TOP ACTIVATIONS
MAX = 1.548

Pop ulate D ensity Grid ( Uniform Grid < float >
Part icle :: Get Mass ( float ambient D ensity )
(' j q depend ency ', [ ]) . direct ive
, unstable and , above all , an uncons c ion
Sh and ling 1999 John Lith gow 1999 Michael
Sh and ling 1997 John Lith gow 1997 Michael
b _ sub div ide ( space ) { // 1
, and could upset Na ` Vi in some universe ,
_ argument (" - i ", " -- images ", required
app data _ full v ) { v . vertex .
a boot c amped Na ` Vi team fresh off of
Sunderland 's manager before ext oll ing the Tex an 's
Occ asionally dismissed as a one - dimensional film
map ($ SR . Width , $ SR . Height )
. <|endoftext|> From the very beginning , the Obama administration
Sh and ling 1996 John Lith gow 1996 Kel
the game . <|endoftext|> Share . Two iconic horror titles are
help us continue to write about the issues that matter .
this comment on Facebook Share this comment on Twitter
You are more guilty than innocent . It comes

MIN ACTIVATIONS
MIN = -1.335

www . bel fast te legraph . co . uk /
www . bel fast te legraph . co . uk /
. Newsletter Sign Up Continue reading the main story
March 24 , 2016 . REUTERS / Nick Oxford / File
IES M OST READ <|endoftext|> K illed for watching
Newsletter Sign Up Continue reading the main story
) party | AFP / Getty Opinion It won
https :// doi . org / 10 . 13 71 /
. Newsletter Sign Up Continue reading the main story
mail this to a friend Print able version <|endoftext|> A university
mail this to a friend Print able version <|endoftext|> Rob C
| Select Width , Height Write - Ver b ose -
f d | < -- Stack pointer + -------------------- --+ |
. Newsletter Sign Up Continue reading the main story
to Reuters . ADVERTISEMENT Twenty - three
Today w e can d raw up the most g
May 28 , 2014 . REUTERS / Michael K lim enty
or Share this story : http :// usat . ly /
. Over and over , things that were im
Their Employees Email Print Whats app Menu Whats app

INTERVAL 0.827 - 1.548
CONTAINS 0.010%

very small lens . Image via Pan or am io .
_ CLASS _ ST ART ( mem c py _ speed
mer 2000 John Lith gow 2000 Eric
) Pretty safe to say , Red Son ja is
Sunderland 's manager before ext oll ing the Tex an 's

INTERVAL 0.107 - 0.827
CONTAINS 27.075%

had killed dozens of heroes , and won in seconds .
, B hi w ani , J h aj jar and
approach Lac an s teaching either you believe
fine , she told reporters . Certainly
adm iring column in The New York Times portrayed him as

INTERVAL -0.614 - 0.107
CONTAINS 72.765%

é des Cors aires ay ant c id és de
maps that show things like most popular film or job or
The FIR further quotes the contents of the audio clip
and seeing what my inner child wants ." X
Nav igator news release on March 2 , 2012 , said

INTERVAL -1.335 - -0.614
CONTAINS 0.151%

H t / W t Comp . Rating 247 ESPN Rivals
our top stories Free Sign Up The picture was
System . Draw ing . Font ($ Font Name , $
boys or beauty in the case of girls .
BY library ORDER BY count desc | Row | library |
TokenPop
Token ID16979
Feature activation-2.37e-01

Pos logit contributions
+1.538
 contro+1.180
 prin+1.139
 subdivision+1.127
tie+1.122
Neg logit contributions
itars-1.314
lees-1.253
 Axe-1.231
iltr-1.231
orks-1.224
Tokenulate
Token ID5039
Feature activation+1.46e-01

Pos logit contributions
+0.831
 contro+0.556
edia+0.527
 subdivision+0.511
tie+0.511
Neg logit contributions
itars-1.482
lees-1.417
 Axe-1.412
 Ashes-1.411
orks-1.409
TokenD
Token ID35
Feature activation-8.55e-02

Pos logit contributions
itars+0.516
lees+0.490
 Axe+0.480
iltr+0.479
 Ashes+0.472
Neg logit contributions
-0.912
 contro-0.730
 prin-0.715
 nomine-0.699
 subdivision-0.696
Tokenensity
Token ID6377
Feature activation+3.15e-02

Pos logit contributions
+0.489
 contro+0.384
edia+0.380
 prin+0.375
 subdivision+0.375
Neg logit contributions
itars-0.342
 Axe-0.325
 Ashes-0.321
lees-0.320
 Karma-0.318
TokenGrid
Token ID41339
Feature activation+2.51e-01

Pos logit contributions
itars+0.101
lees+0.096
 Axe+0.093
iltr+0.093
orks+0.091
Neg logit contributions
-0.207
 contro-0.168
 prin-0.164
 nomine-0.161
 subdivision-0.161
Token(
Token ID7
Feature activation+1.55e+00

Pos logit contributions
itars+1.009
lees+0.971
 Axe+0.955
iltr+0.954
 Ashes+0.945
Neg logit contributions
-1.441
 contro-1.121
 prin-1.090
 nomine-1.065
edia-1.064
Token Uniform
Token ID35712
Feature activation+1.17e-02

Pos logit contributions
itars+5.613
 Axe+5.409
lees+5.352
iltr+5.248
 Ashes+5.242
Neg logit contributions
-8.892
 contro-6.863
 prin-6.700
ario-6.577
 nomine-6.556
TokenGrid
Token ID41339
Feature activation-3.49e-01

Pos logit contributions
itars+0.038
lees+0.035
 Axe+0.035
iltr+0.035
orks+0.034
Neg logit contributions
-0.077
 contro-0.062
 prin-0.061
 subdivision-0.059
edia-0.059
Token<
Token ID27
Feature activation+1.78e-01

Pos logit contributions
+1.968
 contro+1.558
 prin+1.517
 subdivision+1.497
edia+1.481
Neg logit contributions
itars-1.463
lees-1.394
iltr-1.365
 Axe-1.347
lash-1.341
Token float
Token ID12178
Feature activation-2.18e-01

Pos logit contributions
itars+0.701
lees+0.667
iltr+0.654
 Axe+0.652
orks+0.648
Neg logit contributions
-1.044
 contro-0.823
 prin-0.802
 subdivision-0.790
edia-0.784
Token >
Token ID1875
Feature activation+2.52e-01

Pos logit contributions
+1.186
 contro+0.921
 prin+0.900
 subdivision+0.890
edia+0.878
Neg logit contributions
itars-0.942
lees-0.910
iltr-0.885
orks-0.884
 Axe-0.877
Token Part
Token ID2142
Feature activation-1.40e-01

Pos logit contributions
itars+0.401
lees+0.384
iltr+0.376
orks+0.374
 Axe+0.373
Neg logit contributions
-0.546
 contro-0.430
 prin-0.418
 subdivision-0.412
edia-0.405
Tokenicle
Token ID1548
Feature activation-2.33e-01

Pos logit contributions
+0.692
 contro+0.516
 prin+0.499
 subdivision+0.486
edia+0.484
Neg logit contributions
itars-0.685
lees-0.658
 Axe-0.650
iltr-0.649
orks-0.643
Token::
Token ID3712
Feature activation-3.23e-01

Pos logit contributions
+1.329
 contro+1.043
 prin+1.012
 subdivision+1.001
edia+0.993
Neg logit contributions
itars-0.957
lees-0.906
iltr-0.891
 Axe-0.887
orks-0.883
TokenGet
Token ID3855
Feature activation-1.98e-01

Pos logit contributions
+1.599
 contro+1.203
 prin+1.159
 subdivision+1.148
tie+1.139
Neg logit contributions
itars-1.561
lees-1.491
 Axe-1.470
iltr-1.470
orks-1.460
TokenMass
Token ID20273
Feature activation+1.95e-01

Pos logit contributions
+1.264
 contro+1.015
 prin+0.989
 subdivision+0.980
edia+0.975
Neg logit contributions
itars-0.672
lees-0.633
iltr-0.620
 Axe-0.618
orks-0.617
Token(
Token ID7
Feature activation+1.17e+00

Pos logit contributions
itars+0.696
lees+0.661
 Axe+0.649
iltr+0.647
 Ashes+0.639
Neg logit contributions
-1.213
 contro-0.965
 prin-0.941
edia-0.924
 subdivision-0.921
Token float
Token ID12178
Feature activation+2.85e-01

Pos logit contributions
itars+4.278
lees+4.114
 Axe+4.080
iltr+4.017
 Ashes+3.974
Neg logit contributions
-6.874
 contro-5.391
 prin-5.255
 citiz-5.147
 nomine-5.111
Token ambient
Token ID25237
Feature activation-3.18e-01

Pos logit contributions
itars+1.184
lees+1.131
iltr+1.108
 Axe+1.102
orks+1.101
Neg logit contributions
-1.613
 contro-1.267
 prin-1.233
 subdivision-1.212
edia-1.198
TokenD
Token ID35
Feature activation-8.75e-02

Pos logit contributions
+2.076
 contro+1.690
 prin+1.655
 subdivision+1.637
 nomine+1.617
Neg logit contributions
itars-1.026
lees-0.970
iltr-0.952
 Axe-0.941
orks-0.939
Tokenensity
Token ID6377
Feature activation-1.00e-01

Pos logit contributions
+0.528
 contro+0.421
 prin+0.414
 subdivision+0.405
edia+0.402
Neg logit contributions
itars-0.327
lees-0.310
iltr-0.304
 Axe-0.304
orks-0.300
Token )
Token ID1267
Feature activation+6.19e-01

Pos logit contributions
+0.689
 contro+0.566
 prin+0.556
 subdivision+0.550
 nomine+0.543
Neg logit contributions
itars-0.293
lees-0.277
iltr-0.270
orks-0.268
 Axe-0.266
Token('
Token ID10786
Feature activation+6.80e-01

Pos logit contributions
itars+0.921
lees+0.867
 Axe+0.850
iltr+0.847
 Ashes+0.842
Neg logit contributions
-1.434
 contro-1.134
 prin-1.104
edia-1.086
 subdivision-1.081
Tokenj
Token ID73
Feature activation+4.86e-02

Pos logit contributions
itars+2.808
lees+2.688
iltr+2.642
 Axe+2.641
orks+2.607
Neg logit contributions
-3.837
 contro-2.991
 prin-2.922
 subdivision-2.849
 nomine-2.846
Tokenq
Token ID80
Feature activation+1.52e-01

Pos logit contributions
itars+0.199
lees+0.189
 Axe+0.187
 Ashes+0.186
iltr+0.185
Neg logit contributions
-0.277
 contro-0.216
 prin-0.210
edia-0.207
 subdivision-0.206
Tokendepend
Token ID45841
Feature activation+3.39e-01

Pos logit contributions
itars+0.568
lees+0.542
iltr+0.530
 Axe+0.528
orks+0.523
Neg logit contributions
-0.926
 contro-0.736
 prin-0.719
 subdivision-0.705
 nomine-0.701
Tokenency
Token ID1387
Feature activation+6.61e-02

Pos logit contributions
itars+1.307
lees+1.240
 Axe+1.221
iltr+1.218
orks+1.204
Neg logit contributions
-2.019
 contro-1.595
 prin-1.554
 subdivision-1.522
edia-1.519
Token',
Token ID3256
Feature activation+1.17e+00

Pos logit contributions
itars+0.212
lees+0.198
 Axe+0.195
iltr+0.193
 Ashes+0.192
Neg logit contributions
-0.438
 contro-0.355
 prin-0.346
 subdivision-0.340
edia-0.340
Token [
Token ID685
Feature activation+2.24e-01

Pos logit contributions
itars+3.605
lees+3.395
 Axe+3.382
iltr+3.328
 Karma+3.322
Neg logit contributions
-7.678
 contro-6.184
 prin-6.045
edia-5.967
 nomine-5.938
Token])
Token ID12962
Feature activation+5.17e-01

Pos logit contributions
itars+0.880
lees+0.830
 Axe+0.816
iltr+0.816
orks+0.809
Neg logit contributions
-1.325
 contro-1.042
 prin-1.017
 subdivision-1.002
edia-0.993
Token.
Token ID764
Feature activation-2.97e-01

Pos logit contributions
itars+1.895
lees+1.799
 Axe+1.767
iltr+1.766
orks+1.742
Neg logit contributions
-3.166
 contro-2.514
 prin-2.452
 subdivision-2.406
edia-2.402
Tokendirect
Token ID12942
Feature activation-3.41e-02

Pos logit contributions
+1.705
 contro+1.354
 prin+1.320
tie+1.312
 subdivision+1.307
Neg logit contributions
itars-1.181
 Axe-1.111
 Ashes-1.100
lees-1.099
iltr-1.098
Tokenive
Token ID425
Feature activation-2.18e-01

Pos logit contributions
+0.159
 contro+0.117
 prin+0.113
 subdivision+0.110
 nomine+0.109
Neg logit contributions
itars-0.175
lees-0.167
 Axe-0.166
iltr-0.166
 Ashes-0.165
Token,
Token ID11
Feature activation+1.33e-01

Pos logit contributions
itars+0.992
lees+0.924
 Axe+0.912
iltr+0.904
 Ashes+0.891
Neg logit contributions
-2.322
 contro-1.878
 prin-1.836
edia-1.818
 nomine-1.811
Token unstable
Token ID21354
Feature activation+3.97e-01

Pos logit contributions
itars+0.557
lees+0.530
iltr+0.521
 Axe+0.520
orks+0.517
Neg logit contributions
-0.746
 contro-0.587
 prin-0.569
 subdivision-0.557
edia-0.552
Token and
Token ID290
Feature activation-6.81e-02

Pos logit contributions
itars+1.145
lees+1.068
 Axe+1.041
iltr+1.037
 Ashes+1.025
Neg logit contributions
-2.762
 contro-2.221
 prin-2.172
edia-2.157
 nomine-2.148
Token,
Token ID11
Feature activation+2.47e-01

Pos logit contributions
+0.354
 contro+0.283
 prin+0.270
 subdivision+0.264
 nomine+0.259
Neg logit contributions
itars-0.311
lees-0.295
iltr-0.292
orks-0.290
 Axe-0.288
Token above
Token ID2029
Feature activation+9.09e-02

Pos logit contributions
itars+1.126
lees+1.080
iltr+1.064
 Axe+1.061
orks+1.055
Neg logit contributions
-1.288
 contro-0.992
 prin-0.960
 subdivision-0.937
 nomine-0.927
Token all
Token ID477
Feature activation+1.16e+00

Pos logit contributions
itars+0.429
lees+0.411
iltr+0.405
 Axe+0.405
orks+0.402
Neg logit contributions
-0.461
 contro-0.352
 prin-0.340
 subdivision-0.332
edia-0.329
Token,
Token ID11
Feature activation+3.24e-01

Pos logit contributions
itars+2.841
lees+2.724
 Axe+2.640
 Karma+2.598
iltr+2.532
Neg logit contributions
-8.374
 nomine-6.755
 contro-6.622
 citiz-6.613
 prin-6.574
Token an
Token ID281
Feature activation+2.68e-01

Pos logit contributions
itars+1.451
lees+1.388
iltr+1.367
 Axe+1.365
orks+1.353
Neg logit contributions
-1.729
 contro-1.330
 prin-1.289
 subdivision-1.260
edia-1.252
Token uncons
Token ID13962
Feature activation-4.36e-02

Pos logit contributions
itars+1.238
lees+1.187
 Axe+1.171
iltr+1.170
orks+1.157
Neg logit contributions
-1.394
 contro-1.057
 prin-1.026
 subdivision-1.001
edia-0.997
Tokenc
Token ID66
Feature activation-3.38e-01

Pos logit contributions
+0.205
 contro+0.154
 prin+0.150
edia+0.146
 subdivision+0.145
Neg logit contributions
itars-0.218
lees-0.209
 Axe-0.206
iltr-0.205
 Ashes-0.205
Tokenion
Token ID295
Feature activation+3.27e-01

Pos logit contributions
+1.940
 contro+1.628
edia+1.595
tie+1.561
ario+1.557
Neg logit contributions
itars-1.275
lees-1.184
 Karma-1.177
 Ashes-1.175
lash-1.166
Token Sh
Token ID911
Feature activation+3.91e-01

Pos logit contributions
itars+0.609
iltr+0.573
lees+0.564
orks+0.563
ioxide+0.546
Neg logit contributions
-1.039
 contro-0.835
 prin-0.821
 subdivision-0.807
edia-0.802
Tokenand
Token ID392
Feature activation+4.06e-02

Pos logit contributions
itars+1.223
 Axe+1.125
 Ashes+1.124
lees+1.119
iltr+1.118
Neg logit contributions
-2.584
 contro-2.122
tie-2.086
 prin-2.062
edia-2.057
Tokenling
Token ID1359
Feature activation-1.98e-01

Pos logit contributions
itars+0.230
 Axe+0.221
 Ashes+0.220
iltr+0.219
ioxide+0.217
Neg logit contributions
-0.161
 contro-0.116
tie-0.113
edia-0.110
 prin-0.108
Token 1999
Token ID7358
Feature activation+1.92e-01

Pos logit contributions
+1.118
 contro+0.874
 prin+0.852
 subdivision+0.828
 nomine+0.823
Neg logit contributions
itars-0.816
lees-0.787
 Axe-0.772
 Ashes-0.763
iltr-0.761
Token John
Token ID1757
Feature activation+4.07e-01

Pos logit contributions
itars+0.719
lees+0.683
iltr+0.670
 Axe+0.669
orks+0.662
Neg logit contributions
-1.166
 contro-0.926
 prin-0.903
 subdivision-0.886
edia-0.884
Token Lith
Token ID19730
Feature activation+1.10e+00

Pos logit contributions
itars+1.165
lees+1.077
iltr+1.067
orks+1.052
 Axe+1.032
Neg logit contributions
-2.835
 contro-2.326
 prin-2.278
edia-2.244
 subdivision-2.243
Tokengow
Token ID21175
Feature activation+6.74e-02

Pos logit contributions
itars+4.154
lees+4.003
iltr+3.877
lash+3.842
orks+3.838
Neg logit contributions
-6.615
 contro-5.208
 nomine-5.168
 prin-5.124
 citiz-5.070
Token
Token ID198
Feature activation+3.00e-01

Pos logit contributions
itars+0.284
iltr+0.268
lees+0.268
orks+0.262
 Axe+0.261
Neg logit contributions
-0.376
 contro-0.293
 prin-0.284
edia-0.283
tie-0.282
Token
Token ID198
Feature activation+3.74e-01

Pos logit contributions
itars+1.243
lees+1.168
iltr+1.164
orks+1.146
 Axe+1.143
Neg logit contributions
-1.695
 contro-1.335
 prin-1.289
tie-1.277
edia-1.277
Token1999
Token ID18946
Feature activation+5.27e-01

Pos logit contributions
itars+1.493
lees+1.460
iltr+1.399
 Ferguson+1.378
lash+1.377
Neg logit contributions
-2.086
 contro-1.688
 prin-1.644
 citiz-1.612
 nomine-1.602
Token Michael
Token ID3899
Feature activation+2.32e-01

Pos logit contributions
itars+1.867
lees+1.772
 Axe+1.758
iltr+1.727
 Ashes+1.721
Neg logit contributions
-3.291
 contro-2.631
 prin-2.561
 subdivision-2.521
 nomine-2.521
Token Sh
Token ID911
Feature activation+3.46e-01

Pos logit contributions
itars+0.345
iltr+0.324
orks+0.318
lees+0.318
ioxide+0.308
Neg logit contributions
-0.573
 contro-0.461
 prin-0.455
 subdivision-0.446
tie-0.444
Tokenand
Token ID392
Feature activation+2.17e-02

Pos logit contributions
itars+1.098
 Ashes+1.016
 Axe+1.013
iltr+1.004
lees+1.003
Neg logit contributions
-2.261
 contro-1.861
tie-1.834
edia-1.805
 prin-1.802
Tokenling
Token ID1359
Feature activation-2.80e-01

Pos logit contributions
itars+0.124
 Axe+0.120
 Ashes+0.119
iltr+0.118
ioxide+0.117
Neg logit contributions
-0.085
 contro-0.061
tie-0.060
edia-0.058
 prin-0.057
Token 1997
Token ID8309
Feature activation+1.01e-01

Pos logit contributions
+1.682
 contro+1.328
 prin+1.295
 subdivision+1.269
edia+1.264
Neg logit contributions
itars-1.071
lees-1.019
 Axe-0.999
iltr-0.996
 Ashes-0.987
Token John
Token ID1757
Feature activation+2.44e-01

Pos logit contributions
itars+0.402
lees+0.383
iltr+0.377
 Axe+0.374
orks+0.372
Neg logit contributions
-0.585
 contro-0.460
 prin-0.449
 subdivision-0.439
edia-0.438
Token Lith
Token ID19730
Feature activation+1.04e+00

Pos logit contributions
itars+0.670
lees+0.624
 Axe+0.610
iltr+0.607
orks+0.596
Neg logit contributions
-1.726
 contro-1.420
 prin-1.390
 subdivision-1.369
edia-1.364
Tokengow
Token ID21175
Feature activation+1.59e-02

Pos logit contributions
itars+3.928
lees+3.790
iltr+3.665
orks+3.633
lash+3.629
Neg logit contributions
-6.259
 contro-4.931
 nomine-4.878
 prin-4.851
 citiz-4.787
Token
Token ID198
Feature activation+2.58e-01

Pos logit contributions
itars+0.066
lees+0.063
iltr+0.063
orks+0.061
 Axe+0.061
Neg logit contributions
-0.089
 contro-0.069
 prin-0.067
edia-0.067
tie-0.067
Token
Token ID198
Feature activation+2.64e-01

Pos logit contributions
itars+1.080
lees+1.014
iltr+1.012
orks+0.995
 Axe+0.992
Neg logit contributions
-1.449
 contro-1.141
 prin-1.100
tie-1.094
edia-1.092
Token1997
Token ID21498
Feature activation+5.53e-01

Pos logit contributions
itars+0.968
lees+0.926
iltr+0.902
 Axe+0.895
lash+0.885
Neg logit contributions
-1.612
 contro-1.288
 prin-1.256
 nomine-1.232
 subdivision-1.230
Token Michael
Token ID3899
Feature activation+1.36e-01

Pos logit contributions
itars+1.995
lees+1.891
 Axe+1.880
 Ashes+1.843
iltr+1.843
Neg logit contributions
-3.418
 contro-2.718
 prin-2.637
 nomine-2.605
 subdivision-2.601
Tokenb
Token ID65
Feature activation-1.04e-01

Pos logit contributions
+0.748
 contro+0.614
 prin+0.602
 subdivision+0.592
edia+0.590
Neg logit contributions
itars-0.295
lees-0.275
 Axe-0.268
iltr-0.268
orks-0.264
Token_
Token ID62
Feature activation-1.63e-01

Pos logit contributions
+0.611
 contro+0.481
 prin+0.469
 subdivision+0.461
edia+0.458
Neg logit contributions
itars-0.409
lees-0.389
iltr-0.383
 Axe-0.383
orks-0.378
Tokensub
Token ID7266
Feature activation-2.54e-02

Pos logit contributions
+0.903
 contro+0.700
 prin+0.685
 subdivision+0.677
tie+0.667
Neg logit contributions
itars-0.692
lees-0.657
 Axe-0.651
iltr-0.649
 Ashes-0.642
Tokendiv
Token ID7146
Feature activation+7.24e-03

Pos logit contributions
+0.136
 contro+0.104
 prin+0.102
 subdivision+0.099
edia+0.099
Neg logit contributions
itars-0.113
lees-0.108
 Axe-0.106
iltr-0.106
orks-0.105
Tokenide
Token ID485
Feature activation-2.88e-02

Pos logit contributions
itars+0.028
lees+0.027
 Axe+0.026
iltr+0.026
orks+0.026
Neg logit contributions
-0.043
 contro-0.034
 prin-0.033
 subdivision-0.032
edia-0.032
Token(
Token ID7
Feature activation+1.03e+00

Pos logit contributions
+0.172
 contro+0.136
 prin+0.133
 subdivision+0.130
edia+0.130
Neg logit contributions
itars-0.110
lees-0.105
 Axe-0.103
iltr-0.103
orks-0.102
Token space
Token ID2272
Feature activation-1.88e-02

