TOP ACTIVATIONS
MAX = 5.469

/ 3 minutes until golden brown . These are lightly fried
Natural World episode " Snow Leopard Beyond the Myth ".[
/ 3 minutes until golden brown . These are lightly fried
energy goals . <|endoftext|> Media playback is unsupported on your device
also said Ross must rec use himself from all Russia -
to every citizen over the age of 18 at a federal
At the tender age of 69 , my wife
s best wel ter weight while suffering double vision and
for the former UFC Heavy weight champion who vowed to
on Twitter . <|endoftext|> Media playback is unsupported on your device
b ] Personal best : [/ b ] 00 : 47
b ] Personal best : [/ b ] 1 : 07
b ] Est imate : [/ b ] 1 : 20
varieties for children of all age groups . Every parent loves
younger than 15 years of age , according to the online
b ] Est imate : [/ b ] 00 : 55
reality this is seldom the case . To understand
the White House at the age of just 25 , one
at medium - high heat until the onion is clear or
oil and fry it at medium - high heat until the

MIN ACTIVATIONS
MIN = -4.925

when perform a R OP exploit , there 's a very
center for the city ," Ful op said .
Monday . ATT ENTION , en ra ison des
and his co - p il ots tried to stop them
, change the Fire wall Settings to the minimum setting .
ITT SM ITH , FL OR IDA Y ards
of Pre y https :// kill ert of ure
the Club and a new sponsor is for the Premier League
when the rubber ' t ent acles ' started interfering with
put ts easily , feel free to make more than one
category , where Emmy - neg lected The Good Wife was
SAS K ATCH EW AN - favorite favorite favorite favorite favorite
shop for free , legal copies of e
: Sylvia 's En ch il ada Kitchen Previously : Gro
) ( K ath leen Flynn )
www . bel fast te legraph . co . uk /
) and Henry ( P yr g os ) on the
) shows the three available settings , including sil
the brain areas controlling these movements for the first time ,
oppose what my president stands for , his incompetence , potential

INTERVAL 2.871 - 5.469
CONTAINS 0.294%

decades to come back after finishing operations ; we will re
ma v Goodell Original Compl aint V il ma
ume is , finally , very much part of the women
August A . Bus ch Jr . and Ad olph us
ention : 706 Main Today : The Burger Guys

INTERVAL 0.272 - 2.871
CONTAINS 36.396%

" Working on Yog ventures was an amazing experience and
uses ? How about after a year ? How about when
in the Medicare Advantage business ; they 're not in the
ci / 2 yp d G uf <|endoftext|> A statistical modeling
This teen is being ID 'd because he 's a

INTERVAL -2.327 - 0.272
CONTAINS 62.538%

men , 18 59 . 11 ) When Dancing
s important to enable them for the future .
House at the age of just 25 , one of her
accommodate a brief work stopp age . But if MA VEN
, an admin must be placed behind every team for the

INTERVAL -4.925 - -2.327
CONTAINS 0.772%

as it can be mult il ine $ art ext =
who paid extra for other rewards on top of a copy
There are knit - a ... <|endoftext|> Buy Photo F SU
this visualization , you can find a static version of it
make sure he knew the rules . He hadn
Token/
Token ID14
Feature activation+1.26e+00

Pos logit contributions
Sov+0.546
+0.512
 Zhu+0.507
vacc+0.499
 Qin+0.485
Neg logit contributions
 commute-0.396
 commuting-0.324
 notation-0.313
 flakes-0.297
 aeros-0.297
Token3
Token ID18
Feature activation+4.49e-01

Pos logit contributions
Sov+0.849
+0.778
 Zhu+0.765
vacc+0.753
 Qin+0.721
Neg logit contributions
 commute-1.117
 commuting-0.968
 notation-0.945
 aeros-0.910
 flakes-0.907
Token minutes
Token ID2431
Feature activation+4.27e-01

Pos logit contributions
Sov+0.370
+0.343
 Zhu+0.340
vacc+0.334
 Qin+0.323
Neg logit contributions
 commute-0.333
 commuting-0.279
 notation-0.270
 flakes-0.260
 aeros-0.259
Token until
Token ID1566
Feature activation+3.03e+00

Pos logit contributions
Sov+0.315
+0.294
 Zhu+0.291
vacc+0.284
 Qin+0.275
Neg logit contributions
 commute-0.348
 commuting-0.297
 notation-0.291
 flakes-0.279
 aeros-0.279
Token golden
Token ID10861
Feature activation+4.38e+00

Pos logit contributions
Sov+2.404
 Zhu+2.276
+2.269
vacc+2.199
 Qin+2.189
Neg logit contributions
 commute-2.237
 commuting-1.877
 notation-1.813
minster-1.697
 aeros-1.691
Token brown
Token ID7586
Feature activation+5.47e+00

Pos logit contributions
Sov+3.632
+3.571
 Zhu+3.492
vacc+3.412
 Qin+3.315
Neg logit contributions
 commute-3.032
 commuting-2.508
 notation-2.379
 aeros-2.269
minster-2.195
Token.
Token ID13
Feature activation-2.52e-01

Pos logit contributions
Sov+3.866
+3.784
 Zhu+3.677
vacc+3.577
 Qin+3.510
Neg logit contributions
 commute-4.392
 commuting-3.754
 notation-3.533
 aeros-3.457
minster-3.406
Token These
Token ID2312
Feature activation-7.17e-01

Pos logit contributions
 commute+0.194
 commuting+0.164
 notation+0.158
 aeros+0.152
 flakes+0.152
Neg logit contributions
Sov-0.199
-0.186
 Zhu-0.185
vacc-0.181
 Qin-0.175
Token are
Token ID389
Feature activation+2.64e-01

Pos logit contributions
 commute+0.518
 commuting+0.431
 notation+0.418
 flakes+0.404
 aeros+0.401
Neg logit contributions
Sov-0.606
-0.561
 Zhu-0.558
vacc-0.551
 Qin-0.529
Token lightly
Token ID15376
Feature activation+1.92e+00

Pos logit contributions
Sov+0.209
+0.193
 Zhu+0.192
vacc+0.189
 Qin+0.182
Neg logit contributions
 commute-0.204
 commuting-0.172
 notation-0.167
 flakes-0.161
 aeros-0.161
Token fried
Token ID23018
Feature activation+1.05e+00

Pos logit contributions
Sov+1.505
+1.425
 Zhu+1.420
vacc+1.384
 Qin+1.345
Neg logit contributions
 commute-1.450
 commuting-1.222
 notation-1.187
minster-1.123
 aeros-1.109
Token Natural
Token ID12068
Feature activation+1.32e+00

Pos logit contributions
 commute+0.141
 commuting+0.120
 notation+0.117
 flakes+0.112
 aeros+0.112
Neg logit contributions
Sov-0.139
-0.128
 Zhu-0.127
vacc-0.125
 Qin-0.121
Token World
Token ID2159
Feature activation+2.41e+00

Pos logit contributions
Sov+0.880
+0.804
 Zhu+0.799
vacc+0.779
 Qin+0.744
Neg logit contributions
 commute-1.191
 commuting-1.031
 notation-1.005
 flakes-0.973
 aeros-0.967
Token episode
Token ID4471
Feature activation+6.30e-01

Pos logit contributions
Sov+1.794
+1.663
 Zhu+1.644
vacc+1.605
 Qin+1.547
Neg logit contributions
 commute-1.953
 commuting-1.660
 notation-1.630
 flakes-1.561
 aeros-1.554
Token "
Token ID366
Feature activation+3.19e-01

Pos logit contributions
Sov+0.482
+0.444
 Zhu+0.442
vacc+0.434
 Qin+0.418
Neg logit contributions
 commute-0.504
 commuting-0.428
 notation-0.417
 flakes-0.401
 aeros-0.400
TokenSnow
Token ID28974
Feature activation+2.92e+00

Pos logit contributions
Sov+0.216
+0.196
 Zhu+0.194
vacc+0.191
 Qin+0.182
Neg logit contributions
 commute-0.285
 commuting-0.247
 notation-0.241
 flakes-0.233
 aeros-0.232
Token Leopard
Token ID49072
Feature activation+5.38e+00

Pos logit contributions
Sov+2.012
+1.858
 Zhu+1.836
vacc+1.788
 Qin+1.716
Neg logit contributions
 commute-2.544
 commuting-2.179
 notation-2.149
 aeros-2.061
 flakes-2.033
Token
Token ID784
Feature activation+1.34e-02

Pos logit contributions
Sov+3.664
+3.446
 Zhu+3.426
vacc+3.294
 Qin+3.202
Neg logit contributions
 commute-4.591
 commuting-3.917
 notation-3.869
 aeros-3.705
 flakes-3.640
Token Beyond
Token ID12197
Feature activation+1.26e+00

Pos logit contributions
Sov+0.010
+0.009
 Zhu+0.009
vacc+0.009
 Qin+0.009
Neg logit contributions
 commute-0.011
 commuting-0.009
 notation-0.009
 flakes-0.009
 aeros-0.009
Token the
Token ID262
Feature activation-9.06e-02

Pos logit contributions
Sov+0.920
+0.844
 Zhu+0.842
vacc+0.824
 Qin+0.792
Neg logit contributions
 commute-1.051
 commuting-0.896
 notation-0.873
 flakes-0.844
 aeros-0.841
Token Myth
Token ID18900
Feature activation+2.84e+00

Pos logit contributions
 commute+0.072
 commuting+0.061
 notation+0.060
 flakes+0.058
 aeros+0.057
Neg logit contributions
Sov-0.070
-0.064
 Zhu-0.064
vacc-0.063
 Qin-0.060
Token".[
Token ID42924
Feature activation+1.18e+00

Pos logit contributions
Sov+1.755
+1.607
 Zhu+1.579
vacc+1.545
 Qin+1.469
Neg logit contributions
 commute-2.672
 commuting-2.336
 notation-2.273
 aeros-2.204
 flakes-2.200
Token/
Token ID14
Feature activation+1.15e+00

Pos logit contributions
Sov+0.010
 Zhu+0.009
+0.009
vacc+0.009
��+0.009
Neg logit contributions
 commute-0.018
 commuting-0.015
 notation-0.015
 flakes-0.015
 aeros-0.015
Token3
Token ID18
Feature activation+1.41e-01

Pos logit contributions
Sov+0.809
+0.738
 Zhu+0.732
vacc+0.720
 Qin+0.688
Neg logit contributions
 commute-0.986
 commuting-0.848
 notation-0.827
 flakes-0.800
 aeros-0.798
Token minutes
Token ID2431
Feature activation+3.29e-01

Pos logit contributions
Sov+0.135
+0.125
 Zhu+0.125
vacc+0.124
 Qin+0.119
Neg logit contributions
 commute-0.086
 commuting-0.069
 notation-0.067
 flakes-0.063
 aeros-0.063
Token until
Token ID1566
Feature activation+2.86e+00

Pos logit contributions
Sov+0.226
+0.201
 Zhu+0.198
vacc+0.196
��+0.188
Neg logit contributions
 commute-0.296
 commuting-0.255
 notation-0.247
 flakes-0.241
 aeros-0.239
Token golden
Token ID10861
Feature activation+4.23e+00

Pos logit contributions
Sov+2.693
+2.604
 Zhu+2.568
vacc+2.524
 Qin+2.467
Neg logit contributions
 commute-1.701
 commuting-1.350
 notation-1.290
 aeros-1.211
 flakes-1.169
Token brown
Token ID7586
Feature activation+5.31e+00

Pos logit contributions
Sov+3.736
+3.589
 Zhu+3.559
vacc+3.452
 Qin+3.409
Neg logit contributions
 commute-2.732
 commuting-2.217
 notation-2.132
 aeros-2.032
 flakes-1.997
Token.
Token ID13
Feature activation+2.98e-02

Pos logit contributions
Sov+3.274
+3.091
 Zhu+3.068
vacc+2.907
 Qin+2.858
Neg logit contributions
 commute-4.907
 commuting-4.277
 notation-4.129
 aeros-4.010
 flakes-3.932
Token These
Token ID2312
Feature activation-4.21e-01

Pos logit contributions
Sov+0.024
+0.022
 Zhu+0.022
vacc+0.022
 Qin+0.021
Neg logit contributions
 commute-0.023
 commuting-0.019
 notation-0.019
 flakes-0.018
 aeros-0.018
Token are
Token ID389
Feature activation+5.56e-01

Pos logit contributions
 commute+0.270
 commuting+0.219
 notation+0.211
 flakes+0.202
 aeros+0.201
Neg logit contributions
Sov-0.389
-0.363
 Zhu-0.361
vacc-0.357
 Qin-0.345
Token lightly
Token ID15376
Feature activation+1.98e+00

Pos logit contributions
Sov+0.435
+0.401
 Zhu+0.399
vacc+0.392
 Qin+0.377
Neg logit contributions
 commute-0.435
 commuting-0.367
 notation-0.357
 flakes-0.344
 aeros-0.343
Token fried
Token ID23018
Feature activation+5.78e-01

Pos logit contributions
Sov+1.361
+1.268
 Zhu+1.261
vacc+1.219
 Qin+1.195
Neg logit contributions
 commute-1.704
 commuting-1.457
 notation-1.428
 aeros-1.372
 flakes-1.359
Token energy
Token ID2568
Feature activation-8.15e-01

Pos logit contributions
 commute+0.026
 commuting+0.021
 notation+0.021
 flakes+0.020
 aeros+0.020
Neg logit contributions
Sov-0.034
-0.031
 Zhu-0.031
vacc-0.031
 Qin-0.030
Token goals
Token ID4661
Feature activation+3.24e-01

Pos logit contributions
 commute+0.677
 commuting+0.578
 notation+0.562
 flakes+0.543
 aeros+0.542
Neg logit contributions
Sov-0.602
-0.551
 Zhu-0.547
vacc-0.540
 Qin-0.516
Token.
Token ID13
Feature activation+4.95e-01

Pos logit contributions
Sov+0.233
+0.219
 Zhu+0.215
vacc+0.209
 Qin+0.202
Neg logit contributions
 commute-0.270
 commuting-0.231
 notation-0.226
 flakes-0.219
 aeros-0.218
Token<|endoftext|>
Token ID50256
Feature activation-3.51e-01

Pos logit contributions
Sov+0.410
+0.383
 Zhu+0.381
vacc+0.370
 Qin+0.361
Neg logit contributions
 commute-0.366
 commuting-0.306
 notation-0.300
 flakes-0.290
 aeros-0.284
TokenMedia
Token ID13152
Feature activation+2.29e+00

Pos logit contributions
 commute+0.307
 commuting+0.265
 notation+0.259
 flakes+0.250
 aeros+0.249
Neg logit contributions
Sov-0.241
-0.220
 Zhu-0.219
vacc-0.214
 Qin-0.205
Token playback
Token ID16388
Feature activation+5.06e+00

Pos logit contributions
Sov+2.255
+2.113
 Zhu+2.109
vacc+2.089
 Qin+2.030
Neg logit contributions
 commute-1.320
 commuting-1.040
 notation-0.992
 aeros-0.937
 flakes-0.933
Token is
Token ID318
Feature activation+2.57e-01

Pos logit contributions
Sov+3.720
+3.546
 Zhu+3.545
vacc+3.405
 Qin+3.368
Neg logit contributions
 commute-3.971
 commuting-3.350
 notation-3.258
 aeros-3.196
 flakes-3.146
Token unsupported
Token ID24222
Feature activation+8.14e-01

Pos logit contributions
Sov+0.174
+0.158
 Zhu+0.157
vacc+0.154
 Qin+0.147
Neg logit contributions
 commute-0.228
 commuting-0.197
 notation-0.192
 flakes-0.187
 aeros-0.186
Token on
Token ID319
Feature activation+5.32e-01

Pos logit contributions
Sov+0.689
+0.634
 Zhu+0.631
vacc+0.625
 Qin+0.601
Neg logit contributions
 commute-0.589
 commuting-0.490
 notation-0.477
 flakes-0.457
 aeros-0.455
Token your
Token ID534
Feature activation-5.83e-01

Pos logit contributions
Sov+0.345
+0.308
 Zhu+0.305
vacc+0.300
 Qin+0.286
Neg logit contributions
 commute-0.493
 commuting-0.428
 notation-0.420
 flakes-0.407
 aeros-0.406
Token device
Token ID3335
Feature activation+1.38e+00

Pos logit contributions
 commute+0.396
 commuting+0.324
 notation+0.316
 aeros+0.301
 flakes+0.301
Neg logit contributions
Sov-0.520
-0.480
 Zhu-0.478
vacc-0.473
 Qin-0.457
Token also
Token ID635
Feature activation+1.02e+00

Pos logit contributions
 commute+0.014
 commuting+0.011
 notation+0.011
 flakes+0.011
 aeros+0.011
Neg logit contributions
Sov-0.014
-0.013
 Zhu-0.013
vacc-0.013
 Qin-0.013
Token said
Token ID531
Feature activation-1.64e-01

Pos logit contributions
Sov+0.797
+0.749
 Zhu+0.743
vacc+0.725
 Qin+0.705
Neg logit contributions
 commute-0.780
 commuting-0.656
 notation-0.640
 flakes-0.617
 aeros-0.615
Token Ross
Token ID9847
Feature activation+1.11e+00

Pos logit contributions
 commute+0.124
 commuting+0.104
 notation+0.102
 flakes+0.098
 aeros+0.097
Neg logit contributions
Sov-0.133
 Zhu-0.122
-0.122
vacc-0.120
 Qin-0.116
Token must
Token ID1276
Feature activation+5.33e-01

Pos logit contributions
Sov+0.868
+0.802
 Zhu+0.795
vacc+0.783
 Qin+0.752
Neg logit contributions
 commute-0.863
 commuting-0.730
 notation-0.710
 flakes-0.685
 aeros-0.684
Token rec
Token ID664
Feature activation+1.63e+00

Pos logit contributions
Sov+0.429
+0.399
 Zhu+0.395
vacc+0.390
 Qin+0.376
Neg logit contributions
 commute-0.395
 commuting-0.337
 notation-0.327
 flakes-0.315
 aeros-0.314
Tokenuse
Token ID1904
Feature activation+5.03e+00

Pos logit contributions
Sov+1.075
+0.984
 Zhu+0.973
vacc+0.960
 Qin+0.915
Neg logit contributions
 commute-1.463
 commuting-1.271
 notation-1.239
 flakes-1.205
 aeros-1.198
Token himself
Token ID2241
Feature activation-5.74e-01

Pos logit contributions
Sov+3.925
 Zhu+3.736
+3.683
 Qin+3.550
vacc+3.547
Neg logit contributions
 commute-3.713
 commuting-3.086
 notation-3.016
 aeros-2.944
 flakes-2.920
Token from
Token ID422
Feature activation-1.31e+00

Pos logit contributions
 commute+0.441
 commuting+0.371
 notation+0.362
 flakes+0.348
 aeros+0.348
Neg logit contributions
Sov-0.454
-0.423
 Zhu-0.419
vacc-0.411
 Qin-0.397
Token all
Token ID477
Feature activation+2.11e-01

Pos logit contributions
 commute+1.064
 commuting+0.908
 notation+0.882
 flakes+0.852
 aeros+0.849
Neg logit contributions
Sov-0.986
-0.904
 Zhu-0.896
vacc-0.884
 Qin-0.846
Token Russia
Token ID3284
Feature activation+4.94e-01

Pos logit contributions
Sov+0.178
+0.165
 Zhu+0.165
vacc+0.161
 Qin+0.156
Neg logit contributions
 commute-0.151
 commuting-0.125
 notation-0.122
 flakes-0.117
 aeros-0.117
Token-
Token ID12
Feature activation+2.86e-01

Pos logit contributions
Sov+0.391
+0.362
 Zhu+0.358
vacc+0.352
 Qin+0.339
Neg logit contributions
 commute-0.383
 commuting-0.322
 notation-0.314
 flakes-0.302
 aeros-0.301
Token to
Token ID284
Feature activation+6.30e-02

Pos logit contributions
 commute+0.265
 commuting+0.221
 notation+0.215
 flakes+0.208
 aeros+0.206
Neg logit contributions
Sov-0.299
-0.281
 Zhu-0.277
vacc-0.272
 Qin-0.263
Token every
Token ID790
Feature activation-8.57e-02

Pos logit contributions
Sov+0.050
+0.046
 Zhu+0.046
vacc+0.045
 Qin+0.043
Neg logit contributions
 commute-0.048
 commuting-0.041
 notation-0.040
 flakes-0.039
 aeros-0.038
Token citizen
Token ID9511
Feature activation+1.36e+00

Pos logit contributions
 commute+0.064
 commuting+0.054
 notation+0.052
 flakes+0.050
 aeros+0.050
Neg logit contributions
Sov-0.070
-0.065
 Zhu-0.064
vacc-0.063
 Qin-0.061
Token over
Token ID625
Feature activation-4.06e-01

Pos logit contributions
Sov+1.156
+1.090
 Zhu+1.075
vacc+1.053
 Qin+1.022
Neg logit contributions
 commute-0.958
 commuting-0.782
 notation-0.776
 flakes-0.745
 aeros-0.744
Token the
Token ID262
Feature activation+1.36e+00

Pos logit contributions
 commute+0.338
 commuting+0.288
 notation+0.283
 flakes+0.275
 aeros+0.273
Neg logit contributions
Sov-0.296
-0.272
 Zhu-0.270
vacc-0.266
 Qin-0.255
Token age
Token ID2479
Feature activation+4.95e+00

Pos logit contributions
Sov+1.085
+1.020
 Zhu+1.015
vacc+0.993
 Qin+0.969
Neg logit contributions
 commute-1.002
 commuting-0.843
 notation-0.828
 flakes-0.814
 aeros-0.800
Token of
Token ID286
Feature activation+1.35e+00

Pos logit contributions
Sov+3.897
+3.692
 Zhu+3.649
vacc+3.557
 Qin+3.484
Neg logit contributions
 commute-3.672
 commuting-3.072
 notation-3.003
 flakes-2.943
 aeros-2.910
Token 18
Token ID1248
Feature activation+1.96e+00

Pos logit contributions
Sov+0.998
+0.918
 Zhu+0.912
vacc+0.894
 Qin+0.862
Neg logit contributions
 commute-1.111
 commuting-0.946
 notation-0.924
 flakes-0.895
 aeros-0.890
Token at
Token ID379
Feature activation+4.69e-01

Pos logit contributions
Sov+1.629
+1.548
 Zhu+1.518
vacc+1.497
 Qin+1.445
Neg logit contributions
 commute-1.404
 commuting-1.149
 notation-1.135
 flakes-1.098
 aeros-1.097
Token a
Token ID257
Feature activation+8.92e-01

Pos logit contributions
Sov+0.344
+0.320
 Zhu+0.319
vacc+0.309
 Qin+0.301
Neg logit contributions
 commute-0.379
 commuting-0.322
 notation-0.317
 flakes-0.310
 aeros-0.309
Token federal
Token ID2717
Feature activation+8.82e-01

Pos logit contributions
Sov+0.732
+0.686
 Zhu+0.683
vacc+0.665
 Qin+0.648
Neg logit contributions
 commute-0.644
 commuting-0.537
 notation-0.524
 flakes-0.511
 aeros-0.509
Token
Token ID447
Feature activation+8.75e-02

Pos logit contributions
 commute+0.431
 commuting+0.381
 notation+0.375
 flakes+0.364
 aeros+0.363
Neg logit contributions
Sov-0.211
 Zhu-0.186
-0.182
vacc-0.179
 Qin-0.169
Token
Token ID250
Feature activation-3.06e-01

Pos logit contributions
Sov+0.046
+0.041
 Zhu+0.040
vacc+0.039
 Qin+0.037
Neg logit contributions
 commute-0.091
 commuting-0.081
 notation-0.079
 flakes-0.077
 aeros-0.077
TokenAt
Token ID2953
Feature activation-1.81e-01

Pos logit contributions
 commute+0.264
 commuting+0.227
 notation+0.222
 flakes+0.214
 aeros+0.214
Neg logit contributions
Sov-0.215
-0.195
 Zhu-0.194
vacc-0.191
 Qin-0.182
Token the
Token ID262
Feature activation+4.38e-01

Pos logit contributions
 commute+0.147
 commuting+0.125
 notation+0.122
 flakes+0.118
 aeros+0.117
Neg logit contributions
Sov-0.137
-0.125
 Zhu-0.124
vacc-0.122
 Qin-0.118
Token tender
Token ID15403
Feature activation-3.12e-01

Pos logit contributions
Sov+0.327
+0.303
 Zhu+0.300
vacc+0.295
 Qin+0.284
Neg logit contributions
 commute-0.356
 commuting-0.304
 notation-0.296
 flakes-0.287
 aeros-0.285
Token age
Token ID2479
Feature activation+4.91e+00

Pos logit contributions
 commute+0.218
 commuting+0.180
 notation+0.175
 flakes+0.168
 aeros+0.167
Neg logit contributions
Sov-0.271
-0.249
 Zhu-0.248
vacc-0.245
 Qin-0.236
Token of
Token ID286
Feature activation+1.37e+00

Pos logit contributions
Sov+3.736
+3.629
 Zhu+3.526
vacc+3.483
 Qin+3.346
Neg logit contributions
 commute-3.732
 commuting-3.152
 notation-3.057
 flakes-2.989
 aeros-2.974
Token 69
Token ID8644
Feature activation+1.82e+00

