TOP ACTIVATIONS
MAX = 2.881

Dis pat ches from the Evangel ical Youth Movement
than the recommended 8 1 / 2 to 9 1 /
get at least 8 1 / 2 hours of sleep a
know that eating those packaged anch ovies is scary , but
not about playing the best football , it s
ari (@ k rist inc av all ari ) on Jan
This discount will only be valid until October 8 th ,
2014 Ricky G erv ais 2014 Matt
100 . G err ard s 100
shorter period of 16 1 / 2 months since the start
their ability to run the football and defend the run ,
The fact that a device like the
at 6 - 11 1 / 2 this week .
. Simon A xt en , a Facebook spokesman
- pack aged spicy dried anch ovies sold in s ari
would be ] blank !" Dw or ak l aments .
urn did not field a football team in 1943 due to
agenda . The real problem for the United States
ADVERTISEMENT N ug ent s pledge
photo posted by Krist in Cav all ari (@ k rist

MIN ACTIVATIONS
MIN = -2.395

to Reuters . ADVERTISEMENT Twenty - three
cy . The Devils wrap up a home - and -
secret myth ographer . Her sil ences fall at times like
. Copyright © 2016 Else vier B . V
MORE and Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
presidential nominee Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
still at least two years away , it seems unlikely that
including clay pot tery , sil vers mith ing , and
- 1100 MHz Memory : 2 GB GDDR 5
pro team in 1946 ( Mic key Mc Bride
shortly thereafter , in a waste of system resources All
MORE and Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
8 election . ADVERTISEMENT Clinton mentioned the
relations . <|endoftext|> Mic published a report last week
him , leading to his death , police Chief Frank Stra
mail this to a friend Print able version <|endoftext|> A university
mail this to a friend Print able version <|endoftext|> Rob C
not a fight to the death . Which means that anyone
species in its episode " Sil ent Ro ar : Search
' Congratulations , you have finished the initiation ceremony , and

INTERVAL 1.562 - 2.881
CONTAINS 0.128%

the Atlanta Journal - Const itution 's published scouting report on
leaving Mr . Sc r utch ins with $ 1 million
American all women 's swing band .[ 46 ]
shift on opioids , I plead for caution . Patients with
( Equ ipe Cycl iste FD J - Big Mat )

INTERVAL 0.243 - 1.562
CONTAINS 27.445%

local government to train their police force more effectively , improve
Strike with Master mind makes him a beast if you don
biological weapons by a terrorist group after A um Shin ri
Dolphins will be in pretty good shape next offseason .
W K AND AP AC HE T OC RE P ORTS

INTERVAL -1.076 - 0.243
CONTAINS 71.140%

is coming to Xbox One . " Our vision
is what eventually breaks through the awkward ness . Both of
from her , which I have kept for almost 30 years
them to sleep each night as children , she would softly
use the command sl s logs - f test -- start

INTERVAL -2.395 - -1.076
CONTAINS 1.288%

a kingdom of the earth !" - excerpt from
step would produce trans uran ics such
to convert income into capital gains as a way of paying
vital strategic position that some fear is threatened by Brexit .
a Guard ) -> Option < Shared < ' a ,
Token Dis
Token ID3167
Feature activation-7.94e-01

Pos logit contributions
arth+0.738
igers+0.706
heast+0.704
arian+0.657
erson+0.643
Neg logit contributions
thood-0.785
 rgb-0.756
cas-0.755
angan-0.751
Cry-0.745
Tokenpat
Token ID8071
Feature activation+4.94e-01

Pos logit contributions
thood+1.878
cas+1.837
angan+1.792
 rgb+1.766
beit+1.739
Neg logit contributions
arth-2.843
igers-2.793
heast-2.755
arian-2.581
erson-2.563
Tokenches
Token ID2052
Feature activation+6.75e-01

Pos logit contributions
arth+1.389
heast+1.328
igers+1.327
arian+1.256
erson+1.216
Neg logit contributions
thood-1.554
 rgb-1.545
angan-1.519
cas-1.516
Cry-1.512
Token from
Token ID422
Feature activation+1.48e+00

Pos logit contributions
arth+1.873
igers+1.798
heast+1.792
arian+1.688
erson+1.636
Neg logit contributions
thood-2.153
 rgb-2.095
cas-2.088
angan-2.081
Cry-2.055
Token the
Token ID262
Feature activation+7.11e-01

Pos logit contributions
arth+4.169
igers+3.926
heast+3.914
arian+3.748
erson+3.662
Neg logit contributions
thood-4.513
angan-4.461
 rgb-4.441
cas-4.402
Cry-4.383
Token Evangel
Token ID27834
Feature activation+2.88e+00

Pos logit contributions
arth+2.130
heast+2.032
igers+2.029
arian+1.902
erson+1.870
Neg logit contributions
thood-2.141
 rgb-2.061
cas-2.056
angan-2.053
Cry-2.029
Tokenical
Token ID605
Feature activation+7.53e-01

Pos logit contributions
arth+5.256
arian+5.073
heast+4.997
igers+4.913
ues+4.620
Neg logit contributions
 rgb-11.132
 Carbuncle-10.943
angan-10.775
thood-10.603
dinand-10.528
Token Youth
Token ID17582
Feature activation+6.27e-01

Pos logit contributions
arth+2.263
heast+2.148
igers+2.146
arian+2.027
erson+1.980
Neg logit contributions
thood-2.251
 rgb-2.194
angan-2.175
cas-2.168
Cry-2.145
Token Movement
Token ID15477
Feature activation+6.94e-01

Pos logit contributions
arth+1.925
igers+1.845
heast+1.834
arian+1.736
erson+1.715
Neg logit contributions
thood-1.819
 rgb-1.783
angan-1.761
cas-1.752
Cry-1.730
Token
Token ID447
Feature activation+1.97e-01

Pos logit contributions
arth+2.208
igers+2.130
heast+2.115
arian+2.013
erson+1.973
Neg logit contributions
thood-1.937
 rgb-1.879
cas-1.866
angan-1.864
Cry-1.832
Token
Token ID251
Feature activation-6.09e-02

Pos logit contributions
arth+0.635
igers+0.610
heast+0.608
arian+0.572
erson+0.561
Neg logit contributions
thood-0.554
 rgb-0.531
cas-0.530
angan-0.528
Cry-0.523
Token than
Token ID621
Feature activation+1.13e-01

Pos logit contributions
arth+2.376
heast+2.287
igers+2.280
arian+2.178
erson+2.131
Neg logit contributions
thood-1.594
cas-1.507
 rgb-1.507
angan-1.497
Cry-1.479
Token the
Token ID262
Feature activation-4.45e-02

Pos logit contributions
arth+0.309
igers+0.296
heast+0.293
arian+0.265
erson+0.260
Neg logit contributions
thood-0.369
 rgb-0.366
cas-0.365
angan-0.360
Cry-0.357
Token recommended
Token ID7151
Feature activation+6.00e-01

Pos logit contributions
thood+0.136
 rgb+0.135
cas+0.135
angan+0.133
Cry+0.132
Neg logit contributions
arth-0.131
igers-0.126
heast-0.124
arian-0.114
erson-0.112
Token 8
Token ID807
Feature activation-2.92e-01

Pos logit contributions
arth+1.614
igers+1.540
heast+1.529
arian+1.413
erson+1.382
Neg logit contributions
thood-2.003
 rgb-1.942
cas-1.940
angan-1.927
Cry-1.916
Token 1
Token ID352
Feature activation+1.14e-01

Pos logit contributions
thood+0.851
cas+0.818
 rgb+0.810
angan+0.804
Cry+0.799
Neg logit contributions
arth-0.919
igers-0.875
heast-0.872
arian-0.822
erson-0.805
Token/
Token ID14
Feature activation+2.60e+00

Pos logit contributions
arth+0.358
igers+0.351
heast+0.351
arian+0.321
illes+0.314
Neg logit contributions
thood-0.322
 rgb-0.319
cas-0.316
angan-0.312
Cry-0.312
Token2
Token ID17
Feature activation+6.26e-01

Pos logit contributions
arth+4.889
heast+4.348
arian+4.207
igers+4.205
ues+3.968
Neg logit contributions
dinand-10.329
thood-10.242
 Carbuncle-10.072
angan-9.996
 rgb-9.903
Token to
Token ID284
Feature activation+1.49e-01

Pos logit contributions
arth+1.947
igers+1.847
heast+1.838
arian+1.787
erson+1.747
Neg logit contributions
thood-1.785
cas-1.723
 rgb-1.704
angan-1.685
Cry-1.675
Token 9
Token ID860
Feature activation-1.22e-01

Pos logit contributions
arth+0.352
igers+0.333
heast+0.331
arian+0.304
erson+0.296
Neg logit contributions
thood-0.544
 rgb-0.527
cas-0.527
angan-0.524
Cry-0.521
Token 1
Token ID352
Feature activation+1.56e-01

Pos logit contributions
thood+0.338
cas+0.327
 rgb+0.319
angan+0.318
Cry+0.315
Neg logit contributions
arth-0.400
igers-0.381
heast-0.381
arian-0.361
erson-0.355
Token/
Token ID14
Feature activation+1.95e+00

Pos logit contributions
arth+0.482
igers+0.468
heast+0.465
arian+0.431
erson+0.418
Neg logit contributions
thood-0.451
 rgb-0.444
cas-0.442
angan-0.436
Cry-0.431
Token get
Token ID651
Feature activation+8.90e-01

Pos logit contributions
arth+0.678
igers+0.655
heast+0.654
arian+0.615
erson+0.603
Neg logit contributions
thood-0.483
 rgb-0.463
cas-0.461
angan-0.458
Cry-0.453
Token at
Token ID379
Feature activation+8.15e-01

Pos logit contributions
arth+2.727
igers+2.614
heast+2.604
arian+2.428
erson+2.384
Neg logit contributions
thood-2.644
 rgb-2.551
cas-2.545
angan-2.528
Cry-2.505
Token least
Token ID1551
Feature activation-3.05e-01

Pos logit contributions
arth+1.695
igers+1.583
heast+1.570
arian+1.453
erson+1.407
Neg logit contributions
thood-3.201
 rgb-3.117
cas-3.094
angan-3.089
Cry-3.088
Token 8
Token ID807
Feature activation-4.46e-01

Pos logit contributions
 rgb+0.920
thood+0.918
cas+0.916
angan+0.907
Cry+0.892
Neg logit contributions
arth-0.899
heast-0.854
igers-0.854
arian-0.765
yre-0.764
Token 1
Token ID352
Feature activation-2.89e-01

Pos logit contributions
thood+1.093
 rgb+1.046
cas+1.043
angan+1.041
Cry+1.029
Neg logit contributions
arth-1.586
igers-1.531
heast-1.530
arian-1.443
erson-1.418
Token/
Token ID14
Feature activation+2.58e+00

Pos logit contributions
thood+0.957
 rgb+0.926
cas+0.920
angan+0.918
Cry+0.911
Neg logit contributions
arth-0.787
igers-0.747
heast-0.743
arian-0.691
erson-0.679
Token2
Token ID17
Feature activation+3.29e-01

Pos logit contributions
arth+4.473
heast+4.136
igers+3.851
arian+3.767
erson+3.610
Neg logit contributions
dinand-10.436
 Carbuncle-10.430
thood-10.243
 rgb-10.188
angan-10.157
Token hours
Token ID2250
Feature activation-1.37e-01

Pos logit contributions
arth+1.138
igers+1.095
heast+1.091
arian+1.035
erson+1.019
Neg logit contributions
thood-0.843
 rgb-0.804
cas-0.803
angan-0.799
Cry-0.790
Token of
Token ID286
Feature activation-2.75e-01

Pos logit contributions
thood+0.388
 rgb+0.374
cas+0.372
angan+0.369
Cry+0.366
Neg logit contributions
arth-0.439
igers-0.422
heast-0.418
arian-0.390
erson-0.385
Token sleep
Token ID3993
Feature activation-1.25e-02

Pos logit contributions
thood+0.529
 rgb+0.506
cas+0.498
angan+0.496
Cry+0.488
Neg logit contributions
arth-1.121
igers-1.099
heast-1.086
arian-1.026
erson-1.011
Token a
Token ID257
Feature activation+3.22e-01

Pos logit contributions
thood+0.035
 rgb+0.034
cas+0.034
angan+0.033
Cry+0.033
Neg logit contributions
arth-0.040
igers-0.039
heast-0.038
arian-0.036
erson-0.035
Token know
Token ID760
Feature activation-2.54e-01

Pos logit contributions
thood+0.551
 rgb+0.534
cas+0.532
angan+0.522
Cry+0.515
Neg logit contributions
arth-0.750
igers-0.728
heast-0.722
arian-0.677
illes-0.662
Token that
Token ID326
Feature activation+1.51e-01

Pos logit contributions
thood+0.661
 rgb+0.658
cas+0.656
angan+0.641
Cry+0.636
Neg logit contributions
arth-0.851
igers-0.818
heast-0.814
arian-0.755
illes-0.747
Token eating
Token ID6600
Feature activation+3.27e-01

Pos logit contributions
arth+0.492
igers+0.476
heast+0.473
arian+0.442
erson+0.434
Neg logit contributions
thood-0.414
 rgb-0.404
cas-0.403
angan-0.398
Cry-0.394
Token those
Token ID883
Feature activation-5.77e-02

Pos logit contributions
arth+1.002
igers+0.962
heast+0.956
arian+0.894
erson+0.876
Neg logit contributions
thood-0.962
cas-0.935
 rgb-0.935
angan-0.926
Cry-0.917
Token packaged
Token ID25555
Feature activation+4.60e-01

Pos logit contributions
thood+0.154
cas+0.152
 rgb+0.152
angan+0.150
Cry+0.148
Neg logit contributions
arth-0.190
igers-0.183
heast-0.182
arian-0.171
erson-0.167
Token anch
Token ID12619
Feature activation+2.48e+00

Pos logit contributions
arth+1.499
igers+1.440
heast+1.436
arian+1.351
erson+1.325
Neg logit contributions
thood-1.275
 rgb-1.222
cas-1.220
angan-1.213
Cry-1.202
Tokenovies
Token ID20526
Feature activation+4.18e-01

Pos logit contributions
arth+5.995
igers+5.859
heast+5.656
arian+5.563
ues+5.361
Neg logit contributions
thood-8.426
 Carbuncle-8.024
 rgb-7.947
Cry-7.905
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯-7.820
Token is
Token ID318
Feature activation-2.24e-01

Pos logit contributions
arth+1.406
igers+1.353
heast+1.349
arian+1.267
erson+1.244
Neg logit contributions
thood-1.112
 rgb-1.072
cas-1.070
angan-1.058
Cry-1.047
Token scary
Token ID14343
Feature activation-1.44e-01

Pos logit contributions
thood+0.606
cas+0.600
 rgb+0.596
angan+0.584
Cry+0.572
Neg logit contributions
arth-0.724
igers-0.707
heast-0.698
arian-0.650
erson-0.640
Token,
Token ID11
Feature activation-2.79e-01

Pos logit contributions
thood+0.383
 rgb+0.367
cas+0.367
angan+0.363
Cry+0.361
Neg logit contributions
arth-0.485
igers-0.467
heast-0.466
arian-0.439
erson-0.431
Token but
Token ID475
Feature activation-4.62e-01

Pos logit contributions
thood+0.733
cas+0.711
 rgb+0.711
angan+0.702
Cry+0.695
Neg logit contributions
arth-0.941
igers-0.906
heast-0.905
arian-0.848
erson-0.831
Token not
Token ID407
Feature activation-3.07e-01

Pos logit contributions
thood+0.068
 rgb+0.065
cas+0.065
angan+0.064
Cry+0.064
Neg logit contributions
arth-0.085
igers-0.082
heast-0.082
arian-0.077
erson-0.075
Token about
Token ID546
Feature activation+2.27e-01

Pos logit contributions
thood+0.819
 rgb+0.790
cas+0.788
Cry+0.776
angan+0.770
Neg logit contributions
arth-1.029
igers-0.992
heast-0.985
arian-0.920
erson-0.910
Token playing
Token ID2712
Feature activation+7.51e-01

Pos logit contributions
arth+0.721
igers+0.692
heast+0.691
arian+0.647
erson+0.634
Neg logit contributions
thood-0.651
 rgb-0.625
cas-0.624
angan-0.619
Cry-0.615
Token the
Token ID262
Feature activation+3.36e-01

Pos logit contributions
arth+2.294
igers+2.192
heast+2.190
arian+2.059
erson+2.016
Neg logit contributions
thood-2.225
 rgb-2.133
cas-2.129
angan-2.127
Cry-2.101
Token best
Token ID1266
Feature activation+6.49e-01

Pos logit contributions
arth+1.099
heast+1.051
igers+1.050
arian+0.985
erson+0.963
Neg logit contributions
thood-0.929
cas-0.900
 rgb-0.897
angan-0.887
Cry-0.879
Token football
Token ID4346
Feature activation+2.46e+00

Pos logit contributions
arth+2.081
igers+1.999
heast+1.995
arian+1.870
erson+1.833
Neg logit contributions
thood-1.831
 rgb-1.757
cas-1.756
angan-1.743
Cry-1.728
Token,
Token ID11
Feature activation+3.31e-02

Pos logit contributions
arth+6.574
heast+6.165
igers+6.132
erson+5.950
arian+5.899
Neg logit contributions
thood-7.343
?????-?????--7.142
dinand-7.113
angan-7.078
Cry-7.029
Token it
Token ID340
Feature activation+4.49e-02

Pos logit contributions
arth+0.118
igers+0.114
heast+0.114
arian+0.107
erson+0.106
Neg logit contributions
thood-0.081
 rgb-0.077
cas-0.077
angan-0.077
Cry-0.076
Token
Token ID447
Feature activation-5.97e-02

Pos logit contributions
arth+0.174
igers+0.169
heast+0.167
arian+0.160
erson+0.157
Neg logit contributions
thood-0.096
 rgb-0.091
cas-0.091
angan-0.090
Cry-0.089
Token
Token ID247
Feature activation-1.69e-01

Pos logit contributions
thood+0.128
 rgb+0.124
cas+0.122
angan+0.120
Cry+0.119
Neg logit contributions
arth-0.232
heast-0.225
igers-0.221
arian-0.211
erson-0.208
Tokens
Token ID82
Feature activation-1.08e-02

Pos logit contributions
thood+0.384
cas+0.369
 rgb+0.366
angan+0.363
Cry+0.357
Neg logit contributions
arth-0.633
heast-0.613
igers-0.608
arian-0.577
erson-0.567
Tokenari
Token ID2743
Feature activation+9.89e-01

Pos logit contributions
arth+3.007
igers+2.835
heast+2.807
arian+2.701
erson+2.614
Neg logit contributions
thood-4.254
 rgb-4.086
Cry-4.066
cas-4.045
angan-4.018
Token (@
Token ID4275
Feature activation+4.09e-01

Pos logit contributions
arth+2.000
igers+1.867
heast+1.838
arian+1.707
erson+1.669
Neg logit contributions
thood-3.904
 rgb-3.768
cas-3.767
Cry-3.724
angan-3.712
Tokenk
Token ID74
Feature activation+5.96e-01

Pos logit contributions
arth+1.348
igers+1.287
heast+1.282
arian+1.218
erson+1.192
Neg logit contributions
thood-1.119
 rgb-1.078
angan-1.061
cas-1.055
Cry-1.050
Tokenrist
Token ID1585
Feature activation+3.71e-01

Pos logit contributions
arth+1.827
igers+1.721
heast+1.719
arian+1.639
erson+1.599
Neg logit contributions
thood-1.772
 rgb-1.718
angan-1.685
Cry-1.682
cas-1.677
Tokeninc
Token ID1939
Feature activation+1.11e+00

Pos logit contributions
arth+0.928
igers+0.873
heast+0.864
arian+0.809
erson+0.790
Neg logit contributions
thood-1.320
 rgb-1.278
Cry-1.265
cas-1.258
angan-1.253
Tokenav
Token ID615
Feature activation+2.43e+00

Pos logit contributions
arth+3.551
igers+3.321
heast+3.263
arian+3.160
erson+3.104
Neg logit contributions
thood-3.212
Cry-3.065
 rgb-3.018
beit-2.983
 Carbuncle-2.950
Tokenall
Token ID439
Feature activation+1.26e+00

Pos logit contributions
arth+5.515
igers+4.815
arian+4.753
heast+4.586
illes+4.462
Neg logit contributions
thood-8.770
Cry-8.579
?????-?????--8.555
 rgb-8.510
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯-8.478
Tokenari
Token ID2743
Feature activation+5.77e-01

Pos logit contributions
arth+2.187
igers+1.934
arian+1.886
heast+1.874
erson+1.678
Neg logit contributions
thood-5.470
 rgb-5.285
Cry-5.272
beit-5.204
angan-5.182
Token)
Token ID8
Feature activation+2.31e-01

Pos logit contributions
arth+1.678
igers+1.602
heast+1.576
arian+1.489
erson+1.465
Neg logit contributions
thood-1.815
 rgb-1.711
cas-1.700
Cry-1.698
 Carbuncle-1.697
Token on
Token ID319
Feature activation+3.66e-01

Pos logit contributions
arth+0.842
igers+0.822
heast+0.819
arian+0.765
erson+0.749
Neg logit contributions
thood-0.540
 rgb-0.531
cas-0.523
Cry-0.514
angan-0.514
Token Jan
Token ID2365
Feature activation+1.36e+00

Pos logit contributions
arth+1.016
igers+0.970
heast+0.969
arian+0.896
erson+0.875
Neg logit contributions
thood-1.187
 rgb-1.152
cas-1.152
angan-1.141
Cry-1.140
Token This
Token ID770
Feature activation-4.82e-02

Pos logit contributions
arth+0.064
igers+0.062
heast+0.062
arian+0.057
erson+0.056
Neg logit contributions
thood-0.065
cas-0.062
 rgb-0.062
Cry-0.062
angan-0.061
Token discount
Token ID9780
Feature activation+1.32e-01

Pos logit contributions
thood+0.131
 rgb+0.126
cas+0.125
angan+0.124
Cry+0.123
Neg logit contributions
arth-0.160
igers-0.155
heast-0.153
arian-0.143
erson-0.141
Token will
Token ID481
Feature activation-2.67e-01

Pos logit contributions
arth+0.447
igers+0.433
heast+0.430
arian+0.402
erson+0.397
Neg logit contributions
thood-0.348
 rgb-0.335
cas-0.332
angan-0.331
Cry-0.327
Token only
Token ID691
Feature activation+3.60e-01

Pos logit contributions
thood+0.693
 rgb+0.678
angan+0.664
cas+0.661
Cry+0.654
Neg logit contributions
arth-0.915
igers-0.886
heast-0.876
arian-0.827
illes-0.811
Token be
Token ID307
Feature activation+3.29e-01

Pos logit contributions
arth+1.160
heast+1.113
igers+1.110
arian+1.047
erson+1.027
Neg logit contributions
thood-1.007
cas-0.964
 rgb-0.959
angan-0.954
Cry-0.948
Token valid
Token ID4938
Feature activation+2.41e+00

Pos logit contributions
arth+0.889
igers+0.850
heast+0.843
arian+0.782
erson+0.765
Neg logit contributions
thood-1.093
 rgb-1.060
cas-1.056
angan-1.051
Cry-1.041
Token until
Token ID1566
Feature activation+9.45e-01

Pos logit contributions
arth+6.553
heast+6.150
igers+6.018
arian+5.771
erson+5.638
Neg logit contributions
thood-7.315
?????-?????--7.148
 rgb-7.145
cas-7.104
 Carbuncle-7.020
Token October
Token ID3267
Feature activation+8.42e-01

