TOP ACTIVATIONS
MAX = 2.230

mission objectives may go much farther than just preparing for terrorists
OTH IN M EST AND SHAR AN UPDATE : 05 20
ella Vol pe . At worse , it insults them .
really prepared me for how closely connected everything is , how
related skills . Springfield , VA : US Department of Transportation
The group also attempted ( un successfully ) to spray anth
. The ( un named ) parent spoke to
you re looking closely , it turns into something
in other forms of physical exercise , they are also generally
s lab , then applied state - space analysis ,
if granted will do far more damage than good to the
to reflect a move being applied and subsequently un - app
Bron cos coach Vance Joseph said Monday that the
showing when , and how intensely , each set of neurons
> , which points to uniquely - owned data that has
ercise . High - intensity exercise de ple tes glucose and
. New research has gone further , exposing how American capitalism
how this pr imate was uniquely adapted to its environment ,
everywhere . THE PUR GE D ATES * Spread
no interest in seeking a patent for the Love t ron

MIN ACTIVATIONS
MIN = -3.018

past . With Kron stadt and M akh no
on Him C ull in an was positioned stage
Medline | ISI Sent se , M ., Sch
Republican victory . Sent iment about how to proceed
Wikimedia Commons . <|endoftext|> T ucker Carlson laid out a number
the United States Conference of Catholic B ishops ( US CC
, more than double its original goal of $ 250 k
uncertainty is not how their original love story went . But
anti - street harassment organization Holl ab ack showed that 90
al . ( 2002 ); Hoff ert & Cove y (
Google Scholar Ol we us , D .
in New Jersey by Richard Holl ings head . He got
Eventually though they changed their mind and despite the risk they
common with than class war anarch o - commun ists like
team s third straight in pads , that focused
The @ T ucker Carl son opening statement about
replacing Confederate General Edmund Kirby Smith .[ 7 ]
: Clinton staff are ' big gest a -- holes in
A US 16 Steele Von Hoff ( Team Chip otle )
, which would have qu elled demand for Argentine debt ;

INTERVAL 0.918 - 2.230
CONTAINS 2.434%

4 of an Eastern Conference playoff series , said on the
. ( I am talking of elegance in the mathematical
Gram mer 2004 Larry David 2004 Matt
happening in the vent ral sensory motor cortex ( v S
. This was achieved by repeatedly restart ing the engine in

INTERVAL -0.394 - 0.918
CONTAINS 80.077%

in America . The post in which that account
come to watch , but on this occasion he had decided
burned arm T ori and family and a friend
earing of the hijab or veil , the school
, run the power off command and then i w config

INTERVAL -1.706 - -0.394
CONTAINS 17.439%

the film , I pushed him every single play . I
the upcoming revival of a historic Broadway musical has gone missing
old Naval Air Station in South We ym outh . This
. Let them know in advance that their characters
in a world where those who shout the loud est are

INTERVAL -3.018 - -1.706
CONTAINS 0.049%

unsupported on your device Media caption A drone - camera was
Photo Pitt sburgh The visceral
Republican victory . Sent iment about how to proceed
our daily newsletter Upgrade your inbox and get our Daily Dispatch
on Wednesday on efforts to cool down a plutonium - fuel
Token mission
Token ID4365
Feature activation-9.07e-01

Pos logit contributions
AMS+1.432
bara+1.406
Keefe+1.377
enhagen+1.358
ACTED+1.343
Neg logit contributions
��-1.354
adelphia-1.311
cens-1.294
aries-1.199
buster-1.194
Token objectives
Token ID15221
Feature activation-5.78e-01

Pos logit contributions
��+2.564
adelphia+2.491
cens+2.435
aries+2.340
buster+2.264
Neg logit contributions
AMS-3.180
bara-3.081
enhagen-3.027
Keefe-3.019
ACTED-3.013
Token may
Token ID743
Feature activation-1.35e-01

Pos logit contributions
��+1.561
adelphia+1.493
cens+1.481
aries+1.375
buster+1.354
Neg logit contributions
AMS-2.124
bara-2.084
Keefe-2.034
enhagen-2.034
ACTED-2.016
Token go
Token ID467
Feature activation+3.74e-01

Pos logit contributions
��+0.424
adelphia+0.410
cens+0.406
aries+0.376
buster+0.374
Neg logit contributions
AMS-0.433
bara-0.426
Keefe-0.414
enhagen-0.413
ACTED-0.408
Token much
Token ID881
Feature activation+8.08e-01

Pos logit contributions
AMS+1.194
bara+1.176
enhagen+1.142
Keefe+1.142
ACTED+1.122
Neg logit contributions
��-1.187
adelphia-1.150
cens-1.138
aries-1.053
buster-1.046
Token farther
Token ID18485
Feature activation+2.23e+00

Pos logit contributions
AMS+2.292
bara+2.264
Keefe+2.191
enhagen+2.191
ACTED+2.122
Neg logit contributions
��-2.793
adelphia-2.736
cens-2.697
aries-2.530
buster-2.504
Token than
Token ID621
Feature activation+4.46e-01

Pos logit contributions
AMS+5.576
bara+5.436
unning+5.205
Keefe+5.169
enhagen+5.168
Neg logit contributions
��-8.048
adelphia-7.913
cens-7.677
buster-7.279
taboola-7.220
Token just
Token ID655
Feature activation-1.43e-01

Pos logit contributions
AMS+1.508
bara+1.480
Keefe+1.446
enhagen+1.441
ACTED+1.416
Neg logit contributions
��-1.339
adelphia-1.287
cens-1.277
buster-1.176
aries-1.164
Token preparing
Token ID10629
Feature activation-5.52e-01

Pos logit contributions
��+0.428
adelphia+0.413
cens+0.409
aries+0.380
buster+0.376
Neg logit contributions
AMS-0.485
bara-0.476
Keefe-0.465
enhagen-0.463
ACTED-0.458
Token for
Token ID329
Feature activation-5.76e-01

Pos logit contributions
��+1.573
adelphia+1.523
cens+1.510
aries+1.419
oslov+1.391
Neg logit contributions
AMS-1.916
bara-1.888
Keefe-1.851
enhagen-1.839
ACTED-1.816
Token terrorists
Token ID10509
Feature activation+5.35e-01

Pos logit contributions
��+1.652
adelphia+1.593
cens+1.579
aries+1.462
buster+1.447
Neg logit contributions
AMS-2.013
bara-1.977
Keefe-1.933
enhagen-1.925
ACTED-1.908
TokenOTH
Token ID26946
Feature activation+2.60e-01

Pos logit contributions
AMS+0.882
bara+0.859
Keefe+0.838
enhagen+0.834
ACTED+0.831
Neg logit contributions
��-0.969
adelphia-0.939
cens-0.926
aries-0.868
buster-0.862
Token IN
Token ID3268
Feature activation+2.73e-01

Pos logit contributions
AMS+0.905
bara+0.875
Keefe+0.860
ACTED+0.854
enhagen+0.850
Neg logit contributions
��-0.762
adelphia-0.734
cens-0.720
buster-0.663
aries-0.661
Token M
Token ID337
Feature activation+3.96e-01

Pos logit contributions
AMS+0.894
bara+0.856
ACTED+0.843
Keefe+0.841
enhagen+0.828
Neg logit contributions
��-0.864
adelphia-0.834
cens-0.820
buster-0.759
aries-0.754
TokenEST
Token ID6465
Feature activation+6.62e-01

Pos logit contributions
AMS+1.074
bara+1.026
Keefe+0.999
ACTED+0.997
enhagen+0.992
Neg logit contributions
��-1.462
adelphia-1.424
cens-1.412
buster-1.325
oslov-1.313
Token AND
Token ID5357
Feature activation+1.64e-01

Pos logit contributions
AMS+2.142
bara+2.011
ACTED+2.006
Keefe+1.994
enhagen+1.974
Neg logit contributions
��-2.128
adelphia-2.048
cens-2.021
buster-1.887
oslov-1.861
Token SHAR
Token ID39225
Feature activation+2.19e+00

Pos logit contributions
AMS+0.581
bara+0.569
Keefe+0.557
enhagen+0.554
ACTED+0.550
Neg logit contributions
��-0.466
adelphia-0.448
cens-0.443
aries-0.408
buster-0.406
TokenAN
Token ID1565
Feature activation+8.27e-01

Pos logit contributions
AMS+5.721
ACTED+5.212
Keefe+5.177
bara+5.107
RAY+5.040
Neg logit contributions
��-8.391
adelphia-8.004
cens-7.927
emia-7.482
oslov-7.455
Token UPDATE
Token ID35717
Feature activation+5.20e-01

Pos logit contributions
AMS+2.851
bara+2.728
ACTED+2.693
Keefe+2.654
enhagen+2.633
Neg logit contributions
��-2.473
adelphia-2.390
cens-2.364
buster-2.146
oslov-2.133
Token:
Token ID25
Feature activation-9.56e-02

Pos logit contributions
AMS+1.797
bara+1.722
Keefe+1.697
ACTED+1.693
enhagen+1.681
Neg logit contributions
��-1.541
adelphia-1.481
cens-1.448
buster-1.340
oslov-1.333
Token 05
Token ID8870
Feature activation+2.66e-01

Pos logit contributions
��+0.252
adelphia+0.242
cens+0.240
aries+0.219
buster+0.217
Neg logit contributions
AMS-0.357
bara-0.351
Keefe-0.344
enhagen-0.343
ACTED-0.339
Token20
Token ID1238
Feature activation+6.50e-01

Pos logit contributions
AMS+0.652
bara+0.632
Keefe+0.611
enhagen+0.607
ACTED+0.600
Neg logit contributions
��-1.048
adelphia-1.016
cens-1.007
aries-0.951
buster-0.947
Tokenella
Token ID12627
Feature activation+7.42e-01

Pos logit contributions
��+0.044
adelphia+0.042
cens+0.042
aries+0.039
buster+0.039
Neg logit contributions
AMS-0.046
bara-0.045
Keefe-0.044
enhagen-0.044
ACTED-0.043
Token Vol
Token ID4709
Feature activation-6.73e-01

Pos logit contributions
AMS+3.451
bara+3.427
Keefe+3.379
ACTED+3.320
unning+3.313
Neg logit contributions
��-1.294
adelphia-1.178
cens-1.140
aries-0.959
taboola-0.948
Tokenpe
Token ID431
Feature activation-1.02e-01

Pos logit contributions
adelphia+1.782
��+1.750
cens+1.743
buster+1.611
oslov+1.575
Neg logit contributions
AMS-2.510
enhagen-2.382
bara-2.350
ACTED-2.342
Keefe-2.319
Token.
Token ID13
Feature activation+5.10e-02

Pos logit contributions
��+0.302
adelphia+0.291
cens+0.289
aries+0.267
buster+0.265
Neg logit contributions
AMS-0.350
bara-0.344
Keefe-0.336
enhagen-0.335
ACTED-0.331
Token At
Token ID1629
Feature activation+1.94e-01

Pos logit contributions
AMS+0.183
bara+0.180
Keefe+0.177
enhagen+0.175
ACTED+0.173
Neg logit contributions
��-0.142
adelphia-0.137
cens-0.135
aries-0.124
buster-0.123
Token worse
Token ID4785
Feature activation+2.15e+00

Pos logit contributions
AMS+0.741
bara+0.736
Keefe+0.722
enhagen+0.710
ACTED+0.703
Neg logit contributions
��-0.496
adelphia-0.476
cens-0.468
aries-0.425
oslov-0.424
Token,
Token ID11
Feature activation+3.38e-01

Pos logit contributions
AMS+6.220
bara+6.094
Keefe+5.926
enhagen+5.891
unning+5.878
Neg logit contributions
��-6.907
adelphia-6.642
cens-6.517
oslov-6.144
taboola-6.050
Token it
Token ID340
Feature activation+7.26e-01

Pos logit contributions
AMS+1.115
bara+1.100
Keefe+1.071
enhagen+1.057
ACTED+1.049
Neg logit contributions
��-1.047
adelphia-1.007
cens-0.990
oslov-0.915
buster-0.915
Token insults
Token ID27819
Feature activation+2.21e-02

Pos logit contributions
AMS+2.319
bara+2.302
Keefe+2.210
enhagen+2.206
unning+2.182
Neg logit contributions
��-2.309
adelphia-2.211
cens-2.163
buster-1.991
oslov-1.981
Token them
Token ID606
Feature activation-2.62e-01

Pos logit contributions
AMS+0.075
bara+0.074
Keefe+0.072
enhagen+0.072
ACTED+0.071
Neg logit contributions
��-0.065
adelphia-0.063
cens-0.062
aries-0.057
buster-0.057
Token.
Token ID13
Feature activation-5.48e-03

Pos logit contributions
��+0.788
adelphia+0.759
cens+0.747
aries+0.688
buster+0.686
Neg logit contributions
AMS-0.885
bara-0.873
enhagen-0.848
Keefe-0.846
ACTED-0.836
Token really
Token ID1107
Feature activation-3.37e-01

Pos logit contributions
��+0.012
adelphia+0.012
cens+0.012
aries+0.011
buster+0.011
Neg logit contributions
AMS-0.014
bara-0.013
Keefe-0.013
enhagen-0.013
ACTED-0.013
Token prepared
Token ID5597
Feature activation-3.71e-02

Pos logit contributions
��+0.985
adelphia+0.956
cens+0.946
aries+0.885
buster+0.875
Neg logit contributions
AMS-1.150
bara-1.129
enhagen-1.106
Keefe-1.104
ACTED-1.092
Token me
Token ID502
Feature activation-3.20e-01

Pos logit contributions
��+0.103
adelphia+0.099
cens+0.098
aries+0.090
buster+0.089
Neg logit contributions
AMS-0.134
bara-0.132
Keefe-0.128
enhagen-0.128
ACTED-0.127
Token for
Token ID329
Feature activation-4.72e-01

Pos logit contributions
��+0.977
adelphia+0.948
cens+0.939
aries+0.875
buster+0.866
Neg logit contributions
AMS-1.060
bara-1.038
Keefe-1.015
enhagen-1.011
ACTED-0.999
Token how
Token ID703
Feature activation+5.80e-01

Pos logit contributions
��+1.381
adelphia+1.336
cens+1.326
aries+1.228
buster+1.210
Neg logit contributions
AMS-1.615
bara-1.582
Keefe-1.551
enhagen-1.548
ACTED-1.534
Token closely
Token ID7173
Feature activation+2.14e+00

Pos logit contributions
AMS+1.921
bara+1.898
Keefe+1.832
enhagen+1.817
ACTED+1.807
Neg logit contributions
��-1.772
adelphia-1.707
cens-1.681
buster-1.556
oslov-1.546
Token connected
Token ID5884
Feature activation+5.02e-01

Pos logit contributions
AMS+6.546
bara+6.446
Keefe+6.204
enhagen+6.167
ACTED+6.165
Neg logit contributions
��-6.666
adelphia-6.389
cens-6.155
buster-5.740
oslov-5.712
Token everything
Token ID2279
Feature activation+5.68e-01

Pos logit contributions
AMS+1.682
bara+1.664
Keefe+1.602
enhagen+1.601
ACTED+1.582
Neg logit contributions
��-1.524
adelphia-1.459
cens-1.436
buster-1.323
aries-1.312
Token is
Token ID318
Feature activation+5.62e-02

Pos logit contributions
AMS+1.859
bara+1.836
Keefe+1.780
enhagen+1.772
unning+1.756
Neg logit contributions
��-1.776
adelphia-1.683
cens-1.659
buster-1.526
aries-1.521
Token,
Token ID11
Feature activation-1.74e-01

Pos logit contributions
AMS+0.168
bara+0.165
Keefe+0.161
enhagen+0.160
ACTED+0.158
Neg logit contributions
��-0.190
adelphia-0.184
cens-0.182
aries-0.170
buster-0.169
Token how
Token ID703
Feature activation+5.84e-01

Pos logit contributions
��+0.483
adelphia+0.465
cens+0.461
aries+0.425
buster+0.420
Neg logit contributions
AMS-0.625
bara-0.614
Keefe-0.601
enhagen-0.600
ACTED-0.593
Token related
Token ID3519
Feature activation+8.01e-01

Pos logit contributions
AMS+0.659
bara+0.645
Keefe+0.627
enhagen+0.622
unning+0.617
Neg logit contributions
��-0.668
adelphia-0.645
cens-0.633
aries-0.590
buster-0.588
Token skills
Token ID4678
Feature activation+1.23e-01

Pos logit contributions
AMS+2.471
bara+2.428
Keefe+2.349
enhagen+2.314
unning+2.309
Neg logit contributions
��-2.626
adelphia-2.557
cens-2.512
aries-2.326
ipel-2.317
Token.
Token ID13
Feature activation+3.15e-01

Pos logit contributions
AMS+0.425
bara+0.417
Keefe+0.408
enhagen+0.406
unning+0.400
Neg logit contributions
��-0.363
adelphia-0.349
cens-0.344
aries-0.317
buster-0.316
Token Springfield
Token ID27874
Feature activation-6.02e-01

Pos logit contributions
AMS+1.108
bara+1.078
Keefe+1.056
ACTED+1.043
enhagen+1.040
Neg logit contributions
��-0.906
adelphia-0.870
cens-0.860
buster-0.791
aries-0.789
Token,
Token ID11
Feature activation+1.11e+00

Pos logit contributions
��+1.690
adelphia+1.628
cens+1.610
aries+1.483
buster+1.471
Neg logit contributions
AMS-2.143
bara-2.108
Keefe-2.060
enhagen-2.054
ACTED-2.031
Token VA
Token ID13753
Feature activation+2.13e+00

Pos logit contributions
AMS+3.692
ACTED+3.468
Keefe+3.457
bara+3.431
RAY+3.340
Neg logit contributions
��-3.313
adelphia-3.223
cens-3.128
ipel-2.953
aries-2.942
Token:
Token ID25
Feature activation+1.23e+00

Pos logit contributions
AMS+5.940
bara+5.540
Keefe+5.466
ACTED+5.343
unning+5.252
Neg logit contributions
��-7.498
cens-6.823
adelphia-6.748
oslov-6.400
��-6.400
Token US
Token ID1294
Feature activation+3.83e-01

Pos logit contributions
AMS+4.387
bara+4.120
Keefe+4.094
ACTED+4.088
enhagen+3.973
Neg logit contributions
��-3.485
adelphia-3.313
cens-3.279
ipel-3.072
taboola-3.009
Token Department
Token ID2732
Feature activation+5.14e-01

Pos logit contributions
AMS+1.079
bara+1.044
Keefe+1.010
ACTED+0.999
enhagen+0.998
Neg logit contributions
��-1.369
adelphia-1.334
cens-1.316
aries-1.237
buster-1.236
Token of
Token ID286
Feature activation-5.16e-01

Pos logit contributions
AMS+1.585
bara+1.554
Keefe+1.515
enhagen+1.475
ACTED+1.474
Neg logit contributions
��-1.712
adelphia-1.644
cens-1.615
aries-1.500
buster-1.494
Token Transportation
Token ID15198
Feature activation+4.88e-01

Pos logit contributions
��+1.680
adelphia+1.630
cens+1.615
aries+1.516
oslov+1.499
Neg logit contributions
AMS-1.597
bara-1.567
enhagen-1.527
Keefe-1.523
ACTED-1.495
Token The
Token ID383
Feature activation+5.15e-01

Pos logit contributions
AMS+1.387
bara+1.356
Keefe+1.332
enhagen+1.305
ACTED+1.303
Neg logit contributions
��-1.156
adelphia-1.108
cens-1.081
aries-0.997
buster-0.989
Token group
Token ID1448
Feature activation-2.21e-01

Pos logit contributions
AMS+1.755
bara+1.735
Keefe+1.682
enhagen+1.681
ACTED+1.646
Neg logit contributions
��-1.523
adelphia-1.473
cens-1.434
buster-1.324
aries-1.322
Token also
Token ID635
Feature activation-2.39e-01

Pos logit contributions
��+0.667
adelphia+0.645
cens+0.639
aries+0.593
buster+0.588
Neg logit contributions
AMS-0.737
bara-0.723
Keefe-0.707
enhagen-0.705
ACTED-0.697
Token attempted
Token ID7482
Feature activation+4.52e-01

Pos logit contributions
��+0.694
adelphia+0.670
cens+0.664
aries+0.615
buster+0.608
Neg logit contributions
AMS-0.828
bara-0.812
Keefe-0.796
enhagen-0.793
ACTED-0.785
Token (
Token ID357
Feature activation+1.30e+00

Pos logit contributions
AMS+1.076
bara+1.058
Keefe+1.016
enhagen+1.007
ACTED+0.987
Neg logit contributions
��-1.791
adelphia-1.750
cens-1.733
aries-1.632
buster-1.625
Tokenun
Token ID403
Feature activation+2.07e+00

Pos logit contributions
AMS+3.994
bara+3.934
Keefe+3.836
enhagen+3.747
unning+3.707
Neg logit contributions
��-4.277
adelphia-4.153
cens-3.852
aries-3.747
 Gutenberg-3.741
Tokensuccessfully
Token ID37351
Feature activation+8.14e-01

Pos logit contributions
bara+2.273
AMS+2.266
Keefe+2.190
enhagen+1.976
likely+1.969
Neg logit contributions
��-10.406
adelphia-10.217
 Ragnarok-9.798
taboola-9.779
 Gutenberg-9.749
Token)
Token ID8
Feature activation+6.56e-01

Pos logit contributions
AMS+1.763
bara+1.724
Keefe+1.660
enhagen+1.655
ACTED+1.642
Neg logit contributions
��-3.341
adelphia-3.327
cens-3.224
aries-3.070
 Gutenberg-3.055
Token to
Token ID284
Feature activation+4.50e-01

Pos logit contributions
AMS+1.471
bara+1.467
Keefe+1.407
enhagen+1.380
ACTED+1.352
Neg logit contributions
��-2.661
adelphia-2.623
cens-2.585
aries-2.443
buster-2.428
Token spray
Token ID11662
Feature activation+2.31e-01

Pos logit contributions
AMS+1.458
bara+1.451
Keefe+1.398
enhagen+1.388
unning+1.376
Neg logit contributions
��-1.392
adelphia-1.343
cens-1.327
aries-1.229
oslov-1.213
Token anth
Token ID26794
Feature activation+3.69e-01

Pos logit contributions
AMS+0.745
bara+0.736
Keefe+0.712
enhagen+0.707
ACTED+0.699
Neg logit contributions
��-0.726
adelphia-0.701
cens-0.693
aries-0.640
buster-0.634
Token.
Token ID13
Feature activation+7.07e-03

Pos logit contributions
AMS+0.979
bara+0.972
enhagen+0.940
Keefe+0.940
ACTED+0.930
Neg logit contributions
��-0.835
adelphia-0.806
cens-0.791
oslov-0.729
aries-0.729
Token
Token ID198
Feature activation-3.22e-01

Pos logit contributions
AMS+0.024
bara+0.024
Keefe+0.023
enhagen+0.023
ACTED+0.023
Neg logit contributions
��-0.021
adelphia-0.020
cens-0.020
aries-0.019
buster-0.018
Token
Token ID198
Feature activation+1.66e-01

Pos logit contributions
��+0.778
adelphia+0.757
cens+0.753
aries+0.690
buster+0.684
Neg logit contributions
AMS-1.255
bara-1.238
enhagen-1.229
Keefe-1.208
ACTED-1.197
TokenThe
Token ID464
Feature activation+5.42e-02

Pos logit contributions
AMS+0.470
bara+0.459
Keefe+0.448
enhagen+0.440
ACTED+0.438
Neg logit contributions
��-0.593
adelphia-0.574
cens-0.568
aries-0.534
buster-0.530
Token (
Token ID357
Feature activation+8.45e-01

Pos logit contributions
AMS+0.195
bara+0.193
Keefe+0.189
enhagen+0.188
ACTED+0.185
Neg logit contributions
��-0.150
adelphia-0.144
cens-0.142
aries-0.131
buster-0.130
Tokenun
Token ID403
Feature activation+2.04e+00

Pos logit contributions
AMS+2.643
bara+2.592
Keefe+2.539
unning+2.474
ACTED+2.471
Neg logit contributions
��-2.757
adelphia-2.659
cens-2.539
aries-2.425
oslov-2.425
Tokennamed
Token ID13190
Feature activation-6.70e-01