Pos logit contributions
itars+4.191
lees+4.025
 Axe+3.983
orks+3.909
iltr+3.908
Neg logit contributions
-5.726
 contro-4.439
 prin-4.269
 nomine-4.251
edia-4.225
Token )
Token ID1267
Feature activation+5.60e-01

Pos logit contributions
+0.126
 contro+0.102
 prin+0.100
 subdivision+0.099
edia+0.098
Neg logit contributions
itars-0.059
lees-0.055
iltr-0.055
 Axe-0.054
orks-0.054
Token {
Token ID1391
Feature activation+2.34e-01

Pos logit contributions
itars+1.936
lees+1.824
 Axe+1.801
iltr+1.781
 Ashes+1.772
Neg logit contributions
-3.543
 contro-2.807
 prin-2.737
edia-2.715
 nomine-2.704
Token //
Token ID3373
Feature activation+3.44e-02

Pos logit contributions
itars+1.025
lees+0.980
 Axe+0.965
iltr+0.965
orks+0.955
Neg logit contributions
-1.265
 contro-0.974
 prin-0.946
 subdivision-0.925
edia-0.920
Token 1
Token ID352
Feature activation-3.25e-01

Pos logit contributions
itars+0.150
lees+0.143
iltr+0.141
 Axe+0.141
orks+0.139
Neg logit contributions
-0.187
 contro-0.145
 prin-0.141
 subdivision-0.138
edia-0.136
Token,
Token ID11
Feature activation+1.38e-01

Pos logit contributions
itars+0.436
lees+0.413
iltr+0.411
 Axe+0.407
orks+0.406
Neg logit contributions
-0.573
 contro-0.447
 prin-0.434
 subdivision-0.424
edia-0.424
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
itars+0.566
lees+0.539
iltr+0.531
 Axe+0.526
orks+0.526
Neg logit contributions
-0.783
 contro-0.614
 prin-0.597
 subdivision-0.584
edia-0.582
Token could
Token ID714
Feature activation-2.55e-01

Pos logit contributions
+0.061
 contro+0.049
 prin+0.047
 subdivision+0.046
edia+0.046
Neg logit contributions
itars-0.046
lees-0.044
iltr-0.043
orks-0.043
ioxide-0.042
Token upset
Token ID9247
Feature activation-6.05e-01

Pos logit contributions
+1.271
 contro+1.013
 prin+0.958
 subdivision+0.936
tie+0.931
Neg logit contributions
itars-1.202
lees-1.149
iltr-1.134
ioxide-1.127
orks-1.122
Token Na
Token ID11013
Feature activation-4.53e-02

Pos logit contributions
+3.359
 contro+2.692
 prin+2.627
 subdivision+2.539
tie+2.528
Neg logit contributions
itars-2.513
iltr-2.380
lees-2.350
orks-2.328
ioxide-2.311
Token`
Token ID63
Feature activation+1.02e+00

Pos logit contributions
+0.292
 contro+0.236
 prin+0.231
edia+0.226
 subdivision+0.226
Neg logit contributions
itars-0.153
lees-0.143
iltr-0.141
 Axe-0.140
orks-0.139
TokenVi
Token ID38432
Feature activation+3.07e-01

Pos logit contributions
itars+4.167
lees+3.956
 Axe+3.923
iltr+3.920
lash+3.888
Neg logit contributions
-5.822
 contro-4.474
 prin-4.435
 nomine-4.319
 subdivision-4.287
Token in
Token ID287
Feature activation+1.83e-01

Pos logit contributions
itars+1.264
lees+1.205
iltr+1.186
 Axe+1.182
orks+1.174
Neg logit contributions
-1.747
 contro-1.367
 prin-1.328
 subdivision-1.301
edia-1.295
Token some
Token ID617
Feature activation-4.98e-02

Pos logit contributions
itars+0.769
lees+0.734
iltr+0.723
 Axe+0.720
orks+0.714
Neg logit contributions
-1.025
 contro-0.799
 prin-0.777
 subdivision-0.760
edia-0.756
Token universe
Token ID6881
Feature activation+2.46e-02

Pos logit contributions
+0.256
 contro+0.198
 prin+0.191
 subdivision+0.186
tie+0.183
Neg logit contributions
itars-0.231
lees-0.220
iltr-0.219
 Axe-0.216
orks-0.216
Token,
Token ID11
Feature activation-1.20e-01

Pos logit contributions
itars+0.098
lees+0.093
iltr+0.092
 Axe+0.091
orks+0.090
Neg logit contributions
-0.144
 contro-0.114
 prin-0.111
 subdivision-0.109
edia-0.108
Token_
Token ID62
Feature activation+1.10e-01

Pos logit contributions
+0.549
 contro+0.442
tie+0.435
edia+0.427
 prin+0.426
Neg logit contributions
itars-0.337
iltr-0.316
 Ashes-0.310
lees-0.309
 Axe-0.308
Tokenargument
Token ID49140
Feature activation+2.87e-02

Pos logit contributions
itars+0.321
 Ashes+0.298
 Axe+0.292
lees+0.291
ioxide+0.284
Neg logit contributions
-0.739
 contro-0.618
tie-0.607
ario-0.602
 prin-0.601
Token("
Token ID7203
Feature activation+5.66e-01

Pos logit contributions
itars+0.142
iltr+0.135
lees+0.133
 Ashes+0.133
orks+0.132
Neg logit contributions
-0.140
 contro-0.104
 prin-0.100
edia-0.099
 subdivision-0.098
Token-
Token ID12
Feature activation+1.51e-01

Pos logit contributions
itars+1.727
lees+1.589
iltr+1.567
 Axe+1.562
 Ashes+1.546
Neg logit contributions
-3.840
 contro-3.146
 prin-3.077
edia-3.027
 subdivision-3.026
Tokeni
Token ID72
Feature activation-1.26e-01

Pos logit contributions
itars+0.646
 Ashes+0.611
lees+0.607
 Axe+0.606
iltr+0.605
Neg logit contributions
-0.826
 contro-0.642
edia-0.631
tie-0.628
 prin-0.622
Token",
Token ID1600
Feature activation+1.01e+00

Pos logit contributions
+0.729
 contro+0.571
 prin+0.557
edia+0.549
tie+0.545
Neg logit contributions
itars-0.497
lees-0.470
iltr-0.466
 Axe-0.464
orks-0.463
Token "
Token ID366
Feature activation+9.77e-03

Pos logit contributions
itars+3.238
lees+3.052
 Axe+3.027
iltr+2.972
 Ashes+2.944
Neg logit contributions
-6.661
 contro-5.368
 prin-5.250
 nomine-5.203
 subdivision-5.156
Token--
Token ID438
Feature activation-9.77e-02

Pos logit contributions
itars+0.030
iltr+0.027
ioxide+0.027
lees+0.027
 Axe+0.027
Neg logit contributions
-0.065
 contro-0.054
tie-0.052
 prin-0.052
edia-0.052
Tokenimages
Token ID17566
Feature activation-1.11e-01

Pos logit contributions
+0.439
 contro+0.313
edia+0.306
tie+0.304
 prin+0.300
Neg logit contributions
itars-0.515
 Axe-0.495
 Ashes-0.490
iltr-0.488
ioxide-0.484
Token",
Token ID1600
Feature activation+2.70e-01

Pos logit contributions
+0.650
 contro+0.514
 prin+0.497
edia+0.490
tie+0.489
Neg logit contributions
itars-0.439
lees-0.415
 Ashes-0.409
iltr-0.409
 Axe-0.408
Token required
Token ID2672
Feature activation+1.07e-01

Pos logit contributions
itars+1.259
lees+1.206
 Axe+1.199
iltr+1.190
orks+1.177
Neg logit contributions
-1.378
 contro-1.033
 prin-1.002
edia-0.981
 subdivision-0.981
Token app
Token ID598
Feature activation-3.56e-02

Pos logit contributions
+0.745
 contro+0.594
 prin+0.567
 subdivision+0.553
edia+0.527
Neg logit contributions
itars-0.755
lees-0.730
iltr-0.713
orks-0.705
 Axe-0.703
Tokendata
Token ID7890
Feature activation+3.58e-03

Pos logit contributions
+0.149
 contro+0.108
edia+0.102
 prin+0.102
tie+0.101
Neg logit contributions
itars-0.198
 Axe-0.190
lees-0.188
iltr-0.188
 Ashes-0.186
Token _
Token ID4808
Feature activation+5.27e-01

Pos logit contributions
itars+0.013
iltr+0.012
lees+0.012
orks+0.012
 Axe+0.011
Neg logit contributions
-0.022
 contro-0.018
 prin-0.018
edia-0.017
 subdivision-0.017
Token full
Token ID1336
Feature activation+3.45e-01

Pos logit contributions
itars+2.415
lees+2.333
iltr+2.314
 Ashes+2.303
 Axe+2.303
Neg logit contributions
-2.688
 contro-2.010
 prin-1.915
 nomine-1.909
edia-1.899
Token v
Token ID410
Feature activation+4.79e-01

Pos logit contributions
itars+1.169
lees+1.103
 Axe+1.082
iltr+1.080
orks+1.065
Neg logit contributions
-2.219
 contro-1.787
 prin-1.746
 subdivision-1.715
edia-1.709
Token )
Token ID1267
Feature activation+1.01e+00

Pos logit contributions
itars+1.419
lees+1.310
 Axe+1.283
iltr+1.279
 Ashes+1.250
Neg logit contributions
-3.282
 contro-2.723
 prin-2.667
edia-2.616
 subdivision-2.611
Token {
Token ID1391
Feature activation+5.05e-01

Pos logit contributions
itars+2.870
lees+2.685
 Axe+2.631
iltr+2.588
orks+2.584
Neg logit contributions
-7.070
 contro-5.696
 prin-5.573
 nomine-5.552
 subdivision-5.518
Token v
Token ID410
Feature activation+3.27e-02

Pos logit contributions
itars+1.679
lees+1.582
 Axe+1.551
iltr+1.549
orks+1.527
Neg logit contributions
-3.269
 contro-2.636
 prin-2.577
 subdivision-2.532
edia-2.524
Token.
Token ID764
Feature activation-4.28e-01

Pos logit contributions
itars+0.143
lees+0.134
iltr+0.133
orks+0.130
 Ashes+0.130
Neg logit contributions
-0.176
 contro-0.141
 prin-0.136
tie-0.133
 subdivision-0.133
Token vertex
Token ID37423
Feature activation-1.11e-01

Pos logit contributions
+2.100
 contro+1.738
 prin+1.659
 subdivision+1.625
edia+1.519
Neg logit contributions
itars-2.035
lees-1.977
orks-1.907
iltr-1.906
 Ashes-1.898
Token.
Token ID764
Feature activation-5.36e-01

Pos logit contributions
+0.590
 contro+0.470
 prin+0.457
edia+0.445
 subdivision+0.445
Neg logit contributions
itars-0.490
lees-0.462
iltr-0.459
orks-0.450
 Ashes-0.445
Token a
Token ID257
Feature activation-1.13e-01

Pos logit contributions
+0.564
 contro+0.449
 prin+0.438
 subdivision+0.427
edia+0.423
Neg logit contributions
itars-0.395
lees-0.373
iltr-0.372
orks-0.367
ioxide-0.362
Token boot
Token ID6297
Feature activation-1.26e-01

Pos logit contributions
+0.582
 contro+0.456
 prin+0.440
 subdivision+0.429
tie+0.418
Neg logit contributions
itars-0.530
lees-0.505
iltr-0.502
orks-0.496
ioxide-0.491
Tokenc
Token ID66
Feature activation-8.13e-02

Pos logit contributions
+0.646
 contro+0.491
 prin+0.475
 subdivision+0.464
edia+0.461
Neg logit contributions
itars-0.586
lees-0.558
iltr-0.552
 Axe-0.551
orks-0.547
Tokenamped
Token ID13322
Feature activation+2.35e-02

Pos logit contributions
+0.479
 contro+0.394
ario+0.383
 prin+0.382
 subdivision+0.379
Neg logit contributions
itars-0.307
lees-0.285
 Ashes-0.278
iltr-0.274
ioxide-0.274
Token Na
Token ID11013
Feature activation+1.01e-01

Pos logit contributions
itars+0.100
lees+0.095
iltr+0.093
orks+0.092
ioxide+0.092
Neg logit contributions
-0.132
 contro-0.104
 prin-0.101
 subdivision-0.099
edia-0.097
Token`
Token ID63
Feature activation+9.82e-01

Pos logit contributions
itars+0.336
lees+0.316
iltr+0.309
 Axe+0.308
orks+0.306
Neg logit contributions
-0.654
 contro-0.529
 prin-0.518
 subdivision-0.508
edia-0.507
TokenVi
Token ID38432
Feature activation+4.04e-01

Pos logit contributions
itars+4.113
lees+3.914
iltr+3.884
 Axe+3.856
orks+3.822
Neg logit contributions
-5.509
 contro-4.246
 prin-4.163
 nomine-4.075
 subdivision-4.064
Token team
Token ID1074
Feature activation+3.82e-03

Pos logit contributions
itars+1.643
lees+1.565
iltr+1.539
 Axe+1.531
orks+1.523
Neg logit contributions
-2.325
 contro-1.826
 prin-1.776
 subdivision-1.740
edia-1.729
Token fresh
Token ID4713
Feature activation+1.29e-01

Pos logit contributions
itars+0.016
iltr+0.015
lees+0.015
orks+0.015
ioxide+0.015
Neg logit contributions
-0.021
 contro-0.017
 prin-0.016
 subdivision-0.016
edia-0.016
Token off
Token ID572
Feature activation+3.26e-02

Pos logit contributions
itars+0.509
lees+0.483
iltr+0.475
 Axe+0.475
orks+0.471
Neg logit contributions
-0.754
 contro-0.595
 prin-0.579
 subdivision-0.567
edia-0.565
Token of
Token ID286
Feature activation+7.24e-02

Pos logit contributions
itars+0.134
lees+0.128
iltr+0.126
 Axe+0.125
orks+0.124
Neg logit contributions
-0.186
 contro-0.146
 prin-0.142
 subdivision-0.139
edia-0.138
Token Sunderland
Token ID35706
Feature activation+2.71e-01

Pos logit contributions
itars+1.471
lees+1.389
 Axe+1.387
iltr+1.365
 Ashes+1.355
Neg logit contributions
-2.735
 contro-2.187
 prin-2.152
edia-2.104
 nomine-2.104
Token's
Token ID338
Feature activation+3.39e-01

Pos logit contributions
itars+1.093
lees+1.040
iltr+1.022
 Axe+1.020
orks+1.009
Neg logit contributions
-1.571
 contro-1.232
 prin-1.199
 subdivision-1.174
edia-1.168
Token manager
Token ID4706
Feature activation+3.52e-01

Pos logit contributions
itars+1.521
lees+1.455
iltr+1.433
 Axe+1.427
orks+1.417
Neg logit contributions
-1.811
 contro-1.392
 prin-1.347
 subdivision-1.319
edia-1.309
Token before
Token ID878
Feature activation+3.34e-01

Pos logit contributions
itars+1.232
lees+1.164
 Axe+1.152
iltr+1.141
 Ashes+1.131
Neg logit contributions
-2.204
 contro-1.759
 prin-1.726
 subdivision-1.690
edia-1.689
Token ext
Token ID1070
Feature activation+1.83e-01

Pos logit contributions
itars+1.545
lees+1.479
iltr+1.458
 Axe+1.453
orks+1.442
Neg logit contributions
-1.733
 contro-1.320
 prin-1.278
 subdivision-1.250
edia-1.241
Tokenoll
Token ID692
Feature activation+9.78e-01

Pos logit contributions
itars+0.710
lees+0.672
 Axe+0.662
iltr+0.658
 Ashes+0.654
Neg logit contributions
-1.073
 contro-0.851
 prin-0.825
edia-0.824
 subdivision-0.810
Tokening
Token ID278
Feature activation+5.85e-02

Pos logit contributions
itars+3.055
lees+2.888
 Axe+2.856
iltr+2.821
 Ashes+2.785
Neg logit contributions
-6.431
 contro-5.205
 prin-5.118
 nomine-5.033
edia-5.027
Token the
Token ID262
Feature activation+1.27e-01

Pos logit contributions
itars+0.235
lees+0.222
iltr+0.219
orks+0.216
 Axe+0.216
Neg logit contributions
-0.341
 contro-0.269
 prin-0.261
 subdivision-0.257
edia-0.254
Token Tex
Token ID3567
Feature activation+3.07e-01

Pos logit contributions
itars+0.584
lees+0.557
iltr+0.551
orks+0.544
 Axe+0.543
Neg logit contributions
-0.668
 contro-0.518
 prin-0.501
 subdivision-0.488
 nomine-0.479
Tokenan
Token ID272
Feature activation-8.21e-02

Pos logit contributions
itars+1.163
lees+1.105
 Axe+1.084
iltr+1.082
orks+1.068
Neg logit contributions
-1.848
 contro-1.463
 prin-1.426
edia-1.397
 subdivision-1.396
Token's
Token ID338
Feature activation+1.73e-02

Pos logit contributions
+0.469
 contro+0.368
 prin+0.359
 subdivision+0.350
 nomine+0.348
Neg logit contributions
itars-0.338
lees-0.322
iltr-0.317
orks-0.314
 Axe-0.313
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
itars+0.725
lees+0.687
iltr+0.677
 Axe+0.668
orks+0.667
Neg logit contributions
-1.001
 contro-0.775
 prin-0.758
 subdivision-0.742
edia-0.739
Token
Token ID198
Feature activation+1.56e-01

Pos logit contributions
itars+0.609
iltr+0.570
lees+0.568
orks+0.561
 Axe+0.558
Neg logit contributions
-0.801
 contro-0.629
 prin-0.607
tie-0.605
edia-0.602
TokenOcc
Token ID29223
Feature activation+1.04e-01

Pos logit contributions
itars+0.613
lees+0.577
iltr+0.572
 Axe+0.569
orks+0.561
Neg logit contributions
-0.924
 contro-0.720
 prin-0.702
tie-0.694
edia-0.692
Tokenasionally
Token ID31775
Feature activation-1.15e-01

Pos logit contributions
itars+0.355
lees+0.335
 Axe+0.331
iltr+0.327
 Ashes+0.325
Neg logit contributions
-0.659
 contro-0.529
 prin-0.518
edia-0.508
 subdivision-0.508
Token dismissed
Token ID11126
Feature activation-7.47e-02

Pos logit contributions
+0.692
 contro+0.559
 prin+0.542
 subdivision+0.534
edia+0.529
Neg logit contributions
itars-0.429
lees-0.401
iltr-0.399
orks-0.392
ioxide-0.389
Token as
Token ID355
Feature activation+9.55e-01

Pos logit contributions
+0.404
 contro+0.311
 prin+0.302
 subdivision+0.296
edia+0.292
Neg logit contributions
itars-0.329
lees-0.313
iltr-0.309
 Axe-0.309
orks-0.306
Token a
Token ID257
Feature activation+1.33e-01

Pos logit contributions
itars+3.968
 Axe+3.829
lees+3.810
 Ashes+3.778
iltr+3.720
Neg logit contributions
-5.292
 contro-4.016
 prin-3.931
 nomine-3.870
edia-3.852
Token one
Token ID530
Feature activation+2.21e-01

Pos logit contributions
itars+0.615
lees+0.590
iltr+0.580
 Axe+0.575
orks+0.574
Neg logit contributions
-0.687
 contro-0.528
 prin-0.509
 subdivision-0.500
 nomine-0.493
Token-
Token ID12
Feature activation-4.22e-01

Pos logit contributions
itars+0.612
lees+0.574
 Axe+0.567
iltr+0.566
orks+0.558
Neg logit contributions
-1.548
 contro-1.256
 prin-1.230
edia-1.219
 nomine-1.211
Tokendimensional
Token ID19577
Feature activation-1.30e-01

Pos logit contributions
+2.332
 contro+1.828
tie+1.784
 prin+1.781
 subdivision+1.754
Neg logit contributions
itars-1.790
lees-1.678
 Axe-1.645
iltr-1.637
 Ashes-1.635
Token film
Token ID2646
Feature activation-1.22e-01

Pos logit contributions
+0.679
 contro+0.530
 prin+0.512
 subdivision+0.506
 nomine+0.493
Neg logit contributions
itars-0.591
lees-0.564
iltr-0.551
ioxide-0.546
orks-0.545
Tokenmap
Token ID8899
Feature activation+1.46e-01

Pos logit contributions
itars+0.729
lees+0.694
iltr+0.678
 Ashes+0.676
 Axe+0.676
Neg logit contributions
-1.191
 contro-0.951
 prin-0.926
edia-0.922
tie-0.922
Token($
Token ID16763
Feature activation+4.11e-01

Pos logit contributions
itars+0.443
lees+0.415
 Axe+0.408
iltr+0.406
 Ashes+0.401
Neg logit contributions
-0.988
 contro-0.806
 prin-0.787
 subdivision-0.775
edia-0.773
TokenSR
Token ID12562
Feature activation+1.38e-01

Pos logit contributions
itars+1.554
lees+1.482
 Axe+1.467
iltr+1.453
orks+1.442
Neg logit contributions
-2.445
 contro-1.947
 prin-1.905
 nomine-1.871
 subdivision-1.867
Token.
Token ID13
Feature activation-5.79e-02

Pos logit contributions
itars+0.407
lees+0.378
 Axe+0.377
iltr+0.372
orks+0.368
Neg logit contributions
-0.931
 contro-0.772
 prin-0.750
 subdivision-0.742
 nomine-0.739
TokenWidth
Token ID30916
Feature activation+1.36e-01

Pos logit contributions
+0.305
 contro+0.230
 prin+0.224
edia+0.219
 subdivision+0.219
Neg logit contributions
itars-0.265
lees-0.253
iltr-0.250
 Axe-0.249
orks-0.247
Token,
Token ID11
Feature activation+9.34e-01

Pos logit contributions
itars+0.393
lees+0.367
iltr+0.358
 Axe+0.358
orks+0.352
Neg logit contributions
-0.941
 contro-0.770
 prin-0.754
 subdivision-0.742
edia-0.739
Token$
Token ID3
Feature activation+1.80e-01

Pos logit contributions
itars+3.613
 Axe+3.512
iltr+3.458
lees+3.455
orks+3.435
Neg logit contributions
-5.146
 contro-4.122
 prin-4.020
 citiz-3.966
 nomine-3.962
TokenSR
Token ID12562
Feature activation-5.55e-02

Pos logit contributions
itars+0.696
lees+0.666
 Axe+0.654
iltr+0.653
orks+0.647
Neg logit contributions
-1.061
 contro-0.843
 prin-0.827
 nomine-0.810
 subdivision-0.808
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
+0.314
 contro+0.240
tie+0.237
edia+0.232
 prin+0.231
Neg logit contributions
itars-0.234
iltr-0.220
lees-0.217
 Ashes-0.214
ioxide-0.212
TokenHeight
Token ID23106
Feature activation+1.94e-01

Pos logit contributions
+1.394
 contro+1.079
 prin+1.050
tie+1.046
 subdivision+1.045
Neg logit contributions
itars-0.915
lees-0.861
iltr-0.854
 Axe-0.843
orks-0.843
Token)
Token ID8
Feature activation+4.14e-01

Pos logit contributions
itars+0.513
lees+0.476
 Axe+0.463
iltr+0.463
orks+0.455
Neg logit contributions
-1.389
 contro-1.145
 prin-1.123
 subdivision-1.106
edia-1.101
Token.
Token ID13
Feature activation+5.63e-02

Pos logit contributions
+0.311
 contro+0.248
 prin+0.242
 subdivision+0.237
edia+0.236
Neg logit contributions
itars-0.204
lees-0.193
iltr-0.191
 Axe-0.189
orks-0.188
Token<|endoftext|>
Token ID50256
Feature activation-1.37e-01

Pos logit contributions
itars+0.224
lees+0.212
iltr+0.210
orks+0.207
ioxide+0.206
Neg logit contributions
-0.330
 contro-0.257
 prin-0.253
edia-0.247
 subdivision-0.247
TokenFrom
Token ID4863
Feature activation-5.66e-01

