TOP ACTIVATIONS
MAX = 1.032

v 2 . im read ( image Path ) image =
2 . M OR PH _ RECT , ( 21 ,
has been the greatest honor of my life , and I
, detected as EL F _ UM RE ON . B
whereabouts unknown ) TIM EL INE : 04 30 z
2 . [ color = red ][ b ] U f
. Heat about an inch of oil in a skillet over
v 2 . im read ( image Path ) image =
34 lb .- ft . of torque . The
s Format . Al ignment = [ system . draw ing
. 5 - liter Eco Boost proved its met tle off
Element ( cv 2 . M OR PH _ RECT ,
) = '. cl js ' OR RIGHT ( path ,
- to - female ( M TF ) transgender people are
102 ] For the 2014 15 Atlantic Coast Conference men
YR DS cent ering The Garg ant ua is
Mysteries , comic book short stories , prose , and non
with bad manners . - January 4 , 2010 User reviews
' " I 'll Feel a Whole Lot Better " (
the Democratic National Committee leak R obby M ook

MIN ACTIVATIONS
MIN = -0.960

this webpage , in whole or in part , is strictly
any antenna , both external and internal , and note if
el , and Schiff man , Outside the Bible , 3
Hall ion , Richard P . Design ers and Test
webpage , in whole or in part , is strictly prohibited
Follow Justin on Twitter <|endoftext|> by Julia Py per
Frank iv sk . <|endoftext|> [ Ex clusive ] Best Buy
and metal , sing ly or in combination , every Monday
? and how does it look from
the flow of on coming cars and pedestrians to make a
( i . e . is the syntax just
to behave properly . <|endoftext|> by Erik Alt ieri , NOR
by | in | in babys itting
` represent able :( I
o ko Kal an ial i il
d up , aren 't you ? Let 's try some
YouTube screen grab ] <|endoftext|> ( Updated below )
333 68 46 . <|endoftext|> ( FIL ES ) US Treasury
hard work , leadership and ( are ) great characters ,"
type ) @ 144 Hz ( OD = Normal ) The

INTERVAL 0.534 - 1.032
CONTAINS 0.124%

the subjects featured in the images intended them to remain private
had not been captured but rather walked away from his unit
be ek . <|endoftext|> Share . We found a home for
] :: From Ar gb ($ FC 1 [ 0 ],
the CG PR OG RAM / END CG section ! ):

INTERVAL 0.036 - 0.534
CONTAINS 40.434%

," he said . " We 're a little
, an anti - fascist activist , was released after three
stop Laura from overwhelming them quickly . Laura is
, young human , motor ized wheelchair ( Figure 2 A
book sales , rental , or lending records .

INTERVAL -0.462 - 0.036
CONTAINS 59.072%

to federal public lands , and then figure out how to
foundation of everything and Vietnamese people work hard I
for women that would basically consist of a piece of metal
i M ok up uni ma
gave T read well an immediate advantage over smaller corner backs

INTERVAL -0.960 - -0.462
CONTAINS 0.369%

> li > ul > body >
case , since I mm ap the file , this code
FG <|endoftext|> By Andrew Benson Veter an Nick He
a fore closed home May 7 , 2009 in Antioch ,
you can . It all kind of depends on how you
Tokenv
Token ID85
Feature activation+1.78e-01

Pos logit contributions
phe+2.698
ū+2.590
aug+2.555
Ur+2.540
kus+2.399
Neg logit contributions
 Howell-4.539
 Birch-4.016
 Clarkson-4.012
 JJ-3.871
 Hendricks-3.714
Token2
Token ID17
Feature activation+2.36e-01

Pos logit contributions
phe+1.127
ū+1.080
aug+1.060
Ur+1.056
kus+1.002
Neg logit contributions
 Howell-1.810
 Birch-1.601
 Clarkson-1.596
 JJ-1.543
 Hendricks-1.476
Token.
Token ID13
Feature activation+5.51e-01

Pos logit contributions
phe+1.668
ū+1.609
aug+1.587
Ur+1.586
UG+1.506
Neg logit contributions
 Howell-2.218
 Birch-1.939
 Clarkson-1.934
 JJ-1.861
 Hendricks-1.774
Tokenim
Token ID320
Feature activation+8.52e-02

Pos logit contributions
phe+4.313
Ur+4.268
ū+4.246
aug+4.213
kus+4.028
Neg logit contributions
 Howell-4.658
 Clarkson-4.104
 Birch-4.020
 JJ-3.807
 Hendricks-3.674
Tokenread
Token ID961
Feature activation+1.07e-01

Pos logit contributions
phe+0.654
ū+0.632
aug+0.622
Ur+0.622
kus+0.595
Neg logit contributions
 Howell-0.751
 Birch-0.650
 Clarkson-0.649
 JJ-0.623
 Hendricks-0.591
Token(
Token ID7
Feature activation+1.03e+00

Pos logit contributions
phe+0.851
ū+0.823
aug+0.810
Ur+0.808
kus+0.776
Neg logit contributions
 Howell-0.908
 Birch-0.783
 Clarkson-0.781
 JJ-0.749
 Hendricks-0.708
Tokenimage
Token ID9060
Feature activation+2.54e-01

Pos logit contributions
aug+4.220
phe+4.178
ū+4.091
Ur+3.811
kus+3.639
Neg logit contributions
 Howell-12.474
 Clarkson-11.484
 Birch-11.351
 JJ-10.868
 Hendricks-10.685
TokenPath
Token ID15235
Feature activation+3.70e-01

Pos logit contributions
phe+1.477
ū+1.410
Ur+1.384
aug+1.383
kus+1.299
Neg logit contributions
 Howell-2.712
 Birch-2.412
 Clarkson-2.407
 JJ-2.330
 Hendricks-2.235
Token)
Token ID8
Feature activation+2.99e-01

Pos logit contributions
phe+2.546
ū+2.455
Ur+2.431
aug+2.426
UG+2.305
Neg logit contributions
 Howell-3.534
 Birch-3.094
 Clarkson-3.091
 JJ-2.971
 Hendricks-2.837
Token image
Token ID2939
Feature activation+2.52e-02

Pos logit contributions
phe+1.812
ū+1.766
aug+1.743
Ur+1.733
UG+1.634
Neg logit contributions
 Howell-3.065
 Clarkson-2.730
 Birch-2.710
 JJ-2.610
 Hendricks-2.524
Token =
Token ID796
Feature activation+2.02e-01

Pos logit contributions
phe+0.268
ū+0.261
aug+0.258
Ur+0.255
kus+0.250
Neg logit contributions
 Howell-0.148
 Birch-0.118
 Clarkson-0.117
 JJ-0.110
 Hendricks-0.101
Token2
Token ID17
Feature activation+1.22e-01

Pos logit contributions
 Howell+1.940
 Birch+1.705
 Clarkson+1.696
 JJ+1.645
 Dalton+1.558
Neg logit contributions
phe-1.470
ū-1.416
aug-1.374
anamo-1.350
Ur-1.348
Token.
Token ID13
Feature activation+6.57e-01

Pos logit contributions
phe+0.897
ū+0.864
aug+0.848
Ur+0.846
kus+0.811
Neg logit contributions
 Howell-1.111
 Birch-0.969
 Clarkson-0.966
 JJ-0.930
 Hendricks-0.884
TokenM
Token ID44
Feature activation+6.72e-01

Pos logit contributions
phe+3.597
Ur+3.528
UG+3.455
aug+3.401
ū+3.389
Neg logit contributions
 Howell-6.965
 Clarkson-6.203
 Birch-6.078
 JJ-5.861
 Hendricks-5.715
TokenOR
Token ID1581
Feature activation+4.79e-02

Pos logit contributions
phe+2.510
Ur+2.446
ū+2.391
UG+2.385
aug+2.298
Neg logit contributions
 Howell-8.414
 Birch-7.589
 Clarkson-7.537
 JJ-7.342
 Hendricks-7.178
TokenPH
Token ID11909
Feature activation+1.24e-01

Pos logit contributions
phe+0.290
ū+0.282
aug+0.276
Ur+0.274
kus+0.262
Neg logit contributions
 Howell-0.495
 Birch-0.440
 Clarkson-0.439
 JJ-0.424
 Hendricks-0.408
Token_
Token ID62
Feature activation+9.12e-01

Pos logit contributions
phe+0.873
ū+0.838
aug+0.825
Ur+0.820
kus+0.784
Neg logit contributions
 Howell-1.176
 Birch-1.030
 Clarkson-1.028
 JJ-0.992
 Hendricks-0.944
TokenRECT
Token ID23988
Feature activation+6.29e-02

Pos logit contributions
UG+4.682
phe+4.606
ū+4.548
Ur+4.529
aug+4.401
Neg logit contributions
 Howell-9.906
 Birch-8.700
 Clarkson-8.600
 JJ-8.382
 Gad-8.185
Token,
Token ID11
Feature activation+3.91e-01

Pos logit contributions
phe+0.443
ū+0.423
Ur+0.418
aug+0.414
UG+0.406
Neg logit contributions
 Howell-0.599
 Birch-0.525
 Clarkson-0.523
 JJ-0.500
 Hendricks-0.481
Token (
Token ID357
Feature activation-7.14e-02

Pos logit contributions
phe+2.699
ū+2.581
Ur+2.544
aug+2.533
UG+2.405
Neg logit contributions
 Howell-3.686
 Clarkson-3.199
 Birch-3.149
 JJ-3.026
 Hendricks-2.954
Token21
Token ID2481
Feature activation+5.11e-02

Pos logit contributions
 Howell+0.707
 Birch+0.622
 Clarkson+0.620
 JJ+0.598
 Hendricks+0.572
Neg logit contributions
phe-0.474
ū-0.455
aug-0.448
Ur-0.447
kus-0.424
Token,
Token ID11
Feature activation+2.26e-01

Pos logit contributions
phe+0.367
ū+0.354
aug+0.348
Ur+0.347
UG+0.333
Neg logit contributions
 Howell-0.479
 Clarkson-0.417
 Birch-0.417
 JJ-0.399
 Hendricks-0.381
Token has
Token ID468
Feature activation+1.30e-01

Pos logit contributions
 Howell+1.123
 Birch+0.967
 Clarkson+0.963
 JJ+0.923
 Hendricks+0.874
Neg logit contributions
phe-1.060
ū-1.027
aug-1.013
Ur-1.009
kus-0.966
Token been
Token ID587
Feature activation+2.21e-01

Pos logit contributions
phe+0.896
ū+0.879
aug+0.864
Ur+0.860
UG+0.817
Neg logit contributions
 Howell-1.226
 Birch-1.080
 Clarkson-1.066
 JJ-1.026
 Hendricks-0.983
Token the
Token ID262
Feature activation+3.51e-01

Pos logit contributions
phe+1.477
ū+1.441
aug+1.425
Ur+1.410
UG+1.346
Neg logit contributions
 Howell-2.134
 Clarkson-1.872
 Birch-1.872
 JJ-1.795
 Hendricks-1.718
Token greatest
Token ID6000
Feature activation+1.13e-01

Pos logit contributions
phe+2.459
ū+2.458
aug+2.398
Ur+2.348
kus+2.252
Neg logit contributions
 Howell-3.269
 Birch-2.805
 Clarkson-2.797
 JJ-2.701
 Hendricks-2.560
Token honor
Token ID7522
Feature activation+4.08e-01

Pos logit contributions
phe+0.756
ū+0.735
aug+0.724
Ur+0.716
UG+0.681
Neg logit contributions
 Howell-1.092
 Birch-0.963
 Clarkson-0.948
 JJ-0.919
 Hendricks-0.874
Token of
Token ID286
Feature activation+9.00e-01

Pos logit contributions
phe+2.786
ū+2.707
aug+2.643
Ur+2.600
UG+2.502
Neg logit contributions
 Howell-3.855
 Birch-3.401
 Clarkson-3.363
 JJ-3.267
 Hendricks-3.114
Token my
Token ID616
Feature activation+6.20e-01

Pos logit contributions
phe+5.393
aug+5.299
ū+5.249
Ur+5.122
+4.902
Neg logit contributions
 Howell-8.631
 Birch-7.607
 Clarkson-7.550
 JJ-7.280
 Hendricks-6.918
Token life
Token ID1204
Feature activation+5.23e-01

Pos logit contributions
phe+3.691
ū+3.609
aug+3.576
Ur+3.486
ogo+3.311
Neg logit contributions
 Howell-6.315
 Birch-5.583
 Clarkson-5.565
 JJ-5.403
 Hendricks-5.159
Token,
Token ID11
Feature activation+2.68e-01

Pos logit contributions
phe+3.224
ū+3.145
aug+3.059
Ur+3.001
ura+2.867
Neg logit contributions
 Howell-5.252
 Birch-4.647
 Clarkson-4.571
 JJ-4.427
 Hendricks-4.225
Token and
Token ID290
Feature activation+1.97e-01

Pos logit contributions
phe+2.012
ū+1.947
aug+1.940
Ur+1.917
UG+1.827
Neg logit contributions
 Howell-2.369
 Birch-2.052
 Clarkson-2.040
 JJ-1.959
 Hendricks-1.858
Token I
Token ID314
Feature activation+1.98e-01

Pos logit contributions
phe+1.478
aug+1.431
ū+1.430
Ur+1.409
UG+1.344
Neg logit contributions
 Howell-1.742
 Birch-1.511
 Clarkson-1.500
 JJ-1.433
 Hendricks-1.368
Token,
Token ID11
Feature activation-2.21e-01

Pos logit contributions
 Howell+2.728
 Birch+2.370
 Clarkson+2.363
 JJ+2.271
 Hendricks+2.157
Neg logit contributions
phe-2.289
ū-2.210
aug-2.176
Ur-2.174
kus-2.077
Token detected
Token ID12326
Feature activation+2.75e-01

Pos logit contributions
 Howell+1.787
 Birch+1.528
 Clarkson+1.523
 JJ+1.454
 Hendricks+1.372
Neg logit contributions
phe-1.859
ū-1.802
aug-1.779
Ur-1.779
UG-1.706
Token as
Token ID355
Feature activation+4.11e-01

Pos logit contributions
phe+2.003
ū+1.948
Ur+1.920
aug+1.913
UG+1.837
Neg logit contributions
 Howell-2.493
 Birch-2.163
 Clarkson-2.161
 JJ-2.070
 Hendricks-1.971
Token EL
Token ID17852
Feature activation+2.42e-01

Pos logit contributions
phe+3.126
ū+3.037
aug+3.021
Ur+3.011
UG+2.938
Neg logit contributions
 Howell-3.512
 Clarkson-2.984
 Birch-2.980
 JJ-2.788
 Hendricks-2.710
TokenF
Token ID37
Feature activation+3.34e-01

Pos logit contributions
phe+1.387
ū+1.315
Ur+1.306
aug+1.295
UG+1.239
Neg logit contributions
 Howell-2.605
 Birch-2.312
 Clarkson-2.310
 JJ-2.230
 Hendricks-2.139
Token_
Token ID62
Feature activation+8.62e-01

Pos logit contributions
phe+2.144
ū+2.072
Ur+2.052
aug+2.036
UG+1.977
Neg logit contributions
 Howell-3.345
 Birch-2.938
 Clarkson-2.925
 JJ-2.822
 Hendricks-2.703
TokenUM
Token ID5883
Feature activation+5.90e-02

Pos logit contributions
phe+4.567
Ur+4.476
UG+4.474
ū+4.413
aug+4.327
Neg logit contributions
 Howell-9.367
 Birch-8.303
 Clarkson-8.206
 JJ-7.971
 Hendricks-7.642
TokenRE
Token ID2200
Feature activation+7.51e-02

Pos logit contributions
phe+0.290
Ur+0.277
ū+0.275
aug+0.269
UG+0.260
Neg logit contributions
 Howell-0.684
 Birch-0.615
 Clarkson-0.610
 JJ-0.592
 Hendricks-0.569
TokenON
Token ID1340
Feature activation-2.60e-01

Pos logit contributions
phe+0.398
ū+0.380
Ur+0.374
aug+0.371
UG+0.357
Neg logit contributions
 Howell-0.843
 Birch-0.754
 Clarkson-0.748
 JJ-0.728
 Hendricks-0.698
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
 Howell+2.438
 Birch+2.131
 Clarkson+2.125
 JJ+2.047
 Hendricks+1.950
Neg logit contributions
phe-1.846
ū-1.779
aug-1.751
Ur-1.749
kus-1.666
TokenB
Token ID33
Feature activation+1.83e-01

Pos logit contributions
phe+1.979
Ur+1.892
ū+1.885
aug+1.864
UG+1.836
Neg logit contributions
 Howell-3.806
 Birch-3.377
 Clarkson-3.358
 JJ-3.228
 Hendricks-3.108
Token
Token ID784
Feature activation+4.37e-02

Pos logit contributions
phe+0.305
ū+0.295
Ur+0.289
aug+0.287
UG+0.276
Neg logit contributions
 Howell-0.372
 Birch-0.322
 Clarkson-0.322
 JJ-0.309
 Hendricks-0.294
Token whereabouts
Token ID33035
Feature activation-7.97e-02

Pos logit contributions
phe+0.335
ū+0.326
aug+0.321
Ur+0.320
kus+0.306
Neg logit contributions
 Howell-0.381
 Birch-0.330
 Clarkson-0.329
 JJ-0.315
 Hendricks-0.300
Token unknown
Token ID6439
Feature activation+1.49e-01

Pos logit contributions
 Howell+0.733
 Birch+0.640
 Clarkson+0.638
 JJ+0.613
 Hendricks+0.584
Neg logit contributions
phe-0.581
ū-0.561
Ur-0.552
aug-0.551
kus-0.525
Token)
Token ID8
Feature activation+3.13e-01

Pos logit contributions
phe+1.070
ū+1.042
Ur+1.019
aug+1.012
UG+0.973
Neg logit contributions
 Howell-1.378
 Birch-1.202
 Clarkson-1.196
 JJ-1.144
 Hendricks-1.100
Token TIM
Token ID31742
Feature activation+2.36e-01

Pos logit contributions
phe+2.234
ū+2.191
Ur+2.166
aug+2.139
UG+2.077
Neg logit contributions
 Howell-2.825
 Birch-2.467
 Clarkson-2.464
 JJ-2.325
 Hendricks-2.260
TokenEL
Token ID3698
Feature activation+8.32e-01

Pos logit contributions
phe+1.547
Ur+1.510
ū+1.503
aug+1.462
UG+1.445
Neg logit contributions
 Howell-2.272
 Birch-2.008
 Clarkson-1.993
 JJ-1.915
 Hendricks-1.846
TokenINE
Token ID8881
Feature activation+5.25e-02

Pos logit contributions
UG+3.550
phe+3.473
Ur+3.342
ū+3.321
+3.238
Neg logit contributions
 Howell-9.672
 Birch-8.704
 Clarkson-8.616
 JJ-8.218
 Hendricks-8.161
Token:
Token ID25
Feature activation+1.30e-01

Pos logit contributions
phe+0.377
ū+0.367
aug+0.361
Ur+0.361
UG+0.346
Neg logit contributions
 Howell-0.484
 Birch-0.422
 Clarkson-0.421
 JJ-0.404
 Hendricks-0.386
Token 04
Token ID8702
Feature activation+2.33e-01

Pos logit contributions
phe+0.970
ū+0.945
aug+0.932
Ur+0.928
UG+0.889
Neg logit contributions
 Howell-1.162
 Birch-1.010
 Clarkson-1.006
 JJ-0.967
 Hendricks-0.918
Token30
Token ID1270
Feature activation+9.72e-02

Pos logit contributions
phe+1.500
ū+1.469
aug+1.453
Ur+1.451
UG+1.390
Neg logit contributions
 Howell-2.295
 Birch-2.020
 Clarkson-2.016
 JJ-1.942
 Hendricks-1.866
Tokenz
Token ID89
Feature activation-2.04e-01

Pos logit contributions
phe+0.688
ū+0.670
aug+0.660
Ur+0.659
UG+0.631
Neg logit contributions
 Howell-0.906
 Birch-0.793
 Clarkson-0.791
 JJ-0.758
 Hendricks-0.725
Token 2
Token ID362
Feature activation+1.44e-01

Pos logit contributions
phe+1.785
Ur+1.733
ū+1.711
aug+1.709
UG+1.637
Neg logit contributions
 Howell-2.639
 Birch-2.316
 Clarkson-2.299
 JJ-2.197
 Hendricks-2.141
Token.
Token ID13
Feature activation+3.23e-01

Pos logit contributions
phe+1.025
ū+0.989
aug+0.974
Ur+0.972
kus+0.925
Neg logit contributions
 Howell-1.346
 Birch-1.176
 Clarkson-1.172
 JJ-1.128
 Hendricks-1.076
Token [
Token ID685
Feature activation+6.91e-02

Pos logit contributions
phe+1.786
ū+1.693
Ur+1.684
aug+1.671
UG+1.562
Neg logit contributions
 Howell-3.476
 Birch-3.089
 Clarkson-3.085
 JJ-2.950
 Hendricks-2.879
Tokencolor
Token ID8043
Feature activation+5.04e-01

Pos logit contributions
phe+0.316
ū+0.296
aug+0.290
Ur+0.290
UG+0.266
Neg logit contributions
 Howell-0.831
 Clarkson-0.747
 Birch-0.745
 JJ-0.727
 Hendricks-0.703
Token=
Token ID28
Feature activation+2.32e-01

Pos logit contributions
phe+4.031
ū+3.915
Ur+3.880
aug+3.851
UG+3.690
Neg logit contributions
 Howell-4.249
 Birch-3.645
 Clarkson-3.626
 JJ-3.457
 Hendricks-3.297
Tokenred
Token ID445
Feature activation+8.30e-01

Pos logit contributions
phe+1.517
ū+1.440
aug+1.437
Ur+1.423
kus+1.349
Neg logit contributions
 Howell-2.323
 Clarkson-2.045
 Birch-2.043
 JJ-1.970
 Hendricks-1.892
Token][
Token ID7131
Feature activation+4.45e-01

Pos logit contributions
phe+1.824
ū+1.596
aug+1.508
]]+1.480
Ur+1.449
Neg logit contributions
 Howell-11.418
 Clarkson-10.344
 Birch-10.329
 JJ-10.101
 Hendricks-9.889
Tokenb
Token ID65
Feature activation+3.29e-01

Pos logit contributions
phe+2.603
aug+2.453
ū+2.442
Ur+2.421
ura+2.280
Neg logit contributions
 Howell-4.732
 Clarkson-4.157
 Birch-4.157
 JJ-4.050
 Hendricks-3.914
Token]
Token ID60
Feature activation+7.72e-02

Pos logit contributions
phe+1.182
ū+1.099
aug+1.065
Ur+1.062
kus+0.953
Neg logit contributions
 Howell-4.234
 Birch-3.848
 Clarkson-3.839
 JJ-3.739
 Hendricks-3.617
TokenU
Token ID52
Feature activation+8.62e-02

Pos logit contributions
phe+0.448
Ur+0.427
ū+0.424
aug+0.419
UG+0.397
Neg logit contributions
 Howell-0.831
 Birch-0.738
 Clarkson-0.736
 JJ-0.709
 Hendricks-0.683
Tokenf
Token ID69
Feature activation+3.29e-01

Pos logit contributions
phe+0.553
ū+0.531
Ur+0.522
aug+0.520
UG+0.500
Neg logit contributions
 Howell-0.869
 Birch-0.769
 Clarkson-0.769
 JJ-0.739
 Hendricks-0.708
Token.
Token ID13
Feature activation-2.59e-02

Pos logit contributions
phe+1.292
ū+1.245
aug+1.224
Ur+1.223
kus+1.167
Neg logit contributions
 Howell-1.658
 Birch-1.448
 Clarkson-1.444
 JJ-1.390
 Hendricks-1.323
Token Heat
Token ID12308
Feature activation+3.65e-01

Pos logit contributions
 Howell+0.130
 Clarkson+0.100
 Birch+0.099
 JJ+0.093
 Hendricks+0.080
Neg logit contributions
phe-0.292
ū-0.287
aug-0.286
Ur-0.286
UG-0.275
Token about
Token ID546
Feature activation+3.09e-01

Pos logit contributions
phe+3.161
ū+3.095
aug+3.062
Ur+3.033
kus+2.937
Neg logit contributions
 Howell-2.808
 Clarkson-2.380
 Birch-2.378
 JJ-2.244
 Hendricks-2.133
Token an
Token ID281
Feature activation+3.00e-01

Pos logit contributions
phe+2.164
ū+2.105
aug+2.079
Ur+2.072
kus+1.966
Neg logit contributions
 Howell-2.893
 Birch-2.532
 Clarkson-2.512
 JJ-2.399
 Hendricks-2.292
Token inch
Token ID11111
Feature activation+3.27e-01

Pos logit contributions
phe+1.981
ū+1.919
aug+1.889
Ur+1.885
UG+1.779
Neg logit contributions
 Howell-2.908
 Clarkson-2.575
 Birch-2.563
 JJ-2.455
 Hendricks-2.338
Token of
Token ID286
Feature activation+8.16e-01

Pos logit contributions
phe+2.433
ū+2.352
Ur+2.320
aug+2.314
UG+2.210
Neg logit contributions
 Howell-2.943
 Birch-2.558
 Clarkson-2.547
 JJ-2.444
 Hendricks-2.326
Token oil
Token ID3056
Feature activation+1.34e-01

Pos logit contributions
phe+4.434
ū+4.298
aug+4.252
Ur+4.191
+4.051
Neg logit contributions
 Howell-8.396
 Birch-7.434
 Clarkson-7.356
 JJ-7.032
 Hendricks-6.811
Token in
Token ID287
Feature activation+6.13e-01

Pos logit contributions
phe+1.067
ū+1.032
aug+1.017
Ur+1.016
kus+0.973
Neg logit contributions
 Howell-1.148
 Birch-0.990
 Clarkson-0.987
 JJ-0.946
 Hendricks-0.896
Token a
Token ID257
Feature activation+7.19e-01

