TOP ACTIVATIONS
MAX = 17.478

struggles against the catastrophic and explo itative choices of the state
the donation would have on financially disadvantaged students by drawing from
, 2012 . ( Published Thursday , Dec . 27 ,
in their fine because they cooper ated with investigators .
soon . 2 nd and 6 : B ugg
battling display . Sl ov akia s
incident in the revolution - wr acked nation , a senior
De vers . Sl ov akia : Gre if
at Wel ford Road , Saturday 21 January live on BT
! When : Thursday , Jul 12 11 :
a way to make a profit . But that profit has
repeat . Posted on August 1 on Facebook , the video
Fore casters said late on Monday local time that Matthew would
an Israeli official confirmed on Thursday . Although there
said in a tweet on Thursday , echoing criticisms he made
was the Caps who struck first when Alex O ve ch
be placed at the 0 th index . After
phone in downtown Toronto on Monday . Liberal MP P Y
, in a statement on Monday . But given
okane police arrested one suspect Thursday night and charged him with

MIN ACTIVATIONS
MIN = -17.396

to supposedly kill actor Neil Patrick Harris , who is never
country , have to accept mass immigration from Africa , the
dialect ic of an extended mass revolt and a defeated proletarian
dominated political institutions and the mass media , leading to a
United Nations , Susan E . Rice , said Friday that
her rival Sen . Barbara Box er , D - California
crisis of capitalism , with mass unemployment at home and the
Car lo Alleg ri ) Michael Flynn The 57 - year
years ago Rolling Stone reporter Michael Hastings writing in America
July . Advertisement Continue reading the main story
for the flight home . Expect ing another tired clone of
F inance Minister Michael Noon an said on Wednesday
the induction of President William V . S . Tub man
to NBC s Matt L auer that he he
. We will continue to keep a close eye
Take mankind in the mass , and for
If Dallas ren ounces Charlie V , Greg Smith , Richard
topical , Trey Parker and Matt Stone 's news y cartoon
Sanders : ' I fully expect ' fair treatment by DNC
finance and ro iled by mass street protests . These were

INTERVAL 8.760 - 17.478
CONTAINS 0.913%

no one can take any risks with this . Everything must
recession . On Thursday , Carney said the independent
Trump (@ realDonaldTrump ) June 3 , 2017 Shortly
three games with their 14 th defeat in 16 outings .
dispute in its statement on Monday , but said it would

INTERVAL 0.041 - 8.760
CONTAINS 47.692%

though I knew I wanted to get into tech
with leadership earlier this year and pushed to trim a spending
endi st rolled off to entertain ( or be entertained )
in his infinite wisdom , tweeted the following at Ham ill
a meltdown or other releases , for instance from spent fuel

INTERVAL -8.677 - 0.041
CONTAINS 50.734%

the beginning of the catastrophic phase , Sebastian P
voluntary filter , stating the plan lacked transparency in the selection
ILL NOT DIV IDE . US due to dangerous , illegal
. The game also includes a character creation system for making
I jab all the time . It seems I

INTERVAL -17.396 - -8.677
CONTAINS 0.660%

which were discovered on the infant dated three to four weeks
ys 3 way Dream - Ant @ Casino Recap - Sports
pornography or spam . The change comes about six months after
. 2014 Don C head le 2014
no distinction between youth and adult punishment or between consecutive and
Token struggles
Token ID12766
Feature activation+2.57e+00

Pos logit contributions
 holiest+2.122
saf+1.940
cific+1.910
Trivia+1.892
 Advantage+1.877
Neg logit contributions
 debates-1.377
 adoption-1.335
birth-1.334
Pg-1.320
rons-1.304
Token against
Token ID1028
Feature activation-7.27e-01

Pos logit contributions
 holiest+2.204
saf+2.009
cific+1.981
Trivia+1.960
 Advantage+1.942
Neg logit contributions
 debates-1.506
 adoption-1.462
birth-1.455
Pg-1.441
rons-1.426
Token the
Token ID262
Feature activation+9.96e-01

Pos logit contributions
 debates+0.412
 adoption+0.402
birth+0.392
 amounts+0.389
Pg+0.388
Neg logit contributions
 holiest-0.642
saf-0.588
cific-0.583
Trivia-0.576
 Advantage-0.566
Token catastrophic
Token ID22694
Feature activation+1.23e+00

Pos logit contributions
 holiest+0.879
saf+0.805
cific+0.796
Trivia+0.787
 Advantage+0.777
Neg logit contributions
 debates-0.561
 adoption-0.545
birth-0.538
Pg-0.533
rons-0.527
Token and
Token ID290
Feature activation+4.10e+00

Pos logit contributions
 holiest+1.085
saf+0.993
cific+0.983
Trivia+0.971
 Advantage+0.959
Neg logit contributions
 debates-0.690
 adoption-0.669
birth-0.660
Pg-0.652
 amounts-0.649
Token explo
Token ID6694
Feature activation+1.75e+01

Pos logit contributions
 holiest+3.560
saf+3.230
cific+3.174
Trivia+3.146
 Advantage+3.124
Neg logit contributions
 debates-2.329
birth-2.262
 adoption-2.249
Pg-2.236
rons-2.224
Tokenitative
Token ID12464
Feature activation+7.95e+00

Pos logit contributions
 holiest+8.395
saf+8.047
cific+7.509
 Advantage+7.151
Trivia+7.081
Neg logit contributions
rons-13.755
 adoption-13.573
 Lauder-13.554
 bathing-13.317
croft-13.305
Token choices
Token ID7747
Feature activation+1.02e+00

Pos logit contributions
 holiest+6.535
saf+5.944
 Advantage+5.825
Trivia+5.724
cific+5.701
Neg logit contributions
birth-4.501
Pg-4.490
tumblr-4.483
 debates-4.456
rons-4.411
Token of
Token ID286
Feature activation+4.33e+00

Pos logit contributions
 holiest+0.916
saf+0.838
cific+0.830
Trivia+0.822
 Advantage+0.811
Neg logit contributions
 debates-0.558
 adoption-0.540
birth-0.534
Pg-0.528
rons-0.524
Token the
Token ID262
Feature activation+3.12e+00

Pos logit contributions
 holiest+3.669
saf+3.341
cific+3.280
Trivia+3.249
 Advantage+3.239
Neg logit contributions
 debates-2.528
birth-2.462
Pg-2.449
 adoption-2.446
rons-2.406
Token state
Token ID1181
Feature activation-2.54e+00

Pos logit contributions
 holiest+2.700
saf+2.460
cific+2.421
Trivia+2.398
 Advantage+2.382
Neg logit contributions
 debates-1.798
birth-1.743
 adoption-1.741
Pg-1.727
rons-1.704
Token the
Token ID262
Feature activation-9.76e-01

Pos logit contributions
 debates+0.588
 adoption+0.570
birth+0.554
 amounts+0.549
Pg+0.538
Neg logit contributions
 holiest-0.990
saf-0.910
cific-0.902
Trivia-0.894
 Advantage-0.872
Token donation
Token ID13784
Feature activation-3.36e+00

Pos logit contributions
 debates+0.545
 adoption+0.532
 amounts+0.510
birth+0.509
 viewing+0.496
Neg logit contributions
 holiest-0.874
saf-0.805
cific-0.801
Trivia-0.791
INGTON-0.774
Token would
Token ID561
Feature activation-6.60e+00

Pos logit contributions
 debates+1.840
 amounts+1.778
 adoption+1.771
Pg+1.698
birth+1.692
Neg logit contributions
 holiest-3.039
saf-2.801
cific-2.764
Trivia-2.739
INGTON-2.684
Token have
Token ID423
Feature activation-4.00e+00

Pos logit contributions
 debates+2.368
 adoption+2.341
 amounts+2.338
birth+2.177
 clam+2.168
Neg logit contributions
 holiest-7.115
cific-6.513
Trivia-6.501
saf-6.400
 Advantage-6.327
Token on
Token ID319
Feature activation-3.32e+00

Pos logit contributions
 debates+2.023
 adoption+1.993
 amounts+1.939
birth+1.916
Pg+1.866
Neg logit contributions
 holiest-3.771
saf-3.408
Trivia-3.407
cific-3.395
 Advantage-3.322
Token financially
Token ID18786
Feature activation+1.70e+01

Pos logit contributions
 debates+1.607
 adoption+1.556
 amounts+1.469
birth+1.467
 breastfeeding+1.443
Neg logit contributions
 holiest-3.248
saf-3.006
cific-2.972
Trivia-2.951
INGTON-2.883
Token disadvantaged
Token ID36327
Feature activation+3.64e+00

Pos logit contributions
 holiest+12.457
saf+10.894
 Advantage+10.720
ever+10.417
INGTON+10.378
Neg logit contributions
xon-10.236
rons-9.792
Pg-9.758
anamo-9.653
croft-9.548
Token students
Token ID2444
Feature activation-5.99e+00

Pos logit contributions
 holiest+3.888
saf+3.612
cific+3.555
 Advantage+3.540
Trivia+3.530
Neg logit contributions
 debates-1.326
Pg-1.276
birth-1.276
 adoption-1.263
rons-1.227
Token by
Token ID416
Feature activation+1.53e+00

Pos logit contributions
 debates+3.204
 adoption+3.082
 viewing+3.046
 amounts+3.041
birth+3.021
Neg logit contributions
 holiest-5.393
saf-4.974
cific-4.871
Trivia-4.849
INGTON-4.805
Token drawing
Token ID8263
Feature activation+2.71e-01

Pos logit contributions
 holiest+1.527
saf+1.410
cific+1.395
Trivia+1.382
 Advantage+1.368
Neg logit contributions
 debates-0.691
 adoption-0.666
birth-0.656
Pg-0.643
rons-0.637
Token from
Token ID422
Feature activation+2.00e+00

Pos logit contributions
 holiest+0.279
saf+0.259
cific+0.255
Trivia+0.253
 Advantage+0.251
Neg logit contributions
 debates-0.114
 adoption-0.109
birth-0.107
Pg-0.106
 amounts-0.104
Token,
Token ID11
Feature activation+9.05e+00

Pos logit contributions
 holiest+8.744
saf+7.887
 Advantage+7.808
Trivia+7.765
INGTON+7.652
Neg logit contributions
Pg-8.093
 debates-7.878
 adoption-7.596
tumblr-7.586
 Lauder-7.561
Token 2012
Token ID2321
Feature activation+2.96e+00

Pos logit contributions
 holiest+5.266
saf+4.628
 Advantage+4.595
cific+4.504
Trivia+4.492
Neg logit contributions
 debates-7.322
Pg-7.301
birth-7.119
 adoption-7.052
xon-6.971
Token.
Token ID13
Feature activation+2.02e-01

Pos logit contributions
 holiest+2.382
saf+2.157
cific+2.125
Trivia+2.099
 Advantage+2.076
Neg logit contributions
 debates-1.894
 adoption-1.843
birth-1.835
Pg-1.816
rons-1.802
Token (
Token ID357
Feature activation+3.16e+00

Pos logit contributions
 holiest+0.193
saf+0.177
cific+0.175
Trivia+0.173
 Advantage+0.171
Neg logit contributions
 debates-0.099
 adoption-0.096
birth-0.096
Pg-0.094
rons-0.093
TokenPublished
Token ID24492
Feature activation+5.15e+00

Pos logit contributions
 holiest+2.700
saf+2.466
cific+2.415
Trivia+2.409
 Advantage+2.379
Neg logit contributions
 debates-1.862
 adoption-1.797
birth-1.789
Pg-1.768
rons-1.760
Token Thursday
Token ID3635
Feature activation+1.67e+01

Pos logit contributions
 holiest+4.003
saf+3.618
cific+3.512
 Advantage+3.511
Trivia+3.486
Neg logit contributions
 debates-3.349
Pg-3.308
birth-3.267
 adoption-3.247
rons-3.194
Token,
Token ID11
Feature activation+1.16e+01

Pos logit contributions
 holiest+9.311
 Advantage+9.201
saf+8.822
Trivia+8.577
gin+8.520
Neg logit contributions
 debates-11.236
ritical-11.069
 adoption-11.061
birth-11.006
Pg-10.985
Token Dec
Token ID4280
Feature activation+8.81e+00

Pos logit contributions
 holiest+6.622
 Advantage+5.847
Trivia+5.667
saf+5.667
INGTON+5.441
Neg logit contributions
 debates-9.003
Pg-8.884
birth-8.804
 stret-8.737
tumblr-8.737
Token.
Token ID13
Feature activation+4.62e+00

Pos logit contributions
 holiest+5.594
saf+5.278
cific+5.180
 Advantage+5.097
Trivia+4.979
Neg logit contributions
 debates-6.451
 adoption-6.260
Pg-6.249
 clam-6.136
 bathing-6.135
Token 27
Token ID2681
Feature activation+1.27e+01

Pos logit contributions
 holiest+2.900
saf+2.593
cific+2.506
 Advantage+2.500
Trivia+2.494
Neg logit contributions
 debates-3.717
 adoption-3.628
Pg-3.607
birth-3.591
rons-3.573
Token,
Token ID11
Feature activation+9.67e+00

Pos logit contributions
 holiest+7.469
saf+7.440
 Advantage+7.204
Trivia+7.124
INGTON+7.041
Neg logit contributions
 debates-8.957
anamo-8.732
 clam-8.679
 stret-8.618
ritical-8.594
Token in
Token ID287
Feature activation-2.45e+00

Pos logit contributions
 debates+2.302
 adoption+2.285
 amounts+2.236
rons+2.153
birth+2.149
Neg logit contributions
 holiest-4.736
Trivia-4.300
saf-4.291
cific-4.266
INGTON-4.216
Token their
Token ID511
Feature activation+5.54e-01

Pos logit contributions
 debates+1.336
 adoption+1.311
 amounts+1.298
 viewing+1.230
 clam+1.220
Neg logit contributions
 holiest-2.226
cific-2.038
Trivia-2.024
saf-2.017
INGTON-1.979
Token fine
Token ID3734
Feature activation-1.74e+00

Pos logit contributions
 holiest+0.458
saf+0.414
cific+0.413
Trivia+0.408
 Advantage+0.398
Neg logit contributions
 debates-0.347
 adoption-0.338
 amounts-0.332
birth-0.329
Pg-0.328
Token because
Token ID780
Feature activation+1.90e+00

Pos logit contributions
 debates+1.006
 adoption+0.972
 amounts+0.965
birth+0.945
rons+0.945
Neg logit contributions
 holiest-1.528
saf-1.388
cific-1.372
Trivia-1.361
 Advantage-1.338
Token they
Token ID484
Feature activation+5.52e+00

Pos logit contributions
 holiest+1.656
saf+1.512
cific+1.491
Trivia+1.477
 Advantage+1.458
Neg logit contributions
 debates-1.099
 adoption-1.066
birth-1.055
Pg-1.046
rons-1.038
Token cooper
Token ID6788
Feature activation+1.66e+01

Pos logit contributions
 holiest+4.790
saf+4.401
cific+4.315
Trivia+4.268
 Advantage+4.247
Neg logit contributions
 debates-3.095
birth-3.025
 adoption-3.019
Pg-2.982
rons-2.922
Tokenated
Token ID515
Feature activation+8.62e+00

Pos logit contributions
saf+7.014
 holiest+6.615
rown+6.439
cific+6.350
Trivia+5.769
Neg logit contributions
 adoption-14.209
birth-14.205
 Lauder-14.005
 viewing-13.859
 debates-13.848
Token with
Token ID351
Feature activation+4.06e+00

Pos logit contributions
 holiest+6.867
saf+6.415
cific+6.181
Trivia+6.113
 Advantage+6.094
Neg logit contributions
birth-5.084
 debates-5.065
Pg-5.017
 adoption-4.992
tumblr-4.931
Token investigators
Token ID10093
Feature activation+6.70e-01

Pos logit contributions
 holiest+3.439
saf+3.147
cific+3.094
Trivia+3.050
 Advantage+3.034
Neg logit contributions
 debates-2.385
birth-2.327
 adoption-2.310
Pg-2.297
rons-2.268
Token.
Token ID13
Feature activation-1.81e+00

Pos logit contributions
 holiest+0.572
saf+0.517
cific+0.512
Trivia+0.507
 Advantage+0.501
Neg logit contributions
 debates-0.404
 adoption-0.390
birth-0.383
 amounts-0.382
rons-0.381
Token
Token ID198
Feature activation-5.64e-01

Pos logit contributions
 debates+1.097
 adoption+1.063
birth+1.062
Pg+1.049
rons+1.045
Neg logit contributions
 holiest-1.522
saf-1.368
cific-1.352
Trivia-1.337
 Advantage-1.308
Token soon
Token ID2582
Feature activation-2.94e-01

Pos logit contributions
 holiest+0.810
saf+0.737
cific+0.724
Trivia+0.719
 Advantage+0.709
Neg logit contributions
 debates-0.620
 adoption-0.601
birth-0.598
Pg-0.590
rons-0.587
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
 debates+0.173
 adoption+0.167
birth+0.167
rons+0.164
Pg+0.164
Neg logit contributions
 holiest-0.254
saf-0.230
cific-0.227
Trivia-0.224
 Advantage-0.222
Token
Token ID198
Feature activation+3.68e+00

Pos logit contributions
 holiest+1.119
saf+1.011
cific+0.997
Trivia+0.984
 Advantage+0.970
Neg logit contributions
 debates-0.846
 adoption-0.822
birth-0.821
Pg-0.813
rons-0.802
Token
Token ID198
Feature activation+2.15e+00

Pos logit contributions
 holiest+2.724
saf+2.528
Trivia+2.460
cific+2.443
 Advantage+2.414
Neg logit contributions
 debates-2.517
 adoption-2.446
rons-2.411
birth-2.398
 amounts-2.373
Token2
Token ID17
Feature activation+2.55e+00

Pos logit contributions
 holiest+1.751
saf+1.568
cific+1.554
 Advantage+1.524
Trivia+1.521
Neg logit contributions
 debates-1.366
birth-1.337
 adoption-1.330
Pg-1.327
rons-1.302
Tokennd
Token ID358
Feature activation+1.66e+01

Pos logit contributions
 holiest+2.142
saf+1.943
cific+1.912
Trivia+1.891
 Advantage+1.870
Neg logit contributions
 debates-1.556
 adoption-1.506
birth-1.496
Pg-1.490
rons-1.472
Token and
Token ID290
Feature activation+5.21e+00

Pos logit contributions
 holiest+12.716
 Advantage+11.409
cific+11.170
saf+11.103
Trivia+10.955
Neg logit contributions
tumblr-9.009
 debates-8.854
 Lauder-8.846
Pg-8.608
birth-8.580
Token 6
Token ID718
Feature activation-9.05e-01

Pos logit contributions
 holiest+3.753
saf+3.362
cific+3.289
Trivia+3.250
 Advantage+3.234
Neg logit contributions
 debates-3.735
 adoption-3.641
birth-3.640
Pg-3.614
rons-3.591
Token:
Token ID25
Feature activation+1.40e+00

Pos logit contributions
 debates+0.530
 adoption+0.512
 amounts+0.499
birth+0.499
Pg+0.498
Neg logit contributions
 holiest-0.788
saf-0.713
cific-0.704
Trivia-0.698
 Advantage-0.683
Token B
Token ID347
Feature activation+1.15e+00

Pos logit contributions
 holiest+1.177
saf+1.060
cific+1.051
Trivia+1.039
 Advantage+1.021
Neg logit contributions
 debates-0.848
 adoption-0.824
birth-0.821
Pg-0.813
rons-0.802
Tokenugg
Token ID6837
Feature activation+9.85e-01

Pos logit contributions
 holiest+0.903
saf+0.816
cific+0.802
Trivia+0.793
 Advantage+0.785
Neg logit contributions
 debates-0.752
 adoption-0.733
birth-0.727
Pg-0.723
rons-0.716
Token battling
Token ID20581
Feature activation+3.11e+00

Pos logit contributions
 debates+0.368
 adoption+0.362
 amounts+0.350
birth+0.350
 viewing+0.347
Neg logit contributions
 holiest-0.604
saf-0.549
cific-0.546
Trivia-0.546
INGTON-0.534
Token display
Token ID3359
Feature activation-1.42e+00

Pos logit contributions
 holiest+2.702
saf+2.464
cific+2.431
Trivia+2.404
 Advantage+2.394
Neg logit contributions
 debates-1.765
birth-1.709
 adoption-1.707
Pg-1.695
rons-1.671
Token.
Token ID13
Feature activation-7.07e-01

Pos logit contributions
 debates+0.792
 adoption+0.772
 amounts+0.758
rons+0.752
birth+0.745
Neg logit contributions
 holiest-1.268
saf-1.159
cific-1.152
Trivia-1.141
INGTON-1.114
Token
Token ID198
Feature activation-5.28e-01

Pos logit contributions
 debates+0.408
birth+0.396
Pg+0.395
 adoption+0.395
 amounts+0.383
Neg logit contributions
 holiest-0.617
saf-0.555
cific-0.547
Trivia-0.537
INGTON-0.524
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
 debates+0.314
birth+0.308
 adoption+0.306
Pg+0.305
rons+0.298
Neg logit contributions
 holiest-0.451
saf-0.405
cific-0.403
Trivia-0.394
 Advantage-0.392
TokenSl
Token ID11122
Feature activation+1.65e+01

Pos logit contributions
Pg+1.357
birth+1.332
 debates+1.301
 adoption+1.283
tumblr+1.263
Neg logit contributions
 holiest-1.814
cific-1.606
 Advantage-1.589
saf-1.583
INGTON-1.520
Tokenov
Token ID709
Feature activation+2.28e+00

Pos logit contributions
 holiest+11.624
saf+11.221
rown+11.193
ever+11.181
cific+10.661
Neg logit contributions
 Lauder-9.729
tumblr-9.146
 adoption-9.048
birth-8.987
 breastfeeding-8.936
Tokenakia
Token ID21897
Feature activation+7.97e+00

Pos logit contributions
 holiest+1.610
saf+1.447
cific+1.420
Trivia+1.400
 Advantage+1.382
Neg logit contributions
 debates-1.668
 adoption-1.627
birth-1.622
Pg-1.612
rons-1.596
Token
Token ID447
Feature activation+4.89e+00

Pos logit contributions
 holiest+6.560
saf+5.993
 Advantage+5.935
Trivia+5.827
cific+5.772
Neg logit contributions
 debates-4.556
Pg-4.498
tumblr-4.462
birth-4.438
 adoption-4.373
Token
Token ID247
Feature activation+1.40e+00

Pos logit contributions
 holiest+3.823
saf+3.456
cific+3.391
Trivia+3.369
 Advantage+3.333
Neg logit contributions
 debates-3.216
 adoption-3.120
birth-3.104
Pg-3.089
rons-3.081
Tokens
Token ID82
Feature activation+8.87e+00

Pos logit contributions
 holiest+1.174
saf+1.061
cific+1.050
Trivia+1.036
 Advantage+1.028
Neg logit contributions
 debates-0.851
birth-0.829
 adoption-0.829
Pg-0.820
rons-0.810
Token incident
Token ID4519
Feature activation+6.29e-01

Pos logit contributions
 holiest+1.486
saf+1.359
cific+1.340
Trivia+1.327
 Advantage+1.315
Neg logit contributions
 debates-0.941
 adoption-0.912
birth-0.907
Pg-0.898
rons-0.888
Token in
Token ID287
Feature activation+1.42e+00

Pos logit contributions
 holiest+0.572
saf+0.525
cific+0.522
Trivia+0.513
 Advantage+0.510
Neg logit contributions
 debates-0.341
 adoption-0.328
birth-0.324
 amounts-0.320
rons-0.319
Token the
Token ID262
Feature activation-5.44e-01

Pos logit contributions
 holiest+1.195
saf+1.089
cific+1.076
Trivia+1.066
 Advantage+1.051
Neg logit contributions
 debates-0.854
 adoption-0.829
birth-0.820
Pg-0.809
 amounts-0.805
Token revolution
Token ID5854
Feature activation-7.91e+00

Pos logit contributions
 debates+0.334
 adoption+0.326
birth+0.320
 amounts+0.316
Pg+0.314
Neg logit contributions
 holiest-0.447
saf-0.412
cific-0.411
Trivia-0.407
 Advantage-0.398
Token-
Token ID12
Feature activation+1.54e+00

Pos logit contributions
 debates+4.379
 adoption+4.103
 amounts+4.083
rons+4.013
 viewing+3.971
Neg logit contributions
 holiest-6.552
Trivia-6.200
cific-6.151
 Advantage-6.050
saf-6.025
Tokenwr
Token ID18351
Feature activation+1.65e+01

Pos logit contributions
 holiest+1.223
saf+1.101
cific+1.091
Trivia+1.079
 Advantage+1.071
Neg logit contributions
 debates-1.000
birth-0.973
 adoption-0.969
Pg-0.963
rons-0.952
Tokenacked
Token ID6021
Feature activation+7.33e-01

Pos logit contributions
 holiest+4.420
rown+3.995
saf+3.812
cific+3.650
cture+3.388
Neg logit contributions
 adoption-16.568
 Lauder-16.264
birth-16.157
tumblr-16.003
 debates-15.910
Token nation
Token ID3277
Feature activation-1.68e+00

