TOP ACTIVATIONS
MAX = 1.440

posted by Robert Math is (@ r math is _ the
Cruz told the Texas Tribune the next month . "
, and at the very least , ensure the president knew
Krist in Cav all ari (@ k rist inc av all
weekend . Michael Sch um acher 's Mercedes was third ahead
References <|endoftext|> Police have also seized two dump ers and arrested
Sonia R inc ón (@ S onia R in con
threats ." However , the Department of Health In format ics
and confusion is sitting right next to them .
our reaction has been mild too . Myst ification is a
the brakes and get in front of them . " You
s Cody Wester lund (@ C ody W ester lund
youngster ," says Kevin O ' Malley , whose son Joshua
tell me to get out of here . They just sit
ild on an for counselling toll free on 1800 5 45
Meanwhile , the shutdown forced the Centers for Disease Control
=" Phone List Ctrl "> < ul > < li ng
photo posted by Von Miller (@ von m iller ) on
in puberty and a little too curious about girls and that
previously available on a 1989 Byr ds tribute album .

MIN ACTIVATIONS
MIN = -1.519

Im more n are made up of a mot ley crew
clothes , no make - up and pulled a hood y
" Under ground is it ? We 're
on his chest before she fell to the ground , also
be found at bit . ly / x OV T UB
explain why the f ier cest crackdown s against the protest
York Times . You may opt - out at any time
York Times . You may opt - out at any time
Journal of Research on Ad olesc ence , 8 , 333
measurement was the 24 - item Hamilton Depression Rating Scale measured
Thank you for signing up . For more from The
, this was completely made up . There was no actual
s findings are not an exception . In a 2014 article
York Times . You may opt - out at any time
to Alex Sal mond swinging butt naked on a wreck ing
knew that if we fl unk ed out of school or
AB arry Maryland 1 hour ago This election was not about
55 Recommend Recommend Share this comment on Facebook
- aged Italians had been cons cript ed into forced labour
14 Recommend Recommend Share this comment on Facebook

INTERVAL 0.700 - 1.440
CONTAINS 0.400%

featuring more high - strength steel than the outgoing Rapt or
od . J ag d ish Sh ind e
hot - button issues that galvan ized all unions into signing
sold to UK publisher Jonathan Cape , with an auction understood
more agreement than the rating implied . A larger number of

INTERVAL -0.040 - 0.700
CONTAINS 56.723%

a lot of moving around with the second unit as well
they saw as the over polit ic isation of his role
til I get my here IM M IG RANT food from
The year to year increase of the anthrop ic
is National Debt Bad ? If a government increases

INTERVAL -0.780 - -0.040
CONTAINS 42.614%

the frontrunner for the role . The film recently
written , P ossible shoulder imp ing ement ,
The case began to unfold on September 23 , when
our prototype version of Arena and does not describe completely what
In positive news , Mitch Wall is is likely

INTERVAL -1.519 - -0.780
CONTAINS 0.263%

the cause of national liberation we must foil the expansion
BE ER ! For a mid - strength As ahi dec
at McCoy has a fo os ball table , and it
recipes follow . With the exception of the first recipe ,
pass measures Congress will take up when it returns on Sept
Token posted
Token ID4481
Feature activation-3.94e-01

Pos logit contributions
usra+0.693
matched+0.666
 honors+0.649
 Armen+0.648
 ovarian+0.606
Neg logit contributions
acebook-0.689
wagon-0.674
 Wem-0.608
 NETWORK-0.601
 Lith-0.598
Token by
Token ID416
Feature activation+2.88e-01

Pos logit contributions
usra+1.257
matched+1.208
 honors+1.184
 Armen+1.176
 ovarian+1.096
Neg logit contributions
acebook-1.311
wagon-1.283
 Wem-1.159
 Lith-1.142
 NETWORK-1.139
Token Robert
Token ID5199
Feature activation+6.90e-02

Pos logit contributions
acebook+0.966
wagon+0.946
 Wem+0.862
 NETWORK+0.854
 Lith+0.852
Neg logit contributions
usra-0.911
matched-0.872
 honors-0.841
 Armen-0.837
 ovarian-0.785
Token Math
Token ID16320
Feature activation+2.63e-01

Pos logit contributions
acebook+0.230
wagon+0.225
 Wem+0.203
 NETWORK+0.202
 Lith+0.200
Neg logit contributions
usra-0.221
matched-0.212
 Armen-0.206
 honors-0.206
 ovarian-0.192
Tokenis
Token ID271
Feature activation+2.27e-01

Pos logit contributions
acebook+1.076
wagon+1.057
 Wem+0.976
 NETWORK+0.968
 Lith+0.965
Neg logit contributions
usra-0.643
matched-0.607
 Armen-0.584
 honors-0.584
 ovarian-0.532
Token (@
Token ID4275
Feature activation+1.44e+00

Pos logit contributions
acebook+0.669
wagon+0.656
 Wem+0.584
 NETWORK+0.579
 Lith+0.576
Neg logit contributions
usra-0.815
matched-0.784
 Armen-0.763
 honors-0.762
 ovarian-0.719
Tokenr
Token ID81
Feature activation+3.29e-01

Pos logit contributions
acebook+4.573
wagon+4.554
 Lith+3.950
 Wem+3.947
 NETWORK+3.928
Neg logit contributions
usra-4.614
matched-4.428
 Armen-4.396
 honors-4.366
 ovarian-4.150
Tokenmath
Token ID11018
Feature activation+1.03e-03

Pos logit contributions
acebook+1.097
wagon+1.074
 Wem+0.966
 NETWORK+0.956
 Lith+0.955
Neg logit contributions
usra-1.050
matched-1.007
 Armen-0.983
 honors-0.978
 ovarian-0.917
Tokenis
Token ID271
Feature activation-2.22e-01

Pos logit contributions
acebook+0.004
wagon+0.004
 Wem+0.004
 NETWORK+0.004
 Lith+0.004
Neg logit contributions
usra-0.003
matched-0.003
 Armen-0.002
 honors-0.002
 ovarian-0.002
Token_
Token ID62
Feature activation+1.62e-01

Pos logit contributions
usra+0.722
matched+0.692
 honors+0.672
 Armen+0.672
 ovarian+0.628
Neg logit contributions
acebook-0.731
wagon-0.716
 Wem-0.647
 NETWORK-0.641
 Lith-0.638
Tokenthe
Token ID1169
Feature activation+4.92e-02

Pos logit contributions
acebook+0.544
wagon+0.533
 Wem+0.483
 NETWORK+0.478
 Lith+0.476
Neg logit contributions
usra-0.512
matched-0.491
 honors-0.477
 Armen-0.476
 ovarian-0.444
Token
Token ID250
Feature activation+2.77e-01

Pos logit contributions
acebook+0.259
wagon+0.253
 Wem+0.230
 NETWORK+0.227
 Lith+0.226
Neg logit contributions
usra-0.238
matched-0.227
 Armen-0.221
 honors-0.221
 ovarian-0.206
Token Cruz
Token ID8742
Feature activation+1.78e-02

Pos logit contributions
acebook+1.010
wagon+0.994
 Wem+0.909
 NETWORK+0.899
 Lith+0.899
Neg logit contributions
usra-0.794
matched-0.755
 Armen-0.730
 honors-0.729
 ovarian-0.675
Token told
Token ID1297
Feature activation-2.72e-01

Pos logit contributions
acebook+0.049
wagon+0.048
 Wem+0.042
 NETWORK+0.042
 Lith+0.042
Neg logit contributions
usra-0.067
matched-0.064
 Armen-0.063
 honors-0.063
 ovarian-0.059
Token the
Token ID262
Feature activation+1.55e-02

Pos logit contributions
usra+0.925
matched+0.887
 honors+0.868
 Armen+0.867
 ovarian+0.811
Neg logit contributions
acebook-0.856
wagon-0.838
 Wem-0.747
 NETWORK-0.739
 Lith-0.736
Token Texas
Token ID3936
Feature activation+2.64e-01

Pos logit contributions
acebook+0.051
wagon+0.050
 Wem+0.045
 NETWORK+0.044
 Lith+0.044
Neg logit contributions
usra-0.050
matched-0.048
 Armen-0.047
 honors-0.047
 ovarian-0.044
Token Tribune
Token ID17588
Feature activation+1.36e+00

Pos logit contributions
acebook+0.764
wagon+0.746
 Wem+0.664
 NETWORK+0.660
 Lith+0.654
Neg logit contributions
usra-0.961
matched-0.927
 honors-0.901
 Armen-0.901
 ovarian-0.849
Token the
Token ID262
Feature activation+1.49e-01

Pos logit contributions
acebook+4.270
wagon+4.255
 NETWORK+3.951
 Wem+3.874
 Lith+3.830
Neg logit contributions
usra-4.449
matched-4.235
 Armen-4.101
 honors-4.085
��-3.915
Token next
Token ID1306
Feature activation+4.54e-01

Pos logit contributions
acebook+0.521
wagon+0.510
 Wem+0.466
 NETWORK+0.463
 Lith+0.461
Neg logit contributions
usra-0.450
matched-0.431
 Armen-0.416
 honors-0.415
 ovarian-0.388
Token month
Token ID1227
Feature activation+1.28e-01

Pos logit contributions
acebook+1.427
wagon+1.409
 Wem+1.282
 NETWORK+1.282
 Lith+1.268
Neg logit contributions
usra-1.497
matched-1.447
 Armen-1.388
 honors-1.374
 ovarian-1.296
Token.
Token ID13
Feature activation-2.20e-02

Pos logit contributions
acebook+0.415
wagon+0.409
 Wem+0.370
 NETWORK+0.370
 Lith+0.366
Neg logit contributions
usra-0.418
matched-0.398
 Armen-0.387
 honors-0.386
 ovarian-0.362
Token "
Token ID366
Feature activation-1.64e-01

Pos logit contributions
usra+0.069
matched+0.066
 honors+0.064
 Armen+0.063
 ovarian+0.060
Neg logit contributions
acebook-0.075
wagon-0.073
 Wem-0.067
 NETWORK-0.067
 Lith-0.066
Token,
Token ID11
Feature activation-1.24e-01

Pos logit contributions
acebook+0.719
wagon+0.707
 Wem+0.640
 Lith+0.634
 NETWORK+0.634
Neg logit contributions
usra-0.644
matched-0.614
 Armen-0.593
 honors-0.592
 ovarian-0.553
Token and
Token ID290
Feature activation-2.59e-01

Pos logit contributions
usra+0.421
matched+0.404
 honors+0.395
 Armen+0.394
 ovarian+0.370
Neg logit contributions
acebook-0.387
wagon-0.378
 Wem-0.340
 NETWORK-0.336
 Lith-0.334
Token at
Token ID379
Feature activation+3.35e-02

Pos logit contributions
usra+0.906
matched+0.872
 honors+0.852
 Armen+0.851
 ovarian+0.799
Neg logit contributions
acebook-0.787
wagon-0.769
 Wem-0.686
 NETWORK-0.680
 Lith-0.676
Token the
Token ID262
Feature activation-9.13e-02

Pos logit contributions
acebook+0.101
wagon+0.099
 Wem+0.089
 NETWORK+0.088
 Lith+0.087
Neg logit contributions
usra-0.117
matched-0.113
 Armen-0.110
 honors-0.110
 ovarian-0.103
Token very
Token ID845
Feature activation-2.93e-01

Pos logit contributions
usra+0.227
matched+0.215
 Armen+0.207
 honors+0.206
 ovarian+0.188
Neg logit contributions
acebook-0.369
wagon-0.363
 Wem-0.335
 NETWORK-0.332
 Lith-0.331
Token least
Token ID1551
Feature activation+1.32e+00

Pos logit contributions
usra+0.794
matched+0.754
 Armen+0.729
 honors+0.728
 ovarian+0.670
Neg logit contributions
acebook-1.117
wagon-1.097
 Wem-1.006
 NETWORK-0.998
 Lith-0.994
Token,
Token ID11
Feature activation-9.30e-02

Pos logit contributions
acebook+4.096
wagon+4.046
 Wem+3.715
 Lith+3.670
 NETWORK+3.667
Neg logit contributions
usra-4.367
matched-4.135
 Armen-3.932
 honors-3.862
��-3.762
Token ensure
Token ID4155
Feature activation+7.67e-02

Pos logit contributions
usra+0.330
matched+0.318
 honors+0.312
 Armen+0.311
 ovarian+0.292
Neg logit contributions
acebook-0.277
wagon-0.271
 Wem-0.241
 NETWORK-0.239
 Lith-0.237
Token the
Token ID262
Feature activation+2.69e-01

Pos logit contributions
acebook+0.236
wagon+0.230
 Wem+0.207
 NETWORK+0.204
 Lith+0.204
Neg logit contributions
usra-0.265
matched-0.255
 Armen-0.248
 honors-0.248
 ovarian-0.233
Token president
Token ID1893
Feature activation+3.69e-01

Pos logit contributions
acebook+0.922
wagon+0.905
 Wem+0.822
 NETWORK+0.815
 Lith+0.813
Neg logit contributions
usra-0.833
matched-0.799
 Armen-0.771
 honors-0.770
 ovarian-0.719
Token knew
Token ID2993
Feature activation-6.92e-02

Pos logit contributions
acebook+1.205
wagon+1.184
 Wem+1.072
 NETWORK+1.059
 Lith+1.056
Neg logit contributions
usra-1.197
matched-1.144
 Armen-1.109
 honors-1.101
 ovarian-1.039
Token Krist
Token ID14912
Feature activation+2.13e-01

Pos logit contributions
acebook+1.150
wagon+1.126
 Wem+1.023
 NETWORK+1.014
 Lith+1.010
Neg logit contributions
usra-1.120
matched-1.075
 honors-1.037
 Armen-1.034
 ovarian-0.969
Tokenin
Token ID259
Feature activation+1.82e-01

Pos logit contributions
acebook+0.828
wagon+0.815
 Wem+0.749
 NETWORK+0.741
 Lith+0.740
Neg logit contributions
usra-0.561
matched-0.532
 Armen-0.514
 honors-0.513
 ovarian-0.472
Token Cav
Token ID19931
Feature activation+1.21e-01

Pos logit contributions
acebook+0.600
wagon+0.589
 Wem+0.534
 Lith+0.527
 NETWORK+0.526
Neg logit contributions
usra-0.590
matched-0.565
 honors-0.548
 Armen-0.547
 ovarian-0.513
Tokenall
Token ID439
Feature activation+3.49e-01

Pos logit contributions
acebook+0.440
wagon+0.432
 Wem+0.393
 NETWORK+0.390
 Lith+0.388
Neg logit contributions
usra-0.353
matched-0.337
 Armen-0.326
 honors-0.326
 ovarian-0.302
Tokenari
Token ID2743
Feature activation+4.61e-01

Pos logit contributions
acebook+1.255
wagon+1.237
 Wem+1.123
 Lith+1.115
 NETWORK+1.114
Neg logit contributions
usra-1.014
matched-0.970
 Armen-0.939
 honors-0.938
 ovarian-0.872
Token (@
Token ID4275
Feature activation+1.26e+00

Pos logit contributions
acebook+1.276
wagon+1.262
 Wem+1.113
 NETWORK+1.106
 Lith+1.106
Neg logit contributions
usra-1.729
matched-1.660
 Armen-1.605
 honors-1.604
 ovarian-1.521
Tokenk
Token ID74
Feature activation+4.66e-01

Pos logit contributions
wagon+4.463
acebook+4.422
 Lith+3.948
 Wem+3.920
 NETWORK+3.902
Neg logit contributions
usra-3.589
matched-3.410
 Armen-3.396
 honors-3.378
 ovarian-3.158
Tokenrist
Token ID1585
Feature activation+5.04e-01

Pos logit contributions
acebook+1.481
wagon+1.460
 Wem+1.301
 NETWORK+1.286
 Lith+1.282
Neg logit contributions
usra-1.548
matched-1.485
 Armen-1.457
 honors-1.450
 ovarian-1.364
Tokeninc
Token ID1939
Feature activation+4.15e-01

Pos logit contributions
acebook+1.897
wagon+1.870
 Wem+1.686
 Lith+1.679
 NETWORK+1.671
Neg logit contributions
usra-1.368
matched-1.304
 Armen-1.282
 honors-1.268
 ovarian-1.178
Tokenav
Token ID615
Feature activation+6.65e-02

Pos logit contributions
acebook+1.564
wagon+1.542
 Wem+1.395
 NETWORK+1.384
 Lith+1.380
Neg logit contributions
usra-1.140
matched-1.087
 Armen-1.056
 honors-1.051
 ovarian-0.972
Tokenall
Token ID439
Feature activation+2.17e-01

Pos logit contributions
acebook+0.243
wagon+0.240
 Wem+0.216
 NETWORK+0.215
 Lith+0.214
Neg logit contributions
usra-0.191
matched-0.182
 Armen-0.177
 honors-0.176
 ovarian-0.164
Token weekend
Token ID5041
Feature activation+1.04e-01

Pos logit contributions
acebook+0.285
wagon+0.280
 Wem+0.255
 NETWORK+0.253
 Lith+0.252
Neg logit contributions
usra-0.245
matched-0.234
 Armen-0.227
 honors-0.226
 ovarian-0.210
Token.
Token ID13
Feature activation+4.84e-02

Pos logit contributions
acebook+0.347
wagon+0.340
 Wem+0.309
 NETWORK+0.306
 Lith+0.304
Neg logit contributions
usra-0.331
matched-0.316
 Armen-0.307
 honors-0.306
 ovarian-0.286
Token Michael
Token ID3899
Feature activation-1.23e-02

Pos logit contributions
acebook+0.172
wagon+0.169
 Wem+0.154
 NETWORK+0.153
 Lith+0.152
Neg logit contributions
usra-0.144
matched-0.137
 honors-0.133
 Armen-0.133
 ovarian-0.124
Token Sch
Token ID3059
Feature activation+2.81e-01

Pos logit contributions
usra+0.048
matched+0.047
 Armen+0.046
 honors+0.046
 ovarian+0.043
Neg logit contributions
acebook-0.032
wagon-0.031
 Wem-0.027
 NETWORK-0.027
 Lith-0.026
Tokenum
Token ID388
Feature activation+1.94e-01

Pos logit contributions
acebook+1.310
wagon+1.310
 Wem+1.212
 Transmission+1.207
 Lith+1.205
Neg logit contributions
usra-0.503
matched-0.463
 Armen-0.453
 honors-0.442
��-0.393
Tokenacher
Token ID3493
Feature activation+1.26e+00

Pos logit contributions
acebook+0.857
wagon+0.820
 NETWORK+0.775
 Wem+0.774
 Lith+0.753
Neg logit contributions
usra-0.421
matched-0.398
 Armen-0.389
 honors-0.385
zan-0.352
Token's
Token ID338
Feature activation+3.12e-01

Pos logit contributions
wagon+3.839
acebook+3.828
 Wem+3.441
 Lith+3.437
 Transmission+3.386
Neg logit contributions
usra-4.181
matched-3.958
 Armen-3.905
 honors-3.792
��-3.782
Token Mercedes
Token ID21279
Feature activation+6.76e-01

Pos logit contributions
acebook+0.978
wagon+0.957
 Wem+0.861
 NETWORK+0.851
 Lith+0.850
Neg logit contributions
usra-1.059
matched-1.016
 Armen-0.988
 honors-0.988
 ovarian-0.926
Token was
Token ID373
Feature activation+2.64e-01

Pos logit contributions
acebook+2.116
wagon+2.078
 Wem+1.868
 NETWORK+1.846
 Lith+1.841
Neg logit contributions
usra-2.287
matched-2.193
 Armen-2.132
 honors-2.129
 ovarian-1.999
Token third
Token ID2368
Feature activation+2.51e-01

Pos logit contributions
acebook+0.862
wagon+0.843
 Wem+0.760
 NETWORK+0.754
 Lith+0.749
Neg logit contributions
usra-0.865
matched-0.830
 honors-0.807
 Armen-0.806
 ovarian-0.754
Token ahead
Token ID4058
Feature activation+5.85e-03

Pos logit contributions
acebook+0.855
wagon+0.838
 Wem+0.760
 NETWORK+0.753
 Lith+0.750
Neg logit contributions
usra-0.783
matched-0.748
 Armen-0.727
 honors-0.725
 ovarian-0.676
TokenReferences
Token ID19927
Feature activation+4.43e-02

Pos logit contributions
acebook+0.925
wagon+0.914
 Wem+0.827
 Lith+0.823
 NETWORK+0.822
Neg logit contributions
usra-0.718
matched-0.682
 Armen-0.666
 honors-0.664
 ovarian-0.615
Token<|endoftext|>
Token ID50256
Feature activation+1.56e-01

Pos logit contributions
acebook+0.149
wagon+0.146
 Wem+0.132
 NETWORK+0.132
 Lith+0.132
Neg logit contributions
usra-0.141
matched-0.135
 Armen-0.130
 honors-0.129
��-0.122
TokenPolice
Token ID9039
Feature activation+2.22e-01

Pos logit contributions
acebook+0.536
wagon+0.531
 Wem+0.478
 NETWORK+0.475
 Lith+0.474
Neg logit contributions
usra-0.478
matched-0.454
 Armen-0.445
 honors-0.444
 ovarian-0.413
Token have
Token ID423
Feature activation-5.37e-02

Pos logit contributions
acebook+0.712
wagon+0.701
 Wem+0.633
 NETWORK+0.628
 Lith+0.628
Neg logit contributions
usra-0.731
matched-0.698
 Armen-0.677
 honors-0.675
 ovarian-0.633
Token also
Token ID635
Feature activation-1.46e-02

Pos logit contributions
usra+0.174
matched+0.166
 Armen+0.162
 honors+0.161
 ovarian+0.151
Neg logit contributions
acebook-0.176
wagon-0.173
 Wem-0.157
 NETWORK-0.155
 Lith-0.155
Token seized
Token ID12000
Feature activation+1.23e+00

Pos logit contributions
usra+0.048
matched+0.046
 Armen+0.045
 honors+0.045
 ovarian+0.042
Neg logit contributions
acebook-0.047
wagon-0.046
 Wem-0.041
 NETWORK-0.041
 Lith-0.041
Token two
Token ID734
Feature activation+2.19e-02

Pos logit contributions
acebook+3.688
wagon+3.585
 Lith+3.321
 Wem+3.308
 NETWORK+3.235
Neg logit contributions
usra-4.231
matched-4.034
 Armen-3.866
 honors-3.855
��-3.762
Token dump
Token ID10285
Feature activation-3.85e-01

Pos logit contributions
acebook+0.070
wagon+0.068
 Wem+0.062
 Lith+0.061
 NETWORK+0.061
Neg logit contributions
usra-0.073
matched-0.070
 honors-0.068
 Armen-0.067
��-0.063
Tokeners
Token ID364
Feature activation-1.71e-01

Pos logit contributions
usra+1.127
matched+1.074
 honors+1.046
 Armen+1.042
 ovarian+0.963
Neg logit contributions
acebook-1.402
wagon-1.348
 Wem-1.246
 NETWORK-1.235
 Transmission-1.218
Token and
Token ID290
Feature activation+1.52e-01

Pos logit contributions
usra+0.540
matched+0.518
 honors+0.504
 Armen+0.503
 ovarian+0.469
Neg logit contributions
acebook-0.576
wagon-0.562
 Wem-0.509
 NETWORK-0.505
 Lith-0.502
Token arrested
Token ID5169
Feature activation+4.84e-01

Pos logit contributions
acebook+0.474
wagon+0.463
 Wem+0.416
 NETWORK+0.412
 Lith+0.409
Neg logit contributions
usra-0.521
matched-0.501
 honors-0.488
 Armen-0.488
 ovarian-0.458
Token
Token ID851
Feature activation-1.91e-01

Pos logit contributions
acebook+0.260
wagon+0.255
 Wem+0.231
 NETWORK+0.228
 Lith+0.227
Neg logit contributions
usra-0.244
matched-0.234
 Armen-0.227
 honors-0.227
 ovarian-0.212
Token Sonia
Token ID20733
Feature activation+3.04e-01

Pos logit contributions
usra+0.606
matched+0.580
 Armen+0.567
 honors+0.565
 ovarian+0.526
Neg logit contributions
acebook-0.643
wagon-0.631
 Wem-0.569
 NETWORK-0.563
 Lith-0.561
Token R
Token ID371
Feature activation+6.43e-02

Pos logit contributions
acebook+1.037
wagon+1.019
 Wem+0.931
 Lith+0.921
 NETWORK+0.917
Neg logit contributions
usra-0.946
matched-0.905
 honors-0.875
 Armen-0.871
 ovarian-0.817
Tokeninc
Token ID1939
Feature activation+8.28e-01

Pos logit contributions
acebook+0.228
wagon+0.224
 Wem+0.204
 NETWORK+0.202
 Lith+0.201
Neg logit contributions
usra-0.191
matched-0.183
 honors-0.177
 Armen-0.177
 ovarian-0.165
Tokenón
Token ID18840
Feature activation+3.19e-01

Pos logit contributions
wagon+2.759
acebook+2.752
 Wem+2.458
 Lith+2.428
 Transmission+2.425
Neg logit contributions
usra-2.588
matched-2.501
 honors-2.416
 Armen-2.414
��-2.257
Token (@
Token ID4275
Feature activation+1.23e+00

Pos logit contributions
acebook+0.912
wagon+0.895
 Wem+0.799
 NETWORK+0.792
 Lith+0.789
Neg logit contributions
usra-1.166
matched-1.124
 honors-1.090
 Armen-1.087
 ovarian-1.029
TokenS
Token ID50
Feature activation+3.43e-01

Pos logit contributions
acebook+4.098
wagon+4.097
 NETWORK+3.593
 Wem+3.583
 Lith+3.579
Neg logit contributions
usra-3.656
matched-3.553
 Armen-3.488
 honors-3.486
 ovarian-3.271
Tokenonia
Token ID11339
Feature activation+1.04e+00

