TOP ACTIVATIONS
MAX = 10.979

ghost invasion of the big Apple . To make
land <|endoftext|> By Sam , updated on 15 July 2017
Half Ac re collaboration An ic ca . Brew ed with
. Oklahoma , a seism ically inactive area before gas fracking
best , such an approach alien ates young voters , says
debt , which has an impact on students life
New York branch of the Foot into a criminal powerhouse involved
under study , Norm Van Brock lin . Far
of the limestone surrounding the fossils , said the question of
" A movement is a foot that must not fade away
earthquakes . Oklahoma , a seism ically inactive area before gas
not ch studio specializing in ecc les ial art had drawn
The electric applause inside the Ecc les after Manchester
all that stuff has an impact on our long - term
, as Toronto Police Chief Bill Blair confirmed in October .
experiences of college students , first year students on this campus
Jeff Baker , chief of police , said the man was
a new study Sven D ref ahl from the Max Plan
Far rah W ether s Mysteries , comic book short stories
2011 and 2012 , the Geological Society of America in 2011

MIN ACTIVATIONS
MIN = -11.021

open my mouth and her tongue sl ither s into mine
of the manga series have cum ul atively sold over 22
. A pill called Sugar Cum , for instance , allegedly
sudo ch mod + x / etc / pm
given by people like Bill Moy ers , suggests that the
ways that aren 't comm ens urate with their past performances
Show nested quote + On September 20
The Lerner emails have become almost as big a scandal as
Appeals to identity are now almost exclusively the preserve of the
or < Tab >) { vi : | vim : |
told the Today show 's Savannah Guth rie who brought up
paragraph that said God considers masturbation to be a " hom
ver tex . xy z += v . normal * 1
map $ b mp = new - object system . draw
il ine $ art ext = ($ text - split "\
text ] { white }{ vi : | vim : |
of Muhammad with his hands tied to his neck with a
the point where I tried masturb ating as Bruce C odd
the contact of her lips against mine . "
T > { pub fn load < ' a > (

INTERVAL 5.479 - 10.979
CONTAINS 0.293%

How St uff Works . com The next breakthrough
be locked up ? It depends on how you define a
Some kind of bailout , whether granted with soft or tough
's our version of a Martian car wash ," said Chris
which were considered likely Apollo landing sites . On the first

INTERVAL -0.021 - 5.479
CONTAINS 50.397%

. Exactly 50 years later December 17 , 1995
dist ros . In some ways , it 's
to prevent another Portsmouth , but not another Manchester City ,
Abstract Background Depression presents a significant burden to both
: Carly Fiorina 's political career Fiorina concedes defeat to her

INTERVAL -5.521 - -0.021
CONTAINS 48.968%

regulations have been explored at a national level ( e .
for Star Wars ? No . My parents are
Over drive is a piece I ve
The young man was a junior clerk in the
to voters , than the bully pul pit . PK claims

INTERVAL -11.021 - -5.521
CONTAINS 0.342%

was valued as good became
. H aj ime Tab ata : There were
the University of California , Santa Barbara , and an organizer
the European rule book in terms of its sensible application to
first Ghostbusters , the ne igh bor hood in New York
Token ghost
Token ID10905
Feature activation+6.83e+00

Pos logit contributions
orian+3.911
orb+3.750
kson+3.649
tale+3.602
arious+3.571
Neg logit contributions
Random-3.349
 Sham-3.332
dump-3.307
nam-3.247
 ASA-3.160
Token invasion
Token ID11796
Feature activation+1.64e+00

Pos logit contributions
orian+3.079
orb+2.870
kson+2.760
rupal+2.675
tale+2.635
Neg logit contributions
Random-6.288
dump-6.252
 Sham-6.225
nam-6.145
 ASA-5.989
Token of
Token ID286
Feature activation+2.85e+00

Pos logit contributions
orian+1.198
orb+1.137
kson+1.136
rupal+1.099
oulos+1.095
Neg logit contributions
dump-1.072
Random-1.070
 Sham-1.061
nam-1.049
 ASA-1.003
Token the
Token ID262
Feature activation+2.62e+00

Pos logit contributions
orian+2.228
orb+2.123
kson+2.118
rupal+2.055
oulos+2.046
Neg logit contributions
dump-1.716
Random-1.710
 Sham-1.694
nam-1.673
 ASA-1.598
Token big
Token ID1263
Feature activation+3.68e+00

Pos logit contributions
orian+1.955
orb+1.905
kson+1.845
arious+1.813
tale+1.808
Neg logit contributions
Random-1.620
dump-1.617
 Sham-1.602
nam-1.571
 ASA-1.523
Token Apple
Token ID4196
Feature activation+1.10e+01

Pos logit contributions
orian+1.927
orb+1.832
kson+1.763
oulos+1.710
rupal+1.705
Neg logit contributions
dump-3.118
 Sham-3.101
Random-3.094
nam-3.074
 ASA-2.967
Token.
Token ID13
Feature activation+4.01e+00

Pos logit contributions
orian+5.922
orb+5.632
kson+5.549
tale+5.401
rupal+5.269
Neg logit contributions
dump-8.399
Random-8.293
 Sham-8.194
nam-8.180
 ASA-8.009
Token
Token ID198
Feature activation+9.96e-01

Pos logit contributions
orian+2.510
orb+2.407
kson+2.307
tale+2.258
rupal+2.247
Neg logit contributions
dump-2.947
 Sham-2.900
Random-2.899
nam-2.873
 ASA-2.799
Token
Token ID198
Feature activation-1.04e-01

Pos logit contributions
orian+0.711
orb+0.673
kson+0.672
rupal+0.651
oulos+0.650
Neg logit contributions
dump-0.670
Random-0.670
 Sham-0.665
nam-0.658
 ASA-0.627
TokenTo
Token ID2514
Feature activation-1.83e-01

Pos logit contributions
dump+0.055
Random+0.055
 Sham+0.054
nam+0.054
 ASA+0.051
Neg logit contributions
orian-0.089
orb-0.085
kson-0.085
rupal-0.082
oulos-0.082
Token make
Token ID787
Feature activation-2.90e-01

Pos logit contributions
dump+0.114
Random+0.113
 Sham+0.113
nam+0.111
 ASA+0.106
Neg logit contributions
orian-0.139
orb-0.132
kson-0.132
rupal-0.128
oulos-0.128
Tokenland
Token ID1044
Feature activation+4.19e+00

Pos logit contributions
orian+0.885
orb+0.837
kson+0.835
rupal+0.805
oulos+0.802
Neg logit contributions
dump-0.928
Random-0.927
 Sham-0.920
nam-0.908
 ASA-0.874
Token<|endoftext|>
Token ID50256
Feature activation+4.72e+00

Pos logit contributions
orian+2.807
orb+2.642
kson+2.639
rupal+2.549
oulos+2.529
Neg logit contributions
Random-2.960
dump-2.960
 Sham-2.937
nam-2.878
 ASA-2.796
TokenBy
Token ID3886
Feature activation+2.15e-02

Pos logit contributions
orian+3.906
orb+3.765
kson+3.656
tale+3.599
rupal+3.589
Neg logit contributions
 Sham-2.550
dump-2.487
nam-2.425
 ASA-2.416
Random-2.404
Token Sam
Token ID3409
Feature activation+4.94e+00

Pos logit contributions
orian+0.016
orb+0.015
kson+0.015
rupal+0.015
oulos+0.015
Neg logit contributions
dump-0.014
Random-0.014
 Sham-0.014
nam-0.014
 ASA-0.013
Token,
Token ID11
Feature activation+7.49e-01

Pos logit contributions
orian+4.067
orb+3.881
kson+3.865
rupal+3.746
oulos+3.746
Neg logit contributions
dump-2.714
Random-2.706
nam-2.600
 Sham-2.564
 unres-2.514
Token updated
Token ID6153
Feature activation+1.04e+01

Pos logit contributions
orian+0.572
orb+0.543
kson+0.543
rupal+0.526
oulos+0.524
Neg logit contributions
dump-0.466
Random-0.464
 Sham-0.459
nam-0.454
 ASA-0.433
Token on
Token ID319
Feature activation+6.65e+00

Pos logit contributions
orian+6.282
orb+5.884
kson+5.807
oulos+5.646
rupal+5.630
Neg logit contributions
dump-7.327
Random-7.203
nam-7.161
 Sham-7.041
-6.781
Token 15
Token ID1315
Feature activation+2.91e+00

Pos logit contributions
orian+4.327
orb+4.090
kson+4.079
rupal+3.942
oulos+3.910
Neg logit contributions
dump-4.665
Random-4.640
nam-4.535
 Sham-4.475
-4.298
Token July
Token ID2901
Feature activation+7.85e+00

Pos logit contributions
orian+2.065
orb+1.957
kson+1.945
rupal+1.889
oulos+1.874
Neg logit contributions
dump-1.948
Random-1.944
 Sham-1.919
nam-1.897
 ASA-1.822
Token 2017
Token ID2177
Feature activation+3.71e+00

Pos logit contributions
orian+4.728
orb+4.472
kson+4.452
oulos+4.315
rupal+4.299
Neg logit contributions
dump-5.766
Random-5.731
 Sham-5.610
nam-5.600
 ASA-5.326
Token
Token ID198
Feature activation+2.01e+00

Pos logit contributions
orian+2.512
orb+2.374
kson+2.360
rupal+2.285
oulos+2.274
Neg logit contributions
dump-2.608
Random-2.597
 Sham-2.568
nam-2.542
 ASA-2.431
TokenHalf
Token ID31305
Feature activation+1.04e+00

Pos logit contributions
orian+2.382
orb+2.276
kson+2.236
oulos+2.161
arious+2.155
Neg logit contributions
dump-2.186
Random-2.170
 Sham-2.167
nam-2.133
 ASA-2.074
Token Ac
Token ID4013
Feature activation+4.67e+00

Pos logit contributions
orian+0.807
orb+0.769
kson+0.768
rupal+0.744
oulos+0.741
Neg logit contributions
dump-0.632
Random-0.630
 Sham-0.625
nam-0.617
 ASA-0.589
Tokenre
Token ID260
Feature activation+2.23e+00

Pos logit contributions
orian+2.992
orb+2.771
kson+2.758
arious+2.611
rupal+2.606
Neg logit contributions
dump-3.548
Random-3.496
 Sham-3.470
nam-3.440
 unres-3.325
Token collaboration
Token ID12438
Feature activation+5.25e-01

Pos logit contributions
orian+1.734
kson+1.651
orb+1.649
oulos+1.592
rupal+1.592
Neg logit contributions
dump-1.361
Random-1.355
 Sham-1.333
nam-1.326
 ASA-1.258
Token An
Token ID1052
Feature activation-1.15e+00

Pos logit contributions
orian+0.389
orb+0.369
kson+0.369
rupal+0.358
oulos+0.356
Neg logit contributions
dump-0.339
Random-0.338
 Sham-0.337
nam-0.332
 ASA-0.318
Tokenic
Token ID291
Feature activation+1.01e+01

Pos logit contributions
dump+0.744
Random+0.742
 Sham+0.741
nam+0.741
 ASA+0.699
Neg logit contributions
orian-0.838
orb-0.796
kson-0.795
rupal-0.774
oulos-0.766
Tokenca
Token ID6888
Feature activation+1.37e+00

Pos logit contributions
orian+7.607
orb+7.165
kson+7.068
arious+6.966
uria+6.834
Neg logit contributions
Random-6.190
dump-6.077
nam-5.911
 Sham-5.897
 unres-5.848
Token.
Token ID13
Feature activation+5.87e-01

Pos logit contributions
orian+1.037
orb+0.988
kson+0.986
rupal+0.952
oulos+0.950
Neg logit contributions
dump-0.859
Random-0.855
 Sham-0.844
nam-0.838
 ASA-0.798
Token Brew
Token ID9702
Feature activation+1.25e+00

Pos logit contributions
orian+0.459
orb+0.437
kson+0.436
rupal+0.424
oulos+0.422
Neg logit contributions
Random-0.353
dump-0.353
 Sham-0.352
nam-0.346
 ASA-0.331
Tokened
Token ID276
Feature activation-3.18e+00

Pos logit contributions
orian+0.727
orb+0.681
kson+0.680
rupal+0.652
oulos+0.648
Neg logit contributions
dump-1.009
Random-1.007
 Sham-1.001
nam-0.991
 ASA-0.956
Token with
Token ID351
Feature activation-1.51e+00

Pos logit contributions
 Sham+2.083
Random+2.042
dump+2.035
nam+2.014
 ASA+1.937
Neg logit contributions
orian-2.320
orb-2.194
kson-2.191
rupal-2.161
oulos-2.146
Token.
Token ID13
Feature activation+4.47e-01

Pos logit contributions
orian+2.889
orb+2.754
kson+2.719
rupal+2.635
oulos+2.626
Neg logit contributions
dump-2.894
Random-2.892
nam-2.833
 Sham-2.809
 ASA-2.721
Token Oklahoma
Token ID10433
Feature activation-1.20e+00

Pos logit contributions
orian+0.346
orb+0.330
kson+0.328
rupal+0.319
oulos+0.317
Neg logit contributions
dump-0.273
Random-0.273
 Sham-0.272
nam-0.267
 ASA-0.256
Token,
Token ID11
Feature activation-1.89e-01

Pos logit contributions
dump+0.739
Random+0.736
 Sham+0.732
nam+0.722
 ASA+0.691
Neg logit contributions
orian-0.923
orb-0.880
kson-0.877
rupal-0.851
oulos-0.847
Token a
Token ID257
Feature activation+1.02e+00

Pos logit contributions
dump+0.112
Random+0.112
 Sham+0.111
nam+0.109
 ASA+0.105
Neg logit contributions
orian-0.150
orb-0.143
kson-0.143
rupal-0.139
oulos-0.138
Token seism
Token ID30518
Feature activation+8.69e+00

Pos logit contributions
orian+0.808
kson+0.768
orb+0.768
rupal+0.743
oulos+0.742
Neg logit contributions
Random-0.603
dump-0.603
 Sham-0.592
nam-0.588
 ASA-0.558
Tokenically
Token ID1146
Feature activation+9.36e+00

Pos logit contributions
orian+3.807
orb+3.398
kson+3.120
arious+3.081
uitive+2.936
Neg logit contributions
Random-8.278
 Sham-8.155
dump-8.083
nam-8.036
 ASA-7.876
Token inactive
Token ID28621
Feature activation+5.02e+00

Pos logit contributions
orian+6.054
orb+5.870
kson+5.811
rupal+5.527
oulos+5.506
Neg logit contributions
Random-6.506
dump-6.489
nam-6.073
 Sham-6.040
 ASA-5.870
Token area
Token ID1989
Feature activation+1.59e+00

Pos logit contributions
orian+3.675
kson+3.509
orb+3.482
arious+3.332
oulos+3.330
Neg logit contributions
Random-3.239
dump-3.203
nam-3.103
 Sham-3.078
 ASA-2.895
Token before
Token ID878
Feature activation+3.91e+00

Pos logit contributions
orian+1.165
kson+1.106
orb+1.105
rupal+1.069
oulos+1.058
Neg logit contributions
Random-1.043
dump-1.042
 Sham-1.027
nam-1.016
 ASA-0.975
Token gas
Token ID3623
Feature activation+1.14e+00

Pos logit contributions
orian+2.936
kson+2.779
orb+2.770
oulos+2.707
rupal+2.697
Neg logit contributions
Random-2.454
dump-2.446
nam-2.390
 Sham-2.361
 ASA-2.248
Token fracking
Token ID25441
Feature activation+2.20e+00

Pos logit contributions
orian+0.850
orb+0.810
kson+0.805
oulos+0.781
rupal+0.778
Neg logit contributions
Random-0.732
dump-0.726
 Sham-0.719
nam-0.713
 ASA-0.679
Token best
Token ID1266
Feature activation-2.09e+00

Pos logit contributions
dump+0.318
Random+0.317
 Sham+0.314
nam+0.310
 ASA+0.295
Neg logit contributions
orian-0.421
orb-0.402
kson-0.401
rupal-0.389
oulos-0.387
Token,
Token ID11
Feature activation-1.55e+00

Pos logit contributions
dump+1.303
Random+1.299
 Sham+1.287
nam+1.272
 ASA+1.215
Neg logit contributions
orian-1.589
orb-1.513
kson-1.510
rupal-1.463
oulos-1.457
Token such
Token ID884
Feature activation-4.08e-01

Pos logit contributions
dump+0.930
Random+0.924
 Sham+0.922
nam+0.906
 ASA+0.869
Neg logit contributions
orian-1.217
orb-1.159
kson-1.156
rupal-1.123
oulos-1.118
Token an
Token ID281
Feature activation-2.47e+00

Pos logit contributions
dump+0.247
Random+0.246
 Sham+0.244
nam+0.241
 ASA+0.230
Neg logit contributions
orian-0.317
orb-0.302
kson-0.302
rupal-0.293
oulos-0.292
Token approach
Token ID3164
Feature activation-8.73e-01

Pos logit contributions
dump+1.497
 Sham+1.492
Random+1.492
nam+1.472
 ASA+1.424
Neg logit contributions
orian-1.921
kson-1.810
orb-1.806
rupal-1.765
agascar-1.750
Token alien
Token ID8756
Feature activation+9.18e+00

Pos logit contributions
dump+0.560
Random+0.558
 Sham+0.556
nam+0.549
 ASA+0.522
Neg logit contributions
orian-0.650
orb-0.617
kson-0.614
rupal-0.597
oulos-0.594
Tokenates
Token ID689
Feature activation+4.31e+00

Pos logit contributions
orian+4.523
orb+4.206
kson+3.958
oulos+3.948
arious+3.930
Neg logit contributions
dump-7.824
Random-7.804
 Sham-7.553
 ASA-7.542
nam-7.428
Token young
Token ID1862
Feature activation-2.99e+00

Pos logit contributions
orian+3.120
kson+2.979
orb+2.954
rupal+2.873
arious+2.839
Neg logit contributions
dump-2.777
Random-2.764
nam-2.689
 Sham-2.674
 ASA-2.542
Token voters
Token ID4446
Feature activation-7.51e-01

Pos logit contributions
 Sham+1.568
dump+1.559
Random+1.555
nam+1.536
 ASA+1.460
Neg logit contributions
orian-2.573
orb-2.461
kson-2.447
oulos-2.385
rupal-2.382
Token,
Token ID11
Feature activation-2.99e-01

Pos logit contributions
dump+0.475
 Sham+0.473
Random+0.472
nam+0.465
 ASA+0.442
Neg logit contributions
orian-0.566
orb-0.537
kson-0.537
rupal-0.520
oulos-0.518
Token says
Token ID1139
Feature activation+1.39e-01

Pos logit contributions
dump+0.184
Random+0.184
 Sham+0.182
nam+0.180
 ASA+0.172
Neg logit contributions
orian-0.230
orb-0.219
kson-0.218
rupal-0.212
oulos-0.211
Token debt
Token ID5057
Feature activation-3.26e+00

Pos logit contributions
 Sham+0.860
dump+0.860
Random+0.858
nam+0.856
 ASA+0.806
Neg logit contributions
orian-1.139
orb-1.092
kson-1.081
rupal-1.048
oulos-1.048
Token,
Token ID11
Feature activation-1.74e+00

Pos logit contributions
dump+2.027
 Sham+2.019
Random+2.013
nam+2.007
 ASA+1.895
Neg logit contributions
orian-2.468
orb-2.352
kson-2.347
rupal-2.279
arious-2.263
Token which
Token ID543
Feature activation-2.13e+00

Pos logit contributions
dump+1.152
Random+1.148
 Sham+1.144
nam+1.131
 ASA+1.081
Neg logit contributions
orian-1.257
kson-1.201
orb-1.198
rupal-1.155
arious-1.149
Token has
Token ID468
Feature activation+1.69e-01

Pos logit contributions
dump+1.314
Random+1.308
 Sham+1.307
nam+1.288
 ASA+1.231
Neg logit contributions
orian-1.627
orb-1.551
kson-1.541
rupal-1.503
oulos-1.492
Token an
Token ID281
Feature activation+6.11e-01

Pos logit contributions
orian+0.119
orb+0.112
kson+0.112
rupal+0.108
oulos+0.108
Neg logit contributions
dump-0.115
Random-0.115
 Sham-0.113
nam-0.112
 ASA-0.108
Token impact
Token ID2928
Feature activation+9.05e+00

Pos logit contributions
orian+0.447
orb+0.425
kson+0.424
rupal+0.410
oulos+0.409
Neg logit contributions
dump-0.399
Random-0.398
 Sham-0.394
nam-0.390
 ASA-0.373
Token on
Token ID319
Feature activation+4.80e+00

Pos logit contributions
orian+4.529
kson+4.137
orb+4.090
tale+3.920
agascar+3.915
Neg logit contributions
dump-7.696
Random-7.559
 Sham-7.427
 ASA-7.286
nam-7.261
Token students
Token ID2444
Feature activation+1.24e+00

Pos logit contributions
orian+3.339
kson+3.166
orb+3.115
rupal+3.022
oulos+3.000
Neg logit contributions
dump-3.266
Random-3.239
 Sham-3.174
nam-3.133
 ASA-2.986
Token
Token ID447
Feature activation+2.04e+00

Pos logit contributions
orian+0.990
orb+0.941
kson+0.940
rupal+0.913
oulos+0.910
Neg logit contributions
dump-0.735
Random-0.730
 Sham-0.723
nam-0.711
 ASA-0.681
Token
Token ID247
Feature activation+2.85e+00

Pos logit contributions
orian+1.706
orb+1.629
kson+1.628
rupal+1.583
oulos+1.579
Neg logit contributions
dump-1.120
Random-1.116
 Sham-1.103
nam-1.091
 ASA-1.034
Token life
Token ID1204
Feature activation+1.49e+00

Pos logit contributions
orian+2.087
kson+1.985
orb+1.984
rupal+1.924
oulos+1.919
Neg logit contributions
dump-1.848
Random-1.843
 Sham-1.815
nam-1.796
 ASA-1.719
Token New
Token ID968
Feature activation+6.40e-01

Pos logit contributions
orian+2.029
kson+1.931
orb+1.922
rupal+1.861
oulos+1.860
Neg logit contributions
Random-1.550
dump-1.536
nam-1.477
 Sham-1.453
 ASA-1.400
Token York
Token ID1971
Feature activation+3.16e+00

Pos logit contributions
orian+0.499
orb+0.473
kson+0.472
rupal+0.458
oulos+0.457
Neg logit contributions
Random-0.388
dump-0.388
 Sham-0.378
nam-0.374
 ASA-0.360
Token branch
Token ID8478
Feature activation+3.24e+00

Pos logit contributions
orian+2.345
kson+2.206
orb+2.197
rupal+2.127
tale+2.114
Neg logit contributions
Random-2.024
dump-2.019
nam-1.956
 Sham-1.947
 ASA-1.878
Token of
Token ID286
Feature activation+2.02e+00

Pos logit contributions
orian+2.247
kson+2.103
orb+2.096
rupal+2.029
arious+2.015
Neg logit contributions
dump-2.228
Random-2.221
nam-2.113
 Sham-2.107
 ASA-2.064
Token the
Token ID262
Feature activation+2.01e+00

Pos logit contributions
orian+1.723
orb+1.641
kson+1.632
rupal+1.596
arious+1.583
Neg logit contributions
dump-1.080
Random-1.065
nam-1.006
 Sham-1.001
 ASA-0.963
Token Foot
Token ID7870
Feature activation+9.04e+00

Pos logit contributions
orian+1.656
orb+1.570
kson+1.564
rupal+1.520
arious+1.518
Neg logit contributions
dump-1.120
Random-1.117
nam-1.067
 Sham-1.047
 ASA-1.001
Token into
Token ID656
Feature activation-1.65e+00

Pos logit contributions
orian+6.107
orb+5.514
kson+5.506
tale+5.352
rupal+5.314
Neg logit contributions
dump-6.116
Random-6.051
 ASA-5.669
nam-5.653
 Sham-5.623
Token a
Token ID257
Feature activation-2.46e+00

