TOP ACTIVATIONS
MAX = 5.765

Atomic < T > { /// Create a new , null
our work is appreciated . Please click below to become an
me feel all sort of -" She cuts me
impl Board { pub fn copy _ board ( &
$ 11 . 25 million contract signed in March 2016
sudo l sh w - C network This will
t top Curtis K uy k end all
things . See | aut oc omm and | . 3
STR UCT URE Please find a full list of
$ 16 . 25 million contract signed in February 2017
Guard { ... } pub fn pin () -> Guard ;
surface . Media playback is unsupported on your device
f rit ters in the skillet ( don t
gh sacrificed and Dirk K uy t switching fl anks .
weird feeling ." Video : CH I @ ST
free newsletters . Update , 3 : 01 p
ta Pi ($ 400 per semester ), and Delta Tau Delta
ay ko ( 11 : 05 ) and Vladimir Tar as
ushes : 33 Opp onent : Miami
he says , sounding p ained . So you

MIN ACTIVATIONS
MIN = -6.111

comment on Facebook Share this comment on Twitter NY
Recommend Share this comment on Facebook Share this comment
type - 94 Jin - class and type - 96 ),
: 05 43 z ST OW MA IN RE P ORTS
comment on Facebook Share this comment on Twitter NY
Recommend Share this comment on Facebook Share this comment
Middle Level Education , 33 ( 10 ), 1 - 13
Recommend Share this comment on Facebook Share this comment
10 . 13 71 / journal . p one . 00
comment on Facebook Share this comment on Twitter NY
type - 93 Shang - class and type - 95 ,
comment on Facebook Share this comment on Twitter NY
Recommend Share this comment on Facebook Share this comment
Facebook Share this comment on Twitter NY T Pick
Recommend Share this comment on Facebook Share this comment on Twitter
in your performance as a result of truly believing in your
atives . <|endoftext|> FILE : Delhi Law Minister and
Recommend Share this comment on Facebook Share this comment on Twitter
Recommend Share this comment on Facebook Share this comment on Twitter
Enter Your Name Add a comment here Ver ification Send Email

INTERVAL 2.796 - 5.765
CONTAINS 0.315%

are also alike in the fact that they have at some
their life from the polar opposite vantage point . For Bob
bit strange ." Video : W PG @ FL
Dear George , I had a dream of a
ar ap at ang p anta o ( Although we are

INTERVAL -0.173 - 2.796
CONTAINS 57.232%

a ur inal . Pretty much every other day I can
businesses , be in employment , qualify for benefits , access
's offices in Seoul today , C NET has learned .
for the Sh river Award , please download the Sh river
says have contributed to Pruitt s campaigns and organizations

INTERVAL -3.142 - -0.173
CONTAINS 42.305%

Do not use social media to let people know
she would put them to sleep each night as children ,
action to protect Oklahoma residents impacted by sw arms of fracking
The cat has been featured in segments of other episodes of
] tradition , where you get the composer --

INTERVAL -6.111 - -3.142
CONTAINS 0.148%

rop yl methyl - 7 -( 2 , 6 - dim
Alberta is gonna succeed by pitching a radical program . It
the Catholic Encyclopedia , Church Fathers , Sum ma , Bible
you this post . <|endoftext|> THE BALL OT FOR industrial action
pc Any where , Splash Car Wash , Steven La M
Token Atomic
Token ID28976
Feature activation-3.36e-01

Pos logit contributions
acs+0.298
olla+0.297
ktop+0.297
rog+0.292
 impaired+0.285
Neg logit contributions
 Yao-0.247
 Debor-0.219
 intern-0.214
 JC-0.213
 Spencer-0.213
Token <
Token ID1279
Feature activation+9.87e-01

Pos logit contributions
acs+0.276
olla+0.276
ktop+0.276
rog+0.271
 impaired+0.265
Neg logit contributions
 Yao-0.224
 Debor-0.198
 intern-0.193
 JC-0.193
 Spencer-0.193
Token T
Token ID309
Feature activation+2.09e+00

Pos logit contributions
 Yao+0.707
 Debor+0.626
 intern+0.620
 JC+0.617
 Spencer+0.617
Neg logit contributions
acs-0.761
ktop-0.760
olla-0.758
rog-0.748
 impaired-0.725
Token >
Token ID1875
Feature activation-5.82e-01

Pos logit contributions
 Yao+1.133
 Debor+0.962
 JC+0.950
 intern+0.948
 Spencer+0.946
Neg logit contributions
acs-1.974
ktop-1.973
olla-1.960
rog-1.940
 impaired-1.900
Token {
Token ID1391
Feature activation+2.65e+00

Pos logit contributions
acs+0.357
olla+0.356
ktop+0.356
rog+0.348
 impaired+0.337
Neg logit contributions
 Yao-0.509
 Debor-0.464
 intern-0.456
 JC-0.456
 Spencer-0.455
Token ///
Token ID34013
Feature activation+5.76e+00

Pos logit contributions
 Yao+1.946
 intern+1.735
 Debor+1.727
 Spencer+1.718
 JC+1.692
Neg logit contributions
acs-1.992
ktop-1.978
olla-1.975
rog-1.949
 impaired-1.878
Token Create
Token ID13610
Feature activation+2.66e+00

Pos logit contributions
 Yao+4.173
 intern+3.768
 Debor+3.731
 Spencer+3.647
 JC+3.638
Neg logit contributions
acs-4.309
ktop-4.300
olla-4.285
rog-4.179
lime-4.086
Token a
Token ID257
Feature activation+1.52e+00

Pos logit contributions
 Yao+2.188
 intern+1.984
 Debor+1.974
 JC+1.944
 Spencer+1.932
Neg logit contributions
acs-1.772
olla-1.769
ktop-1.768
rog-1.729
 impaired-1.655
Token new
Token ID649
Feature activation+1.01e+00

Pos logit contributions
 Yao+1.235
 Debor+1.112
 intern+1.103
 JC+1.094
 Spencer+1.090
Neg logit contributions
acs-1.039
ktop-1.037
olla-1.033
rog-1.013
 impaired-0.977
Token,
Token ID11
Feature activation+9.41e-01

Pos logit contributions
 Yao+0.725
 Debor+0.646
 intern+0.639
 JC+0.631
 Spencer+0.629
Neg logit contributions
acs-0.777
olla-0.775
ktop-0.774
rog-0.760
 impaired-0.738
Token null
Token ID9242
Feature activation+9.44e-01

Pos logit contributions
 Yao+0.741
 intern+0.664
 Debor+0.664
 JC+0.655
 unden+0.654
Neg logit contributions
acs-0.660
ktop-0.659
olla-0.658
rog-0.645
lime-0.618
Token our
Token ID674
Feature activation+4.81e-01

Pos logit contributions
 Yao+0.283
 Debor+0.256
 intern+0.251
 JC+0.251
 Spencer+0.251
Neg logit contributions
ktop-0.237
olla-0.237
acs-0.236
rog-0.231
 impaired-0.224
Token work
Token ID670
Feature activation-1.02e+00

Pos logit contributions
 Yao+0.372
 Debor+0.336
 intern+0.329
 JC+0.329
 Spencer+0.328
Neg logit contributions
olla-0.343
acs-0.342
ktop-0.342
rog-0.334
 impaired-0.326
Token is
Token ID318
Feature activation+7.02e-01

Pos logit contributions
olla+0.635
ktop+0.633
acs+0.630
rog+0.614
 impaired+0.594
Neg logit contributions
 Yao-0.890
 Debor-0.810
 intern-0.801
 JC-0.801
 Spencer-0.797
Token appreciated
Token ID16373
Feature activation+1.21e+00

Pos logit contributions
 Yao+0.610
 Debor+0.566
 unden+0.551
••+0.549
 Spencer+0.546
Neg logit contributions
acs-0.434
olla-0.425
rog-0.421
 impaired-0.416
ktop-0.413
Token.
Token ID13
Feature activation+9.81e-01

Pos logit contributions
 Yao+0.855
 JC+0.764
 Debor+0.762
 intern+0.756
 Spencer+0.748
Neg logit contributions
olla-0.950
ktop-0.944
acs-0.933
rog-0.921
 neur-0.896
Token Please
Token ID4222
Feature activation+5.43e+00

Pos logit contributions
 Yao+0.709
 Debor+0.634
 Spencer+0.622
 JC+0.619
 intern+0.614
Neg logit contributions
ktop-0.755
olla-0.749
acs-0.744
rog-0.731
 impaired-0.713
Token click
Token ID3904
Feature activation+3.51e+00

Pos logit contributions
 Yao+3.420
 intern+3.121
 JC+3.078
 Spencer+3.044
 EB+3.010
Neg logit contributions
ktop-4.662
olla-4.599
acs-4.403
\/\/-4.285
rog-4.254
Token below
Token ID2174
Feature activation-3.15e-01

Pos logit contributions
 Yao+2.487
 JC+2.145
 EB+2.139
 intern+2.135
 Spencer+2.132
Neg logit contributions
olla-2.819
ktop-2.800
acs-2.735
lime-2.631
phthal-2.602
Token to
Token ID284
Feature activation+8.74e-01

Pos logit contributions
ktop+0.225
olla+0.224
acs+0.224
rog+0.219
 impaired+0.213
Neg logit contributions
 Yao-0.244
 Debor-0.219
 JC-0.216
 intern-0.215
 Spencer-0.214
Token become
Token ID1716
Feature activation+6.61e-01

Pos logit contributions
 Yao+0.790
 Spencer+0.727
 Debor+0.726
 intern+0.724
 JC+0.724
Neg logit contributions
ktop-0.509
olla-0.505
acs-0.489
rog-0.477
 impaired-0.464
Token an
Token ID281
Feature activation-1.34e+00

Pos logit contributions
 Yao+0.536
 Debor+0.489
 intern+0.480
 Spencer+0.479
 JC+0.477
Neg logit contributions
ktop-0.457
olla-0.456
acs-0.447
rog-0.437
\/\/-0.430
Token me
Token ID502
Feature activation+1.40e+00

Pos logit contributions
olla+0.434
acs+0.434
ktop+0.433
rog+0.427
 impaired+0.419
Neg logit contributions
 Yao-0.261
 Debor-0.226
 intern-0.218
 JC-0.218
 Spencer-0.217
Token feel
Token ID1254
Feature activation-1.55e+00

Pos logit contributions
 Yao+1.129
 intern+1.003
 Spencer+1.001
 JC+1.000
 Debor+1.000
Neg logit contributions
ktop-0.967
olla-0.955
acs-0.942
rog-0.928
 impaired-0.891
Token all
Token ID477
Feature activation+2.82e-01

Pos logit contributions
acs+1.034
olla+1.034
ktop+1.029
rog+1.011
 impaired+0.986
Neg logit contributions
 Yao-1.265
 Debor-1.152
 intern-1.123
 JC-1.123
 Spencer-1.121
Token sort
Token ID3297
Feature activation+2.70e+00

Pos logit contributions
 Yao+0.235
 Debor+0.211
 Spencer+0.209
 intern+0.209
 JC+0.208
Neg logit contributions
olla-0.187
ktop-0.187
acs-0.186
rog-0.182
 impaired-0.174
Token of
Token ID286
Feature activation+9.04e-02

Pos logit contributions
 Yao+2.084
 JC+1.856
 Spencer+1.854
 intern+1.852
 Debor+1.842
Neg logit contributions
ktop-1.900
acs-1.891
olla-1.879
rog-1.845
 impaired-1.791
Token-"
Token ID21215
Feature activation+5.34e+00

Pos logit contributions
 Yao+0.074
 Debor+0.067
 intern+0.066
 JC+0.065
 Spencer+0.065
Neg logit contributions
olla-0.061
ktop-0.061
acs-0.061
rog-0.059
 impaired-0.057
Token
Token ID198
Feature activation+2.38e+00

Pos logit contributions
 Yao+4.139
 Spencer+3.714
 Debor+3.672
 JC+3.650
 intern+3.581
Neg logit contributions
ktop-3.840
acs-3.761
olla-3.750
rog-3.660
 impaired-3.556
Token
Token ID198
Feature activation+2.22e+00

Pos logit contributions
 Yao+1.973
 Spencer+1.768
 Debor+1.747
 JC+1.744
••+1.738
Neg logit contributions
ktop-1.610
acs-1.578
olla-1.571
 impaired-1.533
 neur-1.528
TokenShe
Token ID3347
Feature activation+2.11e+00

Pos logit contributions
 Yao+1.631
••+1.439
 Spencer+1.432
 Debor+1.432
 JC+1.419
Neg logit contributions
ktop-1.669
olla-1.644
acs-1.642
 impaired-1.605
rog-1.592
Token cuts
Token ID6630
Feature activation+1.16e+00

Pos logit contributions
 Yao+1.697
 intern+1.534
 Debor+1.515
 Spencer+1.514
 JC+1.501
Neg logit contributions
ktop-1.462
olla-1.435
acs-1.423
rog-1.405
 impaired-1.347
Token me
Token ID502
Feature activation-7.08e-02

Pos logit contributions
 Yao+0.730
 Debor+0.638
 Spencer+0.626
 JC+0.625
 intern+0.622
Neg logit contributions
acs-0.997
ktop-0.995
olla-0.993
rog-0.974
 impaired-0.951
Token
Token ID198
Feature activation-8.57e-01

Pos logit contributions
ktop+0.598
acs+0.593
olla+0.592
rog+0.576
 impaired+0.563
Neg logit contributions
 Yao-0.840
 Debor-0.760
 JC-0.752
 intern-0.750
 Spencer-0.749
Tokenimpl
Token ID23928
Feature activation+2.64e+00

Pos logit contributions
ktop+0.570
acs+0.569
olla+0.569
rog+0.555
 impaired+0.542
Neg logit contributions
 Yao-0.703
 Debor-0.636
 intern-0.623
 JC-0.623
 Spencer-0.622
Token Board
Token ID5926
Feature activation-1.47e+00

Pos logit contributions
 Yao+1.733
 Debor+1.515
 JC+1.505
 intern+1.500
 EB+1.490
Neg logit contributions
ktop-2.204
olla-2.176
acs-2.167
rog-2.153
 impaired-2.081
Token {
Token ID1391
Feature activation+2.33e+00

Pos logit contributions
acs+0.950
olla+0.950
ktop+0.948
rog+0.927
 impaired+0.901
Neg logit contributions
 Yao-1.230
 Debor-1.119
 intern-1.096
 JC-1.095
 Spencer-1.093
Token pub
Token ID2240
Feature activation+2.63e+00

Pos logit contributions
 Yao+1.870
 intern+1.696
 Debor+1.678
 Spencer+1.673
 JC+1.666
Neg logit contributions
acs-1.590
ktop-1.590
olla-1.587
rog-1.545
lime-1.487
Token fn
Token ID24714
Feature activation+5.29e+00

Pos logit contributions
 Yao+1.836
 intern+1.625
 Debor+1.598
 JC+1.597
 EB+1.594
Neg logit contributions
olla-2.069
ktop-2.066
acs-2.042
rog-1.997
lime-1.959
Token copy
Token ID4866
Feature activation+9.24e-01

Pos logit contributions
 Yao+3.741
 intern+3.378
 JC+3.340
 EB+3.273
 Debor+3.271
Neg logit contributions
ktop-4.146
olla-4.046
acs-4.005
rog-3.932
lime-3.824
Token_
Token ID62
Feature activation+1.14e+00

Pos logit contributions
 Yao+0.693
 Debor+0.621
 intern+0.611
 JC+0.608
 Spencer+0.607
Neg logit contributions
ktop-0.681
acs-0.679
olla-0.679
rog-0.664
 impaired-0.649
Tokenboard
Token ID3526
Feature activation+7.90e-01

Pos logit contributions
 Yao+0.904
 Debor+0.812
 intern+0.801
 JC+0.800
 Spencer+0.794
Neg logit contributions
ktop-0.793
olla-0.786
acs-0.784
rog-0.762
 impaired-0.752
Token (
Token ID357
Feature activation+1.15e+00

Pos logit contributions
 Yao+0.592
 Debor+0.530
 intern+0.524
 JC+0.522
 Spencer+0.519
Neg logit contributions
ktop-0.583
acs-0.578
olla-0.577
rog-0.567
 impaired-0.553
Token &
Token ID1222
Feature activation+3.17e+00

Pos logit contributions
 Yao+0.697
 intern+0.604
 Debor+0.596
 JC+0.587
 Spencer+0.586
Neg logit contributions
ktop-1.024
acs-1.009
olla-1.005
rog-0.988
 impaired-0.976
Token $
Token ID720
Feature activation+1.68e+00

Pos logit contributions
 Yao+0.514
 Debor+0.465
 intern+0.456
 Spencer+0.455
 JC+0.455
Neg logit contributions
acs-0.452
ktop-0.452
olla-0.452
rog-0.441
 impaired-0.429
Token11
Token ID1157
Feature activation+5.08e-01

Pos logit contributions
 Yao+1.074
 Debor+0.934
 Spencer+0.922
 JC+0.921
••+0.918
Neg logit contributions
ktop-1.428
acs-1.406
olla-1.403
rog-1.373
 impaired-1.371
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 Yao+0.389
 Debor+0.352
 intern+0.343
 JC+0.343
 Spencer+0.343
Neg logit contributions
olla-0.364
acs-0.364
ktop-0.363
rog-0.356
 impaired-0.347
Token25
Token ID1495
Feature activation+8.98e-01

Pos logit contributions
 Yao+0.722
 Debor+0.643
 JC+0.630
 Spencer+0.627
 intern+0.623
Neg logit contributions
ktop-0.781
acs-0.776
olla-0.772
rog-0.760
 impaired-0.750
Token million
Token ID1510
Feature activation+1.83e+00

Pos logit contributions
 Yao+0.674
 Debor+0.606
 intern+0.592
 JC+0.591
 Spencer+0.591
Neg logit contributions
acs-0.659
olla-0.659
ktop-0.658
rog-0.645
 impaired-0.629
Token contract
Token ID2775
Feature activation+5.29e+00

Pos logit contributions
 Yao+1.688
 Debor+1.539
 intern+1.528
 Spencer+1.527
 JC+1.523
Neg logit contributions
ktop-1.038
acs-1.026
olla-1.025
rog-0.995
 impaired-0.962
Token signed
Token ID4488
Feature activation+2.27e+00

Pos logit contributions
 Yao+3.304
 intern+2.870
 Spencer+2.852
 JC+2.829
 Debor+2.829
Neg logit contributions
ktop-4.543
acs-4.473
olla-4.472
rog-4.351
lime-4.306
Token in
Token ID287
Feature activation-8.57e-02

Pos logit contributions
 Yao+1.599
 Debor+1.429
 intern+1.403
 Spencer+1.394
 JC+1.391
Neg logit contributions
olla-1.784
ktop-1.782
acs-1.772
rog-1.737
 impaired-1.689
Token March
Token ID2805
Feature activation-3.56e-01

Pos logit contributions
ktop+0.067
acs+0.067
olla+0.067
rog+0.066
 impaired+0.064
Neg logit contributions
 Yao-0.060
 Debor-0.054
 intern-0.053
 Spencer-0.052
 JC-0.052
Token 2016
Token ID1584
Feature activation-6.86e-01

Pos logit contributions
ktop+0.262
olla+0.261
acs+0.261
rog+0.255
 impaired+0.249
Neg logit contributions
 Yao-0.268
 Debor-0.241
 intern-0.236
 JC-0.235
 Spencer-0.235
Token
Token ID198
Feature activation+4.89e-01

Pos logit contributions
acs+0.398
olla+0.396
ktop+0.394
rog+0.387
 impaired+0.375
Neg logit contributions
 Yao-0.621
 Debor-0.571
 JC-0.558
 intern-0.557
 Spencer-0.556
Tokensudo
Token ID24032
Feature activation+1.32e+00

Pos logit contributions
 Yao+0.091
 Debor+0.081
 intern+0.079
 JC+0.079
 Spencer+0.079
Neg logit contributions
ktop-0.091
olla-0.091
acs-0.091
rog-0.089
 impaired-0.087
Token l
Token ID300
Feature activation-2.17e-01

Pos logit contributions
 Yao+1.073
 Debor+0.968
 intern+0.961
 JC+0.950
 Spencer+0.947
Neg logit contributions
olla-0.892
ktop-0.889
acs-0.887
rog-0.874
 impaired-0.844
Tokensh
Token ID1477
Feature activation+4.92e-01

Pos logit contributions
ktop+0.115
olla+0.114
acs+0.114
rog+0.111
 impaired+0.108
Neg logit contributions
 Yao-0.207
 Debor-0.191
 intern-0.187
 JC-0.187
 Spencer-0.187
Tokenw
Token ID86
Feature activation-9.97e-01

Pos logit contributions
 Yao+0.384
 Debor+0.346
 intern+0.339
 JC+0.338
 Spencer+0.337
Neg logit contributions
ktop-0.346
olla-0.346
acs-0.345
rog-0.339
 impaired-0.330
Token -
Token ID532
Feature activation+1.50e+00

Pos logit contributions
acs+0.662
olla+0.661
ktop+0.660
rog+0.646
 impaired+0.628
Neg logit contributions
 Yao-0.820
 Debor-0.745
 intern-0.729
 JC-0.728
 Spencer-0.727
TokenC
Token ID34
Feature activation+5.28e+00

Pos logit contributions
 Yao+1.280
 Debor+1.165
 intern+1.142
 Spencer+1.139
 JC+1.138
Neg logit contributions
ktop-0.944
acs-0.939
olla-0.938
rog-0.915
 impaired-0.902
Token network
Token ID3127
Feature activation-2.46e+00

Pos logit contributions
 Yao+3.939
 Debor+3.522
 intern+3.506
 Spencer+3.495
 EB+3.469
Neg logit contributions
ktop-3.781
olla-3.764
acs-3.731
rog-3.675
 impaired-3.615
Token
Token ID198
Feature activation+6.67e-01

Pos logit contributions
acs+1.754
olla+1.742
ktop+1.741
rog+1.714
 impaired+1.658
Neg logit contributions
 Yao-1.897
 Debor-1.718
 JC-1.679
 Spencer-1.675
 unden-1.668
Token
Token ID198
Feature activation+9.54e-01

Pos logit contributions
 Yao+0.564
 JC+0.503
 Debor+0.503
 Spencer+0.501
 intern+0.500
Neg logit contributions
ktop-0.435
acs-0.427
olla-0.426
rog-0.413
 neur-0.409
TokenThis
Token ID1212
Feature activation+6.47e-01

Pos logit contributions
 Yao+0.704
 Debor+0.632
••+0.617
 intern+0.617
 JC+0.616
Neg logit contributions
ktop-0.706
olla-0.703
acs-0.703
rog-0.686
 impaired-0.682
Token will
Token ID481
Feature activation-2.21e-01

Pos logit contributions
 Yao+0.567
 Debor+0.519
 intern+0.511
 JC+0.508
 Spencer+0.506
Neg logit contributions
olla-0.396
ktop-0.394
acs-0.393
rog-0.384
 impaired-0.374
Token
Token ID247
Feature activation+3.54e-01

Pos logit contributions
 Yao+0.108
 Debor+0.098
 intern+0.096
 Spencer+0.096
 JC+0.096
Neg logit contributions
ktop-0.074
acs-0.073
olla-0.073
rog-0.071
 impaired-0.070
Tokent
Token ID83
Feature activation+6.01e-01

Pos logit contributions
 Yao+0.272
 Debor+0.245
 intern+0.240
 JC+0.240
 Spencer+0.240
Neg logit contributions
ktop-0.252
acs-0.252
olla-0.252
rog-0.247
 impaired-0.241
Token top
Token ID1353
Feature activation+2.39e+00

Pos logit contributions
 Yao+0.490
 Debor+0.440
 intern+0.437
 JC+0.436
 Spencer+0.435
Neg logit contributions
olla-0.404
ktop-0.404
acs-0.402
rog-0.395
 impaired-0.382
Token Curtis
Token ID25157
Feature activation+1.28e+00

Pos logit contributions
 Yao+1.928
 Debor+1.728
 Spencer+1.723
 JC+1.710
 intern+1.700
Neg logit contributions
ktop-1.658
acs-1.653
olla-1.652
rog-1.611
 impaired-1.561
Token K
Token ID509
Feature activation+5.23e-01

Pos logit contributions
 Yao+0.940
 Debor+0.841
 Spencer+0.823
 intern+0.822
 JC+0.821
Neg logit contributions
olla-0.967
acs-0.967
ktop-0.966
rog-0.950
 impaired-0.924
Tokenuy
Token ID4669
Feature activation+5.20e+00

Pos logit contributions
 Yao+0.404
 Debor+0.364
 Spencer+0.357
 intern+0.356
 JC+0.355
Neg logit contributions
ktop-0.374
olla-0.369
acs-0.368
rog-0.362
 impaired-0.357
Tokenk
Token ID74
Feature activation+3.65e-01

Pos logit contributions
 Yao+4.176
 Spencer+3.722
 Debor+3.720
 intern+3.714
 JC+3.713
Neg logit contributions
olla-3.387
acs-3.375
ktop-3.373
 impaired-3.336
rog-3.334
Tokenend
Token ID437
Feature activation-7.11e-01

