig-0.327
 spoilers-0.320
emale-0.315
adium-0.305
Token you
Token ID345
Feature activation-3.64e-01

Pos logit contributions
 spoiler+0.195
 dilig+0.186
 spoilers+0.183
emale+0.180
adium+0.173
Neg logit contributions
-0.242
eteenth-0.223
ORK-0.210
glers-0.206
IGHTS-0.205
Token
Token ID447
Feature activation-4.48e-01

Pos logit contributions
 spoiler+0.910
 dilig+0.856
 spoilers+0.850
emale+0.824
adium+0.787
Neg logit contributions
-1.251
eteenth-1.159
ORK-1.096
glers-1.075
IGHTS-1.074
Token
Token ID247
Feature activation+1.45e-02

Pos logit contributions
 spoiler+1.534
 spoilers+1.458
 dilig+1.457
emale+1.417
adium+1.378
Neg logit contributions
-1.126
eteenth-1.001
ORK-0.927
glers-0.911
IGHTS-0.903
Tokenre
Token ID260
Feature activation-3.04e-01

Pos logit contributions
+0.045
eteenth+0.041
ORK+0.038
glers+0.038
IGHTS+0.038
Neg logit contributions
 spoiler-0.042
 dilig-0.040
 spoilers-0.039
emale-0.038
adium-0.037
Token an
Token ID281
Feature activation+1.21e-01

Pos logit contributions
 spoiler+0.820
 dilig+0.777
 spoilers+0.771
emale+0.751
adium+0.720
Neg logit contributions
-0.984
eteenth-0.907
ORK-0.854
glers-0.838
IGHTS-0.836
Token emanc
Token ID37672
Feature activation-2.22e-01

Pos logit contributions
+0.416
eteenth+0.386
ORK+0.365
IGHTS+0.357
glers+0.357
Neg logit contributions
 spoiler-0.298
 dilig-0.282
 spoilers-0.279
emale-0.271
adium-0.259
Tokenip
Token ID541
Feature activation-5.41e-01

Pos logit contributions
 spoiler+0.724
 dilig+0.696
 spoilers+0.692
emale+0.672
adium+0.650
Neg logit contributions
-0.589
eteenth-0.539
ORK-0.495
IGHTS-0.485
glers-0.484
Tokenated
Token ID515
Feature activation-2.21e-01

Pos logit contributions
 spoiler+0.990
 dilig+0.914
 spoilers+0.904
emale+0.867
adium+0.813
Neg logit contributions
-2.215
eteenth-2.079
ORK-1.983
glers-1.954
IGHTS-1.951
Token American
Token ID1605
Feature activation-3.86e-01

Pos logit contributions
 spoiler+0.586
 dilig+0.553
 spoilers+0.550
emale+0.535
 volunt+0.511
Neg logit contributions
-0.721
eteenth-0.666
ORK-0.628
glers-0.617
IGHTS-0.615
Token woman
Token ID2415
Feature activation+3.82e-02

Pos logit contributions
 spoiler+1.035
 dilig+0.981
 spoilers+0.973
emale+0.948
adium+0.909
Neg logit contributions
-1.252
eteenth-1.154
ORK-1.087
glers-1.066
IGHTS-1.064
Tokenor
Token ID273
Feature activation+1.06e-01

Pos logit contributions
+1.550
eteenth+1.429
ORK+1.330
glers+1.292
IGHTS+1.282
Neg logit contributions
 spoiler-1.722
 dilig-1.707
 spoilers-1.648
emale-1.621
 tremend-1.614
Token
Token ID198
Feature activation+1.39e-01

Pos logit contributions
+0.289
eteenth+0.262
ORK+0.244
glers+0.238
IGHTS+0.238
Neg logit contributions
 spoiler-0.338
 dilig-0.325
 spoilers-0.322
emale-0.315
adium-0.304
Token
Token ID198
Feature activation+1.32e-01

Pos logit contributions
+0.386
eteenth+0.351
ORK+0.327
glers+0.320
IGHTS+0.319
Neg logit contributions
 spoiler-0.436
 dilig-0.419
 spoilers-0.414
emale-0.407
adium-0.391
Tokenspons
Token ID20587
Feature activation+5.28e-01

Pos logit contributions
+0.357
eteenth+0.323
ORK+0.300
IGHTS+0.293
glers+0.291
Neg logit contributions
 spoiler-0.427
 dilig-0.411
 spoilers-0.406
emale-0.397
 volunt-0.385
Tokenor
Token ID273
Feature activation+9.13e-02

Pos logit contributions
+1.471
eteenth+1.355
ORK+1.261
glers+1.226
IGHTS+1.218
Neg logit contributions
 spoiler-1.625
 dilig-1.608
 spoilers-1.554
emale-1.529
 tremend-1.519
Token
Token ID198
Feature activation+1.19e-01

Pos logit contributions
+0.249
eteenth+0.226
ORK+0.210
glers+0.205
IGHTS+0.205
Neg logit contributions
 spoiler-0.290
 dilig-0.279
 spoilers-0.276
emale-0.270
adium-0.261
Token
Token ID198
Feature activation+1.12e-01

