TOP ACTIVATIONS
MAX = 4.657

him on Twitter at @ Future Cr imes . <|endoftext|> An
When you watch Sarah Huckabee Sanders right now , you
the dungeon ( what we call our tv room in the
publish it on Ar X iv , before sending it to
for publication ; ar X iv : 14 05 . 7
he spr ained his left ACL after a vicious back hand
TW EL VE ) quarterback hur ries . He is a
if you see what I mean ) there could be a
" You know what I mean ." I pull away at
this season after tearing his ACL last year .
she is comfortable knowing that Valiant stands behind them and that
uck back into the Alberta legislature in 2004 , admits he
see a softer corner or side ? Well , a few
enc ased in copper and dated from about 200 B .
in your garage . This picture shows the two seat heater
compared to couples where both partners are the same age .
some trouble clearing it Sh owing the location of the two
et ernal and und iv ided capital and
NY : Worth Publishers . Google Scholar
just two guys -- I mean , that 's the old

MIN ACTIVATIONS
MIN = -4.424

to disrupt Democratic front - runner Hillary Rodham Clinton 's path
includes the Walker - over run Cell Block D and a
cases , since Dartmouth College v . Woodward in 18 19
] se [ t ] { options } :[ text ]
s Format ) } else { $ font 2 = New
Width , Height } else { Write - Warning - Message
Want Some Pictures of That Corner Vari ation , Don
in Bram pton to the shore of Lake Ontario south of
ex :" [ white ] optional white space se [ t
V il ma v . Goodell Def amation /
] any text or empty { white } at least one
div ide ( space ) { // 1 . Fit an
As part of that case , P eder appeared before
be the equivalent of Loving v . Virginia , which declared
IS FREE | NO FE ES | NO MIN IM U
The Icelandic singer Bj ör k has composed and performed
form : [ text ] { white }{ vi : |
:: Center break } Left { $ s Format . Al
a major Oscars cont ender , potentially picking up
search Space ` *) (* { i , { Sub script

INTERVAL 2.387 - 4.657
CONTAINS 0.205%

" You know what I mean ." I pull away at
aluminum composite panels . The core of many of the panels
hit for the franchise . Granted , we don
the Beer Festival . Make sure to get your tickets !
divides them in the Hell esp ont region . And cru

INTERVAL 0.116 - 2.387
CONTAINS 42.265%

from which we will launch all future stores .
employee said . Looking back now , several Douglas
the UC I was prompted to revise its rules .
Jama al Charles also participated in 11 - on - 11
, Ju wan Thompson and rookie De Angelo Henderson

INTERVAL -2.154 - 0.116
CONTAINS 57.153%

serial ization , and for that I need the current version
s including interrupts and timers . Things started to
social problems from a radical antic ap ital ist perspective ,"
al ism in South Korea . <|endoftext|> This article is about
than one issued on Wednesday by F itch Ratings .

INTERVAL -4.424 - -2.154
CONTAINS 0.377%

continually burning sugar ( gl uc ose ) from the fed
be more cost over - runs . Then there
of all documents in the case . Two justices declined a
You contributed money to Al Qaeda ) without revealing
omet hin ' Better Comes Along !", a song about their
Token him
Token ID683
Feature activation-8.29e-01

Pos logit contributions
 Rue+0.124
yss+0.119
 Jung+0.111
nir+0.107
Tags+0.106
Neg logit contributions
sbm-0.148
bro-0.142
Cub-0.135
worth-0.128
\/-0.127
Token on
Token ID319
Feature activation-1.13e+00

Pos logit contributions
 Rue+0.525
yss+0.503
 Jung+0.469
nir+0.448
Tags+0.444
Neg logit contributions
sbm-0.721
bro-0.691
Cub-0.662
worth-0.631
\/-0.621
Token Twitter
Token ID3009
Feature activation-2.20e+00

Pos logit contributions
 Rue+0.547
yss+0.517
 Jung+0.471
nir+0.441
Tags+0.436
Neg logit contributions
sbm-1.158
bro-1.115
Cub-1.076
worth-1.034
\/-1.019
Token at
Token ID379
Feature activation+3.67e-02

Pos logit contributions
 Rue+1.655
yss+1.584
 Jung+1.504
nir+1.444
Tags+1.437
Neg logit contributions
sbm-1.671
bro-1.572
Cub-1.501
worth-1.419
\/-1.381
Token @
Token ID2488
Feature activation-8.98e-01

Pos logit contributions
sbm+0.027
bro+0.025
Cub+0.024
worth+0.023
\/+0.022
Neg logit contributions
 Rue-0.028
yss-0.028
 Jung-0.026
nir-0.025
Tags-0.025
TokenFuture
Token ID29783
Feature activation+4.66e+00

Pos logit contributions
 Rue+0.695
yss+0.671
 Jung+0.634
nir+0.611
Tags+0.607
Neg logit contributions
sbm-0.655
bro-0.621
Cub-0.590
worth-0.557
\/-0.545
TokenCr
Token ID13916
Feature activation+1.01e+00

Pos logit contributions
sbm+3.513
bro+3.378
Cub+3.300
worth+3.074
\/+2.980
Neg logit contributions
 Rue-3.438
yss-3.268
 Jung-3.103
 refriger-2.979
nir-2.929
Tokenimes
Token ID999
Feature activation-4.98e-01

Pos logit contributions
sbm+0.648
bro+0.609
Cub+0.576
worth+0.541
\/+0.527
Neg logit contributions
 Rue-0.868
yss-0.845
 Jung-0.800
nir-0.775
Tags-0.770
Token.
Token ID13
Feature activation+2.91e-01

Pos logit contributions
 Rue+0.377
yss+0.364
 Jung+0.344
nir+0.330
Tags+0.328
Neg logit contributions
sbm-0.372
bro-0.354
Cub-0.337
worth-0.318
\/-0.311
Token<|endoftext|>
Token ID50256
Feature activation-5.06e-01

Pos logit contributions
sbm+0.231
bro+0.220
Cub+0.210
worth+0.200
\/+0.196
Neg logit contributions
 Rue-0.207
yss-0.200
 Jung-0.186
nir-0.180
 refriger-0.177
TokenAn
Token ID2025
Feature activation+4.64e-01

Pos logit contributions
 Rue+0.389
yss+0.376
 Jung+0.355
nir+0.341
 refriger+0.338
Neg logit contributions
sbm-0.372
bro-0.355
Cub-0.337
worth-0.318
\/-0.311
Token
Token ID250
Feature activation+6.78e-01

Pos logit contributions
sbm+1.081
bro+1.027
Cub+0.976
worth+0.923
\/+0.904
Neg logit contributions
 Rue-1.100
yss-1.061
 Jung-1.002
nir-0.964
Tags-0.958
TokenWhen
Token ID2215
Feature activation+2.69e-02

Pos logit contributions
sbm+0.492
bro+0.465
Cub+0.440
worth+0.416
\/+0.409
Neg logit contributions
 Rue-0.531
yss-0.512
 Jung-0.484
nir-0.467
Tags-0.463
Token you
Token ID345
Feature activation+8.45e-01

Pos logit contributions
sbm+0.020
bro+0.019
Cub+0.018
worth+0.017
\/+0.016
Neg logit contributions
 Rue-0.021
yss-0.020
 Jung-0.019
nir-0.018
Tags-0.018
Token watch
Token ID2342
Feature activation-8.75e-01

Pos logit contributions
sbm+0.676
bro+0.650
Cub+0.613
worth+0.588
\/+0.579
Neg logit contributions
 Rue-0.589
yss-0.574
 Jung-0.528
Tags-0.513
nir-0.509
Token Sarah
Token ID10490
Feature activation+1.22e+00

Pos logit contributions
 Rue+0.646
yss+0.622
 Jung+0.587
nir+0.563
Tags+0.560
Neg logit contributions
sbm-0.671
bro-0.637
Cub-0.607
worth-0.575
\/-0.563
Token Huckabee
Token ID38253
Feature activation+4.10e+00

Pos logit contributions
sbm+0.988
bro+0.948
Cub+0.906
worth+0.864
\/+0.850
Neg logit contributions
 Rue-0.831
yss-0.810
 Jung-0.745
nir-0.737
Tags-0.725
Token Sanders
Token ID5831
Feature activation+1.40e+00

Pos logit contributions
sbm+2.775
bro+2.617
Cub+2.454
worth+2.418
\/+2.282
Neg logit contributions
 Rue-3.358
yss-3.290
 Jung-3.038
nir-3.004
 refriger-2.949
Token right
Token ID826
Feature activation+7.79e-01

Pos logit contributions
sbm+1.065
bro+1.025
Cub+0.973
worth+0.934
\/+0.912
Neg logit contributions
 Rue-1.014
yss-0.990
 Jung-0.920
nir-0.895
Tags-0.888
Token now
Token ID783
Feature activation-2.44e-01

Pos logit contributions
sbm+0.487
bro+0.462
Cub+0.429
worth+0.407
\/+0.397
Neg logit contributions
 Rue-0.682
yss-0.662
 Jung-0.627
nir-0.611
Tags-0.610
Token,
Token ID11
Feature activation+3.71e-01

Pos logit contributions
 Rue+0.174
yss+0.167
 Jung+0.157
nir+0.151
Tags+0.150
Neg logit contributions
sbm-0.193
bro-0.184
Cub-0.176
worth-0.167
\/-0.164
Token you
Token ID345
Feature activation+6.87e-01

Pos logit contributions
sbm+0.247
bro+0.235
Cub+0.222
worth+0.209
\/+0.203
Neg logit contributions
 Rue-0.308
yss-0.299
 Jung-0.283
nir-0.275
Tags-0.274
Token the
Token ID262
Feature activation+7.86e-01

Pos logit contributions
 Rue+0.161
yss+0.156
 Jung+0.146
nir+0.141
Tags+0.140
Neg logit contributions
sbm-0.175
bro-0.167
Cub-0.159
worth-0.150
\/-0.148
Token dungeon
Token ID18974
Feature activation+1.72e+00

Pos logit contributions
sbm+0.639
bro+0.612
Cub+0.582
worth+0.554
\/+0.543
Neg logit contributions
 Rue-0.537
yss-0.520
 Jung-0.484
nir-0.468
Tags-0.466
Token (
Token ID357
Feature activation+6.38e-01

Pos logit contributions
sbm+1.293
bro+1.251
Cub+1.176
worth+1.123
\/+1.103
Neg logit contributions
 Rue-1.271
yss-1.232
 Jung-1.146
nir-1.110
Tags-1.109
Tokenwhat
Token ID10919
Feature activation-2.42e-01

Pos logit contributions
sbm+0.443
bro+0.423
Cub+0.399
worth+0.377
\/+0.365
Neg logit contributions
 Rue-0.515
yss-0.499
 Jung-0.472
nir-0.453
Tags-0.452
Token we
Token ID356
Feature activation+1.19e+00

Pos logit contributions
 Rue+0.182
yss+0.176
 Jung+0.165
nir+0.158
Tags+0.158
Neg logit contributions
sbm-0.182
bro-0.174
Cub-0.165
worth-0.156
\/-0.153
Token call
Token ID869
Feature activation+3.96e+00

Pos logit contributions
sbm+0.832
bro+0.800
Cub+0.750
worth+0.711
\/+0.696
Neg logit contributions
 Rue-0.953
yss-0.926
 Jung-0.870
nir-0.842
Tags-0.840
Token our
Token ID674
Feature activation+4.50e-01

Pos logit contributions
sbm+2.991
bro+2.892
Cub+2.712
worth+2.561
\/+2.518
Neg logit contributions
 Rue-2.802
yss-2.776
 Jung-2.518
Tags-2.514
nir-2.491
Token tv
Token ID31557
Feature activation-3.25e-01

Pos logit contributions
sbm+0.360
bro+0.344
Cub+0.328
worth+0.311
\/+0.305
Neg logit contributions
 Rue-0.316
yss-0.306
 Jung-0.284
nir-0.275
Tags-0.274
Token room
Token ID2119
Feature activation+1.94e+00

Pos logit contributions
 Rue+0.231
yss+0.223
 Jung+0.209
nir+0.200
Tags+0.200
Neg logit contributions
sbm-0.257
bro-0.246
Cub-0.234
worth-0.222
\/-0.218
Token in
Token ID287
Feature activation+1.51e-01

Pos logit contributions
sbm+1.554
bro+1.505
Cub+1.424
worth+1.361
\/+1.337
Neg logit contributions
 Rue-1.337
yss-1.302
 Jung-1.200
Tags-1.174
nir-1.164
Token the
Token ID262
Feature activation+5.30e-01

Pos logit contributions
sbm+0.118
bro+0.113
Cub+0.108
worth+0.102
\/+0.100
Neg logit contributions
 Rue-0.109
yss-0.105
 Jung-0.098
nir-0.095
Tags-0.095
Token publish
Token ID7715
Feature activation+7.89e-01

Pos logit contributions
 Rue+0.642
yss+0.618
 Jung+0.582
nir+0.559
Tags+0.556
Neg logit contributions
sbm-0.681
bro-0.648
Cub-0.617
worth-0.585
\/-0.573
Token it
Token ID340
Feature activation+1.48e-01

Pos logit contributions
sbm+0.618
bro+0.589
Cub+0.561
worth+0.533
\/+0.522
Neg logit contributions
 Rue-0.567
yss-0.546
 Jung-0.514
nir-0.493
Tags-0.490
Token on
Token ID319
Feature activation+6.21e-01

Pos logit contributions
sbm+0.114
bro+0.109
Cub+0.104
worth+0.099
\/+0.097
Neg logit contributions
 Rue-0.108
yss-0.104
 Jung-0.097
nir-0.094
Tags-0.094
Token Ar
Token ID943
Feature activation+3.74e-01

Pos logit contributions
sbm+0.476
bro+0.455
Cub+0.432
worth+0.410
\/+0.406
Neg logit contributions
 Rue-0.449
yss-0.440
 Jung-0.408
nir-0.396
Tags-0.392
TokenX
Token ID55
Feature activation-5.11e-01

Pos logit contributions
sbm+0.263
bro+0.252
Cub+0.237
worth+0.222
\/+0.218
Neg logit contributions
 Rue-0.301
yss-0.288
 Jung-0.275
nir-0.264
Tags-0.264
Tokeniv
Token ID452
Feature activation+3.94e+00

Pos logit contributions
 Rue+0.527
yss+0.515
 Jung+0.493
nir+0.480
Tags+0.476
Neg logit contributions
sbm-0.240
bro-0.223
Cub-0.205
worth-0.187
\/-0.178
Token,
Token ID11
Feature activation+4.90e-01

Pos logit contributions
sbm+2.788
bro+2.722
Cub+2.609
worth+2.426
\/+2.411
Neg logit contributions
 Rue-2.950
yss-2.886
 Jung-2.689
nir-2.617
ukong-2.574
Token before
Token ID878
Feature activation-4.54e-01

Pos logit contributions
sbm+0.371
bro+0.355
Cub+0.338
worth+0.321
\/+0.314
Neg logit contributions
 Rue-0.361
yss-0.352
 Jung-0.328
nir-0.319
Tags-0.316
Token sending
Token ID7216
Feature activation+4.87e-01

Pos logit contributions
 Rue+0.339
yss+0.329
 Jung+0.308
nir+0.298
Tags+0.297
Neg logit contributions
sbm-0.340
bro-0.326
Cub-0.310
worth-0.293
\/-0.288
Token it
Token ID340
Feature activation+1.80e-02

Pos logit contributions
sbm+0.331
bro+0.316
Cub+0.295
worth+0.277
\/+0.275
Neg logit contributions
 Rue-0.397
yss-0.387
 Jung-0.363
nir-0.354
Tags-0.351
Token to
Token ID284
Feature activation+3.09e-01

Pos logit contributions
sbm+0.014
bro+0.014
Cub+0.013
worth+0.013
\/+0.012
Neg logit contributions
 Rue-0.012
yss-0.012
 Jung-0.011
Tags-0.011
nir-0.011
Token for
Token ID329
Feature activation+7.03e-01

Pos logit contributions
 Rue+0.334
yss+0.325
 Jung+0.305
nir+0.297
Tags+0.294
Neg logit contributions
sbm-0.296
bro-0.282
Cub-0.267
worth-0.251
\/-0.247
Token publication
Token ID9207
Feature activation+4.99e-01

Pos logit contributions
sbm+0.534
bro+0.515
Cub+0.491
worth+0.464
\/+0.455
Neg logit contributions
 Rue-0.513
yss-0.498
 Jung-0.462
nir-0.455
Tags-0.446
Token;
Token ID26
Feature activation+9.40e-01

Pos logit contributions
sbm+0.398
bro+0.382
Cub+0.365
worth+0.346
\/+0.341
Neg logit contributions
 Rue-0.348
yss-0.339
 Jung-0.313
nir-0.306
Tags-0.301
Token ar
Token ID610
Feature activation+1.40e+00

Pos logit contributions
sbm+0.774
bro+0.739
Cub+0.707
worth+0.673
\/+0.660
Neg logit contributions
 Rue-0.633
yss-0.610
 Jung-0.564
nir-0.555
Tags-0.539
TokenX
Token ID55
Feature activation-1.34e-01

Pos logit contributions
sbm+1.020
bro+0.984
Cub+0.927
worth+0.877
\/+0.860
Neg logit contributions
 Rue-1.078
yss-1.031
 Jung-0.980
nir-0.944
 refriger-0.936
Tokeniv
Token ID452
Feature activation+3.77e+00

Pos logit contributions
 Rue+0.140
yss+0.136
 Jung+0.131
nir+0.127
Tags+0.126
Neg logit contributions
sbm-0.062
bro-0.057
Cub-0.052
worth-0.048
\/-0.046
Token:
Token ID25
Feature activation+1.58e+00

Pos logit contributions
sbm+2.307
bro+2.223
Cub+2.075
\/+1.940
worth+1.915
Neg logit contributions
 Rue-3.239
yss-3.132
 Jung-2.960
nir-2.950
Tags-2.864
Token 14
Token ID1478
Feature activation+1.19e+00

Pos logit contributions
sbm+1.095
bro+1.044
Cub+0.973
worth+0.925
\/+0.903
Neg logit contributions
 Rue-1.281
yss-1.235
 Jung-1.175
nir-1.140
Tags-1.120
Token05
Token ID2713
Feature activation+1.06e+00

Pos logit contributions
sbm+0.794
bro+0.755
Cub+0.708
worth+0.669
\/+0.659
Neg logit contributions
 Rue-0.990
yss-0.967
 Jung-0.909
nir-0.881
 refriger-0.875
Token.
Token ID13
Feature activation+6.27e-01

Pos logit contributions
sbm+0.800
bro+0.764
Cub+0.726
worth+0.688
\/+0.677
Neg logit contributions
 Rue-0.785
yss-0.759
 Jung-0.712
nir-0.686
Tags-0.679
Token7
Token ID22
Feature activation+1.56e-01

Pos logit contributions
sbm+0.416
bro+0.391
Cub+0.368
worth+0.346
\/+0.337
Neg logit contributions
 Rue-0.529
yss-0.514
 Jung-0.487
nir-0.472
 refriger-0.467
Token he
Token ID339
Feature activation+9.05e-01

Pos logit contributions
sbm+0.187
bro+0.180
Cub+0.168
worth+0.159
\/+0.153
Neg logit contributions
 Rue-0.247
yss-0.242
 Jung-0.227
nir-0.221
Tags-0.220
Token spr
Token ID7500
Feature activation+1.89e+00

Pos logit contributions
sbm+0.642
bro+0.628
Cub+0.588
worth+0.562
\/+0.542
Neg logit contributions
 Rue-0.700
yss-0.686
 Jung-0.636
nir-0.620
Tags-0.618
Tokenained
Token ID1328
Feature activation+9.99e-01

Pos logit contributions
sbm+1.253
bro+1.192
Cub+1.119
worth+1.055
\/+1.033
Neg logit contributions
 Rue-1.580
yss-1.531
 Jung-1.455
nir-1.400
Tags-1.399
Token his
Token ID465
Feature activation+1.31e+00

Pos logit contributions
sbm+0.778
bro+0.753
Cub+0.714
worth+0.677
\/+0.663
Neg logit contributions
 Rue-0.708
yss-0.694
 Jung-0.640
nir-0.618
Tags-0.616
Token left
Token ID1364
Feature activation+2.32e+00

Pos logit contributions
sbm+1.014
bro+0.978
Cub+0.932
worth+0.879
\/+0.871
Neg logit contributions
 Rue-0.916
yss-0.905
 Jung-0.825
Tags-0.810
nir-0.805
Token ACL
Token ID17382
Feature activation+3.71e+00

Pos logit contributions
sbm+1.789
bro+1.738
Cub+1.667
worth+1.564
\/+1.551
Neg logit contributions
 Rue-1.618
yss-1.591
 Jung-1.446
Tags-1.423
nir-1.412
Token after
Token ID706
Feature activation+7.06e-01

Pos logit contributions
sbm+2.722
bro+2.679
Cub+2.507
worth+2.376
\/+2.355
Neg logit contributions
 Rue-2.674
yss-2.627
 Jung-2.436
nir-2.405
Tags-2.365
Token a
Token ID257
Feature activation+1.29e+00

Pos logit contributions
sbm+0.537
bro+0.518
Cub+0.492
worth+0.468
\/+0.456
Neg logit contributions
 Rue-0.515
yss-0.502
 Jung-0.467
nir-0.453
Tags-0.450
Token vicious
Token ID17686
Feature activation+2.23e+00

Pos logit contributions
sbm+0.954
bro+0.925
Cub+0.879
worth+0.830
\/+0.814
Neg logit contributions
 Rue-0.953
yss-0.935
 Jung-0.867
nir-0.847
Tags-0.843
Token back
Token ID736
Feature activation+1.84e+00

Pos logit contributions
sbm+1.644
bro+1.628
Cub+1.547
worth+1.461
\/+1.438
Neg logit contributions
 Rue-1.608
yss-1.597
 Jung-1.461
nir-1.441
Tags-1.428
Tokenhand
Token ID4993
Feature activation+1.32e+00

Pos logit contributions
sbm+1.315
bro+1.260
Cub+1.186
worth+1.117
\/+1.092
Neg logit contributions
 Rue-1.443
yss-1.402
 Jung-1.323
Tags-1.269
nir-1.268
Token TW
Token ID17306
Feature activation+2.61e-01

Pos logit contributions
sbm+0.793
bro+0.754
Cub+0.715
worth+0.678
\/+0.660
Neg logit contributions
 Rue-0.866
yss-0.843
 Jung-0.795
nir-0.771
Tags-0.764
TokenEL
Token ID3698
Feature activation+1.27e+00

Pos logit contributions
sbm+0.194
bro+0.187
Cub+0.177
worth+0.167
EEE+0.165
Neg logit contributions
 Rue-0.196
yss-0.190
 Jung-0.179
nir-0.173
Tags-0.171
TokenVE
Token ID6089
Feature activation-2.87e-01

Pos logit contributions
sbm+0.844
bro+0.804
Cub+0.757
worth+0.711
EEE+0.696
Neg logit contributions
 Rue-1.054
yss-1.024
 Jung-0.973
nir-0.944
Tags-0.931
Token)
Token ID8
Feature activation+1.66e+00

Pos logit contributions
 Rue+0.197
yss+0.189
 Jung+0.177
nir+0.170
Tags+0.168
Neg logit contributions
sbm-0.235
bro-0.225
Cub-0.215
worth-0.205
\/-0.201
Token quarterback
Token ID7880
Feature activation+9.49e-01

Pos logit contributions
sbm+1.278
bro+1.247
Cub+1.176
worth+1.117
\/+1.101
Neg logit contributions
 Rue-1.180
yss-1.170
 Jung-1.059
nir-1.046
Tags-1.024
Token hur
Token ID6990
Feature activation+3.69e+00

Pos logit contributions
sbm+0.644
bro+0.628
Cub+0.579
worth+0.545
\/+0.542
Neg logit contributions
yss-0.764
 Rue-0.761
 Jung-0.691
nir-0.686
Tags-0.677
Tokenries
Token ID1678
Feature activation+6.46e-01

Pos logit contributions
sbm+2.467
bro+2.356
Cub+2.229
worth+2.056
\/+2.029
Neg logit contributions
 Rue-3.060
yss-2.970
 Jung-2.815
nir-2.700
 refriger-2.682
Token.
Token ID13
Feature activation+1.57e+00