Pos logit contributions
 Yao+0.389
 Debor+0.362
 intern+0.356
 JC+0.356
 Spencer+0.355
Neg logit contributions
acs-0.153
olla-0.153
ktop-0.152
rog-0.147
 impaired-0.141
Tokenall
Token ID439
Feature activation-2.17e-01

Pos logit contributions
ktop+0.455
acs+0.452
olla+0.450
rog+0.442
 impaired+0.433
Neg logit contributions
 Yao-0.603
 Debor-0.543
 intern-0.538
 JC-0.535
 Spencer-0.535
Token
Token ID447
Feature activation+1.16e+00

Pos logit contributions
olla+0.166
acs+0.166
ktop+0.166
rog+0.163
 impaired+0.159
Neg logit contributions
 Yao-0.157
 Debor-0.140
 intern-0.137
 Spencer-0.137
 JC-0.137
Token
Token ID247
Feature activation+2.33e-01

Pos logit contributions
 Yao+0.998
 Debor+0.903
 intern+0.898
 JC+0.889
 Spencer+0.888
Neg logit contributions
ktop-0.725
acs-0.715
olla-0.713
rog-0.688
 impaired-0.680
Token things
Token ID1243
Feature activation+2.79e-01

Pos logit contributions
acs+0.610
ktop+0.609
olla+0.607
rog+0.596
 impaired+0.582
Neg logit contributions
 Yao-0.669
 Debor-0.605
 Spencer-0.588
 JC-0.588
 unden-0.587
Token.
Token ID13
Feature activation-9.49e-02

Pos logit contributions
 Yao+0.215
 Debor+0.194
 JC+0.190
 intern+0.190
 Spencer+0.189
Neg logit contributions
acs-0.199
olla-0.199
ktop-0.199
rog-0.195
 impaired-0.190
Token See
Token ID4091
Feature activation+1.86e+00

Pos logit contributions
olla+0.074
ktop+0.074
acs+0.074
rog+0.073
 impaired+0.071
Neg logit contributions
 Yao-0.067
 Debor-0.060
 intern-0.059
 JC-0.059
 Spencer-0.058
Token |
Token ID930
Feature activation+3.11e-01

Pos logit contributions
 Yao+1.350
 Debor+1.217
 intern+1.199
 JC+1.190
 Spencer+1.186
Neg logit contributions
olla-1.410
ktop-1.399
acs-1.398
rog-1.373
 impaired-1.338
Tokenaut
Token ID2306
Feature activation+1.75e+00

Pos logit contributions
 Yao+0.218
 Debor+0.194
 intern+0.189
 JC+0.189
 Spencer+0.189
Neg logit contributions
olla-0.244
acs-0.244
ktop-0.243
rog-0.239
 impaired-0.233
Tokenoc
Token ID420
Feature activation+5.13e+00

Pos logit contributions
 Yao+1.417
 Debor+1.275
 intern+1.266
 JC+1.262
 Spencer+1.253
Neg logit contributions
olla-1.158
ktop-1.156
acs-1.144
rog-1.130
 impaired-1.117
Tokenomm
Token ID2002
Feature activation+1.41e+00

Pos logit contributions
 Yao+3.643
 intern+3.341
 Debor+3.305
 JC+3.244
 Spencer+3.205
Neg logit contributions
olla-3.712
ktop-3.702
 impaired-3.648
acs-3.628
 neur-3.607
Tokenand
Token ID392
Feature activation+9.70e-01

Pos logit contributions
 Yao+1.209
 Debor+1.123
 intern+1.104
 Spencer+1.098
 JC+1.095
Neg logit contributions
ktop-0.860
olla-0.859
acs-0.841
rog-0.839
 impaired-0.827
Token|
Token ID91
Feature activation+1.56e+00

Pos logit contributions
 Yao+0.644
 Debor+0.573
 intern+0.559
 JC+0.557
 Spencer+0.555
Neg logit contributions
olla-0.794
acs-0.792
ktop-0.792
rog-0.777
 impaired-0.762
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
 Yao+1.191
 Debor+1.080
 intern+1.063
 JC+1.058
 Spencer+1.052
Neg logit contributions
olla-1.116
ktop-1.111
acs-1.109
rog-1.088
 impaired-1.065
Token 3
Token ID513
Feature activation-1.50e+00

Pos logit contributions
 Yao+0.270
 Debor+0.244
 JC+0.239
 intern+0.238
 Spencer+0.238
Neg logit contributions
olla-0.264
ktop-0.264
acs-0.262
rog-0.258
 impaired-0.251
Token STR
Token ID19269
Feature activation+3.90e-01

Pos logit contributions
 Yao+0.051
 Debor+0.046
 JC+0.045
 intern+0.045
 Spencer+0.045
Neg logit contributions
acs-0.049
ktop-0.049
olla-0.049
rog-0.049
 impaired-0.047
TokenUCT
Token ID18415
Feature activation-9.01e-01

Pos logit contributions
 Yao+0.244
 Debor+0.212
 JC+0.208
 intern+0.208
 Spencer+0.207
Neg logit contributions
ktop-0.338
olla-0.337
acs-0.337
rog-0.332
 impaired-0.325
TokenURE
Token ID11335
Feature activation-2.36e-01

Pos logit contributions
acs+0.719
ktop+0.719
olla+0.719
rog+0.705
 impaired+0.690
Neg logit contributions
 Yao-0.623
 Debor-0.553
 intern-0.539
 JC-0.539
 Spencer-0.539
Token
Token ID198
Feature activation+2.68e+00

Pos logit contributions
acs+0.166
olla+0.165
ktop+0.165
rog+0.162
 impaired+0.157
Neg logit contributions
 Yao-0.187
 Debor-0.169
 JC-0.165
 intern-0.165
 Spencer-0.165
Token
Token ID198
Feature activation+2.92e+00

Pos logit contributions
 Yao+2.134
 JC+1.902
 Spencer+1.883
 intern+1.870
 Debor+1.857
Neg logit contributions
ktop-1.882
acs-1.835
olla-1.820
 neur-1.782
 impaired-1.771
TokenPlease
Token ID5492
Feature activation+5.10e+00

Pos logit contributions
 Yao+2.214
••+1.990
 Spencer+1.957
 Debor+1.940
 JC+1.937
Neg logit contributions
ktop-2.109
acs-2.090
olla-2.083
 impaired-2.051
 neur-2.014
Token find
Token ID1064
Feature activation+2.70e+00

Pos logit contributions
 Yao+3.244
 intern+2.911
 JC+2.872
 Spencer+2.842
 Debor+2.833
Neg logit contributions
ktop-4.267
olla-4.223
acs-4.215
rog-4.073
lime-4.000
Token a
Token ID257
Feature activation+1.21e+00

Pos logit contributions
 Yao+2.149
 Spencer+1.927
 Debor+1.922
 intern+1.922
 JC+1.922
Neg logit contributions
acs-1.866
olla-1.865
ktop-1.853
rog-1.802
 impaired-1.751
Token full
Token ID1336
Feature activation-9.53e-01

Pos logit contributions
 Yao+0.911
 Debor+0.807
 Spencer+0.805
 intern+0.801
 JC+0.798
Neg logit contributions
acs-0.893
ktop-0.892
olla-0.886
rog-0.868
 impaired-0.850
Token list
Token ID1351
Feature activation+7.77e-01

Pos logit contributions
acs+0.731
ktop+0.730
olla+0.730
rog+0.714
 impaired+0.696
Neg logit contributions
 Yao-0.689
 Debor-0.614
 intern-0.604
 Spencer-0.602
 JC-0.600
Token of
Token ID286
Feature activation-3.85e-01

Pos logit contributions
 Yao+0.653
 Debor+0.595
 intern+0.583
 JC+0.582
 Spencer+0.582
Neg logit contributions
olla-0.501
acs-0.500
ktop-0.500
rog-0.489
 impaired-0.475
Token $
Token ID720
Feature activation+1.76e+00

Pos logit contributions
 Yao+0.479
 Debor+0.433
 intern+0.426
 Spencer+0.426
 JC+0.426
Neg logit contributions
acs-0.430
ktop-0.430
olla-0.429
rog-0.419
 impaired-0.408
Token16
Token ID1433
Feature activation+8.22e-01

Pos logit contributions
 Yao+1.146
 Debor+0.999
 Spencer+0.986
 JC+0.986
••+0.983
Neg logit contributions
ktop-1.477
acs-1.453
olla-1.447
rog-1.420
 impaired-1.418
Token.
Token ID13
Feature activation+2.01e+00

Pos logit contributions
 Yao+0.626
 Debor+0.564
 intern+0.551
 JC+0.550
 Spencer+0.549
Neg logit contributions
acs-0.594
olla-0.594
ktop-0.593
rog-0.582
 impaired-0.567
Token25
Token ID1495
Feature activation+1.05e+00

Pos logit contributions
 Yao+1.422
 Debor+1.264
 JC+1.240
 Spencer+1.234
••+1.224
Neg logit contributions
ktop-1.569
acs-1.556
olla-1.543
rog-1.526
 neur-1.515
Token million
Token ID1510
Feature activation+1.79e+00

Pos logit contributions
 Yao+0.785
 Debor+0.706
 intern+0.690
 JC+0.689
 Spencer+0.688
Neg logit contributions
acs-0.774
olla-0.773
ktop-0.772
rog-0.758
 impaired-0.739
Token contract
Token ID2775
Feature activation+5.09e+00

Pos logit contributions
 Yao+1.611
 Debor+1.473
 intern+1.459
 Spencer+1.458
 JC+1.456
Neg logit contributions
ktop-1.048
acs-1.036
olla-1.033
rog-1.003
lime-0.972
Token signed
Token ID4488
Feature activation+1.87e+00

Pos logit contributions
 Yao+3.253
 intern+2.839
 Spencer+2.822
 Debor+2.817
 JC+2.799
Neg logit contributions
ktop-4.293
olla-4.223
acs-4.222
rog-4.111
lime-4.069
Token in
Token ID287
Feature activation-4.95e-01

Pos logit contributions
 Yao+1.318
 Debor+1.178
 intern+1.157
 Spencer+1.149
 JC+1.148
Neg logit contributions
olla-1.469
ktop-1.468
acs-1.459
rog-1.431
 impaired-1.389
Token February
Token ID3945
Feature activation+4.10e-01

Pos logit contributions
acs+0.385
olla+0.384
ktop+0.384
rog+0.377
 impaired+0.367
Neg logit contributions
 Yao-0.352
 Debor-0.314
 intern-0.307
 JC-0.306
 Spencer-0.306
Token 2017
Token ID2177
Feature activation+2.64e-01

Pos logit contributions
 Yao+0.301
 Debor+0.270
 intern+0.264
 JC+0.263
 Spencer+0.263
Neg logit contributions
ktop-0.310
olla-0.309
acs-0.309
rog-0.302
 impaired-0.295
Token
Token ID198
Feature activation+1.13e+00

Pos logit contributions
 Yao+0.236
 Debor+0.216
 intern+0.212
 JC+0.212
 Spencer+0.212
Neg logit contributions
acs-0.156
olla-0.156
ktop-0.155
rog-0.152
 impaired-0.147
Token Guard
Token ID4932
Feature activation-1.32e+00

Pos logit contributions
 Yao+1.933
 Debor+1.691
 JC+1.671
 intern+1.670
 Spencer+1.661
Neg logit contributions
acs-2.297
ktop-2.288
olla-2.285
rog-2.257
lime-2.186
Token {
Token ID1391
Feature activation+3.03e+00

Pos logit contributions
olla+0.908
acs+0.908
ktop+0.908
rog+0.888
 impaired+0.865
Neg logit contributions
 Yao-1.046
 Debor-0.946
 intern-0.926
 JC-0.925
 Spencer-0.924
Token...
Token ID2644
Feature activation+2.88e+00

Pos logit contributions
 Yao+2.287
 intern+2.083
 Debor+2.043
 Spencer+2.035
 JC+2.023
Neg logit contributions
acs-2.218
ktop-2.214
olla-2.204
rog-2.135
lime-2.087
Token }
Token ID1782
Feature activation-4.50e-01

Pos logit contributions
 Yao+2.099
 intern+1.895
 Debor+1.846
 JC+1.834
 Spencer+1.830
Neg logit contributions
ktop-2.194
acs-2.193
olla-2.164
rog-2.103
lime-2.056
Token pub
Token ID2240
Feature activation+9.02e-02

Pos logit contributions
acs+0.297
olla+0.297
ktop+0.295
rog+0.288
 impaired+0.278
Neg logit contributions
 Yao-0.374
 Debor-0.339
 intern-0.336
 Spencer-0.333
 JC-0.332
Token fn
Token ID24714
Feature activation+5.02e+00

Pos logit contributions
 Yao+0.073
 Debor+0.066
 intern+0.065
 JC+0.065
 Spencer+0.065
Neg logit contributions
olla-0.061
acs-0.061
ktop-0.061
rog-0.060
 impaired-0.058
Token pin
Token ID6757
Feature activation-2.11e-01

Pos logit contributions
 Yao+3.821
 intern+3.455
 JC+3.398
 Spencer+3.348
 Debor+3.344
Neg logit contributions
ktop-3.649
acs-3.636
olla-3.603
rog-3.516
lime-3.443
Token ()
Token ID7499
Feature activation-2.22e-02

Pos logit contributions
ktop+0.147
acs+0.146
olla+0.146
rog+0.142
 impaired+0.139
Neg logit contributions
 Yao-0.167
 Debor-0.150
 intern-0.148
 JC-0.148
 Spencer-0.147
Token ->
Token ID4613
Feature activation+2.77e+00

Pos logit contributions
ktop+0.013
acs+0.013
olla+0.013
rog+0.013
 impaired+0.012
Neg logit contributions
 Yao-0.020
 Debor-0.018
 intern-0.018
 JC-0.018
 Spencer-0.018
Token Guard
Token ID4932
Feature activation+3.82e-01

Pos logit contributions
 Yao+1.941
 intern+1.718
 Debor+1.690
 JC+1.688
 Spencer+1.672
Neg logit contributions
acs-2.229
ktop-2.209
olla-2.175
rog-2.156
lime-2.096
Token ;
Token ID2162
Feature activation+3.75e-01

Pos logit contributions
 Yao+0.299
 intern+0.267
 Debor+0.266
 Spencer+0.264
 JC+0.264
Neg logit contributions
ktop-0.273
acs-0.270
olla-0.269
rog-0.265
 impaired-0.257
Token surface
Token ID4417
Feature activation+2.75e-01

Pos logit contributions
 Yao+0.483
 Debor+0.439
 intern+0.434
 Spencer+0.433
 JC+0.431
Neg logit contributions
olla-0.375
ktop-0.373
acs-0.372
rog-0.366
 impaired-0.349
Token.
Token ID13
Feature activation-2.42e-01

Pos logit contributions
 Yao+0.203
 Debor+0.182
 intern+0.179
 Spencer+0.178
 JC+0.178
Neg logit contributions
olla-0.209
ktop-0.208
acs-0.207
rog-0.203
 impaired-0.196
Token
Token ID198
Feature activation-1.69e-01

Pos logit contributions
ktop+0.155
olla+0.153
acs+0.152
rog+0.149
 impaired+0.146
Neg logit contributions
 Yao-0.208
 Debor-0.189
 Spencer-0.186
 JC-0.186
 intern-0.184
Token
Token ID198
Feature activation-3.69e-01

Pos logit contributions
ktop+0.111
acs+0.109
olla+0.109
rog+0.106
 neur+0.105
Neg logit contributions
 Yao-0.143
 JC-0.128
 Debor-0.128
 Spencer-0.128
 intern-0.127
TokenMedia
Token ID13152
Feature activation+1.98e+00

Pos logit contributions
ktop+0.272
olla+0.269
acs+0.267
 impaired+0.261
rog+0.260
Neg logit contributions
 Yao-0.277
 Debor-0.247
••-0.244
 Spencer-0.243
 JC-0.243
Token playback
Token ID16388
Feature activation+4.89e+00

Pos logit contributions
 Yao+1.151
 Debor+1.001
 intern+0.992
 Spencer+0.982
 JC+0.980
Neg logit contributions
ktop-1.793
olla-1.785
acs-1.774
rog-1.742
 impaired-1.696
Token is
Token ID318
Feature activation-6.14e-02

Pos logit contributions
 Yao+3.740
 Spencer+3.335
 intern+3.328
 JC+3.318
 Debor+3.220
Neg logit contributions
olla-3.548
acs-3.509
ktop-3.509
rog-3.368
lime-3.324
Token unsupported
Token ID24222
Feature activation+2.45e-01

Pos logit contributions
olla+0.031
ktop+0.031
acs+0.031
rog+0.030
 impaired+0.029
Neg logit contributions
 Yao-0.060
 Debor-0.056
 Spencer-0.055
 intern-0.055
 JC-0.055
Token on
Token ID319
Feature activation+4.00e-01

Pos logit contributions
 Yao+0.162
 Debor+0.142
 JC+0.141
 intern+0.140
 Spencer+0.140
Neg logit contributions
acs-0.203
ktop-0.203
olla-0.202
rog-0.199
 impaired-0.193
Token your
Token ID534
Feature activation-2.57e-01

Pos logit contributions
 Yao+0.325
 Debor+0.292
 intern+0.290
 JC+0.290
 Spencer+0.288
Neg logit contributions
acs-0.271
olla-0.271
ktop-0.269
rog-0.264
 impaired-0.255
Token device
Token ID3335
Feature activation-3.19e-01

Pos logit contributions
acs+0.137
ktop+0.136
olla+0.135
rog+0.131
 impaired+0.123
Neg logit contributions
 Yao-0.248
 intern-0.227
 Debor-0.227
 Spencer-0.225
 JC-0.225
Token f
Token ID277
Feature activation+9.54e-02

Pos logit contributions
 Yao+1.719
 intern+1.546
 JC+1.517
 Spencer+1.502
 EB+1.498
Neg logit contributions
olla-1.755
ktop-1.727
acs-1.726
rog-1.694
lime-1.626
Tokenrit
Token ID799
Feature activation+1.29e+00

Pos logit contributions
 Yao+0.104
 Spencer+0.097
 Debor+0.096
 intern+0.096
••+0.096
Neg logit contributions
olla-0.036
ktop-0.035
acs-0.035
 impaired-0.034
 neur-0.033
Tokenters
Token ID1010
Feature activation+1.94e-01

Pos logit contributions
 Yao+0.805
 Debor+0.706
 intern+0.694
 Spencer+0.692
 JC+0.689
Neg logit contributions
olla-1.094
ktop-1.093
acs-1.081
rog-1.063
 impaired-1.059
Token in
Token ID287
Feature activation+9.06e-01

Pos logit contributions
 Yao+0.132
 Debor+0.116
 intern+0.115
 JC+0.114
 Spencer+0.114
Neg logit contributions
olla-0.157
ktop-0.156
acs-0.155
rog-0.152
 impaired-0.148
Token the
Token ID262
Feature activation+9.46e-01

Pos logit contributions
 Yao+0.735
 intern+0.655
 JC+0.653
 Debor+0.650
 Spencer+0.649
Neg logit contributions
acs-0.622
olla-0.617
ktop-0.617
rog-0.600
 impaired-0.579
Token skillet
Token ID41306
Feature activation+4.88e+00

Pos logit contributions
 Yao+0.746
 intern+0.664
 JC+0.663
 Spencer+0.662
 Debor+0.660
Neg logit contributions
olla-0.662
acs-0.661
ktop-0.656
rog-0.648
 impaired-0.627
Token (
Token ID357
Feature activation+2.40e+00

Pos logit contributions
 Yao+3.238
 JC+2.853
 intern+2.849
 Debor+2.804
 Spencer+2.764
Neg logit contributions
ktop-4.011
olla-3.920
acs-3.903
rog-3.819
phthal-3.708
Tokendon
Token ID9099
Feature activation+1.99e+00

Pos logit contributions
 Yao+1.846
 Debor+1.674
 intern+1.668
••+1.661
 Spencer+1.637
Neg logit contributions
olla-1.624
ktop-1.613
acs-1.608
 impaired-1.593
 neur-1.553
Token
Token ID447
Feature activation+2.15e+00

Pos logit contributions
 Yao+1.253
 intern+1.103
 Debor+1.101
 Spencer+1.081
 JC+1.081
Neg logit contributions
ktop-1.684
olla-1.671
acs-1.664
rog-1.628
 impaired-1.626
Token
Token ID247
Feature activation+9.20e-01

Pos logit contributions
 Yao+1.834
 Debor+1.644
 intern+1.634
 Spencer+1.632
 JC+1.610
Neg logit contributions
ktop-1.373
acs-1.356
olla-1.346
rog-1.301
 impaired-1.295
Tokent
Token ID83
Feature activation+2.14e+00

Pos logit contributions
 Yao+0.677
 Debor+0.606
 intern+0.600
 Spencer+0.597
 JC+0.595
Neg logit contributions
ktop-0.681
olla-0.679
acs-0.677
rog-0.658
 impaired-0.653
Tokengh
Token ID456
Feature activation+3.01e-01

Pos logit contributions
 Yao+1.080
 Debor+0.982
 JC+0.968
 intern+0.968
 Spencer+0.968
Neg logit contributions
acs-0.786
ktop-0.785
olla-0.782
rog-0.761
 impaired-0.744
Token sacrificed
Token ID27445
Feature activation+4.14e-01

Pos logit contributions
 Yao+0.233
 Debor+0.209
 intern+0.206
 JC+0.205
 Spencer+0.205
Neg logit contributions
olla-0.215
acs-0.214
ktop-0.214
rog-0.209
 impaired-0.203
Token and
Token ID290
Feature activation-6.71e-01

Pos logit contributions
 Yao+0.320
 Debor+0.289
 JC+0.284
 intern+0.283
 Spencer+0.283
Neg logit contributions
acs-0.298
olla-0.298
ktop-0.295
rog-0.289
 impaired-0.281
Token Dirk
Token ID42761
Feature activation+9.73e-01

Pos logit contributions
acs+0.469
ktop+0.467
olla+0.466
rog+0.455
 impaired+0.441
Neg logit contributions
 Yao-0.532
 Debor-0.481
 JC-0.473
 Spencer-0.472
 intern-0.471
Token K
Token ID509
Feature activation+7.41e-01

Pos logit contributions
 Yao+0.714
 Debor+0.637
 Spencer+0.629
 JC+0.627
 intern+0.624
Neg logit contributions
ktop-0.736
acs-0.734
olla-0.730
rog-0.717
 impaired-0.698
Tokenuy
Token ID4669
Feature activation+4.84e+00

Pos logit contributions
 Yao+0.580
 Debor+0.524
 intern+0.513
 JC+0.512
 Spencer+0.512
Neg logit contributions
acs-0.520
olla-0.520
ktop-0.519
rog-0.508
 impaired-0.496
Tokent
Token ID83
Feature activation-8.02e-01

Pos logit contributions
 Yao+3.484
 JC+3.106
 Spencer+3.101
 Debor+3.083
 EB+3.060
Neg logit contributions
olla-3.629
ktop-3.607
acs-3.602
rog-3.561
 impaired-3.537
Token switching
Token ID15430
Feature activation-9.39e-02

Pos logit contributions
olla+0.530
acs+0.529
ktop+0.529
rog+0.516
 impaired+0.502
Neg logit contributions
 Yao-0.661
 Debor-0.601
 intern-0.590
 JC-0.589
 Spencer-0.588
Token fl
Token ID781
Feature activation-3.76e-01

Pos logit contributions
olla+0.067
acs+0.067
ktop+0.067
rog+0.065
 impaired+0.063
Neg logit contributions
 Yao-0.073
 Debor-0.066
 JC-0.065
 intern-0.065
 Spencer-0.065
Tokenanks
Token ID2283
Feature activation-1.21e-03

Pos logit contributions
ktop+0.315
olla+0.314
acs+0.313
rog+0.306
 impaired+0.302
Neg logit contributions
 Yao-0.244
 Debor-0.214
 intern-0.209
 JC-0.209
 Spencer-0.209
Token.
Token ID13
Feature activation+1.14e-01

Pos logit contributions
olla+0.001
acs+0.001
ktop+0.001
rog+0.001
 impaired+0.001
Neg logit contributions
 Yao-0.001
 Debor-0.001
 intern-0.001
 JC-0.001
 Spencer-0.001
Token weird
Token ID7650
Feature activation-1.64e+00

Pos logit contributions
olla+0.336
acs+0.335
ktop+0.334
rog+0.323
 impaired+0.312
Neg logit contributions
 Yao-0.485
 Debor-0.441
 intern-0.436
 JC-0.435
 Spencer-0.435
Token feeling
Token ID4203
Feature activation-1.71e+00

Pos logit contributions
olla+0.757
acs+0.757
ktop+0.754
rog+0.732
 impaired+0.702
Neg logit contributions
 Yao-1.680
 Debor-1.557
 intern-1.530
 JC-1.529
 Spencer-1.528
Token."
Token ID526
Feature activation+2.61e+00

Pos logit contributions
acs+1.236
olla+1.235
ktop+1.232
rog+1.210
 impaired+1.174
Neg logit contributions
 Yao-1.304
 Debor-1.173
 intern-1.151
 Spencer-1.147
 JC-1.147
Token
Token ID198
Feature activation+1.36e+00

