TOP ACTIVATIONS
MAX = 10.495

scrap . Article Continued Below The T
last . Article Continued Below T od
mess seriously Article Continued Below
pell . Story continues below advertisement "
keeper . Story continues below advertisement Story
below advertisement Story continues below advertisement The
dollars . Story continues below advertisement Story
stage . Story continues below advertisement He
classes . [ np - related ] <|endoftext|> The
statement . Story continues below advertisement It
AP ) Story continues There were a
relations with Gaddafi had s oured . The Libyan leader demanded
que tr iste . J ' ai l ' hon ne
<|endoftext|> BR USS ELS ( Reuters ) - The world
ents ind iqu ent qu ' ils ont mont é une
ant neut re . J ' esp ère que v ous
club . Story continues below advertisement He
K hal isha told NBC news that her brother survived
<|endoftext|> HA V ANA ( Reuters ) - Latin American and
[ H / t The Hill ] <|endoftext|>

MIN ACTIVATIONS
MIN = -8.308

support from former Ku Klux Klan leader David Duke . (
lives , or am I fool ing myself ?
reliable in the fight against IS in the north of the
partners in the fight against IS - and Russia .
We must commit ourselves very res olutely because there
as the Caps out - shot the Blues 10 - 8
training ground . I was lucky . I was in a
el m ose , an Ike a manager . " The
in 1999 . Am ad ou Di allo said he was
in Spain , should expose themselves to the challenge of advancing
Wiki Leaks pr ides itself as a website devoted to
or am I fool ing myself ? All these
kingdom for alleged anti - state acts , died at 2
the idea that a foreign state could be trying to influence
enemies of the North Korean state . The only recognizable special
which is the BIOS default . With two cards
they have opened themselves up to the disbelief , the
to reduce the motion blur even more through the use of
…… . Dear George , I
to get someone to open up . It s

INTERVAL 5.794 - 10.495
CONTAINS 0.071%

2 ) $ rect 2 = New - Object System .
throne . See also [ edit ]
is gaining ground in the race .
attorneys general to oppose the confirmation of Mer rick Garland to
iji Press , AFP / Getty Images ) A

INTERVAL 1.093 - 5.794
CONTAINS 21.970%

, access to Kindle Owners L ending Library ,
Korean retaliation towards Sony surfaced . If you aren
people have visited since it opened , Lee said .
won , but there will also be a ton of pressure
easy to respond to this woman with sentimental plat itudes ,

INTERVAL -3.608 - 1.093
CONTAINS 76.692%

the only workers getting extra benefits for tough conditions .
the first water , an enormous White Elephant , completely unnecessary
standing Actor in a Comedy in Emmy history Robert Gu
workload s including interrupts and timers . Things started
nomination locked up and is lining up support within his own

INTERVAL -8.308 - -3.608
CONTAINS 1.267%

g lor ious diversity ' of people of all faiths ,
plant to a lined structural fill solution while continuing to search
Some Pictures of That Corner Vari ation , Don
finished eighth in D Y AR ( total value at his
five - day custody of Mr Tom ar .
Token scrap
Token ID15881
Feature activation-3.87e-01

Pos logit contributions
emetery+0.178
ospel+0.176
vernment+0.172
ppa+0.171
appa+0.163
Neg logit contributions
 Frie-0.185
spir-0.179
Male-0.169
 AAA-0.165
 UCHIJ-0.162
Token.
Token ID13
Feature activation+6.45e-01

Pos logit contributions
emetery+0.296
ospel+0.293
vernment+0.286
ppa+0.286
appa+0.273
Neg logit contributions
 Frie-0.300
spir-0.290
Male-0.275
 AAA-0.267
querque-0.263
Token
Token ID198
Feature activation-4.21e-01

Pos logit contributions
 Frie+0.502
spir+0.482
Male+0.456
 AAA+0.449
 UCHIJ+0.437
Neg logit contributions
emetery-0.501
ospel-0.493
vernment-0.481
ppa-0.478
appa-0.457
Token
Token ID198
Feature activation-1.54e-01

Pos logit contributions
emetery+0.321
ospel+0.320
ppa+0.312
vernment+0.311
appa+0.298
Neg logit contributions
 Frie-0.330
spir-0.315
Male-0.297
 AAA-0.291
querque-0.290
TokenArticle
Token ID14906
Feature activation+4.14e+00

Pos logit contributions
emetery+0.127
ospel+0.126
vernment+0.124
ppa+0.123
appa+0.118
Neg logit contributions
 Frie-0.111
spir-0.106
Male-0.100
 AAA-0.098
 UCHIJ-0.096
Token Continued
Token ID22168
Feature activation+1.05e+01

Pos logit contributions
 Frie+3.501
spir+3.413
Male+3.207
 AAA+3.165
 UCHIJ+3.093
Neg logit contributions
emetery-2.931
ospel-2.852
vernment-2.822
ppa-2.733
appa-2.609
Token Below
Token ID10383
Feature activation+6.67e+00

Pos logit contributions
spir+2.855
 Frie+2.552
Male+2.280
 AAA+2.264
 UCHIJ+1.925
Neg logit contributions
emetery-13.241
vernment-13.035
ailability-12.930
ospel-12.698
jri-12.501
Token
Token ID198
Feature activation-1.41e+00

Pos logit contributions
spir+4.196
 Frie+4.133
Male+3.939
 AAA+3.892
 UCHIJ+3.719
Neg logit contributions
emetery-6.079
vernment-5.856
ospel-5.791
ppa-5.567
ailability-5.563
Token
Token ID198
Feature activation-1.49e+00

Pos logit contributions
ospel+1.049
emetery+1.045
ppa+1.025
vernment+1.013
appa+0.975
Neg logit contributions
 Frie-1.133
spir-1.074
Male-1.015
querque-1.014
 AAA-0.993
TokenThe
Token ID464
Feature activation-1.42e+00

Pos logit contributions
emetery+1.245
ospel+1.241
ppa+1.218
vernment+1.214
appa+1.166
Neg logit contributions
 Frie-1.050
spir-0.990
Male-0.922
 AAA-0.912
querque-0.911
Token T
Token ID309
Feature activation+1.27e+00

Pos logit contributions
emetery+1.056
ospel+1.050
vernment+1.030
ppa+1.024
appa+0.979
Neg logit contributions
 Frie-1.134
spir-1.096
Male-1.043
 AAA-1.003
querque-0.998
Token last
Token ID938
Feature activation+8.65e-01

Pos logit contributions
emetery+1.029
ospel+1.016
vernment+0.989
ppa+0.985
appa+0.935
Neg logit contributions
 Frie-1.249
spir-1.202
Male-1.144
 AAA-1.123
 UCHIJ-1.101
Token.
Token ID13
Feature activation+3.97e-01

Pos logit contributions
 Frie+0.675
spir+0.642
Male+0.610
 AAA+0.604
querque+0.583
Neg logit contributions
emetery-0.672
ospel-0.662
vernment-0.641
ppa-0.640
appa-0.611
Token
Token ID198
Feature activation-1.52e+00

Pos logit contributions
 Frie+0.305
spir+0.293
Male+0.277
 AAA+0.272
 UCHIJ+0.265
Neg logit contributions
emetery-0.313
ospel-0.307
vernment-0.300
ppa-0.298
appa-0.286
Token
Token ID198
Feature activation-1.50e+00

Pos logit contributions
ospel+1.110
emetery+1.099
ppa+1.089
vernment+1.070
appa+1.033
Neg logit contributions
 Frie-1.242
spir-1.170
querque-1.126
Male-1.105
 AAA-1.083
TokenArticle
Token ID14906
Feature activation+5.12e-01

Pos logit contributions
emetery+1.132
ospel+1.127
ppa+1.102
vernment+1.099
appa+1.048
Neg logit contributions
 Frie-1.180
spir-1.126
Male-1.061
 AAA-1.050
querque-1.040
Token Continued
Token ID22168
Feature activation+1.04e+01

Pos logit contributions
 Frie+0.448
spir+0.433
Male+0.412
 AAA+0.404
 UCHIJ+0.397
Neg logit contributions
emetery-0.344
ospel-0.339
vernment-0.330
ppa-0.329
appa-0.312
Token Below
Token ID10383
Feature activation+6.76e+00

Pos logit contributions
spir+2.754
 Frie+2.387
Male+2.122
 AAA+2.101
 UCHIJ+1.686
Neg logit contributions
emetery-13.104
vernment-12.894
ailability-12.750
ospel-12.639
jri-12.322
Token
Token ID198
Feature activation-8.21e-01

Pos logit contributions
spir+4.191
 Frie+4.104
Male+3.946
 AAA+3.881
 UCHIJ+3.695
Neg logit contributions
emetery-6.226
vernment-5.998
ospel-5.941
ailability-5.767
ppa-5.684
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
emetery+0.624
ospel+0.622
ppa+0.607
vernment+0.604
appa+0.578
Neg logit contributions
 Frie-0.644
spir-0.615
Male-0.581
querque-0.569
 AAA-0.569
TokenT
Token ID51
Feature activation+1.33e+00

Pos logit contributions
emetery+0.970
ospel+0.966
ppa+0.944
vernment+0.944
appa+0.904
Neg logit contributions
 Frie-0.840
spir-0.799
Male-0.749
 AAA-0.737
querque-0.729
Tokenod
Token ID375
Feature activation+1.98e+00

Pos logit contributions
 Frie+0.999
spir+0.975
Male+0.914
 AAA+0.890
 UCHIJ+0.865
Neg logit contributions
emetery-1.047
ospel-1.035
vernment-1.018
ppa-1.015
appa-0.963
Token mess
Token ID2085
Feature activation-1.69e+00

Pos logit contributions
 Frie+0.462
spir+0.445
Male+0.421
 AAA+0.412
 UCHIJ+0.403
Neg logit contributions
emetery-0.456
ospel-0.451
vernment-0.440
ppa-0.438
appa-0.419
Token seriously
Token ID6411
Feature activation-2.77e+00

Pos logit contributions
emetery+1.053
ospel+1.041
vernment+1.015
ppa+1.008
appa+0.953
Neg logit contributions
 Frie-1.557
spir-1.499
Male-1.433
 AAA-1.406
 UCHIJ-1.390
Token
Token ID198
Feature activation-2.62e+00

Pos logit contributions
emetery+2.070
ospel+2.056
ppa+2.017
vernment+2.016
appa+1.914
Neg logit contributions
 Frie-2.161
spir-2.088
Male-1.973
querque-1.921
 AAA-1.914
Token
Token ID198
Feature activation-2.25e+00

Pos logit contributions
ospel+1.892
emetery+1.874
ppa+1.869
vernment+1.823
appa+1.767
Neg logit contributions
 Frie-2.146
spir-2.022
querque-1.960
Male-1.910
 AAA-1.875
TokenArticle
Token ID14906
Feature activation+4.14e+00

Pos logit contributions
emetery+1.485
ospel+1.474
ppa+1.445
vernment+1.433
appa+1.358
Neg logit contributions
 Frie-1.986
spir-1.894
Male-1.796
 AAA-1.780
querque-1.772
Token Continued
Token ID22168
Feature activation+1.03e+01

Pos logit contributions
 Frie+3.416
spir+3.361
Male+3.124
 AAA+3.087
 UCHIJ+3.006
Neg logit contributions
emetery-3.031
vernment-2.942
ospel-2.925
ppa-2.791
jri-2.695
Token Below
Token ID10383
Feature activation+6.42e+00

Pos logit contributions
spir+2.899
 Frie+2.651
Male+2.352
 AAA+2.339
 UCHIJ+2.036
Neg logit contributions
emetery-12.853
vernment-12.761
ailability-12.470
ospel-12.431
jri-12.179
Token
Token ID198
Feature activation-3.72e-01

Pos logit contributions
spir+4.077
 Frie+4.049
Male+3.851
 AAA+3.790
 UCHIJ+3.630
Neg logit contributions
emetery-5.805
vernment-5.591
ospel-5.559
ppa-5.333
ailability-5.277
Token
Token ID198
Feature activation-5.05e-01

Pos logit contributions
emetery+0.287
ospel+0.285
ppa+0.278
vernment+0.278
appa+0.265
Neg logit contributions
 Frie-0.288
spir-0.276
Male-0.261
 AAA-0.255
querque-0.253
Token
Token ID447
Feature activation-1.09e+00

Pos logit contributions
emetery+0.438
ospel+0.434
ppa+0.425
vernment+0.425
appa+0.407
Neg logit contributions
 Frie-0.344
spir-0.327
Male-0.306
 AAA-0.299
querque-0.294
Token
Token ID250
Feature activation-6.59e-02

Pos logit contributions
emetery+0.935
ospel+0.923
vernment+0.910
ppa+0.906
appa+0.868
Neg logit contributions
 Frie-0.744
spir-0.709
Male-0.665
 AAA-0.647
 UCHIJ-0.637
Tokenpell
Token ID23506
Feature activation+1.04e+00

Pos logit contributions
 Frie+0.295
spir+0.281
Male+0.264
 AAA+0.257
querque+0.253
Neg logit contributions
emetery-0.399
ospel-0.395
ppa-0.389
vernment-0.386
appa-0.373
Token.
Token ID13
Feature activation+9.52e-01

Pos logit contributions
 Frie+0.810
spir+0.778
Male+0.738
 AAA+0.718
querque+0.708
Neg logit contributions
emetery-0.797
ospel-0.790
ppa-0.771
vernment-0.771
appa-0.736
Token
Token ID198
Feature activation-1.16e-01

Pos logit contributions
 Frie+0.723
spir+0.697
Male+0.659
 AAA+0.647
 UCHIJ+0.627
Neg logit contributions
emetery-0.755
ospel-0.741
vernment-0.724
ppa-0.719
appa-0.690
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
emetery+0.089
ospel+0.088
ppa+0.086
vernment+0.086
appa+0.082
Neg logit contributions
 Frie-0.090
spir-0.086
Male-0.081
 AAA-0.080
querque-0.079
TokenStory
Token ID11605
Feature activation+4.75e+00

Pos logit contributions
 Frie+0.089
spir+0.085
Male+0.081
 AAA+0.079
 UCHIJ+0.077
Neg logit contributions
emetery-0.092
ospel-0.090
vernment-0.088
ppa-0.088
appa-0.084
Token continues
Token ID4477
Feature activation+1.01e+01

Pos logit contributions
spir+2.822
 Frie+2.793
Male+2.554
 AAA+2.496
 UCHIJ+2.386
Neg logit contributions
emetery-4.457
ospel-4.345
vernment-4.305
ppa-4.178
appa-4.076
Token below
Token ID2174
Feature activation+5.51e+00

Pos logit contributions
spir+4.226
 Frie+3.940
 AAA+3.892
Male+3.802
 UCHIJ+3.527
Neg logit contributions
emetery-10.912
ospel-10.539
vernment-10.525
ailability-10.393
ppa-10.278
Token advertisement
Token ID15422
Feature activation+3.75e+00

Pos logit contributions
 Frie+5.208
spir+5.157
 AAA+5.065
Male+4.986
 UCHIJ+4.791
Neg logit contributions
emetery-3.163
ospel-3.058
vernment-2.946
ppa-2.837
appa-2.672
Token
Token ID198
Feature activation-8.80e-01

Pos logit contributions
spir+2.501
 Frie+2.486
Male+2.357
 AAA+2.308
 UCHIJ+2.209
Neg logit contributions
emetery-3.315
ospel-3.177
vernment-3.176
ppa-3.063
jri-2.983
Token
Token ID198
Feature activation-7.98e-01

Pos logit contributions
ospel+0.652
emetery+0.649
ppa+0.637
vernment+0.629
appa+0.606
Neg logit contributions
 Frie-0.707
spir-0.669
querque-0.634
Male-0.632
 AAA-0.619
Token"
Token ID1
Feature activation+2.26e+00

Pos logit contributions
emetery+0.645
ospel+0.640
ppa+0.626
vernment+0.625
appa+0.599
Neg logit contributions
 Frie-0.590
spir-0.560
Male-0.526
 AAA-0.519
querque-0.513
Tokenkeeper
Token ID13884
Feature activation+3.94e-01

Pos logit contributions
 Frie+1.283
spir+1.257
Male+1.204
 AAA+1.177
 UCHIJ+1.158
Neg logit contributions
emetery-0.728
ospel-0.719
vernment-0.695
ppa-0.686
appa-0.644
Token.
Token ID13
Feature activation+8.53e-01

Pos logit contributions
 Frie+0.296
spir+0.284
Male+0.268
 AAA+0.263
 UCHIJ+0.257
Neg logit contributions
emetery-0.314
ospel-0.310
vernment-0.303
ppa-0.302
appa-0.289
Token
Token ID198
Feature activation+1.72e+00

Pos logit contributions
 Frie+0.658
spir+0.632
Male+0.598
 AAA+0.586
 UCHIJ+0.574
Neg logit contributions
emetery-0.665
ospel-0.656
vernment-0.642
ppa-0.637
appa-0.609
Token
Token ID198
Feature activation+1.44e+00

Pos logit contributions
 Frie+1.236
spir+1.215
Male+1.147
 AAA+1.120
 UCHIJ+1.088
Neg logit contributions
emetery-1.425
ospel-1.387
vernment-1.373
ppa-1.345
appa-1.291
TokenStory
Token ID11605
Feature activation+4.62e+00

Pos logit contributions
 Frie+1.019
spir+0.993
Male+0.942
 AAA+0.902
 UCHIJ+0.885
Neg logit contributions
emetery-1.199
ospel-1.180
vernment-1.161
ppa-1.144
appa-1.100
Token continues
Token ID4477
Feature activation+9.98e+00

Pos logit contributions
spir+2.777
 Frie+2.724
Male+2.500
 AAA+2.447
 UCHIJ+2.324
Neg logit contributions
emetery-4.323
ospel-4.215
vernment-4.188
ppa-4.055
appa-3.987
Token below
Token ID2174
Feature activation+4.75e+00

Pos logit contributions
spir+4.244
 Frie+3.904
 AAA+3.852
Male+3.820
 UCHIJ+3.535
Neg logit contributions
emetery-10.694
vernment-10.529
ospel-10.347
ailability-10.278
ppa-10.103
Token advertisement
Token ID15422
Feature activation+4.22e+00

Pos logit contributions
 Frie+4.618
spir+4.552
 AAA+4.440
Male+4.392
 UCHIJ+4.247
Neg logit contributions
emetery-2.626
ospel-2.546
vernment-2.471
ppa-2.382
appa-2.235
Token
Token ID198
Feature activation-1.32e+00

Pos logit contributions
spir+2.787
 Frie+2.774
Male+2.633
 AAA+2.583
 UCHIJ+2.463
Neg logit contributions
emetery-3.751
vernment-3.600
ospel-3.593
ppa-3.460
ailability-3.381
Token
Token ID198
Feature activation-1.39e+00

Pos logit contributions
ospel+0.965
emetery+0.956
ppa+0.943
vernment+0.927
appa+0.896
Neg logit contributions
 Frie-1.075
spir-1.012
querque-0.971
Male-0.955
 AAA-0.938
TokenStory
Token ID11605
Feature activation+3.24e+00

Pos logit contributions
emetery+0.844
ospel+0.844
ppa+0.823
vernment+0.804
appa+0.771
Neg logit contributions
 Frie-1.313
spir-1.242
 AAA-1.185
querque-1.182
Male-1.174
Token below
Token ID2174
Feature activation+4.57e+00

Pos logit contributions
spir+4.127
 Frie+4.069
 AAA+3.836
Male+3.797
 UCHIJ+3.459
Neg logit contributions
emetery-10.509
ospel-10.190
vernment-10.009
ppa-9.955
ailability-9.678
Token advertisement
Token ID15422
Feature activation+4.25e+00

Pos logit contributions
 Frie+4.559
spir+4.464
Male+4.304
 AAA+4.264
 UCHIJ+4.122
Neg logit contributions
emetery-2.435
ospel-2.409
vernment-2.269
ppa-2.249
jri-2.098
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
spir+2.798
 Frie+2.783
Male+2.652
 AAA+2.588
 UCHIJ+2.470
Neg logit contributions
emetery-3.788
ospel-3.625
vernment-3.613
ppa-3.490
ailability-3.424
Token
Token ID198
Feature activation-1.16e+00

Pos logit contributions
ospel+0.766
emetery+0.761
ppa+0.749
vernment+0.738
appa+0.711
Neg logit contributions
 Frie-0.842
spir-0.795
querque-0.758
Male-0.750
 AAA-0.736
TokenStory
Token ID11605
Feature activation+2.64e+00

Pos logit contributions
emetery+0.741
ospel+0.739
ppa+0.722
vernment+0.712
appa+0.678
Neg logit contributions
 Frie-1.054
spir-1.003
 AAA-0.947
querque-0.946
Male-0.945
Token continues
Token ID4477
Feature activation+9.83e+00

Pos logit contributions
 Frie+1.685
spir+1.657
Male+1.513
 AAA+1.485
 UCHIJ+1.430
Neg logit contributions
emetery-2.378
ospel-2.340
vernment-2.313
ppa-2.254
appa-2.189
Token below
Token ID2174
Feature activation+4.76e+00

Pos logit contributions
spir+4.122
 Frie+3.748
Male+3.718
 AAA+3.690
 UCHIJ+3.401
Neg logit contributions
emetery-10.569
vernment-10.361
ospel-10.252
ailability-10.245
ppa-10.057
Token advertisement
Token ID15422
Feature activation+2.86e+00

Pos logit contributions
 Frie+4.574
spir+4.519
 AAA+4.414
Male+4.369
 UCHIJ+4.201
Neg logit contributions
emetery-2.664
ospel-2.590
vernment-2.508
ppa-2.422
appa-2.294
Token
Token ID198
Feature activation-9.36e-01

Pos logit contributions
 Frie+1.998
spir+1.969
Male+1.864
 AAA+1.823
 UCHIJ+1.764
Neg logit contributions
emetery-2.443
ospel-2.363
vernment-2.344
ppa-2.284
appa-2.204
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
ospel+0.696
emetery+0.693
ppa+0.680
vernment+0.672
appa+0.647
Neg logit contributions
 Frie-0.751
spir-0.711
querque-0.672
Male-0.672
 AAA-0.658
TokenThe
Token ID464
Feature activation-1.00e+00

Pos logit contributions
emetery+0.888
ospel+0.886
ppa+0.869
vernment+0.863
appa+0.828
Neg logit contributions
 Frie-0.823
spir-0.776
Male-0.724
querque-0.721
 AAA-0.720
Token dollars
Token ID5054
Feature activation+1.86e+00

Pos logit contributions
emetery+0.182
ospel+0.181
vernment+0.177
ppa+0.176
appa+0.168
Neg logit contributions
 Frie-0.195
spir-0.189
Male-0.178
 AAA-0.172
querque-0.171
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
 Frie+1.371
spir+1.306
Male+1.242
 AAA+1.225
 UCHIJ+1.179
Neg logit contributions
emetery-1.513
ospel-1.498
ppa-1.453
vernment-1.443
appa-1.393
Token
Token ID198
Feature activation+3.20e-02

Pos logit contributions
emetery+0.151
ospel+0.150
vernment+0.146
ppa+0.146
appa+0.139
Neg logit contributions
 Frie-0.153
spir-0.147
Male-0.139
 AAA-0.136
 UCHIJ-0.133
Token
Token ID198
Feature activation+2.41e-01

Pos logit contributions
 Frie+0.025
spir+0.024
Male+0.022
 AAA+0.022
 UCHIJ+0.021
Neg logit contributions
emetery-0.025
ospel-0.025
vernment-0.024
ppa-0.024
appa-0.023
TokenStory
Token ID11605
Feature activation+2.90e+00

Pos logit contributions
 Frie+0.176
spir+0.169
Male+0.159
 AAA+0.155
 UCHIJ+0.152
Neg logit contributions
emetery-0.197
ospel-0.195
vernment-0.191
ppa-0.190
appa-0.182
Token continues
Token ID4477
Feature activation+9.73e+00

Pos logit contributions
 Frie+1.830
spir+1.801
Male+1.647
 AAA+1.618
 UCHIJ+1.568
Neg logit contributions
emetery-2.631
ospel-2.605
vernment-2.551
ppa-2.488
 Kak-2.398
Token below
Token ID2174
Feature activation+4.57e+00

Pos logit contributions
spir+4.127
 Frie+4.069
 AAA+3.836
Male+3.797
 UCHIJ+3.459
Neg logit contributions
emetery-10.509
ospel-10.190
vernment-10.009
ppa-9.955
ailability-9.678
Token advertisement
Token ID15422
Feature activation+4.25e+00

Pos logit contributions
 Frie+4.559
spir+4.464
Male+4.304
 AAA+4.264
 UCHIJ+4.122
Neg logit contributions
emetery-2.435
ospel-2.409
vernment-2.269
ppa-2.249
jri-2.098
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
spir+2.798
 Frie+2.783
Male+2.652
 AAA+2.588
 UCHIJ+2.470
Neg logit contributions
emetery-3.788
ospel-3.625
vernment-3.613
ppa-3.490
ailability-3.424
Token
Token ID198
Feature activation-1.16e+00