Pos logit contributions
arth+2.168
igers+2.047
heast+2.040
arian+1.865
erson+1.811
Neg logit contributions
thood-3.530
 rgb-3.421
cas-3.417
angan-3.402
Cry-3.380
Token 8
Token ID807
Feature activation+2.42e-01

Pos logit contributions
arth+1.633
igers+1.527
heast+1.518
arian+1.359
erson+1.309
Neg logit contributions
thood-3.447
 rgb-3.352
cas-3.350
angan-3.339
Cry-3.321
Tokenth
Token ID400
Feature activation+1.08e+00

Pos logit contributions
arth+0.767
igers+0.733
heast+0.729
arian+0.685
erson+0.672
Neg logit contributions
thood-0.692
 rgb-0.665
cas-0.662
angan-0.656
Cry-0.654
Token,
Token ID11
Feature activation+6.47e-01

Pos logit contributions
arth+3.457
igers+3.284
heast+3.278
arian+3.091
erson+3.028
Neg logit contributions
thood-3.036
 rgb-2.925
cas-2.904
angan-2.878
Cry-2.854
Token
Token ID198
Feature activation-6.57e-01

Pos logit contributions
thood+0.190
cas+0.183
 rgb+0.182
Cry+0.181
angan+0.180
Neg logit contributions
arth-0.157
igers-0.149
heast-0.146
arian-0.138
erson-0.136
Token
Token ID198
Feature activation+1.48e-01

Pos logit contributions
 rgb+1.527
cas+1.519
Cry+1.513
bus+1.488
thood+1.456
Neg logit contributions
heast-2.367
arth-2.341
igers-2.323
 opio-2.204
arian-2.098
Token2014
Token ID4967
Feature activation-1.18e+00

Pos logit contributions
arth+0.316
heast+0.305
igers+0.301
arian+0.270
erson+0.264
Neg logit contributions
thood-0.573
cas-0.560
Cry-0.558
angan-0.555
 rgb-0.553
Token Ricky
Token ID31668
Feature activation-2.59e-01

Pos logit contributions
thood+2.945
cas+2.902
 rgb+2.878
Cry+2.862
 Carbuncle+2.835
Neg logit contributions
arth-3.897
heast-3.871
igers-3.793
arian-3.495
erson-3.477
Token G
Token ID402
Feature activation+5.50e-01

Pos logit contributions
thood+0.453
 rgb+0.452
angan+0.445
cas+0.440
Cry+0.429
Neg logit contributions
arth-1.086
heast-1.070
igers-1.061
arian-1.005
 seams-0.982
Tokenerv
Token ID712
Feature activation+2.40e+00

Pos logit contributions
arth+1.752
heast+1.688
igers+1.686
arian+1.575
erson+1.538
Neg logit contributions
thood-1.547
cas-1.494
 rgb-1.492
angan-1.483
Cry-1.465
Tokenais
Token ID15152
Feature activation+1.00e+00

Pos logit contributions
arth+7.848
igers+7.535
heast+7.223
arian+7.130
illes+6.966
Neg logit contributions
thood-6.442
��-6.377
 rgb-6.231
?????-?????--6.184
Cry-6.134
Token
Token ID198
Feature activation-3.68e-01

Pos logit contributions
arth+2.222
igers+2.029
heast+1.944
arian+1.933
erson+1.871
Neg logit contributions
thood-3.652
 rgb-3.591
cas-3.580
Cry-3.548
beit-3.541
Token
Token ID198
Feature activation+2.25e-01

Pos logit contributions
 rgb+0.898
cas+0.896
Cry+0.893
thood+0.875
bus+0.873
Neg logit contributions
heast-1.278
arth-1.274
igers-1.258
 opio-1.164
arian-1.142
Token2014
Token ID4967
Feature activation-1.10e+00

Pos logit contributions
arth+0.466
heast+0.443
igers+0.440
arian+0.396
erson+0.385
Neg logit contributions
thood-0.889
cas-0.866
 rgb-0.861
angan-0.861
Cry-0.859
Token Matt
Token ID4705
Feature activation+8.91e-01

Pos logit contributions
thood+2.817
cas+2.770
 rgb+2.742
Cry+2.735
angan+2.702
Neg logit contributions
arth-3.639
heast-3.596
igers-3.525
arian-3.250
erson-3.233
Token 100
Token ID1802
Feature activation-5.82e-01

Pos logit contributions
arth+0.342
igers+0.329
heast+0.328
arian+0.308
erson+0.300
Neg logit contributions
thood-0.295
 rgb-0.286
cas-0.285
angan-0.282
Cry-0.279
Token.
Token ID13
Feature activation-3.09e-01

Pos logit contributions
thood+1.614
cas+1.548
 rgb+1.547
angan+1.526
Cry+1.518
Neg logit contributions
arth-1.882
igers-1.813
heast-1.804
arian-1.699
erson-1.662
Token
Token ID198
Feature activation+1.19e-01

Pos logit contributions
thood+0.993
 rgb+0.953
cas+0.951
angan+0.944
Cry+0.939
Neg logit contributions
arth-0.869
heast-0.840
igers-0.837
arian-0.773
erson-0.751
Token
Token ID198
Feature activation+1.28e-01

Pos logit contributions
arth+0.387
heast+0.380
igers+0.376
arian+0.348
illes+0.341
Neg logit contributions
thood-0.324
cas-0.319
 rgb-0.318
Cry-0.318
angan-0.311
TokenG
Token ID38
Feature activation+1.30e+00

Pos logit contributions
arth+0.416
igers+0.400
heast+0.399
arian+0.375
erson+0.367
Neg logit contributions
thood-0.358
cas-0.343
 rgb-0.343
angan-0.341
Cry-0.339
Tokenerr
Token ID8056
Feature activation+2.40e+00

Pos logit contributions
arth+3.490
igers+3.199
heast+3.153
arian+3.053
erson+3.022
Neg logit contributions
thood-4.520
 rgb-4.228
beit-4.211
cas-4.208
angan-4.197
Tokenard
Token ID446
Feature activation+7.17e-01

Pos logit contributions
arth+6.524
heast+5.988
igers+5.985
arian+5.943
erson+5.822
Neg logit contributions
thood-7.836
Cry-7.563
cas-7.465
 rgb-7.390
?????-?????--7.369
Token
Token ID447
Feature activation-9.41e-02

Pos logit contributions
arth+2.259
igers+2.164
heast+2.154
arian+2.029
erson+1.992
Neg logit contributions
thood-2.067
cas-1.974
 rgb-1.972
angan-1.965
Cry-1.951
Token
Token ID247
Feature activation+2.64e-02

Pos logit contributions
thood+0.222
 rgb+0.212
cas+0.211
angan+0.209
Cry+0.207
Neg logit contributions
arth-0.345
heast-0.332
igers-0.331
arian-0.315
erson-0.308
Tokens
Token ID82
Feature activation+1.21e-01

Pos logit contributions
arth+0.083
heast+0.080
igers+0.080
arian+0.075
erson+0.073
Neg logit contributions
thood-0.075
cas-0.072
 rgb-0.072
angan-0.071
Cry-0.071
Token 100
Token ID1802
Feature activation-7.80e-01

Pos logit contributions
arth+0.366
igers+0.352
heast+0.350
arian+0.328
erson+0.320
Neg logit contributions
thood-0.362
 rgb-0.350
cas-0.348
angan-0.346
Cry-0.343
Token shorter
Token ID12238
Feature activation+9.87e-01

Pos logit contributions
arth+0.905
igers+0.874
heast+0.866
arian+0.813
erson+0.795
Neg logit contributions
thood-0.787
 rgb-0.765
cas-0.763
angan-0.754
Cry-0.749
Token period
Token ID2278
Feature activation-3.97e-02

Pos logit contributions
arth+3.175
heast+3.044
igers+3.031
arian+2.884
erson+2.816
Neg logit contributions
thood-2.763
angan-2.628
cas-2.627
 rgb-2.622
Cry-2.584
Token of
Token ID286
Feature activation-2.77e-01

Pos logit contributions
thood+0.115
 rgb+0.110
cas+0.110
angan+0.110
Cry+0.109
Neg logit contributions
arth-0.124
igers-0.119
heast-0.119
arian-0.112
erson-0.109
Token 16
Token ID1467
Feature activation-3.08e-01

Pos logit contributions
thood+0.932
 rgb+0.907
cas+0.902
Cry+0.897
angan+0.883
Neg logit contributions
arth-0.729
igers-0.703
heast-0.698
arian-0.632
illes-0.616
Token 1
Token ID352
Feature activation-1.80e-01

Pos logit contributions
thood+0.987
cas+0.956
 rgb+0.955
angan+0.947
Cry+0.944
Neg logit contributions
arth-0.861
igers-0.822
heast-0.821
arian-0.759
erson-0.747
Token/
Token ID14
Feature activation+2.34e+00

Pos logit contributions
thood+0.574
 rgb+0.553
cas+0.552
angan+0.549
Cry+0.545
Neg logit contributions
arth-0.511
igers-0.487
heast-0.486
arian-0.453
erson-0.443
Token2
Token ID17
Feature activation+2.19e-01

Pos logit contributions
arth+4.153
heast+3.950
igers+3.788
arian+3.621
ues+3.531
Neg logit contributions
dinand-9.143
thood-9.118
angan-9.073
 Carbuncle-9.038
 rgb-9.024
Token months
Token ID1933
Feature activation+5.06e-02

Pos logit contributions
arth+0.613
igers+0.585
heast+0.582
arian+0.546
erson+0.533
Neg logit contributions
thood-0.706
 rgb-0.679
cas-0.678
angan-0.678
Cry-0.670
Token since
Token ID1201
Feature activation+7.32e-01

Pos logit contributions
arth+0.168
igers+0.162
heast+0.162
arian+0.152
erson+0.149
Neg logit contributions
thood-0.136
 rgb-0.131
cas-0.130
angan-0.130
Cry-0.128
Token the
Token ID262
Feature activation+3.68e-01

Pos logit contributions
arth+2.215
igers+2.122
heast+2.113
arian+1.984
erson+1.944
Neg logit contributions
thood-2.193
 rgb-2.107
cas-2.103
angan-2.097
Cry-2.073
Token start
Token ID923
Feature activation+1.29e-01

Pos logit contributions
arth+1.100
heast+1.053
igers+1.052
arian+0.978
erson+0.959
Neg logit contributions
thood-1.113
cas-1.080
 rgb-1.078
angan-1.067
Cry-1.065
Token their
Token ID511
Feature activation+1.04e-01

Pos logit contributions
arth+0.862
igers+0.825
heast+0.822
arian+0.766
erson+0.750
Neg logit contributions
thood-0.906
 rgb-0.874
cas-0.872
angan-0.868
Cry-0.860
Token ability
Token ID2694
Feature activation-1.81e-01

Pos logit contributions
arth+0.382
igers+0.373
heast+0.370
arian+0.349
erson+0.341
Neg logit contributions
thood-0.239
 rgb-0.238
cas-0.232
angan-0.232
Cry-0.226
Token to
Token ID284
Feature activation-1.78e-01

Pos logit contributions
thood+0.545
 rgb+0.520
cas+0.520
angan+0.513
beit+0.512
Neg logit contributions
arth-0.551
igers-0.529
heast-0.525
arian-0.496
erson-0.486
Token run
Token ID1057
Feature activation+4.99e-01

Pos logit contributions
thood+0.395
 rgb+0.389
cas+0.383
angan+0.379
Cry+0.371
Neg logit contributions
arth-0.664
igers-0.646
heast-0.645
arian-0.607
erson-0.592
Token the
Token ID262
Feature activation+5.16e-01

Pos logit contributions
arth+1.497
igers+1.432
heast+1.430
arian+1.339
erson+1.314
Neg logit contributions
thood-1.511
 rgb-1.448
cas-1.446
angan-1.441
Cry-1.427
Token football
Token ID4346
Feature activation+2.34e+00

Pos logit contributions
arth+1.544
igers+1.477
heast+1.473
arian+1.378
erson+1.349
Neg logit contributions
thood-1.565
 rgb-1.505
cas-1.503
angan-1.495
Cry-1.483
Token and
Token ID290
Feature activation+5.11e-01

Pos logit contributions
arth+6.562
heast+6.385
igers+6.232
arian+6.074
erson+6.019
Neg logit contributions
thood-6.968
angan-6.508
?????-?????--6.469
 rgb-6.421
Cry-6.360
Token defend
Token ID4404
Feature activation+1.15e+00

Pos logit contributions
arth+1.751
igers+1.685
heast+1.681
arian+1.588
erson+1.559
Neg logit contributions
thood-1.326
 rgb-1.265
cas-1.263
angan-1.256
Cry-1.244
Token the
Token ID262
Feature activation+3.74e-01

Pos logit contributions
arth+3.257
igers+3.093
heast+3.075
arian+2.960
erson+2.903
Neg logit contributions
thood-3.655
cas-3.468
angan-3.458
 rgb-3.449
Cry-3.429
Token run
Token ID1057
Feature activation+6.75e-02

Pos logit contributions
arth+1.423
igers+1.375
heast+1.373
arian+1.303
erson+1.282
Neg logit contributions
thood-0.828
 rgb-0.786
cas-0.784
angan-0.778
Cry-0.769
Token,
Token ID11
Feature activation-1.17e-01

Pos logit contributions
arth+0.231
igers+0.223
heast+0.222
arian+0.210
erson+0.207
Neg logit contributions
thood-0.175
 rgb-0.167
cas-0.167
angan-0.166
Cry-0.164
Token
Token ID447
Feature activation-4.91e-01

Pos logit contributions
arth+0.353
igers+0.339
heast+0.339
arian+0.318
erson+0.312
Neg logit contributions
thood-0.297
 rgb-0.285
cas-0.284
angan-0.282
Cry-0.281
Token
Token ID251
Feature activation-1.65e-01

Pos logit contributions
thood+1.289
cas+1.231
 rgb+1.226
angan+1.226
Cry+1.212
Neg logit contributions
arth-1.671
igers-1.608
heast-1.605
arian-1.513
erson-1.492
Token
Token ID198
Feature activation-1.21e-01

Pos logit contributions
thood+0.473
 rgb+0.458
Cry+0.456
cas+0.454
angan+0.452
Neg logit contributions
arth-0.516
heast-0.498
igers-0.495
arian-0.461
erson-0.454
Token
Token ID198
Feature activation+4.91e-02

Pos logit contributions
cas+0.307
 rgb+0.306
Cry+0.306
thood+0.305
angan+0.299
Neg logit contributions
arth-0.407
heast-0.405
igers-0.400
arian-0.364
illes-0.361
TokenThe
Token ID464
Feature activation+2.53e-02

Pos logit contributions
arth+0.184
heast+0.179
igers+0.178
arian+0.169
erson+0.166
Neg logit contributions
thood-0.111
cas-0.106
 rgb-0.105
angan-0.105
Cry-0.104
Token fact
Token ID1109
Feature activation+2.30e+00

Pos logit contributions
arth+0.077
igers+0.075
heast+0.074
arian+0.069
erson+0.068
Neg logit contributions
thood-0.074
 rgb-0.072
cas-0.072
angan-0.072
Cry-0.071
Token that
Token ID326
Feature activation+9.65e-01

Pos logit contributions
arth+5.830
igers+5.782
arian+5.409
heast+5.340
olls+5.231
Neg logit contributions
thood-7.503
 rgb-7.096
cas-6.978
 Carbuncle-6.914
?????-?????--6.877
Token a
Token ID257
Feature activation+3.53e-01

Pos logit contributions
arth+3.010
igers+2.872
heast+2.856
arian+2.696
erson+2.649
Neg logit contributions
thood-2.796
 rgb-2.670
cas-2.669
angan-2.651
Cry-2.616
Token device
Token ID3335
Feature activation+1.65e-01

Pos logit contributions
arth+1.117
igers+1.078
heast+1.074
arian+1.005
erson+0.984
Neg logit contributions
thood-1.005
 rgb-0.972
cas-0.969
angan-0.965
Cry-0.958
Token like
Token ID588
Feature activation-3.11e-01

Pos logit contributions
arth+0.564
igers+0.545
heast+0.545
arian+0.510
erson+0.502
Neg logit contributions
thood-0.429
 rgb-0.412
cas-0.411
angan-0.408
Cry-0.405
Token the
Token ID262
Feature activation-3.57e-01

Pos logit contributions
thood+0.940
 rgb+0.905
cas+0.904
angan+0.899
Cry+0.892
Neg logit contributions
arth-0.932
igers-0.892
heast-0.891
arian-0.832
erson-0.814
Token at
Token ID379
Feature activation+4.21e-01

Pos logit contributions
thood+0.340
 rgb+0.330
cas+0.326
angan+0.323
Cry+0.321
Neg logit contributions
arth-0.393
igers-0.378
heast-0.375
arian-0.354
erson-0.343
Token 6
Token ID718
Feature activation-9.06e-02

Pos logit contributions
arth+1.058
igers+1.006
heast+1.004
arian+0.922
erson+0.894
Neg logit contributions
thood-1.478
 rgb-1.435
cas-1.430
angan-1.418
Cry-1.410
Token-
Token ID12
Feature activation+1.14e+00

Pos logit contributions
thood+0.235
 rgb+0.224
cas+0.224
angan+0.223
Cry+0.220
Neg logit contributions
arth-0.312
igers-0.299
heast-0.299
arian-0.283
erson-0.277
Token11
Token ID1157
Feature activation-5.37e-01

Pos logit contributions
arth+2.668
igers+2.466
heast+2.449
arian+2.279
erson+2.243
Neg logit contributions
thood-4.137
angan-4.012
 rgb-3.981
 Carbuncle-3.961
cas-3.943
Token 1
Token ID352
Feature activation+2.65e-01

Pos logit contributions
thood+1.438
 rgb+1.385
cas+1.376
angan+1.363
Cry+1.355
Neg logit contributions
arth-1.792
igers-1.738
heast-1.726
arian-1.617
erson-1.574
Token/
Token ID14
Feature activation+2.29e+00

Pos logit contributions
arth+0.724
heast+0.681
igers+0.676
arian+0.638
erson+0.631
Neg logit contributions
thood-0.877
cas-0.847
 rgb-0.846
angan-0.844
Cry-0.832
Token2
Token ID17
Feature activation+3.12e-01

Pos logit contributions
arth+4.190
heast+3.895
igers+3.734
arian+3.593
erson+3.453
Neg logit contributions
dinand-8.993
angan-8.987
thood-8.950
 Carbuncle-8.940
 rgb-8.777
Token this
Token ID428
Feature activation+4.88e-01

Pos logit contributions
arth+0.960
igers+0.914
heast+0.907
arian+0.869
erson+0.862
Neg logit contributions
thood-0.913
cas-0.873
angan-0.872
 rgb-0.860
Cry-0.855
Token week
Token ID1285
Feature activation+9.09e-01

Pos logit contributions
arth+1.288
igers+1.225
heast+1.222
arian+1.132
erson+1.105
Neg logit contributions
thood-1.650
cas-1.591
 rgb-1.591
angan-1.583
Cry-1.571
Token.
Token ID13
Feature activation+2.31e-01

Pos logit contributions
arth+2.805
igers+2.678
heast+2.659
arian+2.562
erson+2.501
Neg logit contributions
thood-2.623
angan-2.476
 rgb-2.471
cas-2.465
Cry-2.453
Token
Token ID198
Feature activation+1.91e-01

Pos logit contributions
arth+0.698
igers+0.669
heast+0.667
arian+0.624
erson+0.610
Neg logit contributions
thood-0.694
 rgb-0.668
cas-0.666
angan-0.662
Cry-0.658
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
thood+2.646
cas+2.588
angan+2.548
 rgb+2.544
Cry+2.522
Neg logit contributions
arth-3.703
igers-3.587
heast-3.585
arian-3.352
erson-3.293
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
arth+0.502
heast+0.481
igers+0.480
arian+0.445
erson+0.436
Neg logit contributions
thood-0.534
 rgb-0.515
cas-0.515
angan-0.511
Cry-0.508
Token
Token ID198
Feature activation+2.28e-01

Pos logit contributions
arth+0.480
heast+0.470
igers+0.467
arian+0.429
illes+0.420
Neg logit contributions
thood-0.392
 rgb-0.389
cas-0.389
Cry-0.386
angan-0.381
TokenSimon
Token ID35475
Feature activation-1.03e+00

Pos logit contributions
arth+0.700
igers+0.671
heast+0.668
arian+0.627
erson+0.614
Neg logit contributions
thood-0.676
 rgb-0.651
cas-0.648
angan-0.645
Cry-0.638
Token A
Token ID317
Feature activation+3.03e-01

Pos logit contributions
thood+2.959
cas+2.908
angan+2.863
beit+2.850
 rgb+2.842
Neg logit contributions
arth-3.108
heast-3.020
igers-3.016
arian-2.784
illes-2.730
Tokenxt
Token ID742
Feature activation+2.28e+00

Pos logit contributions
arth+0.970
igers+0.931
heast+0.927
arian+0.872
erson+0.858
Neg logit contributions
thood-0.860
 rgb-0.826
cas-0.819
angan-0.812
Cry-0.811
Tokenen
Token ID268
Feature activation+1.35e+00

Pos logit contributions
arth+6.517
igers+6.087
heast+5.944
arian+5.847
erson+5.769
Neg logit contributions
thood-7.116
 rgb-6.904
?????-?????--6.770
Cry-6.691
cas-6.656
Token,
Token ID11
Feature activation+1.24e-01

Pos logit contributions
arth+4.310
igers+4.049
heast+3.935
arian+3.902
erson+3.797
Neg logit contributions
thood-3.777
 rgb-3.678
Cry-3.582
cas-3.543
angan-3.543
Token a
Token ID257
Feature activation+4.04e-02

Pos logit contributions
arth+0.361
igers+0.345
heast+0.344
arian+0.321
erson+0.314
Neg logit contributions
thood-0.387
 rgb-0.372
cas-0.372
angan-0.370
Cry-0.367
Token Facebook
Token ID3203
Feature activation+4.70e-01

Pos logit contributions
arth+0.135
heast+0.132
igers+0.131
arian+0.121
illes+0.119
Neg logit contributions
thood-0.107
cas-0.105
 rgb-0.104
angan-0.103
Cry-0.102
Token spokesman
Token ID6523
Feature activation-2.31e-02

Pos logit contributions
arth+1.645
igers+1.582
heast+1.574
arian+1.500
erson+1.468
Neg logit contributions
thood-1.190
 rgb-1.133
cas-1.129
angan-1.122
Cry-1.113
Token-
Token ID12
Feature activation-1.65e-01

Pos logit contributions
thood+1.349
cas+1.291
 rgb+1.279
angan+1.269
Cry+1.251
Neg logit contributions
arth-1.944
heast-1.900
igers-1.890
arian-1.783
erson-1.740
Tokenpack
Token ID8002
Feature activation-4.20e-02

Pos logit contributions
thood+0.449
cas+0.433
 rgb+0.428
angan+0.426
Cry+0.425
Neg logit contributions
arth-0.540
heast-0.523
igers-0.522
arian-0.490
erson-0.479
Tokenaged
Token ID1886
Feature activation+1.82e-01

Pos logit contributions
thood+0.121
cas+0.117
angan+0.116
 rgb+0.116
Cry+0.114
Neg logit contributions
arth-0.131
igers-0.127
heast-0.126
arian-0.117
erson-0.115
Token spicy
Token ID26880
Feature activation+3.87e-01