Pos logit contributions
 holiest+0.605
saf+0.553
cific+0.548
Trivia+0.544
 Advantage+0.533
Neg logit contributions
 debates-0.453
 adoption-0.442
birth-0.436
Pg-0.429
 amounts-0.429
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
 debates+0.968
birth+0.929
 adoption+0.927
 amounts+0.915
rons+0.914
Neg logit contributions
 holiest-1.458
saf-1.328
cific-1.324
Trivia-1.304
 Advantage-1.297
Token a
Token ID257
Feature activation-1.98e-01

Pos logit contributions
 debates+0.090
 adoption+0.088
birth+0.086
 amounts+0.085
Pg+0.084
Neg logit contributions
 holiest-0.128
saf-0.117
cific-0.116
Trivia-0.115
 Advantage-0.113
Token senior
Token ID4664
Feature activation+3.69e+00

Pos logit contributions
 debates+0.117
 adoption+0.115
birth+0.111
 amounts+0.110
Pg+0.110
Neg logit contributions
 holiest-0.168
saf-0.155
cific-0.153
Trivia-0.152
 Advantage-0.149
Token De
Token ID1024
Feature activation-6.55e+00

Pos logit contributions
 debates+0.669
 adoption+0.646
birth+0.643
Pg+0.638
rons+0.629
Neg logit contributions
 holiest-1.181
saf-1.081
cific-1.067
Trivia-1.053
INGTON-1.039
Tokenvers
Token ID690
Feature activation-1.38e+00

Pos logit contributions
 debates+4.160
birth+4.131
 adoption+4.070
Pg+3.999
rons+3.972
Neg logit contributions
 holiest-4.998
saf-4.478
cific-4.430
 Advantage-4.285
INGTON-4.277
Token.
Token ID13
Feature activation-2.94e+00

Pos logit contributions
 debates+0.702
 adoption+0.678
birth+0.678
Pg+0.665
rons+0.663
Neg logit contributions
 holiest-1.297
saf-1.187
cific-1.173
Trivia-1.159
 Advantage-1.149
Token
Token ID198
Feature activation+7.30e-01

Pos logit contributions
 debates+1.726
birth+1.705
 adoption+1.701
Pg+1.683
rons+1.661
Neg logit contributions
 holiest-2.480
saf-2.222
cific-2.202
Trivia-2.176
INGTON-2.129
Token
Token ID198
Feature activation+2.28e-01

Pos logit contributions
 holiest+0.590
saf+0.535
cific+0.527
Trivia+0.522
 Advantage+0.516
Neg logit contributions
 debates-0.463
 adoption-0.450
birth-0.448
Pg-0.444
rons-0.440
TokenSl
Token ID11122
Feature activation+1.64e+01

Pos logit contributions
 holiest+0.161
saf+0.140
cific+0.138
 Advantage+0.136
Trivia+0.134
Neg logit contributions
 debates-0.169
birth-0.167
Pg-0.166
 adoption-0.166
rons-0.164
Tokenov
Token ID709
Feature activation+5.28e+00

Pos logit contributions
saf+11.243
ever+11.136
 holiest+11.100
rown+10.983
cific+10.899
Neg logit contributions
 Lauder-9.519
 breastfeeding-8.934
 bathing-8.917
 adoption-8.687
birth-8.686
Tokenakia
Token ID21897
Feature activation+9.60e+00

Pos logit contributions
 holiest+3.222
saf+3.056
cific+2.953
Trivia+2.840
 Advantage+2.822
Neg logit contributions
 debates-4.168
Pg-4.073
 adoption-4.060
birth-4.034
 amounts-4.011
Token:
Token ID25
Feature activation+1.36e+00

Pos logit contributions
 holiest+6.597
saf+6.024
 Advantage+5.919
cific+5.842
Trivia+5.834
Neg logit contributions
 debates-6.639
Pg-6.540
tumblr-6.438
 adoption-6.402
xon-6.402
Token Gre
Token ID11955
Feature activation+1.47e+00

Pos logit contributions
 holiest+1.236
saf+1.132
cific+1.118
Trivia+1.107
 Advantage+1.094
Neg logit contributions
 debates-0.725
 adoption-0.702
birth-0.698
Pg-0.690
rons-0.682
Tokenif
Token ID361
Feature activation-4.53e+00

Pos logit contributions
 holiest+1.148
saf+1.031
cific+1.013
Trivia+1.004
 Advantage+0.996
Neg logit contributions
 debates-0.972
birth-0.947
 adoption-0.946
Pg-0.936
rons-0.930
Token at
Token ID379
Feature activation+2.77e+00

Pos logit contributions
 holiest+0.075
saf+0.068
cific+0.067
Trivia+0.066
 Advantage+0.065
Neg logit contributions
 debates-0.059
 adoption-0.057
birth-0.057
rons-0.056
 amounts-0.056
Token Wel
Token ID22268
Feature activation+6.01e+00

Pos logit contributions
 holiest+2.630
saf+2.420
cific+2.390
Trivia+2.367
 Advantage+2.348
Neg logit contributions
 debates-1.364
 adoption-1.316
birth-1.308
Pg-1.294
rons-1.277
Tokenford
Token ID3841
Feature activation+6.09e+00

Pos logit contributions
 holiest+4.551
saf+4.351
cific+4.203
Trivia+4.165
rown+4.023
Neg logit contributions
 debates-3.824
 adoption-3.726
 clam-3.671
 amounts-3.660
Pg-3.658
Token Road
Token ID5567
Feature activation+7.20e+00

Pos logit contributions
 holiest+3.083
saf+2.695
 Advantage+2.604
Trivia+2.589
cific+2.577
Neg logit contributions
 debates-5.479
 adoption-5.373
Pg-5.367
birth-5.330
 bathing-5.280
Token,
Token ID11
Feature activation+4.20e+00

Pos logit contributions
 holiest+5.692
saf+5.192
cific+5.075
Trivia+5.073
 Advantage+5.073
Neg logit contributions
 debates-4.408
Pg-4.364
 adoption-4.320
birth-4.277
tumblr-4.248
Token Saturday
Token ID3909
Feature activation+1.61e+01

Pos logit contributions
 holiest+3.294
saf+2.968
cific+2.931
Trivia+2.887
 Advantage+2.880
Neg logit contributions
 debates-2.734
Pg-2.666
 adoption-2.653
birth-2.650
rons-2.614
Token 21
Token ID2310
Feature activation+7.89e+00

Pos logit contributions
 holiest+9.970
 Advantage+9.270
saf+9.220
cific+8.934
Trivia+8.703
Neg logit contributions
tumblr-10.595
Pg-10.535
 debates-10.280
xon-10.076
 adoption-10.068
Token January
Token ID3269
Feature activation+1.15e+01

Pos logit contributions
 holiest+5.598
saf+5.090
cific+4.983
Trivia+4.954
 Advantage+4.949
Neg logit contributions
 debates-5.367
Pg-5.263
 adoption-5.260
birth-5.226
tumblr-5.165
Token live
Token ID2107
Feature activation+6.88e-01

Pos logit contributions
 holiest+7.692
 Advantage+7.063
saf+6.981
Trivia+6.853
cific+6.812
Neg logit contributions
Pg-7.720
 debates-7.673
 adoption-7.569
tumblr-7.498
birth-7.489
Token on
Token ID319
Feature activation-2.07e+00

Pos logit contributions
 holiest+0.609
saf+0.555
cific+0.547
Trivia+0.542
 Advantage+0.537
Neg logit contributions
 debates-0.387
 adoption-0.374
birth-0.372
Pg-0.366
rons-0.365
Token BT
Token ID22205
Feature activation-4.69e+00

Pos logit contributions
 debates+1.095
 adoption+1.047
birth+1.032
 viewing+1.025
 amounts+1.017
Neg logit contributions
 holiest-1.882
saf-1.742
cific-1.715
Trivia-1.710
INGTON-1.679
Token!
Token ID0
Feature activation+2.98e+00

Pos logit contributions
 debates+0.656
 adoption+0.632
birth+0.627
Pg+0.621
rons+0.619
Neg logit contributions
 holiest-0.963
saf-0.885
cific-0.869
Trivia-0.856
 Advantage-0.845
Token
Token ID198
Feature activation+3.99e+00

Pos logit contributions
 holiest+2.428
saf+2.205
cific+2.170
Trivia+2.155
 Advantage+2.140
Neg logit contributions
 debates-1.857
 adoption-1.809
birth-1.799
Pg-1.783
rons-1.766
Token
Token ID198
Feature activation+2.49e+00

Pos logit contributions
 holiest+2.944
saf+2.722
Trivia+2.681
cific+2.642
 Advantage+2.612
Neg logit contributions
 debates-2.727
 adoption-2.650
rons-2.600
birth-2.588
 amounts-2.572
TokenWhen
Token ID2215
Feature activation+2.45e-01

Pos logit contributions
 holiest+1.936
saf+1.746
cific+1.720
Trivia+1.698
 Advantage+1.682
Neg logit contributions
 debates-1.652
 adoption-1.608
birth-1.603
Pg-1.590
rons-1.575
Token:
Token ID25
Feature activation+5.63e+00

Pos logit contributions
 holiest+0.206
saf+0.189
cific+0.186
Trivia+0.182
 Advantage+0.180
Neg logit contributions
 debates-0.150
 adoption-0.145
birth-0.143
 amounts-0.141
rons-0.141
Token Thursday
Token ID3635
Feature activation+1.59e+01

Pos logit contributions
 holiest+4.397
saf+3.959
 Advantage+3.877
cific+3.873
Trivia+3.864
Neg logit contributions
 debates-3.619
 adoption-3.538
Pg-3.533
birth-3.530
rons-3.486
Token,
Token ID11
Feature activation+8.64e+00

Pos logit contributions
 holiest+10.160
 Advantage+9.240
saf+9.021
Trivia+8.716
cific+8.625
Neg logit contributions
Pg-10.155
tumblr-10.125
anamo-10.021
 debates-9.909
birth-9.821
Token Jul
Token ID5979
Feature activation+1.29e+01

Pos logit contributions
 holiest+6.149
 Advantage+5.443
saf+5.437
Trivia+5.329
cific+5.324
Neg logit contributions
 debates-5.889
Pg-5.782
birth-5.721
 adoption-5.701
rons-5.697
Token 12
Token ID1105
Feature activation+8.57e+00

Pos logit contributions
 holiest+6.739
saf+6.267
cific+5.974
 Advantage+5.960
Trivia+5.824
Neg logit contributions
 debates-10.439
Pg-10.197
 adoption-10.185
 breastfeeding-10.082
 clam-10.011
Token 11
Token ID1367
Feature activation+1.73e+00

Pos logit contributions
 holiest+6.370
saf+5.813
 Advantage+5.703
cific+5.602
Trivia+5.588
Neg logit contributions
 debates-5.535
 adoption-5.442
Pg-5.412
birth-5.305
tumblr-5.297
Token:
Token ID25
Feature activation+2.94e-01

Pos logit contributions
 holiest+1.248
saf+1.118
cific+1.099
Trivia+1.082
 Advantage+1.065
Neg logit contributions
 debates-1.253
 adoption-1.223
birth-1.221
Pg-1.204
rons-1.195
Token a
Token ID257
Feature activation+2.41e+00

Pos logit contributions
 holiest+2.175
saf+1.991
cific+1.969
Trivia+1.945
 Advantage+1.913
Neg logit contributions
 debates-1.388
 adoption-1.353
birth-1.334
Pg-1.318
 amounts-1.308
Token way
Token ID835
Feature activation+6.97e+00

Pos logit contributions
 holiest+1.669
saf+1.487
cific+1.463
Trivia+1.445
 Advantage+1.421
Neg logit contributions
 debates-1.810
 adoption-1.775
birth-1.763
Pg-1.752
rons-1.734
Token to
Token ID284
Feature activation+9.48e+00

Pos logit contributions
 holiest+6.217
saf+5.750
cific+5.629
Trivia+5.573
 Advantage+5.518
Neg logit contributions
 debates-3.643
birth-3.501
 adoption-3.497
Pg-3.477
rons-3.450
Token make
Token ID787
Feature activation+8.30e+00

Pos logit contributions
 holiest+7.400
saf+6.883
cific+6.644
 Advantage+6.603
Trivia+6.496
Neg logit contributions
 debates-5.697
birth-5.638
Pg-5.595
 adoption-5.488
rons-5.469
Token a
Token ID257
Feature activation+4.90e+00

Pos logit contributions
 holiest+6.748
 Advantage+6.054
saf+6.045
Trivia+5.950
cific+5.944
Neg logit contributions
 debates-4.805
birth-4.760
Pg-4.697
rons-4.696
croft-4.668
Token profit
Token ID7630
Feature activation+1.58e+01

Pos logit contributions
 holiest+3.754
saf+3.378
cific+3.308
Trivia+3.285
 Advantage+3.257
Neg logit contributions
 debates-3.308
birth-3.196
 adoption-3.177
Pg-3.167
rons-3.165
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
 holiest+10.958
saf+10.177
 Advantage+9.982
Trivia+9.886
cific+9.784
Neg logit contributions
 debates-9.018
tumblr-8.827
Pg-8.730
birth-8.673
anamo-8.628
Token But
Token ID887
Feature activation+5.33e+00

Pos logit contributions
 debates+0.065
birth+0.064
 adoption+0.064
Pg+0.063
rons+0.062
Neg logit contributions
 holiest-0.090
saf-0.080
cific-0.080
Trivia-0.078
INGTON-0.077
Token that
Token ID326
Feature activation-1.68e+00

Pos logit contributions
 holiest+4.509
saf+4.122
cific+4.035
 Advantage+4.023
Trivia+3.999
Neg logit contributions
 debates-3.070
Pg-3.023
birth-2.986
 adoption-2.960
rons-2.925
Token profit
Token ID7630
Feature activation+7.58e+00

Pos logit contributions
 adoption+1.008
 debates+1.008
 amounts+0.983
birth+0.971
Pg+0.953
Neg logit contributions
 holiest-1.406
cific-1.284
saf-1.276
Trivia-1.263
INGTON-1.245
Token has
Token ID468
Feature activation+6.42e+00

Pos logit contributions
 holiest+6.274
saf+5.776
cific+5.672
Trivia+5.597
 Advantage+5.572
Neg logit contributions
 debates-4.382
Pg-4.226
birth-4.200
 adoption-4.178
rons-4.163
Token repeat
Token ID9585
Feature activation-5.63e+00

Pos logit contributions
 debates+1.664
 adoption+1.643
birth+1.604
Pg+1.584
rons+1.564
Neg logit contributions
 holiest-2.564
saf-2.370
cific-2.350
Trivia-2.322
 Advantage-2.263
Token.
Token ID13
Feature activation-2.43e+00

Pos logit contributions
 debates+3.099
 adoption+3.074
 amounts+3.022
 viewing+3.019
birth+2.967
Neg logit contributions
 holiest-4.897
saf-4.532
cific-4.489
Trivia-4.415
 Advantage-4.309
Token Posted
Token ID12918
Feature activation+3.89e+00

Pos logit contributions
 debates+1.399
Pg+1.377
birth+1.374
 adoption+1.368
tumblr+1.345
Neg logit contributions
 holiest-2.099
saf-1.885
cific-1.867
Trivia-1.808
INGTON-1.773
Token on
Token ID319
Feature activation-8.72e-01

Pos logit contributions
 holiest+3.157
saf+2.862
cific+2.820
Trivia+2.788
 Advantage+2.761
Neg logit contributions
 debates-2.451
 adoption-2.382
birth-2.374
Pg-2.354
rons-2.328
Token August
Token ID2932
Feature activation+8.36e+00

Pos logit contributions
 debates+0.517
 adoption+0.505
birth+0.498
 amounts+0.486
rons+0.482
Neg logit contributions
 holiest-0.743
cific-0.679
saf-0.675
Trivia-0.661
INGTON-0.654
Token 1
Token ID352
Feature activation+1.57e+01

Pos logit contributions
 holiest+4.826
saf+4.406
 Advantage+4.245
Trivia+4.216
cific+4.185
Neg logit contributions
 debates-6.803
 adoption-6.648
Pg-6.607
birth-6.547
rons-6.540
Token on
Token ID319
Feature activation+1.51e+00

Pos logit contributions
 holiest+9.737
saf+9.240
 Advantage+8.953
Trivia+8.787
cific+8.646
Neg logit contributions
 debates-10.409
Pg-10.309
 adoption-10.150
birth-10.059
 bathing-9.911
Token Facebook
Token ID3203
Feature activation+6.80e+00

Pos logit contributions
 holiest+1.297
saf+1.179
cific+1.172
Trivia+1.151
 Advantage+1.136
Neg logit contributions
 debates-0.891
 adoption-0.868
birth-0.854
Pg-0.841
rons-0.838
Token,
Token ID11
Feature activation+4.80e+00

Pos logit contributions
 holiest+5.348
saf+4.842
Trivia+4.767
cific+4.758
 Advantage+4.705
Neg logit contributions
 debates-4.324
 adoption-4.207
birth-4.205
Pg-4.185
rons-4.133
Token the
Token ID262
Feature activation+3.34e+00

Pos logit contributions
 holiest+4.077
saf+3.708
cific+3.665
Trivia+3.627
 Advantage+3.604
Neg logit contributions
 debates-2.792
birth-2.713
 adoption-2.704
Pg-2.691
rons-2.667
Token video
Token ID2008
Feature activation-5.49e+00

Pos logit contributions
 holiest+3.112
saf+2.855
cific+2.819
Trivia+2.792
 Advantage+2.771
Neg logit contributions
 debates-1.702
 adoption-1.640
birth-1.639
Pg-1.621
rons-1.604
Token Fore
Token ID4558
Feature activation+4.65e+00

Pos logit contributions
 debates+0.436
birth+0.422
 adoption+0.421
Pg+0.418
 amounts+0.413
Neg logit contributions
 holiest-0.603
saf-0.540
cific-0.536
Trivia-0.529
 Advantage-0.514
Tokencasters
Token ID26248
Feature activation+2.05e+00

Pos logit contributions
 holiest+3.945
saf+3.647
cific+3.569
Trivia+3.523
 Advantage+3.514
Neg logit contributions
 debates-2.701
 adoption-2.640
birth-2.610
Pg-2.596
rons-2.560
Token said
Token ID531
Feature activation+1.21e+00

Pos logit contributions
 holiest+1.817
saf+1.661
cific+1.639
Trivia+1.623
 Advantage+1.607
Neg logit contributions
 debates-1.141
 adoption-1.106
birth-1.099
Pg-1.087
rons-1.077
Token late
Token ID2739
Feature activation+3.95e+00

Pos logit contributions
 holiest+1.065
saf+0.977
cific+0.963
Trivia+0.955
 Advantage+0.940
Neg logit contributions
 debates-0.690
 adoption-0.669
birth-0.658
Pg-0.652
 amounts-0.650
Token on
Token ID319
Feature activation+1.62e-01

Pos logit contributions
 holiest+3.229
saf+2.907
cific+2.871
Trivia+2.832
 Advantage+2.830
Neg logit contributions
 debates-2.439
birth-2.386
 adoption-2.368
Pg-2.363
rons-2.328
Token Monday
Token ID3321
Feature activation+1.57e+01

Pos logit contributions
 holiest+0.140
saf+0.129
Trivia+0.126
cific+0.126
 Advantage+0.123
Neg logit contributions
 debates-0.095
 adoption-0.092
birth-0.091
 amounts-0.090
Pg-0.089
Token local
Token ID1957
Feature activation+3.00e+00

Pos logit contributions
 holiest+11.037
 Advantage+9.751
saf+9.689
cific+9.515
INGTON+9.262
Neg logit contributions
birth-9.486
Pg-9.295
tumblr-9.246
rons-9.025
 debates-9.018
Token time
Token ID640
Feature activation+1.23e+00

Pos logit contributions
 holiest+2.616
saf+2.387
cific+2.353
Trivia+2.329
 Advantage+2.314
Neg logit contributions
 debates-1.693
birth-1.644
 adoption-1.641
Pg-1.628
rons-1.605
Token that
Token ID326
Feature activation+5.42e-01

Pos logit contributions
 holiest+1.076
saf+0.983
cific+0.969
Trivia+0.962
 Advantage+0.946
Neg logit contributions
 debates-0.704
 adoption-0.681
birth-0.672
Pg-0.666
 amounts-0.662
Token Matthew
Token ID9308
Feature activation-4.92e+00

Pos logit contributions
 holiest+0.476
saf+0.436
cific+0.430
Trivia+0.426
 Advantage+0.419
Neg logit contributions
 debates-0.310
 adoption-0.302
birth-0.295
 amounts-0.295
Pg-0.293
Token would
Token ID561
Feature activation-5.02e+00

Pos logit contributions
 debates+2.705
 adoption+2.697
 amounts+2.692
 viewing+2.573
rons+2.560
Neg logit contributions
 holiest-4.302
cific-4.046
saf-3.969
Trivia-3.921
INGTON-3.799
Token an
Token ID281
Feature activation+3.00e+00

Pos logit contributions
 debates+0.700
 adoption+0.683
 amounts+0.666
Pg+0.660
birth+0.659
Neg logit contributions
 holiest-0.972
saf-0.889
Trivia-0.877
cific-0.871
 Advantage-0.863
Token Israeli
Token ID6085
Feature activation+2.51e+00

Pos logit contributions
 holiest+2.175
saf+1.950
cific+1.917
Trivia+1.893
 Advantage+1.870
Neg logit contributions
 debates-2.159
 adoption-2.109
birth-2.097
Pg-2.081
rons-2.063
Token official
Token ID1743
Feature activation+5.17e+00

Pos logit contributions
 holiest+1.752
saf+1.561
cific+1.534
Trivia+1.514
 Advantage+1.496
Neg logit contributions
 debates-1.864
 adoption-1.820
birth-1.815
Pg-1.801
rons-1.787
Token confirmed
Token ID4999
Feature activation+2.60e+00

Pos logit contributions
 holiest+4.084
saf+3.712
cific+3.639
Trivia+3.608
 Advantage+3.554
Neg logit contributions
 debates-3.286
birth-3.213
 adoption-3.207
Pg-3.204
rons-3.157
Token on
Token ID319
Feature activation+5.89e-01

Pos logit contributions
 holiest+2.288
saf+2.091
cific+2.062
Trivia+2.041
 Advantage+2.022
Neg logit contributions
 debates-1.470
 adoption-1.424
birth-1.418
Pg-1.404
rons-1.389
Token Thursday
Token ID3635
Feature activation+1.56e+01

Pos logit contributions
 holiest+0.477
saf+0.433
cific+0.429
Trivia+0.425
 Advantage+0.418
Neg logit contributions
 debates-0.373
 adoption-0.364
birth-0.360
Pg-0.356
 amounts-0.352
Token.
Token ID13
Feature activation+5.51e-01

Pos logit contributions
 holiest+9.789
saf+8.792
cific+8.524
 Advantage+8.259
Trivia+8.252
Neg logit contributions
tumblr-10.512
Pg-10.436
rons-10.261
birth-10.212
xon-10.172
Token
Token ID198
Feature activation+1.58e+00

Pos logit contributions
 holiest+0.462
saf+0.419
cific+0.413
Trivia+0.408
 Advantage+0.402
Neg logit contributions
 debates-0.334
 adoption-0.324
birth-0.322
Pg-0.322
rons-0.315
Token
Token ID198
Feature activation+3.20e-01

Pos logit contributions
 holiest+1.252
saf+1.140
cific+1.118
Trivia+1.110
 Advantage+1.097
Neg logit contributions
 debates-1.028
 adoption-0.999
birth-0.990
Pg-0.980
rons-0.979
TokenAlthough
Token ID7003
Feature activation-1.94e+00

Pos logit contributions
 holiest+0.254
saf+0.225
cific+0.225
 Advantage+0.224
Trivia+0.216
Neg logit contributions
Pg-0.208
 debates-0.207
birth-0.205
 adoption-0.203
rons-0.199
Token there
Token ID612
Feature activation-2.66e+00

Pos logit contributions
 debates+1.079
 adoption+1.039
Pg+1.007
birth+1.005
 amounts+1.002
Neg logit contributions
 holiest-1.733
saf-1.598
cific-1.572
Trivia-1.569
 Advantage-1.546
Token said
Token ID531
Feature activation+4.64e+00

Pos logit contributions
 holiest+1.092
saf+0.994
cific+0.981
Trivia+0.965
 Advantage+0.955
Neg logit contributions
 debates-0.807
 adoption-0.782
birth-0.778
Pg-0.766
rons-0.761
Token in
Token ID287
Feature activation+2.82e+00

Pos logit contributions
 holiest+3.921
saf+3.565
cific+3.494
Trivia+3.471
 Advantage+3.440
Neg logit contributions
 debates-2.691
Pg-2.642
birth-2.632
 adoption-2.630
rons-2.566
Token a
Token ID257
Feature activation+1.65e+00

Pos logit contributions
 holiest+2.326
saf+2.106
cific+2.073
Trivia+2.052
 Advantage+2.041
Neg logit contributions
 debates-1.718
 adoption-1.678
birth-1.675
Pg-1.673
rons-1.645
Token tweet
Token ID6126
Feature activation+7.05e+00