Pos logit contributions
+0.752
 contro+0.577
 prin+0.559
edia+0.553
tie+0.551
Neg logit contributions
itars-0.594
lees-0.564
 Axe-0.559
iltr-0.557
orks-0.551
Token the
Token ID262
Feature activation+3.08e-01

Pos logit contributions
+3.232
 contro+2.537
 prin+2.492
edia+2.478
 subdivision+2.428
Neg logit contributions
itars-2.276
lees-2.193
iltr-2.155
orks-2.126
ioxide-2.103
Token very
Token ID845
Feature activation+3.37e-01

Pos logit contributions
itars+1.425
lees+1.366
 Axe+1.354
iltr+1.342
 Ashes+1.339
Neg logit contributions
-1.590
 contro-1.201
 prin-1.166
 subdivision-1.136
 nomine-1.135
Token beginning
Token ID3726
Feature activation+9.33e-01

Pos logit contributions
itars+1.652
lees+1.588
 Axe+1.568
iltr+1.565
orks+1.551
Neg logit contributions
-1.652
 contro-1.229
 prin-1.189
 subdivision-1.159
edia-1.153
Token,
Token ID11
Feature activation+9.84e-02

Pos logit contributions
itars+2.909
 Axe+2.734
 Ashes+2.718
lees+2.660
 Karma+2.634
Neg logit contributions
-6.134
 contro-4.985
 prin-4.837
 nomine-4.773
tie-4.753
Token the
Token ID262
Feature activation+3.46e-02

Pos logit contributions
itars+0.391
lees+0.373
iltr+0.368
 Axe+0.364
orks+0.362
Neg logit contributions
-0.573
 contro-0.451
 prin-0.439
 subdivision-0.431
edia-0.429
Token Obama
Token ID2486
Feature activation-4.29e-02

Pos logit contributions
itars+0.154
lees+0.147
iltr+0.145
 Axe+0.143
orks+0.143
Neg logit contributions
-0.185
 contro-0.143
 prin-0.139
 subdivision-0.136
edia-0.135
Token administration
Token ID3662
Feature activation+1.06e-01

Pos logit contributions
+0.189
 contro+0.136
 prin+0.131
 subdivision+0.127
edia+0.126
Neg logit contributions
itars-0.232
lees-0.223
iltr-0.221
 Axe-0.220
orks-0.219
Token
Token ID447
Feature activation+1.97e-01

Pos logit contributions
itars+0.446
lees+0.424
iltr+0.418
orks+0.413
 Axe+0.413
Neg logit contributions
-0.594
 contro-0.468
 prin-0.452
 subdivision-0.442
edia-0.437
Token Sh
Token ID911
Feature activation+2.53e-01

Pos logit contributions
itars+0.136
iltr+0.128
orks+0.126
lees+0.125
ioxide+0.122
Neg logit contributions
-0.222
 contro-0.178
 prin-0.176
tie-0.173
 subdivision-0.173
Tokenand
Token ID392
Feature activation+1.58e-03

Pos logit contributions
itars+0.819
 Ashes+0.767
 Axe+0.758
iltr+0.750
lees+0.749
Neg logit contributions
-1.625
 contro-1.337
tie-1.320
edia-1.301
 prin-1.285
Tokenling
Token ID1359
Feature activation-3.25e-01

Pos logit contributions
itars+0.009
 Axe+0.009
 Ashes+0.009
iltr+0.009
 Karma+0.008
Neg logit contributions
-0.006
 contro-0.004
tie-0.004
edia-0.004
 prin-0.004
Token 1996
Token ID8235
Feature activation+3.52e-02

Pos logit contributions
+1.936
 contro+1.525
 prin+1.487
 subdivision+1.459
 nomine+1.452
Neg logit contributions
itars-1.257
lees-1.193
 Axe-1.174
iltr-1.171
orks-1.156
Token John
Token ID1757
Feature activation+2.82e-01

Pos logit contributions
itars+0.136
lees+0.130
iltr+0.128
 Axe+0.126
orks+0.126
Neg logit contributions
-0.208
 contro-0.165
 prin-0.161
 subdivision-0.157
edia-0.157
Token Lith
Token ID19730
Feature activation+9.29e-01

Pos logit contributions
itars+1.154
lees+1.116
 Axe+1.116
iltr+1.087
 Ashes+1.084
Neg logit contributions
-1.598
 contro-1.248
 prin-1.207
 subdivision-1.189
 nomine-1.187
Tokengow
Token ID21175
Feature activation+2.56e-01

Pos logit contributions
itars+3.598
lees+3.419
 Axe+3.363
iltr+3.342
 Ashes+3.299
Neg logit contributions
-5.543
 contro-4.338
 prin-4.231
 nomine-4.161
 subdivision-4.136
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
itars+0.909
lees+0.846
 Axe+0.839
iltr+0.828
 Ashes+0.825
Neg logit contributions
-1.613
 contro-1.284
 prin-1.254
 subdivision-1.233
 citiz-1.224
Token
Token ID198
Feature activation+2.49e-01

Pos logit contributions
itars+1.420
lees+1.339
iltr+1.330
 Axe+1.309
orks+1.308
Neg logit contributions
-1.980
 contro-1.561
 prin-1.510
edia-1.492
tie-1.490
Token1996
Token ID22288
Feature activation+3.38e-01

Pos logit contributions
itars+0.868
lees+0.828
iltr+0.805
 Axe+0.800
orks+0.789
Neg logit contributions
-1.561
 contro-1.253
 prin-1.228
 nomine-1.209
 subdivision-1.205
Token Kel
Token ID15150
Feature activation-1.07e-01

Pos logit contributions
itars+1.386
lees+1.321
 Axe+1.305
iltr+1.297
 Ashes+1.284
Neg logit contributions
-1.932
 contro-1.506
 prin-1.464
 subdivision-1.435
 nomine-1.430
Token the
Token ID262
Feature activation+1.52e-01

Pos logit contributions
itars+0.935
lees+0.889
iltr+0.874
 Axe+0.872
orks+0.864
Neg logit contributions
-1.374
 contro-1.080
 prin-1.051
 subdivision-1.031
edia-1.026
Token game
Token ID983
Feature activation+7.21e-03

Pos logit contributions
itars+0.713
lees+0.684
iltr+0.675
 Axe+0.669
orks+0.666
Neg logit contributions
-0.778
 contro-0.589
 prin-0.570
 subdivision-0.556
edia-0.550
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
itars+0.027
lees+0.026
iltr+0.025
 Axe+0.025
orks+0.025
Neg logit contributions
-0.044
 contro-0.035
 prin-0.034
 subdivision-0.033
edia-0.033
Token<|endoftext|>
Token ID50256
Feature activation-6.69e-02

Pos logit contributions
itars+0.054
lees+0.051
iltr+0.051
orks+0.050
ioxide+0.050
Neg logit contributions
-0.075
 contro-0.058
 prin-0.057
 subdivision-0.056
edia-0.056
TokenShare
Token ID11649
Feature activation+5.02e-02

Pos logit contributions
+0.368
 contro+0.282
 prin+0.274
edia+0.270
tie+0.269
Neg logit contributions
itars-0.289
lees-0.275
 Axe-0.272
iltr-0.271
orks-0.268
Token.
Token ID13
Feature activation+9.18e-01

Pos logit contributions
itars+0.185
lees+0.175
iltr+0.172
 Axe+0.170
orks+0.169
Neg logit contributions
-0.309
 contro-0.245
 prin-0.239
 subdivision-0.235
edia-0.234
Token Two
Token ID4930
Feature activation+2.15e-01

Pos logit contributions
itars+3.730
 Axe+3.652
 Ashes+3.624
lees+3.560
 Karma+3.554
Neg logit contributions
-5.121
 contro-4.038
 nomine-3.909
 prin-3.901
 citiz-3.881
Token iconic
Token ID14133
Feature activation-1.95e-02

Pos logit contributions
itars+0.944
lees+0.903
iltr+0.890
 Axe+0.888
orks+0.878
Neg logit contributions
-1.167
 contro-0.901
 prin-0.874
 subdivision-0.855
edia-0.849
Token horror
Token ID9961
Feature activation-1.43e-02

Pos logit contributions
+0.105
 contro+0.083
 prin+0.080
 subdivision+0.078
 nomine+0.077
Neg logit contributions
itars-0.085
lees-0.081
iltr-0.081
ioxide-0.079
orks-0.079
Token titles
Token ID8714
Feature activation-1.03e-01

Pos logit contributions
+0.078
 contro+0.061
 prin+0.059
 subdivision+0.058
tie+0.057
Neg logit contributions
itars-0.061
lees-0.059
iltr-0.058
ioxide-0.057
 Axe-0.057
Token are
Token ID389
Feature activation-1.19e-01

Pos logit contributions
+0.535
 contro+0.423
 prin+0.405
 subdivision+0.396
tie+0.393
Neg logit contributions
itars-0.462
lees-0.444
iltr-0.438
ioxide-0.433
orks-0.432
Token help
Token ID1037
Feature activation+1.95e-01

Pos logit contributions
itars+0.505
lees+0.481
 Axe+0.474
iltr+0.472
orks+0.469
Neg logit contributions
-0.684
 contro-0.543
 prin-0.524
 subdivision-0.514
edia-0.513
Token us
Token ID514
Feature activation-2.33e-02

Pos logit contributions
itars+0.613
lees+0.573
iltr+0.562
 Axe+0.562
orks+0.552
Neg logit contributions
-1.303
 contro-1.068
 prin-1.037
 subdivision-1.022
edia-1.021
Token continue
Token ID2555
Feature activation+3.43e-01

Pos logit contributions
+0.105
 contro+0.078
 prin+0.073
edia+0.071
 subdivision+0.071
Neg logit contributions
itars-0.124
lees-0.119
iltr-0.118
 Axe-0.118
orks-0.117
Token to
Token ID284
Feature activation+4.36e-02

Pos logit contributions
itars+1.564
lees+1.490
iltr+1.473
 Axe+1.466
orks+1.457
Neg logit contributions
-1.794
 contro-1.382
 prin-1.328
 subdivision-1.307
edia-1.305
Token write
Token ID3551
Feature activation+5.06e-01

Pos logit contributions
itars+0.205
lees+0.197
iltr+0.195
 Axe+0.193
 Ashes+0.191
Neg logit contributions
-0.220
 contro-0.173
 prin-0.163
edia-0.161
 subdivision-0.160
Token about
Token ID546
Feature activation+9.10e-01

Pos logit contributions
itars+2.293
lees+2.196
iltr+2.163
 Axe+2.162
orks+2.142
Neg logit contributions
-2.670
 contro-2.040
 prin-1.976
 subdivision-1.933
edia-1.925
Token the
Token ID262
Feature activation+6.06e-01

Pos logit contributions
itars+3.359
lees+3.196
 Axe+3.171
iltr+3.121
 Ashes+3.100
Neg logit contributions
-5.529
 contro-4.370
 prin-4.289
 nomine-4.278
 citiz-4.221
Token issues
Token ID2428
Feature activation+2.29e-01

Pos logit contributions
itars+1.907
lees+1.785
iltr+1.752
 Axe+1.751
orks+1.716
Neg logit contributions
-4.032
 contro-3.297
 prin-3.214
 subdivision-3.155
edia-3.145
Token that
Token ID326
Feature activation+2.23e-02

Pos logit contributions
itars+0.986
lees+0.937
iltr+0.922
orks+0.914
 Axe+0.913
Neg logit contributions
-1.268
 contro-0.995
 prin-0.958
 subdivision-0.941
edia-0.939
Token matter
Token ID2300
Feature activation+3.44e-01

Pos logit contributions
itars+0.100
lees+0.096
iltr+0.094
 Axe+0.094
orks+0.093
Neg logit contributions
-0.118
 contro-0.093
 prin-0.090
 subdivision-0.087
edia-0.086
Token.
Token ID13
Feature activation+1.65e-01

Pos logit contributions
itars+1.303
lees+1.228
iltr+1.209
 Axe+1.200
orks+1.196
Neg logit contributions
-2.077
 contro-1.650
 prin-1.602
 subdivision-1.578
edia-1.576
Token this
Token ID428
Feature activation+4.70e-01

Pos logit contributions
itars+0.809
lees+0.753
iltr+0.745
orks+0.724
 Axe+0.721
Neg logit contributions
-1.844
 contro-1.541
 prin-1.495
 subdivision-1.477
edia-1.462
Token comment
Token ID2912
Feature activation+1.07e-01

Pos logit contributions
itars+2.113
lees+2.020
iltr+1.991
 Axe+1.989
orks+1.971
Neg logit contributions
-2.497
 contro-1.919
 prin-1.859
 subdivision-1.822
edia-1.808
Token on
Token ID319
Feature activation+6.73e-01

Pos logit contributions
itars+0.431
lees+0.408
iltr+0.406
orks+0.399
 Axe+0.394
Neg logit contributions
-0.623
 contro-0.495
 prin-0.476
 subdivision-0.470
edia-0.469
Token Facebook
Token ID3203
Feature activation+3.65e-01

Pos logit contributions
itars+2.041
lees+1.921
iltr+1.874
orks+1.843
 Axe+1.841
Neg logit contributions
-4.577
 contro-3.742
 prin-3.670
 subdivision-3.604
edia-3.594
Token Share
Token ID8734
Feature activation+3.63e-01

Pos logit contributions
itars+1.550
lees+1.477
iltr+1.454
 Axe+1.441
orks+1.438
Neg logit contributions
-2.031
 contro-1.585
 prin-1.541
 subdivision-1.510
edia-1.503
Token this
Token ID428
Feature activation+9.06e-01

Pos logit contributions
itars+1.028
lees+0.956
iltr+0.937
 Axe+0.927
orks+0.919
Neg logit contributions
-2.531
 contro-2.096
 prin-2.046
 subdivision-2.016
edia-2.006
Token comment
Token ID2912
Feature activation+3.05e-01

Pos logit contributions
itars+3.802
lees+3.652
 Axe+3.612
iltr+3.588
 Ashes+3.552
Neg logit contributions
-5.057
 contro-3.836
 prin-3.759
 nomine-3.748
edia-3.672
Token on
Token ID319
Feature activation+8.27e-01

Pos logit contributions
itars+1.184
lees+1.122
iltr+1.108
 Axe+1.093
orks+1.092
Neg logit contributions
-1.813
 contro-1.443
 prin-1.396
 subdivision-1.377
edia-1.373
Token Twitter
Token ID3009
Feature activation+1.49e-01

Pos logit contributions
itars+1.541
lees+1.385
 Axe+1.341
iltr+1.327
orks+1.294
Neg logit contributions
-6.564
 contro-5.525
 prin-5.428
 subdivision-5.350
 nomine-5.349
Token
Token ID198
Feature activation+6.12e-01

Pos logit contributions
itars+0.541
lees+0.513
 Axe+0.511
iltr+0.502
 Ashes+0.501
Neg logit contributions
-0.919
 contro-0.730
 prin-0.709
 subdivision-0.701
 nomine-0.697
Token
Token ID198
Feature activation+5.33e-01

Pos logit contributions
itars+2.321
lees+2.207
 Axe+2.170
iltr+2.163
orks+2.138
Neg logit contributions
-3.681
 contro-2.910
 prin-2.839
 subdivision-2.783
 nomine-2.779
Token You
Token ID921
Feature activation-8.61e-02

Pos logit contributions
itars+0.037
lees+0.035
iltr+0.034
 Axe+0.034
orks+0.034
Neg logit contributions
-0.053
 contro-0.042
 prin-0.041
 subdivision-0.040
edia-0.040
Token are
Token ID389
Feature activation+1.11e-01

Pos logit contributions
+0.420
 contro+0.324
 prin+0.310
 subdivision+0.302
tie+0.297
Neg logit contributions
itars-0.420
lees-0.404
iltr-0.394
 Ashes-0.392
orks-0.391
Token more
Token ID517
Feature activation+1.17e-01

Pos logit contributions
itars+0.487
lees+0.463
iltr+0.456
 Axe+0.452
orks+0.451
Neg logit contributions
-0.600
 contro-0.470
 prin-0.454
 subdivision-0.444
edia-0.439
Token guilty
Token ID6717
Feature activation+2.01e-01

Pos logit contributions
itars+0.547
lees+0.519
iltr+0.513
 Axe+0.509
orks+0.506
Neg logit contributions
-0.606
 contro-0.473
 prin-0.452
 subdivision-0.441
edia-0.436
Token than
Token ID621
Feature activation+1.15e-01

Pos logit contributions
itars+0.766
lees+0.728
 Axe+0.715
iltr+0.714
orks+0.706
Neg logit contributions
-1.205
 contro-0.952
 prin-0.928
 subdivision-0.910
edia-0.908
Token innocent
Token ID10218
Feature activation+9.05e-01

Pos logit contributions
itars+0.459
lees+0.433
iltr+0.428
ioxide+0.423
orks+0.422
Neg logit contributions
-0.667
 contro-0.539
 prin-0.520
 subdivision-0.508
edia-0.505
Token.
Token ID13
Feature activation+1.12e-03

Pos logit contributions
itars+3.100
lees+2.957
 Axe+2.877
iltr+2.859
 Karma+2.852
Neg logit contributions
-5.688
 contro-4.475
 prin-4.400
edia-4.357
 nomine-4.344
Token
Token ID198
Feature activation+9.74e-02

Pos logit contributions
itars+0.005
lees+0.004
iltr+0.004
orks+0.004
ioxide+0.004
Neg logit contributions
-0.006
 contro-0.005
 prin-0.005
 subdivision-0.005
edia-0.005
Token
Token ID198
Feature activation+1.13e-01

Pos logit contributions
itars+0.418
iltr+0.392
lees+0.391
orks+0.386
 Axe+0.383
Neg logit contributions
-0.534
 contro-0.420
tie-0.405
 prin-0.405
edia-0.403
TokenIt
Token ID1026
Feature activation+3.03e-02

Pos logit contributions
itars+0.496
lees+0.469
iltr+0.466
 Axe+0.463
orks+0.460
Neg logit contributions
-0.616
 contro-0.469
 prin-0.456
tie-0.454
edia-0.450
Token comes
Token ID2058
Feature activation-2.36e-01

Pos logit contributions
itars+0.126
lees+0.120
iltr+0.118
 Axe+0.117
orks+0.117
Neg logit contributions
-0.171
 contro-0.135
 prin-0.131
 subdivision-0.128
edia-0.127
Tokenwww
Token ID2503
Feature activation-3.59e-01

Pos logit contributions
+1.491
 contro+1.085
tie+1.059
edia+1.011
ario+1.008
Neg logit contributions
itars-2.320
 Axe-2.237
 Ashes-2.225
 Karma-2.208
ioxide-2.200
Token.
Token ID13
Feature activation-2.98e-01

Pos logit contributions
+1.911
 contro+1.472
tie+1.445
edia+1.424
ario+1.400
Neg logit contributions
itars-1.588
iltr-1.488
lees-1.474
ioxide-1.452
 Axe-1.446
Tokenbel
Token ID6667
Feature activation-4.62e-01

Pos logit contributions
+1.626
tie+1.354
 contro+1.327
edia+1.326
iae+1.289
Neg logit contributions
itars-1.198
 Ashes-1.143
 Axe-1.127
 Karma-1.112
 turb-1.084
Tokenfast
Token ID7217
Feature activation-2.25e-01

Pos logit contributions
+2.370
 contro+1.856
edia+1.767
tie+1.765
ario+1.748
Neg logit contributions
itars-2.077
lees-1.997
 Ashes-1.989
 Axe-1.972
orks-1.955
Tokente
Token ID660
Feature activation-1.28e-02

Pos logit contributions
+1.048
 contro+0.793
tie+0.750
edia+0.745
 prin+0.736
Neg logit contributions
itars-1.160
lees-1.095
 Ashes-1.087
 Axe-1.081
iltr-1.078
Tokenlegraph
Token ID16606
Feature activation-1.33e+00

Pos logit contributions
+0.061
 contro+0.046
 prin+0.044
edia+0.043
tie+0.043
Neg logit contributions
itars-0.065
 Axe-0.060
lees-0.060
 Ashes-0.060
iltr-0.059
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
+5.809
tie+4.461
edia+4.327
ario+4.285
 contro+4.134
Neg logit contributions
itars-6.446
iltr-6.176
 turb-6.170
 Ashes-6.079
 Axe-6.062
Tokenco
Token ID1073
Feature activation-1.78e-01

Pos logit contributions
+0.816
 contro+0.644
 prin+0.618
tie+0.610
ario+0.608
Neg logit contributions
itars-0.745
 Ashes-0.703
 Axe-0.702
lees-0.694
ioxide-0.688
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
+0.985
 contro+0.769
edia+0.748
tie+0.743
ario+0.736
Neg logit contributions
itars-0.749
lees-0.702
iltr-0.701
 Axe-0.699
 Ashes-0.693
Tokenuk
Token ID2724
Feature activation-3.05e-01

Pos logit contributions
itars+0.553
 Axe+0.522
lees+0.519
 Ashes+0.516
ioxide+0.513
Neg logit contributions
-0.597
 contro-0.455
 prin-0.437
edia-0.432
tie-0.431
Token/
Token ID14
Feature activation-4.71e-01

Pos logit contributions
+1.411
 contro+1.003
edia+0.993
tie+0.985
ario+0.964
Neg logit contributions
itars-1.578
iltr-1.495
lees-1.481
orks-1.469
ioxide-1.465
Tokenwww
Token ID2503
Feature activation-2.02e-01

Pos logit contributions
+1.302
 contro+0.947
tie+0.918
 prin+0.891
ario+0.873
Neg logit contributions
itars-1.895
 Axe-1.830
 Ashes-1.809
ioxide-1.800
 Karma-1.790
Token.
Token ID13
Feature activation-1.42e-01

Pos logit contributions
+1.101
 contro+0.856
tie+0.836
edia+0.823
 prin+0.813
Neg logit contributions
itars-0.873
iltr-0.819
lees-0.808
ioxide-0.799
orks-0.793
Tokenbel
Token ID6667
Feature activation-4.21e-01

Pos logit contributions
+0.805
 contro+0.663
tie+0.660
edia+0.649
ario+0.637
Neg logit contributions
itars-0.554
 Ashes-0.523
 Axe-0.513
ioxide-0.504
 Karma-0.502
Tokenfast
Token ID7217
Feature activation-5.66e-01

Pos logit contributions
+1.995
 contro+1.581
tie+1.532
ario+1.498
edia+1.493
Neg logit contributions
itars-1.977
 Axe-1.949
 Ashes-1.930
 Karma-1.892
orks-1.874
Tokente
Token ID660
Feature activation-2.24e-01

Pos logit contributions
+2.356
tie+1.834
 contro+1.827
edia+1.765
ario+1.753
Neg logit contributions
itars-3.046
 Ashes-2.899
 Axe-2.898
 Karma-2.817
 Boots-2.785
Tokenlegraph
Token ID16606
Feature activation-1.29e+00

Pos logit contributions
+1.027
 contro+0.782
edia+0.753
tie+0.746
ario+0.735
Neg logit contributions
itars-1.143
 Axe-1.077
 Ashes-1.074
lees-1.070
iltr-1.051
Token.
Token ID13
Feature activation-2.85e-01

Pos logit contributions
+5.865
tie+4.513
edia+4.343
ario+4.330
 contro+4.231
Neg logit contributions
itars-6.153
iltr-5.895
 turb-5.810
 Ashes-5.718
ioxide-5.717
Tokenco
Token ID1073
Feature activation-9.16e-02

Pos logit contributions
+1.432
 contro+1.113
tie+1.089
ario+1.067
edia+1.065
Neg logit contributions
itars-1.332
 Ashes-1.263
iltr-1.243
 Axe-1.243
lees-1.226
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
+0.511
 contro+0.399
edia+0.387
tie+0.386
 prin+0.380
Neg logit contributions
itars-0.385
iltr-0.361
lees-0.360
 Axe-0.355
 Ashes-0.352
Tokenuk
Token ID2724
Feature activation-3.64e-01