Pos logit contributions
arth+0.601
igers+0.580
heast+0.577
arian+0.541
erson+0.531
Neg logit contributions
thood-0.496
cas-0.478
 rgb-0.478
angan-0.473
Cry-0.470
Token dried
Token ID16577
Feature activation+6.42e-01

Pos logit contributions
arth+1.302
igers+1.249
heast+1.245
arian+1.180
erson+1.157
Neg logit contributions
thood-1.037
 rgb-0.986
cas-0.981
angan-0.980
Cry-0.969
Token anch
Token ID12619
Feature activation+2.28e+00

Pos logit contributions
arth+2.112
igers+2.026
heast+2.019
arian+1.914
erson+1.877
Neg logit contributions
thood-1.761
 rgb-1.670
cas-1.662
angan-1.659
Cry-1.645
Tokenovies
Token ID20526
Feature activation+6.59e-01

Pos logit contributions
arth+5.975
igers+5.679
heast+5.467
arian+5.450
erson+5.223
Neg logit contributions
thood-7.671
 rgb-7.142
 Carbuncle-7.130
Cry-7.126
cas-7.095
Token sold
Token ID2702
Feature activation+3.20e-01

Pos logit contributions
arth+2.202
igers+2.107
heast+2.100
arian+1.995
erson+1.957
Neg logit contributions
thood-1.773
 rgb-1.687
cas-1.685
angan-1.682
Cry-1.665
Token in
Token ID287
Feature activation+3.91e-01

Pos logit contributions
arth+1.004
igers+0.964
heast+0.960
arian+0.901
erson+0.883
Neg logit contributions
thood-0.923
 rgb-0.886
cas-0.885
angan-0.879
Cry-0.872
Token s
Token ID264
Feature activation-2.52e-01

Pos logit contributions
arth+1.260
igers+1.207
heast+1.205
arian+1.136
erson+1.112
Neg logit contributions
thood-1.097
 rgb-1.047
cas-1.046
angan-1.040
Cry-1.031
Tokenari
Token ID2743
Feature activation+3.89e-01

Pos logit contributions
thood+0.747
cas+0.721
 rgb+0.719
angan+0.716
Cry+0.711
Neg logit contributions
arth-0.763
igers-0.733
heast-0.731
arian-0.681
erson-0.669
Tokenwould
Token ID19188
Feature activation+2.92e-01

Pos logit contributions
arth+2.203
igers+2.121
heast+2.114
arian+2.010
erson+1.978
Neg logit contributions
thood-1.376
 rgb-1.311
angan-1.286
cas-1.278
beit-1.256
Token be
Token ID307
Feature activation+3.59e-01

Pos logit contributions
arth+0.950
igers+0.913
heast+0.910
arian+0.856
erson+0.840
Neg logit contributions
thood-0.808
 rgb-0.774
cas-0.773
angan-0.769
Cry-0.761
Token]
Token ID60
Feature activation+1.65e-01

Pos logit contributions
arth+1.025
igers+0.988
heast+0.975
arian+0.916
erson+0.895
Neg logit contributions
thood-1.135
 rgb-1.103
cas-1.099
angan-1.087
Cry-1.079
Token blank
Token ID9178
Feature activation-7.18e-01

Pos logit contributions
arth+0.521
igers+0.505
heast+0.499
arian+0.470
erson+0.458
Neg logit contributions
thood-0.472
 rgb-0.458
cas-0.456
angan-0.448
Cry-0.445
Token!"
Token ID2474
Feature activation-1.16e+00

Pos logit contributions
thood+1.772
 rgb+1.719
cas+1.714
Cry+1.654
angan+1.625
Neg logit contributions
arth-2.481
heast-2.470
igers-2.453
arian-2.288
erson-2.208
Token Dw
Token ID19113
Feature activation+2.28e+00

Pos logit contributions
thood+2.686
cas+2.635
 rgb+2.632
Cry+2.626
angan+2.569
Neg logit contributions
arth-4.111
heast-4.012
igers-4.004
arian-3.758
illes-3.724
Tokenor
Token ID273
Feature activation+8.29e-01

Pos logit contributions
arth+4.283
igers+3.646
arian+3.553
erson+3.413
heast+3.411
Neg logit contributions
thood-9.650
?????-?????--9.343
 Carbuncle-9.335
 rgb-9.310
��-9.188
Tokenak
Token ID461
Feature activation+6.72e-01

Pos logit contributions
arth+1.924
igers+1.819
heast+1.813
arian+1.658
erson+1.611
Neg logit contributions
thood-3.069
 rgb-2.974
cas-2.972
angan-2.959
Cry-2.937
Token l
Token ID300
Feature activation-5.57e-01

Pos logit contributions
arth+2.203
igers+2.093
heast+2.069
arian+1.993
erson+1.975
Neg logit contributions
thood-1.854
angan-1.743
cas-1.733
 rgb-1.723
Cry-1.711
Tokenaments
Token ID12604
Feature activation-2.99e-01

Pos logit contributions
thood+1.544
cas+1.512
angan+1.496
 rgb+1.478
Cry+1.471
Neg logit contributions
arth-1.772
heast-1.716
igers-1.689
arian-1.567
 seams-1.549
Token.
Token ID13
Feature activation+2.13e-03

Pos logit contributions
thood+0.786
 rgb+0.744
cas+0.741
angan+0.736
Cry+0.726
Neg logit contributions
arth-1.025
igers-0.987
heast-0.984
arian-0.936
erson-0.921
Tokenurn
Token ID700
Feature activation+9.86e-01

Pos logit contributions
arth+1.950
igers+1.825
heast+1.818
arian+1.640
erson+1.586
Neg logit contributions
thood-3.880
 rgb-3.767
cas-3.763
angan-3.748
Cry-3.725
Token did
Token ID750
Feature activation-2.07e-01

Pos logit contributions
arth+3.032
igers+2.917
heast+2.868
arian+2.754
erson+2.703
Neg logit contributions
thood-2.904
cas-2.741
 rgb-2.736
angan-2.729
Cry-2.705
Token not
Token ID407
Feature activation-5.33e-03

Pos logit contributions
thood+0.566
 rgb+0.542
cas+0.542
angan+0.538
Cry+0.533
Neg logit contributions
arth-0.679
igers-0.652
heast-0.651
arian-0.612
erson-0.601
Token field
Token ID2214
Feature activation+5.84e-01

Pos logit contributions
thood+0.013
 rgb+0.013
cas+0.012
angan+0.012
Cry+0.012
Neg logit contributions
arth-0.019
igers-0.018
heast-0.018
arian-0.017
erson-0.017
Token a
Token ID257
Feature activation+5.67e-01

Pos logit contributions
arth+1.762
igers+1.687
heast+1.683
arian+1.575
erson+1.542
Neg logit contributions
thood-1.754
 rgb-1.686
cas-1.684
angan-1.675
Cry-1.661
Token football
Token ID4346
Feature activation+2.26e+00

Pos logit contributions
arth+1.793
igers+1.726
heast+1.720
arian+1.603
erson+1.567
Neg logit contributions
thood-1.619
 rgb-1.567
angan-1.557
cas-1.551
Cry-1.536
Token team
Token ID1074
Feature activation+7.88e-01

Pos logit contributions
arth+6.482
heast+6.092
igers+6.034
arian+5.906
erson+5.845
Neg logit contributions
thood-6.772
cas-6.439
angan-6.430
 rgb-6.400
beit-6.392
Token in
Token ID287
Feature activation+2.47e-01

Pos logit contributions
arth+2.506
igers+2.401
heast+2.394
arian+2.254
erson+2.211
Neg logit contributions
thood-2.243
 rgb-2.146
cas-2.144
angan-2.134
Cry-2.114
Token 1943
Token ID21577
Feature activation-6.56e-01

Pos logit contributions
arth+0.631
heast+0.607
igers+0.600
arian+0.556
erson+0.537
Neg logit contributions
thood-0.853
 rgb-0.828
cas-0.821
angan-0.820
Cry-0.816
Token due
Token ID2233
Feature activation+9.45e-01

Pos logit contributions
thood+1.676
cas+1.616
 rgb+1.604
angan+1.587
Cry+1.585
Neg logit contributions
arth-2.232
igers-2.166
heast-2.160
arian-2.035
erson-1.990
Token to
Token ID284
Feature activation+8.11e-01

Pos logit contributions
arth+2.609
igers+2.494
heast+2.467
arian+2.213
ues+2.199
Neg logit contributions
thood-3.042
cas-2.922
 rgb-2.907
beit-2.897
 Carbuncle-2.891
Token agenda
Token ID8666
Feature activation-2.44e-01

Pos logit contributions
arth+2.384
igers+2.298
heast+2.289
arian+2.200
erson+2.162
Neg logit contributions
thood-1.462
cas-1.374
angan-1.373
 rgb-1.372
Cry-1.355
Token.
Token ID13
Feature activation+9.45e-03

Pos logit contributions
thood+0.621
 rgb+0.593
cas+0.592
angan+0.589
Cry+0.582
Neg logit contributions
arth-0.852
igers-0.820
heast-0.818
arian-0.775
erson-0.761
Token
Token ID198
Feature activation+3.30e-01

Pos logit contributions
arth+0.029
igers+0.027
heast+0.027
arian+0.025
erson+0.025
Neg logit contributions
thood-0.028
 rgb-0.027
cas-0.027
angan-0.027
Cry-0.027
Token
Token ID198
Feature activation+4.16e-01

Pos logit contributions
arth+1.059
heast+1.031
igers+1.026
arian+0.946
erson+0.926
Neg logit contributions
thood-0.913
 rgb-0.899
cas-0.898
Cry-0.889
angan-0.884
TokenThe
Token ID464
Feature activation+7.87e-02

Pos logit contributions
arth+1.340
igers+1.281
heast+1.275
arian+1.207
erson+1.181
Neg logit contributions
thood-1.172
 rgb-1.129
cas-1.112
angan-1.112
Cry-1.088
Token real
Token ID1103
Feature activation+2.23e+00

Pos logit contributions
arth+0.243
igers+0.234
heast+0.234
arian+0.218
erson+0.213
Neg logit contributions
thood-0.229
cas-0.222
 rgb-0.221
angan-0.221
Cry-0.218
Token problem
Token ID1917
Feature activation+1.40e+00

Pos logit contributions
arth+6.484
igers+6.077
heast+5.873
arian+5.619
erson+5.584
Neg logit contributions
thood-6.759
 rgb-6.412
angan-6.343
cas-6.245
beit-6.236
Token for
Token ID329
Feature activation-2.36e-02

Pos logit contributions
arth+4.132
heast+3.871
igers+3.861
arian+3.695
ues+3.637
Neg logit contributions
thood-4.263
 rgb-4.108
cas-4.037
 Carbuncle-3.964
Cry-3.958
Token the
Token ID262
Feature activation-2.47e-01

Pos logit contributions
thood+0.075
 rgb+0.072
cas+0.072
angan+0.071
Cry+0.071
Neg logit contributions
arth-0.068
igers-0.065
heast-0.064
arian-0.060
erson-0.059
Token United
Token ID1578
Feature activation+3.37e-02

Pos logit contributions
thood+0.683
cas+0.661
 rgb+0.657
angan+0.657
Cry+0.649
Neg logit contributions
arth-0.797
heast-0.768
igers-0.767
arian-0.720
erson-0.701
Token States
Token ID1829
Feature activation-5.03e-01

Pos logit contributions
arth+0.107
igers+0.104
heast+0.104
arian+0.096
erson+0.094
Neg logit contributions
thood-0.093
cas-0.092
 rgb-0.092
Cry-0.091
angan-0.091
Token
Token ID198
Feature activation+2.12e-01

Pos logit contributions
arth+0.296
heast+0.290
igers+0.288
arian+0.265
illes+0.260
Neg logit contributions
thood-0.243
cas-0.242
 rgb-0.241
Cry-0.239
angan-0.236
TokenADVERTISEMENT
Token ID19053
Feature activation-2.01e+00

Pos logit contributions
arth+0.752
igers+0.722
heast+0.719
arian+0.686
erson+0.674
Neg logit contributions
thood-0.528
 rgb-0.505
angan-0.500
cas-0.498
beit-0.487
Token
Token ID198
Feature activation+4.52e-02

Pos logit contributions
thood+4.784
Cry+4.732
 rgb+4.724
cas+4.643
angan+4.510
Neg logit contributions
arth-6.850
igers-6.594
heast-6.579
 seams-6.250
arian-6.079
Token
Token ID198
Feature activation+1.25e-01

Pos logit contributions
arth+0.149
heast+0.147
igers+0.145
arian+0.133
illes+0.131
Neg logit contributions
thood-0.120
cas-0.119
 rgb-0.119
Cry-0.118
angan-0.116
TokenN
Token ID45
Feature activation+3.94e-01

Pos logit contributions
arth+0.401
igers+0.385
heast+0.383
arian+0.362
erson+0.355
Neg logit contributions
thood-0.353
 rgb-0.338
cas-0.336
angan-0.336
Cry-0.330
Tokenug
Token ID1018
Feature activation+2.21e+00

Pos logit contributions
arth+1.085
igers+1.031
heast+1.031
arian+0.957
erson+0.932
Neg logit contributions
thood-1.289
cas-1.244
 rgb-1.242
angan-1.238
Cry-1.225
Tokenent
Token ID298
Feature activation+2.24e-01

Pos logit contributions
arth+2.034
igers+1.585
heast+1.558
arian+1.415
erson+1.323
Neg logit contributions
thood-11.178
 rgb-11.010
 Carbuncle-10.975
angan-10.839
cas-10.836
Token
Token ID447
Feature activation+2.58e-01

Pos logit contributions
arth+0.710
igers+0.682
heast+0.681
arian+0.637
erson+0.624
Neg logit contributions
thood-0.638
 rgb-0.613
cas-0.611
angan-0.607
Cry-0.602
Token
Token ID247
Feature activation-4.14e-02

Pos logit contributions
arth+0.740
igers+0.706
heast+0.700
arian+0.661
erson+0.649
Neg logit contributions
thood-0.805
cas-0.776
 rgb-0.774
angan-0.771
Cry-0.768
Tokens
Token ID82
Feature activation-1.30e-01

Pos logit contributions
thood+0.117
 rgb+0.112
cas+0.112
angan+0.111
Cry+0.110
Neg logit contributions
arth-0.133
igers-0.128
heast-0.128
arian-0.119
erson-0.116
Token pledge
Token ID13995
Feature activation+9.45e-02

Pos logit contributions
thood+0.344
 rgb+0.329
cas+0.328
angan+0.326
Cry+0.324
Neg logit contributions
arth-0.437
igers-0.425
heast-0.421
arian-0.392
illes-0.382
Token photo
Token ID4590
Feature activation-6.92e-01

Pos logit contributions
thood+0.352
 rgb+0.340
cas+0.339
angan+0.337
Cry+0.332
Neg logit contributions
arth-0.358
igers-0.342
heast-0.341
arian-0.317
erson-0.313
Token posted
Token ID4481
Feature activation+9.54e-01

Pos logit contributions
thood+2.237
 rgb+2.198
cas+2.170
Cry+2.148
angan+2.133
Neg logit contributions
arth-1.877
heast-1.824
igers-1.802
arian-1.646
erson-1.627
Token by
Token ID416
Feature activation+1.52e-01

Pos logit contributions
arth+3.223
igers+3.100
heast+3.093
arian+2.918
erson+2.863
Neg logit contributions
thood-2.523
 rgb-2.410
cas-2.408
angan-2.394
Cry-2.369
Token Krist
Token ID14912
Feature activation+1.11e+00

Pos logit contributions
arth+0.455
igers+0.435
heast+0.434
arian+0.407
erson+0.398
Neg logit contributions
thood-0.460
cas-0.441
 rgb-0.440
angan-0.439
Cry-0.435
Tokenin
Token ID259
Feature activation+1.31e-01

Pos logit contributions
arth+3.084
igers+2.924
heast+2.918
arian+2.739
erson+2.705
Neg logit contributions
thood-3.593
 rgb-3.471
cas-3.409
Cry-3.395
angan-3.385
Token Cav
Token ID19931
Feature activation+2.19e+00

Pos logit contributions
arth+0.397
igers+0.380
heast+0.379
arian+0.355
erson+0.349
Neg logit contributions
thood-0.392
 rgb-0.376
cas-0.375
angan-0.373
Cry-0.369
Tokenall
Token ID439
Feature activation+1.21e+00

Pos logit contributions
arth+6.559
igers+6.139
arian+5.952
heast+5.943
erson+5.822
Neg logit contributions
thood-6.440
 rgb-6.313
?????-?????--6.109
Cry-6.089
��-6.022
Tokenari
Token ID2743
Feature activation+9.89e-01

Pos logit contributions
arth+3.007
igers+2.835
heast+2.807
arian+2.701
erson+2.614
Neg logit contributions
thood-4.254
 rgb-4.086
Cry-4.066
cas-4.045
angan-4.018
Token (@
Token ID4275
Feature activation+4.09e-01

Pos logit contributions
arth+2.000
igers+1.867
heast+1.838
arian+1.707
erson+1.669
Neg logit contributions
thood-3.904
 rgb-3.768
cas-3.767
Cry-3.724
angan-3.712
Tokenk
Token ID74
Feature activation+5.96e-01

Pos logit contributions
arth+1.348
igers+1.287
heast+1.282
arian+1.218
erson+1.192
Neg logit contributions
thood-1.119
 rgb-1.078
angan-1.061
cas-1.055
Cry-1.050
Tokenrist
Token ID1585
Feature activation+3.71e-01

Pos logit contributions
arth+1.827
igers+1.721
heast+1.719
arian+1.639
erson+1.599
Neg logit contributions
thood-1.772
 rgb-1.718
angan-1.685
Cry-1.682
cas-1.677
Token to
Token ID284
Feature activation-6.83e-01

Pos logit contributions
Cry+1.778
 rgb+1.753
cas+1.749
thood+1.726
angan+1.692
Neg logit contributions
arth-3.005
heast-2.972
igers-2.922
arian-2.740
illes-2.724
Token Reuters
Token ID8428
Feature activation+3.23e-01

Pos logit contributions
thood+2.088
 rgb+2.069
cas+2.058
Cry+2.038
angan+2.022
Neg logit contributions
arth-1.951
heast-1.852
igers-1.850
arian-1.724
erson-1.665
Token.
Token ID13
Feature activation-4.24e-01

Pos logit contributions
arth+1.085
heast+1.044
igers+1.041
arian+0.993
erson+0.965
Neg logit contributions
thood-0.862
 rgb-0.824
angan-0.819
cas-0.815
beit-0.804
Token
Token ID198
Feature activation-6.22e-01

Pos logit contributions
thood+1.293
cas+1.248
 rgb+1.247
angan+1.236
Cry+1.236
Neg logit contributions
arth-1.257
igers-1.206
heast-1.200
arian-1.116
erson-1.095
Token
Token ID198
Feature activation-3.60e-01

Pos logit contributions
cas+1.476
Cry+1.475
 rgb+1.465
bus+1.434
thood+1.417
Neg logit contributions
heast-2.208
arth-2.187
igers-2.173
 opio-2.032
arian-1.968
TokenADVERTISEMENT
Token ID19053
Feature activation-2.40e+00

Pos logit contributions
thood+1.044
Cry+1.032
cas+1.027
 rgb+1.001
angan+1.001
Neg logit contributions
arth-1.103
heast-1.072
igers-1.068
arian-0.985
 seams-0.973
Token
Token ID198
Feature activation-1.50e-01

Pos logit contributions
thood+6.270
Cry+6.033
cas+6.015
 rgb+6.015
angan+5.863
Neg logit contributions
arth-7.528
igers-7.338
heast-7.208
 seams-6.969
arian-6.701
Token
Token ID198
Feature activation-9.59e-02

Pos logit contributions
cas+0.384
 rgb+0.381
thood+0.381
Cry+0.380
angan+0.371
Neg logit contributions
arth-0.505
heast-0.503
igers-0.496
arian-0.453
illes-0.447
TokenTwenty
Token ID34096
Feature activation+1.85e-01

Pos logit contributions
thood+0.287
cas+0.280
Cry+0.280
 rgb+0.276
angan+0.275
Neg logit contributions
arth-0.287
heast-0.278
igers-0.277
arian-0.256
erson-0.252
Token-
Token ID12
Feature activation+4.43e-01

Pos logit contributions
arth+0.648
igers+0.624
heast+0.623
arian+0.591
erson+0.580
Neg logit contributions
thood-0.466
 rgb-0.443
cas-0.441
angan-0.439
Cry-0.433
Tokenthree
Token ID15542
Feature activation-3.14e-01

Pos logit contributions
arth+0.867
igers+0.810
heast+0.807
arian+0.726
erson+0.701
Neg logit contributions
thood-1.803
 rgb-1.752
cas-1.749
angan-1.742
Cry-1.731
Tokency
Token ID948
Feature activation-2.59e-01

Pos logit contributions
arth+2.272
igers+2.145
heast+2.143
arian+2.051
erson+2.016
Neg logit contributions
thood-1.913
 rgb-1.852
angan-1.820
cas-1.816
Cry-1.800
Token.
Token ID13
Feature activation-5.23e-02

Pos logit contributions
thood+0.687
cas+0.659
angan+0.654
 rgb+0.650
Cry+0.647
Neg logit contributions
arth-0.864
heast-0.849
igers-0.843
arian-0.784
erson-0.765
Token The
Token ID383
Feature activation-1.06e-02

Pos logit contributions
thood+0.155
cas+0.149
 rgb+0.149
angan+0.148
Cry+0.148
Neg logit contributions
arth-0.160
heast-0.154
igers-0.154
arian-0.143
erson-0.140
Token Devils
Token ID26199
Feature activation+5.99e-01

Pos logit contributions
thood+0.034
cas+0.033
angan+0.033
 rgb+0.033
Cry+0.033
Neg logit contributions
arth-0.029
heast-0.028
igers-0.028
arian-0.026
erson-0.025
Token wrap
Token ID14441
Feature activation-1.11e+00

Pos logit contributions
arth+1.933
igers+1.856
heast+1.848
arian+1.743
erson+1.708
Neg logit contributions
thood-1.678
 rgb-1.607
cas-1.603
angan-1.596
Cry-1.581
Token up
Token ID510
Feature activation-2.35e+00

Pos logit contributions
thood+2.531
angan+2.492
cas+2.473
 rgb+2.439
Cry+2.421
Neg logit contributions
arth-3.957
heast-3.861
igers-3.797
arian-3.534
ordan-3.491
Token a
Token ID257
Feature activation-1.09e+00

Pos logit contributions
angan+6.186
cas+6.070
beit+6.032
Cry+6.030
 rgb+5.993
Neg logit contributions
heast-6.763
arth-6.720
igers-6.518
ordan-6.108
arian-5.949
Token home
Token ID1363
Feature activation-1.17e+00

Pos logit contributions
 rgb+3.153
cas+3.101
beit+3.069
thood+3.066
angan+3.054
Neg logit contributions
arth-3.195
heast-3.093
igers-3.092
arian-2.822
erson-2.765
Token-
Token ID12
Feature activation-5.79e-01

Pos logit contributions
thood+2.880
cas+2.862
Cry+2.811
 rgb+2.805
angan+2.746
Neg logit contributions
arth-4.000
igers-3.908
heast-3.862
arian-3.588
erson-3.572
Tokenand
Token ID392
Feature activation-5.79e-01