Pos logit contributions
 holiest+1.388
saf+1.262
cific+1.244
Trivia+1.231
 Advantage+1.219
Neg logit contributions
 debates-0.992
 adoption-0.963
birth-0.959
Pg-0.952
rons-0.941
Token on
Token ID319
Feature activation+2.03e+00

Pos logit contributions
 holiest+5.784
saf+5.236
cific+5.109
Trivia+5.078
 Advantage+5.033
Neg logit contributions
Pg-4.160
 debates-4.142
birth-4.073
 adoption-4.048
rons-3.981
Token Thursday
Token ID3635
Feature activation+1.55e+01

Pos logit contributions
 holiest+1.679
saf+1.525
cific+1.503
Trivia+1.487
 Advantage+1.472
Neg logit contributions
 debates-1.245
 adoption-1.210
birth-1.205
Pg-1.192
rons-1.181
Token,
Token ID11
Feature activation+6.18e+00

Pos logit contributions
 holiest+10.910
saf+9.644
Trivia+9.381
 Advantage+9.366
cific+9.187
Neg logit contributions
Pg-9.513
tumblr-8.935
birth-8.932
xon-8.889
 adoption-8.788
Token echoing
Token ID39915
Feature activation+1.18e-01

Pos logit contributions
 holiest+5.664
saf+5.174
cific+5.076
Trivia+5.033
 Advantage+5.029
Neg logit contributions
 debates-3.121
Pg-3.085
birth-3.027
 adoption-3.017
rons-3.006
Token criticisms
Token ID25094
Feature activation-2.88e-01

Pos logit contributions
 holiest+0.108
saf+0.100
cific+0.099
Trivia+0.097
 Advantage+0.096
Neg logit contributions
 debates-0.064
 adoption-0.061
birth-0.060
 amounts-0.059
rons-0.058
Token he
Token ID339
Feature activation+3.90e+00

Pos logit contributions
 debates+0.147
 adoption+0.141
birth+0.138
 amounts+0.137
rons+0.136
Neg logit contributions
 holiest-0.271
saf-0.250
cific-0.247
Trivia-0.245
 Advantage-0.241
Token made
Token ID925
Feature activation+4.01e+00

Pos logit contributions
 holiest+3.376
saf+3.090
cific+3.038
Trivia+3.006
 Advantage+2.985
Neg logit contributions
 debates-2.222
 adoption-2.159
birth-2.154
Pg-2.138
rons-2.108
Token was
Token ID373
Feature activation+2.28e+00

Pos logit contributions
 holiest+0.191
saf+0.175
cific+0.174
Trivia+0.172
 Advantage+0.169
Neg logit contributions
 debates-0.126
birth-0.120
 adoption-0.120
 amounts-0.120
Pg-0.119
Token the
Token ID262
Feature activation+2.56e+00

Pos logit contributions
 holiest+2.008
saf+1.836
cific+1.820
Trivia+1.801
 Advantage+1.774
Neg logit contributions
 debates-1.286
 adoption-1.245
birth-1.238
Pg-1.225
rons-1.209
Token Caps
Token ID23534
Feature activation-4.86e+00

Pos logit contributions
 holiest+2.185
saf+1.994
cific+1.975
Trivia+1.958
 Advantage+1.923
Neg logit contributions
 debates-1.519
 adoption-1.475
birth-1.457
Pg-1.440
 amounts-1.431
Token who
Token ID508
Feature activation+4.76e+00

Pos logit contributions
 debates+2.438
 adoption+2.400
rons+2.399
birth+2.329
 clam+2.319
Neg logit contributions
 holiest-4.426
saf-4.089
cific-4.083
Trivia-4.012
INGTON-3.863
Token struck
Token ID7425
Feature activation+7.40e+00

Pos logit contributions
 holiest+4.141
saf+3.785
cific+3.721
Trivia+3.684
 Advantage+3.660
Neg logit contributions
 debates-2.719
 adoption-2.639
birth-2.628
Pg-2.600
rons-2.573
Token first
Token ID717
Feature activation+1.54e+01

Pos logit contributions
 holiest+6.409
saf+5.790
 Advantage+5.691
cific+5.655
Trivia+5.588
Neg logit contributions
 debates-4.107
 adoption-3.980
birth-3.979
Pg-3.974
rons-3.920
Token when
Token ID618
Feature activation+2.70e+00

Pos logit contributions
 holiest+10.355
 Advantage+9.277
saf+8.855
cific+8.828
Trivia+8.611
Neg logit contributions
tumblr-9.879
Pg-9.668
 debates-9.580
catentry-9.537
rons-9.530
Token Alex
Token ID4422
Feature activation-6.70e+00

Pos logit contributions
 holiest+2.337
saf+2.133
cific+2.102
Trivia+2.081
 Advantage+2.071
Neg logit contributions
 debates-1.542
 adoption-1.495
birth-1.492
Pg-1.478
rons-1.461
Token O
Token ID440
Feature activation-1.64e+00

Pos logit contributions
 debates+3.155
birth+3.080
Pg+3.071
 amounts+3.049
 adoption+3.031
Neg logit contributions
 holiest-6.470
cific-5.925
saf-5.824
Trivia-5.675
INGTON-5.545
Tokenve
Token ID303
Feature activation-3.86e+00

Pos logit contributions
 debates+1.172
birth+1.126
Pg+1.122
rons+1.116
 adoption+1.107
Neg logit contributions
 holiest-1.224
saf-1.092
cific-1.059
Trivia-1.054
 Advantage-1.037
Tokench
Token ID354
Feature activation-3.06e+00

Pos logit contributions
 debates+1.677
 adoption+1.607
birth+1.599
Pg+1.580
rons+1.555
Neg logit contributions
 holiest-3.898
saf-3.615
cific-3.570
Trivia-3.531
 Advantage-3.493
Token be
Token ID307
Feature activation+2.97e+00

Pos logit contributions
 debates+0.258
 adoption+0.247
birth+0.246
 amounts+0.244
Pg+0.242
Neg logit contributions
 holiest-0.625
saf-0.574
cific-0.572
Trivia-0.570
 Advantage-0.563
Token placed
Token ID4624
Feature activation+5.32e+00

Pos logit contributions
 holiest+2.323
saf+2.098
cific+2.064
Trivia+2.040
 Advantage+2.020
Neg logit contributions
 debates-1.969
 adoption-1.917
birth-1.910
Pg-1.893
rons-1.876
Token at
Token ID379
Feature activation+2.68e+00

Pos logit contributions
 holiest+4.630
saf+4.231
cific+4.165
Trivia+4.127
 Advantage+4.094
Neg logit contributions
 debates-3.016
 adoption-2.928
birth-2.918
Pg-2.892
rons-2.849
Token the
Token ID262
Feature activation+2.68e+00

Pos logit contributions
 holiest+2.332
saf+2.127
cific+2.101
Trivia+2.078
 Advantage+2.053
Neg logit contributions
 debates-1.542
 adoption-1.500
birth-1.491
Pg-1.472
rons-1.458
Token 0
Token ID657
Feature activation+5.28e+00

Pos logit contributions
 holiest+2.197
saf+1.996
cific+1.970
Trivia+1.946
 Advantage+1.923
Neg logit contributions
 debates-1.669
 adoption-1.626
birth-1.615
Pg-1.599
rons-1.582
Tokenth
Token ID400
Feature activation+1.53e+01

Pos logit contributions
 holiest+4.089
saf+3.683
cific+3.599
Trivia+3.562
 Advantage+3.534
Neg logit contributions
 debates-3.492
 adoption-3.391
birth-3.361
Pg-3.351
rons-3.345
Token index
Token ID6376
Feature activation+1.64e+00

Pos logit contributions
 holiest+11.546
saf+10.216
 Advantage+9.980
cific+9.744
Trivia+9.549
Neg logit contributions
 debates-8.917
rons-8.673
tumblr-8.638
anamo-8.525
Pg-8.466
Token.
Token ID13
Feature activation-1.53e+00

Pos logit contributions
 holiest+1.418
saf+1.294
cific+1.280
Trivia+1.269
 Advantage+1.249
Neg logit contributions
 debates-0.949
 adoption-0.926
birth-0.919
Pg-0.910
rons-0.903
Token
Token ID198
Feature activation+1.12e+00

Pos logit contributions
 debates+0.905
 adoption+0.882
birth+0.882
Pg+0.870
 amounts+0.862
Neg logit contributions
 holiest-1.318
saf-1.186
cific-1.170
Trivia-1.145
INGTON-1.137
Token
Token ID198
Feature activation-8.35e-01

Pos logit contributions
 holiest+0.899
saf+0.817
cific+0.803
Trivia+0.796
 Advantage+0.787
Neg logit contributions
 debates-0.714
 adoption-0.695
birth-0.690
Pg-0.684
rons-0.680
TokenAfter
Token ID3260
Feature activation-3.37e+00

Pos logit contributions
birth+0.529
Pg+0.528
 debates+0.527
 adoption+0.520
tumblr+0.509
Neg logit contributions
 holiest-0.682
cific-0.599
saf-0.595
 Advantage-0.592
INGTON-0.580
Token phone
Token ID3072
Feature activation-8.72e-01

Pos logit contributions
 debates+0.085
 adoption+0.083
birth+0.081
Pg+0.081
rons+0.080
Neg logit contributions
 holiest-0.171
saf-0.156
cific-0.156
Trivia-0.153
 Advantage-0.152
Token in
Token ID287
Feature activation+1.28e+00

Pos logit contributions
 debates+0.502
 adoption+0.487
birth+0.478
 amounts+0.471
 viewing+0.470
Neg logit contributions
 holiest-0.765
saf-0.700
cific-0.689
Trivia-0.678
 Advantage-0.669
Token downtown
Token ID9436
Feature activation+3.52e+00

Pos logit contributions
 holiest+1.007
saf+0.913
cific+0.901
Trivia+0.887
 Advantage+0.875
Neg logit contributions
 debates-0.848
 adoption-0.826
birth-0.818
Pg-0.810
rons-0.805
Token Toronto
Token ID6586
Feature activation+3.59e+00

Pos logit contributions
 holiest+2.369
saf+2.097
cific+2.053
Trivia+2.035
 Advantage+2.015
Neg logit contributions
 debates-2.691
birth-2.628
 adoption-2.624
Pg-2.613
rons-2.582
Token on
Token ID319
Feature activation-1.20e+00

Pos logit contributions
 holiest+2.963
saf+2.693
cific+2.651
Trivia+2.634
 Advantage+2.607
Neg logit contributions
 debates-2.188
 adoption-2.127
birth-2.122
Pg-2.116
rons-2.087
Token Monday
Token ID3321
Feature activation+1.52e+01

Pos logit contributions
 debates+0.685
 adoption+0.678
birth+0.658
 amounts+0.648
 viewing+0.637
Neg logit contributions
 holiest-1.034
saf-0.961
cific-0.953
Trivia-0.942
INGTON-0.925
Token.
Token ID13
Feature activation+8.49e-01

Pos logit contributions
 holiest+10.120
saf+9.029
Trivia+8.912
 Advantage+8.832
cific+8.736
Neg logit contributions
Pg-9.707
 debates-9.551
tumblr-9.459
birth-9.447
xon-9.408
Token Liberal
Token ID12266
Feature activation-1.72e-01

Pos logit contributions
 holiest+0.772
saf+0.705
cific+0.698
Trivia+0.689
 Advantage+0.678
Neg logit contributions
 debates-0.455
 adoption-0.443
birth-0.441
Pg-0.434
rons-0.429
Token MP
Token ID4904
Feature activation-4.83e+00

Pos logit contributions
 debates+0.105
 adoption+0.101
birth+0.098
 amounts+0.098
rons+0.097
Neg logit contributions
 holiest-0.146
saf-0.135
cific-0.134
Trivia-0.131
 Advantage-0.128
TokenP
Token ID47
Feature activation+1.61e-01

Pos logit contributions
 debates+2.632
 adoption+2.524
rons+2.433
Pg+2.431
birth+2.422
Neg logit contributions
 holiest-4.370
saf-4.008
cific-3.907
Trivia-3.860
INGTON-3.852
Token Y
Token ID575
Feature activation-4.76e+00

Pos logit contributions
 holiest+0.142
saf+0.130
cific+0.129
Trivia+0.127
 Advantage+0.125
Neg logit contributions
 debates-0.092
 adoption-0.088
birth-0.087
Pg-0.085
 amounts-0.085
Token,
Token ID11
Feature activation+9.29e-01

Pos logit contributions
 holiest+5.091
saf+4.619
cific+4.570
Trivia+4.499
 Advantage+4.495
Neg logit contributions
 debates-4.182
Pg-4.158
birth-4.140
 adoption-4.090
rons-4.045
Token in
Token ID287
Feature activation+3.49e+00

Pos logit contributions
 holiest+0.872
saf+0.800
cific+0.787
Trivia+0.785
 Advantage+0.773
Neg logit contributions
 debates-0.477
 adoption-0.460
birth-0.454
rons-0.443
 amounts-0.443
Token a
Token ID257
Feature activation+1.56e+00

Pos logit contributions
 holiest+2.898
saf+2.628
cific+2.603
Trivia+2.562
 Advantage+2.551
Neg logit contributions
 debates-2.099
 adoption-2.047
birth-2.046
Pg-2.035
rons-2.011
Token statement
Token ID2643
Feature activation+3.29e+00

Pos logit contributions
 holiest+1.333
saf+1.215
cific+1.197
Trivia+1.186
 Advantage+1.174
Neg logit contributions
 debates-0.919
 adoption-0.892
birth-0.887
Pg-0.878
rons-0.870
Token on
Token ID319
Feature activation+5.40e-01

Pos logit contributions
 holiest+2.656
saf+2.407
cific+2.371
Trivia+2.338
 Advantage+2.320
Neg logit contributions
 debates-2.080
 adoption-2.024
birth-2.021
Pg-2.010
rons-1.983
Token Monday
Token ID3321
Feature activation+1.51e+01

Pos logit contributions
 holiest+0.464
saf+0.425
cific+0.418
Trivia+0.416
 Advantage+0.407
Neg logit contributions
 debates-0.320
 adoption-0.311
birth-0.306
Pg-0.301
rons-0.299
Token.
Token ID13
Feature activation-2.20e-01

Pos logit contributions
 holiest+9.179
saf+8.153
cific+8.046
 Advantage+7.979
Trivia+7.738
Neg logit contributions
tumblr-10.472
Pg-10.419
 debates-10.207
birth-10.201
rons-10.133
Token
Token ID198
Feature activation-4.01e-01

Pos logit contributions
 debates+0.135
 adoption+0.131
birth+0.130
Pg+0.129
rons+0.128
Neg logit contributions
 holiest-0.183
saf-0.166
cific-0.163
Trivia-0.162
 Advantage-0.159
Token
Token ID198
Feature activation-2.14e+00

Pos logit contributions
 debates+0.243
birth+0.237
 adoption+0.236
Pg+0.235
rons+0.230
Neg logit contributions
 holiest-0.338
saf-0.304
cific-0.302
Trivia-0.296
 Advantage-0.294
TokenBut
Token ID1537
Feature activation+3.33e+00

Pos logit contributions
Pg+1.282
birth+1.265
 debates+1.252
 adoption+1.217
tumblr+1.206
Neg logit contributions
 holiest-1.832
cific-1.634
saf-1.610
 Advantage-1.600
INGTON-1.538
Token given
Token ID1813
Feature activation-3.84e+00

Pos logit contributions
 holiest+3.148
saf+2.889
cific+2.861
Trivia+2.830
 Advantage+2.819
Neg logit contributions
 debates-1.630
birth-1.581
 adoption-1.579
Pg-1.570
rons-1.543
Tokenokane
Token ID41776
Feature activation+1.21e+01

Pos logit contributions
 holiest+4.582
saf+4.357
cific+4.337
Trivia+3.973
INGTON+3.756
Neg logit contributions
 debates-10.230
 Lauder-10.061
 cort-10.050
 adoption-10.024
 bathing-10.017
Token police
Token ID1644
Feature activation+1.45e+00

Pos logit contributions
 holiest+9.181
saf+8.410
INGTON+8.370
 Advantage+8.357
Trivia+8.311
Neg logit contributions
 debates-7.045
birth-7.041
tumblr-7.025
rons-7.013
Pg-6.966
Token arrested
Token ID5169
Feature activation+4.58e+00

Pos logit contributions
 holiest+1.229
saf+1.113
cific+1.106
Trivia+1.092
 Advantage+1.071
Neg logit contributions
 debates-0.880
 adoption-0.857
birth-0.841
rons-0.836
 amounts-0.828
Token one
Token ID530
Feature activation+9.93e+00

Pos logit contributions
 holiest+3.776
saf+3.429
cific+3.376
Trivia+3.335
 Advantage+3.324
Neg logit contributions
 debates-2.795
birth-2.719
 adoption-2.713
Pg-2.704
rons-2.660
Token suspect
Token ID4099
Feature activation+4.92e+00

Pos logit contributions
 holiest+7.385
saf+6.552
cific+6.520
 Advantage+6.514
Trivia+6.402
Neg logit contributions
 debates-6.498
Pg-6.336
birth-6.256
rons-6.183
 adoption-6.131
Token Thursday
Token ID3635
Feature activation+1.51e+01

Pos logit contributions
 holiest+4.183
saf+3.796
cific+3.750
Trivia+3.711
 Advantage+3.683
Neg logit contributions
 debates-2.871
birth-2.795
 adoption-2.781
Pg-2.768
rons-2.722
Token night
Token ID1755
Feature activation+1.10e+01

Pos logit contributions
 holiest+10.041
saf+8.922
cific+8.858
 Advantage+8.774
Trivia+8.553
Neg logit contributions
Pg-9.774
birth-9.721
tumblr-9.557
 debates-9.473
xon-9.412
Token and
Token ID290
Feature activation+6.79e+00

Pos logit contributions
 holiest+8.238
saf+7.447
cific+7.441
 Advantage+7.243
Trivia+7.233
Neg logit contributions
birth-6.727
Pg-6.716
 debates-6.712
 adoption-6.578
tumblr-6.520
Token charged
Token ID5047
Feature activation+2.27e+00

Pos logit contributions
 holiest+5.810
saf+5.372
cific+5.200
 Advantage+5.194
Trivia+5.145
Neg logit contributions
 debates-3.765
Pg-3.718
birth-3.702
 adoption-3.630
rons-3.549
Token him
Token ID683
Feature activation+1.80e+00

Pos logit contributions
 holiest+1.934
saf+1.759
cific+1.735
Trivia+1.720
 Advantage+1.696
Neg logit contributions
 debates-1.358
 adoption-1.321
birth-1.307
Pg-1.291
rons-1.287
Token with
Token ID351
Feature activation+2.28e+00

Pos logit contributions
 holiest+1.601
saf+1.465
cific+1.445
Trivia+1.429
 Advantage+1.415
Neg logit contributions
 debates-0.999
 adoption-0.970
birth-0.961
Pg-0.947
rons-0.945
Token to
Token ID284
Feature activation+1.93e+00

Pos logit contributions
birth+5.114
 viewing+5.070
 adoption+5.062
 crying+4.969
 debates+4.929
Neg logit contributions
 holiest-10.476
cific-9.717
saf-9.562
 Advantage-9.466
INGTON-9.415
Token supposedly
Token ID13519
Feature activation+4.42e+00

Pos logit contributions
 holiest+1.642
saf+1.494
cific+1.479
Trivia+1.458
 Advantage+1.446
Neg logit contributions
 debates-1.161
 adoption-1.127
birth-1.119
Pg-1.100
 amounts-1.092
Token kill
Token ID1494
Feature activation+2.91e+00

Pos logit contributions
 holiest+3.753
saf+3.424
cific+3.361
Trivia+3.330
 Advantage+3.301
Neg logit contributions
 debates-2.595
 adoption-2.520
birth-2.509
Pg-2.499
rons-2.472
Token actor
Token ID8674
Feature activation+1.03e+00

Pos logit contributions
 holiest+2.674
saf+2.455
cific+2.420
Trivia+2.398
 Advantage+2.379
Neg logit contributions
 debates-1.512
 adoption-1.463
birth-1.457
Pg-1.441
rons-1.424
Token Neil
Token ID15929
Feature activation-5.34e+00

Pos logit contributions
 holiest+0.910
saf+0.830
cific+0.822
Trivia+0.808
 Advantage+0.799
Neg logit contributions
 debates-0.588
 adoption-0.569
birth-0.566
Pg-0.558
rons-0.555
Token Patrick
Token ID9925
Feature activation-1.74e+01

Pos logit contributions
 debates+2.790
birth+2.747
rons+2.741
 Weiner+2.707
croft+2.663
Neg logit contributions
 holiest-4.726
cific-4.384
saf-4.372
Trivia-4.267
INGTON-4.256
Token Harris
Token ID10026
Feature activation-6.17e+00

Pos logit contributions
 Weiner+5.728
 Bradley+5.629
 reading+5.614
rons+5.495
 debates+5.464
Neg logit contributions
 holiest-17.868
cific-16.616
saf-16.049
rown-15.742
INGTON-15.610
Token,
Token ID11
Feature activation-2.50e+00

Pos logit contributions
 debates+3.177
birth+3.073
 amounts+3.053
 adoption+3.012
 viewing+2.989
Neg logit contributions
 holiest-5.630
saf-5.119
cific-5.105
 Advantage-5.029
Trivia-4.883
Token who
Token ID508
Feature activation+1.14e+00

Pos logit contributions
 debates+1.272
 adoption+1.234
birth+1.210
 amounts+1.200
 viewing+1.194
Neg logit contributions
 holiest-2.322
saf-2.142
cific-2.136
Trivia-2.091
 Advantage-2.077
Token is
Token ID318
Feature activation+5.06e-01

Pos logit contributions
 holiest+1.018
saf+0.928
cific+0.925
Trivia+0.906
 Advantage+0.903
Neg logit contributions
 debates-0.641
 adoption-0.614
birth-0.609
 amounts-0.602
Pg-0.601
Token never
Token ID1239
Feature activation-1.87e+00

Pos logit contributions
 holiest+0.457
saf+0.419
cific+0.419
Trivia+0.409
 Advantage+0.408
Neg logit contributions
 debates-0.273
 adoption-0.264
birth-0.263
Pg-0.259
 amounts-0.256
Token country
Token ID1499
Feature activation-1.90e+00

Pos logit contributions
 debates+0.367
 adoption+0.352
birth+0.349
 amounts+0.337
Pg+0.336
Neg logit contributions
 holiest-0.840
saf-0.783
cific-0.782
Trivia-0.773
 Advantage-0.756
Token,
Token ID11
Feature activation-7.64e-01

Pos logit contributions
 debates+1.071
birth+1.036
 adoption+1.027
 amounts+1.005
rons+1.001
Neg logit contributions
 holiest-1.677
saf-1.538
cific-1.526
Trivia-1.502
 Advantage-1.486
Token have
Token ID423
Feature activation-1.06e-01

Pos logit contributions
 debates+0.431
 adoption+0.418
birth+0.413
 amounts+0.404
 viewing+0.401
Neg logit contributions
 holiest-0.673
saf-0.618
cific-0.613
Trivia-0.610
 Advantage-0.597
Token to
Token ID284
Feature activation-4.22e+00

Pos logit contributions
 debates+0.062
 adoption+0.060
birth+0.059
rons+0.058
Pg+0.058
Neg logit contributions
 holiest-0.092
saf-0.084
cific-0.084
Trivia-0.083
 Advantage-0.081
Token accept
Token ID2453
Feature activation-4.60e+00

Pos logit contributions
 debates+2.114
 adoption+2.035
birth+1.989
 clam+1.976
 amounts+1.957
Neg logit contributions
 holiest-3.928
cific-3.675
Trivia-3.640
saf-3.569
 Advantage-3.551
Token mass
Token ID2347
Feature activation-1.70e+01

Pos logit contributions
 debates+2.501
 adoption+2.454
birth+2.337
 amounts+2.310
 viewing+2.273
Neg logit contributions
 holiest-4.093
cific-3.875
saf-3.836
Trivia-3.784
INGTON-3.650
Token immigration
Token ID6272
Feature activation-9.35e+00

Pos logit contributions
 adoption+8.705
 amounts+8.353
 debates+7.966
birth+7.903
 viewing+7.620
Neg logit contributions
 holiest-14.431
cific-13.631
saf-13.237
Trivia-13.204
cture-12.553
Token from
Token ID422
Feature activation-8.34e-01

Pos logit contributions
 debates+4.621
 amounts+4.424
 adoption+4.378
 viewing+4.177
birth+4.126
Neg logit contributions
 holiest-8.549
saf-8.046
cific-8.007
Trivia-7.760
cture-7.580
Token Africa
Token ID5478
Feature activation+2.86e+00

Pos logit contributions
 debates+0.489
 adoption+0.476
birth+0.470
 amounts+0.461
Pg+0.457
Neg logit contributions
 holiest-0.717
saf-0.656
cific-0.650
Trivia-0.642
 Advantage-0.630
Token,
Token ID11
Feature activation-2.89e+00

Pos logit contributions
 holiest+2.476
saf+2.260
cific+2.224
Trivia+2.203
 Advantage+2.185
Neg logit contributions
 debates-1.647
 adoption-1.598
birth-1.591
Pg-1.576
rons-1.561
Token the
Token ID262
Feature activation-6.80e-01

