TOP ACTIVATIONS
MAX = 13.397

carrying his child to a grave in # Gaza ,
intervention of Ecuador ian president Core a . Assange applied for
its way out of his grave following a collision with a
says . Dinosaur bones with Carbon - 14 dates in the
just to stay in the pel oton and then Old Will
of the study is that carbon emission and climate change -
so they censored them . Carbon - 14 is considered to
up well ings that recycle carbon absorbed at higher lat itudes
a fan holds in his heart when watching a sporting contest
Pearce at An Evening with Conor McGregor at the SEC Arm
in 2013 . Car la del P onte ,
( Photo by REUTERS / Car lo Alleg ri ) Michael
task ed to fly by comet 19 P / B or
iron rod enc ased in copper and dated from about 200
determine the social costs of carbon . Sh ind
1 was intended to visit comet 76 P / West
or the Egyptians or the Cy pri ots they weren 't
<|endoftext|> WH EN Catherine Mull igan , a part
. <|endoftext|> WASHINGTON A Cy gn us cargo mission to
Block did you have a blueprint for the way you wanted

MIN ACTIVATIONS
MIN = -12.791

applies to humans . Mi ikk ul ain en and Hoffman
child is transgender , society inst ills in them rules about
r ims , laced to Suz ue road hubs with an
, P . A ., inst ig ates 13 lawsuits against
, too , with each inst al ment representing a sizeable
version | count | | -------------------- -+ -------- -+ ------- |
rock festival , or a skate park or hanging out in
cent . Leg isl ation [ edit ]
. This new local ism is pragmatic
that he had been an inst igator of the Mau Mau
am , a benz od iazep ine anx io ly tic
echoes of M . Night Shy am alan s
orient ations . Small er local es in the same time
BS , Food Network , HG TV , Cartoon Network ,
activity returns to normal , seasonal flu levels . BACK {
by a combination of the Soon ers ' own inept offense
books , the hipp ie inside me thinks that
. For the Yog ventures Kickstarter backers the physical
the north than the tiny sl iver of sea that divides
radio in FP 1 at Suz uka to say : "

INTERVAL 6.850 - 13.397
CONTAINS 0.349%

F ender Jaguar C ob ain was affected enough
of your existence you are complete , whole , perfect and
the absorption grows with [ CO 2 ] due to fertil
speaker of Catalan Parliament , Car me For cade ll ,
OWER mag azine ) <|endoftext|> C it ib ank fore closed

INTERVAL 0.303 - 6.850
CONTAINS 41.156%

one side , and not much on the other . But
. He graduated from Dartmouth in 1973 and then law school
through the Flor a Family Foundation . Others involved
key plan ks of this world beating military machine .
brain was not necessary to master multiple simultaneous conceptual rule learning

INTERVAL -6.244 - 0.303
CONTAINS 58.031%

of the first water , an enormous White Elephant , completely
farm nearby ? ( Think of The Simpsons and the mon
been a dedicated anti - gun advocate in her private life
The trailers and still s for the upcoming episode have already
on some pretty heavy software correction , especially in the corners

INTERVAL -12.791 - -6.244
CONTAINS 0.463%

film than in any previous live - action TM NT movie
fight him . The Her ok iller was big enough that
0 , ]. This can be done with the following equation
the north than the tiny sl iver of sea that divides
Sp ires vs Ank le Shank er Ph y
Token carrying
Token ID6872
Feature activation+3.63e+00

Pos logit contributions
itized+0.664
PD+0.655
olk+0.650
 renamed+0.649
 reviewer+0.643
Neg logit contributions
apult-1.262
aeda-1.247
cles-1.247
elaide-1.205
riots-1.201
Token his
Token ID465
Feature activation+2.69e-01

Pos logit contributions
cles+3.454
apult+3.445
aeda+3.401
riots+3.271
elaide+3.265
Neg logit contributions
itized-1.951
olk-1.901
PD-1.887
 reviewer-1.880
essor-1.868
Token child
Token ID1200
Feature activation+1.79e+00

Pos logit contributions
apult+0.256
cles+0.254
aeda+0.252
riots+0.243
elaide+0.243
Neg logit contributions
itized-0.145
PD-0.143
olk-0.142
 reviewer-0.141
 renamed-0.140
Token to
Token ID284
Feature activation+9.29e-01

Pos logit contributions
apult+1.717
cles+1.710
aeda+1.696
riots+1.633
elaide+1.632
Neg logit contributions
itized-0.954
PD-0.934
olk-0.931
 reviewer-0.924
 renamed-0.920
Token a
Token ID257
Feature activation+1.71e+00

Pos logit contributions
apult+0.909
cles+0.907
aeda+0.897
riots+0.865
elaide+0.864
Neg logit contributions
itized-0.478
PD-0.468
olk-0.468
 reviewer-0.463
agers-0.460
Token grave
Token ID12296
Feature activation+1.34e+01

Pos logit contributions
apult+1.610
cles+1.606
aeda+1.588
riots+1.529
elaide+1.526
Neg logit contributions
itized-0.943
PD-0.922
olk-0.922
 reviewer-0.914
agers-0.907
Token in
Token ID287
Feature activation+1.68e+00

Pos logit contributions
apult+11.218
cles+11.195
aeda+10.784
riots+10.627
elaide+10.469
Neg logit contributions
itized-7.348
ansky-7.274
essor-7.272
agers-7.242
olk-7.212
Token #
Token ID1303
Feature activation+2.38e+00

Pos logit contributions
apult+1.562
cles+1.557
aeda+1.540
riots+1.482
elaide+1.479
Neg logit contributions
itized-0.949
PD-0.930
olk-0.929
 reviewer-0.922
agers-0.915
TokenGaza
Token ID48790
Feature activation+1.48e+00

Pos logit contributions
cles+1.751
apult+1.751
aeda+1.722
riots+1.643
elaide+1.636
Neg logit contributions
itized-1.793
olk-1.762
PD-1.760
 reviewer-1.760
 renamed-1.743
Token,
Token ID11
Feature activation+9.94e-01

Pos logit contributions
apult+1.441
cles+1.437
aeda+1.426
riots+1.371
berus+1.370
Neg logit contributions
itized-0.764
PD-0.754
olk-0.750
 reviewer-0.739
 renamed-0.739
Token
Token ID447
Feature activation+2.76e-01

Pos logit contributions
apult+0.936
cles+0.932
aeda+0.923
riots+0.889
elaide+0.888
Neg logit contributions
itized-0.550
PD-0.540
olk-0.538
 reviewer-0.533
 renamed-0.532
Token intervention
Token ID9572
Feature activation-1.24e+00

Pos logit contributions
 reviewer+1.926
PD+1.898
itized+1.894
olk+1.880
agers+1.877
Neg logit contributions
aeda-3.134
cles-3.108
apult-3.108
prus-2.950
riots-2.947
Token of
Token ID286
Feature activation+6.29e-01

Pos logit contributions
itized+0.656
PD+0.648
olk+0.642
 reviewer+0.638
 renamed+0.635
Neg logit contributions
apult-1.189
cles-1.183
aeda-1.180
riots-1.135
elaide-1.132
Token Ecuador
Token ID25794
Feature activation+3.82e+00