Pos logit contributions
itars+0.936
 Axe+0.883
lees+0.883
 Ashes+0.875
iltr+0.874
Neg logit contributions
-1.053
 contro-0.800
 prin-0.769
edia-0.767
tie-0.759
Token/
Token ID14
Feature activation-3.95e-01

Pos logit contributions
+1.638
 contro+1.161
tie+1.154
edia+1.143
ario+1.126
Neg logit contributions
itars-1.916
iltr-1.816
lees-1.796
ioxide-1.790
orks-1.784
Token.
Token ID13
Feature activation-3.80e-02

Pos logit contributions
itars+0.071
lees+0.067
 Axe+0.066
iltr+0.066
orks+0.065
Neg logit contributions
-0.118
 contro-0.094
 prin-0.092
 subdivision-0.090
edia-0.090
Token
Token ID198
Feature activation+3.00e-02

Pos logit contributions
+0.226
 contro+0.178
 prin+0.174
 subdivision+0.170
edia+0.170
Neg logit contributions
itars-0.147
lees-0.139
iltr-0.137
 Axe-0.137
orks-0.136
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
itars+0.129
iltr+0.122
lees+0.121
orks+0.120
ioxide+0.119
Neg logit contributions
-0.164
 contro-0.128
tie-0.124
 prin-0.124
edia-0.123
TokenNewsletter
Token ID33031
Feature activation-3.51e-01

Pos logit contributions
itars+0.703
lees+0.667
iltr+0.664
 Axe+0.662
orks+0.657
Neg logit contributions
-0.800
 contro-0.604
 prin-0.587
edia-0.575
tie-0.573
Token Sign
Token ID5865
Feature activation-4.48e-01

Pos logit contributions
+1.916
 contro+1.525
 prin+1.473
edia+1.453
 subdivision+1.431
Neg logit contributions
itars-1.503
iltr-1.423
lees-1.411
ioxide-1.362
orks-1.359
Token Up
Token ID3205
Feature activation-1.16e+00

Pos logit contributions
+2.185
edia+1.589
 contro+1.578
 subdivision+1.553
 prin+1.545
Neg logit contributions
itars-2.152
iltr-2.064
ioxide-2.027
lees-2.009
 turb-1.995
Token Continue
Token ID10054
Feature activation-4.02e-01

Pos logit contributions
+4.538
 subdivision+3.092
 contro+3.054
 prin+3.037
edia+3.024
Neg logit contributions
itars-6.509
iltr-6.173
ioxide-6.156
orks-6.142
lash-6.040
Token reading
Token ID3555
Feature activation-3.78e-01

Pos logit contributions
+1.767
 contro+1.358
 subdivision+1.275
 prin+1.271
edia+1.259
Neg logit contributions
itars-2.117
iltr-2.040
lees-2.014
 Axe-1.996
orks-1.985
Token the
Token ID262
Feature activation+1.07e-02

Pos logit contributions
+1.915
 contro+1.530
 subdivision+1.456
 prin+1.444
tie+1.435
Neg logit contributions
itars-1.714
iltr-1.682
lees-1.640
orks-1.623
ioxide-1.617
Token main
Token ID1388
Feature activation+2.42e-01

Pos logit contributions
itars+0.049
lees+0.047
iltr+0.047
orks+0.047
ioxide+0.046
Neg logit contributions
-0.055
 contro-0.044
 prin-0.042
 subdivision-0.041
edia-0.040
Token story
Token ID1621
Feature activation-1.42e-01

Pos logit contributions
itars+1.059
lees+1.006
iltr+0.996
orks+0.992
 Axe+0.990
Neg logit contributions
-1.309
 contro-1.031
 prin-0.991
 subdivision-0.977
edia-0.964
Token March
Token ID2805
Feature activation-4.04e-01

Pos logit contributions
+2.187
 contro+1.714
 subdivision+1.639
 prin+1.625
edia+1.583
Neg logit contributions
itars-2.032
lees-1.965
iltr-1.938
 Axe-1.919
ioxide-1.918
Token 24
Token ID1987
Feature activation+8.09e-02

Pos logit contributions
+1.762
 contro+1.303
 subdivision+1.253
 prin+1.240
tie+1.225
Neg logit contributions
itars-2.165
iltr-2.058
lees-2.037
orks-2.032
ioxide-2.007
Token,
Token ID11
Feature activation-1.48e-01

Pos logit contributions
itars+0.269
iltr+0.249
lees+0.249
 Axe+0.243
orks+0.243
Neg logit contributions
-0.523
 contro-0.428
 prin-0.414
 subdivision-0.412
tie-0.410
Token 2016
Token ID1584
Feature activation+1.21e-01

Pos logit contributions
+0.869
 contro+0.697
 prin+0.669
 subdivision+0.669
tie+0.658
Neg logit contributions
itars-0.581
lees-0.548
iltr-0.543
orks-0.532
 Axe-0.530
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
itars+0.409
lees+0.387
 Axe+0.380
orks+0.376
iltr+0.375
Neg logit contributions
-0.774
 contro-0.621
 prin-0.610
 nomine-0.599
 subdivision-0.596
Token REUTERS
Token ID15862
Feature activation-1.13e+00

Pos logit contributions
+0.637
 contro+0.509
 prin+0.498
 subdivision+0.489
edia+0.487
Neg logit contributions
itars-0.359
lees-0.337
iltr-0.332
 Axe-0.330
orks-0.327
Token/
Token ID14
Feature activation-3.57e-01

Pos logit contributions
+4.746
 contro+3.375
tie+3.321
edia+3.242
ario+3.218
Neg logit contributions
itars-6.075
iltr-5.845
ioxide-5.788
lees-5.670
 Axe-5.653
TokenNick
Token ID23609
Feature activation-1.08e-01

Pos logit contributions
+2.003
 contro+1.543
 prin+1.496
tie+1.480
edia+1.480
Neg logit contributions
itars-1.495
lees-1.412
iltr-1.399
 Axe-1.392
 Ashes-1.388
Token Oxford
Token ID13643
Feature activation-1.34e-01

Pos logit contributions
+0.576
 contro+0.445
 prin+0.434
edia+0.428
tie+0.423
Neg logit contributions
itars-0.477
lees-0.454
iltr-0.450
 Ashes-0.439
 Axe-0.438
Token/
Token ID14
Feature activation-5.11e-02

Pos logit contributions
+0.774
 contro+0.607
 prin+0.588
 nomine+0.575
 subdivision+0.573
Neg logit contributions
itars-0.540
lees-0.525
 Axe-0.512
iltr-0.507
 Ashes-0.505
TokenFile
Token ID8979
Feature activation-2.08e-02

Pos logit contributions
+0.202
 contro+0.138
 prin+0.132
 subdivision+0.127
edia+0.126
Neg logit contributions
itars-0.300
lees-0.290
 Axe-0.287
iltr-0.287
orks-0.285
TokenIES
Token ID11015
Feature activation-5.32e-01

Pos logit contributions
+0.208
 contro+0.155
 prin+0.151
tie+0.148
edia+0.148
Neg logit contributions
itars-0.180
iltr-0.175
lees-0.172
orks-0.171
 Axe-0.170
Token
Token ID198
Feature activation-2.67e-01

Pos logit contributions
+3.194
 contro+2.502
 prin+2.446
 subdivision+2.396
edia+2.348
Neg logit contributions
itars-2.013
iltr-1.926
lees-1.923
orks-1.907
ioxide-1.898
Token
Token ID198
Feature activation-2.75e-01

Pos logit contributions
+1.372
 contro+1.067
tie+1.042
edia+1.026
ario+1.013
Neg logit contributions
itars-1.225
iltr-1.155
lees-1.136
orks-1.129
ioxide-1.121
TokenM
Token ID44
Feature activation-4.36e-02

Pos logit contributions
+1.527
 contro+1.161
 prin+1.127
tie+1.121
edia+1.119
Neg logit contributions
itars-1.170
lees-1.104
iltr-1.095
 Axe-1.095
orks-1.089
TokenOST
Token ID10892
Feature activation+1.02e-01

Pos logit contributions
+0.244
 contro+0.188
 prin+0.183
edia+0.181
 subdivision+0.179
Neg logit contributions
itars-0.183
lees-0.175
 Axe-0.173
iltr-0.171
 Ashes-0.171
Token READ
Token ID20832
Feature activation-1.13e+00

Pos logit contributions
itars+0.469
lees+0.445
iltr+0.441
 Axe+0.437
orks+0.436
Neg logit contributions
-0.536
 contro-0.414
 prin-0.399
 subdivision-0.388
edia-0.386
Token<|endoftext|>
Token ID50256
Feature activation-5.99e-02

Pos logit contributions
+5.534
 contro+4.029
 prin+3.831
+3.771
tie+3.767
Neg logit contributions
iltr-5.276
ioxide-5.167
itars-5.142
orks-5.058
lees-5.025
TokenK
Token ID42
Feature activation-1.34e-01

Pos logit contributions
+0.330
 contro+0.253
 prin+0.246
edia+0.242
 subdivision+0.241
Neg logit contributions
itars-0.258
lees-0.245
 Axe-0.242
iltr-0.242
orks-0.239
Tokenilled
Token ID2967
Feature activation+4.86e-02

Pos logit contributions
+0.767
 contro+0.597
 prin+0.582
edia+0.577
 subdivision+0.571
Neg logit contributions
itars-0.540
lees-0.510
 Axe-0.508
 Ashes-0.505
iltr-0.504
Token for
Token ID329
Feature activation+4.23e-01

Pos logit contributions
itars+0.215
lees+0.206
iltr+0.203
 Axe+0.203
orks+0.201
Neg logit contributions
-0.261
 contro-0.200
 prin-0.194
 subdivision-0.190
edia-0.189
Token watching
Token ID4964
Feature activation+2.05e-01

Pos logit contributions
itars+1.910
lees+1.830
iltr+1.801
 Axe+1.801
orks+1.782
Neg logit contributions
-2.235
 contro-1.707
 prin-1.656
 subdivision-1.619
edia-1.611
Token
Token ID251
Feature activation-1.70e-01

Pos logit contributions
+1.305
 contro+1.032
 prin+1.006
 subdivision+0.986
edia+0.983
Neg logit contributions
itars-0.831
lees-0.790
 Axe-0.776
iltr-0.775
orks-0.766
Token
Token ID198
Feature activation-8.14e-02

Pos logit contributions
+0.944
 contro+0.729
 prin+0.715
 subdivision+0.697
edia+0.695
Neg logit contributions
itars-0.717
lees-0.678
iltr-0.673
orks-0.665
 Axe-0.665
Token
Token ID198
Feature activation-7.60e-02

Pos logit contributions
+0.430
 contro+0.336
tie+0.327
edia+0.324
 prin+0.322
Neg logit contributions
itars-0.363
iltr-0.342
lees-0.336
orks-0.335
ioxide-0.333
TokenNewsletter
Token ID33031
Feature activation-2.80e-01

Pos logit contributions
+0.408
 contro+0.308
 prin+0.301
tie+0.298
edia+0.296
Neg logit contributions
itars-0.338
iltr-0.319
lees-0.318
 Axe-0.317
orks-0.315
Token Sign
Token ID5865
Feature activation-4.49e-01

Pos logit contributions
+1.551
 contro+1.238
 prin+1.195
edia+1.174
 subdivision+1.163
Neg logit contributions
itars-1.188
lees-1.117
iltr-1.116
ioxide-1.083
 Axe-1.069
Token Up
Token ID3205
Feature activation-1.10e+00

Pos logit contributions
+2.185
edia+1.589
 contro+1.583
 subdivision+1.562
 prin+1.557
Neg logit contributions
itars-2.149
iltr-2.054
ioxide-2.036
lees-2.015
 turb-1.985
Token Continue
Token ID10054
Feature activation-3.50e-01

Pos logit contributions
+4.350
 subdivision+3.007
 prin+2.973
 contro+2.955
edia+2.869
Neg logit contributions
itars-6.187
ioxide-5.875
orks-5.812
iltr-5.803
lash-5.800
Token reading
Token ID3555
Feature activation-3.70e-01

Pos logit contributions
+1.559
 contro+1.187
 subdivision+1.124
 prin+1.121
edia+1.108
Neg logit contributions
itars-1.834
iltr-1.767
lees-1.748
 Axe-1.733
orks-1.719
Token the
Token ID262
Feature activation-6.84e-03

Pos logit contributions
+1.883
 contro+1.501
 subdivision+1.433
 prin+1.422
tie+1.406
Neg logit contributions
itars-1.666
iltr-1.638
lees-1.601
orks-1.581
ioxide-1.577
Token main
Token ID1388
Feature activation+2.98e-01

Pos logit contributions
+0.035
 contro+0.028
 prin+0.026
 subdivision+0.026
edia+0.025
Neg logit contributions
itars-0.032
lees-0.031
iltr-0.030
orks-0.030
ioxide-0.030
Token story
Token ID1621
Feature activation-7.55e-02

Pos logit contributions
itars+1.287
lees+1.226
iltr+1.207
 Axe+1.206
orks+1.200
Neg logit contributions
-1.637
 contro-1.285
 prin-1.239
 subdivision-1.219
edia-1.207
Token)
Token ID8
Feature activation+8.22e-02

Pos logit contributions
itars+0.184
lees+0.170
iltr+0.165
 Axe+0.164
orks+0.161
Neg logit contributions
-0.610
 contro-0.513
 prin-0.503
edia-0.493
 subdivision-0.492
Token party
Token ID2151
Feature activation-5.98e-02

Pos logit contributions
itars+0.379
lees+0.362
 Axe+0.357
iltr+0.357
orks+0.353
Neg logit contributions
-0.427
 contro-0.327
 prin-0.316
 subdivision-0.310
edia-0.307
Token |
Token ID930
Feature activation-1.20e-01

Pos logit contributions
+0.315
 contro+0.245
 prin+0.236
 subdivision+0.232
edia+0.228
Neg logit contributions
itars-0.270
lees-0.257
iltr-0.254
 Axe-0.252
orks-0.252
Token AFP
Token ID8916
Feature activation-7.87e-01

Pos logit contributions
+0.669
 contro+0.519
 prin+0.506
 subdivision+0.492
edia+0.491
Neg logit contributions
itars-0.503
lees-0.482
iltr-0.472
 Axe-0.472
orks-0.469
Token/
Token ID14
Feature activation-8.06e-01

Pos logit contributions
+4.738
 contro+3.719
 prin+3.649
edia+3.537
 subdivision+3.533
Neg logit contributions
itars-2.979
lees-2.795
iltr-2.790
ioxide-2.782
 Axe-2.724
TokenGetty
Token ID6633
Feature activation-1.08e+00

Pos logit contributions
+2.133
 contro+1.089
 prin+1.038
tie+1.006
edia+0.945
Neg logit contributions
itars-5.705
lees-5.523
iltr-5.509
ioxide-5.499
 Axe-5.485
Token Opinion
Token ID29525
Feature activation-6.34e-01

Pos logit contributions
+6.106
 contro+4.787
 prin+4.629
edia+4.605
 subdivision+4.539
Neg logit contributions
itars-4.312
lees-4.021
iltr-4.013
ioxide-3.939
 Axe-3.864
Token It
Token ID632
Feature activation-4.73e-02

Pos logit contributions
+3.501
 contro+2.720
 prin+2.649
 subdivision+2.613
edia+2.591
Neg logit contributions
itars-2.641
lees-2.535
iltr-2.525
ioxide-2.487
orks-2.464
Token won
Token ID1839
Feature activation+2.99e-02

Pos logit contributions
+0.275
 contro+0.216
 prin+0.210
 subdivision+0.205
edia+0.205
Neg logit contributions
itars-0.189
lees-0.180
 Axe-0.177
iltr-0.177
 Ashes-0.175
Token
Token ID447
Feature activation+2.33e-01

Pos logit contributions
itars+0.128
lees+0.122
iltr+0.120
 Axe+0.120
orks+0.119
Neg logit contributions
-0.166
 contro-0.129
 prin-0.125
 subdivision-0.122
edia-0.122
Token
Token ID247
Feature activation-1.00e-01

Pos logit contributions
itars+1.197
lees+1.153
 Axe+1.138
iltr+1.137
orks+1.128
Neg logit contributions
-1.092
 contro-0.799
 prin-0.771
 subdivision-0.751
edia-0.746
Token https
Token ID3740
Feature activation-3.47e-01

Pos logit contributions
+1.368
 contro+1.071
 prin+1.044
 subdivision+1.027
edia+1.012
Neg logit contributions
itars-1.072
lees-1.014
iltr-1.006
orks-0.992
ioxide-0.988
Token://
Token ID1378
Feature activation-2.90e-01

Pos logit contributions
+1.300
 contro+0.875
edia+0.826
tie+0.817
 subdivision+0.808
Neg logit contributions
itars-2.092
lees-2.009
iltr-2.003
 Axe-1.990
orks-1.980
Tokendoi
Token ID34023
Feature activation-4.25e-01

Pos logit contributions
+1.536
 contro+1.188
 prin+1.153
edia+1.140
 subdivision+1.130
Neg logit contributions
itars-1.287
 Axe-1.231
iltr-1.220
lees-1.218
 Ashes-1.218
Token.
Token ID13
Feature activation-7.77e-01

Pos logit contributions
+2.284
 contro+1.756
tie+1.714
edia+1.705
ario+1.679
Neg logit contributions
itars-1.839
iltr-1.755
lees-1.740
 Ashes-1.710
 Axe-1.698
Tokenorg
Token ID2398
Feature activation-7.45e-01

Pos logit contributions
+3.003
 contro+2.265
edia+2.068
tie+2.027
 prin+2.016
Neg logit contributions
itars-4.375
 Ashes-4.257
 Axe-4.245
iltr-4.178
lash-4.176
Token/
Token ID14
Feature activation-1.08e+00

Pos logit contributions
+3.138
 contro+2.202
tie+2.118
edia+2.101
NL+2.043
Neg logit contributions
itars-4.084
iltr-3.919
lees-3.853
 Ashes-3.851
orks-3.800
Token10
Token ID940
Feature activation-7.54e-01

Pos logit contributions
+5.030
 contro+3.859
tie+3.755
edia+3.724
 prin+3.606
Neg logit contributions
itars-5.106
 Ashes-4.996
 Axe-4.986
orks-4.867
 Karma-4.793
Token.
Token ID13
Feature activation-4.85e-01

Pos logit contributions
+3.971
 contro+2.995
tie+2.962
edia+2.903
NL+2.873
Neg logit contributions
itars-3.350
lees-3.183
iltr-3.167
orks-3.124
 Axe-3.086
Token13
Token ID1485
Feature activation-2.94e-02

Pos logit contributions
+2.684
 contro+2.075
 prin+2.012
ario+1.973
edia+1.972
Neg logit contributions
itars-2.003
lees-1.923
 Axe-1.912
 Ashes-1.910
lash-1.872
Token71
Token ID4869
Feature activation-2.04e-01

Pos logit contributions
+0.185
 contro+0.151
 nomine+0.147
 prin+0.147
 subdivision+0.145
Neg logit contributions
itars-0.100
lees-0.094
 Axe-0.094
iltr-0.094
orks-0.092
Token/
Token ID14
Feature activation-2.62e-01

Pos logit contributions
+0.990
 contro+0.730
tie+0.690
edia+0.690
 prin+0.690
Neg logit contributions
itars-1.011
iltr-0.964
lees-0.962
orks-0.951
 Axe-0.947
Token.
Token ID13
Feature activation+4.00e-02

Pos logit contributions
+0.812
 contro+0.651
 prin+0.636
 subdivision+0.624
edia+0.621
Neg logit contributions
itars-0.456
lees-0.428
iltr-0.423
 Axe-0.422
orks-0.418
Token
Token ID198
Feature activation+6.63e-02

Pos logit contributions
itars+0.168
lees+0.159
iltr+0.157
orks+0.156
ioxide+0.155
Neg logit contributions
-0.226
 contro-0.174
 prin-0.171
 subdivision-0.167
edia-0.166
Token
Token ID198
Feature activation+5.52e-02

Pos logit contributions
itars+0.285
iltr+0.267
lees+0.267
orks+0.263
 Axe+0.261
Neg logit contributions
-0.363
 contro-0.285
tie-0.275
 prin-0.274
edia-0.273
TokenNewsletter
Token ID33031
Feature activation-3.98e-01

Pos logit contributions
itars+0.252
lees+0.239
iltr+0.237
 Axe+0.237
orks+0.236
Neg logit contributions
-0.290
 contro-0.218
 prin-0.212
tie-0.211
edia-0.208
Token Sign
Token ID5865
Feature activation-4.32e-01

Pos logit contributions
+2.112
 contro+1.707
 prin+1.643
edia+1.611
 subdivision+1.586
Neg logit contributions
itars-1.751
lees-1.659
iltr-1.647
orks-1.586
ioxide-1.584
Token Up
Token ID3205
Feature activation-1.07e+00

Pos logit contributions
+2.099
edia+1.537
 contro+1.536
 subdivision+1.502
 prin+1.492
Neg logit contributions
itars-2.088
iltr-1.989
ioxide-1.960
lees-1.956
 turb-1.926
Token Continue
Token ID10054
Feature activation-3.72e-01

Pos logit contributions
+4.163
 subdivision+2.827
 prin+2.798
 contro+2.773
tie+2.740
Neg logit contributions
itars-6.065
ioxide-5.785
orks-5.745
iltr-5.710
 turb-5.669
Token reading
Token ID3555
Feature activation-5.02e-01

Pos logit contributions
+1.674
 contro+1.269
 subdivision+1.198
 prin+1.194
edia+1.185
Neg logit contributions
itars-1.928
iltr-1.858
lees-1.842
 Axe-1.820
orks-1.809
Token the
Token ID262
Feature activation+2.55e-01

Pos logit contributions
+2.458
 contro+1.989
 subdivision+1.900
 prin+1.883
edia+1.866
Neg logit contributions
iltr-2.282
itars-2.267
lees-2.211
ioxide-2.185
orks-2.178
Token main
Token ID1388
Feature activation+2.33e-01

Pos logit contributions
itars+1.094
lees+1.049
iltr+1.034
 Axe+1.028
orks+1.021
Neg logit contributions
-1.407
 contro-1.092
 prin-1.059
 subdivision-1.041
edia-1.031
Token story
Token ID1621
Feature activation-2.07e-01

Pos logit contributions
itars+1.039
lees+0.984
iltr+0.983
orks+0.978
 Axe+0.970
Neg logit contributions
-1.239
 contro-0.977
 prin-0.937
 subdivision-0.926
tie-0.913
Tokenmail
Token ID4529
Feature activation-3.22e-01

Pos logit contributions
+1.317
 contro+1.090
tie+1.055
 prin+1.049
edia+1.044
Neg logit contributions
itars-0.551
iltr-0.508
ioxide-0.505
lees-0.494
orks-0.489
Token this
Token ID428
Feature activation+3.09e-01

Pos logit contributions
+1.979
 contro+1.680
 prin+1.639
 subdivision+1.602
edia+1.580
Neg logit contributions
itars-1.139
lees-1.059
iltr-1.053
ioxide-1.049
orks-1.045
Token to
Token ID284
Feature activation+5.74e-01

Pos logit contributions
itars+1.300
 Axe+1.226
lees+1.224
iltr+1.214
 Ashes+1.207
Neg logit contributions
-1.738
 contro-1.326
 prin-1.295
 nomine-1.276
edia-1.274
Token a
Token ID257
Feature activation-4.62e-02

Pos logit contributions
itars+2.093
 Axe+1.966
lees+1.965
 Karma+1.932
iltr+1.912
Neg logit contributions
-3.549
 contro-2.775
 prin-2.695
 nomine-2.665
 subdivision-2.658
Token friend
Token ID1545
Feature activation-3.84e-01

Pos logit contributions
+0.179
 contro+0.121
 prin+0.115
 subdivision+0.111
edia+0.110
Neg logit contributions
itars-0.274
lees-0.266
 Axe-0.263
iltr-0.263
orks-0.260
Token Print
Token ID12578
Feature activation-1.06e+00

Pos logit contributions
+1.670
 contro+1.224
 prin+1.190
 subdivision+1.128
edia+1.122
Neg logit contributions
itars-2.099
lees-2.011
iltr-1.971
orks-1.949
ioxide-1.946
Tokenable
Token ID540
Feature activation-4.84e-01

