TOP ACTIVATIONS
MAX = 1.657

55 Recommend Recommend Share this comment on Facebook Share
19 Recommend Recommend Share this comment on Facebook Share
14 Recommend Recommend Share this comment on Facebook Share
PT PowerPoint slide Power Point slide PNG larger image
27 Recommend Recommend Share this comment on Facebook Share
, Mikhail Al "] [ Result " 1 / 2 -
( old ) website . Nevertheless we worked hard to cover
= $ b mp | Select Width , Height } else
pling subway station in Et obic oke . Police
. <|endoftext|> For rapper Off set , of the hip -
and Property B ounds | Select Width , Height Write -
Mill Rd . in Et obic oke s Mark
Share this comment on Facebook Share this comment on Twitter
been made . On one hand , the film was turning
reens | Where Primary | Select - Exp and Property B
at 5 . 5 yards per carry ) and another 388
Share this comment on Facebook Share this comment on Twitter
Share this comment on Facebook Share this comment on Twitter
. Google Scholar Crossref M asure ,
at 5 . 4 yards per carry . His follow -

MIN ACTIVATIONS
MIN = -1.689

. <|endoftext|> V ern acular architecture is a style
Club Bay ern Munich Jun iors [ 92
. UN DE AD * + Soul
book , C arn al Abuse by De ce
47 . Rec y cling scheme [ via ]
with 25 60 CU DA cores and 20 SM units .
will know in only a matter of days , but if
a friend clarified pr ide fully and unp rompt ed
Joshua Roberts DE AD LIN ES LO OM
year has been an un mit igated disaster . But what
all came together in a matter of weeks ," said Mel
The rest of the class are the 99 %; Cart
.) War ner Bros / Courtesy Everett Collection Amy
component const float TA U = 6 . 283 185 307
more than 60 % of respondents who identified themselves as middle
stomach contents found a con ge aled , brown ish -
93 ] Bay ern Munich II Bay
car . B art was discovered by its owner
under here . Thank you Find out
like Mormons love a tab ern acle choir . We pass

INTERVAL 0.821 - 1.657
CONTAINS 0.171%

list _ images ( args [" images "] ): # load
costs . L NG has a number of prominent
. Article Continued Below T od as
92 . 2 - mile per hour ) change of velocity
can be of great mutual benefit to fans and club alike

INTERVAL -0.016 - 0.821
CONTAINS 52.957%

, 15 } -> " S ", { 9 , 15
Jud icial Watch , which sued to force the production
Quest Diagn ostics , based in New Jersey ,
, was trained by the United States , a senior U
the year . This 3 - 3 - 5

INTERVAL -0.852 - -0.016
CONTAINS 46.760%

omm ers II ) Ivanka Trump A wild card choice for
but they were usually too stunned to realize what had happened
. In addition , they would be required to undergo five
is a construct that we use to remove the stuff we
SS N coming on line from 2017 . The UK has

INTERVAL -1.689 - -0.852
CONTAINS 0.111%

reduces power supply noise as well as increases overcl ocking stability
Hide Caption 13 of 15 Photos : Carly Fiorina 's political
tied to the " United Nations Millennium Development Goals ." Students
understand and execute the Mu ay Thai I have been training
H VM ", after the drivers . This improves some kinds
Token55
Token ID2816
Feature activation+3.53e-01

Pos logit contributions
illac+0.880
Leaks+0.848
ILY+0.837
 Nib+0.829
 CLASS+0.823
Neg logit contributions
angered-0.901
genre-0.820
adem-0.728
bnb-0.719
arios-0.708
Token Recommend
Token ID30361
Feature activation+7.47e-01

Pos logit contributions
angered+1.090
genre+0.995
adem+0.893
bnb+0.886
arios+0.872
Neg logit contributions
illac-0.900
Leaks-0.870
ILY-0.855
 Nib-0.841
 CLASS-0.833
Token
Token ID198
Feature activation-9.24e-02

Pos logit contributions
angered+2.152
genre+1.945
adem+1.716
bnb+1.697
arios+1.675
Neg logit contributions
illac-2.078
Leaks-1.980
ILY-1.959
 Nib-1.930
-1.924
Token
Token ID198
Feature activation-2.20e-01

Pos logit contributions
illac+0.237
Leaks+0.229
ILY+0.226
 Nib+0.223
 CLASS+0.222
Neg logit contributions
angered-0.282
genre-0.259
adem-0.233
bnb-0.230
arios-0.227
TokenRecommend
Token ID41248
Feature activation+8.19e-01

Pos logit contributions
illac+0.508
Leaks+0.493
ILY+0.484
 CLASS+0.476
 Nib+0.471
Neg logit contributions
angered-0.727
genre-0.668
adem-0.610
bnb-0.603
arios-0.599
Token Share
Token ID8734
Feature activation+1.66e+00

Pos logit contributions
angered+1.747
genre+1.529
adem+1.281
bnb+1.279
arios+1.239
Neg logit contributions
illac-2.848
Leaks-2.784
ILY-2.741
 Nib-2.716
-2.712
Token this
Token ID428
Feature activation-7.07e-02

Pos logit contributions
angered+4.383
genre+3.894
adem+3.432
bnb+3.373
arios+3.328
Neg logit contributions
illac-4.866
Leaks-4.777
ILY-4.695
-4.595
 Nib-4.568
Token comment
Token ID2912
Feature activation+1.10e-01

Pos logit contributions
illac+0.186
Leaks+0.180
ILY+0.179
 CLASS+0.178
 Nib+0.178
Neg logit contributions
angered-0.210
genre-0.191
adem-0.173
bnb-0.170
arios-0.168
Token on
Token ID319
Feature activation+1.93e-02

Pos logit contributions
angered+0.396
genre+0.366
adem+0.335
bnb+0.331
arios+0.328
Neg logit contributions
illac-0.224
Leaks-0.212
ILY-0.209
 Nib-0.205
 CLASS-0.202
Token Facebook
Token ID3203
Feature activation+4.04e-01

Pos logit contributions
angered+0.051
genre+0.045
adem+0.040
bnb+0.039
arios+0.039
Neg logit contributions
illac-0.058
Leaks-0.056
ILY-0.056
 Nib-0.055
 CLASS-0.055
Token Share
Token ID8734
Feature activation+1.37e+00

Pos logit contributions
angered+0.908
genre+0.803
adem+0.687
bnb+0.675
arios+0.659
Neg logit contributions
illac-1.370
Leaks-1.331
ILY-1.317
 Nib-1.304
 CLASS-1.296
Token19
Token ID1129
Feature activation+3.46e-01

Pos logit contributions
illac+0.819
Leaks+0.789
ILY+0.778
 Nib+0.770
 CLASS+0.764
Neg logit contributions
angered-0.931
genre-0.851
adem-0.762
bnb-0.752
arios-0.741
Token Recommend
Token ID30361
Feature activation+8.31e-01

Pos logit contributions
angered+1.065
genre+0.972
adem+0.872
bnb+0.864
arios+0.849
Neg logit contributions
illac-0.886
Leaks-0.856
ILY-0.840
 Nib-0.827
-0.820
Token
Token ID198
Feature activation-2.65e-02

Pos logit contributions
angered+2.371
genre+2.140
adem+1.885
bnb+1.863
arios+1.837
Neg logit contributions
illac-2.336
Leaks-2.221
ILY-2.198
-2.164
 Nib-2.164
Token
Token ID198
Feature activation-1.92e-01

Pos logit contributions
illac+0.069
Leaks+0.066
ILY+0.065
 Nib+0.065
 CLASS+0.064
Neg logit contributions
angered-0.080
genre-0.074
adem-0.066
bnb-0.065
arios-0.064
TokenRecommend
Token ID41248
Feature activation+8.03e-01

Pos logit contributions
illac+0.448
Leaks+0.433
ILY+0.425
 CLASS+0.417
 Nib+0.416
Neg logit contributions
angered-0.632
genre-0.581
adem-0.530
bnb-0.524
arios-0.520
Token Share
Token ID8734
Feature activation+1.65e+00

Pos logit contributions
angered+1.738
genre+1.523
adem+1.282
bnb+1.277
arios+1.237
Neg logit contributions
illac-2.777
Leaks-2.706
ILY-2.675
 Nib-2.648
-2.635
Token this
Token ID428
Feature activation-5.24e-02

Pos logit contributions
angered+4.287
genre+3.801
adem+3.331
bnb+3.271
argo+3.225
Neg logit contributions
illac-4.921
Leaks-4.776
ILY-4.686
-4.608
 Nib-4.582
Token comment
Token ID2912
Feature activation+1.66e-01

Pos logit contributions
illac+0.138
Leaks+0.134
ILY+0.133
 Nib+0.132
 CLASS+0.132
Neg logit contributions
angered-0.155
genre-0.141
adem-0.127
bnb-0.125
arios-0.124
Token on
Token ID319
Feature activation+5.19e-02

Pos logit contributions
angered+0.599
genre+0.555
adem+0.507
bnb+0.502
arios+0.496
Neg logit contributions
illac-0.340
Leaks-0.321
ILY-0.316
 Nib-0.310
 CLASS-0.307
Token Facebook
Token ID3203
Feature activation+4.58e-01

Pos logit contributions
angered+0.136
genre+0.122
adem+0.107
bnb+0.106
arios+0.104
Neg logit contributions
illac-0.157
Leaks-0.152
ILY-0.150
 Nib-0.148
 CLASS-0.147
Token Share
Token ID8734
Feature activation+1.37e+00

Pos logit contributions
angered+1.022
genre+0.901
adem+0.770
bnb+0.757
arios+0.738
Neg logit contributions
illac-1.557
Leaks-1.512
ILY-1.497
 Nib-1.480
 CLASS-1.471
Token14
Token ID1415
Feature activation+3.80e-01

Pos logit contributions
illac+0.502
Leaks+0.477
ILY+0.472
 Nib+0.470
 CLASS+0.462
Neg logit contributions
angered-0.570
genre-0.523
adem-0.464
bnb-0.458
arios-0.451
Token Recommend
Token ID30361
Feature activation+8.74e-01

Pos logit contributions
angered+1.136
genre+1.034
adem+0.923
bnb+0.918
arios+0.896
Neg logit contributions
illac-1.009
Leaks-0.977
ILY-0.955
 Nib-0.933
-0.931
Token
Token ID198
Feature activation-1.29e-01

Pos logit contributions
angered+2.508
genre+2.257
adem+1.996
bnb+1.977
arios+1.951
Neg logit contributions
illac-2.430
Leaks-2.322
ILY-2.299
 Nib-2.260
-2.256
Token
Token ID198
Feature activation-2.67e-01

Pos logit contributions
illac+0.326
Leaks+0.317
ILY+0.312
 Nib+0.308
 CLASS+0.306
Neg logit contributions
angered-0.397
genre-0.364
adem-0.329
bnb-0.325
arios-0.320
TokenRecommend
Token ID41248
Feature activation+8.72e-01

Pos logit contributions
illac+0.599
Leaks+0.581
ILY+0.572
 CLASS+0.564
+0.553
Neg logit contributions
angered-0.893
genre-0.820
adem-0.751
bnb-0.746
arios-0.741
Token Share
Token ID8734
Feature activation+1.63e+00

Pos logit contributions
angered+1.867
genre+1.640
adem+1.381
bnb+1.366
arios+1.330
Neg logit contributions
illac-3.019
Leaks-2.960
ILY-2.905
 Nib-2.881
-2.875
Token this
Token ID428
Feature activation-1.25e-01

Pos logit contributions
angered+4.252
genre+3.745
adem+3.387
bnb+3.331
arios+3.257
Neg logit contributions
Leaks-4.729
illac-4.720
ILY-4.639
 Nib-4.524
-4.518
Token comment
Token ID2912
Feature activation+4.06e-02

Pos logit contributions
illac+0.329
ILY+0.317
Leaks+0.315
 CLASS+0.314
 Nib+0.311
Neg logit contributions
angered-0.371
genre-0.341
adem-0.307
bnb-0.297
arios-0.296
Token on
Token ID319
Feature activation-4.93e-02

Pos logit contributions
angered+0.145
genre+0.134
adem+0.123
bnb+0.121
arios+0.120
Neg logit contributions
illac-0.084
Leaks-0.080
ILY-0.079
 Nib-0.077
-0.076
Token Facebook
Token ID3203
Feature activation+3.35e-01

Pos logit contributions
illac+0.148
Leaks+0.143
ILY+0.142
 Nib+0.140
 CLASS+0.139
Neg logit contributions
angered-0.130
genre-0.117
adem-0.103
bnb-0.102
arios-0.100
Token Share
Token ID8734
Feature activation+1.39e+00

Pos logit contributions
angered+0.682
genre+0.579
bnb+0.490
adem+0.487
arios+0.470
Neg logit contributions
illac-1.200
Leaks-1.179
 Nib-1.146
-1.144
ILY-1.144
TokenPT
Token ID11571
Feature activation+2.41e-01

Pos logit contributions
illac+0.025
Leaks+0.024
ILY+0.024
 Nib+0.024
 CLASS+0.023
Neg logit contributions
angered-0.027
genre-0.025
adem-0.022
bnb-0.022
arios-0.022
Token PowerPoint
Token ID43563
Feature activation+7.88e-01

Pos logit contributions
angered+0.712
genre+0.659
adem+0.584
bnb+0.566
arios+0.563
Neg logit contributions
illac-0.641
ILY-0.610
Leaks-0.602
-0.594
 Nib-0.583
Token slide
Token ID10649
Feature activation+4.77e-01

Pos logit contributions
angered+1.995
genre+1.809
adem+1.562
bnb+1.513
arios+1.494
Neg logit contributions
illac-2.431
ILY-2.357
Leaks-2.318
-2.309
 CLASS-2.269
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
angered+1.398
genre+1.269
adem+1.131
bnb+1.118
arios+1.098
Neg logit contributions
illac-1.293
Leaks-1.234
ILY-1.227
 Nib-1.206
-1.202
Token
Token ID198
Feature activation-1.70e-01

Pos logit contributions
illac+0.344
Leaks+0.334
ILY+0.328
 Nib+0.324
 CLASS+0.322
Neg logit contributions
angered-0.415
genre-0.381
adem-0.343
bnb-0.340
arios-0.335
TokenPower
Token ID13434
Feature activation+1.61e+00

Pos logit contributions
illac+0.242
Leaks+0.225
ILY+0.220
 Nib+0.215
 CLASS+0.212
Neg logit contributions
angered-0.715
genre-0.671
adem-0.622
bnb-0.617
arios-0.612
TokenPoint
Token ID12727
Feature activation+3.59e-01

Pos logit contributions
angered+4.871
genre+4.497
adem+4.036
bnb+3.991
arios+3.945
Neg logit contributions
illac-4.083
Leaks-3.903
ILY-3.859
 Nib-3.785
 CLASS-3.757
Token slide
Token ID10649
Feature activation+5.77e-01

Pos logit contributions
angered+1.032
genre+0.933
adem+0.833
bnb+0.831
arios+0.808
Neg logit contributions
illac-0.986
Leaks-0.964
 CLASS-0.943
 Nib-0.940
ILY-0.937
Token PNG
Token ID36182
Feature activation+5.18e-01

Pos logit contributions
angered+1.405
genre+1.267
adem+1.094
bnb+1.060
arios+1.037
Neg logit contributions
illac-1.848
-1.772
Leaks-1.766
ILY-1.764
 Nib-1.734
Token larger
Token ID4025
Feature activation+3.32e-01

Pos logit contributions
angered+1.392
genre+1.258
adem+1.110
bnb+1.099
arios+1.076
Neg logit contributions
illac-1.520
Leaks-1.477
ILY-1.457
 Nib-1.442
 CLASS-1.437
Token image
Token ID2939
Feature activation+5.19e-01

Pos logit contributions
angered+0.703
genre+0.617
adem+0.519
bnb+0.517
arios+0.497
Neg logit contributions
illac-1.164
Leaks-1.143
 Nib-1.124
ILY-1.124
 CLASS-1.112
Token27
Token ID1983
Feature activation+4.41e-01

Pos logit contributions
illac+0.934
Leaks+0.902
ILY+0.889
 Nib+0.878
 CLASS+0.873
Neg logit contributions
angered-1.054
genre-0.963
adem-0.863
bnb-0.852
arios-0.840
Token Recommend
Token ID30361
Feature activation+6.70e-01

Pos logit contributions
angered+1.348
genre+1.228
adem+1.100
bnb+1.091
arios+1.070
Neg logit contributions
illac-1.141
Leaks-1.099
ILY-1.080
 Nib-1.062
-1.053
Token
Token ID198
Feature activation-1.28e-01

Pos logit contributions
angered+1.939
genre+1.755
adem+1.553
bnb+1.536
arios+1.515
Neg logit contributions
illac-1.854
Leaks-1.768
ILY-1.748
 Nib-1.723
-1.717
Token
Token ID198
Feature activation-2.73e-01

Pos logit contributions
illac+0.326
Leaks+0.316
ILY+0.311
 Nib+0.307
 CLASS+0.305
Neg logit contributions
angered-0.391
genre-0.359
adem-0.323
bnb-0.320
arios-0.315
TokenRecommend
Token ID41248
Feature activation+7.46e-01

Pos logit contributions
illac+0.632
Leaks+0.612
ILY+0.602
 CLASS+0.589
 Nib+0.586
Neg logit contributions
angered-0.901
genre-0.829
adem-0.756
bnb-0.747
arios-0.742
Token Share
Token ID8734
Feature activation+1.59e+00

Pos logit contributions
angered+1.622
genre+1.425
adem+1.202
bnb+1.196
arios+1.159
Neg logit contributions
illac-2.572
Leaks-2.507
ILY-2.478
 Nib-2.454
-2.441
Token this
Token ID428
Feature activation-8.75e-02

Pos logit contributions
angered+4.170
genre+3.709
adem+3.249
bnb+3.193
argo+3.147
Neg logit contributions
illac-4.737
Leaks-4.598
ILY-4.508
-4.438
 Nib-4.410
Token comment
Token ID2912
Feature activation+6.06e-02

Pos logit contributions
illac+0.230
Leaks+0.225
ILY+0.222
 Nib+0.221
 CLASS+0.220
Neg logit contributions
angered-0.259
genre-0.236
adem-0.212
bnb-0.210
arios-0.207
Token on
Token ID319
Feature activation+4.56e-03

Pos logit contributions
angered+0.221
genre+0.205
adem+0.188
bnb+0.186
arios+0.184
Neg logit contributions
illac-0.121
Leaks-0.115
ILY-0.113
 Nib-0.111
 CLASS-0.110
Token Facebook
Token ID3203
Feature activation+3.53e-01

Pos logit contributions
angered+0.012
genre+0.011
adem+0.009
bnb+0.009
arios+0.009
Neg logit contributions
illac-0.014
Leaks-0.013
ILY-0.013
 Nib-0.013
 CLASS-0.013
Token Share
Token ID8734
Feature activation+1.30e+00

Pos logit contributions
angered+0.798
genre+0.706
adem+0.605
bnb+0.595
arios+0.582
Neg logit contributions
illac-1.192
Leaks-1.159
ILY-1.147
 Nib-1.135
 CLASS-1.130
Token,
Token ID11
Feature activation+6.51e-03

Pos logit contributions
angered+0.251
genre+0.228
adem+0.203
bnb+0.200
arios+0.197
Neg logit contributions
illac-0.245
Leaks-0.237
ILY-0.234
 Nib-0.232
 CLASS-0.230
Token Mikhail
Token ID42040
Feature activation+3.80e-01

Pos logit contributions
angered+0.020
genre+0.018
adem+0.016
bnb+0.016
arios+0.016
Neg logit contributions
illac-0.017
Leaks-0.016
ILY-0.016
 CLASS-0.016
 Nib-0.016
Token Al
Token ID978
Feature activation-1.10e-02

Pos logit contributions
angered+0.660
genre+0.564
adem+0.468
bnb+0.443
arios+0.434
Neg logit contributions
illac-1.471
Leaks-1.444
ILY-1.422
 CLASS-1.408
 Nib-1.406
Token"]
Token ID8973
Feature activation-8.36e-02

Pos logit contributions
illac+0.029
Leaks+0.028
ILY+0.028
 Nib+0.028
 CLASS+0.027
Neg logit contributions
angered-0.032
genre-0.030
adem-0.027
bnb-0.026
arios-0.026
Token [
Token ID685
Feature activation+4.31e-01

Pos logit contributions
illac+0.256
Leaks+0.248
ILY+0.245
 Nib+0.243
 CLASS+0.241
Neg logit contributions
angered-0.215
genre-0.194
adem-0.170
bnb-0.167
arios-0.164
TokenResult
Token ID23004
Feature activation+1.54e+00

Pos logit contributions
angered+1.316
genre+1.207
adem+1.079
bnb+1.059
arios+1.053
Neg logit contributions
illac-1.116
Leaks-1.067
ILY-1.050
-1.042
 Nib-1.036
Token "
Token ID366
Feature activation-1.58e-01

Pos logit contributions
angered+3.104
genre+2.673
adem+2.197
bnb+2.186
argo+2.090
Neg logit contributions
illac-5.534
Leaks-5.335
ILY-5.289
-5.250
 CLASS-5.213
Token1
Token ID16
Feature activation-8.91e-02

Pos logit contributions
illac+0.394
Leaks+0.378
ILY+0.373
 Nib+0.369
 CLASS+0.366
Neg logit contributions
angered-0.495
genre-0.455
adem-0.410
bnb-0.405
arios-0.399
Token/
Token ID14
Feature activation+2.71e-02

Pos logit contributions
illac+0.226
Leaks+0.218
ILY+0.215
 Nib+0.212
 CLASS+0.211
Neg logit contributions
angered-0.275
genre-0.252
adem-0.227
bnb-0.224
arios-0.221
Token2
Token ID17
Feature activation-1.69e-01

Pos logit contributions
angered+0.088
genre+0.081
adem+0.073
bnb+0.072
arios+0.071
Neg logit contributions
illac-0.065
Leaks-0.062
ILY-0.061
 Nib-0.061
 CLASS-0.060
Token-
Token ID12
Feature activation+1.87e-02

Pos logit contributions
illac+0.416
Leaks+0.400
ILY+0.394
 Nib+0.389
 CLASS+0.386
Neg logit contributions
angered-0.533
genre-0.490
adem-0.442
bnb-0.437
arios-0.431
Token (
Token ID357
Feature activation-2.60e-02

Pos logit contributions
illac+0.322
Leaks+0.312
ILY+0.307
 Nib+0.305
 CLASS+0.303
Neg logit contributions
angered-0.346
genre-0.315
adem-0.281
bnb-0.277
arios-0.274
Tokenold
Token ID727
Feature activation-2.73e-01

Pos logit contributions
illac+0.070
Leaks+0.068
ILY+0.067
 Nib+0.066
 CLASS+0.066
Neg logit contributions
angered-0.076
genre-0.069
adem-0.062
bnb-0.061
arios-0.060
Token)
Token ID8
Feature activation+3.50e-01

Pos logit contributions
illac+0.671
Leaks+0.645
ILY+0.634
 Nib+0.626
 CLASS+0.622
Neg logit contributions
angered-0.868
genre-0.796
adem-0.721
bnb-0.713
arios-0.700
Token website
Token ID3052
Feature activation+6.40e-02

Pos logit contributions
angered+0.987
genre+0.894
adem+0.797
bnb+0.788
arios+0.772
Neg logit contributions
illac-0.989
Leaks-0.952
ILY-0.941
 Nib-0.924
 CLASS-0.923
Token.
Token ID13
Feature activation-5.85e-02

Pos logit contributions
angered+0.187
genre+0.170
adem+0.152
bnb+0.150
arios+0.148
Neg logit contributions
illac-0.174
Leaks-0.168
ILY-0.165
 Nib-0.163
 CLASS-0.162
Token Nevertheless
Token ID15933
Feature activation+1.53e+00

Pos logit contributions
illac+0.148
Leaks+0.142
ILY+0.140
 Nib+0.139
 CLASS+0.138
Neg logit contributions
angered-0.182
genre-0.166
adem-0.150
bnb-0.148
arios-0.146
Token we
Token ID356
Feature activation+2.80e-01

Pos logit contributions
angered+3.749
genre+3.383
bnb+3.017
adem+2.992
argo+2.827
Neg logit contributions
illac-4.634
Leaks-4.528
ILY-4.413
 Nib-4.397
 CLASS-4.338
Token worked
Token ID3111
Feature activation-6.38e-02

