TOP ACTIVATIONS
MAX = 10.916

commander , Gen . Douglas MacArthur , defied him ,
worked out great . Competitive Trib es Ascend player . Sym
did not issue the total Loving v . Virginia victory that
, the Fire house in Trib eca neighborhood in New York
especially since Rep . Tom MacArthur of New Jersey authored an
will be the equivalent of Loving v . Virginia , which
HUN TER + Advent urous , Cult ured ,
bird sey e map of Brigham City , Utah in 18
16 . Pat MacArthur ( 147 ) ( 35
support the mission of New Advent and get the full contents
a person of interest at Brigham and Women 's Hospital ,
, multi - ethnic society hosp itable to all . Israeli
) who were marching on Downing Street , clashed with anti
- bad - guy , unconditional - l oyal ty -
a patient s immune system attacks the new organ
Bird sey e view of Brigham City , Utah Date :
A bench of justices H L D att u
on Nov . 8 in Vaughan , Ont . The three
For some actors , like Ford and Fisher , being in
more children than died in Hiroshima . And , you know

MIN ACTIVATIONS
MIN = -10.489

the equivalent of an Olympic gymn astics routine for the speaker
x . Just as a gymn ast s twists
ren owned perf umer Fr é d é ric Mal le
't somehow destabil ize the grid could help that jump happen
of a person who is nude or engaged in a sexual
effects here . Access to freshwater , already in limited supply
pdf © Copyright 2018 Red s Land
Copyright © 2019 The Washington Times , LLC
as Le Fort de Br é gan ç on ser a
has opened the door for nude and sexually explicit photos and
is currently over a deep gou ge in which the bedrock
. Copyright © 2019 The Washington Times , LLC
concentrations of collagen can attract contamination , they compared precision Acceler
at the sites that permitted nude photos to be posted of
applied it to the Barnett shale , a mile - and
even our well water is contaminated , Yun told
. Copyright © 2016 Else vier B . V
criminals who need to be locked up ? It depends on
in 2013 to create a mural capturing the spirit of Toronto
is going to ban most nude photos and video from publicly

INTERVAL 5.565 - 10.916
CONTAINS 0.131%

46 . 35 million that Melvin Upton Jr . is due
such as The New York Times calling on them to ban
passenger vehicles . Unlike in Uber s model ,
which was later dubbed , Zuckerberg s Law of
. It s kind of a comedy runner ,

INTERVAL 0.214 - 5.565
CONTAINS 42.650%

or highlighted how important it was for him to defend his
, further Russian inc ursions , would bring the crisis to
s bliss ful , se rene save game music
the longest and most laud atory article about The
Council member John Elder , who is also a

INTERVAL -5.137 - 0.214
CONTAINS 56.938%

potentially dangerous Trap Card . If you learn how best to
Hillary Clinton to Bernie Sanders in the primary last year .
go hand in hand to realize the full potential of process
Jay C z ark owski : And you ll
to Recap San Juan Del Sur Episode 5 Coach

INTERVAL -10.489 - -5.137
CONTAINS 0.281%

rise to 11 reviews by 2021 , and 22 by 2024
applied it to the Barnett shale , a mile - and
The move would be cheaper than raising its $ 31 -
on those who have a Lock out sol en oid which
took special care to avoid contamination . That included protecting the
Token commander
Token ID11561
Feature activation+2.58e+00

Pos logit contributions
ONES+0.323
Naz+0.316
OSP+0.304
areth+0.300
HTTP+0.280
Neg logit contributions
isine-0.424
opian-0.390
chen-0.383
ulic-0.369
 chefs-0.363
Token,
Token ID11
Feature activation-4.38e-01

Pos logit contributions
ONES+1.818
Naz+1.805
OSP+1.713
areth+1.692
Sing+1.583
Neg logit contributions
isine-2.361
opian-2.175
chen-2.124
ulic-2.063
 chefs-1.999
Token Gen
Token ID5215
Feature activation+4.62e-01

Pos logit contributions
isine+0.428
opian+0.395
chen+0.388
ulic+0.375
 chefs+0.368
Neg logit contributions
ONES-0.287
Naz-0.282
OSP-0.269
areth-0.265
HTTP-0.246
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
ONES+0.334
Naz+0.328
OSP+0.314
areth+0.311
HTTP+0.290
Neg logit contributions
isine-0.419
opian-0.384
chen-0.376
ulic-0.363
 chefs-0.356
Token Douglas
Token ID15796
Feature activation+4.10e+00

Pos logit contributions
ONES+0.382
Naz+0.375
OSP+0.360
areth+0.356
HTTP+0.333
Neg logit contributions
isine-0.455
opian-0.417
chen-0.408
ulic-0.394
 chefs-0.385
Token MacArthur
Token ID46626
Feature activation+1.09e+01

Pos logit contributions
ONES+1.573
Naz+1.493
areth+1.356
OSP+1.356
Sing+1.187
Neg logit contributions
isine-5.112
opian-4.807
chen-4.697
ulic-4.621
 chefs-4.515
Token,
Token ID11
Feature activation-1.63e-01

Pos logit contributions
Naz+6.485
ONES+6.345
OSP+5.985
areth+5.798
Sing+5.628
Neg logit contributions
isine-10.548
opian-10.101
chen-9.544
ulic-9.347
 chefs-8.992
Token defied
Token ID47437
Feature activation+9.37e-01

Pos logit contributions
isine+0.148
opian+0.136
chen+0.134
ulic+0.129
 chefs+0.127
Neg logit contributions
ONES-0.118
Naz-0.115
OSP-0.111
areth-0.110
ospels-0.103
Token him
Token ID683
Feature activation-1.69e+00

Pos logit contributions
ONES+0.704
Naz+0.689
OSP+0.665
areth+0.657
HTTP+0.616
Neg logit contributions
isine-0.826
opian-0.756
chen-0.743
ulic-0.714
 chefs-0.700
Token,
Token ID11
Feature activation-1.55e-01

Pos logit contributions
isine+1.580
opian+1.452
chen+1.430
ulic+1.376
 chefs+1.346
Neg logit contributions
ONES-1.186
Naz-1.151
OSP-1.116
areth-1.103
ospels-1.032
Token
Token ID447
Feature activation+1.86e-01

Pos logit contributions
isine+0.150
opian+0.138
chen+0.136
ulic+0.131
 chefs+0.129
Neg logit contributions
ONES-0.103
Naz-0.100
OSP-0.097
areth-0.096
ospels-0.089
Token worked
Token ID3111
Feature activation-2.14e-01

Pos logit contributions
ONES+0.220
Naz+0.216
OSP+0.206
areth+0.203
HTTP+0.189
Neg logit contributions
isine-0.318
opian-0.293
chen-0.288
ulic-0.278
 chefs-0.272
Token out
Token ID503
Feature activation+2.47e+00

Pos logit contributions
isine+0.158
opian+0.143
chen+0.140
ulic+0.133
 chefs+0.130
Neg logit contributions
ONES-0.190
Naz-0.188
areth-0.181
OSP-0.181
ospels-0.171
Token great
Token ID1049
Feature activation+1.47e+00

Pos logit contributions
ONES+1.775
Naz+1.740
OSP+1.673
areth+1.639
HTTP+1.538
Neg logit contributions
isine-2.255
opian-2.066
chen-2.026
ulic-1.953
 chefs-1.909
Token.
Token ID13
Feature activation+8.62e-01

Pos logit contributions
ONES+1.071
Naz+1.052
OSP+1.009
areth+0.998
HTTP+0.933
Neg logit contributions
isine-1.330
opian-1.219
chen-1.197
ulic-1.154
 chefs-1.129
Token Competitive
Token ID47665
Feature activation+1.12e+00

Pos logit contributions
ONES+0.643
Naz+0.632
OSP+0.607
areth+0.600
HTTP+0.562
Neg logit contributions
isine-0.763
opian-0.698
chen-0.686
ulic-0.660
 chefs-0.646
Token Trib
Token ID10841
Feature activation+1.06e+01

Pos logit contributions
ONES+0.827
Naz+0.813
OSP+0.780
areth+0.772
HTTP+0.723
Neg logit contributions
isine-1.004
opian-0.920
chen-0.904
ulic-0.869
 chefs-0.852
Tokenes
Token ID274
Feature activation+2.93e+00

Pos logit contributions
ONES+6.028
Naz+5.678
areth+5.292
OSP+5.222
Sing+4.977
Neg logit contributions
isine-10.826
opian-9.959
chen-9.861
 chefs-9.670
ulic-9.623
Token Ascend
Token ID45387
Feature activation+1.13e+00

Pos logit contributions
ONES+2.095
Naz+2.060
OSP+1.966
areth+1.945
HTTP+1.813
Neg logit contributions
isine-2.677
opian-2.456
chen-2.409
ulic-2.331
 chefs-2.275
Token player
Token ID2137
Feature activation+6.25e-01

Pos logit contributions
ONES+0.837
Naz+0.823
OSP+0.789
areth+0.780
HTTP+0.730
Neg logit contributions
isine-1.002
opian-0.917
chen-0.899
ulic-0.866
 chefs-0.846
Token.
Token ID13
Feature activation+6.93e-01

Pos logit contributions
ONES+0.458
Naz+0.450
OSP+0.432
areth+0.427
HTTP+0.399
Neg logit contributions
isine-0.561
opian-0.514
chen-0.505
ulic-0.486
 chefs-0.476
Token Sym
Token ID15845
Feature activation+6.14e-01

Pos logit contributions
ONES+0.515
Naz+0.506
OSP+0.486
areth+0.481
HTTP+0.450
Neg logit contributions
isine-0.615
opian-0.563
chen-0.553
ulic-0.532
 chefs-0.521
Token did
Token ID750
Feature activation+2.37e+00

Pos logit contributions
ONES+0.551
Naz+0.540
OSP+0.514
areth+0.505
HTTP+0.468
Neg logit contributions
isine-0.919
opian-0.853
chen-0.841
ulic-0.813
 chefs-0.799
Token not
Token ID407
Feature activation+8.31e-01

Pos logit contributions
ONES+1.955
Naz+1.926
OSP+1.853
areth+1.837
HTTP+1.733
Neg logit contributions
isine-1.912
opian-1.730
chen-1.695
ulic-1.624
 chefs-1.585
Token issue
Token ID2071
Feature activation-2.70e+00

Pos logit contributions
ONES+0.615
Naz+0.605
OSP+0.577
areth+0.574
HTTP+0.536
Neg logit contributions
isine-0.741
opian-0.676
chen-0.665
ulic-0.639
 chefs-0.624
Token the
Token ID262
Feature activation+7.35e-01

Pos logit contributions
isine+2.133
opian+1.936
chen+1.911
ulic+1.836
 chefs+1.810
Neg logit contributions
ONES-2.205
Naz-2.194
OSP-2.123
areth-2.066
ospels-1.973
Token total
Token ID2472
Feature activation+8.72e-02

Pos logit contributions
ONES+0.534
Naz+0.523
OSP+0.501
areth+0.497
HTTP+0.464
Neg logit contributions
isine-0.667
opian-0.610
chen-0.599
ulic-0.577
 chefs-0.564
Token Loving
Token ID39202
Feature activation+1.04e+01

Pos logit contributions
ONES+0.064
Naz+0.063
OSP+0.061
areth+0.060
HTTP+0.056
Neg logit contributions
isine-0.078
opian-0.071
chen-0.070
ulic-0.068
 chefs-0.066
Token v
Token ID410
Feature activation+4.96e+00

Pos logit contributions
ONES+6.329
Naz+6.034
areth+5.802
OSP+5.693
 prophets+5.436
Neg logit contributions
isine-10.366
opian-9.453
ulic-9.126
chen-9.080
 chefs-8.631
Token.
Token ID13
Feature activation+6.48e-01

Pos logit contributions
ONES+2.879
Naz+2.836
areth+2.755
OSP+2.637
CTV+2.491
Neg logit contributions
isine-5.095
opian-4.732
ulic-4.479
chen-4.434
untled-4.317
Token Virginia
Token ID6025
Feature activation+4.84e-01

Pos logit contributions
ONES+0.588
Naz+0.580
OSP+0.561
areth+0.556
HTTP+0.528
Neg logit contributions
isine-0.469
opian-0.420
chen-0.410
ulic-0.392
 chefs-0.380
Token victory
Token ID5373
Feature activation+3.35e+00

Pos logit contributions
ONES+0.321
Naz+0.318
OSP+0.303
areth+0.298
HTTP+0.277
Neg logit contributions
isine-0.466
opian-0.431
chen-0.425
ulic-0.409
 chefs-0.403
Token that
Token ID326
Feature activation+6.40e-01

Pos logit contributions
ONES+2.453
Naz+2.404
OSP+2.306
areth+2.283
HTTP+2.141
Neg logit contributions
isine-3.015
opian-2.761
chen-2.701
ulic-2.610
 chefs-2.536
Token,
Token ID11
Feature activation+2.90e-01

Pos logit contributions
ONES+2.621
Naz+2.590
OSP+2.458
areth+2.453
HTTP+2.268
Neg logit contributions
isine-3.480
opian-3.203
chen-3.127
ulic-3.026
 chefs-2.944
Token the
Token ID262
Feature activation-6.59e-02

Pos logit contributions
ONES+0.224
Naz+0.220
OSP+0.212
areth+0.210
HTTP+0.197
Neg logit contributions
isine-0.249
opian-0.227
chen-0.223
ulic-0.214
 chefs-0.210
Token Fire
Token ID3764
Feature activation-1.86e+00

Pos logit contributions
isine+0.056
opian+0.051
chen+0.050
ulic+0.048
 chefs+0.047
Neg logit contributions
ONES-0.051
Naz-0.050
OSP-0.048
areth-0.048
HTTP-0.045
Tokenhouse
Token ID4803
Feature activation-9.76e-02

Pos logit contributions
isine+1.552
chen+1.422
opian+1.416
ulic+1.347
 chefs+1.312
Neg logit contributions
ONES-1.472
Naz-1.453
OSP-1.395
areth-1.376
HTTP-1.294
Token in
Token ID287
Feature activation-1.19e+00

Pos logit contributions
isine+0.085
opian+0.078
chen+0.077
ulic+0.074
 chefs+0.072
Neg logit contributions
ONES-0.074
Naz-0.073
OSP-0.070
areth-0.069
HTTP-0.065
Token Trib
Token ID10841
Feature activation+1.03e+01

Pos logit contributions
isine+0.989
opian+0.905
chen+0.892
ulic+0.850
 chefs+0.836
Neg logit contributions
ONES-0.947
Naz-0.928
OSP-0.901
areth-0.889
HTTP-0.840
Tokeneca
Token ID31047
Feature activation+1.99e+00

Pos logit contributions
ONES+9.667
Naz+9.383
areth+9.206
OSP+9.040
ospels+8.675
Neg logit contributions
isine-6.621
opian-5.613
 chefs-5.437
chen-5.432
ulic-5.345
Token neighborhood
Token ID6232
Feature activation+1.64e+00

Pos logit contributions
ONES+1.407
Naz+1.382
OSP+1.323
areth+1.309
HTTP+1.220
Neg logit contributions
isine-1.833
opian-1.685
chen-1.654
ulic-1.596
 chefs-1.561
Token in
Token ID287
Feature activation-5.15e-01

Pos logit contributions
ONES+1.201
Naz+1.181
OSP+1.133
areth+1.120
HTTP+1.048
Neg logit contributions
isine-1.472
opian-1.349
chen-1.324
ulic-1.276
 chefs-1.248
Token New
Token ID968
Feature activation+1.46e+00

Pos logit contributions
isine+0.436
opian+0.400
chen+0.393
ulic+0.376
 chefs+0.369
Neg logit contributions
ONES-0.401
Naz-0.395
OSP-0.381
areth-0.376
HTTP-0.355
Token York
Token ID1971
Feature activation+4.06e-01

Pos logit contributions
ONES+1.178
Naz+1.155
OSP+1.117
areth+1.099
HTTP+1.039
Neg logit contributions
isine-1.201
opian-1.094
chen-1.076
ulic-1.030
 chefs-1.006
Token especially
Token ID2592
Feature activation-1.55e+00

Pos logit contributions
ONES+0.097
Naz+0.096
OSP+0.091
areth+0.090
HTTP+0.084
Neg logit contributions
isine-0.131
opian-0.121
chen-0.119
ulic-0.115
 chefs-0.112
Token since
Token ID1201
Feature activation-2.49e+00

Pos logit contributions
isine+1.263
opian+1.147
chen+1.132
ulic+1.082
 chefs+1.064
Neg logit contributions
ONES-1.253
Naz-1.237
OSP-1.189
areth-1.181
ospels-1.113
Token Rep
Token ID1432
Feature activation+7.35e-01

Pos logit contributions
isine+2.025
opian+1.840
chen+1.819
ulic+1.738
 chefs+1.725
Neg logit contributions
ONES-2.022
Naz-1.996
OSP-1.910
areth-1.902
HTTP-1.793
Token.
Token ID13
Feature activation-1.26e+00

Pos logit contributions
ONES+0.554
Naz+0.548
OSP+0.525
areth+0.520
HTTP+0.492
Neg logit contributions
isine-0.644
opian-0.589
chen-0.582
ulic-0.562
 chefs-0.545
Token Tom
Token ID4186
Feature activation-7.17e-01

Pos logit contributions
isine+1.109
opian+1.015
chen+1.005
ulic+0.964
 chefs+0.945
Neg logit contributions
ONES-0.934
Naz-0.921
OSP-0.884
areth-0.876
HTTP-0.823
Token MacArthur
Token ID46626
Feature activation+1.03e+01

Pos logit contributions
isine+0.653
opian+0.598
chen+0.592
ulic+0.572
 chefs+0.558
Neg logit contributions
ONES-0.514
Naz-0.508
OSP-0.482
areth-0.478
HTTP-0.448
Token of
Token ID286
Feature activation-6.45e-01

Pos logit contributions
ONES+6.124
Naz+5.980
OSP+5.783
areth+5.533
Sing+5.316
Neg logit contributions
isine-10.074
opian-9.283
chen-8.803
ulic-8.797
untled-8.429
Token New
Token ID968
Feature activation+1.04e+00

Pos logit contributions
isine+0.512
opian+0.464
chen+0.456
ulic+0.436
 chefs+0.427
Neg logit contributions
ONES-0.537
Naz-0.529
OSP-0.511
areth-0.506
ospels-0.479
Token Jersey
Token ID8221
Feature activation-9.77e-01

Pos logit contributions
ONES+0.909
Naz+0.893
OSP+0.867
areth+0.855
HTTP+0.812
Neg logit contributions
isine-0.785
opian-0.707
chen-0.696
ulic-0.663
 chefs-0.647
Token authored
Token ID33941
Feature activation+3.63e-01

Pos logit contributions
isine+0.921
opian+0.848
chen+0.839
ulic+0.804
 chefs+0.796
Neg logit contributions
ONES-0.669
Naz-0.660
OSP-0.628
areth-0.621
ospels-0.581
Token an
Token ID281
Feature activation+7.53e-01

Pos logit contributions
ONES+0.284
Naz+0.280
OSP+0.268
areth+0.266
HTTP+0.250
Neg logit contributions
isine-0.308
opian-0.281
chen-0.276
ulic-0.264
 chefs-0.259
Token will
Token ID481
Feature activation-1.15e+00

Pos logit contributions
ONES+0.873
Naz+0.856
OSP+0.816
areth+0.806
HTTP+0.746
Neg logit contributions
isine-1.332
opian-1.230
chen-1.208
ulic-1.170
 chefs-1.144
Token be
Token ID307
Feature activation+7.45e-01

Pos logit contributions
isine+0.973
opian+0.892
chen+0.878
ulic+0.842
 chefs+0.826
Neg logit contributions
ONES-0.898
Naz-0.885
OSP-0.852
areth-0.840
ospels-0.792
Token the
Token ID262
Feature activation-1.29e+00

Pos logit contributions
ONES+0.551
Naz+0.540
OSP+0.518
areth+0.514
HTTP+0.481
Neg logit contributions
isine-0.665
opian-0.609
chen-0.596
ulic-0.575
 chefs-0.562
Token equivalent
Token ID7548
Feature activation+1.18e+00

Pos logit contributions
isine+0.969
opian+0.879
chen+0.857
ulic+0.820
 chefs+0.801
Neg logit contributions
ONES-1.129
Naz-1.119
OSP-1.080
areth-1.070
ospels-1.014
Token of
Token ID286
Feature activation-9.87e-01

Pos logit contributions
ONES+0.945
Naz+0.936
OSP+0.896
areth+0.888
HTTP+0.837
Neg logit contributions
isine-0.969
opian-0.894
chen-0.871
ulic-0.837
 chefs-0.818
Token Loving
Token ID39202
Feature activation+9.99e+00

Pos logit contributions
isine+0.817
opian+0.745
chen+0.731
ulic+0.701
 chefs+0.690
Neg logit contributions
ONES-0.786
Naz-0.778
OSP-0.748
areth-0.740
ospels-0.698
Token v
Token ID410
Feature activation+4.66e+00

Pos logit contributions
ONES+5.332
Naz+5.183
OSP+4.761
areth+4.724
HTTP+4.453
Neg logit contributions
isine-10.577
opian-9.678
chen-9.316
ulic-9.286
 chefs-8.948
Token.
Token ID13
Feature activation+8.09e-01

Pos logit contributions
Naz+2.795
ONES+2.795
areth+2.600
OSP+2.577
Sing+2.445
Neg logit contributions
isine-4.813
opian-4.419
ulic-4.196
chen-4.158
untled-4.058
Token Virginia
Token ID6025
Feature activation+7.96e-01

Pos logit contributions
ONES+0.733
Naz+0.724
OSP+0.699
areth+0.694
HTTP+0.658
Neg logit contributions
isine-0.587
opian-0.525
chen-0.513
ulic-0.490
 chefs-0.476
Token,
Token ID11
Feature activation+2.43e-01

Pos logit contributions
ONES+0.572
Naz+0.563
OSP+0.539
areth+0.533
HTTP+0.498
Neg logit contributions
isine-0.726
opian-0.666
chen-0.655
ulic-0.631
 chefs-0.618
Token which
Token ID543
Feature activation+1.68e+00

Pos logit contributions
ONES+0.180
Naz+0.177
OSP+0.170
areth+0.168
HTTP+0.158
Neg logit contributions
isine-0.217
opian-0.198
chen-0.195
ulic-0.188
 chefs-0.183
Token HUN
Token ID41041
Feature activation+5.53e-01

Pos logit contributions
isine+1.304
opian+1.193
chen+1.176
ulic+1.123
 chefs+1.107
Neg logit contributions
ONES-1.146
Naz-1.137
OSP-1.086
areth-1.079
ospels-1.013
TokenTER
Token ID5781
Feature activation+1.09e+00

Pos logit contributions
ONES+0.352
Naz+0.345
OSP+0.329
areth+0.325
ospels+0.300
Neg logit contributions
isine-0.550
opian-0.509
chen-0.501
ulic-0.484
 chefs-0.475
Token
Token ID198
Feature activation-8.57e-01

Pos logit contributions
ONES+0.796
Naz+0.782
OSP+0.750
areth+0.741
HTTP+0.694
Neg logit contributions
isine-0.981
opian-0.899
chen-0.882
ulic-0.850
 chefs-0.832
Token
Token ID198
Feature activation-7.89e-01

Pos logit contributions
isine+0.855
opian+0.789
chen+0.769
ulic+0.751
 chefs+0.738
Neg logit contributions
ONES-0.551
Naz-0.544
OSP-0.514
areth-0.506
HTTP-0.472
Token+
Token ID10
Feature activation-3.52e-01

Pos logit contributions
isine+0.794
opian+0.735
chen+0.731
ulic+0.702
 chefs+0.685
Neg logit contributions
ONES-0.477
Naz-0.466
areth-0.446
OSP-0.444
ospels-0.413
Token Advent
Token ID33732
Feature activation+9.77e+00

Pos logit contributions
isine+0.322
opian+0.295
chen+0.290
ulic+0.280
 chefs+0.274
Neg logit contributions
ONES-0.251
Naz-0.248
OSP-0.237
areth-0.235
HTTP-0.219
Tokenurous
Token ID29277
Feature activation+3.37e+00

Pos logit contributions
ONES+7.139
Naz+7.031
areth+6.739
OSP+6.704
 wip+6.278
Neg logit contributions
isine-8.289
opian-7.416
chen-7.313
ulic-7.138
 chefs-6.880
Token,
Token ID11
Feature activation+9.29e-01

