TOP ACTIVATIONS
MAX = 1.326

.. *) graph List = Table [ { Keys [ search
and Caribbean States ( C EL AC ) held its first
OT TA WA ( Reuters ) - Canada s
, says N ett les . This occurs as
result of supply - and - demand fundamentals . More and
( 13 , 5 )) sq K ernel = c v
HA V ANA ( Reuters ) - Latin American and Caribbean
2 . get Struct uring Element ( cv 2 . M
ent , eastern bar bar ians .
12 13 14 15 16 17 18 19 20 21 22
BR USS ELS ( Reuters ) - The world
United Supporters Trust ( N UST ), N UFC Fans United
Story Send email to this address Enter Your Name Add a
= New - Object System . Draw ing . Rect angle
2 . get Struct uring Element ( cv 2 . M
a Rails ( yes , Rails ) development team . Of
12 13 14 15 16 17 18 19 20 21 22
. Width ), ($ SR . Height ))) ) } }
state ( such as through a or ) must not modify
Boston ( pictured ), the Latin Academy , some areas in

MIN ACTIVATIONS
MIN = -1.232

Old Man Car rick (@ andy f erv s )
< li ng - repeat =" phone in phones "> <
. Old gift be arer setting box underneath roughly (
the iceberg ," he told The Associated Press in an interview
. Sw immer means to keep fit moving about ( 7
Europe against short - and medium - range Iranian missiles .
Advertisement Continue reading the main story Although
@ 144 Hz ( AMA = High ) 23
be arer setting box underneath roughly ( 6 ) C
MP P grade : C - In an appearance
the margin , as the dwelling supply builds over time .
= ($ text - split "\ r ") $
posted by Robert Math is (@ r math is _ the
wild beasts and tearing them to shred s , it
{{ 2 , 6 }, {{ 1 , 6 }, {
Sw immer means to keep fit moving about ( 7 )
which would likely involve medication ; or the talking
"] [ P ly Count " 94 "] [ Event Date
{ | i | print "# { i } " }
tele S UR English (@ tel es ure ng lish

INTERVAL 0.686 - 1.326
CONTAINS 0.193%

to open flights to US on sidelines of Trump - Kim
to do with electoral politics than it had to do with
suggest a few non - tax ing activities that the person
This is also mentioned in Sunni Had ith collections :
s point of view ) right - wing ers

INTERVAL 0.047 - 0.686
CONTAINS 40.593%

parliament . Relations between the Catalan and
services of Elliot Weinstein , a well - known defense lawyer
say it 's a circle . So , Earth 's orbit
more commun icative . But it was so baff ling to
recognize that his campaign often ve ered off - road and

INTERVAL -0.593 - 0.047
CONTAINS 58.772%

| aut oc omm and | . 3 . If you
C ultural and educational representations continue to perpetuate negative stereotypes
test methods to measure weak gravitational lens ing , another way
Forum at Newcastle United will be required to select an individual
ation might have been a black ace

INTERVAL -1.232 - -0.593
CONTAINS 0.442%

--+ | [ address of " pp pr "] | +
| < -- read () ' s frame + -------------------- --+
/ blogs / beat - the - press / the -
of 1987 , included Hat ay as part of Syria .
ar con Ortiz upon arrival at the Jose Mart i International
Token..
Token ID492
Feature activation+4.73e-02

Pos logit contributions
 Mug+0.134
iron+0.127
imus+0.120
rone+0.111
mia+0.109
Neg logit contributions
Animation-0.179
bj-0.176
lections-0.175
 DAR-0.173
 +=-0.173
Token *)
Token ID31936
Feature activation+4.11e-01

Pos logit contributions
Animation+0.283
bj+0.276
lections+0.273
 +=+0.272
 DAR+0.270
Neg logit contributions
 Mug-0.313
iron-0.299
imus-0.287
rone-0.271
mia-0.266
Token graph
Token ID4823
Feature activation+4.22e-01

Pos logit contributions
Animation+2.562
bj+2.517
 +=+2.500
lections+2.485
 DAR+2.454
Neg logit contributions
 Mug-2.577
iron-2.472
imus-2.389
rone-2.240
mia-2.197
TokenList
Token ID8053
Feature activation+5.59e-01

Pos logit contributions
Animation+2.132
bj+2.072
 +=+2.055
lections+2.042
 DAR+2.003
Neg logit contributions
 Mug-3.183
iron-3.059
imus-2.964
rone-2.817
mia-2.772
Token =
Token ID796
Feature activation+3.59e-01

Pos logit contributions
Animation+2.455
 +=+2.382
bj+2.362
lections+2.337
 DAR+2.267
Neg logit contributions
 Mug-4.565
iron-4.397
imus-4.273
rone-4.084
mia-4.037
Token Table
Token ID8655
Feature activation+1.33e+00

Pos logit contributions
Animation+2.243
bj+2.201
 +=+2.181
lections+2.176
 DAR+2.154
Neg logit contributions
 Mug-2.258
iron-2.163
imus-2.082
rone-1.956
mia-1.920
Token[
Token ID58
Feature activation+3.25e-02

Pos logit contributions
Animation+3.901
 +=+3.776
lections+3.497
bj+3.471
CH+3.391
Neg logit contributions
 Mug-12.120
iron-11.615
imus-11.613
rone-11.137
mia-10.957
Token {
Token ID1391
Feature activation-1.09e-02

Pos logit contributions
Animation+0.199
bj+0.194
lections+0.192
 +=+0.191
 DAR+0.189
Neg logit contributions
 Mug-0.211
iron-0.202
imus-0.194
rone-0.182
mia-0.179
Token Keys
Token ID26363
Feature activation+6.51e-01

Pos logit contributions
 Mug+0.070
iron+0.067
imus+0.064
rone+0.060
mia+0.059
Neg logit contributions
Animation-0.068
bj-0.066
lections-0.066
 +=-0.066
 DAR-0.065
Token[
Token ID58
Feature activation-2.22e-01

Pos logit contributions
Animation+1.904
 +=+1.847
bj+1.768
lections+1.753
CH+1.699
Neg logit contributions
 Mug-6.246
iron-6.046
imus-5.917
rone-5.688
mia-5.630
Tokensearch
Token ID12947
Feature activation-1.47e-01

Pos logit contributions
 Mug+1.339
iron+1.285
imus+1.219
rone+1.133
mia+1.117
Neg logit contributions
Animation-1.447
bj-1.400
lections-1.400
 +=-1.394
 DAR-1.388
Token and
Token ID290
Feature activation-1.55e-01

Pos logit contributions
 Mug+2.476
iron+2.294
imus+2.245
mia+2.067
rone+2.063
Neg logit contributions
Animation-1.958
bj-1.913
lections-1.884
 +=-1.824
awar-1.793
Token Caribbean
Token ID18020
Feature activation-2.41e-01

Pos logit contributions
 Mug+1.228
iron+1.152
imus+1.119
rone+1.068
 throat+1.051
Neg logit contributions
Animation-0.745
bj-0.719
lections-0.702
 +=-0.683
 DAR-0.675
Token States
Token ID1829
Feature activation-3.03e-01

Pos logit contributions
 Mug+1.644
iron+1.514
imus+1.456
rone+1.360
omy+1.354
Neg logit contributions
Animation-1.428
bj-1.417
lections-1.383
 +=-1.349
awar-1.317
Token (
Token ID357
Feature activation+1.39e-01

Pos logit contributions
 Mug+1.979
iron+1.868
imus+1.813
rone+1.663
mia+1.660
Neg logit contributions
Animation-1.811
bj-1.784
lections-1.749
 +=-1.729
 DAR-1.711
TokenC
Token ID34
Feature activation+1.47e-01

Pos logit contributions
Animation+0.701
bj+0.692
lections+0.678
 +=+0.677
 DAR+0.669
Neg logit contributions
 Mug-1.040
iron-1.008
imus-0.968
rone-0.923
mia-0.904
TokenEL
Token ID3698
Feature activation+1.28e+00

Pos logit contributions
Animation+0.783
bj+0.774
lections+0.759
 +=+0.757
 DAR+0.754
Neg logit contributions
 Mug-1.047
iron-1.023
imus-0.981
rone-0.924
omy-0.910
TokenAC
Token ID2246
Feature activation+6.79e-01

Pos logit contributions
Animation+4.719
CH+4.648
 DAR+4.355
bj+4.353
 +=+4.320
Neg logit contributions
 Mug-10.962
iron-10.426
imus-10.345
rone-9.919
omy-9.680
Token)
Token ID8
Feature activation-2.65e-01

Pos logit contributions
Animation+3.115
bj+3.028
lections+2.989
CH+2.967
 +=+2.963
Neg logit contributions
 Mug-5.366
iron-5.150
imus-4.974
rone-4.798
mia-4.697
Token held
Token ID2714
Feature activation-3.03e-01

Pos logit contributions
 Mug+1.865
iron+1.760
imus+1.702
rone+1.586
 isol+1.581
Neg logit contributions
Animation-1.457
bj-1.442
lections-1.421
 +=-1.393
 DAR-1.384
Token its
Token ID663
Feature activation-6.70e-01

Pos logit contributions
 Mug+1.896
iron+1.760
imus+1.691
rone+1.568
 throat+1.558
Neg logit contributions
Animation-1.963
bj-1.924
 +=-1.870
lections-1.869
 DAR-1.835
Token first
Token ID717
Feature activation-6.01e-01

Pos logit contributions
 Mug+3.807
iron+3.395
imus+3.349
rone+3.080
 throat+3.080
Neg logit contributions
Animation-4.650
bj-4.593
lections-4.455
 +=-4.412
ternity-4.334
TokenOT
Token ID2394
Feature activation-7.03e-02

Pos logit contributions
 Mug+0.126
iron+0.122
imus+0.116
rone+0.109
mia+0.108
Neg logit contributions
Animation-0.116
bj-0.115
lections-0.114
 +=-0.114
 DAR-0.113
TokenTA
Token ID5603
Feature activation+1.09e-02

Pos logit contributions
 Mug+0.522
iron+0.503
imus+0.485
rone+0.460
mia+0.451
Neg logit contributions
Animation-0.368
bj-0.359
lections-0.353
 +=-0.349
 DAR-0.342
TokenWA
Token ID15543
Feature activation+2.25e-01

Pos logit contributions
lections+0.039
Animation+0.038
bj+0.037
 +=+0.034
ternity+0.034
Neg logit contributions
 Mug-0.100
iron-0.096
imus-0.091
 throat-0.089
mia-0.088
Token (
Token ID357
Feature activation+3.75e-01

Pos logit contributions
Animation+1.472
bj+1.443
lections+1.427
 +=+1.423
 DAR+1.408
Neg logit contributions
 Mug-1.363
iron-1.298
imus-1.246
rone-1.163
mia-1.140
TokenReuters
Token ID12637
Feature activation+2.47e-01

Pos logit contributions
Animation+2.473
bj+2.413
 +=+2.370
lections+2.362
 DAR+2.361
Neg logit contributions
 Mug-2.249
iron-2.137
imus-2.071
rone-1.920
mia-1.886
Token)
Token ID8
Feature activation+1.22e+00

Pos logit contributions
Animation+1.156
bj+1.119
 +=+1.104
lections+1.096
 DAR+1.086
Neg logit contributions
 Mug-1.958
iron-1.894
imus-1.840
rone-1.746
mia-1.720
Token -
Token ID532
Feature activation+1.00e+00

Pos logit contributions
 +=+5.012
 Women+4.981
Animation+4.941
 DAR+4.681
CH+4.647
Neg logit contributions
imus-9.615
iron-9.448
 Mug-9.189
 territ-9.062
mia-8.915
Token Canada
Token ID3340
Feature activation-2.63e-02

Pos logit contributions
 Women+5.358
 DAR+5.315
Animation+5.302
bj+5.183
 +=+5.103
Neg logit contributions
iron-6.720
 Mug-6.692
imus-6.473
rone-6.123
omy-6.024
Token
Token ID447
Feature activation+3.90e-01

Pos logit contributions
 Mug+0.193
iron+0.184
imus+0.177
rone+0.167
 throat+0.165
Neg logit contributions
Animation-0.139
bj-0.138
lections-0.137
 +=-0.134
 DAR-0.132
Token
Token ID247
Feature activation+2.71e-01

Pos logit contributions
Animation+2.216
bj+2.159
lections+2.129
 +=+2.125
 DAR+2.092
Neg logit contributions
 Mug-2.694
iron-2.581
imus-2.490
rone-2.361
mia-2.304
Tokens
Token ID82
Feature activation+8.84e-02

Pos logit contributions
Animation+1.540
bj+1.503
lections+1.484
 +=+1.482
 DAR+1.464
Neg logit contributions
 Mug-1.872
iron-1.794
imus-1.730
rone-1.631
mia-1.604
Token,
Token ID11
Feature activation+1.04e-01

Pos logit contributions
Animation+1.124
bj+1.099
lections+1.090
 +=+1.082
 DAR+1.071
Neg logit contributions
 Mug-1.280
iron-1.226
imus-1.179
rone-1.110
mia-1.091
Token
Token ID447
Feature activation+2.32e-02

Pos logit contributions
Animation+0.575
bj+0.562
lections+0.559
 +=+0.555
 DAR+0.545
Neg logit contributions
 Mug-0.739
iron-0.710
imus-0.683
rone-0.647
mia-0.638
Token
Token ID251
Feature activation+9.67e-02

Pos logit contributions
Animation+0.148
bj+0.144
lections+0.143
 +=+0.141
 DAR+0.141
Neg logit contributions
 Mug-0.144
iron-0.139
imus-0.132
rone-0.123
mia-0.122
Token says
Token ID1139
Feature activation+4.62e-01

Pos logit contributions
Animation+0.591
bj+0.578
lections+0.576
 +=+0.572
 DAR+0.561
Neg logit contributions
 Mug-0.628
iron-0.599
imus-0.573
rone-0.540
mia-0.531
Token N
Token ID399
Feature activation+3.63e-01

Pos logit contributions
Animation+2.743
bj+2.694
 DAR+2.641
 +=+2.640
lections+2.637
Neg logit contributions
 Mug-3.038
iron-2.938
imus-2.837
rone-2.651
mia-2.607
Tokenett
Token ID3087
Feature activation+1.19e+00

Pos logit contributions
Animation+1.718
bj+1.677
lections+1.648
 +=+1.643
 DAR+1.608
Neg logit contributions
 Mug-2.862
iron-2.735
imus-2.656
rone-2.525
mia-2.488
Tokenles
Token ID829
Feature activation+2.74e-01

Pos logit contributions
lections+3.886
bj+3.806
Animation+3.776
 +=+3.643
CH+3.510
Neg logit contributions
 Mug-10.992
iron-10.027
imus-9.875
 metic-9.612
 throat-9.574
Token.
Token ID13
Feature activation-4.74e-02

Pos logit contributions
Animation+1.547
bj+1.511
lections+1.490
 +=+1.487
 DAR+1.469
Neg logit contributions
 Mug-1.907
iron-1.827
imus-1.764
rone-1.663
mia-1.634
Token This
Token ID770
Feature activation+2.85e-01

Pos logit contributions
 Mug+0.315
iron+0.295
imus+0.285
rone+0.269
mia+0.263
Neg logit contributions
Animation-0.282
lections-0.281
bj-0.279
 +=-0.271
 DAR-0.267
Token occurs
Token ID8833
Feature activation+1.90e-01

Pos logit contributions
Animation+1.643
bj+1.607
lections+1.588
 +=+1.580
 DAR+1.562
Neg logit contributions
 Mug-1.951
iron-1.866
imus-1.801
rone-1.697
mia-1.668
Token as
Token ID355
Feature activation+7.18e-02

Pos logit contributions
Animation+1.089
bj+1.065
lections+1.052
 +=+1.047
 DAR+1.035
Neg logit contributions
 Mug-1.311
iron-1.256
imus-1.211
rone-1.142
mia-1.121
Token result
Token ID1255
Feature activation-8.99e-05

Pos logit contributions
Animation+1.048
bj+1.024
lections+1.012
 +=+1.010
 DAR+0.994
Neg logit contributions
 Mug-0.897
iron-0.844
imus-0.809
rone-0.755
 throat-0.740
Token of
Token ID286
Feature activation-8.42e-02

Pos logit contributions
 Mug+0.001
iron+0.001
imus+0.001
rone+0.001
mia+0.001
Neg logit contributions
Animation-0.000
bj-0.000
lections-0.000
 +=-0.000
 DAR-0.000
Token supply
Token ID5127
Feature activation-2.73e-01

Pos logit contributions
 Mug+0.534
iron+0.501
imus+0.484
rone+0.455
 throat+0.448
Neg logit contributions
Animation-0.535
bj-0.524
 +=-0.515
lections-0.513
 DAR-0.502
Token-
Token ID12
Feature activation+6.53e-01

Pos logit contributions
 Mug+1.812
iron+1.715
imus+1.639
rone+1.558
 isol+1.555
Neg logit contributions
Animation-1.634
bj-1.605
lections-1.575
 +=-1.562
 DAR-1.537
Tokenand
Token ID392
Feature activation+7.28e-01

Pos logit contributions
Animation+3.318
bj+3.210
 +=+3.204
lections+3.178
 DAR+3.145
Neg logit contributions
 Mug-4.858
iron-4.533
imus-4.464
omy-4.199
 throat-4.185
Token-
Token ID12
Feature activation+1.19e+00

Pos logit contributions
Animation+3.373
 +=+3.244
 DAR+3.226
bj+3.223
 Women+3.193
Neg logit contributions
 Mug-5.619
iron-5.356
imus-5.211
rone-4.942
omy-4.837
Tokendemand
Token ID28550
Feature activation+5.72e-03

Pos logit contributions
weight+7.091
Animation+7.073
bj+6.931
CH+6.886
 +=+6.776
Neg logit contributions
 Mug-7.557
iron-6.608
imus-6.539
 throat-6.345
 isol-6.206
Token fundamentals
Token ID33099
Feature activation+4.63e-01

Pos logit contributions
Animation+0.035
bj+0.035
lections+0.034
 +=+0.034
 DAR+0.034
Neg logit contributions
 Mug-0.037
iron-0.035
imus-0.034
rone-0.032
mia-0.031
Token.
Token ID13
Feature activation+2.85e-01

Pos logit contributions
Animation+2.598
bj+2.541
lections+2.507
 +=+2.494
 DAR+2.473
Neg logit contributions
 Mug-3.186
iron-3.057
imus-2.967
rone-2.816
omy-2.736
Token More
Token ID3125
Feature activation+1.92e-01

Pos logit contributions
Animation+1.518
bj+1.477
 +=+1.456
lections+1.452
 DAR+1.447
Neg logit contributions
 Mug-2.061
iron-1.990
imus-1.927
rone-1.821
mia-1.795
Token and
Token ID290
Feature activation+1.38e-01

Pos logit contributions
Animation+1.261
bj+1.238
lections+1.222
 +=+1.219
 DAR+1.205
Neg logit contributions
 Mug-1.159
iron-1.102
imus-1.059
rone-0.990
mia-0.968
Token (
Token ID357
Feature activation-2.67e-01

Pos logit contributions
 Mug+1.183
iron+1.128
imus+1.081
rone+1.009
mia+0.987
Neg logit contributions
Animation-1.248
bj-1.228
lections-1.213
 +=-1.205
 DAR-1.191
Token13
Token ID1485
Feature activation-1.57e-01

Pos logit contributions
 Mug+1.308
iron+1.300
imus+1.203
rone+1.118
omy+1.083
Neg logit contributions
Animation-2.006
bj-1.964
lections-1.954
 +=-1.943
 DAR-1.941
Token,
Token ID11
Feature activation+1.58e-01

Pos logit contributions
 Mug+1.071
iron+1.030
imus+0.984
rone+0.930
mia+0.920
Neg logit contributions
Animation-0.903
lections-0.883
bj-0.879
 +=-0.854
 DAR-0.854
Token 5
Token ID642
Feature activation-4.50e-02

Pos logit contributions
Animation+0.749
bj+0.729
lections+0.718
 +=+0.711
 DAR+0.702
Neg logit contributions
 Mug-1.243
iron-1.194
imus-1.158
rone-1.101
mia-1.084
Token))
Token ID4008
Feature activation+6.95e-01

Pos logit contributions
 Mug+0.242
iron+0.229
imus+0.218
rone+0.202
mia+0.197
Neg logit contributions
Animation-0.326
bj-0.320
lections-0.316
 +=-0.316
 DAR-0.313
Token sq
Token ID19862
Feature activation+1.15e+00

Pos logit contributions
 +=+4.006
Animation+3.962
bj+3.920
lections+3.867
 DAR+3.829
Neg logit contributions
 Mug-4.597
iron-4.422
imus-4.320
rone-4.044
mia-3.906
TokenK
Token ID42
Feature activation+1.53e-01

Pos logit contributions
Animation+4.776
 +=+4.669
CH+4.652
bj+4.366
++)+4.316
Neg logit contributions
 Mug-9.252
imus-9.041
iron-9.025
 metic-8.842
 throat-8.659
Tokenernel
Token ID7948
Feature activation+8.79e-01

Pos logit contributions
Animation+0.723
bj+0.705
 +=+0.695
lections+0.695
 DAR+0.676
Neg logit contributions
 Mug-1.203
iron-1.155
imus-1.119
rone-1.058
 throat-1.048
Token =
Token ID796
Feature activation+7.37e-02

Pos logit contributions
 +=+2.033
Animation+1.850
bj+1.720
++)+1.611
CH+1.602
Neg logit contributions
 Mug-8.971
iron-8.664
imus-8.545
rone-8.361
 throat-8.334
Token c
Token ID269
Feature activation+5.08e-01

Pos logit contributions
Animation+0.475
bj+0.465
lections+0.460
 +=+0.459
 DAR+0.455
Neg logit contributions
 Mug-0.454
iron-0.433
imus-0.416
rone-0.389
mia-0.381
Tokenv
Token ID85
Feature activation+4.36e-01

Pos logit contributions
Animation+2.016
bj+2.002
 +=+1.945
lections+1.938
CH+1.851
Neg logit contributions
 Mug-4.390
iron-4.163
imus-4.081
rone-3.905
 throat-3.860
TokenHA
Token ID7801
Feature activation+3.74e-01

Pos logit contributions
Animation+0.196
bj+0.193
lections+0.191
 +=+0.191
 DAR+0.189
Neg logit contributions
 Mug-0.211
iron-0.204
imus-0.195
rone-0.183
mia-0.180
TokenV
Token ID53
Feature activation-2.94e-01

Pos logit contributions
Animation+1.940
bj+1.891
 +=+1.859
lections+1.858
 DAR+1.841
Neg logit contributions
 Mug-2.769
iron-2.649
imus-2.589
rone-2.446
mia-2.404
TokenANA
Token ID31574
Feature activation+1.27e-01

Pos logit contributions
 Mug+2.206
iron+2.163
imus+2.057
rone+1.948
Rog+1.940
Neg logit contributions
Animation-1.439
lections-1.390
bj-1.379
 +=-1.347
 DAR-1.327
Token (
Token ID357
Feature activation+3.21e-01

Pos logit contributions
Animation+0.767
bj+0.753
lections+0.745
 +=+0.738
 DAR+0.728
Neg logit contributions
 Mug-0.833
iron-0.793
imus-0.761
rone-0.719
mia-0.704
TokenReuters
Token ID12637
Feature activation+1.59e-01

Pos logit contributions
Animation+2.119
bj+2.072
 +=+2.041
lections+2.038
 DAR+2.021
Neg logit contributions
 Mug-1.928
iron-1.832
imus-1.770
rone-1.643
mia-1.610
Token)
Token ID8
Feature activation+1.10e+00

Pos logit contributions
Animation+0.763
bj+0.741
lections+0.729
 +=+0.729
 DAR+0.718
Neg logit contributions
 Mug-1.244
iron-1.199
imus-1.163
rone-1.104
mia-1.087
Token -
Token ID532
Feature activation+9.74e-01

Pos logit contributions
 +=+4.808
Animation+4.744
 Women+4.727
 DAR+4.519
CH+4.472
Neg logit contributions
imus-8.503
iron-8.405
 Mug-8.257
 territ-7.950
mia-7.895
Token Latin
Token ID9133
Feature activation+2.33e-01

