TOP ACTIVATIONS
MAX = 3.184

you can . # 2 : A Little Prepar
: Show nested quote + On September
be grounded in a rebuilt labor movement : P
== " A " && # != " D " &
== " S " || # == " A " ||
ernel ) L ines 20 and 21 loads our
== " S " || # == " A " ||
== " E " || # == " A " &&
constantly post photos of your damn cle ats . Conf ession
search Space = Select [ # == " S " ||
Ha ! Fuck off ! he
search Space = Select [ # == " S " ||
by 247 Sports . <|endoftext|> Labor s reform proposal
Com plement [ Select [ # == " E " ||
ethical pleas to abolish child labor , and the movement towards
== " A " || # == " D " &
veterans and female reporters ). Asked about sexual harassment in increasingly
VID E OS HAVE BE EN T AK EN DOWN UP
product of a LOT of fuck ups . One guy summed
. An athletic field at Harvard - West lake

MIN ACTIVATIONS
MIN = -3.821

able version <|endoftext|> Rob C estern ino hosts a jam packed
which were considered likely Apollo landing sites . On the first
[ 10 : 47 ] <@ t ay l ort ot
number called The Count , which is
[ 10 : 47 ] < mom per > lol m
[ 10 : 47 ] < sn iping 117 > H
position lights were now c anted inward as the wings had
[ 10 : 47 ] < sych omen > GU YS
[ 10 : 47 ] < k asse mm el >
[ 10 : 47 ] < fen ren > m 2
[ 10 : 48 ] < mom per > lol m
[ 10 : 47 ] < mom per > lol m
[ 10 : 48 ] < qu ij ii > 2
[ 10 : 47 ] < ok clock zy > lol
[ 10 : 47 ] < chain x 9999 > lol
[ 10 : 47 ] < dan ides u > lol
[ 10 : 47 ] < ok clock zy > Dude
[ 10 : 47 ] < kw ij ibo 00 800
[ 10 : 47 ] < literally _ worst _ user
[ 10 : 47 ] < en 7 _> lol Mang

INTERVAL 1.432 - 3.184
CONTAINS 0.655%

government did almost 25 years ago . Some restrictions have already
s signature food . Maps like these are fun ,
work of moving the Democratic Party right ward . ( Bill
and Mexico to craft a North American climate agreement to signal
is little agreement on how best to proceed .

INTERVAL -0.319 - 1.432
CONTAINS 75.291%

matters most in geop olitics it is plain to see
would force one side of our planet to always face the
47 19 35 19 23
them down Broadway to the main gate , where that photo
on a metal bench . A sales woman behind the ticket

INTERVAL -2.070 - -0.319
CONTAINS 23.982%

was another word . Giant another . Huge , En orm
in exaggerated accents . Wat ters approaches a number of men
unfor g ivably bad tort illas , it 's good to
better - Most of the questions interview ers asked me were
Mississippi got in Brown s ear about kicking

INTERVAL -3.821 - -2.070
CONTAINS 0.071%

slide Power Point slide PNG larger image
[ 10 : 47 ] < fen ren > m 2
top leadership . Instead he named Cohn , his long -
achieved without players such as Sad io Man é , Adam
a fast and fun arcade style racing game that takes inspiration
Token you
Token ID345
Feature activation+2.73e-01

Pos logit contributions
alsh+0.023
 Steal+0.022
zee+0.020
BACK+0.020
horn+0.020
Neg logit contributions
ascript-0.019
ウス-0.019
atism-0.017
hesion-0.017
 Tad-0.016
Token can
Token ID460
Feature activation-3.21e-01

Pos logit contributions
ascript+0.198
ウス+0.196
atism+0.179
hesion+0.178
 Tad+0.177
Neg logit contributions
alsh-0.212
 Steal-0.201
BACK-0.187
zee-0.186
horn-0.179
Token.
Token ID13
Feature activation+6.16e-01

Pos logit contributions
alsh+0.260
 Steal+0.249
zee+0.231
BACK+0.231
horn+0.223
Neg logit contributions
ascript-0.221
ウス-0.221
atism-0.199
hesion-0.198
 Tad-0.197
Token
Token ID198
Feature activation+1.39e-01

Pos logit contributions
ascript+0.472
ウス+0.471
atism+0.430
hesion+0.428
 Tad+0.426
Neg logit contributions
alsh-0.452
 Steal-0.429
zee-0.396
BACK-0.395
horn-0.379
Token
Token ID198
Feature activation+5.38e-02

Pos logit contributions
ウス+0.092
ascript+0.091
hesion+0.083
 Tad+0.083
atism+0.082
Neg logit contributions
alsh-0.116
 Steal-0.110
zee-0.103
BACK-0.101
horn-0.098
Token#
Token ID2
Feature activation+3.18e+00

Pos logit contributions
ascript+0.046
ウス+0.046
atism+0.042
hesion+0.042
 Tad+0.042
Neg logit contributions
alsh-0.035
 Steal-0.033
BACK-0.030
zee-0.030
horn-0.029
Token2
Token ID17
Feature activation+1.27e+00

Pos logit contributions
ウス+2.402
ascript+2.392
atism+2.182
hesion+2.179
 Tad+2.177
Neg logit contributions
alsh-2.353
 Steal-2.212
zee-2.052
BACK-2.036
horn-1.957
Token:
Token ID25
Feature activation+2.10e+00

Pos logit contributions
ascript+0.855
ウス+0.852
atism+0.767
hesion+0.762
 Tad+0.757
Neg logit contributions
alsh-1.057
 Steal-1.009
zee-0.942
BACK-0.940
horn-0.907
Token A
Token ID317
Feature activation+1.03e+00

Pos logit contributions
ascript+1.629
ウス+1.626
 Tad+1.498
atism+1.495
hesion+1.485
Neg logit contributions
alsh-1.500
 Steal-1.395
zee-1.306
BACK-1.297
horn-1.248
Token Little
Token ID7703
Feature activation+1.05e-01

Pos logit contributions
ascript+0.744
ウス+0.743
atism+0.674
hesion+0.670
 Tad+0.667
Neg logit contributions
alsh-0.803
 Steal-0.764
zee-0.710
BACK-0.709
horn-0.682
Token Prepar
Token ID38397
Feature activation-5.42e-02

Pos logit contributions
ascript+0.075
ウス+0.075
atism+0.068
hesion+0.068
 Tad+0.067
Neg logit contributions
alsh-0.082
 Steal-0.078
zee-0.073
BACK-0.073
horn-0.070
Token:
Token ID25
Feature activation+3.66e-01

Pos logit contributions
ascript+0.375
ウス+0.375
 Tad+0.325
hesion+0.325
atism+0.324
Neg logit contributions
alsh-0.809
 Steal-0.774
BACK-0.734
zee-0.733
horn-0.705
Token
Token ID198
Feature activation+3.46e-01

Pos logit contributions
ウス+0.238
ascript+0.237
 Tad+0.216
hesion+0.215
atism+0.213
Neg logit contributions
alsh-0.307
 Steal-0.292
zee-0.273
BACK-0.272
horn-0.259
Token
Token ID198
Feature activation+2.97e-01

Pos logit contributions
ウス+0.224
ascript+0.223
 Tad+0.204
hesion+0.204
atism+0.202
Neg logit contributions
alsh-0.291
 Steal-0.276
zee-0.259
BACK-0.257
horn-0.245
TokenShow
Token ID15307
Feature activation-9.25e-01

Pos logit contributions
ascript+0.256
ウス+0.255
atism+0.235
hesion+0.235
 Tad+0.233
Neg logit contributions
alsh-0.190
 Steal-0.180
zee-0.163
BACK-0.163
horn-0.155
Token nested
Token ID28376
Feature activation+3.90e-02

Pos logit contributions
alsh+0.764
 Steal+0.727
zee+0.681
BACK+0.680
horn+0.654
Neg logit contributions
ascript-0.624
ウス-0.622
atism-0.562
 Tad-0.557
hesion-0.557
Token quote
Token ID9577
Feature activation+3.18e+00

Pos logit contributions
ascript+0.035
ウス+0.035
atism+0.032
hesion+0.032
 Tad+0.032
Neg logit contributions
alsh-0.024
 Steal-0.022
zee-0.020
BACK-0.020
horn-0.019
Token +
Token ID1343
Feature activation+1.06e+00

Pos logit contributions
ascript+1.714
ウス+1.589
atism+1.455
hesion+1.449
 partName+1.447
Neg logit contributions
alsh-3.085
 Steal-2.939
zee-2.808
BACK-2.778
horn-2.636
Token
Token ID198
Feature activation+9.29e-01

Pos logit contributions
ウス+0.684
ascript+0.681
 Tad+0.622
hesion+0.620
 partName+0.618
Neg logit contributions
alsh-0.887
 Steal-0.837
zee-0.791
BACK-0.776
horn-0.748
Token
Token ID198
Feature activation+8.86e-01

Pos logit contributions
ウス+0.587
ascript+0.584
 Tad+0.537
hesion+0.533
 partName+0.532
Neg logit contributions
alsh-0.793
 Steal-0.750
zee-0.707
BACK-0.698
horn-0.668
TokenOn
Token ID2202
Feature activation+3.18e-01

Pos logit contributions
ascript+0.830
ウス+0.829
atism+0.769
hesion+0.765
 Tad+0.761
Neg logit contributions
alsh-0.501
 Steal-0.469
zee-0.422
BACK-0.421
horn-0.398
Token September
Token ID2693
Feature activation-6.32e-01

Pos logit contributions
ascript+0.162
ウス+0.162
atism+0.140
hesion+0.139
 Tad+0.137
Neg logit contributions
alsh-0.316
 Steal-0.304
zee-0.287
BACK-0.286
horn-0.278
Token be
Token ID307
Feature activation-3.12e-01

Pos logit contributions
alsh+0.225
 Steal+0.214
zee+0.197
BACK+0.197
horn+0.189
Neg logit contributions
ウス-0.241
ascript-0.241
atism-0.219
hesion-0.218
 Tad-0.216
Token grounded
Token ID22804
Feature activation+9.91e-01

Pos logit contributions
alsh+0.233
 Steal+0.221
BACK+0.204
zee+0.203
horn+0.196
Neg logit contributions
ウス-0.237
ascript-0.236
atism-0.213
hesion-0.212
 Tad-0.211
Token in
Token ID287
Feature activation+3.59e-01

Pos logit contributions
ウス+0.659
ascript+0.657
atism+0.586
hesion+0.586
 Tad+0.581
Neg logit contributions
alsh-0.829
 Steal-0.792
zee-0.738
BACK-0.736
horn-0.714
Token a
Token ID257
Feature activation+3.46e-01

Pos logit contributions
ascript+0.245
ウス+0.244
atism+0.219
hesion+0.218
 Tad+0.217
Neg logit contributions
alsh-0.295
 Steal-0.282
zee-0.262
BACK-0.262
horn-0.252
Token rebuilt
Token ID30080
Feature activation-7.72e-01

Pos logit contributions
ascript+0.255
ウス+0.254
atism+0.231
hesion+0.229
 Tad+0.228
Neg logit contributions
alsh-0.265
 Steal-0.253
zee-0.234
BACK-0.234
horn-0.225
Token labor
Token ID4827
Feature activation+3.10e+00

Pos logit contributions
alsh+0.636
 Steal+0.608
BACK+0.566
zee+0.565
horn+0.542
Neg logit contributions
ascript-0.526
ウス-0.524
atism-0.466
hesion-0.463
 Tad-0.460
Token movement
Token ID3356
Feature activation+1.33e+00

Pos logit contributions
ascript+1.858
ウス+1.853
hesion+1.671
atism+1.667
 Tad+1.627
Neg logit contributions
alsh-2.758
 Steal-2.644
zee-2.497
BACK-2.469
horn-2.384
Token:
Token ID25
Feature activation+1.17e-01

Pos logit contributions
ascript+0.941
ウス+0.938
atism+0.849
hesion+0.844
 Tad+0.838
Neg logit contributions
alsh-1.058
 Steal-1.010
zee-0.938
BACK-0.936
horn-0.902
Token
Token ID564
Feature activation-7.73e-01

Pos logit contributions
ascript+0.082
ウス+0.082
atism+0.074
hesion+0.073
 Tad+0.073
Neg logit contributions
alsh-0.095
 Steal-0.090
zee-0.084
BACK-0.084
horn-0.081
Token
Token ID250
Feature activation-7.95e-01

Pos logit contributions
alsh+0.636
 Steal+0.607
BACK+0.567
zee+0.564
horn+0.545
Neg logit contributions
ascript-0.525
ウス-0.520
atism-0.471
hesion-0.469
 Tad-0.467
TokenP
Token ID47
Feature activation-3.02e-01

Pos logit contributions
alsh+0.568
 Steal+0.538
BACK+0.498
zee+0.496
horn+0.476
Neg logit contributions
ascript-0.627
ウス-0.627
atism-0.570
 Tad-0.568
hesion-0.567
Token ==
Token ID6624
Feature activation+1.21e+00

Pos logit contributions
ウス+1.279
ascript+1.245
 partName+1.104
)].+1.092
 Tad+1.089
Neg logit contributions
alsh-3.178
 Steal-3.030
zee-2.898
BACK-2.880
horn-2.784
Token "
Token ID366
Feature activation+7.94e-01

Pos logit contributions
ウス+0.884
ascript+0.879
 Tad+0.819
)].+0.816
 partName+0.816
Neg logit contributions
alsh-0.929
 Steal-0.861
zee-0.808
BACK-0.802
horn-0.761
TokenA
Token ID32
Feature activation+1.96e-01

Pos logit contributions
ascript+0.630
ウス+0.629
atism+0.575
hesion+0.572
 Tad+0.569
Neg logit contributions
alsh-0.563
 Steal-0.534
zee-0.491
BACK-0.490
horn-0.469
Token"
Token ID1
Feature activation+7.39e-01

Pos logit contributions
ウス+0.155
ascript+0.155
 partName+0.143
)].+0.143
hesion+0.143
Neg logit contributions
alsh-0.137
 Steal-0.128
zee-0.117
BACK-0.116
horn-0.111
Token &&
Token ID11405
Feature activation+2.79e-01

Pos logit contributions
ascript+0.464
ウス+0.464
atism+0.417
hesion+0.414
 Tad+0.409
Neg logit contributions
alsh-0.642
 Steal-0.623
BACK-0.578
zee-0.572
horn-0.558
Token #
Token ID1303
Feature activation+3.09e+00

Pos logit contributions
ウス+0.179
ascript+0.178
atism+0.160
hesion+0.158
 Tad+0.156
Neg logit contributions
alsh-0.241
 Steal-0.232
BACK-0.216
zee-0.215
horn-0.208
Token!=
Token ID14512
Feature activation+1.07e+00

Pos logit contributions
ascript+1.575
ウス+1.568
atism+1.363
hesion+1.352
 Tad+1.337
Neg logit contributions
alsh-3.053
 Steal-2.938
zee-2.777
BACK-2.770
horn-2.689
Token "
Token ID366
Feature activation+8.73e-01

Pos logit contributions
ウス+0.844
ascript+0.843
atism+0.772
hesion+0.767
 Tad+0.760
Neg logit contributions
alsh-0.757
 Steal-0.722
BACK-0.662
zee-0.661
horn-0.633
TokenD
Token ID35
Feature activation-1.19e+00

Pos logit contributions
ascript+0.752
ウス+0.751
atism+0.692
hesion+0.689
 Tad+0.685
Neg logit contributions
alsh-0.558
 Steal-0.526
zee-0.478
BACK-0.476
horn-0.455
Token"
Token ID1
Feature activation+8.03e-01

Pos logit contributions
alsh+0.754
 Steal+0.711
BACK+0.647
zee+0.647
horn+0.614
Neg logit contributions
ascript-1.039
ウス-1.038
atism-0.957
hesion-0.952
 Tad-0.949
Token &
Token ID1222
Feature activation+3.05e-01

Pos logit contributions
ascript+0.436
ウス+0.435
atism+0.381
hesion+0.377
 Tad+0.372
Neg logit contributions
alsh-0.770
 Steal-0.744
BACK-0.698
zee-0.697
horn-0.676
Token ==
Token ID6624
Feature activation+6.04e-01

Pos logit contributions
ascript+1.510
ウス+1.503
atism+1.310
hesion+1.297
 Tad+1.285
Neg logit contributions
alsh-2.850
 Steal-2.741
zee-2.588
BACK-2.583
horn-2.507
Token "
Token ID366
Feature activation+8.50e-01

Pos logit contributions
ウス+0.496
ascript+0.496
atism+0.456
hesion+0.453
 Tad+0.449
Neg logit contributions
alsh-0.410
 Steal-0.390
BACK-0.356
zee-0.355
horn-0.340
TokenS
Token ID50
Feature activation-2.31e-01

Pos logit contributions
ascript+0.735
ウス+0.734
atism+0.677
hesion+0.673
 Tad+0.669
Neg logit contributions
alsh-0.542
 Steal-0.511
zee-0.466
BACK-0.465
horn-0.442
Token"
Token ID1
Feature activation+6.45e-01

Pos logit contributions
alsh+0.146
 Steal+0.138
zee+0.125
BACK+0.125
horn+0.119
Neg logit contributions
ascript-0.200
ウス-0.200
atism-0.185
hesion-0.184
 Tad-0.183
Token ||
Token ID8614
Feature activation+1.81e-01

Pos logit contributions
ウス+0.416
ascript+0.415
atism+0.373
hesion+0.372
 Tad+0.368
Neg logit contributions
alsh-0.551
 Steal-0.532
BACK-0.493
zee-0.491
horn-0.477
Token #
Token ID1303
Feature activation+3.07e+00

Pos logit contributions
ascript+0.063
ウス+0.062
atism+0.050
hesion+0.050
 Tad+0.049
Neg logit contributions
alsh-0.208
 Steal-0.202
zee-0.192
BACK-0.192
horn-0.187
Token ==
Token ID6624
Feature activation+1.07e+00

Pos logit contributions
ウス+1.306
ascript+1.283
 partName+1.130
 Tad+1.108
 Iro+1.104
Neg logit contributions
alsh-3.262
 Steal-3.112
zee-2.973
BACK-2.967
horn-2.860
Token "
Token ID366
Feature activation+9.27e-01

Pos logit contributions
ウス+0.786
ascript+0.781
 Tad+0.726
 partName+0.725
)].+0.724
Neg logit contributions
alsh-0.818
 Steal-0.760
zee-0.710
BACK-0.707
horn-0.670
TokenA
Token ID32
Feature activation+2.83e-01

Pos logit contributions
ウス+0.672
ascript+0.671
atism+0.607
hesion+0.605
 Tad+0.601
Neg logit contributions
alsh-0.719
 Steal-0.684
zee-0.632
BACK-0.624
horn-0.606
Token"
Token ID1
Feature activation+7.94e-01

Pos logit contributions
ウス+0.220
ascript+0.218
 partName+0.203
hesion+0.202
)].+0.202
Neg logit contributions
alsh-0.201
 Steal-0.189
zee-0.173
BACK-0.172
horn-0.163
Token ||
Token ID8614
Feature activation+4.91e-01

Pos logit contributions
ascript+0.506
ウス+0.506
atism+0.455
hesion+0.451
 Tad+0.447
Neg logit contributions
alsh-0.685
 Steal-0.660
BACK-0.612
zee-0.611
horn-0.593
Tokenernel
Token ID7948
Feature activation-2.06e-01

Pos logit contributions
alsh+0.077
 Steal+0.074
BACK+0.069
zee+0.069
horn+0.066
Neg logit contributions
ascript-0.066
ウス-0.065
atism-0.060
hesion-0.060
 Tad-0.058
Token )
Token ID1267
Feature activation+6.45e-01

Pos logit contributions
alsh+0.206
 Steal+0.197
zee+0.187
BACK+0.186
horn+0.181
Neg logit contributions
ascript-0.103
ウス-0.103
atism-0.089
hesion-0.089
 Tad-0.088
Token
Token ID198
Feature activation-1.42e-01

Pos logit contributions
ウス+0.400
ascript+0.399
atism+0.354
hesion+0.350
 Tad+0.348
Neg logit contributions
alsh-0.572
 Steal-0.550
BACK-0.515
zee-0.513
horn-0.497
Token
Token ID198
Feature activation-4.28e-02

Pos logit contributions
alsh+0.118
 Steal+0.112
zee+0.105
BACK+0.104
horn+0.100
Neg logit contributions
ウス-0.094
ascript-0.094
hesion-0.085
atism-0.085
 Tad-0.085
TokenL
Token ID43
Feature activation+4.19e-01

Pos logit contributions
alsh+0.027
 Steal+0.026
zee+0.023
BACK+0.023
horn+0.022
Neg logit contributions
ascript-0.037
ウス-0.037
atism-0.034
hesion-0.034
 Tad-0.034
Tokenines
Token ID1127
Feature activation+3.02e+00

Pos logit contributions
ascript+0.270
ウス+0.269
atism+0.241
hesion+0.239
 Tad+0.237
Neg logit contributions
alsh-0.360
 Steal-0.344
zee-0.322
BACK-0.321
horn-0.310
Token 20
Token ID1160
Feature activation-1.25e-01

Pos logit contributions
ascript+1.844
ウス+1.817
hesion+1.642
atism+1.641
 Tad+1.636
Neg logit contributions
alsh-2.661
 Steal-2.537
BACK-2.386
zee-2.386
horn-2.300
Token and
Token ID290
Feature activation-2.53e-01

Pos logit contributions
alsh+0.089
 Steal+0.084
zee+0.078
BACK+0.077
horn+0.074
Neg logit contributions
ascript-0.099
ウス-0.099
atism-0.090
hesion-0.090
 Tad-0.089
Token 21
Token ID2310
Feature activation+8.29e-02

Pos logit contributions
alsh+0.197
 Steal+0.188
zee+0.174
BACK+0.174
horn+0.168
Neg logit contributions
ウス-0.184
ascript-0.183
atism-0.166
hesion-0.164
 Tad-0.163
Token loads
Token ID15989
Feature activation+1.53e-01

Pos logit contributions
ascript+0.059
ウス+0.059
atism+0.053
hesion+0.053
 Tad+0.053
Neg logit contributions
alsh-0.065
 Steal-0.062
zee-0.058
BACK-0.058
horn-0.056
Token our
Token ID674
Feature activation+4.96e-01

Pos logit contributions
ウス+0.105
ascript+0.105
atism+0.095
hesion+0.094
 Tad+0.093
Neg logit contributions
alsh-0.124
 Steal-0.119
zee-0.110
BACK-0.110
horn-0.106
Token ==
Token ID6624
Feature activation+7.54e-01

Pos logit contributions
ascript+2.093
ウス+2.092
atism+1.894
hesion+1.885
 Tad+1.871
Neg logit contributions
alsh-2.363
 Steal-2.253
zee-2.088
BACK-2.078
horn-2.008
Token "
Token ID366
Feature activation+7.16e-01

Pos logit contributions
ascript+0.501
ウス+0.499
atism+0.449
hesion+0.445
 Tad+0.441
Neg logit contributions
alsh-0.633
 Steal-0.607
BACK-0.566
zee-0.566
horn-0.545
TokenS
Token ID50
Feature activation-1.80e-01

Pos logit contributions
ascript+0.562
ウス+0.561
atism+0.512
hesion+0.509
 Tad+0.506
Neg logit contributions
alsh-0.514
 Steal-0.488
zee-0.451
BACK-0.450
horn-0.431
Token"
Token ID1
Feature activation+2.74e-01

Pos logit contributions
alsh+0.125
 Steal+0.119
zee+0.109
BACK+0.109
horn+0.104
Neg logit contributions
ascript-0.145
ウス-0.145
atism-0.133
hesion-0.132
 Tad-0.131
Token ||
Token ID8614
Feature activation+1.66e-01

Pos logit contributions
ascript+0.173
ウス+0.173
atism+0.154
hesion+0.153
 Tad+0.151
Neg logit contributions
alsh-0.238
 Steal-0.229
BACK-0.214
zee-0.213
horn-0.206
Token #
Token ID1303
Feature activation+2.99e+00

Pos logit contributions
ウス+0.096
ascript+0.095
atism+0.084
hesion+0.084
 Tad+0.083
Neg logit contributions
alsh-0.154
 Steal-0.148
BACK-0.139
zee-0.138
horn-0.134
Token ==
Token ID6624
Feature activation+1.11e+00

Pos logit contributions
ascript+1.561
ウス+1.552
atism+1.357
hesion+1.342
 Tad+1.331
Neg logit contributions
alsh-2.929
 Steal-2.816
zee-2.660
BACK-2.652
horn-2.575
Token "
Token ID366
Feature activation+8.84e-01