Pos logit contributions
ONES+2.657
Naz+2.613
OSP+2.518
areth+2.492
HTTP+2.342
Neg logit contributions
isine-2.812
opian-2.560
chen-2.496
ulic-2.417
 chefs-2.319
Token Cult
Token ID22449
Feature activation+9.93e-01

Pos logit contributions
ONES+0.731
Naz+0.720
OSP+0.692
areth+0.685
HTTP+0.644
Neg logit contributions
isine-0.784
opian-0.715
chen-0.701
ulic-0.673
 chefs-0.658
Tokenured
Token ID1522
Feature activation+6.39e-01

Pos logit contributions
ONES+0.931
Naz+0.920
OSP+0.891
areth+0.883
HTTP+0.838
Neg logit contributions
isine-0.685
opian-0.609
chen-0.595
ulic-0.567
 chefs-0.549
Token,
Token ID11
Feature activation+1.09e+00

Pos logit contributions
ONES+0.475
Naz+0.467
OSP+0.448
areth+0.443
HTTP+0.415
Neg logit contributions
isine-0.567
opian-0.519
chen-0.510
ulic-0.490
 chefs-0.481
Token bird
Token ID6512
Feature activation-2.21e-01

Pos logit contributions
isine+0.649
opian+0.593
chen+0.581
ulic+0.556
 chefs+0.547
Neg logit contributions
ONES-0.619
Naz-0.610
OSP-0.587
areth-0.583
HTTP-0.548
Tokensey
Token ID4397
Feature activation+3.03e-01

Pos logit contributions
isine+0.200
opian+0.184
chen+0.181
ulic+0.173
 chefs+0.171
Neg logit contributions
ONES-0.161
Naz-0.157
OSP-0.151
areth-0.150
HTTP-0.140
Tokene
Token ID68
Feature activation-6.54e-01

Pos logit contributions
ONES+0.143
Naz+0.138
OSP+0.131
areth+0.127
HTTP+0.116
Neg logit contributions
isine-0.351
opian-0.329
chen-0.324
ulic-0.315
 chefs-0.310
Token map
Token ID3975
Feature activation-1.64e+00

Pos logit contributions
isine+0.586
opian+0.538
chen+0.530
ulic+0.508
 chefs+0.500
Neg logit contributions
ONES-0.479
Naz-0.471
OSP-0.453
areth-0.447
HTTP-0.419
Token of
Token ID286
Feature activation+8.90e-01

Pos logit contributions
isine+1.481
opian+1.364
chen+1.347
ulic+1.291
 chefs+1.264
Neg logit contributions
ONES-1.186
Naz-1.170
OSP-1.119
areth-1.108
HTTP-1.033
Token Brigham
Token ID37434
Feature activation+9.62e+00

Pos logit contributions
ONES+0.715
Naz+0.704
OSP+0.679
areth+0.672
HTTP+0.633
Neg logit contributions
isine-0.735
opian-0.669
chen-0.656
ulic-0.629
 chefs-0.618
Token City
Token ID2254
Feature activation+9.11e-01

Pos logit contributions
ONES+6.966
Naz+6.677
OSP+6.533
areth+6.505
 prophets+6.117
Neg logit contributions
isine-8.422
opian-7.622
chen-7.437
ulic-7.201
 chefs-7.030
Token,
Token ID11
Feature activation+5.51e-01

Pos logit contributions
ONES+0.637
Naz+0.627
OSP+0.599
areth+0.591
HTTP+0.552
Neg logit contributions
isine-0.848
opian-0.781
chen-0.767
ulic-0.738
 chefs-0.727
Token Utah
Token ID10202
Feature activation+1.03e+00

Pos logit contributions
ONES+0.378
Naz+0.371
OSP+0.355
areth+0.351
HTTP+0.327
Neg logit contributions
isine-0.519
opian-0.478
chen-0.470
ulic-0.454
 chefs-0.445
Token in
Token ID287
Feature activation+3.89e-03

Pos logit contributions
ONES+0.713
Naz+0.700
OSP+0.670
areth+0.662
HTTP+0.617
Neg logit contributions
isine-0.966
opian-0.889
chen-0.873
ulic-0.843
 chefs-0.825
Token 18
Token ID1248
Feature activation-1.10e+00

Pos logit contributions
ONES+0.003
Naz+0.003
OSP+0.003
areth+0.003
HTTP+0.003
Neg logit contributions
isine-0.003
opian-0.003
chen-0.003
ulic-0.002
 chefs-0.002
Token
Token ID198
Feature activation-2.38e-01

Pos logit contributions
ONES+0.290
Naz+0.285
OSP+0.274
areth+0.270
HTTP+0.255
Neg logit contributions
isine-0.367
opian-0.337
chen-0.334
ulic-0.320
 chefs-0.314
Token
Token ID198
Feature activation-2.61e-01

Pos logit contributions
isine+0.239
opian+0.220
chen+0.214
ulic+0.209
 chefs+0.206
Neg logit contributions
ONES-0.152
Naz-0.151
OSP-0.142
areth-0.140
HTTP-0.130
Token16
Token ID1433
Feature activation-1.63e+00

Pos logit contributions
isine+0.260
opian+0.241
chen+0.241
ulic+0.230
 chefs+0.225
Neg logit contributions
ONES-0.160
Naz-0.155
OSP-0.149
areth-0.148
 wip-0.139
Token.
Token ID13
Feature activation+9.54e-01

Pos logit contributions
isine+1.354
chen+1.243
opian+1.223
ulic+1.161
 chefs+1.142
Neg logit contributions
ONES-1.272
Naz-1.239
OSP-1.211
areth-1.185
HTTP-1.136
Token Pat
Token ID3208
Feature activation+5.85e-01

Pos logit contributions
ONES+0.672
Naz+0.661
OSP+0.635
areth+0.625
HTTP+0.589
Neg logit contributions
isine-0.877
opian-0.805
chen-0.798
ulic-0.764
 chefs-0.749
Token MacArthur
Token ID46626
Feature activation+9.58e+00

Pos logit contributions
ONES+0.451
Naz+0.444
OSP+0.426
areth+0.420
HTTP+0.397
Neg logit contributions
isine-0.504
opian-0.461
chen-0.454
ulic-0.434
 chefs-0.424
Token (
Token ID357
Feature activation+8.37e-02

Pos logit contributions
ONES+5.923
Naz+5.765
OSP+5.541
areth+5.422
Sing+5.066
Neg logit contributions
isine-9.274
opian-8.633
chen-8.184
ulic-7.967
 chefs-7.935
Token147
Token ID20198
Feature activation-2.07e+00

Pos logit contributions
ONES+0.054
Naz+0.053
OSP+0.050
areth+0.050
ospels+0.046
Neg logit contributions
isine-0.082
opian-0.076
chen-0.075
ulic-0.073
 chefs-0.071
Token)
Token ID8
Feature activation+5.58e-01

Pos logit contributions
isine+1.917
opian+1.762
chen+1.744
ulic+1.675
 chefs+1.638
Neg logit contributions
ONES-1.449
Naz-1.420
OSP-1.362
areth-1.346
HTTP-1.259
Token (
Token ID357
Feature activation+7.65e-01

Pos logit contributions
ONES+0.408
Naz+0.401
OSP+0.384
areth+0.384
ospels+0.359
Neg logit contributions
isine-0.500
opian-0.457
chen-0.453
ulic-0.434
 chefs-0.424
Token35
Token ID2327
Feature activation+2.27e-01

Pos logit contributions
ONES+0.494
Naz+0.486
OSP+0.462
areth+0.455
HTTP+0.424
Neg logit contributions
isine-0.760
opian-0.701
chen-0.685
ulic-0.666
 chefs-0.655
Token support
Token ID1104
Feature activation+2.89e+00

Pos logit contributions
isine+0.485
opian+0.450
chen+0.446
ulic+0.429
 chefs+0.427
Neg logit contributions
ONES-0.251
Naz-0.244
OSP-0.231
areth-0.226
ospels-0.207
Token the
Token ID262
Feature activation-6.67e-01

Pos logit contributions
ONES+2.158
Naz+2.129
OSP+2.044
areth+2.015
HTTP+1.892
Neg logit contributions
isine-2.542
opian-2.337
chen-2.276
ulic-2.218
 chefs-2.142
Token mission
Token ID4365
Feature activation-2.61e-01

Pos logit contributions
isine+0.624
opian+0.577
chen+0.562
ulic+0.544
 chefs+0.530
Neg logit contributions
ONES-0.465
Naz-0.460
OSP-0.437
areth-0.431
HTTP-0.402
Token of
Token ID286
Feature activation-2.41e-01

Pos logit contributions
isine+0.225
opian+0.206
chen+0.201
ulic+0.194
 chefs+0.190
Neg logit contributions
ONES-0.200
Naz-0.197
OSP-0.190
areth-0.188
HTTP-0.176
Token New
Token ID968
Feature activation+1.36e+00

Pos logit contributions
isine+0.216
opian+0.198
chen+0.195
ulic+0.188
 chefs+0.184
Neg logit contributions
ONES-0.176
Naz-0.173
OSP-0.166
areth-0.164
HTTP-0.153
Token Advent
Token ID33732
Feature activation+9.32e+00

Pos logit contributions
ONES+0.265
Naz+0.239
OSP+0.207
areth+0.193
ospels+0.133
Neg logit contributions
isine-1.953
opian-1.859
chen-1.836
ulic-1.797
 chefs-1.775
Token and
Token ID290
Feature activation+9.50e-01

Pos logit contributions
ONES+4.061
Naz+4.000
areth+3.879
OSP+3.476
Sing+3.466
Neg logit contributions
isine-10.769
opian-9.914
ulic-9.798
chen-9.660
untled-9.546
Token get
Token ID651
Feature activation+1.12e-01

Pos logit contributions
ONES+0.672
Naz+0.652
OSP+0.628
areth+0.615
ospels+0.576
Neg logit contributions
isine-0.881
opian-0.818
chen-0.808
ulic-0.775
 chefs-0.762
Token the
Token ID262
Feature activation-1.84e+00

Pos logit contributions
ONES+0.092
Naz+0.089
areth+0.086
OSP+0.086
ospels+0.081
Neg logit contributions
isine-0.090
opian-0.082
chen-0.081
ulic-0.077
 chefs-0.077
Token full
Token ID1336
Feature activation-1.59e+00

Pos logit contributions
isine+1.178
chen+1.060
opian+1.044
 chefs+0.991
ulic+0.961
Neg logit contributions
ONES-1.770
Naz-1.669
OSP-1.666
areth-1.633
HTTP-1.614
Token contents
Token ID10154
Feature activation-1.43e+00

Pos logit contributions
isine+1.246
opian+1.120
chen+1.103
ulic+1.049
 chefs+1.030
Neg logit contributions
ONES-1.351
Naz-1.322
OSP-1.281
areth-1.267
HTTP-1.198
Token a
Token ID257
Feature activation+8.12e-01

Pos logit contributions
ONES+1.877
Naz+1.838
OSP+1.769
areth+1.745
ospels+1.642
Neg logit contributions
isine-2.055
opian-1.878
chen-1.824
ulic-1.762
 chefs-1.693
Token person
Token ID1048
Feature activation-2.47e+00

Pos logit contributions
ONES+0.656
Naz+0.648
OSP+0.624
areth+0.613
HTTP+0.581
Neg logit contributions
isine-0.667
opian-0.607
chen-0.589
ulic-0.567
 chefs-0.551
Token of
Token ID286
Feature activation-1.25e+00

Pos logit contributions
isine+1.982
chen+1.772
opian+1.771
ulic+1.672
 chefs+1.655
Neg logit contributions
ONES-2.040
Naz-2.002
OSP-1.932
areth-1.929
ospels-1.819
Token interest
Token ID1393
Feature activation-1.34e+00

Pos logit contributions
isine+1.233
opian+1.139
chen+1.128
ulic+1.078
 chefs+1.070
Neg logit contributions
ONES-0.812
Naz-0.795
OSP-0.757
areth-0.753
HTTP-0.694
Token at
Token ID379
Feature activation-5.76e-01

Pos logit contributions
isine+1.030
opian+0.928
chen+0.913
ulic+0.869
 chefs+0.850
Neg logit contributions
ONES-1.156
Naz-1.139
OSP-1.100
areth-1.090
ospels-1.031
Token Brigham
Token ID37434
Feature activation+9.26e+00

Pos logit contributions
isine+0.481
opian+0.439
chen+0.433
ulic+0.413
 chefs+0.405
Neg logit contributions
ONES-0.457
Naz-0.450
OSP-0.432
areth-0.429
HTTP-0.405
Token and
Token ID290
Feature activation-8.71e-01

Pos logit contributions
ONES+6.483
OSP+6.155
Naz+6.149
areth+5.962
 prophets+5.580
Neg logit contributions
isine-8.341
opian-7.624
chen-7.362
ulic-7.083
 chefs-6.945
Token Women
Token ID6926
Feature activation-2.43e+00

Pos logit contributions
isine+0.920
opian+0.856
chen+0.845
ulic+0.816
 chefs+0.802
Neg logit contributions
ONES-0.499
Naz-0.489
OSP-0.459
areth-0.454
HTTP-0.418
Token's
Token ID338
Feature activation-7.49e-01

Pos logit contributions
isine+2.368
opian+2.182
chen+2.134
ulic+2.075
 chefs+2.027
Neg logit contributions
ONES-1.594
Naz-1.578
OSP-1.508
areth-1.486
HTTP-1.372
Token Hospital
Token ID9256
Feature activation+9.52e-01

Pos logit contributions
isine+0.752
opian+0.697
chen+0.694
ulic+0.664
 chefs+0.655
Neg logit contributions
ONES-0.469
Naz-0.457
OSP-0.429
areth-0.429
HTTP-0.397
Token,
Token ID11
Feature activation-7.51e-01

Pos logit contributions
ONES+0.723
Naz+0.711
OSP+0.684
areth+0.676
HTTP+0.634
Neg logit contributions
isine-0.829
opian-0.759
chen-0.743
ulic-0.716
 chefs-0.699
Token,
Token ID11
Feature activation+1.65e+00

Pos logit contributions
isine+0.329
opian+0.303
chen+0.299
ulic+0.285
 chefs+0.284
Neg logit contributions
ONES-0.254
Naz-0.249
OSP-0.239
areth-0.235
HTTP-0.222
Token multi
Token ID5021
Feature activation+1.65e+00

Pos logit contributions
ONES+1.276
Naz+1.262
OSP+1.209
areth+1.197
HTTP+1.125
Neg logit contributions
isine-1.410
opian-1.279
chen-1.251
ulic-1.209
 chefs-1.175
Token-
Token ID12
Feature activation+5.67e-01

Pos logit contributions
ONES+1.007
Naz+0.977
OSP+0.928
areth+0.915
HTTP+0.840
Neg logit contributions
isine-1.701
opian-1.567
chen-1.549
ulic-1.502
 chefs-1.466
Tokenethnic
Token ID38546
Feature activation+3.68e+00

Pos logit contributions
ONES+0.469
Naz+0.459
OSP+0.445
areth+0.441
HTTP+0.415
Neg logit contributions
isine-0.457
opian-0.413
chen-0.407
ulic-0.389
 chefs-0.377
Token society
Token ID3592
Feature activation+1.92e+00

Pos logit contributions
ONES+2.411
Naz+2.367
OSP+2.255
areth+2.238
HTTP+2.061
Neg logit contributions
isine-3.580
opian-3.305
chen-3.240
ulic-3.150
 chefs-3.072
Token hosp
Token ID10496
Feature activation+8.87e+00

Pos logit contributions
ONES+1.531
Naz+1.506
OSP+1.449
areth+1.431
HTTP+1.345
Neg logit contributions
isine-1.600
opian-1.451
chen-1.422
ulic-1.370
 chefs-1.329
Tokenitable
Token ID4674
Feature activation+3.61e+00

Pos logit contributions
ONES+5.275
Naz+5.218
areth+5.130
OSP+5.012
Sing+4.678
Neg logit contributions
isine-8.281
opian-7.696
 chefs-7.331
chen-7.328
ulic-7.291
Token to
Token ID284
Feature activation+1.49e-01

Pos logit contributions
ONES+2.558
Naz+2.517
OSP+2.409
areth+2.381
HTTP+2.220
Neg logit contributions
isine-3.311
opian-3.039
chen-2.986
ulic-2.884
 chefs-2.822
Token all
Token ID477
Feature activation+6.98e-02

Pos logit contributions
ONES+0.122
Naz+0.120
OSP+0.116
areth+0.115
HTTP+0.109
Neg logit contributions
isine-0.121
opian-0.110
chen-0.108
ulic-0.103
 chefs-0.101
Token.
Token ID13
Feature activation-9.48e-02

Pos logit contributions
ONES+0.052
Naz+0.051
OSP+0.049
areth+0.048
HTTP+0.046
Neg logit contributions
isine-0.062
opian-0.057
chen-0.056
ulic-0.053
 chefs-0.053
Token Israeli
Token ID6085
Feature activation+4.57e+00

Pos logit contributions
isine+0.088
opian+0.081
chen+0.080
ulic+0.077
 chefs+0.075
Neg logit contributions
ONES-0.066
Naz-0.065
OSP-0.062
areth-0.061
HTTP-0.057
Token)
Token ID8
Feature activation+1.13e+00

Pos logit contributions
ONES+0.325
Naz+0.316
OSP+0.306
areth+0.305
 wip+0.283
Neg logit contributions
isine-0.394
chen-0.360
opian-0.359
ulic-0.345
 chefs-0.335
Token who
Token ID508
Feature activation+3.44e+00

Pos logit contributions
ONES+0.795
Naz+0.780
OSP+0.747
areth+0.738
HTTP+0.689
Neg logit contributions
isine-1.046
opian-0.962
chen-0.945
ulic-0.911
 chefs-0.893
Token were
Token ID547
Feature activation+1.80e+00

Pos logit contributions
ONES+2.348
Naz+2.331
OSP+2.206
areth+2.194
HTTP+2.027
Neg logit contributions
isine-3.249
opian-2.980
chen-2.907
ulic-2.829
 chefs-2.749
Token marching
Token ID26409
Feature activation+1.49e+00

Pos logit contributions
ONES+1.432
Naz+1.422
OSP+1.358
areth+1.348
HTTP+1.265
Neg logit contributions
isine-1.508
opian-1.377
chen-1.337
ulic-1.289
 chefs-1.247
Token on
Token ID319
Feature activation+8.19e-01

Pos logit contributions
ONES+1.187
Naz+1.174
OSP+1.124
areth+1.117
HTTP+1.049
Neg logit contributions
isine-1.235
opian-1.122
chen-1.099
ulic-1.056
 chefs-1.029
Token Downing
Token ID31355
Feature activation+8.61e+00

Pos logit contributions
ONES+0.630
Naz+0.617
OSP+0.597
areth+0.589
HTTP+0.554
Neg logit contributions
isine-0.706
opian-0.646
chen-0.633
ulic-0.608
 chefs-0.598
Token Street
Token ID3530
Feature activation+4.10e+00

Pos logit contributions
ONES+5.246
Naz+5.103
areth+4.943
OSP+4.870
ships+4.487
Neg logit contributions
isine-8.540
opian-7.897
chen-7.479
ulic-7.370
 chefs-7.205
Token,
Token ID11
Feature activation+1.02e+00

Pos logit contributions
ONES+2.937
Naz+2.902
OSP+2.760
areth+2.756
HTTP+2.552
Neg logit contributions
isine-3.726
opian-3.423
chen-3.325
ulic-3.228
 chefs-3.140
Token clashed
Token ID37003
Feature activation-1.87e+00

Pos logit contributions
ONES+0.743
Naz+0.730
OSP+0.701
areth+0.692
HTTP+0.648
Neg logit contributions
isine-0.918
opian-0.842
chen-0.828
ulic-0.797
 chefs-0.780
Token with
Token ID351
Feature activation+1.40e+00

Pos logit contributions
isine+1.503
opian+1.366
chen+1.347
ulic+1.284
 chefs+1.278
Neg logit contributions
ONES-1.526
Naz-1.504
OSP-1.472
areth-1.446
ospels-1.377
Token anti
Token ID3098
Feature activation+3.68e+00

Pos logit contributions
ONES+1.103
Naz+1.086
OSP+1.042
areth+1.032
HTTP+0.970
Neg logit contributions
isine-1.189
opian-1.084
chen-1.062
ulic-1.020
 chefs-0.994
Token-
Token ID12
Feature activation-1.80e-01

Pos logit contributions
isine+0.036
opian+0.034
chen+0.033
ulic+0.032
 chefs+0.032
Neg logit contributions
ONES-0.019
Naz-0.019
OSP-0.018
areth-0.018
HTTP-0.016
Tokenbad
Token ID14774
Feature activation-3.26e-01

Pos logit contributions
isine+0.155
opian+0.142
chen+0.141
ulic+0.132
 chefs+0.129
Neg logit contributions
ONES-0.140
Naz-0.136
OSP-0.133
areth-0.131
ospels-0.123
Token-
Token ID12
Feature activation-4.78e-01

Pos logit contributions
isine+0.321
opian+0.294
chen+0.292
ulic+0.279
 chefs+0.276
Neg logit contributions
ONES-0.212
Naz-0.206
OSP-0.197
areth-0.195
ospels-0.182
Tokenguy
Token ID22932
Feature activation+1.72e+00

Pos logit contributions
isine+0.348
opian+0.310
chen+0.308
ulic+0.286
 chefs+0.278
Neg logit contributions
ONES-0.431
Naz-0.424
OSP-0.413
areth-0.405
ospels-0.387
Token,
Token ID11
Feature activation+5.34e-01

Pos logit contributions
ONES+1.336
Naz+1.316
OSP+1.264
areth+1.253
HTTP+1.177
Neg logit contributions
isine-1.471
opian-1.343
chen-1.315
ulic-1.266
 chefs-1.235
Token unconditional
Token ID42423
Feature activation+8.55e+00

Pos logit contributions
ONES+0.386
Naz+0.378
OSP+0.365
areth+0.359
ospels+0.336
Neg logit contributions
isine-0.486
opian-0.446
chen-0.438
ulic-0.421
 chefs-0.414
Token-
Token ID12
Feature activation-2.25e-02

Pos logit contributions
Naz+5.811
ONES+5.685
OSP+5.341
areth+5.314
 wip+5.132
Neg logit contributions
isine-7.725
opian-6.985
chen-6.887
ulic-6.797
untled-6.498
Tokenl
Token ID75
Feature activation-2.25e-02

Pos logit contributions
isine+0.019
opian+0.018
chen+0.018
ulic+0.017
 chefs+0.016
Neg logit contributions
ONES-0.017
Naz-0.017
OSP-0.016
areth-0.016
ospels-0.015
Tokenoyal
Token ID4815
Feature activation+3.45e+00

Pos logit contributions
isine+0.019
opian+0.018
chen+0.017
ulic+0.017
 chefs+0.016
Neg logit contributions
ONES-0.017
Naz-0.017
OSP-0.016
areth-0.016
HTTP-0.015
Tokenty
Token ID774
Feature activation+2.23e+00

Pos logit contributions
ONES+2.738
Naz+2.705
OSP+2.600
areth+2.578
HTTP+2.423
Neg logit contributions
isine-2.877
opian-2.617
chen-2.565
ulic-2.472
 chefs-2.405
Token-
Token ID12
Feature activation+1.02e-01

Pos logit contributions
ONES+1.554
Naz+1.527
OSP+1.461
areth+1.444
HTTP+1.346
Neg logit contributions
isine-2.080
opian-1.913
chen-1.879
ulic-1.813
 chefs-1.776
Token a
Token ID257
Feature activation+1.03e-02

Pos logit contributions
ONES+0.537
Naz+0.528
OSP+0.508
areth+0.502
HTTP+0.471
Neg logit contributions
isine-0.602
opian-0.549
chen-0.539
ulic-0.519
 chefs-0.505
Token patient
Token ID5827
Feature activation-2.99e+00

Pos logit contributions
ONES+0.008
Naz+0.007
OSP+0.007
areth+0.007
HTTP+0.007
Neg logit contributions
isine-0.009
opian-0.009
chen-0.008
ulic-0.008
 chefs-0.008
Token
Token ID447
Feature activation-6.40e-01