Pos logit contributions
apult+0.553
cles+0.551
aeda+0.545
riots+0.523
elaide+0.522
Neg logit contributions
itized-0.386
PD-0.379
olk-0.379
 reviewer-0.376
agers-0.373
Tokenian
Token ID666
Feature activation+2.38e+00

Pos logit contributions
apult+3.431
cles+3.431
aeda+3.398
riots+3.267
berus+3.252
Neg logit contributions
itized-2.233
olk-2.176
PD-2.169
 reviewer-2.152
agers-2.144
Token president
Token ID1893
Feature activation-3.53e-01

Pos logit contributions
cles+2.108
apult+2.104
aeda+2.079
riots+2.001
berus+1.984
Neg logit contributions
itized-1.435
olk-1.402
PD-1.383
agers-1.373
stead-1.367
Token Core
Token ID7231
Feature activation+1.33e+01

Pos logit contributions
itized+0.313
PD+0.310
olk+0.309
 reviewer+0.308
agers+0.307
Neg logit contributions
apult-0.214
cles-0.212
aeda-0.209
elaide-0.198
riots-0.197
Tokena
Token ID64
Feature activation-1.62e-02

Pos logit contributions
aeda+9.531
cles+9.365
apult+9.217
nea+9.123
lain+8.686
Neg logit contributions
itized-9.375
 reviewer-9.362
olk-9.260
stead-9.143
ansky-9.111
Token.
Token ID13
Feature activation+8.21e-01

Pos logit contributions
itized+0.009
PD+0.008
olk+0.008
 reviewer+0.008
 renamed+0.008
Neg logit contributions
apult-0.016
cles-0.016
aeda-0.016
berus-0.015
elaide-0.015
Token Assange
Token ID21882
Feature activation+3.45e+00

Pos logit contributions
apult+0.778
cles+0.776
aeda+0.767
riots+0.739
elaide+0.738
Neg logit contributions
itized-0.448
PD-0.439
olk-0.439
 reviewer-0.435
 renamed-0.431
Token applied
Token ID5625
Feature activation+2.31e+00

Pos logit contributions
cles+3.160
apult+3.126
aeda+3.068
riots+2.968
berus+2.953
Neg logit contributions
itized-1.988
olk-1.936
PD-1.915
essor-1.894
 reviewer-1.888
Token for
Token ID329
Feature activation-1.02e-01

Pos logit contributions
apult+2.085
cles+2.079
aeda+2.055
riots+1.975
elaide+1.972
Neg logit contributions
itized-1.360
PD-1.333
olk-1.332
 reviewer-1.322
agers-1.312
Token its
Token ID663
Feature activation-1.18e+00

Pos logit contributions
itized+0.161
PD+0.158
olk+0.157
 reviewer+0.157
agers+0.155
Neg logit contributions
apult-0.305
cles-0.304
aeda-0.301
riots-0.290
elaide-0.290
Token way
Token ID835
Feature activation-1.01e+00

Pos logit contributions
itized+0.416
 reviewer+0.407
 renamed+0.405
PD+0.404
olk+0.399
Neg logit contributions
apult-1.338
cles-1.327
aeda-1.322
elaide-1.286
riots-1.286
Token out
Token ID503
Feature activation-1.47e+00

Pos logit contributions
itized+0.541
PD+0.527
 reviewer+0.524
olk+0.523
 renamed+0.522
Neg logit contributions
apult-0.963
cles-0.957
aeda-0.953
riots-0.917
berus-0.916
Token of
Token ID286
Feature activation+4.53e-01

Pos logit contributions
itized+0.776
PD+0.753
olk+0.751
 reviewer+0.744
 renamed+0.742
Neg logit contributions
apult-1.416
cles-1.414
aeda-1.409
berus-1.358
riots-1.354
Token his
Token ID465
Feature activation-2.14e-01

Pos logit contributions
apult+0.451
cles+0.449
aeda+0.445
elaide+0.429
riots+0.428
Neg logit contributions
itized-0.226
PD-0.221
 reviewer-0.220
olk-0.219
 renamed-0.218
Token grave
Token ID12296
Feature activation+1.23e+01

Pos logit contributions
itized+0.131
PD+0.129
olk+0.128
 reviewer+0.128
 renamed+0.127
Neg logit contributions
apult-0.188
cles-0.187
aeda-0.186
elaide-0.178
riots-0.177
Token following
Token ID1708
Feature activation+9.92e-02

Pos logit contributions
cles+10.241
apult+10.097
aeda+9.738
elaide+9.614
riots+9.611
Neg logit contributions
itized-7.231
essor-7.220
PD-7.195
ansky-7.148
olk-7.126
Token a
Token ID257
Feature activation+3.76e-01

Pos logit contributions
apult+0.099
cles+0.099
aeda+0.098
elaide+0.094
berus+0.094
Neg logit contributions
itized-0.049
PD-0.048
 reviewer-0.048
olk-0.048
 renamed-0.048
Token collision
Token ID17661
Feature activation+3.84e-01

Pos logit contributions
apult+0.343
cles+0.341
aeda+0.339
riots+0.325
elaide+0.324
Neg logit contributions
itized-0.218
PD-0.215
olk-0.214
 reviewer-0.214
 renamed-0.212
Token with
Token ID351
Feature activation-1.08e+00

Pos logit contributions
apult+0.380
cles+0.378
aeda+0.376
riots+0.362
berus+0.361
Neg logit contributions
itized-0.193
PD-0.190
olk-0.190
 reviewer-0.188
 renamed-0.187
Token a
Token ID257
Feature activation+2.27e-01

Pos logit contributions
itized+0.507
PD+0.497
olk+0.495
 reviewer+0.492
 renamed+0.488
Neg logit contributions
apult-1.098
cles-1.095
aeda-1.085
riots-1.047
elaide-1.045
Token says
Token ID1139
Feature activation-3.62e+00

Pos logit contributions
itized+0.006
PD+0.006
olk+0.006
 reviewer+0.006
agers+0.006
Neg logit contributions
apult-0.010
cles-0.010
aeda-0.010
riots-0.010
elaide-0.010
Token.
Token ID13
Feature activation-3.65e-01

Pos logit contributions
itized+1.694
PD+1.680
agers+1.680
olk+1.664
 reviewer+1.662
Neg logit contributions
apult-3.698
aeda-3.628
cles-3.626
berus-3.519
riots-3.508
Token Dinosaur
Token ID47808
Feature activation+3.95e-01

Pos logit contributions
itized+0.194
PD+0.191
olk+0.190
 reviewer+0.189
 renamed+0.187
Neg logit contributions
apult-0.351
cles-0.351
aeda-0.347
riots-0.335
elaide-0.334
Token bones
Token ID11945
Feature activation+3.94e+00

Pos logit contributions
apult+0.335
cles+0.335
aeda+0.330
riots+0.316
elaide+0.316
Neg logit contributions
itized-0.255
PD-0.250
olk-0.250
 reviewer-0.248
agers-0.246
Token with
Token ID351
Feature activation-2.07e+00

Pos logit contributions
cles+3.545
apult+3.510
aeda+3.460
riots+3.329
elaide+3.291
Neg logit contributions
itized-2.316
PD-2.262
olk-2.244
essor-2.225
 reviewer-2.222
Token Carbon
Token ID23699
Feature activation+1.23e+01