Pos logit contributions
bara+6.890
AMS+6.837
Keefe+6.672
unning+6.553
enhagen+6.456
Neg logit contributions
��-5.842
adelphia-5.424
 Ragnarok-5.115
oslov-4.984
 Homo-4.954
Token)
Token ID8
Feature activation+1.01e-01

Pos logit contributions
��+2.526
adelphia+2.454
cens+2.452
aries+2.305
buster+2.294
Neg logit contributions
AMS-1.735
bara-1.681
enhagen-1.625
Keefe-1.620
ACTED-1.591
Token parent
Token ID2560
Feature activation+3.64e-01

Pos logit contributions
AMS+0.371
bara+0.365
Keefe+0.359
enhagen+0.355
ACTED+0.352
Neg logit contributions
��-0.274
adelphia-0.262
cens-0.257
aries-0.237
buster-0.235
Token spoke
Token ID5158
Feature activation+3.30e-01

Pos logit contributions
AMS+1.190
bara+1.174
Keefe+1.141
enhagen+1.136
ACTED+1.118
Neg logit contributions
��-1.133
adelphia-1.093
cens-1.080
aries-0.999
buster-0.994
Token to
Token ID284
Feature activation+5.36e-01

Pos logit contributions
AMS+0.995
bara+0.979
Keefe+0.949
enhagen+0.944
ACTED+0.937
Neg logit contributions
��-1.108
adelphia-1.072
cens-1.055
aries-0.984
buster-0.983
Token you
Token ID345
Feature activation-4.32e-01

Pos logit contributions
��+0.077
adelphia+0.074
cens+0.073
aries+0.067
buster+0.067
Neg logit contributions
AMS-0.101
bara-0.100
Keefe-0.097
enhagen-0.097
ACTED-0.096
Token
Token ID447
Feature activation+4.57e-02

Pos logit contributions
��+1.112
adelphia+1.067
cens+1.055
aries+0.964
buster+0.955
Neg logit contributions
AMS-1.637
bara-1.611
Keefe-1.577
enhagen-1.573
ACTED-1.557
Token
Token ID247
Feature activation-2.01e-01

Pos logit contributions
AMS+0.165
bara+0.162
Keefe+0.158
enhagen+0.158
ACTED+0.156
Neg logit contributions
��-0.126
adelphia-0.121
cens-0.120
aries-0.110
buster-0.110
Tokenre
Token ID260
Feature activation+2.18e-02

Pos logit contributions
��+0.727
adelphia+0.706
cens+0.701
aries+0.658
buster+0.654
Neg logit contributions
AMS-0.554
bara-0.542
Keefe-0.526
enhagen-0.525
ACTED-0.517
Token looking
Token ID2045
Feature activation+8.18e-01

Pos logit contributions
AMS+0.074
bara+0.073
Keefe+0.071
enhagen+0.071
ACTED+0.070
Neg logit contributions
��-0.065
adelphia-0.062
cens-0.061
aries-0.057
buster-0.056
Token closely
Token ID7173
Feature activation+2.04e+00

Pos logit contributions
AMS+2.507
bara+2.503
enhagen+2.437
Keefe+2.399
ACTED+2.362
Neg logit contributions
��-2.626
adelphia-2.573
cens-2.535
buster-2.331
aries-2.324
Token,
Token ID11
Feature activation-1.08e-01

Pos logit contributions
enhagen+5.995
bara+5.976
AMS+5.921
Keefe+5.714
unning+5.655
Neg logit contributions
��-6.232
adelphia-6.216
cens-6.118
buster-5.634
taboola-5.621
Token it
Token ID340
Feature activation+8.77e-02

Pos logit contributions
��+0.300
adelphia+0.289
cens+0.285
aries+0.262
buster+0.260
Neg logit contributions
AMS-0.386
bara-0.380
Keefe-0.371
enhagen-0.370
ACTED-0.366
Token turns
Token ID4962
Feature activation-1.87e-01

Pos logit contributions
AMS+0.284
bara+0.281
enhagen+0.274
Keefe+0.272
ACTED+0.267
Neg logit contributions
��-0.275
adelphia-0.265
cens-0.261
aries-0.242
buster-0.242
Token into
Token ID656
Feature activation+1.19e-02

Pos logit contributions
��+0.535
adelphia+0.515
cens+0.510
aries+0.470
buster+0.467
Neg logit contributions
AMS-0.658
bara-0.647
Keefe-0.632
enhagen-0.630
ACTED-0.623
Token something
Token ID1223
Feature activation+4.01e-01

Pos logit contributions
AMS+0.040
bara+0.039
enhagen+0.038
Keefe+0.038
ACTED+0.038
Neg logit contributions
��-0.036
adelphia-0.035
cens-0.034
aries-0.032
buster-0.032
Token in
Token ID287
Feature activation-8.53e-01

Pos logit contributions
��+1.463
adelphia+1.415
cens+1.400
aries+1.304
buster+1.295
Neg logit contributions
AMS-1.490
bara-1.463
Keefe-1.425
enhagen-1.422
ACTED-1.402
Token other
Token ID584
Feature activation-1.19e-01

Pos logit contributions
��+2.442
adelphia+2.346
cens+2.309
aries+2.165
buster+2.148
Neg logit contributions
AMS-2.950
bara-2.896
Keefe-2.842
enhagen-2.836
ACTED-2.792
Token forms
Token ID5107
Feature activation-2.33e-02

Pos logit contributions
��+0.393
adelphia+0.381
cens+0.378
aries+0.351
buster+0.349
Neg logit contributions
AMS-0.368
bara-0.361
Keefe-0.351
enhagen-0.349
ACTED-0.346
Token of
Token ID286
Feature activation-1.14e-01

Pos logit contributions
��+0.073
adelphia+0.070
cens+0.070
aries+0.065
buster+0.065
Neg logit contributions
AMS-0.075
bara-0.074
Keefe-0.072
enhagen-0.072
ACTED-0.071
Token physical
Token ID3518
Feature activation+3.82e-01

Pos logit contributions
��+0.373
adelphia+0.362
cens+0.358
aries+0.334
buster+0.332
Neg logit contributions
AMS-0.354
bara-0.347
Keefe-0.338
enhagen-0.336
ACTED-0.333
Token exercise
Token ID5517
Feature activation+1.99e+00

Pos logit contributions
AMS+1.020
bara+0.995
Keefe+0.972
unning+0.963
ACTED+0.946
Neg logit contributions
��-1.415
adelphia-1.373
cens-1.349
aries-1.284
buster-1.263
Token,
Token ID11
Feature activation+2.13e-01

Pos logit contributions
AMS+5.993
bara+5.789
enhagen+5.694
Keefe+5.633
unning+5.558
Neg logit contributions
��-6.305
adelphia-6.100
cens-5.951
buster-5.463
oslov-5.455
Token they
Token ID484
Feature activation+1.61e-01

Pos logit contributions
AMS+0.732
bara+0.715
Keefe+0.698
enhagen+0.696
ACTED+0.692
Neg logit contributions
��-0.630
adelphia-0.605
cens-0.600
buster-0.551
aries-0.549
Token are
Token ID389
Feature activation-6.43e-02

Pos logit contributions
AMS+0.562
bara+0.552
enhagen+0.537
Keefe+0.536
unning+0.529
Neg logit contributions
��-0.465
adelphia-0.447
cens-0.441
buster-0.402
aries-0.402
Token also
Token ID635
Feature activation-1.94e-01

Pos logit contributions
��+0.199
adelphia+0.192
cens+0.190
aries+0.176
buster+0.175
Neg logit contributions
AMS-0.211
bara-0.207
Keefe-0.202
enhagen-0.201
ACTED-0.199
Token generally
Token ID4143
Feature activation+5.92e-03

Pos logit contributions
��+0.584
adelphia+0.564
cens+0.558
aries+0.518
buster+0.514
Neg logit contributions
AMS-0.649
bara-0.638
Keefe-0.623
enhagen-0.621
ACTED-0.613
Token
Token ID247
Feature activation+1.70e-01

Pos logit contributions
��+0.308
adelphia+0.296
cens+0.293
aries+0.270
buster+0.268
Neg logit contributions
AMS-0.398
bara-0.391
Keefe-0.383
enhagen-0.381
ACTED-0.377
Tokens
Token ID82
Feature activation+3.87e-01

Pos logit contributions
AMS+0.619
bara+0.610
Keefe+0.596
enhagen+0.593
ACTED+0.586
Neg logit contributions
��-0.469
adelphia-0.450
cens-0.444
aries-0.408
buster-0.404
Token lab
Token ID2248
Feature activation+6.64e-01

Pos logit contributions
AMS+1.036
bara+1.015
Keefe+0.986
enhagen+0.974
unning+0.959
Neg logit contributions
��-1.423
adelphia-1.387
cens-1.374
aries-1.286
buster-1.284
Token,
Token ID11
Feature activation+3.47e-01

Pos logit contributions
AMS+2.320
bara+2.286
Keefe+2.241
enhagen+2.234
unning+2.199
Neg logit contributions
��-1.885
adelphia-1.823
cens-1.808
buster-1.657
aries-1.641
Token then
Token ID788
Feature activation-1.10e+00

Pos logit contributions
AMS+1.159
bara+1.138
Keefe+1.111
enhagen+1.108
ACTED+1.092
Neg logit contributions
��-1.047
adelphia-1.012
cens-1.004
aries-0.928
buster-0.925
Token applied
Token ID5625
Feature activation+1.99e+00

Pos logit contributions
��+3.417
adelphia+3.350
cens+3.318
aries+3.160
 Homo+3.081
Neg logit contributions
AMS-3.526
bara-3.398
ACTED-3.353
Keefe-3.350
enhagen-3.315
Token state
Token ID1181
Feature activation+8.02e-01

Pos logit contributions
AMS+6.086
bara+5.949
Keefe+5.816
enhagen+5.788
ACTED+5.549
Neg logit contributions
��-6.230
adelphia-6.177
cens-6.100
taboola-5.611
buster-5.588
Token-
Token ID12
Feature activation+7.30e-01

Pos logit contributions
AMS+2.733
bara+2.696
Keefe+2.630
enhagen+2.600
unning+2.576
Neg logit contributions
��-2.362
adelphia-2.295
cens-2.241
aries-2.070
buster-2.063
Tokenspace
Token ID13200
Feature activation+3.51e-01

Pos logit contributions
AMS+2.939
bara+2.886
Keefe+2.829
unning+2.798
enhagen+2.783
Neg logit contributions
��-1.719
adelphia-1.658
cens-1.561
aries-1.440
oslov-1.437
Token analysis
Token ID3781
Feature activation+7.05e-01

Pos logit contributions
AMS+1.135
bara+1.114
Keefe+1.086
enhagen+1.080
ACTED+1.066
Neg logit contributions
��-1.101
adelphia-1.067
cens-1.055
aries-0.980
buster-0.972
Token,
Token ID11
Feature activation+3.80e-01

Pos logit contributions
AMS+1.967
bara+1.928
Keefe+1.871
enhagen+1.857
ACTED+1.818
Neg logit contributions
��-2.511
adelphia-2.456
cens-2.424
aries-2.260
buster-2.254
Token if
Token ID611
Feature activation-1.58e-01

Pos logit contributions
��+0.367
adelphia+0.354
cens+0.350
aries+0.323
buster+0.321
Neg logit contributions
AMS-0.433
bara-0.425
Keefe-0.415
enhagen-0.414
ACTED-0.409
Token granted
Token ID7520
Feature activation+5.04e-01

Pos logit contributions
��+0.496
adelphia+0.480
cens+0.475
aries+0.440
buster+0.439
Neg logit contributions
AMS-0.513
bara-0.503
Keefe-0.490
enhagen-0.489
ACTED-0.483
Token will
Token ID481
Feature activation-2.91e-01

Pos logit contributions
AMS+1.738
bara+1.708
Keefe+1.678
enhagen+1.656
ACTED+1.645
Neg logit contributions
��-1.459
adelphia-1.418
cens-1.383
aries-1.272
buster-1.263
Token do
Token ID466
Feature activation+1.36e-02

Pos logit contributions
��+0.880
adelphia+0.848
cens+0.840
aries+0.785
buster+0.781
Neg logit contributions
AMS-0.972
bara-0.953
Keefe-0.932
enhagen-0.931
ACTED-0.917
Token far
Token ID1290
Feature activation+1.24e+00

Pos logit contributions
AMS+0.048
bara+0.047
Keefe+0.046
enhagen+0.046
ACTED+0.046
Neg logit contributions
��-0.039
adelphia-0.037
cens-0.037
aries-0.034
buster-0.034
Token more
Token ID517
Feature activation+1.98e+00

Pos logit contributions
AMS+4.029
bara+3.933
Keefe+3.895
enhagen+3.754
ACTED+3.723
Neg logit contributions
��-3.660
adelphia-3.610
cens-3.516
buster-3.301
aries-3.279
Token damage
Token ID2465
Feature activation+6.01e-01

Pos logit contributions
AMS+4.630
bara+4.572
Keefe+4.426
ACTED+4.257
enhagen+4.204
Neg logit contributions
��-7.567
adelphia-7.502
cens-7.297
oslov-6.903
aries-6.880
Token than
Token ID621
Feature activation+8.88e-02

Pos logit contributions
AMS+1.548
bara+1.511
Keefe+1.467
enhagen+1.453
ACTED+1.428
Neg logit contributions
��-2.267
adelphia-2.208
cens-2.188
aries-2.051
buster-2.051
Token good
Token ID922
Feature activation-1.08e-01

Pos logit contributions
AMS+0.302
bara+0.297
Keefe+0.290
enhagen+0.288
ACTED+0.285
Neg logit contributions
��-0.264
adelphia-0.255
cens-0.252
aries-0.232
buster-0.231
Token to
Token ID284
Feature activation+2.22e-01

Pos logit contributions
��+0.331
adelphia+0.321
cens+0.317
aries+0.292
buster+0.291
Neg logit contributions
AMS-0.361
bara-0.354
Keefe-0.345
enhagen-0.344
ACTED-0.340
Token the
Token ID262
Feature activation+9.41e-02

Pos logit contributions
AMS+0.781
bara+0.767
Keefe+0.745
enhagen+0.740
ACTED+0.738
Neg logit contributions
��-0.627
adelphia-0.613
cens-0.603
buster-0.548
oslov-0.548
Token to
Token ID284
Feature activation-2.06e-01

Pos logit contributions
AMS+0.640
bara+0.629
Keefe+0.612
enhagen+0.611
ACTED+0.602
Neg logit contributions
��-0.605
adelphia-0.586
cens-0.577
aries-0.533
buster-0.532
Token reflect
Token ID4079
Feature activation-1.07e-01

Pos logit contributions
��+0.594
adelphia+0.572
cens+0.565
aries+0.521
buster+0.518
Neg logit contributions
AMS-0.717
bara-0.705
Keefe-0.689
enhagen-0.686
ACTED-0.679
Token a
Token ID257
Feature activation+3.96e-01

Pos logit contributions
��+0.303
adelphia+0.291
cens+0.288
aries+0.265
buster+0.264
Neg logit contributions
AMS-0.376
bara-0.370
Keefe-0.361
enhagen-0.360
ACTED-0.356
Token move
Token ID1445
Feature activation+2.76e-01

Pos logit contributions
AMS+1.329
bara+1.308
Keefe+1.281
enhagen+1.263
unning+1.258
Neg logit contributions
��-1.187
adelphia-1.148
cens-1.126
aries-1.043
buster-1.038
Token being
Token ID852
Feature activation+7.79e-02

Pos logit contributions
AMS+0.901
bara+0.887
Keefe+0.866
enhagen+0.864
ACTED+0.851
Neg logit contributions
��-0.854
adelphia-0.824
cens-0.815
aries-0.756
buster-0.751
Token applied
Token ID5625
Feature activation+1.97e+00

Pos logit contributions
AMS+0.239
bara+0.235
Keefe+0.228
enhagen+0.228
ACTED+0.224
Neg logit contributions
��-0.257
adelphia-0.249
cens-0.246
aries-0.229
buster-0.229
Token and
Token ID290
Feature activation+2.39e-01

Pos logit contributions
bara+5.542
AMS+5.508
enhagen+5.416
Keefe+5.306
unning+5.270
Neg logit contributions
��-6.500
adelphia-6.350
cens-6.143
buster-5.724
 Gutenberg-5.702
Token subsequently
Token ID12412
Feature activation-7.17e-02

Pos logit contributions
AMS+0.812
bara+0.800
Keefe+0.783
enhagen+0.775
ACTED+0.767
Neg logit contributions
��-0.712
adelphia-0.690
cens-0.675
buster-0.624
aries-0.624
Token un
Token ID555
Feature activation+9.64e-01

Pos logit contributions
��+0.214
adelphia+0.207
cens+0.204
aries+0.189
buster+0.188
Neg logit contributions
AMS-0.243
bara-0.239
Keefe-0.233
enhagen-0.232
ACTED-0.229
Token-
Token ID12
Feature activation+3.77e-01

Pos logit contributions
bara+2.865
AMS+2.863
Keefe+2.770
unning+2.704
enhagen+2.700
Neg logit contributions
��-3.251
adelphia-3.122
cens-3.007
 Gutenberg-2.856
oslov-2.843
Tokenapp
Token ID1324
Feature activation+9.15e-01

Pos logit contributions
AMS+1.094
bara+1.080
Keefe+1.050
enhagen+1.036
unning+1.023
Neg logit contributions
��-1.308
adelphia-1.270
cens-1.239
aries-1.173
buster-1.164
Token
Token ID198
Feature activation-2.58e-01

Pos logit contributions
AMS+0.416
bara+0.407
Keefe+0.402
enhagen+0.396
ACTED+0.396
Neg logit contributions
��-0.315
adelphia-0.300
cens-0.299
aries-0.273
buster-0.270
Token
Token ID198
Feature activation+2.69e-01

Pos logit contributions
��+0.625
adelphia+0.609
cens+0.604
aries+0.554
buster+0.548
Neg logit contributions
AMS-1.004
bara-0.990
enhagen-0.982
Keefe-0.966
ACTED-0.957
TokenBron
Token ID18760
Feature activation+4.36e-01

Pos logit contributions
AMS+0.764
bara+0.745
Keefe+0.728
enhagen+0.718
ACTED+0.714
Neg logit contributions
��-0.949
adelphia-0.919
cens-0.912
aries-0.855
buster-0.850
Tokencos
Token ID6966
Feature activation-5.58e-01

Pos logit contributions
bara+1.293
AMS+1.233
Keefe+1.203
unning+1.199
enhagen+1.193
Neg logit contributions
��-1.522
cens-1.408
adelphia-1.406
 Gutenberg-1.351
oslov-1.327
Token coach
Token ID3985
Feature activation+5.14e-01

Pos logit contributions
��+1.577
adelphia+1.519
cens+1.494
aries+1.387
buster+1.378
Neg logit contributions
AMS-1.979
bara-1.948
enhagen-1.900
Keefe-1.895
ACTED-1.870
Token Vance
Token ID40154
Feature activation+1.97e+00

Pos logit contributions
AMS+1.573
bara+1.546
Keefe+1.503
enhagen+1.499
ACTED+1.479
Neg logit contributions
��-1.700
adelphia-1.641
cens-1.628
aries-1.511
buster-1.506
Token Joseph
Token ID7212
Feature activation-5.35e-01

Pos logit contributions
bara+4.833
AMS+4.770
Keefe+4.663
unning+4.431
enhagen+4.343
Neg logit contributions
adelphia-7.440
��-7.417
cens-7.264
ipel-6.804
taboola-6.800
Token said
Token ID531
Feature activation+2.82e-01

Pos logit contributions
��+1.624
adelphia+1.571
cens+1.546
aries+1.448
buster+1.437
Neg logit contributions
AMS-1.776
bara-1.741
Keefe-1.702
enhagen-1.692
ACTED-1.673
Token Monday
Token ID3321
Feature activation-1.90e-01

Pos logit contributions
AMS+0.955
bara+0.940
Keefe+0.921
enhagen+0.912
ACTED+0.905
Neg logit contributions
��-0.837
adelphia-0.805
cens-0.804
aries-0.737
buster-0.733
Token that
Token ID326
Feature activation+3.57e-01

Pos logit contributions
��+0.578
adelphia+0.558
cens+0.553
aries+0.513
buster+0.509
Neg logit contributions
AMS-0.631
bara-0.620
Keefe-0.605
enhagen-0.603
ACTED-0.596
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
AMS+1.182
bara+1.164
Keefe+1.141
enhagen+1.127
ACTED+1.121
Neg logit contributions
��-1.084
cens-1.043
adelphia-1.043
aries-0.956
buster-0.950
Token showing
Token ID4478
Feature activation+9.16e-03

Pos logit contributions
AMS+0.512
bara+0.504
Keefe+0.492
enhagen+0.490
ACTED+0.483
Neg logit contributions
��-0.445
adelphia-0.431
cens-0.425
aries-0.393
buster-0.391
Token when
Token ID618
Feature activation+4.08e-01

Pos logit contributions
AMS+0.031
bara+0.030
Keefe+0.029
enhagen+0.029
ACTED+0.029
Neg logit contributions
��-0.028
adelphia-0.027
cens-0.026
aries-0.024
buster-0.024
Token,
Token ID11
Feature activation+3.31e-01

Pos logit contributions
AMS+1.414
bara+1.390
Keefe+1.356
enhagen+1.352
ACTED+1.337
Neg logit contributions
��-1.179
adelphia-1.142
cens-1.127
aries-1.033
buster-1.033
Token and
Token ID290
Feature activation+7.16e-01

Pos logit contributions
AMS+1.105
bara+1.085
Keefe+1.056
enhagen+1.052
ACTED+1.041
Neg logit contributions
��-1.009
adelphia-0.974
cens-0.962
aries-0.892
buster-0.888
Token how
Token ID703
Feature activation+1.55e+00

Pos logit contributions
AMS+2.395
bara+2.359
Keefe+2.299
enhagen+2.288
ACTED+2.258
Neg logit contributions
��-2.151
adelphia-2.079
cens-2.055
buster-1.896
aries-1.876
Token intensely
Token ID31146
Feature activation+1.97e+00

Pos logit contributions
AMS+4.891
bara+4.816
Keefe+4.673
ACTED+4.659
enhagen+4.618
Neg logit contributions
��-4.654
adelphia-4.629
cens-4.515
buster-4.189
oslov-4.117
Token,
Token ID11
Feature activation+9.26e-01

Pos logit contributions
AMS+6.042
bara+5.890
ACTED+5.780
Keefe+5.746
enhagen+5.698
Neg logit contributions
��-5.868
adelphia-5.859
cens-5.694
buster-5.379
oslov-5.297
Token each
Token ID1123
Feature activation+6.44e-01

Pos logit contributions
AMS+3.063
bara+3.006
Keefe+2.936
enhagen+2.907
ACTED+2.881
Neg logit contributions
��-2.784
adelphia-2.728
cens-2.656
buster-2.464
oslov-2.438
Token set
Token ID900
Feature activation+3.94e-01

Pos logit contributions
AMS+2.174
bara+2.152
Keefe+2.107
enhagen+2.092
unning+2.068
Neg logit contributions
��-1.896
adelphia-1.823
cens-1.806
aries-1.667
buster-1.657
Token of
Token ID286
Feature activation+5.34e-02

Pos logit contributions
AMS+1.213
bara+1.189
Keefe+1.166
enhagen+1.161
unning+1.136
Neg logit contributions
��-1.283
adelphia-1.237
cens-1.230
oslov-1.151
buster-1.143
Token neurons
Token ID16890
Feature activation+1.57e-01

Pos logit contributions
AMS+0.190
bara+0.187
Keefe+0.182
enhagen+0.182
ACTED+0.180
Neg logit contributions
��-0.151
adelphia-0.145
cens-0.143
aries-0.132
buster-0.131
Token>
Token ID29
Feature activation-6.53e-01

Pos logit contributions
��+0.688
adelphia+0.668
cens+0.662
aries+0.618
buster+0.613
Neg logit contributions
AMS-0.622
bara-0.609
Keefe-0.593
enhagen-0.591
ACTED-0.584
Token,
Token ID837
Feature activation-3.93e-01

Pos logit contributions
��+1.570
adelphia+1.501
cens+1.483
aries+1.349
buster+1.332
Neg logit contributions
AMS-2.589
bara-2.550
Keefe-2.497
enhagen-2.493
ACTED-2.463
Token which
Token ID543
Feature activation-4.10e-01