Pos logit contributions
acebook+1.205
wagon+1.182
 Wem+1.066
 NETWORK+1.061
 Lith+1.056
Neg logit contributions
usra-1.027
matched-0.990
 honors-0.960
 Armen-0.959
 ovarian-0.890
TokenR
Token ID49
Feature activation+2.35e-01

Pos logit contributions
acebook+2.818
wagon+2.787
 Wem+2.384
 Lith+2.381
 NETWORK+2.379
Neg logit contributions
usra-3.832
matched-3.738
 honors-3.643
 Armen-3.640
 ovarian-3.439
Tokenin
Token ID259
Feature activation+1.03e-01

Pos logit contributions
acebook+0.739
wagon+0.717
 Wem+0.638
 NETWORK+0.633
 Lith+0.628
Neg logit contributions
usra-0.794
matched-0.768
 Armen-0.752
 honors-0.749
 ovarian-0.707
Tokencon
Token ID1102
Feature activation-2.54e-01

Pos logit contributions
acebook+0.362
wagon+0.355
 Wem+0.322
 NETWORK+0.320
 Lith+0.319
Neg logit contributions
usra-0.308
matched-0.295
 Armen-0.286
 honors-0.286
 ovarian-0.265
Token threats
Token ID7432
Feature activation+4.61e-03

Pos logit contributions
acebook+0.601
wagon+0.588
 Wem+0.529
 NETWORK+0.524
 Lith+0.521
Neg logit contributions
usra-0.625
matched-0.600
 honors-0.584
 Armen-0.583
 ovarian-0.547
Token."
Token ID526
Feature activation+2.03e-01

Pos logit contributions
acebook+0.016
wagon+0.015
 Wem+0.014
 NETWORK+0.014
 Lith+0.014
Neg logit contributions
usra-0.014
matched-0.014
 honors-0.013
 Armen-0.013
 ovarian-0.012
Token However
Token ID2102
Feature activation+4.61e-01

Pos logit contributions
acebook+0.661
wagon+0.646
 Wem+0.587
 NETWORK+0.582
 Lith+0.578
Neg logit contributions
usra-0.668
matched-0.639
 honors-0.621
 Armen-0.620
 ovarian-0.581
Token,
Token ID11
Feature activation-1.24e-01

Pos logit contributions
acebook+1.582
wagon+1.533
 Wem+1.423
 NETWORK+1.411
 Lith+1.398
Neg logit contributions
usra-1.431
matched-1.357
 honors-1.305
 Armen-1.303
��-1.238
Token the
Token ID262
Feature activation+1.58e-01

Pos logit contributions
usra+0.406
matched+0.390
 honors+0.380
 Armen+0.380
 ovarian+0.355
Neg logit contributions
acebook-0.406
wagon-0.398
 Wem-0.357
 NETWORK-0.354
 Lith-0.352
Token Department
Token ID2732
Feature activation+1.22e+00

Pos logit contributions
acebook+0.491
wagon+0.480
 Wem+0.432
 NETWORK+0.428
 Lith+0.425
Neg logit contributions
usra-0.542
matched-0.520
 Armen-0.506
 honors-0.506
 ovarian-0.474
Token of
Token ID286
Feature activation+9.36e-02

Pos logit contributions
acebook+3.951
wagon+3.887
 Wem+3.535
 NETWORK+3.509
 Lith+3.488
Neg logit contributions
usra-3.944
matched-3.651
 Armen-3.502
 honors-3.497
��-3.350
Token Health
Token ID3893
Feature activation-1.11e-01

Pos logit contributions
acebook+0.312
wagon+0.304
 Wem+0.280
 NETWORK+0.278
 Transmission+0.276
Neg logit contributions
usra-0.301
matched-0.285
 Armen-0.276
 honors-0.276
��-0.258
Token In
Token ID554
Feature activation-1.98e-01

Pos logit contributions
usra+0.385
matched+0.371
 honors+0.361
 Armen+0.361
 ovarian+0.339
Neg logit contributions
acebook-0.341
wagon-0.333
 Wem-0.298
 NETWORK-0.295
 Lith-0.293
Tokenformat
Token ID18982
Feature activation+1.87e-01

Pos logit contributions
usra+0.790
matched+0.763
 honors+0.745
 Armen+0.745
 ovarian+0.706
Neg logit contributions
acebook-0.505
wagon-0.491
 Wem-0.428
 NETWORK-0.423
 Lith-0.419
Tokenics
Token ID873
Feature activation-4.44e-01

Pos logit contributions
acebook+0.827
wagon+0.813
 Wem+0.754
 NETWORK+0.750
 Lith+0.746
Neg logit contributions
usra-0.395
matched-0.370
 Armen-0.353
 honors-0.353
 ovarian-0.316
Token and
Token ID290
Feature activation-7.28e-02

Pos logit contributions
usra+0.423
matched+0.406
 Armen+0.395
 honors+0.395
 ovarian+0.369
Neg logit contributions
acebook-0.410
wagon-0.401
 Wem-0.361
 NETWORK-0.358
 Lith-0.356
Token confusion
Token ID10802
Feature activation-2.18e-01

Pos logit contributions
usra+0.234
matched+0.224
 honors+0.218
 Armen+0.218
 ovarian+0.204
Neg logit contributions
acebook-0.242
wagon-0.236
 Wem-0.214
 NETWORK-0.212
 Lith-0.211
Token is
Token ID318
Feature activation-1.58e-01

Pos logit contributions
usra+0.725
matched+0.697
 Armen+0.679
 honors+0.679
 ovarian+0.635
Neg logit contributions
acebook-0.697
wagon-0.681
 Wem-0.613
 NETWORK-0.607
 Lith-0.604
Token sitting
Token ID5586
Feature activation-1.93e-01

Pos logit contributions
usra+0.406
matched+0.384
 honors+0.370
 Armen+0.370
 ovarian+0.339
Neg logit contributions
acebook-0.625
wagon-0.615
 Wem-0.566
 NETWORK-0.562
 Lith-0.560
Token right
Token ID826
Feature activation+3.69e-01

Pos logit contributions
usra+0.607
matched+0.581
 honors+0.565
 Armen+0.564
 ovarian+0.526
Neg logit contributions
acebook-0.656
wagon-0.642
 Wem-0.582
 NETWORK-0.577
 Lith-0.574
Token next
Token ID1306
Feature activation+1.20e+00

Pos logit contributions
acebook+1.199
wagon+1.181
 Wem+1.066
 NETWORK+1.054
 Lith+1.052
Neg logit contributions
usra-1.202
matched-1.137
 Armen-1.112
 honors-1.106
��-1.044
Token to
Token ID284
Feature activation+1.20e-01

Pos logit contributions
wagon+3.846
acebook+3.792
 Wem+3.499
 Lith+3.465
 Transmission+3.431
Neg logit contributions
usra-3.851
matched-3.652
 honors-3.541
 Armen-3.509
��-3.347
Token them
Token ID606
Feature activation+6.17e-02

Pos logit contributions
acebook+0.451
wagon+0.444
 Wem+0.409
 Lith+0.404
 NETWORK+0.404
Neg logit contributions
usra-0.333
matched-0.315
 honors-0.305
 Armen-0.304
��-0.281
Token.
Token ID13
Feature activation-1.09e-01

Pos logit contributions
acebook+0.210
wagon+0.206
 Wem+0.187
 NETWORK+0.185
 Lith+0.184
Neg logit contributions
usra-0.193
matched-0.184
 Armen-0.179
 honors-0.179
 ovarian-0.166
Token
Token ID198
Feature activation-1.92e-01

Pos logit contributions
usra+0.318
matched+0.303
 honors+0.293
 Armen+0.293
 ovarian+0.272
Neg logit contributions
acebook-0.392
wagon-0.384
 Wem-0.351
 NETWORK-0.348
 Lith-0.347
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
usra+0.543
matched+0.518
 honors+0.501
 Armen+0.501
 ovarian+0.462
Neg logit contributions
acebook-0.713
wagon-0.697
 Wem-0.638
 NETWORK-0.632
 Lith-0.629
Token our
Token ID674
Feature activation+2.74e-01

Pos logit contributions
acebook+0.875
wagon+0.861
 Wem+0.779
 Lith+0.767
 NETWORK+0.766
Neg logit contributions
usra-0.922
matched-0.885
 honors-0.859
 Armen-0.854
 ovarian-0.804
Token reaction
Token ID6317
Feature activation+5.28e-01

Pos logit contributions
acebook+0.979
wagon+0.959
 Wem+0.879
 Lith+0.869
 NETWORK+0.869
Neg logit contributions
usra-0.808
matched-0.775
 honors-0.743
 Armen-0.743
��-0.691
Token has
Token ID468
Feature activation-2.33e-02

Pos logit contributions
acebook+1.618
wagon+1.600
 Wem+1.442
 NETWORK+1.429
 Lith+1.426
Neg logit contributions
usra-1.780
matched-1.698
 honors-1.656
 Armen-1.652
 ovarian-1.575
Token been
Token ID587
Feature activation+1.27e-01

Pos logit contributions
usra+0.077
matched+0.074
 honors+0.071
 Armen+0.071
 ovarian+0.067
Neg logit contributions
acebook-0.075
wagon-0.074
 Wem-0.067
 Lith-0.066
 NETWORK-0.066
Token mild
Token ID11607
Feature activation+2.31e-01

Pos logit contributions
acebook+0.423
wagon+0.416
 Wem+0.378
 NETWORK+0.374
 Lith+0.374
Neg logit contributions
usra-0.401
matched-0.384
 honors-0.372
 Armen-0.370
 ovarian-0.347
Token too
Token ID1165
Feature activation+1.19e+00

Pos logit contributions
acebook+0.792
wagon+0.780
 Wem+0.708
 Lith+0.701
 NETWORK+0.701
Neg logit contributions
usra-0.708
matched-0.677
 honors-0.655
 Armen-0.655
 ovarian-0.611
Token.
Token ID13
Feature activation+5.92e-02

Pos logit contributions
acebook+3.722
wagon+3.715
 Lith+3.367
 Wem+3.353
 NETWORK+3.344
Neg logit contributions
usra-3.886
matched-3.687
 honors-3.547
 Armen-3.529
 ovarian-3.341
Token Myst
Token ID32347
Feature activation+1.43e-02

Pos logit contributions
acebook+0.203
wagon+0.199
 Wem+0.181
 NETWORK+0.179
 Lith+0.179
Neg logit contributions
usra-0.183
matched-0.175
 honors-0.170
 Armen-0.170
 ovarian-0.159
Tokenification
Token ID2649
Feature activation+2.57e-01

Pos logit contributions
acebook+0.047
wagon+0.046
 Wem+0.042
 NETWORK+0.041
 Lith+0.041
Neg logit contributions
usra-0.046
matched-0.044
 honors-0.043
 Armen-0.043
 ovarian-0.040
Token is
Token ID318
Feature activation+1.30e-01

Pos logit contributions
acebook+0.849
wagon+0.836
 Wem+0.756
 NETWORK+0.749
 Lith+0.747
Neg logit contributions
usra-0.825
matched-0.790
 Armen-0.764
 honors-0.763
 ovarian-0.715
Token a
Token ID257
Feature activation+3.33e-01

Pos logit contributions
acebook+0.428
wagon+0.420
 Wem+0.380
 NETWORK+0.377
 Lith+0.376
Neg logit contributions
usra-0.417
matched-0.400
 honors-0.387
 Armen-0.387
 ovarian-0.361
Token the
Token ID262
Feature activation-2.53e-02

Pos logit contributions
acebook+0.095
wagon+0.093
 Wem+0.083
 NETWORK+0.083
 Lith+0.082
Neg logit contributions
usra-0.112
matched-0.108
 honors-0.105
 Armen-0.105
 ovarian-0.099
Token brakes
Token ID23746
Feature activation+2.52e-01

Pos logit contributions
usra+0.088
matched+0.085
 honors+0.082
 Armen+0.082
 ovarian+0.077
Neg logit contributions
acebook-0.078
wagon-0.076
 Wem-0.068
 NETWORK-0.067
 Lith-0.067
Token and
Token ID290
Feature activation+2.52e-01

Pos logit contributions
acebook+0.854
wagon+0.837
 Wem+0.758
 NETWORK+0.752
 Lith+0.748
Neg logit contributions
usra-0.791
matched-0.757
 honors-0.735
 Armen-0.735
 ovarian-0.685
Token get
Token ID651
Feature activation+1.72e-01

Pos logit contributions
acebook+0.832
wagon+0.815
 Wem+0.737
 NETWORK+0.730
 Lith+0.727
Neg logit contributions
usra-0.815
matched-0.780
 Armen-0.757
 honors-0.757
 ovarian-0.707
Token in
Token ID287
Feature activation+3.31e-01

Pos logit contributions
acebook+0.576
wagon+0.563
 Wem+0.509
 NETWORK+0.506
 Lith+0.502
Neg logit contributions
usra-0.549
matched-0.527
 honors-0.513
 Armen-0.512
 ovarian-0.478
Token front
Token ID2166
Feature activation+1.19e+00

Pos logit contributions
acebook+1.067
wagon+1.045
 Wem+0.943
 NETWORK+0.931
 Lith+0.929
Neg logit contributions
usra-1.095
matched-1.047
 Armen-1.021
 honors-1.019
 ovarian-0.955
Token of
Token ID286
Feature activation+4.90e-01

Pos logit contributions
acebook+4.012
wagon+3.958
 Wem+3.568
 Lith+3.554
 Transmission+3.552
Neg logit contributions
usra-3.623
matched-3.400
 Armen-3.338
 honors-3.302
��-3.126
Token them
Token ID606
Feature activation+3.45e-01

Pos logit contributions
acebook+1.732
wagon+1.697
 Wem+1.550
 Lith+1.531
 NETWORK+1.526
Neg logit contributions
usra-1.463
matched-1.392
 Armen-1.350
 honors-1.348
 ovarian-1.254
Token.
Token ID13
Feature activation+3.49e-01

Pos logit contributions
acebook+1.156
wagon+1.133
 Wem+1.025
 NETWORK+1.015
 Lith+1.012
Neg logit contributions
usra-1.094
matched-1.045
 Armen-1.016
 honors-1.015
 ovarian-0.947
Token "
Token ID366
Feature activation+1.23e-01

Pos logit contributions
acebook+1.157
wagon+1.131
 Wem+1.015
 NETWORK+1.006
 Lith+0.998
Neg logit contributions
usra-1.128
matched-1.085
 Armen-1.059
 honors-1.051
 ovarian-0.981
TokenYou
Token ID1639
Feature activation+2.14e-01

Pos logit contributions
acebook+0.444
wagon+0.432
 Wem+0.393
 NETWORK+0.391
 Lith+0.387
Neg logit contributions
usra-0.361
matched-0.347
 Armen-0.336
 honors-0.333
 ovarian-0.308
Tokens
Token ID82
Feature activation+7.12e-03

Pos logit contributions
usra+0.324
matched+0.309
 honors+0.300
 Armen+0.298
 ovarian+0.278
Neg logit contributions
acebook-0.402
wagon-0.392
 Wem-0.358
 Lith-0.354
 NETWORK-0.354
Token
Token ID851
Feature activation+1.41e-01

Pos logit contributions
acebook+0.024
wagon+0.023
 Wem+0.021
 Lith+0.021
 NETWORK+0.020
Neg logit contributions
usra-0.023
matched-0.022
 honors-0.021
 Armen-0.021
 ovarian-0.020
Token Cody
Token ID27035
Feature activation+4.83e-01

Pos logit contributions
acebook+0.479
wagon+0.469
 Wem+0.426
 NETWORK+0.422
 Lith+0.420
Neg logit contributions
usra-0.444
matched-0.424
 honors-0.411
 Armen-0.410
 ovarian-0.384
Token Wester
Token ID32104
Feature activation+2.99e-01

Pos logit contributions
acebook+1.556
wagon+1.530
 Wem+1.401
 Lith+1.393
 NETWORK+1.376
Neg logit contributions
usra-1.592
matched-1.526
 honors-1.471
 Armen-1.454
 ovarian-1.384
Tokenlund
Token ID37525
Feature activation+4.93e-01

Pos logit contributions
acebook+1.140
wagon+1.124
 Wem+1.029
 NETWORK+1.022
 Lith+1.017
Neg logit contributions
usra-0.811
matched-0.769
 Armen-0.744
 honors-0.743
 ovarian-0.685
Token (@
Token ID4275
Feature activation+1.15e+00

Pos logit contributions
acebook+1.341
wagon+1.327
 Wem+1.181
 Lith+1.167
 NETWORK+1.166
Neg logit contributions
usra-1.872
matched-1.791
 honors-1.740
 Armen-1.728
 ovarian-1.652
TokenC
Token ID34
Feature activation+6.23e-01

Pos logit contributions
wagon+3.594
acebook+3.538
 Lith+3.087
 NETWORK+3.072
 Wem+3.040
Neg logit contributions
usra-3.852
 Armen-3.633
matched-3.632
 honors-3.612
 ovarian-3.444
Tokenody
Token ID1118
Feature activation+8.22e-01

Pos logit contributions
acebook+2.594
wagon+2.562
 NETWORK+2.332
 Wem+2.327
 Lith+2.322
Neg logit contributions
usra-1.450
matched-1.367
 Armen-1.328
 honors-1.324
��-1.209
TokenW
Token ID54
Feature activation+1.85e-02

Pos logit contributions
wagon+2.531
acebook+2.503
 Wem+2.202
 NETWORK+2.156
 Lith+2.156
Neg logit contributions
usra-2.803
matched-2.688
 Armen-2.653
 honors-2.620
 ovarian-2.489
Tokenester
Token ID7834
Feature activation+3.57e-01

Pos logit contributions
acebook+0.067
wagon+0.065
 Wem+0.060
 NETWORK+0.059
 Lith+0.059
Neg logit contributions
usra-0.055
matched-0.052
 honors-0.051
 Armen-0.051
 ovarian-0.047
Tokenlund
Token ID37525
Feature activation+2.39e-01

Pos logit contributions
acebook+1.211
wagon+1.193
 Wem+1.072
 NETWORK+1.069
 Lith+1.063
Neg logit contributions
usra-1.113
matched-1.063
 Armen-1.039
 honors-1.037
 ovarian-0.967
Token youngster
Token ID40944
Feature activation+2.71e-01

Pos logit contributions
usra+0.163
matched+0.157
 honors+0.154
 Armen+0.153
 ovarian+0.144
Neg logit contributions
acebook-0.139
wagon-0.134
 Wem-0.119
 NETWORK-0.119
 Lith-0.117
Token,"
Token ID553
Feature activation+2.68e-01

Pos logit contributions
acebook+0.949
wagon+0.927
 Wem+0.844
 NETWORK+0.837
 Lith+0.831
Neg logit contributions
usra-0.824
matched-0.788
 honors-0.765
 Armen-0.764
 ovarian-0.710
Token says
Token ID1139
Feature activation+9.32e-02

Pos logit contributions
acebook+0.726
wagon+0.707
 Wem+0.624
 NETWORK+0.617
 Lith+0.614
Neg logit contributions
usra-1.028
matched-0.991
 Armen-0.967
 honors-0.967
 ovarian-0.914
Token Kevin
Token ID7939
Feature activation+1.27e-01

Pos logit contributions
acebook+0.281
wagon+0.275
 Wem+0.246
 NETWORK+0.243
 Lith+0.242
Neg logit contributions
usra-0.327
matched-0.315
 Armen-0.307
 honors-0.307
 ovarian-0.288
Token O
Token ID440
Feature activation+3.83e-01

Pos logit contributions
acebook+0.412
wagon+0.403
 Wem+0.365
 NETWORK+0.360
 Lith+0.360
Neg logit contributions
usra-0.416
matched-0.398
 honors-0.387
 Armen-0.386
 ovarian-0.362
Token'
Token ID6
Feature activation+1.15e+00

Pos logit contributions
acebook+1.330
wagon+1.304
 Wem+1.188
 NETWORK+1.174
 Lith+1.170
Neg logit contributions
usra-1.169
matched-1.118
 honors-1.086
 Armen-1.085
 ovarian-1.011
TokenMalley
Token ID33776
Feature activation+3.52e-01

Pos logit contributions
acebook+3.612
wagon+3.582
 Wem+3.259
 Lith+3.234
 NETWORK+3.228
Neg logit contributions
usra-3.810
matched-3.596
 honors-3.532
 Armen-3.506
 ovarian-3.314
Token,
Token ID11
Feature activation+3.35e-01

Pos logit contributions
acebook+1.207
wagon+1.204
 Lith+1.090
 Wem+1.087
 NETWORK+1.071
Neg logit contributions
usra-1.079
matched-1.021
 honors-0.990
 Armen-0.988
 ovarian-0.917
Token whose
Token ID3025
Feature activation+1.27e-01

Pos logit contributions
acebook+1.046
wagon+1.023
 Wem+0.919
 NETWORK+0.910
 Lith+0.906
Neg logit contributions
usra-1.144
matched-1.099
 Armen-1.069
 honors-1.068
 ovarian-1.001
Token son
Token ID3367
Feature activation+7.89e-01

Pos logit contributions
acebook+0.440
wagon+0.431
 Wem+0.389
 NETWORK+0.387
 Lith+0.383
Neg logit contributions
usra-0.393
matched-0.376
 honors-0.367
 Armen-0.365
 ovarian-0.340
Token Joshua
Token ID20700
Feature activation+4.15e-01

Pos logit contributions
acebook+2.620
wagon+2.577
 Wem+2.366
 Lith+2.331
 NETWORK+2.312
Neg logit contributions
usra-2.489
matched-2.374
 Armen-2.284
 honors-2.275
 ovarian-2.157
Token tell
Token ID1560
Feature activation-3.00e-01

Pos logit contributions
acebook+0.380
wagon+0.375
 Wem+0.337
 NETWORK+0.335
 Lith+0.334
Neg logit contributions
usra-0.364
matched-0.349
 honors-0.337
 Armen-0.336
��-0.315
Token me
Token ID502
Feature activation+2.09e-01

Pos logit contributions
usra+0.979
matched+0.938
 Armen+0.917
 honors+0.913
 ovarian+0.853
Neg logit contributions
acebook-0.985
wagon-0.963
 Wem-0.868
 NETWORK-0.861
 Lith-0.854
Token to
Token ID284
Feature activation+2.39e-01

Pos logit contributions
acebook+0.673
wagon+0.662
 Wem+0.598
 NETWORK+0.592
 Lith+0.591
Neg logit contributions
usra-0.687
matched-0.659
 honors-0.638
 Armen-0.637
��-0.599
Token get
Token ID651
Feature activation+1.90e-01

Pos logit contributions
acebook+0.742
wagon+0.736
 Wem+0.658
 NETWORK+0.655
 Lith+0.652
Neg logit contributions
usra-0.809
matched-0.781
 Armen-0.751
 honors-0.749
��-0.716
Token out
Token ID503
Feature activation+4.86e-01

Pos logit contributions
acebook+0.644
wagon+0.632
 Wem+0.573
 NETWORK+0.567
 Lith+0.566
Neg logit contributions
usra-0.594
matched-0.568
 Armen-0.550
 honors-0.550
 ovarian-0.512
Token of
Token ID286
Feature activation+1.15e+00

Pos logit contributions
wagon+1.666
acebook+1.659
 Wem+1.495
 Lith+1.484
 NETWORK+1.476
Neg logit contributions
usra-1.479
matched-1.374
 Armen-1.358
 honors-1.354
��-1.272
Token here
Token ID994
Feature activation+8.08e-01

Pos logit contributions
acebook+3.318
wagon+3.304
 Lith+2.990
 Wem+2.988
 NETWORK+2.919
Neg logit contributions
usra-3.997
matched-3.852
 honors-3.731
 Armen-3.723
��-3.607
Token.
Token ID13
Feature activation+1.73e-02

Pos logit contributions
acebook+2.665
wagon+2.662
 Wem+2.368
 NETWORK+2.367
 Lith+2.355
Neg logit contributions
usra-2.563
matched-2.429
 Armen-2.361
 honors-2.351
 ovarian-2.209
Token They
Token ID1119
Feature activation+1.06e-01

Pos logit contributions
acebook+0.064
wagon+0.063
 Wem+0.058
 NETWORK+0.057
 Lith+0.057
Neg logit contributions
usra-0.049
matched-0.046
 honors-0.045
 Armen-0.045
 ovarian-0.041
Token just
Token ID655
Feature activation+2.81e-02

Pos logit contributions
acebook+0.381
wagon+0.375
 Wem+0.341
 NETWORK+0.338
 Lith+0.336
Neg logit contributions
usra-0.310
matched-0.296
 Armen-0.287
 honors-0.287
 ovarian-0.266
Token sit
Token ID1650
Feature activation+1.09e-01

Pos logit contributions
acebook+0.095
wagon+0.093
 Wem+0.084
 NETWORK+0.083
 Lith+0.083
Neg logit contributions
usra-0.089
matched-0.085
 honors-0.082
 Armen-0.082
 ovarian-0.077
Tokenild
Token ID688
Feature activation+2.94e-01

Pos logit contributions
acebook+0.449
wagon+0.437
 Wem+0.404
 NETWORK+0.403
 Lith+0.402
Neg logit contributions
usra-0.255
matched-0.238
 honors-0.235
 Armen-0.234
��-0.212
Tokenon
Token ID261
Feature activation+2.82e-01

Pos logit contributions
acebook+1.106
wagon+1.083
 Wem+0.993
 NETWORK+0.985
 Lith+0.979
Neg logit contributions
usra-0.818
matched-0.780
 honors-0.754
 Armen-0.753
 ovarian-0.694
Tokenan
Token ID272
Feature activation+3.41e-01

Pos logit contributions
acebook+0.933
wagon+0.906
 Wem+0.822
 NETWORK+0.813
 Lith+0.802
Neg logit contributions
usra-0.919
matched-0.883
 Armen-0.858
 honors-0.855
 ovarian-0.801
Token for
Token ID329
Feature activation+1.52e-01