Pos logit contributions
Animation+5.283
 Women+5.236
 DAR+5.207
bj+5.150
 +=+5.072
Neg logit contributions
iron-6.460
 Mug-6.391
imus-6.303
omy-5.846
rone-5.827
Token American
Token ID1605
Feature activation+4.74e-02

Pos logit contributions
Animation+1.478
bj+1.453
lections+1.437
 +=+1.425
 DAR+1.410
Neg logit contributions
 Mug-1.476
iron-1.397
imus-1.348
rone-1.256
mia-1.244
Token and
Token ID290
Feature activation-3.97e-02

Pos logit contributions
Animation+0.339
bj+0.336
lections+0.332
 +=+0.329
 DAR+0.323
Neg logit contributions
 Mug-0.263
iron-0.244
imus-0.233
rone-0.216
mia-0.212
Token Caribbean
Token ID18020
Feature activation-1.03e-01

Pos logit contributions
 Mug+0.294
iron+0.274
imus+0.265
 throat+0.251
rone+0.251
Neg logit contributions
Animation-0.214
bj-0.208
lections-0.206
 +=-0.201
 DAR-0.195
Token2
Token ID17
Feature activation+4.15e-01

Pos logit contributions
Animation+3.001
bj+2.935
 +=+2.919
lections+2.865
CH+2.843
Neg logit contributions
 Mug-2.505
iron-2.337
imus-2.283
rone-2.112
 throat-2.092
Token.
Token ID13
Feature activation+6.09e-01

Pos logit contributions
Animation+2.208
bj+2.160
 +=+2.153
lections+2.099
 DAR+2.082
Neg logit contributions
 Mug-3.003
iron-2.870
imus-2.801
rone-2.657
 throat-2.607
Tokenget
Token ID1136
Feature activation+4.57e-01

Pos logit contributions
Animation+3.773
bj+3.664
 +=+3.633
CH+3.613
lections+3.558
Neg logit contributions
 Mug-3.884
iron-3.598
imus-3.530
 throat-3.357
rone-3.356
TokenStruct
Token ID44909
Feature activation-1.70e-02

Pos logit contributions
Animation+2.928
 +=+2.809
bj+2.799
lections+2.749
CH+2.733
Neg logit contributions
 Mug-2.841
iron-2.738
imus-2.641
rone-2.505
 throat-2.469
Tokenuring
Token ID870
Feature activation+1.46e-01

Pos logit contributions
 Mug+0.068
iron+0.064
imus+0.060
rone+0.053
omy+0.052
Neg logit contributions
Animation-0.146
bj-0.144
lections-0.142
 +=-0.142
 DAR-0.142
TokenElement
Token ID20180
Feature activation+1.10e+00

Pos logit contributions
Animation+0.988
bj+0.965
 +=+0.956
lections+0.955
 DAR+0.944
Neg logit contributions
 Mug-0.852
iron-0.809
imus-0.776
rone-0.724
mia-0.708
Token(
Token ID7
Feature activation+4.27e-01

Pos logit contributions
Animation+2.966
 +=+2.840
bj+2.738
CH+2.657
weight+2.491
Neg logit contributions
 Mug-10.641
imus-10.170
iron-10.006
 metic-9.896
 throat-9.844
Tokencv
Token ID33967
Feature activation+2.60e-01

Pos logit contributions
Animation+2.746
bj+2.719
lections+2.669
 +=+2.664
 DAR+2.622
Neg logit contributions
 Mug-2.640
iron-2.472
imus-2.402
rone-2.235
 throat-2.201
Token2
Token ID17
Feature activation+1.35e-01

Pos logit contributions
Animation+1.861
bj+1.824
 +=+1.806
lections+1.798
 DAR+1.780
Neg logit contributions
 Mug-1.425
iron-1.341
imus-1.289
rone-1.192
 throat-1.163
Token.
Token ID13
Feature activation+2.11e-01

Pos logit contributions
Animation+0.779
bj+0.762
lections+0.752
 +=+0.749
 DAR+0.741
Neg logit contributions
 Mug-0.926
iron-0.887
imus-0.855
rone-0.805
mia-0.792
TokenM
Token ID44
Feature activation+8.98e-01

Pos logit contributions
Animation+1.484
bj+1.455
lections+1.439
 +=+1.437
 DAR+1.424
Neg logit contributions
 Mug-1.180
iron-1.119
imus-1.071
rone-0.993
mia-0.970
Tokenent
Token ID298
Feature activation+1.25e-01

Pos logit contributions
Animation+0.816
bj+0.799
lections+0.794
 +=+0.790
 DAR+0.776
Neg logit contributions
 Mug-1.031
iron-0.983
imus-0.952
rone-0.900
mia-0.882
Token,
Token ID11
Feature activation-2.25e-01

Pos logit contributions
Animation+0.672
bj+0.656
lections+0.646
 +=+0.645
 DAR+0.637
Neg logit contributions
 Mug-0.898
iron-0.861
imus-0.833
rone-0.787
mia-0.774
Token eastern
Token ID10183
Feature activation+9.56e-01

Pos logit contributions
 Mug+1.314
iron+1.289
imus+1.203
rone+1.143
 isol+1.130
Neg logit contributions
Animation-1.500
bj-1.480
lections-1.459
CH-1.426
 +=-1.423
Token
Token ID564
Feature activation+9.31e-02

Pos logit contributions
Animation+4.216
 +=+4.064
bj+4.031
lections+4.026
 DAR+3.954
Neg logit contributions
 Mug-7.476
iron-7.182
imus-6.916
rone-6.646
Rog-6.519
Token
Token ID246
Feature activation+5.10e-01

Pos logit contributions
Animation+0.610
bj+0.598
 +=+0.591
lections+0.590
 DAR+0.582
Neg logit contributions
 Mug-0.565
iron-0.534
imus-0.515
rone-0.479
mia-0.470
Tokenbar
Token ID5657
Feature activation+1.09e+00

Pos logit contributions
bj+2.726
Animation+2.660
 +=+2.587
lections+2.555
CH+2.511
Neg logit contributions
 Mug-3.746
imus-3.391
iron-3.388
rone-3.201
 throat-3.183
Tokenbar
Token ID5657
Feature activation+1.55e-01

Pos logit contributions
bj+4.754
 +=+4.411
Animation+4.358
weight+4.329
awar+4.244
Neg logit contributions
 Mug-8.924
imus-7.904
 Lime-7.721
iron-7.667
 isol-7.637
Tokenians
Token ID1547
Feature activation+5.60e-01

Pos logit contributions
Animation+1.286
bj+1.268
lections+1.255
 +=+1.253
 DAR+1.242
Neg logit contributions
 Mug-0.664
iron-0.616
imus-0.581
rone-0.523
mia-0.508
Token
Token ID447
Feature activation+1.79e-01

Pos logit contributions
Animation+2.374
bj+2.268
lections+2.247
 +=+2.227
 DAR+2.174
Neg logit contributions
 Mug-4.663
iron-4.459
imus-4.326
rone-4.131
 throat-4.068
Token
Token ID247
Feature activation-1.13e-02

Pos logit contributions
Animation+0.984
bj+0.961
lections+0.948
 +=+0.943
 DAR+0.934
Neg logit contributions
 Mug-1.273
iron-1.223
imus-1.180
rone-1.117
mia-1.097
Token.
Token ID13
Feature activation+1.06e-01

Pos logit contributions
 Mug+0.075
iron+0.073
imus+0.070
rone+0.066
mia+0.064
Neg logit contributions
Animation-0.067
bj-0.065
lections-0.064
 +=-0.064
 DAR-0.064
Token 12
Token ID1105
Feature activation+1.82e-01

Pos logit contributions
Animation+3.144
 +=+3.108
bj+3.106
lections+3.068
 DAR+3.065
Neg logit contributions
 Mug-3.499
iron-3.311
imus-3.192
rone-3.022
mia-3.017
Token 13
Token ID1511
Feature activation+5.04e-01

Pos logit contributions
Animation+1.208
bj+1.193
 +=+1.185
lections+1.179
 DAR+1.172
Neg logit contributions
 Mug-1.078
iron-1.020
imus-0.980
rone-0.919
mia-0.910
Token 14
Token ID1478
Feature activation+5.19e-01

Pos logit contributions
Animation+2.896
bj+2.860
 +=+2.843
 DAR+2.819
lections+2.806
Neg logit contributions
 Mug-3.373
iron-3.198
imus-3.087
rone-2.950
mia-2.905
Token 15
Token ID1315
Feature activation+8.20e-01

Pos logit contributions
Animation+2.769
bj+2.740
 +=+2.712
lections+2.692
 DAR+2.672
Neg logit contributions
 Mug-3.729
iron-3.553
imus-3.449
rone-3.262
mia-3.231
Token 16
Token ID1467
Feature activation+6.80e-01

Pos logit contributions
Animation+4.253
 DAR+4.231
 +=+4.231
bj+4.229
lections+4.093
Neg logit contributions
 Mug-5.871
iron-5.554
imus-5.396
mia-5.110
rone-5.095
Token 17
Token ID1596
Feature activation+1.09e+00

Pos logit contributions
Animation+3.113
 +=+3.093
bj+3.091
 DAR+3.065
lections+3.039
Neg logit contributions
 Mug-5.318
iron-5.136
imus-4.914
rone-4.727
mia-4.722
Token 18
Token ID1248
Feature activation+6.45e-01

Pos logit contributions
Animation+4.771
 +=+4.755
 DAR+4.740
bj+4.718
CH+4.615
Neg logit contributions
 Mug-8.375
iron-7.977
imus-7.685
rone-7.506
mia-7.312
Token 19
Token ID678
Feature activation+7.03e-01

Pos logit contributions
bj+3.968
Animation+3.949
 +=+3.921
CH+3.879
 DAR+3.833
Neg logit contributions
 Mug-4.017
iron-3.768
imus-3.724
mia-3.454
rone-3.446
Token 20
Token ID1160
Feature activation+6.61e-01

Pos logit contributions
Animation+3.733
bj+3.673
 +=+3.654
lections+3.569
 DAR+3.556
Neg logit contributions
 Mug-4.945
iron-4.738
imus-4.656
rone-4.364
mia-4.345
Token 21
Token ID2310
Feature activation+6.24e-01

Pos logit contributions
Animation+3.789
bj+3.761
 +=+3.759
 DAR+3.683
lections+3.656
Neg logit contributions
 Mug-4.401
iron-4.208
imus-4.100
mia-3.867
rone-3.804
Token 22
Token ID2534
Feature activation+2.56e-01

Pos logit contributions
Animation+3.448
 +=+3.395
bj+3.376
 DAR+3.325
lections+3.316
Neg logit contributions
 Mug-4.313
iron-4.129
imus-4.010
mia-3.779
rone-3.762
TokenBR
Token ID11473
Feature activation+4.82e-01

Pos logit contributions
Animation+0.076
bj+0.075
lections+0.075
 +=+0.074
 DAR+0.074
Neg logit contributions
 Mug-0.083
iron-0.080
imus-0.076
rone-0.072
mia-0.071
TokenUSS
Token ID32835
Feature activation+1.59e-01

Pos logit contributions
Animation+2.633
bj+2.562
 +=+2.532
lections+2.514
 DAR+2.501
Neg logit contributions
 Mug-3.424
iron-3.298
imus-3.201
rone-3.024
mia-2.970
TokenELS
Token ID37142
Feature activation+3.72e-01

Pos logit contributions
Animation+0.626
lections+0.608
bj+0.607
 +=+0.589
 DAR+0.567
Neg logit contributions
 Mug-1.383
iron-1.322
imus-1.280
rone-1.221
omy-1.210
Token (
Token ID357
Feature activation+3.21e-01

Pos logit contributions
Animation+2.334
bj+2.283
 +=+2.261
lections+2.252
 DAR+2.239
Neg logit contributions
 Mug-2.337
iron-2.230
imus-2.155
rone-2.011
mia-1.982
TokenReuters
Token ID12637
Feature activation+1.28e-01

Pos logit contributions
Animation+2.119
bj+2.072
 +=+2.037
lections+2.027
 DAR+2.017
Neg logit contributions
 Mug-1.931
iron-1.836
imus-1.782
rone-1.650
mia-1.625
Token)
Token ID8
Feature activation+1.09e+00

Pos logit contributions
Animation+0.616
bj+0.600
lections+0.591
 +=+0.588
 DAR+0.580
Neg logit contributions
 Mug-0.992
iron-0.955
imus-0.925
rone-0.879
mia-0.865
Token -
Token ID532
Feature activation+8.95e-01

Pos logit contributions
 +=+4.763
Animation+4.723
 Women+4.668
 DAR+4.492
CH+4.450
Neg logit contributions
imus-8.372
iron-8.300
 Mug-8.170
 territ-7.860
mia-7.802
Token The
Token ID383
Feature activation+3.83e-01

Pos logit contributions
Animation+5.094
 Women+5.080
 DAR+5.054
bj+5.011
 +=+4.889
Neg logit contributions
iron-5.705
 Mug-5.652
imus-5.529
mia-5.150
omy-5.119
Token world
Token ID995
Feature activation+2.99e-02

Pos logit contributions
Animation+2.373
bj+2.324
lections+2.292
 +=+2.287
 DAR+2.275
Neg logit contributions
 Mug-2.435
iron-2.341
imus-2.252
rone-2.107
mia-2.073
Token
Token ID447
Feature activation+2.22e-01

Pos logit contributions
Animation+0.157
lections+0.153
bj+0.153
 +=+0.152
 DAR+0.148
Neg logit contributions
 Mug-0.221
iron-0.211
imus-0.204
rone-0.193
 throat-0.191
Token
Token ID247
Feature activation+3.27e-01

Pos logit contributions
Animation+1.309
bj+1.280
lections+1.263
 +=+1.261
 DAR+1.245
Neg logit contributions
 Mug-1.493
iron-1.428
imus-1.378
rone-1.297
mia-1.272
Token United
Token ID1578
Feature activation+1.72e-01

Pos logit contributions
 Mug+0.141
iron+0.135
imus+0.128
rone+0.121
mia+0.119
Neg logit contributions
Animation-0.113
bj-0.111
lections-0.109
 +=-0.109
 DAR-0.107
Token Supporters
Token ID39995
Feature activation-3.38e-02

Pos logit contributions
Animation+0.922
bj+0.902
lections+0.889
 +=+0.880
 DAR+0.869
Neg logit contributions
 Mug-1.263
iron-1.208
imus-1.166
rone-1.101
mia-1.086
Token Trust
Token ID9870
Feature activation+1.15e-01

Pos logit contributions
 Mug+0.223
iron+0.211
imus+0.203
rone+0.189
omy+0.185
Neg logit contributions
Animation-0.207
bj-0.202
lections-0.198
 +=-0.198
 DAR-0.195
Token (
Token ID357
Feature activation-1.92e-01

Pos logit contributions
Animation+0.663
bj+0.646
lections+0.637
 +=+0.636
 DAR+0.629
Neg logit contributions
 Mug-0.795
iron-0.761
imus-0.735
rone-0.691
mia-0.677
TokenN
Token ID45
Feature activation+5.81e-02

Pos logit contributions
 Mug+1.280
iron+1.237
imus+1.178
rone+1.112
mia+1.091
Neg logit contributions
Animation-1.117
bj-1.100
lections-1.098
 +=-1.093
 DAR-1.082
TokenUST
Token ID7759
Feature activation+1.09e+00

Pos logit contributions
Animation+0.350
bj+0.343
 DAR+0.337
 +=+0.336
lections+0.336
Neg logit contributions
 Mug-0.382
iron-0.372
imus-0.356
rone-0.329
omy-0.327
Token),
Token ID828
Feature activation-1.68e-03

Pos logit contributions
Animation+5.291
lections+5.242
CH+5.190
bj+5.142
 Women+5.091
Neg logit contributions
 Mug-7.998
iron-7.560
imus-7.443
mia-7.090
rone-6.939
Token N
Token ID399
Feature activation-8.27e-02

Pos logit contributions
 Mug+0.011
iron+0.010
imus+0.010
rone+0.009
mia+0.009
Neg logit contributions
Animation-0.011
bj-0.010
lections-0.010
 +=-0.010
 DAR-0.010
TokenUFC
Token ID44534
Feature activation+4.47e-01

Pos logit contributions
 Mug+0.579
iron+0.561
imus+0.537
rone+0.506
omy+0.500
Neg logit contributions
Animation-0.462
bj-0.454
 +=-0.446
 DAR-0.444
lections-0.443
Token Fans
Token ID24964
Feature activation+2.70e-02

Pos logit contributions
Animation+2.420
bj+2.360
lections+2.334
 +=+2.323
 DAR+2.294
Neg logit contributions
 Mug-3.183
iron-3.059
imus-2.960
rone-2.796
mia-2.757
Token United
Token ID1578
Feature activation+9.05e-02

Pos logit contributions
Animation+0.154
bj+0.150
 +=+0.148
lections+0.147
 DAR+0.146
Neg logit contributions
 Mug-0.188
iron-0.179
imus-0.174
rone-0.162
mia-0.159
Token Story
Token ID8362
Feature activation+5.03e-01

Pos logit contributions
Animation+0.178
bj+0.175
lections+0.174
 +=+0.173
 DAR+0.170
Neg logit contributions
 Mug-0.104
iron-0.095
imus-0.091
rone-0.082
mia-0.080
Token Send
Token ID16290
Feature activation+8.25e-01

Pos logit contributions
 +=+2.693
Animation+2.666
 DAR+2.648
 Women+2.624
bj+2.613
Neg logit contributions
iron-3.416
 Mug-3.372
imus-3.315
rone-3.218
mia-3.109
Token email
Token ID3053
Feature activation+1.04e+00

Pos logit contributions
 Women+2.668
 DAR+2.664
bj+2.583
 +=+2.503
Animation+2.461
Neg logit contributions
iron-7.235
 Mug-7.009
imus-6.954
rone-6.907
omy-6.858
Token to
Token ID284
Feature activation+4.38e-01

Pos logit contributions
 +=+4.360
Animation+4.285
bj+4.216
 DAR+4.187
lections+4.184
Neg logit contributions
 Mug-8.259
iron-8.125
imus-7.809
omy-7.521
rone-7.482
Token this
Token ID428
Feature activation+1.74e-01

Pos logit contributions
Animation+2.387
lections+2.356
bj+2.318
 DAR+2.309
 Women+2.279
Neg logit contributions
 Mug-3.049
iron-2.970
imus-2.775
rone-2.661
mia-2.632
Token address
Token ID2209
Feature activation+1.09e+00

Pos logit contributions
Animation+0.977
bj+0.973
lections+0.970
 +=+0.956
 DAR+0.951
Neg logit contributions
 Mug-1.207
iron-1.162
imus-1.106
rone-1.053
ebted-1.031
Token Enter
Token ID6062
Feature activation+2.90e-01

Pos logit contributions
 DAR+6.216
 Women+6.173
 +=+6.162
lections+6.050
bj+6.027
Neg logit contributions
iron-6.824
 Mug-6.819
omy-6.444
imus-6.427
ebted-6.316
Token Your
Token ID3406
Feature activation+3.69e-01

Pos logit contributions
Animation+1.693
 +=+1.640
bj+1.637
lections+1.633
 Women+1.625
Neg logit contributions
 Mug-1.938
iron-1.894
imus-1.819
rone-1.706
omy-1.659
Token Name
Token ID6530
Feature activation+1.02e+00

Pos logit contributions
Animation+2.416
lections+2.371
 +=+2.357
 Women+2.355
 DAR+2.338
Neg logit contributions
 Mug-2.167
iron-2.155
imus-1.989
rone-1.856
 throat-1.846
Token Add
Token ID3060
Feature activation+7.24e-01

Pos logit contributions
 +=+3.864
Animation+3.855
 Women+3.848
 Architects+3.682
bj+3.680
Neg logit contributions
iron-8.526
 Mug-8.323
imus-8.068
ebted-7.939
rone-7.893
Token a
Token ID257
Feature activation+5.66e-01

Pos logit contributions
Animation+3.344
lections+3.283
 Women+3.243
 DAR+3.235
 +=+3.222
Neg logit contributions
 Mug-5.491
iron-5.426
imus-5.210
rone-5.068
 throat-4.929
Token =
Token ID796
Feature activation+7.09e-01

Pos logit contributions
Animation+0.726
bj+0.694
 +=+0.679
lections+0.672
 DAR+0.655
Neg logit contributions
 Mug-2.362
iron-2.290
imus-2.235
rone-2.146
mia-2.118
Token New
Token ID968
Feature activation+1.48e-01

Pos logit contributions
Animation+2.205
 +=+2.125
 Women+2.078
bj+2.044
 DAR+2.043
Neg logit contributions
 Mug-6.493
iron-6.461
imus-6.280
rone-6.038
 throat-6.010
Token-
Token ID12
Feature activation+5.53e-01

Pos logit contributions
Animation+0.814
bj+0.795
lections+0.784
 +=+0.782
 DAR+0.772
Neg logit contributions
 Mug-1.055
iron-1.011
imus-0.977
rone-0.923
mia-0.907
TokenObject
Token ID10267
Feature activation-2.76e-01

Pos logit contributions
Animation+2.579
 +=+2.394
bj+2.382
CH+2.356
++)+2.277
Neg logit contributions
 Mug-4.518
imus-4.268
iron-4.225
 throat-4.038
rone-4.001
Token System
Token ID4482
Feature activation+6.20e-01

Pos logit contributions
 Mug+1.168
iron+1.046
imus+0.987
rone+0.869
omy+0.853
Neg logit contributions
Animation-2.310
bj-2.309
lections-2.277
 +=-2.249
ternity-2.235
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
Animation+3.085
 +=+3.002
bj+2.972
CH+2.876
 Women+2.865
Neg logit contributions
 Mug-4.686
iron-4.457
imus-4.399
rone-4.171
 throat-4.129
TokenDraw
Token ID25302
Feature activation+1.27e-01

Pos logit contributions
Animation+3.416
 +=+2.892
CH+2.834
bj+2.780
 Women+2.711
Neg logit contributions
 Mug-10.215
imus-9.886
iron-9.700
 metic-9.614
 throat-9.591
Tokening
Token ID278
Feature activation+1.23e-01

Pos logit contributions
Animation+0.682
bj+0.664
lections+0.655
 +=+0.654
 DAR+0.643
Neg logit contributions
 Mug-0.916
iron-0.876
imus-0.850
rone-0.804
mia-0.789
Token.
Token ID13
Feature activation+3.17e-01

Pos logit contributions
Animation+0.703
bj+0.687
lections+0.677
 +=+0.677
 DAR+0.668
Neg logit contributions
 Mug-0.847
iron-0.811
imus-0.783
rone-0.738
mia-0.725
TokenRect
Token ID45474
Feature activation+3.97e-01

Pos logit contributions
Animation+1.599
bj+1.520
 +=+1.510
lections+1.493
 DAR+1.462
Neg logit contributions
 Mug-2.431
iron-2.325
imus-2.266
rone-2.145
mia-2.122
Tokenangle
Token ID9248
Feature activation+3.28e-01

Pos logit contributions
Animation+1.769
bj+1.723
 +=+1.713
lections+1.693
CH+1.612
Neg logit contributions
 Mug-3.267
iron-3.064
imus-3.012
 throat-2.843
rone-2.842
Token2
Token ID17
Feature activation+6.51e-02

Pos logit contributions
Animation+1.896
bj+1.857
 +=+1.841
lections+1.824
 DAR+1.805
Neg logit contributions
 Mug-1.493
iron-1.402
imus-1.355
rone-1.253
 throat-1.228
Token.
Token ID13
Feature activation+1.46e-01

Pos logit contributions
Animation+0.380
bj+0.372
lections+0.368
 +=+0.365
 DAR+0.363
Neg logit contributions
 Mug-0.440
iron-0.422
imus-0.406
rone-0.382
mia-0.376
Tokenget
Token ID1136
Feature activation+4.80e-01