Pos logit contributions
itized+1.096
olk+1.072
PD+1.071
 reviewer+1.068
 renamed+1.063
Neg logit contributions
apult-1.996
cles-1.980
aeda-1.969
riots-1.899
elaide-1.892
Token-
Token ID12
Feature activation+2.27e+00

Pos logit contributions
cles+11.676
aeda+11.569
apult+11.414
nea+10.924
berus+10.861
Neg logit contributions
itized-5.594
olk-5.560
PD-5.541
 reviewer-5.491
agers-5.389
Token14
Token ID1415
Feature activation+8.80e-01

Pos logit contributions
cles+1.845
apult+1.843
aeda+1.818
riots+1.739
elaide+1.737
Neg logit contributions
itized-1.540
olk-1.514
PD-1.509
 reviewer-1.506
 renamed-1.490
Token dates
Token ID9667
Feature activation+2.28e-01

Pos logit contributions
cles+0.809
apult+0.807
aeda+0.797
riots+0.768
elaide+0.764
Neg logit contributions
itized-0.503
olk-0.494
PD-0.490
 reviewer-0.488
agers-0.483
Token in
Token ID287
Feature activation-7.34e-01

Pos logit contributions
apult+0.212
cles+0.212
aeda+0.210
riots+0.202
elaide+0.201
Neg logit contributions
itized-0.128
PD-0.125
olk-0.125
 reviewer-0.124
agers-0.123
Token the
Token ID262
Feature activation-6.35e-02

Pos logit contributions
itized+0.380
PD+0.373
olk+0.372
 reviewer+0.370
agers+0.368
Neg logit contributions
apult-0.716
cles-0.712
aeda-0.707
riots-0.682
elaide-0.680
Token just
Token ID655
Feature activation-8.99e-01

Pos logit contributions
apult+0.826
cles+0.824
aeda+0.815
riots+0.785
elaide+0.782
Neg logit contributions
itized-0.500
PD-0.491
olk-0.491
 reviewer-0.486
agers-0.483
Token to
Token ID284
Feature activation-2.52e-01

Pos logit contributions
itized+0.507
PD+0.500
olk+0.500
 reviewer+0.494
 renamed+0.492
Neg logit contributions
apult-0.831
cles-0.831
aeda-0.823
berus-0.793
riots-0.793
Token stay
Token ID2652
Feature activation-2.44e+00

Pos logit contributions
itized+0.143
PD+0.141
olk+0.140
 reviewer+0.139
agers+0.138
Neg logit contributions
apult-0.234
cles-0.233
aeda-0.231
riots-0.222
elaide-0.222
Token in
Token ID287
Feature activation+1.94e+00

Pos logit contributions
itized+1.237
PD+1.218
stead+1.207
olk+1.206
 reviewer+1.200
Neg logit contributions
apult-2.401
cles-2.388
aeda-2.387
riots-2.300
berus-2.298
Token the
Token ID262
Feature activation+1.71e+00

Pos logit contributions
apult+1.853
cles+1.848
aeda+1.826
elaide+1.761
riots+1.756
Neg logit contributions
itized-1.042
olk-1.021
PD-1.018
 reviewer-1.011
agers-1.005
Token pel
Token ID16176
Feature activation+1.22e+01

Pos logit contributions
apult+1.565
cles+1.563
aeda+1.540
riots+1.481
elaide+1.479
Neg logit contributions
itized-0.992
olk-0.970
PD-0.970
 reviewer-0.958
agers-0.956
Tokenoton
Token ID18970
Feature activation+4.79e+00

Pos logit contributions
cles+7.016
apult+6.736
riots+6.681
nea+6.552
aeda+6.538
Neg logit contributions
 renamed-10.397
itized-10.373
hips-10.369
 reviewer-10.331
DOS-10.148
Token and
Token ID290
Feature activation+1.81e+00

Pos logit contributions
apult+4.388
cles+4.381
aeda+4.308
elaide+4.159
riots+4.146
Neg logit contributions
itized-2.739
olk-2.685
PD-2.669
 reviewer-2.659
essor-2.641
Token then
Token ID788
Feature activation+6.87e-01

Pos logit contributions
apult+1.635
cles+1.632
aeda+1.611
riots+1.548
elaide+1.545
Neg logit contributions
itized-1.070
olk-1.049
PD-1.048
 reviewer-1.040
agers-1.032
Token Old
Token ID5706
Feature activation-1.19e+00

Pos logit contributions
apult+0.635
cles+0.633
aeda+0.627
riots+0.603
elaide+0.602
Neg logit contributions
itized-0.390
PD-0.383
olk-0.382
 reviewer-0.379
agers-0.376
Token Will
Token ID2561
Feature activation-6.86e-01

Pos logit contributions
itized+0.702
olk+0.698
PD+0.694
stead+0.686
 reviewer+0.684
Neg logit contributions
apult-1.064
cles-1.056
aeda-1.050
berus-1.012
riots-1.006
Token of
Token ID286
Feature activation-7.35e-02

Pos logit contributions
itized+0.188
PD+0.185
olk+0.184
 reviewer+0.184
 renamed+0.181
Neg logit contributions
apult-0.329
cles-0.328
aeda-0.326
elaide-0.315
berus-0.314
Token the
Token ID262
Feature activation-1.11e+00

Pos logit contributions
itized+0.042
PD+0.041
olk+0.041
 reviewer+0.041
agers+0.040
Neg logit contributions
cles-0.068
apult-0.068
aeda-0.067
riots-0.065
elaide-0.065
Token study
Token ID2050
Feature activation+5.99e-01

Pos logit contributions
itized+0.668
 reviewer+0.657
olk+0.657
PD+0.656
 renamed+0.648
Neg logit contributions
cles-0.982
apult-0.980
aeda-0.965
elaide-0.933
riots-0.933
Token is
Token ID318
Feature activation-1.22e-01

Pos logit contributions
cles+0.575
apult+0.575
aeda+0.569
riots+0.550
elaide+0.549
Neg logit contributions
itized-0.317
PD-0.312
olk-0.311
 reviewer-0.309
agers-0.306
Token that
Token ID326
Feature activation+1.94e+00

Pos logit contributions
itized+0.064
PD+0.064
olk+0.064
 reviewer+0.063
agers+0.062
Neg logit contributions
cles-0.118
apult-0.118
aeda-0.116
elaide-0.113
riots-0.113
Token carbon
Token ID6588
Feature activation+1.22e+01

Pos logit contributions
apult+1.831
cles+1.827
aeda+1.811
riots+1.740
elaide+1.735
Neg logit contributions
itized-1.052
olk-1.028
PD-1.028
 reviewer-1.019
agers-1.009
Token emission
Token ID25592
Feature activation+2.16e+00

Pos logit contributions
cles+9.383
apult+9.224
aeda+9.195
nea+8.734
riots+8.587
Neg logit contributions
olk-7.828
itized-7.828
essor-7.739
ansky-7.678
PD-7.647
Token and
Token ID290
Feature activation-3.73e-01

Pos logit contributions
cles+2.020
apult+2.019
aeda+1.996
riots+1.916
elaide+1.908
Neg logit contributions
itized-1.198
olk-1.176
PD-1.171
 reviewer-1.160
essor-1.155
Token climate
Token ID4258
Feature activation+2.00e+00

