TOP ACTIVATIONS
MAX = 12.742

( 132 s )} B d 7 { ( 507 s
unanswered goals through Kyle Bro d zi ak ( 4 :
When a board is cl oned , any modification of the
should get less than 10 years in prison MORE , in
bin / iw config w l x 001 f 1 f
Center in Washington , D . C ., who wrote a
the curly brace syntax e . g .: ruby
is not a problem e . g .: ruby
supposedly incor rupt ible white - collar division has leaked sensitive
should get less than 10 years in prison MORE and Hillary
R aj appa B hatt ar 9 44 20 30
s )} 9 . B g 5 { ( 8 65
the distance traveled over the time taken , Earth 's speed
c v 2 . COL OR _ B GR 2 G
( 6 s )} B c 6 { ( 153 s
rebutt als toward cliché bo hem ian ideals that have been
s )} 4 . B g 2 { ( 0 s
been so successful at Bro d ard . A decade ago
go ahead late on the power - play however Jake Allen
Comedy Louis C . K . Louie FX Mind

MIN ACTIVATIONS
MIN = -13.537

always see completely eye to eye on things , but on
aur # 2 Had ros aur # 2
stranger s apartment and hide under his bed ,
Free = 80 ) 27 " 1 ms G
other words : One plus one equals " That 's unfair
didn t seem f azed . While
About Dw ark adh ish Temple Here 8 .
s talk THE FANT AST IC F OUR !
Free = 80 ) 27 " 12 ms G
35 z 1 GER ON IM O T OC IN IT
OD = Normal ) 27 " 1 ms G
See the full list of previous award winners .
aur # 2 Had ros aur # 2
grab someone by the ankles and climb on top of them
terms of a qu id pro quo , it
with people one - on - one at scale and our
Time = Normal ) 27 " 8 ms G
struggling but I cannot f athom why you , someone
$ ($ _. Exception . Message )" break } } End
15 of 15 Photo : Erin Bre th auer , The

INTERVAL 6.172 - 12.742
CONTAINS 0.402%

4 ) DOI : 10 . 10 86 / 34 110
- 08 Election - Larry King R aps - Black President
illion aire Koch brothers bank roll attacks on climate change science
7 consecutive days decreased sexual behavior . These results indicate
<|endoftext|> Al ain B ad i ou The Fasc is m

INTERVAL -0.397 - 6.172
CONTAINS 58.113%

when she died at one month old . She was
those shows were new series or one - time - only
opy locks , he shines as the dead pan , action
to it , because Google 's Gallery is the best around
than RT prop , so until we reach B DP ,

INTERVAL -6.967 - -0.397
CONTAINS 41.332%

s one thing the Jets really need to happen
would make the populace less likely to vote for a man
medium . For the song , see Legal T ender (
( In fact , transgender activists have talked about Do lez
features of classical theories of rationality make it hard to support

INTERVAL -13.537 - -6.967
CONTAINS 0.152%

I can use it as lap board , and I can
situation . As both the NFL and the NFL PA state
has never released a death toll from the crackdown after troops
ra ha and the entire temple is very beautiful filled with
traff icked across peer to peer and virtual private networks .
Token(
Token ID7
Feature activation+8.15e-01

Pos logit contributions
spot+1.602
amy+1.544
 laps+1.520
ground+1.503
dirty+1.425
Neg logit contributions
�士-6.244
 conclud-5.036
 Debor-4.743
ntil-4.672
\\\\\\\\-4.664
Token132
Token ID19924
Feature activation+1.50e+00

Pos logit contributions
spot+0.530
amy+0.524
 laps+0.519
ground+0.512
ooter+0.504
Neg logit contributions
�士-0.803
 conclud-0.579
 Debor-0.567
\\\\\\\\-0.566
 Russo-0.527
Tokens
Token ID82
Feature activation+1.41e+00

Pos logit contributions
spot+0.987
 laps+0.969
amy+0.968
ground+0.947
ooter+0.926
Neg logit contributions
�士-1.512
 conclud-1.097
 Debor-1.057
\\\\\\\\-1.056
 Russo-0.972
Token)}
Token ID38165
Feature activation+5.34e-01

Pos logit contributions
spot+0.642
amy+0.638
 laps+0.629
ground+0.611
ooter+0.602
Neg logit contributions
�士-1.690
 conclud-1.298
 Debor-1.260
\\\\\\\\-1.252
ntil-1.184
Token B
Token ID347
Feature activation+1.74e+00

Pos logit contributions
spot+0.341
 laps+0.341
amy+0.335
ground+0.330
ooter+0.325
Neg logit contributions
�士-0.537
 conclud-0.383
\\\\\\\\-0.379
 Debor-0.374
 Russo-0.346
Tokend
Token ID67
Feature activation+1.27e+01

Pos logit contributions
spot+1.158
amy+1.146
 laps+1.122
ground+1.116
arten+1.095
Neg logit contributions
�士-1.713
 conclud-1.237
 Debor-1.198
\\\\\\\\-1.196
 Russo-1.117
Token7
Token ID22
Feature activation+4.02e+00

Pos logit contributions
spot+6.826
ground+6.585
 laps+6.444
amy+6.386
ooter+6.304
Neg logit contributions
�士-13.707
 conclud-10.332
\\\\\\\\-10.175
 Debor-9.846
PDATE-9.551
Token {
Token ID1391
Feature activation+5.19e+00

Pos logit contributions
 laps+2.284
spot+2.274
ground+2.247
amy+2.198
ooter+2.174
Neg logit contributions
�士-4.340
 conclud-3.234
\\\\\\\\-3.198
 Debor-3.110
ntil-2.914
Token(
Token ID7
Feature activation+7.91e-01

Pos logit contributions
spot+1.744
amy+1.671
 laps+1.646
ground+1.628
dirty+1.543
Neg logit contributions
�士-7.058
 conclud-5.729
 Debor-5.353
ntil-5.328
\\\\\\\\-5.257
Token507
Token ID35378
Feature activation-1.76e+00

Pos logit contributions
spot+0.515
amy+0.509
 laps+0.505
ground+0.497
ooter+0.490
Neg logit contributions
�士-0.779
 conclud-0.561
 Debor-0.549
\\\\\\\\-0.549
 Russo-0.510
Tokens
Token ID82
Feature activation+2.27e+00

Pos logit contributions
�士+1.619
 Debor+1.127
\\\\\\\\+1.125
 conclud+1.122
 Russo+1.050
Neg logit contributions
spot-1.221
amy-1.209
 laps-1.195
ooter-1.174
arten-1.174
Token unanswered
Token ID34001
Feature activation+1.74e+00

Pos logit contributions
 laps+3.042
spot+3.037
amy+3.004
ground+2.892
 Freedom+2.857
Neg logit contributions
�士-4.483
 conclud-3.184
\\\\\\\\-3.180
 Debor-3.113
utsu-2.840
Token goals
Token ID4661
Feature activation+1.76e+00

Pos logit contributions
 laps+1.155
spot+1.150
amy+1.138
ground+1.110
 Freedom+1.092
Neg logit contributions
�士-1.715
\\\\\\\\-1.218
 conclud-1.212
 Debor-1.196
 Inquisitor-1.098
Token through
Token ID832
Feature activation+1.87e+00

Pos logit contributions
spot+1.160
 laps+1.157
amy+1.139
ground+1.113
arten+1.093
Neg logit contributions
�士-1.767
 conclud-1.238
\\\\\\\\-1.227
 Debor-1.221
 Russo-1.118
Token Kyle
Token ID14316
Feature activation+2.51e+00

Pos logit contributions
 laps+1.224
spot+1.219
amy+1.210
ground+1.177
ooter+1.168
Neg logit contributions
�士-1.832
 conclud-1.302
\\\\\\\\-1.289
 Debor-1.276
 Inquisitor-1.176
Token Bro
Token ID2806
Feature activation+7.41e-01

Pos logit contributions
spot+1.757
amy+1.746
 laps+1.731
ooter+1.693
 Freedom+1.676
Neg logit contributions
�士-2.346
 conclud-1.704
\\\\\\\\-1.629
 Debor-1.598
ntil-1.456
Tokend
Token ID67
Feature activation+1.22e+01

Pos logit contributions
spot+0.397
amy+0.391
 laps+0.377
ground+0.364
ooter+0.363
Neg logit contributions
�士-0.838
 conclud-0.644
\\\\\\\\-0.623
 Debor-0.619
 Inquisitor-0.576
Tokenzi
Token ID17027
Feature activation+4.97e+00

Pos logit contributions
amy+7.376
spot+7.345
ground+7.056
 laps+6.945
chie+6.826
Neg logit contributions
�士-11.732
\\\\\\\\-8.588
 Debor-8.518
 conclud-8.469
ntil-7.857
Tokenak
Token ID461
Feature activation+2.02e+00

Pos logit contributions
spot+2.843
amy+2.790
ooter+2.760
 laps+2.747
ground+2.714
Neg logit contributions
�士-5.228
\\\\\\\\-3.983
 conclud-3.976
 Debor-3.932
 Inquisitor-3.637
Token (
Token ID357
Feature activation-5.38e-01

Pos logit contributions
amy+1.330
spot+1.329
 laps+1.322
ground+1.277
ooter+1.266
Neg logit contributions
�士-1.984
 conclud-1.396
 Debor-1.382
\\\\\\\\-1.363
 Inquisitor-1.271
Token4
Token ID19
Feature activation+1.71e+00

Pos logit contributions
�士+0.532
 conclud+0.382
 Debor+0.375
\\\\\\\\+0.374
 Russo+0.348
Neg logit contributions
spot-0.354
amy-0.349
 laps-0.343
ground-0.340
dirty-0.333
Token:
Token ID25
Feature activation+4.18e-01

Pos logit contributions
spot+1.127
 laps+1.118
amy+1.116
ground+1.075
arten+1.057
Neg logit contributions
�士-1.691
 conclud-1.206
 Debor-1.203
\\\\\\\\-1.181
 Russo-1.093
Token When
Token ID1649
Feature activation-6.43e-03

Pos logit contributions
spot+0.409
amy+0.403
 laps+0.403
ground+0.393
ooter+0.388
Neg logit contributions
�士-0.727
 conclud-0.531
\\\\\\\\-0.526
 Debor-0.519
 Russo-0.487
Token a
Token ID257
Feature activation+3.00e+00

Pos logit contributions
�士+0.006
 conclud+0.005
\\\\\\\\+0.004
 Debor+0.004
 Russo+0.004
Neg logit contributions
spot-0.004
 laps-0.004
amy-0.004
ground-0.004
arten-0.004
Token board
Token ID3096
Feature activation+2.98e-01

Pos logit contributions
 laps+2.198
spot+2.182
amy+2.156
ground+2.143
arten+2.099
Neg logit contributions
�士-2.816
 conclud-1.935
\\\\\\\\-1.878
 Debor-1.849
ntil-1.723
Token is
Token ID318
Feature activation+4.89e+00

Pos logit contributions
spot+0.204
 laps+0.201
amy+0.201
ground+0.197
arten+0.194
Neg logit contributions
�士-0.291
 conclud-0.206
 Debor-0.200
\\\\\\\\-0.200
 Russo-0.184
Token cl
Token ID537
Feature activation+5.25e+00

Pos logit contributions
 laps+2.683
spot+2.612
amy+2.564
ground+2.515
dirty+2.497
Neg logit contributions
�士-5.421
 conclud-3.963
\\\\\\\\-3.928
 Debor-3.912
ntil-3.673
Tokenoned
Token ID12004
Feature activation+1.19e+01

Pos logit contributions
amy+3.623
ground+3.517
spot+3.509
 laps+3.484
ooter+3.484
Neg logit contributions
�士-5.369
 conclud-3.892
\\\\\\\\-3.636
 Debor-3.552
ntil-3.339
Token,
Token ID11
Feature activation+2.19e+00

Pos logit contributions
 laps+5.575
ground+5.399
spot+5.395
amy+5.272
 Freedom+5.111
Neg logit contributions
�士-14.692
 conclud-11.471
ntil-11.009
 millenn-10.866
 pione-10.719
Token any
Token ID597
Feature activation+2.36e+00

Pos logit contributions
spot+1.334
 laps+1.322
amy+1.321
ground+1.286
arten+1.268
Neg logit contributions
�士-2.246
 conclud-1.619
 Debor-1.608
\\\\\\\\-1.604
 Russo-1.496
Token modification
Token ID17613
Feature activation+5.05e+00

Pos logit contributions
 laps+1.048
spot+1.028
amy+1.022
ground+0.989
ooter+0.958
Neg logit contributions
�士-2.874
 conclud-2.172
\\\\\\\\-2.155
 Debor-2.127
 Russo-2.011
Token of
Token ID286
Feature activation+2.26e+00

Pos logit contributions
 laps+3.021
spot+2.903
amy+2.892
ground+2.875
 Freedom+2.812
Neg logit contributions
�士-5.672
 conclud-4.162
ntil-3.890
\\\\\\\\-3.879
 Debor-3.835
Token the
Token ID262
Feature activation-6.54e-01

Pos logit contributions
 laps+1.424
spot+1.411
amy+1.399
ground+1.374
ooter+1.347
Neg logit contributions
�士-2.355
 conclud-1.714
 Debor-1.626
\\\\\\\\-1.624
ntil-1.541
Token should
Token ID815
Feature activation+1.84e+00

Pos logit contributions
spot+1.273
amy+1.255
 laps+1.236
ground+1.217
arten+1.214
Neg logit contributions
�士-1.632
 conclud-1.132
 Debor-1.114
\\\\\\\\-1.106
 Russo-1.031
Token get
Token ID651
Feature activation+1.71e+00

Pos logit contributions
amy+1.107
 laps+1.105
spot+1.081
 Freedom+1.072
ground+1.052
Neg logit contributions
�士-1.889
 Debor-1.380
\\\\\\\\-1.368
 conclud-1.365
ntil-1.262
Token less
Token ID1342
Feature activation+3.71e+00

Pos logit contributions
spot+1.175
amy+1.171
 laps+1.157
ground+1.138
ooter+1.122
Neg logit contributions
�士-1.606
 conclud-1.136
 Debor-1.121
\\\\\\\\-1.113
 Russo-1.024
Token than
Token ID621
Feature activation+2.76e+00

Pos logit contributions
amy+1.955
 Freedom+1.902
spot+1.892
 laps+1.891
ground+1.831
Neg logit contributions
�士-4.177
 conclud-3.091
\\\\\\\\-3.077
 Debor-3.029
ntil-2.829
Token 10
Token ID838
Feature activation+5.81e+00

Pos logit contributions
 Freedom+1.712
amy+1.708
ground+1.682
spot+1.613
 laps+1.606
Neg logit contributions
�士-2.708
\\\\\\\\-2.099
 conclud-2.045
 Debor-2.008
ntil-1.896
Token years
Token ID812
Feature activation+1.18e+01

Pos logit contributions
amy+3.886
 Freedom+3.813
 laps+3.760
spot+3.694
ground+3.642
Neg logit contributions
�士-5.502
 Debor-3.995
 conclud-3.961
\\\\\\\\-3.919
ntil-3.708
Token in
Token ID287
Feature activation+4.06e+00

Pos logit contributions
amy+6.930
 Freedom+6.650
ground+6.406
 laps+6.375
spot+6.239
Neg logit contributions
�士-11.992
 conclud-8.949
\\\\\\\\-8.779
 Debor-8.361
ntil-7.959
Token prison
Token ID3770
Feature activation+2.86e+00

Pos logit contributions
amy+2.644
spot+2.618
 laps+2.613
ground+2.597
 Freedom+2.548
Neg logit contributions
�士-3.976
\\\\\\\\-2.851
 conclud-2.844
 Debor-2.816
 Russo-2.591
Token MORE
Token ID12011
Feature activation+5.25e+00

Pos logit contributions
 laps+1.693
amy+1.683
spot+1.659
 Freedom+1.645
ground+1.618
Neg logit contributions
�士-3.015
 conclud-2.199
\\\\\\\\-2.195
 Debor-2.158
ntil-1.980
Token,
Token ID11
Feature activation-6.30e-01

Pos logit contributions
 laps+3.344
spot+3.340
amy+3.288
 Freedom+3.186
ground+3.176
Neg logit contributions
�士-5.247
 conclud-3.739
\\\\\\\\-3.704
 Debor-3.628
ntil-3.378
Token in
Token ID287
Feature activation+1.96e+00

Pos logit contributions
�士+0.590
 conclud+0.413
\\\\\\\\+0.408
 Debor+0.406
 Russo+0.376
Neg logit contributions
spot-0.441
amy-0.436
 laps-0.434
ground-0.425
arten-0.421
Tokenbin
Token ID8800
Feature activation+6.03e-01

Pos logit contributions
�士+1.292
 conclud+0.960
 Debor+0.949
\\\\\\\\+0.948
 Russo+0.892
Neg logit contributions
spot-0.645
amy-0.636
 laps-0.630
ground-0.615
arten-0.608
Token/
Token ID14
Feature activation-2.48e+00

Pos logit contributions
spot+0.387
 laps+0.381
amy+0.379
ground+0.372
ooter+0.368
Neg logit contributions
�士-0.615
 conclud-0.443
 Debor-0.429
\\\\\\\\-0.424
 Russo-0.399
Tokeniw
Token ID14246
Feature activation-1.09e+00

Pos logit contributions
�士+2.637
 conclud+1.942
\\\\\\\\+1.928
 Debor+1.922
 Russo+1.799
Neg logit contributions
spot-1.394
amy-1.376
 laps-1.374
arten-1.334
ground-1.331
Tokenconfig
Token ID11250
Feature activation-8.90e-01

Pos logit contributions
�士+1.278
 conclud+0.974
 Debor+0.964
\\\\\\\\+0.963
 Russo+0.910
Neg logit contributions
spot-0.502
amy-0.494
 laps-0.488
ground-0.474
arten-0.468
Token w
Token ID266
Feature activation+1.81e+00

Pos logit contributions
�士+0.856
 conclud+0.605
 Debor+0.597
\\\\\\\\+0.596
 Russo+0.554
Neg logit contributions
spot-0.602
amy-0.594
 laps-0.592
ground-0.579
arten-0.574
Tokenl
Token ID75
Feature activation+1.18e+01

Pos logit contributions
spot+1.180
amy+1.168
 laps+1.150
ground+1.134
arten+1.124
Neg logit contributions
�士-1.797
 conclud-1.295
\\\\\\\\-1.267
 Debor-1.266
 Russo-1.190
Tokenx
Token ID87
Feature activation+6.29e+00

Pos logit contributions
spot+6.527
amy+6.360
ground+6.213
ooter+6.118
dirty+6.081
Neg logit contributions
�士-12.228
 conclud-9.035
 Debor-9.013
\\\\\\\\-8.713
 Russo-8.550
Token001
Token ID8298
Feature activation-5.22e-01

Pos logit contributions
spot+4.421
amy+4.398
ground+4.306
 laps+4.295
ooter+4.276
Neg logit contributions
�士-5.785
 conclud-3.991
 Debor-3.984
\\\\\\\\-3.827
 Russo-3.683
Tokenf
Token ID69
Feature activation-3.52e-01

Pos logit contributions
�士+0.568
 conclud+0.421
 Debor+0.416
\\\\\\\\+0.416
 Russo+0.391
Neg logit contributions
spot-0.285
amy-0.281
 laps-0.278
ground-0.271
arten-0.269
Token1
Token ID16
Feature activation-8.74e-01

Pos logit contributions
�士+0.340
 conclud+0.241
\\\\\\\\+0.238
 Debor+0.238
 Russo+0.221
Neg logit contributions
spot-0.235
amy-0.232
 laps-0.231
ground-0.226
arten-0.224
Tokenf
Token ID69
Feature activation+4.97e+00

Pos logit contributions
�士+0.961
 conclud+0.716
 Debor+0.708
\\\\\\\\+0.707
 Russo+0.665
Neg logit contributions
spot-0.469
amy-0.462
 laps-0.458
ground-0.446
arten-0.442
Token Center
Token ID3337
Feature activation+2.13e+00

Pos logit contributions
spot+1.278
amy+1.261
ground+1.233
 laps+1.229
arten+1.211
Neg logit contributions
�士-3.121
 conclud-2.401
\\\\\\\\-2.357
 Debor-2.340
utsu-2.194
Token in
Token ID287
Feature activation+7.17e-01

Pos logit contributions
spot+1.444
amy+1.436
 laps+1.427
ground+1.396
arten+1.381
Neg logit contributions
�士-2.048
 conclud-1.440
\\\\\\\\-1.436
 Debor-1.406
 Russo-1.306
Token Washington
Token ID2669
Feature activation-2.96e+00

Pos logit contributions
spot+0.492
amy+0.489
 laps+0.489
ground+0.477
ooter+0.471
Neg logit contributions
�士-0.683
 conclud-0.483
\\\\\\\\-0.476
 Debor-0.467
 Russo-0.430
Token,
Token ID11
Feature activation+1.83e+00

Pos logit contributions
�士+2.683
 conclud+1.874
 Debor+1.851
\\\\\\\\+1.816
 Russo+1.707
Neg logit contributions
spot-2.106
amy-2.077
 laps-2.052
ooter-2.026
arten-2.016
Token D
Token ID360
Feature activation+7.10e+00

Pos logit contributions
spot+1.436
amy+1.423
 laps+1.414
ground+1.390
arten+1.368
Neg logit contributions
�士-1.567
\\\\\\\\-1.051
 conclud-1.048
 Debor-1.017
 Inquisitor-0.926
Token.
Token ID13
Feature activation+1.18e+01

Pos logit contributions
spot+4.131
 laps+4.056
ground+4.021
amy+3.988
 Freedom+3.870
Neg logit contributions
�士-7.978
 conclud-6.153
ntil-5.504
\\\\\\\\-5.428
 Debor-5.368
TokenC
Token ID34
Feature activation+1.03e+00

Pos logit contributions
 Freedom+5.682
spot+5.655
 laps+5.635
ground+5.477
amy+5.410
Neg logit contributions
�士-13.616
 conclud-11.395
ntil-10.861
 tremend-10.478
 tradem-10.376
Token.,
Token ID1539
Feature activation+9.72e-01

Pos logit contributions
spot+0.672
amy+0.665
 laps+0.659
ground+0.646
arten+0.641
Neg logit contributions
�士-1.012
 conclud-0.723
\\\\\\\\-0.713
 Debor-0.713
 Russo-0.663
Token who
Token ID508
Feature activation-7.33e-02

Pos logit contributions
spot+0.634
amy+0.630
 laps+0.627
ground+0.612
arten+0.603
Neg logit contributions
�士-0.959
 conclud-0.681
\\\\\\\\-0.680
 Debor-0.666
 Russo-0.620
Token wrote
Token ID2630
Feature activation-1.82e+00

Pos logit contributions
�士+0.069
 conclud+0.048
\\\\\\\\+0.048
 Debor+0.047
 Russo+0.044
Neg logit contributions
spot-0.051
amy-0.051
 laps-0.050
ground-0.049
arten-0.049
Token a
Token ID257
Feature activation+1.98e+00

Pos logit contributions
�士+1.737
 conclud+1.228
 Debor+1.210
\\\\\\\\+1.209
 Russo+1.122
Neg logit contributions
spot-1.238
amy-1.224
 laps-1.215
ground-1.192
arten-1.182
Token the
Token ID262
Feature activation-2.28e+00

Pos logit contributions
spot+0.904
amy+0.899
 laps+0.896
ground+0.875
ooter+0.862
Neg logit contributions
�士-1.409
 conclud-0.994
\\\\\\\\-0.987
 Debor-0.979
 Russo-0.910
Token curly
Token ID45731
Feature activation-1.63e+00

Pos logit contributions
�士+2.233
 conclud+1.595
 Debor+1.573
\\\\\\\\+1.571
 Russo+1.463
Neg logit contributions
spot-1.497
amy-1.479
 laps-1.467
ground-1.438
arten-1.427
Token brace
Token ID22581
Feature activation+7.51e-01

Pos logit contributions
�士+1.354
 conclud+0.897
 Debor+0.882
\\\\\\\\+0.881
 Russo+0.802
Neg logit contributions
spot-1.307
amy-1.297
 laps-1.286
ground-1.266
ooter-1.257
Token syntax
Token ID15582
Feature activation+3.88e-01

Pos logit contributions
spot+0.507
amy+0.503
 laps+0.497
ground+0.491
ooter+0.482
Neg logit contributions
�士-0.732
 conclud-0.514
\\\\\\\\-0.503
 Debor-0.503
 Russo-0.467
Token e
Token ID304
Feature activation+1.34e+00

Pos logit contributions
spot+0.259
amy+0.255
 laps+0.254
ground+0.249
ooter+0.245
Neg logit contributions
�士-0.380
 conclud-0.269
\\\\\\\\-0.264
 Debor-0.264
 Russo-0.245
Token.
Token ID13
Feature activation+1.18e+01

Pos logit contributions
spot+0.913
amy+0.906
 laps+0.896
ground+0.884
arten+0.868
Neg logit contributions
�士-1.271
 conclud-0.893
 Debor-0.883
\\\\\\\\-0.878
 Russo-0.817
Tokeng
Token ID70
Feature activation-1.05e+00

Pos logit contributions
spot+5.402
ground+5.291
 laps+5.179
amy+5.028
 Freedom+4.919
Neg logit contributions
�士-13.898
 conclud-10.804
 Debor-9.844
 tradem-9.659
\\\\\\\\-9.628
Token.:
Token ID11207
Feature activation+1.03e+00