Pos logit contributions
phe+3.709
aug+3.559
ū+3.546
Ur+3.494
kus+3.335
Neg logit contributions
 Howell-6.202
 Birch-5.475
 Clarkson-5.435
 JJ-5.220
 Hendricks-4.979
Token skillet
Token ID41306
Feature activation+2.23e-01

Pos logit contributions
phe+4.079
ū+3.879
Ur+3.855
aug+3.841
kus+3.695
Neg logit contributions
 Howell-7.424
 Birch-6.672
 Clarkson-6.548
 JJ-6.373
 Davies-6.068
Token over
Token ID625
Feature activation+6.89e-01

Pos logit contributions
phe+1.722
ū+1.663
aug+1.639
Ur+1.630
kus+1.558
Neg logit contributions
 Howell-1.957
 Birch-1.696
 Clarkson-1.686
 JJ-1.618
 Hendricks-1.524
Tokenv
Token ID85
Feature activation+1.09e-02

Pos logit contributions
phe+0.921
ū+0.885
aug+0.870
Ur+0.866
kus+0.819
Neg logit contributions
 Howell-1.522
 Clarkson-1.350
 Birch-1.348
 JJ-1.300
 Hendricks-1.248
Token2
Token ID17
Feature activation+2.56e-01

Pos logit contributions
phe+0.071
ū+0.068
aug+0.066
Ur+0.066
kus+0.063
Neg logit contributions
 Howell-0.108
 Birch-0.096
 Clarkson-0.095
 JJ-0.092
 Hendricks-0.088
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
phe+1.807
ū+1.745
aug+1.718
Ur+1.718
kus+1.633
Neg logit contributions
 Howell-2.404
 Birch-2.101
 Clarkson-2.099
 JJ-2.019
 Hendricks-1.923
Tokenim
Token ID320
Feature activation-3.04e-01

Pos logit contributions
phe+1.645
Ur+1.590
aug+1.570
ū+1.569
kus+1.501
Neg logit contributions
 Howell-2.481
 Clarkson-2.186
 Birch-2.184
 JJ-2.085
 Hendricks-2.009
Tokenread
Token ID961
Feature activation-2.10e-01

Pos logit contributions
 Howell+3.025
 Birch+2.662
 Clarkson+2.657
 JJ+2.568
 Hendricks+2.453
Neg logit contributions
phe-1.982
ū-1.904
aug-1.870
Ur-1.863
UG-1.765
Token(
Token ID7
Feature activation+8.01e-01

Pos logit contributions
 Howell+1.949
 Birch+1.703
 Clarkson+1.699
 JJ+1.633
 Hendricks+1.556
Neg logit contributions
phe-1.520
ū-1.466
aug-1.444
Ur-1.441
kus-1.376
Tokenimage
Token ID9060
Feature activation-4.39e-02

Pos logit contributions
phe+5.144
aug+4.879
ū+4.737
Ur+4.737
kus+4.594
Neg logit contributions
 Howell-7.899
 Clarkson-7.031
 Birch-6.803
 JJ-6.637
 Hendricks-6.370
TokenPath
Token ID15235
Feature activation+7.42e-02

Pos logit contributions
 Howell+0.472
 Clarkson+0.419
 Birch+0.418
 JJ+0.405
 Hendricks+0.388
Neg logit contributions
phe-0.254
ū-0.242
Ur-0.240
aug-0.237
kus-0.224
Token)
Token ID8
Feature activation+2.43e-01

Pos logit contributions
phe+0.510
ū+0.492
aug+0.485
Ur+0.485
kus+0.459
Neg logit contributions
 Howell-0.712
 Clarkson-0.628
 Birch-0.623
 JJ-0.598
 Hendricks-0.573
Token image
Token ID2939
Feature activation-2.03e-01

Pos logit contributions
phe+1.730
ū+1.679
aug+1.673
Ur+1.663
kus+1.587
Neg logit contributions
 Howell-2.225
 Clarkson-1.942
 Birch-1.928
 JJ-1.842
 Hendricks-1.777
Token =
Token ID796
Feature activation+3.30e-01

Pos logit contributions
 Howell+1.929
 Birch+1.691
 Clarkson+1.686
 JJ+1.624
 Hendricks+1.548
Neg logit contributions
phe-1.419
ū-1.367
aug-1.344
Ur-1.343
kus-1.278
Token34
Token ID2682
Feature activation-2.03e-01

Pos logit contributions
 Howell+1.562
 Birch+1.367
 Clarkson+1.363
 JJ+1.314
 Hendricks+1.252
Neg logit contributions
phe-1.165
ū-1.123
aug-1.104
Ur-1.102
kus-1.051
Token lb
Token ID18360
Feature activation+3.02e-01

Pos logit contributions
 Howell+1.951
 Birch+1.712
 Clarkson+1.708
 JJ+1.648
 Hendricks+1.571
Neg logit contributions
phe-1.402
ū-1.350
aug-1.329
Ur-1.326
kus-1.259
Token.-
Token ID7874
Feature activation+3.34e-01

Pos logit contributions
phe+2.036
ū+1.964
Ur+1.931
aug+1.921
kus+1.827
Neg logit contributions
 Howell-2.939
 Birch-2.582
 Clarkson-2.564
 JJ-2.471
 Hendricks-2.361
Tokenft
Token ID701
Feature activation+1.18e-01

Pos logit contributions
phe+2.009
ū+1.920
aug+1.899
Ur+1.892
kus+1.786
Neg logit contributions
 Howell-3.502
 Birch-3.121
 Clarkson-3.088
 JJ-2.983
 Hendricks-2.855
Token.
Token ID13
Feature activation+6.28e-01

Pos logit contributions
phe+0.809
ū+0.782
Ur+0.766
aug+0.765
kus+0.727
Neg logit contributions
 Howell-1.136
 Birch-0.998
 Clarkson-0.989
 JJ-0.955
 Hendricks-0.910
Token of
Token ID286
Feature activation+7.87e-01

Pos logit contributions
phe+4.176
ū+3.952
Ur+3.892
aug+3.862
UG+3.745
Neg logit contributions
 Howell-5.902
 Birch-5.178
 Clarkson-5.040
 JJ-4.875
 Hendricks-4.560
Token torque
Token ID26415
Feature activation+5.56e-01

Pos logit contributions
phe+3.195
ū+3.063
aug+3.012
Ur+2.979
ura+2.861
Neg logit contributions
 Howell-9.044
 Birch-8.095
 Clarkson-8.026
 JJ-7.746
 Gad-7.467
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
phe+3.469
ū+3.334
aug+3.207
Ur+3.198
UG+3.076
Neg logit contributions
 Howell-5.450
 Birch-4.840
 Clarkson-4.690
 JJ-4.622
 Hendricks-4.405
Token
Token ID198
Feature activation+1.10e-01

Pos logit contributions
phe+1.902
aug+1.823
Ur+1.822
ū+1.821
UG+1.735
Neg logit contributions
 Howell-2.384
 Birch-2.056
 Clarkson-2.023
 JJ-1.962
 Dalton-1.848
Token
Token ID198
Feature activation+1.55e-01

Pos logit contributions
phe+0.912
ū+0.883
aug+0.869
Ur+0.868
kus+0.835
Neg logit contributions
 Howell-0.910
 Birch-0.781
 Clarkson-0.779
 JJ-0.745
 Hendricks-0.704
TokenThe
Token ID464
Feature activation+2.26e-01

Pos logit contributions
phe+0.896
Ur+0.878
aug+0.861
ū+0.855
UG+0.821
Neg logit contributions
 Howell-1.661
 Birch-1.478
 Clarkson-1.458
 JJ-1.425
 Hendricks-1.354
Tokens
Token ID82
Feature activation-2.46e-01

Pos logit contributions
 Howell+1.410
 Birch+1.255
 Clarkson+1.252
 JJ+1.212
 Hendricks+1.162
Neg logit contributions
phe-0.774
ū-0.738
aug-0.726
Ur-0.724
kus-0.679
TokenFormat
Token ID26227
Feature activation-1.39e-01

Pos logit contributions
 Howell+2.045
 Clarkson+1.748
 Birch+1.748
 JJ+1.653
 Hendricks+1.597
Neg logit contributions
phe-1.967
ū-1.914
aug-1.865
anamo-1.833
kus-1.832
Token.
Token ID13
Feature activation+7.29e-02

Pos logit contributions
 Howell+1.215
 Birch+1.054
 Clarkson+1.050
 JJ+1.010
 Hendricks+0.956
Neg logit contributions
phe-1.073
ū-1.035
aug-1.010
Ur-0.994
kus-0.984
TokenAl
Token ID2348
Feature activation-1.33e-02

Pos logit contributions
phe+0.442
Ur+0.426
ū+0.422
aug+0.418
UG+0.393
Neg logit contributions
 Howell-0.762
 Birch-0.675
 Clarkson-0.675
 JJ-0.654
 Hendricks-0.626
Tokenignment
Token ID16747
Feature activation-4.61e-02

Pos logit contributions
 Howell+0.116
 Clarkson+0.101
 Birch+0.100
 JJ+0.096
 Hendricks+0.091
Neg logit contributions
phe-0.102
ū-0.099
Ur-0.098
aug-0.097
UG-0.093
Token =
Token ID796
Feature activation+7.83e-01

Pos logit contributions
 Howell+0.327
 Birch+0.275
 Clarkson+0.274
 JJ+0.259
 Hendricks+0.242
Neg logit contributions
phe-0.431
ū-0.418
Ur-0.418
aug-0.413
UG-0.400
Token [
Token ID685
Feature activation+4.26e-02

Pos logit contributions
phe+3.605
ū+3.305
Ur+3.281
aug+3.280
ura+3.054
Neg logit contributions
 Howell-8.510
 Clarkson-7.774
 Birch-7.607
 JJ-7.361
 Hendricks-7.170
Tokensystem
Token ID10057
Feature activation-1.43e-02

Pos logit contributions
phe+0.316
ū+0.304
aug+0.301
Ur+0.298
kus+0.285
Neg logit contributions
 Howell-0.388
 Clarkson-0.340
 Birch-0.338
 JJ-0.325
 Hendricks-0.308
Token.
Token ID13
Feature activation-6.53e-03

Pos logit contributions
 Howell+0.124
 Birch+0.108
 Clarkson+0.108
 JJ+0.104
 Hendricks+0.098
Neg logit contributions
phe-0.111
ū-0.107
aug-0.104
Ur-0.104
anamo-0.102
Tokendraw
Token ID19334
Feature activation-9.31e-02

Pos logit contributions
 Howell+0.062
 Birch+0.054
 Clarkson+0.054
 JJ+0.052
 Hendricks+0.050
Neg logit contributions
phe-0.046
ū-0.044
Ur-0.043
aug-0.043
kus-0.041
Tokening
Token ID278
Feature activation+1.72e-02

Pos logit contributions
 Howell+0.722
 Birch+0.618
 Clarkson+0.611
 JJ+0.588
 Dalton+0.546
Neg logit contributions
phe-0.801
ū-0.773
Ur-0.754
aug-0.748
anamo-0.743
Token.
Token ID13
Feature activation+2.10e-01

Pos logit contributions
phe+1.011
ū+0.973
aug+0.958
Ur+0.956
kus+0.913
Neg logit contributions
 Howell-1.279
 Birch-1.116
 Clarkson-1.113
 JJ-1.072
 Hendricks-1.020
Token5
Token ID20
Feature activation+1.45e-01

Pos logit contributions
phe+0.928
ū+0.874
aug+0.849
Ur+0.847
kus+0.782
Neg logit contributions
 Howell-2.528
 Birch-2.282
 Clarkson-2.278
 JJ-2.214
 Hendricks-2.135
Token-
Token ID12
Feature activation+1.21e-02

Pos logit contributions
phe+0.873
ū+0.843
Ur+0.831
aug+0.829
UG+0.780
Neg logit contributions
 Howell-1.497
 Birch-1.334
 Clarkson-1.321
 JJ-1.273
 Hendricks-1.223
Tokenliter
Token ID17201
Feature activation+5.47e-01

Pos logit contributions
phe+0.096
ū+0.093
aug+0.092
Ur+0.092
kus+0.088
Neg logit contributions
 Howell-0.104
 Birch-0.090
 Clarkson-0.090
 JJ-0.086
 Hendricks-0.081
Token Eco
Token ID38719
Feature activation+5.79e-01

Pos logit contributions
phe+2.957
aug+2.850
ū+2.831
Ur+2.803
UG+2.675
Neg logit contributions
 Howell-5.705
 Birch-5.077
 Clarkson-5.047
 JJ-4.844
 Hendricks-4.673
TokenBoost
Token ID45686
Feature activation+7.82e-01

Pos logit contributions
phe+1.728
Ur+1.596
ū+1.588
aug+1.586
UG+1.382
Neg logit contributions
 Howell-7.711
 Birch-7.015
 Clarkson-6.991
 JJ-6.834
 Hendricks-6.580
Token proved
Token ID8302
Feature activation-4.86e-02

Pos logit contributions
phe+4.735
ū+4.621
Ur+4.581
aug+4.559
ura+4.350
Neg logit contributions
 Howell-7.512
 Birch-6.709
 Clarkson-6.517
 JJ-6.242
 Hendricks-6.054
Token its
Token ID663
Feature activation+2.29e-01

Pos logit contributions
 Howell+0.423
 Birch+0.366
 Clarkson+0.361
 JJ+0.349
 Hendricks+0.329
Neg logit contributions
phe-0.375
ū-0.363
aug-0.359
Ur-0.359
kus-0.344
Token met
Token ID1138
Feature activation+4.68e-02

Pos logit contributions
phe+1.588
ū+1.551
Ur+1.541
aug+1.523
UG+1.444
Neg logit contributions
 Howell-2.154
 Birch-1.876
 Clarkson-1.861
 JJ-1.784
 Hendricks-1.697
Tokentle
Token ID7100
Feature activation+3.83e-01

Pos logit contributions
phe+0.213
ū+0.200
aug+0.197
Ur+0.194
kus+0.179
Neg logit contributions
 Howell-0.560
 Birch-0.503
 Clarkson-0.502
 JJ-0.488
 Hendricks-0.472
Token off
Token ID572
Feature activation-1.87e-01

Pos logit contributions
phe+2.689
ū+2.626
aug+2.607
Ur+2.579
UG+2.483
Neg logit contributions
 Howell-3.480
 Birch-3.049
 Clarkson-2.986
 JJ-2.895
 Hendricks-2.762
TokenElement
Token ID20180
Feature activation-2.31e-01

Pos logit contributions
 Howell+0.838
 Birch+0.706
 Clarkson+0.703
 JJ+0.666
 Hendricks+0.627
Neg logit contributions
phe-1.034
ū-1.008
aug-0.992
Ur-0.981
kus-0.960
Token(
Token ID7
Feature activation+3.47e-01

Pos logit contributions
 Howell+1.808
 Clarkson+1.547
 Birch+1.536
 JJ+1.473
 Hendricks+1.377
Neg logit contributions
phe-1.954
ū-1.910
aug-1.863
Ur-1.850
anamo-1.826
Tokencv
Token ID33967
Feature activation-7.38e-02

Pos logit contributions
phe+1.773
ū+1.675
aug+1.660
Ur+1.634
kus+1.538
Neg logit contributions
 Howell-3.958
 Clarkson-3.540
 Birch-3.540
 JJ-3.431
 Hendricks-3.312
Token2
Token ID17
Feature activation+3.56e-02

Pos logit contributions
 Howell+0.703
 Birch+0.620
 Clarkson+0.617
 JJ+0.599
 Hendricks+0.567
Neg logit contributions
phe-0.508
ū-0.488
aug-0.475
Ur-0.465
anamo-0.461
Token.
Token ID13
Feature activation+5.35e-01

Pos logit contributions
phe+0.266
ū+0.257
aug+0.251
Ur+0.250
kus+0.241
Neg logit contributions
 Howell-0.320
 Birch-0.279
 Clarkson-0.278
 JJ-0.268
 Hendricks-0.254
TokenM
Token ID44
Feature activation+7.78e-01

Pos logit contributions
phe+2.979
Ur+2.963
UG+2.854
aug+2.838
ū+2.802
Neg logit contributions
 Howell-5.692
 Clarkson-5.137
 Birch-5.050
 JJ-4.854
 Hendricks-4.658
TokenOR
Token ID1581
Feature activation+1.04e-01

Pos logit contributions
Ur+2.652
phe+2.622
UG+2.610
ū+2.523
aug+2.428
Neg logit contributions
 Howell-9.938
 Birch-8.979
 Clarkson-8.914
 JJ-8.627
 Hendricks-8.488
TokenPH
Token ID11909
Feature activation+8.69e-02

Pos logit contributions
phe+0.628
ū+0.608
aug+0.594
Ur+0.592
kus+0.563
Neg logit contributions
 Howell-1.081
 Birch-0.961
 Clarkson-0.958
 JJ-0.926
 Hendricks-0.891
Token_
Token ID62
Feature activation+6.74e-01

Pos logit contributions
phe+0.624
ū+0.598
aug+0.588
Ur+0.583
kus+0.561
Neg logit contributions
 Howell-0.810
 Birch-0.708
 Clarkson-0.707
 JJ-0.683
 Hendricks-0.649
TokenRECT
Token ID23988
Feature activation+1.38e-01

Pos logit contributions
phe+5.185
Ur+5.140
UG+5.125
ū+5.103
aug+5.038
Neg logit contributions
 Howell-5.744
 Birch-4.940
 Clarkson-4.915
 JJ-4.673
 Hendricks-4.451
Token,
Token ID11
Feature activation+4.05e-01

Pos logit contributions
phe+1.037
ū+1.002
aug+0.986
Ur+0.985
kus+0.941
Neg logit contributions
 Howell-1.233
 Birch-1.071
 Clarkson-1.068
 JJ-1.027
 Hendricks-0.975
Token )
Token ID1267
Feature activation+1.28e-01

Pos logit contributions
phe+0.391
ū+0.382
Ur+0.377
aug+0.374
UG+0.363
Neg logit contributions
 Howell-0.374
 Birch-0.319
 Clarkson-0.318
 JJ-0.303
 Hendricks-0.288
Token =
Token ID796
Feature activation+2.35e-01

Pos logit contributions
phe+1.226
ū+1.204
Ur+1.202
aug+1.178
UG+1.167
Neg logit contributions
 Howell-0.871
 Clarkson-0.724
 Birch-0.719
 JJ-0.671
 Hendricks-0.637
Token '.
Token ID45302
Feature activation-7.13e-02

Pos logit contributions
phe+1.683
ū+1.628
aug+1.615
Ur+1.602
UG+1.520
Neg logit contributions
 Howell-2.138
 Birch-1.839
 Clarkson-1.808
 JJ-1.770
 Hendricks-1.701
Tokencl
Token ID565
Feature activation-5.75e-01

Pos logit contributions
 Howell+0.696
 Birch+0.609
 Clarkson+0.606
 JJ+0.585
 Hendricks+0.559
Neg logit contributions
phe-0.486
ū-0.467
aug-0.463
Ur-0.457
kus-0.438
Tokenjs
Token ID8457
Feature activation+3.72e-01

Pos logit contributions
 Howell+5.162
 Clarkson+4.523
 Birch+4.501
 JJ+4.394
 Hendricks+4.137
Neg logit contributions
phe-4.144
ū-3.983
Ur-3.930
aug-3.898
UG-3.752
Token'
Token ID6
Feature activation+7.73e-01

Pos logit contributions
phe+1.825
ū+1.752
Ur+1.738
aug+1.703
UG+1.606
Neg logit contributions
 Howell-4.264
 Birch-3.824
 Clarkson-3.775
 JJ-3.670
 Hendricks-3.554
Token OR
Token ID6375
Feature activation+2.09e-01

Pos logit contributions
phe+4.913
Ur+4.880
ū+4.773
UG+4.700
]]+4.605
Neg logit contributions
 Howell-7.088
 Birch-6.105
 Clarkson-6.055
 Hendricks-5.722
 JJ-5.708
Token RIGHT
Token ID33621
Feature activation+2.40e-02

Pos logit contributions
phe+1.710
ū+1.674
Ur+1.648
aug+1.629
UG+1.601
Neg logit contributions
 Howell-1.675
 Birch-1.417
 Clarkson-1.393
 JJ-1.326
 Hendricks-1.291
Token (
Token ID357
Feature activation+3.22e-01

Pos logit contributions
phe+0.190
ū+0.183
aug+0.181
Ur+0.179
kus+0.173
Neg logit contributions
 Howell-0.207
 Birch-0.179
 Clarkson-0.179
 JJ-0.172
 Hendricks-0.162
Token path
Token ID3108
Feature activation+2.97e-02

Pos logit contributions
phe+1.799
ū+1.734
Ur+1.702
aug+1.676
UG+1.598
Neg logit contributions
 Howell-3.435
 Clarkson-3.009
 Birch-2.994
 JJ-2.899
 Hendricks-2.823
Token,
Token ID837
Feature activation+2.87e-01

Pos logit contributions
phe+0.255
ū+0.247
aug+0.244
Ur+0.242
kus+0.234
Neg logit contributions
 Howell-0.235
 Birch-0.201
 Clarkson-0.200
 JJ-0.192
 Hendricks-0.180
Token-
Token ID12
Feature activation+1.41e-01

Pos logit contributions
phe+0.398
ū+0.384
aug+0.377
Ur+0.375
UG+0.358
Neg logit contributions
 Howell-0.587
 Birch-0.516
 Clarkson-0.514
 JJ-0.494
 Hendricks-0.474
Tokento
Token ID1462
Feature activation-7.88e-02

Pos logit contributions
phe+0.851
ū+0.803
aug+0.795
Ur+0.790
UG+0.751
Neg logit contributions
 Howell-1.491
 Clarkson-1.324
 Birch-1.322
 JJ-1.276
 Hendricks-1.226
Token-
Token ID12
Feature activation+5.04e-02

Pos logit contributions
 Howell+0.758
 Birch+0.664
 Clarkson+0.663
 JJ+0.642
 Hendricks+0.611
Neg logit contributions
phe-0.537
ū-0.518
aug-0.508
Ur-0.508
UG-0.483
Tokenfemale
Token ID24724
Feature activation-2.01e-02

Pos logit contributions
phe+0.209
ū+0.193
aug+0.190
Ur+0.188
kus+0.174
Neg logit contributions
 Howell-0.626
 Clarkson-0.571
 Birch-0.570
 JJ-0.553
 Hendricks-0.532
Token (
Token ID357
Feature activation+4.68e-01

Pos logit contributions
 Howell+0.182
 Birch+0.159
 Clarkson+0.158
 JJ+0.151
 Hendricks+0.144
Neg logit contributions
phe-0.148
ū-0.143
aug-0.140
Ur-0.140
UG-0.134
TokenM
Token ID44
Feature activation+7.69e-01

Pos logit contributions
phe+2.366
aug+2.232
ū+2.221
UG+2.162
Ur+2.142
Neg logit contributions
 Howell-5.283
 Clarkson-4.806
 Birch-4.776
 JJ-4.468
 Dalton-4.429
TokenTF
Token ID10234
Feature activation+5.62e-02

Pos logit contributions
phe+2.352
ū+2.230
Ur+2.216
UG+2.189
aug+2.099
Neg logit contributions
 Howell-10.134
 Birch-9.253
 Clarkson-9.128
 JJ-8.727
 Hendricks-8.650
Token)
Token ID8
Feature activation-3.91e-01

Pos logit contributions
phe+0.386
ū+0.375
Ur+0.368
aug+0.366
UG+0.352
Neg logit contributions
 Howell-0.538
 Birch-0.472
 Clarkson-0.471
 JJ-0.452
 Hendricks-0.432
Token transgender
Token ID10637
Feature activation-2.17e-01

Pos logit contributions
 Howell+3.384
 Birch+2.921
 Clarkson+2.912
 JJ+2.804
 Hendricks+2.655
Neg logit contributions
phe-3.054
ū-2.954
aug-2.910
Ur-2.909
kus-2.790
Token people
Token ID661
Feature activation+6.26e-02

Pos logit contributions
 Howell+1.818
 Birch+1.563
 Clarkson+1.559
 JJ+1.489
 Hendricks+1.408
Neg logit contributions
phe-1.765
ū-1.709
aug-1.685
Ur-1.680
UG-1.613
Token are
Token ID389
Feature activation+3.62e-02

Pos logit contributions
phe+0.453
ū+0.435
aug+0.428
Ur+0.425
kus+0.408
Neg logit contributions
 Howell-0.580
 Birch-0.505
 Clarkson-0.504
 JJ-0.484
 Hendricks-0.463
Token102
Token ID15377
Feature activation+1.64e-01

Pos logit contributions
phe+0.804
ū+0.782
Ur+0.774
aug+0.774
UG+0.745
Neg logit contributions
 Howell-0.886
 Birch-0.762
 Clarkson-0.757
 JJ-0.728
 Hendricks-0.692
Token]
Token ID60
Feature activation+1.81e-02

Pos logit contributions
phe+0.546
ū+0.511
aug+0.494
Ur+0.486
UG+0.433
Neg logit contributions
 Howell-2.146
 Birch-1.950
 Clarkson-1.949
 JJ-1.901
 Hendricks-1.840
Token For
Token ID1114
Feature activation+3.02e-01

Pos logit contributions
phe+0.130
ū+0.126
Ur+0.124
aug+0.124
UG+0.118
Neg logit contributions
 Howell-0.166
 Birch-0.145
 Clarkson-0.144
 JJ-0.139
 Hendricks-0.132
Token the
Token ID262
Feature activation+2.27e-01

Pos logit contributions
phe+2.049
ū+1.994
aug+1.945
Ur+1.910
kus+1.879
Neg logit contributions
 Howell-2.860
 Birch-2.499
 Clarkson-2.462
 JJ-2.401
 Hendricks-2.289
Token 2014
Token ID1946
Feature activation+4.56e-01