Pos logit contributions
isine+2.812
opian+2.623
chen+2.568
ulic+2.469
 chefs+2.454
Neg logit contributions
ONES-2.029
Naz-1.987
OSP-1.897
areth-1.854
HTTP-1.744
Token
Token ID247
Feature activation-6.05e-01

Pos logit contributions
isine+0.607
opian+0.557
chen+0.548
ulic+0.529
 chefs+0.518
Neg logit contributions
ONES-0.439
Naz-0.432
OSP-0.413
areth-0.410
HTTP-0.380
Tokens
Token ID82
Feature activation-1.13e+00

Pos logit contributions
isine+0.556
opian+0.514
chen+0.505
ulic+0.487
 chefs+0.474
Neg logit contributions
ONES-0.430
Naz-0.421
OSP-0.404
areth-0.396
HTTP-0.372
Token immune
Token ID10900
Feature activation+8.38e+00

Pos logit contributions
isine+0.977
opian+0.903
chen+0.881
ulic+0.841
 chefs+0.828
Neg logit contributions
ONES-0.864
Naz-0.849
OSP-0.812
areth-0.807
HTTP-0.757
Token system
Token ID1080
Feature activation+1.08e+00

Pos logit contributions
ONES+4.466
Naz+4.429
OSP+4.365
areth+4.200
HTTP+3.883
Neg logit contributions
isine-8.717
opian-7.996
chen-7.947
ulic-7.685
 chefs-7.512
Token attacks
Token ID3434
Feature activation+2.88e-01

Pos logit contributions
ONES+0.714
Naz+0.701
OSP+0.669
areth+0.660
HTTP+0.613
Neg logit contributions
isine-1.045
opian-0.964
chen-0.948
ulic-0.916
 chefs-0.898
Token the
Token ID262
Feature activation-4.00e-01

Pos logit contributions
ONES+0.226
Naz+0.222
OSP+0.214
areth+0.211
ospels+0.199
Neg logit contributions
isine-0.243
opian-0.222
chen-0.217
ulic-0.209
 chefs-0.205
Token new
Token ID649
Feature activation-1.31e+00

Pos logit contributions
isine+0.348
opian+0.319
chen+0.312
ulic+0.300
 chefs+0.294
Neg logit contributions
ONES-0.305
Naz-0.299
OSP-0.287
areth-0.285
HTTP-0.267
Token organ
Token ID1618
Feature activation+1.65e+00

Pos logit contributions
isine+1.159
opian+1.069
chen+1.045
ulic+1.000
 chefs+0.983
Neg logit contributions
ONES-0.974
Naz-0.953
OSP-0.915
areth-0.906
ospels-0.850
TokenBird
Token ID42562
Feature activation+1.76e-01

Pos logit contributions
ONES+0.062
Naz+0.061
OSP+0.058
areth+0.058
ospels+0.053
Neg logit contributions
isine-0.106
opian-0.098
chen-0.097
ulic-0.093
 chefs-0.091
Tokensey
Token ID4397
Feature activation-2.16e-01

Pos logit contributions
ONES+0.145
Naz+0.143
OSP+0.138
areth+0.137
HTTP+0.129
Neg logit contributions
isine-0.143
opian-0.130
chen-0.128
ulic-0.121
 chefs-0.119
Tokene
Token ID68
Feature activation-1.05e+00

Pos logit contributions
isine+0.244
opian+0.230
chen+0.225
ulic+0.220
 chefs+0.215
Neg logit contributions
ONES-0.109
Naz-0.105
OSP-0.101
areth-0.097
HTTP-0.089
Token view
Token ID1570
Feature activation-2.27e+00

Pos logit contributions
isine+0.981
opian+0.903
chen+0.889
ulic+0.857
 chefs+0.847
Neg logit contributions
ONES-0.729
Naz-0.719
OSP-0.692
areth-0.679
HTTP-0.638
Token of
Token ID286
Feature activation+6.32e-01

Pos logit contributions
isine+1.915
opian+1.759
chen+1.724
ulic+1.641
 chefs+1.614
Neg logit contributions
ONES-1.776
Naz-1.750
OSP-1.672
areth-1.665
HTTP-1.571
Token Brigham
Token ID37434
Feature activation+8.16e+00

Pos logit contributions
ONES+0.360
Naz+0.352
OSP+0.333
areth+0.329
HTTP+0.302
Neg logit contributions
isine-0.670
opian-0.624
chen-0.614
ulic-0.595
 chefs-0.587
Token City
Token ID2254
Feature activation+8.90e-01

Pos logit contributions
ONES+5.977
Naz+5.710
areth+5.686
OSP+5.680
 prophets+5.319
Neg logit contributions
isine-6.998
opian-6.260
chen-6.101
ulic-5.906
untled-5.806
Token,
Token ID11
Feature activation+3.32e-01

Pos logit contributions
ONES+0.615
Naz+0.604
OSP+0.576
areth+0.570
HTTP+0.531
Neg logit contributions
isine-0.837
opian-0.772
chen-0.758
ulic-0.730
 chefs-0.717
Token Utah
Token ID10202
Feature activation+5.83e-01

Pos logit contributions
ONES+0.222
Naz+0.218
OSP+0.208
areth+0.206
HTTP+0.191
Neg logit contributions
isine-0.319
opian-0.294
chen-0.290
ulic-0.280
 chefs-0.275
Token Date
Token ID7536
Feature activation-1.40e+00

Pos logit contributions
ONES+0.433
Naz+0.425
OSP+0.408
areth+0.404
HTTP+0.378
Neg logit contributions
isine-0.518
opian-0.474
chen-0.465
ulic-0.448
 chefs-0.438
Token:
Token ID25
Feature activation-1.26e+00

Pos logit contributions
isine+1.200
opian+1.091
chen+1.074
ulic+1.030
 chefs+1.006
Neg logit contributions
ONES-1.090
Naz-1.072
OSP-1.031
areth-1.018
HTTP-0.959
Token
Token ID198
Feature activation+3.49e-01

Pos logit contributions
ONES+0.439
Naz+0.424
OSP+0.409
areth+0.407
ospels+0.378
Neg logit contributions
isine-0.678
opian-0.623
chen-0.623
ulic-0.598
 chefs-0.585
Token
Token ID198
Feature activation+2.10e-01

Pos logit contributions
ONES+0.225
Naz+0.223
OSP+0.211
areth+0.206
HTTP+0.194
Neg logit contributions
isine-0.347
opian-0.321
chen-0.312
ulic-0.305
 chefs-0.300
TokenA
Token ID32
Feature activation+1.44e+00

Pos logit contributions
ONES+0.128
Naz+0.122
areth+0.118
OSP+0.118
 wip+0.110
Neg logit contributions
isine-0.211
chen-0.195
opian-0.194
ulic-0.187
 chefs-0.182
Token bench
Token ID7624
Feature activation+2.56e+00

Pos logit contributions
ONES+0.991
Naz+0.969
OSP+0.926
areth+0.917
ospels+0.856
Neg logit contributions
isine-1.356
opian-1.246
chen-1.232
ulic-1.187
 chefs-1.161
Token of
Token ID286
Feature activation+3.08e-01

Pos logit contributions
ONES+1.825
Naz+1.798
OSP+1.719
areth+1.702
HTTP+1.586
Neg logit contributions
isine-2.351
opian-2.165
chen-2.116
ulic-2.049
 chefs-1.999
Token justices
Token ID27818
Feature activation+8.12e+00

Pos logit contributions
ONES+0.224
Naz+0.218
OSP+0.211
areth+0.207
ospels+0.195
Neg logit contributions
isine-0.278
chen-0.251
opian-0.251
ulic-0.241
 chefs-0.238
Token H
Token ID367
Feature activation+1.06e+00

Pos logit contributions
Naz+6.032
ONES+5.976
areth+5.663
OSP+5.601
Sing+5.390
Neg logit contributions
isine-6.886
opian-6.484
chen-6.101
ulic-6.009
 chefs-5.701
Token L
Token ID406
Feature activation+3.29e-01

Pos logit contributions
ONES+0.847
Naz+0.833
OSP+0.801
areth+0.792
HTTP+0.748
Neg logit contributions
isine-0.882
opian-0.801
chen-0.787
ulic-0.756
 chefs-0.736
Token D
Token ID360
Feature activation+2.84e-02

Pos logit contributions
ONES+0.256
Naz+0.251
OSP+0.242
areth+0.238
HTTP+0.226
Neg logit contributions
isine-0.282
opian-0.257
chen-0.252
ulic-0.243
 chefs-0.236
Tokenatt
Token ID1078
Feature activation-3.73e-01

Pos logit contributions
ONES+0.021
Naz+0.021
OSP+0.020
areth+0.020
HTTP+0.019
Neg logit contributions
isine-0.025
opian-0.023
chen-0.022
ulic-0.022
 chefs-0.021
Tokenu
Token ID84
Feature activation-9.17e-01

Pos logit contributions
isine+0.295
opian+0.268
chen+0.262
ulic+0.251
 chefs+0.245
Neg logit contributions
ONES-0.312
Naz-0.308
OSP-0.297
areth-0.294
HTTP-0.278
Token on
Token ID319
Feature activation-2.27e-03

Pos logit contributions
ONES+1.707
Naz+1.685
OSP+1.627
areth+1.596
Sing+1.505
Neg logit contributions
isine-1.872
opian-1.713
chen-1.665
ulic-1.610
 chefs-1.560
Token Nov
Token ID5267
Feature activation+6.30e-01

Pos logit contributions
isine+0.002
opian+0.002
chen+0.002
ulic+0.002
 chefs+0.002
Neg logit contributions
ONES-0.002
Naz-0.002
OSP-0.002
areth-0.002
HTTP-0.001
Token.
Token ID13
Feature activation+5.24e-01

Pos logit contributions
ONES+0.410
Naz+0.401
OSP+0.384
areth+0.377
CTV+0.354
Neg logit contributions
isine-0.625
opian-0.572
chen-0.550
ulic-0.543
 chefs-0.536
Token 8
Token ID807
Feature activation-9.36e-01

Pos logit contributions
ONES+0.410
Naz+0.407
OSP+0.388
areth+0.380
Sing+0.364
Neg logit contributions
isine-0.456
opian-0.412
chen-0.395
ulic-0.388
 chefs-0.377
Token in
Token ID287
Feature activation+6.96e-01

Pos logit contributions
isine+0.821
opian+0.749
chen+0.741
ulic+0.708
 chefs+0.692
Neg logit contributions
ONES-0.708
Naz-0.692
OSP-0.666
areth-0.658
HTTP-0.621
Token Vaughan
Token ID47451
Feature activation+8.08e+00

Pos logit contributions
ONES+0.550
Naz+0.541
OSP+0.521
areth+0.515
HTTP+0.485
Neg logit contributions
isine-0.586
opian-0.534
chen-0.523
ulic-0.503
 chefs-0.491
Token,
Token ID11
Feature activation+3.14e-01

Pos logit contributions
Naz+4.645
ONES+4.612
OSP+4.382
areth+4.240
Sing+4.025
Neg logit contributions
isine-7.998
opian-7.538
chen-7.294
ulic-7.142
untled-6.996
Token Ont
Token ID9463
Feature activation+1.82e-01

Pos logit contributions
ONES+0.253
Naz+0.249
OSP+0.240
areth+0.237
HTTP+0.223
Neg logit contributions
isine-0.259
opian-0.236
chen-0.231
ulic-0.222
 chefs-0.217
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
ONES+0.143
Naz+0.142
OSP+0.136
areth+0.134
HTTP+0.127
Neg logit contributions
isine-0.155
opian-0.140
chen-0.138
ulic-0.132
 chefs-0.128
Token The
Token ID383
Feature activation-1.36e-01

Pos logit contributions
isine+0.183
opian+0.168
chen+0.165
ulic+0.159
 chefs+0.156
Neg logit contributions
ONES-0.142
Naz-0.140
OSP-0.134
areth-0.133
HTTP-0.124
Token three
Token ID1115
Feature activation+1.57e-01

Pos logit contributions
isine+0.114
opian+0.104
chen+0.102
ulic+0.098
 chefs+0.096
Neg logit contributions
ONES-0.107
Naz-0.105
OSP-0.101
areth-0.100
HTTP-0.094
TokenFor
Token ID1890
Feature activation-1.28e+00

Pos logit contributions
isine+0.784
opian+0.730
chen+0.725
ulic+0.698
 chefs+0.676
Neg logit contributions
ONES-0.469
Naz-0.448
areth-0.437
OSP-0.434
 wip-0.407
Token some
Token ID617
Feature activation-4.48e+00

Pos logit contributions
isine+1.050
opian+0.959
chen+0.945
ulic+0.902
 chefs+0.891
Neg logit contributions
ONES-1.021
Naz-1.010
OSP-0.973
areth-0.964
HTTP-0.910
Token actors
Token ID10544
Feature activation+4.78e-01

Pos logit contributions
isine+3.655
chen+3.347
opian+3.331
 chefs+3.216
ulic+3.129
Neg logit contributions
Naz-3.489
ONES-3.458
OSP-3.299
areth-3.256
HTTP-3.126
Token,
Token ID11
Feature activation-1.82e+00

Pos logit contributions
ONES+0.338
Naz+0.333
OSP+0.318
areth+0.315
HTTP+0.295
Neg logit contributions
isine-0.441
opian-0.406
chen-0.399
ulic-0.384
 chefs-0.378
Token like
Token ID588
Feature activation+2.59e-01

Pos logit contributions
isine+1.488
opian+1.362
chen+1.339
ulic+1.275
 chefs+1.274
Neg logit contributions
ONES-1.449
Naz-1.433
OSP-1.380
areth-1.366
HTTP-1.296
Token Ford
Token ID8092
Feature activation+8.07e+00

Pos logit contributions
ONES+0.186
Naz+0.183
OSP+0.176
areth+0.174
HTTP+0.162
Neg logit contributions
isine-0.235
opian-0.216
chen-0.213
ulic-0.205
 chefs-0.201
Token and
Token ID290
Feature activation-7.15e-01

Pos logit contributions
ONES+5.088
Naz+4.945
OSP+4.738
areth+4.669
Sing+4.347
Neg logit contributions
isine-7.767
opian-7.258
chen-6.967
ulic-6.889
 chefs-6.607
Token Fisher
Token ID14388
Feature activation+3.86e+00

Pos logit contributions
isine+0.655
opian+0.601
chen+0.597
ulic+0.571
 chefs+0.566
Neg logit contributions
ONES-0.502
Naz-0.495
OSP-0.477
areth-0.471
HTTP-0.444
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
ONES+2.611
Naz+2.564
OSP+2.450
areth+2.420
HTTP+2.251
Neg logit contributions
isine-3.677
opian-3.388
chen-3.330
ulic-3.216
 chefs-3.151
Token being
Token ID852
Feature activation+2.34e+00

Pos logit contributions
isine+0.870
opian+0.796
chen+0.783
ulic+0.745
 chefs+0.744
Neg logit contributions
ONES-0.821
Naz-0.811
OSP-0.779
areth-0.771
HTTP-0.731
Token in
Token ID287
Feature activation-1.32e+00

Pos logit contributions
ONES+1.688
Naz+1.656
OSP+1.589
areth+1.578
HTTP+1.466
Neg logit contributions
isine-2.123
opian-1.948
chen-1.900
ulic-1.842
 chefs-1.778
Token more
Token ID517
Feature activation-9.46e-01

Pos logit contributions
isine+1.195
opian+1.088
chen+1.069
ulic+1.021
 chefs+1.010
Neg logit contributions
ONES-1.195
Naz-1.173
OSP-1.136
areth-1.123
ospels-1.062
Token children
Token ID1751
Feature activation-1.65e+00

Pos logit contributions
isine+0.796
opian+0.727
chen+0.716
ulic+0.684
 chefs+0.678
Neg logit contributions
ONES-0.741
Naz-0.728
OSP-0.706
areth-0.698
HTTP-0.657
Token than
Token ID621
Feature activation-4.73e+00

Pos logit contributions
isine+1.377
opian+1.255
chen+1.240
ulic+1.181
 chefs+1.161
Neg logit contributions
ONES-1.301
Naz-1.277
OSP-1.235
areth-1.222
ospels-1.155
Token died
Token ID3724
Feature activation-5.40e-01

Pos logit contributions
isine+3.895
opian+3.558
chen+3.526
 chefs+3.403
ulic+3.342
Neg logit contributions
ONES-3.714
Naz-3.606
OSP-3.570
areth-3.480
HTTP-3.322
Token in
Token ID287
Feature activation-2.12e-01

Pos logit contributions
isine+0.411
opian+0.370
chen+0.363
ulic+0.346
 chefs+0.339
Neg logit contributions
ONES-0.470
Naz-0.462
OSP-0.448
areth-0.444
ospels-0.420
Token Hiroshima
Token ID42922
Feature activation+8.06e+00

Pos logit contributions
isine+0.183
opian+0.167
chen+0.164
ulic+0.158
 chefs+0.155
Neg logit contributions
ONES-0.163
Naz-0.160
OSP-0.155
areth-0.153
HTTP-0.143
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
ONES+5.116
Naz+5.087
OSP+4.734
areth+4.686
Sing+4.342
Neg logit contributions
isine-7.746
opian-7.166
chen-6.944
ulic-6.693
 chefs-6.609
Token And
Token ID843
Feature activation+1.55e+00

Pos logit contributions
isine+0.170
opian+0.155
chen+0.152
ulic+0.146
 chefs+0.143
Neg logit contributions
ONES-0.152
Naz-0.149
OSP-0.144
areth-0.142
HTTP-0.133
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
ONES+1.215
Naz+1.197
OSP+1.147
areth+1.141
HTTP+1.066
Neg logit contributions
isine-1.319
opian-1.202
chen-1.175
ulic-1.131
 chefs-1.095
Token you
Token ID345
Feature activation+1.88e+00

Pos logit contributions
isine+0.181
opian+0.166
chen+0.163
ulic+0.156
 chefs+0.153
Neg logit contributions
ONES-0.158
Naz-0.156
OSP-0.150
areth-0.148
HTTP-0.139
Token know
Token ID760
Feature activation+2.61e+00

Pos logit contributions
ONES+1.345
Naz+1.323
OSP+1.262
areth+1.257
HTTP+1.168
Neg logit contributions
isine-1.722
opian-1.575
chen-1.540
ulic-1.493
 chefs-1.447
Token the
Token ID262
Feature activation-1.58e+00

Pos logit contributions
isine+0.877
opian+0.813
chen+0.797
ulic+0.763
 chefs+0.754
Neg logit contributions
ONES-0.725
Naz-0.709
OSP-0.679
areth-0.670
ospels-0.634
Token equivalent
Token ID7548
Feature activation+1.34e+00

Pos logit contributions
isine+1.262
opian+1.149
chen+1.126
ulic+1.073
 chefs+1.057
Neg logit contributions
ONES-1.314
Naz-1.297
OSP-1.250
areth-1.239
ospels-1.170
Token of
Token ID286
Feature activation-7.62e-01

Pos logit contributions
ONES+1.039
Naz+1.022
OSP+0.982
areth+0.973
HTTP+0.913
Neg logit contributions
isine-1.151
opian-1.052
chen-1.031
ulic-0.990
 chefs-0.969
Token an
Token ID281
Feature activation-2.67e-02

Pos logit contributions
isine+0.624
opian+0.568
chen+0.557
ulic+0.532
 chefs+0.526
Neg logit contributions
ONES-0.617
Naz-0.607
OSP-0.586
areth-0.581
ospels-0.546
Token Olympic
Token ID11514
Feature activation-3.91e+00

Pos logit contributions
isine+0.022
opian+0.020
chen+0.019
ulic+0.018
 chefs+0.018
Neg logit contributions
ONES-0.022
Naz-0.022
OSP-0.021
areth-0.021
ospels-0.019
Token gymn
Token ID38581
Feature activation-1.05e+01

Pos logit contributions
isine+3.252
opian+2.949
chen+2.923
ulic+2.774
 chefs+2.765
Neg logit contributions
ONES-3.078
Naz-3.026
OSP-2.931
areth-2.897
ospels-2.756
Tokenastics
Token ID24232
Feature activation-5.48e+00

Pos logit contributions
isine+7.171
chen+6.531
opian+6.466
ulic+5.924
rast+5.715
Neg logit contributions
ONES-9.559
Naz-9.387
OSP-9.163
areth-8.844
HTTP-8.759
Token routine
Token ID8027
Feature activation-1.98e+00

Pos logit contributions
isine+4.458
opian+4.072
chen+4.068
 chefs+3.825
ulic+3.824
Neg logit contributions
ONES-4.332
Naz-4.271
OSP-4.128
areth-4.079
ospels-3.919
Token for
Token ID329
Feature activation-1.40e-01

Pos logit contributions
isine+1.737
opian+1.590
chen+1.568
ulic+1.495
 chefs+1.475
Neg logit contributions
ONES-1.483
Naz-1.462
OSP-1.400
areth-1.391
ospels-1.305
Token the
Token ID262
Feature activation-1.45e+00

Pos logit contributions
isine+0.116
opian+0.105
chen+0.103
ulic+0.099
 chefs+0.097
Neg logit contributions
ONES-0.113
Naz-0.111
OSP-0.107
areth-0.106
HTTP-0.100
Token speaker
Token ID10834
Feature activation+2.14e-01

Pos logit contributions
isine+1.166
opian+1.061
chen+1.038
ulic+0.993
 chefs+0.974
Neg logit contributions
ONES-1.193
Naz-1.176
OSP-1.132
areth-1.124
ospels-1.058
Tokenx
Token ID87
Feature activation+8.18e-01

Pos logit contributions
ONES+1.249
Naz+1.228
OSP+1.178
areth+1.157
HTTP+1.085
Neg logit contributions
isine-1.603
opian-1.472
chen-1.455
ulic-1.395
 chefs-1.367
Token.
Token ID13
Feature activation-1.84e-01

Pos logit contributions
ONES+0.593
Naz+0.583
OSP+0.559
areth+0.553
HTTP+0.516
Neg logit contributions
isine-0.742
opian-0.680
chen-0.668
ulic-0.644
 chefs-0.631
Token Just
Token ID2329
Feature activation+8.21e-01

Pos logit contributions
isine+0.167
opian+0.154
chen+0.151
ulic+0.145
 chefs+0.142
Neg logit contributions
ONES-0.132
Naz-0.130
OSP-0.124
areth-0.123
HTTP-0.115
Token as
Token ID355
Feature activation-1.27e+00

Pos logit contributions
ONES+0.628
Naz+0.617
OSP+0.594
areth+0.588
HTTP+0.552
Neg logit contributions
isine-0.711
opian-0.649
chen-0.636
ulic-0.612
 chefs-0.597
Token a
Token ID257
Feature activation-9.44e-01

Pos logit contributions
isine+1.064
opian+0.966
chen+0.952
ulic+0.908
 chefs+0.902
Neg logit contributions
ONES-1.000
Naz-0.987
OSP-0.952
areth-0.945
ospels-0.886
Token gymn
Token ID38581
Feature activation-1.03e+01

Pos logit contributions
isine+0.806
opian+0.734
chen+0.723
ulic+0.692
 chefs+0.680
Neg logit contributions
ONES-0.734
Naz-0.723
OSP-0.694
areth-0.690
ospels-0.647
Tokenast
Token ID459
Feature activation-2.82e+00

Pos logit contributions
isine+7.226
chen+6.528
opian+6.510
ulic+6.061
 chefs+5.779
Neg logit contributions
ONES-9.104
Naz-9.018
OSP-8.668
areth-8.449
HTTP-8.236
Token
Token ID447
Feature activation-6.66e-01

Pos logit contributions
isine+2.698
opian+2.504
chen+2.467
ulic+2.370
 chefs+2.352
Neg logit contributions
ONES-1.880
Naz-1.853
OSP-1.769
areth-1.726
HTTP-1.620
Token
Token ID247
Feature activation-4.59e-01

Pos logit contributions
isine+0.617
opian+0.567
chen+0.557
ulic+0.537
 chefs+0.526
Neg logit contributions
ONES-0.469
Naz-0.461
OSP-0.441
areth-0.435
HTTP-0.406
Tokens
Token ID82
Feature activation-1.22e+00

Pos logit contributions
isine+0.424
opian+0.391
chen+0.386
ulic+0.371
 chefs+0.362
Neg logit contributions
ONES-0.327
Naz-0.319
OSP-0.307
areth-0.300
HTTP-0.282
Token twists
Token ID30953
Feature activation-1.50e+00