Pos logit contributions
 Yao+2.086
 Spencer+1.849
 JC+1.845
 Debor+1.844
••+1.812
Neg logit contributions
ktop-1.819
acs-1.774
 neur-1.757
olla-1.748
 impaired-1.725
Token
Token ID198
Feature activation+1.11e+00

Pos logit contributions
 Yao+1.114
 JC+0.990
 Spencer+0.987
 intern+0.981
 Debor+0.976
Neg logit contributions
ktop-0.936
olla-0.913
acs-0.912
rog-0.882
 neur-0.881
TokenVideo
Token ID10798
Feature activation+4.84e+00

Pos logit contributions
 Yao+0.853
••+0.758
 Debor+0.754
 Spencer+0.748
 JC+0.748
Neg logit contributions
ktop-0.804
olla-0.792
acs-0.788
 impaired-0.770
rog-0.767
Token:
Token ID25
Feature activation+2.53e+00

Pos logit contributions
 Yao+2.996
 intern+2.567
 Spencer+2.517
 JC+2.512
 Debor+2.512
Neg logit contributions
ktop-4.366
olla-4.232
acs-4.151
rog-4.042
\/\/-4.008
Token CH
Token ID5870
Feature activation+1.08e-01

Pos logit contributions
 Yao+1.828
 JC+1.611
 Debor+1.604
 Spencer+1.602
 EB+1.573
Neg logit contributions
ktop-2.008
olla-1.975
acs-1.959
rog-1.933
 impaired-1.887
TokenI
Token ID40
Feature activation-1.66e+00

Pos logit contributions
 Yao+0.081
 Debor+0.073
 intern+0.071
 JC+0.071
 Spencer+0.071
Neg logit contributions
acs-0.079
olla-0.079
ktop-0.079
rog-0.078
 impaired-0.075
Token@
Token ID31
Feature activation+6.55e-01

Pos logit contributions
acs+1.184
olla+1.183
ktop+1.179
rog+1.159
 impaired+1.129
Neg logit contributions
 Yao-1.277
 Debor-1.155
 intern-1.126
 Spencer-1.124
 JC-1.122
TokenST
Token ID2257
Feature activation+7.32e-01

Pos logit contributions
 Yao+0.416
 Debor+0.357
 JC+0.355
 Spencer+0.355
 intern+0.350
Neg logit contributions
ktop-0.564
olla-0.558
acs-0.557
rog-0.548
 impaired-0.540
Token free
Token ID1479
Feature activation-1.80e+00

Pos logit contributions
 Yao+0.826
 intern+0.702
 Debor+0.701
 Spencer+0.701
 JC+0.696
Neg logit contributions
olla-1.007
acs-1.006
ktop-0.997
rog-0.985
 neur-0.953
Token newsletters
Token ID16983
Feature activation-2.17e+00

Pos logit contributions
ktop+1.468
acs+1.462
olla+1.454
rog+1.436
 impaired+1.397
Neg logit contributions
 Yao-1.193
 Debor-1.072
 unden-1.059
 Spencer-1.034
 intern-1.031
Token.
Token ID13
Feature activation+9.75e-02

Pos logit contributions
olla+1.547
acs+1.545
ktop+1.542
rog+1.512
 impaired+1.474
Neg logit contributions
 Yao-1.682
 Debor-1.520
 unden-1.482
 intern-1.481
 JC-1.480
Token
Token ID198
Feature activation-9.47e-01

Pos logit contributions
 Yao+0.064
 Debor+0.057
 JC+0.056
 Spencer+0.055
 EB+0.055
Neg logit contributions
ktop-0.081
acs-0.081
olla-0.080
rog-0.080
 impaired-0.078
Token
Token ID198
Feature activation-1.07e+00

Pos logit contributions
ktop+0.574
acs+0.572
olla+0.570
rog+0.556
 impaired+0.542
Neg logit contributions
 Yao-0.838
 Debor-0.763
 JC-0.751
 Spencer-0.750
 intern-0.749
TokenUpdate
Token ID10260
Feature activation+4.82e+00

Pos logit contributions
olla+0.790
acs+0.790
ktop+0.787
rog+0.774
 impaired+0.753
Neg logit contributions
 Yao-0.799
 Debor-0.720
 intern-0.703
 JC-0.701
 Spencer-0.700
Token,
Token ID11
Feature activation+1.74e+00

Pos logit contributions
 Yao+3.214
 Debor+2.869
 intern+2.833
 Spencer+2.825
 JC+2.806
Neg logit contributions
ktop-3.930
acs-3.879
olla-3.875
rog-3.775
 impaired-3.684
Token 3
Token ID513
Feature activation+3.19e-01

Pos logit contributions
 Yao+1.277
 Debor+1.144
 Spencer+1.127
 intern+1.123
 JC+1.122
Neg logit contributions
ktop-1.317
olla-1.311
acs-1.310
rog-1.279
 impaired-1.237
Token:
Token ID25
Feature activation+1.14e+00

Pos logit contributions
 Yao+0.218
 Debor+0.194
 intern+0.189
 JC+0.189
 Spencer+0.189
Neg logit contributions
ktop-0.256
acs-0.256
olla-0.256
rog-0.250
 impaired-0.245
Token01
Token ID486
Feature activation+2.59e+00

Pos logit contributions
 Yao+0.746
 Debor+0.656
 JC+0.644
 Spencer+0.642
 intern+0.636
Neg logit contributions
ktop-0.954
acs-0.950
olla-0.948
rog-0.931
 impaired-0.914
Token p
Token ID279
Feature activation+5.69e-01

Pos logit contributions
 Yao+1.920
 Debor+1.731
 JC+1.726
 Spencer+1.707
 intern+1.706
Neg logit contributions
ktop-1.916
olla-1.900
acs-1.898
rog-1.837
 impaired-1.806
Tokenta
Token ID8326
Feature activation-4.16e-01

Pos logit contributions
 Yao+0.319
 Debor+0.284
 JC+0.277
 Spencer+0.277
 intern+0.276
Neg logit contributions
ktop-0.382
olla-0.381
acs-0.380
rog-0.374
 impaired-0.367
Token Pi
Token ID13993
Feature activation+9.78e-02

Pos logit contributions
olla+0.365
ktop+0.365
acs+0.365
rog+0.359
 impaired+0.351
Neg logit contributions
 Yao-0.253
 Debor-0.221
 JC-0.215
 intern-0.215
 Spencer-0.215
Token ($
Token ID7198
Feature activation-1.64e+00

Pos logit contributions
 Yao+0.073
 Debor+0.066
 intern+0.064
 JC+0.064
 Spencer+0.064
Neg logit contributions
ktop-0.072
olla-0.072
acs-0.072
rog-0.071
 impaired-0.069
Token400
Token ID7029
Feature activation+1.55e+00

Pos logit contributions
olla+1.112
acs+1.112
ktop+1.108
rog+1.087
 impaired+1.055
Neg logit contributions
 Yao-1.320
 Debor-1.198
 intern-1.173
 JC-1.170
 Spencer-1.168
Token per
Token ID583
Feature activation+2.94e+00

Pos logit contributions
 Yao+1.183
 Debor+1.063
 intern+1.048
 Spencer+1.045
 JC+1.044
Neg logit contributions
ktop-1.112
olla-1.111
acs-1.108
rog-1.091
 impaired-1.059
Token semester
Token ID24878
Feature activation+4.77e+00

Pos logit contributions
 Yao+1.823
 intern+1.601
 Debor+1.591
 Spencer+1.583
 JC+1.574
Neg logit contributions
olla-2.524
ktop-2.522
acs-2.498
rog-2.473
 impaired-2.404
Token),
Token ID828
Feature activation-9.20e-01

Pos logit contributions
 Yao+3.832
 intern+3.475
 Debor+3.461
 JC+3.440
 Spencer+3.427
Neg logit contributions
ktop-3.163
acs-3.129
olla-3.119
rog-3.088
 neur-2.960
Token and
Token ID290
Feature activation-1.49e-01

Pos logit contributions
acs+0.728
olla+0.727
ktop+0.726
rog+0.713
 impaired+0.697
Neg logit contributions
 Yao-0.638
 Debor-0.569
 intern-0.554
 JC-0.553
 Spencer-0.552
Token Delta
Token ID16978
Feature activation+9.77e-01

Pos logit contributions
ktop+0.115
olla+0.115
acs+0.115
rog+0.113
 impaired+0.110
Neg logit contributions
 Yao-0.106
 Debor-0.095
 JC-0.093
 Spencer-0.093
 intern-0.093
Token Tau
Token ID36849
Feature activation+1.18e+00

Pos logit contributions
 Yao+0.650
 Debor+0.576
 JC+0.566
 Spencer+0.564
 intern+0.562
Neg logit contributions
ktop-0.805
olla-0.803
acs-0.801
rog-0.787
 impaired-0.773
Token Delta
Token ID16978
Feature activation-1.91e-01

Pos logit contributions
 Yao+0.821
 Debor+0.730
 JC+0.718
 Spencer+0.714
 intern+0.713
Neg logit contributions
ktop-0.930
acs-0.924
olla-0.921
rog-0.904
 impaired-0.891
Tokenay
Token ID323
Feature activation-4.21e-01

Pos logit contributions
 Yao+0.442
 Debor+0.352
 Spencer+0.342
 intern+0.342
 JC+0.340
Neg logit contributions
ktop-1.156
acs-1.152
olla-1.144
rog-1.131
 impaired-1.122
Tokenko
Token ID7204
Feature activation+2.80e-01

Pos logit contributions
ktop+0.369
olla+0.365
acs+0.364
rog+0.360
 impaired+0.353
Neg logit contributions
 Yao-0.257
 Debor-0.225
 JC-0.221
 intern-0.220
 Spencer-0.219
Token (
Token ID357
Feature activation+5.81e-01

Pos logit contributions
 Yao+0.216
 Debor+0.195
 intern+0.191
 JC+0.191
 Spencer+0.191
Neg logit contributions
ktop-0.198
olla-0.198
acs-0.198
rog-0.194
 impaired-0.189
Token11
Token ID1157
Feature activation-1.71e-01

Pos logit contributions
 Yao+0.399
 Debor+0.355
 Spencer+0.349
 JC+0.348
 intern+0.346
Neg logit contributions
ktop-0.463
olla-0.460
acs-0.459
rog-0.448
 impaired-0.444
Token:
Token ID25
Feature activation+1.71e+00

Pos logit contributions
olla+0.134
acs+0.133
ktop+0.133
rog+0.131
 impaired+0.128
Neg logit contributions
 Yao-0.120
 Debor-0.108
 intern-0.104
 JC-0.104
 Spencer-0.104
Token05
Token ID2713
Feature activation+4.74e+00

Pos logit contributions
 Yao+1.080
 Debor+0.935
 JC+0.926
 Spencer+0.922
 intern+0.911
Neg logit contributions
ktop-1.476
acs-1.456
olla-1.454
rog-1.428
 impaired-1.414
Token)
Token ID8
Feature activation+2.27e+00

Pos logit contributions
 Yao+3.878
 JC+3.482
 Spencer+3.467
 Debor+3.460
 intern+3.450
Neg logit contributions
ktop-3.111
acs-3.093
olla-3.060
rog-3.014
 impaired-2.915
Token and
Token ID290
Feature activation+3.02e-01

Pos logit contributions
 Yao+1.523
 Debor+1.352
 Spencer+1.329
 JC+1.328
 intern+1.326
Neg logit contributions
ktop-1.843
acs-1.837
olla-1.835
rog-1.802
 impaired-1.758
Token Vladimir
Token ID14840
Feature activation+1.13e+00

Pos logit contributions
 Yao+0.211
 Debor+0.188
 Spencer+0.185
 JC+0.184
 intern+0.183
Neg logit contributions
ktop-0.239
olla-0.239
acs-0.238
rog-0.234
 impaired-0.227
Token Tar
Token ID14110
Feature activation-9.81e-02

Pos logit contributions
 Yao+0.492
 Debor+0.409
 intern+0.390
 JC+0.388
 Spencer+0.387
Neg logit contributions
acs-1.187
olla-1.185
ktop-1.184
rog-1.169
 impaired-1.149
Tokenas
Token ID292
Feature activation-7.81e-01

Pos logit contributions
ktop+0.082
olla+0.082
acs+0.082
rog+0.080
 impaired+0.079
Neg logit contributions
 Yao-0.063
 Debor-0.056
 intern-0.054
 JC-0.054
 Spencer-0.054
Tokenushes
Token ID17237
Feature activation+3.63e+00

Pos logit contributions
 Yao+1.367
 Spencer+1.248
 intern+1.244
 Debor+1.231
 JC+1.228
Neg logit contributions
ktop-0.828
olla-0.806
rog-0.788
acs-0.783
 impaired-0.777
Token:
Token ID25
Feature activation+1.50e+00

Pos logit contributions
 Yao+2.200
 JC+1.886
 Spencer+1.883
 intern+1.856
 Debor+1.844
Neg logit contributions
ktop-3.214
acs-3.157
olla-3.140
 neur-3.100
rog-3.085
Token 33
Token ID4747
Feature activation+1.74e+00

Pos logit contributions
 Yao+0.960
 Debor+0.844
 Spencer+0.825
 JC+0.823
 intern+0.815
Neg logit contributions
ktop-1.292
acs-1.286
olla-1.284
rog-1.259
 impaired-1.229
Token
Token ID198
Feature activation+3.14e+00

Pos logit contributions
 Yao+1.488
 Debor+1.347
 JC+1.336
 intern+1.331
 Spencer+1.330
Neg logit contributions
ktop-1.110
acs-1.098
olla-1.089
rog-1.068
 neur-1.043
Token
Token ID198
Feature activation+3.49e+00

Pos logit contributions
 Yao+2.501
 JC+2.224
 Spencer+2.216
 Debor+2.213
 intern+2.195
Neg logit contributions
ktop-2.187
acs-2.145
olla-2.114
 neur-2.074
 impaired-2.053
TokenOpp
Token ID27524
Feature activation+4.73e+00

Pos logit contributions
 Yao+2.557
••+2.342
 Debor+2.239
 Spencer+2.226
 JC+2.194
Neg logit contributions
ktop-2.573
acs-2.554
olla-2.521
 impaired-2.487
 neur-2.469
Tokenonent
Token ID3471
Feature activation+4.02e+00

Pos logit contributions
 Yao+3.852
 Debor+3.485
 Spencer+3.442
 JC+3.439
 intern+3.436
Neg logit contributions
ktop-3.022
acs-3.000
olla-2.950
 impaired-2.862
rog-2.840
Token:
Token ID25
Feature activation-6.39e-02

Pos logit contributions
 Yao+2.426
 JC+2.084
 Spencer+2.075
 Debor+2.052
 intern+2.037
Neg logit contributions
ktop-3.591
acs-3.532
olla-3.500
 neur-3.443
rog-3.428
Token Miami
Token ID8437
Feature activation+3.82e+00

Pos logit contributions
ktop+0.051
acs+0.051
olla+0.051
rog+0.049
 impaired+0.048
Neg logit contributions
 Yao-0.045
 Debor-0.040
 JC-0.039
 Spencer-0.039
 intern-0.039
Token
Token ID198
Feature activation+2.44e+00

Pos logit contributions
 Yao+3.142
 JC+2.843
 Debor+2.841
 intern+2.816
 Spencer+2.798
Neg logit contributions
ktop-2.534
acs-2.494
olla-2.494
rog-2.441
lime-2.370
Token
Token ID198
Feature activation+2.62e+00

Pos logit contributions
 Yao+1.969
 JC+1.757
 Spencer+1.747
 intern+1.736
 Debor+1.732
Neg logit contributions
ktop-1.690
acs-1.652
olla-1.634
 neur-1.604
rog-1.598
Token he
Token ID339
Feature activation+3.68e-01

Pos logit contributions
 Yao+0.353
 Debor+0.320
 Spencer+0.315
 JC+0.313
 intern+0.312
Neg logit contributions
ktop-0.293
acs-0.292
olla-0.292
rog-0.285
 impaired-0.276
Token says
Token ID1139
Feature activation-1.51e+00

Pos logit contributions
 Yao+0.319
 Debor+0.292
 intern+0.288
 Spencer+0.286
 JC+0.286
Neg logit contributions
ktop-0.230
acs-0.227
olla-0.226
rog-0.223
 impaired-0.214
Token,
Token ID11
Feature activation+4.76e-01

Pos logit contributions
acs+1.080
olla+1.079
ktop+1.076
rog+1.056
 impaired+1.030
Neg logit contributions
 Yao-1.154
 Debor-1.041
 intern-1.017
 JC-1.016
 Spencer-1.014
Token sounding
Token ID22655
Feature activation+1.68e+00

Pos logit contributions
 Yao+0.353
 Debor+0.316
 intern+0.310
 Spencer+0.309
 JC+0.308
Neg logit contributions
olla-0.357
ktop-0.356
acs-0.355
rog-0.348
 impaired-0.337
Token p
Token ID279
Feature activation+6.77e-01

Pos logit contributions
 Yao+1.422
 intern+1.274
 Debor+1.272
 Spencer+1.266
 JC+1.257
Neg logit contributions
olla-1.104
ktop-1.097
acs-1.089
rog-1.055
lime-1.022
Tokenained
Token ID1328
Feature activation+4.72e+00

Pos logit contributions
 Yao+0.707
 Debor+0.649
 intern+0.643
 Spencer+0.642
 JC+0.641
Neg logit contributions
ktop-0.300
acs-0.297
olla-0.295
rog-0.281
 impaired-0.278
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
 Yao+3.190
 intern+2.793
 Debor+2.773
 Spencer+2.760
 JC+2.723
Neg logit contributions
acs-3.823
ktop-3.784
olla-3.737
rog-3.713
\/\/-3.551
Token
Token ID198
Feature activation+8.71e-01

Pos logit contributions
 Yao+0.889
 Debor+0.801
 Spencer+0.789
 JC+0.784
 intern+0.769
Neg logit contributions
ktop-0.813
acs-0.806
olla-0.803
rog-0.788
 impaired-0.774
Token
Token ID198
Feature activation+2.65e-01

Pos logit contributions
 Yao+0.732
 Spencer+0.652
 JC+0.651
 Debor+0.651
••+0.645
Neg logit contributions
ktop-0.575
acs-0.564
olla-0.562
rog-0.545
 neur-0.544
TokenSo
Token ID2396
Feature activation+9.75e-01

Pos logit contributions
 Yao+0.199
 Debor+0.178
••+0.175
 Spencer+0.175
 JC+0.174
Neg logit contributions
ktop-0.195
olla-0.194
acs-0.194
rog-0.189
 impaired-0.187
Token you
Token ID345
Feature activation+5.67e-01

Pos logit contributions
 Yao+0.808
 Debor+0.727
 Spencer+0.721
 intern+0.715
 JC+0.715
Neg logit contributions
olla-0.646
acs-0.643
ktop-0.642
rog-0.626
 impaired-0.607
Token comment
Token ID2912
Feature activation-6.02e+00

Pos logit contributions
acs+2.387
olla+2.386
ktop+2.380
rog+2.346
 impaired+2.293
Neg logit contributions
 Yao-2.257
 Debor-2.049
 unden-1.999
 intern-1.956
 Spencer-1.955
Token on
Token ID319
Feature activation-3.72e+00

Pos logit contributions
olla+3.824
 impaired+3.772
rog+3.763
ktop+3.718
acs+3.704
Neg logit contributions
 Yao-4.931
 unden-4.679
 Debor-4.609
 confir-4.421
••-4.344
Token Facebook
Token ID3203
Feature activation-4.44e+00

Pos logit contributions
olla+2.197
acs+2.176
ktop+2.162
rog+2.156
 impaired+2.109
Neg logit contributions
 Yao-3.268
 Debor-3.041
 unden-2.970
 intern-2.878
 JC-2.869
Token Share
Token ID8734
Feature activation-6.36e-01

Pos logit contributions
acs+3.128
olla+3.120
 impaired+3.089
rog+3.068
lime+3.031
Neg logit contributions
 Yao-3.269
 Debor-3.066
 unden-2.915
••-2.874
 Palest-2.842
Token this
Token ID428
Feature activation-1.52e+00

Pos logit contributions
olla+0.492
ktop+0.491
acs+0.490
rog+0.478
 impaired+0.466
Neg logit contributions
 Yao-0.456
 Debor-0.406
 intern-0.399
 JC-0.398
 Spencer-0.397
Token comment
Token ID2912
Feature activation-6.11e+00

Pos logit contributions
acs+1.169
olla+1.169
ktop+1.164
rog+1.151
 impaired+1.123
Neg logit contributions
 Yao-1.080
 Debor-0.974
 unden-0.951
 Spencer-0.937
 JC-0.937
Token on
Token ID319
Feature activation-3.76e+00

Pos logit contributions
olla+4.205
acs+4.154
ktop+4.126
rog+4.109
 impaired+4.023
Neg logit contributions
 Yao-4.709
 unden-4.698
 Debor-4.400
 confir-4.308
 Palest-4.261
Token Twitter
Token ID3009
Feature activation-4.22e+00

Pos logit contributions
olla+2.657
rog+2.632
acs+2.617
ktop+2.598
 impaired+2.559
Neg logit contributions
 Yao-2.879
 unden-2.580
 Debor-2.570
 Palest-2.470
••-2.443
Token
Token ID198
Feature activation-2.44e+00

Pos logit contributions
acs+2.600
olla+2.594
ktop+2.557
rog+2.531
 impaired+2.494
Neg logit contributions
 Yao-3.556
 Debor-3.262
 intern-3.190
 unden-3.185
••-3.169
Token
Token ID198
Feature activation-1.63e+00

Pos logit contributions
ktop+1.456
acs+1.456
olla+1.454
rog+1.417
 impaired+1.375
Neg logit contributions
 Yao-2.174
 Debor-1.985
 JC-1.951
 intern-1.950
 Spencer-1.948
TokenNY
Token ID12805
Feature activation-8.22e-01

Pos logit contributions
ktop+1.100
acs+1.098
olla+1.097
rog+1.070
 impaired+1.047
Neg logit contributions
 Yao-1.322
 Debor-1.198
 JC-1.174
 intern-1.174
 Spencer-1.173
Token
Token ID198
Feature activation-2.19e+00

Pos logit contributions
ktop+0.204
acs+0.201
olla+0.200
rog+0.194
 impaired+0.189
Neg logit contributions
 Yao-0.268
 Debor-0.242
 JC-0.241
 Spencer-0.239
 intern-0.239
Token
Token ID198
Feature activation-9.84e-01

Pos logit contributions
ktop+1.342
acs+1.333
olla+1.331
rog+1.295
 impaired+1.262
Neg logit contributions
 Yao-1.931
 Debor-1.752
 JC-1.731
 intern-1.727
 Spencer-1.727
TokenRecommend
Token ID41248
Feature activation+1.30e+00

Pos logit contributions
ktop+0.674
acs+0.673
olla+0.671
rog+0.657
 impaired+0.640
Neg logit contributions
 Yao-0.789
 Debor-0.714
 JC-0.700
 intern-0.699
 Spencer-0.698
Token Share
Token ID8734
Feature activation+2.09e-01

Pos logit contributions
 Yao+0.763
 Debor+0.660
 JC+0.651
 Spencer+0.651
 intern+0.650
Neg logit contributions
ktop-1.169
olla-1.169
acs-1.168
rog-1.142
 impaired-1.119
Token this
Token ID428
Feature activation-3.14e+00

Pos logit contributions
 Yao+0.145
 Debor+0.128
 Spencer+0.127
 intern+0.127
 JC+0.126
Neg logit contributions
ktop-0.169
olla-0.168
acs-0.167
rog-0.162
\/\/-0.158
Token comment
Token ID2912
Feature activation-6.02e+00

Pos logit contributions
acs+2.387
olla+2.386
ktop+2.380
rog+2.346
 impaired+2.293
Neg logit contributions
 Yao-2.257
 Debor-2.049
 unden-1.999
 intern-1.956
 Spencer-1.955
Token on
Token ID319
Feature activation-3.72e+00

Pos logit contributions
olla+3.824
 impaired+3.772
rog+3.763
ktop+3.718
acs+3.704
Neg logit contributions
 Yao-4.931
 unden-4.679
 Debor-4.609
 confir-4.421
••-4.344
Token Facebook
Token ID3203
Feature activation-4.44e+00

Pos logit contributions
olla+2.197
acs+2.176
ktop+2.162
rog+2.156
 impaired+2.109
Neg logit contributions
 Yao-3.268
 Debor-3.041
 unden-2.970
 intern-2.878
 JC-2.869
Token Share
Token ID8734
Feature activation-6.36e-01

Pos logit contributions
acs+3.128
olla+3.120
 impaired+3.089
rog+3.068
lime+3.031
Neg logit contributions
 Yao-3.269
 Debor-3.066
 unden-2.915
••-2.874
 Palest-2.842
Token this
Token ID428
Feature activation-1.52e+00

Pos logit contributions
olla+0.492
ktop+0.491
acs+0.490
rog+0.478
 impaired+0.466
Neg logit contributions
 Yao-0.456
 Debor-0.406
 intern-0.399
 JC-0.398
 Spencer-0.397
Token comment
Token ID2912
Feature activation-6.11e+00