Pos logit contributions
thood+1.902
cas+1.881
angan+1.844
 rgb+1.843
Cry+1.840
Neg logit contributions
arth-1.556
igers-1.496
heast-1.483
arian-1.364
erson-1.332
Token-
Token ID12
Feature activation+4.69e-01

Pos logit contributions
cas+1.051
thood+1.042
 rgb+1.016
beit+0.984
bus+0.977
Neg logit contributions
arth-2.363
igers-2.328
heast-2.319
olls-2.146
arian-2.142
Token secret
Token ID3200
Feature activation-7.72e-01

Pos logit contributions
thood+0.147
 rgb+0.141
cas+0.141
angan+0.139
Cry+0.138
Neg logit contributions
arth-0.174
igers-0.168
heast-0.167
arian-0.156
erson-0.153
Token myth
Token ID7918
Feature activation-8.02e-01

Pos logit contributions
thood+1.940
 rgb+1.869
cas+1.861
angan+1.844
Cry+1.844
Neg logit contributions
arth-2.666
heast-2.580
igers-2.579
arian-2.358
illes-2.349
Tokenographer
Token ID18539
Feature activation-4.84e-01

Pos logit contributions
thood+2.120
cas+2.025
 rgb+2.016
angan+2.011
Cry+1.999
Neg logit contributions
arth-2.682
heast-2.593
igers-2.588
arian-2.391
erson-2.371
Token.
Token ID13
Feature activation-6.52e-02

Pos logit contributions
thood+1.197
cas+1.143
 rgb+1.132
angan+1.126
Cry+1.124
Neg logit contributions
arth-1.716
igers-1.658
heast-1.652
arian-1.546
erson-1.527
Token Her
Token ID2332
Feature activation+5.66e-02

Pos logit contributions
thood+0.192
 rgb+0.185
cas+0.184
Cry+0.183
angan+0.182
Neg logit contributions
arth-0.201
igers-0.194
heast-0.194
arian-0.179
erson-0.176
Token sil
Token ID3313
Feature activation-2.30e+00

Pos logit contributions
arth+0.185
igers+0.178
heast+0.178
arian+0.166
erson+0.163
Neg logit contributions
thood-0.156
 rgb-0.150
cas-0.150
angan-0.149
Cry-0.148
Tokenences
Token ID3007
Feature activation-1.57e+00

Pos logit contributions
thood+5.912
cas+5.826
angan+5.800
beit+5.601
ittal+5.585
Neg logit contributions
arth-7.104
igers-7.005
heast-6.912
ordan-6.399
 seams-6.369
Token fall
Token ID2121
Feature activation+4.43e-01

Pos logit contributions
thood+3.750
cas+3.638
 rgb+3.576
angan+3.486
Cry+3.446
Neg logit contributions
arth-5.451
igers-5.305
heast-5.303
yre-4.837
arian-4.796
Token at
Token ID379
Feature activation+9.99e-01

Pos logit contributions
arth+1.512
heast+1.451
igers+1.449
arian+1.377
erson+1.349
Neg logit contributions
thood-1.161
 rgb-1.104
angan-1.098
cas-1.094
Cry-1.080
Token times
Token ID1661
Feature activation-2.45e-01

Pos logit contributions
arth+2.820
igers+2.686
heast+2.667
arian+2.520
erson+2.468
Neg logit contributions
thood-3.197
cas-3.027
 rgb-3.017
angan-3.012
Cry-3.009
Token like
Token ID588
Feature activation+1.56e-01

Pos logit contributions
thood+0.674
cas+0.649
 rgb+0.648
angan+0.641
Cry+0.638
Neg logit contributions
arth-0.800
igers-0.772
heast-0.767
arian-0.720
erson-0.706
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
arth+1.385
heast+1.327
igers+1.325
arian+1.257
erson+1.232
Neg logit contributions
thood-1.031
 rgb-0.980
cas-0.977
angan-0.971
Cry-0.963
Token
Token ID198
Feature activation+4.02e-01

Pos logit contributions
thood+0.411
 rgb+0.396
Cry+0.396
angan+0.395
cas+0.393
Neg logit contributions
arth-0.556
igers-0.540
heast-0.537
arian-0.499
erson-0.493
Token
Token ID198
Feature activation+3.52e-01

Pos logit contributions
arth+1.287
heast+1.251
igers+1.250
arian+1.152
erson+1.129
Neg logit contributions
thood-1.121
cas-1.099
 rgb-1.098
Cry-1.090
angan-1.083
TokenCopyright
Token ID15269
Feature activation-4.20e-01

Pos logit contributions
arth+1.131
igers+1.085
heast+1.082
arian+1.018
erson+0.998
Neg logit contributions
thood-0.991
 rgb-0.950
cas-0.948
angan-0.943
Cry-0.934
Token ©
Token ID10673
Feature activation-5.53e-01

Pos logit contributions
thood+1.393
cas+1.342
 rgb+1.341
angan+1.337
Cry+1.328
Neg logit contributions
arth-1.134
igers-1.084
heast-1.079
arian-0.998
erson-0.974
Token 2016
Token ID1584
Feature activation-2.29e+00

Pos logit contributions
thood+2.303
cas+2.261
Cry+2.254
 rgb+2.239
beit+2.227
Neg logit contributions
arth-0.980
igers-0.954
heast-0.939
arian-0.823
 seams-0.790
Token Else
Token ID25974
Feature activation-1.97e-01

Pos logit contributions
beit+6.119
thood+6.111
Cry+6.040
cas+5.989
 rgb+5.853
Neg logit contributions
arth-6.824
igers-6.660
heast-6.640
 seams-6.119
arian-5.968
Tokenvier
Token ID49663
Feature activation+4.93e-01

Pos logit contributions
thood+0.747
cas+0.728
 rgb+0.723
angan+0.722
Cry+0.719
Neg logit contributions
arth-0.434
igers-0.414
heast-0.409
arian-0.372
erson-0.360
Token B
Token ID347
Feature activation-4.83e-01

Pos logit contributions
arth+1.424
heast+1.352
igers+1.350
arian+1.273
erson+1.238
Neg logit contributions
thood-1.539
 rgb-1.495
angan-1.487
cas-1.484
Cry-1.460
Token.
Token ID13
Feature activation+5.26e-01

Pos logit contributions
thood+1.078
cas+1.033
angan+1.016
 rgb+1.016
beit+1.011
Neg logit contributions
arth-1.813
igers-1.778
heast-1.760
arian-1.644
 seams-1.626
TokenV
Token ID53
Feature activation+2.56e-01

Pos logit contributions
arth+1.788
igers+1.709
heast+1.703
arian+1.615
erson+1.584
Neg logit contributions
thood-1.394
 rgb-1.325
cas-1.324
angan-1.311
Cry-1.289
Token MORE
Token ID12011
Feature activation-6.47e-01

Pos logit contributions
thood+2.383
 rgb+2.328
angan+2.292
cas+2.285
Cry+2.283
Neg logit contributions
arth-2.255
heast-2.218
igers-2.182
arian-2.009
illes-1.960
Token and
Token ID290
Feature activation-6.38e-01

Pos logit contributions
thood+1.804
 rgb+1.728
cas+1.726
angan+1.717
Cry+1.701
Neg logit contributions
arth-2.097
igers-2.013
heast-2.008
arian-1.891
erson-1.855
Token Hillary
Token ID5073
Feature activation-1.34e+00

Pos logit contributions
thood+1.512
 rgb+1.468
cas+1.458
angan+1.424
Cry+1.421
Neg logit contributions
arth-2.297
igers-2.240
heast-2.216
arian-2.059
illes-2.030
Token Clinton
Token ID2605
Feature activation-5.16e-01

Pos logit contributions
cas+2.405
 rgb+2.378
Cry+2.363
beit+2.295
thood+2.275
Neg logit contributions
igers-5.321
arth-5.299
heast-5.267
 opio-4.876
yre-4.838
Token Hillary
Token ID5073
Feature activation-9.85e-01

Pos logit contributions
thood+1.232
 rgb+1.193
cas+1.177
Cry+1.161
angan+1.159
Neg logit contributions
arth-1.842
igers-1.810
heast-1.798
arian-1.668
ues-1.631
Token Diane
Token ID26542
Feature activation-2.29e+00

Pos logit contributions
angan+1.411
Cry+1.384
thood+1.334
 rgb+1.310
othing+1.297
Neg logit contributions
arth-4.400
heast-4.321
igers-4.299
 seams-4.026
yre-3.984
Token Rodham
Token ID41848
Feature activation-2.70e-01

Pos logit contributions
 rgb+2.132
thood+2.065
cas+1.942
angan+1.892
Cry+1.798
Neg logit contributions
igers-11.186
arth-11.007
heast-10.847
 seams-10.373
ourney-10.369
Token Clinton
Token ID2605
Feature activation-4.33e-01

Pos logit contributions
 rgb+0.583
thood+0.575
cas+0.562
angan+0.559
Cry+0.559
Neg logit contributions
arth-1.030
heast-0.990
igers-0.978
arian-0.928
yre-0.911
TokenSanders
Token ID26747
Feature activation-6.48e-01

Pos logit contributions
thood+0.903
Cry+0.872
cas+0.869
 rgb+0.858
angan+0.852
Neg logit contributions
arth-1.679
heast-1.631
igers-1.615
arian-1.545
erson-1.521
Token:
Token ID25
Feature activation-2.94e-01

Pos logit contributions
thood+1.385
 rgb+1.364
Cry+1.324
angan+1.311
cas+1.310
Neg logit contributions
arth-2.501
heast-2.374
igers-2.349
arian-2.277
yre-2.185
Token '
Token ID705
Feature activation-5.00e-02

Pos logit contributions
thood+0.660
Cry+0.637
 rgb+0.628
beit+0.624
angan+0.622
Neg logit contributions
arth-1.101
heast-1.096
igers-1.049
arian-1.005
ourney-0.989
Token presidential
Token ID4787
Feature activation-9.79e-01

Pos logit contributions
thood+0.744
 rgb+0.713
cas+0.707
angan+0.700
Cry+0.690
Neg logit contributions
arth-1.520
heast-1.475
igers-1.469
arian-1.396
erson-1.371
Token nominee
Token ID10429
Feature activation+1.86e-01

Pos logit contributions
thood+1.839
 rgb+1.809
cas+1.780
angan+1.735
Cry+1.698
Neg logit contributions
arth-3.974
heast-3.867
igers-3.826
arian-3.612
erson-3.579
Token Hillary
Token ID5073
Feature activation-9.32e-01

Pos logit contributions
arth+0.620
igers+0.595
heast+0.594
arian+0.562
erson+0.551
Neg logit contributions
thood-0.501
 rgb-0.478
cas-0.477
angan-0.475
Cry-0.471
Token Clinton
Token ID2605
Feature activation-1.87e-01

Pos logit contributions
cas+1.920
 rgb+1.894
thood+1.879
Cry+1.869
angan+1.835
Neg logit contributions
arth-3.557
igers-3.501
heast-3.469
arian-3.176
yre-3.172
Token Hillary
Token ID5073
Feature activation-1.12e+00

Pos logit contributions
thood+0.504
 rgb+0.491
cas+0.487
angan+0.482
Cry+0.478
Neg logit contributions
arth-0.614
igers-0.593
heast-0.591
arian-0.549
erson-0.539
Token Diane
Token ID26542
Feature activation-2.25e+00

Pos logit contributions
Cry+1.599
thood+1.571
angan+1.570
 rgb+1.522
othing+1.509
Neg logit contributions
arth-4.937
heast-4.868
igers-4.862
 seams-4.555
yre-4.517
Token Rodham
Token ID41848
Feature activation-2.53e-01

Pos logit contributions
 rgb+2.114
thood+2.079
cas+2.077
angan+1.995
Cry+1.873
Neg logit contributions
igers-10.885
arth-10.684
heast-10.633
ourney-10.181
 seams-10.069
Token Clinton
Token ID2605
Feature activation-4.31e-01

Pos logit contributions
 rgb+0.551
thood+0.541
cas+0.531
Cry+0.525
angan+0.520
Neg logit contributions
arth-0.962
heast-0.922
igers-0.913
arian-0.864
yre-0.851
TokenSanders
Token ID26747
Feature activation-5.77e-01

Pos logit contributions
thood+1.038
Cry+1.011
cas+1.004
 rgb+1.001
angan+0.988
Neg logit contributions
arth-1.537
heast-1.487
igers-1.471
arian-1.396
erson-1.377
Token:
Token ID25
Feature activation-4.37e-01

Pos logit contributions
thood+1.242
 rgb+1.215
Cry+1.187
angan+1.168
cas+1.167
Neg logit contributions
arth-2.216
heast-2.109
igers-2.082
arian-2.019
erson-1.954
Token '
Token ID705
Feature activation+5.54e-02

Pos logit contributions
thood+0.968
Cry+0.943
angan+0.915
ittal+0.905
 rgb+0.904
Neg logit contributions
arth-1.640
heast-1.637
igers-1.554
arian-1.491
ourney-1.482
Token still
Token ID991
Feature activation-4.59e-01

Pos logit contributions
thood+0.119
 rgb+0.117
cas+0.116
angan+0.115
Cry+0.113
Neg logit contributions
arth-0.135
igers-0.132
heast-0.131
arian-0.123
erson-0.120
Token at
Token ID379
Feature activation+1.37e-01

Pos logit contributions
 rgb+1.240
thood+1.236
cas+1.226
angan+1.205
bus+1.198
Neg logit contributions
arth-1.438
igers-1.437
heast-1.413
arian-1.312
erson-1.297
Token least
Token ID1551
Feature activation-4.07e-01

Pos logit contributions
arth+0.390
heast+0.376
igers+0.374
arian+0.346
erson+0.339
Neg logit contributions
thood-0.429
cas-0.416
angan-0.414
 rgb-0.414
Cry-0.410
Token two
Token ID734
Feature activation-2.35e-01

Pos logit contributions
thood+1.174
 rgb+1.161
cas+1.158
Cry+1.143
angan+1.143
Neg logit contributions
arth-1.223
igers-1.223
heast-1.192
arian-1.103
erson-1.082
Token years
Token ID812
Feature activation-1.11e+00

Pos logit contributions
thood+0.679
 rgb+0.656
cas+0.653
angan+0.650
Cry+0.648
Neg logit contributions
arth-0.727
igers-0.705
heast-0.705
arian-0.650
erson-0.644
Token away
Token ID1497
Feature activation-2.24e+00

Pos logit contributions
thood+2.889
 rgb+2.874
cas+2.807
bus+2.805
beit+2.802
Neg logit contributions
arth-3.563
igers-3.524
heast-3.438
illes-3.194
ordan-3.176
Token,
Token ID11
Feature activation+9.27e-02

Pos logit contributions
thood+5.281
 rgb+5.160
cas+5.122
Cry+5.054
angan+5.010
Neg logit contributions
arth-7.589
heast-7.386
igers-7.340
arian-6.783
erson-6.752
Token it
Token ID340
Feature activation+1.52e-01

Pos logit contributions
arth+0.314
igers+0.302
heast+0.302
arian+0.284
erson+0.278
Neg logit contributions
thood-0.244
 rgb-0.234
cas-0.234
angan-0.233
Cry-0.230
Token seems
Token ID2331
Feature activation-1.12e+00

Pos logit contributions
arth+0.513
igers+0.496
heast+0.495
arian+0.465
erson+0.455
Neg logit contributions
thood-0.396
 rgb-0.384
cas-0.382
angan-0.378
beit-0.374
Token unlikely
Token ID7485
Feature activation+3.25e-01

Pos logit contributions
thood+2.577
cas+2.527
beit+2.515
 rgb+2.514
Cry+2.510
Neg logit contributions
arth-4.022
heast-3.875
igers-3.849
arian-3.631
erson-3.531
Token that
Token ID326
Feature activation+4.47e-01

Pos logit contributions
arth+1.041
igers+1.000
heast+0.998
arian+0.939
erson+0.920
Neg logit contributions
thood-0.915
 rgb-0.876
cas-0.875
angan-0.869
Cry-0.861
Token including
Token ID1390
Feature activation-4.97e-01

Pos logit contributions
thood+0.146
cas+0.141
 rgb+0.141
angan+0.140
Cry+0.139
Neg logit contributions
arth-0.160
heast-0.154
igers-0.154
arian-0.143
erson-0.140
Token clay
Token ID21558
Feature activation-4.50e-01

Pos logit contributions
thood+1.387
cas+1.356
 rgb+1.352
angan+1.344
Cry+1.329
Neg logit contributions
arth-1.574
heast-1.524
igers-1.510
arian-1.411
erson-1.377
Token pot
Token ID1787
Feature activation-8.12e-01

Pos logit contributions
thood+1.194
cas+1.150
 rgb+1.135
angan+1.135
Cry+1.119
Neg logit contributions
arth-1.505
heast-1.460
igers-1.447
arian-1.362
erson-1.328
Tokentery
Token ID11471
Feature activation-8.26e-01

Pos logit contributions
thood+0.684
cas+0.589
 rgb+0.540
angan+0.533
beit+0.507
Neg logit contributions
arth-4.220
heast-4.136
igers-4.104
arian-3.944
erson-3.880
Token,
Token ID11
Feature activation-2.14e-01

Pos logit contributions
thood+2.061
cas+2.000
 rgb+1.981
angan+1.965
Cry+1.943
Neg logit contributions
arth-2.878
heast-2.786
igers-2.756
arian-2.593
erson-2.533
Token sil
Token ID3313
Feature activation-2.24e+00

Pos logit contributions
thood+0.585
cas+0.567
 rgb+0.567
angan+0.562
Cry+0.557
Neg logit contributions
arth-0.700
heast-0.679
igers-0.673
arian-0.631
erson-0.616
Tokenvers
Token ID690
Feature activation-5.68e-01

Pos logit contributions
thood+5.815
cas+5.765
angan+5.689
bus+5.453
beit+5.412
Neg logit contributions
arth-6.890
heast-6.768
igers-6.743
 seams-6.290
 opio-6.242
Tokenmith
Token ID22947
Feature activation-9.23e-01

Pos logit contributions
thood+1.691
angan+1.629
cas+1.629
 rgb+1.612
Cry+1.596
Neg logit contributions
arth-1.719
heast-1.652
igers-1.650
arian-1.529
erson-1.499
Tokening
Token ID278
Feature activation-1.97e-01

Pos logit contributions
thood+2.619
cas+2.556
 rgb+2.551
angan+2.520
beit+2.518
Neg logit contributions
arth-2.801
heast-2.738
igers-2.707
arian-2.488
yre-2.434
Token,
Token ID11
Feature activation-3.76e-01

Pos logit contributions
thood+0.524
cas+0.504
 rgb+0.504
angan+0.500
Cry+0.495
Neg logit contributions
arth-0.660
heast-0.635
igers-0.635
arian-0.596
erson-0.584
Token and
Token ID290
Feature activation-2.63e-02

Pos logit contributions
thood+1.016
cas+0.988
 rgb+0.985
angan+0.979
Cry+0.969
Neg logit contributions
arth-1.231
heast-1.199
igers-1.185
arian-1.112
erson-1.086
Token -
Token ID532
Feature activation-1.90e-01

Pos logit contributions
thood+2.075
 rgb+2.028
cas+2.023
Cry+1.998
angan+1.991
Neg logit contributions
arth-2.208
igers-2.122
heast-2.120
arian-1.974
erson-1.930
Token 1100
Token ID36566
Feature activation-6.39e-01

Pos logit contributions
thood+0.608
 rgb+0.593
cas+0.590
angan+0.586
Cry+0.585
Neg logit contributions
arth-0.531
igers-0.508
heast-0.508
arian-0.468
erson-0.458
Token MHz
Token ID19805
Feature activation-1.01e+00

Pos logit contributions
thood+1.368
cas+1.347
 rgb+1.335
Cry+1.332
angan+1.315
Neg logit contributions
arth-2.443
heast-2.380
igers-2.375
arian-2.235
erson-2.195
Token
Token ID198
Feature activation-7.69e-01

Pos logit contributions
 rgb+2.766
thood+2.756
cas+2.750
Cry+2.739
angan+2.700
Neg logit contributions
arth-3.222
heast-3.118
igers-3.116
arian-2.874
erson-2.806
Token
Token ID198
Feature activation-8.31e-01

Pos logit contributions
Cry+1.774
cas+1.760
 rgb+1.758
bus+1.734
thood+1.670
Neg logit contributions
heast-2.794
arth-2.745
igers-2.725
 opio-2.585
arian-2.470
TokenMemory
Token ID30871
Feature activation-2.24e+00

Pos logit contributions
thood+2.248
Cry+2.236
cas+2.230
angan+2.185
 rgb+2.165
Neg logit contributions
arth-2.671
heast-2.628
igers-2.602
arian-2.408
erson-2.366
Token:
Token ID25
Feature activation-8.75e-02

Pos logit contributions
thood+4.421
Cry+4.333
 rgb+4.308
bus+4.297
angan+4.293
Neg logit contributions
arth-8.495
igers-8.338
heast-8.231
arian-7.819
illes-7.593
Token 2
Token ID362
Feature activation-3.83e-01

Pos logit contributions
thood+0.305
 rgb+0.296
cas+0.296
angan+0.294
Cry+0.293
Neg logit contributions
arth-0.222
igers-0.211
heast-0.210
arian-0.193
erson-0.188
TokenGB
Token ID4579
Feature activation-7.78e-01

Pos logit contributions
thood+0.745
 rgb+0.709
cas+0.706
angan+0.696
Cry+0.691
Neg logit contributions
arth-1.556
igers-1.507
heast-1.506
arian-1.435
erson-1.409
Token GDDR
Token ID50092
Feature activation-3.75e-01

Pos logit contributions
thood+1.560
 rgb+1.526
cas+1.524
Cry+1.504
angan+1.488
Neg logit contributions
arth-3.062
igers-2.992
heast-2.962
arian-2.812
illes-2.764
Token5
Token ID20
Feature activation-3.60e-01

Pos logit contributions
thood+1.478
 rgb+1.432
cas+1.430
angan+1.422
Cry+1.419
Neg logit contributions
arth-0.782
heast-0.741
igers-0.740
arian-0.667
erson-0.641
Token pro
Token ID386
Feature activation-3.37e-01

Pos logit contributions
thood+2.642
cas+2.539
 rgb+2.533
angan+2.498
Cry+2.480
Neg logit contributions
arth-3.212
heast-3.091
igers-3.084
arian-2.860
erson-2.814
Token team
Token ID1074
Feature activation+5.67e-01

Pos logit contributions
thood+1.035
cas+0.998
 rgb+0.994
angan+0.987
Cry+0.979
Neg logit contributions
arth-0.994
igers-0.950
heast-0.949
arian-0.888
erson-0.866
Token in
Token ID287
Feature activation-2.69e-01

Pos logit contributions
arth+1.797
igers+1.724
heast+1.720
arian+1.622
erson+1.593
Neg logit contributions
thood-1.610
 rgb-1.547
cas-1.542
angan-1.538
Cry-1.525
Token 1946
Token ID22717
Feature activation-1.15e+00

Pos logit contributions
thood+1.027
 rgb+1.002
cas+0.994
angan+0.988
Cry+0.983
Neg logit contributions
arth-0.587
heast-0.559
igers-0.553
arian-0.505
erson-0.477
Token (
Token ID357
Feature activation-3.80e-01

Pos logit contributions
thood+2.892
cas+2.737
 rgb+2.713
angan+2.713
Cry+2.664
Neg logit contributions
arth-3.961
igers-3.834
heast-3.818
arian-3.594
erson-3.508
TokenMic
Token ID25437
Feature activation-2.24e+00

