TOP ACTIVATIONS
MAX = 2.149

the traits of early modern accounts He ikes finds objectionable are
move on to the other Reno cards , how happy are
Last T empt ation of Christ was protested vigorously . The
, but corrupt . <|endoftext|> Please enable Javascript to watch this
% of respondents to the Lok Survey , with a sample
: 1961 1963 [ edit ] Ren ison
in an attempt to protect Christ ophe ] makes anything possible
which involves charge - density wave fluctuations . These periodic fluctuations
to start developing in AWS Lamb da with server less framework
to lead their friends to Christ and sang an anthem with
to do so ? Charles Buk owski Fortunately it
, could only refer to Christ on the cross and his
in the field of gravitational wave detection . The collaboration that
of Star Wars fandom is warm and embracing , there is
I clot he myself with Christ , with his lifestyle .
ev / R IA Nov ost i / K remlin
contacted the Save Our C em eter ies organization to get
Middle Ages [ edit ] The most
- Ali , the former bishop of Rochester , said proposals
368 <|endoftext|> To all the patient American readers who have been

MIN ACTIVATIONS
MIN = -2.250

messages relating to their troop dispos itions , according to a
their animals roam as they gra ze and for age like
us monkeys ( Mac aca mul atta ) were housed under
of her movie , Train wreck , in a Lafayette ,
them and their own tax dodge at all . We think
apartment complex in the 3000 block of Maryland Street .
pop up of the traveling gra ff ito .
allow citizens the right to gra ze sheep on any golf
to work smarter , not harder . Ind ividually , this
to vote against the GOP tax reform package .
Climate Works ). Har old K . H och
the secondary fal tered , Sherman performed to his ability against
screen . Source : Game FAQ s The focus
agent , also showed an anx io ly tic effect in
. As a matter of fact , we went through 251
lightsaber as the Har lem Shake bl
explain the decision . In fact , Trump s
a benz od iazep ine anx io ly tic agent ,
Every time it sent a cor onal mass eject ion (
are ." In fact , the GW Batt leground

INTERVAL 1.049 - 2.149
CONTAINS 0.779%

to a party . But then we hit the opposite problem
it , straight from the horse 's mouth ! Now ,
a poet old enough to draw Social Security making new contracts
Exec ut ors [ edit ] Several accounts
January 15 , 2010 Subject : Que er magnet

INTERVAL -0.050 - 1.049
CONTAINS 55.996%

In the two separate but related cases , the
and has always been a story - first company . Everything
Except , that is , for Michael Ign at ie ff
completely . Still , we can t help but
", allocated to states on the basis of population ,[ 185

INTERVAL -1.150 - -0.050
CONTAINS 42.895%

a third . Get our daily newsletter Upgrade your
( ARM version , detected as EL F _ UM RE
which the components of the last meal are still in the
ger , even if the subjects featured in the images intended
been doing the bidding of corporate interests , by fighting for

INTERVAL -2.250 - -1.150
CONTAINS 0.330%

are unwelcome in their home countries . US state
the tactics learned in this interview to create our own best
ot is group identifies additional tax a . Australian Journal of
government should also examine offshore tax havens held by wealthier Canadians
include a $ 15 minimum wage . See the
Token the
Token ID262
Feature activation+1.26e-01

Pos logit contributions
orthern+0.739
imir+0.729
etsk+0.721
oline+0.715
oslav+0.708
Neg logit contributions
 dise-0.529
 Indies-0.484
 goof-0.481
 サ-0.478
ドラ-0.473
Token traits
Token ID12796
Feature activation-2.86e-01

Pos logit contributions
orthern+0.349
imir+0.346
etsk+0.341
oline+0.339
oslav+0.335
Neg logit contributions
 dise-0.294
 goof-0.271
 Indies-0.270
 サ-0.266
ドラ-0.265
Token of
Token ID286
Feature activation+4.87e-02

Pos logit contributions
 dise+0.616
 goof+0.550
 Indies+0.548
 Rosenthal+0.540
 サ+0.538
Neg logit contributions
orthern-0.864
imir-0.842
etsk-0.834
oline-0.827
oslav-0.819
Token early
Token ID1903
Feature activation+7.24e-01

Pos logit contributions
orthern+0.153
imir+0.151
etsk+0.150
oline+0.148
oslav+0.147
Neg logit contributions
 dise-0.097
 Indies-0.087
 goof-0.087
 サ-0.086
ドラ-0.085
Token modern
Token ID3660
Feature activation+5.27e-02

Pos logit contributions
orthern+2.040
imir+2.022
etsk+1.993
oline+1.982
oslav+1.956
Neg logit contributions
 dise-1.649
 Indies-1.521
 goof-1.513
ドラ-1.510
 サ-1.502
Token accounts
Token ID5504
Feature activation+2.15e+00

Pos logit contributions
orthern+0.148
imir+0.146
etsk+0.145
oline+0.144
oslav+0.141
Neg logit contributions
 dise-0.121
 goof-0.111
 Indies-0.111
 サ-0.109
ドラ-0.109
Token He
Token ID679
Feature activation+3.08e-01

Pos logit contributions
imir+5.772
orthern+5.719
etsk+5.643
oline+5.639
oslav+5.547
Neg logit contributions
 dise-4.837
ドラ-4.688
 Indies-4.512
 サ-4.490
 goof-4.479
Tokenikes
Token ID7938
Feature activation+5.36e-01

Pos logit contributions
orthern+0.617
etsk+0.604
imir+0.597
oline+0.580
oslav+0.570
Neg logit contributions
 dise-0.948
 Indies-0.894
 goof-0.892
ドラ-0.879
 サ-0.878
Token finds
Token ID7228
Feature activation+6.92e-01

Pos logit contributions
orthern+1.506
imir+1.497
etsk+1.473
oline+1.466
oslav+1.447
Neg logit contributions
 dise-1.218
 Indies-1.125
ドラ-1.119
 goof-1.119
 サ-1.111
Token objectionable
Token ID48540
Feature activation-5.10e-01

Pos logit contributions
orthern+2.071
imir+2.065
etsk+2.033
oline+2.025
oslav+1.997
Neg logit contributions
 dise-1.417
ドラ-1.318
 Indies-1.308
 サ-1.296
 goof-1.294
Token are
Token ID389
Feature activation-4.41e-01

Pos logit contributions
 dise+1.039
 goof+0.948
 Indies+0.941
 サ+0.926
 Barr+0.905
Neg logit contributions
orthern-1.562
imir-1.544
etsk-1.519
oline-1.515
oslav-1.499
Token move
Token ID1445
Feature activation+6.21e-01

Pos logit contributions
 dise+0.505
 goof+0.469
 Indies+0.464
 サ+0.455
ドラ+0.452
Neg logit contributions
orthern-0.783
imir-0.775
etsk-0.770
oline-0.759
oslav-0.751
Token on
Token ID319
Feature activation+1.77e-01

Pos logit contributions
orthern+1.818
imir+1.806
etsk+1.781
oline+1.769
oslav+1.748
Neg logit contributions
 dise-1.338
 Indies-1.231
 goof-1.227
ドラ-1.221
 サ-1.216
Token to
Token ID284
Feature activation-3.30e-01

Pos logit contributions
orthern+0.496
imir+0.493
etsk+0.486
oline+0.483
oslav+0.477
Neg logit contributions
 dise-0.405
 Indies-0.374
 goof-0.373
ドラ-0.372
 サ-0.370
Token the
Token ID262
Feature activation-9.73e-02

Pos logit contributions
 dise+0.683
 goof+0.627
 Indies+0.624
 サ+0.616
ドラ+0.616
Neg logit contributions
orthern-0.999
imir-0.987
etsk-0.985
oline-0.973
oslav-0.962
Token other
Token ID584
Feature activation-2.17e-01

Pos logit contributions
 dise+0.215
 goof+0.198
 Indies+0.196
 サ+0.193
ドラ+0.193
Neg logit contributions
orthern-0.282
imir-0.279
etsk-0.278
oline-0.274
oslav-0.271
Token Reno
Token ID33817
Feature activation+2.09e+00

Pos logit contributions
 dise+0.458
 goof+0.422
 Indies+0.417
 サ+0.412
ドラ+0.411
Neg logit contributions
orthern-0.647
imir-0.639
etsk-0.637
oline-0.629
oslav-0.622
Token cards
Token ID4116
Feature activation+3.08e-01

Pos logit contributions
orthern+5.931
imir+5.930
etsk+5.823
oline+5.797
oslav+5.679
Neg logit contributions
 dise-4.528
ドラ-4.235
 サ-4.193
 Indies-4.171
 goof-4.115
Token,
Token ID11
Feature activation-2.77e-01

Pos logit contributions
orthern+0.843
imir+0.835
etsk+0.824
oline+0.818
oslav+0.810
Neg logit contributions
 dise-0.724
 goof-0.671
 Indies-0.670
ドラ-0.665
 サ-0.664
Token how
Token ID703
Feature activation-3.35e-01

Pos logit contributions
 dise+0.564
 goof+0.523
 Indies+0.521
 サ+0.505
 Barr+0.501
Neg logit contributions
orthern-0.853
imir-0.836
etsk-0.834
oline-0.823
oslav-0.819
Token happy
Token ID3772
Feature activation-5.39e-01

Pos logit contributions
 dise+0.632
 goof+0.573
 Indies+0.572
 サ+0.561
ドラ+0.554
Neg logit contributions
orthern-1.081
imir-1.069
etsk-1.057
oline-1.049
oslav-1.035
Token are
Token ID389
Feature activation-3.42e-01

Pos logit contributions
 dise+0.995
 Indies+0.909
 goof+0.905
ドラ+0.889
 サ+0.888
Neg logit contributions
orthern-1.745
imir-1.728
etsk-1.706
oline-1.697
oslav-1.679
Token Last
Token ID4586
Feature activation-5.57e-01

Pos logit contributions
 dise+0.331
 Indies+0.305
 goof+0.305
 サ+0.297
ドラ+0.294
Neg logit contributions
orthern-0.428
imir-0.425
etsk-0.422
oline-0.415
oslav-0.413
Token T
Token ID309
Feature activation+5.06e-01

Pos logit contributions
 dise+1.222
 Indies+1.191
 サ+1.172
ドラ+1.143
 goof+1.143
Neg logit contributions
orthern-1.581
etsk-1.569
imir-1.566
oline-1.524
oslav-1.509
Tokenempt
Token ID1791
Feature activation+4.77e-01

Pos logit contributions
orthern+1.458
imir+1.456
etsk+1.438
oline+1.422
oslav+1.418
Neg logit contributions
 dise-1.095
 Indies-1.023
 goof-1.004
ドラ-1.002
 サ-0.996
Tokenation
Token ID341
Feature activation+2.19e-01

Pos logit contributions
imir+1.148
orthern+1.146
etsk+1.108
oslav+1.095
oline+1.090
Neg logit contributions
 dise-1.269
 goof-1.200
 Indies-1.198
 サ-1.188
ドラ-1.169
Token of
Token ID286
Feature activation+3.85e-01

Pos logit contributions
orthern+0.632
imir+0.629
etsk+0.620
oline+0.616
oslav+0.610
Neg logit contributions
 dise-0.484
 Indies-0.447
 goof-0.444
ドラ-0.440
 サ-0.438
Token Christ
Token ID1951
Feature activation+2.07e+00

Pos logit contributions
orthern+0.908
imir+0.901
oline+0.882
etsk+0.880
oslav+0.863
Neg logit contributions
 dise-1.049
 Indies-0.992
 goof-0.982
ドラ-0.980
 サ-0.977
Token was
Token ID373
Feature activation+5.69e-01

Pos logit contributions
imir+5.513
orthern+5.510
oline+5.424
etsk+5.334
oslav+5.280
Neg logit contributions
 dise-4.750
ドラ-4.489
 サ-4.436
 Indies-4.390
 goof-4.371
Token protested
Token ID27278
Feature activation+7.09e-02

Pos logit contributions
orthern+1.692
imir+1.678
etsk+1.655
oline+1.646
oslav+1.626
Neg logit contributions
 dise-1.209
 Indies-1.110
 goof-1.105
ドラ-1.100
 サ-1.092
Token vigorously
Token ID31609
Feature activation-7.39e-02

Pos logit contributions
orthern+0.201
imir+0.200
etsk+0.197
oline+0.197
oslav+0.194
Neg logit contributions
 dise-0.159
 Indies-0.147
 goof-0.146
ドラ-0.145
 サ-0.144
Token.
Token ID13
Feature activation+1.07e-01

Pos logit contributions
 dise+0.165
 Indies+0.152
 goof+0.152
 サ+0.149
ドラ+0.149
Neg logit contributions
orthern-0.211
imir-0.211
etsk-0.206
oline-0.206
oslav-0.203
Token The
Token ID383
Feature activation-1.81e-01

Pos logit contributions
orthern+0.308
imir+0.303
etsk+0.301
oline+0.296
oslav+0.295
Neg logit contributions
 dise-0.236
 Indies-0.223
 サ-0.219
ドラ-0.217
 goof-0.217
Token,
Token ID11
Feature activation+6.21e-02

Pos logit contributions
 dise+0.634
 goof+0.591
 Indies+0.583
 サ+0.573
ドラ+0.570
Neg logit contributions
orthern-0.744
imir-0.742
etsk-0.736
oline-0.725
oslav-0.720
Token but
Token ID475
Feature activation-1.47e-01

Pos logit contributions
orthern+0.168
imir+0.166
etsk+0.164
oline+0.163
oslav+0.161
Neg logit contributions
 dise-0.149
 goof-0.138
 Indies-0.138
ドラ-0.136
 サ-0.136
Token corrupt
Token ID10622
Feature activation+1.35e-01

Pos logit contributions
 dise+0.312
 goof+0.285
 Indies+0.284
ドラ+0.281
 サ+0.279
Neg logit contributions
orthern-0.438
imir-0.435
etsk-0.428
oline-0.425
oslav-0.422
Token.
Token ID13
Feature activation+2.09e-01

Pos logit contributions
orthern+0.335
imir+0.334
etsk+0.327
oline+0.325
oslav+0.322
Neg logit contributions
 dise-0.353
 Indies-0.328
 goof-0.328
ドラ-0.325
 サ-0.325
Token<|endoftext|>
Token ID50256
Feature activation+2.07e-01

Pos logit contributions
orthern+0.582
imir+0.573
etsk+0.568
oline+0.560
oslav+0.557
Neg logit contributions
 dise-0.485
 Indies-0.457
 サ-0.449
ドラ-0.449
 goof-0.448
TokenPlease
Token ID5492
Feature activation+2.06e+00

Pos logit contributions
orthern+0.530
imir+0.524
etsk+0.516
oline+0.511
oslav+0.505
Neg logit contributions
 dise-0.518
ドラ-0.485
 Indies-0.485
 goof-0.480
 サ-0.477
Token enable
Token ID7139
Feature activation+3.04e-02

Pos logit contributions
orthern+4.822
imir+4.781
etsk+4.688
oline+4.648
oslav+4.584
Neg logit contributions
 dise-5.556
ドラ-5.242
 Indies-5.191
 goof-5.149
 サ-5.148
Token Javascript
Token ID24711
Feature activation+5.88e-01

Pos logit contributions
orthern+0.072
imir+0.071
etsk+0.070
oline+0.070
oslav+0.069
Neg logit contributions
 dise-0.083
 Indies-0.078
 goof-0.078
ドラ-0.077
 サ-0.077
Token to
Token ID284
Feature activation-6.22e-02

Pos logit contributions
orthern+1.851
etsk+1.818
imir+1.815
oline+1.792
oslav+1.781
Neg logit contributions
 dise-1.162
 Indies-1.059
 goof-1.056
 サ-1.045
ドラ-1.041
Token watch
Token ID2342
Feature activation+3.01e-01

Pos logit contributions
 dise+0.121
 goof+0.113
 Indies+0.111
 サ+0.111
ドラ+0.109
Neg logit contributions
orthern-0.193
etsk-0.191
oline-0.191
imir-0.190
oslav-0.188
Token this
Token ID428
Feature activation-8.34e-02

Pos logit contributions
orthern+0.960
imir+0.946
etsk+0.936
oline+0.927
oslav+0.922
Neg logit contributions
 dise-0.582
 Indies-0.533
 goof-0.526
ドラ-0.512
 サ-0.511
Token%
Token ID4
Feature activation-8.12e-01

Pos logit contributions
orthern+0.873
imir+0.865
etsk+0.850
oline+0.847
oslav+0.836
Neg logit contributions
 dise-0.818
ドラ-0.761
 Indies-0.759
 goof-0.757
 サ-0.755
Token of
Token ID286
Feature activation-6.35e-01

Pos logit contributions
 dise+1.885
ドラ+1.752
 goof+1.740
 Indies+1.735
 サ+1.732
Neg logit contributions
orthern-2.246
imir-2.220
etsk-2.181
oline-2.169
oslav-2.164
Token respondents
Token ID14502
Feature activation-8.65e-01

Pos logit contributions
 dise+1.290
 Indies+1.187
 goof+1.165
 サ+1.143
ドラ+1.125
Neg logit contributions
orthern-1.950
imir-1.940
etsk-1.913
oline-1.908
oslav-1.870
Token to
Token ID284
Feature activation-1.75e-01

Pos logit contributions
 dise+1.864
 goof+1.719
 Indies+1.712
 サ+1.672
ドラ+1.649
Neg logit contributions
orthern-2.530
imir-2.519
etsk-2.497
oline-2.468
oslav-2.435
Token the
Token ID262
Feature activation-2.47e-03

Pos logit contributions
 dise+0.367
 Indies+0.337
 goof+0.334
ドラ+0.333
 サ+0.333
Neg logit contributions
orthern-0.523
imir-0.519
etsk-0.511
oline-0.510
oslav-0.503
Token Lok
Token ID36861
Feature activation+2.06e+00

Pos logit contributions
 dise+0.005
 Indies+0.005
 goof+0.005
 サ+0.005
ドラ+0.005
Neg logit contributions
orthern-0.007
imir-0.007
etsk-0.007
oline-0.007
oslav-0.007
Token Survey
Token ID13084
Feature activation-3.44e-01

Pos logit contributions
orthern+4.234
imir+4.226
etsk+4.120
oline+4.095
oslav+4.031
Neg logit contributions
 dise-6.122
ドラ-5.755
 Indies-5.753
 goof-5.740
 サ-5.712
Token,
Token ID11
Feature activation-2.55e-01

Pos logit contributions
 dise+0.745
 Indies+0.695
 goof+0.691
 サ+0.675
ドラ+0.674
Neg logit contributions
orthern-1.008
imir-0.995
etsk-0.986
oline-0.977
oslav-0.963
Token with
Token ID351
Feature activation+4.09e-01

Pos logit contributions
 dise+0.531
 Indies+0.489
 goof+0.488
 サ+0.481
ドラ+0.477
Neg logit contributions
orthern-0.766
imir-0.763
etsk-0.751
oline-0.750
oslav-0.736
Token a
Token ID257
Feature activation+7.05e-02

Pos logit contributions
orthern+1.243
imir+1.236
etsk+1.218
oline+1.212
oslav+1.197
Neg logit contributions
 dise-0.839
 Indies-0.769
 goof-0.764
ドラ-0.762
 サ-0.757
Token sample
Token ID6291
Feature activation-6.59e-01

Pos logit contributions
orthern+0.199
imir+0.198
etsk+0.196
oline+0.193
oslav+0.191
Neg logit contributions
 dise-0.161
 goof-0.148
 Indies-0.148
 サ-0.146
ドラ-0.145
Token:
Token ID25
Feature activation+3.58e-01

Pos logit contributions
orthern+2.340
imir+2.329
etsk+2.294
oline+2.282
oslav+2.248
Neg logit contributions
 dise-2.177
ドラ-2.019
 goof-2.017
 Indies-2.017
 サ-1.992
Token 1961
Token ID20510
Feature activation+1.53e-01

Pos logit contributions
orthern+1.032
imir+1.026
etsk+1.010
oline+1.005
oslav+0.993
Neg logit contributions
 dise-0.787
 Indies-0.724
ドラ-0.723
 goof-0.721
 サ-0.715
Token
Token ID1906
Feature activation+5.73e-01

Pos logit contributions
orthern+0.411
imir+0.409
etsk+0.403
oline+0.400
oslav+0.394
Neg logit contributions
 dise-0.368
 Indies-0.342
 goof-0.340
 サ-0.339
ドラ-0.338
Token1963
Token ID45192
Feature activation-3.23e-01

Pos logit contributions
orthern+1.666
imir+1.655
etsk+1.631
oline+1.622
oslav+1.602
Neg logit contributions
 dise-1.248
 Indies-1.150
ドラ-1.145
 goof-1.142
 サ-1.135
Token [
Token ID685
Feature activation+7.64e-01

Pos logit contributions
 dise+0.775
 Indies+0.724
 goof+0.715
 サ+0.713
ドラ+0.712
Neg logit contributions
orthern-0.864
imir-0.859
etsk-0.843
oline-0.838
oslav-0.827
Token edit
Token ID4370
Feature activation+2.03e+00

Pos logit contributions
orthern+2.121
imir+2.109
etsk+2.074
oline+2.066
oslav+2.038
Neg logit contributions
 dise-1.755
 Indies-1.623
ドラ-1.617
 goof-1.614
 サ-1.603
Token ]
Token ID2361
Feature activation+1.47e+00

Pos logit contributions
orthern+3.054
imir+3.023
etsk+2.917
oline+2.910
oslav+2.825
Neg logit contributions
 dise-7.221
ドラ-6.857
 Indies-6.854
 goof-6.836
 サ-6.797
Token
Token ID198
Feature activation+4.08e-01

Pos logit contributions
orthern+3.790
imir+3.767
etsk+3.699
oline+3.684
oslav+3.630
Neg logit contributions
 dise-3.670
 Indies-3.414
ドラ-3.404
 goof-3.398
 サ-3.377
Token
Token ID198
Feature activation+5.30e-01

Pos logit contributions
orthern+1.160
imir+1.135
etsk+1.131
oline+1.102
oslav+1.100
Neg logit contributions
 dise-0.927
 Indies-0.875
 goof-0.860
ドラ-0.850
 サ-0.849
TokenRen
Token ID26764
Feature activation+1.07e+00

Pos logit contributions
orthern+1.360
imir+1.349
etsk+1.326
oline+1.317
oslav+1.299
Neg logit contributions
 dise-1.330
 Indies-1.247
ドラ-1.245
 goof-1.230
 サ-1.229
Tokenison
Token ID1653
Feature activation-2.71e-01

Pos logit contributions
orthern+2.175
imir+2.165
etsk+2.109
oline+2.100
oslav+2.068
Neg logit contributions
 dise-3.224
 Indies-3.048
 goof-3.033
ドラ-3.023
 サ-3.010
Token in
Token ID287
Feature activation+1.96e-01

Pos logit contributions
orthern+0.495
imir+0.493
etsk+0.481
oline+0.476
oslav+0.470
Neg logit contributions
 dise-0.812
 Indies-0.770
 goof-0.766
ドラ-0.763
 サ-0.760
Token an
Token ID281
Feature activation+2.17e-01

Pos logit contributions
orthern+0.586
imir+0.585
etsk+0.575
oline+0.570
oslav+0.565
Neg logit contributions
 dise-0.412
 Indies-0.378
 goof-0.376
ドラ-0.371
 サ-0.371
Token attempt
Token ID2230
Feature activation+4.31e-01

Pos logit contributions
orthern+0.618
imir+0.615
etsk+0.606
oline+0.599
oslav+0.593
Neg logit contributions
 dise-0.487
 Indies-0.448
 goof-0.445
ドラ-0.441
 サ-0.439
Token to
Token ID284
Feature activation+7.68e-02

Pos logit contributions
orthern+1.193
imir+1.181
etsk+1.150
oline+1.142
oslav+1.132
Neg logit contributions
 dise-0.993
 Indies-0.927
ドラ-0.913
 サ-0.913
 goof-0.911
Token protect
Token ID1805
Feature activation+3.49e-01

Pos logit contributions
orthern+0.216
imir+0.216
etsk+0.211
oline+0.210
oslav+0.208
Neg logit contributions
 dise-0.176
 goof-0.163
 Indies-0.161
 サ-0.159
ドラ-0.158
Token Christ
Token ID1951
Feature activation+2.02e+00

Pos logit contributions
orthern+1.203
imir+1.198
etsk+1.181
oline+1.177
oslav+1.166
Neg logit contributions
 dise-0.575
 Indies-0.514
ドラ-0.510
 goof-0.509
 サ-0.501
Tokenophe
Token ID43852
Feature activation+3.25e-01

Pos logit contributions
orthern+4.790
imir+4.747
oline+4.669
etsk+4.656
oslav+4.568
Neg logit contributions
 dise-5.421
 Indies-5.077
ドラ-5.064
 サ-5.045
 goof-5.031
Token]
Token ID60
Feature activation+7.88e-02