Pos logit contributions
�士+0.969
 conclud+0.676
 Debor+0.665
\\\\\\\\+0.665
 Russo+0.614
Neg logit contributions
spot-0.750
amy-0.740
 laps-0.735
ground-0.722
arten-0.716
Token
Token ID198
Feature activation+1.02e+00

Pos logit contributions
spot+0.702
amy+0.697
 laps+0.690
ground+0.675
arten+0.668
Neg logit contributions
�士-0.989
 conclud-0.692
 Debor-0.687
\\\\\\\\-0.683
 Russo-0.638
Token
Token ID198
Feature activation+1.26e+00

Pos logit contributions
spot+0.709
amy+0.700
 laps+0.696
ground+0.684
ooter+0.672
Neg logit contributions
�士-0.990
 conclud-0.703
 Debor-0.676
\\\\\\\\-0.676
 Russo-0.622
Tokenruby
Token ID49137
Feature activation+3.29e-01

Pos logit contributions
spot+0.825
amy+0.814
ground+0.791
 laps+0.791
dirty+0.777
Neg logit contributions
�士-1.263
 conclud-0.913
 Debor-0.892
\\\\\\\\-0.881
 Russo-0.834
Token is
Token ID318
Feature activation+5.19e+00

Pos logit contributions
 laps+1.323
spot+1.318
amy+1.307
ground+1.280
 Freedom+1.257
Neg logit contributions
�士-2.269
 conclud-1.607
\\\\\\\\-1.606
 Debor-1.587
ntil-1.482
Token not
Token ID407
Feature activation+3.42e+00

Pos logit contributions
spot+3.101
 laps+3.089
amy+3.054
ground+3.029
 Freedom+2.960
Neg logit contributions
�士-5.364
 conclud-3.817
\\\\\\\\-3.806
 Debor-3.757
 Russo-3.485
Token a
Token ID257
Feature activation+9.60e-01

Pos logit contributions
spot+2.097
 laps+2.066
amy+2.061
ground+2.032
 Freedom+1.972
Neg logit contributions
�士-3.529
 conclud-2.529
\\\\\\\\-2.482
 Debor-2.479
 Russo-2.301
Token problem
Token ID1917
Feature activation+4.40e+00

Pos logit contributions
spot+0.756
 laps+0.746
amy+0.746
ground+0.732
dirty+0.721
Neg logit contributions
�士-0.824
 conclud-0.545
\\\\\\\\-0.540
 Debor-0.535
 Russo-0.486
Token e
Token ID304
Feature activation+2.77e+00

Pos logit contributions
spot+2.762
 laps+2.714
amy+2.667
ground+2.638
ooter+2.577
Neg logit contributions
�士-4.517
 conclud-3.225
\\\\\\\\-3.164
 Debor-3.137
 Russo-2.902
Token.
Token ID13
Feature activation+1.17e+01

Pos logit contributions
spot+1.843
amy+1.823
 laps+1.816
ground+1.787
ooter+1.758
Neg logit contributions
�士-2.798
 conclud-2.017
 Debor-1.914
\\\\\\\\-1.904
ntil-1.760
Tokeng
Token ID70
Feature activation-1.76e+00

Pos logit contributions
ground+5.556
spot+5.554
amy+5.195
 laps+5.186
llan+5.098
Neg logit contributions
�士-14.323
 conclud-11.326
 millenn-10.301
 pione-10.127
 tremend-10.104
Token.:
Token ID11207
Feature activation+1.12e-01

Pos logit contributions
�士+1.579
 conclud+1.091
\\\\\\\\+1.071
 Debor+1.069
 Russo+0.982
Neg logit contributions
spot-1.303
amy-1.286
 laps-1.272
ground-1.254
arten-1.243
Token
Token ID198
Feature activation+9.02e-01

Pos logit contributions
spot+0.078
amy+0.077
 laps+0.076
ground+0.075
ooter+0.074
Neg logit contributions
�士-0.106
 conclud-0.074
 Debor-0.073
\\\\\\\\-0.073
 Russo-0.068
Token
Token ID198
Feature activation+7.10e-01

Pos logit contributions
spot+0.627
amy+0.620
 laps+0.616
ground+0.605
ooter+0.596
Neg logit contributions
�士-0.867
 conclud-0.614
\\\\\\\\-0.592
 Debor-0.592
 Russo-0.546
Tokenruby
Token ID49137
Feature activation+1.15e+00

Pos logit contributions
spot+0.444
amy+0.438
 laps+0.429
ground+0.425
arten+0.419
Neg logit contributions
�士-0.723
 conclud-0.526
 Debor-0.517
\\\\\\\\-0.514
 Russo-0.484
Token supposedly
Token ID13519
Feature activation+6.10e-02

Pos logit contributions
�士+0.474
 conclud+0.334
\\\\\\\\+0.331
 Debor+0.330
 Russo+0.304
Neg logit contributions
spot-0.331
 laps-0.328
amy-0.327
ground-0.318
ooter-0.316
Token incor
Token ID5970
Feature activation+9.27e-01

Pos logit contributions
spot+0.037
 laps+0.036
amy+0.036
ground+0.035
arten+0.035
Neg logit contributions
�士-0.063
 conclud-0.046
\\\\\\\\-0.046
 Debor-0.045
 Russo-0.042
Tokenrupt
Token ID3622
Feature activation+1.54e+00

Pos logit contributions
spot+0.573
 laps+0.565
amy+0.564
ground+0.552
arten+0.546
Neg logit contributions
�士-0.949
 conclud-0.690
\\\\\\\\-0.676
 Debor-0.675
 Russo-0.636
Tokenible
Token ID856
Feature activation-9.08e-01

Pos logit contributions
spot+0.973
 laps+0.972
amy+0.963
ground+0.934
ooter+0.929
Neg logit contributions
�士-1.541
 conclud-1.115
\\\\\\\\-1.095
 Debor-1.093
 Russo-1.015
Token white
Token ID2330
Feature activation+1.66e+00

Pos logit contributions
�士+0.878
 conclud+0.621
\\\\\\\\+0.613
 Debor+0.612
 Russo+0.565
Neg logit contributions
spot-0.610
 laps-0.604
amy-0.602
ground-0.587
ooter-0.582
Token-
Token ID12
Feature activation+1.17e+01

Pos logit contributions
spot+1.092
 laps+1.083
amy+1.069
ground+1.048
arten+1.030
Neg logit contributions
�士-1.631
 conclud-1.171
\\\\\\\\-1.147
 Debor-1.142
utsu-1.053
Tokencollar
Token ID37676
Feature activation+3.67e+00

Pos logit contributions
spot+7.090
ground+6.791
amy+6.679
dirty+6.650
hair+6.487
Neg logit contributions
�士-11.804
 conclud-8.702
\\\\\\\\-8.572
 Debor-7.920
��-7.738
Token division
Token ID7297
Feature activation-1.34e+00

Pos logit contributions
 laps+2.442
spot+2.423
amy+2.362
ground+2.330
 Freedom+2.316
Neg logit contributions
�士-3.538
 conclud-2.536
\\\\\\\\-2.493
 Debor-2.491
 Russo-2.263
Token has
Token ID468
Feature activation+2.38e+00

Pos logit contributions
�士+1.294
 conclud+0.917
\\\\\\\\+0.904
 Debor+0.904
 Russo+0.838
Neg logit contributions
spot-0.903
amy-0.892
 laps-0.888
ground-0.868
arten-0.861
Token leaked
Token ID14109
Feature activation+4.42e+00

Pos logit contributions
 laps+1.532
spot+1.514
amy+1.480
ground+1.458
arten+1.437
Neg logit contributions
�士-2.380
 conclud-1.706
\\\\\\\\-1.690
 Debor-1.664
 Russo-1.545
Token sensitive
Token ID8564
Feature activation+1.28e+00

Pos logit contributions
 laps+2.715
spot+2.655
amy+2.624
ground+2.566
 Freedom+2.563
Neg logit contributions
�士-4.526
 conclud-3.270
\\\\\\\\-3.262
 Debor-3.226
ntil-2.989
Token should
Token ID815
Feature activation+1.66e+00

Pos logit contributions
spot+0.968
amy+0.948
 laps+0.923
arten+0.919
ground+0.916
Neg logit contributions
�士-1.166
 conclud-0.797
 Debor-0.782
\\\\\\\\-0.768
 Russo-0.727
Token get
Token ID651
Feature activation+2.05e+00

Pos logit contributions
 laps+1.017
amy+1.017
spot+1.005
 Freedom+0.979
ground+0.973
Neg logit contributions
�士-1.681
 Debor-1.215
 conclud-1.211
\\\\\\\\-1.207
 Inquisitor-1.111
Token less
Token ID1342
Feature activation+3.58e+00

Pos logit contributions
spot+1.375
amy+1.367
 laps+1.352
ground+1.329
ooter+1.311
Neg logit contributions
�士-1.974
 conclud-1.406
 Debor-1.387
\\\\\\\\-1.381
 Russo-1.275
Token than
Token ID621
Feature activation+2.36e+00

Pos logit contributions
amy+1.790
 laps+1.733
 Freedom+1.732
spot+1.730
ground+1.670
Neg logit contributions
�士-4.139
 conclud-3.086
\\\\\\\\-3.083
 Debor-3.028
ntil-2.836
Token 10
Token ID838
Feature activation+5.51e+00

Pos logit contributions
 Freedom+1.447
amy+1.433
ground+1.421
spot+1.357
 laps+1.356
Neg logit contributions
�士-2.355
\\\\\\\\-1.843
 conclud-1.791
 Debor-1.746
ntil-1.661
Token years
Token ID812
Feature activation+1.17e+01

Pos logit contributions
amy+3.706
 Freedom+3.631
 laps+3.580
spot+3.544
ground+3.492
Neg logit contributions
�士-5.219
 Debor-3.778
 conclud-3.716
\\\\\\\\-3.699
ntil-3.491
Token in
Token ID287
Feature activation+3.66e+00

Pos logit contributions
amy+6.795
 Freedom+6.486
ground+6.293
 laps+6.242
spot+6.094
Neg logit contributions
�士-11.992
 conclud-8.909
\\\\\\\\-8.754
 Debor-8.272
ntil-7.944
Token prison
Token ID3770
Feature activation+2.79e+00

Pos logit contributions
amy+2.411
spot+2.396
 laps+2.390
ground+2.368
 Freedom+2.322
Neg logit contributions
�士-3.543
\\\\\\\\-2.531
 conclud-2.528
 Debor-2.501
 Russo-2.302
Token MORE
Token ID12011
Feature activation+3.91e+00

Pos logit contributions
 laps+1.615
amy+1.607
spot+1.582
 Freedom+1.567
ground+1.542
Neg logit contributions
�士-2.986
 conclud-2.183
\\\\\\\\-2.182
 Debor-2.147
ntil-1.973
Token and
Token ID290
Feature activation+2.04e+00

Pos logit contributions
spot+2.443
amy+2.430
 laps+2.427
ground+2.355
 Freedom+2.349
Neg logit contributions
�士-3.945
 conclud-2.802
\\\\\\\\-2.794
 Debor-2.762
 Russo-2.565
Token Hillary
Token ID5073
Feature activation+2.62e+00

Pos logit contributions
spot+1.128
 laps+1.127
amy+1.107
ground+1.099
 Freedom+1.087
Neg logit contributions
�士-2.215
\\\\\\\\-1.632
 conclud-1.620
 Debor-1.563
utsu-1.477
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
�士+1.461
 Debor+1.016
\\\\\\\\+1.006
 conclud+0.980
 Russo+0.942
Neg logit contributions
spot-1.264
amy-1.249
 laps-1.234
arten-1.221
ooter-1.215
TokenR
Token ID49
Feature activation+4.03e+00

Pos logit contributions
�士+1.056
 conclud+0.744
 Debor+0.739
\\\\\\\\+0.739
 Russo+0.686
Neg logit contributions
spot-0.743
amy-0.733
 laps-0.731
ground-0.714
arten-0.711
Tokenaj
Token ID1228
Feature activation+3.34e+00

Pos logit contributions
amy+2.434
spot+2.347
ooter+2.303
 laps+2.289
ground+2.286
Neg logit contributions
�士-4.253
 conclud-3.114
 Debor-3.049
\\\\\\\\-3.033
 Inquisitor-2.807
Tokenappa
Token ID20975
Feature activation+5.63e+00

Pos logit contributions
spot+2.030
amy+2.029
ground+1.948
 laps+1.940
ooter+1.902
Neg logit contributions
�士-3.453
 conclud-2.548
\\\\\\\\-2.491
 Debor-2.457
 Inquisitor-2.293
Token B
Token ID347
Feature activation+2.42e-01

Pos logit contributions
amy+3.608
spot+3.534
 laps+3.504
ground+3.398
ooter+3.378
Neg logit contributions
�士-5.575
 conclud-4.031
\\\\\\\\-3.966
 Debor-3.818
ntil-3.563
Tokenhatt
Token ID11653
Feature activation+1.16e+01

Pos logit contributions
spot+0.140
amy+0.139
 laps+0.137
ground+0.134
ooter+0.133
Neg logit contributions
�士-0.257
 conclud-0.190
 Debor-0.187
\\\\\\\\-0.187
 Russo-0.174
Tokenar
Token ID283
Feature activation-1.66e-01

Pos logit contributions
amy+6.123
spot+5.739
arten+5.486
ooter+5.481
ground+5.466
Neg logit contributions
�士-12.456
 conclud-9.483
\\\\\\\\-9.162
 Debor-9.072
 Inquisitor-8.498
Token 9
Token ID860
Feature activation+3.01e+00

Pos logit contributions
�士+0.160
 conclud+0.114
\\\\\\\\+0.112
 Debor+0.112
 Russo+0.103
Neg logit contributions
spot-0.111
amy-0.110
 laps-0.109
ground-0.107
ooter-0.106
Token44
Token ID2598
Feature activation-1.77e+00

Pos logit contributions
amy+1.648
spot+1.646
 laps+1.624
ground+1.599
ooter+1.574
Neg logit contributions
�士-3.268
 conclud-2.439
 Debor-2.397
\\\\\\\\-2.376
ntil-2.231
Token20
Token ID1238
Feature activation-4.06e+00

Pos logit contributions
�士+1.744
 conclud+1.246
 Debor+1.234
\\\\\\\\+1.232
 Russo+1.151
Neg logit contributions
spot-1.151
amy-1.134
 laps-1.125
ground-1.102
arten-1.099
Token 30
Token ID1542
Feature activation-1.75e+00

Pos logit contributions
�士+3.925
 Debor+2.805
 conclud+2.794
\\\\\\\\+2.789
 Russo+2.618
Neg logit contributions
spot-2.653
amy-2.608
 laps-2.563
arten-2.548
ooter-2.521
Tokens
Token ID82
Feature activation+2.11e+00

Pos logit contributions
spot+2.393
 laps+2.392
amy+2.338
ground+2.315
dirty+2.239
Neg logit contributions
�士-4.068
 conclud-3.000
 Debor-2.851
\\\\\\\\-2.828
ntil-2.681
Token)}
Token ID38165
Feature activation-1.89e+00

Pos logit contributions
spot+0.936
amy+0.931
 laps+0.926
ground+0.891
ooter+0.881
Neg logit contributions
�士-2.582
 conclud-1.988
 Debor-1.919
\\\\\\\\-1.906
ntil-1.829
Token 9
Token ID860
Feature activation+4.89e-03

Pos logit contributions
�士+1.787
 conclud+1.257
 Debor+1.240
\\\\\\\\+1.238
 Russo+1.147
Neg logit contributions
spot-1.304
amy-1.288
 laps-1.279
ground-1.255
ooter-1.245
Token.
Token ID13
Feature activation+1.91e+00

Pos logit contributions
spot+0.003
amy+0.003
 laps+0.003
ground+0.003
arten+0.003
Neg logit contributions
�士-0.005
 conclud-0.003
 Debor-0.003
\\\\\\\\-0.003
 Russo-0.003
Token B
Token ID347
Feature activation+1.12e+00

Pos logit contributions
 laps+1.222
spot+1.220
amy+1.198
ground+1.174
 Freedom+1.166
Neg logit contributions
�士-1.916
\\\\\\\\-1.368
 conclud-1.364
 Debor-1.337
 Russo-1.234
Tokeng
Token ID70
Feature activation+1.16e+01

Pos logit contributions
spot+0.718
amy+0.711
 laps+0.698
ground+0.691
arten+0.679
Neg logit contributions
�士-1.128
 conclud-0.818
 Debor-0.797
\\\\\\\\-0.797
 Russo-0.746
Token5
Token ID20
Feature activation+3.78e+00

Pos logit contributions
spot+5.362
amy+5.185
ground+5.136
 laps+4.994
dirty+4.954
Neg logit contributions
�士-13.081
\\\\\\\\-9.947
 conclud-9.837
 Debor-9.658
PDATE-9.154
Token {
Token ID1391
Feature activation+3.56e+00

Pos logit contributions
spot+2.253
 laps+2.241
amy+2.209
ground+2.177
ooter+2.141
Neg logit contributions
�士-3.881
 conclud-2.838
 Debor-2.818
\\\\\\\\-2.796
 Russo-2.596
Token(
Token ID7
Feature activation-1.16e+00

Pos logit contributions
spot+1.287
amy+1.246
 laps+1.222
ground+1.204
dirty+1.150
Neg logit contributions
�士-4.700
 conclud-3.749
 Debor-3.572
\\\\\\\\-3.530
ntil-3.464
Token8
Token ID23
Feature activation+1.77e-01

Pos logit contributions
�士+1.136
 conclud+0.811
 Debor+0.801
\\\\\\\\+0.801
 Russo+0.745
Neg logit contributions
spot-0.756
amy-0.747
 laps-0.741
ground-0.726
arten-0.721
Token65
Token ID2996
Feature activation+6.22e-01

Pos logit contributions
spot+0.119
amy+0.118
 laps+0.117
ground+0.115
arten+0.114
Neg logit contributions
�士-0.170
 conclud-0.120
 Debor-0.119
\\\\\\\\-0.119
 Russo-0.110
Token the
Token ID262
Feature activation+2.70e+00

Pos logit contributions
 laps+3.135
spot+3.125
ground+3.053
amy+3.048
 Freedom+2.978
Neg logit contributions
�士-5.462
\\\\\\\\-3.946
 conclud-3.941
 Debor-3.868
ntil-3.585
Token distance
Token ID5253
Feature activation-1.13e+00

Pos logit contributions
spot+1.416
 laps+1.394
amy+1.373
ground+1.341
 Freedom+1.304
Neg logit contributions
�士-3.042
 conclud-2.273
\\\\\\\\-2.252
 Debor-2.243
 Russo-2.083
Token traveled
Token ID14113
Feature activation-1.57e+00

Pos logit contributions
�士+1.054
 conclud+0.739
 Debor+0.729
\\\\\\\\+0.728
 Russo+0.675
Neg logit contributions
spot-0.786
amy-0.777
 laps-0.771
ground-0.757
arten-0.752
Token over
Token ID625
Feature activation+3.85e+00

Pos logit contributions
�士+1.451
 conclud+1.015
 Debor+1.001
\\\\\\\\+0.998
 Russo+0.927
Neg logit contributions
spot-1.114
amy-1.102
 laps-1.089
ground-1.072
arten-1.068
Token the
Token ID262
Feature activation+2.85e+00

Pos logit contributions
 laps+2.383
spot+2.371
ground+2.361
amy+2.339
 Freedom+2.237
Neg logit contributions
�士-3.945
 conclud-2.850
\\\\\\\\-2.796
 Debor-2.782
 Russo-2.578
Token time
Token ID640
Feature activation+1.16e+01

Pos logit contributions
spot+1.738
 laps+1.735
amy+1.699
ground+1.672
 Freedom+1.623
Neg logit contributions
�士-2.948
 conclud-2.144
\\\\\\\\-2.128
 Debor-2.096
ntil-1.948
Token taken
Token ID2077
Feature activation-3.17e-01

Pos logit contributions
 laps+6.217
spot+5.976
ground+5.806
amy+5.725
 Freedom+5.601
Neg logit contributions
�士-12.220
 conclud-9.343
\\\\\\\\-9.078
 Debor-8.710
utsu-8.452
Token,
Token ID11
Feature activation+1.76e+00

Pos logit contributions
�士+0.304
 conclud+0.215
\\\\\\\\+0.212
 Debor+0.212
 Russo+0.196
Neg logit contributions
spot-0.215
amy-0.213
 laps-0.212
ground-0.208
ooter-0.205
Token Earth
Token ID3668
Feature activation+3.95e+00

Pos logit contributions
spot+1.107
 laps+1.092
amy+1.090
ground+1.068
ooter+1.049
Neg logit contributions
�士-1.775
 conclud-1.273
\\\\\\\\-1.267
 Debor-1.255
 Russo-1.165
Token's
Token ID338
Feature activation-2.29e-01

Pos logit contributions
spot+2.666
 laps+2.660
amy+2.587
ground+2.513
ooter+2.469
Neg logit contributions
�士-3.851
 conclud-2.709
 Debor-2.692
\\\\\\\\-2.677
 Russo-2.481
Token speed
Token ID2866
Feature activation+1.56e+00

Pos logit contributions
�士+0.215
 conclud+0.150
\\\\\\\\+0.149
 Debor+0.148
 Russo+0.137
Neg logit contributions
spot-0.160
amy-0.158
 laps-0.158
ground-0.154
ooter-0.153
Token c
Token ID269
Feature activation+3.98e+00

Pos logit contributions
�士+0.330
 conclud+0.227
\\\\\\\\+0.223
 Debor+0.223
 Russo+0.205
Neg logit contributions
spot-0.268
amy-0.265
 laps-0.265
ground-0.259
ooter-0.257
Tokenv
Token ID85
Feature activation+8.34e+00

Pos logit contributions
spot+1.741
amy+1.658
ground+1.645
 laps+1.634
ooter+1.579
Neg logit contributions
�士-5.046
 conclud-3.914
\\\\\\\\-3.727
 Debor-3.699
ntil-3.543
Token2
Token ID17
Feature activation+2.34e+00

Pos logit contributions
spot+3.639
ground+3.557
 laps+3.402
amy+3.384
llan+3.211
Neg logit contributions
�士-10.653
 conclud-8.516
ntil-7.912
 millenn-7.825
 tremend-7.819
Token.
Token ID764
Feature activation+7.97e+00

Pos logit contributions
spot+1.490
 laps+1.474
amy+1.460
ground+1.450
ooter+1.409
Neg logit contributions
�士-2.425
 conclud-1.774
\\\\\\\\-1.673
 Debor-1.661
ntil-1.609
Token COL
Token ID20444
Feature activation+3.26e+00

Pos logit contributions
 laps+5.086
ground+4.953
spot+4.918
amy+4.831
dirty+4.828
Neg logit contributions
�士-7.740
 conclud-5.430
 Debor-5.387
\\\\\\\\-5.361
ntil-4.976
TokenOR
Token ID1581
Feature activation+1.13e+01

Pos logit contributions
spot+2.229
 laps+2.188
ground+2.181
amy+2.180
ooter+2.117
Neg logit contributions
�士-3.197
 conclud-2.311
 Debor-2.169
\\\\\\\\-2.119
ntil-2.036
Token_
Token ID62
Feature activation-1.25e+00

Pos logit contributions
ground+4.116
 laps+4.077
spot+4.027
amy+3.867
 Freedom+3.718
Neg logit contributions
�士-14.847
 conclud-11.846
ntil-11.480
 tremend-11.219
 millenn-11.202
TokenB
Token ID33
Feature activation+1.03e+00

Pos logit contributions
�士+1.191
\\\\\\\\+0.835
 conclud+0.834
 Debor+0.831
 Russo+0.772
Neg logit contributions
spot-0.850
amy-0.842
 laps-0.836
arten-0.818
ground-0.815
TokenGR
Token ID10761
Feature activation+7.38e+00

Pos logit contributions
spot+0.635
amy+0.627
 laps+0.622
ground+0.612
ooter+0.604
Neg logit contributions
�士-1.060
 conclud-0.776
 Debor-0.758
\\\\\\\\-0.751
 Russo-0.705
Token2
Token ID17
Feature activation+3.00e+00

Pos logit contributions
spot+3.196
ground+3.186
 laps+3.101
amy+3.089
ooter+3.035
Neg logit contributions
�士-8.952
 conclud-7.172
ntil-6.719
 Debor-6.619
 tradem-6.583
TokenG
Token ID38
Feature activation+3.59e+00

Pos logit contributions
spot+2.097
 laps+2.068
ground+2.059
amy+2.050
ooter+2.003
Neg logit contributions
�士-2.871
 conclud-2.064
 Debor-1.963
\\\\\\\\-1.909
ntil-1.881
Token(
Token ID7
Feature activation+1.86e+00

Pos logit contributions
spot+1.535
amy+1.483
 laps+1.458
ground+1.439
dirty+1.368
Neg logit contributions
�士-5.923
 conclud-4.765
 Debor-4.492
\\\\\\\\-4.421
ntil-4.415
Token6
Token ID21
Feature activation-6.27e-01

Pos logit contributions
spot+1.207
amy+1.193
 laps+1.181
ground+1.170
ooter+1.146
Neg logit contributions
�士-1.838
 conclud-1.330
 Debor-1.295
\\\\\\\\-1.293
 Russo-1.202
Tokens
Token ID82
Feature activation+1.59e+00

Pos logit contributions
�士+0.596
 conclud+0.421
 Debor+0.415
\\\\\\\\+0.414
 Russo+0.383
Neg logit contributions
spot-0.430
amy-0.425
 laps-0.423
ground-0.415
arten-0.410
Token)}
Token ID38165
Feature activation-8.07e-01