Pos logit contributions
itized+0.208
PD+0.204
olk+0.204
 reviewer+0.203
 renamed+0.201
Neg logit contributions
apult-0.349
cles-0.348
aeda-0.344
riots-0.331
elaide-0.331
Token change
Token ID1487
Feature activation-5.98e-01

Pos logit contributions
apult+1.945
cles+1.943
aeda+1.920
riots+1.850
elaide+1.847
Neg logit contributions
itized-1.029
olk-1.006
PD-1.004
 reviewer-0.994
agers-0.989
Token-
Token ID12
Feature activation+2.26e+00

Pos logit contributions
itized+0.318
PD+0.314
olk+0.312
 reviewer+0.311
 renamed+0.309
Neg logit contributions
apult-0.572
cles-0.569
aeda-0.564
elaide-0.545
riots-0.544
Token so
Token ID523
Feature activation-1.78e+00

Pos logit contributions
itized+0.335
PD+0.328
olk+0.328
 reviewer+0.327
 renamed+0.324
Neg logit contributions
apult-0.622
cles-0.620
aeda-0.614
elaide-0.592
riots-0.592
Token they
Token ID484
Feature activation-1.38e+00

Pos logit contributions
itized+0.905
PD+0.888
 reviewer+0.887
 renamed+0.884
olk+0.881
Neg logit contributions
apult-1.750
cles-1.740
aeda-1.729
elaide-1.667
riots-1.665
Token censored
Token ID43847
Feature activation-7.90e-01

Pos logit contributions
itized+0.671
PD+0.654
olk+0.654
 reviewer+0.647
agers+0.643
Neg logit contributions
apult-1.392
cles-1.389
aeda-1.374
riots-1.327
elaide-1.324
Token them
Token ID606
Feature activation-1.33e-01

Pos logit contributions
itized+0.391
 reviewer+0.383
PD+0.382
olk+0.379
 renamed+0.377
Neg logit contributions
apult-0.792
cles-0.787
aeda-0.782
riots-0.756
elaide-0.755
Token.
Token ID13
Feature activation-1.82e-01

Pos logit contributions
itized+0.073
PD+0.072
olk+0.072
 reviewer+0.071
 renamed+0.071
Neg logit contributions
apult-0.126
cles-0.126
aeda-0.124
riots-0.120
elaide-0.120
Token Carbon
Token ID23699
Feature activation+1.21e+01

Pos logit contributions
itized+0.098
PD+0.096
olk+0.096
 reviewer+0.095
 renamed+0.094
Neg logit contributions
apult-0.174
cles-0.173
aeda-0.171
elaide-0.165
riots-0.165
Token-
Token ID12
Feature activation+1.58e+00

Pos logit contributions
cles+11.779
aeda+11.719
apult+11.546
nea+11.131
berus+10.954
Neg logit contributions
itized-5.314
 renamed-5.241
stead-5.195
olk-5.187
PD-5.169
Token14
Token ID1415
Feature activation-3.36e-01

Pos logit contributions
apult+1.368
cles+1.367
aeda+1.350
riots+1.296
elaide+1.292
Neg logit contributions
itized-0.983
olk-0.965
PD-0.964
 reviewer-0.959
 renamed-0.951
Token is
Token ID318
Feature activation-2.97e-01

Pos logit contributions
itized+0.177
PD+0.174
olk+0.173
 reviewer+0.173
 renamed+0.171
Neg logit contributions
apult-0.325
cles-0.323
aeda-0.320
elaide-0.309
riots-0.309
Token considered
Token ID3177
Feature activation+1.41e+00

Pos logit contributions
itized+0.156
PD+0.153
olk+0.153
 reviewer+0.151
 renamed+0.150
Neg logit contributions
apult-0.287
cles-0.286
aeda-0.283
riots-0.273
elaide-0.273
Token to
Token ID284
Feature activation-2.37e+00

Pos logit contributions
cles+1.388
apult+1.385
aeda+1.369
elaide+1.316
riots+1.316
Neg logit contributions
itized-0.719
PD-0.702
olk-0.700
 reviewer-0.695
agers-0.691
Token up
Token ID510
Feature activation-3.73e+00

Pos logit contributions
cles+1.116
apult+1.113
aeda+1.099
riots+1.058
elaide+1.057
Neg logit contributions
itized-0.663
PD-0.648
olk-0.648
 reviewer-0.642
agers-0.638
Tokenwell
Token ID4053
Feature activation-2.66e+00

Pos logit contributions
itized+2.884
olk+2.843
PD+2.820
stead+2.799
agers+2.786
Neg logit contributions
apult-2.688
aeda-2.647
cles-2.637
berus-2.526
riots-2.518
Tokenings
Token ID654
Feature activation-8.27e-01

Pos logit contributions
itized+1.492
olk+1.489
PD+1.470
agers+1.461
stead+1.447
Neg logit contributions
apult-2.480
cles-2.456
aeda-2.448
berus-2.353
riots-2.351
Token that
Token ID326
Feature activation+1.68e+00

Pos logit contributions
itized+0.446
PD+0.435
olk+0.435
 reviewer+0.432
 renamed+0.431
Neg logit contributions
apult-0.792
cles-0.785
aeda-0.780
elaide-0.752
riots-0.751
Token recycle
Token ID48914
Feature activation+5.34e+00

Pos logit contributions
cles+1.583
apult+1.580
aeda+1.560
riots+1.501
berus+1.493
Neg logit contributions
itized-0.922
olk-0.908
PD-0.903
 reviewer-0.890
agers-0.887
Token carbon
Token ID6588
Feature activation+1.21e+01

Pos logit contributions
cles+4.773
apult+4.710
aeda+4.636
riots+4.492
elaide+4.492
Neg logit contributions
itized-3.023
essor-2.979
PD-2.978
olk-2.976
 reviewer-2.958
Token absorbed
Token ID19233
Feature activation+2.54e+00

Pos logit contributions
cles+10.126
apult+9.798
aeda+9.650
nea+9.403
elaide+9.315
Neg logit contributions
 reviewer-6.883
essor-6.871
PD-6.693
ansky-6.662
olk-6.654
Token at
Token ID379
Feature activation+2.61e+00

Pos logit contributions
cles+2.308
apult+2.302
aeda+2.270
riots+2.191
elaide+2.183
Neg logit contributions
itized-1.463
PD-1.437
olk-1.434
 reviewer-1.426
agers-1.411
Token higher
Token ID2440
Feature activation+1.15e+00

Pos logit contributions
apult+2.488
cles+2.480
aeda+2.445
riots+2.361
elaide+2.359
Neg logit contributions
itized-1.403
PD-1.375
olk-1.368
 reviewer-1.356
essor-1.342
Token lat
Token ID3042
Feature activation+3.29e+00

Pos logit contributions
apult+1.014
cles+1.013
aeda+1.000
riots+0.960
elaide+0.959
Neg logit contributions
itized-0.696
PD-0.684
olk-0.684
 reviewer-0.677
agers-0.673
Tokenitudes
Token ID10455
Feature activation-1.10e+00

Pos logit contributions
cles+2.353
apult+2.342
aeda+2.295
riots+2.198
elaide+2.179
Neg logit contributions
itized-2.543
olk-2.519
PD-2.490
 renamed-2.479
agers-2.473
Token a
Token ID257
Feature activation-1.02e+00