Pos logit contributions
angered+0.939
genre+0.861
adem+0.783
bnb+0.781
arios+0.767
Neg logit contributions
illac-0.645
Leaks-0.618
ILY-0.604
 Nib-0.598
 CLASS-0.591
Token hard
Token ID1327
Feature activation+7.03e-02

Pos logit contributions
illac+0.142
Leaks+0.135
ILY+0.132
 Nib+0.131
 CLASS+0.130
Neg logit contributions
angered-0.218
genre-0.201
adem-0.183
bnb-0.182
arios-0.180
Token to
Token ID284
Feature activation-5.43e-02

Pos logit contributions
angered+0.241
genre+0.223
adem+0.203
bnb+0.202
arios+0.200
Neg logit contributions
illac-0.154
Leaks-0.147
ILY-0.143
 Nib-0.142
 CLASS-0.141
Token cover
Token ID3002
Feature activation-6.12e-03

Pos logit contributions
illac+0.140
Leaks+0.134
ILY+0.132
 Nib+0.131
 CLASS+0.130
Neg logit contributions
angered-0.166
genre-0.152
adem-0.137
bnb-0.135
arios-0.133
Token =
Token ID796
Feature activation-7.48e-01

Pos logit contributions
angered+0.760
genre+0.704
adem+0.638
bnb+0.627
arios+0.614
Neg logit contributions
illac-0.608
Leaks-0.581
ILY-0.574
 CLASS-0.569
 Nib-0.569
Token $
Token ID720
Feature activation+4.42e-01

Pos logit contributions
illac+2.035
Leaks+1.964
ILY+1.940
 Nib+1.932
 CLASS+1.927
Neg logit contributions
angered-2.167
genre-1.974
adem-1.751
bnb-1.739
arios-1.710
Tokenb
Token ID65
Feature activation+9.94e-02

Pos logit contributions
angered+1.401
genre+1.302
adem+1.177
bnb+1.148
arios+1.126
Neg logit contributions
illac-1.083
Leaks-1.038
ILY-1.026
 Nib-1.019
 CLASS-1.011
Tokenmp
Token ID3149
Feature activation+7.34e-02

Pos logit contributions
angered+0.286
genre+0.261
adem+0.232
bnb+0.229
arios+0.225
Neg logit contributions
illac-0.274
Leaks-0.264
ILY-0.261
 Nib-0.259
 CLASS-0.257
Token |
Token ID930
Feature activation-4.34e-02

Pos logit contributions
angered+0.214
genre+0.195
adem+0.174
bnb+0.172
arios+0.169
Neg logit contributions
illac-0.200
Leaks-0.192
ILY-0.189
 Nib-0.187
 CLASS-0.185
Token Select
Token ID9683
Feature activation+1.49e+00

Pos logit contributions
illac+0.116
Leaks+0.112
ILY+0.111
 Nib+0.109
 CLASS+0.108
Neg logit contributions
angered-0.129
genre-0.117
adem-0.105
bnb-0.104
arios-0.102
Token Width
Token ID38807
Feature activation+1.29e-01

Pos logit contributions
angered+4.251
genre+3.887
adem+3.482
arios+3.343
bnb+3.305
Neg logit contributions
illac-4.036
ILY-3.815
Leaks-3.802
-3.712
 CLASS-3.653
Token,
Token ID11
Feature activation-7.13e-02

Pos logit contributions
angered+0.378
genre+0.346
adem+0.309
bnb+0.303
arios+0.299
Neg logit contributions
illac-0.350
Leaks-0.336
ILY-0.330
 Nib-0.326
 CLASS-0.324
TokenHeight
Token ID23106
Feature activation-1.10e-01

Pos logit contributions
illac+0.160
Leaks+0.151
ILY+0.150
 Nib+0.147
 CLASS+0.146
Neg logit contributions
angered-0.242
genre-0.224
adem-0.203
bnb-0.201
arios-0.198
Token }
Token ID1782
Feature activation-4.33e-01

Pos logit contributions
illac+0.300
Leaks+0.289
ILY+0.285
 Nib+0.282
 CLASS+0.280
Neg logit contributions
angered-0.318
genre-0.290
adem-0.258
bnb-0.255
arios-0.251
Token else
Token ID2073
Feature activation+3.86e-02

Pos logit contributions
illac+1.170
Leaks+1.130
ILY+1.115
 Nib+1.102
 CLASS+1.095
Neg logit contributions
angered-1.268
genre-1.156
adem-1.032
bnb-1.019
arios-1.004
Tokenpling
Token ID11347
Feature activation+1.55e-01

Pos logit contributions
angered+0.212
genre+0.180
adem+0.143
bnb+0.138
arios+0.135
Neg logit contributions
illac-0.514
Leaks-0.500
ILY-0.498
 Nib-0.492
 CLASS-0.491
Token subway
Token ID19612
Feature activation+3.33e-01

Pos logit contributions
angered+0.491
genre+0.451
adem+0.406
bnb+0.405
arios+0.400
Neg logit contributions
illac-0.376
Leaks-0.363
ILY-0.361
-0.355
 Nib-0.352
Token station
Token ID4429
Feature activation+1.73e-01

Pos logit contributions
angered+0.882
genre+0.794
adem+0.705
bnb+0.694
arios+0.691
Neg logit contributions
illac-0.984
Leaks-0.951
ILY-0.947
-0.927
 CLASS-0.926
Token in
Token ID287
Feature activation+5.28e-02

Pos logit contributions
angered+0.503
genre+0.455
adem+0.410
bnb+0.407
arios+0.400
Neg logit contributions
illac-0.466
Leaks-0.452
ILY-0.448
-0.437
 Nib-0.437
Token Et
Token ID17906
Feature activation+4.54e-01

Pos logit contributions
angered+0.145
genre+0.131
adem+0.116
bnb+0.114
arios+0.113
Neg logit contributions
illac-0.152
Leaks-0.147
ILY-0.146
-0.143
 CLASS-0.143
Tokenobic
Token ID20803
Feature activation+1.46e+00

Pos logit contributions
angered+1.569
genre+1.450
adem+1.325
bnb+1.305
arios+1.290
Neg logit contributions
illac-0.981
Leaks-0.949
ILY-0.934
 Nib-0.914
 CLASS-0.911
Tokenoke
Token ID2088
Feature activation+4.07e-01

Pos logit contributions
angered+3.133
genre+2.804
bnb+2.373
adem+2.344
arios+2.281
Neg logit contributions
illac-5.054
ILY-4.877
-4.781
Leaks-4.756
 CLASS-4.747
Token.
Token ID13
Feature activation-1.60e-01

Pos logit contributions
angered+1.148
genre+1.038
bnb+0.924
adem+0.918
arios+0.912
Neg logit contributions
illac-1.126
Leaks-1.096
ILY-1.084
-1.073
 Nib-1.064
Token
Token ID198
Feature activation-2.53e-01

Pos logit contributions
illac+0.427
Leaks+0.411
ILY+0.406
 Nib+0.398
 CLASS+0.397
Neg logit contributions
angered-0.479
genre-0.433
adem-0.388
bnb-0.385
arios-0.378
Token
Token ID198
Feature activation-2.77e-01

Pos logit contributions
illac+0.638
Leaks+0.620
ILY+0.610
 Nib+0.602
 CLASS+0.597
Neg logit contributions
angered-0.779
genre-0.716
adem-0.646
bnb-0.638
arios-0.628
TokenPolice
Token ID9039
Feature activation-2.82e-01

Pos logit contributions
illac+0.655
Leaks+0.622
ILY+0.614
 Nib+0.612
 CLASS+0.608
Neg logit contributions
angered-0.910
genre-0.839
adem-0.758
bnb-0.749
arios-0.739
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
angered+0.076
genre+0.069
adem+0.061
bnb+0.061
arios+0.060
Neg logit contributions
illac-0.074
Leaks-0.071
ILY-0.071
 Nib-0.069
 CLASS-0.069
Token<|endoftext|>
Token ID50256
Feature activation+1.35e-01

Pos logit contributions
illac+0.422
Leaks+0.407
ILY+0.400
 Nib+0.396
 CLASS+0.394
Neg logit contributions
angered-0.517
genre-0.474
adem-0.427
bnb-0.422
arios-0.416
TokenFor
Token ID1890
Feature activation-9.35e-02

Pos logit contributions
angered+0.431
genre+0.399
adem+0.358
bnb+0.351
arios+0.347
Neg logit contributions
illac-0.330
 Nib-0.310
Leaks-0.309
ILY-0.307
 CLASS-0.306
Token rapper
Token ID25670
Feature activation-2.51e-01

Pos logit contributions
illac+0.235
Leaks+0.226
ILY+0.223
 Nib+0.220
 CLASS+0.219
Neg logit contributions
angered-0.292
genre-0.267
adem-0.241
bnb-0.238
arios-0.235
Token Off
Token ID3242
Feature activation+3.68e-02

Pos logit contributions
illac+0.707
Leaks+0.684
ILY+0.675
 Nib+0.667
 CLASS+0.663
Neg logit contributions
angered-0.708
genre-0.644
adem-0.572
bnb-0.564
arios-0.556
Tokenset
Token ID2617
Feature activation+1.46e+00

Pos logit contributions
angered+0.116
genre+0.107
adem+0.096
bnb+0.095
arios+0.094
Neg logit contributions
illac-0.091
Leaks-0.087
ILY-0.087
 Nib-0.085
 CLASS-0.085
Token,
Token ID11
Feature activation-1.67e-01

Pos logit contributions
angered+4.108
genre+3.795
adem+3.330
arios+3.289
bnb+3.288
Neg logit contributions
illac-3.900
ILY-3.782
-3.694
Leaks-3.688
 Nib-3.644
Token of
Token ID286
Feature activation-2.92e-01

Pos logit contributions
illac+0.445
Leaks+0.429
ILY+0.423
 Nib+0.419
 CLASS+0.417
Neg logit contributions
angered-0.497
genre-0.454
adem-0.407
bnb-0.402
arios-0.396
Token the
Token ID262
Feature activation-2.18e-01

Pos logit contributions
illac+0.736
Leaks+0.710
ILY+0.699
 Nib+0.690
 CLASS+0.685
Neg logit contributions
angered-0.910
genre-0.836
adem-0.751
bnb-0.742
arios-0.732
Token hip
Token ID10359
Feature activation-2.27e-01

Pos logit contributions
illac+0.588
Leaks+0.568
ILY+0.560
 Nib+0.554
 CLASS+0.550
Neg logit contributions
angered-0.639
genre-0.583
adem-0.520
bnb-0.514
arios-0.506
Token-
Token ID12
Feature activation-1.95e-01

Pos logit contributions
illac+0.568
Leaks+0.547
ILY+0.539
 Nib+0.532
 CLASS+0.530
Neg logit contributions
angered-0.710
genre-0.651
adem-0.586
bnb-0.580
arios-0.572
Tokenand
Token ID392
Feature activation-3.77e-01

Pos logit contributions
angered+1.255
genre+1.144
adem+1.027
bnb+1.004
arios+0.993
Neg logit contributions
illac-1.163
Leaks-1.120
ILY-1.112
 Nib-1.093
 CLASS-1.091
TokenProperty
Token ID21746
Feature activation+2.19e-01

Pos logit contributions
illac+0.804
Leaks+0.765
ILY+0.755
 Nib+0.742
 CLASS+0.737
Neg logit contributions
angered-1.320
genre-1.222
adem-1.115
bnb-1.102
arios-1.091
Token B
Token ID347
Feature activation+8.84e-02

Pos logit contributions
angered+0.678
genre+0.622
adem+0.561
bnb+0.551
arios+0.544
Neg logit contributions
illac-0.555
Leaks-0.533
ILY-0.525
 Nib-0.514
-0.511
Tokenounds
Token ID3733
Feature activation-2.19e-01

Pos logit contributions
angered+0.258
genre+0.237
adem+0.212
bnb+0.207
arios+0.204
Neg logit contributions
illac-0.239
Leaks-0.230
ILY-0.227
 Nib-0.226
 CLASS-0.223
Token |
Token ID930
Feature activation+1.25e-01

Pos logit contributions
illac+0.572
Leaks+0.550
ILY+0.543
 Nib+0.535
 CLASS+0.531
Neg logit contributions
angered-0.658
genre-0.603
adem-0.542
bnb-0.535
arios-0.526
Token Select
Token ID9683
Feature activation+1.42e+00

Pos logit contributions
angered+0.401
genre+0.369
adem+0.333
bnb+0.329
arios+0.324
Neg logit contributions
illac-0.301
Leaks-0.289
ILY-0.286
 Nib-0.278
 CLASS-0.276
Token Width
Token ID38807
Feature activation+5.28e-02

Pos logit contributions
angered+4.107
genre+3.741
adem+3.396
bnb+3.262
arios+3.235
Neg logit contributions
illac-3.739
ILY-3.566
Leaks-3.484
-3.435
theless-3.347
Token,
Token ID11
Feature activation+1.40e-02

Pos logit contributions
angered+0.145
genre+0.132
adem+0.117
bnb+0.115
arios+0.113
Neg logit contributions
illac-0.153
Leaks-0.147
ILY-0.145
 Nib-0.142
-0.142
TokenHeight
Token ID23106
Feature activation-9.36e-02

Pos logit contributions
angered+0.055
genre+0.052
adem+0.048
bnb+0.047
arios+0.046
Neg logit contributions
illac-0.024
Leaks-0.022
ILY-0.022
 CLASS-0.021
 Nib-0.021
Token Write
Token ID19430
Feature activation+1.92e-01

Pos logit contributions
illac+0.270
Leaks+0.261
ILY+0.258
 Nib+0.253
 CLASS+0.252
Neg logit contributions
angered-0.257
genre-0.234
adem-0.207
bnb-0.204
arios-0.200
Token-
Token ID12
Feature activation+6.00e-01

Pos logit contributions
angered+0.580
genre+0.534
adem+0.479
bnb+0.472
arios+0.466
Neg logit contributions
illac-0.496
Leaks-0.473
ILY-0.469
 CLASS-0.460
 Nib-0.459
Token Mill
Token ID9212
Feature activation+3.73e-01

Pos logit contributions
angered+0.723
genre+0.658
adem+0.587
bnb+0.578
arios+0.572
Neg logit contributions
illac-0.656
Leaks-0.633
ILY-0.626
-0.618
 CLASS-0.607
Token Rd
Token ID20769
Feature activation+6.00e-01

Pos logit contributions
angered+1.124
genre+1.017
adem+0.926
bnb+0.913
arios+0.910
Neg logit contributions
illac-0.961
Leaks-0.935
ILY-0.934
-0.913
 Nib-0.910
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
angered+1.651
genre+1.491
adem+1.316
bnb+1.289
arios+1.272
Neg logit contributions
illac-1.704
Leaks-1.679
ILY-1.641
-1.617
 CLASS-1.609
Token in
Token ID287
Feature activation+5.38e-03

Pos logit contributions
illac+0.279
Leaks+0.269
ILY+0.265
 Nib+0.260
 CLASS+0.259
Neg logit contributions
angered-0.318
genre-0.290
adem-0.259
bnb-0.256
arios-0.252
Token Et
Token ID17906
Feature activation+4.24e-01

Pos logit contributions
angered+0.015
genre+0.014
adem+0.012
bnb+0.012
arios+0.012
Neg logit contributions
illac-0.015
Leaks-0.015
ILY-0.014
 Nib-0.014
 CLASS-0.014
Tokenobic
Token ID20803
Feature activation+1.39e+00

Pos logit contributions
angered+1.451
genre+1.337
adem+1.226
bnb+1.202
arios+1.187
Neg logit contributions
illac-0.920
Leaks-0.900
ILY-0.886
 Nib-0.869
 CLASS-0.868
Tokenoke
Token ID2088
Feature activation+4.45e-01

Pos logit contributions
angered+3.122
genre+2.803
adem+2.388
bnb+2.370
arios+2.293
Neg logit contributions
illac-4.669
ILY-4.504
Leaks-4.455
-4.426
 Nib-4.421
Token
Token ID447
Feature activation-8.67e-02

Pos logit contributions
angered+1.302
genre+1.186
adem+1.052
bnb+1.041
arios+1.030
Neg logit contributions
illac-1.203
Leaks-1.155
ILY-1.146
-1.124
 Nib-1.123
Token
Token ID247
Feature activation+4.38e-02

Pos logit contributions
illac+0.274
Leaks+0.265
ILY+0.262
 Nib+0.260
 CLASS+0.259
Neg logit contributions
angered-0.215
genre-0.192
adem-0.168
bnb-0.165
arios-0.162
Tokens
Token ID82
Feature activation-6.97e-02

Pos logit contributions
angered+0.131
genre+0.120
adem+0.107
bnb+0.106
arios+0.104
Neg logit contributions
illac-0.116
Leaks-0.112
ILY-0.110
 Nib-0.109
 CLASS-0.108
Token Mark
Token ID2940
Feature activation+3.69e-01

Pos logit contributions
illac+0.197
Leaks+0.190
ILY+0.188
 Nib+0.185
 CLASS+0.184
Neg logit contributions
angered-0.196
genre-0.178
adem-0.158
bnb-0.155
arios-0.153
Token Share
Token ID8734
Feature activation+1.63e+00

Pos logit contributions
angered+1.867
genre+1.640
adem+1.381
bnb+1.366
arios+1.330
Neg logit contributions
illac-3.019
Leaks-2.960
ILY-2.905
 Nib-2.881
-2.875
Token this
Token ID428
Feature activation-1.25e-01

Pos logit contributions
angered+4.252
genre+3.745
adem+3.387
bnb+3.331
arios+3.257
Neg logit contributions
Leaks-4.729
illac-4.720
ILY-4.639
 Nib-4.524
-4.518
Token comment
Token ID2912
Feature activation+4.06e-02

Pos logit contributions
illac+0.329
ILY+0.317
Leaks+0.315
 CLASS+0.314
 Nib+0.311
Neg logit contributions
angered-0.371
genre-0.341
adem-0.307
bnb-0.297
arios-0.296
Token on
Token ID319
Feature activation-4.93e-02

Pos logit contributions
angered+0.145
genre+0.134
adem+0.123
bnb+0.121
arios+0.120
Neg logit contributions
illac-0.084
Leaks-0.080
ILY-0.079
 Nib-0.077
-0.076
Token Facebook
Token ID3203
Feature activation+3.35e-01

Pos logit contributions
illac+0.148
Leaks+0.143
ILY+0.142
 Nib+0.140
 CLASS+0.139
Neg logit contributions
angered-0.130
genre-0.117
adem-0.103
bnb-0.102
arios-0.100
Token Share
Token ID8734
Feature activation+1.39e+00

Pos logit contributions
angered+0.682
genre+0.579
bnb+0.490
adem+0.487
arios+0.470
Neg logit contributions
illac-1.200
Leaks-1.179
 Nib-1.146
-1.144
ILY-1.144
Token this
Token ID428
Feature activation-1.78e-01

Pos logit contributions
angered+3.884
genre+3.455
adem+3.092
bnb+3.057
arios+3.005
Neg logit contributions
illac-3.879
Leaks-3.833
ILY-3.773
 Nib-3.679
-3.649
Token comment
Token ID2912
Feature activation-1.65e-01

Pos logit contributions
illac+0.475
Leaks+0.459
ILY+0.455
 CLASS+0.453
 Nib+0.451
Neg logit contributions
angered-0.523
genre-0.478
adem-0.430
bnb-0.423
arios-0.418
Token on
Token ID319
Feature activation-1.48e-01

Pos logit contributions
illac+0.316
Leaks+0.302
ILY+0.295
 Nib+0.291
 CLASS+0.289
Neg logit contributions
angered-0.612
genre-0.571
adem-0.523
bnb-0.519
arios-0.513
Token Twitter
Token ID3009
Feature activation-4.01e-01

Pos logit contributions
illac+0.397
Leaks+0.383
ILY+0.378
 Nib+0.373
 CLASS+0.371
Neg logit contributions
angered-0.434
genre-0.396
adem-0.353
bnb-0.350
arios-0.344
Token
Token ID198
Feature activation-1.90e-01

Pos logit contributions
illac+1.048
Leaks+1.011
ILY+0.997
 Nib+0.985
 CLASS+0.979
Neg logit contributions
angered-1.208
genre-1.105
adem-0.990
bnb-0.978
arios-0.964
Token been
Token ID587
Feature activation+8.03e-02

Pos logit contributions
angered+0.973
genre+0.884
adem+0.787
bnb+0.771
arios+0.763
Neg logit contributions
illac-0.906
Leaks-0.873
ILY-0.854
 Nib-0.843
 CLASS-0.839
Token made
Token ID925
Feature activation+3.86e-01

Pos logit contributions
angered+0.244
genre+0.224
adem+0.200
bnb+0.197
arios+0.195
Neg logit contributions
illac-0.209
Leaks-0.202
ILY-0.198
 Nib-0.195
 CLASS-0.193
Token.
Token ID13
Feature activation+2.89e-02

Pos logit contributions
angered+1.134
genre+1.041
adem+0.923
bnb+0.915
arios+0.902
Neg logit contributions
illac-1.041
Leaks-1.009
ILY-0.986
 Nib-0.969
-0.956
Token On
Token ID1550
Feature activation+2.41e-01

Pos logit contributions
angered+0.087
genre+0.079
adem+0.071
bnb+0.070
arios+0.069
Neg logit contributions
illac-0.076
Leaks-0.073
ILY-0.072
 Nib-0.071
 CLASS-0.071
Token one
Token ID530
Feature activation+6.77e-01

Pos logit contributions
angered+0.755
genre+0.696
adem+0.627
bnb+0.616
arios+0.606
Neg logit contributions
illac-0.609
Leaks-0.572
ILY-0.570
 Nib-0.554
-0.553
Token hand
Token ID1021
Feature activation+1.39e+00

Pos logit contributions
angered+1.614
genre+1.446
adem+1.246
bnb+1.223
arios+1.206
Neg logit contributions
illac-2.207
Leaks-2.137
ILY-2.108
 Nib-2.081
 CLASS-2.075
Token,
Token ID11
Feature activation+4.46e-02

Pos logit contributions
angered+3.575
genre+3.256
adem+2.852
bnb+2.771
arios+2.759
Neg logit contributions
illac-4.140
Leaks-4.016
ILY-3.885
 Nib-3.818
-3.817
Token the
Token ID262
Feature activation-7.59e-02

Pos logit contributions
angered+0.130
genre+0.118
adem+0.106
bnb+0.104
arios+0.103
Neg logit contributions
illac-0.122
Leaks-0.117
ILY-0.116
 Nib-0.114
 CLASS-0.113
Token film
Token ID2646
Feature activation+1.89e-01

Pos logit contributions
illac+0.207
Leaks+0.200
ILY+0.197
 Nib+0.194
 CLASS+0.193
Neg logit contributions
angered-0.221
genre-0.202
adem-0.179
bnb-0.177
arios-0.175
Token was
Token ID373
Feature activation-1.03e-02

Pos logit contributions
angered+0.581
genre+0.532
adem+0.478
bnb+0.471
arios+0.465
Neg logit contributions
illac-0.487
Leaks-0.469
ILY-0.462
 Nib-0.457
 CLASS-0.453
Token turning
Token ID6225
Feature activation-9.26e-03

Pos logit contributions
illac+0.027
Leaks+0.026
ILY+0.025
 Nib+0.025
 CLASS+0.025
Neg logit contributions
angered-0.031
genre-0.029
adem-0.026
bnb-0.025
arios-0.025
Tokenreens
Token ID5681
Feature activation-2.76e-03

Pos logit contributions
angered+0.100
genre+0.091
adem+0.081
bnb+0.080
arios+0.079
Neg logit contributions
illac-0.089
Leaks-0.086
ILY-0.085
 Nib-0.083
 CLASS-0.083
Token |
Token ID930
Feature activation-9.19e-03

Pos logit contributions
illac+0.007
Leaks+0.007
ILY+0.007
 Nib+0.007
 CLASS+0.007
Neg logit contributions
angered-0.008
genre-0.008
adem-0.007
bnb-0.007
arios-0.007
Token Where
Token ID6350
Feature activation+8.80e-01

Pos logit contributions
illac+0.024
Leaks+0.023
ILY+0.023
 Nib+0.023
 CLASS+0.023
Neg logit contributions
angered-0.027
genre-0.025
adem-0.022
bnb-0.022
arios-0.022
Token Primary
Token ID21087
Feature activation-9.98e-02