Pos logit contributions
thood+1.159
cas+1.139
Cry+1.118
 rgb+1.116
angan+1.111
Neg logit contributions
arth-1.104
heast-1.063
igers-1.059
arian-0.992
erson-0.965
Tokenkey
Token ID2539
Feature activation-2.83e-01

Pos logit contributions
thood+5.317
cas+5.268
 rgb+5.053
bus+4.864
Cry+4.811
Neg logit contributions
arth-7.399
heast-7.231
igers-7.229
 seams-6.790
arian-6.658
Token Mc
Token ID1982
Feature activation-4.35e-01

Pos logit contributions
thood+0.795
cas+0.765
 rgb+0.764
angan+0.754
Cry+0.754
Neg logit contributions
arth-0.905
igers-0.869
heast-0.868
arian-0.815
erson-0.793
TokenBride
Token ID47148
Feature activation-9.46e-02

Pos logit contributions
thood+1.133
cas+1.084
 rgb+1.084
angan+1.075
Cry+1.068
Neg logit contributions
arth-1.483
igers-1.428
heast-1.425
arian-1.343
erson-1.318
Token
Token ID447
Feature activation-5.47e-02

Pos logit contributions
thood+0.251
 rgb+0.241
cas+0.240
angan+0.239
Cry+0.237
Neg logit contributions
arth-0.318
igers-0.306
heast-0.305
arian-0.288
erson-0.282
Token
Token ID247
Feature activation+4.76e-02

Pos logit contributions
thood+0.127
 rgb+0.122
cas+0.121
angan+0.120
Cry+0.118
Neg logit contributions
arth-0.203
heast-0.195
igers-0.195
arian-0.185
erson-0.181
Token shortly
Token ID8972
Feature activation+6.81e-01

Pos logit contributions
thood+0.510
cas+0.490
 rgb+0.486
angan+0.484
Cry+0.481
Neg logit contributions
arth-0.554
igers-0.539
heast-0.534
arian-0.501
erson-0.487
Token thereafter
Token ID19547
Feature activation-3.05e-01

Pos logit contributions
arth+1.932
igers+1.840
heast+1.839
arian+1.716
erson+1.680
Neg logit contributions
thood-2.150
 rgb-2.078
cas-2.067
angan-2.064
Cry-2.047
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
thood+0.775
cas+0.741
 rgb+0.738
angan+0.733
Cry+0.727
Neg logit contributions
arth-1.063
igers-1.027
heast-1.024
arian-0.963
erson-0.946
Token in
Token ID287
Feature activation-1.81e-01

Pos logit contributions
thood+0.031
cas+0.030
 rgb+0.030
angan+0.030
Cry+0.030
Neg logit contributions
arth-0.038
heast-0.037
igers-0.036
arian-0.034
erson-0.033
Token a
Token ID257
Feature activation+1.36e-01

Pos logit contributions
thood+0.507
cas+0.493
angan+0.490
 rgb+0.490
Cry+0.486
Neg logit contributions
arth-0.575
igers-0.559
heast-0.557
arian-0.519
erson-0.508
Token waste
Token ID7030
Feature activation-2.22e+00

Pos logit contributions
arth+0.425
igers+0.410
heast+0.407
arian+0.381
erson+0.373
Neg logit contributions
thood-0.393
cas-0.382
 rgb-0.381
angan-0.379
Cry-0.376
Token of
Token ID286
Feature activation-1.07e+00

Pos logit contributions
thood+5.887
cas+5.771
Cry+5.616
 rgb+5.606
angan+5.598
Neg logit contributions
arth-7.184
heast-6.934
igers-6.906
arian-6.435
erson-6.270
Token system
Token ID1080
Feature activation+3.28e-01

Pos logit contributions
 rgb+3.046
cas+3.038
thood+3.032
angan+3.003
beit+2.991
Neg logit contributions
arth-3.191
igers-3.156
heast-3.143
arian-2.840
illes-2.783
Token resources
Token ID4133
Feature activation-5.88e-01

Pos logit contributions
arth+1.033
heast+0.983
igers+0.983
arian+0.933
erson+0.915
Neg logit contributions
thood-0.947
 rgb-0.903
cas-0.901
angan-0.899
Cry-0.888
Token
Token ID1399
Feature activation-4.21e-01

Pos logit contributions
thood+1.458
 rgb+1.404
cas+1.403
angan+1.387
Cry+1.377
Neg logit contributions
arth-2.067
heast-1.994
igers-1.992
arian-1.867
erson-1.828
Token All
Token ID1439
Feature activation+6.04e-01

Pos logit contributions
thood+1.225
cas+1.203
 rgb+1.185
Cry+1.179
angan+1.167
Neg logit contributions
arth-1.281
heast-1.248
igers-1.240
arian-1.153
illes-1.120
Token MORE
Token ID12011
Feature activation-7.91e-01

Pos logit contributions
arth+0.601
heast+0.572
igers+0.571
arian+0.528
erson+0.517
Neg logit contributions
thood-0.698
 rgb-0.677
cas-0.672
angan-0.671
Cry-0.669
Token and
Token ID290
Feature activation-6.67e-01

Pos logit contributions
thood+2.085
 rgb+1.994
cas+1.982
angan+1.958
Cry+1.958
Neg logit contributions
arth-2.669
igers-2.582
heast-2.574
arian-2.394
erson-2.343
Token Hillary
Token ID5073
Feature activation-1.01e+00

Pos logit contributions
thood+1.699
 rgb+1.666
cas+1.622
angan+1.610
Cry+1.607
Neg logit contributions
arth-2.282
igers-2.236
heast-2.223
arian-2.042
illes-2.015
Token Clinton
Token ID2605
Feature activation-3.96e-01

Pos logit contributions
thood+2.509
 rgb+2.405
cas+2.400
Cry+2.381
angan+2.380
Neg logit contributions
arth-3.515
heast-3.404
igers-3.401
arian-3.179
erson-3.127
Token Hillary
Token ID5073
Feature activation-8.29e-01

Pos logit contributions
thood+1.042
 rgb+0.998
cas+0.995
angan+0.989
Cry+0.981
Neg logit contributions
arth-1.340
igers-1.292
heast-1.288
arian-1.213
erson-1.187
Token Diane
Token ID26542
Feature activation-2.21e+00

Pos logit contributions
angan+1.239
Cry+1.215
thood+1.200
 rgb+1.169
othing+1.143
Neg logit contributions
arth-3.687
igers-3.581
heast-3.580
yre-3.355
 seams-3.354
Token Rodham
Token ID41848
Feature activation-2.27e-01

Pos logit contributions
thood+2.395
 rgb+2.343
cas+2.163
angan+2.102
Cry+2.041
Neg logit contributions
igers-10.525
arth-10.447
heast-10.332
ourney-9.798
olls-9.733
Token Clinton
Token ID2605
Feature activation-4.07e-01

Pos logit contributions
 rgb+0.501
thood+0.497
cas+0.485
Cry+0.484
angan+0.482
Neg logit contributions
arth-0.857
heast-0.820
igers-0.810
arian-0.769
yre-0.754
TokenSanders
Token ID26747
Feature activation-6.40e-01

Pos logit contributions
thood+0.808
Cry+0.772
cas+0.770
 rgb+0.768
angan+0.757
Neg logit contributions
arth-1.631
heast-1.579
igers-1.569
arian-1.499
erson-1.476
Token:
Token ID25
Feature activation-3.47e-01

Pos logit contributions
thood+1.350
 rgb+1.333
Cry+1.295
cas+1.275
angan+1.273
Neg logit contributions
arth-2.496
heast-2.355
igers-2.342
arian-2.269
yre-2.176
Token '
Token ID705
Feature activation-4.01e-02

Pos logit contributions
thood+0.785
Cry+0.764
 rgb+0.747
angan+0.744
beit+0.738
Neg logit contributions
arth-1.294
heast-1.283
igers-1.235
arian-1.180
 seams-1.154
Token 8
Token ID807
Feature activation-2.08e-01

Pos logit contributions
cas+0.753
Cry+0.750
 rgb+0.746
thood+0.741
 Runner+0.707
Neg logit contributions
arth-0.687
igers-0.668
heast-0.660
erson-0.593
illes-0.587
Token election
Token ID3071
Feature activation-3.47e-01

Pos logit contributions
thood+0.478
cas+0.468
 rgb+0.464
Cry+0.456
angan+0.456
Neg logit contributions
arth-0.764
igers-0.740
heast-0.737
arian-0.694
erson-0.688
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
thood+0.821
cas+0.795
 rgb+0.789
angan+0.781
Cry+0.777
Neg logit contributions
arth-1.258
igers-1.213
heast-1.209
arian-1.134
erson-1.118
Token
Token ID198
Feature activation-9.57e-02

Pos logit contributions
thood+0.388
 rgb+0.373
cas+0.373
angan+0.371
Cry+0.368
Neg logit contributions
arth-0.383
igers-0.367
heast-0.366
arian-0.342
erson-0.335
Token
Token ID198
Feature activation+4.02e-02

Pos logit contributions
cas+0.248
 rgb+0.248
thood+0.247
Cry+0.246
angan+0.240
Neg logit contributions
arth-0.320
heast-0.316
igers-0.313
arian-0.286
 seams-0.282
TokenADVERTISEMENT
Token ID19053
Feature activation-2.20e+00

Pos logit contributions
arth+0.156
igers+0.151
heast+0.151
arian+0.143
erson+0.141
Neg logit contributions
thood-0.085
cas-0.081
 rgb-0.081
angan-0.080
Cry-0.080
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
Cry+4.395
 rgb+4.297
cas+4.205
bus+4.139
cry+4.069
Neg logit contributions
heast-8.065
igers-8.063
arth-8.021
 opio-8.011
 seams-7.688
Token
Token ID198
Feature activation-5.77e-02

Pos logit contributions
cas+0.430
 rgb+0.428
thood+0.426
Cry+0.426
angan+0.415
Neg logit contributions
arth-0.563
heast-0.559
igers-0.553
arian-0.505
 opio-0.498
TokenClinton
Token ID16549
Feature activation-2.53e-02

Pos logit contributions
thood+0.160
cas+0.155
Cry+0.155
 rgb+0.153
angan+0.153
Neg logit contributions
arth-0.186
igers-0.180
heast-0.179
arian-0.168
erson-0.164
Token mentioned
Token ID4750
Feature activation-1.05e-01

Pos logit contributions
thood+0.073
 rgb+0.071
cas+0.071
angan+0.070
Cry+0.069
Neg logit contributions
arth-0.079
igers-0.076
heast-0.076
arian-0.070
erson-0.069
Token the
Token ID262
Feature activation+3.87e-01

Pos logit contributions
thood+0.291
 rgb+0.284
cas+0.282
angan+0.279
Cry+0.279
Neg logit contributions
arth-0.339
igers-0.326
heast-0.325
arian-0.303
erson-0.295
Token relations
Token ID2316
Feature activation+1.35e-01

Pos logit contributions
thood+0.298
cas+0.287
 rgb+0.284
angan+0.283
Cry+0.281
Neg logit contributions
arth-0.274
igers-0.266
heast-0.263
arian-0.240
erson-0.237
Token
Token ID447
Feature activation+1.40e-01

Pos logit contributions
arth+0.441
igers+0.424
heast+0.423
arian+0.399
erson+0.392
Neg logit contributions
thood-0.369
 rgb-0.353
cas-0.352
angan-0.350
Cry-0.348
Token
Token ID251
Feature activation+2.45e-01

Pos logit contributions
arth+0.466
igers+0.448
heast+0.445
arian+0.423
erson+0.415
Neg logit contributions
thood-0.375
cas-0.359
angan-0.358
 rgb-0.357
Cry-0.357
Token.
Token ID13
Feature activation+2.47e-01

Pos logit contributions
arth+0.785
igers+0.753
heast+0.751
arian+0.706
erson+0.692
Neg logit contributions
thood-0.690
 rgb-0.661
cas-0.661
angan-0.657
Cry-0.651
Token<|endoftext|>
Token ID50256
Feature activation-7.38e-01

Pos logit contributions
arth+0.711
heast+0.683
igers+0.681
arian+0.642
erson+0.630
Neg logit contributions
thood-0.770
 rgb-0.735
cas-0.734
angan-0.731
Cry-0.719
TokenMic
Token ID25437
Feature activation-2.19e+00

Pos logit contributions
thood+2.087
cas+2.039
Cry+2.032
angan+2.004
 rgb+1.986
Neg logit contributions
arth-2.308
heast-2.246
igers-2.234
arian-2.079
erson-2.047
Token published
Token ID3199
Feature activation-6.22e-02

Pos logit contributions
thood+5.790
cas+5.698
 rgb+5.585
bus+5.428
Cry+5.422
Neg logit contributions
arth-6.665
heast-6.588
igers-6.581
 seams-5.978
arian-5.938
Token a
Token ID257
Feature activation+1.42e-01

Pos logit contributions
thood+0.187
 rgb+0.182
cas+0.180
angan+0.179
Cry+0.178
Neg logit contributions
arth-0.187
heast-0.180
igers-0.180
arian-0.165
erson-0.163
Token report
Token ID989
Feature activation+4.73e-02

Pos logit contributions
arth+0.445
igers+0.426
heast+0.426
arian+0.397
erson+0.389
Neg logit contributions
thood-0.410
 rgb-0.401
cas-0.399
angan-0.394
Cry-0.391
Token last
Token ID938
Feature activation+5.14e-01

Pos logit contributions
arth+0.150
igers+0.144
heast+0.144
arian+0.133
erson+0.131
Neg logit contributions
thood-0.135
 rgb-0.131
cas-0.131
angan-0.129
Cry-0.128
Token week
Token ID1285
Feature activation+1.41e-01

Pos logit contributions
arth+1.214
igers+1.148
heast+1.144
arian+1.049
erson+1.020
Neg logit contributions
thood-1.882
 rgb-1.824
cas-1.822
angan-1.813
Cry-1.801
Token him
Token ID683
Feature activation-7.65e-02

Pos logit contributions
arth+1.018
igers+0.983
heast+0.982
arian+0.935
erson+0.920
Neg logit contributions
thood-0.645
 rgb-0.607
cas-0.606
angan-0.603
Cry-0.596
Token,
Token ID11
Feature activation-3.28e-01

Pos logit contributions
thood+0.196
cas+0.191
 rgb+0.190
angan+0.187
Cry+0.187
Neg logit contributions
arth-0.262
igers-0.253
heast-0.252
arian-0.236
erson-0.231
Token leading
Token ID3756
Feature activation-7.82e-01

Pos logit contributions
thood+0.777
 rgb+0.756
cas+0.751
Cry+0.736
angan+0.735
Neg logit contributions
arth-1.194
igers-1.150
heast-1.146
arian-1.083
erson-1.054
Token to
Token ID284
Feature activation-3.20e-01

Pos logit contributions
thood+1.884
 rgb+1.805
cas+1.799
angan+1.784
Cry+1.767
Neg logit contributions
arth-2.816
igers-2.710
heast-2.699
arian-2.559
erson-2.502
Token his
Token ID465
Feature activation+6.17e-02

Pos logit contributions
thood+0.913
cas+0.895
 rgb+0.890
angan+0.879
Cry+0.869
Neg logit contributions
arth-1.008
heast-0.968
igers-0.968
arian-0.899
erson-0.874
Token death
Token ID1918
Feature activation-2.18e+00

Pos logit contributions
arth+0.155
igers+0.148
heast+0.147
arian+0.135
erson+0.131
Neg logit contributions
thood-0.216
cas-0.210
 rgb-0.210
angan-0.209
Cry-0.207
Token,
Token ID11
Feature activation-7.18e-01

Pos logit contributions
thood+5.188
cas+5.155
 rgb+4.976
bus+4.974
Cry+4.964
Neg logit contributions
arth-7.314
igers-6.896
heast-6.780
arian-6.438
ordan-6.386
Token police
Token ID1644
Feature activation-4.35e-02

Pos logit contributions
thood+1.759
 rgb+1.714
cas+1.697
angan+1.652
Cry+1.645
Neg logit contributions
arth-2.556
igers-2.454
heast-2.442
arian-2.316
yre-2.262
Token Chief
Token ID5953
Feature activation-5.20e-01

Pos logit contributions
thood+0.131
 rgb+0.126
cas+0.126
angan+0.125
Cry+0.124
Neg logit contributions
arth-0.132
igers-0.126
heast-0.126
arian-0.117
erson-0.115
Token Frank
Token ID5278
Feature activation-3.09e-01

Pos logit contributions
thood+1.391
 rgb+1.347
cas+1.345
Cry+1.326
angan+1.322
Neg logit contributions
arth-1.722
igers-1.662
heast-1.657
arian-1.544
erson-1.512
Token Stra
Token ID15195
Feature activation+1.08e+00

Pos logit contributions
thood+0.887
cas+0.858
 rgb+0.854
angan+0.852
Cry+0.844
Neg logit contributions
arth-0.970
igers-0.931
heast-0.930
arian-0.867
erson-0.847
Tokenmail
Token ID4529
Feature activation+5.90e-02

Pos logit contributions
thood+0.526
 rgb+0.508
angan+0.504
cas+0.504
Cry+0.497
Neg logit contributions
arth-0.431
igers-0.410
heast-0.407
arian-0.381
erson-0.370
Token this
Token ID428
Feature activation+2.79e-01

Pos logit contributions
arth+0.168
heast+0.163
igers+0.163
arian+0.148
erson+0.145
Neg logit contributions
thood-0.185
 rgb-0.181
cas-0.180
angan-0.179
Cry-0.176
Token to
Token ID284
Feature activation+2.92e-01

Pos logit contributions
arth+0.943
heast+0.915
igers+0.912
arian+0.855
erson+0.836
Neg logit contributions
thood-0.731
 rgb-0.708
cas-0.703
angan-0.695
Cry-0.693
Token a
Token ID257
Feature activation-2.02e-02

Pos logit contributions
arth+0.830
igers+0.792
heast+0.789
arian+0.737
erson+0.720
Neg logit contributions
thood-0.933
cas-0.897
 rgb-0.897
angan-0.892
Cry-0.885
Token friend
Token ID1545
Feature activation-4.14e-01

Pos logit contributions
thood+0.062
 rgb+0.061
cas+0.060
angan+0.060
Cry+0.060
Neg logit contributions
arth-0.060
igers-0.057
heast-0.057
arian-0.053
 seams-0.051
Token Print
Token ID12578
Feature activation-2.17e+00

Pos logit contributions
thood+0.918
 rgb+0.866
cas+0.865
angan+0.862
Cry+0.850
Neg logit contributions
arth-1.578
igers-1.526
heast-1.522
arian-1.448
erson-1.423
Tokenable
Token ID540
Feature activation+2.87e-01

Pos logit contributions
 Carbuncle+5.262
thood+5.185
cas+4.966
 rgb+4.868
beit+4.852
Neg logit contributions
arth-7.554
heast-7.462
igers-7.246
ues-6.859
olls-6.764
Token version
Token ID2196
Feature activation+7.84e-01

Pos logit contributions
arth+0.706
heast+0.673
igers+0.671
arian+0.616
erson+0.596
Neg logit contributions
thood-1.024
 rgb-0.991
cas-0.989
angan-0.978
Cry-0.977
Token<|endoftext|>
Token ID50256
Feature activation-6.95e-01

Pos logit contributions
arth+2.523
igers+2.403
heast+2.343
arian+2.277
erson+2.255
Neg logit contributions
thood-2.182
 rgb-2.107
cas-2.105
angan-2.100
Cry-2.075
TokenA
Token ID32
Feature activation+7.37e-02

Pos logit contributions
thood+1.964
cas+1.916
Cry+1.910
angan+1.884
 rgb+1.870
Neg logit contributions
arth-2.174
heast-2.116
igers-2.104
arian-1.959
erson-1.928
Token university
Token ID6403
Feature activation-3.42e-01

Pos logit contributions
arth+0.226
igers+0.217
heast+0.216
arian+0.202
erson+0.198
Neg logit contributions
thood-0.218
 rgb-0.209
cas-0.209
angan-0.208
Cry-0.206
Tokenmail
Token ID4529
Feature activation+5.04e-02

Pos logit contributions
thood+0.542
 rgb+0.522
angan+0.519
cas+0.517
beit+0.512
Neg logit contributions
arth-0.432
igers-0.409
heast-0.405
arian-0.381
erson-0.369
Token this
Token ID428
Feature activation+1.97e-01

Pos logit contributions
arth+0.143
heast+0.138
igers+0.138
arian+0.125
erson+0.123
Neg logit contributions
thood-0.160
 rgb-0.156
cas-0.155
angan-0.154
Cry-0.152
Token to
Token ID284
Feature activation+2.35e-01

Pos logit contributions
arth+0.676
heast+0.660
igers+0.657
arian+0.616
illes+0.602
Neg logit contributions
thood-0.500
 rgb-0.489
cas-0.481
Cry-0.476
angan-0.474
Token a
Token ID257
Feature activation-1.81e-02

Pos logit contributions
arth+0.677
igers+0.648
heast+0.647
arian+0.602
erson+0.589
Neg logit contributions
thood-0.740
 rgb-0.714
cas-0.712
angan-0.709
Cry-0.703
Token friend
Token ID1545
Feature activation-4.82e-01

Pos logit contributions
thood+0.055
 rgb+0.054
cas+0.053
angan+0.053
Cry+0.053
Neg logit contributions
arth-0.055
igers-0.052
heast-0.052
arian-0.048
 seams-0.046
Token Print
Token ID12578
Feature activation-2.16e+00

Pos logit contributions
thood+1.028
 rgb+0.976
cas+0.974
angan+0.963
Cry+0.953
Neg logit contributions
arth-1.875
igers-1.812
heast-1.810
arian-1.718
erson-1.691
Tokenable
Token ID540
Feature activation+2.43e-01

Pos logit contributions
 Carbuncle+5.267
thood+5.180
cas+4.906
 rgb+4.898
beit+4.867
Neg logit contributions
arth-7.537
heast-7.416
igers-7.219
ues-6.863
olls-6.788
Token version
Token ID2196
Feature activation+8.13e-01

Pos logit contributions
arth+0.613
heast+0.588
igers+0.582
arian+0.538
erson+0.518
Neg logit contributions
thood-0.851
 rgb-0.824
cas-0.822
Cry-0.811
angan-0.807
Token<|endoftext|>
Token ID50256
Feature activation-7.42e-01

Pos logit contributions
arth+2.579
igers+2.450
heast+2.386
arian+2.324
erson+2.310
Neg logit contributions
thood-2.286
cas-2.214
 rgb-2.211
angan-2.210
beit-2.188
TokenRob
Token ID14350
Feature activation-8.91e-01

Pos logit contributions
thood+2.097
cas+2.048
Cry+2.041
angan+2.013
 rgb+1.995
Neg logit contributions
arth-2.318
heast-2.257
igers-2.244
arian-2.089
erson-2.057
Token C
Token ID327
Feature activation-4.00e-01

Pos logit contributions
thood+2.893
cas+2.829
angan+2.817
 rgb+2.793
Cry+2.789
Neg logit contributions
arth-2.352
heast-2.288
igers-2.268
arian-2.119
illes-2.033
Token not
Token ID407
Feature activation+1.56e-01

Pos logit contributions
thood+0.809
cas+0.778
 rgb+0.773
angan+0.767
Cry+0.759
Neg logit contributions
arth-1.128
heast-1.095
igers-1.090
arian-1.020
erson-1.003
Token a
Token ID257
Feature activation+1.32e-01

