TOP ACTIVATIONS
MAX = 16.346

long time and this sub wo ofer is worth every penny
you get from this sub wo ofer . I have this
, Iowa . Hide Caption 5 of 15 Photos : Carly
# deb ates # Occup y The Deb ates pic .
energy - and - ut ilities , family - and -
tell which Wall Street entities provoke the most grip es .
s what the Consumer Financial Protection Bureau which was
B from The best sub wo ofer ever !!! So I
't see this as too big of a concern though since
- children , consumer - f inance , wh itt les
. ( Photo by Kathleen Flynn , N OL A .
. I have this sub wo ofer paired up with Martin
as the Great E man c ip ator , standing tall
July . Advertisement Continue reading the main story
schemes , guys who best fit their locker room and culture
k ong / a - flex ible - limit - tr
vette forum . com / forums ... with - p ics
Bac ile indirectly and inadvertently infl amed people half a world
it , I call these instances " P V H VM
Michael G . Flynn and his wife , Jen

MIN ACTIVATIONS
MIN = -15.506

tapes , clothes , and jewelry , burned posters , read
vs Pyro blast Prim al Druid vs Er t
Sam P anche vre ( Sam s Burger Joint
@ 144 Hz ( Tr ace Free = 80 )
Anders takes me on a det our into the brewery to
for the purpose of stealing jewelry or money ," the email
@ 144 Hz ( Tr ace Free = 80 )
meet . M ort g ages , rent ,
i . e . the prim etime soap or the romantic
okingly . One of the rare st of his Lead b
ik ram Bak shi , managing director of CPR L ,
The executive coach and mother has lived on Pot rero
there . Black Donkey is located in Ros common
gl ove Courier Prim al Surge vs Safe Passage
L IG O , is complete and the project starts taking
around to them while the mother is tranquil ized . It
Friday , June 16 Last day to place Player on
, it has long been recognized by science and medicine as
/ or Survival + The Prim er from your local book
. The opposite may be true if teachers in poor health

INTERVAL 8.383 - 16.346
CONTAINS 0.351%

A . Maybe a black variant will be coming soon as
border with Bangladesh . Two narratives quickly emerged , with the
Other governments only borrow to stimulate the economy during a recession
months for the larger Hyp ac ros aurus . Most birds
The early social ization of aggressive victims of bullying . Child

INTERVAL 0.420 - 8.383
CONTAINS 43.554%

, too . Prime Minister Trudeau might
have had when taking up these principles shown by S if
- working crew from his TV show , Alfred H itch
a veteran safety expert e - mail ed NASA 's chief
the fire and called 911 . Dep uties found scor ch

INTERVAL -7.543 - 0.420
CONTAINS 55.400%

ing way book to get it started what a lifes aver
ashes And Block Basics . I mentioned that blocks are not
adult male engaged these officers with a handgun and began firing
). The defects of sonic technology that become encoded in digital
( It 's a good idea to dip these in boiling

INTERVAL -15.506 - -7.543
CONTAINS 0.696%

58 per cent in the rest of Canada .
once outside she was seen inspecting the bad burn on her
only possible if you can find things that you may not
updated with any information we receive . The St
meet in the Sword - Art Festival finals . That was
Token long
Token ID890
Feature activation-2.12e+00

Pos logit contributions
race+2.072
hibited+1.457
uning+1.387
strate+1.361
ilaterally+1.360
Neg logit contributions
orthy-1.522
terday-1.287
Years-1.281
oppy-1.262
ounters-1.235
Token time
Token ID640
Feature activation-3.84e+00

Pos logit contributions
race+2.431
hibited+1.786
uning+1.708
strate+1.698
ilaterally+1.685
Neg logit contributions
orthy-1.340
Years-1.101
terday-1.098
oppy-1.072
ounters-1.039
Token and
Token ID290
Feature activation+2.96e+00

Pos logit contributions
race+3.488
hibited+2.329
uning+2.218
strate+2.160
inary+2.148
Neg logit contributions
orthy-3.265
Years-2.849
terday-2.801
oppy-2.793
ounters-2.714
Token this
Token ID428
Feature activation+3.23e+00

Pos logit contributions
orthy+2.332
Years+2.033
terday+2.002
oppy+1.957
ounters+1.925
Neg logit contributions
race-2.931
hibited-2.030
uning-1.911
ilaterally-1.904
strate-1.897
Token sub
Token ID850
Feature activation+5.51e+00

Pos logit contributions
orthy+2.646
Years+2.318
terday+2.293
oppy+2.236
ounters+2.203
Neg logit contributions
race-3.094
hibited-2.113
ilaterally-1.982
uning-1.974
strate-1.963
Tokenwo
Token ID21638
Feature activation+1.63e+01

Pos logit contributions
orthy+4.367
Years+3.842
terday+3.792
oppy+3.703
ounters+3.669
Neg logit contributions
race-5.234
hibited-3.592
ilaterally-3.431
uning-3.354
inary-3.329
Tokenofer
Token ID30288
Feature activation+1.07e+01

Pos logit contributions
orthy+5.592
onder+3.884
oppy+3.741
Years+3.181
ounters+2.959
Neg logit contributions
race-21.087
COR-16.348
ilaterally-16.262
gdala-16.044
hibited-16.016
Token is
Token ID318
Feature activation+5.80e+00

Pos logit contributions
orthy+7.628
Years+6.793
terday+6.720
onder+6.549
 imag+6.528
Neg logit contributions
race-10.257
hibited-7.247
ilaterally-6.889
strate-6.754
uning-6.644
Token worth
Token ID2861
Feature activation+8.99e+00

Pos logit contributions
orthy+4.556
Years+3.989
terday+3.936
oppy+3.809
ounters+3.777
Neg logit contributions
race-5.631
hibited-3.868
uning-3.661
ilaterally-3.661
strate-3.585
Token every
Token ID790
Feature activation+3.95e+00

Pos logit contributions
orthy+5.463
Years+4.707
terday+4.607
oppy+4.460
onder+4.324
Neg logit contributions
race-10.130
hibited-7.470
ilaterally-7.120
uning-7.052
strate-7.010
Token penny
Token ID26369
Feature activation+6.72e-01

Pos logit contributions
orthy+2.608
Years+2.209
terday+2.167
oppy+2.111
ounters+2.065
Neg logit contributions
race-4.417
hibited-3.215
uning-3.057
ilaterally-3.047
strate-3.038
Token you
Token ID345
Feature activation+4.28e+00

Pos logit contributions
orthy+2.073
Years+1.786
terday+1.759
oppy+1.718
ounters+1.686
Neg logit contributions
race-2.863
hibited-2.016
uning-1.910
ilaterally-1.898
strate-1.893
Token get
Token ID651
Feature activation-5.57e-01

Pos logit contributions
orthy+3.085
Years+2.641
terday+2.586
oppy+2.522
ounters+2.486
Neg logit contributions
race-4.497
hibited-3.205
uning-3.046
ilaterally-3.035
strate-3.005
Token from
Token ID422
Feature activation+1.91e+00

Pos logit contributions
race+0.555
hibited+0.386
uning+0.364
strate+0.360
ilaterally+0.360
Neg logit contributions
orthy-0.435
Years-0.377
terday-0.373
oppy-0.367
ounters-0.356
Token this
Token ID428
Feature activation+3.04e+00

Pos logit contributions
orthy+1.493
Years+1.297
terday+1.275
oppy+1.249
ounters+1.228
Neg logit contributions
race-1.906
hibited-1.323
uning-1.249
ilaterally-1.241
strate-1.238
Token sub
Token ID850
Feature activation+4.17e+00

Pos logit contributions
orthy+2.340
Years+2.021
terday+1.993
oppy+1.949
ounters+1.915
Neg logit contributions
race-3.057
hibited-2.138
ilaterally-2.018
uning-2.015
strate-1.999
Tokenwo
Token ID21638
Feature activation+1.54e+01

Pos logit contributions
orthy+3.359
Years+2.923
terday+2.881
oppy+2.826
ounters+2.777
Neg logit contributions
race-3.988
hibited-2.751
ilaterally-2.607
uning-2.582
strate-2.540
Tokenofer
Token ID30288
Feature activation+9.07e+00

Pos logit contributions
orthy+5.917
onder+4.171
oppy+3.973
Years+3.663
ounters+3.381
Neg logit contributions
race-19.623
COR-15.024
ilaterally-14.896
hibited-14.739
gdala-14.606
Token.
Token ID13
Feature activation+4.86e+00

Pos logit contributions
orthy+6.725
Years+5.864
terday+5.745
onder+5.548
oppy+5.536
Neg logit contributions
race-8.731
hibited-6.174
ilaterally-5.921
strate-5.781
uning-5.774
Token I
Token ID314
Feature activation-9.71e-01

Pos logit contributions
orthy+3.871
Years+3.404
terday+3.334
oppy+3.252
ounters+3.202
Neg logit contributions
race-4.714
hibited-3.249
ilaterally-3.069
uning-3.054
strate-3.040
Token have
Token ID423
Feature activation-8.81e-01

Pos logit contributions
race+0.905
hibited+0.610
uning+0.574
strate+0.566
ilaterally+0.561
Neg logit contributions
orthy-0.827
Years-0.724
terday-0.713
oppy-0.697
ounters-0.686
Token this
Token ID428
Feature activation+1.05e+00

Pos logit contributions
race+0.824
hibited+0.559
uning+0.526
ilaterally+0.516
strate+0.515
Neg logit contributions
orthy-0.748
Years-0.648
terday-0.643
oppy-0.631
ounters-0.617
Token,
Token ID11
Feature activation+8.65e-01

Pos logit contributions
race+1.280
hibited+0.858
uning+0.814
ilaterally+0.793
strate+0.792
Neg logit contributions
orthy-1.166
Years-1.033
terday-1.026
oppy-0.996
ounters-0.980
Token Iowa
Token ID9406
Feature activation-2.79e+00

Pos logit contributions
orthy+0.652
Years+0.563
terday+0.559
oppy+0.539
ounters+0.534
Neg logit contributions
race-0.890
hibited-0.623
uning-0.593
ilaterally-0.586
strate-0.582
Token.
Token ID13
Feature activation-2.10e+00

Pos logit contributions
race+2.489
hibited+1.631
uning+1.534
ilaterally+1.509
strate+1.505
Neg logit contributions
orthy-2.454
Years-2.180
terday-2.166
oppy-2.113
ounters-2.071
Token Hide
Token ID10415
Feature activation+3.58e+00

Pos logit contributions
race+2.136
hibited+1.498
uning+1.401
 Offensive+1.393
strate+1.393
Neg logit contributions
orthy-1.612
terday-1.379
Years-1.367
oppy-1.345
ounters-1.317
Token Caption
Token ID11260
Feature activation-2.64e+00

Pos logit contributions
orthy+2.199
Years+1.880
oppy+1.756
terday+1.753
ounters+1.726
Neg logit contributions
race-4.085
hibited-3.004
ilaterally-2.918
uning-2.895
strate-2.842
Token 5
Token ID642
Feature activation+1.53e+01

Pos logit contributions
race+2.672
hibited+1.892
 Offensive+1.796
COR+1.794
uning+1.792
Neg logit contributions
orthy-1.999
terday-1.735
Years-1.673
oppy-1.639
ounters-1.597
Token of
Token ID286
Feature activation+3.83e+00

Pos logit contributions
orthy+5.236
Years+5.009
 imag+3.969
ounters+3.845
oppy+3.711
Neg logit contributions
race-17.914
 cryst-15.371
 mathemat-14.985
ilaterally-14.729
hibited-14.262
Token 15
Token ID1315
Feature activation+3.45e+00

Pos logit contributions
orthy+2.117
Years+1.734
oppy+1.615
terday+1.614
ounters+1.577
Neg logit contributions
race-4.659
hibited-3.490
ilaterally-3.403
uning-3.389
strate-3.339
Token Photos
Token ID9434
Feature activation-4.07e-01

Pos logit contributions
orthy+2.404
Years+2.144
oppy+1.994
ounters+1.979
terday+1.966
Neg logit contributions
race-3.636
hibited-2.567
ilaterally-2.508
uning-2.484
strate-2.443
Token:
Token ID25
Feature activation+2.07e+00

Pos logit contributions
race+0.354
hibited+0.230
uning+0.214
strate+0.211
ilaterally+0.211
Neg logit contributions
orthy-0.372
Years-0.329
terday-0.326
oppy-0.319
ounters-0.314
Token Carly
Token ID35982
Feature activation+4.56e+00

Pos logit contributions
orthy+1.124
Years+0.923
terday+0.873
oppy+0.858
ounters+0.837
Neg logit contributions
race-2.549
hibited-1.912
uning-1.852
ilaterally-1.844
strate-1.825
Token #
Token ID1303
Feature activation-2.81e+00

Pos logit contributions
orthy+0.860
Years+0.740
terday+0.728
oppy+0.711
ounters+0.698
Neg logit contributions
race-1.198
hibited-0.844
uning-0.800
ilaterally-0.793
strate-0.792
Tokendeb
Token ID11275
Feature activation+8.22e+00

Pos logit contributions
race+2.631
hibited+1.722
uning+1.618
COR+1.609
ilaterally+1.599
Neg logit contributions
orthy-2.405
terday-2.100
Years-2.091
oppy-2.042
ounters-2.039
Tokenates
Token ID689
Feature activation+5.09e+00

Pos logit contributions
orthy+5.616
Years+4.705
oppy+4.625
terday+4.575
onder+4.564
Neg logit contributions
race-8.506
hibited-6.244
strate-5.959
ilaterally-5.930
uning-5.918
Token #
Token ID1303
Feature activation-2.05e+00

Pos logit contributions
orthy+3.834
Years+3.325
terday+3.274
oppy+3.182
onder+3.121
Neg logit contributions
race-5.075
hibited-3.588
uning-3.387
strate-3.380
ilaterally-3.362
TokenOccup
Token ID47658
Feature activation+7.56e+00

Pos logit contributions
race+1.988
hibited+1.335
uning+1.257
ilaterally+1.248
strate+1.243
Neg logit contributions
orthy-1.675
Years-1.452
terday-1.449
oppy-1.411
ounters-1.399
Tokeny
Token ID88
Feature activation+1.52e+01

Pos logit contributions
orthy+6.648
Years+5.882
oppy+5.675
terday+5.620
ounters+5.562
Neg logit contributions
race-6.567
hibited-4.368
uning-4.081
ilaterally-4.030
strate-4.016
TokenThe
Token ID464
Feature activation+1.98e+00

Pos logit contributions
orthy+10.906
Years+10.111
terday+9.238
onder+9.141
oppy+9.127
Neg logit contributions
race-13.239
hibited-9.379
uning-9.006
strate-8.788
ilaterally-8.782
TokenDeb
Token ID16587
Feature activation+7.21e+00

Pos logit contributions
orthy+1.473
Years+1.263
terday+1.248
oppy+1.219
ounters+1.195
Neg logit contributions
race-2.064
hibited-1.454
uning-1.377
ilaterally-1.366
strate-1.365
Tokenates
Token ID689
Feature activation+5.58e+00

Pos logit contributions
orthy+4.892
Years+4.158
oppy+4.034
terday+3.951
ounters+3.927
Neg logit contributions
race-7.531
hibited-5.550
uning-5.313
ilaterally-5.287
strate-5.237
Token pic
Token ID8301
Feature activation-3.73e-02

Pos logit contributions
orthy+3.759
Years+3.247
terday+3.162
oppy+3.052
onder+2.961
Neg logit contributions
race-6.001
hibited-4.356
uning-4.176
strate-4.144
ilaterally-4.112
Token.
Token ID13
Feature activation+5.32e+00

Pos logit contributions
race+0.035
hibited+0.023
uning+0.022
ilaterally+0.022
strate+0.021
Neg logit contributions
orthy-0.032
Years-0.028
terday-0.028
oppy-0.027
ounters-0.027
Tokenenergy
Token ID22554
Feature activation+1.27e+01

Pos logit contributions
orthy+5.209
Years+4.741
oppy+4.589
onder+4.534
terday+4.533
Neg logit contributions
race-4.674
hibited-2.979
strate-2.804
uning-2.747
ilaterally-2.704
Token-
Token ID12
Feature activation+6.01e+00

Pos logit contributions
orthy+8.973
Years+7.837
ounters+7.536
oppy+7.474
terday+7.386
Neg logit contributions
race-12.394
hibited-8.744
ilaterally-8.354
strate-8.235
COR-8.090
Tokenand
Token ID392
Feature activation+3.99e+00

Pos logit contributions
orthy+4.835
Years+4.342
oppy+4.166
terday+4.156
ounters+4.127
Neg logit contributions
race-5.557
hibited-3.777
strate-3.590
ilaterally-3.541
uning-3.518
Token-
Token ID12
Feature activation+5.10e+00

Pos logit contributions
orthy+3.239
Years+2.822
terday+2.741
oppy+2.724
ounters+2.694
Neg logit contributions
race-3.766
hibited-2.588
ilaterally-2.462
uning-2.414
strate-2.399
Tokenut
Token ID315
Feature activation-1.72e+00

Pos logit contributions
orthy+4.179
Years+3.683
terday+3.575
oppy+3.553
onder+3.519
Neg logit contributions
race-4.734
hibited-3.260
strate-3.040
ilaterally-3.015
uning-2.987
Tokenilities
Token ID2410
Feature activation+1.51e+01

Pos logit contributions
race+1.466
hibited+0.926
uning+0.866
inary+0.850
strate+0.849
Neg logit contributions
orthy-1.626
terday-1.455
Years-1.441
oppy-1.401
ounters-1.378
Token,
Token ID11
Feature activation+6.67e+00

Pos logit contributions
orthy+8.005
Years+6.940
ounters+6.644
terday+6.254
oppy+6.098
Neg logit contributions
race-15.898
ilaterally-11.846
hibited-11.825
 cryst-11.617
matically-11.361
Token family
Token ID1641
Feature activation+1.15e-01

Pos logit contributions
orthy+4.632
Years+3.972
terday+3.903
ounters+3.805
oppy+3.789
Neg logit contributions
race-6.941
hibited-5.069
strate-4.761
uning-4.726
ilaterally-4.721
Token-
Token ID12
Feature activation+3.55e+00

Pos logit contributions
orthy+0.100
Years+0.088
terday+0.087
oppy+0.085
ounters+0.084
Neg logit contributions
race-0.106
hibited-0.071
uning-0.066
ilaterally-0.065
strate-0.065
Tokenand
Token ID392
Feature activation+8.43e-01

Pos logit contributions
orthy+2.713
Years+2.360
onder+2.282
terday+2.272
oppy+2.262
Neg logit contributions
race-3.506
hibited-2.419
gdala-2.319
 Offensive-2.313
uning-2.305
Token-
Token ID12
Feature activation+9.31e-01

Pos logit contributions
orthy+0.739
Years+0.651
terday+0.643
oppy+0.631
ounters+0.621
Neg logit contributions
race-0.763
hibited-0.505
uning-0.473
ilaterally-0.468
strate-0.468
Token tell
Token ID1560
Feature activation-4.04e-01

Pos logit contributions
orthy+1.975
Years+1.708
terday+1.682
oppy+1.645
ounters+1.617
Neg logit contributions
race-2.601
hibited-1.818
uning-1.722
ilaterally-1.706
strate-1.702
Token which
Token ID543
Feature activation-2.35e-02

Pos logit contributions
race+0.387
hibited+0.261
uning+0.246
strate+0.244
ilaterally+0.243
Neg logit contributions
orthy-0.336
Years-0.292
terday-0.287
oppy-0.284
ounters-0.278
Token Wall
Token ID5007
Feature activation+5.57e+00

Pos logit contributions
race+0.025
hibited+0.018
uning+0.017
ilaterally+0.017
strate+0.017
Neg logit contributions
orthy-0.017
Years-0.014
terday-0.014
oppy-0.014
ounters-0.013
Token Street
Token ID3530
Feature activation+3.60e+00

Pos logit contributions
orthy+4.237
Years+3.711
oppy+3.578
ounters+3.573
terday+3.549
Neg logit contributions
race-5.469
hibited-3.848
uning-3.627
strate-3.625
ilaterally-3.596
Token entities
Token ID12066
Feature activation+5.38e+00

Pos logit contributions
orthy+2.472
Years+2.104
terday+2.065
oppy+2.008
ounters+1.992
Neg logit contributions
race-3.916
hibited-2.828
uning-2.695
strate-2.665
ilaterally-2.665
Token provoke
Token ID29791
Feature activation+1.50e+01

Pos logit contributions
orthy+4.085
Years+3.552
terday+3.522
ounters+3.395
oppy+3.370
Neg logit contributions
race-5.298
hibited-3.700
uning-3.580
strate-3.477
ilaterally-3.469
Token the
Token ID262
Feature activation+8.90e+00

Pos logit contributions
orthy+8.967
Years+7.925
 imag+7.836
terday+7.753
ounters+7.666
Neg logit contributions
race-14.483
hibited-10.455
ilaterally-10.135
uning-10.074
strate-10.045
Token most
Token ID749
Feature activation+7.54e+00

Pos logit contributions
orthy+4.852
Years+4.073
terday+3.945
oppy+3.841
ounters+3.762
Neg logit contributions
race-10.386
hibited-7.730
strate-7.521
ilaterally-7.447
uning-7.437
Token grip
Token ID11762
Feature activation+3.00e+00

Pos logit contributions
orthy+5.337
Years+4.596
terday+4.577
oppy+4.454
ounters+4.408
Neg logit contributions
race-7.648
hibited-5.440
ilaterally-5.172
strate-5.155
uning-5.128
Tokenes
Token ID274
Feature activation+4.37e+00

Pos logit contributions
orthy+2.641
Years+2.354
terday+2.299
ounters+2.267
oppy+2.264
Neg logit contributions
race-2.623
hibited-1.751
strate-1.609
uning-1.605
ilaterally-1.592
Token.
Token ID13
Feature activation+2.26e+00

Pos logit contributions
orthy+3.611
Years+3.143
terday+3.134
ounters+3.014
oppy+3.009
Neg logit contributions
race-4.108
hibited-2.788
uning-2.634
strate-2.613
ilaterally-2.589
Token
Token ID247
Feature activation+5.79e-01

Pos logit contributions
race+1.141
hibited+0.661
uning+0.610
strate+0.598
ilaterally+0.596
Neg logit contributions
orthy-1.627
Years-1.470
terday-1.447
oppy-1.433
ounters-1.414
Tokens
Token ID82
Feature activation+3.71e+00

Pos logit contributions
orthy+0.482
Years+0.421
terday+0.414
oppy+0.408
ounters+0.400
Neg logit contributions
race-0.553
hibited-0.373
uning-0.352
strate-0.348
ilaterally-0.347
Token what
Token ID644
Feature activation+1.68e+00

Pos logit contributions
orthy+2.954
Years+2.589
terday+2.566
oppy+2.480
ounters+2.449
Neg logit contributions
race-3.605
hibited-2.486
uning-2.347
ilaterally-2.324
strate-2.319
Token the
Token ID262
Feature activation+7.42e-01

Pos logit contributions
orthy+1.362
Years+1.184
terday+1.164
oppy+1.143
ounters+1.123
Neg logit contributions
race-1.643
hibited-1.126
uning-1.061
ilaterally-1.051
strate-1.050
Token Consumer
Token ID18110
Feature activation+4.70e+00

Pos logit contributions
orthy+0.583
Years+0.506
terday+0.496
oppy+0.488
ounters+0.479
Neg logit contributions
race-0.741
hibited-0.513
uning-0.485
ilaterally-0.481
strate-0.478
Token Financial
Token ID11302
Feature activation+1.47e+01

Pos logit contributions
orthy+3.429
Years+2.960
terday+2.871
oppy+2.811
ounters+2.780
Neg logit contributions
race-4.895
hibited-3.448
uning-3.276
ilaterally-3.272
strate-3.240
Token Protection
Token ID9985
Feature activation+5.51e+00