Pos logit contributions
Animation+0.979
bj+0.961
lections+0.948
 +=+0.947
 DAR+0.934
Neg logit contributions
 Mug-0.861
iron-0.813
imus-0.782
rone-0.730
 throat-0.712
TokenStruct
Token ID44909
Feature activation-2.05e-01

Pos logit contributions
Animation+3.033
 +=+2.900
bj+2.890
lections+2.832
CH+2.820
Neg logit contributions
 Mug-3.047
iron-2.928
imus-2.838
rone-2.681
 throat-2.664
Tokenuring
Token ID870
Feature activation+1.70e-01

Pos logit contributions
 Mug+0.757
iron+0.715
imus+0.662
rone+0.580
omy+0.578
Neg logit contributions
Animation-1.807
bj-1.792
 DAR-1.775
 +=-1.758
lections-1.756
TokenElement
Token ID20180
Feature activation+1.08e+00

Pos logit contributions
Animation+1.151
bj+1.121
 +=+1.112
lections+1.109
 DAR+1.096
Neg logit contributions
 Mug-1.002
iron-0.950
imus-0.912
rone-0.851
mia-0.833
Token(
Token ID7
Feature activation+1.35e-01

Pos logit contributions
Animation+2.832
 +=+2.731
bj+2.664
CH+2.527
weight+2.332
Neg logit contributions
 Mug-10.536
imus-10.006
iron-9.882
 throat-9.670
 metic-9.636
Tokencv
Token ID33967
Feature activation+1.10e-01

Pos logit contributions
Animation+0.924
bj+0.905
lections+0.896
 +=+0.894
 DAR+0.886
Neg logit contributions
 Mug-0.780
iron-0.742
imus-0.710
rone-0.661
mia-0.647
Token2
Token ID17
Feature activation-2.40e-01

Pos logit contributions
Animation+0.806
bj+0.792
lections+0.785
 +=+0.782
 DAR+0.776
Neg logit contributions
 Mug-0.582
iron-0.552
imus-0.525
rone-0.485
mia-0.474
Token.
Token ID13
Feature activation-7.89e-02

Pos logit contributions
 Mug+1.498
iron+1.446
imus+1.364
mia+1.275
rone+1.273
Neg logit contributions
Animation-1.491
lections-1.479
bj-1.464
 DAR-1.439
ternity-1.431
TokenM
Token ID44
Feature activation+8.90e-01

Pos logit contributions
 Mug+0.408
iron+0.385
imus+0.363
mia+0.332
rone+0.332
Neg logit contributions
bj-0.578
lections-0.578
Animation-0.575
 +=-0.565
 DAR-0.559
Token a
Token ID257
Feature activation+4.71e-02

Pos logit contributions
 Mug+0.991
iron+0.940
imus+0.898
rone+0.846
 throat+0.841
Neg logit contributions
Animation-0.938
bj-0.917
lections-0.902
 +=-0.893
 DAR-0.876
Token Rails
Token ID31493
Feature activation+4.19e-01

Pos logit contributions
Animation+0.333
bj+0.326
lections+0.322
 +=+0.320
 DAR+0.315
Neg logit contributions
 Mug-0.264
iron-0.248
imus-0.236
rone-0.220
 throat-0.216
Token (
Token ID357
Feature activation+1.18e-01

Pos logit contributions
Animation+2.731
bj+2.677
lections+2.643
 +=+2.640
 DAR+2.614
Neg logit contributions
 Mug-2.547
iron-2.421
imus-2.331
rone-2.176
mia-2.126
Tokenyes
Token ID8505
Feature activation-1.04e-01

Pos logit contributions
Animation+0.645
bj+0.631
lections+0.623
 +=+0.621
 DAR+0.614
Neg logit contributions
 Mug-0.836
iron-0.809
imus-0.776
rone-0.733
mia-0.722
Token,
Token ID11
Feature activation+1.20e-01

Pos logit contributions
 Mug+0.716
iron+0.690
imus+0.658
rone+0.622
 throat+0.613
Neg logit contributions
Animation-0.596
bj-0.585
lections-0.571
 +=-0.570
 DAR-0.558
Token Rails
Token ID31493
Feature activation+1.07e+00

Pos logit contributions
Animation+0.735
bj+0.719
lections+0.708
 +=+0.706
 DAR+0.696
Neg logit contributions
 Mug-0.778
iron-0.743
imus-0.712
rone-0.668
mia-0.657
Token)
Token ID8
Feature activation+2.71e-01

Pos logit contributions
Animation+5.072
bj+4.941
 +=+4.913
 DAR+4.890
 Women+4.886
Neg logit contributions
 Mug-7.854
iron-7.521
imus-7.352
rone-7.050
mia-6.776
Token development
Token ID2478
Feature activation+3.35e-01

Pos logit contributions
Animation+1.854
bj+1.819
lections+1.800
 +=+1.795
 DAR+1.778
Neg logit contributions
 Mug-1.561
iron-1.482
imus-1.419
rone-1.320
mia-1.292
Token team
Token ID1074
Feature activation+9.05e-02

Pos logit contributions
Animation+2.293
bj+2.248
lections+2.223
 +=+2.223
 DAR+2.203
Neg logit contributions
 Mug-1.930
iron-1.834
imus-1.759
rone-1.634
mia-1.599
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
Animation+0.539
bj+0.527
lections+0.520
 +=+0.519
 DAR+0.513
Neg logit contributions
 Mug-0.603
iron-0.576
imus-0.555
rone-0.522
mia-0.513
Token Of
Token ID3226
Feature activation-7.46e-02

Pos logit contributions
Animation+0.881
bj+0.862
lections+0.853
 +=+0.848
 DAR+0.837
Neg logit contributions
 Mug-0.996
iron-0.950
imus-0.915
rone-0.860
mia-0.844
Token 12
Token ID1105
Feature activation+1.93e-01

Pos logit contributions
Animation+2.835
 +=+2.798
bj+2.785
 DAR+2.769
lections+2.767
Neg logit contributions
 Mug-3.077
iron-2.918
imus-2.814
mia-2.670
rone-2.656
Token 13
Token ID1511
Feature activation+4.76e-01

Pos logit contributions
Animation+1.300
bj+1.279
 +=+1.273
lections+1.268
 DAR+1.262
Neg logit contributions
 Mug-1.125
iron-1.066
imus-1.022
rone-0.959
mia-0.952
Token 14
Token ID1478
Feature activation+5.24e-01

Pos logit contributions
Animation+2.803
bj+2.744
 +=+2.741
 DAR+2.729
lections+2.716
Neg logit contributions
 Mug-3.117
iron-2.970
imus-2.852
rone-2.733
mia-2.705
Token 15
Token ID1315
Feature activation+8.08e-01

Pos logit contributions
Animation+2.781
bj+2.744
 +=+2.728
lections+2.709
 DAR+2.697
Neg logit contributions
 Mug-3.753
iron-3.580
imus-3.470
rone-3.295
mia-3.275
Token 16
Token ID1467
Feature activation+8.82e-01

Pos logit contributions
 DAR+4.177
Animation+4.176
 +=+4.147
bj+4.099
 Women+4.022
Neg logit contributions
 Mug-5.803
iron-5.480
imus-5.307
mia-5.100
rone-5.059
Token 17
Token ID1596
Feature activation+1.07e+00

Pos logit contributions
 +=+3.750
 DAR+3.733
Animation+3.713
bj+3.652
lections+3.626
Neg logit contributions
 Mug-7.081
iron-6.857
imus-6.509
mia-6.408
rone-6.370
Token 18
Token ID1248
Feature activation+5.82e-01

Pos logit contributions
Animation+4.695
 DAR+4.658
 +=+4.620
bj+4.564
 Women+4.555
Neg logit contributions
 Mug-8.134
iron-7.748
imus-7.479
rone-7.339
mia-7.214
Token 19
Token ID678
Feature activation+7.00e-01

Pos logit contributions
Animation+3.648
bj+3.633
 +=+3.595
CH+3.558
 DAR+3.539
Neg logit contributions
 Mug-3.558
iron-3.355
imus-3.300
mia-3.079
rone-3.059
Token 20
Token ID1160
Feature activation+7.09e-01

Pos logit contributions
Animation+3.684
 +=+3.608
bj+3.592
 DAR+3.533
lections+3.516
Neg logit contributions
 Mug-4.924
iron-4.744
imus-4.663
mia-4.387
rone-4.376
Token 21
Token ID2310
Feature activation+6.29e-01

Pos logit contributions
Animation+3.973
 +=+3.966
bj+3.923
 DAR+3.895
lections+3.836
Neg logit contributions
 Mug-4.755
iron-4.558
imus-4.465
mia-4.270
rone-4.151
Token 22
Token ID2534
Feature activation+2.45e-01

Pos logit contributions
Animation+3.443
 +=+3.399
 DAR+3.362
bj+3.359
lections+3.306
Neg logit contributions
 Mug-4.335
iron-4.161
imus-4.050
mia-3.854
rone-3.807
Token.
Token ID13
Feature activation+6.26e-01

Pos logit contributions
Animation+3.440
 +=+3.366
bj+3.312
lections+3.279
++)+3.222
Neg logit contributions
 Mug-5.092
iron-4.842
imus-4.767
rone-4.499
mia-4.420
TokenWidth
Token ID30916
Feature activation+4.48e-01

Pos logit contributions
Animation+2.688
bj+2.505
 +=+2.486
lections+2.437
CH+2.436
Neg logit contributions
 Mug-5.203
iron-5.019
imus-4.942
rone-4.664
 throat-4.613
Token),
Token ID828
Feature activation+4.32e-01

Pos logit contributions
Animation+2.329
bj+2.268
 +=+2.262
lections+2.226
 DAR+2.207
Neg logit contributions
 Mug-3.297
iron-3.156
imus-3.066
rone-2.908
mia-2.855
Token($
Token ID16763
Feature activation+2.49e-01

Pos logit contributions
Animation+2.037
bj+1.963
 +=+1.934
lections+1.924
 DAR+1.895
Neg logit contributions
 Mug-3.401
iron-3.240
imus-3.184
rone-3.009
 throat-2.969
TokenSR
Token ID12562
Feature activation+4.82e-01

Pos logit contributions
Animation+1.857
bj+1.825
lections+1.805
 +=+1.801
 DAR+1.784
Neg logit contributions
 Mug-1.286
iron-1.209
imus-1.154
rone-1.064
mia-1.035
Token.
Token ID13
Feature activation+1.07e+00

Pos logit contributions
Animation+2.509
 +=+2.457
bj+2.441
CH+2.368
lections+2.367
Neg logit contributions
 Mug-3.551
iron-3.385
imus-3.326
rone-3.145
 throat-3.095
TokenHeight
Token ID23106
Feature activation+2.01e-01

Pos logit contributions
Animation+3.501
CH+3.135
 +=+3.032
bj+2.987
++)+2.890
Neg logit contributions
 Mug-9.745
imus-9.441
iron-9.438
rone-8.961
 isol-8.953
Token)))
Token ID22305
Feature activation+4.44e-01

Pos logit contributions
Animation+1.156
bj+1.130
lections+1.115
 +=+1.114
 DAR+1.100
Neg logit contributions
 Mug-1.371
iron-1.312
imus-1.267
rone-1.193
mia-1.172
Token )
Token ID1267
Feature activation+5.42e-01

Pos logit contributions
Animation+2.558
 +=+2.500
bj+2.489
lections+2.464
 DAR+2.444
Neg logit contributions
 Mug-2.995
iron-2.888
imus-2.780
rone-2.629
mia-2.582
Token }
Token ID1782
Feature activation+2.59e-01

Pos logit contributions
Animation+3.132
 +=+3.077
bj+3.045
lections+3.014
 DAR+2.998
Neg logit contributions
 Mug-3.631
iron-3.495
imus-3.374
rone-3.171
mia-3.143
Token }
Token ID1782
Feature activation+5.53e-02

Pos logit contributions
Animation+1.422
bj+1.388
 +=+1.373
lections+1.368
 DAR+1.352
Neg logit contributions
 Mug-1.834
iron-1.761
imus-1.703
rone-1.610
mia-1.583
Token state
Token ID1181
Feature activation+7.65e-01

Pos logit contributions
 Mug+1.390
iron+1.281
imus+1.256
rone+1.117
 throat+1.115
Neg logit contributions
Animation-2.456
bj-2.452
lections-2.434
 +=-2.387
 DAR-2.375
Token (
Token ID357
Feature activation+9.00e-02

Pos logit contributions
Animation+4.278
 +=+4.173
bj+4.026
 Women+3.958
 DAR+3.956
Neg logit contributions
 Mug-5.314
iron-5.137
imus-4.920
rone-4.703
omy-4.591
Tokensuch
Token ID10508
Feature activation+4.53e-02

Pos logit contributions
Animation+0.368
bj+0.355
lections+0.350
 +=+0.347
 DAR+0.344
Neg logit contributions
 Mug-0.764
iron-0.745
imus-0.720
rone-0.685
mia-0.678
Token as
Token ID355
Feature activation-3.71e-01

Pos logit contributions
Animation+0.211
bj+0.204
lections+0.204
 +=+0.198
 DAR+0.197
Neg logit contributions
 Mug-0.361
iron-0.349
imus-0.336
rone-0.318
mia-0.318
Token through
Token ID832
Feature activation+6.95e-01

Pos logit contributions
 Mug+2.036
iron+1.933
imus+1.850
 throat+1.730
 isol+1.726
Neg logit contributions
Animation-2.531
bj-2.498
lections-2.480
 +=-2.412
ternity-2.405
Token a
Token ID257
Feature activation+1.06e+00

Pos logit contributions
Animation+3.391
bj+3.285
 +=+3.242
lections+3.220
 DAR+3.194
Neg logit contributions
 Mug-5.262
iron-5.144
imus-5.024
rone-4.760
mia-4.619
Token or
Token ID393
Feature activation+4.54e-01

Pos logit contributions
Animation+4.722
bj+4.558
lections+4.415
 +=+4.412
 DAR+4.356
Neg logit contributions
 Mug-8.369
iron-8.153
imus-7.889
mia-7.507
rone-7.504
Token )
Token ID1267
Feature activation+1.66e-01

Pos logit contributions
Animation+2.699
bj+2.641
lections+2.606
 +=+2.599
 DAR+2.571
Neg logit contributions
 Mug-3.018
iron-2.888
imus-2.785
rone-2.616
mia-2.570
Token must
Token ID1276
Feature activation+2.05e-01

Pos logit contributions
Animation+0.835
bj+0.813
 +=+0.805
lections+0.801
 DAR+0.786
Neg logit contributions
 Mug-1.256
iron-1.200
imus-1.164
rone-1.105
mia-1.087
Token not
Token ID407
Feature activation+1.10e-01

Pos logit contributions
Animation+1.248
bj+1.226
 +=+1.215
lections+1.206
 DAR+1.189
Neg logit contributions
 Mug-1.342
iron-1.275
imus-1.229
rone-1.153
mia-1.131
Token modify
Token ID13096
Feature activation-3.33e-01

Pos logit contributions
Animation+0.660
bj+0.645
lections+0.638
 +=+0.631
 DAR+0.629
Neg logit contributions
 Mug-0.720
iron-0.689
imus-0.666
rone-0.625
mia-0.614
Token Boston
Token ID6182
Feature activation+3.75e-01

Pos logit contributions
Animation+0.275
bj+0.267
lections+0.264
 +=+0.263
 DAR+0.260
Neg logit contributions
 Mug-0.385
iron-0.370
imus-0.357
rone-0.338
omy-0.332
Token (
Token ID357
Feature activation+3.89e-02

Pos logit contributions
Animation+2.245
bj+2.186
 +=+2.175
 DAR+2.154
lections+2.133
Neg logit contributions
 Mug-2.440
iron-2.363
imus-2.282
rone-2.147
 throat-2.096
Tokenpictured
Token ID28852
Feature activation+1.88e-01

Pos logit contributions
Animation+0.285
bj+0.280
lections+0.278
 +=+0.277
 DAR+0.274
Neg logit contributions
 Mug-0.205
iron-0.194
imus-0.185
rone-0.171
mia-0.167
Token),
Token ID828
Feature activation-1.38e-01

Pos logit contributions
Animation+0.895
bj+0.876
lections+0.858
 +=+0.857
 DAR+0.849
Neg logit contributions
 Mug-1.469
iron-1.413
imus-1.371
rone-1.302
mia-1.284
Token the
Token ID262
Feature activation-1.56e-01

Pos logit contributions
 Mug+0.867
iron+0.819
imus+0.783
rone+0.734
mia+0.724
Neg logit contributions
Animation-0.880
bj-0.860
lections-0.858
 +=-0.845
 DAR-0.834
Token Latin
Token ID9133
Feature activation+1.06e+00

Pos logit contributions
 Mug+1.062
iron+1.028
imus+0.981
rone+0.919
omy+0.911
Neg logit contributions
Animation-0.896
bj-0.883
lections-0.874
 +=-0.873
 DAR-0.863
Token Academy
Token ID8581
Feature activation+4.26e-01

Pos logit contributions
Animation+4.183
 DAR+4.055
 Women+3.992
 Architects+3.879
 +=+3.860
Neg logit contributions
 Mug-8.836
iron-8.729
imus-8.306
rone-8.152
ebted-7.993
Token,
Token ID11
Feature activation-4.15e-01

Pos logit contributions
Animation+2.083
bj+2.055
 +=+2.017
 DAR+2.005
 Women+1.972
Neg logit contributions
 Mug-3.227
iron-3.109
imus-3.047
rone-2.870
omy-2.828
Token some
Token ID617
Feature activation-8.22e-02

Pos logit contributions
 Mug+2.134
iron+1.940
imus+1.791
 throat+1.725
rone+1.709
Neg logit contributions
Animation-3.101
bj-3.008
lections-2.969
 +=-2.968
++)-2.935
Token areas
Token ID3006
Feature activation+2.36e-02

Pos logit contributions
 Mug+0.642
iron+0.616
imus+0.598
rone+0.572
 isol+0.570
Neg logit contributions
Animation-0.394
bj-0.380
 +=-0.369
lections-0.363
++)-0.358
Token in
Token ID287
Feature activation-1.21e-02

Pos logit contributions
Animation+0.137
bj+0.134
lections+0.132
 +=+0.132
 DAR+0.130
Neg logit contributions
 Mug-0.160
iron-0.154
imus-0.148
rone-0.139
mia-0.137
Token
Token ID851
Feature activation-2.78e-01

Pos logit contributions
 Mug+1.066
iron+1.013
imus+0.977
rone+0.912
mia+0.904
Neg logit contributions
Animation-0.967
bj-0.943
lections-0.929
 +=-0.918
 DAR-0.908
Token Old
Token ID5706
Feature activation-5.11e-01

Pos logit contributions
 Mug+1.848
iron+1.721
imus+1.658
rone+1.538
mia+1.537
Neg logit contributions
Animation-1.691
bj-1.634
lections-1.622
 +=-1.613
++)-1.573
Token Man
Token ID1869
Feature activation-2.25e-01

Pos logit contributions
 Mug+3.572
iron+3.344
imus+3.163
rone+3.026
mia+2.955
Neg logit contributions
Animation-2.862
 +=-2.796
bj-2.780
lections-2.757
++)-2.718
Token Car
Token ID1879
Feature activation-3.59e-01

Pos logit contributions
 Mug+1.522
iron+1.424
imus+1.371
rone+1.288
mia+1.266
Neg logit contributions
Animation-1.346
bj-1.307
lections-1.299
 +=-1.284
 DAR-1.257
Tokenrick
Token ID5557
Feature activation-4.94e-01

Pos logit contributions
 Mug+2.498
iron+2.426
imus+2.324
rone+2.254
omy+2.189
Neg logit contributions
Animation-2.012
bj-1.931
lections-1.922
 +=-1.902
 DAR-1.897
Token (@
Token ID4275
Feature activation-1.23e+00

Pos logit contributions
 Mug+3.226
iron+3.072
imus+2.960
rone+2.734
omy+2.692
Neg logit contributions
Animation-2.986
lections-2.884
bj-2.865
 +=-2.862
 DAR-2.803
Tokenandy
Token ID10757
Feature activation-3.77e-01

Pos logit contributions
iron+7.447
 Mug+7.045
imus+6.860
rone+6.401
mia+6.354
Neg logit contributions
 DAR-7.108
lections-6.972
 +=-6.938
Animation-6.781
 Women-6.743
Tokenf
Token ID69
Feature activation-7.58e-01

Pos logit contributions
 Mug+2.278
iron+2.247
imus+2.143
rone+2.013
mia+1.969
Neg logit contributions
Animation-2.405
lections-2.327
 DAR-2.327
bj-2.321
 +=-2.320
Tokenerv
Token ID712
Feature activation+6.48e-03

Pos logit contributions
iron+5.045
 Mug+4.886
imus+4.734
rone+4.507
omy+4.372
Neg logit contributions
Animation-4.370
 DAR-4.165
 +=-4.084
 Women-4.055
bj-4.041
Tokens
Token ID82
Feature activation-1.89e-01

Pos logit contributions
Animation+0.033
bj+0.032
 +=+0.032
lections+0.032
 DAR+0.032
Neg logit contributions
 Mug-0.048
iron-0.047
imus-0.046
rone-0.043
omy-0.042
Token)
Token ID8
Feature activation-5.92e-01

Pos logit contributions
 Mug+1.323
iron+1.294
imus+1.250
rone+1.176
mia+1.156
Neg logit contributions
Animation-1.046
bj-1.010
 +=-1.008
lections-1.006
 DAR-1.004
Token <
Token ID1279
Feature activation-5.19e-01

Pos logit contributions
 Mug+2.145
iron+2.061
imus+1.974
rone+1.856
omy+1.822
Neg logit contributions
Animation-1.771
bj-1.731
lections-1.723
 DAR-1.696
 +=-1.683
Tokenli
Token ID4528
Feature activation+6.87e-01

Pos logit contributions
 Mug+1.875
iron+1.852
imus+1.688
rone+1.514
omy+1.434
Neg logit contributions
Animation-4.481
 DAR-4.438
bj-4.403
lections-4.373
 +=-4.363
Token ng
Token ID23370
Feature activation-1.47e-02

Pos logit contributions
Animation+3.030
 +=+2.976
bj+2.920
lections+2.883
 DAR+2.817
Neg logit contributions
 Mug-5.507
iron-5.315
imus-5.180
mia-4.922
rone-4.887
Token-
Token ID12
Feature activation+3.40e-01

Pos logit contributions
 Mug+0.101
iron+0.097
imus+0.094
rone+0.088
mia+0.087
Neg logit contributions
Animation-0.083
bj-0.082
lections-0.081
 DAR-0.080
 +=-0.080
Tokenrepeat
Token ID44754
Feature activation-1.93e-01

Pos logit contributions
Animation+2.361
bj+2.328
lections+2.295
 +=+2.295
 DAR+2.250
Neg logit contributions
 Mug-1.930
iron-1.800
imus-1.728
rone-1.599
mia-1.578
Token="
Token ID2625
Feature activation-1.18e+00

Pos logit contributions
 Mug+1.655
iron+1.602
imus+1.552
rone+1.474
mia+1.463
Neg logit contributions
Animation-0.760
lections-0.754
bj-0.747
 DAR-0.726
 Women-0.698
Tokenphone
Token ID4862
Feature activation-2.93e-01

Pos logit contributions
iron+5.226
 Mug+5.001
imus+4.702
rone+4.437
mia+4.417
Neg logit contributions
 DAR-8.574
Animation-8.376
 Architects-8.366
龍喚士-8.294
lections-8.209
Token in
Token ID287
Feature activation-2.09e-01

Pos logit contributions
 Mug+1.893
iron+1.813
imus+1.734
rone+1.631
 throat+1.607
Neg logit contributions
Animation-1.765
bj-1.729
lections-1.714
 DAR-1.711
 +=-1.685
Token phones
Token ID9512
Feature activation-1.60e-01

Pos logit contributions
 Mug+1.037
iron+0.970
imus+0.918
rone+0.857
 isol+0.840
Neg logit contributions
Animation-1.588
bj-1.545
 DAR-1.529
lections-1.528
 +=-1.524
Token">
Token ID5320
Feature activation-1.48e-01