Pos logit contributions
sbm+0.496
bro+0.475
Cub+0.451
worth+0.432
\/+0.423
Neg logit contributions
 Rue-0.472
yss-0.459
 Jung-0.427
nir-0.415
Tags-0.409
Token He
Token ID679
Feature activation+1.15e+00

Pos logit contributions
sbm+1.241
bro+1.182
Cub+1.132
worth+1.084
\/+1.057
Neg logit contributions
yss-1.101
 Rue-1.068
nir-0.976
 Jung-0.973
 refriger-0.964
Token is
Token ID318
Feature activation+1.35e-01

Pos logit contributions
sbm+0.877
bro+0.850
Cub+0.797
worth+0.768
\/+0.746
Neg logit contributions
 Rue-0.838
yss-0.817
 Jung-0.760
nir-0.735
Tags-0.728
Token a
Token ID257
Feature activation+4.12e-01

Pos logit contributions
sbm+0.103
bro+0.100
Cub+0.095
worth+0.091
\/+0.088
Neg logit contributions
 Rue-0.097
yss-0.095
 Jung-0.089
nir-0.086
Tags-0.085
Tokenif
Token ID361
Feature activation+4.76e-01

Pos logit contributions
sbm+0.414
bro+0.394
Cub+0.374
worth+0.351
\/+0.340
Neg logit contributions
 Rue-0.490
yss-0.475
 Jung-0.450
nir-0.434
Tags-0.430
Token you
Token ID345
Feature activation-6.18e-02

Pos logit contributions
sbm+0.341
bro+0.327
Cub+0.309
worth+0.293
\/+0.285
Neg logit contributions
 Rue-0.370
yss-0.360
 Jung-0.338
nir-0.327
Tags-0.325
Token see
Token ID766
Feature activation-4.56e-01

Pos logit contributions
 Rue+0.047
yss+0.046
 Jung+0.043
nir+0.041
Tags+0.041
Neg logit contributions
sbm-0.046
bro-0.044
Cub-0.041
worth-0.039
\/-0.038
Token what
Token ID644
Feature activation-1.20e-01

Pos logit contributions
 Rue+0.346
yss+0.335
 Jung+0.315
nir+0.305
Tags+0.302
Neg logit contributions
sbm-0.338
bro-0.323
Cub-0.306
worth-0.289
\/-0.283
Token I
Token ID314
Feature activation+5.03e-01

Pos logit contributions
 Rue+0.097
yss+0.094
 Jung+0.089
nir+0.086
Tags+0.086
Neg logit contributions
sbm-0.083
bro-0.079
Cub-0.075
worth-0.070
\/-0.068
Token mean
Token ID1612
Feature activation+3.69e+00

Pos logit contributions
sbm+0.420
bro+0.404
Cub+0.383
worth+0.367
\/+0.360
Neg logit contributions
 Rue-0.336
yss-0.325
 Jung-0.301
nir-0.290
Tags-0.287
Token)
Token ID8
Feature activation+8.10e-01

Pos logit contributions
sbm+2.770
bro+2.680
Cub+2.560
worth+2.416
\/+2.389
Neg logit contributions
 Rue-2.644
yss-2.576
 Jung-2.377
nir-2.340
ukong-2.326
Token there
Token ID612
Feature activation+7.43e-01

Pos logit contributions
sbm+0.605
bro+0.574
Cub+0.546
worth+0.517
\/+0.506
Neg logit contributions
 Rue-0.612
yss-0.592
 Jung-0.556
nir-0.539
Tags-0.534
Token could
Token ID714
Feature activation-5.46e-02

Pos logit contributions
sbm+0.507
bro+0.483
Cub+0.455
worth+0.429
\/+0.419
Neg logit contributions
 Rue-0.608
yss-0.591
 Jung-0.555
nir-0.538
Tags-0.535
Token be
Token ID307
Feature activation+1.75e-01

Pos logit contributions
 Rue+0.040
yss+0.039
 Jung+0.037
nir+0.035
Tags+0.035
Neg logit contributions
sbm-0.042
bro-0.040
Cub-0.038
worth-0.036
\/-0.035
Token a
Token ID257
Feature activation+1.12e-01

Pos logit contributions
sbm+0.120
bro+0.114
Cub+0.107
worth+0.101
\/+0.099
Neg logit contributions
 Rue-0.143
yss-0.138
 Jung-0.131
nir-0.127
Tags-0.126
Token "
Token ID366
Feature activation+8.13e-03

Pos logit contributions
sbm+0.847
bro+0.824
Cub+0.776
worth+0.739
\/+0.715
Neg logit contributions
 Rue-0.901
yss-0.876
 Jung-0.819
nir-0.803
Tags-0.791
TokenYou
Token ID1639
Feature activation+2.16e-01

Pos logit contributions
sbm+0.006
bro+0.005
Cub+0.005
worth+0.005
\/+0.005
Neg logit contributions
 Rue-0.007
yss-0.006
 Jung-0.006
nir-0.006
 refriger-0.006
Token know
Token ID760
Feature activation+2.13e-01

Pos logit contributions
sbm+0.158
bro+0.154
Cub+0.143
worth+0.137
\/+0.135
Neg logit contributions
 Rue-0.164
yss-0.160
 Jung-0.149
nir-0.145
Tags-0.144
Token what
Token ID644
Feature activation+2.14e-01

Pos logit contributions
sbm+0.150
bro+0.145
Cub+0.136
worth+0.129
\/+0.127
Neg logit contributions
 Rue-0.166
yss-0.162
 Jung-0.151
nir-0.148
Tags-0.147
Token I
Token ID314
Feature activation+8.00e-01

Pos logit contributions
sbm+0.147
bro+0.146
Cub+0.135
worth+0.129
\/+0.125
Neg logit contributions
 Rue-0.168
yss-0.164
 Jung-0.152
Tags-0.150
nir-0.150
Token mean
Token ID1612
Feature activation+3.65e+00

Pos logit contributions
sbm+0.619
bro+0.606
Cub+0.561
worth+0.547
EEE+0.535
Neg logit contributions
 Rue-0.572
yss-0.562
 Jung-0.518
nir-0.504
Tags-0.499
Token."
Token ID526
Feature activation+2.76e-01

Pos logit contributions
sbm+2.608
bro+2.598
Cub+2.457
worth+2.325
EEE+2.303
Neg logit contributions
 Rue-2.662
yss-2.608
nir-2.398
Tags-2.380
 Jung-2.374
Token I
Token ID314
Feature activation-3.31e-02

Pos logit contributions
sbm+0.200
bro+0.191
Cub+0.181
worth+0.172
\/+0.167
Neg logit contributions
 Rue-0.211
yss-0.205
 Jung-0.192
nir-0.188
Tags-0.186
Token pull
Token ID2834
Feature activation-4.82e-01

Pos logit contributions
 Rue+0.022
yss+0.022
 Jung+0.020
nir+0.019
Tags+0.019
Neg logit contributions
sbm-0.027
bro-0.026
Cub-0.025
worth-0.024
\/-0.023
Token away
Token ID1497
Feature activation+1.31e+00

Pos logit contributions
 Rue+0.356
yss+0.345
 Jung+0.322
nir+0.314
Tags+0.312
Neg logit contributions
sbm-0.362
bro-0.349
Cub-0.329
worth-0.314
\/-0.308
Token at
Token ID379
Feature activation+4.43e-01

Pos logit contributions
sbm+0.911
bro+0.884
Cub+0.829
worth+0.792
\/+0.770
Neg logit contributions
 Rue-1.030
yss-1.006
 Jung-0.941
nir-0.920
Tags-0.914
Token this
Token ID428
Feature activation+1.59e-01

Pos logit contributions
 Rue+0.146
yss+0.141
 Jung+0.132
nir+0.127
Tags+0.126
Neg logit contributions
sbm-0.148
bro-0.141
Cub-0.134
worth-0.128
\/-0.125
Token season
Token ID1622
Feature activation+1.24e+00

Pos logit contributions
sbm+0.121
bro+0.115
Cub+0.110
worth+0.104
\/+0.102
Neg logit contributions
 Rue-0.117
yss-0.113
 Jung-0.106
nir-0.103
Tags-0.102
Token after
Token ID706
Feature activation-2.14e-02

Pos logit contributions
sbm+0.938
bro+0.900
Cub+0.852
worth+0.815
\/+0.797
Neg logit contributions
 Rue-0.917
yss-0.889
 Jung-0.832
nir-0.805
Tags-0.798
Token tearing
Token ID24447
Feature activation+1.35e+00

Pos logit contributions
 Rue+0.015
yss+0.015
 Jung+0.014
nir+0.013
Tags+0.013
Neg logit contributions
sbm-0.017
bro-0.016
Cub-0.015
worth-0.015
\/-0.014
Token his
Token ID465
Feature activation+1.34e+00

Pos logit contributions
sbm+1.045
bro+1.006
Cub+0.955
worth+0.905
\/+0.901
Neg logit contributions
 Rue-0.965
yss-0.944
 Jung-0.876
nir-0.851
Tags-0.844
Token ACL
Token ID17382
Feature activation+3.65e+00

Pos logit contributions
sbm+1.019
bro+0.987
Cub+0.940
\/+0.892
worth+0.881
Neg logit contributions
 Rue-0.955
yss-0.947
 Jung-0.861
nir-0.845
Tags-0.838
Token last
Token ID938
Feature activation+3.25e-01

Pos logit contributions
sbm+2.685
bro+2.627
Cub+2.445
worth+2.357
\/+2.343
Neg logit contributions
 Rue-2.638
yss-2.596
 Jung-2.402
nir-2.377
Tags-2.338
Token year
Token ID614
Feature activation+1.63e-01

Pos logit contributions
sbm+0.265
bro+0.257
Cub+0.244
worth+0.234
\/+0.230
Neg logit contributions
 Rue-0.218
yss-0.212
 Jung-0.196
nir-0.191
Tags-0.190
Token.
Token ID13
Feature activation+4.92e-01

Pos logit contributions
sbm+0.127
bro+0.121
Cub+0.115
worth+0.109
\/+0.107
Neg logit contributions
 Rue-0.118
yss-0.114
 Jung-0.107
nir-0.103
Tags-0.102
Token
Token ID198
Feature activation+3.29e-01

Pos logit contributions
sbm+0.370
bro+0.352
Cub+0.338
worth+0.321
\/+0.311
Neg logit contributions
 Rue-0.364
yss-0.361
 Jung-0.329
nir-0.325
Tags-0.320
Token
Token ID198
Feature activation-7.24e-02

Pos logit contributions
sbm+0.239
bro+0.229
Cub+0.217
worth+0.206
\/+0.201
Neg logit contributions
 Rue-0.254
yss-0.248
 Jung-0.231
nir-0.225
Tags-0.221
Token she
Token ID673
Feature activation+8.02e-01

Pos logit contributions
 Rue+0.153
yss+0.149
 Jung+0.142
nir+0.138
Tags+0.137
Neg logit contributions
sbm-0.094
bro-0.088
Cub-0.083
worth-0.077
\/-0.074
Token is
Token ID318
Feature activation-6.66e-01

Pos logit contributions
sbm+0.541
bro+0.517
Cub+0.486
worth+0.461
\/+0.452
Neg logit contributions
 Rue-0.661
yss-0.640
 Jung-0.604
nir-0.586
Tags-0.582
Token comfortable
Token ID6792
Feature activation-7.75e-01

Pos logit contributions
 Rue+0.490
yss+0.475
 Jung+0.445
nir+0.431
Tags+0.428
Neg logit contributions
sbm-0.507
bro-0.487
Cub-0.462
worth-0.441
\/-0.432
Token knowing
Token ID6970
Feature activation+9.89e-02

Pos logit contributions
 Rue+0.578
yss+0.558
 Jung+0.526
nir+0.509
Tags+0.505
Neg logit contributions
sbm-0.585
bro-0.559
Cub-0.530
worth-0.503
\/-0.494
Token that
Token ID326
Feature activation-8.20e-01

Pos logit contributions
sbm+0.068
bro+0.065
Cub+0.061
worth+0.058
\/+0.056
Neg logit contributions
 Rue-0.080
yss-0.078
 Jung-0.074
nir-0.072
Tags-0.071
Token Valiant
Token ID47781
Feature activation+3.63e+00

Pos logit contributions
 Rue+0.650
yss+0.628
 Jung+0.594
nir+0.576
Tags+0.572
Neg logit contributions
sbm-0.581
bro-0.553
Cub-0.523
worth-0.494
\/-0.483
Token stands
Token ID6296
Feature activation-1.79e+00

Pos logit contributions
sbm+2.405
bro+2.364
Cub+2.210
worth+2.092
\/+2.067
Neg logit contributions
 Rue-2.916
yss-2.842
 Jung-2.699
nir-2.640
Tags-2.587
Token behind
Token ID2157
Feature activation-8.40e-01

Pos logit contributions
 Rue+1.188
yss+1.145
 Jung+1.067
nir+1.031
Tags+1.015
Neg logit contributions
sbm-1.482
bro-1.438
Cub-1.366
worth-1.318
\/-1.287
Token them
Token ID606
Feature activation+2.42e-01

Pos logit contributions
 Rue+0.633
yss+0.611
 Jung+0.577
nir+0.558
Tags+0.552
Neg logit contributions
sbm-0.628
bro-0.599
Cub-0.568
worth-0.539
\/-0.528
Token and
Token ID290
Feature activation+3.84e-01

Pos logit contributions
sbm+0.184
bro+0.175
Cub+0.166
worth+0.158
\/+0.155
Neg logit contributions
 Rue-0.180
yss-0.173
 Jung-0.164
nir-0.157
Tags-0.156
Token that
Token ID326
Feature activation-2.32e-01

Pos logit contributions
sbm+0.265
bro+0.253
Cub+0.239
worth+0.226
\/+0.221
Neg logit contributions
 Rue-0.308
yss-0.298
 Jung-0.283
nir-0.274
Tags-0.272
Tokenuck
Token ID1347
Feature activation-2.37e-01

Pos logit contributions
 Rue+0.364
yss+0.350
 Jung+0.331
nir+0.318
Tags+0.316
Neg logit contributions
sbm-0.373
bro-0.355
Cub-0.338
worth-0.321
\/-0.314
Token back
Token ID736
Feature activation+1.20e+00

Pos logit contributions
 Rue+0.152
yss+0.148
 Jung+0.136
nir+0.132
Tags+0.131
Neg logit contributions
sbm-0.201
bro-0.194
Cub-0.184
worth-0.178
\/-0.173
Token into
Token ID656
Feature activation+1.01e+00

Pos logit contributions
sbm+1.035
bro+1.005
Cub+0.951
worth+0.926
\/+0.902
Neg logit contributions
 Rue-0.746
yss-0.717
 Jung-0.660
Tags-0.644
nir-0.635
Token the
Token ID262
Feature activation+1.06e+00

Pos logit contributions
sbm+0.797
bro+0.762
Cub+0.728
worth+0.690
\/+0.678
Neg logit contributions
 Rue-0.711
yss-0.696
 Jung-0.643
nir-0.630
Tags-0.625
Token Alberta
Token ID15555
Feature activation+8.60e-01

Pos logit contributions
sbm+0.839
bro+0.805
Cub+0.769
worth+0.729
\/+0.716
Neg logit contributions
 Rue-0.733
yss-0.719
 Jung-0.664
nir-0.647
Tags-0.645
Token legislature
Token ID15928
Feature activation+3.62e+00

Pos logit contributions
sbm+0.683
bro+0.659
Cub+0.626
worth+0.594
\/+0.589
Neg logit contributions
 Rue-0.600
yss-0.580
 Jung-0.538
nir-0.526
Tags-0.523
Token in
Token ID287
Feature activation+2.39e-01

Pos logit contributions
sbm+2.632
bro+2.571
Cub+2.374
worth+2.341
\/+2.276
Neg logit contributions
 Rue-2.672
yss-2.628
nir-2.425
 Jung-2.418
Tags-2.396
Token 2004
Token ID5472
Feature activation+5.13e-01

Pos logit contributions
sbm+0.153
bro+0.147
Cub+0.137
worth+0.130
\/+0.127
Neg logit contributions
 Rue-0.201
yss-0.199
 Jung-0.186
nir-0.182
Tags-0.181
Token,
Token ID11
Feature activation+9.38e-02

Pos logit contributions
sbm+0.394
bro+0.376
Cub+0.356
worth+0.342
\/+0.334
Neg logit contributions
 Rue-0.376
yss-0.364
 Jung-0.340
nir-0.329
Tags-0.327
Token admits
Token ID15534
Feature activation+1.53e+00

Pos logit contributions
sbm+0.069
bro+0.066
Cub+0.063
worth+0.059
\/+0.058
Neg logit contributions
 Rue-0.072
yss-0.069
 Jung-0.065
nir-0.063
Tags-0.063
Token he
Token ID339
Feature activation+4.66e-01

Pos logit contributions
sbm+1.046
bro+1.008
Cub+0.942
worth+0.893
\/+0.871
Neg logit contributions
 Rue-1.224
yss-1.202
 Jung-1.119
nir-1.104
Tags-1.095
Token see
Token ID766
Feature activation+9.09e-01

Pos logit contributions
sbm+0.424
bro+0.404
Cub+0.386
worth+0.366
\/+0.359
Neg logit contributions
 Rue-0.387
yss-0.373
 Jung-0.351
nir-0.337
Tags-0.335
Token a
Token ID257
Feature activation+4.54e-01

Pos logit contributions
sbm+0.645
bro+0.613
Cub+0.581
worth+0.547
\/+0.538
Neg logit contributions
 Rue-0.718
yss-0.697
 Jung-0.656
nir-0.638
Tags-0.629
Token softer
Token ID32359
Feature activation-4.45e-01

Pos logit contributions
sbm+0.410
bro+0.395
Cub+0.380
worth+0.363
\/+0.358
Neg logit contributions
 Rue-0.271
yss-0.260
 Jung-0.237
nir-0.231
Tags-0.227
Token corner
Token ID5228
Feature activation-4.38e-02

Pos logit contributions
 Rue+0.278
yss+0.266
 Jung+0.246
nir+0.236
Tags+0.234
Neg logit contributions
sbm-0.390
bro-0.375
Cub-0.361
worth-0.344
\/-0.338
Token or
Token ID393
Feature activation+5.34e-01

Pos logit contributions
 Rue+0.031
yss+0.030
 Jung+0.028
nir+0.027
Tags+0.027
Neg logit contributions
sbm-0.035
bro-0.033
Cub-0.032
worth-0.030
\/-0.030
Token side
Token ID1735
Feature activation+3.61e+00

Pos logit contributions
sbm+0.410
bro+0.393
Cub+0.374
worth+0.354
\/+0.350
Neg logit contributions
 Rue-0.390
yss-0.377
 Jung-0.353
nir-0.341
Tags-0.338
Token?
Token ID30
Feature activation-1.00e-01

Pos logit contributions
sbm+2.721
bro+2.655
Cub+2.546
worth+2.397
\/+2.365
Neg logit contributions
 Rue-2.637
yss-2.552
 Jung-2.370
nir-2.302
Tags-2.277
Token Well
Token ID3894
Feature activation-2.27e-01

Pos logit contributions
 Rue+0.069
yss+0.067
 Jung+0.062
nir+0.061
Tags+0.060
Neg logit contributions
sbm-0.081
bro-0.077
Cub-0.074
worth-0.070
\/-0.069
Token,
Token ID11
Feature activation+4.61e-01

Pos logit contributions
 Rue+0.157
yss+0.151
 Jung+0.142
nir+0.136
Tags+0.135
Neg logit contributions
sbm-0.185
bro-0.176
Cub-0.168
worth-0.160
\/-0.157
Token a
Token ID257
Feature activation-1.05e-01

Pos logit contributions
sbm+0.337
bro+0.322
Cub+0.306
worth+0.289
\/+0.283
Neg logit contributions
 Rue-0.352
yss-0.341
 Jung-0.320
nir-0.311
Tags-0.309
Token few
Token ID1178
Feature activation-1.31e-01

Pos logit contributions
 Rue+0.075
yss+0.072
 Jung+0.067
nir+0.065
Tags+0.065
Neg logit contributions
sbm-0.082
bro-0.079
Cub-0.075
worth-0.071
\/-0.070
Token enc
Token ID2207
Feature activation-3.46e-01

Pos logit contributions
sbm+0.738
bro+0.718
Cub+0.676
worth+0.648
\/+0.631
Neg logit contributions
 Rue-0.722
yss-0.701
 Jung-0.651
nir-0.629
Tags-0.627
Tokenased
Token ID839
Feature activation-1.24e+00

Pos logit contributions
 Rue+0.305
yss+0.294
 Jung+0.282
nir+0.272
Tags+0.271
Neg logit contributions
sbm-0.215
bro-0.205
Cub-0.190
worth-0.176
\/-0.173
Token in
Token ID287
Feature activation+2.31e-01

Pos logit contributions
 Rue+0.814
yss+0.780
 Jung+0.728
nir+0.698
Tags+0.692
Neg logit contributions
sbm-1.053
bro-1.009
Cub-0.965
worth-0.922
\/-0.903
Token copper
Token ID15317
Feature activation+1.53e+00

Pos logit contributions
sbm+0.174
bro+0.166
Cub+0.157
worth+0.149
\/+0.146
Neg logit contributions
 Rue-0.172
yss-0.166
 Jung-0.156
nir-0.151
Tags-0.150
Token and
Token ID290
Feature activation-4.17e-01

Pos logit contributions
sbm+1.137
bro+1.101
Cub+1.035
worth+0.993
\/+0.972
Neg logit contributions
 Rue-1.139
yss-1.102
 Jung-1.031
nir-1.000
Tags-0.989
Token dated
Token ID14567
Feature activation+3.56e+00

Pos logit contributions
 Rue+0.305
yss+0.296
 Jung+0.276
nir+0.267
Tags+0.266
Neg logit contributions
sbm-0.317
bro-0.306
Cub-0.290
worth-0.277
\/-0.270
Token from
Token ID422
Feature activation+4.13e-01

Pos logit contributions
sbm+2.675
bro+2.612
Cub+2.473
worth+2.363
\/+2.279
Neg logit contributions
yss-2.516
 Rue-2.513
 Jung-2.259
nir-2.245
Tags-2.236
Token about
Token ID546
Feature activation-1.79e-01

Pos logit contributions
sbm+0.321
bro+0.308
Cub+0.293
worth+0.281
\/+0.273
Neg logit contributions
 Rue-0.295
yss-0.287
 Jung-0.266
nir-0.258
Tags-0.257
Token 200
Token ID939
Feature activation+1.37e-01

Pos logit contributions
 Rue+0.126
yss+0.123
 Jung+0.114
nir+0.111
Tags+0.110
Neg logit contributions
sbm-0.141
bro-0.136
Cub-0.129
worth-0.123
\/-0.121
Token B
Token ID347
Feature activation+1.06e+00

Pos logit contributions
sbm+0.104
bro+0.099
Cub+0.094
worth+0.089
\/+0.088
Neg logit contributions
 Rue-0.101
yss-0.098
 Jung-0.092
nir-0.088
Tags-0.088
Token.
Token ID13
Feature activation+7.24e-01

Pos logit contributions
sbm+0.778
bro+0.748
Cub+0.712
worth+0.673
\/+0.660
Neg logit contributions
 Rue-0.813
yss-0.788
 Jung-0.733
nir-0.718
Tags-0.714
Token in
Token ID287
Feature activation-5.35e-01

Pos logit contributions
 Rue+0.449
yss+0.434
 Jung+0.407
nir+0.393
Tags+0.390
Neg logit contributions
sbm-0.472
bro-0.451
Cub-0.428
worth-0.406
\/-0.399
Token your
Token ID534
Feature activation+1.01e-01

Pos logit contributions
 Rue+0.361
yss+0.348
 Jung+0.325
nir+0.312
Tags+0.310
Neg logit contributions
sbm-0.443
bro-0.423
Cub-0.404
worth-0.384
\/-0.378
Token garage
Token ID15591
Feature activation-1.20e+00

Pos logit contributions
sbm+0.086
bro+0.082
Cub+0.079
worth+0.075
\/+0.074
Neg logit contributions
 Rue-0.066
yss-0.063
 Jung-0.059
nir-0.057
Tags-0.056
Token.
Token ID13
Feature activation-9.06e-02