Pos logit contributions
acebook+1.116
wagon+1.090
 Wem+0.988
 NETWORK+0.986
 Lith+0.977
Neg logit contributions
usra-1.108
matched-1.057
 honors-1.029
 Armen-1.026
 ovarian-0.960
Token counselling
Token ID47586
Feature activation+4.26e-02

Pos logit contributions
acebook+0.521
wagon+0.511
 Wem+0.464
 NETWORK+0.460
 Lith+0.458
Neg logit contributions
usra-0.469
matched-0.449
 Armen-0.436
 honors-0.436
 ovarian-0.405
Token toll
Token ID13592
Feature activation+1.15e+00

Pos logit contributions
acebook+0.147
wagon+0.144
 Wem+0.131
 NETWORK+0.130
 Lith+0.129
Neg logit contributions
usra-0.131
matched-0.126
 Armen-0.122
 honors-0.122
 ovarian-0.113
Token free
Token ID1479
Feature activation+3.17e-01

Pos logit contributions
acebook+3.556
wagon+3.484
 NETWORK+3.149
 Wem+3.148
 Lith+3.146
Neg logit contributions
usra-3.804
matched-3.621
 honors-3.560
 Armen-3.560
��-3.352
Token on
Token ID319
Feature activation+5.86e-02

Pos logit contributions
acebook+1.052
wagon+1.030
 Wem+0.931
 NETWORK+0.924
 Lith+0.920
Neg logit contributions
usra-1.019
matched-0.976
 Armen-0.949
 honors-0.948
 ovarian-0.885
Token 1800
Token ID21431
Feature activation+6.79e-02

Pos logit contributions
acebook+0.196
wagon+0.192
 Wem+0.174
 NETWORK+0.171
 Transmission+0.169
Neg logit contributions
usra-0.187
matched-0.180
 Armen-0.175
 honors-0.174
 ovarian-0.164
Token 5
Token ID642
Feature activation+4.01e-01

Pos logit contributions
acebook+0.195
wagon+0.192
 Wem+0.171
 NETWORK+0.166
 Lith+0.164
Neg logit contributions
usra-0.246
matched-0.239
 honors-0.234
 Armen-0.232
 ovarian-0.220
Token45
Token ID2231
Feature activation+3.73e-01

Pos logit contributions
acebook+1.542
wagon+1.514
 Wem+1.388
 NETWORK+1.376
 Lith+1.370
Neg logit contributions
usra-1.079
matched-1.027
 Armen-0.991
 honors-0.990
 ovarian-0.910
Token
Token ID198
Feature activation-3.40e-02

Pos logit contributions
usra+0.080
matched+0.077
 Armen+0.074
 honors+0.074
 ovarian+0.069
Neg logit contributions
acebook-0.105
wagon-0.103
 Wem-0.094
 NETWORK-0.094
 Lith-0.093
TokenMeanwhile
Token ID10294
Feature activation-3.46e-01

Pos logit contributions
usra+0.102
matched+0.097
 Armen+0.094
 honors+0.094
 ovarian+0.087
Neg logit contributions
acebook-0.120
wagon-0.118
 Wem-0.107
 NETWORK-0.107
 Lith-0.106
Token,
Token ID11
Feature activation-2.85e-01

Pos logit contributions
usra+1.026
matched+0.978
 Armen+0.946
 honors+0.944
 ovarian+0.872
Neg logit contributions
acebook-1.242
wagon-1.215
 Wem-1.106
 NETWORK-1.100
 Lith-1.100
Token the
Token ID262
Feature activation+3.51e-02

Pos logit contributions
usra+0.930
matched+0.891
 honors+0.870
 Armen+0.869
 ovarian+0.815
Neg logit contributions
acebook-0.931
wagon-0.912
 Wem-0.820
 NETWORK-0.812
 Lith-0.804
Token shutdown
Token ID18325
Feature activation+4.34e-01

Pos logit contributions
acebook+0.118
wagon+0.115
 Wem+0.105
 NETWORK+0.104
 Lith+0.103
Neg logit contributions
usra-0.111
matched-0.107
 Armen-0.104
 honors-0.104
 ovarian-0.097
Token forced
Token ID4137
Feature activation+1.14e+00

Pos logit contributions
acebook+1.506
wagon+1.485
 Wem+1.347
 NETWORK+1.336
 Lith+1.335
Neg logit contributions
usra-1.314
matched-1.257
 Armen-1.215
 honors-1.211
��-1.129
Token the
Token ID262
Feature activation+2.16e-01

Pos logit contributions
acebook+3.576
wagon+3.480
 Lith+3.219
 Wem+3.193
 Transmission+3.172
Neg logit contributions
usra-3.748
matched-3.626
 Armen-3.457
 honors-3.452
��-3.282
Token Centers
Token ID22223
Feature activation+2.76e-01

Pos logit contributions
acebook+0.731
wagon+0.716
 Wem+0.650
 NETWORK+0.645
 Lith+0.643
Neg logit contributions
usra-0.675
matched-0.647
 honors-0.626
 Armen-0.626
 ovarian-0.583
Token for
Token ID329
Feature activation-4.65e-02

Pos logit contributions
acebook+0.926
wagon+0.907
 Lith+0.815
 Transmission+0.814
 NETWORK+0.814
Neg logit contributions
usra-0.878
matched-0.839
 honors-0.811
 Armen-0.802
��-0.752
Token Disease
Token ID17344
Feature activation-1.73e-01

Pos logit contributions
usra+0.116
matched+0.109
 honors+0.105
 Armen+0.105
 ovarian+0.096
Neg logit contributions
acebook-0.188
wagon-0.185
 Wem-0.170
 NETWORK-0.169
 Lith-0.169
Token Control
Token ID6779
Feature activation-4.30e-01

Pos logit contributions
usra+0.633
matched+0.611
 Armen+0.600
 honors+0.599
 ovarian+0.564
Neg logit contributions
acebook-0.498
wagon-0.481
 Wem-0.427
 NETWORK-0.419
 Lith-0.416
Token="
Token ID2625
Feature activation+2.76e-01

Pos logit contributions
usra+0.676
matched+0.651
 honors+0.628
 Armen+0.626
 ovarian+0.584
Neg logit contributions
acebook-0.779
wagon-0.762
 Wem-0.689
 NETWORK-0.683
 Lith-0.681
TokenPhone
Token ID6132
Feature activation+2.40e-01

Pos logit contributions
acebook+0.957
wagon+0.940
 Wem+0.852
 NETWORK+0.845
 Lith+0.841
Neg logit contributions
usra-0.844
matched-0.805
 Armen-0.784
 honors-0.783
 ovarian-0.728
TokenList
Token ID8053
Feature activation+1.85e-02

Pos logit contributions
acebook+0.830
wagon+0.814
 Wem+0.738
 NETWORK+0.732
 Lith+0.729
Neg logit contributions
usra-0.739
matched-0.704
 Armen-0.685
 honors-0.685
 ovarian-0.637
TokenCtrl
Token ID40069
Feature activation+1.47e-01

Pos logit contributions
acebook+0.062
wagon+0.060
 Wem+0.055
 NETWORK+0.054
 Lith+0.054
Neg logit contributions
usra-0.059
matched-0.057
 honors-0.055
 Armen-0.055
 ovarian-0.051
Token">
Token ID5320
Feature activation-1.20e-01

Pos logit contributions
acebook+0.518
wagon+0.508
 Wem+0.463
 NETWORK+0.459
 Lith+0.458
Neg logit contributions
usra-0.443
matched-0.422
 Armen-0.410
 honors-0.410
 ovarian-0.380
Token <
Token ID1279
Feature activation+1.14e+00

Pos logit contributions
usra+0.387
matched+0.372
 Armen+0.361
 honors+0.360
 ovarian+0.337
Neg logit contributions
acebook-0.393
wagon-0.386
 Wem-0.349
 NETWORK-0.344
 Lith-0.343
Tokenul
Token ID377
Feature activation-3.34e-01

Pos logit contributions
acebook+4.132
wagon+4.039
 NETWORK+3.618
 Transmission+3.610
 Wem+3.608
Neg logit contributions
usra-3.233
 Armen-3.022
matched-3.005
 honors-3.005
 ovarian-2.796
Token>
Token ID29
Feature activation+3.15e-01

Pos logit contributions
usra+0.882
matched+0.837
 honors+0.808
 Armen+0.807
 ovarian+0.741
Neg logit contributions
acebook-1.299
wagon-1.277
 Wem-1.172
 NETWORK-1.162
 Lith-1.158
Token <
Token ID1279
Feature activation+1.09e+00

Pos logit contributions
acebook+0.997
wagon+0.972
 Wem+0.874
 NETWORK+0.869
 Lith+0.866
Neg logit contributions
usra-1.058
matched-1.013
 honors-0.990
 Armen-0.989
 ovarian-0.926
Tokenli
Token ID4528
Feature activation-3.09e-03

Pos logit contributions
acebook+3.721
wagon+3.641
 Wem+3.258
 NETWORK+3.253
 Lith+3.244
Neg logit contributions
usra-3.312
matched-3.109
 Armen-3.108
 honors-3.098
 ovarian-2.892
Token ng
Token ID23370
Feature activation+8.25e-02

Pos logit contributions
usra+0.008
matched+0.008
 Armen+0.008
 honors+0.008
 ovarian+0.007
Neg logit contributions
acebook-0.012
wagon-0.011
 Wem-0.011
 NETWORK-0.010
 Lith-0.010
Token photo
Token ID4590
Feature activation-3.35e-01

Pos logit contributions
acebook+0.058
wagon+0.057
 Wem+0.051
 NETWORK+0.050
 Lith+0.050
Neg logit contributions
usra-0.062
matched-0.060
 honors-0.058
 Armen-0.058
 ovarian-0.055
Token posted
Token ID4481
Feature activation-2.62e-01

Pos logit contributions
usra+1.369
matched+1.326
 honors+1.298
 Armen+1.295
 ovarian+1.229
Neg logit contributions
acebook-0.819
wagon-0.797
 Wem-0.691
 NETWORK-0.679
 Lith-0.673
Token by
Token ID416
Feature activation+2.78e-01

Pos logit contributions
usra+0.867
matched+0.835
 honors+0.818
 Armen+0.814
 ovarian+0.761
Neg logit contributions
acebook-0.850
wagon-0.828
 Wem-0.743
 NETWORK-0.732
 Lith-0.726
Token Von
Token ID26985
Feature activation+2.20e-01

Pos logit contributions
acebook+0.942
wagon+0.924
 Wem+0.844
 Lith+0.836
 NETWORK+0.834
Neg logit contributions
usra-0.869
matched-0.834
 honors-0.800
 Armen-0.795
 ovarian-0.748
Token Miller
Token ID7920
Feature activation+3.08e-01

Pos logit contributions
acebook+0.790
wagon+0.780
 Wem+0.710
 Lith+0.703
 NETWORK+0.703
Neg logit contributions
usra-0.645
matched-0.616
 honors-0.596
 Armen-0.594
 ovarian-0.554
Token (@
Token ID4275
Feature activation+1.14e+00

Pos logit contributions
acebook+0.882
wagon+0.871
 Wem+0.774
 NETWORK+0.766
 Lith+0.765
Neg logit contributions
usra-1.127
matched-1.083
 honors-1.051
 Armen-1.051
 ovarian-0.992
Tokenvon
Token ID26982
Feature activation+9.05e-02

Pos logit contributions
wagon+4.122
acebook+4.051
 Wem+3.585
 Lith+3.570
 NETWORK+3.561
Neg logit contributions
usra-3.221
matched-3.058
 Armen-3.041
 honors-3.010
 ovarian-2.807
Tokenm
Token ID76
Feature activation-1.21e-01

Pos logit contributions
acebook+0.299
wagon+0.294
 Wem+0.264
 NETWORK+0.261
 Lith+0.260
Neg logit contributions
usra-0.292
matched-0.279
 Armen-0.273
 honors-0.272
 ovarian-0.254
Tokeniller
Token ID4665
Feature activation+4.14e-01

Pos logit contributions
usra+0.323
matched+0.308
 honors+0.297
 Armen+0.294
 ovarian+0.270
Neg logit contributions
acebook-0.469
wagon-0.458
 Wem-0.425
 NETWORK-0.421
 Lith-0.419
Token)
Token ID8
Feature activation+2.28e-01

Pos logit contributions
acebook+1.406
wagon+1.392
 Wem+1.240
 NETWORK+1.237
 Lith+1.233
Neg logit contributions
usra-1.284
matched-1.226
 Armen-1.198
 honors-1.194
 ovarian-1.115
Token on
Token ID319
Feature activation+2.30e-01

Pos logit contributions
acebook+0.755
wagon+0.741
 Wem+0.672
 NETWORK+0.668
 Lith+0.666
Neg logit contributions
usra-0.729
matched-0.695
 Armen-0.674
 honors-0.674
 ovarian-0.630
Token in
Token ID287
Feature activation-2.47e-02

Pos logit contributions
acebook+0.993
wagon+0.982
 Wem+0.895
 NETWORK+0.887
 Lith+0.885
Neg logit contributions
usra-0.853
matched-0.808
 Armen-0.785
 honors-0.782
��-0.730
Token puberty
Token ID35149
Feature activation+2.07e-01

Pos logit contributions
usra+0.081
matched+0.078
 honors+0.076
 Armen+0.076
 ovarian+0.071
Neg logit contributions
acebook-0.081
wagon-0.079
 Wem-0.071
 NETWORK-0.070
 Lith-0.070
Token and
Token ID290
Feature activation-1.91e-01

Pos logit contributions
acebook+0.719
wagon+0.709
 Wem+0.644
 NETWORK+0.639
 Lith+0.638
Neg logit contributions
usra-0.626
matched-0.593
 Armen-0.578
 honors-0.575
 ovarian-0.536
Token a
Token ID257
Feature activation-5.64e-02

Pos logit contributions
usra+0.606
matched+0.581
 honors+0.565
 Armen+0.565
 ovarian+0.527
Neg logit contributions
acebook-0.638
wagon-0.625
 Wem-0.565
 NETWORK-0.560
 Lith-0.557
Token little
Token ID1310
Feature activation+1.22e-01

Pos logit contributions
usra+0.170
matched+0.163
 honors+0.158
 Armen+0.157
 ovarian+0.146
Neg logit contributions
acebook-0.200
wagon-0.195
 Wem-0.177
 NETWORK-0.176
 Lith-0.174
Token too
Token ID1165
Feature activation+1.14e+00

Pos logit contributions
acebook+0.426
wagon+0.417
 Wem+0.379
 NETWORK+0.376
 Lith+0.374
Neg logit contributions
usra-0.371
matched-0.354
 honors-0.344
 Armen-0.344
 ovarian-0.319
Token curious
Token ID11040
Feature activation-2.09e-01

Pos logit contributions
wagon+3.992
acebook+3.981
 Wem+3.640
 Lith+3.629
 NETWORK+3.610
Neg logit contributions
usra-3.335
matched-3.104
 Armen-3.026
 honors-2.981
��-2.831
Token about
Token ID546
Feature activation+4.83e-02

Pos logit contributions
usra+0.638
matched+0.614
 honors+0.596
 Armen+0.594
 ovarian+0.554
Neg logit contributions
acebook-0.732
wagon-0.710
 Wem-0.647
 NETWORK-0.643
 Lith-0.638
Token girls
Token ID4813
Feature activation-2.28e-02

Pos logit contributions
acebook+0.164
wagon+0.160
 Wem+0.146
 NETWORK+0.144
 Lith+0.144
Neg logit contributions
usra-0.152
matched-0.145
 Armen-0.141
 honors-0.141
 ovarian-0.131
Token and
Token ID290
Feature activation+3.13e-02

Pos logit contributions
usra+0.071
matched+0.067
 Armen+0.065
 honors+0.065
 ovarian+0.061
Neg logit contributions
acebook-0.078
wagon-0.077
 Wem-0.070
 NETWORK-0.069
 Lith-0.069
Token that
Token ID326
Feature activation+1.97e-01

Pos logit contributions
acebook+0.108
wagon+0.105
 Wem+0.096
 NETWORK+0.095
 Lith+0.095
Neg logit contributions
usra-0.097
matched-0.092
 Armen-0.089
 honors-0.089
��-0.083
Token previously
Token ID4271
Feature activation-1.19e-01

Pos logit contributions
usra+0.323
matched+0.312
 honors+0.305
 Armen+0.303
 ovarian+0.285
Neg logit contributions
acebook-0.289
wagon-0.282
 Wem-0.251
 NETWORK-0.250
 Lith-0.247
Token available
Token ID1695
Feature activation-2.23e-01

Pos logit contributions
usra+0.416
matched+0.402
 honors+0.392
 Armen+0.391
 ovarian+0.367
Neg logit contributions
acebook-0.361
wagon-0.351
 Wem-0.314
 NETWORK-0.311
 Lith-0.308
Token on
Token ID319
Feature activation-1.05e-01

Pos logit contributions
usra+0.673
matched+0.642
 Armen+0.623
 honors+0.623
 ovarian+0.578
Neg logit contributions
acebook-0.787
wagon-0.772
 Wem-0.702
 NETWORK-0.696
 Lith-0.693
Token a
Token ID257
Feature activation-1.53e-01

Pos logit contributions
usra+0.342
matched+0.328
 Armen+0.319
 honors+0.319
 ovarian+0.298
Neg logit contributions
acebook-0.342
wagon-0.334
 Wem-0.302
 NETWORK-0.299
 Lith-0.297
Token 1989
Token ID11104
Feature activation+1.47e-01

Pos logit contributions
usra+0.497
matched+0.477
 Armen+0.464
 honors+0.463
 ovarian+0.433
Neg logit contributions
acebook-0.500
wagon-0.489
 Wem-0.440
 NETWORK-0.437
 Lith-0.433
Token Byr
Token ID24437
Feature activation+1.14e+00

Pos logit contributions
acebook+0.487
wagon+0.477
 Wem+0.432
 NETWORK+0.427
 Lith+0.426
Neg logit contributions
usra-0.476
matched-0.456
 Armen-0.442
 honors-0.442
 ovarian-0.413
Tokends
Token ID9310
Feature activation-2.93e-03

Pos logit contributions
wagon+2.590
acebook+2.571
 Wem+2.172
 Lith+2.165
 NETWORK+2.130
Neg logit contributions
usra-4.664
matched-4.571
 Armen-4.500
 honors-4.417
��-4.342
Token tribute
Token ID17547
Feature activation-7.53e-01

Pos logit contributions
usra+0.010
matched+0.010
 Armen+0.009
 honors+0.009
 ovarian+0.009
Neg logit contributions
acebook-0.009
wagon-0.009
 Wem-0.008
 NETWORK-0.008
 Lith-0.008
Token album
Token ID5062
Feature activation-3.93e-01

Pos logit contributions
usra+2.154
matched+2.091
 honors+2.073
 Armen+2.035
 ovarian+1.902
Neg logit contributions
acebook-2.705
wagon-2.626
 Wem-2.394
 NETWORK-2.370
 Lith-2.341
Token.
Token ID13
Feature activation+6.29e-02

Pos logit contributions
usra+1.225
matched+1.183
 honors+1.151
 Armen+1.148
 ovarian+1.066
Neg logit contributions
acebook-1.338
wagon-1.303
 Wem-1.181
 NETWORK-1.169
 Lith-1.158
Token
Token ID198
Feature activation+1.42e-01

Pos logit contributions
acebook+0.212
wagon+0.207
 Wem+0.187
 NETWORK+0.185
 Lith+0.184
Neg logit contributions
usra-0.199
matched-0.191
 Armen-0.186
 honors-0.185
 ovarian-0.172
Token Im
Token ID1846
Feature activation-7.23e-03

Pos logit contributions
acebook+0.039
wagon+0.038
 Wem+0.034
 NETWORK+0.034
 Lith+0.034
Neg logit contributions
usra-0.037
matched-0.035
 Armen-0.034
 honors-0.034
 ovarian-0.032
Tokenmore
Token ID3549
Feature activation-6.98e-02

Pos logit contributions
usra+0.023
matched+0.022
 honors+0.021
 Armen+0.021
 ovarian+0.020
Neg logit contributions
acebook-0.024
wagon-0.024
 Wem-0.022
 NETWORK-0.021
 Lith-0.021
Tokenn
Token ID77
Feature activation-1.87e-01

Pos logit contributions
usra+0.216
matched+0.206
 honors+0.200
 Armen+0.200
 ovarian+0.186
Neg logit contributions
acebook-0.240
wagon-0.235
 Wem-0.213
 NETWORK-0.212
 Lith-0.211
Token are
Token ID389
Feature activation-3.48e-01

Pos logit contributions
usra+0.602
matched+0.576
 honors+0.560
 Armen+0.560
 ovarian+0.522
Neg logit contributions
acebook-0.623
wagon-0.609
 Wem-0.551
 NETWORK-0.547
 Lith-0.543
Token made
Token ID925
Feature activation-2.53e-01

Pos logit contributions
usra+1.123
matched+1.080
 Armen+1.051
 honors+1.050
 ovarian+0.979
Neg logit contributions
acebook-1.152
wagon-1.122
 Wem-1.014
 NETWORK-1.006
 Lith-0.995
Token up
Token ID510
Feature activation-1.52e+00

Pos logit contributions
usra+0.891
matched+0.855
 honors+0.833
 Armen+0.833
 ovarian+0.784
Neg logit contributions
acebook-0.759
wagon-0.744
 Wem-0.665
 NETWORK-0.659
 Lith-0.656
Token of
Token ID286
Feature activation-2.75e-01

Pos logit contributions
usra+4.428
matched+4.237
 Armen+4.119
 honors+4.118
 ovarian+3.812
Neg logit contributions
acebook-5.438
wagon-5.310
 Wem-4.860
 NETWORK-4.812
 Lith-4.777
Token a
Token ID257
Feature activation-1.64e-01

Pos logit contributions
usra+0.872
matched+0.836
 Armen+0.814
 honors+0.813
 ovarian+0.758
Neg logit contributions
acebook-0.923
wagon-0.902
 Wem-0.816
 NETWORK-0.809
 Lith-0.802
Token mot
Token ID2369
Feature activation-2.82e-01

Pos logit contributions
usra+0.515
matched+0.493
 honors+0.478
 Armen+0.478
 ovarian+0.446
Neg logit contributions
acebook-0.554
wagon-0.542
 Wem-0.491
 NETWORK-0.487
 Lith-0.485
Tokenley
Token ID1636
Feature activation-3.54e-02

Pos logit contributions
usra+0.833
matched+0.797
 honors+0.770
 Armen+0.770
 ovarian+0.713
Neg logit contributions
acebook-1.011
wagon-0.989
 Wem-0.904
 NETWORK-0.896
 Lith-0.892
Token crew
Token ID5462
Feature activation+6.66e-02

Pos logit contributions
usra+0.117
matched+0.112
 Armen+0.109
 honors+0.109
 ovarian+0.102
Neg logit contributions
acebook-0.113
wagon-0.112
 Wem-0.101
 NETWORK-0.100
 Lith-0.099
Token clothes
Token ID8242
Feature activation-1.49e-01

Pos logit contributions
usra+0.109
matched+0.104
 Armen+0.101
 honors+0.101
 ovarian+0.094
Neg logit contributions
acebook-0.113
wagon-0.111
 Wem-0.100
 NETWORK-0.099
 Lith-0.099
Token,
Token ID11
Feature activation-6.40e-03

Pos logit contributions
usra+0.462
matched+0.441
 Armen+0.428
 honors+0.427
 ovarian+0.398
Neg logit contributions
acebook-0.513
wagon-0.503
 Wem-0.457
 NETWORK-0.453
 Lith-0.451
Token no
Token ID645
Feature activation-1.46e-01

Pos logit contributions
usra+0.021
matched+0.020
 Armen+0.019
 honors+0.019
 ovarian+0.018
Neg logit contributions
acebook-0.021
wagon-0.021
 Wem-0.019
 NETWORK-0.019
 Lith-0.018
Token make
Token ID787
Feature activation+8.50e-02

Pos logit contributions
usra+0.433
matched+0.415
 honors+0.406
 Armen+0.403
 ovarian+0.378
Neg logit contributions
acebook-0.520
wagon-0.513
 Wem-0.464
 NETWORK-0.460
 Lith-0.457
Token-
Token ID12
Feature activation-1.90e-01

Pos logit contributions
acebook+0.293
wagon+0.287
 Wem+0.261
 NETWORK+0.259
 Lith+0.257
Neg logit contributions
usra-0.263
matched-0.250
 Armen-0.243
 honors-0.243
 ovarian-0.226
Tokenup
Token ID929
Feature activation-1.49e+00

Pos logit contributions
usra+0.570
matched+0.550
 honors+0.530
 Armen+0.528
 ovarian+0.490
Neg logit contributions
acebook-0.673
wagon-0.658
 Wem-0.602
 NETWORK-0.596
 Lith-0.594
Token and
Token ID290
Feature activation-4.59e-01

Pos logit contributions
usra+4.199
matched+4.076
 honors+4.064
 Armen+3.956
 ovarian+3.676
Neg logit contributions
acebook-5.414
wagon-5.309
 Wem-4.858
 NETWORK-4.774
 Transmission-4.742
Token pulled
Token ID5954
Feature activation-3.33e-02

Pos logit contributions
usra+1.472
matched+1.415
 honors+1.392
 Armen+1.384
 ovarian+1.302
Neg logit contributions
acebook-1.521
wagon-1.491
 Wem-1.336
 NETWORK-1.329
 Lith-1.311
Token a
Token ID257
Feature activation-4.07e-01

Pos logit contributions
usra+0.103
matched+0.099
 Armen+0.096
 honors+0.096
 ovarian+0.089
Neg logit contributions
acebook-0.114
wagon-0.112
 Wem-0.101
 NETWORK-0.101
 Lith-0.100
Token hood
Token ID14263
Feature activation-3.75e-02

Pos logit contributions
usra+1.244
matched+1.197
 honors+1.162
 Armen+1.162
 ovarian+1.087
Neg logit contributions
acebook-1.413
wagon-1.385
 Wem-1.248
 NETWORK-1.242
 Lith-1.227
Tokeny
Token ID88
Feature activation-1.64e-01