Pos logit contributions
dump+0.953
Random+0.950
 Sham+0.932
nam+0.924
 ASA+0.880
Neg logit contributions
orian-1.337
orb-1.276
kson-1.273
rupal-1.236
oulos-1.231
Token criminal
Token ID4301
Feature activation+1.34e+00

Pos logit contributions
 Sham+1.380
dump+1.379
Random+1.371
nam+1.358
 ASA+1.283
Neg logit contributions
orian-2.013
kson-1.929
orb-1.929
rupal-1.875
oulos-1.868
Token powerhouse
Token ID34886
Feature activation+1.07e-01

Pos logit contributions
orian+1.087
orb+1.035
kson+1.026
rupal+1.002
arious+0.995
Neg logit contributions
Random-0.765
dump-0.757
nam-0.738
 Sham-0.736
 ASA-0.703
Token involved
Token ID2950
Feature activation+5.21e-02

Pos logit contributions
orian+0.079
orb+0.075
kson+0.075
rupal+0.073
oulos+0.072
Neg logit contributions
dump-0.069
Random-0.069
 Sham-0.068
nam-0.068
 ASA-0.065
Token under
Token ID739
Feature activation+2.29e+00

Pos logit contributions
dump+0.591
Random+0.588
 Sham+0.587
nam+0.577
 ASA+0.548
Neg logit contributions
orian-0.893
orb-0.852
kson-0.850
rupal-0.830
oulos-0.825
Tokenstudy
Token ID44517
Feature activation-3.31e+00

Pos logit contributions
orian+1.982
orb+1.903
kson+1.882
oulos+1.830
rupal+1.829
Neg logit contributions
Random-1.180
dump-1.174
 Sham-1.156
nam-1.134
 ASA-1.084
Token,
Token ID11
Feature activation-1.79e+00

Pos logit contributions
 Sham+2.074
dump+2.027
Random+2.015
nam+2.009
 ASA+1.909
Neg logit contributions
orian-2.526
orb-2.406
kson-2.381
rupal-2.353
oulos-2.323
Token Norm
Token ID11220
Feature activation+1.36e+00

Pos logit contributions
 Sham+1.168
dump+1.163
Random+1.160
nam+1.143
 ASA+1.096
Neg logit contributions
orian-1.305
orb-1.243
kson-1.234
rupal-1.204
oulos-1.192
Token Van
Token ID6656
Feature activation-4.12e+00

Pos logit contributions
orian+1.072
orb+1.020
kson+1.020
rupal+0.987
oulos+0.985
Neg logit contributions
dump-0.813
Random-0.812
 Sham-0.799
nam-0.791
 ASA-0.758
Token Brock
Token ID20501
Feature activation+9.02e+00

Pos logit contributions
 Sham+2.410
Random+2.392
dump+2.390
nam+2.337
 ASA+2.220
Neg logit contributions
orian-3.274
orb-3.091
kson-3.059
oulos-3.053
rupal-3.047
Tokenlin
Token ID2815
Feature activation+2.94e-01

Pos logit contributions
orian+4.785
orb+4.441
kson+4.387
tale+4.174
oulos+4.073
Neg logit contributions
Random-7.423
 Sham-7.355
dump-7.278
nam-7.019
 ASA-6.994
Token.
Token ID13
Feature activation+4.92e-01

Pos logit contributions
orian+0.211
orb+0.200
kson+0.200
rupal+0.193
oulos+0.192
Neg logit contributions
dump-0.196
Random-0.195
 Sham-0.194
nam-0.191
 ASA-0.184
Token
Token ID198
Feature activation+9.02e-01

Pos logit contributions
orian+0.390
orb+0.371
kson+0.370
rupal+0.361
oulos+0.359
Neg logit contributions
dump-0.291
Random-0.291
 Sham-0.291
nam-0.285
 ASA-0.273
Token
Token ID198
Feature activation+6.98e-01

Pos logit contributions
orian+0.643
orb+0.608
kson+0.608
rupal+0.588
oulos+0.587
Neg logit contributions
dump-0.608
Random-0.608
 Sham-0.603
nam-0.597
 ASA-0.570
TokenFar
Token ID21428
Feature activation-3.26e+00

Pos logit contributions
orian+0.588
orb+0.565
kson+0.560
rupal+0.544
arious+0.541
Neg logit contributions
dump-0.376
 Sham-0.372
Random-0.372
nam-0.366
 ASA-0.351
Token of
Token ID286
Feature activation+3.61e+00

Pos logit contributions
orian+2.440
kson+2.313
orb+2.310
rupal+2.231
oulos+2.217
Neg logit contributions
dump-2.153
Random-2.150
 Sham-2.108
nam-2.093
 ASA-1.999
Token the
Token ID262
Feature activation+2.58e+00

Pos logit contributions
orian+2.679
kson+2.553
orb+2.542
rupal+2.467
agascar+2.445
Neg logit contributions
Random-2.282
dump-2.270
 Sham-2.180
nam-2.176
 ASA-2.072
Token limestone
Token ID48520
Feature activation+3.95e+00

Pos logit contributions
orian+2.114
kson+2.012
orb+2.004
rupal+1.943
oulos+1.934
Neg logit contributions
dump-1.456
Random-1.450
 Sham-1.406
nam-1.401
 ASA-1.325
Token surrounding
Token ID7346
Feature activation-1.04e+00

Pos logit contributions
orian+2.923
kson+2.789
orb+2.782
rupal+2.703
oulos+2.663
Neg logit contributions
Random-2.519
dump-2.500
 Sham-2.458
nam-2.453
 ASA-2.337
Token the
Token ID262
Feature activation+1.97e+00

Pos logit contributions
dump+0.614
Random+0.611
 Sham+0.607
nam+0.599
 ASA+0.571
Neg logit contributions
orian-0.832
orb-0.793
kson-0.792
rupal-0.768
oulos-0.766
Token fossils
Token ID34066
Feature activation+8.94e+00

Pos logit contributions
orian+1.407
kson+1.337
orb+1.329
rupal+1.287
oulos+1.280
Neg logit contributions
Random-1.314
dump-1.309
 Sham-1.281
nam-1.277
 ASA-1.220
Token,
Token ID11
Feature activation+2.06e+00

Pos logit contributions
orian+5.833
kson+5.538
orb+5.435
rupal+5.306
oulos+5.267
Neg logit contributions
Random-6.251
dump-6.127
nam-5.989
 Sham-5.983
 ASA-5.778
Token said
Token ID531
Feature activation-1.05e+00

Pos logit contributions
orian+1.213
kson+1.137
orb+1.131
rupal+1.083
oulos+1.079
Neg logit contributions
dump-1.647
Random-1.646
 Sham-1.622
nam-1.607
 ASA-1.553
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
dump+0.682
Random+0.680
 Sham+0.678
nam+0.670
 ASA+0.641
Neg logit contributions
orian-0.770
orb-0.732
kson-0.731
rupal-0.708
oulos-0.705
Token question
Token ID1808
Feature activation-1.72e+00

Pos logit contributions
orian+1.028
orb+0.974
kson+0.974
rupal+0.941
oulos+0.937
Neg logit contributions
dump-0.839
Random-0.836
 Sham-0.820
nam-0.814
 ASA-0.777
Token of
Token ID286
Feature activation-1.55e+00

Pos logit contributions
dump+1.099
Random+1.096
 Sham+1.088
nam+1.075
 ASA+1.029
Neg logit contributions
orian-1.276
orb-1.212
kson-1.210
rupal-1.172
oulos-1.167
Token "
Token ID366
Feature activation-2.34e+00

Pos logit contributions
 Sham+0.741
Random+0.739
dump+0.735
nam+0.722
 ASA+0.696
Neg logit contributions
orian-0.923
orb-0.881
kson-0.870
rupal-0.854
oulos-0.843
TokenA
Token ID32
Feature activation-1.11e+00

Pos logit contributions
Random+1.305
dump+1.283
 Sham+1.264
nam+1.255
 ASA+1.178
Neg logit contributions
orian-1.951
kson-1.863
orb-1.859
rupal-1.817
oulos-1.812
Token movement
Token ID3356
Feature activation+3.04e+00

Pos logit contributions
dump+0.660
Random+0.655
 Sham+0.652
nam+0.647
 ASA+0.611
Neg logit contributions
orian-0.885
kson-0.842
orb-0.841
rupal-0.820
oulos-0.811
Token is
Token ID318
Feature activation+3.51e-01

Pos logit contributions
orian+2.236
orb+2.120
kson+2.113
rupal+2.041
oulos+2.037
Neg logit contributions
dump-1.979
Random-1.976
 Sham-1.952
nam-1.936
 ASA-1.856
Token a
Token ID257
Feature activation+2.30e-01

Pos logit contributions
orian+0.286
orb+0.273
kson+0.273
rupal+0.265
oulos+0.264
Neg logit contributions
dump-0.200
Random-0.199
 Sham-0.198
nam-0.195
 ASA-0.186
Tokenfoot
Token ID5898
Feature activation+8.74e+00

Pos logit contributions
orian+0.164
orb+0.156
kson+0.155
rupal+0.150
oulos+0.150
Neg logit contributions
dump-0.154
Random-0.154
 Sham-0.153
nam-0.151
 ASA-0.144
Token that
Token ID326
Feature activation+2.01e+00

Pos logit contributions
orian+5.687
orb+5.333
kson+5.204
oulos+5.118
arious+5.075
Neg logit contributions
Random-6.170
dump-6.145
nam-5.926
 Sham-5.832
 ASA-5.773
Token must
Token ID1276
Feature activation+2.38e+00

Pos logit contributions
orian+1.512
kson+1.439
orb+1.436
rupal+1.382
oulos+1.381
Neg logit contributions
Random-1.273
dump-1.269
 Sham-1.244
nam-1.235
 ASA-1.183
Token not
Token ID407
Feature activation+2.47e-01

Pos logit contributions
orian+1.803
orb+1.728
kson+1.701
rupal+1.660
oulos+1.659
Neg logit contributions
Random-1.498
dump-1.486
 Sham-1.467
nam-1.442
 ASA-1.387
Token fade
Token ID22100
Feature activation-3.27e+00

Pos logit contributions
orian+0.201
orb+0.192
kson+0.191
rupal+0.186
oulos+0.186
Neg logit contributions
Random-0.141
dump-0.141
 Sham-0.139
nam-0.137
 ASA-0.131
Token away
Token ID1497
Feature activation-6.34e+00

Pos logit contributions
 Sham+1.833
Random+1.819
dump+1.817
nam+1.812
 unres+1.703
Neg logit contributions
orian-2.659
kson-2.554
orb-2.550
rupal-2.497
oulos-2.459
Token earthquakes
Token ID29781
Feature activation+4.20e+00

Pos logit contributions
dump+0.279
 Sham+0.277
Random+0.277
nam+0.274
 ASA+0.263
Neg logit contributions
orian-0.289
orb-0.275
kson-0.272
rupal-0.264
oulos-0.263
Token.
Token ID13
Feature activation+4.47e-01

Pos logit contributions
orian+2.889
orb+2.754
kson+2.719
rupal+2.635
oulos+2.626
Neg logit contributions
dump-2.894
Random-2.892
nam-2.833
 Sham-2.809
 ASA-2.721
Token Oklahoma
Token ID10433
Feature activation-1.20e+00

Pos logit contributions
orian+0.346
orb+0.330
kson+0.328
rupal+0.319
oulos+0.317
Neg logit contributions
dump-0.273
Random-0.273
 Sham-0.272
nam-0.267
 ASA-0.256
Token,
Token ID11
Feature activation-1.89e-01

Pos logit contributions
dump+0.739
Random+0.736
 Sham+0.732
nam+0.722
 ASA+0.691
Neg logit contributions
orian-0.923
orb-0.880
kson-0.877
rupal-0.851
oulos-0.847
Token a
Token ID257
Feature activation+1.02e+00

Pos logit contributions
dump+0.112
Random+0.112
 Sham+0.111
nam+0.109
 ASA+0.105
Neg logit contributions
orian-0.150
orb-0.143
kson-0.143
rupal-0.139
oulos-0.138
Token seism
Token ID30518
Feature activation+8.69e+00

Pos logit contributions
orian+0.808
kson+0.768
orb+0.768
rupal+0.743
oulos+0.742
Neg logit contributions
Random-0.603
dump-0.603
 Sham-0.592
nam-0.588
 ASA-0.558
Tokenically
Token ID1146
Feature activation+9.36e+00

Pos logit contributions
orian+3.807
orb+3.398
kson+3.120
arious+3.081
uitive+2.936
Neg logit contributions
Random-8.278
 Sham-8.155
dump-8.083
nam-8.036
 ASA-7.876
Token inactive
Token ID28621
Feature activation+5.02e+00

Pos logit contributions
orian+6.054
orb+5.870
kson+5.811
rupal+5.527
oulos+5.506
Neg logit contributions
Random-6.506
dump-6.489
nam-6.073
 Sham-6.040
 ASA-5.870
Token area
Token ID1989
Feature activation+1.59e+00

Pos logit contributions
orian+3.675
kson+3.509
orb+3.482
arious+3.332
oulos+3.330
Neg logit contributions
Random-3.239
dump-3.203
nam-3.103
 Sham-3.078
 ASA-2.895
Token before
Token ID878
Feature activation+3.91e+00

Pos logit contributions
orian+1.165
kson+1.106
orb+1.105
rupal+1.069
oulos+1.058
Neg logit contributions
Random-1.043
dump-1.042
 Sham-1.027
nam-1.016
 ASA-0.975
Token gas
Token ID3623
Feature activation+1.14e+00

Pos logit contributions
orian+2.936
kson+2.779
orb+2.770
oulos+2.707
rupal+2.697
Neg logit contributions
Random-2.454
dump-2.446
nam-2.390
 Sham-2.361
 ASA-2.248
Tokennot
Token ID1662
Feature activation+6.87e-01

Pos logit contributions
orian+2.788
orb+2.686
kson+2.590
tale+2.541
rupal+2.528
Neg logit contributions
 Sham-2.333
dump-2.318
Random-2.315
nam-2.261
 ASA-2.212
Tokench
Token ID354
Feature activation+1.20e+00

Pos logit contributions
orian+0.480
kson+0.455
orb+0.453
rupal+0.438
oulos+0.437
Neg logit contributions
dump-0.476
Random-0.471
nam-0.471
 Sham-0.465
 ASA-0.439
Token studio
Token ID8034
Feature activation-3.52e+00

Pos logit contributions
orian+0.945
kson+0.898
orb+0.896
rupal+0.867
oulos+0.864
Neg logit contributions
dump-0.718
Random-0.716
 Sham-0.703
nam-0.695
 ASA-0.664
Token specializing
Token ID40847
Feature activation-7.21e-01

Pos logit contributions
 Sham+2.170
dump+2.155
nam+2.143
Random+2.137
 ASA+2.025
Neg logit contributions
orian-2.667
orb-2.558
kson-2.529
rupal-2.484
oulos-2.471
Token in
Token ID287
Feature activation+3.61e-01

Pos logit contributions
dump+0.453
Random+0.452
 Sham+0.444
nam+0.439
 ASA+0.422
Neg logit contributions
orian-0.547
kson-0.521
orb-0.520
rupal-0.503
oulos-0.501
Token ecc
Token ID21399
Feature activation+8.61e+00

Pos logit contributions
orian+0.284
kson+0.270
orb+0.270
rupal+0.261
oulos+0.260
Neg logit contributions
dump-0.217
Random-0.217
 Sham-0.213
nam-0.210
 ASA-0.201
Tokenles
Token ID829
Feature activation+5.62e-01

Pos logit contributions
orian+4.346
orb+3.782
arious+3.664
kson+3.607
rupal+3.517
Neg logit contributions
 Sham-7.572
Random-7.557
dump-7.543
 ASA-7.373
 unres-7.302
Tokenial
Token ID498
Feature activation-9.34e-01

Pos logit contributions
orian+0.425
orb+0.404
kson+0.403
rupal+0.391
oulos+0.389
Neg logit contributions
dump-0.353
Random-0.352
 Sham-0.349
nam-0.345
 ASA-0.330
Token art
Token ID1242
Feature activation+6.14e-01

Pos logit contributions
dump+0.529
Random+0.528
 Sham+0.527
nam+0.521
 ASA+0.493
Neg logit contributions
orian-0.760
orb-0.729
kson-0.726
rupal-0.706
oulos-0.703
Token had
Token ID550
Feature activation-1.69e+00

Pos logit contributions
orian+0.454
orb+0.431
kson+0.430
rupal+0.417
oulos+0.415
Neg logit contributions
dump-0.397
Random-0.396
 Sham-0.392
nam-0.387
 ASA-0.371
Token drawn
Token ID7428
Feature activation-2.55e+00

Pos logit contributions
dump+1.039
Random+1.037
 Sham+1.036
nam+1.029
 ASA+0.976
Neg logit contributions
orian-1.290
orb-1.226
kson-1.218
rupal-1.189
oulos-1.183
Token The
Token ID383
Feature activation+8.11e-01

Pos logit contributions
orian+0.649
orb+0.618
kson+0.615
rupal+0.598
oulos+0.594
Neg logit contributions
Random-0.537
dump-0.535
 Sham-0.535
nam-0.526
 ASA-0.504
Token electric
Token ID5186
Feature activation+2.57e+00

Pos logit contributions
orian+0.598
orb+0.569
kson+0.567
oulos+0.547
rupal+0.547
Neg logit contributions
dump-0.526
Random-0.522
 Sham-0.513
nam-0.511
 ASA-0.486
Token applause
Token ID28445
Feature activation-4.84e+00

Pos logit contributions
orian+2.002
orb+1.910
kson+1.899
rupal+1.840
arious+1.838
Neg logit contributions
dump-1.552
Random-1.548
 Sham-1.528
nam-1.508
 ASA-1.438
Token inside
Token ID2641
Feature activation-1.85e-01

Pos logit contributions
dump+2.987
 Sham+2.984
Random+2.962
nam+2.902
 unres+2.777
Neg logit contributions
orian-3.615
orb-3.430
kson-3.424
rupal-3.374
natureconservancy-3.366
Token the
Token ID262
Feature activation+9.90e-01

Pos logit contributions
dump+0.110
Random+0.110
 Sham+0.109
nam+0.107
 ASA+0.102
Neg logit contributions
orian-0.146
orb-0.139
kson-0.139
rupal-0.135
oulos-0.134
Token Ecc
Token ID38308
Feature activation+8.58e+00

Pos logit contributions
orian+0.757
kson+0.720
orb+0.719
rupal+0.692
oulos+0.692
Neg logit contributions
dump-0.611
Random-0.608
nam-0.594
 Sham-0.593
 ASA-0.561
Tokenles
Token ID829
Feature activation+8.83e-01

Pos logit contributions
orian+5.789
orb+5.430
kson+5.284
arious+5.183
rupal+5.112
Neg logit contributions
dump-6.036
Random-5.950
 Sham-5.917
nam-5.748
 ASA-5.694
Token after
Token ID706
Feature activation-2.46e+00

Pos logit contributions
orian+0.711
orb+0.680
kson+0.679
rupal+0.661
oulos+0.658
Neg logit contributions
Random-0.509
dump-0.509
 Sham-0.506
nam-0.500
 ASA-0.474
Token
Token ID564
Feature activation+1.96e+00

Pos logit contributions
 Sham+1.473
Random+1.472
dump+1.468
nam+1.443
 ASA+1.378
Neg logit contributions
orian-1.923
kson-1.830
orb-1.828
rupal-1.778
oulos-1.764
Token
Token ID250
Feature activation+2.28e-01

Pos logit contributions
orian+1.612
orb+1.539
kson+1.526
rupal+1.480
arious+1.471
Neg logit contributions
dump-1.110
Random-1.100
 Sham-1.099
nam-1.074
 ASA-1.031
TokenManchester
Token ID40744
Feature activation-1.18e+00

Pos logit contributions
orian+0.209
orb+0.201
kson+0.200
rupal+0.195
oulos+0.194
Neg logit contributions
dump-0.107
Random-0.106
 Sham-0.105
nam-0.103
 ASA-0.098
Tokenall
Token ID439
Feature activation+1.36e+00

Pos logit contributions
orian+2.731
orb+2.583
kson+2.542
rupal+2.444
tale+2.426
Neg logit contributions
Random-3.065
 Sham-3.041
dump-3.038
nam-2.998
 ASA-2.930
Token that
Token ID326
Feature activation+1.89e+00

Pos logit contributions
orian+0.995
orb+0.943
kson+0.939
rupal+0.914
oulos+0.906
Neg logit contributions
dump-0.884
Random-0.883
 Sham-0.871
nam-0.862
 ASA-0.830
Token stuff
Token ID3404
Feature activation-1.93e-01

Pos logit contributions
orian+1.392
kson+1.323
orb+1.321
rupal+1.278
oulos+1.272
Neg logit contributions
Random-1.215
dump-1.210
 Sham-1.193
nam-1.186
 ASA-1.136
Token has
Token ID468
Feature activation+1.22e+00

Pos logit contributions
Random+0.127
dump+0.127
 Sham+0.125
nam+0.124
 ASA+0.119
Neg logit contributions
orian-0.140
orb-0.133
kson-0.133
rupal-0.128
oulos-0.127
Token an
Token ID281
Feature activation+3.30e-01

Pos logit contributions
orian+0.876
kson+0.837
orb+0.833
rupal+0.802
oulos+0.799
Neg logit contributions
dump-0.805
Random-0.805
 Sham-0.790
nam-0.786
 ASA-0.756
Token impact
Token ID2928
Feature activation+8.50e+00

Pos logit contributions
orian+0.230
orb+0.218
kson+0.218
rupal+0.210
oulos+0.210
Neg logit contributions
dump-0.227
Random-0.226
 Sham-0.224
nam-0.222
 ASA-0.213
Token on
Token ID319
Feature activation+3.33e+00

Pos logit contributions
orian+4.590
kson+4.316
orb+4.277
rupal+4.073
tale+4.066
Neg logit contributions
dump-6.803
Random-6.799
 Sham-6.573
 ASA-6.536
nam-6.510
Token our
Token ID674
Feature activation+1.49e+00

Pos logit contributions
orian+2.497
kson+2.362
orb+2.341
rupal+2.277
oulos+2.266
Neg logit contributions
dump-2.116
Random-2.104
 Sham-2.049
nam-2.040
 ASA-1.953
Token long
Token ID890
Feature activation-4.63e-01

Pos logit contributions
orian+1.165
kson+1.109
orb+1.105
rupal+1.068
oulos+1.068
Neg logit contributions
dump-0.903
Random-0.899
 Sham-0.885
nam-0.874
 ASA-0.834
Token-
Token ID12
Feature activation+1.52e+00

Pos logit contributions
dump+0.267
Random+0.266
 Sham+0.264
nam+0.261
 ASA+0.248
Neg logit contributions
orian-0.373
orb-0.356
kson-0.355
rupal-0.346
oulos-0.344
Tokenterm
Token ID4354
Feature activation-2.77e+00

Pos logit contributions
orian+0.989
orb+0.935
kson+0.919
rupal+0.888
arious+0.886
Neg logit contributions
Random-1.115
dump-1.109
 Sham-1.103
nam-1.087
 ASA-1.053
Token,
Token ID11
Feature activation+1.11e+00

Pos logit contributions
orian+1.108
orb+1.054
kson+1.049
rupal+1.012
oulos+1.010
Neg logit contributions
Random-1.035
dump-1.032
 Sham-1.018
nam-1.014
 ASA-0.970
Token as
Token ID355
Feature activation+1.25e+00

Pos logit contributions
orian+0.853
orb+0.811
kson+0.809
rupal+0.782
oulos+0.781
Neg logit contributions
dump-0.677
Random-0.676
 Sham-0.667
nam-0.662
 ASA-0.632
Token Toronto
Token ID6586
Feature activation+2.65e+00

Pos logit contributions
orian+0.944
orb+0.898
kson+0.898
rupal+0.866
oulos+0.866
Neg logit contributions
dump-0.783
Random-0.781
 Sham-0.769
nam-0.766
 ASA-0.733
Token Police
Token ID4287
Feature activation+3.13e+00