Pos logit contributions
arth+0.476
igers+0.457
heast+0.456
arian+0.425
erson+0.417
Neg logit contributions
thood-0.463
cas-0.446
 rgb-0.443
angan-0.438
Cry-0.437
Token fight
Token ID1907
Feature activation-2.96e-03

Pos logit contributions
arth+0.425
igers+0.410
heast+0.409
arian+0.382
erson+0.374
Neg logit contributions
thood-0.370
cas-0.357
 rgb-0.355
angan-0.352
Cry-0.350
Token to
Token ID284
Feature activation-4.97e-01

Pos logit contributions
thood+0.008
 rgb+0.007
angan+0.007
cas+0.007
Cry+0.007
Neg logit contributions
arth-0.010
igers-0.010
heast-0.010
arian-0.009
erson-0.009
Token the
Token ID262
Feature activation-1.43e-01

Pos logit contributions
thood+1.222
cas+1.165
 rgb+1.159
Cry+1.145
angan+1.142
Neg logit contributions
arth-1.765
heast-1.722
igers-1.698
arian-1.609
erson-1.575
Token death
Token ID1918
Feature activation-2.15e+00

Pos logit contributions
thood+0.449
 rgb+0.437
cas+0.436
Cry+0.430
angan+0.430
Neg logit contributions
arth-0.412
heast-0.392
igers-0.391
arian-0.360
erson-0.355
Token.
Token ID13
Feature activation+8.61e-02

Pos logit contributions
thood+4.407
cas+4.354
angan+4.137
beit+4.096
 rgb+4.089
Neg logit contributions
arth-7.972
heast-7.968
igers-7.785
arian-7.167
erson-7.155
Token Which
Token ID9022
Feature activation-3.66e-01

Pos logit contributions
arth+0.251
igers+0.243
heast+0.242
arian+0.221
erson+0.219
Neg logit contributions
thood-0.267
cas-0.258
 rgb-0.257
Cry-0.257
angan-0.252
Token means
Token ID1724
Feature activation-5.14e-01

Pos logit contributions
thood+0.928
cas+0.907
 rgb+0.902
Cry+0.897
angan+0.884
Neg logit contributions
arth-1.263
igers-1.221
heast-1.213
arian-1.126
erson-1.119
Token that
Token ID326
Feature activation+1.21e-01

Pos logit contributions
thood+1.373
cas+1.329
 rgb+1.322
Cry+1.312
angan+1.292
Neg logit contributions
arth-1.692
igers-1.642
heast-1.639
arian-1.513
erson-1.496
Token anyone
Token ID2687
Feature activation-7.53e-01

Pos logit contributions
arth+0.390
igers+0.378
heast+0.376
arian+0.351
erson+0.345
Neg logit contributions
thood-0.335
cas-0.323
 rgb-0.322
Cry-0.318
angan-0.317
Token species
Token ID4693
Feature activation+1.47e+00

Pos logit contributions
arth+0.548
heast+0.526
igers+0.525
arian+0.492
erson+0.483
Neg logit contributions
thood-0.513
 rgb-0.494
cas-0.493
angan-0.491
Cry-0.487
Token in
Token ID287
Feature activation+5.78e-01

Pos logit contributions
arth+4.482
igers+4.288
heast+4.265
arian+4.068
ues+3.898
Neg logit contributions
thood-4.264
 rgb-4.128
cas-4.124
angan-4.062
beit-4.017
Token its
Token ID663
Feature activation+5.59e-01

Pos logit contributions
arth+1.702
igers+1.629
heast+1.626
arian+1.517
erson+1.485
Neg logit contributions
thood-1.777
 rgb-1.712
cas-1.708
angan-1.702
Cry-1.688
Token episode
Token ID4471
Feature activation+6.45e-01

Pos logit contributions
arth+1.718
igers+1.647
heast+1.641
arian+1.532
erson+1.508
Neg logit contributions
thood-1.646
 rgb-1.597
cas-1.590
angan-1.587
Cry-1.572
Token "
Token ID366
Feature activation+3.57e-01

Pos logit contributions
arth+1.959
igers+1.875
heast+1.868
arian+1.755
erson+1.713
Neg logit contributions
thood-1.923
 rgb-1.849
cas-1.849
angan-1.835
Cry-1.817
TokenSil
Token ID15086
Feature activation-2.15e+00

Pos logit contributions
arth+1.234
igers+1.188
heast+1.182
arian+1.118
erson+1.097
Neg logit contributions
thood-0.917
 rgb-0.878
cas-0.873
angan-0.869
Cry-0.854
Tokenent
Token ID298
Feature activation-1.03e+00

Pos logit contributions
thood+8.133
cas+7.943
angan+7.928
beit+7.812
bus+7.732
Neg logit contributions
arth-3.980
heast-3.910
igers-3.803
 seams-3.584
olls-3.387
Token Ro
Token ID5564
Feature activation-8.39e-01

Pos logit contributions
thood+2.922
Cry+2.784
cas+2.781
angan+2.756
 rgb+2.742
Neg logit contributions
arth-3.147
heast-3.060
igers-2.992
arian-2.811
erson-2.796
Tokenar
Token ID283
Feature activation+3.89e-01

Pos logit contributions
thood+2.673
cas+2.606
angan+2.603
 rgb+2.582
Cry+2.570
Neg logit contributions
arth-2.265
igers-2.193
heast-2.182
arian-2.012
 seams-1.989
Token:
Token ID25
Feature activation+3.20e-01

Pos logit contributions
arth+1.221
igers+1.173
heast+1.165
arian+1.100
erson+1.075
Neg logit contributions
thood-1.118
 rgb-1.081
cas-1.077
angan-1.069
Cry-1.056
Token Search
Token ID11140
Feature activation+2.02e-01

Pos logit contributions
arth+0.988
igers+0.947
heast+0.944
arian+0.885
erson+0.867
Neg logit contributions
thood-0.942
 rgb-0.905
cas-0.904
angan-0.899
Cry-0.891
Token '
Token ID705
Feature activation+2.88e-01

Pos logit contributions
arth+0.453
heast+0.425
igers+0.421
arian+0.396
erson+0.390
Neg logit contributions
thood-0.629
cas-0.602
 rgb-0.602
angan-0.593
Cry-0.588
TokenCongratulations
Token ID45048
Feature activation-1.50e+00

Pos logit contributions
arth+0.953
igers+0.917
heast+0.916
arian+0.862
erson+0.845
Neg logit contributions
thood-0.781
cas-0.748
 rgb-0.746
angan-0.742
Cry-0.738
Token,
Token ID11
Feature activation-7.08e-01

Pos logit contributions
thood+3.610
 rgb+3.508
cas+3.467
Cry+3.437
angan+3.402
Neg logit contributions
arth-5.265
heast-5.103
igers-5.100
arian-4.722
erson-4.680
Token you
Token ID345
Feature activation-6.88e-01

Pos logit contributions
thood+1.691
 rgb+1.653
cas+1.615
Cry+1.610
angan+1.601
Neg logit contributions
arth-2.526
heast-2.442
igers-2.437
arian-2.272
illes-2.230
Token have
Token ID423
Feature activation-3.84e-01

Pos logit contributions
thood+1.667
 rgb+1.602
cas+1.587
angan+1.548
Cry+1.543
Neg logit contributions
arth-2.462
igers-2.382
heast-2.371
arian-2.217
ues-2.179
Token finished
Token ID5201
Feature activation-2.14e+00

Pos logit contributions
thood+1.108
 rgb+1.086
cas+1.061
angan+1.055
Cry+1.047
Neg logit contributions
arth-1.199
igers-1.153
heast-1.147
arian-1.057
erson-1.038
Token the
Token ID262
Feature activation-6.57e-01

Pos logit contributions
 rgb+5.242
thood+5.228
cas+5.049
beit+4.910
angan+4.881
Neg logit contributions
arth-7.076
heast-6.885
igers-6.876
arian-6.165
ordan-6.140
Token initiation
Token ID30122
Feature activation-1.79e-01

Pos logit contributions
thood+1.768
 rgb+1.726
angan+1.697
cas+1.685
Cry+1.670
Neg logit contributions
arth-2.144
heast-2.093
igers-2.070
arian-1.915
erson-1.887
Token ceremony
Token ID10542
Feature activation-1.29e-01

Pos logit contributions
thood+0.522
 rgb+0.504
cas+0.502
angan+0.499
Cry+0.496
Neg logit contributions
arth-0.552
igers-0.532
heast-0.531
arian-0.491
erson-0.484
Token,
Token ID11
Feature activation-4.22e-01

Pos logit contributions
thood+0.343
 rgb+0.329
cas+0.329
angan+0.326
Cry+0.323
Neg logit contributions
arth-0.431
igers-0.415
heast-0.414
arian-0.388
erson-0.382
Token and
Token ID290
Feature activation+1.71e-01

Pos logit contributions
thood+1.070
 rgb+1.037
cas+1.029
angan+1.023
Cry+1.013
Neg logit contributions
arth-1.459
heast-1.412
igers-1.407
arian-1.309
illes-1.285
Token the
Token ID262
Feature activation+2.81e-01

Pos logit contributions
arth+0.404
igers+0.386
heast+0.385
arian+0.358
erson+0.349
Neg logit contributions
thood-0.443
 rgb-0.427
cas-0.426
angan-0.424
Cry-0.419
Token Atlanta
Token ID9371
Feature activation-3.00e-01

Pos logit contributions
arth+0.875
igers+0.837
heast+0.834
arian+0.783
erson+0.766
Neg logit contributions
thood-0.819
 rgb-0.795
cas-0.788
angan-0.783
Cry-0.777
Token Journal
Token ID4913
Feature activation+4.89e-01

Pos logit contributions
thood+0.853
cas+0.814
 rgb+0.814
angan+0.811
Cry+0.803
Neg logit contributions
arth-0.957
igers-0.920
heast-0.919
arian-0.864
erson-0.845
Token-
Token ID12
Feature activation+7.96e-01

Pos logit contributions
arth+1.687
igers+1.632
heast+1.619
arian+1.545
erson+1.519
Neg logit contributions
thood-1.262
 rgb-1.191
angan-1.186
cas-1.186
Cry-1.169
TokenConst
Token ID34184
Feature activation+1.43e+00

Pos logit contributions
arth+2.859
igers+2.765
heast+2.751
arian+2.610
erson+2.567
Neg logit contributions
thood-1.943
 rgb-1.837
cas-1.830
angan-1.822
Cry-1.796
Tokenitution
Token ID2738
Feature activation+2.12e+00

Pos logit contributions
arth+3.537
igers+3.403
heast+3.360
arian+3.133
erson+3.033
Neg logit contributions
thood-5.054
 rgb-4.920
cas-4.887
angan-4.853
Cry-4.848
Token's
Token ID338
Feature activation+2.48e-01

Pos logit contributions
igers+5.588
arth+5.566
arian+5.454
heast+5.370
erson+5.159
Neg logit contributions
thood-6.483
cas-6.206
angan-6.202
 rgb-6.167
Cry-6.153
Token published
Token ID3199
Feature activation+8.26e-01

Pos logit contributions
arth+0.736
heast+0.704
igers+0.704
arian+0.657
erson+0.641
Neg logit contributions
thood-0.757
 rgb-0.733
cas-0.731
angan-0.726
Cry-0.719
Token scouting
Token ID27088
Feature activation+5.99e-01

Pos logit contributions
arth+2.387
igers+2.283
heast+2.270
arian+2.126
erson+2.076
Neg logit contributions
thood-2.591
 rgb-2.489
cas-2.487
angan-2.478
Cry-2.457
Token report
Token ID989
Feature activation+1.82e-02

Pos logit contributions
arth+1.349
igers+1.272
heast+1.267
arian+1.157
erson+1.124
Neg logit contributions
thood-2.258
 rgb-2.188
cas-2.186
angan-2.177
Cry-2.163
Token on
Token ID319
Feature activation+3.19e-01

Pos logit contributions
arth+0.059
heast+0.057
igers+0.057
arian+0.053
erson+0.052
Neg logit contributions
thood-0.050
 rgb-0.048
cas-0.048
angan-0.048
Cry-0.047
Token leaving
Token ID4305
Feature activation-1.09e-01

Pos logit contributions
thood+0.044
cas+0.043
 rgb+0.043
angan+0.042
Cry+0.042
Neg logit contributions
arth-0.053
igers-0.051
heast-0.051
arian-0.048
erson-0.047
Token Mr
Token ID1770
Feature activation+1.69e-01

Pos logit contributions
thood+0.305
 rgb+0.299
cas+0.298
angan+0.294
Cry+0.291
Neg logit contributions
arth-0.351
heast-0.336
igers-0.335
arian-0.313
erson-0.306
Token.
Token ID13
Feature activation-3.68e-01

Pos logit contributions
arth+0.568
igers+0.548
heast+0.544
arian+0.521
erson+0.508
Neg logit contributions
thood-0.456
 rgb-0.435
cas-0.431
Cry-0.427
beit-0.427
Token Sc
Token ID1446
Feature activation+6.57e-01

Pos logit contributions
thood+1.020
 rgb+0.981
cas+0.977
angan+0.973
Cry+0.964
Neg logit contributions
arth-1.194
igers-1.147
heast-1.146
arian-1.073
erson-1.052
Tokenr
Token ID81
Feature activation+1.47e+00

Pos logit contributions
arth+2.147
igers+2.071
heast+2.070
arian+1.943
erson+1.901
Neg logit contributions
thood-1.797
 rgb-1.730
cas-1.729
angan-1.715
Cry-1.692
Tokenutch
Token ID7140
Feature activation+1.84e+00

Pos logit contributions
arth+3.841
igers+3.653
heast+3.569
arian+3.315
erson+3.291
Neg logit contributions
thood-5.014
 rgb-4.815
Cry-4.802
 Carbuncle-4.796
cas-4.792
Tokenins
Token ID1040
Feature activation+9.24e-02

Pos logit contributions
arth+1.899
igers+1.691
heast+1.451
arian+1.335
erson+1.302
Neg logit contributions
thood-9.152
?????-?????--8.915
 Carbuncle-8.912
 rgb-8.894
Cry-8.840
Token with
Token ID351
Feature activation-4.91e-01

Pos logit contributions
arth+0.293
igers+0.281
heast+0.280
arian+0.265
erson+0.259
Neg logit contributions
thood-0.264
 rgb-0.252
cas-0.252
angan-0.251
Cry-0.249
Token $
Token ID720
Feature activation+2.64e-01

Pos logit contributions
thood+1.389
 rgb+1.366
cas+1.362
angan+1.345
Cry+1.323
Neg logit contributions
arth-1.537
heast-1.480
igers-1.477
arian-1.365
erson-1.347
Token1
Token ID16
Feature activation-3.42e-01

Pos logit contributions
arth+0.703
heast+0.675
igers+0.675
arian+0.620
erson+0.605
Neg logit contributions
thood-0.885
cas-0.860
 rgb-0.856
angan-0.850
Cry-0.849
Token million
Token ID1510
Feature activation-8.60e-01

Pos logit contributions
thood+0.933
 rgb+0.885
cas+0.879
angan+0.876
Cry+0.872
Neg logit contributions
arth-1.134
igers-1.084
heast-1.083
arian-1.031
erson-1.013
TokenAmerican
Token ID7437
Feature activation+2.31e-01

Pos logit contributions
thood+0.195
 rgb+0.186
cas+0.185
angan+0.184
Cry+0.182
Neg logit contributions
arth-0.247
igers-0.237
heast-0.236
arian-0.224
erson-0.219
Token all
Token ID477
Feature activation+9.96e-02

Pos logit contributions
arth+0.722
igers+0.694
heast+0.693
arian+0.645
erson+0.633
Neg logit contributions
thood-0.671
 rgb-0.649
cas-0.648
angan-0.641
Cry-0.635
Token women
Token ID1466
Feature activation+1.71e-01

Pos logit contributions
arth+0.369
igers+0.356
heast+0.356
arian+0.336
erson+0.330
Neg logit contributions
thood-0.231
cas-0.219
 rgb-0.219
angan-0.216
Cry-0.213
Token's
Token ID338
Feature activation-1.77e-01

Pos logit contributions
arth+0.547
igers+0.527
heast+0.527
arian+0.490
erson+0.481
Neg logit contributions
thood-0.482
 rgb-0.466
cas-0.465
angan-0.458
Cry-0.454
Token swing
Token ID9628
Feature activation+7.82e-01

Pos logit contributions
thood+0.504
 rgb+0.497
cas+0.493
angan+0.480
bus+0.480
Neg logit contributions
arth-0.549
heast-0.534
igers-0.533
arian-0.485
illes-0.481
Token band
Token ID4097
Feature activation+1.68e+00

Pos logit contributions
arth+2.358
igers+2.253
heast+2.249
arian+2.113
erson+2.072
Neg logit contributions
thood-2.350
 rgb-2.259
cas-2.251
angan-2.246
Cry-2.230
Token.[
Token ID3693
Feature activation+5.05e-01

Pos logit contributions
arth+5.264
igers+4.996
heast+4.985
arian+4.806
erson+4.719
Neg logit contributions
thood-4.694
angan-4.515
Cry-4.505
 rgb-4.488
cas-4.442
Token46
Token ID3510
Feature activation-1.48e-01

Pos logit contributions
arth+1.295
igers+1.230
heast+1.226
arian+1.133
erson+1.105
Neg logit contributions
thood-1.746
 rgb-1.687
cas-1.685
angan-1.677
Cry-1.665
Token]
Token ID60
Feature activation+1.75e-01

Pos logit contributions
thood+0.538
 rgb+0.518
angan+0.516
cas+0.513
Cry+0.510
Neg logit contributions
arth-0.359
igers-0.337
heast-0.336
arian-0.312
erson-0.302
Token
Token ID198
Feature activation+4.42e-01

Pos logit contributions
arth+0.527
igers+0.506
heast+0.504
arian+0.470
erson+0.458
Neg logit contributions
thood-0.526
 rgb-0.507
cas-0.505
angan-0.501
Cry-0.500
Token
Token ID198
Feature activation+5.77e-01

Pos logit contributions
arth+1.395
heast+1.355
igers+1.349
arian+1.246
erson+1.223
Neg logit contributions
thood-1.260
cas-1.229
 rgb-1.226
Cry-1.218
angan-1.210
Token shift
Token ID6482
Feature activation-1.49e-01

Pos logit contributions
arth+1.723
igers+1.657
heast+1.652
arian+1.561
erson+1.532
Neg logit contributions
thood-1.323
 rgb-1.264
cas-1.260
angan-1.253
Cry-1.243
Token on
Token ID319
Feature activation-3.99e-02

Pos logit contributions
thood+0.418
cas+0.402
 rgb+0.401
angan+0.397
Cry+0.395
Neg logit contributions
arth-0.478
igers-0.458
heast-0.457
arian-0.426
erson-0.418
Token opioids
Token ID39032
Feature activation+5.88e-01

Pos logit contributions
thood+0.121
 rgb+0.117
cas+0.117
angan+0.116
Cry+0.115
Neg logit contributions
arth-0.118
igers-0.115
heast-0.114
arian-0.105
erson-0.103
Token,
Token ID11
Feature activation+1.39e-01

Pos logit contributions
arth+1.889
igers+1.808
heast+1.800
arian+1.716
erson+1.679
Neg logit contributions
thood-1.637
 rgb-1.575
angan-1.563
cas-1.563
Cry-1.547
Token I
Token ID314
Feature activation-1.61e-01

Pos logit contributions
arth+0.425
igers+0.409
heast+0.408
arian+0.380
erson+0.372
Neg logit contributions
thood-0.411
cas-0.396
 rgb-0.396
angan-0.392
Cry-0.388
Token plead
Token ID30701
Feature activation+1.81e+00

Pos logit contributions
thood+0.394
cas+0.379
 rgb+0.378
angan+0.374
Cry+0.367
Neg logit contributions
arth-0.572
igers-0.556
heast-0.553
arian-0.517
illes-0.507
Token for
Token ID329
Feature activation+6.08e-01

Pos logit contributions
arth+5.132
igers+4.732
heast+4.677
erson+4.575
arian+4.544
Neg logit contributions
thood-5.526
 rgb-5.350
cas-5.293
Cry-5.191
angan-5.175
Token caution
Token ID13041
Feature activation-2.20e-01

Pos logit contributions
arth+1.894
igers+1.808
heast+1.806
arian+1.698
erson+1.666
Neg logit contributions
thood-1.773
cas-1.697
 rgb-1.696
angan-1.687
Cry-1.676
Token.
Token ID13
Feature activation+4.29e-02

Pos logit contributions
thood+0.573
cas+0.547
 rgb+0.547
angan+0.542
Cry+0.537
Neg logit contributions
arth-0.750
igers-0.723
heast-0.721
arian-0.677
erson-0.665
Token Patients
Token ID28021
Feature activation+2.20e-01

Pos logit contributions
arth+0.127
igers+0.124
heast+0.123
arian+0.112
erson+0.111
Neg logit contributions
thood-0.131
 rgb-0.127
cas-0.126
Cry-0.126
angan-0.125
Token with
Token ID351
Feature activation+2.39e-01

Pos logit contributions
arth+0.723
igers+0.697
heast+0.696
arian+0.650
erson+0.639
Neg logit contributions
thood-0.601
 rgb-0.576
cas-0.575
angan-0.570
Cry-0.565
Token (
Token ID357
Feature activation+3.18e-01

Pos logit contributions
thood+0.324
 rgb+0.312
cas+0.311
angan+0.310
Cry+0.308
Neg logit contributions
arth-0.266
igers-0.253
heast-0.253
arian-0.235
erson-0.230
TokenEqu
Token ID23588
Feature activation-2.91e-01

Pos logit contributions
arth+1.098
igers+1.047
heast+1.039
arian+1.000
erson+0.974
Neg logit contributions
thood-0.827
 rgb-0.785
angan-0.781
cas-0.769
beit-0.759
Tokenipe
Token ID3757
Feature activation+2.16e-01

Pos logit contributions
thood+0.707
cas+0.680
angan+0.678
Cry+0.663
beit+0.659
Neg logit contributions
arth-1.029
igers-0.999
heast-0.997
arian-0.928
erson-0.921
Token Cycl
Token ID28007
Feature activation+3.72e-01

Pos logit contributions
arth+0.749
heast+0.727
igers+0.724
arian+0.674
erson+0.671
Neg logit contributions
thood-0.546
 rgb-0.539
cas-0.539
Cry-0.531
angan-0.530
Tokeniste
Token ID40833
Feature activation-2.19e-02

Pos logit contributions
arth+1.043
igers+0.992
heast+0.990
arian+0.920
erson+0.898
Neg logit contributions
thood-1.194
cas-1.159
 rgb-1.153
angan-1.150
Cry-1.138
Token FD
Token ID30002
Feature activation+1.81e+00

Pos logit contributions
thood+0.071
cas+0.067
angan+0.067
Cry+0.066
 rgb+0.066
Neg logit contributions
arth-0.062
igers-0.060
heast-0.059
arian-0.055
erson-0.053
TokenJ
Token ID41
Feature activation+4.71e-01

Pos logit contributions
arth+4.454
igers+4.215
heast+4.051
arian+3.873
erson+3.784
Neg logit contributions
thood-6.449
angan-6.021
dinand-5.993
 rgb-5.926
cas-5.914
Token -
Token ID532
Feature activation-1.38e-02

Pos logit contributions
arth+1.589
heast+1.540
igers+1.537
arian+1.434
erson+1.408
Neg logit contributions
thood-1.240
 rgb-1.203
cas-1.195
angan-1.183
Cry-1.178
Token Big
Token ID4403
Feature activation+7.92e-01