Pos logit contributions
ospel+0.766
emetery+0.761
ppa+0.749
vernment+0.738
appa+0.711
Neg logit contributions
 Frie-0.842
spir-0.795
querque-0.758
Male-0.750
 AAA-0.736
TokenStory
Token ID11605
Feature activation+2.64e+00

Pos logit contributions
emetery+0.741
ospel+0.739
ppa+0.722
vernment+0.712
appa+0.678
Neg logit contributions
 Frie-1.054
spir-1.003
 AAA-0.947
querque-0.946
Male-0.945
Token stage
Token ID3800
Feature activation-3.65e-01

Pos logit contributions
emetery+0.821
ospel+0.815
ppa+0.802
vernment+0.800
appa+0.770
Neg logit contributions
 Frie-0.503
spir-0.482
Male-0.444
querque-0.425
 UCHIJ-0.423
Token.
Token ID13
Feature activation+6.54e-01

Pos logit contributions
emetery+0.279
ospel+0.276
vernment+0.270
ppa+0.270
appa+0.257
Neg logit contributions
 Frie-0.285
spir-0.274
Male-0.259
 AAA-0.253
querque-0.249
Token
Token ID198
Feature activation+2.78e+00

Pos logit contributions
 Frie+0.505
spir+0.486
Male+0.459
 AAA+0.449
 UCHIJ+0.440
Neg logit contributions
emetery-0.506
ospel-0.501
vernment-0.489
ppa-0.488
appa-0.466
Token
Token ID198
Feature activation+2.90e+00

Pos logit contributions
 Frie+1.953
spir+1.936
Male+1.829
 AAA+1.783
 UCHIJ+1.728
Neg logit contributions
emetery-2.352
ospel-2.276
vernment-2.264
ppa-2.203
appa-2.120
TokenStory
Token ID11605
Feature activation+3.80e+00

Pos logit contributions
 Frie+1.919
spir+1.876
Male+1.784
 AAA+1.697
 UCHIJ+1.652
Neg logit contributions
emetery-2.566
ospel-2.521
vernment-2.487
ppa-2.440
appa-2.352
Token continues
Token ID4477
Feature activation+9.39e+00

Pos logit contributions
 Frie+2.543
spir+2.467
Male+2.266
 AAA+2.241
 UCHIJ+2.148
Neg logit contributions
emetery-3.338
ospel-3.294
vernment-3.242
ppa-3.188
appa-3.056
Token below
Token ID2174
Feature activation+4.05e+00

Pos logit contributions
 Frie+4.210
spir+4.195
 AAA+3.910
Male+3.864
 UCHIJ+3.499
Neg logit contributions
emetery-9.953
ospel-9.669
vernment-9.644
ppa-9.404
ailability-9.130
Token advertisement
Token ID15422
Feature activation+4.04e+00

Pos logit contributions
 Frie+4.084
spir+3.979
Male+3.849
 AAA+3.824
 UCHIJ+3.703
Neg logit contributions
emetery-2.145
ospel-2.109
vernment-2.008
ppa-1.982
jri-1.839
Token
Token ID198
Feature activation-1.46e-01

Pos logit contributions
spir+2.692
 Frie+2.688
Male+2.553
 AAA+2.492
 UCHIJ+2.384
Neg logit contributions
emetery-3.559
ospel-3.420
vernment-3.408
ppa-3.298
jri-3.208
Token
Token ID198
Feature activation-2.02e-01

Pos logit contributions
emetery+0.111
ospel+0.110
ppa+0.108
vernment+0.107
appa+0.103
Neg logit contributions
 Frie-0.114
spir-0.109
Male-0.103
querque-0.101
 AAA-0.101
TokenHe
Token ID1544
Feature activation+6.59e-01

Pos logit contributions
emetery+0.170
ospel+0.169
ppa+0.166
vernment+0.165
appa+0.159
Neg logit contributions
 Frie-0.142
spir-0.134
Male-0.125
 AAA-0.124
querque-0.122
Token classes
Token ID6097
Feature activation+1.61e+00

Pos logit contributions
 Frie+1.123
spir+1.077
Male+1.024
 AAA+1.000
 UCHIJ+0.974
Neg logit contributions
emetery-1.206
ospel-1.188
vernment-1.159
ppa-1.155
appa-1.109
Token.
Token ID13
Feature activation+8.79e-01

Pos logit contributions
 Frie+1.202
spir+1.152
Male+1.091
 AAA+1.067
 UCHIJ+1.042
Neg logit contributions
emetery-1.300
ospel-1.286
vernment-1.253
ppa-1.249
appa-1.195
Token
Token ID198
Feature activation+5.99e-01

Pos logit contributions
 Frie+0.670
spir+0.644
Male+0.609
 AAA+0.596
 UCHIJ+0.583
Neg logit contributions
emetery-0.691
ospel-0.683
vernment-0.666
ppa-0.664
appa-0.636
Token
Token ID198
Feature activation+7.38e-01

Pos logit contributions
 Frie+0.454
spir+0.438
Male+0.414
 AAA+0.405
 UCHIJ+0.396
Neg logit contributions
emetery-0.473
ospel-0.467
vernment-0.457
ppa-0.454
appa-0.434
Token[
Token ID58
Feature activation+3.87e+00

Pos logit contributions
 Frie+0.533
spir+0.511
Male+0.482
 AAA+0.470
 UCHIJ+0.460
Neg logit contributions
emetery-0.608
ospel-0.602
vernment-0.589
ppa-0.587
appa-0.562
Tokennp
Token ID37659
Feature activation+9.19e+00

Pos logit contributions
 Frie+2.329
spir+2.239
Male+2.113
 AAA+2.012
 UCHIJ+1.950
Neg logit contributions
emetery-3.647
ospel-3.600
vernment-3.515
ppa-3.494
appa-3.366
Token-
Token ID12
Feature activation+3.56e+00

Pos logit contributions
 Frie+5.182
spir+5.121
Male+4.952
 AAA+4.694
querque+4.361
Neg logit contributions
emetery-8.573
ospel-8.452
ppa-8.217
vernment-8.215
appa-7.881
Tokenrelated
Token ID5363
Feature activation+5.88e+00

Pos logit contributions
 Frie+2.466
spir+2.399
Male+2.258
 AAA+2.175
 UCHIJ+2.116
Neg logit contributions
emetery-3.018
ospel-2.960
ppa-2.890
vernment-2.885
 Kak-2.763
Token]
Token ID60
Feature activation+2.82e+00

Pos logit contributions
 Frie+3.982
spir+3.881
Male+3.679
 AAA+3.558
 UCHIJ+3.448
Neg logit contributions
emetery-4.995
ospel-4.909
vernment-4.807
ppa-4.780
appa-4.536
Token<|endoftext|>
Token ID50256
Feature activation+7.39e-01

Pos logit contributions
 Frie+2.085
spir+2.018
Male+1.911
 AAA+1.866
 UCHIJ+1.825
Neg logit contributions
emetery-2.271
ospel-2.233
vernment-2.186
ppa-2.175
appa-2.083
TokenThe
Token ID464
Feature activation-1.40e+00

Pos logit contributions
 Frie+0.516
spir+0.493
Male+0.463
 AAA+0.452
 UCHIJ+0.442
Neg logit contributions
emetery-0.627
ospel-0.622
vernment-0.608
ppa-0.607
appa-0.582
Token statement
Token ID2643
Feature activation+5.89e-01

Pos logit contributions
 Frie+0.726
spir+0.689
Male+0.640
 AAA+0.623
 UCHIJ+0.606
Neg logit contributions
emetery-1.136
ospel-1.124
vernment-1.103
ppa-1.100
appa-1.058
Token.
Token ID13
Feature activation+6.70e-01

Pos logit contributions
 Frie+0.450
spir+0.431
Male+0.407
 AAA+0.400
 UCHIJ+0.391
Neg logit contributions
emetery-0.463
ospel-0.457
vernment-0.447
ppa-0.445
appa-0.423
Token
Token ID198
Feature activation+6.13e-01

Pos logit contributions
 Frie+0.540
spir+0.519
Male+0.493
 AAA+0.484
 UCHIJ+0.473
Neg logit contributions
emetery-0.501
ospel-0.493
vernment-0.482
ppa-0.479
appa-0.457
Token
Token ID198
Feature activation+4.51e-01

Pos logit contributions
 Frie+0.464
spir+0.448
Male+0.423
 AAA+0.413
 UCHIJ+0.405
Neg logit contributions
emetery-0.484
ospel-0.478
vernment-0.468
ppa-0.465
appa-0.445
TokenStory
Token ID11605
Feature activation+4.38e+00

Pos logit contributions
 Frie+0.343
spir+0.331
Male+0.314
 AAA+0.305
 UCHIJ+0.299
Neg logit contributions
emetery-0.354
ospel-0.350
vernment-0.342
ppa-0.341
appa-0.326
Token continues
Token ID4477
Feature activation+9.14e+00

Pos logit contributions
spir+2.632
 Frie+2.603
Male+2.376
 AAA+2.328
 UCHIJ+2.218
Neg logit contributions
emetery-4.099
ospel-4.002
vernment-3.963
ppa-3.851
appa-3.756
Token below
Token ID2174
Feature activation+5.47e+00

Pos logit contributions
spir+4.058
 Frie+3.799
 AAA+3.699
Male+3.673
 UCHIJ+3.438
Neg logit contributions
emetery-9.699
vernment-9.459
ospel-9.405
ppa-9.230
ailability-9.184
Token advertisement
Token ID15422
Feature activation+3.53e+00

Pos logit contributions
 Frie+5.175
spir+5.128
 AAA+5.046
Male+4.963
 UCHIJ+4.777
Neg logit contributions
emetery-3.140
ospel-3.033
vernment-2.931
ppa-2.830
appa-2.653
Token
Token ID198
Feature activation-9.03e-01

Pos logit contributions
spir+2.374
 Frie+2.370
Male+2.239
 AAA+2.192
 UCHIJ+2.106
Neg logit contributions
emetery-3.081
ospel-2.961
vernment-2.956
ppa-2.858
jri-2.769
Token
Token ID198
Feature activation-9.31e-01

Pos logit contributions
ospel+0.670
emetery+0.668
ppa+0.655
vernment+0.647
appa+0.623
Neg logit contributions
 Frie-0.725
spir-0.687
querque-0.649
Male-0.649
 AAA-0.636
TokenIt
Token ID1026
Feature activation-9.28e-01

Pos logit contributions
emetery+0.749
ospel+0.745
ppa+0.729
vernment+0.726
appa+0.696
Neg logit contributions
 Frie-0.692
spir-0.655
Male-0.612
 AAA-0.607
querque-0.604
TokenAP
Token ID2969
Feature activation+2.92e+00

Pos logit contributions
 Frie+0.668
spir+0.640
Male+0.600
 AAA+0.585
querque+0.573
Neg logit contributions
emetery-0.816
ospel-0.809
vernment-0.791
ppa-0.789
appa-0.757
Token)
Token ID8
Feature activation+2.08e+00

Pos logit contributions
 Frie+2.281
spir+2.208
Male+2.103
 AAA+2.053
querque+2.001
Neg logit contributions
emetery-2.191
ospel-2.166
vernment-2.148
ppa-2.137
appa-2.014
Token
Token ID198
Feature activation-1.20e+00

Pos logit contributions
 Frie+1.557
spir+1.505
Male+1.414
 AAA+1.389
 UCHIJ+1.351
Neg logit contributions
emetery-1.667
ospel-1.638
vernment-1.609
ppa-1.592
appa-1.525
Token
Token ID198
Feature activation-1.74e+00

Pos logit contributions
ospel+0.883
emetery+0.879
ppa+0.864
vernment+0.851
appa+0.822
Neg logit contributions
 Frie-0.964
spir-0.912
querque-0.865
Male-0.862
 AAA-0.844
TokenStory
Token ID11605
Feature activation+1.65e+00

Pos logit contributions
ospel+1.450
emetery+1.446
ppa+1.434
vernment+1.402
appa+1.362
Neg logit contributions
 Frie-1.230
spir-1.147
querque-1.078
 AAA-1.071
Male-1.064
Token continues
Token ID4477
Feature activation+8.99e+00

Pos logit contributions
 Frie+1.413
spir+1.372
Male+1.293
 AAA+1.280
 UCHIJ+1.244
Neg logit contributions
emetery-1.150
ospel-1.134
vernment-1.108
ppa-1.092
appa-1.036
Token
Token ID198
Feature activation+1.69e+00

Pos logit contributions
 Frie+4.299
spir+4.221
Male+3.879
 AAA+3.851
 Ely+3.476
Neg logit contributions
emetery-9.222
ospel-9.076
vernment-9.001
ppa-8.878
appa-8.475
Token
Token ID198
Feature activation+1.32e+00

Pos logit contributions
 Frie+1.223
spir+1.196
Male+1.133
 AAA+1.102
 UCHIJ+1.073
Neg logit contributions
emetery-1.388
ospel-1.354
vernment-1.338
ppa-1.313
appa-1.261
TokenThere
Token ID1858
Feature activation-1.90e+00

Pos logit contributions
 Frie+1.132
spir+1.098
Male+1.048
 AAA+1.019
 UCHIJ+1.001
Neg logit contributions
emetery-0.914
ospel-0.900
vernment-0.881
ppa-0.870
appa-0.828
Token were
Token ID547
Feature activation+6.58e-02

Pos logit contributions
emetery+1.503
ospel+1.491
ppa+1.460
vernment+1.460
appa+1.398
Neg logit contributions
 Frie-1.417
spir-1.362
Male-1.287
 AAA-1.259
 UCHIJ-1.241
Token a
Token ID257
Feature activation-3.07e-01

Pos logit contributions
 Frie+0.050
spir+0.048
Male+0.046
 AAA+0.045
 UCHIJ+0.044
Neg logit contributions
emetery-0.052
ospel-0.051
vernment-0.050
ppa-0.050
appa-0.047
Token relations
Token ID2316
Feature activation+1.77e+00

Pos logit contributions
emetery+0.658
ospel+0.652
vernment+0.636
ppa+0.634
appa+0.604
Neg logit contributions
 Frie-0.717
spir-0.691
Male-0.655
 AAA-0.640
 UCHIJ-0.629
Token with
Token ID351
Feature activation+2.71e-01

Pos logit contributions
 Frie+1.356
spir+1.307
Male+1.227
 AAA+1.205
 UCHIJ+1.170
Neg logit contributions
emetery-1.397
ospel-1.381
vernment-1.331
ppa-1.327
appa-1.272
Token Gaddafi
Token ID40320
Feature activation-1.69e+00

Pos logit contributions
 Frie+0.214
spir+0.205
Male+0.194
 AAA+0.191
 UCHIJ+0.187
Neg logit contributions
emetery-0.206
ospel-0.204
ppa-0.198
vernment-0.197
appa-0.189
Token had
Token ID550
Feature activation+1.21e+00

Pos logit contributions
emetery+1.180
ospel+1.167
vernment+1.144
ppa+1.136
appa+1.080
Neg logit contributions
 Frie-1.425
spir-1.374
Male-1.309
 AAA-1.282
 UCHIJ-1.263
Token s
Token ID264
Feature activation+2.63e+00

Pos logit contributions
 Frie+0.847
spir+0.815
Male+0.755
 AAA+0.747
 UCHIJ+0.719
Neg logit contributions
emetery-1.029
ospel-1.017
vernment-0.988
ppa-0.985
appa-0.942
Tokenoured
Token ID8167
Feature activation+8.77e+00

Pos logit contributions
 Frie+2.418
spir+2.379
Male+2.240
 AAA+2.205
 UCHIJ+2.156
Neg logit contributions
emetery-1.650
ospel-1.600
vernment-1.560
ppa-1.542
appa-1.445
Token.
Token ID13
Feature activation+2.91e+00

Pos logit contributions
 Frie+6.448
spir+6.163
Male+5.845
 AAA+5.775
 UCHIJ+5.431
Neg logit contributions
emetery-6.761
ospel-6.690
ppa-6.327
vernment-6.306
appa-6.163
Token The
Token ID383
Feature activation+1.10e-01

Pos logit contributions
 Frie+2.338
spir+2.236
Male+2.132
 AAA+2.117
 UCHIJ+2.046
Neg logit contributions
emetery-2.227
ospel-2.150
vernment-2.084
ppa-2.074
appa-2.001
Token Libyan
Token ID28661
Feature activation-1.29e+00

Pos logit contributions
 Frie+0.089
spir+0.085
Male+0.081
 AAA+0.080
 UCHIJ+0.078
Neg logit contributions
emetery-0.082
ospel-0.081
vernment-0.079
ppa-0.078
appa-0.075
Token leader
Token ID3554
Feature activation-6.93e-01

Pos logit contributions
emetery+0.928
ospel+0.923
vernment+0.908
ppa+0.898
appa+0.852
Neg logit contributions
 Frie-1.057
spir-1.018
Male-0.967
 AAA-0.940
 UCHIJ-0.931
Token demanded
Token ID12284
Feature activation+1.12e-01

Pos logit contributions
emetery+0.500
ospel+0.494
vernment+0.478
ppa+0.477
appa+0.454
Neg logit contributions
 Frie-0.575
spir-0.554
Male-0.526
 AAA-0.515
 UCHIJ-0.504
Token que
Token ID8358
Feature activation+4.84e-01

Pos logit contributions
emetery+0.252
ospel+0.249
vernment+0.245
ppa+0.244
appa+0.234
Neg logit contributions
 Frie-0.234
spir-0.224
Male-0.212
 AAA-0.205
 UCHIJ-0.203
Token tr
Token ID491
Feature activation+1.76e+00

Pos logit contributions
 Frie+0.345
spir+0.331
Male+0.311
 AAA+0.303
 UCHIJ+0.298
Neg logit contributions
emetery-0.404
ospel-0.399
vernment-0.392
ppa-0.391
appa-0.374
Tokeniste
Token ID40833
Feature activation+2.45e+00

Pos logit contributions
 Frie+1.221
spir+1.181
Male+1.111
 AAA+1.077
querque+1.048
Neg logit contributions
emetery-1.492
ospel-1.475
vernment-1.444
ppa-1.430
appa-1.375
Token.
Token ID13
Feature activation+3.36e-01

Pos logit contributions
 Frie+1.806
spir+1.733
Male+1.640
 AAA+1.605
 UCHIJ+1.559
Neg logit contributions
emetery-1.976
ospel-1.962
vernment-1.905
ppa-1.901
appa-1.819
TokenJ
Token ID41
Feature activation+1.06e+00

Pos logit contributions
 Frie+0.252
spir+0.242
Male+0.228
 AAA+0.223
querque+0.219
Neg logit contributions
emetery-0.268
ospel-0.265
vernment-0.259
ppa-0.258
appa-0.247
Token'
Token ID6
Feature activation+8.67e+00

Pos logit contributions
 Frie+0.780
spir+0.748
Male+0.706
 AAA+0.689
 UCHIJ+0.674
Neg logit contributions
emetery-0.864
ospel-0.855
vernment-0.836
ppa-0.834
appa-0.798
Tokenai
Token ID1872
Feature activation+2.32e+00

Pos logit contributions
spir+6.631
 Frie+6.543
Male+6.268
 AAA+6.004
querque+5.858
Neg logit contributions
emetery-6.150
ospel-5.896
ppa-5.685
vernment-5.678
 Kak-5.506
Token l
Token ID300
Feature activation+5.86e-01

Pos logit contributions
 Frie+1.701
spir+1.637
Male+1.545
 AAA+1.512
querque+1.468
Neg logit contributions
emetery-1.886
ospel-1.869
vernment-1.814
ppa-1.808
appa-1.732
Token'
Token ID6
Feature activation+5.41e+00

Pos logit contributions
 Frie+0.396
spir+0.380
Male+0.356
 AAA+0.346
 UCHIJ+0.338
Neg logit contributions
emetery-0.510
ospel-0.504
vernment-0.493
ppa-0.490
appa-0.472
Tokenhon
Token ID24130
Feature activation+2.49e+00

Pos logit contributions
 Frie+4.081
spir+4.040
Male+3.846
 AAA+3.699
querque+3.595
Neg logit contributions
emetery-4.028
ospel-4.003
ppa-3.872
vernment-3.828
 Kak-3.709
Tokenne
Token ID710
Feature activation+2.18e+00

Pos logit contributions
 Frie+1.584
spir+1.514
Male+1.415
 AAA+1.371
querque+1.338
Neg logit contributions
emetery-2.271
ospel-2.247
vernment-2.186
ppa-2.177
appa-2.100
Token<|endoftext|>
Token ID50256
Feature activation+9.20e-01

Pos logit contributions
emetery+0.535
ospel+0.531
ppa+0.519
vernment+0.518
appa+0.495
Neg logit contributions
 Frie-0.500
spir-0.480
Male-0.452
 AAA-0.441
querque-0.435
TokenBR
Token ID11473
Feature activation-1.48e+00

Pos logit contributions
 Frie+0.642
spir+0.615
Male+0.578
 AAA+0.563
 UCHIJ+0.551
Neg logit contributions
emetery-0.781
ospel-0.773
vernment-0.757
ppa-0.755
appa-0.724
TokenUSS
Token ID32835
Feature activation-1.07e+00

Pos logit contributions
emetery+1.127
ospel+1.115
ppa+1.086
vernment+1.084
appa+1.037
Neg logit contributions
 Frie-1.159
spir-1.113
Male-1.044
 AAA-1.026
querque-1.018
TokenELS
Token ID37142
Feature activation+2.32e+00

Pos logit contributions
emetery+0.849
ospel+0.840
vernment+0.822
ppa+0.816
 Kak+0.784
Neg logit contributions
 Frie-0.796
spir-0.765
Male-0.720
querque-0.704
 AAA-0.702
Token (
Token ID357
Feature activation+2.02e+00

Pos logit contributions
 Frie+1.876
spir+1.807
Male+1.719
 AAA+1.682
 UCHIJ+1.647
Neg logit contributions
emetery-1.719
ospel-1.697
vernment-1.653
ppa-1.645
appa-1.571
TokenReuters
Token ID12637
Feature activation+8.55e+00

Pos logit contributions
 Frie+1.489
spir+1.436
Male+1.359
 AAA+1.320
 UCHIJ+1.294
Neg logit contributions
emetery-1.632
ospel-1.610
vernment-1.572
ppa-1.564
appa-1.499
Token)
Token ID8
Feature activation+7.14e+00

Pos logit contributions
spir+6.123
 Frie+6.110
Male+5.902
 AAA+5.895
 UCHIJ+5.694
Neg logit contributions
emetery-6.815
vernment-6.664
ospel-6.591
ppa-6.173
jri-6.152
Token -
Token ID532
Feature activation+3.36e+00

Pos logit contributions
 Frie+4.044
spir+3.998
Male+3.750
 AAA+3.690
 UCHIJ+3.576
Neg logit contributions
emetery-7.042
ospel-6.743
vernment-6.741
ppa-6.533
jri-6.380
Token The
Token ID383
Feature activation+2.92e-01

Pos logit contributions
 Frie+2.581
spir+2.464
Male+2.331
 AAA+2.313
 UCHIJ+2.229
Neg logit contributions
emetery-2.669
ospel-2.606
vernment-2.542
ppa-2.520
appa-2.432
Token world
Token ID995
Feature activation+2.59e+00

Pos logit contributions
 Frie+0.213
spir+0.205
Male+0.193
 AAA+0.188
 UCHIJ+0.184
Neg logit contributions
emetery-0.239
ospel-0.236
vernment-0.231
ppa-0.231
appa-0.221
Token
Token ID447
Feature activation+1.31e+00

Pos logit contributions
 Frie+1.935
spir+1.859
Male+1.753
 AAA+1.723
 UCHIJ+1.670
Neg logit contributions
emetery-2.074
ospel-2.047
vernment-1.991
ppa-1.979
appa-1.905
Tokenents
Token ID658
Feature activation+2.00e-01

Pos logit contributions
 Frie+1.246
spir+1.213
Male+1.140
 AAA+1.106
 UCHIJ+1.085
Neg logit contributions
emetery-1.307
ospel-1.292
vernment-1.261
ppa-1.254
appa-1.196
Token ind
Token ID773
Feature activation+3.56e-01

Pos logit contributions
 Frie+0.149
spir+0.142
Male+0.134
 AAA+0.131
 UCHIJ+0.129
Neg logit contributions
emetery-0.161
ospel-0.159
vernment-0.156
ppa-0.155
appa-0.148
Tokeniqu
Token ID1557
Feature activation-1.60e+00

Pos logit contributions
 Frie+0.267
spir+0.256
Male+0.241
 AAA+0.236
querque+0.231
Neg logit contributions
emetery-0.285
ospel-0.281
vernment-0.275
ppa-0.274
appa-0.262
Tokenent
Token ID298
Feature activation-5.68e-02

Pos logit contributions
emetery+1.223
ospel+1.210
vernment+1.195
ppa+1.183
appa+1.136
Neg logit contributions
 Frie-1.245
spir-1.190
Male-1.136
 AAA-1.098
 UCHIJ-1.089
Token qu
Token ID627
Feature activation+2.26e+00