Pos logit contributions
 Mug+0.927
iron+0.883
imus+0.843
rone+0.783
mia+0.770
Neg logit contributions
Animation-1.077
bj-1.061
lections-1.047
 DAR-1.043
 +=-1.038
Token <
Token ID1279
Feature activation-6.65e-02

Pos logit contributions
 Mug+1.402
iron+1.364
imus+1.324
rone+1.272
mia+1.255
Neg logit contributions
Animation-0.455
bj-0.438
lections-0.431
 DAR-0.423
 +=-0.421
Token.
Token ID13
Feature activation-9.56e-02

Pos logit contributions
 Mug+3.626
iron+3.473
imus+3.278
mia+3.032
rone+3.016
Neg logit contributions
Animation-3.940
lections-3.938
bj-3.875
 DAR-3.795
ternity-3.793
Token Old
Token ID5706
Feature activation-2.69e-01

Pos logit contributions
 Mug+0.651
iron+0.604
imus+0.585
rone+0.545
mia+0.534
Neg logit contributions
Animation-0.567
bj-0.558
lections-0.556
 +=-0.546
 DAR-0.532
Token gift
Token ID6979
Feature activation+9.92e-02

Pos logit contributions
 Mug+1.453
iron+1.348
imus+1.290
rone+1.201
 throat+1.177
Neg logit contributions
Animation-1.942
bj-1.911
lections-1.885
 +=-1.865
 DAR-1.863
Token
Token ID1906
Feature activation+8.01e-03

Pos logit contributions
Animation+0.584
bj+0.573
lections+0.566
 +=+0.562
 DAR+0.557
Neg logit contributions
 Mug-0.666
iron-0.637
imus-0.614
rone-0.576
mia-0.566
Tokenbe
Token ID1350
Feature activation-1.35e-01

Pos logit contributions
Animation+0.032
bj+0.030
lections+0.030
 +=+0.030
 DAR+0.029
Neg logit contributions
 Mug-0.069
iron-0.067
imus-0.065
rone-0.062
mia-0.062
Tokenarer
Token ID11258
Feature activation-1.17e+00

Pos logit contributions
 Mug+0.577
iron+0.551
imus+0.520
rone+0.470
omy+0.451
Neg logit contributions
Animation-1.122
bj-1.099
 DAR-1.087
 +=-1.086
lections-1.086
Token setting
Token ID4634
Feature activation-3.83e-01

Pos logit contributions
 Mug+4.808
iron+4.531
 isol+4.092
imus+4.087
 throat+3.983
Neg logit contributions
lections-9.377
bj-9.265
Animation-8.940
ternity-8.927
++)-8.919
Token box
Token ID3091
Feature activation-9.33e-02

Pos logit contributions
 Mug+2.486
iron+2.375
imus+2.220
rone+2.136
 throat+2.125
Neg logit contributions
Animation-2.362
lections-2.316
bj-2.279
ternity-2.224
 DAR-2.217
Token underneath
Token ID14638
Feature activation-1.07e+00

Pos logit contributions
 Mug+0.699
iron+0.671
imus+0.650
rone+0.608
 throat+0.602
Neg logit contributions
Animation-0.479
lections-0.467
bj-0.467
 DAR-0.452
 +=-0.449
Token roughly
Token ID7323
Feature activation+3.23e-01

Pos logit contributions
 Mug+4.417
imus+4.043
iron+3.969
 throat+3.456
rone+3.408
Neg logit contributions
Animation-8.572
bj-8.331
lections-8.320
 DAR-8.143
ternity-7.962
Token (
Token ID357
Feature activation-1.19e-01

Pos logit contributions
Animation+2.024
bj+1.978
 +=+1.959
lections+1.953
 DAR+1.930
Neg logit contributions
 Mug-2.048
iron-1.951
imus-1.878
rone-1.763
mia-1.724
Token the
Token ID262
Feature activation-9.56e-01

Pos logit contributions
 Mug+4.767
iron+4.424
imus+4.079
rone+3.891
 throat+3.878
Neg logit contributions
Animation-5.657
 +=-5.608
bj-5.587
lections-5.524
++)-5.322
Token iceberg
Token ID34849
Feature activation-4.36e-01

Pos logit contributions
 Mug+4.635
iron+4.196
imus+3.754
 throat+3.733
rone+3.572
Neg logit contributions
Animation-7.242
lections-7.159
bj-7.127
 +=-7.090
awar-6.795
Token,"
Token ID553
Feature activation+1.70e-02

Pos logit contributions
 Mug+2.675
iron+2.520
imus+2.425
 isol+2.262
 throat+2.234
Neg logit contributions
Animation-2.764
bj-2.746
 +=-2.704
lections-2.671
 DAR-2.621
Token he
Token ID339
Feature activation+2.17e-02

Pos logit contributions
Animation+0.092
bj+0.089
lections+0.089
 +=+0.088
 DAR+0.087
Neg logit contributions
 Mug-0.123
iron-0.117
imus-0.113
rone-0.107
 throat-0.105
Token told
Token ID1297
Feature activation-4.29e-01

Pos logit contributions
Animation+0.113
bj+0.110
lections+0.109
 +=+0.108
 DAR+0.107
Neg logit contributions
 Mug-0.161
iron-0.155
imus-0.150
rone-0.141
mia-0.139
Token The
Token ID383
Feature activation-1.10e+00

Pos logit contributions
 Mug+2.557
iron+2.403
imus+2.275
rone+2.146
omy+2.108
Neg logit contributions
Animation-2.777
lections-2.724
 +=-2.719
bj-2.685
++)-2.676
Token Associated
Token ID10575
Feature activation-5.85e-01

Pos logit contributions
 Mug+6.829
iron+6.270
imus+5.743
rone+5.609
rio+5.487
Neg logit contributions
lections-6.397
ternity-6.286
Animation-6.206
bj-6.176
 +=-6.160
Token Press
Token ID4332
Feature activation-9.11e-01

Pos logit contributions
 Mug+2.657
iron+2.378
imus+2.156
rone+1.991
omy+1.966
Neg logit contributions
bj-4.662
lections-4.650
Animation-4.609
ternity-4.551
 DAR-4.524
Token in
Token ID287
Feature activation-3.20e-01

Pos logit contributions
 Mug+5.242
iron+5.240
imus+4.770
rone+4.568
 throat+4.446
Neg logit contributions
bj-5.643
Animation-5.589
++)-5.572
 DAR-5.483
lections-5.433
Token an
Token ID281
Feature activation-4.25e-01

Pos logit contributions
 Mug+2.071
iron+1.923
imus+1.825
 throat+1.740
rone+1.736
Neg logit contributions
Animation-2.010
bj-1.927
 +=-1.914
lections-1.905
++)-1.874
Token interview
Token ID2720
Feature activation-5.88e-01

Pos logit contributions
 Mug+1.832
iron+1.711
imus+1.605
rone+1.452
 throat+1.439
Neg logit contributions
Animation-3.500
bj-3.449
lections-3.417
 +=-3.410
++)-3.378
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
 Mug+2.623
iron+2.507
imus+2.372
rone+2.205
mia+2.204
Neg logit contributions
Animation-2.661
lections-2.640
bj-2.607
 DAR-2.554
ternity-2.533
Token Sw
Token ID2451
Feature activation-3.08e-01

Pos logit contributions
 Mug+1.105
iron+1.030
imus+0.990
rone+0.931
 throat+0.909
Neg logit contributions
Animation-0.952
bj-0.936
lections-0.932
 +=-0.911
 DAR-0.891
Tokenimmer
Token ID10957
Feature activation+3.09e-02

Pos logit contributions
 Mug+2.518
iron+2.490
imus+2.417
rone+2.278
mia+2.253
Neg logit contributions
Animation-1.320
bj-1.271
 DAR-1.256
 +=-1.250
lections-1.222
Token means
Token ID1724
Feature activation-6.81e-01

Pos logit contributions
Animation+0.173
bj+0.170
lections+0.168
 +=+0.166
 DAR+0.165
Neg logit contributions
 Mug-0.217
iron-0.208
imus-0.201
rone-0.189
mia-0.186
Token to
Token ID284
Feature activation-6.91e-01

Pos logit contributions
 Mug+4.268
iron+4.052
imus+3.813
 throat+3.604
rone+3.563
Neg logit contributions
Animation-4.149
bj-4.105
lections-4.045
 DAR-3.965
 +=-3.920
Token keep
Token ID1394
Feature activation-1.09e+00

Pos logit contributions
 Mug+3.847
iron+3.622
imus+3.408
 throat+3.246
 isol+3.208
Neg logit contributions
Animation-4.740
lections-4.571
bj-4.570
ternity-4.440
 DAR-4.424
Token fit
Token ID4197
Feature activation-1.02e+00

Pos logit contributions
 Mug+5.709
iron+5.527
imus+5.074
 throat+4.994
 isol+4.982
Neg logit contributions
lections-7.130
Animation-7.068
bj-7.000
 DAR-6.875
INC-6.767
Token moving
Token ID3867
Feature activation-5.55e-01

Pos logit contributions
 Mug+5.464
iron+5.111
imus+4.955
 isol+4.670
 throat+4.528
Neg logit contributions
bj-6.618
lections-6.584
Animation-6.582
 DAR-6.485
++)-6.315
Token about
Token ID546
Feature activation+4.02e-01

Pos logit contributions
 Mug+3.420
iron+3.188
imus+3.118
 throat+2.903
 isol+2.862
Neg logit contributions
Animation-3.480
bj-3.480
lections-3.371
 DAR-3.324
 +=-3.311
Token (
Token ID357
Feature activation-7.94e-02

Pos logit contributions
Animation+2.426
bj+2.354
 +=+2.348
lections+2.329
 DAR+2.302
Neg logit contributions
 Mug-2.631
iron-2.511
imus-2.416
rone-2.282
mia-2.236
Token7
Token ID22
Feature activation-1.31e-01

Pos logit contributions
 Mug+0.423
iron+0.408
imus+0.385
rone+0.356
mia+0.349
Neg logit contributions
Animation-0.571
bj-0.557
lections-0.556
 +=-0.554
 DAR-0.553
Token Europe
Token ID2031
Feature activation-4.93e-01

Pos logit contributions
Animation+1.067
bj+1.045
lections+1.033
 +=+1.031
 DAR+1.018
Neg logit contributions
 Mug-0.983
iron-0.932
imus-0.894
rone-0.835
mia-0.817
Token against
Token ID1028
Feature activation-3.01e-02

Pos logit contributions
 Mug+3.006
iron+2.878
imus+2.737
rone+2.576
 isol+2.567
Neg logit contributions
Animation-3.111
bj-3.027
 +=-3.026
lections-3.000
 DAR-2.987
Token short
Token ID1790
Feature activation-7.03e-02

Pos logit contributions
 Mug+0.203
iron+0.189
imus+0.182
rone+0.171
 throat+0.171
Neg logit contributions
Animation-0.182
bj-0.177
lections-0.174
 +=-0.174
 DAR-0.170
Token-
Token ID12
Feature activation-4.63e-01

Pos logit contributions
 Mug+0.487
iron+0.465
imus+0.442
rone+0.424
 throat+0.418
Neg logit contributions
Animation-0.400
bj-0.392
lections-0.390
 +=-0.386
 DAR-0.380
Token and
Token ID290
Feature activation-9.03e-01

Pos logit contributions
 Mug+2.978
iron+2.911
imus+2.691
rone+2.597
omy+2.501
Neg logit contributions
Animation-2.760
lections-2.716
bj-2.705
 +=-2.652
 DAR-2.624
Token medium
Token ID7090
Feature activation-1.09e+00

Pos logit contributions
 Mug+4.016
iron+3.381
imus+3.205
 throat+3.146
omy+3.053
Neg logit contributions
Animation-7.326
bj-7.113
lections-7.006
 +=-6.973
ternity-6.931
Token-
Token ID12
Feature activation-6.72e-01

Pos logit contributions
 Mug+5.497
iron+5.429
imus+4.790
 isol+4.643
rone+4.604
Neg logit contributions
Animation-7.343
lections-7.313
ternity-7.271
龍喚士-7.247
bj-7.122
Tokenrange
Token ID9521
Feature activation-4.18e-01

Pos logit contributions
 Mug+3.912
iron+3.904
imus+3.499
rone+3.458
mia+3.280
Neg logit contributions
Animation-4.308
bj-4.239
lections-4.178
 +=-4.044
 Architects-4.015
Token Iranian
Token ID10704
Feature activation+2.32e-02

Pos logit contributions
 Mug+2.631
iron+2.412
imus+2.296
 throat+2.211
rone+2.210
Neg logit contributions
Animation-2.690
bj-2.612
lections-2.535
 +=-2.534
CH-2.494
Token missiles
Token ID12798
Feature activation-3.64e-01

Pos logit contributions
Animation+0.154
bj+0.151
lections+0.149
 +=+0.148
 DAR+0.146
Neg logit contributions
 Mug-0.140
iron-0.131
imus-0.126
rone-0.119
 throat-0.116
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
 Mug+2.333
iron+2.234
imus+2.132
rone+1.971
 isol+1.963
Neg logit contributions
Animation-2.258
bj-2.171
 +=-2.154
lections-2.150
++)-2.113
Token
Token ID198
Feature activation+7.14e-02

Pos logit contributions
 Mug+0.003
iron+0.003
imus+0.003
rone+0.002
mia+0.002
Neg logit contributions
Animation-0.003
bj-0.003
lections-0.003
 +=-0.003
 DAR-0.003
Token
Token ID198
Feature activation-7.47e-02

Pos logit contributions
Animation+0.442
bj+0.433
lections+0.427
 +=+0.426
 DAR+0.422
Neg logit contributions
 Mug-0.458
iron-0.437
imus-0.421
rone-0.395
mia-0.387
TokenAdvertisement
Token ID4723
Feature activation-2.97e-01

Pos logit contributions
 Mug+0.454
iron+0.435
imus+0.414
rone+0.387
mia+0.382
Neg logit contributions
Animation-0.479
bj-0.475
lections-0.472
 +=-0.470
 DAR-0.468
Token Continue
Token ID10054
Feature activation+7.35e-02

Pos logit contributions
 Mug+1.781
iron+1.662
imus+1.611
rone+1.492
mia+1.488
Neg logit contributions
Animation-1.947
bj-1.925
lections-1.902
 DAR-1.859
 +=-1.849
Token reading
Token ID3555
Feature activation-4.33e-01

Pos logit contributions
Animation+0.475
bj+0.466
lections+0.461
 +=+0.459
 DAR+0.454
Neg logit contributions
 Mug-0.452
iron-0.430
imus-0.413
rone-0.385
mia-0.379
Token the
Token ID262
Feature activation-1.08e+00

Pos logit contributions
 Mug+2.524
iron+2.335
imus+2.236
omy+2.079
mia+2.071
Neg logit contributions
Animation-2.902
lections-2.860
bj-2.852
 +=-2.773
ternity-2.759
Token main
Token ID1388
Feature activation-4.80e-01

Pos logit contributions
 Mug+3.736
iron+3.213
imus+2.875
 throat+2.835
omy+2.804
Neg logit contributions
龍喚士-9.539
Animation-9.267
bj-9.195
ternity-9.172
lections-9.165
Token story
Token ID1621
Feature activation+3.23e-01

Pos logit contributions
 Mug+2.042
iron+1.834
imus+1.706
rone+1.611
omy+1.594
Neg logit contributions
Animation-3.987
lections-3.906
bj-3.893
 +=-3.853
龍喚士-3.846
Token
Token ID198
Feature activation-1.58e-01

Pos logit contributions
Animation+1.876
 +=+1.813
bj+1.805
 DAR+1.786
 Women+1.776
Neg logit contributions
 Mug-2.172
iron-2.107
imus-2.043
rone-1.926
 throat-1.897
Token
Token ID198
Feature activation-3.78e-01

Pos logit contributions
 Mug+0.949
iron+0.902
imus+0.860
rone+0.802
mia+0.794
Neg logit contributions
Animation-1.033
lections-1.015
bj-1.014
 +=-0.989
 DAR-0.987
TokenAlthough
Token ID7003
Feature activation-1.88e-01

Pos logit contributions
 Mug+2.351
iron+2.278
imus+2.144
Rog+2.016
rone+2.014
Neg logit contributions
bj-2.288
lections-2.287
 +=-2.283
 DAR-2.280
Animation-2.272
Token @
Token ID2488
Feature activation-9.45e-01

Pos logit contributions
Animation+0.410
bj+0.401
lections+0.395
 +=+0.392
 DAR+0.387
Neg logit contributions
 Mug-0.609
iron-0.584
imus-0.566
rone-0.536
mia-0.527
Token 144
Token ID20224
Feature activation-2.88e-01

Pos logit contributions
 Mug+5.102
iron+4.514
imus+4.371
 throat+3.931
 impedance+3.873
Neg logit contributions
bj-6.610
lections-6.495
Animation-6.453
ternity-6.390
 +=-6.152
TokenHz
Token ID7399
Feature activation+2.01e-01

Pos logit contributions
 Mug+1.249
iron+1.182
imus+1.087
mia+1.009
rone+1.007
Neg logit contributions
Animation-2.329
lections-2.300
bj-2.285
 +=-2.260
 DAR-2.258
Token (
Token ID357
Feature activation-5.57e-02

Pos logit contributions
Animation+1.273
bj+1.246
lections+1.231
 +=+1.230
 DAR+1.217
Neg logit contributions
 Mug-1.263
iron-1.206
imus-1.159
rone-1.086
mia-1.064
TokenAMA
Token ID25087
Feature activation-1.33e-01

Pos logit contributions
 Mug+0.362
iron+0.348
imus+0.335
rone+0.313
mia+0.308
Neg logit contributions
Animation-0.332
bj-0.331
lections-0.326
 +=-0.325
 DAR-0.323
Token =
Token ID796
Feature activation-1.08e+00

Pos logit contributions
 Mug+1.201
iron+1.163
imus+1.125
rone+1.081
mia+1.067
Neg logit contributions
Animation-0.467
bj-0.454
lections-0.445
 DAR-0.437
 +=-0.426
Token High
Token ID3334
Feature activation-4.86e-01

Pos logit contributions
 Mug+7.098
imus+6.282
iron+6.152
 Lime+5.827
 throat+5.641
Neg logit contributions
bj-6.010
lections-5.937
ternity-5.888
Animation-5.748
 +=-5.590
Token)
Token ID8
Feature activation-6.22e-02

Pos logit contributions
 Mug+3.392
iron+3.161
imus+3.084
rone+2.900
 isol+2.842
Neg logit contributions
Animation-2.655
bj-2.637
lections-2.613
 +=-2.555
ternity-2.506
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
 Mug+0.393
iron+0.370
imus+0.354
rone+0.330
 throat+0.325
Neg logit contributions
Animation-0.394
bj-0.389
lections-0.385
 +=-0.381
 DAR-0.375
Token
Token ID198
Feature activation+2.48e-01

Pos logit contributions
 Mug+0.715
iron+0.682
imus+0.647
rone+0.604
mia+0.597
Neg logit contributions
Animation-0.772
lections-0.759
bj-0.758
 +=-0.740
 DAR-0.738
Token23
Token ID1954
Feature activation-6.08e-01

Pos logit contributions
Animation+1.539
bj+1.500
lections+1.477
 +=+1.477
 DAR+1.456
Neg logit contributions
 Mug-1.592
iron-1.516
imus-1.465
rone-1.375
mia-1.345
Token
Token ID1906
Feature activation+8.01e-03

Pos logit contributions
Animation+0.584
bj+0.573
lections+0.566
 +=+0.562
 DAR+0.557
Neg logit contributions
 Mug-0.666
iron-0.637
imus-0.614
rone-0.576
mia-0.566
Tokenbe
Token ID1350
Feature activation-1.35e-01

Pos logit contributions
Animation+0.032
bj+0.030
lections+0.030
 +=+0.030
 DAR+0.029
Neg logit contributions
 Mug-0.069
iron-0.067
imus-0.065
rone-0.062
mia-0.062
Tokenarer
Token ID11258
Feature activation-1.17e+00

Pos logit contributions
 Mug+0.577
iron+0.551
imus+0.520
rone+0.470
omy+0.451
Neg logit contributions
Animation-1.122
bj-1.099
 DAR-1.087
 +=-1.086
lections-1.086
Token setting
Token ID4634
Feature activation-3.83e-01

Pos logit contributions
 Mug+4.808
iron+4.531
 isol+4.092
imus+4.087
 throat+3.983
Neg logit contributions
lections-9.377
bj-9.265
Animation-8.940
ternity-8.927
++)-8.919
Token box
Token ID3091
Feature activation-9.33e-02

Pos logit contributions
 Mug+2.486
iron+2.375
imus+2.220
rone+2.136
 throat+2.125
Neg logit contributions
Animation-2.362
lections-2.316
bj-2.279
ternity-2.224
 DAR-2.217
Token underneath
Token ID14638
Feature activation-1.07e+00

Pos logit contributions
 Mug+0.699
iron+0.671
imus+0.650
rone+0.608
 throat+0.602
Neg logit contributions
Animation-0.479
lections-0.467
bj-0.467
 DAR-0.452
 +=-0.449
Token roughly
Token ID7323
Feature activation+3.23e-01

Pos logit contributions
 Mug+4.417
imus+4.043
iron+3.969
 throat+3.456
rone+3.408
Neg logit contributions
Animation-8.572
bj-8.331
lections-8.320
 DAR-8.143
ternity-7.962
Token (
Token ID357
Feature activation-1.19e-01

Pos logit contributions
Animation+2.024
bj+1.978
 +=+1.959
lections+1.953
 DAR+1.930
Neg logit contributions
 Mug-2.048
iron-1.951
imus-1.878
rone-1.763
mia-1.724
Token6
Token ID21
Feature activation-4.12e-01

Pos logit contributions
 Mug+0.669
iron+0.651
imus+0.612
rone+0.576
omy+0.561
Neg logit contributions
Animation-0.820
bj-0.799
 DAR-0.794
 +=-0.793
lections-0.792
Token)
Token ID8
Feature activation-2.09e-01

Pos logit contributions
 Mug+2.927
iron+2.849
imus+2.723
rone+2.575
omy+2.558
Neg logit contributions
Animation-2.182
bj-2.126
lections-2.113
 +=-2.101
 DAR-2.084
Token C
Token ID327
Feature activation-5.30e-03

Pos logit contributions
 Mug+1.266
iron+1.160
imus+1.125
rone+1.019
 throat+1.015
Neg logit contributions
Animation-1.398
bj-1.382
lections-1.365
 +=-1.323
ternity-1.318
Token MP
Token ID4904
Feature activation+5.33e-01

Pos logit contributions
Animation+0.701
bj+0.688
lections+0.683
 +=+0.677
 DAR+0.668
Neg logit contributions
 Mug-0.677
iron-0.628
imus-0.608
rone-0.567
mia-0.558
TokenP
Token ID47
Feature activation+3.53e-02

Pos logit contributions
Animation+2.716
bj+2.648
 +=+2.599
CH+2.559
++)+2.501
Neg logit contributions
 Mug-4.003
iron-3.802
imus-3.737
 throat-3.510
rone-3.496
Token grade
Token ID9559
Feature activation+4.06e-02

Pos logit contributions
Animation+0.331
bj+0.325
lections+0.324
 +=+0.321
 DAR+0.319
Neg logit contributions
 Mug-0.115
iron-0.105
imus-0.097
rone-0.084
mia-0.081
Token:
Token ID25
Feature activation-5.43e-01

Pos logit contributions
Animation+0.202
bj+0.197
lections+0.194
 +=+0.192
 DAR+0.190
Neg logit contributions
 Mug-0.310
iron-0.298
imus-0.289
rone-0.274
mia-0.270
Token C
Token ID327
Feature activation-4.16e-01

Pos logit contributions
 Mug+3.684
iron+3.401
imus+3.291
rone+3.158
mia+3.077
Neg logit contributions
Animation-3.207
bj-3.109
lections-3.064
ternity-2.963
 +=-2.929
Token-
Token ID12
Feature activation-1.07e+00