Pos logit contributions
thood+0.043
cas+0.042
angan+0.042
 rgb+0.041
Cry+0.041
Neg logit contributions
arth-0.040
igers-0.038
heast-0.038
arian-0.035
erson-0.034
TokenMat
Token ID19044
Feature activation-5.94e-01

Pos logit contributions
arth+1.766
igers+1.662
heast+1.655
arian+1.512
erson+1.466
Neg logit contributions
thood-3.008
 rgb-2.913
cas-2.908
angan-2.898
Cry-2.872
Token)
Token ID8
Feature activation+5.56e-01

Pos logit contributions
 rgb+1.420
thood+1.400
cas+1.384
Cry+1.372
angan+1.356
Neg logit contributions
arth-2.096
heast-2.061
igers-2.035
arian-1.889
 opio-1.872
Token local
Token ID1957
Feature activation+1.65e-01

Pos logit contributions
 rgb+1.628
cas+1.621
thood+1.597
Cry+1.571
angan+1.568
Neg logit contributions
arth-2.206
heast-2.124
igers-2.118
arian-1.990
erson-1.939
Token government
Token ID1230
Feature activation+2.67e-01

Pos logit contributions
arth+0.580
igers+0.559
heast+0.558
arian+0.526
erson+0.517
Neg logit contributions
thood-0.410
 rgb-0.393
cas-0.393
angan-0.389
Cry-0.385
Token to
Token ID284
Feature activation-5.90e-01

Pos logit contributions
arth+0.886
igers+0.850
heast+0.848
arian+0.802
erson+0.786
Neg logit contributions
thood-0.726
 rgb-0.694
cas-0.692
angan-0.689
Cry-0.683
Token train
Token ID4512
Feature activation-4.89e-01

Pos logit contributions
thood+1.392
 rgb+1.384
cas+1.343
Cry+1.328
angan+1.317
Neg logit contributions
arth-2.130
igers-2.060
heast-2.052
arian-1.915
erson-1.878
Token their
Token ID511
Feature activation-1.49e-01

Pos logit contributions
thood+1.313
cas+1.276
 rgb+1.271
angan+1.248
Cry+1.237
Neg logit contributions
arth-1.615
igers-1.558
heast-1.551
arian-1.457
erson-1.415
Token police
Token ID1644
Feature activation+3.68e-01

Pos logit contributions
thood+0.359
cas+0.349
 rgb+0.349
angan+0.343
Cry+0.339
Neg logit contributions
arth-0.537
heast-0.516
igers-0.515
arian-0.486
erson-0.474
Token force
Token ID2700
Feature activation+6.80e-01

Pos logit contributions
arth+1.216
igers+1.171
heast+1.161
arian+1.099
erson+1.084
Neg logit contributions
thood-1.000
 rgb-0.956
angan-0.952
cas-0.948
Cry-0.942
Token more
Token ID517
Feature activation+5.37e-01

Pos logit contributions
arth+2.188
igers+2.110
heast+2.081
arian+1.997
erson+1.961
Neg logit contributions
thood-1.895
 rgb-1.809
angan-1.803
cas-1.791
Cry-1.778
Token effectively
Token ID6840
Feature activation+4.19e-01

Pos logit contributions
arth+1.978
heast+1.897
igers+1.896
arian+1.811
erson+1.783
Neg logit contributions
thood-1.266
angan-1.193
 rgb-1.185
Cry-1.176
cas-1.171
Token,
Token ID11
Feature activation+5.37e-02

Pos logit contributions
arth+1.374
igers+1.316
heast+1.315
arian+1.250
erson+1.225
Neg logit contributions
thood-1.151
 rgb-1.096
angan-1.093
cas-1.091
Cry-1.084
Token improve
Token ID2987
Feature activation+2.66e-01

Pos logit contributions
arth+0.178
igers+0.171
heast+0.171
arian+0.160
erson+0.157
Neg logit contributions
thood-0.146
 rgb-0.140
cas-0.140
angan-0.139
Cry-0.137
Token Strike
Token ID12282
Feature activation-1.97e-01

Pos logit contributions
thood+1.987
 rgb+1.920
cas+1.908
Cry+1.900
angan+1.866
Neg logit contributions
arth-2.625
igers-2.523
heast-2.517
arian-2.350
erson-2.304
Token with
Token ID351
Feature activation+1.56e-01

Pos logit contributions
thood+0.512
 rgb+0.493
cas+0.489
Cry+0.484
angan+0.484
Neg logit contributions
arth-0.677
heast-0.652
igers-0.652
arian-0.609
erson-0.599
Token Master
Token ID5599
Feature activation-1.23e+00

Pos logit contributions
arth+0.485
igers+0.466
heast+0.465
arian+0.435
erson+0.426
Neg logit contributions
thood-0.452
 rgb-0.435
cas-0.434
angan-0.432
Cry-0.429
Tokenmind
Token ID10155
Feature activation-1.24e+00

Pos logit contributions
thood+3.333
cas+3.257
 rgb+3.215
Cry+3.208
angan+3.203
Neg logit contributions
arth-3.936
igers-3.818
heast-3.783
arian-3.552
erson-3.485
Token makes
Token ID1838
Feature activation+3.57e-02

Pos logit contributions
thood+3.215
Cry+3.076
 rgb+3.065
cas+3.058
 Carbuncle+3.022
Neg logit contributions
arth-4.156
heast-4.023
igers-3.963
arian-3.705
erson-3.654
Token him
Token ID683
Feature activation+2.92e-01

Pos logit contributions
arth+0.132
heast+0.128
igers+0.128
arian+0.121
erson+0.119
Neg logit contributions
thood-0.082
 rgb-0.079
cas-0.078
angan-0.078
Cry-0.077
Token a
Token ID257
Feature activation-1.41e-01

Pos logit contributions
arth+0.911
igers+0.874
heast+0.872
arian+0.818
erson+0.801
Neg logit contributions
thood-0.846
 rgb-0.812
cas-0.811
angan-0.806
Cry-0.799
Token beast
Token ID13824
Feature activation-6.53e-01

Pos logit contributions
thood+0.373
 rgb+0.364
cas+0.363
angan+0.359
Cry+0.356
Neg logit contributions
arth-0.471
igers-0.454
heast-0.451
arian-0.423
erson-0.414
Token if
Token ID611
Feature activation-1.79e-01

Pos logit contributions
thood+1.718
cas+1.660
 rgb+1.654
Cry+1.643
angan+1.617
Neg logit contributions
arth-2.185
heast-2.104
igers-2.099
arian-1.935
erson-1.927
Token you
Token ID345
Feature activation-1.71e-01

Pos logit contributions
thood+0.454
cas+0.439
 rgb+0.436
Cry+0.434
angan+0.431
Neg logit contributions
arth-0.618
igers-0.594
heast-0.593
arian-0.558
erson-0.545
Token don
Token ID836
Feature activation+8.60e-03

Pos logit contributions
thood+0.435
cas+0.425
 rgb+0.421
Cry+0.417
angan+0.417
Neg logit contributions
arth-0.589
igers-0.566
heast-0.563
arian-0.531
erson-0.522
Token biological
Token ID10685
Feature activation-9.83e-02

Pos logit contributions
thood+2.199
angan+2.181
 rgb+2.179
cas+2.158
Cry+2.148
Neg logit contributions
arth-1.801
igers-1.784
heast-1.783
arian-1.590
illes-1.585
Token weapons
Token ID3777
Feature activation-5.67e-01

Pos logit contributions
thood+0.257
 rgb+0.250
cas+0.249
angan+0.247
Cry+0.246
Neg logit contributions
arth-0.333
heast-0.324
igers-0.322
arian-0.299
erson-0.295
Token by
Token ID416
Feature activation-5.24e-01

Pos logit contributions
thood+1.414
cas+1.371
 rgb+1.363
Cry+1.344
angan+1.339
Neg logit contributions
arth-1.968
heast-1.923
igers-1.915
arian-1.768
erson-1.747
Token a
Token ID257
Feature activation-6.61e-03

Pos logit contributions
thood+1.355
cas+1.319
 rgb+1.310
angan+1.310
Cry+1.308
Neg logit contributions
arth-1.757
heast-1.721
igers-1.702
arian-1.567
erson-1.548
Token terrorist
Token ID7417
Feature activation-8.53e-01

Pos logit contributions
thood+0.018
cas+0.017
 rgb+0.017
angan+0.017
Cry+0.017
Neg logit contributions
arth-0.022
igers-0.021
heast-0.021
arian-0.019
erson-0.019
Token group
Token ID1448
Feature activation+6.86e-01

Pos logit contributions
thood+2.430
cas+2.368
 rgb+2.345
Cry+2.311
angan+2.286
Neg logit contributions
arth-2.664
heast-2.583
igers-2.573
arian-2.346
erson-2.326
Token after
Token ID706
Feature activation+6.53e-01

Pos logit contributions
arth+2.245
igers+2.159
heast+2.138
arian+2.062
erson+2.007
Neg logit contributions
thood-1.867
 rgb-1.782
angan-1.780
cas-1.765
Cry-1.756
Token A
Token ID317
Feature activation-1.44e-01

Pos logit contributions
arth+1.983
igers+1.890
heast+1.882
arian+1.784
erson+1.741
Neg logit contributions
thood-1.952
 rgb-1.866
cas-1.859
angan-1.857
Cry-1.838
Tokenum
Token ID388
Feature activation-1.04e-01

Pos logit contributions
thood+0.415
cas+0.401
 rgb+0.399
angan+0.399
Cry+0.396
Neg logit contributions
arth-0.447
igers-0.430
heast-0.428
arian-0.401
erson-0.392
Token Shin
Token ID11466
Feature activation-4.29e-01

Pos logit contributions
thood+0.252
cas+0.240
 rgb+0.239
angan+0.239
Cry+0.236
Neg logit contributions
arth-0.375
igers-0.362
heast-0.362
arian-0.341
erson-0.335
Tokenri
Token ID380
Feature activation-2.39e-01

Pos logit contributions
thood+1.013
cas+0.974
 rgb+0.972
angan+0.965
Cry+0.959
Neg logit contributions
arth-1.560
heast-1.520
igers-1.496
arian-1.415
illes-1.381
Token Dolphins
Token ID21668
Feature activation+7.28e-01

Pos logit contributions
arth+0.300
heast+0.288
igers+0.286
arian+0.270
erson+0.264
Neg logit contributions
thood-0.263
cas-0.256
 rgb-0.256
angan-0.255
Cry-0.252
Token will
Token ID481
Feature activation+8.81e-02

Pos logit contributions
arth+2.353
igers+2.262
heast+2.241
arian+2.134
erson+2.086
Neg logit contributions
thood-2.029
 rgb-1.931
cas-1.926
angan-1.920
Cry-1.902
Token be
Token ID307
Feature activation+7.94e-02

Pos logit contributions
arth+0.310
heast+0.300
igers+0.299
arian+0.281
erson+0.275
Neg logit contributions
thood-0.219
 rgb-0.213
cas-0.211
angan-0.209
Cry-0.207
Token in
Token ID287
Feature activation-4.16e-02

Pos logit contributions
arth+0.260
heast+0.252
igers+0.252
arian+0.236
erson+0.232
Neg logit contributions
 rgb-0.210
thood-0.209
cas-0.207
angan-0.203
Cry-0.201
Token pretty
Token ID2495
Feature activation+2.79e-03

Pos logit contributions
thood+0.122
 rgb+0.119
cas+0.118
angan+0.118
Cry+0.117
Neg logit contributions
arth-0.126
heast-0.122
igers-0.121
arian-0.113
erson-0.111
Token good
Token ID922
Feature activation+7.80e-01

Pos logit contributions
arth+0.009
igers+0.009
heast+0.009
arian+0.009
erson+0.008
Neg logit contributions
thood-0.007
 rgb-0.007
cas-0.007
angan-0.007
Cry-0.007
Token shape
Token ID5485
Feature activation+4.97e-02

Pos logit contributions
arth+2.466
igers+2.359
heast+2.355
arian+2.212
erson+2.169
Neg logit contributions
thood-2.239
angan-2.137
cas-2.137
 rgb-2.128
Cry-2.105
Token next
Token ID1306
Feature activation+2.24e-01

Pos logit contributions
arth+0.164
igers+0.158
heast+0.158
arian+0.148
erson+0.145
Neg logit contributions
thood-0.135
 rgb-0.130
cas-0.129
angan-0.128
Cry-0.127
Token offseason
Token ID16349
Feature activation+9.68e-02

Pos logit contributions
arth+0.598
igers+0.568
heast+0.568
arian+0.523
erson+0.513
Neg logit contributions
thood-0.752
 rgb-0.731
cas-0.729
angan-0.723
Cry-0.721
Token.
Token ID13
Feature activation+2.55e-02

Pos logit contributions
arth+0.327
igers+0.315
heast+0.314
arian+0.297
erson+0.292
Neg logit contributions
thood-0.256
 rgb-0.244
cas-0.243
angan-0.242
Cry-0.240
Token
Token ID198
Feature activation+4.91e-02

Pos logit contributions
arth+0.074
igers+0.071
heast+0.071
arian+0.066
erson+0.064
Neg logit contributions
thood-0.079
 rgb-0.077
cas-0.077
angan-0.076
Cry-0.076
TokenW
Token ID54
Feature activation+1.46e-01

Pos logit contributions
 rgb+1.968
thood+1.952
cas+1.923
angan+1.923
Cry+1.911
Neg logit contributions
arth-2.246
igers-2.161
heast-2.158
arian-1.989
erson-1.953
TokenK
Token ID42
Feature activation+4.88e-01

Pos logit contributions
arth+0.463
igers+0.446
heast+0.444
arian+0.416
erson+0.408
Neg logit contributions
thood-0.417
 rgb-0.402
cas-0.400
angan-0.399
Cry-0.395
Token AND
Token ID5357
Feature activation+2.21e-01

Pos logit contributions
arth+1.536
igers+1.474
heast+1.470
arian+1.380
erson+1.353
Neg logit contributions
thood-1.402
 rgb-1.345
cas-1.344
angan-1.336
Cry-1.324
Token AP
Token ID3486
Feature activation+5.21e-01

Pos logit contributions
arth+0.695
igers+0.667
heast+0.665
arian+0.624
erson+0.612
Neg logit contributions
thood-0.636
 rgb-0.610
cas-0.609
angan-0.606
Cry-0.600
TokenAC
Token ID2246
Feature activation+5.94e-01

Pos logit contributions
arth+1.610
heast+1.510
igers+1.503
arian+1.432
erson+1.414
Neg logit contributions
thood-1.551
 rgb-1.462
beit-1.454
cas-1.451
angan-1.450
TokenHE
Token ID13909
Feature activation+6.36e-01

Pos logit contributions
arth+2.014
igers+1.944
heast+1.937
arian+1.827
erson+1.788
Neg logit contributions
thood-1.560
 rgb-1.498
cas-1.497
angan-1.486
Cry-1.480
Token T
Token ID309
Feature activation+5.02e-01

Pos logit contributions
arth+1.746
igers+1.676
heast+1.661
arian+1.574
erson+1.533
Neg logit contributions
thood-2.080
cas-1.974
angan-1.971
Cry-1.953
 rgb-1.950
TokenOC
Token ID4503
Feature activation+2.29e-01

Pos logit contributions
arth+1.416
heast+1.344
igers+1.330
arian+1.246
erson+1.217
Neg logit contributions
thood-1.605
cas-1.577
 rgb-1.571
Cry-1.551
angan-1.548
Token RE
Token ID4526
Feature activation+3.99e-01

Pos logit contributions
arth+0.629
igers+0.603
heast+0.599
arian+0.558
erson+0.546
Neg logit contributions
thood-0.752
cas-0.719
angan-0.715
 rgb-0.714
Cry-0.710
TokenP
Token ID47
Feature activation+8.21e-01

Pos logit contributions
arth+1.590
heast+1.540
igers+1.540
arian+1.463
erson+1.439
Neg logit contributions
thood-0.812
 rgb-0.773
cas-0.771
angan-0.762
Cry-0.755
TokenORTS
Token ID33002
Feature activation-2.08e-02

Pos logit contributions
arth+2.379
igers+2.279
heast+2.265
arian+2.121
erson+2.077
Neg logit contributions
thood-2.566
cas-2.459
 rgb-2.454
angan-2.449
Cry-2.428
Tokenis
Token ID271
Feature activation-3.60e-01

Pos logit contributions
arth+0.121
igers+0.116
heast+0.115
arian+0.108
erson+0.106
Neg logit contributions
thood-0.119
cas-0.114
 rgb-0.114
angan-0.114
Cry-0.113
Token coming
Token ID2406
Feature activation+3.99e-01

Pos logit contributions
thood+0.984
cas+0.966
 rgb+0.965
angan+0.955
Cry+0.930
Neg logit contributions
arth-1.155
igers-1.125
heast-1.109
arian-1.054
erson-1.019
Token to
Token ID284
Feature activation+3.69e-02

Pos logit contributions
arth+1.251
igers+1.198
heast+1.197
arian+1.126
erson+1.103
Neg logit contributions
thood-1.151
cas-1.104
 rgb-1.103
angan-1.096
Cry-1.090
Token Xbox
Token ID9445
Feature activation+5.89e-01

Pos logit contributions
arth+0.110
igers+0.105
heast+0.105
arian+0.098
erson+0.096
Neg logit contributions
thood-0.112
 rgb-0.108
cas-0.108
angan-0.107
Cry-0.106
Token One
Token ID1881
Feature activation+1.96e-01

Pos logit contributions
arth+1.371
heast+1.293
igers+1.293
arian+1.183
erson+1.155
Neg logit contributions
thood-2.177
 rgb-2.102
cas-2.099
angan-2.089
Cry-2.080
Token.
Token ID13
Feature activation-1.00e-01

Pos logit contributions
arth+0.643
igers+0.618
heast+0.616
arian+0.580
erson+0.570
Neg logit contributions
thood-0.538
 rgb-0.514
cas-0.514
angan-0.511
Cry-0.506
Token
Token ID198
Feature activation-2.88e-01

Pos logit contributions
thood+0.311
cas+0.301
 rgb+0.301
Cry+0.299
angan+0.299
Neg logit contributions
arth-0.290
igers-0.279
heast-0.278
arian-0.257
erson-0.251
Token
Token ID198
Feature activation-2.43e-01

Pos logit contributions
cas+0.725
Cry+0.725
 rgb+0.720
thood+0.711
angan+0.699
Neg logit contributions
arth-0.982
heast-0.978
igers-0.965
arian-0.882
 opio-0.878
Token"
Token ID1
Feature activation+2.60e-01

Pos logit contributions
thood+0.693
cas+0.676
Cry+0.673
angan+0.665
 rgb+0.661
Neg logit contributions
arth-0.763
igers-0.738
heast-0.737
arian-0.686
erson-0.673
TokenOur
Token ID5122
Feature activation-8.26e-02

Pos logit contributions
arth+0.824
igers+0.792
heast+0.789
arian+0.741
erson+0.725
Neg logit contributions
thood-0.744
cas-0.717
 rgb-0.713
angan-0.711
Cry-0.709
Token vision
Token ID5761
Feature activation-2.81e-01

Pos logit contributions
thood+0.227
cas+0.220
 rgb+0.219
angan+0.218
Cry+0.216
Neg logit contributions
arth-0.270
igers-0.259
heast-0.256
arian-0.244
erson-0.235
Token is
Token ID318
Feature activation+2.26e-01

Pos logit contributions
arth+1.674
igers+1.604
heast+1.597
arian+1.512
erson+1.483
Neg logit contributions
thood-1.408
 rgb-1.343
cas-1.338
angan-1.334
Cry-1.321
Token what
Token ID644
Feature activation-4.23e-01

Pos logit contributions
arth+0.761
igers+0.733
heast+0.731
arian+0.686
erson+0.671
Neg logit contributions
thood-0.599
 rgb-0.578
cas-0.578
angan-0.573
Cry-0.565
Token eventually
Token ID4191
Feature activation-8.85e-02

Pos logit contributions
thood+1.095
cas+1.068
 rgb+1.068
angan+1.054
Cry+1.053
Neg logit contributions
arth-1.418
heast-1.388
igers-1.375
arian-1.274
erson-1.261
Token breaks
Token ID9457
Feature activation+2.36e-01

Pos logit contributions
thood+0.255
 rgb+0.251
cas+0.250
angan+0.246
Cry+0.245
Neg logit contributions
arth-0.275
igers-0.264
heast-0.263
arian-0.243
erson-0.239
Token through
Token ID832
Feature activation+2.56e-01

Pos logit contributions
arth+0.710
igers+0.683
heast+0.680
arian+0.633
erson+0.619
Neg logit contributions
thood-0.710
cas-0.683
 rgb-0.682
angan-0.679
Cry-0.676
Token the
Token ID262
Feature activation-1.55e-01

Pos logit contributions
arth+0.842
igers+0.809
heast+0.807
arian+0.759
erson+0.745
Neg logit contributions
thood-0.699
 rgb-0.670
cas-0.668
angan-0.664
Cry-0.659
Token awkward
Token ID13006
Feature activation+4.45e-02

Pos logit contributions
thood+0.390
 rgb+0.383
cas+0.381
Cry+0.380
angan+0.379
Neg logit contributions
arth-0.538
igers-0.522
heast-0.522
arian-0.484
erson-0.477
Tokenness
Token ID1108
Feature activation+3.08e-01

Pos logit contributions
arth+0.131
igers+0.126
heast+0.125
arian+0.115
erson+0.113
Neg logit contributions
thood-0.138
cas-0.133
 rgb-0.133
angan-0.132
Cry-0.131
Token.
Token ID13
Feature activation+5.18e-02

Pos logit contributions
arth+1.004
igers+0.963
heast+0.962
arian+0.911
erson+0.890
Neg logit contributions
thood-0.849
 rgb-0.813
cas-0.809
angan-0.806
Cry-0.797
Token Both
Token ID5747
Feature activation+2.28e-01

Pos logit contributions
arth+0.159
heast+0.153
igers+0.153
arian+0.141
erson+0.138
Neg logit contributions
thood-0.153
 rgb-0.149
cas-0.148
Cry-0.148
angan-0.146
Token of
Token ID286
Feature activation+7.75e-01

Pos logit contributions
arth+0.742
igers+0.712
heast+0.712
arian+0.668
erson+0.654
Neg logit contributions
thood-0.631
cas-0.605
 rgb-0.605
angan-0.599
Cry-0.598
Token from
Token ID422
Feature activation+8.00e-01

Pos logit contributions
arth+2.616
igers+2.511
heast+2.477
arian+2.403
erson+2.344
Neg logit contributions
thood-2.407
 rgb-2.279
angan-2.247
Cry-2.235
beit-2.231
Token her
Token ID607
Feature activation-1.44e-01

Pos logit contributions
arth+2.439
igers+2.322
heast+2.309
arian+2.180
erson+2.149
Neg logit contributions
thood-2.367
cas-2.271
angan-2.260
 rgb-2.257
Cry-2.236
Token,
Token ID11
Feature activation-2.21e-01

Pos logit contributions
thood+0.379
 rgb+0.364
cas+0.363
angan+0.361
Cry+0.357
Neg logit contributions
arth-0.487
heast-0.470
igers-0.470
arian-0.439
erson-0.431
Token which
Token ID543
Feature activation-7.70e-01

Pos logit contributions
thood+0.580
 rgb+0.566
cas+0.565
angan+0.558
Cry+0.550
Neg logit contributions
arth-0.746
heast-0.714
igers-0.713
arian-0.666
erson-0.654
Token I
Token ID314
Feature activation-6.23e-01