Pos logit contributions
phe+1.649
ū+1.606
aug+1.565
Ur+1.553
kus+1.516
Neg logit contributions
 Howell-2.052
 Birch-1.775
 Clarkson-1.755
 JJ-1.696
 Hendricks-1.605
Token
Token ID1906
Feature activation+7.69e-01

Pos logit contributions
phe+2.905
ū+2.863
aug+2.808
Ur+2.751
UG+2.712
Neg logit contributions
 Howell-4.401
 Birch-3.823
 Clarkson-3.766
 JJ-3.688
 Hendricks-3.549
Token15
Token ID1314
Feature activation+5.12e-01

Pos logit contributions
aug+3.284
phe+3.219
Ur+3.119
ū+2.996
kus+2.812
Neg logit contributions
 Howell-8.957
 Birch-8.176
 Clarkson-7.991
 JJ-7.892
 Hendricks-7.676
Token Atlantic
Token ID10596
Feature activation+2.08e-01

Pos logit contributions
phe+3.378
ū+3.338
aug+3.229
Ur+3.166
UG+3.127
Neg logit contributions
 Howell-4.822
 Birch-4.183
 Clarkson-4.101
 JJ-4.013
 Hendricks-3.860
Token Coast
Token ID8545
Feature activation+2.16e-01

Pos logit contributions
phe+1.732
ū+1.693
aug+1.685
Ur+1.658
UG+1.599
Neg logit contributions
 Howell-1.665
 Clarkson-1.403
 Birch-1.396
 JJ-1.355
 Hendricks-1.277
Token Conference
Token ID8785
Feature activation+5.90e-01

Pos logit contributions
phe+1.584
ū+1.540
aug+1.517
Ur+1.502
UG+1.445
Neg logit contributions
 Howell-1.955
 Birch-1.698
 Clarkson-1.675
 JJ-1.634
 Hendricks-1.547
Token men
Token ID1450
Feature activation+4.44e-01

Pos logit contributions
phe+4.016
ū+3.941
aug+3.830
Ur+3.775
kus+3.656
Neg logit contributions
 Howell-5.449
 Birch-4.708
 Clarkson-4.632
 JJ-4.578
 Hendricks-4.327
TokenYR
Token ID38162
Feature activation+6.76e-02

Pos logit contributions
phe+1.089
ū+1.074
Ur+1.049
aug+1.026
UG+1.006
Neg logit contributions
 Howell-1.753
 Birch-1.538
 Clarkson-1.534
 JJ-1.491
 Hendricks-1.427
Token DS
Token ID17400
Feature activation-2.53e-01

Pos logit contributions
phe+0.471
ū+0.454
Ur+0.444
aug+0.435
UG+0.430
Neg logit contributions
 Howell-0.646
 Clarkson-0.563
 Birch-0.561
 JJ-0.538
 Hendricks-0.518
Token cent
Token ID1247
Feature activation-1.25e-01

Pos logit contributions
 Howell+2.292
 Birch+1.997
 Clarkson+1.989
 JJ+1.916
 Hendricks+1.819
Neg logit contributions
phe-1.871
ū-1.805
aug-1.779
Ur-1.775
kus-1.696
Tokenering
Token ID1586
Feature activation-6.01e-02

Pos logit contributions
 Howell+1.144
 Birch+0.995
 Clarkson+0.990
 JJ+0.953
 Hendricks+0.910
Neg logit contributions
phe-0.916
ū-0.889
aug-0.872
Ur-0.870
kus-0.830
Token
Token ID198
Feature activation+4.92e-01

Pos logit contributions
 Howell+0.528
 Birch+0.454
 Clarkson+0.453
 JJ+0.434
 Hendricks+0.413
Neg logit contributions
phe-0.465
ū-0.450
Ur-0.441
aug-0.440
UG-0.423
Token
Token ID198
Feature activation+7.66e-01

Pos logit contributions
phe+3.614
ū+3.501
aug+3.492
Ur+3.482
UG+3.307
Neg logit contributions
 Howell-4.424
 Birch-3.838
 Clarkson-3.801
 JJ-3.661
 Hendricks-3.478
TokenThe
Token ID464
Feature activation+1.96e-01

Pos logit contributions
Ur+3.381
phe+3.371
UG+3.161
aug+3.150
ū+3.109
Neg logit contributions
 Howell-9.024
 Birch-8.117
 Clarkson-8.071
 JJ-7.810
 Hendricks-7.536
Token Garg
Token ID39013
Feature activation-5.05e-02

Pos logit contributions
phe+1.285
ū+1.239
Ur+1.208
aug+1.201
UG+1.158
Neg logit contributions
 Howell-1.930
 Clarkson-1.697
 Birch-1.693
 JJ-1.614
 Hendricks-1.556
Tokenant
Token ID415
Feature activation-4.70e-02

Pos logit contributions
 Howell+0.451
 Birch+0.392
 Clarkson+0.389
 JJ+0.374
 Hendricks+0.356
Neg logit contributions
phe-0.379
ū-0.362
Ur-0.361
aug-0.356
kus-0.346
Tokenua
Token ID6413
Feature activation-1.41e-01

Pos logit contributions
 Howell+0.421
 Birch+0.365
 Clarkson+0.363
 JJ+0.351
 Hendricks+0.333
Neg logit contributions
phe-0.352
ū-0.337
Ur-0.335
aug-0.333
kus-0.319
Token is
Token ID318
Feature activation+1.12e-01

Pos logit contributions
 Howell+1.233
 Birch+1.067
 Clarkson+1.064
 JJ+1.019
 Hendricks+0.969
Neg logit contributions
phe-1.090
ū-1.055
aug-1.037
Ur-1.037
kus-0.992
Token Mysteries
Token ID28298
Feature activation+4.60e-01

Pos logit contributions
phe+0.620
ū+0.598
Ur+0.590
aug+0.590
kus+0.568
Neg logit contributions
 Howell-0.558
 Birch-0.475
 Clarkson-0.471
 JJ-0.449
 Hendricks-0.423
Token,
Token ID11
Feature activation+4.34e-01

Pos logit contributions
phe+3.222
ū+3.134
Ur+3.071
aug+3.057
UG+2.917
Neg logit contributions
 Howell-4.302
 Birch-3.759
 Clarkson-3.747
 JJ-3.596
 Hendricks-3.427
Token comic
Token ID9048
Feature activation+2.23e-01

Pos logit contributions
phe+3.150
ū+3.110
aug+3.026
Ur+2.996
UG+2.894
Neg logit contributions
 Howell-3.920
 Birch-3.359
 Clarkson-3.354
 JJ-3.191
 Hendricks-3.077
Token book
Token ID1492
Feature activation+9.03e-02

Pos logit contributions
phe+1.933
ū+1.881
aug+1.856
Ur+1.853
kus+1.783
Neg logit contributions
 Howell-1.735
 Birch-1.469
 Clarkson-1.466
 JJ-1.395
 Hendricks-1.316
Token short
Token ID1790
Feature activation+4.31e-01

Pos logit contributions
phe+0.646
ū+0.621
Ur+0.610
aug+0.609
kus+0.584
Neg logit contributions
 Howell-0.846
 Birch-0.744
 Clarkson-0.741
 JJ-0.711
 Hendricks-0.679
Token stories
Token ID3923
Feature activation+7.66e-01

Pos logit contributions
phe+3.475
ū+3.442
Ur+3.397
aug+3.360
kus+3.238
Neg logit contributions
 Howell-3.553
 Clarkson-3.042
 Birch-3.032
 JJ-2.860
 Hendricks-2.721
Token,
Token ID11
Feature activation+2.62e-01

Pos logit contributions
phe+4.841
ū+4.723
Ur+4.657
aug+4.626
UG+4.403
Neg logit contributions
 Howell-7.437
 Birch-6.543
 Clarkson-6.530
 JJ-6.258
 Hendricks-5.981
Token prose
Token ID27149
Feature activation+6.17e-01

Pos logit contributions
phe+1.622
ū+1.569
Ur+1.520
aug+1.518
kus+1.431
Neg logit contributions
 Howell-2.683
 Birch-2.377
 Clarkson-2.366
 JJ-2.281
 Hendricks-2.183
Token,
Token ID11
Feature activation-6.37e-02

Pos logit contributions
phe+4.074
ū+3.959
aug+3.939
Ur+3.935
UG+3.727
Neg logit contributions
 Howell-5.899
 Clarkson-5.176
 Birch-5.166
 JJ-4.934
 Hendricks-4.722
Token and
Token ID290
Feature activation+9.10e-02

Pos logit contributions
 Howell+0.512
 Birch+0.440
 Clarkson+0.436
 JJ+0.418
 Hendricks+0.395
Neg logit contributions
phe-0.541
ū-0.521
aug-0.514
Ur-0.512
kus-0.496
Token non
Token ID1729
Feature activation+5.20e-01

Pos logit contributions
phe+0.699
ū+0.674
aug+0.665
Ur+0.664
kus+0.635
Neg logit contributions
 Howell-0.803
 Birch-0.696
 Clarkson-0.693
 JJ-0.667
 Hendricks-0.632
Token with
Token ID351
Feature activation-3.83e-02

Pos logit contributions
 Howell+0.352
 Birch+0.300
 Clarkson+0.298
 JJ+0.284
 Hendricks+0.269
Neg logit contributions
phe-0.380
ū-0.368
aug-0.363
Ur-0.363
kus-0.348
Token bad
Token ID2089
Feature activation+2.38e-02

Pos logit contributions
 Howell+0.335
 Birch+0.290
 Clarkson+0.289
 JJ+0.277
 Hendricks+0.263
Neg logit contributions
phe-0.296
ū-0.285
aug-0.282
Ur-0.281
kus-0.270
Token manners
Token ID33558
Feature activation-1.46e-01

Pos logit contributions
phe+0.179
ū+0.172
Ur+0.170
aug+0.170
kus+0.163
Neg logit contributions
 Howell-0.213
 Clarkson-0.186
 Birch-0.186
 JJ-0.177
 Hendricks-0.169
Token.
Token ID13
Feature activation+2.67e-02

Pos logit contributions
 Howell+1.321
 Birch+1.150
 Clarkson+1.146
 JJ+1.101
 Hendricks+1.047
Neg logit contributions
phe-1.081
ū-1.044
aug-1.028
Ur-1.027
kus-0.979
Token -
Token ID532
Feature activation-1.27e-01

Pos logit contributions
phe+0.187
ū+0.180
Ur+0.178
aug+0.178
UG+0.169
Neg logit contributions
 Howell-0.253
 Birch-0.221
 Clarkson-0.221
 JJ-0.212
 Hendricks-0.203
Token January
Token ID3269
Feature activation+7.61e-01

Pos logit contributions
 Howell+1.060
 Clarkson+0.916
 Birch+0.910
 JJ+0.876
 Hendricks+0.834
Neg logit contributions
phe-1.033
ū-0.997
Ur-0.985
aug-0.977
anamo-0.945
Token 4
Token ID604
Feature activation+2.89e-01

Pos logit contributions
ū+4.520
phe+4.475
Ur+4.389
aug+4.387
UG+4.191
Neg logit contributions
 Howell-7.571
 Clarkson-6.696
 Birch-6.678
 JJ-6.435
 Hendricks-6.216
Token,
Token ID11
Feature activation+2.60e-01

Pos logit contributions
phe+2.114
ū+2.043
aug+2.019
Ur+2.016
UG+1.921
Neg logit contributions
 Howell-2.648
 Birch-2.310
 Clarkson-2.300
 JJ-2.209
 Hendricks-2.102
Token 2010
Token ID3050
Feature activation+5.86e-01

Pos logit contributions
phe+1.816
ū+1.750
aug+1.723
Ur+1.721
UG+1.640
Neg logit contributions
 Howell-2.430
 Birch-2.136
 Clarkson-2.135
 JJ-2.051
 Hendricks-1.951
TokenUser
Token ID12982
Feature activation-2.34e-02

Pos logit contributions
phe+2.063
Ur+2.051
ū+2.003
aug+1.970
UG+1.894
Neg logit contributions
 Howell-7.536
 Birch-6.817
 Clarkson-6.758
 JJ-6.615
 Hendricks-6.448
Token reviews
Token ID8088
Feature activation+3.51e-01

Pos logit contributions
 Howell+0.183
 Birch+0.156
 Clarkson+0.156
 JJ+0.149
 Hendricks+0.140
Neg logit contributions
phe-0.204
ū-0.196
Ur-0.194
aug-0.194
kus-0.187
Token'
Token ID6
Feature activation-6.94e-02

Pos logit contributions
 Howell+1.874
 Birch+1.653
 Clarkson+1.648
 JJ+1.592
 Hendricks+1.525
Neg logit contributions
phe-1.206
ū-1.159
aug-1.138
Ur-1.136
kus-1.077
Token "
Token ID366
Feature activation+5.26e-02

Pos logit contributions
 Howell+0.559
 Birch+0.475
 Clarkson+0.473
 JJ+0.451
 Hendricks+0.429
Neg logit contributions
phe-0.585
ū-0.565
aug-0.559
Ur-0.557
kus-0.537
TokenI
Token ID40
Feature activation-1.59e-02

Pos logit contributions
phe+0.301
Ur+0.288
ū+0.285
aug+0.281
UG+0.267
Neg logit contributions
 Howell-0.570
 Birch-0.506
 Clarkson-0.504
 JJ-0.489
 Hendricks-0.471
Token'll
Token ID1183
Feature activation+2.12e-01

Pos logit contributions
 Howell+0.144
 Birch+0.125
 Clarkson+0.125
 JJ+0.120
 Hendricks+0.115
Neg logit contributions
phe-0.118
ū-0.113
aug-0.111
Ur-0.111
kus-0.107
Token Feel
Token ID18571
Feature activation-2.47e-01

Pos logit contributions
phe+0.969
ū+0.916
aug+0.893
Ur+0.877
kus+0.806
Neg logit contributions
 Howell-2.506
 Clarkson-2.255
 Birch-2.248
 JJ-2.174
 Hendricks-2.134
Token a
Token ID257
Feature activation+7.52e-01

Pos logit contributions
 Howell+2.324
 Birch+2.034
 Clarkson+2.028
 JJ+1.954
 Hendricks+1.861
Neg logit contributions
phe-1.746
ū-1.682
aug-1.655
Ur-1.653
kus-1.574
Token Whole
Token ID23431
Feature activation+2.17e-01

Pos logit contributions
phe+4.644
ū+4.367
aug+4.346
Ur+4.234
UG+4.146
Neg logit contributions
 Howell-7.320
 Birch-6.484
 Clarkson-6.362
 JJ-6.253
 Hendricks-5.934
Token Lot
Token ID15099
Feature activation+4.34e-02

Pos logit contributions
phe+1.392
ū+1.336
aug+1.312
Ur+1.310
kus+1.241
Neg logit contributions
 Howell-2.193
 Birch-1.937
 Clarkson-1.932
 JJ-1.867
 Hendricks-1.785
Token Better
Token ID11625
Feature activation-1.25e-01

Pos logit contributions
phe+0.308
ū+0.297
aug+0.292
Ur+0.291
UG+0.278
Neg logit contributions
 Howell-0.407
 Birch-0.355
 Clarkson-0.354
 JJ-0.340
 Hendricks-0.326
Token"
Token ID1
Feature activation-7.15e-02

Pos logit contributions
 Howell+1.124
 Birch+0.976
 Clarkson+0.973
 JJ+0.934
 Hendricks+0.888
Neg logit contributions
phe-0.945
ū-0.913
aug-0.899
Ur-0.897
kus-0.857
Token (
Token ID357
Feature activation-4.20e-03

Pos logit contributions
 Howell+0.632
 Birch+0.548
 Clarkson+0.545
 JJ+0.523
 Hendricks+0.498
Neg logit contributions
phe-0.546
ū-0.530
Ur-0.521
aug-0.520
kus-0.497
Token the
Token ID262
Feature activation+7.44e-02

Pos logit contributions
 Howell+0.985
 Birch+0.861
 Clarkson+0.857
 JJ+0.823
 Hendricks+0.788
Neg logit contributions
phe-0.754
ū-0.732
aug-0.724
Ur-0.717
UG-0.687
Token Democratic
Token ID4390
Feature activation-1.28e-01

Pos logit contributions
phe+0.546
ū+0.534
aug+0.529
Ur+0.523
UG+0.504
Neg logit contributions
 Howell-0.659
 Birch-0.574
 Clarkson-0.573
 JJ-0.548
 Hendricks-0.525
Token National
Token ID2351
Feature activation-8.63e-02

Pos logit contributions
 Howell+0.932
 Clarkson+0.782
 Birch+0.781
 JJ+0.742
 Hendricks+0.693
Neg logit contributions
phe-1.168
ū-1.140
aug-1.128
Ur-1.124
kus-1.085
Token Committee
Token ID4606
Feature activation+1.02e-01

Pos logit contributions
 Howell+0.879
 Birch+0.777
 Clarkson+0.774
 JJ+0.750
 Hendricks+0.716
Neg logit contributions
phe-0.553
ū-0.525
Ur-0.518
aug-0.512
UG-0.490
Token leak
Token ID13044
Feature activation+2.36e-01

Pos logit contributions
phe+0.773
ū+0.758
aug+0.752
Ur+0.748
UG+0.714
Neg logit contributions
 Howell-0.886
 Clarkson-0.773
 Birch-0.772
 JJ-0.739
 Hendricks-0.704
Token
Token ID198
Feature activation+7.50e-01

Pos logit contributions
phe+1.724
ū+1.694
aug+1.675
Ur+1.670
UG+1.585
Neg logit contributions
 Howell-2.099
 Birch-1.834
 Clarkson-1.829
 JJ-1.744
 Hendricks-1.690
Token
Token ID198
Feature activation+5.03e-01

Pos logit contributions
phe+5.116
Ur+5.052
aug+4.997
ū+4.985
UG+4.740
Neg logit contributions
 Howell-6.891
 Birch-5.988
 Clarkson-5.910
 JJ-5.710
 Hendricks-5.462
TokenR
Token ID49
Feature activation-1.21e-01

Pos logit contributions
Ur+2.736
phe+2.644
aug+2.622
ū+2.545
UG+2.535
Neg logit contributions
 Howell-5.522
 Birch-4.948
 Clarkson-4.918
 JJ-4.784
 Hendricks-4.605
Tokenobby
Token ID11369
Feature activation+1.92e-01

Pos logit contributions
 Howell+1.241
 Clarkson+1.100
 Birch+1.099
 JJ+1.061
 Hendricks+1.020
Neg logit contributions
phe-0.764
ū-0.738
aug-0.723
Ur-0.718
UG-0.685
Token M
Token ID337
Feature activation-2.07e-01

Pos logit contributions
phe+1.523
ū+1.469
aug+1.444
Ur+1.431
kus+1.377
Neg logit contributions
 Howell-1.603
 Clarkson-1.369
 Birch-1.362
 JJ-1.327
 Hendricks-1.226
Tokenook
Token ID566
Feature activation+5.03e-02

Pos logit contributions
 Howell+1.596
 Birch+1.361
 Clarkson+1.346
 JJ+1.270
 Hendricks+1.198
Neg logit contributions
phe-1.809
ū-1.734
Ur-1.728
aug-1.704
kus-1.654
Token this
Token ID428
Feature activation-2.39e-01

Pos logit contributions
 Howell+3.588
 Birch+3.145
 Clarkson+3.136
 JJ+3.023
 Hendricks+2.867
Neg logit contributions
phe-2.816
ū-2.710
Ur-2.673
aug-2.667
kus-2.539
Token webpage
Token ID35699
Feature activation+1.95e-01

Pos logit contributions
 Howell+2.031
 Birch+1.750
 Clarkson+1.744
 JJ+1.672
 Hendricks+1.583
Neg logit contributions
phe-1.909
ū-1.848
aug-1.821
Ur-1.819
kus-1.743
Token,
Token ID11
Feature activation+1.22e-01

Pos logit contributions
phe+1.406
ū+1.376
aug+1.346
Ur+1.345
ura+1.275
Neg logit contributions
 Howell-1.791
 Birch-1.551
 Clarkson-1.530
 JJ-1.489
 Hendricks-1.416
Token in
Token ID287
Feature activation-2.67e-01

Pos logit contributions
phe+0.906
ū+0.877
aug+0.864
Ur+0.864
kus+0.824
Neg logit contributions
 Howell-1.091
 Birch-0.946
 Clarkson-0.939
 JJ-0.906
 Hendricks-0.859
Token whole
Token ID2187
Feature activation-1.65e-01

Pos logit contributions
 Howell+2.414
 Birch+2.100
 Clarkson+2.092
 JJ+2.010
 Hendricks+1.911
Neg logit contributions
phe-1.992
ū-1.924
aug-1.901
Ur-1.894
kus-1.810
Token or
Token ID393
Feature activation-9.60e-01

Pos logit contributions
 Howell+1.526
 Birch+1.329
 Clarkson+1.311
 JJ+1.268
 Hendricks+1.219
Neg logit contributions
phe-1.203
ū-1.168
Ur-1.149
aug-1.146
kus-1.092
Token in
Token ID287
Feature activation-8.36e-01

Pos logit contributions
 Howell+7.115
 Birch+6.118
 Clarkson+6.067
 JJ+5.813
 Hendricks+5.495
Neg logit contributions
phe-8.360
aug-7.976
ū-7.951
Ur-7.877
anamo-7.679
Token part
Token ID636
Feature activation-6.60e-01

Pos logit contributions
 Howell+3.841
 Birch+2.903
 Clarkson+2.886
 JJ+2.761
 Hendricks+2.410
Neg logit contributions
phe-9.685
ū-9.400
aug-9.268
Ur-9.252
anamo-9.214
Token,
Token ID11
Feature activation-6.99e-02

Pos logit contributions
 Howell+5.532
 Birch+4.815
 Clarkson+4.812
 JJ+4.583
 Hendricks+4.372
Neg logit contributions
phe-5.200
ū-4.982
Ur-4.947
aug-4.939
kus-4.756
Token is
Token ID318
Feature activation-4.20e-01

Pos logit contributions
 Howell+0.630
 Birch+0.543
 Clarkson+0.540
 JJ+0.522
 Hendricks+0.495
Neg logit contributions
phe-0.522
ū-0.508
aug-0.499
Ur-0.499
kus-0.475
Token strictly
Token ID14084
Feature activation-1.43e-02

Pos logit contributions
 Howell+3.411
 Clarkson+2.930
 Birch+2.921
 JJ+2.792
 Hendricks+2.640
Neg logit contributions
phe-3.514
ū-3.381
aug-3.330
Ur-3.327
kus-3.191
Token any
Token ID597
Feature activation-2.72e-01

Pos logit contributions
 Howell+1.364
 Birch+1.191
 Clarkson+1.189
 JJ+1.141
 Hendricks+1.094
Neg logit contributions
phe-1.033
ū-0.996
aug-0.978
Ur-0.977
kus-0.932
Token antenna
Token ID20509
Feature activation-1.60e-01

Pos logit contributions
 Howell+2.403
 Birch+2.084
 Clarkson+2.078
 JJ+1.992
 Hendricks+1.894
Neg logit contributions
phe-2.083
ū-2.012
Ur-1.981
aug-1.979
kus-1.895
Token,
Token ID11
Feature activation-6.71e-02

Pos logit contributions
 Howell+1.423
 Birch+1.231
 Clarkson+1.230
 JJ+1.176
 Hendricks+1.123
Neg logit contributions
phe-1.216
ū-1.175
Ur-1.161
aug-1.160
UG-1.106
Token both
Token ID1111
Feature activation-1.06e-01

Pos logit contributions
 Howell+0.572
 Birch+0.493
 Clarkson+0.492
 JJ+0.469
 Hendricks+0.447
Neg logit contributions
phe-0.532
ū-0.512
Ur-0.505
aug-0.505
kus-0.487
Token external
Token ID7097
Feature activation-2.99e-01

Pos logit contributions
 Howell+0.930
 Birch+0.805
 Clarkson+0.803
 JJ+0.769
 Hendricks+0.732
Neg logit contributions
phe-0.811
ū-0.784
Ur-0.772
aug-0.771
kus-0.739
Token and
Token ID290
Feature activation-9.42e-01

Pos logit contributions
 Howell+2.576
 Birch+2.222
 Clarkson+2.217
 JJ+2.121
 Hendricks+2.016
Neg logit contributions
phe-2.361
ū-2.284
Ur-2.250
aug-2.249
kus-2.153
Token internal
Token ID5387
Feature activation-4.97e-01

Pos logit contributions
 Howell+7.531
 Birch+6.432
 Clarkson+6.300
 JJ+6.099
 Gad+5.778
Neg logit contributions
phe-7.790
aug-7.502
ū-7.430
Ur-7.417
anamo-7.103
Token,
Token ID11
Feature activation-2.74e-01

Pos logit contributions
 Howell+4.403
 Birch+3.827
 Clarkson+3.811
 JJ+3.674
 Hendricks+3.466
Neg logit contributions
phe-3.767
ū-3.642
aug-3.595
Ur-3.576
kus-3.426
Token and
Token ID290
Feature activation-1.72e-01

Pos logit contributions
 Howell+2.329
 Birch+2.005
 Clarkson+1.998
 JJ+1.915
 Hendricks+1.815
Neg logit contributions
phe-2.190
ū-2.120
aug-2.091
Ur-2.088
kus-2.001
Token note
Token ID3465
Feature activation+6.90e-02

Pos logit contributions
 Howell+1.516
 Birch+1.312
 Clarkson+1.307
 JJ+1.254
 Hendricks+1.194
Neg logit contributions
phe-1.327
ū-1.284
aug-1.264
Ur-1.263
kus-1.212
Token if
Token ID611
Feature activation-1.79e-01