Pos logit contributions
 debates+1.671
 adoption+1.641
birth+1.614
 amounts+1.572
 viewing+1.553
Neg logit contributions
 holiest-2.488
saf-2.277
Trivia-2.273
cific-2.268
 Advantage-2.202
Token dialect
Token ID23637
Feature activation+1.31e+00

Pos logit contributions
 holiest+0.341
saf+0.312
cific+0.309
Trivia+0.306
 Advantage+0.301
Neg logit contributions
 debates-0.220
 adoption-0.214
birth-0.211
Pg-0.209
rons-0.207
Tokenic
Token ID291
Feature activation+2.13e-01

Pos logit contributions
 holiest+0.945
saf+0.841
cific+0.827
Trivia+0.819
 Advantage+0.808
Neg logit contributions
 debates-0.957
 adoption-0.933
birth-0.932
Pg-0.922
rons-0.917
Token of
Token ID286
Feature activation+9.44e-01

Pos logit contributions
 holiest+0.187
saf+0.171
cific+0.169
Trivia+0.167
 Advantage+0.165
Neg logit contributions
 debates-0.122
 adoption-0.118
birth-0.117
Pg-0.116
rons-0.115
Token an
Token ID281
Feature activation-9.25e-01

Pos logit contributions
 holiest+0.831
saf+0.761
cific+0.751
Trivia+0.743
 Advantage+0.729
Neg logit contributions
 debates-0.542
 adoption-0.525
birth-0.517
Pg-0.512
rons-0.508
Token extended
Token ID7083
Feature activation-7.69e+00

Pos logit contributions
 debates+0.569
 adoption+0.561
birth+0.545
Pg+0.538
rons+0.536
Neg logit contributions
 holiest-0.776
saf-0.708
cific-0.695
Trivia-0.691
INGTON-0.676
Token mass
Token ID2347
Feature activation-1.68e+01

Pos logit contributions
 debates+4.303
 adoption+4.205
 clam+3.976
 amounts+3.945
 viewing+3.941
Neg logit contributions
 holiest-6.613
saf-6.190
cific-6.127
Trivia-6.085
INGTON-5.813
Token revolt
Token ID27360
Feature activation-5.44e+00

Pos logit contributions
 adoption+8.631
 debates+8.336
 clam+8.120
birth+8.102
 discussion+7.906
Neg logit contributions
 holiest-13.947
Trivia-12.296
saf-12.261
cific-11.991
INGTON-11.596
Token and
Token ID290
Feature activation-1.47e+00

Pos logit contributions
 debates+2.697
 adoption+2.560
Pg+2.530
 amounts+2.517
rons+2.510
Neg logit contributions
 holiest-5.138
saf-4.645
Trivia-4.606
cific-4.597
 Advantage-4.554
Token a
Token ID257
Feature activation-3.86e+00

Pos logit contributions
 debates+0.840
 adoption+0.816
birth+0.794
Pg+0.789
rons+0.777
Neg logit contributions
 holiest-1.297
saf-1.191
cific-1.168
Trivia-1.166
 Advantage-1.148
Token defeated
Token ID9772
Feature activation-4.72e-01

Pos logit contributions
 debates+2.189
 adoption+2.130
Pg+2.098
birth+2.082
 clam+2.056
Neg logit contributions
 holiest-3.362
saf-3.102
Trivia-3.048
cific-3.015
 Advantage-3.009
Token proletarian
Token ID47393
Feature activation-5.79e-01

Pos logit contributions
 debates+0.270
 adoption+0.263
birth+0.257
Pg+0.257
rons+0.254
Neg logit contributions
 holiest-0.414
saf-0.380
cific-0.375
Trivia-0.373
 Advantage-0.363
Token dominated
Token ID13354
Feature activation+5.39e-01

Pos logit contributions
 holiest+1.605
saf+1.466
cific+1.448
Trivia+1.434
 Advantage+1.415
Neg logit contributions
 debates-1.061
 adoption-1.027
birth-1.017
Pg-1.008
rons-1.000
Token political
Token ID1964
Feature activation-5.59e-01

Pos logit contributions
 holiest+0.481
saf+0.442
cific+0.436
Trivia+0.432
 Advantage+0.426
Neg logit contributions
 debates-0.300
 adoption-0.289
birth-0.285
Pg-0.281
rons-0.279
Token institutions
Token ID6712
Feature activation-3.70e-01

Pos logit contributions
 debates+0.257
 adoption+0.241
birth+0.231
 amounts+0.229
rons+0.227
Neg logit contributions
 holiest-0.562
cific-0.520
saf-0.520
Trivia-0.514
 Advantage-0.505
Token and
Token ID290
Feature activation-9.13e-02

Pos logit contributions
 debates+0.203
 adoption+0.195
birth+0.192
 amounts+0.189
rons+0.188
Neg logit contributions
 holiest-0.333
saf-0.307
cific-0.305
Trivia-0.303
 Advantage-0.298
Token the
Token ID262
Feature activation-2.07e+00

Pos logit contributions
 debates+0.050
 adoption+0.047
 amounts+0.046
birth+0.046
rons+0.045
Neg logit contributions
 holiest-0.083
saf-0.077
cific-0.076
Trivia-0.075
 Advantage-0.074
Token mass
Token ID2347
Feature activation-1.65e+01

Pos logit contributions
 debates+1.079
 adoption+1.026
 amounts+0.983
rons+0.976
birth+0.972
Neg logit contributions
 holiest-1.932
cific-1.806
saf-1.798
Trivia-1.770
 Advantage-1.746
Token media
Token ID2056
Feature activation-8.27e+00

Pos logit contributions
 adoption+6.236
 debates+6.225
 amounts+5.869
 viewing+5.676
 discussion+5.600
Neg logit contributions
 holiest-15.933
cific-15.041
saf-14.493
 Advantage-14.354
Trivia-14.344
Token,
Token ID11
Feature activation-2.02e+00

Pos logit contributions
 debates+4.459
 adoption+4.210
 amounts+4.082
 viewing+4.031
 clam+3.961
Neg logit contributions
 holiest-7.362
cific-6.875
saf-6.863
Trivia-6.735
INGTON-6.726
Token leading
Token ID3756
Feature activation-2.37e+00

Pos logit contributions
 debates+1.118
 adoption+1.072
birth+1.038
 amounts+1.037
 viewing+1.032
Neg logit contributions
 holiest-1.812
saf-1.673
cific-1.667
Trivia-1.652
 Advantage-1.614
Token to
Token ID284
Feature activation-2.53e+00

Pos logit contributions
 debates+1.118
 adoption+1.054
Pg+1.019
 amounts+1.019
birth+1.016
Neg logit contributions
 holiest-2.329
saf-2.166
cific-2.136
Trivia-2.121
 Advantage-2.090
Token a
Token ID257
Feature activation-4.82e+00

Pos logit contributions
 debates+1.442
 adoption+1.364
 amounts+1.317
birth+1.306
 viewing+1.298
Neg logit contributions
 holiest-2.261
saf-2.091
cific-2.066
Trivia-2.050
 Advantage-2.018
Token United
Token ID1578
Feature activation-1.93e+00

Pos logit contributions
 debates+0.008
 adoption+0.008
birth+0.008
Pg+0.008
 amounts+0.008
Neg logit contributions
 holiest-0.013
saf-0.012
cific-0.012
Trivia-0.011
 Advantage-0.011
Token Nations
Token ID7973
Feature activation-8.20e+00

Pos logit contributions
 debates+1.687
 adoption+1.651
birth+1.646
rons+1.628
Pg+1.627
Neg logit contributions
 holiest-1.088
saf-0.949
cific-0.928
Trivia-0.912
 Advantage-0.897
Token,
Token ID11
Feature activation-4.45e+00

Pos logit contributions
 debates+3.776
 adoption+3.549
 amounts+3.427
birth+3.403
 viewing+3.385
Neg logit contributions
 holiest-7.870
cific-7.280
 Advantage-7.253
saf-7.203
INGTON-7.009
Token Susan
Token ID14919
Feature activation-6.42e+00

Pos logit contributions
 debates+2.404
 adoption+2.341
birth+2.297
 amounts+2.241
Pg+2.198
Neg logit contributions
 holiest-4.037
saf-3.710
Trivia-3.630
cific-3.629
 Advantage-3.607
Token E
Token ID412
Feature activation-9.59e+00

Pos logit contributions
 debates+2.634
birth+2.526
 Lauder+2.486
 adoption+2.467
 Weiner+2.456
Neg logit contributions
 holiest-6.465
saf-6.118
Trivia-5.995
INGTON-5.962
cific-5.957
Token.
Token ID13
Feature activation-1.65e+01

Pos logit contributions
 debates+4.415
birth+4.301
 adoption+4.128
 amounts+4.050
 bell+4.042
Neg logit contributions
 holiest-9.175
saf-8.248
INGTON-8.193
 Advantage-8.163
Trivia-8.021
Token Rice
Token ID13823
Feature activation-7.11e+00

Pos logit contributions
 Lauder+4.522
 Bradley+4.085
 Weiner+4.045
birth+3.887
 Flynn+3.808
Neg logit contributions
 holiest-18.153
saf-17.129
INGTON-16.382
Trivia-16.293
cific-16.023
Token,
Token ID11
Feature activation-3.90e+00

Pos logit contributions
 debates+3.361
birth+3.205
 adoption+3.167
 amounts+3.093
rons+3.091
Neg logit contributions
 holiest-6.813
saf-6.134
cific-6.089
 Advantage-6.087
Trivia-6.013
Token said
Token ID531
Feature activation+7.31e-01

Pos logit contributions
 debates+2.221
 adoption+2.124
birth+2.113
 viewing+2.081
 amounts+2.066
Neg logit contributions
 holiest-3.403
cific-3.072
saf-3.065
 Advantage-3.047
Trivia-3.025
Token Friday
Token ID3217
Feature activation+1.21e+01

Pos logit contributions
 holiest+0.648
saf+0.593
cific+0.585
Trivia+0.581
 Advantage+0.575
Neg logit contributions
 debates-0.411
 adoption-0.397
birth-0.394
Pg-0.388
rons-0.386
Token that
Token ID326
Feature activation+1.69e+00

Pos logit contributions
 holiest+8.678
saf+7.745
cific+7.578
 Advantage+7.382
Trivia+7.375
Neg logit contributions
Pg-7.568
tumblr-7.513
birth-7.492
 debates-7.320
xon-7.315
Token her
Token ID607
Feature activation-1.36e+00

Pos logit contributions
 debates+0.388
 adoption+0.376
birth+0.364
 amounts+0.362
Pg+0.357
Neg logit contributions
 holiest-0.596
saf-0.545
cific-0.538
Trivia-0.533
 Advantage-0.519
Token rival
Token ID8976
Feature activation-2.76e+00

Pos logit contributions
 debates+0.904
 adoption+0.879
birth+0.857
 amounts+0.847
rons+0.840
Neg logit contributions
 holiest-1.075
saf-0.983
cific-0.975
Trivia-0.957
INGTON-0.932
Token Sen
Token ID2311
Feature activation-2.02e+00

Pos logit contributions
 debates+1.462
 adoption+1.398
 amounts+1.349
birth+1.339
rons+1.333
Neg logit contributions
 holiest-2.558
saf-2.359
cific-2.334
Trivia-2.301
INGTON-2.240
Token.
Token ID13
Feature activation-6.82e+00

Pos logit contributions
 debates+1.206
birth+1.166
 adoption+1.161
Pg+1.145
rons+1.132
Neg logit contributions
 holiest-1.745
saf-1.570
Trivia-1.536
cific-1.526
INGTON-1.522
Token Barbara
Token ID16685
Feature activation-8.94e+00

Pos logit contributions
 debates+3.092
 adoption+2.941
 amounts+2.891
 Bradley+2.799
 bell+2.793
Neg logit contributions
 holiest-6.751
saf-6.313
cific-6.184
INGTON-6.030
Trivia-5.992
Token Box
Token ID8315
Feature activation-1.64e+01

Pos logit contributions
 Bradley+2.263
 debates+2.166
 Weiner+2.135
birth+2.048
 viewing+2.019
Neg logit contributions
 holiest-10.874
saf-9.856
cific-9.621
Trivia-9.571
INGTON-9.457
Tokener
Token ID263
Feature activation-6.12e+00

Pos logit contributions
birth+4.992
 debates+4.760
xon+4.683
 amounts+4.591
croft+4.422
Neg logit contributions
 holiest-17.383
cific-16.043
saf-15.916
Trivia-15.794
alties-15.344
Token,
Token ID11
Feature activation-4.79e+00

Pos logit contributions
 debates+3.020
 amounts+2.800
 adoption+2.797
birth+2.748
rons+2.738
Neg logit contributions
 holiest-5.845
saf-5.386
cific-5.297
Trivia-5.236
INGTON-5.065
Token D
Token ID360
Feature activation-1.95e+00

Pos logit contributions
 debates+2.409
 adoption+2.309
 amounts+2.244
birth+2.223
rons+2.222
Neg logit contributions
 holiest-4.516
saf-4.198
cific-4.145
Trivia-4.079
INGTON-3.959
Token-
Token ID12
Feature activation-2.63e+00

Pos logit contributions
 debates+1.221
 adoption+1.180
birth+1.178
Pg+1.164
rons+1.150
Neg logit contributions
 holiest-1.607
saf-1.443
cific-1.428
Trivia-1.405
 Advantage-1.391
TokenCalifornia
Token ID25284
Feature activation-3.16e+00

Pos logit contributions
 debates+1.443
birth+1.430
Pg+1.412
 adoption+1.385
rons+1.370
Neg logit contributions
 holiest-2.342
cific-2.124
saf-2.123
 Advantage-2.052
Trivia-2.045
Token crisis
Token ID4902
Feature activation-3.34e+00

Pos logit contributions
 debates+1.941
 adoption+1.798
 amounts+1.724
 clam+1.684
birth+1.675
Neg logit contributions
 holiest-3.222
saf-2.995
cific-2.994
Trivia-2.993
 Advantage-2.873
Token of
Token ID286
Feature activation+1.79e+00

Pos logit contributions
 debates+1.936
 adoption+1.814
 viewing+1.758
 amounts+1.757
birth+1.755
Neg logit contributions
 holiest-2.954
saf-2.713
Trivia-2.679
cific-2.666
 Advantage-2.621
Token capitalism
Token ID12129
Feature activation+6.39e-01

Pos logit contributions
 holiest+1.587
saf+1.453
cific+1.433
Trivia+1.430
 Advantage+1.393
Neg logit contributions
 debates-1.030
 adoption-0.994
birth-0.974
Pg-0.959
 amounts-0.956
Token,
Token ID11
Feature activation-3.63e+00

Pos logit contributions
 holiest+0.547
saf+0.500
cific+0.493
Trivia+0.488
 Advantage+0.480
Neg logit contributions
 debates-0.383
 adoption-0.370
birth-0.366
Pg-0.360
 amounts-0.359
Token with
Token ID351
Feature activation+9.86e-01

Pos logit contributions
 debates+2.116
 adoption+2.015
 viewing+1.941
 amounts+1.931
birth+1.931
Neg logit contributions
 holiest-3.209
saf-2.944
Trivia-2.907
cific-2.875
INGTON-2.823
Token mass
Token ID2347
Feature activation-1.56e+01

Pos logit contributions
 holiest+0.895
saf+0.823
cific+0.812
Trivia+0.807
 Advantage+0.791
Neg logit contributions
 debates-0.540
 adoption-0.521
birth-0.509
Pg-0.505
 amounts-0.502
Token unemployment
Token ID10681
Feature activation-1.94e+00

Pos logit contributions
 adoption+8.592
 debates+8.527
 amounts+8.082
 clam+7.600
 viewing+7.559
Neg logit contributions
 holiest-13.087
cific-11.745
Trivia-11.670
saf-11.545
cture-11.005
Token at
Token ID379
Feature activation-2.62e+00

Pos logit contributions
 debates+1.076
 adoption+1.017
 amounts+1.011
birth+0.994
 viewing+0.990
Neg logit contributions
 holiest-1.750
saf-1.621
cific-1.615
Trivia-1.579
 Advantage-1.560
Token home
Token ID1363
Feature activation-1.47e+00

Pos logit contributions
 debates+1.500
 adoption+1.457
 amounts+1.436
birth+1.422
 viewing+1.368
Neg logit contributions
 holiest-2.278
cific-2.117
saf-2.113
Trivia-2.090
INGTON-2.071
Token and
Token ID290
Feature activation-2.35e+00

Pos logit contributions
 debates+0.811
 adoption+0.776
birth+0.766
 amounts+0.765
Pg+0.758
Neg logit contributions
 holiest-1.325
saf-1.227
cific-1.221
Trivia-1.196
 Advantage-1.180
Token the
Token ID262
Feature activation-2.31e+00

Pos logit contributions
 debates+1.315
 adoption+1.269
 amounts+1.214
birth+1.211
Pg+1.196
Neg logit contributions
 holiest-2.130
saf-1.976
cific-1.924
Trivia-1.924
INGTON-1.875
TokenCar
Token ID9914
Feature activation-1.46e-01

Pos logit contributions
 holiest+6.094
saf+5.525
Trivia+5.510
cific+5.345
 Advantage+5.290
Neg logit contributions
 debates-6.171
 adoption-5.907
rons-5.811
 amounts-5.805
birth-5.791
Tokenlo
Token ID5439
Feature activation+4.28e+00

Pos logit contributions
 debates+0.089
 adoption+0.087
birth+0.086
rons+0.085
croft+0.084
Neg logit contributions
 holiest-0.122
saf-0.111
cific-0.110
Trivia-0.109
 Advantage-0.107
Token Alleg
Token ID26326
Feature activation-8.01e+00

Pos logit contributions
 holiest+2.780
saf+2.457
cific+2.408
Trivia+2.378
 Advantage+2.348
Neg logit contributions
 debates-3.388
 adoption-3.314
birth-3.305
Pg-3.285
rons-3.254
Tokenri
Token ID380
Feature activation-6.04e-01

Pos logit contributions
rons+2.560
 debates+2.274
croft+2.184
 adoption+2.143
birth+2.103
Neg logit contributions
 holiest-9.090
cific-8.475
Trivia-8.311
INGTON-8.288
 Advantage-8.249
Token)
Token ID8
Feature activation+9.22e-02

Pos logit contributions
 debates+0.382
 adoption+0.371
birth+0.369
Pg+0.363
 amounts+0.363
Neg logit contributions
 holiest-0.490
saf-0.443
cific-0.441
Trivia-0.431
INGTON-0.422
Token Michael
Token ID3899
Feature activation-1.54e+01

Pos logit contributions
 holiest+0.076
saf+0.070
cific+0.069
Trivia+0.067
 Advantage+0.066
Neg logit contributions
 debates-0.057
 adoption-0.056
birth-0.055
Pg-0.054
 amounts-0.054
Token Flynn
Token ID14654
Feature activation-3.13e+00

Pos logit contributions
 debates+7.136
 Weiner+6.871
 Bradley+6.718
 Flynn+6.712
birth+6.621
Neg logit contributions
 holiest-13.384
saf-13.086
cific-12.972
Trivia-11.802
INGTON-11.794
Token The
Token ID383
Feature activation+1.61e+00

Pos logit contributions
 debates+1.847
 adoption+1.792
birth+1.731
 amounts+1.726
rons+1.710
Neg logit contributions
 holiest-2.665
cific-2.459
saf-2.436
Trivia-2.376
 Advantage-2.305
Token 57
Token ID7632
Feature activation-9.09e-01

Pos logit contributions
 holiest+1.399
saf+1.276
cific+1.257
Trivia+1.245
 Advantage+1.234
Neg logit contributions
 debates-0.925
 adoption-0.897
birth-0.895
Pg-0.886
rons-0.876
Token-
Token ID12
Feature activation-6.99e-01

Pos logit contributions
 debates+0.598
 adoption+0.582
birth+0.580
Pg+0.574
rons+0.570
Neg logit contributions
 holiest-0.714
saf-0.645
cific-0.636
Trivia-0.628
 Advantage-0.621
Tokenyear
Token ID1941
Feature activation-6.47e+00

Pos logit contributions
 debates+0.397
 adoption+0.385
birth+0.385
Pg+0.380
rons+0.376
Neg logit contributions
 holiest-0.612
saf-0.557
cific-0.550
Trivia-0.545
 Advantage-0.540
Token years
Token ID812
Feature activation+2.55e+00

Pos logit contributions
 holiest+5.106
saf+4.645
cific+4.608
Trivia+4.562
 Advantage+4.533
Neg logit contributions
 debates-2.579
birth-2.568
Pg-2.543
 adoption-2.524
rons-2.496
Token ago
Token ID2084
Feature activation+2.36e+00

Pos logit contributions
 holiest+2.048
saf+1.856
cific+1.825
Trivia+1.803
 Advantage+1.785
Neg logit contributions
 debates-1.647
 adoption-1.597
birth-1.591
Pg-1.576
rons-1.562
Token Rolling
Token ID21567
Feature activation-1.72e+00

Pos logit contributions
 holiest+2.071
saf+1.896
cific+1.867
Trivia+1.849
 Advantage+1.835
Neg logit contributions
 debates-1.313
 adoption-1.280
birth-1.280
Pg-1.270
rons-1.260
Token Stone
Token ID8026
Feature activation+1.11e+00

Pos logit contributions
 debates+0.839
 adoption+0.802
Pg+0.798
birth+0.797
 amounts+0.785
Neg logit contributions
 holiest-1.668
saf-1.536
cific-1.525
Trivia-1.470
 Advantage-1.446
Token reporter
Token ID9095
Feature activation+1.07e-01

Pos logit contributions
 holiest+0.950
saf+0.861
cific+0.857
Trivia+0.840
 Advantage+0.834
Neg logit contributions
 debates-0.664
 adoption-0.640
birth-0.628
Pg-0.625
 amounts-0.619
Token Michael
Token ID3899
Feature activation-1.53e+01

Pos logit contributions
 holiest+0.095
saf+0.087
cific+0.086
Trivia+0.085
INGTON+0.083
Neg logit contributions
 debates-0.060
 adoption-0.058
birth-0.058
 amounts-0.056
Pg-0.056
Token Hastings
Token ID38330
Feature activation-1.08e+00

Pos logit contributions
 Weiner+7.253
 Kimmel+6.937
 Bradley+6.899
 Berk+6.659
birth+6.449
Neg logit contributions
 holiest-13.483
cific-13.208
saf-13.145
Trivia-12.300
INGTON-12.117
Token writing
Token ID3597
Feature activation+4.80e+00

Pos logit contributions
 debates+0.642
 adoption+0.608
birth+0.603
 amounts+0.596
 clam+0.594
Neg logit contributions
 holiest-0.942
cific-0.856
saf-0.847
 Advantage-0.830
Trivia-0.827
Token in
Token ID287
Feature activation-1.08e+00

Pos logit contributions
 holiest+4.245
saf+3.878
cific+3.833
Trivia+3.783
 Advantage+3.773
Neg logit contributions
 debates-2.633
 adoption-2.557
birth-2.555
Pg-2.545
rons-2.504
Token America
Token ID2253
Feature activation+1.76e+00

Pos logit contributions
 debates+0.615
 adoption+0.592
birth+0.585
 amounts+0.574
Pg+0.572
Neg logit contributions
 holiest-0.949
saf-0.868
Trivia-0.852
cific-0.852
INGTON-0.826
Token
Token ID447
Feature activation+2.24e+00

Pos logit contributions
 holiest+1.480
saf+1.343
cific+1.326
Trivia+1.306
 Advantage+1.286
Neg logit contributions
 debates-1.081
 adoption-1.042
birth-1.036
Pg-1.021
rons-1.019
Token July
Token ID2901
Feature activation+3.40e+00

Pos logit contributions
 holiest+2.310
saf+2.101
cific+2.069
Trivia+2.048
 Advantage+2.028
Neg logit contributions
 debates-1.663
 adoption-1.616
birth-1.610
Pg-1.595
rons-1.579
Token.
Token ID13
Feature activation-1.95e+00

Pos logit contributions
 holiest+2.868
saf+2.610
cific+2.577
Trivia+2.548
 Advantage+2.523
Neg logit contributions
 debates-2.045
 adoption-1.982
birth-1.973
Pg-1.951
rons-1.934
Token
Token ID198
Feature activation-6.06e-01

Pos logit contributions
 debates+1.149
birth+1.118
Pg+1.097
 adoption+1.092
rons+1.079
Neg logit contributions
 holiest-1.670
cific-1.505
saf-1.501
Trivia-1.476
INGTON-1.438
Token
Token ID198
Feature activation-2.42e+00

Pos logit contributions
 debates+0.365
birth+0.357
 adoption+0.354
Pg+0.353
rons+0.346
Neg logit contributions
 holiest-0.513
saf-0.461
cific-0.457
Trivia-0.450
 Advantage-0.446
TokenAdvertisement
Token ID4723
Feature activation-1.28e+00

Pos logit contributions
Pg+1.449
birth+1.447
 debates+1.406
 adoption+1.358
rons+1.356
Neg logit contributions
 holiest-2.059
cific-1.857
 Advantage-1.834
saf-1.786
INGTON-1.740
Token Continue
Token ID10054
Feature activation-1.53e+01