Pos logit contributions
ウス+0.905
ascript+0.904
atism+0.829
hesion+0.825
 Tad+0.818
Neg logit contributions
alsh-0.760
 Steal-0.724
BACK-0.662
zee-0.660
horn-0.631
TokenA
Token ID32
Feature activation+4.54e-01

Pos logit contributions
ascript+0.731
ウス+0.730
atism+0.670
hesion+0.667
 Tad+0.663
Neg logit contributions
alsh-0.597
 Steal-0.565
zee-0.518
BACK-0.517
horn-0.493
Token"
Token ID1
Feature activation+4.50e-01

Pos logit contributions
ascript+0.389
ウス+0.389
atism+0.358
hesion+0.357
 Tad+0.354
Neg logit contributions
alsh-0.292
 Steal-0.276
BACK-0.251
zee-0.251
horn-0.239
Token ||
Token ID8614
Feature activation+3.24e-01

Pos logit contributions
ascript+0.293
ウス+0.292
atism+0.262
hesion+0.261
 Tad+0.258
Neg logit contributions
alsh-0.382
 Steal-0.368
BACK-0.343
zee-0.341
horn-0.330
Token ==
Token ID6624
Feature activation+6.48e-01

Pos logit contributions
ascript+1.628
ウス+1.621
atism+1.431
hesion+1.420
 Tad+1.408
Neg logit contributions
alsh-2.652
 Steal-2.546
zee-2.396
BACK-2.390
horn-2.316
Token "
Token ID366
Feature activation+5.19e-01

Pos logit contributions
ウス+0.525
ascript+0.524
atism+0.482
hesion+0.478
 Tad+0.473
Neg logit contributions
alsh-0.448
 Steal-0.428
BACK-0.391
zee-0.389
horn-0.373
TokenE
Token ID36
Feature activation+2.99e-01

Pos logit contributions
ascript+0.429
ウス+0.428
atism+0.394
hesion+0.391
 Tad+0.389
Neg logit contributions
alsh-0.350
 Steal-0.331
zee-0.303
BACK-0.303
horn-0.289
Token"
Token ID1
Feature activation+5.19e-01

Pos logit contributions
ウス+0.260
ascript+0.260
atism+0.240
hesion+0.239
 Tad+0.238
Neg logit contributions
alsh-0.189
 Steal-0.178
BACK-0.162
zee-0.162
horn-0.154
Token ||
Token ID8614
Feature activation+1.44e-01

Pos logit contributions
ウス+0.325
ascript+0.324
atism+0.291
hesion+0.290
 Tad+0.286
Neg logit contributions
alsh-0.451
 Steal-0.437
BACK-0.406
zee-0.403
horn-0.392
Token #
Token ID1303
Feature activation+2.99e+00

Pos logit contributions
ウス+0.059
ascript+0.058
atism+0.049
hesion+0.049
 Tad+0.046
Neg logit contributions
alsh-0.157
 Steal-0.154
BACK-0.145
zee-0.144
horn-0.141
Token ==
Token ID6624
Feature activation+1.21e+00

Pos logit contributions
ウス+1.279
ascript+1.245
 partName+1.104
)].+1.092
 Tad+1.089
Neg logit contributions
alsh-3.178
 Steal-3.030
zee-2.898
BACK-2.880
horn-2.784
Token "
Token ID366
Feature activation+7.94e-01

Pos logit contributions
ウス+0.884
ascript+0.879
 Tad+0.819
)].+0.816
 partName+0.816
Neg logit contributions
alsh-0.929
 Steal-0.861
zee-0.808
BACK-0.802
horn-0.761
TokenA
Token ID32
Feature activation+1.96e-01

Pos logit contributions
ascript+0.630
ウス+0.629
atism+0.575
hesion+0.572
 Tad+0.569
Neg logit contributions
alsh-0.563
 Steal-0.534
zee-0.491
BACK-0.490
horn-0.469
Token"
Token ID1
Feature activation+7.39e-01

Pos logit contributions
ウス+0.155
ascript+0.155
 partName+0.143
)].+0.143
hesion+0.143
Neg logit contributions
alsh-0.137
 Steal-0.128
zee-0.117
BACK-0.116
horn-0.111
Token &&
Token ID11405
Feature activation+2.79e-01

Pos logit contributions
ascript+0.464
ウス+0.464
atism+0.417
hesion+0.414
 Tad+0.409
Neg logit contributions
alsh-0.642
 Steal-0.623
BACK-0.578
zee-0.572
horn-0.558
Token constantly
Token ID7558
Feature activation+1.56e+00

Pos logit contributions
ascript+0.300
ウス+0.298
atism+0.274
hesion+0.272
 Tad+0.271
Neg logit contributions
alsh-0.285
 Steal-0.269
zee-0.249
BACK-0.249
horn-0.239
Token post
Token ID1281
Feature activation+4.07e-01

Pos logit contributions
ascript+1.202
ウス+1.179
atism+1.095
 Tad+1.088
hesion+1.086
Neg logit contributions
alsh-1.136
 Steal-1.070
zee-0.995
BACK-0.994
horn-0.954
Token photos
Token ID5205
Feature activation+9.64e-01

Pos logit contributions
ascript+0.300
ウス+0.299
atism+0.272
hesion+0.270
 Tad+0.268
Neg logit contributions
alsh-0.312
 Steal-0.297
zee-0.275
BACK-0.275
horn-0.264
Token of
Token ID286
Feature activation+4.51e-01

Pos logit contributions
ascript+0.696
ウス+0.695
atism+0.630
hesion+0.626
 Tad+0.621
Neg logit contributions
alsh-0.752
 Steal-0.718
zee-0.665
BACK-0.664
horn-0.640
Token your
Token ID534
Feature activation-2.34e-01

Pos logit contributions
ウス+0.269
ascript+0.268
atism+0.236
hesion+0.235
 partName+0.230
Neg logit contributions
alsh-0.410
 Steal-0.396
BACK-0.369
zee-0.369
horn-0.359
Token damn
Token ID12270
Feature activation+2.98e+00

Pos logit contributions
alsh+0.197
 Steal+0.190
BACK+0.176
zee+0.176
horn+0.170
Neg logit contributions
ウス-0.155
ascript-0.155
atism-0.138
hesion-0.137
 partName-0.134
Token cle
Token ID1190
Feature activation-6.25e-01

Pos logit contributions
ascript+2.025
ウス+2.017
atism+1.821
hesion+1.807
 Tad+1.800
Neg logit contributions
alsh-2.442
 Steal-2.330
zee-2.171
BACK-2.167
horn-2.088
Tokenats
Token ID1381
Feature activation-3.04e-01

Pos logit contributions
alsh+0.686
 Steal+0.662
zee+0.631
BACK+0.627
horn+0.615
Neg logit contributions
ウス-0.257
ascript-0.251
 Tad-0.207
atism-0.206
hesion-0.206
Token.
Token ID13
Feature activation-2.10e-01

Pos logit contributions
alsh+0.242
 Steal+0.232
zee+0.215
BACK+0.214
horn+0.207
Neg logit contributions
ascript-0.214
ウス-0.214
atism-0.193
hesion-0.192
 Tad-0.190
Token Conf
Token ID7326
Feature activation+3.69e-01

Pos logit contributions
alsh+0.155
 Steal+0.149
zee+0.137
BACK+0.136
horn+0.131
Neg logit contributions
ascript-0.160
ウス-0.159
atism-0.145
hesion-0.145
 Tad-0.143
Tokenession
Token ID2521
Feature activation-1.15e-01

Pos logit contributions
ascript+0.284
ウス+0.283
atism+0.258
hesion+0.257
 Tad+0.255
Neg logit contributions
alsh-0.270
 Steal-0.257
zee-0.237
BACK-0.237
horn-0.227
Tokensearch
Token ID12947
Feature activation-1.17e-02

Pos logit contributions
alsh+0.804
 Steal+0.766
BACK+0.721
zee+0.718
horn+0.690
Neg logit contributions
ascript-0.703
ウス-0.698
atism-0.633
 Tad-0.626
hesion-0.626
TokenSpace
Token ID14106
Feature activation+5.64e-02

Pos logit contributions
alsh+0.008
 Steal+0.008
zee+0.007
BACK+0.007
horn+0.007
Neg logit contributions
ascript-0.009
ウス-0.009
atism-0.009
hesion-0.009
 Tad-0.008
Token =
Token ID796
Feature activation+3.98e-01

Pos logit contributions
ascript+0.038
ウス+0.037
atism+0.034
hesion+0.033
 Tad+0.033
Neg logit contributions
alsh-0.047
 Steal-0.045
BACK-0.042
zee-0.042
horn-0.040
Token Select
Token ID9683
Feature activation+3.22e-02

Pos logit contributions
ascript+0.264
ウス+0.264
atism+0.237
hesion+0.235
 Tad+0.232
Neg logit contributions
alsh-0.333
 Steal-0.321
BACK-0.298
zee-0.298
horn-0.286
Token[
Token ID58
Feature activation+1.72e+00

Pos logit contributions
ascript+0.023
ウス+0.023
atism+0.020
hesion+0.020
 Tad+0.020
Neg logit contributions
alsh-0.026
 Steal-0.025
BACK-0.023
zee-0.023
horn-0.022
Token#
Token ID2
Feature activation+2.98e+00

Pos logit contributions
ascript+1.283
ウス+1.279
atism+1.164
hesion+1.157
 Tad+1.149
Neg logit contributions
alsh-1.302
 Steal-1.239
zee-1.147
BACK-1.145
horn-1.100
Token ==
Token ID6624
Feature activation+7.54e-01

Pos logit contributions
ascript+2.093
ウス+2.092
atism+1.894
hesion+1.885
 Tad+1.871
Neg logit contributions
alsh-2.363
 Steal-2.253
zee-2.088
BACK-2.078
horn-2.008
Token "
Token ID366
Feature activation+7.16e-01

Pos logit contributions
ascript+0.501
ウス+0.499
atism+0.449
hesion+0.445
 Tad+0.441
Neg logit contributions
alsh-0.633
 Steal-0.607
BACK-0.566
zee-0.566
horn-0.545
TokenS
Token ID50
Feature activation-1.80e-01

Pos logit contributions
ascript+0.562
ウス+0.561
atism+0.512
hesion+0.509
 Tad+0.506
Neg logit contributions
alsh-0.514
 Steal-0.488
zee-0.451
BACK-0.450
horn-0.431
Token"
Token ID1
Feature activation+2.74e-01

Pos logit contributions
alsh+0.125
 Steal+0.119
zee+0.109
BACK+0.109
horn+0.104
Neg logit contributions
ascript-0.145
ウス-0.145
atism-0.133
hesion-0.132
 Tad-0.131
Token ||
Token ID8614
Feature activation+1.66e-01

Pos logit contributions
ascript+0.173
ウス+0.173
atism+0.154
hesion+0.153
 Tad+0.151
Neg logit contributions
alsh-0.238
 Steal-0.229
BACK-0.214
zee-0.213
horn-0.206
Token
Token ID198
Feature activation+4.30e-01

Pos logit contributions
ウス+0.349
ascript+0.347
hesion+0.317
 Tad+0.317
atism+0.315
Neg logit contributions
alsh-0.457
 Steal-0.434
zee-0.406
BACK-0.403
horn-0.386
Token
Token ID447
Feature activation+9.21e-01

Pos logit contributions
ウス+0.268
ascript+0.268
atism+0.239
hesion+0.238
 Tad+0.235
Neg logit contributions
alsh-0.377
 Steal-0.362
zee-0.338
BACK-0.337
horn-0.326
Token
Token ID250
Feature activation-9.95e-02

Pos logit contributions
ascript+0.665
ウス+0.663
atism+0.602
hesion+0.599
 Tad+0.594
Neg logit contributions
alsh-0.718
 Steal-0.684
zee-0.634
BACK-0.634
horn-0.609
TokenHa
Token ID23303
Feature activation+2.05e-01

Pos logit contributions
alsh+0.064
 Steal+0.060
zee+0.055
BACK+0.055
horn+0.052
Neg logit contributions
ascript-0.086
ウス-0.085
atism-0.079
hesion-0.078
 Tad-0.078
Token!
Token ID0
Feature activation+1.57e+00

Pos logit contributions
ascript+0.154
ウス+0.154
atism+0.140
hesion+0.139
 Tad+0.138
Neg logit contributions
alsh-0.153
 Steal-0.146
zee-0.135
BACK-0.135
horn-0.129
Token Fuck
Token ID25617
Feature activation+2.94e+00

Pos logit contributions
ウス+0.943
ascript+0.941
atism+0.837
hesion+0.836
 Tad+0.833
Neg logit contributions
alsh-1.400
 Steal-1.339
zee-1.257
BACK-1.256
horn-1.217
Token off
Token ID572
Feature activation-1.39e-01

Pos logit contributions
ascript+2.026
ウス+2.024
atism+1.845
hesion+1.836
 Tad+1.823
Neg logit contributions
alsh-2.347
 Steal-2.234
BACK-2.075
zee-2.072
horn-1.986
Token!
Token ID0
Feature activation+1.50e-01

Pos logit contributions
alsh+0.109
 Steal+0.105
zee+0.097
BACK+0.097
horn+0.093
Neg logit contributions
ascript-0.100
ウス-0.100
atism-0.090
hesion-0.089
 Tad-0.088
Token
Token ID447
Feature activation+4.13e-02

Pos logit contributions
ascript+0.096
ウス+0.095
atism+0.085
hesion+0.085
 Tad+0.084
Neg logit contributions
alsh-0.130
 Steal-0.124
zee-0.116
BACK-0.116
horn-0.112
Token
Token ID251
Feature activation-1.42e-01

Pos logit contributions
ascript+0.024
ウス+0.024
atism+0.021
hesion+0.021
 Tad+0.021
Neg logit contributions
alsh-0.038
 Steal-0.036
zee-0.034
BACK-0.034
horn-0.033
Token he
Token ID339
Feature activation-2.18e-01

Pos logit contributions
alsh+0.110
 Steal+0.105
BACK+0.097
zee+0.097
horn+0.093
Neg logit contributions
ascript-0.103
ウス-0.103
atism-0.093
hesion-0.092
 Tad-0.092
Tokensearch
Token ID12947
Feature activation+3.92e-01

Pos logit contributions
alsh+0.326
 Steal+0.306
BACK+0.281
zee+0.280
horn+0.266
Neg logit contributions
ascript-0.444
ウス-0.442
atism-0.408
hesion-0.405
 Tad-0.404
TokenSpace
Token ID14106
Feature activation+4.88e-01

Pos logit contributions
ascript+0.312
ウス+0.311
atism+0.284
hesion+0.283
 Tad+0.281
Neg logit contributions
alsh-0.277
 Steal-0.263
zee-0.242
BACK-0.241
horn-0.231
Token =
Token ID796
Feature activation+9.34e-01

Pos logit contributions
ascript+0.331
ウス+0.331
atism+0.297
hesion+0.296
 Tad+0.294
Neg logit contributions
alsh-0.400
 Steal-0.384
BACK-0.358
zee-0.357
horn-0.343
Token Select
Token ID9683
Feature activation+3.85e-01

Pos logit contributions
ascript+0.582
ウス+0.582
atism+0.518
hesion+0.514
 Tad+0.509
Neg logit contributions
alsh-0.820
 Steal-0.788
zee-0.736
BACK-0.735
horn-0.710
Token[
Token ID58
Feature activation+1.41e+00

Pos logit contributions
ウス+0.231
ascript+0.230
atism+0.205
hesion+0.203
 Tad+0.202
Neg logit contributions
alsh-0.346
 Steal-0.334
BACK-0.314
zee-0.313
horn-0.302
Token#
Token ID2
Feature activation+2.90e+00

Pos logit contributions
ウス+0.789
ascript+0.786
atism+0.691
hesion+0.686
 Tad+0.678
Neg logit contributions
alsh-1.333
 Steal-1.283
BACK-1.210
zee-1.206
horn-1.171
Token ==
Token ID6624
Feature activation+6.04e-01

Pos logit contributions
ascript+1.510
ウス+1.503
atism+1.310
hesion+1.297
 Tad+1.285
Neg logit contributions
alsh-2.850
 Steal-2.741
zee-2.588
BACK-2.583
horn-2.507
Token "
Token ID366
Feature activation+8.50e-01

Pos logit contributions
ウス+0.496
ascript+0.496
atism+0.456
hesion+0.453
 Tad+0.449
Neg logit contributions
alsh-0.410
 Steal-0.390
BACK-0.356
zee-0.355
horn-0.340
TokenS
Token ID50
Feature activation-2.31e-01

Pos logit contributions
ascript+0.735
ウス+0.734
atism+0.677
hesion+0.673
 Tad+0.669
Neg logit contributions
alsh-0.542
 Steal-0.511
zee-0.466
BACK-0.465
horn-0.442
Token"
Token ID1
Feature activation+6.45e-01

Pos logit contributions
alsh+0.146
 Steal+0.138
zee+0.125
BACK+0.125
horn+0.119
Neg logit contributions
ascript-0.200
ウス-0.200
atism-0.185
hesion-0.184
 Tad-0.183
Token ||
Token ID8614
Feature activation+1.81e-01

Pos logit contributions
ウス+0.416
ascript+0.415
atism+0.373
hesion+0.372
 Tad+0.368
Neg logit contributions
alsh-0.551
 Steal-0.532
BACK-0.493
zee-0.491
horn-0.477
Token by
Token ID416
Feature activation-4.43e-01

Pos logit contributions
alsh+0.325
 Steal+0.311
BACK+0.287
zee+0.286
horn+0.281
Neg logit contributions
ウス-0.262
ascript-0.260
atism-0.235
hesion-0.233
 partName-0.227
Token 247
Token ID30179
Feature activation+6.46e-02

Pos logit contributions
alsh+0.379
 Steal+0.365
BACK+0.338
zee+0.337
horn+0.328
Neg logit contributions
ウス-0.289
ascript-0.289
atism-0.255
hesion-0.254
 partName-0.249
TokenSports
Token ID18153
Feature activation+1.76e-01

Pos logit contributions
ウス+0.043
ascript+0.043
atism+0.039
hesion+0.038
 Tad+0.038
Neg logit contributions
alsh-0.054
 Steal-0.052
BACK-0.048
zee-0.048
horn-0.047
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
ウス+0.121
ascript+0.120
atism+0.108
hesion+0.108
 Tad+0.107
Neg logit contributions
alsh-0.144
 Steal-0.137
BACK-0.128
zee-0.127
horn-0.124
Token<|endoftext|>
Token ID50256
Feature activation-2.02e-01

Pos logit contributions
alsh+0.277
 Steal+0.265
BACK+0.245
zee+0.245
horn+0.237
Neg logit contributions
ascript-0.250
ウス-0.247
atism-0.225
hesion-0.223
 Tad-0.219
TokenLabor
Token ID42230
Feature activation+2.86e+00

Pos logit contributions
alsh+0.136
 Steal+0.128
BACK+0.118
zee+0.118
horn+0.112
Neg logit contributions
ascript-0.168
ウス-0.167
atism-0.153
hesion-0.153
 Tad-0.152
Token
Token ID447
Feature activation-3.55e-01

Pos logit contributions
ascript+1.906
ウス+1.897
atism+1.727
hesion+1.706
 Tad+1.689
Neg logit contributions
alsh-2.384
 Steal-2.262
zee-2.134
BACK-2.111
horn-2.029
Token
Token ID247
Feature activation+1.19e-01

Pos logit contributions
alsh+0.328
 Steal+0.315
BACK+0.297
zee+0.295
horn+0.286
Neg logit contributions
ascript-0.204
ウス-0.203
hesion-0.180
 Tad-0.178
atism-0.178
Tokens
Token ID82
Feature activation+2.65e-01

Pos logit contributions
ascript+0.082
ウス+0.082
atism+0.074
hesion+0.073
 Tad+0.073
Neg logit contributions
alsh-0.097
 Steal-0.093
BACK-0.087
zee-0.086
horn-0.083
Token reform
Token ID4975
Feature activation-7.76e-01

Pos logit contributions
ascript+0.175
ウス+0.175
atism+0.156
hesion+0.156
 Tad+0.154
Neg logit contributions
alsh-0.222
 Steal-0.214
BACK-0.199
zee-0.198
horn-0.192
Token proposal
Token ID6961
Feature activation-1.64e-01

Pos logit contributions
alsh+0.622
 Steal+0.595
BACK+0.554
zee+0.553
horn+0.534
Neg logit contributions
ウス-0.543
ascript-0.542
hesion-0.484
atism-0.484
 Tad-0.480
Token Com
Token ID955
Feature activation-1.29e-01

Pos logit contributions
ウス+0.104
ascript+0.103
atism+0.094
hesion+0.093
 Tad+0.092
Neg logit contributions
alsh-0.115
 Steal-0.110
zee-0.102
BACK-0.102
horn-0.098
Tokenplement
Token ID26908
Feature activation-7.17e-01

Pos logit contributions
alsh+0.081
 Steal+0.076
zee+0.070
BACK+0.069
horn+0.066
Neg logit contributions
ウス-0.113
ascript-0.112
atism-0.104
hesion-0.103
 Tad-0.103
Token[
Token ID58
Feature activation+1.16e+00

Pos logit contributions
alsh+0.631
 Steal+0.608
BACK+0.570
zee+0.568
horn+0.547
Neg logit contributions
ウス-0.443
ascript-0.443
atism-0.394
hesion-0.391
 Tad-0.387
Token Select
Token ID9683
Feature activation-1.55e-01

Pos logit contributions
ascript+0.896
ウス+0.896
atism+0.817
hesion+0.811
 Tad+0.806
Neg logit contributions
alsh-0.852
 Steal-0.811
BACK-0.750
zee-0.748
horn-0.717
Token[
Token ID58
Feature activation+1.70e+00

Pos logit contributions
alsh+0.138
 Steal+0.133
BACK+0.125
zee+0.124
horn+0.120
Neg logit contributions
ウス-0.094
ascript-0.094
atism-0.084
hesion-0.083
 Tad-0.082
Token#
Token ID2
Feature activation+2.85e+00

Pos logit contributions
ウス+1.084
ascript+1.084
atism+0.968
hesion+0.960
 Tad+0.951
Neg logit contributions
alsh-1.467
 Steal-1.407
BACK-1.315
zee-1.314
horn-1.269
Token ==
Token ID6624
Feature activation+6.48e-01

Pos logit contributions
ascript+1.628
ウス+1.621
atism+1.431
hesion+1.420
 Tad+1.408
Neg logit contributions
alsh-2.652
 Steal-2.546
zee-2.396
BACK-2.390
horn-2.316
Token "
Token ID366
Feature activation+5.19e-01

Pos logit contributions
ウス+0.525
ascript+0.524
atism+0.482
hesion+0.478
 Tad+0.473
Neg logit contributions
alsh-0.448
 Steal-0.428
BACK-0.391
zee-0.389
horn-0.373
TokenE
Token ID36
Feature activation+2.99e-01

Pos logit contributions
ascript+0.429
ウス+0.428
atism+0.394
hesion+0.391
 Tad+0.389
Neg logit contributions
alsh-0.350
 Steal-0.331
zee-0.303
BACK-0.303
horn-0.289
Token"
Token ID1
Feature activation+5.19e-01

Pos logit contributions
ウス+0.260
ascript+0.260
atism+0.240
hesion+0.239
 Tad+0.238
Neg logit contributions
alsh-0.189
 Steal-0.178
BACK-0.162
zee-0.162
horn-0.154
Token ||
Token ID8614
Feature activation+1.44e-01

Pos logit contributions
ウス+0.325
ascript+0.324
atism+0.291
hesion+0.290
 Tad+0.286
Neg logit contributions
alsh-0.451
 Steal-0.437
BACK-0.406
zee-0.403
horn-0.392
Token ethical
Token ID15028
Feature activation-2.02e-02

Pos logit contributions
ascript+0.981
ウス+0.978
atism+0.889
hesion+0.884
 Tad+0.878
Neg logit contributions
alsh-1.020
 Steal-0.971
zee-0.899
BACK-0.898
horn-0.863
Token pleas
Token ID21289
Feature activation+3.22e-01

Pos logit contributions
alsh+0.016
 Steal+0.016
zee+0.015
BACK+0.015
horn+0.014
Neg logit contributions
ascript-0.014
ウス-0.014
atism-0.013
hesion-0.012
 Tad-0.012
Token to
Token ID284
Feature activation+3.38e-01

Pos logit contributions
ascript+0.231
ウス+0.230
atism+0.209
hesion+0.207
 Tad+0.206
Neg logit contributions
alsh-0.252
 Steal-0.240
zee-0.223
BACK-0.223
horn-0.214
Token abolish
Token ID35531
Feature activation-2.85e-01