Pos logit contributions
��+1.143
adelphia+1.103
cens+1.094
aries+1.012
buster+1.002
Neg logit contributions
AMS-1.361
bara-1.338
Keefe-1.306
enhagen-1.304
ACTED-1.285
Token points
Token ID2173
Feature activation+1.86e-01

Pos logit contributions
��+1.245
adelphia+1.202
cens+1.192
aries+1.111
buster+1.098
Neg logit contributions
AMS-1.363
bara-1.339
Keefe-1.308
enhagen-1.306
ACTED-1.287
Token to
Token ID284
Feature activation+6.84e-01

Pos logit contributions
AMS+0.472
bara+0.462
Keefe+0.447
enhagen+0.446
ACTED+0.438
Neg logit contributions
��-0.712
adelphia-0.695
cens-0.688
aries-0.647
buster-0.644
Token uniquely
Token ID24139
Feature activation+1.95e+00

Pos logit contributions
AMS+2.239
bara+2.205
enhagen+2.149
Keefe+2.134
ACTED+2.130
Neg logit contributions
��-2.084
adelphia-2.027
cens-1.983
buster-1.827
oslov-1.802
Token-
Token ID12
Feature activation+9.48e-01

Pos logit contributions
AMS+5.552
bara+5.393
ACTED+5.324
Keefe+5.307
unning+5.177
Neg logit contributions
��-6.370
adelphia-6.251
cens-6.031
buster-5.693
emia-5.638
Tokenowned
Token ID11990
Feature activation+1.00e+00

Pos logit contributions
AMS+2.740
bara+2.691
Keefe+2.624
ACTED+2.573
enhagen+2.567
Neg logit contributions
��-3.290
adelphia-3.165
cens-3.072
buster-2.916
aries-2.907
Token data
Token ID1366
Feature activation+6.98e-01

Pos logit contributions
AMS+3.201
bara+3.100
ACTED+3.026
Keefe+3.019
enhagen+3.012
Neg logit contributions
��-3.098
adelphia-3.036
cens-2.958
buster-2.716
ipel-2.667
Token that
Token ID326
Feature activation+2.62e-01

Pos logit contributions
AMS+2.279
bara+2.226
Keefe+2.176
enhagen+2.172
ACTED+2.166
Neg logit contributions
��-2.127
adelphia-2.079
cens-2.038
buster-1.868
oslov-1.844
Token has
Token ID468
Feature activation+3.41e-01

Pos logit contributions
AMS+0.877
bara+0.861
Keefe+0.840
enhagen+0.832
ACTED+0.828
Neg logit contributions
��-0.794
adelphia-0.766
cens-0.757
buster-0.695
aries-0.692
Tokenercise
Token ID23697
Feature activation+9.87e-01

Pos logit contributions
AMS+0.684
bara+0.671
enhagen+0.648
Keefe+0.648
unning+0.637
Neg logit contributions
��-0.859
adelphia-0.822
cens-0.818
buster-0.768
oslov-0.766
Token.
Token ID13
Feature activation+5.23e-01

Pos logit contributions
AMS+3.142
bara+3.046
Keefe+3.007
enhagen+2.957
unning+2.952
Neg logit contributions
��-3.151
adelphia-3.008
cens-2.913
buster-2.727
oslov-2.721
Token High
Token ID3334
Feature activation-3.04e-01

Pos logit contributions
AMS+1.760
bara+1.704
Keefe+1.677
ACTED+1.663
enhagen+1.650
Neg logit contributions
��-1.586
adelphia-1.520
cens-1.507
aries-1.384
buster-1.378
Token-
Token ID12
Feature activation+1.12e-01

Pos logit contributions
��+0.988
adelphia+0.956
cens+0.947
aries+0.883
buster+0.877
Neg logit contributions
AMS-0.948
bara-0.930
Keefe-0.906
enhagen-0.903
ACTED-0.891
Tokenintensity
Token ID47799
Feature activation+6.54e-01

Pos logit contributions
AMS+0.322
bara+0.315
Keefe+0.306
enhagen+0.304
ACTED+0.300
Neg logit contributions
��-0.391
adelphia-0.379
cens-0.374
aries-0.352
buster-0.350
Token exercise
Token ID5517
Feature activation+1.95e+00

Pos logit contributions
AMS+2.135
bara+2.108
Keefe+2.033
unning+2.021
enhagen+2.013
Neg logit contributions
��-2.004
adelphia-1.963
cens-1.931
oslov-1.766
buster-1.759
Token de
Token ID390
Feature activation+4.02e-02

Pos logit contributions
AMS+5.782
bara+5.665
Keefe+5.564
enhagen+5.435
unning+5.424
Neg logit contributions
��-6.420
adelphia-6.171
cens-5.949
oslov-5.496
taboola-5.492
Tokenple
Token ID1154
Feature activation+3.39e-01

Pos logit contributions
AMS+0.063
bara+0.061
Keefe+0.057
enhagen+0.056
ACTED+0.055
Neg logit contributions
��-0.193
adelphia-0.190
cens-0.188
aries-0.179
buster-0.179
Tokentes
Token ID4879
Feature activation+1.37e-01

Pos logit contributions
AMS+1.386
bara+1.362
Keefe+1.331
enhagen+1.331
unning+1.317
Neg logit contributions
��-0.791
adelphia-0.737
cens-0.729
aries-0.653
buster-0.653
Token glucose
Token ID15701
Feature activation+1.35e-01

Pos logit contributions
AMS+0.474
bara+0.463
Keefe+0.449
enhagen+0.447
ACTED+0.447
Neg logit contributions
��-0.403
adelphia-0.388
cens-0.384
buster-0.351
aries-0.351
Token and
Token ID290
Feature activation+2.43e-01

Pos logit contributions
AMS+0.472
bara+0.461
Keefe+0.452
enhagen+0.450
ACTED+0.446
Neg logit contributions
��-0.387
adelphia-0.372
cens-0.369
aries-0.339
buster-0.337
Token.
Token ID13
Feature activation-1.79e-01

Pos logit contributions
AMS+2.308
bara+2.290
Keefe+2.193
unning+2.193
enhagen+2.186
Neg logit contributions
��-2.341
adelphia-2.273
cens-2.200
oslov-2.033
 Gutenberg-2.027
Token New
Token ID968
Feature activation-6.30e-01

Pos logit contributions
��+0.521
adelphia+0.503
cens+0.498
aries+0.460
buster+0.457
Neg logit contributions
AMS-0.621
bara-0.610
Keefe-0.596
enhagen-0.595
ACTED-0.587
Token research
Token ID2267
Feature activation+4.77e-01

Pos logit contributions
��+1.768
adelphia+1.701
cens+1.689
aries+1.570
buster+1.550
Neg logit contributions
AMS-2.235
bara-2.196
enhagen-2.142
Keefe-2.140
ACTED-2.118
Token has
Token ID468
Feature activation+7.27e-01

Pos logit contributions
AMS+1.499
bara+1.475
Keefe+1.436
enhagen+1.428
ACTED+1.408
Neg logit contributions
��-1.540
adelphia-1.487
cens-1.468
buster-1.359
aries-1.357
Token gone
Token ID3750
Feature activation+8.37e-01

Pos logit contributions
AMS+2.231
bara+2.226
enhagen+2.137
Keefe+2.125
ACTED+2.089
Neg logit contributions
��-2.387
adelphia-2.301
cens-2.260
buster-2.106
ipel-2.080
Token further
Token ID2252
Feature activation+1.95e+00

Pos logit contributions
AMS+2.764
bara+2.746
enhagen+2.654
Keefe+2.630
ACTED+2.578
Neg logit contributions
��-2.567
adelphia-2.488
cens-2.441
aries-2.246
oslov-2.232
Token,
Token ID11
Feature activation+6.13e-01

Pos logit contributions
bara+5.904
AMS+5.883
enhagen+5.661
unning+5.563
ACTED+5.508
Neg logit contributions
��-6.122
adelphia-6.015
cens-5.671
 Gutenberg-5.324
taboola-5.273
Token exposing
Token ID21294
Feature activation+1.67e-01

Pos logit contributions
AMS+1.998
bara+1.996
Keefe+1.921
enhagen+1.905
unning+1.893
Neg logit contributions
��-1.889
adelphia-1.834
cens-1.784
aries-1.645
ipel-1.640
Token how
Token ID703
Feature activation+8.41e-01

Pos logit contributions
AMS+0.578
bara+0.569
Keefe+0.554
enhagen+0.551
ACTED+0.545
Neg logit contributions
��-0.487
adelphia-0.469
cens-0.460
aries-0.422
buster-0.422
Token American
Token ID1605
Feature activation-4.77e-01

Pos logit contributions
AMS+2.892
bara+2.880
Keefe+2.765
enhagen+2.745
ACTED+2.742
Neg logit contributions
��-2.459
adelphia-2.354
cens-2.275
taboola-2.085
buster-2.073
Token capitalism
Token ID12129
Feature activation-5.11e-01

Pos logit contributions
��+1.200
adelphia+1.150
cens+1.140
aries+1.045
buster+1.033
Neg logit contributions
AMS-1.835
bara-1.804
enhagen-1.767
Keefe-1.767
ACTED-1.746
Token how
Token ID703
Feature activation+9.45e-01

Pos logit contributions
AMS+0.135
bara+0.133
Keefe+0.129
enhagen+0.129
ACTED+0.127
Neg logit contributions
��-0.114
adelphia-0.109
cens-0.108
aries-0.099
buster-0.099
Token this
Token ID428
Feature activation+7.32e-01

Pos logit contributions
bara+3.085
AMS+3.083
Keefe+2.918
enhagen+2.915
ACTED+2.867
Neg logit contributions
��-2.931
adelphia-2.798
cens-2.763
taboola-2.543
buster-2.513
Token pr
Token ID778
Feature activation-2.29e-02

Pos logit contributions
bara+2.499
AMS+2.463
Keefe+2.371
enhagen+2.362
unning+2.361
Neg logit contributions
��-2.201
adelphia-2.076
cens-2.043
taboola-1.883
buster-1.868
Tokenimate
Token ID1920
Feature activation-1.72e-01

Pos logit contributions
��+0.080
adelphia+0.077
cens+0.077
aries+0.072
buster+0.071
Neg logit contributions
AMS-0.066
bara-0.065
Keefe-0.063
enhagen-0.063
unning-0.062
Token was
Token ID373
Feature activation-2.78e-01

Pos logit contributions
��+0.487
adelphia+0.468
cens+0.463
aries+0.427
buster+0.423
Neg logit contributions
AMS-0.611
bara-0.602
Keefe-0.588
enhagen-0.586
ACTED-0.579
Token uniquely
Token ID24139
Feature activation+1.94e+00

Pos logit contributions
��+0.835
adelphia+0.807
cens+0.801
aries+0.743
buster+0.735
Neg logit contributions
AMS-0.933
bara-0.915
Keefe-0.893
enhagen-0.892
ACTED-0.881
Token adapted
Token ID16573
Feature activation+8.64e-01

Pos logit contributions
AMS+5.409
bara+5.345
Keefe+5.264
unning+5.070
ACTED+5.033
Neg logit contributions
��-6.710
adelphia-6.414
cens-6.197
buster-5.841
taboola-5.790
Token to
Token ID284
Feature activation-3.99e-02

Pos logit contributions
AMS+2.169
bara+2.153
enhagen+2.063
Keefe+2.056
unning+2.008
Neg logit contributions
��-3.322
adelphia-3.201
cens-3.171
buster-2.958
taboola-2.931
Token its
Token ID663
Feature activation+3.93e-01

Pos logit contributions
��+0.120
adelphia+0.116
cens+0.114
aries+0.106
buster+0.105
Neg logit contributions
AMS-0.135
bara-0.133
Keefe-0.129
enhagen-0.129
ACTED-0.127
Token environment
Token ID2858
Feature activation-2.43e-01

Pos logit contributions
AMS+1.264
bara+1.250
Keefe+1.210
enhagen+1.207
unning+1.195
Neg logit contributions
��-1.242
adelphia-1.194
cens-1.180
buster-1.091
aries-1.084
Token,
Token ID11
Feature activation+1.98e-01

Pos logit contributions
��+0.676
adelphia+0.652
cens+0.646
aries+0.596
buster+0.589
Neg logit contributions
AMS-0.872
bara-0.857
Keefe-0.838
enhagen-0.836
ACTED-0.827
Token everywhere
Token ID8347
Feature activation+2.48e-01

Pos logit contributions
��+1.858
adelphia+1.785
cens+1.773
aries+1.630
buster+1.619
Neg logit contributions
AMS-2.384
bara-2.342
Keefe-2.291
enhagen-2.287
ACTED-2.260
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
AMS+0.796
bara+0.785
Keefe+0.768
enhagen+0.762
ACTED+0.757
Neg logit contributions
��-0.773
adelphia-0.747
cens-0.737
buster-0.680
aries-0.680
Token
Token ID198
Feature activation-4.70e-01

Pos logit contributions
��+0.641
adelphia+0.616
cens+0.609
aries+0.561
buster+0.557
Neg logit contributions
AMS-0.774
bara-0.760
Keefe-0.744
enhagen-0.738
ACTED-0.732
Token
Token ID198
Feature activation+1.24e-02

Pos logit contributions
��+1.088
cens+1.069
adelphia+1.068
aries+0.979
buster+0.970
Neg logit contributions
AMS-1.859
enhagen-1.836
bara-1.835
Keefe-1.788
ACTED-1.775
TokenTHE
Token ID10970
Feature activation-3.36e-01

Pos logit contributions
AMS+0.035
bara+0.035
Keefe+0.034
enhagen+0.034
ACTED+0.033
Neg logit contributions
��-0.043
adelphia-0.042
cens-0.042
aries-0.039
buster-0.039
Token PUR
Token ID33079
Feature activation+1.94e+00

Pos logit contributions
��+0.968
adelphia+0.933
cens+0.926
aries+0.854
buster+0.848
Neg logit contributions
AMS-1.171
bara-1.153
Keefe-1.127
enhagen-1.124
ACTED-1.109
TokenGE
Token ID8264
Feature activation-4.92e-02

Pos logit contributions
AMS+3.818
ACTED+3.409
RAY+3.377
Keefe+3.286
bara+3.238
Neg logit contributions
��-8.720
adelphia-8.304
cens-8.226
emia-7.879
oslov-7.805
Token D
Token ID360
Feature activation-4.07e-01

Pos logit contributions
��+0.140
adelphia+0.135
cens+0.133
aries+0.123
buster+0.121
Neg logit contributions
AMS-0.174
bara-0.170
Keefe-0.166
enhagen-0.165
ACTED-0.164
TokenATES
Token ID29462
Feature activation-6.80e-01

Pos logit contributions
��+1.525
adelphia+1.483
cens+1.477
aries+1.398
buster+1.383
Neg logit contributions
AMS-1.046
bara-1.043
enhagen-1.009
Keefe-1.001
ACTED-0.976
Token*
Token ID9
Feature activation+4.77e-02

Pos logit contributions
��+1.932
adelphia+1.851
cens+1.848
aries+1.699
buster+1.691
Neg logit contributions
AMS-2.384
bara-2.359
enhagen-2.304
Keefe-2.303
ACTED-2.267
Token Spread
Token ID31843
Feature activation-5.56e-01

Pos logit contributions
AMS+0.174
bara+0.170
Keefe+0.167
enhagen+0.166
ACTED+0.164
Neg logit contributions
��-0.131
adelphia-0.127
cens-0.123
aries-0.114
oslov-0.113
Token no
Token ID645
Feature activation-5.32e-01

Pos logit contributions
AMS+2.493
bara+2.487
enhagen+2.396
Keefe+2.393
ACTED+2.355
Neg logit contributions
��-2.410
adelphia-2.344
cens-2.304
buster-2.134
oslov-2.118
Token interest
Token ID1393
Feature activation-8.08e-01

Pos logit contributions
��+1.583
adelphia+1.522
cens+1.520
aries+1.426
buster+1.403
Neg logit contributions
AMS-1.797
bara-1.748
Keefe-1.712
enhagen-1.705
ACTED-1.685
Token in
Token ID287
Feature activation-7.59e-01

Pos logit contributions
��+2.452
adelphia+2.350
cens+2.343
aries+2.190
buster+2.149
Neg logit contributions
AMS-2.688
bara-2.622
enhagen-2.570
Keefe-2.563
ACTED-2.524
Token seeking
Token ID6095
Feature activation-2.00e-02

Pos logit contributions
��+2.169
cens+2.079
adelphia+2.063
aries+1.922
 Homo+1.889
Neg logit contributions
AMS-2.655
bara-2.596
Keefe-2.546
enhagen-2.541
ACTED-2.532
Token a
Token ID257
Feature activation+6.00e-01

Pos logit contributions
��+0.061
adelphia+0.059
cens+0.058
aries+0.054
buster+0.054
Neg logit contributions
AMS-0.066
bara-0.065
Keefe-0.064
enhagen-0.063
ACTED-0.063
Token patent
Token ID12701
Feature activation+1.93e+00

Pos logit contributions
AMS+2.037
bara+2.010
Keefe+1.957
enhagen+1.939
unning+1.923
Neg logit contributions
��-1.755
adelphia-1.732
cens-1.653
aries-1.534
buster-1.531
Token for
Token ID329
Feature activation+7.32e-01

Pos logit contributions
bara+5.836
AMS+5.785
enhagen+5.605
unning+5.595
ACTED+5.450
Neg logit contributions
adelphia-6.048
��-6.022
cens-5.722
aries-5.337
taboola-5.335
Token the
Token ID262
Feature activation+5.42e-01

Pos logit contributions
AMS+2.348
bara+2.303
enhagen+2.251
Keefe+2.229
unning+2.197
Neg logit contributions
��-2.287
adelphia-2.244
cens-2.189
aries-2.022
oslov-2.017
Token Love
Token ID5896
Feature activation+6.90e-01

Pos logit contributions
AMS+1.736
bara+1.703
enhagen+1.657
Keefe+1.652
unning+1.631
Neg logit contributions
��-1.697
adelphia-1.668
cens-1.632
aries-1.507
buster-1.497
Tokent
Token ID83
Feature activation+9.76e-01

Pos logit contributions
AMS+2.592
bara+2.572
Keefe+2.506
enhagen+2.486
unning+2.467
Neg logit contributions
��-1.810
adelphia-1.714
cens-1.679
aries-1.538
oslov-1.521
Tokenron
Token ID1313
Feature activation+2.56e-01

Pos logit contributions
bara+2.451
AMS+2.439
Keefe+2.316
unning+2.314
enhagen+2.277
Neg logit contributions
��-3.790
adelphia-3.620
cens-3.555
oslov-3.349
 Homo-3.326
Token past
Token ID1613
Feature activation-2.14e-01

Pos logit contributions
AMS+0.715
bara+0.705
Keefe+0.687
enhagen+0.686
ACTED+0.676
Neg logit contributions
��-0.516
adelphia-0.498
cens-0.489
buster-0.444
aries-0.443
Token.
Token ID13
Feature activation-5.33e-02

Pos logit contributions
��+0.633
adelphia+0.612
cens+0.604
aries+0.557
buster+0.555
Neg logit contributions
AMS-0.728
bara-0.716
Keefe-0.697
enhagen-0.696
ACTED-0.687
Token
Token ID198
Feature activation-3.08e-01

Pos logit contributions
��+0.147
adelphia+0.141
cens+0.140
aries+0.128
buster+0.127
Neg logit contributions
AMS-0.193
bara-0.189
Keefe-0.185
enhagen-0.184
ACTED-0.183
Token
Token ID198
Feature activation+3.13e-01

Pos logit contributions
��+0.750
adelphia+0.730
cens+0.726
aries+0.664
buster+0.658
Neg logit contributions
AMS-1.196
bara-1.180
enhagen-1.168
Keefe-1.152
ACTED-1.141
TokenWith
Token ID3152
Feature activation-3.78e-01

Pos logit contributions
AMS+0.904
bara+0.882
Keefe+0.860
enhagen+0.847
ACTED+0.844
Neg logit contributions
��-1.097
adelphia-1.063
cens-1.048
aries-0.985
buster-0.978
Token Kron
Token ID44732
Feature activation-3.02e+00

Pos logit contributions
��+1.095
adelphia+1.052
cens+1.047
aries+0.971
oslov+0.961
Neg logit contributions
AMS-1.309
bara-1.281
Keefe-1.256
enhagen-1.251
ACTED-1.238
Tokenstadt
Token ID38863
Feature activation-1.09e+00

Pos logit contributions
��+6.302
adelphia+6.229
cens+6.031
aries+5.624
oslov+5.571
Neg logit contributions
AMS-11.518
ACTED-11.493
Keefe-11.285
bara-11.090
RAY-10.975
Token and
Token ID290
Feature activation-4.00e-01

Pos logit contributions
��+2.955
cens+2.830
adelphia+2.821
aries+2.621
oslov+2.584
Neg logit contributions
AMS-3.983
bara-3.917
enhagen-3.832
Keefe-3.832
ACTED-3.777
Token M
Token ID337
Feature activation-5.39e-01

Pos logit contributions
��+1.118
adelphia+1.072
cens+1.065
aries+0.981
oslov+0.972
Neg logit contributions
AMS-1.429
bara-1.404
Keefe-1.373
enhagen-1.372
ACTED-1.357
Tokenakh
Token ID11322
Feature activation+1.72e-01

Pos logit contributions
��+2.122
adelphia+2.066
cens+2.048
aries+1.945
oslov+1.930
Neg logit contributions
AMS-1.301
bara-1.271
enhagen-1.232
Keefe-1.229
ACTED-1.208
Tokenno
Token ID3919
Feature activation-3.99e-01

Pos logit contributions
AMS+0.586
bara+0.585
enhagen+0.562
unning+0.562
Keefe+0.562
Neg logit contributions
��-0.513
adelphia-0.490
cens-0.483
aries-0.443
buster-0.442
Token on
Token ID319
Feature activation-1.43e-02

Pos logit contributions
AMS+0.411
bara+0.404
Keefe+0.396
enhagen+0.393
ACTED+0.388
Neg logit contributions
��-0.317
adelphia-0.305
cens-0.299
aries-0.275
oslov-0.272
Token Him
Token ID10978
Feature activation+6.06e-01

Pos logit contributions
��+0.042
adelphia+0.040
cens+0.040
aries+0.037
buster+0.036
Neg logit contributions
AMS-0.050
bara-0.049
Keefe-0.048
enhagen-0.048
ACTED-0.047
Token
Token ID198
Feature activation-4.37e-02

Pos logit contributions
AMS+2.111
bara+2.091
Keefe+2.052
enhagen+2.027
ACTED+2.008
Neg logit contributions
��-1.702
adelphia-1.643
cens-1.622
aries-1.475
oslov-1.475
Token
Token ID198
Feature activation+2.70e-01

Pos logit contributions
��+0.112
adelphia+0.108
cens+0.107
aries+0.098
buster+0.097
Neg logit contributions
AMS-0.166
bara-0.163
enhagen-0.160
Keefe-0.160
ACTED-0.158
TokenC
Token ID34
Feature activation-5.84e-01

Pos logit contributions
AMS+0.787
bara+0.766
Keefe+0.753
enhagen+0.738
ACTED+0.735
Neg logit contributions
��-0.937
adelphia-0.907
cens-0.896
aries-0.841
oslov-0.835
Tokenull
Token ID724
Feature activation-2.39e+00

Pos logit contributions
��+1.619
cens+1.593
adelphia+1.592
aries+1.473
buster+1.440
Neg logit contributions
AMS-2.038
bara-2.005
ACTED-1.957
Keefe-1.952
enhagen-1.947
Tokenin
Token ID259
Feature activation-1.64e-01

Pos logit contributions
cens+4.321
adelphia+4.304
buster+3.816
emia+3.698
oslov+3.654
Neg logit contributions
AMS-10.322
ACTED-10.104
bara-9.729
Keefe-9.727
enhagen-9.696
Tokenan
Token ID272
Feature activation+9.28e-02

Pos logit contributions
��+0.519
adelphia+0.510
cens+0.507
aries+0.474
buster+0.470
Neg logit contributions
AMS-0.520
bara-0.505
enhagen-0.497
Keefe-0.494
ACTED-0.492
Token was
Token ID373
Feature activation-2.75e-01

Pos logit contributions
AMS+0.303
bara+0.299
Keefe+0.291
enhagen+0.290
ACTED+0.287
Neg logit contributions
��-0.288
adelphia-0.277
cens-0.275
aries-0.254
buster-0.253
Token positioned
Token ID19378
Feature activation+5.22e-02