Pos logit contributions
acs+1.169
olla+1.169
ktop+1.164
rog+1.151
 impaired+1.123
Neg logit contributions
 Yao-1.080
 Debor-0.974
 unden-0.951
 Spencer-0.937
 JC-0.937
Token type
Token ID2099
Feature activation-2.38e+00

Pos logit contributions
olla+1.600
acs+1.596
ktop+1.582
rog+1.559
 impaired+1.521
Neg logit contributions
 Yao-1.788
 Debor-1.626
 intern-1.580
 unden-1.578
 JC-1.576
Token-
Token ID12
Feature activation-1.88e-01

Pos logit contributions
acs+1.497
olla+1.496
ktop+1.472
rog+1.461
 impaired+1.422
Neg logit contributions
 Yao-2.026
 Debor-1.854
 unden-1.805
 Spencer-1.798
 intern-1.796
Token94
Token ID5824
Feature activation-1.84e+00

Pos logit contributions
ktop+0.142
acs+0.141
olla+0.141
rog+0.138
 impaired+0.135
Neg logit contributions
 Yao-0.138
 Debor-0.124
 JC-0.122
 Spencer-0.121
 intern-0.121
Token Jin
Token ID17297
Feature activation-1.64e+00

Pos logit contributions
olla+1.510
acs+1.507
ktop+1.501
rog+1.482
 impaired+1.450
Neg logit contributions
 Yao-1.204
 Debor-1.074
 intern-1.045
 unden-1.043
 JC-1.040
Token-
Token ID12
Feature activation-1.86e+00

Pos logit contributions
olla+1.121
acs+1.120
ktop+1.111
rog+1.096
 impaired+1.063
Neg logit contributions
 Yao-1.310
 Debor-1.197
 intern-1.165
 Spencer-1.164
 JC-1.163
Tokenclass
Token ID4871
Feature activation-5.99e+00

Pos logit contributions
acs+1.319
olla+1.319
ktop+1.311
rog+1.292
 impaired+1.252
Neg logit contributions
 Yao-1.444
 Debor-1.310
 intern-1.279
 Spencer-1.275
 JC-1.273
Token and
Token ID290
Feature activation-2.11e+00

Pos logit contributions
olla+4.195
acs+4.189
rog+4.117
ktop+4.046
 impaired+4.022
Neg logit contributions
 Yao-4.506
 Debor-4.127
 unden-4.033
 Spencer-3.960
 JC-3.939
Token type
Token ID2099
Feature activation-2.70e+00

Pos logit contributions
olla+1.477
acs+1.475
ktop+1.468
rog+1.445
 impaired+1.411
Neg logit contributions
 Yao-1.646
 Debor-1.494
 intern-1.454
 Spencer-1.452
 JC-1.450
Token-
Token ID12
Feature activation-3.21e-01

Pos logit contributions
olla+1.750
acs+1.749
ktop+1.742
rog+1.711
 impaired+1.661
Neg logit contributions
 Yao-2.250
 Debor-2.054
 unden-2.010
 intern-2.005
 Spencer-2.000
Token96
Token ID4846
Feature activation-4.92e-01

Pos logit contributions
ktop+0.228
olla+0.226
acs+0.226
rog+0.221
 impaired+0.217
Neg logit contributions
 Yao-0.250
 Debor-0.225
 JC-0.222
 Spencer-0.221
 intern-0.221
Token),
Token ID828
Feature activation-2.38e+00

Pos logit contributions
olla+0.385
acs+0.385
ktop+0.384
rog+0.378
 impaired+0.369
Neg logit contributions
 Yao-0.344
 Debor-0.308
 intern-0.300
 JC-0.299
 Spencer-0.299
Token:
Token ID25
Feature activation-3.59e-01

Pos logit contributions
 Yao+1.201
 Debor+1.052
 JC+1.040
 Spencer+1.033
 intern+1.028
Neg logit contributions
ktop-1.564
acs-1.551
olla-1.544
rog-1.520
 impaired-1.488
Token 05
Token ID8870
Feature activation+8.40e-01

Pos logit contributions
acs+0.289
ktop+0.288
olla+0.288
rog+0.284
 impaired+0.277
Neg logit contributions
 Yao-0.245
 Debor-0.218
 JC-0.213
 intern-0.213
 Spencer-0.212
Token43
Token ID3559
Feature activation-1.28e+00

Pos logit contributions
 Yao+0.536
 Debor+0.470
 JC+0.458
 Spencer+0.455
 intern+0.454
Neg logit contributions
ktop-0.719
acs-0.714
olla-0.711
rog-0.699
 impaired-0.689
Tokenz
Token ID89
Feature activation+2.64e-02

Pos logit contributions
ktop+0.732
acs+0.727
olla+0.726
rog+0.706
 impaired+0.690
Neg logit contributions
 Yao-1.168
 Debor-1.069
 intern-1.055
 JC-1.054
 Spencer-1.052
Token ST
Token ID3563
Feature activation-1.71e+00

Pos logit contributions
 Yao+0.019
 Debor+0.017
 JC+0.017
 intern+0.017
 Spencer+0.017
Neg logit contributions
ktop-0.020
acs-0.020
olla-0.020
rog-0.020
 impaired-0.019
TokenOW
Token ID3913
Feature activation-5.91e+00

Pos logit contributions
olla+1.151
acs+1.147
ktop+1.140
rog+1.124
 impaired+1.089
Neg logit contributions
 Yao-1.378
 Debor-1.259
 JC-1.224
 intern-1.224
 Spencer-1.220
Token MA
Token ID8779
Feature activation-7.64e-01

Pos logit contributions
olla+4.503
acs+4.484
ktop+4.403
rog+4.358
 impaired+4.305
Neg logit contributions
 Yao-4.113
 Debor-3.683
 unden-3.647
 intern-3.549
 Spencer-3.543
TokenIN
Token ID1268
Feature activation-5.78e-01

Pos logit contributions
acs+0.648
ktop+0.648
olla+0.647
rog+0.636
 impaired+0.624
Neg logit contributions
 Yao-0.488
 Debor-0.427
 JC-0.420
 intern-0.418
 Spencer-0.418
Token RE
Token ID4526
Feature activation+2.77e-01

Pos logit contributions
olla+0.439
acs+0.439
ktop+0.439
rog+0.430
 impaired+0.419
Neg logit contributions
 Yao-0.420
 Debor-0.377
 JC-0.368
 intern-0.368
 Spencer-0.367
TokenP
Token ID47
Feature activation-1.85e-01

Pos logit contributions
 Yao+0.206
 Debor+0.185
 intern+0.180
 JC+0.180
 Spencer+0.180
Neg logit contributions
olla-0.206
acs-0.206
ktop-0.206
rog-0.202
 impaired-0.197
TokenORTS
Token ID33002
Feature activation-4.89e-01

Pos logit contributions
acs+0.149
olla+0.149
ktop+0.148
rog+0.146
 impaired+0.142
Neg logit contributions
 Yao-0.126
 Debor-0.112
 intern-0.109
 JC-0.109
 Spencer-0.109
Token comment
Token ID2912
Feature activation-5.80e+00

Pos logit contributions
olla+2.033
acs+2.032
ktop+2.023
rog+1.997
 impaired+1.952
Neg logit contributions
 Yao-1.848
 Debor-1.661
 unden-1.614
 JC-1.603
 Spencer-1.603
Token on
Token ID319
Feature activation-4.33e+00

Pos logit contributions
olla+4.064
acs+4.014
ktop+3.982
rog+3.977
 impaired+3.876
Neg logit contributions
 Yao-4.420
 unden-4.356
 Debor-4.108
 confir-4.069
 Palest-3.948
Token Facebook
Token ID3203
Feature activation-5.23e+00

Pos logit contributions
olla+2.690
acs+2.667
ktop+2.646
rog+2.625
 impaired+2.510
Neg logit contributions
 Yao-3.632
 unden-3.473
 Debor-3.405
 confir-3.315
 intern-3.273
Token Share
Token ID8734
Feature activation-8.02e-01

Pos logit contributions
acs+3.938
olla+3.935
rog+3.858
ktop+3.856
 impaired+3.774
Neg logit contributions
 Yao-3.580
 unden-3.483
 Debor-3.342
 confir-3.254
 intern-3.160
Token this
Token ID428
Feature activation-1.65e+00

Pos logit contributions
ktop+0.625
acs+0.624
olla+0.622
rog+0.608
 impaired+0.593
Neg logit contributions
 Yao-0.570
 Debor-0.506
 intern-0.499
 JC-0.498
 Spencer-0.498
Token comment
Token ID2912
Feature activation-5.83e+00

Pos logit contributions
olla+1.305
acs+1.305
ktop+1.303
rog+1.280
 impaired+1.250
Neg logit contributions
 Yao-1.151
 Debor-1.027
 intern-1.000
 JC-0.999
 Spencer-0.998
Token on
Token ID319
Feature activation-3.85e+00

Pos logit contributions
olla+4.156
acs+4.110
ktop+4.085
rog+4.063
 impaired+3.966
Neg logit contributions
 Yao-4.384
 unden-4.268
 Debor-4.064
 confir-3.998
 Palest-3.899
Token Twitter
Token ID3009
Feature activation-5.27e+00

Pos logit contributions
olla+2.885
acs+2.846
rog+2.838
ktop+2.820
 impaired+2.748
Neg logit contributions
 Yao-2.730
 unden-2.570
 Debor-2.472
 confir-2.460
 intern-2.399
Token
Token ID198
Feature activation-3.78e+00

Pos logit contributions
olla+2.955
acs+2.951
ktop+2.895
rog+2.884
 impaired+2.798
Neg logit contributions
 Yao-4.707
 Debor-4.340
 unden-4.245
 intern-4.237
••-4.226
Token
Token ID198
Feature activation-3.12e+00

Pos logit contributions
olla+2.146
acs+2.140
ktop+2.119
rog+2.089
 impaired+2.012
Neg logit contributions
 Yao-3.453
 Debor-3.191
 unden-3.176
 intern-3.116
 JC-3.104
TokenNY
Token ID12805
Feature activation-6.62e-01

Pos logit contributions
olla+1.847
acs+1.846
ktop+1.832
rog+1.804
 impaired+1.734
Neg logit contributions
 Yao-2.787
 Debor-2.557
 intern-2.502
 JC-2.497
 Spencer-2.495
Token
Token ID198
Feature activation-2.44e+00

Pos logit contributions
ktop+1.073
acs+1.068
olla+1.066
rog+1.035
 impaired+1.007
Neg logit contributions
 Yao-1.535
 Debor-1.395
 JC-1.375
 Spencer-1.373
 intern-1.373
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
ktop+1.461
acs+1.459
olla+1.458
rog+1.419
 impaired+1.378
Neg logit contributions
 Yao-2.172
 Debor-1.982
 JC-1.948
 intern-1.948
 Spencer-1.946
TokenRecommend
Token ID41248
Feature activation+8.69e-01

Pos logit contributions
ktop+0.933
acs+0.925
olla+0.917
rog+0.895
 impaired+0.885
Neg logit contributions
 Yao-1.004
 Debor-0.898
 JC-0.889
 Spencer-0.887
••-0.886
Token Share
Token ID8734
Feature activation-1.61e-01

Pos logit contributions
 Yao+0.505
 Debor+0.435
 Spencer+0.431
 JC+0.431
 intern+0.427
Neg logit contributions
ktop-0.793
acs-0.791
olla-0.790
rog-0.772
 impaired-0.756
Token this
Token ID428
Feature activation-2.62e+00

Pos logit contributions
ktop+0.131
olla+0.130
acs+0.130
rog+0.126
lime+0.122
Neg logit contributions
 Yao-0.110
 intern-0.097
 Debor-0.097
 JC-0.096
 Spencer-0.096
Token comment
Token ID2912
Feature activation-5.80e+00

Pos logit contributions
olla+2.033
acs+2.032
ktop+2.023
rog+1.997
 impaired+1.952
Neg logit contributions
 Yao-1.848
 Debor-1.661
 unden-1.614
 JC-1.603
 Spencer-1.603
Token on
Token ID319
Feature activation-4.33e+00

Pos logit contributions
olla+4.064
acs+4.014
ktop+3.982
rog+3.977
 impaired+3.876
Neg logit contributions
 Yao-4.420
 unden-4.356
 Debor-4.108
 confir-4.069
 Palest-3.948
Token Facebook
Token ID3203
Feature activation-5.23e+00

Pos logit contributions
olla+2.690
acs+2.667
ktop+2.646
rog+2.625
 impaired+2.510
Neg logit contributions
 Yao-3.632
 unden-3.473
 Debor-3.405
 confir-3.315
 intern-3.273
Token Share
Token ID8734
Feature activation-8.02e-01

Pos logit contributions
acs+3.938
olla+3.935
rog+3.858
ktop+3.856
 impaired+3.774
Neg logit contributions
 Yao-3.580
 unden-3.483
 Debor-3.342
 confir-3.254
 intern-3.160
Token this
Token ID428
Feature activation-1.65e+00

Pos logit contributions
ktop+0.625
acs+0.624
olla+0.622
rog+0.608
 impaired+0.593
Neg logit contributions
 Yao-0.570
 Debor-0.506
 intern-0.499
 JC-0.498
 Spencer-0.498
Token comment
Token ID2912
Feature activation-5.83e+00

Pos logit contributions
olla+1.305
acs+1.305
ktop+1.303
rog+1.280
 impaired+1.250
Neg logit contributions
 Yao-1.151
 Debor-1.027
 intern-1.000
 JC-0.999
 Spencer-0.998
Token Middle
Token ID6046
Feature activation-1.84e-01

Pos logit contributions
olla+0.881
ktop+0.881
acs+0.880
rog+0.863
 impaired+0.842
Neg logit contributions
 Yao-0.779
 Debor-0.697
 intern-0.679
 JC-0.678
 Spencer-0.677
Token Level
Token ID5684
Feature activation+1.07e+00

Pos logit contributions
olla+0.138
ktop+0.138
acs+0.137
rog+0.134
 impaired+0.131
Neg logit contributions
 Yao-0.135
 Debor-0.121
 JC-0.119
 intern-0.118
 Spencer-0.118
Token Education
Token ID7868
Feature activation-1.06e+00

Pos logit contributions
 Yao+0.735
 Debor+0.656
 intern+0.641
 JC+0.641
 Spencer+0.639
Neg logit contributions
ktop-0.859
olla-0.857
acs-0.853
rog-0.835
 impaired-0.816
Token,
Token ID11
Feature activation-5.10e-01

Pos logit contributions
acs+0.801
olla+0.800
ktop+0.798
rog+0.784
 impaired+0.766
Neg logit contributions
 Yao-0.772
 Debor-0.692
 intern-0.674
 JC-0.674
 Spencer-0.673
Token 33
Token ID4747
Feature activation-1.41e+00

Pos logit contributions
olla+0.395
acs+0.395
ktop+0.394
rog+0.387
 impaired+0.377
Neg logit contributions
 Yao-0.363
 Debor-0.324
 intern-0.317
 JC-0.316
 Spencer-0.316
Token(
Token ID7
Feature activation-5.66e+00

Pos logit contributions
olla+0.952
acs+0.951
ktop+0.938
rog+0.928
 impaired+0.901
Neg logit contributions
 Yao-1.143
 Debor-1.036
 Spencer-1.008
 unden-1.005
 JC-1.004
Token10
Token ID940
Feature activation-1.25e+00

Pos logit contributions
olla+4.049
acs+4.045
rog+3.963
ktop+3.952
 impaired+3.825
Neg logit contributions
 Yao-4.256
 Debor-3.848
 unden-3.799
 intern-3.740
 JC-3.685
Token),
Token ID828
Feature activation-6.29e-01

Pos logit contributions
olla+0.739
acs+0.739
ktop+0.736
rog+0.720
 impaired+0.697
Neg logit contributions
 Yao-1.118
 Debor-1.024
 intern-1.003
 JC-1.002
 Spencer-1.001
Token 1
Token ID352
Feature activation-2.03e-01

Pos logit contributions
olla+0.494
acs+0.494
ktop+0.494
rog+0.484
 impaired+0.473
Neg logit contributions
 Yao-0.441
 Debor-0.393
 JC-0.383
 intern-0.383
 Spencer-0.382
Token -
Token ID532
Feature activation-2.72e-02

Pos logit contributions
ktop+0.118
olla+0.118
acs+0.117
rog+0.115
 impaired+0.111
Neg logit contributions
 Yao-0.184
 Debor-0.169
 JC-0.166
 Spencer-0.166
 intern-0.166
Token 13
Token ID1511
Feature activation+5.82e-01

Pos logit contributions
ktop+0.022
acs+0.022
olla+0.022
rog+0.022
 impaired+0.021
Neg logit contributions
 Yao-0.018
 Debor-0.016
 JC-0.016
 intern-0.016
 Spencer-0.016
Token
Token ID198
Feature activation-1.94e+00

Pos logit contributions
ktop+1.291
acs+1.288
olla+1.287
rog+1.251
 impaired+1.215
Neg logit contributions
 Yao-1.901
 Debor-1.734
 JC-1.704
 intern-1.703
 Spencer-1.701
Token
Token ID198
Feature activation-7.76e-01

Pos logit contributions
ktop+1.183
acs+1.177
olla+1.175
rog+1.143
 impaired+1.113
Neg logit contributions
 Yao-1.708
 Debor-1.552
 JC-1.531
 intern-1.529
 Spencer-1.528
TokenRecommend
Token ID41248
Feature activation+4.69e-01

Pos logit contributions
ktop+0.572
acs+0.564
olla+0.558
rog+0.544
 impaired+0.543
Neg logit contributions
 Yao-0.589
 Debor-0.522
 JC-0.521
••-0.520
 Spencer-0.519
Token Share
Token ID8734
Feature activation-1.43e-01

Pos logit contributions
 Yao+0.277
 Debor+0.240
 JC+0.236
 Spencer+0.236
 intern+0.235
Neg logit contributions
ktop-0.423
acs-0.422
olla-0.421
rog-0.412
 impaired-0.404
Token this
Token ID428
Feature activation-2.46e+00

Pos logit contributions
ktop+0.116
acs+0.116
olla+0.115
rog+0.112
 impaired+0.109
Neg logit contributions
 Yao-0.098
 Debor-0.086
 intern-0.086
 JC-0.086
 Spencer-0.086
Token comment
Token ID2912
Feature activation-5.62e+00

Pos logit contributions
olla+1.932
acs+1.932
ktop+1.927
rog+1.896
 impaired+1.853
Neg logit contributions
 Yao-1.722
 Debor-1.540
 JC-1.494
 intern-1.494
 Spencer-1.493
Token on
Token ID319
Feature activation-4.10e+00

Pos logit contributions
olla+4.007
acs+3.961
ktop+3.929
rog+3.912
 impaired+3.818
Neg logit contributions
 Yao-4.236
 unden-4.109
 Debor-3.915
 confir-3.851
 Palest-3.743
Token Facebook
Token ID3203
Feature activation-5.04e+00

Pos logit contributions
olla+2.641
acs+2.624
ktop+2.609
rog+2.571
 impaired+2.473
Neg logit contributions
 Yao-3.383
 unden-3.175
 Debor-3.150
 intern-3.046
 confir-3.040
Token Share
Token ID8734
Feature activation-8.25e-01

Pos logit contributions
olla+3.893
acs+3.883
ktop+3.832
rog+3.805
 impaired+3.715
Neg logit contributions
 Yao-3.384
 unden-3.283
 Debor-3.139
 confir-3.083
 intern-2.991
Token this
Token ID428
Feature activation-1.44e+00

Pos logit contributions
ktop+0.644
acs+0.644
olla+0.642
rog+0.627
 impaired+0.611
Neg logit contributions
 Yao-0.585
 Debor-0.519
 intern-0.512
 JC-0.511
 Spencer-0.511
Token comment
Token ID2912
Feature activation-5.56e+00

Pos logit contributions
acs+1.150
olla+1.149
ktop+1.149
rog+1.125
 impaired+1.099
Neg logit contributions
 Yao-0.995
 Debor-0.884
 intern-0.866
 JC-0.864
 Spencer-0.862
Token10
Token ID940
Feature activation+7.43e-02

Pos logit contributions
ktop+0.378
olla+0.377
acs+0.375
rog+0.368
 impaired+0.361
Neg logit contributions
 Yao-0.411
 Debor-0.370
 Spencer-0.362
 intern-0.362
 JC-0.361
Token.
Token ID13
Feature activation-2.02e+00

Pos logit contributions
 Yao+0.055
 Debor+0.049
 JC+0.048
 intern+0.048
 Spencer+0.048
Neg logit contributions
ktop-0.055
acs-0.055
olla-0.055
rog-0.054
 impaired-0.053
Token13
Token ID1485
Feature activation-1.73e+00

Pos logit contributions
ktop+1.660
olla+1.654
acs+1.644
rog+1.610
 impaired+1.592
Neg logit contributions
 Yao-1.336
 Debor-1.177
••-1.160
 Spencer-1.157
 JC-1.157
Token71
Token ID4869
Feature activation-2.49e+00

Pos logit contributions
olla+1.252
ktop+1.251
acs+1.249
rog+1.226
 impaired+1.199
Neg logit contributions
 Yao-1.323
 Debor-1.189
 intern-1.173
 unden-1.171
 Spencer-1.157
Token/
Token ID14
Feature activation-2.26e+00

Pos logit contributions
ktop+1.780
acs+1.775
olla+1.775
rog+1.738
 impaired+1.700
Neg logit contributions
 Yao-1.932
 Debor-1.736
 JC-1.705
 Spencer-1.703
 intern-1.699
Tokenjournal
Token ID24891
Feature activation-5.62e+00

Pos logit contributions
ktop+1.366
olla+1.365
acs+1.359
rog+1.329
 impaired+1.291
Neg logit contributions
 Yao-1.984
 Debor-1.812
 JC-1.781
 intern-1.781
 Spencer-1.777
Token.
Token ID13
Feature activation-2.47e+00

Pos logit contributions
olla+3.741
acs+3.722
rog+3.668
ktop+3.652
 impaired+3.439
Neg logit contributions
 Yao-4.586
 unden-4.457
 Debor-4.265
 confir-4.199
 Spencer-4.101
Tokenp
Token ID79
Feature activation-2.79e+00

Pos logit contributions
acs+1.956
olla+1.939
ktop+1.914
rog+1.909
 impaired+1.831
Neg logit contributions
 Yao-1.751
 Debor-1.577
 unden-1.537
 JC-1.521
 Spencer-1.516
Tokenone
Token ID505
Feature activation-2.48e-01

Pos logit contributions
olla+2.722
acs+2.718
ktop+2.677
rog+2.671
 impaired+2.588
Neg logit contributions
 Yao-1.457
 Debor-1.288
 unden-1.212
 JC-1.203
 Spencer-1.188
Token.
Token ID13
Feature activation-9.27e-01

Pos logit contributions
ktop+0.190
acs+0.189
olla+0.188
rog+0.184
 impaired+0.182
Neg logit contributions
 Yao-0.180
 JC-0.157
 Debor-0.157
 intern-0.156
 Spencer-0.155
Token00
Token ID405
Feature activation-5.57e-01

Pos logit contributions
ktop+0.673
olla+0.672
acs+0.671
rog+0.658
 impaired+0.644
Neg logit contributions
 Yao-0.704
 Debor-0.632
 intern-0.620
 JC-0.619
 Spencer-0.618
Token comment
Token ID2912
Feature activation-5.43e+00

Pos logit contributions
olla+1.928
acs+1.927
ktop+1.922
rog+1.892
 impaired+1.849
Neg logit contributions
 Yao-1.721
 Debor-1.541
 JC-1.494
 intern-1.494
 Spencer-1.493
Token on
Token ID319
Feature activation-4.03e+00

Pos logit contributions
olla+3.873
acs+3.830
ktop+3.801
rog+3.786
 impaired+3.692
Neg logit contributions
 Yao-4.089
 unden-3.966
 Debor-3.781
 confir-3.714
 Palest-3.612
Token Facebook
Token ID3203
Feature activation-5.02e+00

Pos logit contributions
olla+2.585
acs+2.567
ktop+2.551
rog+2.519
 impaired+2.418
Neg logit contributions
 Yao-3.334
 unden-3.144
 Debor-3.110
 confir-3.009
 intern-3.005
Token Share
Token ID8734
Feature activation-5.72e-01

Pos logit contributions
olla+3.867
acs+3.861
ktop+3.799
rog+3.784
 impaired+3.694
Neg logit contributions
 Yao-3.374
 unden-3.274
 Debor-3.134
 confir-3.078
 intern-2.981
Token this
Token ID428
Feature activation-1.63e+00

Pos logit contributions
ktop+0.449
acs+0.448
olla+0.447
rog+0.437
 impaired+0.425
Neg logit contributions
 Yao-0.404
 Debor-0.358
 intern-0.353
 JC-0.353
 Spencer-0.353
Token comment
Token ID2912
Feature activation-5.59e+00

Pos logit contributions
acs+1.286
olla+1.286
ktop+1.284
rog+1.261
 impaired+1.231
Neg logit contributions
 Yao-1.128
 Debor-1.005
 intern-0.980
 JC-0.979
 Spencer-0.977
Token on
Token ID319
Feature activation-3.49e+00