Pos logit contributions
orian+2.023
orb+1.907
kson+1.906
oulos+1.849
rupal+1.847
Neg logit contributions
Random-1.634
dump-1.633
 Sham-1.600
nam-1.591
 ASA-1.527
Token Chief
Token ID5953
Feature activation+2.99e+00

Pos logit contributions
orian+2.343
orb+2.210
kson+2.192
oulos+2.122
rupal+2.121
Neg logit contributions
dump-1.969
Random-1.969
 Sham-1.917
nam-1.910
 ASA-1.821
Token Bill
Token ID3941
Feature activation+8.47e+00

Pos logit contributions
orian+1.700
kson+1.590
orb+1.588
rupal+1.519
oulos+1.518
Neg logit contributions
dump-2.437
Random-2.427
 Sham-2.401
nam-2.386
 ASA-2.309
Token Blair
Token ID18520
Feature activation+9.65e-01

Pos logit contributions
orian+5.879
kson+5.742
arious+5.606
tale+5.474
orb+5.454
Neg logit contributions
nam-5.505
dump-5.483
Random-5.406
 unres-5.261
 ASA-5.187
Token confirmed
Token ID4999
Feature activation+2.53e+00

Pos logit contributions
orian+0.667
orb+0.632
kson+0.630
rupal+0.610
oulos+0.606
Neg logit contributions
dump-0.669
Random-0.667
 Sham-0.662
nam-0.656
 ASA-0.628
Token in
Token ID287
Feature activation+9.57e-01

Pos logit contributions
orian+1.808
orb+1.711
kson+1.706
oulos+1.645
rupal+1.645
Neg logit contributions
dump-1.689
Random-1.688
 Sham-1.666
nam-1.656
 ASA-1.589
Token October
Token ID3267
Feature activation+2.47e+00

Pos logit contributions
orian+0.725
orb+0.686
kson+0.685
rupal+0.665
arious+0.663
Neg logit contributions
Random-0.599
dump-0.599
 Sham-0.588
nam-0.586
 ASA-0.559
Token.
Token ID13
Feature activation+1.34e-01

Pos logit contributions
orian+1.655
kson+1.562
orb+1.560
rupal+1.507
oulos+1.500
Neg logit contributions
dump-1.754
Random-1.750
 Sham-1.731
nam-1.714
 ASA-1.651
Token experiences
Token ID6461
Feature activation+3.47e+00

Pos logit contributions
orian+1.690
kson+1.610
orb+1.595
oulos+1.546
rupal+1.537
Neg logit contributions
dump-1.415
Random-1.412
 Sham-1.375
nam-1.366
 ASA-1.286
Token of
Token ID286
Feature activation+2.40e+00

Pos logit contributions
orian+2.377
kson+2.230
orb+2.213
rupal+2.159
oulos+2.138
Neg logit contributions
dump-2.445
Random-2.421
 Sham-2.380
nam-2.361
 ASA-2.276
Token college
Token ID4152
Feature activation+1.25e+00

Pos logit contributions
orian+1.745
kson+1.660
orb+1.647
rupal+1.598
oulos+1.594
Neg logit contributions
dump-1.563
Random-1.551
 Sham-1.522
nam-1.518
 ASA-1.434
Token students
Token ID2444
Feature activation+1.24e-01

Pos logit contributions
orian+0.927
orb+0.880
kson+0.879
rupal+0.853
oulos+0.850
Neg logit contributions
dump-0.802
Random-0.797
 Sham-0.787
nam-0.778
 ASA-0.744
Token,
Token ID11
Feature activation+1.51e+00

Pos logit contributions
orian+0.079
orb+0.075
kson+0.074
rupal+0.071
oulos+0.071
Neg logit contributions
dump-0.093
Random-0.092
 Sham-0.092
nam-0.091
 ASA-0.088
Token first
Token ID717
Feature activation+8.42e+00

Pos logit contributions
orian+1.136
orb+1.077
kson+1.077
rupal+1.044
oulos+1.042
Neg logit contributions
dump-0.962
Random-0.958
 Sham-0.945
nam-0.936
 ASA-0.895
Token year
Token ID614
Feature activation+1.68e+00

Pos logit contributions
orian+5.668
orb+5.369
kson+5.248
oulos+5.245
rupal+5.206
Neg logit contributions
dump-5.658
Random-5.593
 Sham-5.306
nam-5.272
 ASA-5.048
Token students
Token ID2444
Feature activation+2.30e+00

Pos logit contributions
orian+1.232
orb+1.169
kson+1.167
rupal+1.129
oulos+1.126
Neg logit contributions
dump-1.095
Random-1.090
 Sham-1.076
nam-1.067
 ASA-1.017
Token on
Token ID319
Feature activation+2.57e+00

Pos logit contributions
orian+1.552
orb+1.465
kson+1.464
rupal+1.414
oulos+1.408
Neg logit contributions
dump-1.629
Random-1.621
 Sham-1.602
nam-1.587
 ASA-1.526
Token this
Token ID428
Feature activation+3.73e-01

Pos logit contributions
orian+1.823
kson+1.721
orb+1.717
rupal+1.666
oulos+1.656
Neg logit contributions
dump-1.730
Random-1.712
nam-1.681
 Sham-1.679
 ASA-1.594
Token campus
Token ID7611
Feature activation+2.42e+00

Pos logit contributions
orian+0.259
orb+0.245
kson+0.245
rupal+0.237
oulos+0.236
Neg logit contributions
dump-0.258
Random-0.257
 Sham-0.255
nam-0.253
 ASA-0.243
Token Jeff
Token ID5502
Feature activation+3.61e+00

Pos logit contributions
orian+0.948
kson+0.904
orb+0.902
oulos+0.874
rupal+0.873
Neg logit contributions
dump-0.699
Random-0.699
 Sham-0.688
nam-0.683
 ASA-0.648
Token Baker
Token ID14372
Feature activation+1.01e+00

Pos logit contributions
orian+2.485
kson+2.369
orb+2.344
rupal+2.265
arious+2.254
Neg logit contributions
dump-2.496
Random-2.463
 Sham-2.430
nam-2.427
 ASA-2.341
Token,
Token ID11
Feature activation+2.35e-01

Pos logit contributions
orian+0.741
kson+0.703
orb+0.703
rupal+0.679
oulos+0.679
Neg logit contributions
dump-0.655
Random-0.652
 Sham-0.647
nam-0.639
 ASA-0.612
Token chief
Token ID4039
Feature activation+1.74e+00

Pos logit contributions
orian+0.183
orb+0.174
kson+0.174
rupal+0.168
oulos+0.168
Neg logit contributions
dump-0.143
Random-0.142
 Sham-0.141
nam-0.140
 ASA-0.133
Token of
Token ID286
Feature activation+3.13e+00

Pos logit contributions
orian+1.286
orb+1.220
kson+1.218
rupal+1.180
oulos+1.179
Neg logit contributions
dump-1.118
Random-1.111
 Sham-1.100
nam-1.092
 ASA-1.038
Token police
Token ID1644
Feature activation+8.38e+00

Pos logit contributions
orian+2.363
orb+2.258
kson+2.244
rupal+2.178
oulos+2.177
Neg logit contributions
dump-1.943
Random-1.938
 Sham-1.897
nam-1.893
 ASA-1.784
Token,
Token ID11
Feature activation+3.53e+00

Pos logit contributions
orian+5.375
orb+5.122
kson+4.902
oulos+4.837
 helicop+4.794
Neg logit contributions
dump-5.857
Random-5.810
nam-5.665
 Sham-5.659
 ASA-5.390
Token said
Token ID531
Feature activation+6.79e-01

Pos logit contributions
orian+2.460
kson+2.327
orb+2.321
oulos+2.256
rupal+2.234
Neg logit contributions
dump-2.413
Random-2.397
 Sham-2.359
nam-2.352
 ASA-2.243
Token the
Token ID262
Feature activation+1.22e+00

Pos logit contributions
orian+0.535
orb+0.510
kson+0.509
rupal+0.494
oulos+0.492
Neg logit contributions
dump-0.406
Random-0.404
 Sham-0.401
nam-0.396
 ASA-0.378
Token man
Token ID582
Feature activation-9.70e-01

Pos logit contributions
orian+0.990
kson+0.945
orb+0.943
oulos+0.914
rupal+0.913
Neg logit contributions
dump-0.706
Random-0.702
 Sham-0.693
nam-0.687
 ASA-0.651
Token was
Token ID373
Feature activation+1.52e+00

Pos logit contributions
dump+0.619
Random+0.619
 Sham+0.617
nam+0.608
 ASA+0.581
Neg logit contributions
orian-0.724
orb-0.689
kson-0.684
rupal-0.665
arious-0.661
Token a
Token ID257
Feature activation+5.98e-01

Pos logit contributions
orian+1.504
kson+1.428
orb+1.421
rupal+1.369
arious+1.364
Neg logit contributions
dump-1.372
Random-1.361
 Sham-1.338
nam-1.333
 ASA-1.272
Token new
Token ID649
Feature activation-4.97e+00

Pos logit contributions
orian+0.500
kson+0.478
orb+0.478
rupal+0.463
oulos+0.462
Neg logit contributions
dump-0.328
Random-0.324
 Sham-0.320
nam-0.318
 ASA-0.302
Token study
Token ID2050
Feature activation-6.58e+00

Pos logit contributions
Random+2.018
 Sham+2.010
dump+1.950
nam+1.892
 ASA+1.837
Neg logit contributions
orian-4.833
orb-4.663
kson-4.635
rupal-4.607
oulos-4.539
Token Sven
Token ID44611
Feature activation+5.80e-01

Pos logit contributions
 Sham+3.699
Random+3.658
dump+3.612
nam+3.586
 ASA+3.417
Neg logit contributions
orian-5.287
orb-5.044
kson-5.033
arious-4.985
rupal-4.979
Token D
Token ID360
Feature activation-6.12e-01

Pos logit contributions
orian+0.456
kson+0.436
orb+0.435
rupal+0.420
oulos+0.419
Neg logit contributions
dump-0.347
Random-0.346
 Sham-0.342
nam-0.338
 ASA-0.323
Tokenref
Token ID5420
Feature activation+8.38e+00

Pos logit contributions
dump+0.415
Random+0.414
 Sham+0.411
nam+0.407
 ASA+0.390
Neg logit contributions
orian-0.432
orb-0.409
kson-0.409
rupal-0.396
oulos-0.393
Tokenahl
Token ID15668
Feature activation-1.51e+00

Pos logit contributions
orian+6.036
kson+5.724
orb+5.722
oulos+5.464
arious+5.372
Neg logit contributions
Random-5.554
dump-5.430
 Sham-5.316
 ASA-5.148
 unres-5.104
Token from
Token ID422
Feature activation-2.86e-01

Pos logit contributions
dump+0.961
Random+0.960
 Sham+0.953
nam+0.942
 ASA+0.900
Neg logit contributions
orian-1.132
orb-1.076
kson-1.072
rupal-1.043
oulos-1.036
Token the
Token ID262
Feature activation-9.02e-01

Pos logit contributions
dump+0.168
Random+0.167
 Sham+0.165
nam+0.163
 ASA+0.155
Neg logit contributions
orian-0.229
orb-0.218
kson-0.218
rupal-0.211
oulos-0.211
Token Max
Token ID5436
Feature activation+4.08e-01

Pos logit contributions
dump+0.516
Random+0.513
 Sham+0.506
nam+0.502
 ASA+0.476
Neg logit contributions
orian-0.735
orb-0.701
kson-0.701
rupal-0.678
oulos-0.677
Token Plan
Token ID5224
Feature activation-1.95e+00

Pos logit contributions
orian+0.287
orb+0.273
kson+0.272
rupal+0.261
oulos+0.260
Neg logit contributions
dump-0.277
Random-0.276
 Sham-0.272
nam-0.272
 ASA-0.261
Token Far
Token ID6755
Feature activation-3.78e-01

Pos logit contributions
orian+1.942
orb+1.861
kson+1.859
rupal+1.811
oulos+1.805
Neg logit contributions
dump-1.064
Random-1.062
 Sham-1.052
nam-1.033
 ASA-0.975
Tokenrah
Token ID11392
Feature activation+2.31e+00

Pos logit contributions
dump+0.141
nam+0.138
Random+0.138
 Sham+0.138
 ASA+0.119
Neg logit contributions
orian-0.379
kson-0.370
orb-0.365
 helicop-0.365
oulos-0.362
Token W
Token ID370
Feature activation+1.29e+00

Pos logit contributions
orian+2.183
orb+2.097
kson+2.093
rupal+2.044
oulos+2.038
Neg logit contributions
dump-1.013
Random-1.009
 Sham-1.000
nam-0.978
 ASA-0.917
Tokenether
Token ID6750
Feature activation+3.61e+00

Pos logit contributions
orian+1.112
kson+1.066
orb+1.055
rupal+1.038
oulos+1.032
Neg logit contributions
dump-0.682
Random-0.673
nam-0.665
 Sham-0.664
 ASA-0.618
Tokens
Token ID82
Feature activation+4.07e+00

Pos logit contributions
orian+2.779
kson+2.660
orb+2.654
rupal+2.555
oulos+2.541
Neg logit contributions
Random-2.193
dump-2.189
 Sham-2.170
nam-2.117
 ASA-2.061
Token Mysteries
Token ID28298
Feature activation+8.37e+00

Pos logit contributions
orian+3.342
kson+3.185
orb+3.178
rupal+3.083
oulos+3.068
Neg logit contributions
dump-2.284
Random-2.267
 Sham-2.239
nam-2.216
 ASA-2.115
Token,
Token ID11
Feature activation+3.31e+00

Pos logit contributions
orian+5.438
orb+5.176
kson+5.138
tale+4.956
rupal+4.910
Neg logit contributions
dump-5.852
Random-5.723
 Sham-5.685
nam-5.637
 unres-5.448
Token comic
Token ID9048
Feature activation+4.54e+00

Pos logit contributions
orian+1.845
orb+1.716
kson+1.713
rupal+1.644
oulos+1.613
Neg logit contributions
dump-2.722
Random-2.699
 Sham-2.685
nam-2.667
 ASA-2.575
Token book
Token ID1492
Feature activation+4.47e+00

Pos logit contributions
orian+3.093
orb+2.934
kson+2.896
rupal+2.808
tale+2.802
Neg logit contributions
Random-3.157
dump-3.154
 Sham-3.103
nam-3.064
 ASA-2.960
Token short
Token ID1790
Feature activation+2.64e+00

Pos logit contributions
orian+3.806
orb+3.636
kson+3.622
rupal+3.528
oulos+3.506
Neg logit contributions
dump-2.342
Random-2.329
 Sham-2.281
nam-2.263
 ASA-2.150
Token stories
Token ID3923
Feature activation+5.45e+00

Pos logit contributions
orian+1.640
kson+1.560
orb+1.545
rupal+1.489
tale+1.474
Neg logit contributions
dump-2.003
Random-1.995
 Sham-1.957
nam-1.946
 ASA-1.882
Token 2011
Token ID2813
Feature activation+1.80e+00

Pos logit contributions
orian+0.902
orb+0.855
kson+0.853
rupal+0.819
arious+0.811
Neg logit contributions
dump-1.007
Random-1.003
 Sham-0.982
nam-0.976
 ASA-0.937
Token and
Token ID290
Feature activation+1.61e+00

Pos logit contributions
orian+1.290
orb+1.228
kson+1.221
rupal+1.184
oulos+1.182
Neg logit contributions
dump-1.188
Random-1.187
 Sham-1.163
nam-1.147
 ASA-1.089
Token 2012
Token ID2321
Feature activation-6.88e-01

Pos logit contributions
orian+1.214
kson+1.156
orb+1.155
rupal+1.114
oulos+1.113
Neg logit contributions
dump-1.014
Random-1.011
 Sham-0.990
nam-0.982
 ASA-0.930
Token,
Token ID11
Feature activation+6.60e-01

Pos logit contributions
dump+0.446
Random+0.445
 Sham+0.440
nam+0.435
 ASA+0.415
Neg logit contributions
orian-0.507
orb-0.482
kson-0.481
rupal-0.466
oulos-0.464
Token the
Token ID262
Feature activation+1.19e+00

Pos logit contributions
orian+0.491
kson+0.466
orb+0.466
rupal+0.452
oulos+0.449
Neg logit contributions
dump-0.423
Random-0.421
 Sham-0.415
nam-0.411
 ASA-0.390
Token Geological
Token ID34246
Feature activation+8.37e+00

Pos logit contributions
orian+0.934
kson+0.893
orb+0.892
oulos+0.862
rupal+0.859
Neg logit contributions
dump-0.707
Random-0.705
 Sham-0.688
nam-0.686
 ASA-0.638
Token Society
Token ID7023
Feature activation+5.22e+00

Pos logit contributions
orian+5.550
kson+5.352
orb+5.188
rupal+5.010
tale+4.985
Neg logit contributions
dump-5.917
Random-5.805
nam-5.665
 Sham-5.582
-5.419
Token of
Token ID286
Feature activation-2.46e-01

Pos logit contributions
orian+3.433
orb+3.277
kson+3.221
rupal+3.128
oulos+3.062
Neg logit contributions
dump-3.671
Random-3.597
 Sham-3.554
nam-3.516
Gh-3.335
Token America
Token ID2253
Feature activation-1.90e-01

Pos logit contributions
dump+0.137
Random+0.136
 Sham+0.134
nam+0.133
 ASA+0.126
Neg logit contributions
orian-0.204
orb-0.195
kson-0.195
rupal-0.189
oulos-0.188
Token in
Token ID287
Feature activation+1.89e+00

Pos logit contributions
dump+0.117
Random+0.117
 Sham+0.116
nam+0.114
 ASA+0.109
Neg logit contributions
orian-0.145
orb-0.138
kson-0.138
rupal-0.134
oulos-0.133
Token 2011
Token ID2813
Feature activation+2.74e+00

Pos logit contributions
orian+1.090
orb+1.023
kson+1.020
rupal+0.975
oulos+0.970
Neg logit contributions
dump-1.519
Random-1.514
 Sham-1.499
nam-1.487
 ASA-1.436
Token open
Token ID1280
Feature activation-2.39e+00

Pos logit contributions
dump+1.701
 Sham+1.671
nam+1.653
Random+1.644
 ASA+1.577
Neg logit contributions
orian-1.862
kson-1.777
orb-1.747
rupal-1.727
oulos-1.718
Token my
Token ID616
Feature activation-3.93e+00

Pos logit contributions
dump+1.578
 Sham+1.575
Random+1.574
nam+1.548
 ASA+1.488
Neg logit contributions
orian-1.725
kson-1.644
orb-1.638
rupal-1.589
oulos-1.585
Token mouth
Token ID5422
Feature activation-8.15e+00

Pos logit contributions
 Sham+2.040
dump+2.037
Random+2.033
nam+1.999
 ASA+1.892
Neg logit contributions
orian-3.366
kson-3.236
orb-3.220
rupal-3.162
oulos-3.146
Token and
Token ID290
Feature activation-3.08e+00

Pos logit contributions
dump+4.638
nam+4.619
 Sham+4.594
Random+4.563
 unres+4.485
Neg logit contributions
orian-6.323
kson-6.165
rupal-6.039
oulos-5.994
orb-5.948
Token her
Token ID607
Feature activation-2.15e+00

Pos logit contributions
dump+1.948
 Sham+1.934
Random+1.898
nam+1.889
 ASA+1.818
Neg logit contributions
orian-2.318
kson-2.224
orb-2.205
rupal-2.166
oulos-2.141
Token tongue
Token ID11880
Feature activation-1.10e+01

Pos logit contributions
dump+1.340
Random+1.335
 Sham+1.333
nam+1.321
 ASA+1.255
Neg logit contributions
orian-1.634
kson-1.557
orb-1.554
rupal-1.516
oulos-1.506
Token sl
Token ID1017
Feature activation-4.37e+00

Pos logit contributions
nam+6.587
 Sham+6.512
dump+6.424
 unres+6.195
Random+6.145
Neg logit contributions
orian-8.100
kson-7.825
agascar-7.688
orb-7.567
rupal-7.562
Tokenither
Token ID1555
Feature activation-2.23e+00

Pos logit contributions
dump+2.903
nam+2.874
 Sham+2.861
Random+2.842
 ASA+2.663
Neg logit contributions
orian-3.047
kson-2.943
orb-2.865
agascar-2.841
 helicop-2.825
Tokens
Token ID82
Feature activation-8.69e-01

Pos logit contributions
dump+1.237
 Sham+1.227
nam+1.225
Random+1.225
 ASA+1.136
Neg logit contributions
orian-1.849
kson-1.768
orb-1.761
rupal-1.721
oulos-1.715
Token into
Token ID656
Feature activation-4.66e+00

Pos logit contributions
dump+0.543
Random+0.542
 Sham+0.539
nam+0.533
 ASA+0.508
Neg logit contributions
orian-0.660
kson-0.628
orb-0.627
rupal-0.609
oulos-0.606
Token mine
Token ID6164
Feature activation-3.55e+00

Pos logit contributions
 Sham+2.980
dump+2.960
Random+2.945
nam+2.908
 ASA+2.791
Neg logit contributions
orian-3.389
kson-3.252
orb-3.247
oulos-3.147
rupal-3.146
Token of
Token ID286
Feature activation-1.32e+00

Pos logit contributions
dump+1.334
Random+1.334
 Sham+1.327
nam+1.304
 ASA+1.255
Neg logit contributions
orian-1.535
kson-1.462
orb-1.455
rupal-1.412
oulos-1.405
Token the
Token ID262
Feature activation-3.59e-01

Pos logit contributions
dump+0.755
Random+0.752
 Sham+0.745
nam+0.736
 ASA+0.700
Neg logit contributions
orian-1.067
orb-1.018
kson-1.017
rupal-0.987
oulos-0.983
Token manga
Token ID15911
Feature activation+1.78e-01

Pos logit contributions
dump+0.230
Random+0.229
 Sham+0.225
nam+0.225
 ASA+0.213
Neg logit contributions
orian-0.267
orb-0.254
kson-0.253
rupal-0.245
oulos-0.245
Token series
Token ID2168
Feature activation+3.18e-01

Pos logit contributions
orian+0.127
orb+0.121
kson+0.121
rupal+0.116
oulos+0.116
Neg logit contributions
dump-0.119
Random-0.118
 Sham-0.116
nam-0.116
 ASA-0.111
Token have
Token ID423
Feature activation-3.10e+00

Pos logit contributions
orian+0.227
orb+0.216
kson+0.214
oulos+0.207
rupal+0.206
Neg logit contributions
dump-0.214
Random-0.213
 Sham-0.210
nam-0.209
 ASA-0.199
Token cum
Token ID10973
Feature activation-1.10e+01

Pos logit contributions
Random+1.901
dump+1.896
 Sham+1.895
nam+1.867
 ASA+1.794
Neg logit contributions
orian-2.383
kson-2.270
orb-2.266
rupal-2.204
oulos-2.189
Tokenul
Token ID377
Feature activation-6.91e+00

Pos logit contributions
dump+6.071
Random+5.848
nam+5.841
 Sham+5.761
 ASA+5.378
Neg logit contributions
kson-8.618
orian-8.442
orb-8.022
rupal-7.988
natureconservancy-7.931
Tokenatively
Token ID9404
Feature activation-8.34e-01

Pos logit contributions
nam+4.762
Random+4.652
 Sham+4.615
dump+4.574
 ASA+4.287
Neg logit contributions
kson-4.466
orian-4.466
orb-4.352
oulos-4.327
rupal-4.302
Token sold
Token ID2702
Feature activation+7.36e-01

Pos logit contributions
dump+0.504
Random+0.502
 Sham+0.497
nam+0.491
 ASA+0.469
Neg logit contributions
orian-0.652
orb-0.621
kson-0.620
rupal-0.601
oulos-0.599
Token over
Token ID625
Feature activation-3.35e+00