Pos logit contributions
��+0.853
adelphia+0.827
cens+0.819
aries+0.763
buster+0.756
Neg logit contributions
AMS-0.894
bara-0.878
enhagen-0.857
Keefe-0.856
ACTED-0.844
Token stage
Token ID3800
Feature activation+4.95e-01

Pos logit contributions
AMS+0.163
bara+0.160
Keefe+0.155
enhagen+0.155
ACTED+0.153
Neg logit contributions
��-0.170
adelphia-0.164
cens-0.163
aries-0.152
buster-0.151
Token Medline
Token ID34582
Feature activation+1.16e-01

Pos logit contributions
��+0.312
adelphia+0.302
cens+0.299
aries+0.279
buster+0.277
Neg logit contributions
AMS-0.285
bara-0.279
Keefe-0.272
enhagen-0.270
ACTED-0.267
Token |
Token ID930
Feature activation-1.26e-01

Pos logit contributions
AMS+0.444
bara+0.436
Keefe+0.429
enhagen+0.428
ACTED+0.424
Neg logit contributions
��-0.296
adelphia-0.286
cens-0.281
aries-0.254
buster-0.252
Token ISI
Token ID22048
Feature activation-1.75e-01

Pos logit contributions
��+0.390
adelphia+0.378
cens+0.376
aries+0.349
buster+0.347
Neg logit contributions
AMS-0.412
bara-0.405
enhagen-0.396
Keefe-0.394
ACTED-0.389
Token
Token ID198
Feature activation-6.59e-01

Pos logit contributions
��+0.445
adelphia+0.429
cens+0.425
aries+0.388
buster+0.385
Neg logit contributions
AMS-0.667
bara-0.657
enhagen-0.644
Keefe-0.642
ACTED-0.635
Token
Token ID198
Feature activation-7.80e-02

Pos logit contributions
��+1.469
cens+1.459
adelphia+1.452
aries+1.341
buster+1.318
Neg logit contributions
AMS-2.636
enhagen-2.621
bara-2.609
Keefe-2.536
ACTED-2.522
TokenSent
Token ID31837
Feature activation-2.36e+00

Pos logit contributions
��+0.264
adelphia+0.256
cens+0.254
aries+0.238
buster+0.236
Neg logit contributions
AMS-0.232
bara-0.227
enhagen-0.221
Keefe-0.221
ACTED-0.217
Tokense
Token ID325
Feature activation-8.49e-01

Pos logit contributions
cens+7.419
adelphia+7.393
��+7.263
aries+7.075
buster+6.988
Neg logit contributions
AMS-6.663
ACTED-6.586
Keefe-6.340
bara-6.208
ONSORED-6.170
Token,
Token ID11
Feature activation+5.77e-02

Pos logit contributions
��+2.515
cens+2.431
adelphia+2.430
buster+2.254
aries+2.250
Neg logit contributions
AMS-2.841
bara-2.764
ACTED-2.724
Keefe-2.720
enhagen-2.706
Token M
Token ID337
Feature activation+9.67e-02

Pos logit contributions
AMS+0.210
bara+0.206
enhagen+0.202
Keefe+0.202
ACTED+0.199
Neg logit contributions
��-0.158
adelphia-0.152
cens-0.150
aries-0.138
buster-0.137
Token.,
Token ID1539
Feature activation+4.48e-01

Pos logit contributions
AMS+0.300
bara+0.294
Keefe+0.287
enhagen+0.286
ACTED+0.282
Neg logit contributions
��-0.316
adelphia-0.305
cens-0.304
buster-0.282
aries-0.281
Token Sch
Token ID3059
Feature activation-6.45e-01

Pos logit contributions
AMS+1.477
bara+1.449
Keefe+1.428
enhagen+1.395
unning+1.385
Neg logit contributions
��-1.380
adelphia-1.331
cens-1.311
aries-1.211
buster-1.209
Token Republican
Token ID3415
Feature activation-9.82e-02

Pos logit contributions
��+0.339
adelphia+0.326
cens+0.322
aries+0.296
buster+0.295
Neg logit contributions
AMS-0.433
bara-0.426
Keefe-0.417
enhagen-0.414
ACTED-0.409
Token victory
Token ID5373
Feature activation-6.80e-02

Pos logit contributions
��+0.275
adelphia+0.264
cens+0.261
aries+0.239
buster+0.238
Neg logit contributions
AMS-0.352
bara-0.346
Keefe-0.338
enhagen-0.336
ACTED-0.332
Token.
Token ID13
Feature activation+5.94e-02

Pos logit contributions
��+0.209
adelphia+0.201
cens+0.199
aries+0.183
oslov+0.183
Neg logit contributions
AMS-0.225
bara-0.221
Keefe-0.216
enhagen-0.215
ACTED-0.212
Token
Token ID198
Feature activation-3.90e-01

Pos logit contributions
AMS+0.207
bara+0.203
Keefe+0.199
enhagen+0.196
ACTED+0.196
Neg logit contributions
��-0.172
adelphia-0.165
cens-0.163
aries-0.150
buster-0.149
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
��+0.920
adelphia+0.903
cens+0.898
aries+0.825
buster+0.814
Neg logit contributions
AMS-1.527
bara-1.507
enhagen-1.500
Keefe-1.469
ACTED-1.457
TokenSent
Token ID31837
Feature activation-2.34e+00

Pos logit contributions
AMS+0.474
bara+0.462
Keefe+0.453
enhagen+0.446
ACTED+0.444
Neg logit contributions
��-0.507
adelphia-0.489
cens-0.484
aries-0.452
buster-0.449
Tokeniment
Token ID3681
Feature activation-1.27e+00

Pos logit contributions
cens+7.091
adelphia+7.086
aries+7.082
��+6.860
buster+6.542
Neg logit contributions
AMS-6.777
ACTED-6.508
enhagen-6.428
Keefe-6.369
bara-6.323
Token about
Token ID546
Feature activation-3.94e-01

Pos logit contributions
��+3.696
adelphia+3.607
cens+3.521
aries+3.419
buster+3.251
Neg logit contributions
AMS-4.295
bara-4.179
enhagen-4.163
Keefe-4.146
ACTED-4.080
Token how
Token ID703
Feature activation+7.34e-01

Pos logit contributions
��+1.095
adelphia+1.055
cens+1.045
aries+0.962
buster+0.953
Neg logit contributions
AMS-1.412
bara-1.386
enhagen-1.354
Keefe-1.354
ACTED-1.338
Token to
Token ID284
Feature activation+3.13e-01

Pos logit contributions
AMS+2.443
bara+2.423
Keefe+2.366
enhagen+2.314
ACTED+2.312
Neg logit contributions
��-2.217
adelphia-2.134
cens-2.098
oslov-1.929
buster-1.927
Token proceed
Token ID5120
Feature activation-1.11e-01

Pos logit contributions
AMS+1.103
bara+1.087
Keefe+1.065
enhagen+1.054
ACTED+1.046
Neg logit contributions
��-0.889
adelphia-0.853
cens-0.841
aries-0.772
oslov-0.770
Token Wikimedia
Token ID44877
Feature activation+1.20e+00

Pos logit contributions
AMS+0.305
bara+0.300
Keefe+0.293
enhagen+0.291
ACTED+0.288
Neg logit contributions
��-0.285
adelphia-0.275
cens-0.271
aries-0.252
buster-0.250
Token Commons
Token ID13815
Feature activation+2.49e-01

Pos logit contributions
AMS+3.306
bara+3.254
Keefe+3.198
enhagen+3.172
unning+3.120
Neg logit contributions
��-4.149
adelphia-4.036
cens-3.955
aries-3.742
buster-3.713
Token.
Token ID13
Feature activation-1.29e-01

Pos logit contributions
AMS+0.895
bara+0.880
Keefe+0.865
enhagen+0.862
ACTED+0.849
Neg logit contributions
��-0.686
adelphia-0.658
cens-0.647
aries-0.595
buster-0.589
Token<|endoftext|>
Token ID50256
Feature activation-5.50e-01

Pos logit contributions
��+0.343
adelphia+0.329
cens+0.324
aries+0.297
buster+0.294
Neg logit contributions
AMS-0.480
bara-0.473
Keefe-0.463
enhagen-0.461
ACTED-0.456
TokenT
Token ID51
Feature activation-5.06e-01

Pos logit contributions
��+1.884
adelphia+1.833
cens+1.829
aries+1.702
buster+1.697
Neg logit contributions
AMS-1.587
bara-1.569
enhagen-1.545
Keefe-1.515
ACTED-1.496
Tokenucker
Token ID12603
Feature activation-2.34e+00

Pos logit contributions
��+1.754
adelphia+1.713
cens+1.692
aries+1.597
buster+1.581
Neg logit contributions
AMS-1.433
bara-1.415
Keefe-1.374
enhagen-1.371
ACTED-1.354
Token Carlson
Token ID33059
Feature activation-1.38e+00

Pos logit contributions
��+5.455
adelphia+5.252
cens+5.176
buster+4.980
 Homo+4.843
Neg logit contributions
bara-8.605
AMS-8.599
enhagen-8.443
ACTED-8.412
unning-8.269
Token laid
Token ID8104
Feature activation+1.25e-01

Pos logit contributions
��+3.945
adelphia+3.789
cens+3.737
aries+3.534
buster+3.478
Neg logit contributions
AMS-4.679
bara-4.630
ACTED-4.534
Keefe-4.526
enhagen-4.481
Token out
Token ID503
Feature activation+8.62e-01

Pos logit contributions
AMS+0.432
bara+0.424
Keefe+0.414
enhagen+0.413
ACTED+0.407
Neg logit contributions
��-0.366
adelphia-0.354
cens-0.349
aries-0.322
buster-0.318
Token a
Token ID257
Feature activation+4.52e-01

Pos logit contributions
AMS+2.737
bara+2.681
Keefe+2.635
enhagen+2.603
ACTED+2.542
Neg logit contributions
��-2.727
adelphia-2.655
cens-2.601
taboola-2.403
buster-2.388
Token number
Token ID1271
Feature activation-5.01e-01

Pos logit contributions
AMS+1.550
bara+1.522
Keefe+1.494
enhagen+1.473
unning+1.465
Neg logit contributions
��-1.326
adelphia-1.289
cens-1.262
aries-1.161
buster-1.154
Token the
Token ID262
Feature activation-2.29e-01

Pos logit contributions
AMS+1.620
bara+1.602
Keefe+1.560
enhagen+1.556
ACTED+1.533
Neg logit contributions
��-1.557
adelphia-1.501
cens-1.478
oslov-1.358
aries-1.358
Token United
Token ID1578
Feature activation-1.94e-01

Pos logit contributions
��+0.632
adelphia+0.608
cens+0.601
aries+0.550
buster+0.548
Neg logit contributions
AMS-0.828
bara-0.815
Keefe-0.798
enhagen-0.795
ACTED-0.786
Token States
Token ID1829
Feature activation-1.66e-01

Pos logit contributions
��+0.456
adelphia+0.438
cens+0.431
buster+0.389
ipel+0.384
Neg logit contributions
AMS-0.774
bara-0.766
Keefe-0.748
enhagen-0.744
unning-0.741
Token Conference
Token ID8785
Feature activation+5.78e-01

Pos logit contributions
��+0.486
adelphia+0.468
cens+0.462
aries+0.424
buster+0.424
Neg logit contributions
AMS-0.574
bara-0.565
Keefe-0.551
enhagen-0.545
ACTED-0.542
Token of
Token ID286
Feature activation-1.01e+00

Pos logit contributions
AMS+1.679
bara+1.673
Keefe+1.626
enhagen+1.606
unning+1.595
Neg logit contributions
��-1.962
adelphia-1.909
cens-1.871
buster-1.748
oslov-1.738
Token Catholic
Token ID7835
Feature activation-2.29e+00

Pos logit contributions
��+2.083
adelphia+1.976
cens+1.970
aries+1.843
buster+1.787
Neg logit contributions
AMS-4.283
bara-4.208
enhagen-4.136
Keefe-4.124
ACTED-4.071
Token B
Token ID347
Feature activation-3.52e-01

Pos logit contributions
��+5.247
cens+5.127
adelphia+4.961
aries+4.780
 Homo+4.672
Neg logit contributions
enhagen-8.741
AMS-8.732
unning-8.565
Keefe-8.560
bara-8.555
Tokenishops
Token ID21863
Feature activation-7.19e-01

Pos logit contributions
��+1.042
adelphia+1.008
cens+0.984
oslov+0.907
aries+0.905
Neg logit contributions
AMS-1.228
bara-1.197
Keefe-1.162
unning-1.161
enhagen-1.158
Token (
Token ID357
Feature activation+2.34e-01

Pos logit contributions
��+2.081
adelphia+2.010
cens+1.995
aries+1.851
buster+1.829
Neg logit contributions
AMS-2.485
bara-2.432
enhagen-2.385
Keefe-2.380
ACTED-2.351
TokenUS
Token ID2937
Feature activation-3.79e-01

Pos logit contributions
AMS+0.671
bara+0.639
Keefe+0.631
ACTED+0.627
unning+0.625
Neg logit contributions
��-0.829
adelphia-0.799
cens-0.786
aries-0.747
buster-0.737
TokenCC
Token ID4093
Feature activation+1.52e-01

Pos logit contributions
��+1.222
adelphia+1.183
cens+1.174
aries+1.092
buster+1.085
Neg logit contributions
AMS-1.190
bara-1.167
Keefe-1.138
enhagen-1.135
ACTED-1.119
Token,
Token ID11
Feature activation+1.54e-01

Pos logit contributions
��+1.201
adelphia+1.157
cens+1.147
aries+1.059
buster+1.051
Neg logit contributions
AMS-1.443
bara-1.418
Keefe-1.386
enhagen-1.382
ACTED-1.366
Token more
Token ID517
Feature activation+5.73e-01

Pos logit contributions
AMS+0.549
bara+0.541
Keefe+0.528
enhagen+0.525
ACTED+0.519
Neg logit contributions
��-0.433
adelphia-0.416
cens-0.409
aries-0.377
buster-0.375
Token than
Token ID621
Feature activation-1.06e+00

Pos logit contributions
AMS+1.342
bara+1.314
enhagen+1.261
Keefe+1.259
unning+1.234
Neg logit contributions
��-2.300
adelphia-2.233
cens-2.221
aries-2.091
buster-2.087
Token double
Token ID4274
Feature activation-3.61e-01

Pos logit contributions
��+2.444
adelphia+2.366
cens+2.334
aries+2.149
buster+2.104
Neg logit contributions
AMS-4.221
bara-4.148
Keefe-4.070
ACTED-4.066
enhagen-4.031
Token its
Token ID663
Feature activation-8.56e-01

Pos logit contributions
��+1.039
adelphia+1.001
cens+0.986
aries+0.909
buster+0.903
Neg logit contributions
AMS-1.263
bara-1.239
Keefe-1.214
enhagen-1.209
ACTED-1.192
Token original
Token ID2656
Feature activation-2.26e+00

Pos logit contributions
��+2.209
adelphia+2.102
cens+2.087
aries+1.919
buster+1.890
Neg logit contributions
AMS-3.242
bara-3.193
Keefe-3.126
enhagen-3.118
ACTED-3.092
Token goal
Token ID3061
Feature activation-1.45e+00

Pos logit contributions
��+5.753
cens+5.434
adelphia+5.314
aries+5.123
 Gutenberg+5.087
Neg logit contributions
AMS-8.217
bara-8.122
Keefe-7.970
enhagen-7.960
ACTED-7.945
Token of
Token ID286
Feature activation-3.59e-01

Pos logit contributions
��+4.142
cens+3.895
adelphia+3.855
aries+3.694
buster+3.595
Neg logit contributions
AMS-5.040
bara-4.966
Keefe-4.827
enhagen-4.813
ACTED-4.806
Token $
Token ID720
Feature activation-1.73e-01

Pos logit contributions
��+0.999
adelphia+0.961
cens+0.951
aries+0.877
buster+0.869
Neg logit contributions
AMS-1.285
bara-1.263
Keefe-1.235
enhagen-1.232
ACTED-1.219
Token250
Token ID9031
Feature activation-2.96e-01

Pos logit contributions
��+0.609
adelphia+0.596
cens+0.593
aries+0.557
buster+0.553
Neg logit contributions
AMS-0.485
bara-0.478
enhagen-0.466
Keefe-0.463
ACTED-0.455
Tokenk
Token ID74
Feature activation+1.94e-01

Pos logit contributions
��+0.836
adelphia+0.801
cens+0.792
aries+0.731
buster+0.726
Neg logit contributions
AMS-1.054
bara-1.036
enhagen-1.013
Keefe-1.011
ACTED-1.000
Token uncertainty
Token ID13479
Feature activation-1.30e-02

Pos logit contributions
AMS+0.187
bara+0.184
Keefe+0.179
enhagen+0.178
ACTED+0.177
Neg logit contributions
��-0.175
adelphia-0.169
cens-0.167
aries-0.154
buster-0.154
Token is
Token ID318
Feature activation+1.16e-01

Pos logit contributions
��+0.037
adelphia+0.036
cens+0.035
aries+0.032
buster+0.032
Neg logit contributions
AMS-0.046
bara-0.045
Keefe-0.044
enhagen-0.044
ACTED-0.043
Token not
Token ID407
Feature activation-4.57e-02

Pos logit contributions
AMS+0.401
bara+0.395
Keefe+0.384
enhagen+0.382
ACTED+0.378
Neg logit contributions
��-0.336
adelphia-0.325
cens-0.321
aries-0.295
buster-0.294
Token how
Token ID703
Feature activation+2.26e-01

Pos logit contributions
��+0.131
adelphia+0.127
cens+0.125
aries+0.116
buster+0.115
Neg logit contributions
AMS-0.159
bara-0.157
enhagen-0.153
Keefe-0.153
ACTED-0.151
Token their
Token ID511
Feature activation-4.57e-01

Pos logit contributions
AMS+0.724
bara+0.711
Keefe+0.692
enhagen+0.690
ACTED+0.682
Neg logit contributions
��-0.716
adelphia-0.692
cens-0.685
aries-0.637
buster-0.633
Token original
Token ID2656
Feature activation-2.24e+00

Pos logit contributions
��+1.245
adelphia+1.197
cens+1.184
aries+1.087
buster+1.078
Neg logit contributions
AMS-1.670
bara-1.643
Keefe-1.606
enhagen-1.602
ACTED-1.584
Token love
Token ID1842
Feature activation+6.63e-01

Pos logit contributions
��+6.072
adelphia+5.912
cens+5.751
aries+5.696
 Homo+5.601
Neg logit contributions
bara-7.590
AMS-7.515
Keefe-7.288
enhagen-7.236
unning-6.951
Token story
Token ID1621
Feature activation-1.11e+00

Pos logit contributions
AMS+2.329
bara+2.287
Keefe+2.245
ACTED+2.220
enhagen+2.218
Neg logit contributions
��-1.876
cens-1.809
adelphia-1.781
oslov-1.628
 Gutenberg-1.608
Token went
Token ID1816
Feature activation+1.03e-01

Pos logit contributions
��+3.090
adelphia+3.004
cens+2.962
aries+2.805
buster+2.742
Neg logit contributions
AMS-3.935
bara-3.862
Keefe-3.777
enhagen-3.776
ACTED-3.713
Token.
Token ID13
Feature activation-1.57e-01

Pos logit contributions
AMS+0.336
bara+0.330
Keefe+0.321
enhagen+0.320
ACTED+0.317
Neg logit contributions
��-0.321
adelphia-0.310
cens-0.307
aries-0.285
buster-0.284
Token But
Token ID887
Feature activation+4.16e-01

Pos logit contributions
��+0.459
adelphia+0.442
cens+0.438
aries+0.405
buster+0.402
Neg logit contributions
AMS-0.541
bara-0.532
Keefe-0.519
enhagen-0.518
ACTED-0.511
Token anti
Token ID3098
Feature activation-3.84e-01

Pos logit contributions
��+0.136
adelphia+0.131
cens+0.130
aries+0.119
buster+0.118
Neg logit contributions
AMS-0.173
bara-0.170
Keefe-0.166
enhagen-0.166
ACTED-0.164
Token-
Token ID12
Feature activation-8.63e-01

Pos logit contributions
��+1.108
adelphia+1.066
cens+1.053
aries+0.973
buster+0.966
Neg logit contributions
AMS-1.343
bara-1.320
Keefe-1.290
enhagen-1.285
ACTED-1.271
Tokenstreet
Token ID25662
Feature activation+3.44e-01

Pos logit contributions
cens+2.705
��+2.665
adelphia+2.605
buster+2.457
aries+2.434
Neg logit contributions
AMS-2.718
bara-2.655
enhagen-2.632
Keefe-2.595
ACTED-2.594
Token harassment
Token ID10556
Feature activation-1.94e-01

Pos logit contributions
AMS+0.924
bara+0.918
Keefe+0.886
enhagen+0.876
unning+0.869
Neg logit contributions
��-1.252
adelphia-1.213
cens-1.196
aries-1.135
oslov-1.126
Token organization
Token ID4009
Feature activation-6.57e-01

Pos logit contributions
��+0.574
adelphia+0.553
cens+0.547
aries+0.503
buster+0.501
Neg logit contributions
AMS-0.664
bara-0.654
Keefe-0.639
enhagen-0.633
ACTED-0.627
Token Holl
Token ID11806
Feature activation-2.24e+00

Pos logit contributions
��+1.794
adelphia+1.734
cens+1.716
aries+1.590
buster+1.571
Neg logit contributions
AMS-2.365
bara-2.334
enhagen-2.283
Keefe-2.277
ACTED-2.253
Tokenab
Token ID397
Feature activation+1.08e+00

Pos logit contributions
adelphia+7.476
��+7.337
aries+7.237
cens+7.223
oslov+6.715
Neg logit contributions
AMS-6.182
bara-6.131
ACTED-6.080
enhagen-5.906
Keefe-5.831
Tokenack
Token ID441
Feature activation-6.15e-01

Pos logit contributions
bara+2.241
AMS+2.237
Keefe+2.089
unning+2.084
enhagen+2.076
Neg logit contributions
��-4.720
adelphia-4.364
cens-4.328
��-4.192
 Gutenberg-4.119
Token showed
Token ID3751
Feature activation+3.02e-01

Pos logit contributions
��+2.055
adelphia+2.003
cens+1.969
aries+1.861
buster+1.842
Neg logit contributions
AMS-1.835
bara-1.815
Keefe-1.753
ACTED-1.751
enhagen-1.742
Token that
Token ID326
Feature activation+6.27e-01

Pos logit contributions
AMS+0.986
bara+0.969
Keefe+0.942
enhagen+0.941
ACTED+0.924
Neg logit contributions
��-0.942
adelphia-0.906
cens-0.894
buster-0.826
oslov-0.824
Token 90
Token ID4101
Feature activation+4.35e-02

Pos logit contributions
AMS+2.236
bara+2.204
Keefe+2.137
enhagen+2.132
ACTED+2.101
Neg logit contributions
��-1.764
adelphia-1.688
cens-1.651
oslov-1.508
buster-1.504
Token al
Token ID435
Feature activation+4.78e-01

Pos logit contributions
AMS+2.573
bara+2.546
Keefe+2.484
enhagen+2.435
unning+2.417
Neg logit contributions
��-2.829
adelphia-2.727
cens-2.659
buster-2.496
aries-2.465
Token.
Token ID13
Feature activation+9.62e-02

Pos logit contributions
AMS+1.564
bara+1.542
enhagen+1.500
Keefe+1.498
unning+1.477
Neg logit contributions
��-1.472
adelphia-1.426
cens-1.405
buster-1.319
aries-1.295
Token (
Token ID357
Feature activation+1.07e+00

Pos logit contributions
AMS+0.369
bara+0.363
Keefe+0.357
enhagen+0.355
unning+0.350
Neg logit contributions
��-0.244
adelphia-0.235
cens-0.230
aries-0.210
buster-0.210
Token2002
Token ID16942
Feature activation+1.06e+00

Pos logit contributions
AMS+2.994
bara+2.903
Keefe+2.851
ACTED+2.741
unning+2.737
Neg logit contributions
��-3.860
adelphia-3.714
cens-3.569
 Ragnarok-3.424
 Gutenberg-3.420
Token);
Token ID1776
Feature activation+4.20e-01