Pos logit contributions
isine+1.067
opian+0.977
chen+0.959
ulic+0.918
 chefs+0.906
Neg logit contributions
ONES-0.932
Naz-0.918
OSP-0.880
areth-0.873
HTTP-0.818
Tokenren
Token ID918
Feature activation+1.31e+00

Pos logit contributions
isine+0.553
opian+0.503
chen+0.496
ulic+0.473
 chefs+0.463
Neg logit contributions
ONES-0.537
Naz-0.526
OSP-0.507
areth-0.502
HTTP-0.472
Tokenowned
Token ID11990
Feature activation+2.04e+00

Pos logit contributions
ONES+0.840
Naz+0.822
OSP+0.784
areth+0.775
ospels+0.717
Neg logit contributions
isine-1.290
opian-1.195
chen-1.171
ulic-1.137
 chefs-1.112
Token perf
Token ID23035
Feature activation-2.75e+00

Pos logit contributions
ONES+1.650
Naz+1.620
OSP+1.558
areth+1.545
 wip+1.461
Neg logit contributions
isine-1.664
opian-1.515
chen-1.474
ulic-1.426
 chefs-1.342
Tokenumer
Token ID6975
Feature activation-9.08e-02

Pos logit contributions
isine+1.620
opian+1.414
chen+1.372
ulic+1.291
 chefs+1.244
Neg logit contributions
ONES-2.863
Naz-2.828
OSP-2.747
areth-2.728
HTTP-2.605
Token Fr
Token ID1305
Feature activation-4.07e+00

Pos logit contributions
isine+0.079
opian+0.072
chen+0.070
ulic+0.068
 chefs+0.066
Neg logit contributions
ONES-0.070
Naz-0.069
OSP-0.066
areth-0.065
HTTP-0.061
Tokené
Token ID2634
Feature activation-9.29e+00

Pos logit contributions
isine+3.012
opian+2.700
chen+2.648
ulic+2.550
 chefs+2.444
Neg logit contributions
ONES-3.595
Naz-3.560
OSP-3.439
areth-3.361
HTTP-3.245
Tokend
Token ID67
Feature activation-5.53e+00

Pos logit contributions
isine+7.096
chen+6.798
opian+6.407
ulic+6.356
 chefs+6.044
Neg logit contributions
ONES-7.619
OSP-7.401
Naz-7.322
areth-6.923
ospels-6.649
Tokené
Token ID2634
Feature activation-7.17e+00

Pos logit contributions
isine+3.002
chen+2.614
opian+2.602
ulic+2.418
 chefs+2.231
Neg logit contributions
ONES-5.984
Naz-5.872
OSP-5.783
areth-5.617
 wip-5.467
Tokenric
Token ID1173
Feature activation-3.15e+00

Pos logit contributions
isine+3.549
chen+3.131
opian+3.025
ulic+2.760
 chefs+2.697
Neg logit contributions
ONES-7.914
Naz-7.844
OSP-7.740
areth-7.567
HTTP-7.356
Token Mal
Token ID4434
Feature activation-6.29e-01

Pos logit contributions
isine+2.603
chen+2.368
opian+2.341
ulic+2.237
 chefs+2.206
Neg logit contributions
ONES-2.497
Naz-2.441
OSP-2.385
areth-2.338
HTTP-2.232
Tokenle
Token ID293
Feature activation-5.54e+00

Pos logit contributions
isine+0.534
opian+0.487
chen+0.475
ulic+0.458
 chefs+0.448
Neg logit contributions
ONES-0.492
Naz-0.484
OSP-0.464
areth-0.462
HTTP-0.433
Token't
Token ID470
Feature activation-1.22e+00

Pos logit contributions
ONES+0.307
Naz+0.304
OSP+0.280
areth+0.273
HTTP+0.248
Neg logit contributions
isine-0.779
opian-0.724
chen-0.702
ulic-0.692
 chefs-0.680
Token somehow
Token ID7599
Feature activation-4.85e+00

Pos logit contributions
isine+1.048
opian+0.962
chen+0.942
ulic+0.907
 chefs+0.889
Neg logit contributions
ONES-0.938
Naz-0.919
OSP-0.892
areth-0.875
HTTP-0.827
Token destabil
Token ID27397
Feature activation-3.29e+00

Pos logit contributions
isine+4.000
opian+3.727
chen+3.597
ulic+3.492
 chefs+3.451
Neg logit contributions
ONES-3.841
Naz-3.696
OSP-3.665
areth-3.515
HTTP-3.375
Tokenize
Token ID1096
Feature activation-1.58e+00

Pos logit contributions
isine+2.244
opian+2.028
chen+1.973
ulic+1.875
 chefs+1.808
Neg logit contributions
ONES-3.102
Naz-3.072
OSP-2.962
areth-2.931
ospels-2.798
Token the
Token ID262
Feature activation-9.37e-01

Pos logit contributions
isine+1.313
opian+1.200
chen+1.182
ulic+1.138
 chefs+1.114
Neg logit contributions
ONES-1.260
Naz-1.239
OSP-1.195
areth-1.179
ospels-1.115
Token grid
Token ID10706
Feature activation-8.81e+00

Pos logit contributions
isine+0.797
opian+0.731
chen+0.717
ulic+0.689
 chefs+0.675
Neg logit contributions
ONES-0.727
Naz-0.716
OSP-0.689
areth-0.681
ospels-0.641
Token could
Token ID714
Feature activation+3.84e-01

Pos logit contributions
isine+7.130
opian+6.865
chen+6.761
 chefs+6.273
ulic+6.272
Neg logit contributions
ONES-6.510
Naz-6.421
OSP-6.297
areth-5.983
ospels-5.691
Token help
Token ID1037
Feature activation-1.23e+00

Pos logit contributions
ONES+0.278
Naz+0.273
OSP+0.262
areth+0.259
HTTP+0.242
Neg logit contributions
isine-0.348
opian-0.320
chen-0.314
ulic-0.303
 chefs-0.296
Token that
Token ID326
Feature activation-2.53e+00

Pos logit contributions
isine+1.053
opian+0.966
chen+0.947
ulic+0.914
 chefs+0.897
Neg logit contributions
ONES-0.945
Naz-0.932
OSP-0.895
areth-0.884
ospels-0.832
Token jump
Token ID4391
Feature activation-4.30e+00

Pos logit contributions
isine+2.190
opian+2.018
chen+1.986
ulic+1.911
 chefs+1.889
Neg logit contributions
ONES-1.898
Naz-1.873
OSP-1.801
areth-1.788
ospels-1.679
Token happen
Token ID1645
Feature activation+3.67e-01

Pos logit contributions
isine+3.592
opian+3.335
chen+3.241
ulic+3.133
 chefs+3.033
Neg logit contributions
ONES-3.348
Naz-3.312
OSP-3.185
areth-3.144
ospels-2.964
Token of
Token ID286
Feature activation-4.11e-01

Pos logit contributions
isine+3.594
opian+3.239
chen+3.217
 chefs+3.028
ulic+3.019
Neg logit contributions
ONES-3.888
Naz-3.784
OSP-3.655
areth-3.643
ospels-3.487
Token a
Token ID257
Feature activation+3.29e-01

Pos logit contributions
isine+0.322
opian+0.292
chen+0.286
ulic+0.273
 chefs+0.267
Neg logit contributions
ONES-0.347
Naz-0.342
OSP-0.330
areth-0.327
HTTP-0.309
Token person
Token ID1048
Feature activation-2.14e+00

Pos logit contributions
ONES+0.289
Naz+0.286
OSP+0.276
areth+0.272
HTTP+0.259
Neg logit contributions
isine-0.247
opian-0.223
chen-0.217
ulic-0.207
 chefs-0.202
Token who
Token ID508
Feature activation+1.21e+00

Pos logit contributions
isine+1.827
opian+1.666
chen+1.635
ulic+1.571
 chefs+1.537
Neg logit contributions
ONES-1.664
Naz-1.637
OSP-1.573
areth-1.557
ospels-1.464
Token is
Token ID318
Feature activation-1.34e+00

Pos logit contributions
ONES+0.753
Naz+0.739
OSP+0.704
areth+0.697
HTTP+0.642
Neg logit contributions
isine-1.223
opian-1.132
chen-1.111
ulic-1.079
 chefs-1.054
Token nude
Token ID26349
Feature activation-8.71e+00

Pos logit contributions
isine+1.004
opian+0.904
chen+0.884
ulic+0.844
 chefs+0.821
Neg logit contributions
ONES-1.185
Naz-1.168
OSP-1.128
areth-1.118
HTTP-1.059
Token or
Token ID393
Feature activation-3.01e+00

Pos logit contributions
isine+7.027
opian+6.279
chen+6.248
ulic+5.914
 chefs+5.847
Neg logit contributions
ONES-6.986
Naz-6.772
areth-6.509
OSP-6.448
ospels-6.269
Token engaged
Token ID7953
Feature activation-2.53e+00

Pos logit contributions
isine+2.510
opian+2.289
chen+2.247
ulic+2.156
 chefs+2.112
Neg logit contributions
ONES-2.389
Naz-2.350
OSP-2.253
areth-2.235
ospels-2.108
Token in
Token ID287
Feature activation+2.05e-01

Pos logit contributions
isine+1.765
opian+1.598
chen+1.553
ulic+1.477
 chefs+1.446
Neg logit contributions
ONES-2.340
Naz-2.308
OSP-2.225
areth-2.207
ospels-2.107
Token a
Token ID257
Feature activation+2.38e-01

Pos logit contributions
ONES+0.162
Naz+0.160
OSP+0.154
areth+0.152
HTTP+0.143
Neg logit contributions
isine-0.171
opian-0.156
chen-0.153
ulic-0.147
 chefs-0.143
Token sexual
Token ID3206
Feature activation-5.79e+00

Pos logit contributions
ONES+0.188
Naz+0.186
OSP+0.180
areth+0.177
HTTP+0.167
Neg logit contributions
isine-0.199
opian-0.182
chen-0.178
ulic-0.171
 chefs-0.167
Token effects
Token ID3048
Feature activation+1.59e+00

Pos logit contributions
isine+2.048
opian+1.889
chen+1.887
ulic+1.796
 chefs+1.787
Neg logit contributions
ONES-1.973
Naz-1.956
OSP-1.873
areth-1.859
ospels-1.750
Token here
Token ID994
Feature activation+7.31e-01

Pos logit contributions
ONES+1.175
Naz+1.155
OSP+1.109
areth+1.096
HTTP+1.026
Neg logit contributions
isine-1.412
opian-1.291
chen-1.263
ulic-1.220
 chefs-1.193
Token.
Token ID13
Feature activation-4.52e-01

Pos logit contributions
ONES+0.516
Naz+0.507
OSP+0.486
areth+0.480
HTTP+0.448
Neg logit contributions
isine-0.676
opian-0.621
chen-0.610
ulic-0.589
 chefs-0.576
Token Access
Token ID8798
Feature activation-3.08e+00

Pos logit contributions
isine+0.402
opian+0.369
chen+0.362
ulic+0.349
 chefs+0.341
Neg logit contributions
ONES-0.333
Naz-0.328
OSP-0.315
areth-0.311
HTTP-0.291
Token to
Token ID284
Feature activation-1.87e+00

Pos logit contributions
isine+2.590
opian+2.410
chen+2.384
ulic+2.295
 chefs+2.244
Neg logit contributions
ONES-2.366
Naz-2.323
OSP-2.234
areth-2.189
ospels-2.069
Token freshwater
Token ID40941
Feature activation-8.71e+00

Pos logit contributions
isine+1.482
opian+1.344
chen+1.321
ulic+1.268
 chefs+1.244
Neg logit contributions
ONES-1.551
Naz-1.531
OSP-1.476
areth-1.467
ospels-1.385
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
isine+7.367
opian+6.835
chen+6.824
 chefs+6.751
ulic+6.669
Neg logit contributions
ONES-6.220
Naz-6.074
OSP-5.980
areth-5.729
ospels-5.552
Token already
Token ID1541
Feature activation-2.15e+00

Pos logit contributions
isine+0.953
opian+0.867
chen+0.852
ulic+0.820
 chefs+0.806
Neg logit contributions
ONES-0.909
Naz-0.897
OSP-0.866
areth-0.858
ospels-0.808
Token in
Token ID287
Feature activation-1.06e+00

Pos logit contributions
isine+1.831
opian+1.673
chen+1.647
ulic+1.579
 chefs+1.554
Neg logit contributions
ONES-1.667
Naz-1.644
OSP-1.579
areth-1.558
ospels-1.472
Token limited
Token ID3614
Feature activation+1.42e+00

Pos logit contributions
isine+0.914
opian+0.844
chen+0.823
ulic+0.794
 chefs+0.778
Neg logit contributions
ONES-0.802
Naz-0.791
OSP-0.756
areth-0.751
ospels-0.705
Token supply
Token ID5127
Feature activation+1.60e+00

Pos logit contributions
ONES+1.016
Naz+0.999
OSP+0.958
areth+0.945
HTTP+0.885
Neg logit contributions
isine-1.309
opian-1.199
chen-1.178
ulic-1.135
 chefs-1.107
Tokenpdf
Token ID12315
Feature activation+7.25e-01

Pos logit contributions
ONES+0.536
Naz+0.526
OSP+0.503
areth+0.497
HTTP+0.463
Neg logit contributions
isine-0.738
opian-0.680
chen-0.668
ulic-0.645
 chefs-0.631
Token
Token ID198
Feature activation+6.61e-01

Pos logit contributions
ONES+0.521
Naz+0.512
OSP+0.491
areth+0.485
HTTP+0.453
Neg logit contributions
isine-0.661
opian-0.607
chen-0.596
ulic-0.575
 chefs-0.562
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
ONES+0.406
Naz+0.404
OSP+0.378
areth+0.371
Sing+0.348
Neg logit contributions
isine-0.680
opian-0.626
chen-0.607
ulic-0.596
 chefs-0.589
Token©
Token ID16224
Feature activation-4.69e+00

Pos logit contributions
ONES+0.094
Naz+0.092
OSP+0.088
areth+0.087
ospels+0.081
Neg logit contributions
isine-0.148
opian-0.137
chen-0.135
ulic-0.131
 chefs-0.128
Token Copyright
Token ID15069
Feature activation-3.28e+00

Pos logit contributions
isine+3.808
chen+3.468
opian+3.451
ulic+3.282
 chefs+3.240
Neg logit contributions
ONES-3.714
Naz-3.632
OSP-3.550
areth-3.497
ospels-3.318
Token 2018
Token ID2864
Feature activation-8.63e+00

Pos logit contributions
isine+2.578
opian+2.336
chen+2.329
ulic+2.206
 chefs+2.165
Neg logit contributions
ONES-2.725
Naz-2.676
OSP-2.598
areth-2.566
ospels-2.436
Token Red
Token ID2297
Feature activation-3.26e+00

Pos logit contributions
isine+6.470
chen+6.038
opian+5.846
 chefs+5.634
ulic+5.528
Neg logit contributions
ONES-6.919
Naz-6.875
OSP-6.746
areth-6.503
ospels-6.304
Token
Token ID447
Feature activation-9.07e-01

Pos logit contributions
isine+2.803
opian+2.565
chen+2.550
ulic+2.433
 chefs+2.375
Neg logit contributions
ONES-2.459
Naz-2.431
OSP-2.346
areth-2.324
ospels-2.185
Token
Token ID247
Feature activation+3.91e-02

Pos logit contributions
isine+0.791
opian+0.726
chen+0.712
ulic+0.685
 chefs+0.667
Neg logit contributions
ONES-0.687
Naz-0.672
OSP-0.644
areth-0.635
ospels-0.599
Tokens
Token ID82
Feature activation-9.50e-01

Pos logit contributions
ONES+0.025
Naz+0.024
OSP+0.023
areth+0.023
HTTP+0.021
Neg logit contributions
isine-0.039
opian-0.036
chen-0.036
ulic-0.034
 chefs-0.034
Token Land
Token ID6379
Feature activation+9.16e-01

Pos logit contributions
isine+0.812
opian+0.741
chen+0.729
ulic+0.699
 chefs+0.682
Neg logit contributions
ONES-0.737
Naz-0.727
OSP-0.700
areth-0.691
HTTP-0.651
Token
Token ID251
Feature activation-5.57e-01

Pos logit contributions
ONES+0.173
Naz+0.170
OSP+0.164
areth+0.162
ospels+0.154
Neg logit contributions
isine-0.165
opian-0.150
chen-0.147
ulic-0.140
 chefs-0.137
Token
Token ID198
Feature activation+2.35e-01

Pos logit contributions
isine+0.509
opian+0.467
chen+0.463
ulic+0.444
 chefs+0.434
Neg logit contributions
ONES-0.395
Naz-0.388
OSP-0.373
areth-0.372
ospels-0.345
Token
Token ID198
Feature activation+1.89e-02

Pos logit contributions
ONES+0.145
Naz+0.144
OSP+0.135
areth+0.133
Sing+0.124
Neg logit contributions
isine-0.240
opian-0.221
chen-0.214
ulic-0.211
 chefs-0.208
TokenCopyright
Token ID15269
Feature activation-1.94e+00

Pos logit contributions
ONES+0.012
Naz+0.012
OSP+0.011
areth+0.011
ospels+0.010
Neg logit contributions
isine-0.019
opian-0.017
chen-0.017
ulic-0.016
 chefs-0.016
Token ©
Token ID10673
Feature activation-4.69e+00

Pos logit contributions
isine+1.413
opian+1.275
chen+1.253
ulic+1.184
 chefs+1.158
Neg logit contributions
ONES-1.749
Naz-1.718
OSP-1.671
areth-1.652
ospels-1.565
Token 2019
Token ID13130
Feature activation-8.51e+00

Pos logit contributions
isine+3.076
opian+2.789
chen+2.773
ulic+2.568
 chefs+2.497
Neg logit contributions
ONES-4.455
Naz-4.374
OSP-4.269
areth-4.239
ospels-4.017
Token The
Token ID383
Feature activation-2.23e+00

Pos logit contributions
isine+6.206
chen+5.739
opian+5.635
 chefs+5.202
ulic+5.183
Neg logit contributions
ONES-7.160
Naz-7.082
areth-6.841
OSP-6.779
ospels-6.420
Token Washington
Token ID2669
Feature activation+4.28e-01

Pos logit contributions
isine+1.664
opian+1.513
chen+1.497
ulic+1.415
 chefs+1.382
Neg logit contributions
ONES-1.949
Naz-1.924
OSP-1.860
areth-1.852
HTTP-1.743
Token Times
Token ID3782
Feature activation+2.70e+00

Pos logit contributions
ONES+0.242
OSP+0.233
Naz+0.233
areth+0.228
Sing+0.208
Neg logit contributions
isine-0.455
opian-0.414
chen-0.407
ulic-0.401
 chefs-0.390
Token,
Token ID11
Feature activation-1.73e+00

Pos logit contributions
ONES+1.557
Naz+1.472
OSP+1.472
areth+1.429
ospels+1.308
Neg logit contributions
isine-2.826
opian-2.601
chen-2.561
ulic-2.500
 chefs-2.458
Token LLC
Token ID11419
Feature activation-2.65e+00

Pos logit contributions
isine+1.382
opian+1.258
chen+1.225
ulic+1.178
 chefs+1.146
Neg logit contributions
ONES-1.435
Naz-1.412
OSP-1.362
areth-1.351
HTTP-1.273
Tokenas
Token ID292
Feature activation+2.24e-01

Pos logit contributions
isine+1.611
opian+1.456
chen+1.452
ulic+1.388
 chefs+1.360
Neg logit contributions
ONES-1.438
Naz-1.414
OSP-1.359
areth-1.356
ospels-1.272
Token Le
Token ID1004
Feature activation-3.57e+00

Pos logit contributions
ONES+0.176
Naz+0.174
OSP+0.167
areth+0.165
ospels+0.155
Neg logit contributions
isine-0.189
opian-0.172
chen-0.169
ulic-0.162
 chefs-0.159
Token Fort
Token ID6401
Feature activation+2.50e+00

Pos logit contributions
isine+3.127
opian+2.836
chen+2.820
ulic+2.699
 chefs+2.669
Neg logit contributions
ONES-2.656
Naz-2.615
OSP-2.521
areth-2.484
ospels-2.333
Token de
Token ID390
Feature activation-3.33e+00

Pos logit contributions
ONES+2.354
Naz+2.325
OSP+2.250
areth+2.230
HTTP+2.121
Neg logit contributions
isine-1.719
opian-1.533
chen-1.494
ulic-1.420
 chefs-1.378
Token Br
Token ID1709
Feature activation-1.43e+00

Pos logit contributions
isine+2.743
chen+2.477
opian+2.438
ulic+2.356
 chefs+2.312
Neg logit contributions
ONES-2.663
Naz-2.536
OSP-2.493
areth-2.477
ospels-2.352
Tokené
Token ID2634
Feature activation-8.39e+00

Pos logit contributions
isine+1.076
opian+0.966
chen+0.948
ulic+0.906
 chefs+0.879
Neg logit contributions
ONES-1.259
Naz-1.242
OSP-1.201
areth-1.186
HTTP-1.125
Tokengan
Token ID1030
Feature activation-1.10e+00

Pos logit contributions
isine+7.294
chen+6.739
opian+6.584
ulic+6.352
 chefs+6.089
Neg logit contributions
ONES-6.240
OSP-5.929
Naz-5.925
areth-5.489
HTTP-5.378
Tokenç
Token ID16175
Feature activation-6.44e+00

Pos logit contributions
isine+0.855
chen+0.767
opian+0.762
ulic+0.717
 chefs+0.698
Neg logit contributions
ONES-0.944
Naz-0.924
OSP-0.892
areth-0.881
ospels-0.838
Tokenon
Token ID261
Feature activation-2.68e+00

Pos logit contributions
isine+5.067
chen+4.621
opian+4.534
ulic+4.370
 chefs+4.229
Neg logit contributions
ONES-5.088
Naz-5.076
OSP-4.901
areth-4.796
HTTP-4.593
Token ser
Token ID1055
Feature activation-1.29e+00

Pos logit contributions
isine+2.278
opian+2.054
chen+2.052
ulic+1.953
 chefs+1.926
Neg logit contributions
ONES-2.090
Naz-2.052
OSP-1.970
areth-1.959
ospels-1.850
Tokena
Token ID64
Feature activation-2.19e-01

Pos logit contributions
isine+1.146
opian+1.047
chen+1.032
ulic+0.988
 chefs+0.972
Neg logit contributions
ONES-0.966
Naz-0.949
OSP-0.911
areth-0.900
ospels-0.845
Token has
Token ID468
Feature activation-1.85e+00

Pos logit contributions
isine+1.264
opian+1.174
chen+1.155
ulic+1.106
 chefs+1.098
Neg logit contributions
ONES-0.935
Naz-0.915
OSP-0.875
areth-0.855
HTTP-0.806
Token opened
Token ID4721
Feature activation-1.29e+00

Pos logit contributions
isine+1.583
opian+1.454
chen+1.434
ulic+1.370
 chefs+1.360
Neg logit contributions
ONES-1.420
Naz-1.393
OSP-1.344
areth-1.321
ospels-1.255
Token the
Token ID262
Feature activation-2.50e-01

Pos logit contributions
isine+1.001
opian+0.910
chen+0.898
ulic+0.851
 chefs+0.849
Neg logit contributions
ONES-1.085
Naz-1.073
OSP-1.031
areth-1.027
ospels-0.967
Token door
Token ID3420
Feature activation+1.55e+00

Pos logit contributions
isine+0.218
opian+0.200
chen+0.197
ulic+0.189
 chefs+0.186
Neg logit contributions
ONES-0.190
Naz-0.187
OSP-0.179
areth-0.177
ospels-0.166
Token for
Token ID329
Feature activation+2.64e-01

Pos logit contributions
ONES+1.272
Naz+1.248
OSP+1.197
areth+1.192
HTTP+1.118
Neg logit contributions
isine-1.267
opian-1.167
chen-1.144
ulic-1.093
 chefs-1.069
Token nude
Token ID26349
Feature activation-8.27e+00

Pos logit contributions
ONES+0.212
Naz+0.209
OSP+0.201
areth+0.199
HTTP+0.188
Neg logit contributions
isine-0.218
opian-0.198
chen-0.194
ulic-0.186
 chefs-0.181
Token and
Token ID290
Feature activation-3.18e-01