Pos logit contributions
+5.509
 contro+4.553
edia+4.423
tie+4.422
 prin+4.380
Neg logit contributions
itars-4.396
lees-4.318
ioxide-4.243
iltr-4.199
orks-4.146
Token version
Token ID2196
Feature activation-2.11e-01

Pos logit contributions
+2.214
 contro+1.729
 subdivision+1.677
 prin+1.637
edia+1.607
Neg logit contributions
itars-2.507
lees-2.455
iltr-2.399
ioxide-2.384
orks-2.340
Token<|endoftext|>
Token ID50256
Feature activation-1.08e-01

Pos logit contributions
+1.106
 contro+0.821
 prin+0.808
edia+0.785
 subdivision+0.776
Neg logit contributions
itars-0.981
lees-0.947
iltr-0.938
orks-0.905
ioxide-0.896
TokenA
Token ID32
Feature activation-8.74e-02

Pos logit contributions
+0.592
 contro+0.454
 prin+0.441
edia+0.436
tie+0.434
Neg logit contributions
itars-0.466
lees-0.443
 Axe-0.438
iltr-0.437
orks-0.432
Token university
Token ID6403
Feature activation-1.36e-01

Pos logit contributions
+0.450
 contro+0.344
 prin+0.333
 subdivision+0.327
edia+0.324
Neg logit contributions
itars-0.404
lees-0.390
iltr-0.383
 Axe-0.383
orks-0.379
Tokenmail
Token ID4529
Feature activation-3.44e-01

Pos logit contributions
+1.573
 contro+1.301
tie+1.259
 prin+1.253
edia+1.251
Neg logit contributions
itars-0.664
iltr-0.617
ioxide-0.609
lees-0.596
orks-0.592
Token this
Token ID428
Feature activation+2.96e-01

Pos logit contributions
+2.122
 contro+1.798
 prin+1.759
 subdivision+1.715
edia+1.702
Neg logit contributions
itars-1.214
lees-1.133
iltr-1.133
ioxide-1.116
orks-1.109
Token to
Token ID284
Feature activation+5.54e-01

Pos logit contributions
itars+1.259
lees+1.191
 Axe+1.186
iltr+1.179
 Ashes+1.168
Neg logit contributions
-1.652
 contro-1.263
 prin-1.232
 nomine-1.210
edia-1.209
Token a
Token ID257
Feature activation-2.20e-02

Pos logit contributions
itars+2.005
lees+1.886
 Axe+1.886
 Karma+1.854
iltr+1.828
Neg logit contributions
-3.448
 contro-2.691
 prin-2.611
 nomine-2.590
 subdivision-2.579
Token friend
Token ID1545
Feature activation-4.06e-01

Pos logit contributions
+0.087
 contro+0.059
 prin+0.056
edia+0.054
 subdivision+0.054
Neg logit contributions
itars-0.128
lees-0.125
 Axe-0.123
iltr-0.123
orks-0.122
Token Print
Token ID12578
Feature activation-1.04e+00

Pos logit contributions
+1.760
 contro+1.290
 prin+1.257
 subdivision+1.187
edia+1.182
Neg logit contributions
itars-2.224
lees-2.128
iltr-2.088
orks-2.066
ioxide-2.061
Tokenable
Token ID540
Feature activation-5.15e-01

Pos logit contributions
+5.400
 contro+4.438
edia+4.327
tie+4.309
 prin+4.273
Neg logit contributions
itars-4.300
lees-4.224
ioxide-4.173
iltr-4.116
orks-4.074
Token version
Token ID2196
Feature activation-1.99e-01

Pos logit contributions
+2.362
 contro+1.852
 subdivision+1.804
 prin+1.749
edia+1.739
Neg logit contributions
itars-2.647
lees-2.592
iltr-2.533
ioxide-2.497
orks-2.488
Token<|endoftext|>
Token ID50256
Feature activation-6.65e-02

Pos logit contributions
+1.052
 contro+0.785
 prin+0.772
edia+0.754
 subdivision+0.740
Neg logit contributions
itars-0.922
lees-0.887
iltr-0.882
orks-0.853
 Axe-0.847
TokenRob
Token ID14350
Feature activation+7.20e-02

Pos logit contributions
+0.365
 contro+0.281
 prin+0.272
edia+0.269
tie+0.267
Neg logit contributions
itars-0.287
lees-0.273
 Axe-0.270
iltr-0.269
orks-0.267
Token C
Token ID327
Feature activation-3.92e-01

Pos logit contributions
itars+0.295
lees+0.282
iltr+0.278
 Axe+0.276
orks+0.274
Neg logit contributions
-0.411
 contro-0.320
 prin-0.311
 subdivision-0.306
edia-0.306
Token |
Token ID930
Feature activation-9.36e-02

Pos logit contributions
+0.816
 contro+0.638
 prin+0.625
 subdivision+0.616
edia+0.611
Neg logit contributions
itars-0.533
lees-0.509
iltr-0.497
orks-0.491
 Axe-0.485
Token Select
Token ID9683
Feature activation-5.23e-01

Pos logit contributions
+0.517
 contro+0.399
 prin+0.391
 subdivision+0.383
edia+0.378
Neg logit contributions
itars-0.401
lees-0.384
iltr-0.376
 Axe-0.374
orks-0.373
Token Width
Token ID38807
Feature activation-5.39e-01

Pos logit contributions
+3.138
 contro+2.450
 prin+2.409
 subdivision+2.399
edia+2.362
Neg logit contributions
itars-1.989
lees-1.897
iltr-1.847
orks-1.824
ioxide-1.794
Token,
Token ID11
Feature activation+4.08e-01

Pos logit contributions
+3.521
 contro+2.820
 prin+2.774
 subdivision+2.754
tie+2.717
Neg logit contributions
itars-1.744
lees-1.665
iltr-1.610
orks-1.582
ioxide-1.581
TokenHeight
Token ID23106
Feature activation-8.79e-02

Pos logit contributions
itars+1.374
lees+1.286
 Axe+1.275
iltr+1.263
 Ashes+1.248
Neg logit contributions
-2.623
 contro-2.125
 prin-2.072
edia-2.023
 nomine-2.021
Token Write
Token ID19430
Feature activation-1.03e+00

Pos logit contributions
+0.556
 contro+0.444
 prin+0.436
 subdivision+0.429
edia+0.424
Neg logit contributions
itars-0.307
lees-0.293
iltr-0.285
orks-0.281
 Axe-0.281
Token-
Token ID12
Feature activation-6.79e-03

Pos logit contributions
+6.891
 contro+5.530
 prin+5.463
 subdivision+5.376
edia+5.351
Neg logit contributions
itars-3.194
lees-3.009
 Axe-2.897
orks-2.897
iltr-2.886
TokenVer
Token ID13414
Feature activation-1.35e-01

Pos logit contributions
+0.038
 contro+0.030
 prin+0.029
 subdivision+0.028
edia+0.028
Neg logit contributions
itars-0.028
lees-0.027
 Axe-0.026
iltr-0.026
orks-0.026
Tokenb
Token ID65
Feature activation-2.46e-03

Pos logit contributions
+0.908
 contro+0.727
 prin+0.722
 subdivision+0.715
tie+0.710
Neg logit contributions
itars-0.423
lees-0.418
orks-0.409
iltr-0.382
 Ashes-0.380
Tokenose
Token ID577
Feature activation-2.79e-02

Pos logit contributions
+0.011
 contro+0.008
 prin+0.008
 subdivision+0.008
edia+0.008
Neg logit contributions
itars-0.013
lees-0.012
iltr-0.012
ioxide-0.012
orks-0.012
Token -
Token ID532
Feature activation-1.94e-01

Pos logit contributions
+0.176
 contro+0.140
 prin+0.138
 subdivision+0.134
edia+0.133
Neg logit contributions
itars-0.099
lees-0.094
iltr-0.092
 Axe-0.091
orks-0.090
Token f
Token ID277
Feature activation+5.91e-02

Pos logit contributions
+1.352
 contro+1.052
 prin+1.019
edia+1.003
 subdivision+1.001
Neg logit contributions
itars-0.964
lees-0.916
iltr-0.905
 Axe-0.905
orks-0.892
Tokend
Token ID67
Feature activation+1.24e-01

Pos logit contributions
itars+0.247
lees+0.231
 Axe+0.229
iltr+0.229
 Ashes+0.227
Neg logit contributions
-0.331
 contro-0.261
 prin-0.253
edia-0.250
tie-0.249
Token |
Token ID930
Feature activation-5.48e-02

Pos logit contributions
itars+0.359
iltr+0.328
lees+0.327
orks+0.319
 Axe+0.314
Neg logit contributions
-0.862
 contro-0.712
 prin-0.701
 subdivision-0.687
tie-0.680
Token <
Token ID1279
Feature activation-1.36e-01

Pos logit contributions
+0.401
 contro+0.332
 prin+0.324
edia+0.321
 subdivision+0.319
Neg logit contributions
itars-0.137
lees-0.126
 Axe-0.124
iltr-0.123
 Ashes-0.121
Token--
Token ID438
Feature activation+5.67e-02

Pos logit contributions
+0.999
 contro+0.828
 prin+0.810
edia+0.797
 nomine+0.796
Neg logit contributions
itars-0.337
lees-0.313
 Axe-0.306
iltr-0.306
orks-0.300
Token Stack
Token ID23881
Feature activation-1.01e+00

Pos logit contributions
itars+0.182
lees+0.172
 Axe+0.170
iltr+0.169
 Ashes+0.167
Neg logit contributions
-0.373
 contro-0.301
 prin-0.295
 subdivision-0.289
edia-0.289
Token pointer
Token ID17562
Feature activation-3.41e-01

Pos logit contributions
+4.725
 contro+3.566
 prin+3.406
 subdivision+3.334
 nomine+3.253
Neg logit contributions
itars-5.155
lees-4.904
iltr-4.855
orks-4.777
 Axe-4.775
Token +
Token ID1343
Feature activation-1.34e-01

Pos logit contributions
+2.408
 contro+1.982
 prin+1.943
 subdivision+1.913
edia+1.903
Neg logit contributions
itars-0.932
lees-0.866
iltr-0.844
 Axe-0.843
orks-0.829
Token--------------------
Token ID19351
Feature activation-4.26e-01

Pos logit contributions
+0.579
 contro+0.411
 prin+0.391
tie+0.388
 subdivision+0.386
Neg logit contributions
itars-0.732
iltr-0.702
lees-0.698
orks-0.696
 Axe-0.695
Token--+
Token ID44785
Feature activation-1.98e-01

Pos logit contributions
+1.899
 contro+1.432
 subdivision+1.374
tie+1.368
ario+1.342
Neg logit contributions
itars-2.189
iltr-2.093
lees-2.070
orks-2.045
 Ashes-2.045
Token |
Token ID930
Feature activation-7.50e-02

Pos logit contributions
+1.281
 contro+1.059
 prin+1.045
 subdivision+1.024
tie+1.013
Neg logit contributions
itars-0.653
iltr-0.613
lees-0.596
orks-0.591
ioxide-0.578
Token.
Token ID13
Feature activation+1.54e-01

Pos logit contributions
itars+0.233
lees+0.221
 Axe+0.217
iltr+0.217
orks+0.214
Neg logit contributions
-0.377
 contro-0.300
 prin-0.292
 subdivision-0.287
edia-0.286
Token
Token ID198
Feature activation-1.75e-01

Pos logit contributions
itars+0.606
lees+0.576
iltr+0.567
 Axe+0.566
orks+0.560
Neg logit contributions
-0.906
 contro-0.712
 prin-0.695
 subdivision-0.681
edia-0.679
Token
Token ID198
Feature activation-5.02e-02

Pos logit contributions
+0.920
 contro+0.722
tie+0.699
edia+0.690
 prin+0.688
Neg logit contributions
itars-0.784
iltr-0.738
lees-0.727
orks-0.725
ioxide-0.717
TokenNewsletter
Token ID33031
Feature activation-3.59e-01

Pos logit contributions
+0.279
 contro+0.214
 prin+0.208
edia+0.206
tie+0.205
Neg logit contributions
itars-0.215
lees-0.202
iltr-0.201
 Axe-0.201
orks-0.199
Token Sign
Token ID5865
Feature activation-4.35e-01

Pos logit contributions
+1.938
 contro+1.560
 prin+1.496
 subdivision+1.463
edia+1.456
Neg logit contributions
itars-1.569
iltr-1.482
lees-1.482
ioxide-1.429
orks-1.428
Token Up
Token ID3205
Feature activation-1.00e+00

Pos logit contributions
+2.082
 contro+1.527
edia+1.518
 subdivision+1.509
 prin+1.478
Neg logit contributions
itars-2.120
iltr-2.020
lees-2.005
ioxide-1.992
 turb-1.955
Token Continue
Token ID10054
Feature activation-4.72e-01

Pos logit contributions
+3.912
 subdivision+2.728
 contro+2.685
 prin+2.653
edia+2.611
Neg logit contributions
itars-5.575
iltr-5.339
ioxide-5.292
orks-5.270
 turb-5.256
Token reading
Token ID3555
Feature activation-5.60e-01

Pos logit contributions
+2.049
 contro+1.563
 subdivision+1.478
 prin+1.455
edia+1.454
Neg logit contributions
itars-2.497
iltr-2.422
lees-2.392
 Axe-2.352
orks-2.348
Token the
Token ID262
Feature activation+1.73e-01

Pos logit contributions
+2.692
 contro+2.159
 subdivision+2.072
 prin+2.025
edia+2.017
Neg logit contributions
iltr-2.603
itars-2.581
lees-2.519
ioxide-2.481
orks-2.474
Token main
Token ID1388
Feature activation+1.95e-01

Pos logit contributions
itars+0.757
lees+0.729
iltr+0.720
 Axe+0.711
orks+0.711
Neg logit contributions
-0.941
 contro-0.733
 prin-0.707
 subdivision-0.698
edia-0.687
Token story
Token ID1621
Feature activation-3.17e-01

Pos logit contributions
itars+0.875
lees+0.827
iltr+0.826
orks+0.823
 Axe+0.814
Neg logit contributions
-1.034
 contro-0.817
 prin-0.781
 subdivision-0.774
tie-0.760
Token to
Token ID284
Feature activation-9.03e-02

Pos logit contributions
itars+0.553
lees+0.529
iltr+0.521
 Axe+0.518
orks+0.515
Neg logit contributions
-0.650
 contro-0.499
 prin-0.483
 subdivision-0.474
edia-0.471
Token Reuters
Token ID8428
Feature activation-5.47e-01

Pos logit contributions
+0.496
 contro+0.387
 prin+0.377
 subdivision+0.369
edia+0.366
Neg logit contributions
itars-0.388
lees-0.371
iltr-0.364
 Axe-0.360
orks-0.360
Token.
Token ID13
Feature activation-7.45e-02

Pos logit contributions
+3.259
 contro+2.579
 prin+2.500
 subdivision+2.473
edia+2.456
Neg logit contributions
itars-2.102
lees-1.984
 Axe-1.942
iltr-1.941
ioxide-1.919
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
+0.442
 contro+0.350
 prin+0.340
 subdivision+0.334
 nomine+0.333
Neg logit contributions
itars-0.288
lees-0.274
 Axe-0.270
iltr-0.269
orks-0.266
Token
Token ID198
Feature activation-3.25e-02

Pos logit contributions
+0.701
 contro+0.551
tie+0.532
edia+0.526
 prin+0.525
Neg logit contributions
itars-0.585
iltr-0.550
lees-0.545
orks-0.540
ioxide-0.537
TokenADVERTISEMENT
Token ID19053
Feature activation-9.81e-01

Pos logit contributions
+0.179
 contro+0.137
 prin+0.133
edia+0.131
tie+0.131
Neg logit contributions
itars-0.141
lees-0.134
 Axe-0.132
iltr-0.132
orks-0.131
Token
Token ID198
Feature activation+6.29e-02

Pos logit contributions
+5.511
 contro+4.225
edia+4.119
 prin+4.101
 subdivision+4.039
Neg logit contributions
itars-4.089
lees-3.893
iltr-3.840
 Axe-3.771
ioxide-3.763
Token
Token ID198
Feature activation+1.71e-02

Pos logit contributions
itars+0.268
iltr+0.252
lees+0.251
orks+0.247
ioxide+0.246
Neg logit contributions
-0.347
 contro-0.273
 prin-0.263
tie-0.262
edia-0.261
TokenTwenty
Token ID34096
Feature activation+1.89e-01

Pos logit contributions
itars+0.072
lees+0.069
 Axe+0.068
iltr+0.068
orks+0.067
Neg logit contributions
-0.096
 contro-0.074
 prin-0.072
edia-0.071
tie-0.071
Token-
Token ID12
Feature activation-2.76e-01

Pos logit contributions
itars+0.566
lees+0.531
 Axe+0.519
iltr+0.517
orks+0.511
Neg logit contributions
-1.291
 contro-1.050
 prin-1.030
 subdivision-1.014
edia-1.011
Tokenthree
Token ID15542
Feature activation-3.73e-01

Pos logit contributions
+1.416
 contro+1.086
 prin+1.045
tie+1.035
 subdivision+1.024
Neg logit contributions
itars-1.271
lees-1.207
 Axe-1.196
iltr-1.195
 Ashes-1.191
Token
Token ID198
Feature activation+3.23e-01

Pos logit contributions
itars+1.318
lees+1.240
iltr+1.233
 Axe+1.214
orks+1.213
Neg logit contributions
-1.812
 contro-1.428
 prin-1.381
edia-1.365
tie-1.365
TokenToday
Token ID8888
Feature activation-3.93e-02

Pos logit contributions
itars+1.230
lees+1.168
 Axe+1.148
iltr+1.147
orks+1.134
Neg logit contributions
-1.934
 contro-1.531
 prin-1.493
 subdivision-1.463
edia-1.457
Token w
Token ID266
Feature activation-1.01e-01

Pos logit contributions
+0.244
 contro+0.195
 prin+0.191
 subdivision+0.187
edia+0.186
Neg logit contributions
itars-0.142
lees-0.135
iltr-0.132
 Axe-0.131
orks-0.130
Token e
Token ID304
Feature activation+1.09e-01

Pos logit contributions
+0.560
 contro+0.439
 prin+0.426
edia+0.417
 subdivision+0.415
Neg logit contributions
itars-0.424
lees-0.403
 Axe-0.397
iltr-0.397
ioxide-0.393
Token can
Token ID460
Feature activation-3.43e-01

Pos logit contributions
itars+0.481
lees+0.458
iltr+0.452
 Axe+0.452
orks+0.447
Neg logit contributions
-0.589
 contro-0.454
 prin-0.441
 subdivision-0.431
edia-0.429
Token d
Token ID288
Feature activation-9.72e-01

Pos logit contributions
+1.782
 contro+1.387
 prin+1.348
 subdivision+1.298
edia+1.286
Neg logit contributions
itars-1.574
lees-1.483
iltr-1.477
 Axe-1.467
orks-1.461
Token raw
Token ID8246
Feature activation-5.59e-02

Pos logit contributions
+5.082
 contro+4.076
 prin+4.006
tie+3.842
 subdivision+3.777
Neg logit contributions
itars-4.161
iltr-3.875
lees-3.874
ioxide-3.842
lash-3.791
Token up
Token ID510
Feature activation-3.25e-01

Pos logit contributions
+0.310
 contro+0.244
 prin+0.239
 subdivision+0.231
tie+0.230
Neg logit contributions
itars-0.238
lees-0.223
iltr-0.222
 Axe-0.220
orks-0.219
Token the
Token ID262
Feature activation+1.39e-02

Pos logit contributions
+1.779
 contro+1.404
 prin+1.384
edia+1.330
 subdivision+1.327
Neg logit contributions
itars-1.394
lees-1.308
 Axe-1.289
iltr-1.288
orks-1.275
Token most
Token ID749
Feature activation-2.65e-02

Pos logit contributions
itars+0.061
lees+0.058
iltr+0.057
 Axe+0.057
orks+0.057
Neg logit contributions
-0.075
 contro-0.059
 prin-0.057
 subdivision-0.056
 nomine-0.055
Token g
Token ID308
Feature activation-2.73e-01

Pos logit contributions
+0.132
 contro+0.103
 prin+0.099
 subdivision+0.096
edia+0.095
Neg logit contributions
itars-0.127
lees-0.121
iltr-0.119
 Axe-0.118
orks-0.118
Token May
Token ID1737
Feature activation-3.28e-01

Pos logit contributions
+1.030
 contro+0.806
 prin+0.781
 subdivision+0.763
tie+0.759
Neg logit contributions
itars-0.813
lees-0.786
iltr-0.771
 Axe-0.762
ioxide-0.759
Token 28
Token ID2579
Feature activation+7.90e-02

Pos logit contributions
+1.421
 contro+1.050
 prin+1.006
 subdivision+0.999
tie+0.981
Neg logit contributions
itars-1.769
iltr-1.682
lees-1.666
orks-1.661
ioxide-1.641
Token,
Token ID11
Feature activation-1.38e-01

Pos logit contributions
itars+0.256
lees+0.240
iltr+0.238
 Axe+0.233
orks+0.231
Neg logit contributions
-0.518
 contro-0.425
 prin-0.413
 subdivision-0.408
edia-0.405
Token 2014
Token ID1946
Feature activation+1.30e-01

Pos logit contributions
+0.845
 contro+0.678
 prin+0.657
 subdivision+0.646
edia+0.640
Neg logit contributions
itars-0.506
lees-0.486
iltr-0.474
 Axe-0.469
orks-0.465
Token.
Token ID13
Feature activation+1.04e-01

Pos logit contributions
itars+0.508
lees+0.479
iltr+0.475
 Axe+0.467
orks+0.464
Neg logit contributions
-0.766
 contro-0.613
 prin-0.591
 subdivision-0.583
edia-0.579
Token REUTERS
Token ID15862
Feature activation-9.69e-01

Pos logit contributions
itars+0.349
lees+0.331
 Axe+0.326
iltr+0.323
orks+0.320
Neg logit contributions
-0.667
 contro-0.538
 prin-0.525
 nomine-0.517
 subdivision-0.517
Token/
Token ID14
Feature activation-2.24e-01

Pos logit contributions
+4.223
 contro+3.036
tie+2.922
edia+2.879
 prin+2.876
Neg logit contributions
itars-5.130
iltr-4.918
ioxide-4.862
lees-4.812
 Axe-4.750
TokenMichael
Token ID13256
Feature activation+2.24e-02

Pos logit contributions
+1.232
 contro+0.935
 prin+0.906
tie+0.897
edia+0.893
Neg logit contributions
itars-0.975
lees-0.930
iltr-0.920
 Axe-0.913
 Ashes-0.912
Token K
Token ID509
Feature activation-1.55e-01

Pos logit contributions
itars+0.088
iltr+0.084
lees+0.083
orks+0.082
ioxide+0.082
Neg logit contributions
-0.131
 contro-0.103
 prin-0.099
edia-0.099
ario-0.098
Tokenlim
Token ID2475
Feature activation+5.52e-02

Pos logit contributions
+0.934
 contro+0.740
 prin+0.721
edia+0.710
 subdivision+0.709
Neg logit contributions
itars-0.583
lees-0.553
 Axe-0.545
iltr-0.544
 Ashes-0.537
Tokenenty
Token ID3787
Feature activation-1.09e-01

Pos logit contributions
itars+0.118
 Axe+0.115
iltr+0.114
 Ashes+0.110
lees+0.108
Neg logit contributions
-0.407
edia-0.343
 contro-0.341
tie-0.339
 prin-0.338
Token or
Token ID393
Feature activation+1.87e-02

Pos logit contributions
itars+0.418
lees+0.399
iltr+0.394
 Axe+0.392
orks+0.388
Neg logit contributions
-0.557
 contro-0.433
 prin-0.420
 subdivision-0.412
edia-0.409
Token Share
Token ID8734
Feature activation-1.25e-01

Pos logit contributions
itars+0.084
lees+0.081
iltr+0.079
ioxide+0.079
 Axe+0.078
Neg logit contributions
-0.100
 contro-0.077
 prin-0.075
 subdivision-0.073
tie-0.072
Token this
Token ID428
Feature activation+1.92e-01