Pos logit contributions
emetery+0.044
ospel+0.044
vernment+0.043
ppa+0.043
appa+0.041
Neg logit contributions
 Frie-0.043
spir-0.042
Male-0.039
 AAA-0.038
 UCHIJ-0.038
Token'
Token ID6
Feature activation+8.55e+00

Pos logit contributions
 Frie+1.640
spir+1.587
Male+1.490
 AAA+1.457
querque+1.421
Neg logit contributions
emetery-1.838
ospel-1.821
ppa-1.769
vernment-1.768
appa-1.696
Tokenils
Token ID4487
Feature activation+2.63e+00

Pos logit contributions
spir+4.900
 Frie+4.763
Male+4.516
 AAA+4.158
querque+4.113
Neg logit contributions
emetery-7.761
ospel-7.617
ppa-7.337
vernment-7.242
 Kak-7.183
Token ont
Token ID39585
Feature activation+3.92e+00

Pos logit contributions
 Frie+1.970
spir+1.898
Male+1.792
 AAA+1.761
 UCHIJ+1.709
Neg logit contributions
emetery-2.089
ospel-2.065
vernment-2.006
ppa-1.997
appa-1.913
Token mont
Token ID40689
Feature activation-1.25e-01

Pos logit contributions
 Frie+2.899
spir+2.789
Male+2.626
 AAA+2.609
 UCHIJ+2.502
Neg logit contributions
emetery-3.159
ospel-3.118
vernment-3.009
ppa-2.997
appa-2.871
Tokené
Token ID2634
Feature activation+1.97e+00

Pos logit contributions
emetery+0.096
ospel+0.095
vernment+0.092
ppa+0.092
appa+0.088
Neg logit contributions
 Frie-0.098
spir-0.094
Male-0.089
 AAA-0.087
 UCHIJ-0.085
Token une
Token ID17809
Feature activation+1.13e+00

Pos logit contributions
 Frie+1.479
spir+1.421
Male+1.342
 AAA+1.317
querque+1.281
Neg logit contributions
emetery-1.560
ospel-1.548
vernment-1.507
ppa-1.501
appa-1.436
Tokenant
Token ID415
Feature activation+1.06e+00

Pos logit contributions
 Frie+2.113
spir+2.053
Male+1.916
 AAA+1.872
querque+1.833
Neg logit contributions
emetery-2.363
ospel-2.322
vernment-2.278
ppa-2.265
 Kak-2.168
Token neut
Token ID22190
Feature activation+5.48e+00

Pos logit contributions
 Frie+0.804
spir+0.773
Male+0.730
 AAA+0.714
 UCHIJ+0.698
Neg logit contributions
emetery-0.843
ospel-0.835
vernment-0.815
ppa-0.812
appa-0.777
Tokenre
Token ID260
Feature activation+5.31e-01

Pos logit contributions
 Frie+3.718
spir+3.564
Male+3.341
 AAA+3.307
querque+3.213
Neg logit contributions
emetery-4.673
ospel-4.610
ppa-4.491
vernment-4.474
 Kak-4.266
Token.
Token ID13
Feature activation-4.51e-01

Pos logit contributions
 Frie+0.402
spir+0.386
Male+0.365
 AAA+0.356
 UCHIJ+0.350
Neg logit contributions
emetery-0.418
ospel-0.413
vernment-0.406
ppa-0.404
appa-0.386
Token J
Token ID449
Feature activation-7.27e-01

Pos logit contributions
emetery+0.364
ospel+0.361
ppa+0.353
vernment+0.353
appa+0.338
Neg logit contributions
 Frie-0.332
spir-0.318
Male-0.298
 AAA-0.292
querque-0.289
Token'
Token ID6
Feature activation+8.44e+00

Pos logit contributions
emetery+0.577
ospel+0.572
ppa+0.557
vernment+0.556
appa+0.533
Neg logit contributions
 Frie-0.551
spir-0.527
Male-0.496
 AAA-0.487
querque-0.479
Tokenesp
Token ID9774
Feature activation+3.09e+00

Pos logit contributions
spir+5.899
 Frie+5.829
Male+5.563
 AAA+5.293
querque+5.107
Neg logit contributions
emetery-6.588
ospel-6.345
vernment-6.142
ppa-6.098
 Kak-5.921
Tokenère
Token ID35979
Feature activation+9.64e-01

Pos logit contributions
 Frie+1.750
spir+1.698
Male+1.554
 AAA+1.490
querque+1.463
Neg logit contributions
emetery-2.977
ospel-2.928
vernment-2.883
ppa-2.862
 Kak-2.788
Token que
Token ID8358
Feature activation+8.56e-01

Pos logit contributions
 Frie+0.715
spir+0.686
Male+0.648
 AAA+0.632
 UCHIJ+0.619
Neg logit contributions
emetery-0.776
ospel-0.769
vernment-0.751
ppa-0.749
appa-0.716
Token v
Token ID410
Feature activation+1.20e+00

Pos logit contributions
 Frie+0.607
spir+0.581
Male+0.547
 AAA+0.533
 UCHIJ+0.522
Neg logit contributions
emetery-0.718
ospel-0.711
vernment-0.696
ppa-0.694
appa-0.665
Tokenous
Token ID516
Feature activation+3.17e+00

Pos logit contributions
 Frie+0.908
spir+0.878
Male+0.833
 AAA+0.807
 UCHIJ+0.791
Neg logit contributions
emetery-0.938
ospel-0.928
vernment-0.909
ppa-0.901
appa-0.860
Token club
Token ID3430
Feature activation-3.47e-01

Pos logit contributions
emetery+0.047
ospel+0.046
vernment+0.045
ppa+0.045
appa+0.043
Neg logit contributions
 Frie-0.045
spir-0.043
Male-0.041
 AAA-0.040
 UCHIJ-0.039
Token.
Token ID13
Feature activation+8.25e-01

Pos logit contributions
emetery+0.265
ospel+0.262
vernment+0.256
ppa+0.256
appa+0.244
Neg logit contributions
 Frie-0.271
spir-0.261
Male-0.247
 AAA-0.240
querque-0.237
Token
Token ID198
Feature activation+2.05e+00

Pos logit contributions
 Frie+0.636
spir+0.611
Male+0.578
 AAA+0.566
 UCHIJ+0.554
Neg logit contributions
emetery-0.643
ospel-0.635
vernment-0.621
ppa-0.617
appa-0.590
Token
Token ID198
Feature activation+1.79e+00

Pos logit contributions
 Frie+1.470
spir+1.445
Male+1.365
 AAA+1.332
 UCHIJ+1.293
Neg logit contributions
emetery-1.712
ospel-1.665
vernment-1.649
ppa-1.614
appa-1.551
TokenStory
Token ID11605
Feature activation+4.22e+00

Pos logit contributions
 Frie+1.243
spir+1.212
Male+1.149
 AAA+1.100
 UCHIJ+1.078
Neg logit contributions
emetery-1.515
ospel-1.490
vernment-1.465
ppa-1.446
appa-1.391
Token continues
Token ID4477
Feature activation+8.38e+00

Pos logit contributions
spir+2.559
 Frie+2.486
Male+2.281
 AAA+2.251
 UCHIJ+2.135
Neg logit contributions
emetery-3.951
ospel-3.853
vernment-3.819
ppa-3.708
appa-3.628
Token below
Token ID2174
Feature activation+4.56e+00

Pos logit contributions
spir+3.932
 Frie+3.690
 AAA+3.543
Male+3.533
 UCHIJ+3.351
Neg logit contributions
emetery-8.739
vernment-8.576
ospel-8.482
ppa-8.327
ailability-8.232
Token advertisement
Token ID15422
Feature activation+3.62e+00

Pos logit contributions
 Frie+4.448
spir+4.401
 AAA+4.287
Male+4.239
 UCHIJ+4.100
Neg logit contributions
emetery-2.508
ospel-2.431
vernment-2.360
ppa-2.276
appa-2.133
Token
Token ID198
Feature activation-8.07e-01

Pos logit contributions
 Frie+2.433
spir+2.431
Male+2.294
 AAA+2.250
 UCHIJ+2.158
Neg logit contributions
emetery-3.165
ospel-3.043
vernment-3.038
ppa-2.935
jri-2.848
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
ospel+0.601
emetery+0.599
ppa+0.587
vernment+0.580
appa+0.558
Neg logit contributions
 Frie-0.647
spir-0.613
Male-0.579
querque-0.578
 AAA-0.567
TokenHe
Token ID1544
Feature activation-1.07e+00

Pos logit contributions
emetery+0.979
ospel+0.977
ppa+0.958
vernment+0.950
appa+0.916
Neg logit contributions
 Frie-0.835
spir-0.784
Male-0.730
 AAA-0.727
querque-0.726
Token
Token ID198
Feature activation-1.66e-01

Pos logit contributions
 Frie+0.205
spir+0.197
Male+0.186
 AAA+0.182
 UCHIJ+0.178
Neg logit contributions
emetery-0.208
ospel-0.206
vernment-0.201
ppa-0.201
appa-0.192
TokenK
Token ID42
Feature activation+8.21e-01

Pos logit contributions
emetery+0.128
ospel+0.126
vernment+0.123
ppa+0.123
appa+0.117
Neg logit contributions
 Frie-0.129
spir-0.124
Male-0.118
 AAA-0.115
 UCHIJ-0.113
Tokenhal
Token ID14201
Feature activation+2.19e+00

Pos logit contributions
 Frie+0.542
spir+0.520
Male+0.488
 AAA+0.473
 UCHIJ+0.463
Neg logit contributions
emetery-0.723
ospel-0.716
vernment-0.705
ppa-0.702
appa-0.671
Tokenisha
Token ID19388
Feature activation+1.01e+00

Pos logit contributions
 Frie+1.534
spir+1.491
Male+1.402
 AAA+1.369
 UCHIJ+1.337
Neg logit contributions
emetery-1.845
ospel-1.811
vernment-1.784
ppa-1.742
 Kak-1.668
Token told
Token ID1297
Feature activation-1.20e+00

Pos logit contributions
 Frie+0.808
spir+0.774
Male+0.734
 AAA+0.719
 UCHIJ+0.705
Neg logit contributions
emetery-0.769
ospel-0.760
vernment-0.738
ppa-0.732
appa-0.699
Token NBC
Token ID9716
Feature activation+8.33e+00

Pos logit contributions
emetery+0.924
ospel+0.914
vernment+0.894
ppa+0.892
appa+0.856
Neg logit contributions
 Frie-0.919
spir-0.893
Male-0.843
 AAA-0.812
querque-0.811
Token news
Token ID1705
Feature activation+3.53e+00

Pos logit contributions
 Frie+5.989
spir+5.730
Male+5.520
 AAA+5.362
 UCHIJ+5.124
Neg logit contributions
emetery-6.557
ospel-6.478
vernment-6.431
ppa-6.289
appa-5.938
Token that
Token ID326
Feature activation+5.96e-01

Pos logit contributions
 Frie+2.677
spir+2.588
Male+2.449
 AAA+2.407
querque+2.333
Neg logit contributions
emetery-2.739
ospel-2.706
vernment-2.663
ppa-2.647
appa-2.507
Token her
Token ID607
Feature activation+1.67e+00

Pos logit contributions
 Frie+0.479
spir+0.460
Male+0.436
 AAA+0.429
 UCHIJ+0.418
Neg logit contributions
emetery-0.445
ospel-0.440
vernment-0.431
ppa-0.428
appa-0.407
Token brother
Token ID3956
Feature activation-5.88e-01

Pos logit contributions
 Frie+1.364
spir+1.313
Male+1.245
 AAA+1.231
 UCHIJ+1.195
Neg logit contributions
emetery-1.220
ospel-1.200
vernment-1.184
ppa-1.161
appa-1.111
Token survived
Token ID11803
Feature activation+7.03e-01

Pos logit contributions
emetery+0.453
ospel+0.448
vernment+0.438
ppa+0.436
appa+0.416
Neg logit contributions
 Frie-0.456
spir-0.438
Male-0.415
 AAA-0.406
 UCHIJ-0.398
Token<|endoftext|>
Token ID50256
Feature activation+9.57e-01

Pos logit contributions
 Frie+0.115
spir+0.111
Male+0.105
 AAA+0.102
querque+0.101
Neg logit contributions
emetery-0.117
ospel-0.116
ppa-0.113
vernment-0.113
appa-0.108
TokenHA
Token ID7801
Feature activation-1.40e+00

Pos logit contributions
 Frie+0.667
spir+0.639
Male+0.600
 AAA+0.585
 UCHIJ+0.572
Neg logit contributions
emetery-0.813
ospel-0.805
vernment-0.788
ppa-0.786
appa-0.754
TokenV
Token ID53
Feature activation-4.21e-01

Pos logit contributions
emetery+1.268
ospel+1.260
ppa+1.245
vernment+1.237
appa+1.189
Neg logit contributions
 Frie-0.891
spir-0.847
Male-0.777
 AAA-0.758
querque-0.754
TokenANA
Token ID31574
Feature activation+2.19e+00

Pos logit contributions
emetery+0.386
ospel+0.382
vernment+0.374
ppa+0.374
appa+0.362
Neg logit contributions
 Frie-0.266
spir-0.252
Male-0.235
 AAA-0.228
querque-0.224
Token (
Token ID357
Feature activation+8.42e-01

Pos logit contributions
 Frie+1.785
spir+1.723
Male+1.637
 AAA+1.606
 UCHIJ+1.572
Neg logit contributions
emetery-1.600
ospel-1.581
vernment-1.540
ppa-1.531
appa-1.463
TokenReuters
Token ID12637
Feature activation+8.27e+00

Pos logit contributions
 Frie+0.636
spir+0.610
Male+0.576
 AAA+0.563
querque+0.552
Neg logit contributions
emetery-0.667
ospel-0.661
vernment-0.646
ppa-0.644
appa-0.616
Token)
Token ID8
Feature activation+7.14e+00

Pos logit contributions
 Frie+5.993
spir+5.988
Male+5.782
 AAA+5.751
 UCHIJ+5.560
Neg logit contributions
emetery-6.528
vernment-6.384
ospel-6.333
ppa-5.940
jri-5.893
Token -
Token ID532
Feature activation+3.13e+00

Pos logit contributions
 Frie+4.053
spir+4.018
Male+3.763
 AAA+3.698
 UCHIJ+3.585
Neg logit contributions
emetery-7.003
ospel-6.725
vernment-6.711
ppa-6.518
jri-6.349
Token Latin
Token ID9133
Feature activation-1.45e+00

Pos logit contributions
 Frie+2.576
spir+2.476
Male+2.354
 AAA+2.328
 UCHIJ+2.256
Neg logit contributions
emetery-2.282
ospel-2.245
vernment-2.190
ppa-2.172
appa-2.081
Token American
Token ID1605
Feature activation+3.39e+00

Pos logit contributions
emetery+0.790
ospel+0.778
ppa+0.755
vernment+0.751
appa+0.701
Neg logit contributions
 Frie-1.454
spir-1.406
Male-1.348
 AAA-1.321
 UCHIJ-1.309
Token and
Token ID290
Feature activation+5.47e-01

Pos logit contributions
 Frie+2.567
spir+2.462
Male+2.326
 AAA+2.315
 UCHIJ+2.223
Neg logit contributions
emetery-2.674
ospel-2.642
vernment-2.569
ppa-2.550
appa-2.468
Token
Token ID251
Feature activation+1.32e+00

Pos logit contributions
 Frie+0.841
spir+0.797
Male+0.744
 AAA+0.722
 UCHIJ+0.703
Neg logit contributions
emetery-1.306
ospel-1.293
vernment-1.269
ppa-1.263
appa-1.214
Token
Token ID198
Feature activation-1.50e-01

Pos logit contributions
 Frie+0.993
spir+0.954
Male+0.901
 AAA+0.889
 UCHIJ+0.864
Neg logit contributions
emetery-1.057
ospel-1.034
vernment-1.016
ppa-1.007
appa-0.970
Token
Token ID198
Feature activation-3.91e-01

Pos logit contributions
emetery+0.115
ospel+0.114
ppa+0.112
vernment+0.111
appa+0.106
Neg logit contributions
 Frie-0.117
spir-0.112
Male-0.106
 AAA-0.104
querque-0.103
Token[
Token ID58
Feature activation+3.37e+00

Pos logit contributions
emetery+0.298
ospel+0.295
vernment+0.288
ppa+0.287
appa+0.274
Neg logit contributions
 Frie-0.306
spir-0.295
Male-0.279
 AAA-0.273
 UCHIJ-0.268
TokenH
Token ID39
Feature activation+1.00e+00

Pos logit contributions
 Frie+2.249
spir+2.164
Male+2.047
 AAA+1.974
 UCHIJ+1.921
Neg logit contributions
emetery-2.954
ospel-2.914
vernment-2.854
ppa-2.830
appa-2.713
Token/
Token ID14
Feature activation+8.26e+00

Pos logit contributions
 Frie+0.708
spir+0.684
Male+0.645
 AAA+0.625
 UCHIJ+0.610
Neg logit contributions
emetery-0.838
ospel-0.827
vernment-0.810
ppa-0.807
appa-0.772
Tokent
Token ID83
Feature activation+4.02e+00

Pos logit contributions
spir+4.183
 Frie+4.116
Male+4.058
 AAA+3.758
 UCHIJ+3.574
Neg logit contributions
emetery-8.296
ospel-8.073
vernment-8.054
ppa-7.694
appa-7.465
Token The
Token ID383
Feature activation+2.78e+00

Pos logit contributions
 Frie+3.215
spir+3.054
 AAA+2.900
Male+2.897
 UCHIJ+2.788
Neg logit contributions
emetery-3.031
ospel-2.985
vernment-2.897
ppa-2.890
appa-2.744
Token Hill
Token ID3327
Feature activation+2.44e+00

Pos logit contributions
 Frie+2.124
spir+2.039
Male+1.929
 AAA+1.907
 UCHIJ+1.841
Neg logit contributions
emetery-2.188
ospel-2.145
vernment-2.113
ppa-2.096
appa-1.997
Token]
Token ID60
Feature activation+1.76e+00

Pos logit contributions
 Frie+1.788
spir+1.725
Male+1.626
 AAA+1.588
 UCHIJ+1.544
Neg logit contributions
emetery-1.975
ospel-1.950
vernment-1.911
ppa-1.891
appa-1.810
Token<|endoftext|>
Token ID50256
Feature activation+8.03e-01

Pos logit contributions
 Frie+1.211
spir+1.163
Male+1.095
 AAA+1.066
 UCHIJ+1.040
Neg logit contributions
emetery-1.504
ospel-1.488
vernment-1.456
ppa-1.451
appa-1.391
Token support
Token ID1104
Feature activation+6.94e-01

Pos logit contributions
emetery+1.035
ospel+1.026
vernment+1.002
ppa+0.994
appa+0.952
Neg logit contributions
 Frie-1.267
spir-1.222
Male-1.158
 AAA-1.130
querque-1.122
Token from
Token ID422
Feature activation+1.93e+00

Pos logit contributions
 Frie+0.492
spir+0.472
Male+0.444
 AAA+0.433
 UCHIJ+0.424
Neg logit contributions
emetery-0.580
ospel-0.575
vernment-0.562
ppa-0.561
appa-0.538
Token former
Token ID1966
Feature activation-1.75e+00

Pos logit contributions
 Frie+1.576
spir+1.514
Male+1.443
 AAA+1.417
 UCHIJ+1.387
Neg logit contributions
emetery-1.416
ospel-1.397
vernment-1.357
ppa-1.355
appa-1.283
Token Ku
Token ID12554
Feature activation-1.24e+00

Pos logit contributions
ospel+1.183
emetery+1.182
ppa+1.154
vernment+1.145
appa+1.109
Neg logit contributions
 Frie-1.494
spir-1.447
Male-1.367
 AAA-1.327
querque-1.323
Token Klux
Token ID45092
Feature activation-6.35e+00

Pos logit contributions
emetery+0.597
ospel+0.585
vernment+0.571
ppa+0.570
appa+0.530
Neg logit contributions
 Frie-1.332
spir-1.283
Male-1.233
 AAA-1.214
 UCHIJ-1.198
Token Klan
Token ID31151
Feature activation-8.31e+00

Pos logit contributions
ospel+1.507
emetery+1.407
vernment+1.346
ppa+1.324
appa+1.277
Neg logit contributions
 Frie-8.167
spir-7.960
Male-7.666
querque-7.649
 UCHIJ-7.599
Token leader
Token ID3554
Feature activation-3.10e+00

Pos logit contributions
emetery+4.615
ospel+4.525
ppa+4.457
vernment+4.388
 Kak+4.337
Neg logit contributions
 Frie-7.827
spir-7.605
Male-7.208
 UCHIJ-7.084
querque-6.915
Token David
Token ID3271
Feature activation-2.27e+00

Pos logit contributions
emetery+1.922
ospel+1.901
vernment+1.842
ppa+1.838
appa+1.737
Neg logit contributions
 Frie-2.864
spir-2.777
Male-2.651
 AAA-2.586
querque-2.562
Token Duke
Token ID11083
Feature activation-2.02e+00

Pos logit contributions
emetery+1.284
ospel+1.270
vernment+1.224
ppa+1.212
appa+1.146
Neg logit contributions
 Frie-2.209
spir-2.143
Male-2.064
 AAA-2.008
querque-1.998
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
emetery+1.526
ospel+1.504
vernment+1.482
ppa+1.474
appa+1.409
Neg logit contributions
 Frie-1.593
spir-1.538
Male-1.453
 AAA-1.422
 UCHIJ-1.399
Token (
Token ID357
Feature activation+1.77e+00

Pos logit contributions
 Frie+0.095
spir+0.092
Male+0.087
 AAA+0.085
querque+0.084
Neg logit contributions
emetery-0.087
ospel-0.086
vernment-0.084
ppa-0.084
appa-0.080
Token lives
Token ID3160
Feature activation-1.62e-01

Pos logit contributions
emetery+0.368
ospel+0.364
vernment+0.356
ppa+0.355
appa+0.339
Neg logit contributions
 Frie-0.346
spir-0.332
Male-0.314
 AAA-0.307
 UCHIJ-0.300
Token,
Token ID11
Feature activation+4.29e-01

Pos logit contributions
emetery+0.127
ospel+0.126
vernment+0.123
ppa+0.123
appa+0.117
Neg logit contributions
 Frie-0.123
spir-0.118
Male-0.112
 AAA-0.109
 UCHIJ-0.107
Token or
Token ID393
Feature activation+1.24e+00

Pos logit contributions
 Frie+0.331
spir+0.317
Male+0.301
 AAA+0.294
 UCHIJ+0.288
Neg logit contributions
emetery-0.333
ospel-0.330
vernment-0.322
ppa-0.321
appa-0.306
Token am
Token ID716
Feature activation+2.76e+00

Pos logit contributions
 Frie+0.923
spir+0.883
Male+0.837
 AAA+0.818
 UCHIJ+0.797
Neg logit contributions
emetery-0.996
ospel-0.985
vernment-0.960
ppa-0.958
appa-0.915
Token I
Token ID314
Feature activation-3.22e+00

Pos logit contributions
 Frie+2.237
spir+2.183
Male+2.068
 AAA+2.003
 UCHIJ+1.966
Neg logit contributions
emetery-1.993
ospel-1.978
vernment-1.959
ppa-1.945
appa-1.816
Token fool
Token ID9192
Feature activation-8.10e+00

Pos logit contributions
emetery+2.370
ospel+2.332
vernment+2.302
ppa+2.298
 Kak+2.214
Neg logit contributions
 Frie-2.543
spir-2.431
Male-2.290
 AAA-2.258
 UCHIJ-2.247
Tokening
Token ID278
Feature activation-4.04e+00

Pos logit contributions
ospel+4.629
vernment+4.612
emetery+4.602
ppa+4.470
appa+4.305
Neg logit contributions
 Frie-7.270
spir-7.022
Male-6.878
querque-6.731
 UCHIJ-6.711
Token myself
Token ID3589
Feature activation-7.43e+00

Pos logit contributions
emetery+2.676
ospel+2.640
vernment+2.620
ppa+2.582
 Kak+2.445
Neg logit contributions
 Frie-3.516
spir-3.383
Male-3.230
querque-3.158
 AAA-3.120
Token?
Token ID30
Feature activation-3.96e-01

Pos logit contributions
emetery+5.221
ppa+5.117
vernment+5.103
ospel+5.074
 Kak+4.888
Neg logit contributions
 Frie-5.884
spir-5.719
Male-5.330
querque-5.304
 UCHIJ-5.259
Token
Token ID198
Feature activation+6.75e-01

Pos logit contributions
emetery+0.302
ospel+0.299
ppa+0.293
vernment+0.292
appa+0.279
Neg logit contributions
 Frie-0.309
spir-0.297
Male-0.281
 AAA-0.274
querque-0.271
Token
Token ID198
Feature activation-4.31e-01