Pos logit contributions
orthern+0.791
imir+0.785
etsk+0.767
oline+0.763
oslav+0.758
Neg logit contributions
 dise-0.867
 Indies-0.812
 goof-0.809
ドラ-0.804
 サ-0.798
Token makes
Token ID1838
Feature activation+1.47e-02

Pos logit contributions
orthern+0.234
imir+0.232
etsk+0.229
oline+0.228
oslav+0.225
Neg logit contributions
 dise-0.168
 Indies-0.154
 goof-0.154
ドラ-0.152
 サ-0.151
Token anything
Token ID1997
Feature activation+2.77e-01

Pos logit contributions
orthern+0.047
imir+0.047
etsk+0.047
oline+0.046
oslav+0.046
Neg logit contributions
 dise-0.028
 goof-0.025
 Indies-0.025
ドラ-0.025
 サ-0.025
Token possible
Token ID1744
Feature activation+5.29e-01

Pos logit contributions
orthern+0.896
imir+0.889
etsk+0.879
oline+0.876
oslav+0.868
Neg logit contributions
 dise-0.519
 goof-0.467
 Indies-0.463
 サ-0.458
ドラ-0.458
Token which
Token ID543
Feature activation+2.12e-01

Pos logit contributions
orthern+1.174
imir+1.166
etsk+1.151
oline+1.146
oslav+1.134
Neg logit contributions
 dise-0.774
 Indies-0.703
 goof-0.701
ドラ-0.698
 サ-0.693
Token involves
Token ID9018
Feature activation+4.90e-01

Pos logit contributions
orthern+0.605
imir+0.600
etsk+0.591
oline+0.588
oslav+0.582
Neg logit contributions
 dise-0.474
 Indies-0.436
 goof-0.435
ドラ-0.433
 サ-0.430
Token charge
Token ID3877
Feature activation+4.30e-01

Pos logit contributions
orthern+1.428
imir+1.418
etsk+1.398
oline+1.390
oslav+1.375
Neg logit contributions
 dise-1.068
 Indies-0.979
 goof-0.976
ドラ-0.974
 サ-0.967
Token-
Token ID12
Feature activation+3.44e-01

Pos logit contributions
orthern+1.173
imir+1.149
etsk+1.139
oslav+1.121
oline+1.119
Neg logit contributions
 dise-1.044
 goof-0.960
 Indies-0.947
 サ-0.944
ドラ-0.942
Tokendensity
Token ID43337
Feature activation+7.40e-01

Pos logit contributions
orthern+0.868
imir+0.851
etsk+0.846
oline+0.831
oslav+0.827
Neg logit contributions
 dise-0.893
 goof-0.826
 Indies-0.823
ドラ-0.821
 サ-0.819
Token wave
Token ID6769
Feature activation+2.01e+00

Pos logit contributions
orthern+2.083
imir+2.067
etsk+2.035
oline+2.024
oslav+2.001
Neg logit contributions
 dise-1.686
 Indies-1.551
 goof-1.547
ドラ-1.543
 サ-1.534
Token fluctuations
Token ID31101
Feature activation+4.37e-01

Pos logit contributions
imir+5.415
orthern+5.363
oline+5.327
etsk+5.307
oslav+5.205
Neg logit contributions
 dise-4.555
ドラ-4.351
 Indies-4.333
 サ-4.273
 goof-4.255
Token.
Token ID13
Feature activation-9.53e-02

Pos logit contributions
orthern+1.145
imir+1.135
etsk+1.117
oline+1.107
oslav+1.097
Neg logit contributions
 dise-1.083
 Indies-1.002
 goof-1.002
ドラ-0.992
 サ-0.988
Token These
Token ID2312
Feature activation+7.06e-02

Pos logit contributions
 dise+0.229
 Indies+0.213
ドラ+0.212
 サ+0.211
 goof+0.211
Neg logit contributions
orthern-0.256
imir-0.253
etsk-0.250
oline-0.247
oslav-0.245
Token periodic
Token ID27458
Feature activation-4.61e-01

Pos logit contributions
orthern+0.203
imir+0.201
etsk+0.199
oline+0.198
oslav+0.196
Neg logit contributions
 dise-0.158
 goof-0.144
 Indies-0.143
ドラ-0.143
 サ-0.141
Token fluctuations
Token ID31101
Feature activation+3.28e-01

Pos logit contributions
 dise+1.031
 goof+0.943
 Indies+0.920
ドラ+0.915
 サ+0.908
Neg logit contributions
orthern-1.338
imir-1.326
etsk-1.308
oslav-1.292
oline-1.290
Token to
Token ID284
Feature activation-3.38e-02

Pos logit contributions
imir+0.983
orthern+0.981
oline+0.958
etsk+0.947
oslav+0.928
Neg logit contributions
 dise-0.859
 Indies-0.790
ドラ-0.786
 goof-0.776
 サ-0.775
Token start
Token ID923
Feature activation-3.75e-01

Pos logit contributions
 dise+0.074
 goof+0.069
 Indies+0.069
ドラ+0.068
 サ+0.067
Neg logit contributions
orthern-0.098
imir-0.097
etsk-0.096
oline-0.095
oslav-0.094
Token developing
Token ID5922
Feature activation+3.24e-01

Pos logit contributions
 dise+0.738
 Indies+0.688
 goof+0.687
ドラ+0.675
 サ+0.666
Neg logit contributions
orthern-1.169
imir-1.152
etsk-1.142
oline-1.130
oslav-1.121
Token in
Token ID287
Feature activation+2.54e-02

Pos logit contributions
orthern+0.943
imir+0.933
etsk+0.922
oline+0.916
oslav+0.904
Neg logit contributions
 dise-0.712
 Indies-0.661
 goof-0.656
 サ-0.650
ドラ-0.649
Token AWS
Token ID30865
Feature activation+9.03e-01

Pos logit contributions
orthern+0.070
imir+0.070
etsk+0.069
oline+0.068
oslav+0.067
Neg logit contributions
 dise-0.059
 Indies-0.055
 goof-0.055
ドラ-0.054
 サ-0.054
Token Lamb
Token ID21114
Feature activation+2.01e+00

Pos logit contributions
orthern+2.356
imir+2.338
etsk+2.301
oline+2.285
oslav+2.254
Neg logit contributions
 dise-2.240
 Indies-2.093
 goof-2.076
ドラ-2.074
 サ-2.060
Tokenda
Token ID6814
Feature activation+5.44e-01

Pos logit contributions
orthern+3.211
imir+3.156
etsk+3.101
oline+2.995
oslav+2.991
Neg logit contributions
 dise-7.083
 Indies-6.716
 goof-6.707
ドラ-6.651
 サ-6.587
Token with
Token ID351
Feature activation+2.70e-01

Pos logit contributions
orthern+1.404
imir+1.387
etsk+1.373
oline+1.354
oslav+1.338
Neg logit contributions
 dise-1.375
 Indies-1.287
 goof-1.276
ドラ-1.272
 サ-1.265
Token server
Token ID4382
Feature activation+3.59e-01

Pos logit contributions
orthern+0.750
imir+0.745
etsk+0.734
oline+0.728
oslav+0.720
Neg logit contributions
 dise-0.624
 Indies-0.581
 goof-0.578
ドラ-0.575
 サ-0.573
Tokenless
Token ID1203
Feature activation-1.40e-01

Pos logit contributions
orthern+0.810
imir+0.801
etsk+0.791
oslav+0.779
oline+0.775
Neg logit contributions
 dise-1.015
 goof-0.954
 Indies-0.954
ドラ-0.937
 サ-0.929
Token framework
Token ID9355
Feature activation+1.09e-02

Pos logit contributions
 dise+0.343
 goof+0.322
 Indies+0.322
ドラ+0.316
 サ+0.315
Neg logit contributions
orthern-0.369
imir-0.364
etsk-0.360
oline-0.356
oslav-0.353
Token to
Token ID284
Feature activation+3.76e-02

Pos logit contributions
 dise+1.440
 goof+1.327
 Indies+1.322
ドラ+1.302
 サ+1.301
Neg logit contributions
orthern-1.985
imir-1.962
etsk-1.950
oline-1.933
oslav-1.911
Token lead
Token ID1085
Feature activation-1.69e-01

Pos logit contributions
orthern+0.109
imir+0.108
etsk+0.106
oline+0.106
oslav+0.104
Neg logit contributions
 dise-0.083
 Indies-0.076
 goof-0.076
ドラ-0.075
 サ-0.075
Token their
Token ID511
Feature activation-3.52e-01

Pos logit contributions
 dise+0.360
 Indies+0.331
 goof+0.330
ドラ+0.327
 サ+0.326
Neg logit contributions
orthern-0.500
imir-0.497
etsk-0.490
oline-0.487
oslav-0.482
Token friends
Token ID2460
Feature activation-4.99e-01

Pos logit contributions
 dise+0.756
 goof+0.695
 Indies+0.692
 サ+0.680
ドラ+0.674
Neg logit contributions
orthern-1.037
imir-1.031
etsk-1.021
oline-1.012
oslav-1.000
Token to
Token ID284
Feature activation-1.04e-01

Pos logit contributions
 dise+1.084
 goof+1.006
 Indies+1.006
 サ+0.991
ドラ+0.984
Neg logit contributions
orthern-1.443
imir-1.433
etsk-1.419
oline-1.410
oslav-1.386
Token Christ
Token ID1951
Feature activation+1.98e+00

Pos logit contributions
 dise+0.232
 Indies+0.214
 goof+0.213
 サ+0.211
ドラ+0.211
Neg logit contributions
orthern-0.298
imir-0.297
etsk-0.292
oline-0.289
oslav-0.287
Token and
Token ID290
Feature activation-7.45e-04

Pos logit contributions
orthern+5.008
imir+4.964
oline+4.928
etsk+4.849
oslav+4.786
Neg logit contributions
 dise-4.920
ドラ-4.622
 Indies-4.553
 サ-4.551
 goof-4.520
Token sang
Token ID25889
Feature activation+4.39e-02

Pos logit contributions
 dise+0.002
 Indies+0.001
 goof+0.001
ドラ+0.001
 サ+0.001
Neg logit contributions
orthern-0.002
imir-0.002
etsk-0.002
oline-0.002
oslav-0.002
Token an
Token ID281
Feature activation+1.29e-01

Pos logit contributions
orthern+0.130
imir+0.129
etsk+0.127
oline+0.126
oslav+0.125
Neg logit contributions
 dise-0.094
 goof-0.086
 Indies-0.086
 サ-0.085
ドラ-0.085
Token anthem
Token ID24577
Feature activation-1.83e-01

Pos logit contributions
orthern+0.375
imir+0.373
etsk+0.367
oline+0.365
oslav+0.361
Neg logit contributions
 dise-0.282
 Indies-0.259
 goof-0.258
ドラ-0.258
 サ-0.256
Token with
Token ID351
Feature activation+4.28e-01

Pos logit contributions
 dise+0.403
 goof+0.371
 Indies+0.369
 サ+0.365
ドラ+0.363
Neg logit contributions
orthern-0.531
imir-0.529
etsk-0.522
oline-0.518
oslav-0.511
Token to
Token ID284
Feature activation-2.68e-01

Pos logit contributions
orthern+0.054
imir+0.053
etsk+0.053
oline+0.052
oslav+0.052
Neg logit contributions
 dise-0.041
 goof-0.038
 Indies-0.038
ドラ-0.038
 サ-0.038
Token do
Token ID466
Feature activation+3.15e-01

Pos logit contributions
 dise+0.544
 goof+0.509
 Indies+0.496
 サ+0.493
ドラ+0.483
Neg logit contributions
orthern-0.819
imir-0.811
etsk-0.803
oline-0.797
oslav-0.793
Token so
Token ID523
Feature activation-6.58e-02

Pos logit contributions
orthern+0.930
imir+0.923
etsk+0.912
oline+0.905
oslav+0.894
Neg logit contributions
 dise-0.674
 Indies-0.619
 goof-0.618
ドラ-0.615
 サ-0.612
Token?
Token ID30
Feature activation-2.02e-01

Pos logit contributions
 dise+0.149
 Indies+0.138
 goof+0.138
 サ+0.137
ドラ+0.136
Neg logit contributions
orthern-0.185
imir-0.184
etsk-0.182
oline-0.180
oslav-0.179
Token Charles
Token ID7516
Feature activation-3.69e-01

Pos logit contributions
 dise+0.470
 Indies+0.443
 サ+0.439
 goof+0.435
ドラ+0.434
Neg logit contributions
orthern-0.559
imir-0.548
etsk-0.547
oline-0.535
oslav-0.533
Token Buk
Token ID36810
Feature activation+1.96e+00

Pos logit contributions
 dise+0.734
 goof+0.684
 Indies+0.675
 サ+0.669
 Barr+0.662
Neg logit contributions
orthern-1.145
imir-1.126
etsk-1.124
oline-1.098
oslav-1.097
Tokenowski
Token ID12079
Feature activation+5.91e-01

Pos logit contributions
imir+3.222
orthern+3.160
oline+3.086
etsk+3.047
oslav+2.947
Neg logit contributions
 dise-6.678
ドラ-6.386
 Indies-6.347
 サ-6.311
 goof-6.301
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
orthern+1.634
imir+1.620
etsk+1.598
oline+1.588
oslav+1.568
Neg logit contributions
 dise-1.374
 Indies-1.270
 goof-1.267
ドラ-1.264
 サ-1.257
Token
Token ID198
Feature activation+2.61e-01

Pos logit contributions
orthern+0.441
etsk+0.430
imir+0.429
oline+0.418
VIDIA+0.418
Neg logit contributions
 dise-0.343
 Indies-0.325
 goof-0.319
ドラ-0.314
 サ-0.314
TokenFortunately
Token ID31276
Feature activation+4.44e-01

Pos logit contributions
orthern+0.675
imir+0.664
etsk+0.659
oline+0.649
oslav+0.643
Neg logit contributions
 dise-0.651
ドラ-0.611
 Indies-0.610
 goof-0.604
 サ-0.602
Token it
Token ID340
Feature activation-2.05e-01

Pos logit contributions
orthern+1.169
imir+1.161
etsk+1.141
oline+1.136
oslav+1.120
Neg logit contributions
 dise-1.084
 Indies-1.007
ドラ-1.004
 goof-1.002
 サ-0.996
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
orthern+2.025
imir+2.016
etsk+1.985
oline+1.973
oslav+1.948
Neg logit contributions
 dise-1.747
 Indies-1.621
 goof-1.607
ドラ-1.603
 サ-1.592
Token could
Token ID714
Feature activation+3.83e-01

Pos logit contributions
orthern+0.674
imir+0.668
etsk+0.662
oline+0.657
oslav+0.647
Neg logit contributions
 dise-0.504
 Indies-0.460
 goof-0.459
 サ-0.452
ドラ-0.452
Token only
Token ID691
Feature activation+3.23e-01

Pos logit contributions
orthern+1.096
imir+1.089
etsk+1.081
oline+1.072
oslav+1.060
Neg logit contributions
 dise-0.852
 goof-0.784
 Indies-0.780
 サ-0.770
ドラ-0.765
Token refer
Token ID3522
Feature activation+4.00e-01

Pos logit contributions
orthern+0.901
imir+0.894
etsk+0.889
oline+0.880
oslav+0.866
Neg logit contributions
 dise-0.747
 goof-0.691
 Indies-0.683
 サ-0.671
ドラ-0.667
Token to
Token ID284
Feature activation+4.86e-01

Pos logit contributions
orthern+1.097
imir+1.088
oline+1.069
oslav+1.054
etsk+1.051
Neg logit contributions
 dise-0.908
 Indies-0.859
ドラ-0.859
 goof-0.849
 PARK-0.841
Token Christ
Token ID1951
Feature activation+1.94e+00

Pos logit contributions
orthern+1.436
imir+1.428
etsk+1.411
oline+1.401
oslav+1.384
Neg logit contributions
 dise-1.039
 Indies-0.952
 goof-0.945
ドラ-0.942
 サ-0.937
Token on
Token ID319
Feature activation+7.87e-01

Pos logit contributions
orthern+5.310
imir+5.287
oline+5.189
etsk+5.179
oslav+5.105
Neg logit contributions
 dise-4.472
ドラ-4.158
 Indies-4.129
 サ-4.113
 goof-4.110
Token the
Token ID262
Feature activation+2.43e-01

Pos logit contributions
orthern+2.291
imir+2.278
etsk+2.242
oline+2.233
oslav+2.205
Neg logit contributions
 dise-1.704
 Indies-1.568
ドラ-1.563
 goof-1.559
 サ-1.549
Token cross
Token ID3272
Feature activation+5.51e-01

Pos logit contributions
orthern+0.767
imir+0.764
etsk+0.753
oline+0.748
oslav+0.740
Neg logit contributions
 dise-0.472
 Indies-0.431
 goof-0.426
ドラ-0.423
 サ-0.420
Token and
Token ID290
Feature activation+4.84e-01

Pos logit contributions
orthern+1.426
imir+1.418
etsk+1.395
oline+1.380
oslav+1.367
Neg logit contributions
 dise-1.383
 Indies-1.289
 goof-1.280
 サ-1.272
ドラ-1.272
Token his
Token ID465
Feature activation+1.60e-01

Pos logit contributions
orthern+1.415
imir+1.403
etsk+1.393
oline+1.378
oslav+1.363
Neg logit contributions
 dise-1.054
 Indies-0.967
 goof-0.962
ドラ-0.955
 サ-0.953
Token in
Token ID287
Feature activation+1.13e-01

Pos logit contributions
 dise+0.754
 goof+0.698
 Indies+0.696
 サ+0.690
ドラ+0.684
Neg logit contributions
orthern-0.909
imir-0.904
etsk-0.884
oline-0.883
oslav-0.871
Token the
Token ID262
Feature activation+6.04e-03

Pos logit contributions
orthern+0.340
imir+0.339
etsk+0.333
oline+0.332
oslav+0.328
Neg logit contributions
 dise-0.234
 Indies-0.214
 goof-0.213
ドラ-0.211
 サ-0.211
Token field
Token ID2214
Feature activation-1.40e-01

Pos logit contributions
orthern+0.018
imir+0.018
etsk+0.017
oline+0.017
oslav+0.017
Neg logit contributions
 dise-0.013
 Indies-0.012
 goof-0.012
 サ-0.012
ドラ-0.012
Token of
Token ID286
Feature activation-2.89e-01

Pos logit contributions
 dise+0.333
ドラ+0.313
 Indies+0.309
 goof+0.306
 サ+0.304
Neg logit contributions
orthern-0.376
imir-0.370
etsk-0.365
oline-0.363
oslav-0.361
Token gravitational
Token ID29973
Feature activation-1.13e-01

Pos logit contributions
 dise+0.629
 goof+0.573
 Indies+0.568
 サ+0.563
ドラ+0.556
Neg logit contributions
orthern-0.851
imir-0.841
etsk-0.831
oline-0.831
oslav-0.820
Token wave
Token ID6769
Feature activation+1.94e+00

Pos logit contributions
 dise+0.267
 goof+0.244
 Indies+0.240
 サ+0.238
ドラ+0.236
Neg logit contributions
orthern-0.313
imir-0.308
etsk-0.305
oline-0.304
oslav-0.300
Token detection
Token ID13326
Feature activation+3.70e-01

Pos logit contributions
imir+5.556
orthern+5.548
etsk+5.471
oline+5.432
oslav+5.339
Neg logit contributions
 dise-4.090
ドラ-3.907
 Indies-3.875
 サ-3.825
 goof-3.805
Token.
Token ID13
Feature activation+1.75e-01

Pos logit contributions
orthern+0.966
imir+0.958
etsk+0.941
oline+0.937
oslav+0.925
Neg logit contributions
 dise-0.914
 Indies-0.850
 goof-0.846
ドラ-0.845
 サ-0.840
Token The
Token ID383
Feature activation-1.87e-01

Pos logit contributions
orthern+0.495
imir+0.487
etsk+0.482
oline+0.477
oslav+0.473
Neg logit contributions
 dise-0.395
 Indies-0.370
ドラ-0.366
 サ-0.366
 goof-0.364
Token collaboration
Token ID12438
Feature activation-1.45e-01

Pos logit contributions
 dise+0.403
 goof+0.371
 Indies+0.369
 サ+0.362
ドラ+0.359
Neg logit contributions
orthern-0.553
imir-0.547
etsk-0.537
oline-0.536
oslav-0.532
Token that
Token ID326
Feature activation+4.55e-02

Pos logit contributions
 dise+0.321
 goof+0.295
 Indies+0.293
 サ+0.290
ドラ+0.290
Neg logit contributions
orthern-0.418
imir-0.413
oline-0.406
etsk-0.406
oslav-0.402
Token of
Token ID286
Feature activation+2.77e-01

Pos logit contributions
orthern+1.084
imir+1.079
etsk+1.064
oline+1.056
oslav+1.044
Neg logit contributions
 dise-0.703
 Indies-0.644
 goof-0.641
ドラ-0.635
 サ-0.629
Token Star
Token ID2907
Feature activation-4.87e-02

Pos logit contributions
orthern+0.832
imir+0.827
etsk+0.816
oline+0.811
oslav+0.802
Neg logit contributions
 dise-0.573
 Indies-0.528
 goof-0.524
ドラ-0.522
 サ-0.519
Token Wars
Token ID6176
Feature activation+9.29e-01

Pos logit contributions
 dise+0.120
 Indies+0.115
 goof+0.114
 PARK+0.111
 Barr+0.111
Neg logit contributions
orthern-0.129
imir-0.125
etsk-0.125
oline-0.122
oslav-0.119
Token fandom
Token ID35387
Feature activation+8.52e-01

Pos logit contributions
orthern+2.881
imir+2.875
etsk+2.823
oline+2.820
oslav+2.781
Neg logit contributions
 dise-1.822
ドラ-1.665
 Indies-1.656
 サ-1.648
 goof-1.641
Token is
Token ID318
Feature activation+2.56e-01

Pos logit contributions
orthern+2.350
imir+2.341
etsk+2.299
oline+2.296
oslav+2.260
Neg logit contributions
 dise-1.944
ドラ-1.824
 Indies-1.802
 サ-1.794
 goof-1.775
Token warm
Token ID5814
Feature activation+1.92e+00

Pos logit contributions
orthern+0.773
imir+0.766
etsk+0.757
oline+0.750
oslav+0.742
Neg logit contributions
 dise-0.536
 goof-0.490
 Indies-0.488
 サ-0.478
ドラ-0.475
Token and
Token ID290
Feature activation+4.56e-01

Pos logit contributions
orthern+4.882
imir+4.882
oline+4.786
etsk+4.727
oslav+4.697
Neg logit contributions
 dise-4.738
ドラ-4.498
 Indies-4.419
 サ-4.409
 goof-4.331
Token embracing
Token ID26005
Feature activation-1.28e-01

Pos logit contributions
orthern+1.501
imir+1.494
etsk+1.474
oline+1.469
oslav+1.452
Neg logit contributions
 dise-0.814
 Indies-0.735
 goof-0.733
ドラ-0.726
 サ-0.722
Token,
Token ID11
Feature activation+3.54e-01

Pos logit contributions
 dise+0.273
 goof+0.252
 Indies+0.251
 サ+0.244
ドラ+0.244
Neg logit contributions
orthern-0.378
imir-0.376
etsk-0.371
oline-0.368
oslav-0.363
Token there
Token ID612
Feature activation+1.77e-01

Pos logit contributions
orthern+1.094
imir+1.086
etsk+1.072
oline+1.064
oslav+1.053
Neg logit contributions
 dise-0.713
 Indies-0.654
 goof-0.651
ドラ-0.640
 サ-0.639
Token is
Token ID318
Feature activation+7.84e-01

Pos logit contributions
orthern+0.507
imir+0.505
etsk+0.496
oline+0.495
oslav+0.488
Neg logit contributions
 dise-0.389
ドラ-0.359
 Indies-0.359
 goof-0.356
 サ-0.355
Token I
Token ID314
Feature activation-2.65e-01

Pos logit contributions
 dise+0.225
 Indies+0.207
 goof+0.207
 サ+0.207
ドラ+0.206
Neg logit contributions
orthern-0.264
imir-0.263
etsk-0.260
oline-0.258
oslav-0.257
Token clot
Token ID5148
Feature activation+1.25e+00

Pos logit contributions
 dise+0.603
 goof+0.558
 サ+0.550
 Indies+0.549
ドラ+0.546
Neg logit contributions
orthern-0.749
imir-0.744
etsk-0.736
oline-0.733
oslav-0.727
Tokenhe
Token ID258
Feature activation+2.08e-01

Pos logit contributions
orthern+2.880
imir+2.863
etsk+2.802
oline+2.786
oslav+2.741
Neg logit contributions
 dise-3.470
 Indies-3.267
ドラ-3.245
 goof-3.241
 サ-3.234
Token myself
Token ID3589
Feature activation+1.41e-01