Pos logit contributions
apult+1.003
cles+1.001
aeda+0.987
riots+0.952
elaide+0.950
Neg logit contributions
itized-0.612
olk-0.598
PD-0.598
 reviewer-0.591
agers-0.587
Token fan
Token ID4336
Feature activation-2.51e+00

Pos logit contributions
itized+0.569
 reviewer+0.561
PD+0.557
olk+0.557
 renamed+0.551
Neg logit contributions
apult-0.951
cles-0.947
aeda-0.940
riots-0.903
berus-0.901
Token holds
Token ID6622
Feature activation-5.12e-01

Pos logit contributions
itized+1.322
 reviewer+1.306
PD+1.305
olk+1.298
agers+1.291
Neg logit contributions
apult-2.408
cles-2.402
aeda-2.399
berus-2.298
elaide-2.287
Token in
Token ID287
Feature activation+6.17e-01

Pos logit contributions
itized+0.270
PD+0.264
olk+0.264
 reviewer+0.263
 renamed+0.261
Neg logit contributions
apult-0.493
cles-0.492
aeda-0.489
berus-0.470
riots-0.470
Token his
Token ID465
Feature activation+4.73e-01

Pos logit contributions
apult+0.580
cles+0.577
aeda+0.572
riots+0.551
elaide+0.549
Neg logit contributions
itized-0.342
olk-0.334
PD-0.334
 reviewer-0.332
agers-0.329
Token heart
Token ID2612
Feature activation+1.19e+01

Pos logit contributions
apult+0.405
cles+0.403
aeda+0.400
riots+0.383
elaide+0.382
Neg logit contributions
itized-0.301
olk-0.296
PD-0.295
 reviewer-0.294
agers-0.292
Token when
Token ID618
Feature activation-1.50e+00

Pos logit contributions
apult+9.963
cles+9.939
elaide+9.451
aeda+9.395
riots+9.281
Neg logit contributions
itized-7.009
PD-6.837
essor-6.831
 renamed-6.810
olk-6.797
Token watching
Token ID4964
Feature activation+2.49e+00

Pos logit contributions
itized+0.796
PD+0.784
 reviewer+0.783
olk+0.779
 renamed+0.772
Neg logit contributions
apult-1.436
cles-1.431
aeda-1.420
berus-1.367
riots-1.362
Token a
Token ID257
Feature activation+7.31e-02

Pos logit contributions
cles+2.393
apult+2.389
aeda+2.360
riots+2.287
elaide+2.278
Neg logit contributions
itized-1.306
olk-1.279
PD-1.269
essor-1.257
stead-1.253
Token sporting
Token ID17702
Feature activation-3.68e+00

Pos logit contributions
apult+0.066
cles+0.066
aeda+0.065
riots+0.063
elaide+0.063
Neg logit contributions
itized-0.043
PD-0.042
olk-0.042
 reviewer-0.042
 renamed-0.041
Token contest
Token ID8414
Feature activation-2.33e+00

Pos logit contributions
itized+1.980
 reviewer+1.934
PD+1.925
 renamed+1.910
olk+1.902
Neg logit contributions
cles-3.508
apult-3.497
aeda-3.487
berus-3.349
riots-3.304
Token Pearce
Token ID41902
Feature activation+2.32e+00

Pos logit contributions
apult+9.203
cles+9.183
aeda+8.878
riots+8.735
elaide+8.667
Neg logit contributions
itized-6.015
olk-5.738
agers-5.670
essor-5.647
 renamed-5.604
Token at
Token ID379
Feature activation+4.78e+00

Pos logit contributions
apult+2.189
cles+2.182
aeda+2.159
riots+2.078
elaide+2.075
Neg logit contributions
itized-1.280
PD-1.251
olk-1.250
 reviewer-1.240
agers-1.231
Token An
Token ID1052
Feature activation+2.07e+00

Pos logit contributions
apult+4.330
cles+4.240
aeda+4.192
riots+4.066
elaide+4.058
Neg logit contributions
itized-2.799
essor-2.702
olk-2.699
agers-2.697
PD-2.674
Token Evening
Token ID31867
Feature activation-1.76e+00

Pos logit contributions
apult+1.865
cles+1.860
aeda+1.835
riots+1.767
elaide+1.762
Neg logit contributions
itized-1.219
olk-1.201
PD-1.198
 reviewer-1.190
 renamed-1.182
Token with
Token ID351
Feature activation+1.30e-01

Pos logit contributions
itized+0.946
PD+0.927
olk+0.927
 reviewer+0.923
stead+0.913
Neg logit contributions
cles-1.692
aeda-1.674
apult-1.660
berus-1.614
riots-1.600
Token Conor
Token ID41708
Feature activation+1.19e+01

Pos logit contributions
apult+0.116
cles+0.115
aeda+0.114
berus+0.109
riots+0.109
Neg logit contributions
itized-0.078
PD-0.077
 reviewer-0.077
olk-0.077
 renamed-0.076
Token McGregor
Token ID32777
Feature activation+7.88e+00

Pos logit contributions
apult+9.022
cles+8.876
aeda+8.799
riots+8.547
elaide+8.320
Neg logit contributions
itized-8.040
essor-7.865
olk-7.825
agers-7.806
 reviewer-7.675
Token at
Token ID379
Feature activation+4.89e+00

Pos logit contributions
apult+6.983
cles+6.847
aeda+6.762
elaide+6.548
riots+6.530
Neg logit contributions
itized-4.569
essor-4.426
olk-4.415
agers-4.414
PD-4.375
Token the
Token ID262
Feature activation+2.10e+00

Pos logit contributions
apult+4.346
cles+4.272
aeda+4.208
riots+4.088
elaide+4.061
Neg logit contributions
itized-2.913
essor-2.849
olk-2.825
agers-2.820
PD-2.800
Token SEC
Token ID10729
Feature activation-1.04e+00

Pos logit contributions
apult+1.897
cles+1.887
aeda+1.864
riots+1.795
elaide+1.790
Neg logit contributions
itized-1.232
olk-1.207
PD-1.204
 reviewer-1.194
agers-1.189
Token Arm
Token ID7057
Feature activation+2.14e+00

Pos logit contributions
itized+0.554
PD+0.553
olk+0.545
 reviewer+0.542
 renamed+0.536
Neg logit contributions
cles-0.994
apult-0.992
aeda-0.985
riots-0.946
berus-0.944
Token in
Token ID287
Feature activation+1.77e+00

Pos logit contributions
itized+0.239
PD+0.236
olk+0.236
 reviewer+0.234
 renamed+0.232
Neg logit contributions
apult-0.393
cles-0.392
aeda-0.390
berus-0.375
riots-0.375
Token 2013
Token ID2211
Feature activation-7.29e-01

Pos logit contributions
apult+1.732
cles+1.727
aeda+1.709
riots+1.649
elaide+1.646
Neg logit contributions
itized-0.905
PD-0.887
olk-0.886
 reviewer-0.878
agers-0.871
Token.
Token ID13
Feature activation+7.80e-01

Pos logit contributions
itized+0.390
olk+0.388
PD+0.387
 reviewer+0.383
 renamed+0.381
Neg logit contributions
cles-0.691
aeda-0.690
apult-0.689
berus-0.660
riots-0.659
Token
Token ID198
Feature activation+1.95e-01