Pos logit contributions
 Rue+0.872
yss+0.841
 Jung+0.791
nir+0.760
Tags+0.754
Neg logit contributions
sbm-0.932
bro-0.888
Cub-0.846
worth-0.802
\/-0.787
TokenThis
Token ID1212
Feature activation+9.83e-01

Pos logit contributions
 Rue+0.064
yss+0.063
 Jung+0.058
nir+0.056
 refriger+0.056
Neg logit contributions
sbm-0.071
bro-0.068
Cub-0.065
worth-0.062
\/-0.061
Token picture
Token ID4286
Feature activation+3.55e+00

Pos logit contributions
sbm+0.705
bro+0.675
Cub+0.634
worth+0.603
\/+0.593
Neg logit contributions
 Rue-0.765
yss-0.749
 Jung-0.698
nir-0.676
Tags-0.669
Token shows
Token ID2523
Feature activation+1.44e+00

Pos logit contributions
sbm+2.352
bro+2.293
Cub+2.128
worth+2.035
\/+1.989
Neg logit contributions
 Rue-2.911
yss-2.840
 Jung-2.662
nir-2.604
Tags-2.554
Token the
Token ID262
Feature activation+2.43e-01

Pos logit contributions
sbm+1.019
bro+0.978
Cub+0.914
worth+0.865
\/+0.853
Neg logit contributions
 Rue-1.133
yss-1.109
 Jung-1.039
nir-1.011
Tags-0.999
Token two
Token ID734
Feature activation-5.48e-01

Pos logit contributions
sbm+0.199
bro+0.191
Cub+0.182
worth+0.173
\/+0.171
Neg logit contributions
 Rue-0.164
yss-0.159
 Jung-0.148
nir-0.143
Tags-0.141
Token seat
Token ID5852
Feature activation-1.31e+00

Pos logit contributions
 Rue+0.414
yss+0.401
 Jung+0.377
nir+0.364
Tags+0.361
Neg logit contributions
sbm-0.408
bro-0.389
Cub-0.369
worth-0.350
\/-0.343
Token heater
Token ID39844
Feature activation+1.14e+00

Pos logit contributions
 Rue+0.772
yss+0.737
 Jung+0.684
nir+0.649
Tags+0.644
Neg logit contributions
sbm-1.202
bro-1.152
Cub-1.107
worth-1.059
\/-1.041
Token compared
Token ID3688
Feature activation-5.61e-01

Pos logit contributions
sbm+0.028
bro+0.027
Cub+0.025
worth+0.024
\/+0.024
Neg logit contributions
 Rue-0.027
yss-0.027
 Jung-0.025
nir-0.024
Tags-0.024
Token to
Token ID284
Feature activation-3.20e-01

Pos logit contributions
 Rue+0.356
yss+0.341
 Jung+0.318
nir+0.304
Tags+0.301
Neg logit contributions
sbm-0.488
bro-0.467
Cub-0.447
worth-0.427
\/-0.419
Token couples
Token ID11886
Feature activation+1.57e+00

Pos logit contributions
 Rue+0.246
yss+0.239
 Jung+0.224
nir+0.217
Tags+0.215
Neg logit contributions
sbm-0.233
bro-0.223
Cub-0.211
worth-0.200
\/-0.196
Token where
Token ID810
Feature activation-1.61e+00

Pos logit contributions
sbm+1.191
bro+1.162
Cub+1.082
worth+1.044
\/+1.028
Neg logit contributions
 Rue-1.139
yss-1.126
 Jung-1.021
nir-1.015
Tags-1.004
Token both
Token ID1111
Feature activation-4.42e-01

Pos logit contributions
 Rue+1.162
yss+1.119
 Jung+1.053
nir+1.011
Tags+1.004
Neg logit contributions
sbm-1.257
bro-1.197
Cub-1.141
worth-1.082
\/-1.060
Token partners
Token ID4887
Feature activation+3.53e+00

Pos logit contributions
 Rue+0.325
yss+0.316
 Jung+0.294
nir+0.285
Tags+0.282
Neg logit contributions
sbm-0.337
bro-0.323
Cub-0.306
worth-0.292
\/-0.286
Token are
Token ID389
Feature activation+1.87e-01

Pos logit contributions
sbm+2.506
bro+2.473
Cub+2.286
worth+2.228
\/+2.197
Neg logit contributions
yss-2.662
 Rue-2.648
 Jung-2.399
Tags-2.385
nir-2.360
Token the
Token ID262
Feature activation+1.38e-01

Pos logit contributions
sbm+0.136
bro+0.131
Cub+0.124
worth+0.119
\/+0.116
Neg logit contributions
 Rue-0.143
yss-0.141
 Jung-0.129
nir-0.126
Tags-0.126
Token same
Token ID976
Feature activation+5.42e-01

Pos logit contributions
sbm+0.117
bro+0.112
Cub+0.107
worth+0.103
\/+0.101
Neg logit contributions
 Rue-0.089
yss-0.087
 Jung-0.079
nir-0.077
ukong-0.076
Token age
Token ID2479
Feature activation-1.49e+00

Pos logit contributions
sbm+0.512
bro+0.502
Cub+0.474
worth+0.465
\/+0.457
Neg logit contributions
 Rue-0.290
yss-0.284
 Jung-0.252
nir-0.246
ukong-0.243
Token.
Token ID13
Feature activation-4.40e-03

Pos logit contributions
 Rue+1.066
yss+1.024
 Jung+0.967
nir+0.926
Tags+0.920
Neg logit contributions
sbm-1.181
bro-1.122
Cub-1.072
worth-1.016
\/-0.995
Token some
Token ID617
Feature activation-3.83e-01

Pos logit contributions
 Rue+0.103
yss+0.099
 Jung+0.093
nir+0.089
Tags+0.089
Neg logit contributions
sbm-0.115
bro-0.110
Cub-0.104
worth-0.099
\/-0.097
Token trouble
Token ID5876
Feature activation+8.15e-01

Pos logit contributions
 Rue+0.286
yss+0.278
 Jung+0.260
nir+0.252
Tags+0.249
Neg logit contributions
sbm-0.288
bro-0.275
Cub-0.261
worth-0.247
\/-0.243
Token clearing
Token ID17304
Feature activation-2.90e-01

Pos logit contributions
sbm+0.647
bro+0.628
Cub+0.595
worth+0.564
\/+0.556
Neg logit contributions
 Rue-0.572
yss-0.551
 Jung-0.515
nir-0.493
Tags-0.493
Token it
Token ID340
Feature activation-5.85e-01

Pos logit contributions
 Rue+0.214
yss+0.207
 Jung+0.195
nir+0.188
Tags+0.186
Neg logit contributions
sbm-0.221
bro-0.211
Cub-0.201
worth-0.190
\/-0.186
TokenSh
Token ID2484
Feature activation+7.68e-01

Pos logit contributions
 Rue+0.423
yss+0.408
 Jung+0.383
nir+0.367
Tags+0.366
Neg logit contributions
sbm-0.457
bro-0.435
Cub-0.415
worth-0.394
\/-0.385
Tokenowing
Token ID7855
Feature activation+3.52e+00

Pos logit contributions
sbm+0.478
bro+0.457
Cub+0.428
worth+0.411
\/+0.393
Neg logit contributions
 Rue-0.663
yss-0.644
 Jung-0.620
Tags-0.594
 refriger-0.590
Token the
Token ID262
Feature activation+1.05e+00

Pos logit contributions
sbm+2.461
bro+2.366
Cub+2.219
worth+2.096
\/+2.070
Neg logit contributions
 Rue-2.775
yss-2.691
 Jung-2.538
nir-2.470
Tags-2.428
Token location
Token ID4067
Feature activation+9.79e-01

Pos logit contributions
sbm+0.829
bro+0.793
Cub+0.755
worth+0.715
\/+0.704
Neg logit contributions
 Rue-0.743
yss-0.719
 Jung-0.670
nir-0.649
Tags-0.641
Token of
Token ID286
Feature activation+1.32e+00

Pos logit contributions
sbm+0.780
bro+0.752
Cub+0.714
worth+0.681
\/+0.670
Neg logit contributions
 Rue-0.684
yss-0.663
 Jung-0.618
nir-0.595
Tags-0.587
Token the
Token ID262
Feature activation+9.26e-01

Pos logit contributions
sbm+1.016
bro+0.976
Cub+0.924
worth+0.873
\/+0.860
Neg logit contributions
 Rue-0.954
yss-0.927
 Jung-0.864
nir-0.837
Tags-0.824
Token two
Token ID734
Feature activation-7.79e-01

Pos logit contributions
sbm+0.712
bro+0.681
Cub+0.647
worth+0.612
\/+0.603
Neg logit contributions
 Rue-0.676
yss-0.654
 Jung-0.611
nir-0.593
Tags-0.585
Token
Token ID250
Feature activation+6.99e-01

Pos logit contributions
sbm+0.246
bro+0.234
Cub+0.220
worth+0.208
\/+0.204
Neg logit contributions
 Rue-0.302
yss-0.293
 Jung-0.277
nir-0.269
Tags-0.267
Tokenet
Token ID316
Feature activation+9.89e-01

Pos logit contributions
sbm+0.492
bro+0.473
Cub+0.450
worth+0.427
\/+0.415
Neg logit contributions
 Rue-0.555
yss-0.537
 Jung-0.510
nir-0.489
 refriger-0.488
Tokenernal
Token ID35220
Feature activation-2.93e-01

Pos logit contributions
sbm+0.766
bro+0.733
Cub+0.696
worth+0.663
\/+0.650
Neg logit contributions
 Rue-0.717
yss-0.696
 Jung-0.654
nir-0.626
Tags-0.624
Token and
Token ID290
Feature activation+3.45e-01

Pos logit contributions
 Rue+0.179
yss+0.174
 Jung+0.160
nir+0.154
Tags+0.153
Neg logit contributions
sbm-0.260
bro-0.249
Cub-0.240
worth-0.230
\/-0.228
Token und
Token ID3318
Feature activation-1.44e-01

Pos logit contributions
sbm+0.252
bro+0.241
Cub+0.228
worth+0.217
\/+0.213
Neg logit contributions
 Rue-0.265
yss-0.256
 Jung-0.241
nir-0.233
Tags-0.231
Tokeniv
Token ID452
Feature activation+3.50e+00

Pos logit contributions
 Rue+0.149
yss+0.145
 Jung+0.139
nir+0.136
Tags+0.136
Neg logit contributions
sbm-0.068
bro-0.063
Cub-0.057
worth-0.053
\/-0.050
Tokenided
Token ID1384
Feature activation-7.60e-01

Pos logit contributions
sbm+2.553
bro+2.516
Cub+2.356
worth+2.294
\/+2.278
Neg logit contributions
 Rue-2.618
yss-2.471
 Jung-2.370
nir-2.284
Tags-2.261
Token capital
Token ID3139
Feature activation-7.24e-01

Pos logit contributions
 Rue+0.426
yss+0.410
 Jung+0.375
nir+0.358
Tags+0.355
Neg logit contributions
sbm-0.714
bro-0.686
Cub-0.661
worth-0.635
\/-0.628
Token
Token ID447
Feature activation-1.05e+00

Pos logit contributions
 Rue+0.535
yss+0.516
 Jung+0.486
nir+0.468
Tags+0.464
Neg logit contributions
sbm-0.554
bro-0.527
Cub-0.502
worth-0.476
\/-0.467
Token
Token ID251
Feature activation-3.83e-01

Pos logit contributions
 Rue+0.801
yss+0.773
 Jung+0.730
nir+0.702
Tags+0.698
Neg logit contributions
sbm-0.782
bro-0.742
Cub-0.706
worth-0.667
\/-0.653
Token and
Token ID290
Feature activation-1.98e-01

Pos logit contributions
 Rue+0.287
yss+0.277
 Jung+0.261
nir+0.252
Tags+0.250
Neg logit contributions
sbm-0.289
bro-0.275
Cub-0.261
worth-0.248
\/-0.242
Token NY
Token ID6645
Feature activation-3.85e-01

Pos logit contributions
sbm+1.299
bro+1.263
Cub+1.190
worth+1.153
\/+1.129
Neg logit contributions
 Rue-1.187
yss-1.165
nir-1.080
 Jung-1.075
Tags-1.053
Token :
Token ID1058
Feature activation+1.05e+00

Pos logit contributions
 Rue+0.325
yss+0.314
 Jung+0.299
nir+0.289
Tags+0.287
Neg logit contributions
sbm-0.255
bro-0.240
Cub-0.227
worth-0.213
\/-0.208
Token Worth
Token ID22301
Feature activation+1.40e+00

Pos logit contributions
sbm+0.762
bro+0.728
Cub+0.692
worth+0.662
\/+0.645
Neg logit contributions
 Rue-0.796
yss-0.784
nir-0.726
 Jung-0.721
Tags-0.707
Token Publishers
Token ID43403
Feature activation+1.05e+00

Pos logit contributions
sbm+1.162
bro+1.124
Cub+1.072
worth+1.033
\/+1.004
Neg logit contributions
 Rue-0.922
yss-0.897
 Jung-0.832
nir-0.805
Tags-0.788
Token.
Token ID764
Feature activation+1.06e+00

Pos logit contributions
sbm+0.584
bro+0.551
Cub+0.514
worth+0.483
\/+0.465
Neg logit contributions
 Rue-0.981
yss-0.961
 Jung-0.910
nir-0.893
Tags-0.885
Token
Token ID198
Feature activation+3.48e+00

Pos logit contributions
sbm+0.799
bro+0.759
Cub+0.723
worth+0.685
\/+0.670
Neg logit contributions
 Rue-0.791
yss-0.764
 Jung-0.720
nir-0.694
Tags-0.688
Token
Token ID198
Feature activation+3.12e+00

Pos logit contributions
sbm+2.286
bro+2.228
Cub+2.091
worth+1.988
\/+1.955
Neg logit contributions
yss-2.867
 Rue-2.847
 Jung-2.595
nir-2.588
 refriger-2.566
TokenGoogle
Token ID11708
Feature activation+1.37e+00

Pos logit contributions
sbm+1.931
bro+1.852
Cub+1.769
worth+1.648
\/+1.587
Neg logit contributions
 Rue-2.692
yss-2.643
 Jung-2.497
 refriger-2.438
nir-2.407
Token Scholar
Token ID11713
Feature activation+9.57e-01

Pos logit contributions
sbm+0.892
bro+0.843
Cub+0.797
worth+0.749
\/+0.740
Neg logit contributions
 Rue-1.157
yss-1.150
 Jung-1.055
nir-1.047
 refriger-1.033
Token
Token ID198
Feature activation+2.50e+00

Pos logit contributions
sbm+0.741
bro+0.703
Cub+0.671
worth+0.637
\/+0.625
Neg logit contributions
 Rue-0.691
yss-0.672
 Jung-0.628
nir-0.609
Tags-0.602
Token
Token ID198
Feature activation+2.22e+00

Pos logit contributions
sbm+1.686
bro+1.626
Cub+1.536
worth+1.461
\/+1.435
Neg logit contributions
yss-2.018
 Rue-2.012
 Jung-1.836
nir-1.822
 refriger-1.800
Token just
Token ID655
Feature activation-6.45e-01

Pos logit contributions
 Rue+0.092
yss+0.090
 Jung+0.083
nir+0.081
Tags+0.080
Neg logit contributions
sbm-0.095
bro-0.091
Cub-0.086
worth-0.082
\/-0.080
Token two
Token ID734
Feature activation-4.99e-01

Pos logit contributions
 Rue+0.485
yss+0.469
 Jung+0.440
nir+0.425
Tags+0.422
Neg logit contributions
sbm-0.483
bro-0.461
Cub-0.437
worth-0.415
\/-0.405
Token guys
Token ID3730
Feature activation-4.20e-01

Pos logit contributions
 Rue+0.356
yss+0.345
 Jung+0.321
nir+0.312
Tags+0.307
Neg logit contributions
sbm-0.389
bro-0.374
Cub-0.356
worth-0.338
\/-0.331
Token --
Token ID1377
Feature activation+9.72e-01

Pos logit contributions
 Rue+0.325
yss+0.316
 Jung+0.296
nir+0.288
Tags+0.285
Neg logit contributions
sbm-0.303
bro-0.290
Cub-0.274
worth-0.260
\/-0.254
Token I
Token ID314
Feature activation+1.95e-01

Pos logit contributions
sbm+0.700
bro+0.670
Cub+0.633
worth+0.602
\/+0.583
Neg logit contributions
 Rue-0.752
yss-0.725
 Jung-0.681
Tags-0.663
nir-0.663
Token mean
Token ID1612
Feature activation+3.46e+00

Pos logit contributions
sbm+0.150
bro+0.147
Cub+0.138
worth+0.132
EEE+0.130
Neg logit contributions
 Rue-0.141
yss-0.138
 Jung-0.127
nir-0.123
Tags-0.123
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
sbm+2.456
bro+2.412
Cub+2.250
worth+2.180
\/+2.089
Neg logit contributions
 Rue-2.577
yss-2.492
Tags-2.306
nir-2.298
 Jung-2.290
Token that
Token ID326
Feature activation+1.06e+00

Pos logit contributions
sbm+1.379
bro+1.324
Cub+1.242
worth+1.196
\/+1.145
Neg logit contributions
 Rue-1.520
yss-1.474
 Jung-1.363
Tags-1.360
nir-1.357
Token's
Token ID338
Feature activation-1.09e+00

Pos logit contributions
sbm+0.852
bro+0.836
Cub+0.796
worth+0.755
\/+0.737
Neg logit contributions
 Rue-0.711
yss-0.696
 Jung-0.631
nir-0.616
Tags-0.616
Token the
Token ID262
Feature activation-8.88e-02

Pos logit contributions
 Rue+0.841
yss+0.813
 Jung+0.763
nir+0.740
Tags+0.735
Neg logit contributions
sbm-0.799
bro-0.763
Cub-0.722
worth-0.685
\/-0.666
Token old
Token ID1468
Feature activation-1.03e+00

Pos logit contributions
 Rue+0.062
yss+0.060
 Jung+0.056
nir+0.054
Tags+0.054
Neg logit contributions
sbm-0.071
bro-0.068
Cub-0.065
worth-0.062
\/-0.061
Token to
Token ID284
Feature activation+3.01e-02

Pos logit contributions
sbm+0.113
bro+0.108
Cub+0.103
worth+0.098
\/+0.096
Neg logit contributions
 Rue-0.088
yss-0.084
 Jung-0.079
nir-0.075
Tags-0.075
Token disrupt
Token ID10114
Feature activation+3.89e-01

Pos logit contributions
sbm+0.025
bro+0.024
Cub+0.023
worth+0.022
\/+0.021
Neg logit contributions
 Rue-0.020
yss-0.019
 Jung-0.018
nir-0.017
Tags-0.017
Token Democratic
Token ID4390
Feature activation-1.63e+00

Pos logit contributions
sbm+0.301
bro+0.291
Cub+0.275
worth+0.261
\/+0.256
Neg logit contributions
 Rue-0.280
yss-0.271
 Jung-0.254
nir-0.245
Tags-0.242
Token front
Token ID2166
Feature activation-2.26e-01

Pos logit contributions
 Rue+1.161
yss+1.112
 Jung+1.053
nir+1.004
Tags+1.001
Neg logit contributions
sbm-1.294
bro-1.225
Cub-1.173
worth-1.109
\/-1.088
Token-
Token ID12
Feature activation-1.23e+00

Pos logit contributions
 Rue+0.171
yss+0.165
 Jung+0.155
nir+0.150
Tags+0.148
Neg logit contributions
sbm-0.170
bro-0.161
Cub-0.153
worth-0.145
\/-0.142
Tokenrunner
Token ID16737
Feature activation-4.42e+00

Pos logit contributions
 Rue+1.023
yss+0.992
 Jung+0.941
nir+0.908
Tags+0.904
Neg logit contributions
sbm-0.826
bro-0.783
Cub-0.736
worth-0.693
\/-0.676
Token Hillary
Token ID5073
Feature activation+4.75e-01

Pos logit contributions
 Rue+2.699
yss+2.560
 Jung+2.412
nir+2.267
Tags+2.258
Neg logit contributions
sbm-3.968
bro-3.767
Cub-3.629
worth-3.459
\/-3.407
Token Rodham
Token ID41848
Feature activation+1.15e+00

Pos logit contributions
sbm+0.332
bro+0.318
Cub+0.298
worth+0.283
\/+0.277
Neg logit contributions
 Rue-0.378
yss-0.370
 Jung-0.345
nir-0.339
Tags-0.335
Token Clinton
Token ID2605
Feature activation+5.76e-01

Pos logit contributions
sbm+0.804
bro+0.765
Cub+0.717
worth+0.684
\/+0.665
Neg logit contributions
 Rue-0.921
yss-0.899
 Jung-0.842
nir-0.822
Tags-0.816
Token's
Token ID338
Feature activation+2.20e-01

Pos logit contributions
sbm+0.444
bro+0.428
Cub+0.404
worth+0.386
\/+0.377
Neg logit contributions
 Rue-0.419
yss-0.406
 Jung-0.378
nir-0.368
Tags-0.364
Token path
Token ID3108
Feature activation+3.11e-01

Pos logit contributions
sbm+0.174
bro+0.168
Cub+0.160
worth+0.152
\/+0.149
Neg logit contributions
 Rue-0.155
yss-0.150
 Jung-0.140
nir-0.135
Tags-0.134
Token includes
Token ID3407
Feature activation+7.19e-01

Pos logit contributions
 Rue+0.939
yss+0.911
 Jung+0.853
nir+0.824
Tags+0.813
Neg logit contributions
sbm-0.956
bro-0.915
Cub-0.868
worth-0.824
\/-0.811
Token the
Token ID262
Feature activation-7.22e-02

Pos logit contributions
sbm+0.543
bro+0.517
Cub+0.489
worth+0.467
\/+0.459
Neg logit contributions
 Rue-0.528
yss-0.518
 Jung-0.481
nir-0.472
Tags-0.461
Token Walker
Token ID10120
Feature activation+6.03e-01

Pos logit contributions
 Rue+0.049
yss+0.048
 Jung+0.044
nir+0.043
Tags+0.042
Neg logit contributions
sbm-0.059
bro-0.057
Cub-0.054
worth-0.051
\/-0.051
Token-
Token ID12
Feature activation-7.07e-01

Pos logit contributions
sbm+0.480
bro+0.466
Cub+0.442
worth+0.425
\/+0.414
Neg logit contributions
 Rue-0.417
yss-0.406
 Jung-0.376
nir-0.368
Tags-0.365
Tokenover
Token ID2502
Feature activation-9.08e-01

Pos logit contributions
 Rue+0.566
yss+0.549
 Jung+0.519
nir+0.501
Tags+0.496
Neg logit contributions
sbm-0.496
bro-0.473
Cub-0.448
worth-0.423
\/-0.411
Tokenrun
Token ID5143
Feature activation-4.41e+00

Pos logit contributions
 Rue+0.673
yss+0.655
 Jung+0.611
nir+0.592
Tags+0.589
Neg logit contributions
sbm-0.689
bro-0.663
Cub-0.623
worth-0.599
\/-0.584
Token Cell
Token ID12440
Feature activation-2.02e-01

Pos logit contributions
 Rue+3.057
yss+2.904
 Jung+2.756
nir+2.617
 refriger+2.612
Neg logit contributions
sbm-3.578
bro-3.389
Cub-3.254
worth-3.074
\/-3.006
Token Block
Token ID9726
Feature activation+5.88e-01

Pos logit contributions
 Rue+0.144
yss+0.140
 Jung+0.130
nir+0.126
Tags+0.125
Neg logit contributions
sbm-0.159
bro-0.153
Cub-0.145
worth-0.139
\/-0.135
Token D
Token ID360
Feature activation-4.08e-01

Pos logit contributions
sbm+0.455
bro+0.439
Cub+0.416
worth+0.400
\/+0.388
Neg logit contributions
 Rue-0.424
yss-0.414
 Jung-0.383
nir-0.374
Tags-0.369
Token and
Token ID290
Feature activation-6.33e-01

Pos logit contributions
 Rue+0.331
yss+0.322
 Jung+0.302
nir+0.294
Tags+0.293
Neg logit contributions
sbm-0.282
bro-0.270
Cub-0.254
worth-0.238
\/-0.233
Token a
Token ID257
Feature activation-4.79e-01