Pos logit contributions
orthern+0.735
imir+0.732
etsk+0.726
oline+0.722
oslav+0.716
Neg logit contributions
 dise-0.326
 Indies-0.288
 goof-0.286
 サ-0.284
ドラ-0.283
Token with
Token ID351
Feature activation+4.28e-01

Pos logit contributions
orthern+0.416
imir+0.413
etsk+0.409
oline+0.407
oslav+0.402
Neg logit contributions
 dise-0.302
 Indies-0.276
 goof-0.275
 サ-0.274
ドラ-0.273
Token Christ
Token ID1951
Feature activation+1.91e+00

Pos logit contributions
orthern+1.254
imir+1.245
etsk+1.229
oline+1.221
oslav+1.208
Neg logit contributions
 dise-0.926
 Indies-0.850
 goof-0.845
ドラ-0.840
 サ-0.839
Token,
Token ID11
Feature activation+2.52e-01

Pos logit contributions
orthern+4.824
imir+4.795
oline+4.713
etsk+4.675
oslav+4.598
Neg logit contributions
 dise-4.798
ドラ-4.510
 Indies-4.475
 goof-4.445
 サ-4.427
Token with
Token ID351
Feature activation+7.26e-01

Pos logit contributions
orthern+0.661
imir+0.657
etsk+0.648
oline+0.643
oslav+0.637
Neg logit contributions
 dise-0.622
 Indies-0.575
 goof-0.573
 サ-0.571
ドラ-0.570
Token his
Token ID465
Feature activation+1.40e-02

Pos logit contributions
orthern+2.095
imir+2.081
etsk+2.051
oline+2.039
oslav+2.016
Neg logit contributions
 dise-1.599
 Indies-1.471
 goof-1.462
ドラ-1.459
 サ-1.452
Token lifestyle
Token ID12263
Feature activation-7.99e-01

Pos logit contributions
orthern+0.040
imir+0.040
etsk+0.039
oline+0.038
oslav+0.038
Neg logit contributions
 dise-0.032
 Indies-0.029
 goof-0.029
 サ-0.029
ドラ-0.028
Token.
Token ID13
Feature activation+1.35e-01

Pos logit contributions
 dise+1.888
 goof+1.751
 サ+1.733
 Indies+1.730
ドラ+1.701
Neg logit contributions
orthern-2.152
imir-2.149
etsk-2.143
oline-2.100
oslav-2.082
Tokenev
Token ID1990
Feature activation-9.16e-02

Pos logit contributions
 dise+2.370
 goof+2.235
 Indies+2.190
 Rosenthal+2.181
 PARK+2.163
Neg logit contributions
orthern-1.503
oline-1.377
VIDIA-1.366
etsk-1.354
imir-1.331
Token/
Token ID14
Feature activation-2.93e-02

Pos logit contributions
 dise+0.239
ドラ+0.225
 Indies+0.223
 goof+0.222
 サ+0.221
Neg logit contributions
imir-0.229
orthern-0.225
etsk-0.222
oline-0.222
oslav-0.218
TokenR
Token ID49
Feature activation-7.69e-01

Pos logit contributions
 dise+0.055
ドラ+0.050
 Indies+0.050
 goof+0.050
 サ+0.049
Neg logit contributions
orthern-0.094
imir-0.091
etsk-0.091
oline-0.091
oslav-0.089
TokenIA
Token ID3539
Feature activation-7.44e-02

Pos logit contributions
 dise+1.271
 goof+1.159
 Indies+1.131
ドラ+1.105
 PARK+1.090
Neg logit contributions
orthern-2.622
etsk-2.583
imir-2.544
oline-2.501
 Dragonbound-2.453
Token Nov
Token ID5267
Feature activation-4.31e-01

Pos logit contributions
 dise+0.164
 goof+0.151
 Indies+0.149
ドラ+0.147
 PARK+0.146
Neg logit contributions
orthern-0.215
imir-0.211
etsk-0.210
oline-0.209
oslav-0.204
Tokenost
Token ID455
Feature activation+1.90e+00

Pos logit contributions
 dise+1.447
 goof+1.361
 Indies+1.347
 Rosenthal+1.347
 Barr+1.344
Neg logit contributions
orthern-0.754
etsk-0.684
imir-0.673
ewater-0.661
VIDIA-0.656
Tokeni
Token ID72
Feature activation+3.54e-01

Pos logit contributions
orthern+5.670
imir+5.665
etsk+5.591
oline+5.557
oslav+5.491
Neg logit contributions
 dise-3.948
 Indies-3.633
ドラ-3.623
 サ-3.604
 goof-3.593
Token/
Token ID14
Feature activation-1.47e-02

Pos logit contributions
imir+0.891
orthern+0.884
etsk+0.873
oline+0.864
oslav+0.856
Neg logit contributions
 dise-0.907
ドラ-0.854
 サ-0.847
 Indies-0.845
 goof-0.841
TokenK
Token ID42
Feature activation-3.82e-01

Pos logit contributions
 dise+0.031
ドラ+0.029
 goof+0.029
 Indies+0.029
 サ+0.028
Neg logit contributions
orthern-0.044
imir-0.042
oline-0.042
etsk-0.042
oslav-0.041
Tokenremlin
Token ID17244
Feature activation-2.09e-01

Pos logit contributions
 dise+1.041
 goof+0.980
 Indies+0.970
 Barr+0.961
 Rosenthal+0.954
Neg logit contributions
orthern-0.888
etsk-0.862
imir-0.846
oline-0.828
ewater-0.804
Token
Token ID198
Feature activation+3.55e-02

Pos logit contributions
 dise+0.535
 サ+0.503
ドラ+0.502
 Indies+0.502
 goof+0.497
Neg logit contributions
imir-0.529
orthern-0.525
etsk-0.516
oline-0.515
oslav-0.504
Token contacted
Token ID11237
Feature activation+4.56e-01

Pos logit contributions
 dise+0.078
 goof+0.072
 Indies+0.071
 サ+0.070
 PARK+0.069
Neg logit contributions
orthern-0.113
imir-0.112
etsk-0.111
oline-0.109
oslav-0.108
Token the
Token ID262
Feature activation+1.76e-02

Pos logit contributions
orthern+1.331
imir+1.323
etsk+1.303
oline+1.297
oslav+1.281
Neg logit contributions
 dise-0.987
 Indies-0.907
 goof-0.903
ドラ-0.896
 サ-0.893
Token Save
Token ID12793
Feature activation+3.93e-01

Pos logit contributions
orthern+0.049
imir+0.049
etsk+0.048
oline+0.047
oslav+0.047
Neg logit contributions
 dise-0.041
 Indies-0.038
 goof-0.038
 PARK-0.037
 Barr-0.037
Token Our
Token ID3954
Feature activation-4.49e-01

Pos logit contributions
orthern+1.140
imir+1.135
etsk+1.115
oline+1.107
oslav+1.101
Neg logit contributions
 dise-0.860
 Indies-0.792
 goof-0.783
ドラ-0.781
 サ-0.774
Token C
Token ID327
Feature activation-2.97e-02

Pos logit contributions
 dise+0.915
 Indies+0.849
 goof+0.824
 Barr+0.819
 サ+0.818
Neg logit contributions
orthern-1.371
imir-1.357
etsk-1.337
oline-1.320
oslav-1.319
Tokenem
Token ID368
Feature activation+1.89e+00

Pos logit contributions
 dise+0.085
 Indies+0.080
 goof+0.079
ドラ+0.079
 サ+0.078
Neg logit contributions
orthern-0.065
imir-0.064
etsk-0.063
oslav-0.062
oline-0.062
Tokeneter
Token ID2357
Feature activation+3.20e-01

Pos logit contributions
orthern+1.685
imir+1.652
oline+1.626
etsk+1.611
oslav+1.468
Neg logit contributions
 dise-7.828
ドラ-7.539
 サ-7.504
 Indies-7.498
 goof-7.483
Tokenies
Token ID444
Feature activation-4.86e-03

Pos logit contributions
orthern+0.878
imir+0.870
etsk+0.858
oline+0.856
oslav+0.843
Neg logit contributions
 dise-0.748
ドラ-0.693
 Indies-0.689
 goof-0.687
 サ-0.684
Token organization
Token ID4009
Feature activation-3.54e-01

Pos logit contributions
 dise+0.011
 Indies+0.010
 goof+0.010
 サ+0.010
 PARK+0.010
Neg logit contributions
orthern-0.014
imir-0.013
etsk-0.013
oslav-0.013
oline-0.013
Token to
Token ID284
Feature activation-8.47e-02

Pos logit contributions
 dise+0.782
 goof+0.726
 Indies+0.721
 PARK+0.706
 サ+0.705
Neg logit contributions
imir-1.021
orthern-1.020
etsk-1.001
oline-0.987
oslav-0.983
Token get
Token ID651
Feature activation-2.09e-01

Pos logit contributions
 dise+0.182
 goof+0.170
 Indies+0.167
 サ+0.165
 PARK+0.162
Neg logit contributions
orthern-0.252
imir-0.250
etsk-0.246
oline-0.243
oslav-0.242
Token
Token ID198
Feature activation-5.57e-01

Pos logit contributions
 dise+0.255
 Indies+0.243
 サ+0.240
 Barr+0.236
ドラ+0.235
Neg logit contributions
orthern-0.323
imir-0.316
etsk-0.315
oline-0.309
oslav-0.307
Token
Token ID198
Feature activation-3.20e-01

Pos logit contributions
 dise+1.139
 Indies+1.091
 goof+1.059
 Barr+1.039
 サ+1.038
Neg logit contributions
orthern-1.701
VIDIA-1.661
etsk-1.655
imir-1.637
 tremend-1.632
TokenMiddle
Token ID34621
Feature activation-4.25e-01

Pos logit contributions
 dise+0.782
ドラ+0.749
 Indies+0.743
 サ+0.731
 goof+0.722
Neg logit contributions
orthern-0.825
imir-0.805
etsk-0.803
oline-0.787
oslav-0.782
Token Ages
Token ID21449
Feature activation-4.69e-01

Pos logit contributions
 dise+0.973
 Indies+0.911
 goof+0.899
 サ+0.889
ドラ+0.884
Neg logit contributions
etsk-1.163
orthern-1.163
imir-1.156
oline-1.129
oslav-1.123
Token [
Token ID685
Feature activation+6.32e-01

Pos logit contributions
 dise+1.089
 Indies+1.008
 goof+1.001
 サ+0.995
ドラ+0.981
Neg logit contributions
orthern-1.293
imir-1.283
etsk-1.277
oline-1.246
oslav-1.228
Token edit
Token ID4370
Feature activation+1.89e+00

Pos logit contributions
orthern+1.925
imir+1.915
etsk+1.905
oline+1.868
oslav+1.852
Neg logit contributions
 dise-1.300
 Indies-1.198
 goof-1.192
ドラ-1.188
 サ-1.176
Token ]
Token ID2361
Feature activation+1.45e+00

Pos logit contributions
orthern+2.853
imir+2.827
etsk+2.731
oline+2.723
oslav+2.646
Neg logit contributions
 dise-6.703
ドラ-6.366
 Indies-6.365
 goof-6.344
 サ-6.311
Token
Token ID198
Feature activation+5.19e-01

Pos logit contributions
orthern+3.750
imir+3.725
etsk+3.661
oline+3.641
oslav+3.590
Neg logit contributions
 dise-3.599
 Indies-3.351
ドラ-3.338
 goof-3.333
 サ-3.314
Token
Token ID198
Feature activation+6.29e-01

Pos logit contributions
orthern+1.463
imir+1.432
etsk+1.427
oline+1.393
oslav+1.387
Neg logit contributions
 dise-1.188
 Indies-1.121
 goof-1.103
 サ-1.089
ドラ-1.088
TokenThe
Token ID464
Feature activation-1.79e-01

Pos logit contributions
orthern+1.593
imir+1.575
etsk+1.558
oline+1.538
oslav+1.517
Neg logit contributions
 dise-1.593
ドラ-1.502
 Indies-1.500
 サ-1.479
 goof-1.475
Token most
Token ID749
Feature activation+3.43e-01

Pos logit contributions
 dise+0.414
 Indies+0.384
 goof+0.380
 サ+0.377
ドラ+0.370
Neg logit contributions
orthern-0.496
imir-0.492
etsk-0.491
oline-0.484
oslav-0.473
Token-
Token ID12
Feature activation-1.14e-01

Pos logit contributions
 dise+2.383
 Indies+2.203
ドラ+2.199
 サ+2.187
 goof+2.185
Neg logit contributions
orthern-2.935
imir-2.876
etsk-2.861
oline-2.821
oslav-2.798
TokenAli
Token ID37893
Feature activation-2.29e-01

Pos logit contributions
 dise+0.272
ドラ+0.252
 Indies+0.252
 goof+0.250
 サ+0.248
Neg logit contributions
orthern-0.307
imir-0.302
etsk-0.298
oline-0.295
oslav-0.292
Token,
Token ID11
Feature activation+1.56e-01

Pos logit contributions
 dise+0.543
 Indies+0.501
 goof+0.499
ドラ+0.498
 サ+0.496
Neg logit contributions
orthern-0.624
imir-0.616
etsk-0.607
oline-0.606
oslav-0.599
Token the
Token ID262
Feature activation+3.83e-01

Pos logit contributions
orthern+0.455
imir+0.454
etsk+0.450
oline+0.446
oslav+0.442
Neg logit contributions
 dise-0.335
 Indies-0.307
 goof-0.303
ドラ-0.303
 サ-0.302
Token former
Token ID1966
Feature activation+3.18e-01

Pos logit contributions
orthern+1.185
imir+1.178
etsk+1.167
oline+1.157
oslav+1.147
Neg logit contributions
 dise-0.764
 Indies-0.697
 goof-0.690
ドラ-0.685
 サ-0.683
Token bishop
Token ID24233
Feature activation+1.89e+00

Pos logit contributions
orthern+0.993
imir+0.989
etsk+0.976
oline+0.969
oslav+0.961
Neg logit contributions
 dise-0.624
 Indies-0.570
 goof-0.564
ドラ-0.561
 サ-0.558
Token of
Token ID286
Feature activation+5.64e-01

Pos logit contributions
orthern+5.015
imir+4.982
oline+4.909
etsk+4.865
oslav+4.849
Neg logit contributions
 dise-4.402
ドラ-4.155
 goof-4.126
 サ-4.117
 Indies-4.103
Token Rochester
Token ID27008
Feature activation+5.32e-01

Pos logit contributions
orthern+1.685
imir+1.676
etsk+1.651
oline+1.643
oslav+1.624
Neg logit contributions
 dise-1.179
 Indies-1.082
ドラ-1.076
 goof-1.075
 サ-1.068
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
orthern+1.439
imir+1.431
etsk+1.407
oline+1.400
oslav+1.381
Neg logit contributions
 dise-1.264
 Indies-1.172
ドラ-1.168
 goof-1.166
 サ-1.159
Token said
Token ID531
Feature activation-7.98e-02

Pos logit contributions
imir+0.334
orthern+0.333
etsk+0.328
oline+0.326
oslav+0.324
Neg logit contributions
 dise-0.249
 Indies-0.228
 goof-0.226
ドラ-0.224
 サ-0.222
Token proposals
Token ID11628
Feature activation-1.83e-02

Pos logit contributions
 dise+0.167
 Indies+0.152
 goof+0.151
 サ+0.150
ドラ+0.150
Neg logit contributions
orthern-0.239
imir-0.238
etsk-0.235
oline-0.233
oslav-0.231
Token368
Token ID27412
Feature activation-2.61e-01

Pos logit contributions
etsk+0.593
imir+0.589
orthern+0.582
oslav+0.575
oline+0.556
Neg logit contributions
 dise-0.498
ドラ-0.481
 Indies-0.469
 サ-0.467
 goof-0.462
Token<|endoftext|>
Token ID50256
Feature activation+1.25e-01

Pos logit contributions
 dise+0.648
 Indies+0.615
 サ+0.608
 goof+0.604
ドラ+0.602
Neg logit contributions
etsk-0.670
orthern-0.668
imir-0.667
oslav-0.655
oline-0.645
TokenTo
Token ID2514
Feature activation+6.49e-01

Pos logit contributions
orthern+0.322
imir+0.318
etsk+0.313
oline+0.310
oslav+0.306
Neg logit contributions
 dise-0.313
ドラ-0.294
 Indies-0.293
 goof-0.291
 サ-0.289
Token all
Token ID477
Feature activation+1.20e-01

Pos logit contributions
orthern+1.852
imir+1.842
etsk+1.812
oline+1.804
oslav+1.781
Neg logit contributions
 dise-1.442
 Indies-1.330
ドラ-1.324
 goof-1.322
 サ-1.313
Token the
Token ID262
Feature activation+1.07e-01

Pos logit contributions
orthern+0.353
imir+0.351
etsk+0.345
oline+0.344
oslav+0.339
Neg logit contributions
 dise-0.256
 Indies-0.236
 goof-0.233
ドラ-0.233
 サ-0.232
Token patient
Token ID5827
Feature activation+1.88e+00

Pos logit contributions
orthern+0.323
imir+0.321
etsk+0.316
oline+0.314
oslav+0.311
Neg logit contributions
 dise-0.222
 Indies-0.204
 goof-0.203
 サ-0.200
ドラ-0.200
Token American
Token ID1605
Feature activation-1.79e-01

Pos logit contributions
orthern+5.134
imir+5.124
etsk+5.025
oline+5.024
oslav+4.974
Neg logit contributions
 dise-4.287
ドラ-4.012
 Indies-3.991
 サ-3.951
 goof-3.925
Token readers
Token ID7183
Feature activation+7.57e-01

Pos logit contributions
 dise+0.379
 Indies+0.349
 goof+0.347
ドラ+0.340
 サ+0.339
Neg logit contributions
orthern-0.534
imir-0.529
etsk-0.522
oline-0.516
oslav-0.507
Token who
Token ID508
Feature activation+4.10e-01

Pos logit contributions
orthern+2.038
imir+2.025
etsk+1.991
oline+1.981
oslav+1.953
Neg logit contributions
 dise-1.813
 Indies-1.680
 goof-1.673
ドラ-1.669
 サ-1.660
Token have
Token ID423
Feature activation+3.26e-02

Pos logit contributions
orthern+1.198
imir+1.191
etsk+1.173
oline+1.168
oslav+1.153
Neg logit contributions
 dise-0.887
 Indies-0.815
 goof-0.813
ドラ-0.809
 サ-0.805
Token been
Token ID587
Feature activation-1.26e-01

Pos logit contributions
orthern+0.094
imir+0.093
etsk+0.092
oline+0.091
oslav+0.090
Neg logit contributions
 dise-0.073
 goof-0.068
 Indies-0.067
 サ-0.066
ドラ-0.066
Token messages
Token ID6218
Feature activation+3.39e-01

Pos logit contributions
orthern+1.335
imir+1.328
etsk+1.310
oline+1.301
oslav+1.289
Neg logit contributions
 dise-0.931
 Indies-0.847
 goof-0.847
ドラ-0.841
 サ-0.834
Token relating
Token ID11270
Feature activation+2.67e-01

Pos logit contributions
orthern+0.981
imir+0.975
etsk+0.959
oline+0.955
oslav+0.943
Neg logit contributions
 dise-0.747
 Indies-0.686
 goof-0.686
ドラ-0.680
 サ-0.675
Token to
Token ID284
Feature activation-2.18e-01

Pos logit contributions
orthern+0.801
imir+0.796
etsk+0.785
oline+0.781
oslav+0.771
Neg logit contributions
 dise-0.557
 Indies-0.510
 goof-0.508
ドラ-0.507
 サ-0.502
Token their
Token ID511
Feature activation-3.73e-01

Pos logit contributions
 dise+0.466
 Indies+0.427
 goof+0.425
ドラ+0.422
 サ+0.419
Neg logit contributions
orthern-0.642
imir-0.639
etsk-0.628
oline-0.625
oslav-0.618
Token troop
Token ID31874
Feature activation-4.51e-01

Pos logit contributions
 dise+0.843
 Indies+0.775
 goof+0.774
 サ+0.758
ドラ+0.752
Neg logit contributions
orthern-1.066
imir-1.063
etsk-1.044
oline-1.039
oslav-1.024
Token dispos
Token ID12483
Feature activation-2.25e+00

Pos logit contributions
 dise+1.037
 goof+0.965
 Indies+0.939
 サ+0.936
ドラ+0.922
Neg logit contributions
imir-1.271
orthern-1.265
etsk-1.241
oline-1.216
oslav-1.211
Tokenitions
Token ID1756
Feature activation-2.85e-01

Pos logit contributions
 dise+5.699
 goof+5.438
 Indies+5.385
 サ+5.305
ドラ+5.204
Neg logit contributions
orthern-5.240
imir-5.204
oline-5.097
oslav-4.980
VIDIA-4.977
Token,
Token ID11
Feature activation-1.92e-01

Pos logit contributions
 dise+0.702
 goof+0.653
 Indies+0.649
ドラ+0.640
 サ+0.638
Neg logit contributions
imir-0.748
orthern-0.747
etsk-0.729
oline-0.729
oslav-0.721
Token according
Token ID1864
Feature activation-6.40e-01

Pos logit contributions
 dise+0.434
 Indies+0.399
 goof+0.398
 サ+0.390
ドラ+0.389
Neg logit contributions
orthern-0.546
imir-0.545
etsk-0.534
oline-0.533
oslav-0.527
Token to
Token ID284
Feature activation+2.17e-02

Pos logit contributions
 dise+1.115
 Indies+1.044
 goof+1.025
 Barr+1.007
 サ+1.006
Neg logit contributions
orthern-2.120
etsk-2.117
VIDIA-2.082
imir-2.077
oline-2.047
Token a
Token ID257
Feature activation+5.10e-02

Pos logit contributions
orthern+0.064
imir+0.063
etsk+0.062
oline+0.062
oslav+0.062
Neg logit contributions
 dise-0.046
 Indies-0.043
 goof-0.042
 サ-0.042
ドラ-0.042
Token their
Token ID511
Feature activation-1.05e-01

Pos logit contributions
orthern+0.403
imir+0.401
etsk+0.395
oline+0.394
oslav+0.389
Neg logit contributions
 dise-0.247
 Indies-0.224
 goof-0.223
ドラ-0.221
 サ-0.220
Token animals
Token ID4695
Feature activation-1.33e-01

Pos logit contributions
 dise+0.228
 goof+0.207
 Indies+0.206
 サ+0.203
ドラ+0.201
Neg logit contributions
orthern-0.310
imir-0.309
etsk-0.305
oline-0.302
oslav-0.299
Token roam
Token ID35563
Feature activation+6.01e-02

Pos logit contributions
 dise+0.305
 goof+0.280
 Indies+0.278
 サ+0.276
ドラ+0.272
Neg logit contributions
orthern-0.373
imir-0.371
etsk-0.365
oline-0.363
oslav-0.359
Token as
Token ID355
Feature activation-3.94e-01

Pos logit contributions
orthern+0.180
imir+0.180
etsk+0.177
oline+0.175
oslav+0.174
Neg logit contributions
 dise-0.127
 Indies-0.116
 goof-0.116
 サ-0.114
ドラ-0.112
Token they
Token ID484
Feature activation-2.85e-01

Pos logit contributions
 dise+0.772
 goof+0.697
 Indies+0.695
 サ+0.683
 PARK+0.672
Neg logit contributions
orthern-1.243
imir-1.241
etsk-1.229
oline-1.209
oslav-1.200
Token gra
Token ID7933
Feature activation-2.18e+00

Pos logit contributions
 dise+0.619
 goof+0.571
 サ+0.561
 Indies+0.560
 PARK+0.545
Neg logit contributions
orthern-0.834
imir-0.832
etsk-0.819
oline-0.817
oslav-0.806
Tokenze
Token ID2736
Feature activation-3.30e-01

Pos logit contributions
 dise+4.323
 goof+4.067
 Indies+3.868
ドラ+3.810
 Berm+3.726
Neg logit contributions
VIDIA-6.387
orthern-6.331
imir-6.212
 Dragonbound-6.204
oslav-6.201
Token and
Token ID290
Feature activation+2.03e-02

Pos logit contributions
 dise+0.776
 Indies+0.713
 goof+0.711
 サ+0.706
ドラ+0.692
Neg logit contributions
imir-0.908
orthern-0.907
etsk-0.889
oline-0.882
oslav-0.875
Token for
Token ID329
Feature activation-3.10e-01

Pos logit contributions
orthern+0.059
imir+0.059
etsk+0.058
oline+0.058
oslav+0.057
Neg logit contributions
 dise-0.044
 goof-0.041
 Indies-0.040
 サ-0.040
ドラ-0.040
Tokenage
Token ID496
Feature activation-4.99e-01

Pos logit contributions
 dise+0.577
 goof+0.519
 Indies+0.517
 サ+0.510
ドラ+0.502
Neg logit contributions
orthern-1.005
imir-0.998
etsk-0.989
oline-0.982
oslav-0.973
Token like
Token ID588
Feature activation-6.15e-01