Pos logit contributions
orian+0.571
orb+0.544
kson+0.543
rupal+0.526
oulos+0.524
Neg logit contributions
dump-0.448
Random-0.446
 Sham-0.442
nam-0.437
 ASA-0.417
Token 22
Token ID2534
Feature activation-1.13e+00

Pos logit contributions
dump+2.123
 Sham+2.115
Random+2.112
nam+2.089
 ASA+1.992
Neg logit contributions
orian-2.499
kson-2.377
orb-2.356
rupal-2.308
arious-2.292
Token.
Token ID13
Feature activation-1.20e+00

Pos logit contributions
dump+0.162
Random+0.161
 Sham+0.160
nam+0.158
 ASA+0.152
Neg logit contributions
orian-0.176
orb-0.167
kson-0.167
rupal-0.161
oulos-0.161
Token A
Token ID317
Feature activation-1.08e+00

Pos logit contributions
 Sham+0.758
Random+0.751
dump+0.744
nam+0.736
 ASA+0.710
Neg logit contributions
orian-0.906
orb-0.866
kson-0.854
rupal-0.832
oulos-0.832
Token pill
Token ID9582
Feature activation-2.08e+00

Pos logit contributions
dump+0.653
Random+0.652
 Sham+0.650
nam+0.639
 ASA+0.611
Neg logit contributions
orian-0.844
kson-0.804
orb-0.804
oulos-0.775
rupal-0.775
Token called
Token ID1444
Feature activation-3.64e+00

Pos logit contributions
dump+1.216
Random+1.209
 Sham+1.195
nam+1.173
 ASA+1.124
Neg logit contributions
orian-1.652
kson-1.599
orb-1.580
oulos-1.550
rupal-1.537
Token Sugar
Token ID20874
Feature activation-3.03e+00

Pos logit contributions
 Sham+2.126
Random+2.086
dump+2.083
nam+2.051
 ASA+1.983
Neg logit contributions
orian-2.928
kson-2.786
orb-2.771
arious-2.695
oulos-2.691
Token Cum
Token ID27843
Feature activation-1.03e+01

Pos logit contributions
dump+1.859
Random+1.838
 Sham+1.834
nam+1.800
 ASA+1.721
Neg logit contributions
orian-2.337
kson-2.247
orb-2.210
rupal-2.166
oulos-2.155
Token,
Token ID11
Feature activation-3.92e+00

Pos logit contributions
dump+6.905
 Sham+6.653
Random+6.600
nam+6.278
 ASA+6.118
Neg logit contributions
orian-6.910
kson-6.799
natureconservancy-6.616
oulos-6.504
agascar-6.468
Token for
Token ID329
Feature activation+2.43e-01

Pos logit contributions
 Sham+2.466
Random+2.439
dump+2.435
nam+2.401
 ASA+2.301
Neg logit contributions
orian-2.926
kson-2.779
orb-2.772
rupal-2.709
oulos-2.688
Token instance
Token ID4554
Feature activation+1.38e+00

Pos logit contributions
orian+0.206
orb+0.197
kson+0.197
rupal+0.192
oulos+0.191
Neg logit contributions
dump-0.130
Random-0.130
 Sham-0.128
nam-0.127
 ASA-0.120
Token,
Token ID11
Feature activation-5.76e-01

Pos logit contributions
orian+1.025
orb+0.978
kson+0.973
rupal+0.944
oulos+0.938
Neg logit contributions
dump-0.880
Random-0.878
 Sham-0.871
nam-0.858
 ASA-0.826
Token allegedly
Token ID7910
Feature activation+7.10e-01

Pos logit contributions
dump+0.357
Random+0.356
 Sham+0.353
nam+0.349
 ASA+0.333
Neg logit contributions
orian-0.440
orb-0.419
kson-0.418
rupal-0.405
oulos-0.404
Token
Token ID198
Feature activation-6.83e-01

Pos logit contributions
dump+0.337
Random+0.336
 Sham+0.334
nam+0.330
 ASA+0.316
Neg logit contributions
orian-0.378
orb-0.360
kson-0.358
rupal-0.347
oulos-0.346
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
Random+0.441
dump+0.440
 Sham+0.438
nam+0.435
 ASA+0.410
Neg logit contributions
orian-0.507
kson-0.480
orb-0.480
 helicop-0.475
oulos-0.470
Tokensudo
Token ID24032
Feature activation-5.29e+00

Pos logit contributions
dump+0.659
Random+0.656
 Sham+0.643
nam+0.638
 ASA+0.594
Neg logit contributions
orian-1.223
kson-1.173
orb-1.171
oulos-1.141
rupal-1.140
Token ch
Token ID442
Feature activation-3.49e+00

Pos logit contributions
dump+3.256
 Sham+3.220
Random+3.201
nam+3.196
 ASA+3.039
Neg logit contributions
orian-4.013
orb-3.834
kson-3.820
oulos-3.766
rupal-3.711
Tokenmod
Token ID4666
Feature activation-4.80e+00

Pos logit contributions
dump+2.232
Random+2.195
nam+2.184
 Sham+2.157
 ASA+2.029
Neg logit contributions
orian-2.597
kson-2.484
orb-2.443
oulos-2.436
rupal-2.429
Token +
Token ID1343
Feature activation-1.01e+01

Pos logit contributions
dump+2.848
Random+2.822
 Sham+2.792
nam+2.748
 ASA+2.629
Neg logit contributions
orian-3.782
kson-3.625
orb-3.596
rupal-3.489
arious-3.480
Tokenx
Token ID87
Feature activation-2.14e+00

Pos logit contributions
Random+4.224
nam+4.203
dump+4.175
 Sham+4.005
 ASA+3.667
Neg logit contributions
orian-9.376
oulos-9.262
agascar-9.054
kson-8.953
orb-8.950
Token /
Token ID1220
Feature activation-2.50e+00

Pos logit contributions
dump+1.256
Random+1.239
 Sham+1.238
nam+1.223
 ASA+1.166
Neg logit contributions
orian-1.715
orb-1.639
kson-1.634
rupal-1.587
oulos-1.585
Tokenetc
Token ID14784
Feature activation-5.16e-01

Pos logit contributions
dump+1.539
Random+1.531
 Sham+1.515
nam+1.504
 ASA+1.427
Neg logit contributions
orian-1.933
kson-1.840
orb-1.840
rupal-1.786
oulos-1.781
Token/
Token ID14
Feature activation-3.29e+00

Pos logit contributions
dump+0.313
Random+0.308
 Sham+0.305
nam+0.304
 ASA+0.287
Neg logit contributions
orian-0.405
kson-0.387
orb-0.386
oulos-0.376
arious-0.375
Tokenpm
Token ID4426
Feature activation-1.50e+00

Pos logit contributions
dump+2.029
Random+1.995
nam+1.984
 Sham+1.976
 ASA+1.846
Neg logit contributions
orian-2.547
kson-2.419
orb-2.414
rupal-2.347
oulos-2.342
Token given
Token ID1813
Feature activation-8.99e-01

Pos logit contributions
orian+0.701
orb+0.671
kson+0.670
rupal+0.651
oulos+0.647
Neg logit contributions
dump-0.414
Random-0.408
 Sham-0.408
nam-0.399
 ASA-0.378
Token by
Token ID416
Feature activation-2.81e-01

Pos logit contributions
dump+0.576
Random+0.575
 Sham+0.572
nam+0.565
 ASA+0.538
Neg logit contributions
orian-0.665
orb-0.633
kson-0.632
rupal-0.614
oulos-0.609
Token people
Token ID661
Feature activation+5.80e-01

Pos logit contributions
dump+0.175
Random+0.175
 Sham+0.173
nam+0.171
 ASA+0.163
Neg logit contributions
orian-0.214
orb-0.203
kson-0.203
rupal-0.197
oulos-0.196
Token like
Token ID588
Feature activation+2.70e+00

Pos logit contributions
orian+0.425
orb+0.403
kson+0.403
rupal+0.390
oulos+0.388
Neg logit contributions
dump-0.378
Random-0.377
 Sham-0.374
nam-0.370
 ASA-0.354
Token Bill
Token ID3941
Feature activation+5.57e+00

Pos logit contributions
orian+2.029
kson+1.944
orb+1.926
rupal+1.865
oulos+1.860
Neg logit contributions
dump-1.699
Random-1.684
nam-1.670
 Sham-1.649
 ASA-1.583
Token Moy
Token ID28523
Feature activation-9.96e+00

Pos logit contributions
orian+4.405
kson+4.278
orb+4.193
oulos+4.060
rupal+4.045
Neg logit contributions
dump-3.158
Random-3.145
nam-3.121
 Sham-3.033
 ASA-2.973
Tokeners
Token ID364
Feature activation-5.80e-01

Pos logit contributions
dump+4.291
nam+4.239
 Sham+4.083
Random+3.977
 Ut+3.675
Neg logit contributions
orian-9.069
kson-8.897
 helicop-8.873
agascar-8.784
orb-8.731
Token,
Token ID11
Feature activation+3.95e-01

Pos logit contributions
dump+0.381
Random+0.380
 Sham+0.377
nam+0.373
 ASA+0.356
Neg logit contributions
orian-0.422
orb-0.400
kson-0.400
rupal-0.387
oulos-0.385
Token suggests
Token ID5644
Feature activation+2.08e-01

Pos logit contributions
orian+0.288
orb+0.273
kson+0.273
rupal+0.264
oulos+0.263
Neg logit contributions
dump-0.259
Random-0.258
 Sham-0.255
nam-0.253
 ASA-0.242
Token that
Token ID326
Feature activation+9.37e-01

Pos logit contributions
orian+0.160
kson+0.153
orb+0.152
rupal+0.147
oulos+0.147
Neg logit contributions
dump-0.128
Random-0.127
 Sham-0.126
nam-0.125
 ASA-0.120
Token the
Token ID262
Feature activation-4.64e-01

Pos logit contributions
orian+0.745
kson+0.713
orb+0.710
oulos+0.687
rupal+0.686
Neg logit contributions
dump-0.551
Random-0.549
 Sham-0.541
nam-0.538
 ASA-0.513
Token ways
Token ID2842
Feature activation-2.13e+00

Pos logit contributions
orian+2.746
kson+2.611
orb+2.595
rupal+2.520
oulos+2.505
Neg logit contributions
dump-2.387
Random-2.373
 Sham-2.334
nam-2.314
 ASA-2.214
Token that
Token ID326
Feature activation+2.66e+00

Pos logit contributions
Random+1.257
dump+1.256
 Sham+1.255
nam+1.238
 ASA+1.174
Neg logit contributions
orian-1.696
orb-1.614
kson-1.608
oulos-1.560
rupal-1.560
Token aren
Token ID3588
Feature activation+2.83e+00

Pos logit contributions
orian+2.002
orb+1.916
kson+1.906
rupal+1.840
oulos+1.838
Neg logit contributions
Random-1.659
dump-1.657
 Sham-1.635
nam-1.620
 ASA-1.552
Token't
Token ID470
Feature activation+2.89e+00

Pos logit contributions
orian+1.820
orb+1.717
kson+1.714
rupal+1.650
oulos+1.633
Neg logit contributions
dump-2.097
Random-2.089
 Sham-2.076
nam-2.050
 ASA-1.985
Token comm
Token ID725
Feature activation-4.53e-02

Pos logit contributions
orian+2.319
orb+2.215
kson+2.202
rupal+2.147
oulos+2.130
Neg logit contributions
dump-1.670
Random-1.655
 Sham-1.637
nam-1.605
 ASA-1.544
Tokenens
Token ID641
Feature activation-9.64e+00

Pos logit contributions
dump+0.037
Random+0.037
 Sham+0.037
nam+0.037
 ASA+0.035
Neg logit contributions
orian-0.026
kson-0.024
orb-0.024
rupal-0.023
oulos-0.023
Tokenurate
Token ID15537
Feature activation+3.97e+00

Pos logit contributions
nam+7.558
Random+7.534
dump+7.495
 Sham+7.494
 unres+7.109
Neg logit contributions
kson-5.130
rupal-4.944
orian-4.936
oulos-4.902
agascar-4.854
Token with
Token ID351
Feature activation+1.35e+00

Pos logit contributions
orian+2.270
orb+2.141
kson+2.097
rupal+2.025
tale+2.002
Neg logit contributions
dump-3.190
Random-3.161
 Sham-3.119
nam-3.085
 ASA-3.014
Token their
Token ID511
Feature activation-3.87e-01

Pos logit contributions
orian+1.057
orb+1.008
kson+1.005
rupal+0.975
oulos+0.973
Neg logit contributions
dump-0.810
Random-0.806
 Sham-0.796
nam-0.786
 ASA-0.751
Token past
Token ID1613
Feature activation+5.78e-01

Pos logit contributions
dump+0.217
Random+0.216
 Sham+0.215
nam+0.212
 ASA+0.202
Neg logit contributions
orian-0.319
orb-0.304
kson-0.304
rupal-0.296
oulos-0.294
Token performances
Token ID13289
Feature activation-3.59e-01

Pos logit contributions
orian+0.486
orb+0.464
kson+0.464
rupal+0.451
oulos+0.449
Neg logit contributions
dump-0.315
Random-0.314
 Sham-0.311
nam-0.307
 ASA-0.291
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
orian+0.224
orb+0.212
kson+0.212
oulos+0.206
rupal+0.205
Neg logit contributions
Random-0.202
dump-0.201
 Sham-0.200
nam-0.199
 ASA-0.188
Token
Token ID198
Feature activation-1.20e+00

Pos logit contributions
Random+0.845
 Sham+0.842
dump+0.839
nam+0.832
 ASA+0.778
Neg logit contributions
orian-1.002
 helicop-0.954
orb-0.950
kson-0.949
oulos-0.932
TokenShow
Token ID15307
Feature activation-3.95e-01

Pos logit contributions
Random+0.719
dump+0.717
 Sham+0.705
nam+0.701
 ASA+0.657
Neg logit contributions
orian-0.944
kson-0.901
orb-0.896
rupal-0.876
oulos-0.875
Token nested
Token ID28376
Feature activation-6.78e+00

Pos logit contributions
Random+0.206
dump+0.205
 Sham+0.203
nam+0.200
 ASA+0.188
Neg logit contributions
orian-0.344
kson-0.329
orb-0.328
rupal-0.319
oulos-0.318
Token quote
Token ID9577
Feature activation-4.81e+00

Pos logit contributions
nam+3.198
Random+3.140
dump+3.107
 Sham+3.032
 ASA+3.008
Neg logit contributions
orb-5.954
orian-5.922
kson-5.819
ngth-5.682
uitive-5.646
Token +
Token ID1343
Feature activation-9.62e+00

Pos logit contributions
Random+1.900
dump+1.865
 Sham+1.789
nam+1.786
 Dota+1.673
Neg logit contributions
orian-4.679
orb-4.580
agascar-4.527
oulos-4.513
kson-4.480
Token
Token ID198
Feature activation-2.64e+00

Pos logit contributions
Random+4.994
 Sham+4.909
nam+4.724
dump+4.581
 Ut+4.507
Neg logit contributions
 helicop-8.700
orian-8.169
 carbohyd-8.145
oulos-8.002
ngth-7.930
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
Random+1.626
 Sham+1.614
dump+1.601
nam+1.594
 ASA+1.485
Neg logit contributions
orian-2.056
 helicop-2.000
orb-1.950
kson-1.943
oulos-1.922
TokenOn
Token ID2202
Feature activation-4.24e-01

Pos logit contributions
Random+1.683
dump+1.664
nam+1.641
 Sham+1.638
Gh+1.553
Neg logit contributions
orian-1.358
kson-1.285
orb-1.283
oulos-1.248
rupal-1.244
Token September
Token ID2693
Feature activation+3.84e+00

Pos logit contributions
 Sham+0.270
Random+0.268
dump+0.268
nam+0.264
 ASA+0.250
Neg logit contributions
orian-0.320
orb-0.305
kson-0.305
oulos-0.296
rupal-0.295
Token 20
Token ID1160
Feature activation+1.37e+00

Pos logit contributions
orian+2.309
orb+2.197
kson+2.161
oulos+2.065
tale+2.059
Neg logit contributions
dump-2.985
Random-2.953
 Sham-2.902
nam-2.880
 ASA-2.816
TokenThe
Token ID464
Feature activation+5.64e-01

Pos logit contributions
orian+0.325
orb+0.310
kson+0.309
rupal+0.301
oulos+0.300
Neg logit contributions
dump-0.222
Random-0.220
 Sham-0.219
nam-0.216
 ASA-0.206
Token Lerner
Token ID49750
Feature activation+2.43e+00

Pos logit contributions
orian+0.384
kson+0.364
orb+0.363
rupal+0.350
oulos+0.349
Neg logit contributions
dump-0.395
Random-0.394
 Sham-0.390
nam-0.387
 ASA-0.371
Token emails
Token ID7237
Feature activation+1.59e+00

Pos logit contributions
orian+1.957
kson+1.881
orb+1.858
rupal+1.813
arious+1.807
Neg logit contributions
Random-1.382
dump-1.371
 Sham-1.338
nam-1.338
 ASA-1.275
Token have
Token ID423
Feature activation-1.38e+00

Pos logit contributions
orian+1.131
orb+1.077
kson+1.072
rupal+1.033
oulos+1.032
Neg logit contributions
Random-1.060
dump-1.050
 Sham-1.037
nam-1.033
 ASA-0.993
Token become
Token ID1716
Feature activation-4.11e+00

Pos logit contributions
dump+0.883
Random+0.880
 Sham+0.876
nam+0.865
 ASA+0.827
Neg logit contributions
orian-1.034
orb-0.982
kson-0.980
rupal-0.951
oulos-0.946
Token almost
Token ID2048
Feature activation-9.49e+00

Pos logit contributions
dump+2.214
 Sham+2.205
Random+2.185
nam+2.173
 ASA+2.049
Neg logit contributions
orian-3.452
kson-3.321
orb-3.314
rupal-3.243
oulos-3.207
Token as
Token ID355
Feature activation-3.17e+00

Pos logit contributions
 Sham+5.304
nam+5.283
Random+5.092
dump+5.045
 unres+5.033
Neg logit contributions
orian-7.460
kson-7.425
rupal-7.262
orb-7.222
oulos-7.129
Token big
Token ID1263
Feature activation-1.89e+00

Pos logit contributions
Random+1.786
dump+1.783
 Sham+1.777
nam+1.747
 ASA+1.655
Neg logit contributions
orian-2.613
kson-2.490
orb-2.487
rupal-2.435
oulos-2.397
Token a
Token ID257
Feature activation-1.68e-01

Pos logit contributions
dump+1.070
Random+1.068
 Sham+1.058
nam+1.044
 ASA+0.992
Neg logit contributions
orian-1.551
kson-1.482
orb-1.481
rupal-1.438
oulos-1.430
Token scandal
Token ID10731
Feature activation-4.22e-01

Pos logit contributions
dump+0.098
Random+0.098
 Sham+0.096
nam+0.095
 ASA+0.091
Neg logit contributions
orian-0.134
orb-0.128
kson-0.128
rupal-0.124
oulos-0.124
Token as
Token ID355
Feature activation+4.41e-01

Pos logit contributions
dump+0.243
Random+0.243
 Sham+0.240
nam+0.237
 ASA+0.226
Neg logit contributions
orian-0.341
orb-0.325
kson-0.325
rupal-0.315
oulos-0.314
Token Appeals
Token ID20172
Feature activation+1.33e+00

Pos logit contributions
 Sham+0.477
Random+0.474
dump+0.472
nam+0.464
 ASA+0.447
Neg logit contributions
orian-0.632
orb-0.605
kson-0.598
rupal-0.586
oulos-0.582
Token to
Token ID284
Feature activation+5.70e-01

Pos logit contributions
orian+0.902
orb+0.852
kson+0.844
rupal+0.820
oulos+0.815
Neg logit contributions
dump-0.943
Random-0.942
 Sham-0.931
nam-0.922
 ASA-0.889
Token identity
Token ID5369
Feature activation+1.68e+00

Pos logit contributions
orian+0.456
orb+0.435
kson+0.434
rupal+0.421
oulos+0.420
Neg logit contributions
dump-0.334
Random-0.333
 Sham-0.329
nam-0.326
 ASA-0.310
Token are
Token ID389
Feature activation-1.34e+00

Pos logit contributions
orian+1.276
orb+1.212
kson+1.211
rupal+1.175
oulos+1.168
Neg logit contributions
dump-1.043
Random-1.043
 Sham-1.028
nam-1.018
 ASA-0.976
Token now
Token ID783
Feature activation-1.56e+00

Pos logit contributions
 Sham+0.742
dump+0.740
Random+0.739
nam+0.735
 ASA+0.691
Neg logit contributions
orian-1.106
orb-1.060
kson-1.058
rupal-1.029
oulos-1.021
Token almost
Token ID2048
Feature activation-9.28e+00

Pos logit contributions
 Sham+0.878
dump+0.876
Random+0.875
nam+0.869
 ASA+0.819
Neg logit contributions
orian-1.278
orb-1.227
kson-1.220
rupal-1.189
oulos-1.179
Token exclusively
Token ID11541
Feature activation-1.91e+00

Pos logit contributions
nam+5.087
 Sham+5.069
 unres+5.017
Random+4.880
 unse+4.715
Neg logit contributions
orian-7.239
kson-7.225
orb-7.056
rupal-7.040
ngth-6.901
Token the
Token ID262
Feature activation-3.18e+00

Pos logit contributions
 Sham+1.177
dump+1.171
Random+1.166
nam+1.163
 ASA+1.112
Neg logit contributions
orian-1.458
orb-1.400
kson-1.382
rupal-1.350
oulos-1.341
Token preserve
Token ID12201
Feature activation-2.71e+00

Pos logit contributions
dump+1.842
 Sham+1.838
Random+1.835
nam+1.817
 ASA+1.749
Neg logit contributions
orian-2.514
orb-2.425
kson-2.406
rupal-2.349
oulos-2.331
Token of
Token ID286
Feature activation+1.09e-01

Pos logit contributions
dump+1.783
Random+1.778
 Sham+1.763
nam+1.744
 ASA+1.671
Neg logit contributions
orian-1.967
orb-1.866
kson-1.863
rupal-1.802
oulos-1.794
Token the
Token ID262
Feature activation+7.02e-01

Pos logit contributions
orian+0.085
orb+0.081
kson+0.081
rupal+0.078
oulos+0.078
Neg logit contributions
dump-0.066
Random-0.065
 Sham-0.065
nam-0.064
 ASA-0.061
Token or
Token ID393
Feature activation-1.53e+00

Pos logit contributions
dump+1.309
Random+1.307
 Sham+1.292
nam+1.288
 ASA+1.218
Neg logit contributions
orian-1.486
kson-1.411
orb-1.401
rupal-1.366
oulos-1.365
Token <
Token ID1279
Feature activation-2.83e+00

Pos logit contributions
dump+0.943
Random+0.940
 Sham+0.933
nam+0.923
 ASA+0.880
Neg logit contributions
orian-1.173
orb-1.116
kson-1.115
rupal-1.081
oulos-1.077
TokenTab
Token ID33349
Feature activation-7.21e+00

Pos logit contributions
Random+1.560
dump+1.547
nam+1.523
 Sham+1.509
 ASA+1.402
Neg logit contributions
orian-2.374
kson-2.278
orb-2.251
oulos-2.222
rupal-2.217
Token>)
Token ID43734
Feature activation-3.37e+00

Pos logit contributions
dump+3.608
Random+3.558
nam+3.519
 Sham+3.497
 ASA+3.167
Neg logit contributions
orian-6.269
kson-6.012
oulos-5.979
orb-5.855
rupal-5.844
Token {
Token ID1391
Feature activation-1.76e+00

Pos logit contributions
Random+2.097
dump+2.085
 Sham+2.061
nam+2.046
 ASA+1.963
Neg logit contributions
orian-2.570
kson-2.448
orb-2.447
oulos-2.387
rupal-2.376
Tokenvi
Token ID8903
Feature activation-9.19e+00

Pos logit contributions
dump+1.107
Random+1.103
 Sham+1.083
nam+1.081
 ASA+1.024
Neg logit contributions
orian-1.337
kson-1.273
orb-1.268
oulos-1.233
rupal-1.233
Token:
Token ID25
Feature activation-2.46e+00