Pos logit contributions
+0.330
eteenth+0.300
ORK+0.280
glers+0.273
IGHTS+0.273
Neg logit contributions
 spoiler-0.372
 dilig-0.357
 spoilers-0.353
emale-0.346
adium-0.333
Tokenspons
Token ID20587
Feature activation+5.04e-01

Pos logit contributions
+0.302
eteenth+0.273
ORK+0.254
IGHTS+0.248
glers+0.246
Neg logit contributions
 spoiler-0.360
 dilig-0.347
 spoilers-0.342
emale-0.335
 volunt-0.324
Tokenor
Token ID273
Feature activation+7.47e-02

Pos logit contributions
+1.406
eteenth+1.295
ORK+1.206
glers+1.173
IGHTS+1.165
Neg logit contributions
 spoiler-1.547
 dilig-1.529
 spoilers-1.479
emale-1.455
 tremend-1.443
Token
Token ID198
Feature activation+1.05e-01

Pos logit contributions
+0.204
eteenth+0.185
ORK+0.172
glers+0.168
IGHTS+0.168
Neg logit contributions
 spoiler-0.237
 dilig-0.228
 spoilers-0.226
emale-0.221
adium-0.213
Token
Token ID198
Feature activation+9.63e-02

Pos logit contributions
+0.294
eteenth+0.268
ORK+0.249
glers+0.244
IGHTS+0.243
Neg logit contributions
 spoiler-0.330
 dilig-0.316
 spoilers-0.313
emale-0.307
adium-0.296
Token was
Token ID373
Feature activation+1.86e-01

Pos logit contributions
+2.469
eteenth+2.238
ORK+2.136
glers+2.082
ters+2.059
Neg logit contributions
 spoiler-2.181
 dilig-2.087
 spoilers-2.068
emale-2.059
adium-1.939
Token the
Token ID262
Feature activation+1.13e-01

Pos logit contributions
+0.588
eteenth+0.540
ORK+0.511
IGHTS+0.498
glers+0.496
Neg logit contributions
 spoiler-0.507
 dilig-0.486
 spoilers-0.478
emale-0.477
adium-0.451
Token one
Token ID530
Feature activation-9.95e-03

Pos logit contributions
+0.363
eteenth+0.333
ORK+0.313
glers+0.308
IGHTS+0.307
Neg logit contributions
 spoiler-0.306
 dilig-0.294
 spoilers-0.289
emale-0.286
adium-0.272
Token that
Token ID326
Feature activation+5.40e-01

Pos logit contributions
 spoiler+0.025
 dilig+0.024
 spoilers+0.024
emale+0.024
adium+0.022
Neg logit contributions
-0.033
eteenth-0.031
ORK-0.029
glers-0.029
IGHTS-0.028
Token just
Token ID655
Feature activation+8.12e-01

Pos logit contributions
+1.724
eteenth+1.575
ORK+1.491
glers+1.466
IGHTS+1.465
Neg logit contributions
 spoiler-1.445
 dilig-1.385
 spoilers-1.365
emale-1.365
adium-1.286
Token kind
Token ID1611
Feature activation-3.64e-01

Pos logit contributions
+2.524
eteenth+2.314
ORK+2.160
IGHTS+2.144
glers+2.131
Neg logit contributions
 spoiler-2.234
 dilig-2.146
 spoilers-2.110
emale-2.109
adium-1.989
Token of
Token ID286
Feature activation+7.88e-02

Pos logit contributions
 spoiler+0.875
 dilig+0.816
 spoilers+0.816
emale+0.785
adium+0.754
Neg logit contributions
-1.285
eteenth-1.191
ORK-1.129
glers-1.109
IGHTS-1.108
Token haunted
Token ID26688
Feature activation+6.62e-01

Pos logit contributions
+0.253
eteenth+0.233
ORK+0.219
glers+0.216
IGHTS+0.215
Neg logit contributions
 spoiler-0.212
 dilig-0.202
 spoilers-0.199
emale-0.197
adium-0.188
Token all
Token ID477
Feature activation+4.28e-01

Pos logit contributions
+2.180
eteenth+1.981
ORK+1.917
glers+1.875
IGHTS+1.857
Neg logit contributions
 spoiler-1.677
 dilig-1.604
emale-1.598
 spoilers-1.577
adium-1.490
Token of
Token ID286
Feature activation+6.84e-01

Pos logit contributions
+1.382
eteenth+1.261
ORK+1.211
glers+1.184
IGHTS+1.171
Neg logit contributions
 spoiler-1.113
emale-1.058
 dilig-1.057
 spoilers-1.048
adium-0.987
Token us
Token ID514
Feature activation+5.57e-01

Pos logit contributions
+1.937
eteenth+1.729
ORK+1.652
glers+1.638
ters+1.614
Neg logit contributions
 spoiler-2.037
 dilig-1.962
emale-1.952
 spoilers-1.937
adium-1.846
Token V
Token ID569
Feature activation-2.74e-01