Pos logit contributions
 debates+0.876
 adoption+0.860
birth+0.855
Pg+0.849
rons+0.834
Neg logit contributions
 holiest-0.971
saf-0.865
cific-0.855
Trivia-0.844
 Advantage-0.825
Token reading
Token ID3555
Feature activation-5.38e+00

Pos logit contributions
 reading+1.838
 viewing+1.290
 adoption+0.586
 debates+0.548
 crying+0.487
Neg logit contributions
 holiest-19.662
saf-19.092
Trivia-19.030
 Advantage-18.785
cific-18.774
Token the
Token ID262
Feature activation-6.81e+00

Pos logit contributions
 debates+2.492
 adoption+2.433
Pg+2.431
birth+2.408
 amounts+2.351
Neg logit contributions
 holiest-5.205
saf-4.763
Trivia-4.705
cific-4.703
INGTON-4.652
Token main
Token ID1388
Feature activation-6.69e+00

Pos logit contributions
 debates+4.248
 adoption+4.189
 bell+4.067
 amounts+4.062
 clam+4.034
Neg logit contributions
 holiest-5.338
saf-4.972
cific-4.933
Trivia-4.854
INGTON-4.840
Token story
Token ID1621
Feature activation-1.04e-01

Pos logit contributions
 debates+3.367
 adoption+3.311
 bell+3.165
 amounts+3.161
 viewing+3.158
Neg logit contributions
 holiest-6.188
cific-5.717
saf-5.716
Trivia-5.593
 Advantage-5.572
Token
Token ID198
Feature activation+4.16e-01

Pos logit contributions
 debates+0.063
 adoption+0.062
birth+0.061
Pg+0.061
rons+0.060
Neg logit contributions
 holiest-0.088
saf-0.079
cific-0.079
Trivia-0.077
 Advantage-0.076
Token for
Token ID329
Feature activation-9.83e-01

Pos logit contributions
 debates+2.543
 adoption+2.402
 amounts+2.379
Pg+2.354
birth+2.345
Neg logit contributions
 holiest-5.520
saf-5.219
cific-5.108
Trivia-5.068
 Advantage-4.991
Token the
Token ID262
Feature activation+1.84e-01

Pos logit contributions
 debates+0.565
 adoption+0.549
birth+0.533
Pg+0.531
 amounts+0.527
Neg logit contributions
 holiest-0.863
saf-0.796
cific-0.784
Trivia-0.775
 Advantage-0.757
Token flight
Token ID5474
Feature activation-1.88e+00

Pos logit contributions
 holiest+0.167
saf+0.155
cific+0.152
Trivia+0.151
 Advantage+0.147
Neg logit contributions
 debates-0.100
 adoption-0.097
birth-0.094
Pg-0.093
 amounts-0.093
Token home
Token ID1363
Feature activation+2.69e-01

Pos logit contributions
 debates+1.031
 adoption+0.995
birth+0.974
Pg+0.969
rons+0.967
Neg logit contributions
 holiest-1.682
saf-1.544
cific-1.533
Trivia-1.510
 Advantage-1.498
Token.
Token ID13
Feature activation-1.62e+00

Pos logit contributions
 holiest+0.246
saf+0.227
cific+0.224
Trivia+0.222
 Advantage+0.219
Neg logit contributions
 debates-0.143
 adoption-0.137
birth-0.136
Pg-0.135
rons-0.134
Token Expect
Token ID23600
Feature activation-1.51e+01

Pos logit contributions
 debates+0.926
Pg+0.893
 adoption+0.892
birth+0.891
rons+0.876
Neg logit contributions
 holiest-1.420
saf-1.289
cific-1.271
Trivia-1.245
 Advantage-1.214
Tokening
Token ID278
Feature activation-4.40e+00

Pos logit contributions
 debates+7.156
rons+6.912
 adoption+6.780
Pg+6.635
 reading+6.567
Neg logit contributions
 holiest-12.694
saf-12.112
cific-11.821
Trivia-11.705
 Advantage-11.293
Token another
Token ID1194
Feature activation+1.95e+00

Pos logit contributions
 debates+2.304
 adoption+2.236
Pg+2.131
birth+2.125
 amounts+2.124
Neg logit contributions
 holiest-4.034
saf-3.772
cific-3.742
Trivia-3.687
 Advantage-3.560
Token tired
Token ID10032
Feature activation-3.90e+00

Pos logit contributions
 holiest+1.736
saf+1.592
cific+1.570
Trivia+1.554
 Advantage+1.535
Neg logit contributions
 debates-1.082
 adoption-1.053
birth-1.042
Pg-1.030
rons-1.018
Token clone
Token ID17271
Feature activation-4.11e+00

Pos logit contributions
 debates+2.200
 adoption+2.138
birth+2.084
Pg+2.072
 clam+2.058
Neg logit contributions
 holiest-3.429
saf-3.197
cific-3.139
Trivia-3.075
 Advantage-3.003
Token of
Token ID286
Feature activation-1.17e+00

Pos logit contributions
 debates+2.155
 adoption+2.101
birth+2.059
Pg+2.043
 clam+2.021
Neg logit contributions
 holiest-3.751
saf-3.517
cific-3.423
Trivia-3.372
 Advantage-3.313
Token
Token ID198
Feature activation-2.49e-01

Pos logit contributions
 debates+0.587
 adoption+0.568
birth+0.565
Pg+0.559
 amounts+0.552
Neg logit contributions
 holiest-0.819
saf-0.742
cific-0.731
Trivia-0.722
 Advantage-0.705
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
 debates+0.152
birth+0.148
 adoption+0.148
Pg+0.147
rons+0.144
Neg logit contributions
 holiest-0.208
saf-0.188
cific-0.186
Trivia-0.183
 Advantage-0.182
TokenF
Token ID37
Feature activation+6.69e+00

Pos logit contributions
 debates+0.753
birth+0.750
Pg+0.748
 adoption+0.735
tumblr+0.716
Neg logit contributions
 holiest-0.991
cific-0.882
saf-0.874
 Advantage-0.862
Trivia-0.835
Tokeninance
Token ID14149
Feature activation+3.81e+00

Pos logit contributions
 holiest+5.125
saf+4.603
cific+4.544
Trivia+4.507
INGTON+4.421
Neg logit contributions
 debates-4.350
birth-4.277
Pg-4.251
 adoption-4.244
 amounts-4.138
Token Minister
Token ID4139
Feature activation-3.26e+00

Pos logit contributions
 holiest+2.790
saf+2.502
cific+2.448
Trivia+2.429
 Advantage+2.416
Neg logit contributions
 debates-2.668
birth-2.617
 adoption-2.613
Pg-2.597
rons-2.571
Token Michael
Token ID3899
Feature activation-1.50e+01

Pos logit contributions
 debates+1.816
 amounts+1.738
birth+1.704
 adoption+1.696
 viewing+1.657
Neg logit contributions
 holiest-2.928
saf-2.664
cific-2.658
INGTON-2.593
Trivia-2.591
Token Noon
Token ID41035
Feature activation-7.95e+00

Pos logit contributions
 debates+5.362
 Lauder+5.073
 Bradley+5.023
 Fallon+4.982
 Weiner+4.847
Neg logit contributions
 holiest-14.921
saf-14.205
INGTON-13.646
cific-13.530
Trivia-13.168
Tokenan
Token ID272
Feature activation-2.52e+00

Pos logit contributions
 debates+4.460
 adoption+4.354
 clam+4.114
birth+4.105
rons+4.075
Neg logit contributions
 holiest-7.139
cific-6.436
saf-6.395
Trivia-6.151
 Advantage-5.989
Token said
Token ID531
Feature activation+2.17e+00

Pos logit contributions
 debates+1.470
 adoption+1.391
birth+1.381
 amounts+1.379
rons+1.353
Neg logit contributions
 holiest-2.196
saf-1.986
cific-1.978
Trivia-1.940
 Advantage-1.938
Token on
Token ID319
Feature activation-4.71e+00

Pos logit contributions
 holiest+1.898
saf+1.734
cific+1.710
Trivia+1.693
 Advantage+1.676
Neg logit contributions
 debates-1.238
 adoption-1.200
birth-1.191
Pg-1.177
rons-1.168
Token Wednesday
Token ID3583
Feature activation+1.30e+01

Pos logit contributions
 debates+2.641
 adoption+2.550
birth+2.500
 amounts+2.449
 viewing+2.447
Neg logit contributions
 holiest-4.109
saf-3.771
cific-3.768
Trivia-3.749
 Advantage-3.637
Token the
Token ID262
Feature activation-7.48e-01

Pos logit contributions
 holiest+1.559
saf+1.412
cific+1.392
Trivia+1.378
 Advantage+1.362
Neg logit contributions
 debates-1.239
 adoption-1.206
birth-1.198
Pg-1.187
rons-1.175
Token induction
Token ID28471
Feature activation-5.52e+00

Pos logit contributions
 debates+0.441
 adoption+0.432
birth+0.418
Pg+0.414
 amounts+0.412
Neg logit contributions
 holiest-0.636
saf-0.590
cific-0.585
Trivia-0.581
 Advantage-0.568
Token of
Token ID286
Feature activation-4.37e-01

Pos logit contributions
 debates+2.796
 adoption+2.577
 viewing+2.495
 amounts+2.458
 cort+2.438
Neg logit contributions
 holiest-5.217
saf-4.885
cific-4.846
Trivia-4.763
 Advantage-4.727
Token President
Token ID1992
Feature activation-5.26e+00

Pos logit contributions
 debates+0.260
 adoption+0.254
birth+0.248
Pg+0.246
 amounts+0.244
Neg logit contributions
 holiest-0.372
saf-0.341
cific-0.338
Trivia-0.334
 Advantage-0.329
Token William
Token ID3977
Feature activation-3.70e+00

Pos logit contributions
 debates+2.482
 adoption+2.346
birth+2.309
Pg+2.279
 Lauder+2.263
Neg logit contributions
 holiest-5.107
saf-4.690
Trivia-4.655
cific-4.640
INGTON-4.584
Token V
Token ID569
Feature activation-1.49e+01

Pos logit contributions
 debates+1.831
birth+1.771
 Lauder+1.766
 adoption+1.760
rons+1.703
Neg logit contributions
 holiest-3.540
saf-3.244
cific-3.151
Trivia-3.148
INGTON-3.079
Token.
Token ID13
Feature activation-1.24e+01

Pos logit contributions
 debates+8.860
rons+8.846
 adoption+8.557
Pg+8.212
 Lauder+8.144
Neg logit contributions
 holiest-10.941
saf-10.187
cific-10.016
Trivia-9.673
 Advantage-9.555
TokenS
Token ID50
Feature activation-8.00e-01

Pos logit contributions
 Lauder+5.418
 Weiner+5.384
 debates+5.375
birth+5.270
 Bradley+5.243
Neg logit contributions
 holiest-11.865
saf-11.082
Trivia-10.639
cific-10.618
onyms-10.524
Token.
Token ID13
Feature activation-8.08e+00

Pos logit contributions
 debates+0.507
 adoption+0.493
birth+0.492
Pg+0.485
rons+0.482
Neg logit contributions
 holiest-0.648
saf-0.588
cific-0.577
Trivia-0.574
 Advantage-0.566
Token Tub
Token ID42850
Feature activation-4.44e+00

Pos logit contributions
 debates+3.779
 Lauder+3.634
 adoption+3.604
birth+3.553
Pg+3.478
Neg logit contributions
 holiest-7.772
saf-7.305
cific-7.028
Trivia-6.972
INGTON-6.967
Tokenman
Token ID805
Feature activation-5.21e+00

Pos logit contributions
 debates+2.562
birth+2.547
 adoption+2.468
rons+2.468
croft+2.462
Neg logit contributions
 holiest-3.840
saf-3.438
cific-3.386
Trivia-3.343
 Advantage-3.325
Token to
Token ID284
Feature activation-2.96e+00

Pos logit contributions
 holiest+0.276
saf+0.254
cific+0.250
Trivia+0.247
 Advantage+0.244
Neg logit contributions
 debates-0.175
 adoption-0.169
birth-0.167
Pg-0.164
 amounts-0.164
Token NBC
Token ID9716
Feature activation-6.35e+00

Pos logit contributions
 debates+1.572
 adoption+1.499
rons+1.453
birth+1.452
 viewing+1.447
Neg logit contributions
 holiest-2.704
saf-2.494
Trivia-2.465
cific-2.450
INGTON-2.372
Token
Token ID447
Feature activation+1.75e+00

Pos logit contributions
 debates+3.311
 adoption+3.094
 viewing+3.024
 amounts+3.021
birth+2.969
Neg logit contributions
 holiest-5.803
saf-5.346
cific-5.286
Trivia-5.114
 Advantage-4.961
Token
Token ID247
Feature activation+2.08e-01

Pos logit contributions
 holiest+1.539
saf+1.407
cific+1.387
Trivia+1.373
 Advantage+1.360
Neg logit contributions
 debates-0.984
 adoption-0.953
birth-0.949
Pg-0.939
rons-0.928
Tokens
Token ID82
Feature activation-3.78e-01

Pos logit contributions
 holiest+0.176
saf+0.159
cific+0.157
Trivia+0.156
 Advantage+0.154
Neg logit contributions
 debates-0.125
birth-0.121
 adoption-0.121
Pg-0.119
rons-0.119
Token Matt
Token ID4705
Feature activation-1.49e+01

Pos logit contributions
 debates+0.216
 adoption+0.208
birth+0.205
Pg+0.202
rons+0.201
Neg logit contributions
 holiest-0.331
saf-0.305
cific-0.302
Trivia-0.298
 Advantage-0.293
Token L
Token ID406
Feature activation-2.01e+00

Pos logit contributions
 Weiner+5.149
 debates+5.021
 Boyle+4.892
 Bradley+4.830
rons+4.643
Neg logit contributions
 holiest-14.556
cific-13.941
saf-13.777
Trivia-13.585
INGTON-13.583
Tokenauer
Token ID16261
Feature activation-3.05e+00

Pos logit contributions
 debates+0.986
birth+0.948
rons+0.936
 adoption+0.933
Pg+0.916
Neg logit contributions
 holiest-1.925
saf-1.797
cific-1.741
Trivia-1.721
 Advantage-1.717
Token that
Token ID326
Feature activation+1.67e+00

Pos logit contributions
 debates+1.711
 adoption+1.616
birth+1.592
 amounts+1.585
 viewing+1.570
Neg logit contributions
 holiest-2.746
saf-2.515
cific-2.443
Trivia-2.421
 Advantage-2.394
Token he
Token ID339
Feature activation+3.20e+00

Pos logit contributions
 holiest+1.486
saf+1.362
cific+1.342
Trivia+1.329
 Advantage+1.314
Neg logit contributions
 debates-0.927
 adoption-0.896
birth-0.888
Pg-0.878
rons-0.869
Token he
Token ID339
Feature activation+2.38e+00

Pos logit contributions
 holiest+2.680
saf+2.437
cific+2.400
Trivia+2.375
 Advantage+2.352
Neg logit contributions
 debates-1.942
 adoption-1.888
birth-1.880
Pg-1.863
rons-1.844
Token.
Token ID13
Feature activation+1.78e+00

Pos logit contributions
 holiest+3.430
saf+3.129
cific+3.078
 Advantage+3.046
Trivia+3.043
Neg logit contributions
 debates-3.151
birth-3.064
Pg-3.054
 adoption-3.050
rons-3.028
Token
Token ID198
Feature activation+2.30e+00

Pos logit contributions
 holiest+1.417
saf+1.285
cific+1.265
Trivia+1.253
 Advantage+1.241
Neg logit contributions
 debates-1.140
 adoption-1.109
birth-1.106
Pg-1.100
rons-1.085
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
 holiest+1.783
saf+1.633
cific+1.594
Trivia+1.588
 Advantage+1.567
Neg logit contributions
 debates-1.513
 adoption-1.471
birth-1.454
rons-1.444
Pg-1.442
TokenWe
Token ID1135
Feature activation-2.85e+00

Pos logit contributions
 debates+0.851
Pg+0.846
birth+0.839
 adoption+0.829
rons+0.821
Neg logit contributions
 holiest-1.088
cific-0.957
saf-0.945
 Advantage-0.943
INGTON-0.910
Token will
Token ID481
Feature activation-8.32e+00

Pos logit contributions
 debates+1.742
rons+1.685
birth+1.677
 adoption+1.662
Pg+1.637
Neg logit contributions
 holiest-2.415
saf-2.149
cific-2.140
Trivia-2.120
 Advantage-2.100
Token continue
Token ID2555
Feature activation-1.49e+01

Pos logit contributions
 debates+4.194
 viewing+3.902
 adoption+3.875
 clam+3.866
rons+3.862
Neg logit contributions
 holiest-7.717
cific-7.103
Trivia-6.916
 Advantage-6.800
saf-6.738
Token to
Token ID284
Feature activation-6.75e+00

Pos logit contributions
 debates+6.014
 viewing+5.777
 reading+5.732
 adoption+5.537
 discussion+5.427
Neg logit contributions
 holiest-14.321
Trivia-13.181
cific-13.170
saf-12.954
 Advantage-12.856
Token keep
Token ID1394
Feature activation-5.56e+00

Pos logit contributions
 debates+3.871
 clam+3.595
 adoption+3.557
 viewing+3.529
 amounts+3.449
Neg logit contributions
 holiest-5.977
cific-5.528
Trivia-5.461
saf-5.330
 Advantage-5.286
Token a
Token ID257
Feature activation-5.38e+00

Pos logit contributions
 debates+2.506
 adoption+2.386
 viewing+2.345
 breastfeeding+2.244
 reading+2.236
Neg logit contributions
 holiest-5.577
cific-5.225
Trivia-5.171
saf-5.158
 Advantage-4.963
Token close
Token ID1969
Feature activation-6.72e+00

Pos logit contributions
 debates+3.049
 viewing+2.958
 adoption+2.929
 reading+2.865
 clam+2.855
Neg logit contributions
 holiest-4.557
saf-4.271
cific-4.263
Trivia-4.201
 Advantage-4.157
Token eye
Token ID4151
Feature activation-3.79e+00

Pos logit contributions
 debates+1.798
 adoption+1.759
 reading+1.733
 viewing+1.732
 clam+1.569
Neg logit contributions
 holiest-7.735
saf-7.394
cific-7.352
INGTON-7.161
Trivia-7.143
Token
Token ID198
Feature activation-8.26e-01

Pos logit contributions
 debates+0.065
 adoption+0.063
birth+0.063
Pg+0.062
rons+0.061
Neg logit contributions
 holiest-0.086
saf-0.078
cific-0.077
Trivia-0.076
 Advantage-0.075
TokenTake
Token ID12322
Feature activation+2.26e+00

Pos logit contributions
 debates+0.553
birth+0.550
Pg+0.544
 adoption+0.539
rons+0.529
Neg logit contributions
 holiest-0.641
cific-0.566
saf-0.562
 Advantage-0.556
INGTON-0.548
Token mankind
Token ID18019
Feature activation-3.43e+00

Pos logit contributions
 holiest+2.023
saf+1.851
cific+1.826
Trivia+1.808
 Advantage+1.792
Neg logit contributions
 debates-1.240
 adoption-1.201
birth-1.195
Pg-1.183
rons-1.170
Token in
Token ID287
Feature activation-3.94e+00

Pos logit contributions
 debates+1.838
 adoption+1.777
birth+1.744
 amounts+1.738
 bathing+1.721
Neg logit contributions
 holiest-3.086
cific-2.872
saf-2.856
Trivia-2.810
INGTON-2.768
Token the
Token ID262
Feature activation-2.58e+00

Pos logit contributions
 debates+2.191
 adoption+2.139
 amounts+2.057
birth+2.040
 bathing+2.031
Neg logit contributions
 holiest-3.446
cific-3.232
saf-3.230
Trivia-3.169
INGTON-3.113
Token mass
Token ID2347
Feature activation-1.48e+01

Pos logit contributions
 debates+1.470
 adoption+1.436
 amounts+1.378
birth+1.375
Pg+1.360
Neg logit contributions
 holiest-2.196
cific-2.080
saf-2.054
Trivia-2.030
INGTON-2.001
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
 adoption+8.051
 debates+7.905
birth+7.760
 amounts+7.743
 clam+7.665
Neg logit contributions
 holiest-11.443
cific-10.651
saf-10.402
Trivia-10.332
 Advantage-10.036
Token
Token ID198
Feature activation+2.17e-01

Pos logit contributions
 debates+0.623
 adoption+0.611
birth+0.597
Pg+0.590
 amounts+0.585
Neg logit contributions
 holiest-0.934
saf-0.864
cific-0.856
Trivia-0.847
 Advantage-0.829
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 holiest+0.179
saf+0.161
cific+0.159
Trivia+0.157
 Advantage+0.156
Neg logit contributions
 debates-0.135
 adoption-0.131
birth-0.131
Pg-0.130
rons-0.128
Tokenand
Token ID392
Feature activation-2.48e+00

Pos logit contributions
birth+0.732
 debates+0.730
Pg+0.721
 adoption+0.719
rons+0.708
Neg logit contributions
 holiest-0.715
cific-0.629
saf-0.620
 Advantage-0.614
Trivia-0.607
Token for
Token ID329
Feature activation-1.30e+00

Pos logit contributions
 debates+1.418
 adoption+1.377
birth+1.344
 amounts+1.328
rons+1.324
Neg logit contributions
 holiest-2.148
saf-1.987
cific-1.981
Trivia-1.961
INGTON-1.916
TokenIf
Token ID1532
Feature activation-2.36e+00

Pos logit contributions
 holiest+0.437
cific+0.381
saf+0.379
 Advantage+0.373
INGTON+0.362
Neg logit contributions
birth-0.358
Pg-0.357
 debates-0.357
 adoption-0.350
tumblr-0.345
Token Dallas
Token ID8533
Feature activation+7.01e+00

Pos logit contributions
 debates+1.299
 adoption+1.250
 amounts+1.227
birth+1.209
 viewing+1.206
Neg logit contributions
 holiest-2.138
saf-1.959
cific-1.934
Trivia-1.907
INGTON-1.850
Token ren
Token ID8851
Feature activation+8.79e+00

Pos logit contributions
 holiest+5.748
saf+5.189
Trivia+5.137
cific+5.129
 Advantage+5.122
Neg logit contributions
 debates-4.100
birth-4.085
Pg-4.031
 adoption-4.011
rons-3.983
Tokenounces
Token ID45982
Feature activation+1.39e+00

Pos logit contributions
 holiest+5.919
cific+5.455
saf+5.429
Trivia+5.342
 Advantage+5.152
Neg logit contributions
 adoption-6.224
 debates-6.107
birth-6.082
 breastfeeding-6.010
Pg-5.996
Token Charlie
Token ID11526
Feature activation-9.06e+00

Pos logit contributions
 holiest+1.221
saf+1.119
cific+1.106
Trivia+1.093
 Advantage+1.073
Neg logit contributions
 debates-0.795
 adoption-0.771
birth-0.759
 amounts-0.751
Pg-0.749
Token V
Token ID569
Feature activation-1.48e+01

Pos logit contributions
Pg+6.788
 adoption+6.787
 debates+6.717
 amounts+6.617
 breastfeeding+6.519
Neg logit contributions
 holiest-6.037
saf-5.193
cific-5.125
INGTON-5.011
Trivia-4.932
Token,
Token ID11
Feature activation-2.33e+00

Pos logit contributions
rons+8.618
 debates+8.468
ogue+8.261
Pg+8.064
 Weiner+7.989
Neg logit contributions
 holiest-10.941
 Advantage-10.122
saf-10.061
cific-9.630
alties-9.383
Token Greg
Token ID8547
Feature activation-5.50e+00

Pos logit contributions
 debates+1.277
 adoption+1.242
 amounts+1.225
birth+1.196
 viewing+1.187
Neg logit contributions
 holiest-2.110
saf-1.936
cific-1.891
Trivia-1.884
 Advantage-1.826
Token Smith
Token ID4176
Feature activation-3.44e+00

Pos logit contributions
 debates+2.272
 adoption+2.138
rons+2.099
 amounts+2.084
Pg+2.084
Neg logit contributions
 holiest-5.655
saf-5.310
cific-5.215
Trivia-5.072
INGTON-5.033
Token,
Token ID11
Feature activation-2.09e+00

Pos logit contributions
 debates+1.788
 amounts+1.713
 adoption+1.705
Pg+1.685
birth+1.684
Neg logit contributions
 holiest-3.206
saf-2.924
cific-2.888
Trivia-2.832
 Advantage-2.814
Token Richard
Token ID6219
Feature activation-5.68e+00

Pos logit contributions
 debates+1.197
 adoption+1.171
 amounts+1.139
birth+1.128
Pg+1.125
Neg logit contributions
 holiest-1.815
saf-1.663
cific-1.637
Trivia-1.613
INGTON-1.583
Token topical
Token ID39867
Feature activation+2.34e-01

Pos logit contributions
 debates+0.105
 adoption+0.102
birth+0.101
Pg+0.100
 amounts+0.099
Neg logit contributions
 holiest-0.170
saf-0.158
cific-0.156
Trivia-0.153
 Advantage-0.152
Token,
Token ID11
Feature activation+5.03e-01