Pos logit contributions
 Rue+0.448
yss+0.436
 Jung+0.405
nir+0.393
Tags+0.389
Neg logit contributions
sbm-0.500
bro-0.477
Cub-0.455
worth-0.432
\/-0.424
Token cases
Token ID2663
Feature activation-2.05e+00

Pos logit contributions
sbm+0.066
bro+0.064
Cub+0.060
worth+0.058
\/+0.057
Neg logit contributions
 Rue-0.057
yss-0.055
 Jung-0.051
nir-0.050
Tags-0.049
Token,
Token ID11
Feature activation-9.04e-01

Pos logit contributions
 Rue+1.535
yss+1.478
 Jung+1.397
nir+1.342
Tags+1.333
Neg logit contributions
sbm-1.552
bro-1.471
Cub-1.402
worth-1.326
\/-1.298
Token since
Token ID1201
Feature activation-5.22e-02

Pos logit contributions
 Rue+0.759
yss+0.734
 Jung+0.698
nir+0.673
Tags+0.670
Neg logit contributions
sbm-0.602
bro-0.567
Cub-0.536
worth-0.502
\/-0.491
Token Dartmouth
Token ID47888
Feature activation+6.34e-01

Pos logit contributions
 Rue+0.038
yss+0.037
 Jung+0.034
nir+0.033
Tags+0.033
Neg logit contributions
sbm-0.040
bro-0.039
Cub-0.037
worth-0.035
\/-0.034
Token College
Token ID5535
Feature activation-6.88e-01

Pos logit contributions
sbm+0.519
bro+0.499
Cub+0.474
worth+0.453
\/+0.444
Neg logit contributions
 Rue-0.431
yss-0.418
 Jung-0.388
nir-0.375
Tags-0.371
Token v
Token ID410
Feature activation-4.28e+00

Pos logit contributions
 Rue+0.477
yss+0.461
 Jung+0.431
nir+0.414
Tags+0.411
Neg logit contributions
sbm-0.555
bro-0.532
Cub-0.507
worth-0.482
\/-0.474
Token.
Token ID13
Feature activation-7.68e-01

Pos logit contributions
 Rue+2.922
yss+2.664
 Jung+2.636
Tags+2.461
nir+2.403
Neg logit contributions
sbm-3.557
bro-3.345
Cub-3.211
senal-3.134
worth-3.035
Token Woodward
Token ID40782
Feature activation+2.85e-01

Pos logit contributions
 Rue+0.545
yss+0.531
 Jung+0.494
nir+0.479
Tags+0.474
Neg logit contributions
sbm-0.605
bro-0.577
Cub-0.550
worth-0.523
\/-0.512
Token in
Token ID287
Feature activation-1.90e-01

Pos logit contributions
sbm+0.226
bro+0.217
Cub+0.206
worth+0.197
\/+0.192
Neg logit contributions
 Rue-0.200
yss-0.194
 Jung-0.181
nir-0.175
Tags-0.173
Token 18
Token ID1248
Feature activation-4.55e-02

Pos logit contributions
 Rue+0.150
yss+0.148
 Jung+0.138
nir+0.134
Tags+0.134
Neg logit contributions
sbm-0.132
bro-0.127
Cub-0.120
worth-0.114
\/-0.111
Token19
Token ID1129
Feature activation+4.16e-01

Pos logit contributions
 Rue+0.040
yss+0.039
 Jung+0.037
nir+0.036
Tags+0.036
Neg logit contributions
sbm-0.028
bro-0.026
Cub-0.025
worth-0.023
\/-0.023
Token]
Token ID60
Feature activation-7.48e-01

Pos logit contributions
sbm+0.443
bro+0.425
Cub+0.404
worth+0.384
\/+0.378
Neg logit contributions
 Rue-0.416
yss-0.402
 Jung-0.377
nir-0.364
Tags-0.360
Tokense
Token ID325
Feature activation-1.01e+00

Pos logit contributions
 Rue+0.539
yss+0.518
 Jung+0.488
nir+0.468
Tags+0.465
Neg logit contributions
sbm-0.587
bro-0.559
Cub-0.533
worth-0.505
\/-0.495
Token[
Token ID58
Feature activation+3.57e-01

Pos logit contributions
 Rue+0.798
yss+0.771
 Jung+0.728
nir+0.702
Tags+0.699
Neg logit contributions
sbm-0.727
bro-0.685
Cub-0.653
worth-0.615
\/-0.599
Tokent
Token ID83
Feature activation-1.07e+00

Pos logit contributions
sbm+0.244
bro+0.232
Cub+0.218
worth+0.206
\/+0.202
Neg logit contributions
 Rue-0.293
yss-0.283
 Jung-0.269
nir-0.259
Tags-0.257
Token]
Token ID60
Feature activation-8.86e-01

Pos logit contributions
 Rue+0.811
yss+0.782
 Jung+0.738
nir+0.710
Tags+0.706
Neg logit contributions
sbm-0.802
bro-0.762
Cub-0.724
worth-0.685
\/-0.671
Token {
Token ID1391
Feature activation-4.09e+00

Pos logit contributions
 Rue+0.669
yss+0.645
 Jung+0.609
nir+0.585
Tags+0.582
Neg logit contributions
sbm-0.664
bro-0.631
Cub-0.600
worth-0.568
\/-0.556
Tokenoptions
Token ID25811
Feature activation-1.35e+00

Pos logit contributions
 Rue+3.025
yss+2.909
 Jung+2.747
Tags+2.661
nir+2.638
Neg logit contributions
sbm-3.109
bro-2.922
Cub-2.798
worth-2.636
��極-2.575
Token}
Token ID92
Feature activation-1.66e+00

Pos logit contributions
 Rue+1.393
yss+1.356
 Jung+1.302
nir+1.266
Tags+1.261
Neg logit contributions
sbm-0.633
bro-0.580
Cub-0.535
worth-0.484
\/-0.465
Token:[
Token ID33250
Feature activation+7.27e-01

Pos logit contributions
 Rue+1.180
yss+1.137
 Jung+1.069
nir+1.025
Tags+1.017
Neg logit contributions
sbm-1.315
bro-1.253
Cub-1.195
worth-1.134
\/-1.113
Tokentext
Token ID5239
Feature activation-1.82e-01

Pos logit contributions
sbm+0.524
bro+0.499
Cub+0.472
worth+0.448
\/+0.440
Neg logit contributions
 Rue-0.568
yss-0.548
 Jung-0.519
nir-0.499
 refriger-0.495
Token]
Token ID60
Feature activation-1.51e+00

Pos logit contributions
 Rue+0.132
yss+0.127
 Jung+0.120
nir+0.115
Tags+0.114
Neg logit contributions
sbm-0.141
bro-0.136
Cub-0.129
worth-0.122
\/-0.120
Tokens
Token ID82
Feature activation+2.21e-01

Pos logit contributions
sbm+0.265
bro+0.250
Cub+0.237
worth+0.222
\/+0.217
Neg logit contributions
 Rue-0.322
yss-0.311
 Jung-0.296
nir-0.285
Tags-0.283
TokenFormat
Token ID26227
Feature activation-1.24e+00

Pos logit contributions
sbm+0.177
bro+0.169
Cub+0.161
worth+0.153
\/+0.150
Neg logit contributions
 Rue-0.155
yss-0.149
 Jung-0.140
nir-0.134
Tags-0.133
Token)
Token ID8
Feature activation-4.37e-01

Pos logit contributions
 Rue+0.871
yss+0.840
 Jung+0.790
nir+0.757
Tags+0.748
Neg logit contributions
sbm-0.988
bro-0.944
Cub-0.902
worth-0.854
\/-0.838
Token }
Token ID1782
Feature activation-8.83e-01

Pos logit contributions
 Rue+0.398
yss+0.387
 Jung+0.368
nir+0.358
Tags+0.355
Neg logit contributions
sbm-0.258
bro-0.244
Cub-0.227
worth-0.212
\/-0.206
Token else
Token ID2073
Feature activation+1.45e+00

Pos logit contributions
 Rue+0.823
yss+0.801
 Jung+0.764
nir+0.742
Tags+0.737
Neg logit contributions
sbm-0.503
bro-0.472
Cub-0.440
worth-0.407
\/-0.396
Token {
Token ID1391
Feature activation-4.06e+00

Pos logit contributions
sbm+1.004
bro+0.964
Cub+0.903
worth+0.853
\/+0.830
Neg logit contributions
 Rue-1.159
yss-1.128
 Jung-1.069
nir-1.027
Tags-1.016
Token $
Token ID720
Feature activation+2.56e-01

Pos logit contributions
 Rue+2.643
yss+2.512
 Jung+2.363
Tags+2.266
nir+2.248
Neg logit contributions
sbm-3.455
bro-3.250
Cub-3.141
worth-2.996
\/-2.933
Tokenfont
Token ID10331
Feature activation+7.08e-01

Pos logit contributions
sbm+0.176
bro+0.166
Cub+0.157
worth+0.148
\/+0.144
Neg logit contributions
 Rue-0.208
yss-0.202
 Jung-0.191
nir-0.185
Tags-0.184
Token2
Token ID17
Feature activation+1.79e-01

Pos logit contributions
sbm+0.532
bro+0.506
Cub+0.481
worth+0.455
\/+0.445
Neg logit contributions
 Rue-0.533
yss-0.514
 Jung-0.485
nir-0.466
Tags-0.462
Token =
Token ID796
Feature activation-9.32e-01

Pos logit contributions
sbm+0.129
bro+0.123
Cub+0.116
worth+0.110
\/+0.107
Neg logit contributions
 Rue-0.141
yss-0.137
 Jung-0.129
nir-0.124
Tags-0.123
Token New
Token ID968
Feature activation+1.18e+00

Pos logit contributions
 Rue+0.604
yss+0.579
 Jung+0.541
nir+0.517
Tags+0.513
Neg logit contributions
sbm-0.797
bro-0.762
Cub-0.730
worth-0.695
\/-0.683
Token Width
Token ID38807
Feature activation-1.01e+00

Pos logit contributions
sbm+0.865
bro+0.828
Cub+0.788
worth+0.743
\/+0.729
Neg logit contributions
 Rue-0.879
yss-0.850
 Jung-0.799
nir-0.769
Tags-0.761
Token,
Token ID11
Feature activation+5.97e-01

Pos logit contributions
 Rue+0.726
yss+0.697
 Jung+0.657
nir+0.629
Tags+0.626
Neg logit contributions
sbm-0.799
bro-0.758
Cub-0.723
worth-0.687
\/-0.672
TokenHeight
Token ID23106
Feature activation+9.65e-01

Pos logit contributions
sbm+0.562
bro+0.542
Cub+0.523
worth+0.499
\/+0.493
Neg logit contributions
 Rue-0.331
yss-0.318
 Jung-0.292
nir-0.279
Tags-0.274
Token }
Token ID1782
Feature activation-6.29e-01

Pos logit contributions
sbm+0.742
bro+0.710
Cub+0.680
worth+0.641
\/+0.630
Neg logit contributions
 Rue-0.701
yss-0.680
 Jung-0.639
nir-0.617
Tags-0.606
Token else
Token ID2073
Feature activation+1.59e+00

Pos logit contributions
 Rue+0.431
yss+0.417
 Jung+0.390
nir+0.375
Tags+0.371
Neg logit contributions
sbm-0.511
bro-0.491
Cub-0.466
worth-0.444
\/-0.437
Token {
Token ID1391
Feature activation-4.04e+00

Pos logit contributions
sbm+1.101
bro+1.061
Cub+0.988
worth+0.937
\/+0.910
Neg logit contributions
 Rue-1.282
yss-1.251
 Jung-1.182
nir-1.139
Tags-1.128
Token Write
Token ID19430
Feature activation-5.89e-01

Pos logit contributions
 Rue+2.718
yss+2.585
 Jung+2.443
nir+2.328
Tags+2.321
Neg logit contributions
sbm-3.348
bro-3.164
Cub-3.044
worth-2.899
\/-2.843
Token-
Token ID12
Feature activation+1.22e+00

Pos logit contributions
 Rue+0.431
yss+0.413
 Jung+0.390
Tags+0.374
nir+0.374
Neg logit contributions
sbm-0.458
bro-0.431
Cub-0.412
worth-0.391
EEE-0.380
TokenWarning
Token ID20361
Feature activation+1.53e+00

Pos logit contributions
sbm+0.801
bro+0.769
Cub+0.724
worth+0.674
\/+0.661
Neg logit contributions
 Rue-1.031
yss-1.007
 Jung-0.950
 refriger-0.911
nir-0.908
Token -
Token ID532
Feature activation+3.48e-01

Pos logit contributions
sbm+1.040
bro+0.999
Cub+0.948
worth+0.878
\/+0.873
Neg logit contributions
 Rue-1.246
yss-1.224
 Jung-1.138
nir-1.113
ukong-1.096
TokenMessage
Token ID12837
Feature activation+6.88e-01

Pos logit contributions
sbm+0.235
bro+0.222
Cub+0.210
worth+0.197
\/+0.193
Neg logit contributions
 Rue-0.288
yss-0.279
 Jung-0.265
nir-0.256
Tags-0.254
Token Want
Token ID16168
Feature activation-1.31e-01

Pos logit contributions
sbm+0.152
bro+0.145
Cub+0.137
worth+0.130
\/+0.128
Neg logit contributions
 Rue-0.166
yss-0.162
 Jung-0.152
nir-0.147
Tags-0.146
Token Some
Token ID2773
Feature activation-1.51e+00

Pos logit contributions
 Rue+0.091
yss+0.088
 Jung+0.083
nir+0.079
Tags+0.079
Neg logit contributions
sbm-0.105
bro-0.100
Cub-0.096
worth-0.091
\/-0.089
Token Pictures
Token ID20051
Feature activation+3.33e-01

Pos logit contributions
 Rue+1.115
yss+1.071
 Jung+1.014
nir+0.971
Tags+0.967
Neg logit contributions
sbm-1.158
bro-1.099
Cub-1.046
worth-0.990
\/-0.969
Token of
Token ID286
Feature activation-9.34e-01

Pos logit contributions
sbm+0.252
bro+0.242
Cub+0.231
worth+0.219
\/+0.215
Neg logit contributions
 Rue-0.248
yss-0.240
 Jung-0.224
nir-0.217
Tags-0.215
Token That
Token ID1320
Feature activation-9.61e-01

Pos logit contributions
 Rue+0.669
yss+0.644
 Jung+0.606
nir+0.581
Tags+0.577
Neg logit contributions
sbm-0.737
bro-0.701
Cub-0.669
worth-0.634
\/-0.622
Token Corner
Token ID26212
Feature activation-3.99e+00

Pos logit contributions
 Rue+0.703
yss+0.676
 Jung+0.638
nir+0.612
Tags+0.608
Neg logit contributions
sbm-0.743
bro-0.706
Cub-0.673
worth-0.637
\/-0.624
Token Vari
Token ID15965
Feature activation-2.66e+00

Pos logit contributions
 Rue+2.927
yss+2.786
 Jung+2.662
nir+2.540
Tags+2.511
Neg logit contributions
sbm-3.080
bro-2.898
Cub-2.756
worth-2.603
EEE-2.559
Tokenation
Token ID341
Feature activation-1.74e+00

Pos logit contributions
 Rue+1.642
yss+1.559
 Jung+1.462
nir+1.398
Tags+1.377
Neg logit contributions
sbm-2.356
bro-2.250
Cub-2.157
worth-2.057
\/-2.020
Token,
Token ID11
Feature activation-5.18e-01

Pos logit contributions
 Rue+1.318
yss+1.275
 Jung+1.199
nir+1.158
Tags+1.149
Neg logit contributions
sbm-1.293
bro-1.229
Cub-1.171
worth-1.107
\/-1.084
Token Don
Token ID2094
Feature activation-1.85e+00

Pos logit contributions
 Rue+0.365
yss+0.353
 Jung+0.330
nir+0.318
Tags+0.316
Neg logit contributions
sbm-0.412
bro-0.394
Cub-0.376
worth-0.357
\/-0.350
Token
Token ID447
Feature activation-5.32e-01

Pos logit contributions
 Rue+1.314
yss+1.261
 Jung+1.189
nir+1.139
Tags+1.132
Neg logit contributions
sbm-1.470
bro-1.400
Cub-1.336
worth-1.267
\/-1.241
Token in
Token ID287
Feature activation-4.55e-01

Pos logit contributions
 Rue+0.333
yss+0.326
 Jung+0.303
nir+0.294
Tags+0.292
Neg logit contributions
sbm-0.394
bro-0.378
Cub-0.360
worth-0.347
\/-0.338
Token Bram
Token ID35315
Feature activation-7.80e-01

Pos logit contributions
 Rue+0.314
yss+0.308
 Jung+0.285
nir+0.277
Tags+0.276
Neg logit contributions
sbm-0.362
bro-0.348
Cub-0.331
worth-0.317
\/-0.310
Tokenpton
Token ID10972
Feature activation+7.61e-02

Pos logit contributions
 Rue+0.540
yss+0.517
 Jung+0.487
nir+0.465
Tags+0.461
Neg logit contributions
sbm-0.635
bro-0.598
Cub-0.575
worth-0.544
EEE-0.536
Token to
Token ID284
Feature activation+2.81e-01

Pos logit contributions
sbm+0.062
bro+0.059
Cub+0.056
worth+0.054
\/+0.053
Neg logit contributions
 Rue-0.052
yss-0.051
 Jung-0.047
nir-0.046
Tags-0.045
Token the
Token ID262
Feature activation+2.76e-01

Pos logit contributions
sbm+0.219
bro+0.210
Cub+0.200
worth+0.190
\/+0.186
Neg logit contributions
 Rue-0.198
yss-0.194
 Jung-0.180
nir-0.176
Tags-0.175
Token shore
Token ID15191
Feature activation-3.96e+00

Pos logit contributions
sbm+0.220
bro+0.210
Cub+0.201
worth+0.191
\/+0.187
Neg logit contributions
 Rue-0.191
yss-0.186
 Jung-0.173
nir-0.169
Tags-0.168
Token of
Token ID286
Feature activation+2.36e-01

Pos logit contributions
 Rue+2.784
yss+2.667
 Jung+2.512
nir+2.396
Tags+2.390
Neg logit contributions
sbm-3.186
bro-3.010
Cub-2.889
worth-2.716
\/-2.676
Token Lake
Token ID6233
Feature activation-3.80e-01

Pos logit contributions
sbm+0.160
bro+0.153
Cub+0.144
worth+0.137
\/+0.133
Neg logit contributions
 Rue-0.189
yss-0.186
 Jung-0.175
nir-0.171
Tags-0.171
Token Ontario
Token ID10553
Feature activation-1.59e+00

Pos logit contributions
 Rue+0.240
yss+0.232
 Jung+0.214
nir+0.209
Tags+0.208
Neg logit contributions
sbm-0.329
bro-0.317
Cub-0.300
worth-0.293
\/-0.284
Token south
Token ID5366
Feature activation-9.96e-01

Pos logit contributions
 Rue+1.141
yss+1.105
 Jung+1.035
nir+0.999
Tags+0.992
Neg logit contributions
sbm-1.247
bro-1.193
Cub-1.134
worth-1.082
\/-1.061
Token of
Token ID286
Feature activation-5.50e-01

Pos logit contributions
 Rue+0.658
yss+0.631
 Jung+0.591
nir+0.564
Tags+0.560
Neg logit contributions
sbm-0.840
bro-0.802
Cub-0.768
worth-0.730
\/-0.717
Tokenex
Token ID1069
Feature activation-1.08e-01

Pos logit contributions
 Rue+0.914
yss+0.891
 Jung+0.853
nir+0.833
Tags+0.828
Neg logit contributions
sbm-0.442
bro-0.406
Cub-0.377
worth-0.341
\/-0.328
Token:"
Token ID11097
Feature activation-1.09e+00

Pos logit contributions
 Rue+0.088
yss+0.085
 Jung+0.081
nir+0.078
Tags+0.077
Neg logit contributions
sbm-0.074
bro-0.070
Cub-0.066
worth-0.062
\/-0.061
Token [
Token ID685
Feature activation-8.51e-01

Pos logit contributions
 Rue+0.724
yss+0.699
 Jung+0.651
nir+0.625
Tags+0.616
Neg logit contributions
sbm-0.916
bro-0.874
Cub-0.836
worth-0.798
\/-0.783
Tokenwhite
Token ID11186
Feature activation+8.94e-01

Pos logit contributions
 Rue+0.805
yss+0.782
 Jung+0.747
nir+0.725
Tags+0.724
Neg logit contributions
sbm-0.475
bro-0.441
Cub-0.413
worth-0.380
\/-0.369
Token]
Token ID60
Feature activation-6.06e-01

Pos logit contributions
sbm+0.680
bro+0.656
Cub+0.623
worth+0.591
\/+0.584
Neg logit contributions
 Rue-0.653
yss-0.633
 Jung-0.592
nir-0.573
Tags-0.564
Token optional
Token ID11902
Feature activation-3.82e+00

Pos logit contributions
 Rue+0.365
yss+0.350
 Jung+0.324
nir+0.308
Tags+0.305
Neg logit contributions
sbm-0.546
bro-0.524
Cub-0.502
worth-0.481
\/-0.473
Token white
Token ID2330
Feature activation+2.28e-01

Pos logit contributions
 Rue+2.938
yss+2.809
 Jung+2.685
Tags+2.570
nir+2.555
Neg logit contributions
sbm-2.809
bro-2.649
Cub-2.536
worth-2.379
\/-2.312
Token space
Token ID2272
Feature activation+4.86e-01

Pos logit contributions
sbm+0.234
bro+0.228
Cub+0.220
worth+0.212
\/+0.210
Neg logit contributions
 Rue-0.106
yss-0.102
 Jung-0.090
nir-0.085
Tags-0.083
Token se
Token ID384
Feature activation-1.43e+00

Pos logit contributions
sbm+0.340
bro+0.324
Cub+0.305
worth+0.287
\/+0.286
Neg logit contributions
 Rue-0.386
yss-0.376
 Jung-0.354
nir-0.342
ukong-0.337
Token[
Token ID58
Feature activation+4.27e-01

Pos logit contributions
 Rue+1.014
yss+0.976
 Jung+0.918
nir+0.881
Tags+0.872
Neg logit contributions
sbm-1.136
bro-1.084
Cub-1.033
worth-0.981
\/-0.962
Tokent
Token ID83
Feature activation-5.09e-01

Pos logit contributions
sbm+0.327
bro+0.312
Cub+0.295
worth+0.282
\/+0.278
Neg logit contributions
 Rue-0.314
yss-0.302
 Jung-0.286
nir-0.272
 refriger-0.272
Token
Token ID198
Feature activation+5.48e-01

Pos logit contributions
 Rue+0.777
yss+0.749
 Jung+0.707
nir+0.680
Tags+0.676
Neg logit contributions
sbm-0.776
bro-0.737
Cub-0.702
worth-0.663
\/-0.649
Token
Token ID198
Feature activation+1.47e-01

Pos logit contributions
sbm+0.395
bro+0.378
Cub+0.359
worth+0.340
\/+0.333
Neg logit contributions
 Rue-0.425
yss-0.419
 Jung-0.388
nir-0.377
 refriger-0.373
TokenV
Token ID53
Feature activation-1.21e+00

Pos logit contributions
sbm+0.109
bro+0.104
Cub+0.100
worth+0.093
\/+0.091
Neg logit contributions
 Rue-0.112
yss-0.108
 Jung-0.103
nir-0.098
 refriger-0.097
Tokenil
Token ID346
Feature activation+1.39e+00

Pos logit contributions
 Rue+0.975
yss+0.942
 Jung+0.893
nir+0.861
Tags+0.856
Neg logit contributions
sbm-0.846
bro-0.801
Cub-0.759
worth-0.714
\/-0.698
Tokenma
Token ID2611
Feature activation+2.67e-01

Pos logit contributions
sbm+0.990
bro+0.966
Cub+0.903
worth+0.867
\/+0.838
Neg logit contributions
 Rue-1.081
yss-1.048
 Jung-0.993
Tags-0.953
 refriger-0.948
Token v
Token ID410
Feature activation-3.81e+00