Pos logit contributions
 Frie+0.515
spir+0.495
Male+0.468
 AAA+0.458
 UCHIJ+0.448
Neg logit contributions
emetery-0.529
ospel-0.523
vernment-0.512
ppa-0.509
appa-0.487
Token reliable
Token ID9314
Feature activation-2.33e+00

Pos logit contributions
 Frie+0.100
spir+0.096
Male+0.091
 AAA+0.088
querque+0.087
Neg logit contributions
emetery-0.097
ospel-0.095
vernment-0.094
ppa-0.093
appa-0.089
Token in
Token ID287
Feature activation+4.56e-02

Pos logit contributions
emetery+1.618
ospel+1.600
ppa+1.596
vernment+1.584
 Kak+1.513
Neg logit contributions
 Frie-1.950
spir-1.869
Male-1.795
querque-1.730
 UCHIJ-1.709
Token the
Token ID262
Feature activation+3.15e-01

Pos logit contributions
 Frie+0.037
spir+0.035
Male+0.033
 AAA+0.033
 UCHIJ+0.032
Neg logit contributions
emetery-0.034
ospel-0.033
vernment-0.033
ppa-0.033
appa-0.031
Token fight
Token ID1907
Feature activation+1.72e+00

Pos logit contributions
 Frie+0.247
spir+0.238
Male+0.226
 AAA+0.220
 UCHIJ+0.217
Neg logit contributions
emetery-0.240
ospel-0.237
vernment-0.232
ppa-0.231
appa-0.220
Token against
Token ID1028
Feature activation+7.32e-01

Pos logit contributions
 Frie+1.058
spir+1.003
Male+0.934
 AAA+0.911
querque+0.879
Neg logit contributions
emetery-1.613
ospel-1.593
vernment-1.555
ppa-1.555
appa-1.497
Token IS
Token ID3180
Feature activation-8.03e+00

Pos logit contributions
 Frie+0.603
spir+0.580
Male+0.550
 AAA+0.543
 UCHIJ+0.527
Neg logit contributions
emetery-0.533
ospel-0.525
ppa-0.511
vernment-0.508
appa-0.486
Token in
Token ID287
Feature activation-1.28e+00

Pos logit contributions
emetery+4.957
vernment+4.884
ospel+4.868
ppa+4.865
 Kak+4.675
Neg logit contributions
 Frie-7.036
spir-6.779
Male-6.398
 UCHIJ-6.323
querque-6.290
Token the
Token ID262
Feature activation+1.07e-01

Pos logit contributions
emetery+0.927
ospel+0.920
vernment+0.903
ppa+0.901
 Kak+0.856
Neg logit contributions
 Frie-1.043
spir-1.010
Male-0.961
 AAA-0.927
 UCHIJ-0.925
Token north
Token ID5093
Feature activation+1.45e+00

Pos logit contributions
 Frie+0.073
spir+0.070
Male+0.066
 AAA+0.064
querque+0.063
Neg logit contributions
emetery-0.092
ospel-0.092
vernment-0.090
ppa-0.090
appa-0.086
Token of
Token ID286
Feature activation-9.14e-02

Pos logit contributions
 Frie+1.148
spir+1.100
Male+1.046
 AAA+1.027
querque+0.996
Neg logit contributions
emetery-1.090
ospel-1.078
vernment-1.047
ppa-1.041
appa-0.996
Token the
Token ID262
Feature activation-1.38e-01

Pos logit contributions
emetery+0.062
ospel+0.062
vernment+0.060
ppa+0.060
appa+0.057
Neg logit contributions
 Frie-0.079
spir-0.076
Male-0.073
 AAA-0.071
 UCHIJ-0.070
Token partners
Token ID4887
Feature activation-3.20e+00

Pos logit contributions
 Frie+0.357
spir+0.343
Male+0.325
 AAA+0.319
 UCHIJ+0.312
Neg logit contributions
emetery-0.340
ospel-0.337
vernment-0.328
ppa-0.326
appa-0.311
Token in
Token ID287
Feature activation-9.57e-01

Pos logit contributions
emetery+2.400
ospel+2.379
vernment+2.359
ppa+2.354
 Kak+2.262
Neg logit contributions
 Frie-2.460
spir-2.388
Male-2.242
querque-2.172
 AAA-2.156
Token the
Token ID262
Feature activation-3.51e-01

Pos logit contributions
emetery+0.696
ospel+0.690
vernment+0.679
ppa+0.676
appa+0.641
Neg logit contributions
 Frie-0.776
spir-0.752
Male-0.713
 AAA-0.685
querque-0.682
Token fight
Token ID1907
Feature activation+1.62e+00

Pos logit contributions
emetery+0.254
ospel+0.253
vernment+0.248
ppa+0.247
appa+0.234
Neg logit contributions
 Frie-0.286
spir-0.277
Male-0.263
 AAA-0.254
 UCHIJ-0.252
Token against
Token ID1028
Feature activation+5.66e-01

Pos logit contributions
 Frie+0.998
spir+0.946
Male+0.881
 AAA+0.860
querque+0.832
Neg logit contributions
emetery-1.513
ospel-1.491
ppa-1.457
vernment-1.456
appa-1.402
Token IS
Token ID3180
Feature activation-7.90e+00

Pos logit contributions
 Frie+0.504
spir+0.485
Male+0.463
 AAA+0.459
 UCHIJ+0.446
Neg logit contributions
emetery-0.375
ospel-0.367
ppa-0.357
vernment-0.354
appa-0.336
Token -
Token ID532
Feature activation-1.77e+00

Pos logit contributions
emetery+5.337
ospel+5.312
ppa+5.217
vernment+5.214
 Kak+5.055
Neg logit contributions
 Frie-6.407
spir-6.143
Male-5.743
 UCHIJ-5.677
querque-5.651
Token and
Token ID290
Feature activation-9.36e-01

Pos logit contributions
emetery+1.248
ospel+1.231
vernment+1.215
ppa+1.205
appa+1.149
Neg logit contributions
 Frie-1.483
spir-1.435
Male-1.360
 AAA-1.323
querque-1.314
Token Russia
Token ID3284
Feature activation-1.29e-01

Pos logit contributions
emetery+0.687
ospel+0.680
vernment+0.671
ppa+0.667
appa+0.633
Neg logit contributions
 Frie-0.754
spir-0.729
Male-0.690
 AAA-0.668
querque-0.666
Token.
Token ID13
Feature activation+6.50e-01

Pos logit contributions
emetery+0.096
ospel+0.095
vernment+0.093
ppa+0.092
appa+0.088
Neg logit contributions
 Frie-0.103
spir-0.099
Male-0.094
 AAA-0.092
 UCHIJ-0.090
Token
Token ID198
Feature activation+5.20e-01

Pos logit contributions
 Frie+0.506
spir+0.486
Male+0.460
 AAA+0.449
querque+0.442
Neg logit contributions
emetery-0.499
ospel-0.495
vernment-0.483
ppa-0.482
appa-0.460
Token
Token ID447
Feature activation-7.72e-01

Pos logit contributions
 Frie+0.249
spir+0.236
Male+0.221
 AAA+0.218
querque+0.215
Neg logit contributions
emetery-0.304
ospel-0.302
ppa-0.296
vernment-0.295
appa-0.283
Token
Token ID246
Feature activation-5.17e-01

Pos logit contributions
emetery+0.682
ospel+0.676
ppa+0.663
vernment+0.663
appa+0.637
Neg logit contributions
 Frie-0.512
spir-0.486
Male-0.455
 AAA-0.442
 UCHIJ-0.433
TokenWe
Token ID1135
Feature activation+5.99e-01

Pos logit contributions
emetery+0.402
ospel+0.398
vernment+0.389
ppa+0.388
appa+0.370
Neg logit contributions
 Frie-0.396
spir-0.381
Male-0.360
 AAA-0.351
querque-0.346
Token must
Token ID1276
Feature activation+9.54e-01

Pos logit contributions
 Frie+0.437
spir+0.420
Male+0.395
 AAA+0.386
 UCHIJ+0.376
Neg logit contributions
emetery-0.491
ospel-0.485
vernment-0.473
ppa-0.472
appa-0.452
Token commit
Token ID4589
Feature activation-4.82e+00

Pos logit contributions
 Frie+0.734
spir+0.706
Male+0.668
 AAA+0.654
 UCHIJ+0.638
Neg logit contributions
emetery-0.743
ospel-0.733
vernment-0.716
ppa-0.712
appa-0.681
Token ourselves
Token ID6731
Feature activation-7.69e+00

Pos logit contributions
emetery+3.579
ospel+3.554
vernment+3.494
ppa+3.464
 Kak+3.334
Neg logit contributions
 Frie-3.766
spir-3.629
Male-3.430
 UCHIJ-3.358
querque-3.355
Token very
Token ID845
Feature activation-1.47e+00

Pos logit contributions
emetery+5.438
ospel+5.356
vernment+5.356
ppa+5.272
 Kak+5.122
Neg logit contributions
 Frie-6.063
spir-5.821
 UCHIJ-5.476
Male-5.449
querque-5.387
Token res
Token ID581
Feature activation-1.14e+00

Pos logit contributions
emetery+0.971
ospel+0.957
vernment+0.936
ppa+0.934
appa+0.888
Neg logit contributions
 Frie-1.296
spir-1.255
Male-1.194
 AAA-1.167
 UCHIJ-1.164
Tokenolutely
Token ID16780
Feature activation-1.55e+00

Pos logit contributions
emetery+0.654
ospel+0.644
ppa+0.627
vernment+0.624
appa+0.583
Neg logit contributions
 Frie-1.113
spir-1.073
Male-1.032
 AAA-1.015
querque-1.005
Token because
Token ID780
Feature activation-1.03e+00

Pos logit contributions
emetery+1.225
ospel+1.217
vernment+1.199
ppa+1.192
appa+1.138
Neg logit contributions
 Frie-1.163
spir-1.118
Male-1.052
 AAA-1.028
 UCHIJ-1.017
Token there
Token ID612
Feature activation-2.07e+00

Pos logit contributions
emetery+0.766
ospel+0.759
vernment+0.741
ppa+0.739
appa+0.704
Neg logit contributions
 Frie-0.819
spir-0.790
Male-0.748
 AAA-0.728
querque-0.721
Token as
Token ID355
Feature activation-1.58e+00

Pos logit contributions
emetery+1.065
ospel+1.050
ppa+1.029
vernment+1.026
appa+0.984
Neg logit contributions
 Frie-1.042
spir-0.998
Male-0.947
 AAA-0.920
 UCHIJ-0.909
Token the
Token ID262
Feature activation-6.60e-01

Pos logit contributions
emetery+1.129
ospel+1.119
ppa+1.089
vernment+1.085
 Kak+1.044
Neg logit contributions
 Frie-1.307
spir-1.261
Male-1.202
 AAA-1.159
 UCHIJ-1.156
Token Caps
Token ID23534
Feature activation-1.94e+00

Pos logit contributions
emetery+0.480
ospel+0.475
ppa+0.463
vernment+0.463
appa+0.441
Neg logit contributions
 Frie-0.539
spir-0.520
Male-0.494
 AAA-0.481
 UCHIJ-0.475
Token out
Token ID503
Feature activation-3.86e-01

Pos logit contributions
emetery+1.467
ospel+1.450
ppa+1.421
vernment+1.418
appa+1.353
Neg logit contributions
 Frie-1.529
spir-1.465
Male-1.391
 AAA-1.352
 UCHIJ-1.334
Token-
Token ID12
Feature activation-1.38e+00

Pos logit contributions
emetery+0.312
ospel+0.309
vernment+0.302
ppa+0.301
appa+0.288
Neg logit contributions
 Frie-0.286
spir-0.274
Male-0.259
 AAA-0.253
 UCHIJ-0.247
Tokenshot
Token ID9442
Feature activation-7.63e+00

Pos logit contributions
emetery+1.076
ospel+1.070
ppa+1.050
vernment+1.040
appa+0.998
Neg logit contributions
 Frie-1.060
spir-0.998
Male-0.952
 AAA-0.937
querque-0.923
Token the
Token ID262
Feature activation-2.93e+00

Pos logit contributions
ospel+4.915
emetery+4.894
ppa+4.775
 Kak+4.742
vernment+4.721
Neg logit contributions
 Frie-6.451
spir-6.202
Male-6.020
querque-5.753
 UCHIJ-5.700
Token Blues
Token ID15261
Feature activation-4.61e+00

Pos logit contributions
emetery+2.606
ospel+2.601
ppa+2.562
vernment+2.546
 Kak+2.462
Neg logit contributions
 Frie-1.879
spir-1.789
Male-1.686
 UCHIJ-1.603
querque-1.593
Token 10
Token ID838
Feature activation-2.01e+00

Pos logit contributions
emetery+3.300
ospel+3.247
ppa+3.201
vernment+3.178
appa+3.043
Neg logit contributions
 Frie-3.779
spir-3.609
Male-3.449
querque-3.324
 UCHIJ-3.308
Token-
Token ID12
Feature activation-1.49e+00

Pos logit contributions
emetery+1.670
ospel+1.640
ppa+1.610
vernment+1.607
appa+1.542
Neg logit contributions
 Frie-1.448
spir-1.378
Male-1.297
 AAA-1.266
querque-1.248
Token8
Token ID23
Feature activation-1.76e+00

Pos logit contributions
emetery+1.103
ospel+1.096
ppa+1.073
vernment+1.065
appa+1.023
Neg logit contributions
 Frie-1.195
spir-1.133
Male-1.076
 AAA-1.064
querque-1.048
Token training
Token ID3047
Feature activation-1.12e-02

Pos logit contributions
 Frie+0.126
spir+0.121
Male+0.114
 AAA+0.112
 UCHIJ+0.109
Neg logit contributions
emetery-0.137
ospel-0.136
vernment-0.133
ppa-0.132
appa-0.127
Token ground
Token ID2323
Feature activation+3.69e-01

Pos logit contributions
emetery+0.009
ospel+0.009
vernment+0.009
ppa+0.009
appa+0.008
Neg logit contributions
 Frie-0.008
spir-0.008
Male-0.007
 AAA-0.007
 UCHIJ-0.007
Token.
Token ID13
Feature activation-6.25e-02

Pos logit contributions
 Frie+0.279
spir+0.268
Male+0.254
 AAA+0.247
 UCHIJ+0.243
Neg logit contributions
emetery-0.292
ospel-0.289
vernment-0.282
ppa-0.282
appa-0.270
Token I
Token ID314
Feature activation-1.46e+00

Pos logit contributions
emetery+0.046
ospel+0.046
ppa+0.045
vernment+0.045
appa+0.043
Neg logit contributions
 Frie-0.050
spir-0.048
Male-0.045
 AAA-0.044
querque-0.044
Token was
Token ID373
Feature activation-2.60e+00

Pos logit contributions
emetery+1.149
ospel+1.139
vernment+1.115
ppa+1.111
appa+1.063
Neg logit contributions
 Frie-1.107
spir-1.061
Male-1.004
 AAA-0.981
 UCHIJ-0.963
Token lucky
Token ID9670
Feature activation-7.59e+00

Pos logit contributions
emetery+2.002
ospel+1.972
ppa+1.942
vernment+1.922
appa+1.863
Neg logit contributions
 Frie-1.998
spir-1.920
Male-1.810
 AAA-1.757
querque-1.754
Token.
Token ID13
Feature activation-6.36e-01

Pos logit contributions
ospel+4.411
emetery+4.409
ppa+4.341
vernment+4.304
 Kak+4.226
Neg logit contributions
 Frie-6.786
spir-6.554
Male-6.292
querque-6.269
 UCHIJ-6.193
Token I
Token ID314
Feature activation-1.21e+00

Pos logit contributions
emetery+0.467
ospel+0.465
ppa+0.454
vernment+0.450
 Kak+0.431
Neg logit contributions
 Frie-0.509
spir-0.492
Male-0.465
 AAA-0.453
querque-0.452
Token was
Token ID373
Feature activation-1.52e+00

Pos logit contributions
emetery+0.933
ospel+0.925
vernment+0.904
ppa+0.901
appa+0.861
Neg logit contributions
 Frie-0.940
spir-0.902
Male-0.854
 AAA-0.835
 UCHIJ-0.820
Token in
Token ID287
Feature activation-2.87e+00

Pos logit contributions
emetery+1.172
ospel+1.155
ppa+1.134
vernment+1.125
appa+1.085
Neg logit contributions
 Frie-1.165
spir-1.122
Male-1.058
 AAA-1.026
querque-1.020
Token a
Token ID257
Feature activation-2.04e+00

Pos logit contributions
emetery+2.095
ospel+2.094
ppa+2.035
vernment+2.018
 Kak+1.947
Neg logit contributions
 Frie-2.282
spir-2.226
Male-2.108
querque-2.026
 AAA-2.021
Tokenel
Token ID417
Feature activation+1.99e+00

Pos logit contributions
 Frie+1.140
spir+1.098
Male+1.022
 AAA+1.001
 UCHIJ+0.976
Neg logit contributions
emetery-1.295
ospel-1.278
vernment-1.256
ppa-1.250
appa-1.193
Tokenm
Token ID76
Feature activation-1.07e+00

Pos logit contributions
 Frie+1.486
spir+1.431
Male+1.332
 AAA+1.311
 UCHIJ+1.275
Neg logit contributions
emetery-1.597
ospel-1.569
vernment-1.540
ppa-1.522
appa-1.458
Tokenose
Token ID577
Feature activation-4.80e-01

Pos logit contributions
emetery+0.778
ospel+0.773
ppa+0.754
vernment+0.751
appa+0.719
Neg logit contributions
 Frie-0.879
spir-0.846
Male-0.807
 AAA-0.787
 UCHIJ-0.776
Token,
Token ID11
Feature activation-1.42e+00

Pos logit contributions
emetery+0.346
ospel+0.343
ppa+0.336
vernment+0.335
appa+0.318
Neg logit contributions
 Frie-0.393
spir-0.380
Male-0.362
 AAA-0.353
 UCHIJ-0.348
Token an
Token ID281
Feature activation-3.05e+00

Pos logit contributions
emetery+1.024
ospel+1.013
vernment+0.989
ppa+0.984
appa+0.938
Neg logit contributions
 Frie-1.175
spir-1.137
Male-1.078
 AAA-1.051
querque-1.037
Token Ike
Token ID34880
Feature activation-7.58e+00

Pos logit contributions
emetery+1.808
ospel+1.788
vernment+1.738
ppa+1.720
appa+1.646
Neg logit contributions
 Frie-2.871
spir-2.803
Male-2.678
querque-2.596
 AAA-2.591
Tokena
Token ID64
Feature activation-2.12e+00

Pos logit contributions
ospel+4.196
ppa+4.060
emetery+4.053
vernment+3.880
appa+3.879
Neg logit contributions
 Frie-7.502
spir-7.060
querque-6.841
Male-6.774
 UCHIJ-6.622
Token manager
Token ID4706
Feature activation-2.07e+00

Pos logit contributions
emetery+1.462
ospel+1.443
vernment+1.410
ppa+1.400
appa+1.335
Neg logit contributions
 Frie-1.803
spir-1.745
Male-1.659
 AAA-1.616
querque-1.600
Token.
Token ID13
Feature activation-1.32e+00

Pos logit contributions
emetery+1.507
ospel+1.488
vernment+1.459
ppa+1.449
appa+1.392
Neg logit contributions
 Frie-1.675
spir-1.626
Male-1.535
 AAA-1.492
querque-1.487
Token "
Token ID366
Feature activation+1.71e+00

Pos logit contributions
emetery+0.985
ospel+0.975
vernment+0.953
ppa+0.950
appa+0.905
Neg logit contributions
 Frie-1.053
spir-1.013
Male-0.958
 AAA-0.940
querque-0.929
TokenThe
Token ID464
Feature activation-9.39e-01

Pos logit contributions
 Frie+1.124
spir+1.083
Male+1.031
 AAA+0.982
 UCHIJ+0.958
Neg logit contributions
emetery-1.534
ospel-1.511
vernment-1.488
ppa-1.469
appa-1.421
Token in
Token ID287
Feature activation-5.00e-01

Pos logit contributions
 Frie+0.022
spir+0.021
Male+0.020
 AAA+0.019
 UCHIJ+0.019
Neg logit contributions
emetery-0.022
ospel-0.022
vernment-0.021
ppa-0.021
appa-0.020
Token 1999
Token ID7358
Feature activation-8.35e-01

Pos logit contributions
emetery+0.366
ospel+0.362
vernment+0.353
ppa+0.352
appa+0.335
Neg logit contributions
 Frie-0.408
spir-0.393
Male-0.373
 AAA-0.365
 UCHIJ-0.358
Token.
Token ID13
Feature activation+2.82e-02

Pos logit contributions
emetery+0.641
ospel+0.632
vernment+0.620
ppa+0.618
appa+0.589
Neg logit contributions
 Frie-0.649
spir-0.626
Male-0.590
 AAA-0.577
 UCHIJ-0.567
Token Am
Token ID1703
Feature activation-8.38e-01

Pos logit contributions
 Frie+0.022
spir+0.021
Male+0.020
 AAA+0.019
querque+0.019
Neg logit contributions
emetery-0.022
ospel-0.021
ppa-0.021
vernment-0.021
appa-0.020
Tokenad
Token ID324
Feature activation-4.21e+00

Pos logit contributions
emetery+0.640
ospel+0.633
vernment+0.618
ppa+0.616
appa+0.588
Neg logit contributions
 Frie-0.656
spir-0.631
Male-0.598
 AAA-0.585
 UCHIJ-0.574
Tokenou
Token ID280
Feature activation-7.54e+00

Pos logit contributions
ospel+4.112
emetery+4.045
ppa+4.010
vernment+4.007
 Kak+3.918
Neg logit contributions
 Frie-2.314
spir-2.195
Male-2.045
 AAA-1.956
 UCHIJ-1.908
Token Di
Token ID6031
Feature activation-5.49e-02

Pos logit contributions
vernment+5.315
ospel+5.263
emetery+5.208
ppa+5.195
 Kak+5.100
Neg logit contributions
 Frie-5.817
spir-5.778
Male-5.456
 UCHIJ-5.289
 AAA-5.272
Tokenallo
Token ID49457
Feature activation+2.58e-01

Pos logit contributions
emetery+0.045
ospel+0.044
vernment+0.043
ppa+0.043
appa+0.041
Neg logit contributions
 Frie-0.040
spir-0.039
Male-0.036
 AAA-0.036
 UCHIJ-0.035
Token said
Token ID531
Feature activation-9.78e-01

Pos logit contributions
 Frie+0.207
spir+0.200
Male+0.189
 AAA+0.185
 UCHIJ+0.183
Neg logit contributions
emetery-0.190
ospel-0.188
vernment-0.184
ppa-0.184
appa-0.175
Token he
Token ID339
Feature activation+1.40e+00

Pos logit contributions
emetery+0.718
ospel+0.710
vernment+0.692
ppa+0.691
appa+0.661
Neg logit contributions
 Frie-0.790
spir-0.766
Male-0.724
 AAA-0.703
 UCHIJ-0.698
Token was
Token ID373
Feature activation-6.55e-01

Pos logit contributions
 Frie+1.022
spir+0.980
Male+0.922
 AAA+0.902
 UCHIJ+0.878
Neg logit contributions
emetery-1.150
ospel-1.133
vernment-1.100
ppa-1.092
appa-1.047
Token in
Token ID287
Feature activation-1.63e+00

Pos logit contributions
emetery+0.384
ospel+0.380
vernment+0.372
ppa+0.371
appa+0.353
Neg logit contributions
 Frie-0.415
spir-0.399
Male-0.379
 AAA-0.369
 UCHIJ-0.365
Token Spain
Token ID8602
Feature activation-4.23e-01

Pos logit contributions
emetery+1.240
ospel+1.226
vernment+1.206
ppa+1.202
 Kak+1.143
Neg logit contributions
 Frie-1.271
spir-1.218
Male-1.163
 AAA-1.119
querque-1.119
Token,
Token ID11
Feature activation-8.28e-01

Pos logit contributions
emetery+0.308
ospel+0.304
vernment+0.298
ppa+0.296
appa+0.282
Neg logit contributions
 Frie-0.345
spir-0.333
Male-0.316
 AAA-0.309
 UCHIJ-0.304
Token should
Token ID815
Feature activation-1.18e+00

Pos logit contributions
emetery+0.662
ospel+0.655
vernment+0.641
ppa+0.639
appa+0.611
Neg logit contributions
 Frie-0.619
spir-0.595
Male-0.561
 AAA-0.547
 UCHIJ-0.537
Token expose
Token ID15651
Feature activation-1.98e+00

Pos logit contributions
emetery+0.934
ospel+0.926
vernment+0.906
ppa+0.903
appa+0.864
Neg logit contributions
 Frie-0.884
spir-0.848
Male-0.802
 AAA-0.781
 UCHIJ-0.768
Token themselves
Token ID2405
Feature activation-7.53e+00

Pos logit contributions
emetery+1.217
ospel+1.204
vernment+1.173
ppa+1.168
appa+1.097
Neg logit contributions
 Frie-1.840
spir-1.780
Male-1.704
 AAA-1.664
 UCHIJ-1.649
Token to
Token ID284
Feature activation-3.97e+00