Pos logit contributions
usra+0.113
matched+0.108
 honors+0.105
 Armen+0.104
 ovarian+0.097
Neg logit contributions
acebook-0.133
wagon-0.129
 Wem-0.118
 NETWORK-0.117
 Lith-0.117
Token
Token ID198
Feature activation-1.36e-01

Pos logit contributions
usra+1.125
matched+1.088
 Armen+1.051
 honors+1.037
 ovarian+0.947
Neg logit contributions
acebook-1.719
wagon-1.647
 Wem-1.508
 NETWORK-1.490
 Lith-1.470
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
usra+0.381
matched+0.365
 honors+0.352
 Armen+0.352
 ovarian+0.324
Neg logit contributions
acebook-0.511
wagon-0.498
 Wem-0.456
 NETWORK-0.452
 Lith-0.449
Token"
Token ID1
Feature activation-5.38e-01

Pos logit contributions
usra+0.319
matched+0.304
 Armen+0.293
 honors+0.293
 ovarian+0.270
Neg logit contributions
acebook-0.449
wagon-0.441
 Wem-0.405
 NETWORK-0.401
 Lith-0.400
TokenUnder
Token ID9203
Feature activation-2.92e-01

Pos logit contributions
usra+1.500
matched+1.461
 Armen+1.403
 honors+1.384
��+1.272
Neg logit contributions
acebook-2.022
wagon-1.924
 Wem-1.777
 NETWORK-1.767
 Lith-1.730
Tokenground
Token ID2833
Feature activation+1.47e-01

Pos logit contributions
usra+0.935
matched+0.899
 honors+0.870
 Armen+0.867
 ovarian+0.811
Neg logit contributions
acebook-0.973
wagon-0.940
 Wem-0.857
 NETWORK-0.847
 Lith-0.842
Token
Token ID1399
Feature activation-1.49e+00

Pos logit contributions
acebook+0.558
wagon+0.549
 Wem+0.502
 NETWORK+0.499
 Lith+0.497
Neg logit contributions
usra-0.404
matched-0.384
 Armen-0.371
 honors-0.371
 ovarian-0.342
Token is
Token ID318
Feature activation-3.02e-01

Pos logit contributions
usra+4.290
matched+4.101
 Armen+4.099
 honors+4.012
 ovarian+3.691
Neg logit contributions
acebook-5.173
wagon-4.934
 Wem-4.492
 NETWORK-4.486
 Lith-4.330
Token it
Token ID340
Feature activation+6.95e-02

Pos logit contributions
usra+1.014
matched+0.973
 Armen+0.950
 honors+0.949
 ovarian+0.890
Neg logit contributions
acebook-0.965
wagon-0.933
 Wem-0.838
 NETWORK-0.831
 Lith-0.817
Token?
Token ID30
Feature activation-3.23e-01

Pos logit contributions
acebook+0.250
wagon+0.245
 Wem+0.224
 NETWORK+0.222
 Lith+0.221
Neg logit contributions
usra-0.204
matched-0.194
 honors-0.188
 Armen-0.188
 ovarian-0.174
Token We
Token ID775
Feature activation-4.45e-01

Pos logit contributions
usra+0.974
matched+0.939
 Armen+0.926
 honors+0.909
 ovarian+0.843
Neg logit contributions
acebook-1.133
wagon-1.098
 Wem-0.984
 NETWORK-0.979
 Lith-0.961
Token're
Token ID821
Feature activation-4.45e-01

Pos logit contributions
usra+1.398
matched+1.347
 Armen+1.306
 honors+1.305
 ovarian+1.217
Neg logit contributions
acebook-1.515
wagon-1.464
 Wem-1.334
 NETWORK-1.319
 Lith-1.311
Token on
Token ID319
Feature activation-3.96e-01

Pos logit contributions
usra+0.812
matched+0.780
 honors+0.761
 Armen+0.756
 ovarian+0.708
Neg logit contributions
acebook-0.927
wagon-0.904
 Wem-0.822
 NETWORK-0.816
 Lith-0.808
Token his
Token ID465
Feature activation-2.35e-01

Pos logit contributions
usra+1.372
matched+1.320
 Armen+1.286
 honors+1.284
 ovarian+1.207
Neg logit contributions
acebook-1.216
wagon-1.186
 Wem-1.062
 NETWORK-1.053
 Lith-1.046
Token chest
Token ID7721
Feature activation-5.66e-01

Pos logit contributions
usra+0.641
matched+0.610
 honors+0.590
 Armen+0.589
 ovarian+0.543
Neg logit contributions
acebook-0.894
wagon-0.876
 Wem-0.803
 NETWORK-0.797
 Lith-0.793
Token before
Token ID878
Feature activation-9.32e-01

Pos logit contributions
usra+1.612
matched+1.560
 honors+1.507
 Armen+1.491
 ovarian+1.384
Neg logit contributions
acebook-2.080
wagon-2.006
 Wem-1.852
 NETWORK-1.847
 Lith-1.823
Token she
Token ID673
Feature activation-5.85e-01

Pos logit contributions
usra+2.838
matched+2.741
 Armen+2.691
 honors+2.676
 ovarian+2.504
Neg logit contributions
acebook-3.238
wagon-3.112
 NETWORK-2.812
 Wem-2.786
 Lith-2.754
Token fell
Token ID3214
Feature activation-1.42e+00

Pos logit contributions
usra+1.776
matched+1.702
 honors+1.659
 Armen+1.653
 ovarian+1.538
Neg logit contributions
acebook-2.056
wagon-1.992
 Wem-1.811
 NETWORK-1.805
 Lith-1.786
Token to
Token ID284
Feature activation-3.93e-01

Pos logit contributions
usra+3.715
matched+3.647
 honors+3.532
 Armen+3.459
 ovarian+3.212
Neg logit contributions
acebook-5.476
wagon-5.251
 NETWORK-4.825
 Wem-4.818
 Lith-4.764
Token the
Token ID262
Feature activation-2.14e-01

Pos logit contributions
usra+1.371
matched+1.320
 honors+1.286
 Armen+1.282
 ovarian+1.209
Neg logit contributions
acebook-1.193
wagon-1.161
 Wem-1.035
 NETWORK-1.031
 Lith-1.017
Token ground
Token ID2323
Feature activation-2.37e-02

Pos logit contributions
usra+0.859
matched+0.829
 honors+0.813
 Armen+0.811
 ovarian+0.770
Neg logit contributions
acebook-0.539
wagon-0.520
 Wem-0.455
 NETWORK-0.451
 Lith-0.446
Token,
Token ID11
Feature activation-2.67e-01

Pos logit contributions
usra+0.069
matched+0.066
 Armen+0.064
 honors+0.064
 ovarian+0.059
Neg logit contributions
acebook-0.086
wagon-0.084
 Wem-0.077
 NETWORK-0.076
 Lith-0.076
Token also
Token ID635
Feature activation-1.53e-01

Pos logit contributions
usra+0.840
matched+0.804
 honors+0.781
 Armen+0.781
 ovarian+0.727
Neg logit contributions
acebook-0.902
wagon-0.882
 Wem-0.799
 NETWORK-0.793
 Lith-0.788
Token be
Token ID307
Feature activation+2.32e-01

Pos logit contributions
acebook+0.276
wagon+0.271
 Wem+0.242
 NETWORK+0.241
 Lith+0.240
Neg logit contributions
usra-0.313
matched-0.300
 Armen-0.293
 honors-0.291
��-0.275
Token found
Token ID1043
Feature activation-1.12e-01

Pos logit contributions
acebook+0.716
wagon+0.696
 Wem+0.631
 NETWORK+0.622
 Lith+0.621
Neg logit contributions
usra-0.800
matched-0.765
 Armen-0.746
 honors-0.744
 ovarian-0.697
Token at
Token ID379
Feature activation+3.83e-01

Pos logit contributions
usra+0.358
matched+0.343
 honors+0.334
 Armen+0.333
 ovarian+0.311
Neg logit contributions
acebook-0.373
wagon-0.365
 Wem-0.330
 NETWORK-0.327
 Lith-0.325
Token bit
Token ID1643
Feature activation-2.61e-01

Pos logit contributions
acebook+1.149
wagon+1.119
 Wem+1.009
 NETWORK+1.004
 Lith+1.000
Neg logit contributions
usra-1.350
matched-1.292
 honors-1.257
 Armen-1.255
 ovarian-1.181
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
usra+0.814
matched+0.783
 honors+0.754
 Armen+0.753
 ovarian+0.702
Neg logit contributions
acebook-0.890
wagon-0.868
 Wem-0.792
 NETWORK-0.784
 Lith-0.780
Tokenly
Token ID306
Feature activation-1.39e+00

Pos logit contributions
usra+0.518
matched+0.499
 honors+0.481
 Armen+0.475
 ovarian+0.443
Neg logit contributions
acebook-0.582
wagon-0.564
 Wem-0.517
 NETWORK-0.513
 Transmission-0.501
Token/
Token ID14
Feature activation+1.00e-01

Pos logit contributions
usra+3.823
matched+3.641
 honors+3.565
 Armen+3.485
zan+3.211
Neg logit contributions
acebook-5.195
wagon-5.040
 Wem-4.661
 NETWORK-4.499
 Lith-4.469
Tokenx
Token ID87
Feature activation-3.49e-01

Pos logit contributions
acebook+0.338
wagon+0.331
 Wem+0.300
 NETWORK+0.297
 Lith+0.295
Neg logit contributions
usra-0.319
matched-0.305
 honors-0.296
 Armen-0.296
 ovarian-0.276
TokenOV
Token ID8874
Feature activation-4.01e-01

Pos logit contributions
usra+1.120
matched+1.067
 honors+1.030
 Armen+1.024
zan+0.956
Neg logit contributions
acebook-1.165
wagon-1.138
 Wem-1.042
 NETWORK-1.034
 Lith-1.021
TokenT
Token ID51
Feature activation-2.21e-01

Pos logit contributions
usra+1.261
matched+1.204
 honors+1.165
 Armen+1.160
 ovarian+1.081
Neg logit contributions
acebook-1.359
wagon-1.323
 Wem-1.213
 NETWORK-1.202
 Lith-1.186
TokenUB
Token ID10526
Feature activation-4.68e-01

Pos logit contributions
usra+0.699
matched+0.669
 honors+0.647
 Armen+0.645
 ovarian+0.601
Neg logit contributions
acebook-0.748
wagon-0.728
 Wem-0.663
 NETWORK-0.657
 Lith-0.651
Token explain
Token ID4727
Feature activation-4.76e-01

Pos logit contributions
usra+0.468
matched+0.449
 honors+0.437
 Armen+0.437
 ovarian+0.409
Neg logit contributions
acebook-0.445
wagon-0.435
 Wem-0.392
 NETWORK-0.388
 Lith-0.386
Token why
Token ID1521
Feature activation-2.17e-01

Pos logit contributions
usra+1.583
matched+1.507
 Armen+1.475
 honors+1.472
 ovarian+1.376
Neg logit contributions
acebook-1.536
wagon-1.506
 Wem-1.346
 NETWORK-1.336
 Lith-1.326
Token the
Token ID262
Feature activation-7.98e-02

Pos logit contributions
usra+0.674
matched+0.646
 honors+0.626
 Armen+0.625
 ovarian+0.583
Neg logit contributions
acebook-0.740
wagon-0.725
 Wem-0.659
 NETWORK-0.653
 Lith-0.650
Token f
Token ID277
Feature activation-3.56e-01

Pos logit contributions
usra+0.240
matched+0.230
 honors+0.222
 Armen+0.222
 ovarian+0.207
Neg logit contributions
acebook-0.281
wagon-0.275
 Wem-0.250
 NETWORK-0.248
 Lith-0.247
Tokenier
Token ID959
Feature activation-6.55e-01

Pos logit contributions
usra+1.086
matched+1.029
 Armen+0.998
 honors+0.994
 ovarian+0.923
Neg logit contributions
acebook-1.243
wagon-1.219
 Wem-1.111
 NETWORK-1.107
 Lith-1.099
Tokencest
Token ID9165
Feature activation-1.31e+00

Pos logit contributions
usra+0.799
matched+0.715
 honors+0.655
 Armen+0.645
 ovarian+0.517
Neg logit contributions
acebook-3.476
wagon-3.414
 Wem-3.226
 Lith-3.206
 NETWORK-3.206
Token crackdown
Token ID22671
Feature activation+2.86e-01

Pos logit contributions
usra+4.478
matched+4.248
 Armen+4.219
 honors+4.219
 ovarian+3.955
Neg logit contributions
acebook-4.075
wagon-3.995
 Wem-3.546
 NETWORK-3.522
 Lith-3.435
Tokens
Token ID82
Feature activation-2.66e-01

Pos logit contributions
acebook+0.927
wagon+0.908
 Wem+0.820
 NETWORK+0.814
 Lith+0.813
Neg logit contributions
usra-0.932
matched-0.896
 Armen-0.864
 honors-0.864
 ovarian-0.812
Token against
Token ID1028
Feature activation-3.45e-01

Pos logit contributions
usra+0.863
matched+0.827
 Armen+0.805
 honors+0.804
 ovarian+0.751
Neg logit contributions
acebook-0.872
wagon-0.853
 Wem-0.770
 NETWORK-0.763
 Lith-0.759
Token the
Token ID262
Feature activation+4.24e-02

Pos logit contributions
usra+1.076
matched+1.024
 Armen+1.003
 honors+0.999
 ovarian+0.928
Neg logit contributions
acebook-1.186
wagon-1.161
 Wem-1.050
 NETWORK-1.041
 Lith-1.033
Token protest
Token ID5402
Feature activation+2.87e-01

Pos logit contributions
acebook+0.152
wagon+0.149
 Wem+0.135
 NETWORK+0.134
 Lith+0.133
Neg logit contributions
usra-0.126
matched-0.120
 Armen-0.117
 honors-0.116
 ovarian-0.108
Token York
Token ID1971
Feature activation-5.16e-01

Pos logit contributions
usra+0.113
matched+0.110
 honors+0.107
 Armen+0.107
 ovarian+0.099
Neg logit contributions
acebook-0.111
wagon-0.107
 Wem-0.095
 NETWORK-0.094
 Lith-0.094
Token Times
Token ID3782
Feature activation+1.85e-01

Pos logit contributions
usra+1.739
matched+1.695
 honors+1.671
 Armen+1.666
 ovarian+1.550
Neg logit contributions
acebook-1.650
wagon-1.588
 Wem-1.388
 NETWORK-1.372
 Lith-1.345
Token.
Token ID13
Feature activation-3.10e-01

Pos logit contributions
acebook+0.637
wagon+0.621
 Wem+0.563
 NETWORK+0.557
 Lith+0.552
Neg logit contributions
usra-0.576
matched-0.552
 honors-0.537
 Armen-0.536
 ovarian-0.498
Token You
Token ID921
Feature activation-1.58e-01

Pos logit contributions
usra+1.011
matched+0.984
 Armen+0.964
 honors+0.950
zan+0.883
Neg logit contributions
acebook-1.043
wagon-1.000
 Wem-0.873
 NETWORK-0.861
 Lith-0.845
Token may
Token ID743
Feature activation-4.14e-01

Pos logit contributions
usra+0.368
matched+0.347
 honors+0.335
 Armen+0.334
 ovarian+0.302
Neg logit contributions
acebook-0.664
wagon-0.651
 Wem-0.601
 NETWORK-0.597
 Lith-0.594
Token opt
Token ID2172
Feature activation-1.29e+00

Pos logit contributions
usra+1.131
matched+1.099
 honors+1.069
 Armen+1.051
 ovarian+0.965
Neg logit contributions
acebook-1.632
wagon-1.558
 Wem-1.397
 NETWORK-1.392
 Transmission-1.369
Token-
Token ID12
Feature activation-4.91e-03

Pos logit contributions
usra+3.147
matched+3.123
 honors+2.884
 Armen+2.862
 ovarian+2.668
Neg logit contributions
acebook-5.476
wagon-5.138
 Wem-4.684
 NETWORK-4.544
 Transmission-4.497
Tokenout
Token ID448
Feature activation-3.97e-01

Pos logit contributions
usra+0.015
matched+0.014
 honors+0.014
 Armen+0.014
 ovarian+0.013
Neg logit contributions
acebook-0.018
wagon-0.017
 Wem-0.015
 NETWORK-0.015
 Lith-0.015
Token at
Token ID379
Feature activation-3.93e-01

Pos logit contributions
usra+1.109
matched+1.081
 honors+1.040
 Armen+1.032
 ovarian+0.956
Neg logit contributions
acebook-1.500
wagon-1.453
 Wem-1.322
 NETWORK-1.306
 Lith-1.298
Token any
Token ID597
Feature activation-1.14e+00

Pos logit contributions
usra+0.958
matched+0.909
 honors+0.886
 Armen+0.875
 ovarian+0.800
Neg logit contributions
acebook-1.644
wagon-1.598
 Wem-1.458
 NETWORK-1.445
 Lith-1.433
Token time
Token ID640
Feature activation-4.92e-01

Pos logit contributions
usra+3.549
matched+3.433
 honors+3.345
 Armen+3.343
 ovarian+3.115
Neg logit contributions
acebook-3.949
wagon-3.852
 Wem-3.369
 NETWORK-3.335
 Lith-3.316
Token York
Token ID1971
Feature activation-4.95e-01

Pos logit contributions
usra+0.002
matched+0.002
 honors+0.002
 Armen+0.002
 ovarian+0.002
Neg logit contributions
acebook-0.002
wagon-0.002
 Wem-0.002
 NETWORK-0.002
 Lith-0.002
Token Times
Token ID3782
Feature activation+1.97e-01

Pos logit contributions
usra+1.679
matched+1.634
 honors+1.607
 Armen+1.604
 ovarian+1.495
Neg logit contributions
acebook-1.583
wagon-1.524
 Wem-1.325
 NETWORK-1.314
 Lith-1.287
Token.
Token ID13
Feature activation-3.29e-01

Pos logit contributions
acebook+0.677
wagon+0.661
 Wem+0.598
 NETWORK+0.592
 Lith+0.588
Neg logit contributions
usra-0.614
matched-0.589
 honors-0.572
 Armen-0.572
 ovarian-0.531
Token You
Token ID921
Feature activation-8.80e-02

Pos logit contributions
usra+1.071
matched+1.043
 Armen+1.021
 honors+1.007
zan+0.937
Neg logit contributions
acebook-1.107
wagon-1.064
 Wem-0.930
 NETWORK-0.916
 Lith-0.898
Token may
Token ID743
Feature activation-3.40e-01

Pos logit contributions
usra+0.208
matched+0.196
 honors+0.189
 Armen+0.189
 ovarian+0.171
Neg logit contributions
acebook-0.367
wagon-0.361
 Wem-0.333
 NETWORK-0.331
 Lith-0.329
Token opt
Token ID2172
Feature activation-1.28e+00

Pos logit contributions
usra+0.934
matched+0.909
 honors+0.882
 Armen+0.868
 ovarian+0.798
Neg logit contributions
acebook-1.328
wagon-1.274
 Wem-1.140
 NETWORK-1.138
 Transmission-1.120
Token-
Token ID12
Feature activation+6.29e-02

Pos logit contributions
usra+3.101
matched+3.092
 honors+2.851
 Armen+2.825
 ovarian+2.639
Neg logit contributions
acebook-5.443
wagon-5.110
 Wem-4.651
 NETWORK-4.510
 Transmission-4.475
Tokenout
Token ID448
Feature activation-4.08e-01

Pos logit contributions
acebook+0.222
wagon+0.215
 Wem+0.196
 NETWORK+0.194
 Lith+0.192
Neg logit contributions
usra-0.192
matched-0.185
 honors-0.178
 Armen-0.177
 ovarian-0.165
Token at
Token ID379
Feature activation-3.91e-01

Pos logit contributions
usra+1.125
matched+1.101
 honors+1.057
 Armen+1.047
 ovarian+0.971
Neg logit contributions
acebook-1.559
wagon-1.507
 Wem-1.370
 NETWORK-1.353
 Lith-1.344
Token any
Token ID597
Feature activation-1.08e+00

Pos logit contributions
usra+0.948
matched+0.899
 honors+0.875
 Armen+0.864
 ovarian+0.793
Neg logit contributions
acebook-1.641
wagon-1.595
 Wem-1.455
 NETWORK-1.441
 Lith-1.430
Token time
Token ID640
Feature activation-5.01e-01

Pos logit contributions
usra+3.371
matched+3.264
 honors+3.183
 Armen+3.177
 ovarian+2.966
Neg logit contributions
acebook-3.725
wagon-3.638
 Wem-3.176
 NETWORK-3.154
 Lith-3.134
Token Journal
Token ID4913
Feature activation+1.73e-01

Pos logit contributions
usra+1.133
matched+1.106
 Armen+1.083
 honors+1.077
 ovarian+0.999
Neg logit contributions
acebook-1.216
wagon-1.191
 Wem-1.054
 NETWORK-1.042
 Lith-1.031
Token of
Token ID286
Feature activation-3.53e-01

Pos logit contributions
acebook+0.670
wagon+0.657
 Wem+0.603
 NETWORK+0.599
 Lith+0.596
Neg logit contributions
usra-0.458
matched-0.435
 Armen-0.420
 honors-0.420
 ovarian-0.386
Token Research
Token ID4992
Feature activation-3.43e-01

Pos logit contributions
usra+1.081
matched+1.040
 honors+1.012
 Armen+1.011
 ovarian+0.940
Neg logit contributions
acebook-1.217
wagon-1.191
 Wem-1.077
 NETWORK-1.069
 Lith-1.062
Token on
Token ID319
Feature activation-3.79e-01

Pos logit contributions
usra+1.059
matched+1.011
 Armen+0.980
 honors+0.978
 ovarian+0.911
Neg logit contributions
acebook-1.183
wagon-1.160
 Wem-1.054
 NETWORK-1.046
 Lith-1.040
Token Ad
Token ID1215
Feature activation-1.06e-01

Pos logit contributions
usra+1.150
matched+1.113
 honors+1.084
 Armen+1.081
 ovarian+1.006
Neg logit contributions
acebook-1.314
wagon-1.286
 Wem-1.161
 NETWORK-1.151
 Lith-1.142
Tokenolesc
Token ID16850
Feature activation-1.27e+00

Pos logit contributions
usra+0.319
matched+0.305
 honors+0.296
 Armen+0.296
 ovarian+0.275
Neg logit contributions
acebook-0.371
wagon-0.364
 Wem-0.331
 NETWORK-0.328
 Lith-0.327
Tokenence
Token ID594
Feature activation-3.99e-01

Pos logit contributions
usra+2.433
matched+2.252
 honors+2.218
 Armen+2.187
zan+1.930
Neg logit contributions
acebook-5.774
wagon-5.737
 Wem-5.294
 NETWORK-5.215
 Lith-5.206
Token,
Token ID11
Feature activation-4.74e-01

Pos logit contributions
usra+1.181
matched+1.120
 honors+1.082
 Armen+1.082
 ovarian+1.004
Neg logit contributions
acebook-1.438
wagon-1.409
 Wem-1.284
 NETWORK-1.283
 Lith-1.275
Token 8
Token ID807
Feature activation-3.65e-01

Pos logit contributions
usra+1.442
matched+1.408
 Armen+1.375
 honors+1.365
 ovarian+1.264
Neg logit contributions
acebook-1.664
wagon-1.612
 Wem-1.445
 NETWORK-1.415
 Lith-1.401
Token,
Token ID11
Feature activation-1.49e-01

Pos logit contributions
usra+1.087
matched+1.029
 honors+1.002
 Armen+1.000
 ovarian+0.927
Neg logit contributions
acebook-1.307
wagon-1.280
 Wem-1.166
 NETWORK-1.158
 Lith-1.156
Token 333
Token ID23460
Feature activation+2.37e-01

Pos logit contributions
usra+0.550
matched+0.533
 Armen+0.524
 honors+0.522
 ovarian+0.490
Neg logit contributions
acebook-0.426
wagon-0.414
 Wem-0.364
 NETWORK-0.357
 Lith-0.353
Token measurement
Token ID15558
Feature activation-2.06e-01

Pos logit contributions
usra+1.930
matched+1.874
 honors+1.817
 Armen+1.813
 ovarian+1.692
Neg logit contributions
acebook-2.195
wagon-2.164
 Wem-1.951
 NETWORK-1.928
 Transmission-1.912
Token was
Token ID373
Feature activation-3.44e-01

Pos logit contributions
usra+0.694
matched+0.667
 honors+0.649
 Armen+0.649
 ovarian+0.608
Neg logit contributions
acebook-0.649
wagon-0.635
 Wem-0.571
 NETWORK-0.565
 Lith-0.562
Token the
Token ID262
Feature activation-2.62e-01

Pos logit contributions
usra+1.123
matched+1.084
 honors+1.061
 Armen+1.059
 ovarian+1.003
Neg logit contributions
acebook-1.118
wagon-1.098
 Wem-0.977
 NETWORK-0.969
 Transmission-0.953
Token 24
Token ID1987
Feature activation-2.24e-01

Pos logit contributions
usra+0.871
matched+0.837
 Armen+0.817
 honors+0.817
 ovarian+0.767
Neg logit contributions
acebook-0.839
wagon-0.822
 Wem-0.735
 NETWORK-0.728
 Lith-0.721
Token-
Token ID12
Feature activation-2.65e-01

Pos logit contributions
usra+0.674
matched+0.645
 Armen+0.625
 honors+0.624
 ovarian+0.582
Neg logit contributions
acebook-0.787
wagon-0.773
 Wem-0.701
 NETWORK-0.694
 Lith-0.689
Tokenitem
Token ID9186
Feature activation-1.27e+00

Pos logit contributions
usra+0.904
matched+0.875
 honors+0.843
 Armen+0.843
 ovarian+0.792
Neg logit contributions
acebook-0.827
wagon-0.800
 Wem-0.723
 NETWORK-0.716
 Transmission-0.706
Token Hamilton
Token ID11582
Feature activation-8.87e-01