Pos logit contributions
angered+2.609
genre+2.374
adem+2.148
arios+2.071
bnb+2.029
Neg logit contributions
illac-2.311
ILY-2.225
Leaks-2.210
-2.155
 Nib-2.135
Token |
Token ID930
Feature activation-2.13e-01

Pos logit contributions
illac+0.246
Leaks+0.235
ILY+0.232
 Nib+0.229
 CLASS+0.227
Neg logit contributions
angered-0.315
genre-0.290
adem-0.264
bnb-0.258
arios-0.254
Token Select
Token ID9683
Feature activation+1.38e+00

Pos logit contributions
illac+0.526
Leaks+0.506
ILY+0.500
 Nib+0.491
 CLASS+0.487
Neg logit contributions
angered-0.671
genre-0.616
adem-0.556
bnb-0.549
arios-0.541
Token -
Token ID532
Feature activation+3.90e-01

Pos logit contributions
angered+4.245
genre+3.860
adem+3.532
arios+3.368
bnb+3.363
Neg logit contributions
illac-3.419
ILY-3.268
Leaks-3.243
-3.156
Chem-3.050
TokenExp
Token ID16870
Feature activation+4.30e-01

Pos logit contributions
angered+1.176
genre+1.084
adem+0.966
bnb+0.943
arios+0.934
Neg logit contributions
illac-1.023
Leaks-0.976
ILY-0.968
 Nib-0.955
-0.952
Tokenand
Token ID392
Feature activation-3.77e-01

Pos logit contributions
angered+1.255
genre+1.144
adem+1.027
bnb+1.004
arios+0.993
Neg logit contributions
illac-1.163
Leaks-1.120
ILY-1.112
 Nib-1.093
 CLASS-1.091
TokenProperty
Token ID21746
Feature activation+2.19e-01

Pos logit contributions
illac+0.804
Leaks+0.765
ILY+0.755
 Nib+0.742
 CLASS+0.737
Neg logit contributions
angered-1.320
genre-1.222
adem-1.115
bnb-1.102
arios-1.091
Token B
Token ID347
Feature activation+8.84e-02

Pos logit contributions
angered+0.678
genre+0.622
adem+0.561
bnb+0.551
arios+0.544
Neg logit contributions
illac-0.555
Leaks-0.533
ILY-0.525
 Nib-0.514
-0.511
Tokenat
Token ID265
Feature activation+4.32e-01

Pos logit contributions
illac+0.261
Leaks+0.250
ILY+0.248
 Nib+0.245
 CLASS+0.244
Neg logit contributions
angered-0.291
genre-0.267
adem-0.238
bnb-0.236
arios-0.231
Token 5
Token ID642
Feature activation-7.48e-02

Pos logit contributions
angered+1.251
genre+1.138
adem+1.027
bnb+1.002
arios+0.997
Neg logit contributions
illac-1.166
Leaks-1.136
ILY-1.116
 Nib-1.096
-1.092
Token.
Token ID13
Feature activation+2.43e-01

Pos logit contributions
illac+0.196
Leaks+0.188
ILY+0.186
 Nib+0.184
 CLASS+0.182
Neg logit contributions
angered-0.226
genre-0.206
adem-0.185
bnb-0.183
arios-0.180
Token5
Token ID20
Feature activation-2.98e-01

Pos logit contributions
angered+0.752
genre+0.689
adem+0.619
bnb+0.611
arios+0.602
Neg logit contributions
illac-0.621
Leaks-0.594
ILY-0.586
 Nib-0.580
 CLASS-0.575
Token yards
Token ID5695
Feature activation+5.92e-01

Pos logit contributions
illac+0.894
Leaks+0.866
ILY+0.856
 Nib+0.848
 CLASS+0.845
Neg logit contributions
angered-0.785
genre-0.708
adem-0.620
bnb-0.614
arios-0.604
Token per
Token ID583
Feature activation+1.37e+00

Pos logit contributions
angered+1.662
genre+1.508
adem+1.347
bnb+1.334
arios+1.302
Neg logit contributions
illac-1.673
Leaks-1.615
ILY-1.587
 Nib-1.565
-1.552
Token carry
Token ID3283
Feature activation+3.46e-01

Pos logit contributions
angered+2.981
genre+2.669
adem+2.302
bnb+2.223
arios+2.185
Neg logit contributions
illac-4.667
Leaks-4.503
ILY-4.456
-4.368
 Nib-4.352
Token)
Token ID8
Feature activation+3.44e-02

Pos logit contributions
angered+1.020
genre+0.928
adem+0.834
bnb+0.826
arios+0.809
Neg logit contributions
illac-0.929
Leaks-0.901
ILY-0.878
 Nib-0.868
 CLASS-0.861
Token and
Token ID290
Feature activation+8.21e-02

Pos logit contributions
angered+0.102
genre+0.093
adem+0.084
bnb+0.083
arios+0.082
Neg logit contributions
illac-0.092
Leaks-0.089
ILY-0.087
 Nib-0.086
 CLASS-0.085
Token another
Token ID1194
Feature activation-1.14e-01

Pos logit contributions
angered+0.268
genre+0.246
adem+0.223
bnb+0.220
arios+0.218
Neg logit contributions
illac-0.195
Leaks-0.187
ILY-0.184
 Nib-0.181
 CLASS-0.180
Token 388
Token ID43550
Feature activation+1.46e-01

Pos logit contributions
illac+0.253
Leaks+0.242
ILY+0.239
 Nib+0.236
 CLASS+0.234
Neg logit contributions
angered-0.387
genre-0.358
adem-0.325
bnb-0.322
arios-0.318
Token Share
Token ID8734
Feature activation+1.66e+00

Pos logit contributions
angered+1.747
genre+1.529
adem+1.281
bnb+1.279
arios+1.239
Neg logit contributions
illac-2.848
Leaks-2.784
ILY-2.741
 Nib-2.716
-2.712
Token this
Token ID428
Feature activation-7.07e-02

Pos logit contributions
angered+4.383
genre+3.894
adem+3.432
bnb+3.373
arios+3.328
Neg logit contributions
illac-4.866
Leaks-4.777
ILY-4.695
-4.595
 Nib-4.568
Token comment
Token ID2912
Feature activation+1.10e-01

Pos logit contributions
illac+0.186
Leaks+0.180
ILY+0.179
 CLASS+0.178
 Nib+0.178
Neg logit contributions
angered-0.210
genre-0.191
adem-0.173
bnb-0.170
arios-0.168
Token on
Token ID319
Feature activation+1.93e-02

Pos logit contributions
angered+0.396
genre+0.366
adem+0.335
bnb+0.331
arios+0.328
Neg logit contributions
illac-0.224
Leaks-0.212
ILY-0.209
 Nib-0.205
 CLASS-0.202
Token Facebook
Token ID3203
Feature activation+4.04e-01

Pos logit contributions
angered+0.051
genre+0.045
adem+0.040
bnb+0.039
arios+0.039
Neg logit contributions
illac-0.058
Leaks-0.056
ILY-0.056
 Nib-0.055
 CLASS-0.055
Token Share
Token ID8734
Feature activation+1.37e+00

Pos logit contributions
angered+0.908
genre+0.803
adem+0.687
bnb+0.675
arios+0.659
Neg logit contributions
illac-1.370
Leaks-1.331
ILY-1.317
 Nib-1.304
 CLASS-1.296
Token this
Token ID428
Feature activation-1.51e-01

Pos logit contributions
angered+3.754
genre+3.356
adem+2.954
bnb+2.924
arios+2.867
Neg logit contributions
illac-3.936
Leaks-3.812
ILY-3.748
 Nib-3.685
-3.677
Token comment
Token ID2912
Feature activation-1.13e-01

Pos logit contributions
illac+0.396
Leaks+0.384
ILY+0.380
 Nib+0.379
 CLASS+0.378
Neg logit contributions
angered-0.450
genre-0.410
adem-0.371
bnb-0.366
arios-0.362
Token on
Token ID319
Feature activation-9.48e-02

Pos logit contributions
illac+0.216
Leaks+0.206
ILY+0.202
 Nib+0.199
 CLASS+0.197
Neg logit contributions
angered-0.419
genre-0.390
adem-0.358
bnb-0.355
arios-0.351
Token Twitter
Token ID3009
Feature activation-2.78e-01

Pos logit contributions
illac+0.251
Leaks+0.243
ILY+0.239
 Nib+0.237
 CLASS+0.236
Neg logit contributions
angered-0.282
genre-0.258
adem-0.231
bnb-0.228
arios-0.225
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
illac+0.732
Leaks+0.705
ILY+0.695
 Nib+0.686
 CLASS+0.682
Neg logit contributions
angered-0.833
genre-0.760
adem-0.681
bnb-0.673
arios-0.664
Token Share
Token ID8734
Feature activation+1.65e+00

Pos logit contributions
angered+1.738
genre+1.523
adem+1.282
bnb+1.277
arios+1.237
Neg logit contributions
illac-2.777
Leaks-2.706
ILY-2.675
 Nib-2.648
-2.635
Token this
Token ID428
Feature activation-5.24e-02

Pos logit contributions
angered+4.287
genre+3.801
adem+3.331
bnb+3.271
argo+3.225
Neg logit contributions
illac-4.921
Leaks-4.776
ILY-4.686
-4.608
 Nib-4.582
Token comment
Token ID2912
Feature activation+1.66e-01

Pos logit contributions
illac+0.138
Leaks+0.134
ILY+0.133
 Nib+0.132
 CLASS+0.132
Neg logit contributions
angered-0.155
genre-0.141
adem-0.127
bnb-0.125
arios-0.124
Token on
Token ID319
Feature activation+5.19e-02

Pos logit contributions
angered+0.599
genre+0.555
adem+0.507
bnb+0.502
arios+0.496
Neg logit contributions
illac-0.340
Leaks-0.321
ILY-0.316
 Nib-0.310
 CLASS-0.307
Token Facebook
Token ID3203
Feature activation+4.58e-01

Pos logit contributions
angered+0.136
genre+0.122
adem+0.107
bnb+0.106
arios+0.104
Neg logit contributions
illac-0.157
Leaks-0.152
ILY-0.150
 Nib-0.148
 CLASS-0.147
Token Share
Token ID8734
Feature activation+1.37e+00

Pos logit contributions
angered+1.022
genre+0.901
adem+0.770
bnb+0.757
arios+0.738
Neg logit contributions
illac-1.557
Leaks-1.512
ILY-1.497
 Nib-1.480
 CLASS-1.471
Token this
Token ID428
Feature activation-1.58e-01

Pos logit contributions
angered+3.729
genre+3.333
adem+2.927
bnb+2.896
arios+2.835
Neg logit contributions
illac-3.962
Leaks-3.824
ILY-3.762
 Nib-3.697
-3.693
Token comment
Token ID2912
Feature activation-8.51e-02

Pos logit contributions
illac+0.415
Leaks+0.403
ILY+0.399
 Nib+0.397
 CLASS+0.396
Neg logit contributions
angered-0.469
genre-0.428
adem-0.386
bnb-0.382
arios-0.378
Token on
Token ID319
Feature activation-5.44e-02

Pos logit contributions
illac+0.163
Leaks+0.156
ILY+0.153
 Nib+0.151
 CLASS+0.149
Neg logit contributions
angered-0.315
genre-0.293
adem-0.269
bnb-0.267
arios-0.264
Token Twitter
Token ID3009
Feature activation-1.54e-01

Pos logit contributions
illac+0.145
Leaks+0.140
ILY+0.138
 Nib+0.136
 CLASS+0.135
Neg logit contributions
angered-0.161
genre-0.147
adem-0.132
bnb-0.130
arios-0.128
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
illac+0.410
Leaks+0.395
ILY+0.389
 Nib+0.383
 CLASS+0.381
Neg logit contributions
angered-0.458
genre-0.417
adem-0.374
bnb-0.369
arios-0.365
Token.
Token ID764
Feature activation-7.07e-02

Pos logit contributions
angered+0.294
genre+0.268
adem+0.241
bnb+0.236
arios+0.233
Neg logit contributions
illac-0.259
Leaks-0.251
ILY-0.246
 Nib-0.241
-0.241
Token
Token ID198
Feature activation+3.19e-01

Pos logit contributions
illac+0.197
Leaks+0.191
ILY+0.188
 Nib+0.185
 CLASS+0.184
Neg logit contributions
angered-0.201
genre-0.183
adem-0.163
bnb-0.161
arios-0.158
Token
Token ID198
Feature activation+1.54e-01

Pos logit contributions
angered+0.932
genre+0.846
adem+0.751
bnb+0.738
arios+0.730
Neg logit contributions
illac-0.873
Leaks-0.829
ILY-0.818
 Nib-0.814
 CLASS-0.810
TokenGoogle
Token ID11708
Feature activation+5.78e-01

Pos logit contributions
angered+0.468
genre+0.431
adem+0.385
bnb+0.375
arios+0.374
Neg logit contributions
illac-0.397
Leaks-0.378
 Nib-0.374
 CLASS-0.372
ILY-0.372
Token Scholar
Token ID11713
Feature activation+5.03e-01

Pos logit contributions
angered+1.683
genre+1.541
adem+1.385
bnb+1.359
arios+1.331
Neg logit contributions
illac-1.568
Leaks-1.510
ILY-1.484
 Nib-1.463
-1.456
Token Crossref
Token ID23613
Feature activation+1.35e+00

Pos logit contributions
angered+1.421
genre+1.289
adem+1.146
bnb+1.136
arios+1.106
Neg logit contributions
illac-1.406
Leaks-1.361
ILY-1.327
-1.313
 Nib-1.313
Token
Token ID198
Feature activation+7.38e-01

Pos logit contributions
angered+3.460
genre+3.109
adem+2.720
bnb+2.655
arios+2.607
Neg logit contributions
illac-3.988
Leaks-3.953
ILY-3.805
 Nib-3.792
 CLASS-3.749
Token
Token ID198
Feature activation+5.69e-01

Pos logit contributions
angered+2.078
genre+1.868
adem+1.643
bnb+1.615
arios+1.605
Neg logit contributions
illac-2.102
Leaks-1.993
ILY-1.975
 CLASS-1.954
 Nib-1.949
TokenM
Token ID44
Feature activation+3.47e-01

Pos logit contributions
angered+1.840
genre+1.704
adem+1.532
arios+1.482
bnb+1.480
Neg logit contributions
illac-1.367
 CLASS-1.281
 Nib-1.272
Leaks-1.261
-1.246
Tokenasure
Token ID5015
Feature activation+4.10e-01

Pos logit contributions
angered+1.000
genre+0.909
adem+0.816
bnb+0.800
arios+0.797
Neg logit contributions
illac-0.947
Leaks-0.920
ILY-0.905
 Nib-0.902
 CLASS-0.895
Token,
Token ID11
Feature activation+4.37e-01

Pos logit contributions
angered+1.199
genre+1.096
adem+0.988
bnb+0.975
arios+0.957
Neg logit contributions
illac-1.095
Leaks-1.069
ILY-1.058
 Nib-1.037
-1.031
Token at
Token ID379
Feature activation-2.95e-03

Pos logit contributions
angered+1.592
genre+1.453
adem+1.296
bnb+1.287
arios+1.265
Neg logit contributions
illac-1.481
Leaks-1.448
ILY-1.409
 Nib-1.384
-1.370
Token 5
Token ID642
Feature activation+5.24e-02

Pos logit contributions
illac+0.009
Leaks+0.009
ILY+0.009
 Nib+0.009
 CLASS+0.009
Neg logit contributions
angered-0.007
genre-0.007
adem-0.006
bnb-0.006
arios-0.006
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
angered+0.154
genre+0.141
adem+0.126
bnb+0.124
arios+0.122
Neg logit contributions
illac-0.141
Leaks-0.136
ILY-0.135
 Nib-0.133
 CLASS-0.131
Token4
Token ID19
Feature activation+1.52e-01

Pos logit contributions
angered+0.641
genre+0.587
adem+0.527
bnb+0.520
arios+0.513
Neg logit contributions
illac-0.533
Leaks-0.510
ILY-0.503
 Nib-0.498
 CLASS-0.494
Token yards
Token ID5695
Feature activation+6.10e-01

Pos logit contributions
angered+0.376
genre+0.337
adem+0.294
bnb+0.289
arios+0.283
Neg logit contributions
illac-0.477
Leaks-0.464
ILY-0.458
 Nib-0.453
 CLASS-0.450
Token per
Token ID583
Feature activation+1.34e+00

Pos logit contributions
angered+1.735
genre+1.578
adem+1.408
bnb+1.391
arios+1.365
Neg logit contributions
illac-1.695
Leaks-1.644
ILY-1.616
 Nib-1.593
 CLASS-1.579
Token carry
Token ID3283
Feature activation+2.17e-01

Pos logit contributions
angered+2.874
genre+2.575
adem+2.195
bnb+2.119
arios+2.083
Neg logit contributions
illac-4.604
Leaks-4.499
ILY-4.426
 Nib-4.364
-4.352
Token.
Token ID13
Feature activation-1.85e-02

Pos logit contributions
angered+0.622
genre+0.565
adem+0.505
bnb+0.499
arios+0.491
Neg logit contributions
illac-0.598
Leaks-0.582
ILY-0.569
 Nib-0.563
 CLASS-0.557
Token His
Token ID2399
Feature activation-4.06e-03

Pos logit contributions
illac+0.048
Leaks+0.046
ILY+0.045
 Nib+0.045
 CLASS+0.044
Neg logit contributions
angered-0.057
genre-0.052
adem-0.046
bnb-0.046
arios-0.045
Token follow
Token ID1061
Feature activation-4.74e-01

Pos logit contributions
illac+0.010
Leaks+0.010
ILY+0.010
 Nib+0.010
+0.010
Neg logit contributions
angered-0.013
genre-0.011
adem-0.010
bnb-0.010
arios-0.010
Token-
Token ID12
Feature activation-1.46e-01

Pos logit contributions
illac+1.212
Leaks+1.168
ILY+1.151
 Nib+1.137
 CLASS+1.130
Neg logit contributions
angered-1.458
genre-1.335
adem-1.200
bnb-1.187
arios-1.169
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
angered+0.108
genre+0.099
adem+0.089
bnb+0.088
arios+0.086
Neg logit contributions
illac-0.091
Leaks-0.088
ILY-0.087
 Nib-0.086
 CLASS-0.085
Token
Token ID447
Feature activation-7.34e-02

Pos logit contributions
angered+0.030
genre+0.028
adem+0.025
bnb+0.025
arios+0.024
Neg logit contributions
illac-0.027
Leaks-0.026
ILY-0.026
 Nib-0.025
 CLASS-0.025
Token
Token ID251
Feature activation-1.27e-02

Pos logit contributions
illac+0.258
Leaks+0.252
ILY+0.249
 Nib+0.247
 CLASS+0.246
Neg logit contributions
angered-0.155
genre-0.136
adem-0.115
bnb-0.112
arios-0.111
Token<|endoftext|>
Token ID50256
Feature activation+2.03e-01

Pos logit contributions
illac+0.034
Leaks+0.032
ILY+0.032
 Nib+0.032
 CLASS+0.031
Neg logit contributions
angered-0.038
genre-0.035
adem-0.031
bnb-0.031
arios-0.030
TokenV
Token ID53
Feature activation-1.43e-01

Pos logit contributions
angered+0.649
genre+0.601
adem+0.539
bnb+0.528
arios+0.523
Neg logit contributions
illac-0.497
 Nib-0.466
Leaks-0.465
ILY-0.461
 CLASS-0.461
Tokenern
Token ID1142
Feature activation-1.69e+00

Pos logit contributions
illac+0.375
Leaks+0.362
ILY+0.357
 Nib+0.355
 CLASS+0.352
Neg logit contributions
angered-0.428
genre-0.390
adem-0.352
bnb-0.345
arios-0.343
Tokenacular
Token ID12754
Feature activation-1.53e-01

Pos logit contributions
illac+3.471
Leaks+3.403
 Nib+3.252
ILY+3.230
 CLASS+3.156
Neg logit contributions
angered-5.924
genre-5.543
bnb-4.990
adem-4.964
arios-4.852
Token architecture
Token ID10959
Feature activation+2.45e-02

Pos logit contributions
illac+0.398
Leaks+0.383
ILY+0.379
 Nib+0.372
 CLASS+0.370
Neg logit contributions
angered-0.463
genre-0.423
adem-0.380
bnb-0.376
arios-0.369
Token is
Token ID318
Feature activation-1.62e-01

Pos logit contributions
angered+0.075
genre+0.068
adem+0.061
bnb+0.061
arios+0.060
Neg logit contributions
illac-0.063
Leaks-0.061
ILY-0.060
 Nib-0.059
 CLASS-0.059
Token a
Token ID257
Feature activation-4.02e-01

Pos logit contributions
illac+0.410
Leaks+0.395
ILY+0.389
 Nib+0.385
 CLASS+0.382
Neg logit contributions
angered-0.503
genre-0.461
adem-0.415
bnb-0.410
arios-0.404
Token style
Token ID3918
Feature activation+1.96e-02

Pos logit contributions
illac+1.120
Leaks+1.082
ILY+1.072
 Nib+1.068
 CLASS+1.067
Neg logit contributions
angered-1.133
genre-1.023
adem-0.917
bnb-0.904
arios-0.888
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
illac+0.012
Leaks+0.012
ILY+0.012
 Nib+0.011
 CLASS+0.011
Neg logit contributions
angered-0.014
genre-0.013
adem-0.012
bnb-0.011
arios-0.011
TokenClub
Token ID42350
Feature activation+3.61e-01

Pos logit contributions
illac+0.282
Leaks+0.269
ILY+0.266
 Nib+0.265
 CLASS+0.263
Neg logit contributions
angered-0.332
genre-0.305
adem-0.274
bnb-0.268
arios-0.265
Token
Token ID198
Feature activation+1.45e-02

Pos logit contributions
angered+1.042
genre+0.950
adem+0.852
bnb+0.836
arios+0.822
Neg logit contributions
illac-0.992
Leaks-0.945
ILY-0.941
 Nib-0.922
-0.914
Token
Token ID198
Feature activation+2.94e-02

Pos logit contributions
angered+0.044
genre+0.040
adem+0.036
bnb+0.035
arios+0.035
Neg logit contributions
illac-0.038
Leaks-0.036
ILY-0.036
 Nib-0.035
 CLASS-0.035
TokenBay
Token ID15262
Feature activation-1.07e-01

Pos logit contributions
angered+0.091
genre+0.084
adem+0.075
bnb+0.074
arios+0.073
Neg logit contributions
illac-0.075
Leaks-0.071
ILY-0.071
 Nib-0.071
 CLASS-0.070
Tokenern
Token ID1142
Feature activation-1.51e+00

Pos logit contributions
illac+0.248
Leaks+0.236
ILY+0.235
 Nib+0.230
 CLASS+0.230
Neg logit contributions
angered-0.358
genre-0.329
adem-0.301
bnb-0.296
arios-0.293
Token Munich
Token ID22418
Feature activation-7.48e-01

Pos logit contributions
illac+4.170
Leaks+4.059
 Nib+3.984
ILY+3.971
 CLASS+3.968
Neg logit contributions
angered-4.210
genre-3.849
bnb-3.367
adem-3.335
arios-3.284
Token Jun
Token ID7653
Feature activation+3.59e-01

Pos logit contributions
illac+1.932
Leaks+1.869
ILY+1.838
 Nib+1.834
 CLASS+1.821
Neg logit contributions
angered-2.258
genre-2.070
adem-1.841
bnb-1.836
arios-1.804
Tokeniors
Token ID12706
Feature activation+5.71e-03

Pos logit contributions
angered+1.235
genre+1.142
adem+1.045
bnb+1.028
arios+1.018
Neg logit contributions
illac-0.780
Leaks-0.750
ILY-0.743
 Nib-0.730
 CLASS-0.727
Token[
Token ID58
Feature activation-1.14e-02

Pos logit contributions
angered+0.017
genre+0.015
adem+0.014
bnb+0.014
arios+0.013
Neg logit contributions
illac-0.015
Leaks-0.015
ILY-0.015
 Nib-0.014
-0.014
Token92
Token ID5892
Feature activation+2.34e-01

Pos logit contributions
illac+0.032
Leaks+0.031
ILY+0.031
 Nib+0.030
 CLASS+0.030
Neg logit contributions
angered-0.032
genre-0.029
adem-0.026
bnb-0.026
arios-0.025
Token.
Token ID13
Feature activation-7.58e-02