Pos logit contributions
emetery+5.163
vernment+5.121
ospel+5.091
ppa+5.034
 Kak+4.888
Neg logit contributions
 Frie-6.090
spir-5.735
Male-5.468
 UCHIJ-5.439
querque-5.393
Token the
Token ID262
Feature activation-2.63e+00

Pos logit contributions
emetery+2.773
ospel+2.759
vernment+2.708
ppa+2.692
 Kak+2.584
Neg logit contributions
 Frie-3.292
spir-3.165
Male-3.014
querque-2.923
 AAA-2.900
Token challenge
Token ID4427
Feature activation+2.88e-01

Pos logit contributions
emetery+1.665
ospel+1.662
vernment+1.617
ppa+1.617
appa+1.530
Neg logit contributions
 Frie-2.355
spir-2.267
Male-2.186
querque-2.116
 UCHIJ-2.106
Token of
Token ID286
Feature activation-3.31e+00

Pos logit contributions
 Frie+0.223
spir+0.215
Male+0.203
 AAA+0.199
 UCHIJ+0.194
Neg logit contributions
emetery-0.225
ospel-0.222
vernment-0.216
ppa-0.215
appa-0.206
Token advancing
Token ID19988
Feature activation-6.52e-01

Pos logit contributions
emetery+2.434
ospel+2.410
vernment+2.380
ppa+2.375
 Kak+2.272
Neg logit contributions
 Frie-2.626
spir-2.521
Male-2.403
querque-2.327
 UCHIJ-2.306
Token
Token ID198
Feature activation-5.09e-01

Pos logit contributions
ospel+0.398
emetery+0.397
ppa+0.389
vernment+0.385
appa+0.370
Neg logit contributions
 Frie-0.422
spir-0.401
Male-0.379
querque-0.376
 AAA-0.371
TokenWiki
Token ID32603
Feature activation-1.27e+00

Pos logit contributions
emetery+0.427
ospel+0.424
ppa+0.417
vernment+0.416
appa+0.400
Neg logit contributions
 Frie-0.360
spir-0.340
Male-0.317
 AAA-0.314
querque-0.312
TokenLeaks
Token ID17874
Feature activation-5.12e+00

Pos logit contributions
emetery+1.101
ospel+1.091
ppa+1.077
vernment+1.071
appa+1.032
Neg logit contributions
 Frie-0.862
spir-0.809
Male-0.754
 AAA-0.740
querque-0.737
Token pr
Token ID778
Feature activation-3.12e-01

Pos logit contributions
emetery+3.604
vernment+3.536
ppa+3.514
ospel+3.507
 Kak+3.397
Neg logit contributions
 Frie-4.149
spir-3.992
Male-3.814
querque-3.700
 AAA-3.640
Tokenides
Token ID1460
Feature activation-4.91e+00

Pos logit contributions
emetery+0.159
ospel+0.156
vernment+0.151
ppa+0.150
appa+0.139
Neg logit contributions
 Frie-0.324
spir-0.315
Male-0.302
 AAA-0.297
 UCHIJ-0.293
Token itself
Token ID2346
Feature activation-7.50e+00

Pos logit contributions
vernment+2.597
emetery+2.583
ospel+2.568
ppa+2.434
 Kak+2.364
Neg logit contributions
 Frie-4.840
spir-4.709
Male-4.494
querque-4.410
 UCHIJ-4.373
Token as
Token ID355
Feature activation-4.33e+00

Pos logit contributions
emetery+4.818
vernment+4.709
ospel+4.683
ppa+4.467
appa+4.369
Neg logit contributions
 Frie-6.624
spir-6.315
Male-5.974
querque-5.858
 AAA-5.853
Token a
Token ID257
Feature activation-2.59e+00

Pos logit contributions
emetery+3.133
vernment+3.097
ospel+3.097
ppa+2.986
 Kak+2.889
Neg logit contributions
 Frie-3.514
spir-3.342
Male-3.179
querque-3.088
 UCHIJ-3.080
Token website
Token ID3052
Feature activation-3.15e+00

Pos logit contributions
emetery+1.937
ospel+1.923
vernment+1.911
ppa+1.870
 Kak+1.791
Neg logit contributions
 Frie-2.048
spir-1.955
Male-1.861
querque-1.804
 AAA-1.787
Token devoted
Token ID13378
Feature activation-4.03e+00

Pos logit contributions
emetery+2.358
ospel+2.328
vernment+2.323
ppa+2.273
 Kak+2.183
Neg logit contributions
 Frie-2.477
spir-2.371
Male-2.271
 AAA-2.181
querque-2.180
Token to
Token ID284
Feature activation-1.10e+00

Pos logit contributions
emetery+3.098
ospel+3.073
vernment+3.061
ppa+2.973
appa+2.846
Neg logit contributions
 Frie-3.105
spir-2.962
Male-2.813
 AAA-2.725
 UCHIJ-2.710
Token or
Token ID393
Feature activation+1.24e+00

Pos logit contributions
 Frie+0.331
spir+0.317
Male+0.301
 AAA+0.294
 UCHIJ+0.288
Neg logit contributions
emetery-0.333
ospel-0.330
vernment-0.322
ppa-0.321
appa-0.306
Token am
Token ID716
Feature activation+2.76e+00

Pos logit contributions
 Frie+0.923
spir+0.883
Male+0.837
 AAA+0.818
 UCHIJ+0.797
Neg logit contributions
emetery-0.996
ospel-0.985
vernment-0.960
ppa-0.958
appa-0.915
Token I
Token ID314
Feature activation-3.22e+00

Pos logit contributions
 Frie+2.237
spir+2.183
Male+2.068
 AAA+2.003
 UCHIJ+1.966
Neg logit contributions
emetery-1.993
ospel-1.978
vernment-1.959
ppa-1.945
appa-1.816
Token fool
Token ID9192
Feature activation-8.10e+00

Pos logit contributions
emetery+2.370
ospel+2.332
vernment+2.302
ppa+2.298
 Kak+2.214
Neg logit contributions
 Frie-2.543
spir-2.431
Male-2.290
 AAA-2.258
 UCHIJ-2.247
Tokening
Token ID278
Feature activation-4.04e+00

Pos logit contributions
ospel+4.629
vernment+4.612
emetery+4.602
ppa+4.470
appa+4.305
Neg logit contributions
 Frie-7.270
spir-7.022
Male-6.878
querque-6.731
 UCHIJ-6.711
Token myself
Token ID3589
Feature activation-7.43e+00

Pos logit contributions
emetery+2.676
ospel+2.640
vernment+2.620
ppa+2.582
 Kak+2.445
Neg logit contributions
 Frie-3.516
spir-3.383
Male-3.230
querque-3.158
 AAA-3.120
Token?
Token ID30
Feature activation-3.96e-01

Pos logit contributions
emetery+5.221
ppa+5.117
vernment+5.103
ospel+5.074
 Kak+4.888
Neg logit contributions
 Frie-5.884
spir-5.719
Male-5.330
querque-5.304
 UCHIJ-5.259
Token
Token ID198
Feature activation+6.75e-01

Pos logit contributions
emetery+0.302
ospel+0.299
ppa+0.293
vernment+0.292
appa+0.279
Neg logit contributions
 Frie-0.309
spir-0.297
Male-0.281
 AAA-0.274
querque-0.271
Token
Token ID198
Feature activation-4.31e-01

Pos logit contributions
 Frie+0.515
spir+0.495
Male+0.468
 AAA+0.458
 UCHIJ+0.448
Neg logit contributions
emetery-0.529
ospel-0.523
vernment-0.512
ppa-0.509
appa-0.487
TokenAll
Token ID3237
Feature activation+2.26e+00

Pos logit contributions
emetery+0.357
ospel+0.355
ppa+0.348
vernment+0.346
appa+0.332
Neg logit contributions
 Frie-0.309
spir-0.294
Male-0.274
 AAA-0.271
querque-0.269
Token these
Token ID777
Feature activation+1.17e+00

Pos logit contributions
 Frie+1.761
spir+1.696
Male+1.612
 AAA+1.587
 UCHIJ+1.533
Neg logit contributions
emetery-1.720
ospel-1.697
vernment-1.671
ppa-1.647
appa-1.578
Token kingdom
Token ID13239
Feature activation-1.21e+00

Pos logit contributions
ospel+1.184
emetery+1.172
vernment+1.153
ppa+1.127
appa+1.071
Neg logit contributions
 Frie-1.983
spir-1.928
Male-1.851
 AAA-1.806
querque-1.785
Token for
Token ID329
Feature activation+1.15e+00

Pos logit contributions
emetery+0.893
ospel+0.883
vernment+0.864
ppa+0.858
appa+0.820
Neg logit contributions
 Frie-0.975
spir-0.941
Male-0.893
 AAA-0.870
querque-0.859
Token alleged
Token ID4260
Feature activation-1.16e+00

Pos logit contributions
 Frie+0.929
spir+0.896
Male+0.848
 AAA+0.836
 UCHIJ+0.815
Neg logit contributions
emetery-0.849
ospel-0.839
vernment-0.818
ppa-0.818
appa-0.778
Token anti
Token ID3098
Feature activation+2.73e-01

Pos logit contributions
emetery+0.886
ospel+0.878
vernment+0.857
ppa+0.850
 Kak+0.816
Neg logit contributions
 Frie-0.908
spir-0.873
Male-0.830
querque-0.798
 AAA-0.796
Token-
Token ID12
Feature activation-2.53e+00

Pos logit contributions
 Frie+0.188
spir+0.179
Male+0.169
 AAA+0.165
querque+0.161
Neg logit contributions
emetery-0.233
ospel-0.231
vernment-0.227
ppa-0.226
appa-0.217
Tokenstate
Token ID5219
Feature activation-7.30e+00

Pos logit contributions
ospel+1.626
emetery+1.620
vernment+1.592
ppa+1.543
appa+1.507
Neg logit contributions
 Frie-2.279
spir-2.139
 AAA-2.053
querque-2.042
Male-2.040
Token acts
Token ID6529
Feature activation-2.68e+00

Pos logit contributions
ospel+4.551
emetery+4.516
vernment+4.476
 Kak+4.342
ppa+4.296
Neg logit contributions
 Frie-6.365
spir-5.949
Male-5.911
querque-5.727
 UCHIJ-5.705
Token,
Token ID11
Feature activation-4.03e-01

Pos logit contributions
emetery+1.872
ospel+1.828
vernment+1.821
ppa+1.799
appa+1.721
Neg logit contributions
 Frie-2.237
spir-2.164
Male-2.059
 AAA-2.008
querque-1.995
Token died
Token ID3724
Feature activation+3.39e+00

Pos logit contributions
emetery+0.339
ospel+0.335
vernment+0.329
ppa+0.328
appa+0.315
Neg logit contributions
 Frie-0.283
spir-0.271
Male-0.255
 AAA-0.247
querque-0.244
Token at
Token ID379
Feature activation-1.70e-01

Pos logit contributions
 Frie+2.539
spir+2.421
Male+2.291
 AAA+2.276
 UCHIJ+2.203
Neg logit contributions
emetery-2.690
ospel-2.688
vernment-2.618
ppa-2.601
appa-2.481
Token 2
Token ID362
Feature activation+1.81e+00

Pos logit contributions
emetery+0.126
ospel+0.124
vernment+0.121
ppa+0.121
appa+0.115
Neg logit contributions
 Frie-0.137
spir-0.133
Male-0.126
 AAA-0.123
 UCHIJ-0.121
Token the
Token ID262
Feature activation+1.81e-01

Pos logit contributions
emetery+0.418
ospel+0.414
vernment+0.405
ppa+0.403
appa+0.384
Neg logit contributions
 Frie-0.463
spir-0.446
Male-0.423
 AAA-0.412
querque-0.409
Token idea
Token ID2126
Feature activation+1.59e+00

Pos logit contributions
 Frie+0.155
spir+0.150
Male+0.142
 AAA+0.140
 UCHIJ+0.137
Neg logit contributions
emetery-0.126
ospel-0.124
vernment-0.121
ppa-0.120
appa-0.114
Token that
Token ID326
Feature activation-5.59e-01

Pos logit contributions
 Frie+1.187
spir+1.140
Male+1.073
 AAA+1.057
 UCHIJ+1.024
Neg logit contributions
emetery-1.270
ospel-1.254
vernment-1.221
ppa-1.220
appa-1.168
Token a
Token ID257
Feature activation-1.33e-01

Pos logit contributions
emetery+0.427
ospel+0.423
vernment+0.414
ppa+0.413
appa+0.394
Neg logit contributions
 Frie-0.436
spir-0.419
Male-0.397
 AAA-0.386
querque-0.382
Token foreign
Token ID3215
Feature activation-2.55e-01

Pos logit contributions
emetery+0.104
ospel+0.102
vernment+0.100
ppa+0.100
appa+0.095
Neg logit contributions
 Frie-0.102
spir-0.098
Male-0.093
 AAA-0.091
 UCHIJ-0.089
Token state
Token ID1181
Feature activation-7.26e+00

Pos logit contributions
emetery+0.187
ospel+0.185
vernment+0.180
ppa+0.179
appa+0.171
Neg logit contributions
 Frie-0.208
spir-0.200
Male-0.190
 AAA-0.186
 UCHIJ-0.183
Token could
Token ID714
Feature activation-2.18e+00

Pos logit contributions
emetery+4.981
ppa+4.968
ospel+4.901
vernment+4.869
 Kak+4.778
Neg logit contributions
 Frie-5.927
spir-5.478
Male-5.251
querque-5.189
 UCHIJ-5.135
Token be
Token ID307
Feature activation-2.01e+00

Pos logit contributions
ospel+1.731
emetery+1.730
ppa+1.694
vernment+1.684
appa+1.618
Neg logit contributions
 Frie-1.636
spir-1.547
Male-1.473
 AAA-1.420
querque-1.418
Token trying
Token ID2111
Feature activation-2.95e+00

Pos logit contributions
emetery+1.562
ospel+1.547
ppa+1.520
vernment+1.511
appa+1.461
Neg logit contributions
 Frie-1.534
spir-1.456
Male-1.383
 AAA-1.336
querque-1.330
Token to
Token ID284
Feature activation-2.00e+00

Pos logit contributions
emetery+2.327
ospel+2.304
vernment+2.267
ppa+2.250
appa+2.152
Neg logit contributions
 Frie-2.245
spir-2.138
Male-2.024
 AAA-1.962
 UCHIJ-1.938
Token influence
Token ID4588
Feature activation-1.59e+00

Pos logit contributions
ospel+1.454
emetery+1.453
ppa+1.424
vernment+1.419
appa+1.353
Neg logit contributions
 Frie-1.627
spir-1.554
Male-1.486
querque-1.433
 AAA-1.432
Token enemies
Token ID5775
Feature activation-2.24e+00

Pos logit contributions
 Frie+0.356
spir+0.344
Male+0.324
 AAA+0.319
 UCHIJ+0.311
Neg logit contributions
emetery-0.343
ospel-0.339
vernment-0.330
ppa-0.329
appa-0.313
Token of
Token ID286
Feature activation-2.43e+00

Pos logit contributions
emetery+1.661
ospel+1.641
vernment+1.614
ppa+1.606
appa+1.531
Neg logit contributions
 Frie-1.786
spir-1.720
Male-1.632
 AAA-1.593
querque-1.576
Token the
Token ID262
Feature activation-1.59e+00

Pos logit contributions
emetery+1.765
ospel+1.750
vernment+1.719
ppa+1.702
 Kak+1.629
Neg logit contributions
 Frie-1.967
spir-1.898
Male-1.802
 AAA-1.753
querque-1.742
Token North
Token ID2258
Feature activation-2.44e+00

Pos logit contributions
emetery+1.135
ospel+1.132
vernment+1.111
ppa+1.097
 Kak+1.052
Neg logit contributions
 Frie-1.301
spir-1.256
Male-1.194
querque-1.161
 AAA-1.158
Token Korean
Token ID6983
Feature activation-3.44e+00

Pos logit contributions
emetery+1.637
ospel+1.619
vernment+1.584
ppa+1.571
appa+1.492
Neg logit contributions
 Frie-2.123
spir-2.050
Male-1.954
 AAA-1.915
querque-1.898
Token state
Token ID1181
Feature activation-7.26e+00

Pos logit contributions
ospel+2.389
emetery+2.384
vernment+2.367
ppa+2.322
 Kak+2.232
Neg logit contributions
 Frie-2.843
spir-2.737
Male-2.605
querque-2.558
 AAA-2.532
Token.
Token ID13
Feature activation-1.84e+00

Pos logit contributions
emetery+4.757
vernment+4.745
ospel+4.732
ppa+4.682
 Kak+4.557
Neg logit contributions
 Frie-6.081
spir-5.737
Male-5.537
querque-5.473
 UCHIJ-5.426
Token The
Token ID383
Feature activation-1.72e+00

Pos logit contributions
ospel+1.374
emetery+1.374
ppa+1.347
vernment+1.336
 Kak+1.292
Neg logit contributions
 Frie-1.432
spir-1.388
Male-1.307
querque-1.290
 AAA-1.267
Token only
Token ID691
Feature activation+1.28e-01

Pos logit contributions
emetery+1.237
ospel+1.224
vernment+1.196
ppa+1.191
appa+1.136
Neg logit contributions
 Frie-1.409
spir-1.360
Male-1.294
 AAA-1.257
querque-1.246
Token recognizable
Token ID30264
Feature activation-1.66e+00

Pos logit contributions
 Frie+0.107
spir+0.103
Male+0.098
 AAA+0.097
 UCHIJ+0.095
Neg logit contributions
emetery-0.091
ospel-0.090
vernment-0.087
ppa-0.087
appa-0.083
Token special
Token ID2041
Feature activation-1.47e+00

Pos logit contributions
emetery+1.202
ospel+1.190
vernment+1.159
ppa+1.154
appa+1.097
Neg logit contributions
 Frie-1.377
spir-1.324
Male-1.258
 AAA-1.237
 UCHIJ-1.210
Token
Token ID447
Feature activation-1.06e+00

Pos logit contributions
emetery+0.381
ospel+0.376
vernment+0.367
ppa+0.366
appa+0.349
Neg logit contributions
 Frie-0.418
spir-0.402
Male-0.382
 AAA-0.373
 UCHIJ-0.367
Token
Token ID247
Feature activation-1.18e+00

Pos logit contributions
emetery+1.125
ospel+1.116
vernment+1.097
ppa+1.095
appa+1.061
Neg logit contributions
 Frie-0.514
spir-0.484
Male-0.441
 AAA-0.425
 UCHIJ-0.410
Token which
Token ID543
Feature activation-2.84e+00

Pos logit contributions
emetery+0.897
ospel+0.886
vernment+0.865
ppa+0.862
appa+0.822
Neg logit contributions
 Frie-0.937
spir-0.902
Male-0.855
 AAA-0.836
 UCHIJ-0.820
Token is
Token ID318
Feature activation-2.25e+00

Pos logit contributions
emetery+2.261
ospel+2.245
ppa+2.222
vernment+2.197
appa+2.119
Neg logit contributions
 Frie-2.099
spir-2.004
Male-1.900
querque-1.832
 AAA-1.828
Token the
Token ID262
Feature activation-3.20e+00

Pos logit contributions
emetery+1.689
ospel+1.672
vernment+1.636
ppa+1.635
appa+1.561
Neg logit contributions
 Frie-1.768
spir-1.701
Male-1.613
 AAA-1.561
querque-1.553
Token BIOS
Token ID27553
Feature activation-7.21e+00

Pos logit contributions
emetery+2.352
ospel+2.345
ppa+2.291
vernment+2.275
 Kak+2.188
Neg logit contributions
 Frie-2.538
spir-2.450
Male-2.327
querque-2.245
 AAA-2.230
Token default
Token ID4277
Feature activation+6.25e-01

Pos logit contributions
emetery+4.948
ospel+4.932
ppa+4.887
vernment+4.827
 Kak+4.714
Neg logit contributions
 Frie-5.687
spir-5.605
Male-5.305
querque-5.135
 UCHIJ-5.060
Token.
Token ID13
Feature activation-1.64e+00

Pos logit contributions
 Frie+0.482
spir+0.461
Male+0.437
 AAA+0.432
 UCHIJ+0.420
Neg logit contributions
emetery-0.490
ospel-0.482
vernment-0.472
ppa-0.468
appa-0.447
Token With
Token ID2080
Feature activation-1.19e-01

Pos logit contributions
emetery+1.233
ospel+1.229
ppa+1.200
vernment+1.194
appa+1.142
Neg logit contributions
 Frie-1.291
spir-1.246
Male-1.175
 AAA-1.145
querque-1.141
Token two
Token ID734
Feature activation+1.02e+00

Pos logit contributions
emetery+0.091
ospel+0.090
vernment+0.088
ppa+0.087
appa+0.083
Neg logit contributions
 Frie-0.094
spir-0.090
Male-0.086
 AAA-0.084
 UCHIJ-0.082
Token cards
Token ID4116
Feature activation-3.95e-01

Pos logit contributions
 Frie+0.785
spir+0.751
Male+0.711
 AAA+0.704
 UCHIJ+0.684
Neg logit contributions
emetery-0.801
ospel-0.792
vernment-0.776
ppa-0.767
appa-0.734
Token
Token ID784
Feature activation-3.81e-01

Pos logit contributions
 Frie+0.862
spir+0.831
Male+0.784
 AAA+0.770
 UCHIJ+0.751
Neg logit contributions
emetery-0.835
ospel-0.824
vernment-0.801
ppa-0.800
appa-0.763
Token they
Token ID484
Feature activation+1.17e+00

Pos logit contributions
emetery+0.281
ospel+0.278
ppa+0.271
vernment+0.271
appa+0.259
Neg logit contributions
 Frie-0.306
spir-0.295
Male-0.280
 AAA-0.273
querque-0.269
Token have
Token ID423
Feature activation+4.46e-01

Pos logit contributions
 Frie+0.851
spir+0.825
Male+0.766
 AAA+0.764
 UCHIJ+0.740
Neg logit contributions
emetery-0.974
ospel-0.954
vernment-0.924
ppa-0.924
appa-0.882
Token opened
Token ID4721
Feature activation+2.18e+00

Pos logit contributions
 Frie+0.337
spir+0.324
Male+0.305
 AAA+0.300
 UCHIJ+0.293
Neg logit contributions
emetery-0.354
ospel-0.350
vernment-0.341
ppa-0.340
appa-0.325
Token themselves
Token ID2405
Feature activation-5.00e+00

Pos logit contributions
 Frie+1.739
spir+1.684
Male+1.581
 AAA+1.580
 UCHIJ+1.519
Neg logit contributions
emetery-1.630
ospel-1.613
vernment-1.577
ppa-1.560
appa-1.492
Token up
Token ID510
Feature activation-7.20e+00

Pos logit contributions
emetery+3.881
ospel+3.822
vernment+3.743
ppa+3.740
 Kak+3.610
Neg logit contributions
 Frie-3.758
spir-3.553
Male-3.371
 UCHIJ-3.268
querque-3.261
Token to
Token ID284
Feature activation-2.01e+00

Pos logit contributions
emetery+4.934
ospel+4.906
vernment+4.855
ppa+4.816
 Kak+4.695
Neg logit contributions
 Frie-5.796
spir-5.451
Male-5.232
 UCHIJ-5.085
querque-5.076
Token the
Token ID262
Feature activation-3.75e-01

Pos logit contributions
emetery+1.453
ospel+1.449
ppa+1.415
vernment+1.407
appa+1.350
Neg logit contributions
 Frie-1.619
spir-1.563
Male-1.484
querque-1.432
 AAA-1.421
Token disbelief
Token ID29894
Feature activation+1.03e-01

Pos logit contributions
emetery+0.271
ospel+0.269
vernment+0.262
ppa+0.261
appa+0.248
Neg logit contributions
 Frie-0.309
spir-0.297
Male-0.283
 AAA-0.276
 UCHIJ-0.271
Token,
Token ID11
Feature activation+5.65e-01

Pos logit contributions
 Frie+0.082
spir+0.079
Male+0.075
 AAA+0.073
 UCHIJ+0.072
Neg logit contributions
emetery-0.078
ospel-0.077
vernment-0.075
ppa-0.075
appa-0.072
Token the
Token ID262
Feature activation+8.91e-01

Pos logit contributions
 Frie+0.462
spir+0.445
Male+0.422
 AAA+0.414
 UCHIJ+0.406
Neg logit contributions
emetery-0.413
ospel-0.408
vernment-0.398
ppa-0.397
appa-0.378
Token to
Token ID284
Feature activation-3.37e+00

Pos logit contributions
ospel+4.377
ppa+4.345
emetery+4.316
vernment+4.285
appa+4.126
Neg logit contributions
 Frie-5.106
spir-4.723
querque-4.652
Male-4.547
 UCHIJ-4.377
Token reduce
Token ID4646
Feature activation-1.89e+00

Pos logit contributions
emetery+2.365
ospel+2.358
ppa+2.317
vernment+2.304
appa+2.190
Neg logit contributions
 Frie-2.827
spir-2.695
Male-2.578
querque-2.512
 AAA-2.486
Token the
Token ID262
Feature activation-1.39e+00