Pos logit contributions
isine+6.622
opian+6.210
chen+6.049
 chefs+5.988
 chef+5.697
Neg logit contributions
ONES-6.436
Naz-6.191
areth-6.092
OSP-5.947
ospels-5.638
Token sexually
Token ID11363
Feature activation-5.51e+00

Pos logit contributions
isine+0.256
opian+0.232
chen+0.227
ulic+0.218
 chefs+0.212
Neg logit contributions
ONES-0.262
Naz-0.259
OSP-0.249
areth-0.247
HTTP-0.233
Token explicit
Token ID7952
Feature activation-5.88e+00

Pos logit contributions
isine+3.737
opian+3.329
chen+3.282
 chefs+3.106
ulic+3.058
Neg logit contributions
ONES-5.191
Naz-4.967
areth-4.883
OSP-4.844
ospels-4.694
Token photos
Token ID5205
Feature activation-4.23e+00

Pos logit contributions
isine+4.908
opian+4.515
chen+4.437
 chefs+4.303
ulic+4.151
Neg logit contributions
ONES-4.519
Naz-4.400
OSP-4.273
areth-4.260
ospels-4.011
Token and
Token ID290
Feature activation-4.16e-01

Pos logit contributions
isine+3.723
opian+3.428
chen+3.396
ulic+3.224
 chefs+3.189
Neg logit contributions
ONES-3.142
Naz-3.078
OSP-2.951
areth-2.928
ospels-2.754
Token is
Token ID318
Feature activation-7.35e-01

Pos logit contributions
ONES+0.260
Naz+0.254
OSP+0.244
areth+0.239
ospels+0.224
Neg logit contributions
isine-0.368
opian-0.340
chen-0.334
ulic-0.323
 chefs-0.316
Token currently
Token ID3058
Feature activation-5.00e+00

Pos logit contributions
isine+0.611
opian+0.555
chen+0.544
ulic+0.522
 chefs+0.509
Neg logit contributions
ONES-0.588
Naz-0.580
OSP-0.558
areth-0.552
HTTP-0.520
Token over
Token ID625
Feature activation-1.22e+00

Pos logit contributions
isine+3.849
opian+3.524
chen+3.461
ulic+3.320
 chefs+3.252
Neg logit contributions
ONES-4.175
Naz-4.097
OSP-3.953
areth-3.945
ospels-3.778
Token a
Token ID257
Feature activation+7.68e-02

Pos logit contributions
isine+1.105
opian+1.017
chen+1.001
ulic+0.962
 chefs+0.940
Neg logit contributions
ONES-0.887
Naz-0.871
OSP-0.837
areth-0.826
ospels-0.775
Token deep
Token ID2769
Feature activation-3.03e+00

Pos logit contributions
ONES+0.063
Naz+0.062
OSP+0.060
areth+0.059
HTTP+0.056
Neg logit contributions
isine-0.062
opian-0.056
chen-0.055
ulic-0.053
 chefs-0.052
Token gou
Token ID50162
Feature activation-8.26e+00

Pos logit contributions
isine+2.613
opian+2.396
chen+2.372
ulic+2.268
 chefs+2.204
Neg logit contributions
ONES-2.318
Naz-2.256
OSP-2.177
areth-2.156
ospels-2.032
Tokenge
Token ID469
Feature activation-4.06e+00

Pos logit contributions
isine+4.019
chen+3.612
opian+3.535
ulic+3.203
 chefs+2.819
Neg logit contributions
ONES-9.375
Naz-9.172
OSP-9.048
areth-8.723
CTV-8.546
Token in
Token ID287
Feature activation-2.12e-01

Pos logit contributions
isine+3.179
opian+2.915
chen+2.869
ulic+2.721
 chefs+2.662
Neg logit contributions
ONES-3.381
Naz-3.331
OSP-3.214
areth-3.187
ospels-3.033
Token which
Token ID543
Feature activation+1.51e+00

Pos logit contributions
isine+0.178
opian+0.162
chen+0.160
ulic+0.154
 chefs+0.149
Neg logit contributions
ONES-0.167
Naz-0.164
OSP-0.158
areth-0.156
ospels-0.148
Token the
Token ID262
Feature activation+2.01e-01

Pos logit contributions
ONES+1.188
Naz+1.169
OSP+1.124
areth+1.112
HTTP+1.047
Neg logit contributions
isine-1.278
opian-1.165
chen-1.141
ulic-1.095
 chefs-1.069
Token bedrock
Token ID47856
Feature activation-2.97e+00

Pos logit contributions
ONES+0.170
Naz+0.168
OSP+0.162
areth+0.160
HTTP+0.151
Neg logit contributions
isine-0.158
opian-0.143
chen-0.140
ulic-0.134
 chefs-0.130
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
isine+0.306
opian+0.279
chen+0.274
ulic+0.263
 chefs+0.257
Neg logit contributions
ONES-0.275
Naz-0.270
OSP-0.260
areth-0.259
ospels-0.243
Token
Token ID198
Feature activation-1.46e-01

Pos logit contributions
ONES+0.186
Naz+0.183
OSP+0.175
areth+0.173
HTTP+0.162
Neg logit contributions
isine-0.242
opian-0.222
chen-0.218
ulic-0.210
 chefs-0.206
Token
Token ID198
Feature activation-3.69e-01

Pos logit contributions
isine+0.148
opian+0.137
chen+0.133
ulic+0.130
 chefs+0.129
Neg logit contributions
ONES-0.091
Naz-0.091
OSP-0.085
areth-0.084
Sing-0.078
TokenCopyright
Token ID15269
Feature activation-2.07e+00

Pos logit contributions
isine+0.367
opian+0.339
chen+0.336
ulic+0.323
 chefs+0.314
Neg logit contributions
ONES-0.232
Naz-0.226
areth-0.217
OSP-0.216
ospels-0.200
Token ©
Token ID10673
Feature activation-4.74e+00

Pos logit contributions
isine+1.490
opian+1.345
chen+1.321
ulic+1.246
 chefs+1.217
Neg logit contributions
ONES-1.892
Naz-1.852
OSP-1.801
areth-1.783
ospels-1.691
Token 2019
Token ID13130
Feature activation-8.15e+00

Pos logit contributions
isine+3.215
opian+2.945
chen+2.936
ulic+2.717
 chefs+2.626
Neg logit contributions
ONES-4.435
Naz-4.324
OSP-4.196
areth-4.173
ospels-3.967
Token The
Token ID383
Feature activation-2.31e+00

Pos logit contributions
isine+6.024
chen+5.587
opian+5.566
ulic+5.035
 chefs+5.016
Neg logit contributions
ONES-6.894
Naz-6.747
areth-6.501
OSP-6.408
ospels-6.089
Token Washington
Token ID2669
Feature activation+3.55e-01

Pos logit contributions
isine+1.716
opian+1.570
chen+1.547
ulic+1.464
 chefs+1.423
Neg logit contributions
ONES-2.023
Naz-1.991
OSP-1.918
areth-1.913
HTTP-1.802
Token Times
Token ID3782
Feature activation+2.83e+00

Pos logit contributions
ONES+0.197
OSP+0.192
Naz+0.191
areth+0.186
Sing+0.170
Neg logit contributions
isine-0.381
opian-0.345
chen-0.340
ulic-0.336
 chefs-0.328
Token,
Token ID11
Feature activation-1.90e+00

Pos logit contributions
ONES+1.628
Naz+1.554
OSP+1.546
areth+1.502
ospels+1.389
Neg logit contributions
isine-2.958
opian-2.717
chen-2.680
ulic-2.606
 chefs-2.569
Token LLC
Token ID11419
Feature activation-2.84e+00

Pos logit contributions
isine+1.498
opian+1.357
chen+1.327
ulic+1.272
 chefs+1.239
Neg logit contributions
ONES-1.595
Naz-1.572
OSP-1.516
areth-1.502
HTTP-1.418
Token concentrations
Token ID14587
Feature activation+3.90e-01

Pos logit contributions
ONES+3.543
Naz+3.440
OSP+3.320
areth+3.282
HTTP+3.075
Neg logit contributions
isine-4.498
opian-4.155
chen-4.035
ulic-3.924
 chefs-3.749
Token of
Token ID286
Feature activation+3.41e-01

Pos logit contributions
ONES+0.303
Naz+0.298
OSP+0.288
areth+0.282
HTTP+0.267
Neg logit contributions
isine-0.333
opian-0.304
chen-0.300
ulic-0.287
 chefs-0.281
Token collagen
Token ID45452
Feature activation+2.97e+00

Pos logit contributions
ONES+0.286
Naz+0.281
OSP+0.271
areth+0.269
HTTP+0.254
Neg logit contributions
isine-0.270
opian-0.245
chen-0.239
ulic-0.229
 chefs-0.223
Token can
Token ID460
Feature activation+2.84e+00

Pos logit contributions
ONES+1.999
Naz+1.948
areth+1.868
OSP+1.855
HTTP+1.716
Neg logit contributions
isine-2.836
opian-2.616
chen-2.576
ulic-2.489
 chefs-2.432
Token attract
Token ID4729
Feature activation+4.77e-01

Pos logit contributions
ONES+2.086
Naz+2.053
areth+1.977
OSP+1.956
ospels+1.826
Neg logit contributions
isine-2.529
opian-2.306
chen-2.265
ulic-2.175
 chefs-2.127
Token contamination
Token ID22733
Feature activation-8.13e+00

Pos logit contributions
ONES+0.370
Naz+0.364
OSP+0.350
areth+0.346
HTTP+0.325
Neg logit contributions
isine-0.409
opian-0.373
chen-0.366
ulic-0.352
 chefs-0.343
Token,
Token ID11
Feature activation-5.41e-01

Pos logit contributions
isine+6.690
opian+6.240
chen+6.086
 chefs+5.882
ulic+5.687
Neg logit contributions
ONES-6.011
Naz-5.957
OSP-5.847
areth-5.646
ospels-5.426
Token they
Token ID484
Feature activation-3.30e-01

Pos logit contributions
isine+0.457
opian+0.415
chen+0.409
ulic+0.392
 chefs+0.387
Neg logit contributions
ONES-0.425
Naz-0.419
OSP-0.403
areth-0.399
ospels-0.376
Token compared
Token ID3688
Feature activation+1.73e+00

Pos logit contributions
isine+0.296
opian+0.272
chen+0.267
ulic+0.257
 chefs+0.253
Neg logit contributions
ONES-0.242
Naz-0.238
OSP-0.229
areth-0.225
HTTP-0.211
Token precision
Token ID15440
Feature activation-1.79e+00

Pos logit contributions
ONES+1.349
Naz+1.326
OSP+1.275
areth+1.262
HTTP+1.187
Neg logit contributions
isine-1.471
opian-1.342
chen-1.315
ulic-1.265
 chefs-1.234
Token Acceler
Token ID29805
Feature activation+2.32e+00

Pos logit contributions
isine+1.577
opian+1.433
chen+1.413
ulic+1.356
 chefs+1.344
Neg logit contributions
ONES-1.329
Naz-1.317
OSP-1.263
areth-1.247
HTTP-1.168
Token at
Token ID379
Feature activation+9.92e-01

Pos logit contributions
ONES+1.747
Naz+1.724
OSP+1.661
areth+1.640
HTTP+1.547
Neg logit contributions
isine-1.800
opian-1.632
chen-1.600
ulic-1.542
 chefs-1.499
Token the
Token ID262
Feature activation+2.71e-01

Pos logit contributions
ONES+0.769
Naz+0.757
OSP+0.727
areth+0.720
HTTP+0.676
Neg logit contributions
isine-0.849
opian-0.775
chen-0.760
ulic-0.731
 chefs-0.714
Token sites
Token ID5043
Feature activation-7.52e-01

Pos logit contributions
ONES+0.199
Naz+0.196
OSP+0.188
areth+0.186
HTTP+0.174
Neg logit contributions
isine-0.243
opian-0.222
chen-0.218
ulic-0.210
 chefs-0.206
Token that
Token ID326
Feature activation-3.98e-01

Pos logit contributions
isine+0.648
opian+0.593
chen+0.582
ulic+0.559
 chefs+0.548
Neg logit contributions
ONES-0.577
Naz-0.568
OSP-0.545
areth-0.540
ospels-0.507
Token permitted
Token ID10431
Feature activation+1.59e+00

Pos logit contributions
isine+0.348
opian+0.319
chen+0.313
ulic+0.301
 chefs+0.295
Neg logit contributions
ONES-0.300
Naz-0.295
OSP-0.283
areth-0.280
ospels-0.263
Token nude
Token ID26349
Feature activation-8.13e+00

Pos logit contributions
ONES+1.306
Naz+1.287
OSP+1.244
areth+1.224
HTTP+1.166
Neg logit contributions
isine-1.283
opian-1.163
chen-1.135
ulic-1.092
 chefs-1.049
Token photos
Token ID5205
Feature activation-3.68e+00

Pos logit contributions
isine+5.963
opian+5.410
chen+5.321
 chefs+5.220
 chef+4.968
Neg logit contributions
ONES-6.973
Naz-6.727
areth-6.628
OSP-6.438
ospels-6.201
Token to
Token ID284
Feature activation-2.01e-01

Pos logit contributions
isine+3.267
opian+2.998
chen+2.972
ulic+2.829
 chefs+2.783
Neg logit contributions
ONES-2.707
Naz-2.662
OSP-2.535
areth-2.523
ospels-2.371
Token be
Token ID307
Feature activation+1.60e+00

Pos logit contributions
isine+0.177
opian+0.162
chen+0.159
ulic+0.153
 chefs+0.150
Neg logit contributions
ONES-0.151
Naz-0.149
OSP-0.143
areth-0.141
HTTP-0.132
Token posted
Token ID4481
Feature activation-2.48e+00

Pos logit contributions
ONES+1.190
Naz+1.179
OSP+1.124
areth+1.117
HTTP+1.051
Neg logit contributions
isine-1.408
opian-1.286
chen-1.250
ulic-1.214
 chefs-1.176
Token of
Token ID286
Feature activation-5.84e-01

Pos logit contributions
isine+2.123
opian+1.947
chen+1.911
ulic+1.825
 chefs+1.796
Neg logit contributions
ONES-1.913
Naz-1.886
OSP-1.810
areth-1.791
ospels-1.693
Token applied
Token ID5625
Feature activation-1.72e+00

Pos logit contributions
ONES+0.168
Naz+0.166
OSP+0.159
areth+0.157
HTTP+0.147
Neg logit contributions
isine-0.214
opian-0.197
chen-0.193
ulic-0.187
 chefs-0.183
Token it
Token ID340
Feature activation-1.32e+00

Pos logit contributions
isine+1.425
opian+1.295
chen+1.274
ulic+1.232
 chefs+1.207
Neg logit contributions
ONES-1.364
Naz-1.350
OSP-1.297
areth-1.288
ospels-1.214
Token to
Token ID284
Feature activation+4.53e-01

Pos logit contributions
isine+1.126
opian+1.028
chen+1.008
ulic+0.973
 chefs+0.951
Neg logit contributions
ONES-1.017
Naz-1.005
OSP-0.966
areth-0.956
ospels-0.900
Token the
Token ID262
Feature activation-1.03e-01

Pos logit contributions
ONES+0.359
Naz+0.353
OSP+0.340
areth+0.336
HTTP+0.316
Neg logit contributions
isine-0.380
opian-0.345
chen-0.339
ulic-0.324
 chefs-0.317
Token Barnett
Token ID38174
Feature activation-3.30e+00

Pos logit contributions
isine+0.086
opian+0.078
chen+0.076
ulic+0.073
 chefs+0.071
Neg logit contributions
ONES-0.082
Naz-0.081
OSP-0.078
areth-0.077
HTTP-0.072
Token shale
Token ID30498
Feature activation-8.13e+00

Pos logit contributions
isine+2.863
opian+2.663
chen+2.613
ulic+2.560
 chefs+2.451
Neg logit contributions
ONES-2.427
Naz-2.405
OSP-2.314
areth-2.263
HTTP-2.144
Token,
Token ID11
Feature activation-6.12e-01

Pos logit contributions
isine+6.668
opian+6.316
ulic+6.142
chen+6.138
 chefs+5.815
Neg logit contributions
ONES-5.942
Naz-5.889
OSP-5.616
areth-5.591
ospels-5.285
Token a
Token ID257
Feature activation-4.03e-01

Pos logit contributions
isine+0.546
opian+0.501
chen+0.492
ulic+0.475
 chefs+0.464
Neg logit contributions
ONES-0.450
Naz-0.443
OSP-0.425
areth-0.421
HTTP-0.394
Token mile
Token ID10591
Feature activation-1.29e+00

Pos logit contributions
isine+0.349
opian+0.319
chen+0.313
ulic+0.301
 chefs+0.294
Neg logit contributions
ONES-0.308
Naz-0.303
OSP-0.291
areth-0.288
HTTP-0.270
Token-
Token ID12
Feature activation-2.49e+00

Pos logit contributions
isine+1.157
opian+1.070
chen+1.048
ulic+1.003
 chefs+0.985
Neg logit contributions
ONES-0.937
Naz-0.918
OSP-0.880
areth-0.867
ospels-0.821
Tokenand
Token ID392
Feature activation+1.52e+00

Pos logit contributions
isine+1.828
opian+1.657
chen+1.630
ulic+1.523
 chefs+1.462
Neg logit contributions
ONES-2.218
Naz-2.156
OSP-2.104
areth-2.052
ospels-1.989
Token even
Token ID772
Feature activation+2.21e-01

Pos logit contributions
ONES+0.161
Naz+0.159
OSP+0.152
areth+0.150
HTTP+0.141
Neg logit contributions
isine-0.191
opian-0.175
chen-0.172
ulic-0.165
 chefs-0.162
Token our
Token ID674
Feature activation+2.12e-01

Pos logit contributions
ONES+0.178
Naz+0.176
OSP+0.169
areth+0.167
HTTP+0.158
Neg logit contributions
isine-0.183
opian-0.166
chen-0.162
ulic-0.156
 chefs-0.152
Token well
Token ID880
Feature activation+2.88e+00

Pos logit contributions
ONES+0.173
Naz+0.170
OSP+0.164
areth+0.163
HTTP+0.153
Neg logit contributions
isine-0.173
opian-0.157
chen-0.154
ulic-0.148
 chefs-0.145
Token water
Token ID1660
Feature activation-2.03e+00

Pos logit contributions
ONES+1.960
Naz+1.929
OSP+1.847
areth+1.813
HTTP+1.702
Neg logit contributions
isine-2.722
opian-2.509
chen-2.453
ulic-2.383
 chefs-2.317
Token is
Token ID318
Feature activation-2.82e-01

Pos logit contributions
isine+1.843
opian+1.686
chen+1.677
ulic+1.602
 chefs+1.581
Neg logit contributions
ONES-1.454
Naz-1.428
OSP-1.369
areth-1.364
ospels-1.269
Token contaminated
Token ID23543
Feature activation-8.10e+00

Pos logit contributions
isine+0.220
opian+0.199
chen+0.193
ulic+0.186
 chefs+0.180
Neg logit contributions
ONES-0.241
Naz-0.237
OSP-0.229
areth-0.226
HTTP-0.215
Token,
Token ID11
Feature activation-3.20e-01

Pos logit contributions
isine+6.362
opian+5.755
chen+5.659
ulic+5.388
 chefs+5.311
Neg logit contributions
ONES-6.518
Naz-6.361
OSP-6.290
areth-6.252
ospels-5.901
Token
Token ID447
Feature activation+7.26e-02

Pos logit contributions
isine+0.290
opian+0.266
chen+0.261
ulic+0.252
 chefs+0.247
Neg logit contributions
ONES-0.231
Naz-0.227
OSP-0.218
areth-0.216
ospels-0.201
Token
Token ID251
Feature activation-5.57e-01

Pos logit contributions
ONES+0.061
Naz+0.060
OSP+0.058
areth+0.057
ospels+0.054
Neg logit contributions
isine-0.057
opian-0.052
chen-0.051
ulic-0.049
 chefs-0.047
Token Yun
Token ID20757
Feature activation+5.44e+00

Pos logit contributions
isine+0.473
opian+0.431
chen+0.425
ulic+0.406
 chefs+0.399
Neg logit contributions
ONES-0.435
Naz-0.427
OSP-0.413
areth-0.409
ospels-0.384
Token told
Token ID1297
Feature activation-1.94e+00

Pos logit contributions
ONES+3.809
Naz+3.785
areth+3.528
OSP+3.525
HTTP+3.302
Neg logit contributions
isine-4.946
opian-4.543
chen-4.377
ulic-4.312
 chefs-4.171
Token.
Token ID13
Feature activation+3.64e-01

Pos logit contributions
isine+0.114
opian+0.104
chen+0.102
ulic+0.099
 chefs+0.096
Neg logit contributions
ONES-0.095
Naz-0.094
OSP-0.090
areth-0.089
HTTP-0.083
Token
Token ID198
Feature activation+4.74e-01

Pos logit contributions
ONES+0.284
Naz+0.279
OSP+0.268
areth+0.266
ospels+0.250
Neg logit contributions
isine-0.310
opian-0.283
chen-0.278
ulic-0.267
 chefs-0.260
Token
Token ID198
Feature activation+1.55e-01

Pos logit contributions
ONES+0.292
Naz+0.291
OSP+0.273
areth+0.266
Sing+0.252
Neg logit contributions
isine-0.487
opian-0.449
chen-0.434
ulic-0.426
 chefs-0.422
TokenCopyright
Token ID15269
Feature activation-3.87e-01

Pos logit contributions
ONES+0.094
Naz+0.091
areth+0.087
OSP+0.086
ospels+0.080
Neg logit contributions
isine-0.157
opian-0.145
chen-0.144
ulic-0.140
 chefs-0.135
Token ©
Token ID10673
Feature activation-4.05e+00

Pos logit contributions
isine+0.288
opian+0.259
chen+0.256
ulic+0.242
 chefs+0.237
Neg logit contributions
ONES-0.343
Naz-0.337
OSP-0.326
areth-0.324
ospels-0.308
Token 2016
Token ID1584
Feature activation-8.07e+00

Pos logit contributions
isine+2.791
opian+2.495
chen+2.490
ulic+2.328
 chefs+2.284
Neg logit contributions
ONES-3.719
Naz-3.647
OSP-3.543
areth-3.528
ospels-3.376
Token Else
Token ID25974
Feature activation-3.25e+00

Pos logit contributions
isine+6.359
chen+5.925
opian+5.774
 chefs+5.402
ulic+5.282
Neg logit contributions
ONES-6.404
Naz-6.176
OSP-6.058
areth-5.825
ospels-5.697
Tokenvier
Token ID49663
Feature activation+9.04e-01

Pos logit contributions
isine+2.509
opian+2.297
chen+2.229
ulic+2.111
 chefs+2.082
Neg logit contributions
ONES-2.730
Naz-2.686
areth-2.547
OSP-2.538
CTV-2.436
Token B
Token ID347
Feature activation-4.42e-01

Pos logit contributions
ONES+0.644
Naz+0.633
OSP+0.606
areth+0.599
HTTP+0.560
Neg logit contributions
isine-0.830
opian-0.763
chen-0.747
ulic-0.720
 chefs-0.707
Token.
Token ID13
Feature activation-9.03e-01

Pos logit contributions
isine+0.387
opian+0.354
chen+0.352
ulic+0.340
 chefs+0.328
Neg logit contributions
ONES-0.331
Naz-0.326
OSP-0.311
areth-0.309
HTTP-0.289
TokenV
Token ID53
Feature activation+3.32e+00

Pos logit contributions
isine+1.064
opian+0.996
chen+0.986
ulic+0.959
 chefs+0.944
Neg logit contributions
ONES-0.405
Naz-0.392
OSP-0.366
areth-0.362
ospels-0.320
Token criminals
Token ID12954
Feature activation-3.65e+00

Pos logit contributions
isine+1.305
opian+1.194
chen+1.179
ulic+1.126
 chefs+1.121
Neg logit contributions
ONES-1.167
Naz-1.145
OSP-1.105
areth-1.094
HTTP-1.027
Token who
Token ID508
Feature activation+1.75e+00

Pos logit contributions
isine+2.914
opian+2.638
chen+2.617
ulic+2.478
 chefs+2.443
Neg logit contributions
ONES-3.028
Naz-2.965
OSP-2.873
areth-2.852
ospels-2.696
Token need
Token ID761
Feature activation+2.58e+00