Pos logit contributions
ウス+0.243
ascript+0.242
atism+0.217
hesion+0.217
 Tad+0.214
Neg logit contributions
alsh-0.266
 Steal-0.255
zee-0.236
BACK-0.235
horn-0.226
Token child
Token ID1200
Feature activation+7.47e-01

Pos logit contributions
alsh+0.236
 Steal+0.226
zee+0.210
BACK+0.209
horn+0.202
Neg logit contributions
ウス-0.193
ascript-0.192
atism-0.172
hesion-0.172
 Tad-0.170
Token labor
Token ID4827
Feature activation+2.85e+00

Pos logit contributions
ウス+0.518
ascript+0.518
atism+0.468
hesion+0.468
 Tad+0.465
Neg logit contributions
alsh-0.595
 Steal-0.568
BACK-0.531
zee-0.530
horn-0.510
Token,
Token ID11
Feature activation+4.69e-01

Pos logit contributions
ウス+1.917
ascript+1.916
atism+1.751
hesion+1.720
 Tad+1.714
Neg logit contributions
alsh-2.308
 Steal-2.207
zee-2.066
BACK-2.065
horn-1.991
Token and
Token ID290
Feature activation-1.15e-01

Pos logit contributions
ascript+0.350
ウス+0.349
atism+0.317
hesion+0.315
 Tad+0.313
Neg logit contributions
alsh-0.355
 Steal-0.338
zee-0.312
BACK-0.312
horn-0.300
Token the
Token ID262
Feature activation-2.23e-02

Pos logit contributions
alsh+0.090
 Steal+0.086
zee+0.080
BACK+0.079
horn+0.076
Neg logit contributions
ウス-0.083
ascript-0.083
atism-0.074
hesion-0.074
 Tad-0.073
Token movement
Token ID3356
Feature activation+5.75e-01

Pos logit contributions
alsh+0.018
 Steal+0.017
zee+0.016
BACK+0.015
horn+0.015
Neg logit contributions
ascript-0.016
ウス-0.016
atism-0.014
hesion-0.014
 Tad-0.014
Token towards
Token ID3371
Feature activation+8.91e-02

Pos logit contributions
ascript+0.430
ウス+0.429
atism+0.389
hesion+0.387
 Tad+0.384
Neg logit contributions
alsh-0.435
 Steal-0.414
zee-0.382
BACK-0.382
horn-0.367
Token ==
Token ID6624
Feature activation+1.07e+00

Pos logit contributions
ウス+1.306
ascript+1.283
 partName+1.130
 Tad+1.108
 Iro+1.104
Neg logit contributions
alsh-3.262
 Steal-3.112
zee-2.973
BACK-2.967
horn-2.860
Token "
Token ID366
Feature activation+9.27e-01

Pos logit contributions
ウス+0.786
ascript+0.781
 Tad+0.726
 partName+0.725
)].+0.724
Neg logit contributions
alsh-0.818
 Steal-0.760
zee-0.710
BACK-0.707
horn-0.670
TokenA
Token ID32
Feature activation+2.83e-01

Pos logit contributions
ウス+0.672
ascript+0.671
atism+0.607
hesion+0.605
 Tad+0.601
Neg logit contributions
alsh-0.719
 Steal-0.684
zee-0.632
BACK-0.624
horn-0.606
Token"
Token ID1
Feature activation+7.94e-01

Pos logit contributions
ウス+0.220
ascript+0.218
 partName+0.203
hesion+0.202
)].+0.202
Neg logit contributions
alsh-0.201
 Steal-0.189
zee-0.173
BACK-0.172
horn-0.163
Token ||
Token ID8614
Feature activation+4.91e-01

Pos logit contributions
ascript+0.506
ウス+0.506
atism+0.455
hesion+0.451
 Tad+0.447
Neg logit contributions
alsh-0.685
 Steal-0.660
BACK-0.612
zee-0.611
horn-0.593
Token #
Token ID1303
Feature activation+2.85e+00

Pos logit contributions
ascript+0.164
ウス+0.163
atism+0.130
 Tad+0.128
hesion+0.128
Neg logit contributions
alsh-0.573
 Steal-0.553
zee-0.528
BACK-0.527
horn-0.514
Token ==
Token ID6624
Feature activation+1.15e+00

Pos logit contributions
ウス+1.236
ascript+1.209
 partName+1.057
 Iro+1.044
atism+1.042
Neg logit contributions
alsh-3.015
 Steal-2.872
zee-2.745
BACK-2.739
horn-2.638
Token "
Token ID366
Feature activation+8.74e-01

Pos logit contributions
ウス+0.839
ascript+0.833
 Tad+0.775
)].+0.775
 partName+0.773
Neg logit contributions
alsh-0.882
 Steal-0.819
zee-0.767
BACK-0.763
horn-0.722
TokenD
Token ID35
Feature activation-9.76e-01

Pos logit contributions
ウス+0.718
ascript+0.700
)].+0.655
 Tad+0.655
 partName+0.651
Neg logit contributions
alsh-0.593
 Steal-0.553
zee-0.506
BACK-0.490
horn-0.480
Token"
Token ID1
Feature activation+1.02e+00

Pos logit contributions
alsh+0.677
 Steal+0.641
zee+0.582
BACK+0.578
horn+0.552
Neg logit contributions
ウス-0.778
ascript-0.776
hesion-0.717
 partName-0.715
atism-0.714
Token &
Token ID1222
Feature activation+3.59e-01

Pos logit contributions
ascript+0.502
ウス+0.500
atism+0.432
hesion+0.428
 Tad+0.422
Neg logit contributions
alsh-1.037
 Steal-1.004
BACK-0.944
zee-0.941
horn-0.916
Token veterans
Token ID11255
Feature activation+4.01e-01

Pos logit contributions
alsh+0.430
 Steal+0.412
BACK+0.385
zee+0.384
horn+0.373
Neg logit contributions
ascript-0.317
ウス-0.315
atism-0.280
hesion-0.279
 Tad-0.275
Token and
Token ID290
Feature activation+5.70e-01

Pos logit contributions
ascript+0.279
ウス+0.278
atism+0.251
hesion+0.249
 Tad+0.247
Neg logit contributions
alsh-0.323
 Steal-0.308
zee-0.287
BACK-0.286
horn-0.276
Token female
Token ID4048
Feature activation+1.36e-02

Pos logit contributions
ascript+0.385
ウス+0.384
atism+0.343
hesion+0.342
 Tad+0.338
Neg logit contributions
alsh-0.474
 Steal-0.452
zee-0.421
BACK-0.420
horn-0.406
Token reporters
Token ID7638
Feature activation+1.11e+00

Pos logit contributions
ascript+0.009
ウス+0.009
atism+0.008
hesion+0.008
 Tad+0.008
Neg logit contributions
alsh-0.012
 Steal-0.011
zee-0.010
BACK-0.010
horn-0.010
Token).
Token ID737
Feature activation+1.34e-01

Pos logit contributions
ascript+0.747
ウス+0.746
atism+0.672
hesion+0.668
 Tad+0.664
Neg logit contributions
alsh-0.914
 Steal-0.873
zee-0.814
BACK-0.812
horn-0.783
Token Asked
Token ID26220
Feature activation+2.81e+00

Pos logit contributions
ascript+0.101
ウス+0.101
atism+0.092
hesion+0.091
 Tad+0.090
Neg logit contributions
alsh-0.101
 Steal-0.096
zee-0.089
BACK-0.089
horn-0.085
Token about
Token ID546
Feature activation+1.61e-01

Pos logit contributions
ascript+1.719
ウス+1.708
atism+1.529
hesion+1.517
 Tad+1.512
Neg logit contributions
alsh-2.490
 Steal-2.390
zee-2.243
BACK-2.239
horn-2.160
Token sexual
Token ID3206
Feature activation-3.63e-01

Pos logit contributions
ascript+0.107
ウス+0.107
atism+0.096
hesion+0.096
 Tad+0.094
Neg logit contributions
alsh-0.135
 Steal-0.129
BACK-0.119
zee-0.119
horn-0.115
Token harassment
Token ID10556
Feature activation+5.79e-01

Pos logit contributions
alsh+0.251
 Steal+0.237
BACK+0.218
zee+0.218
horn+0.208
Neg logit contributions
ascript-0.296
ウス-0.293
atism-0.269
hesion-0.268
 Tad-0.266
Token in
Token ID287
Feature activation-3.21e-02

Pos logit contributions
ascript+0.387
ウス+0.384
atism+0.345
hesion+0.344
 Tad+0.339
Neg logit contributions
alsh-0.486
 Steal-0.464
BACK-0.434
zee-0.432
horn-0.418
Token increasingly
Token ID6481
Feature activation-2.96e-01

Pos logit contributions
alsh+0.026
 Steal+0.025
zee+0.023
BACK+0.023
horn+0.022
Neg logit contributions
ascript-0.022
ウス-0.022
atism-0.020
hesion-0.020
 Tad-0.020
TokenVID
Token ID11008
Feature activation-8.30e-01

Pos logit contributions
alsh+0.431
 Steal+0.407
BACK+0.376
zee+0.373
horn+0.358
Neg logit contributions
ascript-0.564
ウス-0.560
atism-0.517
hesion-0.514
 Tad-0.511
TokenE
Token ID36
Feature activation-1.55e-01

Pos logit contributions
alsh+0.486
 Steal+0.461
BACK+0.416
zee+0.413
horn+0.390
Neg logit contributions
ascript-0.762
ウス-0.759
atism-0.704
hesion-0.698
 Tad-0.691
TokenOS
Token ID2640
Feature activation-3.55e-02

Pos logit contributions
alsh+0.159
 Steal+0.153
zee+0.144
BACK+0.144
horn+0.140
Neg logit contributions
ascript-0.074
ウス-0.073
atism-0.063
hesion-0.062
 Tad-0.062
Token HAVE
Token ID21515
Feature activation+2.64e-01

Pos logit contributions
alsh+0.027
 Steal+0.026
zee+0.024
BACK+0.024
horn+0.023
Neg logit contributions
ascript-0.026
ウス-0.026
atism-0.024
hesion-0.024
 Tad-0.024
Token BE
Token ID9348
Feature activation+9.21e-02

Pos logit contributions
ascript+0.187
ウス+0.187
atism+0.169
hesion+0.168
 Tad+0.167
Neg logit contributions
alsh-0.209
 Steal-0.200
zee-0.185
BACK-0.185
horn-0.178
TokenEN
Token ID1677
Feature activation+2.79e+00

Pos logit contributions
ascript+0.048
ウス+0.047
atism+0.041
hesion+0.041
 Tad+0.040
Neg logit contributions
alsh-0.091
 Steal-0.088
BACK-0.084
zee-0.083
horn-0.080
Token T
Token ID309
Feature activation+1.25e-01

Pos logit contributions
ウス+1.925
ascript+1.907
 Tad+1.747
atism+1.729
hesion+1.725
Neg logit contributions
alsh-2.241
 Steal-2.100
zee-1.977
BACK-1.947
horn-1.893
TokenAK
Token ID10206
Feature activation-4.37e-01

Pos logit contributions
ascript+0.096
ウス+0.096
atism+0.087
hesion+0.087
 Tad+0.086
Neg logit contributions
alsh-0.092
 Steal-0.088
BACK-0.081
zee-0.081
horn-0.077
TokenEN
Token ID1677
Feature activation-9.96e-02

Pos logit contributions
alsh+0.435
 Steal+0.420
BACK+0.398
zee+0.396
horn+0.384
Neg logit contributions
ascript-0.223
ウス-0.221
atism-0.193
hesion-0.191
 Tad-0.187
Token DOWN
Token ID30320
Feature activation-2.69e-01

Pos logit contributions
alsh+0.085
 Steal+0.081
BACK+0.076
zee+0.076
horn+0.073
Neg logit contributions
ascript-0.065
ウス-0.065
atism-0.058
hesion-0.058
 Tad-0.057
Token UP
Token ID15958
Feature activation-4.32e-01

Pos logit contributions
alsh+0.215
 Steal+0.207
BACK+0.193
zee+0.191
horn+0.185
Neg logit contributions
ascript-0.189
ウス-0.188
atism-0.170
hesion-0.169
 Tad-0.166
Token product
Token ID1720
Feature activation-7.22e-01

Pos logit contributions
ascript+0.132
ウス+0.131
atism+0.117
hesion+0.117
 Tad+0.115
Neg logit contributions
alsh-0.163
 Steal-0.157
zee-0.146
BACK-0.145
horn-0.140
Token of
Token ID286
Feature activation+4.18e-01

Pos logit contributions
alsh+0.547
 Steal+0.521
BACK+0.480
zee+0.480
horn+0.464
Neg logit contributions
ascript-0.535
ウス-0.532
atism-0.484
hesion-0.484
 Tad-0.480
Token a
Token ID257
Feature activation+2.60e-01

Pos logit contributions
ascript+0.289
ウス+0.288
atism+0.259
hesion+0.258
 Tad+0.255
Neg logit contributions
alsh-0.340
 Steal-0.325
zee-0.302
BACK-0.301
horn-0.291
Token LOT
Token ID30314
Feature activation-2.82e-01

Pos logit contributions
ascript+0.190
ウス+0.189
atism+0.171
hesion+0.170
 Tad+0.169
Neg logit contributions
alsh-0.201
 Steal-0.191
zee-0.177
BACK-0.176
horn-0.170
Token of
Token ID286
Feature activation+4.98e-01

Pos logit contributions
alsh+0.214
 Steal+0.204
BACK+0.190
zee+0.189
horn+0.182
Neg logit contributions
ascript-0.210
ウス-0.208
atism-0.189
hesion-0.188
 Tad-0.187
Token fuck
Token ID5089
Feature activation+2.78e+00

Pos logit contributions
ascript+0.380
ウス+0.379
atism+0.345
hesion+0.343
 Tad+0.340
Neg logit contributions
alsh-0.369
 Steal-0.351
zee-0.324
BACK-0.323
horn-0.310
Token ups
Token ID19649
Feature activation-1.48e+00

Pos logit contributions
ascript+2.008
ウス+2.008
atism+1.827
hesion+1.816
 Tad+1.804
Neg logit contributions
alsh-2.152
 Steal-2.055
zee-1.898
BACK-1.892
horn-1.820
Token.
Token ID13
Feature activation+3.94e-02

Pos logit contributions
alsh+1.146
 Steal+1.094
zee+1.017
BACK+1.008
horn+0.973
Neg logit contributions
ascript-1.080
ウス-1.076
atism-0.967
hesion-0.960
 Tad-0.949
Token One
Token ID1881
Feature activation-7.41e-02

Pos logit contributions
ascript+0.031
ウス+0.031
atism+0.028
hesion+0.028
 Tad+0.028
Neg logit contributions
alsh-0.028
 Steal-0.027
zee-0.024
BACK-0.024
horn-0.023
Token guy
Token ID3516
Feature activation+7.64e-01

Pos logit contributions
alsh+0.058
 Steal+0.056
zee+0.052
BACK+0.051
horn+0.050
Neg logit contributions
ascript-0.054
ウス-0.053
atism-0.048
hesion-0.048
 Tad-0.047
Token summed
Token ID32794
Feature activation-2.67e-01

Pos logit contributions
ascript+0.566
ウス+0.564
atism+0.514
hesion+0.511
 Tad+0.508
Neg logit contributions
alsh-0.580
 Steal-0.552
zee-0.511
BACK-0.510
horn-0.490
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
ascript+0.958
ウス+0.954
atism+0.867
hesion+0.862
 Tad+0.857
Neg logit contributions
alsh-1.030
 Steal-0.982
zee-0.911
BACK-0.910
horn-0.875
Token
Token ID198
Feature activation-2.27e-01

Pos logit contributions
ascript+0.078
ウス+0.078
atism+0.071
hesion+0.071
 Tad+0.070
Neg logit contributions
alsh-0.075
 Steal-0.072
zee-0.066
BACK-0.066
horn-0.063
Token
Token ID198
Feature activation-3.68e-01

Pos logit contributions
alsh+0.187
 Steal+0.178
zee+0.166
BACK+0.165
horn+0.158
Neg logit contributions
ウス-0.152
ascript-0.151
hesion-0.137
atism-0.137
 Tad-0.137
TokenAn
Token ID2025
Feature activation-5.97e-03

Pos logit contributions
alsh+0.229
 Steal+0.215
BACK+0.196
zee+0.196
horn+0.186
Neg logit contributions
ascript-0.325
ウス-0.323
atism-0.298
hesion-0.297
 Tad-0.295
Token athletic
Token ID15177
Feature activation-1.64e-01

Pos logit contributions
alsh+0.005
 Steal+0.004
zee+0.004
BACK+0.004
horn+0.004
Neg logit contributions
ascript-0.004
ウス-0.004
atism-0.004
hesion-0.004
 Tad-0.004
Token field
Token ID2214
Feature activation+2.77e+00

Pos logit contributions
alsh+0.136
 Steal+0.130
zee+0.121
BACK+0.121
horn+0.117
Neg logit contributions
ascript-0.110
ウス-0.110
atism-0.099
hesion-0.098
 Tad-0.097
Token at
Token ID379
Feature activation-6.14e-02

Pos logit contributions
ascript+1.892
ウス+1.891
atism+1.712
hesion+1.707
 Tad+1.694
Neg logit contributions
alsh-2.235
 Steal-2.136
zee-1.985
BACK-1.983
horn-1.896
Token Harvard
Token ID11131
Feature activation+4.82e-01

Pos logit contributions
alsh+0.051
 Steal+0.049
zee+0.046
BACK+0.045
horn+0.044
Neg logit contributions
ascript-0.041
ウス-0.041
atism-0.037
hesion-0.037
 Tad-0.036
Token-
Token ID12
Feature activation+3.55e-01

Pos logit contributions
ascript+0.339
ウス+0.337
atism+0.304
hesion+0.302
 Tad+0.299
Neg logit contributions
alsh-0.386
 Steal-0.369
zee-0.343
BACK-0.341
horn-0.330
TokenWest
Token ID15045
Feature activation+1.84e-01

Pos logit contributions
ascript+0.273
ウス+0.273
atism+0.249
hesion+0.247
 Tad+0.246
Neg logit contributions
alsh-0.260
 Steal-0.247
zee-0.228
BACK-0.227
horn-0.218
Tokenlake
Token ID27180
Feature activation-6.44e-01

Pos logit contributions
ウス+0.148
ascript+0.147
atism+0.135
hesion+0.135
 Tad+0.135
Neg logit contributions
alsh-0.127
 Steal-0.120
zee-0.111
BACK-0.111
horn-0.105
Tokenable
Token ID540
Feature activation-2.81e-01

Pos logit contributions
ウス+1.013
ascript+1.004
 Tad+0.917
hesion+0.907
 partName+0.906
Neg logit contributions
alsh-1.300
 Steal-1.212
zee-1.146
BACK-1.123
horn-1.097
Token version
Token ID2196
Feature activation-3.49e-01

Pos logit contributions
alsh+0.258
 Steal+0.246
zee+0.232
BACK+0.231
horn+0.225
Neg logit contributions
ascript-0.164
ウス-0.163
atism-0.144
hesion-0.144
 Tad-0.144
Token<|endoftext|>
Token ID50256
Feature activation+2.87e-01

Pos logit contributions
alsh+0.309
 Steal+0.302
BACK+0.283
zee+0.281
horn+0.269
Neg logit contributions
ascript-0.216
ウス-0.213
atism-0.188
hesion-0.186
 Iro-0.182
TokenRob
Token ID14350
Feature activation+9.59e-01

Pos logit contributions
ascript+0.239
ウス+0.239
atism+0.219
hesion+0.218
 Tad+0.217
Neg logit contributions
alsh-0.192
 Steal-0.181
BACK-0.166
zee-0.166
horn-0.158
Token C
Token ID327
Feature activation+8.00e-02

Pos logit contributions
ascript+0.639
ウス+0.637
atism+0.572
hesion+0.568
 Tad+0.563
Neg logit contributions
alsh-0.802
 Steal-0.767
zee-0.715
BACK-0.714
horn-0.690
Tokenestern
Token ID3330
Feature activation-3.82e+00

Pos logit contributions
ウス+0.067
ascript+0.067
atism+0.062
hesion+0.061
 Tad+0.061
Neg logit contributions
alsh-0.053
 Steal-0.050
zee-0.046
BACK-0.045
horn-0.044
Tokenino
Token ID2879
Feature activation+1.96e-02

Pos logit contributions
alsh+2.443
 Steal+2.273
zee+2.100
BACK+2.060
horn+1.993
Neg logit contributions
ascript-3.303
ウス-3.261
hesion-3.041
 partName-3.020
atism-3.018
Token hosts
Token ID11453
Feature activation-4.84e-01

Pos logit contributions
ウス+0.014
ascript+0.014
atism+0.013
hesion+0.013
 Tad+0.013
Neg logit contributions
alsh-0.015
 Steal-0.014
zee-0.013
BACK-0.013
horn-0.013
Token a
Token ID257
Feature activation-5.63e-01

Pos logit contributions
alsh+0.392
 Steal+0.377
BACK+0.349
zee+0.349
horn+0.336
Neg logit contributions
ascript-0.334
ウス-0.334
hesion-0.300
atism-0.300
 Tad-0.293
Token jam
Token ID16853
Feature activation-1.48e+00

Pos logit contributions
alsh+0.457
 Steal+0.438
zee+0.406
BACK+0.406
horn+0.391
Neg logit contributions
ascript-0.389
ウス-0.388
atism-0.349
hesion-0.348
 Tad-0.344
Token packed
Token ID11856
Feature activation-1.59e+00

Pos logit contributions
alsh+1.100
 Steal+1.048
zee+0.968
BACK+0.967
horn+0.931
Neg logit contributions
ascript-1.127
ウス-1.126
atism-1.026
hesion-1.020
 Tad-1.009
Token which
Token ID543
Feature activation+6.58e-01

Pos logit contributions
ascript+0.084
ウス+0.084
atism+0.076
hesion+0.075
 Tad+0.074
Neg logit contributions
alsh-0.089
 Steal-0.085
zee-0.079
BACK-0.079
horn-0.076
Token were
Token ID547
Feature activation-2.73e-01

Pos logit contributions
ascript+0.445
ウス+0.445
atism+0.398
hesion+0.396
 Tad+0.391
Neg logit contributions
alsh-0.544
 Steal-0.521
zee-0.485
BACK-0.483
horn-0.467
Token considered
Token ID3177
Feature activation+8.61e-02

Pos logit contributions
alsh+0.215
 Steal+0.205
BACK+0.191
zee+0.191
horn+0.184
Neg logit contributions
ウス-0.196
ascript-0.194
atism-0.175
hesion-0.174
 Tad-0.171
Token likely
Token ID1884
Feature activation-5.13e-01

Pos logit contributions
ascript+0.062
ウス+0.062
atism+0.056
hesion+0.056
 Tad+0.055
Neg logit contributions
alsh-0.067
 Steal-0.064
zee-0.059
BACK-0.059
horn-0.057
Token Apollo
Token ID17508
Feature activation-1.42e+00

Pos logit contributions
alsh+0.382
 Steal+0.365
BACK+0.337
zee+0.336
horn+0.324
Neg logit contributions
ウス-0.389
ascript-0.389
atism-0.353
hesion-0.350
 Tad-0.345
Token landing
Token ID9581
Feature activation-3.81e+00

Pos logit contributions
alsh+1.192
 Steal+1.146
zee+1.070
BACK+1.063
horn+1.029
Neg logit contributions
ascript-0.949
ウス-0.943
atism-0.844
hesion-0.838
 Tad-0.833
Token sites
Token ID5043
Feature activation-8.04e-01

Pos logit contributions
alsh+3.508
 Steal+3.395
BACK+3.215
zee+3.192
horn+3.102
Neg logit contributions
ascript-2.228
ウス-2.176
atism-1.930
hesion-1.890
 Tad-1.868
Token.
Token ID13
Feature activation+1.91e-01

Pos logit contributions
alsh+0.645
 Steal+0.616
zee+0.574
BACK+0.573
horn+0.552
Neg logit contributions
ウス-0.564
ascript-0.561
atism-0.506
hesion-0.501
 Tad-0.496
Token On
Token ID1550
Feature activation-5.56e-01

Pos logit contributions
ascript+0.149
ウス+0.149
atism+0.136
hesion+0.135
 Tad+0.134
Neg logit contributions
alsh-0.139
 Steal-0.132
zee-0.121
BACK-0.121
horn-0.116
Token the
Token ID262
Feature activation-2.95e-01