Pos logit contributions
 spoiler+0.307
 dilig+0.292
 spoilers+0.290
emale+0.284
adium+0.272
Neg logit contributions
-0.311
eteenth-0.284
ORK-0.266
glers-0.260
IGHTS-0.260
Tokenivid
Token ID1699
Feature activation-4.68e-01

Pos logit contributions
 spoiler+0.850
 dilig+0.812
 spoilers+0.806
emale+0.790
adium+0.765
Neg logit contributions
-0.774
eteenth-0.703
ORK-0.654
glers-0.644
IGHTS-0.638
Token Audio
Token ID13491
Feature activation+1.02e+00

Pos logit contributions
 spoiler+1.397
 dilig+1.330
 spoilers+1.322
emale+1.292
adium+1.250
Neg logit contributions
-1.368
eteenth-1.253
ORK-1.171
glers-1.148
IGHTS-1.144
Token --
Token ID1377
Feature activation-2.08e-01

Pos logit contributions
+3.124
eteenth+2.801
ORK+2.654
IGHTS+2.586
glers+2.576
Neg logit contributions
 spoiler-2.867
 dilig-2.735
 spoilers-2.693
emale-2.678
 volunt-2.555
Token and
Token ID290
Feature activation+2.87e-01

Pos logit contributions
 spoiler+0.556
 dilig+0.528
 spoilers+0.523
emale+0.511
adium+0.489
Neg logit contributions
-0.677
eteenth-0.623
ORK-0.587
glers-0.576
IGHTS-0.574
Token their
Token ID511
Feature activation-2.27e-01

Pos logit contributions
+0.931
eteenth+0.847
ORK+0.802
glers+0.792
IGHTS+0.786
Neg logit contributions
 spoiler-0.754
 dilig-0.725
 spoilers-0.710
emale-0.706
adium-0.673
Token lowest
Token ID9016
Feature activation+3.86e-01

Pos logit contributions
 spoiler+0.628
 dilig+0.595
 spoilers+0.592
emale+0.576
adium+0.553
Neg logit contributions
-0.716
eteenth-0.660
ORK-0.620
glers-0.608
IGHTS-0.606
Token-
Token ID12
Feature activation-2.88e-01

Pos logit contributions
+1.171
eteenth+1.067
ORK+1.007
IGHTS+0.986
glers+0.981
Neg logit contributions
 spoiler-1.093
 dilig-1.061
 spoilers-1.030
emale-1.030
 volunt-0.984
Tokenpriced
Token ID30883
Feature activation-3.72e-01

Pos logit contributions
 spoiler+0.807
 dilig+0.768
 spoilers+0.761
emale+0.743
adium+0.713
Neg logit contributions
-0.900
eteenth-0.827
ORK-0.777
glers-0.762
IGHTS-0.760
Token models
Token ID4981
Feature activation-2.99e-01

Pos logit contributions
 spoiler+1.084
 spoilers+1.026
 dilig+1.017
emale+0.986
adium+0.957
Neg logit contributions
-1.123
eteenth-1.037
ORK-0.971
glers-0.950
IGHTS-0.947
Token cost
Token ID1575
Feature activation-3.98e-01

Pos logit contributions
 spoiler+0.764
 dilig+0.725
 spoilers+0.717
emale+0.700
adium+0.669
Neg logit contributions
-1.004
eteenth-0.928
ORK-0.877
glers-0.861
IGHTS-0.860
Token what
Token ID644
Feature activation-7.29e-01

Pos logit contributions
+0.694
eteenth+0.639
ORK+0.599
IGHTS+0.593
glers+0.591
Neg logit contributions
 spoiler-0.605
 dilig-0.578
 spoilers-0.567
emale-0.563
adium-0.537
Token the
Token ID262
Feature activation-1.49e-01

Pos logit contributions
 spoiler+1.910
 dilig+1.798
 spoilers+1.795
emale+1.713
adium+1.659
Neg logit contributions
-2.413
eteenth-2.234
ORK-2.108
glers-2.057
IGHTS-2.050
Token shop
Token ID6128
Feature activation-2.22e-01

Pos logit contributions
 spoiler+0.421
 dilig+0.401
 spoilers+0.397
emale+0.390
adium+0.374
Neg logit contributions
-0.462
eteenth-0.424
ORK-0.398
glers-0.391
IGHTS-0.390
Token
Token ID447
Feature activation+1.80e-01

Pos logit contributions
 spoiler+0.603
 dilig+0.572
 spoilers+0.567
emale+0.557
adium+0.530
Neg logit contributions
-0.713
eteenth-0.657
ORK-0.617
glers-0.610
IGHTS-0.605
Token
Token ID247
Feature activation+2.16e-01

Pos logit contributions
+0.451
eteenth+0.413
ORK+0.378
IGHTS+0.367
glers+0.363
Neg logit contributions
 spoiler-0.612
 dilig-0.589
 spoilers-0.585
emale-0.578
adium-0.556
Tokens
Token ID82
Feature activation-7.07e-02

Pos logit contributions
+0.655
eteenth+0.603
ORK+0.562
IGHTS+0.553
glers+0.552
Neg logit contributions
 spoiler-0.622
 dilig-0.593
 spoilers-0.588
emale-0.574
 volunt-0.551
Token security
Token ID2324
Feature activation-1.82e+00