Pos logit contributions
AMS+2.406
bara+2.334
Keefe+2.259
enhagen+2.236
ACTED+2.199
Neg logit contributions
��-4.271
adelphia-4.208
cens-4.074
aries-3.854
 Gutenberg-3.852
Token Hoff
Token ID21890
Feature activation-2.23e+00

Pos logit contributions
AMS+1.415
bara+1.388
Keefe+1.364
enhagen+1.349
unning+1.331
Neg logit contributions
��-1.262
adelphia-1.222
cens-1.199
buster-1.106
aries-1.105
Tokenert
Token ID861
Feature activation-4.26e-01

Pos logit contributions
��+6.419
cens+6.306
adelphia+6.187
buster+5.872
oslov+5.818
Neg logit contributions
AMS-7.010
ACTED-6.857
bara-6.833
Keefe-6.719
unning-6.569
Token &
Token ID1222
Feature activation+4.85e-01

Pos logit contributions
��+1.279
adelphia+1.235
cens+1.227
aries+1.137
buster+1.127
Neg logit contributions
AMS-1.428
bara-1.404
Keefe-1.369
enhagen-1.362
ACTED-1.355
Token Cove
Token ID39534
Feature activation-1.31e-01

Pos logit contributions
AMS+1.609
bara+1.575
Keefe+1.555
enhagen+1.524
unning+1.508
Neg logit contributions
��-1.480
adelphia-1.433
cens-1.406
buster-1.298
aries-1.297
Tokeny
Token ID88
Feature activation+3.26e-01

Pos logit contributions
��+0.369
adelphia+0.355
cens+0.350
aries+0.323
buster+0.320
Neg logit contributions
AMS-0.464
bara-0.456
Keefe-0.446
enhagen-0.444
ACTED-0.438
Token (
Token ID357
Feature activation+7.57e-01

Pos logit contributions
AMS+1.237
bara+1.221
Keefe+1.197
enhagen+1.192
unning+1.174
Neg logit contributions
��-0.838
adelphia-0.810
cens-0.792
aries-0.723
buster-0.721
Token
Token ID198
Feature activation+1.90e-01

Pos logit contributions
��+0.995
adelphia+0.972
cens+0.971
aries+0.889
buster+0.878
Neg logit contributions
AMS-1.661
bara-1.637
enhagen-1.633
Keefe-1.597
ACTED-1.586
TokenGoogle
Token ID11708
Feature activation+3.63e-01

Pos logit contributions
AMS+0.574
bara+0.560
Keefe+0.548
enhagen+0.540
ACTED+0.536
Neg logit contributions
��-0.642
adelphia-0.620
cens-0.613
aries-0.574
buster-0.570
Token Scholar
Token ID11713
Feature activation-2.08e-01

Pos logit contributions
AMS+0.895
bara+0.870
Keefe+0.845
ACTED+0.823
enhagen+0.822
Neg logit contributions
��-1.432
adelphia-1.383
cens-1.369
aries-1.284
ipel-1.276
Token
Token ID198
Feature activation-1.08e-01

Pos logit contributions
��+0.618
adelphia+0.598
cens+0.587
aries+0.543
buster+0.541
Neg logit contributions
AMS-0.712
bara-0.697
Keefe-0.681
enhagen-0.680
ACTED-0.672
Token
Token ID198
Feature activation+2.71e-01

Pos logit contributions
��+0.271
adelphia+0.262
cens+0.260
aries+0.238
buster+0.235
Neg logit contributions
AMS-0.415
bara-0.409
enhagen-0.402
Keefe-0.400
ACTED-0.395
TokenOl
Token ID30098
Feature activation-2.23e+00

Pos logit contributions
AMS+0.854
bara+0.832
Keefe+0.820
ACTED+0.798
enhagen+0.797
Neg logit contributions
��-0.884
adelphia-0.850
cens-0.842
aries-0.785
buster-0.782
Tokenwe
Token ID732
Feature activation-8.52e-01

Pos logit contributions
adelphia+6.523
cens+6.444
��+6.377
aries+6.057
oslov+6.051
Neg logit contributions
AMS-7.134
ACTED-6.883
bara-6.747
Keefe-6.628
enhagen-6.590
Tokenus
Token ID385
Feature activation-4.71e-01

Pos logit contributions
cens+1.440
��+1.417
adelphia+1.414
aries+1.276
buster+1.220
Neg logit contributions
AMS-3.879
bara-3.805
Keefe-3.774
ACTED-3.770
enhagen-3.768
Token,
Token ID11
Feature activation-1.67e-01

Pos logit contributions
��+1.234
adelphia+1.200
cens+1.199
aries+1.103
buster+1.094
Neg logit contributions
AMS-1.741
bara-1.708
enhagen-1.683
Keefe-1.665
ACTED-1.660
Token D
Token ID360
Feature activation+2.56e-02

Pos logit contributions
��+0.403
adelphia+0.386
cens+0.383
aries+0.348
buster+0.344
Neg logit contributions
AMS-0.662
bara-0.652
enhagen-0.639
Keefe-0.638
ACTED-0.632
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
AMS+0.080
bara+0.078
Keefe+0.076
enhagen+0.076
unning+0.075
Neg logit contributions
��-0.083
adelphia-0.080
cens-0.080
aries-0.074
buster-0.074
Token in
Token ID287
Feature activation-3.31e-01

Pos logit contributions
��+1.976
adelphia+1.925
cens+1.909
aries+1.772
buster+1.757
Neg logit contributions
AMS-2.438
bara-2.381
Keefe-2.342
enhagen-2.341
ACTED-2.322
Token New
Token ID968
Feature activation-9.11e-01

Pos logit contributions
��+0.967
adelphia+0.934
cens+0.924
aries+0.855
buster+0.848
Neg logit contributions
AMS-1.139
bara-1.119
Keefe-1.093
enhagen-1.090
ACTED-1.077
Token Jersey
Token ID8221
Feature activation-4.31e-02

Pos logit contributions
��+2.315
adelphia+2.276
cens+2.231
aries+2.058
oslov+2.034
Neg logit contributions
AMS-3.445
bara-3.346
Keefe-3.298
ACTED-3.293
enhagen-3.263
Token by
Token ID416
Feature activation-2.95e-01

Pos logit contributions
��+0.127
adelphia+0.122
cens+0.121
aries+0.111
buster+0.111
Neg logit contributions
AMS-0.148
bara-0.146
Keefe-0.142
enhagen-0.142
ACTED-0.140
Token Richard
Token ID6219
Feature activation+8.03e-01

Pos logit contributions
��+0.902
adelphia+0.871
cens+0.863
aries+0.801
buster+0.795
Neg logit contributions
AMS-0.980
bara-0.962
Keefe-0.939
enhagen-0.936
ACTED-0.925
Token Holl
Token ID11806
Feature activation-2.21e+00

Pos logit contributions
AMS+2.575
bara+2.541
Keefe+2.486
enhagen+2.426
unning+2.412
Neg logit contributions
��-2.506
adelphia-2.396
cens-2.393
aries-2.188
taboola-2.183
Tokenings
Token ID654
Feature activation+3.23e-01

Pos logit contributions
adelphia+6.455
��+6.261
cens+6.229
aries+6.030
oslov+5.846
Neg logit contributions
AMS-7.034
bara-6.901
ACTED-6.894
Keefe-6.708
unning-6.439
Tokenhead
Token ID2256
Feature activation-3.79e-01

Pos logit contributions
AMS+0.729
bara+0.711
enhagen+0.686
Keefe+0.685
unning+0.661
Neg logit contributions
��-1.331
adelphia-1.295
cens-1.282
aries-1.215
oslov-1.204
Token.
Token ID13
Feature activation+1.53e-01

Pos logit contributions
��+1.094
adelphia+1.055
cens+1.045
aries+0.967
buster+0.961
Neg logit contributions
AMS-1.319
bara-1.296
Keefe-1.264
enhagen-1.262
ACTED-1.251
Token He
Token ID679
Feature activation+8.74e-02

Pos logit contributions
AMS+0.497
bara+0.485
Keefe+0.477
enhagen+0.468
ACTED+0.466
Neg logit contributions
��-0.480
adelphia-0.459
cens-0.456
aries-0.421
buster-0.417
Token got
Token ID1392
Feature activation-1.69e-01

Pos logit contributions
AMS+0.288
bara+0.285
Keefe+0.276
enhagen+0.275
ACTED+0.272
Neg logit contributions
��-0.270
adelphia-0.259
cens-0.257
aries-0.236
buster-0.235
Token Eventually
Token ID16178
Feature activation-7.29e-01

Pos logit contributions
��+1.385
adelphia+1.337
cens+1.332
aries+1.228
buster+1.222
Neg logit contributions
AMS-1.660
bara-1.638
enhagen-1.600
Keefe-1.593
ACTED-1.572
Token though
Token ID996
Feature activation+5.41e-01

Pos logit contributions
��+2.007
adelphia+1.933
cens+1.928
aries+1.769
buster+1.757
Neg logit contributions
AMS-2.617
bara-2.578
Keefe-2.517
enhagen-2.509
ACTED-2.483
Token they
Token ID484
Feature activation-5.24e-01

Pos logit contributions
AMS+1.807
bara+1.782
Keefe+1.744
enhagen+1.737
ACTED+1.713
Neg logit contributions
��-1.619
adelphia-1.567
cens-1.517
aries-1.417
buster-1.403
Token changed
Token ID3421
Feature activation-5.16e-01

Pos logit contributions
��+1.588
adelphia+1.533
cens+1.523
aries+1.411
buster+1.403
Neg logit contributions
AMS-1.744
bara-1.711
Keefe-1.669
enhagen-1.665
ACTED-1.646
Token their
Token ID511
Feature activation-5.39e-01

Pos logit contributions
��+1.512
adelphia+1.462
cens+1.456
aries+1.344
buster+1.335
Neg logit contributions
AMS-1.769
bara-1.738
Keefe-1.691
enhagen-1.688
ACTED-1.667
Token mind
Token ID2000
Feature activation-2.17e+00

Pos logit contributions
��+1.158
adelphia+1.102
cens+1.082
aries+0.969
buster+0.959
Neg logit contributions
AMS-2.276
bara-2.245
Keefe-2.204
enhagen-2.198
ACTED-2.178
Token and
Token ID290
Feature activation-3.00e-01

Pos logit contributions
��+5.278
cens+5.162
adelphia+4.971
buster+4.707
aries+4.700
Neg logit contributions
AMS-8.045
bara-7.757
Keefe-7.748
enhagen-7.635
ACTED-7.522
Token despite
Token ID3805
Feature activation+6.82e-02

Pos logit contributions
��+0.900
adelphia+0.869
cens+0.858
aries+0.795
buster+0.789
Neg logit contributions
AMS-1.015
bara-0.998
Keefe-0.974
enhagen-0.970
ACTED-0.959
Token the
Token ID262
Feature activation-3.97e-01

Pos logit contributions
AMS+0.229
bara+0.225
Keefe+0.220
enhagen+0.219
ACTED+0.216
Neg logit contributions
��-0.205
adelphia-0.199
cens-0.194
aries-0.181
buster-0.180
Token risk
Token ID2526
Feature activation-1.33e-01

Pos logit contributions
��+1.109
adelphia+1.067
cens+1.057
aries+0.972
buster+0.965
Neg logit contributions
AMS-1.421
bara-1.397
Keefe-1.365
enhagen-1.362
ACTED-1.347
Token they
Token ID484
Feature activation-3.28e-01

Pos logit contributions
��+0.416
adelphia+0.402
cens+0.398
aries+0.370
buster+0.368
Neg logit contributions
AMS-0.432
bara-0.424
Keefe-0.414
enhagen-0.413
ACTED-0.407
Token common
Token ID2219
Feature activation+1.27e+00

Pos logit contributions
AMS+0.216
bara+0.211
Keefe+0.206
enhagen+0.204
ACTED+0.203
Neg logit contributions
��-0.204
adelphia-0.198
cens-0.195
aries-0.181
buster-0.181
Token with
Token ID351
Feature activation+1.57e-01

Pos logit contributions
bara+3.335
AMS+3.296
Keefe+3.197
enhagen+3.146
ACTED+3.119
Neg logit contributions
��-4.620
adelphia-4.512
cens-4.394
buster-4.139
aries-4.109
Token than
Token ID621
Feature activation-1.82e-01

Pos logit contributions
AMS+0.559
bara+0.551
Keefe+0.537
enhagen+0.533
ACTED+0.528
Neg logit contributions
��-0.441
adelphia-0.425
cens-0.419
aries-0.383
buster-0.382
Token class
Token ID1398
Feature activation-7.15e-01

Pos logit contributions
��+0.549
adelphia+0.530
cens+0.524
aries+0.486
buster+0.483
Neg logit contributions
AMS-0.608
bara-0.597
Keefe-0.582
enhagen-0.581
ACTED-0.574
Token war
Token ID1175
Feature activation-6.47e-02

Pos logit contributions
��+1.788
cens+1.720
adelphia+1.719
aries+1.592
buster+1.562
Neg logit contributions
AMS-2.733
bara-2.687
Keefe-2.640
enhagen-2.620
ACTED-2.612
Token anarch
Token ID14061
Feature activation-2.16e+00

Pos logit contributions
��+0.192
adelphia+0.186
cens+0.183
aries+0.168
buster+0.168
Neg logit contributions
AMS-0.219
bara-0.217
Keefe-0.211
enhagen-0.209
unning-0.207
Tokeno
Token ID78
Feature activation-8.60e-01

Pos logit contributions
��+4.008
adelphia+4.002
cens+3.965
aries+3.747
oslov+3.541
Neg logit contributions
AMS-9.263
Keefe-8.999
bara-8.962
ACTED-8.910
enhagen-8.743
Token-
Token ID12
Feature activation-3.89e-01

Pos logit contributions
��+2.395
adelphia+2.318
cens+2.286
aries+2.120
buster+2.089
Neg logit contributions
AMS-3.071
bara-3.021
Keefe-2.953
enhagen-2.938
ACTED-2.914
Tokencommun
Token ID10709
Feature activation-6.02e-01

Pos logit contributions
��+0.970
adelphia+0.933
cens+0.928
aries+0.845
buster+0.838
Neg logit contributions
AMS-1.501
bara-1.476
Keefe-1.447
enhagen-1.443
ACTED-1.435
Tokenists
Token ID1023
Feature activation-8.49e-01

Pos logit contributions
��+0.733
adelphia+0.674
cens+0.660
aries+0.536
buster+0.519
Neg logit contributions
AMS-3.095
bara-3.055
Keefe-3.012
enhagen-3.006
ACTED-2.984
Token like
Token ID588
Feature activation-1.68e-02

Pos logit contributions
��+2.401
adelphia+2.308
cens+2.290
aries+2.131
buster+2.102
Neg logit contributions
AMS-2.990
bara-2.927
enhagen-2.871
Keefe-2.866
ACTED-2.836
Token team
Token ID1074
Feature activation-1.55e-01

Pos logit contributions
��+0.309
adelphia+0.297
cens+0.294
aries+0.271
buster+0.269
Neg logit contributions
AMS-0.388
bara-0.381
Keefe-0.373
enhagen-0.372
ACTED-0.367
Token
Token ID447
Feature activation+1.12e-01

Pos logit contributions
��+0.470
adelphia+0.454
cens+0.450
aries+0.417
buster+0.414
Neg logit contributions
AMS-0.516
bara-0.507
Keefe-0.494
enhagen-0.493
ACTED-0.487
Token
Token ID247
Feature activation-1.33e-01

Pos logit contributions
AMS+0.436
bara+0.427
Keefe+0.419
enhagen+0.414
ACTED+0.413
Neg logit contributions
��-0.270
adelphia-0.268
cens-0.265
aries-0.239
oslov-0.237
Tokens
Token ID82
Feature activation-9.04e-02

Pos logit contributions
��+0.376
adelphia+0.361
cens+0.357
aries+0.329
buster+0.326
Neg logit contributions
AMS-0.475
bara-0.467
Keefe-0.457
enhagen-0.455
ACTED-0.450
Token third
Token ID2368
Feature activation-5.08e-01

Pos logit contributions
��+0.258
adelphia+0.248
cens+0.246
aries+0.226
buster+0.225
Neg logit contributions
AMS-0.318
bara-0.312
Keefe-0.306
enhagen-0.305
ACTED-0.301
Token straight
Token ID3892
Feature activation-2.16e+00

Pos logit contributions
��+1.487
adelphia+1.437
cens+1.415
aries+1.323
buster+1.305
Neg logit contributions
AMS-1.742
bara-1.721
enhagen-1.673
Keefe-1.671
ACTED-1.647
Token in
Token ID287
Feature activation-3.02e-01

Pos logit contributions
��+5.956
adelphia+5.780
cens+5.570
 Homo+5.385
buster+5.359
Neg logit contributions
bara-7.221
AMS-7.110
enhagen-6.927
Keefe-6.840
ACTED-6.788
Token pads
Token ID21226
Feature activation+6.97e-01

Pos logit contributions
��+0.831
adelphia+0.801
cens+0.790
aries+0.729
buster+0.721
Neg logit contributions
AMS-1.092
bara-1.074
enhagen-1.049
Keefe-1.049
ACTED-1.035
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
AMS+2.380
bara+2.327
Keefe+2.287
enhagen+2.264
unning+2.261
Neg logit contributions
��-2.008
adelphia-1.973
cens-1.959
aries-1.792
oslov-1.770
Token that
Token ID326
Feature activation-4.27e-01

Pos logit contributions
��+0.531
adelphia+0.512
cens+0.506
aries+0.468
buster+0.464
Neg logit contributions
AMS-0.644
bara-0.633
Keefe-0.619
enhagen-0.617
ACTED-0.610
Token focused
Token ID5670
Feature activation-1.83e-01

Pos logit contributions
��+1.216
adelphia+1.175
cens+1.163
aries+1.078
buster+1.067
Neg logit contributions
AMS-1.500
bara-1.472
enhagen-1.438
Keefe-1.435
ACTED-1.417
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
��+0.043
adelphia+0.042
cens+0.041
aries+0.038
buster+0.038
Neg logit contributions
AMS-0.052
bara-0.051
Keefe-0.050
enhagen-0.049
ACTED-0.049
Token
Token ID198
Feature activation+2.39e-01

Pos logit contributions
��+0.392
adelphia+0.378
cens+0.375
aries+0.343
buster+0.340
Neg logit contributions
AMS-0.597
bara-0.589
enhagen-0.579
Keefe-0.575
ACTED-0.569
TokenThe
Token ID464
Feature activation-2.04e-01

Pos logit contributions
AMS+0.692
bara+0.677
Keefe+0.659
enhagen+0.655
ACTED+0.647
Neg logit contributions
��-0.832
adelphia-0.807
cens-0.800
aries-0.750
buster-0.745
Token @
Token ID2488
Feature activation-1.67e-01

Pos logit contributions
��+0.563
adelphia+0.542
cens+0.536
aries+0.493
buster+0.489
Neg logit contributions
AMS-0.734
bara-0.723
Keefe-0.706
enhagen-0.705
ACTED-0.696
TokenT
Token ID51
Feature activation-1.40e-01

Pos logit contributions
��+0.557
adelphia+0.540
cens+0.536
aries+0.500
buster+0.497
Neg logit contributions
AMS-0.504
bara-0.494
Keefe-0.481
enhagen-0.480
ACTED-0.473
Tokenucker
Token ID12603
Feature activation-2.14e+00

Pos logit contributions
��+0.249
adelphia+0.237
cens+0.232
aries+0.203
buster+0.201
Neg logit contributions
AMS-0.641
bara-0.635
enhagen-0.623
Keefe-0.621
ACTED-0.617
TokenCarl
Token ID26886
Feature activation-1.45e+00

Pos logit contributions
adelphia+6.483
��+6.426
cens+6.323
buster+6.113
aries+5.729
Neg logit contributions
enhagen-6.320
bara-6.219
AMS-6.138
unning-6.050
ACTED-5.962
Tokenson
Token ID1559
Feature activation-1.03e+00

Pos logit contributions
��+3.616
adelphia+3.614
cens+3.523
oslov+3.286
aries+3.264
Neg logit contributions
AMS-5.316
bara-5.260
ACTED-5.207
enhagen-5.173
Keefe-5.133
Token opening
Token ID4756
Feature activation-1.52e-01

Pos logit contributions
��+3.097
adelphia+3.032
cens+2.990
aries+2.802
buster+2.767
Neg logit contributions
AMS-3.365
bara-3.329
enhagen-3.252
ACTED-3.209
Keefe-3.203
Token statement
Token ID2643
Feature activation-5.08e-01

Pos logit contributions
��+0.422
adelphia+0.406
cens+0.401
aries+0.368
buster+0.365
Neg logit contributions
AMS-0.549
bara-0.540
Keefe-0.528
enhagen-0.526
ACTED-0.520
Token about
Token ID546
Feature activation-1.10e-02

Pos logit contributions
��+1.503
adelphia+1.453
cens+1.445
aries+1.355
buster+1.335
Neg logit contributions
AMS-1.718
bara-1.683
Keefe-1.645
enhagen-1.642
ACTED-1.629
Token replacing
Token ID13586
Feature activation-6.27e-01

Pos logit contributions
��+0.219
adelphia+0.211
cens+0.209
aries+0.194
buster+0.193
Neg logit contributions
AMS-0.247
bara-0.242
Keefe-0.236
enhagen-0.236
ACTED-0.233
Token Confederate
Token ID21900
Feature activation-9.83e-01

Pos logit contributions
��+1.807
adelphia+1.749
cens+1.735
aries+1.605
buster+1.588
Neg logit contributions
AMS-2.174
bara-2.133
Keefe-2.086
enhagen-2.077
ACTED-2.054
Token General
Token ID3611
Feature activation+2.04e-01

Pos logit contributions
��+2.530
cens+2.447
adelphia+2.438
aries+2.272
buster+2.251
Neg logit contributions
AMS-3.657
bara-3.610
Keefe-3.538
enhagen-3.528
ACTED-3.476
Token Edmund
Token ID35646
Feature activation-6.46e-01

Pos logit contributions
AMS+0.592
bara+0.587
Keefe+0.574
unning+0.561
enhagen+0.560
Neg logit contributions
��-0.708
adelphia-0.679
cens-0.674
taboola-0.626
ipel-0.624
Token Kirby
Token ID23965
Feature activation-6.51e-01

Pos logit contributions
��+2.102
adelphia+2.029
cens+2.013
aries+1.872
buster+1.864
Neg logit contributions
AMS-2.016
bara-1.972
Keefe-1.928
enhagen-1.917
ACTED-1.896
Token Smith
Token ID4176
Feature activation-2.14e+00

Pos logit contributions
��+1.941
adelphia+1.881
cens+1.867
buster+1.720
aries+1.720
Neg logit contributions
AMS-2.184
bara-2.145
enhagen-2.092
Keefe-2.091
ACTED-2.075
Token.[
Token ID3693
Feature activation-2.89e-01

Pos logit contributions
��+5.634
cens+5.508
adelphia+5.419
buster+5.099
oslov+5.052
Neg logit contributions
AMS-7.441
bara-7.363
enhagen-7.113
Keefe-7.096
unning-7.074
Token7
Token ID22
Feature activation+2.84e-01

Pos logit contributions
��+1.132
cens+1.103
adelphia+1.099
buster+1.038
aries+1.038
Neg logit contributions
AMS-0.697
bara-0.681
enhagen-0.667
Keefe-0.655
ACTED-0.648
Token]
Token ID60
Feature activation+3.07e-01

Pos logit contributions
AMS+0.866
bara+0.847
Keefe+0.826
enhagen+0.822
ACTED+0.814
Neg logit contributions
��-0.941
adelphia-0.912
cens-0.902
aries-0.843
buster-0.838
Token
Token ID198
Feature activation-4.68e-01

Pos logit contributions
AMS+1.057
bara+1.037
Keefe+1.020
ACTED+1.000
enhagen+0.999
Neg logit contributions
��-0.908
adelphia-0.863
cens-0.849
aries-0.787
buster-0.780
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
��+1.071
cens+1.058
adelphia+1.055
aries+0.969
buster+0.958
Neg logit contributions
AMS-1.856
enhagen-1.834
bara-1.830
Keefe-1.784
ACTED-1.771
Token:
Token ID25
Feature activation-5.99e-01

Pos logit contributions
��+2.103
adelphia+1.955
cens+1.943
aries+1.804
oslov+1.782
Neg logit contributions
AMS-2.752
bara-2.700
enhagen-2.696
ACTED-2.628
Keefe-2.628
Token Clinton
Token ID2605
Feature activation-4.48e-01