Pos logit contributions
orthy+8.298
Years+8.072
ounters+7.238
 Sketch+6.868
 Guinness+6.850
Neg logit contributions
race-14.843
hibited-10.771
uning-10.628
gdala-10.477
ilaterally-10.443
Token Bureau
Token ID9840
Feature activation+5.40e+00

Pos logit contributions
orthy+2.800
Years+2.399
terday+2.220
onder+2.130
oppy+2.099
Neg logit contributions
race-6.778
hibited-5.057
ilaterally-4.937
uning-4.895
strate-4.834
Token
Token ID960
Feature activation+1.66e+00

Pos logit contributions
orthy+4.081
Years+3.566
terday+3.529
oppy+3.413
ounters+3.389
Neg logit contributions
race-5.382
hibited-3.766
uning-3.551
ilaterally-3.539
strate-3.519
Tokenwhich
Token ID4758
Feature activation+7.47e-01

Pos logit contributions
orthy+1.624
Years+1.449
terday+1.434
oppy+1.412
ounters+1.393
Neg logit contributions
race-1.342
hibited-0.831
uning-0.769
ilaterally-0.758
strate-0.756
Token was
Token ID373
Feature activation-7.50e-02

Pos logit contributions
orthy+0.603
Years+0.524
terday+0.511
oppy+0.507
ounters+0.495
Neg logit contributions
race-0.733
hibited-0.503
uning-0.474
ilaterally-0.470
strate-0.468
TokenB
Token ID33
Feature activation-1.50e+00

Pos logit contributions
race+2.035
hibited+1.354
uning+1.282
strate+1.266
ilaterally+1.259
Neg logit contributions
orthy-1.816
Years-1.581
terday-1.569
oppy-1.539
ounters-1.512
Token from
Token ID422
Feature activation-1.94e+00

Pos logit contributions
race+1.337
hibited+0.871
uning+0.823
ilaterally+0.816
inary+0.810
Neg logit contributions
orthy-1.325
Years-1.174
terday-1.166
oppy-1.135
ounters-1.120
Token The
Token ID383
Feature activation-7.54e-01

Pos logit contributions
race+1.860
hibited+1.273
uning+1.201
ilaterally+1.177
inary+1.174
Neg logit contributions
orthy-1.592
Years-1.374
terday-1.364
oppy-1.342
ounters-1.316
Token best
Token ID1266
Feature activation+1.13e+00

Pos logit contributions
race+0.794
hibited+0.565
uning+0.538
strate+0.526
ilaterally+0.526
Neg logit contributions
orthy-0.554
Years-0.470
terday-0.464
oppy-0.453
ounters-0.444
Token sub
Token ID850
Feature activation+2.63e+00

Pos logit contributions
orthy+0.867
Years+0.749
terday+0.737
oppy+0.722
ounters+0.708
Neg logit contributions
race-1.148
hibited-0.802
uning-0.760
ilaterally-0.752
strate-0.751
Tokenwo
Token ID21638
Feature activation+1.47e+01

Pos logit contributions
orthy+2.065
Years+1.803
terday+1.770
oppy+1.731
ounters+1.703
Neg logit contributions
race-2.601
hibited-1.802
uning-1.699
ilaterally-1.698
strate-1.679
Tokenofer
Token ID30288
Feature activation+9.44e+00

Pos logit contributions
orthy+5.106
onder+3.311
oppy+3.251
Years+2.967
terday+2.626
Neg logit contributions
race-19.471
gdala-15.100
ilaterally-14.998
hibited-14.922
COR-14.833
Token ever
Token ID1683
Feature activation+1.34e+00

Pos logit contributions
orthy+6.427
Years+5.708
terday+5.506
onder+5.266
ounters+5.254
Neg logit contributions
race-9.547
hibited-6.848
ilaterally-6.576
strate-6.484
COR-6.387
Token!!!
Token ID10185
Feature activation+9.95e-01

Pos logit contributions
orthy+1.118
Years+0.978
terday+0.965
oppy+0.946
ounters+0.930
Neg logit contributions
race-1.274
hibited-0.864
uning-0.813
ilaterally-0.805
strate-0.803
Token So
Token ID1406
Feature activation-2.78e+00

Pos logit contributions
orthy+0.827
Years+0.720
terday+0.711
oppy+0.699
ounters+0.688
Neg logit contributions
race-0.948
hibited-0.643
uning-0.607
ilaterally-0.599
strate-0.598
Token I
Token ID314
Feature activation-2.03e+00

Pos logit contributions
race+2.701
hibited+1.856
uning+1.764
strate+1.734
ilaterally+1.712
Neg logit contributions
orthy-2.199
Years-1.891
terday-1.883
oppy-1.817
ounters-1.816
Token't
Token ID470
Feature activation+1.33e+00

Pos logit contributions
orthy+4.227
Years+3.788
oppy+3.601
terday+3.578
ounters+3.562
Neg logit contributions
race-4.931
hibited-3.386
ilaterally-3.297
uning-3.211
strate-3.157
Token see
Token ID766
Feature activation+7.16e+00

Pos logit contributions
orthy+0.871
Years+0.733
terday+0.718
oppy+0.699
ounters+0.683
Neg logit contributions
race-1.500
hibited-1.098
uning-1.046
ilaterally-1.039
strate-1.035
Token this
Token ID428
Feature activation+7.19e+00

Pos logit contributions
orthy+4.725
Years+4.129
terday+3.922
oppy+3.836
onder+3.820
Neg logit contributions
race-7.508
hibited-5.495
ilaterally-5.265
uning-5.163
strate-5.127
Token as
Token ID355
Feature activation+9.89e+00

Pos logit contributions
orthy+4.253
Years+3.626
onder+3.391
ounters+3.317
 imag+3.296
Neg logit contributions
race-7.970
hibited-6.066
ilaterally-5.831
uning-5.703
gdala-5.653
Token too
Token ID1165
Feature activation+1.12e+01

Pos logit contributions
orthy+4.412
Years+3.520
terday+3.051
oppy+3.017
onder+2.955
Neg logit contributions
race-12.442
hibited-9.688
ilaterally-9.351
strate-9.328
COR-9.295
Token big
Token ID1263
Feature activation+1.41e+01

Pos logit contributions
orthy+3.334
Years+2.535
oppy+2.207
onder+2.180
 imag+2.141
Neg logit contributions
race-15.198
hibited-12.512
strate-12.088
ilaterally-12.024
gdala-11.956
Token of
Token ID286
Feature activation+3.19e+00

Pos logit contributions
orthy+5.000
Years+4.692
 imag+4.110
onder+4.005
oppy+3.740
Neg logit contributions
race-16.489
hibited-13.202
ilaterally-13.135
strate-12.736
gdala-12.722
Token a
Token ID257
Feature activation+5.55e+00

Pos logit contributions
orthy+2.264
Years+1.983
terday+1.881
oppy+1.879
onder+1.841
Neg logit contributions
race-3.316
hibited-2.376
ilaterally-2.274
uning-2.245
strate-2.244
Token concern
Token ID2328
Feature activation+7.94e+00

Pos logit contributions
orthy+3.554
Years+3.031
oppy+2.894
onder+2.893
terday+2.846
Neg logit contributions
race-6.009
hibited-4.468
ilaterally-4.271
strate-4.271
uning-4.220
Token though
Token ID996
Feature activation+5.43e+00

Pos logit contributions
orthy+3.158
Years+2.448
terday+2.132
onder+2.102
ounters+2.000
Neg logit contributions
race-10.653
hibited-8.280
ilaterally-7.971
strate-7.903
uning-7.880
Token since
Token ID1201
Feature activation+3.42e+00

Pos logit contributions
orthy+3.333
Years+2.908
terday+2.839
oppy+2.662
ounters+2.631
Neg logit contributions
race-6.076
hibited-4.521
ilaterally-4.307
strate-4.289
uning-4.277
Token-
Token ID12
Feature activation+9.31e-01

Pos logit contributions
orthy+0.739
Years+0.651
terday+0.643
oppy+0.631
ounters+0.621
Neg logit contributions
race-0.763
hibited-0.505
uning-0.473
ilaterally-0.468
strate-0.468
Tokenchildren
Token ID17197
Feature activation-7.82e-01

Pos logit contributions
orthy+1.018
Years+0.921
terday+0.901
oppy+0.893
ounters+0.884
Neg logit contributions
race-0.634
hibited-0.358
uning-0.321
ilaterally-0.315
strate-0.313
Token,
Token ID11
Feature activation+5.76e+00

Pos logit contributions
race+0.758
hibited+0.519
uning+0.489
ilaterally+0.485
strate+0.484
Neg logit contributions
orthy-0.636
Years-0.555
terday-0.547
oppy-0.535
ounters-0.527
Token consumer
Token ID7172
Feature activation+7.12e+00

Pos logit contributions
orthy+4.073
Years+3.500
terday+3.445
oppy+3.346
ounters+3.337
Neg logit contributions
race-5.990
hibited-4.340
strate-4.083
uning-4.064
ilaterally-4.045
Token-
Token ID12
Feature activation+1.03e+01

Pos logit contributions
orthy+5.600
Years+4.930
terday+4.836
oppy+4.675
ounters+4.661
Neg logit contributions
race-6.866
hibited-4.721
ilaterally-4.452
uning-4.385
strate-4.333
Tokenf
Token ID69
Feature activation+1.41e+01

Pos logit contributions
orthy+7.580
Years+6.760
oppy+6.483
terday+6.402
onder+6.360
Neg logit contributions
race-9.305
hibited-6.577
gdala-6.491
 Offensive-6.324
heastern-6.230
Tokeninance
Token ID14149
Feature activation+1.14e+01

Pos logit contributions
orthy+8.326
oppy+7.099
onder+6.875
Years+6.773
ounters+6.713
Neg logit contributions
race-14.861
hibited-11.067
gdala-11.044
 Offensive-10.928
 BaseType-10.802
Token,
Token ID11
Feature activation+7.16e+00

Pos logit contributions
orthy+6.929
ounters+5.860
Years+5.723
terday+5.642
onder+5.624
Neg logit contributions
race-12.026
hibited-8.890
ilaterally-8.393
matically-8.298
COR-8.293
Token wh
Token ID348
Feature activation-1.74e+00

Pos logit contributions
orthy+4.881
Years+4.177
terday+4.111
ounters+3.998
oppy+3.969
Neg logit contributions
race-7.508
hibited-5.500
strate-5.194
ilaterally-5.130
uning-5.124
Tokenitt
Token ID715
Feature activation+2.73e+00

Pos logit contributions
race+1.962
hibited+1.418
uning+1.365
inary+1.358
ilaterally+1.356
Neg logit contributions
orthy-1.129
Years-0.987
terday-0.965
oppy-0.914
ounters-0.880
Tokenles
Token ID829
Feature activation-2.35e+00

Pos logit contributions
orthy+1.716
Years+1.421
terday+1.395
oppy+1.369
ounters+1.336
Neg logit contributions
race-3.127
hibited-2.308
uning-2.197
ilaterally-2.194
strate-2.188
Token.
Token ID13
Feature activation+6.05e+00

Pos logit contributions
orthy+1.038
Years+0.914
terday+0.903
oppy+0.886
ounters+0.868
Neg logit contributions
race-1.136
hibited-0.762
uning-0.716
ilaterally-0.709
strate-0.707
Token (
Token ID357
Feature activation+9.28e+00

Pos logit contributions
orthy+4.466
Years+3.919
terday+3.736
oppy+3.643
ounters+3.593
Neg logit contributions
race-6.171
hibited-4.303
ilaterally-4.176
uning-4.117
strate-4.088
TokenPhoto
Token ID6191
Feature activation+3.06e+00

Pos logit contributions
orthy+6.965
Years+6.331
terday+5.764
oppy+5.729
ounters+5.616
Neg logit contributions
race-8.830
hibited-6.181
ilaterally-6.041
uning-5.969
strate-5.886
Token by
Token ID416
Feature activation+5.89e+00

Pos logit contributions
orthy+2.573
Years+2.279
terday+2.238
oppy+2.162
onder+2.149
Neg logit contributions
race-2.811
hibited-1.871
uning-1.791
ilaterally-1.761
strate-1.757
Token Kathleen
Token ID31275
Feature activation+5.34e+00

Pos logit contributions
orthy+4.082
Years+3.500
terday+3.428
oppy+3.318
ounters+3.276
Neg logit contributions
race-6.186
hibited-4.459
uning-4.260
ilaterally-4.251
strate-4.223
Token Flynn
Token ID14654
Feature activation+1.39e+01

Pos logit contributions
orthy+3.837
Years+3.261
terday+3.176
oppy+3.144
onder+3.054
Neg logit contributions
race-5.580
hibited-3.992
ilaterally-3.806
uning-3.772
strate-3.767
Token,
Token ID11
Feature activation+4.99e+00

Pos logit contributions
orthy+9.867
Years+8.153
ounters+7.939
terday+7.935
 Guinness+7.759
Neg logit contributions
race-13.239
hibited-9.392
uning-8.846
ilaterally-8.812
gdala-8.539
Token N
Token ID399
Feature activation+1.24e+00

Pos logit contributions
orthy+3.824
Years+3.288
terday+3.220
oppy+3.141
ounters+3.120
Neg logit contributions
race-5.016
hibited-3.510
uning-3.332
ilaterally-3.318
strate-3.280
TokenOL
Token ID3535
Feature activation-8.33e-01

Pos logit contributions
orthy+0.869
Years+0.740
terday+0.728
oppy+0.709
ounters+0.695
Neg logit contributions
race-1.341
hibited-0.962
uning-0.915
ilaterally-0.907
strate-0.905
TokenA
Token ID32
Feature activation-8.56e-01

Pos logit contributions
race+0.722
hibited+0.478
COR+0.455
uning+0.448
ilaterally+0.440
Neg logit contributions
orthy-0.735
terday-0.661
ounters-0.650
Years-0.648
oppy-0.648
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
race+0.719
hibited+0.460
uning+0.432
COR+0.430
inary+0.425
Neg logit contributions
orthy-0.794
terday-0.715
Years-0.710
oppy-0.694
ounters-0.678
Token.
Token ID13
Feature activation+4.86e+00

Pos logit contributions
orthy+6.725
Years+5.864
terday+5.745
onder+5.548
oppy+5.536
Neg logit contributions
race-8.731
hibited-6.174
ilaterally-5.921
strate-5.781
uning-5.774
Token I
Token ID314
Feature activation-9.71e-01

Pos logit contributions
orthy+3.871
Years+3.404
terday+3.334
oppy+3.252
ounters+3.202
Neg logit contributions
race-4.714
hibited-3.249
ilaterally-3.069
uning-3.054
strate-3.040
Token have
Token ID423
Feature activation-8.81e-01

Pos logit contributions
race+0.905
hibited+0.610
uning+0.574
strate+0.566
ilaterally+0.561
Neg logit contributions
orthy-0.827
Years-0.724
terday-0.713
oppy-0.697
ounters-0.686
Token this
Token ID428
Feature activation+1.05e+00

Pos logit contributions
race+0.824
hibited+0.559
uning+0.526
ilaterally+0.516
strate+0.515
Neg logit contributions
orthy-0.748
Years-0.648
terday-0.643
oppy-0.631
ounters-0.617
Token sub
Token ID850
Feature activation+3.74e+00

Pos logit contributions
orthy+0.809
Years+0.699
terday+0.687
oppy+0.673
ounters+0.660
Neg logit contributions
race-1.067
hibited-0.744
uning-0.706
strate-0.698
ilaterally-0.696
Tokenwo
Token ID21638
Feature activation+1.38e+01

Pos logit contributions
orthy+2.830
Years+2.475
terday+2.430
oppy+2.381
ounters+2.333
Neg logit contributions
race-3.758
hibited-2.628
ilaterally-2.490
uning-2.473
strate-2.448
Tokenofer
Token ID30288
Feature activation+7.72e+00

Pos logit contributions
orthy+5.300
onder+3.645
oppy+3.552
Years+3.338
ounters+3.039
Neg logit contributions
race-17.973
COR-13.799
ilaterally-13.515
hibited-13.470
 Offensive-13.316
Token paired
Token ID20312
Feature activation+2.31e+00

Pos logit contributions
orthy+5.520
Years+4.899
terday+4.826
oppy+4.651
ounters+4.592
Neg logit contributions
race-7.730
hibited-5.480
ilaterally-5.216
uning-5.104
strate-5.082
Token up
Token ID510
Feature activation+2.88e+00

Pos logit contributions
orthy+1.729
Years+1.491
terday+1.466
oppy+1.434
ounters+1.406
Neg logit contributions
race-2.387
hibited-1.682
uning-1.591
ilaterally-1.581
strate-1.575
Token with
Token ID351
Feature activation+3.40e+00

Pos logit contributions
orthy+2.147
Years+1.854
terday+1.824
oppy+1.779
ounters+1.747
Neg logit contributions
race-2.962
hibited-2.089
uning-1.973
ilaterally-1.963
strate-1.956
Token Martin
Token ID5780
Feature activation-2.62e+00

Pos logit contributions
orthy+2.470
Years+2.140
terday+2.107
oppy+2.058
ounters+2.012
Neg logit contributions
race-3.532
hibited-2.503
ilaterally-2.365
uning-2.362
strate-2.356
Token as
Token ID355
Feature activation+9.05e-01

Pos logit contributions
orthy+1.156
Years+1.006
terday+0.991
oppy+0.970
ounters+0.953
Neg logit contributions
race-1.437
hibited-0.992
uning-0.936
ilaterally-0.928
strate-0.927
Token the
Token ID262
Feature activation-4.12e-01

Pos logit contributions
orthy+0.723
Years+0.630
terday+0.620
oppy+0.607
ounters+0.597
Neg logit contributions
race-0.891
hibited-0.614
uning-0.579
ilaterally-0.574
strate-0.573
Token Great
Token ID3878
Feature activation-8.09e-01

Pos logit contributions
race+0.411
hibited+0.285
uning+0.267
strate+0.266
ilaterally+0.265
Neg logit contributions
orthy-0.323
Years-0.284
terday-0.278
oppy-0.272
ounters-0.268
Token E
Token ID412
Feature activation+4.91e+00

Pos logit contributions
race+0.796
hibited+0.547
uning+0.515
strate+0.510
ilaterally+0.510
Neg logit contributions
orthy-0.647
Years-0.566
terday-0.558
oppy-0.545
ounters-0.535
Tokenman
Token ID805
Feature activation+6.44e-01

Pos logit contributions
orthy+3.888
Years+3.277
terday+3.251
oppy+3.210
onder+3.183
Neg logit contributions
race-4.774
hibited-3.303
ilaterally-3.173
uning-3.131
inary-3.089
Tokenc
Token ID66
Feature activation+1.35e+01

Pos logit contributions
orthy+0.616
Years+0.549
terday+0.543
oppy+0.533
ounters+0.526
Neg logit contributions
race-0.531
hibited-0.335
uning-0.310
ilaterally-0.306
strate-0.306
Tokenip
Token ID541
Feature activation+3.26e+00

Pos logit contributions
orthy+7.598
ounters+6.087
onder+5.842
terday+5.769
oppy+5.761
Neg logit contributions
race-14.917
hibited-11.162
ilaterally-10.894
uning-10.788
gdala-10.717
Tokenator
Token ID1352
Feature activation-1.39e-01

Pos logit contributions
orthy+2.762
Years+2.395
oppy+2.356
onder+2.315
terday+2.310
Neg logit contributions
race-2.986
hibited-2.020
uning-1.908
strate-1.885
ilaterally-1.860
Token,
Token ID11
Feature activation+9.46e-01

Pos logit contributions
race+0.131
hibited+0.089
uning+0.083
strate+0.082
ilaterally+0.082
Neg logit contributions
orthy-0.116
Years-0.102
terday-0.101
oppy-0.099
ounters-0.097
Token standing
Token ID5055
Feature activation+2.39e+00

Pos logit contributions
orthy+0.767
Years+0.669
terday+0.661
oppy+0.646
ounters+0.635
Neg logit contributions
race-0.921
hibited-0.631
uning-0.595
strate-0.589
ilaterally-0.589
Token tall
Token ID7331
Feature activation+6.35e+00

Pos logit contributions
orthy+1.912
Years+1.667
terday+1.643
oppy+1.601
ounters+1.583
Neg logit contributions
race-2.340
hibited-1.616
uning-1.522
ilaterally-1.508
strate-1.499
Token July
Token ID2901
Feature activation-2.73e+00

Pos logit contributions
race+0.606
hibited+0.432
uning+0.410
ilaterally+0.409
strate+0.405
Neg logit contributions
orthy-0.403
Years-0.343
terday-0.339
oppy-0.331
ounters-0.322
Token.
Token ID13
Feature activation-9.93e-01

Pos logit contributions
race+2.461
hibited+1.605
ilaterally+1.519
uning+1.503
strate+1.470
Neg logit contributions
orthy-2.390
Years-2.115
terday-2.072
oppy-2.050
ounters-1.986
Token
Token ID198
Feature activation-1.77e+00

Pos logit contributions
race+0.992
hibited+0.691
uning+0.649
ilaterally+0.641
strate+0.639
Neg logit contributions
orthy-0.777
Years-0.667
terday-0.660
oppy-0.650
ounters-0.635
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
race+1.776
hibited+1.226
uning+1.157
strate+1.145
ilaterally+1.132
Neg logit contributions
orthy-1.391
terday-1.193
Years-1.187
oppy-1.165
ounters-1.133
TokenAdvertisement
Token ID4723
Feature activation-4.55e+00

Pos logit contributions
race+0.426
hibited+0.295
uning+0.277
COR+0.276
strate+0.275
Neg logit contributions
orthy-0.330
terday-0.281
Years-0.278
oppy-0.276
ounters-0.270
Token Continue
Token ID10054
Feature activation+1.34e+01

Pos logit contributions
race+3.287
hibited+1.901
uning+1.760
 Offensive+1.695
strate+1.687
Neg logit contributions
orthy-4.784
terday-4.248
Years-4.243
oppy-4.209
ounters-4.102
Token reading
Token ID3555
Feature activation+5.64e+00

Pos logit contributions
orthy+7.151
Years+6.298
terday+6.097
 imag+6.016
oppy+6.001
Neg logit contributions
race-14.072
hibited-10.583
ilaterally-10.441
strate-10.260
uning-9.939
Token the
Token ID262
Feature activation+1.03e+01

Pos logit contributions
orthy+3.486
Years+3.021
terday+2.900
oppy+2.829
ounters+2.753
Neg logit contributions
race-6.295
hibited-4.622
ilaterally-4.487
uning-4.444
strate-4.377
Token main
Token ID1388
Feature activation+8.02e-01

Pos logit contributions
orthy+3.651
onder+2.623
Years+2.567
 imag+2.540
oppy+2.517
Neg logit contributions
race-13.404
hibited-10.700
ilaterally-10.507
strate-10.262
uning-10.228
Token story
Token ID1621
Feature activation+8.44e+00

Pos logit contributions
orthy+0.572
Years+0.489
terday+0.480
oppy+0.469
ounters+0.460
Neg logit contributions
race-0.855
hibited-0.611
uning-0.580
ilaterally-0.577
strate-0.575
Token
Token ID198
Feature activation-2.43e-01

Pos logit contributions
orthy+4.574
Years+4.172
onder+3.671
terday+3.649
oppy+3.612
Neg logit contributions
race-9.556
hibited-7.147
ilaterally-7.107
uning-6.985
strate-6.805
Token schemes
Token ID16546
Feature activation+3.10e+00

Pos logit contributions
orthy+3.330
Years+2.900
terday+2.825
oppy+2.757
ounters+2.713
Neg logit contributions
race-4.558
hibited-3.221
uning-3.039
strate-3.004
ilaterally-2.987
Token,
Token ID11
Feature activation+1.87e+00

Pos logit contributions
orthy+2.512
Years+2.185
terday+2.170
oppy+2.112
ounters+2.079
Neg logit contributions
race-2.993
hibited-2.055
uning-1.933
strate-1.919
ilaterally-1.912
Token guys
Token ID3730
Feature activation+1.09e+00