Pos logit contributions
Sov+1.022
+0.939
 Zhu+0.932
vacc+0.916
 Qin+0.879
Neg logit contributions
 commute-1.127
 commuting-0.960
 notation-0.936
 flakes-0.905
 aeros-0.901
Token,
Token ID11
Feature activation+6.86e-01

Pos logit contributions
Sov+1.540
+1.453
 Zhu+1.432
vacc+1.417
 Qin+1.365
Neg logit contributions
 commute-1.292
 commuting-1.069
 notation-1.039
 flakes-0.999
 aeros-0.995
Token my
Token ID616
Feature activation-1.15e+00

Pos logit contributions
Sov+0.453
+0.414
 Zhu+0.409
vacc+0.402
 Qin+0.384
Neg logit contributions
 commute-0.620
 commuting-0.537
 notation-0.525
 flakes-0.509
 aeros-0.507
Token wife
Token ID3656
Feature activation-1.08e+00

Pos logit contributions
 commute+0.905
 commuting+0.764
 notation+0.744
 flakes+0.715
 aeros+0.712
Neg logit contributions
Sov-0.904
-0.824
 Zhu-0.820
vacc-0.810
 Qin-0.776
Token
Token ID247
Feature activation-5.14e-01

Pos logit contributions
 commute+0.042
 commuting+0.037
 notation+0.036
 flakes+0.035
 aeros+0.035
Neg logit contributions
Sov-0.022
-0.019
 Zhu-0.019
vacc-0.019
 Qin-0.018
Tokens
Token ID82
Feature activation-1.37e-01

Pos logit contributions
 commute+0.387
 commuting+0.325
 notation+0.315
 flakes+0.304
 aeros+0.303
Neg logit contributions
Sov-0.416
-0.387
 Zhu-0.383
vacc-0.378
 Qin-0.364
Token best
Token ID1266
Feature activation-9.01e-01

Pos logit contributions
 commute+0.108
 commuting+0.092
 notation+0.089
 flakes+0.086
 aeros+0.086
Neg logit contributions
Sov-0.106
-0.098
 Zhu-0.097
vacc-0.095
 Qin-0.092
Token wel
Token ID5029
Feature activation+2.27e+00

Pos logit contributions
 commute+0.753
 commuting+0.644
 notation+0.628
 flakes+0.607
 aeros+0.605
Neg logit contributions
Sov-0.659
-0.601
 Zhu-0.597
vacc-0.588
 Qin-0.563
Tokenter
Token ID353
Feature activation+1.36e+00

Pos logit contributions
Sov+1.977
+1.830
 Zhu+1.817
vacc+1.788
 Qin+1.728
Neg logit contributions
 commute-1.584
 commuting-1.314
 notation-1.272
 flakes-1.220
 aeros-1.215
Tokenweight
Token ID6551
Feature activation+4.81e+00

Pos logit contributions
Sov+1.150
+1.063
 Zhu+1.059
vacc+1.043
 Qin+1.005
Neg logit contributions
 commute-0.980
 commuting-0.815
 notation-0.791
 flakes-0.760
 aeros-0.756
Token while
Token ID981
Feature activation+5.63e-01

Pos logit contributions
Sov+3.475
+3.310
 Zhu+3.256
vacc+3.116
 Qin+3.098
Neg logit contributions
 commute-3.866
 commuting-3.319
 notation-3.195
 flakes-3.127
 aeros-3.122
Token suffering
Token ID7195
Feature activation-7.83e-01

Pos logit contributions
Sov+0.464
+0.433
 Zhu+0.431
vacc+0.421
 Qin+0.409
Neg logit contributions
 commute-0.415
 commuting-0.344
 notation-0.337
 flakes-0.323
 aeros-0.321
Token double
Token ID4274
Feature activation+6.25e-01

Pos logit contributions
 commute+0.614
 commuting+0.520
 notation+0.506
 aeros+0.488
 flakes+0.487
Neg logit contributions
Sov-0.607
-0.562
 Zhu-0.560
vacc-0.547
 Qin-0.529
Token vision
Token ID5761
Feature activation+2.49e-01

Pos logit contributions
Sov+0.483
+0.447
 Zhu+0.445
vacc+0.437
 Qin+0.421
Neg logit contributions
 commute-0.490
 commuting-0.413
 notation-0.403
 flakes-0.389
 aeros-0.388
Token and
Token ID290
Feature activation-6.94e-01

Pos logit contributions
Sov+0.189
+0.176
 Zhu+0.173
vacc+0.170
 Qin+0.164
Neg logit contributions
 commute-0.200
 commuting-0.169
 notation-0.166
 aeros-0.160
 flakes-0.159
Token for
Token ID329
Feature activation+3.79e-01

Pos logit contributions
Sov+0.620
+0.584
 Zhu+0.575
vacc+0.564
 Qin+0.546
Neg logit contributions
 commute-0.560
 commuting-0.468
 notation-0.452
 flakes-0.438
 aeros-0.437
Token the
Token ID262
Feature activation+1.45e-01

Pos logit contributions
Sov+0.385
+0.364
 Zhu+0.362
vacc+0.356
 Qin+0.348
Neg logit contributions
 commute-0.208
 commuting-0.162
 notation-0.154
 flakes-0.147
 aeros-0.145
Token former
Token ID1966
Feature activation-3.92e-01

Pos logit contributions
Sov+0.109
+0.100
 Zhu+0.099
vacc+0.097
 Qin+0.094
Neg logit contributions
 commute-0.118
 commuting-0.101
 notation-0.098
 flakes-0.095
 aeros-0.094
Token UFC
Token ID11448
Feature activation+1.52e+00

Pos logit contributions
 commute+0.318
 commuting+0.271
 notation+0.263
 flakes+0.255
 aeros+0.254
Neg logit contributions
Sov-0.293
-0.272
 Zhu-0.269
vacc-0.263
 Qin-0.255
Token Heavy
Token ID14089
Feature activation+1.55e+00

Pos logit contributions
Sov+1.205
+1.143
 Zhu+1.124
vacc+1.093
 Qin+1.069
Neg logit contributions
 commute-1.145
 commuting-0.961
 notation-0.931
 flakes-0.903
 aeros-0.901
Tokenweight
Token ID6551
Feature activation+4.80e+00

Pos logit contributions
Sov+1.180
+1.126
 Zhu+1.112
vacc+1.072
 Qin+1.055
Neg logit contributions
 commute-1.214
 commuting-1.027
 notation-1.000
 flakes-0.966
 aeros-0.962
Token champion
Token ID8783
Feature activation+1.55e+00

Pos logit contributions
Sov+3.177
+3.040
 Zhu+2.981
 Qin+2.821
vacc+2.809
Neg logit contributions
 commute-4.125
 commuting-3.552
 notation-3.439
 flakes-3.388
 aeros-3.367
Token who
Token ID508
Feature activation-9.32e-01

Pos logit contributions
Sov+1.259
+1.203
 Zhu+1.175
vacc+1.152
 Qin+1.117
Neg logit contributions
 commute-1.142
 commuting-0.949
 notation-0.929
 flakes-0.892
 aeros-0.887
Token vowed
Token ID19982
Feature activation-1.98e+00

Pos logit contributions
 commute+0.699
 commuting+0.587
 notation+0.570
 flakes+0.549
 aeros+0.546
Neg logit contributions
Sov-0.761
-0.701
 Zhu-0.698
vacc-0.688
 Qin-0.662
Token to
Token ID284
Feature activation-8.11e-01

Pos logit contributions
 commute+1.554
 commuting+1.315
 notation+1.279
 flakes+1.233
 aeros+1.228
Neg logit contributions
Sov-1.551
-1.427
 Zhu-1.418
vacc-1.397
 Qin-1.342
Token
Token ID564
Feature activation-1.48e+00

Pos logit contributions
 commute+0.608
 commuting+0.507
 notation+0.494
 flakes+0.474
 aeros+0.473
Neg logit contributions
Sov-0.668
-0.614
 Zhu-0.611
vacc-0.602
 Qin-0.579
Token on
Token ID319
Feature activation+5.69e-01

Pos logit contributions
 commute+0.157
 commuting+0.132
 notation+0.127
 flakes+0.123
 aeros+0.122
Neg logit contributions
Sov-0.177
-0.163
 Zhu-0.162
vacc-0.160
 Qin-0.154
Token Twitter
Token ID3009
Feature activation+2.60e-01

Pos logit contributions
Sov+0.435
+0.401
 Zhu+0.398
vacc+0.391
 Qin+0.376
Neg logit contributions
 commute-0.453
 commuting-0.385
 notation-0.376
 flakes-0.362
 aeros-0.361
Token.
Token ID13
Feature activation-5.34e-01

Pos logit contributions
Sov+0.205
+0.189
 Zhu+0.188
vacc+0.184
 Qin+0.178
Neg logit contributions
 commute-0.202
 commuting-0.171
 notation-0.166
 flakes-0.160
 aeros-0.160
Token<|endoftext|>
Token ID50256
Feature activation-8.49e-01

Pos logit contributions
 commute+0.378
 commuting+0.313
 notation+0.304
 flakes+0.292
 aeros+0.290
Neg logit contributions
Sov-0.458
-0.424
 Zhu-0.418
vacc-0.416
 Qin-0.398
TokenMedia
Token ID13152
Feature activation+1.97e+00

Pos logit contributions
 commute+0.740
 commuting+0.638
 notation+0.624
 flakes+0.603
 aeros+0.601
Neg logit contributions
Sov-0.583
 Zhu-0.531
-0.531
vacc-0.518
 Qin-0.499
Token playback
Token ID16388
Feature activation+4.78e+00

Pos logit contributions
Sov+1.938
+1.818
 Zhu+1.813
vacc+1.796
 Qin+1.745
Neg logit contributions
 commute-1.122
 commuting-0.883
 notation-0.842
 aeros-0.797
 flakes-0.793
Token is
Token ID318
Feature activation+2.36e-01

Pos logit contributions
Sov+3.558
 Zhu+3.384
+3.381
vacc+3.258
 Qin+3.218
Neg logit contributions
 commute-3.716
 commuting-3.125
 notation-3.045
 aeros-2.978
 flakes-2.940
Token unsupported
Token ID24222
Feature activation+2.19e-01

Pos logit contributions
Sov+0.158
+0.143
 Zhu+0.142
vacc+0.139
 Qin+0.133
Neg logit contributions
 commute-0.212
 commuting-0.184
 notation-0.179
 flakes-0.174
 aeros-0.173
Token on
Token ID319
Feature activation+5.02e-01

Pos logit contributions
Sov+0.188
+0.173
 Zhu+0.172
vacc+0.171
��+0.165
Neg logit contributions
 commute-0.156
 commuting-0.129
 notation-0.126
 flakes-0.120
 aeros-0.120
Token your
Token ID534
Feature activation-3.88e-01

Pos logit contributions
Sov+0.329
+0.293
 Zhu+0.290
vacc+0.286
��+0.273
Neg logit contributions
 commute-0.463
 commuting-0.401
 notation-0.393
 flakes-0.381
 aeros-0.380
Token device
Token ID3335
Feature activation+1.21e+00

Pos logit contributions
 commute+0.263
 commuting+0.214
 notation+0.209
 aeros+0.199
 flakes+0.199
Neg logit contributions
Sov-0.348
-0.321
 Zhu-0.319
vacc-0.315
 Qin-0.305
Tokenb
Token ID65
Feature activation+8.82e-01

Pos logit contributions
Sov+0.548
+0.506
 Zhu+0.495
vacc+0.494
 Qin+0.463
Neg logit contributions
 commute-0.766
 commuting-0.669
 notation-0.644
 aeros-0.631
 flakes-0.630
Token]
Token ID60
Feature activation-4.75e-01

Pos logit contributions
Sov+0.842
+0.790
 Zhu+0.784
vacc+0.773
 Qin+0.750
Neg logit contributions
 commute-0.541
 commuting-0.435
 notation-0.417
 flakes-0.397
 aeros-0.395
TokenPersonal
Token ID30228
Feature activation+4.35e-01

Pos logit contributions
 commute+0.389
 commuting+0.332
 notation+0.323
 flakes+0.313
 aeros+0.311
Neg logit contributions
Sov-0.355
-0.326
 Zhu-0.323
vacc-0.318
 Qin-0.305
Token best
Token ID1266
Feature activation+3.37e-01

Pos logit contributions
Sov+0.347
+0.327
 Zhu+0.321
vacc+0.314
 Qin+0.304
Neg logit contributions
 commute-0.327
 commuting-0.277
 notation-0.266
 flakes-0.260
 aeros-0.258
Token:
Token ID25
Feature activation+6.34e-01

Pos logit contributions
Sov+0.296
+0.274
 Zhu+0.273
vacc+0.270
 Qin+0.260
Neg logit contributions
 commute-0.232
 commuting-0.192
 notation-0.186
 flakes-0.178
 aeros-0.177
Token[/
Token ID13412
Feature activation+4.71e+00

Pos logit contributions
Sov+0.320
+0.277
 Zhu+0.276
vacc+0.271
 Qin+0.251
Neg logit contributions
 commute-0.673
 commuting-0.596
 notation-0.586
 flakes-0.572
 aeros-0.570
Tokenb
Token ID65
Feature activation+8.53e-01

Pos logit contributions
Sov+2.880
+2.684
vacc+2.621
 Zhu+2.604
 Qin+2.429
Neg logit contributions
 commute-4.425
 commuting-3.875
 notation-3.717
 aeros-3.671
 flakes-3.643
Token]
Token ID60
Feature activation+6.48e-01

Pos logit contributions
Sov+0.823
+0.769
 Zhu+0.766
vacc+0.757
 Qin+0.733
Neg logit contributions
 commute-0.512
 commuting-0.409
 notation-0.394
 flakes-0.374
 aeros-0.372
Token 00
Token ID3571
Feature activation+2.65e-01

Pos logit contributions
Sov+0.486
+0.449
 Zhu+0.446
vacc+0.436
 Qin+0.423
Neg logit contributions
 commute-0.527
 commuting-0.449
 notation-0.436
 flakes-0.421
 aeros-0.420
Token:
Token ID25
Feature activation-3.11e-01

Pos logit contributions
Sov+0.234
+0.217
 Zhu+0.216
vacc+0.213
 Qin+0.206
Neg logit contributions
 commute-0.181
 commuting-0.149
 notation-0.145
 flakes-0.139
 aeros-0.138
Token47
Token ID2857
Feature activation+2.69e-01

Pos logit contributions
 commute+0.284
 commuting+0.246
 notation+0.242
 flakes+0.235
 aeros+0.234
Neg logit contributions
Sov-0.199
 Zhu-0.179
-0.178
vacc-0.176
��-0.171
Tokenb
Token ID65
Feature activation+9.06e-01

Pos logit contributions
Sov+0.428
+0.399
 Zhu+0.395
vacc+0.392
 Qin+0.375
Neg logit contributions
 commute-0.391
 commuting-0.329
 notation-0.316
 flakes-0.306
 aeros-0.306
Token]
Token ID60
Feature activation-5.99e-01

Pos logit contributions
Sov+0.803
+0.758
 Zhu+0.744
vacc+0.733
 Qin+0.714
Neg logit contributions
 commute-0.608
 commuting-0.505
 notation-0.475
 flakes-0.462
 aeros-0.460
TokenPersonal
Token ID30228
Feature activation-3.05e-01

Pos logit contributions
 commute+0.541
 commuting+0.469
 notation+0.458
 flakes+0.444
 aeros+0.443
Neg logit contributions
Sov-0.397
-0.360
 Zhu-0.357
vacc-0.351
 Qin-0.334
Token best
Token ID1266
Feature activation-1.83e-01

Pos logit contributions
 commute+0.247
 commuting+0.210
 notation+0.204
 flakes+0.198
 aeros+0.197
Neg logit contributions
Sov-0.230
-0.211
 Zhu-0.210
vacc-0.206
 Qin-0.198
Token:
Token ID25
Feature activation+1.11e-01

Pos logit contributions
 commute+0.135
 commuting+0.113
 notation+0.109
 flakes+0.106
 aeros+0.106
Neg logit contributions
Sov-0.151
-0.140
 Zhu-0.139
vacc-0.137
 Qin-0.132
Token[/
Token ID13412
Feature activation+4.69e+00

Pos logit contributions
Sov+0.054
+0.048
 Zhu+0.047
vacc+0.046
 Qin+0.043
Neg logit contributions
 commute-0.119
 commuting-0.106
 notation-0.104
 flakes-0.102
 aeros-0.101
Tokenb
Token ID65
Feature activation+9.13e-01

Pos logit contributions
Sov+2.855
+2.683
vacc+2.622
 Zhu+2.601
 Qin+2.428
Neg logit contributions
 commute-4.388
 commuting-3.844
 notation-3.676
 aeros-3.646
 flakes-3.627
Token]
Token ID60
Feature activation+5.03e-01

Pos logit contributions
Sov+0.810
+0.763
 Zhu+0.751
vacc+0.740
 Qin+0.718
Neg logit contributions
 commute-0.615
 commuting-0.509
 notation-0.486
 aeros-0.466
 flakes-0.466
Token 1
Token ID352
Feature activation+8.74e-01

Pos logit contributions
Sov+0.376
+0.346
 Zhu+0.344
vacc+0.337
 Qin+0.325
Neg logit contributions
 commute-0.410
 commuting-0.349
 notation-0.340
 flakes-0.329
 aeros-0.328
Token:
Token ID25
Feature activation+2.70e-02

Pos logit contributions
Sov+0.732
+0.680
 Zhu+0.673
vacc+0.661
 Qin+0.642
Neg logit contributions
 commute-0.636
 commuting-0.532
 notation-0.513
 flakes-0.494
 aeros-0.492
Token07
Token ID2998
Feature activation+2.04e-01

Pos logit contributions
Sov+0.018
+0.016
 Zhu+0.016
vacc+0.016
 Qin+0.015
Neg logit contributions
 commute-0.024
 commuting-0.021
 notation-0.020
 flakes-0.020
 aeros-0.020
Tokenb
Token ID65
Feature activation+6.34e-01

Pos logit contributions
 commute+0.298
 commuting+0.250
 notation+0.242
 flakes+0.233
 aeros+0.232
Neg logit contributions
Sov-0.330
-0.305
 Zhu-0.303
vacc-0.299
 Qin-0.287
Token]
Token ID60
Feature activation-9.73e-01

Pos logit contributions
Sov+0.548
+0.516
 Zhu+0.506
vacc+0.500
 Qin+0.486
Neg logit contributions
 commute-0.440
 commuting-0.367
 notation-0.347
 flakes-0.337
 aeros-0.336
TokenEst
Token ID22362
Feature activation-4.06e-02

Pos logit contributions
 commute+0.881
 commuting+0.764
 notation+0.747
 flakes+0.724
 aeros+0.722
Neg logit contributions
Sov-0.639
-0.579
 Zhu-0.576
vacc-0.564
 Qin-0.538
Tokenimate
Token ID1920
Feature activation-2.29e-02

Pos logit contributions
 commute+0.035
 commuting+0.030
 notation+0.029
 flakes+0.028
 aeros+0.028
Neg logit contributions
Sov-0.029
-0.026
 Zhu-0.026
vacc-0.026
 Qin-0.025
Token:
Token ID25
Feature activation-1.06e+00

Pos logit contributions
 commute+0.021
 commuting+0.018
 notation+0.018
 flakes+0.017
 aeros+0.017
Neg logit contributions
Sov-0.015
-0.014
 Zhu-0.013
vacc-0.013
 Qin-0.013
Token[/
Token ID13412
Feature activation+4.64e+00

Pos logit contributions
 commute+0.967
 commuting+0.840
 notation+0.821
 flakes+0.796
 aeros+0.793
Neg logit contributions
Sov-0.688
-0.618
 Zhu-0.615
vacc-0.605
 Qin-0.574
Tokenb
Token ID65
Feature activation+8.48e-01

Pos logit contributions
Sov+2.741
+2.599
vacc+2.554
 Zhu+2.503
 Qin+2.334
Neg logit contributions
 commute-4.380
 commuting-3.854
 notation-3.652
 aeros-3.646
 flakes-3.632
Token]
Token ID60
Feature activation+4.57e-01

Pos logit contributions
Sov+0.610
+0.569
 Zhu+0.557
vacc+0.548
 Qin+0.528
Neg logit contributions
 commute-0.711
 commuting-0.613
 notation-0.588
 flakes-0.573
 aeros-0.573
Token 1
Token ID352
Feature activation+8.10e-01

Pos logit contributions
Sov+0.349
+0.321
 Zhu+0.319
vacc+0.313
 Qin+0.302
Neg logit contributions
 commute-0.366
 commuting-0.311
 notation-0.302
 flakes-0.292
 aeros-0.292
Token:
Token ID25
Feature activation-8.43e-02

Pos logit contributions
Sov+0.619
+0.571
 Zhu+0.567
vacc+0.556
 Qin+0.536
Neg logit contributions
 commute-0.647
 commuting-0.550
 notation-0.534
 flakes-0.517
 aeros-0.515
Token20
Token ID1238
Feature activation+8.91e-01

Pos logit contributions
 commute+0.075
 commuting+0.065
 notation+0.063
 flakes+0.061
 aeros+0.061
Neg logit contributions
Sov-0.057
-0.052
 Zhu-0.051
vacc-0.050
 Qin-0.048
Token varieties
Token ID20328
Feature activation+4.29e-01

Pos logit contributions
Sov+0.215
+0.201
 Zhu+0.201
vacc+0.197
 Qin+0.192
Neg logit contributions
 commute-0.154
 commuting-0.124
 notation-0.121
 flakes-0.114
 aeros-0.114
Token for
Token ID329
Feature activation+1.09e-01

Pos logit contributions
Sov+0.322
+0.302
 Zhu+0.299
vacc+0.292
 Qin+0.282
Neg logit contributions
 commute-0.344
 commuting-0.291
 notation-0.285
 aeros-0.274
 flakes-0.273
Token children
Token ID1751
Feature activation-9.06e-01

Pos logit contributions
Sov+0.088
+0.081
 Zhu+0.081
vacc+0.079
 Qin+0.077
Neg logit contributions
 commute-0.083
 commuting-0.069
 notation-0.068
 flakes-0.065
 aeros-0.065
Token of
Token ID286
Feature activation+1.10e+00

Pos logit contributions
 commute+0.698
 commuting+0.586
 notation+0.573
 flakes+0.551
 aeros+0.551
Neg logit contributions
Sov-0.715
-0.665
 Zhu-0.660
vacc-0.649
 Qin-0.625
Token all
Token ID477
Feature activation-2.13e-01

Pos logit contributions
Sov+0.798
+0.738
 Zhu+0.735
vacc+0.719
 Qin+0.692
Neg logit contributions
 commute-0.903
 commuting-0.769
 notation-0.755
 flakes-0.732
 aeros-0.727
Token age
Token ID2479
Feature activation+4.61e+00

Pos logit contributions
 commute+0.149
 commuting+0.123
 notation+0.120
 flakes+0.115
 aeros+0.115
Neg logit contributions
Sov-0.183
-0.171
 Zhu-0.169
vacc-0.167
 Qin-0.161
Token groups
Token ID2628
Feature activation-3.89e-01

Pos logit contributions
Sov+3.293
+3.107
 Zhu+3.048
vacc+3.008
 Qin+2.851
Neg logit contributions
 commute-3.710
 commuting-3.121
 notation-3.070
 flakes-2.999
 aeros-2.999
Token.
Token ID13
Feature activation-6.36e-01

Pos logit contributions
 commute+0.324
 commuting+0.276
 notation+0.272
 flakes+0.262
 aeros+0.262
Neg logit contributions
Sov-0.282
-0.262
 Zhu-0.259
vacc-0.255
 Qin-0.244
TokenEvery
Token ID6109
Feature activation-9.70e-01

Pos logit contributions
 commute+0.498
 commuting+0.421
 notation+0.409
 flakes+0.395
 aeros+0.393
Neg logit contributions
Sov-0.499
-0.458
 Zhu-0.455
vacc-0.449
 Qin-0.431
Token parent
Token ID2560
Feature activation-1.18e+00

Pos logit contributions
 commute+0.711
 commuting+0.594
 notation+0.576
 flakes+0.554
 aeros+0.551
Neg logit contributions
Sov-0.809
-0.749
 Zhu-0.744
vacc-0.734
 Qin-0.707
Token loves
Token ID10408
Feature activation-6.54e-02

Pos logit contributions
 commute+0.877
 commuting+0.734
 notation+0.714
 flakes+0.686
 aeros+0.684
Neg logit contributions
Sov-0.969
-0.897
 Zhu-0.891
vacc-0.878
 Qin-0.846
Token younger
Token ID7099
Feature activation+1.21e+00

Pos logit contributions
Sov+0.835
+0.783
 Zhu+0.775
vacc+0.766
 Qin+0.737
Neg logit contributions
 commute-0.751
 commuting-0.624
 notation-0.609
 flakes-0.586
 aeros-0.584
Token than
Token ID621
Feature activation+1.41e-01

Pos logit contributions
Sov+1.136
+1.061
 Zhu+1.056
vacc+1.042
 Qin+1.010
Neg logit contributions
 commute-0.753
 commuting-0.608
 notation-0.586
 flakes-0.558
 aeros-0.555
Token 15
Token ID1315
Feature activation+1.29e+00