Pos logit contributions
 holiest+0.211
saf+0.194
cific+0.191
Trivia+0.189
 Advantage+0.187
Neg logit contributions
 debates-0.129
 adoption-0.123
birth-0.121
Pg-0.120
 amounts-0.120
Token Trey
Token ID36085
Feature activation-2.83e+00

Pos logit contributions
 holiest+0.440
saf+0.401
cific+0.398
Trivia+0.393
 Advantage+0.388
Neg logit contributions
 debates-0.288
 adoption-0.279
birth-0.276
Pg-0.272
rons-0.270
Token Parker
Token ID13612
Feature activation-1.02e+00

Pos logit contributions
 debates+1.429
 adoption+1.312
Pg+1.295
rons+1.280
 viewing+1.278
Neg logit contributions
 holiest-2.722
saf-2.509
cific-2.491
Trivia-2.427
INGTON-2.420
Token and
Token ID290
Feature activation-9.57e-01

Pos logit contributions
 debates+0.581
 adoption+0.553
birth+0.546
 amounts+0.541
Pg+0.536
Neg logit contributions
 holiest-0.899
cific-0.822
saf-0.821
 Advantage-0.795
Trivia-0.792
Token Matt
Token ID4705
Feature activation-1.48e+01

Pos logit contributions
 debates+0.538
 adoption+0.528
birth+0.510
 amounts+0.506
rons+0.504
Neg logit contributions
 holiest-0.846
saf-0.774
cific-0.770
Trivia-0.755
 Advantage-0.743
Token Stone
Token ID8026
Feature activation-5.39e+00

Pos logit contributions
 Weiner+5.174
 debates+5.015
 adoption+4.796
 Bradley+4.694
 viewing+4.557
Neg logit contributions
 holiest-14.643
cific-14.506
saf-14.091
Trivia-13.707
abouts-13.430
Token's
Token ID338
Feature activation+2.48e+00

Pos logit contributions
 debates+2.837
birth+2.693
 adoption+2.653
rons+2.609
 amounts+2.594
Neg logit contributions
 holiest-4.968
cific-4.508
saf-4.479
Trivia-4.393
 Advantage-4.342
Token news
Token ID1705
Feature activation-4.96e+00

Pos logit contributions
 holiest+2.174
saf+1.985
cific+1.957
Trivia+1.937
 Advantage+1.920
Neg logit contributions
 debates-1.409
 adoption-1.365
birth-1.361
Pg-1.347
rons-1.333
Tokeny
Token ID88
Feature activation+2.18e+00

Pos logit contributions
 debates+2.727
 adoption+2.645
birth+2.632
 viewing+2.612
 amounts+2.585
Neg logit contributions
 holiest-4.352
cific-4.022
saf-3.900
Trivia-3.865
 Advantage-3.860
Token cartoon
Token ID16251
Feature activation-4.13e+00

Pos logit contributions
 holiest+1.980
saf+1.815
cific+1.790
Trivia+1.773
 Advantage+1.758
Neg logit contributions
 debates-1.168
 adoption-1.130
birth-1.126
Pg-1.115
rons-1.102
TokenSanders
Token ID26747
Feature activation-3.68e+00

Pos logit contributions
 debates+1.486
Pg+1.446
birth+1.443
 adoption+1.424
 amounts+1.385
Neg logit contributions
 holiest-2.311
cific-2.089
saf-2.074
 Advantage-2.026
INGTON-1.996
Token:
Token ID25
Feature activation-4.83e+00

Pos logit contributions
 debates+2.233
 adoption+2.150
birth+2.108
 amounts+2.104
Pg+2.103
Neg logit contributions
 holiest-3.155
saf-2.866
cific-2.852
Trivia-2.758
 Advantage-2.728
Token '
Token ID705
Feature activation-5.55e+00

Pos logit contributions
 debates+2.749
 adoption+2.679
birth+2.602
 amounts+2.569
rons+2.556
Neg logit contributions
 holiest-4.294
cific-3.987
saf-3.918
Trivia-3.898
INGTON-3.688
TokenI
Token ID40
Feature activation-2.68e+00

Pos logit contributions
birth+3.072
 debates+3.005
 adoption+2.976
rons+2.897
Pg+2.857
Neg logit contributions
 holiest-4.960
cific-4.531
saf-4.422
INGTON-4.308
 Advantage-4.289
Token fully
Token ID3938
Feature activation-1.19e+01

Pos logit contributions
 debates+1.460
 adoption+1.412
birth+1.403
Pg+1.382
rons+1.377
Neg logit contributions
 holiest-2.416
saf-2.214
cific-2.186
Trivia-2.161
 Advantage-2.141
Token expect
Token ID1607
Feature activation-1.48e+01

Pos logit contributions
 debates+5.275
 adoption+5.172
birth+5.130
rons+5.096
croft+4.945
Neg logit contributions
 holiest-11.117
cific-10.889
 Advantage-10.458
saf-10.432
INGTON-10.416
Token'
Token ID6
Feature activation-8.81e+00

Pos logit contributions
 debates+8.264
 amounts+7.773
 Weiner+7.556
croft+7.387
 adoption+7.291
Neg logit contributions
 holiest-12.607
saf-12.173
Trivia-11.859
cific-11.535
INGTON-11.489
Token fair
Token ID3148
Feature activation-8.57e+00

Pos logit contributions
 debates+4.222
 adoption+4.167
 amounts+4.095
birth+4.028
 viewing+3.928
Neg logit contributions
 holiest-8.423
saf-8.033
cific-7.644
Trivia-7.636
 Advantage-7.418
Token treatment
Token ID3513
Feature activation-5.81e+00

Pos logit contributions
 debates+5.080
 adoption+4.707
 amounts+4.663
 viewing+4.472
 breastfeeding+4.433
Neg logit contributions
 holiest-7.664
cific-7.055
saf-6.935
Trivia-6.842
 Advantage-6.579
Token by
Token ID416
Feature activation-4.94e+00

Pos logit contributions
 debates+3.200
 adoption+3.034
 amounts+2.999
rons+2.920
 viewing+2.894
Neg logit contributions
 holiest-5.184
saf-4.856
cific-4.782
Trivia-4.699
INGTON-4.554
Token DNC
Token ID17824
Feature activation-6.57e+00

Pos logit contributions
 debates+2.690
 adoption+2.595
birth+2.579
Pg+2.546
rons+2.527
Neg logit contributions
 holiest-4.440
saf-4.067
cific-4.019
Trivia-3.980
 Advantage-3.937
Token finance
Token ID9604
Feature activation+4.11e+00

Pos logit contributions
 debates+4.659
 adoption+4.587
 amounts+4.343
 viewing+4.260
 clam+4.182
Neg logit contributions
 holiest-5.764
cific-5.338
saf-5.291
Trivia-5.233
INGTON-5.162
Token and
Token ID290
Feature activation-6.64e-02

Pos logit contributions
 holiest+3.401
saf+3.077
cific+3.017
 Advantage+2.988
Trivia+2.983
Neg logit contributions
 debates-2.434
birth-2.410
Pg-2.397
 adoption-2.372
rons-2.351
Token ro
Token ID686
Feature activation+1.35e+00

Pos logit contributions
 debates+0.038
 adoption+0.037
birth+0.036
 amounts+0.035
Pg+0.035
Neg logit contributions
 holiest-0.059
saf-0.054
cific-0.053
Trivia-0.053
 Advantage-0.052
Tokeniled
Token ID3902
Feature activation-2.41e+00

Pos logit contributions
 holiest+1.071
saf+0.947
Trivia+0.940
cific+0.939
 Advantage+0.924
Neg logit contributions
 debates-0.890
birth-0.873
Pg-0.863
 adoption-0.861
rons-0.858
Token by
Token ID416
Feature activation-1.96e-01

Pos logit contributions
 debates+1.436
 adoption+1.354
 amounts+1.301
Pg+1.293
rons+1.293
Neg logit contributions
 holiest-2.084
saf-1.949
cific-1.910
Trivia-1.895
 Advantage-1.869
Token mass
Token ID2347
Feature activation-1.47e+01

Pos logit contributions
 debates+0.113
 adoption+0.109
birth+0.105
 amounts+0.105
Pg+0.103
Neg logit contributions
 holiest-0.172
saf-0.159
cific-0.156
Trivia-0.155
 Advantage-0.153
Token street
Token ID4675
Feature activation-3.20e+00

Pos logit contributions
 adoption+7.958
 debates+7.950
 amounts+7.662
 clam+7.197
 viewing+6.981
Neg logit contributions
 holiest-12.327
cific-11.450
saf-11.307
Trivia-11.163
 Advantage-10.972
Token protests
Token ID8536
Feature activation-7.64e+00

Pos logit contributions
 debates+1.183
 adoption+1.091
 amounts+1.032
birth+1.030
Pg+1.024
Neg logit contributions
 holiest-3.512
cific-3.249
saf-3.247
Trivia-3.206
 Advantage-3.192
Token.
Token ID13
Feature activation-3.91e+00

Pos logit contributions
 debates+3.833
 clam+3.649
 amounts+3.599
 adoption+3.598
 viewing+3.547
Neg logit contributions
 holiest-6.913
cific-6.495
saf-6.483
Trivia-6.430
 Advantage-6.365
Token These
Token ID2312
Feature activation-4.03e+00

Pos logit contributions
 debates+2.239
birth+2.167
Pg+2.155
 adoption+2.136
 Lauder+2.107
Neg logit contributions
 holiest-3.417
saf-3.058
cific-3.023
Trivia-2.957
INGTON-2.899
Token were
Token ID547
Feature activation-4.55e+00

Pos logit contributions
 debates+2.360
 adoption+2.212
 amounts+2.165
 clam+2.109
birth+2.099
Neg logit contributions
 holiest-3.536
saf-3.250
cific-3.241
Trivia-3.186
 Advantage-3.161
Token no
Token ID645
Feature activation+3.03e+00

Pos logit contributions
 holiest+0.345
saf+0.315
cific+0.313
Trivia+0.310
 Advantage+0.305
Neg logit contributions
 debates-0.197
 adoption-0.189
birth-0.188
rons-0.186
Pg-0.185
Token one
Token ID530
Feature activation+5.40e+00

Pos logit contributions
 holiest+2.092
saf+1.862
cific+1.829
Trivia+1.805
 Advantage+1.783
Neg logit contributions
 debates-2.279
 adoption-2.226
birth-2.218
Pg-2.201
rons-2.184
Token can
Token ID460
Feature activation+4.33e+00

Pos logit contributions
 holiest+4.352
saf+3.902
cific+3.838
Trivia+3.825
 Advantage+3.806
Neg logit contributions
 debates-3.334
birth-3.304
Pg-3.298
 adoption-3.273
rons-3.225
Token take
Token ID1011
Feature activation+2.78e+00

Pos logit contributions
 holiest+3.520
saf+3.201
cific+3.142
Trivia+3.105
 Advantage+3.083
Neg logit contributions
 debates-2.687
 adoption-2.628
birth-2.627
Pg-2.600
rons-2.564
Token any
Token ID597
Feature activation+6.24e+00

Pos logit contributions
 holiest+2.391
saf+2.174
cific+2.143
Trivia+2.123
 Advantage+2.118
Neg logit contributions
 debates-1.610
birth-1.565
 adoption-1.562
Pg-1.549
rons-1.533
Token risks
Token ID7476
Feature activation+1.00e+01

Pos logit contributions
 holiest+5.040
saf+4.520
 Advantage+4.451
cific+4.436
Trivia+4.380
Neg logit contributions
 debates-3.825
birth-3.804
Pg-3.767
 adoption-3.734
rons-3.724
Token with
Token ID351
Feature activation+3.45e+00

Pos logit contributions
 holiest+8.065
saf+7.317
Trivia+7.101
 Advantage+7.064
cific+7.037
Neg logit contributions
Pg-5.852
birth-5.777
 debates-5.721
tumblr-5.659
 adoption-5.628
Token this
Token ID428
Feature activation-3.91e+00

Pos logit contributions
 holiest+3.094
saf+2.828
cific+2.789
Trivia+2.764
 Advantage+2.745
Neg logit contributions
 debates-1.871
birth-1.812
 adoption-1.811
Pg-1.795
rons-1.773
Token.
Token ID13
Feature activation+2.56e-01

Pos logit contributions
 debates+2.233
 adoption+2.214
 amounts+2.145
 viewing+2.085
 clam+2.049
Neg logit contributions
 holiest-3.337
cific-3.136
saf-3.134
Trivia-3.092
INGTON-3.005
Token Everything
Token ID11391
Feature activation+1.89e+00

Pos logit contributions
 holiest+0.219
saf+0.198
cific+0.195
Trivia+0.191
INGTON+0.187
Neg logit contributions
 debates-0.154
 adoption-0.149
birth-0.148
Pg-0.146
 amounts-0.144
Token must
Token ID1276
Feature activation-9.29e-01

Pos logit contributions
 holiest+1.674
saf+1.534
cific+1.515
Trivia+1.493
 Advantage+1.478
Neg logit contributions
 debates-1.066
 adoption-1.030
birth-1.016
 amounts-1.007
Pg-1.004
Token recession
Token ID16457
Feature activation+4.05e+00

Pos logit contributions
 debates+0.846
 adoption+0.818
 viewing+0.781
 amounts+0.781
Pg+0.775
Neg logit contributions
 holiest-1.354
saf-1.255
cific-1.243
Trivia-1.238
INGTON-1.201
Token.
Token ID13
Feature activation-3.00e+00

Pos logit contributions
 holiest+3.263
saf+2.960
cific+2.906
Trivia+2.869
 Advantage+2.858
Neg logit contributions
 debates-2.548
 adoption-2.485
birth-2.482
Pg-2.459
rons-2.430
Token
Token ID198
Feature activation-1.60e+00

Pos logit contributions
 debates+1.733
birth+1.664
 adoption+1.648
Pg+1.629
rons+1.615
Neg logit contributions
 holiest-2.617
saf-2.369
cific-2.339
Trivia-2.299
 Advantage-2.227
Token
Token ID198
Feature activation-3.97e+00

Pos logit contributions
 debates+0.926
birth+0.913
Pg+0.903
 adoption+0.900
 amounts+0.876
Neg logit contributions
 holiest-1.396
cific-1.249
saf-1.246
Trivia-1.217
 Advantage-1.212
TokenOn
Token ID2202
Feature activation-4.48e+00

Pos logit contributions
Pg+2.426
birth+2.387
 debates+2.305
tumblr+2.270
 adoption+2.241
Neg logit contributions
 holiest-3.352
cific-2.983
 Advantage-2.966
saf-2.881
INGTON-2.757
Token Thursday
Token ID3635
Feature activation+1.31e+01

Pos logit contributions
 debates+2.545
 adoption+2.457
birth+2.409
 viewing+2.367
 amounts+2.353
Neg logit contributions
 holiest-3.882
saf-3.564
cific-3.561
Trivia-3.554
INGTON-3.452
Token,
Token ID11
Feature activation+4.23e+00

Pos logit contributions
 holiest+9.613
saf+8.554
 Advantage+8.467
cific+8.410
INGTON+8.386
Neg logit contributions
Pg-7.658
birth-7.516
tumblr-7.460
 adoption-7.230
anamo-7.214
Token Carney
Token ID40775
Feature activation-7.86e-02

Pos logit contributions
 holiest+3.680
saf+3.349
cific+3.312
Trivia+3.271
 Advantage+3.265
Neg logit contributions
 debates-2.333
Pg-2.295
birth-2.291
 adoption-2.278
rons-2.245
Token said
Token ID531
Feature activation+2.21e+00

Pos logit contributions
 debates+0.046
 adoption+0.044
birth+0.044
 amounts+0.043
rons+0.043
Neg logit contributions
 holiest-0.068
saf-0.062
cific-0.062
Trivia-0.061
 Advantage-0.060
Token the
Token ID262
Feature activation+3.78e-02

Pos logit contributions
 holiest+1.920
saf+1.753
cific+1.728
Trivia+1.711
 Advantage+1.694
Neg logit contributions
 debates-1.274
 adoption-1.234
birth-1.228
Pg-1.214
rons-1.204
Token independent
Token ID4795
Feature activation-3.62e+00

Pos logit contributions
 holiest+0.034
saf+0.031
cific+0.031
Trivia+0.031
 Advantage+0.030
Neg logit contributions
 debates-0.021
 adoption-0.020
birth-0.019
 amounts-0.019
Pg-0.019
Token Trump
Token ID1301
Feature activation-2.01e+00

Pos logit contributions
birth+3.040
Pg+3.002
 Weiner+2.935
 debates+2.926
 Lauder+2.852
Neg logit contributions
 holiest-11.685
cific-10.882
saf-10.866
alties-10.292
 challeng-10.247
Token (@
Token ID4275
Feature activation+1.79e+00

Pos logit contributions
 debates+1.423
 adoption+1.385
birth+1.378
 amounts+1.351
Pg+1.344
Neg logit contributions
 holiest-1.491
saf-1.341
cific-1.324
Trivia-1.285
 Advantage-1.271
TokenrealDonaldTrump
Token ID28024
Feature activation-6.64e-01

Pos logit contributions
 holiest+1.036
saf+0.909
cific+0.884
Trivia+0.875
 Advantage+0.850
Neg logit contributions
 debates-1.542
 adoption-1.506
birth-1.502
Pg-1.491
rons-1.478
Token)
Token ID8
Feature activation+2.98e+00

Pos logit contributions
 debates+0.373
birth+0.363
 adoption+0.362
Pg+0.357
 amounts+0.351
Neg logit contributions
 holiest-0.590
saf-0.533
cific-0.529
Trivia-0.519
 Advantage-0.518
Token June
Token ID2795
Feature activation+7.50e+00

Pos logit contributions
 holiest+2.367
saf+2.142
cific+2.110
Trivia+2.085
 Advantage+2.063
Neg logit contributions
 debates-1.929
 adoption-1.877
birth-1.870
Pg-1.852
rons-1.835
Token 3
Token ID513
Feature activation+1.11e+01

Pos logit contributions
 holiest+4.426
saf+3.944
 Advantage+3.829
Trivia+3.799
cific+3.750
Neg logit contributions
 debates-6.093
Pg-5.954
 adoption-5.933
rons-5.924
birth-5.892
Token,
Token ID11
Feature activation+1.12e+01

Pos logit contributions
 holiest+7.188
saf+6.917
 Advantage+6.738
Trivia+6.721
cific+6.559
Neg logit contributions
 debates-7.585
 stret-7.437
 adoption-7.418
 bathing-7.377
 clam-7.356
Token 2017
Token ID2177
Feature activation+4.49e+00

Pos logit contributions
 holiest+5.162
saf+4.162
 Advantage+4.011
Trivia+3.870
cific+3.818
Neg logit contributions
Pg-10.573
 debates-10.500
rons-10.225
tumblr-10.102
birth-10.078
Token
Token ID198
Feature activation+3.50e+00

Pos logit contributions
 holiest+3.347
saf+3.021
cific+2.944
Trivia+2.943
 Advantage+2.941
Neg logit contributions
 debates-3.033
birth-2.959
Pg-2.957
 adoption-2.956
rons-2.942
Token
Token ID198
Feature activation+1.28e+00

Pos logit contributions
 holiest+2.594
saf+2.392
Trivia+2.329
cific+2.315
 Advantage+2.287
Neg logit contributions
 debates-2.393
 adoption-2.329
rons-2.294
birth-2.285
Pg-2.260
TokenShortly
Token ID30513
Feature activation+6.17e+00

Pos logit contributions
 holiest+1.012
saf+0.905
cific+0.901
 Advantage+0.885
Trivia+0.875
Neg logit contributions
 debates-0.840
birth-0.823
Pg-0.819
 adoption-0.818
rons-0.802
Token three
Token ID1115
Feature activation+4.86e+00

Pos logit contributions
 holiest+3.925
saf+3.524
cific+3.445
Trivia+3.401
 Advantage+3.386
Neg logit contributions
 debates-3.959
birth-3.876
Pg-3.858
 adoption-3.858
rons-3.813
Token games
Token ID1830
Feature activation+4.09e-01

Pos logit contributions
 holiest+3.997
saf+3.624
cific+3.569
Trivia+3.524
 Advantage+3.516
Neg logit contributions
 debates-2.929
birth-2.900
 adoption-2.879
Pg-2.861
rons-2.821
Token with
Token ID351
Feature activation+3.77e+00

Pos logit contributions
 holiest+0.359
saf+0.328
cific+0.324
Trivia+0.320
 Advantage+0.315
Neg logit contributions
 debates-0.234
 adoption-0.227
birth-0.224
Pg-0.222
rons-0.221
Token their
Token ID511
Feature activation+4.42e+00

Pos logit contributions
 holiest+3.131
saf+2.846
cific+2.806
Trivia+2.775
 Advantage+2.743
Neg logit contributions
 debates-2.310
 adoption-2.243
birth-2.229
Pg-2.208
rons-2.189
Token 14
Token ID1478
Feature activation+2.40e+00

Pos logit contributions
 holiest+3.846
saf+3.500
cific+3.443
Trivia+3.404
 Advantage+3.388
Neg logit contributions
 debates-2.522
birth-2.443
 adoption-2.441
Pg-2.427
rons-2.400
Tokenth
Token ID400
Feature activation+1.31e+01

Pos logit contributions
 holiest+1.921
saf+1.739
cific+1.713
Trivia+1.695
 Advantage+1.675
Neg logit contributions
 debates-1.557
 adoption-1.510
birth-1.504
Pg-1.489
rons-1.476
Token defeat
Token ID7433
Feature activation+6.64e+00

Pos logit contributions
 holiest+9.825
 Advantage+8.683
saf+8.607
cific+8.476
INGTON+8.315
Neg logit contributions
 debates-7.954
Pg-7.943
rons-7.817
tumblr-7.686
croft-7.666
Token in
Token ID287
Feature activation+5.57e+00

Pos logit contributions
 holiest+5.422
saf+4.950
cific+4.830
Trivia+4.801
 Advantage+4.774
Neg logit contributions
 debates-3.991
 adoption-3.883
birth-3.871
Pg-3.856
tumblr-3.766
Token 16
Token ID1467
Feature activation+6.31e-01

Pos logit contributions
 holiest+4.105
saf+3.669
cific+3.594
Trivia+3.565
 Advantage+3.555
Neg logit contributions
 debates-3.874
birth-3.792
Pg-3.774
 adoption-3.762
rons-3.720
Token outings
Token ID47280
Feature activation+4.34e+00

Pos logit contributions
 holiest+0.573
saf+0.524
cific+0.519
Trivia+0.514
INGTON+0.505
Neg logit contributions
 debates-0.351
 adoption-0.336
birth-0.330
 amounts-0.324
Pg-0.322
Token.
Token ID13
Feature activation+7.55e-01

Pos logit contributions
 holiest+3.541
saf+3.213
cific+3.161
Trivia+3.132
 Advantage+3.104
Neg logit contributions
 debates-2.706
 adoption-2.633
birth-2.623
Pg-2.603
rons-2.569
Token dispute
Token ID11047
Feature activation+9.26e-02

Pos logit contributions
 debates+1.768
 adoption+1.690
 amounts+1.633
birth+1.560
 viewing+1.556
Neg logit contributions
 holiest-3.776
cific-3.498
saf-3.458
Trivia-3.454
INGTON-3.393
Token in
Token ID287
Feature activation+1.44e+00

Pos logit contributions
 holiest+0.081
saf+0.074
cific+0.073
Trivia+0.073
 Advantage+0.071
Neg logit contributions
 debates-0.054
 adoption-0.052
 amounts-0.051
birth-0.051
rons-0.050
Token its
Token ID663
Feature activation+3.19e+00

Pos logit contributions
 holiest+1.224
saf+1.118
cific+1.099
Trivia+1.094
 Advantage+1.073
Neg logit contributions
 debates-0.874
 adoption-0.845
birth-0.834
 amounts-0.819
Pg-0.815
Token statement
Token ID2643
Feature activation+4.73e-03

Pos logit contributions
 holiest+2.730
saf+2.486
cific+2.449
Trivia+2.424
 Advantage+2.402
Neg logit contributions
 debates-1.872
 adoption-1.815
birth-1.812
Pg-1.796
rons-1.778
Token on
Token ID319
Feature activation+4.37e-01

Pos logit contributions
 holiest+0.004
saf+0.004
cific+0.004
Trivia+0.004
 Advantage+0.004
Neg logit contributions
 debates-0.003
 adoption-0.003
birth-0.002
 amounts-0.002
rons-0.002
Token Monday
Token ID3321
Feature activation+1.24e+01

Pos logit contributions
 holiest+0.368
saf+0.337
cific+0.334
Trivia+0.332
 Advantage+0.325
Neg logit contributions
 debates-0.264
 adoption-0.258
birth-0.254
 amounts-0.247
Pg-0.247
Token,
Token ID11
Feature activation+4.42e+00

Pos logit contributions
 holiest+8.690
saf+7.867
cific+7.595
 Advantage+7.551
Trivia+7.498
Neg logit contributions
Pg-7.999
tumblr-7.872
 debates-7.849
rons-7.838
birth-7.806
Token but
Token ID475
Feature activation+5.45e+00

Pos logit contributions
 holiest+4.323
saf+3.979
cific+3.932
Trivia+3.890
 Advantage+3.865
Neg logit contributions
 debates-2.025
birth-1.946
 adoption-1.944
Pg-1.938
rons-1.909
Token said
Token ID531
Feature activation+4.95e+00