Pos logit contributions
emetery+1.370
ospel+1.353
vernment+1.319
ppa+1.319
appa+1.254
Neg logit contributions
 Frie-1.542
spir-1.489
Male-1.415
 AAA-1.366
 UCHIJ-1.359
Token motion
Token ID6268
Feature activation-3.33e+00

Pos logit contributions
emetery+1.007
ospel+0.997
ppa+0.973
vernment+0.972
appa+0.925
Neg logit contributions
 Frie-1.131
spir-1.091
Male-1.038
 AAA-1.004
querque-0.997
Token blur
Token ID23671
Feature activation-6.05e+00

Pos logit contributions
emetery+2.310
ospel+2.289
ppa+2.239
vernment+2.219
appa+2.119
Neg logit contributions
 Frie-2.816
spir-2.711
Male-2.592
 AAA-2.513
querque-2.501
Token even
Token ID772
Feature activation-7.18e+00

Pos logit contributions
emetery+4.292
ospel+4.220
ppa+4.194
vernment+4.103
 Kak+4.020
Neg logit contributions
 Frie-4.928
spir-4.711
Male-4.502
querque-4.405
 UCHIJ-4.287
Token more
Token ID517
Feature activation-9.41e-01

Pos logit contributions
emetery+3.581
ppa+3.480
ospel+3.479
vernment+3.313
 Kak+3.269
Neg logit contributions
 Frie-7.299
spir-7.011
Male-6.742
querque-6.735
 UCHIJ-6.601
Token through
Token ID832
Feature activation-3.10e+00

Pos logit contributions
emetery+0.724
ospel+0.716
vernment+0.699
ppa+0.696
appa+0.665
Neg logit contributions
 Frie-0.733
spir-0.705
Male-0.668
 AAA-0.653
 UCHIJ-0.640
Token the
Token ID262
Feature activation-1.72e+00

Pos logit contributions
emetery+2.244
ospel+2.233
ppa+2.181
vernment+2.172
 Kak+2.089
Neg logit contributions
 Frie-2.491
spir-2.413
Male-2.282
querque-2.211
 UCHIJ-2.197
Token use
Token ID779
Feature activation-5.40e-01

Pos logit contributions
emetery+1.267
ospel+1.258
ppa+1.230
vernment+1.223
appa+1.171
Neg logit contributions
 Frie-1.377
spir-1.330
Male-1.262
 AAA-1.216
 UCHIJ-1.214
Token of
Token ID286
Feature activation-2.47e+00

Pos logit contributions
emetery+0.395
ospel+0.392
ppa+0.382
vernment+0.380
appa+0.364
Neg logit contributions
 Frie-0.440
spir-0.422
Male-0.400
 AAA-0.390
querque-0.389
Token
Token ID198
Feature activation-1.61e+00

Pos logit contributions
ospel+1.142
emetery+1.128
ppa+1.118
vernment+1.097
appa+1.060
Neg logit contributions
 Frie-1.288
spir-1.211
querque-1.166
Male-1.145
 AAA-1.120
Token……
Token ID7398
Feature activation-1.79e+00

Pos logit contributions
emetery+1.270
ospel+1.263
ppa+1.233
vernment+1.227
appa+1.178
Neg logit contributions
 Frie-1.226
spir-1.170
Male-1.097
 AAA-1.082
querque-1.069
Token.
Token ID13
Feature activation-1.16e+00

Pos logit contributions
emetery+1.636
ospel+1.622
vernment+1.589
ppa+1.580
appa+1.521
Neg logit contributions
 Frie-1.130
spir-1.077
Male-0.995
 AAA-0.973
 UCHIJ-0.953
Token
Token ID198
Feature activation-1.41e+00

Pos logit contributions
emetery+0.863
ospel+0.862
ppa+0.841
vernment+0.835
appa+0.801
Neg logit contributions
 Frie-0.920
spir-0.877
Male-0.826
querque-0.821
 AAA-0.809
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
ospel+1.035
emetery+1.025
ppa+1.013
vernment+0.996
appa+0.961
Neg logit contributions
 Frie-1.150
spir-1.086
querque-1.039
Male-1.027
 AAA-1.003
TokenDear
Token ID20266
Feature activation-7.18e+00

Pos logit contributions
emetery+2.129
ospel+2.123
ppa+2.083
vernment+2.071
appa+2.012
Neg logit contributions
 Frie-1.241
spir-1.153
Male-1.053
 AAA-1.042
querque-1.036
Token George
Token ID4502
Feature activation-3.03e+00

Pos logit contributions
emetery+4.220
ospel+4.216
ppa+4.104
vernment+4.074
 Kak+3.996
Neg logit contributions
 Frie-6.388
spir-6.371
querque-5.980
Male-5.969
 UCHIJ-5.856
Token,
Token ID11
Feature activation-2.98e+00

Pos logit contributions
emetery+2.090
ospel+2.066
vernment+2.026
ppa+2.018
appa+1.921
Neg logit contributions
 Frie-2.569
spir-2.484
Male-2.350
 AAA-2.306
 UCHIJ-2.289
Token
Token ID198
Feature activation-2.97e+00

Pos logit contributions
emetery+2.162
ospel+2.151
ppa+2.099
vernment+2.095
appa+2.001
Neg logit contributions
 Frie-2.414
spir-2.302
Male-2.176
querque-2.158
 AAA-2.123
Token
Token ID198
Feature activation-3.04e+00

Pos logit contributions
ospel+2.069
ppa+2.039
emetery+2.010
vernment+1.969
 Kak+1.928
Neg logit contributions
 Frie-2.528
spir-2.351
querque-2.346
Male-2.222
 AAA-2.174
TokenI
Token ID40
Feature activation-3.14e+00

Pos logit contributions
emetery+2.434
ospel+2.433
ppa+2.394
vernment+2.369
appa+2.286
Neg logit contributions
 Frie-2.250
spir-2.098
querque-1.967
 AAA-1.964
Male-1.960
Token to
Token ID284
Feature activation+2.27e+00

Pos logit contributions
 Frie+1.450
spir+1.387
Male+1.306
 AAA+1.282
 UCHIJ+1.243
Neg logit contributions
emetery-1.665
ospel-1.647
vernment-1.603
ppa-1.596
appa-1.531
Token get
Token ID651
Feature activation+2.99e+00

Pos logit contributions
 Frie+1.697
spir+1.634
Male+1.537
 AAA+1.516
 UCHIJ+1.474
Neg logit contributions
emetery-1.828
ospel-1.795
vernment-1.749
ppa-1.733
appa-1.668
Token someone
Token ID2130
Feature activation+4.38e+00

Pos logit contributions
 Frie+2.170
spir+2.076
Male+1.959
 AAA+1.929
 UCHIJ+1.866
Neg logit contributions
emetery-2.473
ospel-2.445
vernment-2.371
ppa-2.348
appa-2.265
Token to
Token ID284
Feature activation-6.90e-01

Pos logit contributions
 Frie+3.072
spir+2.959
Male+2.782
 AAA+2.750
 UCHIJ+2.627
Neg logit contributions
emetery-3.736
ospel-3.690
vernment-3.550
ppa-3.502
appa-3.383
Token open
Token ID1280
Feature activation-6.81e-01

Pos logit contributions
emetery+0.483
ospel+0.479
vernment+0.468
ppa+0.467
appa+0.442
Neg logit contributions
 Frie-0.581
spir-0.560
Male-0.533
 AAA-0.519
 UCHIJ-0.513
Token up
Token ID510
Feature activation-7.15e+00

Pos logit contributions
emetery+0.581
ospel+0.574
vernment+0.562
ppa+0.560
appa+0.537
Neg logit contributions
 Frie-0.474
spir-0.455
Male-0.427
 AAA-0.417
 UCHIJ-0.405
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
emetery+4.846
vernment+4.775
ospel+4.772
ppa+4.745
 Kak+4.565
Neg logit contributions
 Frie-5.913
spir-5.578
Male-5.351
 UCHIJ-5.263
querque-5.210
Token It
Token ID632
Feature activation+7.14e-01

Pos logit contributions
 Frie+0.794
spir+0.761
Male+0.722
 AAA+0.707
 UCHIJ+0.690
Neg logit contributions
emetery-0.816
ospel-0.804
vernment-0.787
ppa-0.780
appa-0.748
Token
Token ID447
Feature activation+1.15e+00

Pos logit contributions
 Frie+0.593
spir+0.572
Male+0.544
 AAA+0.532
 UCHIJ+0.521
Neg logit contributions
emetery-0.514
ospel-0.506
vernment-0.491
ppa-0.489
appa-0.466
Token
Token ID247
Feature activation+1.04e+00

Pos logit contributions
 Frie+0.513
spir+0.480
Male+0.437
 AAA+0.417
 UCHIJ+0.401
Neg logit contributions
emetery-1.261
ospel-1.251
vernment-1.231
ppa-1.227
appa-1.186
Tokens
Token ID82
Feature activation+2.23e+00

Pos logit contributions
 Frie+0.717
spir+0.692
Male+0.647
 AAA+0.630
 UCHIJ+0.615
Neg logit contributions
emetery-0.891
ospel-0.880
vernment-0.860
ppa-0.857
appa-0.823
Token2
Token ID17
Feature activation-2.32e-01

Pos logit contributions
ospel+1.441
emetery+1.426
ppa+1.399
vernment+1.370
appa+1.316
Neg logit contributions
 Frie-2.304
spir-2.181
querque-2.098
Male-2.092
 AAA-2.071
Token)
Token ID8
Feature activation+1.82e+00

Pos logit contributions
emetery+0.155
ospel+0.154
ppa+0.150
vernment+0.149
appa+0.142
Neg logit contributions
 Frie-0.203
spir-0.196
Male-0.187
 AAA-0.182
querque-0.182
Token $
Token ID720
Feature activation-2.25e-01

Pos logit contributions
 Frie+1.197
spir+1.139
Male+1.065
 AAA+1.044
 UCHIJ+1.015
Neg logit contributions
emetery-1.629
ospel-1.613
vernment-1.580
ppa-1.574
appa-1.512
Tokenrect
Token ID2554
Feature activation-2.03e+00

Pos logit contributions
emetery+0.176
ospel+0.175
ppa+0.171
vernment+0.171
appa+0.163
Neg logit contributions
 Frie-0.171
spir-0.163
Male-0.155
 AAA-0.152
 UCHIJ-0.149
Token2
Token ID17
Feature activation+1.02e+00

Pos logit contributions
emetery+1.263
ospel+1.254
vernment+1.209
ppa+1.209
appa+1.146
Neg logit contributions
 Frie-1.878
spir-1.801
Male-1.721
 AAA-1.703
querque-1.680
Token =
Token ID796
Feature activation+5.83e+00

Pos logit contributions
 Frie+0.646
spir+0.618
Male+0.578
 AAA+0.561
 UCHIJ+0.547
Neg logit contributions
emetery-0.936
ospel-0.926
vernment-0.909
ppa-0.904
appa-0.870
Token New
Token ID968
Feature activation+2.97e+00

Pos logit contributions
 Frie+3.539
spir+3.342
 AAA+3.171
Male+3.161
 UCHIJ+3.084
Neg logit contributions
emetery-5.587
vernment-5.390
ospel-5.355
ppa-5.201
appa-5.077
Token-
Token ID12
Feature activation+3.03e+00

Pos logit contributions
 Frie+1.873
spir+1.828
Male+1.726
 AAA+1.674
 UCHIJ+1.620
Neg logit contributions
emetery-2.728
ospel-2.660
vernment-2.639
ppa-2.587
appa-2.499
TokenObject
Token ID10267
Feature activation+9.95e-01

Pos logit contributions
 Frie+2.178
spir+2.122
Male+2.028
 AAA+1.949
 UCHIJ+1.916
Neg logit contributions
emetery-2.499
ospel-2.459
vernment-2.422
ppa-2.397
appa-2.294
Token System
Token ID4482
Feature activation+8.36e-01

Pos logit contributions
 Frie+0.662
spir+0.631
Male+0.592
 AAA+0.572
querque+0.569
Neg logit contributions
emetery-0.872
ospel-0.869
vernment-0.850
ppa-0.847
appa-0.815
Token.
Token ID13
Feature activation+2.49e+00

Pos logit contributions
 Frie+0.626
spir+0.604
Male+0.572
 AAA+0.558
 UCHIJ+0.546
Neg logit contributions
emetery-0.669
ospel-0.658
vernment-0.646
ppa-0.641
appa-0.614
Token throne
Token ID19262
Feature activation+4.58e+00

Pos logit contributions
 Frie+1.684
spir+1.596
Male+1.505
 AAA+1.490
 UCHIJ+1.440
Neg logit contributions
emetery-2.056
ospel-2.025
vernment-1.981
ppa-1.977
appa-1.895
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
 Frie+3.274
spir+3.109
Male+2.967
 AAA+2.913
 UCHIJ+2.832
Neg logit contributions
emetery-3.753
ospel-3.737
vernment-3.617
ppa-3.579
appa-3.451
Token
Token ID198
Feature activation+9.67e-01

Pos logit contributions
 Frie+0.208
spir+0.200
Male+0.190
 AAA+0.186
 UCHIJ+0.183
Neg logit contributions
emetery-0.191
ospel-0.189
vernment-0.184
ppa-0.183
appa-0.175
Token
Token ID198
Feature activation-3.10e-01

Pos logit contributions
 Frie+0.719
spir+0.698
Male+0.660
 AAA+0.645
 UCHIJ+0.629
Neg logit contributions
emetery-0.779
ospel-0.764
vernment-0.751
ppa-0.742
appa-0.712
TokenSee
Token ID6214
Feature activation-9.76e-01

Pos logit contributions
emetery+0.216
ospel+0.214
ppa+0.209
vernment+0.208
appa+0.198
Neg logit contributions
 Frie-0.263
spir-0.253
Male-0.238
 AAA-0.236
querque-0.233
Token also
Token ID635
Feature activation+6.22e+00

Pos logit contributions
emetery+0.689
ospel+0.681
ppa+0.665
vernment+0.665
appa+0.631
Neg logit contributions
 Frie-0.815
spir-0.790
Male-0.749
 AAA-0.732
querque-0.721
Token [
Token ID685
Feature activation-9.90e-02

Pos logit contributions
 Frie+4.399
spir+4.121
Male+3.906
 AAA+3.878
 UCHIJ+3.731
Neg logit contributions
ospel-5.123
emetery-5.097
vernment-5.003
ppa-4.830
appa-4.694
Token edit
Token ID4370
Feature activation+2.86e-01

Pos logit contributions
emetery+0.072
ospel+0.072
ppa+0.070
vernment+0.070
appa+0.067
Neg logit contributions
 Frie-0.081
spir-0.077
Male-0.073
 AAA-0.072
querque-0.071
Token ]
Token ID2361
Feature activation-2.36e+00

Pos logit contributions
 Frie+0.217
spir+0.209
Male+0.197
 AAA+0.193
querque+0.189
Neg logit contributions
emetery-0.225
ospel-0.223
vernment-0.217
ppa-0.217
appa-0.207
Token
Token ID198
Feature activation-7.17e-01

Pos logit contributions
emetery+1.877
ospel+1.843
ppa+1.811
vernment+1.804
appa+1.728
Neg logit contributions
 Frie-1.777
spir-1.704
Male-1.607
 AAA-1.567
querque-1.546
Token
Token ID198
Feature activation-1.02e+00

Pos logit contributions
emetery+0.537
ospel+0.536
ppa+0.525
vernment+0.519
appa+0.499
Neg logit contributions
 Frie-0.570
spir-0.541
Male-0.511
querque-0.508
 AAA-0.500
Token is
Token ID318
Feature activation+4.72e-01

Pos logit contributions
 Frie+2.014
spir+1.934
Male+1.819
 AAA+1.780
 UCHIJ+1.722
Neg logit contributions
emetery-2.260
ospel-2.230
ppa-2.154
vernment-2.153
appa-2.066
Token gaining
Token ID13977
Feature activation-2.27e+00

Pos logit contributions
 Frie+0.371
spir+0.357
Male+0.338
 AAA+0.331
 UCHIJ+0.325
Neg logit contributions
emetery-0.359
ospel-0.355
vernment-0.346
ppa-0.345
appa-0.329
Token ground
Token ID2323
Feature activation+2.91e-01

Pos logit contributions
emetery+1.791
ospel+1.770
vernment+1.736
ppa+1.732
appa+1.649
Neg logit contributions
 Frie-1.710
spir-1.646
Male-1.553
querque-1.505
 AAA-1.505
Token in
Token ID287
Feature activation-3.58e-01

Pos logit contributions
 Frie+0.218
spir+0.209
Male+0.198
 AAA+0.193
 UCHIJ+0.188
Neg logit contributions
emetery-0.233
ospel-0.231
vernment-0.225
ppa-0.224
appa-0.215
Token the
Token ID262
Feature activation+2.09e-01

Pos logit contributions
emetery+0.261
ospel+0.258
vernment+0.251
ppa+0.250
appa+0.238
Neg logit contributions
 Frie-0.294
spir-0.282
Male-0.268
 AAA-0.263
 UCHIJ-0.258
Token race
Token ID3234
Feature activation+6.37e+00

Pos logit contributions
 Frie+0.171
spir+0.164
Male+0.156
 AAA+0.153
 UCHIJ+0.150
Neg logit contributions
emetery-0.153
ospel-0.151
vernment-0.147
ppa-0.146
appa-0.139
Token.
Token ID13
Feature activation+5.61e-01

Pos logit contributions
 Frie+4.465
spir+4.211
Male+3.952
 AAA+3.879
 UCHIJ+3.649
Neg logit contributions
emetery-5.372
ospel-5.303
ppa-5.049
vernment-4.983
appa-4.842
Token
Token ID198
Feature activation+1.89e-01

Pos logit contributions
 Frie+0.437
spir+0.421
Male+0.398
 AAA+0.390
 UCHIJ+0.382
Neg logit contributions
emetery-0.431
ospel-0.426
vernment-0.416
ppa-0.414
appa-0.395
Token
Token ID198
Feature activation+3.14e-01

Pos logit contributions
 Frie+0.144
spir+0.139
Male+0.131
 AAA+0.128
 UCHIJ+0.126
Neg logit contributions
emetery-0.149
ospel-0.147
vernment-0.144
ppa-0.143
appa-0.137
Token
Token ID447
Feature activation-7.46e-01

Pos logit contributions
 Frie+0.232
spir+0.223
Male+0.210
 AAA+0.205
 UCHIJ+0.201
Neg logit contributions
emetery-0.253
ospel-0.251
vernment-0.245
ppa-0.244
appa-0.234
Token
Token ID250
Feature activation-1.08e+00

Pos logit contributions
emetery+0.679
ospel+0.673
ppa+0.661
vernment+0.661
appa+0.636
Neg logit contributions
 Frie-0.473
spir-0.451
Male-0.420
 AAA-0.409
 UCHIJ-0.401
Token attorneys
Token ID14449
Feature activation-2.18e+00

Pos logit contributions
emetery+3.047
ospel+3.023
vernment+2.964
ppa+2.960
appa+2.847
Neg logit contributions
 Frie-3.723
spir-3.561
Male-3.404
 UCHIJ-3.312
querque-3.264
Token general
Token ID2276
Feature activation-6.20e-01

Pos logit contributions
emetery+1.773
ospel+1.757
vernment+1.723
ppa+1.717
appa+1.652
Neg logit contributions
 Frie-1.580
spir-1.512
Male-1.421
 AAA-1.376
querque-1.373
Token to
Token ID284
Feature activation+8.01e-01

Pos logit contributions
emetery+0.494
ospel+0.489
vernment+0.478
ppa+0.477
appa+0.457
Neg logit contributions
 Frie-0.464
spir-0.446
Male-0.421
 AAA-0.411
 UCHIJ-0.403
Token oppose
Token ID12856
Feature activation+2.19e+00

Pos logit contributions
 Frie+0.602
spir+0.577
Male+0.545
 AAA+0.538
 UCHIJ+0.523
Neg logit contributions
emetery-0.643
ospel-0.633
vernment-0.615
ppa-0.612
appa-0.585
Token the
Token ID262
Feature activation-5.61e-01

Pos logit contributions
 Frie+1.704
spir+1.627
Male+1.548
 AAA+1.537
 UCHIJ+1.490
Neg logit contributions
emetery-1.686
ospel-1.664
ppa-1.617
vernment-1.613
appa-1.536
Token confirmation
Token ID12641
Feature activation+5.81e+00

Pos logit contributions
emetery+0.410
ospel+0.407
vernment+0.397
ppa+0.395
appa+0.379
Neg logit contributions
 Frie-0.456
spir-0.440
Male-0.417
 AAA-0.404
 UCHIJ-0.400
Token of
Token ID286
Feature activation-7.97e-02

Pos logit contributions
 Frie+4.139
spir+3.965
Male+3.726
 AAA+3.681
querque+3.514
Neg logit contributions
emetery-4.741
ospel-4.673
vernment-4.543
ppa-4.505
jri-4.288
Token Mer
Token ID4638
Feature activation-9.82e-01

Pos logit contributions
emetery+0.058
ospel+0.058
vernment+0.056
ppa+0.056
appa+0.053
Neg logit contributions
 Frie-0.065
spir-0.063
Male-0.059
 AAA-0.058
 UCHIJ-0.057
Tokenrick
Token ID5557
Feature activation+2.05e+00

Pos logit contributions
emetery+0.646
ospel+0.638
ppa+0.620
vernment+0.615
appa+0.591
Neg logit contributions
 Frie-0.872
spir-0.839
Male-0.804
 AAA-0.786
 UCHIJ-0.775
Token Garland
Token ID35466
Feature activation+3.12e+00

Pos logit contributions
 Frie+1.743
spir+1.666
Male+1.590
 AAA+1.567
 UCHIJ+1.539
Neg logit contributions
emetery-1.435
ospel-1.422
vernment-1.377
ppa-1.368
appa-1.297
Token to
Token ID284
Feature activation+3.33e+00

Pos logit contributions
 Frie+2.367
spir+2.261
Male+2.154
 AAA+2.098
 UCHIJ+2.053
Neg logit contributions
emetery-2.462
ospel-2.438
ppa-2.364
vernment-2.358
appa-2.244
Tokeniji
Token ID20770
Feature activation-1.43e+00

Pos logit contributions
emetery+1.556
ospel+1.547
ppa+1.511
vernment+1.510
appa+1.453
Neg logit contributions
 Frie-1.357
spir-1.298
Male-1.218
 AAA-1.187
querque-1.179
Token Press
Token ID4332
Feature activation+2.56e+00

Pos logit contributions
emetery+0.960
ospel+0.951
vernment+0.933
ppa+0.925
 Kak+0.883
Neg logit contributions
 Frie-1.242
spir-1.202
Male-1.144
 AAA-1.116
 UCHIJ-1.103
Token,
Token ID11
Feature activation+2.33e-01

Pos logit contributions
 Frie+1.998
spir+1.930
Male+1.829
 AAA+1.796
 UCHIJ+1.746
Neg logit contributions
emetery-1.950
ospel-1.922
vernment-1.870
ppa-1.864
appa-1.776
Token AFP
Token ID8916
Feature activation+1.08e+00

Pos logit contributions
 Frie+0.185
spir+0.178
Male+0.168
 AAA+0.164
querque+0.162
Neg logit contributions
emetery-0.176
ospel-0.174
vernment-0.170
ppa-0.169
appa-0.161
Token/
Token ID14
Feature activation+4.02e+00

Pos logit contributions
 Frie+0.832
spir+0.802
Male+0.761
 AAA+0.744
 UCHIJ+0.726
Neg logit contributions
emetery-0.837
ospel-0.827
vernment-0.807
ppa-0.805
appa-0.770
TokenGetty
Token ID6633
Feature activation+6.43e+00

Pos logit contributions
 Frie+2.135
spir+2.065
Male+1.939
 AAA+1.833
 UCHIJ+1.762
Neg logit contributions
emetery-4.030
ospel-3.988
ppa-3.904
vernment-3.867
appa-3.763
Token Images
Token ID5382
Feature activation+4.84e+00

Pos logit contributions
 Frie+3.390
spir+3.305
Male+3.131
 AAA+2.933
 UCHIJ+2.867
Neg logit contributions
emetery-6.322
ospel-6.233
ppa-6.136
vernment-6.058
appa-5.897
Token)
Token ID8
Feature activation+1.52e+00

Pos logit contributions
 Frie+3.844
spir+3.744
Male+3.595
 AAA+3.536
 UCHIJ+3.404
Neg logit contributions
emetery-3.497
ospel-3.468
ppa-3.351
vernment-3.347
appa-3.175
Token
Token ID198
Feature activation-2.45e+00

Pos logit contributions
 Frie+1.130
spir+1.091
Male+1.032
 AAA+1.011
 UCHIJ+0.987
Neg logit contributions
emetery-1.220
ospel-1.208
vernment-1.180
ppa-1.174
appa-1.120
Token
Token ID198
Feature activation-2.68e+00