Pos logit contributions
illac+0.383
Leaks+0.371
ILY+0.364
 Nib+0.360
 CLASS+0.357
Neg logit contributions
angered-0.403
genre-0.368
adem-0.327
bnb-0.323
arios-0.318
Token
Token ID198
Feature activation-9.61e-02

Pos logit contributions
illac+0.201
Leaks+0.194
ILY+0.191
 Nib+0.188
 CLASS+0.186
Neg logit contributions
angered-0.226
genre-0.207
adem-0.185
bnb-0.182
arios-0.180
Token
Token ID198
Feature activation-3.03e-01

Pos logit contributions
illac+0.246
Leaks+0.238
ILY+0.235
 Nib+0.232
 CLASS+0.230
Neg logit contributions
angered-0.294
genre-0.269
adem-0.243
bnb-0.240
arios-0.236
TokenUN
Token ID4944
Feature activation-7.75e-02

Pos logit contributions
illac+0.707
Leaks+0.675
ILY+0.662
 Nib+0.658
 CLASS+0.650
Neg logit contributions
angered-1.003
genre-0.927
adem-0.837
bnb-0.827
arios-0.817
TokenDE
Token ID7206
Feature activation-5.84e-01

Pos logit contributions
illac+0.200
Leaks+0.191
ILY+0.188
 Nib+0.186
 CLASS+0.184
Neg logit contributions
angered-0.238
genre-0.218
adem-0.195
bnb-0.193
arios-0.190
TokenAD
Token ID2885
Feature activation-1.45e+00

Pos logit contributions
illac+1.396
Leaks+1.347
ILY+1.335
 Nib+1.309
 CLASS+1.307
Neg logit contributions
angered-1.882
genre-1.733
adem-1.568
bnb-1.554
arios-1.533
Token*
Token ID9
Feature activation-5.94e-01

Pos logit contributions
illac+3.577
ILY+3.523
 CLASS+3.506
Leaks+3.432
 Nib+3.407
Neg logit contributions
angered-4.473
genre-4.126
adem-3.750
bnb-3.667
arios-3.660
Token
Token ID198
Feature activation-1.24e-01

Pos logit contributions
illac+1.541
Leaks+1.486
ILY+1.467
 Nib+1.448
 CLASS+1.442
Neg logit contributions
angered-1.803
genre-1.649
adem-1.481
bnb-1.463
arios-1.442
Token
Token ID198
Feature activation-2.54e-01

Pos logit contributions
illac+0.315
Leaks+0.306
ILY+0.302
 Nib+0.297
 CLASS+0.296
Neg logit contributions
angered-0.381
genre-0.350
adem-0.315
bnb-0.312
arios-0.307
Token+
Token ID10
Feature activation+7.48e-02

Pos logit contributions
illac+0.756
Leaks+0.728
ILY+0.718
 Nib+0.715
 CLASS+0.707
Neg logit contributions
angered-0.680
genre-0.616
adem-0.541
bnb-0.533
arios-0.524
Token Soul
Token ID8653
Feature activation+2.52e-01

Pos logit contributions
angered+0.232
genre+0.209
adem+0.189
bnb+0.185
arios+0.184
Neg logit contributions
illac-0.192
Leaks-0.183
ILY-0.182
-0.177
 CLASS-0.175
Token book
Token ID1492
Feature activation-3.71e-01

Pos logit contributions
angered+0.327
genre+0.296
adem+0.262
bnb+0.258
arios+0.254
Neg logit contributions
illac-0.352
Leaks-0.340
ILY-0.336
 Nib-0.332
 CLASS-0.330
Token,
Token ID11
Feature activation-3.12e-01

Pos logit contributions
illac+1.021
Leaks+0.988
ILY+0.974
 Nib+0.963
 CLASS+0.958
Neg logit contributions
angered-1.068
genre-0.972
adem-0.866
bnb-0.856
arios-0.843
Token
Token ID564
Feature activation-4.01e-01

Pos logit contributions
illac+0.884
Leaks+0.854
ILY+0.843
 Nib+0.834
 CLASS+0.829
Neg logit contributions
angered-0.871
genre-0.790
adem-0.701
bnb-0.692
arios-0.681
Token
Token ID250
Feature activation-2.73e-01

Pos logit contributions
illac+1.208
Leaks+1.173
ILY+1.158
 Nib+1.145
 CLASS+1.140
Neg logit contributions
angered-1.050
genre-0.946
adem-0.832
bnb-0.820
arios-0.807
TokenC
Token ID34
Feature activation+6.58e-02

Pos logit contributions
illac+0.663
Leaks+0.636
ILY+0.628
 Nib+0.620
 CLASS+0.615
Neg logit contributions
angered-0.876
genre-0.806
adem-0.727
bnb-0.719
arios-0.709
Tokenarn
Token ID1501
Feature activation-1.43e+00

Pos logit contributions
angered+0.174
genre+0.156
adem+0.138
bnb+0.136
arios+0.134
Neg logit contributions
illac-0.198
Leaks-0.191
ILY-0.188
 Nib-0.188
 CLASS-0.186
Tokenal
Token ID282
Feature activation-3.78e-01

Pos logit contributions
illac+3.904
Leaks+3.773
ILY+3.689
 Nib+3.669
 CLASS+3.629
Neg logit contributions
angered-4.072
genre-3.722
adem-3.289
bnb-3.281
arios-3.202
Token Abuse
Token ID24221
Feature activation-2.47e-01

Pos logit contributions
illac+0.961
Leaks+0.923
ILY+0.913
 Nib+0.900
 CLASS+0.897
Neg logit contributions
angered-1.169
genre-1.071
adem-0.963
bnb-0.952
arios-0.939
Token by
Token ID416
Feature activation-3.67e-01

Pos logit contributions
illac+0.670
Leaks+0.647
ILY+0.638
 Nib+0.631
 CLASS+0.626
Neg logit contributions
angered-0.722
genre-0.658
adem-0.587
bnb-0.580
arios-0.571
Token De
Token ID1024
Feature activation-4.62e-01

Pos logit contributions
illac+0.920
Leaks+0.886
ILY+0.873
 Nib+0.862
 CLASS+0.857
Neg logit contributions
angered-1.149
genre-1.054
adem-0.949
bnb-0.938
arios-0.925
Tokence
Token ID344
Feature activation-7.60e-01

Pos logit contributions
illac+1.542
Leaks+1.499
ILY+1.483
 Nib+1.469
 CLASS+1.462
Neg logit contributions
angered-1.060
genre-0.941
adem-0.809
bnb-0.796
arios-0.779
Token
Token ID198
Feature activation+4.60e-01

Pos logit contributions
angered+0.110
genre+0.101
adem+0.090
bnb+0.089
arios+0.088
Neg logit contributions
illac-0.092
Leaks-0.089
ILY-0.087
 Nib-0.086
 CLASS-0.086
Token
Token ID198
Feature activation+3.08e-01

Pos logit contributions
angered+1.338
genre+1.217
adem+1.074
bnb+1.062
arios+1.044
Neg logit contributions
illac-1.266
Leaks-1.198
ILY-1.186
 Nib-1.184
 CLASS-1.179
Token47
Token ID2857
Feature activation+4.03e-01

Pos logit contributions
angered+0.977
genre+0.907
adem+0.811
bnb+0.793
arios+0.785
Neg logit contributions
illac-0.759
Leaks-0.716
 Nib-0.714
ILY-0.710
 CLASS-0.708
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
angered+1.229
genre+1.122
adem+1.012
bnb+0.997
arios+0.983
Neg logit contributions
illac-1.035
Leaks-1.003
ILY-0.986
 Nib-0.961
-0.959
Token Rec
Token ID3311
Feature activation+3.64e-01

Pos logit contributions
angered+0.341
genre+0.311
adem+0.278
bnb+0.275
arios+0.271
Neg logit contributions
illac-0.298
Leaks-0.288
ILY-0.283
 Nib-0.278
 CLASS-0.276
Tokeny
Token ID88
Feature activation-1.38e+00

Pos logit contributions
angered+1.052
genre+0.961
adem+0.869
bnb+0.848
arios+0.836
Neg logit contributions
illac-0.989
Leaks-0.960
ILY-0.955
 Nib-0.937
 CLASS-0.931
Tokencling
Token ID8493
Feature activation-1.93e-01

Pos logit contributions
illac+3.305
Leaks+3.126
ILY+3.056
 Nib+3.050
+3.050
Neg logit contributions
angered-4.403
genre-4.074
bnb-3.639
adem-3.631
arios-3.583
Token scheme
Token ID7791
Feature activation+1.28e-01

Pos logit contributions
illac+0.502
Leaks+0.485
ILY+0.478
 Nib+0.473
 CLASS+0.470
Neg logit contributions
angered-0.581
genre-0.532
adem-0.477
bnb-0.471
arios-0.464
Token [
Token ID685
Feature activation-1.80e-01

Pos logit contributions
angered+0.382
genre+0.349
adem+0.313
bnb+0.309
arios+0.305
Neg logit contributions
illac-0.340
Leaks-0.328
ILY-0.323
 Nib-0.319
 CLASS-0.317
Tokenvia
Token ID8869
Feature activation+8.85e-02

Pos logit contributions
illac+0.385
Leaks+0.366
ILY+0.358
 Nib+0.354
 CLASS+0.350
Neg logit contributions
angered-0.633
genre-0.588
adem-0.534
bnb-0.530
arios-0.522
Token]
Token ID60
Feature activation-2.74e-01

Pos logit contributions
angered+0.265
genre+0.242
adem+0.217
bnb+0.215
arios+0.211
Neg logit contributions
illac-0.234
Leaks-0.225
ILY-0.222
 Nib-0.218
 CLASS-0.217
Token with
Token ID351
Feature activation+6.91e-02

Pos logit contributions
angered+0.340
genre+0.312
adem+0.283
bnb+0.279
arios+0.275
Neg logit contributions
illac-0.262
Leaks-0.251
ILY-0.248
 Nib-0.243
 CLASS-0.240
Token 25
Token ID1679
Feature activation-3.51e-02

Pos logit contributions
angered+0.221
genre+0.203
adem+0.184
bnb+0.181
arios+0.179
Neg logit contributions
illac-0.167
Leaks-0.162
ILY-0.159
 Nib-0.156
-0.154
Token60
Token ID1899
Feature activation-3.16e-01

Pos logit contributions
illac+0.090
Leaks+0.087
ILY+0.085
 Nib+0.084
 CLASS+0.084
Neg logit contributions
angered-0.108
genre-0.099
adem-0.089
bnb-0.088
arios-0.086
Token CU
Token ID29369
Feature activation-8.41e-01

Pos logit contributions
illac+0.762
Leaks+0.734
ILY+0.723
 Nib+0.717
 CLASS+0.715
Neg logit contributions
angered-1.013
genre-0.931
adem-0.843
bnb-0.830
arios-0.819
TokenDA
Token ID5631
Feature activation-1.11e+00

Pos logit contributions
illac+2.208
Leaks+2.185
ILY+2.149
 Nib+2.127
 CLASS+2.125
Neg logit contributions
angered-2.483
genre-2.256
adem-2.027
bnb-1.996
arios-1.943
Token cores
Token ID21758
Feature activation-1.34e+00

Pos logit contributions
illac+2.893
Leaks+2.808
ILY+2.776
 Nib+2.739
 CLASS+2.736
Neg logit contributions
angered-3.360
genre-3.069
adem-2.731
bnb-2.710
arios-2.656
Token and
Token ID290
Feature activation-1.76e-01

Pos logit contributions
illac+3.330
Leaks+3.184
ILY+3.183
 CLASS+3.151
 Nib+3.142
Neg logit contributions
angered-4.147
genre-3.782
adem-3.377
bnb-3.345
arios-3.258
Token 20
Token ID1160
Feature activation+1.86e-02

Pos logit contributions
illac+0.388
Leaks+0.371
ILY+0.365
 Nib+0.360
 CLASS+0.357
Neg logit contributions
angered-0.601
genre-0.556
adem-0.506
bnb-0.500
arios-0.495
Token SM
Token ID9447
Feature activation-6.95e-02

Pos logit contributions
angered+0.058
genre+0.053
adem+0.048
bnb+0.047
arios+0.047
Neg logit contributions
illac-0.047
Leaks-0.045
ILY-0.045
 Nib-0.044
 CLASS-0.043
Token units
Token ID4991
Feature activation-3.98e-01

Pos logit contributions
illac+0.170
Leaks+0.163
ILY+0.160
 Nib+0.159
 CLASS+0.157
Neg logit contributions
angered-0.222
genre-0.204
adem-0.184
bnb-0.182
arios-0.180
Token.
Token ID13
Feature activation-2.29e-01

Pos logit contributions
illac+1.052
Leaks+1.013
ILY+1.002
 Nib+0.990
 CLASS+0.986
Neg logit contributions
angered-1.190
genre-1.086
adem-0.972
bnb-0.960
arios-0.944
Token will
Token ID481
Feature activation-1.11e-01

Pos logit contributions
illac+0.050
Leaks+0.048
ILY+0.047
 Nib+0.047
 CLASS+0.046
Neg logit contributions
angered-0.069
genre-0.064
adem-0.058
bnb-0.057
arios-0.056
Token know
Token ID760
Feature activation+8.60e-02

Pos logit contributions
illac+0.264
Leaks+0.253
ILY+0.250
 Nib+0.246
 CLASS+0.245
Neg logit contributions
angered-0.358
genre-0.330
adem-0.299
bnb-0.295
arios-0.291
Token in
Token ID287
Feature activation-1.21e-01

Pos logit contributions
angered+0.262
genre+0.240
adem+0.215
bnb+0.213
arios+0.210
Neg logit contributions
illac-0.223
Leaks-0.214
ILY-0.211
 Nib-0.209
 CLASS-0.207
Token only
Token ID691
Feature activation-1.83e-01

Pos logit contributions
illac+0.294
Leaks+0.282
ILY+0.279
 Nib+0.274
 CLASS+0.272
Neg logit contributions
angered-0.388
genre-0.357
adem-0.323
bnb-0.319
arios-0.314
Token a
Token ID257
Feature activation-4.08e-01

Pos logit contributions
illac+0.432
Leaks+0.415
ILY+0.409
 Nib+0.404
 CLASS+0.402
Neg logit contributions
angered-0.599
genre-0.552
adem-0.499
bnb-0.494
arios-0.488
Token matter
Token ID2300
Feature activation-1.33e+00

Pos logit contributions
illac+1.263
Leaks+1.235
ILY+1.216
 Nib+1.205
 CLASS+1.200
Neg logit contributions
angered-1.026
genre-0.918
adem-0.805
bnb-0.791
arios-0.777
Token of
Token ID286
Feature activation-7.60e-01

Pos logit contributions
illac+3.265
ILY+3.222
Leaks+3.214
 Nib+3.163
 CLASS+3.121
Neg logit contributions
angered-3.953
genre-3.660
adem-3.335
arios-3.238
bnb-3.234
Token days
Token ID1528
Feature activation-5.26e-01

Pos logit contributions
illac+1.491
Leaks+1.439
 Nib+1.405
ILY+1.404
 CLASS+1.388
Neg logit contributions
angered-2.747
genre-2.540
adem-2.338
bnb-2.321
arios-2.285
Token,
Token ID11
Feature activation+2.51e-01

Pos logit contributions
illac+1.368
Leaks+1.320
ILY+1.305
 Nib+1.291
 CLASS+1.283
Neg logit contributions
angered-1.595
genre-1.454
adem-1.305
bnb-1.284
arios-1.265
Token but
Token ID475
Feature activation+2.42e-01

Pos logit contributions
angered+0.667
genre+0.603
adem+0.531
bnb+0.524
arios+0.515
Neg logit contributions
illac-0.747
Leaks-0.724
ILY-0.715
 Nib-0.707
 CLASS-0.703
Token if
Token ID611
Feature activation+4.46e-02

Pos logit contributions
angered+0.724
genre+0.662
adem+0.592
bnb+0.585
arios+0.578
Neg logit contributions
illac-0.639
Leaks-0.616
ILY-0.608
 Nib-0.599
 CLASS-0.596
Token a
Token ID257
Feature activation+2.01e-01

Pos logit contributions
angered+1.268
genre+1.156
adem+1.036
bnb+1.025
arios+1.008
Neg logit contributions
illac-1.123
Leaks-1.085
ILY-1.065
 Nib-1.048
 CLASS-1.047
Token friend
Token ID1545
Feature activation+2.72e-01

Pos logit contributions
angered+0.583
genre+0.530
adem+0.473
bnb+0.467
arios+0.460
Neg logit contributions
illac-0.547
Leaks-0.529
ILY-0.520
 Nib-0.513
 CLASS-0.510
Token clarified
Token ID28464
Feature activation-1.49e-02

Pos logit contributions
angered+0.795
genre+0.725
adem+0.647
bnb+0.639
arios+0.630
Neg logit contributions
illac-0.736
Leaks-0.711
ILY-0.701
 Nib-0.693
 CLASS-0.689
Token
Token ID960
Feature activation-3.23e-02

Pos logit contributions
illac+0.038
Leaks+0.037
ILY+0.036
 Nib+0.036
 CLASS+0.036
Neg logit contributions
angered-0.046
genre-0.042
adem-0.038
bnb-0.037
arios-0.037
Tokenpr
Token ID1050
Feature activation-9.37e-02

Pos logit contributions
illac+0.085
Leaks+0.082
ILY+0.081
 Nib+0.080
 CLASS+0.079
Neg logit contributions
angered-0.097
genre-0.089
adem-0.080
bnb-0.079
arios-0.077
Tokenide
Token ID485
Feature activation-1.33e+00

Pos logit contributions
illac+0.264
Leaks+0.257
ILY+0.253
 Nib+0.251
 CLASS+0.249
Neg logit contributions
angered-0.263
genre-0.239
adem-0.213
bnb-0.209
arios-0.205
Tokenfully
Token ID2759
Feature activation-4.20e-01

Pos logit contributions
illac+3.353
ILY+3.231
Leaks+3.200
 Nib+3.175
 CLASS+3.123
Neg logit contributions
angered-4.021
genre-3.689
adem-3.283
arios-3.247
bnb-3.231
Token and
Token ID290
Feature activation-6.40e-03

Pos logit contributions
illac+1.131
Leaks+1.092
ILY+1.079
 Nib+1.067
 CLASS+1.061
Neg logit contributions
angered-1.229
genre-1.121
adem-0.999
bnb-0.986
arios-0.975
Token unp
Token ID8593
Feature activation-2.75e-01

Pos logit contributions
illac+0.015
Leaks+0.014
ILY+0.014
 Nib+0.014
 CLASS+0.014
Neg logit contributions
angered-0.021
genre-0.019
adem-0.018
bnb-0.017
arios-0.017
Tokenrompt
Token ID45700
Feature activation-5.96e-01

Pos logit contributions
illac+0.472
Leaks+0.446
ILY+0.435
 Nib+0.422
 CLASS+0.421
Neg logit contributions
angered-1.068
genre-1.002
bnb-0.916
adem-0.913
arios-0.906
Tokened
Token ID276
Feature activation+2.78e-02

Pos logit contributions
illac+1.343
Leaks+1.288
ILY+1.266
 Nib+1.247
 CLASS+1.237
Neg logit contributions
angered-1.977
genre-1.832
adem-1.650
bnb-1.648
arios-1.613
TokenJoshua
Token ID47740
Feature activation+3.80e-01

Pos logit contributions
angered+0.031
genre+0.029
adem+0.026
bnb+0.026
arios+0.026
Neg logit contributions
illac-0.023
Leaks-0.022
ILY-0.021
 Nib-0.021
 CLASS-0.021
Token Roberts
Token ID10918
Feature activation+8.66e-03

Pos logit contributions
angered+0.972
genre+0.870
adem+0.776
arios+0.755
bnb+0.748
Neg logit contributions
illac-1.155
Leaks-1.124
ILY-1.113
 CLASS-1.102
-1.097
Token
Token ID198
Feature activation+3.06e-01

Pos logit contributions
angered+0.026
genre+0.023
adem+0.021
bnb+0.021
arios+0.020
Neg logit contributions
illac-0.023
Leaks-0.022
ILY-0.022
 Nib-0.022
 CLASS-0.022
Token
Token ID198
Feature activation+1.36e-01

Pos logit contributions
angered+0.897
genre+0.815
adem+0.724
bnb+0.715
arios+0.706
Neg logit contributions
illac-0.833
Leaks-0.792
ILY-0.784
 Nib-0.777
 CLASS-0.773
TokenDE
Token ID7206
Feature activation-1.46e-01

Pos logit contributions
angered+0.428
genre+0.394
adem+0.352
bnb+0.345
arios+0.342
Neg logit contributions
illac-0.339
 Nib-0.318
Leaks-0.317
 CLASS-0.314
ILY-0.314
TokenAD
Token ID2885
Feature activation-1.30e+00

Pos logit contributions
illac+0.339
Leaks+0.325
ILY+0.319
 Nib+0.315
 CLASS+0.313
Neg logit contributions
angered-0.482
genre-0.445
adem-0.403
bnb-0.399
arios-0.394
TokenLIN
Token ID34509
Feature activation+2.55e-01

Pos logit contributions
illac+3.527
ILY+3.475
 CLASS+3.443
Leaks+3.425
 Nib+3.342
Neg logit contributions
angered-3.708
genre-3.423
adem-3.062
bnb-3.016
arios-2.964
TokenES
Token ID1546
Feature activation+3.89e-01

Pos logit contributions
angered+0.793
genre+0.730
adem+0.651
bnb+0.647
arios+0.643
Neg logit contributions
illac-0.645
Leaks-0.614
ILY-0.600
 Nib-0.596
-0.590
Token LO
Token ID17579
Feature activation+3.27e-02

Pos logit contributions
angered+1.159
genre+1.053
adem+0.937
bnb+0.929
arios+0.921
Neg logit contributions
illac-1.040
Leaks-0.993
ILY-0.960
 Nib-0.959
-0.956
TokenOM
Token ID2662
Feature activation+7.66e-01

Pos logit contributions
angered+0.098
genre+0.089
adem+0.079
bnb+0.079
arios+0.078
Neg logit contributions
illac-0.087
Leaks-0.083
 Nib-0.081
ILY-0.080
-0.080
Token
Token ID198
Feature activation+3.57e-01

Pos logit contributions
angered+2.262
genre+2.036
bnb+1.798
 RELE+1.796
adem+1.791
Neg logit contributions
illac-2.055
Leaks-1.948
 Nib-1.891
-1.867
ILY-1.832
Token year
Token ID614
Feature activation+5.87e-01

Pos logit contributions
angered+0.611
genre+0.556
adem+0.498
bnb+0.490
arios+0.485
Neg logit contributions
illac-0.572
Leaks-0.551
ILY-0.544
 Nib-0.536
 CLASS-0.534
Token has
Token ID468
Feature activation+2.99e-01

Pos logit contributions
angered+1.737
genre+1.573
adem+1.422
bnb+1.392
arios+1.386
Neg logit contributions
illac-1.574
Leaks-1.513
ILY-1.493
 Nib-1.468
 CLASS-1.467
Token been
Token ID587
Feature activation+9.75e-03

Pos logit contributions
angered+0.907
genre+0.829
adem+0.744
bnb+0.734
arios+0.726
Neg logit contributions
illac-0.777
Leaks-0.747
ILY-0.736
 Nib-0.726
 CLASS-0.723
Token an
Token ID281
Feature activation+2.05e-01

Pos logit contributions
angered+0.030
genre+0.028
adem+0.025
bnb+0.024
arios+0.024
Neg logit contributions
illac-0.025
Leaks-0.024
ILY-0.024
 Nib-0.023
 CLASS-0.023
Token un
Token ID555
Feature activation-4.51e-01

Pos logit contributions
angered+0.623
genre+0.567
adem+0.508
bnb+0.500
arios+0.495
Neg logit contributions
illac-0.531
Leaks-0.511
ILY-0.503
 Nib-0.498
 CLASS-0.493
Tokenmit
Token ID2781
Feature activation-1.28e+00

Pos logit contributions
illac+1.259
Leaks+1.217
ILY+1.202
 Nib+1.187
 CLASS+1.182
Neg logit contributions
angered-1.278
genre-1.162
adem-1.032
bnb-1.022
arios-1.007
Tokenigated
Token ID26963
Feature activation-6.98e-02