Pos logit contributions
phe+0.485
ū+0.470
aug+0.463
Ur+0.461
UG+0.443
Neg logit contributions
 Howell-0.644
 Clarkson-0.562
 Birch-0.562
 JJ-0.536
 Hendricks-0.518
Tokenel
Token ID417
Feature activation-5.04e-01

Pos logit contributions
 Howell+4.758
 Birch+4.107
 Clarkson+4.099
 JJ+3.939
 Hendricks+3.738
Neg logit contributions
phe-3.979
ū-3.826
Ur-3.783
aug-3.763
UG-3.619
Token,
Token ID11
Feature activation-3.54e-01

Pos logit contributions
 Howell+4.471
 Birch+3.884
 Clarkson+3.850
 JJ+3.723
 Hendricks+3.529
Neg logit contributions
phe-3.776
ū-3.646
Ur-3.619
aug-3.617
UG-3.445
Token and
Token ID290
Feature activation-5.35e-01

Pos logit contributions
 Howell+3.067
 Birch+2.650
 Clarkson+2.641
 JJ+2.539
 Hendricks+2.403
Neg logit contributions
phe-2.773
ū-2.679
aug-2.648
Ur-2.639
kus-2.531
Token Schiff
Token ID41665
Feature activation-4.01e-01

Pos logit contributions
 Howell+4.589
 Birch+3.942
 Clarkson+3.937
 JJ+3.782
 Hendricks+3.604
Neg logit contributions
phe-4.199
ū-4.086
aug-4.047
Ur-4.030
UG-3.862
Tokenman
Token ID805
Feature activation-6.34e-01

Pos logit contributions
 Howell+3.256
 Birch+2.784
 Clarkson+2.783
 JJ+2.722
 Hendricks+2.529
Neg logit contributions
phe-3.201
Ur-3.111
ū-3.092
aug-3.022
UG-2.997
Token,
Token ID11
Feature activation-8.62e-01

Pos logit contributions
 Howell+5.373
 Birch+4.656
 Clarkson+4.627
 JJ+4.522
 Hendricks+4.194
Neg logit contributions
phe-4.904
Ur-4.733
ū-4.709
aug-4.703
UG-4.526
Token Outside
Token ID22151
Feature activation-2.56e-01

Pos logit contributions
 Howell+6.720
 Birch+5.714
 Clarkson+5.685
 JJ+5.626
 Hendricks+5.122
Neg logit contributions
phe-7.216
ū-6.970
aug-6.951
Ur-6.881
kus-6.702
Token the
Token ID262
Feature activation-2.31e-01

Pos logit contributions
 Howell+2.321
 Birch+2.020
 Clarkson+2.012
 JJ+1.937
 Hendricks+1.839
Neg logit contributions
phe-1.906
ū-1.839
aug-1.813
Ur-1.810
kus-1.729
Token Bible
Token ID9111
Feature activation-5.52e-01

Pos logit contributions
 Howell+1.868
 Birch+1.604
 Clarkson+1.580
 JJ+1.519
 Hendricks+1.435
Neg logit contributions
phe-1.957
ū-1.883
aug-1.873
Ur-1.864
kus-1.795
Token,
Token ID11
Feature activation-3.64e-01

Pos logit contributions
 Howell+5.085
 Birch+4.444
 Clarkson+4.419
 JJ+4.280
 Hendricks+4.065
Neg logit contributions
phe-3.931
ū-3.759
aug-3.740
Ur-3.725
kus-3.561
Token 3
Token ID513
Feature activation-3.32e-01

Pos logit contributions
 Howell+3.198
 Birch+2.769
 Clarkson+2.760
 JJ+2.656
 Hendricks+2.515
Neg logit contributions
phe-2.801
ū-2.708
aug-2.670
Ur-2.664
kus-2.562
Token
Token ID198
Feature activation+2.23e-02

Pos logit contributions
 Howell+0.437
 Clarkson+0.374
 Birch+0.373
 JJ+0.356
 Hendricks+0.336
Neg logit contributions
phe-0.480
ū-0.463
aug-0.453
Ur-0.452
anamo-0.442
TokenHall
Token ID34194
Feature activation-8.19e-02

Pos logit contributions
phe+0.126
ū+0.120
Ur+0.119
aug+0.118
UG+0.110
Neg logit contributions
 Howell-0.243
 Birch-0.217
 Clarkson-0.215
 JJ-0.210
 Hendricks-0.201
Tokenion
Token ID295
Feature activation-2.72e-02

Pos logit contributions
 Howell+0.799
 Clarkson+0.700
 Birch+0.699
 JJ+0.674
 Hendricks+0.642
Neg logit contributions
phe-0.555
ū-0.536
aug-0.529
Ur-0.520
kus-0.497
Token,
Token ID11
Feature activation+8.62e-02

Pos logit contributions
 Howell+0.248
 Birch+0.216
 Clarkson+0.216
 JJ+0.208
 Hendricks+0.197
Neg logit contributions
phe-0.199
ū-0.192
aug-0.189
Ur-0.187
kus-0.180
Token Richard
Token ID6219
Feature activation-7.31e-01

Pos logit contributions
phe+0.712
ū+0.690
Ur+0.684
aug+0.682
UG+0.653
Neg logit contributions
 Howell-0.689
 Birch-0.589
 Clarkson-0.587
 JJ-0.556
 Hendricks-0.528
Token P
Token ID350
Feature activation-8.51e-01

Pos logit contributions
 Howell+6.485
 Birch+5.647
 Clarkson+5.640
 JJ+5.393
 Hendricks+5.157
Neg logit contributions
phe-5.375
ū-5.214
Ur-5.194
aug-5.131
anamo-4.991
Token.
Token ID13
Feature activation-3.22e-01

Pos logit contributions
 Howell+7.580
 Clarkson+6.630
 Birch+6.591
 JJ+6.329
 Hendricks+6.013
Neg logit contributions
phe-5.959
Ur-5.713
ū-5.677
aug-5.605
kus-5.475
Token Design
Token ID8495
Feature activation+5.60e-02

Pos logit contributions
 Howell+2.793
 Birch+2.415
 Clarkson+2.407
 JJ+2.310
 Hendricks+2.190
Neg logit contributions
phe-2.520
ū-2.435
aug-2.400
Ur-2.397
kus-2.297
Tokeners
Token ID364
Feature activation+1.86e-01

Pos logit contributions
phe+0.420
ū+0.411
aug+0.403
Ur+0.401
kus+0.384
Neg logit contributions
 Howell-0.502
 Clarkson-0.434
 Birch-0.433
 JJ-0.417
 Hendricks-0.395
Token and
Token ID290
Feature activation-1.21e-01

Pos logit contributions
phe+1.349
ū+1.319
Ur+1.282
aug+1.282
kus+1.226
Neg logit contributions
 Howell-1.694
 Clarkson-1.473
 Birch-1.473
 JJ-1.417
 Hendricks-1.347
Token Test
Token ID6208
Feature activation+9.93e-03

Pos logit contributions
 Howell+1.087
 Birch+0.944
 Clarkson+0.942
 JJ+0.905
 Hendricks+0.860
Neg logit contributions
phe-0.903
ū-0.875
aug-0.861
Ur-0.859
kus-0.822
Token webpage
Token ID35699
Feature activation+1.95e-01

Pos logit contributions
 Howell+2.031
 Birch+1.750
 Clarkson+1.744
 JJ+1.672
 Hendricks+1.583
Neg logit contributions
phe-1.909
ū-1.848
aug-1.821
Ur-1.819
kus-1.743
Token,
Token ID11
Feature activation+1.22e-01

Pos logit contributions
phe+1.406
ū+1.376
aug+1.346
Ur+1.345
ura+1.275
Neg logit contributions
 Howell-1.791
 Birch-1.551
 Clarkson-1.530
 JJ-1.489
 Hendricks-1.416
Token in
Token ID287
Feature activation-2.67e-01

Pos logit contributions
phe+0.906
ū+0.877
aug+0.864
Ur+0.864
kus+0.824
Neg logit contributions
 Howell-1.091
 Birch-0.946
 Clarkson-0.939
 JJ-0.906
 Hendricks-0.859
Token whole
Token ID2187
Feature activation-1.65e-01

Pos logit contributions
 Howell+2.414
 Birch+2.100
 Clarkson+2.092
 JJ+2.010
 Hendricks+1.911
Neg logit contributions
phe-1.992
ū-1.924
aug-1.901
Ur-1.894
kus-1.810
Token or
Token ID393
Feature activation-9.60e-01

Pos logit contributions
 Howell+1.526
 Birch+1.329
 Clarkson+1.311
 JJ+1.268
 Hendricks+1.219
Neg logit contributions
phe-1.203
ū-1.168
Ur-1.149
aug-1.146
kus-1.092
Token in
Token ID287
Feature activation-8.36e-01

Pos logit contributions
 Howell+7.115
 Birch+6.118
 Clarkson+6.067
 JJ+5.813
 Hendricks+5.495
Neg logit contributions
phe-8.360
aug-7.976
ū-7.951
Ur-7.877
anamo-7.679
Token part
Token ID636
Feature activation-6.60e-01

Pos logit contributions
 Howell+3.841
 Birch+2.903
 Clarkson+2.886
 JJ+2.761
 Hendricks+2.410
Neg logit contributions
phe-9.685
ū-9.400
aug-9.268
Ur-9.252
anamo-9.214
Token,
Token ID11
Feature activation-6.99e-02

Pos logit contributions
 Howell+5.532
 Birch+4.815
 Clarkson+4.812
 JJ+4.583
 Hendricks+4.372
Neg logit contributions
phe-5.200
ū-4.982
Ur-4.947
aug-4.939
kus-4.756
Token is
Token ID318
Feature activation-4.20e-01

Pos logit contributions
 Howell+0.630
 Birch+0.543
 Clarkson+0.540
 JJ+0.522
 Hendricks+0.495
Neg logit contributions
phe-0.522
ū-0.508
aug-0.499
Ur-0.499
kus-0.475
Token strictly
Token ID14084
Feature activation-1.43e-02

Pos logit contributions
 Howell+3.411
 Clarkson+2.930
 Birch+2.921
 JJ+2.792
 Hendricks+2.640
Neg logit contributions
phe-3.514
ū-3.381
aug-3.330
Ur-3.327
kus-3.191
Token prohibited
Token ID12244
Feature activation+1.33e-01

Pos logit contributions
 Howell+0.132
 Birch+0.116
 Clarkson+0.115
 JJ+0.111
 Hendricks+0.105
Neg logit contributions
phe-0.103
ū-0.100
Ur-0.099
aug-0.099
UG-0.094
TokenFollow
Token ID7155
Feature activation-2.30e-01

Pos logit contributions
 Howell+0.072
 Birch+0.064
 Clarkson+0.064
 JJ+0.062
 Hendricks+0.059
Neg logit contributions
phe-0.041
ū-0.040
aug-0.039
Ur-0.039
UG-0.037
Token Justin
Token ID10799
Feature activation+2.67e-01

Pos logit contributions
 Howell+1.918
 Birch+1.649
 Clarkson+1.641
 JJ+1.579
 Hendricks+1.486
Neg logit contributions
phe-1.876
ū-1.814
aug-1.788
Ur-1.785
kus-1.714
Token on
Token ID319
Feature activation-1.45e-01

Pos logit contributions
phe+1.814
Ur+1.726
aug+1.726
ū+1.721
kus+1.636
Neg logit contributions
 Howell-2.503
 Birch-2.222
 Clarkson-2.220
 JJ-2.128
 Hendricks-2.012
Token Twitter
Token ID3009
Feature activation-9.56e-02

Pos logit contributions
 Howell+1.260
 Birch+1.090
 Clarkson+1.087
 JJ+1.043
 Hendricks+0.989
Neg logit contributions
phe-1.127
ū-1.089
aug-1.073
Ur-1.072
kus-1.026
Token<|endoftext|>
Token ID50256
Feature activation-9.91e-02

Pos logit contributions
 Howell+0.927
 Birch+0.814
 Clarkson+0.814
 JJ+0.783
 Hendricks+0.749
Neg logit contributions
phe-0.647
ū-0.623
Ur-0.614
aug-0.614
UG-0.583
Tokenby
Token ID1525
Feature activation-8.35e-01

Pos logit contributions
 Howell+1.061
 Birch+0.944
 Clarkson+0.941
 JJ+0.911
 Hendricks+0.874
Neg logit contributions
phe-0.577
ū-0.551
Ur-0.543
aug-0.542
UG-0.509
Token Julia
Token ID22300
Feature activation-2.78e-03

Pos logit contributions
 Howell+7.072
 Birch+6.106
 Clarkson+6.092
 JJ+5.929
 Dalton+5.510
Neg logit contributions
phe-6.493
aug-6.166
ū-6.163
Ur-6.086
kus-5.921
Token Py
Token ID9485
Feature activation+4.64e-02

Pos logit contributions
 Howell+0.023
 Birch+0.020
 Clarkson+0.020
 JJ+0.019
 Hendricks+0.018
Neg logit contributions
phe-0.022
ū-0.022
aug-0.021
Ur-0.021
UG-0.020
Tokenper
Token ID525
Feature activation+1.26e-01

Pos logit contributions
phe+0.276
ū+0.269
aug+0.260
Ur+0.258
kus+0.250
Neg logit contributions
 Howell-0.490
 Birch-0.440
 Clarkson-0.437
 JJ-0.422
 Hendricks-0.403
Token
Token ID198
Feature activation-4.69e-01

Pos logit contributions
phe+0.897
ū+0.875
aug+0.868
Ur+0.850
kus+0.830
Neg logit contributions
 Howell-1.155
 Birch-1.014
 Clarkson-1.011
 JJ-0.967
 Hendricks-0.927
Token
Token ID198
Feature activation-4.79e-01

Pos logit contributions
 Howell+3.272
 Clarkson+2.766
 Birch+2.735
 JJ+2.621
 Hendricks+2.431
Neg logit contributions
phe-4.254
ū-4.106
anamo-4.096
aug-3.988
Ur-3.944
TokenFrank
Token ID17439
Feature activation+1.76e-01

Pos logit contributions
 Howell+0.066
 Birch+0.059
 Clarkson+0.059
 JJ+0.057
 Hendricks+0.055
Neg logit contributions
phe-0.030
ū-0.029
Ur-0.029
aug-0.028
UG-0.027
Tokeniv
Token ID452
Feature activation+2.87e-01

Pos logit contributions
phe+1.617
ū+1.609
aug+1.589
Ur+1.585
kus+1.541
Neg logit contributions
 Howell-1.271
 Birch-1.060
 Clarkson-1.055
 JJ-0.993
 Hendricks-0.948
Tokensk
Token ID8135
Feature activation+3.93e-01

Pos logit contributions
phe+1.055
ū+0.998
Ur+0.958
aug+0.955
kus+0.868
Neg logit contributions
 Howell-3.655
 Birch-3.332
 Clarkson-3.320
 JJ-3.234
 Hendricks-3.141
Token.
Token ID13
Feature activation-7.17e-02

Pos logit contributions
phe+2.820
ū+2.739
aug+2.704
Ur+2.697
ogo+2.574
Neg logit contributions
 Howell-3.587
 Birch-3.157
 Clarkson-3.112
 JJ-2.950
 Hendricks-2.876
Token<|endoftext|>
Token ID50256
Feature activation-2.37e-01

Pos logit contributions
 Howell+0.655
 Birch+0.572
 Clarkson+0.570
 JJ+0.547
 Hendricks+0.520
Neg logit contributions
phe-0.521
ū-0.503
Ur-0.500
aug-0.497
UG-0.474
Token[
Token ID58
Feature activation-8.31e-01

Pos logit contributions
 Howell+2.524
 Birch+2.246
 Clarkson+2.242
 JJ+2.170
 Hendricks+2.082
Neg logit contributions
phe-1.367
ū-1.307
aug-1.278
Ur-1.273
kus-1.204
TokenEx
Token ID3109
Feature activation+1.31e-01

Pos logit contributions
 Howell+8.589
 Birch+7.692
 Clarkson+7.651
 JJ+7.422
 Hendricks+7.106
Neg logit contributions
phe-4.654
ū-4.446
aug-4.248
Ur-4.228
kus-4.136
Tokenclusive
Token ID5731
Feature activation+9.51e-02

Pos logit contributions
phe+0.935
aug+0.904
ū+0.900
Ur+0.895
kus+0.848
Neg logit contributions
 Howell-1.224
 Birch-1.062
 Clarkson-1.059
 JJ-1.020
 Hendricks-0.978
Token]
Token ID60
Feature activation-1.21e-01

Pos logit contributions
phe+0.505
ū+0.480
aug+0.473
Ur+0.471
UG+0.441
Neg logit contributions
 Howell-1.059
 Birch-0.945
 Clarkson-0.943
 JJ-0.915
 Hendricks-0.880
Token Best
Token ID6705
Feature activation-1.41e-01

Pos logit contributions
 Howell+1.084
 Birch+0.939
 Clarkson+0.936
 JJ+0.897
 Hendricks+0.854
Neg logit contributions
phe-0.916
ū-0.882
Ur-0.875
aug-0.871
UG-0.834
Token Buy
Token ID11763
Feature activation-7.07e-04

Pos logit contributions
 Howell+1.280
 Birch+1.114
 Clarkson+1.110
 JJ+1.067
 Hendricks+1.017
Neg logit contributions
phe-1.051
ū-1.012
aug-0.997
Ur-0.994
kus-0.953
Token and
Token ID290
Feature activation-6.07e-01

Pos logit contributions
 Howell+1.632
 Birch+1.414
 Clarkson+1.410
 JJ+1.350
 Hendricks+1.285
Neg logit contributions
phe-1.411
ū-1.368
Ur-1.345
aug-1.344
kus-1.287
Token metal
Token ID6147
Feature activation+1.34e-01

Pos logit contributions
 Howell+5.606
 Birch+4.910
 Clarkson+4.882
 JJ+4.732
 Hendricks+4.465
Neg logit contributions
phe-4.348
ū-4.210
aug-4.149
Ur-4.116
UG-3.928
Token,
Token ID11
Feature activation-3.20e-02

Pos logit contributions
phe+0.992
ū+0.965
Ur+0.947
aug+0.945
UG+0.910
Neg logit contributions
 Howell-1.210
 Birch-1.050
 Clarkson-1.050
 JJ-0.995
 Hendricks-0.959
Token sing
Token ID1702
Feature activation+4.30e-02

Pos logit contributions
 Howell+0.282
 Birch+0.244
 Clarkson+0.243
 JJ+0.233
 Hendricks+0.222
Neg logit contributions
phe-0.244
ū-0.236
aug-0.232
Ur-0.232
kus-0.223
Tokenly
Token ID306
Feature activation+3.39e-02

Pos logit contributions
phe+0.228
ū+0.218
aug+0.213
Ur+0.212
kus+0.200
Neg logit contributions
 Howell-0.479
 Birch-0.432
 Clarkson-0.427
 JJ-0.415
 Hendricks-0.400
Token or
Token ID393
Feature activation-8.18e-01

Pos logit contributions
phe+0.248
ū+0.240
aug+0.236
Ur+0.230
kus+0.227
Neg logit contributions
 Howell-0.313
 Birch-0.273
 Clarkson-0.270
 JJ-0.260
 Hendricks-0.249
Token in
Token ID287
Feature activation-3.59e-01

Pos logit contributions
 Howell+6.592
 Clarkson+5.613
 Birch+5.591
 JJ+5.454
 Hendricks+5.103
Neg logit contributions
phe-6.629
ū-6.435
aug-6.408
Ur-6.360
UG-6.078
Token combination
Token ID6087
Feature activation-2.40e-01

Pos logit contributions
 Howell+3.115
 Birch+2.690
 Clarkson+2.686
 JJ+2.583
 Hendricks+2.442
Neg logit contributions
phe-2.794
ū-2.701
aug-2.658
Ur-2.658
kus-2.542
Token,
Token ID11
Feature activation-4.47e-02

Pos logit contributions
 Howell+2.204
 Birch+1.924
 Clarkson+1.919
 JJ+1.846
 Hendricks+1.757
Neg logit contributions
phe-1.755
ū-1.690
aug-1.666
Ur-1.662
kus-1.586
Token every
Token ID790
Feature activation-3.15e-01

Pos logit contributions
 Howell+0.381
 Birch+0.327
 Clarkson+0.326
 JJ+0.311
 Hendricks+0.297
Neg logit contributions
phe-0.355
ū-0.344
aug-0.339
Ur-0.337
kus-0.324
Token Monday
Token ID3321
Feature activation-1.84e-01

Pos logit contributions
 Howell+2.872
 Birch+2.508
 Clarkson+2.497
 JJ+2.405
 Hendricks+2.285
Neg logit contributions
phe-2.318
ū-2.233
aug-2.204
Ur-2.193
kus-2.093
Token
Token ID447
Feature activation+5.47e-02

Pos logit contributions
 Howell+1.161
 Birch+1.015
 Clarkson+1.012
 JJ+0.974
 Hendricks+0.930
Neg logit contributions
phe-0.872
ū-0.842
aug-0.826
Ur-0.826
UG-0.784
Token
Token ID247
Feature activation-1.15e-02

Pos logit contributions
phe+0.243
ū+0.237
Ur+0.226
aug+0.225
ogo+0.206
Neg logit contributions
 Howell-0.655
 Birch-0.593
 Clarkson-0.589
 JJ-0.569
 Hendricks-0.554
Token?
Token ID30
Feature activation-2.47e-01

Pos logit contributions
 Howell+0.108
 Birch+0.095
 Clarkson+0.094
 JJ+0.091
 Hendricks+0.087
Neg logit contributions
phe-0.082
ū-0.079
aug-0.078
Ur-0.078
UG-0.074
Token
Token ID198
Feature activation-8.67e-02

Pos logit contributions
 Howell+2.110
 Birch+1.819
 Clarkson+1.814
 JJ+1.738
 Hendricks+1.647
Neg logit contributions
phe-1.962
ū-1.898
aug-1.871
Ur-1.869
kus-1.790
Token
Token ID198
Feature activation-1.39e-01

Pos logit contributions
 Howell+0.673
 Clarkson+0.575
 Birch+0.573
 JJ+0.548
 Hendricks+0.515
Neg logit contributions
phe-0.753
ū-0.728
Ur-0.712
aug-0.711
anamo-0.699
Tokenand
Token ID392
Feature activation-8.13e-01

Pos logit contributions
 Howell+1.435
 Birch+1.271
 Clarkson+1.268
 JJ+1.226
 Hendricks+1.175
Neg logit contributions
phe-0.859
ū-0.823
aug-0.808
Ur-0.807
kus-0.762
Token how
Token ID703
Feature activation-4.07e-01

Pos logit contributions
 Howell+5.732
 Birch+4.787
 Clarkson+4.695
 JJ+4.623
 Hendricks+4.226
Neg logit contributions
phe-7.368
ū-7.146
aug-7.106
Ur-7.094
anamo-6.885
Token does
Token ID857
Feature activation-5.58e-01

Pos logit contributions
 Howell+3.739
 Clarkson+3.256
 Birch+3.246
 JJ+3.146
 Hendricks+2.978
Neg logit contributions
phe-2.966
ū-2.841
Ur-2.807
aug-2.796
kus-2.684
Token it
Token ID340
Feature activation-4.15e-01

Pos logit contributions
 Howell+3.903
 Birch+3.304
 Clarkson+3.231
 JJ+3.133
 Hendricks+2.850
Neg logit contributions
phe-5.274
ū-4.980
anamo-4.948
aug-4.943
Ur-4.924
Token look
Token ID804
Feature activation-5.29e-01

Pos logit contributions
 Howell+2.813
 Clarkson+2.334
 Birch+2.303
 JJ+2.243
 Hendricks+2.004
Neg logit contributions
phe-3.988
ū-3.860
Ur-3.841
aug-3.807
anamo-3.783
Token from
Token ID422
Feature activation-4.05e-01

Pos logit contributions
 Howell+4.064
 Clarkson+3.449
 Birch+3.441
 JJ+3.269
 Hendricks+3.078
Neg logit contributions
phe-4.586
ū-4.418
aug-4.404
Ur-4.356
anamo-4.335
Token the
Token ID262
Feature activation-2.46e-01

Pos logit contributions
 Howell+1.198
 Birch+1.039
 Clarkson+1.032
 JJ+0.993
 Hendricks+0.940
Neg logit contributions
phe-1.094
ū-1.056
Ur-1.041
aug-1.036
UG-0.993
Token flow
Token ID5202
Feature activation-2.83e-01

Pos logit contributions
 Howell+2.051
 Birch+1.762
 Clarkson+1.755
 JJ+1.682
 Hendricks+1.590
Neg logit contributions
phe-2.002
ū-1.939
aug-1.911
Ur-1.910
kus-1.831
Token of
Token ID286
Feature activation-4.81e-01

Pos logit contributions
 Howell+2.473
 Birch+2.141
 Clarkson+2.135
 JJ+2.050
 Hendricks+1.944
Neg logit contributions
phe-2.191
ū-2.120
aug-2.094
Ur-2.086
kus-2.000
Token on
Token ID319
Feature activation-3.99e-01

Pos logit contributions
 Howell+3.874
 Clarkson+3.310
 Birch+3.301
 JJ+3.163
 Hendricks+2.986
Neg logit contributions
phe-4.061
ū-3.908
aug-3.881
Ur-3.853
kus-3.740
Tokencoming
Token ID4976
Feature activation-4.08e-01

Pos logit contributions
 Howell+3.292
 Birch+2.829
 Clarkson+2.814
 JJ+2.687
 Hendricks+2.547
Neg logit contributions
phe-3.271
ū-3.168
Ur-3.121
aug-3.120
kus-3.003
Token cars
Token ID5006
Feature activation-8.06e-01