Pos logit contributions
 Mug+2.623
iron+2.538
imus+2.406
rone+2.273
mia+2.236
Neg logit contributions
Animation-2.562
bj-2.501
lections-2.490
 DAR-2.447
 +=-2.429
Token
Token ID198
Feature activation-4.51e-01

Pos logit contributions
 Mug+5.525
iron+5.468
imus+4.984
rone+4.828
mia+4.600
Neg logit contributions
bj-7.197
Animation-7.106
lections-7.036
 DAR-6.959
 +=-6.829
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 Mug+2.468
iron+2.337
imus+2.182
rone+2.031
mia+2.030
Neg logit contributions
lections-3.137
Animation-3.124
bj-3.084
ternity-3.038
 DAR-2.995
TokenIn
Token ID818
Feature activation-2.77e-02

Pos logit contributions
 Mug+1.279
iron+1.231
imus+1.143
mia+1.056
Rog+1.053
Neg logit contributions
Animation-1.775
 DAR-1.770
lections-1.770
bj-1.758
 +=-1.749
Token an
Token ID281
Feature activation-3.49e-01

Pos logit contributions
 Mug+0.187
iron+0.178
imus+0.171
rone+0.162
mia+0.159
Neg logit contributions
Animation-0.165
bj-0.160
lections-0.158
 +=-0.157
 DAR-0.155
Token appearance
Token ID5585
Feature activation-2.34e-02

Pos logit contributions
 Mug+1.823
iron+1.726
imus+1.646
 throat+1.495
rone+1.488
Neg logit contributions
Animation-2.568
bj-2.528
lections-2.518
 +=-2.496
++)-2.463
Token the
Token ID262
Feature activation+4.24e-01

Pos logit contributions
 Mug+0.401
iron+0.381
imus+0.367
rone+0.345
mia+0.339
Neg logit contributions
Animation-0.386
bj-0.378
lections-0.375
 +=-0.371
 DAR-0.368
Token margin
Token ID10330
Feature activation+4.54e-01

Pos logit contributions
Animation+2.991
bj+2.929
 +=+2.905
 DAR+2.880
lections+2.864
Neg logit contributions
 Mug-2.305
iron-2.206
imus-2.087
rone-1.958
omy-1.911
Token,
Token ID11
Feature activation+3.33e-01

Pos logit contributions
Animation+2.300
bj+2.234
 +=+2.200
lections+2.189
 DAR+2.167
Neg logit contributions
 Mug-3.382
iron-3.232
imus-3.151
rone-2.987
mia-2.936
Token as
Token ID355
Feature activation+1.04e-01

Pos logit contributions
Animation+1.444
bj+1.400
 +=+1.367
lections+1.364
 DAR+1.343
Neg logit contributions
 Mug-2.745
iron-2.644
imus-2.579
rone-2.465
mia-2.429
Token the
Token ID262
Feature activation-2.83e-01

Pos logit contributions
Animation+0.634
bj+0.620
lections+0.613
 +=+0.611
 DAR+0.604
Neg logit contributions
 Mug-0.680
iron-0.649
imus-0.625
rone-0.587
mia-0.576
Token dwelling
Token ID26765
Feature activation-1.06e+00

Pos logit contributions
 Mug+1.936
iron+1.835
imus+1.772
rone+1.707
mia+1.650
Neg logit contributions
Animation-1.641
bj-1.596
lections-1.567
 +=-1.557
 DAR-1.525
Token supply
Token ID5127
Feature activation-7.21e-01

Pos logit contributions
 Mug+2.238
iron+2.146
imus+1.667
rone+1.489
 impedance+1.455
Neg logit contributions
Animation-10.591
bj-10.504
lections-10.374
龍喚士-10.246
ternity-10.220
Token builds
Token ID12188
Feature activation-6.58e-02

Pos logit contributions
 Mug+4.670
iron+4.332
imus+4.112
 isol+4.083
mia+3.973
Neg logit contributions
Animation-4.252
lections-4.220
bj-4.064
龍喚士-4.000
ternity-3.996
Token over
Token ID625
Feature activation-3.23e-01

Pos logit contributions
 Mug+0.391
iron+0.371
imus+0.355
rone+0.330
mia+0.324
Neg logit contributions
Animation-0.441
bj-0.430
lections-0.429
 +=-0.423
 DAR-0.421
Token time
Token ID640
Feature activation+9.95e-02

Pos logit contributions
 Mug+2.099
iron+1.991
imus+1.896
 throat+1.795
rone+1.784
Neg logit contributions
Animation-1.967
lections-1.914
bj-1.901
 DAR-1.848
 +=-1.847
Token.
Token ID13
Feature activation+3.67e-01

Pos logit contributions
Animation+0.578
bj+0.566
lections+0.560
 +=+0.557
 DAR+0.552
Neg logit contributions
 Mug-0.675
iron-0.647
imus-0.624
rone-0.585
mia-0.575
Token =
Token ID796
Feature activation+6.44e-02

Pos logit contributions
Animation+0.851
bj+0.813
 +=+0.799
lections+0.797
 DAR+0.771
Neg logit contributions
 Mug-2.464
iron-2.386
imus-2.324
rone-2.231
mia-2.204
Token ($
Token ID7198
Feature activation+3.15e-01

Pos logit contributions
Animation+0.402
bj+0.395
lections+0.389
 +=+0.385
 DAR+0.383
Neg logit contributions
 Mug-0.412
iron-0.392
imus-0.377
rone-0.352
mia-0.346
Tokentext
Token ID5239
Feature activation+8.48e-02

Pos logit contributions
Animation+2.033
bj+1.986
lections+1.961
 +=+1.953
CH+1.919
Neg logit contributions
 Mug-1.947
iron-1.836
imus-1.771
rone-1.669
 throat-1.624
Token -
Token ID532
Feature activation-1.53e-01

Pos logit contributions
Animation+0.463
bj+0.458
lections+0.449
 DAR+0.444
 +=+0.439
Neg logit contributions
 Mug-0.603
iron-0.580
imus-0.559
rone-0.525
mia-0.520
Tokensplit
Token ID35312
Feature activation-1.60e-01

Pos logit contributions
 Mug+0.962
iron+0.934
imus+0.888
rone+0.828
omy+0.816
Neg logit contributions
Animation-0.952
bj-0.940
lections-0.928
 DAR-0.918
 +=-0.913
Token "\
Token ID37082
Feature activation-1.05e+00

Pos logit contributions
 Mug+1.266
iron+1.220
imus+1.177
rone+1.107
 throat+1.097
Neg logit contributions
Animation-0.747
bj-0.739
lections-0.727
 +=-0.704
 DAR-0.701
Tokenr
Token ID81
Feature activation-3.70e-01

Pos logit contributions
 Mug+6.725
iron+6.640
imus+6.104
rone+5.922
mia+5.854
Neg logit contributions
 DAR-5.655
bj-5.593
lections-5.510
Animation-5.495
ternity-5.265
Token
Token ID198
Feature activation-3.47e-01

Pos logit contributions
 Mug+2.190
iron+2.131
imus+1.996
rone+1.891
mia+1.868
Neg logit contributions
Animation-2.387
bj-2.386
lections-2.368
 DAR-2.295
 +=-2.261
Token
Token ID198
Feature activation-3.00e-01

Pos logit contributions
 Mug+1.953
iron+1.899
imus+1.775
rone+1.660
mia+1.645
Neg logit contributions
Animation-2.345
lections-2.322
bj-2.304
 DAR-2.270
ternity-2.244
Token")
Token ID4943
Feature activation+1.18e-01

Pos logit contributions
 Mug+1.997
iron+1.963
imus+1.874
rone+1.777
mia+1.742
Neg logit contributions
Animation-1.694
bj-1.673
 DAR-1.663
lections-1.660
 +=-1.636
Token $
Token ID720
Feature activation-4.85e-02

Pos logit contributions
Animation+0.615
bj+0.601
lections+0.591
 +=+0.582
 DAR+0.580
Neg logit contributions
 Mug-0.880
iron-0.844
imus-0.817
rone-0.773
mia-0.760
Token posted
Token ID4481
Feature activation-9.47e-03

Pos logit contributions
 Mug+0.484
iron+0.456
imus+0.441
rone+0.411
 throat+0.406
Neg logit contributions
Animation-0.451
bj-0.444
lections-0.438
 +=-0.428
 DAR-0.425
Token by
Token ID416
Feature activation-3.83e-01

Pos logit contributions
 Mug+0.071
iron+0.068
imus+0.066
rone+0.062
omy+0.061
Neg logit contributions
Animation-0.049
bj-0.048
lections-0.047
 +=-0.046
 DAR-0.046
Token Robert
Token ID5199
Feature activation-1.89e-01

Pos logit contributions
 Mug+2.630
iron+2.475
imus+2.388
 throat+2.215
rone+2.204
Neg logit contributions
Animation-2.233
bj-2.148
lections-2.145
 +=-2.115
++)-2.070
Token Math
Token ID16320
Feature activation+3.14e-01

Pos logit contributions
 Mug+1.267
iron+1.177
imus+1.134
rone+1.078
mia+1.045
Neg logit contributions
Animation-1.157
bj-1.113
lections-1.112
 +=-1.106
 DAR-1.084
Tokenis
Token ID271
Feature activation+1.61e-02

Pos logit contributions
Animation+1.911
bj+1.874
lections+1.850
 +=+1.845
 DAR+1.824
Neg logit contributions
 Mug-2.048
iron-1.952
imus-1.880
rone-1.766
mia-1.734
Token (@
Token ID4275
Feature activation-1.04e+00

Pos logit contributions
Animation+0.093
bj+0.091
lections+0.091
 +=+0.090
 DAR+0.088
Neg logit contributions
 Mug-0.110
iron-0.105
imus-0.102
rone-0.095
mia-0.094
Tokenr
Token ID81
Feature activation-5.32e-01

Pos logit contributions
iron+6.463
 Mug+6.177
imus+6.079
rone+5.867
mia+5.652
Neg logit contributions
 DAR-5.898
 +=-5.800
 Women-5.761
Animation-5.723
lections-5.674
Tokenmath
Token ID11018
Feature activation-5.97e-02

Pos logit contributions
iron+3.178
 Mug+3.162
imus+3.037
omy+2.843
mia+2.828
Neg logit contributions
Animation-3.358
 DAR-3.328
 Women-3.260
 +=-3.242
lections-3.211
Tokenis
Token ID271
Feature activation+2.16e-02

Pos logit contributions
 Mug+0.403
iron+0.401
imus+0.390
rone+0.361
omy+0.357
Neg logit contributions
Animation-0.345
 DAR-0.328
 +=-0.328
bj-0.326
lections-0.325
Token_
Token ID62
Feature activation-3.42e-01

Pos logit contributions
Animation+0.122
bj+0.118
 +=+0.117
lections+0.117
 DAR+0.116
Neg logit contributions
 Mug-0.150
iron-0.145
imus-0.140
rone-0.132
mia-0.129
Tokenthe
Token ID1169
Feature activation-2.70e-01

Pos logit contributions
 Mug+2.259
iron+2.244
imus+2.171
rone+2.026
mia+2.002
Neg logit contributions
Animation-1.994
 +=-1.920
 DAR-1.902
lections-1.896
bj-1.873
Token wild
Token ID4295
Feature activation+2.69e-01

Pos logit contributions
Animation+0.621
bj+0.608
lections+0.601
 +=+0.598
 DAR+0.589
Neg logit contributions
 Mug-0.664
iron-0.632
imus-0.609
rone-0.571
mia-0.560
Token beasts
Token ID21930
Feature activation+2.88e-01

Pos logit contributions
Animation+1.645
bj+1.612
lections+1.592
 +=+1.587
 DAR+1.566
Neg logit contributions
 Mug-1.752
iron-1.672
imus-1.609
rone-1.513
mia-1.482
Token and
Token ID290
Feature activation+8.44e-03

Pos logit contributions
Animation+1.654
bj+1.617
 +=+1.593
lections+1.592
 DAR+1.576
Neg logit contributions
 Mug-1.977
iron-1.892
imus-1.825
rone-1.724
mia-1.692
Token tearing
Token ID24447
Feature activation-1.36e-01

Pos logit contributions
Animation+0.054
bj+0.053
lections+0.053
 +=+0.052
 DAR+0.052
Neg logit contributions
 Mug-0.052
iron-0.050
imus-0.048
rone-0.044
 throat-0.044
Token them
Token ID606
Feature activation-3.74e-01

Pos logit contributions
 Mug+0.863
iron+0.816
imus+0.790
rone+0.734
 throat+0.731
Neg logit contributions
Animation-0.859
bj-0.839
lections-0.837
 +=-0.824
 DAR-0.808
Token to
Token ID284
Feature activation-1.04e+00

Pos logit contributions
 Mug+2.157
iron+2.063
imus+1.981
 throat+1.880
rone+1.824
Neg logit contributions
Animation-2.548
lections-2.487
bj-2.487
 +=-2.413
 DAR-2.388
Token shred
Token ID21163
Feature activation-2.13e-01

Pos logit contributions
 Mug+4.683
iron+4.480
 throat+4.116
imus+4.072
omy+3.798
Neg logit contributions
Animation-7.722
bj-7.604
lections-7.459
 +=-7.337
 DAR-7.290
Tokens
Token ID82
Feature activation-1.52e-01

Pos logit contributions
 Mug+1.579
iron+1.534
imus+1.473
rone+1.411
 throat+1.388
Neg logit contributions
Animation-1.095
lections-1.052
bj-1.032
 +=-1.024
 DAR-1.021
Token,
Token ID11
Feature activation+3.43e-01

Pos logit contributions
 Mug+1.023
iron+0.984
imus+0.950
rone+0.884
 throat+0.882
Neg logit contributions
Animation-0.887
bj-0.868
lections-0.867
 +=-0.848
 DAR-0.841
Token it
Token ID340
Feature activation+5.02e-01

Pos logit contributions
Animation+2.078
bj+2.031
 +=+2.005
lections+2.004
 DAR+1.986
Neg logit contributions
 Mug-2.231
iron-2.135
imus-2.058
rone-1.935
mia-1.899
Token
Token ID447
Feature activation+2.70e-01

Pos logit contributions
Animation+2.529
bj+2.463
 +=+2.421
lections+2.413
 DAR+2.379
Neg logit contributions
 Mug-3.787
iron-3.637
imus-3.518
rone-3.344
mia-3.288
Token {{
Token ID22935
Feature activation-5.89e-01

Pos logit contributions
 Mug+0.437
iron+0.414
imus+0.396
rone+0.369
mia+0.362
Neg logit contributions
Animation-0.469
bj-0.460
lections-0.455
 +=-0.450
 DAR-0.449
Token2
Token ID17
Feature activation-2.27e-01

Pos logit contributions
 Mug+3.380
iron+3.263
imus+3.006
rone+2.834
mia+2.807
Neg logit contributions
Animation-3.854
 DAR-3.784
lections-3.780
bj-3.749
 +=-3.715
Token,
Token ID11
Feature activation-2.95e-01

Pos logit contributions
 Mug+1.549
iron+1.490
imus+1.414
rone+1.339
mia+1.316
Neg logit contributions
Animation-1.305
lections-1.274
bj-1.270
 +=-1.242
 DAR-1.237
Token 6
Token ID718
Feature activation-3.14e-01

Pos logit contributions
 Mug+1.815
iron+1.710
imus+1.616
rone+1.523
omy+1.493
Neg logit contributions
Animation-1.887
bj-1.855
lections-1.854
 DAR-1.802
 +=-1.796
Token},
Token ID5512
Feature activation-1.96e-01

Pos logit contributions
 Mug+2.310
iron+2.231
imus+2.140
rone+2.019
omy+2.002
Neg logit contributions
Animation-1.614
bj-1.560
lections-1.548
 +=-1.536
 DAR-1.514
Token {{
Token ID22935
Feature activation-1.02e+00

Pos logit contributions
 Mug+1.272
iron+1.209
imus+1.162
rone+1.083
omy+1.068
Neg logit contributions
Animation-1.193
bj-1.170
lections-1.157
 +=-1.141
 DAR-1.140
Token1
Token ID16
Feature activation-2.07e-01

Pos logit contributions
 Mug+4.186
iron+4.179
imus+3.509
rone+3.422
omy+3.308
Neg logit contributions
 DAR-7.950
Animation-7.800
lections-7.734
bj-7.686
 Architects-7.643
Token,
Token ID11
Feature activation-1.08e-01

Pos logit contributions
 Mug+1.419
iron+1.363
imus+1.302
rone+1.229
mia+1.214
Neg logit contributions
Animation-1.185
lections-1.164
bj-1.153
 +=-1.126
 DAR-1.124
Token 6
Token ID718
Feature activation-1.11e-01

Pos logit contributions
 Mug+0.679
iron+0.642
imus+0.611
rone+0.575
omy+0.562
Neg logit contributions
Animation-0.687
bj-0.674
lections-0.670
 +=-0.654
 DAR-0.652
Token},
Token ID5512
Feature activation-1.25e-01

Pos logit contributions
 Mug+0.845
iron+0.815
imus+0.786
rone+0.744
omy+0.733
Neg logit contributions
Animation-0.555
bj-0.540
lections-0.534
 +=-0.530
 DAR-0.522
Token {
Token ID1391
Feature activation-6.55e-01

Pos logit contributions
 Mug+0.718
iron+0.678
imus+0.649
rone+0.599
mia+0.588
Neg logit contributions
Animation-0.858
bj-0.843
lections-0.834
 +=-0.827
 DAR-0.823
Token Sw
Token ID2451
Feature activation-3.08e-01

Pos logit contributions
 Mug+1.105
iron+1.030
imus+0.990
rone+0.931
 throat+0.909
Neg logit contributions
Animation-0.952
bj-0.936
lections-0.932
 +=-0.911
 DAR-0.891
Tokenimmer
Token ID10957
Feature activation+3.09e-02

Pos logit contributions
 Mug+2.518
iron+2.490
imus+2.417
rone+2.278
mia+2.253
Neg logit contributions
Animation-1.320
bj-1.271
 DAR-1.256
 +=-1.250
lections-1.222
Token means
Token ID1724
Feature activation-6.81e-01

Pos logit contributions
Animation+0.173
bj+0.170
lections+0.168
 +=+0.166
 DAR+0.165
Neg logit contributions
 Mug-0.217
iron-0.208
imus-0.201
rone-0.189
mia-0.186
Token to
Token ID284
Feature activation-6.91e-01

Pos logit contributions
 Mug+4.268
iron+4.052
imus+3.813
 throat+3.604
rone+3.563
Neg logit contributions
Animation-4.149
bj-4.105
lections-4.045
 DAR-3.965
 +=-3.920
Token keep
Token ID1394
Feature activation-1.09e+00

Pos logit contributions
 Mug+3.847
iron+3.622
imus+3.408
 throat+3.246
 isol+3.208
Neg logit contributions
Animation-4.740
lections-4.571
bj-4.570
ternity-4.440
 DAR-4.424
Token fit
Token ID4197
Feature activation-1.02e+00

Pos logit contributions
 Mug+5.709
iron+5.527
imus+5.074
 throat+4.994
 isol+4.982
Neg logit contributions
lections-7.130
Animation-7.068
bj-7.000
 DAR-6.875
INC-6.767
Token moving
Token ID3867
Feature activation-5.55e-01

Pos logit contributions
 Mug+5.464
iron+5.111
imus+4.955
 isol+4.670
 throat+4.528
Neg logit contributions
bj-6.618
lections-6.584
Animation-6.582
 DAR-6.485
++)-6.315
Token about
Token ID546
Feature activation+4.02e-01

Pos logit contributions
 Mug+3.420
iron+3.188
imus+3.118
 throat+2.903
 isol+2.862
Neg logit contributions
Animation-3.480
bj-3.480
lections-3.371
 DAR-3.324
 +=-3.311
Token (
Token ID357
Feature activation-7.94e-02

Pos logit contributions
Animation+2.426
bj+2.354
 +=+2.348
lections+2.329
 DAR+2.302
Neg logit contributions
 Mug-2.631
iron-2.511
imus-2.416
rone-2.282
mia-2.236
Token7
Token ID22
Feature activation-1.31e-01

Pos logit contributions
 Mug+0.423
iron+0.408
imus+0.385
rone+0.356
mia+0.349
Neg logit contributions
Animation-0.571
bj-0.557
lections-0.556
 +=-0.554
 DAR-0.553
Token)
Token ID8
Feature activation+1.25e-01

Pos logit contributions
 Mug+0.985
iron+0.954
imus+0.921
rone+0.873
omy+0.857
Neg logit contributions
Animation-0.662
bj-0.645
lections-0.637
 +=-0.634
 DAR-0.627
Token which
Token ID543
Feature activation-2.47e-01

Pos logit contributions
 Mug+4.618
iron+4.282
imus+4.083
 isol+4.057
 throat+3.950
Neg logit contributions
Animation-4.072
lections-3.975
bj-3.948
++)-3.903
龍喚士-3.857
Token would
Token ID561
Feature activation-1.93e-01

Pos logit contributions
 Mug+1.883
iron+1.746
imus+1.720
 isol+1.637
rone+1.618
Neg logit contributions
Animation-1.260
bj-1.217
lections-1.216
 +=-1.177
ternity-1.145
Token likely
Token ID1884
Feature activation-2.25e-01

Pos logit contributions
 Mug+1.169
iron+1.115
imus+1.076
rone+0.991
 throat+0.991
Neg logit contributions
Animation-1.277
bj-1.232
lections-1.225
 +=-1.202
 DAR-1.198
Token involve
Token ID6211
Feature activation-3.84e-01

Pos logit contributions
 Mug+1.305
iron+1.237
imus+1.195
 throat+1.099
rone+1.097
Neg logit contributions
Animation-1.543
bj-1.489
lections-1.482
 +=-1.452
 DAR-1.446
Token medication
Token ID14103
Feature activation-1.08e-01

Pos logit contributions
 Mug+2.386
iron+2.200
imus+2.142
 isol+2.041
 throat+2.036
Neg logit contributions
Animation-2.464
bj-2.432
lections-2.376
 +=-2.355
++)-2.301
Token;
Token ID26
Feature activation-1.02e+00

Pos logit contributions
 Mug+0.758
iron+0.718
imus+0.698
rone+0.657
mia+0.650
Neg logit contributions
Animation-0.602
bj-0.590
lections-0.582
 +=-0.570
 DAR-0.569
Token or
Token ID393
Feature activation-4.47e-01

Pos logit contributions
 Mug+6.356
iron+5.811
 isol+5.669
imus+5.502
omy+5.456
Neg logit contributions
Animation-5.834
lections-5.715
bj-5.600
龍喚士-5.592
++)-5.480
Token the
Token ID262
Feature activation-4.46e-01

Pos logit contributions
 Mug+2.778
iron+2.547
imus+2.479
 isol+2.389
rone+2.371
Neg logit contributions
Animation-2.828
bj-2.738
lections-2.727
 +=-2.663
++)-2.632
Token
Token ID564
Feature activation-1.26e-01

Pos logit contributions
 Mug+2.670
iron+2.447
imus+2.406
 isol+2.294
 throat+2.289
Neg logit contributions
Animation-2.940
bj-2.866
lections-2.839
 +=-2.757
++)-2.725
Token
Token ID246
Feature activation+8.02e-03

Pos logit contributions
 Mug+0.804
iron+0.783
imus+0.743
rone+0.698
mia+0.687
Neg logit contributions
Animation-0.773
bj-0.756
lections-0.745
 +=-0.743
 DAR-0.743
Tokentalking
Token ID48186
Feature activation-1.26e-01

Pos logit contributions
Animation+0.048
bj+0.047
lections+0.046
 +=+0.046
 DAR+0.046
Neg logit contributions
 Mug-0.053
iron-0.051
imus-0.049
rone-0.046
mia-0.045
Token"]
Token ID8973
Feature activation-9.81e-02

Pos logit contributions
Animation+0.904
bj+0.889
 +=+0.883
lections+0.874
 DAR+0.870
Neg logit contributions
 Mug-0.684
iron-0.648
imus-0.622
rone-0.572
 throat-0.559
Token [
Token ID685
Feature activation-4.41e-01