Pos logit contributions
alsh+0.473
 Steal+0.455
zee+0.425
BACK+0.423
horn+0.408
Neg logit contributions
ascript-0.366
ウス-0.366
atism-0.325
hesion-0.320
 partName-0.315
Token first
Token ID717
Feature activation-3.06e-01

Pos logit contributions
alsh+0.252
 Steal+0.243
zee+0.227
BACK+0.226
horn+0.219
Neg logit contributions
ascript-0.192
ウス-0.192
atism-0.171
hesion-0.169
 partName-0.166
Token [
Token ID685
Feature activation-1.93e+00

Pos logit contributions
alsh+0.169
 Steal+0.162
zee+0.151
BACK+0.150
horn+0.145
Neg logit contributions
ascript-0.141
ウス-0.141
atism-0.127
hesion-0.126
 Tad-0.125
Token10
Token ID940
Feature activation-5.34e-01

Pos logit contributions
alsh+1.438
 Steal+1.369
zee+1.263
BACK+1.257
horn+1.203
Neg logit contributions
ascript-1.449
ウス-1.448
atism-1.321
hesion-1.317
 Tad-1.307
Token:
Token ID25
Feature activation-1.03e+00

Pos logit contributions
alsh+0.526
 Steal+0.506
zee+0.477
BACK+0.477
horn+0.461
Neg logit contributions
ascript-0.273
ウス-0.273
atism-0.238
hesion-0.237
 Tad-0.236
Token47
Token ID2857
Feature activation-6.17e-01

Pos logit contributions
alsh+0.694
 Steal+0.658
zee+0.600
BACK+0.597
horn+0.568
Neg logit contributions
ウス-0.863
ascript-0.844
atism-0.786
hesion-0.780
 Iro-0.771
Token]
Token ID60
Feature activation-2.32e+00

Pos logit contributions
alsh+0.493
 Steal+0.470
zee+0.435
BACK+0.434
horn+0.415
Neg logit contributions
ウス-0.428
ascript-0.424
 Tad-0.389
hesion-0.388
)].-0.388
Token <@
Token ID32406
Feature activation-3.77e+00

Pos logit contributions
alsh+1.884
 Steal+1.811
BACK+1.690
zee+1.674
horn+1.623
Neg logit contributions
ウス-1.595
ascript-1.592
atism-1.447
hesion-1.430
)].-1.399
Tokent
Token ID83
Feature activation-7.31e-01

Pos logit contributions
alsh+2.823
 Steal+2.643
zee+2.551
BACK+2.462
horn+2.445
Neg logit contributions
ウス-2.829
ascript-2.825
atism-2.554
 partName-2.545
hesion-2.529
Tokenay
Token ID323
Feature activation-2.42e-01

Pos logit contributions
alsh+0.573
 Steal+0.546
zee+0.507
BACK+0.506
horn+0.487
Neg logit contributions
ascript-0.525
ウス-0.524
atism-0.474
hesion-0.471
 Tad-0.469
Tokenl
Token ID75
Feature activation-2.65e-01

Pos logit contributions
alsh+0.180
 Steal+0.171
zee+0.158
BACK+0.158
horn+0.152
Neg logit contributions
ascript-0.183
ウス-0.183
atism-0.167
hesion-0.166
 Tad-0.164
Tokenort
Token ID419
Feature activation+1.93e-01

Pos logit contributions
alsh+0.191
 Steal+0.182
BACK+0.167
zee+0.167
horn+0.160
Neg logit contributions
ascript-0.206
ウス-0.205
atism-0.188
hesion-0.187
 Tad-0.186
Tokenot
Token ID313
Feature activation+5.16e-01

Pos logit contributions
ascript+0.142
ウス+0.142
atism+0.129
hesion+0.128
 Tad+0.127
Neg logit contributions
alsh-0.148
 Steal-0.142
BACK-0.131
zee-0.131
horn-0.125
Token number
Token ID1271
Feature activation+3.55e-01

Pos logit contributions
ascript+0.006
ウス+0.006
atism+0.005
hesion+0.005
 Tad+0.005
Neg logit contributions
alsh-0.006
 Steal-0.006
zee-0.006
BACK-0.006
horn-0.005
Token called
Token ID1444
Feature activation-6.38e-01

Pos logit contributions
ascript+0.248
ウス+0.248
atism+0.224
hesion+0.223
 Tad+0.221
Neg logit contributions
alsh-0.284
 Steal-0.271
zee-0.252
BACK-0.252
horn-0.242
Token
Token ID564
Feature activation-4.17e-01

Pos logit contributions
alsh+0.485
 Steal+0.465
zee+0.428
BACK+0.427
horn+0.411
Neg logit contributions
ascript-0.475
ウス-0.473
atism-0.429
hesion-0.428
 Tad-0.422
Token
Token ID250
Feature activation-4.27e-03

Pos logit contributions
alsh+0.348
 Steal+0.333
BACK+0.310
zee+0.310
horn+0.299
Neg logit contributions
ascript-0.278
ウス-0.276
atism-0.249
hesion-0.248
 Tad-0.245
TokenThe
Token ID464
Feature activation+2.76e-02

Pos logit contributions
alsh+0.003
 Steal+0.003
zee+0.002
BACK+0.002
horn+0.002
Neg logit contributions
ascript-0.004
ウス-0.004
atism-0.003
hesion-0.003
 Tad-0.003
Token Count
Token ID2764
Feature activation-3.46e+00

Pos logit contributions
ascript+0.019
ウス+0.019
atism+0.017
hesion+0.017
 Tad+0.017
Neg logit contributions
alsh-0.022
 Steal-0.021
zee-0.020
BACK-0.020
horn-0.019
Token,
Token ID11
Feature activation-1.86e-01

Pos logit contributions
alsh+2.732
 Steal+2.643
zee+2.412
BACK+2.402
horn+2.353
Neg logit contributions
ascript-2.483
ウス-2.437
atism-2.213
hesion-2.205
 partName-2.179
Token
Token ID447
Feature activation+3.52e-01

Pos logit contributions
alsh+0.148
 Steal+0.141
zee+0.131
BACK+0.131
horn+0.126
Neg logit contributions
ascript-0.131
ウス-0.131
atism-0.118
hesion-0.117
 Tad-0.116
Token
Token ID251
Feature activation-6.69e-02

Pos logit contributions
ウス+0.222
ascript+0.221
atism+0.197
hesion+0.197
 Tad+0.196
Neg logit contributions
alsh-0.306
 Steal-0.294
zee-0.275
BACK-0.275
horn-0.265
Token which
Token ID543
Feature activation+1.05e-01

Pos logit contributions
alsh+0.050
 Steal+0.048
zee+0.044
BACK+0.044
horn+0.042
Neg logit contributions
ascript-0.051
ウス-0.050
atism-0.046
hesion-0.046
 Tad-0.045
Token is
Token ID318
Feature activation-2.38e-01

Pos logit contributions
ascript+0.076
ウス+0.075
atism+0.068
hesion+0.068
 Tad+0.067
Neg logit contributions
alsh-0.082
 Steal-0.078
zee-0.073
BACK-0.072
horn-0.070
Token [
Token ID685
Feature activation-2.05e+00

Pos logit contributions
alsh+0.390
 Steal+0.374
zee+0.349
BACK+0.347
horn+0.336
Neg logit contributions
ascript-0.311
ウス-0.310
atism-0.279
hesion-0.277
 Tad-0.273
Token10
Token ID940
Feature activation-7.23e-01

Pos logit contributions
alsh+1.532
 Steal+1.457
zee+1.346
BACK+1.338
horn+1.280
Neg logit contributions
ascript-1.540
ウス-1.540
atism-1.404
hesion-1.400
 Tad-1.390
Token:
Token ID25
Feature activation-1.42e+00

Pos logit contributions
alsh+0.711
 Steal+0.683
zee+0.644
BACK+0.643
horn+0.622
Neg logit contributions
ascript-0.373
ウス-0.373
atism-0.325
hesion-0.324
 Tad-0.321
Token47
Token ID2857
Feature activation-8.42e-01

Pos logit contributions
alsh+0.992
 Steal+0.942
zee+0.864
BACK+0.862
horn+0.828
Neg logit contributions
ascript-1.142
ウス-1.142
atism-1.044
hesion-1.037
 Tad-1.025
Token]
Token ID60
Feature activation-2.04e+00

Pos logit contributions
alsh+0.667
 Steal+0.635
zee+0.588
BACK+0.587
horn+0.561
Neg logit contributions
ウス-0.590
ascript-0.588
hesion-0.536
 Tad-0.536
atism-0.535
Token <
Token ID1279
Feature activation-3.46e+00

Pos logit contributions
alsh+1.655
 Steal+1.587
BACK+1.479
zee+1.467
horn+1.422
Neg logit contributions
ascript-1.403
ウス-1.403
atism-1.271
hesion-1.266
)].-1.235
Tokenmom
Token ID32542
Feature activation-7.04e-01

Pos logit contributions
alsh+2.628
 Steal+2.442
zee+2.339
BACK+2.290
horn+2.256
Neg logit contributions
ウス-2.562
ascript-2.550
atism-2.318
 Tad-2.297
hesion-2.295
Tokenper
Token ID525
Feature activation-1.89e-01

Pos logit contributions
alsh+0.528
 Steal+0.507
BACK+0.469
zee+0.459
horn+0.441
Neg logit contributions
ascript-0.529
ウス-0.520
atism-0.481
hesion-0.480
 Tad-0.466
Token>
Token ID29
Feature activation-1.85e-01

Pos logit contributions
alsh+0.151
 Steal+0.145
BACK+0.133
zee+0.132
horn+0.125
Neg logit contributions
ウス-0.131
ascript-0.130
hesion-0.120
atism-0.118
 partName-0.118
Token lol
Token ID19462
Feature activation-5.79e-01

Pos logit contributions
alsh+0.128
 Steal+0.122
zee+0.112
BACK+0.111
horn+0.107
Neg logit contributions
ascript-0.150
ウス-0.149
atism-0.137
hesion-0.136
 Tad-0.135
Token m
Token ID285
Feature activation-3.81e-01

Pos logit contributions
alsh+0.428
 Steal+0.407
zee+0.376
BACK+0.373
horn+0.359
Neg logit contributions
ascript-0.443
ウス-0.442
atism-0.403
hesion-0.401
 Tad-0.396
Token [
Token ID685
Feature activation-1.96e+00

Pos logit contributions
alsh+0.263
 Steal+0.250
BACK+0.236
zee+0.235
horn+0.227
Neg logit contributions
ascript-0.181
ウス-0.179
atism-0.161
 Tad-0.161
hesion-0.160
Token10
Token ID940
Feature activation-4.33e-01

Pos logit contributions
alsh+1.464
 Steal+1.393
zee+1.286
BACK+1.279
horn+1.224
Neg logit contributions
ウス-1.474
ascript-1.474
atism-1.343
hesion-1.340
 Tad-1.331
Token:
Token ID25
Feature activation-1.09e+00

Pos logit contributions
alsh+0.427
 Steal+0.410
zee+0.387
BACK+0.387
horn+0.374
Neg logit contributions
ascript-0.221
ウス-0.221
atism-0.192
hesion-0.192
 Tad-0.190
Token47
Token ID2857
Feature activation-5.59e-01

Pos logit contributions
alsh+0.786
 Steal+0.745
zee+0.687
BACK+0.686
horn+0.656
Neg logit contributions
ascript-0.849
ウス-0.846
atism-0.774
hesion-0.771
 Tad-0.768
Token]
Token ID60
Feature activation-1.92e+00

Pos logit contributions
alsh+0.445
 Steal+0.424
zee+0.393
BACK+0.392
horn+0.375
Neg logit contributions
ウス-0.389
ascript-0.387
hesion-0.354
 Tad-0.354
)].-0.353
Token <
Token ID1279
Feature activation-3.44e+00

Pos logit contributions
alsh+1.561
 Steal+1.496
BACK+1.394
zee+1.383
horn+1.341
Neg logit contributions
ascript-1.311
ウス-1.309
atism-1.186
hesion-1.181
 Tad-1.151
Tokensn
Token ID16184
Feature activation-1.59e+00

Pos logit contributions
alsh+2.622
 Steal+2.434
zee+2.332
BACK+2.285
horn+2.250
Neg logit contributions
ウス-2.542
ascript-2.532
atism-2.300
hesion-2.278
 Tad-2.276
Tokeniping
Token ID34690
Feature activation-2.27e-02

Pos logit contributions
alsh+1.162
 Steal+1.095
zee+1.017
BACK+1.007
horn+0.974
Neg logit contributions
ウス-1.236
ascript-1.230
atism-1.120
hesion-1.113
 Tad-1.112
Token117
Token ID17657
Feature activation-3.48e-01

Pos logit contributions
alsh+0.017
 Steal+0.016
BACK+0.015
zee+0.015
horn+0.015
Neg logit contributions
ascript-0.017
ウス-0.017
atism-0.015
hesion-0.015
 Tad-0.015
Token>
Token ID29
Feature activation-2.57e-01

Pos logit contributions
alsh+0.257
 Steal+0.244
zee+0.226
BACK+0.225
horn+0.217
Neg logit contributions
ascript-0.266
ウス-0.265
atism-0.242
hesion-0.241
 Tad-0.239
Token H
Token ID367
Feature activation-4.19e-01

Pos logit contributions
alsh+0.190
 Steal+0.181
zee+0.167
BACK+0.166
horn+0.160
Neg logit contributions
ascript-0.197
ウス-0.196
atism-0.179
hesion-0.178
 Tad-0.176
Token position
Token ID2292
Feature activation-1.13e+00

Pos logit contributions
alsh+1.268
 Steal+1.209
BACK+1.134
zee+1.130
horn+1.097
Neg logit contributions
ascript-1.061
ウス-1.059
atism-0.945
hesion-0.933
 Tad-0.925
Token lights
Token ID7588
Feature activation-9.33e-01

Pos logit contributions
alsh+0.579
 Steal+0.536
BACK+0.479
zee+0.477
horn+0.450
Neg logit contributions
ascript-1.123
ウス-1.122
atism-1.043
hesion-1.035
 Tad-1.028
Token were
Token ID547
Feature activation-1.14e-01

Pos logit contributions
alsh+0.746
 Steal+0.712
zee+0.662
BACK+0.658
horn+0.641
Neg logit contributions
ウス-0.661
ascript-0.656
atism-0.590
hesion-0.585
 Tad-0.575
Token now
Token ID783
Feature activation-1.63e-01

Pos logit contributions
alsh+0.084
 Steal+0.080
zee+0.074
BACK+0.074
horn+0.071
Neg logit contributions
ascript-0.086
ウス-0.086
atism-0.078
hesion-0.078
 Tad-0.077
Token c
Token ID269
Feature activation-8.36e-01

Pos logit contributions
alsh+0.124
 Steal+0.118
zee+0.109
BACK+0.109
horn+0.105
Neg logit contributions
ascript-0.121
ウス-0.121
atism-0.110
hesion-0.109
 Tad-0.108
Tokenanted
Token ID4126
Feature activation-3.43e+00

Pos logit contributions
alsh+0.543
 Steal+0.509
zee+0.468
BACK+0.465
horn+0.445
Neg logit contributions
ウス-0.714
ascript-0.713
atism-0.654
hesion-0.651
 Tad-0.649
Token inward
Token ID29879
Feature activation-2.31e-01

Pos logit contributions
alsh+2.487
 Steal+2.366
BACK+2.212
zee+2.181
horn+2.103
Neg logit contributions
ウス-2.627
ascript-2.619
atism-2.385
hesion-2.367
 partName-2.315
Token as
Token ID355
Feature activation-4.98e-01

Pos logit contributions
alsh+0.180
 Steal+0.172
zee+0.159
BACK+0.159
horn+0.153
Neg logit contributions
ウス-0.167
ascript-0.167
atism-0.151
hesion-0.150
 Tad-0.149
Token the
Token ID262
Feature activation+2.68e-02

Pos logit contributions
alsh+0.437
 Steal+0.419
zee+0.392
BACK+0.389
horn+0.377
Neg logit contributions
ウス-0.313
ascript-0.312
atism-0.278
hesion-0.275
 Tad-0.271
Token wings
Token ID12098
Feature activation+2.62e-01

Pos logit contributions
ascript+0.017
ウス+0.017
atism+0.015
hesion+0.015
 Tad+0.015
Neg logit contributions
alsh-0.023
 Steal-0.022
zee-0.021
BACK-0.021
horn-0.020
Token had
Token ID550
Feature activation-2.35e-01

Pos logit contributions
ウス+0.184
ascript+0.183
atism+0.165
hesion+0.164
 Tad+0.162
Neg logit contributions
alsh-0.211
 Steal-0.201
zee-0.188
BACK-0.186
horn-0.181
Token [
Token ID685
Feature activation-1.87e+00

Pos logit contributions
alsh+0.160
 Steal+0.153
zee+0.143
BACK+0.142
horn+0.138
Neg logit contributions
ascript-0.127
ウス-0.127
atism-0.114
hesion-0.113
 Tad-0.112
Token10
Token ID940
Feature activation-7.11e-01

Pos logit contributions
alsh+1.406
 Steal+1.339
zee+1.236
BACK+1.227
horn+1.172
Neg logit contributions
ascript-1.388
ウス-1.388
atism-1.266
hesion-1.264
 Tad-1.255
Token:
Token ID25
Feature activation-9.04e-01

Pos logit contributions
alsh+0.699
 Steal+0.671
zee+0.633
BACK+0.632
horn+0.612
Neg logit contributions
ascript-0.368
ウス-0.367
atism-0.320
hesion-0.319
 Tad-0.316
Token47
Token ID2857
Feature activation-6.28e-01

Pos logit contributions
alsh+0.615
 Steal+0.582
zee+0.531
BACK+0.528
horn+0.504
Neg logit contributions
ウス-0.750
ascript-0.736
atism-0.684
hesion-0.679
 Iro-0.669
Token]
Token ID60
Feature activation-2.10e+00

Pos logit contributions
alsh+0.501
 Steal+0.478
zee+0.443
BACK+0.442
horn+0.422
Neg logit contributions
ウス-0.436
ascript-0.433
 Tad-0.397
hesion-0.396
)].-0.395
Token <
Token ID1279
Feature activation-3.42e+00

Pos logit contributions
alsh+1.671
 Steal+1.605
BACK+1.489
zee+1.478
horn+1.430
Neg logit contributions
ウス-1.478
ascript-1.471
atism-1.341
hesion-1.331
)].-1.302
Tokensych
Token ID2924
Feature activation-1.90e+00

Pos logit contributions
alsh+2.613
 Steal+2.435
zee+2.333
BACK+2.289
horn+2.250
Neg logit contributions
ウス-2.514
ascript-2.503
atism-2.267
hesion-2.255
 Tad-2.253
Tokenomen
Token ID3674
Feature activation-1.40e+00

Pos logit contributions
alsh+1.501
 Steal+1.413
zee+1.336
BACK+1.309
horn+1.275
Neg logit contributions
ウス-1.361
ascript-1.348
atism-1.220
hesion-1.220
 Tad-1.217
Token>
Token ID29
Feature activation+3.46e-01

Pos logit contributions
alsh+1.109
 Steal+1.051
zee+0.982
BACK+0.974
horn+0.945
Neg logit contributions
ascript-0.997
ウス-0.995
atism-0.901
hesion-0.895
 Tad-0.891
Token GU
Token ID19348
Feature activation+4.34e-02

Pos logit contributions
ascript+0.258
ウス+0.258
atism+0.235
hesion+0.233
 Tad+0.232
Neg logit contributions
alsh-0.262
 Steal-0.249
zee-0.230
BACK-0.230
horn-0.221
TokenYS
Token ID16309
Feature activation+4.93e-01

Pos logit contributions
ウス+0.018
ascript+0.018
atism+0.015
hesion+0.015
 Tad+0.015
Neg logit contributions
alsh-0.047
 Steal-0.045
zee-0.043
BACK-0.043
horn-0.042
Token [
Token ID685
Feature activation-1.79e+00

Pos logit contributions
alsh+0.276
 Steal+0.265
zee+0.247
BACK+0.246
horn+0.238
Neg logit contributions
ascript-0.222
ウス-0.222
atism-0.200
hesion-0.198
 Tad-0.196
Token10
Token ID940
Feature activation-5.39e-01

Pos logit contributions
alsh+1.341
 Steal+1.277
zee+1.180
BACK+1.171
horn+1.120
Neg logit contributions
ウス-1.334
ascript-1.334
atism-1.216
hesion-1.214
 Tad-1.205
Token:
Token ID25
Feature activation-8.68e-01

Pos logit contributions
alsh+0.531
 Steal+0.510
zee+0.481
BACK+0.480
horn+0.465
Neg logit contributions
ascript-0.276
ウス-0.276
atism-0.241
hesion-0.240
 Tad-0.238
Token47
Token ID2857
Feature activation-6.64e-01

Pos logit contributions
alsh+0.630
 Steal+0.597
zee+0.551
BACK+0.550
horn+0.526
Neg logit contributions
ascript-0.673
ウス-0.670
atism-0.613
hesion-0.611
 Tad-0.609
Token]
Token ID60
Feature activation-1.79e+00

Pos logit contributions
alsh+0.527
 Steal+0.503
zee+0.466
BACK+0.464
horn+0.444
Neg logit contributions
ウス-0.463
ascript-0.461
hesion-0.421
 Tad-0.421
atism-0.420
Token <
Token ID1279
Feature activation-3.42e+00

Pos logit contributions
alsh+1.496
 Steal+1.435
BACK+1.336
zee+1.333
horn+1.289
Neg logit contributions
ascript-1.192
ウス-1.191
atism-1.070
hesion-1.063
 Tad-1.046
Tokenk
Token ID74
Feature activation-7.43e-01

Pos logit contributions
alsh+2.613
 Steal+2.431
zee+2.320
BACK+2.277
horn+2.243
Neg logit contributions
ウス-2.518
ascript-2.507
atism-2.279
hesion-2.254
 Tad-2.252
Tokenasse
Token ID21612
Feature activation-5.96e-01

Pos logit contributions
alsh+0.478
 Steal+0.449
zee+0.412
BACK+0.408
horn+0.392
Neg logit contributions
ウス-0.639
ascript-0.638
atism-0.588
hesion-0.584
 Tad-0.583
Tokenmm
Token ID3020
Feature activation+3.69e-01

Pos logit contributions
alsh+0.457
 Steal+0.434
zee+0.404
BACK+0.401
horn+0.388
Neg logit contributions
ascript-0.438
ウス-0.438
atism-0.397
hesion-0.395
 Tad-0.393
Tokenel
Token ID417
Feature activation-1.06e+00

Pos logit contributions
ascript+0.271
ウス+0.270
atism+0.246
hesion+0.244
 Tad+0.242
Neg logit contributions
alsh-0.282
 Steal-0.269
BACK-0.249
zee-0.248
horn-0.239
Token>
Token ID29
Feature activation+3.45e-02

Pos logit contributions
alsh+0.801
 Steal+0.761
zee+0.707
BACK+0.703
horn+0.678
Neg logit contributions
ascript-0.789
ウス-0.789
atism-0.717
hesion-0.712
 Tad-0.709
Token [
Token ID685
Feature activation-1.69e+00

Pos logit contributions
alsh+1.226
 Steal+1.174
zee+1.095
BACK+1.089
horn+1.054
Neg logit contributions
ascript-1.005
ウス-1.003
atism-0.902
hesion-0.896
 Tad-0.886
Token10
Token ID940
Feature activation-7.29e-01

Pos logit contributions
alsh+1.269
 Steal+1.209
zee+1.116
BACK+1.108
horn+1.060
Neg logit contributions
ウス-1.258
ascript-1.256
atism-1.146
hesion-1.143
 Tad-1.135
Token:
Token ID25
Feature activation-9.20e-01

Pos logit contributions
alsh+0.714
 Steal+0.686
zee+0.647
BACK+0.646
horn+0.626
Neg logit contributions
ascript-0.379
ウス-0.378
atism-0.330
hesion-0.328
 Tad-0.325
Token47
Token ID2857
Feature activation-6.68e-01

Pos logit contributions
alsh+0.645
 Steal+0.613
zee+0.562
BACK+0.561
horn+0.538
Neg logit contributions
ascript-0.737
ウス-0.737
atism-0.674
hesion-0.670
 Tad-0.662
Token]
Token ID60
Feature activation-1.68e+00

Pos logit contributions
alsh+0.529
 Steal+0.505
zee+0.468
BACK+0.466
horn+0.446
Neg logit contributions
ウス-0.467
ascript-0.465
hesion-0.424
 Tad-0.424
atism-0.423
Token <
Token ID1279
Feature activation-3.40e+00