Pos logit contributions
illac+1.560
Leaks+1.414
 Nib+1.394
 CLASS+1.367
Men+1.358
Neg logit contributions
angered-5.415
genre-5.140
bnb-4.821
adem-4.757
arios-4.704
Token disaster
Token ID9336
Feature activation+2.81e-01

Pos logit contributions
illac+0.209
Leaks+0.203
ILY+0.200
 Nib+0.198
 CLASS+0.197
Neg logit contributions
angered-0.184
genre-0.166
adem-0.146
bnb-0.144
arios-0.141
Token.
Token ID13
Feature activation-5.96e-03

Pos logit contributions
angered+0.785
genre+0.718
adem+0.633
bnb+0.625
arios+0.614
Neg logit contributions
illac-0.800
Leaks-0.776
ILY-0.759
 Nib-0.751
 CLASS-0.748
Token But
Token ID887
Feature activation-6.15e-02

Pos logit contributions
illac+0.015
Leaks+0.015
ILY+0.015
 Nib+0.014
 CLASS+0.014
Neg logit contributions
angered-0.018
genre-0.017
adem-0.015
bnb-0.015
arios-0.015
Token what
Token ID644
Feature activation-4.17e-01

Pos logit contributions
illac+0.163
Leaks+0.157
ILY+0.155
 Nib+0.153
 CLASS+0.152
Neg logit contributions
angered-0.183
genre-0.168
adem-0.150
bnb-0.148
arios-0.146
Token all
Token ID477
Feature activation-4.08e-02

Pos logit contributions
angered+1.341
genre+1.220
adem+1.106
bnb+1.085
arios+1.077
Neg logit contributions
illac-1.129
Leaks-1.085
ILY-1.073
-1.045
 Nib-1.040
Token came
Token ID1625
Feature activation-1.96e-01

Pos logit contributions
illac+0.105
Leaks+0.101
ILY+0.100
 Nib+0.099
 CLASS+0.098
Neg logit contributions
angered-0.124
genre-0.114
adem-0.102
bnb-0.101
arios-0.100
Token together
Token ID1978
Feature activation+8.48e-02

Pos logit contributions
illac+0.518
Leaks+0.498
ILY+0.490
 Nib+0.485
 CLASS+0.482
Neg logit contributions
angered-0.584
genre-0.534
adem-0.479
bnb-0.472
arios-0.467
Token in
Token ID287
Feature activation-1.77e-01

Pos logit contributions
angered+0.254
genre+0.232
adem+0.208
bnb+0.206
arios+0.203
Neg logit contributions
illac-0.223
Leaks-0.215
ILY-0.212
 Nib-0.208
 CLASS-0.208
Token a
Token ID257
Feature activation-3.75e-01

Pos logit contributions
illac+0.435
Leaks+0.417
ILY+0.412
 Nib+0.404
 CLASS+0.402
Neg logit contributions
angered-0.565
genre-0.519
adem-0.469
bnb-0.464
arios-0.458
Token matter
Token ID2300
Feature activation-1.24e+00

Pos logit contributions
illac+1.108
Leaks+1.074
ILY+1.060
 Nib+1.051
 CLASS+1.045
Neg logit contributions
angered-1.005
genre-0.907
adem-0.800
bnb-0.789
arios-0.776
Token of
Token ID286
Feature activation-7.78e-01

Pos logit contributions
illac+3.142
Leaks+3.084
 Nib+3.047
ILY+3.041
 CLASS+3.023
Neg logit contributions
angered-3.631
genre-3.319
adem-3.026
bnb-2.939
arios-2.932
Token weeks
Token ID2745
Feature activation-7.90e-01

Pos logit contributions
illac+1.557
Leaks+1.503
 Nib+1.469
ILY+1.467
 CLASS+1.455
Neg logit contributions
angered-2.793
genre-2.594
adem-2.365
bnb-2.358
arios-2.316
Token,"
Token ID553
Feature activation-7.54e-02

Pos logit contributions
illac+2.203
Leaks+2.125
ILY+2.109
 Nib+2.092
 CLASS+2.080
Neg logit contributions
angered-2.235
genre-2.028
adem-1.808
bnb-1.760
arios-1.745
Token said
Token ID531
Feature activation-3.42e-01

Pos logit contributions
illac+0.191
Leaks+0.183
ILY+0.181
 CLASS+0.177
 Nib+0.177
Neg logit contributions
angered-0.234
genre-0.215
adem-0.192
bnb-0.191
arios-0.189
Token Mel
Token ID5616
Feature activation-2.33e-01

Pos logit contributions
illac+0.930
Leaks+0.898
ILY+0.886
 Nib+0.874
 CLASS+0.870
Neg logit contributions
angered-0.996
genre-0.907
adem-0.810
bnb-0.799
arios-0.788
Token
Token ID198
Feature activation-1.86e-01

Pos logit contributions
illac+0.142
Leaks+0.138
ILY+0.135
 Nib+0.134
 CLASS+0.133
Neg logit contributions
angered-0.167
genre-0.153
adem-0.138
bnb-0.136
arios-0.134
TokenThe
Token ID464
Feature activation-1.43e-01

Pos logit contributions
illac+0.463
Leaks+0.440
ILY+0.434
 Nib+0.431
 CLASS+0.428
Neg logit contributions
angered-0.586
genre-0.539
adem-0.484
bnb-0.476
arios-0.472
Token rest
Token ID1334
Feature activation+2.82e-01

Pos logit contributions
illac+0.367
Leaks+0.352
ILY+0.347
 Nib+0.340
 CLASS+0.338
Neg logit contributions
angered-0.438
genre-0.401
adem-0.361
bnb-0.356
arios-0.352
Token of
Token ID286
Feature activation-2.26e-01

Pos logit contributions
angered+0.736
genre+0.654
adem+0.575
bnb+0.567
arios+0.558
Neg logit contributions
illac-0.857
Leaks-0.837
ILY-0.820
 Nib-0.807
-0.804
Token the
Token ID262
Feature activation-1.35e-01

Pos logit contributions
illac+0.551
Leaks+0.528
ILY+0.518
+0.507
 Nib+0.506
Neg logit contributions
angered-0.723
genre-0.666
adem-0.601
bnb-0.593
arios-0.586
Token class
Token ID1398
Feature activation-1.22e+00

Pos logit contributions
illac+0.321
Leaks+0.307
ILY+0.300
+0.293
 Nib+0.292
Neg logit contributions
angered-0.440
genre-0.406
adem-0.368
bnb-0.362
arios-0.358
Token are
Token ID389
Feature activation-3.62e-02

Pos logit contributions
illac+2.891
Leaks+2.756
 Nib+2.749
ILY+2.739
 CLASS+2.732
Neg logit contributions
angered-3.930
genre-3.642
adem-3.261
bnb-3.247
arios-3.194
Token the
Token ID262
Feature activation-3.12e-01

Pos logit contributions
illac+0.097
Leaks+0.094
ILY+0.092
 Nib+0.091
 CLASS+0.090
Neg logit contributions
angered-0.107
genre-0.097
adem-0.087
bnb-0.086
arios-0.085
Token 99
Token ID7388
Feature activation-2.48e-01

Pos logit contributions
illac+0.848
Leaks+0.819
ILY+0.808
 Nib+0.799
 CLASS+0.794
Neg logit contributions
angered-0.907
genre-0.827
adem-0.738
bnb-0.729
arios-0.718
Token%;
Token ID26525
Feature activation-8.54e-03

Pos logit contributions
illac+0.692
Leaks+0.667
ILY+0.660
 Nib+0.651
 CLASS+0.646
Neg logit contributions
angered-0.704
genre-0.639
adem-0.569
bnb-0.561
arios-0.553
Token Cart
Token ID13690
Feature activation-2.79e-01

Pos logit contributions
illac+0.022
Leaks+0.021
ILY+0.021
 Nib+0.021
 CLASS+0.021
Neg logit contributions
angered-0.026
genre-0.024
adem-0.021
bnb-0.021
arios-0.021
Token.)
Token ID2014
Feature activation-2.09e-01

Pos logit contributions
angered+1.717
genre+1.562
adem+1.414
bnb+1.395
arios+1.363
Neg logit contributions
illac-1.689
Leaks-1.646
ILY-1.609
-1.568
 CLASS-1.567
Token
Token ID198
Feature activation+1.77e-01

Pos logit contributions
illac+0.553
Leaks+0.531
ILY+0.524
 Nib+0.512
 CLASS+0.512
Neg logit contributions
angered-0.626
genre-0.571
adem-0.507
bnb-0.503
arios-0.495
Token
Token ID198
Feature activation+7.28e-02

Pos logit contributions
angered+0.529
genre+0.482
adem+0.431
bnb+0.426
arios+0.420
Neg logit contributions
illac-0.468
Leaks-0.450
ILY-0.444
 Nib-0.439
 CLASS-0.436
TokenWar
Token ID13195
Feature activation-3.67e-01

Pos logit contributions
angered+0.234
genre+0.215
adem+0.192
bnb+0.188
arios+0.186
Neg logit contributions
illac-0.179
Leaks-0.168
 Nib-0.167
 CLASS-0.166
ILY-0.166
Tokenner
Token ID1008
Feature activation-7.02e-01

Pos logit contributions
illac+1.098
Leaks+1.066
ILY+1.050
 Nib+1.039
 CLASS+1.034
Neg logit contributions
angered-0.970
genre-0.874
adem-0.768
bnb-0.760
arios-0.745
Token Bros
Token ID14266
Feature activation-1.22e+00

Pos logit contributions
illac+1.320
Leaks+1.257
ILY+1.230
 Nib+1.210
 CLASS+1.198
Neg logit contributions
angered-2.630
genre-2.449
adem-2.250
bnb-2.227
arios-2.204
Token /
Token ID1220
Feature activation+2.01e-01

Pos logit contributions
illac+3.106
Leaks+2.986
ILY+2.941
 Nib+2.912
 CLASS+2.885
Neg logit contributions
angered-3.696
genre-3.402
adem-3.057
bnb-3.012
arios-2.985
Token Courtesy
Token ID22984
Feature activation-1.64e-02

Pos logit contributions
angered+0.554
genre+0.501
adem+0.444
bnb+0.439
arios+0.430
Neg logit contributions
illac-0.580
Leaks-0.559
ILY-0.549
 Nib-0.540
-0.539
Token Everett
Token ID36815
Feature activation-3.00e-01

Pos logit contributions
illac+0.046
Leaks+0.045
ILY+0.044
 CLASS+0.043
 Nib+0.043
Neg logit contributions
angered-0.046
genre-0.042
adem-0.037
bnb-0.037
arios-0.036
Token Collection
Token ID12251
Feature activation-4.98e-01

Pos logit contributions
illac+0.634
Leaks+0.600
ILY+0.591
 Nib+0.580
 CLASS+0.576
Neg logit contributions
angered-1.057
genre-0.979
adem-0.896
bnb-0.887
arios-0.874
Token Amy
Token ID14235
Feature activation+1.38e-02

Pos logit contributions
illac+1.284
Leaks+1.238
ILY+1.220
 Nib+1.205
 CLASS+1.197
Neg logit contributions
angered-1.518
genre-1.390
adem-1.247
bnb-1.233
arios-1.215
Token component
Token ID7515
Feature activation+3.65e-01

Pos logit contributions
angered+0.705
genre+0.643
adem+0.576
bnb+0.569
arios+0.560
Neg logit contributions
illac-0.630
Leaks-0.606
ILY-0.596
 Nib-0.589
 CLASS-0.586
Token const
Token ID1500
Feature activation-7.44e-01

Pos logit contributions
angered+1.071
genre+0.975
adem+0.871
bnb+0.857
arios+0.847
Neg logit contributions
illac-0.986
Leaks-0.950
ILY-0.927
 Nib-0.921
 CLASS-0.911
Token float
Token ID12178
Feature activation-2.17e-01

Pos logit contributions
illac+2.025
Leaks+1.951
ILY+1.940
 Nib+1.910
 CLASS+1.909
Neg logit contributions
angered-2.152
genre-1.962
adem-1.751
bnb-1.733
arios-1.706
Token TA
Token ID21664
Feature activation+1.21e-01

Pos logit contributions
illac+0.574
Leaks+0.554
ILY+0.545
 Nib+0.539
 CLASS+0.536
Neg logit contributions
angered-0.649
genre-0.593
adem-0.531
bnb-0.524
arios-0.517
TokenU
Token ID52
Feature activation+1.59e-01

Pos logit contributions
angered+0.389
genre+0.360
adem+0.325
bnb+0.323
arios+0.316
Neg logit contributions
illac-0.290
Leaks-0.280
 Nib-0.272
 CLASS-0.268
ILY-0.267
Token =
Token ID796
Feature activation-1.22e+00

Pos logit contributions
angered+0.500
genre+0.461
adem+0.415
bnb+0.411
arios+0.402
Neg logit contributions
illac-0.397
Leaks-0.380
 Nib-0.372
ILY-0.369
 CLASS-0.365
Token 6
Token ID718
Feature activation+2.80e-02

Pos logit contributions
illac+2.837
 CLASS+2.710
ILY+2.704
Leaks+2.692
 Nib+2.682
Neg logit contributions
angered-3.961
genre-3.656
bnb-3.290
adem-3.272
arios-3.221
Token.
Token ID13
Feature activation+2.93e-01

Pos logit contributions
angered+0.082
genre+0.074
adem+0.066
bnb+0.065
arios+0.064
Neg logit contributions
illac-0.076
Leaks-0.074
ILY-0.072
 Nib-0.072
 CLASS-0.071
Token283
Token ID30290
Feature activation+1.02e-01

Pos logit contributions
angered+0.794
genre+0.718
adem+0.638
bnb+0.624
arios+0.616
Neg logit contributions
illac-0.859
Leaks-0.829
ILY-0.814
 Nib-0.810
 CLASS-0.802
Token185
Token ID21652
Feature activation-1.80e-01

Pos logit contributions
angered+0.295
genre+0.268
adem+0.239
bnb+0.236
arios+0.232
Neg logit contributions
illac-0.282
Leaks-0.272
ILY-0.267
 Nib-0.265
 CLASS-0.263
Token307
Token ID22996
Feature activation-7.56e-02

Pos logit contributions
illac+0.476
Leaks+0.459
ILY+0.454
 Nib+0.448
 CLASS+0.445
Neg logit contributions
angered-0.538
genre-0.491
adem-0.439
bnb-0.435
arios-0.428
Token more
Token ID517
Feature activation-2.25e-01

Pos logit contributions
angered+0.645
genre+0.595
adem+0.542
bnb+0.534
arios+0.528
Neg logit contributions
illac-0.462
Leaks-0.443
ILY-0.433
 Nib-0.426
 CLASS-0.423
Token than
Token ID621
Feature activation-3.57e-01

Pos logit contributions
illac+0.518
Leaks+0.497
ILY+0.489
 Nib+0.482
 CLASS+0.479
Neg logit contributions
angered-0.748
genre-0.690
adem-0.626
bnb-0.619
arios-0.611
Token 60
Token ID3126
Feature activation-4.28e-01

Pos logit contributions
illac+0.724
Leaks+0.691
ILY+0.682
 Nib+0.675
 CLASS+0.670
Neg logit contributions
angered-1.283
genre-1.190
adem-1.085
bnb-1.080
arios-1.065
Token%
Token ID4
Feature activation-1.72e-01

Pos logit contributions
illac+1.302
Leaks+1.262
ILY+1.248
 Nib+1.235
 CLASS+1.230
Neg logit contributions
angered-1.106
genre-0.996
adem-0.873
bnb-0.860
arios-0.846
Token of
Token ID286
Feature activation-3.48e-01

Pos logit contributions
illac+0.500
Leaks+0.485
ILY+0.478
 Nib+0.473
 CLASS+0.470
Neg logit contributions
angered-0.468
genre-0.423
adem-0.375
bnb-0.369
arios-0.364
Token respondents
Token ID14502
Feature activation-1.21e+00

Pos logit contributions
illac+0.953
Leaks+0.921
ILY+0.910
 Nib+0.900
 CLASS+0.895
Neg logit contributions
angered-1.005
genre-0.915
adem-0.814
bnb-0.804
arios-0.793
Token who
Token ID508
Feature activation-2.61e-01

Pos logit contributions
illac+3.147
Leaks+3.002
ILY+2.999
 Nib+2.947
 CLASS+2.946
Neg logit contributions
angered-3.639
genre-3.315
adem-2.949
bnb-2.941
arios-2.889
Token identified
Token ID5174
Feature activation-5.68e-01

Pos logit contributions
illac+0.632
Leaks+0.607
ILY+0.598
 Nib+0.591
 CLASS+0.587
Neg logit contributions
angered-0.836
genre-0.768
adem-0.692
bnb-0.686
arios-0.677
Token themselves
Token ID2405
Feature activation+3.38e-01

Pos logit contributions
illac+1.181
Leaks+1.125
ILY+1.110
 Nib+1.092
 CLASS+1.084
Neg logit contributions
angered-2.016
genre-1.870
adem-1.706
bnb-1.690
arios-1.671
Token as
Token ID355
Feature activation-3.41e-02

Pos logit contributions
angered+1.056
genre+0.966
adem+0.875
bnb+0.862
arios+0.850
Neg logit contributions
illac-0.843
Leaks-0.827
ILY-0.794
 Nib-0.790
 CLASS-0.778
Token middle
Token ID3504
Feature activation-2.45e-02

Pos logit contributions
illac+0.085
Leaks+0.082
ILY+0.081
 Nib+0.080
 CLASS+0.079
Neg logit contributions
angered-0.107
genre-0.098
adem-0.089
bnb-0.087
arios-0.086
Token stomach
Token ID11384
Feature activation-5.12e-01

Pos logit contributions
illac+0.029
Leaks+0.028
ILY+0.028
 Nib+0.027
 CLASS+0.027
Neg logit contributions
angered-0.033
genre-0.030
adem-0.027
bnb-0.027
arios-0.026
Token contents
Token ID10154
Feature activation+1.15e-01

Pos logit contributions
illac+1.351
Leaks+1.308
ILY+1.286
 Nib+1.275
 CLASS+1.265
Neg logit contributions
angered-1.525
genre-1.396
adem-1.246
bnb-1.236
arios-1.218
Token found
Token ID1043
Feature activation+6.45e-02

Pos logit contributions
angered+0.343
genre+0.312
adem+0.280
bnb+0.276
arios+0.272
Neg logit contributions
illac-0.308
Leaks-0.297
ILY-0.293
 Nib-0.289
 CLASS-0.288
Token a
Token ID257
Feature activation-5.84e-02

Pos logit contributions
angered+0.191
genre+0.173
adem+0.155
bnb+0.152
arios+0.151
Neg logit contributions
illac-0.173
Leaks-0.166
ILY-0.164
 CLASS-0.161
 Nib-0.161
Token con
Token ID369
Feature activation-4.54e-02

Pos logit contributions
illac+0.161
Leaks+0.156
ILY+0.154
 Nib+0.152
 CLASS+0.151
Neg logit contributions
angered-0.168
genre-0.153
adem-0.136
bnb-0.134
arios-0.132
Tokenge
Token ID469
Feature activation-1.21e+00

Pos logit contributions
illac+0.120
Leaks+0.117
ILY+0.115
 Nib+0.114
 CLASS+0.113
Neg logit contributions
angered-0.136
genre-0.124
adem-0.111
bnb-0.109
arios-0.108
Tokenaled
Token ID3021
Feature activation+6.40e-02

Pos logit contributions
illac+3.445
Leaks+3.285
 Nib+3.245
ILY+3.220
+3.182
Neg logit contributions
angered-3.297
genre-2.962
bnb-2.639
adem-2.593
arios-2.576
Token,
Token ID11
Feature activation-7.56e-02

Pos logit contributions
angered+0.187
genre+0.170
adem+0.152
bnb+0.150
arios+0.148
Neg logit contributions
illac-0.173
Leaks-0.167
ILY-0.165
 Nib-0.162
 CLASS-0.162
Token brown
Token ID7586
Feature activation+6.94e-02

Pos logit contributions
illac+0.197
Leaks+0.189
ILY+0.187
 Nib+0.184
 CLASS+0.183
Neg logit contributions
angered-0.229
genre-0.209
adem-0.188
bnb-0.186
arios-0.183
Tokenish
Token ID680
Feature activation-2.46e-01

Pos logit contributions
angered+0.203
genre+0.185
adem+0.165
bnb+0.163
arios+0.160
Neg logit contributions
illac-0.187
Leaks-0.180
ILY-0.179
 Nib-0.175
 CLASS-0.175
Token-
Token ID12
Feature activation-3.13e-02

Pos logit contributions
illac+0.643
Leaks+0.621
ILY+0.611
 Nib+0.607
 CLASS+0.601
Neg logit contributions
angered-0.744
genre-0.681
adem-0.610
bnb-0.605
arios-0.595
Token93
Token ID6052
Feature activation+1.19e-02

Pos logit contributions
angered+0.890
genre+0.808
adem+0.698
bnb+0.680
arios+0.670
Neg logit contributions
illac-1.149
Leaks-1.110
ILY-1.101
 CLASS-1.091
 Nib-1.090
Token]
Token ID60
Feature activation+1.70e-01

Pos logit contributions
angered+0.037
genre+0.034
adem+0.031
bnb+0.030
arios+0.030
Neg logit contributions
illac-0.030
Leaks-0.029
ILY-0.028
 Nib-0.028
 CLASS-0.028
Token
Token ID198
Feature activation+4.50e-01

Pos logit contributions
angered+0.503
genre+0.459
adem+0.413
bnb+0.404
arios+0.398
Neg logit contributions
illac-0.456
Leaks-0.440
ILY-0.434
 Nib-0.425
-0.423
Token
Token ID198
Feature activation+2.02e-01

Pos logit contributions
angered+1.305
genre+1.182
adem+1.049
bnb+1.030
arios+1.019
Neg logit contributions
illac-1.245
Leaks-1.184
ILY-1.172
 Nib-1.160
 CLASS-1.156
TokenBay
Token ID15262
Feature activation-1.46e-01

Pos logit contributions
angered+0.625
genre+0.577
adem+0.519
bnb+0.504
arios+0.497
Neg logit contributions
illac-0.516
 Nib-0.484
Leaks-0.484
ILY-0.481
 CLASS-0.481
Tokenern
Token ID1142
Feature activation-1.20e+00

Pos logit contributions
illac+0.324
Leaks+0.310
ILY+0.305
 Nib+0.301
 CLASS+0.299
Neg logit contributions
angered-0.496
genre-0.459
adem-0.417
bnb-0.413
arios-0.408
Token Munich
Token ID22418
Feature activation-6.00e-01

Pos logit contributions
illac+3.389
Leaks+3.291
 Nib+3.237
ILY+3.230
 CLASS+3.210
Neg logit contributions
angered-3.328
genre-3.030
bnb-2.657
adem-2.646
arios-2.594
Token II
Token ID2873
Feature activation-6.73e-02

Pos logit contributions
illac+1.675
Leaks+1.620
ILY+1.596
 Nib+1.585
 CLASS+1.575
Neg logit contributions
angered-1.701
genre-1.548
adem-1.371
bnb-1.360
arios-1.337
Token
Token ID198
Feature activation+7.84e-02

Pos logit contributions
illac+0.188
Leaks+0.182
ILY+0.179
 Nib+0.177
 CLASS+0.175
Neg logit contributions
angered-0.191
genre-0.173
adem-0.156
bnb-0.152
arios-0.151
Token
Token ID198
Feature activation-1.43e-02

Pos logit contributions
angered+0.234
genre+0.214
adem+0.191
bnb+0.189
arios+0.186
Neg logit contributions
illac-0.208
Leaks-0.200
ILY-0.197
 Nib-0.195
 CLASS-0.194
TokenBay
Token ID15262
Feature activation-1.44e-01

Pos logit contributions
illac+0.033
Leaks+0.031
ILY+0.031
 Nib+0.031
 CLASS+0.030
Neg logit contributions
angered-0.048
genre-0.045
adem-0.041
bnb-0.040
arios-0.039
Token car
Token ID1097
Feature activation+1.89e-01

Pos logit contributions
angered+0.418
genre+0.379
adem+0.340
bnb+0.335
arios+0.330
Neg logit contributions
illac-0.382
Leaks-0.370
ILY-0.365
 Nib-0.359
 CLASS-0.357
Token.
Token ID13
Feature activation+1.96e-01

Pos logit contributions
angered+0.566
genre+0.515
adem+0.464
bnb+0.457
arios+0.447
Neg logit contributions
illac-0.498
Leaks-0.486
ILY-0.479
 Nib-0.471
 CLASS-0.469
Token
Token ID198
Feature activation+1.87e-01