Pos logit contributions
 Howell+3.057
 Birch+2.571
 Clarkson+2.570
 JJ+2.451
 Hendricks+2.294
Neg logit contributions
phe-3.686
ū-3.558
aug-3.523
Ur-3.510
kus-3.398
Token and
Token ID290
Feature activation-5.02e-01

Pos logit contributions
 Howell+6.294
 Clarkson+5.416
 Birch+5.334
 JJ+5.178
 Hendricks+4.888
Neg logit contributions
phe-6.650
aug-6.412
ū-6.398
Ur-6.350
kus-6.250
Token pedestrians
Token ID26735
Feature activation-4.86e-01

Pos logit contributions
 Howell+4.369
 Clarkson+3.764
 Birch+3.764
 JJ+3.612
 Hendricks+3.425
Neg logit contributions
phe-3.876
ū-3.754
aug-3.727
Ur-3.684
kus-3.548
Token to
Token ID284
Feature activation-3.68e-01

Pos logit contributions
 Howell+4.186
 Clarkson+3.607
 Birch+3.601
 JJ+3.472
 Hendricks+3.279
Neg logit contributions
phe-3.776
ū-3.643
aug-3.612
Ur-3.603
kus-3.493
Token make
Token ID787
Feature activation-4.70e-02

Pos logit contributions
 Howell+3.227
 Birch+2.791
 Clarkson+2.786
 JJ+2.674
 Hendricks+2.534
Neg logit contributions
phe-2.847
ū-2.748
aug-2.711
Ur-2.702
kus-2.586
Token a
Token ID257
Feature activation+2.48e-02

Pos logit contributions
 Howell+0.394
 Birch+0.342
 Clarkson+0.338
 JJ+0.325
 Hendricks+0.308
Neg logit contributions
phe-0.376
ū-0.366
Ur-0.360
aug-0.359
kus-0.343
Token
Token ID198
Feature activation-2.24e-01

Pos logit contributions
 Howell+1.811
 Birch+1.562
 Clarkson+1.559
 JJ+1.492
 Hendricks+1.417
Neg logit contributions
phe-1.648
ū-1.595
aug-1.572
Ur-1.571
kus-1.502
Token
Token ID198
Feature activation-2.72e-01

Pos logit contributions
 Howell+1.672
 Clarkson+1.426
 Birch+1.415
 JJ+1.355
 Hendricks+1.266
Neg logit contributions
phe-2.005
ū-1.942
anamo-1.896
Ur-1.889
aug-1.888
Token(
Token ID7
Feature activation-5.88e-01

Pos logit contributions
 Howell+2.837
 Birch+2.522
 Clarkson+2.512
 JJ+2.434
 Hendricks+2.328
Neg logit contributions
phe-1.623
ū-1.554
aug-1.516
Ur-1.513
kus-1.437
Tokeni
Token ID72
Feature activation-4.07e-01

Pos logit contributions
 Howell+5.367
 Birch+4.692
 Clarkson+4.690
 JJ+4.528
 Hendricks+4.294
Neg logit contributions
phe-4.152
ū-4.001
aug-3.906
Ur-3.886
kus-3.741
Token.
Token ID13
Feature activation-1.45e-01

Pos logit contributions
 Howell+3.254
 Clarkson+2.807
 Birch+2.805
 JJ+2.693
 Hendricks+2.545
Neg logit contributions
phe-3.362
ū-3.181
anamo-3.175
aug-3.114
Ur-3.101
Tokene
Token ID68
Feature activation-7.82e-01

Pos logit contributions
 Howell+1.232
 Clarkson+1.062
 Birch+1.057
 JJ+1.012
 Hendricks+0.967
Neg logit contributions
phe-1.127
ū-1.090
Ur-1.076
aug-1.066
anamo-1.051
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
 Howell+5.770
 Birch+5.005
 Clarkson+4.974
 JJ+4.696
 Hendricks+4.471
Neg logit contributions
phe-6.557
anamo-6.387
ū-6.301
Ur-6.199
aug-6.158
Token is
Token ID318
Feature activation-4.53e-01

Pos logit contributions
 Howell+1.229
 Clarkson+1.061
 Birch+1.058
 JJ+1.016
 Hendricks+0.967
Neg logit contributions
phe-1.070
ū-1.041
Ur-1.020
aug-1.019
kus-0.971
Token the
Token ID262
Feature activation-3.04e-01

Pos logit contributions
 Howell+3.588
 Birch+3.101
 Clarkson+3.052
 JJ+2.969
 Hendricks+2.754
Neg logit contributions
phe-3.824
aug-3.610
Ur-3.602
ū-3.592
anamo-3.577
Token syntax
Token ID15582
Feature activation+5.30e-02

Pos logit contributions
 Howell+2.425
 Birch+2.113
 Clarkson+2.084
 JJ+2.010
 Hendricks+1.893
Neg logit contributions
phe-2.571
aug-2.460
Ur-2.449
ū-2.443
kus-2.372
Token just
Token ID655
Feature activation+8.72e-03

Pos logit contributions
phe+0.423
ū+0.405
Ur+0.401
aug+0.401
UG+0.383
Neg logit contributions
 Howell-0.454
 Birch-0.393
 Clarkson-0.391
 JJ-0.376
 Hendricks-0.355
Token to
Token ID284
Feature activation-7.28e-03

Pos logit contributions
phe+1.192
ū+1.160
Ur+1.139
aug+1.135
UG+1.093
Neg logit contributions
 Howell-1.388
 Birch-1.211
 Clarkson-1.201
 JJ-1.148
 Hendricks-1.099
Token behave
Token ID17438
Feature activation+2.87e-01

Pos logit contributions
 Howell+0.064
 Birch+0.055
 Clarkson+0.055
 JJ+0.052
 Hendricks+0.050
Neg logit contributions
phe-0.056
ū-0.054
Ur-0.054
aug-0.053
kus-0.052
Token properly
Token ID6105
Feature activation+1.93e-01

Pos logit contributions
phe+2.183
ū+2.137
Ur+2.112
aug+2.092
UG+2.028
Neg logit contributions
 Howell-2.452
 Birch-2.142
 Clarkson-2.102
 JJ-2.027
 Hendricks-1.941
Token.
Token ID13
Feature activation-6.43e-02

Pos logit contributions
phe+1.396
ū+1.360
aug+1.330
Ur+1.330
UG+1.282
Neg logit contributions
 Howell-1.760
 Birch-1.536
 Clarkson-1.524
 JJ-1.467
 Hendricks-1.402
Token<|endoftext|>
Token ID50256
Feature activation-1.85e-01

Pos logit contributions
 Howell+0.590
 Birch+0.514
 Clarkson+0.513
 JJ+0.493
 Hendricks+0.469
Neg logit contributions
phe-0.469
ū-0.453
Ur-0.446
aug-0.446
UG-0.425
Tokenby
Token ID1525
Feature activation-7.81e-01

Pos logit contributions
 Howell+1.981
 Birch+1.763
 Clarkson+1.758
 JJ+1.702
 Hendricks+1.633
Neg logit contributions
phe-1.075
ū-1.027
aug-1.007
Ur-1.006
kus-0.946
Token Erik
Token ID22722
Feature activation+1.57e-01

Pos logit contributions
 Howell+6.610
 Birch+5.697
 Clarkson+5.677
 JJ+5.524
 Hendricks+5.144
Neg logit contributions
phe-6.131
ū-5.841
aug-5.829
Ur-5.761
kus-5.585
Token Alt
Token ID12344
Feature activation+8.86e-02

Pos logit contributions
phe+1.217
ū+1.179
aug+1.161
Ur+1.157
kus+1.109
Neg logit contributions
 Howell-1.337
 Clarkson-1.156
 Birch-1.149
 JJ-1.113
 Hendricks-1.040
Tokenieri
Token ID29864
Feature activation+3.10e-01

Pos logit contributions
phe+0.889
ū+0.874
aug+0.865
ura+0.843
kus+0.842
Neg logit contributions
 Howell-0.579
 Birch-0.467
 Clarkson-0.464
 JJ-0.439
 Hendricks-0.400
Token,
Token ID11
Feature activation-1.27e-01

Pos logit contributions
phe+2.193
ū+2.185
aug+2.138
Ur+2.094
UG+2.043
Neg logit contributions
 Howell-2.810
 Birch-2.445
 Clarkson-2.419
 JJ-2.324
 Hendricks-2.226
Token NOR
Token ID25273
Feature activation-1.23e-01

Pos logit contributions
 Howell+1.116
 Birch+0.965
 Clarkson+0.962
 JJ+0.922
 Hendricks+0.878
Neg logit contributions
phe-0.971
ū-0.938
aug-0.925
Ur-0.924
kus-0.884
Token by
Token ID416
Feature activation-2.97e-01

Pos logit contributions
phe+0.038
ū+0.037
aug+0.037
Ur+0.037
UG+0.035
Neg logit contributions
 Howell-0.044
 Birch-0.038
 Clarkson-0.038
 JJ-0.037
 Hendricks-0.035
Token |
Token ID930
Feature activation-1.80e-01

Pos logit contributions
 Howell+2.575
 Birch+2.227
 Clarkson+2.218
 JJ+2.132
 Hendricks+2.017
Neg logit contributions
phe-2.326
ū-2.247
aug-2.215
Ur-2.212
kus-2.119
Token in
Token ID287
Feature activation-1.80e-01

Pos logit contributions
 Howell+1.560
 Birch+1.349
 Clarkson+1.344
 JJ+1.289
 Hendricks+1.222
Neg logit contributions
phe-1.405
ū-1.361
aug-1.342
Ur-1.340
UG-1.281
Token
Token ID198
Feature activation-2.17e-01

Pos logit contributions
 Howell+1.636
 Birch+1.424
 Clarkson+1.420
 JJ+1.365
 Hendricks+1.298
Neg logit contributions
phe-1.339
ū-1.292
aug-1.272
Ur-1.271
kus-1.213
Token
Token ID198
Feature activation-2.84e-01

Pos logit contributions
 Howell+1.636
 Clarkson+1.393
 Birch+1.381
 JJ+1.325
 Hendricks+1.244
Neg logit contributions
phe-1.921
ū-1.860
aug-1.812
anamo-1.805
Ur-1.797
Token|
Token ID91
Feature activation-7.81e-01

Pos logit contributions
 Howell+3.001
 Clarkson+2.666
 Birch+2.665
 JJ+2.582
 Hendricks+2.473
Neg logit contributions
phe-1.652
ū-1.580
aug-1.539
Ur-1.523
kus-1.456
Token in
Token ID287
Feature activation-2.65e-01

Pos logit contributions
 Howell+7.029
 Birch+6.114
 Clarkson+6.113
 JJ+5.926
 Hendricks+5.562
Neg logit contributions
phe-5.642
ū-5.337
Ur-5.306
aug-5.251
kus-5.100
Token babys
Token ID46711
Feature activation-9.89e-02

Pos logit contributions
 Howell+2.401
 Birch+2.090
 Clarkson+2.083
 JJ+2.004
 Hendricks+1.905
Neg logit contributions
phe-1.964
ū-1.894
aug-1.864
Ur-1.863
kus-1.780
Tokenitting
Token ID2535
Feature activation-3.07e-01

Pos logit contributions
 Howell+1.005
 Birch+0.890
 Clarkson+0.885
 JJ+0.856
 Hendricks+0.825
Neg logit contributions
phe-0.629
ū-0.607
aug-0.595
Ur-0.592
UG-0.561
Token
Token ID198
Feature activation-1.21e-01

Pos logit contributions
 Howell+2.857
 Birch+2.496
 Clarkson+2.489
 JJ+2.397
 Hendricks+2.279
Neg logit contributions
phe-2.210
ū-2.127
aug-2.095
Ur-2.092
kus-1.993
Token
Token ID198
Feature activation-6.03e-02

Pos logit contributions
 Howell+0.937
 Clarkson+0.798
 Birch+0.795
 JJ+0.762
 Hendricks+0.715
Neg logit contributions
phe-1.061
ū-1.025
Ur-1.002
aug-1.001
anamo-0.988
Token`
Token ID63
Feature activation-1.25e-01

Pos logit contributions
 Howell+1.278
 Birch+1.122
 Clarkson+1.118
 JJ+1.073
 Hendricks+1.030
Neg logit contributions
phe-0.906
ū-0.871
Ur-0.863
aug-0.857
UG-0.814
Token represent
Token ID2380
Feature activation-2.05e-01

Pos logit contributions
 Howell+1.104
 Birch+0.960
 Clarkson+0.956
 JJ+0.913
 Hendricks+0.871
Neg logit contributions
phe-0.956
ū-0.924
aug-0.913
Ur-0.912
UG-0.869
Tokenable
Token ID540
Feature activation-1.68e-01

Pos logit contributions
 Howell+1.847
 Birch+1.606
 Clarkson+1.601
 JJ+1.542
 Hendricks+1.462
Neg logit contributions
phe-1.532
ū-1.479
aug-1.455
Ur-1.453
kus-1.389
Token
Token ID198
Feature activation-9.50e-02

Pos logit contributions
 Howell+1.529
 Birch+1.332
 Clarkson+1.328
 JJ+1.277
 Hendricks+1.215
Neg logit contributions
phe-1.235
ū-1.192
aug-1.174
Ur-1.172
kus-1.119
Token
Token ID198
Feature activation-6.80e-03

Pos logit contributions
 Howell+0.731
 Clarkson+0.624
 Birch+0.622
 JJ+0.593
 Hendricks+0.557
Neg logit contributions
phe-0.834
ū-0.804
aug-0.787
Ur-0.784
anamo-0.777
Token:(
Token ID37498
Feature activation-7.76e-01

Pos logit contributions
 Howell+0.073
 Birch+0.065
 Clarkson+0.065
 JJ+0.063
 Hendricks+0.061
Neg logit contributions
phe-0.039
ū-0.037
Ur-0.037
aug-0.037
UG-0.034
Token
Token ID198
Feature activation-2.21e-01

Pos logit contributions
 Howell+7.730
 Birch+6.862
 Clarkson+6.821
 JJ+6.663
 Hendricks+6.287
Neg logit contributions
phe-4.757
ū-4.546
aug-4.382
Ur-4.339
kus-4.271
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
 Howell+1.635
 Clarkson+1.391
 Birch+1.384
 JJ+1.320
 Hendricks+1.234
Neg logit contributions
phe-1.984
ū-1.910
anamo-1.872
aug-1.863
Ur-1.858
TokenI
Token ID40
Feature activation-3.56e-03

Pos logit contributions
 Howell+1.401
 Birch+1.239
 Clarkson+1.235
 JJ+1.193
 Hendricks+1.142
Neg logit contributions
phe-0.877
ū-0.841
aug-0.826
Ur-0.825
kus-0.780
Token
Token ID447
Feature activation-1.78e-01

Pos logit contributions
 Howell+0.033
 Clarkson+0.028
 Birch+0.028
 JJ+0.027
 Hendricks+0.026
Neg logit contributions
phe-0.026
ū-0.025
Ur-0.025
aug-0.025
UG-0.024
Token
Token ID247
Feature activation-3.16e-01

Pos logit contributions
 Howell+2.205
 Birch+1.999
 Clarkson+1.984
 JJ+1.943
 Hendricks+1.870
Neg logit contributions
phe-0.738
ū-0.667
aug-0.661
Ur-0.652
kus-0.609
Tokeno
Token ID78
Feature activation+1.38e-01

Pos logit contributions
phe+0.487
ū+0.471
aug+0.458
Ur+0.454
kus+0.428
Neg logit contributions
 Howell-0.888
 Birch-0.792
 Clarkson-0.792
 JJ-0.763
 Hendricks-0.735
Token
Token ID198
Feature activation-1.26e-01

Pos logit contributions
phe+1.028
ū+1.004
Ur+0.978
aug+0.977
kus+0.935
Neg logit contributions
 Howell-1.244
 Birch-1.090
 Clarkson-1.085
 JJ-1.036
 Hendricks-0.993
Token
Token ID198
Feature activation-9.68e-02

Pos logit contributions
 Howell+0.977
 Clarkson+0.831
 Birch+0.829
 JJ+0.792
 Hendricks+0.745
Neg logit contributions
phe-1.104
ū-1.062
aug-1.043
Ur-1.039
anamo-1.031
Tokenko
Token ID7204
Feature activation+3.04e-04

Pos logit contributions
 Howell+1.030
 Birch+0.917
 Clarkson+0.914
 JJ+0.885
 Hendricks+0.849
Neg logit contributions
phe-0.566
ū-0.541
aug-0.530
Ur-0.530
kus-0.499
Token Kal
Token ID12612
Feature activation+5.52e-03

Pos logit contributions
phe+0.002
ū+0.002
aug+0.002
Ur+0.002
kus+0.002
Neg logit contributions
 Howell-0.003
 Birch-0.003
 Clarkson-0.002
 JJ-0.002
 Hendricks-0.002
Tokenan
Token ID272
Feature activation-7.69e-01

Pos logit contributions
phe+0.024
ū+0.022
aug+0.022
Ur+0.021
kus+0.020
Neg logit contributions
 Howell-0.068
 Birch-0.061
 Clarkson-0.061
 JJ-0.059
 Hendricks-0.057
Tokenial
Token ID498
Feature activation-3.43e-01

Pos logit contributions
 Howell+6.600
 Birch+5.713
 Clarkson+5.603
 JJ+5.557
 Hendricks+5.112
Neg logit contributions
phe-5.830
aug-5.456
Ur-5.415
ū-5.381
UG-5.294
Tokeni
Token ID72
Feature activation-2.89e-01

Pos logit contributions
 Howell+3.099
 Birch+2.692
 Clarkson+2.673
 JJ+2.589
 Hendricks+2.449
Neg logit contributions
phe-2.545
ū-2.439
aug-2.414
Ur-2.413
UG-2.311
Token
Token ID134
Feature activation-6.05e-02

Pos logit contributions
 Howell+3.126
 Birch+2.785
 Clarkson+2.775
 JJ+2.695
 Hendricks+2.583
Neg logit contributions
phe-1.632
ū-1.540
aug-1.517
Ur-1.516
kus-1.425
Token
Token ID119
Feature activation-2.58e-01

Pos logit contributions
 Howell+0.516
 Birch+0.449
 Clarkson+0.442
 JJ+0.426
 Hendricks+0.407
Neg logit contributions
phe-0.481
aug-0.455
ū-0.454
Ur-0.449
anamo-0.441
Tokenil
Token ID346
Feature activation+2.39e-01

Pos logit contributions
 Howell+2.924
 Birch+2.621
 Clarkson+2.608
 JJ+2.536
 Hendricks+2.437
Neg logit contributions
phe-1.323
ū-1.251
aug-1.226
Ur-1.224
kus-1.143
Tokend
Token ID67
Feature activation-2.76e-01

Pos logit contributions
 Howell+1.281
 Birch+1.106
 Clarkson+1.102
 JJ+1.056
 Hendricks+1.003
Neg logit contributions
phe-1.170
ū-1.131
aug-1.115
Ur-1.114
kus-1.067
Token up
Token ID510
Feature activation+3.12e-02

Pos logit contributions
 Howell+2.469
 Birch+2.143
 Clarkson+2.136
 JJ+2.052
 Hendricks+1.950
Neg logit contributions
phe-2.082
ū-2.013
aug-1.981
Ur-1.979
kus-1.891
Token,
Token ID11
Feature activation-1.56e-02

Pos logit contributions
phe+0.228
ū+0.222
Ur+0.217
aug+0.216
kus+0.208
Neg logit contributions
 Howell-0.286
 Birch-0.248
 Clarkson-0.247
 JJ-0.237
 Hendricks-0.226
Token aren
Token ID3588
Feature activation-2.16e-01

Pos logit contributions
 Howell+0.138
 Birch+0.119
 Clarkson+0.119
 JJ+0.113
 Hendricks+0.108
Neg logit contributions
phe-0.118
ū-0.114
Ur-0.113
aug-0.112
UG-0.108
Token't
Token ID470
Feature activation-5.67e-01

Pos logit contributions
 Howell+1.654
 Clarkson+1.406
 Birch+1.403
 JJ+1.346
 Hendricks+1.263
Neg logit contributions
phe-1.876
ū-1.818
Ur-1.777
aug-1.761
anamo-1.751
Token you
Token ID345
Feature activation-7.64e-01

Pos logit contributions
 Howell+5.146
 Birch+4.500
 Clarkson+4.475
 JJ+4.337
 Hendricks+4.092
Neg logit contributions
phe-4.084
ū-3.983
Ur-3.931
aug-3.906
UG-3.721
Token?
Token ID30
Feature activation-5.28e-02

Pos logit contributions
 Howell+6.574
 Birch+5.728
 Clarkson+5.652
 JJ+5.524
 Hendricks+5.161
Neg logit contributions
phe-5.823
ū-5.604
aug-5.546
Ur-5.495
anamo-5.283
Token Let
Token ID3914
Feature activation-1.89e-01

Pos logit contributions
 Howell+0.508
 Birch+0.444
 Clarkson+0.443
 JJ+0.426
 Hendricks+0.408
Neg logit contributions
phe-0.362
ū-0.348
Ur-0.344
aug-0.343
UG-0.327
Token's
Token ID338
Feature activation-2.46e-01

Pos logit contributions
 Howell+1.627
 Birch+1.404
 Clarkson+1.395
 JJ+1.335
 Hendricks+1.273
Neg logit contributions
phe-1.489
ū-1.443
aug-1.418
Ur-1.413
kus-1.360
Token try
Token ID1949
Feature activation-1.24e-01

Pos logit contributions
 Howell+2.212
 Birch+1.925
 Clarkson+1.919
 JJ+1.847
 Hendricks+1.753
Neg logit contributions
phe-1.836
ū-1.772
aug-1.744
Ur-1.742
kus-1.662
Token some
Token ID617
Feature activation-1.17e-02

Pos logit contributions
 Howell+1.091
 Birch+0.941
 Clarkson+0.939
 JJ+0.898
 Hendricks+0.854
Neg logit contributions
phe-0.951
ū-0.923
aug-0.912
Ur-0.907
UG-0.871
Token YouTube
Token ID7444
Feature activation+1.84e-01

Pos logit contributions
phe+1.068
ū+1.039
Ur+1.020
aug+1.020
UG+0.983
Neg logit contributions
 Howell-1.188
 Clarkson-1.022
 Birch-1.019
 JJ-0.971
 Hendricks-0.933
Token screen
Token ID3159
Feature activation+1.94e-01

Pos logit contributions
phe+0.877
ū+0.856
Ur+0.832
aug+0.830
UG+0.773
Neg logit contributions
 Howell-2.119
 Birch-1.899
 Clarkson-1.895
 JJ-1.840
 Hendricks-1.780
Token grab
Token ID5552
Feature activation+1.38e-01

Pos logit contributions
phe+1.003
ū+0.981
aug+0.958
Ur+0.941
UG+0.881
Neg logit contributions
 Howell-2.183
 Birch-1.955
 Clarkson-1.924
 JJ-1.869
 Hendricks-1.811
Token]
Token ID60
Feature activation-2.83e-01

Pos logit contributions
phe+0.704
ū+0.678
aug+0.666
Ur+0.661
UG+0.620
Neg logit contributions
 Howell-1.562
 Birch-1.394
 Clarkson-1.392
 JJ-1.349
 Hendricks-1.301
Token<|endoftext|>
Token ID50256
Feature activation-1.51e-01

Pos logit contributions
 Howell+2.707
 Birch+2.377
 Clarkson+2.368
 JJ+2.284
 Hendricks+2.178
Neg logit contributions
phe-1.952
ū-1.872
aug-1.841
Ur-1.838
kus-1.757
Token(
Token ID7
Feature activation-7.63e-01

Pos logit contributions
 Howell+1.615
 Birch+1.437
 Clarkson+1.433
 JJ+1.388
 Hendricks+1.331
Neg logit contributions
phe-0.878
ū-0.839
aug-0.823
Ur-0.823
kus-0.773
TokenUpdated
Token ID17354
Feature activation-2.42e-01

Pos logit contributions
 Howell+7.964
 Birch+7.085
 Clarkson+7.081
 JJ+6.852
 Hendricks+6.562
Neg logit contributions
phe-4.397
ū-4.158
aug-4.027
Ur-3.963
kus-3.851
Token below
Token ID2174
Feature activation+6.71e-02

Pos logit contributions
 Howell+2.127
 Birch+1.841
 Clarkson+1.837
 JJ+1.763
 Hendricks+1.670
Neg logit contributions
phe-1.864
ū-1.798
aug-1.771
Ur-1.769
kus-1.694
Token)
Token ID8
Feature activation-2.76e-01

Pos logit contributions
phe+0.467
ū+0.451
aug+0.444
Ur+0.444
UG+0.424
Neg logit contributions
 Howell-0.635
 Birch-0.556
 Clarkson-0.553
 JJ-0.532
 Hendricks-0.509
Token
Token ID198
Feature activation-5.49e-01

Pos logit contributions
 Howell+2.454
 Birch+2.129
 Clarkson+2.122
 JJ+2.037
 Hendricks+1.935
Neg logit contributions
phe-2.095
ū-2.025
Ur-1.996
aug-1.995
UG-1.903
Token
Token ID198
Feature activation-4.25e-01

Pos logit contributions
 Howell+3.734
 Clarkson+3.165
 Birch+3.114
 JJ+2.978
 Hendricks+2.781
Neg logit contributions
phe-5.083
anamo-4.941
ū-4.898
aug-4.760
trak-4.727
Token 333
Token ID23460
Feature activation-3.64e-01

Pos logit contributions
 Howell+2.152
 Birch+1.662
 Clarkson+1.597
 JJ+1.497
 Gad+1.415
Neg logit contributions
phe-4.339
ū-4.335
Ur-4.212
aug-4.160
trak-4.048
Token 68
Token ID8257
Feature activation-2.15e-01