Pos logit contributions
ONES+1.185
Naz+1.166
OSP+1.108
areth+1.104
HTTP+1.022
Neg logit contributions
isine-1.661
opian-1.522
chen-1.492
ulic-1.451
 chefs-1.409
Token to
Token ID284
Feature activation-9.08e-01

Pos logit contributions
ONES+1.876
Naz+1.847
OSP+1.771
areth+1.747
HTTP+1.637
Neg logit contributions
isine-2.329
opian-2.132
chen-2.093
ulic-2.017
 chefs-1.971
Token be
Token ID307
Feature activation+1.37e+00

Pos logit contributions
isine+0.784
opian+0.718
chen+0.706
ulic+0.680
 chefs+0.664
Neg logit contributions
ONES-0.694
Naz-0.681
OSP-0.657
areth-0.649
HTTP-0.610
Token locked
Token ID8970
Feature activation-8.07e+00

Pos logit contributions
ONES+1.076
Naz+1.063
OSP+1.019
areth+1.012
HTTP+0.950
Neg logit contributions
isine-1.157
opian-1.053
chen-1.024
ulic-0.990
 chefs-0.960
Token up
Token ID510
Feature activation+2.79e-01

Pos logit contributions
isine+5.056
opian+4.577
chen+4.550
 chefs+4.181
ulic+4.149
Neg logit contributions
ONES-7.711
Naz-7.510
OSP-7.385
areth-7.382
ospels-7.011
Token?
Token ID30
Feature activation-1.20e+00

Pos logit contributions
ONES+0.208
Naz+0.205
OSP+0.196
areth+0.194
HTTP+0.182
Neg logit contributions
isine-0.246
opian-0.225
chen-0.220
ulic-0.212
 chefs-0.208
Token It
Token ID632
Feature activation-1.04e+00

Pos logit contributions
isine+1.082
opian+0.994
chen+0.984
ulic+0.943
 chefs+0.923
Neg logit contributions
ONES-0.864
Naz-0.847
OSP-0.814
areth-0.805
ospels-0.752
Token depends
Token ID8338
Feature activation+1.71e-01

Pos logit contributions
isine+0.997
opian+0.925
chen+0.914
ulic+0.873
 chefs+0.866
Neg logit contributions
ONES-0.695
Naz-0.685
OSP-0.655
areth-0.639
HTTP-0.602
Token on
Token ID319
Feature activation-1.46e+00

Pos logit contributions
ONES+0.131
Naz+0.129
OSP+0.124
areth+0.123
ospels+0.115
Neg logit contributions
isine-0.149
opian-0.136
chen-0.134
ulic-0.128
 chefs-0.125
Token in
Token ID287
Feature activation-1.46e+00

Pos logit contributions
isine+3.839
opian+3.415
chen+3.394
ulic+3.239
 chefs+3.216
Neg logit contributions
ONES-4.118
Naz-4.014
OSP-3.853
areth-3.813
HTTP-3.663
Token 2013
Token ID2211
Feature activation-3.19e+00

Pos logit contributions
isine+1.117
opian+1.011
chen+0.990
ulic+0.946
 chefs+0.924
Neg logit contributions
ONES-1.254
Naz-1.234
OSP-1.193
areth-1.182
HTTP-1.118
Token to
Token ID284
Feature activation+6.90e-02

Pos logit contributions
isine+2.671
opian+2.441
chen+2.418
ulic+2.303
 chefs+2.268
Neg logit contributions
ONES-2.519
Naz-2.456
OSP-2.377
areth-2.322
HTTP-2.215
Token create
Token ID2251
Feature activation-1.76e+00

Pos logit contributions
ONES+0.054
Naz+0.053
OSP+0.051
areth+0.051
HTTP+0.047
Neg logit contributions
isine-0.058
opian-0.053
chen-0.052
ulic-0.050
 chefs-0.049
Token a
Token ID257
Feature activation+2.36e-01

Pos logit contributions
isine+1.457
opian+1.324
chen+1.299
ulic+1.247
 chefs+1.226
Neg logit contributions
ONES-1.401
Naz-1.390
OSP-1.322
areth-1.318
HTTP-1.248
Token mural
Token ID36192
Feature activation-8.01e+00

Pos logit contributions
ONES+0.191
Naz+0.188
OSP+0.181
areth+0.179
HTTP+0.168
Neg logit contributions
isine-0.195
opian-0.177
chen-0.173
ulic-0.166
 chefs-0.162
Token capturing
Token ID21430
Feature activation-8.35e-01

Pos logit contributions
isine+5.838
opian+5.271
chen+5.238
 chefs+4.915
ulic+4.888
Neg logit contributions
ONES-6.791
Naz-6.753
areth-6.463
OSP-6.409
ospels-6.175
Token the
Token ID262
Feature activation-9.82e-01

Pos logit contributions
isine+0.694
opian+0.631
chen+0.619
ulic+0.594
 chefs+0.590
Neg logit contributions
ONES-0.664
Naz-0.657
OSP-0.632
areth-0.625
HTTP-0.591
Token spirit
Token ID4437
Feature activation+5.30e-01

Pos logit contributions
isine+0.850
opian+0.778
chen+0.762
ulic+0.732
 chefs+0.722
Neg logit contributions
ONES-0.751
Naz-0.739
OSP-0.710
areth-0.704
ospels-0.661
Token of
Token ID286
Feature activation-9.71e-01

Pos logit contributions
ONES+0.425
Naz+0.418
OSP+0.401
areth+0.398
HTTP+0.375
Neg logit contributions
isine-0.442
opian-0.403
chen-0.394
ulic-0.378
 chefs-0.373
Token Toronto
Token ID6586
Feature activation+2.37e+00

Pos logit contributions
isine+0.813
opian+0.740
chen+0.725
ulic+0.697
 chefs+0.690
Neg logit contributions
ONES-0.766
Naz-0.756
OSP-0.727
areth-0.718
HTTP-0.680
Token is
Token ID318
Feature activation-1.36e+00

Pos logit contributions
isine+0.303
opian+0.282
chen+0.278
ulic+0.267
 chefs+0.265
Neg logit contributions
ONES-0.214
Naz-0.210
OSP-0.201
areth-0.197
ospels-0.184
Token going
Token ID1016
Feature activation-6.46e-01

Pos logit contributions
isine+1.105
opian+1.004
chen+0.985
ulic+0.944
 chefs+0.923
Neg logit contributions
ONES-1.107
Naz-1.090
OSP-1.050
areth-1.039
ospels-0.980
Token to
Token ID284
Feature activation-1.27e+00

Pos logit contributions
isine+0.539
opian+0.491
chen+0.482
ulic+0.461
 chefs+0.452
Neg logit contributions
ONES-0.515
Naz-0.507
OSP-0.488
areth-0.482
ospels-0.454
Token ban
Token ID3958
Feature activation-2.65e+00

Pos logit contributions
isine+1.076
opian+0.986
chen+0.968
ulic+0.930
 chefs+0.910
Neg logit contributions
ONES-0.993
Naz-0.974
OSP-0.939
areth-0.928
ospels-0.872
Token most
Token ID749
Feature activation-2.11e+00

Pos logit contributions
isine+2.163
opian+1.969
chen+1.932
ulic+1.848
 chefs+1.822
Neg logit contributions
ONES-2.151
Naz-2.114
OSP-2.027
areth-2.014
ospels-1.901
Token nude
Token ID26349
Feature activation-7.99e+00

Pos logit contributions
isine+1.727
opian+1.573
chen+1.547
ulic+1.475
 chefs+1.465
Neg logit contributions
ONES-1.698
Naz-1.673
OSP-1.605
areth-1.601
ospels-1.510
Token photos
Token ID5205
Feature activation-3.51e+00

Pos logit contributions
isine+6.250
opian+5.780
chen+5.637
 chefs+5.508
 chef+5.274
Neg logit contributions
ONES-6.474
Naz-6.212
areth-6.109
OSP-5.931
ospels-5.702
Token and
Token ID290
Feature activation-3.30e-01

Pos logit contributions
isine+3.134
opian+2.882
chen+2.857
ulic+2.723
 chefs+2.683
Neg logit contributions
ONES-2.570
Naz-2.511
OSP-2.396
areth-2.382
ospels-2.243
Token video
Token ID2008
Feature activation+5.78e-01

Pos logit contributions
isine+0.297
opian+0.273
chen+0.268
ulic+0.259
 chefs+0.254
Neg logit contributions
ONES-0.240
Naz-0.236
OSP-0.226
areth-0.223
ospels-0.209
Token from
Token ID422
Feature activation+3.97e-02

Pos logit contributions
ONES+0.424
Naz+0.417
OSP+0.400
areth+0.395
HTTP+0.371
Neg logit contributions
isine-0.517
opian-0.474
chen-0.465
ulic-0.449
 chefs-0.437
Token publicly
Token ID7271
Feature activation-3.46e+00

Pos logit contributions
ONES+0.032
Naz+0.031
OSP+0.030
areth+0.030
ospels+0.028
Neg logit contributions
isine-0.033
opian-0.030
chen-0.030
ulic-0.028
 chefs-0.028
Token46
Token ID3510
Feature activation+8.04e-01

Pos logit contributions
isine+0.000
opian+0.000
chen+0.000
ulic+0.000
 chefs+0.000
Neg logit contributions
ONES-0.000
Naz-0.000
OSP-0.000
areth-0.000
HTTP-0.000
Token.
Token ID13
Feature activation+1.37e-02

Pos logit contributions
ONES+0.571
Naz+0.561
OSP+0.538
areth+0.531
HTTP+0.496
Neg logit contributions
isine-0.740
opian-0.680
chen-0.667
ulic-0.644
 chefs-0.630
Token35
Token ID2327
Feature activation-7.80e-01

Pos logit contributions
ONES+0.007
Naz+0.007
OSP+0.006
areth+0.006
HTTP+0.006
Neg logit contributions
isine-0.015
opian-0.014
chen-0.014
ulic-0.014
 chefs-0.013
Token million
Token ID1510
Feature activation+7.91e-02

Pos logit contributions
isine+0.767
opian+0.710
chen+0.699
ulic+0.674
 chefs+0.662
Neg logit contributions
ONES-0.504
Naz-0.493
OSP-0.470
areth-0.465
HTTP-0.430
Token that
Token ID326
Feature activation-2.94e-01

Pos logit contributions
ONES+0.065
Naz+0.064
OSP+0.061
areth+0.061
HTTP+0.057
Neg logit contributions
isine-0.064
opian-0.059
chen-0.057
ulic-0.055
 chefs-0.053
Token Melvin
Token ID48834
Feature activation+7.02e+00

Pos logit contributions
isine+0.258
opian+0.236
chen+0.233
ulic+0.223
 chefs+0.219
Neg logit contributions
ONES-0.221
Naz-0.216
OSP-0.208
areth-0.206
HTTP-0.193
Token Upton
Token ID47755
Feature activation+2.09e+00

Pos logit contributions
ONES+5.036
Naz+4.953
OSP+4.645
areth+4.569
CTV+4.370
Neg logit contributions
isine-6.167
opian-5.869
chen-5.514
ulic-5.219
untled-5.194
Token Jr
Token ID7504
Feature activation+1.21e+00

Pos logit contributions
ONES+1.395
Naz+1.377
OSP+1.315
areth+1.293
HTTP+1.205
Neg logit contributions
isine-2.011
opian-1.858
chen-1.809
ulic-1.752
 chefs-1.720
Token.
Token ID13
Feature activation-8.79e-01

Pos logit contributions
ONES+0.920
Naz+0.904
OSP+0.867
areth+0.862
ospels+0.812
Neg logit contributions
isine-1.052
opian-0.960
chen-0.955
ulic-0.915
 chefs-0.887
Token is
Token ID318
Feature activation-8.14e-01

Pos logit contributions
isine+0.825
opian+0.758
chen+0.756
ulic+0.724
 chefs+0.711
Neg logit contributions
ONES-0.607
Naz-0.591
OSP-0.568
areth-0.562
ospels-0.526
Token due
Token ID2233
Feature activation-2.32e+00

Pos logit contributions
isine+0.625
opian+0.565
chen+0.551
ulic+0.528
 chefs+0.514
Neg logit contributions
ONES-0.702
Naz-0.692
OSP-0.668
areth-0.661
HTTP-0.626
Token such
Token ID884
Feature activation+2.74e+00

Pos logit contributions
ONES+2.362
Naz+2.321
OSP+2.227
areth+2.198
HTTP+2.070
Neg logit contributions
isine-2.620
opian-2.398
chen-2.333
ulic-2.267
 chefs-2.180
Token as
Token ID355
Feature activation-1.11e-01

Pos logit contributions
ONES+1.672
Naz+1.656
OSP+1.562
areth+1.541
HTTP+1.438
Neg logit contributions
isine-2.808
opian-2.573
chen-2.503
ulic-2.439
 chefs-2.391
Token The
Token ID383
Feature activation-5.43e-01

Pos logit contributions
isine+0.094
opian+0.085
chen+0.084
ulic+0.080
 chefs+0.079
Neg logit contributions
ONES-0.087
Naz-0.086
OSP-0.083
areth-0.082
HTTP-0.077
Token New
Token ID968
Feature activation+5.76e-01

Pos logit contributions
isine+0.460
opian+0.420
chen+0.414
ulic+0.396
 chefs+0.387
Neg logit contributions
ONES-0.423
Naz-0.417
OSP-0.401
areth-0.397
HTTP-0.373
Token York
Token ID1971
Feature activation+1.31e+00

Pos logit contributions
ONES+0.465
Naz+0.457
OSP+0.440
areth+0.436
HTTP+0.410
Neg logit contributions
isine-0.475
opian-0.432
chen-0.424
ulic-0.407
 chefs-0.396
Token Times
Token ID3782
Feature activation+5.74e+00

Pos logit contributions
ONES+0.886
Naz+0.874
OSP+0.829
areth+0.820
HTTP+0.764
Neg logit contributions
isine-1.240
opian-1.148
chen-1.127
ulic-1.085
 chefs-1.069
Token calling
Token ID4585
Feature activation+1.40e+00

Pos logit contributions
ONES+4.169
Naz+4.076
OSP+3.925
areth+3.840
Sing+3.653
Neg logit contributions
isine-5.047
opian-4.666
chen-4.504
ulic-4.411
 chefs-4.241
Token on
Token ID319
Feature activation+1.80e+00

Pos logit contributions
ONES+1.112
Naz+1.096
OSP+1.053
areth+1.040
HTTP+0.983
Neg logit contributions
isine-1.168
opian-1.063
chen-1.039
ulic-1.000
 chefs-0.973
Token them
Token ID606
Feature activation-1.36e+00

Pos logit contributions
ONES+1.423
Naz+1.395
OSP+1.343
areth+1.327
HTTP+1.252
Neg logit contributions
isine-1.513
opian-1.381
chen-1.345
ulic-1.294
 chefs-1.252
Token to
Token ID284
Feature activation+5.93e-01

Pos logit contributions
isine+1.130
opian+1.028
chen+1.014
ulic+0.971
 chefs+0.959
Neg logit contributions
ONES-1.083
Naz-1.056
OSP-1.019
areth-1.012
HTTP-0.956
Token ban
Token ID3958
Feature activation-2.46e+00

Pos logit contributions
ONES+0.440
Naz+0.433
OSP+0.413
areth+0.409
HTTP+0.384
Neg logit contributions
isine-0.527
opian-0.483
chen-0.474
ulic-0.456
 chefs-0.444
Token passenger
Token ID11849
Feature activation-7.84e-01

Pos logit contributions
isine+1.324
opian+1.211
chen+1.188
ulic+1.144
 chefs+1.131
Neg logit contributions
ONES-1.209
Naz-1.195
OSP-1.149
areth-1.135
HTTP-1.066
Token vehicles
Token ID5672
Feature activation+2.96e-01

Pos logit contributions
isine+0.832
opian+0.770
chen+0.762
ulic+0.737
 chefs+0.732
Neg logit contributions
ONES-0.442
Naz-0.435
OSP-0.410
areth-0.407
ospels-0.374
Token.
Token ID13
Feature activation-8.45e-01

Pos logit contributions
ONES+0.220
Naz+0.216
OSP+0.207
areth+0.205
HTTP+0.192
Neg logit contributions
isine-0.262
opian-0.240
chen-0.236
ulic-0.227
 chefs-0.222
Token Unlike
Token ID12101
Feature activation-1.37e+00

Pos logit contributions
isine+0.748
opian+0.685
chen+0.675
ulic+0.649
 chefs+0.635
Neg logit contributions
ONES-0.626
Naz-0.616
OSP-0.591
areth-0.585
ospels-0.548
Token in
Token ID287
Feature activation-1.35e+00

Pos logit contributions
isine+1.165
opian+1.067
chen+1.047
ulic+1.005
 chefs+0.988
Neg logit contributions
ONES-1.071
Naz-1.055
OSP-1.014
areth-1.003
ospels-0.942
Token Uber
Token ID12024
Feature activation+5.65e+00

Pos logit contributions
isine+1.121
opian+1.027
chen+1.005
ulic+0.967
 chefs+0.948
Neg logit contributions
ONES-1.072
Naz-1.054
OSP-1.014
areth-1.003
ospels-0.942
Token
Token ID447
Feature activation-2.55e-01

Pos logit contributions
ONES+3.665
Naz+3.607
OSP+3.432
areth+3.386
Sing+3.166
Neg logit contributions
isine-5.515
opian-5.060
chen-4.965
ulic-4.802
 chefs-4.711
Token
Token ID247
Feature activation-1.09e-01

Pos logit contributions
isine+0.236
opian+0.217
chen+0.213
ulic+0.206
 chefs+0.202
Neg logit contributions
ONES-0.179
Naz-0.176
OSP-0.169
areth-0.167
HTTP-0.156
Tokens
Token ID82
Feature activation-7.12e-01

Pos logit contributions
isine+0.099
opian+0.091
chen+0.090
ulic+0.087
 chefs+0.085
Neg logit contributions
ONES-0.078
Naz-0.076
OSP-0.073
areth-0.072
ospels-0.067
Token model
Token ID2746
Feature activation+4.13e-02

Pos logit contributions
isine+0.606
opian+0.558
chen+0.548
ulic+0.527
 chefs+0.517
Neg logit contributions
ONES-0.552
Naz-0.541
OSP-0.519
areth-0.513
HTTP-0.483
Token,
Token ID11
Feature activation+4.88e-03

Pos logit contributions
ONES+0.030
Naz+0.029
areth+0.028
OSP+0.028
ospels+0.026
Neg logit contributions
isine-0.038
opian-0.035
chen-0.034
ulic-0.033
 chefs-0.032
Token which
Token ID543
Feature activation+1.53e+00

Pos logit contributions
ONES+0.270
Naz+0.266
OSP+0.255
areth+0.252
HTTP+0.237
Neg logit contributions
isine-0.308
opian-0.281
chen-0.276
ulic-0.266
 chefs-0.259
Token was
Token ID373
Feature activation+1.88e+00

Pos logit contributions
ONES+1.070
Naz+1.052
OSP+1.006
areth+0.996
HTTP+0.928
Neg logit contributions
isine-1.423
opian-1.308
chen-1.281
ulic-1.239
 chefs-1.207
Token later
Token ID1568
Feature activation+1.09e+00

Pos logit contributions
ONES+1.464
Naz+1.445
OSP+1.400
areth+1.381
HTTP+1.299
Neg logit contributions
isine-1.598
opian-1.445
chen-1.415
ulic-1.363
 chefs-1.326
Token dubbed
Token ID17494
Feature activation-4.30e-01

Pos logit contributions
ONES+0.847
Naz+0.836
OSP+0.805
areth+0.797
HTTP+0.749
Neg logit contributions
isine-0.925
opian-0.842
chen-0.823
ulic-0.795
 chefs-0.772
Token,
Token ID11
Feature activation+5.03e-01

Pos logit contributions
isine+0.361
opian+0.329
chen+0.324
ulic+0.311
 chefs+0.303
Neg logit contributions
ONES-0.340
Naz-0.334
OSP-0.320
areth-0.317
ospels-0.300
Token Zuckerberg
Token ID32584
Feature activation+6.00e+00

Pos logit contributions
ONES+0.405
Naz+0.399
OSP+0.384
areth+0.381
HTTP+0.358
Neg logit contributions
isine-0.415
opian-0.377
chen-0.370
ulic-0.355
 chefs-0.346
Token
Token ID447
Feature activation+4.71e-01

Pos logit contributions
ONES+4.331
Naz+4.219
OSP+4.061
areth+3.983
HTTP+3.791
Neg logit contributions
isine-5.292
opian-4.884
chen-4.710
ulic-4.590
 chefs-4.500
Token
Token ID247
Feature activation+4.75e-02

Pos logit contributions
ONES+0.320
Naz+0.316
OSP+0.302
areth+0.300
HTTP+0.279
Neg logit contributions
isine-0.448
opian-0.412
chen-0.404
ulic-0.391
 chefs-0.383
Tokens
Token ID82
Feature activation-4.89e-01

Pos logit contributions
ONES+0.034
Naz+0.033
OSP+0.031
areth+0.031
ospels+0.029
Neg logit contributions
isine-0.044
opian-0.040
chen-0.040
ulic-0.038
 chefs-0.038
Token Law
Token ID3854
Feature activation+2.21e+00

Pos logit contributions
isine+0.407
opian+0.371
chen+0.364
ulic+0.349
 chefs+0.341
Neg logit contributions
ONES-0.390
Naz-0.384
OSP-0.369
areth-0.366
ospels-0.345
Token of
Token ID286
Feature activation+2.22e-01

Pos logit contributions
ONES+1.645
Naz+1.612
OSP+1.559
areth+1.531
HTTP+1.443
Neg logit contributions
isine-1.939
opian-1.776
chen-1.733
ulic-1.680
 chefs-1.644
Token.
Token ID13
Feature activation+5.27e-01

Pos logit contributions
ONES+0.144
Naz+0.141
OSP+0.136
areth+0.134
HTTP+0.125
Neg logit contributions
isine-0.181
opian-0.166
chen-0.163
ulic-0.157
 chefs-0.154
Token It
Token ID632
Feature activation-1.76e-01

Pos logit contributions
ONES+0.360
Naz+0.355
OSP+0.337
areth+0.333
HTTP+0.310
Neg logit contributions
isine-0.503
opian-0.464
chen-0.451
ulic-0.441
 chefs-0.429
Token
Token ID447
Feature activation+1.42e+00

Pos logit contributions
isine+0.168
opian+0.155
chen+0.152
ulic+0.147
 chefs+0.144
Neg logit contributions
ONES-0.120
Naz-0.118
OSP-0.113
areth-0.111
HTTP-0.103
Token
Token ID247
Feature activation+1.61e+00

Pos logit contributions
ONES+0.889
Naz+0.875
areth+0.847
OSP+0.829
HTTP+0.766
Neg logit contributions
isine-1.420
opian-1.318
chen-1.278
ulic-1.237
 chefs-1.225
Tokens
Token ID82
Feature activation+1.08e-01

Pos logit contributions
ONES+1.113
Naz+1.092
OSP+1.046
areth+1.030
HTTP+0.961
Neg logit contributions
isine-1.510
opian-1.390
chen-1.368
ulic-1.319
 chefs-1.291
Token kind
Token ID1611
Feature activation+6.57e+00

Pos logit contributions
ONES+0.085
Naz+0.083
OSP+0.080
areth+0.079
HTTP+0.074
Neg logit contributions
isine-0.092
opian-0.083
chen-0.082
ulic-0.079
 chefs-0.076
Token of
Token ID286
Feature activation+5.32e-01

Pos logit contributions
Naz+3.968
ONES+3.812
OSP+3.632
areth+3.557
ships+3.475
Neg logit contributions
isine-6.516
opian-5.878
ulic-5.682
 chefs-5.598
chen-5.579
Token a
Token ID257
Feature activation+1.13e+00

Pos logit contributions
ONES+0.420
Naz+0.414
OSP+0.397
areth+0.394
HTTP+0.369
Neg logit contributions
isine-0.448
opian-0.407
chen-0.398
ulic-0.385
 chefs-0.373
Token comedy
Token ID10997
Feature activation-2.20e+00