Pos logit contributions
apult+0.812
cles+0.810
aeda+0.802
riots+0.775
elaide+0.774
Neg logit contributions
itized-0.352
PD-0.344
olk-0.343
 reviewer-0.340
agers-0.336
Token
Token ID198
Feature activation+7.25e-01

Pos logit contributions
cles+0.202
apult+0.202
aeda+0.199
riots+0.193
berus+0.193
Neg logit contributions
itized-0.088
olk-0.085
 reviewer-0.085
PD-0.084
essor-0.084
TokenCar
Token ID9914
Feature activation+1.18e+01

Pos logit contributions
apult+0.663
cles+0.661
aeda+0.653
riots+0.629
elaide+0.626
Neg logit contributions
itized-0.419
olk-0.410
PD-0.409
 reviewer-0.408
 renamed-0.404
Tokenla
Token ID5031
Feature activation+6.67e-02

Pos logit contributions
cles+9.472
apult+9.263
aeda+9.178
nea+8.962
riots+8.850
Neg logit contributions
 renamed-7.219
itized-7.123
PD-7.106
 reviewer-7.069
essor-7.061
Token del
Token ID1619
Feature activation-1.71e+00

Pos logit contributions
apult+0.061
cles+0.061
aeda+0.060
riots+0.058
elaide+0.058
Neg logit contributions
itized-0.038
PD-0.038
olk-0.038
 reviewer-0.037
agers-0.037
Token P
Token ID350
Feature activation+4.14e-01

Pos logit contributions
itized+0.966
PD+0.959
olk+0.947
agers+0.939
 reviewer+0.938
Neg logit contributions
apult-1.588
cles-1.581
aeda-1.557
elaide-1.507
berus-1.504
Tokenonte
Token ID38599
Feature activation-8.57e-01

Pos logit contributions
apult+0.421
cles+0.420
aeda+0.416
riots+0.402
elaide+0.401
Neg logit contributions
itized-0.196
olk-0.192
PD-0.192
 reviewer-0.189
agers-0.188
Token,
Token ID11
Feature activation+1.12e+00

Pos logit contributions
itized+0.434
PD+0.428
olk+0.426
 reviewer+0.423
 renamed+0.421
Neg logit contributions
apult-0.842
cles-0.838
aeda-0.833
elaide-0.804
berus-0.803
Token (
Token ID357
Feature activation-6.48e-02

Pos logit contributions
apult+0.247
cles+0.247
aeda+0.244
riots+0.236
elaide+0.235
Neg logit contributions
itized-0.127
PD-0.124
olk-0.124
 reviewer-0.123
agers-0.122
TokenPhoto
Token ID6191
Feature activation-3.60e-01

Pos logit contributions
itized+0.041
PD+0.041
olk+0.040
 reviewer+0.040
stead+0.039
Neg logit contributions
apult-0.056
cles-0.056
aeda-0.055
elaide-0.053
riots-0.053
Token by
Token ID416
Feature activation+9.48e-01

Pos logit contributions
itized+0.200
PD+0.196
olk+0.196
 reviewer+0.195
agers+0.193
Neg logit contributions
apult-0.338
cles-0.337
aeda-0.334
riots-0.321
elaide-0.320
Token REUTERS
Token ID15862
Feature activation+3.69e+00

Pos logit contributions
apult+0.841
cles+0.839
aeda+0.829
riots+0.796
elaide+0.794
Neg logit contributions
itized-0.574
olk-0.563
PD-0.563
 reviewer-0.558
agers-0.554
Token/
Token ID14
Feature activation+2.98e+00

Pos logit contributions
apult+4.208
cles+4.195
aeda+4.143
berus+4.020
riots+4.005
Neg logit contributions
itized-1.254
olk-1.190
 reviewer-1.186
essor-1.162
agers-1.147
TokenCar
Token ID9914
Feature activation+1.17e+01

Pos logit contributions
cles+2.499
apult+2.496
aeda+2.464
riots+2.358
berus+2.349
Neg logit contributions
itized-1.934
olk-1.909
 reviewer-1.897
PD-1.880
agers-1.879
Tokenlo
Token ID5439
Feature activation-1.39e+00

Pos logit contributions
apult+8.515
cles+8.464
nea+8.295
aeda+7.992
riots+7.953
Neg logit contributions
essor-7.946
 renamed-7.898
iciency-7.784
ansky-7.669
PD-7.646
Token Alleg
Token ID26326
Feature activation-2.60e+00

Pos logit contributions
itized+0.853
olk+0.841
 reviewer+0.833
 renamed+0.827
essor+0.823
Neg logit contributions
apult-1.225
cles-1.219
aeda-1.211
riots-1.163
berus-1.150
Tokenri
Token ID380
Feature activation-9.39e-01

Pos logit contributions
itized+2.034
olk+2.021
 renamed+1.992
PD+1.988
stead+1.986
Neg logit contributions
apult-1.850
cles-1.810
aeda-1.787
elaide-1.728
berus-1.713
Token)
Token ID8
Feature activation+1.68e+00

Pos logit contributions
itized+0.319
PD+0.311
olk+0.311
 reviewer+0.303
agers+0.302
Neg logit contributions
apult-1.081
cles-1.078
aeda-1.071
elaide-1.038
riots-1.037
Token Michael
Token ID3899
Feature activation+3.93e+00

Pos logit contributions
apult+1.501
cles+1.495
aeda+1.479
riots+1.421
berus+1.415
Neg logit contributions
itized-1.012
olk-0.988
PD-0.984
 reviewer-0.979
agers-0.975
Tokentask
Token ID35943
Feature activation-7.21e-02

Pos logit contributions
apult+2.102
cles+2.092
aeda+2.060
riots+1.986
elaide+1.981
Neg logit contributions
itized-1.400
 reviewer-1.392
olk-1.390
PD-1.383
agers-1.366
Tokened
Token ID276
Feature activation+4.38e-01

Pos logit contributions
itized+0.059
PD+0.058
olk+0.058
 reviewer+0.057
 renamed+0.057
Neg logit contributions
apult-0.049
cles-0.049
aeda-0.048
riots-0.046
elaide-0.046
Token to
Token ID284
Feature activation-1.02e+00

Pos logit contributions
apult+0.421
cles+0.420
aeda+0.416
riots+0.401
elaide+0.400
Neg logit contributions
itized-0.233
PD-0.228
olk-0.227
 reviewer-0.225
 renamed-0.224
Token fly
Token ID6129
Feature activation-1.44e-01

Pos logit contributions
itized+0.585
PD+0.574
 reviewer+0.573
olk+0.570
 renamed+0.569
Neg logit contributions
apult-0.940
cles-0.937
aeda-0.927
riots-0.895
elaide-0.893
Token by
Token ID416
Feature activation+2.17e+00

Pos logit contributions
itized+0.082
PD+0.080
olk+0.079
 reviewer+0.079
 renamed+0.079
Neg logit contributions
apult-0.133
cles-0.133
aeda-0.131
riots-0.127
elaide-0.126
Token comet
Token ID31733
Feature activation+1.16e+01

Pos logit contributions
apult+2.004
cles+1.996
aeda+1.978
riots+1.900
berus+1.896
Neg logit contributions
itized-1.220
olk-1.196
PD-1.193
 reviewer-1.179
agers-1.172
Token 19
Token ID678
Feature activation+8.70e-02