Pos logit contributions
dump+5.615
Random+5.611
 Sham+5.552
nam+5.544
 ASA+5.151
Neg logit contributions
orian-6.711
kson-6.387
oulos-6.330
orb-6.289
 helicop-6.222
Token|
Token ID91
Feature activation-4.66e+00

Pos logit contributions
dump+1.659
Random+1.650
nam+1.623
 Sham+1.622
 ASA+1.540
Neg logit contributions
orian-1.746
kson-1.660
orb-1.647
oulos-1.608
rupal-1.598
Tokenvim
Token ID31124
Feature activation-7.66e+00

Pos logit contributions
dump+2.790
Random+2.749
nam+2.732
 Sham+2.658
 ASA+2.514
Neg logit contributions
orian-3.638
kson-3.497
orb-3.435
oulos-3.415
arious-3.350
Token:
Token ID25
Feature activation-2.51e+00

Pos logit contributions
dump+4.507
nam+4.417
 Sham+4.322
Random+4.294
 ASA+3.969
Neg logit contributions
orian-5.845
 helicop-5.837
oulos-5.637
kson-5.631
orb-5.499
Token|
Token ID91
Feature activation-3.57e+00

Pos logit contributions
dump+1.718
Random+1.711
 Sham+1.690
nam+1.682
 ASA+1.605
Neg logit contributions
orian-1.759
kson-1.667
orb-1.660
oulos-1.609
rupal-1.606
Token told
Token ID1297
Feature activation-1.59e+00

Pos logit contributions
dump+1.721
 Sham+1.716
Random+1.711
nam+1.704
 ASA+1.631
Neg logit contributions
orian-1.295
orb-1.209
kson-1.198
rupal-1.161
oulos-1.155
Token the
Token ID262
Feature activation+3.62e-01

Pos logit contributions
dump+1.003
Random+1.002
 Sham+0.996
nam+0.980
 ASA+0.940
Neg logit contributions
orian-1.204
orb-1.145
kson-1.142
rupal-1.108
oulos-1.102
Token Today
Token ID6288
Feature activation-1.84e+00

Pos logit contributions
orian+0.279
orb+0.265
kson+0.265
oulos+0.256
rupal+0.255
Neg logit contributions
dump-0.223
Random-0.222
nam-0.218
 Sham-0.218
 ASA-0.206
Token show
Token ID905
Feature activation-3.97e+00

Pos logit contributions
dump+0.941
Random+0.938
 Sham+0.930
nam+0.914
 ASA+0.867
Neg logit contributions
orian-1.604
orb-1.539
kson-1.538
rupal-1.496
oulos-1.490
Token's
Token ID338
Feature activation-2.05e+00

Pos logit contributions
 Sham+2.657
dump+2.643
Random+2.636
nam+2.574
 ASA+2.487
Neg logit contributions
orian-2.801
orb-2.668
kson-2.652
rupal-2.585
arious-2.566
Token Savannah
Token ID40695
Feature activation-9.16e+00

Pos logit contributions
dump+1.392
Random+1.390
 Sham+1.384
nam+1.363
 ASA+1.310
Neg logit contributions
orian-1.441
orb-1.368
kson-1.363
rupal-1.320
oulos-1.313
Token Guth
Token ID44003
Feature activation-5.74e-01

Pos logit contributions
 Sham+4.574
Random+4.288
nam+4.245
dump+4.097
 Ut+3.995
Neg logit contributions
orian-8.026
kson-7.783
orb-7.665
agascar-7.660
oulos-7.608
Tokenrie
Token ID5034
Feature activation-9.41e-01

Pos logit contributions
dump+0.411
Random+0.409
 Sham+0.406
nam+0.399
 ASA+0.387
Neg logit contributions
orian-0.386
orb-0.365
kson-0.365
rupal-0.351
arious-0.347
Token who
Token ID508
Feature activation+5.59e-02

Pos logit contributions
dump+0.660
Random+0.658
 Sham+0.654
nam+0.646
 ASA+0.621
Neg logit contributions
orian-0.643
orb-0.609
kson-0.607
rupal-0.587
oulos-0.584
Token brought
Token ID3181
Feature activation+2.30e+00

Pos logit contributions
orian+0.038
orb+0.036
kson+0.036
rupal+0.034
oulos+0.034
Neg logit contributions
dump-0.040
Random-0.040
 Sham-0.039
nam-0.039
 ASA-0.037
Token up
Token ID510
Feature activation-1.63e+00

Pos logit contributions
orian+1.887
kson+1.808
orb+1.800
rupal+1.748
oulos+1.741
Neg logit contributions
Random-1.283
dump-1.276
nam-1.240
 Sham-1.225
 ASA-1.166
Token paragraph
Token ID7322
Feature activation+1.27e+00

Pos logit contributions
orian+3.247
orb+3.089
kson+3.067
arious+2.966
rupal+2.952
Neg logit contributions
Random-2.618
dump-2.594
nam-2.580
 Sham-2.558
 ASA-2.403
Token that
Token ID326
Feature activation+3.27e-01

Pos logit contributions
orian+0.955
kson+0.905
orb+0.905
rupal+0.875
oulos+0.869
Neg logit contributions
dump-0.796
Random-0.795
 Sham-0.783
nam-0.778
 ASA-0.744
Token said
Token ID531
Feature activation+1.14e+00

Pos logit contributions
orian+0.244
kson+0.232
orb+0.232
rupal+0.224
oulos+0.223
Neg logit contributions
dump-0.209
Random-0.208
 Sham-0.206
nam-0.204
 ASA-0.195
Token God
Token ID1793
Feature activation+2.00e+00

Pos logit contributions
orian+0.889
orb+0.844
kson+0.842
oulos+0.813
rupal+0.812
Neg logit contributions
dump-0.696
Random-0.694
 Sham-0.684
nam-0.676
 ASA-0.644
Token considers
Token ID14358
Feature activation+3.13e+00

Pos logit contributions
orian+1.473
orb+1.395
kson+1.392
rupal+1.348
arious+1.339
Neg logit contributions
Random-1.300
dump-1.300
 Sham-1.275
nam-1.261
 ASA-1.219
Token masturbation
Token ID41054
Feature activation-9.11e+00

Pos logit contributions
orian+2.494
orb+2.375
kson+2.372
rupal+2.291
oulos+2.288
Neg logit contributions
dump-1.836
Random-1.826
 Sham-1.770
nam-1.763
 ASA-1.680
Token to
Token ID284
Feature activation-1.73e+00

Pos logit contributions
 Sham+4.847
Random+4.714
nam+4.707
 unres+4.651
dump+4.588
Neg logit contributions
orian-7.474
kson-7.166
orb-7.056
agascar-6.906
rupal-6.882
Token be
Token ID307
Feature activation-1.01e+00

Pos logit contributions
dump+0.996
Random+0.992
 Sham+0.979
nam+0.965
 ASA+0.922
Neg logit contributions
orian-1.403
orb-1.339
kson-1.333
rupal-1.298
oulos-1.293
Token a
Token ID257
Feature activation-1.63e+00

Pos logit contributions
dump+0.564
Random+0.562
 Sham+0.556
nam+0.549
 ASA+0.522
Neg logit contributions
orian-0.829
orb-0.792
kson-0.791
rupal-0.768
oulos-0.766
Token "
Token ID366
Feature activation-2.07e+00

Pos logit contributions
dump+0.855
Random+0.853
 Sham+0.851
nam+0.835
 ASA+0.790
Neg logit contributions
orian-1.399
kson-1.340
orb-1.340
rupal-1.302
oulos-1.297
Tokenhom
Token ID26452
Feature activation-7.01e-01

Pos logit contributions
dump+1.318
Random+1.312
 Sham+1.294
nam+1.291
 ASA+1.217
Neg logit contributions
orian-1.552
kson-1.485
orb-1.469
rupal-1.429
oulos-1.427
Tokenver
Token ID332
Feature activation-1.71e+00

Pos logit contributions
dump+1.295
Random+1.290
nam+1.267
 Sham+1.266
 ASA+1.193
Neg logit contributions
orian-1.716
kson-1.642
orb-1.623
rupal-1.595
oulos-1.589
Tokentex
Token ID16886
Feature activation-2.61e+00

Pos logit contributions
dump+1.181
Random+1.178
 Sham+1.169
nam+1.156
 ASA+1.110
Neg logit contributions
orian-1.192
orb-1.129
kson-1.126
rupal-1.088
oulos-1.082
Token.
Token ID13
Feature activation-2.29e+00

Pos logit contributions
dump+1.351
Random+1.350
 Sham+1.325
nam+1.315
 ASA+1.237
Neg logit contributions
orian-2.254
kson-2.162
orb-2.156
rupal-2.106
oulos-2.099
Tokenxy
Token ID5431
Feature activation-3.01e+00

Pos logit contributions
dump+1.395
Random+1.380
nam+1.361
 Sham+1.351
 ASA+1.278
Neg logit contributions
orian-1.786
kson-1.715
orb-1.687
rupal-1.664
oulos-1.658
Tokenz
Token ID89
Feature activation-1.63e+00

Pos logit contributions
dump+1.665
Random+1.655
nam+1.619
 Sham+1.611
 ASA+1.528
Neg logit contributions
orian-2.504
kson-2.405
orb-2.376
oulos-2.343
rupal-2.343
Token +=
Token ID15853
Feature activation-9.05e+00

Pos logit contributions
dump+0.856
Random+0.852
 Sham+0.846
nam+0.833
 ASA+0.788
Neg logit contributions
orian-1.406
orb-1.346
kson-1.341
rupal-1.305
oulos-1.299
Token v
Token ID410
Feature activation-2.86e+00

Pos logit contributions
Random+5.155
nam+5.141
dump+5.086
 Sham+5.028
 ASA+4.887
Neg logit contributions
orian-6.874
kson-6.791
rupal-6.587
arious-6.575
oulos-6.515
Token.
Token ID13
Feature activation-1.83e+00

Pos logit contributions
Random+1.891
dump+1.889
 Sham+1.865
nam+1.850
 ASA+1.769
Neg logit contributions
orian-2.063
kson-1.961
orb-1.953
rupal-1.894
oulos-1.891
Tokennormal
Token ID11265
Feature activation-2.06e+00

Pos logit contributions
dump+1.099
Random+1.093
 Sham+1.075
nam+1.074
 ASA+1.015
Neg logit contributions
orian-1.442
kson-1.378
orb-1.368
rupal-1.336
oulos-1.331
Token *
Token ID1635
Feature activation-4.59e+00

Pos logit contributions
dump+1.153
Random+1.152
 Sham+1.133
nam+1.124
 ASA+1.064
Neg logit contributions
orian-1.700
kson-1.628
orb-1.619
rupal-1.579
oulos-1.575
Token 1
Token ID352
Feature activation-7.55e-01

Pos logit contributions
Random+2.587
dump+2.568
 Sham+2.547
nam+2.546
 ASA+2.432
Neg logit contributions
orian-3.694
kson-3.606
orb-3.490
rupal-3.479
oulos-3.466
Tokenmap
Token ID8899
Feature activation+1.80e-01

Pos logit contributions
orian+1.355
orb+1.220
kson+1.168
rupal+1.129
oulos+1.090
Neg logit contributions
 Sham-3.717
Random-3.705
dump-3.696
nam-3.655
 ASA-3.606
Token $
Token ID720
Feature activation-3.76e+00

Pos logit contributions
orian+0.136
orb+0.130
kson+0.130
rupal+0.125
oulos+0.125
Neg logit contributions
dump-0.112
Random-0.112
 Sham-0.111
nam-0.110
 ASA-0.104
Tokenb
Token ID65
Feature activation-1.97e+00

Pos logit contributions
dump+2.391
Random+2.385
nam+2.316
 Sham+2.314
 ASA+2.190
Neg logit contributions
orian-2.818
kson-2.692
orb-2.626
oulos-2.602
rupal-2.593
Tokenmp
Token ID3149
Feature activation-2.66e+00

Pos logit contributions
dump+1.106
Random+1.095
 Sham+1.077
nam+1.076
 ASA+1.009
Neg logit contributions
orian-1.632
kson-1.561
orb-1.555
rupal-1.513
oulos-1.509
Token =
Token ID796
Feature activation-8.52e+00

Pos logit contributions
dump+1.573
Random+1.569
 Sham+1.543
nam+1.533
 ASA+1.457
Neg logit contributions
orian-2.113
kson-2.019
orb-2.010
rupal-1.955
oulos-1.951
Token new
Token ID649
Feature activation-9.04e+00

Pos logit contributions
dump+4.160
Random+4.111
 Sham+4.032
nam+3.880
 Ut+3.699
Neg logit contributions
orian-7.511
kson-7.183
orb-7.126
oulos-7.112
arious-7.077
Token-
Token ID12
Feature activation-3.27e+00

Pos logit contributions
Random+3.901
 Sham+3.825
dump+3.812
nam+3.569
 Ut+3.404
Neg logit contributions
 helicop-8.406
orian-8.214
kson-7.973
oulos-7.970
agascar-7.938
Tokenobject
Token ID15252
Feature activation-3.56e+00

Pos logit contributions
dump+1.573
Random+1.566
nam+1.506
 Sham+1.462
 ASA+1.349
Neg logit contributions
orian-2.966
kson-2.877
 helicop-2.846
agascar-2.814
oulos-2.803
Token system
Token ID1080
Feature activation-1.76e+00

Pos logit contributions
dump+2.220
Random+2.208
 Sham+2.196
nam+2.154
 ASA+2.052
Neg logit contributions
orian-2.683
kson-2.583
orb-2.544
oulos-2.489
arious-2.480
Token.
Token ID13
Feature activation-2.71e+00

Pos logit contributions
Random+1.106
dump+1.095
nam+1.078
 Sham+1.077
 ASA+1.003
Neg logit contributions
orian-1.339
 helicop-1.294
kson-1.278
orb-1.273
oulos-1.263
Tokendraw
Token ID19334
Feature activation-2.69e+00

Pos logit contributions
dump+1.279
Random+1.273
 Sham+1.251
nam+1.237
 ASA+1.157
Neg logit contributions
orian-2.476
kson-2.378
orb-2.372
rupal-2.313
oulos-2.308
Tokenil
Token ID346
Feature activation-2.90e+00

Pos logit contributions
dump+0.740
Random+0.734
 Sham+0.729
nam+0.725
 ASA+0.689
Neg logit contributions
orian-0.720
kson-0.680
orb-0.677
rupal-0.657
oulos-0.654
Tokenine
Token ID500
Feature activation-4.88e-01

Pos logit contributions
dump+1.390
 Sham+1.384
Random+1.372
nam+1.372
 ASA+1.263
Neg logit contributions
orian-2.568
kson-2.502
orb-2.458
oulos-2.415
natureconservancy-2.404
Token $
Token ID720
Feature activation-4.07e+00

Pos logit contributions
dump+0.288
Random+0.287
 Sham+0.285
nam+0.281
 ASA+0.268
Neg logit contributions
orian-0.388
orb-0.370
kson-0.369
rupal-0.359
oulos-0.357
Tokenart
Token ID433
Feature activation-2.54e+00

Pos logit contributions
dump+2.471
Random+2.449
nam+2.395
 Sham+2.377
 ASA+2.218
Neg logit contributions
orian-3.166
kson-3.029
orb-2.967
oulos-2.936
rupal-2.932
Tokenext
Token ID2302
Feature activation-3.78e-01

Pos logit contributions
dump+1.442
Random+1.429
nam+1.403
 Sham+1.402
 ASA+1.314
Neg logit contributions
orian-2.068
kson-1.991
orb-1.976
rupal-1.927
oulos-1.924
Token =
Token ID796
Feature activation-8.92e+00

Pos logit contributions
dump+0.204
 Sham+0.204
Random+0.204
nam+0.199
 ASA+0.191
Neg logit contributions
orian-0.319
orb-0.306
kson-0.303
rupal-0.295
oulos-0.294
Token ($
Token ID7198
Feature activation-4.24e+00

Pos logit contributions
dump+4.641
Random+4.522
 Sham+4.522
nam+4.310
 Ut+4.196
Neg logit contributions
orian-7.529
kson-7.170
orb-7.147
arious-7.086
oulos-7.069
Tokentext
Token ID5239
Feature activation+9.01e-01

Pos logit contributions
Random+2.483
dump+2.456
 Sham+2.399
nam+2.390
 ASA+2.233
Neg logit contributions
orian-3.391
kson-3.254
orb-3.194
oulos-3.166
rupal-3.153
Token -
Token ID532
Feature activation-3.87e+00

Pos logit contributions
orian+0.728
orb+0.696
kson+0.688
rupal+0.668
arious+0.663
Neg logit contributions
 Sham-0.516
dump-0.514
Random-0.513
nam-0.505
 ASA-0.487
Tokensplit
Token ID35312
Feature activation-4.64e+00

Pos logit contributions
dump+2.215
Random+2.212
nam+2.165
 Sham+2.160
 ASA+2.017
Neg logit contributions
orian-3.152
kson-3.020
orb-2.986
rupal-2.931
oulos-2.922
Token "\
Token ID37082
Feature activation-3.39e+00

Pos logit contributions
Random+2.543
dump+2.539
 Sham+2.507
nam+2.487
 ASA+2.319
Neg logit contributions
orian-3.864
kson-3.692
orb-3.659
rupal-3.602
oulos-3.593
Tokentext
Token ID5239
Feature activation-2.68e+00

Pos logit contributions
dump+3.250
Random+3.226
nam+3.190
 Sham+3.106
 ASA+2.941
Neg logit contributions
orian-3.732
kson-3.592
oulos-3.526
orb-3.517
rupal-3.438
Token]
Token ID60
Feature activation-4.43e+00

Pos logit contributions
dump+1.572
Random+1.557
nam+1.529
 Sham+1.529
 ASA+1.442
Neg logit contributions
orian-2.141
kson-2.057
orb-2.042
oulos-2.002
rupal-1.994
Token{
Token ID90
Feature activation-1.50e+00

Pos logit contributions
dump+2.752
Random+2.750
nam+2.685
 Sham+2.664
 ASA+2.506
Neg logit contributions
orian-3.355
kson-3.201
orb-3.199
oulos-3.151
arious-3.081
Tokenwhite
Token ID11186
Feature activation-3.72e+00

Pos logit contributions
dump+0.943
Random+0.941
 Sham+0.924
nam+0.922
 ASA+0.873
Neg logit contributions
orian-1.130
kson-1.077
orb-1.072
oulos-1.042
rupal-1.041
Token}{
Token ID18477
Feature activation-1.34e+00

Pos logit contributions
dump+2.285
Random+2.284
 Sham+2.258
nam+2.247
 ASA+2.107
Neg logit contributions
orian-2.830
kson-2.733
orb-2.665
oulos-2.652
rupal-2.643
Tokenvi
Token ID8903
Feature activation-8.91e+00

Pos logit contributions
dump+0.889
Random+0.888
 Sham+0.874
nam+0.871
 ASA+0.827
Neg logit contributions
orian-0.962
kson-0.916
orb-0.908
rupal-0.885
oulos-0.884
Token:
Token ID25
Feature activation-2.44e+00

Pos logit contributions
Random+5.433
dump+5.407
nam+5.320
 Sham+5.316
 ASA+4.921
Neg logit contributions
orian-6.423
oulos-6.167
kson-6.112
rupal-6.060
orb-6.013
Token|
Token ID91
Feature activation-3.93e+00

Pos logit contributions
dump+1.618
Random+1.614
nam+1.586
 Sham+1.584
 ASA+1.503
Neg logit contributions
orian-1.757
kson-1.666
orb-1.658
oulos-1.613
rupal-1.609
Tokenvim
Token ID31124
Feature activation-7.19e+00

Pos logit contributions
dump+2.507
Random+2.477
nam+2.443
 Sham+2.406
 ASA+2.285
Neg logit contributions
orian-2.941
kson-2.792
orb-2.771
oulos-2.744
rupal-2.692
Token:
Token ID25
Feature activation-2.81e+00

Pos logit contributions
dump+4.720
Random+4.546
nam+4.541
 Sham+4.459
 ASA+4.205
Neg logit contributions
orian-5.140
oulos-4.920
kson-4.898
orb-4.841
rupal-4.749
Token|
Token ID91
Feature activation-3.30e+00

Pos logit contributions
dump+1.810
Random+1.798
nam+1.766
 Sham+1.758
 ASA+1.667
Neg logit contributions
orian-2.079
kson-1.975
orb-1.965
oulos-1.926
rupal-1.907
Token of
Token ID286
Feature activation-1.32e+00

Pos logit contributions
 Sham+2.735
dump+2.695
Random+2.688
nam+2.683
 unres+2.569
Neg logit contributions
orian-3.463
kson-3.341
orb-3.336
oulos-3.222
rupal-3.195
Token Muhammad
Token ID15870
Feature activation+3.66e+00

Pos logit contributions
dump+0.759
Random+0.756
 Sham+0.746
nam+0.739
 ASA+0.703
Neg logit contributions
orian-1.074
orb-1.025
kson-1.023
rupal-0.994
oulos-0.990
Token with
Token ID351
Feature activation-3.46e+00

Pos logit contributions
orian+2.676
orb+2.527
kson+2.511
rupal+2.438
oulos+2.437
Neg logit contributions
Random-2.387
dump-2.379
nam-2.304
 Sham-2.303
 ASA-2.233
Token his
Token ID465
Feature activation-5.29e-01

Pos logit contributions
 Sham+1.952
dump+1.921
Random+1.915
nam+1.897
 ASA+1.803
Neg logit contributions
orian-2.845
orb-2.723
kson-2.711
rupal-2.638
oulos-2.631
Token hands
Token ID2832
Feature activation-4.98e+00

Pos logit contributions
dump+0.311
Random+0.311
 Sham+0.304
nam+0.302
 ASA+0.288
Neg logit contributions
orian-0.422
kson-0.402
orb-0.402
rupal-0.388
oulos-0.387
Token tied
Token ID8165
Feature activation-8.88e+00

Pos logit contributions
 Sham+2.549
dump+2.546
nam+2.513
Random+2.488
 unres+2.383
Neg logit contributions
orian-4.295
kson-4.126
orb-4.069
oulos-4.033
rupal-3.995
Token to
Token ID284
Feature activation-3.69e+00

Pos logit contributions
 Sham+4.414
nam+4.357
Random+4.242
dump+4.201
 unres+4.143
Neg logit contributions
orian-7.393
kson-7.235
oulos-7.173
rupal-7.142
orb-7.094
Token his
Token ID465
Feature activation-3.65e-01

Pos logit contributions
 Sham+1.958
dump+1.954
Random+1.934
nam+1.926
 ASA+1.816
Neg logit contributions
orian-3.116
orb-2.992
kson-2.987
oulos-2.914
rupal-2.911
Token neck
Token ID7393
Feature activation-1.94e+00

Pos logit contributions
dump+0.251
Random+0.251
 Sham+0.247
nam+0.245
 ASA+0.236
Neg logit contributions
orian-0.254
orb-0.240
kson-0.240
rupal-0.231
oulos-0.229
Token with
Token ID351
Feature activation-5.45e+00

Pos logit contributions
dump+1.218
Random+1.211
 Sham+1.209
nam+1.199
 ASA+1.138
Neg logit contributions
orian-1.455
orb-1.385
kson-1.382
rupal-1.341
oulos-1.339
Token a
Token ID257
Feature activation-3.70e+00

Pos logit contributions
 Sham+3.055
nam+2.971
dump+2.963
Random+2.939
 ASA+2.808
Neg logit contributions
orian-4.467
orb-4.300
kson-4.281
oulos-4.183
rupal-4.161
Token the
Token ID262
Feature activation-2.16e+00

Pos logit contributions
dump+0.114
Random+0.114
 Sham+0.113
nam+0.111
 ASA+0.106
Neg logit contributions
orian-0.152
orb-0.145
kson-0.145
rupal-0.140
oulos-0.140
Token point
Token ID966
Feature activation-3.57e+00