Pos logit contributions
orthy+1.531
Years+1.336
terday+1.320
oppy+1.293
ounters+1.269
Neg logit contributions
race-1.798
hibited-1.224
uning-1.155
ilaterally-1.145
strate-1.142
Token who
Token ID508
Feature activation+2.76e+00

Pos logit contributions
orthy+0.946
Years+0.834
terday+0.825
oppy+0.809
ounters+0.795
Neg logit contributions
race-0.995
hibited-0.662
uning-0.620
ilaterally-0.613
strate-0.612
Token best
Token ID1266
Feature activation+4.12e+00

Pos logit contributions
orthy+2.094
Years+1.808
terday+1.780
oppy+1.738
ounters+1.708
Neg logit contributions
race-2.814
hibited-1.973
uning-1.869
ilaterally-1.851
strate-1.848
Token fit
Token ID4197
Feature activation+1.34e+01

Pos logit contributions
orthy+2.574
Years+2.147
terday+2.102
oppy+2.026
ounters+2.000
Neg logit contributions
race-4.754
hibited-3.507
uning-3.350
ilaterally-3.323
strate-3.300
Token their
Token ID511
Feature activation+1.04e+01

Pos logit contributions
orthy+7.854
Years+6.784
 imag+6.591
terday+6.316
oppy+6.306
Neg logit contributions
race-13.866
hibited-10.358
uning-9.909
inary-9.722
strate-9.641
Token locker
Token ID17355
Feature activation-1.55e+00

Pos logit contributions
orthy+7.114
Years+6.201
terday+6.041
 imag+5.952
oppy+5.930
Neg logit contributions
race-10.546
hibited-7.695
uning-7.226
strate-7.104
inary-7.043
Token room
Token ID2119
Feature activation+4.17e+00

Pos logit contributions
race+1.401
hibited+0.923
uning+0.868
strate+0.857
ilaterally+0.854
Neg logit contributions
orthy-1.357
Years-1.194
terday-1.189
oppy-1.153
ounters-1.132
Token and
Token ID290
Feature activation-4.80e-01

Pos logit contributions
orthy+3.284
Years+2.855
terday+2.803
oppy+2.745
ounters+2.705
Neg logit contributions
race-4.104
hibited-2.858
uning-2.689
strate-2.651
ilaterally-2.651
Token culture
Token ID3968
Feature activation-1.13e+00

Pos logit contributions
race+0.472
hibited+0.324
uning+0.307
ilaterally+0.305
strate+0.305
Neg logit contributions
orthy-0.382
Years-0.331
terday-0.327
oppy-0.322
ounters-0.315
Tokenk
Token ID74
Feature activation+6.70e+00

Pos logit contributions
orthy+3.610
Years+3.206
terday+3.163
oppy+3.126
onder+3.065
Neg logit contributions
race-3.299
hibited-2.149
strate-2.010
ilaterally-1.962
 Offensive-1.955
Tokenong
Token ID506
Feature activation+3.05e+00

Pos logit contributions
orthy+4.698
Years+4.002
oppy+3.942
onder+3.883
ounters+3.800
Neg logit contributions
race-6.760
hibited-4.970
strate-4.698
ilaterally-4.688
 Offensive-4.618
Token/
Token ID14
Feature activation+8.51e-01

Pos logit contributions
orthy+2.246
Years+1.933
terday+1.932
oppy+1.855
ounters+1.823
Neg logit contributions
race-3.125
hibited-2.210
uning-2.091
strate-2.075
ilaterally-2.074
Tokena
Token ID64
Feature activation+4.62e+00

Pos logit contributions
orthy+0.671
Years+0.583
terday+0.575
oppy+0.563
ounters+0.553
Neg logit contributions
race-0.848
hibited-0.585
uning-0.554
ilaterally-0.549
strate-0.547
Token-
Token ID12
Feature activation+3.19e+00

Pos logit contributions
orthy+3.781
Years+3.289
terday+3.277
oppy+3.153
ounters+3.110
Neg logit contributions
race-4.401
hibited-2.979
uning-2.818
ilaterally-2.784
strate-2.782
Tokenflex
Token ID32880
Feature activation+1.34e+01

Pos logit contributions
orthy+2.711
Years+2.387
terday+2.346
oppy+2.299
ounters+2.262
Neg logit contributions
race-2.937
hibited-1.981
uning-1.858
ilaterally-1.840
strate-1.833
Tokenible
Token ID856
Feature activation+8.72e+00

Pos logit contributions
orthy+9.547
Years+8.191
oppy+7.963
terday+7.884
ounters+7.806
Neg logit contributions
race-11.772
hibited-8.184
 Offensive-7.968
strate-7.938
gdala-7.827
Token-
Token ID12
Feature activation+4.83e+00

Pos logit contributions
orthy+6.539
Years+5.655
terday+5.516
oppy+5.354
ounters+5.260
Neg logit contributions
race-8.274
hibited-5.763
strate-5.466
ilaterally-5.429
uning-5.384
Tokenlimit
Token ID32374
Feature activation+5.17e+00

Pos logit contributions
orthy+4.303
Years+3.814
terday+3.717
oppy+3.664
ounters+3.625
Neg logit contributions
race-4.112
hibited-2.716
uning-2.501
strate-2.495
ilaterally-2.495
Token-
Token ID12
Feature activation+7.19e-01

Pos logit contributions
orthy+4.198
Years+3.671
terday+3.635
oppy+3.515
ounters+3.512
Neg logit contributions
race-4.821
hibited-3.296
strate-3.076
uning-3.070
ilaterally-3.061
Tokentr
Token ID2213
Feature activation-1.33e+00

Pos logit contributions
orthy+0.594
Years+0.520
terday+0.512
oppy+0.502
ounters+0.494
Neg logit contributions
race-0.686
hibited-0.467
uning-0.439
ilaterally-0.435
strate-0.434
Tokenvette
Token ID33573
Feature activation+9.46e+00

Pos logit contributions
orthy+2.116
Years+1.866
terday+1.841
oppy+1.806
ounters+1.778
Neg logit contributions
race-2.191
hibited-1.452
uning-1.359
ilaterally-1.346
strate-1.343
Tokenforum
Token ID27302
Feature activation+7.06e+00

Pos logit contributions
orthy+8.063
terday+7.098
Years+7.094
onder+6.940
ounters+6.937
Neg logit contributions
race-7.816
hibited-5.205
ilaterally-4.957
 Offensive-4.918
COR-4.790
Token.
Token ID13
Feature activation+5.48e+00

Pos logit contributions
orthy+5.223
Years+4.457
ounters+4.436
oppy+4.399
onder+4.326
Neg logit contributions
race-6.767
hibited-4.806
 Offensive-4.560
ilaterally-4.525
COR-4.520
Tokencom
Token ID785
Feature activation+8.05e+00

Pos logit contributions
orthy+5.053
Years+4.509
oppy+4.431
terday+4.400
ounters+4.360
Neg logit contributions
race-4.425
hibited-2.839
ilaterally-2.650
uning-2.634
strate-2.612
Token/
Token ID14
Feature activation+4.69e+00

Pos logit contributions
orthy+4.947
Years+4.252
terday+4.183
oppy+4.097
ounters+4.035
Neg logit contributions
race-8.561
hibited-6.226
ilaterally-6.071
uning-6.042
COR-5.921
Tokenforums
Token ID37141
Feature activation+1.33e+01

Pos logit contributions
orthy+3.738
Years+3.290
terday+3.200
oppy+3.173
ounters+3.119
Neg logit contributions
race-4.428
hibited-3.077
ilaterally-2.905
uning-2.890
strate-2.871
Token...
Token ID986
Feature activation+3.62e+00

Pos logit contributions
orthy+6.986
Years+6.325
terday+5.863
onder+5.776
ounters+5.739
Neg logit contributions
race-14.078
ilaterally-10.516
hibited-10.376
uning-10.179
 Offensive-10.033
Tokenwith
Token ID4480
Feature activation+6.93e+00

Pos logit contributions
orthy+3.092
Years+2.723
terday+2.678
oppy+2.634
ounters+2.596
Neg logit contributions
race-3.284
hibited-2.211
uning-2.067
ilaterally-2.064
strate-2.037
Token-
Token ID12
Feature activation+6.64e+00

Pos logit contributions
orthy+5.569
Years+4.961
terday+4.854
oppy+4.693
ounters+4.687
Neg logit contributions
race-6.347
hibited-4.309
ilaterally-4.160
uning-4.038
 Offensive-4.021
Tokenp
Token ID79
Feature activation+1.16e+01

Pos logit contributions
orthy+5.869
Years+5.237
terday+5.121
oppy+5.085
ounters+5.020
Neg logit contributions
race-5.510
hibited-3.653
ilaterally-3.414
uning-3.344
 Offensive-3.339
Tokenics
Token ID873
Feature activation+8.42e+00

Pos logit contributions
orthy+9.299
oppy+8.125
Years+8.103
onder+8.068
terday+7.990
Neg logit contributions
race-10.192
hibited-6.997
 Offensive-6.563
gdala-6.546
strate-6.498
Token Bac
Token ID35583
Feature activation-5.81e-01

Pos logit contributions
race+2.859
hibited+1.947
inary+1.815
uning+1.812
ilaterally+1.809
Neg logit contributions
orthy-2.412
Years-2.088
terday-2.048
oppy-2.029
ounters-1.985
Tokenile
Token ID576
Feature activation-4.40e+00

Pos logit contributions
race+0.588
hibited+0.410
uning+0.388
ilaterally+0.385
strate+0.384
Neg logit contributions
orthy-0.447
Years-0.387
terday-0.381
oppy-0.373
ounters-0.366
Token indirectly
Token ID20762
Feature activation+1.72e+00

Pos logit contributions
race+3.831
hibited+2.534
uning+2.313
 Offensive+2.300
ilaterally+2.298
Neg logit contributions
orthy-3.895
Years-3.470
terday-3.400
oppy-3.380
ounters-3.256
Token and
Token ID290
Feature activation-2.28e+00

Pos logit contributions
orthy+1.463
Years+1.285
terday+1.267
oppy+1.242
ounters+1.222
Neg logit contributions
race-1.600
hibited-1.075
uning-1.009
ilaterally-0.999
strate-0.998
Token inadvertently
Token ID29243
Feature activation+2.21e+00

Pos logit contributions
race+1.948
hibited+1.243
ilaterally+1.172
uning+1.141
strate+1.129
Neg logit contributions
orthy-2.099
Years-1.872
terday-1.837
oppy-1.828
ounters-1.789
Token infl
Token ID28472
Feature activation+1.32e+01

Pos logit contributions
orthy+1.867
Years+1.637
terday+1.618
oppy+1.582
ounters+1.562
Neg logit contributions
race-2.060
hibited-1.384
uning-1.304
strate-1.293
ilaterally-1.288
Tokenamed
Token ID2434
Feature activation+4.44e+00

Pos logit contributions
orthy+10.328
ounters+9.086
oppy+8.879
Years+8.836
onder+8.565
Neg logit contributions
race-11.298
COR-8.117
 Offensive-7.611
strate-7.498
 Procedure-7.467
Token people
Token ID661
Feature activation+1.18e-02

Pos logit contributions
orthy+3.494
Years+3.042
terday+2.989
oppy+2.941
ounters+2.879
Neg logit contributions
race-4.334
hibited-3.003
uning-2.845
ilaterally-2.843
strate-2.825
Token half
Token ID2063
Feature activation-5.28e+00

Pos logit contributions
orthy+0.010
Years+0.009
terday+0.009
oppy+0.008
ounters+0.008
Neg logit contributions
race-0.011
hibited-0.007
uning-0.007
ilaterally-0.007
strate-0.007
Token a
Token ID257
Feature activation-3.71e+00

Pos logit contributions
race+4.784
hibited+3.181
strate+3.002
uning+2.972
ilaterally+2.927
Neg logit contributions
orthy-4.545
Years-3.933
oppy-3.932
terday-3.886
ounters-3.810
Token world
Token ID995
Feature activation-5.32e+00

Pos logit contributions
race+3.620
hibited+2.474
uning+2.330
strate+2.315
ilaterally+2.271
Neg logit contributions
orthy-3.007
Years-2.566
terday-2.557
oppy-2.543
ounters-2.474
Token it
Token ID340
Feature activation+6.45e-01

Pos logit contributions
race+3.096
hibited+2.029
uning+1.952
inary+1.916
ilaterally+1.902
Neg logit contributions
orthy-2.792
Years-2.463
terday-2.410
oppy-2.379
ounters-2.325
Token,
Token ID11
Feature activation+9.41e-01

Pos logit contributions
orthy+0.574
Years+0.508
terday+0.500
oppy+0.491
ounters+0.484
Neg logit contributions
race-0.576
hibited-0.377
uning-0.353
ilaterally-0.349
strate-0.349
Token I
Token ID314
Feature activation-3.35e+00

Pos logit contributions
orthy+0.759
Years+0.661
terday+0.649
oppy+0.635
ounters+0.624
Neg logit contributions
race-0.923
hibited-0.629
uning-0.598
ilaterally-0.589
strate-0.588
Token call
Token ID869
Feature activation-1.84e+00

Pos logit contributions
race+2.948
hibited+1.920
uning+1.797
strate+1.775
ilaterally+1.767
Neg logit contributions
orthy-2.978
Years-2.666
terday-2.601
oppy-2.534
ounters-2.493
Token these
Token ID777
Feature activation+2.33e+00

Pos logit contributions
race+1.718
hibited+1.140
uning+1.095
inary+1.075
ilaterally+1.068
Neg logit contributions
orthy-1.558
Years-1.367
terday-1.335
oppy-1.307
ounters-1.285
Token instances
Token ID10245
Feature activation+1.31e+01

Pos logit contributions
orthy+1.754
Years+1.511
terday+1.488
oppy+1.456
ounters+1.431
Neg logit contributions
race-2.397
hibited-1.689
uning-1.594
ilaterally-1.585
strate-1.583
Token "
Token ID366
Feature activation+1.73e+00

Pos logit contributions
orthy+8.484
oppy+7.173
terday+7.172
Years+7.080
ounters+7.069
Neg logit contributions
race-12.799
hibited-9.562
strate-9.001
ilaterally-8.882
uning-8.624
TokenP
Token ID47
Feature activation+2.18e+00

Pos logit contributions
orthy+1.420
Years+1.244
terday+1.222
oppy+1.201
ounters+1.180
Neg logit contributions
race-1.661
hibited-1.136
uning-1.066
ilaterally-1.060
strate-1.057
TokenV
Token ID53
Feature activation-7.50e-01

Pos logit contributions
orthy+1.657
Years+1.430
terday+1.404
oppy+1.380
ounters+1.351
Neg logit contributions
race-2.232
hibited-1.567
uning-1.479
ilaterally-1.469
strate-1.469
TokenH
Token ID39
Feature activation-6.81e-01

Pos logit contributions
race+0.696
hibited+0.466
uning+0.439
ilaterally+0.434
strate+0.433
Neg logit contributions
orthy-0.640
Years-0.562
terday-0.555
oppy-0.543
ounters-0.534
TokenVM
Token ID15996
Feature activation-8.53e-01

Pos logit contributions
race+0.601
hibited+0.392
uning+0.367
ilaterally+0.362
strate+0.362
Neg logit contributions
orthy-0.613
Years-0.543
terday-0.537
oppy-0.525
ounters-0.517
Token
Token ID198
Feature activation-4.47e+00

Pos logit contributions
race+4.289
hibited+2.988
uning+2.820
strate+2.783
inary+2.778
Neg logit contributions
orthy-3.296
Years-2.840
terday-2.832
oppy-2.758
ounters-2.712
Token
Token ID198
Feature activation-3.54e+00

Pos logit contributions
race+4.226
hibited+2.821
COR+2.646
uning+2.633
strate+2.604
Neg logit contributions
orthy-3.742
terday-3.270
oppy-3.180
Years-3.133
ounters-3.079
TokenMichael
Token ID13256
Feature activation-2.85e+00

Pos logit contributions
race+3.462
hibited+2.344
COR+2.247
uning+2.195
strate+2.178
Neg logit contributions
orthy-2.874
terday-2.489
oppy-2.421
ounters-2.401
Years-2.384
Token G
Token ID402
Feature activation+5.50e+00

Pos logit contributions
race+2.929
hibited+2.063
uning+1.967
strate+1.933
inary+1.918
Neg logit contributions
orthy-2.113
Years-1.855
terday-1.794
oppy-1.770
ounters-1.732
Token.
Token ID13
Feature activation+1.19e+00

Pos logit contributions
orthy+4.502
Years+3.914
terday+3.813
oppy+3.791
ounters+3.739
Neg logit contributions
race-5.246
hibited-3.594
uning-3.385
strate-3.350
ilaterally-3.346
Token Flynn
Token ID14654
Feature activation+1.31e+01

Pos logit contributions
orthy+0.890
Years+0.767
terday+0.754
oppy+0.737
ounters+0.723
Neg logit contributions
race-1.240
hibited-0.874
uning-0.829
strate-0.821
ilaterally-0.820
Token and
Token ID290
Feature activation+3.60e+00

Pos logit contributions
orthy+9.061
Years+7.905
terday+7.572
ounters+7.483
onder+7.297
Neg logit contributions
race-12.889
hibited-9.067
ilaterally-8.603
uning-8.518
strate-8.344
Token his
Token ID465
Feature activation-2.36e+00

Pos logit contributions
orthy+2.618
Years+2.247
terday+2.211
oppy+2.153
ounters+2.115
Neg logit contributions
race-3.790
hibited-2.693
uning-2.554
ilaterally-2.535
strate-2.531
Token wife
Token ID3656
Feature activation-4.24e+00

Pos logit contributions
race+2.372
hibited+1.639
uning+1.557
strate+1.551
ilaterally+1.536
Neg logit contributions
orthy-1.826
Years-1.563
terday-1.549
oppy-1.528
ounters-1.489
Token,
Token ID11
Feature activation-1.28e-01

Pos logit contributions
race+3.943
hibited+2.618
ilaterally+2.487
strate+2.480
uning+2.480
Neg logit contributions
orthy-3.556
Years-3.134
oppy-3.023
terday-3.008
ounters-2.949
Token Jen
Token ID13364
Feature activation-3.98e+00

Pos logit contributions
race+0.126
hibited+0.086
uning+0.082
ilaterally+0.081
strate+0.081
Neg logit contributions
orthy-0.103
Years-0.089
terday-0.088
oppy-0.086
ounters-0.085
Token tapes
Token ID23695
Feature activation-2.67e+00

Pos logit contributions
race+3.028
hibited+2.075
uning+1.941
 Offensive+1.917
inary+1.905
Neg logit contributions
orthy-2.543
terday-2.201
Years-2.182
oppy-2.145
ounters-2.104
Token,
Token ID11
Feature activation-2.76e+00

Pos logit contributions
race+2.586
hibited+1.792
uning+1.682
ilaterally+1.648
strate+1.626
Neg logit contributions
orthy-2.156
Years-1.878
terday-1.831
oppy-1.814
ounters-1.769
Token clothes
Token ID8242
Feature activation-6.81e+00

Pos logit contributions
race+2.661
hibited+1.840
uning+1.722
ilaterally+1.706
inary+1.686
Neg logit contributions
orthy-2.250
Years-1.931
terday-1.916
oppy-1.858
ounters-1.846
Token,
Token ID11
Feature activation-1.72e+00

Pos logit contributions
race+5.901
hibited+3.847
uning+3.623
ilaterally+3.610
inary+3.468
Neg logit contributions
orthy-5.925
Years-5.278
terday-5.198
oppy-5.142
onder-5.046
Token and
Token ID290
Feature activation-3.09e+00

Pos logit contributions
race+1.670
hibited+1.142
uning+1.079
strate+1.060
ilaterally+1.059
Neg logit contributions
orthy-1.398
Years-1.213
terday-1.201
oppy-1.160
ounters-1.154
Token jewelry
Token ID22634
Feature activation-1.55e+01

Pos logit contributions
race+3.020
hibited+2.082
uning+1.954
inary+1.928
strate+1.922
Neg logit contributions
orthy-2.483
Years-2.136
terday-2.107
oppy-2.045
ounters-2.041
Token,
Token ID11
Feature activation-4.18e+00

Pos logit contributions
race+11.576
 religiously+7.587
hibited+7.488
lessly+7.060
uning+6.988
Neg logit contributions
orthy-13.083
oppy-11.527
Years-11.187
onder-11.165
terday-11.145
Token burned
Token ID11544
Feature activation+1.32e+00

Pos logit contributions
race+3.811
hibited+2.593
uning+2.405
ilaterally+2.370
inary+2.351
Neg logit contributions
orthy-3.561
terday-3.097
Years-3.074
oppy-3.011
ounters-2.967
Token posters
Token ID19379
Feature activation+4.75e-01

Pos logit contributions
orthy+1.057
Years+0.920
terday+0.907
oppy+0.886
ounters+0.870
Neg logit contributions
race-1.303
hibited-0.898
uning-0.847
strate-0.839
ilaterally-0.839
Token,
Token ID11
Feature activation-3.58e+00

Pos logit contributions
orthy+0.389
Years+0.340
terday+0.335
oppy+0.328
ounters+0.323
Neg logit contributions
race-0.457
hibited-0.312
uning-0.294
ilaterally-0.291
strate-0.290
Token read
Token ID1100
Feature activation-1.61e+00

Pos logit contributions
race+3.201
hibited+2.151
uning+1.971
ilaterally+1.970
strate+1.935
Neg logit contributions
orthy-3.150
Years-2.761
terday-2.728
oppy-2.662
onder-2.643
Token vs
Token ID3691
Feature activation+1.92e-01

Pos logit contributions
race+2.746
hibited+1.918
uning+1.813
strate+1.811
ilaterally+1.796
Neg logit contributions
orthy-2.028
Years-1.756
terday-1.737
oppy-1.685
ounters-1.631
Token Pyro
Token ID44954
Feature activation+1.93e+00

Pos logit contributions
orthy+0.150
Years+0.130
terday+0.128
oppy+0.125
ounters+0.123
Neg logit contributions
race-0.192
hibited-0.134
uning-0.126
strate-0.125
ilaterally-0.125
Tokenblast
Token ID39806
Feature activation-2.27e+00

Pos logit contributions
orthy+1.809
Years+1.605
terday+1.581
oppy+1.558
ounters+1.539
Neg logit contributions
race-1.625
hibited-1.031
uning-0.970
ilaterally-0.953
strate-0.942
Token
Token ID198
Feature activation+7.96e-01

Pos logit contributions
race+2.295
hibited+1.597
uning+1.507
strate+1.498
ilaterally+1.496
Neg logit contributions
orthy-1.747
Years-1.521
terday-1.497
oppy-1.461
ounters-1.423
Token
Token ID198
Feature activation+4.41e-01

Pos logit contributions
orthy+0.579
Years+0.500
terday+0.488
oppy+0.477
ounters+0.469
Neg logit contributions
race-0.836
hibited-0.595
uning-0.564
ilaterally-0.562
strate-0.559
TokenPrim
Token ID23828
Feature activation-1.55e+01

Pos logit contributions
orthy+0.354
Years+0.306
terday+0.304
oppy+0.297
ounters+0.291
Neg logit contributions
race-0.434
hibited-0.298
uning-0.280
strate-0.278
ilaterally-0.278
Tokenal
Token ID282
Feature activation-4.50e+00

Pos logit contributions
race+11.431
hibited+7.100
inary+6.889
strate+6.406
uning+6.204
Neg logit contributions
orthy-13.515
terday-12.568
Years-12.526
oppy-11.946
ounters-11.719
Token Druid
Token ID32685
Feature activation-7.25e-02

Pos logit contributions
race+4.585
hibited+3.232
strate+3.048
uning+3.019
 Offensive+2.996
Neg logit contributions
orthy-3.403
Years-2.933
terday-2.917
oppy-2.879
ounters-2.728
Token vs
Token ID3691
Feature activation-1.26e-01

Pos logit contributions
race+0.075
hibited+0.052
uning+0.050
strate+0.049
ilaterally+0.049
Neg logit contributions
orthy-0.055
Years-0.047
terday-0.047
oppy-0.046
ounters-0.044
Token Er
Token ID5256
Feature activation-6.81e-02