Pos logit contributions
apult+9.621
cles+9.551
aeda+9.460
berus+9.121
riots+8.946
Neg logit contributions
olk-6.590
itized-6.584
essor-6.394
iciency-6.351
PD-6.313
TokenP
Token ID47
Feature activation+2.43e+00

Pos logit contributions
apult+0.086
cles+0.086
aeda+0.085
riots+0.082
elaide+0.082
Neg logit contributions
itized-0.044
PD-0.043
olk-0.043
 reviewer-0.042
 renamed-0.042
Token/
Token ID14
Feature activation+3.06e+00

Pos logit contributions
apult+2.914
cles+2.906
aeda+2.885
riots+2.798
elaide+2.796
Neg logit contributions
itized-0.705
olk-0.673
PD-0.668
 reviewer-0.663
agers-0.655
TokenB
Token ID33
Feature activation+6.04e+00

Pos logit contributions
cles+2.723
apult+2.722
aeda+2.688
riots+2.581
berus+2.573
Neg logit contributions
itized-1.834
 reviewer-1.788
olk-1.786
PD-1.768
agers-1.767
Tokenor
Token ID273
Feature activation+2.55e+00

Pos logit contributions
cles+5.532
aeda+5.492
apult+5.487
riots+5.266
elaide+5.243
Neg logit contributions
itized-3.356
 reviewer-3.297
 renamed-3.270
PD-3.217
agers-3.204
Token iron
Token ID6953
Feature activation+5.78e+00

Pos logit contributions
itized+0.797
olk+0.778
PD+0.776
 reviewer+0.770
agers+0.768
Neg logit contributions
apult-1.358
cles-1.352
aeda-1.338
riots-1.291
elaide-1.288
Token rod
Token ID15299
Feature activation+1.89e+00

Pos logit contributions
cles+5.464
apult+5.445
aeda+5.320
elaide+5.211
berus+5.171
Neg logit contributions
itized-3.007
PD-2.966
essor-2.938
 reviewer-2.920
ansky-2.913
Token enc
Token ID2207
Feature activation+2.21e+00

Pos logit contributions
apult+1.812
cles+1.809
aeda+1.788
riots+1.722
elaide+1.719
Neg logit contributions
itized-1.005
PD-0.984
olk-0.983
 reviewer-0.975
agers-0.967
Tokenased
Token ID839
Feature activation+1.87e+00

Pos logit contributions
apult+1.445
cles+1.437
aeda+1.411
elaide+1.338
riots+1.336
Neg logit contributions
itized-1.842
PD-1.825
 reviewer-1.823
olk-1.822
 renamed-1.798
Token in
Token ID287
Feature activation+3.82e-01

Pos logit contributions
apult+1.806
cles+1.798
aeda+1.781
riots+1.717
elaide+1.713
Neg logit contributions
itized-0.983
olk-0.960
PD-0.959
 reviewer-0.952
 renamed-0.944
Token copper
Token ID15317
Feature activation+1.15e+01

Pos logit contributions
apult+0.382
cles+0.381
aeda+0.377
riots+0.364
elaide+0.363
Neg logit contributions
itized-0.189
olk-0.184
PD-0.184
 reviewer-0.182
 renamed-0.181
Token and
Token ID290
Feature activation+9.56e-01

Pos logit contributions
cles+9.722
apult+9.220
aeda+9.000
nea+8.948
berus+8.921
Neg logit contributions
essor-6.753
itized-6.584
ansky-6.541
PD-6.512
 reviewer-6.495
Token dated
Token ID14567
Feature activation+2.27e+00

Pos logit contributions
cles+0.908
apult+0.907
aeda+0.896
riots+0.863
elaide+0.861
Neg logit contributions
itized-0.517
PD-0.507
olk-0.506
 reviewer-0.501
agers-0.498
Token from
Token ID422
Feature activation-1.85e+00

Pos logit contributions
cles+2.110
apult+2.102
aeda+2.079
riots+1.999
elaide+1.986
Neg logit contributions
itized-1.257
olk-1.246
PD-1.245
 reviewer-1.230
agers-1.222
Token about
Token ID546
Feature activation-1.68e-01

Pos logit contributions
itized+1.015
olk+0.993
PD+0.988
 renamed+0.988
agers+0.987
Neg logit contributions
apult-1.741
cles-1.729
aeda-1.714
elaide-1.661
riots-1.656
Token 200
Token ID939
Feature activation+2.68e-01

Pos logit contributions
itized+0.095
PD+0.093
olk+0.093
 reviewer+0.092
agers+0.091
Neg logit contributions
apult-0.156
cles-0.155
aeda-0.153
riots-0.148
elaide-0.147
Token determine
Token ID5004
Feature activation+1.74e+00

Pos logit contributions
itized+1.476
PD+1.461
 reviewer+1.458
olk+1.450
 renamed+1.436
Neg logit contributions
apult-2.449
cles-2.431
aeda-2.415
elaide-2.330
riots-2.327
Token the
Token ID262
Feature activation-5.89e-01

Pos logit contributions
cles+1.695
apult+1.688
aeda+1.669
riots+1.609
berus+1.598
Neg logit contributions
itized-0.903
olk-0.887
PD-0.882
essor-0.867
stead-0.865
Token social
Token ID1919
Feature activation-7.31e+00

Pos logit contributions
itized+0.328
PD+0.321
 reviewer+0.320
olk+0.320
 renamed+0.317
Neg logit contributions
apult-0.553
cles-0.550
aeda-0.544
elaide-0.525
riots-0.525
Token costs
Token ID3484
Feature activation+2.40e+00

Pos logit contributions
itized+3.279
 reviewer+3.253
 renamed+3.162
 matter+3.148
agers+3.071
Neg logit contributions
apult-7.571
aeda-7.454
cles-7.329
elaide-7.190
riots-7.136
Token of
Token ID286
Feature activation+7.23e-01

Pos logit contributions
apult+2.211
cles+2.209
aeda+2.183
riots+2.099
elaide+2.094
Neg logit contributions
itized-1.366
olk-1.339
PD-1.338
 reviewer-1.325
agers-1.317
Token carbon
Token ID6588
Feature activation+1.14e+01

Pos logit contributions
apult+0.683
cles+0.682
aeda+0.674
riots+0.649
berus+0.647
Neg logit contributions
itized-0.395
olk-0.387
PD-0.386
 reviewer-0.382
agers-0.379
Token.
Token ID13
Feature activation-2.54e-01

Pos logit contributions
cles+9.868
aeda+9.469
apult+9.427
nea+9.125
riots+9.058
Neg logit contributions
essor-6.761
ansky-6.679
olk-6.671
itized-6.642
PD-6.512
Token
Token ID198
Feature activation-1.29e+00

Pos logit contributions
itized+0.128
PD+0.126
olk+0.125
 reviewer+0.124
 renamed+0.123
Neg logit contributions
apult-0.251
cles-0.250
aeda-0.247
elaide-0.239
riots-0.239
Token
Token ID198
Feature activation-8.26e-01

Pos logit contributions
itized+0.545
olk+0.530
PD+0.530
 reviewer+0.525
agers+0.519
Neg logit contributions
apult-1.374
cles-1.371
aeda-1.357
riots-1.313
elaide-1.310
TokenSh
Token ID2484
Feature activation-5.17e-01