Pos logit contributions
Sov+0.108
+0.098
 Zhu+0.098
vacc+0.096
 Qin+0.092
Neg logit contributions
 commute-0.114
 commuting-0.097
 notation-0.095
 flakes-0.091
 aeros-0.091
Token years
Token ID812
Feature activation+4.26e-01

Pos logit contributions
Sov+0.998
+0.932
 Zhu+0.925
vacc+0.912
 Qin+0.877
Neg logit contributions
 commute-1.007
 commuting-0.843
 notation-0.827
 flakes-0.797
 aeros-0.792
Token of
Token ID286
Feature activation+1.10e-01

Pos logit contributions
Sov+0.266
+0.244
 Zhu+0.243
vacc+0.236
 Qin+0.226
Neg logit contributions
 commute-0.396
 commuting-0.343
 notation-0.338
 flakes-0.329
 aeros-0.328
Token age
Token ID2479
Feature activation+4.56e+00

Pos logit contributions
Sov+0.097
+0.089
 Zhu+0.088
vacc+0.087
��+0.084
Neg logit contributions
 commute-0.077
 commuting-0.064
 notation-0.062
 aeros-0.059
 flakes-0.059
Token,
Token ID11
Feature activation+7.59e-01

Pos logit contributions
Sov+3.253
+3.105
 Zhu+3.064
vacc+2.992
 Qin+2.902
Neg logit contributions
 commute-3.649
 commuting-3.057
 notation-3.018
 flakes-2.939
 aeros-2.933
Token according
Token ID1864
Feature activation+5.42e-01

Pos logit contributions
Sov+0.623
+0.577
 Zhu+0.575
vacc+0.565
 Qin+0.545
Neg logit contributions
 commute-0.563
 commuting-0.471
 notation-0.458
 flakes-0.442
 aeros-0.439
Token to
Token ID284
Feature activation+5.58e-01

Pos logit contributions
Sov+0.419
+0.383
 Zhu+0.381
vacc+0.378
��+0.364
Neg logit contributions
 commute-0.429
 commuting-0.363
 notation-0.355
 flakes-0.342
 aeros-0.340
Token the
Token ID262
Feature activation+3.52e-02

Pos logit contributions
Sov+0.416
+0.382
 Zhu+0.380
vacc+0.372
 Qin+0.358
Neg logit contributions
 commute-0.458
 commuting-0.391
 notation-0.381
 flakes-0.368
 aeros-0.366
Token online
Token ID2691
Feature activation-1.71e-01

Pos logit contributions
Sov+0.028
+0.026
 Zhu+0.026
vacc+0.025
 Qin+0.024
Neg logit contributions
 commute-0.027
 commuting-0.023
 notation-0.022
 flakes-0.021
 aeros-0.021
Tokenb
Token ID65
Feature activation+7.36e-01

Pos logit contributions
 commute+0.014
 commuting+0.012
 notation+0.012
 flakes+0.011
 aeros+0.011
Neg logit contributions
Sov-0.010
-0.009
 Zhu-0.009
vacc-0.009
 Qin-0.009
Token]
Token ID60
Feature activation-6.80e-01

Pos logit contributions
Sov+0.703
+0.659
 Zhu+0.654
vacc+0.645
 Qin+0.626
Neg logit contributions
 commute-0.450
 commuting-0.362
 notation-0.347
 flakes-0.331
 aeros-0.329
TokenEst
Token ID22362
Feature activation+8.47e-01

Pos logit contributions
 commute+0.568
 commuting+0.486
 notation+0.473
 flakes+0.458
 aeros+0.456
Neg logit contributions
Sov-0.499
-0.456
 Zhu-0.453
vacc-0.445
 Qin-0.427
Tokenimate
Token ID1920
Feature activation+1.76e-01

Pos logit contributions
Sov+0.593
+0.539
 Zhu+0.535
vacc+0.526
 Qin+0.502
Neg logit contributions
 commute-0.736
 commuting-0.631
 notation-0.619
 flakes-0.596
 aeros-0.595
Token:
Token ID25
Feature activation-4.63e-01

Pos logit contributions
Sov+0.155
+0.143
 Zhu+0.143
vacc+0.141
 Qin+0.136
Neg logit contributions
 commute-0.121
 commuting-0.099
 notation-0.096
 flakes-0.092
 aeros-0.092
Token[/
Token ID13412
Feature activation+4.56e+00

Pos logit contributions
 commute+0.495
 commuting+0.439
 notation+0.431
 flakes+0.420
 aeros+0.419
Neg logit contributions
Sov-0.231
-0.201
 Zhu-0.199
vacc-0.195
 Qin-0.181
Tokenb
Token ID65
Feature activation+6.93e-01

Pos logit contributions
Sov+2.788
+2.598
vacc+2.539
 Zhu+2.515
 Qin+2.350
Neg logit contributions
 commute-4.285
 commuting-3.753
 notation-3.597
 aeros-3.553
 flakes-3.533
Token]
Token ID60
Feature activation+6.69e-01

Pos logit contributions
Sov+0.671
+0.627
 Zhu+0.624
vacc+0.617
 Qin+0.597
Neg logit contributions
 commute-0.415
 commuting-0.331
 notation-0.319
 flakes-0.303
 aeros-0.302
Token 00
Token ID3571
Feature activation+2.80e-01

Pos logit contributions
Sov+0.473
+0.435
 Zhu+0.433
vacc+0.421
 Qin+0.407
Neg logit contributions
 commute-0.572
 commuting-0.491
 notation-0.478
 flakes-0.463
 aeros-0.463
Token:
Token ID25
Feature activation-6.70e-01

Pos logit contributions
Sov+0.235
+0.218
 Zhu+0.216
vacc+0.213
 Qin+0.206
Neg logit contributions
 commute-0.203
 commuting-0.170
 notation-0.164
 flakes-0.158
 aeros-0.157
Token55
Token ID2816
Feature activation+3.77e-01

Pos logit contributions
 commute+0.585
 commuting+0.504
 notation+0.496
 flakes+0.478
 aeros+0.477
Neg logit contributions
Sov-0.458
 Zhu-0.413
-0.411
vacc-0.408
��-0.396
Token reality
Token ID3950
Feature activation-1.18e+00

Pos logit contributions
Sov+0.389
+0.360
 Zhu+0.358
vacc+0.351
 Qin+0.340
Neg logit contributions
 commute-0.395
 commuting-0.334
 notation-0.326
 flakes-0.314
 aeros-0.312
Token this
Token ID428
Feature activation+5.48e-01

Pos logit contributions
 commute+0.865
 commuting+0.722
 notation+0.701
 flakes+0.673
 aeros+0.670
Neg logit contributions
Sov-0.991
-0.918
 Zhu-0.912
vacc-0.898
 Qin-0.867
Token is
Token ID318
Feature activation+4.72e-01

Pos logit contributions
Sov+0.453
+0.420
 Zhu+0.417
vacc+0.410
 Qin+0.399
Neg logit contributions
 commute-0.402
 commuting-0.337
 notation-0.324
 flakes-0.313
 aeros-0.312
Token seldom
Token ID25129
Feature activation+1.23e+00

Pos logit contributions
Sov+0.436
+0.406
 Zhu+0.403
vacc+0.397
 Qin+0.388
Neg logit contributions
 commute-0.304
 commuting-0.246
 notation-0.237
 flakes-0.227
 aeros-0.226
Token the
Token ID262
Feature activation+1.22e+00

Pos logit contributions
Sov+0.866
+0.793
 Zhu+0.782
vacc+0.767
 Qin+0.739
Neg logit contributions
 commute-1.058
 commuting-0.910
 notation-0.888
 flakes-0.864
 aeros-0.857
Token case
Token ID1339
Feature activation+4.55e+00

Pos logit contributions
Sov+0.971
+0.899
 Zhu+0.895
vacc+0.875
 Qin+0.852
Neg logit contributions
 commute-0.925
 commuting-0.781
 notation-0.753
 flakes-0.736
 aeros-0.723
Token.
Token ID13
Feature activation+1.22e+00

Pos logit contributions
Sov+3.236
+3.159
 Zhu+3.027
vacc+2.915
 Qin+2.863
Neg logit contributions
 commute-3.706
 commuting-3.162
 notation-3.072
 flakes-2.998
 aeros-2.985
Token
Token ID198
Feature activation+7.41e-01

Pos logit contributions
Sov+0.926
+0.860
 Zhu+0.853
vacc+0.830
 Qin+0.810
Neg logit contributions
 commute-0.980
 commuting-0.833
 notation-0.808
 flakes-0.778
 aeros-0.775
Token
Token ID198
Feature activation+7.65e-01

Pos logit contributions
Sov+0.656
+0.612
 Zhu+0.608
vacc+0.599
 Qin+0.580
Neg logit contributions
 commute-0.505
 commuting-0.416
 notation-0.401
 flakes-0.384
 aeros-0.382
TokenTo
Token ID2514
Feature activation+9.62e-01

Pos logit contributions
Sov+0.525
+0.478
 Zhu+0.471
vacc+0.464
 Qin+0.443
Neg logit contributions
 commute-0.678
 commuting-0.586
 notation-0.570
 flakes-0.553
 aeros-0.551
Token understand
Token ID1833
Feature activation+7.57e-01

Pos logit contributions
Sov+0.731
+0.673
 Zhu+0.668
vacc+0.657
 Qin+0.632
Neg logit contributions
 commute-0.772
 commuting-0.658
 notation-0.640
 flakes-0.618
 aeros-0.615
Token the
Token ID262
Feature activation+1.13e+00

Pos logit contributions
Sov+1.521
+1.405
 Zhu+1.401
vacc+1.353
 Qin+1.314
Neg logit contributions
 commute-1.756
 commuting-1.512
 notation-1.480
 flakes-1.444
 aeros-1.433
Token White
Token ID2635
Feature activation+6.47e-01

Pos logit contributions
Sov+0.909
+0.852
 Zhu+0.845
vacc+0.824
 Qin+0.801
Neg logit contributions
 commute-0.842
 commuting-0.705
 notation-0.686
 flakes-0.664
 aeros-0.658
Token House
Token ID2097
Feature activation-3.73e-01

Pos logit contributions
Sov+0.508
+0.463
 Zhu+0.459
vacc+0.457
��+0.437
Neg logit contributions
 commute-0.505
 commuting-0.428
 notation-0.416
 flakes-0.403
 aeros-0.400
Token at
Token ID379
Feature activation+1.06e-01

Pos logit contributions
 commute+0.260
 commuting+0.215
 notation+0.209
 flakes+0.201
 aeros+0.199
Neg logit contributions
Sov-0.323
-0.301
 Zhu-0.300
vacc-0.295
 Qin-0.285
Token the
Token ID262
Feature activation+7.89e-01

Pos logit contributions
Sov+0.078
+0.072
 Zhu+0.072
vacc+0.070
 Qin+0.068
Neg logit contributions
 commute-0.087
 commuting-0.074
 notation-0.072
 flakes-0.070
 aeros-0.070
Token age
Token ID2479
Feature activation+4.52e+00

Pos logit contributions
Sov+0.577
+0.533
 Zhu+0.530
vacc+0.516
 Qin+0.499
Neg logit contributions
 commute-0.652
 commuting-0.558
 notation-0.542
 flakes-0.527
 aeros-0.526
Token of
Token ID286
Feature activation+1.05e+00

Pos logit contributions
Sov+3.600
+3.410
 Zhu+3.387
vacc+3.285
 Qin+3.207
Neg logit contributions
 commute-3.371
 commuting-2.822
 notation-2.738
 flakes-2.663
 aeros-2.637
Token just
Token ID655
Feature activation-6.35e-01

Pos logit contributions
Sov+0.768
+0.708
 Zhu+0.703
vacc+0.689
 Qin+0.663
Neg logit contributions
 commute-0.865
 commuting-0.738
 notation-0.719
 flakes-0.697
 aeros-0.693
Token 25
Token ID1679
Feature activation+1.20e+00

Pos logit contributions
 commute+0.509
 commuting+0.434
 notation+0.422
 flakes+0.405
 aeros+0.405
Neg logit contributions
Sov-0.489
-0.444
 Zhu-0.442
vacc-0.439
��-0.419
Token,
Token ID11
Feature activation+6.85e-01

Pos logit contributions
Sov+1.008
+0.957
 Zhu+0.947
vacc+0.924
 Qin+0.893
Neg logit contributions
 commute-0.858
 commuting-0.710
 notation-0.691
 flakes-0.663
 aeros-0.663
Token one
Token ID530
Feature activation+2.82e-01

Pos logit contributions
Sov+0.539
+0.505
 Zhu+0.502
vacc+0.488
 Qin+0.474
Neg logit contributions
 commute-0.528
 commuting-0.443
 notation-0.434
 flakes-0.417
 aeros-0.417
Token at
Token ID379
Feature activation+8.72e-01

Pos logit contributions
Sov+0.369
+0.338
 Zhu+0.336
vacc+0.331
 Qin+0.317
Neg logit contributions
 commute-0.395
 commuting-0.336
 notation-0.327
 flakes-0.316
 aeros-0.315
Token medium
Token ID7090
Feature activation+4.46e+00

Pos logit contributions
Sov+0.644
+0.597
 Zhu+0.594
vacc+0.577
 Qin+0.558
Neg logit contributions
 commute-0.718
 commuting-0.613
 notation-0.594
 flakes-0.571
 aeros-0.566
Token-
Token ID12
Feature activation+4.29e-01

Pos logit contributions
Sov+3.768
+3.609
 Zhu+3.557
vacc+3.498
 Qin+3.407
Neg logit contributions
 commute-3.019
 commuting-2.522
 notation-2.356
 flakes-2.228
minster-2.214
Tokenhigh
Token ID8929
Feature activation+1.45e+00

Pos logit contributions
Sov+0.261
+0.238
vacc+0.233
 Zhu+0.232
 Qin+0.217
Neg logit contributions
 commute-0.410
 commuting-0.359
 notation-0.349
 flakes-0.339
 aeros-0.338
Token heat
Token ID4894
Feature activation+8.56e-02

Pos logit contributions
Sov+1.291
+1.227
 Zhu+1.217
vacc+1.195
 Qin+1.166
Neg logit contributions
 commute-0.954
 commuting-0.780
 notation-0.732
 flakes-0.701
 aeros-0.694
Token until
Token ID1566
Feature activation+4.47e+00

Pos logit contributions
Sov+0.062
+0.057
 Zhu+0.056
vacc+0.055
 Qin+0.053
Neg logit contributions
 commute-0.072
 commuting-0.062
 notation-0.060
 flakes-0.058
 aeros-0.058
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
Sov+3.479
 Zhu+3.388
+3.336
vacc+3.232
 Qin+3.214
Neg logit contributions
 commute-3.307
 commuting-2.771
 notation-2.641
minster-2.499
 aeros-2.474
Token onion
Token ID21670
Feature activation+2.15e+00

Pos logit contributions
Sov+0.758
 Zhu+0.702
+0.701
vacc+0.680
 Qin+0.661
Neg logit contributions
 commute-0.826
 commuting-0.706
 notation-0.681
 aeros-0.650
minster-0.641
Token is
Token ID318
Feature activation+1.03e+00

Pos logit contributions
Sov+1.732
+1.618
 Zhu+1.612
vacc+1.574
 Qin+1.522
Neg logit contributions
 commute-1.615
 commuting-1.364
 notation-1.309
 aeros-1.234
minster-1.208
Token clear
Token ID1598
Feature activation+1.47e+00

Pos logit contributions
Sov+0.922
+0.872
 Zhu+0.871
vacc+0.852
 Qin+0.827
Neg logit contributions
 commute-0.683
 commuting-0.558
 notation-0.539
 aeros-0.504
 flakes-0.497
Token or
Token ID393
Feature activation-4.20e-01

Pos logit contributions
Sov+1.136
+1.061
 Zhu+1.054
vacc+1.033
 Qin+0.996
Neg logit contributions
 commute-1.152
 commuting-0.975
 notation-0.939
 aeros-0.901
 flakes-0.895
Token oil
Token ID3056
Feature activation+1.17e+00

Pos logit contributions
Sov+1.170
+1.099
 Zhu+1.095
vacc+1.075
 Qin+1.042
Neg logit contributions
 commute-0.811
 commuting-0.656
 notation-0.633
 aeros-0.597
minster-0.583
Token and
Token ID290
Feature activation-2.42e-01

Pos logit contributions
Sov+0.904
+0.840
 Zhu+0.834
vacc+0.817
 Qin+0.788
Neg logit contributions
 commute-0.916
 commuting-0.774
 notation-0.751
 aeros-0.715
 flakes-0.708
Token fry
Token ID32959
Feature activation+1.90e+00

Pos logit contributions
 commute+0.191
 commuting+0.162
 notation+0.158
 flakes+0.152
 aeros+0.151
Neg logit contributions
Sov-0.188
-0.173
 Zhu-0.172
vacc-0.169
 Qin-0.163
Token it
Token ID340
Feature activation+4.88e-01

Pos logit contributions
Sov+1.402
+1.298
 Zhu+1.292
vacc+1.263
 Qin+1.217
Neg logit contributions
 commute-1.557
 commuting-1.328
 notation-1.292
 aeros-1.242
 flakes-1.241
Token at
Token ID379
Feature activation+8.72e-01

Pos logit contributions
Sov+0.369
+0.338
 Zhu+0.336
vacc+0.331
 Qin+0.317
Neg logit contributions
 commute-0.395
 commuting-0.336
 notation-0.327
 flakes-0.316
 aeros-0.315
Token medium
Token ID7090
Feature activation+4.46e+00

Pos logit contributions
Sov+0.644
+0.597
 Zhu+0.594
vacc+0.577
 Qin+0.558
Neg logit contributions
 commute-0.718
 commuting-0.613
 notation-0.594
 flakes-0.571
 aeros-0.566
Token-
Token ID12
Feature activation+4.29e-01

Pos logit contributions
Sov+3.768
+3.609
 Zhu+3.557
vacc+3.498
 Qin+3.407
Neg logit contributions
 commute-3.019
 commuting-2.522
 notation-2.356
 flakes-2.228
minster-2.214
Tokenhigh
Token ID8929
Feature activation+1.45e+00

Pos logit contributions
Sov+0.261
+0.238
vacc+0.233
 Zhu+0.232
 Qin+0.217
Neg logit contributions
 commute-0.410
 commuting-0.359
 notation-0.349
 flakes-0.339
 aeros-0.338
Token heat
Token ID4894
Feature activation+8.56e-02

Pos logit contributions
Sov+1.291
+1.227
 Zhu+1.217
vacc+1.195
 Qin+1.166
Neg logit contributions
 commute-0.954
 commuting-0.780
 notation-0.732
 flakes-0.701
 aeros-0.694
Token until
Token ID1566
Feature activation+4.47e+00

Pos logit contributions
Sov+0.062
+0.057
 Zhu+0.056
vacc+0.055
 Qin+0.053
Neg logit contributions
 commute-0.072
 commuting-0.062
 notation-0.060
 flakes-0.058
 aeros-0.058
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
Sov+3.479
 Zhu+3.388
+3.336
vacc+3.232
 Qin+3.214
Neg logit contributions
 commute-3.307
 commuting-2.771
 notation-2.641
minster-2.499
 aeros-2.474
Token when
Token ID618
Feature activation+1.69e+00

Pos logit contributions
 commute+0.198
 commuting+0.168
 notation+0.164
 flakes+0.158
 aeros+0.158
Neg logit contributions
Sov-0.188
-0.173
 Zhu-0.172
vacc-0.169
 Qin-0.162
Token perform
Token ID1620
Feature activation-1.18e+00

Pos logit contributions
Sov+1.216
+1.113
 Zhu+1.109
vacc+1.079
 Qin+1.044
Neg logit contributions
 commute-1.418
 commuting-1.214
 notation-1.178
 flakes-1.148
 aeros-1.142
Token a
Token ID257
Feature activation-1.56e-01

Pos logit contributions
 commute+0.939
 commuting+0.796
 notation+0.775
 flakes+0.748
 aeros+0.745
Neg logit contributions
Sov-0.914
-0.840
 Zhu-0.834
vacc-0.821
 Qin-0.789
Token R
Token ID371
Feature activation-4.21e-02

Pos logit contributions
 commute+0.110
 commuting+0.091
 notation+0.088
 flakes+0.085
 aeros+0.085
Neg logit contributions
Sov-0.133
-0.124
 Zhu-0.123
vacc-0.121
 Qin-0.117
TokenOP
Token ID3185
Feature activation-3.42e-01

Pos logit contributions
 commute+0.036
 commuting+0.031
 notation+0.030
 flakes+0.030
 aeros+0.029
Neg logit contributions
Sov-0.030
-0.027
 Zhu-0.027
vacc-0.026
 Qin-0.025
Token exploit
Token ID14561
Feature activation-4.93e+00

Pos logit contributions
 commute+0.247
 commuting+0.207
 notation+0.200
 flakes+0.194
 aeros+0.192
Neg logit contributions
Sov-0.287
-0.266
 Zhu-0.264
vacc-0.260
 Qin-0.252
Token,
Token ID11
Feature activation-5.28e-01

Pos logit contributions
 commute+3.400
 commuting+2.789
 notation+2.753
 flakes+2.593
 aeros+2.577
Neg logit contributions
Sov-4.284
-3.933
vacc-3.915
 Zhu-3.906
��-3.730
Token there
Token ID612
Feature activation-5.40e-01

Pos logit contributions
 commute+0.433
 commuting+0.369
 notation+0.360
 flakes+0.347
 aeros+0.346
Neg logit contributions
Sov-0.395
-0.362
 Zhu-0.359
vacc-0.354
 Qin-0.339
Token's
Token ID338
Feature activation+4.58e-01

Pos logit contributions
 commute+0.376
 commuting+0.311
 notation+0.300
 flakes+0.288
 aeros+0.287
Neg logit contributions
Sov-0.470
-0.436
 Zhu-0.434
vacc-0.427
 Qin-0.413
Token a
Token ID257
Feature activation-9.06e-01

Pos logit contributions
Sov+0.356
+0.328
 Zhu+0.327
vacc+0.320
 Qin+0.309
Neg logit contributions
 commute-0.360
 commuting-0.305
 notation-0.294
 flakes-0.285
 aeros-0.284
Token very
Token ID845
Feature activation+1.95e+00

Pos logit contributions
 commute+0.711
 commuting+0.601
 notation+0.587
 flakes+0.564
 aeros+0.561
Neg logit contributions
Sov-0.710
-0.653
 Zhu-0.647
vacc-0.639
 Qin-0.613
Token center
Token ID3641
Feature activation+1.19e+00

Pos logit contributions
Sov+0.931
+0.848
 Zhu+0.843
vacc+0.821
 Qin+0.787
Neg logit contributions
 commute-1.238
 commuting-1.071
 notation-1.050
 flakes-1.028
 aeros-1.017
Token for
Token ID329
Feature activation+2.33e-01

Pos logit contributions
Sov+0.941
+0.873
 Zhu+0.865
vacc+0.849
 Qin+0.820
Neg logit contributions
 commute-0.915
 commuting-0.771
 notation-0.753
 flakes-0.730
 aeros-0.726
Token the
Token ID262
Feature activation+1.89e-01

Pos logit contributions
Sov+0.171
+0.157
 Zhu+0.156
vacc+0.153
 Qin+0.147
Neg logit contributions
 commute-0.194
 commuting-0.165
 notation-0.162
 flakes-0.156
 aeros-0.156
Token city
Token ID1748
Feature activation-4.02e-01

Pos logit contributions
Sov+0.156
+0.145
 Zhu+0.144
vacc+0.142
 Qin+0.137
Neg logit contributions
 commute-0.139
 commuting-0.116
 notation-0.113
 flakes-0.109
 aeros-0.109
Token,"
Token ID553
Feature activation-1.19e+00

Pos logit contributions
 commute+0.323
 commuting+0.274
 notation+0.269
 flakes+0.259
 aeros+0.258
Neg logit contributions
Sov-0.305
-0.281
 Zhu-0.279
vacc-0.274
 Qin-0.263
Token Ful
Token ID28040
Feature activation-4.88e+00

Pos logit contributions
 commute+0.835
 commuting+0.691
 notation+0.673
 flakes+0.644
 aeros+0.643
Neg logit contributions
Sov-1.020
-0.948
 Zhu-0.948
vacc-0.928
 Qin-0.900
Tokenop
Token ID404
Feature activation-3.33e-01

Pos logit contributions
 commute+4.793
 commuting+4.168
 notation+4.125
aster+4.117
 flakes+4.032
Neg logit contributions
Sov-2.746
 Zhu-2.447
-2.347
��-2.311
��極-2.285
Token said
Token ID531
Feature activation-1.14e+00

Pos logit contributions
 commute+0.258
 commuting+0.217
 notation+0.212
 flakes+0.205
 aeros+0.204
Neg logit contributions
Sov-0.261
-0.244
 Zhu-0.241
vacc-0.236
 Qin-0.229
Token.
Token ID13
Feature activation-2.85e-01

Pos logit contributions
 commute+0.907
 commuting+0.769
 notation+0.750
 flakes+0.724
 aeros+0.721
Neg logit contributions
Sov-0.876
-0.807
 Zhu-0.801
vacc-0.787
 Qin-0.757
Token
Token ID198
Feature activation-5.51e-01