Pos logit contributions
race+0.124
hibited+0.085
uning+0.080
strate+0.079
ilaterally+0.079
Neg logit contributions
orthy-0.102
Years-0.088
terday-0.087
oppy-0.085
ounters-0.084
Tokent
Token ID83
Feature activation+1.57e-01

Pos logit contributions
race+0.065
hibited+0.044
uning+0.042
strate+0.041
ilaterally+0.041
Neg logit contributions
orthy-0.057
Years-0.050
terday-0.049
oppy-0.048
ounters-0.047
Token Sam
Token ID3409
Feature activation-1.25e+01

Pos logit contributions
race+1.264
hibited+0.880
uning+0.829
ilaterally+0.824
strate+0.821
Neg logit contributions
orthy-0.965
Years-0.836
terday-0.825
oppy-0.809
ounters-0.796
Token P
Token ID350
Feature activation+5.17e+00

Pos logit contributions
race+12.116
hibited+8.378
strate+8.087
uning+8.010
inary+7.998
Neg logit contributions
orthy-8.466
terday-7.305
Years-7.299
oppy-7.203
ounters-6.910
Tokenanche
Token ID6362
Feature activation+5.80e+00

Pos logit contributions
orthy+4.346
Years+3.754
oppy+3.685
onder+3.672
terday+3.654
Neg logit contributions
race-4.794
hibited-3.228
uning-3.012
ilaterally-2.993
strate-2.984
Tokenvre
Token ID43933
Feature activation+2.14e+00

Pos logit contributions
orthy+4.800
Years+4.129
terday+4.072
ounters+4.042
oppy+4.001
Neg logit contributions
race-5.391
hibited-3.734
ilaterally-3.475
inary-3.433
uning-3.429
Token (
Token ID357
Feature activation-8.21e-01

Pos logit contributions
orthy+1.750
Years+1.513
terday+1.489
oppy+1.457
ounters+1.443
Neg logit contributions
race-2.066
hibited-1.422
uning-1.334
ilaterally-1.327
strate-1.319
TokenSam
Token ID16305
Feature activation-1.54e+01

Pos logit contributions
race+0.776
hibited+0.519
uning+0.486
strate+0.482
ilaterally+0.482
Neg logit contributions
orthy-0.695
Years-0.603
terday-0.602
oppy-0.589
ounters-0.581
Token
Token ID447
Feature activation-4.94e+00

Pos logit contributions
race+14.092
hibited+9.636
inary+9.241
strate+9.233
COR+9.057
Neg logit contributions
orthy-10.704
Years-9.241
terday-9.015
oppy-8.940
ounters-8.724
Token
Token ID247
Feature activation-2.94e+00

Pos logit contributions
race+2.739
hibited+1.196
uning+1.070
ilaterally+1.050
strate+1.013
Neg logit contributions
orthy-5.995
Years-5.492
terday-5.430
oppy-5.352
ounters-5.289
Tokens
Token ID82
Feature activation-6.05e+00

Pos logit contributions
race+2.579
hibited+1.670
uning+1.555
strate+1.555
ilaterally+1.537
Neg logit contributions
orthy-2.663
Years-2.350
terday-2.324
oppy-2.280
ounters-2.244
Token Burger
Token ID28983
Feature activation-3.18e+00

Pos logit contributions
race+5.753
hibited+3.879
inary+3.669
 Offensive+3.657
uning+3.655
Neg logit contributions
orthy-4.887
Years-4.243
terday-4.090
oppy-4.025
ounters-4.004
Token Joint
Token ID16798
Feature activation-7.04e+00

Pos logit contributions
race+3.284
hibited+2.306
uning+2.183
ilaterally+2.174
strate+2.169
Neg logit contributions
orthy-2.376
Years-2.046
terday-2.019
oppy-1.960
ounters-1.917
Token @
Token ID2488
Feature activation-5.31e+00

Pos logit contributions
race+4.175
hibited+2.517
uning+2.345
ilaterally+2.309
 Offensive+2.272
Neg logit contributions
orthy-5.418
Years-4.880
terday-4.837
oppy-4.751
ounters-4.624
Token 144
Token ID20224
Feature activation+1.41e+00

Pos logit contributions
race+5.351
hibited+3.727
uning+3.531
strate+3.495
ilaterally+3.471
Neg logit contributions
orthy-3.983
Years-3.498
terday-3.479
oppy-3.347
onder-3.245
TokenHz
Token ID7399
Feature activation-8.92e-01

Pos logit contributions
orthy+1.048
Years+0.905
terday+0.886
oppy+0.867
ounters+0.853
Neg logit contributions
race-1.459
hibited-1.029
uning-0.975
ilaterally-0.969
strate-0.966
Token (
Token ID357
Feature activation+1.42e+00

Pos logit contributions
race+0.887
hibited+0.614
uning+0.581
ilaterally+0.575
strate+0.574
Neg logit contributions
orthy-0.702
Years-0.610
terday-0.602
oppy-0.588
ounters-0.577
TokenTr
Token ID2898
Feature activation-6.43e+00

Pos logit contributions
orthy+0.897
Years+0.750
terday+0.734
oppy+0.714
ounters+0.698
Neg logit contributions
race-1.640
hibited-1.205
uning-1.151
ilaterally-1.143
strate-1.141
Tokenace
Token ID558
Feature activation-1.53e+01

Pos logit contributions
race+3.260
hibited+0.989
uning+0.914
strate+0.805
acqu+0.746
Neg logit contributions
orthy-8.316
terday-7.754
Years-7.694
oppy-7.404
 imag-7.340
Token Free
Token ID3232
Feature activation+2.41e-01

Pos logit contributions
race+8.434
 Offensive+4.424
hibited+4.384
lessly+3.720
 Tradable+3.717
Neg logit contributions
orthy-16.102
terday-15.492
oppy-14.672
Years-14.377
ounters-14.204
Token =
Token ID796
Feature activation-2.86e+00

Pos logit contributions
orthy+0.185
Years+0.159
terday+0.158
oppy+0.154
ounters+0.151
Neg logit contributions
race-0.245
hibited-0.171
uning-0.162
strate-0.160
ilaterally-0.160
Token 80
Token ID4019
Feature activation-1.47e-02

Pos logit contributions
race+3.051
hibited+2.178
uning+2.069
strate+2.048
ilaterally+2.045
Neg logit contributions
orthy-2.034
Years-1.750
terday-1.726
oppy-1.671
ounters-1.619
Token)
Token ID8
Feature activation-2.33e-01

Pos logit contributions
race+0.012
hibited+0.008
uning+0.007
ilaterally+0.007
strate+0.007
Neg logit contributions
orthy-0.014
Years-0.012
terday-0.012
oppy-0.012
ounters-0.012
Token
Token ID198
Feature activation+2.20e-01

Pos logit contributions
race+0.233
hibited+0.162
uning+0.153
ilaterally+0.151
strate+0.151
Neg logit contributions
orthy-0.182
Years-0.157
terday-0.155
oppy-0.152
ounters-0.149
Token Anders
Token ID25519
Feature activation-1.62e+00

Pos logit contributions
race+2.238
hibited+1.500
uning+1.431
strate+1.412
ilaterally+1.400
Neg logit contributions
orthy-1.931
Years-1.677
terday-1.635
oppy-1.622
ounters-1.589
Token takes
Token ID2753
Feature activation-5.75e+00

Pos logit contributions
race+1.516
hibited+1.017
uning+0.972
ilaterally+0.951
strate+0.943
Neg logit contributions
orthy-1.365
Years-1.200
terday-1.168
oppy-1.153
ounters-1.125
Token me
Token ID502
Feature activation-2.03e+00

Pos logit contributions
race+5.480
hibited+3.679
uning+3.477
strate+3.430
ilaterally+3.426
Neg logit contributions
orthy-4.677
Years-4.019
terday-3.924
oppy-3.902
ounters-3.828
Token on
Token ID319
Feature activation-4.66e+00

Pos logit contributions
race+2.019
hibited+1.391
uning+1.321
ilaterally+1.309
strate+1.305
Neg logit contributions
orthy-1.595
Years-1.393
terday-1.348
oppy-1.330
ounters-1.307
Token a
Token ID257
Feature activation-2.93e+00

Pos logit contributions
race+4.292
hibited+2.818
strate+2.699
uning+2.696
ilaterally+2.667
Neg logit contributions
orthy-3.928
Years-3.466
terday-3.396
oppy-3.338
ounters-3.323
Token det
Token ID1062
Feature activation-1.51e+01

Pos logit contributions
race+2.733
hibited+1.821
uning+1.741
strate+1.704
ilaterally+1.692
Neg logit contributions
orthy-2.474
Years-2.171
terday-2.113
oppy-2.092
ounters-2.061
Tokenour
Token ID454
Feature activation-6.66e+00

Pos logit contributions
race+7.586
uning+2.825
hibited+2.013
acqu+1.939
strate+1.779
Neg logit contributions
orthy-17.570
terday-17.389
Years-17.082
oppy-16.241
 imag-15.930
Token into
Token ID656
Feature activation-2.06e+00

Pos logit contributions
race+6.150
hibited+4.000
uning+3.823
ilaterally+3.741
strate+3.649
Neg logit contributions
orthy-5.562
Years-4.961
oppy-4.732
terday-4.707
ounters-4.669
Token the
Token ID262
Feature activation+2.13e-01

Pos logit contributions
race+2.060
hibited+1.434
uning+1.353
strate+1.339
ilaterally+1.334
Neg logit contributions
orthy-1.606
Years-1.390
terday-1.365
oppy-1.339
ounters-1.324
Token brewery
Token ID22120
Feature activation+5.15e-01

Pos logit contributions
orthy+0.173
Years+0.151
terday+0.149
oppy+0.146
ounters+0.144
Neg logit contributions
race-0.207
hibited-0.142
uning-0.134
strate-0.132
ilaterally-0.132
Token to
Token ID284
Feature activation-1.55e+00

Pos logit contributions
orthy+0.434
Years+0.381
terday+0.376
oppy+0.369
ounters+0.362
Neg logit contributions
race-0.484
hibited-0.325
uning-0.307
strate-0.303
ilaterally-0.302
Token for
Token ID329
Feature activation-6.85e+00

Pos logit contributions
race+6.680
hibited+4.530
ilaterally+4.147
strate+4.144
uning+4.122
Neg logit contributions
orthy-6.163
Years-5.411
terday-5.339
oppy-5.285
ounters-5.074
Token the
Token ID262
Feature activation-3.09e+00

Pos logit contributions
race+6.205
hibited+4.218
inary+3.947
strate+3.936
uning+3.913
Neg logit contributions
orthy-5.677
Years-4.970
terday-4.927
oppy-4.829
ounters-4.729
Token purpose
Token ID4007
Feature activation-4.32e+00

Pos logit contributions
race+2.973
hibited+2.041
uning+1.908
strate+1.882
ilaterally+1.878
Neg logit contributions
orthy-2.510
Years-2.196
terday-2.133
oppy-2.088
ounters-2.046
Token of
Token ID286
Feature activation-3.00e+00

Pos logit contributions
race+4.539
hibited+3.222
uning+3.043
strate+3.017
ilaterally+3.011
Neg logit contributions
orthy-3.141
Years-2.698
terday-2.634
oppy-2.586
ounters-2.530
Token stealing
Token ID16568
Feature activation-5.92e+00

Pos logit contributions
race+2.756
hibited+1.840
uning+1.720
ilaterally+1.707
strate+1.694
Neg logit contributions
orthy-2.583
Years-2.269
terday-2.221
oppy-2.206
ounters-2.153
Token jewelry
Token ID22634
Feature activation-1.51e+01

Pos logit contributions
race+5.452
hibited+3.652
strate+3.408
inary+3.405
uning+3.405
Neg logit contributions
orthy-4.915
Years-4.293
terday-4.247
oppy-4.162
ounters-4.087
Token or
Token ID393
Feature activation-6.03e+00

Pos logit contributions
race+12.486
hibited+8.481
ilaterally+8.109
uning+7.984
inary+7.815
Neg logit contributions
orthy-11.230
oppy-10.250
Years-10.112
terday-9.669
onder-9.467
Token money
Token ID1637
Feature activation-8.40e+00

Pos logit contributions
race+5.685
hibited+3.883
uning+3.653
strate+3.628
inary+3.610
Neg logit contributions
orthy-4.822
Years-4.204
terday-4.185
oppy-4.137
ounters-4.009
Token,"
Token ID553
Feature activation+1.60e+00

Pos logit contributions
race+7.363
hibited+4.955
ilaterally+4.554
uning+4.529
strate+4.498
Neg logit contributions
orthy-6.949
Years-6.277
oppy-6.185
terday-6.105
onder-5.857
Token the
Token ID262
Feature activation-1.56e-02

Pos logit contributions
orthy+1.220
Years+1.055
terday+1.038
oppy+1.015
ounters+0.996
Neg logit contributions
race-1.631
hibited-1.141
uning-1.080
ilaterally-1.071
strate-1.069
Token email
Token ID3053
Feature activation+6.35e-02

Pos logit contributions
race+0.017
hibited+0.012
uning+0.012
ilaterally+0.012
strate+0.012
Neg logit contributions
orthy-0.011
Years-0.009
terday-0.009
oppy-0.009
ounters-0.008
Token @
Token ID2488
Feature activation-5.26e+00

Pos logit contributions
race+3.411
hibited+2.025
uning+1.870
 Offensive+1.862
COR+1.846
Neg logit contributions
orthy-4.535
terday-4.053
Years-4.035
oppy-3.989
ounters-3.855
Token 144
Token ID20224
Feature activation+1.08e+00

Pos logit contributions
race+5.352
hibited+3.738
uning+3.551
strate+3.525
ilaterally+3.507
Neg logit contributions
orthy-3.900
Years-3.439
terday-3.410
oppy-3.272
onder-3.166
TokenHz
Token ID7399
Feature activation-1.07e+00

Pos logit contributions
orthy+0.803
Years+0.694
terday+0.679
oppy+0.665
ounters+0.654
Neg logit contributions
race-1.121
hibited-0.790
uning-0.749
ilaterally-0.745
strate-0.742
Token (
Token ID357
Feature activation+7.39e-01

Pos logit contributions
race+1.069
hibited+0.741
uning+0.701
ilaterally+0.694
strate+0.693
Neg logit contributions
orthy-0.838
Years-0.728
terday-0.718
oppy-0.702
ounters-0.689
TokenTr
Token ID2898
Feature activation-6.29e+00

Pos logit contributions
orthy+0.463
Years+0.386
terday+0.379
oppy+0.368
ounters+0.360
Neg logit contributions
race-0.854
hibited-0.628
uning-0.600
ilaterally-0.596
strate-0.595
Tokenace
Token ID558
Feature activation-1.49e+01

Pos logit contributions
race+3.178
hibited+0.974
uning+0.874
strate+0.801
inary+0.720
Neg logit contributions
orthy-8.141
terday-7.591
Years-7.537
oppy-7.262
 imag-7.185
Token Free
Token ID3232
Feature activation+7.51e-01

Pos logit contributions
race+8.254
 Offensive+4.292
hibited+4.266
 Tradable+3.661
lessly+3.596
Neg logit contributions
orthy-15.872
terday-15.126
oppy-14.380
Years-14.050
ounters-13.879
Token =
Token ID796
Feature activation-2.71e+00

Pos logit contributions
orthy+0.562
Years+0.485
terday+0.476
oppy+0.465
ounters+0.457
Neg logit contributions
race-0.775
hibited-0.545
uning-0.517
ilaterally-0.513
strate-0.512
Token 80
Token ID4019
Feature activation-3.66e-01

Pos logit contributions
race+2.947
hibited+2.121
uning+2.018
strate+2.000
ilaterally+1.998
Neg logit contributions
orthy-1.875
Years-1.602
terday-1.577
oppy-1.529
ounters-1.486
Token)
Token ID8
Feature activation-1.35e-01

Pos logit contributions
race+0.301
hibited+0.189
uning+0.175
strate+0.173
ilaterally+0.173
Neg logit contributions
orthy-0.351
Years-0.313
terday-0.309
oppy-0.304
ounters-0.299
Token
Token ID198
Feature activation+1.57e+00

Pos logit contributions
race+0.141
hibited+0.100
uning+0.094
ilaterally+0.094
strate+0.093
Neg logit contributions
orthy-0.100
Years-0.086
terday-0.085
oppy-0.083
ounters-0.081
Token meet
Token ID1826
Feature activation+2.13e+00

Pos logit contributions
race+0.273
hibited+0.194
uning+0.187
ilaterally+0.184
strate+0.184
Neg logit contributions
orthy-0.173
Years-0.148
terday-0.145
oppy-0.143
ounters-0.139
Token.
Token ID13
Feature activation+7.88e-01

Pos logit contributions
orthy+1.817
Years+1.599
terday+1.575
oppy+1.548
ounters+1.521
Neg logit contributions
race-1.971
hibited-1.318
uning-1.240
ilaterally-1.228
strate-1.224
Token
Token ID198
Feature activation-3.04e+00

Pos logit contributions
orthy+0.575
Years+0.494
terday+0.484
oppy+0.473
ounters+0.465
Neg logit contributions
race-0.828
hibited-0.588
uning-0.557
ilaterally-0.555
strate-0.555
Token
Token ID198
Feature activation-1.87e+00

Pos logit contributions
race+2.951
hibited+1.992
uning+1.875
strate+1.858
COR+1.840
Neg logit contributions
orthy-2.491
terday-2.161
Years-2.111
oppy-2.098
ounters-2.029
TokenM
Token ID44
Feature activation-2.52e+00

Pos logit contributions
race+1.754
hibited+1.161
COR+1.091
uning+1.089
inary+1.082
Neg logit contributions
orthy-1.606
terday-1.400
oppy-1.356
Years-1.344
ounters-1.342
Tokenort
Token ID419
Feature activation-1.47e+01

Pos logit contributions
race+2.346
hibited+1.548
uning+1.499
inary+1.470
ilaterally+1.446
Neg logit contributions
orthy-2.109
Years-1.878
terday-1.872
oppy-1.793
ounters-1.777
Tokeng
Token ID70
Feature activation+6.76e+00

Pos logit contributions
race+10.928
uning+6.795
hibited+6.299
strate+6.235
inary+6.211
Neg logit contributions
orthy-12.950
terday-11.746
Years-11.357
ounters-11.265
oppy-10.925
Tokenages
Token ID1095
Feature activation-4.21e+00

Pos logit contributions
orthy+3.902
Years+2.984
oppy+2.944
ounters+2.926
onder+2.817
Neg logit contributions
race-7.989
hibited-6.009
COR-5.748
ilaterally-5.736
uning-5.722
Token,
Token ID11
Feature activation-6.20e-01

Pos logit contributions
race+3.902
hibited+2.601
uning+2.488
ilaterally+2.414
inary+2.408
Neg logit contributions
orthy-3.484
Years-3.085
oppy-2.978
terday-2.965
ounters-2.913
Token rent
Token ID5602
Feature activation-3.99e+00

Pos logit contributions
race+0.616
hibited+0.420
uning+0.400
inary+0.396
ilaterally+0.396
Neg logit contributions
orthy-0.492
Years-0.428
terday-0.422
oppy-0.411
ounters-0.406
Token,
Token ID11
Feature activation+2.10e-01

Pos logit contributions
race+3.552
hibited+2.309
uning+2.267
inary+2.218
ilaterally+2.198
Neg logit contributions
orthy-3.451
Years-3.070
terday-3.036
oppy-2.968
onder-2.923
Token i
Token ID1312
Feature activation-4.44e+00

Pos logit contributions
race+0.405
hibited+0.275
uning+0.260
ilaterally+0.257
strate+0.257
Neg logit contributions
orthy-0.337
Years-0.294
terday-0.292
oppy-0.284
ounters-0.277
Token.
Token ID13
Feature activation-8.95e+00

Pos logit contributions
race+3.783
hibited+2.431
uning+2.278
strate+2.244
inary+2.210
Neg logit contributions
orthy-4.086
terday-3.585
Years-3.567
oppy-3.515
ounters-3.412
Tokene
Token ID68
Feature activation-2.71e+00

Pos logit contributions
race+4.945
hibited+2.171
uning+1.954
inary+1.766
strate+1.750
Neg logit contributions
orthy-10.721
terday-9.837
Years-9.524
oppy-9.485
ounters-9.356
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
race+2.088
hibited+1.253
uning+1.155
strate+1.133
ilaterally+1.129
Neg logit contributions
orthy-2.734
Years-2.465
terday-2.434
oppy-2.395
ounters-2.353
Token the
Token ID262
Feature activation-2.30e+00

Pos logit contributions
race+1.576
hibited+1.092
uning+1.022
strate+1.017
ilaterally+1.017
Neg logit contributions
orthy-1.226
Years-1.058
terday-1.052
oppy-1.022
ounters-0.991
Token prim
Token ID2684
Feature activation-1.46e+01

Pos logit contributions
race+2.346
hibited+1.661
uning+1.551
strate+1.542
ilaterally+1.527
Neg logit contributions
orthy-1.733
Years-1.505
terday-1.493
oppy-1.440
ounters-1.401
Tokenetime
Token ID8079
Feature activation-6.28e-01

Pos logit contributions
race+13.274
hibited+9.678
inary+8.836
strate+8.652
uning+8.650
Neg logit contributions
orthy-9.895
terday-8.710
Years-8.549
oppy-8.325
ounters-8.015
Token soap
Token ID19533
Feature activation-2.29e+00

Pos logit contributions
race+0.633
hibited+0.440
uning+0.416
strate+0.412
ilaterally+0.411
Neg logit contributions
orthy-0.487
Years-0.423
terday-0.418
oppy-0.407
ounters-0.395
Token or
Token ID393
Feature activation+7.91e-01

Pos logit contributions
race+2.125
hibited+1.426
uning+1.334
strate+1.308
inary+1.304
Neg logit contributions
orthy-1.957
Years-1.714
terday-1.713
oppy-1.665
ounters-1.605
Token the
Token ID262
Feature activation+1.51e+00

Pos logit contributions
orthy+0.603
Years+0.522
terday+0.513
oppy+0.501
ounters+0.488
Neg logit contributions
race-0.811
hibited-0.567
uning-0.534
strate-0.532
ilaterally-0.531
Token romantic
Token ID14348
Feature activation-3.41e-01

Pos logit contributions
orthy+1.160
Years+1.004
terday+0.989
oppy+0.965
ounters+0.946
Neg logit contributions
race-1.540
hibited-1.076
uning-1.016
ilaterally-1.008
strate-1.007
Tokenokingly
Token ID48343
Feature activation+2.63e+00

Pos logit contributions
race+7.826
acqu+4.430
uning+4.384
hibited+4.361
ilaterally+4.335
Neg logit contributions
orthy-10.359
Years-9.360
terday-9.276
oppy-9.100
ounters-8.901
Token.
Token ID13
Feature activation+1.18e+00

Pos logit contributions
orthy+2.136
Years+1.861
terday+1.841
oppy+1.787
ounters+1.772
Neg logit contributions
race-2.540
hibited-1.734
uning-1.636
strate-1.623
ilaterally-1.616
Token One
Token ID1881
Feature activation+6.31e+00

Pos logit contributions
orthy+1.056
Years+0.936
terday+0.921
oppy+0.904
ounters+0.890
Neg logit contributions
race-1.049
hibited-0.689
uning-0.644
ilaterally-0.638
strate-0.637
Token of
Token ID286
Feature activation+4.94e-01

Pos logit contributions
orthy+4.388
Years+3.783
terday+3.733
oppy+3.567
ounters+3.508
Neg logit contributions
race-6.674
hibited-4.799
strate-4.559
uning-4.545
ilaterally-4.534
Token the
Token ID262
Feature activation+8.30e-01

Pos logit contributions
orthy+0.379
Years+0.327
terday+0.322
oppy+0.316
ounters+0.310
Neg logit contributions
race-0.502
hibited-0.351
uning-0.332
ilaterally-0.329
strate-0.329
Token rare
Token ID4071
Feature activation-1.40e+01