Pos logit contributions
spot+0.720
amy+0.714
 laps+0.705
ground+0.683
ooter+0.674
Neg logit contributions
�士-1.919
 conclud-1.474
 Debor-1.429
\\\\\\\\-1.421
ntil-1.347
Token B
Token ID347
Feature activation+1.04e+00

Pos logit contributions
�士+0.799
 conclud+0.569
\\\\\\\\+0.562
 Debor+0.559
 Russo+0.518
Neg logit contributions
spot-0.525
 laps-0.520
amy-0.517
ground-0.506
ooter-0.501
Tokenc
Token ID66
Feature activation+1.12e+01

Pos logit contributions
spot+0.714
amy+0.707
 laps+0.695
ground+0.688
arten+0.678
Neg logit contributions
�士-1.009
 conclud-0.721
 Debor-0.701
\\\\\\\\-0.700
 Russo-0.652
Token6
Token ID21
Feature activation+5.24e+00

Pos logit contributions
spot+6.155
ground+5.844
amy+5.796
 laps+5.768
ooter+5.681
Neg logit contributions
�士-12.052
 conclud-9.014
\\\\\\\\-8.919
 Debor-8.442
PDATE-8.181
Token {
Token ID1391
Feature activation+4.82e+00

Pos logit contributions
spot+2.967
 laps+2.912
amy+2.870
ground+2.860
 Freedom+2.786
Neg logit contributions
�士-5.827
 conclud-4.413
\\\\\\\\-4.132
 Debor-4.111
ntil-4.016
Token(
Token ID7
Feature activation+2.26e+00

Pos logit contributions
spot+1.647
amy+1.581
 laps+1.558
ground+1.537
dirty+1.458
Neg logit contributions
�士-6.511
 conclud-5.269
 Debor-4.940
ntil-4.894
\\\\\\\\-4.859
Token153
Token ID21395
Feature activation-2.02e-02

Pos logit contributions
spot+1.456
amy+1.437
 laps+1.424
ground+1.410
ooter+1.379
Neg logit contributions
�士-2.229
 conclud-1.620
 Debor-1.573
\\\\\\\\-1.572
 Russo-1.460
Tokens
Token ID82
Feature activation+2.19e+00

Pos logit contributions
�士+0.020
 conclud+0.014
 Debor+0.014
\\\\\\\\+0.014
 Russo+0.013
Neg logit contributions
spot-0.014
amy-0.013
 laps-0.013
ground-0.013
ooter-0.013
Token rebutt
Token ID46472
Feature activation+2.36e+00

Pos logit contributions
 laps+1.604
spot+1.593
amy+1.578
ground+1.533
arten+1.492
Neg logit contributions
�士-2.559
 conclud-1.820
\\\\\\\\-1.807
 Debor-1.799
utsu-1.668
Tokenals
Token ID874
Feature activation+4.16e-01

Pos logit contributions
amy+1.096
spot+1.095
 laps+1.086
arten+1.045
ground+1.039
Neg logit contributions
�士-2.759
 conclud-2.092
\\\\\\\\-2.077
 Debor-2.070
 Russo-1.958
Token toward
Token ID3812
Feature activation-1.08e-01

Pos logit contributions
spot+0.253
 laps+0.250
amy+0.249
ground+0.242
arten+0.239
Neg logit contributions
�士-0.430
 conclud-0.311
\\\\\\\\-0.307
 Debor-0.307
 Russo-0.287
Token cliché
Token ID43973
Feature activation-2.40e+00

Pos logit contributions
�士+0.110
 conclud+0.080
\\\\\\\\+0.079
 Debor+0.078
 Russo+0.073
Neg logit contributions
spot-0.067
amy-0.066
 laps-0.066
ground-0.064
ooter-0.063
Token bo
Token ID1489
Feature activation-3.53e-01

Pos logit contributions
�士+2.391
 conclud+1.734
 Debor+1.709
\\\\\\\\+1.707
 Russo+1.592
Neg logit contributions
spot-1.499
amy-1.488
 laps-1.471
arten-1.442
ground-1.438
Tokenhem
Token ID4411
Feature activation+1.12e+01

Pos logit contributions
�士+0.403
 conclud+0.303
\\\\\\\\+0.301
 Debor+0.300
 Russo+0.282
Neg logit contributions
spot-0.175
amy-0.174
 laps-0.172
ground-0.166
arten-0.165
Tokenian
Token ID666
Feature activation+4.80e-01

Pos logit contributions
spot+4.740
amy+4.412
 laps+4.385
arten+4.377
ground+4.274
Neg logit contributions
�士-13.220
 conclud-10.106
 Debor-10.039
\\\\\\\\-9.821
ntil-9.279
Token ideals
Token ID22247
Feature activation+1.81e+00

Pos logit contributions
spot+0.304
amy+0.302
 laps+0.300
ground+0.293
arten+0.288
Neg logit contributions
�士-0.485
 conclud-0.348
\\\\\\\\-0.344
 Debor-0.342
 Russo-0.318
Token that
Token ID326
Feature activation+1.98e+00

Pos logit contributions
spot+0.985
 laps+0.973
amy+0.972
ground+0.946
arten+0.921
Neg logit contributions
�士-1.989
 conclud-1.473
 Debor-1.449
\\\\\\\\-1.447
 Russo-1.359
Token have
Token ID423
Feature activation-4.57e-01

Pos logit contributions
spot+1.366
 laps+1.361
amy+1.347
ground+1.320
arten+1.296
Neg logit contributions
�士-1.874
 conclud-1.307
\\\\\\\\-1.298
 Debor-1.273
 Russo-1.171
Token been
Token ID587
Feature activation+3.00e+00

Pos logit contributions
�士+0.451
 conclud+0.323
\\\\\\\\+0.318
 Debor+0.317
 Russo+0.295
Neg logit contributions
spot-0.297
amy-0.293
 laps-0.293
ground-0.285
arten-0.282
Tokens
Token ID82
Feature activation+1.37e+00

Pos logit contributions
spot+0.524
 laps+0.518
amy+0.516
ground+0.505
dirty+0.494
Neg logit contributions
�士-0.799
 conclud-0.576
 Debor-0.557
\\\\\\\\-0.554
 Russo-0.514
Token)}
Token ID38165
Feature activation+1.28e+00

Pos logit contributions
spot+0.620
amy+0.614
 laps+0.611
ground+0.589
ooter+0.577
Neg logit contributions
�士-1.652
 conclud-1.269
 Debor-1.231
\\\\\\\\-1.223
ntil-1.159
Token 4
Token ID604
Feature activation+6.03e-01

Pos logit contributions
spot+0.763
 laps+0.752
amy+0.744
ground+0.732
ooter+0.719
Neg logit contributions
�士-1.351
 conclud-0.983
\\\\\\\\-0.977
 Debor-0.963
 Russo-0.898
Token.
Token ID13
Feature activation+2.22e+00

Pos logit contributions
spot+0.415
amy+0.409
 laps+0.408
ground+0.401
arten+0.393
Neg logit contributions
�士-0.587
 conclud-0.419
 Debor-0.401
\\\\\\\\-0.401
ntil-0.372
Token B
Token ID347
Feature activation+2.93e-01

Pos logit contributions
 laps+1.418
spot+1.414
amy+1.383
ground+1.357
 Freedom+1.351
Neg logit contributions
�士-2.224
\\\\\\\\-1.589
 conclud-1.582
 Debor-1.554
 Russo-1.430
Tokeng
Token ID70
Feature activation+1.11e+01

Pos logit contributions
spot+0.185
amy+0.183
 laps+0.180
ground+0.178
arten+0.175
Neg logit contributions
�士-0.297
 conclud-0.216
 Debor-0.212
\\\\\\\\-0.211
 Russo-0.197
Token2
Token ID17
Feature activation+4.95e+00

Pos logit contributions
spot+5.066
amy+4.856
ground+4.828
 laps+4.698
dirty+4.683
Neg logit contributions
�士-12.875
\\\\\\\\-9.836
 conclud-9.749
 Debor-9.551
PDATE-9.068
Token {
Token ID1391
Feature activation+3.71e+00

Pos logit contributions
 laps+2.906
spot+2.886
amy+2.820
ground+2.777
 Freedom+2.746
Neg logit contributions
�士-5.144
 conclud-3.753
\\\\\\\\-3.692
 Debor-3.677
 Russo-3.417
Token(
Token ID7
Feature activation-7.45e-01

Pos logit contributions
spot+1.338
amy+1.289
 laps+1.265
ground+1.254
dirty+1.200
Neg logit contributions
�士-4.900
 conclud-3.912
 Debor-3.725
\\\\\\\\-3.682
ntil-3.609
Token0
Token ID15
Feature activation-1.16e+00

Pos logit contributions
�士+0.749
 conclud+0.540
 Debor+0.534
\\\\\\\\+0.533
 Russo+0.498
Neg logit contributions
spot-0.468
amy-0.462
 laps-0.459
ground-0.449
arten-0.446
Tokens
Token ID82
Feature activation+1.14e+00

Pos logit contributions
�士+1.087
 conclud+0.762
\\\\\\\\+0.758
 Debor+0.758
 Russo+0.704
Neg logit contributions
spot-0.797
amy-0.789
 laps-0.782
ground-0.766
arten-0.764
Token been
Token ID587
Feature activation+4.25e+00

Pos logit contributions
�士+0.108
 conclud+0.077
\\\\\\\\+0.076
 Debor+0.075
 Russo+0.070
Neg logit contributions
spot-0.071
amy-0.070
 laps-0.070
ground-0.068
arten-0.067
Token so
Token ID523
Feature activation-4.63e-02

Pos logit contributions
spot+2.643
amy+2.588
 laps+2.551
ground+2.475
 Freedom+2.400
Neg logit contributions
�士-4.437
 conclud-3.197
\\\\\\\\-3.196
 Debor-3.111
 Inquisitor-2.871
Token successful
Token ID4388
Feature activation+1.49e+00

Pos logit contributions
�士+0.043
 conclud+0.030
\\\\\\\\+0.029
 Debor+0.029
 Russo+0.026
Neg logit contributions
spot-0.034
amy-0.033
 laps-0.033
ground-0.032
arten-0.032
Token at
Token ID379
Feature activation+3.29e+00

Pos logit contributions
spot+1.004
 laps+0.987
amy+0.986
ground+0.953
ooter+0.940
Neg logit contributions
�士-1.476
 conclud-1.027
\\\\\\\\-1.013
 Debor-1.004
 Russo-0.931
Token Bro
Token ID2806
Feature activation-5.56e-01

Pos logit contributions
spot+2.119
 laps+2.065
amy+2.059
ground+2.006
arten+1.982
Neg logit contributions
�士-3.310
 conclud-2.360
\\\\\\\\-2.342
 Debor-2.315
 Russo-2.134
Tokend
Token ID67
Feature activation+1.10e+01

Pos logit contributions
�士+0.549
 conclud+0.395
 Debor+0.387
\\\\\\\\+0.386
 Russo+0.359
Neg logit contributions
spot-0.363
amy-0.359
 laps-0.355
ground-0.348
ooter-0.345
Tokenard
Token ID446
Feature activation+9.37e-04

Pos logit contributions
spot+7.449
amy+7.295
ground+6.941
arten+6.807
 laps+6.748
Neg logit contributions
�士-10.012
 conclud-7.314
 Debor-7.118
\\\\\\\\-6.989
 Inquisitor-6.378
Token.
Token ID13
Feature activation+1.00e+00

Pos logit contributions
spot+0.001
amy+0.001
 laps+0.001
ground+0.001
arten+0.001
Neg logit contributions
�士-0.001
 conclud-0.001
 Debor-0.001
\\\\\\\\-0.001
 Russo-0.001
Token A
Token ID317
Feature activation-3.07e-01

Pos logit contributions
spot+0.723
amy+0.719
 laps+0.706
ground+0.697
ooter+0.689
Neg logit contributions
�士-0.925
 conclud-0.651
\\\\\\\\-0.626
 Debor-0.619
 Inquisitor-0.568
Token decade
Token ID5707
Feature activation-1.52e+00

Pos logit contributions
�士+0.293
 conclud+0.205
\\\\\\\\+0.202
 Debor+0.202
 Russo+0.185
Neg logit contributions
spot-0.212
amy-0.209
 laps-0.208
ground-0.204
ooter-0.201
Token ago
Token ID2084
Feature activation-8.94e-01

Pos logit contributions
�士+1.514
 conclud+1.085
\\\\\\\\+1.072
 Debor+1.070
 Russo+1.000
Neg logit contributions
spot-0.976
amy-0.964
 laps-0.958
ground-0.935
arten-0.925
Token go
Token ID467
Feature activation+1.53e+00

Pos logit contributions
�士+0.471
 conclud+0.330
 Debor+0.326
\\\\\\\\+0.326
 Russo+0.300
Neg logit contributions
spot-0.338
amy-0.334
 laps-0.333
ground-0.324
ooter-0.322
Token ahead
Token ID4058
Feature activation+1.18e+00

Pos logit contributions
spot+0.961
amy+0.953
 laps+0.950
ground+0.918
ooter+0.904
Neg logit contributions
�士-1.566
 conclud-1.115
\\\\\\\\-1.109
 Debor-1.100
 Inquisitor-1.017
Token late
Token ID2739
Feature activation-1.09e+00

Pos logit contributions
 laps+0.762
spot+0.755
amy+0.746
ground+0.736
arten+0.718
Neg logit contributions
�士-1.205
 conclud-0.844
\\\\\\\\-0.837
 Debor-0.830
 Russo-0.764
Token on
Token ID319
Feature activation-4.22e-01

Pos logit contributions
�士+1.032
 conclud+0.719
\\\\\\\\+0.713
 Debor+0.709
 Russo+0.653
Neg logit contributions
spot-0.760
amy-0.751
 laps-0.751
ground-0.733
arten-0.725
Token the
Token ID262
Feature activation+3.80e+00

Pos logit contributions
�士+0.415
 conclud+0.293
\\\\\\\\+0.290
 Debor+0.288
 Inquisitor+0.265
Neg logit contributions
spot-0.281
 laps-0.279
amy-0.277
ground-0.270
ooter-0.266
Token power
Token ID1176
Feature activation+1.10e+01

Pos logit contributions
 laps+2.232
spot+2.228
amy+2.175
ground+2.129
 Freedom+2.108
Neg logit contributions
�士-4.005
\\\\\\\\-2.948
 conclud-2.924
 Debor-2.896
 Inquisitor-2.649
Token-
Token ID12
Feature activation+6.62e+00

Pos logit contributions
 laps+6.677
spot+6.476
amy+6.169
ground+5.941
arten+5.872
Neg logit contributions
�士-11.478
 conclud-8.486
\\\\\\\\-8.330
 Debor-8.058
 tradem-7.633
Tokenplay
Token ID1759
Feature activation+3.77e+00

Pos logit contributions
spot+3.919
ground+3.700
amy+3.681
 laps+3.608
dirty+3.587
Neg logit contributions
�士-7.657
 conclud-5.802
\\\\\\\\-5.424
 Debor-5.355
 millenn-5.174
Token however
Token ID2158
Feature activation+2.27e+00

Pos logit contributions
 laps+2.405
spot+2.369
amy+2.283
ground+2.253
 Freedom+2.196
Neg logit contributions
�士-3.873
\\\\\\\\-2.765
 Debor-2.731
 conclud-2.695
 Russo-2.464
Token Jake
Token ID14757
Feature activation-2.15e+00

Pos logit contributions
 laps+1.488
spot+1.480
amy+1.454
ground+1.417
ooter+1.403
Neg logit contributions
�士-2.243
 conclud-1.589
\\\\\\\\-1.587
 Debor-1.560
 Inquisitor-1.437
Token Allen
Token ID9659
Feature activation+2.29e+00

Pos logit contributions
�士+2.225
 Debor+1.634
\\\\\\\\+1.602
 conclud+1.598
 Russo+1.549
Neg logit contributions
spot-1.263
 laps-1.228
amy-1.217
ground-1.208
arten-1.203
Token Comedy
Token ID22329
Feature activation-3.46e+00

Pos logit contributions
spot+0.078
amy+0.076
 laps+0.076
ground+0.074
arten+0.073
Neg logit contributions
�士-0.167
 conclud-0.125
 Debor-0.124
\\\\\\\\-0.124
 Russo-0.117
Token
Token ID198
Feature activation-2.98e+00

Pos logit contributions
�士+3.020
 Debor+2.091
\\\\\\\\+2.080
 conclud+2.069
 Russo+1.939
Neg logit contributions
spot-2.530
amy-2.507
 laps-2.484
arten-2.444
ground-2.443
Token
Token ID198
Feature activation+3.32e-01

Pos logit contributions
�士+2.372
 Debor+1.666
\\\\\\\\+1.645
 Russo+1.551
 RW+1.536
Neg logit contributions
spot-2.274
amy-2.253
 laps-2.223
arten-2.219
ooter-2.209
TokenLouis
Token ID32117
Feature activation+4.07e+00

Pos logit contributions
spot+0.222
amy+0.219
 laps+0.217
ground+0.213
arten+0.211
Neg logit contributions
�士-0.321
 conclud-0.228
 Debor-0.225
\\\\\\\\-0.224
 Russo-0.208
Token C
Token ID327
Feature activation-3.90e-01

Pos logit contributions
amy+3.018
spot+2.914
 laps+2.862
 Freedom+2.854
ground+2.849
Neg logit contributions
�士-3.640
 conclud-2.682
\\\\\\\\-2.485
 Debor-2.378
ntil-2.290
Token.
Token ID13
Feature activation+1.09e+01

Pos logit contributions
�士+0.372
 conclud+0.263
 Debor+0.258
\\\\\\\\+0.257
 Russo+0.235
Neg logit contributions
spot-0.270
amy-0.268
 laps-0.264
ooter-0.261
arten-0.260
TokenK
Token ID42
Feature activation+4.85e+00

Pos logit contributions
 laps+4.109
zanne+3.994
amy+3.955
spot+3.718
ooter+3.718
Neg logit contributions
�士-13.296
\\\\\\\\-10.539
 conclud-10.375
 Debor-9.981
ntil-9.938
Token.
Token ID13
Feature activation+4.88e+00

Pos logit contributions
spot+3.064
amy+3.037
 Freedom+2.985
 laps+2.962
ground+2.957
Neg logit contributions
�士-4.888
 conclud-3.626
\\\\\\\\-3.408
 Debor-3.305
ntil-3.165
Token Louie
Token ID48352
Feature activation+3.44e+00

Pos logit contributions
spot+3.057
 Freedom+3.026
amy+3.024
 laps+2.970
ground+2.969
Neg logit contributions
�士-4.910
 conclud-3.638
\\\\\\\\-3.435
 Debor-3.340
ntil-3.258
Token FX
Token ID19534
Feature activation+7.67e-01

Pos logit contributions
spot+2.185
amy+2.149
 laps+2.114
ground+2.098
 Freedom+2.093
Neg logit contributions
�士-3.511
 conclud-2.565
\\\\\\\\-2.440
 Debor-2.399
ntil-2.277
Token Mind
Token ID10175
Feature activation+8.10e-01

Pos logit contributions
spot+0.490
amy+0.485
 laps+0.480
ground+0.472
arten+0.464
Neg logit contributions
�士-0.771
 conclud-0.560
\\\\\\\\-0.543
 Debor-0.537
ntil-0.500
Token always
Token ID1464
Feature activation+1.88e-01

Pos logit contributions
spot+1.314
 laps+1.309
amy+1.303
ground+1.253
ooter+1.240
Neg logit contributions
�士-2.106
 conclud-1.484
\\\\\\\\-1.482
 Debor-1.467
 Russo-1.358
Token see
Token ID766
Feature activation+6.97e-01

Pos logit contributions
spot+0.114
amy+0.112
 laps+0.112
ground+0.108
arten+0.107
Neg logit contributions
�士-0.196
 conclud-0.142
\\\\\\\\-0.141
 Debor-0.140
 Russo-0.131
Token completely
Token ID3190
Feature activation+3.35e+00

Pos logit contributions
spot+0.383
 laps+0.378
amy+0.377
ground+0.366
arten+0.361
Neg logit contributions
�士-0.759
 conclud-0.562
\\\\\\\\-0.555
 Debor-0.553
 Russo-0.517
Token eye
Token ID4151
Feature activation-4.31e+00

Pos logit contributions
 laps+2.068
spot+2.067
amy+2.015
ground+1.995
 Freedom+1.936
Neg logit contributions
�士-3.449
 conclud-2.495
\\\\\\\\-2.466
 Debor-2.451
utsu-2.288
Token to
Token ID284
Feature activation-4.38e+00

Pos logit contributions
�士+3.919
 conclud+2.749
\\\\\\\\+2.714
 Debor+2.706
 Russo+2.524
Neg logit contributions
spot-2.998
amy-2.993
 laps-2.931
ground-2.921
arten-2.905
Token eye
Token ID4151
Feature activation-1.35e+01

Pos logit contributions
�士+4.446
 Debor+3.224
\\\\\\\\+3.220
 conclud+3.211
 Russo+3.068
Neg logit contributions
spot-2.526
amy-2.516
 laps-2.469
ground-2.418
arten-2.404
Token on
Token ID319
Feature activation-1.81e+00

Pos logit contributions
�士+9.748
 Debor+7.200
 conclud+7.004
\\\\\\\\+6.954
 Russo+6.633
Neg logit contributions
amy-9.995
spot-9.847
arten-9.743
ooter-9.684
dirty-9.479
Token things
Token ID1243
Feature activation-1.80e+00

Pos logit contributions
�士+1.725
 conclud+1.222
 Debor+1.209
\\\\\\\\+1.204
 Russo+1.124
Neg logit contributions
spot-1.219
amy-1.206
 laps-1.190
ground-1.170
ooter-1.165
Token,
Token ID11
Feature activation-1.56e+00

Pos logit contributions
�士+1.674
 conclud+1.170
 Debor+1.153
\\\\\\\\+1.152
 Russo+1.065
Neg logit contributions
spot-1.267
amy-1.253
 laps-1.244
ground-1.221
arten-1.211
Token but
Token ID475
Feature activation+1.61e+00

Pos logit contributions
�士+1.114
 conclud+0.676
 Debor+0.661
\\\\\\\\+0.660
 Russo+0.585
Neg logit contributions
spot-1.442
amy-1.430
 laps-1.422
ground-1.402
arten-1.393
Token on
Token ID319
Feature activation-2.60e+00

Pos logit contributions
spot+1.052
 laps+1.049
amy+1.038
ground+1.013
ooter+1.002
Neg logit contributions
�士-1.585
 conclud-1.124
\\\\\\\\-1.116
 Debor-1.096
 Russo-1.020
Tokenaur
Token ID2899
Feature activation-2.92e-01

Pos logit contributions
amy+3.187
spot+3.170
 laps+3.102
ground+3.082
arten+3.073
Neg logit contributions
�士-2.912
 conclud-1.897
\\\\\\\\-1.847
 Debor-1.842
 Russo-1.647
Token #
Token ID1303
Feature activation+1.41e-01

Pos logit contributions
�士+0.282
 conclud+0.200
\\\\\\\\+0.197
 Debor+0.197
 Russo+0.182
Neg logit contributions
spot-0.197
amy-0.194
 laps-0.193
ground-0.189
ooter-0.187
Token2
Token ID17
Feature activation+3.32e-01

Pos logit contributions
spot+0.089
amy+0.087
 laps+0.087
ground+0.085
ooter+0.084
Neg logit contributions
�士-0.143
 conclud-0.103
\\\\\\\\-0.101
 Debor-0.101
 Russo-0.094
Token
Token ID198
Feature activation-3.46e+00

Pos logit contributions
spot+0.230
amy+0.228
 laps+0.225
ground+0.222
arten+0.219
Neg logit contributions
�士-0.315
 conclud-0.222
\\\\\\\\-0.219
 Debor-0.218
 Russo-0.201
Token
Token ID198
Feature activation-4.04e+00

Pos logit contributions
�士+2.776
 Debor+1.943
\\\\\\\\+1.921
 Russo+1.813
 RW+1.794
Neg logit contributions
spot-2.635
amy-2.612
arten-2.580
 laps-2.578
ooter-2.556
TokenHad
Token ID25383
Feature activation-1.23e+01

Pos logit contributions
�士+3.275
\\\\\\\\+2.126
 Debor+2.101
 conclud+2.094
 Russo+1.921
Neg logit contributions
spot-3.236
 laps-3.230
amy-3.207
arten-3.158
ooter-3.147
Tokenros
Token ID4951
Feature activation+4.71e+00

Pos logit contributions
�士+4.395
utsu+2.229
isl+2.186
 Russo+2.026
 RW+2.021
Neg logit contributions
spot-12.494
 laps-12.437
 Freedom-12.365
dirty-12.332
arten-12.292
Tokenaur
Token ID2899
Feature activation-1.81e+00

Pos logit contributions
spot+4.006
amy+4.002
ground+3.889
 laps+3.874
arten+3.860
Neg logit contributions
�士-3.948
 conclud-2.624
\\\\\\\\-2.432
 Debor-2.416
 Russo-2.166
Token #
Token ID1303
Feature activation-1.75e+00

Pos logit contributions
�士+1.705
 conclud+1.200
 Debor+1.194
\\\\\\\\+1.190
 Russo+1.111
Neg logit contributions
spot-1.230
amy-1.217
 laps-1.205
ground-1.183
arten-1.181
Token2
Token ID17
Feature activation-2.70e-01

Pos logit contributions
�士+1.787
 conclud+1.298
 Debor+1.283
\\\\\\\\+1.280
 Russo+1.199
Neg logit contributions
spot-1.054
amy-1.046
 laps-1.038
arten-1.011
ground-1.009
Token
Token ID198
Feature activation-3.77e+00