Pos logit contributions
 Howell+2.871
 Birch+2.499
 Clarkson+2.368
 JJ+2.356
 Gad+2.210
Neg logit contributions
phe-3.082
ū-2.998
Ur-2.969
aug-2.946
kus-2.836
Token46
Token ID3510
Feature activation-2.79e-01

Pos logit contributions
 Howell+2.137
 Birch+1.888
 Clarkson+1.877
 JJ+1.803
 Hendricks+1.734
Neg logit contributions
phe-1.415
ū-1.362
Ur-1.320
aug-1.316
kus-1.255
Token.
Token ID13
Feature activation+6.19e-02

Pos logit contributions
 Howell+2.479
 Birch+2.172
 Clarkson+2.153
 JJ+2.062
 Hendricks+1.952
Neg logit contributions
phe-2.105
ū-2.042
Ur-2.008
aug-1.994
kus-1.911
Token<|endoftext|>
Token ID50256
Feature activation-1.30e-01

Pos logit contributions
phe+0.450
ū+0.434
aug+0.428
Ur+0.427
kus+0.407
Neg logit contributions
 Howell-0.570
 Birch-0.497
 Clarkson-0.495
 JJ-0.478
 Hendricks-0.454
Token(
Token ID7
Feature activation-7.61e-01

Pos logit contributions
 Howell+1.395
 Birch+1.242
 Clarkson+1.238
 JJ+1.198
 Hendricks+1.150
Neg logit contributions
phe-0.760
ū-0.726
Ur-0.713
aug-0.713
UG-0.669
TokenFIL
Token ID46700
Feature activation-3.28e-01

Pos logit contributions
 Howell+7.927
 Birch+7.046
 Clarkson+7.038
 JJ+6.814
 Hendricks+6.525
Neg logit contributions
phe-4.396
ū-4.161
aug-4.023
Ur-3.961
kus-3.856
TokenES
Token ID1546
Feature activation+1.94e-01

Pos logit contributions
 Howell+3.327
 Birch+2.942
 Clarkson+2.934
 JJ+2.834
 Hendricks+2.712
Neg logit contributions
phe-2.077
ū-1.992
aug-1.955
Ur-1.953
kus-1.848
Token)
Token ID8
Feature activation+7.43e-02

Pos logit contributions
phe+1.439
ū+1.399
Ur+1.373
aug+1.371
UG+1.345
Neg logit contributions
 Howell-1.731
 Birch-1.507
 Clarkson-1.495
 JJ-1.411
 Hendricks-1.358
TokenUS
Token ID2937
Feature activation-2.79e-01

Pos logit contributions
phe+0.560
ū+0.543
Ur+0.537
aug+0.532
UG+0.515
Neg logit contributions
 Howell-0.658
 Birch-0.570
 Clarkson-0.568
 JJ-0.542
 Hendricks-0.517
Token Treasury
Token ID13419
Feature activation-2.05e-01

Pos logit contributions
 Howell+2.640
 Birch+2.312
 Clarkson+2.305
 JJ+2.219
 Hendricks+2.116
Neg logit contributions
phe-1.960
ū-1.892
aug-1.860
Ur-1.858
UG-1.771
Token hard
Token ID1327
Feature activation+2.32e-02

Pos logit contributions
 Howell+2.184
 Birch+1.893
 Clarkson+1.883
 JJ+1.809
 Hendricks+1.719
Neg logit contributions
phe-1.872
ū-1.811
aug-1.783
Ur-1.782
kus-1.703
Token work
Token ID670
Feature activation-1.06e-01

Pos logit contributions
phe+0.150
ū+0.146
Ur+0.140
aug+0.140
kus+0.137
Neg logit contributions
 Howell-0.235
 Birch-0.206
 Clarkson-0.205
 JJ-0.194
 Hendricks-0.190
Token,
Token ID11
Feature activation-3.00e-01

Pos logit contributions
 Howell+0.961
 Birch+0.836
 Clarkson+0.828
 JJ+0.794
 Hendricks+0.758
Neg logit contributions
phe-0.794
ū-0.771
aug-0.758
Ur-0.757
kus-0.724
Token leadership
Token ID5531
Feature activation-1.25e-01

Pos logit contributions
 Howell+2.563
 Birch+2.208
 Clarkson+2.197
 JJ+2.105
 Hendricks+1.996
Neg logit contributions
phe-2.381
ū-2.305
aug-2.272
Ur-2.269
kus-2.175
Token and
Token ID290
Feature activation-1.60e-01

Pos logit contributions
 Howell+1.126
 Birch+0.979
 Clarkson+0.969
 JJ+0.929
 Hendricks+0.890
Neg logit contributions
phe-0.927
ū-0.901
Ur-0.888
aug-0.888
UG-0.846
Token (
Token ID357
Feature activation-7.60e-01

Pos logit contributions
 Howell+1.414
 Birch+1.223
 Clarkson+1.216
 JJ+1.165
 Hendricks+1.110
Neg logit contributions
phe-1.218
ū-1.179
aug-1.162
Ur-1.161
kus-1.112
Tokenare
Token ID533
Feature activation-2.38e-01

Pos logit contributions
 Howell+7.601
 Clarkson+6.813
 Birch+6.751
 JJ+6.607
 Hendricks+6.271
Neg logit contributions
phe-4.478
ū-4.319
aug-4.153
Ur-4.153
anamo-3.967
Token)
Token ID8
Feature activation-1.01e-01

Pos logit contributions
 Howell+2.217
 Birch+1.937
 Clarkson+1.929
 JJ+1.855
 Hendricks+1.767
Neg logit contributions
phe-1.718
ū-1.655
aug-1.633
Ur-1.627
kus-1.555
Token great
Token ID1049
Feature activation+4.00e-02

Pos logit contributions
 Howell+0.889
 Birch+0.772
 Clarkson+0.762
 JJ+0.729
 Hendricks+0.696
Neg logit contributions
phe-0.774
ū-0.749
aug-0.742
Ur-0.738
kus-0.711
Token characters
Token ID3435
Feature activation+1.35e-01

Pos logit contributions
phe+0.294
ū+0.288
aug+0.283
Ur+0.282
kus+0.271
Neg logit contributions
 Howell-0.361
 Birch-0.313
 Clarkson-0.310
 JJ-0.297
 Hendricks-0.284
Token,"
Token ID553
Feature activation-3.95e-03

Pos logit contributions
phe+0.966
ū+0.946
aug+0.933
Ur+0.919
UG+0.878
Neg logit contributions
 Howell-1.240
 Birch-1.085
 Clarkson-1.069
 JJ-1.016
 Hendricks-0.982
Tokentype
Token ID4906
Feature activation+1.54e-01

Pos logit contributions
 Howell+0.565
 Clarkson+0.500
 Birch+0.497
 JJ+0.474
 Hendricks+0.451
Neg logit contributions
phe-0.440
ū-0.426
Ur-0.419
aug-0.414
anamo-0.398
Token)
Token ID8
Feature activation-4.79e-02

Pos logit contributions
phe+1.142
ū+1.101
aug+1.083
Ur+1.082
kus+1.034
Neg logit contributions
 Howell-1.402
 Birch-1.222
 Clarkson-1.218
 JJ-1.171
 Hendricks-1.114
Token @
Token ID2488
Feature activation-2.49e-01

Pos logit contributions
 Howell+0.401
 Birch+0.347
 Clarkson+0.343
 JJ+0.329
 Hendricks+0.313
Neg logit contributions
phe-0.384
ū-0.373
Ur-0.368
aug-0.367
UG-0.353
Token 144
Token ID20224
Feature activation+6.48e-02

Pos logit contributions
 Howell+2.018
 Birch+1.726
 Clarkson+1.721
 JJ+1.645
 Hendricks+1.553
Neg logit contributions
phe-2.090
ū-2.029
aug-2.000
Ur-1.997
kus-1.916
TokenHz
Token ID7399
Feature activation-3.68e-01

Pos logit contributions
phe+0.326
ū+0.310
aug+0.302
Ur+0.301
kus+0.282
Neg logit contributions
 Howell-0.741
 Birch-0.664
 Clarkson-0.663
 JJ-0.641
 Hendricks-0.620
Token (
Token ID357
Feature activation-7.57e-01

Pos logit contributions
 Howell+3.269
 Birch+2.836
 Clarkson+2.826
 JJ+2.716
 Hendricks+2.580
Neg logit contributions
phe-2.801
ū-2.707
aug-2.665
Ur-2.662
kus-2.544
TokenOD
Token ID3727
Feature activation-2.01e-01

Pos logit contributions
 Howell+7.261
 Clarkson+6.472
 Birch+6.451
 JJ+6.185
 Hendricks+6.073
Neg logit contributions
phe-4.629
anamo-4.490
ū-4.470
aug-4.345
kus-4.171
Token =
Token ID796
Feature activation+7.29e-02

Pos logit contributions
 Howell+2.164
 Birch+1.929
 Clarkson+1.924
 JJ+1.862
 Hendricks+1.791
Neg logit contributions
phe-1.160
ū-1.104
Ur-1.086
aug-1.081
UG-1.022
Token Normal
Token ID14435
Feature activation-3.27e-02

Pos logit contributions
phe+0.570
ū+0.555
Ur+0.547
aug+0.543
UG+0.527
Neg logit contributions
 Howell-0.616
 Birch-0.537
 Clarkson-0.533
 JJ-0.510
 Hendricks-0.484
Token)
Token ID8
Feature activation-1.98e-01

Pos logit contributions
 Howell+0.307
 Birch+0.270
 Clarkson+0.269
 JJ+0.260
 Hendricks+0.250
Neg logit contributions
phe-0.233
ū-0.221
aug-0.217
Ur-0.217
UG-0.207
Token The
Token ID383
Feature activation+4.92e-02

Pos logit contributions
 Howell+1.722
 Birch+1.489
 Clarkson+1.478
 JJ+1.424
 Hendricks+1.353
Neg logit contributions
phe-1.537
ū-1.493
Ur-1.470
aug-1.468
UG-1.412
Token the
Token ID262
Feature activation+7.91e-02

Pos logit contributions
phe+1.262
ū+1.232
Ur+1.213
aug+1.208
kus+1.159
Neg logit contributions
 Howell-1.630
 Birch-1.416
 Clarkson-1.405
 JJ-1.357
 Hendricks-1.304
Token subjects
Token ID7481
Feature activation-2.29e-02

Pos logit contributions
phe+0.604
ū+0.589
Ur+0.580
aug+0.575
kus+0.554
Neg logit contributions
 Howell-0.693
 Birch-0.598
 Clarkson-0.596
 JJ-0.571
 Hendricks-0.546
Token featured
Token ID8096
Feature activation-7.02e-02

Pos logit contributions
 Howell+0.210
 Birch+0.183
 Clarkson+0.182
 JJ+0.176
 Hendricks+0.167
Neg logit contributions
phe-0.167
ū-0.161
Ur-0.158
aug-0.158
kus-0.151
Token in
Token ID287
Feature activation+9.75e-02

Pos logit contributions
 Howell+0.618
 Birch+0.535
 Clarkson+0.532
 JJ+0.510
 Hendricks+0.485
Neg logit contributions
phe-0.540
ū-0.524
Ur-0.515
aug-0.514
kus-0.492
Token the
Token ID262
Feature activation+1.74e-01

Pos logit contributions
phe+0.669
ū+0.650
aug+0.641
Ur+0.634
kus+0.606
Neg logit contributions
 Howell-0.931
 Birch-0.814
 Clarkson-0.806
 JJ-0.781
 Hendricks-0.749
Token images
Token ID4263
Feature activation+5.38e-01

Pos logit contributions
phe+1.254
ū+1.226
Ur+1.203
aug+1.197
kus+1.146
Neg logit contributions
 Howell-1.588
 Birch-1.379
 Clarkson-1.367
 JJ-1.318
 Hendricks-1.263
Token intended
Token ID5292
Feature activation-1.61e-01

Pos logit contributions
phe+3.464
ū+3.324
Ur+3.222
aug+3.217
ura+3.108
Neg logit contributions
 Howell-5.269
 Birch-4.645
 Clarkson-4.544
 JJ-4.384
 Hendricks-4.290
Token them
Token ID606
Feature activation+7.13e-02

Pos logit contributions
 Howell+1.348
 Birch+1.161
 Clarkson+1.152
 JJ+1.104
 Hendricks+1.046
Neg logit contributions
phe-1.300
ū-1.265
aug-1.246
Ur-1.244
kus-1.194
Token to
Token ID284
Feature activation-5.22e-02

Pos logit contributions
phe+0.549
ū+0.533
aug+0.526
Ur+0.520
kus+0.500
Neg logit contributions
 Howell-0.624
 Birch-0.546
 Clarkson-0.539
 JJ-0.521
 Hendricks-0.494
Token remain
Token ID3520
Feature activation+1.87e-01

Pos logit contributions
 Howell+0.510
 Birch+0.450
 Clarkson+0.446
 JJ+0.430
 Hendricks+0.412
Neg logit contributions
phe-0.350
ū-0.338
aug-0.332
Ur-0.331
kus-0.317
Token private
Token ID2839
Feature activation-3.18e-03

Pos logit contributions
phe+1.445
ū+1.415
Ur+1.400
aug+1.391
kus+1.329
Neg logit contributions
 Howell-1.600
 Birch-1.392
 Clarkson-1.374
 JJ-1.316
 Hendricks-1.262
Token had
Token ID550
Feature activation+1.03e-01

Pos logit contributions
phe+0.778
ū+0.759
aug+0.741
Ur+0.739
kus+0.705
Neg logit contributions
 Howell-0.906
 Birch-0.780
 Clarkson-0.780
 JJ-0.753
 Hendricks-0.710
Token not
Token ID407
Feature activation+1.14e-01

Pos logit contributions
phe+0.763
ū+0.745
Ur+0.731
aug+0.729
kus+0.696
Neg logit contributions
 Howell-0.918
 Birch-0.797
 Clarkson-0.795
 JJ-0.764
 Hendricks-0.723
Token been
Token ID587
Feature activation+2.21e-01

Pos logit contributions
phe+0.848
ū+0.825
aug+0.806
Ur+0.804
kus+0.769
Neg logit contributions
 Howell-1.026
 Birch-0.893
 Clarkson-0.886
 JJ-0.853
 Hendricks-0.813
Token captured
Token ID7907
Feature activation+1.43e-01

Pos logit contributions
phe+1.612
ū+1.562
Ur+1.535
aug+1.529
kus+1.464
Neg logit contributions
 Howell-2.002
 Birch-1.746
 Clarkson-1.728
 JJ-1.664
 Hendricks-1.581
Token but
Token ID475
Feature activation+3.66e-01

Pos logit contributions
phe+1.086
ū+1.059
Ur+1.035
aug+1.035
kus+0.989
Neg logit contributions
 Howell-1.265
 Birch-1.098
 Clarkson-1.090
 JJ-1.047
 Hendricks-0.995
Token rather
Token ID2138
Feature activation+5.84e-01

Pos logit contributions
phe+2.764
ū+2.694
aug+2.649
Ur+2.627
kus+2.507
Neg logit contributions
 Howell-3.162
 Birch-2.752
 Clarkson-2.738
 JJ-2.645
 Hendricks-2.465
Token walked
Token ID6807
Feature activation+1.79e-01

Pos logit contributions
phe+4.201
ū+4.113
aug+4.009
Ur+3.977
ogo+3.790
Neg logit contributions
 Howell-5.075
 Birch-4.455
 Clarkson-4.425
 JJ-4.286
 Hendricks-3.976
Token away
Token ID1497
Feature activation+2.93e-01

Pos logit contributions
phe+1.371
ū+1.342
Ur+1.304
aug+1.294
UG+1.243
Neg logit contributions
 Howell-1.557
 Birch-1.349
 Clarkson-1.339
 JJ-1.289
 Hendricks-1.216
Token from
Token ID422
Feature activation-1.20e-01

Pos logit contributions
phe+2.103
ū+2.057
Ur+2.018
aug+2.016
UG+1.908
Neg logit contributions
 Howell-2.676
 Birch-2.333
 Clarkson-2.308
 JJ-2.233
 Hendricks-2.113
Token his
Token ID465
Feature activation-5.03e-02

Pos logit contributions
 Howell+1.150
 Birch+1.009
 Clarkson+1.006
 JJ+0.969
 Hendricks+0.924
Neg logit contributions
phe-0.828
ū-0.797
aug-0.783
Ur-0.783
kus-0.744
Token unit
Token ID4326
Feature activation+1.19e-01

Pos logit contributions
 Howell+0.446
 Birch+0.386
 Clarkson+0.385
 JJ+0.370
 Hendricks+0.349
Neg logit contributions
phe-0.382
ū-0.371
Ur-0.364
aug-0.363
kus-0.349
Tokenbe
Token ID1350
Feature activation+2.01e-01

Pos logit contributions
 Howell+0.470
 Birch+0.418
 Clarkson+0.417
 JJ+0.403
 Hendricks+0.386
Neg logit contributions
phe-0.266
ū-0.253
aug-0.249
Ur-0.246
kus-0.236
Tokenek
Token ID988
Feature activation+4.27e-02

Pos logit contributions
phe+1.343
aug+1.299
ū+1.298
Ur+1.254
kus+1.224
Neg logit contributions
 Howell-1.940
 Birch-1.715
 Clarkson-1.694
 JJ-1.635
 Hendricks-1.575
Token.
Token ID13
Feature activation+3.11e-01

Pos logit contributions
phe+0.300
ū+0.291
aug+0.286
Ur+0.283
kus+0.273
Neg logit contributions
 Howell-0.401
 Birch-0.352
 Clarkson-0.351
 JJ-0.337
 Hendricks-0.323
Token<|endoftext|>
Token ID50256
Feature activation-1.19e-01

Pos logit contributions
ū+1.829
phe+1.822
Ur+1.805
aug+1.772
UG+1.697
Neg logit contributions
 Howell-3.143
 Birch-2.774
 Clarkson-2.742
 JJ-2.676
 Hendricks-2.574
TokenShare
Token ID11649
Feature activation-6.27e-01

Pos logit contributions
 Howell+1.272
 Birch+1.132
 Clarkson+1.129
 JJ+1.093
 Hendricks+1.048
Neg logit contributions
phe-0.694
ū-0.663
Ur-0.651
aug-0.650
UG-0.611
Token.
Token ID13
Feature activation+5.84e-01

Pos logit contributions
 Howell+5.426
 Birch+4.735
 Clarkson+4.733
 JJ+4.523
 Hendricks+4.296
Neg logit contributions
phe-4.738
ū-4.582
Ur-4.541
aug-4.522
kus-4.334
Token We
Token ID775
Feature activation-5.18e-03

Pos logit contributions
phe+4.232
Ur+4.106
aug+4.069
ū+4.039
UG+3.910
Neg logit contributions
 Howell-4.965
 Birch-4.262
 Clarkson-4.250
 JJ-3.994
 Hendricks-3.912
Token found
Token ID1043
Feature activation+1.51e-01

Pos logit contributions
 Howell+0.048
 Birch+0.042
 Clarkson+0.042
 JJ+0.040
 Hendricks+0.039
Neg logit contributions
phe-0.037
ū-0.036
aug-0.035
Ur-0.035
kus-0.034
Token a
Token ID257
Feature activation-1.75e-02

Pos logit contributions
phe+1.204
ū+1.171
aug+1.158
Ur+1.155
UG+1.109
Neg logit contributions
 Howell-1.252
 Birch-1.064
 Clarkson-1.064
 JJ-1.008
 Hendricks-0.969
Token home
Token ID1363
Feature activation+1.93e-01

Pos logit contributions
 Howell+0.156
 Birch+0.135
 Clarkson+0.134
 JJ+0.129
 Hendricks+0.123
Neg logit contributions
phe-0.133
ū-0.128
Ur-0.126
aug-0.126
kus-0.121
Token for
Token ID329
Feature activation-1.51e-01

Pos logit contributions
phe+1.445
ū+1.415
aug+1.403
Ur+1.392
kus+1.341
Neg logit contributions
 Howell-1.692
 Clarkson-1.463
 Birch-1.460
 JJ-1.385
 Hendricks-1.336
Token]
Token ID60
Feature activation+4.23e-01

Pos logit contributions
phe+1.214
Ur+1.093
ū+1.055
aug+1.043
]]+0.959
Neg logit contributions
 Howell-5.055
 Clarkson-4.631
 Birch-4.602
 JJ-4.474
 Hendricks-4.332
Token::
Token ID3712
Feature activation+5.10e-01

Pos logit contributions
phe+3.027
ū+2.905
Ur+2.893
aug+2.862
UG+2.737
Neg logit contributions
 Howell-3.916
 Birch-3.433
 Clarkson-3.400
 JJ-3.276
 Hendricks-3.114
TokenFrom
Token ID4863
Feature activation-4.81e-02

Pos logit contributions
phe+2.733
Ur+2.706
aug+2.500
ū+2.497
UG+2.488
Neg logit contributions
 Howell-5.463
 Clarkson-4.925
 Birch-4.855
 JJ-4.787
 Davies-4.552
TokenAr
Token ID3163
Feature activation+4.78e-02

Pos logit contributions
 Howell+0.513
 Clarkson+0.457
 Birch+0.456
 JJ+0.441
 Hendricks+0.422
Neg logit contributions
phe-0.281
Ur-0.269
ū-0.267
aug-0.264
UG-0.250
Tokengb
Token ID22296
Feature activation+3.62e-02

Pos logit contributions
phe+0.378
ū+0.365
Ur+0.362
aug+0.358
UG+0.344
Neg logit contributions
 Howell-0.405
 Birch-0.350
 Clarkson-0.347
 JJ-0.336
 Hendricks-0.316
Token($
Token ID16763
Feature activation+5.38e-01

Pos logit contributions
phe+0.288
ū+0.275
Ur+0.273
aug+0.271
UG+0.260
Neg logit contributions
 Howell-0.313
 Birch-0.270
 Clarkson-0.269
 JJ-0.257
 Hendricks-0.243
TokenFC
Token ID4851
Feature activation+4.55e-01

Pos logit contributions
phe+3.183
Ur+2.985
aug+2.950
ū+2.915
UG+2.857
Neg logit contributions
 Howell-5.652
 Clarkson-5.014
 Birch-4.953
 JJ-4.782
 Dalton-4.624
Token1
Token ID16
Feature activation+5.12e-01

Pos logit contributions
phe+2.198
Ur+2.065
ū+2.053
aug+2.030
UG+1.915
Neg logit contributions
 Howell-5.281
 Clarkson-4.760
 Birch-4.733
 JJ-4.580
 Hendricks-4.408
Token[
Token ID58
Feature activation+3.14e-01

Pos logit contributions
phe+2.848
ū+2.758
aug+2.688
Ur+2.665
UG+2.546
Neg logit contributions
 Howell-5.454
 Clarkson-4.861
 Birch-4.826
 JJ-4.682
 Hendricks-4.505
Token0
Token ID15
Feature activation+3.65e-01

Pos logit contributions
phe+1.662
Ur+1.565
aug+1.556
ū+1.546
UG+1.438
Neg logit contributions
 Howell-3.532
 Clarkson-3.151
 Birch-3.146
 JJ-3.033
 Dalton-2.911
Token],
Token ID4357
Feature activation+2.91e-01

Pos logit contributions
phe+1.417
ū+1.351
aug+1.321
Ur+1.310
kus+1.198
Neg logit contributions
 Howell-4.543
 Clarkson-4.120
 Birch-4.119
 JJ-3.989
 Hendricks-3.854
Token the
Token ID262
Feature activation+3.32e-01

Pos logit contributions
phe+2.330
ū+2.255
aug+2.230
Ur+2.213
kus+2.116
Neg logit contributions
 Howell-3.199
 Birch-2.802
 Clarkson-2.795
 JJ-2.672
 Hendricks-2.575
Token CG
Token ID29925
Feature activation+9.44e-02

Pos logit contributions
phe+2.396
ū+2.327
aug+2.293
Ur+2.288
UG+2.170
Neg logit contributions
 Howell-3.010
 Birch-2.607
 Clarkson-2.602
 JJ-2.495
 Hendricks-2.395
TokenPR
Token ID4805
Feature activation+2.16e-02

Pos logit contributions
phe+0.578
ū+0.556
Ur+0.553
aug+0.543
UG+0.516
Neg logit contributions
 Howell-0.980
 Birch-0.870
 Clarkson-0.867
 JJ-0.840
 Hendricks-0.805
TokenOG
Token ID7730
Feature activation+1.38e-01

Pos logit contributions
phe+0.123
ū+0.118
Ur+0.117
aug+0.116
UG+0.110
Neg logit contributions
 Howell-0.233
 Birch-0.209
 Clarkson-0.207
 JJ-0.200
 Hendricks-0.192
TokenRAM
Token ID24115
Feature activation+3.56e-02

Pos logit contributions
phe+0.984
Ur+0.947
ū+0.947
aug+0.920
UG+0.896
Neg logit contributions
 Howell-1.288
 Birch-1.128
 Clarkson-1.119
 JJ-1.074
 Hendricks-1.018
Token/
Token ID14
Feature activation+5.42e-01

Pos logit contributions
phe+0.246
ū+0.236
Ur+0.235
aug+0.232
UG+0.223
Neg logit contributions
 Howell-0.342
 Birch-0.299
 Clarkson-0.297
 JJ-0.287
 Hendricks-0.274
Token END
Token ID23578
Feature activation+3.70e-01

Pos logit contributions
phe+3.390
aug+3.222
ū+3.214
Ur+3.214
UG+3.038
Neg logit contributions
 Howell-5.473
 Birch-4.858
 Clarkson-4.835
 JJ-4.660
 Hendricks-4.481
TokenCG
Token ID39816
Feature activation-1.75e-02

Pos logit contributions
phe+2.371
ū+2.311
Ur+2.296
aug+2.269
UG+2.226
Neg logit contributions
 Howell-3.659
 Birch-3.220
 Clarkson-3.192
 JJ-3.061
 Hendricks-2.966
Token section
Token ID2665
Feature activation-5.95e-02