Pos logit contributions
sbm+0.208
bro+0.199
Cub+0.190
worth+0.180
\/+0.176
Neg logit contributions
 Rue-0.192
yss-0.185
 Jung-0.174
nir-0.168
Tags-0.167
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
 Rue+2.736
yss+2.595
 Jung+2.466
nir+2.341
Tags+2.338
Neg logit contributions
sbm-3.023
bro-2.853
Cub-2.721
worth-2.554
\/-2.526
Token Goodell
Token ID41648
Feature activation+4.17e-01

Pos logit contributions
sbm+0.144
bro+0.138
Cub+0.132
worth+0.125
\/+0.123
Neg logit contributions
 Rue-0.130
yss-0.129
 Jung-0.119
nir-0.117
Tags-0.114
Token Def
Token ID2896
Feature activation-1.40e-01

Pos logit contributions
sbm+0.327
bro+0.313
Cub+0.298
worth+0.284
\/+0.277
Neg logit contributions
 Rue-0.297
yss-0.287
 Jung-0.270
nir-0.261
Tags-0.257
Tokenamation
Token ID14755
Feature activation-1.20e+00

Pos logit contributions
 Rue+0.128
yss+0.124
 Jung+0.119
nir+0.114
Tags+0.114
Neg logit contributions
sbm-0.082
bro-0.077
Cub-0.072
worth-0.067
\/-0.066
Token /
Token ID1220
Feature activation+7.82e-01

Pos logit contributions
 Rue+0.781
yss+0.753
 Jung+0.700
nir+0.673
Tags+0.666
Neg logit contributions
sbm-1.018
bro-0.975
Cub-0.931
worth-0.887
\/-0.874
Token]
Token ID60
Feature activation-9.62e-01

Pos logit contributions
 Rue+0.314
yss+0.303
 Jung+0.285
nir+0.274
Tags+0.271
Neg logit contributions
sbm-0.320
bro-0.308
Cub-0.291
worth-0.277
\/-0.273
Token any
Token ID597
Feature activation-8.10e-01

Pos logit contributions
 Rue+0.709
yss+0.683
 Jung+0.644
nir+0.619
Tags+0.613
Neg logit contributions
sbm-0.738
bro-0.702
Cub-0.669
worth-0.633
\/-0.621
Token text
Token ID2420
Feature activation-2.20e-01

Pos logit contributions
 Rue+0.582
yss+0.560
 Jung+0.525
nir+0.505
Tags+0.498
Neg logit contributions
sbm-0.636
bro-0.607
Cub-0.577
worth-0.549
\/-0.541
Token or
Token ID393
Feature activation-1.68e-01

Pos logit contributions
 Rue+0.160
yss+0.155
 Jung+0.145
nir+0.140
Tags+0.138
Neg logit contributions
sbm-0.169
bro-0.162
Cub-0.153
worth-0.146
\/-0.144
Token empty
Token ID6565
Feature activation-1.01e+00

Pos logit contributions
 Rue+0.116
yss+0.112
 Jung+0.105
nir+0.101
Tags+0.099
Neg logit contributions
sbm-0.136
bro-0.130
Cub-0.124
worth-0.117
\/-0.116
Token {
Token ID1391
Feature activation-3.76e+00

Pos logit contributions
 Rue+0.723
yss+0.698
 Jung+0.655
nir+0.631
Tags+0.623
Neg logit contributions
sbm-0.789
bro-0.751
Cub-0.716
worth-0.679
\/-0.668
Tokenwhite
Token ID11186
Feature activation+8.05e-01

Pos logit contributions
 Rue+2.778
yss+2.668
 Jung+2.512
Tags+2.444
nir+2.434
Neg logit contributions
sbm-2.869
bro-2.710
Cub-2.583
worth-2.427
��極-2.366
Token}
Token ID92
Feature activation-1.67e+00

Pos logit contributions
sbm+0.457
bro+0.432
Cub+0.402
worth+0.375
\/+0.367
Neg logit contributions
 Rue-0.748
yss-0.727
 Jung-0.693
nir-0.673
Tags-0.667
Token at
Token ID379
Feature activation-2.78e-01

Pos logit contributions
 Rue+1.205
yss+1.160
 Jung+1.092
nir+1.048
Tags+1.041
Neg logit contributions
sbm-1.314
bro-1.250
Cub-1.192
worth-1.130
\/-1.108
Token least
Token ID1551
Feature activation-4.77e-01

Pos logit contributions
 Rue+0.197
yss+0.189
 Jung+0.177
nir+0.170
Tags+0.168
Neg logit contributions
sbm-0.222
bro-0.212
Cub-0.202
worth-0.192
\/-0.189
Token one
Token ID530
Feature activation+5.14e-01

Pos logit contributions
 Rue+0.345
yss+0.332
 Jung+0.312
nir+0.300
Tags+0.298
Neg logit contributions
sbm-0.373
bro-0.355
Cub-0.338
worth-0.320
\/-0.314
Tokendiv
Token ID7146
Feature activation-8.42e-01

Pos logit contributions
 Rue+1.669
yss+1.613
 Jung+1.533
nir+1.486
Tags+1.476
Neg logit contributions
sbm-1.316
bro-1.235
Cub-1.170
worth-1.095
EEE-1.070
Tokenide
Token ID485
Feature activation-1.09e+00

Pos logit contributions
 Rue+0.601
yss+0.580
 Jung+0.544
nir+0.521
Tags+0.516
Neg logit contributions
sbm-0.666
bro-0.635
Cub-0.606
worth-0.574
\/-0.566
Token(
Token ID7
Feature activation-9.55e-01

Pos logit contributions
 Rue+0.781
yss+0.752
 Jung+0.708
nir+0.680
Tags+0.676
Neg logit contributions
sbm-0.853
bro-0.811
Cub-0.774
worth-0.734
\/-0.719
Token space
Token ID2272
Feature activation+2.14e-01

Pos logit contributions
 Rue+0.780
yss+0.754
 Jung+0.716
nir+0.689
Tags+0.685
Neg logit contributions
sbm-0.658
bro-0.622
Cub-0.589
worth-0.554
\/-0.541
Token )
Token ID1267
Feature activation-1.04e+00

Pos logit contributions
sbm+0.150
bro+0.144
Cub+0.137
worth+0.129
\/+0.127
Neg logit contributions
 Rue-0.171
yss-0.166
 Jung-0.156
nir-0.151
 refriger-0.149
Token {
Token ID1391
Feature activation-3.71e+00

Pos logit contributions
 Rue+0.783
yss+0.756
 Jung+0.713
nir+0.686
Tags+0.681
Neg logit contributions
sbm-0.781
bro-0.742
Cub-0.706
worth-0.667
\/-0.653
Token //
Token ID3373
Feature activation+6.68e-01

Pos logit contributions
 Rue+2.448
yss+2.325
 Jung+2.206
 refriger+2.101
nir+2.098
Neg logit contributions
sbm-3.114
bro-2.944
Cub-2.821
worth-2.717
EEE-2.649
Token 1
Token ID352
Feature activation-8.06e-01

Pos logit contributions
sbm+0.539
bro+0.519
Cub+0.497
worth+0.468
\/+0.459
Neg logit contributions
 Rue-0.462
yss-0.449
 Jung-0.418
nir-0.402
Tags-0.397
Token.
Token ID13
Feature activation-6.96e-01

Pos logit contributions
 Rue+0.566
yss+0.547
 Jung+0.512
nir+0.491
Tags+0.488
Neg logit contributions
sbm-0.646
bro-0.618
Cub-0.592
worth-0.558
\/-0.550
Token Fit
Token ID25048
Feature activation+1.75e+00

Pos logit contributions
 Rue+0.487
yss+0.471
 Jung+0.441
nir+0.424
Tags+0.420
Neg logit contributions
sbm-0.561
bro-0.534
Cub-0.512
worth-0.484
\/-0.475
Token an
Token ID281
Feature activation+4.38e-02

Pos logit contributions
sbm+1.381
bro+1.323
Cub+1.280
worth+1.190
\/+1.173
Neg logit contributions
 Rue-1.233
yss-1.199
 Jung-1.118
nir-1.067
Tags-1.056
Token
Token ID198
Feature activation-5.52e-01

Pos logit contributions
 Rue+0.169
yss+0.164
 Jung+0.154
nir+0.149
Tags+0.147
Neg logit contributions
sbm-0.164
bro-0.156
Cub-0.149
worth-0.141
\/-0.138
TokenAs
Token ID1722
Feature activation-6.35e-01

Pos logit contributions
 Rue+0.432
yss+0.419
 Jung+0.394
nir+0.377
 refriger+0.376
Neg logit contributions
sbm-0.399
bro-0.383
Cub-0.365
worth-0.343
\/-0.335
Token part
Token ID636
Feature activation-8.86e-01

Pos logit contributions
 Rue+0.439
yss+0.423
 Jung+0.395
nir+0.381
Tags+0.377
Neg logit contributions
sbm-0.514
bro-0.493
Cub-0.469
worth-0.448
\/-0.438
Token of
Token ID286
Feature activation-4.92e-01

Pos logit contributions
 Rue+0.587
yss+0.562
 Jung+0.528
nir+0.504
Tags+0.501
Neg logit contributions
sbm-0.746
bro-0.711
Cub-0.681
worth-0.648
\/-0.636
Token that
Token ID326
Feature activation-8.92e-01

Pos logit contributions
 Rue+0.349
yss+0.336
 Jung+0.315
nir+0.303
Tags+0.301
Neg logit contributions
sbm-0.390
bro-0.373
Cub-0.355
worth-0.338
\/-0.331
Token case
Token ID1339
Feature activation-3.69e+00

Pos logit contributions
 Rue+0.676
yss+0.652
 Jung+0.616
nir+0.593
Tags+0.589
Neg logit contributions
sbm-0.666
bro-0.632
Cub-0.601
worth-0.568
\/-0.556
Token,
Token ID11
Feature activation-1.97e+00

Pos logit contributions
 Rue+2.440
yss+2.334
 Jung+2.213
nir+2.097
 refriger+2.088
Neg logit contributions
sbm-3.104
bro-2.932
Cub-2.833
worth-2.678
\/-2.627
Token P
Token ID350
Feature activation-1.51e+00

Pos logit contributions
 Rue+1.312
yss+1.258
 Jung+1.179
nir+1.126
Tags+1.118
Neg logit contributions
sbm-1.655
bro-1.580
Cub-1.512
worth-1.439
\/-1.412
Tokeneder
Token ID5702
Feature activation-1.00e+00

Pos logit contributions
 Rue+1.004
yss+0.966
 Jung+0.906
nir+0.868
Tags+0.860
Neg logit contributions
sbm-1.267
bro-1.204
Cub-1.157
worth-1.096
\/-1.076
Token appeared
Token ID4120
Feature activation-1.20e-01

Pos logit contributions
 Rue+0.746
yss+0.720
 Jung+0.677
nir+0.653
Tags+0.649
Neg logit contributions
sbm-0.762
bro-0.727
Cub-0.691
worth-0.655
\/-0.640
Token before
Token ID878
Feature activation-1.27e-01

Pos logit contributions
 Rue+0.082
yss+0.079
 Jung+0.073
nir+0.071
Tags+0.071
Neg logit contributions
sbm-0.097
bro-0.094
Cub-0.089
worth-0.085
\/-0.083
Token be
Token ID307
Feature activation-2.40e-01

Pos logit contributions
 Rue+0.493
yss+0.479
 Jung+0.447
nir+0.431
Tags+0.428
Neg logit contributions
sbm-0.534
bro-0.513
Cub-0.486
worth-0.463
\/-0.453
Token the
Token ID262
Feature activation-3.45e-01

Pos logit contributions
 Rue+0.171
yss+0.167
 Jung+0.155
nir+0.150
Tags+0.148
Neg logit contributions
sbm-0.188
bro-0.181
Cub-0.172
worth-0.164
\/-0.160
Token equivalent
Token ID7548
Feature activation-6.42e-01

Pos logit contributions
 Rue+0.234
yss+0.229
 Jung+0.211
nir+0.205
Tags+0.202
Neg logit contributions
sbm-0.280
bro-0.269
Cub-0.258
worth-0.245
\/-0.240
Token of
Token ID286
Feature activation-2.23e-01

Pos logit contributions
 Rue+0.423
yss+0.404
 Jung+0.379
nir+0.361
Tags+0.359
Neg logit contributions
sbm-0.544
bro-0.518
Cub-0.496
worth-0.471
\/-0.463
Token Loving
Token ID39202
Feature activation-8.63e-01

Pos logit contributions
 Rue+0.163
yss+0.158
 Jung+0.148
nir+0.143
Tags+0.141
Neg logit contributions
sbm-0.172
bro-0.164
Cub-0.156
worth-0.148
\/-0.145
Token v
Token ID410
Feature activation-3.68e+00

Pos logit contributions
 Rue+0.472
yss+0.450
 Jung+0.414
nir+0.392
Tags+0.387
Neg logit contributions
sbm-0.824
bro-0.793
Cub-0.763
worth-0.732
\/-0.720
Token.
Token ID13
Feature activation+2.35e-02

Pos logit contributions
 Rue+2.542
yss+2.332
 Jung+2.286
Tags+2.158
nir+2.125
Neg logit contributions
sbm-3.039
bro-2.884
Cub-2.731
senal-2.623
worth-2.576
Token Virginia
Token ID6025
Feature activation+7.68e-01

Pos logit contributions
sbm+0.021
bro+0.020
Cub+0.019
worth+0.018
\/+0.018
Neg logit contributions
 Rue-0.015
yss-0.014
 Jung-0.013
nir-0.012
Tags-0.012
Token,
Token ID11
Feature activation+9.24e-02

Pos logit contributions
sbm+0.582
bro+0.562
Cub+0.532
worth+0.508
\/+0.496
Neg logit contributions
 Rue-0.560
yss-0.549
 Jung-0.510
nir-0.495
Tags-0.487
Token which
Token ID543
Feature activation-3.43e-01

Pos logit contributions
sbm+0.071
bro+0.068
Cub+0.065
worth+0.062
\/+0.060
Neg logit contributions
 Rue-0.067
yss-0.066
 Jung-0.061
nir-0.059
Tags-0.059
Token declared
Token ID6875
Feature activation-8.46e-01

Pos logit contributions
 Rue+0.259
yss+0.254
 Jung+0.236
nir+0.230
Tags+0.227
Neg logit contributions
sbm-0.253
bro-0.243
Cub-0.230
worth-0.218
\/-0.212
Token IS
Token ID3180
Feature activation-7.79e-02

Pos logit contributions
 Rue+0.523
yss+0.508
 Jung+0.474
nir+0.458
Tags+0.455
Neg logit contributions
sbm-0.549
bro-0.526
Cub-0.500
worth-0.474
\/-0.468
Token FREE
Token ID17189
Feature activation-1.81e+00

Pos logit contributions
 Rue+0.053
yss+0.052
 Jung+0.047
nir+0.046
Tags+0.046
Neg logit contributions
sbm-0.063
bro-0.061
Cub-0.058
worth-0.056
\/-0.055
Token |
Token ID930
Feature activation+5.37e-01

Pos logit contributions
 Rue+1.267
yss+1.220
 Jung+1.142
nir+1.099
Tags+1.091
Neg logit contributions
sbm-1.455
bro-1.389
Cub-1.326
worth-1.258
\/-1.238
Token NO
Token ID8005
Feature activation-8.26e-01

Pos logit contributions
sbm+0.430
bro+0.411
Cub+0.392
worth+0.371
\/+0.369
Neg logit contributions
 Rue-0.374
yss-0.363
 Jung-0.337
nir-0.330
Tags-0.325
Token FE
Token ID18630
Feature activation-2.87e-01

Pos logit contributions
 Rue+0.550
yss+0.528
 Jung+0.492
nir+0.474
Tags+0.468
Neg logit contributions
sbm-0.692
bro-0.662
Cub-0.632
worth-0.601
\/-0.593
TokenES
Token ID1546
Feature activation-3.67e+00

Pos logit contributions
 Rue+0.213
yss+0.205
 Jung+0.193
nir+0.186
Tags+0.185
Neg logit contributions
sbm-0.219
bro-0.208
Cub-0.198
worth-0.187
\/-0.184
Token |
Token ID930
Feature activation-3.09e-01

Pos logit contributions
 Rue+2.696
yss+2.588
 Jung+2.461
Tags+2.353
nir+2.350
Neg logit contributions
sbm-2.814
bro-2.651
Cub-2.529
worth-2.398
\/-2.328
Token NO
Token ID8005
Feature activation-8.25e-01

Pos logit contributions
 Rue+0.221
yss+0.214
 Jung+0.199
nir+0.194
Tags+0.192
Neg logit contributions
sbm-0.243
bro-0.232
Cub-0.221
worth-0.209
\/-0.207
Token MIN
Token ID20625
Feature activation-4.21e-01

Pos logit contributions
 Rue+0.550
yss+0.532
 Jung+0.491
nir+0.479
Tags+0.470
Neg logit contributions
sbm-0.686
bro-0.659
Cub-0.630
worth-0.597
\/-0.591
TokenIM
Token ID3955
Feature activation-3.42e-01

Pos logit contributions
 Rue+0.320
yss+0.310
 Jung+0.290
nir+0.284
Tags+0.278
Neg logit contributions
sbm-0.312
bro-0.297
Cub-0.284
worth-0.266
\/-0.264
TokenU
Token ID52
Feature activation-1.24e+00

Pos logit contributions
 Rue+0.190
yss+0.180
 Jung+0.166
nir+0.161
Tags+0.156
Neg logit contributions
sbm-0.325
bro-0.313
Cub-0.301
worth-0.287
EEE-0.285
Token
Token ID198
Feature activation+1.14e-01

Pos logit contributions
sbm+0.172
bro+0.165
Cub+0.156
worth+0.148
\/+0.145
Neg logit contributions
 Rue-0.184
yss-0.180
 Jung-0.167
nir-0.163
 refriger-0.160
TokenThe
Token ID464
Feature activation+1.35e-01

Pos logit contributions
sbm+0.086
bro+0.083
Cub+0.079
worth+0.074
\/+0.072
Neg logit contributions
 Rue-0.086
yss-0.082
 Jung-0.078
 refriger-0.074
nir-0.074
Token Icelandic
Token ID41959
Feature activation-4.18e-01

Pos logit contributions
sbm+0.110
bro+0.105
Cub+0.101
worth+0.096
\/+0.094
Neg logit contributions
 Rue-0.093
yss-0.089
 Jung-0.083
nir-0.081
Tags-0.080
Token singer
Token ID14015
Feature activation+6.59e-01

Pos logit contributions
 Rue+0.278
yss+0.268
 Jung+0.249
nir+0.240
Tags+0.238
Neg logit contributions
sbm-0.349
bro-0.335
Cub-0.320
worth-0.305
\/-0.300
Token Bj
Token ID34254
Feature activation-4.00e-01

Pos logit contributions
sbm+0.537
bro+0.517
Cub+0.491
worth+0.469
\/+0.460
Neg logit contributions
 Rue-0.449
yss-0.435
 Jung-0.401
nir-0.389
Tags-0.388
Tokenör
Token ID30570
Feature activation-3.67e+00

Pos logit contributions
 Rue+0.239
yss+0.227
 Jung+0.211
nir+0.201
Tags+0.199
Neg logit contributions
sbm-0.363
bro-0.349
Cub-0.334
worth-0.320
\/-0.314
Tokenk
Token ID74
Feature activation-1.77e+00

Pos logit contributions
 Rue+2.463
yss+2.377
 Jung+2.234
nir+2.162
Tags+2.104
Neg logit contributions
sbm-3.045
bro-2.868
Cub-2.773
worth-2.632
\/-2.580
Token has
Token ID468
Feature activation+4.30e-01

Pos logit contributions
 Rue+1.323
yss+1.275
 Jung+1.206
nir+1.157
Tags+1.149
Neg logit contributions
sbm-1.338
bro-1.266
Cub-1.206
worth-1.140
\/-1.117
Token composed
Token ID13160
Feature activation-6.09e-01

Pos logit contributions
sbm+0.335
bro+0.327
Cub+0.309
worth+0.293
\/+0.288
Neg logit contributions
 Rue-0.304
yss-0.296
 Jung-0.272
nir-0.267
Tags-0.264
Token and
Token ID290
Feature activation+7.09e-02

Pos logit contributions
 Rue+0.460
yss+0.444
 Jung+0.417
nir+0.404
Tags+0.400
Neg logit contributions
sbm-0.455
bro-0.433
Cub-0.411
worth-0.390
\/-0.382
Token performed
Token ID6157
Feature activation+2.73e-01

Pos logit contributions
sbm+0.057
bro+0.055
Cub+0.052
worth+0.050
\/+0.049
Neg logit contributions
 Rue-0.049
yss-0.048
 Jung-0.044
nir-0.043
Tags-0.042
Token form
Token ID1296
Feature activation+4.43e-01

Pos logit contributions
 Rue+0.077
yss+0.075
 Jung+0.071
nir+0.068
Tags+0.068
Neg logit contributions
sbm-0.072
bro-0.069
Cub-0.065
worth-0.061
\/-0.060
Token:
Token ID25
Feature activation+1.82e-01

Pos logit contributions
sbm+0.313
bro+0.300
Cub+0.283
worth+0.269
\/+0.265
Neg logit contributions
 Rue-0.350
yss-0.339
 Jung-0.318
nir-0.309
Tags-0.307
Token [
Token ID685
Feature activation-3.95e-01

Pos logit contributions
sbm+0.142
bro+0.135
Cub+0.128
worth+0.122
\/+0.120
Neg logit contributions
 Rue-0.132
yss-0.127
 Jung-0.119
nir-0.115
Tags-0.114
Tokentext
Token ID5239
Feature activation-2.25e-01

Pos logit contributions
 Rue+0.313
yss+0.302
 Jung+0.286
nir+0.275
Tags+0.273
Neg logit contributions
sbm-0.282
bro-0.268
Cub-0.254
worth-0.239
\/-0.235
Token]
Token ID60
Feature activation-1.30e+00

Pos logit contributions
 Rue+0.170
yss+0.166
 Jung+0.156
nir+0.150
 refriger+0.148
Neg logit contributions
sbm-0.166
bro-0.160
Cub-0.151
worth-0.144
\/-0.142
Token{
Token ID90
Feature activation-3.66e+00

Pos logit contributions
 Rue+0.994
yss+0.959
 Jung+0.905
nir+0.871
Tags+0.864
Neg logit contributions
sbm-0.968
bro-0.920
Cub-0.874
worth-0.826
\/-0.810
Tokenwhite
Token ID11186
Feature activation+1.18e-01

Pos logit contributions
 Rue+3.019
yss+2.916
 Jung+2.770
Tags+2.692
nir+2.685
Neg logit contributions
sbm-2.454
bro-2.299
Cub-2.190
worth-2.047
EEE-1.990
Token}{
Token ID18477
Feature activation-1.61e+00

Pos logit contributions
sbm+0.081
bro+0.077
Cub+0.073
worth+0.069
\/+0.067
Neg logit contributions
 Rue-0.096
yss-0.093
 Jung-0.088
nir-0.085
Tags-0.084
Tokenvi
Token ID8903
Feature activation-2.48e-01

Pos logit contributions
 Rue+1.359
yss+1.317
 Jung+1.250
nir+1.212
Tags+1.207
Neg logit contributions
sbm-1.054
bro-0.987
Cub-0.935
worth-0.874
\/-0.850
Token:
Token ID25
Feature activation-2.90e-01

Pos logit contributions
 Rue+0.214
yss+0.208
 Jung+0.198
nir+0.191
Tags+0.190
Neg logit contributions
sbm-0.157
bro-0.149
Cub-0.140
worth-0.131
\/-0.129
Token|
Token ID91
Feature activation-7.08e-02

Pos logit contributions
 Rue+0.256
yss+0.248
 Jung+0.236
nir+0.228
Tags+0.227
Neg logit contributions
sbm-0.181
bro-0.170
Cub-0.160
worth-0.149
\/-0.146
Token::
Token ID3712
Feature activation-1.97e+00

Pos logit contributions
 Rue+0.766
yss+0.733
 Jung+0.690
nir+0.659
Tags+0.658
Neg logit contributions
sbm-0.909
bro-0.866
Cub-0.827
worth-0.787
\/-0.768
TokenCenter
Token ID23656
Feature activation-6.10e-02