Pos logit contributions
ONES+0.858
Naz+0.845
OSP+0.812
areth+0.799
 wip+0.752
Neg logit contributions
isine-0.983
opian-0.894
chen-0.872
ulic-0.851
 chefs-0.821
Token runner
Token ID17490
Feature activation+1.85e+00

Pos logit contributions
isine+1.895
opian+1.732
chen+1.699
ulic+1.628
 chefs+1.602
Neg logit contributions
ONES-1.681
Naz-1.658
OSP-1.592
areth-1.576
HTTP-1.483
Token,
Token ID11
Feature activation+2.39e-01

Pos logit contributions
ONES+1.310
Naz+1.279
OSP+1.228
areth+1.212
Sing+1.139
Neg logit contributions
isine-1.682
opian-1.536
chen-1.507
ulic-1.476
 chefs-1.426
Tokenor
Token ID273
Feature activation+5.39e-02

Pos logit contributions
isine+1.933
opian+1.742
chen+1.698
ulic+1.633
 chefs+1.585
Neg logit contributions
ONES-2.221
Naz-2.188
OSP-2.113
areth-2.098
HTTP-1.983
Token highlighted
Token ID14537
Feature activation-1.99e+00

Pos logit contributions
ONES+0.037
Naz+0.037
OSP+0.035
areth+0.035
HTTP+0.032
Neg logit contributions
isine-0.051
opian-0.046
chen-0.046
ulic-0.044
 chefs-0.043
Token how
Token ID703
Feature activation+2.83e+00

Pos logit contributions
isine+1.620
opian+1.462
chen+1.444
ulic+1.372
 chefs+1.360
Neg logit contributions
ONES-1.601
Naz-1.591
OSP-1.529
areth-1.518
ospels-1.431
Token important
Token ID1593
Feature activation+6.28e-01

Pos logit contributions
ONES+2.153
Naz+2.110
OSP+2.025
areth+1.998
HTTP+1.877
Neg logit contributions
isine-2.449
opian-2.254
chen-2.196
ulic-2.120
 chefs-2.049
Token it
Token ID340
Feature activation-6.06e-01

Pos logit contributions
ONES+0.486
Naz+0.479
OSP+0.460
areth+0.456
HTTP+0.429
Neg logit contributions
isine-0.538
opian-0.489
chen-0.481
ulic-0.462
 chefs-0.454
Token was
Token ID373
Feature activation+1.47e+00

Pos logit contributions
isine+0.553
chen+0.503
opian+0.501
ulic+0.476
 chefs+0.475
Neg logit contributions
ONES-0.435
Naz-0.426
OSP-0.411
areth-0.404
ospels-0.381
Token for
Token ID329
Feature activation+5.03e-01

Pos logit contributions
ONES+1.151
Naz+1.134
OSP+1.089
areth+1.077
HTTP+1.012
Neg logit contributions
isine-1.252
opian-1.145
chen-1.119
ulic-1.076
 chefs-1.051
Token him
Token ID683
Feature activation-2.40e+00

Pos logit contributions
ONES+0.373
Naz+0.366
OSP+0.352
areth+0.348
HTTP+0.325
Neg logit contributions
isine-0.448
opian-0.411
chen-0.402
ulic-0.388
 chefs-0.378
Token to
Token ID284
Feature activation-2.35e-01

Pos logit contributions
isine+2.042
opian+1.847
chen+1.835
ulic+1.753
 chefs+1.714
Neg logit contributions
ONES-1.865
Naz-1.815
OSP-1.752
areth-1.736
HTTP-1.648
Token defend
Token ID4404
Feature activation-2.17e+00

Pos logit contributions
isine+0.206
opian+0.188
chen+0.184
ulic+0.177
 chefs+0.173
Neg logit contributions
ONES-0.178
Naz-0.175
OSP-0.168
areth-0.166
HTTP-0.156
Token his
Token ID465
Feature activation+7.68e-01

Pos logit contributions
isine+1.709
opian+1.537
chen+1.521
ulic+1.447
 chefs+1.425
Neg logit contributions
ONES-1.809
Naz-1.784
OSP-1.717
areth-1.706
HTTP-1.613
Token,
Token ID11
Feature activation-7.53e-02

Pos logit contributions
isine+3.516
chen+3.235
opian+3.217
ulic+3.086
 chefs+3.060
Neg logit contributions
ONES-2.791
Naz-2.738
areth-2.622
OSP-2.616
ospels-2.445
Token further
Token ID2252
Feature activation+5.16e-01

Pos logit contributions
isine+0.065
opian+0.059
chen+0.058
ulic+0.056
 chefs+0.054
Neg logit contributions
ONES-0.058
Naz-0.057
OSP-0.055
areth-0.054
HTTP-0.051
Token Russian
Token ID3394
Feature activation+5.10e-01

Pos logit contributions
ONES+0.393
Naz+0.386
OSP+0.371
areth+0.367
HTTP+0.344
Neg logit contributions
isine-0.449
opian-0.411
chen-0.403
ulic-0.388
 chefs-0.379
Token inc
Token ID753
Feature activation+3.71e+00

Pos logit contributions
ONES+0.360
Naz+0.351
OSP+0.339
areth+0.335
ospels+0.313
Neg logit contributions
isine-0.472
opian-0.435
chen-0.430
ulic-0.413
 chefs-0.407
Tokenursions
Token ID42394
Feature activation+1.99e+00

Pos logit contributions
ONES+3.459
Naz+3.437
OSP+3.327
areth+3.299
ospels+3.139
Neg logit contributions
isine-2.505
opian-2.209
chen-2.156
ulic-2.033
 chefs-2.030
Token,
Token ID11
Feature activation+5.10e-01

Pos logit contributions
ONES+1.566
Naz+1.549
OSP+1.483
areth+1.475
HTTP+1.381
Neg logit contributions
isine-1.661
opian-1.508
chen-1.477
ulic-1.430
 chefs-1.391
Token would
Token ID561
Feature activation-1.76e+00

Pos logit contributions
ONES+0.332
Naz+0.325
OSP+0.311
areth+0.306
HTTP+0.284
Neg logit contributions
isine-0.500
opian-0.462
chen-0.455
ulic-0.439
 chefs-0.432
Token bring
Token ID2222
Feature activation-2.10e+00

Pos logit contributions
isine+1.516
opian+1.393
chen+1.364
ulic+1.310
 chefs+1.285
Neg logit contributions
ONES-1.354
Naz-1.321
OSP-1.277
areth-1.261
HTTP-1.187
Token the
Token ID262
Feature activation-7.55e-01

Pos logit contributions
isine+1.804
opian+1.647
chen+1.627
ulic+1.556
 chefs+1.536
Neg logit contributions
ONES-1.617
Naz-1.576
OSP-1.545
areth-1.523
ospels-1.433
Token crisis
Token ID4902
Feature activation-4.52e+00

Pos logit contributions
isine+0.674
opian+0.618
chen+0.607
ulic+0.584
 chefs+0.572
Neg logit contributions
ONES-0.557
Naz-0.548
OSP-0.527
areth-0.521
ospels-0.487
Token to
Token ID284
Feature activation-1.30e-01

Pos logit contributions
isine+3.654
opian+3.360
chen+3.279
ulic+3.117
 chefs+3.094
Neg logit contributions
ONES-3.644
Naz-3.556
OSP-3.488
areth-3.399
ospels-3.269
Token
Token ID447
Feature activation+9.53e-01

Pos logit contributions
ONES+1.370
Naz+1.350
OSP+1.286
areth+1.274
HTTP+1.191
Neg logit contributions
isine-1.780
opian-1.640
chen-1.599
ulic-1.541
 chefs-1.509
Token
Token ID247
Feature activation+7.72e-01

Pos logit contributions
ONES+0.613
Naz+0.604
OSP+0.579
areth+0.575
HTTP+0.529
Neg logit contributions
isine-0.942
opian-0.872
chen-0.850
ulic-0.824
 chefs-0.808
Tokens
Token ID82
Feature activation+1.97e-01

Pos logit contributions
ONES+0.536
Naz+0.526
OSP+0.504
areth+0.497
HTTP+0.464
Neg logit contributions
isine-0.723
opian-0.664
chen-0.655
ulic-0.631
 chefs-0.618
Token bliss
Token ID30533
Feature activation+2.60e+00

Pos logit contributions
ONES+0.159
Naz+0.157
OSP+0.151
areth+0.149
HTTP+0.140
Neg logit contributions
isine-0.162
opian-0.147
chen-0.144
ulic-0.139
 chefs-0.135
Tokenful
Token ID913
Feature activation+1.64e+00

Pos logit contributions
ONES+2.395
Naz+2.366
OSP+2.288
areth+2.272
HTTP+2.154
Neg logit contributions
isine-1.845
opian-1.642
chen-1.604
ulic-1.538
 chefs-1.484
Token,
Token ID11
Feature activation+2.98e-01

Pos logit contributions
ONES+1.270
Naz+1.252
OSP+1.203
areth+1.191
HTTP+1.116
Neg logit contributions
isine-1.410
opian-1.285
chen-1.259
ulic-1.213
 chefs-1.181
Token se
Token ID384
Feature activation-9.03e-02

Pos logit contributions
ONES+0.231
Naz+0.228
OSP+0.219
areth+0.217
HTTP+0.204
Neg logit contributions
isine-0.254
opian-0.232
chen-0.228
ulic-0.219
 chefs-0.214
Tokenrene
Token ID25924
Feature activation+4.78e-02

Pos logit contributions
isine+0.073
opian+0.066
chen+0.065
ulic+0.062
 chefs+0.061
Neg logit contributions
ONES-0.074
Naz-0.073
OSP-0.070
areth-0.070
HTTP-0.066
Token save
Token ID3613
Feature activation+3.85e+00

Pos logit contributions
ONES+0.036
Naz+0.036
OSP+0.034
areth+0.034
HTTP+0.032
Neg logit contributions
isine-0.042
opian-0.038
chen-0.037
ulic-0.036
 chefs-0.035
Token game
Token ID983
Feature activation+8.16e-01

Pos logit contributions
ONES+2.834
Naz+2.785
OSP+2.675
areth+2.648
ospels+2.473
Neg logit contributions
isine-3.438
opian-3.151
chen-3.092
ulic-2.985
 chefs-2.911
Token music
Token ID2647
Feature activation+9.82e-01

Pos logit contributions
ONES+0.580
Naz+0.570
OSP+0.546
areth+0.540
HTTP+0.504
Neg logit contributions
isine-0.751
opian-0.690
chen-0.677
ulic-0.653
 chefs-0.639
Token the
Token ID262
Feature activation-3.79e-01

Pos logit contributions
ONES+1.163
Naz+1.144
OSP+1.099
areth+1.090
HTTP+1.024
Neg logit contributions
isine-1.251
opian-1.142
chen-1.119
ulic-1.074
 chefs-1.050
Token longest
Token ID14069
Feature activation-1.15e+00

Pos logit contributions
isine+0.270
opian+0.242
chen+0.236
ulic+0.224
 chefs+0.219
Neg logit contributions
ONES-0.349
Naz-0.344
OSP-0.332
areth-0.330
HTTP-0.313
Token and
Token ID290
Feature activation+4.99e-02

Pos logit contributions
isine+1.014
opian+0.933
chen+0.911
ulic+0.867
 chefs+0.861
Neg logit contributions
ONES-0.862
Naz-0.846
OSP-0.810
areth-0.809
ospels-0.752
Token most
Token ID749
Feature activation-1.83e+00

Pos logit contributions
ONES+0.054
Naz+0.053
OSP+0.052
areth+0.051
HTTP+0.049
Neg logit contributions
isine-0.028
opian-0.024
chen-0.023
ulic-0.022
 chefs-0.021
Token laud
Token ID28907
Feature activation+2.47e+00

Pos logit contributions
isine+1.529
opian+1.410
chen+1.377
ulic+1.306
 chefs+1.303
Neg logit contributions
ONES-1.446
Naz-1.415
OSP-1.363
areth-1.360
ospels-1.277
Tokenatory
Token ID2870
Feature activation+2.41e+00

Pos logit contributions
Naz+1.634
ONES+1.624
OSP+1.547
areth+1.533
ospels+1.436
Neg logit contributions
isine-2.373
opian-2.148
chen-2.103
ulic-2.050
 chefs-2.020
Token article
Token ID2708
Feature activation-3.93e-01

Pos logit contributions
ONES+1.910
Naz+1.881
OSP+1.812
areth+1.788
HTTP+1.685
Neg logit contributions
isine-2.011
opian-1.828
chen-1.792
ulic-1.728
 chefs-1.677
Token about
Token ID546
Feature activation+3.26e+00

Pos logit contributions
isine+0.326
opian+0.297
chen+0.292
ulic+0.278
 chefs+0.273
Neg logit contributions
ONES-0.314
Naz-0.309
OSP-0.297
areth-0.295
HTTP-0.278
Token
Token ID564
Feature activation-9.15e-01

Pos logit contributions
ONES+2.418
Naz+2.390
OSP+2.286
areth+2.246
HTTP+2.104
Neg logit contributions
isine-2.874
opian-2.633
chen-2.572
ulic-2.486
 chefs-2.409
Token
Token ID250
Feature activation-4.23e-01

Pos logit contributions
isine+0.737
opian+0.668
chen+0.657
ulic+0.627
 chefs+0.613
Neg logit contributions
ONES-0.757
Naz-0.740
OSP-0.716
areth-0.707
ospels-0.667
TokenThe
Token ID464
Feature activation-2.35e-01

Pos logit contributions
isine+0.377
opian+0.344
chen+0.339
ulic+0.326
 chefs+0.318
Neg logit contributions
ONES-0.314
Naz-0.305
OSP-0.296
areth-0.293
ospels-0.274
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
isine+0.489
opian+0.448
chen+0.443
ulic+0.426
 chefs+0.415
Neg logit contributions
ONES-0.399
Naz-0.392
OSP-0.377
areth-0.373
ospels-0.349
Token
Token ID198
Feature activation-5.21e-01

Pos logit contributions
isine+0.320
opian+0.295
chen+0.287
ulic+0.281
 chefs+0.276
Neg logit contributions
ONES-0.202
Naz-0.200
OSP-0.188
areth-0.185
HTTP-0.173
TokenCouncil
Token ID40940
Feature activation+3.48e-01

Pos logit contributions
isine+0.522
opian+0.485
chen+0.481
ulic+0.465
 chefs+0.451
Neg logit contributions
ONES-0.321
Naz-0.312
areth-0.299
OSP-0.299
 wip-0.276
Token member
Token ID2888
Feature activation+2.78e+00

Pos logit contributions
ONES+0.267
Naz+0.262
OSP+0.252
areth+0.249
HTTP+0.234
Neg logit contributions
isine-0.301
opian-0.275
chen-0.270
ulic-0.260
 chefs-0.254
Token John
Token ID1757
Feature activation-8.63e-01

Pos logit contributions
ONES+2.107
Naz+2.077
OSP+1.986
areth+1.973
ospels+1.839
Neg logit contributions
isine-2.410
opian-2.203
chen-2.143
ulic-2.071
 chefs-2.001
Token Elder
Token ID15624
Feature activation+5.40e+00

Pos logit contributions
isine+0.738
opian+0.674
chen+0.664
ulic+0.637
 chefs+0.621
Neg logit contributions
ONES-0.668
Naz-0.658
OSP-0.634
areth-0.624
HTTP-0.590
Token,
Token ID11
Feature activation-1.01e+00

Pos logit contributions
ONES+3.784
Naz+3.686
OSP+3.583
areth+3.529
Sing+3.312
Neg logit contributions
isine-4.938
opian-4.473
chen-4.335
ulic-4.225
 chefs-4.186
Token who
Token ID508
Feature activation+1.99e+00

Pos logit contributions
isine+0.877
opian+0.801
chen+0.786
ulic+0.756
 chefs+0.739
Neg logit contributions
ONES-0.778
Naz-0.765
OSP-0.735
areth-0.727
HTTP-0.683
Token is
Token ID318
Feature activation-1.25e+00

Pos logit contributions
ONES+1.345
Naz+1.321
OSP+1.262
areth+1.248
HTTP+1.160
Neg logit contributions
isine-1.894
opian-1.743
chen-1.712
ulic-1.655
 chefs-1.619
Token also
Token ID635
Feature activation+1.22e+00

Pos logit contributions
isine+1.015
opian+0.921
chen+0.901
ulic+0.865
 chefs+0.843
Neg logit contributions
ONES-1.028
Naz-1.013
OSP-0.976
areth-0.966
HTTP-0.912
Token a
Token ID257
Feature activation+5.61e-03

Pos logit contributions
ONES+0.946
Naz+0.932
OSP+0.895
areth+0.888
HTTP+0.834
Neg logit contributions
isine-1.042
opian-0.946
chen-0.915
ulic-0.886
 chefs-0.859
Token potentially
Token ID6196
Feature activation-8.22e-01

Pos logit contributions
ONES+1.260
Naz+1.241
OSP+1.192
areth+1.183
HTTP+1.109
Neg logit contributions
isine-1.427
opian-1.297
chen-1.267
ulic-1.223
 chefs-1.192
Token dangerous
Token ID4923
Feature activation-8.05e-01

Pos logit contributions
isine+0.680
opian+0.621
chen+0.610
ulic+0.585
 chefs+0.572
Neg logit contributions
ONES-0.658
Naz-0.648
OSP-0.623
areth-0.617
ospels-0.582
Token Trap
Token ID21914
Feature activation-4.30e-01

Pos logit contributions
isine+0.720
opian+0.660
chen+0.650
ulic+0.626
 chefs+0.613
Neg logit contributions
ONES-0.591
Naz-0.580
OSP-0.557
areth-0.551
ospels-0.517
Token Card
Token ID5172
Feature activation+2.28e+00

Pos logit contributions
isine+0.384
opian+0.352
chen+0.346
ulic+0.333
 chefs+0.326
Neg logit contributions
ONES-0.317
Naz-0.312
OSP-0.299
areth-0.296
HTTP-0.277
Token.
Token ID13
Feature activation+4.18e-01

Pos logit contributions
ONES+1.646
Naz+1.621
OSP+1.555
areth+1.529
HTTP+1.447
Neg logit contributions
isine-2.058
opian-1.888
chen-1.835
ulic-1.782
 chefs-1.738
Token If
Token ID1002
Feature activation-2.75e+00

Pos logit contributions
ONES+0.301
Naz+0.296
OSP+0.283
areth+0.280
HTTP+0.262
Neg logit contributions
isine-0.382
opian-0.350
chen-0.341
ulic-0.331
 chefs-0.323
Token you
Token ID345
Feature activation-8.62e-01

Pos logit contributions
isine+2.212
opian+2.013
chen+1.994
ulic+1.891
 chefs+1.876
Neg logit contributions
ONES-2.246
Naz-2.219
OSP-2.142
areth-2.105
ospels-2.018
Token learn
Token ID2193
Feature activation-2.38e+00

Pos logit contributions
isine+0.791
opian+0.726
chen+0.717
ulic+0.689
 chefs+0.675
Neg logit contributions
ONES-0.613
Naz-0.602
OSP-0.580
areth-0.571
ospels-0.535
Token how
Token ID703
Feature activation+2.00e+00

Pos logit contributions
isine+1.998
opian+1.832
chen+1.816
ulic+1.731
 chefs+1.716
Neg logit contributions
ONES-1.867
Naz-1.837
OSP-1.749
areth-1.743
HTTP-1.639
Token best
Token ID1266
Feature activation-6.96e-01

Pos logit contributions
ONES+1.482
Naz+1.457
OSP+1.395
areth+1.384
ospels+1.296
Neg logit contributions
isine-1.778
opian-1.628
chen-1.602
ulic-1.545
 chefs-1.516
Token to
Token ID284
Feature activation-1.45e-01

Pos logit contributions
isine+0.583
opian+0.534
chen+0.525
ulic+0.507
 chefs+0.496
Neg logit contributions
ONES-0.560
Naz-0.541
OSP-0.523
areth-0.521
ospels-0.489
Token Hillary
Token ID5073
Feature activation-2.30e+00

Pos logit contributions
isine+0.624
opian+0.568
chen+0.556
ulic+0.534
 chefs+0.522
Neg logit contributions
ONES-0.595
Naz-0.586
OSP-0.564
areth-0.558
HTTP-0.525
Token Clinton
Token ID2605
Feature activation-9.47e-01

Pos logit contributions
isine+2.001
opian+1.827
chen+1.790
ulic+1.723
 chefs+1.680
Neg logit contributions
ONES-1.758
Naz-1.719
OSP-1.656
areth-1.638
ospels-1.540
Token to
Token ID284
Feature activation-5.01e-01

Pos logit contributions
isine+0.848
opian+0.776
chen+0.761
ulic+0.734
 chefs+0.718
Neg logit contributions
ONES-0.701
Naz-0.685
OSP-0.659
areth-0.652
ospels-0.610
Token Bernie
Token ID10477
Feature activation-2.12e+00

Pos logit contributions
isine+0.439
opian+0.401
chen+0.393
ulic+0.379
 chefs+0.370
Neg logit contributions
ONES-0.379
Naz-0.373
OSP-0.358
areth-0.354
HTTP-0.332
Token Sanders
Token ID5831
Feature activation+1.00e+00

Pos logit contributions
isine+1.747
opian+1.589
chen+1.571
ulic+1.500
 chefs+1.463
Neg logit contributions
ONES-1.700
Naz-1.671
OSP-1.617
areth-1.601
ospels-1.512
Token in
Token ID287
Feature activation-4.58e-01

Pos logit contributions
ONES+0.738
Naz+0.730
OSP+0.697
areth+0.689
HTTP+0.647
Neg logit contributions
isine-0.896
opian-0.820
chen-0.804
ulic-0.775
 chefs-0.759
Token the
Token ID262
Feature activation+1.29e+00

Pos logit contributions
isine+0.382
opian+0.347
chen+0.341
ulic+0.327
 chefs+0.319
Neg logit contributions
ONES-0.365
Naz-0.359
OSP-0.346
areth-0.342
HTTP-0.322
Token primary
Token ID4165
Feature activation-2.28e+00

Pos logit contributions
ONES+1.056
Naz+1.040
OSP+1.006
areth+0.992
HTTP+0.941
Neg logit contributions
isine-1.056
opian-0.943
chen-0.931
ulic-0.891
 chefs-0.868
Token last
Token ID938
Feature activation+9.19e-01

Pos logit contributions
isine+1.990
opian+1.857
chen+1.814
ulic+1.746
 chefs+1.718
Neg logit contributions
ONES-1.704
Naz-1.683
OSP-1.611
areth-1.603
HTTP-1.489
Token year
Token ID614
Feature activation-1.38e+00

Pos logit contributions
ONES+0.832
Naz+0.821
OSP+0.794
areth+0.787
HTTP+0.747
Neg logit contributions
isine-0.666
opian-0.597
chen-0.582
ulic-0.556
 chefs-0.540
Token.
Token ID13
Feature activation+5.50e-01

Pos logit contributions
isine+1.257
opian+1.159
chen+1.140
ulic+1.097
 chefs+1.070
Neg logit contributions
ONES-0.990
Naz-0.965
OSP-0.929
areth-0.919
ospels-0.858
Token go
Token ID467
Feature activation-2.72e-01

Pos logit contributions
ONES+0.309
Naz+0.303
OSP+0.290
areth+0.287
HTTP+0.268
Neg logit contributions
isine-0.400
opian-0.367
chen-0.361
ulic-0.348
 chefs-0.341
Token hand
Token ID1021
Feature activation-7.37e-01

Pos logit contributions
isine+0.218
opian+0.198
chen+0.194
ulic+0.186
 chefs+0.182
Neg logit contributions
ONES-0.226
Naz-0.223
OSP-0.214
areth-0.212
ospels-0.200
Token in
Token ID287
Feature activation+3.33e-01

Pos logit contributions
isine+0.520
opian+0.472
chen+0.456
ulic+0.429
 chefs+0.424
Neg logit contributions
ONES-0.684
Naz-0.673
OSP-0.650
areth-0.639
ospels-0.614
Token hand
Token ID1021
Feature activation+1.86e+00

Pos logit contributions
ONES+0.264
Naz+0.260
OSP+0.250
areth+0.248
HTTP+0.233
Neg logit contributions
isine-0.278
opian-0.253
chen-0.245
ulic-0.238
 chefs-0.231
Token to
Token ID284
Feature activation+8.46e-01