Pos logit contributions
angered+0.583
genre+0.524
adem+0.468
bnb+0.464
arios+0.456
Neg logit contributions
illac-0.523
Leaks-0.499
ILY-0.492
 CLASS-0.482
 Nib-0.482
Token
Token ID198
Feature activation+5.83e-02

Pos logit contributions
angered+0.557
genre+0.507
adem+0.453
bnb+0.448
arios+0.441
Neg logit contributions
illac-0.496
Leaks-0.476
ILY-0.470
 Nib-0.465
 CLASS-0.462
TokenB
Token ID33
Feature activation+1.77e-01

Pos logit contributions
angered+0.191
genre+0.175
adem+0.158
bnb+0.154
arios+0.153
Neg logit contributions
illac-0.140
 Nib-0.130
Leaks-0.130
 CLASS-0.130
ILY-0.129
Tokenart
Token ID433
Feature activation-1.20e+00

Pos logit contributions
angered+0.499
genre+0.450
adem+0.404
bnb+0.394
arios+0.392
Neg logit contributions
illac-0.495
Leaks-0.479
ILY-0.474
 Nib-0.472
 CLASS-0.469
Token was
Token ID373
Feature activation+2.49e-01

Pos logit contributions
illac+3.410
Leaks+3.295
 Nib+3.233
ILY+3.228
 CLASS+3.175
Neg logit contributions
angered-3.332
genre-3.039
adem-2.683
bnb-2.654
arios-2.602
Token discovered
Token ID5071
Feature activation+8.29e-02

Pos logit contributions
angered+0.711
genre+0.644
adem+0.575
bnb+0.563
arios+0.557
Neg logit contributions
illac-0.691
Leaks-0.672
ILY-0.659
 Nib-0.648
 CLASS-0.643
Token by
Token ID416
Feature activation+9.24e-03

Pos logit contributions
angered+0.238
genre+0.215
adem+0.192
bnb+0.189
arios+0.186
Neg logit contributions
illac-0.230
Leaks-0.222
ILY-0.220
 Nib-0.215
 CLASS-0.215
Token its
Token ID663
Feature activation+8.38e-02

Pos logit contributions
angered+0.028
genre+0.025
adem+0.023
bnb+0.022
arios+0.022
Neg logit contributions
illac-0.024
Leaks-0.023
ILY-0.023
-0.023
 Nib-0.023
Token owner
Token ID4870
Feature activation+2.54e-01

Pos logit contributions
angered+0.211
genre+0.189
adem+0.166
bnb+0.163
arios+0.160
Neg logit contributions
illac-0.261
Leaks-0.253
ILY-0.250
 Nib-0.247
 CLASS-0.246
Token under
Token ID739
Feature activation+7.72e-01

Pos logit contributions
angered+0.480
genre+0.438
adem+0.391
bnb+0.385
arios+0.379
Neg logit contributions
illac-0.455
Leaks-0.438
ILY-0.431
 Nib-0.428
 CLASS-0.426
Token here
Token ID994
Feature activation+1.78e-01

Pos logit contributions
angered+2.304
genre+2.112
adem+1.880
bnb+1.850
arios+1.837
Neg logit contributions
illac-2.061
Leaks-1.932
ILY-1.930
 Nib-1.905
 CLASS-1.896
Token.
Token ID13
Feature activation-6.54e-02

Pos logit contributions
angered+0.509
genre+0.461
adem+0.411
bnb+0.407
arios+0.400
Neg logit contributions
illac-0.495
Leaks-0.479
ILY-0.470
 Nib-0.467
 CLASS-0.465
Token
Token ID198
Feature activation-9.32e-02

Pos logit contributions
illac+0.170
Leaks+0.163
ILY+0.161
 Nib+0.159
 CLASS+0.158
Neg logit contributions
angered-0.199
genre-0.182
adem-0.163
bnb-0.161
arios-0.159
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
illac+0.240
Leaks+0.232
ILY+0.229
 Nib+0.226
 CLASS+0.224
Neg logit contributions
angered-0.284
genre-0.261
adem-0.234
bnb-0.232
arios-0.228
TokenThank
Token ID10449
Feature activation-1.20e+00

Pos logit contributions
illac+0.448
Leaks+0.425
ILY+0.420
 Nib+0.419
 CLASS+0.416
Neg logit contributions
angered-0.596
genre-0.549
adem-0.496
bnb-0.488
arios-0.482
Token you
Token ID345
Feature activation-6.05e-01

Pos logit contributions
illac+2.785
Leaks+2.691
ILY+2.664
 Nib+2.608
 CLASS+2.585
Neg logit contributions
angered-3.909
genre-3.599
adem-3.255
bnb-3.219
arios-3.191
Token
Token ID198
Feature activation-3.53e-02

Pos logit contributions
illac+1.554
Leaks+1.498
ILY+1.483
 Nib+1.462
 CLASS+1.452
Neg logit contributions
angered-1.847
genre-1.691
adem-1.517
bnb-1.499
arios-1.479
Token
Token ID198
Feature activation-1.24e-01

Pos logit contributions
illac+0.091
Leaks+0.088
ILY+0.087
 Nib+0.086
 CLASS+0.085
Neg logit contributions
angered-0.108
genre-0.099
adem-0.088
bnb-0.087
arios-0.086
TokenFind
Token ID16742
Feature activation+2.29e-01

Pos logit contributions
illac+0.298
Leaks+0.283
ILY+0.279
 Nib+0.278
 CLASS+0.276
Neg logit contributions
angered-0.402
genre-0.370
adem-0.335
bnb-0.330
arios-0.326
Token out
Token ID503
Feature activation-6.03e-01

Pos logit contributions
angered+0.727
genre+0.663
adem+0.603
bnb+0.596
arios+0.584
Neg logit contributions
illac-0.570
Leaks-0.540
ILY-0.530
 Nib-0.525
 CLASS-0.523
Token like
Token ID588
Feature activation-1.72e-01

Pos logit contributions
angered+0.158
genre+0.143
adem+0.128
bnb+0.126
arios+0.124
Neg logit contributions
illac-0.153
Leaks-0.148
ILY-0.146
 Nib-0.144
 CLASS-0.143
Token Mormons
Token ID33003
Feature activation-6.58e-02

Pos logit contributions
illac+0.448
Leaks+0.433
ILY+0.426
 Nib+0.420
 CLASS+0.418
Neg logit contributions
angered-0.521
genre-0.476
adem-0.427
bnb-0.422
arios-0.416
Token love
Token ID1842
Feature activation-3.00e-01

Pos logit contributions
illac+0.162
Leaks+0.157
ILY+0.154
 Nib+0.152
 CLASS+0.151
Neg logit contributions
angered-0.208
genre-0.191
adem-0.172
bnb-0.171
arios-0.168
Token a
Token ID257
Feature activation+4.43e-01

Pos logit contributions
illac+0.713
Leaks+0.685
ILY+0.674
 Nib+0.663
 CLASS+0.660
Neg logit contributions
angered-0.979
genre-0.901
adem-0.816
bnb-0.806
arios-0.797
Token tab
Token ID7400
Feature activation+1.09e-02

Pos logit contributions
angered+1.328
genre+1.207
adem+1.083
bnb+1.065
arios+1.054
Neg logit contributions
illac-1.174
Leaks-1.131
ILY-1.115
 Nib-1.098
 CLASS-1.092
Tokenern
Token ID1142
Feature activation-1.19e+00

Pos logit contributions
angered+0.033
genre+0.030
adem+0.027
bnb+0.027
arios+0.026
Neg logit contributions
illac-0.028
Leaks-0.027
ILY-0.027
 Nib-0.027
 CLASS-0.027
Tokenacle
Token ID6008
Feature activation+1.91e-01

Pos logit contributions
illac+2.121
Leaks+2.019
ILY+1.956
 Nib+1.955
 CLASS+1.915
Neg logit contributions
angered-4.474
genre-4.205
bnb-3.875
adem-3.854
arios-3.769
Token choir
Token ID42644
Feature activation+1.08e-01

Pos logit contributions
angered+0.549
genre+0.499
adem+0.447
bnb+0.440
arios+0.433
Neg logit contributions
illac-0.526
Leaks-0.509
ILY-0.503
 CLASS-0.493
 Nib-0.492
Token.
Token ID13
Feature activation+4.06e-03

Pos logit contributions
angered+0.311
genre+0.284
adem+0.252
bnb+0.249
arios+0.245
Neg logit contributions
illac-0.298
Leaks-0.291
ILY-0.286
 Nib-0.282
 CLASS-0.280
Token We
Token ID775
Feature activation+3.34e-01

Pos logit contributions
angered+0.012
genre+0.011
adem+0.010
bnb+0.010
arios+0.010
Neg logit contributions
illac-0.010
Leaks-0.010
ILY-0.010
 Nib-0.010
 CLASS-0.010
Token pass
Token ID1208
Feature activation-7.90e-02

Pos logit contributions
angered+1.090
genre+1.000
adem+0.906
bnb+0.896
arios+0.888
Neg logit contributions
illac-0.791
Leaks-0.764
ILY-0.749
 Nib-0.741
 CLASS-0.734
Tokenlist
Token ID4868
Feature activation+5.30e-02

Pos logit contributions
angered+0.558
genre+0.500
adem+0.439
bnb+0.433
arios+0.426
Neg logit contributions
illac-0.678
Leaks-0.657
ILY-0.649
 Nib-0.642
 CLASS-0.639
Token_
Token ID62
Feature activation-8.73e-02

Pos logit contributions
angered+0.170
genre+0.156
adem+0.141
bnb+0.139
arios+0.137
Neg logit contributions
illac-0.129
Leaks-0.124
ILY-0.122
 Nib-0.121
 CLASS-0.120
Tokenimages
Token ID17566
Feature activation-6.60e-03

Pos logit contributions
illac+0.200
Leaks+0.194
ILY+0.190
 Nib+0.186
 CLASS+0.184
Neg logit contributions
angered-0.289
genre-0.267
adem-0.242
bnb-0.241
arios-0.236
Token(
Token ID7
Feature activation+5.64e-02

Pos logit contributions
illac+0.017
Leaks+0.017
ILY+0.016
 Nib+0.016
 CLASS+0.016
Neg logit contributions
angered-0.020
genre-0.018
adem-0.016
bnb-0.016
arios-0.016
Tokenargs
Token ID22046
Feature activation+2.70e-01

Pos logit contributions
angered+0.141
genre+0.127
adem+0.110
bnb+0.108
arios+0.107
Neg logit contributions
illac-0.177
Leaks-0.172
ILY-0.170
 Nib-0.169
 CLASS-0.168
Token["
Token ID14692
Feature activation+8.39e-01

Pos logit contributions
angered+0.565
genre+0.491
adem+0.401
bnb+0.401
arios+0.386
Neg logit contributions
illac-0.958
Leaks-0.935
 Nib-0.923
ILY-0.917
 CLASS-0.917
Tokenimages
Token ID17566
Feature activation+1.39e-01

Pos logit contributions
angered+2.606
genre+2.388
adem+2.144
bnb+2.089
arios+2.071
Neg logit contributions
illac-2.147
 Nib-2.044
Leaks-2.033
 CLASS-2.029
ILY-2.026
Token"]
Token ID8973
Feature activation+9.40e-02

Pos logit contributions
angered+0.246
genre+0.210
adem+0.169
bnb+0.165
arios+0.161
Neg logit contributions
illac-0.537
Leaks-0.523
ILY-0.518
 Nib-0.515
 CLASS-0.513
Token):
Token ID2599
Feature activation+3.50e-01

Pos logit contributions
angered+0.224
genre+0.200
adem+0.173
bnb+0.170
arios+0.167
Neg logit contributions
illac-0.306
Leaks-0.297
ILY-0.293
 Nib-0.290
 CLASS-0.289
Token #
Token ID1303
Feature activation+8.22e-01

Pos logit contributions
angered+0.844
genre+0.754
adem+0.652
bnb+0.637
arios+0.627
Neg logit contributions
illac-1.130
Leaks-1.097
ILY-1.080
 Nib-1.063
-1.060
Token load
Token ID3440
Feature activation+8.35e-02

Pos logit contributions
angered+1.905
genre+1.693
adem+1.482
argo+1.433
bnb+1.431
Neg logit contributions
illac-2.702
Leaks-2.608
ILY-2.582
 Nib-2.550
-2.544
Token costs
Token ID3484
Feature activation-1.65e-01

Pos logit contributions
angered+1.188
genre+1.066
adem+0.952
bnb+0.933
arios+0.931
Neg logit contributions
illac-1.204
Leaks-1.155
ILY-1.150
 Nib-1.135
 CLASS-1.125
Token.
Token ID13
Feature activation-7.11e-02

Pos logit contributions
illac+0.475
Leaks+0.459
ILY+0.453
 Nib+0.449
 CLASS+0.446
Neg logit contributions
angered-0.457
genre-0.415
adem-0.367
bnb-0.362
arios-0.356
Token
Token ID198
Feature activation+2.07e-02

Pos logit contributions
illac+0.183
Leaks+0.177
ILY+0.174
 Nib+0.172
 CLASS+0.171
Neg logit contributions
angered-0.217
genre-0.199
adem-0.178
bnb-0.176
arios-0.174
Token
Token ID198
Feature activation-4.11e-02

Pos logit contributions
angered+0.063
genre+0.057
adem+0.051
bnb+0.051
arios+0.050
Neg logit contributions
illac-0.054
Leaks-0.052
ILY-0.051
 Nib-0.051
 CLASS-0.050
TokenL
Token ID43
Feature activation-1.68e-02

Pos logit contributions
illac+0.101
Leaks+0.096
ILY+0.095
 Nib+0.095
 CLASS+0.094
Neg logit contributions
angered-0.130
genre-0.120
adem-0.108
bnb-0.106
arios-0.105
TokenNG
Token ID10503
Feature activation+9.72e-01

Pos logit contributions
illac+0.043
Leaks+0.041
 Nib+0.041
+0.040
ILY+0.040
Neg logit contributions
angered-0.052
genre-0.047
adem-0.042
arios-0.042
bnb-0.041
Token has
Token ID468
Feature activation+2.17e-01

Pos logit contributions
angered+2.943
genre+2.672
adem+2.405
bnb+2.388
arios+2.368
Neg logit contributions
illac-2.494
ILY-2.378
Leaks-2.352
 Nib-2.326
-2.316
Token a
Token ID257
Feature activation+7.21e-02

Pos logit contributions
angered+0.659
genre+0.602
adem+0.540
bnb+0.534
arios+0.527
Neg logit contributions
illac-0.562
Leaks-0.541
ILY-0.533
 Nib-0.526
 CLASS-0.523
Token number
Token ID1271
Feature activation-3.74e-01

Pos logit contributions
angered+0.205
genre+0.187
adem+0.166
bnb+0.164
arios+0.161
Neg logit contributions
illac-0.201
Leaks-0.194
ILY-0.192
 Nib-0.190
 CLASS-0.188
Token of
Token ID286
Feature activation+1.75e-01

Pos logit contributions
illac+1.045
Leaks+1.012
ILY+1.000
 Nib+0.989
 CLASS+0.987
Neg logit contributions
angered-1.045
genre-0.958
adem-0.851
bnb-0.835
arios-0.822
Token prominent
Token ID9208
Feature activation+4.12e-01

Pos logit contributions
angered+0.463
genre+0.418
adem+0.368
bnb+0.363
arios+0.357
Neg logit contributions
illac-0.521
Leaks-0.505
ILY-0.499
 Nib-0.493
 CLASS-0.491
Token.
Token ID13
Feature activation-7.51e-02

Pos logit contributions
illac+1.610
Leaks+1.555
ILY+1.553
 Nib+1.531
 CLASS+1.520
Neg logit contributions
angered-2.002
genre-1.845
adem-1.662
bnb-1.637
arios-1.614
Token
Token ID198
Feature activation+9.36e-02

Pos logit contributions
illac+0.201
Leaks+0.192
ILY+0.190
 Nib+0.187
 CLASS+0.186
Neg logit contributions
angered-0.223
genre-0.202
adem-0.181
bnb-0.179
arios-0.176
Token
Token ID198
Feature activation-3.66e-02

Pos logit contributions
angered+0.279
genre+0.255
adem+0.228
bnb+0.225
arios+0.222
Neg logit contributions
illac-0.249
Leaks-0.239
ILY-0.236
 Nib-0.233
 CLASS-0.232
TokenArticle
Token ID14906
Feature activation-3.04e-01

Pos logit contributions
illac+0.095
Leaks+0.090
 Nib+0.090
 CLASS+0.089
ILY+0.089
Neg logit contributions
angered-0.112
genre-0.102
adem-0.091
bnb-0.090
arios-0.089
Token Continued
Token ID22168
Feature activation+3.69e-01

Pos logit contributions
illac+0.598
Leaks+0.573
ILY+0.561
 Nib+0.552
 CLASS+0.547
Neg logit contributions
angered-1.109
genre-1.033
adem-0.944
bnb-0.936
arios-0.925
Token Below
Token ID10383
Feature activation+1.14e+00

Pos logit contributions
angered+0.952
genre+0.854
adem+0.749
bnb+0.739
arios+0.726
Neg logit contributions
illac-1.128
Leaks-1.088
ILY-1.077
 Nib-1.065
 CLASS-1.059
Token
Token ID198
Feature activation-2.11e-01

Pos logit contributions
angered+3.080
genre+2.751
adem+2.392
bnb+2.349
arios+2.330
Neg logit contributions
illac-3.366
Leaks-3.138
-3.129
ILY-3.128
 Nib-3.114
Token
Token ID198
Feature activation-3.35e-01

Pos logit contributions
illac+0.531
Leaks+0.517
ILY+0.508
 Nib+0.502
 CLASS+0.497
Neg logit contributions
angered-0.649
genre-0.597
adem-0.539
bnb-0.533
arios-0.524
TokenT
Token ID51
Feature activation-1.25e-01

Pos logit contributions
illac+0.827
Leaks+0.790
ILY+0.779
 Nib+0.773
 CLASS+0.768
Neg logit contributions
angered-1.065
genre-0.977
adem-0.881
bnb-0.869
arios-0.859
Tokenod
Token ID375
Feature activation+2.84e-01

Pos logit contributions
illac+0.316
Leaks+0.305
ILY+0.301
 Nib+0.298
 CLASS+0.295
Neg logit contributions
angered-0.386
genre-0.353
adem-0.321
bnb-0.313
arios-0.312
Tokenas
Token ID292
Feature activation+2.39e-02

Pos logit contributions
angered+0.846
genre+0.772
adem+0.695
bnb+0.679
arios+0.675
Neg logit contributions
illac-0.751
Leaks-0.725
ILY-0.720
 Nib-0.712
 CLASS-0.710
Token92
Token ID5892
Feature activation+2.96e-01

Pos logit contributions
illac+0.110
Leaks+0.105
ILY+0.103
 Nib+0.103
 CLASS+0.102
Neg logit contributions
angered-0.135
genre-0.125
adem-0.112
bnb-0.111
arios-0.109
Token.
Token ID13
Feature activation-4.72e-02

Pos logit contributions
angered+0.895
genre+0.822
adem+0.741
bnb+0.731
arios+0.719
Neg logit contributions
illac-0.771
Leaks-0.740
ILY-0.731
 Nib-0.719
 CLASS-0.713
Token2
Token ID17
Feature activation-2.95e-01

Pos logit contributions
illac+0.117
Leaks+0.112
ILY+0.110
 Nib+0.109
 CLASS+0.108
Neg logit contributions
angered-0.149
genre-0.137
adem-0.123
bnb-0.122
arios-0.120
Token-
Token ID12
Feature activation-2.65e-02

Pos logit contributions
illac+0.726
Leaks+0.698
ILY+0.687
 Nib+0.678
 CLASS+0.673
Neg logit contributions
angered-0.934
genre-0.859
adem-0.775
bnb-0.766
arios-0.755
Tokenmile
Token ID18085
Feature activation-8.30e-02

Pos logit contributions
illac+0.068
Leaks+0.066
ILY+0.064
 Nib+0.064
 CLASS+0.063
Neg logit contributions
angered-0.081
genre-0.075
adem-0.067
bnb-0.066
arios-0.065
Token per
Token ID583
Feature activation+8.44e-01

Pos logit contributions
illac+0.228
Leaks+0.220
ILY+0.217
 CLASS+0.212
 Nib+0.212
Neg logit contributions
angered-0.239
genre-0.218
adem-0.196
bnb-0.192
arios-0.189
Token hour
Token ID1711
Feature activation+2.48e-01

Pos logit contributions
angered+2.994
genre+2.778
adem+2.583
bnb+2.497
arios+2.478
Neg logit contributions
illac-1.706
Leaks-1.624
ILY-1.576
-1.532
 CLASS-1.509
Token)
Token ID8
Feature activation+4.04e-02

Pos logit contributions
angered+0.764
genre+0.702
adem+0.642
bnb+0.624
arios+0.615
Neg logit contributions
illac-0.625
Leaks-0.601
ILY-0.588
 Nib-0.574
 CLASS-0.574
Token change
Token ID1487
Feature activation-3.71e-01

Pos logit contributions
angered+0.117
genre+0.107
adem+0.096
bnb+0.094
arios+0.093
Neg logit contributions
illac-0.110
Leaks-0.106
ILY-0.105
 Nib-0.103
 CLASS-0.103
Token of
Token ID286
Feature activation+1.06e-01

Pos logit contributions
illac+0.994
Leaks+0.960
ILY+0.948
 Nib+0.937
 CLASS+0.930
Neg logit contributions
angered-1.088
genre-0.994
adem-0.887
bnb-0.878
arios-0.863
Token velocity
Token ID15432
Feature activation-3.01e-01

Pos logit contributions
angered+0.307
genre+0.280
adem+0.250
bnb+0.246
arios+0.243
Neg logit contributions
illac-0.291
Leaks-0.281
ILY-0.277
 Nib-0.273
 CLASS-0.272
Token can
Token ID460
Feature activation-8.38e-02

Pos logit contributions
angered+0.285
genre+0.261
adem+0.235
bnb+0.232
arios+0.228
Neg logit contributions
illac-0.240
Leaks-0.231
ILY-0.227
 Nib-0.224
 CLASS-0.223
Token be
Token ID307
Feature activation-7.87e-02

Pos logit contributions
illac+0.212
Leaks+0.205
ILY+0.202
 Nib+0.200
 CLASS+0.198
Neg logit contributions
angered-0.258
genre-0.237
adem-0.213
bnb-0.210
arios-0.207
Token of
Token ID286
Feature activation+1.37e-02

Pos logit contributions
illac+0.203
Leaks+0.196
ILY+0.193
 Nib+0.191
 CLASS+0.190
Neg logit contributions
angered-0.239
genre-0.220
adem-0.197
bnb-0.195
arios-0.191
Token great
Token ID1049
Feature activation-3.27e-02

Pos logit contributions
angered+0.040
genre+0.037
adem+0.033
bnb+0.033
arios+0.032
Neg logit contributions
illac-0.037
Leaks-0.036
ILY-0.035
 Nib-0.035
 CLASS-0.034
Token mutual
Token ID13584
Feature activation+1.04e-01

Pos logit contributions
illac+0.101
Leaks+0.098
ILY+0.097
 Nib+0.096
 CLASS+0.095
Neg logit contributions
angered-0.083
genre-0.075
adem-0.065
bnb-0.065
arios-0.063
Token benefit
Token ID4414
Feature activation+1.00e+00

Pos logit contributions
angered+0.254
genre+0.228
adem+0.198
bnb+0.195
arios+0.191
Neg logit contributions
illac-0.331
Leaks-0.322
ILY-0.319
 Nib-0.316
 CLASS-0.314
Token to
Token ID284
Feature activation-1.33e-01

Pos logit contributions
angered+2.839
genre+2.601
bnb+2.299
adem+2.291
arios+2.269
Neg logit contributions
illac-2.775
Leaks-2.694
ILY-2.590
-2.587
 CLASS-2.585
Token fans
Token ID3296
Feature activation+1.48e-01

Pos logit contributions
illac+0.322
Leaks+0.310
ILY+0.307
 Nib+0.303
 CLASS+0.300
Neg logit contributions
angered-0.425
genre-0.390
adem-0.352
bnb-0.349
arios-0.344
Token and
Token ID290
Feature activation+1.51e-01