Pos logit contributions
+0.794
 contro+0.655
 subdivision+0.634
 prin+0.615
tie+0.611
Neg logit contributions
itars-0.430
iltr-0.415
lees-0.408
orks-0.391
 Ashes-0.390
Token story
Token ID1621
Feature activation-9.11e-03

Pos logit contributions
itars+0.873
lees+0.842
iltr+0.834
orks+0.825
ioxide+0.816
Neg logit contributions
-1.009
 contro-0.788
 subdivision-0.748
 prin-0.742
tie-0.724
Token:
Token ID25
Feature activation-2.51e-01

Pos logit contributions
+0.060
 contro+0.050
 prin+0.048
edia+0.047
 subdivision+0.047
Neg logit contributions
itars-0.029
lees-0.027
iltr-0.027
orks-0.027
 Axe-0.026
Token http
Token ID2638
Feature activation-9.58e-01

Pos logit contributions
+1.317
 contro+1.021
 prin+0.985
 subdivision+0.964
edia+0.947
Neg logit contributions
itars-1.136
lees-1.088
iltr-1.070
 Axe-1.063
orks-1.059
Token://
Token ID1378
Feature activation-6.10e-01

Pos logit contributions
+2.947
 contro+1.811
tie+1.795
ario+1.731
 subdivision+1.672
Neg logit contributions
itars-6.081
iltr-5.919
lees-5.858
 Axe-5.816
 Ashes-5.793
Tokenusat
Token ID37937
Feature activation-3.31e-01

Pos logit contributions
+2.666
 contro+1.915
 prin+1.842
tie+1.836
 subdivision+1.813
Neg logit contributions
itars-3.242
 Axe-3.101
lees-3.098
 Ashes-3.067
ioxide-3.030
Token.
Token ID13
Feature activation-5.84e-01

Pos logit contributions
+1.813
 contro+1.390
tie+1.378
edia+1.368
ario+1.344
Neg logit contributions
itars-1.419
lees-1.323
iltr-1.322
 Ashes-1.298
 Axe-1.294
Tokenly
Token ID306
Feature activation-2.96e-01

Pos logit contributions
+3.512
 contro+2.946
tie+2.863
 subdivision+2.812
 prin+2.783
Neg logit contributions
itars-2.035
iltr-1.882
 Axe-1.868
orks-1.866
 Ashes-1.861
Token/
Token ID14
Feature activation-3.83e-01

Pos logit contributions
+1.398
 contro+1.027
tie+0.992
 prin+0.973
edia+0.969
Neg logit contributions
itars-1.500
lees-1.428
iltr-1.422
orks-1.403
 Ashes-1.402
Token.
Token ID13
Feature activation-1.57e-01

Pos logit contributions
+1.694
 contro+1.335
 prin+1.288
 subdivision+1.261
 nomine+1.246
Neg logit contributions
itars-1.316
lees-1.250
ioxide-1.241
orks-1.234
 Axe-1.232
Token
Token ID198
Feature activation-9.56e-02

Pos logit contributions
+0.880
 contro+0.661
 prin+0.655
edia+0.643
tie+0.641
Neg logit contributions
itars-0.672
iltr-0.634
lees-0.634
ioxide-0.626
orks-0.625
Token
Token ID198
Feature activation-5.30e-02

Pos logit contributions
+0.509
 contro+0.399
tie+0.387
edia+0.382
 prin+0.382
Neg logit contributions
itars-0.424
iltr-0.398
lees-0.394
orks-0.391
ioxide-0.388
TokenOver
Token ID5886
Feature activation-2.55e-01

Pos logit contributions
+0.290
 contro+0.218
tie+0.215
 prin+0.212
edia+0.211
Neg logit contributions
itars-0.232
lees-0.219
iltr-0.218
 Axe-0.216
orks-0.216
Token and
Token ID290
Feature activation-3.21e-01

Pos logit contributions
+1.433
 contro+1.119
 prin+1.086
 subdivision+1.066
edia+1.059
Neg logit contributions
itars-1.057
lees-1.010
iltr-0.990
 Axe-0.987
orks-0.982
Token over
Token ID625
Feature activation-9.52e-01

Pos logit contributions
+1.674
 contro+1.274
 prin+1.224
 subdivision+1.204
 nomine+1.187
Neg logit contributions
itars-1.489
lees-1.417
iltr-1.405
ioxide-1.388
 Axe-1.388
Token,
Token ID11
Feature activation-1.16e-01

Pos logit contributions
+5.110
 contro+4.068
 prin+3.955
 subdivision+3.821
edia+3.757
Neg logit contributions
itars-3.839
lees-3.748
ioxide-3.728
iltr-3.712
orks-3.705
Token things
Token ID1243
Feature activation-9.50e-03

Pos logit contributions
+0.673
 contro+0.538
 prin+0.521
 subdivision+0.509
edia+0.505
Neg logit contributions
itars-0.462
lees-0.440
iltr-0.435
ioxide-0.433
orks-0.428
Token that
Token ID326
Feature activation-3.55e-01

Pos logit contributions
+0.047
 contro+0.036
 prin+0.034
 subdivision+0.033
tie+0.033
Neg logit contributions
itars-0.046
lees-0.045
iltr-0.044
 Axe-0.044
orks-0.044
Token were
Token ID547
Feature activation+1.21e-01

Pos logit contributions
+1.820
 contro+1.411
 prin+1.367
 subdivision+1.319
tie+1.315
Neg logit contributions
itars-1.633
lees-1.573
iltr-1.554
ioxide-1.541
orks-1.532
Token im
Token ID545
Feature activation+3.24e-02

Pos logit contributions
itars+0.562
lees+0.537
iltr+0.533
orks+0.524
ioxide+0.523
Neg logit contributions
-0.627
 contro-0.490
 prin-0.472
 subdivision-0.457
edia-0.451
Token Their
Token ID5334
Feature activation-2.58e-01

Pos logit contributions
+1.036
 contro+0.794
 prin+0.767
 subdivision+0.752
edia+0.749
Neg logit contributions
itars-0.938
lees-0.888
iltr-0.883
 Axe-0.872
ioxide-0.871
Token Employees
Token ID30260
Feature activation-4.81e-01

Pos logit contributions
+1.364
 contro+1.037
 prin+1.011
 subdivision+0.991
edia+0.989
Neg logit contributions
itars-1.171
iltr-1.099
lees-1.097
ioxide-1.093
orks-1.076
Token
Token ID198
Feature activation-2.05e-01

Pos logit contributions
+2.744
 contro+2.153
 prin+2.095
 subdivision+2.064
edia+2.047
Neg logit contributions
itars-1.959
ioxide-1.808
lees-1.806
iltr-1.803
orks-1.790
Token
Token ID198
Feature activation-7.04e-02

Pos logit contributions
+1.151
 contro+0.876
edia+0.852
 prin+0.851
tie+0.848
Neg logit contributions
itars-0.875
iltr-0.822
lees-0.818
orks-0.812
 Axe-0.804
TokenEmail
Token ID15333
Feature activation-2.49e-01

Pos logit contributions
+0.381
 contro+0.292
 prin+0.283
edia+0.278
 subdivision+0.277
Neg logit contributions
itars-0.311
lees-0.295
 Axe-0.292
iltr-0.291
orks-0.289
Token Print
Token ID12578
Feature activation-9.47e-01

Pos logit contributions
+1.554
 contro+1.257
 prin+1.221
 subdivision+1.200
 nomine+1.185
Neg logit contributions
itars-0.883
lees-0.837
iltr-0.835
ioxide-0.819
orks-0.816
Token Whats
Token ID28556
Feature activation-3.49e-01

Pos logit contributions
+5.248
 contro+4.054
 prin+3.920
edia+3.918
 subdivision+3.853
Neg logit contributions
itars-3.886
lees-3.753
ioxide-3.667
iltr-3.661
orks-3.612
Tokenapp
Token ID1324
Feature activation-2.41e-01

Pos logit contributions
+1.681
 contro+1.256
 prin+1.213
edia+1.190
 subdivision+1.175
Neg logit contributions
itars-1.726
lees-1.660
iltr-1.650
orks-1.640
 Axe-1.628
Token Menu
Token ID21860
Feature activation-3.08e-01

Pos logit contributions
+1.293
 contro+1.005
edia+1.003
 prin+0.982
ario+0.939
Neg logit contributions
itars-1.058
orks-1.013
ioxide-1.005
lees-1.003
iltr-0.980
Token Whats
Token ID28556
Feature activation-4.49e-01

Pos logit contributions
+1.750
 contro+1.361
 prin+1.326
edia+1.306
 subdivision+1.298
Neg logit contributions
itars-1.267
lees-1.217
iltr-1.185
ioxide-1.183
orks-1.182
Tokenapp
Token ID1324
Feature activation-1.88e-01

Pos logit contributions
+1.935
 contro+1.477
edia+1.425
 prin+1.379
ario+1.376
Neg logit contributions
itars-2.351
lees-2.283
iltr-2.279
orks-2.261
ioxide-2.227
Token very
Token ID845
Feature activation+1.54e-01

Pos logit contributions
itars+0.597
lees+0.576
iltr+0.565
 Axe+0.563
orks+0.562
Neg logit contributions
-0.613
 contro-0.474
 prin-0.455
 subdivision-0.446
edia-0.436
Token small
Token ID1402
Feature activation+3.09e-01

Pos logit contributions
itars+0.806
lees+0.778
iltr+0.765
 Axe+0.761
orks+0.760
Neg logit contributions
-0.706
 contro-0.526
 prin-0.502
 subdivision-0.490
edia-0.482
Token lens
Token ID10317
Feature activation+2.40e-01

Pos logit contributions
itars+1.378
lees+1.318
iltr+1.294
 Axe+1.290
orks+1.282
Neg logit contributions
-1.649
 contro-1.275
 prin-1.237
 subdivision-1.212
edia-1.199
Token.
Token ID13
Feature activation+6.43e-02

Pos logit contributions
itars+0.942
lees+0.889
iltr+0.871
 Axe+0.869
orks+0.862
Neg logit contributions
-1.415
 contro-1.125
 prin-1.095
 subdivision-1.077
edia-1.066
Token Image
Token ID7412
Feature activation+2.40e-01

Pos logit contributions
itars+0.252
lees+0.239
iltr+0.235
 Axe+0.233
orks+0.232
Neg logit contributions
-0.379
 contro-0.299
 prin-0.292
 subdivision-0.286
edia-0.285
Token via
Token ID2884
Feature activation+8.31e-01

Pos logit contributions
itars+1.091
lees+1.045
 Axe+1.030
iltr+1.029
orks+1.019
Neg logit contributions
-1.266
 contro-0.966
 prin-0.937
 subdivision-0.916
edia-0.911
Token Pan
Token ID5961
Feature activation+2.78e-01

Pos logit contributions
itars+3.222
 Axe+3.090
lees+3.050
 Ashes+3.021
orks+3.012
Neg logit contributions
-4.831
 contro-3.757
 prin-3.652
 nomine-3.602
 subdivision-3.591
Tokenor
Token ID273
Feature activation+2.88e-01

Pos logit contributions
itars+0.952
lees+0.901
iltr+0.882
 Axe+0.882
orks+0.868
Neg logit contributions
-1.770
 contro-1.422
 prin-1.390
 subdivision-1.365
edia-1.363
Tokenam
Token ID321
Feature activation+2.46e-01

Pos logit contributions
itars+1.114
lees+1.059
 Axe+1.043
iltr+1.040
orks+1.029
Neg logit contributions
-1.709
 contro-1.350
 prin-1.317
 subdivision-1.291
 nomine-1.285
Tokenio
Token ID952
Feature activation+9.31e-02

Pos logit contributions
itars+0.950
lees+0.901
 Axe+0.890
iltr+0.887
orks+0.881
Neg logit contributions
-1.455
 contro-1.149
 prin-1.119
 subdivision-1.095
 nomine-1.092
Token.
Token ID13
Feature activation+1.41e-01

Pos logit contributions
itars+0.357
lees+0.339
 Axe+0.333
iltr+0.333
orks+0.329
Neg logit contributions
-0.557
 contro-0.440
 prin-0.429
 subdivision-0.420
edia-0.419
Token_
Token ID62
Feature activation-8.79e-02

Pos logit contributions
+0.670
 contro+0.529
 prin+0.518
edia+0.506
 subdivision+0.505
Neg logit contributions
itars-0.421
lees-0.400
iltr-0.394
 Axe-0.392
orks-0.388
TokenCLASS
Token ID31631
Feature activation-6.16e-03

Pos logit contributions
+0.478
 contro+0.365
 prin+0.356
edia+0.348
 subdivision+0.347
Neg logit contributions
itars-0.386
lees-0.368
 Axe-0.364
iltr-0.364
orks-0.359
Token_
Token ID62
Feature activation-2.04e-01

Pos logit contributions
+0.035
 contro+0.028
 prin+0.027
 subdivision+0.027
edia+0.026
Neg logit contributions
itars-0.025
lees-0.024
iltr-0.023
 Axe-0.023
orks-0.023
TokenST
Token ID2257
Feature activation+4.10e-02

Pos logit contributions
+1.098
 contro+0.833
 prin+0.811
tie+0.795
 subdivision+0.794
Neg logit contributions
itars-0.913
lees-0.867
 Axe-0.857
iltr-0.856
orks-0.847
TokenART
Token ID7227
Feature activation+1.51e-01

Pos logit contributions
itars+0.195
lees+0.187
iltr+0.185
 Axe+0.184
 Ashes+0.182
Neg logit contributions
-0.207
 contro-0.156
 prin-0.151
 subdivision-0.148
edia-0.147
Token(
Token ID7
Feature activation+8.44e-01

Pos logit contributions
itars+0.594
lees+0.564
iltr+0.557
 Axe+0.554
orks+0.548
Neg logit contributions
-0.891
 contro-0.703
 prin-0.685
 subdivision-0.671
edia-0.667
Tokenmem
Token ID11883
Feature activation-1.50e-01

Pos logit contributions
itars+3.352
lees+3.196
 Axe+3.147
iltr+3.110
orks+3.097
Neg logit contributions
-4.812
 contro-3.768
 prin-3.639
 subdivision-3.583
 nomine-3.560
Tokenc
Token ID66
Feature activation-9.47e-02

Pos logit contributions
+0.766
 contro+0.579
 prin+0.560
edia+0.548
 subdivision+0.548
Neg logit contributions
itars-0.706
lees-0.677
iltr-0.667
 Axe-0.667
 Ashes-0.661
Tokenpy
Token ID9078
Feature activation-8.65e-02

Pos logit contributions
+0.576
 contro+0.472
 prin+0.460
tie+0.460
edia+0.454
Neg logit contributions
itars-0.331
 Ashes-0.317
 Axe-0.316
 Karma-0.312
iltr-0.310
Token_
Token ID62
Feature activation-5.75e-02

Pos logit contributions
+0.535
 contro+0.426
 prin+0.417
 subdivision+0.408
edia+0.407
Neg logit contributions
itars-0.314
lees-0.297
 Axe-0.292
iltr-0.291
orks-0.287
Tokenspeed
Token ID12287
Feature activation-1.60e-03

Pos logit contributions
+0.332
 contro+0.260
 prin+0.255
edia+0.249
 subdivision+0.249
Neg logit contributions
itars-0.231
lees-0.219
 Axe-0.217
iltr-0.216
 Ashes-0.214
Tokenmer
Token ID647
Feature activation+4.56e-02

Pos logit contributions
itars+0.764
 Axe+0.728
lees+0.728
 Ashes+0.720
iltr+0.718
Neg logit contributions
-0.968
 contro-0.761
tie-0.734
edia-0.733
 prin-0.732
Token
Token ID198
Feature activation+2.06e-01

Pos logit contributions
itars+0.192
iltr+0.182
lees+0.181
orks+0.178
 Axe+0.176
Neg logit contributions
-0.255
 contro-0.199
 prin-0.192
tie-0.191
edia-0.191
Token
Token ID198
Feature activation+2.57e-01

Pos logit contributions
itars+0.870
iltr+0.817
lees+0.815
orks+0.804
 Axe+0.798
Neg logit contributions
-1.143
 contro-0.900
 prin-0.866
tie-0.864
edia-0.860
Token2000
Token ID11024
Feature activation+4.39e-01

Pos logit contributions
itars+0.971
lees+0.903
iltr+0.903
 Axe+0.901
orks+0.887
Neg logit contributions
-1.573
 contro-1.239
 prin-1.203
tie-1.191
 subdivision-1.191
Token John
Token ID1757
Feature activation+1.99e-01

Pos logit contributions
itars+1.443
lees+1.359
 Axe+1.356
iltr+1.323
 Ashes+1.319
Neg logit contributions
-2.857
 contro-2.300
 prin-2.241
 nomine-2.209
 subdivision-2.209
Token Lith
Token ID19730
Feature activation+8.69e-01

Pos logit contributions
itars+0.629
lees+0.581
iltr+0.578
orks+0.577
ioxide+0.559
Neg logit contributions
-1.328
 contro-1.080
 prin-1.058
edia-1.042
 subdivision-1.038
Tokengow
Token ID21175
Feature activation-2.78e-02

Pos logit contributions
itars+3.401
lees+3.267
iltr+3.179
orks+3.146
 Axe+3.145
Neg logit contributions
-5.117
 contro-4.013
 prin-3.931
 nomine-3.913
 subdivision-3.849
Token
Token ID198
Feature activation+1.61e-01

Pos logit contributions
+0.156
 contro+0.122
 prin+0.118
edia+0.117
 subdivision+0.117
Neg logit contributions
itars-0.116
iltr-0.110
lees-0.110
orks-0.107
ioxide-0.107
Token
Token ID198
Feature activation+2.46e-01

Pos logit contributions
itars+0.688
iltr+0.646
lees+0.644
orks+0.635
 Axe+0.629
Neg logit contributions
-0.891
 contro-0.701
tie-0.675
 prin-0.674
edia-0.671
Token2000
Token ID11024
Feature activation+4.53e-01

Pos logit contributions
itars+0.934
iltr+0.868
lees+0.867
 Axe+0.866
orks+0.851
Neg logit contributions
-1.495
 contro-1.176
 prin-1.140
tie-1.134
edia-1.129
Token Eric
Token ID7651
Feature activation+1.41e-02

Pos logit contributions
itars+1.539
lees+1.455
 Axe+1.437
iltr+1.419
 Ashes+1.406
Neg logit contributions
-2.903
 contro-2.333
 prin-2.275
 subdivision-2.238
 nomine-2.233
Token)
Token ID8
Feature activation+1.72e-01

Pos logit contributions
itars+0.581
lees+0.552
 Axe+0.543
iltr+0.542
orks+0.535
Neg logit contributions
-0.930
 contro-0.737
 prin-0.718
 subdivision-0.704
edia-0.702
Token
Token ID784
Feature activation-2.73e-01

Pos logit contributions
itars+0.569
lees+0.527
 Axe+0.524
 Ashes+0.521
iltr+0.520
Neg logit contributions
-1.110
 contro-0.909
 prin-0.879
 nomine-0.866
edia-0.866
Token Pretty
Token ID20090
Feature activation-1.26e-01

Pos logit contributions
+1.579
 contro+1.234
 prin+1.216
 subdivision+1.185
edia+1.178
Neg logit contributions
itars-1.089
lees-1.043
iltr-1.037
orks-1.019
ioxide-1.005
Token safe
Token ID3338
Feature activation-4.39e-02

Pos logit contributions
+0.659
 contro+0.511
 prin+0.496
 subdivision+0.487
edia+0.473
Neg logit contributions
itars-0.569
lees-0.544
iltr-0.544
ioxide-0.531
orks-0.529
Token to
Token ID284
Feature activation+3.86e-01

Pos logit contributions
+0.234
 contro+0.180
 prin+0.175
 subdivision+0.171
edia+0.169
Neg logit contributions
itars-0.197
lees-0.188
iltr-0.186
 Axe-0.185
orks-0.184
Token say
Token ID910
Feature activation+8.30e-01

Pos logit contributions
itars+1.463
lees+1.387
iltr+1.363
 Axe+1.358
orks+1.345
Neg logit contributions
-2.332
 contro-1.857
 prin-1.809
 subdivision-1.774
edia-1.761
Token,
Token ID11
Feature activation+3.92e-01

Pos logit contributions
itars+2.964
 Axe+2.817
lees+2.812
 Ashes+2.771
 Karma+2.747
Neg logit contributions
-5.108
 contro-4.042
 prin-3.932
 nomine-3.894
edia-3.876
Token Red
Token ID2297
Feature activation-8.18e-02

Pos logit contributions
itars+1.487
lees+1.411
 Axe+1.391
iltr+1.383
orks+1.367
Neg logit contributions
-2.355
 contro-1.859
 prin-1.813
 subdivision-1.778
edia-1.774
Token Son
Token ID6295
Feature activation+8.20e-02

Pos logit contributions
+0.464
 contro+0.362
 prin+0.353
 subdivision+0.346
edia+0.344
Neg logit contributions
itars-0.337
lees-0.322
iltr-0.317
 Axe-0.314
orks-0.314
Tokenja
Token ID6592
Feature activation-2.99e-01

Pos logit contributions
itars+0.352
lees+0.346
iltr+0.337
orks+0.334
 Ashes+0.332
Neg logit contributions
-0.443
 contro-0.341
 prin-0.332
 subdivision-0.327
tie-0.327
Token is
Token ID318
Feature activation+4.60e-03

Pos logit contributions
+1.695
 contro+1.324
 prin+1.286
 subdivision+1.257
edia+1.245
Neg logit contributions
itars-1.231
lees-1.176
iltr-1.161
orks-1.151
 Axe-1.144
Token Sunderland
Token ID35706
Feature activation+2.71e-01

Pos logit contributions
itars+1.471
lees+1.389
 Axe+1.387
iltr+1.365
 Ashes+1.355
Neg logit contributions
-2.735
 contro-2.187
 prin-2.152
edia-2.104
 nomine-2.104
Token's
Token ID338
Feature activation+3.39e-01

Pos logit contributions
itars+1.093
lees+1.040
iltr+1.022
 Axe+1.020
orks+1.009
Neg logit contributions
-1.571
 contro-1.232
 prin-1.199
 subdivision-1.174
edia-1.168
Token manager
Token ID4706
Feature activation+3.52e-01

Pos logit contributions
itars+1.521
lees+1.455
iltr+1.433
 Axe+1.427
orks+1.417
Neg logit contributions
-1.811
 contro-1.392
 prin-1.347
 subdivision-1.319
edia-1.309
Token before
Token ID878
Feature activation+3.34e-01

Pos logit contributions
itars+1.232
lees+1.164
 Axe+1.152
iltr+1.141
 Ashes+1.131
Neg logit contributions
-2.204
 contro-1.759
 prin-1.726
 subdivision-1.690
edia-1.689
Token ext
Token ID1070
Feature activation+1.83e-01

Pos logit contributions
itars+1.545
lees+1.479
iltr+1.458
 Axe+1.453
orks+1.442
Neg logit contributions
-1.733
 contro-1.320
 prin-1.278
 subdivision-1.250
edia-1.241
Tokenoll
Token ID692
Feature activation+9.78e-01

Pos logit contributions
itars+0.710
lees+0.672
 Axe+0.662
iltr+0.658
 Ashes+0.654
Neg logit contributions
-1.073
 contro-0.851
 prin-0.825
edia-0.824
 subdivision-0.810
Tokening
Token ID278
Feature activation+5.85e-02

Pos logit contributions
itars+3.055
lees+2.888
 Axe+2.856
iltr+2.821
 Ashes+2.785
Neg logit contributions
-6.431
 contro-5.205
 prin-5.118
 nomine-5.033
edia-5.027
Token the
Token ID262
Feature activation+1.27e-01

Pos logit contributions
itars+0.235
lees+0.222
iltr+0.219
orks+0.216
 Axe+0.216
Neg logit contributions
-0.341
 contro-0.269
 prin-0.261
 subdivision-0.257
edia-0.254
Token Tex
Token ID3567
Feature activation+3.07e-01