Pos logit contributions
alsh+1.372
 Steal+1.317
BACK+1.228
zee+1.215
horn+1.178
Neg logit contributions
ウス-1.151
ascript-1.150
atism-1.044
hesion-1.038
)].-1.013
Tokenfen
Token ID41037
Feature activation-2.91e-01

Pos logit contributions
alsh+2.597
 Steal+2.410
zee+2.308
BACK+2.260
horn+2.230
Neg logit contributions
ウス-2.513
ascript-2.502
atism-2.273
hesion-2.253
 Tad-2.251
Tokenren
Token ID918
Feature activation-1.76e-01

Pos logit contributions
alsh+0.220
 Steal+0.209
zee+0.194
BACK+0.193
horn+0.186
Neg logit contributions
ascript-0.216
ウス-0.216
atism-0.196
hesion-0.195
 Tad-0.194
Token>
Token ID29
Feature activation+2.71e-02

Pos logit contributions
alsh+0.135
 Steal+0.129
zee+0.119
BACK+0.119
horn+0.115
Neg logit contributions
ascript-0.129
ウス-0.129
atism-0.117
hesion-0.116
 Tad-0.116
Token m
Token ID285
Feature activation-6.28e-01

Pos logit contributions
ascript+0.021
ウス+0.021
atism+0.019
hesion+0.019
 Tad+0.019
Neg logit contributions
alsh-0.020
 Steal-0.019
zee-0.018
BACK-0.018
horn-0.017
Token2
Token ID17
Feature activation-5.37e-01

Pos logit contributions
alsh+0.453
 Steal+0.428
zee+0.398
BACK+0.390
horn+0.379
Neg logit contributions
ウス-0.495
ascript-0.492
atism-0.451
hesion-0.446
 Tad-0.444
Token [
Token ID685
Feature activation-2.05e+00

Pos logit contributions
alsh+0.019
 Steal+0.018
zee+0.017
BACK+0.017
horn+0.016
Neg logit contributions
ascript-0.016
ウス-0.016
atism-0.014
hesion-0.014
 Tad-0.014
Token10
Token ID940
Feature activation-6.50e-01

Pos logit contributions
alsh+1.520
 Steal+1.445
zee+1.334
BACK+1.329
horn+1.274
Neg logit contributions
ascript-1.558
ウス-1.557
atism-1.419
hesion-1.413
 Tad-1.404
Token:
Token ID25
Feature activation-1.14e+00

Pos logit contributions
alsh+0.638
 Steal+0.613
zee+0.578
BACK+0.577
horn+0.559
Neg logit contributions
ascript-0.337
ウス-0.337
atism-0.293
hesion-0.292
 Tad-0.290
Token48
Token ID2780
Feature activation-6.86e-01

Pos logit contributions
alsh+0.820
 Steal+0.774
BACK+0.716
zee+0.715
horn+0.676
Neg logit contributions
ウス-0.904
ascript-0.897
hesion-0.824
atism-0.824
 Iro-0.806
Token]
Token ID60
Feature activation-2.18e+00

Pos logit contributions
alsh+0.542
 Steal+0.516
zee+0.478
BACK+0.476
horn+0.456
Neg logit contributions
ウス-0.483
ascript-0.481
hesion-0.439
 Tad-0.438
atism-0.438
Token <
Token ID1279
Feature activation-3.39e+00

Pos logit contributions
alsh+1.778
 Steal+1.706
BACK+1.593
zee+1.575
horn+1.530
Neg logit contributions
ascript-1.490
ウス-1.489
atism-1.349
hesion-1.342
)].-1.309
Tokenmom
Token ID32542
Feature activation-5.76e-01

Pos logit contributions
alsh+2.609
 Steal+2.424
zee+2.319
BACK+2.273
horn+2.241
Neg logit contributions
ウス-2.490
ascript-2.478
atism-2.251
hesion-2.227
 Tad-2.222
Tokenper
Token ID525
Feature activation-2.54e-01

Pos logit contributions
alsh+0.433
 Steal+0.416
BACK+0.384
zee+0.377
horn+0.361
Neg logit contributions
ascript-0.433
ウス-0.425
atism-0.393
hesion-0.393
 Tad-0.381
Token>
Token ID29
Feature activation-1.58e-01

Pos logit contributions
alsh+0.202
 Steal+0.193
BACK+0.178
zee+0.177
horn+0.167
Neg logit contributions
ウス-0.176
ascript-0.175
hesion-0.161
atism-0.160
 partName-0.159
Token lol
Token ID19462
Feature activation-7.81e-01

Pos logit contributions
alsh+0.107
 Steal+0.102
zee+0.093
BACK+0.093
horn+0.089
Neg logit contributions
ascript-0.131
ウス-0.130
atism-0.119
hesion-0.119
 Tad-0.118
Token m
Token ID285
Feature activation-6.21e-01

Pos logit contributions
alsh+0.571
 Steal+0.544
zee+0.501
BACK+0.498
horn+0.479
Neg logit contributions
ascript-0.603
ウス-0.602
atism-0.548
hesion-0.547
 Tad-0.539
Token [
Token ID685
Feature activation-1.88e+00

Pos logit contributions
alsh+0.056
 Steal+0.054
zee+0.050
BACK+0.050
horn+0.049
Neg logit contributions
ascript-0.044
ウス-0.044
atism-0.040
hesion-0.040
 Tad-0.039
Token10
Token ID940
Feature activation-5.35e-01

Pos logit contributions
alsh+1.407
 Steal+1.338
zee+1.237
BACK+1.228
horn+1.175
Neg logit contributions
ウス-1.403
ascript-1.401
atism-1.277
hesion-1.275
 Tad-1.266
Token:
Token ID25
Feature activation-9.56e-01

Pos logit contributions
alsh+0.527
 Steal+0.506
zee+0.478
BACK+0.477
horn+0.462
Neg logit contributions
ascript-0.275
ウス-0.275
atism-0.239
hesion-0.238
 Tad-0.237
Token47
Token ID2857
Feature activation-5.56e-01

Pos logit contributions
alsh+0.692
 Steal+0.656
zee+0.605
BACK+0.604
horn+0.578
Neg logit contributions
ascript-0.742
ウス-0.739
atism-0.677
hesion-0.674
 Tad-0.672
Token]
Token ID60
Feature activation-1.87e+00

Pos logit contributions
alsh+0.443
 Steal+0.422
zee+0.391
BACK+0.389
horn+0.372
Neg logit contributions
ウス-0.387
ascript-0.384
hesion-0.351
 Tad-0.351
atism-0.350
Token <
Token ID1279
Feature activation-3.39e+00

Pos logit contributions
alsh+1.521
 Steal+1.459
BACK+1.360
zee+1.348
horn+1.307
Neg logit contributions
ascript-1.274
ウス-1.273
atism-1.154
hesion-1.148
 Tad-1.120
Tokenmom
Token ID32542
Feature activation-4.01e-01

Pos logit contributions
alsh+2.598
 Steal+2.417
zee+2.311
BACK+2.267
horn+2.232
Neg logit contributions
ウス-2.493
ascript-2.484
atism-2.256
 Tad-2.234
hesion-2.234
Tokenper
Token ID525
Feature activation+2.12e-01

Pos logit contributions
alsh+0.302
 Steal+0.291
BACK+0.269
zee+0.263
horn+0.252
Neg logit contributions
ascript-0.300
ウス-0.294
hesion-0.273
atism-0.272
 Tad-0.264
Token>
Token ID29
Feature activation+2.60e-02

Pos logit contributions
ウス+0.145
ascript+0.144
hesion+0.133
 partName+0.131
atism+0.131
Neg logit contributions
alsh-0.171
 Steal-0.164
BACK-0.151
zee-0.149
horn-0.141
Token lol
Token ID19462
Feature activation-6.73e-01

Pos logit contributions
ascript+0.021
ウス+0.021
atism+0.019
hesion+0.019
 Tad+0.019
Neg logit contributions
alsh-0.018
 Steal-0.017
zee-0.016
BACK-0.015
horn-0.015
Token m
Token ID285
Feature activation-4.24e-01

Pos logit contributions
alsh+0.496
 Steal+0.473
zee+0.436
BACK+0.433
horn+0.417
Neg logit contributions
ascript-0.516
ウス-0.516
atism-0.469
hesion-0.467
 Tad-0.461
Token [
Token ID685
Feature activation-1.91e+00

Pos logit contributions
alsh+0.092
 Steal+0.088
BACK+0.082
zee+0.082
horn+0.079
Neg logit contributions
ascript-0.065
ウス-0.065
atism-0.058
hesion-0.058
 Tad-0.058
Token10
Token ID940
Feature activation-5.58e-01

Pos logit contributions
alsh+1.417
 Steal+1.347
zee+1.244
BACK+1.239
horn+1.187
Neg logit contributions
ascript-1.449
ウス-1.447
atism-1.319
hesion-1.314
 Tad-1.305
Token:
Token ID25
Feature activation-1.05e+00

Pos logit contributions
alsh+0.549
 Steal+0.527
zee+0.498
BACK+0.497
horn+0.481
Neg logit contributions
ascript-0.287
ウス-0.286
atism-0.249
hesion-0.249
 Tad-0.247
Token48
Token ID2780
Feature activation-8.08e-01

Pos logit contributions
alsh+0.753
 Steal+0.711
BACK+0.658
zee+0.656
horn+0.622
Neg logit contributions
ウス-0.826
ascript-0.820
atism-0.752
hesion-0.751
 Iro-0.737
Token]
Token ID60
Feature activation-2.04e+00

Pos logit contributions
alsh+0.638
 Steal+0.607
zee+0.562
BACK+0.560
horn+0.537
Neg logit contributions
ウス-0.571
ascript-0.569
hesion-0.518
atism-0.517
 Tad-0.517
Token <
Token ID1279
Feature activation-3.39e+00

Pos logit contributions
alsh+1.667
 Steal+1.598
BACK+1.493
zee+1.476
horn+1.434
Neg logit contributions
ascript-1.391
ウス-1.390
atism-1.260
hesion-1.254
)].-1.222
Tokenqu
Token ID421
Feature activation-5.98e-01

Pos logit contributions
alsh+2.595
 Steal+2.413
zee+2.307
BACK+2.265
horn+2.230
Neg logit contributions
ウス-2.494
ascript-2.484
atism-2.256
hesion-2.233
 Tad-2.233
Tokenij
Token ID2926
Feature activation-6.33e-01

Pos logit contributions
alsh+0.448
 Steal+0.422
zee+0.395
BACK+0.390
horn+0.377
Neg logit contributions
ウス-0.456
ascript-0.450
atism-0.409
 Tad-0.407
hesion-0.407
Tokenii
Token ID4178
Feature activation-6.43e-02

Pos logit contributions
alsh+0.388
 Steal+0.368
BACK+0.337
zee+0.324
horn+0.315
Neg logit contributions
ascript-0.560
ウス-0.554
atism-0.517
hesion-0.517
 Tad-0.509
Token>
Token ID29
Feature activation-1.04e-01

Pos logit contributions
alsh+0.051
 Steal+0.049
BACK+0.045
zee+0.045
horn+0.043
Neg logit contributions
ウス-0.044
ascript-0.044
hesion-0.040
atism-0.040
 partName-0.040
Token 2
Token ID362
Feature activation-3.10e-01

Pos logit contributions
alsh+0.079
 Steal+0.075
zee+0.069
BACK+0.069
horn+0.067
Neg logit contributions
ascript-0.077
ウス-0.077
atism-0.070
hesion-0.070
 Tad-0.069
Token [
Token ID685
Feature activation-1.83e+00

Pos logit contributions
alsh+0.219
 Steal+0.210
zee+0.196
BACK+0.195
horn+0.189
Neg logit contributions
ascript-0.174
ウス-0.174
atism-0.156
hesion-0.156
 Tad-0.153
Token10
Token ID940
Feature activation-5.08e-01

Pos logit contributions
alsh+1.370
 Steal+1.304
zee+1.205
BACK+1.197
horn+1.144
Neg logit contributions
ウス-1.364
ascript-1.363
atism-1.242
hesion-1.240
 Tad-1.232
Token:
Token ID25
Feature activation-1.05e+00

Pos logit contributions
alsh+0.501
 Steal+0.481
zee+0.454
BACK+0.453
horn+0.438
Neg logit contributions
ascript-0.261
ウス-0.261
atism-0.227
hesion-0.226
 Tad-0.225
Token47
Token ID2857
Feature activation-6.33e-01

Pos logit contributions
alsh+0.760
 Steal+0.720
zee+0.664
BACK+0.663
horn+0.635
Neg logit contributions
ascript-0.821
ウス-0.818
atism-0.749
hesion-0.745
 Tad-0.743
Token]
Token ID60
Feature activation-2.03e+00

Pos logit contributions
alsh+0.503
 Steal+0.479
zee+0.444
BACK+0.443
horn+0.423
Neg logit contributions
ウス-0.441
ascript-0.439
hesion-0.401
 Tad-0.401
atism-0.400
Token <
Token ID1279
Feature activation-3.38e+00

Pos logit contributions
alsh+1.643
 Steal+1.576
BACK+1.467
zee+1.455
horn+1.411
Neg logit contributions
ascript-1.389
ウス-1.389
atism-1.259
hesion-1.254
)].-1.223
Tokenok
Token ID482
Feature activation-7.09e-01

Pos logit contributions
alsh+2.571
 Steal+2.389
zee+2.286
BACK+2.242
horn+2.207
Neg logit contributions
ウス-2.498
ascript-2.488
atism-2.259
hesion-2.239
 Tad-2.236
Tokenclock
Token ID15750
Feature activation+1.78e+00

Pos logit contributions
alsh+0.444
 Steal+0.414
zee+0.380
BACK+0.375
horn+0.360
Neg logit contributions
ウス-0.622
ascript-0.621
atism-0.574
hesion-0.570
 Tad-0.570
Tokenzy
Token ID7357
Feature activation-7.00e-03

Pos logit contributions
ascript+1.216
ウス+1.207
atism+1.090
hesion+1.082
 Tad+1.073
Neg logit contributions
alsh-1.445
 Steal-1.403
BACK-1.311
horn-1.235
zee-1.230
Token>
Token ID29
Feature activation-1.41e-01

Pos logit contributions
alsh+0.006
 Steal+0.005
BACK+0.005
zee+0.005
horn+0.005
Neg logit contributions
ウス-0.005
ascript-0.005
hesion-0.004
 partName-0.004
 Tad-0.004
Token lol
Token ID19462
Feature activation-6.29e-01

Pos logit contributions
alsh+0.105
 Steal+0.099
zee+0.092
BACK+0.092
horn+0.088
Neg logit contributions
ascript-0.107
ウス-0.106
atism-0.097
hesion-0.096
 Tad-0.096
Token [
Token ID685
Feature activation-1.84e+00

Pos logit contributions
alsh+0.236
 Steal+0.225
zee+0.210
BACK+0.209
horn+0.202
Neg logit contributions
ascript-0.199
ウス-0.199
atism-0.180
hesion-0.178
 Tad-0.177
Token10
Token ID940
Feature activation-5.81e-01

Pos logit contributions
alsh+1.387
 Steal+1.320
zee+1.220
BACK+1.211
horn+1.157
Neg logit contributions
ウス-1.371
ascript-1.370
atism-1.249
hesion-1.247
 Tad-1.238
Token:
Token ID25
Feature activation-9.83e-01

Pos logit contributions
alsh+0.572
 Steal+0.549
zee+0.518
BACK+0.517
horn+0.501
Neg logit contributions
ascript-0.299
ウス-0.299
atism-0.260
hesion-0.259
 Tad-0.257
Token47
Token ID2857
Feature activation-5.84e-01

Pos logit contributions
alsh+0.709
 Steal+0.672
zee+0.620
BACK+0.618
horn+0.592
Neg logit contributions
ascript-0.766
ウス-0.763
atism-0.698
hesion-0.695
 Tad-0.693
Token]
Token ID60
Feature activation-1.94e+00

Pos logit contributions
alsh+0.465
 Steal+0.443
zee+0.410
BACK+0.409
horn+0.391
Neg logit contributions
ウス-0.407
ascript-0.405
hesion-0.370
 Tad-0.369
atism-0.369
Token <
Token ID1279
Feature activation-3.36e+00

Pos logit contributions
alsh+1.580
 Steal+1.516
BACK+1.414
zee+1.400
horn+1.359
Neg logit contributions
ascript-1.325
ウス-1.325
atism-1.201
hesion-1.196
)].-1.165
Tokenchain
Token ID7983
Feature activation+4.88e-01

Pos logit contributions
alsh+2.574
 Steal+2.392
zee+2.288
BACK+2.244
horn+2.210
Neg logit contributions
ウス-2.475
ascript-2.465
atism-2.239
hesion-2.219
 Tad-2.217
Tokenx
Token ID87
Feature activation+1.27e+00

Pos logit contributions
ascript+0.354
ウス+0.353
atism+0.321
hesion+0.319
 Tad+0.316
Neg logit contributions
alsh-0.378
 Steal-0.361
zee-0.334
BACK-0.334
horn-0.321
Token9999
Token ID24214
Feature activation+1.47e+00

Pos logit contributions
ascript+0.944
ウス+0.937
atism+0.856
hesion+0.850
 Tad+0.840
Neg logit contributions
alsh-0.962
 Steal-0.922
BACK-0.849
zee-0.844
horn-0.807
Token>
Token ID29
Feature activation+3.09e-01

Pos logit contributions
ascript+1.079
ウス+1.076
atism+0.973
hesion+0.969
 Tad+0.959
Neg logit contributions
alsh-1.121
 Steal-1.076
BACK-0.994
zee-0.993
horn-0.950
Token lol
Token ID19462
Feature activation-5.00e-01

Pos logit contributions
ascript+0.234
ウス+0.233
atism+0.213
hesion+0.212
 Tad+0.210
Neg logit contributions
alsh-0.230
 Steal-0.218
zee-0.202
BACK-0.201
horn-0.193
Token [
Token ID685
Feature activation-1.91e+00

Pos logit contributions
alsh+0.066
 Steal+0.063
zee+0.059
BACK+0.059
horn+0.057
Neg logit contributions
ascript-0.057
ウス-0.057
atism-0.052
hesion-0.051
 Tad-0.051
Token10
Token ID940
Feature activation-6.43e-01

Pos logit contributions
alsh+1.433
 Steal+1.364
zee+1.259
BACK+1.252
horn+1.197
Neg logit contributions
ウス-1.432
ascript-1.432
atism-1.306
hesion-1.302
 Tad-1.293
Token:
Token ID25
Feature activation-1.02e+00

Pos logit contributions
alsh+0.631
 Steal+0.606
zee+0.572
BACK+0.571
horn+0.553
Neg logit contributions
ascript-0.333
ウス-0.332
atism-0.289
hesion-0.288
 Tad-0.286
Token47
Token ID2857
Feature activation-7.02e-01

Pos logit contributions
alsh+0.690
 Steal+0.657
zee+0.597
BACK+0.594
horn+0.571
Neg logit contributions
ウス-0.851
ascript-0.845
atism-0.778
hesion-0.772
 Iro-0.759
Token]
Token ID60
Feature activation-1.99e+00

Pos logit contributions
alsh+0.556
 Steal+0.530
zee+0.491
BACK+0.490
horn+0.468
Neg logit contributions
ウス-0.492
ascript-0.490
hesion-0.447
 Tad-0.447
atism-0.446
Token <
Token ID1279
Feature activation-3.36e+00

Pos logit contributions
alsh+1.608
 Steal+1.544
BACK+1.436
zee+1.425
horn+1.380
Neg logit contributions
ウス-1.366
ascript-1.366
atism-1.239
hesion-1.233
)].-1.203
Tokendan
Token ID25604
Feature activation-1.30e+00

Pos logit contributions
alsh+2.547
 Steal+2.369
zee+2.265
BACK+2.222
horn+2.186
Neg logit contributions
ウス-2.491
ascript-2.480
atism-2.255
hesion-2.235
 Tad-2.232
Tokenides
Token ID1460
Feature activation-5.41e-01

Pos logit contributions
alsh+1.012
 Steal+0.956
zee+0.897
BACK+0.886
horn+0.861
Neg logit contributions
ウス-0.944
ascript-0.941
atism-0.853
 Tad-0.848
hesion-0.846
Tokenu
Token ID84
Feature activation+6.34e-01

Pos logit contributions
alsh+0.410
 Steal+0.389
zee+0.362
BACK+0.360
horn+0.347
Neg logit contributions
ascript-0.402
ウス-0.401
atism-0.365
hesion-0.362
 Tad-0.361
Token>
Token ID29
Feature activation-3.05e-01

Pos logit contributions
ascript+0.432
ウス+0.429
atism+0.387
hesion+0.384
 Tad+0.382
Neg logit contributions
alsh-0.521
 Steal-0.499
BACK-0.464
zee-0.464
horn-0.446
Token lol
Token ID19462
Feature activation-7.90e-01

Pos logit contributions
alsh+0.226
 Steal+0.215
zee+0.198
BACK+0.198
horn+0.190
Neg logit contributions
ascript-0.232
ウス-0.231
atism-0.211
hesion-0.210
 Tad-0.208
Token [
Token ID685
Feature activation-1.93e+00

Pos logit contributions
alsh+0.262
 Steal+0.251
zee+0.234
BACK+0.233
horn+0.225
Neg logit contributions
ascript-0.210
ウス-0.210
atism-0.188
hesion-0.187
 Tad-0.185
Token10
Token ID940
Feature activation-5.95e-01

Pos logit contributions
alsh+1.447
 Steal+1.376
zee+1.271
BACK+1.263
horn+1.208
Neg logit contributions
ウス-1.444
ascript-1.444
atism-1.317
hesion-1.313
 Tad-1.305
Token:
Token ID25
Feature activation-1.11e+00

Pos logit contributions
alsh+0.587
 Steal+0.563
zee+0.532
BACK+0.531
horn+0.514
Neg logit contributions
ascript-0.305
ウス-0.305
atism-0.265
hesion-0.265
 Tad-0.263
Token47
Token ID2857
Feature activation-7.10e-01

Pos logit contributions
alsh+0.750
 Steal+0.711
zee+0.648
BACK+0.644
horn+0.615
Neg logit contributions
ウス-0.931
ascript-0.914
atism-0.849
hesion-0.843
 Iro-0.831
Token]
Token ID60
Feature activation-2.11e+00

Pos logit contributions
alsh+0.564
 Steal+0.538
zee+0.498
BACK+0.497
horn+0.475
Neg logit contributions
ウス-0.495
ascript-0.492
 Tad-0.450
hesion-0.450
atism-0.449
Token <
Token ID1279
Feature activation-3.35e+00

Pos logit contributions
alsh+1.702
 Steal+1.634
BACK+1.519
zee+1.507
horn+1.461
Neg logit contributions
ウス-1.457
ascript-1.453
atism-1.320
hesion-1.314
)].-1.282
Tokenok
Token ID482
Feature activation-8.70e-01

Pos logit contributions
alsh+2.560
 Steal+2.388
zee+2.284
BACK+2.238
horn+2.202
Neg logit contributions
ウス-2.470
ascript-2.456
atism-2.231
hesion-2.215
 Tad-2.214
Tokenclock
Token ID15750
Feature activation+1.44e+00

Pos logit contributions
alsh+0.678
 Steal+0.640
zee+0.603
BACK+0.593
horn+0.578
Neg logit contributions
ウス-0.630
ascript-0.625
atism-0.570
hesion-0.565
 Tad-0.565
Tokenzy
Token ID7357
Feature activation-4.44e-01

Pos logit contributions
ascript+1.060
ウス+1.056
atism+0.961
hesion+0.954
 Tad+0.946
Neg logit contributions
alsh-1.089
 Steal-1.046
BACK-0.966
zee-0.959
horn-0.918
Token>
Token ID29
Feature activation-3.22e-01

Pos logit contributions
alsh+0.330
 Steal+0.313
zee+0.290
BACK+0.289
horn+0.278
Neg logit contributions
ascript-0.338
ウス-0.337
atism-0.307
hesion-0.305
 Tad-0.303
Token Dude
Token ID40628
Feature activation+1.00e+00

Pos logit contributions
alsh+0.242
 Steal+0.230
zee+0.213
BACK+0.212
horn+0.204
Neg logit contributions
ascript-0.242
ウス-0.241
atism-0.219
hesion-0.218
 Tad-0.216
Token [
Token ID685
Feature activation-1.86e+00