Pos logit contributions
 Howell+0.173
 Birch+0.153
 Clarkson+0.151
 JJ+0.146
 Hendricks+0.140
Neg logit contributions
phe-0.116
ū-0.112
Ur-0.111
aug-0.111
UG-0.106
Token!
Token ID0
Feature activation-1.91e-01

Pos logit contributions
 Howell+0.536
 Birch+0.465
 Clarkson+0.463
 JJ+0.445
 Hendricks+0.424
Neg logit contributions
phe-0.448
ū-0.433
aug-0.425
Ur-0.425
UG-0.405
Token):
Token ID2599
Feature activation-2.56e-02

Pos logit contributions
 Howell+1.562
 Birch+1.338
 Clarkson+1.332
 JJ+1.274
 Hendricks+1.204
Neg logit contributions
phe-1.590
ū-1.542
aug-1.520
Ur-1.519
kus-1.457
Token,"
Token ID553
Feature activation-4.34e-02

Pos logit contributions
phe+0.843
ū+0.820
aug+0.808
Ur+0.803
UG+0.766
Neg logit contributions
 Howell-1.101
 Birch-0.964
 Clarkson-0.956
 JJ-0.918
 Hendricks-0.878
Token he
Token ID339
Feature activation+1.83e-01

Pos logit contributions
 Howell+0.366
 Birch+0.316
 Clarkson+0.313
 JJ+0.303
 Hendricks+0.284
Neg logit contributions
phe-0.345
ū-0.332
aug-0.329
Ur-0.327
kus-0.315
Token said
Token ID531
Feature activation-5.91e-02

Pos logit contributions
phe+1.329
aug+1.291
ū+1.290
Ur+1.248
kus+1.221
Neg logit contributions
 Howell-1.649
 Birch-1.448
 Clarkson-1.418
 JJ-1.377
 Hendricks-1.305
Token.
Token ID13
Feature activation+1.48e-01

Pos logit contributions
 Howell+0.564
 Birch+0.496
 Clarkson+0.492
 JJ+0.475
 Hendricks+0.453
Neg logit contributions
phe-0.409
ū-0.395
aug-0.390
Ur-0.385
UG-0.369
Token
Token ID198
Feature activation-1.58e-02

Pos logit contributions
phe+1.200
ū+1.160
aug+1.148
Ur+1.138
kus+1.094
Neg logit contributions
 Howell-1.221
 Birch-1.049
 Clarkson-1.037
 JJ-1.004
 Hendricks-0.939
Token
Token ID198
Feature activation+5.26e-02

Pos logit contributions
 Howell+0.126
 Clarkson+0.108
 Birch+0.108
 JJ+0.103
 Hendricks+0.097
Neg logit contributions
phe-0.135
ū-0.130
aug-0.128
Ur-0.128
anamo-0.124
Token"
Token ID1
Feature activation-6.63e-02

Pos logit contributions
phe+0.310
ū+0.296
Ur+0.296
aug+0.293
UG+0.277
Neg logit contributions
 Howell-0.560
 Birch-0.499
 Clarkson-0.495
 JJ-0.482
 Hendricks-0.460
TokenWe
Token ID1135
Feature activation+4.00e-02

Pos logit contributions
 Howell+0.726
 Birch+0.649
 Clarkson+0.647
 JJ+0.627
 Hendricks+0.602
Neg logit contributions
phe-0.366
ū-0.349
Ur-0.343
aug-0.343
UG-0.321
Token're
Token ID821
Feature activation+8.11e-02

Pos logit contributions
phe+0.275
ū+0.265
aug+0.260
Ur+0.259
kus+0.248
Neg logit contributions
 Howell-0.384
 Birch-0.337
 Clarkson-0.336
 JJ-0.323
 Hendricks-0.310
Token a
Token ID257
Feature activation+6.91e-02

Pos logit contributions
phe+0.651
ū+0.628
aug+0.626
Ur+0.624
kus+0.600
Neg logit contributions
 Howell-0.673
 Birch-0.581
 Clarkson-0.575
 JJ-0.547
 Hendricks-0.522
Token little
Token ID1310
Feature activation+2.29e-01

Pos logit contributions
phe+0.480
ū+0.459
aug+0.451
Ur+0.450
kus+0.435
Neg logit contributions
 Howell-0.655
 Birch-0.575
 Clarkson-0.570
 JJ-0.550
 Hendricks-0.526
Token,
Token ID11
Feature activation+2.20e-01

Pos logit contributions
 Howell+0.167
 Birch+0.145
 Clarkson+0.145
 JJ+0.139
 Hendricks+0.132
Neg logit contributions
phe-0.137
ū-0.133
aug-0.131
Ur-0.131
kus-0.125
Token an
Token ID281
Feature activation+1.52e-02

Pos logit contributions
phe+1.608
ū+1.559
Ur+1.540
aug+1.535
UG+1.463
Neg logit contributions
 Howell-1.991
 Birch-1.740
 Clarkson-1.734
 JJ-1.665
 Hendricks-1.600
Token anti
Token ID3098
Feature activation+1.15e-01

Pos logit contributions
phe+0.114
ū+0.111
Ur+0.109
aug+0.109
kus+0.104
Neg logit contributions
 Howell-0.136
 Birch-0.119
 Clarkson-0.118
 JJ-0.113
 Hendricks-0.108
Token-
Token ID12
Feature activation+2.36e-01

Pos logit contributions
phe+0.702
ū+0.684
Ur+0.673
aug+0.672
kus+0.629
Neg logit contributions
 Howell-1.194
 Birch-1.060
 Clarkson-1.051
 JJ-1.023
 Hendricks-0.982
Tokenfascist
Token ID46928
Feature activation+5.38e-02

Pos logit contributions
phe+1.345
Ur+1.308
aug+1.295
ū+1.294
UG+1.225
Neg logit contributions
 Howell-2.551
 Birch-2.282
 Clarkson-2.252
 JJ-2.202
 Hendricks-2.130
Token activist
Token ID11276
Feature activation+1.22e-01

Pos logit contributions
phe+0.384
ū+0.375
Ur+0.368
aug+0.366
UG+0.350
Neg logit contributions
 Howell-0.497
 Birch-0.435
 Clarkson-0.433
 JJ-0.418
 Hendricks-0.399
Token,
Token ID11
Feature activation+1.30e-01

Pos logit contributions
phe+0.910
ū+0.887
Ur+0.868
aug+0.865
kus+0.826
Neg logit contributions
 Howell-1.091
 Birch-0.945
 Clarkson-0.944
 JJ-0.909
 Hendricks-0.865
Token was
Token ID373
Feature activation-2.44e-02

Pos logit contributions
phe+1.009
ū+0.981
Ur+0.967
aug+0.963
UG+0.919
Neg logit contributions
 Howell-1.125
 Birch-0.971
 Clarkson-0.970
 JJ-0.933
 Hendricks-0.883
Token released
Token ID2716
Feature activation+1.44e-01

Pos logit contributions
 Howell+0.243
 Birch+0.215
 Clarkson+0.214
 JJ+0.206
 Hendricks+0.197
Neg logit contributions
phe-0.159
ū-0.153
Ur-0.150
aug-0.150
kus-0.142
Token after
Token ID706
Feature activation+1.69e-01

Pos logit contributions
phe+1.080
ū+1.045
Ur+1.026
aug+1.025
UG+0.983
Neg logit contributions
 Howell-1.293
 Birch-1.124
 Clarkson-1.116
 JJ-1.070
 Hendricks-1.020
Token three
Token ID1115
Feature activation-2.43e-02

Pos logit contributions
phe+1.265
ū+1.228
Ur+1.210
aug+1.206
UG+1.161
Neg logit contributions
 Howell-1.506
 Clarkson-1.307
 Birch-1.305
 JJ-1.253
 Hendricks-1.186
Token stop
Token ID2245
Feature activation+5.48e-02

Pos logit contributions
 Howell+0.055
 Birch+0.048
 Clarkson+0.048
 JJ+0.046
 Hendricks+0.044
Neg logit contributions
phe-0.046
ū-0.045
Ur-0.044
aug-0.044
kus-0.042
Token Laura
Token ID16753
Feature activation-1.24e-03

Pos logit contributions
phe+0.387
ū+0.375
Ur+0.368
aug+0.368
UG+0.351
Neg logit contributions
 Howell-0.513
 Clarkson-0.448
 Birch-0.448
 JJ-0.429
 Hendricks-0.409
Token from
Token ID422
Feature activation-2.34e-02

Pos logit contributions
 Howell+0.012
 Birch+0.011
 Clarkson+0.010
 JJ+0.010
 Hendricks+0.010
Neg logit contributions
phe-0.009
ū-0.008
aug-0.008
Ur-0.008
UG-0.008
Token overwhelming
Token ID9721
Feature activation+1.47e-02

Pos logit contributions
 Howell+0.194
 Birch+0.167
 Clarkson+0.166
 JJ+0.158
 Hendricks+0.149
Neg logit contributions
phe-0.190
ū-0.186
aug-0.183
Ur-0.182
kus-0.175
Token them
Token ID606
Feature activation+2.11e-01

Pos logit contributions
phe+0.098
ū+0.095
aug+0.093
Ur+0.093
kus+0.088
Neg logit contributions
 Howell-0.144
 Birch-0.127
 Clarkson-0.127
 JJ-0.122
 Hendricks-0.116
Token quickly
Token ID2952
Feature activation+1.13e-01

Pos logit contributions
phe+1.433
ū+1.393
aug+1.367
Ur+1.359
UG+1.286
Neg logit contributions
 Howell-2.035
 Birch-1.783
 Clarkson-1.779
 JJ-1.704
 Hendricks-1.633
Token.
Token ID13
Feature activation+7.70e-03

Pos logit contributions
phe+0.790
ū+0.770
aug+0.752
Ur+0.750
UG+0.714
Neg logit contributions
 Howell-1.078
 Birch-0.946
 Clarkson-0.942
 JJ-0.908
 Hendricks-0.862
Token
Token ID198
Feature activation+5.89e-02

Pos logit contributions
phe+0.056
ū+0.055
Ur+0.054
aug+0.054
UG+0.051
Neg logit contributions
 Howell-0.070
 Birch-0.061
 Clarkson-0.061
 JJ-0.058
 Hendricks-0.055
Token
Token ID198
Feature activation-9.92e-02

Pos logit contributions
phe+0.497
ū+0.481
aug+0.472
Ur+0.471
kus+0.455
Neg logit contributions
 Howell-0.475
 Clarkson-0.407
 Birch-0.407
 JJ-0.388
 Hendricks-0.366
TokenLaura
Token ID43687
Feature activation+6.49e-02

Pos logit contributions
 Howell+1.059
 Birch+0.943
 Clarkson+0.940
 JJ+0.910
 Hendricks+0.872
Neg logit contributions
phe-0.579
ū-0.553
Ur-0.544
aug-0.543
kus-0.510
Token is
Token ID318
Feature activation-2.07e-02

Pos logit contributions
phe+0.443
ū+0.429
Ur+0.422
aug+0.421
kus+0.397
Neg logit contributions
 Howell-0.623
 Birch-0.547
 Clarkson-0.545
 JJ-0.528
 Hendricks-0.501
Token,
Token ID11
Feature activation-5.54e-02

Pos logit contributions
 Howell+2.313
 Birch+2.003
 Clarkson+1.998
 JJ+1.920
 Hendricks+1.818
Neg logit contributions
phe-2.023
ū-1.956
aug-1.929
Ur-1.924
kus-1.841
Token young
Token ID1862
Feature activation-5.28e-02

Pos logit contributions
 Howell+0.476
 Birch+0.413
 Clarkson+0.411
 JJ+0.393
 Hendricks+0.373
Neg logit contributions
phe-0.434
ū-0.420
Ur-0.414
aug-0.413
kus-0.396
Token human
Token ID1692
Feature activation-6.20e-03

Pos logit contributions
 Howell+0.481
 Birch+0.421
 Clarkson+0.418
 JJ+0.402
 Hendricks+0.384
Neg logit contributions
phe-0.388
ū-0.375
Ur-0.369
aug-0.368
kus-0.352
Token,
Token ID11
Feature activation+4.32e-03

Pos logit contributions
 Howell+0.055
 Birch+0.048
 Clarkson+0.047
 JJ+0.045
 Hendricks+0.043
Neg logit contributions
phe-0.047
ū-0.046
Ur-0.045
aug-0.045
kus-0.043
Token motor
Token ID5584
Feature activation+3.73e-02

Pos logit contributions
phe+0.034
ū+0.032
Ur+0.032
aug+0.032
kus+0.030
Neg logit contributions
 Howell-0.037
 Birch-0.033
 Clarkson-0.032
 JJ-0.031
 Hendricks-0.029
Tokenized
Token ID1143
Feature activation+4.90e-02

Pos logit contributions
phe+0.260
ū+0.250
aug+0.247
Ur+0.246
kus+0.235
Neg logit contributions
 Howell-0.353
 Birch-0.312
 Clarkson-0.310
 JJ-0.298
 Hendricks-0.286
Token wheelchair
Token ID27181
Feature activation-1.65e-01

Pos logit contributions
phe+0.368
ū+0.356
Ur+0.350
aug+0.349
kus+0.334
Neg logit contributions
 Howell-0.434
 Birch-0.380
 Clarkson-0.376
 JJ-0.361
 Hendricks-0.345
Token (
Token ID357
Feature activation-1.73e-02

Pos logit contributions
 Howell+1.471
 Birch+1.280
 Clarkson+1.274
 JJ+1.223
 Hendricks+1.163
Neg logit contributions
phe-1.247
ū-1.205
Ur-1.185
aug-1.184
UG-1.130
TokenFigure
Token ID11337
Feature activation-1.05e-01

Pos logit contributions
 Howell+0.178
 Birch+0.158
 Clarkson+0.157
 JJ+0.152
 Hendricks+0.146
Neg logit contributions
phe-0.108
ū-0.103
Ur-0.102
aug-0.101
UG-0.096
Token 2
Token ID362
Feature activation-3.04e-02

Pos logit contributions
 Howell+0.909
 Birch+0.785
 Clarkson+0.784
 JJ+0.749
 Hendricks+0.712
Neg logit contributions
phe-0.828
ū-0.802
aug-0.788
Ur-0.788
kus-0.755
TokenA
Token ID32
Feature activation-5.86e-02

Pos logit contributions
 Howell+0.296
 Birch+0.260
 Clarkson+0.260
 JJ+0.250
 Hendricks+0.240
Neg logit contributions
phe-0.205
ū-0.198
aug-0.194
Ur-0.193
UG-0.184
Token book
Token ID1492
Feature activation-1.47e-01

Pos logit contributions
phe+0.420
ū+0.408
Ur+0.404
aug+0.402
kus+0.385
Neg logit contributions
 Howell-0.494
 Birch-0.428
 Clarkson-0.426
 JJ-0.410
 Hendricks-0.389
Token sales
Token ID4200
Feature activation+1.98e-01

Pos logit contributions
 Howell+1.328
 Birch+1.152
 Clarkson+1.144
 JJ+1.103
 Hendricks+1.046
Neg logit contributions
phe-1.110
ū-1.072
Ur-1.057
aug-1.055
UG-1.007
Token,
Token ID11
Feature activation+1.21e-03

Pos logit contributions
phe+1.424
ū+1.391
Ur+1.356
aug+1.352
UG+1.290
Neg logit contributions
 Howell-1.826
 Birch-1.595
 Clarkson-1.578
 JJ-1.526
 Hendricks-1.435
Token rental
Token ID14447
Feature activation+1.98e-02

Pos logit contributions
phe+0.009
ū+0.009
Ur+0.009
aug+0.009
UG+0.009
Neg logit contributions
 Howell-0.010
 Birch-0.009
 Clarkson-0.009
 JJ-0.009
 Hendricks-0.008
Token,
Token ID11
Feature activation-1.35e-01

Pos logit contributions
phe+0.144
ū+0.139
Ur+0.137
aug+0.136
kus+0.132
Neg logit contributions
 Howell-0.182
 Birch-0.157
 Clarkson-0.156
 JJ-0.151
 Hendricks-0.143
Token or
Token ID393
Feature activation+5.52e-02

Pos logit contributions
 Howell+1.186
 Birch+1.030
 Clarkson+1.018
 JJ+0.986
 Hendricks+0.929
Neg logit contributions
phe-1.038
ū-1.002
Ur-0.986
aug-0.984
UG-0.945
Token lending
Token ID20983
Feature activation+2.47e-01

Pos logit contributions
phe+0.434
ū+0.418
Ur+0.413
aug+0.411
UG+0.396
Neg logit contributions
 Howell-0.473
 Birch-0.410
 Clarkson-0.403
 JJ-0.391
 Hendricks-0.367
Token records
Token ID4406
Feature activation+2.05e-02

Pos logit contributions
phe+1.771
ū+1.713
Ur+1.690
aug+1.669
kus+1.611
Neg logit contributions
 Howell-2.286
 Clarkson-1.971
 Birch-1.970
 JJ-1.896
 Hendricks-1.810
Token.
Token ID13
Feature activation-5.97e-02

Pos logit contributions
phe+0.147
ū+0.142
Ur+0.139
aug+0.139
UG+0.132
Neg logit contributions
 Howell-0.192
 Birch-0.167
 Clarkson-0.167
 JJ-0.161
 Hendricks-0.153
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
 Howell+0.542
 Birch+0.471
 Clarkson+0.470
 JJ+0.452
 Hendricks+0.431
Neg logit contributions
phe-0.440
ū-0.424
Ur-0.420
aug-0.418
UG-0.399
Token
Token ID198
Feature activation+4.14e-02

Pos logit contributions
 Howell+1.050
 Clarkson+0.895
 Birch+0.891
 JJ+0.849
 Hendricks+0.798
Neg logit contributions
phe-1.228
ū-1.184
aug-1.159
anamo-1.153
Ur-1.152
Token to
Token ID284
Feature activation-4.16e-02

Pos logit contributions
 Howell+0.190
 Birch+0.165
 Clarkson+0.164
 JJ+0.158
 Hendricks+0.150
Neg logit contributions
phe-0.168
ū-0.163
aug-0.160
Ur-0.159
UG-0.152
Token federal
Token ID2717
Feature activation-1.86e-01

Pos logit contributions
 Howell+0.372
 Birch+0.323
 Clarkson+0.323
 JJ+0.310
 Hendricks+0.295
Neg logit contributions
phe-0.313
ū-0.302
aug-0.298
Ur-0.297
kus-0.284
Token public
Token ID1171
Feature activation-7.77e-02

Pos logit contributions
 Howell+1.657
 Birch+1.439
 Clarkson+1.434
 JJ+1.378
 Hendricks+1.309
Neg logit contributions
phe-1.407
ū-1.359
aug-1.338
Ur-1.337
kus-1.278
Token lands
Token ID8604
Feature activation-5.02e-02

Pos logit contributions
 Howell+0.700
 Birch+0.609
 Clarkson+0.608
 JJ+0.583
 Hendricks+0.555
Neg logit contributions
phe-0.582
ū-0.561
aug-0.553
Ur-0.553
UG-0.527
Token,
Token ID11
Feature activation+3.21e-04

Pos logit contributions
 Howell+0.453
 Birch+0.394
 Clarkson+0.392
 JJ+0.377
 Hendricks+0.359
Neg logit contributions
phe-0.376
ū-0.364
aug-0.358
Ur-0.357
UG-0.341
Token and
Token ID290
Feature activation-6.95e-02

Pos logit contributions
phe+0.003
ū+0.002
Ur+0.002
aug+0.002
UG+0.002
Neg logit contributions
 Howell-0.003
 Birch-0.002
 Clarkson-0.002
 JJ-0.002
 Hendricks-0.002
Token then
Token ID788
Feature activation-9.07e-02

Pos logit contributions
 Howell+0.595
 Birch+0.513
 Clarkson+0.512
 JJ+0.491
 Hendricks+0.465
Neg logit contributions
phe-0.550
ū-0.532
Ur-0.524
aug-0.524
kus-0.502
Token figure
Token ID3785
Feature activation-1.24e-01

Pos logit contributions
 Howell+0.799
 Birch+0.692
 Clarkson+0.690
 JJ+0.663
 Hendricks+0.629
Neg logit contributions
phe-0.695
ū-0.672
Ur-0.662
aug-0.662
kus-0.633
Token out
Token ID503
Feature activation-1.97e-01

Pos logit contributions
 Howell+0.934
 Birch+0.787
 Clarkson+0.783
 JJ+0.746
 Hendricks+0.705
Neg logit contributions
phe-1.113
ū-1.086
aug-1.072
Ur-1.067
UG-1.028
Token how
Token ID703
Feature activation-3.59e-01

Pos logit contributions
 Howell+1.531
 Birch+1.300
 Clarkson+1.295
 JJ+1.236
 Hendricks+1.161
Neg logit contributions
phe-1.716
ū-1.664
aug-1.643
Ur-1.641
kus-1.579
Token to
Token ID284
Feature activation-1.76e-02

Pos logit contributions
 Howell+3.000
 Birch+2.583
 Clarkson+2.567
 JJ+2.465
 Hendricks+2.320
Neg logit contributions
phe-2.921
ū-2.804
aug-2.767
Ur-2.767
kus-2.666
Token foundation
Token ID8489
Feature activation-6.53e-02

Pos logit contributions
 Howell+0.490
 Birch+0.418
 Clarkson+0.416
 JJ+0.398
 Hendricks+0.375
Neg logit contributions
phe-0.508
ū-0.494
aug-0.486
Ur-0.485
kus-0.466
Token of
Token ID286
Feature activation-2.07e-01

Pos logit contributions
 Howell+0.577
 Clarkson+0.499
 Birch+0.498
 JJ+0.479
 Hendricks+0.455
Neg logit contributions
phe-0.499
ū-0.485
aug-0.475
Ur-0.475
UG-0.454
Token everything
Token ID2279
Feature activation+7.96e-02

Pos logit contributions
 Howell+1.844
 Birch+1.601
 Clarkson+1.594
 JJ+1.536
 Hendricks+1.457
Neg logit contributions
phe-1.569
ū-1.513
aug-1.490
Ur-1.488
kus-1.424
Token and
Token ID290
Feature activation-2.63e-01

Pos logit contributions
phe+0.583
ū+0.568
aug+0.559
Ur+0.558
UG+0.533
Neg logit contributions
 Howell-0.723
 Birch-0.627
 Clarkson-0.626
 JJ-0.599
 Hendricks-0.570
Token Vietnamese
Token ID23618
Feature activation-3.11e-01

Pos logit contributions
 Howell+2.235
 Birch+1.927
 Clarkson+1.918
 JJ+1.848
 Hendricks+1.744
Neg logit contributions
phe-2.108
ū-2.037
aug-2.007
Ur-2.003
kus-1.920
Token people
Token ID661
Feature activation-1.32e-01

Pos logit contributions
 Howell+2.610
 Birch+2.243
 Clarkson+2.230
 JJ+2.146
 Hendricks+2.029
Neg logit contributions
phe-2.512
ū-2.429
aug-2.394
Ur-2.390
kus-2.298
Token work
Token ID670
Feature activation-5.23e-02

Pos logit contributions
 Howell+1.216
 Birch+1.060
 Clarkson+1.056
 JJ+1.016
 Hendricks+0.967
Neg logit contributions
phe-0.969
ū-0.935
aug-0.920
Ur-0.918
kus-0.877
Token hard
Token ID1327
Feature activation+3.83e-01

Pos logit contributions
 Howell+0.441
 Birch+0.380
 Clarkson+0.378
 JJ+0.362
 Hendricks+0.343
Neg logit contributions
phe-0.417
ū-0.407
aug-0.400
Ur-0.400
kus-0.385
Token
Token ID851
Feature activation+1.03e-02

Pos logit contributions
phe+2.746
ū+2.721
aug+2.670
Ur+2.608
UG+2.534
Neg logit contributions
 Howell-3.464
 Birch-3.024
 Clarkson-3.007
 JJ-2.853
 Hendricks-2.757
Token I
Token ID314
Feature activation+6.98e-02

Pos logit contributions
phe+0.078
ū+0.076
aug+0.075
Ur+0.075
kus+0.072
Neg logit contributions
 Howell-0.091
 Birch-0.079
 Clarkson-0.079
 JJ-0.075
 Hendricks-0.072
Token
Token ID447
Feature activation+9.92e-02

Pos logit contributions
phe+0.492
ū+0.476
aug+0.463
Ur+0.463
kus+0.446
Neg logit contributions
 Howell-0.661
 Birch-0.580
 Clarkson-0.579
 JJ-0.556
 Hendricks-0.532
Token for
Token ID329
Feature activation-7.90e-02

Pos logit contributions
 Howell+0.481
 Birch+0.414
 Clarkson+0.412
 JJ+0.395
 Hendricks+0.374
Neg logit contributions
phe-0.456
ū-0.444
Ur-0.437
aug-0.437
UG-0.418
Token women
Token ID1466
Feature activation+1.46e-01

Pos logit contributions
 Howell+0.753
 Birch+0.661
 Clarkson+0.658
 JJ+0.633
 Hendricks+0.604
Neg logit contributions
phe-0.548
ū-0.529
Ur-0.521
aug-0.520
UG-0.495
Token that
Token ID326
Feature activation-4.43e-01

Pos logit contributions
phe+1.107
ū+1.083
Ur+1.066
aug+1.059
UG+1.016
Neg logit contributions
 Howell-1.301
 Birch-1.125
 Clarkson-1.117
 JJ-1.071
 Hendricks-1.016
Token would
Token ID561
Feature activation-2.64e-01

Pos logit contributions
 Howell+3.605
 Clarkson+3.077
 Birch+3.072
 JJ+2.934
 Hendricks+2.773
Neg logit contributions
phe-3.688
ū-3.535
aug-3.512
Ur-3.488
UG-3.361
Token basically
Token ID6209
Feature activation-1.49e-02