Pos logit contributions
 Rue+1.537
yss+1.468
 Jung+1.397
Tags+1.354
nir+1.347
Neg logit contributions
sbm-1.422
bro-1.343
Cub-1.261
worth-1.204
\/-1.169
Token break
Token ID2270
Feature activation-1.47e+00

Pos logit contributions
 Rue+0.046
yss+0.045
 Jung+0.042
nir+0.041
Tags+0.040
Neg logit contributions
sbm-0.045
bro-0.043
Cub-0.041
worth-0.039
\/-0.038
Token }
Token ID1782
Feature activation-1.24e+00

Pos logit contributions
 Rue+1.400
yss+1.362
 Jung+1.300
nir+1.263
Tags+1.255
Neg logit contributions
sbm-0.813
bro-0.760
Cub-0.709
worth-0.652
\/-0.633
Token Left
Token ID9578
Feature activation+8.65e-01

Pos logit contributions
 Rue+1.076
yss+1.047
 Jung+0.994
nir+0.964
Tags+0.957
Neg logit contributions
sbm-0.781
bro-0.737
Cub-0.694
worth-0.647
\/-0.632
Token {
Token ID1391
Feature activation-3.65e+00

Pos logit contributions
sbm+0.616
bro+0.588
Cub+0.561
worth+0.526
\/+0.516
Neg logit contributions
 Rue-0.679
yss-0.658
 Jung-0.621
nir-0.602
 refriger-0.592
Token $
Token ID720
Feature activation+2.07e-01

Pos logit contributions
 Rue+2.497
yss+2.379
 Jung+2.245
Tags+2.134
nir+2.130
Neg logit contributions
sbm-2.989
bro-2.829
Cub-2.702
worth-2.580
\/-2.530
Tokens
Token ID82
Feature activation+5.38e-01

Pos logit contributions
sbm+0.148
bro+0.140
Cub+0.133
worth+0.126
\/+0.123
Neg logit contributions
 Rue-0.163
yss-0.158
 Jung-0.149
nir-0.144
Tags-0.143
TokenFormat
Token ID26227
Feature activation-4.67e-01

Pos logit contributions
sbm+0.346
bro+0.326
Cub+0.308
worth+0.287
\/+0.280
Neg logit contributions
 Rue-0.463
yss-0.449
 Jung-0.427
nir-0.413
Tags-0.409
Token.
Token ID13
Feature activation-5.30e-01

Pos logit contributions
 Rue+0.341
yss+0.330
 Jung+0.310
nir+0.298
Tags+0.295
Neg logit contributions
sbm-0.361
bro-0.344
Cub-0.328
worth-0.310
\/-0.304
TokenAl
Token ID2348
Feature activation+1.39e+00

Pos logit contributions
 Rue+0.433
yss+0.419
 Jung+0.397
nir+0.383
Tags+0.379
Neg logit contributions
sbm-0.364
bro-0.344
Cub-0.327
worth-0.306
\/-0.299
Token a
Token ID257
Feature activation+2.23e-01

Pos logit contributions
sbm+0.410
bro+0.397
Cub+0.376
worth+0.359
\/+0.350
Neg logit contributions
 Rue-0.405
yss-0.396
 Jung-0.369
nir-0.359
Tags-0.356
Token major
Token ID1688
Feature activation-2.34e-01

Pos logit contributions
sbm+0.169
bro+0.163
Cub+0.154
worth+0.146
\/+0.144
Neg logit contributions
 Rue-0.165
yss-0.159
 Jung-0.149
nir-0.145
Tags-0.144
Token Oscars
Token ID46485
Feature activation+3.87e-01

Pos logit contributions
 Rue+0.177
yss+0.171
 Jung+0.161
nir+0.157
Tags+0.156
Neg logit contributions
sbm-0.173
bro-0.166
Cub-0.157
worth-0.149
\/-0.146
Token
Token ID198
Feature activation+1.71e-01

Pos logit contributions
sbm+0.296
bro+0.284
Cub+0.270
worth+0.257
\/+0.254
Neg logit contributions
 Rue-0.284
yss-0.274
 Jung-0.258
nir-0.250
Tags-0.247
Token
Token ID198
Feature activation-4.63e-03

Pos logit contributions
sbm+0.126
bro+0.120
Cub+0.114
worth+0.108
\/+0.105
Neg logit contributions
 Rue-0.131
yss-0.128
 Jung-0.119
nir-0.115
Tags-0.114
Tokencont
Token ID3642
Feature activation-3.62e+00

Pos logit contributions
 Rue+0.004
yss+0.003
 Jung+0.003
nir+0.003
 refriger+0.003
Neg logit contributions
sbm-0.003
bro-0.003
Cub-0.003
worth-0.003
\/-0.003
Tokenender
Token ID2194
Feature activation-1.29e+00

Pos logit contributions
 Rue+3.050
yss+2.955
 Jung+2.793
nir+2.714
 refriger+2.659
Neg logit contributions
sbm-2.422
bro-2.223
Cub-2.123
worth-1.945
\/-1.935
Token,
Token ID11
Feature activation+2.64e-01

Pos logit contributions
 Rue+0.929
yss+0.896
 Jung+0.842
nir+0.809
Tags+0.804
Neg logit contributions
sbm-1.003
bro-0.957
Cub-0.911
worth-0.865
\/-0.848
Token potentially
Token ID6196
Feature activation-8.08e-01

Pos logit contributions
sbm+0.196
bro+0.187
Cub+0.178
worth+0.169
\/+0.165
Neg logit contributions
 Rue-0.200
yss-0.194
 Jung-0.182
nir-0.176
Tags-0.175
Token picking
Token ID10868
Feature activation+2.60e-01

Pos logit contributions
 Rue+0.583
yss+0.564
 Jung+0.529
nir+0.509
Tags+0.506
Neg logit contributions
sbm-0.629
bro-0.601
Cub-0.572
worth-0.545
\/-0.534
Token up
Token ID510
Feature activation+4.90e-01

Pos logit contributions
sbm+0.220
bro+0.213
Cub+0.203
worth+0.195
\/+0.191
Neg logit contributions
 Rue-0.167
yss-0.162
 Jung-0.150
nir-0.145
Tags-0.143
Tokensearch
Token ID12947
Feature activation-4.87e-01

Pos logit contributions
 Rue+1.660
yss+1.601
 Jung+1.512
nir+1.449
Tags+1.440
Neg logit contributions
sbm-1.668
bro-1.589
Cub-1.510
worth-1.427
\/-1.398
TokenSpace
Token ID14106
Feature activation+2.49e-01

Pos logit contributions
 Rue+0.361
yss+0.349
 Jung+0.328
nir+0.313
 refriger+0.312
Neg logit contributions
sbm-0.371
bro-0.355
Cub-0.340
worth-0.319
\/-0.316
Token`
Token ID63
Feature activation-1.51e+00

Pos logit contributions
sbm+0.157
bro+0.149
Cub+0.141
worth+0.130
\/+0.130
Neg logit contributions
 Rue-0.217
yss-0.211
 Jung-0.200
nir-0.193
 refriger-0.191
Token *)
Token ID31936
Feature activation+4.93e-01

Pos logit contributions
 Rue+1.013
yss+0.975
 Jung+0.910
nir+0.871
Tags+0.859
Neg logit contributions
sbm-1.260
bro-1.206
Cub-1.153
worth-1.095
\/-1.081
Token (*
Token ID20789
Feature activation+1.01e+00

Pos logit contributions
sbm+0.412
bro+0.395
Cub+0.376
\/+0.355
worth+0.355
Neg logit contributions
 Rue-0.321
yss-0.316
 Jung-0.289
ukong-0.281
nir-0.280
Token {
Token ID1391
Feature activation-3.58e+00

Pos logit contributions
sbm+0.794
bro+0.764
Cub+0.724
worth+0.683
\/+0.677
Neg logit contributions
 Rue-0.713
yss-0.698
 Jung-0.648
nir-0.626
ukong-0.623
Tokeni
Token ID72
Feature activation+1.37e-01

Pos logit contributions
 Rue+2.766
yss+2.665
 Jung+2.525
nir+2.431
Tags+2.422
Neg logit contributions
sbm-2.610
bro-2.459
Cub-2.344
worth-2.215
\/-2.159
Token,
Token ID11
Feature activation+1.30e+00

Pos logit contributions
sbm+0.105
bro+0.100
Cub+0.096
worth+0.090
\/+0.089
Neg logit contributions
 Rue-0.101
yss-0.098
 Jung-0.092
nir-0.089
Tags-0.088
Token{
Token ID90
Feature activation-2.02e+00

Pos logit contributions
sbm+1.081
bro+1.036
Cub+0.990
worth+0.939
\/+0.925
Neg logit contributions
 Rue-0.869
yss-0.838
 Jung-0.775
nir-0.751
ukong-0.739
TokenSub
Token ID7004
Feature activation+3.30e-01

Pos logit contributions
 Rue+1.575
yss+1.521
 Jung+1.440
nir+1.387
Tags+1.381
Neg logit contributions
sbm-1.465
bro-1.387
Cub-1.318
worth-1.243
\/-1.216
Tokenscript
Token ID12048
Feature activation+3.57e-02

Pos logit contributions
sbm+0.244
bro+0.234
Cub+0.222
worth+0.210
\/+0.206
Neg logit contributions
 Rue-0.252
yss-0.244
 Jung-0.230
nir-0.220
 refriger-0.219
Token "
Token ID366
Feature activation+8.13e-03

Pos logit contributions
sbm+0.847
bro+0.824
Cub+0.776
worth+0.739
\/+0.715
Neg logit contributions
 Rue-0.901
yss-0.876
 Jung-0.819
nir-0.803
Tags-0.791
TokenYou
Token ID1639
Feature activation+2.16e-01

Pos logit contributions
sbm+0.006
bro+0.005
Cub+0.005
worth+0.005
\/+0.005
Neg logit contributions
 Rue-0.007
yss-0.006
 Jung-0.006
nir-0.006
 refriger-0.006
Token know
Token ID760
Feature activation+2.13e-01

Pos logit contributions
sbm+0.158
bro+0.154
Cub+0.143
worth+0.137
\/+0.135
Neg logit contributions
 Rue-0.164
yss-0.160
 Jung-0.149
nir-0.145
Tags-0.144
Token what
Token ID644
Feature activation+2.14e-01

Pos logit contributions
sbm+0.150
bro+0.145
Cub+0.136
worth+0.129
\/+0.127
Neg logit contributions
 Rue-0.166
yss-0.162
 Jung-0.151
nir-0.148
Tags-0.147
Token I
Token ID314
Feature activation+8.00e-01

Pos logit contributions
sbm+0.147
bro+0.146
Cub+0.135
worth+0.129
\/+0.125
Neg logit contributions
 Rue-0.168
yss-0.164
 Jung-0.152
Tags-0.150
nir-0.150
Token mean
Token ID1612
Feature activation+3.65e+00

Pos logit contributions
sbm+0.619
bro+0.606
Cub+0.561
worth+0.547
EEE+0.535
Neg logit contributions
 Rue-0.572
yss-0.562
 Jung-0.518
nir-0.504
Tags-0.499
Token."
Token ID526
Feature activation+2.76e-01

Pos logit contributions
sbm+2.608
bro+2.598
Cub+2.457
worth+2.325
EEE+2.303
Neg logit contributions
 Rue-2.662
yss-2.608
nir-2.398
Tags-2.380
 Jung-2.374
Token I
Token ID314
Feature activation-3.31e-02

Pos logit contributions
sbm+0.200
bro+0.191
Cub+0.181
worth+0.172
\/+0.167
Neg logit contributions
 Rue-0.211
yss-0.205
 Jung-0.192
nir-0.188
Tags-0.186
Token pull
Token ID2834
Feature activation-4.82e-01

Pos logit contributions
 Rue+0.022
yss+0.022
 Jung+0.020
nir+0.019
Tags+0.019
Neg logit contributions
sbm-0.027
bro-0.026
Cub-0.025
worth-0.024
\/-0.023
Token away
Token ID1497
Feature activation+1.31e+00

Pos logit contributions
 Rue+0.356
yss+0.345
 Jung+0.322
nir+0.314
Tags+0.312
Neg logit contributions
sbm-0.362
bro-0.349
Cub-0.329
worth-0.314
\/-0.308
Token at
Token ID379
Feature activation+4.43e-01

Pos logit contributions
sbm+0.911
bro+0.884
Cub+0.829
worth+0.792
\/+0.770
Neg logit contributions
 Rue-1.030
yss-1.006
 Jung-0.941
nir-0.920
Tags-0.914
Token aluminum
Token ID15955
Feature activation-6.15e-01

Pos logit contributions
 Rue+0.510
yss+0.492
 Jung+0.467
nir+0.450
Tags+0.447
Neg logit contributions
sbm-0.443
bro-0.419
Cub-0.397
worth-0.374
\/-0.365
Token composite
Token ID24185
Feature activation+5.16e-01

Pos logit contributions
 Rue+0.490
yss+0.474
 Jung+0.448
nir+0.433
Tags+0.429
Neg logit contributions
sbm-0.435
bro-0.413
Cub-0.391
worth-0.369
\/-0.361
Token panels
Token ID13043
Feature activation+2.61e-01

Pos logit contributions
sbm+0.363
bro+0.346
Cub+0.326
worth+0.309
\/+0.303
Neg logit contributions
 Rue-0.412
yss-0.400
 Jung-0.376
nir-0.366
Tags-0.360
Token.
Token ID13
Feature activation+3.20e-01

Pos logit contributions
sbm+0.202
bro+0.193
Cub+0.183
worth+0.175
\/+0.171
Neg logit contributions
 Rue-0.190
yss-0.184
 Jung-0.172
nir-0.166
Tags-0.164
Token The
Token ID383
Feature activation-4.74e-01

Pos logit contributions
sbm+0.258
bro+0.244
Cub+0.233
worth+0.222
\/+0.217
Neg logit contributions
 Rue-0.224
yss-0.220
 Jung-0.203
nir-0.198
Tags-0.194
Token core
Token ID4755
Feature activation+2.74e+00

Pos logit contributions
 Rue+0.348
yss+0.337
 Jung+0.316
nir+0.306
Tags+0.302
Neg logit contributions
sbm-0.364
bro-0.346
Cub-0.329
worth-0.313
\/-0.306
Token of
Token ID286
Feature activation+3.83e-01

Pos logit contributions
sbm+2.127
bro+2.046
Cub+1.942
worth+1.865
\/+1.808
Neg logit contributions
 Rue-1.969
yss-1.894
 Jung-1.781
nir-1.734
Tags-1.700
Token many
Token ID867
Feature activation+5.16e-01

Pos logit contributions
sbm+0.299
bro+0.285
Cub+0.271
worth+0.257
\/+0.252
Neg logit contributions
 Rue-0.277
yss-0.267
 Jung-0.251
nir-0.242
Tags-0.239
Token of
Token ID286
Feature activation-2.32e-01

Pos logit contributions
sbm+0.416
bro+0.397
Cub+0.377
worth+0.360
\/+0.354
Neg logit contributions
 Rue-0.360
yss-0.348
 Jung-0.325
nir-0.315
Tags-0.310
Token the
Token ID262
Feature activation-6.40e-02

Pos logit contributions
 Rue+0.170
yss+0.165
 Jung+0.155
nir+0.149
Tags+0.148
Neg logit contributions
sbm-0.178
bro-0.169
Cub-0.161
worth-0.153
\/-0.150
Token panels
Token ID13043
Feature activation-2.89e-01

Pos logit contributions
 Rue+0.045
yss+0.043
 Jung+0.040
nir+0.039
Tags+0.038
Neg logit contributions
sbm-0.052
bro-0.049
Cub-0.047
worth-0.045
\/-0.044
Token hit
Token ID2277
Feature activation+9.96e-01

Pos logit contributions
 Rue+0.193
yss+0.186
 Jung+0.175
nir+0.169
Tags+0.169
Neg logit contributions
sbm-0.197
bro-0.190
Cub-0.180
worth-0.171
\/-0.167
Token for
Token ID329
Feature activation+1.01e-01

Pos logit contributions
sbm+0.750
bro+0.727
Cub+0.690
worth+0.654
\/+0.643
Neg logit contributions
 Rue-0.739
yss-0.715
 Jung-0.669
nir-0.646
Tags-0.645
Token the
Token ID262
Feature activation+2.43e-01

Pos logit contributions
sbm+0.078
bro+0.076
Cub+0.071
worth+0.068
\/+0.067
Neg logit contributions
 Rue-0.072
yss-0.070
 Jung-0.065
nir-0.064
Tags-0.063
Token franchise
Token ID8663
Feature activation-2.08e-01

Pos logit contributions
sbm+0.179
bro+0.173
Cub+0.163
worth+0.154
\/+0.151
Neg logit contributions
 Rue-0.183
yss-0.178
 Jung-0.166
nir-0.163
Tags-0.160
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
 Rue+0.152
yss+0.147
 Jung+0.138
nir+0.133
Tags+0.132
Neg logit contributions
sbm-0.160
bro-0.154
Cub-0.146
worth-0.139
\/-0.136
Token Granted
Token ID38842
Feature activation+2.60e+00

Pos logit contributions
sbm+0.161
bro+0.155
Cub+0.148
worth+0.142
\/+0.139
Neg logit contributions
 Rue-0.119
yss-0.118
nir-0.105
 Jung-0.105
 refriger-0.103
Token,
Token ID11
Feature activation+9.01e-01

Pos logit contributions
sbm+1.961
bro+1.904
Cub+1.795
worth+1.699
\/+1.678
Neg logit contributions
 Rue-1.884
yss-1.827
 Jung-1.695
nir-1.674
Tags-1.651
Token we
Token ID356
Feature activation+5.99e-01

Pos logit contributions
sbm+0.676
bro+0.655
Cub+0.614
worth+0.586
\/+0.573
Neg logit contributions
 Rue-0.664
yss-0.644
 Jung-0.601
nir-0.592
Tags-0.585
Token don
Token ID836
Feature activation-7.33e-01

Pos logit contributions
sbm+0.440
bro+0.427
Cub+0.402
worth+0.379
\/+0.375
Neg logit contributions
 Rue-0.456
yss-0.442
 Jung-0.413
nir-0.401
Tags-0.399
Token
Token ID447
Feature activation+2.92e-01

Pos logit contributions
 Rue+0.555
yss+0.537
 Jung+0.505
nir+0.487
Tags+0.483
Neg logit contributions
sbm-0.548
bro-0.521
Cub-0.495
worth-0.468
\/-0.459
Token
Token ID247
Feature activation+6.78e-02

Pos logit contributions
sbm+0.218
bro+0.208
Cub+0.197
worth+0.187
\/+0.184
Neg logit contributions
 Rue-0.221
yss-0.213
 Jung-0.200
nir-0.194
Tags-0.192
Token the
Token ID262
Feature activation+3.10e-02

Pos logit contributions
sbm+0.026
bro+0.025
Cub+0.024
worth+0.023
\/+0.022
Neg logit contributions
 Rue-0.023
yss-0.022
 Jung-0.020
nir-0.020
Tags-0.020
Token Beer
Token ID16971
Feature activation+4.04e-01

Pos logit contributions
sbm+0.026
bro+0.025
Cub+0.024
worth+0.023
\/+0.022
Neg logit contributions
 Rue-0.020
yss-0.020
 Jung-0.018
nir-0.018
Tags-0.017
Token Festival
Token ID11117
Feature activation-2.57e-01

Pos logit contributions
sbm+0.307
bro+0.295
Cub+0.280
worth+0.264
\/+0.258
Neg logit contributions
 Rue-0.298
yss-0.290
 Jung-0.271
nir-0.263
Tags-0.260
Token.
Token ID13
Feature activation-3.23e-01

Pos logit contributions
 Rue+0.182
yss+0.177
 Jung+0.165
nir+0.160
Tags+0.158
Neg logit contributions
sbm-0.202
bro-0.194
Cub-0.185
worth-0.175
\/-0.173
Token Make
Token ID6889
Feature activation+3.43e-02

Pos logit contributions
 Rue+0.227
yss+0.223
 Jung+0.205
nir+0.201
ukong+0.197
Neg logit contributions
sbm-0.255
bro-0.244
Cub-0.234
worth-0.222
\/-0.218
Token sure
Token ID1654
Feature activation+2.43e+00

Pos logit contributions
sbm+0.028
bro+0.027
Cub+0.026
worth+0.024
\/+0.024
Neg logit contributions
 Rue-0.023
yss-0.022
 Jung-0.021
nir-0.020
Tags-0.020
Token to
Token ID284
Feature activation-1.52e-02

Pos logit contributions
sbm+1.746
bro+1.681
Cub+1.590
worth+1.506
\/+1.499
Neg logit contributions
 Rue-1.856
yss-1.808
 Jung-1.702
nir-1.644
Tags-1.636
Token get
Token ID651
Feature activation+2.79e-02

Pos logit contributions
 Rue+0.010
yss+0.010
 Jung+0.009
nir+0.009
Tags+0.009
Neg logit contributions
sbm-0.012
bro-0.012
Cub-0.011
worth-0.011
\/-0.011
Token your
Token ID534
Feature activation+4.78e-01

Pos logit contributions
sbm+0.021
bro+0.020
Cub+0.019
worth+0.018
\/+0.018
Neg logit contributions
 Rue-0.021
yss-0.020
 Jung-0.019
nir-0.019
Tags-0.018
Token tickets
Token ID8587
Feature activation-7.43e-01

Pos logit contributions
sbm+0.456
bro+0.439
Cub+0.422
worth+0.405
\/+0.400
Neg logit contributions
 Rue-0.261
yss-0.250
 Jung-0.229
nir-0.219
Tags-0.214
Token!
Token ID0
Feature activation-1.23e-01

Pos logit contributions
 Rue+0.550
yss+0.532
 Jung+0.499
nir+0.483
Tags+0.480
Neg logit contributions
sbm-0.565
bro-0.542
Cub-0.513
worth-0.488
\/-0.481
Token divides
Token ID36319
Feature activation-8.17e-01

Pos logit contributions
sbm+0.264
bro+0.257
Cub+0.242
worth+0.229
\/+0.224
Neg logit contributions
 Rue-0.256
yss-0.251
 Jung-0.229
nir-0.226
Tags-0.224
Token them
Token ID606
Feature activation+4.81e-01

Pos logit contributions
 Rue+0.575
yss+0.558
 Jung+0.515
nir+0.501
Tags+0.497
Neg logit contributions
sbm-0.649
bro-0.622
Cub-0.590
worth-0.562
\/-0.552
Token in
Token ID287
Feature activation+1.29e+00

Pos logit contributions
sbm+0.367
bro+0.349
Cub+0.332
worth+0.316
\/+0.310
Neg logit contributions
 Rue-0.355
yss-0.344
 Jung-0.321
nir-0.310
Tags-0.309
Token the
Token ID262
Feature activation+1.16e+00

Pos logit contributions
sbm+1.007
bro+0.964
Cub+0.918
worth+0.874
\/+0.859
Neg logit contributions
 Rue-0.905
yss-0.891
 Jung-0.817
nir-0.799
Tags-0.789
Token Hell
Token ID5783
Feature activation+1.58e+00

Pos logit contributions
sbm+0.939
bro+0.910
Cub+0.871
worth+0.823
\/+0.820
Neg logit contributions
 Rue-0.771
yss-0.762
 Jung-0.685
nir-0.681
Tags-0.673
Tokenesp
Token ID9774
Feature activation+3.00e+00

Pos logit contributions
sbm+1.102
bro+1.066
Cub+0.998
worth+0.955
\/+0.935
Neg logit contributions
 Rue-1.267
yss-1.220
 Jung-1.144
Tags-1.117
nir-1.096
Tokenont
Token ID756
Feature activation+6.05e-01

Pos logit contributions
sbm+2.014
bro+1.938
Cub+1.788
worth+1.762
\/+1.703
Neg logit contributions
 Rue-2.425
yss-2.370
 Jung-2.219
Tags-2.181
nir-2.159
Token region
Token ID3814
Feature activation+2.41e-01

Pos logit contributions
sbm+0.461
bro+0.440
Cub+0.417
worth+0.397
\/+0.392
Neg logit contributions
 Rue-0.446
yss-0.432
 Jung-0.403
Tags-0.389
nir-0.387
Token.
Token ID13
Feature activation+5.64e-01