Pos logit contributions
olla+4.014
acs+3.970
ktop+3.948
rog+3.921
 impaired+3.832
Neg logit contributions
 Yao-4.189
 unden-4.041
 Debor-3.870
 confir-3.786
 Palest-3.699
Token Twitter
Token ID3009
Feature activation-4.94e+00

Pos logit contributions
olla+2.653
acs+2.624
rog+2.613
ktop+2.601
 impaired+2.535
Neg logit contributions
 Yao-2.460
 unden-2.294
 Debor-2.220
 confir-2.193
 intern-2.155
Token
Token ID198
Feature activation-4.10e+00

Pos logit contributions
acs+2.706
olla+2.700
ktop+2.649
rog+2.639
 impaired+2.553
Neg logit contributions
 Yao-4.502
 Debor-4.157
 unden-4.060
 intern-4.058
••-4.044
Token
Token ID198
Feature activation-3.56e+00

Pos logit contributions
olla+2.296
acs+2.289
ktop+2.259
rog+2.235
 impaired+2.148
Neg logit contributions
 Yao-3.764
 unden-3.497
 Debor-3.488
 intern-3.401
 JC-3.385
TokenNY
Token ID12805
Feature activation-4.09e-01

Pos logit contributions
acs+2.064
olla+2.063
ktop+2.040
rog+2.020
 impaired+1.928
Neg logit contributions
 Yao-3.219
 Debor-2.962
 intern-2.894
 JC-2.886
 Spencer-2.885
Token type
Token ID2099
Feature activation-1.17e+00

Pos logit contributions
acs+0.604
olla+0.604
ktop+0.601
rog+0.590
 impaired+0.575
Neg logit contributions
 Yao-0.702
 Debor-0.636
 intern-0.621
 JC-0.621
 Spencer-0.620
Token-
Token ID12
Feature activation-4.97e-01

Pos logit contributions
acs+0.785
olla+0.785
ktop+0.784
rog+0.767
 impaired+0.746
Neg logit contributions
 Yao-0.947
 Debor-0.860
 intern-0.841
 JC-0.840
 Spencer-0.839
Token93
Token ID6052
Feature activation-1.87e-01

Pos logit contributions
ktop+0.358
olla+0.356
acs+0.355
rog+0.347
 impaired+0.339
Neg logit contributions
 Yao-0.382
 Debor-0.344
 intern-0.337
 JC-0.336
 Spencer-0.336
Token Shang
Token ID45797
Feature activation+3.55e-01

Pos logit contributions
ktop+0.133
acs+0.133
olla+0.133
rog+0.130
 impaired+0.127
Neg logit contributions
 Yao-0.144
 Debor-0.130
 intern-0.127
 JC-0.127
 Spencer-0.127
Token-
Token ID12
Feature activation-1.19e+00

Pos logit contributions
 Yao+0.292
 Debor+0.262
 JC+0.258
 Spencer+0.258
 intern+0.257
Neg logit contributions
ktop-0.239
acs-0.238
olla-0.235
rog-0.229
 impaired-0.225
Tokenclass
Token ID4871
Feature activation-5.57e+00

Pos logit contributions
ktop+0.864
acs+0.863
olla+0.863
rog+0.844
 impaired+0.825
Neg logit contributions
 Yao-0.899
 Debor-0.808
 intern-0.789
 JC-0.789
 Spencer-0.788
Token and
Token ID290
Feature activation-2.45e+00

Pos logit contributions
acs+3.776
olla+3.767
rog+3.682
ktop+3.654
 impaired+3.609
Neg logit contributions
 Yao-4.367
 Debor-3.994
 unden-3.891
 Spencer-3.836
 JC-3.825
Token type
Token ID2099
Feature activation-2.53e+00

Pos logit contributions
olla+1.758
acs+1.754
ktop+1.739
rog+1.723
 impaired+1.687
Neg logit contributions
 Yao-1.850
 Debor-1.685
 unden-1.641
 intern-1.629
 Spencer-1.626
Token-
Token ID12
Feature activation-3.62e-01

Pos logit contributions
olla+1.615
acs+1.611
ktop+1.589
rog+1.580
 impaired+1.533
Neg logit contributions
 Yao-2.132
 Debor-1.956
 unden-1.903
 intern-1.896
 Spencer-1.891
Token95
Token ID3865
Feature activation-5.73e-01

Pos logit contributions
ktop+0.272
acs+0.270
olla+0.270
rog+0.264
 impaired+0.259
Neg logit contributions
 Yao-0.268
 Debor-0.240
 JC-0.235
 Spencer-0.235
 intern-0.234
Token,
Token ID11
Feature activation-1.76e+00

Pos logit contributions
olla+0.485
acs+0.485
ktop+0.484
rog+0.477
 impaired+0.466
Neg logit contributions
 Yao-0.363
 Debor-0.321
 intern-0.312
 JC-0.311
 Spencer-0.311
Token comment
Token ID2912
Feature activation-5.62e+00

Pos logit contributions
olla+1.932
acs+1.932
ktop+1.927
rog+1.896
 impaired+1.853
Neg logit contributions
 Yao-1.722
 Debor-1.540
 JC-1.494
 intern-1.494
 Spencer-1.493
Token on
Token ID319
Feature activation-4.10e+00

Pos logit contributions
olla+4.007
acs+3.961
ktop+3.929
rog+3.912
 impaired+3.818
Neg logit contributions
 Yao-4.236
 unden-4.109
 Debor-3.915
 confir-3.851
 Palest-3.743
Token Facebook
Token ID3203
Feature activation-5.04e+00

Pos logit contributions
olla+2.641
acs+2.624
ktop+2.609
rog+2.571
 impaired+2.473
Neg logit contributions
 Yao-3.383
 unden-3.175
 Debor-3.150
 intern-3.046
 confir-3.040
Token Share
Token ID8734
Feature activation-8.25e-01

Pos logit contributions
olla+3.893
acs+3.883
ktop+3.832
rog+3.805
 impaired+3.715
Neg logit contributions
 Yao-3.384
 unden-3.283
 Debor-3.139
 confir-3.083
 intern-2.991
Token this
Token ID428
Feature activation-1.44e+00

Pos logit contributions
ktop+0.644
acs+0.644
olla+0.642
rog+0.627
 impaired+0.611
Neg logit contributions
 Yao-0.585
 Debor-0.519
 intern-0.512
 JC-0.511
 Spencer-0.511
Token comment
Token ID2912
Feature activation-5.56e+00

Pos logit contributions
acs+1.150
olla+1.149
ktop+1.149
rog+1.125
 impaired+1.099
Neg logit contributions
 Yao-0.995
 Debor-0.884
 intern-0.866
 JC-0.864
 Spencer-0.862
Token on
Token ID319
Feature activation-3.45e+00

Pos logit contributions
olla+4.009
acs+3.970
ktop+3.949
rog+3.918
 impaired+3.830
Neg logit contributions
 Yao-4.160
 unden-3.991
 Debor-3.832
 confir-3.741
 Palest-3.660
Token Twitter
Token ID3009
Feature activation-4.94e+00

Pos logit contributions
olla+2.626
acs+2.599
rog+2.585
ktop+2.575
 impaired+2.509
Neg logit contributions
 Yao-2.423
 unden-2.252
 Debor-2.187
 confir-2.149
 intern-2.121
Token
Token ID198
Feature activation-4.42e+00

Pos logit contributions
acs+2.698
olla+2.690
ktop+2.639
rog+2.632
 impaired+2.541
Neg logit contributions
 Yao-4.512
 Debor-4.165
 unden-4.072
 intern-4.069
••-4.050
Token
Token ID198
Feature activation-3.99e+00

Pos logit contributions
olla+2.443
acs+2.434
ktop+2.395
rog+2.378
 impaired+2.281
Neg logit contributions
 Yao-4.079
 unden-3.823
 Debor-3.788
 intern-3.690
 confir-3.679
TokenNY
Token ID12805
Feature activation-6.65e-01

Pos logit contributions
acs+2.286
olla+2.283
ktop+2.248
rog+2.239
 impaired+2.126
Neg logit contributions
 Yao-3.636
 Debor-3.352
 intern-3.270
 JC-3.260
 Spencer-3.260
Token
Token ID198
Feature activation-1.70e+00

Pos logit contributions
ktop+1.004
acs+0.998
olla+0.997
rog+0.969
 impaired+0.942
Neg logit contributions
 Yao-1.438
 Debor-1.308
 JC-1.288
 intern-1.287
 Spencer-1.286
Token
Token ID198
Feature activation-5.39e-01

Pos logit contributions
ktop+1.052
acs+1.044
olla+1.041
rog+1.013
 impaired+0.989
Neg logit contributions
 Yao-1.490
 Debor-1.350
 JC-1.336
 intern-1.333
 Spencer-1.333
TokenRecommend
Token ID41248
Feature activation+5.62e-01

Pos logit contributions
ktop+0.401
acs+0.395
olla+0.390
rog+0.381
 impaired+0.380
Neg logit contributions
 Yao-0.406
••-0.359
 Debor-0.359
 JC-0.358
 Spencer-0.357
Token Share
Token ID8734
Feature activation-9.53e-02

Pos logit contributions
 Yao+0.328
 Debor+0.283
 Spencer+0.280
 JC+0.280
 intern+0.278
Neg logit contributions
ktop-0.510
acs-0.508
olla-0.508
rog-0.497
 impaired-0.486
Token this
Token ID428
Feature activation-2.46e+00

Pos logit contributions
ktop+0.077
acs+0.077
olla+0.077
rog+0.075
 impaired+0.072
Neg logit contributions
 Yao-0.065
 Debor-0.057
 intern-0.057
 JC-0.057
 Spencer-0.057
Token comment
Token ID2912
Feature activation-5.43e+00

Pos logit contributions
olla+1.928
acs+1.927
ktop+1.922
rog+1.892
 impaired+1.849
Neg logit contributions
 Yao-1.721
 Debor-1.541
 JC-1.494
 intern-1.494
 Spencer-1.493
Token on
Token ID319
Feature activation-4.03e+00

Pos logit contributions
olla+3.873
acs+3.830
ktop+3.801
rog+3.786
 impaired+3.692
Neg logit contributions
 Yao-4.089
 unden-3.966
 Debor-3.781
 confir-3.714
 Palest-3.612
Token Facebook
Token ID3203
Feature activation-5.02e+00

Pos logit contributions
olla+2.585
acs+2.567
ktop+2.551
rog+2.519
 impaired+2.418
Neg logit contributions
 Yao-3.334
 unden-3.144
 Debor-3.110
 confir-3.009
 intern-3.005
Token Share
Token ID8734
Feature activation-5.72e-01

Pos logit contributions
olla+3.867
acs+3.861
ktop+3.799
rog+3.784
 impaired+3.694
Neg logit contributions
 Yao-3.374
 unden-3.274
 Debor-3.134
 confir-3.078
 intern-2.981
Token this
Token ID428
Feature activation-1.63e+00

Pos logit contributions
ktop+0.449
acs+0.448
olla+0.447
rog+0.437
 impaired+0.425
Neg logit contributions
 Yao-0.404
 Debor-0.358
 intern-0.353
 JC-0.353
 Spencer-0.353
Token comment
Token ID2912
Feature activation-5.59e+00

Pos logit contributions
acs+1.286
olla+1.286
ktop+1.284
rog+1.261
 impaired+1.231
Neg logit contributions
 Yao-1.128
 Debor-1.005
 intern-0.980
 JC-0.979
 Spencer-0.977
Token Facebook
Token ID3203
Feature activation-5.23e+00

Pos logit contributions
olla+2.690
acs+2.667
ktop+2.646
rog+2.625
 impaired+2.510
Neg logit contributions
 Yao-3.632
 unden-3.473
 Debor-3.405
 confir-3.315
 intern-3.273
Token Share
Token ID8734
Feature activation-8.02e-01

Pos logit contributions
acs+3.938
olla+3.935
rog+3.858
ktop+3.856
 impaired+3.774
Neg logit contributions
 Yao-3.580
 unden-3.483
 Debor-3.342
 confir-3.254
 intern-3.160
Token this
Token ID428
Feature activation-1.65e+00

Pos logit contributions
ktop+0.625
acs+0.624
olla+0.622
rog+0.608
 impaired+0.593
Neg logit contributions
 Yao-0.570
 Debor-0.506
 intern-0.499
 JC-0.498
 Spencer-0.498
Token comment
Token ID2912
Feature activation-5.83e+00

Pos logit contributions
olla+1.305
acs+1.305
ktop+1.303
rog+1.280
 impaired+1.250
Neg logit contributions
 Yao-1.151
 Debor-1.027
 intern-1.000
 JC-0.999
 Spencer-0.998
Token on
Token ID319
Feature activation-3.85e+00

Pos logit contributions
olla+4.156
acs+4.110
ktop+4.085
rog+4.063
 impaired+3.966
Neg logit contributions
 Yao-4.384
 unden-4.268
 Debor-4.064
 confir-3.998
 Palest-3.899
Token Twitter
Token ID3009
Feature activation-5.27e+00

Pos logit contributions
olla+2.885
acs+2.846
rog+2.838
ktop+2.820
 impaired+2.748
Neg logit contributions
 Yao-2.730
 unden-2.570
 Debor-2.472
 confir-2.460
 intern-2.399
Token
Token ID198
Feature activation-3.78e+00

Pos logit contributions
olla+2.955
acs+2.951
ktop+2.895
rog+2.884
 impaired+2.798
Neg logit contributions
 Yao-4.707
 Debor-4.340
 unden-4.245
 intern-4.237
••-4.226
Token
Token ID198
Feature activation-3.12e+00

Pos logit contributions
olla+2.146
acs+2.140
ktop+2.119
rog+2.089
 impaired+2.012
Neg logit contributions
 Yao-3.453
 Debor-3.191
 unden-3.176
 intern-3.116
 JC-3.104
TokenNY
Token ID12805
Feature activation-6.62e-01

Pos logit contributions
olla+1.847
acs+1.846
ktop+1.832
rog+1.804
 impaired+1.734
Neg logit contributions
 Yao-2.787
 Debor-2.557
 intern-2.502
 JC-2.497
 Spencer-2.495
TokenT
Token ID51
Feature activation-2.97e+00

Pos logit contributions
ktop+0.554
acs+0.549
olla+0.545
rog+0.536
 impaired+0.527
Neg logit contributions
 Yao-0.440
 JC-0.381
 Debor-0.380
 Spencer-0.379
 intern-0.377
Token Pick
Token ID12346
Feature activation-2.48e+00

Pos logit contributions
acs+1.555
ktop+1.554
olla+1.549
rog+1.503
 impaired+1.442
Neg logit contributions
 Yao-2.880
 Debor-2.645
 JC-2.614
 Spencer-2.612
 intern-2.610
TokenRecommend
Token ID41248
Feature activation+8.69e-01

Pos logit contributions
ktop+0.933
acs+0.925
olla+0.917
rog+0.895
 impaired+0.885
Neg logit contributions
 Yao-1.004
 Debor-0.898
 JC-0.889
 Spencer-0.887
••-0.886
Token Share
Token ID8734
Feature activation-1.61e-01

Pos logit contributions
 Yao+0.505
 Debor+0.435
 Spencer+0.431
 JC+0.431
 intern+0.427
Neg logit contributions
ktop-0.793
acs-0.791
olla-0.790
rog-0.772
 impaired-0.756
Token this
Token ID428
Feature activation-2.62e+00

Pos logit contributions
ktop+0.131
olla+0.130
acs+0.130
rog+0.126
lime+0.122
Neg logit contributions
 Yao-0.110
 intern-0.097
 Debor-0.097
 JC-0.096
 Spencer-0.096
Token comment
Token ID2912
Feature activation-5.80e+00

Pos logit contributions
olla+2.033
acs+2.032
ktop+2.023
rog+1.997
 impaired+1.952
Neg logit contributions
 Yao-1.848
 Debor-1.661
 unden-1.614
 JC-1.603
 Spencer-1.603
Token on
Token ID319
Feature activation-4.33e+00

Pos logit contributions
olla+4.064
acs+4.014
ktop+3.982
rog+3.977
 impaired+3.876
Neg logit contributions
 Yao-4.420
 unden-4.356
 Debor-4.108
 confir-4.069
 Palest-3.948
Token Facebook
Token ID3203
Feature activation-5.23e+00

Pos logit contributions
olla+2.690
acs+2.667
ktop+2.646
rog+2.625
 impaired+2.510
Neg logit contributions
 Yao-3.632
 unden-3.473
 Debor-3.405
 confir-3.315
 intern-3.273
Token Share
Token ID8734
Feature activation-8.02e-01

Pos logit contributions
acs+3.938
olla+3.935
rog+3.858
ktop+3.856
 impaired+3.774
Neg logit contributions
 Yao-3.580
 unden-3.483
 Debor-3.342
 confir-3.254
 intern-3.160
Token this
Token ID428
Feature activation-1.65e+00

Pos logit contributions
ktop+0.625
acs+0.624
olla+0.622
rog+0.608
 impaired+0.593
Neg logit contributions
 Yao-0.570
 Debor-0.506
 intern-0.499
 JC-0.498
 Spencer-0.498
Token comment
Token ID2912
Feature activation-5.83e+00

Pos logit contributions
olla+1.305
acs+1.305
ktop+1.303
rog+1.280
 impaired+1.250
Neg logit contributions
 Yao-1.151
 Debor-1.027
 intern-1.000
 JC-0.999
 Spencer-0.998
Token on
Token ID319
Feature activation-3.85e+00

Pos logit contributions
olla+4.156
acs+4.110
ktop+4.085
rog+4.063
 impaired+3.966
Neg logit contributions
 Yao-4.384
 unden-4.268
 Debor-4.064
 confir-3.998
 Palest-3.899
Token Twitter
Token ID3009
Feature activation-5.27e+00

Pos logit contributions
olla+2.885
acs+2.846
rog+2.838
ktop+2.820
 impaired+2.748
Neg logit contributions
 Yao-2.730
 unden-2.570
 Debor-2.472
 confir-2.460
 intern-2.399
Token in
Token ID287
Feature activation+4.64e-01

Pos logit contributions
olla+0.441
ktop+0.439
acs+0.439
rog+0.430
 impaired+0.418
Neg logit contributions
 Yao-0.436
 Debor-0.392
 intern-0.383
 JC-0.383
 Spencer-0.382
Token your
Token ID534
Feature activation-1.11e+00

Pos logit contributions
 Yao+0.360
 Debor+0.324
 intern+0.320
 JC+0.320
 Spencer+0.319
Neg logit contributions
olla-0.330
ktop-0.329
acs-0.329
rog-0.322
 impaired-0.310
Token performance
Token ID2854
Feature activation-1.56e+00

Pos logit contributions
acs+0.776
olla+0.776
ktop+0.774
rog+0.759
 impaired+0.741
Neg logit contributions
 Yao-0.869
 Debor-0.787
 intern-0.767
 JC-0.767
 Spencer-0.766
Token as
Token ID355
Feature activation-6.39e-01

Pos logit contributions
acs+1.059
olla+1.058
ktop+1.056
rog+1.035
 impaired+1.010
Neg logit contributions
 Yao-1.254
 Debor-1.138
 intern-1.111
 JC-1.110
 Spencer-1.110
Token a
Token ID257
Feature activation-1.28e+00

Pos logit contributions
olla+0.412
ktop+0.410
acs+0.409
rog+0.399
 impaired+0.385
Neg logit contributions
 Yao-0.541
 Debor-0.492
 JC-0.484
 intern-0.484
 Spencer-0.483
Token result
Token ID1255
Feature activation-5.22e+00

Pos logit contributions
acs+0.870
olla+0.869
ktop+0.868
rog+0.853
 impaired+0.831
Neg logit contributions
 Yao-1.030
 Debor-0.937
 intern-0.913
 JC-0.912
 Spencer-0.911
Token of
Token ID286
Feature activation-7.23e-01

Pos logit contributions
acs+3.101
olla+3.073
ktop+3.058
rog+3.019
 impaired+2.997
Neg logit contributions
 Yao-4.569
 Debor-4.209
 unden-4.128
 JC-4.086
 Spencer-4.085
Token truly
Token ID4988
Feature activation+5.36e-01

Pos logit contributions
olla+0.499
acs+0.498
ktop+0.498
rog+0.486
 impaired+0.470
Neg logit contributions
 Yao-0.577
 Debor-0.522
 intern-0.512
 JC-0.511
 Spencer-0.510
Token believing
Token ID14773
Feature activation+4.36e-01

Pos logit contributions
 Yao+0.424
 Debor+0.381
 intern+0.380
 JC+0.378
 Spencer+0.375
Neg logit contributions
olla-0.377
ktop-0.373
acs-0.372
rog-0.363
\/\/-0.347
Token in
Token ID287
Feature activation-6.28e-01

Pos logit contributions
 Yao+0.329
 Debor+0.295
 JC+0.290
 intern+0.289
 Spencer+0.289
Neg logit contributions
olla-0.321
ktop-0.321
acs-0.319
rog-0.312
 impaired-0.302
Token your
Token ID534
Feature activation-1.58e+00

Pos logit contributions
olla+0.432
acs+0.432
ktop+0.431
rog+0.422
 impaired+0.411
Neg logit contributions
 Yao-0.501
 Debor-0.454
 intern-0.444
 JC-0.444
 Spencer-0.443
Tokenatives
Token ID2929
Feature activation-5.56e-01

Pos logit contributions
 Yao+0.770
 Debor+0.681
 intern+0.672
 Spencer+0.669
 JC+0.667
Neg logit contributions
ktop-0.882
olla-0.873
acs-0.861
rog-0.846
 impaired-0.841
Token.
Token ID13
Feature activation+2.81e-01

Pos logit contributions
acs+0.427
olla+0.427
ktop+0.426
rog+0.419
 impaired+0.408
Neg logit contributions
 Yao-0.398
 Debor-0.357
 intern-0.348
 JC-0.347
 Spencer-0.346
Token
Token ID447
Feature activation-3.81e-01

Pos logit contributions
 Yao+0.195
 Debor+0.174
 JC+0.170
 Spencer+0.170
 intern+0.169
Neg logit contributions
ktop-0.222
olla-0.222
acs-0.222
rog-0.218
 impaired-0.213
Token
Token ID251
Feature activation-2.09e-01

Pos logit contributions
acs+0.266
olla+0.265
ktop+0.264
rog+0.260
 impaired+0.253
Neg logit contributions
 Yao-0.300
 Debor-0.272
 intern-0.266
 JC-0.265
 Spencer-0.265
Token<|endoftext|>
Token ID50256
Feature activation-4.21e-01

Pos logit contributions
acs+0.168
olla+0.168
ktop+0.167
rog+0.165
 impaired+0.161
Neg logit contributions
 Yao-0.142
 Debor-0.126
 intern-0.123
 JC-0.123
 Spencer-0.122
TokenFILE
Token ID25664
Feature activation-5.12e+00

Pos logit contributions
ktop+0.307
olla+0.307
acs+0.307
rog+0.300
 impaired+0.294
Neg logit contributions
 Yao-0.318
 Debor-0.285
 JC-0.279
 Spencer-0.279
 intern-0.278
Token:
Token ID25
Feature activation+8.91e-01

Pos logit contributions
olla+2.750
rog+2.696
acs+2.676
ktop+2.673
 impaired+2.638
Neg logit contributions
 Yao-4.719
 Debor-4.378
 unden-4.293
 JC-4.241
 intern-4.230
Token Delhi
Token ID12517
Feature activation-1.47e+00

Pos logit contributions
 Yao+0.628
 Debor+0.560
 Spencer+0.548
 JC+0.547
 intern+0.542
Neg logit contributions
ktop-0.706
olla-0.703
acs-0.703
rog-0.688
 impaired-0.673
Token Law
Token ID3854
Feature activation+1.05e-02

Pos logit contributions
acs+0.889
olla+0.889
ktop+0.887
rog+0.866
 impaired+0.840
Neg logit contributions
 Yao-1.294
 Debor-1.184
 intern-1.160
 JC-1.159
 Spencer-1.158
Token Minister
Token ID4139
Feature activation+2.13e-01

Pos logit contributions
 Yao+0.009
 Debor+0.008
 JC+0.008
 intern+0.008
 Spencer+0.008
Neg logit contributions
ktop-0.007
acs-0.007
olla-0.007
rog-0.007
 impaired-0.007
Token and
Token ID290
Feature activation-4.18e-01

Pos logit contributions
 Yao+0.159
 Debor+0.143
 JC+0.139
 Spencer+0.139
 intern+0.139
Neg logit contributions
ktop-0.159
olla-0.159
acs-0.159
rog-0.155
 impaired-0.152
TokenRecommend
Token ID41248
Feature activation+4.69e-01

Pos logit contributions
ktop+0.572
acs+0.564
olla+0.558
rog+0.544
 impaired+0.543
Neg logit contributions
 Yao-0.589
 Debor-0.522
 JC-0.521
••-0.520
 Spencer-0.519
Token Share
Token ID8734
Feature activation-1.43e-01

Pos logit contributions
 Yao+0.277
 Debor+0.240
 JC+0.236
 Spencer+0.236
 intern+0.235
Neg logit contributions
ktop-0.423
acs-0.422
olla-0.421
rog-0.412
 impaired-0.404
Token this
Token ID428
Feature activation-2.46e+00