Pos logit contributions
orthy+0.630
Years+0.541
terday+0.535
oppy+0.524
ounters+0.513
Neg logit contributions
race-0.850
hibited-0.597
uning-0.565
ilaterally-0.559
strate-0.557
Tokenst
Token ID301
Feature activation-7.25e+00

Pos logit contributions
race+13.289
hibited+9.399
inary+8.903
uning+8.761
COR+8.605
Neg logit contributions
orthy-9.542
terday-8.329
oppy-8.091
Years-8.053
orney-7.573
Token of
Token ID286
Feature activation-1.95e+00

Pos logit contributions
race+7.103
hibited+4.939
uning+4.606
inary+4.558
strate+4.540
Neg logit contributions
orthy-5.518
terday-4.751
Years-4.718
oppy-4.659
ounters-4.476
Token his
Token ID465
Feature activation-2.77e+00

Pos logit contributions
race+1.924
hibited+1.333
uning+1.245
strate+1.234
ilaterally+1.227
Neg logit contributions
orthy-1.558
Years-1.343
terday-1.341
oppy-1.304
ounters-1.273
Token Lead
Token ID20116
Feature activation-1.45e+00

Pos logit contributions
race+2.807
hibited+1.963
uning+1.839
ilaterally+1.819
strate+1.812
Neg logit contributions
orthy-2.106
terday-1.818
Years-1.818
oppy-1.771
ounters-1.716
Tokenb
Token ID65
Feature activation+1.34e+00

Pos logit contributions
race+1.136
hibited+0.690
uning+0.632
ilaterally+0.623
strate+0.623
Neg logit contributions
orthy-1.457
Years-1.304
terday-1.302
oppy-1.273
ounters-1.253
Tokenik
Token ID1134
Feature activation+4.57e+00

Pos logit contributions
race+0.646
hibited+0.437
uning+0.420
ilaterally+0.413
strate+0.410
Neg logit contributions
orthy-0.527
terday-0.465
Years-0.465
oppy-0.443
ounters-0.434
Tokenram
Token ID859
Feature activation-5.39e+00

Pos logit contributions
orthy+3.541
Years+3.079
terday+2.996
oppy+2.946
onder+2.931
Neg logit contributions
race-4.448
hibited-3.141
ilaterally-2.933
strate-2.920
uning-2.904
Token Bak
Token ID17466
Feature activation-1.04e+00

Pos logit contributions
race+5.356
hibited+3.659
uning+3.577
strate+3.438
 Offensive+3.429
Neg logit contributions
orthy-3.982
Years-3.588
terday-3.496
oppy-3.414
ounters-3.255
Tokenshi
Token ID44019
Feature activation+1.29e+00

Pos logit contributions
race+1.005
hibited+0.683
uning+0.646
strate+0.639
ilaterally+0.635
Neg logit contributions
orthy-0.852
Years-0.753
terday-0.746
oppy-0.722
ounters-0.709
Token,
Token ID11
Feature activation-2.18e+00

Pos logit contributions
orthy+1.052
Years+0.919
terday+0.906
oppy+0.887
ounters+0.872
Neg logit contributions
race-1.242
hibited-0.848
uning-0.799
ilaterally-0.792
strate-0.791
Token managing
Token ID11149
Feature activation-1.37e+01

Pos logit contributions
race+2.141
hibited+1.475
uning+1.394
ilaterally+1.390
strate+1.374
Neg logit contributions
orthy-1.728
Years-1.511
terday-1.476
oppy-1.462
ounters-1.435
Token director
Token ID3437
Feature activation-5.49e+00

Pos logit contributions
race+10.346
hibited+6.544
acqu+6.135
COR+6.053
inary+5.972
Neg logit contributions
orthy-11.838
Years-10.999
terday-10.858
oppy-10.344
ounters-10.225
Token of
Token ID286
Feature activation-7.26e+00

Pos logit contributions
race+5.248
hibited+3.576
uning+3.430
strate+3.358
ilaterally+3.345
Neg logit contributions
orthy-4.348
Years-3.877
oppy-3.709
terday-3.696
ounters-3.547
Token CPR
Token ID42920
Feature activation-5.38e+00

Pos logit contributions
race+7.060
hibited+4.914
uning+4.647
ilaterally+4.642
 Offensive+4.601
Neg logit contributions
orthy-5.489
Years-4.801
terday-4.682
oppy-4.630
ounters-4.466
TokenL
Token ID43
Feature activation-4.52e+00

Pos logit contributions
race+4.990
hibited+3.288
uning+3.161
COR+3.151
inary+3.136
Neg logit contributions
orthy-4.498
Years-3.940
terday-3.921
oppy-3.811
ounters-3.720
Token,
Token ID11
Feature activation-3.46e+00

Pos logit contributions
race+4.184
hibited+2.768
uning+2.685
inary+2.649
ilaterally+2.637
Neg logit contributions
orthy-3.783
Years-3.337
terday-3.268
oppy-3.217
ounters-3.129
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
race+1.353
hibited+0.939
uning+0.889
strate+0.880
ilaterally+0.872
Neg logit contributions
orthy-1.036
terday-0.887
Years-0.886
oppy-0.865
ounters-0.844
TokenThe
Token ID464
Feature activation-1.07e+00

Pos logit contributions
race+1.193
hibited+0.805
uning+0.750
COR+0.749
strate+0.745
Neg logit contributions
orthy-1.056
terday-0.912
Years-0.893
oppy-0.893
ounters-0.877
Token executive
Token ID4640
Feature activation-4.28e+00

Pos logit contributions
race+1.112
hibited+0.783
uning+0.742
strate+0.733
inary+0.728
Neg logit contributions
orthy-0.795
Years-0.681
terday-0.673
oppy-0.656
ounters-0.647
Token coach
Token ID3985
Feature activation-3.10e+00

Pos logit contributions
race+4.074
hibited+2.753
uning+2.605
strate+2.599
inary+2.525
Neg logit contributions
orthy-3.492
terday-3.101
Years-3.055
oppy-2.949
ounters-2.919
Token and
Token ID290
Feature activation-5.26e+00

Pos logit contributions
race+2.983
hibited+2.016
uning+1.929
strate+1.901
inary+1.864
Neg logit contributions
orthy-2.521
Years-2.189
terday-2.180
oppy-2.135
ounters-2.051
Token mother
Token ID2802
Feature activation-1.36e+01

Pos logit contributions
race+5.221
hibited+3.599
strate+3.389
 Offensive+3.363
uning+3.363
Neg logit contributions
orthy-4.036
Years-3.499
terday-3.426
ounters-3.365
oppy-3.353
Token has
Token ID468
Feature activation-3.19e+00

Pos logit contributions
race+11.515
hibited+7.682
strate+7.489
uning+7.155
COR+7.103
Neg logit contributions
orthy-10.741
terday-9.287
Years-9.258
oppy-9.119
onder-8.746
Token lived
Token ID5615
Feature activation+2.97e+00

Pos logit contributions
race+2.908
hibited+1.947
uning+1.802
strate+1.786
ilaterally+1.784
Neg logit contributions
orthy-2.747
terday-2.402
Years-2.383
oppy-2.356
ounters-2.288
Token on
Token ID319
Feature activation+9.05e-02

Pos logit contributions
orthy+2.288
Years+1.983
terday+1.946
oppy+1.905
ounters+1.877
Neg logit contributions
race-2.995
hibited-2.084
uning-1.976
ilaterally-1.958
strate-1.954
Token Pot
Token ID6902
Feature activation-4.40e+00

Pos logit contributions
orthy+0.072
Years+0.062
terday+0.061
oppy+0.060
ounters+0.059
Neg logit contributions
race-0.089
hibited-0.062
uning-0.058
strate-0.058
ilaterally-0.058
Tokenrero
Token ID34785
Feature activation+6.23e-01

Pos logit contributions
race+2.873
hibited+1.475
uning+1.354
inary+1.258
ilaterally+1.220
Neg logit contributions
orthy-4.994
Years-4.585
terday-4.576
ounters-4.414
oppy-4.373
Token there
Token ID612
Feature activation-3.45e+00

Pos logit contributions
race+1.081
hibited+0.733
uning+0.683
strate+0.677
ilaterally+0.676
Neg logit contributions
orthy-0.939
Years-0.821
terday-0.812
oppy-0.800
ounters-0.784
Token.
Token ID13
Feature activation+5.66e-01

Pos logit contributions
race+3.086
hibited+2.029
uning+1.912
ilaterally+1.875
strate+1.867
Neg logit contributions
orthy-3.002
Years-2.637
terday-2.611
oppy-2.585
ounters-2.532
Token
Token ID198
Feature activation+6.07e-01

Pos logit contributions
orthy+0.472
Years+0.410
terday+0.407
oppy+0.400
ounters+0.394
Neg logit contributions
race-0.537
hibited-0.363
uning-0.340
strate-0.336
ilaterally-0.336
Token
Token ID198
Feature activation+3.92e-01

Pos logit contributions
orthy+0.448
Years+0.386
terday+0.378
oppy+0.370
ounters+0.363
Neg logit contributions
race-0.633
hibited-0.448
uning-0.425
ilaterally-0.422
strate-0.421
TokenBlack
Token ID9915
Feature activation-5.06e+00

Pos logit contributions
orthy+0.320
terday+0.276
Years+0.274
oppy+0.270
ounters+0.266
Neg logit contributions
race-0.382
hibited-0.259
uning-0.243
strate-0.241
COR-0.240
Token Donkey
Token ID43823
Feature activation-1.36e+01

Pos logit contributions
race+4.679
hibited+3.104
COR+2.888
uning+2.860
strate+2.859
Neg logit contributions
orthy-4.243
Years-3.747
terday-3.660
ounters-3.581
oppy-3.573
Token is
Token ID318
Feature activation-4.50e+00

Pos logit contributions
race+10.982
hibited+7.011
 Offensive+6.925
uning+6.699
inary+6.584
Neg logit contributions
orthy-10.919
Years-9.734
oppy-9.409
ounters-9.355
terday-9.314
Token located
Token ID5140
Feature activation-6.22e+00

Pos logit contributions
race+4.185
hibited+2.844
ilaterally+2.644
uning+2.616
strate+2.600
Neg logit contributions
orthy-3.728
Years-3.261
terday-3.214
oppy-3.165
ounters-3.136
Token in
Token ID287
Feature activation-2.27e+00

Pos logit contributions
race+5.496
hibited+3.604
uning+3.380
ilaterally+3.371
strate+3.343
Neg logit contributions
orthy-5.370
Years-4.760
oppy-4.647
terday-4.626
ounters-4.463
Token Ros
Token ID10018
Feature activation-2.81e+00

Pos logit contributions
race+2.343
hibited+1.655
uning+1.570
ilaterally+1.553
strate+1.550
Neg logit contributions
orthy-1.657
Years-1.449
terday-1.413
oppy-1.379
ounters-1.375
Tokencommon
Token ID11321
Feature activation-5.28e+00

Pos logit contributions
race+2.572
hibited+1.700
uning+1.607
ilaterally+1.586
inary+1.584
Neg logit contributions
orthy-2.362
Years-2.158
terday-2.120
oppy-2.061
ounters-2.021
Tokengl
Token ID4743
Feature activation+3.82e+00

Pos logit contributions
orthy+2.765
Years+2.440
terday+2.396
oppy+2.371
ounters+2.333
Neg logit contributions
race-2.809
hibited-1.853
uning-1.741
ilaterally-1.724
strate-1.714
Tokenove
Token ID659
Feature activation+7.41e-01

Pos logit contributions
orthy+3.011
Years+2.574
oppy+2.539
terday+2.515
ounters+2.493
Neg logit contributions
race-3.795
hibited-2.638
uning-2.466
ilaterally-2.455
strate-2.453
Token Courier
Token ID34268
Feature activation+4.71e-01

Pos logit contributions
orthy+0.590
Years+0.515
terday+0.508
oppy+0.496
ounters+0.485
Neg logit contributions
race-0.731
hibited-0.503
uning-0.474
strate-0.470
ilaterally-0.470
Token
Token ID198
Feature activation+3.81e-01

Pos logit contributions
orthy+0.352
Years+0.303
terday+0.298
oppy+0.292
ounters+0.287
Neg logit contributions
race-0.487
hibited-0.343
uning-0.325
ilaterally-0.323
strate-0.322
Token
Token ID198
Feature activation-1.72e-01

Pos logit contributions
orthy+0.282
Years+0.243
terday+0.239
oppy+0.234
ounters+0.229
Neg logit contributions
race-0.396
hibited-0.279
uning-0.265
ilaterally-0.263
strate-0.262
TokenPrim
Token ID23828
Feature activation-1.34e+01

Pos logit contributions
race+0.169
hibited+0.115
uning+0.108
strate+0.108
ilaterally+0.107
Neg logit contributions
orthy-0.139
terday-0.119
Years-0.119
oppy-0.117
ounters-0.114
Tokenal
Token ID282
Feature activation-1.70e+00

Pos logit contributions
race+11.149
hibited+7.377
inary+6.979
strate+6.699
uning+6.619
Neg logit contributions
orthy-10.900
terday-10.175
Years-10.139
ounters-9.479
oppy-9.443
Token Surge
Token ID46774
Feature activation-2.58e-01

Pos logit contributions
race+1.636
hibited+1.116
uning+1.041
strate+1.037
ilaterally+1.025
Neg logit contributions
orthy-1.409
Years-1.232
terday-1.220
oppy-1.195
ounters-1.168
Token vs
Token ID3691
Feature activation-3.47e-01

Pos logit contributions
race+0.270
hibited+0.191
uning+0.181
ilaterally+0.180
strate+0.179
Neg logit contributions
orthy-0.190
Years-0.164
terday-0.161
oppy-0.157
ounters-0.154
Token Safe
Token ID19978
Feature activation-1.23e+00

Pos logit contributions
race+0.341
hibited+0.235
uning+0.221
strate+0.219
ilaterally+0.219
Neg logit contributions
orthy-0.278
Years-0.242
terday-0.238
oppy-0.233
ounters-0.228
Token Passage
Token ID46169
Feature activation-3.48e+00

Pos logit contributions
race+1.159
hibited+0.783
uning+0.728
strate+0.728
ilaterally+0.721
Neg logit contributions
orthy-1.029
Years-0.901
terday-0.895
oppy-0.873
ounters-0.852
Token L
Token ID406
Feature activation+1.58e+00

Pos logit contributions
orthy+3.310
Years+2.886
terday+2.806
oppy+2.740
ounters+2.715
Neg logit contributions
race-3.970
hibited-2.721
ilaterally-2.588
uning-2.568
strate-2.559
TokenIG
Token ID3528
Feature activation+1.56e+00

Pos logit contributions
orthy+1.353
Years+1.190
terday+1.175
oppy+1.152
ounters+1.133
Neg logit contributions
race-1.453
hibited-0.971
uning-0.912
ilaterally-0.903
strate-0.900
TokenO
Token ID46
Feature activation+3.04e+00

Pos logit contributions
orthy+1.171
Years+1.011
terday+0.994
oppy+0.972
ounters+0.953
Neg logit contributions
race-1.603
hibited-1.127
uning-1.067
ilaterally-1.059
strate-1.058
Token,
Token ID11
Feature activation-2.28e+00

Pos logit contributions
orthy+2.432
Years+2.115
terday+2.074
oppy+2.015
ounters+2.005
Neg logit contributions
race-2.980
hibited-2.052
uning-1.928
ilaterally-1.923
strate-1.915
Token is
Token ID318
Feature activation-5.72e+00

Pos logit contributions
race+1.978
hibited+1.257
uning+1.204
ilaterally+1.178
inary+1.159
Neg logit contributions
orthy-2.046
terday-1.828
Years-1.826
oppy-1.775
ounters-1.734
Token complete
Token ID1844
Feature activation-1.34e+01

Pos logit contributions
race+4.797
hibited+3.015
uning+2.820
acqu+2.798
ilaterally+2.783
Neg logit contributions
orthy-4.985
Years-4.617
terday-4.601
oppy-4.580
ounters-4.483
Token and
Token ID290
Feature activation-3.75e+00

Pos logit contributions
race+9.940
hibited+5.798
uning+5.559
ilaterally+5.541
strate+5.322
Neg logit contributions
orthy-11.523
oppy-10.764
terday-10.681
Years-10.665
ounters-10.229
Token the
Token ID262
Feature activation-2.02e+00

Pos logit contributions
race+3.601
hibited+2.394
uning+2.315
ilaterally+2.257
inary+2.245
Neg logit contributions
orthy-2.992
Years-2.662
terday-2.637
oppy-2.589
ounters-2.521
Token project
Token ID1628
Feature activation+1.41e+00

Pos logit contributions
race+2.025
hibited+1.402
uning+1.331
strate+1.308
ilaterally+1.306
Neg logit contributions
orthy-1.570
Years-1.373
terday-1.343
oppy-1.317
ounters-1.301
Token starts
Token ID4940
Feature activation+4.92e+00

Pos logit contributions
orthy+1.163
Years+1.018
terday+1.004
oppy+0.984
ounters+0.966
Neg logit contributions
race-1.356
hibited-0.922
uning-0.870
ilaterally-0.860
strate-0.858
Token taking
Token ID2263
Feature activation-4.34e+00

Pos logit contributions
orthy+3.691
Years+3.164
terday+3.103
oppy+3.030
ounters+2.983
Neg logit contributions
race-5.027
hibited-3.537
ilaterally-3.335
strate-3.329
uning-3.324
Token around
Token ID1088
Feature activation-3.53e+00

Pos logit contributions
race+0.151
hibited+0.102
uning+0.095
ilaterally+0.095
strate+0.094
Neg logit contributions
orthy-0.135
Years-0.119
terday-0.117
oppy-0.115
ounters-0.113
Token to
Token ID284
Feature activation-2.36e+00

Pos logit contributions
race+3.384
hibited+2.301
ilaterally+2.164
uning+2.161
strate+2.147
Neg logit contributions
orthy-2.875
Years-2.501
terday-2.485
oppy-2.429
ounters-2.372
Token them
Token ID606
Feature activation+4.76e-01

Pos logit contributions
race+2.351
hibited+1.620
strate+1.529
uning+1.525
ilaterally+1.520
Neg logit contributions
orthy-1.847
terday-1.593
Years-1.583
oppy-1.546
ounters-1.499
Token while
Token ID981
Feature activation-5.12e+00

Pos logit contributions
orthy+0.385
Years+0.335
terday+0.330
oppy+0.324
ounters+0.317
Neg logit contributions
race-0.464
hibited-0.318
uning-0.300
ilaterally-0.298
strate-0.297
Token the
Token ID262
Feature activation-3.64e+00

Pos logit contributions
race+4.740
hibited+3.180
uning+3.025
ilaterally+2.963
inary+2.938
Neg logit contributions
orthy-4.292
Years-3.701
terday-3.652
oppy-3.618
onder-3.475
Token mother
Token ID2802
Feature activation-1.34e+01

Pos logit contributions
race+3.700
hibited+2.586
uning+2.449
strate+2.404
COR+2.398
Neg logit contributions
orthy-2.771
Years-2.360
terday-2.351
oppy-2.324
ounters-2.218
Token is
Token ID318
Feature activation-5.26e+00

Pos logit contributions
race+13.167
hibited+9.362
uning+8.910
lessly+8.817
inary+8.802
Neg logit contributions
orthy-8.936
terday-7.515
Years-7.331
oppy-7.300
ounters-7.016
Token tranquil
Token ID46944
Feature activation-5.41e+00

Pos logit contributions
race+4.744
hibited+3.247
uning+3.053
ilaterally+2.958
strate+2.925
Neg logit contributions
orthy-4.456
Years-3.929
terday-3.889
oppy-3.814
ounters-3.714
Tokenized
Token ID1143
Feature activation-7.56e+00

Pos logit contributions
race+5.018
hibited+3.537
strate+3.318
uning+3.292
ilaterally+3.266
Neg logit contributions
orthy-4.387
Years-3.845
terday-3.768
oppy-3.749
ounters-3.619
Token.
Token ID13
Feature activation+2.86e+00

Pos logit contributions
race+6.564
hibited+4.382
uning+4.193
strate+4.087
ilaterally+4.087
Neg logit contributions
orthy-6.440
Years-5.656
terday-5.564
oppy-5.524
ounters-5.334
Token It
Token ID632
Feature activation+3.23e+00

Pos logit contributions
orthy+2.332
Years+2.047
terday+2.007
oppy+1.965
ounters+1.935
Neg logit contributions
race-2.751
hibited-1.877
uning-1.771
ilaterally-1.759
strate-1.753
Token
Token ID198
Feature activation-2.15e+00

Pos logit contributions
race+1.511
hibited+1.047
uning+0.987
strate+0.979
ilaterally+0.969
Neg logit contributions
orthy-1.168
terday-1.002
Years-0.998
oppy-0.977
ounters-0.953
TokenFriday
Token ID20610
Feature activation+2.71e+00

Pos logit contributions
race+2.126
hibited+1.469
COR+1.374
uning+1.363
ilaterally+1.361
Neg logit contributions
orthy-1.711
terday-1.466
oppy-1.438
Years-1.429
ounters-1.418
Token,
Token ID11
Feature activation-4.10e-01

Pos logit contributions
orthy+2.089
Years+1.817
terday+1.814
oppy+1.764
ounters+1.744
Neg logit contributions
race-2.676
hibited-1.857
uning-1.771
strate-1.750
ilaterally-1.735
Token June
Token ID2795
Feature activation-8.02e+00

Pos logit contributions
race+0.468
hibited+0.343
uning+0.327
ilaterally+0.325
strate+0.324
Neg logit contributions
orthy-0.263
Years-0.220
terday-0.216
oppy-0.210
ounters-0.205
Token 16
Token ID1467
Feature activation-8.74e+00

Pos logit contributions
race+7.482
hibited+5.213
 Offensive+5.030
COR+4.797
uning+4.772
Neg logit contributions
orthy-6.192
terday-5.542
oppy-5.450
Years-5.403
onder-5.100
Token Last
Token ID4586
Feature activation-1.32e+01

Pos logit contributions
race+8.165
hibited+5.677
 Offensive+5.486
ilaterally+5.273
strate+5.116
Neg logit contributions
orthy-6.849
Years-5.848
terday-5.789
oppy-5.708
ounters-5.606
Token day
Token ID1110
Feature activation+2.92e+00

Pos logit contributions
race+11.814
hibited+8.441
 Offensive+8.044
ilaterally+7.786
acqu+7.575
Neg logit contributions
orthy-9.946
Years-8.248
oppy-8.242
ounters-8.121
terday-8.108
Token to
Token ID284
Feature activation+2.81e-01

Pos logit contributions
orthy+2.095
Years+1.804
terday+1.769
oppy+1.720
ounters+1.702
Neg logit contributions
race-3.077
hibited-2.185
uning-2.084
strate-2.072
ilaterally-2.063
Token place
Token ID1295
Feature activation-9.42e-01

Pos logit contributions
orthy+0.219
Years+0.190
terday+0.187
oppy+0.183
ounters+0.179
Neg logit contributions
race-0.282
hibited-0.196
uning-0.185
ilaterally-0.185
strate-0.183
Token Player
Token ID7853
Feature activation+3.07e+00

Pos logit contributions
race+0.896
hibited+0.611
ilaterally+0.574
uning+0.572
strate+0.563
Neg logit contributions
orthy-0.782
Years-0.684
terday-0.676
oppy-0.664
ounters-0.650
Token on
Token ID319
Feature activation+2.73e+00

Pos logit contributions
orthy+2.333
Years+2.018
terday+1.966
oppy+1.928
ounters+1.904
Neg logit contributions
race-3.108
hibited-2.157
uning-2.061
strate-2.042
inary-2.016
Token,
Token ID11
Feature activation-2.99e+00

Pos logit contributions
race+3.098
hibited+2.075
uning+1.934
strate+1.929
ilaterally+1.927
Neg logit contributions
orthy-2.751
Years-2.408
terday-2.366
oppy-2.338
ounters-2.291
Token it
Token ID340
Feature activation-6.60e+00