Pos logit contributions
angered+0.425
genre+0.386
adem+0.344
bnb+0.340
arios+0.335
Neg logit contributions
illac-0.408
Leaks-0.394
ILY-0.389
 Nib-0.385
 CLASS-0.383
Token club
Token ID3430
Feature activation-4.88e-02

Pos logit contributions
angered+0.434
genre+0.396
adem+0.352
bnb+0.348
arios+0.343
Neg logit contributions
illac-0.418
Leaks-0.403
ILY-0.397
 Nib-0.392
 CLASS-0.390
Token alike
Token ID12936
Feature activation-1.15e-01

Pos logit contributions
illac+0.132
Leaks+0.128
ILY+0.127
 Nib+0.125
 CLASS+0.124
Neg logit contributions
angered-0.142
genre-0.129
adem-0.116
bnb-0.114
arios-0.112
Token,
Token ID11
Feature activation+1.23e-01

Pos logit contributions
illac+0.063
Leaks+0.061
ILY+0.060
 Nib+0.060
 CLASS+0.059
Neg logit contributions
angered-0.064
genre-0.058
adem-0.052
bnb-0.051
arios-0.050
Token 15
Token ID1315
Feature activation-1.94e-02

Pos logit contributions
angered+0.456
genre+0.422
adem+0.388
bnb+0.385
arios+0.380
Neg logit contributions
illac-0.237
Leaks-0.224
ILY-0.219
 Nib-0.214
 CLASS-0.213
Token}
Token ID92
Feature activation-4.66e-01

Pos logit contributions
illac+0.052
Leaks+0.050
ILY+0.049
 Nib+0.049
 CLASS+0.049
Neg logit contributions
angered-0.057
genre-0.052
adem-0.047
bnb-0.046
arios-0.045
Token ->
Token ID4613
Feature activation+3.05e-01

Pos logit contributions
illac+0.897
Leaks+0.853
ILY+0.835
 Nib+0.820
 CLASS+0.812
Neg logit contributions
angered-1.731
genre-1.611
adem-1.476
bnb-1.463
arios-1.446
Token "
Token ID366
Feature activation+5.14e-02

Pos logit contributions
angered+0.686
genre+0.608
adem+0.520
bnb+0.513
arios+0.502
Neg logit contributions
illac-1.029
Leaks-1.002
ILY-0.989
 Nib-0.973
 CLASS-0.972
TokenS
Token ID50
Feature activation+2.18e-01

Pos logit contributions
angered+0.179
genre+0.166
adem+0.150
bnb+0.149
arios+0.147
Neg logit contributions
illac-0.111
Leaks-0.105
ILY-0.103
 Nib-0.102
 CLASS-0.102
Token",
Token ID1600
Feature activation+2.89e-02

Pos logit contributions
angered+0.514
genre+0.457
adem+0.394
bnb+0.389
arios+0.381
Neg logit contributions
illac-0.711
Leaks-0.692
ILY-0.681
 Nib-0.676
 CLASS-0.672
Token {
Token ID1391
Feature activation+4.77e-01

Pos logit contributions
angered+0.069
genre+0.062
adem+0.054
bnb+0.053
arios+0.052
Neg logit contributions
illac-0.093
Leaks-0.091
ILY-0.090
 Nib-0.088
 CLASS-0.088
Token9
Token ID24
Feature activation+1.21e-01

Pos logit contributions
angered+1.398
genre+1.273
adem+1.126
bnb+1.118
arios+1.094
Neg logit contributions
illac-1.298
Leaks-1.232
ILY-1.216
 Nib-1.214
 CLASS-1.207
Token,
Token ID11
Feature activation+2.33e-01

Pos logit contributions
angered+0.345
genre+0.314
adem+0.279
bnb+0.276
arios+0.272
Neg logit contributions
illac-0.334
Leaks-0.323
ILY-0.319
 Nib-0.315
 CLASS-0.313
Token 15
Token ID1315
Feature activation+1.38e-01

Pos logit contributions
angered+0.772
genre+0.707
adem+0.640
bnb+0.635
arios+0.627
Neg logit contributions
illac-0.545
Leaks-0.520
ILY-0.511
 Nib-0.499
-0.497
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
angered+0.496
genre+0.451
adem+0.402
bnb+0.397
arios+0.391
Neg logit contributions
illac-0.451
Leaks-0.431
ILY-0.425
 Nib-0.422
 CLASS-0.420
TokenJud
Token ID26141
Feature activation+3.65e-01

Pos logit contributions
angered+0.490
genre+0.450
adem+0.407
bnb+0.396
arios+0.391
Neg logit contributions
illac-0.358
 Nib-0.338
 CLASS-0.331
Leaks-0.328
ILY-0.328
Tokenicial
Token ID6652
Feature activation+3.32e-01

Pos logit contributions
angered+1.357
genre+1.261
adem+1.167
bnb+1.142
argo+1.122
Neg logit contributions
illac-0.688
Leaks-0.644
ILY-0.642
 Nib-0.639
-0.634
Token Watch
Token ID6305
Feature activation+5.47e-01

Pos logit contributions
angered+0.963
genre+0.875
adem+0.787
bnb+0.776
arios+0.759
Neg logit contributions
illac-0.906
ILY-0.866
Leaks-0.861
 Nib-0.852
-0.844
Token,
Token ID11
Feature activation+7.12e-02

Pos logit contributions
angered+1.645
genre+1.474
adem+1.339
bnb+1.322
arios+1.307
Neg logit contributions
illac-1.446
ILY-1.362
Leaks-1.358
 Nib-1.345
-1.322
Token which
Token ID543
Feature activation+5.47e-02

Pos logit contributions
angered+0.231
genre+0.211
adem+0.192
bnb+0.189
arios+0.186
Neg logit contributions
illac-0.171
Leaks-0.163
ILY-0.160
 Nib-0.159
 CLASS-0.157
Token sued
Token ID16334
Feature activation+1.77e-01

Pos logit contributions
angered+0.168
genre+0.153
adem+0.138
bnb+0.136
arios+0.135
Neg logit contributions
illac-0.141
Leaks-0.134
ILY-0.133
 Nib-0.131
 CLASS-0.130
Token to
Token ID284
Feature activation+1.15e-01

Pos logit contributions
angered+0.547
genre+0.497
adem+0.453
bnb+0.447
arios+0.436
Neg logit contributions
illac-0.446
Leaks-0.426
-0.419
ILY-0.418
 Nib-0.417
Token force
Token ID2700
Feature activation+2.99e-01

Pos logit contributions
angered+0.343
genre+0.313
adem+0.284
bnb+0.277
arios+0.273
Neg logit contributions
illac-0.304
Leaks-0.289
ILY-0.286
 Nib-0.283
-0.281
Token the
Token ID262
Feature activation+1.69e-02

Pos logit contributions
angered+0.913
genre+0.828
adem+0.759
bnb+0.748
arios+0.727
Neg logit contributions
illac-0.763
Leaks-0.728
ILY-0.719
 Nib-0.711
-0.710
Token production
Token ID3227
Feature activation+4.46e-01

Pos logit contributions
angered+0.056
genre+0.051
adem+0.047
bnb+0.046
arios+0.046
Neg logit contributions
illac-0.039
Leaks-0.038
ILY-0.037
 Nib-0.037
 CLASS-0.036
Token
Token ID198
Feature activation+3.77e-01

Pos logit contributions
angered+0.022
genre+0.020
adem+0.018
bnb+0.018
arios+0.017
Neg logit contributions
illac-0.018
Leaks-0.018
ILY-0.017
 Nib-0.017
 CLASS-0.017
Token
Token ID198
Feature activation+2.67e-01

Pos logit contributions
angered+1.105
genre+1.003
adem+0.892
bnb+0.879
arios+0.868
Neg logit contributions
illac-1.026
Leaks-0.979
ILY-0.968
 Nib-0.958
 CLASS-0.956
TokenQuest
Token ID12166
Feature activation+2.69e-01

Pos logit contributions
angered+0.859
genre+0.790
adem+0.710
bnb+0.695
arios+0.689
Neg logit contributions
illac-0.654
 Nib-0.614
Leaks-0.611
 CLASS-0.610
ILY-0.606
Token Diagn
Token ID31549
Feature activation-5.05e-01

Pos logit contributions
angered+0.753
genre+0.675
adem+0.603
arios+0.592
bnb+0.591
Neg logit contributions
illac-0.763
ILY-0.736
Leaks-0.730
 Nib-0.725
-0.724
Tokenostics
Token ID34558
Feature activation-1.84e-01

Pos logit contributions
illac+0.943
Leaks+0.895
ILY+0.876
 Nib+0.862
 CLASS+0.855
Neg logit contributions
angered-1.900
genre-1.771
adem-1.625
bnb-1.612
arios-1.593
Token,
Token ID11
Feature activation+4.48e-02

Pos logit contributions
illac+0.481
Leaks+0.464
ILY+0.458
 Nib+0.451
 CLASS+0.448
Neg logit contributions
angered-0.555
genre-0.507
adem-0.455
bnb-0.449
arios-0.443
Token based
Token ID1912
Feature activation+6.42e-02

Pos logit contributions
angered+0.144
genre+0.132
adem+0.120
bnb+0.118
arios+0.117
Neg logit contributions
illac-0.108
Leaks-0.104
ILY-0.102
 Nib-0.100
 CLASS-0.100
Token in
Token ID287
Feature activation+9.94e-02

Pos logit contributions
angered+0.179
genre+0.162
adem+0.145
bnb+0.142
arios+0.141
Neg logit contributions
illac-0.179
Leaks-0.176
ILY-0.174
 Nib-0.170
 CLASS-0.170
Token New
Token ID968
Feature activation+3.78e-02

Pos logit contributions
angered+0.267
genre+0.241
adem+0.213
bnb+0.210
arios+0.207
Neg logit contributions
illac-0.292
Leaks-0.283
ILY-0.280
 Nib-0.275
 CLASS-0.275
Token Jersey
Token ID8221
Feature activation+1.33e-01

Pos logit contributions
angered+0.095
genre+0.086
adem+0.075
bnb+0.074
arios+0.072
Neg logit contributions
illac-0.117
Leaks-0.114
ILY-0.113
 Nib-0.111
 CLASS-0.111
Token,
Token ID11
Feature activation-7.89e-02

Pos logit contributions
angered+0.365
genre+0.331
adem+0.293
bnb+0.289
arios+0.286
Neg logit contributions
illac-0.380
Leaks-0.370
ILY-0.367
 Nib-0.363
 CLASS-0.360
Token,
Token ID11
Feature activation-7.65e-02

Pos logit contributions
angered+1.638
genre+1.487
adem+1.313
bnb+1.298
arios+1.282
Neg logit contributions
illac-1.754
Leaks-1.705
ILY-1.668
 Nib-1.657
 CLASS-1.654
Token was
Token ID373
Feature activation+4.95e-01

Pos logit contributions
illac+0.197
Leaks+0.189
ILY+0.187
 Nib+0.184
 CLASS+0.183
Neg logit contributions
angered-0.235
genre-0.215
adem-0.193
bnb-0.190
arios-0.188
Token trained
Token ID8776
Feature activation+3.69e-01

Pos logit contributions
angered+1.419
genre+1.289
adem+1.152
bnb+1.131
arios+1.119
Neg logit contributions
illac-1.369
Leaks-1.322
ILY-1.304
 Nib-1.288
 CLASS-1.278
Token by
Token ID416
Feature activation+1.60e-01

Pos logit contributions
angered+1.129
genre+1.029
adem+0.929
bnb+0.917
arios+0.915
Neg logit contributions
illac-0.935
Leaks-0.907
ILY-0.892
 Nib-0.879
 CLASS-0.872
Token the
Token ID262
Feature activation-1.98e-01

Pos logit contributions
angered+0.481
genre+0.439
adem+0.395
bnb+0.387
arios+0.386
Neg logit contributions
illac-0.418
Leaks-0.399
ILY-0.394
-0.390
 CLASS-0.389
Token United
Token ID1578
Feature activation+2.19e-01

Pos logit contributions
illac+0.530
Leaks+0.512
ILY+0.505
 Nib+0.500
 CLASS+0.496
Neg logit contributions
angered-0.583
genre-0.533
adem-0.475
bnb-0.471
arios-0.463
Token States
Token ID1829
Feature activation-4.79e-02

Pos logit contributions
angered+0.710
genre+0.649
adem+0.592
arios+0.577
bnb+0.573
Neg logit contributions
illac-0.534
Leaks-0.500
ILY-0.496
-0.496
 CLASS-0.487
Token,
Token ID11
Feature activation-7.01e-02

Pos logit contributions
illac+0.117
Leaks+0.112
ILY+0.111
 Nib+0.109
+0.109
Neg logit contributions
angered-0.153
genre-0.140
adem-0.127
bnb-0.125
arios-0.124
Token a
Token ID257
Feature activation+1.15e-01

Pos logit contributions
illac+0.181
Leaks+0.173
ILY+0.172
 Nib+0.169
 CLASS+0.168
Neg logit contributions
angered-0.214
genre-0.196
adem-0.176
bnb-0.173
arios-0.171
Token senior
Token ID4664
Feature activation-2.11e-01

Pos logit contributions
angered+0.355
genre+0.325
adem+0.293
bnb+0.288
arios+0.285
Neg logit contributions
illac-0.291
Leaks-0.277
ILY-0.274
 Nib-0.270
 CLASS-0.269
Token U
Token ID471
Feature activation-1.76e-01

Pos logit contributions
illac+0.536
Leaks+0.518
ILY+0.509
 Nib+0.505
 CLASS+0.501
Neg logit contributions
angered-0.651
genre-0.596
adem-0.535
bnb-0.531
arios-0.522
Token the
Token ID262
Feature activation+1.50e-01

Pos logit contributions
illac+0.409
Leaks+0.392
ILY+0.386
 Nib+0.380
 CLASS+0.377
Neg logit contributions
angered-0.537
genre-0.495
adem-0.447
bnb-0.441
arios-0.437
Token year
Token ID614
Feature activation+4.35e-01

Pos logit contributions
angered+0.443
genre+0.404
adem+0.363
arios+0.355
bnb+0.352
Neg logit contributions
illac-0.402
Leaks-0.389
ILY-0.382
 Nib-0.376
-0.375
Token.
Token ID13
Feature activation-6.84e-02

Pos logit contributions
angered+1.219
genre+1.105
adem+0.988
bnb+0.972
arios+0.964
Neg logit contributions
illac-1.231
Leaks-1.208
ILY-1.167
 Nib-1.161
-1.148
Token
Token ID198
Feature activation+2.06e-01

Pos logit contributions
illac+0.183
Leaks+0.176
ILY+0.174
 Nib+0.171
 CLASS+0.170
Neg logit contributions
angered-0.203
genre-0.185
adem-0.165
bnb-0.163
arios-0.161
Token
Token ID198
Feature activation+5.74e-02

Pos logit contributions
angered+0.610
genre+0.555
adem+0.496
bnb+0.489
arios+0.483
Neg logit contributions
illac-0.552
Leaks-0.529
ILY-0.522
 Nib-0.517
 CLASS-0.514
TokenThis
Token ID1212
Feature activation-1.43e-02

Pos logit contributions
angered+0.184
genre+0.169
adem+0.152
bnb+0.149
arios+0.148
Neg logit contributions
illac-0.141
Leaks-0.133
 Nib-0.132
ILY-0.132
 CLASS-0.131
Token 3
Token ID513
Feature activation-8.72e-02

Pos logit contributions
illac+0.037
Leaks+0.035
ILY+0.035
 Nib+0.034
 CLASS+0.034
Neg logit contributions
angered-0.044
genre-0.040
adem-0.036
bnb-0.036
arios-0.035
Token-
Token ID12
Feature activation+2.95e-01

Pos logit contributions
illac+0.223
Leaks+0.215
ILY+0.211
 Nib+0.209
 CLASS+0.206
Neg logit contributions
angered-0.269
genre-0.247
adem-0.222
bnb-0.219
arios-0.216
Token3
Token ID18
Feature activation+3.00e-01

Pos logit contributions
angered+0.896
genre+0.829
adem+0.742
bnb+0.729
arios+0.718
Neg logit contributions
illac-0.765
Leaks-0.732
ILY-0.725
 Nib-0.721
-0.713
Token-
Token ID12
Feature activation+3.69e-01

Pos logit contributions
angered+0.837
genre+0.758
adem+0.675
bnb+0.665
arios+0.658
Neg logit contributions
illac-0.859
Leaks-0.827
ILY-0.818
 Nib-0.808
 CLASS-0.800
Token5
Token ID20
Feature activation+2.39e-01

Pos logit contributions
angered+1.138
genre+1.056
adem+0.945
bnb+0.934
arios+0.922
Neg logit contributions
illac-0.938
Leaks-0.889
 Nib-0.886
ILY-0.882
-0.876
Tokenomm
Token ID2002
Feature activation+1.29e-01

Pos logit contributions
angered+1.014
genre+0.919
adem+0.834
arios+0.815
bnb+0.815
Neg logit contributions
illac-0.818
Leaks-0.797
ILY-0.773
 Nib-0.768
-0.764
Tokeners
Token ID364
Feature activation-1.59e-01

Pos logit contributions
angered+0.329
genre+0.298
adem+0.264
arios+0.258
bnb+0.252
Neg logit contributions
illac-0.398
Leaks-0.382
ILY-0.379
 Nib-0.373
-0.373
Token II
Token ID2873
Feature activation-4.81e-02

Pos logit contributions
illac+0.384
Leaks+0.369
ILY+0.363
 Nib+0.359
 CLASS+0.356
Neg logit contributions
angered-0.511
genre-0.470
adem-0.425
bnb-0.421
arios-0.415
Token)
Token ID8
Feature activation-3.12e-01

Pos logit contributions
illac+0.121
Leaks+0.117
ILY+0.115
 Nib+0.114
 CLASS+0.113
Neg logit contributions
angered-0.150
genre-0.137
adem-0.124
bnb-0.122
arios-0.120
Token Ivanka
Token ID31002
Feature activation+2.88e-01

Pos logit contributions
illac+0.900
Leaks+0.870
ILY+0.859
 Nib+0.849
 CLASS+0.845
Neg logit contributions
angered-0.858
genre-0.777
adem-0.688
bnb-0.679
arios-0.668
Token Trump
Token ID1301
Feature activation-2.92e-01

Pos logit contributions
angered+0.771
genre+0.688
adem+0.609
bnb+0.600
arios+0.591
Neg logit contributions
illac-0.855
Leaks-0.812
ILY-0.803
-0.797
 Nib-0.795
Token A
Token ID317
Feature activation+2.58e-01

Pos logit contributions
illac+0.744
Leaks+0.714
ILY+0.705
 Nib+0.694
 CLASS+0.689
Neg logit contributions
angered-0.904
genre-0.827
adem-0.745
bnb-0.736
arios-0.723
Token wild
Token ID4295
Feature activation-1.60e-01

Pos logit contributions
angered+0.749
genre+0.678
adem+0.606
bnb+0.597
arios+0.588
Neg logit contributions
illac-0.708
Leaks-0.682
 Nib-0.667
ILY-0.666
 CLASS-0.657
Tokencard
Token ID9517
Feature activation+1.05e+00

Pos logit contributions
illac+0.447
Leaks+0.432
ILY+0.426
 Nib+0.422
 CLASS+0.419
Neg logit contributions
angered-0.453
genre-0.411
adem-0.366
bnb-0.361
arios-0.355
Token choice
Token ID3572
Feature activation-9.16e-02

Pos logit contributions
angered+3.012
genre+2.727
adem+2.431
bnb+2.412
arios+2.363
Neg logit contributions
illac-2.863
Leaks-2.747
ILY-2.691
-2.663
 Nib-2.656
Token for
Token ID329
Feature activation+2.66e-02

Pos logit contributions
illac+0.235
Leaks+0.227
ILY+0.223
 Nib+0.221
 CLASS+0.220
Neg logit contributions
angered-0.280
genre-0.257
adem-0.230
bnb-0.228
arios-0.224
Token but
Token ID475
Feature activation+2.08e-01

Pos logit contributions
angered+0.625
genre+0.567
adem+0.502
bnb+0.496
arios+0.488
Neg logit contributions
illac-0.636
Leaks-0.615
ILY-0.606
 Nib-0.600
 CLASS-0.596
Token they
Token ID484
Feature activation+1.20e-01

Pos logit contributions
angered+0.589
genre+0.534
adem+0.475
bnb+0.469
arios+0.461
Neg logit contributions
illac-0.583
Leaks-0.564
ILY-0.555
 Nib-0.549
 CLASS-0.546
Token were
Token ID547
Feature activation-9.36e-02

Pos logit contributions
angered+0.372
genre+0.337
adem+0.303
bnb+0.301
arios+0.295
Neg logit contributions
illac-0.305
Leaks-0.296
ILY-0.289
 Nib-0.287
 CLASS-0.284
Token usually
Token ID3221
Feature activation+2.36e-02

Pos logit contributions
illac+0.236
Leaks+0.228
ILY+0.225
 Nib+0.222
 CLASS+0.221
Neg logit contributions
angered-0.290
genre-0.266
adem-0.240
bnb-0.237
arios-0.234
Token too
Token ID1165
Feature activation+1.81e-01

Pos logit contributions
angered+0.069
genre+0.063
adem+0.057
bnb+0.056
arios+0.055
Neg logit contributions
illac-0.064
Leaks-0.061
ILY-0.061
 Nib-0.060
 CLASS-0.060
Token stunned
Token ID19987
Feature activation-2.39e-02

Pos logit contributions
angered+0.515
genre+0.466
adem+0.415
bnb+0.410
arios+0.404
Neg logit contributions
illac-0.504
Leaks-0.487
ILY-0.480
 Nib-0.473
 CLASS-0.470
Token to
Token ID284
Feature activation+2.19e-01

Pos logit contributions
illac+0.057
Leaks+0.055
ILY+0.054
 Nib+0.053
 CLASS+0.053
Neg logit contributions
angered-0.077
genre-0.071
adem-0.064
bnb-0.064
arios-0.063
Token realize
Token ID6537
Feature activation+2.79e-01

Pos logit contributions
angered+0.708
genre+0.649
adem+0.588
bnb+0.581
arios+0.574
Neg logit contributions
illac-0.526
Leaks-0.507
ILY-0.497
 Nib-0.490
 CLASS-0.486
Token what
Token ID644
Feature activation-2.65e-01

Pos logit contributions
angered+0.792
genre+0.716
adem+0.637
bnb+0.629
arios+0.619
Neg logit contributions
illac-0.785
Leaks-0.758
ILY-0.744
 Nib-0.735
 CLASS-0.732
Token had
Token ID550
Feature activation-2.28e-01

Pos logit contributions
illac+0.756
Leaks+0.732
ILY+0.724
 Nib+0.716
 CLASS+0.711
Neg logit contributions
angered-0.732
genre-0.665
adem-0.590
bnb-0.582
arios-0.574
Token happened
Token ID3022
Feature activation-5.83e-01

Pos logit contributions
illac+0.574
Leaks+0.552
ILY+0.542
 Nib+0.532
 CLASS+0.531
Neg logit contributions
angered-0.718
genre-0.656
adem-0.590
bnb-0.585
arios-0.578
Token.
Token ID13
Feature activation-8.30e-02

Pos logit contributions
illac+0.246
Leaks+0.238
ILY+0.232
 Nib+0.230
 CLASS+0.229
Neg logit contributions
angered-0.285
genre-0.260
adem-0.234
bnb-0.232
arios-0.228
Token In
Token ID554
Feature activation+1.39e-01

Pos logit contributions
illac+0.211
Leaks+0.204
ILY+0.201
 Nib+0.199
 CLASS+0.198
Neg logit contributions
angered-0.256
genre-0.235
adem-0.211
bnb-0.209
arios-0.205
Token addition
Token ID3090
Feature activation-6.72e-01

Pos logit contributions
angered+0.413
genre+0.377
adem+0.337
bnb+0.333
arios+0.328
Neg logit contributions
illac-0.370
Leaks-0.357
ILY-0.352
 Nib-0.349
 CLASS-0.346
Token,
Token ID11
Feature activation+6.82e-02

Pos logit contributions
illac+1.797
Leaks+1.726
ILY+1.710
 Nib+1.688
 CLASS+1.678
Neg logit contributions
angered-1.986
genre-1.813
adem-1.620
bnb-1.603
arios-1.572
Token they
Token ID484
Feature activation-3.15e-01