Pos logit contributions
 spoiler+0.191
 dilig+0.182
 spoilers+0.180
emale+0.177
adium+0.169
Neg logit contributions
-0.227
eteenth-0.209
ORK-0.196
IGHTS-0.194
glers-0.193
Token system
Token ID1080
Feature activation-2.78e-01

Pos logit contributions
 spoiler+5.222
 spoilers+4.942
 dilig+4.931
emale+4.656
 lockout+4.635
Neg logit contributions
-5.502
eteenth-5.090
ORK-4.777
glers-4.651
IGHTS-4.596
Token recorded
Token ID6264
Feature activation+1.92e-02

Pos logit contributions
 spoiler+0.757
 dilig+0.721
 spoilers+0.713
emale+0.700
adium+0.669
Neg logit contributions
-0.888
eteenth-0.817
ORK-0.768
IGHTS-0.756
glers-0.755
Token during
Token ID1141
Feature activation-7.68e-01

Pos logit contributions
+0.060
eteenth+0.054
ORK+0.051
IGHTS+0.050
glers+0.050
Neg logit contributions
 spoiler-0.054
 dilig-0.052
 spoilers-0.051
emale-0.050
adium-0.048
Token the
Token ID262
Feature activation+1.50e-02

Pos logit contributions
 spoiler+1.975
 dilig+1.867
 spoilers+1.852
emale+1.801
adium+1.724
Neg logit contributions
-2.578
eteenth-2.383
ORK-2.250
glers-2.208
IGHTS-2.204
Token it
Token ID340
Feature activation+6.18e-03

Pos logit contributions
 spoiler+1.135
 dilig+1.074
 spoilers+1.068
emale+1.035
adium+0.992
Neg logit contributions
-1.415
eteenth-1.305
ORK-1.231
glers-1.205
IGHTS-1.204
Token is
Token ID318
Feature activation+1.47e-02

Pos logit contributions
+0.021
eteenth+0.020
ORK+0.018
glers+0.018
IGHTS+0.018
Neg logit contributions
 spoiler-0.015
 dilig-0.015
 spoilers-0.014
emale-0.014
adium-0.013
Token discreet
Token ID38724
Feature activation-1.13e-01

Pos logit contributions
+0.046
eteenth+0.042
ORK+0.040
glers+0.039
IGHTS+0.039
Neg logit contributions
 spoiler-0.041
 dilig-0.039
 spoilers-0.038
emale-0.038
adium-0.036
Token.
Token ID13
Feature activation-1.86e-01

Pos logit contributions
 spoiler+0.313
 dilig+0.298
 spoilers+0.294
emale+0.290
adium+0.277
Neg logit contributions
-0.358
eteenth-0.328
ORK-0.307
glers-0.304
IGHTS-0.300
Token It
Token ID632
Feature activation+2.37e-01

Pos logit contributions
 spoiler+0.516
 dilig+0.488
 spoilers+0.486
emale+0.473
adium+0.455
Neg logit contributions
-0.586
eteenth-0.540
ORK-0.507
glers-0.496
IGHTS-0.496
Token ref
Token ID1006
Feature activation-5.99e-02

Pos logit contributions
+0.807
eteenth+0.747
ORK+0.702
glers+0.696
IGHTS+0.692
Neg logit contributions
 spoiler-0.591
 dilig-0.562
 spoilers-0.554
emale-0.543
adium-0.518
Tokenr
Token ID81
Feature activation-5.78e-01

Pos logit contributions
 spoiler+0.177
 dilig+0.169
 spoilers+0.167
emale+0.161
 volunt+0.156
Neg logit contributions
-0.178
eteenth-0.164
ORK-0.153
glers-0.150
IGHTS-0.149
Tokenains
Token ID1299
Feature activation-1.91e-02

Pos logit contributions
 spoiler+1.698
 dilig+1.617
 spoilers+1.604
emale+1.564
adium+1.504
Neg logit contributions
-1.732
eteenth-1.586
ORK-1.484
glers-1.454
IGHTS-1.453
Token from
Token ID422
Feature activation+3.34e-01

Pos logit contributions
 spoiler+0.046
 dilig+0.044
 spoilers+0.043
emale+0.042
adium+0.040
Neg logit contributions
-0.067
eteenth-0.062
ORK-0.058
glers-0.057
IGHTS-0.057
Token prose
Token ID27149
Feature activation-2.57e-01

Pos logit contributions
+1.036
eteenth+0.950
ORK+0.892
glers+0.874
IGHTS+0.873
Neg logit contributions
 spoiler-0.922
 dilig-0.889
emale-0.871
 spoilers-0.865
adium-0.827
Tokenly
Token ID306
Feature activation-3.34e-01

Pos logit contributions
 spoiler+0.701
 dilig+0.668
 spoilers+0.660
emale+0.649
adium+0.622
Neg logit contributions
-0.820
eteenth-0.755
ORK-0.709
glers-0.697
IGHTS-0.694
Token in
Token ID287
Feature activation-2.07e-01