Pos logit contributions
 dise+1.166
 goof+1.069
 Indies+1.067
 サ+1.061
 PARK+1.034
Neg logit contributions
imir-1.376
orthern-1.375
etsk-1.353
oline-1.339
oslav-1.332
Tokenus
Token ID385
Feature activation+9.37e-01

Pos logit contributions
orthern+0.147
imir+0.142
etsk+0.139
oslav+0.138
oline+0.137
Neg logit contributions
 dise-0.238
 Indies-0.224
 goof-0.224
 サ-0.224
 PARK-0.220
Token monkeys
Token ID26697
Feature activation-1.09e-01

Pos logit contributions
orthern+3.314
imir+3.296
etsk+3.277
oline+3.241
oslav+3.210
Neg logit contributions
 dise-1.410
ドラ-1.285
 Indies-1.260
 goof-1.246
 サ-1.240
Token (
Token ID357
Feature activation-6.98e-01

Pos logit contributions
 dise+0.236
 goof+0.216
 Indies+0.216
 サ+0.212
ドラ+0.212
Neg logit contributions
orthern-0.322
imir-0.319
etsk-0.312
oline-0.312
oslav-0.309
TokenMac
Token ID14155
Feature activation+3.55e-01

Pos logit contributions
 dise+1.725
ドラ+1.602
 Indies+1.599
 サ+1.588
 goof+1.582
Neg logit contributions
orthern-1.798
imir-1.790
oline-1.751
etsk-1.744
oslav-1.734
Tokenaca
Token ID22260
Feature activation-1.29e+00

Pos logit contributions
orthern+0.742
imir+0.732
etsk+0.715
oline+0.704
oslav+0.696
Neg logit contributions
 dise-1.065
 Indies-1.005
ドラ-0.998
 goof-0.997
 サ-0.992
Token mul
Token ID35971
Feature activation-2.16e+00

Pos logit contributions
 dise+2.041
 goof+1.747
 Indies+1.709
 サ+1.604
 PARK+1.580
Neg logit contributions
etsk-4.586
imir-4.580
orthern-4.481
oline-4.459
oslav-4.393
Tokenatta
Token ID25014
Feature activation-1.79e-01

Pos logit contributions
 dise+6.588
 Indies+6.264
 goof+6.219
 サ+6.091
 Barr+6.023
Neg logit contributions
etsk-4.070
orthern-4.058
imir-4.057
oslav-3.862
oline-3.835
Token)
Token ID8
Feature activation-6.55e-01

Pos logit contributions
 dise+0.433
 Indies+0.402
ドラ+0.399
 goof+0.399
 サ+0.397
Neg logit contributions
orthern-0.476
imir-0.473
etsk-0.465
oline-0.463
oslav-0.457
Token were
Token ID547
Feature activation-2.80e-01

Pos logit contributions
 dise+1.257
 goof+1.129
 Indies+1.124
 サ+1.099
 PARK+1.095
Neg logit contributions
orthern-2.093
imir-2.078
oline-2.033
etsk-2.032
oslav-2.014
Token housed
Token ID23707
Feature activation+4.24e-01

Pos logit contributions
 dise+0.559
 goof+0.507
 Indies+0.500
 サ+0.490
 PARK+0.487
Neg logit contributions
orthern-0.879
imir-0.867
oline-0.855
etsk-0.852
oslav-0.842
Token under
Token ID739
Feature activation-5.83e-01

Pos logit contributions
orthern+1.260
imir+1.253
etsk+1.233
oline+1.229
oslav+1.213
Neg logit contributions
 dise-0.895
 Indies-0.820
 goof-0.817
ドラ-0.816
 サ-0.809
Token of
Token ID286
Feature activation-3.62e-01

Pos logit contributions
orthern+0.389
imir+0.387
etsk+0.380
oline+0.379
oslav+0.374
Neg logit contributions
 dise-0.299
 Indies-0.276
 goof-0.274
ドラ-0.274
 サ-0.272
Token her
Token ID607
Feature activation+6.55e-01

Pos logit contributions
 dise+0.715
 Indies+0.655
 goof+0.649
ドラ+0.641
 サ+0.641
Neg logit contributions
orthern-1.128
imir-1.126
etsk-1.103
oline-1.096
oslav-1.091
Token movie
Token ID3807
Feature activation-3.16e-01

Pos logit contributions
orthern+1.859
imir+1.847
etsk+1.816
oline+1.812
oslav+1.786
Neg logit contributions
 dise-1.465
 Indies-1.351
ドラ-1.350
 goof-1.341
 サ-1.337
Token,
Token ID11
Feature activation-2.95e-01

Pos logit contributions
 dise+0.673
 goof+0.624
 Indies+0.624
ドラ+0.619
 サ+0.614
Neg logit contributions
imir-0.930
orthern-0.928
etsk-0.913
oslav-0.905
oline-0.901
Token Train
Token ID16835
Feature activation+1.88e-01

Pos logit contributions
 dise+0.624
 Indies+0.579
 goof+0.573
 サ+0.567
ドラ+0.566
Neg logit contributions
imir-0.874
orthern-0.873
etsk-0.857
oline-0.850
oslav-0.849
Tokenwreck
Token ID39238
Feature activation-2.01e+00

Pos logit contributions
orthern+0.706
imir+0.702
etsk+0.696
oslav+0.688
oline+0.676
Neg logit contributions
 dise-0.253
 Indies-0.226
 goof-0.222
 サ-0.215
 PARK-0.215
Token,
Token ID11
Feature activation-3.88e-01

Pos logit contributions
 dise+4.902
 Indies+4.698
 goof+4.620
 サ+4.510
ドラ+4.507
Neg logit contributions
orthern-5.076
imir-5.049
etsk-4.947
oslav-4.928
oline-4.868
Token in
Token ID287
Feature activation-4.77e-01

Pos logit contributions
 dise+0.796
 goof+0.734
 Indies+0.734
ドラ+0.712
 サ+0.708
Neg logit contributions
orthern-1.177
imir-1.171
oline-1.149
etsk-1.149
oslav-1.142
Token a
Token ID257
Feature activation-1.19e-01

Pos logit contributions
 dise+0.923
 Indies+0.847
 goof+0.837
 Barr+0.821
 PARK+0.819
Neg logit contributions
imir-1.506
orthern-1.491
etsk-1.472
oslav-1.472
oline-1.454
Token Lafayette
Token ID41388
Feature activation+9.22e-01

Pos logit contributions
 dise+0.257
 goof+0.235
 Indies+0.234
 PARK+0.229
 サ+0.229
Neg logit contributions
imir-0.352
orthern-0.349
etsk-0.346
oslav-0.343
oline-0.342
Token,
Token ID11
Feature activation-1.16e-02

Pos logit contributions
orthern+2.603
imir+2.584
etsk+2.542
oline+2.535
oslav+2.495
Neg logit contributions
 dise-2.077
 Indies-1.917
ドラ-1.917
 goof-1.905
 サ-1.897
Token them
Token ID606
Feature activation-3.43e-01

Pos logit contributions
 dise+2.065
 Indies+1.912
 goof+1.875
 サ+1.847
 Barr+1.829
Neg logit contributions
orthern-3.012
imir-2.986
etsk-2.933
oline-2.909
oslav-2.883
Token and
Token ID290
Feature activation-3.93e-01

Pos logit contributions
 dise+0.791
 Indies+0.733
 goof+0.732
 サ+0.721
ドラ+0.716
Neg logit contributions
orthern-0.955
imir-0.946
etsk-0.932
oline-0.930
oslav-0.915
Token their
Token ID511
Feature activation-5.17e-01

Pos logit contributions
 dise+0.799
 Indies+0.736
 goof+0.733
 サ+0.719
ドラ+0.719
Neg logit contributions
orthern-1.197
imir-1.189
etsk-1.172
oline-1.165
oslav-1.155
Token own
Token ID898
Feature activation-8.73e-02

Pos logit contributions
 dise+1.155
 goof+1.069
 Indies+1.067
 サ+1.043
ドラ+1.031
Neg logit contributions
orthern-1.482
imir-1.468
etsk-1.448
oline-1.440
oslav-1.417
Token tax
Token ID1687
Feature activation-1.51e+00

Pos logit contributions
 dise+0.192
 Indies+0.178
 goof+0.178
ドラ+0.174
 サ+0.174
Neg logit contributions
orthern-0.253
imir-0.251
etsk-0.247
oline-0.246
oslav-0.242
Token dodge
Token ID24885
Feature activation-1.93e+00

Pos logit contributions
 dise+3.371
 goof+3.152
 Indies+3.081
 サ+3.052
ドラ+3.047
Neg logit contributions
orthern-4.286
imir-4.173
etsk-4.117
oslav-4.035
oline-4.009
Token at
Token ID379
Feature activation-3.87e-01

Pos logit contributions
 dise+4.625
 goof+4.389
 Indies+4.328
 サ+4.258
ドラ+4.180
Neg logit contributions
orthern-4.969
imir-4.913
etsk-4.863
oslav-4.747
oline-4.678
Token all
Token ID477
Feature activation+4.07e-02

Pos logit contributions
 dise+0.803
 Indies+0.738
 goof+0.734
 サ+0.726
ドラ+0.726
Neg logit contributions
orthern-1.168
imir-1.161
etsk-1.144
oline-1.137
oslav-1.124
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
orthern+0.097
imir+0.096
etsk+0.094
oline+0.093
oslav+0.092
Neg logit contributions
 dise-0.110
 Indies-0.104
 goof-0.103
 サ-0.102
ドラ-0.102
Token We
Token ID775
Feature activation-3.56e-01

Pos logit contributions
 dise+0.690
 Indies+0.657
 サ+0.648
 goof+0.640
ドラ+0.638
Neg logit contributions
orthern-0.848
imir-0.831
etsk-0.826
oline-0.808
oslav-0.806
Token think
Token ID892
Feature activation-7.86e-01

Pos logit contributions
 dise+0.763
 goof+0.707
 Indies+0.704
 サ+0.691
ドラ+0.683
Neg logit contributions
orthern-1.049
imir-1.037
etsk-1.022
oline-1.015
oslav-1.000
Token apartment
Token ID7962
Feature activation-7.45e-02

Pos logit contributions
orthern+0.511
imir+0.509
etsk+0.503
oline+0.497
oslav+0.490
Neg logit contributions
 dise-0.331
 Indies-0.302
 goof-0.299
 サ-0.295
ドラ-0.294
Token complex
Token ID3716
Feature activation-7.78e-01

Pos logit contributions
 dise+0.173
 goof+0.161
 Indies+0.159
 サ+0.156
 PARK+0.155
Neg logit contributions
orthern-0.206
imir-0.206
etsk-0.205
oline-0.200
oslav-0.199
Token in
Token ID287
Feature activation-2.84e-01

Pos logit contributions
 dise+1.657
 goof+1.539
 Indies+1.499
 PARK+1.492
 サ+1.468
Neg logit contributions
imir-2.296
orthern-2.281
etsk-2.260
oslav-2.225
oline-2.217
Token the
Token ID262
Feature activation-6.16e-02

Pos logit contributions
 dise+0.542
 Indies+0.497
 goof+0.497
 サ+0.483
 PARK+0.482
Neg logit contributions
orthern-0.893
imir-0.892
etsk-0.878
oline-0.876
oslav-0.865
Token 3000
Token ID20343
Feature activation+8.09e-02

Pos logit contributions
 dise+0.113
 Indies+0.103
 goof+0.103
 サ+0.100
 PARK+0.099
Neg logit contributions
imir-0.200
orthern-0.200
etsk-0.197
oline-0.196
oslav-0.194
Token block
Token ID2512
Feature activation-1.91e+00

Pos logit contributions
orthern+0.261
imir+0.261
etsk+0.257
oline+0.254
oslav+0.253
Neg logit contributions
 dise-0.150
 Indies-0.136
 goof-0.135
ドラ-0.134
 サ-0.134
Token of
Token ID286
Feature activation-2.77e-01

Pos logit contributions
 dise+3.067
 Indies+3.028
 Berm+2.901
 goof+2.900
 Barr+2.886
Neg logit contributions
imir-6.331
VIDIA-6.265
etsk-6.253
orthern-6.210
oline-6.124
Token Maryland
Token ID10769
Feature activation+1.00e-01

Pos logit contributions
 dise+0.636
 Indies+0.594
 goof+0.585
 サ+0.581
ドラ+0.578
Neg logit contributions
orthern-0.769
imir-0.765
etsk-0.756
oline-0.747
oslav-0.738
Token Street
Token ID3530
Feature activation+8.81e-02

Pos logit contributions
orthern+0.271
imir+0.270
etsk+0.266
oline+0.262
oslav+0.260
Neg logit contributions
 dise-0.237
 Indies-0.222
 goof-0.220
 サ-0.216
 Barr-0.215
Token.
Token ID13
Feature activation+2.01e-01

Pos logit contributions
imir+0.245
orthern+0.245
etsk+0.240
oline+0.239
oslav+0.236
Neg logit contributions
 dise-0.203
 Indies-0.189
 goof-0.188
 サ-0.184
 PARK-0.184
Token
Token ID198
Feature activation-2.49e-02

Pos logit contributions
orthern+0.543
imir+0.533
etsk+0.528
oline+0.521
oslav+0.515
Neg logit contributions
 dise-0.480
 Indies-0.452
 サ-0.446
 goof-0.445
ドラ-0.442
Token pop
Token ID1461
Feature activation-8.93e-02

Pos logit contributions
 dise+0.653
 goof+0.608
 Indies+0.604
ドラ+0.597
 サ+0.593
Neg logit contributions
orthern-0.796
imir-0.790
etsk-0.778
oline-0.774
oslav-0.768
Token up
Token ID510
Feature activation-4.92e-01

Pos logit contributions
 dise+0.235
 goof+0.220
 Indies+0.219
ドラ+0.218
 サ+0.215
Neg logit contributions
orthern-0.221
imir-0.219
etsk-0.214
oline-0.212
oslav-0.207
Token of
Token ID286
Feature activation-1.92e-01

Pos logit contributions
 dise+1.016
 goof+0.938
 Indies+0.923
 サ+0.898
ドラ+0.890
Neg logit contributions
orthern-1.495
imir-1.491
etsk-1.459
oline-1.454
oslav-1.439
Token the
Token ID262
Feature activation-1.47e-01

Pos logit contributions
 dise+0.367
 goof+0.334
 Indies+0.331
 サ+0.323
ドラ+0.322
Neg logit contributions
orthern-0.614
imir-0.608
etsk-0.605
oline-0.602
oslav-0.594
Token traveling
Token ID11300
Feature activation+2.07e-01

Pos logit contributions
 dise+0.347
 goof+0.320
 Indies+0.315
 サ+0.310
ドラ+0.309
Neg logit contributions
orthern-0.406
imir-0.405
etsk-0.401
oline-0.397
oslav-0.393
Token gra
Token ID7933
Feature activation-1.91e+00

Pos logit contributions
orthern+0.626
imir+0.622
etsk+0.617
oline+0.610
oslav+0.602
Neg logit contributions
 dise-0.433
 goof-0.397
 Indies-0.393
ドラ-0.386
 サ-0.383
Tokenff
Token ID487
Feature activation-6.33e-01

Pos logit contributions
 dise+4.064
 goof+3.816
ドラ+3.677
 Indies+3.632
 サ+3.580
Neg logit contributions
orthern-5.383
imir-5.342
etsk-5.312
oline-5.202
oslav-5.162
Tokenito
Token ID10094
Feature activation-5.29e-01

Pos logit contributions
 dise+1.602
 goof+1.517
 Indies+1.481
 サ+1.469
ドラ+1.468
Neg logit contributions
orthern-1.608
imir-1.590
etsk-1.569
oline-1.542
oslav-1.528
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
 dise+1.165
 goof+1.096
 Indies+1.062
 サ+1.043
ドラ+1.039
Neg logit contributions
orthern-1.532
imir-1.523
etsk-1.513
oline-1.493
oslav-1.479
Token
Token ID198
Feature activation+4.92e-02

Pos logit contributions
orthern+0.456
imir+0.451
etsk+0.446
oline+0.442
oslav+0.437
Neg logit contributions
 dise-0.385
 Indies-0.361
 goof-0.357
 サ-0.356
ドラ-0.355
Token
Token ID198
Feature activation+1.17e-01

Pos logit contributions
orthern+0.144
imir+0.140
etsk+0.140
VIDIA+0.138
oslav+0.136
Neg logit contributions
 dise-0.108
 Indies-0.102
 goof-0.100
 サ-0.098
 PARK-0.098
Token allow
Token ID1249
Feature activation-6.44e-01

Pos logit contributions
 dise+0.636
 goof+0.592
 Indies+0.585
 サ+0.581
ドラ+0.565
Neg logit contributions
orthern-0.810
imir-0.802
etsk-0.789
oline-0.788
oslav-0.781
Token citizens
Token ID4290
Feature activation+3.18e-01

Pos logit contributions
 dise+1.398
 Indies+1.291
 goof+1.272
 サ+1.258
ドラ+1.250
Neg logit contributions
imir-1.860
orthern-1.857
etsk-1.840
oline-1.814
oslav-1.810
Token the
Token ID262
Feature activation+1.87e-01

Pos logit contributions
orthern+0.898
imir+0.888
etsk+0.875
oline+0.874
oslav+0.861
Neg logit contributions
 dise-0.707
ドラ-0.661
 Indies-0.653
 goof-0.653
 サ-0.648
Token right
Token ID826
Feature activation-6.35e-01

Pos logit contributions
orthern+0.479
imir+0.475
etsk+0.468
oline+0.464
oslav+0.458
Neg logit contributions
 dise-0.472
 Indies-0.440
 goof-0.438
ドラ-0.437
 サ-0.436
Token to
Token ID284
Feature activation-4.20e-01

Pos logit contributions
 dise+1.432
ドラ+1.332
 Indies+1.321
 goof+1.318
 サ+1.300
Neg logit contributions
orthern-1.808
imir-1.794
oline-1.760
etsk-1.758
oslav-1.724
Token gra
Token ID7933
Feature activation-1.90e+00

Pos logit contributions
 dise+0.923
 goof+0.848
 Indies+0.844
 サ+0.843
ドラ+0.827
Neg logit contributions
orthern-1.211
imir-1.204
etsk-1.184
oline-1.180
oslav-1.173
Tokenze
Token ID2736
Feature activation-1.17e-01

Pos logit contributions
 dise+4.203
 goof+3.741
ドラ+3.710
 Indies+3.696
 PARK+3.637
Neg logit contributions
orthern-5.335
imir-5.174
VIDIA-5.164
 Dragonbound-5.138
etsk-5.128
Token sheep
Token ID15900
Feature activation+7.44e-01

Pos logit contributions
 dise+0.249
 Indies+0.227
 goof+0.225
 サ+0.223
ドラ+0.222
Neg logit contributions
orthern-0.347
imir-0.346
etsk-0.340
oline-0.338
oslav-0.336
Token on
Token ID319
Feature activation+3.43e-01

Pos logit contributions
orthern+2.021
imir+2.004
etsk+1.978
oline+1.968
oslav+1.937
Neg logit contributions
 dise-1.738
ドラ-1.627
 Indies-1.618
 goof-1.612
 サ-1.604
Token any
Token ID597
Feature activation-6.07e-02

Pos logit contributions
orthern+1.014
imir+1.009
etsk+0.993
oline+0.989
oslav+0.977
Neg logit contributions
 dise-0.729
 Indies-0.670
ドラ-0.667
 goof-0.666
 サ-0.661
Token golf
Token ID13126
Feature activation-8.24e-01

Pos logit contributions
 dise+0.136
 Indies+0.124
 goof+0.124
 サ+0.122
ドラ+0.122
Neg logit contributions
imir-0.174
orthern-0.174
etsk-0.172
oline-0.170
oslav-0.168
Token to
Token ID284
Feature activation-5.16e-01

Pos logit contributions
 dise+2.259
 goof+2.072
 Indies+2.068
 サ+2.039
ドラ+2.025
Neg logit contributions
orthern-2.961
imir-2.945
etsk-2.870
oline-2.866
oslav-2.846
Token work
Token ID670
Feature activation-3.77e-01

Pos logit contributions
 dise+1.129
 goof+1.046
 Indies+1.030
 サ+1.015
ドラ+1.010
Neg logit contributions
orthern-1.497
imir-1.487
oline-1.462
etsk-1.459
oslav-1.442
Token smarter
Token ID23714
Feature activation-7.14e-01

Pos logit contributions
 dise+0.907
 goof+0.844
 サ+0.837
 Indies+0.835
ドラ+0.818
Neg logit contributions
orthern-1.011
imir-0.996
etsk-0.991
oline-0.977
oslav-0.966
Token,
Token ID11
Feature activation-2.92e-01

Pos logit contributions
 dise+1.623
 goof+1.525
 サ+1.509
 Indies+1.505
 PARK+1.469
Neg logit contributions
orthern-1.970
imir-1.965
etsk-1.929
oline-1.908
oslav-1.890
Token not
Token ID407
Feature activation-3.13e-01

Pos logit contributions
 dise+0.614
 goof+0.564
 Indies+0.561
 サ+0.555
ドラ+0.552
Neg logit contributions
orthern-0.874
imir-0.870
etsk-0.855
oline-0.853
oslav-0.842
Token harder
Token ID7069
Feature activation-1.90e+00

Pos logit contributions
 dise+0.561
 goof+0.510
 Indies+0.502
ドラ+0.498
 サ+0.497
Neg logit contributions
orthern-1.030
imir-1.023
etsk-1.011
oline-1.006
oslav-0.999
Token.
Token ID13
Feature activation-4.14e-01

Pos logit contributions
 dise+4.671
 サ+4.397
 goof+4.395
 Indies+4.322
ドラ+4.313
Neg logit contributions
orthern-4.753
imir-4.731
etsk-4.588
oline-4.569
oslav-4.546
Token Ind
Token ID1423
Feature activation-2.31e-01

Pos logit contributions
 dise+0.958
 Indies+0.893
 サ+0.893
 goof+0.887
ドラ+0.884
Neg logit contributions
orthern-1.141
imir-1.129
etsk-1.111
oline-1.101
oslav-1.092
Tokenividually
Token ID16335
Feature activation+1.24e+00

Pos logit contributions
 dise+0.593
 Indies+0.553
 goof+0.552
ドラ+0.547
 サ+0.545
Neg logit contributions
orthern-0.574
imir-0.566
etsk-0.566
oline-0.552
oslav-0.545
Token,
Token ID11
Feature activation-4.69e-01

Pos logit contributions
orthern+3.323
imir+3.293
etsk+3.245
oline+3.241
oslav+3.188
Neg logit contributions
 dise-2.935
ドラ-2.746
 Indies-2.734
 goof-2.707
 サ-2.698
Token this
Token ID428
Feature activation-1.81e-01

Pos logit contributions
 dise+0.945
 Indies+0.864
 goof+0.860
 サ+0.848
ドラ+0.847
Neg logit contributions
orthern-1.446
imir-1.434
etsk-1.415
oline-1.406
oslav-1.391
Token to
Token ID284
Feature activation-4.67e-01

Pos logit contributions
 dise+2.012
 Indies+1.844
 goof+1.841
ドラ+1.836
 サ+1.827
Neg logit contributions
orthern-2.764
imir-2.742
etsk-2.703
oline-2.692
oslav-2.661
Token vote
Token ID3015
Feature activation-4.01e-01

Pos logit contributions
 dise+1.027
 goof+0.968
 サ+0.957
 Indies+0.949
ドラ+0.926
Neg logit contributions
orthern-1.338
imir-1.324
etsk-1.298
oline-1.298
oslav-1.289
Token against
Token ID1028
Feature activation-1.71e-01

Pos logit contributions
 dise+0.925
 サ+0.859
 goof+0.854
 Indies+0.854
ドラ+0.852
Neg logit contributions
orthern-1.101
imir-1.093
etsk-1.078
oline-1.075
oslav-1.062
Token the
Token ID262
Feature activation-1.72e-01

Pos logit contributions
 dise+0.358
 Indies+0.330
 goof+0.328
 サ+0.328
ドラ+0.325
Neg logit contributions
orthern-0.508
imir-0.506
etsk-0.498
oline-0.495
oslav-0.491
Token GOP
Token ID6796
Feature activation-8.57e-02

Pos logit contributions
 dise+0.388
 goof+0.357
 Indies+0.354
 サ+0.353
ドラ+0.350
Neg logit contributions
imir-0.484
orthern-0.482
etsk-0.473
oline-0.472
oslav-0.468
Token tax
Token ID1687
Feature activation-1.89e+00

Pos logit contributions
 dise+0.201
 goof+0.186
 Indies+0.185
 サ+0.185
ドラ+0.185
Neg logit contributions
orthern-0.234
imir-0.233
etsk-0.228
oline-0.227
oslav-0.225
Token reform
Token ID4975
Feature activation-3.20e-01