Pos logit contributions
 commute+0.214
 commuting+0.180
 notation+0.176
 aeros+0.169
 flakes+0.169
Neg logit contributions
Sov-0.231
 Zhu-0.215
-0.215
vacc-0.210
 Qin-0.204
Token
Token ID198
Feature activation-2.70e-01

Pos logit contributions
 commute+0.362
 commuting+0.295
 notation+0.286
 flakes+0.273
 aeros+0.272
Neg logit contributions
Sov-0.500
-0.464
 Zhu-0.463
vacc-0.457
 Qin-0.441
Token Monday
Token ID3321
Feature activation+7.66e-01

Pos logit contributions
Sov+0.050
 Zhu+0.046
+0.046
vacc+0.045
 Qin+0.044
Neg logit contributions
 commute-0.044
 commuting-0.037
 notation-0.036
 flakes-0.034
 aeros-0.034
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
Sov+0.589
+0.553
 Zhu+0.552
vacc+0.536
 Qin+0.520
Neg logit contributions
 commute-0.594
 commuting-0.504
 notation-0.496
 flakes-0.476
 aeros-0.472
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
 commute+0.257
 commuting+0.216
 notation+0.210
 flakes+0.198
 aeros+0.197
Neg logit contributions
Sov-0.287
 Zhu-0.268
-0.268
vacc-0.261
 Qin-0.256
Token
Token ID198
Feature activation+5.10e-02

Pos logit contributions
 commute+0.091
 commuting+0.074
 notation+0.072
 flakes+0.069
 aeros+0.068
Neg logit contributions
Sov-0.124
-0.115
 Zhu-0.115
vacc-0.113
 Qin-0.110
TokenATT
Token ID17139
Feature activation-1.32e+00

Pos logit contributions
Sov+0.036
+0.033
 Zhu+0.032
vacc+0.032
 Qin+0.030
Neg logit contributions
 commute-0.045
 commuting-0.038
 notation-0.037
 flakes-0.036
 aeros-0.036
TokenENTION
Token ID45589
Feature activation-4.80e+00

Pos logit contributions
 commute+1.218
 commuting+1.058
 notation+1.033
 flakes+1.004
 aeros+1.000
Neg logit contributions
Sov-0.853
-0.773
 Zhu-0.765
vacc-0.752
 Qin-0.715
Token,
Token ID837
Feature activation-1.68e+00

Pos logit contributions
 commute+3.578
 commuting+3.003
 notation+2.913
 flakes+2.826
 aeros+2.824
Neg logit contributions
Sov-3.933
 Zhu-3.569
-3.557
vacc-3.511
 Qin-3.370
Token en
Token ID551
Feature activation-1.41e+00

Pos logit contributions
 commute+1.325
 commuting+1.122
 notation+1.093
 flakes+1.051
 aeros+1.046
Neg logit contributions
Sov-1.309
-1.209
 Zhu-1.200
vacc-1.182
 Qin-1.136
Token ra
Token ID2179
Feature activation-7.65e-01

Pos logit contributions
 commute+1.118
 commuting+0.948
 notation+0.923
 flakes+0.891
 aeros+0.887
Neg logit contributions
Sov-1.085
-0.996
 Zhu-0.990
vacc-0.974
 Qin-0.936
Tokenison
Token ID1653
Feature activation+2.26e-01

Pos logit contributions
 commute+0.647
 commuting+0.556
 notation+0.540
 flakes+0.522
 aeros+0.520
Neg logit contributions
Sov-0.549
-0.505
 Zhu-0.501
vacc-0.493
 Qin-0.472
Token des
Token ID748
Feature activation+1.95e-01

Pos logit contributions
Sov+0.180
+0.173
 Zhu+0.169
vacc+0.165
 Qin+0.160
Neg logit contributions
 commute-0.169
 commuting-0.143
 notation-0.138
 flakes-0.134
 aeros-0.131
Token and
Token ID290
Feature activation+4.39e-01

Pos logit contributions
 commute+0.533
 commuting+0.444
 notation+0.432
 flakes+0.413
 aeros+0.412
Neg logit contributions
Sov-0.612
-0.570
 Zhu-0.566
vacc-0.556
 Qin-0.538
Token his
Token ID465
Feature activation-2.47e-01

Pos logit contributions
Sov+0.303
 Zhu+0.277
+0.276
vacc+0.269
 Qin+0.260
Neg logit contributions
 commute-0.383
 commuting-0.329
 notation-0.322
 flakes-0.311
 aeros-0.310
Token co
Token ID763
Feature activation-7.72e-01

Pos logit contributions
 commute+0.175
 commuting+0.146
 notation+0.142
 flakes+0.136
 aeros+0.135
Neg logit contributions
Sov-0.210
-0.195
 Zhu-0.194
vacc-0.191
 Qin-0.185
Token-
Token ID12
Feature activation-3.99e-01

Pos logit contributions
 commute+0.587
 commuting+0.494
 notation+0.481
 flakes+0.464
 aeros+0.461
Neg logit contributions
Sov-0.621
-0.574
 Zhu-0.569
vacc-0.563
 Qin-0.542
Tokenp
Token ID79
Feature activation-3.59e-01

Pos logit contributions
 commute+0.313
 commuting+0.265
 notation+0.258
 flakes+0.249
 aeros+0.248
Neg logit contributions
Sov-0.312
-0.287
 Zhu-0.285
vacc-0.281
 Qin-0.270
Tokenil
Token ID346
Feature activation-4.80e+00

Pos logit contributions
 commute+0.299
 commuting+0.257
 notation+0.249
 aeros+0.240
 flakes+0.240
Neg logit contributions
Sov-0.262
-0.241
 Zhu-0.239
vacc-0.238
 Qin-0.226
Tokenots
Token ID1747
Feature activation-1.38e+00

Pos logit contributions
 commute+2.580
 commuting+1.999
 notation+1.900
 flakes+1.811
 aeros+1.798
Neg logit contributions
Sov-4.937
-4.640
 Zhu-4.606
vacc-4.551
 Qin-4.423
Token tried
Token ID3088
Feature activation-6.85e-01

Pos logit contributions
 commute+0.972
 commuting+0.807
 notation+0.783
 flakes+0.751
 aeros+0.747
Neg logit contributions
Sov-1.180
-1.096
 Zhu-1.089
vacc-1.074
 Qin-1.037
Token to
Token ID284
Feature activation-8.09e-01

Pos logit contributions
 commute+0.552
 commuting+0.470
 notation+0.457
 flakes+0.442
 aeros+0.440
Neg logit contributions
Sov-0.521
-0.478
 Zhu-0.475
vacc-0.468
 Qin-0.449
Token stop
Token ID2245
Feature activation+1.16e+00

Pos logit contributions
 commute+0.583
 commuting+0.485
 notation+0.470
 flakes+0.452
 aeros+0.450
Neg logit contributions
Sov-0.684
-0.634
 Zhu-0.630
vacc-0.621
 Qin-0.599
Token them
Token ID606
Feature activation-1.98e-02

Pos logit contributions
Sov+0.809
 Zhu+0.749
+0.741
vacc+0.726
 Qin+0.711
Neg logit contributions
 commute-0.981
 commuting-0.837
 notation-0.824
 flakes-0.793
 aeros-0.790
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
 commute+0.029
 commuting+0.024
 notation+0.024
 flakes+0.023
 aeros+0.023
Neg logit contributions
Sov-0.034
-0.032
 Zhu-0.032
vacc-0.031
 Qin-0.030
Token change
Token ID1487
Feature activation-2.12e+00

Pos logit contributions
 commute+0.153
 commuting+0.128
 notation+0.124
 flakes+0.119
 aeros+0.118
Neg logit contributions
Sov-0.179
-0.166
 Zhu-0.165
vacc-0.162
 Qin-0.157
Token the
Token ID262
Feature activation-4.89e-01

Pos logit contributions
 commute+1.746
 commuting+1.486
 notation+1.456
 flakes+1.399
 aeros+1.392
Neg logit contributions
Sov-1.590
-1.441
 Zhu-1.428
vacc-1.423
 Qin-1.343
Token Fire
Token ID3764
Feature activation+1.08e+00

Pos logit contributions
 commute+0.378
 commuting+0.319
 notation+0.310
 flakes+0.299
 aeros+0.298
Neg logit contributions
Sov-0.388
-0.357
 Zhu-0.355
vacc-0.350
 Qin-0.336
Tokenwall
Token ID11930
Feature activation-1.46e+00

Pos logit contributions
Sov+0.615
+0.554
 Zhu+0.548
vacc+0.535
 Qin+0.508
Neg logit contributions
 commute-1.073
 commuting-0.944
 notation-0.925
 flakes-0.900
 aeros-0.898
Token Settings
Token ID16163
Feature activation-4.75e+00

Pos logit contributions
 commute+1.076
 commuting+0.900
 notation+0.874
 flakes+0.840
 aeros+0.836
Neg logit contributions
Sov-1.212
-1.121
 Zhu-1.114
vacc-1.098
 Qin-1.058
Token to
Token ID284
Feature activation-7.78e-01

Pos logit contributions
 commute+3.482
 commuting+2.883
 notation+2.876
 flakes+2.723
 aeros+2.698
Neg logit contributions
Sov-3.979
vacc-3.608
-3.601
 Zhu-3.593
��-3.416
Token the
Token ID262
Feature activation-8.72e-01

Pos logit contributions
 commute+0.586
 commuting+0.492
 notation+0.478
 flakes+0.461
 aeros+0.458
Neg logit contributions
Sov-0.632
-0.583
 Zhu-0.580
vacc-0.571
 Qin-0.550
Token minimum
Token ID5288
Feature activation-4.82e-01

Pos logit contributions
 commute+0.691
 commuting+0.585
 notation+0.570
 flakes+0.550
 aeros+0.548
Neg logit contributions
Sov-0.676
-0.621
 Zhu-0.617
vacc-0.608
 Qin-0.583
Token setting
Token ID4634
Feature activation-3.83e+00

Pos logit contributions
 commute+0.364
 commuting+0.306
 notation+0.296
 flakes+0.287
 aeros+0.285
Neg logit contributions
Sov-0.389
-0.361
 Zhu-0.358
vacc-0.351
 Qin-0.340
Token.
Token ID13
Feature activation-7.36e-01

Pos logit contributions
 commute+2.856
 commuting+2.397
 notation+2.341
 flakes+2.233
 aeros+2.228
Neg logit contributions
Sov-3.157
-2.876
 Zhu-2.859
vacc-2.845
��-2.709
TokenITT
Token ID22470
Feature activation-2.17e+00

Pos logit contributions
Sov+0.329
+0.304
 Zhu+0.302
vacc+0.296
 Qin+0.285
Neg logit contributions
 commute-0.346
 commuting-0.294
 notation-0.286
 flakes-0.276
 aeros-0.276
Token SM
Token ID9447
Feature activation-1.95e-01

Pos logit contributions
 commute+1.707
 commuting+1.442
 notation+1.408
 flakes+1.365
 aeros+1.359
Neg logit contributions
Sov-1.683
-1.532
 Zhu-1.519
vacc-1.519
��-1.448
TokenITH
Token ID10554
Feature activation+2.42e+00

Pos logit contributions
 commute+0.217
 commuting+0.194
 notation+0.190
 flakes+0.185
 aeros+0.185
Neg logit contributions
Sov-0.089
-0.078
 Zhu-0.076
vacc-0.074
 Qin-0.069
Token,
Token ID11
Feature activation+3.00e-01

Pos logit contributions
Sov+1.976
+1.875
 Zhu+1.824
vacc+1.807
 Qin+1.728
Neg logit contributions
 commute-1.784
 commuting-1.503
 notation-1.442
 flakes-1.384
 aeros-1.376
Token FL
Token ID9977
Feature activation+9.57e-01

Pos logit contributions
Sov+0.230
+0.213
 Zhu+0.212
vacc+0.207
 Qin+0.200
Neg logit contributions
 commute-0.239
 commuting-0.202
 notation-0.197
 flakes-0.190
 aeros-0.189
TokenOR
Token ID1581
Feature activation-4.71e+00

Pos logit contributions
Sov+0.747
+0.693
 Zhu+0.686
vacc+0.676
 Qin+0.651
Neg logit contributions
 commute-0.751
 commuting-0.636
 notation-0.616
 aeros-0.591
 flakes-0.590
TokenIDA
Token ID41957
Feature activation-2.02e+00

Pos logit contributions
 commute+3.895
 commuting+3.342
 notation+3.288
 aeros+3.199
 flakes+3.180
Neg logit contributions
Sov-3.323
vacc-3.038
 Zhu-3.029
-3.029
��-2.887
Token
Token ID198
Feature activation-1.06e+00

Pos logit contributions
 commute+1.367
 commuting+1.124
 notation+1.087
 flakes+1.042
 aeros+1.037
Neg logit contributions
Sov-1.794
-1.663
 Zhu-1.657
vacc-1.636
 Qin-1.578
Token
Token ID198
Feature activation-4.42e-01

Pos logit contributions
 commute+0.671
 commuting+0.542
 notation+0.528
 flakes+0.502
 aeros+0.501
Neg logit contributions
Sov-0.979
 Zhu-0.904
-0.904
vacc-0.896
��-0.876
TokenY
Token ID56
Feature activation-1.87e+00

Pos logit contributions
 commute+0.447
 commuting+0.394
 notation+0.386
 flakes+0.376
 aeros+0.375
Neg logit contributions
Sov-0.245
-0.217
 Zhu-0.215
vacc-0.210
 Qin-0.198
Tokenards
Token ID1371
Feature activation-6.89e-01

Pos logit contributions
 commute+1.139
 commuting+0.915
 notation+0.901
 flakes+0.854
 aeros+0.854
Neg logit contributions
Sov-1.776
 Zhu-1.646
-1.639
vacc-1.621
��-1.608
Token of
Token ID286
Feature activation+1.81e-01

Pos logit contributions
 commute+0.572
 commuting+0.478
 notation+0.461
 flakes+0.442
 aeros+0.441
Neg logit contributions
Sov-0.647
-0.604
 Zhu-0.599
vacc-0.587
 Qin-0.570
Token Pre
Token ID3771
Feature activation-8.93e-01

Pos logit contributions
Sov+0.193
+0.181
 Zhu+0.181
vacc+0.179
 Qin+0.174
Neg logit contributions
 commute-0.090
 commuting-0.068
 notation-0.065
 flakes-0.061
 aeros-0.061
Tokeny
Token ID88
Feature activation-1.11e+00

Pos logit contributions
 commute+0.650
 commuting+0.540
 notation+0.531
 flakes+0.507
 aeros+0.506
Neg logit contributions
Sov-0.746
 Zhu-0.683
-0.683
vacc-0.672
��-0.650
Token
Token ID198
Feature activation-1.16e+00

Pos logit contributions
 commute+0.805
 commuting+0.671
 notation+0.651
 flakes+0.625
 aeros+0.622
Neg logit contributions
Sov-0.939
-0.869
 Zhu-0.864
vacc-0.852
 Qin-0.821
Token
Token ID198
Feature activation-9.92e-01

Pos logit contributions
 commute+0.730
 commuting+0.588
 notation+0.574
 flakes+0.544
 aeros+0.543
Neg logit contributions
Sov-1.083
 Zhu-0.999
-0.997
vacc-0.992
��-0.974
Tokenhttps
Token ID5450
Feature activation-4.46e+00

Pos logit contributions
 commute+0.873
 commuting+0.753
 notation+0.738
 flakes+0.714
 aeros+0.711
Neg logit contributions
Sov-0.676
-0.613
 Zhu-0.613
vacc-0.600
 Qin-0.575
Token://
Token ID1378
Feature activation-2.03e+00

Pos logit contributions
 commute+3.000
 commuting+2.419
 notation+2.407
aster+2.351
 flakes+2.318
Neg logit contributions
Sov-3.807
��-3.573
 Zhu-3.506
vacc-3.466
��極-3.420
Tokenkill
Token ID12728
Feature activation-1.22e+00

Pos logit contributions
 commute+1.790
 commuting+1.544
 notation+1.509
 flakes+1.461
 aeros+1.456
Neg logit contributions
Sov-1.393
-1.263
 Zhu-1.258
vacc-1.230
 Qin-1.181
Tokenert
Token ID861
Feature activation+1.33e-01

Pos logit contributions
 commute+1.030
 commuting+0.883
 notation+0.860
 flakes+0.833
 aeros+0.830
Neg logit contributions
Sov-0.873
-0.799
 Zhu-0.792
vacc-0.782
 Qin-0.746
Tokenof
Token ID1659
Feature activation-3.90e-01

Pos logit contributions
Sov+0.095
+0.087
 Zhu+0.086
vacc+0.085
 Qin+0.081
Neg logit contributions
 commute-0.114
 commuting-0.099
 notation-0.096
 flakes-0.093
 aeros-0.092
Tokenure
Token ID495
Feature activation+2.56e-01

Pos logit contributions
 commute+0.313
 commuting+0.266
 notation+0.258
 flakes+0.249
 aeros+0.248
Neg logit contributions
Sov-0.299
-0.276
vacc-0.273
 Zhu-0.271
 Qin-0.258
Token the
Token ID262
Feature activation-4.69e-01

Pos logit contributions
Sov+0.939
 Zhu+0.884
+0.882
vacc+0.855
 Qin+0.837
Neg logit contributions
 commute-1.066
 commuting-0.906
 notation-0.890
 flakes-0.855
 aeros-0.850
Token Club
Token ID6289
Feature activation-8.89e-01

Pos logit contributions
 commute+0.349
 commuting+0.292
 notation+0.284
 flakes+0.273
 aeros+0.272
Neg logit contributions
Sov-0.386
-0.357
 Zhu-0.355
vacc-0.349
 Qin-0.337
Token and
Token ID290
Feature activation-1.68e-01

Pos logit contributions
 commute+0.645
 commuting+0.537
 notation+0.522
 flakes+0.501
 aeros+0.499
Neg logit contributions
Sov-0.744
-0.692
 Zhu-0.688
vacc-0.676
 Qin-0.655
Token a
Token ID257
Feature activation-7.25e-01

Pos logit contributions
 commute+0.132
 commuting+0.112
 notation+0.109
 flakes+0.105
 aeros+0.104
Neg logit contributions
Sov-0.130
-0.121
 Zhu-0.120
vacc-0.118
 Qin-0.114
Token new
Token ID649
Feature activation+5.33e-02

Pos logit contributions
 commute+0.566
 commuting+0.479
 notation+0.466
 flakes+0.449
 aeros+0.448
Neg logit contributions
Sov-0.573
-0.525
 Zhu-0.521
vacc-0.514
 Qin-0.493
Token sponsor
Token ID17487
Feature activation-4.45e+00

Pos logit contributions
Sov+0.043
+0.040
 Zhu+0.040
vacc+0.039
 Qin+0.038
Neg logit contributions
 commute-0.040
 commuting-0.033
 notation-0.032
 flakes-0.031
 aeros-0.031
Token is
Token ID318
Feature activation-3.25e-01

Pos logit contributions
 commute+3.066
 commuting+2.532
 notation+2.463
 flakes+2.359
 aeros+2.356
Neg logit contributions
Sov-3.899
-3.565
vacc-3.541
 Zhu-3.534
��-3.400
Token for
Token ID329
Feature activation-6.86e-02

Pos logit contributions
 commute+0.247
 commuting+0.208
 notation+0.202
 flakes+0.195
 aeros+0.194
Neg logit contributions
Sov-0.262
-0.242
 Zhu-0.241
vacc-0.236
 Qin-0.228
Token the
Token ID262
Feature activation-1.38e-01

Pos logit contributions
 commute+0.056
 commuting+0.047
 notation+0.046
 flakes+0.045
 aeros+0.044
Neg logit contributions
Sov-0.051
-0.047
 Zhu-0.047
vacc-0.046
 Qin-0.045
Token Premier
Token ID9952
Feature activation+4.96e-01

Pos logit contributions
 commute+0.105
 commuting+0.088
 notation+0.086
 flakes+0.082
 aeros+0.082
Neg logit contributions
Sov-0.111
-0.102
 Zhu-0.102
vacc-0.100
 Qin-0.096
Token League
Token ID4041
Feature activation+6.64e-01

Pos logit contributions
Sov+0.410
+0.386
 Zhu+0.384
vacc+0.375
 Qin+0.366
Neg logit contributions
 commute-0.360
 commuting-0.300
 notation-0.292
 flakes-0.281
 aeros-0.280
Token when
Token ID618
Feature activation+4.83e-01

Pos logit contributions
 commute+0.476
 commuting+0.396
 notation+0.389
 flakes+0.373
 aeros+0.372
Neg logit contributions
Sov-0.517
-0.481
 Zhu-0.481
vacc-0.469
 Qin-0.456
Token the
Token ID262
Feature activation-2.79e-01

Pos logit contributions
Sov+0.380
 Zhu+0.356
+0.352
vacc+0.342
 Qin+0.339
Neg logit contributions
 commute-0.374
 commuting-0.312
 notation-0.306
 aeros-0.293
 flakes-0.292
Token rubber
Token ID14239
Feature activation+6.77e-01

Pos logit contributions
 commute+0.220
 commuting+0.186
 notation+0.180
 flakes+0.174
 aeros+0.173
Neg logit contributions
Sov-0.217
-0.200
 Zhu-0.199
vacc-0.195
 Qin-0.189
Token '
Token ID705
Feature activation-5.99e-01

Pos logit contributions
Sov+0.555
 Zhu+0.514
+0.514
vacc+0.505
 Qin+0.489
Neg logit contributions
 commute-0.501
 commuting-0.419
 notation-0.405
 aeros-0.386
 flakes-0.385
Tokent
Token ID83
Feature activation+2.47e-01

Pos logit contributions
 commute+0.513
 commuting+0.440
 notation+0.429
 flakes+0.416
 aeros+0.414
Neg logit contributions
Sov-0.427
-0.390
 Zhu-0.386
vacc-0.381
 Qin-0.364
Tokenent
Token ID298
Feature activation-4.44e+00

Pos logit contributions
Sov+0.174
+0.161
 Zhu+0.158
vacc+0.157
 Qin+0.150
Neg logit contributions
 commute-0.211
 commuting-0.182
 notation-0.177
 flakes-0.171
 aeros-0.171
Tokenacles
Token ID9928
Feature activation-1.29e-01

Pos logit contributions
 commute+3.496
 commuting+2.975
 notation+2.916
 flakes+2.833
 aeros+2.787
Neg logit contributions
Sov-3.377
-3.099
 Zhu-3.079
vacc-3.035
��-2.912
Token'
Token ID6
Feature activation-1.08e+00

Pos logit contributions
 commute+0.116
 commuting+0.101
 notation+0.098
 aeros+0.095
 flakes+0.095
Neg logit contributions
Sov-0.086
-0.078
 Zhu-0.077
vacc-0.076
 Qin-0.072
Token started
Token ID2067
Feature activation-1.75e+00

Pos logit contributions
 commute+0.780
 commuting+0.649
 notation+0.629
 flakes+0.603
 aeros+0.601
Neg logit contributions
Sov-0.905
-0.841
 Zhu-0.837
vacc-0.823
 Qin-0.796
Token interfering
Token ID32874
Feature activation+2.23e+00

Pos logit contributions
 commute+1.372
 commuting+1.163
 notation+1.130
 flakes+1.092
 aeros+1.087
Neg logit contributions
Sov-1.367
-1.256
 Zhu-1.247
vacc-1.229
 Qin-1.181
Token with
Token ID351
Feature activation-6.97e-01

Pos logit contributions
Sov+1.559
+1.460
 Zhu+1.455
vacc+1.405
 Qin+1.380
Neg logit contributions
 commute-1.877
 commuting-1.597
 notation-1.563
 aeros-1.504
 flakes-1.494
Token put
Token ID1234
Feature activation-1.31e-01

Pos logit contributions
 commute+0.365
 commuting+0.304
 notation+0.292
 flakes+0.281
 aeros+0.281
Neg logit contributions
Sov-0.439
-0.408
 Zhu-0.405
vacc-0.398
 Qin-0.386
Tokents
Token ID912
Feature activation-1.58e-01

Pos logit contributions
 commute+0.134
 commuting+0.118
 notation+0.115
 flakes+0.112
 aeros+0.112
Neg logit contributions
Sov-0.071
-0.064
 Zhu-0.063
vacc-0.061
 Qin-0.058
Token easily
Token ID3538
Feature activation+8.76e-01

Pos logit contributions
 commute+0.115
 commuting+0.096
 notation+0.093
 flakes+0.090
 aeros+0.090
Neg logit contributions
Sov-0.131
-0.122
 Zhu-0.121
vacc-0.119
 Qin-0.115
Token,
Token ID11
Feature activation-2.99e-01

Pos logit contributions
Sov+0.718
+0.677
 Zhu+0.671
vacc+0.655
 Qin+0.637
Neg logit contributions
 commute-0.634
 commuting-0.528
 notation-0.511
 aeros-0.495
 flakes-0.493
Token feel
Token ID1254
Feature activation-1.14e+00

Pos logit contributions
 commute+0.230
 commuting+0.194
 notation+0.188
 flakes+0.182
 aeros+0.181
Neg logit contributions
Sov-0.236
-0.220
 Zhu-0.218
vacc-0.214
 Qin-0.207
Token free
Token ID1479
Feature activation-4.44e+00