Pos logit contributions
 Howell+2.481
 Birch+2.170
 Clarkson+2.166
 JJ+2.087
 Hendricks+1.986
Neg logit contributions
phe-1.876
ū-1.798
aug-1.773
Ur-1.771
UG-1.684
Token consist
Token ID3473
Feature activation+2.91e-02

Pos logit contributions
 Howell+0.132
 Birch+0.115
 Clarkson+0.114
 JJ+0.110
 Hendricks+0.104
Neg logit contributions
phe-0.113
ū-0.110
Ur-0.108
aug-0.108
kus-0.103
Token of
Token ID286
Feature activation+1.86e-01

Pos logit contributions
phe+0.214
ū+0.209
Ur+0.203
aug+0.203
UG+0.195
Neg logit contributions
 Howell-0.266
 Birch-0.232
 Clarkson-0.230
 JJ-0.222
 Hendricks-0.211
Token a
Token ID257
Feature activation+3.15e-01

Pos logit contributions
phe+1.316
ū+1.289
Ur+1.254
aug+1.251
UG+1.197
Neg logit contributions
 Howell-1.719
 Birch-1.500
 Clarkson-1.494
 JJ-1.435
 Hendricks-1.364
Token piece
Token ID3704
Feature activation+2.89e-01

Pos logit contributions
phe+2.593
ū+2.551
Ur+2.483
aug+2.465
UG+2.423
Neg logit contributions
 Howell-2.493
 Birch-2.139
 Clarkson-2.128
 JJ-2.022
 Hendricks-1.888
Token of
Token ID286
Feature activation+4.23e-01

Pos logit contributions
phe+2.009
ū+1.967
Ur+1.895
aug+1.888
UG+1.822
Neg logit contributions
 Howell-2.708
 Birch-2.373
 Clarkson-2.361
 JJ-2.293
 Hendricks-2.181
Token metal
Token ID6147
Feature activation+2.85e-01

Pos logit contributions
phe+3.145
ū+3.082
Ur+2.999
aug+2.993
UG+2.867
Neg logit contributions
 Howell-3.642
 Birch-3.142
 Clarkson-3.142
 JJ-3.005
 Hendricks-2.851
Token
Token ID134
Feature activation-1.21e-02

Pos logit contributions
phe+0.853
ū+0.840
aug+0.810
Ur+0.806
kus+0.752
Neg logit contributions
 Howell-1.895
 Birch-1.707
 Clarkson-1.698
 JJ-1.642
 Hendricks-1.584
Token
Token ID119
Feature activation-4.95e-01

Pos logit contributions
 Howell+0.100
 Birch+0.086
 Clarkson+0.086
 JJ+0.082
 Hendricks+0.078
Neg logit contributions
phe-0.101
ū-0.094
aug-0.094
Ur-0.094
anamo-0.091
Tokeni
Token ID72
Feature activation-5.62e-01

Pos logit contributions
 Howell+4.304
 Birch+3.705
 Clarkson+3.685
 JJ+3.587
 Hendricks+3.371
Neg logit contributions
phe-3.783
Ur-3.564
ū-3.558
aug-3.549
kus-3.412
Token M
Token ID337
Feature activation-8.78e-02

Pos logit contributions
 Howell+4.745
 Clarkson+4.049
 Birch+4.042
 JJ+3.906
 Hendricks+3.664
Neg logit contributions
phe-4.442
aug-4.249
ū-4.244
Ur-4.228
UG-4.068
Tokenok
Token ID482
Feature activation-1.18e-01

Pos logit contributions
 Howell+1.111
 Birch+1.008
 Clarkson+1.006
 JJ+0.979
 Hendricks+0.946
Neg logit contributions
phe-0.336
ū-0.314
aug-0.304
Ur-0.303
kus-0.275
Tokenup
Token ID929
Feature activation+2.33e-02

Pos logit contributions
 Howell+1.337
 Birch+1.198
 Clarkson+1.195
 JJ+1.160
 Hendricks+1.115
Neg logit contributions
phe-0.608
ū-0.575
Ur-0.564
aug-0.563
kus-0.525
Tokenuni
Token ID35657
Feature activation+6.64e-02

Pos logit contributions
phe+0.107
ū+0.104
aug+0.100
Ur+0.099
kus+0.092
Neg logit contributions
 Howell-0.278
 Birch-0.250
 Clarkson-0.250
 JJ-0.242
 Hendricks-0.234
Token ma
Token ID17266
Feature activation-4.13e-03

Pos logit contributions
phe+0.507
ū+0.494
Ur+0.484
aug+0.483
kus+0.462
Neg logit contributions
 Howell-0.584
 Birch-0.509
 Clarkson-0.508
 JJ-0.484
 Hendricks-0.462
Token
Token ID220
Feature activation+1.14e-01

Pos logit contributions
 Howell+0.037
 Birch+0.032
 Clarkson+0.032
 JJ+0.030
 Hendricks+0.029
Neg logit contributions
phe-0.031
ū-0.030
aug-0.030
Ur-0.030
kus-0.029
Token
Token ID134
Feature activation-2.51e-01

Pos logit contributions
phe+0.595
ū+0.588
aug+0.563
Ur+0.561
kus+0.523
Neg logit contributions
 Howell-1.283
 Clarkson-1.158
 Birch-1.155
 JJ-1.115
 Hendricks-1.076
Token
Token ID119
Feature activation-9.45e-02

Pos logit contributions
 Howell+2.246
 Birch+1.952
 Clarkson+1.945
 JJ+1.869
 Hendricks+1.778
Neg logit contributions
phe-1.890
ū-1.805
aug-1.795
Ur-1.791
kus-1.711
Token gave
Token ID2921
Feature activation+2.40e-02

Pos logit contributions
phe+0.500
ū+0.489
Ur+0.476
aug+0.476
kus+0.455
Neg logit contributions
 Howell-0.632
 Birch-0.552
 Clarkson-0.548
 JJ-0.528
 Hendricks-0.501
Token T
Token ID309
Feature activation-1.38e-01

Pos logit contributions
phe+0.145
ū+0.139
aug+0.137
Ur+0.136
kus+0.129
Neg logit contributions
 Howell-0.249
 Clarkson-0.221
 Birch-0.221
 JJ-0.214
 Hendricks-0.204
Tokenread
Token ID961
Feature activation+7.30e-02

Pos logit contributions
 Howell+1.224
 Birch+1.062
 Clarkson+1.058
 JJ+1.017
 Hendricks+0.965
Neg logit contributions
phe-1.052
ū-1.015
aug-1.000
Ur-0.999
kus-0.955
Tokenwell
Token ID4053
Feature activation+1.89e-01

Pos logit contributions
phe+0.329
ū+0.304
Ur+0.304
aug+0.291
UG+0.277
Neg logit contributions
 Howell-0.876
 Birch-0.788
 Clarkson-0.783
 JJ-0.765
 Hendricks-0.738
Token an
Token ID281
Feature activation-2.76e-02

Pos logit contributions
phe+1.341
ū+1.311
aug+1.277
Ur+1.277
UG+1.220
Neg logit contributions
 Howell-1.766
 Birch-1.538
 Clarkson-1.532
 JJ-1.482
 Hendricks-1.408
Token immediate
Token ID7103
Feature activation+9.56e-04

Pos logit contributions
 Howell+0.237
 Birch+0.204
 Clarkson+0.203
 JJ+0.193
 Hendricks+0.183
Neg logit contributions
phe-0.217
ū-0.212
Ur-0.209
aug-0.209
UG-0.198
Token advantage
Token ID4621
Feature activation+2.12e-01

Pos logit contributions
phe+0.007
ū+0.007
Ur+0.007
aug+0.007
UG+0.007
Neg logit contributions
 Howell-0.009
 Birch-0.007
 Clarkson-0.007
 JJ-0.007
 Hendricks-0.007
Token over
Token ID625
Feature activation-1.32e-02

Pos logit contributions
phe+1.594
ū+1.554
aug+1.525
Ur+1.509
UG+1.444
Neg logit contributions
 Howell-1.882
 Birch-1.631
 Clarkson-1.609
 JJ-1.562
 Hendricks-1.476
Token smaller
Token ID4833
Feature activation+1.46e-01

Pos logit contributions
 Howell+0.120
 Clarkson+0.105
 Birch+0.105
 JJ+0.101
 Hendricks+0.096
Neg logit contributions
phe-0.095
ū-0.092
aug-0.091
Ur-0.091
kus-0.087
Token corner
Token ID5228
Feature activation-2.09e-01

Pos logit contributions
phe+1.141
ū+1.118
Ur+1.104
aug+1.092
UG+1.064
Neg logit contributions
 Howell-1.230
 Clarkson-1.061
 Birch-1.051
 JJ-0.999
 Hendricks-0.956
Tokenbacks
Token ID10146
Feature activation-5.35e-02

Pos logit contributions
 Howell+2.422
 Birch+2.173
 Clarkson+2.169
 JJ+2.104
 Hendricks+2.026
Neg logit contributions
phe-1.032
ū-0.980
aug-0.957
Ur-0.957
kus-0.889
Token>
Token ID29
Feature activation-2.36e-02

Pos logit contributions
 Howell+4.721
 Clarkson+4.098
 Birch+4.094
 JJ+3.972
 Hendricks+3.759
Neg logit contributions
phe-3.766
ū-3.611
Ur-3.534
aug-3.527
kus-3.445
Token
Token ID7359
Feature activation-7.54e-02

Pos logit contributions
 Howell+0.232
 Birch+0.204
 Clarkson+0.201
 JJ+0.195
 Hendricks+0.186
Neg logit contributions
phe-0.158
ū-0.153
aug-0.151
Ur-0.150
UG-0.142
Tokenli
Token ID4528
Feature activation-2.98e-01

Pos logit contributions
 Howell+0.782
 Birch+0.694
 Clarkson+0.690
 JJ+0.667
 Hendricks+0.640
Neg logit contributions
phe-0.467
ū-0.447
aug-0.439
Ur-0.438
kus-0.412
Token>
Token ID29
Feature activation-2.94e-01

Pos logit contributions
 Howell+2.645
 Clarkson+2.311
 Birch+2.290
 JJ+2.225
 Hendricks+2.106
Neg logit contributions
phe-2.245
ū-2.143
aug-2.096
Ur-2.081
kus-2.041
Token
Token ID7359
Feature activation-3.99e-01

Pos logit contributions
 Howell+2.788
 Birch+2.440
 Clarkson+2.423
 JJ+2.339
 Hendricks+2.229
Neg logit contributions
phe-2.070
ū-2.000
aug-1.968
Ur-1.966
UG-1.867
Tokenul
Token ID377
Feature activation-6.86e-01

Pos logit contributions
 Howell+5.054
 Clarkson+4.604
 Birch+4.595
 JJ+4.486
 Hendricks+4.326
Neg logit contributions
phe-1.366
ū-1.254
Ur-1.210
aug-1.199
UG-1.123
Token>
Token ID29
Feature activation-2.59e-01

Pos logit contributions
 Howell+5.426
 Clarkson+4.645
 JJ+4.576
 Birch+4.550
 Hendricks+4.236
Neg logit contributions
phe-5.471
ū-5.294
aug-5.131
Ur-5.112
kus-5.076
Token
Token ID7359
Feature activation-7.29e-01

Pos logit contributions
 Howell+2.435
 Birch+2.126
 Clarkson+2.109
 JJ+2.035
 Hendricks+1.937
Neg logit contributions
phe-1.845
ū-1.786
Ur-1.756
aug-1.756
UG-1.668
Tokenbody
Token ID2618
Feature activation-3.01e-01

Pos logit contributions
 Howell+6.468
 Clarkson+5.693
 Birch+5.691
 JJ+5.474
 Hendricks+5.183
Neg logit contributions
phe-5.077
ū-4.974
Ur-4.827
aug-4.820
anamo-4.705
Token>
Token ID29
Feature activation-1.72e-01

Pos logit contributions
 Howell+2.612
 Clarkson+2.291
 Birch+2.272
 JJ+2.200
 Hendricks+2.085
Neg logit contributions
phe-2.294
ū-2.201
aug-2.139
Ur-2.128
anamo-2.092
Token
Token ID198
Feature activation-2.90e-01

Pos logit contributions
 Howell+1.620
 Birch+1.412
 Clarkson+1.399
 JJ+1.348
 Hendricks+1.285
Neg logit contributions
phe-1.219
ū-1.184
Ur-1.162
aug-1.161
UG-1.101
Token case
Token ID1339
Feature activation-8.14e-02

Pos logit contributions
 Howell+1.906
 Birch+1.656
 Clarkson+1.650
 JJ+1.587
 Hendricks+1.507
Neg logit contributions
phe-1.605
ū-1.549
aug-1.526
Ur-1.524
kus-1.456
Token,
Token ID11
Feature activation-7.00e-02

Pos logit contributions
 Howell+0.734
 Birch+0.637
 Clarkson+0.637
 JJ+0.609
 Hendricks+0.580
Neg logit contributions
phe-0.609
ū-0.588
Ur-0.579
aug-0.579
kus-0.555
Token since
Token ID1201
Feature activation+1.91e-01

Pos logit contributions
 Howell+0.612
 Birch+0.528
 Clarkson+0.528
 JJ+0.503
 Hendricks+0.480
Neg logit contributions
phe-0.542
ū-0.524
Ur-0.517
aug-0.516
kus-0.497
Token I
Token ID314
Feature activation+1.20e-01

Pos logit contributions
phe+1.406
ū+1.356
aug+1.346
Ur+1.338
kus+1.298
Neg logit contributions
 Howell-1.709
 Birch-1.484
 Clarkson-1.479
 JJ-1.399
 Hendricks-1.348
Token mm
Token ID8085
Feature activation-1.10e-01

Pos logit contributions
phe+0.863
ū+0.844
Ur+0.821
aug+0.817
kus+0.797
Neg logit contributions
 Howell-1.108
 Birch-0.967
 Clarkson-0.965
 JJ-0.921
 Hendricks-0.885
Tokenap
Token ID499
Feature activation-5.02e-01

Pos logit contributions
 Howell+1.369
 Birch+1.239
 Clarkson+1.238
 JJ+1.202
 Hendricks+1.165
Neg logit contributions
phe-0.452
ū-0.424
aug-0.414
Ur-0.412
UG-0.375
Token the
Token ID262
Feature activation+4.41e-02

Pos logit contributions
 Howell+4.457
 Birch+3.880
 Clarkson+3.847
 JJ+3.731
 Hendricks+3.516
Neg logit contributions
phe-3.761
ū-3.623
aug-3.566
Ur-3.556
kus-3.395
Token file
Token ID2393
Feature activation-2.00e-01

Pos logit contributions
phe+0.320
ū+0.308
Ur+0.304
aug+0.303
kus+0.291
Neg logit contributions
 Howell-0.405
 Birch-0.352
 Clarkson-0.352
 JJ-0.335
 Hendricks-0.323
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
 Howell+1.761
 Birch+1.524
 Clarkson+1.521
 JJ+1.457
 Hendricks+1.386
Neg logit contributions
phe-1.543
ū-1.490
Ur-1.470
aug-1.466
kus-1.405
Token this
Token ID428
Feature activation-3.25e-01

Pos logit contributions
 Howell+1.596
 Birch+1.376
 Clarkson+1.374
 JJ+1.312
 Hendricks+1.249
Neg logit contributions
phe-1.455
ū-1.408
aug-1.388
Ur-1.388
kus-1.330
Token code
Token ID2438
Feature activation-2.57e-01

Pos logit contributions
 Howell+2.656
 Birch+2.271
 Clarkson+2.264
 JJ+2.170
 Hendricks+2.048
Neg logit contributions
phe-2.703
ū-2.619
aug-2.583
Ur-2.577
kus-2.475
TokenFG
Token ID30386
Feature activation-1.34e-01

Pos logit contributions
phe+0.319
ū+0.305
Ur+0.303
aug+0.299
UG+0.289
Neg logit contributions
 Howell-0.566
 Birch-0.503
 Clarkson-0.500
 JJ-0.480
 Hendricks-0.464
Token<|endoftext|>
Token ID50256
Feature activation-1.76e-01

Pos logit contributions
 Howell+1.305
 Birch+1.147
 Clarkson+1.143
 JJ+1.099
 Hendricks+1.052
Neg logit contributions
phe-0.910
ū-0.874
Ur-0.861
aug-0.860
UG-0.818
TokenBy
Token ID3886
Feature activation-5.89e-01

Pos logit contributions
 Howell+1.876
 Birch+1.669
 Clarkson+1.665
 JJ+1.612
 Hendricks+1.546
Neg logit contributions
phe-1.025
ū-0.980
aug-0.960
Ur-0.957
kus-0.903
Token Andrew
Token ID6858
Feature activation+1.56e-01

Pos logit contributions
 Howell+5.055
 Birch+4.362
 Clarkson+4.351
 JJ+4.207
 Hendricks+3.956
Neg logit contributions
phe-4.590
ū-4.414
aug-4.362
Ur-4.356
kus-4.189
Token Benson
Token ID33940
Feature activation+1.78e-01

Pos logit contributions
phe+1.264
ū+1.216
aug+1.206
Ur+1.204
kus+1.151
Neg logit contributions
 Howell-1.252
 Birch-1.076
 Clarkson-1.073
 JJ-1.044
 Hendricks-0.975
Token
Token ID198
Feature activation-5.42e-01

Pos logit contributions
phe+1.308
ū+1.285
aug+1.269
Ur+1.249
UG+1.207
Neg logit contributions
 Howell-1.586
 Birch-1.391
 Clarkson-1.374
 JJ-1.329
 Hendricks-1.262
Token
Token ID198
Feature activation-4.65e-01

Pos logit contributions
 Howell+3.642
 Clarkson+3.063
 Birch+3.018
 JJ+2.899
 Hendricks+2.688
Neg logit contributions
phe-5.018
anamo-4.882
ū-4.834
aug-4.679
trak-4.673
TokenVeter
Token ID45182
Feature activation-1.46e-01

Pos logit contributions
 Howell+4.859
 Clarkson+4.317
 Birch+4.310
 JJ+4.174
 Hendricks+3.994
Neg logit contributions
phe-2.685
ū-2.574
aug-2.482
Ur-2.439
kus-2.373
Tokenan
Token ID272
Feature activation-1.66e-01

Pos logit contributions
 Howell+1.511
 Birch+1.338
 Clarkson+1.335
 JJ+1.291
 Hendricks+1.231
Neg logit contributions
phe-0.901
ū-0.872
aug-0.855
Ur-0.846
kus-0.808
Token Nick
Token ID8047
Feature activation-1.59e-02

Pos logit contributions
 Howell+1.498
 Birch+1.302
 Clarkson+1.297
 JJ+1.246
 Hendricks+1.187
Neg logit contributions
phe-1.241
ū-1.199
Ur-1.179
aug-1.178
kus-1.128
Token He
Token ID679
Feature activation+1.18e-02

Pos logit contributions
 Howell+0.139
 Birch+0.120
 Clarkson+0.120
 JJ+0.116
 Hendricks+0.109
Neg logit contributions
phe-0.121
ū-0.117
aug-0.116
Ur-0.116
kus-0.110
Token a
Token ID257
Feature activation-2.98e-03

Pos logit contributions
phe+0.966
ū+0.926
aug+0.918
Ur+0.908
kus+0.872
Neg logit contributions
 Howell-1.125
 Clarkson-0.975
 Birch-0.972
 JJ-0.933
 Hendricks-0.887
Token fore
Token ID1674
Feature activation-3.31e-02

Pos logit contributions
 Howell+0.025
 Birch+0.022
 Clarkson+0.021
 JJ+0.021
 Hendricks+0.019
Neg logit contributions
phe-0.024
ū-0.023
aug-0.023
Ur-0.023
UG-0.022
Tokenclosed
Token ID20225
Feature activation+6.05e-02

Pos logit contributions
 Howell+0.322
 Birch+0.282
 Clarkson+0.279
 JJ+0.270
 Hendricks+0.259
Neg logit contributions
phe-0.230
ū-0.218
aug-0.215
Ur-0.210
kus-0.204
Token home
Token ID1363
Feature activation-3.98e-01

Pos logit contributions
phe+0.521
ū+0.502
aug+0.495
Ur+0.495
UG+0.478
Neg logit contributions
 Howell-0.471
 Birch-0.401
 Clarkson-0.399
 JJ-0.383
 Hendricks-0.358
Token May
Token ID1737
Feature activation-3.00e-02

Pos logit contributions
 Howell+3.433
 Birch+2.963
 Clarkson+2.944
 JJ+2.829
 Hendricks+2.681
Neg logit contributions
phe-3.121
ū-3.006
Ur-2.967
aug-2.961
kus-2.848
Token 7
Token ID767
Feature activation-6.03e-01

Pos logit contributions
 Howell+0.248
 Birch+0.212
 Clarkson+0.212
 JJ+0.203
 Hendricks+0.191
Neg logit contributions
phe-0.247
ū-0.239
Ur-0.236
aug-0.236
kus-0.226
Token,
Token ID11
Feature activation-5.23e-01

Pos logit contributions
 Howell+5.122
 Clarkson+4.424
 Birch+4.403
 JJ+4.230
 Hendricks+4.010
Neg logit contributions
phe-4.745
ū-4.513
Ur-4.504
aug-4.464
kus-4.311
Token 2009
Token ID3717
Feature activation-5.83e-01

Pos logit contributions
 Howell+4.339
 Birch+3.725
 Clarkson+3.718
 JJ+3.575
 Hendricks+3.360
Neg logit contributions
phe-4.281
ū-4.116
Ur-4.064
aug-4.050
kus-3.920
Token in
Token ID287
Feature activation-2.06e-01

Pos logit contributions
 Howell+5.084
 Birch+4.409
 Clarkson+4.399
 JJ+4.218
 Hendricks+4.011
Neg logit contributions
phe-4.489
ū-4.293
Ur-4.249
aug-4.243
kus-4.087
Token Antioch
Token ID46590
Feature activation-2.78e-01

Pos logit contributions
 Howell+1.796
 Birch+1.554
 Clarkson+1.549
 JJ+1.487
 Hendricks+1.410
Neg logit contributions
phe-1.604
ū-1.551
aug-1.528
Ur-1.526
kus-1.461
Token,
Token ID11
Feature activation-2.71e-01

Pos logit contributions
 Howell+2.487
 Birch+2.161
 Clarkson+2.153
 JJ+2.071
 Hendricks+1.966
Neg logit contributions
phe-2.092
ū-2.019
aug-1.987
Ur-1.987
kus-1.898
Token you
Token ID345
Feature activation-5.92e-02

Pos logit contributions
phe+0.262
ū+0.252
Ur+0.250
aug+0.249
kus+0.239
Neg logit contributions
 Howell-0.315
 Clarkson-0.274
 Birch-0.272
 JJ-0.261
 Hendricks-0.250
Token can
Token ID460
Feature activation-9.78e-02

Pos logit contributions
 Howell+0.511
 Birch+0.442
 Clarkson+0.439
 JJ+0.419
 Hendricks+0.402
Neg logit contributions
phe-0.464
ū-0.449
aug-0.444
Ur-0.443
kus-0.427
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
 Howell+0.903
 Birch+0.787
 Clarkson+0.786
 JJ+0.754
 Hendricks+0.719
Neg logit contributions
phe-0.710
ū-0.685
aug-0.677
Ur-0.676
kus-0.645
Token It
Token ID632
Feature activation+1.23e-01

Pos logit contributions
phe+0.663
ū+0.631
Ur+0.631
aug+0.629
UG+0.595
Neg logit contributions
 Howell-1.006
 Clarkson-0.887
 Birch-0.883
 JJ-0.850
 Hendricks-0.815
Token all
Token ID477
Feature activation-7.79e-02

Pos logit contributions
phe+0.859
ū+0.834
aug+0.824
Ur+0.819
kus+0.781
Neg logit contributions
 Howell-1.157
 Birch-1.016
 Clarkson-1.001
 JJ-0.958
 Hendricks-0.925
Token kind
Token ID1611
Feature activation-5.79e-01

Pos logit contributions
 Howell+0.706
 Birch+0.616
 Clarkson+0.609
 JJ+0.585
 Hendricks+0.559
Neg logit contributions
phe-0.578
ū-0.560
aug-0.553
Ur-0.549
kus-0.524
Token of
Token ID286
Feature activation-2.39e-01

Pos logit contributions
 Howell+4.187
 Clarkson+3.588
 Birch+3.550
 JJ+3.516
 Hendricks+3.248
Neg logit contributions
phe-4.965
anamo-4.759
ū-4.750
Ur-4.744
aug-4.679
Token depends
Token ID8338
Feature activation-1.00e-01

Pos logit contributions
 Howell+2.099
 Birch+1.818
 Clarkson+1.812
 JJ+1.740
 Hendricks+1.650
Neg logit contributions
phe-1.842
ū-1.781
aug-1.754
Ur-1.752
kus-1.676
Token on
Token ID319
Feature activation-8.26e-02

Pos logit contributions
 Howell+0.861
 Birch+0.741
 Clarkson+0.738
 JJ+0.705
 Hendricks+0.672
Neg logit contributions
phe-0.795
ū-0.764
Ur-0.755
aug-0.755
UG-0.718
Token how
Token ID703
Feature activation+8.83e-02

Pos logit contributions
 Howell+0.735
 Birch+0.635
 Clarkson+0.634
 JJ+0.607
 Hendricks+0.579
Neg logit contributions
phe-0.626
ū-0.603
Ur-0.596
aug-0.594
kus-0.566
Token you
Token ID345
Feature activation+4.95e-02

Pos logit contributions
phe+0.646
ū+0.622
Ur+0.615
aug+0.614
kus+0.582
Neg logit contributions
 Howell-0.808
 Birch-0.699
 Clarkson-0.698
 JJ-0.669
 Hendricks-0.640