Pos logit contributions
�士+0.250
 conclud+0.174
 Debor+0.172
\\\\\\\\+0.171
 Russo+0.159
Neg logit contributions
spot-0.192
amy-0.189
 laps-0.188
ground-0.185
arten-0.183
Token stranger
Token ID16195
Feature activation-3.16e+00

Pos logit contributions
�士+2.577
 conclud+1.856
 Debor+1.835
\\\\\\\\+1.829
 Russo+1.711
Neg logit contributions
spot-1.632
amy-1.612
 laps-1.597
ground-1.566
ooter-1.555
Token
Token ID447
Feature activation-1.34e+00

Pos logit contributions
�士+2.817
 conclud+1.934
 Debor+1.909
\\\\\\\\+1.903
 Russo+1.756
Neg logit contributions
spot-2.341
amy-2.318
 laps-2.300
ground-2.261
arten-2.247
Token
Token ID247
Feature activation-6.39e-01

Pos logit contributions
�士+1.065
 conclud+0.691
 Debor+0.678
\\\\\\\\+0.677
 Russo+0.613
Neg logit contributions
spot-1.122
amy-1.112
 laps-1.105
ground-1.088
arten-1.081
Tokens
Token ID82
Feature activation-4.22e+00

Pos logit contributions
�士+0.609
 conclud+0.429
\\\\\\\\+0.422
 Debor+0.421
 Russo+0.390
Neg logit contributions
spot-0.445
amy-0.436
 laps-0.432
ground-0.428
arten-0.421
Token apartment
Token ID7962
Feature activation-2.84e+00

Pos logit contributions
�士+3.764
 conclud+2.590
 Debor+2.575
\\\\\\\\+2.540
 Russo+2.378
Neg logit contributions
spot-3.086
amy-3.060
 laps-3.017
ground-2.975
ooter-2.966
Token and
Token ID290
Feature activation-1.20e+01

Pos logit contributions
�士+2.648
 conclud+1.861
 Debor+1.837
\\\\\\\\+1.831
 Russo+1.699
Neg logit contributions
spot-1.983
amy-1.964
 laps-1.946
ground-1.908
ooter-1.900
Token hide
Token ID7808
Feature activation-4.33e+00

Pos logit contributions
�士+9.570
 conclud+7.047
 Debor+7.001
 Russo+6.609
 Inquisitor+6.576
Neg logit contributions
spot-7.770
ortium-7.769
amy-7.699
ooter-7.694
arten-7.650
Token under
Token ID739
Feature activation-2.25e+00

Pos logit contributions
�士+3.992
 Debor+2.820
 conclud+2.816
\\\\\\\\+2.772
 Russo+2.611
Neg logit contributions
spot-2.988
amy-2.939
 laps-2.895
ooter-2.866
arten-2.857
Token his
Token ID465
Feature activation-2.30e+00

Pos logit contributions
�士+2.217
 conclud+1.591
 Debor+1.578
\\\\\\\\+1.567
 Russo+1.466
Neg logit contributions
spot-1.450
amy-1.431
 laps-1.415
ground-1.385
ooter-1.380
Token bed
Token ID3996
Feature activation-1.49e+00

Pos logit contributions
�士+2.369
 conclud+1.726
 Debor+1.706
\\\\\\\\+1.703
 Russo+1.594
Neg logit contributions
spot-1.383
amy-1.365
 laps-1.353
ground-1.324
arten-1.312
Token,
Token ID11
Feature activation-4.42e+00

Pos logit contributions
�士+1.414
 conclud+0.991
 Debor+0.978
\\\\\\\\+0.977
 Russo+0.906
Neg logit contributions
spot-1.035
amy-1.022
 laps-1.016
ground-0.997
arten-0.987
Token Free
Token ID3232
Feature activation+9.36e-01

Pos logit contributions
�士+0.600
 Debor+0.457
\\\\\\\\+0.456
 conclud+0.456
 Russo+0.435
Neg logit contributions
spot-0.227
amy-0.224
 laps-0.219
ground-0.213
arten-0.212
Token =
Token ID796
Feature activation-2.71e+00

Pos logit contributions
spot+0.583
amy+0.573
 laps+0.572
ground+0.560
ooter+0.552
Neg logit contributions
�士-0.966
 conclud-0.702
 Debor-0.682
\\\\\\\\-0.680
 Russo-0.631
Token 80
Token ID4019
Feature activation+3.74e+00

Pos logit contributions
�士+2.648
 conclud+1.866
 Debor+1.854
\\\\\\\\+1.846
 Russo+1.734
Neg logit contributions
spot-1.771
amy-1.755
 laps-1.730
arten-1.695
ooter-1.692
Token)
Token ID8
Feature activation-3.51e+00

Pos logit contributions
 laps+2.135
spot+2.127
amy+2.117
ground+2.072
 Freedom+2.002
Neg logit contributions
�士-4.162
 conclud-3.098
 Debor-2.916
\\\\\\\\-2.876
ntil-2.836
Token
Token ID198
Feature activation-5.28e+00

Pos logit contributions
�士+3.110
 conclud+2.120
 Debor+2.104
\\\\\\\\+2.091
 Russo+1.936
Neg logit contributions
spot-2.578
amy-2.561
 laps-2.534
ground-2.497
arten-2.490
Token
Token ID198
Feature activation-1.18e+01

Pos logit contributions
�士+3.704
 Debor+2.621
\\\\\\\\+2.605
 RW+2.496
 Russo+2.490
Neg logit contributions
spot-4.179
amy-4.150
arten-4.137
ooter-4.107
 laps-4.086
Token27
Token ID1983
Feature activation-2.62e+00

Pos logit contributions
�士+7.993
\\\\\\\\+5.140
 Debor+4.739
 conclud+4.566
utsu+4.547
Neg logit contributions
 laps-9.460
ooter-9.443
arten-9.373
amy-9.348
 Freedom-9.329
Token "
Token ID366
Feature activation+2.20e-01

Pos logit contributions
�士+2.584
 Debor+1.858
\\\\\\\\+1.853
 conclud+1.847
 Russo+1.737
Neg logit contributions
spot-1.649
amy-1.630
 laps-1.609
ground-1.578
arten-1.577
Token 1
Token ID352
Feature activation-2.84e+00

Pos logit contributions
spot+0.137
amy+0.134
 laps+0.134
ground+0.131
ooter+0.129
Neg logit contributions
�士-0.224
 conclud-0.163
\\\\\\\\-0.160
 Debor-0.159
 Russo-0.149
Tokenms
Token ID907
Feature activation+2.39e+00

Pos logit contributions
�士+2.695
 conclud+1.898
\\\\\\\\+1.889
 Debor+1.863
 Russo+1.739
Neg logit contributions
spot-1.902
amy-1.894
 laps-1.859
ooter-1.841
arten-1.841
Token G
Token ID402
Feature activation+4.95e+00

Pos logit contributions
spot+1.863
 laps+1.843
amy+1.835
ground+1.799
 Freedom+1.786
Neg logit contributions
�士-2.044
 conclud-1.396
 Debor-1.356
\\\\\\\\-1.346
 Russo-1.225
Token other
Token ID584
Feature activation+2.28e+00

Pos logit contributions
spot+0.851
amy+0.842
 laps+0.839
ground+0.822
arten+0.813
Neg logit contributions
�士-1.173
 conclud-0.825
\\\\\\\\-0.816
 Debor-0.810
 Russo-0.745
Token words
Token ID2456
Feature activation-1.60e+00

Pos logit contributions
spot+1.547
 laps+1.544
amy+1.530
ground+1.492
arten+1.470
Neg logit contributions
�士-2.209
 conclud-1.550
\\\\\\\\-1.543
 Debor-1.515
utsu-1.388
Token:
Token ID25
Feature activation+9.66e-01

Pos logit contributions
�士+1.474
 conclud+1.033
 Debor+1.011
\\\\\\\\+1.005
 Russo+0.938
Neg logit contributions
spot-1.139
amy-1.123
 laps-1.113
ground-1.093
ooter-1.092
Token One
Token ID1881
Feature activation-1.32e+00

Pos logit contributions
spot+0.612
amy+0.605
 laps+0.605
ground+0.590
arten+0.584
Neg logit contributions
�士-0.972
\\\\\\\\-0.697
 conclud-0.694
 Debor-0.682
 Russo-0.634
Token plus
Token ID5556
Feature activation-6.01e+00

Pos logit contributions
�士+1.316
 conclud+0.942
\\\\\\\\+0.931
 Debor+0.928
 Russo+0.862
Neg logit contributions
spot-0.854
amy-0.842
 laps-0.839
ground-0.820
arten-0.812
Token one
Token ID530
Feature activation-1.17e+01

Pos logit contributions
�士+5.296
 conclud+3.646
 Debor+3.627
\\\\\\\\+3.566
 Russo+3.349
Neg logit contributions
spot-4.392
amy-4.332
 laps-4.250
ground-4.202
ooter-4.170
Token equals
Token ID21767
Feature activation-9.39e+00

Pos logit contributions
�士+8.133
 Debor+5.440
 conclud+5.417
 Russo+5.037
\\\\\\\\+4.996
Neg logit contributions
spot-9.546
amy-9.533
ooter-9.276
llan-9.157
ground-9.141
Token "
Token ID366
Feature activation+8.65e-01

Pos logit contributions
�士+7.676
 conclud+5.289
 Debor+5.257
 RW+5.003
 Russo+4.966
Neg logit contributions
spot-7.044
amy-6.771
ooter-6.629
arten-6.603
dirty-6.532
TokenThat
Token ID2504
Feature activation+2.40e-01

Pos logit contributions
spot+0.559
amy+0.550
 laps+0.539
ground+0.539
arten+0.528
Neg logit contributions
�士-0.866
 conclud-0.625
 Debor-0.614
\\\\\\\\-0.614
 Russo-0.571
Token's
Token ID338
Feature activation-3.24e+00

Pos logit contributions
spot+0.164
amy+0.161
 laps+0.160
ground+0.158
arten+0.156
Neg logit contributions
�士-0.231
 conclud-0.163
\\\\\\\\-0.161
 Debor-0.160
 Russo-0.148
Token unfair
Token ID11675
Feature activation-2.58e+00

Pos logit contributions
�士+3.123
 conclud+2.229
 Debor+2.225
\\\\\\\\+2.184
 Russo+2.080
Neg logit contributions
spot-2.118
amy-2.089
 laps-2.062
ground-2.022
ooter-2.013
Token didn
Token ID1422
Feature activation+1.49e+00

Pos logit contributions
amy+0.941
spot+0.940
 laps+0.928
ground+0.906
arten+0.903
Neg logit contributions
�士-1.268
 conclud-0.886
\\\\\\\\-0.874
 Debor-0.870
 Inquisitor-0.800
Token
Token ID447
Feature activation-1.92e-01

Pos logit contributions
spot+0.742
amy+0.731
 laps+0.720
ground+0.708
ooter+0.689
Neg logit contributions
�士-1.736
 conclud-1.335
 Debor-1.279
\\\\\\\\-1.263
ntil-1.216
Token
Token ID247
Feature activation+6.66e-01

Pos logit contributions
�士+0.146
 conclud+0.094
 Debor+0.092
\\\\\\\\+0.091
 Russo+0.082
Neg logit contributions
spot-0.166
amy-0.165
 laps-0.164
ground-0.162
arten-0.160
Tokent
Token ID83
Feature activation+1.20e+00

Pos logit contributions
spot+0.509
amy+0.501
 laps+0.495
ground+0.491
arten+0.486
Neg logit contributions
�士-0.587
 conclud-0.397
\\\\\\\\-0.391
 Debor-0.391
 Russo-0.360
Token seem
Token ID1283
Feature activation+2.15e+00

Pos logit contributions
spot+0.792
 laps+0.783
amy+0.778
ground+0.759
arten+0.753
Neg logit contributions
�士-1.184
\\\\\\\\-0.837
 conclud-0.825
 Debor-0.819
 Russo-0.762
Token f
Token ID277
Feature activation-1.16e+01

Pos logit contributions
spot+1.371
 laps+1.356
amy+1.350
ground+1.309
ooter+1.285
Neg logit contributions
�士-2.152
 conclud-1.551
\\\\\\\\-1.542
 Debor-1.539
 Russo-1.414
Tokenazed
Token ID13865
Feature activation+9.94e-02

Pos logit contributions
�士+8.001
 Debor+5.402
\\\\\\\\+5.327
 conclud+5.116
utsu+5.035
Neg logit contributions
spot-9.231
 laps-9.175
 Freedom-9.069
dirty-8.987
arten-8.905
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
spot+0.071
amy+0.070
 laps+0.069
ground+0.068
arten+0.067
Neg logit contributions
�士-0.093
 conclud-0.065
\\\\\\\\-0.064
 Debor-0.063
 Russo-0.059
Token
Token ID198
Feature activation+1.29e+00

Pos logit contributions
spot+0.167
amy+0.166
 laps+0.165
ground+0.161
ooter+0.159
Neg logit contributions
�士-0.212
 conclud-0.149
\\\\\\\\-0.145
 Debor-0.144
 Russo-0.132
Token
Token ID198
Feature activation-1.92e+00

Pos logit contributions
spot+0.884
amy+0.875
 laps+0.871
ground+0.855
ooter+0.839
Neg logit contributions
�士-1.261
 conclud-0.903
 Debor-0.861
\\\\\\\\-0.860
ntil-0.800
TokenWhile
Token ID3633
Feature activation+3.46e+00

Pos logit contributions
�士+1.246
 conclud+0.705
\\\\\\\\+0.695
 Debor+0.691
 Russo+0.600
Neg logit contributions
spot-1.879
amy-1.863
 laps-1.858
ground-1.830
arten-1.823
Token About
Token ID7994
Feature activation-3.26e+00

Pos logit contributions
�士+0.791
 conclud+0.573
\\\\\\\\+0.563
 Debor+0.561
 Russo+0.524
Neg logit contributions
spot-0.495
amy-0.489
 laps-0.484
ground-0.475
ooter-0.470
Token Dw
Token ID19113
Feature activation-8.62e-01

Pos logit contributions
�士+3.213
 Debor+2.307
 conclud+2.282
\\\\\\\\+2.271
 Russo+2.135
Neg logit contributions
spot-2.087
amy-2.063
 laps-2.047
ground-1.999
arten-1.993
Tokenark
Token ID668
Feature activation+4.31e-01

Pos logit contributions
�士+0.768
 Debor+0.526
 conclud+0.525
\\\\\\\\+0.523
 Russo+0.483
Neg logit contributions
spot-0.630
amy-0.623
 laps-0.621
ground-0.607
ooter-0.603
Tokenadh
Token ID24411
Feature activation-3.12e+00

Pos logit contributions
spot+0.237
amy+0.234
 laps+0.232
ground+0.226
arten+0.224
Neg logit contributions
�士-0.466
 conclud-0.346
 Debor-0.342
\\\\\\\\-0.342
 Russo-0.321
Tokenish
Token ID680
Feature activation-6.94e+00

Pos logit contributions
�士+3.135
 Debor+2.307
\\\\\\\\+2.294
 conclud+2.263
 Russo+2.182
Neg logit contributions
spot-1.812
amy-1.801
 laps-1.798
ground-1.745
arten-1.738
Token Temple
Token ID10857
Feature activation-1.16e+01

Pos logit contributions
�士+5.971
 Debor+4.227
\\\\\\\\+4.086
 conclud+3.994
 Inquisitor+3.973
Neg logit contributions
spot-4.898
amy-4.868
 laps-4.855
arten-4.793
ooter-4.788
Token Here
Token ID3423
Feature activation-5.71e+00

Pos logit contributions
�士+7.679
 Debor+4.884
\\\\\\\\+4.634
 Russo+4.525
 RW+4.514
Neg logit contributions
 laps-9.767
ooter-9.623
spot-9.623
amy-9.607
arten-9.606
Token
Token ID198
Feature activation-3.58e+00

Pos logit contributions
�士+4.674
 Debor+3.144
 conclud+3.124
\\\\\\\\+3.098
 RW+2.858
Neg logit contributions
 laps-4.339
spot-4.332
amy-4.315
arten-4.234
ground-4.189
Token
Token ID198
Feature activation-5.86e+00

Pos logit contributions
�士+2.714
 Debor+1.918
\\\\\\\\+1.901
 Russo+1.788
 RW+1.786
Neg logit contributions
spot-2.774
amy-2.752
arten-2.722
 laps-2.707
ooter-2.700
Token8
Token ID23
Feature activation-1.54e+00

Pos logit contributions
�士+4.302
\\\\\\\\+2.691
 Debor+2.600
 conclud+2.571
isl+2.394
Neg logit contributions
 laps-4.999
amy-4.907
arten-4.875
spot-4.861
ooter-4.852
Token.
Token ID13
Feature activation+1.34e+00

Pos logit contributions
�士+1.374
 Debor+0.946
\\\\\\\\+0.943
 conclud+0.941
 Russo+0.876
Neg logit contributions
spot-1.115
amy-1.104
 laps-1.094
ground-1.074
arten-1.072
Token
Token ID247
Feature activation-4.82e-01

Pos logit contributions
�士+0.449
 conclud+0.312
 Debor+0.307
\\\\\\\\+0.305
 Russo+0.282
Neg logit contributions
spot-0.371
amy-0.368
 laps-0.364
ground-0.358
ooter-0.355
Tokens
Token ID82
Feature activation-2.61e+00

Pos logit contributions
�士+0.362
 conclud+0.226
 Debor+0.221
\\\\\\\\+0.220
 Russo+0.197
Neg logit contributions
spot-0.431
amy-0.426
 laps-0.422
ground-0.418
ooter-0.413
Token talk
Token ID1561
Feature activation-1.42e+00

Pos logit contributions
�士+2.526
 conclud+1.823
 Debor+1.785
\\\\\\\\+1.785
 Russo+1.668
Neg logit contributions
spot-1.704
amy-1.684
 laps-1.669
ground-1.641
arten-1.633
Token THE
Token ID3336
Feature activation-1.17e+00

Pos logit contributions
�士+1.401
 conclud+1.004
\\\\\\\\+0.989
 Debor+0.987
 Russo+0.913
Neg logit contributions
spot-0.921
amy-0.910
 laps-0.906
ground-0.886
ooter-0.874
Token FANT
Token ID29250
Feature activation-2.85e+00

Pos logit contributions
�士+1.112
 conclud+0.781
 Debor+0.771
\\\\\\\\+0.770
 Russo+0.710
Neg logit contributions
spot-0.801
amy-0.790
 laps-0.785
ground-0.771
ooter-0.765
TokenAST
Token ID11262
Feature activation-1.15e+01

Pos logit contributions
�士+2.978
 conclud+2.170
\\\\\\\\+2.154
 Debor+2.144
 Russo+2.031
Neg logit contributions
spot-1.659
amy-1.622
 laps-1.620
ground-1.583
arten-1.577
TokenIC
Token ID2149
Feature activation-1.83e+00

Pos logit contributions
�士+8.532
\\\\\\\\+5.847
 conclud+5.483
 Inquisitor+5.438
 RW+5.409
Neg logit contributions
arten-8.929
 laps-8.834
spot-8.803
ground-8.787
sterdam-8.778
Token F
Token ID376
Feature activation-8.03e+00

Pos logit contributions
�士+1.742
 conclud+1.227
 Debor+1.210
\\\\\\\\+1.208
 Russo+1.119
Neg logit contributions
spot-1.258
amy-1.241
 laps-1.234
ground-1.211
ooter-1.201
TokenOUR
Token ID11698
Feature activation-3.24e+00

Pos logit contributions
�士+7.012
\\\\\\\\+4.833
 Debor+4.689
 conclud+4.678
 Russo+4.482
Neg logit contributions
spot-5.697
 laps-5.692
amy-5.555
ground-5.496
arten-5.481
Token!
Token ID0
Feature activation+1.74e+00

Pos logit contributions
�士+2.981
 conclud+2.069
 Debor+2.040
\\\\\\\\+2.033
 Russo+1.878
Neg logit contributions
spot-2.328
amy-2.298
 laps-2.286
ground-2.241
ooter-2.223
Token
Token ID198
Feature activation+9.41e-01

Pos logit contributions
spot+1.194
amy+1.179
 laps+1.165
ground+1.148
ooter+1.129
Neg logit contributions
�士-1.656
 conclud-1.165
 Debor-1.130
\\\\\\\\-1.127
 Russo-1.037
Token Free
Token ID3232
Feature activation+1.10e+00

Pos logit contributions
�士+0.957
 Debor+0.729
\\\\\\\\+0.727
 conclud+0.726
 Russo+0.693
Neg logit contributions
spot-0.364
amy-0.359
 laps-0.351
ground-0.341
arten-0.340
Token =
Token ID796
Feature activation-2.02e+00

Pos logit contributions
spot+0.671
 laps+0.662
amy+0.657
ground+0.645
ooter+0.632
Neg logit contributions
�士-1.148
 conclud-0.834
 Debor-0.809
\\\\\\\\-0.808
ntil-0.750
Token 80
Token ID4019
Feature activation+3.06e+00

Pos logit contributions
�士+2.055
 conclud+1.481
 Debor+1.465
\\\\\\\\+1.464
 Russo+1.372
Neg logit contributions
spot-1.246
amy-1.233
 laps-1.215
arten-1.189
ooter-1.186
Token)
Token ID8
Feature activation-3.01e+00

Pos logit contributions
spot+1.865
amy+1.840
 laps+1.839
ground+1.791
arten+1.759
Neg logit contributions
�士-3.123
 conclud-2.267
 Debor-2.255
\\\\\\\\-2.229
 Russo-2.092
Token
Token ID198
Feature activation-5.32e+00

Pos logit contributions
�士+2.800
 conclud+1.954
 Debor+1.936
\\\\\\\\+1.928
 Russo+1.791
Neg logit contributions
spot-2.105
amy-2.085
 laps-2.065
ground-2.031
arten-2.020
Token
Token ID198
Feature activation-1.15e+01

Pos logit contributions
�士+3.702
 Debor+2.617
\\\\\\\\+2.604
 RW+2.503
 Russo+2.490
Neg logit contributions
spot-4.219
amy-4.192
arten-4.181
ooter-4.151
 laps-4.123
Token27
Token ID1983
Feature activation-2.00e+00

Pos logit contributions
�士+8.506
\\\\\\\\+5.631
 Debor+5.258
 conclud+5.108
utsu+5.077
Neg logit contributions
ooter-8.675
 laps-8.656
arten-8.643
amy-8.545
ground-8.458
Token"
Token ID1
Feature activation+2.09e+00

Pos logit contributions
�士+2.007
 conclud+1.444
 Debor+1.436
\\\\\\\\+1.430
 Russo+1.340
Neg logit contributions
spot-1.249
amy-1.236
 laps-1.223
ground-1.198
arten-1.191
Token 12
Token ID1105
Feature activation-2.22e-01

Pos logit contributions
spot+1.185
 laps+1.162
amy+1.157
ground+1.123
ooter+1.107
Neg logit contributions
�士-2.223
 conclud-1.657
\\\\\\\\-1.629
 Debor-1.621
 Russo-1.528
Tokenms
Token ID907
Feature activation+2.65e+00

Pos logit contributions
�士+0.220
 conclud+0.158
 Debor+0.155
\\\\\\\\+0.155
 Russo+0.144
Neg logit contributions
spot-0.144
amy-0.142
 laps-0.141
ground-0.138
arten-0.136
Token G
Token ID402
Feature activation+4.44e+00

Pos logit contributions
spot+2.036
 laps+2.023
amy+2.005
 Freedom+1.964
ground+1.959
Neg logit contributions
�士-2.290
 conclud-1.575
\\\\\\\\-1.524
 Debor-1.518
 Russo-1.365
Token35
Token ID2327
Feature activation-9.55e-01

Pos logit contributions
�士+1.396
 conclud+0.987
 Debor+0.980
\\\\\\\\+0.978
 Russo+0.909
Neg logit contributions
spot-0.979
amy-0.966
 laps-0.960
ground-0.940
arten-0.937
Tokenz
Token ID89
Feature activation+5.35e-01

Pos logit contributions
�士+0.880
 conclud+0.612
 Debor+0.603
\\\\\\\\+0.603
 Russo+0.557
Neg logit contributions
spot-0.682
amy-0.675
 laps-0.670
ground-0.658
arten-0.653
Token 1
Token ID352
Feature activation+1.12e+00

Pos logit contributions
spot+0.343
amy+0.339
 laps+0.337
ground+0.330
ooter+0.326
Neg logit contributions
�士-0.533
 conclud-0.383
\\\\\\\\-0.377
 Debor-0.374
 Russo-0.348
Token GER
Token ID44186
Feature activation-1.79e+00

Pos logit contributions
spot+0.784
amy+0.769
 laps+0.766
ground+0.753
arten+0.745
Neg logit contributions
�士-1.048
 conclud-0.739
 Debor-0.720
\\\\\\\\-0.716
utsu-0.658
TokenON
Token ID1340
Feature activation-2.16e+00

Pos logit contributions
�士+1.403
 conclud+0.900
\\\\\\\\+0.885
 Debor+0.882
 Russo+0.805
Neg logit contributions
spot-1.516
amy-1.504
 laps-1.497
ground-1.468
arten-1.462
TokenIM
Token ID3955
Feature activation-1.14e+01

Pos logit contributions
�士+1.761
 conclud+1.155
\\\\\\\\+1.145
 Debor+1.143
 Russo+1.040
Neg logit contributions
spot-1.755
amy-1.739
 laps-1.729
ground-1.701
arten-1.693
TokenO
Token ID46
Feature activation-4.86e+00