Pos logit contributions
usra+4.060
 honors+3.937
matched+3.930
 Armen+3.868
 ovarian+3.693
Neg logit contributions
acebook-4.072
wagon-4.018
 Wem-3.493
 NETWORK-3.461
 Transmission-3.376
Token Depression
Token ID22483
Feature activation-4.41e-01

Pos logit contributions
usra+2.490
matched+2.376
 Armen+2.319
 honors+2.311
 ovarian+2.137
Neg logit contributions
acebook-3.284
wagon-3.222
 Wem-2.941
 NETWORK-2.912
 Lith-2.874
Token Rating
Token ID12028
Feature activation-4.00e-01

Pos logit contributions
usra+1.205
matched+1.146
 honors+1.109
 Armen+1.108
 ovarian+1.020
Neg logit contributions
acebook-1.678
wagon-1.648
 Wem-1.509
 NETWORK-1.497
 Lith-1.489
Token Scale
Token ID21589
Feature activation-8.02e-01

Pos logit contributions
usra+0.912
matched+0.867
 honors+0.834
 Armen+0.833
 ovarian+0.749
Neg logit contributions
acebook-1.697
wagon-1.664
 Wem-1.543
 NETWORK-1.526
 Lith-1.515
Token measured
Token ID8630
Feature activation-3.66e-01

Pos logit contributions
usra+2.496
matched+2.439
 Armen+2.366
 honors+2.366
 ovarian+2.210
Neg logit contributions
acebook-2.689
wagon-2.637
 Wem-2.374
 NETWORK-2.340
 Lith-2.300
Token
Token ID198
Feature activation-2.00e-02

Pos logit contributions
usra+0.014
matched+0.013
 Armen+0.013
 honors+0.013
 ovarian+0.012
Neg logit contributions
acebook-0.018
wagon-0.017
 Wem-0.016
 NETWORK-0.016
 Lith-0.016
TokenThank
Token ID10449
Feature activation+3.66e-01

Pos logit contributions
usra+0.061
matched+0.059
 honors+0.057
 Armen+0.057
 ovarian+0.053
Neg logit contributions
acebook-0.069
wagon-0.068
 Wem-0.062
 NETWORK-0.061
 Lith-0.061
Token you
Token ID345
Feature activation+9.89e-02

Pos logit contributions
acebook+1.081
wagon+1.059
 Wem+0.949
 NETWORK+0.939
 Lith+0.933
Neg logit contributions
usra-1.303
matched-1.255
 Armen-1.218
 honors-1.216
 ovarian-1.145
Token for
Token ID329
Feature activation-4.15e-01

Pos logit contributions
acebook+0.348
wagon+0.342
 Wem+0.311
 NETWORK+0.308
 Lith+0.307
Neg logit contributions
usra-0.297
matched-0.284
 Armen-0.275
 honors-0.275
 ovarian-0.255
Token signing
Token ID8415
Feature activation-6.10e-01

Pos logit contributions
usra+1.266
matched+1.223
 Armen+1.194
 honors+1.193
 ovarian+1.107
Neg logit contributions
acebook-1.437
wagon-1.402
 Wem-1.272
 NETWORK-1.265
 Lith-1.252
Token up
Token ID510
Feature activation-1.27e+00

Pos logit contributions
usra+2.047
matched+2.012
 Armen+1.971
 honors+1.964
 ovarian+1.832
Neg logit contributions
acebook-1.956
wagon-1.880
 Wem-1.646
 NETWORK-1.645
 Transmission-1.622
Token.
Token ID13
Feature activation-5.70e-01

Pos logit contributions
usra+3.558
matched+3.426
 honors+3.378
 Armen+3.361
 ovarian+3.085
Neg logit contributions
acebook-4.555
wagon-4.537
 Wem-4.092
 NETWORK-4.068
 Lith-4.013
Token For
Token ID1114
Feature activation-6.48e-01

Pos logit contributions
usra+1.575
matched+1.503
 Armen+1.462
 honors+1.449
 ovarian+1.337
Neg logit contributions
acebook-2.148
wagon-2.112
 Wem-1.919
 NETWORK-1.907
 Lith-1.894
Token more
Token ID517
Feature activation-8.17e-01

Pos logit contributions
usra+1.508
matched+1.476
 honors+1.439
 Armen+1.422
 ovarian+1.286
Neg logit contributions
acebook-2.727
wagon-2.654
 NETWORK-2.413
 Wem-2.403
 Transmission-2.384
Token from
Token ID422
Feature activation-9.23e-02

Pos logit contributions
usra+2.037
matched+1.916
 honors+1.903
 Armen+1.862
 ovarian+1.706
Neg logit contributions
acebook-3.367
wagon-3.238
 Wem-2.980
 NETWORK-2.927
 Lith-2.914
Token The
Token ID383
Feature activation-2.68e-01

Pos logit contributions
usra+0.332
matched+0.318
 Armen+0.315
 honors+0.313
 ovarian+0.292
Neg logit contributions
acebook-0.274
wagon-0.266
 Wem-0.234
 NETWORK-0.230
 Lith-0.229
Token,
Token ID11
Feature activation-6.09e-02

Pos logit contributions
acebook+1.403
wagon+1.383
 Wem+1.255
 Lith+1.250
 NETWORK+1.242
Neg logit contributions
usra-1.263
matched-1.202
 honors-1.156
 Armen-1.154
��-1.080
Token this
Token ID428
Feature activation+1.84e-01

Pos logit contributions
usra+0.197
matched+0.189
 Armen+0.184
 honors+0.184
 ovarian+0.172
Neg logit contributions
acebook-0.200
wagon-0.196
 Wem-0.177
 NETWORK-0.175
 Lith-0.174
Token was
Token ID373
Feature activation+1.56e-01

Pos logit contributions
acebook+0.593
wagon+0.582
 Wem+0.524
 NETWORK+0.519
 Lith+0.517
Neg logit contributions
usra-0.605
matched-0.581
 Armen-0.564
 honors-0.564
 ovarian-0.527
Token completely
Token ID3190
Feature activation+1.88e-01

Pos logit contributions
acebook+0.514
wagon+0.505
 Wem+0.457
 NETWORK+0.453
 Lith+0.451
Neg logit contributions
usra-0.500
matched-0.479
 honors-0.465
 Armen-0.465
 ovarian-0.433
Token made
Token ID925
Feature activation-2.12e-01

Pos logit contributions
acebook+0.595
wagon+0.583
 Wem+0.525
 NETWORK+0.519
 Lith+0.517
Neg logit contributions
usra-0.634
matched-0.608
 honors-0.592
 Armen-0.592
 ovarian-0.553
Token up
Token ID510
Feature activation-1.27e+00

Pos logit contributions
usra+0.753
matched+0.724
 Armen+0.707
 honors+0.705
 ovarian+0.666
Neg logit contributions
acebook-0.638
wagon-0.619
 Wem-0.553
 NETWORK-0.547
 Lith-0.543
Token.
Token ID13
Feature activation-1.08e-01

Pos logit contributions
usra+3.751
matched+3.571
 honors+3.546
 Armen+3.504
 ovarian+3.304
Neg logit contributions
acebook-4.476
wagon-4.256
 Wem-3.915
 NETWORK-3.851
 Transmission-3.826
Token There
Token ID1318
Feature activation-4.54e-03

Pos logit contributions
usra+0.339
matched+0.327
 Armen+0.319
 honors+0.316
 ovarian+0.294
Neg logit contributions
acebook-0.370
wagon-0.361
 Wem-0.325
 NETWORK-0.322
 Lith-0.319
Token was
Token ID373
Feature activation-6.61e-02

Pos logit contributions
usra+0.016
matched+0.015
 honors+0.015
 Armen+0.015
 ovarian+0.014
Neg logit contributions
acebook-0.014
wagon-0.014
 Wem-0.012
 NETWORK-0.012
 Lith-0.012
Token no
Token ID645
Feature activation+3.37e-03

Pos logit contributions
usra+0.211
matched+0.202
 Armen+0.196
 honors+0.196
 ovarian+0.183
Neg logit contributions
acebook-0.221
wagon-0.216
 Wem-0.195
 NETWORK-0.193
 Lith-0.193
Token actual
Token ID4036
Feature activation+4.82e-03

Pos logit contributions
acebook+0.011
wagon+0.011
 Wem+0.010
 NETWORK+0.010
 Lith+0.010
Neg logit contributions
usra-0.011
matched-0.010
 honors-0.010
 Armen-0.010
 ovarian-0.009
Tokens
Token ID82
Feature activation+2.42e-01

Pos logit contributions
acebook+0.092
wagon+0.090
 Wem+0.082
 NETWORK+0.081
 Lith+0.081
Neg logit contributions
usra-0.087
matched-0.083
 honors-0.081
 Armen-0.081
 ovarian-0.075
Token findings
Token ID6373
Feature activation+8.43e-02

Pos logit contributions
acebook+0.811
wagon+0.794
 Wem+0.719
 NETWORK+0.717
 Lith+0.712
Neg logit contributions
usra-0.765
matched-0.733
 Armen-0.709
 honors-0.708
 ovarian-0.662
Token are
Token ID389
Feature activation-8.91e-03

Pos logit contributions
acebook+0.265
wagon+0.260
 Wem+0.234
 NETWORK+0.232
 Lith+0.231
Neg logit contributions
usra-0.285
matched-0.273
 Armen-0.266
 honors-0.265
 ovarian-0.249
Token not
Token ID407
Feature activation-9.04e-02

Pos logit contributions
usra+0.029
matched+0.028
 Armen+0.027
 honors+0.027
 ovarian+0.026
Neg logit contributions
acebook-0.029
wagon-0.028
 Wem-0.025
 NETWORK-0.025
 Lith-0.025
Token an
Token ID281
Feature activation-1.66e-01

Pos logit contributions
usra+0.281
matched+0.269
 Armen+0.262
 honors+0.261
 ovarian+0.244
Neg logit contributions
acebook-0.310
wagon-0.303
 Wem-0.275
 NETWORK-0.273
 Lith-0.271
Token exception
Token ID6631
Feature activation-1.26e+00

Pos logit contributions
usra+0.495
matched+0.473
 honors+0.458
 Armen+0.458
 ovarian+0.425
Neg logit contributions
acebook-0.586
wagon-0.575
 Wem-0.523
 NETWORK-0.519
 Lith-0.516
Token.
Token ID13
Feature activation-2.97e-01

Pos logit contributions
usra+3.588
matched+3.474
 honors+3.369
 Armen+3.362
 ovarian+3.088
Neg logit contributions
acebook-4.601
wagon-4.493
 Wem-4.115
 NETWORK-4.046
 Lith-4.017
Token In
Token ID554
Feature activation-2.62e-01

Pos logit contributions
usra+0.944
matched+0.908
 Armen+0.887
 honors+0.880
 ovarian+0.821
Neg logit contributions
acebook-0.998
wagon-0.976
 Wem-0.878
 NETWORK-0.868
 Lith-0.861
Token a
Token ID257
Feature activation-6.63e-02

Pos logit contributions
usra+0.902
matched+0.868
 honors+0.845
 Armen+0.845
 ovarian+0.793
Neg logit contributions
acebook-0.809
wagon-0.790
 Wem-0.707
 NETWORK-0.699
 Lith-0.695
Token 2014
Token ID1946
Feature activation-2.38e-01

Pos logit contributions
usra+0.212
matched+0.203
 Armen+0.197
 honors+0.197
 ovarian+0.184
Neg logit contributions
acebook-0.221
wagon-0.216
 Wem-0.197
 NETWORK-0.195
 Lith-0.194
Token article
Token ID2708
Feature activation-7.71e-01

Pos logit contributions
usra+0.734
matched+0.702
 honors+0.682
 Armen+0.682
 ovarian+0.634
Neg logit contributions
acebook-0.821
wagon-0.804
 Wem-0.729
 NETWORK-0.722
 Lith-0.719
Token York
Token ID1971
Feature activation-4.65e-01

Pos logit contributions
usra+0.057
matched+0.055
 honors+0.054
 Armen+0.054
 ovarian+0.050
Neg logit contributions
acebook-0.056
wagon-0.054
 Wem-0.048
 NETWORK-0.047
 Lith-0.047
Token Times
Token ID3782
Feature activation+2.12e-01

Pos logit contributions
usra+1.588
matched+1.539
 honors+1.516
 Armen+1.513
 ovarian+1.410
Neg logit contributions
acebook-1.476
wagon-1.422
 Wem-1.244
 NETWORK-1.231
 Lith-1.206
Token.
Token ID13
Feature activation-3.38e-01

Pos logit contributions
acebook+0.727
wagon+0.710
 Wem+0.643
 NETWORK+0.636
 Lith+0.631
Neg logit contributions
usra-0.660
matched-0.633
 honors-0.615
 Armen-0.614
 ovarian-0.571
Token You
Token ID921
Feature activation-1.02e-01

Pos logit contributions
usra+1.102
matched+1.070
 Armen+1.050
 honors+1.035
zan+0.961
Neg logit contributions
acebook-1.143
wagon-1.098
 Wem-0.957
 NETWORK-0.945
 Lith-0.925
Token may
Token ID743
Feature activation-3.42e-01

Pos logit contributions
usra+0.240
matched+0.227
 honors+0.218
 Armen+0.218
 ovarian+0.197
Neg logit contributions
acebook-0.428
wagon-0.420
 Wem-0.388
 NETWORK-0.385
 Lith-0.384
Token opt
Token ID2172
Feature activation-1.26e+00

Pos logit contributions
usra+0.937
matched+0.910
 honors+0.885
 Armen+0.872
 ovarian+0.800
Neg logit contributions
acebook-1.337
wagon-1.282
 Wem-1.149
 NETWORK-1.146
 Transmission-1.127
Token-
Token ID12
Feature activation-1.80e-02

Pos logit contributions
usra+3.077
matched+3.059
 honors+2.826
 Armen+2.808
 ovarian+2.611
Neg logit contributions
acebook-5.331
wagon-5.010
 Wem-4.562
 NETWORK-4.438
 Transmission-4.390
Tokenout
Token ID448
Feature activation-3.70e-01

Pos logit contributions
usra+0.055
matched+0.053
 honors+0.051
 Armen+0.050
 ovarian+0.047
Neg logit contributions
acebook-0.064
wagon-0.062
 Wem-0.057
 NETWORK-0.056
 Lith-0.056
Token at
Token ID379
Feature activation-3.50e-01

Pos logit contributions
usra+1.034
matched+1.007
 honors+0.970
 Armen+0.963
 ovarian+0.892
Neg logit contributions
acebook-1.395
wagon-1.352
 Wem-1.229
 NETWORK-1.216
 Lith-1.207
Token any
Token ID597
Feature activation-1.11e+00

Pos logit contributions
usra+0.858
matched+0.814
 honors+0.793
 Armen+0.784
 ovarian+0.717
Neg logit contributions
acebook-1.455
wagon-1.417
 Wem-1.292
 NETWORK-1.282
 Lith-1.271
Token time
Token ID640
Feature activation-4.87e-01

Pos logit contributions
usra+3.438
matched+3.330
 honors+3.247
 Armen+3.242
 ovarian+3.021
Neg logit contributions
acebook-3.812
wagon-3.721
 Wem-3.245
 NETWORK-3.222
 Lith-3.197
Token to
Token ID284
Feature activation+3.14e-01

Pos logit contributions
acebook+0.044
wagon+0.043
 Wem+0.039
 NETWORK+0.039
 Lith+0.039
Neg logit contributions
usra-0.039
matched-0.038
 honors-0.036
 Armen-0.036
 ovarian-0.034
Token Alex
Token ID4422
Feature activation-3.62e-01

Pos logit contributions
acebook+1.047
wagon+1.023
 Wem+0.930
 Lith+0.923
 NETWORK+0.921
Neg logit contributions
usra-0.997
matched-0.960
 honors-0.925
 Armen-0.920
��-0.858
Token Sal
Token ID4849
Feature activation-6.58e-02

Pos logit contributions
usra+1.105
matched+1.057
 Armen+1.030
 honors+1.029
 ovarian+0.957
Neg logit contributions
acebook-1.257
wagon-1.229
 Wem-1.119
 NETWORK-1.113
 Lith-1.098
Tokenmond
Token ID6327
Feature activation+2.11e-01

Pos logit contributions
usra+0.219
matched+0.212
 Armen+0.204
 honors+0.204
zan+0.191
Neg logit contributions
acebook-0.213
wagon-0.205
 NETWORK-0.187
 Wem-0.187
 Lith-0.185
Token swinging
Token ID25635
Feature activation-8.67e-02

Pos logit contributions
acebook+0.678
wagon+0.667
 Wem+0.600
 Lith+0.595
 NETWORK+0.594
Neg logit contributions
usra-0.697
matched-0.669
 Armen-0.647
 honors-0.646
��-0.604
Token butt
Token ID8530
Feature activation-1.25e+00

Pos logit contributions
usra+0.282
matched+0.270
 honors+0.263
 Armen+0.263
 ovarian+0.246
Neg logit contributions
acebook-0.284
wagon-0.278
 Wem-0.251
 NETWORK-0.249
 Lith-0.247
Token naked
Token ID12105
Feature activation-5.06e-01

Pos logit contributions
usra+3.616
matched+3.520
 honors+3.376
 Armen+3.354
 ovarian+3.171
Neg logit contributions
acebook-4.492
wagon-4.228
 Wem-4.006
 NETWORK-3.912
 Transmission-3.892
Token on
Token ID319
Feature activation-2.71e-01

Pos logit contributions
usra+1.498
matched+1.434
 honors+1.395
 Armen+1.392
 ovarian+1.296
Neg logit contributions
acebook-1.808
wagon-1.757
 Wem-1.614
 NETWORK-1.598
 Lith-1.583
Token a
Token ID257
Feature activation-3.21e-01

Pos logit contributions
usra+0.929
matched+0.891
 Armen+0.871
 honors+0.869
 ovarian+0.817
Neg logit contributions
acebook-0.842
wagon-0.825
 Wem-0.738
 NETWORK-0.731
 Lith-0.725
Token wreck
Token ID15228
Feature activation-3.55e-01

Pos logit contributions
usra+1.059
matched+1.014
 Armen+0.990
 honors+0.989
 ovarian+0.928
Neg logit contributions
acebook-1.039
wagon-1.015
 Wem-0.912
 NETWORK-0.906
 Lith-0.897
Tokening
Token ID278
Feature activation-1.26e-01

Pos logit contributions
usra+1.161
matched+1.116
 honors+1.084
 Armen+1.080
 ovarian+1.008
Neg logit contributions
acebook-1.160
wagon-1.121
 Wem-1.026
 NETWORK-1.018
 Lith-1.007
Token knew
Token ID2993
Feature activation+1.30e-02

Pos logit contributions
acebook+0.410
wagon+0.403
 Wem+0.362
 NETWORK+0.360
 Lith+0.358
Neg logit contributions
usra-0.413
matched-0.396
 honors-0.384
 Armen-0.383
 ovarian-0.359
Token that
Token ID326
Feature activation+1.02e-01

Pos logit contributions
acebook+0.041
wagon+0.040
 Wem+0.036
 NETWORK+0.035
 Lith+0.035
Neg logit contributions
usra-0.044
matched-0.043
 honors-0.042
 Armen-0.042
 ovarian-0.039
Token if
Token ID611
Feature activation+1.77e-02

Pos logit contributions
acebook+0.331
wagon+0.325
 Wem+0.293
 NETWORK+0.291
 Lith+0.290
Neg logit contributions
usra-0.333
matched-0.320
 honors-0.310
 Armen-0.309
 ovarian-0.289
Token we
Token ID356
Feature activation+2.74e-01

Pos logit contributions
acebook+0.055
wagon+0.054
 Wem+0.048
 NETWORK+0.048
 Lith+0.048
Neg logit contributions
usra-0.061
matched-0.058
 honors-0.057
 Armen-0.056
 ovarian-0.053
Token fl
Token ID781
Feature activation-1.25e-01

Pos logit contributions
acebook+0.849
wagon+0.842
 Wem+0.751
 NETWORK+0.749
 Lith+0.740
Neg logit contributions
usra-0.928
matched-0.888
 honors-0.861
 Armen-0.860
��-0.814
Tokenunk
Token ID2954
Feature activation-1.25e+00

Pos logit contributions
usra+0.387
matched+0.371
 honors+0.360
 Armen+0.360
 ovarian+0.335
Neg logit contributions
acebook-0.428
wagon-0.419
 Wem-0.380
 NETWORK-0.377
 Lith-0.375
Tokened
Token ID276
Feature activation-4.85e-01

Pos logit contributions
usra+4.369
matched+4.256
 honors+4.126
 Armen+4.098
 ovarian+3.839
Neg logit contributions
acebook-3.733
wagon-3.603
 Wem-3.253
 NETWORK-3.208
 Lith-3.196
Token out
Token ID503
Feature activation-2.57e-01

Pos logit contributions
usra+1.578
matched+1.514
 honors+1.479
 Armen+1.474
 ovarian+1.379
Neg logit contributions
acebook-1.587
wagon-1.554
 Wem-1.406
 NETWORK-1.389
 Lith-1.380
Token of
Token ID286
Feature activation+3.25e-01

Pos logit contributions
usra+0.752
matched+0.714
 Armen+0.693
 honors+0.693
 ovarian+0.642
Neg logit contributions
acebook-0.928
wagon-0.912
 Wem-0.830
 NETWORK-0.823
 Lith-0.822
Token school
Token ID1524
Feature activation+5.71e-01

Pos logit contributions
acebook+1.164
wagon+1.140
 Lith+1.039
 Wem+1.038
 NETWORK+1.032
Neg logit contributions
usra-0.948
matched-0.909
 Armen-0.872
 honors-0.858
 ovarian-0.807
Token or
Token ID393
Feature activation+3.43e-03

Pos logit contributions
acebook+1.892
wagon+1.872
 Wem+1.671
 Lith+1.668
 NETWORK+1.667
Neg logit contributions
usra-1.818
matched-1.724
 Armen-1.684
 honors-1.670
 ovarian-1.574
TokenAB
Token ID6242
Feature activation+5.52e-01

Pos logit contributions
acebook+0.209
wagon+0.204
 Wem+0.186
 NETWORK+0.184
 Lith+0.183
Neg logit contributions
usra-0.185
matched-0.177
 honors-0.172
 Armen-0.171
 ovarian-0.159
Tokenarry
Token ID6532
Feature activation+3.26e-02

Pos logit contributions
acebook+1.729
wagon+1.693
 Wem+1.518
 NETWORK+1.509
 Lith+1.502
Neg logit contributions
usra-1.872
matched-1.796
 Armen-1.747
 honors-1.743
 ovarian-1.637
Token Maryland
Token ID10769
Feature activation-3.17e-01

Pos logit contributions
acebook+0.108
wagon+0.106
 Wem+0.095
 NETWORK+0.094
 Lith+0.094
Neg logit contributions
usra-0.105
matched-0.101
 honors-0.098
 Armen-0.098
 ovarian-0.091
Token 1
Token ID352
Feature activation-2.72e-02

Pos logit contributions
usra+1.008
matched+0.968
 honors+0.945
 Armen+0.944
 ovarian+0.879
Neg logit contributions
acebook-1.058
wagon-1.033
 Wem-0.934
 NETWORK-0.919
 Lith-0.914
Token hour
Token ID1711
Feature activation+3.71e-01

Pos logit contributions
usra+0.107
matched+0.103
 honors+0.101
 Armen+0.100
 ovarian+0.095
Neg logit contributions
acebook-0.071
wagon-0.069
 Wem-0.060
 NETWORK-0.060
 Lith-0.059
Token ago
Token ID2084
Feature activation-1.25e+00

Pos logit contributions
acebook+1.242
wagon+1.221
 Wem+1.102
 NETWORK+1.092
 Lith+1.091
Neg logit contributions
usra-1.181
matched-1.129
 honors-1.095
 Armen-1.095
 ovarian-1.020
Token This
Token ID770
Feature activation-3.89e-01

Pos logit contributions
usra+3.819
matched+3.702
 Armen+3.686
 honors+3.640
 ovarian+3.361
Neg logit contributions
acebook-4.208
wagon-4.110
 Wem-3.624
 NETWORK-3.599
 Lith-3.545
Token election
Token ID3071
Feature activation-3.01e-02

Pos logit contributions
usra+1.312
matched+1.261
 honors+1.240
 Armen+1.232
 ovarian+1.154
Neg logit contributions
acebook-1.227
wagon-1.191
 Wem-1.070
 NETWORK-1.061
 Lith-1.052
Token was
Token ID373
Feature activation-2.57e-02

Pos logit contributions
usra+0.103
matched+0.100
 honors+0.097
 Armen+0.097
 ovarian+0.091
Neg logit contributions
acebook-0.093
wagon-0.091
 Wem-0.082
 NETWORK-0.081
 Lith-0.080
Token not
Token ID407
Feature activation+2.29e-02

Pos logit contributions
usra+0.084
matched+0.080
 honors+0.078
 Armen+0.078
 ovarian+0.073
Neg logit contributions
acebook-0.084
wagon-0.082
 Wem-0.074
 NETWORK-0.074
 Lith-0.073
Token about
Token ID546
Feature activation-4.23e-02

Pos logit contributions
acebook+0.072
wagon+0.070
 Wem+0.063
 NETWORK+0.062
 Lith+0.062
Neg logit contributions
usra-0.077
matched-0.075
 honors-0.073
 Armen-0.073
 ovarian-0.068
Token
Token ID198
Feature activation-2.22e-01

Pos logit contributions
usra+0.612
matched+0.587
 honors+0.566
 Armen+0.565
 ovarian+0.520
Neg logit contributions
acebook-0.833
wagon-0.810
 Wem-0.743
 NETWORK-0.736
 Lith-0.730
Token55
Token ID2816
Feature activation-3.45e-01