Pos logit contributions
ONES+1.481
Naz+1.462
OSP+1.408
areth+1.392
HTTP+1.309
Neg logit contributions
isine-1.546
opian-1.397
chen-1.369
ulic-1.324
 chefs-1.288
Token realize
Token ID6537
Feature activation-9.78e-01

Pos logit contributions
ONES+0.655
Naz+0.645
OSP+0.620
areth+0.613
HTTP+0.576
Neg logit contributions
isine-0.726
opian-0.661
chen-0.649
ulic-0.624
 chefs-0.609
Token the
Token ID262
Feature activation-2.60e-01

Pos logit contributions
isine+0.848
opian+0.775
chen+0.761
ulic+0.732
 chefs+0.716
Neg logit contributions
ONES-0.747
Naz-0.735
OSP-0.705
areth-0.699
ospels-0.655
Token full
Token ID1336
Feature activation-4.59e-01

Pos logit contributions
isine+0.218
opian+0.198
chen+0.194
ulic+0.187
 chefs+0.182
Neg logit contributions
ONES-0.207
Naz-0.203
OSP-0.196
areth-0.193
HTTP-0.182
Token potential
Token ID2785
Feature activation+1.10e+00

Pos logit contributions
isine+0.384
opian+0.350
chen+0.343
ulic+0.329
 chefs+0.322
Neg logit contributions
ONES-0.365
Naz-0.359
OSP-0.346
areth-0.343
HTTP-0.322
Token of
Token ID286
Feature activation-4.58e-01

Pos logit contributions
ONES+0.821
Naz+0.808
OSP+0.780
areth+0.761
HTTP+0.720
Neg logit contributions
isine-0.970
opian-0.885
chen-0.866
ulic-0.834
 chefs-0.816
Token process
Token ID1429
Feature activation-2.66e-01

Pos logit contributions
isine+0.391
opian+0.357
chen+0.351
ulic+0.337
 chefs+0.330
Neg logit contributions
ONES-0.356
Naz-0.350
OSP-0.337
areth-0.334
HTTP-0.313
TokenJay
Token ID30568
Feature activation+1.25e+00

Pos logit contributions
ONES+0.097
Naz+0.095
OSP+0.093
areth+0.092
 wip+0.087
Neg logit contributions
isine-0.106
opian-0.096
chen-0.096
ulic-0.092
 chefs-0.088
Token C
Token ID327
Feature activation+7.58e-01

Pos logit contributions
ONES+1.050
Naz+1.038
OSP+1.005
areth+0.996
Sing+0.953
Neg logit contributions
isine-0.998
opian-0.896
ulic-0.836
chen-0.830
 chefs-0.804
Tokenz
Token ID89
Feature activation+8.56e-01

Pos logit contributions
ONES+0.493
Naz+0.488
areth+0.464
OSP+0.460
Sing+0.427
Neg logit contributions
isine-0.742
opian-0.679
chen-0.659
 chefs-0.647
ulic-0.647
Tokenark
Token ID668
Feature activation-9.50e-01

Pos logit contributions
ONES+0.630
Naz+0.619
areth+0.608
OSP+0.587
Sing+0.559
Neg logit contributions
isine-0.754
opian-0.682
ulic-0.659
chen-0.657
 chefs-0.654
Tokenowski
Token ID12079
Feature activation+6.00e-01

Pos logit contributions
isine+0.418
opian+0.337
chen+0.323
ulic+0.300
 chefs+0.294
Neg logit contributions
ONES-1.135
Naz-1.122
OSP-1.091
areth-1.085
HTTP-1.043
Token:
Token ID25
Feature activation-6.59e-01

Pos logit contributions
ONES+0.428
Naz+0.423
OSP+0.399
areth+0.397
Sing+0.377
Neg logit contributions
isine-0.555
opian-0.510
chen-0.487
ulic-0.481
 chefs-0.472
Token And
Token ID843
Feature activation+1.75e+00

Pos logit contributions
isine+0.618
opian+0.569
chen+0.558
ulic+0.539
 chefs+0.528
Neg logit contributions
ONES-0.456
Naz-0.448
OSP-0.429
areth-0.424
HTTP-0.395
Token you
Token ID345
Feature activation+1.02e+00

Pos logit contributions
ONES+1.314
Naz+1.293
OSP+1.241
areth+1.227
HTTP+1.150
Neg logit contributions
isine-1.534
opian-1.401
chen-1.373
ulic-1.322
 chefs-1.279
Token
Token ID447
Feature activation+1.30e+00

Pos logit contributions
ONES+0.645
Naz+0.634
OSP+0.599
areth+0.596
HTTP+0.549
Neg logit contributions
isine-1.020
opian-0.942
chen-0.922
ulic-0.895
 chefs-0.874
Token
Token ID247
Feature activation+9.23e-01

Pos logit contributions
Naz+0.781
ONES+0.780
areth+0.750
OSP+0.731
HTTP+0.682
Neg logit contributions
isine-1.324
opian-1.233
chen-1.189
 chefs-1.149
ulic-1.149
Tokenll
Token ID297
Feature activation-3.60e-01

Pos logit contributions
ONES+0.716
Naz+0.707
OSP+0.678
areth+0.674
HTTP+0.632
Neg logit contributions
isine-0.787
opian-0.717
chen-0.701
ulic-0.675
 chefs-0.660
Token to
Token ID284
Feature activation+7.08e-01

Pos logit contributions
isine+0.025
opian+0.023
chen+0.022
ulic+0.022
 chefs+0.021
Neg logit contributions
ONES-0.022
Naz-0.021
OSP-0.021
areth-0.020
ospels-0.019
Token Recap
Token ID46585
Feature activation-1.68e+00

Pos logit contributions
ONES+0.535
Naz+0.528
OSP+0.506
areth+0.500
ospels+0.471
Neg logit contributions
isine-0.617
opian-0.565
chen-0.555
ulic-0.533
 chefs-0.524
Token San
Token ID2986
Feature activation+2.60e+00

Pos logit contributions
isine+1.458
opian+1.330
chen+1.312
ulic+1.250
 chefs+1.232
Neg logit contributions
ONES-1.269
Naz-1.254
OSP-1.194
areth-1.185
ospels-1.117
Token Juan
Token ID16852
Feature activation-8.52e-01

Pos logit contributions
ONES+1.974
Naz+1.944
OSP+1.865
areth+1.846
HTTP+1.732
Neg logit contributions
isine-2.271
opian-2.078
chen-2.034
ulic-1.958
 chefs-1.913
Token Del
Token ID4216
Feature activation-2.82e+00

Pos logit contributions
isine+0.597
opian+0.534
chen+0.526
ulic+0.502
 chefs+0.491
Neg logit contributions
ONES-0.789
Naz-0.778
OSP-0.750
areth-0.745
ospels-0.711
Token Sur
Token ID4198
Feature activation-1.91e+00

Pos logit contributions
isine+2.217
opian+2.004
chen+1.963
ulic+1.880
 chefs+1.833
Neg logit contributions
ONES-2.386
Naz-2.350
OSP-2.267
areth-2.246
HTTP-2.122
Token Episode
Token ID7922
Feature activation-6.89e-01

Pos logit contributions
isine+1.644
opian+1.498
chen+1.484
ulic+1.418
 chefs+1.401
Neg logit contributions
ONES-1.460
Naz-1.442
OSP-1.377
areth-1.371
ospels-1.295
Token 5
Token ID642
Feature activation-9.39e-01

Pos logit contributions
isine+0.585
opian+0.533
chen+0.522
ulic+0.502
 chefs+0.490
Neg logit contributions
ONES-0.540
Naz-0.531
OSP-0.511
areth-0.506
HTTP-0.475
Token
Token ID198
Feature activation+6.76e-01

Pos logit contributions
isine+0.823
opian+0.751
chen+0.744
ulic+0.711
 chefs+0.700
Neg logit contributions
ONES-0.702
Naz-0.693
OSP-0.661
areth-0.655
HTTP-0.618
Token
Token ID198
Feature activation+4.50e-01

Pos logit contributions
ONES+0.413
Naz+0.411
OSP+0.384
areth+0.376
Sing+0.354
Neg logit contributions
isine-0.699
opian-0.645
chen-0.623
ulic-0.614
 chefs-0.606
TokenCoach
Token ID40677
Feature activation-1.30e-01

Pos logit contributions
ONES+0.269
Naz+0.260
OSP+0.248
areth+0.247
ospels+0.229
Neg logit contributions
isine-0.461
opian-0.427
chen-0.424
ulic-0.408
 chefs-0.400
Token rise
Token ID4485
Feature activation-2.74e+00

Pos logit contributions
isine+1.641
opian+1.498
chen+1.473
ulic+1.418
 chefs+1.383
Neg logit contributions
ONES-1.618
Naz-1.576
OSP-1.525
areth-1.508
HTTP-1.424
Token to
Token ID284
Feature activation-5.50e-01

Pos logit contributions
isine+2.322
opian+2.129
chen+2.076
ulic+2.012
 chefs+1.972
Neg logit contributions
ONES-2.149
Naz-2.095
OSP-2.006
areth-1.992
ospels-1.891
Token 11
Token ID1367
Feature activation-1.91e+00

Pos logit contributions
isine+0.455
opian+0.413
chen+0.405
ulic+0.389
 chefs+0.379
Neg logit contributions
ONES-0.442
Naz-0.436
OSP-0.419
areth-0.415
HTTP-0.391
Token reviews
Token ID8088
Feature activation+4.15e-01

Pos logit contributions
isine+1.588
opian+1.440
chen+1.416
ulic+1.357
 chefs+1.335
Neg logit contributions
ONES-1.517
Naz-1.488
OSP-1.427
areth-1.420
ospels-1.333
Token by
Token ID416
Feature activation+2.37e-01

Pos logit contributions
ONES+0.304
Naz+0.299
OSP+0.286
areth+0.283
HTTP+0.265
Neg logit contributions
isine-0.373
opian-0.342
chen-0.336
ulic-0.324
 chefs-0.316
Token 2021
Token ID33448
Feature activation-5.47e+00

Pos logit contributions
ONES+0.182
Naz+0.180
OSP+0.173
areth+0.171
ospels+0.160
Neg logit contributions
isine-0.205
opian-0.186
chen-0.183
ulic-0.175
 chefs-0.171
Token,
Token ID11
Feature activation-1.75e-01

Pos logit contributions
isine+4.574
opian+4.146
chen+4.122
ulic+3.903
 chefs+3.851
Neg logit contributions
ONES-4.276
Naz-4.148
areth-4.024
OSP-3.975
ospels-3.751
Token and
Token ID290
Feature activation+5.50e-02

Pos logit contributions
isine+0.153
opian+0.140
chen+0.137
ulic+0.132
 chefs+0.129
Neg logit contributions
ONES-0.133
Naz-0.131
OSP-0.126
areth-0.124
HTTP-0.117
Token 22
Token ID2534
Feature activation-1.86e+00

Pos logit contributions
ONES+0.043
Naz+0.042
OSP+0.041
areth+0.040
HTTP+0.038
Neg logit contributions
isine-0.047
opian-0.043
chen-0.042
ulic-0.040
 chefs-0.039
Token by
Token ID416
Feature activation-1.55e-01

Pos logit contributions
isine+1.517
opian+1.378
chen+1.353
ulic+1.295
 chefs+1.274
Neg logit contributions
ONES-1.504
Naz-1.477
OSP-1.415
areth-1.405
HTTP-1.324
Token 2024
Token ID48609
Feature activation-6.30e+00

Pos logit contributions
isine+0.116
opian+0.104
chen+0.102
ulic+0.097
 chefs+0.095
Neg logit contributions
ONES-0.136
Naz-0.134
OSP-0.130
areth-0.129
HTTP-0.122
Token applied
Token ID5625
Feature activation-1.72e+00

Pos logit contributions
ONES+0.168
Naz+0.166
OSP+0.159
areth+0.157
HTTP+0.147
Neg logit contributions
isine-0.214
opian-0.197
chen-0.193
ulic-0.187
 chefs-0.183
Token it
Token ID340
Feature activation-1.32e+00

Pos logit contributions
isine+1.425
opian+1.295
chen+1.274
ulic+1.232
 chefs+1.207
Neg logit contributions
ONES-1.364
Naz-1.350
OSP-1.297
areth-1.288
ospels-1.214
Token to
Token ID284
Feature activation+4.53e-01

Pos logit contributions
isine+1.126
opian+1.028
chen+1.008
ulic+0.973
 chefs+0.951
Neg logit contributions
ONES-1.017
Naz-1.005
OSP-0.966
areth-0.956
ospels-0.900
Token the
Token ID262
Feature activation-1.03e-01

Pos logit contributions
ONES+0.359
Naz+0.353
OSP+0.340
areth+0.336
HTTP+0.316
Neg logit contributions
isine-0.380
opian-0.345
chen-0.339
ulic-0.324
 chefs-0.317
Token Barnett
Token ID38174
Feature activation-3.30e+00

Pos logit contributions
isine+0.086
opian+0.078
chen+0.076
ulic+0.073
 chefs+0.071
Neg logit contributions
ONES-0.082
Naz-0.081
OSP-0.078
areth-0.077
HTTP-0.072
Token shale
Token ID30498
Feature activation-8.13e+00

Pos logit contributions
isine+2.863
opian+2.663
chen+2.613
ulic+2.560
 chefs+2.451
Neg logit contributions
ONES-2.427
Naz-2.405
OSP-2.314
areth-2.263
HTTP-2.144
Token,
Token ID11
Feature activation-6.12e-01

Pos logit contributions
isine+6.668
opian+6.316
ulic+6.142
chen+6.138
 chefs+5.815
Neg logit contributions
ONES-5.942
Naz-5.889
OSP-5.616
areth-5.591
ospels-5.285
Token a
Token ID257
Feature activation-4.03e-01

Pos logit contributions
isine+0.546
opian+0.501
chen+0.492
ulic+0.475
 chefs+0.464
Neg logit contributions
ONES-0.450
Naz-0.443
OSP-0.425
areth-0.421
HTTP-0.394
Token mile
Token ID10591
Feature activation-1.29e+00

Pos logit contributions
isine+0.349
opian+0.319
chen+0.313
ulic+0.301
 chefs+0.294
Neg logit contributions
ONES-0.308
Naz-0.303
OSP-0.291
areth-0.288
HTTP-0.270
Token-
Token ID12
Feature activation-2.49e+00

Pos logit contributions
isine+1.157
opian+1.070
chen+1.048
ulic+1.003
 chefs+0.985
Neg logit contributions
ONES-0.937
Naz-0.918
OSP-0.880
areth-0.867
ospels-0.821
Tokenand
Token ID392
Feature activation+1.52e+00

Pos logit contributions
isine+1.828
opian+1.657
chen+1.630
ulic+1.523
 chefs+1.462
Neg logit contributions
ONES-2.218
Naz-2.156
OSP-2.104
areth-2.052
ospels-1.989
Token The
Token ID383
Feature activation-5.24e-01

Pos logit contributions
ONES+0.211
Naz+0.208
OSP+0.199
areth+0.197
ospels+0.185
Neg logit contributions
isine-0.261
opian-0.239
chen-0.237
ulic-0.227
 chefs-0.222
Token move
Token ID1445
Feature activation-2.65e-01

Pos logit contributions
isine+0.455
opian+0.418
chen+0.411
ulic+0.394
 chefs+0.388
Neg logit contributions
ONES-0.398
Naz-0.391
OSP-0.376
areth-0.372
ospels-0.350
Token would
Token ID561
Feature activation-2.07e+00

Pos logit contributions
isine+0.262
opian+0.244
chen+0.240
ulic+0.231
 chefs+0.229
Neg logit contributions
ONES-0.170
Naz-0.166
OSP-0.159
areth-0.155
HTTP-0.145
Token be
Token ID307
Feature activation+2.01e-01

Pos logit contributions
isine+1.774
opian+1.641
chen+1.599
ulic+1.540
 chefs+1.511
Neg logit contributions
ONES-1.600
Naz-1.559
OSP-1.513
areth-1.490
ospels-1.406
Token cheaper
Token ID11721
Feature activation+1.41e+00

Pos logit contributions
ONES+0.159
Naz+0.156
OSP+0.150
areth+0.148
ospels+0.141
Neg logit contributions
isine-0.168
opian-0.154
chen-0.151
ulic-0.145
 chefs-0.142
Token than
Token ID621
Feature activation-5.27e+00

Pos logit contributions
ONES+1.068
Naz+1.051
OSP+1.009
areth+0.998
HTTP+0.936
Neg logit contributions
isine-1.236
opian-1.130
chen-1.109
ulic-1.067
 chefs-1.044
Token raising
Token ID8620
Feature activation+7.70e-01

Pos logit contributions
isine+4.024
chen+3.661
opian+3.638
ulic+3.484
 chefs+3.439
Neg logit contributions
ONES-4.333
Naz-4.263
OSP-4.143
areth-4.124
ospels-3.946
Token its
Token ID663
Feature activation-2.03e-01

Pos logit contributions
ONES+0.608
Naz+0.599
OSP+0.577
areth+0.571
ospels+0.537
Neg logit contributions
isine-0.647
opian-0.589
chen-0.581
ulic-0.557
 chefs-0.544
Token $
Token ID720
Feature activation+5.39e-01

Pos logit contributions
isine+0.177
opian+0.162
chen+0.161
ulic+0.154
 chefs+0.151
Neg logit contributions
ONES-0.153
Naz-0.150
OSP-0.144
areth-0.143
ospels-0.134
Token31
Token ID3132
Feature activation-6.44e-01

Pos logit contributions
ONES+0.344
Naz+0.337
OSP+0.321
areth+0.317
HTTP+0.294
Neg logit contributions
isine-0.536
opian-0.496
chen-0.487
ulic-0.471
 chefs-0.462
Token-
Token ID12
Feature activation-1.16e+00

Pos logit contributions
isine+0.542
chen+0.491
opian+0.491
ulic+0.464
 chefs+0.454
Neg logit contributions
ONES-0.510
Naz-0.500
OSP-0.481
areth-0.473
HTTP-0.448
Token on
Token ID319
Feature activation+2.41e-01

Pos logit contributions
isine+1.529
opian+1.402
chen+1.375
ulic+1.314
 chefs+1.294
Neg logit contributions
ONES-1.558
Naz-1.536
OSP-1.477
areth-1.470
ospels-1.387
Token those
Token ID883
Feature activation-7.26e-01

Pos logit contributions
ONES+0.191
Naz+0.189
OSP+0.181
areth+0.180
ospels+0.169
Neg logit contributions
isine-0.202
opian-0.184
chen-0.181
ulic-0.174
 chefs-0.170
Token who
Token ID508
Feature activation+2.00e+00

Pos logit contributions
isine+0.623
opian+0.570
chen+0.560
ulic+0.539
 chefs+0.530
Neg logit contributions
ONES-0.557
Naz-0.552
OSP-0.528
areth-0.524
HTTP-0.492
Token have
Token ID423
Feature activation-1.41e+00

Pos logit contributions
ONES+1.411
Naz+1.380
OSP+1.323
areth+1.316
HTTP+1.220
Neg logit contributions
isine-1.849
opian-1.694
chen-1.661
ulic-1.607
 chefs-1.565
Token a
Token ID257
Feature activation-3.52e-01

Pos logit contributions
isine+1.159
opian+1.061
chen+1.047
ulic+0.997
 chefs+0.986
Neg logit contributions
ONES-1.131
Naz-1.122
OSP-1.074
areth-1.062
ospels-1.006
Token Lock
Token ID13656
Feature activation-5.22e+00

Pos logit contributions
isine+0.311
opian+0.285
chen+0.281
ulic+0.270
 chefs+0.264
Neg logit contributions
ONES-0.262
Naz-0.258
OSP-0.247
areth-0.245
ospels-0.229
Token out
Token ID503
Feature activation+1.03e+00

Pos logit contributions
isine+4.860
opian+4.559
chen+4.508
ulic+4.296
 chefs+4.233
Neg logit contributions
ONES-3.436
Naz-3.432
OSP-3.229
areth-3.214
HTTP-2.975
Token sol
Token ID1540
Feature activation-2.43e+00

Pos logit contributions
ONES+0.750
Naz+0.736
OSP+0.707
areth+0.699
HTTP+0.653
Neg logit contributions
isine-0.925
opian-0.846
chen-0.831
ulic-0.801
 chefs-0.784
Tokenen
Token ID268
Feature activation-1.23e-01

Pos logit contributions
isine+2.418
opian+2.278
chen+2.229
ulic+2.140
 chefs+2.077
Neg logit contributions
ONES-1.550
Naz-1.512
OSP-1.433
areth-1.403
HTTP-1.305
Tokenoid
Token ID1868
Feature activation+3.13e+00

Pos logit contributions
isine+0.120
opian+0.111
chen+0.110
ulic+0.106
 chefs+0.103
Neg logit contributions
ONES-0.080
Naz-0.079
OSP-0.075
areth-0.073
HTTP-0.069
Token which
Token ID543
Feature activation+1.89e+00

Pos logit contributions
ONES+2.240
Naz+2.174
OSP+2.124
areth+2.079
 wip+1.960
Neg logit contributions
isine-2.873
opian-2.605
chen-2.550
ulic-2.453
 chefs-2.413
Token took
Token ID1718
Feature activation+6.02e-01

Pos logit contributions
ONES+0.380
Naz+0.373
OSP+0.357
areth+0.353
HTTP+0.329
Neg logit contributions
isine-0.514
opian-0.473
chen-0.464
ulic-0.449
 chefs-0.439
Token special
Token ID2041
Feature activation+7.51e-01

Pos logit contributions
ONES+0.463
Naz+0.455
OSP+0.437
areth+0.433
HTTP+0.407
Neg logit contributions
isine-0.519
opian-0.475
chen-0.465
ulic-0.448
 chefs-0.436
Token care
Token ID1337
Feature activation+1.91e+00

Pos logit contributions
ONES+0.490
Naz+0.481
OSP+0.459
areth+0.453
HTTP+0.421
Neg logit contributions
isine-0.734
opian-0.679
chen-0.667
ulic-0.645
 chefs-0.631
Token to
Token ID284
Feature activation+6.67e-02

Pos logit contributions
ONES+1.489
Naz+1.468
OSP+1.409
areth+1.395
HTTP+1.310
Neg logit contributions
isine-1.623
opian-1.476
chen-1.448
ulic-1.393
 chefs-1.359
Token avoid
Token ID3368
Feature activation-7.21e-01

Pos logit contributions
ONES+0.053
Naz+0.052
OSP+0.050
areth+0.049
HTTP+0.047
Neg logit contributions
isine-0.056
opian-0.051
chen-0.050
ulic-0.048
 chefs-0.047
Token contamination
Token ID22733
Feature activation-7.22e+00

Pos logit contributions
isine+0.570
opian+0.516
chen+0.506
ulic+0.484
 chefs+0.473
Neg logit contributions
ONES-0.605
Naz-0.597
OSP-0.576
areth-0.570
ospels-0.538
Token.
Token ID13
Feature activation-2.42e-01

Pos logit contributions
isine+5.494
opian+5.062
chen+4.946
ulic+4.655
 chefs+4.641
Neg logit contributions
Naz-5.860
ONES-5.849
OSP-5.668
areth-5.621
ospels-5.338
Token That
Token ID1320
Feature activation-6.19e-01

Pos logit contributions
isine+0.218
opian+0.200
chen+0.195
ulic+0.188
 chefs+0.184
Neg logit contributions
ONES-0.178
Naz-0.175
OSP-0.168
areth-0.166
HTTP-0.155
Token included
Token ID3017
Feature activation+2.54e+00

Pos logit contributions
isine+0.574
opian+0.527
chen+0.520
ulic+0.500
 chefs+0.494
Neg logit contributions
ONES-0.434
Naz-0.426
OSP-0.408
areth-0.404
ospels-0.377
Token protecting
Token ID10192
Feature activation-3.23e-01

Pos logit contributions
ONES+2.107
Naz+2.067
OSP+1.982
areth+1.967
HTTP+1.867
Neg logit contributions
isine-2.040
opian-1.844
chen-1.799
ulic-1.730
 chefs-1.648
Token the
Token ID262
Feature activation-3.60e-01

Pos logit contributions
isine+0.273
opian+0.249
chen+0.244
ulic+0.235
 chefs+0.229
Neg logit contributions
ONES-0.253
Naz-0.250
OSP-0.240
areth-0.237
HTTP-0.223