Pos logit contributions
 commute+0.799
 commuting+0.663
 notation+0.644
 flakes+0.616
 aeros+0.612
Neg logit contributions
Sov-0.982
-0.908
 Zhu-0.899
vacc-0.891
 Qin-0.857
Token to
Token ID284
Feature activation-1.47e+00

Pos logit contributions
 commute+3.505
 commuting+2.974
 notation+2.894
 flakes+2.782
 aeros+2.761
Neg logit contributions
Sov-3.441
-3.135
 Zhu-3.129
vacc-3.092
 Qin-2.957
Token make
Token ID787
Feature activation-7.31e-01

Pos logit contributions
 commute+1.027
 commuting+0.850
 notation+0.823
 flakes+0.790
 aeros+0.786
Neg logit contributions
Sov-1.275
-1.184
 Zhu-1.177
vacc-1.161
 Qin-1.121
Token more
Token ID517
Feature activation+7.04e-01

Pos logit contributions
 commute+0.607
 commuting+0.518
 notation+0.504
 flakes+0.488
 aeros+0.487
Neg logit contributions
Sov-0.536
-0.492
 Zhu-0.489
vacc-0.479
 Qin-0.461
Token than
Token ID621
Feature activation+2.89e-01

Pos logit contributions
Sov+0.575
+0.536
 Zhu+0.532
vacc+0.521
 Qin+0.507
Neg logit contributions
 commute-0.520
 commuting-0.435
 notation-0.419
 aeros-0.404
 flakes-0.403
Token one
Token ID530
Feature activation-8.70e-02

Pos logit contributions
Sov+0.210
+0.191
 Zhu+0.190
vacc+0.187
 Qin+0.179
Neg logit contributions
 commute-0.244
 commuting-0.209
 notation-0.204
 flakes-0.197
 aeros-0.196
Token category
Token ID6536
Feature activation-1.66e+00

Pos logit contributions
 commute+0.630
 commuting+0.527
 notation+0.510
 flakes+0.490
 aeros+0.489
Neg logit contributions
Sov-0.717
-0.665
 Zhu-0.660
vacc-0.650
 Qin-0.627
Token,
Token ID11
Feature activation-1.49e-01

Pos logit contributions
 commute+1.251
 commuting+1.051
 notation+1.020
 flakes+0.982
 aeros+0.978
Neg logit contributions
Sov-1.349
-1.248
 Zhu-1.240
vacc-1.220
 Qin-1.175
Token where
Token ID810
Feature activation-2.03e-01

Pos logit contributions
 commute+0.112
 commuting+0.094
 notation+0.091
 flakes+0.088
 aeros+0.088
Neg logit contributions
Sov-0.121
-0.112
 Zhu-0.111
vacc-0.109
 Qin-0.105
Token Emmy
Token ID33953
Feature activation-1.53e+00

Pos logit contributions
 commute+0.161
 commuting+0.137
 notation+0.133
 flakes+0.128
 aeros+0.128
Neg logit contributions
Sov-0.155
-0.144
 Zhu-0.143
vacc-0.140
 Qin-0.135
Token-
Token ID12
Feature activation-1.33e+00

Pos logit contributions
 commute+1.090
 commuting+0.905
 notation+0.876
 flakes+0.840
 aeros+0.838
Neg logit contributions
Sov-1.305
-1.210
 Zhu-1.204
vacc-1.186
 Qin-1.144
Tokenneg
Token ID12480
Feature activation-4.40e+00

Pos logit contributions
 commute+0.964
 commuting+0.802
 notation+0.777
 aeros+0.748
 flakes+0.746
Neg logit contributions
Sov-1.128
-1.047
 Zhu-1.037
vacc-1.029
 Qin-0.984
Tokenlected
Token ID12609
Feature activation-8.10e-01

Pos logit contributions
 commute+3.052
 commuting+2.523
 notation+2.434
 flakes+2.311
 aeros+2.287
Neg logit contributions
Sov-3.811
-3.541
 Zhu-3.540
vacc-3.495
 Qin-3.374
Token The
Token ID383
Feature activation-5.91e-01

Pos logit contributions
 commute+0.593
 commuting+0.496
 notation+0.481
 flakes+0.462
 aeros+0.461
Neg logit contributions
Sov-0.672
-0.624
 Zhu-0.621
vacc-0.610
 Qin-0.590
Token Good
Token ID4599
Feature activation+7.69e-02

Pos logit contributions
 commute+0.497
 commuting+0.426
 notation+0.416
 aeros+0.402
 flakes+0.399
Neg logit contributions
Sov-0.427
-0.394
 Zhu-0.394
vacc-0.384
 Qin-0.371
Token Wife
Token ID34188
Feature activation-1.45e+00

Pos logit contributions
Sov+0.050
+0.045
 Zhu+0.044
vacc+0.043
 Qin+0.041
Neg logit contributions
 commute-0.071
 commuting-0.062
 notation-0.060
 flakes-0.059
 aeros-0.058
Token was
Token ID373
Feature activation-6.15e-01

Pos logit contributions
 commute+1.132
 commuting+0.956
 notation+0.929
 flakes+0.899
 aeros+0.894
Neg logit contributions
Sov-1.143
-1.049
 Zhu-1.043
vacc-1.029
 Qin-0.988
Token SAS
Token ID35516
Feature activation-7.68e-01

Pos logit contributions
 commute+0.644
 commuting+0.543
 notation+0.528
 flakes+0.508
 aeros+0.506
Neg logit contributions
Sov-0.662
-0.612
 Zhu-0.610
vacc-0.598
 Qin-0.577
TokenK
Token ID42
Feature activation-3.08e-01

Pos logit contributions
 commute+0.668
 commuting+0.575
 notation+0.560
 flakes+0.543
 aeros+0.541
Neg logit contributions
Sov-0.537
-0.489
 Zhu-0.486
vacc-0.478
 Qin-0.456
TokenATCH
Token ID11417
Feature activation-1.98e+00

Pos logit contributions
 commute+0.261
 commuting+0.224
 notation+0.218
 flakes+0.211
 aeros+0.210
Neg logit contributions
Sov-0.223
-0.203
 Zhu-0.202
vacc-0.199
 Qin-0.190
TokenEW
Token ID6217
Feature activation-7.34e-01

Pos logit contributions
 commute+1.604
 commuting+1.365
 notation+1.333
 flakes+1.287
 aeros+1.283
Neg logit contributions
Sov-1.491
-1.367
 Zhu-1.357
vacc-1.335
 Qin-1.281
TokenAN
Token ID1565
Feature activation-1.92e+00

Pos logit contributions
 commute+0.597
 commuting+0.508
 notation+0.494
 flakes+0.477
 aeros+0.475
Neg logit contributions
Sov-0.554
-0.509
 Zhu-0.505
vacc-0.497
 Qin-0.477
Token -
Token ID532
Feature activation-4.37e+00

Pos logit contributions
 commute+1.454
 commuting+1.223
 notation+1.187
 flakes+1.143
 aeros+1.138
Neg logit contributions
Sov-1.552
-1.432
 Zhu-1.425
vacc-1.403
 Qin-1.350
Token favorite
Token ID4004
Feature activation-2.76e+00

Pos logit contributions
 commute+3.024
 commuting+2.473
 notation+2.389
 flakes+2.294
 aeros+2.271
Neg logit contributions
Sov-3.944
-3.569
vacc-3.531
 Zhu-3.523
��-3.514
Token favorite
Token ID4004
Feature activation-2.56e+00

Pos logit contributions
 commute+1.996
 commuting+1.655
 notation+1.605
 flakes+1.524
 aeros+1.519
Neg logit contributions
Sov-2.405
-2.190
 Zhu-2.166
vacc-2.156
��-2.113
Token favorite
Token ID4004
Feature activation-2.30e+00

Pos logit contributions
 commute+1.855
 commuting+1.540
 notation+1.492
 flakes+1.420
 aeros+1.415
Neg logit contributions
Sov-2.212
-2.017
 Zhu-1.995
vacc-1.985
��-1.941
Token favorite
Token ID4004
Feature activation-1.94e+00

Pos logit contributions
 commute+1.671
 commuting+1.389
 notation+1.345
 flakes+1.284
 aeros+1.277
Neg logit contributions
Sov-1.973
-1.804
 Zhu-1.784
vacc-1.772
��-1.725
Token favorite
Token ID4004
Feature activation-1.57e+00

Pos logit contributions
 commute+1.452
 commuting+1.218
 notation+1.184
 flakes+1.140
 aeros+1.136
Neg logit contributions
Sov-1.583
-1.465
 Zhu-1.457
vacc-1.435
 Qin-1.382
Token
Token ID250
Feature activation+7.65e-01

Pos logit contributions
 commute+0.078
 commuting+0.069
 notation+0.067
 flakes+0.066
 aeros+0.066
Neg logit contributions
Sov-0.040
-0.035
 Zhu-0.035
vacc-0.034
 Qin-0.032
Tokenshop
Token ID24643
Feature activation-1.22e+00

Pos logit contributions
Sov+0.556
+0.513
 Zhu+0.501
vacc+0.499
 Qin+0.472
Neg logit contributions
 commute-0.641
 commuting-0.552
 notation-0.535
 flakes-0.521
 aeros-0.518
Token
Token ID447
Feature activation-1.69e+00

Pos logit contributions
 commute+0.947
 commuting+0.800
 notation+0.777
 flakes+0.749
 aeros+0.746
Neg logit contributions
Sov-0.967
-0.886
 Zhu-0.883
vacc-0.871
 Qin-0.837
Token
Token ID251
Feature activation-2.97e-01

Pos logit contributions
 commute+1.694
 commuting+1.492
 notation+1.463
 flakes+1.429
 aeros+1.417
Neg logit contributions
Sov-0.952
 Zhu-0.832
-0.830
vacc-0.813
 Qin-0.769
Token for
Token ID329
Feature activation-6.96e-01

Pos logit contributions
 commute+0.241
 commuting+0.205
 notation+0.199
 flakes+0.193
 aeros+0.192
Neg logit contributions
Sov-0.223
-0.207
 Zhu-0.204
vacc-0.201
 Qin-0.193
Token free
Token ID1479
Feature activation-4.35e+00

Pos logit contributions
 commute+0.573
 commuting+0.488
 notation+0.476
 flakes+0.460
 aeros+0.458
Neg logit contributions
Sov-0.516
-0.475
 Zhu-0.471
vacc-0.463
 Qin-0.444
Token,
Token ID11
Feature activation-2.69e-01

Pos logit contributions
 commute+3.246
 commuting+2.731
 notation+2.660
 flakes+2.577
 aeros+2.551
Neg logit contributions
Sov-3.576
 Zhu-3.203
vacc-3.198
-3.186
��-3.074
Token legal
Token ID2742
Feature activation-1.01e-01

Pos logit contributions
 commute+0.200
 commuting+0.168
 notation+0.163
 flakes+0.157
 aeros+0.156
Neg logit contributions
Sov-0.219
-0.205
 Zhu-0.203
vacc-0.199
 Qin-0.192
Token copies
Token ID9088
Feature activation+7.98e-02

Pos logit contributions
 commute+0.074
 commuting+0.061
 notation+0.059
 flakes+0.057
 aeros+0.057
Neg logit contributions
Sov-0.084
-0.079
 Zhu-0.078
vacc-0.076
 Qin-0.074
Token of
Token ID286
Feature activation+5.60e-01

Pos logit contributions
Sov+0.066
+0.062
 Zhu+0.061
vacc+0.060
 Qin+0.058
Neg logit contributions
 commute-0.059
 commuting-0.049
 notation-0.048
 flakes-0.046
 aeros-0.046
Token e
Token ID304
Feature activation-1.25e+00

Pos logit contributions
Sov+0.432
+0.396
 Zhu+0.394
vacc+0.388
 Qin+0.372
Neg logit contributions
 commute-0.446
 commuting-0.379
 notation-0.368
 flakes-0.356
 aeros-0.354
Token:
Token ID25
Feature activation+3.68e-01

Pos logit contributions
Sov+1.043
+0.977
 Zhu+0.974
vacc+0.944
 Qin+0.927
Neg logit contributions
 commute-0.947
 commuting-0.791
 notation-0.773
 aeros-0.742
 flakes-0.741
Token Sylvia
Token ID45425
Feature activation-1.47e-01

Pos logit contributions
Sov+0.285
+0.264
 Zhu+0.263
vacc+0.256
 Qin+0.249
Neg logit contributions
 commute-0.290
 commuting-0.245
 notation-0.239
 flakes-0.230
 aeros-0.229
Token's
Token ID338
Feature activation+6.88e-01

Pos logit contributions
 commute+0.114
 commuting+0.097
 notation+0.094
 flakes+0.090
 aeros+0.090
Neg logit contributions
Sov-0.116
-0.107
 Zhu-0.107
vacc-0.105
 Qin-0.101
Token En
Token ID2039
Feature activation-1.12e+00

Pos logit contributions
Sov+0.539
+0.500
 Zhu+0.498
vacc+0.486
 Qin+0.472
Neg logit contributions
 commute-0.535
 commuting-0.452
 notation-0.439
 flakes-0.422
 aeros-0.422
Tokench
Token ID354
Feature activation-1.29e+00

Pos logit contributions
 commute+0.899
 commuting+0.763
 notation+0.744
 flakes+0.718
 aeros+0.715
Neg logit contributions
Sov-0.855
-0.783
 Zhu-0.775
vacc-0.765
 Qin-0.733
Tokenil
Token ID346
Feature activation-4.30e+00

Pos logit contributions
 commute+0.957
 commuting+0.798
 notation+0.776
 flakes+0.749
 aeros+0.745
Neg logit contributions
Sov-1.066
-0.980
 Zhu-0.976
vacc-0.961
 Qin-0.928
Tokenada
Token ID4763
Feature activation+2.55e-01

Pos logit contributions
 commute+3.014
 commuting+2.500
 notation+2.457
 flakes+2.384
 aeros+2.358
Neg logit contributions
Sov-3.667
-3.362
vacc-3.306
 Zhu-3.296
��-3.185
Token Kitchen
Token ID22541
Feature activation+5.21e-01

Pos logit contributions
Sov+0.208
+0.194
 Zhu+0.193
vacc+0.189
 Qin+0.183
Neg logit contributions
 commute-0.191
 commuting-0.160
 notation-0.155
 flakes-0.149
 aeros-0.149
Token Previously
Token ID29875
Feature activation-8.18e-01

Pos logit contributions
Sov+0.431
+0.401
 Zhu+0.399
vacc+0.391
 Qin+0.379
Neg logit contributions
 commute-0.383
 commuting-0.320
 notation-0.310
 flakes-0.298
 aeros-0.297
Token:
Token ID25
Feature activation+3.01e-01

Pos logit contributions
 commute+0.616
 commuting+0.517
 notation+0.502
 flakes+0.484
 aeros+0.482
Neg logit contributions
Sov-0.665
-0.615
 Zhu-0.611
vacc-0.601
 Qin-0.580
Token Gro
Token ID10299
Feature activation+7.50e-01

Pos logit contributions
Sov+0.231
+0.213
 Zhu+0.212
vacc+0.207
 Qin+0.201
Neg logit contributions
 commute-0.240
 commuting-0.204
 notation-0.198
 flakes-0.191
 aeros-0.190
Token)
Token ID8
Feature activation+1.63e-01

Pos logit contributions
 commute+0.989
 commuting+0.838
 notation+0.814
 flakes+0.785
 aeros+0.782
Neg logit contributions
Sov-0.969
-0.890
 Zhu-0.884
vacc-0.870
 Qin-0.837
Token
Token ID198
Feature activation-1.57e+00

Pos logit contributions
Sov+0.135
+0.127
 Zhu+0.125
vacc+0.123
 Qin+0.119
Neg logit contributions
 commute-0.119
 commuting-0.100
 notation-0.097
 flakes-0.094
 aeros-0.093
Token
Token ID198
Feature activation-7.60e-01

Pos logit contributions
 commute+0.982
 commuting+0.789
 notation+0.771
 flakes+0.732
 aeros+0.730
Neg logit contributions
Sov-1.458
 Zhu-1.351
-1.344
vacc-1.338
��-1.314
Token(
Token ID7
Feature activation+7.59e-01

Pos logit contributions
 commute+0.683
 commuting+0.592
 notation+0.578
 flakes+0.560
 aeros+0.558
Neg logit contributions
Sov-0.507
-0.459
 Zhu-0.456
vacc-0.448
 Qin-0.427
TokenK
Token ID42
Feature activation+6.89e-01

Pos logit contributions
Sov+0.516
+0.470
 Zhu+0.462
vacc+0.456
 Qin+0.434
Neg logit contributions
 commute-0.672
 commuting-0.581
 notation-0.567
 flakes-0.551
 aeros-0.549
Tokenath
Token ID776
Feature activation-4.29e+00

Pos logit contributions
Sov+0.490
+0.446
 Zhu+0.441
vacc+0.436
 Qin+0.416
Neg logit contributions
 commute-0.587
 commuting-0.505
 notation-0.490
 flakes-0.478
 aeros-0.477
Tokenleen
Token ID20042
Feature activation-1.21e+00

Pos logit contributions
 commute+3.147
 commuting+2.642
 notation+2.555
 flakes+2.473
 aeros+2.438
Neg logit contributions
Sov-3.557
-3.291
 Zhu-3.241
vacc-3.207
 Qin-3.063
Token Flynn
Token ID14654
Feature activation+1.51e-01

Pos logit contributions
 commute+1.057
 commuting+0.911
 notation+0.889
 flakes+0.861
 aeros+0.859
Neg logit contributions
Sov-0.837
-0.763
 Zhu-0.758
vacc-0.743
 Qin-0.711
Token)
Token ID8
Feature activation+6.42e-01

Pos logit contributions
Sov+0.111
+0.103
 Zhu+0.102
vacc+0.100
 Qin+0.096
Neg logit contributions
 commute-0.124
 commuting-0.105
 notation-0.103
 flakes-0.099
 aeros-0.099
Token
Token ID198
Feature activation-3.93e-01

Pos logit contributions
Sov+0.530
+0.495
 Zhu+0.490
vacc+0.481
 Qin+0.466
Neg logit contributions
 commute-0.470
 commuting-0.394
 notation-0.384
 flakes-0.371
 aeros-0.368
Token
Token ID198
Feature activation-4.67e-02

Pos logit contributions
 commute+0.258
 commuting+0.210
 notation+0.204
 flakes+0.195
 aeros+0.194
Neg logit contributions
Sov-0.357
-0.331
 Zhu-0.330
vacc-0.327
 Qin-0.315
Tokenwww
Token ID2503
Feature activation-3.57e+00

Pos logit contributions
 commute+1.932
 commuting+1.629
 notation+1.565
aster+1.514
minster+1.511
Neg logit contributions
Sov-1.830
 Zhu-1.668
-1.624
��-1.590
vacc-1.567
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
 commute+2.615
 commuting+2.159
 notation+2.120
 flakes+2.081
aster+2.049
Neg logit contributions
Sov-2.890
��-2.666
 Zhu-2.622
vacc-2.598
-2.563
Tokenbel
Token ID6667
Feature activation+5.77e-01

Pos logit contributions
 commute+0.729
 commuting+0.606
 notation+0.591
 flakes+0.566
 aeros+0.565
Neg logit contributions
Sov-0.856
-0.796
 Zhu-0.788
vacc-0.784
 Qin-0.749
Tokenfast
Token ID7217
Feature activation-7.85e-01

Pos logit contributions
Sov+0.432
+0.398
vacc+0.392
 Zhu+0.391
 Qin+0.369
Neg logit contributions
 commute-0.470
 commuting-0.400
 notation-0.391
 aeros-0.376
 flakes-0.376
Tokente
Token ID660
Feature activation-1.31e+00

Pos logit contributions
 commute+0.638
 commuting+0.545
 notation+0.534
 flakes+0.515
 aeros+0.513
Neg logit contributions
Sov-0.580
-0.543
 Zhu-0.532
vacc-0.528
 Qin-0.502
Tokenlegraph
Token ID16606
Feature activation-4.29e+00

Pos logit contributions
 commute+0.884
 commuting+0.728
 notation+0.706
 flakes+0.677
 aeros+0.670
Neg logit contributions
Sov-1.161
-1.089
 Zhu-1.078
vacc-1.065
 Qin-1.029
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
 commute+3.088
 commuting+2.546
 notation+2.469
aster+2.462
 flakes+2.434
Neg logit contributions
Sov-3.528
��-3.260
 Zhu-3.196
��極-3.114
-3.102
Tokenco
Token ID1073
Feature activation+1.22e+00

Pos logit contributions
 commute+0.850
 commuting+0.683
 notation+0.652
 flakes+0.628
 aeros+0.620
Neg logit contributions
Sov-1.314
-1.225
 Zhu-1.218
vacc-1.194
��-1.165
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
Sov+0.883
+0.804
 Zhu+0.800
vacc+0.786
 Qin+0.753
Neg logit contributions
 commute-1.028
 commuting-0.880
 notation-0.859
 flakes-0.831
 aeros-0.828
Tokenuk
Token ID2724
Feature activation+2.14e+00

Pos logit contributions
 commute+0.925
 commuting+0.801
 notation+0.776
 flakes+0.756
 aeros+0.752
Neg logit contributions
Sov-0.678
 Zhu-0.603
-0.600
vacc-0.583
��-0.571
Token/
Token ID14
Feature activation+2.25e+00

Pos logit contributions
Sov+1.154
+1.029
 Zhu+1.015
vacc+0.989
 Qin+0.931
Neg logit contributions
 commute-2.204
 commuting-1.947
 notation-1.906
 flakes-1.857
 aeros-1.851
Token)
Token ID8
Feature activation-1.32e-01

Pos logit contributions
 commute+2.003
 commuting+1.682
 notation+1.637
 flakes+1.572
 aeros+1.565
Neg logit contributions
Sov-2.179
-1.995
 Zhu-1.994
vacc-1.964
 Qin-1.894
Token and
Token ID290
Feature activation-1.31e+00

Pos logit contributions
 commute+0.097
 commuting+0.080
 notation+0.078
 flakes+0.075
 aeros+0.075
Neg logit contributions
Sov-0.109
-0.102
 Zhu-0.101
vacc-0.099
 Qin-0.096
Token Henry
Token ID8616
Feature activation-2.68e-01

Pos logit contributions
 commute+1.039
 commuting+0.883
 notation+0.857
 flakes+0.827
 aeros+0.822
Neg logit contributions
Sov-1.026
-0.936
 Zhu-0.930
vacc-0.920
 Qin-0.879
Token (
Token ID357
Feature activation-4.24e-01

Pos logit contributions
 commute+0.188
 commuting+0.155
 notation+0.151
 flakes+0.144
 aeros+0.144
Neg logit contributions
Sov-0.233
-0.217
 Zhu-0.215
vacc-0.212
 Qin-0.205
TokenP
Token ID47
Feature activation-2.93e-01

Pos logit contributions
 commute+0.399
 commuting+0.348
 notation+0.341
 flakes+0.331
 aeros+0.329
Neg logit contributions
Sov-0.260
-0.236
 Zhu-0.235
vacc-0.228
 Qin-0.218
Tokenyr
Token ID2417
Feature activation-4.27e+00

Pos logit contributions
 commute+0.249
 commuting+0.213
 notation+0.209
 flakes+0.202
 aeros+0.201
Neg logit contributions
Sov-0.209
-0.191
 Zhu-0.190
vacc-0.186
 Qin-0.178
Tokeng
Token ID70
Feature activation-2.11e-01

Pos logit contributions
 commute+2.620
 commuting+2.108
 notation+2.054
 flakes+1.968
 aeros+1.942
Neg logit contributions
Sov-3.995
-3.688
 Zhu-3.685
vacc-3.564
��-3.533
Tokenos
Token ID418
Feature activation-9.37e-01

Pos logit contributions
 commute+0.134
 commuting+0.108
 notation+0.105
 aeros+0.100
 flakes+0.100
Neg logit contributions
Sov-0.196
-0.182
 Zhu-0.182
vacc-0.179
 Qin-0.173
Token)
Token ID8
Feature activation+3.74e-01

Pos logit contributions
 commute+0.816
 commuting+0.703
 notation+0.686
 flakes+0.665
 aeros+0.662
Neg logit contributions
Sov-0.652
-0.594
 Zhu-0.589
vacc-0.579
 Qin-0.553
Token on
Token ID319
Feature activation-4.60e-02

Pos logit contributions
Sov+0.303
+0.282
 Zhu+0.279
vacc+0.275
 Qin+0.265
Neg logit contributions
 commute-0.282
 commuting-0.235
 notation-0.230
 flakes-0.221
 aeros-0.220
Token the
Token ID262
Feature activation+4.73e-01

Pos logit contributions
 commute+0.039
 commuting+0.033
 notation+0.032
 flakes+0.031
 aeros+0.031
Neg logit contributions
Sov-0.033
-0.030
 Zhu-0.030
vacc-0.030
 Qin-0.028
Token)
Token ID8
Feature activation-7.48e-01

Pos logit contributions
 commute+1.378
 commuting+1.158
 notation+1.128
 flakes+1.085
 aeros+1.081
Neg logit contributions
Sov-1.466
-1.347
 Zhu-1.342
vacc-1.322
 Qin-1.272
Token shows
Token ID2523
Feature activation-1.37e+00