Pos logit contributions
dump+1.454
 Sham+1.445
Random+1.443
nam+1.419
 ASA+1.374
Neg logit contributions
orian-1.539
orb-1.459
kson-1.449
oulos-1.414
rupal-1.413
Token where
Token ID810
Feature activation-7.10e-02

Pos logit contributions
dump+2.227
Random+2.216
 Sham+2.212
nam+2.173
 ASA+2.071
Neg logit contributions
orian-2.688
orb-2.570
kson-2.560
rupal-2.499
oulos-2.497
Token I
Token ID314
Feature activation-2.01e+00

Pos logit contributions
dump+0.042
Random+0.042
 Sham+0.041
nam+0.041
 ASA+0.039
Neg logit contributions
orian-0.057
orb-0.054
kson-0.054
rupal-0.052
oulos-0.052
Token tried
Token ID3088
Feature activation+3.98e-01

Pos logit contributions
dump+1.272
 Sham+1.250
Random+1.245
nam+1.237
 ASA+1.167
Neg logit contributions
orian-1.522
kson-1.444
orb-1.434
rupal-1.408
arious-1.398
Token masturb
Token ID22938
Feature activation-8.85e+00

Pos logit contributions
orian+0.279
orb+0.265
kson+0.264
rupal+0.255
oulos+0.254
Neg logit contributions
dump-0.271
Random-0.271
 Sham-0.269
nam-0.266
 ASA-0.255
Tokenating
Token ID803
Feature activation-2.84e+00

Pos logit contributions
dump+3.482
nam+3.439
Random+3.433
 Sham+3.311
 ASA+2.985
Neg logit contributions
orian-8.324
kson-8.214
orb-8.048
oulos-7.931
rupal-7.909
Token as
Token ID355
Feature activation-1.32e+00

Pos logit contributions
dump+1.824
Random+1.820
 Sham+1.809
nam+1.779
 unres+1.693
Neg logit contributions
orian-2.103
kson-2.013
orb-1.995
oulos-1.950
rupal-1.945
Token Bruce
Token ID11088
Feature activation-1.07e-01

Pos logit contributions
dump+0.767
Random+0.766
 Sham+0.760
nam+0.748
 ASA+0.712
Neg logit contributions
orian-1.059
orb-1.011
kson-1.010
rupal-0.984
oulos-0.978
Token C
Token ID327
Feature activation-2.53e+00

Pos logit contributions
dump+0.070
Random+0.070
 Sham+0.070
nam+0.069
 ASA+0.065
Neg logit contributions
orian-0.078
orb-0.075
kson-0.074
rupal-0.072
oulos-0.072
Tokenodd
Token ID5088
Feature activation+9.90e-01

Pos logit contributions
dump+1.524
Random+1.509
nam+1.500
 Sham+1.464
Jew+1.349
Neg logit contributions
orian-1.968
 helicop-1.907
orb-1.884
kson-1.881
arious-1.837
Token the
Token ID262
Feature activation+8.47e-01

Pos logit contributions
orian+1.940
orb+1.847
kson+1.845
rupal+1.783
oulos+1.773
Neg logit contributions
Random-1.478
dump-1.474
 Sham-1.444
nam-1.437
 ASA-1.373
Token contact
Token ID2800
Feature activation-2.03e-01

Pos logit contributions
orian+0.620
orb+0.589
kson+0.588
rupal+0.569
oulos+0.567
Neg logit contributions
dump-0.553
Random-0.552
 Sham-0.548
nam-0.542
 ASA-0.519
Token of
Token ID286
Feature activation+1.20e+00

Pos logit contributions
dump+0.133
Random+0.133
 Sham+0.131
nam+0.130
 ASA+0.125
Neg logit contributions
orian-0.148
orb-0.140
kson-0.140
rupal-0.135
oulos-0.135
Token her
Token ID607
Feature activation-6.23e-01

Pos logit contributions
orian+0.961
orb+0.914
kson+0.912
rupal+0.881
oulos+0.880
Neg logit contributions
dump-0.705
Random-0.702
 Sham-0.685
nam-0.683
 ASA-0.648
Token lips
Token ID11914
Feature activation-6.07e+00

Pos logit contributions
dump+0.406
Random+0.405
 Sham+0.402
nam+0.398
 ASA+0.380
Neg logit contributions
orian-0.456
orb-0.433
kson-0.433
rupal-0.419
oulos-0.417
Token against
Token ID1028
Feature activation-8.83e+00

Pos logit contributions
nam+3.935
dump+3.912
 Sham+3.901
Random+3.868
 unres+3.714
Neg logit contributions
orian-4.348
kson-4.188
rupal-4.087
oulos-4.036
orb-4.035
Token mine
Token ID6164
Feature activation-5.13e+00

Pos logit contributions
 Sham+5.242
Random+5.104
nam+5.102
dump+5.079
 ASA+4.887
Neg logit contributions
orian-6.554
orb-6.362
kson-6.355
oulos-6.225
agascar-6.192
Token.
Token ID13
Feature activation-2.27e+00

Pos logit contributions
dump+3.069
Random+3.042
 Sham+3.041
nam+3.027
 unres+2.878
Neg logit contributions
orian-3.974
kson-3.766
orb-3.754
oulos-3.681
rupal-3.671
Token
Token ID198
Feature activation-6.40e-01

Pos logit contributions
 Sham+1.321
Random+1.314
dump+1.309
nam+1.278
 ASA+1.231
Neg logit contributions
orian-1.829
orb-1.751
kson-1.733
rupal-1.700
oulos-1.688
Token
Token ID198
Feature activation-4.30e-01

Pos logit contributions
Random+0.415
dump+0.412
 Sham+0.411
nam+0.407
 ASA+0.384
Neg logit contributions
orian-0.476
orb-0.452
kson-0.451
 helicop-0.449
oulos-0.440
Token"
Token ID1
Feature activation-1.13e+00

Pos logit contributions
dump+0.220
 Sham+0.218
Random+0.217
nam+0.214
 ASA+0.205
Neg logit contributions
orian-0.375
orb-0.359
kson-0.357
rupal-0.347
arious-0.345
Token T
Token ID309
Feature activation-1.99e+00

Pos logit contributions
orian+0.551
orb+0.522
kson+0.522
rupal+0.503
oulos+0.502
Neg logit contributions
dump-0.553
Random-0.550
 Sham-0.546
nam-0.542
 ASA-0.520
Token >
Token ID1875
Feature activation-4.45e-01

Pos logit contributions
dump+1.123
Random+1.119
 Sham+1.109
nam+1.093
 ASA+1.041
Neg logit contributions
orian-1.635
orb-1.563
kson-1.561
rupal-1.514
oulos-1.508
Token {
Token ID1391
Feature activation-3.29e-01

Pos logit contributions
dump+0.257
Random+0.256
 Sham+0.252
nam+0.249
 ASA+0.238
Neg logit contributions
orian-0.362
kson-0.345
orb-0.345
rupal-0.334
oulos-0.334
Token pub
Token ID2240
Feature activation-2.15e+00

Pos logit contributions
dump+0.206
Random+0.205
 Sham+0.203
nam+0.201
 ASA+0.192
Neg logit contributions
orian-0.250
orb-0.237
kson-0.237
rupal-0.230
oulos-0.228
Token fn
Token ID24714
Feature activation-5.50e+00

Pos logit contributions
dump+0.921
Random+0.917
 Sham+0.905
nam+0.890
 ASA+0.831
Neg logit contributions
orian-2.063
orb-1.984
kson-1.981
rupal-1.933
oulos-1.927
Token load
Token ID3440
Feature activation-8.83e+00

Pos logit contributions
dump+3.010
Random+2.936
nam+2.876
 Sham+2.849
 unres+2.762
Neg logit contributions
orian-4.603
kson-4.428
orb-4.359
oulos-4.333
rupal-4.303
Token <
Token ID1279
Feature activation-2.43e+00

Pos logit contributions
Random+5.051
dump+4.862
nam+4.716
 Sham+4.607
 ASA+4.361
Neg logit contributions
orian-7.156
kson-6.866
orb-6.780
rupal-6.728
oulos-6.680
Token '
Token ID705
Feature activation-2.57e+00

Pos logit contributions
Random+1.444
 Sham+1.436
dump+1.436
nam+1.397
 ASA+1.342
Neg logit contributions
orian-1.936
orb-1.842
kson-1.814
rupal-1.798
arious-1.787
Tokena
Token ID64
Feature activation-2.17e+00

Pos logit contributions
dump+1.563
Random+1.560
 Sham+1.536
nam+1.520
 ASA+1.441
Neg logit contributions
orian-2.007
kson-1.906
orb-1.903
rupal-1.854
oulos-1.842
Token >
Token ID1875
Feature activation-8.55e-01

Pos logit contributions
dump+1.329
Random+1.326
 Sham+1.314
nam+1.298
 ASA+1.239
Neg logit contributions
orian-1.674
orb-1.593
kson-1.591
rupal-1.543
oulos-1.536
Token (
Token ID357
Feature activation-4.15e+00

Pos logit contributions
dump+0.562
Random+0.560
 Sham+0.557
nam+0.550
 ASA+0.528
Neg logit contributions
orian-0.620
orb-0.590
kson-0.588
rupal-0.569
oulos-0.566
Token How
Token ID1374
Feature activation+2.16e+00

Pos logit contributions
orian+3.557
orb+3.333
kson+3.319
oulos+3.278
tale+3.193
Neg logit contributions
dump-4.050
Random-3.945
nam-3.936
 Sham-3.875
 unres-3.764
TokenSt
Token ID1273
Feature activation+3.13e+00

Pos logit contributions
orian+2.104
orb+2.025
kson+2.023
rupal+1.974
oulos+1.965
Neg logit contributions
dump-0.892
Random-0.885
 Sham-0.876
nam-0.860
 ASA-0.803
Tokenuff
Token ID1648
Feature activation-1.34e+00

Pos logit contributions
orian+1.922
orb+1.813
kson+1.794
rupal+1.733
oulos+1.704
Neg logit contributions
dump-2.397
 Sham-2.394
Random-2.387
nam-2.349
 ASA-2.319
TokenWorks
Token ID23044
Feature activation+2.26e+00

Pos logit contributions
Random+0.605
dump+0.595
nam+0.576
 Sham+0.570
 ASA+0.520
Neg logit contributions
orian-1.263
orb-1.214
kson-1.202
 helicop-1.191
oulos-1.186
Token.
Token ID13
Feature activation+3.43e+00

Pos logit contributions
orian+1.577
orb+1.495
kson+1.492
rupal+1.441
oulos+1.433
Neg logit contributions
dump-1.546
Random-1.540
 Sham-1.529
nam-1.512
 ASA-1.452
Tokencom
Token ID785
Feature activation+5.92e+00

Pos logit contributions
orian+2.542
orb+2.418
kson+2.409
rupal+2.332
oulos+2.319
Neg logit contributions
dump-2.203
Random-2.198
 Sham-2.182
nam-2.145
 ASA-2.067
Token
Token ID198
Feature activation+3.36e+00

Pos logit contributions
orian+3.826
orb+3.602
kson+3.551
oulos+3.461
rupal+3.413
Neg logit contributions
dump-4.264
Random-4.244
 Sham-4.227
nam-4.189
 ASA-3.994
Token
Token ID198
Feature activation+1.67e+00

Pos logit contributions
orian+2.233
orb+2.115
kson+2.108
rupal+2.029
tale+2.006
Neg logit contributions
dump-2.400
Random-2.386
 Sham-2.367
nam-2.338
 ASA-2.268
TokenThe
Token ID464
Feature activation+1.70e-01

Pos logit contributions
orian+1.403
orb+1.350
kson+1.330
rupal+1.290
oulos+1.283
Neg logit contributions
 Sham-0.910
dump-0.908
Random-0.888
nam-0.882
 ASA-0.856
Token next
Token ID1306
Feature activation-7.31e-01

Pos logit contributions
orian+0.130
orb+0.124
kson+0.124
rupal+0.120
oulos+0.120
Neg logit contributions
dump-0.105
Random-0.105
 Sham-0.104
nam-0.102
 ASA-0.098
Token breakthrough
Token ID19304
Feature activation-8.08e-01

Pos logit contributions
dump+0.472
Random+0.471
 Sham+0.469
nam+0.462
 ASA+0.446
Neg logit contributions
orian-0.537
kson-0.513
orb-0.510
rupal-0.496
oulos-0.494
Token be
Token ID307
Feature activation+1.38e+00

Pos logit contributions
orian+1.121
orb+1.071
kson+1.069
rupal+1.037
oulos+1.035
Neg logit contributions
Random-0.810
dump-0.809
 Sham-0.799
nam-0.788
 ASA-0.752
Token locked
Token ID8970
Feature activation-3.80e-01

Pos logit contributions
orian+1.050
orb+0.999
kson+0.997
rupal+0.967
oulos+0.963
Neg logit contributions
dump-0.861
Random-0.859
 Sham-0.852
nam-0.843
 ASA-0.804
Token up
Token ID510
Feature activation-3.00e+00

Pos logit contributions
dump+0.180
Random+0.179
 Sham+0.177
nam+0.174
 ASA+0.164
Neg logit contributions
orian-0.347
orb-0.333
kson-0.332
rupal-0.324
oulos-0.323
Token?
Token ID30
Feature activation+4.29e-01

Pos logit contributions
dump+1.831
Random+1.826
 Sham+1.822
nam+1.807
 unres+1.707
Neg logit contributions
orian-2.290
kson-2.187
orb-2.185
rupal-2.127
arious-2.111
Token It
Token ID632
Feature activation-8.73e-01

Pos logit contributions
orian+0.330
orb+0.315
kson+0.313
rupal+0.304
oulos+0.303
Neg logit contributions
Random-0.264
dump-0.264
 Sham-0.263
nam-0.258
 ASA-0.247
Token depends
Token ID8338
Feature activation+6.10e+00

Pos logit contributions
dump+0.535
Random+0.532
 Sham+0.531
nam+0.524
 ASA+0.496
Neg logit contributions
orian-0.673
orb-0.643
kson-0.640
rupal-0.622
oulos-0.620
Token on
Token ID319
Feature activation+2.43e+00

Pos logit contributions
orian+3.656
kson+3.419
orb+3.395
tale+3.302
oulos+3.264
Neg logit contributions
dump-4.611
Random-4.590
 Sham-4.525
nam-4.479
 ASA-4.382
Token how
Token ID703
Feature activation+3.15e-01

Pos logit contributions
orian+1.832
kson+1.737
orb+1.734
oulos+1.677
rupal+1.674
Neg logit contributions
dump-1.532
Random-1.527
 Sham-1.500
nam-1.492
 ASA-1.424
Token you
Token ID345
Feature activation+8.10e-01

Pos logit contributions
orian+0.246
orb+0.234
kson+0.233
rupal+0.227
oulos+0.226
Neg logit contributions
dump-0.191
Random-0.191
 Sham-0.189
nam-0.186
 ASA-0.178
Token define
Token ID8160
Feature activation-2.42e+00

Pos logit contributions
orian+0.613
orb+0.583
kson+0.582
rupal+0.564
oulos+0.562
Neg logit contributions
dump-0.510
Random-0.507
 Sham-0.503
nam-0.498
 ASA-0.475
Token a
Token ID257
Feature activation-2.23e-01

Pos logit contributions
Random+1.357
dump+1.354
 Sham+1.353
nam+1.324
 ASA+1.254
Neg logit contributions
orian-1.983
orb-1.896
kson-1.895
rupal-1.843
oulos-1.833
TokenSome
Token ID4366
Feature activation+1.53e+00

Pos logit contributions
dump+0.056
Random+0.056
 Sham+0.055
nam+0.054
 ASA+0.052
Neg logit contributions
orian-0.087
orb-0.083
kson-0.083
rupal-0.081
oulos-0.080
Token kind
Token ID1611
Feature activation+1.11e+00

Pos logit contributions
orian+1.152
orb+1.092
kson+1.091
rupal+1.057
oulos+1.053
Neg logit contributions
dump-0.971
Random-0.967
 Sham-0.958
nam-0.949
 ASA-0.905
Token of
Token ID286
Feature activation-7.79e-01

Pos logit contributions
orian+0.785
orb+0.742
kson+0.739
rupal+0.713
arious+0.709
Neg logit contributions
dump-0.755
Random-0.752
 Sham-0.746
nam-0.736
 ASA-0.707
Token bailout
Token ID29928
Feature activation+2.87e-01

Pos logit contributions
dump+0.492
Random+0.490
 Sham+0.488
nam+0.482
 ASA+0.461
Neg logit contributions
orian-0.587
orb-0.559
kson-0.558
rupal-0.540
oulos-0.537
Token,
Token ID11
Feature activation-5.73e-02

Pos logit contributions
orian+0.215
orb+0.204
kson+0.204
rupal+0.197
oulos+0.197
Neg logit contributions
dump-0.182
Random-0.182
 Sham-0.180
nam-0.178
 ASA-0.170
Token whether
Token ID1771
Feature activation+5.64e+00

Pos logit contributions
dump+0.035
Random+0.035
 Sham+0.035
nam+0.034
 ASA+0.033
Neg logit contributions
orian-0.044
orb-0.042
kson-0.042
rupal-0.041
oulos-0.041
Token granted
Token ID7520
Feature activation+2.45e+00

Pos logit contributions
orian+4.092
orb+3.895
kson+3.806
arious+3.724
rupal+3.718
Neg logit contributions
dump-3.626
Random-3.574
nam-3.502
 Sham-3.483
 ASA-3.325
Token with
Token ID351
Feature activation-1.38e+00

Pos logit contributions
orian+1.757
orb+1.668
kson+1.654
rupal+1.605
oulos+1.595
Neg logit contributions
dump-1.636
Random-1.629
 Sham-1.612
nam-1.598
 ASA-1.534
Token soft
Token ID2705
Feature activation+1.95e+00

Pos logit contributions
dump+0.797
Random+0.793
 Sham+0.791
nam+0.778
 ASA+0.742
Neg logit contributions
orian-1.109
orb-1.060
kson-1.059
rupal-1.027
oulos-1.022
Token or
Token ID393
Feature activation-2.35e+00

Pos logit contributions
orian+1.507
orb+1.438
kson+1.424
arious+1.378
rupal+1.377
Neg logit contributions
dump-1.199
Random-1.195
 Sham-1.182
nam-1.159
 ASA-1.115
Token tough
Token ID5802
Feature activation+8.95e-01

Pos logit contributions
nam+1.457
Random+1.441
dump+1.440
 Sham+1.439
 ASA+1.362
Neg logit contributions
orian-1.799
orb-1.722
kson-1.718
oulos-1.660
rupal-1.655
Token's
Token ID338
Feature activation+1.38e-01

Pos logit contributions
dump+0.553
Random+0.547
 Sham+0.546
nam+0.540
 ASA+0.513
Neg logit contributions
orian-0.688
orb-0.653
kson-0.652
rupal-0.635
oulos-0.633
Token our
Token ID674
Feature activation-4.33e-01

Pos logit contributions
orian+0.111
orb+0.106
kson+0.105
rupal+0.102
oulos+0.102
Neg logit contributions
dump-0.080
Random-0.080
 Sham-0.079
nam-0.078
 ASA-0.074
Token version
Token ID2196
Feature activation+1.16e+00

Pos logit contributions
dump+0.248
Random+0.247
 Sham+0.245
nam+0.242
 ASA+0.230
Neg logit contributions
orian-0.352
orb-0.336
kson-0.335
rupal-0.326
oulos-0.325
Token of
Token ID286
Feature activation+1.87e+00

Pos logit contributions
orian+0.791
orb+0.749
kson+0.742
rupal+0.714
oulos+0.708
Neg logit contributions
dump-0.819
Random-0.815
 Sham-0.799
nam-0.798
 ASA-0.766
Token a
Token ID257
Feature activation+1.39e+00

Pos logit contributions
orian+1.461
orb+1.406
kson+1.400
rupal+1.351
oulos+1.344
Neg logit contributions
dump-1.110
Random-1.110
nam-1.088
 Sham-1.087
 ASA-1.025
Token Martian
Token ID32508
Feature activation+5.69e+00

Pos logit contributions
orian+1.087
orb+1.040
kson+1.039
rupal+1.003
oulos+0.999
Neg logit contributions
dump-0.834
Random-0.832
 Sham-0.820
nam-0.815
 ASA-0.775
Token car
Token ID1097
Feature activation-6.57e-01

Pos logit contributions
orian+4.258
orb+4.095
kson+4.090
tale+3.887
rupal+3.880
Neg logit contributions
Random-3.449
dump-3.415
nam-3.398
 Sham-3.343
 ASA-3.218
Tokenwash
Token ID34670
Feature activation-2.18e+00

Pos logit contributions
dump+0.454
Random+0.450
 Sham+0.447
nam+0.443
 ASA+0.426
Neg logit contributions
orian-0.456
kson-0.434
orb-0.430
oulos-0.419
rupal-0.419
Token,"
Token ID553
Feature activation+2.70e+00

Pos logit contributions
dump+1.290
 Sham+1.287
Random+1.275
nam+1.252
 ASA+1.203
Neg logit contributions
orian-1.726
orb-1.632
kson-1.631
oulos-1.601
rupal-1.595
Token said
Token ID531
Feature activation-2.39e+00

Pos logit contributions
orian+1.815
orb+1.738
kson+1.732
rupal+1.657
oulos+1.652
Neg logit contributions
dump-1.912
Random-1.901
nam-1.863
 Sham-1.856
 ASA-1.771
Token Chris
Token ID5180
Feature activation+2.31e+00

Pos logit contributions
 Sham+1.504
dump+1.488
Random+1.484
nam+1.459
 ASA+1.421
Neg logit contributions
orian-1.813
orb-1.710
kson-1.703
rupal-1.671
oulos-1.662
Token which
Token ID543
Feature activation-1.85e+00

Pos logit contributions
dump+0.054
Random+0.054
 Sham+0.053
nam+0.053
 ASA+0.050
Neg logit contributions
orian-0.067
orb-0.063
kson-0.063
rupal-0.061
oulos-0.061
Token were
Token ID547
Feature activation+2.83e-01

Pos logit contributions
dump+1.188
Random+1.184
 Sham+1.179
nam+1.164
 ASA+1.117
Neg logit contributions
orian-1.367
kson-1.294
orb-1.293
rupal-1.259
oulos-1.251
Token considered
Token ID3177
Feature activation+5.24e-01

Pos logit contributions
orian+0.223
orb+0.213
kson+0.213
rupal+0.206
oulos+0.205
Neg logit contributions
dump-0.169
Random-0.169
 Sham-0.167
nam-0.165
 ASA-0.157
Token likely
Token ID1884
Feature activation-8.71e-01

Pos logit contributions
orian+0.391
orb+0.374
kson+0.371
rupal+0.359
oulos+0.356
Neg logit contributions
dump-0.335
Random-0.335
 Sham-0.330
nam-0.326
 ASA-0.312
Token Apollo
Token ID17508
Feature activation+3.68e+00

Pos logit contributions
dump+0.609
Random+0.607
 Sham+0.602
nam+0.596
 ASA+0.573
Neg logit contributions
orian-0.597
orb-0.565
kson-0.564
rupal-0.545
oulos-0.542
Token landing
Token ID9581
Feature activation+6.59e+00

Pos logit contributions
orian+2.664
orb+2.588
kson+2.528
oulos+2.440
rupal+2.434
Neg logit contributions
Random-2.383
dump-2.377
 Sham-2.349
nam-2.315
 ASA-2.237
Token sites
Token ID5043
Feature activation+3.69e+00

Pos logit contributions
orian+4.405
orb+4.338
kson+4.297
rupal+4.041
arious+4.021
Neg logit contributions
Random-4.455
dump-4.396
nam-4.306
 Sham-4.288
 ASA-4.106
Token.
Token ID13
Feature activation+3.13e-02

Pos logit contributions
orian+2.468
orb+2.366
kson+2.336
rupal+2.240
arious+2.220
Neg logit contributions
Random-2.607
dump-2.605
 Sham-2.555
nam-2.532
 ASA-2.449
Token On
Token ID1550
Feature activation+9.45e-01