Pos logit contributions
usra+0.628
matched+0.605
 honors+0.582
 Armen+0.581
 ovarian+0.535
Neg logit contributions
acebook-0.827
wagon-0.804
 Wem-0.740
 NETWORK-0.732
 Lith-0.726
Token Recommend
Token ID30361
Feature activation-8.10e-01

Pos logit contributions
usra+0.880
matched+0.841
 honors+0.816
 Armen+0.812
 ovarian+0.744
Neg logit contributions
acebook-1.372
wagon-1.340
 Wem-1.232
 NETWORK-1.220
 Lith-1.210
Token
Token ID198
Feature activation-3.96e-01

Pos logit contributions
usra+2.035
matched+1.982
 honors+1.900
 Armen+1.895
 ovarian+1.710
Neg logit contributions
acebook-3.314
wagon-3.165
 Wem-2.910
 NETWORK-2.856
 Lith-2.819
Token
Token ID198
Feature activation-3.15e-01

Pos logit contributions
usra+1.071
matched+1.031
 honors+0.995
 Armen+0.991
 ovarian+0.910
Neg logit contributions
acebook-1.534
wagon-1.483
 Wem-1.363
 NETWORK-1.346
 Lith-1.332
TokenRecommend
Token ID41248
Feature activation-1.25e+00

Pos logit contributions
usra+0.869
matched+0.834
 honors+0.804
 Armen+0.800
 ovarian+0.737
Neg logit contributions
acebook-1.191
wagon-1.164
 Wem-1.073
 NETWORK-1.062
 Lith-1.055
Token Share
Token ID8734
Feature activation-5.92e-02

Pos logit contributions
usra+3.822
matched+3.806
 honors+3.687
 Armen+3.676
 ovarian+3.420
Neg logit contributions
acebook-4.157
wagon-4.065
 Wem-3.630
 NETWORK-3.520
 Lith-3.511
Token this
Token ID428
Feature activation-4.00e-01

Pos logit contributions
usra+0.194
matched+0.187
 honors+0.183
 Armen+0.182
 ovarian+0.170
Neg logit contributions
acebook-0.194
wagon-0.189
 Wem-0.170
 NETWORK-0.168
 Lith-0.166
Token comment
Token ID2912
Feature activation-1.87e-02

Pos logit contributions
usra+0.976
matched+0.920
 honors+0.910
 Armen+0.901
 ovarian+0.827
Neg logit contributions
acebook-1.658
wagon-1.615
 Wem-1.483
 NETWORK-1.471
 Transmission-1.446
Token on
Token ID319
Feature activation-2.44e-01

Pos logit contributions
usra+0.058
matched+0.055
 honors+0.054
 Armen+0.054
 ovarian+0.050
Neg logit contributions
acebook-0.065
wagon-0.063
 Wem-0.057
 NETWORK-0.057
 Lith-0.056
Token Facebook
Token ID3203
Feature activation-1.30e-01

Pos logit contributions
usra+0.699
matched+0.667
 Armen+0.660
 honors+0.652
 ovarian+0.606
Neg logit contributions
acebook-0.889
wagon-0.873
 Wem-0.789
 NETWORK-0.769
 Lith-0.766
Token-
Token ID12
Feature activation-3.29e-01

Pos logit contributions
usra+1.825
matched+1.738
 honors+1.709
 Armen+1.701
 ovarian+1.558
Neg logit contributions
acebook-2.531
wagon-2.483
 Wem-2.276
 NETWORK-2.256
 Lith-2.239
Tokenaged
Token ID1886
Feature activation-1.50e-01

Pos logit contributions
usra+1.023
matched+0.988
 honors+0.956
 Armen+0.953
 ovarian+0.885
Neg logit contributions
acebook-1.126
wagon-1.092
 Wem-1.000
 NETWORK-0.989
 Lith-0.984
Token Italians
Token ID41720
Feature activation-2.09e-01

Pos logit contributions
usra+0.399
matched+0.379
 Armen+0.366
 honors+0.366
 ovarian+0.336
Neg logit contributions
acebook-0.581
wagon-0.571
 Wem-0.524
 NETWORK-0.520
 Lith-0.518
Token had
Token ID550
Feature activation-4.17e-01

Pos logit contributions
usra+0.676
matched+0.647
 honors+0.628
 Armen+0.628
 ovarian+0.587
Neg logit contributions
acebook-0.690
wagon-0.677
 Wem-0.612
 NETWORK-0.606
 Lith-0.603
Token been
Token ID587
Feature activation-2.58e-01

Pos logit contributions
usra+1.266
matched+1.210
 Armen+1.177
 honors+1.177
 ovarian+1.094
Neg logit contributions
acebook-1.460
wagon-1.431
 Wem-1.299
 NETWORK-1.289
 Lith-1.281
Token cons
Token ID762
Feature activation-1.24e+00

Pos logit contributions
usra+0.725
matched+0.691
 Armen+0.669
 honors+0.669
 ovarian+0.617
Neg logit contributions
acebook-0.959
wagon-0.940
 Wem-0.860
 NETWORK-0.853
 Lith-0.849
Tokencript
Token ID6519
Feature activation-1.48e-01

Pos logit contributions
usra+2.098
matched+1.986
 honors+1.824
 Armen+1.797
 ovarian+1.542
Neg logit contributions
acebook-5.966
wagon-5.776
 Wem-5.560
 NETWORK-5.465
 Lith-5.386
Tokened
Token ID276
Feature activation-2.17e-01

Pos logit contributions
usra+0.553
matched+0.533
 Armen+0.521
 honors+0.520
 ovarian+0.490
Neg logit contributions
acebook-0.411
wagon-0.401
 Wem-0.355
 NETWORK-0.351
 Lith-0.349
Token into
Token ID656
Feature activation-7.25e-01

Pos logit contributions
usra+0.675
matched+0.646
 Armen+0.628
 honors+0.628
 ovarian+0.584
Neg logit contributions
acebook-0.740
wagon-0.725
 Wem-0.657
 NETWORK-0.651
 Lith-0.648
Token forced
Token ID4137
Feature activation-9.42e-02

Pos logit contributions
usra+2.476
matched+2.377
 honors+2.341
 Armen+2.336
 ovarian+2.187
Neg logit contributions
acebook-2.250
wagon-2.191
 Wem-1.971
 NETWORK-1.944
 Lith-1.925
Token labour
Token ID10515
Feature activation+8.87e-02

Pos logit contributions
usra+0.261
matched+0.248
 Armen+0.240
 honors+0.240
 ovarian+0.221
Neg logit contributions
acebook-0.354
wagon-0.348
 Wem-0.318
 NETWORK-0.316
 Lith-0.315
Token
Token ID198
Feature activation+5.10e-04

Pos logit contributions
acebook+0.118
wagon+0.117
 Wem+0.106
 NETWORK+0.106
 Lith+0.105
Neg logit contributions
usra-0.095
matched-0.090
 Armen-0.087
 honors-0.087
 ovarian-0.081
Token14
Token ID1415
Feature activation-5.21e-02

Pos logit contributions
acebook+0.002
wagon+0.002
 Wem+0.002
 NETWORK+0.002
 Lith+0.002
Neg logit contributions
usra-0.002
matched-0.002
 honors-0.001
 Armen-0.001
 ovarian-0.001
Token Recommend
Token ID30361
Feature activation-6.66e-01

Pos logit contributions
usra+0.140
matched+0.133
 Armen+0.128
 honors+0.128
 ovarian+0.118
Neg logit contributions
acebook-0.200
wagon-0.197
 Wem-0.181
 NETWORK-0.179
 Lith-0.179
Token
Token ID198
Feature activation-2.54e-01

Pos logit contributions
usra+1.706
matched+1.644
 Armen+1.591
 honors+1.582
 ovarian+1.427
Neg logit contributions
acebook-2.689
wagon-2.587
 Wem-2.367
 NETWORK-2.332
 Lith-2.306
Token
Token ID198
Feature activation-1.83e-01

Pos logit contributions
usra+0.706
matched+0.677
 honors+0.653
 Armen+0.652
 ovarian+0.601
Neg logit contributions
acebook-0.959
wagon-0.933
 Wem-0.856
 NETWORK-0.847
 Lith-0.840
TokenRecommend
Token ID41248
Feature activation-1.21e+00

Pos logit contributions
usra+0.547
matched+0.515
 Armen+0.503
 honors+0.499
 ovarian+0.468
Neg logit contributions
acebook-0.649
wagon-0.640
 Wem-0.577
 Lith-0.575
 NETWORK-0.575
Token Share
Token ID8734
Feature activation+6.04e-02

Pos logit contributions
usra+3.723
matched+3.700
 honors+3.609
 Armen+3.604
 ovarian+3.363
Neg logit contributions
acebook-4.029
wagon-3.936
 Wem-3.512
 NETWORK-3.412
 Lith-3.395
Token this
Token ID428
Feature activation-2.81e-01

Pos logit contributions
acebook+0.197
wagon+0.192
 Wem+0.174
 NETWORK+0.172
 Lith+0.171
Neg logit contributions
usra-0.198
matched-0.190
 honors-0.186
 Armen-0.186
 ovarian-0.173
Token comment
Token ID2912
Feature activation+5.18e-02

Pos logit contributions
usra+0.684
matched+0.655
 honors+0.643
 Armen+0.639
 ovarian+0.582
Neg logit contributions
acebook-1.147
wagon-1.126
 Wem-1.038
 NETWORK-1.026
 Lith-1.010
Token on
Token ID319
Feature activation-1.26e-01

Pos logit contributions
acebook+0.183
wagon+0.179
 Wem+0.163
 Lith+0.160
 NETWORK+0.160
Neg logit contributions
usra-0.155
matched-0.149
 honors-0.146
 Armen-0.145
 ovarian-0.135
Token Facebook
Token ID3203
Feature activation-7.92e-02

Pos logit contributions
usra+0.382
matched+0.368
 Armen+0.358
 honors+0.357
 ovarian+0.331
Neg logit contributions
acebook-0.442
wagon-0.434
 Wem-0.393
 NETWORK-0.388
 Lith-0.386
Token featuring
Token ID9593
Feature activation-3.39e-02

Pos logit contributions
acebook+0.163
wagon+0.159
 Wem+0.144
 NETWORK+0.142
 Lith+0.141
Neg logit contributions
usra-0.162
matched-0.155
 honors-0.151
 Armen-0.151
 ovarian-0.141
Token more
Token ID517
Feature activation-1.33e-02

Pos logit contributions
usra+0.111
matched+0.107
 honors+0.105
 Armen+0.104
 ovarian+0.097
Neg logit contributions
acebook-0.111
wagon-0.108
 Wem-0.097
 NETWORK-0.096
 Lith-0.095
Token high
Token ID1029
Feature activation+2.12e-01

Pos logit contributions
usra+0.045
matched+0.043
 honors+0.042
 Armen+0.042
 ovarian+0.039
Neg logit contributions
acebook-0.042
wagon-0.041
 Wem-0.037
 NETWORK-0.037
 Lith-0.036
Token-
Token ID12
Feature activation-4.85e-02

Pos logit contributions
acebook+0.751
wagon+0.736
 Wem+0.669
 NETWORK+0.663
 Lith+0.659
Neg logit contributions
usra-0.636
matched-0.610
 honors-0.592
 Armen-0.589
 ovarian-0.548
Tokenstrength
Token ID41402
Feature activation+8.46e-02

Pos logit contributions
usra+0.145
matched+0.141
 honors+0.136
 Armen+0.134
 ovarian+0.125
Neg logit contributions
acebook-0.172
wagon-0.167
 Wem-0.153
 NETWORK-0.152
 Lith-0.150
Token steel
Token ID7771
Feature activation+7.83e-01

Pos logit contributions
acebook+0.239
wagon+0.233
 Wem+0.207
 NETWORK+0.204
 Lith+0.202
Neg logit contributions
usra-0.314
matched-0.303
 honors-0.296
 Armen-0.295
 ovarian-0.279
Token than
Token ID621
Feature activation-9.21e-02

Pos logit contributions
acebook+2.527
wagon+2.495
 Lith+2.239
 Transmission+2.222
 Wem+2.221
Neg logit contributions
usra-2.548
matched-2.406
 Armen-2.362
 honors-2.332
��-2.230
Token the
Token ID262
Feature activation+1.94e-02

Pos logit contributions
usra+0.272
matched+0.262
 honors+0.254
 Armen+0.252
 ovarian+0.234
Neg logit contributions
acebook-0.330
wagon-0.323
 Wem-0.294
 NETWORK-0.291
 Lith-0.288
Token outgoing
Token ID28181
Feature activation+3.29e-01

Pos logit contributions
acebook+0.065
wagon+0.063
 Wem+0.057
 NETWORK+0.057
 Lith+0.056
Neg logit contributions
usra-0.062
matched-0.060
 honors-0.058
 Armen-0.058
 ovarian-0.054
Token Rapt
Token ID21301
Feature activation-1.95e-03

Pos logit contributions
acebook+1.072
wagon+1.059
 Wem+0.955
 NETWORK+0.948
 Lith+0.948
Neg logit contributions
usra-1.068
matched-1.020
 Armen-0.994
 honors-0.987
 ovarian-0.927
Tokenor
Token ID273
Feature activation-1.87e-02

Pos logit contributions
usra+0.005
matched+0.004
 honors+0.004
 Armen+0.004
 ovarian+0.004
Neg logit contributions
acebook-0.008
wagon-0.008
 Wem-0.007
 NETWORK-0.007
 Lith-0.007
Tokenod
Token ID375
Feature activation+1.61e-01

Pos logit contributions
acebook+1.217
wagon+1.193
 Wem+1.067
 NETWORK+1.057
 Lith+1.052
Neg logit contributions
usra-1.369
matched-1.316
 honors-1.281
 Armen-1.281
 ovarian-1.203
Token.
Token ID13
Feature activation-4.55e-02

Pos logit contributions
acebook+0.544
wagon+0.538
 Wem+0.487
 NETWORK+0.484
 Lith+0.482
Neg logit contributions
usra-0.506
matched-0.484
 honors-0.468
 Armen-0.467
 ovarian-0.436
Token
Token ID198
Feature activation-2.05e-01

Pos logit contributions
usra+0.144
matched+0.138
 Armen+0.134
 honors+0.134
 ovarian+0.125
Neg logit contributions
acebook-0.154
wagon-0.150
 Wem-0.136
 NETWORK-0.134
 Lith-0.134
Token
Token ID198
Feature activation-2.01e-01

Pos logit contributions
usra+0.566
matched+0.543
 Armen+0.523
 honors+0.523
 ovarian+0.481
Neg logit contributions
acebook-0.778
wagon-0.757
 Wem-0.693
 NETWORK-0.686
 Lith-0.680
TokenJ
Token ID41
Feature activation+1.99e-01

Pos logit contributions
usra+0.606
matched+0.582
 honors+0.563
 Armen+0.562
 ovarian+0.521
Neg logit contributions
acebook-0.707
wagon-0.685
 Wem-0.627
 NETWORK-0.621
 Lith-0.615
Tokenag
Token ID363
Feature activation+7.72e-01

Pos logit contributions
acebook+0.700
wagon+0.686
 Wem+0.625
 NETWORK+0.619
 Lith+0.616
Neg logit contributions
usra-0.597
matched-0.570
 honors-0.553
 Armen-0.553
 ovarian-0.513
Tokend
Token ID67
Feature activation-7.20e-02

Pos logit contributions
wagon+2.810
acebook+2.803
 Wem+2.551
 Lith+2.519
 NETWORK+2.511
Neg logit contributions
usra-2.162
matched-2.075
 honors-2.017
 Armen-2.009
 ovarian-1.869
Tokenish
Token ID680
Feature activation-1.41e-01

Pos logit contributions
usra+0.188
matched+0.176
 honors+0.171
 Armen+0.170
 ovarian+0.156
Neg logit contributions
acebook-0.285
wagon-0.277
 Wem-0.256
 NETWORK-0.255
 Lith-0.253
Token Sh
Token ID911
Feature activation-4.38e-01

Pos logit contributions
usra+0.427
matched+0.407
 honors+0.398
 Armen+0.398
 ovarian+0.369
Neg logit contributions
acebook-0.492
wagon-0.479
 Wem-0.435
 NETWORK-0.432
 Lith-0.429
Tokenind
Token ID521
Feature activation+5.07e-01

Pos logit contributions
usra+1.306
matched+1.226
 honors+1.187
 Armen+1.183
zan+1.100
Neg logit contributions
acebook-1.568
wagon-1.529
 Wem-1.411
 NETWORK-1.401
 Lith-1.387
Tokene
Token ID68
Feature activation-6.11e-02

Pos logit contributions
acebook+1.653
wagon+1.634
 Wem+1.469
 NETWORK+1.456
 Lith+1.449
Neg logit contributions
usra-1.638
matched-1.571
 honors-1.531
 Armen-1.525
 ovarian-1.431
Token hot
Token ID3024
Feature activation-2.55e-01

Pos logit contributions
usra+0.802
matched+0.768
 honors+0.746
 Armen+0.746
 ovarian+0.695
Neg logit contributions
acebook-0.871
wagon-0.853
 Wem-0.774
 NETWORK-0.767
 Lith-0.763
Token-
Token ID12
Feature activation-2.36e-01

Pos logit contributions
usra+0.844
matched+0.819
 Armen+0.798
 honors+0.796
 ovarian+0.748
Neg logit contributions
acebook-0.809
wagon-0.784
 NETWORK-0.710
 Wem-0.706
 Lith-0.700
Tokenbutton
Token ID16539
Feature activation-1.03e+00

Pos logit contributions
usra+0.679
matched+0.648
 Armen+0.627
 honors+0.627
 ovarian+0.580
Neg logit contributions
acebook-0.862
wagon-0.844
 Wem-0.771
 NETWORK-0.766
 Lith-0.762
Token issues
Token ID2428
Feature activation-2.04e-02

Pos logit contributions
usra+2.994
matched+2.874
 honors+2.846
 Armen+2.833
 ovarian+2.644
Neg logit contributions
acebook-3.647
wagon-3.544
 NETWORK-3.217
 Wem-3.209
 Transmission-3.172
Token that
Token ID326
Feature activation+1.29e-01

Pos logit contributions
usra+0.063
matched+0.060
 honors+0.058
 Armen+0.058
 ovarian+0.054
Neg logit contributions
acebook-0.070
wagon-0.069
 Wem-0.063
 NETWORK-0.062
 Lith-0.062
Token galvan
Token ID42170
Feature activation+8.08e-01

Pos logit contributions
acebook+0.420
wagon+0.411
 Wem+0.371
 NETWORK+0.368
 Lith+0.366
Neg logit contributions
usra-0.421
matched-0.403
 Armen-0.392
 honors-0.392
 ovarian-0.367
Tokenized
Token ID1143
Feature activation+4.82e-01

Pos logit contributions
acebook+2.879
wagon+2.827
 Wem+2.585
 NETWORK+2.566
 Lith+2.556
Neg logit contributions
usra-2.366
matched-2.253
 honors-2.198
 Armen-2.170
 ovarian-2.015
Token all
Token ID477
Feature activation+2.07e-01

Pos logit contributions
acebook+1.556
wagon+1.517
 Wem+1.382
 NETWORK+1.370
 Lith+1.357
Neg logit contributions
usra-1.593
matched-1.525
 honors-1.475
 Armen-1.471
 ovarian-1.378
Token unions
Token ID11936
Feature activation+4.30e-01

Pos logit contributions
acebook+0.704
wagon+0.690
 Wem+0.627
 NETWORK+0.622
 Lith+0.618
Neg logit contributions
usra-0.646
matched-0.618
 honors-0.599
 Armen-0.598
 ovarian-0.558
Token into
Token ID656
Feature activation-3.21e-01

Pos logit contributions
acebook+1.433
wagon+1.423
 Wem+1.281
 NETWORK+1.279
 Lith+1.270
Neg logit contributions
usra-1.362
matched-1.290
 Armen-1.259
 honors-1.259
 ovarian-1.174
Token signing
Token ID8415
Feature activation+1.40e-01

Pos logit contributions
usra+1.334
matched+1.289
 honors+1.267
 Armen+1.264
 ovarian+1.201
Neg logit contributions
acebook-0.764
wagon-0.739
 Wem-0.636
 NETWORK-0.628
 Lith-0.622
Token sold
Token ID2702
Feature activation-7.02e-02

Pos logit contributions
acebook+0.377
wagon+0.369
 Wem+0.335
 NETWORK+0.331
 Lith+0.331
Neg logit contributions
usra-0.360
matched-0.344
 Armen-0.334
 honors-0.334
 ovarian-0.311
Token to
Token ID284
Feature activation+1.91e-01

Pos logit contributions
usra+0.213
matched+0.204
 Armen+0.198
 honors+0.198
 ovarian+0.184
Neg logit contributions
acebook-0.245
wagon-0.240
 Wem-0.219
 NETWORK-0.217
 Lith-0.216
Token UK
Token ID3482
Feature activation+1.62e-01

Pos logit contributions
acebook+0.568
wagon+0.553
 Wem+0.497
 NETWORK+0.491
 Lith+0.490
Neg logit contributions
usra-0.680
matched-0.654
 Armen-0.636
 honors-0.636
 ovarian-0.598
Token publisher
Token ID9991
Feature activation+2.41e-01

Pos logit contributions
acebook+0.509
wagon+0.497
 Wem+0.448
 NETWORK+0.444
 Lith+0.442
Neg logit contributions
usra-0.549
matched-0.528
 Armen-0.513
 honors-0.512
 ovarian-0.480
Token Jonathan
Token ID11232
Feature activation+5.48e-01

Pos logit contributions
acebook+0.768
wagon+0.751
 Wem+0.684
 Lith+0.675
 NETWORK+0.674
Neg logit contributions
usra-0.808
matched-0.772
 Armen-0.750
 honors-0.750
 ovarian-0.704
Token Cape
Token ID15725
Feature activation+7.97e-01

Pos logit contributions
acebook+1.810
wagon+1.778
 Wem+1.620
 Lith+1.602
 NETWORK+1.591
Neg logit contributions
usra-1.759
matched-1.688
 honors-1.637
 Armen-1.632
 ovarian-1.530
Token,
Token ID11
Feature activation+4.09e-01

Pos logit contributions
acebook+2.689
wagon+2.658
 Wem+2.416
 Lith+2.405
 NETWORK+2.393
Neg logit contributions
usra-2.477
matched-2.362
 Armen-2.293
 honors-2.277
 ovarian-2.141
Token with
Token ID351
Feature activation+2.10e-01

Pos logit contributions
acebook+1.331
wagon+1.301
 Wem+1.183
 NETWORK+1.170
 Lith+1.167
Neg logit contributions
usra-1.338
matched-1.280
 Armen-1.242
 honors-1.241
 ovarian-1.162
Token an
Token ID281
Feature activation+1.65e-01

Pos logit contributions
acebook+0.612
wagon+0.594
 Wem+0.534
 NETWORK+0.527
 Lith+0.526
Neg logit contributions
usra-0.762
matched-0.733
 Armen-0.714
 honors-0.712
 ovarian-0.670
Token auction
Token ID14389
Feature activation-3.61e-01

Pos logit contributions
acebook+0.561
wagon+0.547
 Wem+0.499
 NETWORK+0.495
 Lith+0.493
Neg logit contributions
usra-0.519
matched-0.497
 Armen-0.482
 honors-0.480
 ovarian-0.448
Token understood
Token ID7247
Feature activation-8.42e-02

Pos logit contributions
usra+1.125
matched+1.077
 honors+1.048
 Armen+1.045
 ovarian+0.974
Neg logit contributions
acebook-1.232
wagon-1.206
 Wem-1.095
 NETWORK-1.081
 Lith-1.077
Token more
Token ID517
Feature activation-1.86e-01

Pos logit contributions
acebook+1.186
wagon+1.161
 Wem+1.047
 NETWORK+1.036
 Lith+1.032
Neg logit contributions
usra-1.239
matched-1.188
 Armen-1.154
 honors-1.154
 ovarian-1.080
Token agreement
Token ID4381
Feature activation+2.98e-01

Pos logit contributions
usra+0.582
matched+0.557
 honors+0.542
 Armen+0.542
 ovarian+0.505
Neg logit contributions
acebook-0.638
wagon-0.622
 Wem-0.564
 NETWORK-0.560
 Lith-0.555
Token than
Token ID621
Feature activation-2.00e-01

Pos logit contributions
acebook+0.971
wagon+0.954
 Wem+0.861
 NETWORK+0.854
 Lith+0.851
Neg logit contributions
usra-0.969
matched-0.925
 Armen-0.899
 honors-0.898
 ovarian-0.841
Token the
Token ID262
Feature activation+5.20e-03

Pos logit contributions
usra+0.653
matched+0.628
 honors+0.612
 Armen+0.611
 ovarian+0.570
Neg logit contributions
acebook-0.653
wagon-0.639
 Wem-0.575
 NETWORK-0.570
 Lith-0.566
Token rating
Token ID7955
Feature activation+3.80e-01

Pos logit contributions
acebook+0.017
wagon+0.017
 Wem+0.015
 NETWORK+0.015
 Lith+0.015
Neg logit contributions
usra-0.017
matched-0.016
 Armen-0.015
 honors-0.015
 ovarian-0.014
Token implied
Token ID17142
Feature activation+8.40e-01

Pos logit contributions
acebook+1.228
wagon+1.209
 Wem+1.093
 NETWORK+1.086
 Lith+1.082
Neg logit contributions
usra-1.242
matched-1.186
 Armen-1.147
 honors-1.141
 ovarian-1.079
Token.
Token ID13
Feature activation+3.39e-02

Pos logit contributions
acebook+2.605
wagon+2.549
 Wem+2.298
 NETWORK+2.287
 Lith+2.275
Neg logit contributions
usra-2.836
matched-2.694
 Armen-2.620
 honors-2.598
��-2.478
Token A
Token ID317
Feature activation-1.42e-01