Pos logit contributions
sbm+0.185
bro+0.176
Cub+0.167
worth+0.159
\/+0.156
Neg logit contributions
 Rue-0.177
yss-0.172
 Jung-0.160
nir-0.155
Tags-0.154
Token And
Token ID843
Feature activation-5.28e-01

Pos logit contributions
sbm+0.482
bro+0.461
Cub+0.441
worth+0.421
\/+0.414
Neg logit contributions
 Rue-0.360
yss-0.357
 Jung-0.319
nir-0.316
 refriger-0.311
Token cru
Token ID4630
Feature activation+1.54e+00

Pos logit contributions
 Rue+0.381
yss+0.368
 Jung+0.343
nir+0.333
Tags+0.331
Neg logit contributions
sbm-0.409
bro-0.394
Cub-0.371
worth-0.353
\/-0.346
Token from
Token ID422
Feature activation-1.34e+00

Pos logit contributions
 Rue+0.205
yss+0.198
 Jung+0.186
nir+0.180
Tags+0.178
Neg logit contributions
sbm-0.206
bro-0.197
Cub-0.187
worth-0.178
\/-0.174
Token which
Token ID543
Feature activation-6.98e-01

Pos logit contributions
 Rue+0.892
yss+0.857
 Jung+0.802
nir+0.768
Tags+0.762
Neg logit contributions
sbm-1.120
bro-1.070
Cub-1.023
worth-0.975
\/-0.956
Token we
Token ID356
Feature activation-1.60e+00

Pos logit contributions
 Rue+0.538
yss+0.519
 Jung+0.491
nir+0.472
Tags+0.470
Neg logit contributions
sbm-0.513
bro-0.485
Cub-0.462
worth-0.436
\/-0.426
Token will
Token ID481
Feature activation-8.01e-01

Pos logit contributions
 Rue+1.095
yss+1.047
 Jung+0.992
nir+0.942
 refriger+0.936
Neg logit contributions
sbm-1.318
bro-1.242
Cub-1.199
worth-1.132
\/-1.107
Token launch
Token ID4219
Feature activation+1.28e+00

Pos logit contributions
 Rue+0.576
yss+0.553
 Jung+0.523
nir+0.500
Tags+0.496
Neg logit contributions
sbm-0.632
bro-0.597
Cub-0.572
worth-0.539
\/-0.528
Token all
Token ID477
Feature activation+3.73e-01

Pos logit contributions
sbm+0.948
bro+0.910
Cub+0.859
worth+0.820
\/+0.808
Neg logit contributions
 Rue-0.953
yss-0.921
 Jung-0.867
nir-0.845
Tags-0.836
Token future
Token ID2003
Feature activation+9.97e-01

Pos logit contributions
sbm+0.283
bro+0.272
Cub+0.257
worth+0.247
\/+0.242
Neg logit contributions
 Rue-0.276
yss-0.265
 Jung-0.250
nir-0.243
Tags-0.238
Token stores
Token ID7000
Feature activation-6.53e-01

Pos logit contributions
sbm+0.755
bro+0.728
Cub+0.689
worth+0.662
\/+0.650
Neg logit contributions
 Rue-0.729
yss-0.709
 Jung-0.659
nir-0.647
Tags-0.633
Token.
Token ID13
Feature activation-3.60e-01

Pos logit contributions
 Rue+0.455
yss+0.439
 Jung+0.410
nir+0.396
Tags+0.391
Neg logit contributions
sbm-0.526
bro-0.503
Cub-0.480
worth-0.458
\/-0.449
Token
Token ID198
Feature activation-4.49e-02

Pos logit contributions
 Rue+0.268
yss+0.258
 Jung+0.243
nir+0.233
Tags+0.232
Neg logit contributions
sbm-0.274
bro-0.260
Cub-0.248
worth-0.234
\/-0.230
Token
Token ID198
Feature activation-4.27e-01

Pos logit contributions
 Rue+0.035
yss+0.034
 Jung+0.032
nir+0.031
 refriger+0.030
Neg logit contributions
sbm-0.033
bro-0.031
Cub-0.030
worth-0.028
\/-0.028
Token employee
Token ID6538
Feature activation-7.77e-01

Pos logit contributions
 Rue+0.526
yss+0.505
 Jung+0.474
nir+0.455
Tags+0.451
Neg logit contributions
sbm-0.617
bro-0.588
Cub-0.562
worth-0.534
\/-0.523
Token said
Token ID531
Feature activation-8.20e-01

Pos logit contributions
 Rue+0.619
yss+0.598
 Jung+0.566
nir+0.546
Tags+0.543
Neg logit contributions
sbm-0.550
bro-0.520
Cub-0.493
worth-0.465
\/-0.454
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
 Rue+0.572
yss+0.548
 Jung+0.520
nir+0.493
Tags+0.490
Neg logit contributions
sbm-0.661
bro-0.628
Cub-0.598
worth-0.568
\/-0.557
Token
Token ID198
Feature activation+1.16e-03

Pos logit contributions
 Rue+0.279
yss+0.270
 Jung+0.253
nir+0.244
Tags+0.242
Neg logit contributions
sbm-0.289
bro-0.274
Cub-0.261
worth-0.247
\/-0.242
Token
Token ID198
Feature activation-3.65e-01

Pos logit contributions
sbm+0.001
bro+0.001
Cub+0.001
worth+0.001
\/+0.001
Neg logit contributions
 Rue-0.001
yss-0.001
 Jung-0.001
nir-0.001
Tags-0.001
TokenLooking
Token ID15784
Feature activation+1.20e+00

Pos logit contributions
 Rue+0.288
yss+0.278
 Jung+0.264
nir+0.253
 refriger+0.251
Neg logit contributions
sbm-0.261
bro-0.249
Cub-0.237
worth-0.222
\/-0.217
Token back
Token ID736
Feature activation+3.20e-01

Pos logit contributions
sbm+0.951
bro+0.910
Cub+0.867
worth+0.826
\/+0.808
Neg logit contributions
 Rue-0.849
yss-0.821
 Jung-0.768
nir-0.736
Tags-0.733
Token now
Token ID783
Feature activation-3.52e-01

Pos logit contributions
sbm+0.256
bro+0.244
Cub+0.233
worth+0.221
\/+0.217
Neg logit contributions
 Rue-0.225
yss-0.217
 Jung-0.203
nir-0.195
Tags-0.194
Token,
Token ID11
Feature activation+3.17e-02

Pos logit contributions
 Rue+0.243
yss+0.234
 Jung+0.220
nir+0.210
Tags+0.208
Neg logit contributions
sbm-0.286
bro-0.272
Cub-0.260
worth-0.247
\/-0.242
Token several
Token ID1811
Feature activation+2.33e-01

Pos logit contributions
sbm+0.023
bro+0.022
Cub+0.021
worth+0.020
\/+0.019
Neg logit contributions
 Rue-0.025
yss-0.024
 Jung-0.022
nir-0.022
Tags-0.022
Token Douglas
Token ID15796
Feature activation-9.69e-01

Pos logit contributions
sbm+0.185
bro+0.178
Cub+0.169
worth+0.161
\/+0.158
Neg logit contributions
 Rue-0.163
yss-0.158
 Jung-0.148
nir-0.143
Tags-0.142
Token the
Token ID262
Feature activation+2.23e-01

Pos logit contributions
sbm+0.322
bro+0.311
Cub+0.296
worth+0.278
\/+0.273
Neg logit contributions
 Rue-0.328
yss-0.318
 Jung-0.299
nir-0.290
Tags-0.288
Token UC
Token ID14417
Feature activation+1.13e+00

Pos logit contributions
sbm+0.170
bro+0.163
Cub+0.156
worth+0.147
\/+0.143
Neg logit contributions
 Rue-0.163
yss-0.158
 Jung-0.148
nir-0.143
Tags-0.142
TokenI
Token ID40
Feature activation-6.86e-01

Pos logit contributions
sbm+0.674
bro+0.641
Cub+0.602
worth+0.562
\/+0.546
Neg logit contributions
 Rue-1.019
yss-0.993
 Jung-0.938
nir-0.910
Tags-0.908
Token was
Token ID373
Feature activation+4.47e-01

Pos logit contributions
 Rue+0.491
yss+0.473
 Jung+0.445
nir+0.427
Tags+0.424
Neg logit contributions
sbm-0.541
bro-0.516
Cub-0.492
worth-0.466
\/-0.457
Token prompted
Token ID12053
Feature activation-5.21e-01

Pos logit contributions
sbm+0.347
bro+0.334
Cub+0.318
worth+0.303
\/+0.295
Neg logit contributions
 Rue-0.322
yss-0.311
 Jung-0.288
nir-0.281
Tags-0.280
Token to
Token ID284
Feature activation+9.06e-01

Pos logit contributions
 Rue+0.343
yss+0.329
 Jung+0.308
nir+0.294
Tags+0.292
Neg logit contributions
sbm-0.441
bro-0.421
Cub-0.403
worth-0.384
\/-0.377
Token revise
Token ID32548
Feature activation+1.57e+00

Pos logit contributions
sbm+0.769
bro+0.747
Cub+0.711
worth+0.683
\/+0.671
Neg logit contributions
 Rue-0.577
yss-0.560
 Jung-0.515
Tags-0.495
nir-0.494
Token its
Token ID663
Feature activation-1.37e-01

Pos logit contributions
sbm+1.178
bro+1.137
Cub+1.085
worth+1.018
\/+1.004
Neg logit contributions
 Rue-1.151
yss-1.128
 Jung-1.044
nir-1.012
ukong-0.999
Token rules
Token ID3173
Feature activation+3.90e-01

Pos logit contributions
 Rue+0.102
yss+0.098
 Jung+0.093
nir+0.089
Tags+0.089
Neg logit contributions
sbm-0.105
bro-0.100
Cub-0.095
worth-0.090
\/-0.088
Token.
Token ID13
Feature activation+2.02e-01

Pos logit contributions
sbm+0.302
bro+0.290
Cub+0.275
worth+0.261
\/+0.257
Neg logit contributions
 Rue-0.284
yss-0.274
 Jung-0.257
nir-0.248
Tags-0.246
Token
Token ID198
Feature activation-1.56e-02

Pos logit contributions
sbm+0.160
bro+0.152
Cub+0.147
worth+0.138
\/+0.135
Neg logit contributions
 Rue-0.143
yss-0.141
 Jung-0.130
nir-0.127
Tags-0.124
Token Jama
Token ID21661
Feature activation-9.33e-02

Pos logit contributions
sbm+0.143
bro+0.136
Cub+0.130
worth+0.124
\/+0.120
Neg logit contributions
yss-0.134
 Rue-0.134
 Jung-0.121
nir-0.121
 refriger-0.119
Tokenal
Token ID282
Feature activation+1.19e+00

Pos logit contributions
 Rue+0.088
yss+0.086
 Jung+0.082
nir+0.079
Tags+0.079
Neg logit contributions
sbm-0.052
bro-0.049
Cub-0.045
worth-0.042
\/-0.041
Token Charles
Token ID7516
Feature activation-7.31e-01

Pos logit contributions
sbm+1.011
bro+0.991
Cub+0.945
worth+0.914
EEE+0.876
Neg logit contributions
 Rue-0.737
yss-0.726
 Jung-0.663
nir-0.656
Tags-0.650
Token also
Token ID635
Feature activation+3.58e-01

Pos logit contributions
 Rue+0.535
yss+0.515
 Jung+0.485
nir+0.467
Tags+0.464
Neg logit contributions
sbm-0.563
bro-0.538
Cub-0.512
worth-0.486
\/-0.476
Token participated
Token ID14888
Feature activation-3.68e-01

Pos logit contributions
sbm+0.270
bro+0.261
Cub+0.247
worth+0.235
\/+0.230
Neg logit contributions
 Rue-0.264
yss-0.256
 Jung-0.240
nir-0.232
Tags-0.231
Token in
Token ID287
Feature activation+2.62e-01

Pos logit contributions
 Rue+0.247
yss+0.237
 Jung+0.222
nir+0.213
Tags+0.211
Neg logit contributions
sbm-0.306
bro-0.293
Cub-0.280
worth-0.267
\/-0.262
Token 11
Token ID1367
Feature activation+1.13e-01

Pos logit contributions
sbm+0.195
bro+0.186
Cub+0.178
worth+0.168
\/+0.165
Neg logit contributions
 Rue-0.196
yss-0.191
 Jung-0.179
nir-0.175
Tags-0.172
Token-
Token ID12
Feature activation-9.41e-02

Pos logit contributions
sbm+0.089
bro+0.085
Cub+0.082
worth+0.077
\/+0.076
Neg logit contributions
 Rue-0.080
yss-0.078
 Jung-0.073
nir-0.071
Tags-0.069
Tokenon
Token ID261
Feature activation+8.16e-01

Pos logit contributions
 Rue+0.070
yss+0.068
 Jung+0.064
nir+0.061
Tags+0.061
Neg logit contributions
sbm-0.071
bro-0.069
Cub-0.065
worth-0.062
\/-0.060
Token-
Token ID12
Feature activation+8.73e-01

Pos logit contributions
sbm+0.597
bro+0.569
Cub+0.538
worth+0.513
\/+0.505
Neg logit contributions
 Rue-0.629
yss-0.611
 Jung-0.571
nir-0.553
Tags-0.547
Token11
Token ID1157
Feature activation+6.63e-01

Pos logit contributions
sbm+0.560
bro+0.532
Cub+0.501
worth+0.474
\/+0.458
Neg logit contributions
 Rue-0.752
yss-0.734
 Jung-0.696
 refriger-0.669
nir-0.666
Token,
Token ID11
Feature activation+7.63e-01

Pos logit contributions
sbm+1.365
bro+1.334
Cub+1.257
worth+1.210
\/+1.173
Neg logit contributions
 Rue-1.396
yss-1.358
 Jung-1.271
nir-1.240
Tags-1.228
Token Ju
Token ID12585
Feature activation+1.42e-01

Pos logit contributions
sbm+0.578
bro+0.562
Cub+0.532
worth+0.512
\/+0.490
Neg logit contributions
 Rue-0.542
yss-0.540
 Jung-0.496
nir-0.491
Tags-0.486
Tokenwan
Token ID8149
Feature activation-4.17e-01

Pos logit contributions
sbm+0.103
bro+0.097
Cub+0.093
worth+0.087
\/+0.085
Neg logit contributions
 Rue-0.111
yss-0.108
 Jung-0.101
nir-0.098
Tags-0.097
Token Thompson
Token ID11654
Feature activation+8.62e-01

Pos logit contributions
 Rue+0.300
yss+0.295
 Jung+0.271
nir+0.269
Tags+0.268
Neg logit contributions
sbm-0.322
bro-0.311
Cub-0.294
worth-0.276
\/-0.273
Token and
Token ID290
Feature activation+6.27e-01

Pos logit contributions
sbm+0.630
bro+0.600
Cub+0.569
worth+0.539
\/+0.526
Neg logit contributions
 Rue-0.664
yss-0.641
 Jung-0.606
nir-0.583
Tags-0.581
Token rookie
Token ID12302
Feature activation+6.48e-01

Pos logit contributions
sbm+0.516
bro+0.500
Cub+0.478
worth+0.455
\/+0.445
Neg logit contributions
yss-0.407
 Rue-0.404
nir-0.366
 Jung-0.366
Tags-0.360
Token De
Token ID1024
Feature activation-1.66e-01

Pos logit contributions
sbm+0.531
bro+0.516
Cub+0.494
worth+0.470
\/+0.458
Neg logit contributions
yss-0.423
 Rue-0.418
nir-0.379
 Jung-0.378
Tags-0.375
Token
Token ID447
Feature activation+3.74e-01

Pos logit contributions
 Rue+0.105
yss+0.101
 Jung+0.094
nir+0.089
Tags+0.089
Neg logit contributions
sbm-0.143
bro-0.138
Cub-0.133
worth-0.126
\/-0.123
Token
Token ID247
Feature activation+4.87e-01

Pos logit contributions
sbm+0.293
bro+0.280
Cub+0.267
worth+0.253
\/+0.248
Neg logit contributions
 Rue-0.269
yss-0.259
 Jung-0.243
nir-0.234
Tags-0.232
TokenAngelo
Token ID45585
Feature activation+9.20e-01

Pos logit contributions
sbm+0.357
bro+0.341
Cub+0.324
worth+0.307
\/+0.299
Neg logit contributions
 Rue-0.373
yss-0.361
 Jung-0.341
nir-0.327
Tags-0.327
Token Henderson
Token ID22016
Feature activation+1.11e+00

Pos logit contributions
sbm+0.671
bro+0.638
Cub+0.607
worth+0.573
\/+0.562
Neg logit contributions
 Rue-0.708
yss-0.687
 Jung-0.646
nir-0.627
Tags-0.622
Token serial
Token ID11389
Feature activation-1.47e+00

Pos logit contributions
 Rue+0.582
yss+0.561
 Jung+0.530
nir+0.511
Tags+0.507
Neg logit contributions
sbm-0.538
bro-0.515
Cub-0.486
worth-0.459
\/-0.450
Tokenization
Token ID1634
Feature activation-1.05e+00

Pos logit contributions
 Rue+1.091
yss+1.051
 Jung+0.986
nir+0.953
Tags+0.942
Neg logit contributions
sbm-1.115
bro-1.068
Cub-1.014
worth-0.960
\/-0.942
Token,
Token ID11
Feature activation-3.30e-01

Pos logit contributions
 Rue+0.767
yss+0.743
 Jung+0.696
nir+0.668
Tags+0.665
Neg logit contributions
sbm-0.800
bro-0.768
Cub-0.730
worth-0.691
\/-0.681
Token and
Token ID290
Feature activation-6.20e-01

Pos logit contributions
 Rue+0.262
yss+0.255
 Jung+0.240
nir+0.232
Tags+0.231
Neg logit contributions
sbm-0.231
bro-0.220
Cub-0.208
worth-0.197
\/-0.193
Token for
Token ID329
Feature activation+1.59e-01

Pos logit contributions
 Rue+0.461
yss+0.450
 Jung+0.420
Tags+0.405
nir+0.404
Neg logit contributions
sbm-0.463
bro-0.446
Cub-0.423
worth-0.401
\/-0.394
Token that
Token ID326
Feature activation-1.25e-01

Pos logit contributions
sbm+0.114
bro+0.108
Cub+0.103
worth+0.097
\/+0.095
Neg logit contributions
 Rue-0.125
yss-0.121
 Jung-0.114
nir-0.110
Tags-0.110
Token I
Token ID314
Feature activation-1.06e-01

Pos logit contributions
 Rue+0.101
yss+0.099
 Jung+0.092
Tags+0.090
nir+0.089
Neg logit contributions
sbm-0.085
bro-0.081
Cub-0.077
worth-0.073
\/-0.071
Token need
Token ID761
Feature activation-2.89e-01

Pos logit contributions
 Rue+0.082
yss+0.080
 Jung+0.074
nir+0.072
Tags+0.072
Neg logit contributions
sbm-0.077
bro-0.074
Cub-0.070
worth-0.066
\/-0.065
Token the
Token ID262
Feature activation-3.07e-01

Pos logit contributions
 Rue+0.205
yss+0.198
 Jung+0.185
nir+0.177
Tags+0.177
Neg logit contributions
sbm-0.229
bro-0.219
Cub-0.208
worth-0.198
\/-0.195
Token current
Token ID1459
Feature activation-2.16e-02

Pos logit contributions
 Rue+0.217
yss+0.210
 Jung+0.195
nir+0.189
Tags+0.187
Neg logit contributions
sbm-0.243
bro-0.233
Cub-0.222
worth-0.210
\/-0.207
Token version
Token ID2196
Feature activation-1.36e+00

Pos logit contributions
 Rue+0.016
yss+0.015
 Jung+0.014
nir+0.014
Tags+0.014
Neg logit contributions
sbm-0.016
bro-0.016
Cub-0.015
worth-0.014
\/-0.014
Tokens
Token ID82
Feature activation-5.65e-01

Pos logit contributions
sbm+1.224
bro+1.186
Cub+1.117
worth+1.048
\/+1.032
Neg logit contributions
 Rue-1.417
yss-1.355
 Jung-1.281
nir-1.237
Tags-1.231
Token including
Token ID1390
Feature activation+9.02e-01

Pos logit contributions
 Rue+0.407
yss+0.392
 Jung+0.368
nir+0.354
Tags+0.352
Neg logit contributions
sbm-0.442
bro-0.422
Cub-0.403
worth-0.382
\/-0.375
Token interrupts
Token ID48237
Feature activation+2.49e+00

Pos logit contributions
sbm+0.724
bro+0.700
Cub+0.669
worth+0.636
\/+0.626
Neg logit contributions
 Rue-0.620
yss-0.595
 Jung-0.554
nir-0.538
Tags-0.531
Token and
Token ID290
Feature activation+2.94e-01

Pos logit contributions
sbm+1.777
bro+1.727
Cub+1.618
worth+1.545
\/+1.527
Neg logit contributions
 Rue-1.924
yss-1.874
 Jung-1.742
nir-1.695
Tags-1.686
Token timers
Token ID48085
Feature activation+4.17e-01

Pos logit contributions
sbm+0.267
bro+0.259
Cub+0.248
worth+0.237
\/+0.235
Neg logit contributions
 Rue-0.172
yss-0.164
 Jung-0.150
nir-0.145
ukong-0.143
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
sbm+0.317
bro+0.306
Cub+0.289
worth+0.276
\/+0.271
Neg logit contributions
 Rue-0.306
yss-0.295
 Jung-0.277
nir-0.267
Tags-0.265
Token
Token ID198
Feature activation-2.76e-01

Pos logit contributions
 Rue+0.134
yss+0.130
 Jung+0.121
nir+0.117
Tags+0.115
Neg logit contributions
sbm-0.146
bro-0.140
Cub-0.134
worth-0.127
EEE-0.124
Token
Token ID198
Feature activation-6.05e-01

Pos logit contributions
 Rue+0.211
yss+0.205
 Jung+0.192
nir+0.185
Tags+0.183
Neg logit contributions
sbm-0.204
bro-0.194
Cub-0.184
worth-0.175
\/-0.171
TokenThings
Token ID22248
Feature activation+3.90e-01

Pos logit contributions
 Rue+0.477
yss+0.460
 Jung+0.436
nir+0.417
 refriger+0.415
Neg logit contributions
sbm-0.435
bro-0.415
Cub-0.395
worth-0.372
\/-0.363
Token started
Token ID2067
Feature activation-2.86e-01

Pos logit contributions
sbm+0.303
bro+0.292
Cub+0.276
worth+0.263
\/+0.258
Neg logit contributions
 Rue-0.280
yss-0.272
 Jung-0.254
nir-0.244
Tags-0.244
Token to
Token ID284
Feature activation+7.58e-01

Pos logit contributions
 Rue+0.197
yss+0.190
 Jung+0.178
nir+0.171
Tags+0.170
Neg logit contributions
sbm-0.231
bro-0.221
Cub-0.211
worth-0.201
\/-0.197
Token social
Token ID1919
Feature activation-6.63e-01

Pos logit contributions
sbm+0.417
bro+0.405
Cub+0.384
worth+0.363
\/+0.353
Neg logit contributions
 Rue-0.437
yss-0.425
 Jung-0.396
nir-0.387
Tags-0.382
Token problems
Token ID2761
Feature activation+4.01e-02

Pos logit contributions
 Rue+0.458
yss+0.439
 Jung+0.414
nir+0.395
Tags+0.394
Neg logit contributions
sbm-0.542
bro-0.514
Cub-0.491
worth-0.466
\/-0.458
Token from
Token ID422
Feature activation-5.22e-01

Pos logit contributions
sbm+0.030
bro+0.029
Cub+0.028
worth+0.026
\/+0.026
Neg logit contributions
 Rue-0.030
yss-0.029
 Jung-0.027
nir-0.026
Tags-0.026
Token a
Token ID257
Feature activation-4.31e-01

Pos logit contributions
 Rue+0.383
yss+0.372
 Jung+0.346
nir+0.339
Tags+0.333
Neg logit contributions
sbm-0.395
bro-0.380
Cub-0.361
worth-0.342
\/-0.333
Token radical
Token ID7702
Feature activation-1.43e+00