Pos logit contributions
itars+0.584
lees+0.557
iltr+0.551
orks+0.544
 Axe+0.543
Neg logit contributions
-0.668
 contro-0.518
 prin-0.501
 subdivision-0.488
 nomine-0.479
Tokenan
Token ID272
Feature activation-8.21e-02

Pos logit contributions
itars+1.163
lees+1.105
 Axe+1.084
iltr+1.082
orks+1.068
Neg logit contributions
-1.848
 contro-1.463
 prin-1.426
edia-1.397
 subdivision-1.396
Token's
Token ID338
Feature activation+1.73e-02

Pos logit contributions
+0.469
 contro+0.368
 prin+0.359
 subdivision+0.350
 nomine+0.348
Neg logit contributions
itars-0.338
lees-0.322
iltr-0.317
orks-0.314
 Axe-0.313
Token had
Token ID550
Feature activation+5.80e-01

Pos logit contributions
itars+0.254
lees+0.242
iltr+0.239
orks+0.238
 Axe+0.236
Neg logit contributions
-0.285
 contro-0.219
 prin-0.212
 subdivision-0.206
 nomine-0.205
Token killed
Token ID2923
Feature activation+1.33e-01

Pos logit contributions
itars+2.702
lees+2.591
 Axe+2.568
iltr+2.554
 Ashes+2.531
Neg logit contributions
-2.985
 contro-2.238
 prin-2.172
 subdivision-2.126
edia-2.120
Token dozens
Token ID9264
Feature activation-1.01e-01

Pos logit contributions
itars+0.597
lees+0.571
iltr+0.565
orks+0.558
 Axe+0.557
Neg logit contributions
-0.703
 contro-0.543
 prin-0.529
 subdivision-0.516
edia-0.510
Token of
Token ID286
Feature activation-9.95e-02

Pos logit contributions
+0.616
 contro+0.489
 prin+0.477
 subdivision+0.468
edia+0.466
Neg logit contributions
itars-0.377
lees-0.358
 Axe-0.352
iltr-0.351
orks-0.347
Token heroes
Token ID10281
Feature activation+1.21e-01

Pos logit contributions
+0.497
 contro+0.381
 prin+0.371
 subdivision+0.360
 nomine+0.355
Neg logit contributions
itars-0.476
lees-0.455
iltr-0.451
ioxide-0.445
orks-0.443
Token,
Token ID11
Feature activation+1.35e-01

Pos logit contributions
itars+0.473
lees+0.447
iltr+0.443
 Axe+0.440
orks+0.438
Neg logit contributions
-0.709
 contro-0.563
 prin-0.548
 subdivision-0.536
edia-0.533
Token and
Token ID290
Feature activation+1.43e-01

Pos logit contributions
itars+0.590
lees+0.565
iltr+0.556
orks+0.553
 Axe+0.552
Neg logit contributions
-0.729
 contro-0.566
 prin-0.551
 subdivision-0.536
edia-0.531
Token won
Token ID1839
Feature activation+2.90e-01

Pos logit contributions
itars+0.622
lees+0.597
iltr+0.589
orks+0.583
ioxide+0.581
Neg logit contributions
-0.776
 contro-0.606
 prin-0.589
 subdivision-0.571
 nomine-0.566
Token in
Token ID287
Feature activation+3.61e-01

Pos logit contributions
itars+1.233
lees+1.175
iltr+1.161
 Axe+1.154
orks+1.147
Neg logit contributions
-1.614
 contro-1.256
 prin-1.222
 subdivision-1.194
edia-1.186
Token seconds
Token ID4201
Feature activation-1.87e-02

Pos logit contributions
itars+1.572
lees+1.501
iltr+1.481
 Axe+1.472
orks+1.468
Neg logit contributions
-1.966
 contro-1.524
 prin-1.485
 subdivision-1.448
 nomine-1.438
Token.
Token ID13
Feature activation+1.59e-01

Pos logit contributions
+0.109
 contro+0.087
 prin+0.084
 subdivision+0.083
edia+0.082
Neg logit contributions
itars-0.073
lees-0.070
iltr-0.069
 Axe-0.068
orks-0.068
Token,
Token ID11
Feature activation+1.58e-01

Pos logit contributions
+0.699
 contro+0.540
 prin+0.525
 subdivision+0.515
edia+0.510
Neg logit contributions
itars-0.575
lees-0.546
iltr-0.540
 Axe-0.537
orks-0.533
Token B
Token ID347
Feature activation-3.88e-02

Pos logit contributions
itars+0.671
lees+0.641
 Axe+0.632
iltr+0.630
orks+0.624
Neg logit contributions
-0.877
 contro-0.679
 prin-0.660
 subdivision-0.646
edia-0.644
Tokenhi
Token ID5303
Feature activation-1.23e-01

Pos logit contributions
+0.199
 contro+0.149
 prin+0.145
edia+0.144
 subdivision+0.142
Neg logit contributions
itars-0.181
lees-0.174
 Axe-0.172
iltr-0.171
 Ashes-0.170
Tokenw
Token ID86
Feature activation+1.38e-01

Pos logit contributions
+0.665
 contro+0.516
 prin+0.499
edia+0.495
tie+0.494
Neg logit contributions
itars-0.535
lees-0.507
iltr-0.503
 Axe-0.500
ioxide-0.497
Tokenani
Token ID3216
Feature activation-2.33e-02

Pos logit contributions
itars+0.763
lees+0.741
 Axe+0.734
iltr+0.727
 Ashes+0.725
Neg logit contributions
-0.581
 contro-0.414
 prin-0.399
edia-0.393
 subdivision-0.387
Token,
Token ID11
Feature activation+1.66e-01

Pos logit contributions
+0.155
 contro+0.126
 prin+0.123
 nomine+0.121
edia+0.121
Neg logit contributions
itars-0.073
lees-0.069
 Axe-0.068
iltr-0.067
orks-0.066
Token J
Token ID449
Feature activation+2.29e-02

Pos logit contributions
itars+0.643
lees+0.611
iltr+0.601
 Axe+0.600
orks+0.593
Neg logit contributions
-0.987
 contro-0.778
 prin-0.759
 subdivision-0.745
edia-0.741
Tokenh
Token ID71
Feature activation+8.76e-02

Pos logit contributions
itars+0.108
lees+0.104
 Axe+0.102
iltr+0.102
orks+0.101
Neg logit contributions
-0.116
 contro-0.087
 prin-0.084
 subdivision-0.082
edia-0.082
Tokenaj
Token ID1228
Feature activation+5.29e-02

Pos logit contributions
itars+0.407
lees+0.393
 Axe+0.389
 Ashes+0.386
iltr+0.384
Neg logit contributions
-0.446
 contro-0.336
 prin-0.324
edia-0.323
 subdivision-0.322
Tokenjar
Token ID9491
Feature activation+3.56e-02

Pos logit contributions
itars+0.224
 Axe+0.215
lees+0.215
 Ashes+0.213
iltr+0.211
Neg logit contributions
-0.286
 contro-0.223
 prin-0.219
 subdivision-0.216
tie-0.215
Token and
Token ID290
Feature activation+8.14e-02

Pos logit contributions
itars+0.115
lees+0.108
 Axe+0.106
iltr+0.106
orks+0.104
Neg logit contributions
-0.234
 contro-0.190
 prin-0.185
 nomine-0.182
 subdivision-0.181
Token approach
Token ID3164
Feature activation-6.72e-02

Pos logit contributions
+0.136
 contro+0.105
 prin+0.100
 subdivision+0.097
edia+0.095
Neg logit contributions
itars-0.151
lees-0.144
iltr-0.141
orks-0.140
 Axe-0.140
Token Lac
Token ID23115
Feature activation-2.10e-02

Pos logit contributions
+0.405
 contro+0.324
 prin+0.317
 subdivision+0.310
edia+0.308
Neg logit contributions
itars-0.253
lees-0.239
iltr-0.235
 Axe-0.234
orks-0.233
Tokenan
Token ID272
Feature activation+3.81e-01

Pos logit contributions
+0.135
 contro+0.110
 prin+0.108
 subdivision+0.106
edia+0.105
Neg logit contributions
itars-0.070
lees-0.065
 Axe-0.065
 Ashes-0.065
iltr-0.064
Token
Token ID447
Feature activation-2.00e-02

Pos logit contributions
itars+1.398
lees+1.334
iltr+1.303
 Axe+1.301
orks+1.275
Neg logit contributions
-2.329
 contro-1.843
 prin-1.788
 subdivision-1.766
 nomine-1.763
Token
Token ID247
Feature activation+1.06e-01

Pos logit contributions
+0.069
 contro+0.047
 prin+0.045
 subdivision+0.043
edia+0.042
Neg logit contributions
itars-0.125
lees-0.120
iltr-0.120
 Axe-0.119
orks-0.118
Tokens
Token ID82
Feature activation+1.43e-01

Pos logit contributions
itars+0.475
lees+0.455
iltr+0.447
 Axe+0.446
orks+0.442
Neg logit contributions
-0.566
 contro-0.430
 prin-0.416
 subdivision-0.409
 nomine-0.407
Token teaching
Token ID7743
Feature activation+5.37e-01

Pos logit contributions
itars+0.629
lees+0.598
iltr+0.591
 Axe+0.588
orks+0.586
Neg logit contributions
-0.775
 contro-0.601
 prin-0.586
 subdivision-0.572
edia-0.566
Token
Token ID784
Feature activation-1.75e-01

Pos logit contributions
itars+1.827
lees+1.734
 Axe+1.697
iltr+1.692
 Ashes+1.663
Neg logit contributions
-3.432
 contro-2.739
 prin-2.664
edia-2.628
 subdivision-2.623
Token either
Token ID2035
Feature activation-5.24e-01

Pos logit contributions
+0.929
 contro+0.722
 prin+0.702
 subdivision+0.683
 nomine+0.677
Neg logit contributions
itars-0.776
lees-0.744
orks-0.732
iltr-0.731
 Axe-0.730
Token you
Token ID345
Feature activation-5.23e-02

Pos logit contributions
+2.738
 contro+2.156
 prin+2.084
 subdivision+2.027
 nomine+2.002
Neg logit contributions
itars-2.346
lees-2.240
ioxide-2.221
orks-2.215
iltr-2.197
Token believe
Token ID1975
Feature activation+8.50e-03

Pos logit contributions
+0.272
 contro+0.214
 prin+0.206
 subdivision+0.199
tie+0.197
Neg logit contributions
itars-0.240
lees-0.228
ioxide-0.223
 Axe-0.222
orks-0.222
Token fine
Token ID3734
Feature activation-3.42e-02

Pos logit contributions
itars+0.659
lees+0.632
iltr+0.623
 Axe+0.620
orks+0.617
Neg logit contributions
-0.675
 contro-0.517
 prin-0.498
 subdivision-0.485
 nomine-0.478
Token,
Token ID11
Feature activation-1.81e-02

Pos logit contributions
+0.205
 contro+0.164
 prin+0.160
 subdivision+0.157
edia+0.156
Neg logit contributions
itars-0.129
lees-0.122
 Axe-0.120
iltr-0.120
orks-0.119
Token
Token ID447
Feature activation+3.18e-01

Pos logit contributions
+0.105
 contro+0.084
 prin+0.081
 subdivision+0.080
 nomine+0.079
Neg logit contributions
itars-0.072
lees-0.068
iltr-0.067
 Axe-0.067
orks-0.067
Token
Token ID251
Feature activation+1.92e-01

Pos logit contributions
itars+1.438
lees+1.378
 Axe+1.359
iltr+1.357
orks+1.345
Neg logit contributions
-1.678
 contro-1.273
 prin-1.231
 subdivision-1.207
edia-1.203
Token she
Token ID673
Feature activation+9.96e-02

Pos logit contributions
itars+0.709
lees+0.672
 Axe+0.660
iltr+0.660
orks+0.652
Neg logit contributions
-1.176
 contro-0.936
 prin-0.914
 subdivision-0.895
edia-0.893
Token told
Token ID1297
Feature activation+1.72e-01

Pos logit contributions
itars+0.332
lees+0.313
 Axe+0.307
iltr+0.307
orks+0.303
Neg logit contributions
-0.645
 contro-0.522
 prin-0.509
 subdivision-0.499
edia-0.496
Token reporters
Token ID7638
Feature activation+1.13e-01

Pos logit contributions
itars+0.832
lees+0.799
 Axe+0.788
iltr+0.788
orks+0.781
Neg logit contributions
-0.853
 contro-0.637
 prin-0.617
 subdivision-0.602
edia-0.599
Token.
Token ID13
Feature activation+2.46e-01

Pos logit contributions
itars+0.447
lees+0.424
 Axe+0.419
iltr+0.417
 Ashes+0.412
Neg logit contributions
-0.662
 contro-0.522
 prin-0.507
 subdivision-0.497
edia-0.494
Token
Token ID564
Feature activation+9.00e-02

Pos logit contributions
itars+0.914
lees+0.867
 Axe+0.852
iltr+0.850
orks+0.840
Neg logit contributions
-1.493
 contro-1.186
 prin-1.156
 subdivision-1.135
edia-1.131
Token
Token ID250
Feature activation+6.83e-02

Pos logit contributions
itars+0.355
lees+0.339
 Axe+0.334
iltr+0.332
orks+0.330
Neg logit contributions
-0.528
 contro-0.414
 prin-0.398
 subdivision-0.394
edia-0.393
TokenCertainly
Token ID36001
Feature activation-6.65e-02

Pos logit contributions
itars+0.254
lees+0.238
iltr+0.236
 Axe+0.235
orks+0.232
Neg logit contributions
-0.415
 contro-0.333
 prin-0.326
tie-0.317
 subdivision-0.317
Token adm
Token ID6178
Feature activation-1.33e-01

Pos logit contributions
+0.032
 contro+0.024
 prin+0.024
edia+0.023
 subdivision+0.023
Neg logit contributions
itars-0.032
lees-0.030
iltr-0.030
 Axe-0.029
orks-0.029
Tokeniring
Token ID3428
Feature activation-1.90e-01

Pos logit contributions
+0.744
 contro+0.588
 prin+0.568
edia+0.563
 subdivision+0.556
Neg logit contributions
itars-0.557
lees-0.530
 Axe-0.524
 Ashes-0.515
iltr-0.514
Token column
Token ID5721
Feature activation+1.50e-01

Pos logit contributions
+0.954
 contro+0.752
 prin+0.732
 subdivision+0.718
edia+0.700
Neg logit contributions
itars-0.901
lees-0.859
iltr-0.845
orks-0.839
ioxide-0.832
Token in
Token ID287
Feature activation+6.56e-02

Pos logit contributions
itars+0.676
lees+0.644
 Axe+0.634
iltr+0.631
orks+0.629
Neg logit contributions
-0.799
 contro-0.617
 prin-0.597
 subdivision-0.587
edia-0.581
Token The
Token ID383
Feature activation-6.83e-02

Pos logit contributions
itars+0.278
lees+0.266
iltr+0.260
orks+0.257
 Axe+0.257
Neg logit contributions
-0.366
 contro-0.285
 prin-0.278
 subdivision-0.272
edia-0.271
Token New
Token ID968
Feature activation+2.17e-01

Pos logit contributions
+0.327
 contro+0.239
 prin+0.234
 subdivision+0.228
edia+0.228
Neg logit contributions
itars-0.347
lees-0.330
iltr-0.326
orks-0.323
lash-0.319
Token York
Token ID1971
Feature activation+2.43e-01

Pos logit contributions
itars+0.832
lees+0.790
 Axe+0.776
iltr+0.776
orks+0.766
Neg logit contributions
-1.301
 contro-1.028
 prin-1.002
 subdivision-0.983
edia-0.980
Token Times
Token ID3782
Feature activation-4.12e-02

Pos logit contributions
itars+0.896
lees+0.849
iltr+0.831
 Axe+0.827
orks+0.817
Neg logit contributions
-1.492
 contro-1.190
 prin-1.162
 subdivision-1.139
edia-1.137
Token portrayed
Token ID19152
Feature activation+1.29e-01

Pos logit contributions
+0.231
 contro+0.182
 prin+0.176
 subdivision+0.174
edia+0.171
Neg logit contributions
itars-0.174
lees-0.166
iltr-0.162
ioxide-0.161
 Axe-0.160
Token him
Token ID683
Feature activation+2.10e-02

Pos logit contributions
itars+0.484
lees+0.461
iltr+0.453
 Axe+0.447
orks+0.445
Neg logit contributions
-0.780
 contro-0.622
 prin-0.606
 subdivision-0.595
edia-0.592
Token as
Token ID355
Feature activation+1.68e-01

Pos logit contributions
itars+0.088
lees+0.084
 Axe+0.083
iltr+0.083
orks+0.082
Neg logit contributions
-0.118
 contro-0.091
 prin-0.089
 subdivision-0.087
edia-0.087
Tokené
Token ID2634
Feature activation-4.26e-02

Pos logit contributions
+0.204
 contro+0.155
 prin+0.149
 subdivision+0.145
 nomine+0.144
Neg logit contributions
itars-0.219
lees-0.210
 Axe-0.208
 Ashes-0.206
iltr-0.206
Token des
Token ID748
Feature activation+2.07e-02

Pos logit contributions
+0.223
 contro+0.174
 prin+0.168
 subdivision+0.164
edia+0.163
Neg logit contributions
itars-0.195
lees-0.186
 Axe-0.183
iltr-0.182
orks-0.182
Token Cors
Token ID26978
Feature activation-2.18e-01

Pos logit contributions
itars+0.093
lees+0.088
iltr+0.087
 Axe+0.087
orks+0.086
Neg logit contributions
-0.109
 contro-0.086
 prin-0.083
 subdivision-0.080
 nomine-0.080
Tokenaires
Token ID17693
Feature activation-2.31e-01

Pos logit contributions
+1.218
 contro+0.950
 prin+0.927
 subdivision+0.903
edia+0.903
Neg logit contributions
itars-0.911
lees-0.868
iltr-0.859
 Axe-0.858
 Ashes-0.849
Token ay
Token ID38762
Feature activation+1.91e-01

Pos logit contributions
+1.245
 contro+0.993
 prin+0.962
 subdivision+0.932
 nomine+0.930
Neg logit contributions
itars-1.012
lees-0.960
iltr-0.946
orks-0.946
 Axe-0.944
Tokenant
Token ID415
Feature activation+1.00e-01

Pos logit contributions
itars+0.765
lees+0.722
 Axe+0.717
 Ashes+0.708
iltr+0.704
Neg logit contributions
-1.092
 contro-0.892
 prin-0.862
tie-0.844
edia-0.835
Token
Token ID39073
Feature activation-4.92e-02

Pos logit contributions
itars+0.470
lees+0.447
 Axe+0.442
iltr+0.440
orks+0.439
Neg logit contributions
-0.509
 contro-0.397
 prin-0.383
 nomine-0.369
 subdivision-0.369
Tokenc
Token ID66
Feature activation+2.84e-02

Pos logit contributions
+0.277
 contro+0.219
 prin+0.215
tie+0.211
 subdivision+0.210
Neg logit contributions
itars-0.202
 Ashes-0.190
 Axe-0.189
lees-0.188
orks-0.187
Tokenid
Token ID312
Feature activation-1.66e-01

Pos logit contributions
itars+0.134
 Ashes+0.129
 Axe+0.128
lees+0.127
 Karma+0.127
Neg logit contributions
-0.141
 contro-0.107
 prin-0.104
edia-0.103
tie-0.103
Tokenés
Token ID20954
Feature activation+1.66e-01

Pos logit contributions
+0.781
 contro+0.580
 prin+0.557
tie+0.545
edia+0.542
Neg logit contributions
itars-0.824
 Axe-0.800
 Ashes-0.794
lees-0.794
iltr-0.779
Token de
Token ID390
Feature activation+2.30e-01

Pos logit contributions
itars+0.750
lees+0.715
 Axe+0.705
iltr+0.705
orks+0.704
Neg logit contributions
-0.879
 contro-0.686
 prin-0.662
 subdivision-0.645
 nomine-0.639
Token maps
Token ID8739
Feature activation-4.82e-02

Pos logit contributions
itars+0.161
lees+0.153
iltr+0.152
ioxide+0.150
 Axe+0.149
Neg logit contributions
-0.196
 contro-0.155
 prin-0.149
edia-0.146
 subdivision-0.146
Token that
Token ID326
Feature activation+1.11e-01

Pos logit contributions
+0.286
 contro+0.229
 prin+0.223
 subdivision+0.219
edia+0.219
Neg logit contributions
itars-0.184
lees-0.174
iltr-0.173
 Axe-0.172
orks-0.170
Token show
Token ID905
Feature activation+3.40e-01

Pos logit contributions
itars+0.499
lees+0.479
iltr+0.471
 Axe+0.467
orks+0.466
Neg logit contributions
-0.582
 contro-0.450
 prin-0.436
 subdivision-0.426
edia-0.424
Token things
Token ID1243
Feature activation-2.09e-01

Pos logit contributions
itars+1.494
lees+1.427
iltr+1.407
 Axe+1.403
orks+1.390
Neg logit contributions
-1.839
 contro-1.419
 prin-1.378
 subdivision-1.348
edia-1.340
Token like
Token ID588
Feature activation+1.70e-03

Pos logit contributions
+1.131
 contro+0.920
 prin+0.888
 subdivision+0.870
tie+0.852
Neg logit contributions
itars-0.892
iltr-0.837
lees-0.836
orks-0.829
ioxide-0.823
Token most
Token ID749
Feature activation+9.25e-02

Pos logit contributions
itars+0.007
lees+0.007
iltr+0.007
orks+0.007
ioxide+0.007
Neg logit contributions
-0.009
 contro-0.007
 prin-0.007
 subdivision-0.007
edia-0.007
Token popular
Token ID2968
Feature activation-1.90e-01

Pos logit contributions
itars+0.415
lees+0.394
iltr+0.393
 Axe+0.387
orks+0.384
Neg logit contributions
-0.490
 contro-0.382
 prin-0.369
 subdivision-0.362
edia-0.358
Token film
Token ID2646
Feature activation-3.03e-01

Pos logit contributions
+1.009
 contro+0.804
 prin+0.779
 subdivision+0.768
edia+0.749
Neg logit contributions
itars-0.838
iltr-0.800
lees-0.782
ioxide-0.779
 Axe-0.769
Token or
Token ID393
Feature activation+5.37e-02

Pos logit contributions
+1.656
 contro+1.295
 prin+1.264
 subdivision+1.250
edia+1.241
Neg logit contributions
itars-1.292
iltr-1.229
lees-1.214
ioxide-1.203
 Axe-1.195
Token job
Token ID1693
Feature activation+5.19e-01

Pos logit contributions
itars+0.258
lees+0.248
iltr+0.247
 Axe+0.244
orks+0.243
Neg logit contributions
-0.267
 contro-0.202
 prin-0.194
 subdivision-0.192
edia-0.191
Token or
Token ID393
Feature activation-8.47e-03

Pos logit contributions
itars+2.230
lees+2.144
 Axe+2.109
iltr+2.094
orks+2.081
Neg logit contributions
-2.841
 contro-2.180
 prin-2.117
edia-2.070
 nomine-2.066
Token
Token ID198
Feature activation-1.27e-01

Pos logit contributions
+0.697
 contro+0.542
tie+0.522
edia+0.521
 prin+0.519
Neg logit contributions
itars-0.567
iltr-0.534
lees-0.532
orks-0.523
ioxide-0.518
TokenThe
Token ID464
Feature activation-7.39e-02

Pos logit contributions
+0.705
 contro+0.539
 prin+0.522
edia+0.516
tie+0.513
Neg logit contributions
itars-0.543
lees-0.517
iltr-0.512
 Axe-0.511
orks-0.506
Token FIR
Token ID23703
Feature activation+1.48e-01

Pos logit contributions
+0.364
 contro+0.278
 prin+0.267
 subdivision+0.261
edia+0.256
Neg logit contributions
itars-0.359
lees-0.345
iltr-0.340
orks-0.338
 Axe-0.337
Token further
Token ID2252
Feature activation+1.63e-01