Pos logit contributions
 dise+4.230
 goof+4.080
 サ+3.930
ドラ+3.889
 ROCK+3.824
Neg logit contributions
imir-5.164
orthern-5.109
etsk-4.998
oslav-4.944
oline-4.924
Token package
Token ID5301
Feature activation+3.01e-02

Pos logit contributions
 dise+0.827
 goof+0.776
 Indies+0.767
 サ+0.765
ドラ+0.765
Neg logit contributions
imir-0.793
orthern-0.793
etsk-0.773
oline-0.766
oslav-0.763
Token.
Token ID13
Feature activation-6.11e-02

Pos logit contributions
orthern+0.081
imir+0.080
etsk+0.079
oline+0.078
oslav+0.078
Neg logit contributions
 dise-0.072
 goof-0.067
 Indies-0.067
 サ-0.066
ドラ-0.066
Token
Token ID198
Feature activation-1.89e-01

Pos logit contributions
 dise+0.151
 Indies+0.140
ドラ+0.140
 goof+0.140
 サ+0.139
Neg logit contributions
orthern-0.159
imir-0.158
etsk-0.156
oline-0.155
oslav-0.153
Token
Token ID198
Feature activation-4.99e-02

Pos logit contributions
 dise+0.403
 Indies+0.384
 goof+0.376
 サ+0.368
 PARK+0.367
Neg logit contributions
orthern-0.560
etsk-0.545
imir-0.542
VIDIA-0.540
oslav-0.529
Token Climate
Token ID13963
Feature activation-1.47e-01

Pos logit contributions
orthern+0.593
imir+0.590
etsk+0.581
oline+0.574
oslav+0.570
Neg logit contributions
 dise-0.466
 Indies-0.432
 goof-0.428
ドラ-0.426
 サ-0.425
TokenWorks
Token ID23044
Feature activation+1.39e-01

Pos logit contributions
 dise+0.355
ドラ+0.333
 Indies+0.332
 goof+0.330
 サ+0.326
Neg logit contributions
orthern-0.388
imir-0.385
etsk-0.379
oline-0.373
oslav-0.371
Token).
Token ID737
Feature activation-1.43e-01

Pos logit contributions
orthern+0.405
imir+0.401
etsk+0.396
oline+0.391
oslav+0.390
Neg logit contributions
 dise-0.301
 Indies-0.281
 goof-0.276
ドラ-0.275
 サ-0.273
Token
Token ID198
Feature activation-4.01e-01

Pos logit contributions
 dise+0.333
 Indies+0.312
 goof+0.308
ドラ+0.307
 サ+0.307
Neg logit contributions
orthern-0.395
imir-0.390
etsk-0.386
oline-0.381
oslav-0.376
Token
Token ID198
Feature activation-1.66e-01

Pos logit contributions
 dise+0.844
 Indies+0.806
 goof+0.786
 Barr+0.771
 サ+0.767
Neg logit contributions
orthern-1.201
etsk-1.167
VIDIA-1.165
imir-1.160
 tremend-1.134
TokenHar
Token ID13587
Feature activation-1.87e+00

Pos logit contributions
 dise+0.408
 Indies+0.385
ドラ+0.384
 goof+0.378
 サ+0.376
Neg logit contributions
orthern-0.434
imir-0.427
etsk-0.425
oline-0.416
oslav-0.413
Tokenold
Token ID727
Feature activation+1.16e-02

Pos logit contributions
 dise+2.883
 Indies+2.625
 goof+2.575
 Rosenthal+2.495
 PARK+2.459
Neg logit contributions
etsk-6.352
orthern-6.207
oline-6.055
imir-6.042
oslav-6.036
Token K
Token ID509
Feature activation+6.24e-02

Pos logit contributions
orthern+0.034
imir+0.034
etsk+0.034
oline+0.033
oslav+0.033
Neg logit contributions
 dise-0.024
 Indies-0.022
 goof-0.022
ドラ-0.022
 サ-0.022
Token.
Token ID13
Feature activation-2.09e-01

Pos logit contributions
orthern+0.143
imir+0.141
etsk+0.139
oline+0.137
oslav+0.136
Neg logit contributions
 dise-0.172
 Indies-0.163
 goof-0.161
ドラ-0.159
 サ-0.159
Token H
Token ID367
Feature activation+2.40e-01

Pos logit contributions
 dise+0.424
 Indies+0.393
 goof+0.387
 サ+0.385
ドラ+0.384
Neg logit contributions
orthern-0.637
imir-0.630
etsk-0.625
oline-0.618
oslav-0.609
Tokenoch
Token ID5374
Feature activation+4.38e-01

Pos logit contributions
orthern+0.541
imir+0.534
etsk+0.525
oline+0.523
oslav+0.518
Neg logit contributions
 dise-0.672
 Indies-0.631
 goof-0.628
 サ-0.623
ドラ-0.619
Token the
Token ID262
Feature activation+1.66e-01

Pos logit contributions
orthern+0.784
imir+0.779
etsk+0.767
oline+0.765
oslav+0.756
Neg logit contributions
 dise-0.576
 Indies-0.531
ドラ-0.531
 goof-0.526
 サ-0.525
Token secondary
Token ID9233
Feature activation-2.47e-01

Pos logit contributions
orthern+0.510
imir+0.508
etsk+0.500
oline+0.496
oslav+0.491
Neg logit contributions
 dise-0.334
 Indies-0.305
 goof-0.305
ドラ-0.301
 サ-0.299
Token fal
Token ID24215
Feature activation-8.44e-02

Pos logit contributions
 dise+0.521
 goof+0.479
 Indies+0.478
ドラ+0.472
 サ+0.471
Neg logit contributions
orthern-0.734
imir-0.729
etsk-0.717
oline-0.714
oslav-0.706
Tokentered
Token ID4400
Feature activation-6.84e-02

Pos logit contributions
 dise+0.235
 goof+0.221
 Indies+0.221
ドラ+0.220
 サ+0.217
Neg logit contributions
orthern-0.193
imir-0.191
etsk-0.186
oline-0.185
oslav-0.182
Token,
Token ID11
Feature activation+5.24e-02

Pos logit contributions
 dise+0.148
 goof+0.136
 Indies+0.135
ドラ+0.134
 サ+0.133
Neg logit contributions
orthern-0.200
imir-0.199
etsk-0.196
oline-0.195
oslav-0.193
Token Sherman
Token ID23198
Feature activation-1.86e+00

Pos logit contributions
orthern+0.159
imir+0.159
etsk+0.156
oline+0.156
oslav+0.154
Neg logit contributions
 dise-0.107
 Indies-0.098
 goof-0.097
ドラ-0.097
 サ-0.096
Token performed
Token ID6157
Feature activation-5.97e-02

Pos logit contributions
 dise+3.758
 goof+3.558
 Indies+3.355
 deflect+3.317
 Barr+3.275
Neg logit contributions
orthern-5.676
imir-5.546
etsk-5.486
oline-5.462
oslav-5.442
Token to
Token ID284
Feature activation-4.69e-01

Pos logit contributions
 dise+0.117
 goof+0.107
 Indies+0.106
 サ+0.104
ドラ+0.103
Neg logit contributions
orthern-0.188
imir-0.186
etsk-0.184
oline-0.183
oslav-0.181
Token his
Token ID465
Feature activation-2.80e-01

Pos logit contributions
 dise+0.965
 goof+0.886
 Indies+0.879
ドラ+0.879
 サ+0.868
Neg logit contributions
orthern-1.414
imir-1.401
etsk-1.396
oline-1.381
oslav-1.364
Token ability
Token ID2694
Feature activation-4.88e-01

Pos logit contributions
 dise+0.625
 goof+0.571
 Indies+0.566
ドラ+0.550
 Barr+0.548
Neg logit contributions
orthern-0.813
imir-0.811
etsk-0.804
oline-0.785
oslav-0.781
Token against
Token ID1028
Feature activation-2.49e-01

Pos logit contributions
 dise+1.173
 goof+1.091
 Indies+1.080
ドラ+1.053
 サ+1.051
Neg logit contributions
orthern-1.307
imir-1.307
etsk-1.287
oline-1.266
oslav-1.266
Token screen
Token ID3159
Feature activation-6.26e-01

Pos logit contributions
orthern+1.684
imir+1.671
etsk+1.648
oline+1.632
oslav+1.616
Neg logit contributions
 dise-1.354
 Indies-1.251
 goof-1.244
ドラ-1.242
 サ-1.236
Token.
Token ID13
Feature activation+9.71e-02

Pos logit contributions
 dise+1.410
 Indies+1.307
 goof+1.298
 サ+1.290
ドラ+1.267
Neg logit contributions
orthern-1.767
imir-1.761
etsk-1.732
oslav-1.704
oline-1.692
Token Source
Token ID8090
Feature activation+2.18e-01

Pos logit contributions
orthern+0.273
imir+0.271
etsk+0.267
oline+0.265
oslav+0.262
Neg logit contributions
 dise-0.220
 Indies-0.205
ドラ-0.203
 goof-0.203
 サ-0.202
Token:
Token ID25
Feature activation-3.59e-01

Pos logit contributions
orthern+0.586
imir+0.583
etsk+0.573
oline+0.570
oslav+0.562
Neg logit contributions
 dise-0.522
 Indies-0.484
ドラ-0.482
 goof-0.481
 サ-0.478
Token Game
Token ID3776
Feature activation-1.08e-01

Pos logit contributions
 dise+0.762
 Indies+0.706
 goof+0.700
 サ+0.699
ドラ+0.694
Neg logit contributions
orthern-1.063
imir-1.050
etsk-1.038
oline-1.031
oslav-1.019
TokenFAQ
Token ID42680
Feature activation-1.83e+00

Pos logit contributions
 dise+0.252
 Indies+0.234
ドラ+0.234
 goof+0.234
 サ+0.229
Neg logit contributions
orthern-0.297
imir-0.293
etsk-0.291
oslav-0.283
oline-0.283
Tokens
Token ID82
Feature activation-5.68e-01

Pos logit contributions
 dise+2.403
 Indies+2.261
 goof+2.084
ドラ+2.073
 サ+2.053
Neg logit contributions
orthern-6.838
etsk-6.745
oline-6.596
imir-6.594
VIDIA-6.436
Token
Token ID198
Feature activation+1.81e-01

Pos logit contributions
 dise+1.346
 Indies+1.274
 goof+1.257
 サ+1.252
ドラ+1.247
Neg logit contributions
orthern-1.539
imir-1.517
etsk-1.488
oline-1.487
oslav-1.471
Token
Token ID198
Feature activation+3.24e-01

Pos logit contributions
orthern+0.521
etsk+0.507
imir+0.507
VIDIA+0.493
oline+0.493
Neg logit contributions
 dise-0.406
 Indies-0.385
 goof-0.378
 サ-0.372
ドラ-0.372
TokenThe
Token ID464
Feature activation-1.28e-01

Pos logit contributions
orthern+0.820
imir+0.809
etsk+0.797
oline+0.787
oslav+0.781
Neg logit contributions
 dise-0.827
 Indies-0.782
ドラ-0.780
 goof-0.768
 サ-0.766
Token focus
Token ID2962
Feature activation-3.25e-01

Pos logit contributions
 dise+0.284
 Indies+0.263
 goof+0.261
 サ+0.258
ドラ+0.258
Neg logit contributions
orthern-0.366
imir-0.364
etsk-0.358
oline-0.356
oslav-0.353
Token agent
Token ID5797
Feature activation-3.45e-01

Pos logit contributions
orthern+0.018
imir+0.017
etsk+0.017
oslav+0.017
oline+0.017
Neg logit contributions
 dise-0.014
 goof-0.013
 Indies-0.013
ドラ-0.013
 サ-0.013
Token,
Token ID11
Feature activation-1.39e-01

Pos logit contributions
 dise+0.802
 goof+0.739
 Indies+0.737
ドラ+0.730
 サ+0.728
Neg logit contributions
orthern-0.960
imir-0.950
etsk-0.938
oslav-0.919
oline-0.918
Token also
Token ID635
Feature activation-1.01e-01

Pos logit contributions
 dise+0.295
 Indies+0.269
 goof+0.269
ドラ+0.265
 サ+0.264
Neg logit contributions
orthern-0.414
imir-0.409
etsk-0.405
oline-0.398
oslav-0.397
Token showed
Token ID3751
Feature activation+1.23e-01

Pos logit contributions
 dise+0.218
 goof+0.199
 Indies+0.198
ドラ+0.196
 サ+0.195
Neg logit contributions
orthern-0.301
imir-0.298
etsk-0.294
oline-0.290
oslav-0.289
Token an
Token ID281
Feature activation-3.12e-01

Pos logit contributions
orthern+0.359
imir+0.354
etsk+0.352
oline+0.346
oslav+0.345
Neg logit contributions
 dise-0.270
 Indies-0.246
 goof-0.246
 サ-0.244
ドラ-0.243
Token anx
Token ID7296
Feature activation-1.82e+00

Pos logit contributions
 dise+0.666
 goof+0.604
 Indies+0.604
 サ+0.602
ドラ+0.598
Neg logit contributions
orthern-0.928
etsk-0.913
imir-0.911
oslav-0.888
oline-0.884
Tokenio
Token ID952
Feature activation-1.81e-01

Pos logit contributions
 dise+4.355
ドラ+3.999
 goof+3.994
 Indies+3.967
 Barr+3.902
Neg logit contributions
orthern-4.590
etsk-4.449
imir-4.434
VIDIA-4.385
oslav-4.290
Tokenly
Token ID306
Feature activation-5.44e-02

Pos logit contributions
 dise+0.726
 Indies+0.690
ドラ+0.687
 サ+0.685
 goof+0.682
Neg logit contributions
orthern-0.191
etsk-0.188
imir-0.188
VIDIA-0.169
oline-0.164
Tokentic
Token ID13370
Feature activation+4.33e-02

Pos logit contributions
 dise+0.168
 Indies+0.157
ドラ+0.157
 goof+0.157
 サ+0.156
Neg logit contributions
orthern-0.109
imir-0.108
etsk-0.106
oline-0.104
oslav-0.103
Token effect
Token ID1245
Feature activation+1.72e-01

Pos logit contributions
orthern+0.118
imir+0.116
etsk+0.116
oline+0.113
oslav+0.113
Neg logit contributions
 dise-0.104
 goof-0.096
 Indies-0.095
 サ-0.094
ドラ-0.094
Token in
Token ID287
Feature activation-1.39e-01

Pos logit contributions
orthern+0.505
imir+0.502
etsk+0.494
oline+0.490
oslav+0.486
Neg logit contributions
 dise-0.372
 Indies-0.341
 goof-0.340
ドラ-0.337
 サ-0.336
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
orthern+0.681
imir+0.678
etsk+0.667
oline+0.665
oslav+0.657
Neg logit contributions
 dise-0.475
 goof-0.434
 Indies-0.433
ドラ-0.428
 サ-0.427
Token As
Token ID1081
Feature activation-3.14e-01

Pos logit contributions
 dise+0.047
 Indies+0.044
 サ+0.044
 goof+0.043
ドラ+0.043
Neg logit contributions
orthern-0.058
imir-0.057
etsk-0.057
oline-0.055
oslav-0.055
Token a
Token ID257
Feature activation-4.82e-01

Pos logit contributions
 dise+0.641
 Indies+0.584
 goof+0.582
 サ+0.568
 Barr+0.562
Neg logit contributions
orthern-0.963
imir-0.948
etsk-0.944
oline-0.930
oslav-0.918
Token matter
Token ID2300
Feature activation-8.61e-02

Pos logit contributions
 dise+1.162
 goof+1.084
 Indies+1.068
 サ+1.037
 Barr+1.026
Neg logit contributions
orthern-1.296
imir-1.295
etsk-1.282
oline-1.254
oslav-1.244
Token of
Token ID286
Feature activation-7.52e-02

Pos logit contributions
 dise+0.168
 goof+0.156
 Indies+0.154
 サ+0.150
 Barr+0.148
Neg logit contributions
orthern-0.269
imir-0.268
etsk-0.266
oline-0.264
oslav-0.258
Token fact
Token ID1109
Feature activation-1.82e+00

Pos logit contributions
 dise+0.103
 goof+0.090
 Indies+0.089
ドラ+0.086
 サ+0.086
Neg logit contributions
orthern-0.280
imir-0.279
etsk-0.277
oline-0.275
oslav-0.273
Token,
Token ID11
Feature activation-3.49e-01

Pos logit contributions
 dise+4.188
 goof+3.854
 Indies+3.836
 サ+3.822
ドラ+3.787
Neg logit contributions
orthern-4.941
imir-4.922
etsk-4.862
oline-4.777
oslav-4.775
Token we
Token ID356
Feature activation-2.07e-01

Pos logit contributions
 dise+0.715
 goof+0.650
 Indies+0.649
 サ+0.638
 Barr+0.622
Neg logit contributions
orthern-1.073
imir-1.057
etsk-1.052
oline-1.033
oslav-1.026
Token went
Token ID1816
Feature activation+2.91e-01

Pos logit contributions
 dise+0.433
 goof+0.400
 Indies+0.394
 サ+0.391
ドラ+0.387
Neg logit contributions
orthern-0.620
imir-0.616
etsk-0.610
oline-0.605
oslav-0.596
Token through
Token ID832
Feature activation+1.67e-01

Pos logit contributions
orthern+0.815
imir+0.810
etsk+0.796
oline+0.792
oslav+0.781
Neg logit contributions
 dise-0.668
 goof-0.615
 Indies-0.615
ドラ-0.607
 サ-0.607
Token 251
Token ID34489
Feature activation+3.53e-01

Pos logit contributions
orthern+0.504
imir+0.500
etsk+0.493
oline+0.491
oslav+0.484
Neg logit contributions
 dise-0.346
 Indies-0.316
 goof-0.315
 サ-0.312
ドラ-0.311
Token lightsaber
Token ID45282
Feature activation+1.04e+00

Pos logit contributions
orthern+0.773
imir+0.767
etsk+0.755
oline+0.750
oslav+0.743
Neg logit contributions
 dise-0.606
 Indies-0.557
 goof-0.557
ドラ-0.552
 サ-0.548
Token as
Token ID355
Feature activation-2.38e-01

Pos logit contributions
orthern+2.859
imir+2.844
etsk+2.795
oline+2.788
oslav+2.746
Neg logit contributions
 dise-2.414
ドラ-2.247
 Indies-2.240
 サ-2.219
 goof-2.214
Token the
Token ID262
Feature activation+4.44e-02

Pos logit contributions
 dise+0.511
 goof+0.469
 Indies+0.467
ドラ+0.460
 サ+0.458
Neg logit contributions
orthern-0.704
imir-0.696
etsk-0.688
oline-0.686
oslav-0.681
Token
Token ID564
Feature activation+1.16e-02

Pos logit contributions
orthern+0.129
imir+0.127
etsk+0.125
oline+0.125
oslav+0.124
Neg logit contributions
 dise-0.099
 goof-0.092
 Indies-0.091
ドラ-0.088
 サ-0.088
Token
Token ID250
Feature activation+3.43e-02

Pos logit contributions
orthern+0.031
imir+0.031
etsk+0.030
oline+0.030
oslav+0.030
Neg logit contributions
 dise-0.028
ドラ-0.026
 Indies-0.026
 goof-0.026
 サ-0.026
TokenHar
Token ID13587
Feature activation-1.82e+00

Pos logit contributions
orthern+0.088
imir+0.087
etsk+0.086
oline+0.086
oslav+0.085
Neg logit contributions
 dise-0.086
 Indies-0.080
ドラ-0.080
 goof-0.080
 サ-0.079
Tokenlem
Token ID10671
Feature activation-2.68e-01

Pos logit contributions
 dise+4.733
 Indies+4.518
 goof+4.464
 Barr+4.376
 Rosenthal+4.373
Neg logit contributions
orthern-4.230
etsk-4.163
imir-4.048
oline-4.000
oslav-3.993
Token Shake
Token ID41113
Feature activation+3.58e-01

Pos logit contributions
 dise+0.537
 Indies+0.495
 goof+0.489
ドラ+0.485
 サ+0.481
Neg logit contributions
imir-0.820
orthern-0.815
etsk-0.813
oline-0.800
oslav-0.799
Token
Token ID447
Feature activation-8.21e-01

Pos logit contributions
orthern+0.947
imir+0.935
etsk+0.927
oline+0.917
oslav+0.910
Neg logit contributions
 dise-0.880
 Indies-0.816
 goof-0.813
ドラ-0.812
 サ-0.806
Token
Token ID251
Feature activation-1.56e-01

Pos logit contributions
 dise+1.823
 goof+1.676
 Indies+1.672
ドラ+1.669
 サ+1.649
Neg logit contributions
orthern-2.336
imir-2.320
etsk-2.278
oline-2.276
oslav-2.249
Token bl
Token ID698
Feature activation-3.62e-01

Pos logit contributions
 dise+0.361
 goof+0.332
 Indies+0.332
ドラ+0.332
 サ+0.328
Neg logit contributions
orthern-0.430
imir-0.425
etsk-0.421
oline-0.419
oslav-0.416
Token explain
Token ID4727
Feature activation+1.24e-01

Pos logit contributions
 dise+0.581
 goof+0.539
 Indies+0.537
 サ+0.530
ドラ+0.526
Neg logit contributions
orthern-0.757
imir-0.751
etsk-0.735
oline-0.731
oslav-0.729
Token the
Token ID262
Feature activation+1.68e-01

Pos logit contributions
orthern+0.378
imir+0.375
etsk+0.370
oline+0.369
oslav+0.365
Neg logit contributions
 dise-0.252
 goof-0.230
 Indies-0.230
ドラ-0.228
 サ-0.227
Token decision
Token ID2551
Feature activation-5.49e-01

Pos logit contributions
orthern+0.465
imir+0.464
etsk+0.454
oline+0.453
oslav+0.449
Neg logit contributions
 dise-0.391
 goof-0.363
 Indies-0.359
 サ-0.354
ドラ-0.353
Token.
Token ID13
Feature activation-3.17e-02

Pos logit contributions
 dise+1.347
 goof+1.264
 Indies+1.247
 サ+1.244
ドラ+1.234
Neg logit contributions
orthern-1.434
imir-1.428
oline-1.410
etsk-1.404
oslav-1.390
Token In
Token ID554
Feature activation-1.21e-01

Pos logit contributions
 dise+0.071
 Indies+0.067
 サ+0.066
 goof+0.066
ドラ+0.066
Neg logit contributions
orthern-0.091
imir-0.089
etsk-0.088
oline-0.087
oslav-0.087
Token fact
Token ID1109
Feature activation-1.81e+00

Pos logit contributions
 dise+0.240
 goof+0.219
 Indies+0.218
ドラ+0.216
 サ+0.216
Neg logit contributions
orthern-0.375
imir-0.372
etsk-0.367
oline-0.365
oslav-0.361
Token,
Token ID11
Feature activation-6.33e-01

Pos logit contributions
 dise+4.365
 Indies+4.044
 goof+4.036
ドラ+4.033
 サ+4.008
Neg logit contributions
orthern-4.804
imir-4.780
etsk-4.697
oline-4.674
oslav-4.618
Token Trump
Token ID1301
Feature activation-1.78e-01

Pos logit contributions
 dise+1.249
 goof+1.145
 Indies+1.138
 サ+1.117
 Rosenthal+1.108
Neg logit contributions
orthern-1.973
imir-1.953
etsk-1.927
oline-1.918
oslav-1.906
Token
Token ID447
Feature activation-1.62e-01

Pos logit contributions
 dise+0.378
 goof+0.355
 Indies+0.347
 サ+0.345
ドラ+0.345
Neg logit contributions
orthern-0.527
imir-0.518
etsk-0.513
oline-0.510
oslav-0.509
Token
Token ID247
Feature activation-7.11e-04

Pos logit contributions
 dise+0.356
 goof+0.334
 Indies+0.330
ドラ+0.329
 Barr+0.325
Neg logit contributions
orthern-0.462
imir-0.455
etsk-0.452
oline-0.447
oslav-0.441
Tokens
Token ID82
Feature activation-2.45e-01

Pos logit contributions
 dise+0.001
 goof+0.001
 Indies+0.001
ドラ+0.001
 サ+0.001
Neg logit contributions
orthern-0.003
imir-0.003
etsk-0.003
oline-0.002
oslav-0.002
Token a
Token ID257
Feature activation+1.70e-01

Pos logit contributions
 dise+0.036
 goof+0.033
 Indies+0.033
ドラ+0.032
 サ+0.032
Neg logit contributions
orthern-0.050
imir-0.049
etsk-0.049
oline-0.048
oslav-0.048
Token benz
Token ID39601
Feature activation+6.13e-01

Pos logit contributions
orthern+0.547
imir+0.541
etsk+0.541
oslav+0.530
oline+0.527
Neg logit contributions
 dise-0.323
 goof-0.291
 Indies-0.289
ドラ-0.287
 サ-0.286
Tokenod
Token ID375
Feature activation+7.12e-01