Pos logit contributions
race+2.840
hibited+1.869
uning+1.736
strate+1.734
ilaterally+1.724
Neg logit contributions
orthy-2.537
Years-2.199
terday-2.184
oppy-2.149
ounters-2.098
Token has
Token ID468
Feature activation-8.55e+00

Pos logit contributions
race+5.606
hibited+3.629
uning+3.355
strate+3.296
inary+3.273
Neg logit contributions
orthy-5.911
Years-5.286
terday-5.203
oppy-5.124
ounters-4.934
Token long
Token ID890
Feature activation-3.93e+00

Pos logit contributions
race+7.628
hibited+5.238
inary+4.797
ilaterally+4.766
uning+4.763
Neg logit contributions
orthy-6.881
terday-5.979
Years-5.919
oppy-5.839
ounters-5.710
Token been
Token ID587
Feature activation-7.18e+00

Pos logit contributions
race+3.528
hibited+2.400
ilaterally+2.183
uning+2.178
inary+2.175
Neg logit contributions
orthy-3.343
Years-2.967
oppy-2.889
terday-2.866
ounters-2.794
Token recognized
Token ID8018
Feature activation-1.31e+01

Pos logit contributions
race+6.846
hibited+4.720
strate+4.293
uning+4.271
 Offensive+4.249
Neg logit contributions
orthy-5.662
Years-4.992
terday-4.988
oppy-4.873
ounters-4.771
Token by
Token ID416
Feature activation-5.73e+00

Pos logit contributions
race+10.792
hibited+6.752
inary+6.224
ilaterally+6.202
lessly+6.185
Neg logit contributions
orthy-10.834
Years-9.727
terday-9.595
oppy-9.569
ounters-9.168
Token science
Token ID3783
Feature activation-5.30e+00

Pos logit contributions
race+5.576
hibited+3.756
inary+3.497
strate+3.497
uning+3.475
Neg logit contributions
orthy-4.565
terday-3.965
Years-3.883
oppy-3.846
ounters-3.787
Token and
Token ID290
Feature activation-8.58e-02

Pos logit contributions
race+4.846
hibited+3.192
strate+3.006
uning+3.002
inary+2.949
Neg logit contributions
orthy-4.478
terday-3.940
Years-3.932
oppy-3.842
ounters-3.717
Token medicine
Token ID9007
Feature activation-7.61e+00

Pos logit contributions
race+0.081
hibited+0.054
uning+0.051
ilaterally+0.051
strate+0.051
Neg logit contributions
orthy-0.072
Years-0.063
terday-0.063
oppy-0.061
ounters-0.060
Token as
Token ID355
Feature activation-6.68e+00

Pos logit contributions
race+6.813
hibited+4.426
strate+4.210
uning+4.198
inary+4.169
Neg logit contributions
orthy-6.365
terday-5.629
Years-5.556
oppy-5.467
ounters-5.284
Token/
Token ID14
Feature activation-4.36e+00

Pos logit contributions
race+0.995
hibited+0.676
uning+0.644
ilaterally+0.634
strate+0.633
Neg logit contributions
orthy-0.825
Years-0.720
terday-0.712
oppy-0.701
ounters-0.687
Tokenor
Token ID273
Feature activation-8.06e-01

Pos logit contributions
race+3.467
hibited+2.097
uning+1.933
strate+1.889
COR+1.870
Neg logit contributions
orthy-4.271
terday-3.854
oppy-3.781
Years-3.719
ounters-3.633
Token Survival
Token ID20303
Feature activation-2.03e+00

Pos logit contributions
race+0.725
hibited+0.476
uning+0.448
ilaterally+0.444
strate+0.443
Neg logit contributions
orthy-0.708
Years-0.625
terday-0.620
oppy-0.607
ounters-0.595
Token+
Token ID10
Feature activation-3.05e+00

Pos logit contributions
race+1.928
hibited+1.295
uning+1.221
strate+1.220
inary+1.216
Neg logit contributions
orthy-1.670
Years-1.454
terday-1.452
oppy-1.418
ounters-1.392
Token The
Token ID383
Feature activation-3.88e+00

Pos logit contributions
race+2.781
hibited+1.828
uning+1.729
inary+1.714
ilaterally+1.706
Neg logit contributions
orthy-2.599
terday-2.280
Years-2.276
oppy-2.247
ounters-2.188
Token Prim
Token ID11460
Feature activation-1.30e+01

Pos logit contributions
race+3.865
hibited+2.675
uning+2.538
 Offensive+2.502
inary+2.495
Neg logit contributions
orthy-2.958
terday-2.568
Years-2.557
oppy-2.490
ounters-2.427
Tokener
Token ID263
Feature activation-1.04e+00

Pos logit contributions
race+10.208
hibited+6.735
inary+6.197
strate+6.074
uning+6.022
Neg logit contributions
orthy-11.099
terday-10.052
Years-9.734
oppy-9.642
ounters-9.315
Token from
Token ID422
Feature activation-1.00e+00

Pos logit contributions
race+0.993
hibited+0.672
uning+0.633
strate+0.626
ilaterally+0.624
Neg logit contributions
orthy-0.869
Years-0.758
terday-0.750
oppy-0.737
ounters-0.724
Token your
Token ID534
Feature activation+3.18e+00

Pos logit contributions
race+1.006
hibited+0.696
uning+0.658
ilaterally+0.650
inary+0.650
Neg logit contributions
orthy-0.779
Years-0.670
terday-0.666
oppy-0.650
ounters-0.637
Token local
Token ID1957
Feature activation-7.52e-02

Pos logit contributions
orthy+2.495
Years+2.165
terday+2.127
oppy+2.087
ounters+2.049
Neg logit contributions
race-3.161
hibited-2.190
uning-2.070
ilaterally-2.054
strate-2.047
Token book
Token ID1492
Feature activation-9.44e-01

Pos logit contributions
race+0.072
hibited+0.049
uning+0.047
inary+0.046
strate+0.046
Neg logit contributions
orthy-0.061
Years-0.054
terday-0.053
oppy-0.052
ounters-0.050
Token.
Token ID13
Feature activation-4.05e+00

Pos logit contributions
race+3.420
hibited+2.190
uning+2.102
ilaterally+2.040
inary+2.003
Neg logit contributions
orthy-3.624
Years-3.191
terday-3.153
oppy-3.142
onder-3.030
Token The
Token ID383
Feature activation-2.52e+00

Pos logit contributions
race+3.548
hibited+2.313
 Offensive+2.251
COR+2.184
uning+2.155
Neg logit contributions
orthy-3.565
terday-3.127
oppy-3.097
Years-3.017
ounters-2.984
Token opposite
Token ID6697
Feature activation-1.24e+01

Pos logit contributions
race+2.481
hibited+1.692
uning+1.627
ilaterally+1.589
strate+1.578
Neg logit contributions
orthy-1.994
Years-1.733
terday-1.716
oppy-1.661
ounters-1.635
Token may
Token ID743
Feature activation-7.07e+00

Pos logit contributions
race+9.473
hibited+5.495
uning+5.328
 Offensive+5.264
COR+5.175
Neg logit contributions
orthy-11.110
terday-9.837
Years-9.833
oppy-9.658
ounters-9.460
Token be
Token ID307
Feature activation-1.16e+01

Pos logit contributions
race+6.429
hibited+4.199
inary+4.021
ilaterally+3.910
strate+3.906
Neg logit contributions
orthy-5.844
Years-5.181
terday-5.043
oppy-5.013
ounters-4.805
Token true
Token ID2081
Feature activation-1.30e+01

Pos logit contributions
race+9.112
hibited+5.692
 Offensive+5.257
uning+5.107
strate+5.103
Neg logit contributions
orthy-10.266
Years-9.231
terday-9.166
oppy-8.996
ounters-8.900
Token if
Token ID611
Feature activation-8.44e+00

Pos logit contributions
race+9.803
hibited+5.677
uning+5.544
ilaterally+5.378
inary+5.353
Neg logit contributions
orthy-11.318
Years-10.407
oppy-10.392
terday-10.112
ounters-9.856
Token teachers
Token ID7799
Feature activation-4.98e+00

Pos logit contributions
race+7.739
hibited+4.885
uning+4.883
inary+4.796
acqu+4.723
Neg logit contributions
orthy-6.732
Years-5.839
oppy-5.726
terday-5.671
onder-5.663
Token in
Token ID287
Feature activation-2.38e+00

Pos logit contributions
race+4.544
hibited+2.967
uning+2.810
ilaterally+2.790
inary+2.772
Neg logit contributions
orthy-4.248
Years-3.705
oppy-3.673
terday-3.669
ounters-3.546
Token poor
Token ID3595
Feature activation+6.90e-01

Pos logit contributions
race+2.345
hibited+1.629
uning+1.528
ilaterally+1.519
inary+1.509
Neg logit contributions
orthy-1.859
Years-1.604
terday-1.601
oppy-1.554
ounters-1.539
Token health
Token ID1535
Feature activation-1.97e+00

Pos logit contributions
orthy+0.549
Years+0.472
terday+0.468
oppy+0.457
ounters+0.451
Neg logit contributions
race-0.683
hibited-0.468
uning-0.447
ilaterally-0.441
strate-0.439
TokenA
Token ID32
Feature activation-1.04e+00

Pos logit contributions
race+0.219
hibited+0.146
uning+0.139
ilaterally+0.137
strate+0.137
Neg logit contributions
orthy-0.193
Years-0.168
terday-0.166
oppy-0.162
ounters-0.160
Token.
Token ID13
Feature activation-3.51e+00

Pos logit contributions
race+0.990
hibited+0.673
uning+0.636
strate+0.628
ilaterally+0.627
Neg logit contributions
orthy-0.859
Years-0.755
terday-0.749
oppy-0.728
ounters-0.714
Token Maybe
Token ID6674
Feature activation+6.58e+00

Pos logit contributions
race+3.240
hibited+2.158
uning+2.010
COR+1.998
 Offensive+1.988
Neg logit contributions
orthy-2.976
terday-2.592
Years-2.573
oppy-2.532
ounters-2.512
Token a
Token ID257
Feature activation+1.28e+00

Pos logit contributions
orthy+4.891
Years+4.272
terday+4.182
oppy+4.085
ounters+4.028
Neg logit contributions
race-6.542
hibited-4.629
uning-4.404
strate-4.371
ilaterally-4.343
Token black
Token ID2042
Feature activation+7.24e+00

Pos logit contributions
orthy+0.963
Years+0.830
terday+0.817
oppy+0.798
ounters+0.783
Neg logit contributions
race-1.321
hibited-0.928
uning-0.879
ilaterally-0.872
strate-0.870
Token variant
Token ID15304
Feature activation+8.86e+00

Pos logit contributions
orthy+5.179
Years+4.378
terday+4.362
oppy+4.281
onder+4.245
Neg logit contributions
race-7.475
hibited-5.366
ilaterally-5.034
strate-5.023
uning-5.018
Token will
Token ID481
Feature activation+2.08e+00

Pos logit contributions
orthy+6.213
Years+5.191
terday+5.079
oppy+5.014
onder+4.988
Neg logit contributions
race-8.977
hibited-6.569
strate-6.200
ilaterally-6.191
uning-6.138
Token be
Token ID307
Feature activation+4.29e-01

Pos logit contributions
orthy+1.589
Years+1.373
terday+1.352
oppy+1.322
ounters+1.297
Neg logit contributions
race-2.125
hibited-1.488
uning-1.408
ilaterally-1.396
strate-1.394
Token coming
Token ID2406
Feature activation-3.15e+00

Pos logit contributions
orthy+0.356
Years+0.312
terday+0.309
oppy+0.302
ounters+0.295
Neg logit contributions
race-0.411
hibited-0.278
uning-0.261
ilaterally-0.260
strate-0.258
Token soon
Token ID2582
Feature activation+4.40e+00

Pos logit contributions
race+3.073
hibited+2.104
uning+1.986
ilaterally+1.962
strate+1.953
Neg logit contributions
orthy-2.482
terday-2.160
Years-2.156
oppy-2.085
ounters-2.047
Token as
Token ID355
Feature activation+2.25e+00

Pos logit contributions
orthy+3.406
Years+2.932
terday+2.886
oppy+2.818
ounters+2.780
Neg logit contributions
race-4.412
hibited-3.081
uning-2.905
strate-2.893
ilaterally-2.889
Token border
Token ID4865
Feature activation+1.58e+00

Pos logit contributions
orthy+2.705
Years+2.305
terday+2.267
oppy+2.218
ounters+2.170
Neg logit contributions
race-3.922
hibited-2.790
uning-2.643
ilaterally-2.632
strate-2.625
Token with
Token ID351
Feature activation+1.28e+00

Pos logit contributions
orthy+1.267
Years+1.103
terday+1.088
oppy+1.064
ounters+1.047
Neg logit contributions
race-1.538
hibited-1.057
uning-0.997
ilaterally-0.988
strate-0.987
Token Bangladesh
Token ID19483
Feature activation+5.48e-01

Pos logit contributions
orthy+0.845
Years+0.717
terday+0.704
oppy+0.684
ounters+0.671
Neg logit contributions
race-1.433
hibited-1.041
uning-0.993
ilaterally-0.986
strate-0.981
Token.
Token ID13
Feature activation+2.88e+00

Pos logit contributions
orthy+0.457
Years+0.401
terday+0.395
oppy+0.388
ounters+0.381
Neg logit contributions
race-0.519
hibited-0.351
uning-0.330
ilaterally-0.327
strate-0.326
Token Two
Token ID4930
Feature activation+3.27e+00

Pos logit contributions
orthy+2.266
Years+1.972
terday+1.938
oppy+1.895
ounters+1.863
Neg logit contributions
race-2.863
hibited-1.983
uning-1.874
ilaterally-1.859
strate-1.856
Token narratives
Token ID26274
Feature activation+9.01e+00

Pos logit contributions
orthy+2.459
Years+2.123
terday+2.086
oppy+2.034
ounters+1.998
Neg logit contributions
race-3.355
hibited-2.360
uning-2.234
strate-2.217
ilaterally-2.214
Token quickly
Token ID2952
Feature activation+8.48e+00

Pos logit contributions
orthy+6.535
Years+5.685
terday+5.637
oppy+5.334
onder+5.284
Neg logit contributions
race-8.910
hibited-6.295
uning-6.108
ilaterally-5.992
strate-5.886
Token emerged
Token ID9349
Feature activation-1.34e-01

Pos logit contributions
orthy+6.748
Years+5.900
terday+5.794
oppy+5.631
onder+5.624
Neg logit contributions
race-7.908
hibited-5.391
uning-5.195
ilaterally-5.107
COR-5.052
Token,
Token ID11
Feature activation+1.50e+00

Pos logit contributions
race+0.126
hibited+0.084
uning+0.079
strate+0.078
ilaterally+0.078
Neg logit contributions
orthy-0.113
Years-0.099
terday-0.098
oppy-0.097
ounters-0.095
Token with
Token ID351
Feature activation+4.48e-01

Pos logit contributions
orthy+1.218
Years+1.062
terday+1.048
oppy+1.027
ounters+1.009
Neg logit contributions
race-1.454
hibited-0.993
uning-0.937
ilaterally-0.929
strate-0.923
Token the
Token ID262
Feature activation+2.04e+00

Pos logit contributions
orthy+0.340
Years+0.294
terday+0.289
oppy+0.283
ounters+0.278
Neg logit contributions
race-0.459
hibited-0.321
uning-0.304
ilaterally-0.301
strate-0.299
TokenOther
Token ID6395
Feature activation-4.23e+00

Pos logit contributions
orthy+3.117
Years+2.767
terday+2.639
oppy+2.590
ounters+2.551
Neg logit contributions
race-4.050
hibited-2.841
uning-2.682
ilaterally-2.672
strate-2.656
Token governments
Token ID6905
Feature activation+3.01e+00

Pos logit contributions
race+4.296
hibited+2.987
uning+2.870
inary+2.826
strate+2.810
Neg logit contributions
orthy-3.123
terday-2.708
Years-2.695
oppy-2.676
ounters-2.558
Token only
Token ID691
Feature activation+5.70e+00

Pos logit contributions
orthy+2.393
Years+2.079
terday+2.035
oppy+1.995
ounters+1.978
Neg logit contributions
race-2.938
hibited-2.034
uning-1.914
ilaterally-1.893
strate-1.889
Token borrow
Token ID8804
Feature activation+6.69e+00

Pos logit contributions
orthy+4.392
Years+3.802
terday+3.733
oppy+3.630
ounters+3.594
Neg logit contributions
race-5.650
hibited-3.960
uning-3.743
strate-3.679
ilaterally-3.657
Token to
Token ID284
Feature activation+5.12e+00

Pos logit contributions
orthy+4.753
Years+4.130
terday+4.016
oppy+3.886
ounters+3.860
Neg logit contributions
race-6.941
hibited-5.005
uning-4.697
strate-4.681
ilaterally-4.589
Token stimulate
Token ID26020
Feature activation+9.35e+00

Pos logit contributions
orthy+3.398
Years+2.890
terday+2.794
oppy+2.746
ounters+2.684
Neg logit contributions
race-5.656
hibited-4.133
uning-3.928
ilaterally-3.876
strate-3.869
Token the
Token ID262
Feature activation+6.57e+00

Pos logit contributions
orthy+6.233
Years+5.404
terday+5.218
oppy+5.214
ounters+5.144
Neg logit contributions
race-9.721
hibited-7.071
ilaterally-6.562
uning-6.561
strate-6.491
Token economy
Token ID3773
Feature activation+5.20e+00

Pos logit contributions
orthy+5.450
Years+4.809
oppy+4.702
terday+4.682
ounters+4.624
Neg logit contributions
race-5.935
hibited-4.107
uning-3.776
ilaterally-3.764
strate-3.748
Token during
Token ID1141
Feature activation+4.60e+00

Pos logit contributions
orthy+4.088
Years+3.561
terday+3.467
ounters+3.393
oppy+3.392
Neg logit contributions
race-5.093
hibited-3.547
uning-3.330
strate-3.316
ilaterally-3.283
Token a
Token ID257
Feature activation+4.01e+00

Pos logit contributions
orthy+3.406
Years+2.952
terday+2.864
oppy+2.833
ounters+2.771
Neg logit contributions
race-4.746
hibited-3.346
uning-3.170
ilaterally-3.159
strate-3.141
Token recession
Token ID16457
Feature activation+4.22e+00

Pos logit contributions
orthy+3.029
Years+2.643
terday+2.567
oppy+2.530
ounters+2.485
Neg logit contributions
race-4.035
hibited-2.838
uning-2.677
ilaterally-2.664
strate-2.663
Token months
Token ID1933
Feature activation+1.49e+00

Pos logit contributions
orthy+2.005
Years+1.687
terday+1.638
oppy+1.591
ounters+1.561
Neg logit contributions
race-3.702
hibited-2.722
uning-2.596
strate-2.585
ilaterally-2.575
Token for
Token ID329
Feature activation+2.76e-01

Pos logit contributions
orthy+1.104
Years+0.951
terday+0.937
oppy+0.912
ounters+0.899
Neg logit contributions
race-1.550
hibited-1.098
uning-1.039
strate-1.030
ilaterally-1.029
Token the
Token ID262
Feature activation+6.94e-01

Pos logit contributions
orthy+0.210
Years+0.181
terday+0.179
oppy+0.174
ounters+0.171
Neg logit contributions
race-0.283
hibited-0.198
uning-0.188
ilaterally-0.186
strate-0.186
Token larger
Token ID4025
Feature activation+1.54e+00

Pos logit contributions
orthy+0.495
Years+0.422
terday+0.417
oppy+0.406
ounters+0.396
Neg logit contributions
race-0.744
hibited-0.529
uning-0.504
ilaterally-0.501
strate-0.499
Token Hyp
Token ID21209
Feature activation+6.26e-01

Pos logit contributions
orthy+1.207
Years+1.047
terday+1.030
oppy+1.009
ounters+0.995
Neg logit contributions
race-1.522
hibited-1.058
uning-0.997
ilaterally-0.988
strate-0.986
Tokenac
Token ID330
Feature activation+8.55e+00

Pos logit contributions
orthy+0.487
Years+0.421
terday+0.414
oppy+0.407
ounters+0.399
Neg logit contributions
race-0.626
hibited-0.436
uning-0.412
ilaterally-0.409
strate-0.408
Tokenros
Token ID4951
Feature activation-1.49e+00

Pos logit contributions
orthy+6.585
ounters+5.806
Years+5.647
oppy+5.557
onder+5.524
Neg logit contributions
race-7.638
hibited-5.416
ilaterally-5.161
uning-5.160
 Offensive-5.149
Tokenaurus
Token ID22302
Feature activation-4.65e+00

Pos logit contributions
race+0.939
hibited+0.474
uning+0.415
ilaterally+0.409
strate+0.409
Neg logit contributions
orthy-1.724
Years-1.571
terday-1.564
oppy-1.532
ounters-1.505
Token.
Token ID13
Feature activation+4.59e-01

Pos logit contributions
race+4.378
hibited+2.883
uning+2.741
ilaterally+2.741
strate+2.732
Neg logit contributions
orthy-3.865
Years-3.357
terday-3.316
oppy-3.297
ounters-3.165
Token Most
Token ID4042
Feature activation-4.61e-01

Pos logit contributions
orthy+0.369
Years+0.319
terday+0.317
oppy+0.312
ounters+0.304
Neg logit contributions
race-0.450
hibited-0.309
uning-0.291
strate-0.288
ilaterally-0.287
Token birds
Token ID10087
Feature activation-4.92e+00

Pos logit contributions
race+0.467
hibited+0.322
uning+0.305
ilaterally+0.304
strate+0.303
Neg logit contributions
orthy-0.357
Years-0.307
terday-0.303
oppy-0.298
ounters-0.289
Token The
Token ID383
Feature activation-2.30e+00

Pos logit contributions
race+3.422
hibited+2.337
 Offensive+2.191
uning+2.167
inary+2.135
Neg logit contributions
orthy-2.980
terday-2.624
Years-2.554
oppy-2.546
ounters-2.442
Token early
Token ID1903
Feature activation+3.16e+00

Pos logit contributions
race+2.212
hibited+1.515
uning+1.430
ilaterally+1.408
strate+1.400
Neg logit contributions
orthy-1.860
Years-1.624
terday-1.621
oppy-1.566
ounters-1.541
Token social
Token ID1919
Feature activation+1.49e+00

Pos logit contributions
orthy+2.343
Years+2.022
terday+1.977
oppy+1.935
ounters+1.903
Neg logit contributions
race-3.268
hibited-2.310
uning-2.186
ilaterally-2.180
strate-2.174
Tokenization
Token ID1634
Feature activation+1.13e+00

Pos logit contributions
orthy+1.130
Years+0.975
terday+0.960
oppy+0.938
ounters+0.921
Neg logit contributions
race-1.530
hibited-1.074
uning-1.017
ilaterally-1.008
strate-1.007
Token of
Token ID286
Feature activation+1.61e+00

Pos logit contributions
orthy+0.840
Years+0.722
terday+0.710
oppy+0.694
ounters+0.681
Neg logit contributions
race-1.180
hibited-0.834
uning-0.791
ilaterally-0.784
strate-0.783
Token aggressive
Token ID8361
Feature activation+8.94e+00

Pos logit contributions
orthy+1.237
Years+1.070
terday+1.053
oppy+1.030
ounters+1.011
Neg logit contributions
race-1.636
hibited-1.143
uning-1.081
ilaterally-1.072
strate-1.071
Token victims
Token ID4970
Feature activation+1.47e+00

Pos logit contributions
orthy+6.585
Years+5.712
terday+5.597
ounters+5.480
 imag+5.462
Neg logit contributions
race-8.674
hibited-5.973
uning-5.723
ilaterally-5.706
strate-5.701
Token of
Token ID286
Feature activation+3.38e+00

Pos logit contributions
orthy+1.199
Years+1.047
terday+1.032
oppy+1.010
ounters+0.995
Neg logit contributions
race-1.415
hibited-0.967
uning-0.911
ilaterally-0.902
strate-0.901
Token bullying
Token ID20714
Feature activation-4.80e-01