Pos logit contributions
 spoiler+1.439
 dilig+1.367
 spoilers+1.347
emale+1.296
 volunt+1.258
Neg logit contributions
-1.861
eteenth-1.718
ORK-1.632
glers-1.599
IGHTS-1.587
Token employment
Token ID7184
Feature activation-2.21e-01

Pos logit contributions
 spoiler+0.543
 dilig+0.513
 spoilers+0.509
emale+0.492
adium+0.474
Neg logit contributions
-0.687
eteenth-0.635
ORK-0.599
glers-0.588
IGHTS-0.586
Token,
Token ID11
Feature activation-1.89e-01

Pos logit contributions
 spoiler+0.604
 dilig+0.572
 spoilers+0.568
emale+0.552
adium+0.530
Neg logit contributions
-0.705
eteenth-0.649
ORK-0.611
glers-0.599
IGHTS-0.598
Token qualify
Token ID12780
Feature activation+2.48e-01

Pos logit contributions
 spoiler+0.498
 dilig+0.471
 spoilers+0.468
emale+0.455
adium+0.436
Neg logit contributions
-0.624
eteenth-0.576
ORK-0.543
glers-0.533
IGHTS-0.532
Token for
Token ID329
Feature activation-1.98e-01

Pos logit contributions
+0.830
eteenth+0.763
ORK+0.720
glers+0.709
IGHTS+0.706
Neg logit contributions
 spoiler-0.642
 dilig-0.605
 spoilers-0.603
emale-0.586
adium-0.560
Token benefits
Token ID4034
Feature activation-9.89e-01

Pos logit contributions
 spoiler+0.529
 dilig+0.501
 spoilers+0.497
emale+0.483
adium+0.464
Neg logit contributions
-0.642
eteenth-0.592
ORK-0.558
glers-0.547
IGHTS-0.546
Token,
Token ID11
Feature activation-8.54e-02

Pos logit contributions
 spoiler+2.641
 dilig+2.500
 spoilers+2.484
emale+2.388
 volunt+2.314
Neg logit contributions
-3.199
eteenth-2.964
ORK-2.783
glers-2.741
IGHTS-2.727
Token access
Token ID1895
Feature activation-2.68e-01

Pos logit contributions
 spoiler+0.224
 dilig+0.212
 spoilers+0.210
emale+0.205
adium+0.196
Neg logit contributions
-0.282
eteenth-0.260
ORK-0.245
glers-0.241
IGHTS-0.240
Token education
Token ID3707
Feature activation-6.37e-01

Pos logit contributions
 spoiler+0.724
 dilig+0.688
 spoilers+0.682
emale+0.662
adium+0.637
Neg logit contributions
-0.862
eteenth-0.794
ORK-0.748
glers-0.732
IGHTS-0.730
Token and
Token ID290
Feature activation-2.13e-01

Pos logit contributions
 spoiler+1.726
 dilig+1.636
 spoilers+1.626
emale+1.576
adium+1.516
Neg logit contributions
-2.046
eteenth-1.886
ORK-1.773
glers-1.740
IGHTS-1.735
Token healthcare
Token ID11409
Feature activation-6.85e-01

Pos logit contributions
 spoiler+0.560
 dilig+0.530
 spoilers+0.526
emale+0.512
adium+0.490
Neg logit contributions
-0.704
eteenth-0.650
ORK-0.613
glers-0.601
IGHTS-0.600
Token accordingly
Token ID16062
Feature activation-8.99e-01

Pos logit contributions
+2.845
eteenth+2.609
ORK+2.478
IGHTS+2.436
glers+2.381
Neg logit contributions
 spoiler-2.405
 dilig-2.358
 spoilers-2.311
emale-2.285
adium-2.228
Token.
Token ID13
Feature activation-2.43e-01

Pos logit contributions
 spoiler+2.307
 dilig+2.168
 spoilers+2.158
emale+2.093
adium+1.991
Neg logit contributions
-3.020
eteenth-2.797
ORK-2.646
glers-2.596
IGHTS-2.585
Token<|endoftext|>
Token ID50256
Feature activation+9.38e-01

Pos logit contributions
 spoiler+0.700
 dilig+0.671
 spoilers+0.662
emale+0.649
adium+0.622
Neg logit contributions
-0.738
eteenth-0.675
ORK-0.635
glers-0.621
IGHTS-0.621
TokenStory
Token ID11605
Feature activation-3.12e-01

Pos logit contributions
+2.501
eteenth+2.243
ORK+2.120
IGHTS+2.064
glers+2.032
Neg logit contributions
 spoiler-3.046
 dilig-2.991
 spoilers-2.892
emale-2.867
 tremend-2.795
Token highlights
Token ID11330
Feature activation+2.17e-01

Pos logit contributions
 spoiler+0.728
 dilig+0.686
 spoilers+0.678
emale+0.663
adium+0.628
Neg logit contributions
-1.120
eteenth-1.042
ORK-0.987
IGHTS-0.969
glers-0.968
Token Police
Token ID4287
Feature activation-1.15e+00