Pos logit contributions
ktop+0.116
acs+0.116
olla+0.115
rog+0.112
 impaired+0.109
Neg logit contributions
 Yao-0.098
 Debor-0.086
 intern-0.086
 JC-0.086
 Spencer-0.086
Token comment
Token ID2912
Feature activation-5.62e+00

Pos logit contributions
olla+1.932
acs+1.932
ktop+1.927
rog+1.896
 impaired+1.853
Neg logit contributions
 Yao-1.722
 Debor-1.540
 JC-1.494
 intern-1.494
 Spencer-1.493
Token on
Token ID319
Feature activation-4.10e+00

Pos logit contributions
olla+4.007
acs+3.961
ktop+3.929
rog+3.912
 impaired+3.818
Neg logit contributions
 Yao-4.236
 unden-4.109
 Debor-3.915
 confir-3.851
 Palest-3.743
Token Facebook
Token ID3203
Feature activation-5.04e+00

Pos logit contributions
olla+2.641
acs+2.624
ktop+2.609
rog+2.571
 impaired+2.473
Neg logit contributions
 Yao-3.383
 unden-3.175
 Debor-3.150
 intern-3.046
 confir-3.040
Token Share
Token ID8734
Feature activation-8.25e-01

Pos logit contributions
olla+3.893
acs+3.883
ktop+3.832
rog+3.805
 impaired+3.715
Neg logit contributions
 Yao-3.384
 unden-3.283
 Debor-3.139
 confir-3.083
 intern-2.991
Token this
Token ID428
Feature activation-1.44e+00

Pos logit contributions
ktop+0.644
acs+0.644
olla+0.642
rog+0.627
 impaired+0.611
Neg logit contributions
 Yao-0.585
 Debor-0.519
 intern-0.512
 JC-0.511
 Spencer-0.511
Token comment
Token ID2912
Feature activation-5.56e+00

Pos logit contributions
acs+1.150
olla+1.149
ktop+1.149
rog+1.125
 impaired+1.099
Neg logit contributions
 Yao-0.995
 Debor-0.884
 intern-0.866
 JC-0.864
 Spencer-0.862
Token on
Token ID319
Feature activation-3.45e+00

Pos logit contributions
olla+4.009
acs+3.970
ktop+3.949
rog+3.918
 impaired+3.830
Neg logit contributions
 Yao-4.160
 unden-3.991
 Debor-3.832
 confir-3.741
 Palest-3.660
Token Twitter
Token ID3009
Feature activation-4.94e+00

Pos logit contributions
olla+2.626
acs+2.599
rog+2.585
ktop+2.575
 impaired+2.509
Neg logit contributions
 Yao-2.423
 unden-2.252
 Debor-2.187
 confir-2.149
 intern-2.121
TokenRecommend
Token ID41248
Feature activation+5.62e-01

Pos logit contributions
ktop+0.401
acs+0.395
olla+0.390
rog+0.381
 impaired+0.380
Neg logit contributions
 Yao-0.406
••-0.359
 Debor-0.359
 JC-0.358
 Spencer-0.357
Token Share
Token ID8734
Feature activation-9.53e-02

Pos logit contributions
 Yao+0.328
 Debor+0.283
 Spencer+0.280
 JC+0.280
 intern+0.278
Neg logit contributions
ktop-0.510
acs-0.508
olla-0.508
rog-0.497
 impaired-0.486
Token this
Token ID428
Feature activation-2.46e+00

Pos logit contributions
ktop+0.077
acs+0.077
olla+0.077
rog+0.075
 impaired+0.072
Neg logit contributions
 Yao-0.065
 Debor-0.057
 intern-0.057
 JC-0.057
 Spencer-0.057
Token comment
Token ID2912
Feature activation-5.43e+00

Pos logit contributions
olla+1.928
acs+1.927
ktop+1.922
rog+1.892
 impaired+1.849
Neg logit contributions
 Yao-1.721
 Debor-1.541
 JC-1.494
 intern-1.494
 Spencer-1.493
Token on
Token ID319
Feature activation-4.03e+00

Pos logit contributions
olla+3.873
acs+3.830
ktop+3.801
rog+3.786
 impaired+3.692
Neg logit contributions
 Yao-4.089
 unden-3.966
 Debor-3.781
 confir-3.714
 Palest-3.612
Token Facebook
Token ID3203
Feature activation-5.02e+00

Pos logit contributions
olla+2.585
acs+2.567
ktop+2.551
rog+2.519
 impaired+2.418
Neg logit contributions
 Yao-3.334
 unden-3.144
 Debor-3.110
 confir-3.009
 intern-3.005
Token Share
Token ID8734
Feature activation-5.72e-01

Pos logit contributions
olla+3.867
acs+3.861
ktop+3.799
rog+3.784
 impaired+3.694
Neg logit contributions
 Yao-3.374
 unden-3.274
 Debor-3.134
 confir-3.078
 intern-2.981
Token this
Token ID428
Feature activation-1.63e+00

Pos logit contributions
ktop+0.449
acs+0.448
olla+0.447
rog+0.437
 impaired+0.425
Neg logit contributions
 Yao-0.404
 Debor-0.358
 intern-0.353
 JC-0.353
 Spencer-0.353
Token comment
Token ID2912
Feature activation-5.59e+00

Pos logit contributions
acs+1.286
olla+1.286
ktop+1.284
rog+1.261
 impaired+1.231
Neg logit contributions
 Yao-1.128
 Debor-1.005
 intern-0.980
 JC-0.979
 Spencer-0.977
Token on
Token ID319
Feature activation-3.49e+00

Pos logit contributions
olla+4.014
acs+3.970
ktop+3.948
rog+3.921
 impaired+3.832
Neg logit contributions
 Yao-4.189
 unden-4.041
 Debor-3.870
 confir-3.786
 Palest-3.699
Token Twitter
Token ID3009
Feature activation-4.94e+00

Pos logit contributions
olla+2.653
acs+2.624
rog+2.613
ktop+2.601
 impaired+2.535
Neg logit contributions
 Yao-2.460
 unden-2.294
 Debor-2.220
 confir-2.193
 intern-2.155
Token Enter
Token ID6062
Feature activation+4.07e+00

Pos logit contributions
ktop+2.039
acs+2.003
olla+1.973
rog+1.934
 neur+1.879
Neg logit contributions
 Yao-3.307
 unden-3.233
 Debor-3.149
 intern-3.072
••-3.047
Token Your
Token ID3406
Feature activation+3.30e-01

Pos logit contributions
 Yao+3.252
 Spencer+2.953
 JC+2.932
 Debor+2.907
 intern+2.881
Neg logit contributions
ktop-2.933
olla-2.844
acs-2.819
rog-2.726
 impaired-2.646
Token Name
Token ID6530
Feature activation+9.55e-01

Pos logit contributions
 Yao+0.321
 Debor+0.298
 intern+0.293
 unden+0.291
 JC+0.291
Neg logit contributions
olla-0.167
acs-0.167
ktop-0.164
rog-0.162
 impaired-0.156
Token Add
Token ID3060
Feature activation+6.70e-01

Pos logit contributions
 Yao+0.755
 Debor+0.682
 unden+0.670
 intern+0.669
 JC+0.662
Neg logit contributions
olla-0.665
acs-0.665
ktop-0.661
rog-0.651
 impaired-0.631
Token a
Token ID257
Feature activation+7.05e-01

Pos logit contributions
 Yao+0.582
 JC+0.527
 Spencer+0.526
 Debor+0.525
 intern+0.523
Neg logit contributions
acs-0.429
ktop-0.429
olla-0.418
rog-0.406
 impaired-0.392
Token comment
Token ID2912
Feature activation-4.94e+00

Pos logit contributions
 Yao+0.483
 Debor+0.429
 intern+0.420
 JC+0.419
 Spencer+0.419
Neg logit contributions
ktop-0.568
acs-0.567
olla-0.564
rog-0.554
 impaired-0.541
Token here
Token ID994
Feature activation-1.89e+00

Pos logit contributions
olla+3.037
ktop+3.000
rog+2.991
acs+2.934
 impaired+2.885
Neg logit contributions
 Yao-4.281
 unden-3.964
 Debor-3.903
 intern-3.795
••-3.790
Token Ver
Token ID4643
Feature activation+2.64e-01

Pos logit contributions
olla+1.530
acs+1.512
ktop+1.500
rog+1.471
 impaired+1.446
Neg logit contributions
 Yao-1.281
 Debor-1.163
 unden-1.121
 intern-1.115
••-1.099
Tokenification
Token ID2649
Feature activation-8.55e-01

Pos logit contributions
 Yao+0.209
 Debor+0.189
 JC+0.186
 intern+0.186
 Spencer+0.185
Neg logit contributions
ktop-0.182
olla-0.181
acs-0.181
rog-0.176
 impaired-0.173
Token Send
Token ID16290
Feature activation+9.77e-01

Pos logit contributions
olla+0.748
acs+0.738
rog+0.735
ktop+0.733
 impaired+0.719
Neg logit contributions
 Yao-0.514
 Debor-0.457
 unden-0.447
 intern-0.439
••-0.432
Token Email
Token ID9570
Feature activation+5.15e-01

Pos logit contributions
 Yao+0.458
 Debor+0.385
 JC+0.377
 Spencer+0.371
 intern+0.369
Neg logit contributions
ktop-1.008
olla-1.001
acs-0.997
rog-0.974
 impaired-0.958
Token are
Token ID389
Feature activation+1.57e+00

Pos logit contributions
 Yao+1.399
 Debor+1.269
 intern+1.257
 Spencer+1.246
 JC+1.239
Neg logit contributions
olla-1.168
ktop-1.167
acs-1.161
rog-1.141
 impaired-1.085
Token also
Token ID635
Feature activation+7.65e-01

Pos logit contributions
 Yao+1.275
 Debor+1.157
 intern+1.151
 Spencer+1.139
 JC+1.134
Neg logit contributions
ktop-1.058
olla-1.053
acs-1.042
rog-1.024
\/\/-0.974
Token alike
Token ID12936
Feature activation+2.60e+00

Pos logit contributions
 Yao+0.615
 Debor+0.558
 intern+0.551
 Spencer+0.548
 JC+0.545
Neg logit contributions
ktop-0.524
olla-0.521
acs-0.517
rog-0.509
 impaired-0.486
Token in
Token ID287
Feature activation+2.52e+00

Pos logit contributions
 Yao+1.843
 Debor+1.658
 intern+1.626
 Spencer+1.618
 unden+1.605
Neg logit contributions
ktop-2.015
olla-2.012
acs-1.989
rog-1.955
\/\/-1.883
Token the
Token ID262
Feature activation+1.90e+00

Pos logit contributions
 Yao+2.097
 Debor+1.902
 intern+1.888
 Spencer+1.879
 JC+1.855
Neg logit contributions
acs-1.640
ktop-1.632
olla-1.632
rog-1.600
 impaired-1.521
Token fact
Token ID1109
Feature activation+3.18e+00

Pos logit contributions
 Yao+1.526
 Debor+1.387
 intern+1.374
 Spencer+1.359
 unden+1.354
Neg logit contributions
acs-1.309
olla-1.296
ktop-1.293
rog-1.262
 impaired-1.201
Token that
Token ID326
Feature activation+5.63e-01

Pos logit contributions
 Yao+2.409
 Debor+2.160
 intern+2.134
 Spencer+2.132
 JC+2.110
Neg logit contributions
ktop-2.286
acs-2.277
olla-2.272
rog-2.223
 impaired-2.161
Token they
Token ID484
Feature activation+1.36e+00

Pos logit contributions
 Yao+0.460
 Debor+0.418
 intern+0.412
 Spencer+0.410
 JC+0.407
Neg logit contributions
ktop-0.381
acs-0.379
olla-0.378
rog-0.367
 impaired-0.355
Token have
Token ID423
Feature activation+6.97e-01

Pos logit contributions
 Yao+1.058
 Debor+0.955
 intern+0.946
 Spencer+0.934
 JC+0.933
Neg logit contributions
olla-0.964
acs-0.962
ktop-0.962
rog-0.941
 impaired-0.905
Token at
Token ID379
Feature activation+7.45e-01

Pos logit contributions
 Yao+0.586
 Debor+0.535
 intern+0.529
 Spencer+0.523
 JC+0.521
Neg logit contributions
acs-0.453
olla-0.452
ktop-0.450
rog-0.439
 impaired-0.419
Token some
Token ID617
Feature activation+7.23e-01

Pos logit contributions
 Yao+0.636
 Debor+0.579
 intern+0.573
 Spencer+0.570
 JC+0.566
Neg logit contributions
acs-0.473
ktop-0.469
olla-0.465
rog-0.454
 impaired-0.441
Token their
Token ID511
Feature activation+3.79e-02

Pos logit contributions
ktop+0.127
olla+0.127
acs+0.126
rog+0.123
 impaired+0.119
Neg logit contributions
 Yao-0.172
 Debor-0.156
 intern-0.154
 JC-0.154
 Spencer-0.154
Token life
Token ID1204
Feature activation-1.58e-02

Pos logit contributions
 Yao+0.033
 Debor+0.030
 intern+0.030
 JC+0.029
 Spencer+0.029
Neg logit contributions
acs-0.023
ktop-0.023
olla-0.023
rog-0.023
 impaired-0.022
Token from
Token ID422
Feature activation-7.07e-01

Pos logit contributions
acs+0.012
ktop+0.012
olla+0.012
rog+0.012
 impaired+0.012
Neg logit contributions
 Yao-0.011
 Debor-0.010
 intern-0.010
 JC-0.010
 Spencer-0.010
Token the
Token ID262
Feature activation-3.39e-01

Pos logit contributions
acs+0.456
olla+0.456
ktop+0.455
rog+0.444
 impaired+0.429
Neg logit contributions
 Yao-0.597
 Debor-0.542
 intern-0.534
 JC-0.532
 Spencer-0.532
Token polar
Token ID13559
Feature activation-1.10e+00

Pos logit contributions
olla+0.229
acs+0.229
ktop+0.229
rog+0.224
 impaired+0.217
Neg logit contributions
 Yao-0.274
 Debor-0.248
 intern-0.244
 JC-0.243
 Spencer-0.243
Token opposite
Token ID6697
Feature activation+2.90e+00

Pos logit contributions
acs+0.757
olla+0.755
ktop+0.753
rog+0.742
 impaired+0.723
Neg logit contributions
 Yao-0.873
 Debor-0.792
 JC-0.771
 Spencer-0.768
 intern-0.767
Token vantage
Token ID47929
Feature activation+7.95e-01

Pos logit contributions
 Yao+2.220
 intern+1.990
 Debor+1.990
 Spencer+1.984
 JC+1.972
Neg logit contributions
ktop-2.097
olla-2.082
acs-2.074
rog-2.048
 impaired-1.941
Token point
Token ID966
Feature activation-3.01e-01

Pos logit contributions
 Yao+0.530
 Debor+0.466
 intern+0.461
 Spencer+0.458
 JC+0.457
Neg logit contributions
acs-0.653
olla-0.651
ktop-0.651
rog-0.635
 impaired-0.618
Token.
Token ID13
Feature activation-5.29e-01

Pos logit contributions
acs+0.222
olla+0.222
ktop+0.222
rog+0.217
 impaired+0.212
Neg logit contributions
 Yao-0.224
 Debor-0.202
 intern-0.197
 JC-0.197
 Spencer-0.197
Token For
Token ID1114
Feature activation+2.21e-01

Pos logit contributions
ktop+0.394
acs+0.394
olla+0.393
rog+0.385
 impaired+0.376
Neg logit contributions
 Yao-0.393
 Debor-0.353
 Spencer-0.344
 JC-0.344
 intern-0.343
Token Bob
Token ID5811
Feature activation-1.11e+00

Pos logit contributions
 Yao+0.182
 Debor+0.165
 Spencer+0.162
 intern+0.162
 JC+0.162
Neg logit contributions
ktop-0.147
acs-0.147
olla-0.146
rog-0.143
 impaired-0.138
Token bit
Token ID1643
Feature activation-7.09e-01

Pos logit contributions
olla+0.184
ktop+0.183
acs+0.183
rog+0.177
 impaired+0.168
Neg logit contributions
 Yao-0.309
 Debor-0.283
 intern-0.281
 Spencer-0.279
 JC-0.279
Token strange
Token ID6283
Feature activation-1.54e-01

Pos logit contributions
olla+0.370
ktop+0.369
acs+0.368
rog+0.357
 impaired+0.338
Neg logit contributions
 Yao-0.688
 Debor-0.633
 intern-0.627
 Spencer-0.624
 JC-0.623
Token."
Token ID526
Feature activation+2.28e+00

Pos logit contributions
acs+0.113
olla+0.113
ktop+0.113
rog+0.111
 impaired+0.107
Neg logit contributions
 Yao-0.116
 Debor-0.104
 intern-0.103
 Spencer-0.102
 JC-0.102
Token
Token ID198
Feature activation+2.27e-01

Pos logit contributions
 Yao+1.832
 Spencer+1.635
 Debor+1.634
 JC+1.633
 intern+1.601
Neg logit contributions
ktop-1.567
acs-1.540
olla-1.520
 neur-1.514
 impaired-1.494
Token
Token ID198
Feature activation+3.34e-01

Pos logit contributions
 Yao+0.191
 JC+0.171
 Debor+0.170
 Spencer+0.170
 intern+0.169
Neg logit contributions
ktop-0.149
acs-0.146
olla-0.146
rog-0.142
 neur-0.140
TokenVideo
Token ID10798
Feature activation+3.20e+00

Pos logit contributions
 Yao+0.254
 Debor+0.227
 JC+0.224
 Spencer+0.223
••+0.222
Neg logit contributions
ktop-0.244
olla-0.243
acs-0.241
rog-0.236
 impaired-0.233
Token:
Token ID25
Feature activation+1.66e+00

Pos logit contributions
 Yao+1.956
 JC+1.675
 Spencer+1.649
 intern+1.639
 Debor+1.634
Neg logit contributions
ktop-2.897
acs-2.822
olla-2.811
rog-2.736
 neur-2.699
Token W
Token ID370
Feature activation-4.70e-01

Pos logit contributions
 Yao+1.139
 JC+1.002
 Debor+0.997
 Spencer+0.987
 EB+0.978
Neg logit contributions
ktop-1.360
olla-1.341
acs-1.336
rog-1.322
 impaired-1.280
TokenPG
Token ID6968
Feature activation+1.08e-01

Pos logit contributions
ktop+0.332
olla+0.329
acs+0.329
rog+0.322
 impaired+0.313
Neg logit contributions
 Yao-0.369
 Debor-0.332
 JC-0.327
 intern-0.326
 Spencer-0.325
Token@
Token ID31
Feature activation-1.56e-02

Pos logit contributions
 Yao+0.083
 Debor+0.075
 intern+0.073
 JC+0.073
 Spencer+0.073
Neg logit contributions
acs-0.077
olla-0.077
ktop-0.077
rog-0.076
 impaired-0.074
TokenFL
Token ID3697
Feature activation+1.59e+00

Pos logit contributions
ktop+0.012
olla+0.012
acs+0.012
rog+0.012
 impaired+0.011
Neg logit contributions
 Yao-0.011
 Debor-0.010
 JC-0.010
 Spencer-0.010
 intern-0.010
TokenDear
Token ID20266
Feature activation+7.73e-01

Pos logit contributions
 Yao+0.387
 Debor+0.353
 Spencer+0.347
 JC+0.346
••+0.346
Neg logit contributions
ktop-0.265
olla-0.263
acs-0.263
rog-0.254
 impaired-0.251
Token George
Token ID4502
Feature activation+1.82e+00

Pos logit contributions
 Yao+0.613
 Debor+0.556
 Spencer+0.544
 JC+0.544
 intern+0.542
Neg logit contributions
ktop-0.547
olla-0.542
acs-0.541
rog-0.528
 impaired-0.514
Token,
Token ID11
Feature activation+1.37e+00

Pos logit contributions
 Yao+1.270
 Debor+1.131
 Spencer+1.106
 intern+1.103
 JC+1.100
Neg logit contributions
ktop-1.445
acs-1.439
olla-1.439
rog-1.412
 impaired-1.382
Token
Token ID198
Feature activation+5.48e-01

Pos logit contributions
 Yao+1.161
 Debor+1.051
 JC+1.036
 Spencer+1.035
 intern+1.030
Neg logit contributions
ktop-0.896
acs-0.885
olla-0.878
rog-0.855
 impaired-0.839
Token
Token ID198
Feature activation+1.24e+00

Pos logit contributions
 Yao+0.463
 Debor+0.413
 JC+0.413
 Spencer+0.411
 intern+0.409
Neg logit contributions
ktop-0.361
acs-0.355
olla-0.352
rog-0.343
 neur-0.339
TokenI
Token ID40
Feature activation+2.98e+00

Pos logit contributions
 Yao+0.907
 Debor+0.810
 Spencer+0.794
••+0.793
 JC+0.792
Neg logit contributions
ktop-0.930
olla-0.919
acs-0.918
rog-0.894
 impaired-0.889
Token had
Token ID550
Feature activation+2.65e+00

Pos logit contributions
 Yao+2.317
 Debor+2.099
 intern+2.069
 Spencer+2.066
 JC+2.052
Neg logit contributions
ktop-2.116
acs-2.085
olla-2.084
rog-2.045
 impaired-1.983
Token a
Token ID257
Feature activation+8.34e-01

Pos logit contributions
 Yao+2.118
 Debor+1.912
 intern+1.882
 Spencer+1.877
 JC+1.873
Neg logit contributions
ktop-1.849
acs-1.840
olla-1.832
rog-1.787
lime-1.718
Token dream
Token ID4320
Feature activation-9.68e-01

Pos logit contributions
 Yao+0.693
 Debor+0.627
 JC+0.620
 intern+0.619
 Spencer+0.617
Neg logit contributions
ktop-0.552
acs-0.551
olla-0.548
rog-0.533
 impaired-0.517
Token of
Token ID286
Feature activation-1.25e+00

Pos logit contributions
ktop+0.687
acs+0.686
olla+0.684
rog+0.671
 impaired+0.652
Neg logit contributions
 Yao-0.752
 Debor-0.679
 intern-0.666
 Spencer-0.664
 JC-0.664
Token a
Token ID257
Feature activation-9.25e-01

Pos logit contributions
acs+0.852
olla+0.851
ktop+0.849
rog+0.831
 impaired+0.810
Neg logit contributions
 Yao-1.000
 Debor-0.906
 intern-0.886
 JC-0.885
 Spencer-0.884
Tokenar
Token ID283
Feature activation+2.73e+00

Pos logit contributions
 Yao+1.740
 Debor+1.530
 intern+1.520
 JC+1.519
 Spencer+1.507
Neg logit contributions
ktop-1.859
acs-1.817
olla-1.804
 impaired-1.791
 neur-1.787
Tokenap
Token ID499
Feature activation+1.18e+00

Pos logit contributions
 Yao+2.032
 JC+1.805
 Debor+1.803
 intern+1.797
 Spencer+1.778
Neg logit contributions
ktop-1.981
acs-1.917
olla-1.895
 neur-1.895
 impaired-1.868
Tokenat
Token ID265
Feature activation-4.67e-01

Pos logit contributions
 Yao+0.888
 Debor+0.796
 intern+0.787
 JC+0.780
 Spencer+0.775
Neg logit contributions
ktop-0.856
acs-0.845
olla-0.840
rog-0.823
 impaired-0.811
Tokenang
Token ID648
Feature activation+2.44e+00

Pos logit contributions
ktop+0.337
acs+0.337
olla+0.336
rog+0.329
 impaired+0.321
Neg logit contributions
 Yao-0.356
 Debor-0.321
 intern-0.314
 JC-0.314
 Spencer-0.313
Token p
Token ID279
Feature activation+1.67e+00

Pos logit contributions
 Yao+1.912
 Debor+1.723
 intern+1.711
 JC+1.697
 Spencer+1.680
Neg logit contributions
ktop-1.703
acs-1.690
olla-1.676
rog-1.635
 impaired-1.589
Tokenanta
Token ID4910
Feature activation+3.41e+00

Pos logit contributions
 Yao+1.214
 Debor+1.072
 intern+1.055
 Spencer+1.050
 JC+1.048
Neg logit contributions
ktop-1.265
olla-1.246
acs-1.245
rog-1.225
 impaired-1.215
Tokeno
Token ID78
Feature activation+7.47e-01

Pos logit contributions
 Yao+2.679
 intern+2.405
 JC+2.385
 Debor+2.383
 Spencer+2.338
Neg logit contributions
ktop-2.358
acs-2.304
olla-2.296
rog-2.244
 impaired-2.211
Token (
Token ID357
Feature activation+1.25e+00

Pos logit contributions
 Yao+0.600
 Debor+0.540
 intern+0.534
 JC+0.533
 Spencer+0.529
Neg logit contributions
ktop-0.511
acs-0.508
olla-0.506
rog-0.494
 impaired-0.482
TokenAlthough
Token ID7003
Feature activation+9.03e-01

Pos logit contributions
 Yao+0.938
 Debor+0.843
 Spencer+0.824
 JC+0.824
 intern+0.823
Neg logit contributions
ktop-0.914
olla-0.905
acs-0.903
rog-0.877
 impaired-0.869
Token we
Token ID356
Feature activation+1.04e+00