Pos logit contributions
orthy+2.603
Years+2.251
terday+2.208
oppy+2.168
ounters+2.139
Neg logit contributions
race-3.396
hibited-2.367
uning-2.241
ilaterally-2.225
strate-2.223
Token.
Token ID764
Feature activation+1.50e+00

Pos logit contributions
race+0.458
hibited+0.310
uning+0.292
ilaterally+0.289
strate+0.289
Neg logit contributions
orthy-0.399
Years-0.348
terday-0.344
oppy-0.339
ounters-0.331
Token Child
Token ID5932
Feature activation-2.58e+00

Pos logit contributions
orthy+1.282
Years+1.127
terday+1.111
oppy+1.090
ounters+1.073
Neg logit contributions
race-1.391
hibited-0.932
uning-0.875
ilaterally-0.867
strate-0.865
Token,
Token ID11
Feature activation-1.99e+00

Pos logit contributions
race+2.487
hibited+1.656
uning+1.565
ilaterally+1.563
strate+1.543
Neg logit contributions
orthy-2.231
Years-1.973
terday-1.944
oppy-1.926
ounters-1.862
Token too
Token ID1165
Feature activation+2.53e+00

Pos logit contributions
race+1.921
hibited+1.281
uning+1.222
ilaterally+1.221
inary+1.201
Neg logit contributions
orthy-1.642
terday-1.433
Years-1.424
oppy-1.391
ounters-1.360
Token.
Token ID13
Feature activation-2.04e-01

Pos logit contributions
orthy+2.086
Years+1.812
terday+1.777
oppy+1.749
ounters+1.725
Neg logit contributions
race-2.396
hibited-1.643
uning-1.540
strate-1.530
ilaterally-1.525
Token
Token ID447
Feature activation+5.99e-01

Pos logit contributions
race+0.197
hibited+0.134
uning+0.126
ilaterally+0.124
strate+0.124
Neg logit contributions
orthy-0.167
Years-0.145
terday-0.145
oppy-0.142
ounters-0.139
Token
Token ID251
Feature activation-1.19e+00

Pos logit contributions
orthy+0.626
Years+0.564
terday+0.558
oppy+0.549
ounters+0.542
Neg logit contributions
race-0.441
hibited-0.258
uning-0.234
strate-0.231
ilaterally-0.230
Token
Token ID198
Feature activation+5.41e-01

Pos logit contributions
race+1.132
hibited+0.764
uning+0.719
ilaterally+0.711
strate+0.707
Neg logit contributions
orthy-0.977
terday-0.849
Years-0.846
oppy-0.835
ounters-0.819
Token
Token ID198
Feature activation+2.65e+00

Pos logit contributions
orthy+0.399
Years+0.344
terday+0.337
oppy+0.329
ounters+0.323
Neg logit contributions
race-0.565
hibited-0.400
uning-0.379
ilaterally-0.377
strate-0.376
TokenPrime
Token ID26405
Feature activation-5.74e+00

Pos logit contributions
orthy+2.107
Years+1.847
terday+1.802
oppy+1.766
ounters+1.734
Neg logit contributions
race-2.600
hibited-1.798
uning-1.698
ilaterally-1.685
strate-1.680
Token Minister
Token ID4139
Feature activation+2.23e+00

Pos logit contributions
race+5.126
hibited+3.335
uning+3.223
ilaterally+3.131
strate+3.127
Neg logit contributions
orthy-4.957
terday-4.338
oppy-4.311
Years-4.299
ounters-4.213
Token Trudeau
Token ID17524
Feature activation+1.01e+00

Pos logit contributions
orthy+1.556
Years+1.329
terday+1.301
oppy+1.266
ounters+1.244
Neg logit contributions
race-2.407
hibited-1.740
uning-1.638
strate-1.635
ilaterally-1.634
Token might
Token ID1244
Feature activation+4.97e+00

Pos logit contributions
orthy+0.835
Years+0.732
terday+0.721
oppy+0.708
ounters+0.694
Neg logit contributions
race-0.962
hibited-0.652
uning-0.615
ilaterally-0.609
strate-0.607
Token have
Token ID423
Feature activation+1.37e+00

Pos logit contributions
orthy+0.539
Years+0.470
terday+0.465
oppy+0.455
ounters+0.446
Neg logit contributions
race-0.633
hibited-0.433
uning-0.406
ilaterally-0.404
strate-0.403
Token had
Token ID550
Feature activation-1.72e-02

Pos logit contributions
orthy+1.089
Years+0.945
terday+0.933
oppy+0.914
ounters+0.896
Neg logit contributions
race-1.352
hibited-0.934
uning-0.882
ilaterally-0.874
strate-0.872
Token when
Token ID618
Feature activation-1.98e+00

Pos logit contributions
race+0.017
hibited+0.012
uning+0.011
ilaterally+0.011
strate+0.011
Neg logit contributions
orthy-0.014
Years-0.012
terday-0.012
oppy-0.012
ounters-0.011
Token taking
Token ID2263
Feature activation-5.76e+00

Pos logit contributions
race+1.891
hibited+1.283
uning+1.218
ilaterally+1.205
inary+1.198
Neg logit contributions
orthy-1.629
Years-1.411
terday-1.387
oppy-1.363
ounters-1.333
Token up
Token ID510
Feature activation+3.01e+00

Pos logit contributions
race+5.550
hibited+3.786
ilaterally+3.564
inary+3.496
 Offensive+3.494
Neg logit contributions
orthy-4.603
terday-3.917
Years-3.861
oppy-3.829
ounters-3.742
Token these
Token ID777
Feature activation+6.05e-01

Pos logit contributions
orthy+2.361
Years+2.055
terday+2.017
oppy+1.976
ounters+1.940
Neg logit contributions
race-2.997
hibited-2.074
uning-1.965
ilaterally-1.943
strate-1.942
Token principles
Token ID7811
Feature activation-1.84e+00

Pos logit contributions
orthy+0.459
Years+0.395
terday+0.393
oppy+0.383
ounters+0.375
Neg logit contributions
race-0.618
hibited-0.434
uning-0.409
ilaterally-0.407
strate-0.405
Token shown
Token ID3402
Feature activation-5.22e+00

Pos logit contributions
race+1.685
hibited+1.132
uning+1.054
ilaterally+1.054
strate+1.049
Neg logit contributions
orthy-1.582
Years-1.380
terday-1.371
oppy-1.353
ounters-1.320
Token by
Token ID416
Feature activation+5.68e-01

Pos logit contributions
race+4.750
hibited+3.219
ilaterally+2.942
strate+2.921
uning+2.916
Neg logit contributions
orthy-4.419
Years-3.864
terday-3.851
oppy-3.841
ounters-3.712
Token S
Token ID311
Feature activation+1.72e+00

Pos logit contributions
orthy+0.432
Years+0.371
terday+0.366
oppy+0.358
ounters+0.352
Neg logit contributions
race-0.582
hibited-0.408
uning-0.386
ilaterally-0.383
strate-0.383
Tokenif
Token ID361
Feature activation-2.45e+00

Pos logit contributions
orthy+1.444
Years+1.267
terday+1.248
oppy+1.224
ounters+1.204
Neg logit contributions
race-1.618
hibited-1.092
uning-1.027
ilaterally-1.017
strate-1.015
Token-
Token ID12
Feature activation+5.41e+00

Pos logit contributions
orthy+3.957
Years+3.502
oppy+3.381
terday+3.363
ounters+3.296
Neg logit contributions
race-4.815
hibited-3.348
ilaterally-3.143
strate-3.120
uning-3.116
Tokenworking
Token ID16090
Feature activation+9.95e-01

Pos logit contributions
orthy+4.558
Years+4.124
oppy+3.961
terday+3.918
onder+3.879
Neg logit contributions
race-4.750
hibited-3.247
ilaterally-3.007
uning-2.990
strate-2.987
Token crew
Token ID5462
Feature activation+9.13e-01

Pos logit contributions
orthy+0.777
Years+0.672
terday+0.663
oppy+0.647
ounters+0.637
Neg logit contributions
race-1.000
hibited-0.693
uning-0.656
strate-0.649
ilaterally-0.649
Token from
Token ID422
Feature activation+2.32e+00

Pos logit contributions
orthy+0.708
Years+0.614
terday+0.604
oppy+0.592
ounters+0.581
Neg logit contributions
race-0.918
hibited-0.640
uning-0.604
ilaterally-0.600
strate-0.598
Token his
Token ID465
Feature activation+2.18e+00

Pos logit contributions
orthy+1.817
Years+1.587
terday+1.555
oppy+1.528
ounters+1.500
Neg logit contributions
race-2.301
hibited-1.598
uning-1.509
ilaterally-1.500
strate-1.495
Token TV
Token ID3195
Feature activation+3.44e+00

Pos logit contributions
orthy+1.672
Years+1.447
terday+1.425
oppy+1.394
ounters+1.368
Neg logit contributions
race-2.203
hibited-1.538
uning-1.455
ilaterally-1.443
strate-1.441
Token show
Token ID905
Feature activation+6.38e+00

Pos logit contributions
orthy+2.633
Years+2.291
terday+2.233
oppy+2.199
ounters+2.163
Neg logit contributions
race-3.472
hibited-2.427
uning-2.289
ilaterally-2.287
strate-2.281
Token,
Token ID11
Feature activation+3.99e+00

Pos logit contributions
orthy+4.906
Years+4.360
terday+4.169
oppy+4.142
ounters+4.134
Neg logit contributions
race-6.149
hibited-4.304
ilaterally-4.085
uning-4.062
strate-4.007
Token Alfred
Token ID22044
Feature activation-2.38e+00

Pos logit contributions
orthy+3.120
Years+2.752
terday+2.664
oppy+2.635
ounters+2.602
Neg logit contributions
race-3.915
hibited-2.714
uning-2.562
ilaterally-2.559
strate-2.546
TokenH
Token ID39
Feature activation+3.60e+00

Pos logit contributions
race+2.176
hibited+1.438
uning+1.356
strate+1.348
inary+1.335
Neg logit contributions
orthy-2.072
terday-1.811
Years-1.773
oppy-1.756
ounters-1.722
Tokenitch
Token ID2007
Feature activation+6.39e+00

Pos logit contributions
orthy+2.332
Years+1.946
terday+1.900
oppy+1.877
ounters+1.823
Neg logit contributions
race-4.075
hibited-2.983
uning-2.834
strate-2.823
ilaterally-2.822
Token a
Token ID257
Feature activation-9.33e-01

Pos logit contributions
orthy+2.042
Years+1.774
terday+1.747
oppy+1.708
ounters+1.680
Neg logit contributions
race-2.608
hibited-1.811
uning-1.710
ilaterally-1.697
strate-1.695
Token veteran
Token ID9298
Feature activation+1.98e-03

Pos logit contributions
race+0.922
hibited+0.638
uning+0.602
ilaterally+0.592
strate+0.589
Neg logit contributions
orthy-0.738
Years-0.647
terday-0.633
oppy-0.619
ounters-0.609
Token safety
Token ID3747
Feature activation+2.91e+00

Pos logit contributions
orthy+0.002
Years+0.001
terday+0.001
oppy+0.001
ounters+0.001
Neg logit contributions
race-0.002
hibited-0.001
uning-0.001
strate-0.001
ilaterally-0.001
Token expert
Token ID5887
Feature activation-2.46e+00

Pos logit contributions
orthy+2.085
Years+1.783
terday+1.755
oppy+1.713
ounters+1.679
Neg logit contributions
race-3.087
hibited-2.200
uning-2.088
ilaterally-2.075
strate-2.067
Token e
Token ID304
Feature activation-1.87e+00

Pos logit contributions
race+2.285
hibited+1.524
uning+1.459
ilaterally+1.425
strate+1.420
Neg logit contributions
orthy-2.085
Years-1.832
terday-1.800
oppy-1.784
ounters-1.712
Token-
Token ID12
Feature activation+4.14e+00

Pos logit contributions
race+1.671
hibited+1.114
uning+1.042
ilaterally+1.022
inary+1.021
Neg logit contributions
orthy-1.658
Years-1.453
terday-1.443
oppy-1.417
ounters-1.372
Tokenmail
Token ID4529
Feature activation-8.89e-01

Pos logit contributions
orthy+2.804
Years+2.402
terday+2.344
oppy+2.288
ounters+2.259
Neg logit contributions
race-4.514
hibited-3.254
uning-3.101
strate-3.082
ilaterally-3.069
Tokened
Token ID276
Feature activation-7.46e-01

Pos logit contributions
race+0.862
hibited+0.595
uning+0.560
strate+0.554
ilaterally+0.554
Neg logit contributions
orthy-0.722
Years-0.627
terday-0.620
oppy-0.609
ounters-0.592
Token NASA
Token ID8884
Feature activation+2.98e+00

Pos logit contributions
race+0.741
hibited+0.513
uning+0.485
strate+0.480
ilaterally+0.479
Neg logit contributions
orthy-0.590
Years-0.510
terday-0.501
oppy-0.496
ounters-0.484
Token's
Token ID338
Feature activation+2.87e+00

Pos logit contributions
orthy+2.384
Years+2.080
terday+2.047
oppy+2.003
ounters+1.970
Neg logit contributions
race-2.907
hibited-1.995
uning-1.884
ilaterally-1.874
strate-1.862
Token chief
Token ID4039
Feature activation-2.76e+00

Pos logit contributions
orthy+2.115
Years+1.821
terday+1.790
oppy+1.750
ounters+1.714
Neg logit contributions
race-2.995
hibited-2.116
uning-2.007
ilaterally-1.998
strate-1.991
Token the
Token ID262
Feature activation+3.29e+00

Pos logit contributions
orthy+2.824
Years+2.423
terday+2.378
oppy+2.341
ounters+2.288
Neg logit contributions
race-4.220
hibited-3.018
uning-2.847
ilaterally-2.846
strate-2.825
Token fire
Token ID2046
Feature activation+1.46e+00

Pos logit contributions
orthy+2.483
Years+2.147
terday+2.108
oppy+2.069
ounters+2.025
Neg logit contributions
race-3.352
hibited-2.357
uning-2.228
strate-2.211
ilaterally-2.209
Token and
Token ID290
Feature activation-1.21e+00

Pos logit contributions
orthy+1.197
Years+1.046
terday+1.030
oppy+1.010
ounters+0.993
Neg logit contributions
race-1.406
hibited-0.961
uning-0.903
ilaterally-0.896
strate-0.896
Token called
Token ID1444
Feature activation+5.13e+00

Pos logit contributions
race+1.169
hibited+0.797
uning+0.751
strate+0.746
ilaterally+0.743
Neg logit contributions
orthy-0.991
Years-0.862
terday-0.852
oppy-0.829
ounters-0.814
Token 911
Token ID16679
Feature activation-2.53e+00

Pos logit contributions
orthy+2.842
Years+2.346
terday+2.295
oppy+2.219
ounters+2.164
Neg logit contributions
race-6.178
hibited-4.635
uning-4.443
ilaterally-4.406
strate-4.393
Token.
Token ID13
Feature activation+2.08e+00

Pos logit contributions
race+2.354
hibited+1.572
uning+1.497
ilaterally+1.478
strate+1.463
Neg logit contributions
orthy-2.147
Years-1.877
terday-1.833
oppy-1.815
ounters-1.777
Token Dep
Token ID2129
Feature activation-5.04e+00

Pos logit contributions
orthy+1.631
Years+1.421
terday+1.395
oppy+1.366
ounters+1.344
Neg logit contributions
race-2.066
hibited-1.431
uning-1.353
ilaterally-1.343
strate-1.339
Tokenuties
Token ID8249
Feature activation+1.69e+00

Pos logit contributions
race+4.237
hibited+2.642
uning+2.488
strate+2.416
inary+2.366
Neg logit contributions
orthy-4.645
Years-4.234
terday-4.222
oppy-3.988
ounters-3.946
Token found
Token ID1043
Feature activation-8.10e+00

Pos logit contributions
orthy+1.391
Years+1.216
terday+1.204
oppy+1.176
ounters+1.160
Neg logit contributions
race-1.605
hibited-1.096
uning-1.027
strate-1.021
ilaterally-1.020
Token scor
Token ID34203
Feature activation-4.13e-01

Pos logit contributions
race+7.619
hibited+5.220
uning+4.983
strate+4.939
 Offensive+4.916
Neg logit contributions
orthy-6.322
Years-5.540
terday-5.509
oppy-5.228
ounters-5.209
Tokench
Token ID354
Feature activation-2.59e-01

Pos logit contributions
race+0.408
hibited+0.281
uning+0.266
strate+0.263
ilaterally+0.262
Neg logit contributions
orthy-0.328
Years-0.287
terday-0.283
oppy-0.275
ounters-0.270
Tokening
Token ID278
Feature activation+1.46e+00

Pos logit contributions
orthy+3.246
Years+2.808
oppy+2.796
terday+2.710
ounters+2.679
Neg logit contributions
race-3.793
hibited-2.633
uning-2.474
ilaterally-2.466
strate-2.464
Tokenway
Token ID1014
Feature activation+2.63e+00

Pos logit contributions
orthy+0.975
Years+0.824
terday+0.808
oppy+0.788
ounters+0.770
Neg logit contributions
race-1.631
hibited-1.185
uning-1.130
ilaterally-1.121
strate-1.119
Token book
Token ID1492
Feature activation-2.82e+00

Pos logit contributions
orthy+1.976
Years+1.708
terday+1.673
oppy+1.641
ounters+1.608
Neg logit contributions
race-2.710
hibited-1.905
uning-1.805
ilaterally-1.796
strate-1.788
Token to
Token ID284
Feature activation+5.13e-01

Pos logit contributions
race+2.707
hibited+1.836
uning+1.716
strate+1.706
ilaterally+1.688
Neg logit contributions
orthy-2.325
Years-2.008
terday-2.003
oppy-1.951
ounters-1.915
Token get
Token ID651
Feature activation+1.37e+00

Pos logit contributions
orthy+0.396
Years+0.342
terday+0.337
oppy+0.328
ounters+0.324
Neg logit contributions
race-0.521
hibited-0.362
uning-0.343
strate-0.341
ilaterally-0.339
Token it
Token ID340
Feature activation-1.73e-01

Pos logit contributions
orthy+1.085
Years+0.943
terday+0.929
oppy+0.909
ounters+0.893
Neg logit contributions
race-1.356
hibited-0.937
uning-0.885
ilaterally-0.877
strate-0.876
Token started
Token ID2067
Feature activation+6.84e-02

Pos logit contributions
race+0.174
hibited+0.120
uning+0.113
ilaterally+0.112
strate+0.112
Neg logit contributions
orthy-0.136
Years-0.118
terday-0.116
oppy-0.113
ounters-0.112
Token what
Token ID644
Feature activation-2.40e+00

Pos logit contributions
orthy+0.057
Years+0.050
terday+0.050
oppy+0.049
ounters+0.048
Neg logit contributions
race-0.065
hibited-0.043
uning-0.041
ilaterally-0.041
strate-0.040
Token a
Token ID257
Feature activation+1.10e-01

Pos logit contributions
race+2.305
hibited+1.560
uning+1.465
strate+1.444
inary+1.436
Neg logit contributions
orthy-1.970
Years-1.695
terday-1.660
oppy-1.651
ounters-1.624
Token lifes
Token ID25622
Feature activation-1.19e+00

Pos logit contributions
orthy+0.082
Years+0.070
terday+0.069
oppy+0.067
ounters+0.067
Neg logit contributions
race-0.114
hibited-0.080
uning-0.076
ilaterally-0.075
strate-0.075
Tokenaver
Token ID8770
Feature activation+1.79e+00

Pos logit contributions
race+1.013
hibited+0.650
uning+0.606
strate+0.594
ilaterally+0.592
Neg logit contributions
orthy-1.102
Years-0.982
terday-0.966
oppy-0.948
ounters-0.941
Tokenashes
Token ID7465
Feature activation+9.74e-01

Pos logit contributions
orthy+0.606
Years+0.531
terday+0.525
oppy+0.513
ounters+0.504
Neg logit contributions
race-0.685
hibited-0.463
uning-0.436
ilaterally-0.432
strate-0.431
Token And
Token ID843
Feature activation-1.91e+00

Pos logit contributions
orthy+0.815
Years+0.715
terday+0.703
oppy+0.691
ounters+0.679
Neg logit contributions
race-0.922
hibited-0.623
uning-0.587
ilaterally-0.580
strate-0.579
Token Block
Token ID9726
Feature activation+3.02e+00

Pos logit contributions
race+1.857
hibited+1.273
uning+1.201
ilaterally+1.185
inary+1.184
Neg logit contributions
orthy-1.538
Years-1.335
terday-1.329
oppy-1.299
ounters-1.262
Token Basics
Token ID45884
Feature activation-3.38e+00

Pos logit contributions
orthy+2.478
Years+2.179
terday+2.127
oppy+2.095
ounters+2.073
Neg logit contributions
race-2.882
hibited-1.970
uning-1.845
ilaterally-1.832
strate-1.824
Token.
Token ID13
Feature activation-2.49e-02

Pos logit contributions
race+3.078
hibited+2.036
uning+1.943
ilaterally+1.908
strate+1.898
Neg logit contributions
orthy-2.911
Years-2.542
terday-2.518
oppy-2.503
ounters-2.428
Token I
Token ID314
Feature activation-2.51e+00

Pos logit contributions
race+0.024
hibited+0.016
uning+0.015
strate+0.015
ilaterally+0.015
Neg logit contributions
orthy-0.020
Years-0.018
terday-0.018
oppy-0.017
ounters-0.017
Token mentioned
Token ID4750
Feature activation-2.15e+00

Pos logit contributions
race+2.287
hibited+1.527
uning+1.427
strate+1.415
ilaterally+1.402
Neg logit contributions
orthy-2.156
Years-1.910
terday-1.879
oppy-1.837
ounters-1.796
Token that
Token ID326
Feature activation-2.71e+00

Pos logit contributions
race+2.013
hibited+1.340
uning+1.272
ilaterally+1.256
inary+1.252
Neg logit contributions
orthy-1.816
Years-1.584
terday-1.552
oppy-1.539
ounters-1.505
Token blocks
Token ID7021
Feature activation+1.39e+00

Pos logit contributions
race+2.593
hibited+1.743
uning+1.660
inary+1.638
ilaterally+1.636
Neg logit contributions
orthy-2.228
Years-1.936
terday-1.897
oppy-1.868
ounters-1.827
Token are
Token ID389
Feature activation-5.11e-01

Pos logit contributions
orthy+1.126
Years+0.982
terday+0.965
oppy+0.947
ounters+0.931
Neg logit contributions
race-1.356
hibited-0.929
uning-0.877
ilaterally-0.868
strate-0.867
Token not
Token ID407
Feature activation-5.66e+00

Pos logit contributions
race+0.492
hibited+0.336
uning+0.316
ilaterally+0.313
strate+0.312
Neg logit contributions
orthy-0.418
Years-0.365
terday-0.359
oppy-0.353
ounters-0.346
Token adult
Token ID4044
Feature activation-4.23e+00

Pos logit contributions
race+2.559
hibited+1.839
uning+1.740
ilaterally+1.731
 Offensive+1.719
Neg logit contributions
orthy-1.690
Years-1.484
terday-1.427
oppy-1.394
ounters-1.378
Token male
Token ID4257
Feature activation-1.27e+00

Pos logit contributions
race+3.748
hibited+2.431
uning+2.282
inary+2.240
 Offensive+2.233
Neg logit contributions
orthy-3.697
Years-3.375
terday-3.305
oppy-3.239
ounters-3.152
Token engaged
Token ID7953
Feature activation+1.35e+00

Pos logit contributions
race+1.230
hibited+0.838
uning+0.789
ilaterally+0.786
strate+0.778
Neg logit contributions
orthy-1.036
Years-0.912
terday-0.898
oppy-0.881
ounters-0.861
Token these
Token ID777
Feature activation-2.46e-02