Pos logit contributions
 Mug+0.559
iron+0.523
imus+0.498
rone+0.464
mia+0.457
Neg logit contributions
Animation-0.680
bj-0.672
lections-0.670
 +=-0.652
 DAR-0.650
TokenP
Token ID47
Feature activation+3.15e-01

Pos logit contributions
 Mug+2.507
iron+2.411
mia+2.160
rone+2.091
imus+2.088
Neg logit contributions
bj-2.942
 DAR-2.932
lections-2.920
Animation-2.914
 +=-2.843
Tokenly
Token ID306
Feature activation+5.59e-01

Pos logit contributions
Animation+1.605
bj+1.548
CH+1.547
 +=+1.535
lections+1.486
Neg logit contributions
 Mug-2.351
iron-2.214
imus-2.198
rone-2.096
 throat-2.050
TokenCount
Token ID12332
Feature activation+6.53e-02

Pos logit contributions
 +=+2.393
Animation+2.293
CH+2.271
 DAR+2.260
 Women+2.228
Neg logit contributions
 Mug-4.551
iron-4.509
imus-4.457
rone-4.222
terday-4.198
Token "
Token ID366
Feature activation-1.01e+00

Pos logit contributions
Animation+0.339
bj+0.330
 +=+0.326
lections+0.324
 DAR+0.320
Neg logit contributions
 Mug-0.484
iron-0.466
imus-0.451
rone-0.426
mia-0.419
Token94
Token ID5824
Feature activation-4.56e-01

Pos logit contributions
 Mug+5.445
iron+5.233
imus+4.844
rone+4.601
Rog+4.554
Neg logit contributions
lections-6.573
Animation-6.523
bj-6.435
 DAR-6.337
ternity-6.304
Token"]
Token ID8973
Feature activation-3.41e-01

Pos logit contributions
 Mug+2.107
iron+1.986
imus+1.821
rone+1.717
mia+1.704
Neg logit contributions
Animation-3.582
bj-3.528
lections-3.494
 +=-3.434
 DAR-3.422
Token [
Token ID685
Feature activation-9.30e-01

Pos logit contributions
 Mug+1.883
iron+1.740
imus+1.636
rone+1.530
mia+1.507
Neg logit contributions
bj-2.410
Animation-2.409
lections-2.405
 +=-2.303
 DAR-2.302
TokenEvent
Token ID9237
Feature activation-2.57e-01

Pos logit contributions
 Mug+3.867
iron+3.294
Rog+2.827
rone+2.785
mia+2.768
Neg logit contributions
bj-7.696
Animation-7.510
 DAR-7.490
lections-7.372
awar-7.338
TokenDate
Token ID10430
Feature activation+2.60e-01

Pos logit contributions
 Mug+1.356
iron+1.272
imus+1.193
rone+1.112
mia+1.102
Neg logit contributions
Animation-1.855
lections-1.852
bj-1.837
 +=-1.818
 DAR-1.809
Token {
Token ID1391
Feature activation-2.57e-01

Pos logit contributions
 Mug+0.154
iron+0.148
imus+0.143
rone+0.135
mia+0.132
Neg logit contributions
Animation-0.116
bj-0.114
lections-0.113
 DAR-0.111
 +=-0.109
Token|
Token ID91
Feature activation+8.21e-02

Pos logit contributions
 Mug+1.706
iron+1.612
imus+1.540
rone+1.453
 throat+1.447
Neg logit contributions
Animation-1.520
bj-1.498
lections-1.489
 DAR-1.456
 +=-1.434
Tokeni
Token ID72
Feature activation-2.52e-01

Pos logit contributions
Animation+0.445
bj+0.434
lections+0.429
 +=+0.427
 DAR+0.422
Neg logit contributions
 Mug-0.589
iron-0.566
imus-0.546
rone-0.516
mia-0.508
Token|
Token ID91
Feature activation+2.42e-03

Pos logit contributions
 Mug+1.237
iron+1.173
imus+1.118
rone+0.999
omy+0.992
Neg logit contributions
Animation-1.935
bj-1.921
lections-1.877
 DAR-1.848
 +=-1.841
Token print
Token ID3601
Feature activation+3.30e-02

Pos logit contributions
Animation+0.015
bj+0.015
lections+0.015
 DAR+0.015
 +=+0.015
Neg logit contributions
 Mug-0.015
iron-0.014
imus-0.014
rone-0.013
mia-0.013
Token "#
Token ID25113
Feature activation-1.01e+00

Pos logit contributions
Animation+0.215
bj+0.211
lections+0.209
 +=+0.206
 DAR+0.206
Neg logit contributions
 Mug-0.201
iron-0.191
imus-0.183
rone-0.171
mia-0.168
Token{
Token ID90
Feature activation-4.09e-01

Pos logit contributions
 Mug+6.487
iron+6.390
imus+6.065
mia+5.711
rone+5.639
Neg logit contributions
Animation-5.412
bj-5.357
lections-5.288
 DAR-5.206
 Architects-5.142
Tokeni
Token ID72
Feature activation-2.95e-02

Pos logit contributions
 Mug+2.490
iron+2.425
imus+2.297
rone+2.145
mia+2.124
Neg logit contributions
Animation-2.600
bj-2.532
lections-2.515
 DAR-2.498
 +=-2.467
Token}
Token ID92
Feature activation-5.44e-01

Pos logit contributions
 Mug+0.200
iron+0.194
imus+0.185
rone+0.174
omy+0.172
Neg logit contributions
Animation-0.169
bj-0.168
lections-0.166
 DAR-0.162
 +=-0.159
Token "
Token ID366
Feature activation-4.00e-01

Pos logit contributions
 Mug+3.647
iron+3.479
imus+3.365
 isol+3.168
rone+3.146
Neg logit contributions
Animation-3.078
bj-3.013
lections-2.969
 DAR-2.929
龍喚士-2.880
Token}
Token ID92
Feature activation-4.32e-02

Pos logit contributions
 Mug+2.498
iron+2.420
imus+2.309
rone+2.160
mia+2.135
Neg logit contributions
Animation-2.477
bj-2.412
lections-2.411
 DAR-2.355
CH-2.309
Token
Token ID851
Feature activation-1.52e-01

Pos logit contributions
 Mug+1.929
iron+1.766
imus+1.688
rone+1.581
omy+1.549
Neg logit contributions
Animation-2.683
lections-2.628
bj-2.606
 +=-2.592
 DAR-2.576
Token tele
Token ID5735
Feature activation-1.53e-01

Pos logit contributions
 Mug+1.049
iron+0.981
imus+0.948
rone+0.887
mia+0.883
Neg logit contributions
Animation-0.887
bj-0.861
lections-0.855
 +=-0.851
++)-0.823
TokenS
Token ID50
Feature activation-2.00e-01

Pos logit contributions
 Mug+1.007
iron+0.980
imus+0.937
rone+0.870
mia+0.865
Neg logit contributions
Animation-0.917
bj-0.895
lections-0.885
 +=-0.884
 DAR-0.874
TokenUR
Token ID4261
Feature activation+2.40e-02

Pos logit contributions
 Mug+1.706
iron+1.695
imus+1.610
mia+1.542
omy+1.530
Neg logit contributions
Animation-0.793
lections-0.751
 +=-0.746
bj-0.743
 DAR-0.739
Token English
Token ID3594
Feature activation+3.45e-02

Pos logit contributions
Animation+0.141
bj+0.137
lections+0.135
 +=+0.135
 DAR+0.133
Neg logit contributions
 Mug-0.162
iron-0.155
imus-0.149
rone-0.140
mia-0.138
Token (@
Token ID4275
Feature activation-1.00e+00

Pos logit contributions
Animation+0.201
bj+0.197
lections+0.194
 +=+0.193
 DAR+0.191
Neg logit contributions
 Mug-0.235
iron-0.224
imus-0.217
rone-0.204
mia-0.201
Tokentel
Token ID37524
Feature activation-1.26e-02

Pos logit contributions
iron+5.731
 Mug+5.542
imus+5.405
mia+4.963
Rog+4.841
Neg logit contributions
Animation-6.244
 DAR-6.189
 +=-6.184
lections-6.092
 Architects-6.003
Tokenes
Token ID274
Feature activation-1.49e-01

Pos logit contributions
 Mug+0.086
iron+0.084
imus+0.081
rone+0.075
mia+0.075
Neg logit contributions
Animation-0.072
bj-0.070
 +=-0.069
 DAR-0.069
lections-0.069
Tokenure
Token ID495
Feature activation+3.71e-02

Pos logit contributions
 Mug+1.313
iron+1.293
imus+1.265
rone+1.194
mia+1.184
Neg logit contributions
Animation-0.552
bj-0.516
 DAR-0.509
 +=-0.508
lections-0.503
Tokenng
Token ID782
Feature activation-7.24e-02

Pos logit contributions
Animation+0.213
bj+0.208
lections+0.205
 +=+0.205
 DAR+0.203
Neg logit contributions
 Mug-0.254
iron-0.244
imus-0.235
rone-0.222
mia-0.218
Tokenlish
Token ID1836
Feature activation-6.43e-02

Pos logit contributions
 Mug+0.517
iron+0.501
imus+0.483
rone+0.457
omy+0.449
Neg logit contributions
Animation-0.393
bj-0.382
 +=-0.377
 DAR-0.376
lections-0.376
Token to
Token ID284
Feature activation+1.05e-02

Pos logit contributions
 Mug+1.007
iron+0.971
imus+0.922
rone+0.873
omy+0.856
Neg logit contributions
Animation-0.879
bj-0.857
lections-0.849
 +=-0.843
 DAR-0.835
Token open
Token ID1280
Feature activation+3.61e-01

Pos logit contributions
Animation+0.077
bj+0.075
lections+0.074
 +=+0.074
 DAR+0.073
Neg logit contributions
 Mug-0.055
iron-0.052
imus-0.050
rone-0.046
 throat-0.045
Token flights
Token ID13956
Feature activation+2.48e-01

Pos logit contributions
Animation+2.328
bj+2.280
lections+2.258
 +=+2.253
 DAR+2.220
Neg logit contributions
 Mug-2.254
iron-2.098
imus-2.050
rone-1.899
mia-1.872
Token to
Token ID284
Feature activation+4.73e-02

Pos logit contributions
Animation+1.361
bj+1.328
 +=+1.310
lections+1.300
 DAR+1.292
Neg logit contributions
 Mug-1.753
iron-1.690
imus-1.648
rone-1.550
mia-1.517
Token US
Token ID1294
Feature activation+3.86e-02

Pos logit contributions
Animation+0.295
 +=+0.288
bj+0.285
lections+0.283
++)+0.277
Neg logit contributions
 Mug-0.306
iron-0.292
imus-0.271
rone-0.261
 isol-0.259
Token on
Token ID319
Feature activation+8.26e-01

Pos logit contributions
Animation+0.243
bj+0.237
lections+0.236
 +=+0.235
 DAR+0.229
Neg logit contributions
 Mug-0.248
iron-0.236
imus-0.222
rone-0.215
omy-0.207
Token sidelines
Token ID29394
Feature activation+3.14e-01

Pos logit contributions
Animation+4.944
bj+4.844
lections+4.789
 +=+4.775
 DAR+4.750
Neg logit contributions
 Mug-5.321
iron-5.188
imus-4.981
rone-4.651
mia-4.604
Token of
Token ID286
Feature activation+5.31e-01

Pos logit contributions
Animation+1.572
bj+1.528
 +=+1.527
lections+1.501
 DAR+1.491
Neg logit contributions
 Mug-2.336
iron-2.272
imus-2.219
rone-2.094
omy-2.074
Token Trump
Token ID1301
Feature activation+5.46e-01

Pos logit contributions
 Women+2.641
 DAR+2.530
++)+2.422
Animation+2.404
CH+2.394
Neg logit contributions
 Mug-3.916
iron-3.867
imus-3.833
rone-3.697
omy-3.630
Token-
Token ID12
Feature activation+9.38e-01

Pos logit contributions
Animation+2.757
 Women+2.709
bj+2.665
lections+2.648
 DAR+2.594
Neg logit contributions
 Mug-4.001
iron-3.935
imus-3.765
rone-3.546
ebted-3.543
TokenKim
Token ID26374
Feature activation+3.41e-01

Pos logit contributions
Animation+5.290
bj+5.083
CH+4.972
 DAR+4.864
lections+4.849
Neg logit contributions
 Mug-6.360
imus-6.217
iron-5.934
 throat-5.652
mia-5.641
Token to
Token ID284
Feature activation+3.36e-01

Pos logit contributions
Animation+3.284
bj+3.197
 DAR+3.163
lections+3.160
 +=+3.156
Neg logit contributions
 Mug-3.970
iron-3.819
imus-3.686
rone-3.474
mia-3.425
Token do
Token ID466
Feature activation+4.27e-01

Pos logit contributions
Animation+1.653
bj+1.613
 +=+1.585
lections+1.582
 DAR+1.573
Neg logit contributions
 Mug-2.567
iron-2.487
imus-2.402
rone-2.272
mia-2.246
Token with
Token ID351
Feature activation+3.91e-02

Pos logit contributions
Animation+2.397
bj+2.342
 +=+2.325
 DAR+2.300
lections+2.271
Neg logit contributions
 Mug-2.940
iron-2.827
imus-2.741
rone-2.548
mia-2.545
Token electoral
Token ID13901
Feature activation+1.12e-01

Pos logit contributions
Animation+0.256
bj+0.251
 +=+0.247
lections+0.247
 DAR+0.242
Neg logit contributions
 Mug-0.240
iron-0.225
imus-0.217
rone-0.203
mia-0.199
Token politics
Token ID4819
Feature activation+2.37e-01

Pos logit contributions
Animation+0.680
bj+0.665
lections+0.658
 +=+0.655
 DAR+0.645
Neg logit contributions
 Mug-0.730
iron-0.699
imus-0.666
rone-0.631
mia-0.622
Token than
Token ID621
Feature activation+7.00e-01

Pos logit contributions
Animation+1.360
bj+1.330
lections+1.313
 +=+1.308
 DAR+1.294
Neg logit contributions
 Mug-1.624
iron-1.555
imus-1.500
rone-1.412
mia-1.389
Token it
Token ID340
Feature activation+5.12e-02

Pos logit contributions
Animation+4.120
 DAR+4.109
bj+4.093
 Women+4.006
lections+4.000
Neg logit contributions
 Mug-4.388
iron-4.335
imus-4.157
rone-3.905
mia-3.850
Token had
Token ID550
Feature activation+1.46e-03

Pos logit contributions
Animation+0.256
bj+0.248
lections+0.247
 +=+0.246
 DAR+0.240
Neg logit contributions
 Mug-0.393
iron-0.377
imus-0.365
rone-0.347
omy-0.342
Token to
Token ID284
Feature activation+1.01e-01

Pos logit contributions
Animation+0.009
bj+0.009
 +=+0.009
lections+0.009
 DAR+0.008
Neg logit contributions
 Mug-0.010
iron-0.009
imus-0.009
rone-0.008
omy-0.008
Token do
Token ID466
Feature activation-2.78e-01

Pos logit contributions
Animation+0.553
bj+0.533
lections+0.531
 +=+0.526
 DAR+0.513
Neg logit contributions
 Mug-0.729
iron-0.692
imus-0.670
rone-0.638
omy-0.625
Token with
Token ID351
Feature activation+1.59e-01

Pos logit contributions
 Mug+1.635
iron+1.515
imus+1.451
rone+1.375
omy+1.356
Neg logit contributions
Animation-1.890
bj-1.851
 +=-1.836
lections-1.823
 DAR-1.772
Token suggest
Token ID1950
Feature activation-1.36e-01

Pos logit contributions
 Mug+1.386
iron+1.299
imus+1.252
 throat+1.175
rone+1.167
Neg logit contributions
Animation-1.439
lections-1.400
bj-1.399
 +=-1.377
 DAR-1.364
Token a
Token ID257
Feature activation-1.09e-01

Pos logit contributions
 Mug+0.837
iron+0.790
imus+0.761
rone+0.710
 throat+0.704
Neg logit contributions
Animation-0.867
bj-0.858
lections-0.845
 +=-0.843
 DAR-0.838
Token few
Token ID1178
Feature activation-1.14e-02

Pos logit contributions
 Mug+0.685
iron+0.641
imus+0.612
 throat+0.579
rone+0.579
Neg logit contributions
Animation-0.689
bj-0.679
lections-0.671
 +=-0.664
 DAR-0.658
Token non
Token ID1729
Feature activation+1.13e-01

Pos logit contributions
 Mug+0.068
iron+0.064
imus+0.062
rone+0.057
 throat+0.057
Neg logit contributions
Animation-0.075
bj-0.074
lections-0.073
 +=-0.073
 DAR-0.072
Token-
Token ID12
Feature activation+2.23e-01

Pos logit contributions
Animation+0.650
bj+0.637
lections+0.627
 +=+0.627
 DAR+0.622
Neg logit contributions
 Mug-0.769
iron-0.739
imus-0.710
rone-0.670
mia-0.658
Tokentax
Token ID19290
Feature activation+8.01e-01

Pos logit contributions
Animation+1.384
bj+1.354
lections+1.338
 +=+1.333
 DAR+1.318
Neg logit contributions
 Mug-1.430
iron-1.362
imus-1.313
rone-1.231
mia-1.207
Tokening
Token ID278
Feature activation-1.12e-01

Pos logit contributions
Animation+4.543
bj+4.488
lections+4.410
 +=+4.330
 DAR+4.222
Neg logit contributions
 Mug-5.450
iron-5.136
imus-4.954
rone-4.667
 throat-4.618
Token activities
Token ID4568
Feature activation-1.87e-01

Pos logit contributions
 Mug+0.623
iron+0.576
imus+0.550
rone+0.514
 throat+0.513
Neg logit contributions
Animation-0.795
bj-0.791
lections-0.772
 +=-0.772
 DAR-0.761
Token that
Token ID326
Feature activation-1.43e-01

Pos logit contributions
 Mug+1.228
iron+1.175
imus+1.130
rone+1.050
 isol+1.047
Neg logit contributions
Animation-1.122
bj-1.093
lections-1.091
 +=-1.072
 DAR-1.067
Token the
Token ID262
Feature activation-4.30e-01

Pos logit contributions
 Mug+0.924
iron+0.867
imus+0.841
rone+0.791
 throat+0.780
Neg logit contributions
Animation-0.879
bj-0.858
lections-0.857
 +=-0.841
 DAR-0.828
Token person
Token ID1048
Feature activation-1.92e-01

Pos logit contributions
 Mug+2.382
iron+2.172
imus+2.099
rone+1.990
 throat+1.984
Neg logit contributions
Animation-2.973
bj-2.935
lections-2.918
 +=-2.862
 DAR-2.823
Token This
Token ID770
Feature activation+2.25e-02

Pos logit contributions
Animation+2.659
bj+2.606
 +=+2.568
 DAR+2.547
lections+2.541
Neg logit contributions
 Mug-2.939
iron-2.858
imus-2.748
rone-2.585
mia-2.541
Token is
Token ID318
Feature activation-4.98e-02

Pos logit contributions
Animation+0.122
bj+0.119
lections+0.119
 +=+0.117
 DAR+0.115
Neg logit contributions
 Mug-0.163
iron-0.155
imus-0.150
rone-0.142
 throat-0.140
Token also
Token ID635
Feature activation+1.22e-02

Pos logit contributions
 Mug+0.303
iron+0.288
imus+0.275
rone+0.256
mia+0.252
Neg logit contributions
Animation-0.327
bj-0.319
lections-0.317
 +=-0.316
 DAR-0.311
Token mentioned
Token ID4750
Feature activation+7.12e-02

Pos logit contributions
Animation+0.082
bj+0.080
lections+0.080
 +=+0.079
 DAR+0.078
Neg logit contributions
 Mug-0.072
iron-0.068
imus-0.066
rone-0.061
mia-0.060
Token in
Token ID287
Feature activation+4.15e-01

Pos logit contributions
Animation+0.408
bj+0.400
lections+0.395
 +=+0.393
 DAR+0.388
Neg logit contributions
 Mug-0.490
iron-0.469
imus-0.453
rone-0.426
mia-0.418
Token Sunni
Token ID18592
Feature activation+7.33e-01

Pos logit contributions
Animation+2.460
bj+2.413
lections+2.380
 +=+2.378
 DAR+2.360
Neg logit contributions
 Mug-2.725
iron-2.632
imus-2.533
rone-2.385
mia-2.341
Token Had
Token ID11161
Feature activation+1.94e-01

Pos logit contributions
Animation+3.664
bj+3.505
lections+3.501
 +=+3.491
 Women+3.445
Neg logit contributions
 Mug-5.415
iron-5.274
imus-5.105
rone-4.901
mia-4.729
Tokenith
Token ID342
Feature activation+9.18e-02

Pos logit contributions
Animation+1.244
bj+1.214
 +=+1.203
lections+1.203
 DAR+1.189
Neg logit contributions
 Mug-1.205
iron-1.159
imus-1.106
rone-1.038
mia-1.018
Token collections
Token ID17268
Feature activation+3.15e-01

Pos logit contributions
Animation+0.505
bj+0.497
 +=+0.487
lections+0.484
 DAR+0.483
Neg logit contributions
 Mug-0.652
iron-0.623
imus-0.602
rone-0.570
mia-0.562
Token:
Token ID25
Feature activation+3.25e-01

Pos logit contributions
Animation+1.705
bj+1.663
lections+1.643
 +=+1.637
 DAR+1.618
Neg logit contributions
 Mug-2.264
iron-2.174
imus-2.101
rone-1.990
mia-1.953
Token
Token ID198
Feature activation+4.38e-01

Pos logit contributions
Animation+1.961
bj+1.918
 +=+1.893
lections+1.887
 DAR+1.874
Neg logit contributions
 Mug-2.118
iron-2.037
imus-1.963
rone-1.847
mia-1.809
Token
Token ID447
Feature activation+1.07e-01

Pos logit contributions
Animation+0.031
bj+0.030
 +=+0.030
lections+0.030
 DAR+0.029
Neg logit contributions
 Mug-0.045
iron-0.044
imus-0.042
rone-0.040
 throat-0.039
Token
Token ID247
Feature activation+2.15e-01

Pos logit contributions
Animation+0.607
bj+0.595
lections+0.586
 +=+0.583
 DAR+0.581
Neg logit contributions
 Mug-0.742
iron-0.711
imus-0.684
rone-0.644
mia-0.635
Tokens
Token ID82
Feature activation+1.89e-01

Pos logit contributions
Animation+1.094
bj+1.069
lections+1.055
 +=+1.046
 DAR+1.032
Neg logit contributions
 Mug-1.612
iron-1.546
imus-1.495
rone-1.417
mia-1.393
Token point
Token ID966
Feature activation+1.66e-01

Pos logit contributions
Animation+1.352
bj+1.327
lections+1.313
 +=+1.311
 DAR+1.298
Neg logit contributions
 Mug-1.036
iron-0.980
imus-0.937
rone-0.867
mia-0.847
Token of
Token ID286
Feature activation+5.18e-01

Pos logit contributions
Animation+0.874
bj+0.852
lections+0.841
 +=+0.838
 DAR+0.827
Neg logit contributions
 Mug-1.212
iron-1.164
imus-1.125
rone-1.065
mia-1.047
Token view
Token ID1570
Feature activation+7.60e-01

Pos logit contributions
Animation+3.188
bj+3.111
lections+3.093
 +=+3.079
 DAR+3.073
Neg logit contributions
 Mug-3.293
iron-3.157
imus-3.028
rone-2.855
mia-2.794
Token)
Token ID8
Feature activation+4.38e-01

Pos logit contributions
Animation+3.308
bj+3.216
 +=+3.183
lections+3.162
++)+3.083
Neg logit contributions
 Mug-6.096
iron-5.872
imus-5.665
rone-5.468
mia-5.349
Token right
Token ID826
Feature activation+1.90e-01

Pos logit contributions
Animation+2.580
bj+2.489
 DAR+2.489
 +=+2.482
lections+2.471
Neg logit contributions
 Mug-2.878
iron-2.768
imus-2.665
rone-2.512
mia-2.496
Token-
Token ID12
Feature activation+4.06e-01