Pos logit contributions
��+1.632
cens+1.462
adelphia+1.420
taboola+1.389
buster+1.373
Neg logit contributions
AMS-2.237
bara-2.171
Keefe-2.157
enhagen-2.150
ACTED-2.113
Token staff
Token ID3085
Feature activation+3.50e-01

Pos logit contributions
��+1.412
adelphia+1.368
cens+1.354
aries+1.257
buster+1.249
Neg logit contributions
AMS-1.442
bara-1.417
Keefe-1.381
enhagen-1.374
ACTED-1.359
Token are
Token ID389
Feature activation-2.50e-01

Pos logit contributions
AMS+1.130
bara+1.105
Keefe+1.085
enhagen+1.076
ACTED+1.054
Neg logit contributions
��-1.090
adelphia-1.065
cens-1.051
aries-0.975
buster-0.972
Token '
Token ID705
Feature activation-3.75e-01

Pos logit contributions
��+0.730
adelphia+0.711
cens+0.695
oslov+0.638
taboola+0.637
Neg logit contributions
AMS-0.871
bara-0.848
Keefe-0.843
enhagen-0.828
ACTED-0.822
Tokenbig
Token ID14261
Feature activation-2.14e+00

Pos logit contributions
��+0.854
cens+0.847
adelphia+0.789
buster+0.753
aries+0.750
Neg logit contributions
AMS-1.528
bara-1.488
enhagen-1.466
Keefe-1.454
ACTED-1.445
Tokengest
Token ID3495
Feature activation-1.30e+00

Pos logit contributions
��+5.193
aries+5.170
cens+5.166
adelphia+4.906
oslov+4.717
Neg logit contributions
AMS-8.039
bara-7.794
enhagen-7.704
ACTED-7.573
Keefe-7.548
Token a
Token ID257
Feature activation-5.06e-01

Pos logit contributions
��+2.757
cens+2.666
adelphia+2.572
aries+2.533
buster+2.487
Neg logit contributions
bara-5.275
AMS-5.239
enhagen-5.134
ACTED-5.088
unning-5.075
Token--
Token ID438
Feature activation-7.79e-01

Pos logit contributions
��+1.525
adelphia+1.478
cens+1.456
oslov+1.361
buster+1.330
Neg logit contributions
AMS-1.681
bara-1.672
Keefe-1.649
unning-1.609
enhagen-1.599
Tokenholes
Token ID28439
Feature activation-7.84e-01

Pos logit contributions
��+2.315
adelphia+2.242
cens+2.231
aries+2.068
buster+2.065
Neg logit contributions
AMS-2.624
bara-2.558
enhagen-2.520
Keefe-2.498
ACTED-2.489
Token in
Token ID287
Feature activation-2.97e-01

Pos logit contributions
��+2.054
adelphia+1.962
cens+1.942
aries+1.822
buster+1.781
Neg logit contributions
AMS-2.916
bara-2.887
enhagen-2.838
Keefe-2.802
ACTED-2.790
Token A
Token ID317
Feature activation+4.31e-01

Pos logit contributions
AMS+0.311
bara+0.304
Keefe+0.297
enhagen+0.296
ACTED+0.294
Neg logit contributions
��-0.256
adelphia-0.246
cens-0.243
aries-0.223
buster-0.223
TokenUS
Token ID2937
Feature activation+1.46e-01

Pos logit contributions
AMS+1.287
bara+1.225
Keefe+1.203
ACTED+1.185
unning+1.173
Neg logit contributions
��-1.504
adelphia-1.443
cens-1.427
buster-1.333
aries-1.332
Token 16
Token ID1467
Feature activation+4.39e-01

Pos logit contributions
AMS+0.551
bara+0.541
Keefe+0.531
enhagen+0.528
unning+0.523
Neg logit contributions
��-0.379
adelphia-0.367
cens-0.361
buster-0.327
oslov-0.326
Token Steele
Token ID28549
Feature activation-2.66e-01

Pos logit contributions
AMS+1.378
bara+1.356
Keefe+1.327
ACTED+1.287
enhagen+1.286
Neg logit contributions
��-1.418
adelphia-1.371
cens-1.343
buster-1.248
taboola-1.241
Token Von
Token ID26985
Feature activation-1.73e-03

Pos logit contributions
��+0.794
adelphia+0.766
cens+0.759
aries+0.703
buster+0.698
Neg logit contributions
AMS-0.899
bara-0.883
Keefe-0.862
enhagen-0.860
ACTED-0.849
Token Hoff
Token ID21890
Feature activation-2.13e+00

Pos logit contributions
��+0.005
adelphia+0.005
cens+0.005
aries+0.004
oslov+0.004
Neg logit contributions
AMS-0.006
bara-0.006
Keefe-0.006
enhagen-0.006
unning-0.006
Token (
Token ID357
Feature activation+6.52e-01

Pos logit contributions
��+5.199
cens+4.931
adelphia+4.858
buster+4.645
aries+4.499
Neg logit contributions
AMS-7.949
bara-7.766
ACTED-7.712
Keefe-7.626
unning-7.480
TokenTeam
Token ID15592
Feature activation+5.86e-01

Pos logit contributions
AMS+1.962
Keefe+1.842
bara+1.836
ACTED+1.789
unning+1.756
Neg logit contributions
��-2.262
adelphia-2.166
cens-2.144
oslov-2.009
buster-2.004
Token Chip
Token ID17869
Feature activation+3.03e-01

Pos logit contributions
AMS+2.361
bara+2.274
Keefe+2.242
unning+2.217
ACTED+2.216
Neg logit contributions
��-1.421
adelphia-1.306
cens-1.303
taboola-1.165
buster-1.162
Tokenotle
Token ID23556
Feature activation-4.53e-01

Pos logit contributions
AMS+0.891
bara+0.873
Keefe+0.849
enhagen+0.846
ACTED+0.834
Neg logit contributions
��-1.039
adelphia-1.007
cens-0.998
aries-0.934
buster-0.928
Token)
Token ID8
Feature activation+3.08e-01

Pos logit contributions
��+1.597
adelphia+1.550
cens+1.540
aries+1.447
buster+1.435
Neg logit contributions
AMS-1.282
bara-1.254
Keefe-1.219
enhagen-1.219
ACTED-1.199
Token,
Token ID11
Feature activation-5.00e-01

Pos logit contributions
��+1.371
adelphia+1.323
cens+1.317
aries+1.225
buster+1.213
Neg logit contributions
AMS-1.540
bara-1.507
Keefe-1.476
enhagen-1.469
ACTED-1.452
Token which
Token ID543
Feature activation-5.32e-01

Pos logit contributions
��+1.336
adelphia+1.280
cens+1.272
aries+1.175
buster+1.166
Neg logit contributions
AMS-1.845
bara-1.807
enhagen-1.772
Keefe-1.771
ACTED-1.747
Token would
Token ID561
Feature activation-8.98e-01

Pos logit contributions
��+1.566
adelphia+1.507
cens+1.500
aries+1.418
buster+1.398
Neg logit contributions
AMS-1.803
bara-1.764
enhagen-1.733
Keefe-1.714
ACTED-1.705
Token have
Token ID423
Feature activation+1.11e-01

Pos logit contributions
��+2.535
adelphia+2.445
cens+2.428
buster+2.325
aries+2.296
Neg logit contributions
AMS-3.136
bara-3.041
enhagen-3.007
Keefe-2.989
ACTED-2.946
Token qu
Token ID627
Feature activation-5.05e-02

Pos logit contributions
AMS+0.348
bara+0.342
Keefe+0.333
enhagen+0.332
ACTED+0.327
Neg logit contributions
��-0.360
adelphia-0.348
cens-0.345
aries-0.321
buster-0.319
Tokenelled
Token ID11978
Feature activation-2.13e+00

Pos logit contributions
��+0.199
adelphia+0.193
cens+0.191
aries+0.180
buster+0.180
Neg logit contributions
AMS-0.124
bara-0.121
Keefe-0.117
enhagen-0.117
unning-0.114
Token demand
Token ID3512
Feature activation-1.19e+00

Pos logit contributions
��+5.283
cens+5.124
adelphia+5.014
 Homo+4.860
aries+4.858
Neg logit contributions
AMS-7.732
bara-7.545
enhagen-7.394
Keefe-7.385
ACTED-7.384
Token for
Token ID329
Feature activation-3.97e-01

Pos logit contributions
��+3.196
cens+3.122
adelphia+3.091
aries+2.948
buster+2.905
Neg logit contributions
AMS-4.206
bara-4.157
Keefe-4.041
enhagen-4.029
ACTED-3.977
Token Argentine
Token ID36399
Feature activation-9.47e-01

Pos logit contributions
��+1.157
adelphia+1.116
cens+1.108
aries+1.035
oslov+1.021
Neg logit contributions
AMS-1.366
bara-1.335
Keefe-1.311
enhagen-1.308
ACTED-1.288
Token debt
Token ID5057
Feature activation-5.69e-01

Pos logit contributions
��+2.596
cens+2.502
adelphia+2.500
aries+2.307
oslov+2.303
Neg logit contributions
AMS-3.393
bara-3.327
Keefe-3.279
enhagen-3.271
ACTED-3.206
Token;
Token ID26
Feature activation+2.33e-02

Pos logit contributions
��+1.642
adelphia+1.585
cens+1.569
aries+1.460
buster+1.447
Neg logit contributions
AMS-1.975
bara-1.946
Keefe-1.900
enhagen-1.889
ACTED-1.869
Token 4
Token ID604
Feature activation+5.72e-01

Pos logit contributions
��+1.316
adelphia+1.271
cens+1.266
buster+1.140
aries+1.130
Neg logit contributions
AMS-2.343
bara-2.305
Keefe-2.266
enhagen-2.258
ACTED-2.257
Token of
Token ID286
Feature activation+2.93e-01

Pos logit contributions
AMS+1.738
bara+1.698
Keefe+1.672
enhagen+1.648
unning+1.628
Neg logit contributions
��-1.857
adelphia-1.817
cens-1.806
aries-1.669
oslov-1.662
Token an
Token ID281
Feature activation+7.76e-02

Pos logit contributions
AMS+1.017
bara+0.996
Keefe+0.977
enhagen+0.974
ACTED+0.963
Neg logit contributions
��-0.846
cens-0.814
adelphia-0.813
aries-0.747
buster-0.741
Token Eastern
Token ID8345
Feature activation-7.03e-02

Pos logit contributions
AMS+0.245
bara+0.239
Keefe+0.233
enhagen+0.233
unning+0.229
Neg logit contributions
��-0.249
adelphia-0.241
cens-0.239
aries-0.222
buster-0.221
Token Conference
Token ID8785
Feature activation+1.06e+00

Pos logit contributions
��+0.226
adelphia+0.219
cens+0.217
buster+0.200
aries+0.199
Neg logit contributions
AMS-0.220
bara-0.217
Keefe-0.211
enhagen-0.210
ACTED-0.208
Token playoff
Token ID13119
Feature activation+1.21e+00

Pos logit contributions
AMS+3.517
bara+3.454
Keefe+3.388
unning+3.351
enhagen+3.347
Neg logit contributions
��-3.116
cens-3.006
adelphia-2.963
emia-2.711
oslov-2.690
Token series
Token ID2168
Feature activation+1.94e-01

Pos logit contributions
AMS+3.961
bara+3.850
Keefe+3.812
unning+3.800
enhagen+3.741
Neg logit contributions
��-3.594
cens-3.459
adelphia-3.412
taboola-3.154
emia-3.145
Token,
Token ID11
Feature activation+3.76e-01

Pos logit contributions
AMS+0.652
bara+0.639
Keefe+0.625
enhagen+0.623
unning+0.614
Neg logit contributions
��-0.584
adelphia-0.559
cens-0.555
aries-0.511
oslov-0.509
Token said
Token ID531
Feature activation+2.36e-01

Pos logit contributions
AMS+1.216
bara+1.202
enhagen+1.165
Keefe+1.156
ACTED+1.147
Neg logit contributions
��-1.184
adelphia-1.128
cens-1.126
oslov-1.034
aries-1.028
Token on
Token ID319
Feature activation+3.13e-01

Pos logit contributions
AMS+0.817
bara+0.805
Keefe+0.786
enhagen+0.781
ACTED+0.773
Neg logit contributions
��-0.685
adelphia-0.657
cens-0.652
aries-0.600
buster-0.596
Token the
Token ID262
Feature activation+5.07e-01

Pos logit contributions
AMS+1.191
bara+1.171
Keefe+1.147
enhagen+1.145
ACTED+1.128
Neg logit contributions
��-0.800
adelphia-0.763
cens-0.755
aries-0.690
oslov-0.683
Token.
Token ID13
Feature activation+3.32e-01

Pos logit contributions
AMS+2.098
bara+2.089
enhagen+1.995
unning+1.992
Keefe+1.981
Neg logit contributions
��-2.223
adelphia-2.181
cens-2.125
buster-1.971
oslov-1.965
Token (
Token ID357
Feature activation+1.14e+00

Pos logit contributions
AMS+1.181
bara+1.149
Keefe+1.127
ACTED+1.110
enhagen+1.106
Neg logit contributions
��-0.950
adelphia-0.913
cens-0.898
aries-0.821
buster-0.812
TokenI
Token ID40
Feature activation+1.14e+00

Pos logit contributions
AMS+3.241
bara+3.103
Keefe+3.051
enhagen+2.946
unning+2.942
Neg logit contributions
��-4.066
adelphia-3.931
cens-3.804
aries-3.595
oslov-3.592
Token am
Token ID716
Feature activation+3.96e-01

Pos logit contributions
AMS+3.565
bara+3.554
enhagen+3.333
Keefe+3.324
unning+3.309
Neg logit contributions
��-3.679
adelphia-3.593
cens-3.442
taboola-3.202
buster-3.186
Token talking
Token ID3375
Feature activation+1.32e+00

Pos logit contributions
AMS+1.282
bara+1.266
Keefe+1.222
enhagen+1.218
unning+1.203
Neg logit contributions
��-1.242
adelphia-1.205
cens-1.175
aries-1.091
buster-1.089
Token of
Token ID286
Feature activation+1.04e+00

Pos logit contributions
AMS+4.424
bara+4.321
enhagen+4.200
Keefe+4.190
unning+4.139
Neg logit contributions
��-3.789
adelphia-3.760
cens-3.680
taboola-3.398
buster-3.344
Token elegance
Token ID49198
Feature activation+6.36e-01

Pos logit contributions
AMS+3.518
bara+3.433
enhagen+3.338
Keefe+3.331
unning+3.318
Neg logit contributions
��-3.008
adelphia-2.958
cens-2.903
buster-2.658
taboola-2.644
Token in
Token ID287
Feature activation+3.25e-01

Pos logit contributions
AMS+1.941
bara+1.913
enhagen+1.858
Keefe+1.855
unning+1.822
Neg logit contributions
��-2.093
adelphia-2.030
cens-1.991
buster-1.851
oslov-1.847
Token the
Token ID262
Feature activation+5.38e-01

Pos logit contributions
AMS+1.115
bara+1.097
Keefe+1.064
enhagen+1.063
ACTED+1.050
Neg logit contributions
��-0.954
adelphia-0.928
cens-0.911
buster-0.837
oslov-0.831
Token mathematical
Token ID18069
Feature activation+3.57e-01

Pos logit contributions
AMS+1.782
bara+1.750
Keefe+1.702
enhagen+1.700
unning+1.676
Neg logit contributions
��-1.628
adelphia-1.591
cens-1.557
buster-1.430
aries-1.425
Token
Token ID198
Feature activation+3.17e-01

Pos logit contributions
AMS+1.110
bara+1.087
Keefe+1.062
enhagen+1.056
unning+1.042
Neg logit contributions
��-1.164
adelphia-1.125
cens-1.108
aries-1.028
buster-1.025
Token Gram
Token ID20159
Feature activation-7.37e-01

Pos logit contributions
AMS+1.520
bara+1.505
Keefe+1.476
enhagen+1.452
unning+1.442
Neg logit contributions
��-0.945
adelphia-0.886
cens-0.872
aries-0.786
buster-0.778
Tokenmer
Token ID647
Feature activation-2.55e-01

Pos logit contributions
adelphia+2.293
��+2.266
cens+2.259
buster+2.161
aries+2.139
Neg logit contributions
AMS-2.302
enhagen-2.249
ACTED-2.215
bara-2.189
Keefe-2.182
Token
Token ID198
Feature activation-2.60e-01

Pos logit contributions
��+0.622
adelphia+0.605
cens+0.603
aries+0.549
buster+0.545
Neg logit contributions
AMS-0.990
bara-0.974
enhagen-0.962
Keefe-0.950
ACTED-0.943
Token
Token ID198
Feature activation+1.37e-01

Pos logit contributions
��+0.627
adelphia+0.610
cens+0.610
aries+0.558
buster+0.552
Neg logit contributions
AMS-1.016
bara-1.000
enhagen-0.993
Keefe-0.977
ACTED-0.968
Token2004
Token ID15724
Feature activation+5.38e-01

Pos logit contributions
AMS+0.365
bara+0.357
enhagen+0.356
Keefe+0.344
ACTED+0.341
Neg logit contributions
��-0.498
adelphia-0.490
cens-0.486
aries-0.459
buster-0.455
Token Larry
Token ID13633
Feature activation+1.26e+00

Pos logit contributions
AMS+1.530
bara+1.501
Keefe+1.467
enhagen+1.426
ACTED+1.415
Neg logit contributions
��-1.896
adelphia-1.833
cens-1.813
ipel-1.676
aries-1.675
Token David
Token ID3271
Feature activation+3.22e-01

Pos logit contributions
AMS+2.869
bara+2.766
Keefe+2.765
unning+2.569
ACTED+2.505
Neg logit contributions
��-5.163
adelphia-4.914
cens-4.901
ipel-4.600
taboola-4.557
Token
Token ID198
Feature activation+2.05e-01

Pos logit contributions
AMS+1.192
bara+1.173
Keefe+1.151
enhagen+1.133
ACTED+1.130
Neg logit contributions
��-0.874
adelphia-0.829
cens-0.814
aries-0.746
buster-0.739
Token
Token ID198
Feature activation+4.51e-01

Pos logit contributions
AMS+0.764
bara+0.752
Keefe+0.737
enhagen+0.729
ACTED+0.726
Neg logit contributions
��-0.545
adelphia-0.520
cens-0.512
aries-0.468
buster-0.464
Token2004
Token ID15724
Feature activation+6.78e-01

Pos logit contributions
AMS+1.171
bara+1.144
enhagen+1.118
Keefe+1.104
ACTED+1.087
Neg logit contributions
��-1.692
adelphia-1.652
cens-1.639
aries-1.544
buster-1.535
Token Matt
Token ID4705
Feature activation+1.47e-01

Pos logit contributions
AMS+1.953
bara+1.906
Keefe+1.879
enhagen+1.808
unning+1.805
Neg logit contributions
��-2.362
adelphia-2.285
cens-2.270
ipel-2.088
buster-2.087
Token happening
Token ID5836
Feature activation+6.40e-01

Pos logit contributions
��+0.264
adelphia+0.254
cens+0.252
aries+0.231
buster+0.230
Neg logit contributions
AMS-0.342
bara-0.336
Keefe-0.329
enhagen-0.328
ACTED-0.324
Token in
Token ID287
Feature activation+2.98e-01

Pos logit contributions
AMS+1.940
bara+1.913
Keefe+1.859
enhagen+1.857
ACTED+1.814
Neg logit contributions
��-2.111
adelphia-2.056
cens-2.016
buster-1.879
aries-1.871
Token the
Token ID262
Feature activation+4.46e-01

Pos logit contributions
AMS+1.018
bara+0.999
Keefe+0.979
enhagen+0.978
ACTED+0.961
Neg logit contributions
��-0.877
adelphia-0.848
cens-0.837
buster-0.773
aries-0.771
Token vent
Token ID7435
Feature activation+6.18e-01

Pos logit contributions
AMS+1.565
bara+1.539
Keefe+1.503
enhagen+1.500
ACTED+1.484
Neg logit contributions
��-1.272
adelphia-1.229
cens-1.208
aries-1.111
buster-1.110
Tokenral
Token ID1373
Feature activation-4.18e-04

Pos logit contributions
AMS+1.015
bara+1.007
enhagen+0.924
Keefe+0.910
unning+0.908
Neg logit contributions
��-2.914
adelphia-2.851
cens-2.790
oslov-2.673
buster-2.670
Token sensory
Token ID23326
Feature activation+1.14e+00

Pos logit contributions
��+0.001
adelphia+0.001
cens+0.001
aries+0.001
buster+0.001
Neg logit contributions
AMS-0.001
bara-0.001
Keefe-0.001
enhagen-0.001
ACTED-0.001
Token motor
Token ID5584
Feature activation-9.21e-02

Pos logit contributions
AMS+3.611
bara+3.595
enhagen+3.448
Keefe+3.441
unning+3.412
Neg logit contributions
��-3.565
adelphia-3.445
cens-3.387
buster-3.163
oslov-3.138
Token cortex
Token ID20223
Feature activation+2.38e-01

Pos logit contributions
��+0.320
adelphia+0.311
cens+0.307
aries+0.288
buster+0.288
Neg logit contributions
AMS-0.266
bara-0.261
Keefe-0.253
enhagen-0.252
ACTED-0.248
Token (
Token ID357
Feature activation+9.28e-01

Pos logit contributions
AMS+0.834
bara+0.821
Keefe+0.800
enhagen+0.800
ACTED+0.788
Neg logit contributions
��-0.683
adelphia-0.659
cens-0.649
aries-0.598
buster-0.596
Tokenv
Token ID85
Feature activation+2.61e-01

Pos logit contributions
AMS+2.850
bara+2.708
Keefe+2.647
ACTED+2.630
enhagen+2.617
Neg logit contributions
��-3.132
adelphia-3.011
cens-2.921
aries-2.766
 Gutenberg-2.738
TokenS
Token ID50
Feature activation-2.93e-02

Pos logit contributions
AMS+0.837
bara+0.805
Keefe+0.785
enhagen+0.780
unning+0.777
Neg logit contributions
��-0.848
adelphia-0.811
cens-0.798
buster-0.738
aries-0.732
Token.
Token ID13
Feature activation-4.12e-02

Pos logit contributions
AMS+1.919
bara+1.892
Keefe+1.833
enhagen+1.832
ACTED+1.798
Neg logit contributions
��-1.926
adelphia-1.861
cens-1.824
aries-1.702
oslov-1.686
Token This
Token ID770
Feature activation+6.40e-01

Pos logit contributions
��+0.122
adelphia+0.118
cens+0.116
aries+0.108
buster+0.107
Neg logit contributions
AMS-0.141
bara-0.138
Keefe-0.135
enhagen-0.134
ACTED-0.133
Token was
Token ID373
Feature activation-1.91e-01

Pos logit contributions
AMS+2.081
bara+2.057
Keefe+2.007
enhagen+1.979
ACTED+1.965
Neg logit contributions
��-2.002
adelphia-1.925
cens-1.887
aries-1.745
buster-1.727
Token achieved
Token ID8793
Feature activation+6.10e-01

Pos logit contributions
��+0.603
adelphia+0.583
cens+0.578
aries+0.538
buster+0.534
Neg logit contributions
AMS-0.610
bara-0.599
Keefe-0.584
enhagen-0.583
ACTED-0.575
Token by
Token ID416
Feature activation+3.57e-01

Pos logit contributions
AMS+1.794
bara+1.760
Keefe+1.703
enhagen+1.687
ACTED+1.665
Neg logit contributions
��-2.090
adelphia-2.029
cens-1.983
aries-1.846
buster-1.844
Token repeatedly
Token ID7830
Feature activation+9.47e-01

Pos logit contributions
AMS+1.199
bara+1.176
Keefe+1.147
enhagen+1.131
unning+1.125
Neg logit contributions
��-1.075
adelphia-1.039
cens-1.025
aries-0.945
buster-0.944
Token restart
Token ID15765
Feature activation-2.06e-01

Pos logit contributions
AMS+3.245
bara+3.211
Keefe+3.105
unning+3.059
enhagen+3.047
Neg logit contributions
��-2.748
adelphia-2.619
cens-2.565
oslov-2.375
aries-2.361
Tokening
Token ID278
Feature activation-4.72e-01