Pos logit contributions
�士+6.625
\\\\\\\\+4.472
 Russo+4.251
 RW+4.188
 Inquisitor+4.050
Neg logit contributions
amy-9.988
spot-9.976
ortium-9.974
 laps-9.879
sterdam-9.834
Token T
Token ID309
Feature activation-8.94e+00

Pos logit contributions
�士+3.937
 conclud+2.610
 Debor+2.568
\\\\\\\\+2.567
 Russo+2.359
Neg logit contributions
spot-3.895
amy-3.891
 laps-3.840
ground-3.785
arten-3.777
TokenOC
Token ID4503
Feature activation-5.48e+00

Pos logit contributions
�士+5.157
\\\\\\\\+3.255
 RW+2.826
 Debor+2.780
 Russo+2.760
Neg logit contributions
spot-8.470
amy-8.448
 laps-8.389
arten-8.321
dirty-8.288
Token IN
Token ID3268
Feature activation-3.66e+00

Pos logit contributions
�士+4.679
 conclud+3.203
 Debor+3.175
\\\\\\\\+3.161
 RW+2.962
Neg logit contributions
spot-4.126
amy-4.119
 laps-4.028
arten-3.995
ground-3.995
TokenIT
Token ID2043
Feature activation-3.12e+00

Pos logit contributions
�士+3.381
 conclud+2.369
\\\\\\\\+2.359
 Debor+2.344
 Russo+2.186
Neg logit contributions
spot-2.541
amy-2.526
 laps-2.502
arten-2.449
ground-2.441
TokenOD
Token ID3727
Feature activation-3.92e-02

Pos logit contributions
�士+2.410
 conclud+1.611
\\\\\\\\+1.594
 Debor+1.592
 Russo+1.460
Neg logit contributions
spot-2.135
 laps-2.110
amy-2.106
arten-2.064
ooter-2.058
Token =
Token ID796
Feature activation-2.05e+00

Pos logit contributions
�士+0.038
 conclud+0.027
\\\\\\\\+0.027
 Debor+0.027
 Russo+0.025
Neg logit contributions
spot-0.026
amy-0.025
 laps-0.025
ground-0.025
arten-0.024
Token Normal
Token ID14435
Feature activation+1.46e+00

Pos logit contributions
�士+2.046
 conclud+1.466
 Debor+1.462
\\\\\\\\+1.453
 Russo+1.370
Neg logit contributions
spot-1.289
amy-1.274
 laps-1.257
arten-1.229
ooter-1.227
Token)
Token ID8
Feature activation-2.81e+00

Pos logit contributions
spot+0.924
amy+0.912
 laps+0.906
ground+0.890
arten+0.878
Neg logit contributions
�士-1.463
 conclud-1.055
 Debor-1.042
\\\\\\\\-1.034
 Russo-0.967
Token
Token ID198
Feature activation-3.15e+00

Pos logit contributions
�士+2.613
 conclud+1.824
 Debor+1.808
\\\\\\\\+1.801
 Russo+1.671
Neg logit contributions
spot-1.962
amy-1.941
 laps-1.925
ground-1.891
arten-1.880
Token
Token ID198
Feature activation-1.13e+01

Pos logit contributions
�士+2.460
 Debor+1.720
\\\\\\\\+1.711
 Russo+1.612
 RW+1.601
Neg logit contributions
spot-2.423
amy-2.404
arten-2.376
 laps-2.370
ooter-2.360
Token27
Token ID1983
Feature activation-2.13e+00

Pos logit contributions
�士+8.207
\\\\\\\\+5.431
 Debor+5.119
 RW+4.886
 conclud+4.870
Neg logit contributions
ooter-8.674
 laps-8.670
arten-8.645
amy-8.566
spot-8.447
Token "
Token ID366
Feature activation-9.75e-01

Pos logit contributions
�士+2.125
 conclud+1.527
 Debor+1.525
\\\\\\\\+1.520
 Russo+1.424
Neg logit contributions
spot-1.332
amy-1.316
 laps-1.301
ground-1.276
arten-1.271
Token 1
Token ID352
Feature activation-1.55e+00

Pos logit contributions
�士+0.965
 conclud+0.692
 Debor+0.682
\\\\\\\\+0.682
 Russo+0.635
Neg logit contributions
spot-0.629
amy-0.621
 laps-0.617
ground-0.604
arten-0.599
Tokenms
Token ID907
Feature activation+2.29e+00

Pos logit contributions
�士+1.509
 conclud+1.076
\\\\\\\\+1.072
 Debor+1.070
 Russo+0.997
Neg logit contributions
spot-1.000
amy-0.989
 laps-0.979
ground-0.960
arten-0.957
Token G
Token ID402
Feature activation+4.68e+00

Pos logit contributions
spot+1.770
 laps+1.749
amy+1.730
ground+1.711
 Freedom+1.693
Neg logit contributions
�士-1.990
 conclud-1.370
 Debor-1.315
\\\\\\\\-1.310
 Russo-1.181
Token
Token ID198
Feature activation-2.33e+00

Pos logit contributions
�士+0.528
 Debor+0.364
\\\\\\\\+0.363
 conclud+0.360
 Russo+0.337
Neg logit contributions
spot-0.436
amy-0.432
 laps-0.428
arten-0.420
ground-0.420
TokenSee
Token ID6214
Feature activation-5.00e+00

Pos logit contributions
�士+2.104
\\\\\\\\+1.455
 conclud+1.432
 Debor+1.429
 Russo+1.321
Neg logit contributions
spot-1.652
 laps-1.649
amy-1.647
arten-1.613
ground-1.602
Token the
Token ID262
Feature activation-5.54e+00

Pos logit contributions
�士+4.261
 Debor+3.007
\\\\\\\\+2.965
 conclud+2.886
 Russo+2.778
Neg logit contributions
spot-3.663
amy-3.598
arten-3.534
 laps-3.520
ground-3.511
Token full
Token ID1336
Feature activation-4.48e+00

Pos logit contributions
�士+4.259
 Debor+2.895
\\\\\\\\+2.801
 conclud+2.754
 RW+2.668
Neg logit contributions
spot-4.441
amy-4.396
arten-4.360
ooter-4.336
 laps-4.278
Token list
Token ID1351
Feature activation-6.36e+00

Pos logit contributions
�士+3.403
 Debor+2.249
\\\\\\\\+2.184
 conclud+2.172
 RW+2.041
Neg logit contributions
spot-3.743
amy-3.718
arten-3.635
 laps-3.634
ooter-3.633
Token of
Token ID286
Feature activation-1.12e+01

Pos logit contributions
�士+4.667
 Debor+3.321
\\\\\\\\+3.219
 Russo+3.143
 RW+3.113
Neg logit contributions
spot-4.967
amy-4.944
arten-4.838
ooter-4.834
 laps-4.799
Token previous
Token ID2180
Feature activation-2.08e+00

Pos logit contributions
�士+7.775
 Debor+5.423
\\\\\\\\+5.283
 conclud+5.168
 RW+5.137
Neg logit contributions
amy-9.054
spot-8.916
ooter-8.847
arten-8.838
ground-8.833
Token award
Token ID5764
Feature activation-9.80e+00

Pos logit contributions
�士+2.319
 conclud+1.748
 Debor+1.748
\\\\\\\\+1.744
 Russo+1.650
Neg logit contributions
spot-1.044
amy-1.025
 laps-1.008
ground-0.990
ooter-0.986
Token winners
Token ID14591
Feature activation-4.89e+00

Pos logit contributions
�士+5.327
\\\\\\\\+3.282
 Debor+3.276
 conclud+3.107
 RW+3.078
Neg logit contributions
amy-9.271
spot-9.235
ooter-9.146
dirty-9.114
ground-9.081
Token.
Token ID13
Feature activation-4.62e+00

Pos logit contributions
�士+3.855
 Debor+2.724
\\\\\\\\+2.673
 conclud+2.548
 Russo+2.507
Neg logit contributions
spot-3.741
amy-3.729
ooter-3.641
 laps-3.636
arten-3.622
Token
Token ID198
Feature activation-1.77e+00

Pos logit contributions
�士+3.900
 Debor+2.643
 conclud+2.627
\\\\\\\\+2.615
 RW+2.402
Neg logit contributions
spot-3.511
 laps-3.469
amy-3.464
ground-3.407
arten-3.397
Tokenaur
Token ID2899
Feature activation-1.46e+00

Pos logit contributions
spot+3.804
amy+3.801
ground+3.690
 laps+3.685
arten+3.660
Neg logit contributions
�士-3.703
 conclud-2.449
\\\\\\\\-2.281
 Debor-2.264
 Russo-2.023
Token #
Token ID1303
Feature activation-8.12e-01

Pos logit contributions
�士+1.381
 conclud+0.974
 Debor+0.965
\\\\\\\\+0.962
 Russo+0.898
Neg logit contributions
spot-0.989
amy-0.979
 laps-0.970
ground-0.952
arten-0.949
Token2
Token ID17
Feature activation-1.49e-01

Pos logit contributions
�士+0.829
 conclud+0.602
 Debor+0.594
\\\\\\\\+0.593
 Russo+0.555
Neg logit contributions
spot-0.497
amy-0.491
 laps-0.487
ground-0.476
arten-0.473
Token
Token ID198
Feature activation-3.52e+00

Pos logit contributions
�士+0.139
 conclud+0.098
\\\\\\\\+0.096
 Debor+0.096
 Russo+0.089
Neg logit contributions
spot-0.104
amy-0.103
 laps-0.102
ground-0.100
arten-0.099
Token
Token ID198
Feature activation-3.96e+00

Pos logit contributions
�士+2.789
 Debor+1.954
\\\\\\\\+1.932
 Russo+1.826
 RW+1.807
Neg logit contributions
spot-2.686
amy-2.663
arten-2.631
 laps-2.626
ooter-2.607
TokenHad
Token ID25383
Feature activation-1.11e+01

Pos logit contributions
�士+3.276
\\\\\\\\+2.144
 conclud+2.131
 Debor+2.120
 Russo+1.948
Neg logit contributions
spot-3.108
 laps-3.101
amy-3.084
arten-3.032
ooter-3.023
Tokenros
Token ID4951
Feature activation+4.55e+00

Pos logit contributions
�士+4.254
utsu+1.971
isl+1.955
 Debor+1.938
 Russo+1.913
Neg logit contributions
spot-11.371
 laps-11.369
 Freedom-11.305
amy-11.211
dirty-11.201
Tokenaur
Token ID2899
Feature activation-1.22e+00

Pos logit contributions
spot+3.886
amy+3.884
ground+3.770
 laps+3.765
arten+3.739
Neg logit contributions
�士-3.798
 conclud-2.517
\\\\\\\\-2.341
 Debor-2.320
 Russo-2.072
Token #
Token ID1303
Feature activation-5.78e-01

Pos logit contributions
�士+1.168
 conclud+0.826
 Debor+0.817
\\\\\\\\+0.815
 Russo+0.759
Neg logit contributions
spot-0.827
amy-0.818
 laps-0.811
ground-0.795
arten-0.791
Token2
Token ID17
Feature activation-1.05e-01

Pos logit contributions
�士+0.598
 conclud+0.436
 Debor+0.431
\\\\\\\\+0.430
 Russo+0.403
Neg logit contributions
spot-0.345
amy-0.341
 laps-0.339
ground-0.331
arten-0.329
Token
Token ID198
Feature activation-3.30e+00

Pos logit contributions
�士+0.098
 conclud+0.069
\\\\\\\\+0.068
 Debor+0.068
 Russo+0.063
Neg logit contributions
spot-0.073
amy-0.072
 laps-0.072
ground-0.070
arten-0.070
Token grab
Token ID5552
Feature activation-2.30e+00

Pos logit contributions
�士+8.690
 conclud+6.407
 Debor+6.357
 Russo+5.890
 Inquisitor+5.863
Neg logit contributions
spot-6.754
amy-6.640
ooter-6.597
arten-6.555
ground-6.502
Token someone
Token ID2130
Feature activation-3.76e+00

Pos logit contributions
�士+2.276
 conclud+1.630
\\\\\\\\+1.609
 Debor+1.601
 Russo+1.490
Neg logit contributions
spot-1.486
amy-1.468
 laps-1.462
ground-1.429
arten-1.414
Token by
Token ID416
Feature activation-5.74e+00

Pos logit contributions
�士+3.357
 conclud+2.318
 Debor+2.284
\\\\\\\\+2.274
 Russo+2.103
Neg logit contributions
spot-2.765
amy-2.735
 laps-2.709
ground-2.668
arten-2.651
Token the
Token ID262
Feature activation-2.45e+00

Pos logit contributions
�士+5.090
 conclud+3.573
 Debor+3.542
\\\\\\\\+3.477
 Russo+3.276
Neg logit contributions
spot-4.152
amy-4.108
arten-3.977
 laps-3.972
ground-3.963
Token ankles
Token ID42415
Feature activation-3.96e+00

Pos logit contributions
�士+2.591
 conclud+1.906
 Debor+1.884
\\\\\\\\+1.881
 Russo+1.766
Neg logit contributions
spot-1.413
amy-1.394
 laps-1.380
ground-1.350
arten-1.338
Token and
Token ID290
Feature activation-1.09e+01

Pos logit contributions
�士+3.609
 conclud+2.537
 Debor+2.506
\\\\\\\\+2.486
 Russo+2.311
Neg logit contributions
spot-2.802
amy-2.770
 laps-2.728
ground-2.690
ooter-2.686
Token climb
Token ID12080
Feature activation+2.14e+00

Pos logit contributions
�士+9.109
 conclud+6.804
 Debor+6.612
 Russo+6.216
utsu+6.197
Neg logit contributions
spot-7.184
amy-7.148
ooter-7.018
ortium-7.003
arten-6.990
Token on
Token ID319
Feature activation-1.73e+00

Pos logit contributions
 laps+1.298
spot+1.272
amy+1.266
ground+1.241
 Freedom+1.216
Neg logit contributions
�士-2.243
\\\\\\\\-1.625
 conclud-1.611
 Debor-1.563
 Russo-1.462
Token top
Token ID1353
Feature activation-1.41e+00

Pos logit contributions
�士+1.714
 conclud+1.226
\\\\\\\\+1.211
 Debor+1.208
 Russo+1.124
Neg logit contributions
spot-1.125
amy-1.112
 laps-1.106
ground-1.082
arten-1.071
Token of
Token ID286
Feature activation-2.66e-01

Pos logit contributions
�士+1.295
 conclud+0.904
 Debor+0.891
\\\\\\\\+0.887
 Russo+0.822
Neg logit contributions
spot-1.003
amy-0.990
 laps-0.981
ground-0.965
arten-0.960
Token them
Token ID606
Feature activation-9.55e-01

Pos logit contributions
�士+0.266
 conclud+0.191
\\\\\\\\+0.188
 Debor+0.185
 Russo+0.173
Neg logit contributions
spot-0.171
amy-0.170
 laps-0.170
ground-0.165
ooter-0.162
Token terms
Token ID2846
Feature activation+9.04e-01

Pos logit contributions
�士+0.996
 conclud+0.711
 Debor+0.702
\\\\\\\\+0.701
 Russo+0.652
Neg logit contributions
spot-0.665
amy-0.657
 laps-0.652
ground-0.639
arten-0.633
Token of
Token ID286
Feature activation+2.83e-01

Pos logit contributions
spot+0.602
 laps+0.600
amy+0.598
ground+0.583
arten+0.572
Neg logit contributions
�士-0.902
 conclud-0.646
\\\\\\\\-0.624
 Debor-0.613
ntil-0.578
Token a
Token ID257
Feature activation+1.83e+00

Pos logit contributions
spot+0.176
 laps+0.175
amy+0.174
ground+0.169
arten+0.168
Neg logit contributions
�士-0.287
 conclud-0.206
\\\\\\\\-0.205
 Debor-0.204
utsu-0.187
Token qu
Token ID627
Feature activation-1.52e+00

Pos logit contributions
spot+1.195
 laps+1.186
amy+1.185
ground+1.150
ooter+1.133
Neg logit contributions
�士-1.806
 conclud-1.284
 Debor-1.276
\\\\\\\\-1.266
 Inquisitor-1.168
Tokenid
Token ID312
Feature activation-4.18e+00

Pos logit contributions
�士+1.229
 conclud+0.804
 Debor+0.791
\\\\\\\\+0.789
 Russo+0.717
Neg logit contributions
spot-1.254
amy-1.242
 laps-1.235
ground-1.215
ooter-1.207
Token pro
Token ID386
Feature activation-1.08e+01

Pos logit contributions
�士+4.984
 conclud+3.824
\\\\\\\\+3.776
 Debor+3.772
 Russo+3.591
Neg logit contributions
spot-1.816
amy-1.776
 laps-1.741
ground-1.706
arten-1.692
Token quo
Token ID18658
Feature activation-2.63e+00

Pos logit contributions
�士+5.876
\\\\\\\\+3.207
 Russo+3.169
 Debor+3.048
 conclud+3.025
Neg logit contributions
amy-10.688
spot-10.509
arten-10.439
dirty-10.336
ground-10.247
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
�士+2.509
 conclud+1.784
 Debor+1.761
\\\\\\\\+1.756
 Russo+1.639
Neg logit contributions
spot-1.770
amy-1.753
 laps-1.732
ground-1.702
arten-1.692
Token it
Token ID340
Feature activation+6.62e-01

Pos logit contributions
�士+1.209
 conclud+0.900
\\\\\\\\+0.892
 Debor+0.890
 Russo+0.833
Neg logit contributions
spot-0.583
amy-0.576
 laps-0.573
ground-0.555
ooter-0.549
Token
Token ID447
Feature activation+2.23e+00

Pos logit contributions
spot+0.443
 laps+0.441
amy+0.436
ground+0.424
arten+0.420
Neg logit contributions
�士-0.647
 conclud-0.456
\\\\\\\\-0.453
 Debor-0.449
 Russo-0.417
Token
Token ID247
Feature activation+3.23e-01

Pos logit contributions
spot+1.721
 laps+1.715
amy+1.712
ground+1.678
arten+1.672
Neg logit contributions
�士-1.906
 conclud-1.350
 Debor-1.282
\\\\\\\\-1.272
 Russo-1.157
Token with
Token ID351
Feature activation-3.90e+00

Pos logit contributions
�士+2.422
 conclud+1.720
 Debor+1.689
\\\\\\\\+1.683
 Russo+1.578
Neg logit contributions
spot-1.804
amy-1.789
 laps-1.758
ground-1.737
arten-1.734
Token people
Token ID661
Feature activation-3.72e+00

Pos logit contributions
�士+3.936
 conclud+2.880
 Debor+2.871
\\\\\\\\+2.841
 Russo+2.692
Neg logit contributions
spot-2.373
amy-2.353
 laps-2.300
arten-2.264
ooter-2.258
Token one
Token ID530
Feature activation-3.47e+00

Pos logit contributions
�士+3.380
 conclud+2.375
 Debor+2.349
\\\\\\\\+2.336
 Russo+2.175
Neg logit contributions
spot-2.637
amy-2.611
 laps-2.580
ground-2.542
arten-2.537
Token-
Token ID12
Feature activation-1.39e+00

Pos logit contributions
�士+3.290
 conclud+2.337
 Debor+2.310
\\\\\\\\+2.307
 Russo+2.153
Neg logit contributions
spot-2.346
amy-2.336
 laps-2.300
ground-2.265
arten-2.251
Tokenon
Token ID261
Feature activation-3.27e+00

Pos logit contributions
�士+1.381
 conclud+0.994
 Debor+0.983
\\\\\\\\+0.982
 Russo+0.917
Neg logit contributions
spot-0.885
amy-0.877
 laps-0.870
ground-0.850
ooter-0.846
Token-
Token ID12
Feature activation-1.08e+01

Pos logit contributions
�士+2.929
 Debor+2.070
\\\\\\\\+2.061
 conclud+2.032
 Russo+1.922
Neg logit contributions
spot-2.302
amy-2.271
 laps-2.244
ooter-2.208
arten-2.204
Tokenone
Token ID505
Feature activation-4.83e+00

Pos logit contributions
�士+6.505
\\\\\\\\+4.505
 Debor+4.451
utsu+4.383
isl+4.239
Neg logit contributions
 laps-8.755
 Freedom-8.620
arten-8.583
ooter-8.561
amy-8.558
Token at
Token ID379
Feature activation-3.28e+00

Pos logit contributions
�士+4.266
 conclud+2.981
 Debor+2.950
\\\\\\\\+2.942
 Russo+2.741
Neg logit contributions
spot-3.491
amy-3.462
 laps-3.411
arten-3.371
ooter-3.369
Token scale
Token ID5046
Feature activation-8.86e-01

Pos logit contributions
�士+3.108
 conclud+2.221
 Debor+2.198
\\\\\\\\+2.187
 Russo+2.058
Neg logit contributions
spot-2.198
amy-2.188
 laps-2.141
ground-2.111
arten-2.109
Token and
Token ID290
Feature activation-1.63e+00

Pos logit contributions
�士+0.837
 conclud+0.584
 Debor+0.577
\\\\\\\\+0.576
 Russo+0.532
Neg logit contributions
spot-0.618
amy-0.610
 laps-0.607
ground-0.595
ooter-0.588
Token our
Token ID674
Feature activation-5.82e-01

Pos logit contributions
�士+1.579
 conclud+1.129
 Debor+1.113
\\\\\\\\+1.109
 Russo+1.037
Neg logit contributions
spot-1.077
amy-1.065
 laps-1.054
ground-1.035
arten-1.029
Token Time
Token ID3862
Feature activation+1.13e+00

Pos logit contributions
spot+0.972
amy+0.959
 laps+0.954
ground+0.920
ooter+0.905
Neg logit contributions
�士-2.357
 conclud-1.799
 Debor-1.766
\\\\\\\\-1.763
 Russo-1.657
Token =
Token ID796
Feature activation+9.83e-01

Pos logit contributions
spot+0.722
amy+0.712
 laps+0.708
ground+0.693
arten+0.686
Neg logit contributions
�士-1.130
 conclud-0.813
 Debor-0.803
\\\\\\\\-0.801
 Russo-0.746
Token Normal
Token ID14435
Feature activation+3.66e+00

Pos logit contributions
spot+0.499
amy+0.492
 laps+0.490
ground+0.478
arten+0.468
Neg logit contributions
�士-1.108
 conclud-0.838
\\\\\\\\-0.826
 Debor-0.821
 Russo-0.773
Token)
Token ID8
Feature activation-2.06e+00

Pos logit contributions
spot+2.202
amy+2.166
 laps+2.158
ground+2.143
arten+2.081
Neg logit contributions
�士-3.790
 conclud-2.781
 Debor-2.743
\\\\\\\\-2.694
 Russo-2.533
Token
Token ID198
Feature activation-2.87e+00

Pos logit contributions
�士+1.920
 conclud+1.344
 Debor+1.326
\\\\\\\\+1.324
 Russo+1.227
Neg logit contributions
spot-1.439
amy-1.423
 laps-1.412
ground-1.387
arten-1.376
Token
Token ID198
Feature activation-1.07e+01

Pos logit contributions
�士+2.260
 Debor+1.579
\\\\\\\\+1.571
 Russo+1.478
 Inquisitor+1.467
Neg logit contributions
spot-2.192
amy-2.175
arten-2.147
 laps-2.145
ooter-2.134
Token27
Token ID1983
Feature activation-2.15e+00

Pos logit contributions
�士+8.207
\\\\\\\\+5.534
 Debor+5.215
 Inquisitor+4.994
utsu+4.984
Neg logit contributions
ooter-7.955
arten-7.952
 laps-7.945
amy-7.825
spot-7.753
Token"
Token ID1
Feature activation-1.36e-01

Pos logit contributions
�士+2.114
 conclud+1.501
 Debor+1.496
\\\\\\\\+1.489
 Russo+1.394
Neg logit contributions
spot-1.375
amy-1.364
 laps-1.344
arten-1.323
ground-1.323
Token 8
Token ID807
Feature activation+2.32e+00

Pos logit contributions
�士+0.136
 conclud+0.099
\\\\\\\\+0.097
 Debor+0.097
 Russo+0.090
Neg logit contributions
spot-0.086
amy-0.085
 laps-0.084
ground-0.082
ooter-0.081
Tokenms
Token ID907
Feature activation+1.83e+00

Pos logit contributions
 laps+1.381
spot+1.381
amy+1.373
ground+1.330
arten+1.291
Neg logit contributions
�士-2.486
 conclud-1.842
 Debor-1.766
\\\\\\\\-1.762
 Russo-1.644
Token G
Token ID402
Feature activation+4.47e+00

Pos logit contributions
spot+1.450
 laps+1.431
amy+1.426
ground+1.397
 Freedom+1.383
Neg logit contributions
�士-1.551
 conclud-1.049
 Debor-1.025
\\\\\\\\-1.019
 Russo-0.923
Token struggling
Token ID9648
Feature activation+1.63e+00

Pos logit contributions
�士+0.071
 conclud+0.051
\\\\\\\\+0.051
 Debor+0.050
 Inquisitor+0.047
Neg logit contributions
spot-0.043
amy-0.042
 laps-0.042
ground-0.041
ooter-0.040
Token
Token ID784
Feature activation-2.69e+00

Pos logit contributions
spot+1.085
 laps+1.081
amy+1.067
ground+1.044
ooter+1.033
Neg logit contributions
�士-1.615
 conclud-1.130
 Debor-1.114
\\\\\\\\-1.110
 Russo-1.021
Token but
Token ID475
Feature activation-7.09e-01