Pos logit contributions
 Rue+0.313
yss+0.303
 Jung+0.281
nir+0.275
Tags+0.273
Neg logit contributions
sbm-0.330
bro-0.319
Cub-0.304
worth-0.286
\/-0.279
Token antic
Token ID47792
Feature activation+1.01e-01

Pos logit contributions
 Rue+1.009
yss+0.971
 Jung+0.912
nir+0.876
Tags+0.870
Neg logit contributions
sbm-1.135
bro-1.083
Cub-1.034
worth-0.981
\/-0.961
Tokenap
Token ID499
Feature activation+8.77e-01

Pos logit contributions
sbm+0.069
bro+0.066
Cub+0.062
worth+0.059
\/+0.057
Neg logit contributions
 Rue-0.083
yss-0.080
 Jung-0.076
nir-0.073
Tags-0.073
Tokenital
Token ID1287
Feature activation+4.42e-01

Pos logit contributions
sbm+0.368
bro+0.344
Cub+0.309
worth+0.277
\/+0.265
Neg logit contributions
 Rue-0.949
yss-0.924
 Jung-0.887
Tags-0.862
nir-0.861
Tokenist
Token ID396
Feature activation+1.17e+00

Pos logit contributions
sbm+0.372
bro+0.358
Cub+0.342
worth+0.330
\/+0.322
Neg logit contributions
 Rue-0.290
yss-0.274
 Jung-0.256
nir-0.247
Tags-0.244
Token perspective
Token ID6650
Feature activation-6.45e-01

Pos logit contributions
sbm+0.954
bro+0.934
Cub+0.890
worth+0.843
\/+0.832
Neg logit contributions
 Rue-0.787
yss-0.761
 Jung-0.697
nir-0.680
Tags-0.677
Token,"
Token ID553
Feature activation-8.40e-01

Pos logit contributions
 Rue+0.435
yss+0.419
 Jung+0.390
nir+0.374
Tags+0.372
Neg logit contributions
sbm-0.533
bro-0.511
Cub-0.488
worth-0.466
\/-0.456
Tokenal
Token ID282
Feature activation-1.96e-01

Pos logit contributions
 Rue+0.214
yss+0.208
 Jung+0.199
nir+0.193
Tags+0.192
Neg logit contributions
sbm-0.131
bro-0.122
Cub-0.114
worth-0.106
\/-0.103
Tokenism
Token ID1042
Feature activation+6.21e-01

Pos logit contributions
 Rue+0.122
yss+0.118
 Jung+0.109
nir+0.105
Tags+0.103
Neg logit contributions
sbm-0.171
bro-0.165
Cub-0.158
worth-0.152
\/-0.149
Token in
Token ID287
Feature activation+2.43e-01

Pos logit contributions
sbm+0.509
bro+0.492
Cub+0.468
worth+0.445
\/+0.438
Neg logit contributions
 Rue-0.421
yss-0.406
 Jung-0.378
nir-0.362
Tags-0.359
Token South
Token ID2520
Feature activation-2.82e-01

Pos logit contributions
sbm+0.177
bro+0.171
Cub+0.162
worth+0.152
\/+0.150
Neg logit contributions
 Rue-0.185
yss-0.181
 Jung-0.168
nir-0.164
Tags-0.162
Token Korea
Token ID4969
Feature activation-1.19e+00

Pos logit contributions
 Rue+0.204
yss+0.198
 Jung+0.185
nir+0.179
Tags+0.177
Neg logit contributions
sbm-0.219
bro-0.209
Cub-0.199
worth-0.189
\/-0.186
Token.
Token ID13
Feature activation+1.34e-02

Pos logit contributions
 Rue+0.861
yss+0.825
 Jung+0.782
nir+0.748
Tags+0.744
Neg logit contributions
sbm-0.928
bro-0.881
Cub-0.841
worth-0.797
\/-0.780
Token<|endoftext|>
Token ID50256
Feature activation-8.83e-01

Pos logit contributions
sbm+0.011
bro+0.010
Cub+0.010
worth+0.009
\/+0.009
Neg logit contributions
 Rue-0.010
yss-0.009
 Jung-0.009
nir-0.008
Tags-0.008
TokenThis
Token ID1212
Feature activation+1.55e-01

Pos logit contributions
 Rue+0.680
yss+0.656
 Jung+0.620
nir+0.596
Tags+0.592
Neg logit contributions
sbm-0.648
bro-0.616
Cub-0.586
worth-0.553
\/-0.541
Token article
Token ID2708
Feature activation+6.34e-01

Pos logit contributions
sbm+0.118
bro+0.112
Cub+0.107
worth+0.101
\/+0.099
Neg logit contributions
 Rue-0.115
yss-0.111
 Jung-0.104
nir-0.101
Tags-0.101
Token is
Token ID318
Feature activation+1.65e+00

Pos logit contributions
sbm+0.440
bro+0.422
Cub+0.398
worth+0.378
\/+0.369
Neg logit contributions
 Rue-0.509
yss-0.494
 Jung-0.463
nir-0.450
Tags-0.448
Token about
Token ID546
Feature activation+1.01e+00

Pos logit contributions
sbm+1.158
bro+1.110
Cub+1.052
worth+1.004
\/+0.981
Neg logit contributions
 Rue-1.287
yss-1.263
 Jung-1.170
nir-1.143
Tags-1.139
Token than
Token ID621
Feature activation+7.64e-01

Pos logit contributions
 Rue+0.243
yss+0.235
 Jung+0.220
nir+0.213
Tags+0.211
Neg logit contributions
sbm-0.246
bro-0.234
Cub-0.223
worth-0.211
\/-0.207
Token one
Token ID530
Feature activation-4.81e-01

Pos logit contributions
sbm+0.566
bro+0.546
Cub+0.513
worth+0.490
\/+0.476
Neg logit contributions
 Rue-0.570
yss-0.553
 Jung-0.520
nir-0.507
Tags-0.503
Token issued
Token ID4884
Feature activation-4.92e-02

Pos logit contributions
 Rue+0.364
yss+0.353
 Jung+0.330
nir+0.320
Tags+0.318
Neg logit contributions
sbm-0.357
bro-0.343
Cub-0.324
worth-0.308
\/-0.300
Token on
Token ID319
Feature activation-6.72e-02

Pos logit contributions
 Rue+0.034
yss+0.033
 Jung+0.031
nir+0.030
Tags+0.030
Neg logit contributions
sbm-0.040
bro-0.038
Cub-0.036
worth-0.034
\/-0.034
Token Wednesday
Token ID3583
Feature activation+5.17e-02

Pos logit contributions
 Rue+0.050
yss+0.048
 Jung+0.045
nir+0.044
Tags+0.044
Neg logit contributions
sbm-0.050
bro-0.048
Cub-0.046
worth-0.044
\/-0.043
Token by
Token ID416
Feature activation-5.30e-01

Pos logit contributions
sbm+0.041
bro+0.039
Cub+0.037
worth+0.036
\/+0.035
Neg logit contributions
 Rue-0.036
yss-0.035
 Jung-0.033
nir-0.032
Tags-0.032
Token F
Token ID376
Feature activation+1.58e-01

Pos logit contributions
 Rue+0.394
yss+0.383
 Jung+0.358
nir+0.348
Tags+0.347
Neg logit contributions
sbm-0.397
bro-0.382
Cub-0.360
worth-0.343
\/-0.334
Tokenitch
Token ID2007
Feature activation+7.05e-02

Pos logit contributions
sbm+0.121
bro+0.116
Cub+0.110
worth+0.104
\/+0.102
Neg logit contributions
 Rue-0.115
yss-0.110
 Jung-0.105
nir-0.100
Tags-0.100
Token Ratings
Token ID36826
Feature activation+5.56e-02

Pos logit contributions
sbm+0.056
bro+0.054
Cub+0.052
worth+0.049
\/+0.048
Neg logit contributions
 Rue-0.049
yss-0.047
 Jung-0.044
nir-0.043
Tags-0.042
Token.
Token ID13
Feature activation-6.10e-01

Pos logit contributions
sbm+0.043
bro+0.041
Cub+0.040
worth+0.038
\/+0.037
Neg logit contributions
 Rue-0.040
yss-0.039
 Jung-0.036
nir-0.035
Tags-0.035
Token
Token ID198
Feature activation+6.55e-01

Pos logit contributions
 Rue+0.451
yss+0.435
 Jung+0.410
nir+0.394
Tags+0.391
Neg logit contributions
sbm-0.467
bro-0.444
Cub-0.423
worth-0.400
\/-0.392
Token continually
Token ID17451
Feature activation-1.56e-01

Pos logit contributions
 Rue+0.042
yss+0.041
 Jung+0.038
nir+0.037
Tags+0.036
Neg logit contributions
sbm-0.043
bro-0.042
Cub-0.040
worth-0.038
\/-0.037
Token burning
Token ID9482
Feature activation-5.06e-03

Pos logit contributions
 Rue+0.106
yss+0.102
 Jung+0.095
nir+0.092
Tags+0.091
Neg logit contributions
sbm-0.127
bro-0.123
Cub-0.117
worth-0.112
\/-0.110
Token sugar
Token ID7543
Feature activation-2.27e+00

Pos logit contributions
 Rue+0.004
yss+0.004
 Jung+0.003
nir+0.003
Tags+0.003
Neg logit contributions
sbm-0.004
bro-0.004
Cub-0.003
worth-0.003
\/-0.003
Token (
Token ID357
Feature activation-1.82e-01

Pos logit contributions
 Rue+1.645
yss+1.582
 Jung+1.495
nir+1.435
Tags+1.427
Neg logit contributions
sbm-1.766
bro-1.672
Cub-1.597
worth-1.509
\/-1.476
Tokengl
Token ID4743
Feature activation-7.34e-01

Pos logit contributions
 Rue+0.149
yss+0.144
 Jung+0.137
nir+0.132
Tags+0.131
Neg logit contributions
sbm-0.124
bro-0.118
Cub-0.111
worth-0.105
\/-0.102
Tokenuc
Token ID1229
Feature activation-3.01e+00

Pos logit contributions
 Rue+0.536
yss+0.516
 Jung+0.486
nir+0.467
Tags+0.463
Neg logit contributions
sbm-0.569
bro-0.540
Cub-0.515
worth-0.488
\/-0.478
Tokenose
Token ID577
Feature activation-1.19e+00

Pos logit contributions
 Rue+2.000
yss+1.914
 Jung+1.808
nir+1.733
Tags+1.714
Neg logit contributions
sbm-2.527
bro-2.391
Cub-2.306
worth-2.186
EEE-2.137
Token)
Token ID8
Feature activation+4.23e-02

Pos logit contributions
 Rue+0.858
yss+0.827
 Jung+0.778
nir+0.747
Tags+0.742
Neg logit contributions
sbm-0.927
bro-0.887
Cub-0.845
worth-0.802
\/-0.787
Token from
Token ID422
Feature activation-6.94e-01

Pos logit contributions
sbm+0.032
bro+0.030
Cub+0.029
worth+0.027
\/+0.027
Neg logit contributions
 Rue-0.032
yss-0.031
 Jung-0.029
nir-0.028
Tags-0.027
Token the
Token ID262
Feature activation-2.38e-01

Pos logit contributions
 Rue+0.496
yss+0.479
 Jung+0.448
nir+0.431
Tags+0.428
Neg logit contributions
sbm-0.545
bro-0.523
Cub-0.497
worth-0.472
\/-0.463
Token fed
Token ID11672
Feature activation-2.75e-01

Pos logit contributions
 Rue+0.160
yss+0.155
 Jung+0.143
nir+0.139
Tags+0.137
Neg logit contributions
sbm-0.197
bro-0.190
Cub-0.181
worth-0.171
\/-0.170
Token be
Token ID307
Feature activation+1.48e-02

Pos logit contributions
 Rue+0.626
yss+0.604
 Jung+0.569
nir+0.547
Tags+0.544
Neg logit contributions
sbm-0.640
bro-0.609
Cub-0.579
worth-0.548
\/-0.537
Token more
Token ID517
Feature activation+9.79e-02

Pos logit contributions
sbm+0.010
bro+0.009
Cub+0.009
worth+0.008
\/+0.008
Neg logit contributions
 Rue-0.013
yss-0.012
 Jung-0.012
nir-0.011
Tags-0.011
Token cost
Token ID1575
Feature activation+1.17e+00

Pos logit contributions
sbm+0.076
bro+0.074
Cub+0.070
worth+0.067
\/+0.065
Neg logit contributions
 Rue-0.070
yss-0.067
 Jung-0.063
nir-0.061
Tags-0.060
Token over
Token ID625
Feature activation-1.04e-01

Pos logit contributions
sbm+0.920
bro+0.897
Cub+0.849
worth+0.807
\/+0.797
Neg logit contributions
 Rue-0.828
yss-0.793
 Jung-0.737
nir-0.712
Tags-0.705
Token-
Token ID12
Feature activation-6.87e-01

Pos logit contributions
 Rue+0.062
yss+0.059
 Jung+0.055
nir+0.052
Tags+0.052
Neg logit contributions
sbm-0.095
bro-0.091
Cub-0.088
worth-0.084
\/-0.082
Tokenruns
Token ID48381
Feature activation-2.36e+00

Pos logit contributions
 Rue+0.637
yss+0.619
 Jung+0.591
nir+0.573
Tags+0.570
Neg logit contributions
sbm-0.396
bro-0.369
Cub-0.346
worth-0.320
\/-0.311
Token.
Token ID13
Feature activation-2.87e-01

Pos logit contributions
 Rue+1.691
yss+1.626
 Jung+1.535
nir+1.470
Tags+1.460
Neg logit contributions
sbm-1.857
bro-1.762
Cub-1.683
worth-1.591
\/-1.559
Token
Token ID198
Feature activation-4.48e-01

Pos logit contributions
 Rue+0.198
yss+0.192
 Jung+0.178
nir+0.173
Tags+0.171
Neg logit contributions
sbm-0.232
bro-0.222
Cub-0.212
worth-0.202
\/-0.198
Token
Token ID198
Feature activation-8.23e-01

Pos logit contributions
 Rue+0.340
yss+0.330
 Jung+0.310
nir+0.299
Tags+0.296
Neg logit contributions
sbm-0.333
bro-0.317
Cub-0.301
worth-0.285
\/-0.279
TokenThen
Token ID6423
Feature activation+2.52e-01

Pos logit contributions
 Rue+0.623
yss+0.600
 Jung+0.568
nir+0.544
Tags+0.539
Neg logit contributions
sbm-0.616
bro-0.587
Cub-0.559
worth-0.528
\/-0.516
Token there
Token ID612
Feature activation+8.36e-01

Pos logit contributions
sbm+0.195
bro+0.187
Cub+0.177
worth+0.169
\/+0.165
Neg logit contributions
 Rue-0.183
yss-0.176
 Jung-0.165
nir-0.159
Tags-0.159
Token of
Token ID286
Feature activation-5.67e-01

Pos logit contributions
 Rue+0.455
yss+0.437
 Jung+0.410
Tags+0.388
 refriger+0.387
Neg logit contributions
sbm-0.621
bro-0.591
Cub-0.567
worth-0.536
EEE-0.530
Token all
Token ID477
Feature activation-9.59e-02

Pos logit contributions
 Rue+0.431
yss+0.416
 Jung+0.392
nir+0.378
Tags+0.375
Neg logit contributions
sbm-0.422
bro-0.401
Cub-0.381
worth-0.360
\/-0.352
Token documents
Token ID4963
Feature activation+8.89e-01

Pos logit contributions
 Rue+0.070
yss+0.068
 Jung+0.064
nir+0.061
Tags+0.061
Neg logit contributions
sbm-0.074
bro-0.070
Cub-0.067
worth-0.064
\/-0.062
Token in
Token ID287
Feature activation-5.58e-01

Pos logit contributions
sbm+0.663
bro+0.632
Cub+0.600
worth+0.569
\/+0.556
Neg logit contributions
 Rue-0.672
yss-0.650
 Jung-0.611
nir-0.592
Tags-0.586
Token the
Token ID262
Feature activation-3.22e-01

Pos logit contributions
 Rue+0.396
yss+0.383
 Jung+0.358
nir+0.346
Tags+0.342
Neg logit contributions
sbm-0.442
bro-0.422
Cub-0.402
worth-0.382
\/-0.374
Token case
Token ID1339
Feature activation-2.56e+00

Pos logit contributions
 Rue+0.212
yss+0.205
 Jung+0.190
nir+0.184
Tags+0.182
Neg logit contributions
sbm-0.270
bro-0.259
Cub-0.248
worth-0.237
\/-0.232
Token.
Token ID13
Feature activation-9.01e-02

Pos logit contributions
 Rue+1.815
yss+1.742
 Jung+1.652
 refriger+1.572
nir+1.563
Neg logit contributions
sbm-2.021
bro-1.919
Cub-1.838
worth-1.730
EEE-1.698
Token Two
Token ID4930
Feature activation-8.60e-01

Pos logit contributions
 Rue+0.064
yss+0.063
 Jung+0.058
nir+0.057
 refriger+0.056
Neg logit contributions
sbm-0.071
bro-0.067
Cub-0.064
worth-0.061
\/-0.060
Token justices
Token ID27818
Feature activation-4.40e-01

Pos logit contributions
 Rue+0.592
yss+0.573
 Jung+0.534
nir+0.514
Tags+0.509
Neg logit contributions
sbm-0.697
bro-0.669
Cub-0.637
worth-0.607
\/-0.596
Token declined
Token ID7392
Feature activation-3.38e-01

Pos logit contributions
 Rue+0.316
yss+0.305
 Jung+0.286
nir+0.275
Tags+0.274
Neg logit contributions
sbm-0.345
bro-0.330
Cub-0.314
worth-0.298
\/-0.292
Token a
Token ID257
Feature activation+1.77e-01

Pos logit contributions
 Rue+0.225
yss+0.216
 Jung+0.202
nir+0.193
Tags+0.192
Neg logit contributions
sbm-0.284
bro-0.271
Cub-0.260
worth-0.247
\/-0.243
TokenYou
Token ID1639
Feature activation-1.21e-01

Pos logit contributions
 Rue+0.858
yss+0.828
 Jung+0.780
nir+0.753
Tags+0.744
Neg logit contributions
sbm-0.894
bro-0.850
Cub-0.810
worth-0.768
\/-0.751
Token contributed
Token ID8639
Feature activation+2.81e-02

Pos logit contributions
 Rue+0.090
yss+0.087
 Jung+0.082
nir+0.079
Tags+0.078
Neg logit contributions
sbm-0.091
bro-0.087
Cub-0.083
worth-0.078
\/-0.077
Token money
Token ID1637
Feature activation-1.08e+00

Pos logit contributions
sbm+0.022
bro+0.021
Cub+0.020
worth+0.019
\/+0.019
Neg logit contributions
 Rue-0.020
yss-0.019
 Jung-0.018
nir-0.018
Tags-0.017
Token to
Token ID284
Feature activation-2.01e-02

Pos logit contributions
 Rue+0.754
yss+0.724
 Jung+0.680
nir+0.652
Tags+0.648
Neg logit contributions
sbm-0.876
bro-0.836
Cub-0.798
worth-0.759
\/-0.745
Token Al
Token ID978
Feature activation-1.94e-01

Pos logit contributions
 Rue+0.014
yss+0.014
 Jung+0.013
nir+0.013
Tags+0.013
Neg logit contributions
sbm-0.016
bro-0.015
Cub-0.014
worth-0.014
\/-0.013
Token Qaeda
Token ID17942
Feature activation-2.58e+00

Pos logit contributions
 Rue+0.147
yss+0.142
 Jung+0.134
nir+0.129
Tags+0.128
Neg logit contributions
sbm-0.144
bro-0.136
Cub-0.130
worth-0.122
\/-0.120
Token
Token ID447
Feature activation+1.15e-01

Pos logit contributions
 Rue+1.845
yss+1.780
 Jung+1.676
nir+1.599
Tags+1.588
Neg logit contributions
sbm-2.025
bro-1.925
Cub-1.835
worth-1.736
EEE-1.696
Token
Token ID251
Feature activation-9.92e-02

Pos logit contributions
sbm+0.085
bro+0.081
Cub+0.077
worth+0.073
\/+0.071
Neg logit contributions
 Rue-0.088
yss-0.085
 Jung-0.080
nir-0.078
Tags-0.077
Token)
Token ID8
Feature activation+5.57e-01

Pos logit contributions
 Rue+0.071
yss+0.068
 Jung+0.064
nir+0.062
Tags+0.062
Neg logit contributions
sbm-0.078
bro-0.074
Cub-0.071
worth-0.068
\/-0.066
Token without
Token ID1231
Feature activation+9.48e-01

Pos logit contributions
sbm+0.401
bro+0.380
Cub+0.360
worth+0.341
\/+0.334
Neg logit contributions
 Rue-0.437
yss-0.421
 Jung-0.397
nir-0.387
Tags-0.384
Token revealing
Token ID13477
Feature activation+1.36e+00

Pos logit contributions
sbm+0.698
bro+0.669
Cub+0.633
worth+0.599
\/+0.589
Neg logit contributions
 Rue-0.711
yss-0.698
 Jung-0.645
nir-0.633
Tags-0.629
Tokenomet
Token ID908
Feature activation+3.68e-01

Pos logit contributions
 Rue+0.500
yss+0.484
 Jung+0.459
nir+0.443
Tags+0.440
Neg logit contributions
sbm-0.420
bro-0.397
Cub-0.376
worth-0.354
\/-0.345
Tokenhin
Token ID20079
Feature activation+5.98e-02

Pos logit contributions
sbm+0.255
bro+0.243
Cub+0.228
worth+0.216
\/+0.211
Neg logit contributions
 Rue-0.300
yss-0.287
 Jung-0.274
Tags-0.264
nir-0.264
Token'
Token ID6
Feature activation+1.31e+00

Pos logit contributions
sbm+0.042
bro+0.040
Cub+0.038
worth+0.036
\/+0.035
Neg logit contributions
 Rue-0.048
yss-0.047
 Jung-0.044
Tags-0.042
nir-0.042
Token Better
Token ID11625
Feature activation-1.42e+00

Pos logit contributions
sbm+1.019
bro+0.990
Cub+0.926
worth+0.889
\/+0.868
Neg logit contributions
 Rue-0.919
yss-0.910
 Jung-0.826
nir-0.813
Tags-0.809
Token Comes
Token ID34606
Feature activation-1.36e+00

Pos logit contributions
 Rue+0.980
yss+0.940
 Jung+0.884
nir+0.846
Tags+0.839
Neg logit contributions
sbm-1.161
bro-1.106
Cub-1.058
worth-1.005
\/-0.985
Token Along
Token ID17159
Feature activation-2.16e+00

Pos logit contributions
 Rue+0.884
yss+0.853
 Jung+0.791
Tags+0.758
nir+0.757
Neg logit contributions
sbm-1.148
bro-1.102
Cub-1.054
worth-1.008
\/-0.990
Token!",
Token ID40754
Feature activation-6.58e-01

Pos logit contributions
 Rue+1.474
yss+1.420
 Jung+1.328
nir+1.273
Tags+1.265
Neg logit contributions
sbm-1.775
bro-1.699
Cub-1.621
worth-1.543
\/-1.515
Token a
Token ID257
Feature activation-3.31e-01

Pos logit contributions
 Rue+0.469
yss+0.455
 Jung+0.423
nir+0.413
Tags+0.409
Neg logit contributions
sbm-0.516
bro-0.495
Cub-0.471
worth-0.451
\/-0.438
Token song
Token ID3496
Feature activation+3.77e-01

Pos logit contributions
 Rue+0.233
yss+0.226
 Jung+0.209
nir+0.204
Tags+0.202
Neg logit contributions
sbm-0.262
bro-0.252
Cub-0.240
worth-0.228
\/-0.223
Token about
Token ID546
Feature activation-2.95e-01

Pos logit contributions
sbm+0.278
bro+0.270
Cub+0.258
worth+0.245
\/+0.236
Neg logit contributions
 Rue-0.282
yss-0.274
 Jung-0.253
nir-0.252
Tags-0.248
Token their
Token ID511
Feature activation-6.85e-01

Pos logit contributions
 Rue+0.210
yss+0.207
 Jung+0.188
nir+0.187
Tags+0.185
Neg logit contributions
sbm-0.225
bro-0.219
Cub-0.207
worth-0.199
\/-0.192