Pos logit contributions
alsh+0.227
 Steal+0.216
BACK+0.204
zee+0.202
horn+0.196
Neg logit contributions
ascript-0.154
ウス-0.153
atism-0.138
 Tad-0.138
hesion-0.137
Token10
Token ID940
Feature activation-4.43e-01

Pos logit contributions
alsh+1.386
 Steal+1.319
zee+1.218
BACK+1.212
horn+1.160
Neg logit contributions
ascript-1.400
ウス-1.399
atism-1.275
hesion-1.272
 Tad-1.263
Token:
Token ID25
Feature activation-1.07e+00

Pos logit contributions
alsh+0.436
 Steal+0.419
zee+0.395
BACK+0.395
horn+0.382
Neg logit contributions
ascript-0.227
ウス-0.227
atism-0.198
hesion-0.197
 Tad-0.196
Token47
Token ID2857
Feature activation-5.64e-01

Pos logit contributions
alsh+0.774
 Steal+0.733
zee+0.677
BACK+0.675
horn+0.646
Neg logit contributions
ascript-0.830
ウス-0.827
atism-0.757
hesion-0.754
 Tad-0.751
Token]
Token ID60
Feature activation-1.96e+00

Pos logit contributions
alsh+0.448
 Steal+0.427
zee+0.395
BACK+0.394
horn+0.377
Neg logit contributions
ウス-0.393
ascript-0.391
hesion-0.357
 Tad-0.357
atism-0.356
Token <
Token ID1279
Feature activation-3.35e+00

Pos logit contributions
alsh+1.597
 Steal+1.532
BACK+1.427
zee+1.416
horn+1.372
Neg logit contributions
ascript-1.342
ウス-1.342
atism-1.216
hesion-1.211
)].-1.180
Tokenkw
Token ID46265
Feature activation-1.51e+00

Pos logit contributions
alsh+2.541
 Steal+2.362
zee+2.256
BACK+2.215
horn+2.180
Neg logit contributions
ウス-2.488
ascript-2.476
atism-2.251
hesion-2.228
 Tad-2.225
Tokenij
Token ID2926
Feature activation-4.73e-01

Pos logit contributions
alsh+1.175
 Steal+1.101
zee+1.038
BACK+1.019
horn+0.993
Neg logit contributions
ウス-1.106
ascript-1.099
atism-0.998
 Tad-0.993
hesion-0.992
Tokenibo
Token ID26762
Feature activation-3.44e-02

Pos logit contributions
alsh+0.361
 Steal+0.344
zee+0.318
BACK+0.317
horn+0.305
Neg logit contributions
ascript-0.349
ウス-0.348
atism-0.317
hesion-0.315
 Tad-0.312
Token00
Token ID405
Feature activation-3.06e-01

Pos logit contributions
alsh+0.026
 Steal+0.024
zee+0.022
BACK+0.022
horn+0.021
Neg logit contributions
ascript-0.026
ウス-0.026
atism-0.024
hesion-0.024
 Tad-0.023
Token800
Token ID7410
Feature activation-2.54e-01

Pos logit contributions
alsh+0.229
 Steal+0.218
zee+0.201
BACK+0.201
horn+0.192
Neg logit contributions
ascript-0.231
ウス-0.230
atism-0.210
hesion-0.209
 Tad-0.207
Token [
Token ID685
Feature activation-1.74e+00

Pos logit contributions
alsh+0.201
 Steal+0.193
zee+0.180
BACK+0.179
horn+0.173
Neg logit contributions
ascript-0.160
ウス-0.160
atism-0.144
hesion-0.143
 Tad-0.141
Token10
Token ID940
Feature activation-5.72e-01

Pos logit contributions
alsh+1.308
 Steal+1.245
zee+1.149
BACK+1.142
horn+1.091
Neg logit contributions
ascript-1.298
ウス-1.297
atism-1.183
hesion-1.181
 Tad-1.173
Token:
Token ID25
Feature activation-9.38e-01

Pos logit contributions
alsh+0.563
 Steal+0.541
zee+0.510
BACK+0.510
horn+0.493
Neg logit contributions
ascript-0.294
ウス-0.294
atism-0.256
hesion-0.255
 Tad-0.253
Token47
Token ID2857
Feature activation-5.97e-01

Pos logit contributions
alsh+0.637
 Steal+0.604
zee+0.551
BACK+0.548
horn+0.522
Neg logit contributions
ウス-0.779
ascript-0.764
atism-0.710
hesion-0.705
 Iro-0.695
Token]
Token ID60
Feature activation-2.10e+00

Pos logit contributions
alsh+0.476
 Steal+0.454
zee+0.420
BACK+0.419
horn+0.401
Neg logit contributions
ウス-0.414
ascript-0.411
 Tad-0.377
hesion-0.376
)].-0.375
Token <
Token ID1279
Feature activation-3.35e+00

Pos logit contributions
alsh+1.667
 Steal+1.602
BACK+1.486
zee+1.475
horn+1.429
Neg logit contributions
ウス-1.481
ascript-1.474
atism-1.342
hesion-1.331
)].-1.302
Tokenliterally
Token ID43819
Feature activation+1.53e+00

Pos logit contributions
alsh+2.557
 Steal+2.386
zee+2.282
BACK+2.240
horn+2.198
Neg logit contributions
ウス-2.461
ascript-2.453
atism-2.218
hesion-2.208
 Tad-2.205
Token_
Token ID62
Feature activation-5.38e-01

Pos logit contributions
ascript+1.152
ウス+1.146
atism+1.045
hesion+1.040
 Tad+1.029
Neg logit contributions
alsh-1.139
 Steal-1.091
BACK-1.004
zee-0.996
horn-0.952
Tokenworst
Token ID41430
Feature activation+9.67e-01

Pos logit contributions
alsh+0.403
 Steal+0.381
zee+0.356
BACK+0.353
horn+0.341
Neg logit contributions
ascript-0.406
ウス-0.405
atism-0.369
hesion-0.367
 Tad-0.365
Token_
Token ID62
Feature activation-1.22e-01

Pos logit contributions
ascript+0.690
ウス+0.688
atism+0.625
hesion+0.620
 Tad+0.613
Neg logit contributions
alsh-0.758
 Steal-0.727
BACK-0.672
zee-0.669
horn-0.640
Tokenuser
Token ID7220
Feature activation+2.27e-01

Pos logit contributions
alsh+0.091
 Steal+0.086
zee+0.080
BACK+0.080
horn+0.077
Neg logit contributions
ascript-0.092
ウス-0.092
atism-0.083
hesion-0.083
 Tad-0.082
Token [
Token ID685
Feature activation-1.83e+00

Pos logit contributions
alsh+0.237
 Steal+0.226
BACK+0.213
zee+0.211
horn+0.204
Neg logit contributions
ascript-0.166
ウス-0.164
atism-0.148
 Tad-0.147
hesion-0.147
Token10
Token ID940
Feature activation-5.35e-01

Pos logit contributions
alsh+1.378
 Steal+1.312
zee+1.212
BACK+1.203
horn+1.151
Neg logit contributions
ウス-1.367
ascript-1.365
atism-1.245
hesion-1.243
 Tad-1.234
Token:
Token ID25
Feature activation-1.13e+00

Pos logit contributions
alsh+0.527
 Steal+0.506
zee+0.477
BACK+0.477
horn+0.461
Neg logit contributions
ascript-0.275
ウス-0.274
atism-0.239
hesion-0.238
 Tad-0.236
Token47
Token ID2857
Feature activation-6.55e-01

Pos logit contributions
alsh+0.815
 Steal+0.773
zee+0.713
BACK+0.711
horn+0.681
Neg logit contributions
ascript-0.880
ウス-0.876
atism-0.802
hesion-0.799
 Tad-0.795
Token]
Token ID60
Feature activation-1.93e+00

Pos logit contributions
alsh+0.521
 Steal+0.496
zee+0.460
BACK+0.458
horn+0.438
Neg logit contributions
ウス-0.457
ascript-0.455
hesion-0.415
 Tad-0.415
atism-0.414
Token <
Token ID1279
Feature activation-3.33e+00

Pos logit contributions
alsh+1.568
 Steal+1.504
BACK+1.400
zee+1.390
horn+1.347
Neg logit contributions
ウス-1.323
ascript-1.323
atism-1.199
hesion-1.194
)].-1.163
Tokenen
Token ID268
Feature activation+1.23e-02

Pos logit contributions
alsh+2.521
 Steal+2.345
zee+2.242
BACK+2.199
horn+2.164
Neg logit contributions
ウス-2.477
ascript-2.464
atism-2.239
hesion-2.218
 Tad-2.217
Token7
Token ID22
Feature activation-6.40e-01

Pos logit contributions
ascript+0.009
ウス+0.009
atism+0.008
hesion+0.008
 Tad+0.008
Neg logit contributions
alsh-0.009
 Steal-0.009
BACK-0.008
zee-0.008
horn-0.008
Token_>
Token ID49029
Feature activation+1.81e-02

Pos logit contributions
alsh+0.503
 Steal+0.478
zee+0.446
BACK+0.443
horn+0.429
Neg logit contributions
ascript-0.458
ウス-0.457
atism-0.414
hesion-0.412
 Tad-0.410
Token lol
Token ID19462
Feature activation-6.71e-01

Pos logit contributions
ascript+0.013
ウス+0.013
atism+0.012
hesion+0.012
 Tad+0.012
Neg logit contributions
alsh-0.014
 Steal-0.013
zee-0.012
BACK-0.012
horn-0.012
Token Mang
Token ID27609
Feature activation-7.86e-01

Pos logit contributions
alsh+0.502
 Steal+0.478
zee+0.443
BACK+0.439
horn+0.423
Neg logit contributions
ascript-0.507
ウス-0.506
atism-0.460
hesion-0.457
 Tad-0.452
Token government
Token ID1230
Feature activation-3.47e-01

Pos logit contributions
alsh+0.320
 Steal+0.307
BACK+0.283
zee+0.283
horn+0.274
Neg logit contributions
ascript-0.285
ウス-0.282
atism-0.255
hesion-0.253
 Tad-0.251
Token did
Token ID750
Feature activation+2.29e-01

Pos logit contributions
alsh+0.283
 Steal+0.271
BACK+0.253
zee+0.252
horn+0.243
Neg logit contributions
ascript-0.238
ウス-0.238
atism-0.214
hesion-0.212
 Tad-0.210
Token almost
Token ID2048
Feature activation+2.03e-01

Pos logit contributions
ウス+0.152
ascript+0.151
atism+0.136
hesion+0.135
 Tad+0.134
Neg logit contributions
alsh-0.193
 Steal-0.185
BACK-0.172
zee-0.172
horn-0.167
Token 25
Token ID1679
Feature activation+1.13e-01

Pos logit contributions
ascript+0.157
ウス+0.156
atism+0.142
hesion+0.142
 Tad+0.141
Neg logit contributions
alsh-0.148
 Steal-0.141
zee-0.130
BACK-0.130
horn-0.124
Token years
Token ID812
Feature activation+1.27e-01

Pos logit contributions
ウス+0.074
ascript+0.074
atism+0.067
hesion+0.066
 Tad+0.066
Neg logit contributions
alsh-0.096
 Steal-0.092
zee-0.085
BACK-0.085
horn-0.083
Token ago
Token ID2084
Feature activation+1.45e+00

Pos logit contributions
ウス+0.080
ascript+0.079
atism+0.071
hesion+0.071
 Tad+0.070
Neg logit contributions
alsh-0.111
 Steal-0.106
BACK-0.101
zee-0.099
horn-0.098
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
ascript+0.960
ウス+0.957
atism+0.860
hesion+0.854
 Tad+0.848
Neg logit contributions
alsh-1.222
 Steal-1.169
zee-1.091
BACK-1.089
horn-1.050
Token Some
Token ID2773
Feature activation-1.12e+00

Pos logit contributions
alsh+0.093
 Steal+0.088
zee+0.081
BACK+0.081
horn+0.078
Neg logit contributions
ascript-0.099
ウス-0.098
atism-0.090
hesion-0.089
 Tad-0.089
Token restrictions
Token ID8733
Feature activation-1.50e-01

Pos logit contributions
alsh+0.904
 Steal+0.868
BACK+0.801
zee+0.801
horn+0.775
Neg logit contributions
ascript-0.786
ウス-0.781
atism-0.703
hesion-0.700
 Tad-0.694
Token have
Token ID423
Feature activation-2.96e-02

Pos logit contributions
alsh+0.117
 Steal+0.112
zee+0.104
BACK+0.104
horn+0.100
Neg logit contributions
ascript-0.107
ウス-0.107
atism-0.097
hesion-0.097
 Tad-0.096
Token already
Token ID1541
Feature activation-9.72e-01

Pos logit contributions
alsh+0.022
 Steal+0.021
BACK+0.020
zee+0.020
horn+0.019
Neg logit contributions
ascript-0.022
ウス-0.022
atism-0.020
hesion-0.020
 Tad-0.020
Token
Token ID247
Feature activation-6.34e-02

Pos logit contributions
alsh+0.000
 Steal+0.000
zee+0.000
BACK+0.000
horn+0.000
Neg logit contributions
ascript-0.000
ウス-0.000
atism-0.000
hesion-0.000
 Tad-0.000
Tokens
Token ID82
Feature activation+1.17e-01

Pos logit contributions
alsh+0.051
 Steal+0.049
zee+0.046
BACK+0.046
horn+0.044
Neg logit contributions
ascript-0.044
ウス-0.044
atism-0.040
hesion-0.039
 Tad-0.039
Token signature
Token ID9877
Feature activation+1.34e-01

Pos logit contributions
ascript+0.077
ウス+0.076
hesion+0.068
atism+0.068
 Tad+0.067
Neg logit contributions
alsh-0.100
 Steal-0.096
zee-0.089
BACK-0.089
horn-0.086
Token food
Token ID2057
Feature activation+6.55e-01

Pos logit contributions
ascript+0.082
ウス+0.082
atism+0.072
hesion+0.072
 Tad+0.070
Neg logit contributions
alsh-0.120
 Steal-0.115
zee-0.107
BACK-0.107
horn-0.104
Token.
Token ID13
Feature activation+3.99e-01

Pos logit contributions
ascript+0.447
ウス+0.446
atism+0.402
hesion+0.399
 Tad+0.396
Neg logit contributions
alsh-0.538
 Steal-0.514
zee-0.479
BACK-0.478
horn-0.461
Token Maps
Token ID20347
Feature activation+1.55e+00

Pos logit contributions
ascript+0.302
ウス+0.300
atism+0.274
hesion+0.273
 Tad+0.269
Neg logit contributions
alsh-0.298
 Steal-0.284
zee-0.262
BACK-0.261
horn-0.251
Token like
Token ID588
Feature activation-1.39e-01

Pos logit contributions
ascript+1.108
ウス+1.104
atism+1.002
hesion+0.998
 Tad+0.991
Neg logit contributions
alsh-1.216
 Steal-1.157
BACK-1.076
zee-1.075
horn-1.033
Token these
Token ID777
Feature activation-8.84e-01

Pos logit contributions
alsh+0.124
 Steal+0.119
zee+0.110
BACK+0.110
horn+0.106
Neg logit contributions
ascript-0.087
ウス-0.086
atism-0.076
hesion-0.076
 Tad-0.075
Token are
Token ID389
Feature activation-2.90e-01

Pos logit contributions
alsh+0.702
 Steal+0.676
zee+0.624
BACK+0.618
horn+0.597
Neg logit contributions
ウス-0.630
ascript-0.628
atism-0.563
hesion-0.561
 Tad-0.553
Token fun
Token ID1257
Feature activation+1.57e-02

Pos logit contributions
alsh+0.232
 Steal+0.223
BACK+0.206
zee+0.206
horn+0.199
Neg logit contributions
ウス-0.203
ascript-0.203
atism-0.183
hesion-0.182
 Tad-0.179
Token,
Token ID11
Feature activation-3.15e-01

Pos logit contributions
ascript+0.012
ウス+0.012
atism+0.011
hesion+0.011
 Tad+0.011
Neg logit contributions
alsh-0.012
 Steal-0.011
zee-0.010
BACK-0.010
horn-0.010
Token work
Token ID670
Feature activation+1.34e-01

Pos logit contributions
alsh+0.018
 Steal+0.017
zee+0.016
BACK+0.016
horn+0.015
Neg logit contributions
ascript-0.014
ウス-0.014
hesion-0.013
atism-0.013
 Tad-0.013
Token of
Token ID286
Feature activation+1.39e-01

Pos logit contributions
ascript+0.096
ウス+0.096
atism+0.086
hesion+0.086
 Tad+0.085
Neg logit contributions
alsh-0.106
 Steal-0.101
zee-0.093
BACK-0.093
horn-0.090
Token moving
Token ID3867
Feature activation-2.72e-01

Pos logit contributions
ascript+0.103
ウス+0.103
hesion+0.093
atism+0.093
 Tad+0.091
Neg logit contributions
alsh-0.107
 Steal-0.102
zee-0.094
BACK-0.094
horn-0.090
Token the
Token ID262
Feature activation-4.57e-01

Pos logit contributions
alsh+0.225
 Steal+0.215
zee+0.200
BACK+0.200
horn+0.193
Neg logit contributions
ascript-0.184
ウス-0.184
atism-0.165
hesion-0.164
 Tad-0.163
Token Democratic
Token ID4390
Feature activation-7.95e-02

Pos logit contributions
alsh+0.397
 Steal+0.381
BACK+0.355
zee+0.355
horn+0.343
Neg logit contributions
ascript-0.291
ウス-0.290
atism-0.258
hesion-0.257
 Tad-0.253
Token Party
Token ID3615
Feature activation+1.50e+00

Pos logit contributions
alsh+0.072
 Steal+0.069
zee+0.065
BACK+0.065
horn+0.063
Neg logit contributions
ascript-0.048
ウス-0.047
atism-0.042
hesion-0.042
 Tad-0.041
Token right
Token ID826
Feature activation+4.94e-01

Pos logit contributions
ascript+1.083
ウス+1.080
atism+0.980
hesion+0.974
 Tad+0.968
Neg logit contributions
alsh-1.169
 Steal-1.114
zee-1.034
BACK-1.031
horn-0.993
Tokenward
Token ID904
Feature activation+9.29e-01

Pos logit contributions
ascript+0.442
ウス+0.441
atism+0.407
hesion+0.406
 Tad+0.403
Neg logit contributions
alsh-0.301
 Steal-0.282
zee-0.256
BACK-0.255
horn-0.242
Token.
Token ID13
Feature activation+2.59e-01

Pos logit contributions
ascript+0.652
ウス+0.650
atism+0.587
hesion+0.584
 Tad+0.579
Neg logit contributions
alsh-0.744
 Steal-0.710
zee-0.659
BACK-0.659
horn-0.635
Token (
Token ID357
Feature activation-2.87e-01

Pos logit contributions
ascript+0.211
ウス+0.210
atism+0.193
hesion+0.192
 Tad+0.190
Neg logit contributions
alsh-0.178
 Steal-0.169
zee-0.155
BACK-0.155
horn-0.148
TokenBill
Token ID17798
Feature activation+5.29e-02

Pos logit contributions
alsh+0.178
 Steal+0.167
BACK+0.152
zee+0.152
horn+0.144
Neg logit contributions
ascript-0.254
ウス-0.252
atism-0.233
hesion-0.232
 Tad-0.231
Token and
Token ID290
Feature activation+3.14e-01

Pos logit contributions
ascript+0.108
ウス+0.108
atism+0.098
hesion+0.097
 Tad+0.096
Neg logit contributions
alsh-0.115
 Steal-0.110
zee-0.102
BACK-0.102
horn-0.098
Token Mexico
Token ID5828
Feature activation-4.46e-02

Pos logit contributions
ascript+0.198
ウス+0.197
atism+0.177
hesion+0.176
 Tad+0.175
Neg logit contributions
alsh-0.274
 Steal-0.261
zee-0.245
BACK-0.244
horn-0.237
Token to
Token ID284
Feature activation-9.14e-02

Pos logit contributions
alsh+0.034
 Steal+0.032
zee+0.030
BACK+0.030
horn+0.029
Neg logit contributions
ascript-0.033
ウス-0.033
atism-0.030
hesion-0.030
 Tad-0.029
Token craft
Token ID5977
Feature activation+4.02e-01

Pos logit contributions
alsh+0.069
 Steal+0.065
zee+0.061
BACK+0.060
horn+0.058
Neg logit contributions
ascript-0.068
ウス-0.068
atism-0.062
hesion-0.062
 Tad-0.061
Token a
Token ID257
Feature activation+6.59e-01

Pos logit contributions
ascript+0.260
ウス+0.260
atism+0.233
hesion+0.231
 Tad+0.229
Neg logit contributions
alsh-0.343
 Steal-0.328
zee-0.306
BACK-0.306
horn-0.296
Token North
Token ID2258
Feature activation+1.96e+00

Pos logit contributions
ascript+0.454
ウス+0.450
atism+0.410
hesion+0.409
 Tad+0.408
Neg logit contributions
alsh-0.534
 Steal-0.508
zee-0.475
BACK-0.472
horn-0.456
Token American
Token ID1605
Feature activation+3.11e-01

Pos logit contributions
ascript+1.128
ウス+1.118
hesion+0.993
atism+0.990
 Tad+0.989
Neg logit contributions
alsh-1.814
 Steal-1.718
zee-1.631
BACK-1.627
horn-1.555
Token climate
Token ID4258
Feature activation-2.00e-01

Pos logit contributions
ascript+0.223
ウス+0.222
atism+0.202
hesion+0.202
 Tad+0.201
Neg logit contributions
alsh-0.243
 Steal-0.231
zee-0.214
BACK-0.214
horn-0.206
Token agreement
Token ID4381
Feature activation+1.65e-01

Pos logit contributions
alsh+0.164
 Steal+0.157
zee+0.146
BACK+0.146
horn+0.141
Neg logit contributions
ascript-0.136
ウス-0.135
atism-0.122
hesion-0.121
 Tad-0.120
Token to
Token ID284
Feature activation+1.51e-01

Pos logit contributions
ascript+0.118
ウス+0.118
atism+0.106
hesion+0.106
 Tad+0.105
Neg logit contributions
alsh-0.131
 Steal-0.124
zee-0.116
BACK-0.115
horn-0.111
Token signal
Token ID6737
Feature activation-5.55e-01

Pos logit contributions
ascript+0.114
ウス+0.113
atism+0.105
hesion+0.104
 Tad+0.103
Neg logit contributions
alsh-0.112
 Steal-0.106
zee-0.099
BACK-0.098
horn-0.095
Token is
Token ID318
Feature activation+1.49e-02

Pos logit contributions
alsh+0.078
 Steal+0.074
zee+0.069
BACK+0.069
horn+0.066
Neg logit contributions
ascript-0.070
ウス-0.070
atism-0.063
hesion-0.063
 Tad-0.062
Token little
Token ID1310
Feature activation-2.64e-01

Pos logit contributions
ascript+0.011
ウス+0.011
atism+0.010
hesion+0.010
 Tad+0.010
Neg logit contributions
alsh-0.011
 Steal-0.011
zee-0.010
BACK-0.010
horn-0.010
Token agreement
Token ID4381
Feature activation+9.76e-02

Pos logit contributions
alsh+0.203
 Steal+0.193
zee+0.179
BACK+0.179
horn+0.172
Neg logit contributions
ascript-0.194
ウス-0.193
atism-0.175
hesion-0.174
 Tad-0.173
Token on
Token ID319
Feature activation-6.77e-01

Pos logit contributions
ascript+0.071
ウス+0.071
atism+0.065
hesion+0.064
 Tad+0.063
Neg logit contributions
alsh-0.075
 Steal-0.072
zee-0.067
BACK-0.067
horn-0.064
Token how
Token ID703
Feature activation+1.70e-01

Pos logit contributions
alsh+0.511
 Steal+0.487
BACK+0.448
zee+0.448
horn+0.429
Neg logit contributions
ascript-0.508
ウス-0.505
atism-0.459
hesion-0.457
 Tad-0.451
Token best
Token ID1266
Feature activation+1.89e+00

Pos logit contributions
ascript+0.123
ウス+0.123
atism+0.112
hesion+0.111
 Tad+0.110
Neg logit contributions
alsh-0.132
 Steal-0.125
zee-0.116
BACK-0.116
horn-0.112
Token to
Token ID284
Feature activation-1.01e-01

Pos logit contributions
ウス+1.426
ascript+1.424
atism+1.307
hesion+1.298
 Tad+1.290
Neg logit contributions
alsh-1.385
 Steal-1.320
BACK-1.231
zee-1.228
horn-1.165
Token proceed
Token ID5120
Feature activation-1.05e+00