Pos logit contributions
��+0.449
adelphia+0.427
cens+0.421
aries+0.377
buster+0.373
Neg logit contributions
AMS-0.866
bara-0.854
Keefe-0.837
enhagen-0.835
ACTED-0.827
Token the
Token ID262
Feature activation-3.21e-01

Pos logit contributions
��+1.290
adelphia+1.241
cens+1.226
aries+1.131
buster+1.123
Neg logit contributions
AMS-1.712
bara-1.688
Keefe-1.651
enhagen-1.646
ACTED-1.628
Token engine
Token ID3113
Feature activation-2.95e-01

Pos logit contributions
��+0.853
adelphia+0.819
cens+0.810
aries+0.743
buster+0.737
Neg logit contributions
AMS-1.193
bara-1.175
Keefe-1.149
enhagen-1.146
ACTED-1.134
Token in
Token ID287
Feature activation-4.43e-01

Pos logit contributions
��+0.852
adelphia+0.821
cens+0.816
aries+0.757
buster+0.750
Neg logit contributions
AMS-1.021
bara-1.004
Keefe-0.983
enhagen-0.979
ACTED-0.968
Token in
Token ID287
Feature activation-1.23e-01

Pos logit contributions
AMS+1.184
bara+1.168
Keefe+1.133
enhagen+1.125
ACTED+1.115
Neg logit contributions
��-1.277
adelphia-1.242
cens-1.223
aries-1.141
buster-1.138
Token America
Token ID2253
Feature activation+1.63e-01

Pos logit contributions
��+0.349
adelphia+0.337
cens+0.333
aries+0.307
buster+0.305
Neg logit contributions
AMS-0.431
bara-0.424
Keefe-0.415
enhagen-0.413
ACTED-0.409
Token.
Token ID13
Feature activation-1.88e-03

Pos logit contributions
AMS+0.532
bara+0.524
Keefe+0.510
enhagen+0.509
ACTED+0.504
Neg logit contributions
��-0.505
adelphia-0.488
cens-0.482
aries-0.448
buster-0.446
Token
Token ID447
Feature activation+6.57e-02

Pos logit contributions
��+0.005
adelphia+0.005
cens+0.005
aries+0.005
buster+0.005
Neg logit contributions
AMS-0.007
bara-0.007
Keefe-0.006
enhagen-0.006
ACTED-0.006
Token
Token ID251
Feature activation+3.40e-02

Pos logit contributions
AMS+0.274
bara+0.270
Keefe+0.266
enhagen+0.265
ACTED+0.262
Neg logit contributions
��-0.142
adelphia-0.137
cens-0.136
aries-0.122
buster-0.120
Token The
Token ID383
Feature activation+3.61e-01

Pos logit contributions
AMS+0.123
bara+0.121
Keefe+0.119
enhagen+0.118
ACTED+0.117
Neg logit contributions
��-0.093
adelphia-0.090
cens-0.089
aries-0.081
buster-0.081
Token post
Token ID1281
Feature activation-4.12e-01

Pos logit contributions
AMS+1.282
bara+1.268
Keefe+1.243
enhagen+1.239
ACTED+1.217
Neg logit contributions
��-1.008
adelphia-0.970
cens-0.957
buster-0.880
aries-0.877
Token in
Token ID287
Feature activation-2.59e-01

Pos logit contributions
��+1.233
adelphia+1.189
cens+1.180
aries+1.100
buster+1.087
Neg logit contributions
AMS-1.390
bara-1.361
Keefe-1.330
enhagen-1.326
ACTED-1.315
Token which
Token ID543
Feature activation+1.40e-01

Pos logit contributions
��+0.699
adelphia+0.672
cens+0.664
aries+0.609
buster+0.604
Neg logit contributions
AMS-0.949
bara-0.935
Keefe-0.915
enhagen-0.911
ACTED-0.902
Token that
Token ID326
Feature activation-4.03e-02

Pos logit contributions
AMS+0.422
bara+0.415
Keefe+0.405
enhagen+0.404
ACTED+0.396
Neg logit contributions
��-0.468
adelphia-0.454
cens-0.449
aries-0.418
buster-0.417
Token account
Token ID1848
Feature activation-1.24e+00

Pos logit contributions
��+0.111
adelphia+0.107
cens+0.105
aries+0.097
buster+0.096
Neg logit contributions
AMS-0.146
bara-0.144
Keefe-0.141
enhagen-0.140
ACTED-0.138
Token come
Token ID1282
Feature activation+4.09e-01

Pos logit contributions
��+0.554
adelphia+0.537
cens+0.531
aries+0.495
buster+0.491
Neg logit contributions
AMS-0.622
bara-0.609
Keefe-0.597
enhagen-0.596
ACTED-0.588
Token to
Token ID284
Feature activation+2.35e-01

Pos logit contributions
AMS+1.317
bara+1.300
Keefe+1.259
enhagen+1.254
ACTED+1.241
Neg logit contributions
��-1.297
adelphia-1.251
cens-1.225
aries-1.131
buster-1.127
Token watch
Token ID2342
Feature activation+3.08e-01

Pos logit contributions
AMS+0.811
bara+0.797
Keefe+0.782
enhagen+0.775
ACTED+0.768
Neg logit contributions
��-0.690
adelphia-0.662
cens-0.656
buster-0.601
aries-0.600
Token,
Token ID11
Feature activation-3.36e-01

Pos logit contributions
AMS+1.082
bara+1.065
Keefe+1.041
enhagen+1.033
ACTED+1.028
Neg logit contributions
��-0.877
adelphia-0.839
cens-0.831
buster-0.758
taboola-0.756
Token but
Token ID475
Feature activation+6.64e-02

Pos logit contributions
��+0.909
adelphia+0.875
cens+0.871
aries+0.805
buster+0.794
Neg logit contributions
AMS-1.223
bara-1.199
enhagen-1.174
Keefe-1.172
ACTED-1.160
Token on
Token ID319
Feature activation-2.83e-01

Pos logit contributions
AMS+0.227
bara+0.223
Keefe+0.218
enhagen+0.218
ACTED+0.215
Neg logit contributions
��-0.195
adelphia-0.189
cens-0.187
aries-0.174
buster-0.172
Token this
Token ID428
Feature activation+1.84e-01

Pos logit contributions
��+0.828
adelphia+0.798
cens+0.793
aries+0.733
buster+0.727
Neg logit contributions
AMS-0.974
bara-0.956
Keefe-0.934
enhagen-0.932
ACTED-0.922
Token occasion
Token ID6695
Feature activation+4.48e-01

Pos logit contributions
AMS+0.701
bara+0.695
Keefe+0.679
enhagen+0.675
unning+0.667
Neg logit contributions
��-0.476
adelphia-0.451
cens-0.443
buster-0.401
aries-0.401
Token he
Token ID339
Feature activation-2.92e-01

Pos logit contributions
AMS+1.463
bara+1.443
Keefe+1.408
enhagen+1.393
ACTED+1.373
Neg logit contributions
��-1.394
adelphia-1.342
cens-1.316
buster-1.218
taboola-1.207
Token had
Token ID550
Feature activation-1.53e-01

Pos logit contributions
��+0.850
adelphia+0.821
cens+0.814
aries+0.755
buster+0.747
Neg logit contributions
AMS-1.008
bara-0.988
Keefe-0.968
enhagen-0.964
ACTED-0.954
Token decided
Token ID3066
Feature activation-1.91e-02

Pos logit contributions
��+0.454
adelphia+0.437
cens+0.437
aries+0.409
buster+0.402
Neg logit contributions
AMS-0.514
bara-0.501
enhagen-0.494
Keefe-0.493
ACTED-0.487
Token burned
Token ID11544
Feature activation+1.37e-01

Pos logit contributions
��+1.123
adelphia+1.086
cens+1.075
aries+1.003
buster+0.999
Neg logit contributions
AMS-1.122
bara-1.103
enhagen-1.073
Keefe-1.073
ACTED-1.052
Token arm
Token ID3211
Feature activation+9.47e-02

Pos logit contributions
AMS+0.515
bara+0.507
Keefe+0.496
enhagen+0.495
ACTED+0.491
Neg logit contributions
��-0.355
adelphia-0.340
cens-0.337
aries-0.307
buster-0.304
Token
Token ID198
Feature activation-5.84e-01

Pos logit contributions
AMS+0.334
bara+0.328
Keefe+0.320
enhagen+0.320
ACTED+0.316
Neg logit contributions
��-0.270
adelphia-0.260
cens-0.257
aries-0.237
buster-0.235
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
��+1.303
cens+1.303
adelphia+1.289
aries+1.188
buster+1.181
Neg logit contributions
AMS-2.332
enhagen-2.317
bara-2.300
Keefe-2.241
ACTED-2.229
TokenT
Token ID51
Feature activation-7.39e-02

Pos logit contributions
AMS+0.355
bara+0.349
enhagen+0.341
Keefe+0.339
ACTED+0.334
Neg logit contributions
��-0.349
adelphia-0.338
cens-0.335
aries-0.311
buster-0.310
Tokenori
Token ID10145
Feature activation-2.96e-01

Pos logit contributions
��+0.347
adelphia+0.339
cens+0.337
aries+0.321
buster+0.320
Neg logit contributions
AMS-0.124
bara-0.120
Keefe-0.114
enhagen-0.113
ACTED-0.110
Token and
Token ID290
Feature activation+9.35e-02

Pos logit contributions
��+0.884
adelphia+0.855
cens+0.848
aries+0.787
buster+0.780
Neg logit contributions
AMS-0.996
bara-0.978
Keefe-0.956
enhagen-0.954
ACTED-0.941
Token family
Token ID1641
Feature activation+8.51e-01

Pos logit contributions
AMS+0.292
bara+0.287
Keefe+0.280
enhagen+0.278
ACTED+0.275
Neg logit contributions
��-0.303
adelphia-0.294
cens-0.291
aries-0.271
buster-0.270
Token and
Token ID290
Feature activation+3.02e-01

Pos logit contributions
AMS+3.039
bara+2.989
Keefe+2.919
enhagen+2.899
unning+2.864
Neg logit contributions
��-2.365
adelphia-2.271
cens-2.249
buster-2.022
ipel-2.020
Token a
Token ID257
Feature activation-8.02e-03

Pos logit contributions
AMS+1.285
bara+1.272
Keefe+1.248
enhagen+1.240
ACTED+1.228
Neg logit contributions
��-0.641
adelphia-0.607
cens-0.597
aries-0.529
buster-0.526
Token friend
Token ID1545
Feature activation+3.87e-01

Pos logit contributions
��+0.021
adelphia+0.021
cens+0.020
aries+0.019
buster+0.019
Neg logit contributions
AMS-0.030
bara-0.029
Keefe-0.028
enhagen-0.028
ACTED-0.028
Tokenearing
Token ID6648
Feature activation+4.11e-01

Pos logit contributions
bara+2.260
AMS+2.239
unning+2.199
Keefe+2.185
enhagen+2.177
Neg logit contributions
��-2.045
adelphia-1.938
cens-1.897
oslov-1.784
buster-1.753
Token of
Token ID286
Feature activation+1.54e-01

Pos logit contributions
AMS+1.303
bara+1.287
Keefe+1.246
enhagen+1.239
unning+1.223
Neg logit contributions
��-1.309
adelphia-1.273
cens-1.248
buster-1.161
aries-1.158
Token the
Token ID262
Feature activation+1.48e-01

Pos logit contributions
AMS+0.605
bara+0.599
Keefe+0.583
enhagen+0.579
ACTED+0.574
Neg logit contributions
��-0.374
adelphia-0.363
cens-0.355
aries-0.319
buster-0.318
Token hijab
Token ID48492
Feature activation-1.53e-01

Pos logit contributions
AMS+0.573
bara+0.567
Keefe+0.551
enhagen+0.548
ACTED+0.543
Neg logit contributions
��-0.366
adelphia-0.355
cens-0.348
aries-0.314
buster-0.312
Token or
Token ID393
Feature activation-4.08e-01

Pos logit contributions
��+0.442
adelphia+0.426
cens+0.422
aries+0.389
buster+0.386
Neg logit contributions
AMS-0.534
bara-0.525
Keefe-0.513
enhagen-0.511
ACTED-0.505
Token veil
Token ID30615
Feature activation-1.95e-01

Pos logit contributions
��+1.070
adelphia+1.022
cens+1.015
aries+0.931
buster+0.924
Neg logit contributions
AMS-1.526
bara-1.497
enhagen-1.471
Keefe-1.471
ACTED-1.453
Token,
Token ID11
Feature activation-3.99e-02

Pos logit contributions
��+0.568
adelphia+0.547
cens+0.543
aries+0.502
buster+0.497
Neg logit contributions
AMS-0.676
bara-0.663
Keefe-0.649
enhagen-0.647
ACTED-0.639
Token
Token ID447
Feature activation+1.36e-01

Pos logit contributions
��+0.115
adelphia+0.111
cens+0.110
aries+0.101
buster+0.100
Neg logit contributions
AMS-0.139
bara-0.137
Keefe-0.133
enhagen-0.133
ACTED-0.132
Token
Token ID251
Feature activation+2.52e-01

Pos logit contributions
AMS+0.557
bara+0.550
Keefe+0.539
enhagen+0.536
ACTED+0.532
Neg logit contributions
��-0.302
adelphia-0.293
cens-0.291
aries-0.261
buster-0.259
Token the
Token ID262
Feature activation+4.13e-02

Pos logit contributions
AMS+0.893
bara+0.881
Keefe+0.859
enhagen+0.856
ACTED+0.847
Neg logit contributions
��-0.715
adelphia-0.685
cens-0.671
aries-0.620
buster-0.619
Token school
Token ID1524
Feature activation+9.94e-02

Pos logit contributions
AMS+0.152
bara+0.151
Keefe+0.147
enhagen+0.147
ACTED+0.146
Neg logit contributions
��-0.111
adelphia-0.106
cens-0.104
buster-0.096
aries-0.096
Token,
Token ID11
Feature activation+2.77e-02

Pos logit contributions
��+1.271
adelphia+1.221
cens+1.214
aries+1.128
buster+1.115
Neg logit contributions
AMS-1.440
bara-1.416
Keefe-1.388
enhagen-1.381
ACTED-1.361
Token run
Token ID1057
Feature activation+6.23e-01

Pos logit contributions
AMS+0.098
bara+0.097
Keefe+0.094
enhagen+0.094
ACTED+0.093
Neg logit contributions
��-0.078
adelphia-0.075
cens-0.074
aries-0.068
buster-0.068
Token the
Token ID262
Feature activation-5.93e-02

Pos logit contributions
AMS+2.058
bara+2.022
enhagen+1.965
Keefe+1.950
unning+1.937
Neg logit contributions
��-1.883
adelphia-1.830
cens-1.812
oslov-1.663
buster-1.649
Token power
Token ID1176
Feature activation+4.92e-01

Pos logit contributions
��+0.180
adelphia+0.174
cens+0.172
aries+0.160
buster+0.159
Neg logit contributions
AMS-0.197
bara-0.194
Keefe-0.189
enhagen-0.189
ACTED-0.186
Token off
Token ID572
Feature activation+4.38e-01

Pos logit contributions
AMS+1.557
bara+1.535
enhagen+1.491
Keefe+1.486
unning+1.481
Neg logit contributions
��-1.565
adelphia-1.524
cens-1.490
oslov-1.382
aries-1.377
Token command
Token ID3141
Feature activation+1.72e-01

Pos logit contributions
AMS+1.512
bara+1.489
Keefe+1.448
enhagen+1.448
unning+1.431
Neg logit contributions
��-1.271
adelphia-1.228
cens-1.207
aries-1.106
oslov-1.106
Token and
Token ID290
Feature activation-1.57e-01

Pos logit contributions
AMS+0.585
bara+0.575
Keefe+0.561
enhagen+0.559
ACTED+0.553
Neg logit contributions
��-0.512
adelphia-0.494
cens-0.489
aries-0.451
buster-0.448
Token then
Token ID788
Feature activation-1.66e+00

Pos logit contributions
��+0.446
adelphia+0.429
cens+0.426
aries+0.394
buster+0.390
Neg logit contributions
AMS-0.551
bara-0.541
Keefe-0.529
enhagen-0.528
ACTED-0.522
Token i
Token ID1312
Feature activation+2.05e-01

Pos logit contributions
��+4.143
cens+4.004
adelphia+3.962
aries+3.820
buster+3.703
Neg logit contributions
AMS-6.142
bara-5.980
Keefe-5.967
enhagen-5.943
ACTED-5.878
Tokenw
Token ID86
Feature activation+4.75e-01

Pos logit contributions
AMS+0.572
bara+0.561
Keefe+0.543
enhagen+0.542
ACTED+0.533
Neg logit contributions
��-0.737
adelphia-0.715
cens-0.708
aries-0.663
buster-0.661
Tokenconfig
Token ID11250
Feature activation+1.41e-01

Pos logit contributions
AMS+1.427
bara+1.418
enhagen+1.372
Keefe+1.365
unning+1.355
Neg logit contributions
��-1.578
adelphia-1.523
cens-1.496
oslov-1.404
aries-1.398
Token the
Token ID262
Feature activation+2.49e-01

Pos logit contributions
AMS+0.026
bara+0.026
Keefe+0.025
enhagen+0.025
ACTED+0.025
Neg logit contributions
��-0.022
adelphia-0.022
cens-0.021
aries-0.020
buster-0.020
Token film
Token ID2646
Feature activation+1.79e-01

Pos logit contributions
AMS+0.861
bara+0.847
Keefe+0.832
enhagen+0.824
unning+0.816
Neg logit contributions
��-0.721
adelphia-0.692
cens-0.679
aries-0.625
buster-0.624
Token,
Token ID11
Feature activation-4.16e-01

Pos logit contributions
AMS+0.628
bara+0.620
Keefe+0.603
enhagen+0.602
ACTED+0.592
Neg logit contributions
��-0.513
adelphia-0.490
cens-0.482
oslov-0.444
buster-0.442
Token I
Token ID314
Feature activation-5.04e-02

Pos logit contributions
��+1.099
adelphia+1.060
cens+1.050
aries+0.963
buster+0.953
Neg logit contributions
AMS-1.544
bara-1.516
Keefe-1.483
enhagen-1.482
ACTED-1.467
Token pushed
Token ID7121
Feature activation-3.13e-01

Pos logit contributions
��+0.153
adelphia+0.148
cens+0.146
aries+0.135
buster+0.134
Neg logit contributions
AMS-0.169
bara-0.166
Keefe-0.161
enhagen-0.161
ACTED-0.159
Token him
Token ID683
Feature activation-7.60e-01

Pos logit contributions
��+0.914
adelphia+0.884
cens+0.875
aries+0.811
buster+0.804
Neg logit contributions
AMS-1.077
bara-1.059
enhagen-1.034
Keefe-1.033
ACTED-1.019
Token every
Token ID790
Feature activation-1.71e-01

Pos logit contributions
��+1.996
adelphia+1.933
cens+1.932
aries+1.788
buster+1.765
Neg logit contributions
AMS-2.804
bara-2.738
Keefe-2.700
enhagen-2.695
ACTED-2.667
Token single
Token ID2060
Feature activation-2.04e-01

Pos logit contributions
��+0.461
adelphia+0.442
cens+0.438
aries+0.401
buster+0.398
Neg logit contributions
AMS-0.628
bara-0.618
Keefe-0.605
enhagen-0.602
ACTED-0.597
Token play
Token ID711
Feature activation-1.72e-01

Pos logit contributions
��+0.570
adelphia+0.548
cens+0.542
aries+0.499
buster+0.495
Neg logit contributions
AMS-0.731
bara-0.719
Keefe-0.703
enhagen-0.700
ACTED-0.693
Token.
Token ID13
Feature activation-9.58e-01

Pos logit contributions
��+0.516
adelphia+0.497
cens+0.491
aries+0.454
buster+0.451
Neg logit contributions
AMS-0.578
bara-0.568
Keefe-0.554
enhagen-0.552
ACTED-0.546
Token I
Token ID314
Feature activation-1.25e-01

Pos logit contributions
��+2.596
adelphia+2.560
cens+2.512
aries+2.341
buster+2.325
Neg logit contributions
AMS-3.387
bara-3.362
enhagen-3.337
Keefe-3.246
ACTED-3.232
Token the
Token ID262
Feature activation+6.78e-02

Pos logit contributions
��+0.102
adelphia+0.098
cens+0.097
aries+0.090
buster+0.089
Neg logit contributions
AMS-0.124
bara-0.122
Keefe-0.119
enhagen-0.118
ACTED-0.117
Token upcoming
Token ID7865
Feature activation+2.68e-01

Pos logit contributions
AMS+0.244
bara+0.241
Keefe+0.235
enhagen+0.234
ACTED+0.232
Neg logit contributions
��-0.188
adelphia-0.180
cens-0.179
aries-0.164
buster-0.163
Token revival
Token ID26624
Feature activation-8.04e-02

Pos logit contributions
AMS+0.986
bara+0.970
Keefe+0.945
enhagen+0.940
ACTED+0.933
Neg logit contributions
��-0.724
adelphia-0.695
cens-0.685
aries-0.623
oslov-0.621
Token of
Token ID286
Feature activation+6.83e-03

Pos logit contributions
��+0.254
adelphia+0.246
cens+0.243
aries+0.226
buster+0.225
Neg logit contributions
AMS-0.258
bara-0.253
Keefe-0.247
enhagen-0.245
ACTED-0.243
Token a
Token ID257
Feature activation-7.07e-02

Pos logit contributions
AMS+0.024
bara+0.023
Keefe+0.023
enhagen+0.023
ACTED+0.022
Neg logit contributions
��-0.020
adelphia-0.019
cens-0.019
aries-0.017
buster-0.017
Token historic
Token ID9566
Feature activation-8.12e-01

Pos logit contributions
��+0.188
adelphia+0.181
cens+0.178
aries+0.163
buster+0.162
Neg logit contributions
AMS-0.262
bara-0.259
Keefe-0.252
enhagen-0.251
ACTED-0.249
Token Broadway
Token ID20617
Feature activation+7.56e-01

Pos logit contributions
��+2.130
adelphia+2.059
cens+2.044
aries+1.895
oslov+1.872
Neg logit contributions
AMS-3.017
bara-2.954
enhagen-2.908
Keefe-2.892
ACTED-2.862
Token musical
Token ID10530
Feature activation+1.55e-01

Pos logit contributions
bara+2.490
AMS+2.485
Keefe+2.410
ACTED+2.359
unning+2.357
Neg logit contributions
��-2.279
adelphia-2.185
cens-2.156
aries-1.989
buster-1.952
Token has
Token ID468
Feature activation+8.56e-01

Pos logit contributions
AMS+0.516
bara+0.508
Keefe+0.495
enhagen+0.491
ACTED+0.487
Neg logit contributions
��-0.471
adelphia-0.453
cens-0.448
aries-0.414
buster-0.413
Token gone
Token ID3750
Feature activation+1.09e+00

Pos logit contributions
bara+2.612
AMS+2.610
enhagen+2.488
Keefe+2.479
ACTED+2.441
Neg logit contributions
��-2.826
adelphia-2.747
cens-2.679
oslov-2.500
buster-2.490
Token missing
Token ID4814
Feature activation+1.06e+00

Pos logit contributions
AMS+3.453
bara+3.407
enhagen+3.307
Keefe+3.306
unning+3.220
Neg logit contributions
��-3.436
adelphia-3.310
cens-3.231
oslov-2.974
ipel-2.970
Token old
Token ID1468
Feature activation-7.60e-01

Pos logit contributions
AMS+0.264
bara+0.261
Keefe+0.256
enhagen+0.255
ACTED+0.252
Neg logit contributions
��-0.136
adelphia-0.130
cens-0.127
aries-0.113
buster-0.112
Token Naval
Token ID20818
Feature activation+6.57e-01

Pos logit contributions
��+2.856
adelphia+2.769
cens+2.766
aries+2.607
oslov+2.596
Neg logit contributions
AMS-1.952
bara-1.909
Keefe-1.852
enhagen-1.841
ACTED-1.825
Token Air
Token ID3701
Feature activation+3.07e-01

Pos logit contributions
AMS+2.068
bara+2.016
Keefe+1.971
ACTED+1.945
enhagen+1.915
Neg logit contributions
��-2.159
adelphia-2.043
cens-2.014
buster-1.852
ipel-1.845
Token Station
Token ID9327
Feature activation+1.51e-01