Pos logit contributions
+0.637
eteenth+0.582
ORK+0.546
IGHTS+0.537
glers+0.535
Neg logit contributions
 spoiler-0.643
 dilig-0.624
 spoilers-0.607
emale-0.598
 tremend-0.581
Token chief
Token ID4039
Feature activation-3.30e-01

Pos logit contributions
 spoiler+2.766
 spoilers+2.585
 dilig+2.554
emale+2.435
 volunt+2.368
Neg logit contributions
-4.062
eteenth-3.776
ORK-3.563
glers-3.499
IGHTS-3.485
Token vows
Token ID36605
Feature activation-1.28e-01

Pos logit contributions
 spoiler+0.877
 dilig+0.833
 spoilers+0.825
emale+0.806
adium+0.771
Neg logit contributions
-1.077
eteenth-0.994
ORK-0.936
glers-0.918
IGHTS-0.917
Token wanted
Token ID2227
Feature activation-4.55e-01

Pos logit contributions
 spoiler+0.350
 dilig+0.335
 spoilers+0.329
emale+0.327
adium+0.311
Neg logit contributions
-0.407
eteenth-0.374
ORK-0.353
glers-0.345
IGHTS-0.345
Token suspect
Token ID4099
Feature activation-3.03e-01

Pos logit contributions
 spoiler+1.204
 dilig+1.137
 spoilers+1.132
emale+1.097
adium+1.053
Neg logit contributions
-1.498
eteenth-1.382
ORK-1.303
glers-1.277
IGHTS-1.276
Token "
Token ID366
Feature activation+1.28e-01

Pos logit contributions
 spoiler+0.790
 dilig+0.753
 spoilers+0.742
emale+0.733
adium+0.695
Neg logit contributions
-1.001
eteenth-0.925
ORK-0.871
glers-0.856
IGHTS-0.855
TokenIndeed
Token ID17854
Feature activation-4.12e-01

Pos logit contributions
 spoiler+1.025
 spoilers+0.972
 dilig+0.971
emale+0.948
adium+0.917
Neg logit contributions
-0.914
eteenth-0.832
ORK-0.775
glers-0.760
IGHTS-0.754
Token,
Token ID11
Feature activation-9.33e-02

Pos logit contributions
 spoiler+1.115
 dilig+1.060
 spoilers+1.048
emale+1.025
adium+0.985
Neg logit contributions
-1.327
eteenth-1.223
ORK-1.150
glers-1.126
IGHTS-1.126
Token this
Token ID428
Feature activation-1.46e-01

Pos logit contributions
 spoiler+0.256
 dilig+0.245
 spoilers+0.241
emale+0.237
adium+0.227
Neg logit contributions
-0.295
eteenth-0.272
ORK-0.256
glers-0.250
IGHTS-0.250
Token idea
Token ID2126
Feature activation+3.26e-01

Pos logit contributions
 spoiler+0.378
 dilig+0.362
 spoilers+0.356
emale+0.351
adium+0.336
Neg logit contributions
-0.483
eteenth-0.446
ORK-0.421
glers-0.412
IGHTS-0.412
Token of
Token ID286
Feature activation+1.83e-01

Pos logit contributions
+1.107
eteenth+1.024
ORK+0.957
IGHTS+0.939
glers+0.937
Neg logit contributions
 spoiler-0.810
 dilig-0.781
 spoilers-0.759
emale-0.759
adium-0.714
Token what
Token ID644
Feature activation-1.20e+00

Pos logit contributions
+0.575
eteenth+0.530
ORK+0.496
IGHTS+0.487
glers+0.484
Neg logit contributions
 spoiler-0.501
 dilig-0.479
 spoilers-0.472
emale-0.466
adium-0.446
Token it
Token ID340
Feature activation-1.20e-01

Pos logit contributions
 spoiler+3.110
 spoilers+2.916
 dilig+2.900
emale+2.759
 volunt+2.686
Neg logit contributions
-4.057
eteenth-3.730
ORK-3.542
glers-3.506
IGHTS-3.427
Token means
Token ID1724
Feature activation-3.75e-01

Pos logit contributions
 spoiler+0.304
 dilig+0.289
 spoilers+0.286
emale+0.279
adium+0.267
Neg logit contributions
-0.410
eteenth-0.378
ORK-0.356
IGHTS-0.350
glers-0.349
Token to
Token ID284
Feature activation-1.67e-01

Pos logit contributions
 spoiler+1.030
 dilig+0.977
 spoilers+0.970
emale+0.945
adium+0.907
Neg logit contributions
-1.192
eteenth-1.097
ORK-1.032
glers-1.012
IGHTS-1.010
Token truly
Token ID4988
Feature activation+6.53e-01

Pos logit contributions
 spoiler+0.437
 dilig+0.415
 spoilers+0.411
emale+0.401
adium+0.384
Neg logit contributions
-0.549
eteenth-0.507
ORK-0.478
IGHTS-0.468
glers-0.468
Token be
Token ID307
Feature activation+1.15e-01

Pos logit contributions
+2.060
eteenth+1.893
ORK+1.783
IGHTS+1.754
glers+1.723
Neg logit contributions
 spoiler-1.753
 dilig-1.681
 spoilers-1.659
emale-1.650
adium-1.585
Token Mark
Token ID2940
Feature activation-1.34e+00