Pos logit contributions
orthern+1.455
imir+1.433
etsk+1.417
oline+1.386
oslav+1.384
Neg logit contributions
 dise-1.664
 Indies-1.556
ドラ-1.552
 goof-1.549
 サ-1.540
Tokeniazep
Token ID48826
Feature activation-8.12e-01

Pos logit contributions
orthern+0.965
imir+0.933
etsk+0.919
oslav+0.886
oline+0.877
Neg logit contributions
 dise-2.658
 Indies-2.546
 goof-2.526
ドラ-2.521
 サ-2.516
Tokenine
Token ID500
Feature activation-2.51e-01

Pos logit contributions
 dise+2.411
 Indies+2.257
 サ+2.248
 goof+2.248
ドラ+2.243
Neg logit contributions
orthern-1.704
imir-1.669
etsk-1.651
oslav-1.613
VIDIA-1.514
Token anx
Token ID7296
Feature activation-1.81e+00

Pos logit contributions
 dise+0.571
 goof+0.525
 Indies+0.522
ドラ+0.517
 サ+0.517
Neg logit contributions
orthern-0.711
imir-0.702
etsk-0.700
oslav-0.682
oline-0.675
Tokenio
Token ID952
Feature activation-2.10e-01

Pos logit contributions
 dise+4.340
ドラ+4.092
 goof+4.033
 Indies+3.968
 Barr+3.909
Neg logit contributions
orthern-4.644
etsk-4.474
imir-4.404
oslav-4.347
VIDIA-4.342
Tokenly
Token ID306
Feature activation-1.71e-01

Pos logit contributions
 dise+0.834
 Indies+0.789
ドラ+0.789
 サ+0.787
 PARK+0.784
Neg logit contributions
orthern-0.234
etsk-0.226
imir-0.225
oslav-0.197
ewater-0.195
Tokentic
Token ID13370
Feature activation+6.26e-03

Pos logit contributions
 dise+0.514
ドラ+0.482
 Indies+0.480
 goof+0.476
 サ+0.474
Neg logit contributions
orthern-0.359
imir-0.358
etsk-0.350
oslav-0.342
oline-0.334
Token agent
Token ID5797
Feature activation-3.45e-01

Pos logit contributions
orthern+0.018
imir+0.017
etsk+0.017
oslav+0.017
oline+0.017
Neg logit contributions
 dise-0.014
 goof-0.013
 Indies-0.013
ドラ-0.013
 サ-0.013
Token,
Token ID11
Feature activation-1.39e-01

Pos logit contributions
 dise+0.802
 goof+0.739
 Indies+0.737
ドラ+0.730
 サ+0.728
Neg logit contributions
orthern-0.960
imir-0.950
etsk-0.938
oslav-0.919
oline-0.918
Token Every
Token ID3887
Feature activation+4.61e-01

Pos logit contributions
orthern+0.330
imir+0.324
etsk+0.322
oline+0.316
oslav+0.314
Neg logit contributions
 dise-0.283
 Indies-0.267
 サ-0.262
 goof-0.262
ドラ-0.261
Token time
Token ID640
Feature activation-5.66e-02

Pos logit contributions
orthern+1.348
imir+1.342
etsk+1.322
oline+1.315
oslav+1.299
Neg logit contributions
 dise-0.999
 Indies-0.916
 goof-0.915
ドラ-0.908
 サ-0.902
Token it
Token ID340
Feature activation-1.95e-01

Pos logit contributions
 dise+0.118
 Indies+0.108
 goof+0.108
ドラ+0.106
 サ+0.106
Neg logit contributions
orthern-0.170
imir-0.169
etsk-0.167
oline-0.165
oslav-0.164
Token sent
Token ID1908
Feature activation-1.57e-01

Pos logit contributions
 dise+0.419
 goof+0.384
 Indies+0.384
ドラ+0.380
 サ+0.378
Neg logit contributions
orthern-0.576
imir-0.570
etsk-0.562
oline-0.560
oslav-0.554
Token a
Token ID257
Feature activation+4.70e-02

Pos logit contributions
 dise+0.347
 goof+0.317
 Indies+0.315
ドラ+0.314
 サ+0.312
Neg logit contributions
orthern-0.454
imir-0.452
etsk-0.446
oline-0.442
oslav-0.437
Token cor
Token ID1162
Feature activation-1.81e+00

Pos logit contributions
orthern+0.139
imir+0.139
etsk+0.137
oline+0.136
oslav+0.135
Neg logit contributions
 dise-0.100
 goof-0.091
 Indies-0.091
ドラ-0.090
 サ-0.089
Tokenonal
Token ID20996
Feature activation-5.15e-02

Pos logit contributions
 dise+4.562
 goof+4.415
 Indies+4.282
 サ+4.240
 Rosenthal+4.222
Neg logit contributions
imir-4.303
orthern-4.182
etsk-4.150
oline-4.000
 Dragonbound-3.963
Token mass
Token ID2347
Feature activation-1.45e-01

Pos logit contributions
 dise+0.120
 goof+0.111
 Indies+0.108
 サ+0.107
ドラ+0.106
Neg logit contributions
orthern-0.144
imir-0.143
etsk-0.142
oslav-0.140
oline-0.139
Token eject
Token ID22189
Feature activation-6.06e-01

Pos logit contributions
 dise+0.276
 goof+0.253
 サ+0.245
 Indies+0.239
ドラ+0.238
Neg logit contributions
orthern-0.471
imir-0.459
oline-0.456
oslav-0.456
etsk-0.455
Tokenion
Token ID295
Feature activation-3.73e-01

Pos logit contributions
 dise+0.950
 goof+0.860
 Indies+0.828
 ROCK+0.794
 サ+0.787
Neg logit contributions
orthern-2.135
imir-2.105
etsk-2.094
oslav-2.068
oline-2.033
Token (
Token ID357
Feature activation-3.42e-01

Pos logit contributions
 dise+0.885
 goof+0.820
 Indies+0.815
ドラ+0.804
 サ+0.798
Neg logit contributions
orthern-1.016
imir-1.012
etsk-0.995
oline-0.985
oslav-0.980
Token are
Token ID389
Feature activation-5.99e-01

Pos logit contributions
 dise+1.751
 goof+1.593
 Indies+1.587
 サ+1.545
ドラ+1.541
Neg logit contributions
orthern-3.206
imir-3.167
etsk-3.138
oline-3.110
oslav-3.083
Token."
Token ID526
Feature activation+6.22e-01

Pos logit contributions
 dise+1.447
 goof+1.353
 Indies+1.343
 サ+1.311
ドラ+1.302
Neg logit contributions
orthern-1.611
imir-1.590
etsk-1.562
oline-1.553
oslav-1.529
Token
Token ID198
Feature activation-3.55e-01

Pos logit contributions
imir+1.576
orthern+1.566
oline+1.540
etsk+1.536
oslav+1.510
Neg logit contributions
 dise-1.577
ドラ-1.465
 goof-1.456
 Indies-1.449
 サ-1.437
Token
Token ID198
Feature activation-1.60e-01

Pos logit contributions
 dise+0.735
 Indies+0.703
 goof+0.686
 Barr+0.672
 PARK+0.671
Neg logit contributions
orthern-1.075
VIDIA-1.046
etsk-1.043
imir-1.035
 tremend-1.025
TokenIn
Token ID818
Feature activation-4.83e-02

Pos logit contributions
 dise+0.391
ドラ+0.371
 Indies+0.370
 goof+0.365
 サ+0.362
Neg logit contributions
orthern-0.419
imir-0.408
etsk-0.404
oline-0.398
oslav-0.397
Token fact
Token ID1109
Feature activation-1.80e+00

Pos logit contributions
 dise+0.094
 Indies+0.086
 goof+0.086
ドラ+0.085
 サ+0.084
Neg logit contributions
orthern-0.152
imir-0.151
etsk-0.149
oline-0.148
oslav-0.146
Token,
Token ID11
Feature activation-5.54e-01

Pos logit contributions
 dise+4.394
 Indies+4.083
ドラ+4.066
 goof+4.063
 サ+4.037
Neg logit contributions
orthern-4.724
imir-4.696
etsk-4.614
oline-4.593
oslav-4.530
Token the
Token ID262
Feature activation-1.64e-01

Pos logit contributions
 dise+1.128
 goof+1.035
 Indies+1.033
 サ+1.013
 Rosenthal+0.999
Neg logit contributions
orthern-1.693
imir-1.676
etsk-1.660
oline-1.651
oslav-1.636
Token GW
Token ID27164
Feature activation+1.39e-01

Pos logit contributions
 dise+0.369
 goof+0.340
 Indies+0.338
 サ+0.333
ドラ+0.330
Neg logit contributions
orthern-0.466
imir-0.464
etsk-0.458
oline-0.454
oslav-0.451
Token Batt
Token ID12350
Feature activation+5.73e-01

Pos logit contributions
orthern+0.384
imir+0.380
etsk+0.377
oline+0.373
oslav+0.371
Neg logit contributions
 dise-0.324
 goof-0.302
 Indies-0.300
 サ-0.296
ドラ-0.294
Tokenleground
Token ID28272
Feature activation-8.26e-01

Pos logit contributions
orthern+1.400
imir+1.378
etsk+1.374
oline+1.350
oslav+1.333
Neg logit contributions
 dise-1.515
 goof-1.420
 Indies-1.409
 サ-1.394
ドラ-1.394
Token to
Token ID284
Feature activation+1.73e-01

Pos logit contributions
orthern+0.581
imir+0.578
etsk+0.568
oline+0.566
oslav+0.558
Neg logit contributions
 dise-0.451
 Indies-0.416
ドラ-0.415
 goof-0.413
 サ-0.411
Token a
Token ID257
Feature activation+2.84e-01

Pos logit contributions
orthern+0.511
imir+0.508
etsk+0.501
oline+0.498
oslav+0.492
Neg logit contributions
 dise-0.367
 Indies-0.337
ドラ-0.335
 goof-0.335
 サ-0.333
Token party
Token ID2151
Feature activation-3.65e-01

Pos logit contributions
orthern+0.828
imir+0.822
etsk+0.812
oline+0.806
oslav+0.796
Neg logit contributions
 dise-0.619
 Indies-0.567
 goof-0.566
ドラ-0.560
 サ-0.558
Token.
Token ID13
Feature activation+7.70e-02

Pos logit contributions
 dise+0.834
 goof+0.773
 Indies+0.763
 サ+0.746
ドラ+0.738
Neg logit contributions
orthern-1.030
etsk-1.018
imir-1.017
oline-0.994
oslav-0.987
Token But
Token ID887
Feature activation+6.08e-02

Pos logit contributions
orthern+0.220
imir+0.215
etsk+0.215
oline+0.210
oslav+0.209
Neg logit contributions
 dise-0.174
 Indies-0.165
 サ-0.162
 goof-0.161
ドラ-0.160
Token then
Token ID788
Feature activation+1.49e+00

Pos logit contributions
orthern+0.185
imir+0.182
etsk+0.181
oline+0.179
oslav+0.177
Neg logit contributions
 dise-0.127
 Indies-0.117
 goof-0.116
 サ-0.114
ドラ-0.113
Token we
Token ID356
Feature activation+5.25e-01

Pos logit contributions
imir+3.898
orthern+3.897
oline+3.810
etsk+3.791
oslav+3.747
Neg logit contributions
 dise-3.564
ドラ-3.367
 Indies-3.298
 サ-3.278
 goof-3.274
Token hit
Token ID2277
Feature activation-1.85e-01

Pos logit contributions
orthern+1.519
imir+1.511
etsk+1.488
oline+1.481
oslav+1.463
Neg logit contributions
 dise-1.142
ドラ-1.051
 Indies-1.051
 goof-1.042
 サ-1.039
Token the
Token ID262
Feature activation+1.93e-02

Pos logit contributions
 dise+0.390
 Indies+0.358
 goof+0.357
ドラ+0.355
 サ+0.353
Neg logit contributions
orthern-0.551
imir-0.547
etsk-0.540
oline-0.537
oslav-0.530
Token opposite
Token ID6697
Feature activation-8.49e-01

Pos logit contributions
orthern+0.057
imir+0.057
etsk+0.056
oline+0.056
oslav+0.055
Neg logit contributions
 dise-0.041
 Indies-0.037
 goof-0.037
ドラ-0.037
 サ-0.037
Token problem
Token ID1917
Feature activation-6.08e-01

Pos logit contributions
 dise+1.911
 goof+1.767
 Indies+1.753
 サ+1.695
ドラ+1.691
Neg logit contributions
orthern-2.421
imir-2.413
etsk-2.384
oline-2.345
oslav-2.328
Token it
Token ID340
Feature activation+4.09e-03

Pos logit contributions
orthern+1.675
imir+1.669
etsk+1.629
oline+1.626
oslav+1.607
Neg logit contributions
 dise-1.336
ドラ-1.244
 Indies-1.241
 サ-1.233
 goof-1.211
Token,
Token ID11
Feature activation+8.02e-02

Pos logit contributions
orthern+0.011
imir+0.010
etsk+0.010
oline+0.010
oslav+0.010
Neg logit contributions
 dise-0.010
 goof-0.010
 Indies-0.010
ドラ-0.009
 サ-0.009
Token straight
Token ID3892
Feature activation-2.60e-01

Pos logit contributions
orthern+0.244
imir+0.241
etsk+0.240
oline+0.239
oslav+0.235
Neg logit contributions
 dise-0.165
 goof-0.152
 Indies-0.152
 サ-0.149
ドラ-0.148
Token from
Token ID422
Feature activation-1.77e-01

Pos logit contributions
 dise+0.606
 goof+0.574
 Indies+0.565
ドラ+0.564
 サ+0.553
Neg logit contributions
orthern-0.711
imir-0.701
etsk-0.699
oline-0.690
oslav-0.679
Token the
Token ID262
Feature activation+9.60e-02

Pos logit contributions
 dise+0.366
 Indies+0.338
 goof+0.337
ドラ+0.332
 サ+0.331
Neg logit contributions
orthern-0.531
imir-0.529
etsk-0.523
oline-0.520
oslav-0.513
Token horse
Token ID8223
Feature activation+1.14e+00

Pos logit contributions
orthern+0.273
imir+0.271
etsk+0.268
oline+0.266
oslav+0.263
Neg logit contributions
 dise-0.216
 Indies-0.200
 goof-0.200
ドラ-0.197
 サ-0.196
Token's
Token ID338
Feature activation+1.47e-02

Pos logit contributions
orthern+3.060
imir+3.043
etsk+2.991
oline+2.981
oslav+2.937
Neg logit contributions
 dise-2.699
 Indies-2.506
ドラ-2.501
 goof-2.490
 サ-2.481
Token mouth
Token ID5422
Feature activation-5.87e-02

Pos logit contributions
orthern+0.037
imir+0.036
etsk+0.036
oslav+0.035
oline+0.035
Neg logit contributions
 dise-0.039
 goof-0.036
 Indies-0.036
ドラ-0.035
 サ-0.035
Token!
Token ID0
Feature activation-3.96e-01

Pos logit contributions
 dise+0.147
 goof+0.137
 Indies+0.137
ドラ+0.135
 サ+0.134
Neg logit contributions
orthern-0.152
imir-0.151
etsk-0.149
oline-0.147
oslav-0.145
Token Now
Token ID2735
Feature activation+2.99e-01

Pos logit contributions
 dise+0.866
 Indies+0.832
 goof+0.815
 サ+0.815
ドラ+0.802
Neg logit contributions
orthern-1.147
etsk-1.132
imir-1.119
oline-1.107
oslav-1.095
Token,
Token ID11
Feature activation-1.88e-01

Pos logit contributions
orthern+0.873
imir+0.866
etsk+0.858
oline+0.849
oslav+0.842
Neg logit contributions
 dise-0.651
 Indies-0.602
 goof-0.601
ドラ-0.592
 サ-0.591
Token a
Token ID257
Feature activation+1.62e-01

Pos logit contributions
orthern+2.976
imir+2.966
etsk+2.917
oline+2.910
oslav+2.867
Neg logit contributions
 dise-2.085
ドラ-1.928
 Indies-1.918
 サ-1.900
 goof-1.899
Token poet
Token ID21810
Feature activation-3.90e-02

Pos logit contributions
orthern+0.460
imir+0.459
etsk+0.452
oline+0.447
oslav+0.444
Neg logit contributions
 dise-0.369
 goof-0.340
 Indies-0.338
ドラ-0.334
 サ-0.333
Token old
Token ID1468
Feature activation+5.01e-01

Pos logit contributions
 dise+0.088
 goof+0.081
 Indies+0.080
 サ+0.079
ドラ+0.078
Neg logit contributions
orthern-0.111
imir-0.111
etsk-0.109
oline-0.108
oslav-0.107
Token enough
Token ID1576
Feature activation+6.60e-01

Pos logit contributions
orthern+1.287
imir+1.277
etsk+1.256
oline+1.242
oslav+1.223
Neg logit contributions
 dise-1.266
 goof-1.178
 Indies-1.178
ドラ-1.166
 サ-1.164
Token to
Token ID284
Feature activation+2.47e-01

Pos logit contributions
orthern+1.850
imir+1.843
oline+1.802
etsk+1.800
oslav+1.772
Neg logit contributions
 dise-1.473
 Indies-1.370
ドラ-1.370
 サ-1.345
 goof-1.342
Token draw
Token ID3197
Feature activation+1.23e+00

Pos logit contributions
orthern+0.680
imir+0.676
etsk+0.664
oline+0.662
oslav+0.653
Neg logit contributions
 dise-0.577
 goof-0.537
 Indies-0.530
 サ-0.525
ドラ-0.523
Token Social
Token ID5483
Feature activation-5.56e-01

Pos logit contributions
orthern+3.571
imir+3.551
etsk+3.495
oline+3.480
oslav+3.436
Neg logit contributions
 dise-2.658
 Indies-2.446
ドラ-2.436
 goof-2.432
 サ-2.416
Token Security
Token ID4765
Feature activation+2.46e-01

Pos logit contributions
 dise+1.404
 goof+1.296
 Indies+1.296
 サ+1.281
ドラ+1.272
Neg logit contributions
orthern-1.449
etsk-1.406
imir-1.396
oslav-1.360
oline-1.351
Token making
Token ID1642
Feature activation+3.30e-01

Pos logit contributions
orthern+0.693
imir+0.686
etsk+0.678
oline+0.669
oslav+0.664
Neg logit contributions
 dise-0.567
 goof-0.527
 Indies-0.519
ドラ-0.516
 サ-0.516
Token new
Token ID649
Feature activation+3.07e-01

Pos logit contributions
orthern+0.982
imir+0.977
etsk+0.964
oline+0.954
oslav+0.945
Neg logit contributions
 dise-0.699
 Indies-0.643
 goof-0.642
ドラ-0.635
 サ-0.633
Token contracts
Token ID8592
Feature activation+3.17e-01

Pos logit contributions
orthern+0.892
imir+0.888
etsk+0.875
oline+0.863
oslav+0.855
Neg logit contributions
 dise-0.678
 Indies-0.625
 goof-0.625
ドラ-0.615
 サ-0.611
Token
Token ID198
Feature activation+2.03e-01

Pos logit contributions
 dise+0.079
 Indies+0.075
 goof+0.073
 サ+0.072
 Barr+0.071
Neg logit contributions
orthern-0.107
etsk-0.105
imir-0.104
VIDIA-0.103
oslav-0.101
TokenExec
Token ID23002
Feature activation-6.35e-01

Pos logit contributions
orthern+0.520
imir+0.513
etsk+0.509
oline+0.501
oslav+0.495
Neg logit contributions
 dise-0.510
ドラ-0.478
 Indies-0.475
 サ-0.471
 goof-0.470
Tokenut
Token ID315
Feature activation+2.05e-01

Pos logit contributions
 dise+1.030
 Indies+0.925
ドラ+0.908
 goof+0.907
 サ+0.904
Neg logit contributions
orthern-2.189
imir-2.181
etsk-2.150
oline-2.137
oslav-2.114
Tokenors
Token ID669
Feature activation-4.41e-02

Pos logit contributions
orthern+0.531
imir+0.526
oline+0.514
etsk+0.513
oslav+0.506
Neg logit contributions
 dise-0.509
 Indies-0.475
ドラ-0.470
 サ-0.469
 goof-0.469
Token [
Token ID685
Feature activation+3.55e-01

Pos logit contributions
 dise+0.095
 Indies+0.087
 goof+0.086
 サ+0.086
ドラ+0.085
Neg logit contributions
orthern-0.131
imir-0.130
etsk-0.128
oline-0.127
oslav-0.125
Token edit
Token ID4370
Feature activation+1.65e+00

Pos logit contributions
orthern+1.024
imir+1.015
etsk+1.003
oline+0.992
oslav+0.982
Neg logit contributions
 dise-0.789
 Indies-0.725
ドラ-0.725
 goof-0.721
 サ-0.717
Token ]
Token ID2361
Feature activation+1.18e+00

Pos logit contributions
orthern+2.576
imir+2.548
etsk+2.476
oline+2.453
oslav+2.396
Neg logit contributions
 dise-5.787
 Indies-5.505
ドラ-5.489
 goof-5.485
 サ-5.465
Token
Token ID198
Feature activation+4.37e-01

Pos logit contributions
orthern+3.170
imir+3.137
etsk+3.099
oline+3.054
oslav+3.025
Neg logit contributions
 dise-2.853
 Indies-2.667
ドラ-2.644
 goof-2.641
 サ-2.640
Token
Token ID198
Feature activation+5.71e-01

Pos logit contributions
orthern+1.241
imir+1.214
etsk+1.209
oline+1.177
oslav+1.175
Neg logit contributions
 dise-0.997
 Indies-0.938
 goof-0.924
 サ-0.913
ドラ-0.911
TokenSeveral
Token ID14945
Feature activation-7.35e-02

Pos logit contributions
orthern+1.465
imir+1.452
etsk+1.430
oline+1.417
oslav+1.399
Neg logit contributions
 dise-1.437
ドラ-1.339
 Indies-1.338
 goof-1.326
 サ-1.324
Token accounts
Token ID5504
Feature activation+1.43e+00

Pos logit contributions
 dise+0.159
 Indies+0.145
 goof+0.144
ドラ+0.143
 サ+0.143
Neg logit contributions
orthern-0.216
imir-0.215
etsk-0.213
oline-0.210
oslav-0.207
Token January
Token ID3269
Feature activation-1.43e-01

Pos logit contributions
 dise+0.156
 Indies+0.144
 goof+0.144
 PARK+0.141
 サ+0.141
Neg logit contributions
orthern-0.215
etsk-0.214
imir-0.211
oslav-0.208
oline-0.206
Token 15
Token ID1315
Feature activation+5.19e-01

Pos logit contributions
 dise+0.253
 Indies+0.236
 goof+0.231
 サ+0.228
 PARK+0.227
Neg logit contributions
orthern-0.478
etsk-0.472
imir-0.469
oslav-0.460
oline-0.458
Token,
Token ID11
Feature activation+5.08e-01

Pos logit contributions
orthern+1.458
imir+1.438
etsk+1.434
oline+1.395
oslav+1.394
Neg logit contributions
 dise-1.191
 Indies-1.124
 goof-1.105
ドラ-1.095
 サ-1.090
Token 2010
Token ID3050
Feature activation+3.37e-01

Pos logit contributions
orthern+1.391
imir+1.388
oline+1.354
oslav+1.310
ewater+1.303
Neg logit contributions
 dise-1.165
ドラ-1.094
 サ-1.083
 Indies-1.071
 goof-1.051
Token
Token ID198
Feature activation+1.20e+00

Pos logit contributions
orthern+0.956
imir+0.934
etsk+0.934
oline+0.909
oslav+0.907
Neg logit contributions
 dise-0.770
 Indies-0.728
 goof-0.719
 サ-0.710
ドラ-0.705
Token
Token ID198
Feature activation+1.26e+00

Pos logit contributions
orthern+3.100
imir+3.081
etsk+3.027
oline+3.012
oslav+2.969
Neg logit contributions
 dise-2.987
 Indies-2.780
ドラ-2.770
 goof-2.765
 サ-2.750
TokenSubject
Token ID19776
Feature activation-1.38e-03

Pos logit contributions
orthern+2.770
imir+2.749
etsk+2.696
oline+2.673
oslav+2.633
Neg logit contributions
 dise-3.631
 Indies-3.414
ドラ-3.403
 goof-3.402
 サ-3.379
Token:
Token ID25
Feature activation+2.81e-01

Pos logit contributions
 dise+0.003
 Indies+0.003
 goof+0.003
 サ+0.003
ドラ+0.003
Neg logit contributions
orthern-0.004
etsk-0.004
imir-0.004
VIDIA-0.004
oline-0.004
Token Que
Token ID4670
Feature activation+7.98e-01