Pos logit contributions
alsh+0.072
 Steal+0.068
zee+0.063
BACK+0.063
horn+0.061
Neg logit contributions
ascript-0.079
ウス-0.079
atism-0.073
hesion-0.072
 Tad-0.072
Token.
Token ID13
Feature activation-9.97e-02

Pos logit contributions
alsh+0.830
 Steal+0.791
BACK+0.733
zee+0.731
horn+0.706
Neg logit contributions
ウス-0.751
ascript-0.749
atism-0.677
hesion-0.674
 Tad-0.662
Token
Token ID198
Feature activation-5.36e-03

Pos logit contributions
alsh+0.072
 Steal+0.068
zee+0.063
BACK+0.063
horn+0.060
Neg logit contributions
ascript-0.078
ウス-0.078
atism-0.071
hesion-0.071
 Tad-0.070
Token
Token ID198
Feature activation-1.91e-01

Pos logit contributions
alsh+0.004
 Steal+0.004
zee+0.004
BACK+0.004
horn+0.004
Neg logit contributions
ウス-0.004
ascript-0.003
hesion-0.003
 Tad-0.003
atism-0.003
Token matters
Token ID6067
Feature activation-3.74e-02

Pos logit contributions
ascript+0.012
ウス+0.012
atism+0.011
hesion+0.011
 Tad+0.011
Neg logit contributions
alsh-0.015
 Steal-0.014
zee-0.013
BACK-0.013
horn-0.013
Token most
Token ID749
Feature activation+3.78e-01

Pos logit contributions
alsh+0.030
 Steal+0.029
zee+0.027
BACK+0.027
horn+0.026
Neg logit contributions
ascript-0.026
ウス-0.026
atism-0.023
hesion-0.023
 Tad-0.023
Token in
Token ID287
Feature activation-9.24e-02

Pos logit contributions
ascript+0.283
ウス+0.282
atism+0.256
hesion+0.255
 Tad+0.253
Neg logit contributions
alsh-0.285
 Steal-0.272
zee-0.251
BACK-0.251
horn-0.241
Token geop
Token ID30324
Feature activation-5.84e-02

Pos logit contributions
alsh+0.078
 Steal+0.074
zee+0.069
BACK+0.069
horn+0.067
Neg logit contributions
ascript-0.062
ウス-0.062
atism-0.055
hesion-0.055
 partName-0.054
Tokenolitics
Token ID21704
Feature activation+1.31e-01

Pos logit contributions
alsh+0.047
 Steal+0.044
zee+0.041
BACK+0.041
horn+0.040
Neg logit contributions
ウス-0.041
ascript-0.041
atism-0.037
hesion-0.037
 Tad-0.036
Token
Token ID851
Feature activation+6.11e-01

Pos logit contributions
ascript+0.098
ウス+0.098
atism+0.089
hesion+0.088
 Tad+0.088
Neg logit contributions
alsh-0.099
 Steal-0.094
zee-0.087
BACK-0.087
horn-0.084
Token it
Token ID340
Feature activation+3.56e-01

Pos logit contributions
ascript+0.427
ウス+0.426
atism+0.384
hesion+0.382
 Tad+0.378
Neg logit contributions
alsh-0.492
 Steal-0.469
zee-0.437
BACK-0.436
horn-0.419
Token is
Token ID318
Feature activation+3.45e-01

Pos logit contributions
ascript+0.254
ウス+0.252
hesion+0.227
atism+0.226
 Tad+0.225
Neg logit contributions
alsh-0.283
 Steal-0.268
zee-0.250
BACK-0.250
horn-0.240
Token plain
Token ID8631
Feature activation+6.83e-01

Pos logit contributions
ascript+0.268
ウス+0.267
atism+0.242
hesion+0.242
 Tad+0.239
Neg logit contributions
alsh-0.251
 Steal-0.239
zee-0.220
BACK-0.219
horn-0.210
Token to
Token ID284
Feature activation+1.88e-02

Pos logit contributions
ascript+0.511
ウス+0.509
atism+0.464
hesion+0.461
 Tad+0.457
Neg logit contributions
alsh-0.516
 Steal-0.491
zee-0.454
BACK-0.453
horn-0.435
Token see
Token ID766
Feature activation-1.82e-01

Pos logit contributions
ascript+0.014
ウス+0.014
atism+0.013
hesion+0.013
 Tad+0.013
Neg logit contributions
alsh-0.014
 Steal-0.014
zee-0.013
BACK-0.012
horn-0.012
Token would
Token ID561
Feature activation+2.23e-01

Pos logit contributions
alsh+0.042
 Steal+0.040
zee+0.037
BACK+0.037
horn+0.036
Neg logit contributions
ascript-0.039
ウス-0.038
atism-0.034
hesion-0.034
 Tad-0.034
Token force
Token ID2700
Feature activation-1.21e-01

Pos logit contributions
ウス+0.163
ascript+0.163
atism+0.147
hesion+0.147
 Tad+0.146
Neg logit contributions
alsh-0.172
 Steal-0.164
zee-0.151
BACK-0.151
horn-0.145
Token one
Token ID530
Feature activation-2.50e-01

Pos logit contributions
alsh+0.108
 Steal+0.104
zee+0.097
BACK+0.097
horn+0.094
Neg logit contributions
ascript-0.074
ウス-0.074
atism-0.065
hesion-0.065
 Tad-0.064
Token side
Token ID1735
Feature activation+5.44e-01

Pos logit contributions
alsh+0.195
 Steal+0.187
zee+0.173
BACK+0.173
horn+0.168
Neg logit contributions
ascript-0.180
ウス-0.180
atism-0.162
hesion-0.161
 Tad-0.159
Token of
Token ID286
Feature activation-2.01e-01

Pos logit contributions
ascript+0.409
ウス+0.407
atism+0.371
hesion+0.369
 Tad+0.366
Neg logit contributions
alsh-0.409
 Steal-0.390
BACK-0.360
zee-0.360
horn-0.347
Token our
Token ID674
Feature activation-9.73e-02

Pos logit contributions
alsh+0.167
 Steal+0.160
zee+0.149
BACK+0.149
horn+0.144
Neg logit contributions
ウス-0.135
ascript-0.135
atism-0.121
hesion-0.120
 Tad-0.118
Token planet
Token ID5440
Feature activation-4.15e-01

Pos logit contributions
alsh+0.089
 Steal+0.086
zee+0.080
BACK+0.080
horn+0.078
Neg logit contributions
ascript-0.058
ウス-0.057
atism-0.050
hesion-0.050
 Tad-0.049
Token to
Token ID284
Feature activation+1.39e-01

Pos logit contributions
alsh+0.293
 Steal+0.278
BACK+0.255
zee+0.255
horn+0.245
Neg logit contributions
ascript-0.331
ウス-0.330
atism-0.301
hesion-0.300
 Tad-0.297
Token always
Token ID1464
Feature activation+1.16e-01

Pos logit contributions
ウス+0.106
ascript+0.106
atism+0.096
hesion+0.095
 Tad+0.094
Neg logit contributions
alsh-0.104
 Steal-0.099
zee-0.091
BACK-0.091
horn-0.087
Token face
Token ID1986
Feature activation+1.20e-01

Pos logit contributions
ウス+0.087
ascript+0.087
hesion+0.078
atism+0.078
 Tad+0.077
Neg logit contributions
alsh-0.088
 Steal-0.084
zee-0.077
BACK-0.077
horn-0.074
Token the
Token ID262
Feature activation-2.42e-01

Pos logit contributions
ascript+0.084
ウス+0.084
atism+0.075
hesion+0.075
 Tad+0.074
Neg logit contributions
alsh-0.096
 Steal-0.092
BACK-0.085
zee-0.085
horn-0.082
Token47
Token ID2857
Feature activation+6.49e-02

Pos logit contributions
ascript+0.229
ウス+0.228
atism+0.208
hesion+0.207
 Tad+0.205
Neg logit contributions
alsh-0.228
 Steal-0.217
zee-0.201
BACK-0.200
horn-0.192
Token
Token ID198
Feature activation+1.09e-02

Pos logit contributions
ascript+0.048
ウス+0.048
atism+0.043
hesion+0.043
 Tad+0.042
Neg logit contributions
alsh-0.050
 Steal-0.048
BACK-0.044
zee-0.044
horn-0.042
Token
Token ID198
Feature activation-2.15e-02

Pos logit contributions
ウス+0.007
ascript+0.007
hesion+0.007
atism+0.007
 Tad+0.007
Neg logit contributions
alsh-0.009
 Steal-0.009
zee-0.008
BACK-0.008
horn-0.008
Token19
Token ID1129
Feature activation-2.26e-01

Pos logit contributions
alsh+0.018
 Steal+0.017
BACK+0.016
zee+0.016
horn+0.015
Neg logit contributions
ascript-0.015
ウス-0.015
atism-0.013
hesion-0.013
 Tad-0.013
Token35
Token ID2327
Feature activation-2.97e-01

Pos logit contributions
alsh+0.165
 Steal+0.157
BACK+0.145
zee+0.145
horn+0.139
Neg logit contributions
ascript-0.174
ウス-0.174
atism-0.158
hesion-0.157
 Tad-0.156
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
alsh+0.223
 Steal+0.216
BACK+0.199
zee+0.197
horn+0.192
Neg logit contributions
ascript-0.221
ウス-0.219
atism-0.200
hesion-0.200
 Tad-0.195
Token
Token ID198
Feature activation-6.56e-02

Pos logit contributions
alsh+0.084
 Steal+0.080
zee+0.074
BACK+0.074
horn+0.071
Neg logit contributions
ウス-0.069
ascript-0.069
atism-0.062
hesion-0.062
 Tad-0.062
Token19
Token ID1129
Feature activation-3.29e-01

Pos logit contributions
alsh+0.054
 Steal+0.052
BACK+0.049
zee+0.048
horn+0.047
Neg logit contributions
ascript-0.045
ウス-0.044
atism-0.040
hesion-0.040
 Tad-0.039
Token23
Token ID1954
Feature activation-6.85e-01

Pos logit contributions
alsh+0.242
 Steal+0.231
BACK+0.213
zee+0.212
horn+0.205
Neg logit contributions
ascript-0.254
ウス-0.253
atism-0.230
hesion-0.229
 Tad-0.226
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
alsh+0.518
 Steal+0.499
BACK+0.461
zee+0.456
horn+0.442
Neg logit contributions
ascript-0.509
ウス-0.505
atism-0.460
hesion-0.460
 Tad-0.450
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
alsh+0.229
 Steal+0.217
zee+0.203
BACK+0.202
horn+0.194
Neg logit contributions
ascript-0.191
ウス-0.191
atism-0.173
hesion-0.173
 Tad-0.172
Token them
Token ID606
Feature activation-2.39e-01

Pos logit contributions
ascript+0.272
ウス+0.272
atism+0.247
hesion+0.245
 Tad+0.243
Neg logit contributions
alsh-0.282
 Steal-0.269
zee-0.248
BACK-0.248
horn-0.239
Token down
Token ID866
Feature activation-1.43e-01

Pos logit contributions
alsh+0.156
 Steal+0.147
zee+0.134
BACK+0.133
horn+0.128
Neg logit contributions
ウス-0.204
ascript-0.204
atism-0.187
hesion-0.186
 Tad-0.183
Token Broadway
Token ID20617
Feature activation-9.94e-02

Pos logit contributions
alsh+0.112
 Steal+0.107
zee+0.099
BACK+0.099
horn+0.095
Neg logit contributions
ascript-0.104
ウス-0.104
atism-0.094
hesion-0.093
 Tad-0.092
Token to
Token ID284
Feature activation-7.99e-02

Pos logit contributions
alsh+0.076
 Steal+0.073
zee+0.067
BACK+0.067
horn+0.065
Neg logit contributions
ascript-0.073
ウス-0.072
atism-0.066
hesion-0.066
 Tad-0.065
Token the
Token ID262
Feature activation-2.38e-01

Pos logit contributions
alsh+0.065
 Steal+0.062
zee+0.057
BACK+0.057
horn+0.055
Neg logit contributions
ascript-0.056
ウス-0.056
atism-0.050
hesion-0.050
 Tad-0.049
Token main
Token ID1388
Feature activation-1.90e-01

Pos logit contributions
alsh+0.199
 Steal+0.191
zee+0.177
BACK+0.177
horn+0.171
Neg logit contributions
ascript-0.159
ウス-0.159
atism-0.143
hesion-0.142
 Tad-0.139
Token gate
Token ID8946
Feature activation-2.31e-01

Pos logit contributions
alsh+0.165
 Steal+0.158
zee+0.148
BACK+0.147
horn+0.143
Neg logit contributions
ウス-0.121
ascript-0.121
atism-0.108
hesion-0.107
 Tad-0.105
Token,
Token ID11
Feature activation-2.16e-01

Pos logit contributions
alsh+0.186
 Steal+0.177
zee+0.165
BACK+0.164
horn+0.159
Neg logit contributions
ascript-0.162
ウス-0.161
atism-0.146
hesion-0.145
 Tad-0.144
Token where
Token ID810
Feature activation-2.59e-01

Pos logit contributions
alsh+0.168
 Steal+0.160
zee+0.148
BACK+0.148
horn+0.143
Neg logit contributions
ascript-0.157
ウス-0.156
atism-0.142
hesion-0.141
 Tad-0.140
Token that
Token ID326
Feature activation+2.66e-01

Pos logit contributions
alsh+0.195
 Steal+0.185
zee+0.171
BACK+0.171
horn+0.165
Neg logit contributions
ascript-0.194
ウス-0.194
atism-0.176
hesion-0.175
 Tad-0.173
Token photo
Token ID4590
Feature activation-6.26e-01

Pos logit contributions
ascript+0.190
ウス+0.189
atism+0.171
hesion+0.170
 Tad+0.168
Neg logit contributions
alsh-0.210
 Steal-0.201
zee-0.186
BACK-0.186
horn-0.180
Token on
Token ID319
Feature activation-4.45e-03

Pos logit contributions
alsh+0.571
 Steal+0.548
zee+0.508
BACK+0.505
horn+0.491
Neg logit contributions
ウス-0.500
ascript-0.500
atism-0.451
hesion-0.448
 Tad-0.441
Token a
Token ID257
Feature activation+6.42e-02

Pos logit contributions
alsh+0.004
 Steal+0.003
zee+0.003
BACK+0.003
horn+0.003
Neg logit contributions
ascript-0.003
ウス-0.003
atism-0.003
hesion-0.003
 partName-0.003
Token metal
Token ID6147
Feature activation-1.21e-01

Pos logit contributions
ascript+0.043
ウス+0.043
atism+0.038
hesion+0.038
 partName+0.037
Neg logit contributions
alsh-0.054
 Steal-0.052
BACK-0.048
zee-0.048
horn-0.046
Token bench
Token ID7624
Feature activation+6.64e-01

Pos logit contributions
alsh+0.102
 Steal+0.097
BACK+0.091
zee+0.090
horn+0.089
Neg logit contributions
ウス-0.080
ascript-0.080
atism-0.071
hesion-0.071
 Tad-0.069
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
ascript+0.453
ウス+0.453
atism+0.409
hesion+0.404
 Tad+0.400
Neg logit contributions
alsh-0.545
 Steal-0.521
zee-0.486
BACK-0.484
horn-0.469
Token A
Token ID317
Feature activation+2.85e-03

Pos logit contributions
ascript+0.093
ウス+0.093
atism+0.084
hesion+0.084
 Tad+0.084
Neg logit contributions
alsh-0.094
 Steal-0.090
zee-0.083
BACK-0.083
horn-0.080
Token sales
Token ID4200
Feature activation+2.53e-02

Pos logit contributions
ascript+0.002
ウス+0.002
atism+0.002
hesion+0.002
 Tad+0.002
Neg logit contributions
alsh-0.002
 Steal-0.002
zee-0.002
BACK-0.002
horn-0.002
Tokenwoman
Token ID8580
Feature activation-2.00e-01

Pos logit contributions
ascript+0.016
ウス+0.016
atism+0.014
hesion+0.014
 Tad+0.014
Neg logit contributions
alsh-0.022
 Steal-0.021
zee-0.019
BACK-0.019
horn-0.019
Token behind
Token ID2157
Feature activation+2.84e-01

Pos logit contributions
alsh+0.158
 Steal+0.151
zee+0.140
BACK+0.140
horn+0.135
Neg logit contributions
ウス-0.143
ascript-0.143
atism-0.129
hesion-0.128
 Tad-0.126
Token the
Token ID262
Feature activation-2.41e-01

Pos logit contributions
ascript+0.191
ウス+0.191
atism+0.172
hesion+0.170
 Tad+0.169
Neg logit contributions
alsh-0.236
 Steal-0.226
zee-0.210
BACK-0.210
horn-0.202
Token ticket
Token ID7846
Feature activation+6.70e-01

Pos logit contributions
alsh+0.211
 Steal+0.202
zee+0.189
BACK+0.189
horn+0.183
Neg logit contributions
ascript-0.152
ウス-0.151
atism-0.135
hesion-0.134
 Tad-0.133
Token was
Token ID373
Feature activation-1.89e-01

Pos logit contributions
ascript+0.170
ウス+0.169
atism+0.153
hesion+0.152
 Tad+0.150
Neg logit contributions
alsh-0.185
 Steal-0.177
zee-0.164
BACK-0.163
horn-0.158
Token another
Token ID1194
Feature activation-1.45e-01

Pos logit contributions
alsh+0.155
 Steal+0.148
zee+0.137
BACK+0.137
horn+0.133
Neg logit contributions
ascript-0.129
ウス-0.129
atism-0.116
hesion-0.115
 Tad-0.114
Token word
Token ID1573
Feature activation-2.05e-01

Pos logit contributions
alsh+0.109
 Steal+0.104
zee+0.096
BACK+0.096
horn+0.093
Neg logit contributions
ascript-0.108
ウス-0.108
atism-0.099
hesion-0.098
 partName-0.096
Token.
Token ID13
Feature activation-2.11e-01

Pos logit contributions
alsh+0.166
 Steal+0.160
zee+0.148
BACK+0.147
horn+0.143
Neg logit contributions
ascript-0.141
ウス-0.141
atism-0.128
hesion-0.127
 Tad-0.124
Token Giant
Token ID17384
Feature activation+4.39e-01

Pos logit contributions
alsh+0.157
 Steal+0.150
zee+0.138
BACK+0.138
horn+0.132
Neg logit contributions
ascript-0.160
ウス-0.159
atism-0.145
hesion-0.144
 Tad-0.143
Token another
Token ID1194
Feature activation-9.32e-01

Pos logit contributions
ascript+0.317
ウス+0.316
atism+0.286
hesion+0.284
 Tad+0.282
Neg logit contributions
alsh-0.343
 Steal-0.327
zee-0.303
BACK-0.302
horn-0.292
Token.
Token ID13
Feature activation-5.75e-02

Pos logit contributions
alsh+0.661
 Steal+0.629
zee+0.579
BACK+0.574
horn+0.561
Neg logit contributions
ascript-0.737
ウス-0.734
atism-0.676
hesion-0.667
 Tad-0.660
Token Huge
Token ID35225
Feature activation-1.74e-01

Pos logit contributions
alsh+0.043
 Steal+0.041
zee+0.038
BACK+0.038
horn+0.037
Neg logit contributions
ascript-0.043
ウス-0.043
atism-0.039
hesion-0.039
 Tad-0.038
Token,
Token ID11
Feature activation-2.64e-01

Pos logit contributions
alsh+0.141
 Steal+0.135
zee+0.125
BACK+0.125
horn+0.121
Neg logit contributions
ascript-0.121
ウス-0.120
atism-0.109
hesion-0.108
 Tad-0.106
Token En
Token ID2039
Feature activation+8.88e-01

Pos logit contributions
alsh+0.198
 Steal+0.188
zee+0.174
BACK+0.173
horn+0.167
Neg logit contributions
ascript-0.200
ウス-0.199
atism-0.181
hesion-0.180
 Tad-0.178
Tokenorm
Token ID579
Feature activation-1.18e+00

Pos logit contributions
ascript+0.650
ウス+0.646
atism+0.588
hesion+0.585
 Tad+0.582
Neg logit contributions
alsh-0.682
 Steal-0.650
BACK-0.603
zee-0.600
horn-0.576
Token in
Token ID287
Feature activation-4.89e-01

Pos logit contributions
alsh+0.087
 Steal+0.083
BACK+0.077
zee+0.077
horn+0.074
Neg logit contributions
ascript-0.080
ウス-0.080
atism-0.072
hesion-0.072
 Tad-0.071
Token exaggerated
Token ID25291
Feature activation-6.59e-01

Pos logit contributions
alsh+0.374
 Steal+0.357
zee+0.330
BACK+0.330
horn+0.318
Neg logit contributions
ascript-0.361
ウス-0.359
atism-0.326
hesion-0.325
 Tad-0.320
Token accents
Token ID39271
Feature activation+4.83e-01

Pos logit contributions
alsh+0.503
 Steal+0.482
BACK+0.446
zee+0.445
horn+0.430
Neg logit contributions
ascript-0.485
ウス-0.485
atism-0.440
hesion-0.439
 Tad-0.429
Token.
Token ID13
Feature activation+6.48e-02

Pos logit contributions
ascript+0.344
ウス+0.343
atism+0.311
hesion+0.309
 Tad+0.306
Neg logit contributions
alsh-0.381
 Steal-0.363
zee-0.337
BACK-0.336
horn-0.324
Token Wat
Token ID12242
Feature activation-1.89e-01

Pos logit contributions
ascript+0.050
ウス+0.050
atism+0.045
hesion+0.045
 Tad+0.044
Neg logit contributions
alsh-0.047
 Steal-0.045
BACK-0.042
zee-0.042
horn-0.040
Tokenters
Token ID1010
Feature activation-7.60e-01

Pos logit contributions
alsh+0.141
 Steal+0.135
BACK+0.125
zee+0.121
horn+0.118
Neg logit contributions
ascript-0.143
ウス-0.141
hesion-0.130
atism-0.129
 Tad-0.127
Token approaches
Token ID10581
Feature activation-5.13e-01

Pos logit contributions
alsh+0.598
 Steal+0.569
zee+0.530
BACK+0.527
horn+0.511
Neg logit contributions
ウス-0.546
ascript-0.544
atism-0.490
hesion-0.488
 Tad-0.483
Token a
Token ID257
Feature activation-6.25e-02

Pos logit contributions
alsh+0.459
 Steal+0.441
zee+0.410
BACK+0.410
horn+0.399
Neg logit contributions
ascript-0.314
ウス-0.314
hesion-0.276
atism-0.275
 partName-0.268
Token number
Token ID1271
Feature activation+4.73e-01

Pos logit contributions
alsh+0.047
 Steal+0.045
BACK+0.041
zee+0.041
horn+0.040
Neg logit contributions
ascript-0.047
ウス-0.047
atism-0.043
hesion-0.042
 Tad-0.042
Token of
Token ID286
Feature activation-1.30e-01

Pos logit contributions
ascript+0.344
ウス+0.343
atism+0.312
hesion+0.310
 Tad+0.307
Neg logit contributions
alsh-0.367
 Steal-0.350
zee-0.324
BACK-0.324
horn-0.312
Token men
Token ID1450
Feature activation+8.67e-01

Pos logit contributions
alsh+0.104
 Steal+0.099
BACK+0.092
zee+0.092
horn+0.088
Neg logit contributions
ascript-0.093
ウス-0.092
atism-0.083
hesion-0.083
 Tad-0.082
Token unfor
Token ID28371
Feature activation-1.16e+00

Pos logit contributions
ascript+0.250
ウス+0.250
atism+0.225
hesion+0.223
 Tad+0.219
Neg logit contributions
alsh-0.304
 Steal-0.292
zee-0.271
BACK-0.270
horn-0.261
Tokeng
Token ID70
Feature activation-1.03e-01

Pos logit contributions
alsh+1.374
 Steal+1.331
zee+1.274
BACK+1.262
horn+1.244
Neg logit contributions
ascript-0.365
ウス-0.365
atism-0.282
 Tad-0.275
hesion-0.273
Tokenivably
Token ID47994
Feature activation+9.00e-01

Pos logit contributions
alsh+0.063
 Steal+0.059
zee+0.054
BACK+0.053
horn+0.051
Neg logit contributions
ウス-0.092
ascript-0.092
atism-0.085
hesion-0.085
 Tad-0.084
Token bad
Token ID2089
Feature activation-5.10e-02

Pos logit contributions
ascript+0.702
ウス+0.700
atism+0.640
hesion+0.637
 Tad+0.633
Neg logit contributions
alsh-0.649
 Steal-0.616
zee-0.567
BACK-0.566
horn-0.543
Token tort
Token ID7619
Feature activation-2.82e-02