Pos logit contributions
itars+0.677
lees+0.649
iltr+0.639
 Axe+0.638
orks+0.633
Neg logit contributions
-0.777
 contro-0.595
 prin-0.574
 subdivision-0.562
edia-0.557
Token quotes
Token ID13386
Feature activation+4.55e-03

Pos logit contributions
itars+0.716
lees+0.686
 Axe+0.675
iltr+0.673
orks+0.666
Neg logit contributions
-0.881
 contro-0.690
 prin-0.661
 subdivision-0.650
edia-0.642
Token the
Token ID262
Feature activation+1.01e-02

Pos logit contributions
itars+0.020
lees+0.019
iltr+0.019
 Axe+0.019
orks+0.019
Neg logit contributions
-0.025
 contro-0.019
 prin-0.018
 subdivision-0.018
edia-0.018
Token contents
Token ID10154
Feature activation+1.47e-01

Pos logit contributions
itars+0.049
lees+0.047
iltr+0.046
orks+0.046
 Axe+0.046
Neg logit contributions
-0.050
 contro-0.038
 prin-0.037
 subdivision-0.036
 nomine-0.035
Token of
Token ID286
Feature activation-3.30e-03

Pos logit contributions
itars+0.494
lees+0.452
 Axe+0.446
 Ashes+0.446
iltr+0.442
Neg logit contributions
-0.945
 contro-0.751
 prin-0.739
tie-0.730
 subdivision-0.730
Token the
Token ID262
Feature activation-4.72e-02

Pos logit contributions
+0.018
 contro+0.014
 prin+0.014
 subdivision+0.014
edia+0.014
Neg logit contributions
itars-0.014
lees-0.013
iltr-0.013
 Axe-0.013
orks-0.013
Token audio
Token ID6597
Feature activation+1.93e-01

Pos logit contributions
+0.239
 contro+0.182
 prin+0.176
 subdivision+0.172
edia+0.169
Neg logit contributions
itars-0.224
lees-0.217
iltr-0.213
orks-0.211
 Axe-0.210
Token clip
Token ID10651
Feature activation-3.02e-01

Pos logit contributions
itars+1.044
lees+1.008
iltr+0.995
 Axe+0.995
orks+0.987
Neg logit contributions
-0.845
 contro-0.606
 prin-0.582
 subdivision-0.565
edia-0.561
Token and
Token ID290
Feature activation+1.22e-01

Pos logit contributions
+0.766
 contro+0.608
 prin+0.591
 subdivision+0.579
 nomine+0.576
Neg logit contributions
itars-0.521
lees-0.495
iltr-0.489
 Axe-0.481
orks-0.481
Token seeing
Token ID4379
Feature activation+2.99e-01

Pos logit contributions
itars+0.635
lees+0.607
iltr+0.601
 Axe+0.599
orks+0.596
Neg logit contributions
-0.564
 contro-0.418
 prin-0.403
 subdivision-0.390
edia-0.386
Token what
Token ID644
Feature activation+1.11e-01

Pos logit contributions
itars+1.308
lees+1.250
iltr+1.231
 Axe+1.231
orks+1.218
Neg logit contributions
-1.621
 contro-1.248
 prin-1.213
 subdivision-1.186
edia-1.180
Token my
Token ID616
Feature activation+5.13e-02

Pos logit contributions
itars+0.435
lees+0.411
iltr+0.406
 Axe+0.400
orks+0.399
Neg logit contributions
-0.653
 contro-0.520
 prin-0.505
 subdivision-0.495
edia-0.491
Token inner
Token ID8434
Feature activation-4.00e-01

Pos logit contributions
itars+0.244
lees+0.233
iltr+0.230
orks+0.229
 Axe+0.229
Neg logit contributions
-0.259
 contro-0.197
 prin-0.191
 subdivision-0.187
 nomine-0.184
Token child
Token ID1200
Feature activation+7.86e-02

Pos logit contributions
+2.046
 contro+1.599
 prin+1.570
 subdivision+1.516
 nomine+1.487
Neg logit contributions
itars-1.879
lees-1.753
iltr-1.739
orks-1.736
ioxide-1.706
Token wants
Token ID3382
Feature activation-4.67e-01

Pos logit contributions
itars+0.332
lees+0.314
iltr+0.308
orks+0.306
 Axe+0.306
Neg logit contributions
-0.441
 contro-0.347
 prin-0.337
 subdivision-0.328
edia-0.327
Token."
Token ID526
Feature activation-1.23e-01

Pos logit contributions
+2.574
 contro+2.061
 prin+1.983
 subdivision+1.942
edia+1.929
Neg logit contributions
itars-1.951
lees-1.851
iltr-1.833
ioxide-1.826
orks-1.813
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
+0.730
 contro+0.575
 prin+0.561
 subdivision+0.550
edia+0.549
Neg logit contributions
itars-0.476
lees-0.452
iltr-0.445
 Axe-0.443
orks-0.439
Token
Token ID198
Feature activation+3.43e-02

Pos logit contributions
+0.535
 contro+0.421
tie+0.410
edia+0.403
 prin+0.402
Neg logit contributions
itars-0.461
iltr-0.433
lees-0.428
orks-0.424
ioxide-0.421
TokenX
Token ID55
Feature activation+1.19e-01

Pos logit contributions
itars+0.143
lees+0.135
iltr+0.134
 Axe+0.133
orks+0.133
Neg logit contributions
-0.195
 contro-0.150
 prin-0.145
tie-0.145
edia-0.144
Token Nav
Token ID13244
Feature activation-2.45e-01

Pos logit contributions
+1.141
 contro+0.892
 prin+0.858
 subdivision+0.847
 nomine+0.835
Neg logit contributions
itars-1.032
lees-1.006
 Axe-0.981
iltr-0.980
ioxide-0.968
Tokenigator
Token ID23823
Feature activation+1.37e-01

Pos logit contributions
+1.520
 contro+1.244
edia+1.243
ario+1.211
tie+1.205
Neg logit contributions
itars-0.826
lees-0.789
 Ashes-0.788
 Axe-0.767
orks-0.760
Token news
Token ID1705
Feature activation+2.24e-01

Pos logit contributions
itars+0.672
lees+0.646
iltr+0.636
 Axe+0.636
orks+0.629
Neg logit contributions
-0.670
 contro-0.502
 prin-0.486
 subdivision-0.474
edia-0.470
Token release
Token ID2650
Feature activation-7.98e-02

Pos logit contributions
itars+1.083
lees+1.040
 Axe+1.026
iltr+1.025
orks+1.015
Neg logit contributions
-1.112
 contro-0.833
 prin-0.806
 subdivision-0.789
edia-0.784
Token on
Token ID319
Feature activation+1.90e-01

Pos logit contributions
+0.432
 contro+0.339
 prin+0.327
 subdivision+0.322
edia+0.316
Neg logit contributions
itars-0.352
lees-0.336
iltr-0.330
ioxide-0.329
 Axe-0.327
Token March
Token ID2805
Feature activation-1.05e-01

Pos logit contributions
itars+0.769
lees+0.734
iltr+0.722
 Axe+0.717
orks+0.712
Neg logit contributions
-1.091
 contro-0.859
 prin-0.836
 subdivision-0.822
edia-0.815
Token 2
Token ID362
Feature activation+2.13e-01

Pos logit contributions
+0.450
 contro+0.328
 prin+0.312
 subdivision+0.309
edia+0.301
Neg logit contributions
itars-0.576
iltr-0.549
lees-0.548
orks-0.541
ioxide-0.538
Token,
Token ID11
Feature activation-1.29e-01

Pos logit contributions
itars+0.765
lees+0.723
iltr+0.710
 Axe+0.709
orks+0.701
Neg logit contributions
-1.328
 contro-1.066
 prin-1.036
 subdivision-1.021
edia-1.015
Token 2012
Token ID2321
Feature activation+7.11e-02

Pos logit contributions
+0.828
 contro+0.678
 prin+0.656
 subdivision+0.650
edia+0.643
Neg logit contributions
itars-0.433
lees-0.410
iltr-0.403
 Axe-0.397
orks-0.395
Token,
Token ID11
Feature activation+1.33e-03

Pos logit contributions
itars+0.263
lees+0.248
iltr+0.245
 Axe+0.243
orks+0.242
Neg logit contributions
-0.435
 contro-0.351
 prin-0.340
 subdivision-0.335
edia-0.332
Token said
Token ID531
Feature activation+5.70e-02

Pos logit contributions
itars+0.006
lees+0.006
iltr+0.005
orks+0.005
 Axe+0.005
Neg logit contributions
-0.007
 contro-0.006
 prin-0.005
 subdivision-0.005
edia-0.005
Token H
Token ID367
Feature activation-3.61e-01

Pos logit contributions
+0.707
 contro+0.553
 prin+0.536
 subdivision+0.531
edia+0.524
Neg logit contributions
itars-0.521
lees-0.493
iltr-0.487
orks-0.486
ioxide-0.482
Tokent
Token ID83
Feature activation-3.70e-01

Pos logit contributions
+1.960
 contro+1.487
 prin+1.466
 subdivision+1.429
tie+1.423
Neg logit contributions
itars-1.564
lees-1.495
ioxide-1.465
orks-1.465
lash-1.452
Token/
Token ID14
Feature activation-1.78e-01

Pos logit contributions
+2.385
 contro+1.920
 prin+1.885
 subdivision+1.861
edia+1.838
Neg logit contributions
itars-1.215
lees-1.156
orks-1.150
ioxide-1.132
iltr-1.122
TokenW
Token ID54
Feature activation-1.82e-01

Pos logit contributions
+1.077
 contro+0.854
 prin+0.831
tie+0.828
 subdivision+0.818
Neg logit contributions
itars-0.662
 Ashes-0.617
lees-0.614
ioxide-0.610
lash-0.609
Tokent
Token ID83
Feature activation-1.88e-01

Pos logit contributions
+0.965
 contro+0.746
 prin+0.737
tie+0.724
edia+0.719
Neg logit contributions
itars-0.790
lees-0.759
ioxide-0.758
iltr-0.754
orks-0.753
Token Comp
Token ID3082
Feature activation-6.26e-01

Pos logit contributions
+1.134
 contro+0.897
 prin+0.882
 subdivision+0.867
tie+0.864
Neg logit contributions
itars-0.715
lees-0.676
orks-0.669
iltr-0.667
ioxide-0.648
Token.
Token ID13
Feature activation-2.10e-01

Pos logit contributions
+3.215
 contro+2.474
 prin+2.415
 subdivision+2.363
edia+2.353
Neg logit contributions
itars-2.863
lees-2.679
orks-2.669
ioxide-2.648
 Ashes-2.597
Token Rating
Token ID12028
Feature activation-4.62e-01

Pos logit contributions
+1.204
 contro+0.959
 prin+0.935
 subdivision+0.925
tie+0.913
Neg logit contributions
itars-0.835
lees-0.793
orks-0.789
iltr-0.784
ioxide-0.762
Token 247
Token ID30179
Feature activation-3.94e-02

Pos logit contributions
+2.585
 contro+2.047
 prin+1.976
 subdivision+1.957
tie+1.920
Neg logit contributions
itars-1.936
iltr-1.809
orks-1.801
lees-1.792
ioxide-1.775
Token ESPN
Token ID10409
Feature activation-2.20e-01

Pos logit contributions
+0.227
 contro+0.180
 prin+0.174
edia+0.170
 subdivision+0.170
Neg logit contributions
itars-0.159
iltr-0.148
lees-0.148
ioxide-0.147
orks-0.147
Token Rivals
Token ID42307
Feature activation-1.68e-01

Pos logit contributions
+1.245
 contro+0.971
 prin+0.943
 subdivision+0.933
edia+0.926
Neg logit contributions
itars-0.920
lees-0.858
iltr-0.849
orks-0.844
 Axe-0.841
Token our
Token ID674
Feature activation-9.71e-02

Pos logit contributions
+3.323
 contro+2.741
edia+2.613
 prin+2.566
tie+2.469
Neg logit contributions
lees-3.161
itars-3.121
iltr-2.939
lash-2.872
 Axe-2.854
Token top
Token ID1353
Feature activation-1.67e-01

Pos logit contributions
+0.490
 contro+0.370
 prin+0.359
 subdivision+0.350
edia+0.348
Neg logit contributions
itars-0.462
lees-0.444
iltr-0.437
 Axe-0.436
orks-0.433
Token stories
Token ID3923
Feature activation-1.07e-01

Pos logit contributions
+1.077
 contro+0.872
 prin+0.855
 subdivision+0.829
edia+0.826
Neg logit contributions
itars-0.567
lees-0.542
iltr-0.530
 Axe-0.523
orks-0.516
Token Free
Token ID3232
Feature activation-1.91e-01

Pos logit contributions
+0.660
 contro+0.541
 prin+0.525
 subdivision+0.512
edia+0.510
Neg logit contributions
itars-0.383
lees-0.366
 Axe-0.357
iltr-0.356
orks-0.353
Token Sign
Token ID5865
Feature activation-3.70e-01

Pos logit contributions
+1.036
 contro+0.828
 prin+0.802
 subdivision+0.788
edia+0.782
Neg logit contributions
itars-0.808
lees-0.771
iltr-0.757
orks-0.757
ioxide-0.754
Token Up
Token ID3205
Feature activation-8.67e-01

Pos logit contributions
+1.783
edia+1.303
 subdivision+1.297
 contro+1.290
tie+1.277
Neg logit contributions
itars-1.804
iltr-1.699
ioxide-1.699
lees-1.656
 turb-1.648
Token
Token ID198
Feature activation-5.03e-01

Pos logit contributions
+4.312
 contro+3.176
 subdivision+3.167
edia+3.121
tie+3.120
Neg logit contributions
itars-4.089
iltr-3.858
orks-3.829
ioxide-3.822
lees-3.778
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
+2.509
 contro+1.952
tie+1.926
edia+1.891
ario+1.857
Neg logit contributions
itars-2.340
iltr-2.212
orks-2.167
lees-2.162
ioxide-2.154
TokenThe
Token ID464
Feature activation-1.32e-01

Pos logit contributions
+2.224
 contro+1.668
tie+1.639
edia+1.629
NL+1.628
Neg logit contributions
itars-1.897
lees-1.790
iltr-1.782
 Axe-1.779
orks-1.760
Token picture
Token ID4286
Feature activation+3.98e-02

Pos logit contributions
+0.617
 contro+0.472
 prin+0.453
 subdivision+0.444
edia+0.440
Neg logit contributions
itars-0.669
lees-0.641
iltr-0.633
orks-0.626
 Axe-0.618
Token was
Token ID373
Feature activation-6.19e-02

Pos logit contributions
itars+0.163
lees+0.156
iltr+0.154
orks+0.151
 Axe+0.151
Neg logit contributions
-0.228
 contro-0.180
 prin-0.174
 subdivision-0.171
edia-0.170
Token System
Token ID4482
Feature activation-8.72e-01

Pos logit contributions
+3.199
 contro+2.540
 prin+2.475
 subdivision+2.429
edia+2.424
Neg logit contributions
itars-1.958
lees-1.858
iltr-1.819
 Axe-1.811
orks-1.794
Token.
Token ID13
Feature activation-5.53e-01

Pos logit contributions
+4.228
tie+3.266
 contro+3.191
edia+3.168
NL+3.117
Neg logit contributions
itars-4.101
iltr-3.875
lees-3.783
ioxide-3.739
orks-3.728
TokenDraw
Token ID25302
Feature activation-1.09e-02

Pos logit contributions
+2.772
 contro+1.996
tie+1.949
edia+1.928
NL+1.905
Neg logit contributions
itars-2.719
iltr-2.553
lees-2.551
 Karma-2.510
 Axe-2.483
Tokening
Token ID278
Feature activation-3.58e-01

Pos logit contributions
+0.064
 contro+0.051
edia+0.050
tie+0.050
 prin+0.049
Neg logit contributions
itars-0.043
iltr-0.040
lees-0.040
 Axe-0.039
 Ashes-0.039
Token.
Token ID13
Feature activation-3.68e-01

Pos logit contributions
+1.967
 contro+1.494
tie+1.472
edia+1.461
 subdivision+1.437
Neg logit contributions
itars-1.567
iltr-1.475
lees-1.457
orks-1.417
ioxide-1.409
TokenFont
Token ID23252
Feature activation-6.61e-01

Pos logit contributions
+2.009
 contro+1.526
 prin+1.486
edia+1.466
 subdivision+1.460
Neg logit contributions
itars-1.609
lees-1.538
iltr-1.512
 Axe-1.498
orks-1.491
Token($
Token ID16763
Feature activation+8.09e-02

Pos logit contributions
+3.978
 contro+3.157
 prin+3.080
 subdivision+3.018
edia+3.003
Neg logit contributions
itars-2.500
lees-2.374
 Axe-2.340
iltr-2.338
orks-2.305
TokenFont
Token ID23252
Feature activation-3.34e-01

Pos logit contributions
itars+0.377
lees+0.360
 Axe+0.357
iltr+0.356
orks+0.352
Neg logit contributions
-0.413
 contro-0.317
 prin-0.307
 subdivision-0.300
 nomine-0.297
TokenName
Token ID5376
Feature activation+8.97e-02

Pos logit contributions
+1.869
 contro+1.444
 prin+1.406
 subdivision+1.378
edia+1.375
Neg logit contributions
itars-1.407
lees-1.345
iltr-1.320
 Axe-1.318
orks-1.306
Token,
Token ID11
Feature activation+5.60e-01

Pos logit contributions
itars+0.303
iltr+0.281
lees+0.280
orks+0.275
 Axe+0.271
Neg logit contributions
-0.581
 contro-0.464
 prin-0.455
tie-0.450
 subdivision-0.449
Token$
Token ID3
Feature activation-3.64e-01

Pos logit contributions
itars+2.374
lees+2.279
 Axe+2.249
iltr+2.241
orks+2.221
Neg logit contributions
-3.074
 contro-2.387
 prin-2.325
 nomine-2.286
 subdivision-2.269
Token boys
Token ID6510
Feature activation-9.41e-02

Pos logit contributions
+0.274
 contro+0.217
 prin+0.209
 subdivision+0.206
 nomine+0.202
Neg logit contributions
itars-0.228
lees-0.219
iltr-0.217
orks-0.213
 Axe-0.212
Token or
Token ID393
Feature activation-2.26e-02

Pos logit contributions
+0.581
 contro+0.464
 prin+0.452
 subdivision+0.444
edia+0.442
Neg logit contributions
itars-0.341
lees-0.323
 Axe-0.317
iltr-0.317
orks-0.313
Token beauty
Token ID8737
Feature activation+1.59e-01

Pos logit contributions
+0.110
 contro+0.083
 prin+0.080
 subdivision+0.078
 nomine+0.077
Neg logit contributions
itars-0.111
lees-0.107
iltr-0.106
 Axe-0.105
orks-0.105
Token in
Token ID287
Feature activation-6.85e-02

Pos logit contributions
itars+0.693
lees+0.663
 Axe+0.652
iltr+0.652
orks+0.643
Neg logit contributions
-0.870
 contro-0.665
 prin-0.646
edia-0.633
 subdivision-0.633
Token the
Token ID262
Feature activation-3.36e-02

Pos logit contributions
+0.324
 contro+0.243
 prin+0.234
 subdivision+0.228
 nomine+0.226
Neg logit contributions
itars-0.345
lees-0.331
iltr-0.328
 Axe-0.327
orks-0.324
Token case
Token ID1339
Feature activation-6.22e-01

Pos logit contributions
+0.170
 contro+0.130
 prin+0.126
 subdivision+0.123
edia+0.121
Neg logit contributions
itars-0.160
lees-0.153
iltr-0.151
 Axe-0.150
orks-0.149
Token of
Token ID286
Feature activation-2.91e-01

Pos logit contributions
+3.840
 contro+3.058
 prin+2.984
 subdivision+2.926
edia+2.921
Neg logit contributions
itars-2.268
lees-2.146
 Axe-2.109
iltr-2.105
orks-2.079
Token girls
Token ID4813
Feature activation+2.13e-02

Pos logit contributions
+1.405
 contro+1.084
 prin+1.049
 subdivision+1.024
 nomine+0.994
Neg logit contributions
itars-1.422
lees-1.367
iltr-1.362
orks-1.336
ioxide-1.333
Token.
Token ID13
Feature activation+2.65e-02

Pos logit contributions
itars+0.079
lees+0.075
 Axe+0.074
iltr+0.074
orks+0.073
Neg logit contributions
-0.129
 contro-0.102
 prin-0.100
 subdivision-0.098
edia-0.098
Token
Token ID198
Feature activation-5.75e-02

Pos logit contributions
itars+0.114
lees+0.108
iltr+0.107
orks+0.105
ioxide+0.105
Neg logit contributions
-0.147
 contro-0.113
 prin-0.111
 subdivision-0.109
edia-0.107
Token
Token ID198
Feature activation-4.36e-02

Pos logit contributions
+0.309
 contro+0.242
tie+0.234
 prin+0.232
edia+0.231
Neg logit contributions
itars-0.253
iltr-0.237
lees-0.235
orks-0.233
ioxide-0.231
Token BY
Token ID11050
Feature activation+4.30e-01

Pos logit contributions
itars+0.060
lees+0.058
iltr+0.058
 Axe+0.057
orks+0.057
Neg logit contributions
-0.050
 contro-0.036
 prin-0.035
 subdivision-0.034
 nomine-0.034
Token library
Token ID5888
Feature activation-1.43e-01

Pos logit contributions
itars+1.972
lees+1.889
 Axe+1.866
iltr+1.862
orks+1.845
Neg logit contributions
-2.235
 contro-1.695
 prin-1.642
 subdivision-1.604
edia-1.602
Token ORDER
Token ID38678
Feature activation+8.95e-03

Pos logit contributions
+0.870
 contro+0.693
 prin+0.680
 subdivision+0.666
edia+0.659
Neg logit contributions
itars-0.534
lees-0.508
iltr-0.498
 Axe-0.496
orks-0.492
Token BY
Token ID11050
Feature activation+3.35e-01

Pos logit contributions
itars+0.048
lees+0.046
iltr+0.046
 Axe+0.045
orks+0.045
Neg logit contributions
-0.040
 contro-0.029
 prin-0.028
 subdivision-0.027
 nomine-0.027
Token count
Token ID954
Feature activation-3.87e-01

Pos logit contributions
itars+1.621
lees+1.557
 Axe+1.536
iltr+1.535
orks+1.521
Neg logit contributions
-1.663
 contro-1.245
 prin-1.205
 subdivision-1.175
edia-1.169
Token desc
Token ID1715
Feature activation-7.01e-01

Pos logit contributions
+1.956
 contro+1.502
 prin+1.474
 subdivision+1.436
 nomine+1.400
Neg logit contributions
itars-1.814
lees-1.739
iltr-1.716
orks-1.700
 Axe-1.693
Token |
Token ID930
Feature activation+1.52e-01

Pos logit contributions
+3.876
 contro+3.010
 prin+2.973
 subdivision+2.917
edia+2.871
Neg logit contributions
itars-2.883
lees-2.751
iltr-2.695
orks-2.686
ioxide-2.677
Token Row
Token ID11314
Feature activation-4.65e-01

Pos logit contributions
itars+0.682
lees+0.654
iltr+0.644
 Axe+0.642
orks+0.638
Neg logit contributions
-0.808
 contro-0.617
 prin-0.602
 subdivision-0.588
 nomine-0.582
Token |
Token ID930
Feature activation-3.29e-01

Pos logit contributions
+2.700
 contro+2.105
 prin+2.071
 subdivision+2.044
tie+2.011
Neg logit contributions
itars-1.879
lees-1.771
iltr-1.739
ioxide-1.726
orks-1.723
Token library
Token ID5888
Feature activation-6.29e-01

Pos logit contributions
+1.780
 contro+1.362
 prin+1.342
 subdivision+1.322
 nomine+1.288
Neg logit contributions
itars-1.441
lees-1.390
iltr-1.368
orks-1.352
ioxide-1.350
Token |
Token ID930
Feature activation-4.53e-01

Pos logit contributions
+4.216
 contro+3.458
 prin+3.406
 subdivision+3.371
 nomine+3.284
Neg logit contributions
itars-1.910
lees-1.800
iltr-1.763
ioxide-1.749
orks-1.717