Pos logit contributions
angered+0.213
genre+0.195
adem+0.176
bnb+0.174
arios+0.171
Neg logit contributions
illac-0.171
Leaks-0.165
ILY-0.162
 Nib-0.161
 CLASS-0.159
Token would
Token ID561
Feature activation-3.50e-01

Pos logit contributions
illac+0.905
Leaks+0.874
ILY+0.865
 Nib+0.857
 CLASS+0.851
Neg logit contributions
angered-0.867
genre-0.788
adem-0.696
bnb-0.688
arios-0.676
Token be
Token ID307
Feature activation-1.33e-01

Pos logit contributions
illac+0.868
Leaks+0.837
ILY+0.826
 Nib+0.817
 CLASS+0.810
Neg logit contributions
angered-1.096
genre-1.009
adem-0.907
bnb-0.899
arios-0.881
Token required
Token ID2672
Feature activation-3.12e-01

Pos logit contributions
illac+0.433
Leaks+0.422
ILY+0.417
 Nib+0.414
 CLASS+0.413
Neg logit contributions
angered-0.313
genre-0.280
adem-0.240
bnb-0.238
arios-0.231
Token to
Token ID284
Feature activation-2.29e-01

Pos logit contributions
illac+0.643
Leaks+0.615
ILY+0.601
 Nib+0.593
 CLASS+0.588
Neg logit contributions
angered-1.111
genre-1.031
adem-0.942
bnb-0.933
arios-0.922
Token undergo
Token ID17777
Feature activation-4.29e-01

Pos logit contributions
illac+0.571
Leaks+0.550
ILY+0.542
 Nib+0.536
 CLASS+0.532
Neg logit contributions
angered-0.721
genre-0.662
adem-0.595
bnb-0.589
arios-0.580
Token five
Token ID1936
Feature activation-2.74e-01

Pos logit contributions
illac+1.077
Leaks+1.036
ILY+1.023
 Nib+1.010
 CLASS+1.005
Neg logit contributions
angered-1.338
genre-1.228
adem-1.103
bnb-1.092
arios-1.076
Token is
Token ID318
Feature activation-2.53e-01

Pos logit contributions
angered+0.101
genre+0.093
adem+0.083
bnb+0.083
arios+0.082
Neg logit contributions
illac-0.081
Leaks-0.078
ILY-0.077
 Nib-0.075
-0.075
Token a
Token ID257
Feature activation-3.69e-01

Pos logit contributions
illac+0.641
Leaks+0.617
ILY+0.608
 Nib+0.601
 CLASS+0.596
Neg logit contributions
angered-0.785
genre-0.719
adem-0.647
bnb-0.639
arios-0.631
Token construct
Token ID5678
Feature activation-4.91e-01

Pos logit contributions
illac+1.020
Leaks+0.987
ILY+0.976
 Nib+0.967
 CLASS+0.967
Neg logit contributions
angered-1.053
genre-0.958
adem-0.852
bnb-0.840
arios-0.826
Token that
Token ID326
Feature activation+9.03e-02

Pos logit contributions
illac+1.252
Leaks+1.208
ILY+1.196
 Nib+1.181
 CLASS+1.179
Neg logit contributions
angered-1.501
genre-1.375
adem-1.237
bnb-1.217
arios-1.203
Token we
Token ID356
Feature activation+3.54e-02

Pos logit contributions
angered+0.284
genre+0.261
adem+0.235
bnb+0.233
arios+0.230
Neg logit contributions
illac-0.224
Leaks-0.215
ILY-0.213
 Nib-0.209
-0.207
Token use
Token ID779
Feature activation-2.05e-01

Pos logit contributions
angered+0.118
genre+0.108
adem+0.099
bnb+0.097
arios+0.096
Neg logit contributions
illac-0.082
Leaks-0.078
ILY-0.077
 Nib-0.076
 CLASS-0.075
Token to
Token ID284
Feature activation-2.05e-01

Pos logit contributions
illac+0.474
Leaks+0.457
ILY+0.446
 Nib+0.442
 CLASS+0.437
Neg logit contributions
angered-0.678
genre-0.626
adem-0.567
bnb-0.564
arios-0.556
Token remove
Token ID4781
Feature activation-2.79e-01

Pos logit contributions
illac+0.518
Leaks+0.498
ILY+0.491
 Nib+0.483
 CLASS+0.480
Neg logit contributions
angered-0.637
genre-0.585
adem-0.526
bnb-0.520
arios-0.516
Token the
Token ID262
Feature activation+6.58e-02

Pos logit contributions
illac+0.721
Leaks+0.693
ILY+0.685
 Nib+0.675
 CLASS+0.669
Neg logit contributions
angered-0.854
genre-0.781
adem-0.702
bnb-0.693
arios-0.684
Token stuff
Token ID3404
Feature activation-2.75e-02

Pos logit contributions
angered+0.193
genre+0.175
adem+0.157
bnb+0.155
arios+0.153
Neg logit contributions
illac-0.178
Leaks-0.171
ILY-0.169
 Nib-0.166
-0.165
Token we
Token ID356
Feature activation+3.20e-02

Pos logit contributions
illac+0.075
Leaks+0.072
ILY+0.072
 Nib+0.070
 CLASS+0.070
Neg logit contributions
angered-0.080
genre-0.073
adem-0.065
bnb-0.064
arios-0.063
Token SS
Token ID6723
Feature activation-3.77e-02

Pos logit contributions
illac+1.127
Leaks+1.078
ILY+1.069
 Nib+1.066
 CLASS+1.061
Neg logit contributions
angered-1.748
genre-1.622
adem-1.464
bnb-1.456
arios-1.430
TokenN
Token ID45
Feature activation+8.79e-02

Pos logit contributions
illac+0.094
Leaks+0.090
ILY+0.088
+0.086
 Nib+0.086
Neg logit contributions
angered-0.118
genre-0.109
adem-0.099
bnb-0.098
arios-0.096
Token coming
Token ID2406
Feature activation-1.62e-01

Pos logit contributions
angered+0.275
genre+0.252
adem+0.228
bnb+0.224
arios+0.222
Neg logit contributions
illac-0.220
Leaks-0.212
ILY-0.208
 Nib-0.205
 CLASS-0.203
Token on
Token ID319
Feature activation-1.97e-01

Pos logit contributions
illac+0.436
Leaks+0.421
ILY+0.415
 Nib+0.410
 CLASS+0.407
Neg logit contributions
angered-0.477
genre-0.435
adem-0.389
bnb-0.384
arios-0.378
Token line
Token ID1627
Feature activation+2.23e-01

Pos logit contributions
illac+0.570
Leaks+0.552
ILY+0.545
 Nib+0.539
 CLASS+0.536
Neg logit contributions
angered-0.542
genre-0.491
adem-0.435
bnb-0.429
arios-0.421
Token from
Token ID422
Feature activation-2.09e-01

Pos logit contributions
angered+0.655
genre+0.597
adem+0.534
bnb+0.527
arios+0.521
Neg logit contributions
illac-0.603
Leaks-0.583
ILY-0.574
 Nib-0.566
 CLASS-0.563
Token 2017
Token ID2177
Feature activation-9.87e-02

Pos logit contributions
illac+0.575
Leaks+0.555
ILY+0.547
 Nib+0.543
 CLASS+0.540
Neg logit contributions
angered-0.602
genre-0.548
adem-0.488
bnb-0.483
arios-0.474
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
illac+0.261
Leaks+0.252
ILY+0.248
 Nib+0.245
 CLASS+0.243
Neg logit contributions
angered-0.295
genre-0.269
adem-0.241
bnb-0.239
arios-0.235
Token The
Token ID383
Feature activation-1.12e-01

Pos logit contributions
illac+0.605
Leaks+0.583
ILY+0.574
 Nib+0.569
 CLASS+0.565
Neg logit contributions
angered-0.719
genre-0.660
adem-0.592
bnb-0.586
arios-0.578
Token UK
Token ID3482
Feature activation-3.86e-02

Pos logit contributions
illac+0.297
Leaks+0.287
ILY+0.283
 Nib+0.280
 CLASS+0.279
Neg logit contributions
angered-0.335
genre-0.306
adem-0.274
bnb-0.271
arios-0.267
Token has
Token ID468
Feature activation+9.06e-02

Pos logit contributions
illac+0.094
Leaks+0.090
ILY+0.089
 Nib+0.088
 CLASS+0.087
Neg logit contributions
angered-0.124
genre-0.114
adem-0.103
bnb-0.102
arios-0.100
Token reduces
Token ID12850
Feature activation-2.74e-01

Pos logit contributions
illac+0.819
Leaks+0.787
ILY+0.775
 Nib+0.765
 CLASS+0.759
Neg logit contributions
angered-1.118
genre-1.029
adem-0.931
bnb-0.921
arios-0.909
Token power
Token ID1176
Feature activation-1.75e-01

Pos logit contributions
illac+0.665
Leaks+0.639
ILY+0.629
 Nib+0.621
 CLASS+0.616
Neg logit contributions
angered-0.878
genre-0.806
adem-0.729
bnb-0.721
arios-0.712
Token supply
Token ID5127
Feature activation-3.37e-01

Pos logit contributions
illac+0.629
Leaks+0.613
ILY+0.607
 Nib+0.602
 CLASS+0.599
Neg logit contributions
angered-0.358
genre-0.313
adem-0.263
bnb-0.257
arios-0.250
Token noise
Token ID7838
Feature activation-4.00e-01

Pos logit contributions
illac+0.892
Leaks+0.863
ILY+0.853
 Nib+0.842
 CLASS+0.837
Neg logit contributions
angered-1.003
genre-0.916
adem-0.820
bnb-0.810
arios-0.795
Token as
Token ID355
Feature activation-4.47e-01

Pos logit contributions
illac+1.062
Leaks+1.027
ILY+1.015
 Nib+1.001
 CLASS+0.995
Neg logit contributions
angered-1.188
genre-1.085
adem-0.971
bnb-0.959
arios-0.942
Token well
Token ID880
Feature activation-1.03e+00

Pos logit contributions
illac+1.156
Leaks+1.114
ILY+1.097
 Nib+1.084
 CLASS+1.074
Neg logit contributions
angered-1.363
genre-1.245
adem-1.118
bnb-1.105
arios-1.092
Token as
Token ID355
Feature activation-4.19e-01

Pos logit contributions
illac+2.351
Leaks+2.254
ILY+2.229
 Nib+2.190
 CLASS+2.186
Neg logit contributions
angered-3.436
genre-3.165
adem-2.875
bnb-2.842
arios-2.807
Token increases
Token ID5732
Feature activation+1.29e-01

Pos logit contributions
illac+1.079
Leaks+1.039
ILY+1.025
 Nib+1.012
 CLASS+1.006
Neg logit contributions
angered-1.281
genre-1.173
adem-1.054
bnb-1.041
arios-1.027
Token overcl
Token ID40397
Feature activation+8.43e-02

Pos logit contributions
angered+0.384
genre+0.351
adem+0.314
bnb+0.311
arios+0.307
Neg logit contributions
illac-0.343
Leaks-0.329
ILY-0.324
 Nib-0.321
 CLASS-0.318
Tokenocking
Token ID8629
Feature activation+2.72e-02

Pos logit contributions
angered+0.163
genre+0.142
adem+0.118
bnb+0.114
arios+0.112
Neg logit contributions
illac-0.312
Leaks-0.303
ILY-0.301
 Nib-0.299
 CLASS-0.298
Token stability
Token ID10159
Feature activation-6.13e-01

Pos logit contributions
angered+0.071
genre+0.064
adem+0.056
bnb+0.056
arios+0.055
Neg logit contributions
illac-0.082
Leaks-0.080
ILY-0.079
 Nib-0.078
 CLASS-0.077
Token Hide
Token ID10415
Feature activation+3.29e-01

Pos logit contributions
illac+0.489
Leaks+0.464
ILY+0.457
 Nib+0.443
+0.443
Neg logit contributions
angered-0.856
genre-0.791
adem-0.723
bnb-0.715
arios-0.709
Token Caption
Token ID11260
Feature activation-3.68e-01

Pos logit contributions
angered+0.873
genre+0.788
adem+0.694
bnb+0.685
arios+0.673
Neg logit contributions
illac-0.980
Leaks-0.949
ILY-0.938
 Nib-0.928
 CLASS-0.923
Token 13
Token ID1511
Feature activation+8.51e-02

Pos logit contributions
illac+0.813
Leaks+0.806
 Nib+0.791
ILY+0.783
 CLASS+0.768
Neg logit contributions
angered-1.230
genre-1.152
adem-1.051
bnb-1.045
arios-1.005
Token of
Token ID286
Feature activation-5.18e-01

Pos logit contributions
angered+0.232
genre+0.211
adem+0.187
bnb+0.185
arios+0.182
Neg logit contributions
illac-0.245
Leaks-0.238
ILY-0.236
 Nib-0.233
 CLASS-0.231
Token 15
Token ID1315
Feature activation-4.19e-01

Pos logit contributions
illac+1.073
Leaks+1.043
ILY+1.028
 CLASS+1.026
 Nib+1.017
Neg logit contributions
angered-1.803
genre-1.689
adem-1.545
bnb-1.528
arios-1.503
Token Photos
Token ID9434
Feature activation-9.39e-01

Pos logit contributions
illac+0.847
Leaks+0.816
ILY+0.798
 Nib+0.794
 CLASS+0.787
Neg logit contributions
angered-1.501
genre-1.403
adem-1.286
bnb-1.269
arios-1.251
Token:
Token ID25
Feature activation+2.44e-01

Pos logit contributions
Leaks+2.096
illac+2.092
ILY+2.061
 Nib+2.019
Men+2.004
Neg logit contributions
angered-3.058
genre-2.854
adem-2.622
bnb-2.606
arios-2.540
Token Carly
Token ID35982
Feature activation-3.68e-01

Pos logit contributions
angered+0.951
genre+0.880
adem+0.815
bnb+0.806
arios+0.800
Neg logit contributions
illac-0.427
Leaks-0.397
ILY-0.387
-0.375
 CLASS-0.374
Token Fiorina
Token ID49028
Feature activation-4.52e-02

Pos logit contributions
illac+0.900
Leaks+0.871
ILY+0.857
 Nib+0.849
 CLASS+0.838
Neg logit contributions
angered-1.172
genre-1.078
adem-0.972
bnb-0.963
arios-0.948
Token's
Token ID338
Feature activation-6.19e-01

Pos logit contributions
illac+0.103
Leaks+0.099
ILY+0.097
 Nib+0.096
 CLASS+0.095
Neg logit contributions
angered-0.152
genre-0.140
adem-0.127
bnb-0.125
arios-0.124
Token political
Token ID1964
Feature activation+4.79e-02

Pos logit contributions
illac+1.526
Leaks+1.483
ILY+1.470
 Nib+1.445
 CLASS+1.440
Neg logit contributions
angered-1.939
genre-1.769
bnb-1.595
adem-1.590
arios-1.563
Token tied
Token ID8165
Feature activation-5.01e-01

Pos logit contributions
angered+0.881
genre+0.809
adem+0.724
bnb+0.717
arios+0.711
Neg logit contributions
illac-0.747
Leaks-0.718
ILY-0.705
 Nib-0.692
 CLASS-0.687
Token to
Token ID284
Feature activation+2.30e-01

Pos logit contributions
illac+1.042
Leaks+0.996
ILY+0.974
 Nib+0.962
 CLASS+0.955
Neg logit contributions
angered-1.783
genre-1.654
adem-1.512
bnb-1.495
arios-1.480
Token the
Token ID262
Feature activation+6.57e-02

Pos logit contributions
angered+0.656
genre+0.596
adem+0.531
bnb+0.523
arios+0.517
Neg logit contributions
illac-0.640
Leaks-0.614
ILY-0.604
 Nib-0.595
 CLASS-0.593
Token "
Token ID366
Feature activation-1.67e-01

Pos logit contributions
angered+0.189
genre+0.172
adem+0.153
bnb+0.151
arios+0.149
Neg logit contributions
illac-0.181
Leaks-0.175
ILY-0.173
 Nib-0.171
 CLASS-0.170
TokenUnited
Token ID17013
Feature activation+1.32e-01

Pos logit contributions
illac+0.447
Leaks+0.429
ILY+0.424
 Nib+0.420
 CLASS+0.417
Neg logit contributions
angered-0.498
genre-0.455
adem-0.406
bnb-0.401
arios-0.395
Token Nations
Token ID7973
Feature activation-9.17e-01

Pos logit contributions
angered+0.438
genre+0.400
adem+0.364
bnb+0.359
arios+0.358
Neg logit contributions
illac-0.313
Leaks-0.293
ILY-0.292
-0.284
 Nib-0.282
Token Millennium
Token ID26139
Feature activation-1.33e-01

Pos logit contributions
illac+2.501
Leaks+2.447
 Nib+2.396
ILY+2.392
 CLASS+2.378
Neg logit contributions
angered-2.614
genre-2.395
adem-2.140
bnb-2.111
arios-2.061
Token Development
Token ID7712
Feature activation-3.31e-01

Pos logit contributions
illac+0.305
Leaks+0.295
ILY+0.289
 Nib+0.286
 CLASS+0.284
Neg logit contributions
angered-0.442
genre-0.409
adem-0.370
bnb-0.367
arios-0.362
Token Goals
Token ID28510
Feature activation-3.02e-01

Pos logit contributions
illac+0.651
Leaks+0.627
ILY+0.611
 Nib+0.606
 CLASS+0.600
Neg logit contributions
angered-1.202
genre-1.122
adem-1.024
bnb-1.016
arios-1.004
Token."
Token ID526
Feature activation-1.29e-01

Pos logit contributions
illac+0.856
Leaks+0.828
ILY+0.818
 Nib+0.809
 CLASS+0.805
Neg logit contributions
angered-0.843
genre-0.766
adem-0.679
bnb-0.671
arios-0.660
Token Students
Token ID14882
Feature activation+1.14e-01

Pos logit contributions
illac+0.322
Leaks+0.309
ILY+0.305
 Nib+0.299
 CLASS+0.297
Neg logit contributions
angered-0.405
genre-0.371
adem-0.334
bnb-0.330
arios-0.326
Token understand
Token ID1833
Feature activation+3.51e-01

Pos logit contributions
angered+0.661
genre+0.607
adem+0.550
bnb+0.543
arios+0.535
Neg logit contributions
illac-0.516
Leaks-0.497
ILY-0.484
 Nib-0.476
 CLASS-0.475
Token and
Token ID290
Feature activation+1.30e-01

Pos logit contributions
angered+1.023
genre+0.934
adem+0.835
bnb+0.823
arios+0.813
Neg logit contributions
illac-0.954
Leaks-0.917
ILY-0.899
 Nib-0.885
 CLASS-0.882
Token execute
Token ID12260
Feature activation+1.34e-01

Pos logit contributions
angered+0.399
genre+0.365
adem+0.329
bnb+0.323
arios+0.319
Neg logit contributions
illac-0.336
Leaks-0.323
ILY-0.318
 Nib-0.312
 CLASS-0.311
Token the
Token ID262
Feature activation+1.16e-03

Pos logit contributions
angered+0.392
genre+0.358
adem+0.320
bnb+0.316
arios+0.311
Neg logit contributions
illac-0.360
Leaks-0.347
ILY-0.340
 Nib-0.336
 CLASS-0.334
Token Mu
Token ID8252
Feature activation-4.55e-01

Pos logit contributions
angered+0.003
genre+0.003
adem+0.003
bnb+0.003
arios+0.003
Neg logit contributions
illac-0.003
Leaks-0.003
ILY-0.003
 Nib-0.003
 CLASS-0.003
Tokenay
Token ID323
Feature activation-9.90e-01

Pos logit contributions
illac+1.213
Leaks+1.171
ILY+1.154
 Nib+1.143
 CLASS+1.135
Neg logit contributions
angered-1.350
genre-1.232
adem-1.100
bnb-1.088
arios-1.072
Token Thai
Token ID18933
Feature activation-4.29e-01

Pos logit contributions
illac+3.663
Leaks+3.570
 Nib+3.547
 CLASS+3.530
ILY+3.526
Neg logit contributions
angered-1.898
genre-1.623
adem-1.330
bnb-1.309
arios-1.280
Token I
Token ID314
Feature activation-2.85e-02

Pos logit contributions
illac+1.214
Leaks+1.180
ILY+1.163
 Nib+1.153
 CLASS+1.149
Neg logit contributions
angered-1.204
genre-1.088
adem-0.965
bnb-0.956
arios-0.938
Token have
Token ID423
Feature activation+2.59e-02

Pos logit contributions
illac+0.069
Leaks+0.067
ILY+0.066
 Nib+0.065
 CLASS+0.064
Neg logit contributions
angered-0.091
genre-0.084
adem-0.076
bnb-0.075
arios-0.074
Token been
Token ID587
Feature activation+7.59e-02

Pos logit contributions
angered+0.086
genre+0.079
adem+0.072
bnb+0.071
arios+0.071
Neg logit contributions
illac-0.060
Leaks-0.058
ILY-0.056
 Nib-0.055
 CLASS-0.055
Token training
Token ID3047
Feature activation+8.54e-02

Pos logit contributions
angered+0.228
genre+0.208
adem+0.187
bnb+0.184
arios+0.181
Neg logit contributions
illac-0.200
Leaks-0.193
ILY-0.189
 Nib-0.187
 CLASS-0.186
TokenH
Token ID39
Feature activation-1.07e-01

Pos logit contributions
illac+0.602
Leaks+0.569
ILY+0.565
 Nib+0.564
+0.556
Neg logit contributions
angered-0.769
genre-0.706
adem-0.638
bnb-0.633
arios-0.627
TokenVM
Token ID15996
Feature activation-2.81e-01

Pos logit contributions
illac+0.232
Leaks+0.218
 Nib+0.215
ILY+0.214
+0.211
Neg logit contributions
angered-0.371
genre-0.344
adem-0.316
bnb-0.313
arios-0.311
Token",
Token ID1600
Feature activation+1.65e-01

Pos logit contributions
illac+0.709
Leaks+0.673
ILY+0.669
 Nib+0.660
+0.654
Neg logit contributions
angered-0.881
genre-0.804
adem-0.728
bnb-0.721
arios-0.713
Token after
Token ID706
Feature activation+1.98e-01

Pos logit contributions
angered+0.461
genre+0.417
adem+0.370
bnb+0.367
arios+0.362
Neg logit contributions
illac-0.466
Leaks-0.451
ILY-0.444
 Nib-0.436
-0.433
Token the
Token ID262
Feature activation-7.83e-02

Pos logit contributions
angered+0.614
genre+0.563
adem+0.506
bnb+0.503
arios+0.496
Neg logit contributions
illac-0.497
Leaks-0.480
ILY-0.472
 Nib-0.463
-0.461
Token drivers
Token ID6643
Feature activation-8.64e-01

Pos logit contributions
illac+0.207
Leaks+0.200
ILY+0.197
 Nib+0.194
 CLASS+0.193
Neg logit contributions
angered-0.234
genre-0.213
adem-0.191
bnb-0.189
arios-0.186
Token.
Token ID13
Feature activation+1.92e-03

Pos logit contributions
illac+2.239
Leaks+2.134
ILY+2.121
 CLASS+2.115
 Nib+2.114
Neg logit contributions
angered-2.622
genre-2.388
adem-2.148
bnb-2.119
arios-2.094
Token This
Token ID770
Feature activation-1.31e-01

Pos logit contributions
angered+0.006
genre+0.005
adem+0.005
bnb+0.005
arios+0.005
Neg logit contributions
illac-0.005
Leaks-0.005
ILY-0.005
 Nib-0.005
 CLASS-0.005
Token improves
Token ID19575
Feature activation+2.83e-01

Pos logit contributions
illac+0.326
Leaks+0.313
ILY+0.308
 Nib+0.303
+0.300
Neg logit contributions
angered-0.414
genre-0.381
adem-0.342
bnb-0.340
arios-0.335
Token some
Token ID617
Feature activation-5.34e-02

Pos logit contributions
angered+0.856
genre+0.782
bnb+0.706
adem+0.700
arios+0.696
Neg logit contributions
illac-0.733
Leaks-0.700
ILY-0.687
-0.678
 Nib-0.677
Token kinds
Token ID6982
Feature activation+2.87e-01

Pos logit contributions
illac+0.149
Leaks+0.144
ILY+0.142
 Nib+0.140
 CLASS+0.139
Neg logit contributions
angered-0.152
genre-0.138
adem-0.123
bnb-0.121
arios-0.119