Pos logit contributions
orthern+0.819
imir+0.814
etsk+0.803
oline+0.797
oslav+0.788
Neg logit contributions
 dise-0.610
 Indies-0.561
 goof-0.559
ドラ-0.555
 サ-0.553
Tokener
Token ID263
Feature activation-4.66e-01

Pos logit contributions
orthern+1.967
imir+1.956
etsk+1.928
oline+1.905
oslav+1.883
Neg logit contributions
 dise-2.100
 Indies-1.949
 goof-1.944
 サ-1.928
ドラ-1.924
Token magnet
Token ID19972
Feature activation+2.72e-01

Pos logit contributions
 dise+1.047
 goof+0.965
 Indies+0.963
 サ+0.933
ドラ+0.923
Neg logit contributions
imir-1.330
orthern-1.329
etsk-1.328
oslav-1.286
oline-1.285
Token
Token ID198
Feature activation-2.04e-01

Pos logit contributions
 dise+2.251
ドラ+2.104
 goof+2.095
 Indies+2.091
 サ+2.077
Neg logit contributions
orthern-2.177
imir-2.174
oline-2.141
etsk-2.128
oslav-2.093
Token
Token ID198
Feature activation+1.54e-01

Pos logit contributions
 dise+0.434
 Indies+0.413
 goof+0.403
 Barr+0.394
 PARK+0.393
Neg logit contributions
orthern-0.609
etsk-0.594
imir-0.590
VIDIA-0.590
oline-0.575
TokenIn
Token ID818
Feature activation+2.77e-02

Pos logit contributions
orthern+0.385
imir+0.381
etsk+0.376
oline+0.371
oslav+0.369
Neg logit contributions
 dise-0.394
 Indies-0.370
ドラ-0.369
 goof-0.365
 サ-0.362
Token the
Token ID262
Feature activation-2.67e-01

Pos logit contributions
orthern+0.082
imir+0.081
etsk+0.080
oline+0.080
oslav+0.078
Neg logit contributions
 dise-0.059
 Indies-0.054
 goof-0.054
ドラ-0.054
 サ-0.053
Token two
Token ID734
Feature activation-1.26e-01

Pos logit contributions
 dise+0.622
 goof+0.575
 Indies+0.575
 サ+0.562
ドラ+0.556
Neg logit contributions
imir-0.736
orthern-0.734
etsk-0.727
oline-0.722
oslav-0.708
Token separate
Token ID4553
Feature activation+7.29e-02

Pos logit contributions
 dise+0.301
 goof+0.280
 Indies+0.279
 サ+0.275
ドラ+0.273
Neg logit contributions
orthern-0.338
imir-0.337
etsk-0.335
oline-0.331
oslav-0.325
Token but
Token ID475
Feature activation+1.39e-01

Pos logit contributions
orthern+0.196
imir+0.195
etsk+0.193
oline+0.191
oslav+0.188
Neg logit contributions
 dise-0.176
 goof-0.164
 Indies-0.163
 サ-0.161
ドラ-0.160
Token related
Token ID3519
Feature activation+5.81e-01

Pos logit contributions
orthern+0.383
imir+0.381
etsk+0.375
oline+0.374
oslav+0.368
Neg logit contributions
 dise-0.325
 Indies-0.300
 goof-0.299
ドラ-0.298
 サ-0.296
Token cases
Token ID2663
Feature activation+8.18e-01

Pos logit contributions
orthern+1.548
imir+1.539
etsk+1.514
oline+1.505
oslav+1.485
Neg logit contributions
 dise-1.406
 Indies-1.304
 goof-1.301
ドラ-1.296
 サ-1.289
Token,
Token ID11
Feature activation+1.08e-01

Pos logit contributions
orthern+2.207
imir+2.192
etsk+2.152
oline+2.144
oslav+2.116
Neg logit contributions
 dise-1.933
ドラ-1.800
 Indies-1.792
 サ-1.777
 goof-1.777
Token the
Token ID262
Feature activation+8.84e-03

Pos logit contributions
orthern+0.322
imir+0.321
etsk+0.317
oline+0.315
oslav+0.312
Neg logit contributions
 dise-0.227
 Indies-0.208
 goof-0.208
ドラ-0.205
 サ-0.205
Token and
Token ID290
Feature activation+1.42e-01

Pos logit contributions
 dise+0.032
 goof+0.029
 Indies+0.029
 サ+0.028
ドラ+0.028
Neg logit contributions
orthern-0.049
imir-0.049
etsk-0.048
oline-0.047
oslav-0.047
Token has
Token ID468
Feature activation-4.79e-02

Pos logit contributions
orthern+0.400
imir+0.395
etsk+0.391
oline+0.386
oslav+0.383
Neg logit contributions
 dise-0.323
 Indies-0.299
 goof-0.296
 サ-0.293
ドラ-0.292
Token always
Token ID1464
Feature activation+1.14e-01

Pos logit contributions
 dise+0.115
 Indies+0.107
 goof+0.107
ドラ+0.106
 サ+0.105
Neg logit contributions
orthern-0.129
imir-0.128
etsk-0.126
oline-0.125
oslav-0.124
Token been
Token ID587
Feature activation-3.26e-01

Pos logit contributions
imir+0.281
orthern+0.281
etsk+0.276
oline+0.275
oslav+0.268
Neg logit contributions
 dise-0.294
ドラ-0.280
 サ-0.275
 Indies-0.273
 goof-0.271
Token a
Token ID257
Feature activation+9.18e-02

Pos logit contributions
 dise+0.673
 Indies+0.620
 goof+0.618
 サ+0.597
ドラ+0.595
Neg logit contributions
orthern-0.994
imir-0.986
etsk-0.972
oline-0.961
oslav-0.956
Token story
Token ID1621
Feature activation+3.32e-01

Pos logit contributions
orthern+0.267
imir+0.266
etsk+0.263
oline+0.259
oslav+0.259
Neg logit contributions
 dise-0.202
 goof-0.188
 Indies-0.187
ドラ-0.182
 サ-0.181
Token-
Token ID12
Feature activation+3.14e-01

Pos logit contributions
orthern+0.981
imir+0.977
etsk+0.967
oline+0.955
oslav+0.946
Neg logit contributions
 dise-0.709
 Indies-0.651
 goof-0.649
ドラ-0.642
 サ-0.637
Tokenfirst
Token ID11085
Feature activation+3.76e-01

Pos logit contributions
orthern+0.720
imir+0.718
etsk+0.710
oline+0.695
oslav+0.687
Neg logit contributions
 dise-0.875
 Indies-0.824
 goof-0.820
ドラ-0.815
 サ-0.809
Token company
Token ID1664
Feature activation-1.68e-01

Pos logit contributions
orthern+0.999
imir+0.994
etsk+0.983
oline+0.970
oslav+0.964
Neg logit contributions
 dise-0.915
 Indies-0.856
 goof-0.853
ドラ-0.842
 サ-0.836
Token.
Token ID13
Feature activation+2.40e-02

Pos logit contributions
 dise+0.416
 goof+0.388
 Indies+0.386
 サ+0.380
ドラ+0.378
Neg logit contributions
orthern-0.439
imir-0.439
etsk-0.430
oline-0.426
oslav-0.421
Token Everything
Token ID11391
Feature activation+4.88e-01

Pos logit contributions
orthern+0.068
etsk+0.067
imir+0.067
oline+0.065
oslav+0.065
Neg logit contributions
 dise-0.054
 Indies-0.052
 サ-0.051
 goof-0.050
 PARK-0.050
TokenExcept
Token ID30313
Feature activation+1.28e+00

Pos logit contributions
orthern+0.223
imir+0.219
etsk+0.216
oline+0.214
oslav+0.212
Neg logit contributions
 dise-0.220
ドラ-0.208
 Indies-0.206
 goof-0.204
 サ-0.204
Token,
Token ID11
Feature activation+4.44e-01

Pos logit contributions
orthern+3.710
imir+3.693
etsk+3.627
oline+3.622
oslav+3.568
Neg logit contributions
 dise-2.784
ドラ-2.568
 Indies-2.564
 goof-2.530
 サ-2.525
Token that
Token ID326
Feature activation+1.93e-01

Pos logit contributions
orthern+1.323
imir+1.313
etsk+1.295
oline+1.289
oslav+1.273
Neg logit contributions
 dise-0.937
 Indies-0.859
 goof-0.857
ドラ-0.852
 サ-0.848
Token is
Token ID318
Feature activation+3.35e-01

Pos logit contributions
orthern+0.555
imir+0.548
etsk+0.542
oline+0.539
oslav+0.533
Neg logit contributions
 dise-0.431
 goof-0.396
 Indies-0.395
ドラ-0.394
 サ-0.392
Token,
Token ID11
Feature activation+2.12e-01

Pos logit contributions
orthern+0.961
imir+0.954
etsk+0.940
oline+0.935
oslav+0.924
Neg logit contributions
 dise-0.746
 Indies-0.685
 goof-0.684
ドラ-0.681
 サ-0.678
Token for
Token ID329
Feature activation+2.31e-02

Pos logit contributions
orthern+0.645
imir+0.640
etsk+0.632
oline+0.629
oslav+0.621
Neg logit contributions
 dise-0.437
 Indies-0.400
 goof-0.399
ドラ-0.396
 サ-0.395
Token Michael
Token ID3899
Feature activation-3.99e-01

Pos logit contributions
orthern+0.070
imir+0.070
etsk+0.069
oline+0.069
oslav+0.068
Neg logit contributions
 dise-0.047
 goof-0.043
 Indies-0.043
ドラ-0.043
 サ-0.043
Token Ign
Token ID16583
Feature activation-3.48e-01

Pos logit contributions
 dise+0.802
 Indies+0.737
 goof+0.735
ドラ+0.728
 Barr+0.727
Neg logit contributions
orthern-1.221
imir-1.209
etsk-1.207
oline-1.178
oslav-1.170
Tokenat
Token ID265
Feature activation+8.68e-01

Pos logit contributions
 dise+0.855
 Indies+0.803
 サ+0.801
 goof+0.800
 Rosenthal+0.784
Neg logit contributions
orthern-0.892
imir-0.889
etsk-0.875
oline-0.857
oslav-0.844
Tokenie
Token ID494
Feature activation+2.36e-01

Pos logit contributions
orthern+2.575
imir+2.550
etsk+2.519
oline+2.513
oslav+2.480
Neg logit contributions
 dise-1.835
ドラ-1.683
 Indies-1.681
 goof-1.680
 サ-1.679
Tokenff
Token ID487
Feature activation+1.38e-01

Pos logit contributions
orthern+0.719
imir+0.701
etsk+0.684
oline+0.682
oslav+0.674
Neg logit contributions
 dise-0.505
 サ-0.468
 Indies-0.467
 goof-0.467
 Rosenthal-0.461
Token completely
Token ID3190
Feature activation+5.97e-01

Pos logit contributions
orthern+0.221
imir+0.219
etsk+0.216
oline+0.213
oslav+0.211
Neg logit contributions
 dise-0.188
 goof-0.172
 Indies-0.172
 サ-0.170
ドラ-0.169
Token.
Token ID13
Feature activation-1.71e-02

Pos logit contributions
orthern+1.485
imir+1.476
etsk+1.445
oline+1.434
oslav+1.413
Neg logit contributions
 dise-1.571
 Indies-1.459
 goof-1.457
 サ-1.441
ドラ-1.439
Token Still
Token ID7831
Feature activation+3.86e-01

Pos logit contributions
 dise+0.039
 Indies+0.037
 サ+0.036
 goof+0.036
ドラ+0.036
Neg logit contributions
orthern-0.049
imir-0.048
etsk-0.048
oline-0.047
oslav-0.046
Token,
Token ID11
Feature activation-2.03e-01

Pos logit contributions
orthern+0.945
imir+0.931
etsk+0.903
oline+0.897
oslav+0.893
Neg logit contributions
 dise-0.993
ドラ-0.945
 Indies-0.944
 サ-0.921
 goof-0.920
Token we
Token ID356
Feature activation+1.19e-01

Pos logit contributions
 dise+0.415
 goof+0.377
 Indies+0.374
 サ+0.371
ドラ+0.365
Neg logit contributions
orthern-0.627
imir-0.620
etsk-0.618
oline-0.612
oslav-0.603
Token can
Token ID460
Feature activation+3.29e-01

Pos logit contributions
orthern+0.357
imir+0.354
etsk+0.350
oline+0.347
oslav+0.343
Neg logit contributions
 dise-0.251
 goof-0.232
 Indies-0.229
 サ-0.227
ドラ-0.226
Token
Token ID447
Feature activation-4.99e-02

Pos logit contributions
orthern+0.884
imir+0.876
etsk+0.868
oline+0.865
oslav+0.853
Neg logit contributions
 dise-0.793
 goof-0.742
 Indies-0.730
 サ-0.728
ドラ-0.721
Token
Token ID247
Feature activation-4.99e-02

Pos logit contributions
 dise+0.116
 goof+0.106
 Indies+0.106
ドラ+0.106
 サ+0.105
Neg logit contributions
orthern-0.138
imir-0.137
etsk-0.135
oline-0.134
oslav-0.132
Tokent
Token ID83
Feature activation+2.74e-01

Pos logit contributions
 dise+0.112
 Indies+0.102
 goof+0.102
ドラ+0.102
 サ+0.101
Neg logit contributions
orthern-0.142
imir-0.141
etsk-0.139
oline-0.138
oslav-0.136
Token help
Token ID1037
Feature activation+3.78e-01

Pos logit contributions
orthern+0.763
imir+0.759
etsk+0.746
oline+0.742
oslav+0.732
Neg logit contributions
 dise-0.636
 goof-0.593
 Indies-0.584
 サ-0.580
ドラ-0.574
Token but
Token ID475
Feature activation-2.88e-01

Pos logit contributions
orthern+1.119
imir+1.113
etsk+1.098
oline+1.093
oslav+1.078
Neg logit contributions
 dise-0.809
 goof-0.740
 Indies-0.738
ドラ-0.732
 サ-0.730
Token",
Token ID1600
Feature activation+1.10e-01

Pos logit contributions
orthern+0.186
imir+0.184
etsk+0.180
oline+0.179
oslav+0.177
Neg logit contributions
 dise-0.219
 Indies-0.206
 goof-0.204
ドラ-0.203
 サ-0.202
Token allocated
Token ID19171
Feature activation-2.53e-01

Pos logit contributions
orthern+0.321
imir+0.319
etsk+0.313
oline+0.313
oslav+0.308
Neg logit contributions
 dise-0.240
 Indies-0.221
 goof-0.220
 サ-0.217
ドラ-0.216
Token to
Token ID284
Feature activation-1.73e-01

Pos logit contributions
 dise+0.559
 Indies+0.511
 goof+0.511
 サ+0.502
ドラ+0.498
Neg logit contributions
orthern-0.732
imir-0.726
etsk-0.719
oline-0.712
oslav-0.706
Token states
Token ID2585
Feature activation+2.00e-01

Pos logit contributions
 dise+0.324
 Indies+0.295
 goof+0.291
ドラ+0.289
 サ+0.286
Neg logit contributions
orthern-0.557
imir-0.556
etsk-0.548
oline-0.544
oslav-0.539
Token on
Token ID319
Feature activation+8.56e-01

Pos logit contributions
orthern+0.547
imir+0.546
etsk+0.535
oline+0.530
oslav+0.524
Neg logit contributions
 dise-0.471
 Indies-0.438
 goof-0.434
 サ-0.426
ドラ-0.424
Token the
Token ID262
Feature activation+5.04e-03

Pos logit contributions
orthern+2.472
imir+2.457
etsk+2.416
oline+2.409
oslav+2.375
Neg logit contributions
 dise-1.864
ドラ-1.721
 Indies-1.719
 goof-1.708
 サ-1.701
Token basis
Token ID4308
Feature activation+6.96e-01

Pos logit contributions
orthern+0.012
imir+0.012
etsk+0.011
oline+0.011
oslav+0.011
Neg logit contributions
 dise-0.014
 Indies-0.013
 goof-0.013
 サ-0.013
ドラ-0.013
Token of
Token ID286
Feature activation-1.41e-01

Pos logit contributions
orthern+1.808
imir+1.775
oline+1.762
etsk+1.761
oslav+1.736
Neg logit contributions
 dise-1.710
ドラ-1.616
 goof-1.579
 サ-1.577
 Indies-1.551
Token population
Token ID3265
Feature activation-3.86e-01

Pos logit contributions
 dise+0.300
 Indies+0.274
 goof+0.272
ドラ+0.269
 サ+0.267
Neg logit contributions
orthern-0.420
imir-0.418
etsk-0.413
oline-0.409
oslav-0.404
Token,[
Token ID17414
Feature activation+5.78e-01

Pos logit contributions
 dise+0.979
 goof+0.900
 Indies+0.894
 サ+0.879
ドラ+0.875
Neg logit contributions
orthern-1.003
imir-1.001
etsk-0.981
oline-0.960
oslav-0.954
Token185
Token ID21652
Feature activation-1.00e-01

Pos logit contributions
orthern+1.819
imir+1.816
oline+1.783
etsk+1.782
oslav+1.758
Neg logit contributions
 dise-1.105
 Indies-1.009
ドラ-1.002
 goof-1.001
 サ-0.983
Token a
Token ID257
Feature activation+5.63e-02

Pos logit contributions
orthern+0.553
imir+0.547
etsk+0.546
oline+0.538
oslav+0.533
Neg logit contributions
 dise-0.313
 Indies-0.283
 goof-0.281
 サ-0.275
ドラ-0.270
Token third
Token ID2368
Feature activation+9.58e-02

Pos logit contributions
orthern+0.168
imir+0.166
etsk+0.164
oline+0.162
oslav+0.161
Neg logit contributions
 dise-0.121
 goof-0.110
 Indies-0.110
 サ-0.108
ドラ-0.108
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
orthern+0.253
imir+0.251
etsk+0.247
oline+0.245
oslav+0.242
Neg logit contributions
 dise-0.234
 Indies-0.217
ドラ-0.217
 goof-0.216
 サ-0.215
Token
Token ID198
Feature activation-5.38e-01

Pos logit contributions
 dise+0.380
 Indies+0.366
 サ+0.357
ドラ+0.351
 goof+0.350
Neg logit contributions
orthern-0.474
imir-0.466
etsk-0.464
oslav-0.454
oline-0.453
Token
Token ID198
Feature activation-3.05e-01

Pos logit contributions
 dise+1.099
 Indies+1.049
 goof+1.024
 サ+1.013
 Barr+1.007
Neg logit contributions
orthern-1.635
VIDIA-1.604
etsk-1.593
 tremend-1.576
imir-1.574
TokenGet
Token ID3855
Feature activation-2.45e-01

Pos logit contributions
 dise+0.748
 Indies+0.715
ドラ+0.715
 サ+0.695
 goof+0.689
Neg logit contributions
orthern-0.788
imir-0.773
etsk-0.765
oslav-0.756
oline-0.749
Token our
Token ID674
Feature activation-8.48e-01

Pos logit contributions
 dise+0.510
 Indies+0.466
 goof+0.461
 サ+0.455
 PARK+0.448
Neg logit contributions
orthern-0.734
imir-0.730
etsk-0.729
oline-0.720
oslav-0.705
Token daily
Token ID4445
Feature activation-9.93e-01

Pos logit contributions
 dise+1.826
 goof+1.672
 Indies+1.665
 サ+1.653
ドラ+1.638
Neg logit contributions
orthern-2.493
imir-2.482
etsk-2.461
oline-2.432
oslav-2.392
Token newsletter
Token ID13129
Feature activation-4.24e-01

Pos logit contributions
 dise+2.076
 Indies+1.932
 goof+1.922
ドラ+1.885
 サ+1.883
Neg logit contributions
orthern-2.989
imir-2.985
etsk-2.902
oline-2.864
oslav-2.827
Token Upgrade
Token ID24236
Feature activation-4.80e-02

Pos logit contributions
 dise+0.727
 goof+0.665
 Indies+0.657
 サ+0.654
ドラ+0.644
Neg logit contributions
imir-1.435
orthern-1.423
etsk-1.394
oline-1.386
VIDIA-1.368
Token your
Token ID534
Feature activation-3.73e-01

Pos logit contributions
 dise+0.095
 Indies+0.087
 goof+0.087
 サ+0.084
ドラ+0.084
Neg logit contributions
orthern-0.149
imir-0.149
etsk-0.148
oline-0.145
oslav-0.143
Token (
Token ID357
Feature activation-2.52e-01

Pos logit contributions
orthern+0.175
imir+0.173
etsk+0.170
oline+0.169
oslav+0.167
Neg logit contributions
 dise-0.169
 Indies-0.157
 goof-0.156
ドラ-0.156
 サ-0.155
TokenARM
Token ID33456
Feature activation-4.65e-01

Pos logit contributions
 dise+0.647
ドラ+0.604
 Indies+0.604
 goof+0.600
 サ+0.597
Neg logit contributions
orthern-0.631
imir-0.625
etsk-0.615
oline-0.611
oslav-0.602
Token version
Token ID2196
Feature activation+2.49e-02

Pos logit contributions
 dise+1.361
 Indies+1.280
 goof+1.277
ドラ+1.274
 サ+1.267
Neg logit contributions
orthern-1.002
imir-0.993
etsk-0.977
oline-0.967
oslav-0.950
Token,
Token ID11
Feature activation+3.41e-01

Pos logit contributions
orthern+0.064
imir+0.064
etsk+0.063
oline+0.063
oslav+0.062
Neg logit contributions
 dise-0.061
ドラ-0.057
 Indies-0.057
 goof-0.057
 サ-0.057
Token detected
Token ID12326
Feature activation+3.57e-02

Pos logit contributions
orthern+1.002
imir+0.999
etsk+0.982
oline+0.981
oslav+0.964
Neg logit contributions
 dise-0.715
 Indies-0.661
ドラ-0.660
 サ-0.656
 goof-0.655
Token as
Token ID355
Feature activation-1.72e-01

Pos logit contributions
orthern+0.108
imir+0.106
etsk+0.105
oline+0.104
oslav+0.103
Neg logit contributions
 dise-0.075
 goof-0.070
 Indies-0.069
 サ-0.068
 Rosenthal-0.067
Token EL
Token ID17852
Feature activation+1.76e-01

Pos logit contributions
 dise+0.346
 Indies+0.317
ドラ+0.316
 goof+0.314
 サ+0.312
Neg logit contributions
orthern-0.526
imir-0.524
etsk-0.516
oline-0.514
oslav-0.508
TokenF
Token ID37
Feature activation-2.71e-02

Pos logit contributions
orthern+0.562
etsk+0.552
imir+0.551
oslav+0.539
oline+0.538
Neg logit contributions
 dise-0.335
 Indies-0.312
ドラ-0.308
 goof-0.306
 サ-0.302
Token_
Token ID62
Feature activation+5.85e-02

Pos logit contributions
 dise+0.060
ドラ+0.057
 Indies+0.057
 goof+0.056
 PARK+0.056
Neg logit contributions
orthern-0.078
etsk-0.077
imir-0.076
VIDIA-0.074
oslav-0.074
TokenUM
Token ID5883
Feature activation+4.79e-01

Pos logit contributions
orthern+0.179
imir+0.179
etsk+0.175
oline+0.175
oslav+0.173
Neg logit contributions
 dise-0.118
 Indies-0.108
 goof-0.107
ドラ-0.107
 サ-0.107
TokenRE
Token ID2200
Feature activation-7.54e-01

Pos logit contributions
orthern+1.661
imir+1.633
etsk+1.631
oline+1.602
oslav+1.592
Neg logit contributions
 dise-0.786
 Indies-0.719
ドラ-0.715
 goof-0.702
 PARK-0.697
Token which
Token ID543
Feature activation-5.81e-02

Pos logit contributions
 dise+0.265
 Indies+0.240
 goof+0.240
 サ+0.237
ドラ+0.236
Neg logit contributions
orthern-0.411
imir-0.409
etsk-0.403
oline-0.400
oslav-0.396
Token the
Token ID262
Feature activation+7.60e-02

Pos logit contributions
 dise+0.123
 Indies+0.112
 goof+0.112
 サ+0.111
ドラ+0.111
Neg logit contributions
orthern-0.173
imir-0.172
etsk-0.170
oline-0.168
oslav-0.167
Token components
Token ID6805
Feature activation-1.66e-01

Pos logit contributions
orthern+0.217
imir+0.216
etsk+0.214
oline+0.211
oslav+0.209
Neg logit contributions
 dise-0.172
 goof-0.156
 Indies-0.156
 サ-0.155
ドラ-0.153
Token of
Token ID286
Feature activation-3.63e-01

Pos logit contributions
 dise+0.355
 goof+0.324
 Indies+0.323
 サ+0.319
ドラ+0.315
Neg logit contributions
orthern-0.493
imir-0.491
etsk-0.482
oline-0.477
oslav-0.476
Token the
Token ID262
Feature activation-4.44e-01