Pos logit contributions
 holiest+4.451
saf+4.036
cific+3.974
Trivia+3.913
 Advantage+3.903
Neg logit contributions
 debates-3.312
Pg-3.270
birth-3.250
 adoption-3.227
rons-3.181
Token it
Token ID340
Feature activation+4.72e+00

Pos logit contributions
 holiest+4.076
saf+3.677
cific+3.626
Trivia+3.579
 Advantage+3.575
Neg logit contributions
 debates-2.978
Pg-2.935
birth-2.922
 adoption-2.899
rons-2.859
Token would
Token ID561
Feature activation-1.85e+00

Pos logit contributions
 holiest+3.836
saf+3.474
cific+3.400
Trivia+3.370
 Advantage+3.353
Neg logit contributions
 debates-2.913
birth-2.863
 adoption-2.853
Pg-2.840
rons-2.798
Token though
Token ID996
Feature activation-3.12e+00

Pos logit contributions
 debates+0.526
 adoption+0.517
birth+0.497
 amounts+0.495
 viewing+0.487
Neg logit contributions
 holiest-0.846
saf-0.781
cific-0.776
Trivia-0.759
 Advantage-0.746
Token I
Token ID314
Feature activation-2.10e+00

Pos logit contributions
 debates+1.696
 adoption+1.677
birth+1.609
 amounts+1.592
 breastfeeding+1.572
Neg logit contributions
 holiest-2.821
saf-2.617
cific-2.586
Trivia-2.553
INGTON-2.469
Token knew
Token ID2993
Feature activation-4.42e+00

Pos logit contributions
 debates+1.251
 adoption+1.198
rons+1.191
birth+1.189
 clam+1.186
Neg logit contributions
 holiest-1.796
cific-1.629
saf-1.627
Trivia-1.599
 Advantage-1.579
Token I
Token ID314
Feature activation+1.63e+00

Pos logit contributions
 debates+2.366
 adoption+2.345
 amounts+2.231
birth+2.213
 breastfeeding+2.172
Neg logit contributions
 holiest-4.001
cific-3.721
saf-3.695
Trivia-3.632
INGTON-3.509
Token wanted
Token ID2227
Feature activation-3.53e+00

Pos logit contributions
 holiest+1.327
saf+1.198
cific+1.195
Trivia+1.176
 Advantage+1.162
Neg logit contributions
 debates-1.031
 adoption-1.002
birth-0.997
rons-0.989
Pg-0.982
Token to
Token ID284
Feature activation+4.83e-01

Pos logit contributions
 debates+1.582
 adoption+1.566
birth+1.504
 amounts+1.444
Pg+1.439
Neg logit contributions
 holiest-3.527
saf-3.279
Trivia-3.207
cific-3.200
 Advantage-3.117
Token get
Token ID651
Feature activation-2.04e+00

Pos logit contributions
 holiest+0.441
saf+0.402
cific+0.399
Trivia+0.395
 Advantage+0.391
Neg logit contributions
 debates-0.260
 adoption-0.254
birth-0.248
 amounts-0.244
rons-0.243
Token
Token ID564
Feature activation+2.22e-01

Pos logit contributions
 debates+1.097
 adoption+1.092
birth+1.042
 amounts+1.024
 breastfeeding+1.024
Neg logit contributions
 holiest-1.859
saf-1.740
cific-1.697
Trivia-1.693
INGTON-1.636
Token
Token ID250
Feature activation+2.44e+00

Pos logit contributions
 holiest+0.178
saf+0.161
cific+0.159
Trivia+0.157
 Advantage+0.154
Neg logit contributions
 debates-0.143
 adoption-0.139
birth-0.138
Pg-0.138
 amounts-0.135
Tokeninto
Token ID20424
Feature activation-1.25e+00

Pos logit contributions
 holiest+2.062
saf+1.878
cific+1.850
Trivia+1.831
 Advantage+1.813
Neg logit contributions
 debates-1.460
 adoption-1.417
birth-1.411
Pg-1.397
rons-1.384
Token tech
Token ID7261
Feature activation-3.28e-01

Pos logit contributions
 debates+0.687
 adoption+0.667
birth+0.655
 amounts+0.639
Pg+0.635
Neg logit contributions
 holiest-1.127
saf-1.028
cific-1.024
Trivia-1.001
 Advantage-0.984
Token with
Token ID351
Feature activation+1.02e+00

Pos logit contributions
 debates+1.484
 adoption+1.371
 amounts+1.370
birth+1.358
rons+1.353
Neg logit contributions
 holiest-2.506
saf-2.320
cific-2.269
Trivia-2.267
 Advantage-2.238
Token leadership
Token ID5531
Feature activation+3.39e+00

Pos logit contributions
 holiest+0.918
saf+0.843
cific+0.830
Trivia+0.824
 Advantage+0.813
Neg logit contributions
 debates-0.561
 adoption-0.541
birth-0.532
Pg-0.525
 amounts-0.524
Token earlier
Token ID2961
Feature activation+1.84e+00

Pos logit contributions
 holiest+2.942
saf+2.687
cific+2.649
Trivia+2.623
 Advantage+2.601
Neg logit contributions
 debates-1.915
 adoption-1.866
birth-1.866
Pg-1.851
rons-1.817
Token this
Token ID428
Feature activation+9.58e-01

Pos logit contributions
 holiest+1.607
saf+1.468
cific+1.448
Trivia+1.441
 Advantage+1.418
Neg logit contributions
 debates-1.068
 adoption-1.030
birth-1.017
Pg-1.005
rons-1.000
Token year
Token ID614
Feature activation+5.49e+00

Pos logit contributions
 holiest+0.788
saf+0.719
cific+0.708
Trivia+0.703
 Advantage+0.693
Neg logit contributions
 debates-0.603
 adoption-0.586
birth-0.576
Pg-0.569
 amounts-0.566
Token and
Token ID290
Feature activation+2.19e+00

Pos logit contributions
 holiest+4.540
saf+4.136
cific+4.091
Trivia+4.029
 Advantage+3.992
Neg logit contributions
 debates-3.248
 adoption-3.196
Pg-3.193
birth-3.187
rons-3.118
Token pushed
Token ID7121
Feature activation-3.13e+00

Pos logit contributions
 holiest+1.986
saf+1.820
cific+1.795
Trivia+1.780
 Advantage+1.762
Neg logit contributions
 debates-1.179
 adoption-1.140
birth-1.131
Pg-1.116
rons-1.108
Token to
Token ID284
Feature activation+1.93e+00

Pos logit contributions
 debates+1.658
 adoption+1.610
 amounts+1.557
birth+1.516
Pg+1.516
Neg logit contributions
 holiest-2.893
saf-2.669
Trivia-2.614
cific-2.601
 Advantage-2.561
Token trim
Token ID15797
Feature activation-9.97e-01

Pos logit contributions
 holiest+1.655
saf+1.504
cific+1.484
Trivia+1.471
 Advantage+1.460
Neg logit contributions
 debates-1.152
 adoption-1.121
birth-1.102
Pg-1.087
rons-1.080
Token a
Token ID257
Feature activation-8.94e-01

Pos logit contributions
 debates+0.527
 adoption+0.503
 amounts+0.496
birth+0.492
Pg+0.489
Neg logit contributions
 holiest-0.925
saf-0.856
cific-0.842
Trivia-0.834
 Advantage-0.820
Token spending
Token ID4581
Feature activation+4.21e+00

Pos logit contributions
 debates+0.531
 adoption+0.517
birth+0.507
 amounts+0.505
Pg+0.503
Neg logit contributions
 holiest-0.758
saf-0.697
cific-0.685
Trivia-0.679
 Advantage-0.669
Tokenendi
Token ID43109
Feature activation+6.84e-02

Pos logit contributions
 holiest+1.772
saf+1.630
cific+1.610
Trivia+1.595
 Advantage+1.578
Neg logit contributions
 debates-0.973
 adoption-0.939
birth-0.934
Pg-0.921
rons-0.913
Token st
Token ID336
Feature activation+6.78e+00

Pos logit contributions
 holiest+0.059
saf+0.054
cific+0.054
 Advantage+0.052
Trivia+0.052
Neg logit contributions
 debates-0.040
 adoption-0.039
birth-0.038
 amounts-0.038
Pg-0.038
Tokenrolled
Token ID8375
Feature activation-4.71e-01

Pos logit contributions
 holiest+5.740
saf+5.301
cific+5.242
Trivia+5.179
rown+5.020
Neg logit contributions
 adoption-3.792
 debates-3.753
birth-3.728
Pg-3.677
 amounts-3.593
Token off
Token ID572
Feature activation-6.07e+00

Pos logit contributions
 debates+0.298
 adoption+0.289
birth+0.283
 amounts+0.281
rons+0.278
Neg logit contributions
 holiest-0.385
saf-0.353
cific-0.349
Trivia-0.342
 Advantage-0.339
Token to
Token ID284
Feature activation+2.66e+00

Pos logit contributions
 debates+3.019
 crying+2.910
 adoption+2.889
 viewing+2.871
Pg+2.826
Neg logit contributions
 holiest-5.611
saf-5.182
cific-5.133
 Advantage-5.099
INGTON-4.978
Token entertain
Token ID8204
Feature activation+1.45e+00

Pos logit contributions
 holiest+2.422
saf+2.219
cific+2.191
Trivia+2.168
 Advantage+2.151
Neg logit contributions
 debates-1.421
 adoption-1.374
birth-1.365
Pg-1.349
rons-1.336
Token (
Token ID357
Feature activation+1.02e+00

Pos logit contributions
 holiest+1.297
saf+1.185
cific+1.170
Trivia+1.155
 Advantage+1.145
Neg logit contributions
 debates-0.803
 adoption-0.778
birth-0.771
Pg-0.764
rons-0.756
Tokenor
Token ID273
Feature activation+4.71e+00

Pos logit contributions
 holiest+0.791
saf+0.703
cific+0.702
 Advantage+0.686
Trivia+0.683
Neg logit contributions
 debates-0.686
birth-0.675
Pg-0.669
 adoption-0.668
rons-0.654
Token be
Token ID307
Feature activation+4.44e-01

Pos logit contributions
 holiest+3.986
saf+3.622
cific+3.560
Trivia+3.537
 Advantage+3.504
Neg logit contributions
 debates-2.750
birth-2.685
 adoption-2.678
Pg-2.667
rons-2.633
Token entertained
Token ID34988
Feature activation+2.17e+00

Pos logit contributions
 holiest+0.406
saf+0.374
cific+0.368
Trivia+0.364
 Advantage+0.362
Neg logit contributions
 debates-0.236
 adoption-0.229
birth-0.229
Pg-0.225
rons-0.221
Token)
Token ID8
Feature activation-1.22e+00

Pos logit contributions
 holiest+1.867
saf+1.699
cific+1.677
Trivia+1.656
 Advantage+1.644
Neg logit contributions
 debates-1.271
 adoption-1.230
birth-1.225
Pg-1.212
rons-1.202
Token in
Token ID287
Feature activation+1.40e+00

Pos logit contributions
 debates+0.506
 adoption+0.488
birth+0.480
 viewing+0.472
 amounts+0.471
Neg logit contributions
 holiest-0.819
saf-0.756
cific-0.748
Trivia-0.736
 Advantage-0.726
Token his
Token ID465
Feature activation+5.37e-01

Pos logit contributions
 holiest+1.222
saf+1.116
cific+1.102
Trivia+1.090
 Advantage+1.078
Neg logit contributions
 debates-0.803
 adoption-0.774
birth-0.769
Pg-0.758
rons-0.752
Token infinite
Token ID15541
Feature activation-8.67e+00

Pos logit contributions
 holiest+0.465
saf+0.428
cific+0.424
Trivia+0.420
 Advantage+0.413
Neg logit contributions
 debates-0.312
 adoption-0.301
birth-0.295
 amounts-0.289
Pg-0.289
Token wisdom
Token ID11501
Feature activation+2.00e+00

Pos logit contributions
 debates+4.315
 amounts+4.090
 adoption+4.032
 viewing+3.884
 clam+3.841
Neg logit contributions
 holiest-7.754
cific-7.525
saf-7.401
Trivia-7.298
INGTON-7.140
Token,
Token ID11
Feature activation+9.68e-02

Pos logit contributions
 holiest+1.763
saf+1.608
cific+1.593
Trivia+1.571
 Advantage+1.559
Neg logit contributions
 debates-1.136
 adoption-1.096
birth-1.087
Pg-1.076
rons-1.064
Token tweeted
Token ID10830
Feature activation+6.73e+00

Pos logit contributions
 holiest+0.084
saf+0.076
cific+0.076
Trivia+0.074
 Advantage+0.074
Neg logit contributions
 debates-0.057
 adoption-0.055
birth-0.054
 amounts-0.054
Pg-0.053
Token the
Token ID262
Feature activation+4.33e+00

Pos logit contributions
 holiest+5.575
saf+5.043
cific+5.006
Trivia+4.952
 Advantage+4.909
Neg logit contributions
 debates-3.945
birth-3.871
Pg-3.870
 adoption-3.855
rons-3.784
Token following
Token ID1708
Feature activation+5.04e+00

Pos logit contributions
 holiest+3.669
saf+3.332
cific+3.285
Trivia+3.254
 Advantage+3.225
Neg logit contributions
 debates-2.570
 adoption-2.494
birth-2.491
Pg-2.469
rons-2.443
Token at
Token ID379
Feature activation+1.85e+00

Pos logit contributions
 holiest+4.146
saf+3.745
cific+3.696
Trivia+3.659
 Advantage+3.624
Neg logit contributions
 debates-3.092
birth-3.013
Pg-3.001
 adoption-2.998
rons-2.953
Token Ham
Token ID4345
Feature activation+2.76e+00

Pos logit contributions
 holiest+1.613
saf+1.473
cific+1.454
Trivia+1.439
 Advantage+1.422
Neg logit contributions
 debates-1.058
 adoption-1.026
birth-1.019
Pg-1.006
rons-0.997
Tokenill
Token ID359
Feature activation+4.49e-01

Pos logit contributions
 holiest+1.704
saf+1.522
cific+1.483
Trivia+1.463
 Advantage+1.431
Neg logit contributions
 debates-2.247
 adoption-2.212
birth-2.179
Pg-2.162
rons-2.150
Token a
Token ID257
Feature activation+1.16e+00

Pos logit contributions
 holiest+1.583
saf+1.448
cific+1.431
Trivia+1.416
 Advantage+1.399
Neg logit contributions
 debates-1.065
 adoption-1.037
birth-1.025
Pg-1.009
rons-1.002
Token meltdown
Token ID37824
Feature activation+2.62e+00

Pos logit contributions
 holiest+0.976
saf+0.894
cific+0.882
Trivia+0.872
 Advantage+0.865
Neg logit contributions
 debates-0.695
 adoption-0.677
birth-0.670
Pg-0.664
rons-0.656
Token or
Token ID393
Feature activation+2.79e+00

Pos logit contributions
 holiest+2.158
saf+1.959
cific+1.933
Trivia+1.909
 Advantage+1.892
Neg logit contributions
 debates-1.627
 adoption-1.582
birth-1.574
Pg-1.557
rons-1.546
Token other
Token ID584
Feature activation+5.98e+00

Pos logit contributions
 holiest+2.392
saf+2.181
cific+2.150
Trivia+2.128
 Advantage+2.108
Neg logit contributions
 debates-1.630
 adoption-1.582
birth-1.573
Pg-1.557
rons-1.542
Token releases
Token ID10050
Feature activation+1.64e+00

Pos logit contributions
 holiest+4.891
saf+4.418
cific+4.319
Trivia+4.281
 Advantage+4.228
Neg logit contributions
 debates-3.644
birth-3.565
Pg-3.546
 adoption-3.515
rons-3.508
Token,
Token ID11
Feature activation+5.51e-01

Pos logit contributions
 holiest+1.405
saf+1.284
cific+1.263
Trivia+1.253
 Advantage+1.243
Neg logit contributions
 debates-0.975
 adoption-0.943
birth-0.936
Pg-0.928
rons-0.923
Token for
Token ID329
Feature activation+2.81e-01

Pos logit contributions
 holiest+0.483
saf+0.443
cific+0.437
Trivia+0.434
 Advantage+0.428
Neg logit contributions
 debates-0.314
 adoption-0.304
birth-0.301
Pg-0.297
 amounts-0.297
Token instance
Token ID4554
Feature activation+2.26e+00

Pos logit contributions
 holiest+0.246
saf+0.224
cific+0.223
Trivia+0.221
 Advantage+0.216
Neg logit contributions
 debates-0.161
 adoption-0.158
birth-0.154
 amounts-0.152
Pg-0.152
Token from
Token ID422
Feature activation+1.36e+00

Pos logit contributions
 holiest+1.850
saf+1.679
cific+1.654
Trivia+1.637
 Advantage+1.621
Neg logit contributions
 debates-1.413
 adoption-1.374
birth-1.366
Pg-1.353
rons-1.341
Token spent
Token ID3377
Feature activation-3.44e+00

Pos logit contributions
 holiest+1.181
saf+1.079
cific+1.067
Trivia+1.054
 Advantage+1.042
Neg logit contributions
 debates-0.791
 adoption-0.766
birth-0.757
Pg-0.748
 amounts-0.743
Token fuel
Token ID5252
Feature activation+4.10e+00

Pos logit contributions
 debates+1.667
 adoption+1.619
 amounts+1.603
rons+1.569
birth+1.563
Neg logit contributions
 holiest-3.305
cific-3.077
saf-3.053
Trivia-3.001
INGTON-2.954
Token the
Token ID262
Feature activation-2.61e+00

Pos logit contributions
 debates+2.628
 adoption+2.558
 amounts+2.472
birth+2.452
Pg+2.412
Neg logit contributions
 holiest-4.348
cific-4.027
Trivia-4.010
saf-3.982
 Advantage-3.879
Token beginning
Token ID3726
Feature activation-5.53e-01

Pos logit contributions
 debates+1.571
 adoption+1.539
birth+1.481
 amounts+1.460
 viewing+1.454
Neg logit contributions
 holiest-2.128
cific-2.031
Trivia-2.008
saf-1.998
INGTON-1.964
Token of
Token ID286
Feature activation-9.55e-01

Pos logit contributions
 debates+0.321
 adoption+0.311
birth+0.309
Pg+0.305
rons+0.302
Neg logit contributions
 holiest-0.478
saf-0.436
cific-0.431
Trivia-0.427
 Advantage-0.422
Token the
Token ID262
Feature activation-2.73e+00

Pos logit contributions
 debates+0.532
 adoption+0.513
birth+0.500
 amounts+0.493
Pg+0.492
Neg logit contributions
 holiest-0.857
saf-0.783
cific-0.781
Trivia-0.779
 Advantage-0.763
Token catastrophic
Token ID22694
Feature activation-5.01e-01

Pos logit contributions
 debates+1.620
 adoption+1.577
 amounts+1.504
 clam+1.497
birth+1.491
Neg logit contributions
 holiest-2.300
cific-2.159
Trivia-2.139
saf-2.126
INGTON-2.087
Token phase
Token ID7108
Feature activation-2.11e+00

Pos logit contributions
 debates+0.287
 adoption+0.278
birth+0.271
 amounts+0.271
rons+0.265
Neg logit contributions
 holiest-0.440
cific-0.405
saf-0.402
Trivia-0.397
 Advantage-0.391
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
 debates+1.180
 adoption+1.150
birth+1.129
 amounts+1.106
Pg+1.101
Neg logit contributions
 holiest-1.871
saf-1.695
cific-1.693
Trivia-1.676
 Advantage-1.645
Token
Token ID447
Feature activation+2.74e+00

Pos logit contributions
 holiest+0.196
saf+0.178
cific+0.177
Trivia+0.175
 Advantage+0.173
Neg logit contributions
 debates-0.138
 adoption-0.134
birth-0.133
Pg-0.131
 amounts-0.130
Token
Token ID251
Feature activation+1.84e+00

Pos logit contributions
 holiest+2.489
saf+2.281
cific+2.251
Trivia+2.229
 Advantage+2.209
Neg logit contributions
 debates-1.471
 adoption-1.423
birth-1.416
Pg-1.401
rons-1.385
Token Sebastian
Token ID26190
Feature activation-1.43e+00

Pos logit contributions
 holiest+1.497
saf+1.357
cific+1.340
Trivia+1.325
 Advantage+1.311
Neg logit contributions
 debates-1.159
 adoption-1.125
birth-1.122
Pg-1.110
rons-1.096
Token P
Token ID350
Feature activation-3.02e+00

Pos logit contributions
 debates+0.796
birth+0.763
 adoption+0.762
Pg+0.753
rons+0.753
Neg logit contributions
 holiest-1.278
saf-1.164
cific-1.154
Trivia-1.138
INGTON-1.122
Token voluntary
Token ID16171
Feature activation-5.87e+00

Pos logit contributions
 debates+1.503
 adoption+1.500
birth+1.424
 amounts+1.415
 viewing+1.395
Neg logit contributions
 holiest-2.423
cific-2.203
saf-2.198
Trivia-2.183
 Advantage-2.138
Token filter
Token ID8106
Feature activation-5.85e+00

Pos logit contributions
 adoption+2.493
 debates+2.476
 viewing+2.304
 amounts+2.259
 breastfeeding+2.242
Neg logit contributions
 holiest-5.985
cific-5.533
Trivia-5.485
saf-5.441
 Advantage-5.373
Token,
Token ID11
Feature activation+8.12e-01

Pos logit contributions
 adoption+3.386
 debates+3.380
 amounts+3.142
birth+3.106
 viewing+3.105
Neg logit contributions
 holiest-5.090
cific-4.608
saf-4.551
Trivia-4.536
 Advantage-4.433
Token stating
Token ID12316
Feature activation+3.47e+00

Pos logit contributions
 holiest+0.806
saf+0.743
cific+0.734
Trivia+0.730
 Advantage+0.722
Neg logit contributions
 debates-0.370
 adoption-0.357
birth-0.352
Pg-0.346
 amounts-0.341
Token the
Token ID262
Feature activation+1.91e+00

Pos logit contributions
 holiest+2.803
saf+2.544
cific+2.506
Trivia+2.475
 Advantage+2.451
Neg logit contributions
 debates-2.177
birth-2.121
Pg-2.116
 adoption-2.111
rons-2.086
Token plan
Token ID1410
Feature activation-7.43e+00

Pos logit contributions
 holiest+1.665
saf+1.519
cific+1.499
Trivia+1.484
 Advantage+1.470
Neg logit contributions
 debates-1.091
 adoption-1.059
birth-1.051
Pg-1.041
rons-1.029
Token lacked
Token ID19989
Feature activation+3.66e+00

Pos logit contributions
 amounts+4.033
 debates+4.005
 adoption+3.816
Pg+3.718
 reflected+3.686
Neg logit contributions
 holiest-6.652
Trivia-5.942
saf-5.914
cific-5.895
 Advantage-5.831
Token transparency
Token ID13902
Feature activation+4.51e+00

Pos logit contributions
 holiest+3.132
saf+2.875
cific+2.827
Trivia+2.786
 Advantage+2.761
Neg logit contributions
 debates-2.104
birth-2.052
Pg-2.040
 adoption-2.029
rons-2.022
Token in
Token ID287
Feature activation+5.71e-01

Pos logit contributions
 holiest+3.713
saf+3.404
cific+3.343
Trivia+3.304
 Advantage+3.275
Neg logit contributions
 debates-2.713
birth-2.655
Pg-2.638
 adoption-2.632
rons-2.594
Token the
Token ID262
Feature activation-9.81e-01

Pos logit contributions
 holiest+0.485
saf+0.440
cific+0.435
Trivia+0.432
 Advantage+0.427
Neg logit contributions
 debates-0.345
 adoption-0.336
birth-0.329
 amounts-0.325
Pg-0.323
Token selection
Token ID6356
Feature activation+4.82e+00

Pos logit contributions
 debates+0.592
 adoption+0.581
 amounts+0.561
birth+0.556
Pg+0.548
Neg logit contributions
 holiest-0.834
saf-0.754
cific-0.752
Trivia-0.750
 Advantage-0.738
TokenILL
Token ID8267
Feature activation-2.59e+00

Pos logit contributions
 holiest+1.979
saf+1.795
cific+1.771
Trivia+1.748
 Advantage+1.731
Neg logit contributions
 debates-1.527
 adoption-1.486
birth-1.479
Pg-1.467
rons-1.453
TokenNOT
Token ID11929
Feature activation-2.31e+00

Pos logit contributions
 debates+1.552
 adoption+1.505
birth+1.484
Pg+1.474
 amounts+1.464
Neg logit contributions
 holiest-2.157
cific-1.991
saf-1.960
Trivia-1.922
 Advantage-1.914
TokenDIV
Token ID33569
Feature activation+4.34e+00

Pos logit contributions
 debates+1.236
birth+1.201
 adoption+1.198
Pg+1.197
rons+1.174
Neg logit contributions
 holiest-2.073
cific-1.899
saf-1.894
 Advantage-1.852
Trivia-1.838
TokenIDE
Token ID14114
Feature activation+4.16e-01