Pos logit contributions
 spoiler+0.295
 dilig+0.280
 spoilers+0.277
emale+0.271
adium+0.260
Neg logit contributions
-0.363
eteenth-0.335
ORK-0.315
glers-0.309
IGHTS-0.309
Token Ham
Token ID4345
Feature activation+3.47e-01

Pos logit contributions
 spoiler+3.439
 spoilers+3.219
 dilig+3.071
adium+3.059
emale+3.044
Neg logit contributions
-4.492
eteenth-4.060
ORK-3.905
IGHTS-3.826
glers-3.814
Tokenill
Token ID359
Feature activation+3.08e-01

Pos logit contributions
+0.924
eteenth+0.842
ORK+0.774
glers+0.759
IGHTS+0.754
Neg logit contributions
 spoiler-1.121
 dilig-1.083
 spoilers-1.066
emale-1.049
adium-1.010
Token,
Token ID11
Feature activation-2.05e-02

Pos logit contributions
+0.989
eteenth+0.910
ORK+0.848
IGHTS+0.840
glers+0.832
Neg logit contributions
 spoiler-0.828
 dilig-0.797
 spoilers-0.779
emale-0.773
adium-0.740
Token best
Token ID1266
Feature activation-1.24e-01

Pos logit contributions
 spoiler+0.055
 dilig+0.052
 spoilers+0.052
emale+0.051
adium+0.049
Neg logit contributions
-0.066
eteenth-0.061
ORK-0.057
glers-0.056
IGHTS-0.056
Token known
Token ID1900
Feature activation-1.31e+00

Pos logit contributions
 spoiler+0.290
 dilig+0.276
 spoilers+0.271
emale+0.266
adium+0.252
Neg logit contributions
-0.444
eteenth-0.412
ORK-0.392
glers-0.382
IGHTS-0.381
Token for
Token ID329
Feature activation-3.17e-02

Pos logit contributions
 spoiler+3.184
 spoilers+2.959
 dilig+2.947
emale+2.826
adium+2.717
Neg logit contributions
-4.550
eteenth-4.258
ORK-4.063
IGHTS-3.973
glers-3.940
Token playing
Token ID2712
Feature activation-7.20e-01

Pos logit contributions
 spoiler+0.091
 dilig+0.087
 spoilers+0.086
emale+0.084
adium+0.081
Neg logit contributions
-0.097
eteenth-0.089
ORK-0.083
glers-0.081
IGHTS-0.081
Token Luke
Token ID11336
Feature activation-3.23e-01

Pos logit contributions
 spoiler+1.993
 dilig+1.877
 spoilers+1.873
emale+1.805
adium+1.739
Neg logit contributions
-2.286
eteenth-2.104
ORK-1.981
IGHTS-1.937
glers-1.935
Token Skywalker
Token ID29715
Feature activation+2.06e-01

Pos logit contributions
 spoiler+1.018
 dilig+0.978
 spoilers+0.968
emale+0.956
adium+0.918
Neg logit contributions
-0.890
eteenth-0.810
ORK-0.753
glers-0.734
IGHTS-0.733
Token in
Token ID287
Feature activation-2.28e-01

Pos logit contributions
+0.617
eteenth+0.564
ORK+0.526
glers+0.516
IGHTS+0.516
Neg logit contributions
 spoiler-0.595
 dilig-0.574
 spoilers-0.564
emale-0.563
adium-0.536
Token on
Token ID319
Feature activation+1.59e-01

Pos logit contributions
 spoiler+0.411
 dilig+0.390
 spoilers+0.388
emale+0.375
adium+0.362
Neg logit contributions
-0.450
eteenth-0.413
ORK-0.389
glers-0.380
IGHTS-0.379
Token average
Token ID2811
Feature activation-6.13e-01

Pos logit contributions
+0.443
eteenth+0.403
ORK+0.376
glers+0.368
IGHTS+0.366
Neg logit contributions
 spoiler-0.493
 dilig-0.476
 spoilers-0.470
emale-0.465
adium-0.446
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
 spoiler+1.627
 dilig+1.541
 spoilers+1.528
emale+1.489
adium+1.427
Neg logit contributions
-2.008
eteenth-1.852
ORK-1.745
glers-1.711
IGHTS-1.708
Token In
Token ID554
Feature activation-1.28e-01

Pos logit contributions
 spoiler+0.610
 dilig+0.581
 spoilers+0.577
emale+0.564
adium+0.543
Neg logit contributions
-0.596
eteenth-0.545
ORK-0.509
glers-0.498
IGHTS-0.497
Token Mid
Token ID7215
Feature activation+3.39e-01

Pos logit contributions
 spoiler+0.370
 dilig+0.353
 spoilers+0.350
emale+0.342
adium+0.329
Neg logit contributions
-0.387
eteenth-0.355
ORK-0.333
glers-0.326
IGHTS-0.325
Tokenwestern
Token ID14197
Feature activation-1.29e+00