Pos logit contributions
AMS+1.007
bara+0.987
Keefe+0.966
enhagen+0.958
ACTED+0.945
Neg logit contributions
��-0.954
adelphia-0.915
cens-0.904
aries-0.838
buster-0.831
Token in
Token ID287
Feature activation-3.38e-01

Pos logit contributions
AMS+0.476
bara+0.468
Keefe+0.455
enhagen+0.452
ACTED+0.447
Neg logit contributions
��-0.491
adelphia-0.472
cens-0.467
aries-0.435
buster-0.431
Token South
Token ID2520
Feature activation-4.73e-01

Pos logit contributions
��+0.947
adelphia+0.911
cens+0.901
aries+0.829
buster+0.824
Neg logit contributions
AMS-1.210
bara-1.190
Keefe-1.162
enhagen-1.159
ACTED-1.147
Token We
Token ID775
Feature activation-9.61e-01

Pos logit contributions
��+1.190
adelphia+1.142
cens+1.127
aries+1.027
buster+1.018
Neg logit contributions
AMS-1.826
bara-1.798
Keefe-1.760
enhagen-1.755
ACTED-1.737
Tokenym
Token ID4948
Feature activation-8.22e-02

Pos logit contributions
��+1.642
adelphia+1.591
cens+1.544
aries+1.400
emia+1.343
Neg logit contributions
AMS-4.405
bara-4.321
Keefe-4.289
enhagen-4.266
ACTED-4.246
Tokenouth
Token ID1536
Feature activation+7.67e-02

Pos logit contributions
��+0.233
adelphia+0.224
cens+0.222
aries+0.205
buster+0.203
Neg logit contributions
AMS-0.290
bara-0.286
Keefe-0.279
enhagen-0.278
ACTED-0.275
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
AMS+0.255
bara+0.251
Keefe+0.245
enhagen+0.244
ACTED+0.241
Neg logit contributions
��-0.233
adelphia-0.225
cens-0.223
aries-0.207
buster-0.205
Token This
Token ID770
Feature activation+2.40e-01

Pos logit contributions
��+0.438
adelphia+0.425
cens+0.421
aries+0.395
buster+0.393
Neg logit contributions
AMS-0.351
bara-0.343
Keefe-0.333
enhagen-0.332
ACTED-0.327
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
AMS+1.217
bara+1.195
Keefe+1.163
enhagen+1.160
ACTED+1.144
Neg logit contributions
��-1.107
adelphia-1.073
cens-1.052
aries-0.966
buster-0.966
Token
Token ID198
Feature activation-3.92e-01

Pos logit contributions
AMS+0.749
bara+0.733
Keefe+0.717
enhagen+0.709
ACTED+0.706
Neg logit contributions
��-0.616
adelphia-0.592
cens-0.586
aries-0.538
buster-0.533
Token
Token ID198
Feature activation+1.98e-01

Pos logit contributions
��+0.921
adelphia+0.901
cens+0.900
aries+0.825
buster+0.816
Neg logit contributions
AMS-1.539
bara-1.521
enhagen-1.518
Keefe-1.481
ACTED-1.470
TokenLet
Token ID5756
Feature activation-6.09e-01

Pos logit contributions
AMS+0.574
bara+0.564
enhagen+0.549
Keefe+0.547
ACTED+0.538
Neg logit contributions
��-0.687
adelphia-0.666
cens-0.661
aries-0.619
buster-0.616
Token them
Token ID606
Feature activation-6.34e-01

Pos logit contributions
��+1.914
adelphia+1.839
cens+1.826
aries+1.725
buster+1.696
Neg logit contributions
AMS-1.949
bara-1.908
Keefe-1.864
enhagen-1.864
ACTED-1.830
Token know
Token ID760
Feature activation-6.84e-01

Pos logit contributions
��+1.836
adelphia+1.774
cens+1.762
aries+1.655
buster+1.651
Neg logit contributions
AMS-2.161
bara-2.118
enhagen-2.105
Keefe-2.095
ACTED-2.039
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
��+1.840
adelphia+1.778
cens+1.773
aries+1.655
 Homo+1.617
Neg logit contributions
AMS-2.464
bara-2.420
enhagen-2.390
Keefe-2.384
ACTED-2.350
Token advance
Token ID5963
Feature activation+4.98e-01

Pos logit contributions
��+0.531
adelphia+0.513
cens+0.507
aries+0.466
buster+0.465
Neg logit contributions
AMS-0.635
bara-0.624
Keefe-0.608
enhagen-0.605
ACTED-0.600
Token that
Token ID326
Feature activation+1.49e-01

Pos logit contributions
AMS+1.678
bara+1.647
Keefe+1.602
enhagen+1.597
ACTED+1.578
Neg logit contributions
��-1.492
adelphia-1.441
cens-1.421
buster-1.305
aries-1.302
Token their
Token ID511
Feature activation-2.14e-01

Pos logit contributions
AMS+0.520
bara+0.511
Keefe+0.499
enhagen+0.498
ACTED+0.492
Neg logit contributions
��-0.431
adelphia-0.415
cens-0.411
aries-0.379
buster-0.376
Token characters
Token ID3435
Feature activation-6.04e-02

Pos logit contributions
��+0.664
adelphia+0.641
cens+0.636
aries+0.591
buster+0.587
Neg logit contributions
AMS-0.700
bara-0.687
Keefe-0.671
enhagen-0.669
ACTED-0.660
Token in
Token ID287
Feature activation+7.19e-01

Pos logit contributions
AMS+2.175
bara+2.144
Keefe+2.083
enhagen+2.074
ACTED+2.051
Neg logit contributions
��-2.383
adelphia-2.302
cens-2.277
buster-2.119
aries-2.114
Token a
Token ID257
Feature activation+5.60e-01

Pos logit contributions
AMS+2.385
bara+2.356
Keefe+2.296
enhagen+2.288
unning+2.255
Neg logit contributions
��-2.174
adelphia-2.095
cens-2.067
buster-1.919
aries-1.905
Token world
Token ID995
Feature activation+2.23e-01

Pos logit contributions
AMS+2.072
bara+2.054
Keefe+2.006
enhagen+1.987
unning+1.979
Neg logit contributions
��-1.477
adelphia-1.434
cens-1.392
buster-1.266
aries-1.265
Token where
Token ID810
Feature activation+4.09e-01

Pos logit contributions
AMS+0.724
bara+0.714
Keefe+0.695
enhagen+0.690
ACTED+0.682
Neg logit contributions
��-0.699
adelphia-0.675
cens-0.667
aries-0.618
buster-0.615
Token those
Token ID883
Feature activation-2.22e-01

Pos logit contributions
AMS+1.415
bara+1.398
Keefe+1.357
enhagen+1.354
unning+1.338
Neg logit contributions
��-1.187
adelphia-1.145
cens-1.128
aries-1.034
oslov-1.031
Token who
Token ID508
Feature activation-7.58e-01

Pos logit contributions
��+0.668
adelphia+0.645
cens+0.640
aries+0.597
buster+0.590
Neg logit contributions
AMS-0.747
bara-0.732
enhagen-0.716
Keefe-0.715
ACTED-0.707
Token shout
Token ID9191
Feature activation-4.71e-01

Pos logit contributions
��+2.123
adelphia+2.059
cens+2.033
aries+1.916
buster+1.887
Neg logit contributions
AMS-2.666
bara-2.600
Keefe-2.568
enhagen-2.566
ACTED-2.543
Token the
Token ID262
Feature activation-3.80e-01

Pos logit contributions
��+1.349
adelphia+1.297
cens+1.287
aries+1.196
buster+1.184
Neg logit contributions
AMS-1.650
bara-1.614
enhagen-1.582
Keefe-1.579
ACTED-1.566
Token loud
Token ID7812
Feature activation-7.02e-01

Pos logit contributions
��+1.075
adelphia+1.033
cens+1.025
aries+0.947
buster+0.937
Neg logit contributions
AMS-1.347
bara-1.323
Keefe-1.293
enhagen-1.291
ACTED-1.275
Tokenest
Token ID395
Feature activation+6.80e-01

Pos logit contributions
��+1.474
adelphia+1.401
cens+1.381
aries+1.250
buster+1.223
Neg logit contributions
AMS-2.995
bara-2.935
Keefe-2.894
enhagen-2.885
ACTED-2.859
Token are
Token ID389
Feature activation+3.80e-02

Pos logit contributions
AMS+2.347
bara+2.336
Keefe+2.267
enhagen+2.254
unning+2.245
Neg logit contributions
��-1.931
adelphia-1.877
cens-1.834
ipel-1.687
oslov-1.674
Token unsupported
Token ID24222
Feature activation+1.08e-01

Pos logit contributions
AMS+0.169
bara+0.167
Keefe+0.163
enhagen+0.163
ACTED+0.161
Neg logit contributions
��-0.100
adelphia-0.095
cens-0.093
aries-0.085
buster-0.084
Token on
Token ID319
Feature activation-8.39e-01

Pos logit contributions
AMS+0.376
bara+0.369
Keefe+0.361
enhagen+0.360
ACTED+0.355
Neg logit contributions
��-0.309
adelphia-0.298
cens-0.296
aries-0.273
buster-0.271
Token your
Token ID534
Feature activation-8.36e-01

Pos logit contributions
cens+2.325
��+2.312
adelphia+2.287
aries+2.147
buster+2.145
Neg logit contributions
AMS-2.913
enhagen-2.841
bara-2.828
Keefe-2.776
ACTED-2.774
Token device
Token ID3335
Feature activation-8.91e-01

Pos logit contributions
cens+2.329
��+2.307
adelphia+2.217
buster+2.125
oslov+2.108
Neg logit contributions
AMS-2.947
enhagen-2.853
Keefe-2.842
bara-2.842
ACTED-2.796
Token Media
Token ID6343
Feature activation-8.25e-01

Pos logit contributions
cens+1.698
��+1.675
adelphia+1.639
buster+1.494
aries+1.485
Neg logit contributions
AMS-3.908
enhagen-3.794
bara-3.761
ACTED-3.757
Keefe-3.716
Token caption
Token ID8305
Feature activation-2.12e+00

Pos logit contributions
cens+1.604
��+1.588
adelphia+1.564
aries+1.425
taboola+1.381
Neg logit contributions
AMS-3.534
bara-3.469
enhagen-3.430
ACTED-3.407
Keefe-3.376
Token A
Token ID317
Feature activation-1.86e-01

Pos logit contributions
adelphia+5.870
��+5.841
cens+5.836
 Homo+5.562
aries+5.487
Neg logit contributions
AMS-6.817
bara-6.807
enhagen-6.718
unning-6.574
ACTED-6.552
Token drone
Token ID12170
Feature activation+1.69e-01

Pos logit contributions
��+0.528
adelphia+0.508
cens+0.503
aries+0.464
buster+0.460
Neg logit contributions
AMS-0.655
bara-0.644
Keefe-0.629
enhagen-0.627
ACTED-0.621
Token-
Token ID12
Feature activation+2.21e-01

Pos logit contributions
AMS+0.571
bara+0.562
Keefe+0.547
enhagen+0.545
ACTED+0.538
Neg logit contributions
��-0.508
adelphia-0.489
cens-0.483
aries-0.448
buster-0.443
Tokencamera
Token ID25695
Feature activation-4.16e-01

Pos logit contributions
AMS+0.678
bara+0.667
Keefe+0.648
enhagen+0.645
ACTED+0.635
Neg logit contributions
��-0.730
adelphia-0.705
cens-0.694
aries-0.652
oslov-0.645
Token was
Token ID373
Feature activation+3.55e-01

Pos logit contributions
��+1.240
adelphia+1.203
cens+1.198
aries+1.114
buster+1.107
Neg logit contributions
AMS-1.393
bara-1.367
enhagen-1.341
Keefe-1.334
ACTED-1.328
Token
Token ID198
Feature activation-4.38e-01

Pos logit contributions
AMS+0.548
bara+0.537
Keefe+0.525
enhagen+0.520
ACTED+0.516
Neg logit contributions
��-0.480
adelphia-0.463
cens-0.458
aries-0.422
buster-0.420
Token
Token ID198
Feature activation+4.45e-02

Pos logit contributions
��+1.053
adelphia+1.020
cens+1.015
aries+0.928
buster+0.919
Neg logit contributions
AMS-1.702
bara-1.688
enhagen-1.682
Keefe-1.638
ACTED-1.629
TokenPhoto
Token ID6191
Feature activation-7.11e-02

Pos logit contributions
AMS+0.127
bara+0.125
enhagen+0.121
Keefe+0.121
ACTED+0.119
Neg logit contributions
��-0.156
adelphia-0.152
cens-0.150
aries-0.141
buster-0.140
Token
Token ID198
Feature activation+7.61e-01

Pos logit contributions
��+0.215
adelphia+0.208
cens+0.205
aries+0.190
buster+0.189
Neg logit contributions
AMS-0.238
bara-0.234
Keefe-0.228
enhagen-0.228
ACTED-0.224
Token
Token ID198
Feature activation+9.61e-01

Pos logit contributions
AMS+2.626
bara+2.582
Keefe+2.538
ACTED+2.475
unning+2.458
Neg logit contributions
��-2.288
adelphia-2.122
cens-2.085
ipel-1.928
aries-1.893
TokenPitt
Token ID47627
Feature activation-1.71e+00

Pos logit contributions
AMS+2.699
bara+2.570
Keefe+2.564
ACTED+2.489
unning+2.420
Neg logit contributions
��-3.472
adelphia-3.341
cens-3.289
oslov-3.097
aries-3.095
Tokensburgh
Token ID11931
Feature activation-8.78e-01

Pos logit contributions
��+2.802
cens+2.726
adelphia+2.726
aries+2.310
oslov+2.292
Neg logit contributions
AMS-7.879
bara-7.662
Keefe-7.618
ACTED-7.566
enhagen-7.519
Token
Token ID198
Feature activation+1.75e-01

Pos logit contributions
��+2.607
adelphia+2.536
cens+2.506
aries+2.329
buster+2.299
Neg logit contributions
AMS-2.961
bara-2.900
Keefe-2.836
enhagen-2.829
ACTED-2.801
Token
Token ID198
Feature activation+4.12e-01

Pos logit contributions
AMS+0.653
bara+0.643
Keefe+0.630
enhagen+0.623
ACTED+0.621
Neg logit contributions
��-0.466
adelphia-0.445
cens-0.439
aries-0.401
buster-0.398
TokenThe
Token ID464
Feature activation+1.01e-01

Pos logit contributions
AMS+1.168
bara+1.135
Keefe+1.113
ACTED+1.087
enhagen+1.083
Neg logit contributions
��-1.467
adelphia-1.419
cens-1.403
aries-1.318
buster-1.311
Token visceral
Token ID38259
Feature activation+1.42e-02

Pos logit contributions
AMS+0.358
bara+0.353
Keefe+0.344
enhagen+0.343
ACTED+0.339
Neg logit contributions
��-0.289
adelphia-0.277
cens-0.274
aries-0.252
buster-0.251
Token Republican
Token ID3415
Feature activation-9.82e-02

Pos logit contributions
��+0.339
adelphia+0.326
cens+0.322
aries+0.296
buster+0.295
Neg logit contributions
AMS-0.433
bara-0.426
Keefe-0.417
enhagen-0.414
ACTED-0.409
Token victory
Token ID5373
Feature activation-6.80e-02

Pos logit contributions
��+0.275
adelphia+0.264
cens+0.261
aries+0.239
buster+0.238
Neg logit contributions
AMS-0.352
bara-0.346
Keefe-0.338
enhagen-0.336
ACTED-0.332
Token.
Token ID13
Feature activation+5.94e-02

Pos logit contributions
��+0.209
adelphia+0.201
cens+0.199
aries+0.183
oslov+0.183
Neg logit contributions
AMS-0.225
bara-0.221
Keefe-0.216
enhagen-0.215
ACTED-0.212
Token
Token ID198
Feature activation-3.90e-01

Pos logit contributions
AMS+0.207
bara+0.203
Keefe+0.199
enhagen+0.196
ACTED+0.196
Neg logit contributions
��-0.172
adelphia-0.165
cens-0.163
aries-0.150
buster-0.149
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
��+0.920
adelphia+0.903
cens+0.898
aries+0.825
buster+0.814
Neg logit contributions
AMS-1.527
bara-1.507
enhagen-1.500
Keefe-1.469
ACTED-1.457
TokenSent
Token ID31837
Feature activation-2.34e+00

Pos logit contributions
AMS+0.474
bara+0.462
Keefe+0.453
enhagen+0.446
ACTED+0.444
Neg logit contributions
��-0.507
adelphia-0.489
cens-0.484
aries-0.452
buster-0.449
Tokeniment
Token ID3681
Feature activation-1.27e+00

Pos logit contributions
cens+7.091
adelphia+7.086
aries+7.082
��+6.860
buster+6.542
Neg logit contributions
AMS-6.777
ACTED-6.508
enhagen-6.428
Keefe-6.369
bara-6.323
Token about
Token ID546
Feature activation-3.94e-01

Pos logit contributions
��+3.696
adelphia+3.607
cens+3.521
aries+3.419
buster+3.251
Neg logit contributions
AMS-4.295
bara-4.179
enhagen-4.163
Keefe-4.146
ACTED-4.080
Token how
Token ID703
Feature activation+7.34e-01

Pos logit contributions
��+1.095
adelphia+1.055
cens+1.045
aries+0.962
buster+0.953
Neg logit contributions
AMS-1.412
bara-1.386
enhagen-1.354
Keefe-1.354
ACTED-1.338
Token to
Token ID284
Feature activation+3.13e-01

Pos logit contributions
AMS+2.443
bara+2.423
Keefe+2.366
enhagen+2.314
ACTED+2.312
Neg logit contributions
��-2.217
adelphia-2.134
cens-2.098
oslov-1.929
buster-1.927
Token proceed
Token ID5120
Feature activation-1.11e-01

Pos logit contributions
AMS+1.103
bara+1.087
Keefe+1.065
enhagen+1.054
ACTED+1.046
Neg logit contributions
��-0.889
adelphia-0.853
cens-0.841
aries-0.772
oslov-0.770
Token our
Token ID674
Feature activation-1.07e+00

Pos logit contributions
��+2.051
cens+1.916
adelphia+1.890
aries+1.828
buster+1.789
Neg logit contributions
bara-3.137
AMS-3.120
Keefe-3.066
enhagen-3.053
ACTED-3.022
Token daily
Token ID4445
Feature activation-6.84e-01

Pos logit contributions
��+2.413
adelphia+2.317
cens+2.291
aries+2.075
oslov+2.029
Neg logit contributions
AMS-4.372
bara-4.302
Keefe-4.229
enhagen-4.201
ACTED-4.178
Token newsletter
Token ID13129
Feature activation-5.49e-01

Pos logit contributions
��+1.606
adelphia+1.526
cens+1.495
aries+1.353
buster+1.341
Neg logit contributions
AMS-2.763
bara-2.729
Keefe-2.679
enhagen-2.658
ACTED-2.632
Token Upgrade
Token ID24236
Feature activation-3.67e-01

Pos logit contributions
��+1.604
adelphia+1.548
cens+1.540
aries+1.439
oslov+1.425
Neg logit contributions
AMS-1.877
bara-1.827
enhagen-1.810
Keefe-1.790
ACTED-1.770
Token your
Token ID534
Feature activation-1.75e+00

Pos logit contributions
��+1.185
adelphia+1.148
cens+1.137
aries+1.061
buster+1.053
Neg logit contributions
AMS-1.154
bara-1.132
Keefe-1.103
enhagen-1.101
ACTED-1.085
Token inbox
Token ID13734
Feature activation-1.72e+00

Pos logit contributions
��+2.622
adelphia+2.546
cens+2.453
 Gutenberg+2.185
oslov+2.172
Neg logit contributions
AMS-8.265
bara-8.108
enhagen-8.013
ACTED-7.933
Keefe-7.908
Token and
Token ID290
Feature activation-9.75e-01

Pos logit contributions
��+2.964
cens+2.878
adelphia+2.855
aries+2.670
oslov+2.520
Neg logit contributions
AMS-7.734
bara-7.524
enhagen-7.492
ACTED-7.485
Keefe-7.380
Token get
Token ID651
Feature activation-1.20e+00

Pos logit contributions
��+2.040
adelphia+1.966
cens+1.945
aries+1.796
oslov+1.774
Neg logit contributions
AMS-4.094
bara-4.004
enhagen-3.980
ACTED-3.952
Keefe-3.946
Token our
Token ID674
Feature activation-1.16e+00

Pos logit contributions
��+2.754
cens+2.599
adelphia+2.555
 Homo+2.497
aries+2.494
Neg logit contributions
AMS-4.705
bara-4.593
Keefe-4.488
enhagen-4.473
ACTED-4.451
Token Daily
Token ID6714
Feature activation-1.29e+00

Pos logit contributions
��+2.070
adelphia+1.954
cens+1.942
aries+1.699
oslov+1.664
Neg logit contributions
AMS-5.315
bara-5.234
enhagen-5.142
Keefe-5.130
ACTED-5.110
Token Dispatch
Token ID35934
Feature activation-5.54e-01

Pos logit contributions
��+1.060
adelphia+0.941
cens+0.936
aries+0.668
buster+0.638
Neg logit contributions
AMS-7.075
bara-6.992
enhagen-6.916
Keefe-6.881
ACTED-6.855
Token on
Token ID319
Feature activation+2.59e-02

Pos logit contributions
��+0.446
adelphia+0.429
cens+0.425
aries+0.395
buster+0.391
Neg logit contributions
AMS-0.517
bara-0.508
Keefe-0.497
enhagen-0.496
ACTED-0.490
Token Wednesday
Token ID3583
Feature activation-5.93e-01

Pos logit contributions
AMS+0.085
bara+0.083
Keefe+0.081
enhagen+0.081
ACTED+0.079
Neg logit contributions
��-0.081
adelphia-0.078
cens-0.077
aries-0.071
buster-0.071
Token on
Token ID319
Feature activation-2.94e-01

Pos logit contributions
��+1.954
adelphia+1.882
cens+1.870
aries+1.754
buster+1.737
Neg logit contributions
AMS-1.821
bara-1.781
Keefe-1.739
enhagen-1.729
ACTED-1.717
Token efforts
Token ID4040
Feature activation-6.87e-01

Pos logit contributions
��+0.881
adelphia+0.850
cens+0.842
aries+0.780
buster+0.774
Neg logit contributions
AMS-0.990
bara-0.972
Keefe-0.949
enhagen-0.946
ACTED-0.935
Token to
Token ID284
Feature activation-1.11e-01

Pos logit contributions
��+2.561
adelphia+2.473
cens+2.468
aries+2.336
buster+2.309
Neg logit contributions
AMS-1.800
bara-1.747
enhagen-1.697
Keefe-1.683
ACTED-1.683
Token cool
Token ID3608
Feature activation-1.81e+00

Pos logit contributions
��+0.337
adelphia+0.325
cens+0.322
aries+0.298
oslov+0.296
Neg logit contributions
AMS-0.369
bara-0.363
Keefe-0.354
enhagen-0.352
ACTED-0.347
Token down
Token ID866
Feature activation-5.58e-01

Pos logit contributions
��+4.651
cens+4.508
adelphia+4.457
aries+4.110
oslov+4.077
Neg logit contributions
AMS-6.504
ACTED-6.343
bara-6.341
enhagen-6.305
Keefe-6.285
Token a
Token ID257
Feature activation-7.92e-02

Pos logit contributions
��+1.550
adelphia+1.485
cens+1.477
aries+1.358
buster+1.349
Neg logit contributions
AMS-1.997
bara-1.961
Keefe-1.920
enhagen-1.915
ACTED-1.900
Token plutonium
Token ID47901
Feature activation+3.36e-01

Pos logit contributions
��+0.234
adelphia+0.226
cens+0.223
aries+0.207
buster+0.205
Neg logit contributions
AMS-0.271
bara-0.266
Keefe-0.260
enhagen-0.259
ACTED-0.256
Token-
Token ID12
Feature activation+1.42e-01

Pos logit contributions
AMS+1.130
bara+1.129
Keefe+1.088
enhagen+1.080
ACTED+1.073
Neg logit contributions
��-1.001
adelphia-0.961
cens-0.951
aries-0.875
taboola-0.867
Tokenfuel
Token ID25802
Feature activation+3.83e-01

Pos logit contributions
AMS+0.469
bara+0.467
Keefe+0.451
enhagen+0.446
ACTED+0.443
Neg logit contributions
��-0.439
adelphia-0.423
cens-0.410
aries-0.384
oslov-0.383