Pos logit contributions
orian+0.024
orb+0.023
kson+0.023
rupal+0.023
oulos+0.022
Neg logit contributions
dump-0.019
Random-0.019
 Sham-0.019
nam-0.019
 ASA-0.018
Token the
Token ID262
Feature activation-2.75e-01

Pos logit contributions
orian+0.697
orb+0.664
kson+0.662
rupal+0.640
oulos+0.637
Neg logit contributions
dump-0.610
Random-0.609
 Sham-0.603
nam-0.597
 ASA-0.571
Token first
Token ID717
Feature activation+2.45e+00

Pos logit contributions
dump+0.166
Random+0.165
 Sham+0.165
nam+0.162
 ASA+0.155
Neg logit contributions
orian-0.215
kson-0.204
orb-0.204
rupal-0.198
oulos-0.198
Token.
Token ID13
Feature activation-4.99e-01

Pos logit contributions
dump+1.310
Random+1.302
 Sham+1.298
nam+1.282
 ASA+1.223
Neg logit contributions
orian-1.521
kson-1.447
orb-1.443
rupal-1.407
oulos-1.395
Token Exactly
Token ID36819
Feature activation+8.22e-01

Pos logit contributions
 Sham+0.300
Random+0.296
dump+0.294
nam+0.290
 ASA+0.279
Neg logit contributions
orian-0.396
orb-0.377
kson-0.374
rupal-0.368
oulos-0.365
Token 50
Token ID2026
Feature activation-6.24e-01

Pos logit contributions
orian+0.642
orb+0.612
kson+0.611
rupal+0.594
oulos+0.591
Neg logit contributions
dump-0.496
Random-0.494
 Sham-0.490
nam-0.485
 ASA-0.462
Token years
Token ID812
Feature activation-9.51e-01

Pos logit contributions
dump+0.370
Random+0.369
 Sham+0.365
nam+0.361
 ASA+0.344
Neg logit contributions
orian-0.495
orb-0.472
kson-0.471
rupal-0.457
oulos-0.455
Token later
Token ID1568
Feature activation-3.02e-01

Pos logit contributions
dump+0.534
 Sham+0.530
Random+0.530
nam+0.521
 ASA+0.495
Neg logit contributions
orian-0.779
kson-0.746
orb-0.745
rupal-0.727
oulos-0.724
Token
Token ID960
Feature activation+1.15e+00

Pos logit contributions
dump+0.188
Random+0.188
 Sham+0.186
nam+0.184
 ASA+0.176
Neg logit contributions
orian-0.229
orb-0.218
kson-0.218
rupal-0.211
oulos-0.210
TokenDecember
Token ID20588
Feature activation-5.14e-01

Pos logit contributions
orian+0.825
orb+0.783
kson+0.780
rupal+0.753
oulos+0.751
Neg logit contributions
dump-0.764
Random-0.762
 Sham-0.756
nam-0.747
 ASA-0.717
Token 17
Token ID1596
Feature activation-2.16e+00

Pos logit contributions
 Sham+0.342
Random+0.340
dump+0.340
nam+0.335
 ASA+0.322
Neg logit contributions
orian-0.371
orb-0.352
kson-0.351
rupal-0.344
oulos-0.342
Token,
Token ID11
Feature activation+1.03e+00

Pos logit contributions
dump+1.273
Random+1.271
 Sham+1.261
nam+1.253
 ASA+1.187
Neg logit contributions
orian-1.722
kson-1.637
orb-1.635
rupal-1.596
oulos-1.583
Token 1995
Token ID8735
Feature activation+3.24e-01

Pos logit contributions
orian+0.629
orb+0.592
kson+0.590
rupal+0.569
oulos+0.564
Neg logit contributions
dump-0.792
Random-0.790
 Sham-0.785
nam-0.778
 ASA-0.750
Token
Token ID960
Feature activation-6.97e-01

Pos logit contributions
orian+0.243
orb+0.231
kson+0.231
rupal+0.223
oulos+0.222
Neg logit contributions
dump-0.206
Random-0.205
 Sham-0.204
nam-0.201
 ASA-0.193
Token dist
Token ID1233
Feature activation+4.64e+00

Pos logit contributions
dump+0.496
Random+0.494
 Sham+0.489
nam+0.482
 ASA+0.457
Neg logit contributions
orian-0.823
orb-0.788
kson-0.786
rupal-0.766
oulos-0.763
Tokenros
Token ID4951
Feature activation+2.08e+00

Pos logit contributions
orian+3.276
orb+3.134
kson+3.055
rupal+3.019
arious+3.005
Neg logit contributions
dump-3.080
 Sham-3.067
Random-3.058
nam-3.009
 ASA-2.932
Token.
Token ID13
Feature activation+6.17e-01

Pos logit contributions
orian+1.441
orb+1.362
kson+1.361
rupal+1.314
arious+1.300
Neg logit contributions
dump-1.431
Random-1.430
 Sham-1.412
nam-1.400
 ASA-1.350
Token
Token ID198
Feature activation+8.45e-01

Pos logit contributions
orian+0.443
orb+0.420
kson+0.419
rupal+0.406
oulos+0.405
Neg logit contributions
dump-0.412
Random-0.411
 Sham-0.408
nam-0.403
 ASA-0.387
Token
Token ID198
Feature activation+5.75e-01

Pos logit contributions
orian+0.603
orb+0.571
kson+0.570
oulos+0.551
rupal+0.551
Neg logit contributions
dump-0.570
Random-0.569
 Sham-0.565
nam-0.560
 ASA-0.534
TokenIn
Token ID818
Feature activation+2.02e+00

Pos logit contributions
orian+0.470
orb+0.450
kson+0.447
rupal+0.435
oulos+0.432
Neg logit contributions
dump-0.325
 Sham-0.323
Random-0.323
nam-0.317
 ASA-0.304
Token some
Token ID617
Feature activation-1.35e+00

Pos logit contributions
orian+1.548
orb+1.474
kson+1.468
rupal+1.428
arious+1.416
Neg logit contributions
dump-1.237
Random-1.233
 Sham-1.219
nam-1.198
 ASA-1.150
Token ways
Token ID2842
Feature activation-4.93e+00

Pos logit contributions
Random+0.868
dump+0.866
 Sham+0.859
nam+0.850
 ASA+0.814
Neg logit contributions
orian-1.003
orb-0.956
kson-0.953
rupal-0.923
oulos-0.923
Token,
Token ID11
Feature activation+1.35e+00

Pos logit contributions
 Sham+2.801
dump+2.800
Random+2.779
nam+2.742
 ASA+2.613
Neg logit contributions
orian-3.948
orb-3.759
kson-3.747
oulos-3.680
natureconservancy-3.665
Token it
Token ID340
Feature activation+1.17e+00

Pos logit contributions
orian+1.028
orb+0.976
kson+0.976
rupal+0.945
oulos+0.939
Neg logit contributions
dump-0.845
Random-0.844
 Sham-0.832
nam-0.825
 ASA-0.787
Token's
Token ID338
Feature activation+9.65e-01

Pos logit contributions
orian+0.891
kson+0.848
orb+0.844
rupal+0.819
oulos+0.812
Neg logit contributions
Random-0.733
dump-0.733
 Sham-0.721
nam-0.713
 ASA-0.687
Token to
Token ID284
Feature activation+5.19e-01

Pos logit contributions
orian+0.228
kson+0.216
orb+0.216
rupal+0.209
oulos+0.208
Neg logit contributions
dump-0.217
Random-0.216
 Sham-0.215
nam-0.213
 ASA-0.204
Token prevent
Token ID2948
Feature activation+3.29e-01

Pos logit contributions
orian+0.380
orb+0.361
kson+0.360
rupal+0.349
oulos+0.347
Neg logit contributions
dump-0.338
Random-0.338
 Sham-0.334
nam-0.330
 ASA-0.316
Token another
Token ID1194
Feature activation-2.97e-01

Pos logit contributions
orian+0.261
orb+0.248
kson+0.248
rupal+0.241
oulos+0.240
Neg logit contributions
dump-0.196
Random-0.195
 Sham-0.192
nam-0.191
 ASA-0.182
Token Portsmouth
Token ID48823
Feature activation-3.05e+00

Pos logit contributions
dump+0.191
Random+0.191
 Sham+0.190
nam+0.187
 ASA+0.179
Neg logit contributions
orian-0.220
kson-0.209
orb-0.209
rupal-0.202
oulos-0.201
Token,
Token ID11
Feature activation-2.73e+00

Pos logit contributions
dump+1.856
 Sham+1.851
Random+1.848
nam+1.797
 ASA+1.719
Neg logit contributions
orian-2.362
kson-2.281
orb-2.248
rupal-2.192
oulos-2.166
Token but
Token ID475
Feature activation+8.13e-01

Pos logit contributions
 Sham+1.532
Random+1.517
dump+1.501
nam+1.473
 ASA+1.415
Neg logit contributions
orian-2.250
kson-2.163
orb-2.157
rupal-2.103
arious-2.077
Token not
Token ID407
Feature activation+1.54e+00

Pos logit contributions
orian+0.636
orb+0.605
kson+0.604
rupal+0.585
oulos+0.585
Neg logit contributions
dump-0.490
Random-0.489
 Sham-0.482
nam-0.478
 ASA-0.456
Token another
Token ID1194
Feature activation+5.11e-01

Pos logit contributions
orian+1.274
orb+1.213
kson+1.208
oulos+1.177
rupal+1.173
Neg logit contributions
dump-0.863
Random-0.855
nam-0.835
 Sham-0.835
 ASA-0.793
Token Manchester
Token ID9502
Feature activation+6.37e-02

Pos logit contributions
orian+0.415
orb+0.395
kson+0.395
oulos+0.383
rupal+0.383
Neg logit contributions
dump-0.293
Random-0.291
nam-0.285
 Sham-0.285
 ASA-0.270
Token City
Token ID2254
Feature activation-9.18e-01

Pos logit contributions
orian+0.048
orb+0.045
kson+0.045
rupal+0.044
oulos+0.044
Neg logit contributions
dump-0.041
Random-0.041
 Sham-0.040
nam-0.040
 ASA-0.038
Token,
Token ID11
Feature activation+5.54e-01

Pos logit contributions
dump+0.589
Random+0.588
 Sham+0.584
nam+0.575
 ASA+0.550
Neg logit contributions
orian-0.683
kson-0.650
orb-0.650
rupal-0.628
oulos-0.624
TokenAbstract
Token ID23839
Feature activation-2.17e+00

Pos logit contributions
orian+3.280
orb+3.164
kson+3.077
tale+3.024
rupal+3.018
Neg logit contributions
 Sham-2.147
dump-2.098
nam-2.048
Random-2.035
 ASA-2.034
Token
Token ID198
Feature activation-3.29e+00

Pos logit contributions
 Sham+1.394
Random+1.394
dump+1.386
nam+1.355
 ASA+1.316
Neg logit contributions
orian-1.607
orb-1.526
kson-1.520
rupal-1.476
oulos-1.476
Token
Token ID198
Feature activation-3.01e+00

Pos logit contributions
Random+1.985
 Sham+1.953
nam+1.942
dump+1.937
 ASA+1.798
Neg logit contributions
orian-2.590
 helicop-2.589
kson-2.453
agascar-2.447
orb-2.447
TokenBackground
Token ID21756
Feature activation+1.71e-01

Pos logit contributions
Random+1.615
dump+1.586
 Sham+1.555
nam+1.543
 ASA+1.448
Neg logit contributions
orian-2.582
kson-2.470
orb-2.453
oulos-2.414
rupal-2.404
Token Depression
Token ID22483
Feature activation-3.06e-02

Pos logit contributions
orian+0.133
orb+0.127
kson+0.127
rupal+0.123
oulos+0.123
Neg logit contributions
dump-0.103
Random-0.103
 Sham-0.102
nam-0.101
 ASA-0.096
Token presents
Token ID10969
Feature activation+2.44e+00

Pos logit contributions
dump+0.020
Random+0.020
 Sham+0.019
nam+0.019
 ASA+0.018
Neg logit contributions
orian-0.023
orb-0.022
kson-0.022
rupal-0.021
oulos-0.021
Token a
Token ID257
Feature activation+1.92e+00

Pos logit contributions
orian+1.792
orb+1.707
kson+1.696
rupal+1.646
oulos+1.635
Neg logit contributions
dump-1.585
Random-1.564
 Sham-1.544
nam-1.524
 ASA-1.457
Token significant
Token ID2383
Feature activation-5.13e-01

Pos logit contributions
orian+1.491
orb+1.422
kson+1.416
rupal+1.374
oulos+1.367
Neg logit contributions
dump-1.174
Random-1.164
 Sham-1.149
nam-1.136
 ASA-1.082
Token burden
Token ID10538
Feature activation+3.19e+00

Pos logit contributions
dump+0.339
Random+0.338
 Sham+0.336
nam+0.332
 ASA+0.319
Neg logit contributions
orian-0.372
orb-0.352
kson-0.352
rupal-0.340
oulos-0.339
Token to
Token ID284
Feature activation+2.88e+00

Pos logit contributions
orian+1.948
orb+1.826
kson+1.808
rupal+1.747
tale+1.729
Neg logit contributions
dump-2.476
Random-2.453
 Sham-2.432
nam-2.399
 ASA-2.319
Token both
Token ID1111
Feature activation+3.05e+00

Pos logit contributions
orian+2.147
kson+2.049
orb+2.033
rupal+1.976
oulos+1.970
Neg logit contributions
dump-1.838
Random-1.808
 Sham-1.783
nam-1.764
 ASA-1.658
Token:
Token ID25
Feature activation+4.52e-02

Pos logit contributions
Random+1.487
 Sham+1.484
dump+1.474
nam+1.473
 ASA+1.375
Neg logit contributions
orian-1.739
 helicop-1.700
kson-1.648
orb-1.640
oulos-1.620
Token Carly
Token ID35982
Feature activation-2.05e+00

Pos logit contributions
orian+0.026
orb+0.024
kson+0.024
rupal+0.023
 helicop+0.023
Neg logit contributions
 Sham-0.038
Random-0.037
dump-0.037
nam-0.037
 ASA-0.036
Token Fiorina
Token ID49028
Feature activation-3.45e+00

Pos logit contributions
 Sham+1.905
dump+1.886
Random+1.875
nam+1.867
 ASA+1.804
Neg logit contributions
orian-0.920
orb-0.881
 helicop-0.863
kson-0.854
rupal-0.840
Token's
Token ID338
Feature activation+2.46e-01

Pos logit contributions
 Sham+1.666
nam+1.655
dump+1.624
Random+1.613
 ASA+1.504
Neg logit contributions
orian-3.106
 helicop-3.004
orb-2.995
kson-2.931
rupal-2.922
Token political
Token ID1964
Feature activation+1.01e+00

Pos logit contributions
orian+0.203
orb+0.194
kson+0.194
rupal+0.189
oulos+0.187
Neg logit contributions
Random-0.138
dump-0.138
 Sham-0.137
nam-0.135
 ASA-0.128
Token career
Token ID3451
Feature activation+4.07e-01

Pos logit contributions
orian+0.809
orb+0.770
kson+0.768
rupal+0.748
oulos+0.742
Neg logit contributions
dump-0.588
Random-0.586
 Sham-0.583
nam-0.575
 ASA-0.548
Token Fiorina
Token ID49028
Feature activation-2.92e+00

Pos logit contributions
orian+0.162
kson+0.147
orb+0.146
rupal+0.137
oulos+0.137
Neg logit contributions
dump-0.401
Random-0.401
 Sham-0.397
nam-0.395
 ASA-0.384
Token concedes
Token ID49867
Feature activation-9.24e-02

Pos logit contributions
 Sham+2.234
dump+2.223
nam+2.213
Random+2.205
 ASA+2.115
Neg logit contributions
orian-1.795
orb-1.695
kson-1.667
rupal-1.636
arious-1.619
Token defeat
Token ID7433
Feature activation-8.59e-01

Pos logit contributions
dump+0.052
Random+0.052
 Sham+0.051
nam+0.051
 ASA+0.048
Neg logit contributions
orian-0.076
orb-0.072
kson-0.072
rupal-0.070
oulos-0.070
Token to
Token ID284
Feature activation+3.13e-01

Pos logit contributions
dump+0.546
Random+0.544
 Sham+0.542
nam+0.534
 ASA+0.510
Neg logit contributions
orian-0.644
orb-0.612
kson-0.612
rupal-0.592
oulos-0.589
Token her
Token ID607
Feature activation-1.42e+00

Pos logit contributions
orian+0.234
kson+0.222
orb+0.222
oulos+0.214
rupal+0.214
Neg logit contributions
dump-0.200
Random-0.200
 Sham-0.195
nam-0.195
 ASA-0.185
Token regulations
Token ID6647
Feature activation+5.44e-01

Pos logit contributions
orian+0.393
orb+0.374
kson+0.373
rupal+0.361
oulos+0.359
Neg logit contributions
dump-0.347
Random-0.346
 Sham-0.343
nam-0.339
 ASA-0.325
Token have
Token ID423
Feature activation-1.64e+00

Pos logit contributions
orian+0.416
orb+0.396
kson+0.394
rupal+0.382
oulos+0.381
Neg logit contributions
dump-0.338
Random-0.338
 Sham-0.334
nam-0.330
 ASA-0.315
Token been
Token ID587
Feature activation-1.70e+00

Pos logit contributions
dump+1.007
Random+1.004
 Sham+1.002
nam+0.990
 ASA+0.944
Neg logit contributions
orian-1.256
orb-1.194
kson-1.190
rupal-1.156
oulos-1.151
Token explored
Token ID18782
Feature activation-3.13e+00

Pos logit contributions
 Sham+1.112
Random+1.110
dump+1.109
nam+1.105
 ASA+1.057
Neg logit contributions
orian-1.230
kson-1.173
orb-1.170
rupal-1.130
oulos-1.127
Token at
Token ID379
Feature activation-1.07e+00

Pos logit contributions
dump+1.890
 Sham+1.876
Random+1.871
nam+1.866
 unres+1.758
Neg logit contributions
orian-2.413
kson-2.304
orb-2.303
rupal-2.227
arious-2.224
Token a
Token ID257
Feature activation-1.69e+00

Pos logit contributions
dump+0.645
Random+0.643
 Sham+0.638
nam+0.630
 ASA+0.602
Neg logit contributions
orian-0.837
orb-0.799
kson-0.799
rupal-0.774
oulos-0.772
Token national
Token ID2260
Feature activation+2.00e-01

Pos logit contributions
Random+0.931
dump+0.928
 Sham+0.923
nam+0.915
 ASA+0.867
Neg logit contributions
orian-1.389
kson-1.339
orb-1.338
oulos-1.298
rupal-1.297
Token level
Token ID1241
Feature activation-1.28e+00

Pos logit contributions
orian+0.145
kson+0.137
orb+0.137
rupal+0.133
oulos+0.132
Neg logit contributions
dump-0.132
Random-0.132
 Sham-0.131
nam-0.130
 ASA-0.124
Token (
Token ID357
Feature activation+1.42e+00

Pos logit contributions
dump+0.788
Random+0.782
 Sham+0.781
nam+0.772
 ASA+0.734
Neg logit contributions
orian-0.989
orb-0.942
kson-0.941
rupal-0.911
oulos-0.908
Tokene
Token ID68
Feature activation-4.41e-01

Pos logit contributions
orian+0.977
orb+0.926
kson+0.920
rupal+0.889
oulos+0.884
Neg logit contributions
dump-0.988
Random-0.984
 Sham-0.981
nam-0.968
 ASA-0.933
Token.
Token ID13
Feature activation+1.74e+00

Pos logit contributions
Random+0.281
dump+0.278
 Sham+0.277
nam+0.275
 ASA+0.259
Neg logit contributions
orian-0.332
orb-0.315
kson-0.313
 helicop-0.310
oulos-0.308
Token for
Token ID329
Feature activation-1.78e+00

Pos logit contributions
 Sham+1.863
dump+1.844
Random+1.835
nam+1.816
 ASA+1.711
Neg logit contributions
orian-2.686
kson-2.543
orb-2.541
rupal-2.484
oulos-2.474
Token Star
Token ID2907
Feature activation+3.72e+00

Pos logit contributions
Random+1.054
 Sham+1.054
dump+1.052
nam+1.035
 ASA+0.983
Neg logit contributions
orian-1.401
orb-1.336
kson-1.334
rupal-1.299
oulos-1.291
Token Wars
Token ID6176
Feature activation+5.10e+00

Pos logit contributions
orian+3.683
orb+3.545
kson+3.539
rupal+3.449
oulos+3.439
Neg logit contributions
dump-1.471
Random-1.464
 Sham-1.433
nam-1.411
 ASA-1.319
Token?
Token ID30
Feature activation-1.88e+00

Pos logit contributions
orian+3.690
orb+3.519
kson+3.491
oulos+3.397
tale+3.396
Neg logit contributions
dump-3.303
Random-3.273
nam-3.195
 Sham-3.167
 ASA-3.082
Token
Token ID198
Feature activation-2.80e+00

Pos logit contributions
 Sham+1.187
Random+1.176
dump+1.164
nam+1.150
 ASA+1.108
Neg logit contributions
orian-1.425
orb-1.353
kson-1.341
rupal-1.323
oulos-1.313
Token
Token ID198
Feature activation-2.26e+00

Pos logit contributions
 Sham+1.683
Random+1.675
dump+1.661
nam+1.650
 ASA+1.524
Neg logit contributions
orian-2.225
 helicop-2.214
agascar-2.109
orb-2.107
kson-2.093
TokenNo
Token ID2949
Feature activation+4.86e+00

Pos logit contributions
Random+1.268
dump+1.248
 Sham+1.232
nam+1.220
 ASA+1.137
Neg logit contributions
orian-1.887
kson-1.802
orb-1.796
oulos-1.762
rupal-1.761
Token.
Token ID13
Feature activation+1.03e+00

Pos logit contributions
orian+3.204
orb+3.072
kson+3.032
oulos+2.906
rupal+2.875
Neg logit contributions
dump-3.430
Random-3.410
nam-3.304
 Sham-3.288
 ASA-3.184
Token My
Token ID2011
Feature activation-6.43e-01

Pos logit contributions
orian+0.797
kson+0.758
orb+0.758
rupal+0.733
oulos+0.730
Neg logit contributions
dump-0.635
Random-0.632
 Sham-0.625
nam-0.619
 ASA-0.591
Token parents
Token ID3397
Feature activation-1.31e+00

Pos logit contributions
dump+0.381
Random+0.380
 Sham+0.377
nam+0.372
 ASA+0.355
Neg logit contributions
orian-0.509
orb-0.485
kson-0.484
rupal-0.470
oulos-0.468
Token are
Token ID389
Feature activation-1.08e+00

Pos logit contributions
dump+0.825
 Sham+0.821
Random+0.819
nam+0.811
 ASA+0.771
Neg logit contributions
orian-0.994
orb-0.943
kson-0.942
rupal-0.923
oulos-0.917
Token
Token ID198
Feature activation-1.80e-01

Pos logit contributions
Random+0.214
dump+0.213
 Sham+0.212
nam+0.209
 ASA+0.200
Neg logit contributions
orian-0.259
orb-0.246
kson-0.245
rupal-0.238
oulos-0.238
Token
Token ID198
Feature activation-4.96e-01

Pos logit contributions
Random+0.118
dump+0.118
 Sham+0.117
nam+0.116
 ASA+0.110
Neg logit contributions
orian-0.133
orb-0.126
kson-0.126
 helicop-0.123
oulos-0.122
TokenOver
Token ID5886
Feature activation-3.77e+00

Pos logit contributions
dump+0.258
Random+0.256
 Sham+0.255
nam+0.251
 ASA+0.239
Neg logit contributions
orian-0.428
orb-0.410
kson-0.409
rupal-0.398
oulos-0.395
Tokendrive
Token ID19472
Feature activation-2.45e+00