Pos logit contributions
ospel+1.746
ppa+1.715
emetery+1.714
vernment+1.664
appa+1.625
Neg logit contributions
 Frie-2.052
spir-1.918
querque-1.884
Male-1.813
 AAA-1.777
TokenA
Token ID32
Feature activation+4.84e-01

Pos logit contributions
emetery+2.215
ospel+2.203
ppa+2.183
vernment+2.170
appa+2.081
Neg logit contributions
 Frie-1.921
spir-1.775
querque-1.678
 AAA-1.663
Male-1.639
Token,
Token ID11
Feature activation-4.87e-01

Pos logit contributions
 Frie+0.671
spir+0.645
Male+0.616
 AAA+0.608
 UCHIJ+0.590
Neg logit contributions
emetery-0.623
ospel-0.612
vernment-0.598
ppa-0.595
appa-0.566
Token access
Token ID1895
Feature activation+1.01e+00

Pos logit contributions
emetery+0.347
ospel+0.343
vernment+0.335
ppa+0.334
appa+0.317
Neg logit contributions
 Frie-0.405
spir-0.391
Male-0.371
 AAA-0.363
 UCHIJ-0.357
Token to
Token ID284
Feature activation-7.27e-01

Pos logit contributions
 Frie+0.717
spir+0.685
Male+0.646
 AAA+0.634
 UCHIJ+0.616
Neg logit contributions
emetery-0.849
ospel-0.841
ppa-0.820
vernment-0.819
appa-0.786
Token Kindle
Token ID27114
Feature activation-1.94e+00

Pos logit contributions
emetery+0.546
ospel+0.540
vernment+0.529
ppa+0.527
appa+0.503
Neg logit contributions
 Frie-0.576
spir-0.556
Male-0.526
 AAA-0.511
querque-0.505
Token Owners
Token ID33147
Feature activation+1.15e+00

Pos logit contributions
emetery+1.549
ospel+1.537
ppa+1.506
vernment+1.505
appa+1.441
Neg logit contributions
 Frie-1.441
spir-1.382
Male-1.297
 AAA-1.257
querque-1.250
Token
Token ID447
Feature activation+1.96e+00

Pos logit contributions
 Frie+0.826
spir+0.791
Male+0.748
 AAA+0.734
 UCHIJ+0.713
Neg logit contributions
emetery-0.954
ospel-0.943
vernment-0.922
ppa-0.917
appa-0.880
Token
Token ID247
Feature activation+1.56e+00

Pos logit contributions
 Frie+0.981
spir+0.923
Male+0.846
 AAA+0.815
 UCHIJ+0.786
Neg logit contributions
emetery-2.054
ospel-2.042
vernment-2.005
ppa-1.996
appa-1.928
Token L
Token ID406
Feature activation-2.16e-01

Pos logit contributions
 Frie+1.070
spir+1.038
Male+0.971
 AAA+0.957
 UCHIJ+0.921
Neg logit contributions
emetery-1.329
ospel-1.311
vernment-1.278
ppa-1.272
appa-1.226
Tokenending
Token ID1571
Feature activation+1.68e-01

Pos logit contributions
emetery+0.179
ospel+0.177
vernment+0.173
ppa+0.173
appa+0.165
Neg logit contributions
 Frie-0.155
spir-0.148
Male-0.140
 AAA-0.136
 UCHIJ-0.133
Token Library
Token ID10074
Feature activation-1.73e-01

Pos logit contributions
 Frie+0.121
spir+0.116
Male+0.109
 AAA+0.107
 UCHIJ+0.104
Neg logit contributions
emetery-0.139
ospel-0.138
vernment-0.135
ppa-0.135
appa-0.129
Token,
Token ID11
Feature activation-9.42e-02

Pos logit contributions
emetery+0.126
ospel+0.125
vernment+0.122
ppa+0.121
appa+0.115
Neg logit contributions
 Frie-0.142
spir-0.137
Male-0.130
 AAA-0.127
 UCHIJ-0.125
Token Korean
Token ID6983
Feature activation-2.83e+00

Pos logit contributions
emetery+0.226
ospel+0.223
vernment+0.217
ppa+0.216
appa+0.205
Neg logit contributions
 Frie-0.295
spir-0.285
Male-0.272
 AAA-0.266
 UCHIJ-0.262
Token retaliation
Token ID24671
Feature activation-5.88e-01

Pos logit contributions
emetery+2.270
ospel+2.246
vernment+2.205
ppa+2.196
appa+2.101
Neg logit contributions
 Frie-2.108
spir-2.013
Male-1.893
 AAA-1.840
querque-1.825
Token towards
Token ID3371
Feature activation-1.25e+00

Pos logit contributions
emetery+0.463
ospel+0.457
vernment+0.448
ppa+0.447
appa+0.427
Neg logit contributions
 Frie-0.447
spir-0.429
Male-0.406
 AAA-0.396
 UCHIJ-0.389
Token Sony
Token ID10184
Feature activation+4.50e-01

Pos logit contributions
emetery+0.941
ospel+0.931
vernment+0.910
ppa+0.908
appa+0.866
Neg logit contributions
 Frie-0.992
spir-0.956
Male-0.906
 AAA-0.881
querque-0.870
Token surfaced
Token ID23786
Feature activation+2.89e+00

Pos logit contributions
 Frie+0.348
spir+0.335
Male+0.318
 AAA+0.312
 UCHIJ+0.304
Neg logit contributions
emetery-0.349
ospel-0.346
vernment-0.336
ppa-0.335
appa-0.319
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
 Frie+2.253
spir+2.160
Male+2.051
 AAA+2.040
 UCHIJ+1.956
Neg logit contributions
emetery-2.219
ospel-2.198
vernment-2.127
ppa-2.102
appa-2.012
Token
Token ID198
Feature activation+4.94e-01

Pos logit contributions
 Frie+1.007
spir+0.971
Male+0.921
 AAA+0.905
 UCHIJ+0.880
Neg logit contributions
emetery-1.013
ospel-0.996
vernment-0.973
ppa-0.964
appa-0.926
Token
Token ID198
Feature activation+4.58e-01

Pos logit contributions
 Frie+0.368
spir+0.356
Male+0.337
 AAA+0.328
 UCHIJ+0.321
Neg logit contributions
emetery-0.396
ospel-0.391
vernment-0.383
ppa-0.380
appa-0.364
TokenIf
Token ID1532
Feature activation+4.88e-01

Pos logit contributions
 Frie+0.314
spir+0.303
Male+0.285
 AAA+0.276
 UCHIJ+0.269
Neg logit contributions
emetery-0.395
ospel-0.390
vernment-0.383
ppa-0.380
appa-0.365
Token you
Token ID345
Feature activation-9.40e-01

Pos logit contributions
 Frie+0.347
spir+0.332
Male+0.313
 AAA+0.306
 UCHIJ+0.298
Neg logit contributions
emetery-0.408
ospel-0.404
vernment-0.395
ppa-0.394
appa-0.377
Token aren
Token ID3588
Feature activation-1.72e+00

Pos logit contributions
emetery+0.752
ospel+0.745
vernment+0.731
ppa+0.729
appa+0.696
Neg logit contributions
 Frie-0.699
spir-0.670
Male-0.634
 AAA-0.616
querque-0.606
Token people
Token ID661
Feature activation+2.06e+00

Pos logit contributions
 Frie+0.834
spir+0.799
Male+0.752
 AAA+0.739
 UCHIJ+0.720
Neg logit contributions
emetery-0.909
ospel-0.901
vernment-0.876
ppa-0.875
appa-0.839
Token have
Token ID423
Feature activation-2.23e-01

Pos logit contributions
 Frie+1.567
spir+1.503
Male+1.404
 AAA+1.391
 UCHIJ+1.347
Neg logit contributions
emetery-1.635
ospel-1.621
ppa-1.563
vernment-1.562
appa-1.487
Token visited
Token ID8672
Feature activation+1.64e+00

Pos logit contributions
emetery+0.194
ospel+0.192
vernment+0.189
ppa+0.188
appa+0.181
Neg logit contributions
 Frie-0.150
spir-0.143
Male-0.135
 AAA-0.131
 UCHIJ-0.128
Token since
Token ID1201
Feature activation-1.06e+00

Pos logit contributions
 Frie+1.356
spir+1.297
Male+1.232
 AAA+1.214
 UCHIJ+1.186
Neg logit contributions
emetery-1.185
ospel-1.180
ppa-1.138
vernment-1.135
appa-1.084
Token it
Token ID340
Feature activation-9.27e-02

Pos logit contributions
emetery+0.756
ospel+0.747
vernment+0.729
ppa+0.726
appa+0.691
Neg logit contributions
 Frie-0.887
spir-0.856
Male-0.814
 AAA-0.795
querque-0.782
Token opened
Token ID4721
Feature activation+2.61e+00

Pos logit contributions
emetery+0.074
ospel+0.073
ppa+0.072
vernment+0.072
appa+0.068
Neg logit contributions
 Frie-0.069
spir-0.066
Male-0.063
 AAA-0.061
 UCHIJ-0.060
Token,
Token ID11
Feature activation+1.51e-01

Pos logit contributions
 Frie+1.907
spir+1.818
Male+1.715
 AAA+1.692
 UCHIJ+1.639
Neg logit contributions
emetery-2.147
ospel-2.136
vernment-2.071
ppa-2.059
appa-1.970
Token Lee
Token ID5741
Feature activation-5.07e+00

Pos logit contributions
 Frie+0.119
spir+0.114
Male+0.108
 AAA+0.106
 UCHIJ+0.103
Neg logit contributions
emetery-0.115
ospel-0.115
vernment-0.111
ppa-0.111
appa-0.106
Token said
Token ID531
Feature activation+6.75e-01

Pos logit contributions
ppa+3.119
ospel+3.114
emetery+3.093
vernment+3.055
 Kak+2.940
Neg logit contributions
 Frie-4.481
spir-4.407
Male-4.211
 AAA-4.097
querque-4.083
Token.
Token ID13
Feature activation+1.39e+00

Pos logit contributions
 Frie+0.526
spir+0.506
Male+0.479
 AAA+0.469
 UCHIJ+0.460
Neg logit contributions
emetery-0.517
ospel-0.512
vernment-0.500
ppa-0.498
appa-0.476
Token
Token ID198
Feature activation+9.58e-01

Pos logit contributions
 Frie+1.051
spir+1.006
Male+0.948
 AAA+0.932
 UCHIJ+0.905
Neg logit contributions
emetery-1.121
ospel-1.105
vernment-1.076
ppa-1.072
appa-1.032
Token won
Token ID1839
Feature activation+3.13e+00

Pos logit contributions
 Frie+0.987
spir+0.948
Male+0.896
 AAA+0.879
 UCHIJ+0.859
Neg logit contributions
emetery-1.026
ospel-1.014
vernment-0.988
ppa-0.987
appa-0.944
Token,
Token ID11
Feature activation+1.76e+00

Pos logit contributions
 Frie+2.403
spir+2.295
Male+2.186
 AAA+2.170
 UCHIJ+2.094
Neg logit contributions
emetery-2.443
ospel-2.409
ppa-2.331
vernment-2.321
appa-2.253
Token but
Token ID475
Feature activation+1.80e+00

Pos logit contributions
 Frie+1.448
spir+1.391
Male+1.326
 AAA+1.303
 UCHIJ+1.267
Neg logit contributions
emetery-1.285
ospel-1.268
ppa-1.231
vernment-1.230
appa-1.173
Token there
Token ID612
Feature activation-7.95e-01

Pos logit contributions
 Frie+1.378
spir+1.314
Male+1.245
 AAA+1.234
 UCHIJ+1.189
Neg logit contributions
emetery-1.421
ospel-1.401
ppa-1.362
vernment-1.362
appa-1.304
Token will
Token ID481
Feature activation-9.18e-01

Pos logit contributions
emetery+0.626
ospel+0.620
vernment+0.607
ppa+0.605
appa+0.578
Neg logit contributions
 Frie-0.602
spir-0.579
Male-0.547
 AAA-0.534
 UCHIJ-0.524
Token also
Token ID635
Feature activation+1.35e+00

Pos logit contributions
emetery+0.848
ospel+0.842
vernment+0.826
ppa+0.826
appa+0.793
Neg logit contributions
 Frie-0.568
spir-0.541
Male-0.504
 AAA-0.488
querque-0.480
Token be
Token ID307
Feature activation-6.00e-01

Pos logit contributions
 Frie+0.761
spir+0.719
Male+0.667
 AAA+0.647
 UCHIJ+0.624
Neg logit contributions
emetery-1.327
ospel-1.315
vernment-1.287
ppa-1.285
appa-1.242
Token a
Token ID257
Feature activation+2.96e-01

Pos logit contributions
emetery+0.452
ospel+0.447
vernment+0.436
ppa+0.435
appa+0.415
Neg logit contributions
 Frie-0.476
spir-0.459
Male-0.435
 AAA-0.425
 UCHIJ-0.417
Token ton
Token ID5680
Feature activation+1.84e+00

Pos logit contributions
 Frie+0.211
spir+0.202
Male+0.190
 AAA+0.186
 UCHIJ+0.182
Neg logit contributions
emetery-0.248
ospel-0.245
vernment-0.240
ppa-0.239
appa-0.229
Token of
Token ID286
Feature activation-6.97e-01

Pos logit contributions
 Frie+1.392
spir+1.352
Male+1.270
 AAA+1.245
 UCHIJ+1.211
Neg logit contributions
emetery-1.444
ospel-1.422
vernment-1.388
ppa-1.383
appa-1.331
Token pressure
Token ID3833
Feature activation+4.68e-02

Pos logit contributions
emetery+0.527
ospel+0.521
vernment+0.509
ppa+0.507
appa+0.483
Neg logit contributions
 Frie-0.552
spir-0.531
Male-0.503
 AAA-0.492
 UCHIJ-0.483
Token easy
Token ID2562
Feature activation-2.01e-01

Pos logit contributions
emetery+0.463
ospel+0.458
vernment+0.444
ppa+0.443
appa+0.419
Neg logit contributions
 Frie-0.704
spir-0.680
Male-0.649
 AAA-0.637
 UCHIJ-0.629
Token to
Token ID284
Feature activation+1.24e-01

Pos logit contributions
emetery+0.165
ospel+0.163
vernment+0.159
ppa+0.159
appa+0.152
Neg logit contributions
 Frie-0.146
spir-0.140
Male-0.132
 AAA-0.129
 UCHIJ-0.126
Token respond
Token ID3031
Feature activation+2.40e-01

Pos logit contributions
 Frie+0.095
spir+0.092
Male+0.087
 AAA+0.085
 UCHIJ+0.083
Neg logit contributions
emetery-0.096
ospel-0.095
vernment-0.093
ppa-0.092
appa-0.088
Token to
Token ID284
Feature activation-7.94e-01

Pos logit contributions
 Frie+0.179
spir+0.172
Male+0.163
 AAA+0.159
 UCHIJ+0.155
Neg logit contributions
emetery-0.192
ospel-0.190
vernment-0.186
ppa-0.185
appa-0.177
Token this
Token ID428
Feature activation+8.03e-02

Pos logit contributions
emetery+0.584
ospel+0.578
vernment+0.564
ppa+0.562
appa+0.537
Neg logit contributions
 Frie-0.643
spir-0.619
Male-0.587
 AAA-0.574
querque-0.565
Token woman
Token ID2415
Feature activation+1.71e+00

Pos logit contributions
 Frie+0.065
spir+0.063
Male+0.060
 AAA+0.059
 UCHIJ+0.057
Neg logit contributions
emetery-0.059
ospel-0.059
vernment-0.057
ppa-0.057
appa-0.054
Token with
Token ID351
Feature activation-1.25e+00

Pos logit contributions
 Frie+1.292
spir+1.251
Male+1.176
 AAA+1.149
 UCHIJ+1.114
Neg logit contributions
emetery-1.371
ospel-1.350
vernment-1.310
ppa-1.304
appa-1.246
Token sentimental
Token ID46908
Feature activation-1.26e+00

Pos logit contributions
emetery+0.892
ospel+0.884
vernment+0.860
ppa+0.857
appa+0.817
Neg logit contributions
 Frie-1.031
spir-0.994
Male-0.944
 AAA-0.923
 UCHIJ-0.910
Token plat
Token ID40315
Feature activation+4.76e-01

Pos logit contributions
emetery+0.931
ospel+0.922
vernment+0.899
ppa+0.896
appa+0.854
Neg logit contributions
 Frie-1.019
spir-0.980
Male-0.931
 AAA-0.909
 UCHIJ-0.896
Tokenitudes
Token ID10455
Feature activation-8.47e-01

Pos logit contributions
 Frie+0.449
spir+0.436
Male+0.416
 AAA+0.409
 UCHIJ+0.402
Neg logit contributions
emetery-0.287
ospel-0.283
vernment-0.275
ppa-0.274
appa-0.258
Token,
Token ID11
Feature activation+9.08e-01

Pos logit contributions
emetery+0.636
ospel+0.629
vernment+0.614
ppa+0.612
appa+0.584
Neg logit contributions
 Frie-0.675
spir-0.649
Male-0.615
 AAA-0.602
 UCHIJ-0.591
Token the
Token ID262
Feature activation-1.07e+00

Pos logit contributions
emetery+1.848
ospel+1.822
ppa+1.792
vernment+1.791
 Kak+1.723
Neg logit contributions
 Frie-2.040
spir-1.968
Male-1.871
querque-1.802
 UCHIJ-1.792
Token only
Token ID691
Feature activation+9.21e-01

Pos logit contributions
emetery+0.617
ospel+0.608
vernment+0.589
ppa+0.587
appa+0.551
Neg logit contributions
 Frie-1.034
spir-1.003
Male-0.960
 AAA-0.943
 UCHIJ-0.928
Token workers
Token ID3259
Feature activation+1.64e+00

Pos logit contributions
 Frie+0.794
spir+0.765
Male+0.729
 AAA+0.717
 UCHIJ+0.702
Neg logit contributions
emetery-0.633
ospel-0.626
vernment-0.608
ppa-0.605
appa-0.575
Token getting
Token ID1972
Feature activation+1.65e+00

Pos logit contributions
 Frie+1.241
spir+1.186
Male+1.120
 AAA+1.105
 UCHIJ+1.076
Neg logit contributions
emetery-1.300
ospel-1.293
vernment-1.257
ppa-1.248
appa-1.193
Token extra
Token ID3131
Feature activation+1.54e+00

Pos logit contributions
 Frie+1.283
spir+1.230
Male+1.164
 AAA+1.153
 UCHIJ+1.120
Neg logit contributions
emetery-1.268
ospel-1.255
vernment-1.219
ppa-1.214
appa-1.164
Token benefits
Token ID4034
Feature activation+8.21e-01

Pos logit contributions
 Frie+1.192
spir+1.145
Male+1.084
 AAA+1.069
 UCHIJ+1.039
Neg logit contributions
emetery-1.195
ospel-1.183
vernment-1.152
ppa-1.146
appa-1.096
Token for
Token ID329
Feature activation+2.08e+00

Pos logit contributions
 Frie+0.627
spir+0.603
Male+0.570
 AAA+0.557
 UCHIJ+0.546
Neg logit contributions
emetery-0.643
ospel-0.636
vernment-0.622
ppa-0.620
appa-0.592
Token tough
Token ID5802
Feature activation+6.21e-01

Pos logit contributions
 Frie+1.584
spir+1.524
Male+1.435
 AAA+1.425
 UCHIJ+1.374
Neg logit contributions
emetery-1.630
ospel-1.616
vernment-1.566
ppa-1.565
appa-1.496
Token conditions
Token ID3403
Feature activation+7.82e-02

Pos logit contributions
 Frie+0.450
spir+0.432
Male+0.406
 AAA+0.400
 UCHIJ+0.388
Neg logit contributions
emetery-0.512
ospel-0.507
vernment-0.495
ppa-0.494
appa-0.473
Token.
Token ID13
Feature activation+1.85e+00

Pos logit contributions
 Frie+0.061
spir+0.059
Male+0.056
 AAA+0.054
querque+0.054
Neg logit contributions
emetery-0.060
ospel-0.059
vernment-0.058
ppa-0.058
appa-0.055
Token
Token ID198
Feature activation+1.01e+00

Pos logit contributions
 Frie+1.439
spir+1.384
Male+1.310
 AAA+1.281
 UCHIJ+1.256
Neg logit contributions
emetery-1.417
ospel-1.401
vernment-1.368
ppa-1.364
appa-1.302
Token the
Token ID262
Feature activation-4.70e-01

Pos logit contributions
emetery+1.231
ospel+1.219
vernment+1.190
ppa+1.186
appa+1.130
Neg logit contributions
 Frie-1.371
spir-1.324
Male-1.255
 AAA-1.215
querque-1.208
Token first
Token ID717
Feature activation-9.86e-01

Pos logit contributions
emetery+0.342
ospel+0.340
vernment+0.331
ppa+0.330
appa+0.315
Neg logit contributions
 Frie-0.382
spir-0.369
Male-0.350
 AAA-0.340
querque-0.336
Token water
Token ID1660
Feature activation-2.15e+00

Pos logit contributions
emetery+0.787
ospel+0.781
vernment+0.767
ppa+0.765
appa+0.728
Neg logit contributions
 Frie-0.733
spir-0.706
Male-0.663
 AAA-0.643
querque-0.638
Token,
Token ID11
Feature activation-1.73e+00

Pos logit contributions
emetery+1.647
ospel+1.645
ppa+1.619
vernment+1.602
 Kak+1.538
Neg logit contributions
 Frie-1.634
spir-1.580
Male-1.508
querque-1.444
 AAA-1.440
Token an
Token ID281
Feature activation-1.89e+00

Pos logit contributions
emetery+1.232
ospel+1.214
vernment+1.185
ppa+1.176
appa+1.118
Neg logit contributions
 Frie-1.434
spir-1.383
Male-1.316
querque-1.272
 AAA-1.269
Token enormous
Token ID9812
Feature activation-4.76e-01

Pos logit contributions
emetery+1.385
ospel+1.372
vernment+1.339
ppa+1.328
appa+1.275
Neg logit contributions
 Frie-1.528
spir-1.475
Male-1.401
 AAA-1.353
querque-1.341
Token White
Token ID2635
Feature activation+7.16e-01

Pos logit contributions
emetery+0.343
ospel+0.340
vernment+0.332
ppa+0.330
appa+0.314
Neg logit contributions
 Frie-0.393
spir-0.379
Male-0.360
 AAA-0.350
 UCHIJ-0.345
Token Elephant
Token ID42651
Feature activation-2.13e+00

Pos logit contributions
 Frie+0.681
spir+0.659
Male+0.632
 AAA+0.621
 UCHIJ+0.610
Neg logit contributions
emetery-0.428
ospel-0.421
vernment-0.408
ppa-0.406
appa-0.382
Token,
Token ID11
Feature activation-1.40e+00

Pos logit contributions
emetery+1.602
ospel+1.593
vernment+1.564
ppa+1.555
 Kak+1.486
Neg logit contributions
 Frie-1.657
spir-1.598
Male-1.516
querque-1.466
 AAA-1.462
Token completely
Token ID3190
Feature activation+6.73e-01

Pos logit contributions
emetery+1.054
ospel+1.044
vernment+1.025
ppa+1.019
appa+0.973
Neg logit contributions
 Frie-1.099
spir-1.062
Male-1.005
 AAA-0.971
querque-0.971
Token unnecessary
Token ID13114
Feature activation+8.17e-01

Pos logit contributions
 Frie+0.524
spir+0.504
Male+0.477
 AAA+0.463
querque+0.458
Neg logit contributions
emetery-0.514
ospel-0.510
vernment-0.500
ppa-0.497
appa-0.475
Tokenstanding
Token ID5646
Feature activation+8.96e-01

Pos logit contributions
 Frie+1.511
spir+1.472
Male+1.410
 AAA+1.371
 UCHIJ+1.337
Neg logit contributions
emetery-1.214
ospel-1.205
vernment-1.183
ppa-1.173
appa-1.099
Token Actor
Token ID27274
Feature activation+6.25e+00

Pos logit contributions
 Frie+0.537
spir+0.513
Male+0.473
 AAA+0.458
querque+0.450
Neg logit contributions
emetery-0.845
ospel-0.839
vernment-0.823
ppa-0.821
appa-0.791
Token in
Token ID287
Feature activation+2.26e+00

Pos logit contributions
 Frie+4.149
spir+3.958
Male+3.847
 AAA+3.772
 UCHIJ+3.626
Neg logit contributions
emetery-5.327
ospel-5.261
ppa-5.131
vernment-5.094
jri-4.873
Token a
Token ID257
Feature activation-6.76e-02

Pos logit contributions
 Frie+1.700
spir+1.625
Male+1.543
 AAA+1.517
 UCHIJ+1.474
Neg logit contributions
emetery-1.799
ospel-1.779
ppa-1.734
vernment-1.732
appa-1.657
Token Comedy
Token ID22329
Feature activation+2.73e+00