Pos logit contributions
�士+2.568
 conclud+1.821
 Debor+1.798
\\\\\\\\+1.791
 Russo+1.669
Neg logit contributions
spot-1.819
amy-1.800
 laps-1.779
ground-1.749
arten-1.740
Token I
Token ID314
Feature activation+1.95e-01

Pos logit contributions
�士+0.701
 conclud+0.499
\\\\\\\\+0.493
 Debor+0.490
 Russo+0.454
Neg logit contributions
spot-0.463
amy-0.459
 laps-0.456
ground-0.445
ooter-0.441
Token cannot
Token ID2314
Feature activation-1.13e+00

Pos logit contributions
spot+0.136
amy+0.134
 laps+0.134
ground+0.131
ooter+0.129
Neg logit contributions
�士-0.185
 conclud-0.128
\\\\\\\\-0.128
 Debor-0.127
 Russo-0.118
Token f
Token ID277
Feature activation-1.07e+01

Pos logit contributions
�士+1.080
 conclud+0.757
\\\\\\\\+0.749
 Debor+0.748
 Russo+0.693
Neg logit contributions
spot-0.780
amy-0.771
 laps-0.768
ground-0.750
arten-0.745
Tokenathom
Token ID32910
Feature activation-9.74e-01

Pos logit contributions
�士+9.467
\\\\\\\\+6.825
 Debor+6.699
 conclud+6.671
utsu+6.556
Neg logit contributions
spot-6.766
 laps-6.727
ground-6.680
amy-6.564
ooter-6.541
Token why
Token ID1521
Feature activation+2.08e+00

Pos logit contributions
�士+0.977
 conclud+0.701
\\\\\\\\+0.693
 Debor+0.691
 Russo+0.642
Neg logit contributions
spot-0.618
 laps-0.613
amy-0.611
ground-0.594
ooter-0.588
Token you
Token ID345
Feature activation+1.21e+00

Pos logit contributions
 laps+1.308
spot+1.296
amy+1.281
ground+1.251
 Freedom+1.236
Neg logit contributions
�士-2.114
 conclud-1.513
\\\\\\\\-1.509
 Debor-1.473
utsu-1.362
Token,
Token ID11
Feature activation-2.94e-01

Pos logit contributions
spot+0.868
amy+0.859
 laps+0.854
ground+0.831
arten+0.825
Neg logit contributions
�士-1.126
 conclud-0.772
 Debor-0.763
\\\\\\\\-0.763
 Russo-0.699
Token someone
Token ID2130
Feature activation+6.76e-01

Pos logit contributions
�士+0.294
 conclud+0.212
\\\\\\\\+0.210
 Debor+0.207
 Russo+0.193
Neg logit contributions
spot-0.188
 laps-0.187
amy-0.186
ground-0.181
ooter-0.179
Token $
Token ID720
Feature activation+2.88e+00

Pos logit contributions
spot+0.252
amy+0.249
 laps+0.248
ground+0.243
ooter+0.241
Neg logit contributions
�士-0.315
 conclud-0.217
 Debor-0.215
\\\\\\\\-0.214
 Russo-0.197
Token($
Token ID16763
Feature activation+6.20e+00

Pos logit contributions
spot+1.935
amy+1.906
 laps+1.877
ground+1.852
ooter+1.844
Neg logit contributions
�士-2.767
 conclud-1.974
 Debor-1.954
\\\\\\\\-1.925
 Russo-1.810
Token_.
Token ID44807
Feature activation+4.03e+00

Pos logit contributions
spot+4.198
amy+4.163
 laps+4.065
ooter+4.058
ground+4.031
Neg logit contributions
�士-5.823
 conclud-4.201
 Debor-4.146
\\\\\\\\-4.018
 Russo-3.797
TokenException
Token ID16922
Feature activation-2.39e-01

Pos logit contributions
spot+2.373
amy+2.349
 laps+2.300
ground+2.295
dirty+2.255
Neg logit contributions
�士-4.200
 conclud-3.124
 Debor-3.060
\\\\\\\\-3.029
 Russo-2.854
Token.
Token ID13
Feature activation-2.88e+00

Pos logit contributions
�士+0.225
 conclud+0.159
 Debor+0.155
\\\\\\\\+0.154
 Russo+0.142
Neg logit contributions
spot-0.167
amy-0.165
 laps-0.164
ground-0.162
ooter-0.160
TokenMessage
Token ID12837
Feature activation-1.07e+01

Pos logit contributions
�士+2.171
\\\\\\\\+1.363
 Debor+1.346
 conclud+1.346
 Russo+1.210
Neg logit contributions
spot-2.495
 laps-2.478
amy-2.468
arten-2.426
ground-2.404
Token)"
Token ID16725
Feature activation-6.52e+00

Pos logit contributions
�士+8.566
\\\\\\\\+5.936
 conclud+5.881
 Debor+5.691
 Inquisitor+5.380
Neg logit contributions
spot-7.878
amy-7.643
 laps-7.527
arten-7.426
ooter-7.425
Token break
Token ID2270
Feature activation-4.75e+00

Pos logit contributions
�士+5.428
 Debor+3.904
 conclud+3.857
\\\\\\\\+3.839
 RW+3.720
Neg logit contributions
amy-4.641
spot-4.640
ground-4.490
arten-4.465
ooter-4.452
Token }
Token ID1782
Feature activation-9.83e-01

Pos logit contributions
�士+4.990
 Debor+3.726
\\\\\\\\+3.712
 conclud+3.704
 Russo+3.547
Neg logit contributions
spot-2.599
amy-2.576
 laps-2.474
ground-2.443
arten-2.438
Token }
Token ID1782
Feature activation-1.04e+00

Pos logit contributions
�士+1.103
 conclud+0.829
 Debor+0.819
\\\\\\\\+0.819
 Russo+0.772
Neg logit contributions
spot-0.502
amy-0.495
 laps-0.489
ground-0.477
arten-0.472
Token End
Token ID5268
Feature activation-3.91e+00

Pos logit contributions
�士+1.100
 conclud+0.808
 Debor+0.798
\\\\\\\\+0.798
 Russo+0.748
Neg logit contributions
spot-0.598
amy-0.589
 laps-0.585
ground-0.571
ooter-0.566
Token 15
Token ID1315
Feature activation+4.83e-01

Pos logit contributions
�士+4.662
 Debor+3.504
\\\\\\\\+3.419
 Russo+3.359
 Inquisitor+3.302
Neg logit contributions
amy-3.262
spot-3.260
 laps-3.199
arten-3.167
ooter-3.138
Token of
Token ID286
Feature activation-6.58e-01

Pos logit contributions
spot+0.327
amy+0.324
 laps+0.323
ground+0.316
arten+0.311
Neg logit contributions
�士-0.477
 conclud-0.341
\\\\\\\\-0.327
 Debor-0.326
ntil-0.303
Token 15
Token ID1315
Feature activation+5.14e+00

Pos logit contributions
�士+0.712
 conclud+0.528
 Debor+0.517
\\\\\\\\+0.517
 Russo+0.481
Neg logit contributions
spot-0.370
amy-0.364
 laps-0.363
ground-0.355
arten-0.350
Token Photo
Token ID5555
Feature activation-4.29e+00

Pos logit contributions
spot+3.143
amy+3.119
 laps+3.045
arten+2.996
ground+2.985
Neg logit contributions
�士-5.291
 conclud-3.782
\\\\\\\\-3.769
 Debor-3.674
utsu-3.439
Token:
Token ID25
Feature activation-1.97e+00

Pos logit contributions
�士+3.417
 Debor+2.429
\\\\\\\\+2.416
 Russo+2.276
 Inquisitor+2.261
Neg logit contributions
spot-3.203
amy-3.199
 laps-3.146
arten-3.140
ooter-3.139
Token Erin
Token ID28894
Feature activation-1.06e+01

Pos logit contributions
�士+1.952
 Debor+1.407
 conclud+1.394
\\\\\\\\+1.378
 Russo+1.309
Neg logit contributions
spot-1.254
amy-1.232
 laps-1.222
ground-1.203
ooter-1.196
Token Bre
Token ID3719
Feature activation-1.81e+00

Pos logit contributions
�士+6.684
 Debor+4.787
 Russo+4.752
 RW+4.437
\\\\\\\\+4.351
Neg logit contributions
spot-9.058
dirty-8.813
amy-8.752
ground-8.736
arten-8.734
Tokenth
Token ID400
Feature activation+3.23e+00

Pos logit contributions
�士+1.624
\\\\\\\\+1.136
 Debor+1.135
 conclud+1.118
 Russo+1.065
Neg logit contributions
spot-1.263
 laps-1.248
amy-1.240
ooter-1.222
arten-1.214
Tokenauer
Token ID16261
Feature activation+1.69e+00

Pos logit contributions
amy+1.912
spot+1.902
arten+1.878
ooter+1.847
 laps+1.843
Neg logit contributions
�士-3.525
 conclud-2.643
 Debor-2.509
\\\\\\\\-2.491
ntil-2.306
Token,
Token ID11
Feature activation-2.11e+00

Pos logit contributions
spot+1.084
amy+1.080
 laps+1.073
ground+1.047
arten+1.028
Neg logit contributions
�士-1.722
 conclud-1.258
\\\\\\\\-1.193
 Debor-1.182
ntil-1.132
Token The
Token ID383
Feature activation+5.41e-01

Pos logit contributions
�士+1.984
 Debor+1.408
\\\\\\\\+1.394
 conclud+1.372
 Russo+1.313
Neg logit contributions
spot-1.437
amy-1.420
 laps-1.407
arten-1.380
ground-1.380
Token4
Token ID19
Feature activation+5.22e+00

Pos logit contributions
spot+0.239
amy+0.237
 laps+0.234
ground+0.230
arten+0.228
Neg logit contributions
�士-0.357
 conclud-0.255
 Debor-0.252
\\\\\\\\-0.252
 Russo-0.234
Token)
Token ID8
Feature activation-1.66e-01

Pos logit contributions
spot+2.693
 laps+2.691
amy+2.666
ground+2.549
 Freedom+2.526
Neg logit contributions
�士-5.766
 conclud-4.313
\\\\\\\\-4.246
 Debor-4.203
 Russo-3.991
Token DOI
Token ID40722
Feature activation-2.27e+00

Pos logit contributions
�士+0.157
 conclud+0.111
 Debor+0.109
\\\\\\\\+0.109
 Russo+0.101
Neg logit contributions
spot-0.114
amy-0.113
 laps-0.112
ground-0.110
arten-0.109
Token:
Token ID25
Feature activation-3.65e+00

Pos logit contributions
�士+2.091
 conclud+1.469
 Debor+1.451
\\\\\\\\+1.442
 Russo+1.343
Neg logit contributions
spot-1.597
amy-1.581
 laps-1.564
ground-1.544
arten-1.532
Token 10
Token ID838
Feature activation+5.08e-01

Pos logit contributions
�士+3.903
 conclud+2.925
 Debor+2.909
\\\\\\\\+2.876
 Russo+2.754
Neg logit contributions
spot-1.951
amy-1.937
 laps-1.921
ground-1.868
arten-1.853
Token.
Token ID13
Feature activation+6.46e+00

Pos logit contributions
spot+0.349
amy+0.346
 laps+0.345
ground+0.337
ooter+0.333
Neg logit contributions
�士-0.491
 conclud-0.348
\\\\\\\\-0.335
 Debor-0.335
ntil-0.310
Token10
Token ID940
Feature activation+4.77e+00

Pos logit contributions
spot+3.498
amy+3.480
ground+3.429
ooter+3.301
 laps+3.296
Neg logit contributions
�士-7.005
 conclud-5.340
 Debor-5.156
\\\\\\\\-5.128
ntil-4.917
Token86
Token ID4521
Feature activation+1.53e+00

Pos logit contributions
spot+2.670
amy+2.662
 laps+2.580
ground+2.568
arten+2.517
Neg logit contributions
�士-5.108
 conclud-3.814
\\\\\\\\-3.796
 Debor-3.772
 Russo-3.567
Token/
Token ID14
Feature activation-3.53e-01

Pos logit contributions
spot+0.995
amy+0.984
 laps+0.976
ground+0.961
ooter+0.942
Neg logit contributions
�士-1.529
 conclud-1.110
 Debor-1.065
\\\\\\\\-1.058
ntil-1.000
Token34
Token ID2682
Feature activation-1.62e+00

Pos logit contributions
�士+0.342
 conclud+0.243
 Debor+0.240
\\\\\\\\+0.240
 Russo+0.223
Neg logit contributions
spot-0.235
amy-0.233
 laps-0.231
ground-0.226
arten-0.224
Token110
Token ID11442
Feature activation-1.91e-02

Pos logit contributions
�士+1.567
 conclud+1.111
\\\\\\\\+1.103
 Debor+1.100
 Russo+1.029
Neg logit contributions
spot-1.058
 laps-1.039
amy-1.037
ooter-1.014
arten-1.011
Token-
Token ID12
Feature activation+5.43e+00

Pos logit contributions
spot+1.141
amy+1.126
 laps+1.121
ground+1.107
ooter+1.079
Neg logit contributions
�士-1.847
 conclud-1.365
 Debor-1.282
\\\\\\\\-1.274
ntil-1.222
Token08
Token ID2919
Feature activation+5.63e+00

Pos logit contributions
spot+3.639
amy+3.563
ground+3.489
dirty+3.441
 laps+3.436
Neg logit contributions
�士-5.291
 conclud-3.920
 Debor-3.696
\\\\\\\\-3.623
ntil-3.446
Token Election
Token ID14219
Feature activation-8.50e-01

Pos logit contributions
amy+2.912
spot+2.892
ground+2.803
 laps+2.792
 Freedom+2.766
Neg logit contributions
�士-6.188
 conclud-4.768
\\\\\\\\-4.572
 Debor-4.538
 Inquisitor-4.208
Token-
Token ID12
Feature activation+3.52e+00

Pos logit contributions
�士+0.807
 conclud+0.568
 Debor+0.564
\\\\\\\\+0.562
 Russo+0.523
Neg logit contributions
spot-0.581
amy-0.574
 laps-0.570
ground-0.558
arten-0.555
TokenLarry
Token ID42918
Feature activation+2.89e+00

Pos logit contributions
spot+2.367
amy+2.334
ground+2.269
 laps+2.266
dirty+2.241
Neg logit contributions
�士-3.447
 conclud-2.528
 Debor-2.404
\\\\\\\\-2.380
ntil-2.221
Token King
Token ID2677
Feature activation+7.98e+00

Pos logit contributions
amy+1.932
spot+1.919
 laps+1.867
ground+1.857
 Freedom+1.831
Neg logit contributions
�士-2.816
 conclud-2.066
\\\\\\\\-1.962
 Debor-1.939
ntil-1.811
Token R
Token ID371
Feature activation+2.09e+00

Pos logit contributions
amy+5.213
spot+5.190
ground+5.083
 Freedom+5.064
 laps+5.014
Neg logit contributions
�士-7.690
 conclud-5.642
\\\\\\\\-5.138
 Debor-4.990
ntil-4.965
Tokenaps
Token ID1686
Feature activation+7.26e+00

Pos logit contributions
amy+1.134
spot+1.121
 laps+1.091
ooter+1.079
ground+1.075
Neg logit contributions
�士-2.309
 conclud-1.735
 Debor-1.695
\\\\\\\\-1.681
 Inquisitor-1.583
Token-
Token ID12
Feature activation+5.20e+00

Pos logit contributions
amy+4.458
spot+4.447
 laps+4.374
ground+4.349
 Freedom+4.316
Neg logit contributions
�士-7.240
 conclud-5.580
\\\\\\\\-5.101
 Debor-4.923
ntil-4.791
TokenBlack
Token ID9915
Feature activation+3.48e+00

Pos logit contributions
spot+3.484
amy+3.444
ground+3.336
 laps+3.323
dirty+3.307
Neg logit contributions
�士-5.055
 conclud-3.753
 Debor-3.513
\\\\\\\\-3.470
ntil-3.298
Token President
Token ID1992
Feature activation+8.11e+00

Pos logit contributions
spot+2.272
amy+2.263
 laps+2.197
ground+2.182
 Freedom+2.141
Neg logit contributions
�士-3.483
 conclud-2.533
\\\\\\\\-2.440
 Debor-2.380
utsu-2.213
Tokenillion
Token ID1131
Feature activation-1.22e+00

Pos logit contributions
�士+2.196
 conclud+1.617
\\\\\\\\+1.612
 Debor+1.606
utsu+1.511
Neg logit contributions
spot-1.134
 laps-1.125
amy-1.117
ground-1.087
arten-1.080
Tokenaire
Token ID7626
Feature activation+3.96e+00

Pos logit contributions
�士+1.337
 conclud+0.994
 Debor+0.983
\\\\\\\\+0.980
 Russo+0.922
Neg logit contributions
spot-0.665
amy-0.656
 laps-0.648
ground-0.632
ooter-0.625
Token Koch
Token ID17009
Feature activation+3.29e+00

Pos logit contributions
spot+2.498
 laps+2.467
amy+2.451
 Freedom+2.397
ground+2.380
Neg logit contributions
�士-4.018
 conclud-2.846
\\\\\\\\-2.821
 Debor-2.703
utsu-2.575
Token brothers
Token ID9397
Feature activation+3.53e+00

Pos logit contributions
spot+2.639
amy+2.618
 laps+2.583
 Freedom+2.568
ground+2.552
Neg logit contributions
�士-2.730
 conclud-1.822
\\\\\\\\-1.762
 Debor-1.758
utsu-1.593
Token bank
Token ID3331
Feature activation+2.38e+00

Pos logit contributions
spot+2.382
amy+2.363
 laps+2.351
 Freedom+2.287
ground+2.278
Neg logit contributions
�士-3.424
\\\\\\\\-2.378
 conclud-2.372
 Debor-2.295
ntil-2.136
Tokenroll
Token ID2487
Feature activation+6.26e+00

Pos logit contributions
spot+1.762
amy+1.755
 laps+1.736
ground+1.720
dirty+1.694
Neg logit contributions
�士-2.148
 conclud-1.476
 Debor-1.438
\\\\\\\\-1.428
 Inquisitor-1.304
Token attacks
Token ID3434
Feature activation+3.60e+00

Pos logit contributions
spot+3.926
 laps+3.882
ground+3.869
amy+3.863
 Freedom+3.813
Neg logit contributions
�士-6.263
 conclud-4.498
\\\\\\\\-4.358
 Debor-4.356
utsu-4.004
Token on
Token ID319
Feature activation+2.14e+00

Pos logit contributions
spot+2.640
 laps+2.627
amy+2.607
ground+2.575
ooter+2.523
Neg logit contributions
�士-3.266
 conclud-2.219
\\\\\\\\-2.181
 Debor-2.156
 Russo-1.975
Token climate
Token ID4258
Feature activation-4.94e-01

Pos logit contributions
spot+1.234
 laps+1.226
amy+1.216
ground+1.197
 Freedom+1.178
Neg logit contributions
�士-2.286
 conclud-1.678
\\\\\\\\-1.652
 Debor-1.613
utsu-1.515
Token change
Token ID1487
Feature activation+7.86e-01

Pos logit contributions
�士+0.433
 conclud+0.292
\\\\\\\\+0.288
 Debor+0.287
 Russo+0.264
Neg logit contributions
spot-0.378
amy-0.373
 laps-0.372
ground-0.365
arten-0.362
Token science
Token ID3783
Feature activation-5.67e-01

Pos logit contributions
spot+0.455
 laps+0.446
amy+0.445
ground+0.434
arten+0.431
Neg logit contributions
�士-0.841
 conclud-0.611
\\\\\\\\-0.605
 Debor-0.598
 Russo-0.568
Token
Token ID26870
Feature activation-1.92e-01

Pos logit contributions
�士+0.838
 conclud+0.602
\\\\\\\\+0.595
 Debor+0.593
 Russo+0.552
Neg logit contributions
spot-0.538
amy-0.532
 laps-0.529
ground-0.517
arten-0.512
Token7
Token ID22
Feature activation-2.31e+00

Pos logit contributions
�士+0.193
 conclud+0.139
 Debor+0.137
\\\\\\\\+0.137
 Russo+0.128
Neg logit contributions
spot-0.121
amy-0.119
 laps-0.119
ground-0.117
arten-0.115
Token consecutive
Token ID12785
Feature activation-1.00e+00

Pos logit contributions
�士+2.167
 conclud+1.526
\\\\\\\\+1.499
 Debor+1.494
 Russo+1.394
Neg logit contributions
spot-1.595
amy-1.567
 laps-1.544
ground-1.528
ooter-1.527
Token days
Token ID1528
Feature activation-1.96e+00

Pos logit contributions
�士+0.949
 conclud+0.668
 Debor+0.659
\\\\\\\\+0.658
 Russo+0.610
Neg logit contributions
spot-0.688
amy-0.680
 laps-0.676
ground-0.662
arten-0.657
Token decreased
Token ID11832
Feature activation+3.03e-01

Pos logit contributions
�士+1.870
 conclud+1.329
 Debor+1.315
\\\\\\\\+1.303
 Russo+1.219
Neg logit contributions
spot-1.315
amy-1.299
 laps-1.283
ground-1.264
ooter-1.256
Token sexual
Token ID3206
Feature activation+6.28e+00

Pos logit contributions
spot+0.179
amy+0.178
 laps+0.178
ground+0.171
arten+0.168
Neg logit contributions
�士-0.320
 conclud-0.233
\\\\\\\\-0.232
 Debor-0.230
 Russo-0.213
Token behavior
Token ID4069
Feature activation-9.98e-02

Pos logit contributions
 laps+3.345
amy+3.269
spot+3.254
 Freedom+3.059
ground+3.023
Neg logit contributions
�士-7.020
\\\\\\\\-5.243
 conclud-5.232
 Debor-5.113
utsu-4.822
Token.
Token ID13
Feature activation-1.56e+00

Pos logit contributions
�士+0.097
 conclud+0.068
\\\\\\\\+0.067
 Debor+0.067
 Russo+0.061
Neg logit contributions
spot-0.068
 laps-0.067
amy-0.067
ground-0.065
arten-0.064
Token These
Token ID2312
Feature activation-2.62e+00

Pos logit contributions
�士+1.493
 conclud+1.057
\\\\\\\\+1.041
 Debor+1.038
 Russo+0.962
Neg logit contributions
spot-1.059
amy-1.048
 laps-1.040
ground-1.020
ooter-1.011
Token results
Token ID2482
Feature activation-1.54e+00

Pos logit contributions
�士+2.293
 conclud+1.566
 Debor+1.541
\\\\\\\\+1.534
 Russo+1.416
Neg logit contributions
spot-1.981
amy-1.960
 laps-1.945
ground-1.913
ooter-1.902
Token indicate
Token ID7603
Feature activation-2.49e-01

Pos logit contributions
�士+1.568
 conclud+1.131
\\\\\\\\+1.121
 Debor+1.118
 Russo+1.043
Neg logit contributions
spot-0.953
amy-0.940
 laps-0.933
ground-0.913
arten-0.905
Token<|endoftext|>
Token ID50256
Feature activation+1.50e+00

Pos logit contributions
spot+1.837
amy+1.814
 laps+1.807
ground+1.783
 Freedom+1.763
Neg logit contributions
�士-2.638
 conclud-1.916
\\\\\\\\-1.820
 Debor-1.807
 Russo-1.698
TokenAl
Token ID2348
Feature activation+1.08e+00

Pos logit contributions
spot+1.019
amy+1.006
 laps+0.987
ground+0.980
ooter+0.962
Neg logit contributions
�士-1.443
 conclud-1.041
 Debor-1.013
\\\\\\\\-0.999
 Russo-0.935
Tokenain
Token ID391
Feature activation-1.85e+00

Pos logit contributions
amy+0.728
spot+0.715
 laps+0.693
ground+0.690
ooter+0.685
Neg logit contributions
�士-1.063
 conclud-0.766
 Debor-0.745
\\\\\\\\-0.744
 Russo-0.678
Token B
Token ID347
Feature activation-2.45e+00

Pos logit contributions
�士+1.770
 conclud+1.251
 Debor+1.242
\\\\\\\\+1.235
 Russo+1.160
Neg logit contributions
spot-1.259
amy-1.235
 laps-1.227
ground-1.207
ooter-1.202
Token ad
Token ID512
Feature activation+4.32e-01

Pos logit contributions
�士+2.305
 conclud+1.619
 Debor+1.597
\\\\\\\\+1.595
 Russo+1.479
Neg logit contributions
spot-1.693
amy-1.672
 laps-1.662
ground-1.630
arten-1.617
Tokeni
Token ID72
Feature activation+7.58e+00

Pos logit contributions
spot+0.274
amy+0.273
 laps+0.269
ground+0.264
arten+0.262
Neg logit contributions
�士-0.434
 conclud-0.314
\\\\\\\\-0.309
 Debor-0.308
 Inquisitor-0.284
Tokenou
Token ID280
Feature activation-2.59e+00

Pos logit contributions
amy+5.080
 laps+5.012
spot+4.937
arten+4.886
ooter+4.800
Neg logit contributions
�士-7.090
 Debor-4.938
 conclud-4.914
\\\\\\\\-4.894
 Inquisitor-4.489
Token The
Token ID383
Feature activation+1.60e-01

Pos logit contributions
�士+2.480
 conclud+1.758
 Debor+1.738
\\\\\\\\+1.738
 Russo+1.612
Neg logit contributions
spot-1.741
amy-1.719
 laps-1.706
ground-1.676
arten-1.664
Token Fasc
Token ID41467
Feature activation+3.53e+00