Pos logit contributions
dump+2.242
Random+2.220
 Sham+2.213
nam+2.170
 ASA+2.043
Neg logit contributions
orian-2.955
kson-2.838
orb-2.800
rupal-2.750
oulos-2.717
Token is
Token ID318
Feature activation-1.12e+00

Pos logit contributions
 Sham+1.542
Random+1.541
dump+1.536
nam+1.497
 ASA+1.431
Neg logit contributions
orian-1.861
orb-1.756
kson-1.755
rupal-1.715
oulos-1.700
Token a
Token ID257
Feature activation-5.02e-01

Pos logit contributions
dump+0.638
Random+0.637
 Sham+0.633
nam+0.623
 ASA+0.592
Neg logit contributions
orian-0.916
orb-0.873
kson-0.872
rupal-0.848
oulos-0.844
Token piece
Token ID3704
Feature activation-5.15e-01

Pos logit contributions
dump+0.291
Random+0.291
 Sham+0.289
nam+0.284
 ASA+0.270
Neg logit contributions
orian-0.404
orb-0.385
kson-0.385
rupal-0.374
oulos-0.374
Token I
Token ID314
Feature activation+1.45e+00

Pos logit contributions
dump+0.330
Random+0.329
 Sham+0.325
nam+0.322
 ASA+0.309
Neg logit contributions
orian-0.383
orb-0.364
kson-0.364
rupal-0.352
oulos-0.350
Token
Token ID447
Feature activation+1.02e+00

Pos logit contributions
orian+1.114
orb+1.060
kson+1.058
rupal+1.024
oulos+1.020
Neg logit contributions
dump-0.897
Random-0.895
 Sham-0.888
nam-0.875
 ASA-0.840
Token
Token ID247
Feature activation+4.09e-02

Pos logit contributions
orian+0.610
kson+0.574
orb+0.573
rupal+0.555
oulos+0.552
Neg logit contributions
Random-0.804
dump-0.804
 Sham-0.796
nam-0.794
 ASA-0.759
Tokenve
Token ID303
Feature activation+3.52e-01

Pos logit contributions
orian+0.033
kson+0.031
orb+0.031
rupal+0.030
oulos+0.030
Neg logit contributions
dump-0.024
Random-0.024
 Sham-0.023
nam-0.023
 ASA-0.022
Token
Token ID198
Feature activation-1.28e+00

Pos logit contributions
dump+0.763
Random+0.762
 Sham+0.758
nam+0.748
 ASA+0.716
Neg logit contributions
orian-0.839
orb-0.796
kson-0.795
rupal-0.770
oulos-0.765
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
Random+0.814
 Sham+0.809
dump+0.809
nam+0.801
 ASA+0.754
Neg logit contributions
orian-0.961
 helicop-0.917
orb-0.911
kson-0.910
oulos-0.892
TokenThe
Token ID464
Feature activation-1.51e-01

Pos logit contributions
Random+0.716
dump+0.715
 Sham+0.705
nam+0.698
 ASA+0.661
Neg logit contributions
orian-0.985
kson-0.940
orb-0.939
rupal-0.913
oulos-0.910
Token young
Token ID1862
Feature activation-3.81e+00

Pos logit contributions
dump+0.084
Random+0.083
 Sham+0.083
nam+0.081
 ASA+0.077
Neg logit contributions
orian-0.125
orb-0.119
kson-0.119
rupal-0.116
oulos-0.115
Token man
Token ID582
Feature activation-1.69e+00

Pos logit contributions
 Sham+1.672
dump+1.662
Random+1.651
nam+1.628
 ASA+1.524
Neg logit contributions
orian-3.561
orb-3.428
kson-3.415
oulos-3.357
rupal-3.355
Token was
Token ID373
Feature activation-2.19e-02

Pos logit contributions
 Sham+1.126
dump+1.125
Random+1.114
nam+1.108
 ASA+1.056
Neg logit contributions
orian-1.209
orb-1.148
kson-1.139
rupal-1.116
arious-1.107
Token a
Token ID257
Feature activation+3.72e-01

Pos logit contributions
dump+0.012
Random+0.012
 Sham+0.012
nam+0.012
 ASA+0.011
Neg logit contributions
orian-0.018
orb-0.017
kson-0.017
rupal-0.017
oulos-0.017
Token junior
Token ID13430
Feature activation-1.79e+00

Pos logit contributions
orian+0.297
orb+0.282
kson+0.282
rupal+0.273
oulos+0.272
Neg logit contributions
dump-0.219
Random-0.219
 Sham-0.215
nam-0.213
 ASA-0.203
Token clerk
Token ID21120
Feature activation+1.01e+00

Pos logit contributions
 Sham+1.082
Random+1.079
dump+1.077
nam+1.059
 ASA+1.016
Neg logit contributions
orian-1.393
kson-1.331
orb-1.327
rupal-1.295
oulos-1.289
Token in
Token ID287
Feature activation+5.35e-01

Pos logit contributions
orian+0.734
orb+0.695
kson+0.694
rupal+0.671
oulos+0.668
Neg logit contributions
dump-0.670
Random-0.668
 Sham-0.660
nam-0.654
 ASA-0.627
Token the
Token ID262
Feature activation-6.50e-01

Pos logit contributions
orian+0.417
orb+0.396
kson+0.396
rupal+0.383
oulos+0.381
Neg logit contributions
dump-0.325
Random-0.323
nam-0.316
 Sham-0.315
 ASA-0.300
Token to
Token ID284
Feature activation-6.16e-01

Pos logit contributions
orian+0.817
orb+0.772
kson+0.771
rupal+0.743
oulos+0.739
Neg logit contributions
dump-0.869
Random-0.867
 Sham-0.859
nam-0.851
 ASA-0.818
Token voters
Token ID4446
Feature activation-2.00e-01

Pos logit contributions
dump+0.370
Random+0.369
 Sham+0.366
nam+0.361
 ASA+0.344
Neg logit contributions
orian-0.484
orb-0.461
kson-0.460
rupal-0.446
oulos-0.445
Token,
Token ID11
Feature activation-8.33e-01

Pos logit contributions
dump+0.130
Random+0.130
 Sham+0.129
nam+0.127
 ASA+0.122
Neg logit contributions
orian-0.146
orb-0.139
kson-0.139
rupal-0.134
oulos-0.134
Token than
Token ID621
Feature activation-1.03e+00

Pos logit contributions
dump+0.519
Random+0.517
 Sham+0.517
nam+0.507
 ASA+0.487
Neg logit contributions
orian-0.633
orb-0.604
kson-0.603
rupal-0.585
oulos-0.581
Token the
Token ID262
Feature activation-3.23e-01

Pos logit contributions
dump+0.704
Random+0.701
 Sham+0.699
nam+0.690
 ASA+0.664
Neg logit contributions
orian-0.717
orb-0.679
kson-0.678
rupal-0.655
oulos-0.652
Token bully
Token ID27410
Feature activation-5.84e-01

Pos logit contributions
dump+0.199
Random+0.198
 Sham+0.195
nam+0.194
 ASA+0.184
Neg logit contributions
orian-0.248
kson-0.236
orb-0.235
rupal-0.228
oulos-0.228
Token pul
Token ID17472
Feature activation-8.75e-03

Pos logit contributions
dump+0.296
Random+0.295
 Sham+0.291
nam+0.287
 ASA+0.272
Neg logit contributions
orian-0.512
orb-0.490
kson-0.490
rupal-0.477
oulos-0.475
Tokenpit
Token ID15544
Feature activation-1.20e+00

Pos logit contributions
dump+0.006
Random+0.006
 Sham+0.006
nam+0.006
 ASA+0.006
Neg logit contributions
orian-0.006
orb-0.006
kson-0.006
rupal-0.006
oulos-0.006
Token.
Token ID13
Feature activation-5.78e-01

Pos logit contributions
dump+0.785
Random+0.782
 Sham+0.779
nam+0.769
 ASA+0.736
Neg logit contributions
orian-0.879
orb-0.836
kson-0.833
rupal-0.807
oulos-0.803
Token PK
Token ID29673
Feature activation-2.72e+00

Pos logit contributions
Random+0.351
dump+0.350
 Sham+0.349
nam+0.342
 ASA+0.328
Neg logit contributions
orian-0.451
orb-0.430
kson-0.427
rupal-0.416
oulos-0.414
Token claims
Token ID3667
Feature activation-1.59e+00

Pos logit contributions
 Sham+1.866
dump+1.864
Random+1.860
nam+1.828
 ASA+1.752
Neg logit contributions
orian-1.879
orb-1.790
kson-1.774
rupal-1.714
oulos-1.711
Token was
Token ID373
Feature activation+4.27e-01

Pos logit contributions
orian+0.188
orb+0.179
kson+0.179
rupal+0.173
oulos+0.172
Neg logit contributions
dump-0.149
Random-0.148
 Sham-0.147
nam-0.145
 ASA-0.139
Token valued
Token ID17560
Feature activation-5.91e-01

Pos logit contributions
orian+0.331
orb+0.316
kson+0.315
rupal+0.306
oulos+0.304
Neg logit contributions
dump-0.260
Random-0.259
 Sham-0.257
nam-0.254
 ASA-0.242
Token as
Token ID355
Feature activation+6.71e-02

Pos logit contributions
dump+0.371
Random+0.371
 Sham+0.369
nam+0.366
 ASA+0.347
Neg logit contributions
orian-0.446
orb-0.424
kson-0.424
rupal-0.411
oulos-0.409
Token
Token ID564
Feature activation-2.57e-01

Pos logit contributions
orian+0.055
orb+0.052
kson+0.052
rupal+0.051
oulos+0.051
Neg logit contributions
dump-0.038
Random-0.038
 Sham-0.037
nam-0.037
 ASA-0.035
Token
Token ID246
Feature activation-1.27e+00

Pos logit contributions
dump+0.167
Random+0.167
 Sham+0.165
nam+0.163
 ASA+0.156
Neg logit contributions
orian-0.189
orb-0.180
kson-0.179
rupal-0.174
oulos-0.173
Tokengood
Token ID11274
Feature activation-5.94e+00

Pos logit contributions
dump+0.822
Random+0.820
 Sham+0.809
nam+0.808
 ASA+0.762
Neg logit contributions
orian-0.935
kson-0.890
orb-0.884
rupal-0.860
oulos-0.856
Token
Token ID447
Feature activation-1.45e+00

Pos logit contributions
nam+4.147
dump+4.124
Random+4.111
 Sham+4.109
 unres+3.927
Neg logit contributions
orian-3.945
kson-3.748
orb-3.719
rupal-3.598
oulos-3.567
Token
Token ID247
Feature activation-3.23e-01

Pos logit contributions
dump+1.073
Random+1.072
 Sham+1.065
nam+1.057
 ASA+1.011
Neg logit contributions
orian-0.930
orb-0.876
kson-0.873
rupal-0.847
oulos-0.842
Token became
Token ID2627
Feature activation-2.04e+00

Pos logit contributions
dump+0.208
Random+0.207
 Sham+0.206
nam+0.204
 ASA+0.194
Neg logit contributions
orian-0.239
orb-0.227
kson-0.227
rupal-0.220
oulos-0.219
Token
Token ID564
Feature activation-2.27e-01

Pos logit contributions
dump+1.312
Random+1.309
 Sham+1.307
nam+1.298
 ASA+1.230
Neg logit contributions
orian-1.504
orb-1.431
kson-1.428
rupal-1.381
oulos-1.377
Token
Token ID246
Feature activation-1.93e+00

Pos logit contributions
dump+0.148
Random+0.147
 Sham+0.146
nam+0.145
 ASA+0.138
Neg logit contributions
orian-0.166
orb-0.157
kson-0.157
rupal-0.152
oulos-0.152
Token.
Token ID13
Feature activation-2.48e+00

Pos logit contributions
orian+0.443
orb+0.422
kson+0.421
rupal+0.408
oulos+0.406
Neg logit contributions
dump-0.363
Random-0.362
 Sham-0.358
nam-0.354
 ASA-0.339
Token
Token ID198
Feature activation-4.21e-01

Pos logit contributions
 Sham+1.517
Random+1.516
dump+1.504
nam+1.481
 ASA+1.422
Neg logit contributions
orian-1.915
orb-1.832
kson-1.810
rupal-1.771
oulos-1.765
Token
Token ID198
Feature activation-6.07e-01

Pos logit contributions
Random+0.285
dump+0.284
 Sham+0.282
nam+0.279
 ASA+0.267
Neg logit contributions
orian-0.298
orb-0.283
kson-0.282
rupal-0.273
oulos-0.272
TokenH
Token ID39
Feature activation-3.28e-01

Pos logit contributions
dump+0.330
Random+0.327
 Sham+0.326
nam+0.321
 ASA+0.306
Neg logit contributions
orian-0.510
orb-0.488
kson-0.486
rupal-0.473
oulos-0.470
Tokenaj
Token ID1228
Feature activation-2.13e+00

Pos logit contributions
dump+0.218
Random+0.218
 Sham+0.216
nam+0.214
 ASA+0.204
Neg logit contributions
orian-0.236
kson-0.224
orb-0.223
rupal-0.216
oulos-0.215
Tokenime
Token ID524
Feature activation-5.58e+00

Pos logit contributions
dump+1.299
Random+1.291
 Sham+1.284
nam+1.272
 ASA+1.203
Neg logit contributions
orian-1.643
kson-1.566
orb-1.564
rupal-1.517
oulos-1.516
Token Tab
Token ID16904
Feature activation-6.23e+00

Pos logit contributions
 Sham+3.498
dump+3.432
nam+3.395
Random+3.383
 ASA+3.269
Neg logit contributions
orian-4.242
orb-4.037
kson-3.939
rupal-3.900
arious-3.880
Tokenata
Token ID1045
Feature activation-5.13e+00

Pos logit contributions
dump+3.398
nam+3.376
 Sham+3.296
Random+3.268
 ASA+2.991
Neg logit contributions
orian-5.045
kson-4.878
orb-4.847
natureconservancy-4.793
agascar-4.745
Token:
Token ID25
Feature activation-1.22e+00

Pos logit contributions
 Sham+3.212
Random+3.178
dump+3.161
nam+3.158
 ASA+2.993
Neg logit contributions
orian-3.834
orb-3.634
kson-3.617
agascar-3.535
rupal-3.534
Token There
Token ID1318
Feature activation-3.05e-01

Pos logit contributions
dump+0.731
Random+0.731
 Sham+0.727
nam+0.716
 ASA+0.684
Neg logit contributions
orian-0.952
orb-0.909
kson-0.905
rupal-0.879
oulos-0.875
Token were
Token ID547
Feature activation+5.41e-02

Pos logit contributions
dump+0.195
Random+0.194
 Sham+0.192
nam+0.190
 ASA+0.182
Neg logit contributions
orian-0.228
orb-0.216
kson-0.216
rupal-0.209
oulos-0.208
Token the
Token ID262
Feature activation-1.39e-01

Pos logit contributions
Random+1.057
dump+1.057
 Sham+1.054
nam+1.037
 ASA+0.995
Neg logit contributions
orian-1.326
orb-1.262
kson-1.259
rupal-1.223
oulos-1.215
Token University
Token ID2059
Feature activation-1.64e+00

Pos logit contributions
dump+0.081
Random+0.080
 Sham+0.079
nam+0.079
 ASA+0.075
Neg logit contributions
orian-0.111
orb-0.106
kson-0.106
rupal-0.103
oulos-0.102
Token of
Token ID286
Feature activation-3.66e+00

Pos logit contributions
 Sham+0.997
Random+0.977
nam+0.975
dump+0.974
 ASA+0.921
Neg logit contributions
orian-1.278
orb-1.231
kson-1.221
 helicop-1.197
arious-1.193
Token California
Token ID3442
Feature activation-6.40e+00

Pos logit contributions
 Sham+2.203
Random+2.154
dump+2.141
nam+2.110
 ASA+2.058
Neg logit contributions
orian-2.903
orb-2.746
kson-2.740
rupal-2.686
oulos-2.669
Token,
Token ID11
Feature activation-4.80e+00

Pos logit contributions
 Sham+3.662
Random+3.590
nam+3.555
dump+3.552
 ASA+3.381
Neg logit contributions
orian-5.159
orb-4.872
kson-4.867
rupal-4.785
natureconservancy-4.779
Token Santa
Token ID8909
Feature activation-5.83e+00

Pos logit contributions
 Sham+3.027
Random+3.002
dump+2.973
nam+2.935
 ASA+2.826
Neg logit contributions
orian-3.603
orb-3.433
kson-3.405
rupal-3.322
oulos-3.318
Token Barbara
Token ID16685
Feature activation-3.95e+00

Pos logit contributions
 Sham+3.862
Random+3.668
nam+3.642
dump+3.607
 ASA+3.583
Neg logit contributions
orian-4.201
orb-4.044
oulos-3.958
rupal-3.896
kson-3.894
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
Random+2.469
 Sham+2.469
dump+2.462
nam+2.430
 ASA+2.325
Neg logit contributions
orian-2.952
orb-2.814
kson-2.809
rupal-2.735
arious-2.709
Token and
Token ID290
Feature activation+3.43e-01

Pos logit contributions
dump+0.706
Random+0.705
 Sham+0.699
nam+0.691
 ASA+0.662
Neg logit contributions
orian-0.794
orb-0.754
kson-0.753
rupal-0.729
oulos-0.725
Token an
Token ID281
Feature activation-1.12e+00

Pos logit contributions
orian+0.286
orb+0.272
kson+0.272
rupal+0.264
oulos+0.263
Neg logit contributions
dump-0.191
Random-0.190
 Sham-0.186
nam-0.184
 ASA-0.174
Token organizer
Token ID26311
Feature activation+3.64e+00

Pos logit contributions
Random+0.665
 Sham+0.663
dump+0.662
nam+0.655
 ASA+0.630
Neg logit contributions
orian-0.877
kson-0.838
orb-0.836
rupal-0.815
oulos-0.807
Token the
Token ID262
Feature activation+2.99e+00

Pos logit contributions
dump+0.074
Random+0.074
 Sham+0.074
nam+0.073
 ASA+0.069
Neg logit contributions
orian-0.098
orb-0.094
kson-0.094
rupal-0.091
oulos-0.091
Token European
Token ID3427
Feature activation+1.23e+00

Pos logit contributions
orian+2.229
kson+2.109
orb+2.096
oulos+2.017
rupal+2.016
Neg logit contributions
dump-1.894
Random-1.893
 Sham-1.854
nam-1.846
 ASA-1.747
Token rule
Token ID3896
Feature activation-7.95e-01

Pos logit contributions
orian+0.999
orb+0.952
kson+0.947
rupal+0.920
oulos+0.917
Neg logit contributions
dump-0.706
Random-0.703
 Sham-0.694
nam-0.687
 ASA-0.652
Token book
Token ID1492
Feature activation+1.63e+00

Pos logit contributions
dump+0.508
Random+0.504
 Sham+0.503
nam+0.496
 ASA+0.474
Neg logit contributions
orian-0.592
kson-0.565
orb-0.564
rupal-0.547
oulos-0.543
Token in
Token ID287
Feature activation-2.32e-01

Pos logit contributions
orian+1.168
orb+1.104
kson+1.104
rupal+1.065
oulos+1.062
Neg logit contributions
dump-1.082
Random-1.082
 Sham-1.072
nam-1.060
 ASA-1.018
Token terms
Token ID2846
Feature activation-5.77e+00

Pos logit contributions
dump+0.142
Random+0.142
 Sham+0.141
nam+0.139
 ASA+0.133
Neg logit contributions
orian-0.179
orb-0.171
kson-0.170
rupal-0.165
oulos-0.164
Token of
Token ID286
Feature activation-1.77e+00

Pos logit contributions
 Sham+3.500
dump+3.497
Random+3.485
nam+3.457
 ASA+3.282
Neg logit contributions
orian-4.376
orb-4.218
kson-4.192
oulos-4.060
arious-4.058
Token its
Token ID663
Feature activation-2.09e+00

Pos logit contributions
dump+1.031
Random+1.027
 Sham+1.027
nam+1.012
 ASA+0.966
Neg logit contributions
orian-1.406
orb-1.350
kson-1.346
rupal-1.309
oulos-1.299
Token sensible
Token ID20586
Feature activation-7.33e-01

Pos logit contributions
dump+1.279
Random+1.276
 Sham+1.274
nam+1.255
 ASA+1.201
Neg logit contributions
orian-1.597
orb-1.534
kson-1.527
rupal-1.486
oulos-1.478
Token application
Token ID3586
Feature activation+1.37e+00

Pos logit contributions
dump+0.473
Random+0.471
 Sham+0.467
nam+0.462
 ASA+0.442
Neg logit contributions
orian-0.542
orb-0.515
kson-0.514
rupal-0.498
oulos-0.496
Token to
Token ID284
Feature activation-5.51e-01

Pos logit contributions
orian+0.991
orb+0.937
kson+0.933
rupal+0.904
oulos+0.900
Neg logit contributions
dump-0.913
Random-0.909
 Sham-0.900
nam-0.890
 ASA-0.855
Token first
Token ID717
Feature activation+3.41e+00

Pos logit contributions
orian+1.254
orb+1.197
kson+1.195
rupal+1.161
oulos+1.156
Neg logit contributions
dump-0.881
Random-0.879
 Sham-0.870
nam-0.859
 ASA-0.818
Token Ghostbusters
Token ID50037
Feature activation+6.16e+00

Pos logit contributions
orian+2.225
orb+2.154
kson+2.067
tale+2.027
arious+2.019
Neg logit contributions
dump-2.430
Random-2.415
 Sham-2.410
nam-2.379
 ASA-2.328
Token,
Token ID11
Feature activation+9.81e-01

Pos logit contributions
orian+4.260
orb+4.108
kson+4.034
tale+3.909
rupal+3.882
Neg logit contributions
dump-4.117
Random-4.065
 Sham-4.018
nam-3.984
 ASA-3.876
Token the
Token ID262
Feature activation+1.06e+00

Pos logit contributions
orian+0.791
kson+0.753
orb+0.753
rupal+0.730
oulos+0.729
Neg logit contributions
dump-0.571
Random-0.571
 Sham-0.568
nam-0.560
 ASA-0.530
Tokenne
Token ID710
Feature activation+1.51e+00

Pos logit contributions
orian+0.818
orb+0.783
kson+0.773
oulos+0.752
arious+0.750
Neg logit contributions
dump-0.646
Random-0.646
 Sham-0.636
nam-0.631
 ASA-0.608
Tokenigh
Token ID394
Feature activation-6.35e+00

Pos logit contributions
orian+0.936
orb+0.880
kson+0.878
rupal+0.841
oulos+0.838
Neg logit contributions
Random-1.156
dump-1.155
 Sham-1.145
nam-1.135
 ASA-1.094
Tokenbor
Token ID2865
Feature activation+3.82e-01

Pos logit contributions
 Sham+3.232
dump+3.229
nam+3.223
Random+3.191
 ASA+2.892
Neg logit contributions
orian-5.457
kson-5.160
oulos-5.135
rupal-5.109
orb-5.056
Tokenhood
Token ID2894
Feature activation+1.67e+00

Pos logit contributions
orian+0.314
orb+0.300
kson+0.300
rupal+0.291
oulos+0.290
Neg logit contributions
dump-0.215
Random-0.215
 Sham-0.212
nam-0.210
 ASA-0.200
Token in
Token ID287
Feature activation+1.37e+00

Pos logit contributions
orian+1.198
orb+1.158
kson+1.121
tale+1.100
arious+1.093
Neg logit contributions
Random-1.090
dump-1.080
 Sham-1.055
nam-1.045
 unres-1.023
Token New
Token ID968
Feature activation-2.78e-01

Pos logit contributions
orian+1.060
orb+1.020
kson+1.005
oulos+0.973
rupal+0.973
Neg logit contributions
dump-0.824
Random-0.815
 Sham-0.806
nam-0.794
 ASA-0.771
Token York
Token ID1971
Feature activation+4.79e+00

Pos logit contributions
Random+0.151
 Sham+0.150
dump+0.150
nam+0.149
 ASA+0.138
Neg logit contributions
orian-0.235
orb-0.225
kson-0.222
 helicop-0.220
rupal-0.220