Pos logit contributions
thood+1.823
 rgb+1.821
cas+1.806
Cry+1.767
angan+1.766
Neg logit contributions
arth-2.736
heast-2.631
igers-2.625
arian-2.448
erson-2.418
Token have
Token ID423
Feature activation-1.41e-01

Pos logit contributions
 rgb+1.507
cas+1.493
thood+1.490
angan+1.460
beit+1.433
Neg logit contributions
arth-2.187
igers-2.132
heast-2.114
arian-1.954
erson-1.923
Token kept
Token ID4030
Feature activation-1.13e+00

Pos logit contributions
 rgb+0.398
thood+0.396
cas+0.394
angan+0.389
beit+0.382
Neg logit contributions
arth-0.444
igers-0.429
heast-0.427
arian-0.394
erson-0.387
Token for
Token ID329
Feature activation-1.84e-01

Pos logit contributions
 rgb+2.878
cas+2.834
thood+2.823
beit+2.792
bus+2.757
Neg logit contributions
arth-3.833
igers-3.704
heast-3.676
arian-3.364
yre-3.330
Token almost
Token ID2048
Feature activation+2.53e-03

Pos logit contributions
thood+0.541
cas+0.525
 rgb+0.525
angan+0.519
Cry+0.516
Neg logit contributions
arth-0.567
igers-0.545
heast-0.545
arian-0.504
erson-0.494
Token 30
Token ID1542
Feature activation+1.31e-01

Pos logit contributions
arth+0.007
igers+0.007
heast+0.007
arian+0.006
erson+0.006
Neg logit contributions
thood-0.008
 rgb-0.008
cas-0.008
Cry-0.008
angan-0.008
Token years
Token ID812
Feature activation-5.59e-01

Pos logit contributions
arth+0.388
igers+0.371
heast+0.369
arian+0.351
erson+0.340
Neg logit contributions
thood-0.401
angan-0.380
cas-0.380
 rgb-0.379
Cry-0.378
Token them
Token ID606
Feature activation+2.16e-01

Pos logit contributions
arth+2.400
igers+2.301
heast+2.292
arian+2.157
erson+2.119
Neg logit contributions
thood-2.253
cas-2.156
 rgb-2.150
angan-2.145
Cry-2.117
Token to
Token ID284
Feature activation-2.14e-01

Pos logit contributions
arth+0.641
igers+0.615
heast+0.612
arian+0.572
erson+0.559
Neg logit contributions
thood-0.660
 rgb-0.638
cas-0.635
angan-0.630
Cry-0.627
Token sleep
Token ID3993
Feature activation-5.75e-01

Pos logit contributions
thood+0.550
 rgb+0.527
cas+0.525
angan+0.522
Cry+0.517
Neg logit contributions
arth-0.740
igers-0.713
heast-0.713
arian-0.672
erson-0.659
Token each
Token ID1123
Feature activation-1.98e-01

Pos logit contributions
thood+1.482
Cry+1.411
 rgb+1.411
cas+1.410
angan+1.401
Neg logit contributions
arth-1.967
heast-1.891
igers-1.886
arian-1.771
erson-1.729
Token night
Token ID1755
Feature activation+2.65e-01

Pos logit contributions
thood+0.629
 rgb+0.619
Cry+0.615
cas+0.612
angan+0.612
Neg logit contributions
arth-0.559
heast-0.534
igers-0.534
arian-0.485
erson-0.480
Token as
Token ID355
Feature activation-2.30e-01

Pos logit contributions
arth+0.851
igers+0.822
heast+0.817
arian+0.771
erson+0.760
Neg logit contributions
thood-0.739
 rgb-0.708
cas-0.705
angan-0.700
Cry-0.688
Token children
Token ID1751
Feature activation-1.58e-01

Pos logit contributions
thood+0.618
 rgb+0.596
angan+0.594
cas+0.594
Cry+0.591
Neg logit contributions
arth-0.767
heast-0.742
igers-0.735
arian-0.691
erson-0.672
Token,
Token ID11
Feature activation+2.39e-01

Pos logit contributions
thood+0.427
 rgb+0.409
cas+0.408
angan+0.406
Cry+0.401
Neg logit contributions
arth-0.528
igers-0.508
heast-0.506
arian-0.477
erson-0.469
Token she
Token ID673
Feature activation+3.30e-01

Pos logit contributions
arth+0.784
igers+0.754
heast+0.751
arian+0.707
erson+0.695
Neg logit contributions
thood-0.656
 rgb-0.628
cas-0.627
angan-0.623
Cry-0.617
Token would
Token ID561
Feature activation-1.85e-02

Pos logit contributions
arth+1.230
igers+1.190
heast+1.188
arian+1.123
erson+1.103
Neg logit contributions
thood-0.754
 rgb-0.720
cas-0.718
angan-0.710
Cry-0.704
Token softly
Token ID26625
Feature activation-3.03e-01

Pos logit contributions
thood+0.045
 rgb+0.043
cas+0.043
Cry+0.042
angan+0.042
Neg logit contributions
arth-0.067
igers-0.065
heast-0.065
arian-0.061
erson-0.059
Token use
Token ID779
Feature activation-3.23e-01

Pos logit contributions
thood+1.128
 rgb+1.092
cas+1.072
Cry+1.058
angan+1.056
Neg logit contributions
arth-2.133
igers-2.064
heast-2.053
arian-1.957
erson-1.913
Token the
Token ID262
Feature activation-4.43e-01

Pos logit contributions
thood+0.978
 rgb+0.943
cas+0.941
angan+0.935
Cry+0.928
Neg logit contributions
arth-0.967
igers-0.925
heast-0.923
arian-0.864
erson-0.845
Token command
Token ID3141
Feature activation-5.73e-01

Pos logit contributions
thood+1.044
 rgb+1.022
cas+1.007
Cry+0.988
angan+0.984
Neg logit contributions
arth-1.610
igers-1.550
heast-1.544
arian-1.462
erson-1.433
Token sl
Token ID1017
Feature activation-7.98e-01

Pos logit contributions
thood+1.507
 rgb+1.458
cas+1.448
angan+1.431
Cry+1.421
Neg logit contributions
arth-1.929
igers-1.854
heast-1.851
arian-1.743
erson-1.713
Tokens
Token ID82
Feature activation-1.86e-01

Pos logit contributions
cas+1.554
thood+1.519
 rgb+1.454
bus+1.442
beit+1.409
Neg logit contributions
heast-3.140
arth-3.138
igers-3.108
arian-2.940
 opio-2.940
Token logs
Token ID17259
Feature activation-1.41e-01

Pos logit contributions
thood+0.593
 rgb+0.572
cas+0.572
angan+0.567
Cry+0.563
Neg logit contributions
arth-0.529
igers-0.505
heast-0.504
arian-0.470
erson-0.459
Token -
Token ID532
Feature activation+4.73e-01

Pos logit contributions
thood+0.403
 rgb+0.392
cas+0.391
angan+0.384
Cry+0.381
Neg logit contributions
arth-0.440
igers-0.424
heast-0.423
arian-0.395
erson-0.387
Tokenf
Token ID69
Feature activation-3.53e-01

Pos logit contributions
arth+1.738
igers+1.675
heast+1.672
arian+1.587
erson+1.560
Neg logit contributions
thood-1.110
 rgb-1.055
cas-1.050
angan-1.045
Cry-1.033
Token test
Token ID1332
Feature activation-4.83e-01

Pos logit contributions
thood+0.973
 rgb+0.938
cas+0.934
angan+0.913
Cry+0.906
Neg logit contributions
arth-1.138
igers-1.114
heast-1.100
arian-1.033
erson-1.018
Token --
Token ID1377
Feature activation+2.53e-01

Pos logit contributions
thood+1.510
cas+1.473
 rgb+1.463
angan+1.445
Cry+1.425
Neg logit contributions
arth-1.368
igers-1.337
heast-1.326
arian-1.222
erson-1.197
Tokenstart
Token ID9688
Feature activation-3.99e-01

Pos logit contributions
arth+0.845
igers+0.814
heast+0.812
arian+0.764
erson+0.748
Neg logit contributions
thood-0.681
cas-0.655
 rgb-0.651
angan-0.647
Cry-0.640
Token a
Token ID257
Feature activation+4.13e-01

Pos logit contributions
arth+0.997
igers+0.950
heast+0.943
arian+0.888
erson+0.868
Neg logit contributions
thood-1.050
 rgb-1.011
cas-1.010
angan-1.006
Cry-0.999
Token kingdom
Token ID13239
Feature activation-6.68e-01

Pos logit contributions
arth+1.364
igers+1.311
heast+1.308
arian+1.231
erson+1.208
Neg logit contributions
thood-1.127
 rgb-1.079
cas-1.077
angan-1.071
Cry-1.061
Token of
Token ID286
Feature activation-5.03e-01

Pos logit contributions
thood+1.753
 rgb+1.686
cas+1.671
angan+1.646
beit+1.631
Neg logit contributions
arth-2.248
igers-2.202
heast-2.194
arian-2.004
erson-1.989
Token the
Token ID262
Feature activation-3.08e-01

Pos logit contributions
thood+1.472
 rgb+1.428
cas+1.414
angan+1.408
 Carbuncle+1.390
Neg logit contributions
arth-1.518
heast-1.495
igers-1.479
arian-1.375
erson-1.338
Token earth
Token ID4534
Feature activation+1.49e-01

Pos logit contributions
thood+0.944
 rgb+0.927
cas+0.918
angan+0.912
 Carbuncle+0.905
Neg logit contributions
arth-0.887
igers-0.856
heast-0.854
arian-0.797
erson-0.770
Token!"
Token ID2474
Feature activation-1.34e+00

Pos logit contributions
arth+0.496
igers+0.476
heast+0.474
arian+0.449
erson+0.440
Neg logit contributions
thood-0.403
 rgb-0.386
cas-0.385
angan-0.384
Cry-0.380
Token
Token ID198
Feature activation-4.34e-01

Pos logit contributions
thood+3.823
cas+3.697
 rgb+3.695
Cry+3.656
angan+3.641
Neg logit contributions
arth-4.139
heast-3.997
igers-3.995
arian-3.718
erson-3.647
Token
Token ID198
Feature activation-3.48e-01

Pos logit contributions
cas+1.054
 rgb+1.047
Cry+1.045
thood+1.031
bus+1.022
Neg logit contributions
heast-1.511
arth-1.504
igers-1.492
 opio-1.378
 seams-1.347
Token-
Token ID12
Feature activation+3.72e-01

Pos logit contributions
thood+0.869
 rgb+0.829
cas+0.827
angan+0.822
Cry+0.813
Neg logit contributions
arth-1.228
igers-1.182
heast-1.180
arian-1.116
erson-1.096
Token excerpt
Token ID20911
Feature activation+4.03e-01

Pos logit contributions
arth+1.232
heast+1.175
igers+1.174
arian+1.116
erson+1.094
Neg logit contributions
thood-1.018
cas-0.966
angan-0.964
 rgb-0.963
Cry-0.951
Token from
Token ID422
Feature activation+3.83e-01

Pos logit contributions
arth+1.095
igers+1.020
heast+1.000
arian+0.987
erson+0.925
Neg logit contributions
thood-1.378
cas-1.317
angan-1.297
 rgb-1.282
beit-1.273
Token step
Token ID2239
Feature activation-5.90e-01

Pos logit contributions
arth+1.966
igers+1.890
heast+1.886
arian+1.777
erson+1.743
Neg logit contributions
thood-1.617
 rgb-1.544
cas-1.543
angan-1.535
Cry-1.519
Token would
Token ID561
Feature activation-1.92e-01

Pos logit contributions
thood+1.359
cas+1.297
 rgb+1.297
angan+1.285
Cry+1.277
Neg logit contributions
arth-2.184
igers-2.099
heast-2.094
arian-1.980
erson-1.942
Token produce
Token ID4439
Feature activation-1.94e-01

Pos logit contributions
thood+0.534
cas+0.510
 rgb+0.509
angan+0.506
Cry+0.499
Neg logit contributions
arth-0.626
igers-0.601
heast-0.601
arian-0.563
erson-0.555
Token
Token ID564
Feature activation-6.38e-02

Pos logit contributions
thood+0.560
 rgb+0.546
cas+0.546
angan+0.543
Cry+0.539
Neg logit contributions
arth-0.606
igers-0.581
heast-0.580
arian-0.543
erson-0.529
Token
Token ID250
Feature activation+5.83e-02

Pos logit contributions
thood+0.120
 rgb+0.116
cas+0.115
angan+0.113
Cry+0.112
Neg logit contributions
arth-0.263
igers-0.254
heast-0.254
arian-0.242
erson-0.237
Tokentrans
Token ID7645
Feature activation-1.45e+00

Pos logit contributions
arth+0.177
igers+0.170
heast+0.170
arian+0.159
erson+0.155
Neg logit contributions
thood-0.174
cas-0.168
angan-0.167
 rgb-0.167
Cry-0.166
Tokenuran
Token ID42211
Feature activation-1.62e-01

Pos logit contributions
thood+4.008
cas+3.989
angan+3.983
Cry+3.903
 rgb+3.893
Neg logit contributions
arth-4.369
heast-4.351
igers-4.252
arian-3.969
illes-3.914
Tokenics
Token ID873
Feature activation-5.07e-01

Pos logit contributions
thood+0.499
cas+0.481
 rgb+0.480
angan+0.479
Cry+0.473
Neg logit contributions
arth-0.478
heast-0.461
igers-0.459
arian-0.427
erson-0.419
Token
Token ID447
Feature activation-2.49e-01

Pos logit contributions
thood+1.285
cas+1.241
angan+1.241
 rgb+1.234
Cry+1.217
Neg logit contributions
arth-1.754
heast-1.698
igers-1.689
arian-1.598
erson-1.559
Token
Token ID251
Feature activation-2.10e-02

Pos logit contributions
thood+0.691
 rgb+0.663
cas+0.661
angan+0.657
Cry+0.651
Neg logit contributions
arth-0.811
igers-0.779
heast-0.778
arian-0.731
erson-0.717
Token such
Token ID884
Feature activation-1.19e+00

Pos logit contributions
thood+0.058
cas+0.056
angan+0.055
 rgb+0.055
Cry+0.055
Neg logit contributions
arth-0.069
heast-0.066
igers-0.066
arian-0.062
erson-0.060
Token to
Token ID284
Feature activation-9.36e-02

Pos logit contributions
thood+0.652
 rgb+0.635
cas+0.626
Cry+0.621
beit+0.619
Neg logit contributions
arth-0.601
igers-0.576
heast-0.566
arian-0.539
ues-0.516
Token convert
Token ID10385
Feature activation-3.29e-01

Pos logit contributions
thood+0.232
 rgb+0.224
cas+0.223
angan+0.221
Cry+0.219
Neg logit contributions
arth-0.330
heast-0.319
igers-0.319
arian-0.301
erson-0.295
Token income
Token ID3739
Feature activation-7.64e-01

Pos logit contributions
thood+0.897
cas+0.878
 rgb+0.872
angan+0.866
Cry+0.856
Neg logit contributions
arth-1.075
heast-1.045
igers-1.040
arian-0.956
erson-0.949
Token into
Token ID656
Feature activation-4.66e-01

Pos logit contributions
thood+2.016
 rgb+1.986
cas+1.975
Cry+1.937
angan+1.929
Neg logit contributions
arth-2.541
heast-2.496
igers-2.453
arian-2.244
erson-2.236
Token capital
Token ID3139
Feature activation-1.23e+00

Pos logit contributions
thood+1.173
cas+1.147
 rgb+1.137
angan+1.122
Cry+1.115
Neg logit contributions
arth-1.620
heast-1.579
igers-1.569
arian-1.454
illes-1.423
Token gains
Token ID8810
Feature activation-1.21e+00

Pos logit contributions
thood+1.977
cas+1.912
 rgb+1.890
Cry+1.866
angan+1.808
Neg logit contributions
arth-5.297
heast-5.237
igers-5.160
arian-4.792
erson-4.791
Token as
Token ID355
Feature activation+1.71e-01

Pos logit contributions
thood+2.958
cas+2.824
 rgb+2.778
angan+2.740
Cry+2.709
Neg logit contributions
arth-4.303
heast-4.273
igers-4.158
arian-3.816
erson-3.816
Token a
Token ID257
Feature activation+5.29e-01

Pos logit contributions
arth+0.541
igers+0.519
heast+0.518
arian+0.485
erson+0.476
Neg logit contributions
thood-0.491
cas-0.472
 rgb-0.472
angan-0.469
Cry-0.464
Token way
Token ID835
Feature activation-3.72e-01

Pos logit contributions
arth+1.690
igers+1.620
heast+1.619
arian+1.530
erson+1.493
Neg logit contributions
thood-1.496
 rgb-1.428
cas-1.424
angan-1.417
Cry-1.409
Token of
Token ID286
Feature activation-7.06e-01

Pos logit contributions
thood+1.132
 rgb+1.097
cas+1.078
beit+1.076
angan+1.075
Neg logit contributions
arth-1.123
igers-1.073
heast-1.054
arian-1.008
erson-0.976
Token paying
Token ID5989
Feature activation+4.70e-01

Pos logit contributions
thood+1.760
 rgb+1.719
cas+1.700
angan+1.664
Cry+1.650
Neg logit contributions
arth-2.473
heast-2.404
igers-2.378
arian-2.213
illes-2.179
Token vital
Token ID9204
Feature activation+4.28e-01

Pos logit contributions
thood+1.879
 rgb+1.840
angan+1.835
cas+1.832
beit+1.809
Neg logit contributions
arth-2.450
igers-2.385
heast-2.361
arian-2.191
illes-2.170
Token strategic
Token ID10039
Feature activation-2.21e-01

Pos logit contributions
arth+1.355
igers+1.303
heast+1.298
arian+1.216
erson+1.193
Neg logit contributions
thood-1.222
 rgb-1.178
cas-1.175
angan-1.168
Cry-1.157
Token position
Token ID2292
Feature activation+2.10e-01

Pos logit contributions
 rgb+0.658
thood+0.657
cas+0.655
angan+0.643
Cry+0.639
Neg logit contributions
arth-0.650
igers-0.631
heast-0.622
arian-0.575
erson-0.565
Token that
Token ID326
Feature activation-3.82e-01

Pos logit contributions
arth+0.680
igers+0.653
heast+0.651
arian+0.612
erson+0.600
Neg logit contributions
thood-0.583
 rgb-0.560
cas-0.559
angan-0.556
Cry-0.551
Token some
Token ID617
Feature activation-3.10e-01

Pos logit contributions
thood+0.961
 rgb+0.942
cas+0.935
beit+0.934
angan+0.926
Neg logit contributions
arth-1.297
heast-1.267
igers-1.261
arian-1.169
erson-1.151
Token fear
Token ID3252
Feature activation-1.09e+00

Pos logit contributions
thood+0.725
 rgb+0.712
cas+0.703
angan+0.699
Cry+0.688
Neg logit contributions
arth-1.113
heast-1.090
igers-1.089
arian-1.009
erson-0.996
Token is
Token ID318
Feature activation-5.76e-01

Pos logit contributions
cas+2.346
thood+2.327
Cry+2.321
 rgb+2.312
beit+2.295
Neg logit contributions
arth-3.981
heast-3.849
igers-3.829
arian-3.589
yre-3.527
Token threatened
Token ID8556
Feature activation+7.02e-01

Pos logit contributions
thood+1.514
cas+1.492
 rgb+1.484
angan+1.465
Cry+1.446
Neg logit contributions
arth-1.880
igers-1.853
heast-1.839
arian-1.697
illes-1.671
Token by
Token ID416
Feature activation-6.66e-02

Pos logit contributions
arth+2.231
igers+2.131
heast+2.128
arian+2.034
erson+1.997
Neg logit contributions
thood-1.993
angan-1.900
 rgb-1.891
cas-1.888
Cry-1.853
Token Brexit
Token ID11435
Feature activation-8.75e-01

Pos logit contributions
thood+0.193
cas+0.185
 rgb+0.185
angan+0.184
Cry+0.183
Neg logit contributions
arth-0.208
igers-0.199
heast-0.199
arian-0.186
erson-0.182
Token.
Token ID13
Feature activation-2.36e-01

Pos logit contributions
thood+2.027
cas+1.967
 rgb+1.952
angan+1.937
Cry+1.921
Neg logit contributions
arth-3.177
heast-3.100
igers-3.091
arian-2.882
erson-2.818
Tokena
Token ID64
Feature activation-2.59e-01

Pos logit contributions
arth+0.589
igers+0.556
heast+0.554
arian+0.522
erson+0.508
Neg logit contributions
thood-0.672
 rgb-0.641
cas-0.641
angan-0.641
Cry-0.635
Token Guard
Token ID4932
Feature activation+8.19e-01

Pos logit contributions
thood+0.735
 rgb+0.721
cas+0.703
Cry+0.700
angan+0.699
Neg logit contributions
arth-0.821
igers-0.797
heast-0.793
arian-0.737
erson-0.717
Token )
Token ID1267
Feature activation-1.88e-01

Pos logit contributions
arth+2.273
igers+2.122
heast+2.119
arian+2.020
erson+1.989
Neg logit contributions
thood-2.656
angan-2.556
cas-2.536
 rgb-2.525
beit-2.484
Token ->
Token ID4613
Feature activation-7.97e-01

Pos logit contributions
thood+0.606
 rgb+0.585
cas+0.584
angan+0.580
Cry+0.576
Neg logit contributions
arth-0.527
igers-0.502
heast-0.501
arian-0.466
erson-0.455
Token Option
Token ID16018
Feature activation-8.54e-02

Pos logit contributions
 rgb+2.128
thood+2.114
cas+2.059
beit+2.045
Cry+2.043
Neg logit contributions
arth-2.643
heast-2.562
igers-2.547
arian-2.370
erson-2.301
Token <
Token ID1279
Feature activation-1.15e+00

Pos logit contributions
thood+0.256
 rgb+0.249
cas+0.248
Cry+0.246
angan+0.245
Neg logit contributions
arth-0.256
heast-0.247
igers-0.247
arian-0.228
erson-0.223
Token Shared
Token ID39403
Feature activation-9.41e-02

Pos logit contributions
 rgb+3.159
thood+3.138
Cry+3.080
cas+3.076
angan+3.042
Neg logit contributions
arth-3.602
heast-3.568
igers-3.525
arian-3.203
erson-3.152
Token <
Token ID1279
Feature activation-1.28e+00

Pos logit contributions
thood+0.284
 rgb+0.274
cas+0.273
angan+0.271
Cry+0.270
Neg logit contributions
arth-0.283
igers-0.272
heast-0.271
arian-0.252
erson-0.247
Token '
Token ID705
Feature activation+2.62e-01

Pos logit contributions
thood+3.606
 rgb+3.603
angan+3.536
cas+3.510
Cry+3.491
Neg logit contributions
igers-3.870
heast-3.869
arth-3.869
arian-3.456
erson-3.433
Tokena
Token ID64
Feature activation-1.64e-01

Pos logit contributions
arth+0.785
igers+0.763
heast+0.759
arian+0.702
erson+0.690
Neg logit contributions
thood-0.786
cas-0.767
 rgb-0.766
angan-0.758
Cry-0.748
Token,
Token ID837
Feature activation-2.96e-01

Pos logit contributions
thood+0.585
cas+0.565
angan+0.562
 rgb+0.558
Cry+0.555
Neg logit contributions
arth-0.408
heast-0.382
igers-0.380
arian-0.355
erson-0.350