Pos logit contributions
spot+0.105
amy+0.104
 laps+0.103
ground+0.101
arten+0.100
Neg logit contributions
�士-0.156
 conclud-0.112
\\\\\\\\-0.110
 Debor-0.110
 Russo-0.102
Token is
Token ID318
Feature activation+4.77e-01

Pos logit contributions
spot+1.933
amy+1.921
 laps+1.873
ooter+1.844
ground+1.840
Neg logit contributions
�士-3.853
 conclud-2.901
\\\\\\\\-2.856
 Debor-2.805
 Russo-2.636
Tokenm
Token ID76
Feature activation+1.84e+00

Pos logit contributions
spot+0.313
amy+0.310
 laps+0.307
ground+0.302
ooter+0.298
Neg logit contributions
�士-0.467
 conclud-0.334
\\\\\\\\-0.328
 Debor-0.328
 Russo-0.305
Token
Token ID784
Feature activation-4.94e+00

Pos logit contributions
spot+0.043
amy+0.042
 laps+0.042
ground+0.041
ooter+0.041
Neg logit contributions
�士-0.059
 conclud-0.041
\\\\\\\\-0.041
 Debor-0.040
 Russo-0.037
Token when
Token ID618
Feature activation-7.71e-01

Pos logit contributions
�士+4.467
 conclud+3.113
 Debor+3.097
\\\\\\\\+3.036
 Russo+2.878
Neg logit contributions
spot-3.487
amy-3.444
 laps-3.412
arten-3.391
ooter-3.371
Token she
Token ID673
Feature activation+1.89e+00

Pos logit contributions
�士+0.721
 conclud+0.503
\\\\\\\\+0.498
 Debor+0.491
 Russo+0.452
Neg logit contributions
spot-0.545
amy-0.541
 laps-0.536
ground-0.527
arten-0.519
Token died
Token ID3724
Feature activation+3.05e-01

Pos logit contributions
spot+1.231
amy+1.220
 laps+1.219
ground+1.173
arten+1.160
Neg logit contributions
�士-1.884
 conclud-1.353
\\\\\\\\-1.339
 Debor-1.317
 Russo-1.227
Token at
Token ID379
Feature activation-4.02e-01

Pos logit contributions
spot+0.205
 laps+0.203
amy+0.202
ground+0.199
arten+0.194
Neg logit contributions
�士-0.301
 conclud-0.211
\\\\\\\\-0.208
 Debor-0.204
 Russo-0.190
Token one
Token ID530
Feature activation+7.06e-01

Pos logit contributions
�士+0.401
 conclud+0.289
\\\\\\\\+0.285
 Debor+0.280
 Inquisitor+0.259
Neg logit contributions
spot-0.258
amy-0.257
 laps-0.256
ground-0.250
arten-0.246
Token month
Token ID1227
Feature activation-2.82e+00

Pos logit contributions
spot+0.467
amy+0.457
 laps+0.457
ground+0.446
arten+0.444
Neg logit contributions
�士-0.699
 conclud-0.497
\\\\\\\\-0.497
 Debor-0.490
utsu-0.449
Token old
Token ID1468
Feature activation+2.14e+00

Pos logit contributions
�士+2.657
 conclud+1.869
 Debor+1.843
\\\\\\\\+1.838
 Russo+1.706
Neg logit contributions
spot-1.951
amy-1.929
 laps-1.913
ground-1.878
ooter-1.864
Token.
Token ID13
Feature activation+3.85e-01

Pos logit contributions
spot+1.408
 laps+1.399
amy+1.392
ground+1.375
arten+1.339
Neg logit contributions
�士-2.132
 conclud-1.494
\\\\\\\\-1.476
 Debor-1.424
 Inquisitor-1.341
Token She
Token ID1375
Feature activation+1.65e+00

Pos logit contributions
spot+0.258
amy+0.257
 laps+0.253
ground+0.249
ooter+0.246
Neg logit contributions
�士-0.374
 conclud-0.268
\\\\\\\\-0.261
 Debor-0.258
 Russo-0.238
Token was
Token ID373
Feature activation-1.41e+00

Pos logit contributions
spot+1.132
amy+1.124
 laps+1.112
ground+1.087
ooter+1.072
Neg logit contributions
�士-1.578
 conclud-1.114
\\\\\\\\-1.094
 Debor-1.089
 Russo-1.011
Token those
Token ID883
Feature activation-1.01e+00

Pos logit contributions
�士+2.656
 conclud+1.873
 Debor+1.866
\\\\\\\\+1.849
 Russo+1.740
Neg logit contributions
spot-1.911
amy-1.888
 laps-1.869
ground-1.836
ooter-1.834
Token shows
Token ID2523
Feature activation-7.64e-01

Pos logit contributions
�士+1.027
 conclud+0.743
\\\\\\\\+0.734
 Debor+0.733
 Russo+0.683
Neg logit contributions
spot-0.626
amy-0.618
 laps-0.615
ground-0.600
arten-0.594
Token were
Token ID547
Feature activation+2.33e+00

Pos logit contributions
�士+0.723
 conclud+0.509
 Debor+0.503
\\\\\\\\+0.502
 Russo+0.466
Neg logit contributions
spot-0.525
amy-0.519
 laps-0.515
ground-0.505
arten-0.502
Token new
Token ID649
Feature activation-1.80e+00

Pos logit contributions
spot+1.470
 laps+1.454
amy+1.450
ground+1.422
arten+1.386
Neg logit contributions
�士-2.373
 conclud-1.702
\\\\\\\\-1.690
 Debor-1.658
utsu-1.536
Token series
Token ID2168
Feature activation-3.05e-01

Pos logit contributions
�士+1.702
 conclud+1.197
 Debor+1.180
\\\\\\\\+1.179
 Russo+1.092
Neg logit contributions
spot-1.244
amy-1.229
 laps-1.221
ground-1.197
arten-1.188
Token or
Token ID393
Feature activation+5.63e+00

Pos logit contributions
�士+0.291
 conclud+0.205
\\\\\\\\+0.202
 Debor+0.201
 Russo+0.185
Neg logit contributions
spot-0.211
amy-0.208
 laps-0.207
ground-0.203
arten-0.200
Token one
Token ID530
Feature activation+3.63e+00

Pos logit contributions
 laps+3.654
spot+3.573
amy+3.520
ground+3.467
 Freedom+3.410
Neg logit contributions
�士-5.542
\\\\\\\\-3.971
 conclud-3.935
 Debor-3.892
ntil-3.612
Token-
Token ID12
Feature activation+4.16e+00

Pos logit contributions
spot+2.305
 laps+2.293
amy+2.254
ground+2.214
arten+2.178
Neg logit contributions
�士-3.684
 conclud-2.638
\\\\\\\\-2.598
 Debor-2.559
ntil-2.371
Tokentime
Token ID2435
Feature activation+5.26e+00

Pos logit contributions
spot+2.266
amy+2.192
ground+2.140
 laps+2.103
dirty+2.036
Neg logit contributions
�士-4.691
 conclud-3.566
\\\\\\\\-3.504
 Debor-3.447
ntil-3.213
Token-
Token ID12
Feature activation-1.52e+00

Pos logit contributions
 laps+3.408
spot+3.325
amy+3.279
ground+3.183
 Freedom+3.125
Neg logit contributions
�士-5.273
\\\\\\\\-3.754
 conclud-3.742
 Debor-3.694
utsu-3.448
Tokenonly
Token ID8807
Feature activation+1.62e+00

Pos logit contributions
�士+1.505
 conclud+1.075
 Debor+1.066
\\\\\\\\+1.060
 Russo+0.993
Neg logit contributions
spot-0.963
amy-0.958
 laps-0.952
ooter-0.933
arten-0.933
Tokenopy
Token ID11081
Feature activation+2.35e+00

Pos logit contributions
�士+1.229
 conclud+0.841
\\\\\\\\+0.828
 Debor+0.822
 Russo+0.749
Neg logit contributions
spot-1.054
amy-1.048
 laps-1.031
ground-1.016
ooter-1.013
Token locks
Token ID19253
Feature activation+1.34e+00

Pos logit contributions
 laps+1.510
amy+1.502
spot+1.501
ground+1.452
ooter+1.428
Neg logit contributions
�士-2.341
 conclud-1.685
\\\\\\\\-1.664
 Debor-1.630
 Russo-1.509
Token,
Token ID11
Feature activation-2.02e+00

Pos logit contributions
spot+0.914
amy+0.911
 laps+0.902
ground+0.878
ooter+0.871
Neg logit contributions
�士-1.287
 conclud-0.911
\\\\\\\\-0.896
 Debor-0.887
 Russo-0.821
Token he
Token ID339
Feature activation-4.39e-01

Pos logit contributions
�士+1.943
 conclud+1.380
 Debor+1.362
\\\\\\\\+1.359
 Russo+1.265
Neg logit contributions
spot-1.350
amy-1.334
 laps-1.322
ground-1.298
arten-1.288
Token shines
Token ID32481
Feature activation-2.59e+00

Pos logit contributions
�士+0.411
 conclud+0.286
 Debor+0.283
\\\\\\\\+0.282
 Russo+0.262
Neg logit contributions
spot-0.310
amy-0.307
 laps-0.306
ground-0.298
arten-0.295
Token as
Token ID355
Feature activation-4.34e-03

Pos logit contributions
�士+2.459
 conclud+1.733
 Debor+1.708
\\\\\\\\+1.707
 Russo+1.582
Neg logit contributions
spot-1.771
amy-1.750
 laps-1.739
ground-1.704
arten-1.690
Token the
Token ID262
Feature activation-5.43e-03

Pos logit contributions
�士+0.004
 conclud+0.003
\\\\\\\\+0.003
 Debor+0.003
 Russo+0.003
Neg logit contributions
spot-0.003
amy-0.003
 laps-0.003
ground-0.003
arten-0.003
Token dead
Token ID2636
Feature activation+3.40e-01

Pos logit contributions
�士+0.005
 conclud+0.004
\\\\\\\\+0.004
 Debor+0.004
 Russo+0.003
Neg logit contributions
spot-0.004
amy-0.004
 laps-0.004
ground-0.003
arten-0.003
Tokenpan
Token ID6839
Feature activation+1.97e+00

Pos logit contributions
spot+0.207
amy+0.203
 laps+0.201
ground+0.198
ooter+0.193
Neg logit contributions
�士-0.354
 conclud-0.259
\\\\\\\\-0.255
 Debor-0.252
 Russo-0.235
Token,
Token ID11
Feature activation+7.05e-01

Pos logit contributions
 laps+1.264
spot+1.262
amy+1.253
ground+1.216
arten+1.203
Neg logit contributions
�士-1.953
 conclud-1.406
\\\\\\\\-1.391
 Debor-1.366
utsu-1.265
Token action
Token ID2223
Feature activation+2.97e+00

Pos logit contributions
spot+0.456
 laps+0.455
amy+0.451
ground+0.439
ooter+0.431
Neg logit contributions
�士-0.697
 conclud-0.499
\\\\\\\\-0.495
 Debor-0.491
 Russo-0.453
Token to
Token ID284
Feature activation-3.70e+00

Pos logit contributions
�士+1.243
 conclud+0.907
 Debor+0.897
\\\\\\\\+0.896
 Russo+0.840
Neg logit contributions
spot-0.713
amy-0.705
 laps-0.697
ground-0.682
arten-0.677
Token it
Token ID340
Feature activation-3.12e+00

Pos logit contributions
�士+3.530
 conclud+2.509
 Debor+2.500
\\\\\\\\+2.467
 Russo+2.345
Neg logit contributions
spot-2.434
amy-2.421
 laps-2.366
ground-2.340
arten-2.335
Token,
Token ID11
Feature activation-2.22e+00

Pos logit contributions
�士+2.911
 conclud+2.070
 Debor+2.046
\\\\\\\\+2.027
 Russo+1.899
Neg logit contributions
spot-2.121
amy-2.106
 laps-2.071
ooter-2.042
ground-2.041
Token because
Token ID780
Feature activation-1.11e-01

Pos logit contributions
�士+2.100
 conclud+1.490
 Debor+1.478
\\\\\\\\+1.460
 Russo+1.377
Neg logit contributions
spot-1.494
amy-1.486
 laps-1.460
arten-1.439
ground-1.437
Token Google
Token ID3012
Feature activation-1.89e-01

Pos logit contributions
�士+0.111
 conclud+0.080
\\\\\\\\+0.079
 Debor+0.079
 Russo+0.073
Neg logit contributions
spot-0.070
amy-0.069
 laps-0.069
ground-0.067
ooter-0.067
Token's
Token ID338
Feature activation-1.67e-02

Pos logit contributions
�士+0.175
 conclud+0.122
 Debor+0.121
\\\\\\\\+0.120
 Russo+0.112
Neg logit contributions
spot-0.133
amy-0.132
 laps-0.131
ground-0.128
arten-0.127
Token Gallery
Token ID12917
Feature activation+1.72e+00

Pos logit contributions
�士+0.016
 conclud+0.012
\\\\\\\\+0.011
 Debor+0.011
 Russo+0.011
Neg logit contributions
spot-0.011
 laps-0.011
amy-0.011
ground-0.011
ooter-0.011
Token is
Token ID318
Feature activation+4.38e-01

Pos logit contributions
spot+1.144
 laps+1.122
amy+1.114
ground+1.100
ooter+1.088
Neg logit contributions
�士-1.688
 conclud-1.199
\\\\\\\\-1.185
 Debor-1.178
 Russo-1.091
Token the
Token ID262
Feature activation+2.19e+00

Pos logit contributions
spot+0.285
amy+0.281
 laps+0.279
ground+0.273
ooter+0.270
Neg logit contributions
�士-0.434
 conclud-0.311
\\\\\\\\-0.307
 Debor-0.306
 Russo-0.284
Token best
Token ID1266
Feature activation-1.48e-01

Pos logit contributions
spot+1.428
 laps+1.407
amy+1.402
ground+1.372
ooter+1.353
Neg logit contributions
�士-2.178
 conclud-1.555
\\\\\\\\-1.545
 Debor-1.526
 Russo-1.404
Token around
Token ID1088
Feature activation+3.02e+00

Pos logit contributions
�士+0.149
 conclud+0.107
\\\\\\\\+0.106
 Debor+0.105
 Russo+0.098
Neg logit contributions
spot-0.095
amy-0.093
 laps-0.093
ground-0.091
ooter-0.090
Token than
Token ID621
Feature activation+1.27e+00

Pos logit contributions
�士+0.135
 conclud+0.098
\\\\\\\\+0.097
 Debor+0.096
 Russo+0.090
Neg logit contributions
spot-0.074
 laps-0.073
amy-0.072
ground-0.071
arten-0.070
Token RT
Token ID11923
Feature activation-1.29e+00

Pos logit contributions
spot+0.803
 laps+0.798
amy+0.788
ground+0.780
ooter+0.764
Neg logit contributions
�士-1.287
 conclud-0.918
 Debor-0.904
\\\\\\\\-0.897
 Russo-0.836
Token prop
Token ID2632
Feature activation+5.67e-01

Pos logit contributions
�士+0.938
 conclud+0.579
 Debor+0.566
\\\\\\\\+0.566
 Russo+0.504
Neg logit contributions
spot-1.162
amy-1.153
 laps-1.145
ground-1.129
arten-1.123
Token,
Token ID837
Feature activation+5.08e+00

Pos logit contributions
spot+0.406
 laps+0.401
amy+0.399
ground+0.391
arten+0.385
Neg logit contributions
�士-0.531
 conclud-0.362
 Debor-0.359
\\\\\\\\-0.357
 Russo-0.330
Token so
Token ID523
Feature activation-5.75e-01

Pos logit contributions
spot+3.030
 laps+3.006
amy+2.967
ground+2.958
ooter+2.881
Neg logit contributions
�士-5.264
 Debor-3.721
 conclud-3.714
\\\\\\\\-3.670
 Inquisitor-3.425
Token until
Token ID1566
Feature activation+4.68e+00

Pos logit contributions
�士+0.572
 conclud+0.405
 Debor+0.401
\\\\\\\\+0.401
 Russo+0.371
Neg logit contributions
spot-0.373
 laps-0.369
amy-0.368
ground-0.360
ooter-0.355
Token we
Token ID356
Feature activation+3.28e+00

Pos logit contributions
 laps+2.833
spot+2.777
amy+2.679
ground+2.674
 Freedom+2.625
Neg logit contributions
�士-4.884
 conclud-3.456
\\\\\\\\-3.418
 Debor-3.408
utsu-3.194
Token reach
Token ID3151
Feature activation+8.25e+00

Pos logit contributions
spot+2.311
 laps+2.298
amy+2.256
ground+2.197
ooter+2.196
Neg logit contributions
�士-3.086
\\\\\\\\-2.126
 Debor-2.087
 conclud-2.084
 Russo-1.913
Token B
Token ID347
Feature activation-3.42e-01

Pos logit contributions
 laps+4.754
spot+4.668
ground+4.561
amy+4.519
 Freedom+4.488
Neg logit contributions
�士-8.494
 conclud-6.043
 Debor-6.022
\\\\\\\\-5.923
utsu-5.551
TokenDP
Token ID6322
Feature activation+1.82e+00

Pos logit contributions
�士+0.315
 conclud+0.220
 Debor+0.215
\\\\\\\\+0.213
 Russo+0.198
Neg logit contributions
spot-0.248
amy-0.245
 laps-0.242
ground-0.239
ooter-0.237
Token,
Token ID11
Feature activation+1.90e+00

Pos logit contributions
spot+1.269
 laps+1.259
amy+1.241
ground+1.220
ooter+1.207
Neg logit contributions
�士-1.735
 conclud-1.193
 Debor-1.190
\\\\\\\\-1.177
 Russo-1.096
Token
Token ID447
Feature activation+2.92e-01

Pos logit contributions
�士+1.272
 conclud+0.874
 Debor+0.861
\\\\\\\\+0.860
 Russo+0.793
Neg logit contributions
spot-1.041
amy-1.030
 laps-1.025
ground-1.004
arten-0.996
Token
Token ID247
Feature activation-5.58e-02

Pos logit contributions
spot+0.233
amy+0.232
 laps+0.231
ground+0.227
arten+0.226
Neg logit contributions
�士-0.242
 conclud-0.165
 Debor-0.159
\\\\\\\\-0.158
 Russo-0.144
Tokens
Token ID82
Feature activation+2.84e+00

Pos logit contributions
�士+0.054
 conclud+0.039
\\\\\\\\+0.038
 Debor+0.038
 Russo+0.035
Neg logit contributions
spot-0.037
amy-0.037
 laps-0.037
ground-0.036
arten-0.036
Token one
Token ID530
Feature activation+3.49e+00

Pos logit contributions
spot+1.716
 laps+1.707
amy+1.688
ground+1.650
arten+1.618
Neg logit contributions
�士-2.946
 conclud-2.117
 Debor-2.074
\\\\\\\\-2.072
 Russo-1.934
Token thing
Token ID1517
Feature activation+2.84e+00

Pos logit contributions
spot+2.191
 laps+2.164
amy+2.107
ground+2.057
 Freedom+2.030
Neg logit contributions
�士-3.613
\\\\\\\\-2.577
 conclud-2.572
 Debor-2.505
utsu-2.336
Token the
Token ID262
Feature activation-4.32e-01

Pos logit contributions
 laps+1.764
spot+1.761
amy+1.737
ground+1.699
arten+1.660
Neg logit contributions
�士-2.915
 conclud-2.086
\\\\\\\\-2.059
 Debor-2.043
utsu-1.902
Token Jets
Token ID14728
Feature activation-3.48e+00

Pos logit contributions
�士+0.365
 conclud+0.244
\\\\\\\\+0.241
 Debor+0.240
 Russo+0.216
Neg logit contributions
spot-0.343
amy-0.338
 laps-0.338
ground-0.332
ooter-0.329
Token really
Token ID1107
Feature activation+6.52e-01

Pos logit contributions
�士+3.163
 conclud+2.193
\\\\\\\\+2.163
 Debor+2.163
 Russo+2.003
Neg logit contributions
spot-2.498
amy-2.470
 laps-2.447
ground-2.411
arten-2.402
Token need
Token ID761
Feature activation+2.65e+00

Pos logit contributions
spot+0.409
amy+0.403
 laps+0.402
ground+0.391
arten+0.385
Neg logit contributions
�士-0.664
 conclud-0.479
 Debor-0.472
\\\\\\\\-0.471
 Russo-0.439
Token to
Token ID284
Feature activation-4.67e-01

Pos logit contributions
spot+1.652
 laps+1.642
amy+1.633
ground+1.595
dirty+1.546
Neg logit contributions
�士-2.694
 conclud-1.914
 Debor-1.899
\\\\\\\\-1.880
 Inquisitor-1.749
Token happen
Token ID1645
Feature activation-1.72e+00

Pos logit contributions
�士+0.454
 conclud+0.323
 Debor+0.319
\\\\\\\\+0.318
 Russo+0.296
Neg logit contributions
spot-0.310
amy-0.306
 laps-0.304
ground-0.298
arten-0.295
Token would
Token ID561
Feature activation-9.34e-01

Pos logit contributions
�士+4.324
 conclud+2.989
 Debor+2.972
\\\\\\\\+2.883
 Russo+2.753
Neg logit contributions
spot-3.893
amy-3.841
ooter-3.761
arten-3.737
 laps-3.725
Token make
Token ID787
Feature activation+4.40e-02

Pos logit contributions
�士+0.887
 conclud+0.628
 Debor+0.619
\\\\\\\\+0.617
 Russo+0.574
Neg logit contributions
spot-0.636
amy-0.629
 laps-0.623
ground-0.613
ooter-0.608
Token the
Token ID262
Feature activation-2.80e-01

Pos logit contributions
spot+0.028
amy+0.028
 laps+0.028
ground+0.027
arten+0.027
Neg logit contributions
�士-0.044
 conclud-0.032
\\\\\\\\-0.031
 Debor-0.031
 Russo-0.029
Token populace
Token ID39003
Feature activation-1.43e+00

Pos logit contributions
�士+0.274
 conclud+0.196
 Debor+0.193
\\\\\\\\+0.193
 Russo+0.180
Neg logit contributions
spot-0.184
amy-0.182
 laps-0.180
ground-0.177
arten-0.175
Token less
Token ID1342
Feature activation+1.54e+00

Pos logit contributions
�士+1.453
 conclud+1.059
 Debor+1.047
\\\\\\\\+1.039
 Russo+0.980
Neg logit contributions
spot-0.873
amy-0.865
 laps-0.849
ground-0.836
ooter-0.832
Token likely
Token ID1884
Feature activation-1.86e+00

Pos logit contributions
spot+0.979
 laps+0.970
amy+0.958
ground+0.940
arten+0.922
Neg logit contributions
�士-1.552
 conclud-1.111
\\\\\\\\-1.109
 Debor-1.087
utsu-1.002
Token to
Token ID284
Feature activation+3.25e+00

Pos logit contributions
�士+1.729
 conclud+1.223
 Debor+1.193
\\\\\\\\+1.189
 Russo+1.116
Neg logit contributions
spot-1.297
amy-1.283
 laps-1.261
ground-1.249
arten-1.244
Token vote
Token ID3015
Feature activation+2.99e+00

Pos logit contributions
 laps+1.949
spot+1.936
amy+1.899
ground+1.840
arten+1.828
Neg logit contributions
�士-3.425
\\\\\\\\-2.483
 conclud-2.443
 Debor-2.423
ntil-2.243
Token for
Token ID329
Feature activation+1.35e+00

Pos logit contributions
 laps+2.060
spot+2.049
amy+2.027
ground+2.001
arten+1.976
Neg logit contributions
�士-2.831
 conclud-1.983
\\\\\\\\-1.951
 Debor-1.911
 Inquisitor-1.765
Token a
Token ID257
Feature activation+2.24e+00

Pos logit contributions
 laps+0.830
spot+0.827
amy+0.820
ground+0.806
arten+0.794
Neg logit contributions
�士-1.377
 conclud-0.999
\\\\\\\\-0.977
 Debor-0.962
 Russo-0.898
Token man
Token ID582
Feature activation+3.18e+00

Pos logit contributions
spot+1.454
 laps+1.452
amy+1.431
ground+1.408
 Freedom+1.391
Neg logit contributions
�士-2.220
 conclud-1.580
\\\\\\\\-1.551
 Debor-1.533
 Russo-1.427
Token medium
Token ID7090
Feature activation+3.01e+00

Pos logit contributions
�士+3.099
 conclud+2.225
 Debor+2.204
\\\\\\\\+2.191
 Russo+2.049
Neg logit contributions
spot-2.021
amy-1.998
 laps-1.972
ground-1.932
ooter-1.923
Token.
Token ID13
Feature activation+2.40e+00

Pos logit contributions
spot+1.995
amy+1.945
 laps+1.943
ground+1.908
arten+1.876
Neg logit contributions
�士-2.961
 conclud-2.104
\\\\\\\\-2.070
 Debor-2.020
 Russo-1.896
Token For
Token ID1114
Feature activation-2.95e+00

Pos logit contributions
spot+1.375
amy+1.370
 laps+1.365
arten+1.325
ooter+1.323
Neg logit contributions
�士-2.546
 conclud-1.912
\\\\\\\\-1.847
 Debor-1.811
ntil-1.704
Token the
Token ID262
Feature activation-6.58e-01

Pos logit contributions
�士+2.770
 conclud+1.939
 Debor+1.917
\\\\\\\\+1.912
 Russo+1.776
Neg logit contributions
spot-2.053
amy-2.024
 laps-2.004
ground-1.965
arten-1.962
Token song
Token ID3496
Feature activation-2.30e+00