Pos logit contributions
 commute+0.505
 commuting+0.416
 notation+0.399
 flakes+0.383
 aeros+0.383
Neg logit contributions
Sov-0.663
-0.622
 Zhu-0.616
vacc-0.607
 Qin-0.589
Token the
Token ID262
Feature activation-1.07e+00

Pos logit contributions
 commute+1.050
 commuting+0.884
 notation+0.859
 flakes+0.827
 aeros+0.824
Neg logit contributions
Sov-1.101
-1.017
 Zhu-1.010
vacc-0.994
 Qin-0.957
Token three
Token ID1115
Feature activation-1.50e+00

Pos logit contributions
 commute+0.822
 commuting+0.693
 notation+0.673
 flakes+0.649
 aeros+0.646
Neg logit contributions
Sov-0.851
-0.785
 Zhu-0.780
vacc-0.768
 Qin-0.739
Token available
Token ID1695
Feature activation-1.05e+00

Pos logit contributions
 commute+1.166
 commuting+0.985
 notation+0.959
 flakes+0.925
 aeros+0.920
Neg logit contributions
Sov-1.191
-1.092
 Zhu-1.087
vacc-1.074
 Qin-1.028
Token settings
Token ID6460
Feature activation-4.23e+00

Pos logit contributions
 commute+0.839
 commuting+0.713
 notation+0.694
 flakes+0.670
 aeros+0.667
Neg logit contributions
Sov-0.802
-0.736
 Zhu-0.731
vacc-0.720
 Qin-0.691
Token,
Token ID11
Feature activation-3.07e-01

Pos logit contributions
 commute+2.999
 commuting+2.491
 notation+2.421
 flakes+2.316
 aeros+2.309
Neg logit contributions
Sov-3.630
 Zhu-3.304
-3.301
vacc-3.289
��-3.164
Token including
Token ID1390
Feature activation+2.12e+00

Pos logit contributions
 commute+0.232
 commuting+0.195
 notation+0.189
 flakes+0.182
 aeros+0.181
Neg logit contributions
Sov-0.248
-0.230
 Zhu-0.228
vacc-0.225
 Qin-0.217
Token
Token ID564
Feature activation-1.92e+00

Pos logit contributions
Sov+1.507
+1.416
 Zhu+1.390
vacc+1.343
 Qin+1.316
Neg logit contributions
 commute-1.771
 commuting-1.518
 notation-1.484
 flakes-1.437
 aeros-1.426
Token
Token ID246
Feature activation-6.75e-01

Pos logit contributions
 commute+1.566
 commuting+1.336
 notation+1.299
 flakes+1.254
 aeros+1.252
Neg logit contributions
Sov-1.431
 Zhu-1.301
-1.294
vacc-1.281
 Qin-1.223
Tokensil
Token ID18217
Feature activation-1.24e+00

Pos logit contributions
 commute+0.526
 commuting+0.445
 notation+0.432
 flakes+0.417
 aeros+0.415
Neg logit contributions
Sov-0.532
-0.491
 Zhu-0.487
vacc-0.479
 Qin-0.461
Token the
Token ID262
Feature activation-1.30e-01

Pos logit contributions
 commute+0.160
 commuting+0.136
 notation+0.132
 flakes+0.127
 aeros+0.127
Neg logit contributions
Sov-0.155
-0.144
 Zhu-0.143
vacc-0.140
 Qin-0.135
Token brain
Token ID3632
Feature activation-2.54e-01

Pos logit contributions
 commute+0.100
 commuting+0.084
 notation+0.082
 flakes+0.078
 aeros+0.078
Neg logit contributions
Sov-0.103
-0.096
 Zhu-0.095
vacc-0.093
 Qin-0.090
Token areas
Token ID3006
Feature activation-3.57e-02

Pos logit contributions
 commute+0.189
 commuting+0.158
 notation+0.154
 flakes+0.147
 aeros+0.147
Neg logit contributions
Sov-0.207
-0.193
 Zhu-0.191
vacc-0.188
 Qin-0.181
Token controlling
Token ID12755
Feature activation+1.99e-01

Pos logit contributions
 commute+0.027
 commuting+0.022
 notation+0.022
 flakes+0.021
 aeros+0.021
Neg logit contributions
Sov-0.029
-0.027
 Zhu-0.027
vacc-0.026
 Qin-0.025
Token these
Token ID777
Feature activation-1.25e+00

Pos logit contributions
Sov+0.152
+0.142
 Zhu+0.141
vacc+0.138
 Qin+0.133
Neg logit contributions
 commute-0.157
 commuting-0.132
 notation-0.129
 flakes-0.124
 aeros-0.124
Token movements
Token ID8650
Feature activation-4.18e+00

Pos logit contributions
 commute+0.899
 commuting+0.747
 notation+0.724
 flakes+0.696
 aeros+0.693
Neg logit contributions
Sov-1.064
-0.988
 Zhu-0.982
vacc-0.967
 Qin-0.933
Token for
Token ID329
Feature activation-6.51e-01

Pos logit contributions
 commute+2.823
 commuting+2.319
 notation+2.253
 flakes+2.152
 aeros+2.135
Neg logit contributions
Sov-3.729
 Zhu-3.416
-3.397
vacc-3.382
 Qin-3.261
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
 commute+0.513
 commuting+0.433
 notation+0.421
 flakes+0.407
 aeros+0.405
Neg logit contributions
Sov-0.505
-0.467
 Zhu-0.464
vacc-0.455
 Qin-0.439
Token first
Token ID717
Feature activation-1.53e+00

Pos logit contributions
 commute+0.131
 commuting+0.111
 notation+0.108
 flakes+0.105
 aeros+0.104
Neg logit contributions
Sov-0.126
-0.117
 Zhu-0.116
vacc-0.114
 Qin-0.109
Token time
Token ID640
Feature activation-9.75e-01

Pos logit contributions
 commute+0.995
 commuting+0.810
 notation+0.782
 flakes+0.747
 aeros+0.744
Neg logit contributions
Sov-1.402
-1.308
 Zhu-1.300
vacc-1.283
 Qin-1.242
Token,
Token ID11
Feature activation-9.34e-02

Pos logit contributions
 commute+0.687
 commuting+0.570
 notation+0.550
 flakes+0.529
 aeros+0.526
Neg logit contributions
Sov-0.839
-0.786
 Zhu-0.776
vacc-0.765
 Qin-0.739
Token oppose
Token ID12856
Feature activation-7.13e-01

Pos logit contributions
Sov+0.443
+0.416
 Zhu+0.410
vacc+0.405
 Qin+0.390
Neg logit contributions
 commute-0.386
 commuting-0.323
 notation-0.315
 flakes-0.303
 aeros-0.302
Token what
Token ID644
Feature activation-9.98e-01

Pos logit contributions
 commute+0.571
 commuting+0.485
 notation+0.472
 flakes+0.456
 aeros+0.454
Neg logit contributions
Sov-0.546
-0.501
 Zhu-0.498
vacc-0.490
 Qin-0.471
Token my
Token ID616
Feature activation-1.81e+00

Pos logit contributions
 commute+0.746
 commuting+0.626
 notation+0.608
 flakes+0.585
 aeros+0.583
Neg logit contributions
Sov-0.817
-0.756
 Zhu-0.750
vacc-0.739
 Qin-0.713
Token president
Token ID1893
Feature activation-1.73e+00

Pos logit contributions
 commute+1.289
 commuting+1.070
 notation+1.038
 flakes+0.996
 aeros+0.992
Neg logit contributions
Sov-1.551
-1.439
 Zhu-1.430
vacc-1.409
 Qin-1.360
Token stands
Token ID6296
Feature activation-1.52e+00

Pos logit contributions
 commute+1.250
 commuting+1.041
 notation+1.008
 flakes+0.969
 aeros+0.965
Neg logit contributions
Sov-1.467
-1.356
 Zhu-1.349
vacc-1.330
 Qin-1.282
Token for
Token ID329
Feature activation-4.16e+00

Pos logit contributions
 commute+1.097
 commuting+0.914
 notation+0.887
 flakes+0.852
 aeros+0.848
Neg logit contributions
Sov-1.282
-1.186
 Zhu-1.179
vacc-1.163
 Qin-1.121
Token,
Token ID11
Feature activation-1.10e+00

Pos logit contributions
 commute+3.150
 commuting+2.658
 notation+2.556
 flakes+2.462
 aeros+2.453
Neg logit contributions
Sov-3.359
 Zhu-3.057
vacc-2.996
-2.996
 Qin-2.880
Token his
Token ID465
Feature activation-5.51e-01

Pos logit contributions
 commute+0.915
 commuting+0.783
 notation+0.763
 flakes+0.738
 aeros+0.735
Neg logit contributions
Sov-0.806
-0.737
 Zhu-0.732
vacc-0.720
 Qin-0.690
Token incompetence
Token ID39674
Feature activation-8.89e-01

Pos logit contributions
 commute+0.409
 commuting+0.343
 notation+0.334
 flakes+0.322
 aeros+0.320
Neg logit contributions
Sov-0.452
-0.419
 Zhu-0.416
vacc-0.410
 Qin-0.395
Token,
Token ID11
Feature activation+1.93e-01

Pos logit contributions
 commute+0.645
 commuting+0.538
 notation+0.522
 flakes+0.501
 aeros+0.500
Neg logit contributions
Sov-0.747
-0.694
 Zhu-0.688
vacc-0.678
 Qin-0.655
Token potential
Token ID2785
Feature activation-8.65e-01

Pos logit contributions
Sov+0.141
+0.131
 Zhu+0.129
vacc+0.127
 Qin+0.122
Neg logit contributions
 commute-0.160
 commuting-0.136
 notation-0.133
 flakes-0.129
 aeros-0.128
Token decades
Token ID4647
Feature activation+1.14e+00

Pos logit contributions
Sov+0.211
 Zhu+0.197
+0.196
vacc+0.191
 Qin+0.186
Neg logit contributions
 commute-0.210
 commuting-0.177
 notation-0.173
 flakes-0.167
 aeros-0.164
Token to
Token ID284
Feature activation+4.90e-01

Pos logit contributions
Sov+0.847
+0.793
 Zhu+0.788
vacc+0.767
 Qin+0.744
Neg logit contributions
 commute-0.912
 commuting-0.771
 notation-0.760
 flakes-0.736
 aeros-0.731
Token come
Token ID1282
Feature activation+8.28e-01

Pos logit contributions
Sov+0.360
+0.335
 Zhu+0.332
vacc+0.323
 Qin+0.314
Neg logit contributions
 commute-0.391
 commuting-0.339
 notation-0.331
 flakes-0.317
 aeros-0.313
Token back
Token ID736
Feature activation+5.97e-01

Pos logit contributions
Sov+0.645
+0.600
 Zhu+0.594
vacc+0.578
 Qin+0.563
Neg logit contributions
 commute-0.645
 commuting-0.544
 notation-0.533
 flakes-0.511
 aeros-0.508
Token after
Token ID706
Feature activation+1.38e-01

Pos logit contributions
Sov+0.463
+0.431
 Zhu+0.427
vacc+0.416
 Qin+0.404
Neg logit contributions
 commute-0.467
 commuting-0.394
 notation-0.386
 flakes-0.371
 aeros-0.368
Token finishing
Token ID12848
Feature activation+2.96e+00

Pos logit contributions
Sov+0.109
+0.100
 Zhu+0.100
vacc+0.098
 Qin+0.095
Neg logit contributions
 commute-0.106
 commuting-0.089
 notation-0.087
 flakes-0.084
 aeros-0.083
Token operations
Token ID4560
Feature activation+1.82e+00

Pos logit contributions
Sov+2.070
+1.914
 Zhu+1.910
vacc+1.836
 Qin+1.804
Neg logit contributions
 commute-2.472
 commuting-2.104
 notation-2.084
 flakes-2.015
minster-1.995
Token;
Token ID26
Feature activation+1.88e+00

Pos logit contributions
Sov+1.386
+1.299
 Zhu+1.287
vacc+1.251
 Qin+1.222
Neg logit contributions
 commute-1.426
 commuting-1.201
 notation-1.184
 flakes-1.133
 aeros-1.123
Token we
Token ID356
Feature activation+1.40e+00

Pos logit contributions
Sov+1.419
 Zhu+1.327
+1.316
vacc+1.278
 Qin+1.251
Neg logit contributions
 commute-1.499
 commuting-1.260
 notation-1.240
 flakes-1.193
 aeros-1.175
Token will
Token ID481
Feature activation+1.39e+00

Pos logit contributions
Sov+1.131
+1.060
 Zhu+1.048
vacc+1.029
 Qin+1.000
Neg logit contributions
 commute-1.034
 commuting-0.878
 notation-0.857
 flakes-0.818
 aeros-0.810
Token re
Token ID302
Feature activation+3.21e-01

Pos logit contributions
Sov+1.120
+1.048
 Zhu+1.036
vacc+1.016
 Qin+0.986
Neg logit contributions
 commute-1.027
 commuting-0.877
 notation-0.849
 flakes-0.815
 aeros-0.808
Tokenma
Token ID2611
Feature activation+4.09e-02

Pos logit contributions
 commute+1.476
 commuting+1.292
 notation+1.271
 flakes+1.238
 aeros+1.236
Neg logit contributions
Sov-0.841
 Zhu-0.738
-0.737
vacc-0.711
��-0.696
Token v
Token ID410
Feature activation-8.16e-01

Pos logit contributions
Sov+0.032
+0.029
 Zhu+0.029
vacc+0.028
 Qin+0.027
Neg logit contributions
 commute-0.033
 commuting-0.028
 notation-0.027
 flakes-0.026
 aeros-0.026
Token Goodell
Token ID41648
Feature activation+2.03e+00

Pos logit contributions
 commute+0.686
 commuting+0.588
 notation+0.573
 flakes+0.555
 aeros+0.552
Neg logit contributions
Sov-0.593
-0.540
 Zhu-0.535
vacc-0.527
 Qin-0.503
Token Original
Token ID13745
Feature activation+5.43e-01

Pos logit contributions
Sov+1.593
 Zhu+1.485
+1.478
vacc+1.456
 Qin+1.416
Neg logit contributions
 commute-1.558
 commuting-1.311
 notation-1.263
 flakes-1.228
 aeros-1.222
Token Compl
Token ID20011
Feature activation+3.66e+00

Pos logit contributions
Sov+0.423
+0.391
 Zhu+0.389
vacc+0.382
 Qin+0.369
Neg logit contributions
 commute-0.425
 commuting-0.360
 notation-0.348
 flakes-0.338
 aeros-0.336
Tokenaint
Token ID2913
Feature activation+4.45e+00

Pos logit contributions
Sov+1.965
+1.757
 Zhu+1.741
vacc+1.688
 Qin+1.615
Neg logit contributions
 commute-3.727
 commuting-3.297
 notation-3.196
 flakes-3.151
 aeros-3.149
Token
Token ID198
Feature activation-2.42e-01

Pos logit contributions
Sov+3.479
 Zhu+3.255
+3.255
vacc+3.154
 Qin+3.102
Neg logit contributions
 commute-3.384
 commuting-2.845
 notation-2.693
 flakes-2.641
 aeros-2.636
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
 commute+0.157
 commuting+0.128
 notation+0.124
 flakes+0.118
 aeros+0.118
Neg logit contributions
Sov-0.221
-0.205
 Zhu-0.204
vacc-0.202
��-0.196
TokenV
Token ID53
Feature activation+3.85e-01

Pos logit contributions
 commute+0.125
 commuting+0.109
 notation+0.107
 flakes+0.104
 aeros+0.104
Neg logit contributions
Sov-0.080
-0.072
 Zhu-0.072
vacc-0.070
 Qin-0.067
Tokenil
Token ID346
Feature activation-1.32e+00

Pos logit contributions
Sov+0.310
+0.286
 Zhu+0.283
vacc+0.281
 Qin+0.269
Neg logit contributions
 commute-0.295
 commuting-0.249
 notation-0.240
 aeros-0.232
 flakes-0.231
Tokenma
Token ID2611
Feature activation-1.05e-01

Pos logit contributions
 commute+1.317
 commuting+1.154
 notation+1.135
 flakes+1.106
 aeros+1.106
Neg logit contributions
Sov-0.742
 Zhu-0.654
-0.651
vacc-0.628
��-0.611
Tokenume
Token ID2454
Feature activation-2.75e-02

Pos logit contributions
Sov+0.514
+0.473
 Zhu+0.468
vacc+0.461
 Qin+0.441
Neg logit contributions
 commute-0.576
 commuting-0.493
 notation-0.480
 flakes-0.463
 aeros-0.462
Token is
Token ID318
Feature activation+2.23e-01

Pos logit contributions
 commute+0.020
 commuting+0.017
 notation+0.016
 aeros+0.016
 flakes+0.015
Neg logit contributions
Sov-0.023
-0.021
 Zhu-0.021
vacc-0.021
 Qin-0.020
Token,
Token ID11
Feature activation+3.22e-01

Pos logit contributions
Sov+0.180
+0.167
 Zhu+0.166
vacc+0.163
 Qin+0.158
Neg logit contributions
 commute-0.168
 commuting-0.140
 notation-0.137
 flakes-0.131
 aeros-0.131
Token finally
Token ID3443
Feature activation+2.04e+00

Pos logit contributions
Sov+0.266
+0.249
 Zhu+0.249
vacc+0.242
 Qin+0.236
Neg logit contributions
 commute-0.234
 commuting-0.194
 notation-0.190
 flakes-0.182
 aeros-0.182
Token,
Token ID11
Feature activation-3.58e-01

Pos logit contributions
Sov+1.666
+1.585
 Zhu+1.565
vacc+1.518
 Qin+1.474
Neg logit contributions
 commute-1.487
 commuting-1.241
 notation-1.211
 aeros-1.160
 flakes-1.142
Token very
Token ID845
Feature activation+3.04e+00

Pos logit contributions
 commute+0.278
 commuting+0.234
 notation+0.228
 flakes+0.220
 aeros+0.219
Neg logit contributions
Sov-0.282
-0.260
 Zhu-0.258
vacc-0.254
 Qin-0.245
Token much
Token ID881
Feature activation-1.03e+00

Pos logit contributions
Sov+2.365
 Zhu+2.216
+2.203
vacc+2.133
 Qin+2.081
Neg logit contributions
 commute-2.321
 commuting-1.936
 notation-1.884
 aeros-1.821
minster-1.808
Token part
Token ID636
Feature activation+2.97e-01

Pos logit contributions
 commute+0.781
 commuting+0.657
 notation+0.638
 flakes+0.615
 aeros+0.612
Neg logit contributions
Sov-0.830
-0.766
 Zhu-0.761
vacc-0.750
 Qin-0.721
Token of
Token ID286
Feature activation+3.76e-01

Pos logit contributions
Sov+0.247
+0.230
 Zhu+0.229
vacc+0.225
 Qin+0.218
Neg logit contributions
 commute-0.216
 commuting-0.179
 notation-0.176
 aeros-0.168
 flakes-0.168
Token the
Token ID262
Feature activation-3.73e-02

Pos logit contributions
Sov+0.272
+0.250
 Zhu+0.248
vacc+0.243
 Qin+0.233
Neg logit contributions
 commute-0.317
 commuting-0.270
 notation-0.264
 flakes-0.256
 aeros-0.255
Token women
Token ID1466
Feature activation-5.94e-01

Pos logit contributions
 commute+0.029
 commuting+0.024
 notation+0.024
 flakes+0.023
 aeros+0.023
Neg logit contributions
Sov-0.030
-0.027
 Zhu-0.027
vacc-0.027
 Qin-0.026
Token August
Token ID2932
Feature activation-6.75e-01

Pos logit contributions
 commute+0.511
 commuting+0.435
 notation+0.427
 flakes+0.410
 aeros+0.409
Neg logit contributions
Sov-0.451
 Zhu-0.414
-0.413
vacc-0.402
 Qin-0.390
Token A
Token ID317
Feature activation-1.19e+00

Pos logit contributions
 commute+0.533
 commuting+0.452
 notation+0.439
 aeros+0.423
 flakes+0.423
Neg logit contributions
Sov-0.521
-0.481
 Zhu-0.479
vacc-0.469
 Qin-0.454
Token.
Token ID13
Feature activation+5.59e-01

Pos logit contributions
 commute+0.989
 commuting+0.845
 notation+0.823
 flakes+0.796
 aeros+0.793
Neg logit contributions
Sov-0.877
-0.803
 Zhu-0.798
vacc-0.785
 Qin-0.752
Token Bus
Token ID5869
Feature activation+9.82e-02

Pos logit contributions
Sov+0.418
+0.384
 Zhu+0.383
vacc+0.375
 Qin+0.362
Neg logit contributions
 commute-0.458
 commuting-0.390
 notation-0.380
 flakes-0.366
 aeros-0.365
Tokench
Token ID354
Feature activation+3.12e-01

Pos logit contributions
Sov+0.066
+0.060
 Zhu+0.060
vacc+0.059
 Qin+0.056
Neg logit contributions
 commute-0.088
 commuting-0.076
 notation-0.074
 flakes-0.072
 aeros-0.072
Token Jr
Token ID7504
Feature activation+3.05e+00

Pos logit contributions
Sov+0.251
+0.233
 Zhu+0.231
vacc+0.228
 Qin+0.219
Neg logit contributions
 commute-0.236
 commuting-0.198
 notation-0.192
 flakes-0.185
 aeros-0.184
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
Sov+1.877
+1.723
 Zhu+1.687
vacc+1.671
 Qin+1.572
Neg logit contributions
 commute-2.824
 commuting-2.465
 notation-2.409
 aeros-2.336
 flakes-2.332
Token and
Token ID290
Feature activation+2.43e-01

Pos logit contributions
Sov+0.804
+0.748
 Zhu+0.743
vacc+0.728
 Qin+0.705
Neg logit contributions
 commute-0.785
 commuting-0.662
 notation-0.644
 flakes-0.622
 aeros-0.617
Token Ad
Token ID1215
Feature activation-4.98e-01

Pos logit contributions
Sov+0.183
 Zhu+0.169
+0.169
vacc+0.164
 Qin+0.160
Neg logit contributions
 commute-0.195
 commuting-0.166
 notation-0.162
 flakes-0.156
 aeros-0.155
Tokenolph
Token ID10196
Feature activation-1.75e+00

Pos logit contributions
 commute+0.393
 commuting+0.333
 notation+0.323
 flakes+0.311
 aeros+0.311
Neg logit contributions
Sov-0.387
-0.357
 Zhu-0.355
vacc-0.350
 Qin-0.336
Tokenus
Token ID385
Feature activation+1.75e+00

Pos logit contributions
 commute+1.442
 commuting+1.234
 notation+1.202
 flakes+1.162
 aeros+1.156
Neg logit contributions
Sov-1.293
-1.177
 Zhu-1.165
vacc-1.154
 Qin-1.095
Tokenention
Token ID1463
Feature activation+3.92e-01

Pos logit contributions
Sov+0.177
+0.167
 Zhu+0.164
vacc+0.163
 Qin+0.157
Neg logit contributions
 commute-0.116
 commuting-0.093
 notation-0.089
 aeros-0.085
 flakes-0.084
Token:
Token ID25
Feature activation+1.87e-01

Pos logit contributions
Sov+0.324
+0.306
 Zhu+0.304
vacc+0.294
 Qin+0.288
Neg logit contributions
 commute-0.285
 commuting-0.238
 notation-0.228
 aeros-0.222
 flakes-0.220
Token
Token ID198
Feature activation+5.56e-01

Pos logit contributions
Sov+0.143
+0.132
 Zhu+0.132
vacc+0.129
 Qin+0.125
Neg logit contributions
 commute-0.150
 commuting-0.127
 notation-0.124
 flakes-0.119
 aeros-0.119
Token
Token ID198
Feature activation+7.12e-01

Pos logit contributions
Sov+0.490
+0.458
 Zhu+0.454
vacc+0.447
 Qin+0.433
Neg logit contributions
 commute-0.381
 commuting-0.315
 notation-0.304
 flakes-0.291
 aeros-0.290
Token706
Token ID35402
Feature activation-3.38e-01

Pos logit contributions
Sov+0.481
+0.436
 Zhu+0.430
vacc+0.423
 Qin+0.403
Neg logit contributions
 commute-0.638
 commuting-0.553
 notation-0.539
 flakes-0.523
 aeros-0.521
Token Main
Token ID8774
Feature activation+3.33e+00

Pos logit contributions
 commute+0.273
 commuting+0.232
 notation+0.226
 flakes+0.219
 aeros+0.218
Neg logit contributions
Sov-0.256
-0.234
 Zhu-0.232
vacc-0.230
 Qin-0.219
Token Today
Token ID6288
Feature activation+1.97e+00

Pos logit contributions
Sov+2.523
+2.376
 Zhu+2.361
vacc+2.291
 Qin+2.224
Neg logit contributions
 commute-2.631
 commuting-2.227
 notation-2.181
 flakes-2.103
 aeros-2.090
Token:
Token ID25
Feature activation+9.84e-01

Pos logit contributions
Sov+1.592
+1.496
 Zhu+1.484
vacc+1.437
 Qin+1.408
Neg logit contributions
 commute-1.463
 commuting-1.233
 notation-1.197
 flakes-1.144
 aeros-1.143
Token The
Token ID383
Feature activation+1.50e+00