Pos logit contributions
 Yao+0.720
 Debor+0.652
 intern+0.639
 JC+0.638
 Spencer+0.638
Neg logit contributions
ktop-0.624
acs-0.622
olla-0.621
rog-0.606
 impaired-0.588
Token are
Token ID389
Feature activation+1.11e+00

Pos logit contributions
 Yao+0.858
 Debor+0.781
 intern+0.771
 JC+0.766
 Spencer+0.764
Neg logit contributions
ktop-0.686
olla-0.683
acs-0.680
rog-0.668
 impaired-0.644
Token a
Token ID257
Feature activation-2.01e+00

Pos logit contributions
acs+0.665
olla+0.664
ktop+0.664
rog+0.646
 impaired+0.626
Neg logit contributions
 Yao-0.896
 Debor-0.816
 intern-0.802
 Spencer-0.799
 JC-0.799
Token ur
Token ID2956
Feature activation-3.40e-01

Pos logit contributions
olla+1.405
acs+1.403
ktop+1.401
rog+1.379
 impaired+1.344
Neg logit contributions
 Yao-1.571
 Debor-1.424
 JC-1.388
 intern-1.386
 Spencer-1.384
Tokeninal
Token ID1292
Feature activation-4.68e-01

Pos logit contributions
acs+0.165
olla+0.164
ktop+0.164
rog+0.157
 impaired+0.154
Neg logit contributions
 Yao-0.340
 Debor-0.314
 intern-0.310
 JC-0.309
 Spencer-0.308
Token.
Token ID13
Feature activation-2.26e-01

Pos logit contributions
acs+0.337
olla+0.335
ktop+0.333
rog+0.326
 impaired+0.318
Neg logit contributions
 Yao-0.361
 Debor-0.325
 intern-0.321
 JC-0.319
 Spencer-0.318
Token Pretty
Token ID20090
Feature activation+1.81e-01

Pos logit contributions
ktop+0.170
acs+0.169
olla+0.169
rog+0.165
 impaired+0.162
Neg logit contributions
 Yao-0.169
 Debor-0.151
 Spencer-0.148
 JC-0.148
 intern-0.146
Token much
Token ID881
Feature activation+3.49e-01

Pos logit contributions
 Yao+0.155
 Debor+0.140
 intern+0.139
 Spencer+0.138
 JC+0.138
Neg logit contributions
ktop-0.116
olla-0.115
acs-0.115
rog-0.112
 impaired-0.107
Token every
Token ID790
Feature activation-4.36e-01

Pos logit contributions
 Yao+0.275
 Debor+0.247
 intern+0.243
 Spencer+0.243
 JC+0.242
Neg logit contributions
ktop-0.247
acs-0.247
olla-0.246
rog-0.241
 impaired-0.231
Token other
Token ID584
Feature activation+9.32e-01

Pos logit contributions
acs+0.280
ktop+0.280
olla+0.280
rog+0.273
 impaired+0.264
Neg logit contributions
 Yao-0.369
 Debor-0.336
 intern-0.330
 Spencer-0.329
 JC-0.329
Token day
Token ID1110
Feature activation+6.34e-01

Pos logit contributions
 Yao+0.781
 Debor+0.709
 intern+0.699
 Spencer+0.697
 JC+0.696
Neg logit contributions
ktop-0.607
acs-0.607
olla-0.606
rog-0.590
 impaired-0.570
Token I
Token ID314
Feature activation+7.77e-01

Pos logit contributions
 Yao+0.490
 Debor+0.441
 intern+0.434
 Spencer+0.434
 JC+0.431
Neg logit contributions
ktop-0.458
acs-0.456
olla-0.456
rog-0.446
 impaired-0.428
Token can
Token ID460
Feature activation+5.53e-01

Pos logit contributions
 Yao+0.627
 Debor+0.566
 intern+0.565
 Spencer+0.559
 JC+0.558
Neg logit contributions
ktop-0.529
acs-0.522
olla-0.521
rog-0.513
 impaired-0.493
Token businesses
Token ID5692
Feature activation+1.04e-01

Pos logit contributions
 Yao+0.420
 Debor+0.382
 intern+0.379
 JC+0.375
 Spencer+0.375
Neg logit contributions
ktop-0.331
olla-0.330
acs-0.330
rog-0.322
 impaired-0.311
Token,
Token ID11
Feature activation+5.83e-01

Pos logit contributions
 Yao+0.074
 Debor+0.066
 intern+0.065
 JC+0.065
 Spencer+0.065
Neg logit contributions
olla-0.081
ktop-0.081
acs-0.081
rog-0.079
 impaired-0.077
Token be
Token ID307
Feature activation+4.81e-01

Pos logit contributions
 Yao+0.443
 Debor+0.399
 intern+0.395
 Spencer+0.391
 JC+0.390
Neg logit contributions
olla-0.424
ktop-0.423
acs-0.422
rog-0.413
 impaired-0.401
Token in
Token ID287
Feature activation-1.17e-01

Pos logit contributions
 Yao+0.373
 Debor+0.338
 intern+0.334
 Spencer+0.330
 JC+0.330
Neg logit contributions
ktop-0.342
olla-0.341
acs-0.341
rog-0.333
 impaired-0.323
Token employment
Token ID7184
Feature activation-7.11e-01

Pos logit contributions
olla+0.078
acs+0.078
ktop+0.078
rog+0.076
 impaired+0.074
Neg logit contributions
 Yao-0.096
 Debor-0.088
 intern-0.086
 JC-0.086
 Spencer-0.086
Token,
Token ID11
Feature activation+1.01e-01

Pos logit contributions
olla+0.538
acs+0.538
ktop+0.538
rog+0.527
 impaired+0.514
Neg logit contributions
 Yao-0.517
 Debor-0.464
 intern-0.453
 JC-0.452
 Spencer-0.451
Token qualify
Token ID12780
Feature activation+1.36e-01

Pos logit contributions
 Yao+0.077
 Debor+0.069
 intern+0.068
 Spencer+0.067
 JC+0.067
Neg logit contributions
olla-0.074
acs-0.074
ktop-0.074
rog-0.072
 impaired-0.070
Token for
Token ID329
Feature activation-1.62e-01

Pos logit contributions
 Yao+0.108
 Debor+0.098
 intern+0.096
 JC+0.096
 Spencer+0.096
Neg logit contributions
olla-0.094
acs-0.094
ktop-0.094
rog-0.092
 impaired-0.090
Token benefits
Token ID4034
Feature activation+8.14e-01

Pos logit contributions
olla+0.119
acs+0.119
ktop+0.119
rog+0.116
 impaired+0.113
Neg logit contributions
 Yao-0.121
 Debor-0.109
 intern-0.107
 JC-0.107
 Spencer-0.107
Token,
Token ID11
Feature activation-1.27e-01

Pos logit contributions
 Yao+0.564
 Debor+0.504
 intern+0.498
 JC+0.491
 Spencer+0.490
Neg logit contributions
olla-0.643
ktop-0.642
acs-0.641
rog-0.631
 impaired-0.611
Token access
Token ID1895
Feature activation+2.07e+00

Pos logit contributions
olla+0.091
acs+0.091
ktop+0.091
rog+0.089
 impaired+0.087
Neg logit contributions
 Yao-0.097
 Debor-0.087
 intern-0.086
 JC-0.085
 Spencer-0.085
Token's
Token ID338
Feature activation-1.99e-01

Pos logit contributions
 Yao+0.110
 Debor+0.099
 intern+0.096
 JC+0.096
 Spencer+0.096
Neg logit contributions
acs-0.112
olla-0.112
ktop-0.111
rog-0.109
 impaired-0.107
Token offices
Token ID9730
Feature activation-1.34e-01

Pos logit contributions
acs+0.153
olla+0.153
ktop+0.153
rog+0.150
 impaired+0.146
Neg logit contributions
 Yao-0.143
 Debor-0.128
 intern-0.125
 JC-0.125
 Spencer-0.125
Token in
Token ID287
Feature activation+4.46e-01

Pos logit contributions
olla+0.101
acs+0.101
ktop+0.101
rog+0.099
 impaired+0.097
Neg logit contributions
 Yao-0.098
 Debor-0.088
 intern-0.086
 JC-0.086
 Spencer-0.085
Token Seoul
Token ID22372
Feature activation+2.87e-01

Pos logit contributions
 Yao+0.337
 Debor+0.301
 Spencer+0.297
 JC+0.297
 intern+0.296
Neg logit contributions
acs-0.329
ktop-0.328
olla-0.328
rog-0.321
 impaired-0.311
Token today
Token ID1909
Feature activation+1.25e+00

Pos logit contributions
 Yao+0.207
 Debor+0.186
 intern+0.181
 JC+0.181
 Spencer+0.181
Neg logit contributions
olla-0.219
acs-0.219
ktop-0.219
rog-0.215
 impaired-0.209
Token,
Token ID11
Feature activation+7.86e-01

Pos logit contributions
 Yao+0.883
 Debor+0.790
 intern+0.776
 JC+0.773
 Spencer+0.767
Neg logit contributions
olla-0.981
ktop-0.978
acs-0.975
rog-0.955
 impaired-0.927
Token C
Token ID327
Feature activation+1.46e+00

Pos logit contributions
 Yao+0.605
 Debor+0.546
 intern+0.538
 JC+0.535
 Spencer+0.533
Neg logit contributions
olla-0.567
ktop-0.566
acs-0.565
rog-0.553
 impaired-0.535
TokenNET
Token ID12884
Feature activation+4.26e-01

Pos logit contributions
 Yao+0.947
 Debor+0.832
 JC+0.819
 Spencer+0.815
 intern+0.813
Neg logit contributions
olla-1.214
ktop-1.212
acs-1.209
rog-1.184
 impaired-1.167
Token has
Token ID468
Feature activation+1.04e+00

Pos logit contributions
 Yao+0.296
 Debor+0.264
 intern+0.258
 JC+0.257
 Spencer+0.256
Neg logit contributions
ktop-0.337
acs-0.337
olla-0.337
rog-0.331
 impaired-0.323
Token learned
Token ID4499
Feature activation+1.45e+00

Pos logit contributions
 Yao+0.880
 Debor+0.803
 intern+0.789
 Spencer+0.786
 JC+0.786
Neg logit contributions
acs-0.659
olla-0.657
ktop-0.656
rog-0.641
 impaired-0.620
Token.
Token ID13
Feature activation-5.50e-01

Pos logit contributions
 Yao+1.081
 Debor+0.975
 intern+0.954
 Spencer+0.951
 JC+0.950
Neg logit contributions
ktop-1.081
acs-1.079
olla-1.074
rog-1.053
 impaired-1.026
Token for
Token ID329
Feature activation-2.42e-01

Pos logit contributions
 Yao+0.177
 Debor+0.160
 intern+0.157
 JC+0.157
 Spencer+0.156
Neg logit contributions
acs-0.152
olla-0.152
ktop-0.152
rog-0.149
 impaired-0.145
Token the
Token ID262
Feature activation-8.25e-01

Pos logit contributions
olla+0.150
acs+0.150
ktop+0.150
rog+0.147
 impaired+0.142
Neg logit contributions
 Yao-0.209
 Debor-0.191
 intern-0.187
 JC-0.186
 Spencer-0.186
Token Sh
Token ID911
Feature activation-1.80e-01

Pos logit contributions
olla+0.585
acs+0.585
ktop+0.584
rog+0.573
 impaired+0.557
Neg logit contributions
 Yao-0.640
 Debor-0.578
 Spencer-0.566
 JC-0.565
 intern-0.565
Tokenriver
Token ID38291
Feature activation+2.02e-01

Pos logit contributions
ktop+0.113
acs+0.111
olla+0.108
 impaired+0.106
 neur+0.106
Neg logit contributions
 Yao-0.154
 Debor-0.140
 intern-0.138
 Spencer-0.138
 JC-0.138
Token Award
Token ID11289
Feature activation-8.62e-01

Pos logit contributions
 Yao+0.193
 Debor+0.178
 Spencer+0.175
 JC+0.175
 intern+0.174
Neg logit contributions
ktop-0.107
olla-0.106
acs-0.106
rog-0.104
 impaired-0.100
Token,
Token ID11
Feature activation+1.11e+00

Pos logit contributions
olla+0.654
acs+0.653
ktop+0.650
rog+0.639
 impaired+0.625
Neg logit contributions
 Yao-0.626
 Debor-0.562
 intern-0.547
 JC-0.547
 Spencer-0.545
Token please
Token ID3387
Feature activation+1.39e+00

Pos logit contributions
 Yao+1.017
 Debor+0.933
 Spencer+0.919
 intern+0.919
 JC+0.919
Neg logit contributions
ktop-0.625
olla-0.624
acs-0.624
rog-0.608
 impaired-0.585
Token download
Token ID4321
Feature activation+1.23e+00

Pos logit contributions
 Yao+1.168
 Debor+1.061
 intern+1.049
 JC+1.045
 Spencer+1.043
Neg logit contributions
ktop-0.890
olla-0.890
acs-0.888
rog-0.866
 impaired-0.838
Token the
Token ID262
Feature activation+8.92e-01

Pos logit contributions
 Yao+1.055
 Debor+0.963
 Spencer+0.945
 JC+0.943
 intern+0.943
Neg logit contributions
acs-0.777
ktop-0.776
olla-0.773
rog-0.756
 impaired-0.732
Token Sh
Token ID911
Feature activation-8.76e-01

Pos logit contributions
 Yao+0.565
 Debor+0.497
 Spencer+0.488
 JC+0.486
 intern+0.484
Neg logit contributions
olla-0.764
ktop-0.762
acs-0.762
rog-0.751
 impaired-0.730
Tokenriver
Token ID38291
Feature activation-1.20e+00

Pos logit contributions
ktop+0.545
acs+0.541
olla+0.527
 impaired+0.514
 neur+0.511
Neg logit contributions
 Yao-0.754
 Debor-0.689
 intern-0.677
 Spencer-0.676
 JC-0.676
Token says
Token ID1139
Feature activation-3.77e-01

Pos logit contributions
olla+0.541
acs+0.541
ktop+0.540
rog+0.528
 impaired+0.513
Neg logit contributions
 Yao-0.681
 Debor-0.619
 intern-0.606
 JC-0.606
 Spencer-0.605
Token have
Token ID423
Feature activation-6.37e-01

Pos logit contributions
acs+0.250
olla+0.250
ktop+0.249
rog+0.244
 impaired+0.238
Neg logit contributions
 Yao-0.309
 Debor-0.281
 intern-0.275
 JC-0.275
 Spencer-0.274
Token contributed
Token ID8639
Feature activation-7.19e-02

Pos logit contributions
acs+0.434
olla+0.434
ktop+0.433
rog+0.424
 impaired+0.412
Neg logit contributions
 Yao-0.513
 Debor-0.465
 intern-0.455
 JC-0.454
 Spencer-0.454
Token to
Token ID284
Feature activation-3.80e-01

Pos logit contributions
olla+0.046
ktop+0.046
acs+0.046
rog+0.045
 impaired+0.043
Neg logit contributions
 Yao-0.061
 Debor-0.055
 intern-0.054
 JC-0.054
 Spencer-0.054
Token Pruitt
Token ID39637
Feature activation+7.62e-01

Pos logit contributions
olla+0.283
acs+0.282
ktop+0.282
rog+0.276
 impaired+0.269
Neg logit contributions
 Yao-0.282
 Debor-0.253
 intern-0.248
 JC-0.247
 Spencer-0.247
Token
Token ID447
Feature activation+1.80e+00

Pos logit contributions
 Yao+0.566
 Debor+0.508
 intern+0.496
 JC+0.496
 Spencer+0.495
Neg logit contributions
acs-0.566
olla-0.566
ktop-0.565
rog-0.554
 impaired-0.541
Token
Token ID247
Feature activation+8.84e-01

Pos logit contributions
 Yao+1.537
 Debor+1.388
 intern+1.385
 Spencer+1.372
 JC+1.369
Neg logit contributions
ktop-1.154
acs-1.139
olla-1.131
rog-1.091
 impaired-1.081
Tokens
Token ID82
Feature activation-1.23e-01

Pos logit contributions
 Yao+0.717
 Debor+0.650
 JC+0.635
 intern+0.634
 Spencer+0.633
Neg logit contributions
acs-0.597
olla-0.596
ktop-0.594
rog-0.584
 impaired-0.567
Token campaigns
Token ID9964
Feature activation-1.13e+00

Pos logit contributions
ktop+0.092
olla+0.092
acs+0.092
rog+0.090
 impaired+0.087
Neg logit contributions
 Yao-0.090
 Debor-0.081
 intern-0.079
 JC-0.079
 Spencer-0.079
Token and
Token ID290
Feature activation-3.42e-01

Pos logit contributions
acs+0.819
olla+0.817
ktop+0.814
rog+0.803
 impaired+0.783
Neg logit contributions
 Yao-0.859
 Debor-0.774
 unden-0.754
 JC-0.752
 Spencer-0.751
Token organizations
Token ID5745
Feature activation-6.56e-01

Pos logit contributions
olla+0.244
acs+0.244
ktop+0.244
rog+0.238
 impaired+0.232
Neg logit contributions
 Yao-0.263
 Debor-0.238
 intern-0.233
 JC-0.232
 Spencer-0.232
Token
Token ID198
Feature activation-6.55e-01

Pos logit contributions
olla+0.103
acs+0.103
ktop+0.102
rog+0.100
 impaired+0.097
Neg logit contributions
 Yao-0.152
 Debor-0.139
 intern-0.136
 JC-0.136
 Spencer-0.136
Token
Token ID198
Feature activation-5.16e-01

Pos logit contributions
ktop+0.405
acs+0.402
olla+0.401
rog+0.391
 impaired+0.382
Neg logit contributions
 Yao-0.573
 Debor-0.519
 JC-0.513
 Spencer-0.512
 intern-0.511
TokenDo
Token ID5211
Feature activation-1.42e+00

Pos logit contributions
acs+0.370
ktop+0.370
olla+0.370
rog+0.362
 impaired+0.354
Neg logit contributions
 Yao-0.396
 Debor-0.356
 JC-0.348
 intern-0.348
 Spencer-0.348
Token not
Token ID407
Feature activation+1.03e+00

Pos logit contributions
olla+1.062
acs+1.058
ktop+1.055
rog+1.042
 impaired+1.019
Neg logit contributions
 Yao-1.032
 Debor-0.938
 JC-0.905
 unden-0.902
 Spencer-0.898
Token use
Token ID779
Feature activation+1.42e+00

Pos logit contributions
 Yao+0.749
 Debor+0.668
 intern+0.658
 JC+0.654
 Spencer+0.653
Neg logit contributions
ktop-0.782
acs-0.781
olla-0.780
rog-0.765
 impaired-0.744
Token social
Token ID1919
Feature activation-7.30e-01

Pos logit contributions
 Yao+0.998
 Debor+0.880
 intern+0.874
 Spencer+0.871
 JC+0.870
Neg logit contributions
ktop-1.119
acs-1.119
olla-1.116
rog-1.094
 impaired-1.065
Token media
Token ID2056
Feature activation+4.60e-01

Pos logit contributions
acs+0.548
olla+0.547
ktop+0.546
rog+0.535
 impaired+0.522
Neg logit contributions
 Yao-0.537
 Debor-0.481
 intern-0.472
 JC-0.470
 Spencer-0.470
Token to
Token ID284
Feature activation-6.54e-01

Pos logit contributions
 Yao+0.362
 Debor+0.327
 intern+0.320
 JC+0.320
 Spencer+0.319
Neg logit contributions
acs-0.321
olla-0.321
ktop-0.320
rog-0.313
 impaired-0.305
Token let
Token ID1309
Feature activation+2.19e+00

Pos logit contributions
acs+0.464
olla+0.464
ktop+0.463
rog+0.454
 impaired+0.443
Neg logit contributions
 Yao-0.506
 Debor-0.458
 JC-0.446
 intern-0.445
 Spencer-0.445
Token people
Token ID661
Feature activation-6.44e-01

Pos logit contributions
 Yao+1.765
 Debor+1.580
 Spencer+1.575
 intern+1.573
 JC+1.563
Neg logit contributions
ktop-1.519
olla-1.506
acs-1.485
rog-1.446
 impaired-1.396
Token know
Token ID760
Feature activation-4.82e-01

Pos logit contributions
ktop+0.443
olla+0.443
acs+0.442
rog+0.432
 impaired+0.420
Neg logit contributions
 Yao-0.513
 Debor-0.464
 intern-0.457
 JC-0.455
 Spencer-0.454
Token she
Token ID673
Feature activation-6.29e-01

Pos logit contributions
 Yao+0.364
 Debor+0.331
 intern+0.326
 Spencer+0.325
 JC+0.324
Neg logit contributions
ktop-0.283
olla-0.281
acs-0.280
rog-0.274
 impaired-0.264
Token would
Token ID561
Feature activation+3.03e-01

Pos logit contributions
ktop+0.376
olla+0.373
acs+0.373
rog+0.364
 impaired+0.347
Neg logit contributions
 Yao-0.562
 Debor-0.515
 intern-0.510
 JC-0.505
 Spencer-0.504
Token put
Token ID1234
Feature activation+5.19e-01

Pos logit contributions
 Yao+0.231
 Debor+0.208
 intern+0.205
 JC+0.204
 Spencer+0.203
Neg logit contributions
ktop-0.219
acs-0.219
olla-0.218
rog-0.214
 impaired-0.208
Token them
Token ID606
Feature activation+5.91e-02

Pos logit contributions
 Yao+0.422
 Debor+0.383
 Spencer+0.376
 intern+0.375
 JC+0.375
Neg logit contributions
ktop-0.351
olla-0.350
acs-0.350
rog-0.341
 impaired-0.330
Token to
Token ID284
Feature activation-9.98e-01

Pos logit contributions
 Yao+0.042
 Debor+0.038
 intern+0.037
 Spencer+0.037
 JC+0.037
Neg logit contributions
ktop-0.045
olla-0.045
acs-0.045
rog-0.044
 impaired-0.043
Token sleep
Token ID3993
Feature activation-1.53e+00

Pos logit contributions
olla+0.707
acs+0.702
ktop+0.700
rog+0.689
 impaired+0.675
Neg logit contributions
 Yao-0.772
 Debor-0.700
 JC-0.683
 unden-0.682
 intern-0.680
Token each
Token ID1123
Feature activation+8.84e-01

Pos logit contributions
olla+1.160
acs+1.159
ktop+1.158
rog+1.136
 impaired+1.107
Neg logit contributions
 Yao-1.112
 Debor-0.997
 intern-0.973
 JC-0.971
 Spencer-0.971
Token night
Token ID1755
Feature activation+5.74e-01

Pos logit contributions
 Yao+0.842
 Debor+0.772
 intern+0.765
 Spencer+0.761
 JC+0.760
Neg logit contributions
ktop-0.478
acs-0.476
olla-0.476
rog-0.461
 impaired-0.439
Token as
Token ID355
Feature activation+1.12e+00

Pos logit contributions
 Yao+0.405
 Debor+0.361
 intern+0.356
 Spencer+0.354
 JC+0.351
Neg logit contributions
ktop-0.451
acs-0.448
olla-0.448
rog-0.439
 impaired-0.426
Token children
Token ID1751
Feature activation-1.98e+00

Pos logit contributions
 Yao+0.932
 Debor+0.849
 intern+0.835
 Spencer+0.834
 JC+0.828
Neg logit contributions
ktop-0.742
olla-0.733
acs-0.730
rog-0.713
 impaired-0.685
Token,
Token ID11
Feature activation-2.65e-02

Pos logit contributions
acs+1.489
olla+1.487
ktop+1.483
rog+1.458
 impaired+1.424
Neg logit contributions
 Yao-1.447
 Debor-1.299
 JC-1.266
 intern-1.265
 Spencer-1.262
Token action
Token ID2223
Feature activation+4.12e-01

Pos logit contributions
 Yao+0.707
 Debor+0.631
 intern+0.618
 JC+0.615
 Spencer+0.615
Neg logit contributions
ktop-0.773
olla-0.773
acs-0.773
rog-0.757
 impaired-0.737
Token to
Token ID284
Feature activation+5.36e-02

Pos logit contributions
 Yao+0.308
 Debor+0.277
 intern+0.271
 JC+0.270
 Spencer+0.270
Neg logit contributions
olla-0.303
acs-0.303
ktop-0.303
rog-0.297
 impaired-0.289
Token protect
Token ID1805
Feature activation+2.11e-03

Pos logit contributions
 Yao+0.045
 Debor+0.041
 intern+0.040
 JC+0.040
 Spencer+0.040
Neg logit contributions
olla-0.035
ktop-0.035
acs-0.035
rog-0.034
 impaired-0.033
Token Oklahoma
Token ID10433
Feature activation+6.34e-01

Pos logit contributions
 Yao+0.002
 Debor+0.002
 intern+0.002
 JC+0.002
 Spencer+0.002
Neg logit contributions
acs-0.001
ktop-0.001
olla-0.001
rog-0.001
 impaired-0.001
Token residents
Token ID5085
Feature activation+2.92e-01