Pos logit contributions
Animation+1.059
bj+1.037
lections+1.023
 +=+1.020
 DAR+1.007
Neg logit contributions
 Mug-1.337
iron-1.282
imus-1.239
rone-1.170
omy-1.145
Tokenwing
Token ID5469
Feature activation+5.09e-01

Pos logit contributions
Animation+1.800
bj+1.743
lections+1.709
 +=+1.705
 DAR+1.683
Neg logit contributions
 Mug-3.306
iron-3.162
imus-3.092
rone-2.926
mia-2.906
Tokeners
Token ID364
Feature activation+5.13e-01

Pos logit contributions
Animation+3.122
bj+3.008
 DAR+2.993
lections+2.988
 +=+2.987
Neg logit contributions
 Mug-3.257
iron-3.120
imus-2.970
rone-2.804
mia-2.787
Token parliament
Token ID8540
Feature activation-2.88e-01

Pos logit contributions
 Mug+1.349
iron+1.276
imus+1.225
rone+1.152
 throat+1.143
Neg logit contributions
Animation-1.192
bj-1.161
lections-1.150
 +=-1.139
 DAR-1.120
Token.
Token ID13
Feature activation-2.85e-01

Pos logit contributions
 Mug+1.916
iron+1.846
imus+1.755
rone+1.669
mia+1.637
Neg logit contributions
Animation-1.686
bj-1.643
lections-1.624
 +=-1.622
 DAR-1.608
Token
Token ID447
Feature activation+1.17e-01

Pos logit contributions
 Mug+1.832
iron+1.703
imus+1.620
rone+1.534
mia+1.494
Neg logit contributions
Animation-1.759
lections-1.740
bj-1.737
 +=-1.691
 DAR-1.660
Token
Token ID251
Feature activation-1.60e-01

Pos logit contributions
Animation+0.744
bj+0.729
lections+0.723
 +=+0.719
 DAR+0.714
Neg logit contributions
 Mug-0.725
iron-0.693
imus-0.663
rone-0.621
mia-0.610
Token
Token ID198
Feature activation+5.78e-02

Pos logit contributions
 Mug+1.024
iron+0.957
imus+0.920
rone+0.865
mia+0.848
Neg logit contributions
Animation-0.993
bj-0.978
lections-0.976
 +=-0.960
 DAR-0.948
Token
Token ID198
Feature activation+1.81e-01

Pos logit contributions
Animation+0.362
bj+0.354
lections+0.351
 +=+0.349
 DAR+0.345
Neg logit contributions
 Mug-0.366
iron-0.349
imus-0.335
rone-0.314
mia-0.309
TokenRelations
Token ID47117
Feature activation-1.52e-01

Pos logit contributions
Animation+1.081
bj+1.056
lections+1.039
 +=+1.038
 DAR+1.024
Neg logit contributions
 Mug-1.209
iron-1.152
imus-1.114
rone-1.048
mia-1.026
Token between
Token ID1022
Feature activation-3.22e-02

Pos logit contributions
 Mug+0.934
iron+0.891
imus+0.857
rone+0.794
mia+0.783
Neg logit contributions
Animation-0.970
lections-0.956
bj-0.946
 DAR-0.943
 +=-0.939
Token the
Token ID262
Feature activation-1.27e-01

Pos logit contributions
 Mug+0.231
iron+0.219
imus+0.211
rone+0.200
mia+0.196
Neg logit contributions
Animation-0.177
bj-0.173
lections-0.171
 +=-0.169
 DAR-0.166
Token Catalan
Token ID31066
Feature activation+1.20e-01

Pos logit contributions
 Mug+0.851
iron+0.802
imus+0.773
rone+0.728
 throat+0.716
Neg logit contributions
Animation-0.761
bj-0.744
lections-0.737
 +=-0.731
 DAR-0.716
Token and
Token ID290
Feature activation-4.10e-01

Pos logit contributions
Animation+0.803
bj+0.789
lections+0.780
 +=+0.777
 DAR+0.768
Neg logit contributions
 Mug-0.713
iron-0.676
imus-0.647
rone-0.605
mia-0.592
Token services
Token ID2594
Feature activation+5.56e-01

Pos logit contributions
Animation+1.394
bj+1.367
lections+1.351
 +=+1.348
 DAR+1.334
Neg logit contributions
 Mug-1.292
iron-1.230
imus-1.181
rone-1.103
mia-1.081
Token of
Token ID286
Feature activation+3.13e-01

Pos logit contributions
Animation+2.695
lections+2.581
bj+2.560
 +=+2.546
 DAR+2.526
Neg logit contributions
 Mug-4.208
iron-4.120
imus-3.977
rone-3.793
mia-3.713
Token Elliot
Token ID30451
Feature activation-5.74e-02

Pos logit contributions
Animation+1.878
bj+1.834
lections+1.816
 +=+1.811
 DAR+1.799
Neg logit contributions
 Mug-2.045
iron-1.969
imus-1.895
rone-1.779
mia-1.746
Token Weinstein
Token ID22473
Feature activation+2.91e-01

Pos logit contributions
 Mug+0.364
iron+0.342
imus+0.331
rone+0.311
mia+0.305
Neg logit contributions
Animation-0.367
bj-0.355
lections-0.353
 +=-0.352
 DAR-0.347
Token,
Token ID11
Feature activation+3.33e-01

Pos logit contributions
Animation+1.578
bj+1.540
lections+1.519
 +=+1.515
 DAR+1.496
Neg logit contributions
 Mug-2.089
iron-2.004
imus-1.937
rone-1.830
mia-1.800
Token a
Token ID257
Feature activation+2.38e-01

Pos logit contributions
Animation+2.006
bj+1.964
lections+1.938
 +=+1.936
 DAR+1.925
Neg logit contributions
 Mug-2.165
iron-2.083
imus-2.006
rone-1.888
mia-1.852
Token well
Token ID880
Feature activation+2.22e-01

Pos logit contributions
Animation+1.501
bj+1.470
lections+1.453
 +=+1.451
 DAR+1.439
Neg logit contributions
 Mug-1.494
iron-1.430
imus-1.373
rone-1.286
mia-1.261
Token-
Token ID12
Feature activation-8.23e-02

Pos logit contributions
Animation+1.349
bj+1.321
lections+1.304
 +=+1.301
 DAR+1.287
Neg logit contributions
 Mug-1.447
iron-1.382
imus-1.331
rone-1.249
mia-1.227
Tokenknown
Token ID4002
Feature activation+2.17e-01

Pos logit contributions
 Mug+0.500
iron+0.485
imus+0.458
rone+0.430
mia+0.421
Neg logit contributions
Animation-0.537
lections-0.521
bj-0.521
 +=-0.520
 DAR-0.511
Token defense
Token ID3761
Feature activation+2.70e-01

Pos logit contributions
Animation+1.408
bj+1.380
lections+1.364
 +=+1.361
 DAR+1.348
Neg logit contributions
 Mug-1.329
iron-1.267
imus-1.216
rone-1.137
mia-1.114
Token lawyer
Token ID6853
Feature activation+5.68e-01

Pos logit contributions
Animation+1.897
bj+1.865
lections+1.846
 +=+1.840
 DAR+1.820
Neg logit contributions
 Mug-1.511
iron-1.429
imus-1.368
rone-1.269
mia-1.238
Token say
Token ID910
Feature activation+2.73e-01

Pos logit contributions
Animation+0.293
bj+0.286
lections+0.283
 +=+0.280
 DAR+0.278
Neg logit contributions
 Mug-0.330
iron-0.315
imus-0.303
rone-0.285
mia-0.281
Token it
Token ID340
Feature activation+1.52e-01

Pos logit contributions
Animation+1.716
bj+1.677
 +=+1.661
lections+1.658
 DAR+1.646
Neg logit contributions
 Mug-1.715
iron-1.634
imus-1.579
rone-1.472
mia-1.449
Token's
Token ID338
Feature activation+3.59e-01

Pos logit contributions
Animation+0.724
bj+0.704
lections+0.693
 +=+0.691
 DAR+0.681
Neg logit contributions
 Mug-1.195
iron-1.150
imus-1.116
rone-1.060
mia-1.044
Token a
Token ID257
Feature activation+3.32e-01

Pos logit contributions
Animation+2.097
 +=+2.051
bj+2.043
lections+2.030
 DAR+2.023
Neg logit contributions
 Mug-2.372
iron-2.281
imus-2.198
rone-2.082
mia-2.039
Token circle
Token ID9197
Feature activation+6.90e-02

Pos logit contributions
Animation+2.189
bj+2.152
 +=+2.151
 DAR+2.131
lections+2.123
Neg logit contributions
 Mug-1.958
iron-1.876
imus-1.805
rone-1.667
mia-1.649
Token.
Token ID13
Feature activation+6.22e-02

Pos logit contributions
Animation+0.401
bj+0.393
lections+0.388
 +=+0.386
 DAR+0.382
Neg logit contributions
 Mug-0.468
iron-0.449
imus-0.432
rone-0.407
mia-0.400
Token So
Token ID1406
Feature activation+6.34e-02

Pos logit contributions
Animation+0.376
bj+0.371
lections+0.369
 +=+0.361
 DAR+0.356
Neg logit contributions
 Mug-0.409
iron-0.387
imus-0.371
rone-0.351
omy-0.341
Token,
Token ID11
Feature activation+2.47e-01

Pos logit contributions
Animation+0.384
bj+0.377
lections+0.372
 +=+0.369
 DAR+0.364
Neg logit contributions
 Mug-0.416
iron-0.399
imus-0.381
rone-0.360
mia-0.352
Token Earth
Token ID3668
Feature activation+5.86e-02

Pos logit contributions
Animation+1.456
bj+1.423
 +=+1.406
lections+1.405
 DAR+1.390
Neg logit contributions
 Mug-1.656
iron-1.583
imus-1.530
rone-1.437
mia-1.414
Token's
Token ID338
Feature activation-8.71e-03

Pos logit contributions
Animation+0.301
bj+0.295
lections+0.292
 +=+0.287
 DAR+0.285
Neg logit contributions
 Mug-0.436
iron-0.421
imus-0.406
rone-0.384
mia-0.378
Token orbit
Token ID13066
Feature activation-3.13e-04

Pos logit contributions
 Mug+0.052
iron+0.050
imus+0.048
rone+0.045
 throat+0.044
Neg logit contributions
Animation-0.057
bj-0.057
lections-0.056
 +=-0.055
 DAR-0.055
Token more
Token ID517
Feature activation-1.26e-01

Pos logit contributions
 Mug+0.714
iron+0.679
imus+0.649
 isol+0.603
rone+0.600
Neg logit contributions
Animation-0.782
bj-0.766
lections-0.757
 +=-0.753
 DAR-0.737
Token commun
Token ID1316
Feature activation-1.54e-01

Pos logit contributions
 Mug+0.704
iron+0.667
imus+0.633
 isol+0.583
rone+0.583
Neg logit contributions
Animation-0.895
bj-0.878
lections-0.866
 +=-0.861
 DAR-0.847
Tokenicative
Token ID43058
Feature activation+3.77e-02

Pos logit contributions
 Mug+0.937
iron+0.910
imus+0.867
rone+0.814
omy+0.796
Neg logit contributions
Animation-1.006
bj-0.983
 +=-0.972
lections-0.968
 DAR-0.963
Token.
Token ID13
Feature activation-2.71e-02

Pos logit contributions
Animation+0.216
bj+0.212
lections+0.209
 +=+0.207
 DAR+0.205
Neg logit contributions
 Mug-0.260
iron-0.249
imus-0.240
rone-0.226
 throat-0.222
Token But
Token ID887
Feature activation-4.66e-02

Pos logit contributions
 Mug+0.175
iron+0.164
imus+0.158
rone+0.148
mia+0.144
Neg logit contributions
Animation-0.168
lections-0.165
bj-0.165
 +=-0.161
 DAR-0.157
Token it
Token ID340
Feature activation+9.44e-02

Pos logit contributions
 Mug+0.290
iron+0.274
imus+0.263
rone+0.247
 isol+0.242
Neg logit contributions
Animation-0.299
bj-0.294
lections-0.291
 +=-0.288
 DAR-0.283
Token was
Token ID373
Feature activation-8.20e-02

Pos logit contributions
Animation+0.456
bj+0.441
lections+0.439
 +=+0.432
 DAR+0.428
Neg logit contributions
 Mug-0.734
iron-0.708
imus-0.687
rone-0.651
 isol-0.644
Token so
Token ID523
Feature activation-3.03e-01

Pos logit contributions
 Mug+0.479
iron+0.453
imus+0.430
rone+0.402
 isol+0.398
Neg logit contributions
Animation-0.558
bj-0.546
lections-0.541
 +=-0.538
 DAR-0.529
Token baff
Token ID25989
Feature activation-9.67e-02

Pos logit contributions
 Mug+1.675
iron+1.606
imus+1.494
 isol+1.417
rone+1.396
Neg logit contributions
Animation-2.130
lections-2.076
bj-2.074
 +=-2.051
 DAR-2.013
Tokenling
Token ID1359
Feature activation-1.77e-01

Pos logit contributions
 Mug+0.614
iron+0.596
imus+0.564
rone+0.533
omy+0.523
Neg logit contributions
Animation-0.605
bj-0.590
 +=-0.582
lections-0.579
 DAR-0.578
Token to
Token ID284
Feature activation-2.22e-01

Pos logit contributions
 Mug+1.141
iron+1.095
imus+1.050
 isol+0.977
rone+0.975
Neg logit contributions
Animation-1.084
bj-1.065
lections-1.058
 +=-1.049
 DAR-1.034
Token recognize
Token ID7564
Feature activation-1.93e-01

Pos logit contributions
 Mug+1.230
iron+1.179
imus+1.115
rone+1.047
 throat+1.025
Neg logit contributions
Animation-1.507
bj-1.464
lections-1.439
 +=-1.414
 DAR-1.413
Token that
Token ID326
Feature activation+4.86e-02

Pos logit contributions
 Mug+1.195
iron+1.129
imus+1.079
rone+1.013
mia+0.997
Neg logit contributions
Animation-1.251
bj-1.222
 +=-1.208
lections-1.206
 DAR-1.183
Token his
Token ID465
Feature activation-6.81e-02

Pos logit contributions
Animation+0.295
bj+0.288
lections+0.284
 +=+0.284
 DAR+0.280
Neg logit contributions
 Mug-0.319
iron-0.304
imus-0.292
rone-0.275
mia-0.270
Token campaign
Token ID1923
Feature activation+1.78e-01

Pos logit contributions
 Mug+0.397
iron+0.376
imus+0.359
rone+0.336
 throat+0.329
Neg logit contributions
Animation-0.463
bj-0.454
lections-0.449
 +=-0.448
 DAR-0.441
Token often
Token ID1690
Feature activation-9.23e-02

Pos logit contributions
Animation+1.012
bj+0.993
lections+0.980
 +=+0.976
 DAR+0.963
Neg logit contributions
 Mug-1.236
iron-1.183
imus-1.141
rone-1.077
mia-1.059
Token ve
Token ID1569
Feature activation+2.21e-01

Pos logit contributions
 Mug+0.623
iron+0.596
imus+0.575
rone+0.538
 isol+0.536
Neg logit contributions
Animation-0.544
bj-0.531
lections-0.525
 +=-0.520
 DAR-0.511
Tokenered
Token ID1068
Feature activation+1.84e-02

Pos logit contributions
Animation+1.288
bj+1.257
lections+1.240
 +=+1.239
 DAR+1.225
Neg logit contributions
 Mug-1.501
iron-1.438
imus-1.387
rone-1.306
mia-1.282
Token off
Token ID572
Feature activation+2.13e-01

Pos logit contributions
Animation+0.120
bj+0.118
lections+0.117
 +=+0.116
 DAR+0.115
Neg logit contributions
 Mug-0.112
iron-0.107
imus-0.102
rone-0.095
mia-0.093
Token-
Token ID12
Feature activation+2.27e-01

Pos logit contributions
Animation+1.295
bj+1.267
lections+1.251
 +=+1.248
 DAR+1.235
Neg logit contributions
 Mug-1.388
iron-1.325
imus-1.277
rone-1.199
mia-1.178
Tokenroad
Token ID6344
Feature activation+1.69e-01

Pos logit contributions
Animation+1.484
bj+1.453
lections+1.435
 +=+1.431
 DAR+1.415
Neg logit contributions
 Mug-1.383
iron-1.307
imus-1.263
rone-1.176
mia-1.157
Token and
Token ID290
Feature activation+1.03e-01

Pos logit contributions
Animation+0.956
bj+0.934
lections+0.922
 +=+0.920
 DAR+0.909
Neg logit contributions
 Mug-1.174
iron-1.128
imus-1.087
rone-1.025
mia-1.007
Token |
Token ID930
Feature activation+1.45e-01

Pos logit contributions
Animation+1.273
bj+1.246
lections+1.230
 +=+1.230
 DAR+1.216
Neg logit contributions
 Mug-1.312
iron-1.254
imus-1.206
rone-1.132
mia-1.109
Tokenaut
Token ID2306
Feature activation-2.58e-02

Pos logit contributions
Animation+0.744
bj+0.726
lections+0.716
 +=+0.713
 DAR+0.704
Neg logit contributions
 Mug-1.080
iron-1.038
imus-1.004
rone-0.950
mia-0.937
Tokenoc
Token ID420
Feature activation+1.81e-01

Pos logit contributions
 Mug+0.130
iron+0.125
imus+0.119
rone+0.109
omy+0.108
Neg logit contributions
Animation-0.194
bj-0.191
 DAR-0.189
lections-0.188
 +=-0.187
Tokenomm
Token ID2002
Feature activation+1.07e-01

Pos logit contributions
Animation+1.289
bj+1.261
lections+1.248
 +=+1.240
 DAR+1.239
Neg logit contributions
 Mug-0.988
iron-0.945
imus-0.903
rone-0.836
mia-0.817
Tokenand
Token ID392
Feature activation+1.08e-01

Pos logit contributions
Animation+0.703
bj+0.689
lections+0.681
 +=+0.678
 DAR+0.673
Neg logit contributions
 Mug-0.644
iron-0.612
imus-0.588
rone-0.549
mia-0.538
Token|
Token ID91
Feature activation+4.64e-02

Pos logit contributions
Animation+0.758
bj+0.747
lections+0.738
 +=+0.735
 DAR+0.732
Neg logit contributions
 Mug-0.597
iron-0.567
imus-0.543
rone-0.502
mia-0.492
Token.
Token ID13
Feature activation-5.44e-01

Pos logit contributions
Animation+0.254
bj+0.248
lections+0.246
 +=+0.244
 DAR+0.242
Neg logit contributions
 Mug-0.329
iron-0.317
imus-0.306
rone-0.288
mia-0.284
Token 3
Token ID513
Feature activation+2.83e-01

Pos logit contributions
 Mug+3.332
iron+3.038
imus+2.920
rone+2.724
 throat+2.708
Neg logit contributions
lections-3.461
Animation-3.455
bj-3.432
ternity-3.339
 +=-3.293
Token.
Token ID13
Feature activation+2.99e-01

Pos logit contributions
Animation+1.574
bj+1.534
 +=+1.523
lections+1.504
 DAR+1.494
Neg logit contributions
 Mug-1.990
iron-1.914
imus-1.853
rone-1.750
mia-1.718
Token If
Token ID1002
Feature activation-1.35e-01

Pos logit contributions
Animation+1.673
bj+1.633
 +=+1.611
lections+1.610
 DAR+1.590
Neg logit contributions
 Mug-2.086
iron-2.004
imus-1.936
rone-1.827
mia-1.795
Token you
Token ID345
Feature activation+1.14e-02

Pos logit contributions
 Mug+0.751
iron+0.696
imus+0.670
rone+0.614
mia+0.609
Neg logit contributions
Animation-0.958
bj-0.943
lections-0.931
 +=-0.920
 DAR-0.910
TokenC
Token ID34
Feature activation-1.85e-02

Pos logit contributions
Animation+0.992
bj+0.971
lections+0.959
 +=+0.957
 DAR+0.947
Neg logit contributions
 Mug-1.102
iron-1.054
imus-1.015
rone-0.955
mia-0.938
Tokenultural
Token ID8596
Feature activation-3.77e-01

Pos logit contributions
 Mug+0.134
iron+0.130
imus+0.125
rone+0.119
mia+0.117
Neg logit contributions
Animation-0.098
bj-0.096
 +=-0.094
 DAR-0.094
lections-0.094
Token and
Token ID290
Feature activation-5.51e-01

Pos logit contributions
 Mug+2.443
iron+2.236
imus+2.126
 isol+2.060
rone+2.030
Neg logit contributions
bj-2.333
Animation-2.324
 +=-2.245
lections-2.219
 DAR-2.209
Token educational
Token ID9856
Feature activation-5.40e-01

Pos logit contributions
 Mug+3.197
iron+2.839
imus+2.723
 isol+2.596
omy+2.571
Neg logit contributions
Animation-3.744
bj-3.692
lections-3.656
 +=-3.583
++)-3.577
Token representations
Token ID24612
Feature activation-7.07e-02

Pos logit contributions
 Mug+3.217
iron+2.899
imus+2.733
 isol+2.722
 ostr+2.622
Neg logit contributions
bj-3.584
Animation-3.583
lections-3.435
 +=-3.429
++)-3.428
Token continue
Token ID2555
Feature activation-1.27e-01

Pos logit contributions
 Mug+0.484
iron+0.459
imus+0.441
rone+0.414
 isol+0.412
Neg logit contributions
Animation-0.410
bj-0.403
lections-0.394
 +=-0.391
 DAR-0.387
Token to
Token ID284
Feature activation-1.89e-01

Pos logit contributions
 Mug+0.851
iron+0.816
imus+0.780
rone+0.728
mia+0.727
Neg logit contributions
Animation-0.740
bj-0.734
 +=-0.715
lections-0.714
 DAR-0.712
Token perpetuate
Token ID43874
Feature activation-4.15e-01

Pos logit contributions
 Mug+1.132
iron+1.071
imus+1.027
 throat+0.958
 isol+0.957
Neg logit contributions
Animation-1.258
bj-1.225
lections-1.208
 +=-1.185
 DAR-1.184
Token negative
Token ID4633
Feature activation-3.91e-01

Pos logit contributions
 Mug+2.337
iron+2.144
imus+2.008
 isol+1.948
rone+1.876
Neg logit contributions
Animation-2.957
bj-2.903
 +=-2.849
lections-2.819
++)-2.816
Token stereotypes
Token ID22364
Feature activation-4.34e-01

Pos logit contributions
 Mug+1.810
iron+1.635
imus+1.520
 isol+1.436
rone+1.399
Neg logit contributions
Animation-3.160
bj-3.135
 +=-3.050
lections-3.038
++)-3.021
Token
Token ID198
Feature activation-6.06e-02

Pos logit contributions
 Mug+2.851
iron+2.684
imus+2.545
 isol+2.428
mia+2.403
Neg logit contributions
bj-2.577
Animation-2.575
 +=-2.512
lections-2.475
 DAR-2.467
Token test
Token ID1332
Feature activation-1.47e-01

Pos logit contributions
Animation+0.987
bj+0.969
 +=+0.959
lections+0.958
 DAR+0.952
Neg logit contributions
 Mug-0.834
iron-0.793
imus-0.760
rone-0.709
mia-0.692
Token methods
Token ID5050
Feature activation-2.04e-01

Pos logit contributions
 Mug+0.968
iron+0.908
imus+0.886
rone+0.823
 isol+0.818
Neg logit contributions
Animation-0.896
bj-0.873
lections-0.868
 +=-0.861
++)-0.831
Token to
Token ID284
Feature activation-3.37e-01

Pos logit contributions
 Mug+1.340
iron+1.261
imus+1.230
rone+1.132
 isol+1.128
Neg logit contributions
Animation-1.236
 +=-1.195
lections-1.195
bj-1.194
++)-1.157
Token measure
Token ID3953
Feature activation-1.24e-01

Pos logit contributions
 Mug+1.848
iron+1.733
imus+1.651
 isol+1.533
 throat+1.515
Neg logit contributions
Animation-2.423
bj-2.364
lections-2.347
 +=-2.303
CH-2.266
Token weak
Token ID4939
Feature activation-1.12e-02