Pos logit contributions
 holiest+1.736
saf+1.396
cific+1.345
Trivia+1.339
 Advantage+1.303
Neg logit contributions
 debates-4.506
 adoption-4.419
birth-4.419
rons-4.391
Pg-4.386
Token.
Token ID13
Feature activation-6.91e-01

Pos logit contributions
 holiest+0.345
saf+0.314
cific+0.310
Trivia+0.305
 Advantage+0.303
Neg logit contributions
 debates-0.256
 adoption-0.250
birth-0.248
Pg-0.246
 amounts-0.243
TokenUS
Token ID2937
Feature activation-1.65e+00

Pos logit contributions
 debates+0.399
 adoption+0.389
Pg+0.389
birth+0.388
rons+0.379
Neg logit contributions
 holiest-0.595
saf-0.536
cific-0.535
Trivia-0.526
 Advantage-0.524
Token due
Token ID2233
Feature activation+3.11e-01

Pos logit contributions
 debates+0.887
 adoption+0.866
Pg+0.851
birth+0.846
 amounts+0.835
Neg logit contributions
 holiest-1.488
saf-1.380
cific-1.359
Trivia-1.333
 Advantage-1.329
Token to
Token ID284
Feature activation-1.55e-01

Pos logit contributions
 holiest+0.302
saf+0.278
cific+0.275
Trivia+0.272
 Advantage+0.270
Neg logit contributions
 debates-0.147
 adoption-0.142
birth-0.141
Pg-0.140
rons-0.138
Token dangerous
Token ID4923
Feature activation+1.60e+00

Pos logit contributions
 debates+0.094
 adoption+0.092
 amounts+0.089
birth+0.088
Pg+0.088
Neg logit contributions
 holiest-0.131
saf-0.120
cific-0.118
Trivia-0.117
 Advantage-0.116
Token,
Token ID11
Feature activation+2.23e+00

Pos logit contributions
 holiest+1.396
saf+1.272
cific+1.258
Trivia+1.243
 Advantage+1.234
Neg logit contributions
 debates-0.923
 adoption-0.894
birth-0.880
Pg-0.875
rons-0.869
Token illegal
Token ID5293
Feature activation-5.02e-01

Pos logit contributions
 holiest+1.884
saf+1.717
cific+1.691
Trivia+1.673
 Advantage+1.658
Neg logit contributions
 debates-1.337
 adoption-1.297
birth-1.290
Pg-1.278
rons-1.265
Token.
Token ID13
Feature activation-1.31e+00

Pos logit contributions
 debates+0.523
 adoption+0.506
birth+0.497
 amounts+0.491
rons+0.491
Neg logit contributions
 holiest-0.763
saf-0.700
cific-0.686
INGTON-0.673
Trivia-0.672
Token The
Token ID383
Feature activation+2.41e+00

Pos logit contributions
 debates+0.764
 adoption+0.740
birth+0.739
Pg+0.738
 amounts+0.721
Neg logit contributions
 holiest-1.125
saf-1.017
cific-1.004
INGTON-0.969
Trivia-0.967
Token game
Token ID983
Feature activation-4.09e+00

Pos logit contributions
 holiest+2.092
saf+1.909
cific+1.882
Trivia+1.863
 Advantage+1.846
Neg logit contributions
 debates-1.388
 adoption-1.346
birth-1.341
Pg-1.328
rons-1.314
Token also
Token ID635
Feature activation-1.16e-01

Pos logit contributions
 debates+2.274
 adoption+2.177
 amounts+2.164
birth+2.096
Pg+2.072
Neg logit contributions
 holiest-3.646
saf-3.357
cific-3.303
INGTON-3.266
Trivia-3.233
Token includes
Token ID3407
Feature activation-7.33e-01

Pos logit contributions
 debates+0.068
 adoption+0.065
birth+0.064
 amounts+0.064
Pg+0.063
Neg logit contributions
 holiest-0.101
saf-0.091
cific-0.090
Trivia-0.090
 Advantage-0.089
Token a
Token ID257
Feature activation-3.00e+00

Pos logit contributions
 debates+0.427
 adoption+0.411
birth+0.402
 amounts+0.401
 viewing+0.397
Neg logit contributions
 holiest-0.639
saf-0.583
cific-0.578
Trivia-0.565
INGTON-0.564
Token character
Token ID2095
Feature activation+3.28e+00

Pos logit contributions
 debates+1.758
 adoption+1.712
 viewing+1.688
birth+1.674
 bathing+1.659
Neg logit contributions
 holiest-2.535
saf-2.315
cific-2.297
INGTON-2.256
Trivia-2.247
Token creation
Token ID6282
Feature activation+4.14e+00

Pos logit contributions
 holiest+2.798
saf+2.542
cific+2.512
Trivia+2.489
 Advantage+2.469
Neg logit contributions
 debates-1.918
birth-1.855
 adoption-1.854
Pg-1.841
rons-1.819
Token system
Token ID1080
Feature activation-2.32e+00

Pos logit contributions
 holiest+3.704
saf+3.378
cific+3.324
Trivia+3.304
 Advantage+3.304
Neg logit contributions
 debates-2.222
birth-2.174
 adoption-2.147
Pg-2.140
rons-2.119
Token for
Token ID329
Feature activation-9.65e-02

Pos logit contributions
 debates+1.287
 adoption+1.256
 amounts+1.216
 viewing+1.215
birth+1.211
Neg logit contributions
 holiest-2.065
saf-1.900
cific-1.873
Trivia-1.847
INGTON-1.835
Token making
Token ID1642
Feature activation+2.98e+00

Pos logit contributions
 debates+0.053
 adoption+0.052
birth+0.050
 amounts+0.050
 viewing+0.049
Neg logit contributions
 holiest-0.087
saf-0.080
cific-0.079
Trivia-0.078
INGTON-0.077
Token I
Token ID314
Feature activation+1.18e+00

Pos logit contributions
 holiest+0.142
saf+0.129
cific+0.127
Trivia+0.126
 Advantage+0.125
Neg logit contributions
 debates-0.095
 adoption-0.092
birth-0.091
Pg-0.090
 amounts-0.089
Token jab
Token ID33896
Feature activation+5.31e+00

Pos logit contributions
 holiest+1.034
saf+0.939
cific+0.931
Trivia+0.920
 Advantage+0.911
Neg logit contributions
 debates-0.677
 adoption-0.656
birth-0.652
Pg-0.644
rons-0.642
Token all
Token ID477
Feature activation-9.42e-01

Pos logit contributions
 holiest+4.628
saf+4.232
cific+4.178
Trivia+4.126
 Advantage+4.100
Neg logit contributions
 debates-2.971
 adoption-2.888
birth-2.875
Pg-2.855
rons-2.795
Token the
Token ID262
Feature activation+1.04e+00

Pos logit contributions
 debates+0.509
 adoption+0.487
 amounts+0.481
Pg+0.474
rons+0.474
Neg logit contributions
 holiest-0.860
saf-0.782
Trivia-0.773
cific-0.764
INGTON-0.758
Token time
Token ID640
Feature activation+4.38e-02

Pos logit contributions
 holiest+0.874
saf+0.793
cific+0.779
Trivia+0.777
 Advantage+0.764
Neg logit contributions
 debates-0.636
 adoption-0.611
birth-0.604
 amounts-0.602
Pg-0.601
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
 holiest+0.039
saf+0.035
cific+0.035
Trivia+0.034
 Advantage+0.034
Neg logit contributions
 debates-0.025
 adoption-0.024
birth-0.024
 amounts-0.023
Pg-0.023
Token It
Token ID632
Feature activation-3.45e+00

Pos logit contributions
 debates+0.896
birth+0.865
Pg+0.862
 adoption+0.859
 amounts+0.841
Neg logit contributions
 holiest-1.295
saf-1.163
cific-1.147
Trivia-1.123
INGTON-1.109
Token seems
Token ID2331
Feature activation+2.58e+00

Pos logit contributions
 debates+1.957
 amounts+1.902
birth+1.862
 adoption+1.840
Pg+1.830
Neg logit contributions
 holiest-3.036
saf-2.723
cific-2.711
Trivia-2.699
INGTON-2.692
Token I
Token ID314
Feature activation+3.30e+00

Pos logit contributions
 holiest+2.268
saf+2.072
cific+2.043
Trivia+2.023
 Advantage+2.004
Neg logit contributions
 debates-1.449
 adoption-1.404
birth-1.399
Pg-1.385
rons-1.370
Token
Token ID447
Feature activation-4.44e-01

Pos logit contributions
 holiest+2.814
saf+2.565
cific+2.528
Trivia+2.502
 Advantage+2.478
Neg logit contributions
 debates-1.942
 adoption-1.885
birth-1.876
Pg-1.858
rons-1.839
Token
Token ID247
Feature activation-1.38e+00

Pos logit contributions
 debates+0.231
 adoption+0.224
birth+0.223
Pg+0.221
 amounts+0.216
Neg logit contributions
 holiest-0.410
saf-0.376
cific-0.372
Trivia-0.367
 Advantage-0.363
Token which
Token ID543
Feature activation+5.94e-01

Pos logit contributions
 holiest+2.080
saf+1.901
cific+1.874
Trivia+1.856
 Advantage+1.838
Neg logit contributions
 debates-1.332
 adoption-1.290
birth-1.285
Pg-1.271
rons-1.258
Token were
Token ID547
Feature activation+2.11e-01

Pos logit contributions
 holiest+0.543
saf+0.498
cific+0.491
Trivia+0.488
 Advantage+0.481
Neg logit contributions
 debates-0.316
 adoption-0.305
birth-0.304
Pg-0.299
 amounts-0.297
Token discovered
Token ID5071
Feature activation+2.90e+00

Pos logit contributions
 holiest+0.183
saf+0.168
cific+0.165
Trivia+0.164
 Advantage+0.162
Neg logit contributions
 debates-0.123
 adoption-0.119
birth-0.119
Pg-0.117
rons-0.116
Token on
Token ID319
Feature activation-1.67e-01

Pos logit contributions
 holiest+2.530
saf+2.310
cific+2.278
Trivia+2.254
 Advantage+2.234
Neg logit contributions
 debates-1.664
 adoption-1.612
birth-1.605
Pg-1.587
rons-1.572
Token the
Token ID262
Feature activation+1.69e+00

Pos logit contributions
 debates+0.098
 adoption+0.096
birth+0.095
Pg+0.093
 amounts+0.093
Neg logit contributions
 holiest-0.143
saf-0.131
cific-0.130
Trivia-0.128
 Advantage-0.126
Token infant
Token ID11212
Feature activation-1.10e+01

Pos logit contributions
 holiest+1.462
saf+1.348
cific+1.331
Trivia+1.316
 Advantage+1.295
Neg logit contributions
 debates-0.981
 adoption-0.953
birth-0.941
Pg-0.928
 amounts-0.922
Token dated
Token ID14567
Feature activation+1.56e+00

Pos logit contributions
birth+5.458
 adoption+5.394
 debates+5.351
 breastfeeding+5.340
 stret+5.311
Neg logit contributions
 holiest-9.437
saf-8.752
cific-8.600
INGTON-8.585
Trivia-8.376
Token three
Token ID1115
Feature activation+5.63e+00

Pos logit contributions
 holiest+1.463
saf+1.345
cific+1.327
Trivia+1.315
 Advantage+1.303
Neg logit contributions
 debates-0.786
 adoption-0.758
birth-0.754
Pg-0.746
rons-0.736
Token to
Token ID284
Feature activation+7.05e+00

Pos logit contributions
 holiest+5.347
saf+4.846
cific+4.832
Trivia+4.774
 Advantage+4.700
Neg logit contributions
 debates-2.618
birth-2.528
 adoption-2.521
rons-2.505
tumblr-2.478
Token four
Token ID1440
Feature activation-3.20e-01

Pos logit contributions
 holiest+5.030
saf+4.510
cific+4.402
Trivia+4.337
 Advantage+4.326
Neg logit contributions
 debates-4.991
Pg-4.876
birth-4.854
 adoption-4.845
rons-4.798
Token weeks
Token ID2745
Feature activation-5.89e-01

Pos logit contributions
 debates+0.143
 adoption+0.138
birth+0.136
Pg+0.134
 amounts+0.131
Neg logit contributions
 holiest-0.321
saf-0.299
cific-0.294
Trivia-0.292
 Advantage-0.290
Tokenys
Token ID893
Feature activation-3.08e+00

Pos logit contributions
 debates+4.672
birth+4.609
 adoption+4.504
rons+4.495
tumblr+4.490
Neg logit contributions
 holiest-4.820
 Advantage-4.060
saf-4.028
Trivia-4.026
cific-4.009
Token 3
Token ID513
Feature activation-1.76e+00

Pos logit contributions
 debates+1.976
birth+1.929
 adoption+1.896
rons+1.848
Pg+1.843
Neg logit contributions
 holiest-2.457
saf-2.241
cific-2.215
Trivia-2.160
INGTON-2.149
Tokenway
Token ID1014
Feature activation-2.24e-01

Pos logit contributions
 debates+1.120
birth+1.080
 adoption+1.066
Pg+1.058
rons+1.048
Neg logit contributions
 holiest-1.427
saf-1.308
cific-1.276
Trivia-1.250
INGTON-1.249
Token Dream
Token ID7610
Feature activation-3.43e+00

Pos logit contributions
 debates+0.141
 adoption+0.137
birth+0.136
Pg+0.133
rons+0.133
Neg logit contributions
 holiest-0.184
saf-0.167
cific-0.165
Trivia-0.162
INGTON-0.159
Token-
Token ID12
Feature activation-1.28e+00

Pos logit contributions
 debates+2.148
birth+2.121
 adoption+2.053
rons+2.017
 amounts+2.009
Neg logit contributions
 holiest-2.801
cific-2.515
saf-2.488
INGTON-2.420
Trivia-2.391
TokenAnt
Token ID13217
Feature activation-1.02e+01

Pos logit contributions
 debates+0.806
birth+0.805
Pg+0.798
 adoption+0.781
rons+0.764
Neg logit contributions
 holiest-1.044
cific-0.931
saf-0.924
 Advantage-0.903
INGTON-0.887
Token @
Token ID2488
Feature activation-1.36e+00

Pos logit contributions
 debates+6.420
rons+6.175
birth+6.116
 Weiner+6.076
 adoption+5.978
Neg logit contributions
 holiest-7.713
cific-6.831
INGTON-6.762
saf-6.735
Trivia-6.484
Token Casino
Token ID32802
Feature activation+3.25e+00

Pos logit contributions
 debates+0.820
birth+0.795
 adoption+0.787
Pg+0.781
rons+0.771
Neg logit contributions
 holiest-1.149
saf-1.037
cific-1.030
Trivia-1.012
INGTON-0.996
Token Recap
Token ID46585
Feature activation-1.32e-02

Pos logit contributions
 holiest+2.568
saf+2.324
cific+2.284
Trivia+2.266
 Advantage+2.244
Neg logit contributions
 debates-2.107
 adoption-2.056
birth-2.042
Pg-2.028
rons-2.008
Token-
Token ID12
Feature activation-1.68e+00

Pos logit contributions
 debates+0.009
birth+0.008
 adoption+0.008
Pg+0.008
rons+0.008
Neg logit contributions
 holiest-0.011
saf-0.010
cific-0.009
Trivia-0.009
 Advantage-0.009
TokenSports
Token ID18153
Feature activation+1.24e+00

Pos logit contributions
 debates+1.056
birth+1.055
Pg+1.048
 adoption+1.020
tumblr+0.998
Neg logit contributions
 holiest-1.372
cific-1.223
saf-1.213
 Advantage-1.183
INGTON-1.161
Token pornography
Token ID18384
Feature activation-2.49e-01

Pos logit contributions
birth+2.288
 viewing+2.269
 debates+2.249
 adoption+2.199
 breastfeeding+2.060
Neg logit contributions
 holiest-8.053
cific-7.485
saf-7.385
INGTON-7.260
 Advantage-7.249
Token or
Token ID393
Feature activation-1.09e+00

Pos logit contributions
 debates+0.148
 adoption+0.143
birth+0.141
Pg+0.139
rons+0.138
Neg logit contributions
 holiest-0.213
saf-0.196
cific-0.194
Trivia-0.190
 Advantage-0.189
Token spam
Token ID18084
Feature activation+2.42e+00

Pos logit contributions
 debates+0.601
 adoption+0.584
birth+0.570
 amounts+0.563
Pg+0.560
Neg logit contributions
 holiest-0.982
saf-0.908
cific-0.899
Trivia-0.886
 Advantage-0.878
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
 holiest+1.871
saf+1.687
cific+1.660
Trivia+1.640
 Advantage+1.624
Neg logit contributions
 debates-1.622
 adoption-1.579
birth-1.571
Pg-1.558
rons-1.545
Token The
Token ID383
Feature activation+2.05e+00

Pos logit contributions
 debates+0.909
 adoption+0.876
birth+0.874
Pg+0.869
rons+0.854
Neg logit contributions
 holiest-1.364
saf-1.234
cific-1.229
Trivia-1.207
INGTON-1.183
Token change
Token ID1487
Feature activation-1.13e+01

Pos logit contributions
 holiest+1.739
saf+1.583
cific+1.555
Trivia+1.537
 Advantage+1.529
Neg logit contributions
 debates-1.218
birth-1.187
 adoption-1.182
Pg-1.177
rons-1.162
Token comes
Token ID2058
Feature activation+1.59e+00

Pos logit contributions
 amounts+5.456
 debates+5.353
 adoption+5.191
 reflected+5.089
birth+4.953
Neg logit contributions
 holiest-10.323
Trivia-9.483
cific-9.441
saf-9.210
INGTON-9.208
Token about
Token ID546
Feature activation+3.30e+00

Pos logit contributions
 holiest+1.317
saf+1.198
cific+1.177
Trivia+1.168
 Advantage+1.155
Neg logit contributions
 debates-0.986
 adoption-0.955
birth-0.943
Pg-0.934
rons-0.927
Token six
Token ID2237
Feature activation+3.57e+00

Pos logit contributions
 holiest+2.691
saf+2.440
cific+2.404
Trivia+2.378
 Advantage+2.354
Neg logit contributions
 debates-2.073
 adoption-2.015
birth-2.006
Pg-1.988
rons-1.969
Token months
Token ID1933
Feature activation+4.20e+00

Pos logit contributions
 holiest+3.395
saf+3.116
cific+3.081
Trivia+3.058
 Advantage+3.027
Neg logit contributions
 debates-1.742
birth-1.685
 adoption-1.683
Pg-1.663
rons-1.646
Token after
Token ID706
Feature activation+1.95e+00

Pos logit contributions
 holiest+2.822
saf+2.499
cific+2.459
Trivia+2.424
 Advantage+2.395
Neg logit contributions
 debates-3.229
 adoption-3.157
birth-3.152
Pg-3.132
rons-3.104
Token.
Token ID13
Feature activation-3.07e+00

Pos logit contributions
 holiest+1.740
saf+1.583
cific+1.557
Trivia+1.540
 Advantage+1.527
Neg logit contributions
 debates-1.507
 adoption-1.465
birth-1.455
Pg-1.446
rons-1.435
Token
Token ID198
Feature activation+2.82e-01

Pos logit contributions
 debates+1.755
 adoption+1.727
birth+1.717
Pg+1.673
 amounts+1.655
Neg logit contributions
 holiest-2.696
saf-2.422
cific-2.408
Trivia-2.338
INGTON-2.317
Token
Token ID198
Feature activation-1.18e+00

Pos logit contributions
 holiest+0.234
saf+0.211
cific+0.209
Trivia+0.206
 Advantage+0.204
Neg logit contributions
 debates-0.174
birth-0.169
 adoption-0.169
Pg-0.168
rons-0.165
Token2014
Token ID4967
Feature activation-1.87e+00

Pos logit contributions
birth+0.862
Pg+0.857
 debates+0.847
 adoption+0.841
tumblr+0.830
Neg logit contributions
 holiest-0.864
cific-0.752
saf-0.736
 Advantage-0.729
INGTON-0.709
Token Don
Token ID2094
Feature activation-1.58e+00

Pos logit contributions
 debates+1.117
 adoption+1.063
birth+1.052
 amounts+1.047
rons+1.040
Neg logit contributions
 holiest-1.587
saf-1.434
cific-1.426
Trivia-1.389
INGTON-1.379
Token C
Token ID327
Feature activation-8.81e+00

Pos logit contributions
 debates+0.810
birth+0.784
 adoption+0.778
Pg+0.771
rons+0.762
Neg logit contributions
 holiest-1.477
saf-1.350
cific-1.328
Trivia-1.314
 Advantage-1.302
Tokenhead
Token ID2256
Feature activation-2.12e+00

Pos logit contributions
birth+4.499
croft+4.258
Pg+4.065
tumblr+4.057
 debates+3.997
Neg logit contributions
 holiest-8.319
 Advantage-7.359
INGTON-7.206
cific-7.139
Trivia-7.083
Tokenle
Token ID293
Feature activation-1.70e+00

Pos logit contributions
 debates+1.079
birth+1.065
Pg+1.049
 adoption+1.043
rons+1.026
Neg logit contributions
 holiest-1.981
saf-1.786
cific-1.775
Trivia-1.761
 Advantage-1.760
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
 debates+1.029
 adoption+1.005
birth+0.999
Pg+0.975
rons+0.972
Neg logit contributions
 holiest-1.428
saf-1.290
cific-1.282
Trivia-1.251
 Advantage-1.237
Token
Token ID198
Feature activation-6.51e-01

Pos logit contributions
 debates+0.192
birth+0.188
 adoption+0.186
Pg+0.186
rons+0.182
Neg logit contributions
 holiest-0.271
saf-0.243
cific-0.241
Trivia-0.237
 Advantage-0.235
Token2014
Token ID4967
Feature activation-2.67e+00

Pos logit contributions
birth+0.478
Pg+0.475
 debates+0.474
 adoption+0.469
tumblr+0.460
Neg logit contributions
 holiest-0.467
cific-0.406
saf-0.400
 Advantage-0.393
INGTON-0.384
Token no
Token ID645
Feature activation+1.62e+00

Pos logit contributions
 holiest+3.697
saf+3.365
cific+3.308
Trivia+3.268
 Advantage+3.249
Neg logit contributions
 debates-2.530
birth-2.469
Pg-2.456
 adoption-2.444
rons-2.427
Token distinction
Token ID12941
Feature activation+1.14e+00

Pos logit contributions
 holiest+1.508
saf+1.385
cific+1.367
Trivia+1.355
 Advantage+1.343
Neg logit contributions
 debates-0.829
 adoption-0.802
birth-0.793
Pg-0.784
rons-0.776
Token between
Token ID1022
Feature activation+1.14e+00

Pos logit contributions
 holiest+0.893
saf+0.798
cific+0.786
Trivia+0.780
 Advantage+0.771
Neg logit contributions
 debates-0.761
 adoption-0.738
birth-0.734
 amounts-0.727
Pg-0.722
Token youth
Token ID6205
Feature activation-3.89e+00

Pos logit contributions
 holiest+1.055
saf+0.968
cific+0.957
Trivia+0.947
 Advantage+0.936
Neg logit contributions
 debates-0.600
 adoption-0.582
birth-0.572
Pg-0.565
 amounts-0.561
Token and
Token ID290
Feature activation+8.84e-01

Pos logit contributions
 debates+2.109
 adoption+2.063
 amounts+2.007
 viewing+1.972
rons+1.963
Neg logit contributions
 holiest-3.551
saf-3.213
cific-3.192
Trivia-3.150
INGTON-3.113
Token adult
Token ID4044
Feature activation-9.27e+00

Pos logit contributions
 holiest+0.923
saf+0.856
cific+0.846
Trivia+0.838
 Advantage+0.830
Neg logit contributions
 debates-0.357
 adoption-0.343
birth-0.336
Pg-0.330
rons-0.327
Token punishment
Token ID9837
Feature activation+8.11e-01

Pos logit contributions
 debates+4.531
 adoption+4.427
 amounts+4.329
 viewing+4.192
 cort+4.049
Neg logit contributions
 holiest-8.668
saf-8.028
cific-7.968
INGTON-7.869
Trivia-7.786
Token or
Token ID393
Feature activation+1.50e+00

Pos logit contributions
 holiest+0.703
saf+0.642
cific+0.630
Trivia+0.624
 Advantage+0.617
Neg logit contributions
 debates-0.476
 adoption-0.460
birth-0.452
 amounts-0.452
Pg-0.448
Token between
Token ID1022
Feature activation+7.23e-01

Pos logit contributions
 holiest+1.412
saf+1.297
cific+1.281
Trivia+1.269
 Advantage+1.258
Neg logit contributions
 debates-0.760
 adoption-0.735
birth-0.728
Pg-0.719
rons-0.711
Token consecutive
Token ID12785
Feature activation-1.61e-01

Pos logit contributions
 holiest+0.683
saf+0.629
cific+0.622
Trivia+0.616
 Advantage+0.608
Neg logit contributions
 debates-0.365
 adoption-0.353
birth-0.346
Pg-0.341
 amounts-0.340
Token and
Token ID290
Feature activation+4.90e+00

Pos logit contributions
 debates+0.076
 adoption+0.073
birth+0.072
 amounts+0.071
Pg+0.070
Neg logit contributions
 holiest-0.157
saf-0.145
cific-0.144
Trivia-0.143
 Advantage-0.141