Pos logit contributions
�士+0.636
 conclud+0.451
\\\\\\\\+0.445
 Debor+0.444
 Russo+0.411
Neg logit contributions
spot-0.441
amy-0.435
 laps-0.434
ground-0.424
ooter-0.420
Token,
Token ID11
Feature activation-9.62e-01

Pos logit contributions
�士+2.216
 conclud+1.575
 Debor+1.558
\\\\\\\\+1.554
 Russo+1.446
Neg logit contributions
spot-1.537
amy-1.522
 laps-1.511
ground-1.478
arten-1.472
Token see
Token ID766
Feature activation-4.24e+00

Pos logit contributions
�士+0.857
 conclud+0.586
\\\\\\\\+0.577
 Debor+0.575
 Russo+0.528
Neg logit contributions
spot-0.720
amy-0.712
 laps-0.707
ground-0.695
arten-0.689
Token Legal
Token ID16027
Feature activation-2.97e+00

Pos logit contributions
�士+4.146
 Debor+3.016
 conclud+2.977
\\\\\\\\+2.946
 Russo+2.803
Neg logit contributions
spot-2.684
amy-2.642
 laps-2.616
arten-2.569
ooter-2.566
Token T
Token ID309
Feature activation+2.01e+00

Pos logit contributions
�士+2.924
 conclud+2.110
 Debor+2.093
\\\\\\\\+2.083
 Russo+1.946
Neg logit contributions
spot-1.894
amy-1.853
 laps-1.846
ground-1.800
arten-1.795
Tokenender
Token ID2194
Feature activation+2.08e+00

Pos logit contributions
amy+1.272
spot+1.259
 laps+1.219
ooter+1.218
arten+1.208
Neg logit contributions
�士-2.047
 conclud-1.482
 Debor-1.449
\\\\\\\\-1.447
 Inquisitor-1.338
Token (
Token ID357
Feature activation-3.91e+00

Pos logit contributions
spot+1.388
amy+1.362
 laps+1.349
ground+1.337
ooter+1.319
Neg logit contributions
�士-2.047
 conclud-1.461
 Debor-1.426
\\\\\\\\-1.422
 Russo-1.322
Token (
Token ID357
Feature activation-4.69e+00

Pos logit contributions
�士+0.386
 conclud+0.273
\\\\\\\\+0.266
 Debor+0.265
 Russo+0.245
Neg logit contributions
spot-0.283
amy-0.280
 laps-0.277
ground-0.272
arten-0.269
TokenIn
Token ID818
Feature activation-1.98e+00

Pos logit contributions
�士+4.192
 Debor+2.897
\\\\\\\\+2.890
 conclud+2.843
 Russo+2.692
Neg logit contributions
 laps-3.301
spot-3.295
amy-3.241
ooter-3.227
arten-3.213
Token fact
Token ID1109
Feature activation-1.82e+00

Pos logit contributions
�士+1.892
 conclud+1.341
 Debor+1.324
\\\\\\\\+1.321
 Russo+1.231
Neg logit contributions
spot-1.333
amy-1.318
 laps-1.307
ground-1.282
ooter-1.275
Token,
Token ID11
Feature activation+1.68e+00

Pos logit contributions
�士+1.695
 conclud+1.188
 Debor+1.171
\\\\\\\\+1.169
 Russo+1.084
Neg logit contributions
spot-1.274
amy-1.254
 laps-1.248
ground-1.229
ooter-1.220
Token transgender
Token ID10637
Feature activation-5.53e-01

Pos logit contributions
spot+1.071
amy+1.063
 laps+1.060
ground+1.019
arten+1.012
Neg logit contributions
�士-1.687
 conclud-1.204
\\\\\\\\-1.192
 Debor-1.173
utsu-1.091
Token activists
Token ID7941
Feature activation-2.05e+00

Pos logit contributions
�士+0.598
 conclud+0.443
 Debor+0.437
\\\\\\\\+0.436
 Russo+0.409
Neg logit contributions
spot-0.308
amy-0.304
 laps-0.302
ground-0.294
arten-0.291
Token have
Token ID423
Feature activation-2.64e-01

Pos logit contributions
�士+1.892
 conclud+1.324
 Debor+1.307
\\\\\\\\+1.300
 Russo+1.207
Neg logit contributions
spot-1.449
amy-1.433
 laps-1.422
ground-1.397
ooter-1.388
Token talked
Token ID6619
Feature activation+2.30e+00

Pos logit contributions
�士+0.258
 conclud+0.184
\\\\\\\\+0.181
 Debor+0.180
 Russo+0.168
Neg logit contributions
spot-0.175
amy-0.173
 laps-0.172
ground-0.168
arten-0.166
Token about
Token ID546
Feature activation+2.17e+00

Pos logit contributions
spot+1.344
amy+1.337
 laps+1.326
ground+1.288
arten+1.257
Neg logit contributions
�士-2.420
 conclud-1.777
\\\\\\\\-1.741
 Debor-1.739
 Russo-1.623
Token Do
Token ID2141
Feature activation-4.26e+00

Pos logit contributions
spot+1.366
amy+1.358
 laps+1.358
ground+1.302
arten+1.291
Neg logit contributions
�士-2.204
 conclud-1.575
\\\\\\\\-1.555
 Debor-1.543
 Russo-1.433
Tokenlez
Token ID36858
Feature activation+7.39e-01

Pos logit contributions
�士+1.704
 Debor+0.612
\\\\\\\\+0.604
 conclud+0.559
 Russo+0.435
Neg logit contributions
spot-5.021
 laps-4.955
amy-4.947
ground-4.917
arten-4.889
Token features
Token ID3033
Feature activation-1.37e+00

Pos logit contributions
�士+1.182
 conclud+0.831
 Debor+0.820
\\\\\\\\+0.818
 Russo+0.760
Neg logit contributions
spot-0.868
amy-0.858
 laps-0.850
ground-0.835
ooter-0.830
Token of
Token ID286
Feature activation-1.15e+00

Pos logit contributions
�士+1.262
 conclud+0.880
 Debor+0.871
\\\\\\\\+0.867
 Russo+0.803
Neg logit contributions
spot-0.968
amy-0.958
 laps-0.949
ground-0.933
ooter-0.926
Token classical
Token ID15993
Feature activation-3.18e+00

Pos logit contributions
�士+1.152
 conclud+0.831
 Debor+0.821
\\\\\\\\+0.818
 Russo+0.765
Neg logit contributions
spot-0.727
amy-0.718
 laps-0.711
ground-0.696
ooter-0.691
Token theories
Token ID10946
Feature activation-5.26e+00

Pos logit contributions
�士+2.994
 conclud+2.129
 Debor+2.115
\\\\\\\\+2.088
 Russo+1.955
Neg logit contributions
spot-2.173
amy-2.142
 laps-2.103
ooter-2.087
arten-2.084
Token of
Token ID286
Feature activation-3.87e+00

Pos logit contributions
�士+4.780
 Debor+3.422
 conclud+3.421
\\\\\\\\+3.319
 Russo+3.162
Neg logit contributions
spot-3.613
amy-3.612
ooter-3.506
 laps-3.492
arten-3.462
Token rationality
Token ID45627
Feature activation-6.16e+00

Pos logit contributions
�士+3.009
 conclud+1.995
 Debor+1.937
\\\\\\\\+1.904
 Russo+1.754
Neg logit contributions
spot-3.258
amy-3.205
 laps-3.136
arten-3.135
ooter-3.132
Token make
Token ID787
Feature activation-4.27e-02

Pos logit contributions
�士+5.152
 conclud+3.591
 Debor+3.567
\\\\\\\\+3.486
 Russo+3.298
Neg logit contributions
amy-4.575
spot-4.551
ooter-4.463
dirty-4.433
arten-4.395
Token it
Token ID340
Feature activation-2.36e+00

Pos logit contributions
�士+0.043
 conclud+0.031
\\\\\\\\+0.031
 Debor+0.031
 Russo+0.029
Neg logit contributions
spot-0.027
amy-0.026
 laps-0.026
ground-0.026
arten-0.025
Token hard
Token ID1327
Feature activation-3.43e+00

Pos logit contributions
�士+2.152
 conclud+1.508
 Debor+1.495
\\\\\\\\+1.483
 Russo+1.387
Neg logit contributions
spot-1.659
amy-1.649
 laps-1.618
ooter-1.601
ground-1.592
Token to
Token ID284
Feature activation-1.43e+00

Pos logit contributions
�士+3.075
 conclud+2.142
 Debor+2.106
\\\\\\\\+2.080
 Russo+1.947
Neg logit contributions
spot-2.452
amy-2.429
 laps-2.401
arten-2.367
ooter-2.366
Token support
Token ID1104
Feature activation-5.60e-01

Pos logit contributions
�士+1.339
 conclud+0.946
 Debor+0.930
\\\\\\\\+0.925
 Russo+0.862
Neg logit contributions
spot-0.988
amy-0.978
 laps-0.966
ground-0.951
ooter-0.946
Token I
Token ID314
Feature activation+1.01e+00

Pos logit contributions
 laps+2.223
spot+2.215
amy+2.174
ground+2.150
arten+2.116
Neg logit contributions
�士-3.484
\\\\\\\\-2.462
 conclud-2.445
 Debor-2.375
 Russo-2.219
Token can
Token ID460
Feature activation+1.53e+00

Pos logit contributions
spot+0.665
 laps+0.656
amy+0.653
ground+0.639
arten+0.630
Neg logit contributions
�士-1.002
 conclud-0.707
\\\\\\\\-0.703
 Debor-0.703
 Russo-0.652
Token use
Token ID779
Feature activation-1.06e+00

Pos logit contributions
spot+1.005
 laps+0.989
amy+0.980
ground+0.957
ooter+0.949
Neg logit contributions
�士-1.536
\\\\\\\\-1.079
 Debor-1.077
 conclud-1.075
 Russo-0.999
Token it
Token ID340
Feature activation-2.84e+00

Pos logit contributions
�士+1.083
 conclud+0.785
\\\\\\\\+0.775
 Debor+0.773
 Russo+0.722
Neg logit contributions
spot-0.652
amy-0.643
 laps-0.641
ground-0.626
arten-0.619
Token as
Token ID355
Feature activation-4.71e+00

Pos logit contributions
�士+2.681
 conclud+1.894
 Debor+1.867
\\\\\\\\+1.863
 Russo+1.728
Neg logit contributions
spot-1.948
amy-1.929
 laps-1.908
ground-1.875
ooter-1.863
Token lap
Token ID14779
Feature activation-7.36e+00

Pos logit contributions
�士+4.475
 conclud+3.183
 Debor+3.157
\\\\\\\\+3.124
 Russo+2.917
Neg logit contributions
spot-3.105
amy-3.098
 laps-3.048
ooter-3.017
arten-2.988
Tokenboard
Token ID3526
Feature activation-2.68e+00

Pos logit contributions
�士+7.171
 conclud+5.138
 Debor+5.116
\\\\\\\\+5.015
 RW+4.795
Neg logit contributions
spot-4.546
amy-4.405
ooter-4.361
 laps-4.358
ground-4.331
Token,
Token ID11
Feature activation-2.40e-01

Pos logit contributions
�士+2.509
 conclud+1.766
 Debor+1.740
\\\\\\\\+1.737
 Russo+1.608
Neg logit contributions
spot-1.859
amy-1.841
 laps-1.821
ground-1.787
ooter-1.780
Token and
Token ID290
Feature activation-8.81e-01

Pos logit contributions
�士+0.235
 conclud+0.167
\\\\\\\\+0.165
 Debor+0.164
 Russo+0.153
Neg logit contributions
spot-0.158
 laps-0.157
amy-0.156
ground-0.153
arten-0.151
Token I
Token ID314
Feature activation-1.89e+00

Pos logit contributions
�士+0.859
 conclud+0.610
\\\\\\\\+0.603
 Debor+0.600
 Russo+0.558
Neg logit contributions
spot-0.585
amy-0.578
 laps-0.577
ground-0.564
arten-0.558
Token can
Token ID460
Feature activation-1.48e+00

Pos logit contributions
�士+1.769
 conclud+1.240
 Debor+1.222
\\\\\\\\+1.221
 Russo+1.130
Neg logit contributions
spot-1.321
amy-1.306
 laps-1.296
ground-1.272
arten-1.262
Token situation
Token ID3074
Feature activation+1.47e+00

Pos logit contributions
spot+1.919
 laps+1.899
amy+1.891
ground+1.850
 Freedom+1.836
Neg logit contributions
�士-3.321
 conclud-2.407
\\\\\\\\-2.370
 Debor-2.347
utsu-2.185
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
spot+0.971
 laps+0.953
amy+0.949
ground+0.930
ooter+0.913
Neg logit contributions
�士-1.470
 conclud-1.037
\\\\\\\\-1.027
 Debor-1.013
utsu-0.935
Token As
Token ID1081
Feature activation+2.00e+00

Pos logit contributions
spot+0.946
amy+0.937
 laps+0.931
 Freedom+0.915
ground+0.912
Neg logit contributions
�士-1.471
 conclud-1.080
\\\\\\\\-1.034
 Debor-1.005
ntil-0.955
Token both
Token ID1111
Feature activation-3.54e+00

Pos logit contributions
spot+1.288
 laps+1.284
amy+1.270
ground+1.235
 Freedom+1.225
Neg logit contributions
�士-2.003
 conclud-1.430
\\\\\\\\-1.417
 Debor-1.366
utsu-1.278
Token the
Token ID262
Feature activation-5.77e+00

Pos logit contributions
�士+3.053
 conclud+2.078
 Debor+2.060
\\\\\\\\+2.031
 Russo+1.889
Neg logit contributions
spot-2.708
amy-2.677
 laps-2.648
ground-2.613
arten-2.599
Token NFL
Token ID5134
Feature activation-8.02e+00

Pos logit contributions
�士+5.163
 Debor+3.609
 conclud+3.581
\\\\\\\\+3.513
 Russo+3.369
Neg logit contributions
spot-4.125
amy-4.043
 laps-4.004
arten-3.967
ooter-3.965
Token and
Token ID290
Feature activation-3.51e+00

Pos logit contributions
�士+6.753
 conclud+4.646
\\\\\\\\+4.504
 Debor+4.501
 Russo+4.120
Neg logit contributions
spot-5.901
 laps-5.854
amy-5.782
dirty-5.738
ooter-5.719
Token the
Token ID262
Feature activation-2.34e+00

Pos logit contributions
�士+3.266
 conclud+2.291
 Debor+2.274
\\\\\\\\+2.256
 Russo+2.115
Neg logit contributions
spot-2.448
amy-2.413
 laps-2.388
ground-2.354
arten-2.347
Token NFL
Token ID5134
Feature activation-1.85e+00

Pos logit contributions
�士+2.169
 conclud+1.514
 Debor+1.494
\\\\\\\\+1.491
 Russo+1.381
Neg logit contributions
spot-1.655
amy-1.636
 laps-1.624
ground-1.595
arten-1.583
TokenPA
Token ID4537
Feature activation-5.77e+00

Pos logit contributions
�士+1.722
 conclud+1.202
 Debor+1.185
\\\\\\\\+1.184
 Russo+1.094
Neg logit contributions
spot-1.311
amy-1.298
 laps-1.287
ground-1.263
arten-1.254
Token state
Token ID1181
Feature activation+8.78e-01

Pos logit contributions
�士+5.221
 conclud+3.703
 Debor+3.663
\\\\\\\\+3.542
 Russo+3.391
Neg logit contributions
spot-4.041
amy-4.010
 laps-3.907
ground-3.889
arten-3.885
Token has
Token ID468
Feature activation-7.59e-01

Pos logit contributions
spot+0.038
 laps+0.038
amy+0.037
ground+0.037
arten+0.036
Neg logit contributions
�士-0.052
 conclud-0.036
\\\\\\\\-0.036
 Debor-0.035
 Russo-0.033
Token never
Token ID1239
Feature activation+2.62e+00

Pos logit contributions
�士+0.746
 conclud+0.533
\\\\\\\\+0.528
 Debor+0.522
 Russo+0.486
Neg logit contributions
spot-0.498
 laps-0.492
amy-0.491
ground-0.479
arten-0.473
Token released
Token ID2716
Feature activation+1.98e-01

Pos logit contributions
 laps+1.700
spot+1.677
amy+1.651
ground+1.621
arten+1.581
Neg logit contributions
�士-2.655
\\\\\\\\-1.922
 conclud-1.891
 Debor-1.809
ntil-1.698
Token a
Token ID257
Feature activation-2.56e-01

Pos logit contributions
spot+0.130
 laps+0.128
amy+0.128
ground+0.125
arten+0.123
Neg logit contributions
�士-0.194
 conclud-0.139
\\\\\\\\-0.137
 Debor-0.136
 Russo-0.126
Token death
Token ID1918
Feature activation-9.88e-03

Pos logit contributions
�士+0.240
 conclud+0.168
\\\\\\\\+0.166
 Debor+0.165
 Russo+0.153
Neg logit contributions
spot-0.179
amy-0.176
 laps-0.176
ground-0.172
arten-0.170
Token toll
Token ID13592
Feature activation-8.70e+00

Pos logit contributions
�士+0.011
 conclud+0.008
\\\\\\\\+0.008
 Debor+0.008
 Russo+0.007
Neg logit contributions
spot-0.006
 laps-0.005
amy-0.005
ground-0.005
ooter-0.005
Token from
Token ID422
Feature activation-4.81e-01

Pos logit contributions
�士+7.191
 conclud+5.011
 Debor+4.988
\\\\\\\\+4.775
 Russo+4.603
Neg logit contributions
amy-6.351
spot-6.339
ooter-6.266
 laps-6.170
dirty-6.157
Token the
Token ID262
Feature activation-4.06e-01

Pos logit contributions
�士+0.478
 conclud+0.342
\\\\\\\\+0.338
 Debor+0.336
 Russo+0.311
Neg logit contributions
spot-0.312
 laps-0.308
amy-0.307
ground-0.300
ooter-0.297
Token crackdown
Token ID22671
Feature activation-6.38e-01

Pos logit contributions
�士+0.391
 conclud+0.277
 Debor+0.274
\\\\\\\\+0.273
 Russo+0.254
Neg logit contributions
spot-0.272
amy-0.269
 laps-0.267
ground-0.262
arten-0.260
Token after
Token ID706
Feature activation-8.95e-01

Pos logit contributions
�士+0.621
 conclud+0.437
\\\\\\\\+0.433
 Debor+0.426
 Russo+0.394
Neg logit contributions
spot-0.434
 laps-0.427
amy-0.426
ground-0.419
arten-0.410
Token troops
Token ID6553
Feature activation-9.12e-01

Pos logit contributions
�士+0.893
 conclud+0.642
 Debor+0.634
\\\\\\\\+0.633
 Russo+0.591
Neg logit contributions
spot-0.569
amy-0.562
 laps-0.558
ground-0.546
arten-0.542
Tokenra
Token ID430
Feature activation+4.39e-01

Pos logit contributions
�士+2.541
 conclud+1.992
 Debor+1.972
\\\\\\\\+1.971
 Russo+1.879
Neg logit contributions
spot-0.669
amy-0.653
 laps-0.647
ground-0.620
arten-0.610
Tokenha
Token ID3099
Feature activation+2.34e+00

Pos logit contributions
spot+0.292
amy+0.290
 laps+0.288
ground+0.282
ooter+0.279
Neg logit contributions
�士-0.428
 conclud-0.303
\\\\\\\\-0.300
 Debor-0.299
 Russo-0.277
Token and
Token ID290
Feature activation-3.01e+00

Pos logit contributions
amy+1.537
spot+1.535
 laps+1.517
ground+1.482
ooter+1.470
Neg logit contributions
�士-2.305
 conclud-1.623
\\\\\\\\-1.618
 Debor-1.607
 Russo-1.486
Token the
Token ID262
Feature activation-8.61e-01

Pos logit contributions
�士+2.945
 conclud+2.126
 Debor+2.106
\\\\\\\\+2.076
 Russo+1.959
Neg logit contributions
spot-1.943
amy-1.905
 laps-1.883
ground-1.859
arten-1.853
Token entire
Token ID2104
Feature activation+2.05e-01

Pos logit contributions
�士+0.853
 conclud+0.612
 Debor+0.605
\\\\\\\\+0.603
 Russo+0.563
Neg logit contributions
spot-0.554
amy-0.547
 laps-0.542
ground-0.531
arten-0.528
Token temple
Token ID12505
Feature activation-7.08e+00

Pos logit contributions
spot+0.130
amy+0.129
 laps+0.128
ground+0.125
arten+0.124
Neg logit contributions
�士-0.206
 conclud-0.148
\\\\\\\\-0.146
 Debor-0.146
 Russo-0.136
Token is
Token ID318
Feature activation-2.35e+00

Pos logit contributions
�士+6.163
 conclud+4.359
 Debor+4.217
\\\\\\\\+4.144
 Russo+3.920
Neg logit contributions
spot-5.000
amy-4.967
ooter-4.881
arten-4.876
 laps-4.843
Token very
Token ID845
Feature activation-6.02e-01

Pos logit contributions
�士+2.237
 conclud+1.585
 Debor+1.567
\\\\\\\\+1.554
 Russo+1.453
Neg logit contributions
spot-1.593
amy-1.577
 laps-1.559
ground-1.529
arten-1.528
Token beautiful
Token ID4950
Feature activation-1.60e+00

Pos logit contributions
�士+0.563
 conclud+0.393
\\\\\\\\+0.389
 Debor+0.387
 Russo+0.357
Neg logit contributions
spot-0.424
amy-0.419
 laps-0.418
ground-0.409
arten-0.403
Token filled
Token ID5901
Feature activation+1.62e+00

Pos logit contributions
�士+1.475
 conclud+1.031
 Debor+1.018
\\\\\\\\+1.014
 Russo+0.941
Neg logit contributions
spot-1.124
amy-1.114
 laps-1.104
ground-1.081
arten-1.080
Token with
Token ID351
Feature activation-2.15e+00

Pos logit contributions
spot+1.063
amy+1.050
 laps+1.043
ground+1.027
ooter+1.008
Neg logit contributions
�士-1.580
 conclud-1.130
\\\\\\\\-1.117
 Debor-1.113
 Russo-1.034
Token traff
Token ID11878
Feature activation+2.00e+00

Pos logit contributions
�士+3.273
 conclud+2.366
 Debor+2.355
\\\\\\\\+2.327
 Russo+2.203
Neg logit contributions
spot-2.096
amy-2.096
ooter-2.048
 laps-2.035
arten-2.029
Tokenicked
Token ID9484
Feature activation-8.59e-01

Pos logit contributions
spot+1.177
amy+1.173
 laps+1.152
ground+1.133
ooter+1.126
Neg logit contributions
�士-2.119
 conclud-1.558
\\\\\\\\-1.522
 Debor-1.508
 Russo-1.414
Token across
Token ID1973
Feature activation-3.11e+00

Pos logit contributions
�士+0.825
 conclud+0.583
 Debor+0.575
\\\\\\\\+0.575
 Russo+0.533
Neg logit contributions
spot-0.581
amy-0.574
 laps-0.570
ground-0.559
arten-0.554
Token peer
Token ID12720
Feature activation+2.11e+00

Pos logit contributions
�士+2.961
 conclud+2.090
 Debor+2.062
\\\\\\\\+2.059
 Russo+1.911
Neg logit contributions
spot-2.124
amy-2.099
 laps-2.084
ground-2.043
arten-2.028
Token to
Token ID284
Feature activation-4.68e+00

Pos logit contributions
spot+1.304
amy+1.280
 laps+1.279
ground+1.263
 Freedom+1.222
Neg logit contributions
�士-2.207
 conclud-1.580
 Debor-1.557
\\\\\\\\-1.540
utsu-1.439
Token peer
Token ID12720
Feature activation-7.49e+00

Pos logit contributions
�士+3.820
 Debor+2.584
\\\\\\\\+2.583
 conclud+2.564
 Russo+2.400
Neg logit contributions
amy-3.622
spot-3.614
ooter-3.542
 laps-3.516
ground-3.511
Token and
Token ID290
Feature activation-1.39e+00

Pos logit contributions
�士+6.699
 conclud+4.889
 Debor+4.865
\\\\\\\\+4.760
 Russo+4.567
Neg logit contributions
spot-5.022
amy-5.003
arten-4.907
ooter-4.894
 laps-4.857
Token virtual
Token ID7166
Feature activation-1.11e+00

Pos logit contributions
�士+1.355
 conclud+0.968
 Debor+0.956
\\\\\\\\+0.953
 Russo+0.889
Neg logit contributions
spot-0.908
amy-0.898
 laps-0.889
ground-0.872
ooter-0.867
Token private
Token ID2839
Feature activation+1.13e+00

Pos logit contributions
�士+1.105
 conclud+0.790
 Debor+0.779
\\\\\\\\+0.779
 Russo+0.722
Neg logit contributions
spot-0.717
amy-0.708
 laps-0.703
ground-0.691
arten-0.678
Token networks
Token ID7686
Feature activation+1.48e+00

Pos logit contributions
spot+0.607
amy+0.600
 laps+0.595
ground+0.581
 Freedom+0.561
Neg logit contributions
�士-1.266
 conclud-0.943
\\\\\\\\-0.923
 Debor-0.920
 Russo-0.860
Token.
Token ID13
Feature activation-1.25e+00

Pos logit contributions
spot+0.997
 laps+0.983
amy+0.977
ground+0.960
arten+0.937
Neg logit contributions
�士-1.458
 conclud-1.019
\\\\\\\\-1.010
 Debor-1.002
 Russo-0.931