Pos logit contributions
emetery+0.063
ospel+0.063
vernment+0.063
ppa+0.062
 Kak+0.060
Neg logit contributions
 Frie-0.040
spir-0.039
Male-0.035
querque-0.034
 UCHIJ-0.034
Token in
Token ID287
Feature activation-2.93e-01

Pos logit contributions
 Frie+2.182
spir+2.100
Male+1.999
 AAA+1.961
 UCHIJ+1.916
Neg logit contributions
emetery-2.039
ospel-2.019
vernment-1.961
ppa-1.949
appa-1.861
Token Emmy
Token ID33953
Feature activation+3.97e+00

Pos logit contributions
emetery+0.218
ospel+0.215
vernment+0.211
ppa+0.209
appa+0.200
Neg logit contributions
 Frie-0.235
spir-0.228
Male-0.215
 AAA-0.208
 UCHIJ-0.207
Token history
Token ID2106
Feature activation+7.08e-02

Pos logit contributions
 Frie+3.143
spir+3.031
Male+2.859
 AAA+2.819
 UCHIJ+2.742
Neg logit contributions
emetery-2.997
ospel-2.967
vernment-2.883
ppa-2.856
appa-2.756
Token
Token ID851
Feature activation-6.51e-01

Pos logit contributions
 Frie+0.056
spir+0.054
Male+0.051
 AAA+0.050
 UCHIJ+0.049
Neg logit contributions
emetery-0.054
ospel-0.053
vernment-0.052
ppa-0.052
appa-0.049
Token Robert
Token ID5199
Feature activation-5.24e-01

Pos logit contributions
emetery+0.458
ospel+0.452
vernment+0.440
ppa+0.439
appa+0.418
Neg logit contributions
 Frie-0.548
spir-0.530
Male-0.502
 AAA-0.491
querque-0.485
Token Gu
Token ID1962
Feature activation-6.09e-01

Pos logit contributions
emetery+0.381
ospel+0.376
vernment+0.367
ppa+0.366
appa+0.348
Neg logit contributions
 Frie-0.431
spir-0.415
Male-0.394
 AAA-0.386
 UCHIJ-0.379
Token workload
Token ID26211
Feature activation-3.70e-01

Pos logit contributions
emetery+1.441
ospel+1.427
ppa+1.394
vernment+1.393
appa+1.329
Neg logit contributions
 Frie-1.530
spir-1.476
Male-1.401
 AAA-1.354
querque-1.344
Tokens
Token ID82
Feature activation-3.68e-01

Pos logit contributions
emetery+0.308
ospel+0.305
vernment+0.298
ppa+0.297
appa+0.284
Neg logit contributions
 Frie-0.264
spir-0.255
Male-0.239
 AAA-0.235
 UCHIJ-0.229
Token including
Token ID1390
Feature activation+1.32e+00

Pos logit contributions
emetery+0.281
ospel+0.278
vernment+0.272
ppa+0.270
appa+0.258
Neg logit contributions
 Frie-0.289
spir-0.278
Male-0.263
 AAA-0.258
 UCHIJ-0.253
Token interrupts
Token ID48237
Feature activation-5.17e-02

Pos logit contributions
 Frie+1.025
spir+0.985
Male+0.932
 AAA+0.917
 UCHIJ+0.895
Neg logit contributions
emetery-1.019
ospel-1.009
vernment-0.986
ppa-0.981
appa-0.935
Token and
Token ID290
Feature activation+1.35e+00

Pos logit contributions
emetery+0.038
ospel+0.038
vernment+0.037
ppa+0.036
appa+0.035
Neg logit contributions
 Frie-0.042
spir-0.040
Male-0.038
 AAA-0.038
 UCHIJ-0.037
Token timers
Token ID48085
Feature activation+9.57e-01

Pos logit contributions
 Frie+0.909
spir+0.866
Male+0.812
 AAA+0.795
 UCHIJ+0.774
Neg logit contributions
emetery-1.186
ospel-1.176
vernment-1.150
ppa-1.147
appa-1.101
Token.
Token ID13
Feature activation+8.63e-01

Pos logit contributions
 Frie+0.737
spir+0.707
Male+0.670
 AAA+0.658
 UCHIJ+0.645
Neg logit contributions
emetery-0.745
ospel-0.739
vernment-0.720
ppa-0.715
appa-0.683
Token
Token ID198
Feature activation+4.66e-01

Pos logit contributions
 Frie+0.666
spir+0.637
Male+0.605
 AAA+0.594
 UCHIJ+0.581
Neg logit contributions
emetery-0.675
ospel-0.665
vernment-0.651
ppa-0.645
appa-0.616
Token
Token ID198
Feature activation-2.27e-01

Pos logit contributions
 Frie+0.354
spir+0.341
Male+0.322
 AAA+0.315
 UCHIJ+0.308
Neg logit contributions
emetery-0.367
ospel-0.362
vernment-0.354
ppa-0.352
appa-0.337
TokenThings
Token ID22248
Feature activation-1.30e+00

Pos logit contributions
emetery+0.200
ospel+0.198
ppa+0.194
vernment+0.194
appa+0.187
Neg logit contributions
 Frie-0.152
spir-0.144
Male-0.134
 AAA-0.132
querque-0.130
Token started
Token ID2067
Feature activation+4.28e+00

Pos logit contributions
emetery+1.023
ospel+1.013
vernment+0.991
ppa+0.991
appa+0.947
Neg logit contributions
 Frie-0.978
spir-0.940
Male-0.888
 AAA-0.865
querque-0.852
Token nomination
Token ID11872
Feature activation+2.85e+00

Pos logit contributions
 Frie+1.278
spir+1.228
Male+1.165
 AAA+1.139
 UCHIJ+1.116
Neg logit contributions
emetery-1.243
ospel-1.227
vernment-1.198
ppa-1.194
appa-1.139
Token locked
Token ID8970
Feature activation+1.54e+00

Pos logit contributions
 Frie+2.162
spir+2.056
Male+1.948
 AAA+1.910
 UCHIJ+1.871
Neg logit contributions
emetery-2.259
ospel-2.242
vernment-2.170
ppa-2.164
appa-2.068
Token up
Token ID510
Feature activation-1.93e+00

Pos logit contributions
 Frie+1.040
spir+0.987
Male+0.933
 AAA+0.913
 UCHIJ+0.890
Neg logit contributions
emetery-1.348
ospel-1.332
vernment-1.307
ppa-1.292
appa-1.240
Token and
Token ID290
Feature activation-1.42e-01

Pos logit contributions
emetery+1.459
ospel+1.442
vernment+1.411
ppa+1.408
appa+1.344
Neg logit contributions
 Frie-1.520
spir-1.469
Male-1.384
 AAA-1.354
querque-1.333
Token is
Token ID318
Feature activation-5.49e-01

Pos logit contributions
emetery+0.107
ospel+0.106
vernment+0.103
ppa+0.103
appa+0.098
Neg logit contributions
 Frie-0.113
spir-0.109
Male-0.103
 AAA-0.101
 UCHIJ-0.099
Token lining
Token ID20883
Feature activation-2.85e-01

Pos logit contributions
emetery+0.417
ospel+0.412
vernment+0.403
ppa+0.402
appa+0.384
Neg logit contributions
 Frie-0.432
spir-0.415
Male-0.394
 AAA-0.384
 UCHIJ-0.377
Token up
Token ID510
Feature activation-3.67e-01

Pos logit contributions
emetery+0.245
ospel+0.243
vernment+0.238
ppa+0.237
appa+0.227
Neg logit contributions
 Frie-0.196
spir-0.188
Male-0.176
 AAA-0.172
 UCHIJ-0.168
Token support
Token ID1104
Feature activation-6.35e-01

Pos logit contributions
emetery+0.292
ospel+0.289
vernment+0.283
ppa+0.282
appa+0.269
Neg logit contributions
 Frie-0.276
spir-0.265
Male-0.250
 AAA-0.244
 UCHIJ-0.239
Token within
Token ID1626
Feature activation-1.57e+00

Pos logit contributions
emetery+0.530
ospel+0.524
vernment+0.514
ppa+0.512
appa+0.493
Neg logit contributions
 Frie-0.449
spir-0.431
Male-0.406
 AAA-0.395
querque-0.388
Token his
Token ID465
Feature activation-1.45e+00

Pos logit contributions
emetery+1.120
ospel+1.105
vernment+1.085
ppa+1.075
appa+1.028
Neg logit contributions
 Frie-1.291
spir-1.249
Male-1.189
 AAA-1.152
querque-1.145
Token own
Token ID898
Feature activation-2.97e-01

Pos logit contributions
emetery+1.008
ospel+0.998
vernment+0.978
ppa+0.973
appa+0.936
Neg logit contributions
 Frie-1.213
spir-1.180
Male-1.118
 AAA-1.084
querque-1.080
Tokeng
Token ID70
Feature activation+3.60e+00

Pos logit contributions
 Frie+0.772
spir+0.737
Male+0.696
 AAA+0.680
 UCHIJ+0.666
Neg logit contributions
emetery-0.873
ospel-0.865
vernment-0.846
ppa-0.845
appa-0.809
Tokenlor
Token ID4685
Feature activation-1.94e+00

Pos logit contributions
 Frie+3.233
spir+3.210
Male+3.000
 AAA+2.949
 UCHIJ+2.858
Neg logit contributions
emetery-2.254
ppa-2.127
vernment-2.121
ospel-2.084
 Kak-2.029
Tokenious
Token ID699
Feature activation+6.67e-01

Pos logit contributions
emetery+1.158
ospel+1.152
vernment+1.114
ppa+1.104
appa+1.040
Neg logit contributions
 Frie-1.847
spir-1.778
Male-1.706
 AAA-1.678
querque-1.657
Token diversity
Token ID9573
Feature activation+6.08e-01

Pos logit contributions
 Frie+0.522
spir+0.502
Male+0.476
 AAA+0.465
 UCHIJ+0.456
Neg logit contributions
emetery-0.510
ospel-0.505
vernment-0.493
ppa-0.491
appa-0.469
Token'
Token ID6
Feature activation-5.52e-01

Pos logit contributions
 Frie+0.470
spir+0.452
Male+0.428
 AAA+0.418
 UCHIJ+0.410
Neg logit contributions
emetery-0.470
ospel-0.465
vernment-0.454
ppa-0.453
appa-0.433
Token of
Token ID286
Feature activation-3.89e+00

Pos logit contributions
emetery+0.420
ospel+0.416
vernment+0.406
ppa+0.405
appa+0.386
Neg logit contributions
 Frie-0.433
spir-0.417
Male-0.395
 AAA-0.385
querque-0.378
Token people
Token ID661
Feature activation+2.08e+00

Pos logit contributions
emetery+2.678
ospel+2.677
ppa+2.621
vernment+2.618
 Kak+2.504
Neg logit contributions
 Frie-3.210
spir-3.136
Male-2.970
querque-2.884
 AAA-2.852
Token of
Token ID286
Feature activation-7.79e-01

Pos logit contributions
 Frie+1.609
spir+1.541
Male+1.455
 AAA+1.428
 UCHIJ+1.399
Neg logit contributions
emetery-1.616
ospel-1.598
vernment-1.557
ppa-1.550
appa-1.477
Token all
Token ID477
Feature activation+2.28e+00

Pos logit contributions
emetery+0.572
ospel+0.566
ppa+0.552
vernment+0.552
appa+0.526
Neg logit contributions
 Frie-0.629
spir-0.608
Male-0.578
 AAA-0.562
querque-0.556
Token faiths
Token ID43028
Feature activation-1.19e+00

Pos logit contributions
 Frie+1.539
spir+1.468
Male+1.377
 AAA+1.344
 UCHIJ+1.310
Neg logit contributions
emetery-2.000
ospel-1.980
vernment-1.941
ppa-1.931
appa-1.857
Token,
Token ID11
Feature activation-7.28e-01

Pos logit contributions
emetery+0.848
ospel+0.840
vernment+0.822
ppa+0.821
appa+0.781
Neg logit contributions
 Frie-0.986
spir-0.954
Male-0.905
 AAA-0.887
querque-0.876
Token plant
Token ID4618
Feature activation+6.83e-01

Pos logit contributions
 Frie+0.357
spir+0.344
Male+0.326
 AAA+0.318
 UCHIJ+0.313
Neg logit contributions
emetery-0.331
ospel-0.327
vernment-0.319
ppa-0.318
appa-0.303
Token to
Token ID284
Feature activation+3.46e-01

Pos logit contributions
 Frie+0.519
spir+0.499
Male+0.472
 AAA+0.461
 UCHIJ+0.452
Neg logit contributions
emetery-0.537
ospel-0.532
vernment-0.520
ppa-0.518
appa-0.495
Token a
Token ID257
Feature activation+1.46e+00

Pos logit contributions
 Frie+0.271
spir+0.262
Male+0.248
 AAA+0.241
querque+0.238
Neg logit contributions
emetery-0.265
ospel-0.260
vernment-0.256
ppa-0.254
appa-0.242
Token lined
Token ID16566
Feature activation-8.42e-01

Pos logit contributions
 Frie+0.895
spir+0.847
Male+0.788
 AAA+0.770
 UCHIJ+0.748
Neg logit contributions
emetery-1.369
ospel-1.360
vernment-1.330
ppa-1.330
appa-1.281
Token structural
Token ID13204
Feature activation+1.39e+00

Pos logit contributions
emetery+0.729
ospel+0.720
vernment+0.705
ppa+0.700
appa+0.673
Neg logit contributions
 Frie-0.573
spir-0.551
Male-0.519
 AAA-0.502
querque-0.493
Token fill
Token ID6070
Feature activation-3.95e+00

Pos logit contributions
 Frie+0.795
spir+0.752
Male+0.697
 AAA+0.677
 UCHIJ+0.658
Neg logit contributions
emetery-1.360
ospel-1.349
vernment-1.324
ppa-1.320
appa-1.274
Token solution
Token ID4610
Feature activation-3.34e+00

Pos logit contributions
emetery+3.117
ospel+3.081
vernment+2.985
ppa+2.980
appa+2.854
Neg logit contributions
 Frie-2.978
spir-2.840
Male-2.710
 AAA-2.602
 UCHIJ-2.568
Token while
Token ID981
Feature activation-1.18e-01

Pos logit contributions
emetery+2.409
ospel+2.347
vernment+2.308
ppa+2.284
 Kak+2.192
Neg logit contributions
 Frie-2.725
spir-2.636
Male-2.501
querque-2.437
 AAA-2.427
Token continuing
Token ID8282
Feature activation-1.65e+00

Pos logit contributions
emetery+0.090
ospel+0.089
vernment+0.087
ppa+0.087
appa+0.083
Neg logit contributions
 Frie-0.093
spir-0.090
Male-0.085
 AAA-0.082
querque-0.081
Token to
Token ID284
Feature activation-2.30e-01

Pos logit contributions
emetery+1.286
ospel+1.262
vernment+1.250
ppa+1.230
 Kak+1.187
Neg logit contributions
 Frie-1.263
spir-1.218
Male-1.152
 AAA-1.109
querque-1.103
Token search
Token ID2989
Feature activation+7.50e-01

Pos logit contributions
emetery+0.181
ospel+0.180
vernment+0.176
ppa+0.176
appa+0.168
Neg logit contributions
 Frie-0.174
spir-0.167
Male-0.159
 AAA-0.154
querque-0.152
Token Some
Token ID2773
Feature activation+6.53e-01

Pos logit contributions
 Frie+0.570
spir+0.545
Male+0.516
 AAA+0.508
 UCHIJ+0.493
Neg logit contributions
emetery-0.617
ospel-0.606
vernment-0.591
ppa-0.589
appa-0.565
Token Pictures
Token ID20051
Feature activation-1.34e+00

Pos logit contributions
 Frie+0.497
spir+0.473
Male+0.448
 AAA+0.445
 UCHIJ+0.430
Neg logit contributions
emetery-0.522
ospel-0.511
vernment-0.502
ppa-0.494
appa-0.477
Token of
Token ID286
Feature activation-4.48e-01

Pos logit contributions
emetery+1.040
ospel+1.030
vernment+1.005
ppa+1.003
appa+0.958
Neg logit contributions
 Frie-1.027
spir-0.988
Male-0.934
 AAA-0.911
 UCHIJ-0.895
Token That
Token ID1320
Feature activation-2.26e-01

Pos logit contributions
emetery+0.343
ospel+0.340
vernment+0.332
ppa+0.332
appa+0.316
Neg logit contributions
 Frie-0.349
spir-0.337
Male-0.318
 AAA-0.310
querque-0.305
Token Corner
Token ID26212
Feature activation-2.31e+00

Pos logit contributions
emetery+0.175
ospel+0.173
vernment+0.169
ppa+0.169
appa+0.161
Neg logit contributions
 Frie-0.174
spir-0.167
Male-0.158
 AAA-0.155
 UCHIJ-0.152
Token Vari
Token ID15965
Feature activation-4.80e+00

Pos logit contributions
emetery+1.793
ospel+1.776
vernment+1.735
ppa+1.733
appa+1.654
Neg logit contributions
 Frie-1.768
spir-1.700
Male-1.610
 AAA-1.569
querque-1.543
Tokenation
Token ID341
Feature activation-1.70e+00

Pos logit contributions
emetery+2.797
ospel+2.767
ppa+2.703
vernment+2.679
appa+2.563
Neg logit contributions
 Frie-4.561
spir-4.381
Male-4.232
 AAA-4.108
querque-4.098
Token,
Token ID11
Feature activation-2.35e+00

Pos logit contributions
emetery+1.324
ospel+1.311
vernment+1.280
ppa+1.279
appa+1.220
Neg logit contributions
 Frie-1.309
spir-1.259
Male-1.190
 AAA-1.161
querque-1.142
Token Don
Token ID2094
Feature activation+8.60e-01

Pos logit contributions
emetery+1.834
ospel+1.832
ppa+1.797
vernment+1.781
 Kak+1.736
Neg logit contributions
 Frie-1.746
spir-1.693
Male-1.576
querque-1.540
 UCHIJ-1.515
Token
Token ID447
Feature activation+1.80e+00

Pos logit contributions
 Frie+0.593
spir+0.568
Male+0.534
 AAA+0.520
 UCHIJ+0.508
Neg logit contributions
emetery-0.738
ospel-0.730
vernment-0.716
ppa-0.712
appa-0.684
Token
Token ID247
Feature activation-1.06e-01

Pos logit contributions
 Frie+1.002
spir+0.948
Male+0.876
 AAA+0.847
 UCHIJ+0.823
Neg logit contributions
emetery-1.777
ospel-1.762
vernment-1.731
ppa-1.725
appa-1.664
Token finished
Token ID5201
Feature activation+6.28e-01

Pos logit contributions
 Frie+0.912
spir+0.877
Male+0.831
 AAA+0.812
 UCHIJ+0.794
Neg logit contributions
emetery-0.942
ospel-0.932
vernment-0.904
ppa-0.897
appa-0.860
Token eighth
Token ID16974
Feature activation-1.32e+00

Pos logit contributions
 Frie+0.520
spir+0.502
Male+0.476
 AAA+0.465
querque+0.458
Neg logit contributions
emetery-0.451
ospel-0.446
vernment-0.434
ppa-0.434
appa-0.413
Token in
Token ID287
Feature activation-7.86e-01

Pos logit contributions
emetery+1.037
ospel+1.026
vernment+1.003
ppa+1.002
appa+0.959
Neg logit contributions
 Frie-1.009
spir-0.973
Male-0.915
 AAA-0.891
 UCHIJ-0.878
Token D
Token ID360
Feature activation+4.92e-01

Pos logit contributions
emetery+0.583
ospel+0.577
vernment+0.563
ppa+0.561
appa+0.535
Neg logit contributions
 Frie-0.633
spir-0.609
Male-0.578
 AAA-0.565
 UCHIJ-0.555
TokenY
Token ID56
Feature activation-8.00e-01

Pos logit contributions
 Frie+0.374
spir+0.360
Male+0.340
 AAA+0.332
 UCHIJ+0.325
Neg logit contributions
emetery-0.387
ospel-0.383
vernment-0.374
ppa-0.373
appa-0.356
TokenAR
Token ID1503
Feature activation-4.19e+00

Pos logit contributions
emetery+0.598
ospel+0.595
vernment+0.580
ppa+0.575
appa+0.547
Neg logit contributions
 Frie-0.634
spir-0.618
Male-0.582
 AAA-0.572
 UCHIJ-0.560
Token (
Token ID357
Feature activation-3.20e+00

Pos logit contributions
emetery+3.063
ospel+3.021
vernment+2.986
ppa+2.968
appa+2.854
Neg logit contributions
 Frie-3.388
spir-3.256
Male-3.070
 AAA-2.994
querque-2.944
Tokentotal
Token ID23350
Feature activation-2.05e+00

Pos logit contributions
emetery+2.392
ospel+2.367
ppa+2.324
vernment+2.316
appa+2.219
Neg logit contributions
 Frie-2.564
spir-2.419
Male-2.274
 AAA-2.269
querque-2.234
Token value
Token ID1988
Feature activation-2.40e+00

Pos logit contributions
emetery+1.475
ospel+1.462
vernment+1.435
ppa+1.422
appa+1.363
Neg logit contributions
 Frie-1.683
spir-1.630
Male-1.536
 AAA-1.489
 UCHIJ-1.471
Token at
Token ID379
Feature activation-2.27e+00

Pos logit contributions
emetery+1.798
ospel+1.776
vernment+1.741
ppa+1.739
appa+1.665
Neg logit contributions
 Frie-1.905
spir-1.826
Male-1.728
 AAA-1.680
 UCHIJ-1.661
Token his
Token ID465
Feature activation-9.46e-01

Pos logit contributions
emetery+1.613
ospel+1.592
vernment+1.569
ppa+1.553
 Kak+1.483
Neg logit contributions
 Frie-1.882
spir-1.820
Male-1.721
 AAA-1.662
 UCHIJ-1.654
Token five
Token ID1936
Feature activation+7.28e-01

Pos logit contributions
 Frie+1.227
spir+1.182
Male+1.122
 AAA+1.107
 UCHIJ+1.074
Neg logit contributions
emetery-1.184
ospel-1.175
vernment-1.146
ppa-1.143
appa-1.075
Token-
Token ID12
Feature activation-8.11e-02

Pos logit contributions
 Frie+0.477
spir+0.455
Male+0.426
 AAA+0.415
 UCHIJ+0.404
Neg logit contributions
emetery-0.650
ospel-0.644
vernment-0.630
ppa-0.628
appa-0.604
Tokenday
Token ID820
Feature activation-1.29e+00

Pos logit contributions
emetery+0.060
ospel+0.059
vernment+0.058
ppa+0.058
appa+0.055
Neg logit contributions
 Frie-0.065
spir-0.063
Male-0.059
 AAA-0.058
querque-0.058
Token custody
Token ID10804
Feature activation+1.62e+00

Pos logit contributions
emetery+1.024
ospel+1.014
vernment+0.991
ppa+0.988
appa+0.947
Neg logit contributions
 Frie-0.971
spir-0.933
Male-0.880
 AAA-0.858
querque-0.843
Token of
Token ID286
Feature activation-1.29e+00

Pos logit contributions
 Frie+1.241
spir+1.187
Male+1.132
 AAA+1.102
 UCHIJ+1.081
Neg logit contributions
emetery-1.263
ospel-1.254
vernment-1.222
ppa-1.213
appa-1.156
Token Mr
Token ID1770
Feature activation-3.68e+00

Pos logit contributions
emetery+0.871
ospel+0.858
vernment+0.838
ppa+0.834
appa+0.798
Neg logit contributions
 Frie-1.130
spir-1.090
Male-1.036
 AAA-1.013
querque-1.005
Token Tom
Token ID4186
Feature activation+1.55e+00

Pos logit contributions
emetery+2.386
ospel+2.350
vernment+2.298
ppa+2.285
appa+2.223
Neg logit contributions
 Frie-3.275
spir-3.149
Male-2.982
querque-2.918
 AAA-2.911
Tokenar
Token ID283
Feature activation-1.98e+00

Pos logit contributions
 Frie+1.306
spir+1.298
Male+1.220
 AAA+1.200
 UCHIJ+1.170
Neg logit contributions
emetery-1.078
ospel-1.047
vernment-1.044
ppa-1.006
 Kak-0.951
Token.
Token ID13
Feature activation-3.74e-01

Pos logit contributions
emetery+1.428
ospel+1.406
ppa+1.397
vernment+1.390
appa+1.340
Neg logit contributions
 Frie-1.603
spir-1.545
Male-1.456
 AAA-1.431
querque-1.423
Token
Token ID198
Feature activation+8.36e-02

Pos logit contributions
emetery+0.294
ospel+0.291
vernment+0.284
ppa+0.283
appa+0.271
Neg logit contributions
 Frie-0.284
spir-0.273
Male-0.257
 AAA-0.252
querque-0.247
Token
Token ID198
Feature activation+3.87e-01

Pos logit contributions
 Frie+0.064
spir+0.062
Male+0.058
 AAA+0.057
querque+0.056
Neg logit contributions
emetery-0.065
ospel-0.064
vernment-0.063
ppa-0.063
appa-0.060