Pos logit contributions
 Mug+0.858
iron+0.813
imus+0.791
rone+0.741
 throat+0.731
Neg logit contributions
Animation-0.715
bj-0.698
lections-0.689
 +=-0.681
 DAR-0.664
Token gravitational
Token ID29973
Feature activation+3.38e-03

Pos logit contributions
 Mug+0.078
iron+0.075
imus+0.072
rone+0.068
 throat+0.067
Neg logit contributions
Animation-0.064
bj-0.063
 +=-0.061
lections-0.061
 DAR-0.060
Token lens
Token ID10317
Feature activation-3.13e-03

Pos logit contributions
Animation+0.017
bj+0.016
 +=+0.016
lections+0.016
++)+0.015
Neg logit contributions
 Mug-0.026
iron-0.025
imus-0.024
 throat-0.023
 isol-0.023
Tokening
Token ID278
Feature activation-1.72e-01

Pos logit contributions
 Mug+0.021
iron+0.020
imus+0.020
rone+0.018
omy+0.018
Neg logit contributions
Animation-0.018
bj-0.018
 +=-0.018
lections-0.017
 DAR-0.017
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
 Mug+1.123
iron+1.069
imus+1.043
rone+0.974
 isol+0.963
Neg logit contributions
Animation-1.033
bj-1.016
 +=-0.997
lections-0.993
 DAR-0.975
Token another
Token ID1194
Feature activation+2.09e-01

Pos logit contributions
 Mug+1.304
iron+1.240
imus+1.183
 isol+1.116
rone+1.114
Neg logit contributions
Animation-1.163
bj-1.131
 +=-1.124
lections-1.122
++)-1.087
Token way
Token ID835
Feature activation+1.55e-01

Pos logit contributions
Animation+1.389
bj+1.362
lections+1.347
 +=+1.344
 DAR+1.329
Neg logit contributions
 Mug-1.249
iron-1.187
imus-1.139
rone-1.062
mia-1.040
Token Forum
Token ID14867
Feature activation+2.12e-02

Pos logit contributions
Animation+0.136
bj+0.132
 +=+0.130
lections+0.129
 DAR+0.127
Neg logit contributions
 Mug-0.244
iron-0.233
imus-0.227
rone-0.215
omy-0.211
Token at
Token ID379
Feature activation-9.45e-03

Pos logit contributions
Animation+0.115
bj+0.112
lections+0.110
 +=+0.110
 DAR+0.109
Neg logit contributions
 Mug-0.153
iron-0.147
imus-0.142
rone-0.134
mia-0.132
Token Newcastle
Token ID22410
Feature activation-7.03e-02

Pos logit contributions
 Mug+0.058
iron+0.055
imus+0.053
rone+0.050
mia+0.048
Neg logit contributions
Animation-0.062
bj-0.060
lections-0.060
 +=-0.060
 DAR-0.058
Token United
Token ID1578
Feature activation+1.08e-01

Pos logit contributions
 Mug+0.501
iron+0.478
imus+0.460
rone+0.434
mia+0.425
Neg logit contributions
Animation-0.389
bj-0.382
 +=-0.374
lections-0.373
 DAR-0.368
Token will
Token ID481
Feature activation-3.49e-01

Pos logit contributions
Animation+0.591
bj+0.577
lections+0.569
 +=+0.567
 DAR+0.560
Neg logit contributions
 Mug-0.778
iron-0.744
imus-0.720
rone-0.680
mia-0.668
Token be
Token ID307
Feature activation-3.54e-01

Pos logit contributions
 Mug+2.070
iron+1.999
imus+1.913
rone+1.787
 throat+1.773
Neg logit contributions
Animation-2.334
bj-2.231
lections-2.217
 DAR-2.182
 +=-2.176
Token required
Token ID2672
Feature activation-1.45e-01

Pos logit contributions
 Mug+2.068
iron+1.933
imus+1.865
rone+1.718
 throat+1.715
Neg logit contributions
Animation-2.423
bj-2.367
lections-2.338
 +=-2.325
 DAR-2.284
Token to
Token ID284
Feature activation+3.63e-02

Pos logit contributions
 Mug+0.986
iron+0.945
imus+0.910
rone+0.860
mia+0.840
Neg logit contributions
Animation-0.830
bj-0.818
 +=-0.802
lections-0.799
 DAR-0.795
Token select
Token ID2922
Feature activation+7.49e-02

Pos logit contributions
Animation+0.234
bj+0.229
lections+0.227
 +=+0.226
 DAR+0.223
Neg logit contributions
 Mug-0.224
iron-0.213
imus-0.205
rone-0.191
mia-0.188
Token an
Token ID281
Feature activation+1.57e-01

Pos logit contributions
Animation+0.439
bj+0.430
lections+0.424
 +=+0.423
 DAR+0.417
Neg logit contributions
 Mug-0.509
iron-0.484
imus-0.467
rone-0.441
mia-0.431
Token individual
Token ID1981
Feature activation+7.03e-03

Pos logit contributions
Animation+1.083
bj+1.060
lections+1.049
 +=+1.048
 DAR+1.039
Neg logit contributions
 Mug-0.889
iron-0.847
imus-0.809
rone-0.753
mia-0.739
Tokenation
Token ID341
Feature activation-2.42e-01

Pos logit contributions
 Mug+1.762
iron+1.697
imus+1.615
rone+1.489
omy+1.479
Neg logit contributions
Animation-2.376
lections-2.319
bj-2.317
 DAR-2.309
 +=-2.298
Token might
Token ID1244
Feature activation+8.63e-02

Pos logit contributions
 Mug+1.411
iron+1.330
imus+1.258
 throat+1.194
 isol+1.192
Neg logit contributions
Animation-1.611
lections-1.610
bj-1.599
 +=-1.549
 DAR-1.537
Token have
Token ID423
Feature activation-1.26e-01

Pos logit contributions
Animation+0.534
bj+0.520
lections+0.515
 +=+0.510
 DAR+0.506
Neg logit contributions
 Mug-0.556
iron-0.532
imus-0.511
rone-0.479
 throat-0.471
Token been
Token ID587
Feature activation-1.93e-01

Pos logit contributions
 Mug+0.772
iron+0.729
imus+0.698
 throat+0.649
rone+0.647
Neg logit contributions
Animation-0.823
bj-0.807
lections-0.801
 +=-0.789
 DAR-0.776
Token a
Token ID257
Feature activation+1.80e-02

Pos logit contributions
 Mug+1.134
iron+1.085
imus+1.021
 isol+0.958
rone+0.948
Neg logit contributions
Animation-1.295
bj-1.266
 +=-1.262
lections-1.261
 DAR-1.232
Token
Token ID564
Feature activation-1.40e-01

Pos logit contributions
Animation+0.125
bj+0.122
lections+0.122
 +=+0.121
 DAR+0.119
Neg logit contributions
 Mug-0.103
iron-0.096
imus-0.092
rone-0.086
 throat-0.085
Token
Token ID250
Feature activation-7.64e-02

Pos logit contributions
 Mug+0.772
iron+0.746
imus+0.705
rone+0.652
mia+0.645
Neg logit contributions
Animation-0.981
bj-0.961
lections-0.958
 DAR-0.946
 +=-0.945
Tokenblack
Token ID13424
Feature activation+3.33e-01

Pos logit contributions
 Mug+0.509
iron+0.502
imus+0.475
rone+0.448
mia+0.443
Neg logit contributions
Animation-0.446
bj-0.434
 +=-0.433
lections-0.433
 DAR-0.431
Token ace
Token ID31506
Feature activation+9.81e-02

Pos logit contributions
Animation+2.307
bj+2.264
lections+2.238
 +=+2.237
 DAR+2.214
Neg logit contributions
 Mug-1.882
iron-1.781
imus-1.711
rone-1.585
mia-1.552
Token
Token ID447
Feature activation-8.37e-02

Pos logit contributions
Animation+0.518
bj+0.506
lections+0.501
 +=+0.497
 DAR+0.492
Neg logit contributions
 Mug-0.716
iron-0.692
imus-0.670
rone-0.632
mia-0.624
Token
Token ID251
Feature activation-6.14e-02

Pos logit contributions
 Mug+0.469
iron+0.452
imus+0.427
rone+0.397
omy+0.394
Neg logit contributions
Animation-0.580
bj-0.567
lections-0.565
 +=-0.561
 DAR-0.561
Token--+
Token ID44785
Feature activation-1.39e-01

Pos logit contributions
 Mug+0.497
iron+0.481
imus+0.461
rone+0.434
mia+0.426
Neg logit contributions
Animation-0.429
bj-0.417
lections-0.416
 DAR-0.405
 +=-0.402
Token |
Token ID930
Feature activation+2.40e-01

Pos logit contributions
 Mug+0.706
iron+0.661
imus+0.624
rone+0.572
mia+0.562
Neg logit contributions
Animation-1.042
lections-1.030
bj-1.028
 DAR-0.998
ternity-0.992
Token [
Token ID685
Feature activation-1.47e-01

Pos logit contributions
Animation+1.569
bj+1.532
 +=+1.526
lections+1.510
 DAR+1.504
Neg logit contributions
 Mug-1.448
iron-1.385
imus-1.326
rone-1.242
mia-1.215
Tokenaddress
Token ID21975
Feature activation-3.39e-01

Pos logit contributions
 Mug+0.760
iron+0.736
imus+0.690
rone+0.638
mia+0.630
Neg logit contributions
Animation-1.083
bj-1.051
lections-1.047
 +=-1.038
 DAR-1.036
Token of
Token ID286
Feature activation-7.22e-01

Pos logit contributions
 Mug+2.215
iron+2.120
imus+2.013
rone+1.888
mia+1.873
Neg logit contributions
Animation-2.024
lections-1.977
bj-1.977
ternity-1.938
 DAR-1.905
Token "
Token ID366
Feature activation-6.38e-01

Pos logit contributions
 Mug+2.269
iron+1.960
imus+1.924
 throat+1.747
 isol+1.684
Neg logit contributions
Animation-6.703
bj-6.617
lections-6.558
ternity-6.503
龍喚士-6.500
Tokenpp
Token ID381
Feature activation+1.56e-01

Pos logit contributions
 Mug+3.938
iron+3.852
imus+3.705
mia+3.426
rone+3.411
Neg logit contributions
Animation-3.854
lections-3.755
 +=-3.749
bj-3.699
 DAR-3.695
Tokenpr
Token ID1050
Feature activation+1.10e-01

Pos logit contributions
Animation+0.672
bj+0.650
lections+0.639
 +=+0.637
 DAR+0.629
Neg logit contributions
 Mug-1.293
iron-1.250
imus-1.214
rone-1.157
mia-1.140
Token"]
Token ID8973
Feature activation-5.32e-01

Pos logit contributions
Animation+0.582
bj+0.567
lections+0.560
 +=+0.557
 DAR+0.551
Neg logit contributions
 Mug-0.803
iron-0.771
imus-0.746
rone-0.706
mia-0.695
Token |
Token ID930
Feature activation+6.90e-02

Pos logit contributions
 Mug+2.958
iron+2.799
imus+2.694
rone+2.458
omy+2.452
Neg logit contributions
Animation-3.616
bj-3.574
lections-3.534
 DAR-3.466
 Women-3.394
Token +
Token ID1343
Feature activation-1.98e-01

Pos logit contributions
Animation+0.310
bj+0.302
lections+0.297
 +=+0.291
 DAR+0.290
Neg logit contributions
 Mug-0.558
iron-0.538
imus-0.522
rone-0.497
mia-0.489
Token |
Token ID930
Feature activation-1.09e-02

Pos logit contributions
 Mug+0.955
iron+0.901
imus+0.853
rone+0.783
mia+0.768
Neg logit contributions
Animation-1.407
bj-1.381
lections-1.381
 DAR-1.350
 +=-1.334
Token <
Token ID1279
Feature activation-3.93e-01

Pos logit contributions
 Mug+0.088
iron+0.085
imus+0.082
rone+0.078
mia+0.077
Neg logit contributions
Animation-0.050
bj-0.048
lections-0.047
 +=-0.046
 DAR-0.046
Token--
Token ID438
Feature activation+2.42e-01

Pos logit contributions
 Mug+2.046
iron+1.952
imus+1.848
rone+1.687
 throat+1.661
Neg logit contributions
Animation-2.859
bj-2.797
lections-2.760
 DAR-2.736
 +=-2.734
Token read
Token ID1100
Feature activation+1.73e-01

Pos logit contributions
Animation+1.271
bj+1.240
lections+1.222
 +=+1.217
 DAR+1.202
Neg logit contributions
 Mug-1.776
iron-1.704
imus-1.649
rone-1.560
mia-1.535
Token()
Token ID3419
Feature activation+5.73e-02

Pos logit contributions
Animation+0.937
bj+0.917
lections+0.905
 +=+0.898
 DAR+0.889
Neg logit contributions
 Mug-1.237
iron-1.186
imus-1.147
rone-1.084
mia-1.067
Token'
Token ID6
Feature activation-6.05e-01

Pos logit contributions
Animation+0.346
bj+0.340
lections+0.336
 +=+0.330
 DAR+0.328
Neg logit contributions
 Mug-0.375
iron-0.356
imus-0.345
rone-0.324
 throat-0.320
Tokens
Token ID82
Feature activation-4.61e-02

Pos logit contributions
 Mug+4.204
iron+4.074
imus+3.916
mia+3.697
rone+3.671
Neg logit contributions
Animation-3.203
lections-3.078
bj-3.048
 DAR-3.035
ternity-3.018
Token frame
Token ID5739
Feature activation-8.85e-02

Pos logit contributions
 Mug+0.261
iron+0.246
imus+0.237
rone+0.221
 throat+0.219
Neg logit contributions
Animation-0.319
bj-0.313
lections-0.311
 +=-0.303
 DAR-0.302
Token +
Token ID1343
Feature activation-6.48e-02

Pos logit contributions
 Mug+0.496
iron+0.467
imus+0.448
rone+0.414
 throat+0.408
Neg logit contributions
Animation-0.617
bj-0.610
lections-0.603
 DAR-0.590
 +=-0.589
Token--------------------
Token ID19351
Feature activation+4.44e-03

Pos logit contributions
 Mug+0.440
iron+0.423
imus+0.407
rone+0.382
mia+0.376
Neg logit contributions
Animation-0.376
bj-0.365
lections-0.363
 +=-0.357
 DAR-0.356
Token--+
Token ID44785
Feature activation+4.19e-02

Pos logit contributions
Animation+0.025
bj+0.024
lections+0.024
 DAR+0.024
 +=+0.024
Neg logit contributions
 Mug-0.031
iron-0.030
imus-0.028
rone-0.027
mia-0.026
Token/
Token ID14
Feature activation-5.57e-01

Pos logit contributions
 Mug+2.572
iron+2.452
imus+2.324
rone+2.166
mia+2.142
Neg logit contributions
Animation-3.033
bj-2.949
lections-2.931
 +=-2.930
 DAR-2.892
Tokenblogs
Token ID49096
Feature activation-3.55e-01

Pos logit contributions
 Mug+3.675
iron+3.612
imus+3.422
rone+3.231
mia+3.227
Neg logit contributions
Animation-3.177
 +=-3.094
 DAR-3.079
lections-3.053
bj-3.052
Token/
Token ID14
Feature activation-6.11e-01

Pos logit contributions
 Mug+1.988
iron+1.919
imus+1.832
rone+1.686
mia+1.660
Neg logit contributions
Animation-2.444
bj-2.385
 +=-2.359
 DAR-2.341
lections-2.333
Tokenbeat
Token ID12945
Feature activation-4.75e-01

Pos logit contributions
iron+4.110
 Mug+4.061
imus+3.873
rone+3.663
mia+3.658
Neg logit contributions
Animation-3.410
 +=-3.289
 DAR-3.286
lections-3.210
bj-3.198
Token-
Token ID12
Feature activation-1.20e-01

Pos logit contributions
 Mug+3.194
iron+3.144
imus+2.991
rone+2.814
mia+2.792
Neg logit contributions
Animation-2.731
 DAR-2.631
bj-2.610
 +=-2.607
lections-2.602
Tokenthe
Token ID1169
Feature activation-6.04e-01

Pos logit contributions
 Mug+0.804
iron+0.787
imus+0.751
rone+0.707
mia+0.701
Neg logit contributions
Animation-0.702
bj-0.675
 +=-0.674
 DAR-0.672
lections-0.671
Token-
Token ID12
Feature activation-3.85e-01

Pos logit contributions
 Mug+3.767
iron+3.701
imus+3.535
rone+3.316
mia+3.288
Neg logit contributions
Animation-3.711
bj-3.584
lections-3.566
 +=-3.555
 DAR-3.536
Tokenpress
Token ID8439
Feature activation-3.87e-01

Pos logit contributions
 Mug+2.517
iron+2.507
imus+2.361
rone+2.238
mia+2.207
Neg logit contributions
Animation-2.320
 +=-2.221
 DAR-2.216
lections-2.212
bj-2.198
Token/
Token ID14
Feature activation-4.14e-01

Pos logit contributions
 Mug+2.459
iron+2.386
imus+2.277
rone+2.132
mia+2.078
Neg logit contributions
Animation-2.372
bj-2.319
 +=-2.267
lections-2.267
 DAR-2.248
Tokenthe
Token ID1169
Feature activation-2.50e-01

Pos logit contributions
 Mug+2.754
iron+2.693
imus+2.547
rone+2.414
mia+2.379
Neg logit contributions
Animation-2.424
 +=-2.319
 DAR-2.318
bj-2.317
lections-2.311
Token-
Token ID12
Feature activation+2.50e-02

Pos logit contributions
 Mug+1.679
iron+1.639
imus+1.569
rone+1.474
mia+1.456
Neg logit contributions
Animation-1.462
bj-1.419
 +=-1.398
lections-1.397
 DAR-1.394
Token of
Token ID286
Feature activation-8.07e-02

Pos logit contributions
Animation+1.546
bj+1.511
lections+1.491
 +=+1.487
 DAR+1.469
Neg logit contributions
 Mug-1.912
iron-1.832
imus-1.768
rone-1.667
mia-1.639
Token 1987
Token ID12923
Feature activation-3.43e-01

Pos logit contributions
 Mug+0.525
iron+0.497
imus+0.475
rone+0.447
mia+0.436
Neg logit contributions
Animation-0.500
bj-0.493
lections-0.485
 +=-0.479
 DAR-0.467
Token,
Token ID11
Feature activation-4.24e-02

Pos logit contributions
 Mug+2.290
iron+2.202
imus+2.116
rone+1.972
 isol+1.954
Neg logit contributions
Animation-1.995
bj-1.979
 +=-1.954
lections-1.940
 DAR-1.869
Token included
Token ID3017
Feature activation-5.01e-01

Pos logit contributions
 Mug+0.301
iron+0.289
imus+0.278
rone+0.262
mia+0.258
Neg logit contributions
Animation-0.235
bj-0.229
lections-0.225
 +=-0.225
 DAR-0.220
Token Hat
Token ID10983
Feature activation+1.48e-01

Pos logit contributions
 Mug+3.189
iron+2.947
imus+2.846
 isol+2.689
 throat+2.682
Neg logit contributions
Animation-3.175
bj-3.097
 +=-3.011
lections-3.004
++)-2.950
Tokenay
Token ID323
Feature activation-5.93e-01

Pos logit contributions
Animation+0.741
bj+0.722
lections+0.711
 +=+0.709
 DAR+0.699
Neg logit contributions
 Mug-1.127
iron-1.084
imus-1.050
rone-0.995
mia-0.980
Token as
Token ID355
Feature activation-3.38e-01

Pos logit contributions
 Mug+3.877
iron+3.694
imus+3.522
mia+3.355
rone+3.337
Neg logit contributions
Animation-3.456
bj-3.373
lections-3.366
 +=-3.324
++)-3.301
Token part
Token ID636
Feature activation+8.82e-02

Pos logit contributions
 Mug+2.108
iron+1.970
imus+1.906
 throat+1.775
rone+1.760
Neg logit contributions
Animation-2.175
bj-2.103
lections-2.093
 +=-2.072
 DAR-2.014
Token of
Token ID286
Feature activation-2.23e-01

Pos logit contributions
Animation+0.470
bj+0.458
lections+0.452
 +=+0.451
 DAR+0.445
Neg logit contributions
 Mug-0.642
iron-0.616
imus-0.596
rone-0.563
mia-0.554
Token Syria
Token ID4392
Feature activation-1.08e-01

Pos logit contributions
 Mug+1.416
iron+1.326
imus+1.274
rone+1.194
 throat+1.183
Neg logit contributions
Animation-1.416
bj-1.383
 +=-1.357
lections-1.349
++)-1.312
Token.
Token ID13
Feature activation-1.46e-01

Pos logit contributions
 Mug+0.763
iron+0.732
imus+0.703
rone+0.664
 throat+0.657
Neg logit contributions
Animation-0.600
bj-0.594
lections-0.585
 +=-0.581
 DAR-0.567
Tokenar
Token ID283
Feature activation-2.61e-01

Pos logit contributions
 Mug+0.240
iron+0.233
imus+0.222
rone+0.211
mia+0.208
Neg logit contributions
Animation-0.175
bj-0.166
 +=-0.165
lections-0.165
 DAR-0.164
Tokencon
Token ID1102
Feature activation-6.67e-01

Pos logit contributions
 Mug+1.761
iron+1.723
imus+1.641
rone+1.579
mia+1.564
Neg logit contributions
Animation-1.523
lections-1.490
 +=-1.471
 DAR-1.448
bj-1.440
Token Ortiz
Token ID39039
Feature activation-5.50e-01

Pos logit contributions
 Mug+4.042
iron+3.793
imus+3.653
rone+3.344
omy+3.231
Neg logit contributions
Animation-4.353
 +=-4.232
++)-4.184
lections-4.168
bj-4.158
Token upon
Token ID2402
Feature activation-1.01e-01

Pos logit contributions
 Mug+3.454
iron+3.203
imus+3.103
rone+2.854
 throat+2.775
Neg logit contributions
Animation-3.564
bj-3.449
lections-3.434
 +=-3.393
++)-3.389
Token arrival
Token ID10325
Feature activation-6.47e-01

Pos logit contributions
 Mug+0.612
iron+0.568
imus+0.548
rone+0.508
 throat+0.501
Neg logit contributions
Animation-0.666
bj-0.653
lections-0.644
 +=-0.643
 DAR-0.633
Token at
Token ID379
Feature activation-6.11e-01

Pos logit contributions
 Mug+4.062
iron+3.827
imus+3.608
 throat+3.358
rone+3.338
Neg logit contributions
Animation-4.020
bj-3.954
lections-3.906
++)-3.879
 +=-3.859
Token the
Token ID262
Feature activation-4.11e-01

Pos logit contributions
 Mug+3.715
iron+3.269
imus+3.114
 Lime+2.974
rone+2.921
Neg logit contributions
Animation-4.032
bj-3.989
 +=-3.908
lections-3.848
++)-3.782
Token Jose
Token ID5264
Feature activation-5.06e-02

Pos logit contributions
 Mug+2.722
iron+2.453
imus+2.389
 throat+2.245
rone+2.228
Neg logit contributions
Animation-2.530
bj-2.499
lections-2.479
 +=-2.445
ternity-2.374
Token Mart
Token ID3981
Feature activation+1.31e-01

Pos logit contributions
 Mug+0.317
iron+0.299
imus+0.287
rone+0.268
mia+0.264
Neg logit contributions
Animation-0.326
bj-0.317
lections-0.314
 +=-0.314
 DAR-0.308
Tokeni
Token ID72
Feature activation+2.64e-02

Pos logit contributions
Animation+0.713
bj+0.696
lections+0.686
 +=+0.685
 DAR+0.676
Neg logit contributions
 Mug-0.935
iron-0.897
imus-0.867
rone-0.818
mia-0.803
Token International
Token ID4037
Feature activation-4.60e-01

Pos logit contributions
Animation+0.164
bj+0.161
lections+0.160
 +=+0.159
 DAR+0.156
Neg logit contributions
 Mug-0.169
iron-0.160
imus-0.154
rone-0.144
mia-0.141