Pos logit contributions
 dise+0.776
 Indies+0.701
 goof+0.700
 サ+0.697
ドラ+0.690
Neg logit contributions
orthern-1.080
imir-1.072
etsk-1.066
oline-1.045
oslav-1.037
Token last
Token ID938
Feature activation-4.50e-01

Pos logit contributions
 dise+1.010
 goof+0.905
 サ+0.904
 Indies+0.903
 PARK+0.885
Neg logit contributions
orthern-1.267
etsk-1.261
imir-1.256
oline-1.221
oslav-1.220
Token meal
Token ID9799
Feature activation+1.26e-01

Pos logit contributions
 dise+1.011
 サ+0.915
 goof+0.912
 Indies+0.908
ドラ+0.898
Neg logit contributions
orthern-1.289
etsk-1.282
imir-1.273
oslav-1.236
oline-1.231
Token are
Token ID389
Feature activation-3.95e-01

Pos logit contributions
orthern+0.372
imir+0.368
etsk+0.364
oline+0.359
oslav+0.358
Neg logit contributions
 dise-0.272
 goof-0.250
 Indies-0.249
 サ-0.246
ドラ-0.244
Token still
Token ID991
Feature activation-2.67e-01

Pos logit contributions
 dise+0.888
 goof+0.812
 Indies+0.798
 サ+0.797
 PARK+0.786
Neg logit contributions
orthern-1.139
imir-1.121
etsk-1.114
oline-1.095
oslav-1.092
Token in
Token ID287
Feature activation-1.78e-01

Pos logit contributions
 dise+0.550
 goof+0.497
 Indies+0.492
 サ+0.491
ドラ+0.483
Neg logit contributions
orthern-0.815
imir-0.808
etsk-0.799
oline-0.791
oslav-0.787
Token the
Token ID262
Feature activation-1.98e-01

Pos logit contributions
 dise+0.382
 goof+0.346
 Indies+0.345
 サ+0.343
ドラ+0.339
Neg logit contributions
orthern-0.526
imir-0.526
etsk-0.517
oline-0.510
oslav-0.507
Tokenger
Token ID1362
Feature activation-8.53e-01

Pos logit contributions
 dise+0.952
 Indies+0.924
 goof+0.915
ドラ+0.898
 Rosenthal+0.884
Neg logit contributions
orthern-1.243
imir-1.219
etsk-1.204
oline-1.178
oslav-1.159
Token,
Token ID11
Feature activation-1.58e-01

Pos logit contributions
 dise+1.959
 Indies+1.866
 goof+1.852
ドラ+1.786
 サ+1.783
Neg logit contributions
orthern-2.379
imir-2.326
etsk-2.294
oline-2.269
oslav-2.258
Token even
Token ID772
Feature activation-1.10e-01

Pos logit contributions
 dise+0.331
 goof+0.305
 Indies+0.304
 サ+0.298
ドラ+0.297
Neg logit contributions
orthern-0.475
imir-0.470
oline-0.461
etsk-0.461
oslav-0.456
Token if
Token ID611
Feature activation-2.52e-01

Pos logit contributions
 dise+0.223
 Indies+0.205
 goof+0.204
 サ+0.198
ドラ+0.198
Neg logit contributions
orthern-0.339
imir-0.336
etsk-0.331
oline-0.329
oslav-0.326
Token the
Token ID262
Feature activation+1.84e-01

Pos logit contributions
 dise+0.483
 goof+0.442
 Indies+0.441
 サ+0.428
ドラ+0.426
Neg logit contributions
orthern-0.806
imir-0.800
etsk-0.789
oline-0.784
oslav-0.774
Token subjects
Token ID7481
Feature activation-5.68e-01

Pos logit contributions
orthern+0.529
imir+0.526
etsk+0.518
oline+0.513
oslav+0.510
Neg logit contributions
 dise-0.417
 goof-0.388
 Indies-0.382
 サ-0.374
ドラ-0.372
Token featured
Token ID8096
Feature activation-6.41e-01

Pos logit contributions
 dise+1.121
 goof+1.034
 Indies+1.024
 サ+1.002
ドラ+0.995
Neg logit contributions
orthern-1.775
imir-1.761
oline-1.731
etsk-1.730
oslav-1.707
Token in
Token ID287
Feature activation-3.02e-01

Pos logit contributions
 dise+1.318
 Indies+1.201
 goof+1.201
ドラ+1.183
 サ+1.175
Neg logit contributions
orthern-1.958
imir-1.941
etsk-1.911
oline-1.909
oslav-1.881
Token the
Token ID262
Feature activation-2.12e-01

Pos logit contributions
 dise+0.617
 Indies+0.563
 goof+0.563
ドラ+0.557
 サ+0.553
Neg logit contributions
orthern-0.926
imir-0.920
etsk-0.905
oline-0.904
oslav-0.888
Token images
Token ID4263
Feature activation+3.56e-01

Pos logit contributions
 dise+0.464
 goof+0.430
 Indies+0.420
 サ+0.409
ドラ+0.407
Neg logit contributions
orthern-0.628
imir-0.625
etsk-0.615
oline-0.610
oslav-0.605
Token intended
Token ID5292
Feature activation-3.21e-01

Pos logit contributions
orthern+1.128
imir+1.121
etsk+1.106
oline+1.101
oslav+1.089
Neg logit contributions
 dise-0.681
 Indies-0.620
 goof-0.617
ドラ-0.615
 サ-0.610
Token been
Token ID587
Feature activation+7.51e-02

Pos logit contributions
 dise+0.173
 goof+0.158
 Indies+0.158
 サ+0.155
ドラ+0.155
Neg logit contributions
orthern-0.236
imir-0.234
etsk-0.231
oline-0.229
oslav-0.227
Token doing
Token ID1804
Feature activation-2.24e-01

Pos logit contributions
orthern+0.238
imir+0.236
etsk+0.233
oline+0.232
oslav+0.229
Neg logit contributions
 dise-0.146
 goof-0.132
 Indies-0.132
 サ-0.129
ドラ-0.129
Token the
Token ID262
Feature activation+1.84e-01

Pos logit contributions
 dise+0.450
 goof+0.411
 Indies+0.410
 サ+0.403
ドラ+0.399
Neg logit contributions
orthern-0.694
imir-0.687
etsk-0.680
oline-0.674
oslav-0.667
Token bidding
Token ID23829
Feature activation+8.81e-01

Pos logit contributions
orthern+0.538
imir+0.535
etsk+0.527
oline+0.523
oslav+0.518
Neg logit contributions
 dise-0.399
 Indies-0.367
 goof-0.366
ドラ-0.362
 サ-0.361
Token of
Token ID286
Feature activation+1.08e-01

Pos logit contributions
orthern+2.269
imir+2.236
etsk+2.198
oline+2.188
oslav+2.185
Neg logit contributions
 dise-2.159
ドラ-2.029
 サ-2.000
 goof-1.993
 Indies-1.978
Token corporate
Token ID6355
Feature activation-3.17e-01

Pos logit contributions
orthern+0.333
imir+0.331
etsk+0.327
oline+0.324
oslav+0.321
Neg logit contributions
 dise-0.220
 Indies-0.200
 goof-0.200
 サ-0.197
ドラ-0.196
Token interests
Token ID5353
Feature activation-5.70e-01

Pos logit contributions
 dise+0.664
 goof+0.615
 Indies+0.610
 サ+0.597
ドラ+0.594
Neg logit contributions
orthern-0.941
etsk-0.941
imir-0.940
oline-0.914
oslav-0.912
Token,
Token ID11
Feature activation+4.66e-02

Pos logit contributions
 dise+1.315
 Indies+1.223
 goof+1.217
 サ+1.192
 PARK+1.169
Neg logit contributions
orthern-1.586
imir-1.569
etsk-1.549
oline-1.532
oslav-1.526
Token by
Token ID416
Feature activation-6.38e-02

Pos logit contributions
orthern+0.135
imir+0.134
etsk+0.132
oline+0.131
oslav+0.130
Neg logit contributions
 dise-0.102
 Indies-0.094
 goof-0.094
 サ-0.093
ドラ-0.092
Token fighting
Token ID4330
Feature activation+1.21e-01

Pos logit contributions
 dise+0.123
 goof+0.112
 Indies+0.112
 サ+0.110
ドラ+0.109
Neg logit contributions
orthern-0.202
imir-0.201
etsk-0.198
oline-0.197
oslav-0.195
Token for
Token ID329
Feature activation+4.56e-01

Pos logit contributions
orthern+0.347
imir+0.344
etsk+0.340
oline+0.337
oslav+0.334
Neg logit contributions
 dise-0.271
 Indies-0.249
 goof-0.248
ドラ-0.246
 サ-0.245
Token are
Token ID389
Feature activation-2.23e-01

Pos logit contributions
orthern+0.092
imir+0.092
etsk+0.090
oline+0.090
oslav+0.089
Neg logit contributions
 dise-0.069
 Indies-0.064
 goof-0.064
ドラ-0.063
 サ-0.063
Token unwelcome
Token ID47207
Feature activation-5.79e-01

Pos logit contributions
 dise+0.474
 goof+0.433
 Indies+0.432
 サ+0.422
ドラ+0.420
Neg logit contributions
orthern-0.673
imir-0.664
etsk-0.654
oline-0.652
oslav-0.643
Token in
Token ID287
Feature activation-4.17e-01

Pos logit contributions
 dise+1.220
 Indies+1.117
 goof+1.116
 サ+1.084
ドラ+1.078
Neg logit contributions
orthern-1.737
imir-1.722
etsk-1.697
oline-1.683
oslav-1.654
Token their
Token ID511
Feature activation-1.82e-01

Pos logit contributions
 dise+0.828
 Indies+0.751
 goof+0.748
 サ+0.735
ドラ+0.727
Neg logit contributions
orthern-1.298
imir-1.290
etsk-1.278
oline-1.268
oslav-1.249
Token home
Token ID1363
Feature activation+9.06e-01

Pos logit contributions
 dise+0.434
 Indies+0.399
 goof+0.399
 サ+0.392
ドラ+0.388
Neg logit contributions
orthern-0.498
imir-0.494
etsk-0.491
oline-0.490
oslav-0.480
Token countries
Token ID2678
Feature activation-1.32e+00

Pos logit contributions
orthern+3.016
imir+3.001
etsk+2.959
oline+2.948
oslav+2.917
Neg logit contributions
 dise-1.582
 Indies-1.425
ドラ-1.420
 goof-1.415
 サ-1.404
Token.
Token ID13
Feature activation+1.73e-02

Pos logit contributions
 dise+3.396
 Indies+3.207
 goof+3.157
 サ+3.089
 PARK+3.063
Neg logit contributions
orthern-3.276
imir-3.237
oline-3.167
etsk-3.164
oslav-3.086
Token
Token ID198
Feature activation-4.44e-01

Pos logit contributions
imir+0.041
oline+0.040
orthern+0.040
etsk+0.039
oslav+0.039
Neg logit contributions
 dise-0.047
ドラ-0.044
 goof-0.044
 サ-0.043
 Indies-0.043
Token
Token ID198
Feature activation-2.68e-01

Pos logit contributions
 dise+0.923
 Indies+0.880
 goof+0.856
 Barr+0.841
 PARK+0.836
Neg logit contributions
orthern-1.342
VIDIA-1.309
etsk-1.303
imir-1.297
 tremend-1.280
TokenUS
Token ID2937
Feature activation-4.33e-01

Pos logit contributions
 dise+0.674
 Indies+0.642
ドラ+0.635
 goof+0.627
 サ+0.621
Neg logit contributions
orthern-0.681
imir-0.663
etsk-0.656
oline-0.645
oslav-0.644
Token state
Token ID1181
Feature activation+5.62e-01

Pos logit contributions
 dise+0.871
 Indies+0.806
 goof+0.800
ドラ+0.777
 サ+0.776
Neg logit contributions
orthern-1.332
imir-1.318
etsk-1.302
oline-1.290
oslav-1.279
Token the
Token ID262
Feature activation+2.20e-01

Pos logit contributions
orthern+1.000
imir+0.994
etsk+0.979
oline+0.974
oslav+0.962
Neg logit contributions
 dise-0.755
 Indies-0.695
ドラ-0.693
 goof-0.691
 サ-0.687
Token tactics
Token ID10815
Feature activation-2.87e-01

Pos logit contributions
orthern+0.627
imir+0.623
etsk+0.613
oline+0.609
oslav+0.602
Neg logit contributions
 dise-0.495
 Indies-0.459
 goof-0.457
ドラ-0.453
 サ-0.453
Token learned
Token ID4499
Feature activation-8.59e-01

Pos logit contributions
 dise+0.589
 goof+0.543
 Indies+0.542
 サ+0.535
ドラ+0.525
Neg logit contributions
orthern-0.868
etsk-0.853
imir-0.852
oline-0.842
oslav-0.837
Token in
Token ID287
Feature activation-2.05e-01

Pos logit contributions
 dise+1.872
 goof+1.730
 Indies+1.717
 サ+1.704
ドラ+1.697
Neg logit contributions
orthern-2.490
imir-2.454
oline-2.424
etsk-2.408
oslav-2.397
Token this
Token ID428
Feature activation-2.60e-01

Pos logit contributions
 dise+0.439
 Indies+0.407
 goof+0.403
 サ+0.401
ドラ+0.396
Neg logit contributions
orthern-0.605
imir-0.597
etsk-0.592
oline-0.586
oslav-0.578
Token interview
Token ID2720
Feature activation-1.17e+00

Pos logit contributions
 dise+0.576
 Indies+0.531
 goof+0.530
 サ+0.522
ドラ+0.517
Neg logit contributions
orthern-0.748
imir-0.741
etsk-0.735
oline-0.728
oslav-0.720
Token to
Token ID284
Feature activation-2.83e-01

Pos logit contributions
 dise+2.711
 goof+2.526
 サ+2.507
 Indies+2.502
ドラ+2.450
Neg logit contributions
orthern-3.194
imir-3.141
etsk-3.137
oslav-3.090
oline-3.087
Token create
Token ID2251
Feature activation+4.62e-02

Pos logit contributions
 dise+0.608
 goof+0.564
 Indies+0.561
 サ+0.556
ドラ+0.554
Neg logit contributions
orthern-0.835
imir-0.825
etsk-0.817
oline-0.809
oslav-0.805
Token our
Token ID674
Feature activation-2.74e-01

Pos logit contributions
orthern+0.137
imir+0.136
etsk+0.134
oline+0.134
oslav+0.132
Neg logit contributions
 dise-0.098
 Indies-0.091
 goof-0.090
 サ-0.089
ドラ-0.089
Token own
Token ID898
Feature activation+1.84e-01

Pos logit contributions
 dise+0.583
 Indies+0.540
 goof+0.538
 サ+0.532
ドラ+0.527
Neg logit contributions
orthern-0.817
imir-0.809
etsk-0.801
oline-0.791
oslav-0.785
Token best
Token ID1266
Feature activation+2.14e-01

Pos logit contributions
orthern+0.527
imir+0.523
etsk+0.516
oline+0.512
oslav+0.507
Neg logit contributions
 dise-0.413
 Indies-0.383
 goof-0.380
ドラ-0.378
 サ-0.376
Tokenot
Token ID313
Feature activation+6.49e-01

Pos logit contributions
orthern+3.217
imir+3.180
oline+3.162
etsk+3.132
oslav+3.090
Neg logit contributions
 dise-3.057
 Indies-2.862
ドラ-2.861
 goof-2.838
 サ-2.830
Tokenis
Token ID271
Feature activation+5.49e-01

Pos logit contributions
orthern+1.772
imir+1.762
etsk+1.731
oline+1.724
oslav+1.699
Neg logit contributions
 dise-1.524
 Indies-1.412
ドラ-1.410
 goof-1.405
 サ-1.397
Token group
Token ID1448
Feature activation-4.96e-02

Pos logit contributions
orthern+1.498
imir+1.489
etsk+1.464
oline+1.457
oslav+1.439
Neg logit contributions
 dise-1.291
 Indies-1.196
 goof-1.190
ドラ-1.190
 サ-1.182
Token identifies
Token ID21079
Feature activation-4.28e-01

Pos logit contributions
 dise+0.120
 Indies+0.111
 goof+0.110
ドラ+0.110
 サ+0.110
Neg logit contributions
orthern-0.132
imir-0.132
etsk-0.130
oline-0.129
oslav-0.128
Token additional
Token ID3224
Feature activation-1.48e-01

Pos logit contributions
 dise+0.918
 Indies+0.840
 goof+0.835
 サ+0.825
ドラ+0.824
Neg logit contributions
imir-1.259
orthern-1.258
etsk-1.238
oline-1.234
oslav-1.222
Token tax
Token ID1687
Feature activation-1.47e+00

Pos logit contributions
 dise+0.320
 Indies+0.293
 goof+0.292
 サ+0.289
ドラ+0.289
Neg logit contributions
orthern-0.435
imir-0.434
etsk-0.428
oline-0.425
oslav-0.421
Tokena
Token ID64
Feature activation+9.82e-02

Pos logit contributions
 dise+3.941
 Indies+3.699
 goof+3.678
 サ+3.661
ドラ+3.649
Neg logit contributions
imir-3.430
orthern-3.383
etsk-3.310
oslav-3.256
oline-3.248
Token.
Token ID13
Feature activation-3.00e-01

Pos logit contributions
orthern+0.262
imir+0.262
etsk+0.256
oline+0.255
oslav+0.252
Neg logit contributions
 dise-0.238
 Indies-0.220
 goof-0.219
ドラ-0.218
 サ-0.218
Token Australian
Token ID6638
Feature activation-1.01e+00

Pos logit contributions
 dise+0.572
 Indies+0.525
ドラ+0.518
 サ+0.517
 goof+0.515
Neg logit contributions
orthern-0.951
imir-0.946
etsk-0.937
oline-0.926
oslav-0.920
Token Journal
Token ID4913
Feature activation-3.75e-01

Pos logit contributions
 dise+1.918
 Indies+1.769
 goof+1.726
 サ+1.712
 PARK+1.694
Neg logit contributions
imir-3.199
orthern-3.196
etsk-3.181
oline-3.121
oslav-3.113
Token of
Token ID286
Feature activation-8.08e-02

Pos logit contributions
 dise+0.738
 Indies+0.701
 サ+0.676
 goof+0.670
 PARK+0.665
Neg logit contributions
imir-1.169
etsk-1.160
orthern-1.159
oline-1.122
oslav-1.114
Token government
Token ID1230
Feature activation+3.24e-01

Pos logit contributions
orthern+0.040
imir+0.040
etsk+0.039
oline+0.039
oslav+0.039
Neg logit contributions
 dise-0.030
 goof-0.028
 Indies-0.028
 サ-0.027
ドラ-0.027
Token should
Token ID815
Feature activation+2.74e-01

Pos logit contributions
orthern+0.897
imir+0.893
etsk+0.878
oline+0.875
oslav+0.863
Neg logit contributions
 dise-0.746
 Indies-0.691
ドラ-0.690
 goof-0.685
 サ-0.684
Token also
Token ID635
Feature activation-6.31e-02

Pos logit contributions
orthern+0.783
imir+0.779
etsk+0.765
oline+0.760
oslav+0.753
Neg logit contributions
 dise-0.607
 goof-0.564
 Indies-0.560
 サ-0.554
ドラ-0.547
Token examine
Token ID10716
Feature activation+1.02e-01

Pos logit contributions
 dise+0.143
 goof+0.133
 Indies+0.132
 サ+0.131
ドラ+0.129
Neg logit contributions
orthern-0.178
imir-0.176
etsk-0.174
oline-0.172
oslav-0.171
Token offshore
Token ID18479
Feature activation+1.32e-01

Pos logit contributions
orthern+0.317
imir+0.315
etsk+0.311
oline+0.309
oslav+0.305
Neg logit contributions
 dise-0.201
 Indies-0.183
 goof-0.182
ドラ-0.181
 サ-0.180
Token tax
Token ID1687
Feature activation-1.65e+00

Pos logit contributions
orthern+0.359
imir+0.356
etsk+0.353
oline+0.348
oslav+0.345
Neg logit contributions
 dise-0.316
 Indies-0.293
 goof-0.292
ドラ-0.288
 サ-0.288
Token havens
Token ID47450
Feature activation-1.02e+00

Pos logit contributions
 dise+2.658
 goof+2.416
 Indies+2.330
ドラ+2.291
 サ+2.252
Neg logit contributions
orthern-5.721
imir-5.611
etsk-5.536
oline-5.497
oslav-5.449
Token held
Token ID2714
Feature activation+8.87e-01

Pos logit contributions
 dise+2.287
 Indies+2.119
 goof+2.115
 サ+2.051
 Barr+2.024
Neg logit contributions
orthern-2.921
imir-2.895
etsk-2.862
oline-2.828
oslav-2.801
Token by
Token ID416
Feature activation+2.46e-01

Pos logit contributions
orthern+2.253
imir+2.246
etsk+2.214
oline+2.197
oslav+2.157
Neg logit contributions
 dise-2.204
ドラ-2.082
 サ-2.055
 Indies-2.047
 goof-2.036
Token wealthier
Token ID49311
Feature activation-2.86e-01

Pos logit contributions
orthern+0.726
imir+0.722
etsk+0.713
oline+0.707
oslav+0.699
Neg logit contributions
 dise-0.528
 Indies-0.485
 goof-0.483
ドラ-0.480
 サ-0.477
Token Canadians
Token ID14008
Feature activation-5.75e-01

Pos logit contributions
 dise+0.476
 goof+0.427
 Indies+0.427
 サ+0.408
 Berm+0.404
Neg logit contributions
imir-0.985
orthern-0.983
etsk-0.982
oline-0.961
oslav-0.954
Token include
Token ID2291
Feature activation-5.16e-01

Pos logit contributions
orthern+0.195
imir+0.193
etsk+0.190
oline+0.190
oslav+0.189
Neg logit contributions
 dise-0.110
 goof-0.100
 Indies-0.099
 サ-0.099
ドラ-0.098
Token a
Token ID257
Feature activation-2.04e-01

Pos logit contributions
 dise+1.126
 Indies+1.024
 goof+1.024
 サ+1.024
 PARK+0.994
Neg logit contributions
imir-1.503
orthern-1.503
etsk-1.479
oline-1.467
oslav-1.457
Token $
Token ID720
Feature activation-5.56e-01

Pos logit contributions
 dise+0.466
 goof+0.426
 サ+0.426
 Indies+0.421
ドラ+0.417
Neg logit contributions
imir-0.578
orthern-0.574
etsk-0.572
oslav-0.564
oline-0.562
Token15
Token ID1314
Feature activation+7.68e-02

Pos logit contributions
 dise+0.946
ドラ+0.891
 Indies+0.879
 サ+0.873
 goof+0.848
Neg logit contributions
orthern-1.870
etsk-1.853
imir-1.837
oslav-1.805
oline-1.790
Token minimum
Token ID5288
Feature activation-1.12e+00

Pos logit contributions
orthern+0.217
imir+0.217
etsk+0.215
oslav+0.211
oline+0.211
Neg logit contributions
 dise-0.173
 goof-0.160
 Indies-0.159
ドラ-0.159
 サ-0.159
Token wage
Token ID7699
Feature activation-1.16e+00

Pos logit contributions
 dise+2.278
 goof+2.078
 サ+2.028
 Indies+2.025
 PARK+2.003
Neg logit contributions
imir-3.435
orthern-3.419
etsk-3.407
oslav-3.340
oline-3.273
Token.
Token ID13
Feature activation+5.08e-02

Pos logit contributions
 dise+2.761
 goof+2.595
 サ+2.561
 Indies+2.528
 Barr+2.474
Neg logit contributions
imir-3.110
orthern-3.100
etsk-3.079
oslav-3.007
oline-2.996
Token
Token ID198
Feature activation-5.15e-02

Pos logit contributions
orthern+0.136
imir+0.135
etsk+0.133
oline+0.132
oslav+0.130
Neg logit contributions
 dise-0.122
 Indies-0.114
 サ-0.113
ドラ-0.113
 goof-0.113
Token
Token ID198
Feature activation+7.20e-02

Pos logit contributions
 dise+0.111
 Indies+0.105
 goof+0.104
 サ+0.102
 Barr+0.101
Neg logit contributions
orthern-0.152
etsk-0.148
imir-0.147
VIDIA-0.146
oslav-0.143
TokenSee
Token ID6214
Feature activation+7.16e-01

Pos logit contributions
orthern+0.180
imir+0.177
etsk+0.175
oline+0.174
oslav+0.172
Neg logit contributions
 dise-0.185
ドラ-0.173
 Indies-0.173
 サ-0.172
 goof-0.172
Token the
Token ID262
Feature activation-1.98e-01

Pos logit contributions
orthern+2.076
imir+2.065
etsk+2.032
oline+2.024
oslav+1.998
Neg logit contributions
 dise-1.559
 Indies-1.435
ドラ-1.429
 goof-1.427
 サ-1.418