Pos logit contributions
orthy+1.039
Years+0.898
terday+0.884
oppy+0.865
ounters+0.850
Neg logit contributions
race-1.369
hibited-0.956
uning-0.906
ilaterally-0.897
strate-0.895
Token officers
Token ID3790
Feature activation-9.59e-01

Pos logit contributions
race+0.026
hibited+0.018
uning+0.017
ilaterally+0.017
strate+0.017
Neg logit contributions
orthy-0.018
Years-0.016
terday-0.015
oppy-0.015
ounters-0.014
Token with
Token ID351
Feature activation-4.97e+00

Pos logit contributions
race+0.903
hibited+0.608
ilaterally+0.571
uning+0.570
strate+0.563
Neg logit contributions
orthy-0.807
Years-0.711
terday-0.693
oppy-0.683
ounters-0.672
Token a
Token ID257
Feature activation-4.40e+00

Pos logit contributions
race+4.581
hibited+3.161
ilaterally+2.923
uning+2.913
strate+2.899
Neg logit contributions
orthy-4.183
Years-3.664
terday-3.610
oppy-3.533
ounters-3.515
Token handgun
Token ID17849
Feature activation-6.80e+00

Pos logit contributions
race+4.007
hibited+2.749
uning+2.534
ilaterally+2.509
strate+2.509
Neg logit contributions
orthy-3.764
terday-3.323
Years-3.323
oppy-3.226
ounters-3.173
Token and
Token ID290
Feature activation-6.64e+00

Pos logit contributions
race+5.640
hibited+3.657
ilaterally+3.354
uning+3.292
strate+3.209
Neg logit contributions
orthy-6.227
Years-5.627
terday-5.437
oppy-5.424
ounters-5.327
Token began
Token ID2540
Feature activation-3.01e+00

Pos logit contributions
race+5.697
hibited+3.781
ilaterally+3.540
 Offensive+3.506
strate+3.425
Neg logit contributions
orthy-5.851
Years-5.159
terday-5.132
oppy-5.064
ounters-4.900
Token firing
Token ID9645
Feature activation-3.05e+00

Pos logit contributions
race+2.928
hibited+2.052
uning+1.902
strate+1.896
ilaterally+1.888
Neg logit contributions
orthy-2.429
Years-2.102
terday-2.086
oppy-2.044
ounters-1.982
Token).
Token ID737
Feature activation-3.51e+00

Pos logit contributions
orthy+0.864
Years+0.765
terday+0.756
oppy+0.741
ounters+0.732
Neg logit contributions
race-0.812
hibited-0.525
uning-0.488
ilaterally-0.483
strate-0.483
Token The
Token ID383
Feature activation-3.25e+00

Pos logit contributions
race+3.283
hibited+2.239
uning+2.087
 Offensive+2.062
COR+2.043
Neg logit contributions
orthy-2.909
terday-2.540
Years-2.518
oppy-2.499
ounters-2.441
Token defects
Token ID22448
Feature activation+1.21e+00

Pos logit contributions
race+3.247
hibited+2.269
uning+2.143
strate+2.119
inary+2.092
Neg logit contributions
orthy-2.496
Years-2.171
terday-2.143
oppy-2.098
ounters-2.039
Token of
Token ID286
Feature activation+6.14e-01

Pos logit contributions
orthy+0.947
Years+0.822
terday+0.810
oppy+0.793
ounters+0.779
Neg logit contributions
race-1.208
hibited-0.839
uning-0.791
ilaterally-0.785
strate-0.784
Token sonic
Token ID36220
Feature activation+2.09e+00

Pos logit contributions
orthy+0.485
Years+0.421
terday+0.415
oppy+0.406
ounters+0.399
Neg logit contributions
race-0.610
hibited-0.422
uning-0.399
ilaterally-0.395
strate-0.394
Token technology
Token ID3037
Feature activation+2.43e-01

Pos logit contributions
orthy+1.650
Years+1.432
terday+1.408
oppy+1.383
ounters+1.360
Neg logit contributions
race-2.069
hibited-1.432
uning-1.352
ilaterally-1.342
strate-1.340
Token that
Token ID326
Feature activation-1.91e-01

Pos logit contributions
orthy+0.199
Years+0.174
terday+0.172
oppy+0.169
ounters+0.165
Neg logit contributions
race-0.234
hibited-0.160
uning-0.150
strate-0.149
ilaterally-0.149
Token become
Token ID1716
Feature activation+2.29e+00

Pos logit contributions
race+0.186
hibited+0.128
uning+0.120
strate+0.119
ilaterally+0.119
Neg logit contributions
orthy-0.155
Years-0.135
terday-0.132
oppy-0.130
ounters-0.128
Token encoded
Token ID30240
Feature activation+1.36e+00

Pos logit contributions
orthy+1.850
Years+1.613
terday+1.588
oppy+1.552
ounters+1.529
Neg logit contributions
race-2.230
hibited-1.526
uning-1.444
ilaterally-1.431
strate-1.425
Token in
Token ID287
Feature activation+2.40e+00

Pos logit contributions
orthy+1.078
Years+0.937
terday+0.923
oppy+0.903
ounters+0.888
Neg logit contributions
race-1.352
hibited-0.935
uning-0.883
ilaterally-0.875
strate-0.874
Token digital
Token ID4875
Feature activation+4.87e+00

Pos logit contributions
orthy+1.857
Years+1.611
terday+1.586
oppy+1.559
ounters+1.525
Neg logit contributions
race-2.404
hibited-1.662
uning-1.578
ilaterally-1.571
strate-1.562
Token (
Token ID357
Feature activation-3.63e-01

Pos logit contributions
race+1.490
hibited+0.999
uning+0.934
strate+0.934
 Offensive+0.926
Neg logit contributions
orthy-1.346
terday-1.163
Years-1.158
oppy-1.140
ounters-1.119
TokenIt
Token ID1026
Feature activation-2.17e+00

Pos logit contributions
race+0.339
hibited+0.226
uning+0.212
strate+0.209
COR+0.209
Neg logit contributions
orthy-0.310
terday-0.270
Years-0.266
oppy-0.264
ounters-0.260
Token's
Token ID338
Feature activation+9.56e-01

Pos logit contributions
race+2.004
hibited+1.339
uning+1.283
ilaterally+1.229
inary+1.227
Neg logit contributions
orthy-1.844
Years-1.635
terday-1.583
oppy-1.564
ounters-1.531
Token a
Token ID257
Feature activation-1.23e+00

Pos logit contributions
orthy+0.769
Years+0.670
terday+0.659
oppy+0.646
ounters+0.636
Neg logit contributions
race-0.937
hibited-0.643
uning-0.609
ilaterally-0.600
strate-0.600
Token good
Token ID922
Feature activation-3.73e+00

Pos logit contributions
race+1.262
hibited+0.879
uning+0.843
strate+0.824
ilaterally+0.823
Neg logit contributions
orthy-0.930
Years-0.805
terday-0.785
oppy-0.767
ounters-0.763
Token idea
Token ID2126
Feature activation-1.45e+00

Pos logit contributions
race+3.461
hibited+2.247
uning+2.194
strate+2.146
inary+2.087
Neg logit contributions
orthy-3.163
Years-2.769
oppy-2.688
terday-2.682
ounters-2.672
Token to
Token ID284
Feature activation-3.60e+00

Pos logit contributions
race+1.446
hibited+0.998
uning+0.955
strate+0.934
ilaterally+0.929
Neg logit contributions
orthy-1.136
Years-0.989
terday-0.967
oppy-0.948
ounters-0.930
Token dip
Token ID19550
Feature activation-2.61e+00

Pos logit contributions
race+3.403
hibited+2.239
uning+2.160
strate+2.130
inary+2.125
Neg logit contributions
orthy-2.983
Years-2.644
terday-2.550
oppy-2.539
ounters-2.481
Token these
Token ID777
Feature activation+1.63e-01

Pos logit contributions
race+2.517
hibited+1.692
uning+1.639
strate+1.605
ilaterally+1.597
Neg logit contributions
orthy-2.128
Years-1.855
terday-1.807
oppy-1.776
ounters-1.766
Token in
Token ID287
Feature activation-6.40e-01

Pos logit contributions
orthy+0.130
Years+0.113
terday+0.111
oppy+0.109
ounters+0.108
Neg logit contributions
race-0.160
hibited-0.109
uning-0.105
ilaterally-0.103
strate-0.103
Token boiling
Token ID24372
Feature activation-2.77e+00

Pos logit contributions
race+0.658
hibited+0.458
uning+0.436
strate+0.432
ilaterally+0.430
Neg logit contributions
orthy-0.486
Years-0.420
terday-0.411
oppy-0.401
ounters-0.397
Token 58
Token ID7618
Feature activation+3.07e+00

Pos logit contributions
race+0.648
hibited+0.443
uning+0.416
ilaterally+0.412
strate+0.411
Neg logit contributions
orthy-0.549
Years-0.478
terday-0.471
oppy-0.462
ounters-0.453
Token per
Token ID583
Feature activation+9.54e-01

Pos logit contributions
orthy+1.772
Years+1.443
terday+1.404
oppy+1.377
onder+1.338
Neg logit contributions
race-3.658
hibited-2.722
uning-2.637
strate-2.630
ilaterally-2.618
Token cent
Token ID1247
Feature activation-2.89e+00

Pos logit contributions
orthy+0.424
Years+0.326
terday+0.316
oppy+0.303
ounters+0.292
Neg logit contributions
race-1.273
hibited-0.982
uning-0.946
ilaterally-0.942
strate-0.939
Token in
Token ID287
Feature activation-5.55e-01

Pos logit contributions
race+2.914
hibited+2.008
uning+1.894
inary+1.876
ilaterally+1.864
Neg logit contributions
orthy-2.268
Years-1.945
terday-1.920
oppy-1.887
ounters-1.837
Token the
Token ID262
Feature activation-8.74e-01

Pos logit contributions
race+0.564
hibited+0.394
uning+0.372
ilaterally+0.369
strate+0.368
Neg logit contributions
orthy-0.426
Years-0.369
terday-0.364
oppy-0.355
ounters-0.350
Token rest
Token ID1334
Feature activation-9.08e+00

Pos logit contributions
race+0.838
hibited+0.568
uning+0.534
ilaterally+0.528
strate+0.527
Neg logit contributions
orthy-0.724
Years-0.633
terday-0.625
oppy-0.611
ounters-0.600
Token of
Token ID286
Feature activation-6.29e+00

Pos logit contributions
race+8.811
hibited+5.927
inary+5.622
uning+5.621
strate+5.562
Neg logit contributions
orthy-6.938
Years-6.066
terday-6.012
oppy-5.825
ounters-5.726
Token Canada
Token ID3340
Feature activation-4.52e+00

Pos logit contributions
race+5.989
hibited+4.142
ilaterally+3.812
uning+3.797
strate+3.784
Neg logit contributions
orthy-5.039
Years-4.477
terday-4.388
oppy-4.279
ounters-4.240
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
race+4.003
hibited+2.593
uning+2.434
ilaterally+2.393
strate+2.386
Neg logit contributions
orthy-3.993
Years-3.558
terday-3.504
oppy-3.458
ounters-3.351
Token
Token ID198
Feature activation-4.25e-01

Pos logit contributions
race+1.491
hibited+1.014
uning+0.947
COR+0.935
strate+0.929
Neg logit contributions
orthy-1.300
terday-1.117
Years-1.116
oppy-1.101
ounters-1.080
Token
Token ID198
Feature activation+8.28e-01

Pos logit contributions
race+0.436
hibited+0.305
uning+0.288
strate+0.286
ilaterally+0.285
Neg logit contributions
orthy-0.323
Years-0.277
terday-0.275
oppy-0.269
ounters-0.263
Token once
Token ID1752
Feature activation+3.88e+00

Pos logit contributions
orthy+2.062
Years+1.780
terday+1.757
oppy+1.714
ounters+1.682
Neg logit contributions
race-2.875
hibited-2.033
uning-1.924
ilaterally-1.912
strate-1.910
Token outside
Token ID2354
Feature activation-1.31e+00

Pos logit contributions
orthy+2.796
Years+2.384
terday+2.373
oppy+2.318
ounters+2.268
Neg logit contributions
race-4.067
hibited-2.902
uning-2.752
strate-2.741
ilaterally-2.725
Token she
Token ID673
Feature activation-8.56e-01

Pos logit contributions
race+1.265
hibited+0.866
uning+0.819
strate+0.805
ilaterally+0.798
Neg logit contributions
orthy-1.063
Years-0.937
terday-0.912
oppy-0.895
ounters-0.876
Token was
Token ID373
Feature activation-1.13e+00

Pos logit contributions
race+0.793
hibited+0.532
uning+0.500
ilaterally+0.494
strate+0.490
Neg logit contributions
orthy-0.734
Years-0.646
terday-0.634
oppy-0.621
ounters-0.609
Token seen
Token ID1775
Feature activation-7.23e+00

Pos logit contributions
race+1.049
hibited+0.708
uning+0.662
ilaterally+0.653
strate+0.651
Neg logit contributions
orthy-0.972
Years-0.854
terday-0.843
oppy-0.824
ounters-0.809
Token inspecting
Token ID49889
Feature activation-8.29e+00

Pos logit contributions
race+6.824
hibited+4.680
uning+4.469
ilaterally+4.348
strate+4.317
Neg logit contributions
orthy-5.715
Years-5.024
terday-4.937
oppy-4.808
ounters-4.715
Token the
Token ID262
Feature activation-8.01e-01

Pos logit contributions
race+7.547
hibited+5.108
uning+4.787
inary+4.726
strate+4.717
Neg logit contributions
orthy-6.740
Years-5.978
terday-5.763
ounters-5.625
oppy-5.577
Token bad
Token ID2089
Feature activation-2.42e+00

Pos logit contributions
race+0.758
hibited+0.511
uning+0.480
ilaterally+0.475
strate+0.475
Neg logit contributions
orthy-0.670
Years-0.589
terday-0.580
oppy-0.568
ounters-0.560
Token burn
Token ID4245
Feature activation+3.84e+00

Pos logit contributions
race+2.453
hibited+1.688
uning+1.615
strate+1.594
ilaterally+1.587
Neg logit contributions
orthy-1.867
Years-1.601
terday-1.559
oppy-1.534
ounters-1.505
Token on
Token ID319
Feature activation+2.74e-01

Pos logit contributions
orthy+2.921
Years+2.545
terday+2.492
oppy+2.443
ounters+2.407
Neg logit contributions
race-3.857
hibited-2.699
uning-2.555
ilaterally-2.526
strate-2.513
Token her
Token ID607
Feature activation-3.21e-01

Pos logit contributions
orthy+0.189
Years+0.160
terday+0.157
oppy+0.153
ounters+0.151
Neg logit contributions
race-0.299
hibited-0.215
uning-0.205
ilaterally-0.203
strate-0.203
Token only
Token ID691
Feature activation+4.40e-01

Pos logit contributions
race+1.655
hibited+1.124
uning+1.055
strate+1.048
inary+1.039
Neg logit contributions
orthy-1.415
Years-1.238
terday-1.217
oppy-1.202
ounters-1.179
Token possible
Token ID1744
Feature activation-8.99e-02

Pos logit contributions
orthy+0.356
Years+0.312
terday+0.308
oppy+0.305
ounters+0.297
Neg logit contributions
race-0.425
hibited-0.289
uning-0.274
ilaterally-0.271
strate-0.270
Token if
Token ID611
Feature activation-1.68e+00

Pos logit contributions
race+0.089
hibited+0.062
uning+0.058
ilaterally+0.058
strate+0.058
Neg logit contributions
orthy-0.071
Years-0.062
terday-0.060
oppy-0.060
ounters-0.058
Token you
Token ID345
Feature activation+1.34e+00

Pos logit contributions
race+1.545
hibited+1.020
uning+0.958
strate+0.947
ilaterally+0.945
Neg logit contributions
orthy-1.447
Years-1.277
terday-1.252
oppy-1.230
ounters-1.210
Token can
Token ID460
Feature activation-1.84e-01

Pos logit contributions
orthy+1.039
Years+0.901
terday+0.886
oppy+0.868
ounters+0.852
Neg logit contributions
race-1.353
hibited-0.940
uning-0.889
ilaterally-0.882
strate-0.882
Token find
Token ID1064
Feature activation-7.62e+00

Pos logit contributions
race+0.182
hibited+0.124
uning+0.117
ilaterally+0.117
strate+0.116
Neg logit contributions
orthy-0.147
Years-0.128
terday-0.126
oppy-0.124
ounters-0.121
Token things
Token ID1243
Feature activation-3.85e+00

Pos logit contributions
race+6.804
hibited+4.418
strate+4.173
inary+4.172
uning+4.149
Neg logit contributions
orthy-6.305
Years-5.610
terday-5.501
oppy-5.441
ounters-5.296
Token that
Token ID326
Feature activation-1.12e+00

Pos logit contributions
race+3.417
hibited+2.205
uning+2.049
ilaterally+2.027
strate+2.026
Neg logit contributions
orthy-3.394
Years-3.039
terday-2.940
oppy-2.928
ounters-2.866
Token you
Token ID345
Feature activation-1.62e-01

Pos logit contributions
race+1.071
hibited+0.720
strate+0.674
uning+0.674
ilaterally+0.667
Neg logit contributions
orthy-0.926
Years-0.810
terday-0.793
oppy-0.783
ounters-0.769
Token may
Token ID743
Feature activation+6.88e-01

Pos logit contributions
race+0.159
hibited+0.109
uning+0.102
ilaterally+0.102
strate+0.102
Neg logit contributions
orthy-0.129
Years-0.113
terday-0.111
oppy-0.109
ounters-0.107
Token not
Token ID407
Feature activation-3.03e+00

Pos logit contributions
orthy+0.572
Years+0.502
terday+0.494
oppy+0.485
ounters+0.475
Neg logit contributions
race-0.655
hibited-0.441
uning-0.415
ilaterally-0.412
strate-0.411
Token updated
Token ID6153
Feature activation+1.15e+00

Pos logit contributions
orthy+5.864
Years+5.051
terday+5.007
oppy+4.893
onder+4.859
Neg logit contributions
race-7.919
hibited-5.550
ilaterally-5.314
strate-5.282
inary-5.223
Token with
Token ID351
Feature activation-1.80e+00

Pos logit contributions
orthy+0.918
Years+0.799
terday+0.786
oppy+0.770
ounters+0.756
Neg logit contributions
race-1.129
hibited-0.776
uning-0.734
ilaterally-0.726
strate-0.724
Token any
Token ID597
Feature activation-1.97e+00

Pos logit contributions
race+1.834
hibited+1.264
uning+1.217
inary+1.191
COR+1.184
Neg logit contributions
orthy-1.362
Years-1.182
terday-1.133
oppy-1.122
ounters-1.119
Token information
Token ID1321
Feature activation-5.02e+00

Pos logit contributions
race+1.995
hibited+1.373
uning+1.330
COR+1.294
inary+1.288
Neg logit contributions
orthy-1.482
Years-1.306
oppy-1.247
terday-1.242
ounters-1.226
Token we
Token ID356
Feature activation-4.87e+00

Pos logit contributions
race+4.231
hibited+2.649
uning+2.522
COR+2.481
inary+2.450
Neg logit contributions
orthy-4.603
Years-4.096
terday-4.029
oppy-4.010
ounters-3.899
Token receive
Token ID3328
Feature activation-8.31e+00

Pos logit contributions
race+4.544
hibited+2.895
strate+2.861
inary+2.799
acqu+2.754
Neg logit contributions
orthy-4.014
terday-3.570
Years-3.554
oppy-3.504
ounters-3.324
Token.
Token ID13
Feature activation-2.79e+00

Pos logit contributions
race+6.611
hibited+4.052
uning+3.945
ilaterally+3.786
COR+3.747
Neg logit contributions
orthy-7.530
Years-6.741
oppy-6.660
terday-6.504
ounters-6.443
Token
Token ID198
Feature activation-1.14e+00

Pos logit contributions
race+2.669
hibited+1.806
uning+1.723
COR+1.695
 Offensive+1.684
Neg logit contributions
orthy-2.274
Years-1.959
terday-1.948
oppy-1.920
ounters-1.888
Token
Token ID198
Feature activation-4.43e-01

Pos logit contributions
race+1.153
hibited+0.801
uning+0.756
strate+0.748
ilaterally+0.741
Neg logit contributions
orthy-0.887
terday-0.758
Years-0.758
oppy-0.740
ounters-0.723
TokenThe
Token ID464
Feature activation-1.37e+00

Pos logit contributions
race+0.424
hibited+0.286
uning+0.270
strate+0.266
COR+0.266
Neg logit contributions
orthy-0.368
terday-0.319
Years-0.318
oppy-0.311
ounters-0.307
Token St
Token ID520
Feature activation-2.51e-01

Pos logit contributions
race+1.389
hibited+0.960
uning+0.915
ilaterally+0.898
strate+0.894
Neg logit contributions
orthy-1.052
Years-0.914
terday-0.892
oppy-0.880
ounters-0.870
Token meet
Token ID1826
Feature activation+4.20e+00

Pos logit contributions
race+1.799
hibited+1.237
uning+1.166
strate+1.161
ilaterally+1.149
Neg logit contributions
orthy-1.466
Years-1.270
terday-1.264
oppy-1.227
ounters-1.206
Token in
Token ID287
Feature activation+3.47e+00

Pos logit contributions
orthy+3.112
Years+2.682
terday+2.640
oppy+2.593
ounters+2.532
Neg logit contributions
race-4.317
hibited-3.056
uning-2.882
ilaterally-2.879
strate-2.863
Token the
Token ID262
Feature activation+3.91e+00

Pos logit contributions
orthy+2.494
Years+2.138
terday+2.081
oppy+2.064
ounters+2.003
Neg logit contributions
race-3.658
hibited-2.585
uning-2.464
ilaterally-2.456
strate-2.452
Token Sword
Token ID11535
Feature activation-4.45e+00

Pos logit contributions
orthy+2.928
Years+2.539
terday+2.463
oppy+2.431
ounters+2.366
Neg logit contributions
race-3.981
hibited-2.792
uning-2.651
ilaterally-2.639
strate-2.622
Token-
Token ID12
Feature activation-4.26e+00

Pos logit contributions
race+4.754
hibited+3.387
uning+3.205
strate+3.200
inary+3.179
Neg logit contributions
orthy-3.132
terday-2.678
Years-2.672
oppy-2.601
ounters-2.551
TokenArt
Token ID8001
Feature activation-9.98e+00

Pos logit contributions
race+4.420
hibited+3.075
strate+2.922
uning+2.912
COR+2.874
Neg logit contributions
orthy-3.132
terday-2.718
Years-2.641
oppy-2.628
ounters-2.582
Token Festival
Token ID11117
Feature activation-2.69e+00

Pos logit contributions
race+5.398
hibited+2.519
 Offensive+2.157
inary+2.124
uning+2.081
Neg logit contributions
orthy-11.589
terday-10.654
Years-10.598
oppy-10.557
ounters-10.419
Token finals
Token ID18576
Feature activation+9.82e-01

Pos logit contributions
race+2.568
hibited+1.738
uning+1.651
strate+1.616
 Offensive+1.616
Neg logit contributions
orthy-2.200
terday-1.936
Years-1.927
oppy-1.879
ounters-1.836
Token.
Token ID13
Feature activation+3.26e+00

Pos logit contributions
orthy+0.809
Years+0.707
terday+0.698
oppy+0.685
ounters+0.672
Neg logit contributions
race-0.942
hibited-0.641
uning-0.604
ilaterally-0.597
strate-0.595
Token That
Token ID1320
Feature activation+9.85e-01

Pos logit contributions
orthy+2.527
Years+2.210
terday+2.154
oppy+2.103
ounters+2.070
Neg logit contributions
race-3.269
hibited-2.265
uning-2.148
ilaterally-2.142
strate-2.135
Token was
Token ID373
Feature activation+7.37e+00

Pos logit contributions
orthy+0.804
Years+0.703
terday+0.692
oppy+0.678
ounters+0.668
Neg logit contributions
race-0.952
hibited-0.650
uning-0.612
ilaterally-0.606
strate-0.606