Pos logit contributions
acebook+0.114
wagon+0.112
 Wem+0.101
 NETWORK+0.100
 Lith+0.099
Neg logit contributions
usra-0.107
matched-0.103
 Armen-0.100
 honors-0.100
 ovarian-0.093
Token larger
Token ID4025
Feature activation-2.01e-01

Pos logit contributions
usra+0.441
matched+0.422
 honors+0.409
 Armen+0.409
 ovarian+0.380
Neg logit contributions
acebook-0.489
wagon-0.478
 Wem-0.434
 NETWORK-0.430
 Lith-0.427
Token number
Token ID1271
Feature activation-7.55e-02

Pos logit contributions
usra+0.642
matched+0.615
 Armen+0.598
 honors+0.598
 ovarian+0.557
Neg logit contributions
acebook-0.673
wagon-0.660
 Wem-0.597
 NETWORK-0.592
 Lith-0.589
Token of
Token ID286
Feature activation+2.35e-02

Pos logit contributions
usra+0.218
matched+0.206
 Armen+0.201
 honors+0.199
 ovarian+0.187
Neg logit contributions
acebook-0.274
wagon-0.270
 Wem-0.245
 NETWORK-0.243
 Lith-0.243
Token a
Token ID257
Feature activation+2.80e-02

Pos logit contributions
usra+0.330
matched+0.317
 Armen+0.308
 honors+0.308
 ovarian+0.289
Neg logit contributions
acebook-0.303
wagon-0.295
 Wem-0.265
 NETWORK-0.263
 Lith-0.261
Token lot
Token ID1256
Feature activation-1.90e-01

Pos logit contributions
acebook+0.092
wagon+0.090
 Wem+0.081
 NETWORK+0.080
 Lith+0.080
Neg logit contributions
usra-0.091
matched-0.087
 Armen-0.085
 honors-0.085
 ovarian-0.079
Token of
Token ID286
Feature activation+9.28e-02

Pos logit contributions
usra+0.526
matched+0.499
 honors+0.483
 Armen+0.483
 ovarian+0.445
Neg logit contributions
acebook-0.714
wagon-0.703
 Wem-0.643
 NETWORK-0.638
 Lith-0.636
Token moving
Token ID3867
Feature activation-8.81e-03

Pos logit contributions
acebook+0.303
wagon+0.296
 Wem+0.267
 NETWORK+0.264
 Lith+0.263
Neg logit contributions
usra-0.304
matched-0.292
 honors-0.284
 Armen-0.284
 ovarian-0.265
Token around
Token ID1088
Feature activation+1.24e-01

Pos logit contributions
usra+0.026
matched+0.025
 Armen+0.024
 honors+0.024
 ovarian+0.022
Neg logit contributions
acebook-0.031
wagon-0.031
 Wem-0.028
 NETWORK-0.028
 Lith-0.028
Token with
Token ID351
Feature activation+8.49e-02

Pos logit contributions
acebook+0.427
wagon+0.420
 Wem+0.381
 NETWORK+0.377
 Lith+0.376
Neg logit contributions
usra-0.382
matched-0.364
 Armen-0.354
 honors-0.353
 ovarian-0.330
Token the
Token ID262
Feature activation-6.72e-02

Pos logit contributions
acebook+0.278
wagon+0.273
 Wem+0.247
 Lith+0.245
 NETWORK+0.244
Neg logit contributions
usra-0.276
matched-0.264
 Armen-0.255
 honors-0.255
 ovarian-0.239
Token second
Token ID1218
Feature activation-1.10e-01

Pos logit contributions
usra+0.206
matched+0.197
 honors+0.191
 Armen+0.191
 ovarian+0.178
Neg logit contributions
acebook-0.233
wagon-0.228
 Wem-0.207
 NETWORK-0.205
 Lith-0.204
Token unit
Token ID4326
Feature activation-5.07e-02

Pos logit contributions
usra+0.338
matched+0.323
 honors+0.315
 Armen+0.313
 ovarian+0.291
Neg logit contributions
acebook-0.383
wagon-0.374
 Wem-0.340
 NETWORK-0.337
 Lith-0.334
Token as
Token ID355
Feature activation+2.41e-01

Pos logit contributions
usra+0.152
matched+0.145
 honors+0.141
 Armen+0.141
 ovarian+0.131
Neg logit contributions
acebook-0.179
wagon-0.176
 Wem-0.160
 NETWORK-0.159
 Lith-0.158
Token well
Token ID880
Feature activation+2.68e-01

Pos logit contributions
acebook+0.756
wagon+0.741
 Wem+0.668
 NETWORK+0.659
 Lith+0.659
Neg logit contributions
usra-0.814
matched-0.780
 Armen-0.757
 honors-0.757
 ovarian-0.712
Token they
Token ID484
Feature activation-5.65e-02

Pos logit contributions
usra+0.306
matched+0.292
 honors+0.283
 Armen+0.283
 ovarian+0.263
Neg logit contributions
acebook-0.357
wagon-0.350
 Wem-0.318
 NETWORK-0.316
 Lith-0.314
Token saw
Token ID2497
Feature activation-1.24e-01

Pos logit contributions
usra+0.198
matched+0.191
 Armen+0.186
 honors+0.186
 ovarian+0.175
Neg logit contributions
acebook-0.171
wagon-0.167
 Wem-0.149
 NETWORK-0.148
 Lith-0.147
Token as
Token ID355
Feature activation+3.92e-01

Pos logit contributions
usra+0.417
matched+0.396
 honors+0.386
 Armen+0.386
 ovarian+0.361
Neg logit contributions
acebook-0.396
wagon-0.387
 Wem-0.349
 NETWORK-0.344
 Lith-0.344
Token the
Token ID262
Feature activation-5.39e-02

Pos logit contributions
acebook+1.214
wagon+1.187
 Wem+1.073
 Lith+1.059
 NETWORK+1.057
Neg logit contributions
usra-1.332
matched-1.283
 honors-1.246
 Armen-1.245
��-1.173
Token over
Token ID625
Feature activation+1.63e-01

Pos logit contributions
usra+0.175
matched+0.167
 Armen+0.163
 honors+0.163
 ovarian+0.152
Neg logit contributions
acebook-0.178
wagon-0.174
 Wem-0.157
 NETWORK-0.156
 Lith-0.155
Tokenpolit
Token ID34470
Feature activation+2.60e-01

Pos logit contributions
acebook+0.582
wagon+0.570
 Wem+0.519
 NETWORK+0.515
 Lith+0.512
Neg logit contributions
usra-0.486
matched-0.464
 Armen-0.450
 honors-0.450
 ovarian-0.417
Tokenic
Token ID291
Feature activation+1.41e-01

Pos logit contributions
acebook+0.810
wagon+0.791
 Wem+0.711
 NETWORK+0.704
 Lith+0.700
Neg logit contributions
usra-0.886
matched-0.851
 honors-0.829
 Armen-0.829
 ovarian-0.777
Tokenisation
Token ID5612
Feature activation-2.59e-03

Pos logit contributions
acebook+0.367
wagon+0.357
 Wem+0.313
 NETWORK+0.310
 Lith+0.308
Neg logit contributions
usra-0.551
matched-0.532
 Armen-0.520
 honors-0.520
 ovarian-0.492
Token of
Token ID286
Feature activation-6.66e-02

Pos logit contributions
usra+0.007
matched+0.007
 honors+0.007
 Armen+0.007
��+0.006
Neg logit contributions
acebook-0.009
wagon-0.009
 Wem-0.008
 Lith-0.008
 NETWORK-0.008
Token his
Token ID465
Feature activation+3.10e-02

Pos logit contributions
usra+0.232
matched+0.223
 honors+0.217
 Armen+0.217
 ovarian+0.204
Neg logit contributions
acebook-0.203
wagon-0.198
 Wem-0.177
 NETWORK-0.175
 Lith-0.174
Token role
Token ID2597
Feature activation-4.15e-02

Pos logit contributions
acebook+0.105
wagon+0.103
 Wem+0.093
 NETWORK+0.092
 Lith+0.091
Neg logit contributions
usra-0.098
matched-0.094
 honors-0.092
 Armen-0.091
 ovarian-0.085
Tokentil
Token ID47163
Feature activation-1.65e-01

Pos logit contributions
acebook+0.788
wagon+0.771
 Wem+0.702
 NETWORK+0.696
 Lith+0.693
Neg logit contributions
usra-0.675
matched-0.645
 honors-0.625
 Armen-0.625
 ovarian-0.580
Token I
Token ID314
Feature activation-2.19e-01

Pos logit contributions
usra+0.497
matched+0.475
 Armen+0.463
 honors+0.462
 ovarian+0.429
Neg logit contributions
acebook-0.581
wagon-0.568
 Wem-0.518
 NETWORK-0.513
 Lith-0.510
Token get
Token ID651
Feature activation-1.47e-01

Pos logit contributions
usra+0.693
matched+0.664
 Armen+0.646
 honors+0.646
 ovarian+0.602
Neg logit contributions
acebook-0.736
wagon-0.719
 Wem-0.652
 NETWORK-0.645
 Lith-0.642
Token my
Token ID616
Feature activation+2.93e-01

Pos logit contributions
usra+0.455
matched+0.436
 honors+0.424
 Armen+0.424
 ovarian+0.394
Neg logit contributions
acebook-0.508
wagon-0.495
 Wem-0.451
 NETWORK-0.447
 Lith-0.444
Token here
Token ID994
Feature activation+6.69e-01

Pos logit contributions
acebook+1.063
wagon+1.053
 Wem+0.955
 Lith+0.951
 NETWORK+0.947
Neg logit contributions
usra-0.843
matched-0.805
 Armen-0.773
 honors-0.769
��-0.716
Token IM
Token ID8959
Feature activation+8.67e-02

Pos logit contributions
acebook+2.296
wagon+2.293
 Lith+2.042
 Wem+2.035
 NETWORK+2.030
Neg logit contributions
usra-2.046
matched-1.931
 Armen-1.882
 honors-1.867
 ovarian-1.754
TokenM
Token ID44
Feature activation+2.06e-01

Pos logit contributions
acebook+0.308
wagon+0.302
 Wem+0.276
 NETWORK+0.273
 Lith+0.271
Neg logit contributions
usra-0.258
matched-0.247
 honors-0.240
 Armen-0.239
 ovarian-0.222
TokenIG
Token ID3528
Feature activation+5.57e-01

Pos logit contributions
acebook+0.499
wagon+0.484
 Wem+0.421
 NETWORK+0.415
 Lith+0.412
Neg logit contributions
usra-0.846
matched-0.818
 honors-0.800
 Armen-0.800
 ovarian-0.759
TokenRANT
Token ID32506
Feature activation+2.74e-01

Pos logit contributions
acebook+1.458
wagon+1.416
 Wem+1.235
 NETWORK+1.232
 Lith+1.225
Neg logit contributions
usra-2.182
matched-2.106
 Armen-2.054
 honors-2.051
 ovarian-1.946
Token food
Token ID2057
Feature activation+1.10e-01

Pos logit contributions
acebook+0.963
wagon+0.946
 Wem+0.858
 NETWORK+0.854
 Lith+0.850
Neg logit contributions
usra-0.829
matched-0.791
 Armen-0.766
 honors-0.764
 ovarian-0.710
Token from
Token ID422
Feature activation+3.00e-01

Pos logit contributions
acebook+0.390
wagon+0.385
 Wem+0.347
 NETWORK+0.347
 Lith+0.345
Neg logit contributions
usra-0.327
matched-0.311
 Armen-0.302
 honors-0.300
 ovarian-0.280
Token
Token ID198
Feature activation-2.40e-01

Pos logit contributions
acebook+0.318
wagon+0.311
 Wem+0.283
 NETWORK+0.281
 Lith+0.279
Neg logit contributions
usra-0.272
matched-0.260
 Armen-0.252
 honors-0.252
 ovarian-0.235
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
usra+0.658
matched+0.633
 honors+0.610
 Armen+0.609
 ovarian+0.560
Neg logit contributions
acebook-0.920
wagon-0.893
 Wem-0.819
 NETWORK-0.811
 Lith-0.803
TokenThe
Token ID464
Feature activation-2.05e-01

Pos logit contributions
usra+0.467
matched+0.449
 honors+0.431
 Armen+0.431
 ovarian+0.400
Neg logit contributions
acebook-0.556
wagon-0.540
 Wem-0.497
 NETWORK-0.493
 Lith-0.487
Token year
Token ID614
Feature activation+8.92e-02

Pos logit contributions
usra+0.667
matched+0.638
 Armen+0.624
 honors+0.623
 ovarian+0.583
Neg logit contributions
acebook-0.675
wagon-0.659
 Wem-0.594
 NETWORK-0.588
 Lith-0.584
Token to
Token ID284
Feature activation+1.91e-01

Pos logit contributions
acebook+0.306
wagon+0.299
 Wem+0.271
 NETWORK+0.269
 Lith+0.267
Neg logit contributions
usra-0.277
matched-0.266
 Armen-0.258
 honors-0.258
 ovarian-0.240
Token year
Token ID614
Feature activation+1.70e-01

Pos logit contributions
acebook+0.667
wagon+0.654
 Wem+0.595
 NETWORK+0.590
 Lith+0.588
Neg logit contributions
usra-0.582
matched-0.556
 honors-0.539
 Armen-0.539
 ovarian-0.500
Token increase
Token ID2620
Feature activation+4.27e-01

Pos logit contributions
acebook+0.576
wagon+0.564
 Wem+0.511
 NETWORK+0.506
 Lith+0.504
Neg logit contributions
usra-0.534
matched-0.511
 honors-0.496
 Armen-0.496
 ovarian-0.462
Token of
Token ID286
Feature activation+1.11e-01

Pos logit contributions
acebook+1.481
wagon+1.455
 Wem+1.327
 Lith+1.317
 NETWORK+1.316
Neg logit contributions
usra-1.296
matched-1.231
 honors-1.193
 Armen-1.191
��-1.109
Token the
Token ID262
Feature activation+2.06e-01

Pos logit contributions
acebook+0.320
wagon+0.312
 Wem+0.278
 NETWORK+0.275
 Lith+0.273
Neg logit contributions
usra-0.402
matched-0.387
 Armen-0.377
 honors-0.377
 ovarian-0.355
Token anthrop
Token ID17911
Feature activation+1.54e-01

Pos logit contributions
acebook+0.478
wagon+0.463
 Wem+0.400
 NETWORK+0.395
 Lith+0.393
Neg logit contributions
usra-0.866
matched-0.838
 honors-0.819
 Armen-0.819
 ovarian-0.778
Tokenic
Token ID291
Feature activation+2.00e-01

Pos logit contributions
acebook+0.454
wagon+0.443
 Wem+0.395
 NETWORK+0.392
 Lith+0.391
Neg logit contributions
usra-0.547
matched-0.528
 honors-0.514
 Armen-0.512
 ovarian-0.482
Token is
Token ID318
Feature activation-7.00e-01

Pos logit contributions
acebook+0.494
wagon+0.483
 Wem+0.433
 NETWORK+0.430
 Lith+0.429
Neg logit contributions
usra-0.551
matched-0.528
 Armen-0.513
 honors-0.512
 ovarian-0.482
Token National
Token ID2351
Feature activation-1.15e-01

Pos logit contributions
usra+2.233
matched+2.139
 honors+2.094
 Armen+2.091
 ovarian+1.944
Neg logit contributions
acebook-2.336
wagon-2.277
 Wem-2.064
 NETWORK-2.023
 Lith-1.990
Token Debt
Token ID30319
Feature activation-3.42e-01

Pos logit contributions
usra+0.486
matched+0.471
 Armen+0.462
 honors+0.461
 ovarian+0.438
Neg logit contributions
acebook-0.262
wagon-0.254
 Wem-0.219
 NETWORK-0.215
 Lith-0.213
Token Bad
Token ID7772
Feature activation-1.70e-01

Pos logit contributions
usra+1.104
matched+1.060
 Armen+1.037
 honors+1.037
 ovarian+0.964
Neg logit contributions
acebook-1.131
wagon-1.106
 Wem-0.991
 NETWORK-0.983
 Lith-0.970
Token?
Token ID30
Feature activation-3.93e-02

Pos logit contributions
usra+0.475
matched+0.449
 honors+0.434
 Armen+0.433
 ovarian+0.402
Neg logit contributions
acebook-0.634
wagon-0.626
 Wem-0.571
 Lith-0.568
 NETWORK-0.568
Token
Token ID198
Feature activation+2.39e-01

Pos logit contributions
usra+0.120
matched+0.114
 honors+0.110
 Armen+0.109
 ovarian+0.103
Neg logit contributions
acebook-0.138
wagon-0.135
 Lith-0.123
 NETWORK-0.122
 Transmission-0.122
Token
Token ID198
Feature activation+2.96e-01

Pos logit contributions
acebook+0.826
wagon+0.823
 Lith+0.748
 Wem+0.747
 NETWORK+0.745
Neg logit contributions
usra-0.719
matched-0.677
 Armen-0.660
 honors-0.660
��-0.621
TokenIf
Token ID1532
Feature activation-1.43e-01

Pos logit contributions
acebook+1.012
wagon+1.000
 Wem+0.901
 Lith+0.895
 NETWORK+0.895
Neg logit contributions
usra-0.913
matched-0.869
 Armen-0.847
 honors-0.847
 ovarian-0.791
Token a
Token ID257
Feature activation-4.74e-02

Pos logit contributions
usra+0.484
matched+0.464
 honors+0.453
 Armen+0.453
 ovarian+0.424
Neg logit contributions
acebook-0.453
wagon-0.443
 Wem-0.398
 NETWORK-0.394
 Lith-0.390
Token government
Token ID1230
Feature activation+2.10e-01

Pos logit contributions
usra+0.153
matched+0.147
 honors+0.143
 Armen+0.143
 ovarian+0.134
Neg logit contributions
acebook-0.156
wagon-0.153
 Wem-0.138
 NETWORK-0.136
 Lith-0.136
Token increases
Token ID5732
Feature activation+4.84e-01

Pos logit contributions
acebook+0.645
wagon+0.635
 Wem+0.568
 NETWORK+0.565
 Lith+0.561
Neg logit contributions
usra-0.721
matched-0.692
 Armen-0.673
 honors-0.667
 ovarian-0.633
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
usra+1.146
matched+1.105
 Armen+1.082
 honors+1.081
 ovarian+1.007
Neg logit contributions
acebook-1.235
wagon-1.203
 Wem-1.086
 NETWORK-1.077
 Lith-1.064
Token frontrunner
Token ID49981
Feature activation-1.45e-01

Pos logit contributions
usra+0.458
matched+0.439
 honors+0.429
 Armen+0.427
 ovarian+0.397
Neg logit contributions
acebook-0.512
wagon-0.500
 Wem-0.454
 NETWORK-0.448
 Lith-0.445
Token for
Token ID329
Feature activation-3.59e-01

Pos logit contributions
usra+0.428
matched+0.412
 honors+0.401
 Armen+0.398
 ovarian+0.369
Neg logit contributions
acebook-0.522
wagon-0.508
 Wem-0.465
 NETWORK-0.459
 Lith-0.455
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
usra+1.226
matched+1.184
 honors+1.169
 Armen+1.161
 ovarian+1.084
Neg logit contributions
acebook-1.115
wagon-1.090
 Wem-0.965
 NETWORK-0.956
 Transmission-0.944
Token role
Token ID2597
Feature activation+1.50e-01

Pos logit contributions
usra+0.449
matched+0.429
 honors+0.424
 Armen+0.420
 ovarian+0.390
Neg logit contributions
acebook-0.519
wagon-0.508
 Wem-0.458
 NETWORK-0.454
 Transmission-0.450
Token.
Token ID13
Feature activation-7.31e-02

Pos logit contributions
acebook+0.519
wagon+0.510
 Wem+0.464
 NETWORK+0.460
 Lith+0.459
Neg logit contributions
usra-0.461
matched-0.438
 Armen-0.426
 honors-0.425
 ovarian-0.396
Token
Token ID198
Feature activation-6.39e-02

Pos logit contributions
usra+0.217
matched+0.209
 Armen+0.205
 honors+0.202
 ovarian+0.188
Neg logit contributions
acebook-0.259
wagon-0.254
 Wem-0.230
 NETWORK-0.227
 Lith-0.226
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
usra+0.178
matched+0.170
 Armen+0.165
 honors+0.164
 ovarian+0.151
Neg logit contributions
acebook-0.241
wagon-0.235
 Wem-0.215
 NETWORK-0.213
 Lith-0.211
TokenThe
Token ID464
Feature activation-4.14e-02

Pos logit contributions
usra+0.318
matched+0.305
 Armen+0.294
 honors+0.294
 ovarian+0.272
Neg logit contributions
acebook-0.379
wagon-0.369
 Wem-0.339
 NETWORK-0.334
 Lith-0.333
Token film
Token ID2646
Feature activation+2.75e-02

Pos logit contributions
usra+0.138
matched+0.132
 honors+0.130
 Armen+0.130
 ovarian+0.121
Neg logit contributions
acebook-0.132
wagon-0.130
 Wem-0.116
 NETWORK-0.114
 Lith-0.114
Token recently
Token ID2904
Feature activation-2.39e-01

Pos logit contributions
acebook+0.091
wagon+0.089
 Wem+0.080
 NETWORK+0.079
 Lith+0.079
Neg logit contributions
usra-0.089
matched-0.086
 honors-0.085
 Armen-0.083
 ovarian-0.078
Token written
Token ID3194
Feature activation-1.39e-01

Pos logit contributions
acebook+0.774
wagon+0.757
 Wem+0.683
 NETWORK+0.676
 Lith+0.673
Neg logit contributions
usra-0.793
matched-0.761
 honors-0.740
 Armen-0.740
 ovarian-0.692
Token,
Token ID11
Feature activation+1.78e-02

Pos logit contributions
usra+0.441
matched+0.423
 Armen+0.413
 honors+0.413
 ovarian+0.385
Neg logit contributions
acebook-0.468
wagon-0.457
 Wem-0.412
 NETWORK-0.408
 Lith-0.405
Token
Token ID564
Feature activation+4.41e-01

Pos logit contributions
acebook+0.059
wagon+0.057
 Wem+0.052
 NETWORK+0.051
 Lith+0.051
Neg logit contributions
usra-0.058
matched-0.055
 honors-0.054
 Armen-0.054
 ovarian-0.050
Token
Token ID246
Feature activation+1.41e-01

Pos logit contributions
acebook+1.664
wagon+1.642
 Wem+1.504
 NETWORK+1.497
 Lith+1.487
Neg logit contributions
usra-1.200
matched-1.139
 honors-1.101
 Armen-1.097
 ovarian-1.015
TokenP
Token ID47
Feature activation+3.40e-01

Pos logit contributions
acebook+0.491
wagon+0.480
 Wem+0.437
 NETWORK+0.434
 Lith+0.430
Neg logit contributions
usra-0.427
matched-0.410
 Armen-0.398
 honors-0.397
 ovarian-0.369
Tokenossible
Token ID4733
Feature activation-3.22e-01

Pos logit contributions
acebook+1.153
wagon+1.129
 Wem+1.024
 NETWORK+1.016
 Lith+1.011
Neg logit contributions
usra-1.069
matched-1.021
 Armen-0.993
 honors-0.992
 ovarian-0.924
Token shoulder
Token ID8163
Feature activation-2.70e-01

Pos logit contributions
usra+1.064
matched+1.022
 honors+1.004
 Armen+1.000
 ovarian+0.938
Neg logit contributions
acebook-1.039
wagon-1.011
 Wem-0.910
 NETWORK-0.900
 Lith-0.891
Token imp
Token ID848
Feature activation-2.79e-01

Pos logit contributions
usra+0.873
matched+0.841
 honors+0.824
 Armen+0.821
 ovarian+0.763
Neg logit contributions
acebook-0.889
wagon-0.865
 Wem-0.780
 NETWORK-0.771
 Lith-0.765
Tokening
Token ID278
Feature activation-5.98e-01

Pos logit contributions
usra+0.891
matched+0.843
 honors+0.824
 Armen+0.821
 ovarian+0.762
Neg logit contributions
acebook-0.936
wagon-0.913
 Wem-0.836
 NETWORK-0.832
 Lith-0.826
Tokenement
Token ID972
Feature activation+8.28e-02

Pos logit contributions
usra+1.988
matched+1.906
 honors+1.857
 Armen+1.852
 ovarian+1.736
Neg logit contributions
acebook-1.916
wagon-1.874
 Wem-1.691
 NETWORK-1.677
 Lith-1.663
Token,
Token ID11
Feature activation+9.39e-02

Pos logit contributions
acebook+0.289
wagon+0.284
 Wem+0.258
 NETWORK+0.256
 Lith+0.255
Neg logit contributions
usra-0.251
matched-0.240
 Armen-0.232
 honors-0.232
 ovarian-0.216
Token
Token ID198
Feature activation-1.83e-01

Pos logit contributions
usra+0.733
matched+0.701
 honors+0.677
 Armen+0.676
 ovarian+0.623
Neg logit contributions
acebook-0.986
wagon-0.961
 Wem-0.880
 NETWORK-0.871
 Lith-0.865
TokenThe
Token ID464
Feature activation-9.75e-04

Pos logit contributions
usra+0.547
matched+0.523
 honors+0.506
 Armen+0.505
 ovarian+0.468
Neg logit contributions
acebook-0.652
wagon-0.637
 Wem-0.582
 NETWORK-0.577
 Lith-0.573
Token case
Token ID1339
Feature activation-3.39e-01

Pos logit contributions
usra+0.003
matched+0.003
 Armen+0.003
 honors+0.003
 ovarian+0.003
Neg logit contributions
acebook-0.003
wagon-0.003
 Wem-0.003
 NETWORK-0.003
 Lith-0.003
Token began
Token ID2540
Feature activation-3.30e-02

Pos logit contributions
usra+1.122
matched+1.078
 honors+1.052
 Armen+1.046
 ovarian+0.980
Neg logit contributions
acebook-1.093
wagon-1.067
 Wem-0.962
 NETWORK-0.952
 Lith-0.945
Token to
Token ID284
Feature activation-2.17e-01