Pos logit contributions
alsh+0.040
 Steal+0.038
zee+0.035
BACK+0.035
horn+0.034
Neg logit contributions
ascript-0.037
ウス-0.037
atism-0.033
hesion-0.033
 Tad-0.032
Tokenillas
Token ID25314
Feature activation-3.57e-01

Pos logit contributions
alsh+0.022
 Steal+0.021
zee+0.020
BACK+0.020
horn+0.019
Neg logit contributions
ウス-0.020
ascript-0.020
atism-0.018
hesion-0.018
 Tad-0.018
Token,
Token ID11
Feature activation-6.24e-02

Pos logit contributions
alsh+0.279
 Steal+0.267
zee+0.247
BACK+0.245
horn+0.238
Neg logit contributions
ウス-0.259
ascript-0.258
atism-0.234
hesion-0.231
 Tad-0.229
Token it
Token ID340
Feature activation-1.90e-01

Pos logit contributions
alsh+0.050
 Steal+0.048
zee+0.045
BACK+0.044
horn+0.043
Neg logit contributions
ascript-0.044
ウス-0.043
atism-0.039
hesion-0.039
 Tad-0.039
Token's
Token ID338
Feature activation+4.77e-01

Pos logit contributions
alsh+0.151
 Steal+0.145
zee+0.135
BACK+0.133
horn+0.130
Neg logit contributions
ascript-0.134
ウス-0.134
atism-0.120
hesion-0.119
 Tad-0.118
Token good
Token ID922
Feature activation+1.93e-01

Pos logit contributions
ascript+0.349
ウス+0.348
atism+0.317
hesion+0.315
 Tad+0.313
Neg logit contributions
alsh-0.367
 Steal-0.349
zee-0.324
BACK-0.323
horn-0.311
Token to
Token ID284
Feature activation-6.98e-01

Pos logit contributions
ascript+0.151
ウス+0.151
atism+0.138
hesion+0.137
 Tad+0.136
Neg logit contributions
alsh-0.139
 Steal-0.132
zee-0.122
BACK-0.121
horn-0.116
Token better
Token ID1365
Feature activation+3.32e-01

Pos logit contributions
alsh+0.118
 Steal+0.113
zee+0.104
BACK+0.104
horn+0.100
Neg logit contributions
ウス-0.115
ascript-0.115
atism-0.104
hesion-0.103
 Tad-0.102
Token -
Token ID532
Feature activation+9.51e-03

Pos logit contributions
ウス+0.224
ascript+0.223
atism+0.201
hesion+0.198
 Tad+0.197
Neg logit contributions
alsh-0.276
 Steal-0.265
BACK-0.247
zee-0.246
horn-0.238
Token Most
Token ID4042
Feature activation+1.13e+00

Pos logit contributions
ウス+0.007
ascript+0.007
atism+0.006
hesion+0.006
 Tad+0.006
Neg logit contributions
alsh-0.007
 Steal-0.007
zee-0.007
BACK-0.007
horn-0.006
Token of
Token ID286
Feature activation+3.39e-01

Pos logit contributions
ウス+0.831
ascript+0.829
atism+0.753
hesion+0.748
 Tad+0.742
Neg logit contributions
alsh-0.861
 Steal-0.822
zee-0.759
BACK-0.758
horn-0.730
Token the
Token ID262
Feature activation-2.61e-01

Pos logit contributions
ウス+0.234
ascript+0.234
atism+0.210
hesion+0.209
 Tad+0.206
Neg logit contributions
alsh-0.275
 Steal-0.265
zee-0.245
BACK-0.245
horn-0.236
Token questions
Token ID2683
Feature activation-3.38e-01

Pos logit contributions
alsh+0.218
 Steal+0.210
zee+0.195
BACK+0.195
horn+0.188
Neg logit contributions
ウス-0.174
ascript-0.173
atism-0.155
hesion-0.154
 Tad-0.152
Token interview
Token ID2720
Feature activation+4.03e-01

Pos logit contributions
alsh+0.269
 Steal+0.257
zee+0.239
BACK+0.238
horn+0.229
Neg logit contributions
ウス-0.243
ascript-0.240
atism-0.217
hesion-0.215
 Tad-0.212
Tokeners
Token ID364
Feature activation-4.91e-01

Pos logit contributions
ウス+0.247
ascript+0.247
atism+0.220
hesion+0.218
 Tad+0.216
Neg logit contributions
alsh-0.357
 Steal-0.343
zee-0.322
BACK-0.321
horn-0.310
Token asked
Token ID1965
Feature activation+1.09e+00

Pos logit contributions
alsh+0.358
 Steal+0.341
zee+0.314
BACK+0.313
horn+0.301
Neg logit contributions
ウス-0.380
ascript-0.379
atism-0.345
hesion-0.343
 Tad-0.341
Token me
Token ID502
Feature activation+3.51e-01

Pos logit contributions
ascript+0.754
ウス+0.751
atism+0.680
hesion+0.675
 Tad+0.671
Neg logit contributions
alsh-0.876
 Steal-0.836
zee-0.778
BACK-0.776
horn-0.748
Token were
Token ID547
Feature activation-3.41e-01

Pos logit contributions
ascript+0.236
ウス+0.236
atism+0.212
hesion+0.211
 Tad+0.209
Neg logit contributions
alsh-0.290
 Steal-0.277
zee-0.259
BACK-0.258
horn-0.249
Token Mississippi
Token ID13797
Feature activation-4.93e-02

Pos logit contributions
ascript+0.230
ウス+0.229
atism+0.204
hesion+0.203
 Tad+0.199
Neg logit contributions
alsh-0.307
 Steal-0.295
zee-0.275
BACK-0.274
horn-0.265
Token
Token ID784
Feature activation-2.64e-01

Pos logit contributions
alsh+0.036
 Steal+0.034
zee+0.031
BACK+0.031
horn+0.030
Neg logit contributions
ascript-0.038
ウス-0.038
atism-0.035
hesion-0.035
 Tad-0.034
Token got
Token ID1392
Feature activation+9.85e-02

Pos logit contributions
alsh+0.206
 Steal+0.195
zee+0.181
BACK+0.181
horn+0.175
Neg logit contributions
ascript-0.192
ウス-0.191
atism-0.173
hesion-0.172
 Tad-0.170
Token in
Token ID287
Feature activation+1.01e-03

Pos logit contributions
ascript+0.070
ウス+0.070
atism+0.063
hesion+0.063
 Tad+0.062
Neg logit contributions
alsh-0.078
 Steal-0.075
zee-0.069
BACK-0.069
horn-0.067
Token Brown
Token ID4373
Feature activation-7.49e-01

Pos logit contributions
ascript+0.001
ウス+0.001
atism+0.001
hesion+0.001
 Tad+0.001
Neg logit contributions
alsh-0.001
 Steal-0.001
zee-0.001
BACK-0.001
horn-0.001
Token
Token ID447
Feature activation-6.23e-01

Pos logit contributions
alsh+0.646
 Steal+0.618
zee+0.578
BACK+0.578
horn+0.558
Neg logit contributions
ascript-0.479
ウス-0.477
atism-0.427
hesion-0.424
 Tad-0.420
Token
Token ID247
Feature activation-7.78e-02

Pos logit contributions
alsh+0.640
 Steal+0.618
zee+0.585
BACK+0.583
horn+0.567
Neg logit contributions
ascript-0.294
ウス-0.293
atism-0.252
hesion-0.249
 Tad-0.246
Tokens
Token ID82
Feature activation+1.15e-01

Pos logit contributions
alsh+0.063
 Steal+0.060
zee+0.056
BACK+0.056
horn+0.054
Neg logit contributions
ascript-0.054
ウス-0.054
atism-0.048
hesion-0.048
 Tad-0.048
Token ear
Token ID1027
Feature activation-1.34e+00

Pos logit contributions
ascript+0.084
ウス+0.084
atism+0.077
hesion+0.076
 Tad+0.076
Neg logit contributions
alsh-0.088
 Steal-0.084
zee-0.078
BACK-0.077
horn-0.074
Token about
Token ID546
Feature activation+1.77e-03

Pos logit contributions
alsh+1.057
 Steal+1.007
zee+0.934
BACK+0.932
horn+0.903
Neg logit contributions
ascript-0.959
ウス-0.954
atism-0.865
hesion-0.858
 Tad-0.856
Token kicking
Token ID17997
Feature activation-2.44e-02

Pos logit contributions
ascript+0.001
ウス+0.001
atism+0.001
hesion+0.001
 partName+0.001
Neg logit contributions
alsh-0.001
 Steal-0.001
BACK-0.001
zee-0.001
horn-0.001
Token slide
Token ID10649
Feature activation-2.81e+00

Pos logit contributions
alsh+1.727
 Steal+1.633
zee+1.499
BACK+1.496
horn+1.432
Neg logit contributions
ascript-2.033
ウス-2.027
atism-1.859
hesion-1.851
 Tad-1.840
Token
Token ID198
Feature activation+2.41e-01

Pos logit contributions
alsh+2.196
 Steal+2.096
zee+1.945
BACK+1.944
horn+1.869
Neg logit contributions
ascript-2.023
ウス-2.017
atism-1.826
hesion-1.814
 Tad-1.798
Token
Token ID198
Feature activation+1.57e-01

Pos logit contributions
ウス+0.156
ascript+0.155
hesion+0.142
 Tad+0.141
 partName+0.140
Neg logit contributions
alsh-0.204
 Steal-0.193
zee-0.181
BACK-0.179
horn-0.172
TokenPower
Token ID13434
Feature activation-1.10e+00

Pos logit contributions
ウス+0.121
ascript+0.119
hesion+0.111
)].+0.108
 partName+0.108
Neg logit contributions
alsh-0.115
 Steal-0.109
zee-0.099
BACK-0.096
horn-0.095
TokenPoint
Token ID12727
Feature activation-2.24e+00

Pos logit contributions
alsh+0.735
 Steal+0.690
zee+0.639
BACK+0.630
horn+0.610
Neg logit contributions
ascript-0.931
ウス-0.925
hesion-0.843
 Tad-0.842
 partName-0.838
Token slide
Token ID10649
Feature activation-2.18e+00

Pos logit contributions
alsh+1.600
 Steal+1.514
BACK+1.393
zee+1.384
horn+1.333
Neg logit contributions
ascript-1.763
ウス-1.750
atism-1.610
hesion-1.602
 Tad-1.595
Token PNG
Token ID36182
Feature activation+1.30e+00

Pos logit contributions
alsh+1.733
 Steal+1.656
zee+1.515
BACK+1.503
horn+1.487
Neg logit contributions
ascript-1.494
ウス-1.484
hesion-1.389
 Tad-1.387
atism-1.384
Token larger
Token ID4025
Feature activation-4.73e-01

Pos logit contributions
ウス+0.830
ascript+0.823
atism+0.736
hesion+0.725
 Tad+0.712
Neg logit contributions
alsh-1.128
 Steal-1.085
zee-1.013
BACK-1.007
horn-0.973
Token image
Token ID2939
Feature activation+9.75e-01

Pos logit contributions
alsh+0.402
 Steal+0.384
BACK+0.359
zee+0.359
horn+0.346
Neg logit contributions
ascript-0.308
ウス-0.307
atism-0.276
hesion-0.274
 Tad-0.273
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
ascript+0.659
ウス+0.657
 Tad+0.596
atism+0.594
hesion+0.593
Neg logit contributions
alsh-0.802
 Steal-0.760
zee-0.715
BACK-0.708
horn-0.680
Token
Token ID198
Feature activation+9.06e-01

Pos logit contributions
ウス+0.707
ascript+0.700
hesion+0.647
 Tad+0.646
 partName+0.641
Neg logit contributions
alsh-0.991
 Steal-0.938
zee-0.880
BACK-0.872
horn-0.834
Token [
Token ID685
Feature activation-1.69e+00

Pos logit contributions
alsh+1.226
 Steal+1.174
zee+1.095
BACK+1.089
horn+1.054
Neg logit contributions
ascript-1.005
ウス-1.003
atism-0.902
hesion-0.896
 Tad-0.886
Token10
Token ID940
Feature activation-7.29e-01

Pos logit contributions
alsh+1.269
 Steal+1.209
zee+1.116
BACK+1.108
horn+1.060
Neg logit contributions
ウス-1.258
ascript-1.256
atism-1.146
hesion-1.143
 Tad-1.135
Token:
Token ID25
Feature activation-9.20e-01

Pos logit contributions
alsh+0.714
 Steal+0.686
zee+0.647
BACK+0.646
horn+0.626
Neg logit contributions
ascript-0.379
ウス-0.378
atism-0.330
hesion-0.328
 Tad-0.325
Token47
Token ID2857
Feature activation-6.68e-01

Pos logit contributions
alsh+0.645
 Steal+0.613
zee+0.562
BACK+0.561
horn+0.538
Neg logit contributions
ascript-0.737
ウス-0.737
atism-0.674
hesion-0.670
 Tad-0.662
Token]
Token ID60
Feature activation-1.68e+00

Pos logit contributions
alsh+0.529
 Steal+0.505
zee+0.468
BACK+0.466
horn+0.446
Neg logit contributions
ウス-0.467
ascript-0.465
hesion-0.424
 Tad-0.424
atism-0.423
Token <
Token ID1279
Feature activation-3.40e+00

Pos logit contributions
alsh+1.372
 Steal+1.317
BACK+1.228
zee+1.215
horn+1.178
Neg logit contributions
ウス-1.151
ascript-1.150
atism-1.044
hesion-1.038
)].-1.013
Tokenfen
Token ID41037
Feature activation-2.91e-01

Pos logit contributions
alsh+2.597
 Steal+2.410
zee+2.308
BACK+2.260
horn+2.230
Neg logit contributions
ウス-2.513
ascript-2.502
atism-2.273
hesion-2.253
 Tad-2.251
Tokenren
Token ID918
Feature activation-1.76e-01

Pos logit contributions
alsh+0.220
 Steal+0.209
zee+0.194
BACK+0.193
horn+0.186
Neg logit contributions
ascript-0.216
ウス-0.216
atism-0.196
hesion-0.195
 Tad-0.194
Token>
Token ID29
Feature activation+2.71e-02

Pos logit contributions
alsh+0.135
 Steal+0.129
zee+0.119
BACK+0.119
horn+0.115
Neg logit contributions
ascript-0.129
ウス-0.129
atism-0.117
hesion-0.116
 Tad-0.116
Token m
Token ID285
Feature activation-6.28e-01

Pos logit contributions
ascript+0.021
ウス+0.021
atism+0.019
hesion+0.019
 Tad+0.019
Neg logit contributions
alsh-0.020
 Steal-0.019
zee-0.018
BACK-0.018
horn-0.017
Token2
Token ID17
Feature activation-5.37e-01

Pos logit contributions
alsh+0.453
 Steal+0.428
zee+0.398
BACK+0.390
horn+0.379
Neg logit contributions
ウス-0.495
ascript-0.492
atism-0.451
hesion-0.446
 Tad-0.444
Token top
Token ID1353
Feature activation+7.07e-02

Pos logit contributions
ascript+0.134
ウス+0.134
atism+0.120
hesion+0.119
 Tad+0.118
Neg logit contributions
alsh-0.169
 Steal-0.161
zee-0.150
BACK-0.150
horn-0.145
Token leadership
Token ID5531
Feature activation-4.93e-01

Pos logit contributions
ウス+0.048
ascript+0.048
atism+0.043
hesion+0.043
 Tad+0.042
Neg logit contributions
alsh-0.058
 Steal-0.056
zee-0.052
BACK-0.052
horn-0.050
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
alsh+0.443
 Steal+0.426
BACK+0.401
zee+0.400
horn+0.390
Neg logit contributions
ウス-0.298
ascript-0.295
atism-0.263
hesion-0.259
 partName-0.255
Token Instead
Token ID5455
Feature activation-2.93e-01

Pos logit contributions
ascript+0.222
ウス+0.221
atism+0.202
hesion+0.201
 Tad+0.199
Neg logit contributions
alsh-0.214
 Steal-0.204
zee-0.188
BACK-0.188
horn-0.181
Token he
Token ID339
Feature activation+2.34e-01

Pos logit contributions
alsh+0.230
 Steal+0.220
BACK+0.204
zee+0.203
horn+0.196
Neg logit contributions
ascript-0.211
ウス-0.211
atism-0.190
hesion-0.190
 Tad-0.187
Token named
Token ID3706
Feature activation-2.19e+00

Pos logit contributions
ウス+0.171
ascript+0.171
atism+0.154
hesion+0.154
 Tad+0.152
Neg logit contributions
alsh-0.182
 Steal-0.173
zee-0.161
BACK-0.160
horn-0.155
Token Cohn
Token ID45005
Feature activation-5.08e-01

Pos logit contributions
alsh+1.697
 Steal+1.627
zee+1.492
BACK+1.489
horn+1.453
Neg logit contributions
ウス-1.609
ascript-1.601
hesion-1.440
atism-1.434
 partName-1.391
Token,
Token ID11
Feature activation+8.76e-01

Pos logit contributions
alsh+0.392
 Steal+0.373
zee+0.346
BACK+0.345
horn+0.333
Neg logit contributions
ascript-0.372
ウス-0.372
atism-0.336
hesion-0.335
 Tad-0.331
Token his
Token ID465
Feature activation+6.63e-01

Pos logit contributions
ascript+0.648
ウス+0.645
atism+0.590
hesion+0.585
 Tad+0.585
Neg logit contributions
alsh-0.664
 Steal-0.632
zee-0.586
BACK-0.585
horn-0.561
Token long
Token ID890
Feature activation-1.33e-01

Pos logit contributions
ウス+0.422
ascript+0.422
atism+0.375
hesion+0.375
 Tad+0.367
Neg logit contributions
alsh-0.575
 Steal-0.551
zee-0.514
BACK-0.512
horn-0.497
Token-
Token ID12
Feature activation+3.19e-01

Pos logit contributions
alsh+0.108
 Steal+0.103
zee+0.096
BACK+0.096
horn+0.093
Neg logit contributions
ウス-0.092
ascript-0.092
atism-0.082
hesion-0.082
 Tad-0.081
Token achieved
Token ID8793
Feature activation-4.67e-01

Pos logit contributions
ascript+0.119
ウス+0.118
atism+0.107
hesion+0.106
 Tad+0.105
Neg logit contributions
alsh-0.141
 Steal-0.135
zee-0.126
BACK-0.126
horn-0.121
Token without
Token ID1231
Feature activation+3.43e-01

Pos logit contributions
alsh+0.378
 Steal+0.361
zee+0.335
BACK+0.335
horn+0.323
Neg logit contributions
ascript-0.323
ウス-0.323
atism-0.291
hesion-0.289
 Tad-0.287
Token players
Token ID1938
Feature activation+4.73e-01

Pos logit contributions
ascript+0.240
ウス+0.239
atism+0.216
hesion+0.215
 Tad+0.212
Neg logit contributions
alsh-0.276
 Steal-0.265
zee-0.246
BACK-0.245
horn-0.236
Token such
Token ID884
Feature activation-1.17e-01

Pos logit contributions
ascript+0.359
ウス+0.358
atism+0.326
hesion+0.324
 Tad+0.320
Neg logit contributions
alsh-0.352
 Steal-0.336
zee-0.310
BACK-0.309
horn-0.298
Token as
Token ID355
Feature activation-4.21e-01

Pos logit contributions
alsh+0.090
 Steal+0.086
BACK+0.080
zee+0.079
horn+0.076
Neg logit contributions
ascript-0.085
ウス-0.085
atism-0.077
hesion-0.077
 Tad-0.077
Token Sad
Token ID14668
Feature activation-2.26e+00

Pos logit contributions
alsh+0.332
 Steal+0.317
zee+0.294
BACK+0.293
horn+0.283
Neg logit contributions
ascript-0.300
ウス-0.299
atism-0.271
hesion-0.269
 Tad-0.266
Tokenio
Token ID952
Feature activation-5.84e-01

Pos logit contributions
alsh+1.737
 Steal+1.671
zee+1.562
BACK+1.545
horn+1.494
Neg logit contributions
ascript-1.660
ウス-1.645
hesion-1.484
atism-1.471
 Tad-1.463
Token Man
Token ID1869
Feature activation+3.60e-01

Pos logit contributions
alsh+0.471
 Steal+0.453
zee+0.424
BACK+0.421
horn+0.404
Neg logit contributions
ウス-0.398
ascript-0.396
 Tad-0.361
atism-0.361
hesion-0.358
Tokené
Token ID2634
Feature activation+4.77e-01

Pos logit contributions
ascript+0.247
ウス+0.243
atism+0.225
hesion+0.222
 Tad+0.220
Neg logit contributions
alsh-0.293
 Steal-0.278
BACK-0.258
zee-0.257
horn-0.248
Token,
Token ID11
Feature activation-1.36e-01

Pos logit contributions
ascript+0.343
ウス+0.342
atism+0.310
hesion+0.308
 Tad+0.306
Neg logit contributions
alsh-0.372
 Steal-0.354
zee-0.329
BACK-0.328
horn-0.315
Token Adam
Token ID7244
Feature activation+7.85e-01

Pos logit contributions
alsh+0.108
 Steal+0.103
zee+0.095
BACK+0.095
horn+0.091
Neg logit contributions
ascript-0.097
ウス-0.097
atism-0.088
hesion-0.087
 Tad-0.087
Token a
Token ID257
Feature activation-7.26e-01

Pos logit contributions
alsh+0.636
 Steal+0.613
BACK+0.571
zee+0.570
horn+0.548
Neg logit contributions
ascript-0.523
ウス-0.522
hesion-0.466
atism-0.465
 Tad-0.457
Token fast
Token ID3049
Feature activation-1.27e+00

Pos logit contributions
alsh+0.595
 Steal+0.572
BACK+0.530
zee+0.529
horn+0.509
Neg logit contributions
ascript-0.498
ウス-0.496
atism-0.445
hesion-0.443
 Tad-0.435
Token and
Token ID290
Feature activation-4.11e-01

Pos logit contributions
alsh+0.765
 Steal+0.721
BACK+0.653
zee+0.650
horn+0.618
Neg logit contributions
ascript-1.149
ウス-1.148
atism-1.061
hesion-1.051
 Tad-1.046
Token fun
Token ID1257
Feature activation-4.67e-01

Pos logit contributions
alsh+0.279
 Steal+0.264
zee+0.242
BACK+0.242
horn+0.231
Neg logit contributions
ascript-0.338
ウス-0.337
atism-0.309
hesion-0.308
 Tad-0.306
Token arcade
Token ID27210
Feature activation-1.90e+00

Pos logit contributions
alsh+0.379
 Steal+0.363
zee+0.337
BACK+0.337
horn+0.325
Neg logit contributions
ascript-0.324
ウス-0.323
atism-0.290
hesion-0.287
 Tad-0.284
Token style
Token ID3918
Feature activation-2.21e+00

Pos logit contributions
alsh+1.626
 Steal+1.569
BACK+1.462
zee+1.457
horn+1.412
Neg logit contributions
ascript-1.232
ウス-1.221
atism-1.079
 partName-1.060
hesion-1.056
Token racing
Token ID11717
Feature activation-1.93e+00

Pos logit contributions
alsh+1.803
 Steal+1.742
BACK+1.613
zee+1.604
horn+1.552
Neg logit contributions
ascript-1.529
ウス-1.522
atism-1.343
hesion-1.336
 partName-1.307
Token game
Token ID983
Feature activation-1.85e+00

Pos logit contributions
alsh+1.853
 Steal+1.789
BACK+1.685
zee+1.676
horn+1.648
Neg logit contributions
ascript-1.062
ウス-1.059
atism-0.909
hesion-0.894
 partName-0.878
Token that
Token ID326
Feature activation-8.01e-01

Pos logit contributions
alsh+1.412
 Steal+1.365
zee+1.248
BACK+1.246
horn+1.216
Neg logit contributions
ウス-1.368
ascript-1.349
atism-1.222
hesion-1.205
 partName-1.193
Token takes
Token ID2753
Feature activation+1.33e-01

Pos logit contributions
alsh+0.650
 Steal+0.625
zee+0.581
BACK+0.579
horn+0.559
Neg logit contributions
ウス-0.556
ascript-0.552
atism-0.492
hesion-0.490
 Tad-0.483
Token inspiration
Token ID12141
Feature activation-5.56e-01

Pos logit contributions
ascript+0.085
ウス+0.085
atism+0.075
hesion+0.074
 Tad+0.073
Neg logit contributions
alsh-0.116
 Steal-0.112
zee-0.104
BACK-0.104
horn-0.101