Pos logit contributions
+0.873
eteenth+0.797
ORK+0.729
glers+0.716
IGHTS+0.706
Neg logit contributions
 spoiler-1.136
 dilig-1.093
 spoilers-1.082
emale-1.064
adium-1.023
Token counties
Token ID14683
Feature activation-7.84e-01

Pos logit contributions
 spoiler+3.639
 spoilers+3.418
 dilig+3.360
emale+3.188
 volunt+3.140
Neg logit contributions
-4.052
eteenth-3.717
ORK-3.497
IGHTS-3.435
glers-3.403
Token with
Token ID351
Feature activation-5.05e-01

Pos logit contributions
 spoiler+2.086
 dilig+1.959
 spoilers+1.953
emale+1.882
adium+1.810
Neg logit contributions
-2.571
eteenth-2.377
ORK-2.238
glers-2.196
IGHTS-2.190
Token high
Token ID1029
Feature activation+1.67e-01

Pos logit contributions
 spoiler+1.563
 dilig+1.486
 spoilers+1.484
emale+1.437
adium+1.391
Neg logit contributions
-1.435
eteenth-1.303
ORK-1.221
IGHTS-1.192
glers-1.188
Token mortality
Token ID12430
Feature activation-8.99e-01

Pos logit contributions
+0.524
eteenth+0.482
ORK+0.453
glers+0.444
IGHTS+0.444
Neg logit contributions
 spoiler-0.463
 dilig-0.441
 spoilers-0.435
emale-0.427
adium-0.409
Token rates
Token ID3965
Feature activation-6.51e-01

Pos logit contributions
 spoiler+2.494
 dilig+2.360
 spoilers+2.358
emale+2.262
adium+2.188
Neg logit contributions
-2.833
eteenth-2.611
ORK-2.450
glers-2.405
IGHTS-2.388
Token
Token ID141
Feature activation+2.43e-01

Pos logit contributions
 spoiler+0.069
 dilig+0.067
 spoilers+0.066
emale+0.065
adium+0.063
Neg logit contributions
-0.044
eteenth-0.039
ORK-0.036
glers-0.034
IGHTS-0.034
Token
Token ID230
Feature activation+1.19e-01

Pos logit contributions
+0.650
eteenth+0.597
ORK+0.550
IGHTS+0.535
glers+0.532
Neg logit contributions
 spoiler-0.791
 dilig-0.758
 spoilers-0.750
emale-0.739
adium-0.707
Tokenи
Token ID18849
Feature activation-2.73e-01

Pos logit contributions
+0.266
eteenth+0.235
ORK+0.215
IGHTS+0.208
glers+0.207
Neg logit contributions
 spoiler-0.442
 dilig-0.425
 spoilers-0.422
emale-0.415
adium-0.402
Token
Token ID141
Feature activation-3.88e-02

Pos logit contributions
 spoiler+0.918
 dilig+0.880
 spoilers+0.874
emale+0.856
adium+0.828
Neg logit contributions
-0.701
eteenth-0.632
ORK-0.584
glers-0.569
IGHTS-0.568
Token
Token ID227
Feature activation-1.35e-01

Pos logit contributions
 spoiler+0.130
 dilig+0.125
 spoilers+0.123
emale+0.121
adium+0.117
Neg logit contributions
-0.100
eteenth-0.091
ORK-0.084
glers-0.082
IGHTS-0.082
Token
Token ID12466
Feature activation-1.26e+00

Pos logit contributions
 spoiler+0.382
 dilig+0.364
 spoilers+0.360
emale+0.352
adium+0.338
Neg logit contributions
-0.419
eteenth-0.385
ORK-0.362
glers-0.353
IGHTS-0.353
Token
Token ID121
Feature activation-2.48e-01

Pos logit contributions
 spoiler+3.998
 dilig+3.834
 spoilers+3.803
emale+3.717
adium+3.590
Neg logit contributions
-3.353
eteenth-3.043
ORK-2.837
IGHTS-2.786
glers-2.784
Tokenа
Token ID16142
Feature activation+4.49e-02

Pos logit contributions
 spoiler+0.915
 dilig+0.883
 spoilers+0.876
emale+0.860
adium+0.832
Neg logit contributions
-0.557
eteenth-0.493
ORK-0.452
glers-0.436
IGHTS-0.435
Tokenм
Token ID43108
Feature activation-3.04e-01

Pos logit contributions
+0.129
eteenth+0.117
ORK+0.109
glers+0.106
IGHTS+0.105
Neg logit contributions
 spoiler-0.138
 dilig-0.132
 spoilers-0.130
emale-0.129
adium-0.124
Token
Token ID12466
Feature activation-9.70e-01

Pos logit contributions
 spoiler+1.029
 dilig+0.987
 spoilers+0.980
emale+0.961
adium+0.929
Neg logit contributions
-0.775
eteenth-0.698
ORK-0.645
glers-0.628
IGHTS-0.627
Token
Token ID109
Feature activation-1.31e-01

Pos logit contributions
 spoiler+3.117
 dilig+2.982
 spoilers+2.966
emale+2.896
adium+2.798
Neg logit contributions
-2.589
eteenth-2.346
ORK-2.186
glers-2.139
IGHTS-2.136