Pos logit contributions
usra+0.099
matched+0.094
 Armen+0.091
 honors+0.091
 ovarian+0.084
Neg logit contributions
acebook-0.117
wagon-0.115
 Wem-0.105
 NETWORK-0.104
 Lith-0.104
Token unfold
Token ID16631
Feature activation-1.64e-01

Pos logit contributions
usra+0.677
matched+0.647
 Armen+0.630
 honors+0.630
 ovarian+0.589
Neg logit contributions
acebook-0.743
wagon-0.721
 Wem-0.658
 NETWORK-0.648
 Lith-0.645
Token on
Token ID319
Feature activation-2.19e-01

Pos logit contributions
usra+0.493
matched+0.469
 Armen+0.454
 honors+0.453
 ovarian+0.422
Neg logit contributions
acebook-0.578
wagon-0.568
 Wem-0.518
 NETWORK-0.514
 Lith-0.512
Token September
Token ID2693
Feature activation-6.05e-01

Pos logit contributions
usra+0.596
matched+0.567
 Armen+0.549
 honors+0.549
 ovarian+0.505
Neg logit contributions
acebook-0.836
wagon-0.821
 Wem-0.751
 NETWORK-0.745
 Lith-0.741
Token 23
Token ID2242
Feature activation-1.11e-01

Pos logit contributions
usra+1.910
matched+1.859
 Armen+1.816
 honors+1.810
 ovarian+1.678
Neg logit contributions
acebook-2.068
wagon-1.991
 Wem-1.778
 NETWORK-1.760
 Lith-1.728
Token,
Token ID11
Feature activation-2.73e-01

Pos logit contributions
usra+0.328
matched+0.312
 Armen+0.303
 honors+0.302
 ovarian+0.280
Neg logit contributions
acebook-0.400
wagon-0.393
 Wem-0.358
 NETWORK-0.355
 Lith-0.354
Token when
Token ID618
Feature activation-3.90e-01

Pos logit contributions
usra+0.815
matched+0.782
 honors+0.762
 Armen+0.759
 ovarian+0.705
Neg logit contributions
acebook-0.965
wagon-0.944
 Wem-0.855
 NETWORK-0.850
 Lith-0.843
Token our
Token ID674
Feature activation-1.97e-01

Pos logit contributions
usra+0.496
matched+0.478
 honors+0.467
 Armen+0.466
 ovarian+0.436
Neg logit contributions
acebook-0.476
wagon-0.463
 Wem-0.420
 NETWORK-0.413
 Lith-0.410
Token prototype
Token ID14879
Feature activation-2.32e-01

Pos logit contributions
usra+0.625
matched+0.600
 honors+0.587
 Armen+0.586
 ovarian+0.547
Neg logit contributions
acebook-0.663
wagon-0.649
 Wem-0.588
 NETWORK-0.578
 Lith-0.574
Token version
Token ID2196
Feature activation+1.66e-02

Pos logit contributions
usra+0.694
matched+0.667
 honors+0.651
 Armen+0.650
 ovarian+0.605
Neg logit contributions
acebook-0.819
wagon-0.797
 Wem-0.724
 NETWORK-0.717
 Lith-0.710
Token of
Token ID286
Feature activation-1.68e-01

Pos logit contributions
acebook+0.060
wagon+0.059
 Wem+0.054
 NETWORK+0.054
 Lith+0.053
Neg logit contributions
usra-0.048
matched-0.046
 Armen-0.045
 honors-0.045
 ovarian-0.041
Token Arena
Token ID10937
Feature activation+1.52e-01

Pos logit contributions
usra+0.562
matched+0.541
 Armen+0.527
 honors+0.527
 ovarian+0.494
Neg logit contributions
acebook-0.534
wagon-0.521
 Wem-0.469
 NETWORK-0.464
 Lith-0.461
Token and
Token ID290
Feature activation-6.12e-02

Pos logit contributions
acebook+0.528
wagon+0.517
 Wem+0.470
 NETWORK+0.465
 Lith+0.463
Neg logit contributions
usra-0.466
matched-0.446
 Armen-0.432
 honors-0.432
 ovarian-0.402
Token does
Token ID857
Feature activation-9.27e-02

Pos logit contributions
usra+0.196
matched+0.188
 honors+0.183
 Armen+0.183
 ovarian+0.170
Neg logit contributions
acebook-0.204
wagon-0.199
 Wem-0.180
 NETWORK-0.178
 Lith-0.177
Token not
Token ID407
Feature activation+9.07e-02

Pos logit contributions
usra+0.293
matched+0.280
 Armen+0.271
 honors+0.271
 ovarian+0.253
Neg logit contributions
acebook-0.312
wagon-0.307
 Wem-0.277
 NETWORK-0.276
 Lith-0.275
Token describe
Token ID6901
Feature activation-5.27e-02

Pos logit contributions
acebook+0.268
wagon+0.263
 Wem+0.234
 NETWORK+0.233
 Lith+0.231
Neg logit contributions
usra-0.323
matched-0.311
 Armen-0.302
 honors-0.301
 ovarian-0.284
Token completely
Token ID3190
Feature activation+1.87e-01

Pos logit contributions
usra+0.178
matched+0.171
 honors+0.167
 Armen+0.167
 ovarian+0.156
Neg logit contributions
acebook-0.166
wagon-0.162
 Wem-0.146
 NETWORK-0.144
 Lith-0.143
Token what
Token ID644
Feature activation+1.60e-01

Pos logit contributions
acebook+0.561
wagon+0.547
 Wem+0.490
 NETWORK+0.483
 Lith+0.480
Neg logit contributions
usra-0.659
matched-0.634
 Armen-0.618
 honors-0.618
 ovarian-0.581
Token
Token ID198
Feature activation-8.22e-02

Pos logit contributions
acebook+0.284
wagon+0.279
 Wem+0.254
 NETWORK+0.252
 Lith+0.251
Neg logit contributions
usra-0.236
matched-0.225
 honors-0.219
 Armen-0.218
 ovarian-0.203
Token
Token ID198
Feature activation-7.08e-02

Pos logit contributions
usra+0.231
matched+0.221
 Armen+0.214
 honors+0.214
 ovarian+0.197
Neg logit contributions
acebook-0.307
wagon-0.300
 Wem-0.274
 NETWORK-0.272
 Lith-0.270
TokenIn
Token ID818
Feature activation-1.18e-01

Pos logit contributions
usra+0.201
matched+0.191
 Armen+0.185
 honors+0.185
 ovarian+0.171
Neg logit contributions
acebook-0.261
wagon-0.257
 Wem-0.234
 NETWORK-0.233
 Lith-0.232
Token positive
Token ID3967
Feature activation+2.26e-01

Pos logit contributions
usra+0.396
matched+0.383
 honors+0.373
 Armen+0.371
 ovarian+0.348
Neg logit contributions
acebook-0.374
wagon-0.365
 Wem-0.325
 NETWORK-0.324
 Lith-0.318
Token news
Token ID1705
Feature activation-7.44e-03

Pos logit contributions
acebook+0.738
wagon+0.721
 Wem+0.647
 NETWORK+0.644
 Lith+0.637
Neg logit contributions
usra-0.743
matched-0.712
 honors-0.695
 Armen-0.694
 ovarian-0.651
Token,
Token ID11
Feature activation-1.63e-01

Pos logit contributions
usra+0.022
matched+0.021
 Armen+0.020
 honors+0.020
 ovarian+0.019
Neg logit contributions
acebook-0.026
wagon-0.026
 Wem-0.024
 NETWORK-0.023
 Lith-0.023
Token Mitch
Token ID20472
Feature activation-5.17e-03

Pos logit contributions
usra+0.536
matched+0.516
 honors+0.503
 Armen+0.503
 ovarian+0.469
Neg logit contributions
acebook-0.525
wagon-0.514
 Wem-0.461
 NETWORK-0.458
 Lith-0.453
Token Wall
Token ID5007
Feature activation+5.23e-01

Pos logit contributions
usra+0.017
matched+0.016
 Armen+0.016
 honors+0.015
 ovarian+0.014
Neg logit contributions
acebook-0.017
wagon-0.017
 Wem-0.015
 NETWORK-0.015
 Lith-0.015
Tokenis
Token ID271
Feature activation+2.38e-01

Pos logit contributions
acebook+1.772
wagon+1.742
 Wem+1.577
 Lith+1.562
 NETWORK+1.561
Neg logit contributions
usra-1.636
matched-1.559
 Armen-1.520
 honors-1.508
 ovarian-1.414
Token is
Token ID318
Feature activation+4.79e-01

Pos logit contributions
acebook+0.789
wagon+0.778
 Wem+0.702
 NETWORK+0.696
 Lith+0.695
Neg logit contributions
usra-0.760
matched-0.724
 Armen-0.705
 honors-0.704
 ovarian-0.658
Token likely
Token ID1884
Feature activation+2.25e-01

Pos logit contributions
acebook+1.636
wagon+1.608
 Wem+1.458
 NETWORK+1.448
 Lith+1.445
Neg logit contributions
usra-1.486
matched-1.416
 Armen-1.373
 honors-1.372
 ovarian-1.277
Token the
Token ID262
Feature activation-1.73e-01

Pos logit contributions
usra+2.087
matched+1.995
 honors+1.967
 Armen+1.966
 ovarian+1.828
Neg logit contributions
acebook-2.140
wagon-2.086
 Wem-1.881
 NETWORK-1.861
 Lith-1.832
Token cause
Token ID2728
Feature activation+2.04e-01

Pos logit contributions
usra+0.544
matched+0.519
 honors+0.508
 Armen+0.507
 ovarian+0.472
Neg logit contributions
acebook-0.587
wagon-0.574
 Wem-0.519
 NETWORK-0.514
 Lith-0.511
Token of
Token ID286
Feature activation-2.22e-01

Pos logit contributions
acebook+0.733
wagon+0.726
 Wem+0.665
 Lith+0.661
 NETWORK+0.658
Neg logit contributions
usra-0.591
matched-0.558
 honors-0.536
 Armen-0.533
 ovarian-0.501
Token national
Token ID2260
Feature activation-1.15e-01

Pos logit contributions
usra+0.624
matched+0.591
 Armen+0.578
 honors+0.577
 ovarian+0.532
Neg logit contributions
acebook-0.829
wagon-0.812
 Wem-0.741
 NETWORK-0.734
 Lith-0.728
Token liberation
Token ID22256
Feature activation-2.73e-01

Pos logit contributions
usra+0.281
matched+0.265
 honors+0.257
 Armen+0.256
 ovarian+0.233
Neg logit contributions
acebook-0.469
wagon-0.461
 Wem-0.425
 NETWORK-0.421
 Lith-0.418
Token
Token ID1399
Feature activation-7.98e-01

Pos logit contributions
usra+0.839
matched+0.804
 Armen+0.783
 honors+0.782
 ovarian+0.726
Neg logit contributions
acebook-0.947
wagon-0.926
 Wem-0.841
 NETWORK-0.834
 Lith-0.828
Tokenwe
Token ID732
Feature activation-1.08e-01

Pos logit contributions
usra+2.392
matched+2.284
 Armen+2.226
 honors+2.192
zan+2.035
Neg logit contributions
acebook-2.841
wagon-2.730
 Wem-2.522
 NETWORK-2.489
 Lith-2.452
Token must
Token ID1276
Feature activation-5.39e-02

Pos logit contributions
usra+0.306
matched+0.291
 honors+0.281
 Armen+0.281
 ovarian+0.260
Neg logit contributions
acebook-0.402
wagon-0.395
 Wem-0.361
 NETWORK-0.358
 Lith-0.357
Token foil
Token ID25501
Feature activation+4.74e-02

Pos logit contributions
usra+0.176
matched+0.169
 Armen+0.164
 honors+0.164
 ovarian+0.154
Neg logit contributions
acebook-0.176
wagon-0.172
 Wem-0.155
 NETWORK-0.154
 Lith-0.153
Token the
Token ID262
Feature activation-5.11e-02

Pos logit contributions
acebook+0.151
wagon+0.148
 Wem+0.133
 NETWORK+0.132
 Lith+0.132
Neg logit contributions
usra-0.158
matched-0.152
 honors-0.148
 Armen-0.148
 ovarian-0.138
Token expansion
Token ID7118
Feature activation-2.84e-01

Pos logit contributions
usra+0.140
matched+0.132
 Armen+0.129
 honors+0.129
 ovarian+0.119
Neg logit contributions
acebook-0.194
wagon-0.190
 Wem-0.175
 NETWORK-0.173
 Lith-0.172
Token BE
Token ID9348
Feature activation+8.66e-02

Pos logit contributions
usra+0.153
matched+0.147
 Armen+0.143
 honors+0.143
 ovarian+0.133
Neg logit contributions
acebook-0.150
wagon-0.146
 Wem-0.132
 NETWORK-0.130
 Lith-0.130
TokenER
Token ID1137
Feature activation-2.58e-01

Pos logit contributions
acebook+0.241
wagon+0.235
 Wem+0.208
 NETWORK+0.205
 Lith+0.204
Neg logit contributions
usra-0.325
matched-0.314
 Armen-0.306
 honors-0.306
 ovarian-0.289
Token!
Token ID0
Feature activation-6.57e-02

Pos logit contributions
usra+0.839
matched+0.806
 honors+0.787
 Armen+0.783
 ovarian+0.733
Neg logit contributions
acebook-0.848
wagon-0.822
 Wem-0.749
 Lith-0.732
 Transmission-0.730
Token For
Token ID1114
Feature activation+3.17e-02

Pos logit contributions
usra+0.209
matched+0.201
 Armen+0.196
 honors+0.195
 ovarian+0.182
Neg logit contributions
acebook-0.220
wagon-0.214
 Wem-0.194
 NETWORK-0.191
 Lith-0.190
Token a
Token ID257
Feature activation-1.43e-01

Pos logit contributions
acebook+0.103
wagon+0.100
 Wem+0.090
 NETWORK+0.090
 Lith+0.089
Neg logit contributions
usra-0.104
matched-0.100
 Armen-0.098
 honors-0.098
 ovarian-0.091
Token mid
Token ID3095
Feature activation-7.84e-01

Pos logit contributions
usra+0.450
matched+0.431
 Armen+0.419
 honors+0.418
 ovarian+0.390
Neg logit contributions
acebook-0.484
wagon-0.472
 Wem-0.428
 NETWORK-0.423
 Lith-0.421
Token-
Token ID12
Feature activation+1.72e-01

Pos logit contributions
usra+2.237
matched+2.144
 honors+2.049
 Armen+2.040
 ovarian+1.903
Neg logit contributions
acebook-2.860
wagon-2.801
 Wem-2.566
 NETWORK-2.542
 Lith-2.523
Tokenstrength
Token ID41402
Feature activation-5.31e-02

Pos logit contributions
acebook+0.626
wagon+0.619
 Wem+0.561
 NETWORK+0.557
 Lith+0.556
Neg logit contributions
usra-0.494
matched-0.466
 Armen-0.457
 honors-0.456
 ovarian-0.421
Token As
Token ID1081
Feature activation-1.18e-01

Pos logit contributions
usra+0.176
matched+0.169
 honors+0.164
 Armen+0.164
 ovarian+0.153
Neg logit contributions
acebook-0.171
wagon-0.168
 Wem-0.151
 NETWORK-0.150
 Lith-0.149
Tokenahi
Token ID32810
Feature activation-5.31e-02

Pos logit contributions
usra+0.352
matched+0.337
 Armen+0.327
 honors+0.326
 ovarian+0.302
Neg logit contributions
acebook-0.421
wagon-0.412
 Wem-0.376
 NETWORK-0.373
 Lith-0.370
Token dec
Token ID875
Feature activation-4.57e-02

Pos logit contributions
usra+0.167
matched+0.160
 honors+0.155
 Armen+0.155
 ovarian+0.145
Neg logit contributions
acebook-0.180
wagon-0.176
 Wem-0.160
 NETWORK-0.158
 Lith-0.158
Token at
Token ID379
Feature activation-1.13e-01

Pos logit contributions
acebook+1.357
wagon+1.340
 Wem+1.202
 NETWORK+1.196
 Lith+1.191
Neg logit contributions
usra-1.370
matched-1.309
 Armen-1.266
 honors-1.258
 ovarian-1.190
Token McCoy
Token ID28901
Feature activation+7.63e-02

Pos logit contributions
usra+0.378
matched+0.363
 honors+0.353
 Armen+0.353
 ovarian+0.330
Neg logit contributions
acebook-0.363
wagon-0.355
 Wem-0.320
 NETWORK-0.317
 Lith-0.315
Token has
Token ID468
Feature activation-1.13e-01

Pos logit contributions
acebook+0.253
wagon+0.251
 Wem+0.224
 Lith+0.223
 NETWORK+0.223
Neg logit contributions
usra-0.245
matched-0.234
 honors-0.226
 Armen-0.225
��-0.212
Token a
Token ID257
Feature activation+1.05e-01

Pos logit contributions
usra+0.378
matched+0.363
 honors+0.352
 Armen+0.352
 ovarian+0.330
Neg logit contributions
acebook-0.361
wagon-0.353
 Wem-0.318
 NETWORK-0.315
 Lith-0.313
Token fo
Token ID11511
Feature activation+1.00e-01

Pos logit contributions
acebook+0.353
wagon+0.347
 Wem+0.315
 NETWORK+0.312
 Lith+0.311
Neg logit contributions
usra-0.332
matched-0.318
 honors-0.308
 Armen-0.308
 ovarian-0.287
Tokenos
Token ID418
Feature activation-1.10e+00

Pos logit contributions
acebook+0.343
wagon+0.336
 Wem+0.305
 NETWORK+0.303
 Lith+0.301
Neg logit contributions
usra-0.313
matched-0.299
 Armen-0.291
 honors-0.290
 ovarian-0.270
Tokenball
Token ID1894
Feature activation+5.63e-02

Pos logit contributions
usra+2.363
matched+2.243
 Armen+2.130
 honors+2.130
 ovarian+1.942
Neg logit contributions
acebook-4.800
wagon-4.632
 Wem-4.364
 NETWORK-4.350
 Lith-4.314
Token table
Token ID3084
Feature activation-1.06e-01

Pos logit contributions
acebook+0.193
wagon+0.189
 Wem+0.171
 NETWORK+0.170
 Lith+0.169
Neg logit contributions
usra-0.175
matched-0.168
 Armen-0.162
 honors-0.162
 ovarian-0.151
Token,
Token ID11
Feature activation+3.79e-01

Pos logit contributions
usra+0.330
matched+0.317
 honors+0.307
 Armen+0.307
 ovarian+0.285
Neg logit contributions
acebook-0.362
wagon-0.354
 Wem-0.322
 NETWORK-0.318
 Lith-0.317
Token and
Token ID290
Feature activation+3.67e-01

Pos logit contributions
acebook+1.208
wagon+1.184
 Wem+1.064
 NETWORK+1.050
 Lith+1.050
Neg logit contributions
usra-1.267
matched-1.208
 Armen-1.172
 honors-1.171
��-1.103
Token it
Token ID340
Feature activation+2.09e-01

Pos logit contributions
acebook+1.169
wagon+1.147
 Wem+1.038
 NETWORK+1.026
 Lith+1.023
Neg logit contributions
usra-1.227
matched-1.171
 honors-1.131
 Armen-1.130
��-1.066
Token recipes
Token ID14296
Feature activation-2.45e-01

Pos logit contributions
acebook+1.250
wagon+1.226
 Wem+1.113
 NETWORK+1.105
 Lith+1.103
Neg logit contributions
usra-1.123
matched-1.076
 Armen-1.036
 honors-1.032
��-0.966
Token follow
Token ID1061
Feature activation+1.85e-01

Pos logit contributions
usra+0.805
matched+0.772
 Armen+0.751
 honors+0.750
 ovarian+0.702
Neg logit contributions
acebook-0.793
wagon-0.776
 Wem-0.700
 NETWORK-0.694
 Lith-0.690
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
acebook+0.582
wagon+0.570
 Wem+0.513
 NETWORK+0.508
 Lith+0.506
Neg logit contributions
usra-0.626
matched-0.599
 Armen-0.583
 honors-0.583
 ovarian-0.547
Token With
Token ID2080
Feature activation-1.12e-02

Pos logit contributions
acebook+0.411
wagon+0.402
 Wem+0.364
 NETWORK+0.361
 Lith+0.359
Neg logit contributions
usra-0.387
matched-0.371
 Armen-0.360
 honors-0.360
 ovarian-0.336
Token the
Token ID262
Feature activation-1.10e-01

Pos logit contributions
usra+0.037
matched+0.035
 honors+0.035
 Armen+0.035
 ovarian+0.032
Neg logit contributions
acebook-0.036
wagon-0.035
 Wem-0.032
 NETWORK-0.031
 Lith-0.031
Token exception
Token ID6631
Feature activation-7.81e-01

Pos logit contributions
usra+0.334
matched+0.320
 Armen+0.309
 honors+0.309
 ovarian+0.287
Neg logit contributions
acebook-0.384
wagon-0.376
 Wem-0.342
 NETWORK-0.339
 Lith-0.338
Token of
Token ID286
Feature activation-1.12e-01

Pos logit contributions
usra+2.106
matched+2.000
 honors+1.932
 Armen+1.930
 ovarian+1.775
Neg logit contributions
acebook-2.997
wagon-2.942
 Wem-2.699
 NETWORK-2.678
 Lith-2.669
Token the
Token ID262
Feature activation-2.61e-01

Pos logit contributions
usra+0.373
matched+0.358
 Armen+0.349
 honors+0.349
 ovarian+0.326
Neg logit contributions
acebook-0.360
wagon-0.352
 Wem-0.317
 NETWORK-0.314
 Lith-0.312
Token first
Token ID717
Feature activation-3.19e-01

Pos logit contributions
usra+0.797
matched+0.762
 Armen+0.739
 honors+0.739
 ovarian+0.687
Neg logit contributions
acebook-0.906
wagon-0.887
 Wem-0.806
 NETWORK-0.799
 Lith-0.795
Token recipe
Token ID8364
Feature activation-8.21e-01

Pos logit contributions
usra+0.994
matched+0.950
 honors+0.927
 Armen+0.925
 ovarian+0.863
Neg logit contributions
acebook-1.095
wagon-1.069
 Wem-0.968
 NETWORK-0.960
 Lith-0.953
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
usra+2.390
matched+2.300
 honors+2.249
 Armen+2.238
 ovarian+2.071
Neg logit contributions
acebook-2.955
wagon-2.885
 Wem-2.614
 NETWORK-2.584
 Lith-2.560
Tokenpass
Token ID6603
Feature activation-1.41e-01

Pos logit contributions
acebook+0.348
wagon+0.344
 Wem+0.310
 NETWORK+0.306
 Lith+0.304
Neg logit contributions
usra-0.335
matched-0.318
 Armen-0.311
 honors-0.309
 ovarian-0.291
Token measures
Token ID5260
Feature activation+2.08e-01

Pos logit contributions
usra+0.427
matched+0.409
 honors+0.400
 Armen+0.397
 ovarian+0.370
Neg logit contributions
acebook-0.494
wagon-0.483
 Wem-0.438
 NETWORK-0.435
 Lith-0.432
Token Congress
Token ID3162
Feature activation+4.36e-02

Pos logit contributions
acebook+0.700
wagon+0.684
 Wem+0.625
 Lith+0.619
 NETWORK+0.618
Neg logit contributions
usra-0.655
matched-0.624
 Armen-0.603
 honors-0.603
 ovarian-0.565
Token will
Token ID481
Feature activation-1.37e-01

Pos logit contributions
acebook+0.148
wagon+0.145
 Wem+0.132
 NETWORK+0.131
 Lith+0.131
Neg logit contributions
usra-0.136
matched-0.129
 Armen-0.125
 honors-0.124
 ovarian-0.117
Token take
Token ID1011
Feature activation-4.30e-02

Pos logit contributions
usra+0.454
matched+0.434
 Armen+0.422
 honors+0.420
 ovarian+0.393
Neg logit contributions
acebook-0.441
wagon-0.434
 Wem-0.391
 NETWORK-0.388
 Lith-0.387
Token up
Token ID510
Feature activation-1.01e+00

Pos logit contributions
usra+0.134
matched+0.127
 Armen+0.124
 honors+0.123
 ovarian+0.115
Neg logit contributions
acebook-0.146
wagon-0.144
 Wem-0.131
 NETWORK-0.130
 Lith-0.130
Token when
Token ID618
Feature activation+4.61e-02

Pos logit contributions
usra+2.908
matched+2.840
 honors+2.765
 Armen+2.748
 ovarian+2.535
Neg logit contributions
acebook-3.670
wagon-3.569
 Wem-3.246
 NETWORK-3.209
 Transmission-3.186
Token it
Token ID340
Feature activation-5.19e-02

Pos logit contributions
acebook+0.143
wagon+0.140
 Wem+0.126
 Lith+0.125
 NETWORK+0.125
Neg logit contributions
usra-0.158
matched-0.151
 Armen-0.147
 honors-0.147
 ovarian-0.138
Token returns
Token ID5860
Feature activation+2.16e-02

Pos logit contributions
usra+0.157
matched+0.149
 Armen+0.145
 honors+0.144
 ovarian+0.134
Neg logit contributions
acebook-0.182
wagon-0.178
 Wem-0.163
 NETWORK-0.161
 Lith-0.161
Token on
Token ID319
Feature activation-2.04e-01

Pos logit contributions
acebook+0.075
wagon+0.075
 Wem+0.068
 Lith+0.068
 NETWORK+0.068
Neg logit contributions
usra-0.065
matched-0.061
 Armen-0.060
 honors-0.059
 ovarian-0.055
Token Sept
Token ID2362
Feature activation-3.47e-01

Pos logit contributions
usra+0.571
matched+0.544
 honors+0.527
 Armen+0.526
 ovarian+0.485
Neg logit contributions
acebook-0.764
wagon-0.749
 Wem-0.685
 NETWORK-0.680
 Lith-0.676