Pos logit contributions
Sov+0.748
 Zhu+0.693
+0.691
vacc+0.669
 Qin+0.655
Neg logit contributions
 commute-0.791
 commuting-0.673
 notation-0.655
 flakes-0.629
 aeros-0.628
Token Burger
Token ID28983
Feature activation+1.69e+00

Pos logit contributions
Sov+1.132
 Zhu+1.052
+1.049
vacc+1.014
 Qin+0.995
Neg logit contributions
 commute-1.203
 commuting-1.026
 notation-0.994
 flakes-0.956
 aeros-0.956
Token Guys
Token ID29899
Feature activation-2.63e-01

Pos logit contributions
Sov+1.270
+1.171
 Zhu+1.164
vacc+1.135
 Qin+1.099
Neg logit contributions
 commute-1.377
 commuting-1.174
 notation-1.141
 flakes-1.100
 aeros-1.098
Token
Token ID198
Feature activation+6.38e-01

Pos logit contributions
Sov+0.314
+0.292
 Zhu+0.290
vacc+0.286
 Qin+0.277
Neg logit contributions
 commute-0.238
 commuting-0.196
 notation-0.189
 flakes-0.181
 aeros-0.180
Token"
Token ID1
Feature activation+2.99e-01

Pos logit contributions
Sov+0.427
+0.386
 Zhu+0.382
vacc+0.376
 Qin+0.357
Neg logit contributions
 commute-0.576
 commuting-0.499
 notation-0.486
 flakes-0.472
 aeros-0.471
TokenWorking
Token ID28516
Feature activation-1.28e+00

Pos logit contributions
Sov+0.198
+0.180
 Zhu+0.178
vacc+0.175
 Qin+0.166
Neg logit contributions
 commute-0.271
 commuting-0.235
 notation-0.229
 flakes-0.223
 aeros-0.222
Token on
Token ID319
Feature activation-4.36e-01

Pos logit contributions
 commute+0.977
 commuting+0.822
 notation+0.799
 flakes+0.770
 aeros+0.767
Neg logit contributions
Sov-1.031
-0.952
 Zhu-0.946
vacc-0.931
 Qin-0.897
Token Yog
Token ID31604
Feature activation+3.64e-01

Pos logit contributions
 commute+0.374
 commuting+0.322
 notation+0.314
 flakes+0.304
 aeros+0.303
Neg logit contributions
Sov-0.310
-0.282
 Zhu-0.279
vacc-0.276
 Qin-0.263
Tokenventures
Token ID10065
Feature activation+1.20e+00

Pos logit contributions
Sov+0.220
+0.197
 Zhu+0.195
vacc+0.191
 Qin+0.181
Neg logit contributions
 commute-0.350
 commuting-0.306
 notation-0.300
 flakes-0.291
 aeros-0.290
Token was
Token ID373
Feature activation+3.72e-01

Pos logit contributions
Sov+0.984
+0.913
 Zhu+0.906
vacc+0.888
 Qin+0.861
Neg logit contributions
 commute-0.881
 commuting-0.736
 notation-0.716
 flakes-0.688
 aeros-0.686
Token an
Token ID281
Feature activation+1.09e+00

Pos logit contributions
Sov+0.293
+0.271
 Zhu+0.270
vacc+0.264
 Qin+0.256
Neg logit contributions
 commute-0.286
 commuting-0.241
 notation-0.236
 flakes-0.228
 aeros-0.226
Token amazing
Token ID4998
Feature activation-5.35e-01

Pos logit contributions
Sov+0.906
+0.848
 Zhu+0.843
vacc+0.821
 Qin+0.802
Neg logit contributions
 commute-0.776
 commuting-0.650
 notation-0.635
 flakes-0.610
 aeros-0.600
Token experience
Token ID1998
Feature activation+5.68e-01

Pos logit contributions
 commute+0.387
 commuting+0.324
 notation+0.315
 flakes+0.304
 aeros+0.301
Neg logit contributions
Sov-0.446
-0.415
 Zhu-0.413
vacc-0.405
 Qin-0.392
Token and
Token ID290
Feature activation+5.26e-02

Pos logit contributions
Sov+0.449
+0.421
 Zhu+0.417
vacc+0.406
 Qin+0.395
Neg logit contributions
 commute-0.430
 commuting-0.360
 notation-0.355
 flakes-0.343
 aeros-0.340
Token uses
Token ID3544
Feature activation+7.38e-01

Pos logit contributions
 commute+0.314
 commuting+0.258
 notation+0.250
 flakes+0.239
 aeros+0.238
Neg logit contributions
Sov-0.412
-0.384
 Zhu-0.381
vacc-0.376
 Qin-0.364
Token?
Token ID30
Feature activation+1.12e+00

Pos logit contributions
Sov+0.554
+0.517
 Zhu+0.507
vacc+0.499
 Qin+0.481
Neg logit contributions
 commute-0.595
 commuting-0.507
 notation-0.493
 flakes-0.476
 aeros-0.475
Token How
Token ID1374
Feature activation+2.89e-01

Pos logit contributions
Sov+0.811
+0.750
 Zhu+0.743
vacc+0.725
 Qin+0.701
Neg logit contributions
 commute-0.934
 commuting-0.800
 notation-0.777
 flakes-0.752
 aeros-0.750
Token about
Token ID546
Feature activation-5.81e-01

Pos logit contributions
Sov+0.225
+0.208
 Zhu+0.206
vacc+0.203
 Qin+0.195
Neg logit contributions
 commute-0.227
 commuting-0.193
 notation-0.187
 flakes-0.180
 aeros-0.180
Token after
Token ID706
Feature activation+2.92e-01

Pos logit contributions
 commute+0.409
 commuting+0.339
 notation+0.329
 flakes+0.315
 aeros+0.314
Neg logit contributions
Sov-0.500
-0.464
 Zhu-0.461
vacc-0.455
 Qin-0.439
Token a
Token ID257
Feature activation+3.29e-01

Pos logit contributions
Sov+0.225
+0.207
 Zhu+0.206
vacc+0.202
 Qin+0.195
Neg logit contributions
 commute-0.232
 commuting-0.197
 notation-0.192
 flakes-0.185
 aeros-0.184
Token year
Token ID614
Feature activation-2.50e-02

Pos logit contributions
Sov+0.258
+0.237
 Zhu+0.236
vacc+0.232
 Qin+0.223
Neg logit contributions
 commute-0.258
 commuting-0.218
 notation-0.212
 flakes-0.204
 aeros-0.204
Token?
Token ID30
Feature activation+3.08e-01

Pos logit contributions
 commute+0.020
 commuting+0.017
 notation+0.017
 flakes+0.016
 aeros+0.016
Neg logit contributions
Sov-0.019
-0.017
 Zhu-0.017
vacc-0.017
 Qin-0.016
Token How
Token ID1374
Feature activation+1.27e-01

Pos logit contributions
Sov+0.217
+0.199
 Zhu+0.197
vacc+0.193
 Qin+0.186
Neg logit contributions
 commute-0.265
 commuting-0.228
 notation-0.222
 flakes-0.215
 aeros-0.215
Token about
Token ID546
Feature activation-6.22e-01

Pos logit contributions
Sov+0.097
+0.090
 Zhu+0.089
vacc+0.087
 Qin+0.084
Neg logit contributions
 commute-0.101
 commuting-0.086
 notation-0.083
 flakes-0.080
 aeros-0.080
Token when
Token ID618
Feature activation+6.05e-01

Pos logit contributions
 commute+0.440
 commuting+0.365
 notation+0.353
 flakes+0.339
 aeros+0.338
Neg logit contributions
Sov-0.535
-0.496
 Zhu-0.493
vacc-0.486
 Qin-0.469
Token in
Token ID287
Feature activation+7.07e-01

Pos logit contributions
Sov+0.382
+0.353
 Zhu+0.351
vacc+0.345
 Qin+0.334
Neg logit contributions
 commute-0.352
 commuting-0.293
 notation-0.289
 flakes-0.277
 aeros-0.276
Token the
Token ID262
Feature activation+5.17e-01

Pos logit contributions
Sov+0.495
+0.453
 Zhu+0.449
vacc+0.441
 Qin+0.425
Neg logit contributions
 commute-0.603
 commuting-0.516
 notation-0.509
 flakes-0.493
 aeros-0.490
Token Medicare
Token ID13771
Feature activation+7.37e-02

Pos logit contributions
Sov+0.387
+0.358
 Zhu+0.355
vacc+0.348
 Qin+0.337
Neg logit contributions
 commute-0.416
 commuting-0.354
 notation-0.347
 flakes-0.335
 aeros-0.333
Token Advantage
Token ID45318
Feature activation+6.13e-01

Pos logit contributions
Sov+0.055
+0.051
 Zhu+0.051
vacc+0.050
 Qin+0.048
Neg logit contributions
 commute-0.059
 commuting-0.051
 notation-0.049
 flakes-0.048
 aeros-0.047
Token business
Token ID1597
Feature activation+1.64e+00

Pos logit contributions
Sov+0.433
+0.398
 Zhu+0.394
vacc+0.387
 Qin+0.374
Neg logit contributions
 commute-0.520
 commuting-0.447
 notation-0.436
 flakes-0.423
 aeros-0.420
Token;
Token ID26
Feature activation+7.63e-01

Pos logit contributions
Sov+1.252
+1.149
 Zhu+1.145
vacc+1.124
 Qin+1.088
Neg logit contributions
 commute-1.287
 commuting-1.091
 notation-1.064
 flakes-1.036
 aeros-1.026
Token they
Token ID484
Feature activation+8.83e-01

Pos logit contributions
Sov+0.662
+0.614
 Zhu+0.613
vacc+0.603
 Qin+0.586
Neg logit contributions
 commute-0.528
 commuting-0.434
 notation-0.424
 flakes-0.407
 aeros-0.403
Token're
Token ID821
Feature activation+1.01e+00

Pos logit contributions
Sov+0.699
+0.650
 Zhu+0.641
vacc+0.634
 Qin+0.612
Neg logit contributions
 commute-0.660
 commuting-0.566
 notation-0.554
 flakes-0.529
 aeros-0.525
Token not
Token ID407
Feature activation+7.05e-01

Pos logit contributions
Sov+0.885
+0.820
 Zhu+0.817
vacc+0.803
 Qin+0.782
Neg logit contributions
 commute-0.687
 commuting-0.559
 notation-0.549
 flakes-0.525
 aeros-0.523
Token in
Token ID287
Feature activation+7.63e-01

Pos logit contributions
Sov+0.579
+0.535
 Zhu+0.532
vacc+0.523
 Qin+0.507
Neg logit contributions
 commute-0.522
 commuting-0.434
 notation-0.426
 flakes-0.410
 aeros-0.407
Token the
Token ID262
Feature activation+4.60e-01

Pos logit contributions
Sov+0.541
+0.494
 Zhu+0.491
vacc+0.482
 Qin+0.464
Neg logit contributions
 commute-0.651
 commuting-0.557
 notation-0.546
 flakes-0.531
 aeros-0.526
Tokenci
Token ID979
Feature activation+2.34e-01

Pos logit contributions
Sov+0.480
+0.436
 Zhu+0.433
vacc+0.423
 Qin+0.409
Neg logit contributions
 commute-0.532
 commuting-0.453
 notation-0.442
 flakes-0.427
 aeros-0.426
Token/
Token ID14
Feature activation+3.20e+00

Pos logit contributions
Sov+0.144
 Zhu+0.128
+0.127
vacc+0.124
��+0.122
Neg logit contributions
 commute-0.223
 commuting-0.194
 notation-0.190
 aeros-0.185
 flakes-0.183
Token2
Token ID17
Feature activation+9.48e-01

Pos logit contributions
Sov+1.954
+1.747
 Zhu+1.732
vacc+1.711
 Qin+1.616
Neg logit contributions
 commute-3.066
 commuting-2.686
 notation-2.621
 flakes-2.563
 aeros-2.541
Tokenyp
Token ID4464
Feature activation-1.50e+00

Pos logit contributions
Sov+0.643
+0.582
 Zhu+0.577
vacc+0.568
 Qin+0.540
Neg logit contributions
 commute-0.847
 commuting-0.734
 notation-0.713
 flakes-0.693
 aeros-0.690
Tokend
Token ID67
Feature activation+1.26e+00

Pos logit contributions
 commute+1.393
 commuting+1.209
 notation+1.192
 flakes+1.152
 aeros+1.152
Neg logit contributions
Sov-0.937
-0.851
 Zhu-0.843
vacc-0.824
 Qin-0.787
TokenG
Token ID38
Feature activation+1.31e+00

Pos logit contributions
Sov+0.786
+0.706
 Zhu+0.700
vacc+0.686
 Qin+0.651
Neg logit contributions
 commute-1.190
 commuting-1.040
 notation-1.014
 flakes-0.987
 aeros-0.983
Tokenuf
Token ID3046
Feature activation-2.55e-02

Pos logit contributions
Sov+0.831
+0.747
 Zhu+0.741
vacc+0.727
 Qin+0.690
Neg logit contributions
 commute-1.229
 commuting-1.072
 notation-1.044
 flakes-1.016
 aeros-1.012
Token<|endoftext|>
Token ID50256
Feature activation-2.90e-01

Pos logit contributions
 commute+0.018
 commuting+0.015
 notation+0.015
 flakes+0.014
 aeros+0.014
Neg logit contributions
Sov-0.022
-0.020
 Zhu-0.020
vacc-0.020
 Qin-0.019
TokenA
Token ID32
Feature activation+1.23e+00

Pos logit contributions
 commute+0.254
 commuting+0.219
 notation+0.214
 flakes+0.207
 aeros+0.206
Neg logit contributions
Sov-0.200
-0.182
 Zhu-0.181
vacc-0.177
 Qin-0.170
Token statistical
Token ID13905
Feature activation+3.60e-01

Pos logit contributions
Sov+0.959
+0.888
 Zhu+0.883
vacc+0.871
 Qin+0.837
Neg logit contributions
 commute-0.952
 commuting-0.804
 notation-0.782
 flakes-0.758
 aeros-0.753
Token modeling
Token ID21128
Feature activation+8.08e-01

Pos logit contributions
Sov+0.246
+0.228
 Zhu+0.226
vacc+0.222
 Qin+0.212
Neg logit contributions
 commute-0.311
 commuting-0.268
 notation-0.259
 flakes-0.254
 aeros-0.252
Token
Token ID198
Feature activation-1.89e+00

Pos logit contributions
 commute+1.416
 commuting+1.122
 notation+1.099
 flakes+1.043
 aeros+1.035
Neg logit contributions
Sov-2.268
��-2.095
 Zhu-2.095
vacc-2.088
-2.086
TokenThis
Token ID1212
Feature activation-1.61e-02

Pos logit contributions
 commute+1.603
 commuting+1.371
 notation+1.353
 flakes+1.299
 aeros+1.290
Neg logit contributions
Sov-1.298
 Zhu-1.205
-1.188
vacc-1.168
 Qin-1.130
Token teen
Token ID6036
Feature activation+7.47e-01

Pos logit contributions
 commute+0.012
 commuting+0.010
 notation+0.010
 flakes+0.009
 aeros+0.009
Neg logit contributions
Sov-0.013
-0.012
 Zhu-0.012
vacc-0.012
 Qin-0.012
Token is
Token ID318
Feature activation+3.20e-01

Pos logit contributions
Sov+0.604
+0.559
 Zhu+0.559
vacc+0.549
 Qin+0.529
Neg logit contributions
 commute-0.556
 commuting-0.467
 notation-0.454
 flakes-0.438
 aeros-0.435
Token being
Token ID852
Feature activation+8.58e-02

Pos logit contributions
Sov+0.265
+0.246
 Zhu+0.244
vacc+0.241
 Qin+0.232
Neg logit contributions
 commute-0.236
 commuting-0.197
 notation-0.191
 flakes-0.184
 aeros-0.183
Token ID
Token ID4522
Feature activation+7.87e-01

Pos logit contributions
Sov+0.069
+0.064
 Zhu+0.064
vacc+0.063
 Qin+0.060
Neg logit contributions
 commute-0.065
 commuting-0.054
 notation-0.053
 flakes-0.051
 aeros-0.051
Token'd
Token ID1549
Feature activation+1.06e+00

Pos logit contributions
Sov+0.540
+0.491
 Zhu+0.487
vacc+0.478
 Qin+0.457
Neg logit contributions
 commute-0.692
 commuting-0.597
 notation-0.583
 flakes-0.564
 aeros-0.563
Token because
Token ID780
Feature activation-2.68e-01

Pos logit contributions
Sov+0.913
+0.861
 Zhu+0.859
vacc+0.840
 Qin+0.817
Neg logit contributions
 commute-0.726
 commuting-0.597
 notation-0.579
 flakes-0.558
 aeros-0.556
Token he
Token ID339
Feature activation-2.28e-01

Pos logit contributions
 commute+0.196
 commuting+0.164
 notation+0.160
 flakes+0.153
 aeros+0.153
Neg logit contributions
Sov-0.221
-0.205
 Zhu-0.205
vacc-0.201
 Qin-0.195
Token's
Token ID338
Feature activation+1.30e-01

Pos logit contributions
 commute+0.168
 commuting+0.141
 notation+0.137
 flakes+0.131
 aeros+0.131
Neg logit contributions
Sov-0.187
-0.174
 Zhu-0.173
vacc-0.170
 Qin-0.164
Token a
Token ID257
Feature activation-4.04e-01

Pos logit contributions
Sov+0.106
+0.098
 Zhu+0.097
vacc+0.096
 Qin+0.092
Neg logit contributions
 commute-0.097
 commuting-0.082
 notation-0.079
 flakes-0.076
 aeros-0.076
Tokenmen
Token ID3653
Feature activation+2.14e-01

Pos logit contributions
 commute+0.815
 commuting+0.686
 notation+0.666
 flakes+0.642
 aeros+0.640
Neg logit contributions
Sov-0.864
-0.795
 Zhu-0.791
vacc-0.779
 Qin-0.749
Token,
Token ID11
Feature activation-7.84e-01

Pos logit contributions
Sov+0.180
+0.171
 Zhu+0.167
vacc+0.164
 Qin+0.160
Neg logit contributions
 commute-0.154
 commuting-0.128
 notation-0.123
 flakes-0.119
 aeros-0.118
Token 18
Token ID1248
Feature activation-1.33e+00

Pos logit contributions
 commute+0.615
 commuting+0.520
 notation+0.506
 flakes+0.488
 aeros+0.486
Neg logit contributions
Sov-0.614
-0.564
 Zhu-0.561
vacc-0.553
 Qin-0.530
Token59
Token ID3270
Feature activation-1.24e+00

Pos logit contributions
 commute+1.184
 commuting+1.022
 notation+1.005
 flakes+0.976
 aeros+0.972
Neg logit contributions
Sov-0.885
 Zhu-0.793
-0.791
vacc-0.788
��-0.757
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
 commute+1.055
 commuting+0.906
 notation+0.882
 flakes+0.853
 aeros+0.850
Neg logit contributions
Sov-0.888
-0.816
 Zhu-0.807
vacc-0.793
 Qin-0.759
Token
Token ID198
Feature activation-1.75e-01

Pos logit contributions
 commute+0.809
 commuting+0.669
 notation+0.645
 flakes+0.619
 aeros+0.616
Neg logit contributions
Sov-1.018
-0.955
 Zhu-0.944
vacc-0.931
 Qin-0.901
Token
Token ID198
Feature activation-6.45e-02

Pos logit contributions
 commute+0.115
 commuting+0.094
 notation+0.091
 flakes+0.087
 aeros+0.086
Neg logit contributions
Sov-0.159
-0.147
 Zhu-0.147
vacc-0.145
 Qin-0.140
Token11
Token ID1157
Feature activation-7.64e-01

Pos logit contributions
 commute+0.057
 commuting+0.050
 notation+0.048
 flakes+0.047
 aeros+0.047
Neg logit contributions
Sov-0.044
-0.040
 Zhu-0.039
vacc-0.039
 Qin-0.037
Token)
Token ID8
Feature activation-7.77e-01

Pos logit contributions
 commute+0.543
 commuting+0.450
 notation+0.442
 flakes+0.423
 aeros+0.421
Neg logit contributions
Sov-0.649
 Zhu-0.592
-0.590
vacc-0.588
��-0.573
Token When
Token ID1649
Feature activation+6.12e-01

Pos logit contributions
 commute+0.508
 commuting+0.415
 notation+0.400
 flakes+0.382
 aeros+0.381
Neg logit contributions
Sov-0.709
-0.661
 Zhu-0.658
vacc-0.648
 Qin-0.628
Token Dancing
Token ID31799
Feature activation-8.48e-01

Pos logit contributions
Sov+0.486
+0.450
 Zhu+0.447
vacc+0.437
 Qin+0.424
Neg logit contributions
 commute-0.472
 commuting-0.397
 notation-0.386
 flakes-0.372
 aeros-0.371
Token
Token ID447
Feature activation+5.72e-02

Pos logit contributions
 commute+0.143
 commuting+0.120
 notation+0.117
 flakes+0.112
 aeros+0.112
Neg logit contributions
Sov-0.161
-0.150
 Zhu-0.148
vacc-0.146
 Qin-0.141
Token
Token ID247
Feature activation-2.41e-01

Pos logit contributions
Sov+0.031
+0.027
 Zhu+0.027
vacc+0.026
 Qin+0.025
Neg logit contributions
 commute-0.059
 commuting-0.052
 notation-0.051
 flakes-0.050
 aeros-0.049
Tokens
Token ID82
Feature activation-4.35e-01

Pos logit contributions
 commute+0.176
 commuting+0.147
 notation+0.143
 flakes+0.137
 aeros+0.137
Neg logit contributions
Sov-0.201
-0.188
 Zhu-0.185
vacc-0.183
 Qin-0.176
Token important
Token ID1593
Feature activation-9.44e-01

Pos logit contributions
 commute+0.318
 commuting+0.266
 notation+0.258
 flakes+0.248
 aeros+0.247
Neg logit contributions
Sov-0.362
-0.336
 Zhu-0.333
vacc-0.328
 Qin-0.316
Token to
Token ID284
Feature activation+3.53e-01

Pos logit contributions
 commute+0.737
 commuting+0.623
 notation+0.605
 flakes+0.585
 aeros+0.582
Neg logit contributions
Sov-0.742
-0.685
 Zhu-0.679
vacc-0.668
 Qin-0.642
Token enable
Token ID7139
Feature activation-1.19e-01

Pos logit contributions
Sov+0.288
+0.267
 Zhu+0.265
vacc+0.260
 Qin+0.251
Neg logit contributions
 commute-0.265
 commuting-0.222
 notation-0.216
 flakes-0.208
 aeros-0.207
Token them
Token ID606
Feature activation+5.54e-01

Pos logit contributions
 commute+0.095
 commuting+0.080
 notation+0.078
 flakes+0.075
 aeros+0.075
Neg logit contributions
Sov-0.092
-0.085
 Zhu-0.084
vacc-0.083
 Qin-0.080
Token for
Token ID329
Feature activation+1.69e-01

Pos logit contributions
Sov+0.450
+0.421
 Zhu+0.413
vacc+0.407
 Qin+0.393
Neg logit contributions
 commute-0.415
 commuting-0.348
 notation-0.338
 flakes-0.326
 aeros-0.325
Token the
Token ID262
Feature activation+2.25e-01

Pos logit contributions
Sov+0.129
+0.119
 Zhu+0.118
vacc+0.116
 Qin+0.111
Neg logit contributions
 commute-0.134
 commuting-0.114
 notation-0.111
 flakes-0.108
 aeros-0.107
Token future
Token ID2003
Feature activation+9.07e-01

Pos logit contributions
Sov+0.183
+0.170
 Zhu+0.169
vacc+0.165
 Qin+0.160
Neg logit contributions
 commute-0.168
 commuting-0.141
 notation-0.137
 flakes-0.133
 aeros-0.132
Token.
Token ID13
Feature activation+9.87e-02

Pos logit contributions
Sov+0.693
+0.650
 Zhu+0.635
vacc+0.623
 Qin+0.602
Neg logit contributions
 commute-0.714
 commuting-0.606
 notation-0.592
 flakes-0.572
 aeros-0.571
Token House
Token ID2097
Feature activation-3.73e-01

Pos logit contributions
Sov+0.508
+0.463
 Zhu+0.459
vacc+0.457
��+0.437
Neg logit contributions
 commute-0.505
 commuting-0.428
 notation-0.416
 flakes-0.403
 aeros-0.400
Token at
Token ID379
Feature activation+1.06e-01

Pos logit contributions
 commute+0.260
 commuting+0.215
 notation+0.209
 flakes+0.201
 aeros+0.199
Neg logit contributions
Sov-0.323
-0.301
 Zhu-0.300
vacc-0.295
 Qin-0.285
Token the
Token ID262
Feature activation+7.89e-01

Pos logit contributions
Sov+0.078
+0.072
 Zhu+0.072
vacc+0.070
 Qin+0.068
Neg logit contributions
 commute-0.087
 commuting-0.074
 notation-0.072
 flakes-0.070
 aeros-0.070
Token age
Token ID2479
Feature activation+4.52e+00

Pos logit contributions
Sov+0.577
+0.533
 Zhu+0.530
vacc+0.516
 Qin+0.499
Neg logit contributions
 commute-0.652
 commuting-0.558
 notation-0.542
 flakes-0.527
 aeros-0.526
Token of
Token ID286
Feature activation+1.05e+00