Pos logit contributions
 Yao+0.484
 Debor+0.436
 intern+0.426
 JC+0.426
 Spencer+0.425
Neg logit contributions
olla-0.457
acs-0.457
ktop-0.457
rog-0.447
 impaired-0.436
Token impacted
Token ID20755
Feature activation-2.33e+00

Pos logit contributions
 Yao+0.233
 Debor+0.211
 intern+0.206
 JC+0.206
 Spencer+0.206
Neg logit contributions
acs-0.200
olla-0.200
ktop-0.200
rog-0.196
 impaired-0.191
Token by
Token ID416
Feature activation-1.21e+00

Pos logit contributions
acs+1.715
olla+1.708
ktop+1.692
rog+1.684
 impaired+1.670
Neg logit contributions
 Yao-1.727
 Debor-1.555
 JC-1.516
 unden-1.513
 Spencer-1.498
Token sw
Token ID1509
Feature activation+7.95e-01

Pos logit contributions
acs+0.876
olla+0.876
ktop+0.875
rog+0.858
 impaired+0.836
Neg logit contributions
 Yao-0.916
 Debor-0.825
 intern-0.806
 JC-0.805
 Spencer-0.804
Tokenarms
Token ID8357
Feature activation+1.07e+00

Pos logit contributions
 Yao+0.536
 Debor+0.479
 JC+0.464
 unden+0.463
 intern+0.462
Neg logit contributions
olla-0.647
acs-0.646
ktop-0.640
rog-0.634
 impaired-0.617
Token of
Token ID286
Feature activation+1.43e+00

Pos logit contributions
 Yao+0.902
 Debor+0.821
 intern+0.805
 JC+0.804
 Spencer+0.803
Neg logit contributions
acs-0.683
olla-0.683
ktop-0.682
rog-0.667
 impaired-0.647
Token fracking
Token ID25441
Feature activation+2.11e-01

Pos logit contributions
 Yao+1.137
 Debor+1.021
 intern+1.015
 Spencer+1.012
 JC+1.008
Neg logit contributions
ktop-1.010
olla-0.996
acs-0.993
rog-0.967
lime-0.926
Token The
Token ID383
Feature activation-9.87e-01

Pos logit contributions
ktop+0.072
olla+0.071
acs+0.071
rog+0.070
 impaired+0.068
Neg logit contributions
 Yao-0.077
 Debor-0.069
 Spencer-0.068
 JC-0.067
 intern-0.067
Token cat
Token ID3797
Feature activation-1.05e+00

Pos logit contributions
olla+0.644
ktop+0.643
acs+0.643
rog+0.626
 impaired+0.604
Neg logit contributions
 Yao-0.830
 Debor-0.752
 intern-0.741
 Spencer-0.739
 JC-0.739
Token has
Token ID468
Feature activation-2.37e-01

Pos logit contributions
olla+0.691
acs+0.691
ktop+0.690
rog+0.675
 impaired+0.656
Neg logit contributions
 Yao-0.870
 Debor-0.791
 intern-0.774
 JC-0.773
 Spencer-0.772
Token been
Token ID587
Feature activation-3.13e-01

Pos logit contributions
olla+0.158
acs+0.157
ktop+0.157
rog+0.153
 impaired+0.147
Neg logit contributions
 Yao-0.196
 Debor-0.178
 intern-0.176
 Spencer-0.174
 JC-0.174
Token featured
Token ID8096
Feature activation-2.11e+00

Pos logit contributions
olla+0.232
acs+0.232
ktop+0.232
rog+0.227
 impaired+0.219
Neg logit contributions
 Yao-0.234
 Debor-0.210
 intern-0.207
 Spencer-0.205
 JC-0.205
Token in
Token ID287
Feature activation-1.05e+00

Pos logit contributions
ktop+1.564
olla+1.563
acs+1.563
rog+1.535
 impaired+1.504
Neg logit contributions
 Yao-1.564
 Debor-1.407
 JC-1.371
 intern-1.368
 Spencer-1.367
Token segments
Token ID17894
Feature activation-1.46e+00

Pos logit contributions
acs+0.683
olla+0.683
ktop+0.681
rog+0.666
 impaired+0.646
Neg logit contributions
 Yao-0.878
 Debor-0.797
 intern-0.781
 JC-0.781
 Spencer-0.780
Token of
Token ID286
Feature activation-6.64e-01

Pos logit contributions
acs+1.055
olla+1.055
ktop+1.053
rog+1.033
 impaired+1.007
Neg logit contributions
 Yao-1.117
 Debor-1.007
 intern-0.983
 JC-0.983
 Spencer-0.981
Token other
Token ID584
Feature activation-2.18e-01

Pos logit contributions
acs+0.441
olla+0.440
ktop+0.440
rog+0.429
 impaired+0.416
Neg logit contributions
 Yao-0.549
 Debor-0.498
 JC-0.488
 intern-0.488
 Spencer-0.488
Token episodes
Token ID8640
Feature activation-1.26e-02

Pos logit contributions
olla+0.146
ktop+0.146
acs+0.145
rog+0.142
 impaired+0.137
Neg logit contributions
 Yao-0.179
 Debor-0.162
 intern-0.160
 JC-0.159
 Spencer-0.159
Token of
Token ID286
Feature activation-5.13e-01

Pos logit contributions
olla+0.009
acs+0.009
ktop+0.009
rog+0.009
 impaired+0.009
Neg logit contributions
 Yao-0.010
 Debor-0.009
 intern-0.009
 Spencer-0.009
 JC-0.009
Token]
Token ID60
Feature activation-5.64e-02

Pos logit contributions
 Yao+1.231
 Debor+1.091
 intern+1.071
 JC+1.064
 Spencer+1.061
Neg logit contributions
olla-1.480
ktop-1.480
acs-1.480
rog-1.446
 impaired-1.406
Token tradition
Token ID6761
Feature activation-2.05e+00

Pos logit contributions
olla+0.044
acs+0.044
ktop+0.043
rog+0.043
 impaired+0.042
Neg logit contributions
 Yao-0.040
 Debor-0.036
 intern-0.035
 JC-0.035
 Spencer-0.035
Token,
Token ID11
Feature activation-8.14e-01

Pos logit contributions
acs+1.474
olla+1.473
ktop+1.471
rog+1.444
 impaired+1.409
Neg logit contributions
 Yao-1.559
 Debor-1.408
 intern-1.372
 JC-1.371
 Spencer-1.369
Token where
Token ID810
Feature activation-4.93e-01

Pos logit contributions
acs+0.545
olla+0.545
ktop+0.544
rog+0.531
 impaired+0.516
Neg logit contributions
 Yao-0.667
 Debor-0.605
 intern-0.593
 JC-0.593
 Spencer-0.592
Token you
Token ID345
Feature activation-1.00e+00

Pos logit contributions
olla+0.334
acs+0.334
ktop+0.334
rog+0.325
 impaired+0.316
Neg logit contributions
 Yao-0.400
 Debor-0.363
 Spencer-0.356
 intern-0.356
 JC-0.355
Token get
Token ID651
Feature activation-1.66e+00

Pos logit contributions
olla+0.674
acs+0.674
ktop+0.673
rog+0.658
 impaired+0.639
Neg logit contributions
 Yao-0.817
 Debor-0.742
 intern-0.728
 JC-0.726
 Spencer-0.725
Token the
Token ID262
Feature activation+2.70e-01

Pos logit contributions
acs+1.110
olla+1.110
ktop+1.107
rog+1.088
 impaired+1.060
Neg logit contributions
 Yao-1.343
 Debor-1.219
 intern-1.190
 JC-1.190
 Spencer-1.187
Token composer
Token ID26777
Feature activation-1.53e+00

Pos logit contributions
 Yao+0.210
 Debor+0.190
 intern+0.186
 Spencer+0.186
 JC+0.185
Neg logit contributions
acs-0.192
olla-0.192
ktop-0.192
rog-0.187
 impaired-0.182
Token --
Token ID1377
Feature activation+6.09e-02

Pos logit contributions
acs+1.104
olla+1.103
ktop+1.102
rog+1.081
 impaired+1.057
Neg logit contributions
 Yao-1.166
 Debor-1.051
 JC-1.025
 intern-1.024
 Spencer-1.021
Token
Token ID198
Feature activation-6.19e-01

Pos logit contributions
 Yao+0.049
 Debor+0.045
 Spencer+0.044
 intern+0.044
 JC+0.044
Neg logit contributions
acs-0.042
olla-0.042
ktop-0.041
rog-0.040
 impaired-0.039
Token
Token ID198
Feature activation-7.92e-02

Pos logit contributions
ktop+0.387
acs+0.384
olla+0.383
rog+0.373
 impaired+0.364
Neg logit contributions
 Yao-0.537
 Debor-0.485
 JC-0.481
 Spencer-0.480
 intern-0.479
Tokenrop
Token ID1773
Feature activation+5.39e-01

Pos logit contributions
ktop+0.566
olla+0.565
acs+0.562
rog+0.548
 impaired+0.541
Neg logit contributions
 Yao-0.558
 Debor-0.499
 intern-0.490
 Spencer-0.489
 JC-0.488
Tokenyl
Token ID2645
Feature activation+4.77e-01

Pos logit contributions
 Yao+0.466
 Debor+0.427
 intern+0.420
 Spencer+0.419
 JC+0.419
Neg logit contributions
ktop-0.330
acs-0.329
olla-0.328
rog-0.319
 impaired-0.314
Tokenmethyl
Token ID43654
Feature activation-1.74e+00

Pos logit contributions
 Yao+0.387
 Debor+0.350
 intern+0.346
 JC+0.345
 Spencer+0.344
Neg logit contributions
ktop-0.323
olla-0.322
acs-0.320
rog-0.311
 impaired-0.304
Token-
Token ID12
Feature activation+8.09e-01

Pos logit contributions
acs+1.134
olla+1.128
ktop+1.124
rog+1.111
 impaired+1.077
Neg logit contributions
 Yao-1.452
 Debor-1.328
 Spencer-1.290
 intern-1.289
 JC-1.287
Token7
Token ID22
Feature activation+2.39e-01

Pos logit contributions
 Yao+0.626
 Debor+0.560
 intern+0.554
 JC+0.553
 Spencer+0.551
Neg logit contributions
ktop-0.578
olla-0.576
acs-0.571
rog-0.557
 impaired-0.545
Token-(
Token ID30420
Feature activation-3.83e+00

Pos logit contributions
 Yao+0.194
 intern+0.175
 Debor+0.173
 JC+0.172
 Spencer+0.172
Neg logit contributions
ktop-0.165
olla-0.161
acs-0.160
rog-0.155
 impaired-0.151
Token2
Token ID17
Feature activation-9.45e-01

Pos logit contributions
acs+2.837
olla+2.836
ktop+2.806
rog+2.784
 impaired+2.709
Neg logit contributions
 Yao-2.840
 Debor-2.570
 Spencer-2.495
 intern-2.489
 JC-2.482
Token,
Token ID11
Feature activation-2.73e-01

Pos logit contributions
ktop+0.662
olla+0.661
acs+0.657
rog+0.644
 impaired+0.626
Neg logit contributions
 Yao-0.747
 Debor-0.672
 intern-0.663
 JC-0.660
 Spencer-0.658
Token6
Token ID21
Feature activation+4.86e-03

Pos logit contributions
ktop+0.215
olla+0.215
acs+0.215
rog+0.209
 impaired+0.206
Neg logit contributions
 Yao-0.191
 Debor-0.169
 intern-0.166
 JC-0.166
 Spencer-0.165
Token-
Token ID12
Feature activation+9.75e-02

Pos logit contributions
 Yao+0.004
 Debor+0.003
 intern+0.003
 JC+0.003
 Spencer+0.003
Neg logit contributions
ktop-0.003
olla-0.003
acs-0.003
rog-0.003
 impaired-0.003
Tokendim
Token ID27740
Feature activation-1.19e+00

Pos logit contributions
 Yao+0.079
 Debor+0.072
 intern+0.071
 JC+0.071
 Spencer+0.071
Neg logit contributions
ktop-0.065
olla-0.065
acs-0.064
rog-0.063
 impaired-0.061
Token Alberta
Token ID15555
Feature activation-4.34e-01

Pos logit contributions
 Yao+0.913
 Debor+0.819
 Spencer+0.810
 JC+0.809
 intern+0.808
Neg logit contributions
ktop-0.896
olla-0.886
acs-0.884
rog-0.862
 impaired-0.841
Token is
Token ID318
Feature activation-4.53e-01

Pos logit contributions
olla+0.263
ktop+0.263
acs+0.262
rog+0.256
 impaired+0.248
Neg logit contributions
 Yao-0.383
 Debor-0.350
 intern-0.343
 JC-0.343
 Spencer-0.342
Token gonna
Token ID8066
Feature activation-6.44e-01

Pos logit contributions
ktop+0.306
olla+0.304
acs+0.303
rog+0.296
 impaired+0.287
Neg logit contributions
 Yao-0.370
 Debor-0.335
 intern-0.329
 JC-0.329
 Spencer-0.329
Token succeed
Token ID6758
Feature activation+5.29e-01

Pos logit contributions
olla+0.416
acs+0.416
ktop+0.416
rog+0.406
 impaired+0.395
Neg logit contributions
 Yao-0.541
 Debor-0.492
 intern-0.483
 JC-0.482
 Spencer-0.481
Token by
Token ID416
Feature activation+1.06e-01

Pos logit contributions
 Yao+0.393
 Debor+0.353
 intern+0.345
 Spencer+0.344
 JC+0.344
Neg logit contributions
olla-0.395
ktop-0.394
acs-0.394
rog-0.385
 impaired-0.376
Token pitching
Token ID21088
Feature activation-3.33e+00

Pos logit contributions
 Yao+0.084
 Debor+0.076
 intern+0.074
 JC+0.074
 Spencer+0.074
Neg logit contributions
olla-0.074
acs-0.074
ktop-0.074
rog-0.072
 impaired-0.070
Token a
Token ID257
Feature activation-7.68e-01

Pos logit contributions
acs+2.190
olla+2.176
rog+2.162
ktop+2.139
 impaired+2.103
Neg logit contributions
 Yao-2.706
 Debor-2.471
 unden-2.400
 intern-2.396
 JC-2.379
Token radical
Token ID7702
Feature activation-1.72e+00

Pos logit contributions
olla+0.521
acs+0.521
ktop+0.519
rog+0.510
 impaired+0.496
Neg logit contributions
 Yao-0.619
 Debor-0.561
 intern-0.549
 JC-0.547
 Spencer-0.547
Token program
Token ID1430
Feature activation-4.58e-01

Pos logit contributions
olla+1.270
acs+1.268
ktop+1.262
rog+1.245
 impaired+1.216
Neg logit contributions
 Yao-1.281
 Debor-1.150
 intern-1.120
 JC-1.118
 Spencer-1.116
Token.
Token ID13
Feature activation+4.65e-01

Pos logit contributions
olla+0.324
ktop+0.323
acs+0.323
rog+0.316
 impaired+0.308
Neg logit contributions
 Yao-0.357
 Debor-0.322
 intern-0.315
 Spencer-0.315
 JC-0.315
Token It
Token ID632
Feature activation-7.47e-02

Pos logit contributions
 Yao+0.365
 Debor+0.330
 JC+0.323
 Spencer+0.323
 intern+0.320
Neg logit contributions
ktop-0.331
acs-0.327
olla-0.327
rog-0.321
 impaired-0.314
Token the
Token ID262
Feature activation+1.97e+00

Pos logit contributions
 Yao+1.687
 intern+1.528
 Debor+1.525
 Spencer+1.511
 JC+1.506
Neg logit contributions
ktop-1.325
olla-1.325
acs-1.305
rog-1.279
 impaired-1.229
Token Catholic
Token ID7835
Feature activation-7.91e-01

Pos logit contributions
 Yao+1.339
 Spencer+1.204
 Debor+1.198
 JC+1.184
 intern+1.178
Neg logit contributions
olla-1.598
ktop-1.594
acs-1.564
rog-1.539
 impaired-1.521
Token Encyclopedia
Token ID36732
Feature activation-8.39e-01

Pos logit contributions
acs+0.555
ktop+0.554
olla+0.554
rog+0.543
 impaired+0.530
Neg logit contributions
 Yao-0.618
 Debor-0.558
 JC-0.545
 unden-0.542
 intern-0.542
Token,
Token ID11
Feature activation-4.96e-01

Pos logit contributions
olla+0.646
acs+0.644
ktop+0.642
rog+0.632
 impaired+0.618
Neg logit contributions
 Yao-0.601
 Debor-0.540
 JC-0.524
 unden-0.523
 Spencer-0.523
Token Church
Token ID4564
Feature activation-1.56e+00

Pos logit contributions
acs+0.384
olla+0.382
ktop+0.380
rog+0.377
 impaired+0.369
Neg logit contributions
 Yao-0.351
 Debor-0.314
 unden-0.305
 JC-0.304
 intern-0.303
Token Fathers
Token ID30969
Feature activation-3.32e+00

Pos logit contributions
acs+1.055
ktop+1.049
olla+1.041
rog+1.021
 impaired+0.993
Neg logit contributions
 Yao-1.278
 Debor-1.159
 intern-1.144
 Spencer-1.144
 JC-1.135
Token,
Token ID11
Feature activation-1.10e+00

Pos logit contributions
olla+2.290
acs+2.285
rog+2.280
ktop+2.226
lime+2.195
Neg logit contributions
 Yao-2.563
 Debor-2.391
 unden-2.352
 confir-2.292
 JC-2.258
Token Sum
Token ID5060
Feature activation+5.98e-01

Pos logit contributions
olla+0.886
ktop+0.885
acs+0.885
rog+0.867
 impaired+0.848
Neg logit contributions
 Yao-0.748
 Debor-0.662
 intern-0.650
 Spencer-0.648
 JC-0.647
Tokenma
Token ID2611
Feature activation-1.56e+00

Pos logit contributions
 Yao+0.403
 Debor+0.354
 intern+0.351
 JC+0.347
 Spencer+0.343
Neg logit contributions
ktop-0.490
acs-0.483
olla-0.482
rog-0.472
 impaired-0.468
Token,
Token ID11
Feature activation-6.84e-01

Pos logit contributions
olla+1.126
acs+1.111
ktop+1.103
rog+1.094
 impaired+1.078
Neg logit contributions
 Yao-1.171
 Debor-1.061
 unden-1.048
••-1.020
 JC-1.018
Token Bible
Token ID9111
Feature activation-6.31e-01

Pos logit contributions
olla+0.414
acs+0.412
ktop+0.408
rog+0.402
 impaired+0.393
Neg logit contributions
 Yao-0.599
 Debor-0.551
 unden-0.538
 JC-0.534
 intern-0.534
Token you
Token ID345
Feature activation+2.80e-01

Pos logit contributions
olla+0.199
acs+0.199
ktop+0.199
rog+0.195
 impaired+0.190
Neg logit contributions
 Yao-0.221
 Debor-0.200
 intern-0.196
 JC-0.195
 Spencer-0.195
Token this
Token ID428
Feature activation-3.56e-01

Pos logit contributions
 Yao+0.220
 Debor+0.198
 JC+0.194
 intern+0.194
 Spencer+0.194
Neg logit contributions
ktop-0.197
acs-0.196
olla-0.196
rog-0.191
 impaired-0.186
Token post
Token ID1281
Feature activation-2.02e+00

Pos logit contributions
ktop+0.240
acs+0.240
olla+0.239
rog+0.234
 impaired+0.227
Neg logit contributions
 Yao-0.291
 Debor-0.262
 intern-0.259
 JC-0.258
 Spencer-0.257
Token.
Token ID13
Feature activation-7.54e-01

Pos logit contributions
olla+1.490
acs+1.485
ktop+1.482
rog+1.457
 impaired+1.418
Neg logit contributions
 Yao-1.512
 Debor-1.363
 JC-1.328
 intern-1.327
 unden-1.325
Token<|endoftext|>
Token ID50256
Feature activation-5.41e-01

Pos logit contributions
acs+0.571
ktop+0.570
olla+0.570
rog+0.559
 impaired+0.546
Neg logit contributions
 Yao-0.550
 Debor-0.493
 JC-0.481
 Spencer-0.480
 intern-0.480
TokenTHE
Token ID10970
Feature activation-3.67e+00

Pos logit contributions
ktop+0.395
olla+0.395
acs+0.394
rog+0.385
 impaired+0.378
Neg logit contributions
 Yao-0.408
 Debor-0.366
 JC-0.358
 Spencer-0.358
 intern-0.358
Token BALL
Token ID46433
Feature activation-9.36e-01

Pos logit contributions
acs+2.788
olla+2.781
ktop+2.767
rog+2.731
 impaired+2.672
Neg logit contributions
 Yao-2.625
 Debor-2.369
 Spencer-2.287
 unden-2.286
 intern-2.285
TokenOT
Token ID2394
Feature activation+9.73e-01

Pos logit contributions
ktop+0.675
acs+0.673
olla+0.673
rog+0.658
 impaired+0.643
Neg logit contributions
 Yao-0.718
 Debor-0.645
 JC-0.633
 intern-0.632
 Spencer-0.631
Token FOR
Token ID7473
Feature activation-1.63e-01

Pos logit contributions
 Yao+0.715
 Debor+0.640
 JC+0.631
 intern+0.629
 EB+0.627
Neg logit contributions
ktop-0.733
olla-0.728
acs-0.728
rog-0.713
 impaired-0.690
Token industrial
Token ID7593
Feature activation+7.39e-01

Pos logit contributions
ktop+0.120
olla+0.120
acs+0.120
rog+0.117
 impaired+0.114
Neg logit contributions
 Yao-0.123
 Debor-0.111
 JC-0.108
 Spencer-0.108
 intern-0.108
Token action
Token ID2223
Feature activation+4.78e-01

Pos logit contributions
 Yao+0.557
 Debor+0.500
 intern+0.491
 JC+0.489
 Spencer+0.489
Neg logit contributions
ktop-0.544
olla-0.542
acs-0.541
rog-0.528
 impaired-0.515
Token pc
Token ID40653
Feature activation-1.00e+00

Pos logit contributions
olla+1.559
acs+1.555
ktop+1.552
rog+1.527
 impaired+1.493
Neg logit contributions
 Yao-1.468
 Debor-1.312
 intern-1.279
 JC-1.278
 Spencer-1.274
TokenAny
Token ID7149
Feature activation+7.60e-01

Pos logit contributions
acs+0.691
olla+0.691
ktop+0.687
rog+0.677
 impaired+0.657
Neg logit contributions
 Yao-0.795
 Debor-0.720
 intern-0.702
 Spencer-0.701
 JC-0.701
Tokenwhere
Token ID3003
Feature activation-4.33e-01

Pos logit contributions
 Yao+0.659
 Debor+0.600
 intern+0.591
 JC+0.591
 Spencer+0.588
Neg logit contributions
ktop-0.470
acs-0.468
olla-0.468
rog-0.457
 impaired-0.444
Token,
Token ID11
Feature activation-9.40e-01

Pos logit contributions
olla+0.328
acs+0.328
ktop+0.326
rog+0.321
 impaired+0.313
Neg logit contributions
 Yao-0.315
 Debor-0.282
 intern-0.275
 JC-0.274
 Spencer-0.274
Token Splash
Token ID45275
Feature activation-4.23e-01

Pos logit contributions
acs+0.700
ktop+0.700
olla+0.699
rog+0.684
 impaired+0.667
Neg logit contributions
 Yao-0.696
 Debor-0.627
 intern-0.612
 Spencer-0.612
 JC-0.611
Token Car
Token ID1879
Feature activation-3.32e+00

Pos logit contributions
ktop+0.311
acs+0.310
olla+0.310
rog+0.304
 impaired+0.295
Neg logit contributions
 Yao-0.318
 Debor-0.286
 JC-0.280
 Spencer-0.280
 intern-0.280
Token Wash
Token ID22892
Feature activation-5.98e-01

Pos logit contributions
olla+2.017
acs+2.005
ktop+1.977
rog+1.947
 impaired+1.884
Neg logit contributions
 Yao-2.911
 Debor-2.671
 intern-2.608
 JC-2.603
 unden-2.603
Token,
Token ID11
Feature activation-1.48e+00

Pos logit contributions
acs+0.458
olla+0.458
ktop+0.457
rog+0.449
 impaired+0.438
Neg logit contributions
 Yao-0.430
 Debor-0.385
 intern-0.375
 JC-0.375
 Spencer-0.374
Token Steven
Token ID8239
Feature activation-9.67e-01

Pos logit contributions
acs+1.141
olla+1.139
ktop+1.139
rog+1.117
 impaired+1.090
Neg logit contributions
 Yao-1.059
 Debor-0.948
 intern-0.924
 JC-0.923
 Spencer-0.923
Token La
Token ID4689
Feature activation-1.64e+00

Pos logit contributions
ktop+0.735
olla+0.735
acs+0.735
rog+0.720
 impaired+0.703
Neg logit contributions
 Yao-0.702
 Debor-0.629
 JC-0.613
 intern-0.613
 Spencer-0.613
TokenM
Token ID44
Feature activation+3.20e-01

Pos logit contributions
acs+1.175
olla+1.175
ktop+1.173
rog+1.150
 impaired+1.120
Neg logit contributions
 Yao-1.263
 Debor-1.140
 intern-1.113
 JC-1.112
 Spencer-1.111