Pos logit contributions
Sov+3.600
+3.410
 Zhu+3.387
vacc+3.285
 Qin+3.207
Neg logit contributions
 commute-3.371
 commuting-2.822
 notation-2.738
 flakes-2.663
 aeros-2.637
Token just
Token ID655
Feature activation-6.35e-01

Pos logit contributions
Sov+0.768
+0.708
 Zhu+0.703
vacc+0.689
 Qin+0.663
Neg logit contributions
 commute-0.865
 commuting-0.738
 notation-0.719
 flakes-0.697
 aeros-0.693
Token 25
Token ID1679
Feature activation+1.20e+00

Pos logit contributions
 commute+0.509
 commuting+0.434
 notation+0.422
 flakes+0.405
 aeros+0.405
Neg logit contributions
Sov-0.489
-0.444
 Zhu-0.442
vacc-0.439
��-0.419
Token,
Token ID11
Feature activation+6.85e-01

Pos logit contributions
Sov+1.008
+0.957
 Zhu+0.947
vacc+0.924
 Qin+0.893
Neg logit contributions
 commute-0.858
 commuting-0.710
 notation-0.691
 flakes-0.663
 aeros-0.663
Token one
Token ID530
Feature activation+2.82e-01

Pos logit contributions
Sov+0.539
+0.505
 Zhu+0.502
vacc+0.488
 Qin+0.474
Neg logit contributions
 commute-0.528
 commuting-0.443
 notation-0.434
 flakes-0.417
 aeros-0.417
Token of
Token ID286
Feature activation+1.22e+00

Pos logit contributions
Sov+0.229
+0.215
 Zhu+0.214
vacc+0.209
 Qin+0.203
Neg logit contributions
 commute-0.208
 commuting-0.174
 notation-0.169
 flakes-0.163
 aeros-0.162
Token her
Token ID607
Feature activation+1.45e-01

Pos logit contributions
Sov+0.825
+0.762
 Zhu+0.758
vacc+0.734
 Qin+0.708
Neg logit contributions
 commute-1.077
 commuting-0.926
 notation-0.909
 flakes-0.878
 aeros-0.877
Token accommodate
Token ID15550
Feature activation+3.98e-01

Pos logit contributions
 commute+0.284
 commuting+0.239
 notation+0.232
 flakes+0.223
 aeros+0.222
Neg logit contributions
Sov-0.306
-0.283
 Zhu-0.281
vacc-0.277
 Qin-0.267
Token a
Token ID257
Feature activation-8.17e-03

Pos logit contributions
Sov+0.306
+0.283
 Zhu+0.281
vacc+0.276
 Qin+0.266
Neg logit contributions
 commute-0.313
 commuting-0.265
 notation-0.259
 flakes-0.250
 aeros-0.247
Token brief
Token ID4506
Feature activation+1.17e-01

Pos logit contributions
 commute+0.006
 commuting+0.005
 notation+0.005
 flakes+0.005
 aeros+0.005
Neg logit contributions
Sov-0.006
-0.006
 Zhu-0.006
vacc-0.006
 Qin-0.006
Token work
Token ID670
Feature activation+8.18e-02

Pos logit contributions
Sov+0.094
+0.087
 Zhu+0.086
vacc+0.085
 Qin+0.082
Neg logit contributions
 commute-0.088
 commuting-0.074
 notation-0.072
 flakes-0.070
 aeros-0.069
Token stopp
Token ID43804
Feature activation-4.91e-02

Pos logit contributions
Sov+0.072
+0.067
 Zhu+0.067
vacc+0.066
 Qin+0.063
Neg logit contributions
 commute-0.055
 commuting-0.046
 notation-0.044
 flakes-0.043
 aeros-0.042
Tokenage
Token ID496
Feature activation-7.79e-01

Pos logit contributions
 commute+0.040
 commuting+0.034
 notation+0.033
 aeros+0.031
 flakes+0.031
Neg logit contributions
Sov-0.038
-0.034
 Zhu-0.034
vacc-0.034
��-0.032
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
 commute+0.572
 commuting+0.478
 notation+0.464
 flakes+0.446
 aeros+0.444
Neg logit contributions
Sov-0.647
-0.599
 Zhu-0.595
vacc-0.586
 Qin-0.565
Token But
Token ID887
Feature activation-5.19e-01

Pos logit contributions
 commute+0.114
 commuting+0.096
 notation+0.093
 flakes+0.089
 aeros+0.089
Neg logit contributions
Sov-0.118
-0.110
 Zhu-0.109
vacc-0.106
 Qin-0.103
Token if
Token ID611
Feature activation+8.69e-01

Pos logit contributions
 commute+0.407
 commuting+0.344
 notation+0.335
 flakes+0.323
 aeros+0.321
Neg logit contributions
Sov-0.405
-0.374
 Zhu-0.371
vacc-0.365
 Qin-0.351
Token MA
Token ID8779
Feature activation+1.80e+00

Pos logit contributions
Sov+0.674
+0.622
 Zhu+0.617
vacc+0.604
 Qin+0.585
Neg logit contributions
 commute-0.682
 commuting-0.576
 notation-0.563
 flakes-0.541
 aeros-0.533
TokenVEN
Token ID28290
Feature activation-5.35e-02

Pos logit contributions
Sov+1.079
+0.967
 Zhu+0.960
vacc+0.940
 Qin+0.891
Neg logit contributions
 commute-1.741
 commuting-1.523
 notation-1.491
 flakes-1.449
 aeros-1.445
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
 commute+1.009
 commuting+0.836
 notation+0.807
 flakes+0.777
 aeros+0.775
Neg logit contributions
Sov-1.230
-1.144
 Zhu-1.136
vacc-1.118
 Qin-1.083
Token an
Token ID281
Feature activation+3.84e-01

Pos logit contributions
Sov+0.136
+0.126
 Zhu+0.125
vacc+0.123
 Qin+0.119
Neg logit contributions
 commute-0.139
 commuting-0.118
 notation-0.114
 flakes-0.110
 aeros-0.110
Token admin
Token ID13169
Feature activation-1.22e+00

Pos logit contributions
Sov+0.305
+0.282
 Zhu+0.280
vacc+0.275
 Qin+0.265
Neg logit contributions
 commute-0.296
 commuting-0.250
 notation-0.242
 flakes-0.234
 aeros-0.232
Token must
Token ID1276
Feature activation-4.27e-03

Pos logit contributions
 commute+0.870
 commuting+0.722
 notation+0.699
 flakes+0.672
 aeros+0.669
Neg logit contributions
Sov-1.046
-0.970
 Zhu-0.964
vacc-0.950
 Qin-0.918
Token be
Token ID307
Feature activation-7.02e-02

Pos logit contributions
 commute+0.003
 commuting+0.003
 notation+0.002
 flakes+0.002
 aeros+0.002
Neg logit contributions
Sov-0.004
-0.003
 Zhu-0.003
vacc-0.003
 Qin-0.003
Token placed
Token ID4624
Feature activation-3.04e-01

Pos logit contributions
 commute+0.051
 commuting+0.043
 notation+0.042
 flakes+0.040
 aeros+0.040
Neg logit contributions
Sov-0.058
-0.054
 Zhu-0.054
vacc-0.053
 Qin-0.051
Token behind
Token ID2157
Feature activation+5.81e-01

Pos logit contributions
 commute+0.223
 commuting+0.186
 notation+0.181
 flakes+0.175
 aeros+0.174
Neg logit contributions
Sov-0.251
-0.235
 Zhu-0.232
vacc-0.228
 Qin-0.221
Token every
Token ID790
Feature activation-5.06e-01

Pos logit contributions
Sov+0.413
+0.379
 Zhu+0.375
vacc+0.367
 Qin+0.354
Neg logit contributions
 commute-0.494
 commuting-0.424
 notation-0.411
 flakes-0.399
 aeros-0.397
Token team
Token ID1074
Feature activation-1.42e+00

Pos logit contributions
 commute+0.393
 commuting+0.332
 notation+0.323
 flakes+0.312
 aeros+0.310
Neg logit contributions
Sov-0.399
-0.367
 Zhu-0.365
vacc-0.359
 Qin-0.345
Token for
Token ID329
Feature activation+6.11e-01

Pos logit contributions
 commute+1.056
 commuting+0.885
 notation+0.860
 flakes+0.826
 aeros+0.823
Neg logit contributions
Sov-1.169
-1.079
 Zhu-1.073
vacc-1.057
 Qin-1.018
Token the
Token ID262
Feature activation+2.46e-01

Pos logit contributions
Sov+0.457
+0.424
 Zhu+0.422
vacc+0.412
 Qin+0.399
Neg logit contributions
 commute-0.493
 commuting-0.417
 notation-0.407
 flakes-0.396
 aeros-0.392
Token as
Token ID355
Feature activation+1.13e+00

Pos logit contributions
Sov+0.594
+0.549
 Zhu+0.547
vacc+0.536
 Qin+0.518
Neg logit contributions
 commute-0.566
 commuting-0.477
 notation-0.461
 flakes-0.446
 aeros-0.445
Token it
Token ID340
Feature activation+7.99e-01

Pos logit contributions
Sov+0.880
+0.814
 Zhu+0.809
vacc+0.792
 Qin+0.766
Neg logit contributions
 commute-0.878
 commuting-0.743
 notation-0.719
 flakes-0.695
 aeros-0.694
Token can
Token ID460
Feature activation+4.65e-03

Pos logit contributions
Sov+0.670
+0.624
 Zhu+0.619
vacc+0.608
 Qin+0.590
Neg logit contributions
 commute-0.575
 commuting-0.482
 notation-0.465
 aeros-0.447
 flakes-0.446
Token be
Token ID307
Feature activation-2.35e-01

Pos logit contributions
Sov+0.004
+0.004
 Zhu+0.004
vacc+0.004
 Qin+0.004
Neg logit contributions
 commute-0.003
 commuting-0.003
 notation-0.003
 flakes-0.002
 aeros-0.002
Token mult
Token ID1963
Feature activation+8.01e-01

Pos logit contributions
 commute+0.178
 commuting+0.149
 notation+0.145
 flakes+0.140
 aeros+0.139
Neg logit contributions
Sov-0.191
-0.176
 Zhu-0.175
vacc-0.173
 Qin-0.166
Tokenil
Token ID346
Feature activation-2.93e+00

Pos logit contributions
Sov+0.633
+0.586
 Zhu+0.581
vacc+0.573
 Qin+0.550
Neg logit contributions
 commute-0.620
 commuting-0.525
 notation-0.508
 flakes-0.490
 aeros-0.490
Tokenine
Token ID500
Feature activation-1.75e+00

Pos logit contributions
 commute+1.948
 commuting+1.586
 notation+1.552
 flakes+1.472
 aeros+1.453
Neg logit contributions
Sov-2.645
-2.449
 Zhu-2.439
vacc-2.406
 Qin-2.333
Token $
Token ID720
Feature activation+1.43e+00

Pos logit contributions
 commute+1.343
 commuting+1.127
 notation+1.106
 flakes+1.061
 aeros+1.051
Neg logit contributions
Sov-1.412
-1.293
 Zhu-1.280
vacc-1.273
 Qin-1.214
Tokenart
Token ID433
Feature activation-2.70e-01

Pos logit contributions
Sov+1.004
+0.913
 Zhu+0.909
vacc+0.894
 Qin+0.851
Neg logit contributions
 commute-1.231
 commuting-1.061
 notation-1.022
 aeros-0.999
 flakes-0.995
Tokenext
Token ID2302
Feature activation-1.17e+00

Pos logit contributions
 commute+0.213
 commuting+0.181
 notation+0.174
 flakes+0.170
 aeros+0.169
Neg logit contributions
Sov-0.210
-0.193
 Zhu-0.192
vacc-0.189
 Qin-0.182
Token =
Token ID796
Feature activation-3.77e-01

Pos logit contributions
 commute+0.891
 commuting+0.750
 notation+0.728
 flakes+0.702
 aeros+0.699
Neg logit contributions
Sov-0.940
-0.867
 Zhu-0.862
vacc-0.849
 Qin-0.817
Token who
Token ID508
Feature activation-9.00e-02

Pos logit contributions
 commute+0.473
 commuting+0.392
 notation+0.381
 flakes+0.366
 aeros+0.365
Neg logit contributions
Sov-0.551
-0.511
 Zhu-0.509
vacc-0.501
 Qin-0.484
Token paid
Token ID3432
Feature activation+2.25e-01

Pos logit contributions
 commute+0.065
 commuting+0.055
 notation+0.053
 flakes+0.051
 aeros+0.051
Neg logit contributions
Sov-0.075
-0.070
 Zhu-0.069
vacc-0.068
 Qin-0.066
Token extra
Token ID3131
Feature activation-1.49e+00

Pos logit contributions
Sov+0.178
 Zhu+0.164
+0.164
vacc+0.160
 Qin+0.155
Neg logit contributions
 commute-0.174
 commuting-0.146
 notation-0.142
 flakes-0.137
 aeros-0.137
Token for
Token ID329
Feature activation-5.75e-01

Pos logit contributions
 commute+1.132
 commuting+0.950
 notation+0.921
 flakes+0.889
 aeros+0.887
Neg logit contributions
Sov-1.203
-1.111
 Zhu-1.110
vacc-1.087
 Qin-1.052
Token other
Token ID584
Feature activation+1.09e+00

Pos logit contributions
 commute+0.498
 commuting+0.428
 notation+0.418
 flakes+0.405
 aeros+0.403
Neg logit contributions
Sov-0.402
-0.366
 Zhu-0.364
vacc-0.357
 Qin-0.342
Token rewards
Token ID11530
Feature activation-2.74e+00

Pos logit contributions
Sov+0.839
+0.774
 Zhu+0.771
vacc+0.755
 Qin+0.729
Neg logit contributions
 commute-0.854
 commuting-0.722
 notation-0.705
 flakes-0.679
 aeros-0.677
Token on
Token ID319
Feature activation-1.92e-01

Pos logit contributions
 commute+1.995
 commuting+1.667
 notation+1.617
 flakes+1.555
 aeros+1.546
Neg logit contributions
Sov-2.296
-2.123
 Zhu-2.104
vacc-2.083
 Qin-2.001
Token top
Token ID1353
Feature activation+6.19e-01

Pos logit contributions
 commute+0.175
 commuting+0.152
 notation+0.149
 flakes+0.144
 aeros+0.144
Neg logit contributions
Sov-0.125
-0.113
 Zhu-0.112
vacc-0.110
 Qin-0.105
Token of
Token ID286
Feature activation+4.38e-01

Pos logit contributions
Sov+0.505
+0.469
 Zhu+0.468
vacc+0.458
 Qin+0.443
Neg logit contributions
 commute-0.460
 commuting-0.386
 notation-0.373
 flakes-0.359
 aeros-0.358
Token a
Token ID257
Feature activation+7.97e-01

Pos logit contributions
Sov+0.286
+0.259
 Zhu+0.258
vacc+0.252
 Qin+0.241
Neg logit contributions
 commute-0.399
 commuting-0.345
 notation-0.338
 flakes-0.328
 aeros-0.327
Token copy
Token ID4866
Feature activation+4.93e-01

Pos logit contributions
Sov+0.636
 Zhu+0.592
+0.589
vacc+0.576
 Qin+0.559
Neg logit contributions
 commute-0.600
 commuting-0.506
 notation-0.489
 flakes-0.477
 aeros-0.472
Token There
Token ID1318
Feature activation-1.60e-01

Pos logit contributions
 commute+0.257
 commuting+0.218
 notation+0.212
 flakes+0.204
 aeros+0.204
Neg logit contributions
Sov-0.248
-0.229
 Zhu-0.227
vacc-0.222
 Qin-0.215
Token are
Token ID389
Feature activation+3.33e-01

Pos logit contributions
 commute+0.112
 commuting+0.092
 notation+0.089
 flakes+0.086
 aeros+0.085
Neg logit contributions
Sov-0.139
-0.130
 Zhu-0.129
vacc-0.127
 Qin-0.122
Token knit
Token ID30495
Feature activation+8.10e-01

Pos logit contributions
Sov+0.275
+0.256
 Zhu+0.254
vacc+0.249
 Qin+0.241
Neg logit contributions
 commute-0.245
 commuting-0.204
 notation-0.198
 flakes-0.191
 aeros-0.190
Token-
Token ID12
Feature activation+1.27e+00

Pos logit contributions
Sov+0.551
+0.504
 Zhu+0.495
vacc+0.489
 Qin+0.464
Neg logit contributions
 commute-0.714
 commuting-0.614
 notation-0.597
 flakes-0.581
 aeros-0.581
Tokena
Token ID64
Feature activation+2.91e-01

Pos logit contributions
Sov+0.916
+0.843
vacc+0.829
 Zhu+0.829
 Qin+0.781
Neg logit contributions
 commute-1.073
 commuting-0.916
 notation-0.886
 flakes-0.866
 aeros-0.865
Token...
Token ID986
Feature activation-2.57e+00

Pos logit contributions
Sov+0.228
+0.213
 Zhu+0.209
vacc+0.206
 Qin+0.198
Neg logit contributions
 commute-0.225
 commuting-0.190
 notation-0.184
 aeros-0.179
 flakes-0.178
Token<|endoftext|>
Token ID50256
Feature activation-8.93e-02

Pos logit contributions
 commute+1.761
 commuting+1.451
 notation+1.405
 flakes+1.345
 aeros+1.338
Neg logit contributions
Sov-2.271
-2.113
 Zhu-2.100
vacc-2.072
 Qin-2.001
TokenBuy
Token ID14518
Feature activation-8.48e-01

Pos logit contributions
 commute+0.078
 commuting+0.067
 notation+0.066
 flakes+0.064
 aeros+0.064
Neg logit contributions
Sov-0.062
-0.056
 Zhu-0.056
vacc-0.055
 Qin-0.052
Token Photo
Token ID5555
Feature activation+1.19e+00

Pos logit contributions
 commute+0.630
 commuting+0.528
 notation+0.512
 flakes+0.493
 aeros+0.491
Neg logit contributions
Sov-0.699
-0.645
 Zhu-0.640
vacc-0.632
 Qin-0.608
Token F
Token ID376
Feature activation-5.08e-02

Pos logit contributions
Sov+0.917
+0.859
 Zhu+0.857
vacc+0.829
 Qin+0.811
Neg logit contributions
 commute-0.934
 commuting-0.792
 notation-0.770
 flakes-0.740
 aeros-0.739
TokenSU
Token ID12564
Feature activation+1.95e+00

Pos logit contributions
 commute+0.040
 commuting+0.034
 notation+0.033
 flakes+0.032
 aeros+0.032
Neg logit contributions
Sov-0.040
-0.037
 Zhu-0.036
vacc-0.036
 Qin-0.034
Token this
Token ID428
Feature activation+1.83e-01

Pos logit contributions
Sov+0.078
+0.071
 Zhu+0.071
vacc+0.070
 Qin+0.067
Neg logit contributions
 commute-0.086
 commuting-0.073
 notation-0.071
 flakes-0.069
 aeros-0.069
Token visualization
Token ID32704
Feature activation-1.09e-01

Pos logit contributions
Sov+0.142
+0.132
 Zhu+0.131
vacc+0.129
 Qin+0.124
Neg logit contributions
 commute-0.144
 commuting-0.122
 notation-0.119
 flakes-0.115
 aeros-0.114
Token,
Token ID11
Feature activation-1.16e+00

Pos logit contributions
 commute+0.078
 commuting+0.065
 notation+0.063
 flakes+0.061
 aeros+0.061
Neg logit contributions
Sov-0.092
-0.086
 Zhu-0.085
vacc-0.084
 Qin-0.081
Token you
Token ID345
Feature activation-5.59e-01

Pos logit contributions
 commute+0.942
 commuting+0.802
 notation+0.781
 flakes+0.754
 aeros+0.751
Neg logit contributions
Sov-0.873
-0.802
 Zhu-0.796
vacc-0.783
 Qin-0.752
Token can
Token ID460
Feature activation-1.16e+00

Pos logit contributions
 commute+0.387
 commuting+0.321
 notation+0.311
 flakes+0.298
 aeros+0.296
Neg logit contributions
Sov-0.486
-0.453
 Zhu-0.450
vacc-0.444
 Qin-0.428
Token find
Token ID1064
Feature activation-2.54e+00

Pos logit contributions
 commute+0.797
 commuting+0.662
 notation+0.639
 flakes+0.615
 aeros+0.611
Neg logit contributions
Sov-1.003
-0.938
 Zhu-0.929
vacc-0.917
 Qin-0.886
Token a
Token ID257
Feature activation-2.00e+00

Pos logit contributions
 commute+2.044
 commuting+1.738
 notation+1.696
 flakes+1.629
 aeros+1.622
Neg logit contributions
Sov-1.955
-1.777
 Zhu-1.765
vacc-1.749
 Qin-1.666
Token static
Token ID9037
Feature activation-2.11e-02

Pos logit contributions
 commute+1.598
 commuting+1.354
 notation+1.323
 flakes+1.267
 aeros+1.265
Neg logit contributions
Sov-1.545
-1.412
 Zhu-1.404
vacc-1.384
 Qin-1.327
Token version
Token ID2196
Feature activation-1.04e+00

Pos logit contributions
 commute+0.017
 commuting+0.014
 notation+0.014
 flakes+0.013
 aeros+0.013
Neg logit contributions
Sov-0.016
-0.015
 Zhu-0.015
vacc-0.015
 Qin-0.014
Token of
Token ID286
Feature activation+3.61e-01

Pos logit contributions
 commute+0.843
 commuting+0.718
 notation+0.700
 flakes+0.675
 aeros+0.673
Neg logit contributions
Sov-0.780
-0.712
 Zhu-0.709
vacc-0.698
 Qin-0.669
Token it
Token ID340
Feature activation-8.79e-01

Pos logit contributions
Sov+0.266
+0.245
 Zhu+0.243
vacc+0.238
 Qin+0.229
Neg logit contributions
 commute-0.298
 commuting-0.254
 notation-0.248
 flakes-0.240
 aeros-0.239
Token make
Token ID787
Feature activation+7.28e-01

Pos logit contributions
Sov+0.712
+0.664
 Zhu+0.660
vacc+0.648
 Qin+0.628
Neg logit contributions
 commute-0.581
 commuting-0.483
 notation-0.467
 flakes-0.449
 aeros-0.446
Token sure
Token ID1654
Feature activation-9.30e-01

Pos logit contributions
Sov+0.578
+0.538
 Zhu+0.534
vacc+0.521
 Qin+0.507
Neg logit contributions
 commute-0.559
 commuting-0.470
 notation-0.457
 flakes-0.442
 aeros-0.440
Token he
Token ID339
Feature activation+5.53e-01

Pos logit contributions
 commute+0.744
 commuting+0.632
 notation+0.615
 flakes+0.594
 aeros+0.592
Neg logit contributions
Sov-0.713
-0.652
 Zhu-0.647
vacc-0.641
 Qin-0.611
Token knew
Token ID2993
Feature activation+1.33e+00

Pos logit contributions
Sov+0.446
+0.417
 Zhu+0.410
vacc+0.404
 Qin+0.389
Neg logit contributions
 commute-0.418
 commuting-0.352
 notation-0.341
 flakes-0.328
 aeros-0.327
Token the
Token ID262
Feature activation-2.63e-01

Pos logit contributions
Sov+1.006
+0.935
 Zhu+0.929
vacc+0.903
 Qin+0.877
Neg logit contributions
 commute-1.075
 commuting-0.913
 notation-0.886
 flakes-0.857
 aeros-0.854
Token rules
Token ID3173
Feature activation-3.18e+00

Pos logit contributions
 commute+0.197
 commuting+0.166
 notation+0.160
 flakes+0.155
 aeros+0.154
Neg logit contributions
Sov-0.214
-0.199
 Zhu-0.198
vacc-0.193
 Qin-0.187
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
 commute+2.394
 commuting+2.012
 notation+1.970
 flakes+1.882
 aeros+1.869
Neg logit contributions
Sov-2.581
 Zhu-2.354
-2.342
vacc-2.331
��-2.225
Token He
Token ID679
Feature activation+8.97e-02

Pos logit contributions
 commute+0.121
 commuting+0.103
 notation+0.101
 flakes+0.097
 aeros+0.097
Neg logit contributions
Sov-0.112
-0.103
 Zhu-0.102
vacc-0.101
 Qin-0.096
Token hadn
Token ID8020
Feature activation+1.01e+00

Pos logit contributions
Sov+0.071
+0.066
 Zhu+0.065
vacc+0.064
 Qin+0.062
Neg logit contributions
 commute-0.069
 commuting-0.058
 notation-0.057
 flakes-0.055
 aeros-0.054
Token
Token ID447
Feature activation+3.24e-01

Pos logit contributions
Sov+0.746
+0.682
 Zhu+0.678
vacc+0.667
 Qin+0.639
Neg logit contributions
 commute-0.839
 commuting-0.717
 notation-0.699
 flakes-0.675
 aeros-0.673
Token
Token ID247
Feature activation+3.70e-02

Pos logit contributions
Sov+0.181
 Zhu+0.158
+0.156
vacc+0.154
 Qin+0.145
Neg logit contributions
 commute-0.327
 commuting-0.287
 notation-0.283
 flakes-0.276
 aeros-0.273