Pos logit contributions
itized+0.486
PD+0.481
olk+0.475
 reviewer+0.469
agers+0.469
Neg logit contributions
apult-0.749
cles-0.744
aeda-0.739
elaide-0.713
riots-0.708
Tokenind
Token ID521
Feature activation-4.28e+00

Pos logit contributions
itized+0.248
PD+0.242
olk+0.242
 reviewer+0.240
agers+0.237
Neg logit contributions
apult-0.523
cles-0.522
aeda-0.516
riots-0.499
elaide-0.498
Token 1
Token ID352
Feature activation-3.73e+00

Pos logit contributions
itized+0.585
olk+0.577
PD+0.576
 reviewer+0.573
agers+0.570
Neg logit contributions
apult-0.536
cles-0.534
aeda-0.527
riots-0.501
elaide-0.500
Token was
Token ID373
Feature activation-5.64e-01

Pos logit contributions
itized+1.925
PD+1.908
 reviewer+1.877
 renamed+1.875
olk+1.842
Neg logit contributions
cles-3.610
apult-3.607
aeda-3.577
riots-3.451
elaide-3.445
Token intended
Token ID5292
Feature activation+3.09e-02

Pos logit contributions
itized+0.291
PD+0.284
olk+0.284
 reviewer+0.281
 renamed+0.280
Neg logit contributions
apult-0.552
cles-0.550
aeda-0.545
riots-0.526
elaide-0.524
Token to
Token ID284
Feature activation-8.90e-01

Pos logit contributions
apult+0.030
cles+0.030
aeda+0.030
riots+0.029
berus+0.029
Neg logit contributions
itized-0.016
olk-0.015
PD-0.015
 reviewer-0.015
 renamed-0.015
Token visit
Token ID3187
Feature activation+2.57e+00

Pos logit contributions
itized+0.510
PD+0.500
olk+0.500
 reviewer+0.499
 renamed+0.494
Neg logit contributions
apult-0.817
cles-0.817
aeda-0.808
riots-0.778
elaide-0.776
Token comet
Token ID31733
Feature activation+1.14e+01

Pos logit contributions
apult+2.393
cles+2.388
aeda+2.366
riots+2.275
berus+2.271
Neg logit contributions
itized-1.428
olk-1.399
PD-1.398
 reviewer-1.386
essor-1.370
Token 76
Token ID8684
Feature activation-7.77e-01

Pos logit contributions
cles+9.507
apult+9.398
aeda+9.120
berus+9.057
riots+8.838
Neg logit contributions
essor-6.553
olk-6.400
iciency-6.392
itized-6.389
 reviewer-6.363
TokenP
Token ID47
Feature activation+3.32e+00

Pos logit contributions
itized+0.416
PD+0.412
olk+0.406
 renamed+0.403
 reviewer+0.400
Neg logit contributions
apult-0.744
cles-0.742
aeda-0.732
riots-0.710
elaide-0.709
Token/
Token ID14
Feature activation+3.41e+00

Pos logit contributions
apult+3.798
cles+3.790
aeda+3.770
riots+3.641
elaide+3.635
Neg logit contributions
itized-1.135
olk-1.088
 reviewer-1.079
PD-1.071
agers-1.066
TokenWest
Token ID15045
Feature activation+2.67e-02

Pos logit contributions
cles+3.129
apult+3.126
aeda+3.085
berus+2.969
riots+2.968
Neg logit contributions
itized-1.940
 reviewer-1.896
olk-1.888
agers-1.865
essor-1.864
Token
Token ID1906
Feature activation+2.99e+00

Pos logit contributions
apult+0.024
cles+0.024
aeda+0.024
riots+0.023
elaide+0.023
Neg logit contributions
itized-0.015
PD-0.015
olk-0.015
 reviewer-0.015
agers-0.015
Token or
Token ID393
Feature activation+1.34e+00

Pos logit contributions
apult+0.512
cles+0.509
aeda+0.505
riots+0.486
elaide+0.486
Neg logit contributions
itized-0.277
PD-0.271
olk-0.271
 reviewer-0.269
agers-0.267
Token the
Token ID262
Feature activation+6.70e-02

Pos logit contributions
cles+1.236
apult+1.234
aeda+1.217
riots+1.173
berus+1.167
Neg logit contributions
itized-0.764
PD-0.748
olk-0.747
 reviewer-0.740
agers-0.735
Token Egyptians
Token ID32658
Feature activation+1.28e+00

Pos logit contributions
apult+0.062
cles+0.061
aeda+0.061
riots+0.058
elaide+0.058
Neg logit contributions
itized-0.038
olk-0.038
PD-0.038
 reviewer-0.037
agers-0.037
Token or
Token ID393
Feature activation+2.37e+00

Pos logit contributions
apult+1.233
cles+1.231
aeda+1.217
riots+1.173
elaide+1.170
Neg logit contributions
itized-0.669
PD-0.655
olk-0.652
 reviewer-0.647
agers-0.642
Token the
Token ID262
Feature activation+8.51e-01

Pos logit contributions
cles+2.199
apult+2.182
aeda+2.155
riots+2.091
berus+2.072
Neg logit contributions
itized-1.329
olk-1.300
PD-1.299
 reviewer-1.279
stead-1.268
Token Cy
Token ID5934
Feature activation+1.13e+01

Pos logit contributions
apult+0.769
cles+0.769
aeda+0.758
riots+0.731
berus+0.728
Neg logit contributions
itized-0.500
PD-0.489
olk-0.487
 reviewer-0.483
agers-0.479
Tokenpri
Token ID3448
Feature activation-5.14e+00

Pos logit contributions
cles+7.731
apult+7.122
prus+7.056
aeda+7.029
riots+6.731
Neg logit contributions
itized-9.188
 reviewer-8.857
PD-8.661
 renamed-8.628
essor-8.569
Tokenots
Token ID1747
Feature activation-1.42e+00

Pos logit contributions
itized+2.856
olk+2.772
agers+2.758
PD+2.736
ansky+2.664
Neg logit contributions
aeda-4.852
apult-4.804
cles-4.726
elaide-4.691
berus-4.564
Token they
Token ID484
Feature activation-1.06e+00

Pos logit contributions
itized+0.676
olk+0.666
PD+0.659
 reviewer+0.656
agers+0.652
Neg logit contributions
apult-1.447
cles-1.436
aeda-1.432
berus-1.381
elaide-1.378
Token weren
Token ID6304
Feature activation+1.68e-01

Pos logit contributions
itized+0.590
PD+0.577
olk+0.576
 reviewer+0.572
agers+0.568
Neg logit contributions
apult-0.993
cles-0.992
aeda-0.980
riots-0.943
elaide-0.941
Token't
Token ID470
Feature activation+3.21e+00

Pos logit contributions
apult+0.141
cles+0.141
aeda+0.139
riots+0.133
elaide+0.133
Neg logit contributions
itized-0.110
olk-0.108
PD-0.108
 reviewer-0.108
agers-0.107
Token
Token ID447
Feature activation-1.56e+00

Pos logit contributions
itized+0.084
PD+0.083
olk+0.083
 reviewer+0.082
 renamed+0.081
Neg logit contributions
cles-0.198
apult-0.197
aeda-0.195
elaide-0.189
riots-0.189
Token
Token ID251
Feature activation-1.38e+00

Pos logit contributions
itized+0.516
olk+0.504
PD+0.499
 reviewer+0.494
 renamed+0.477
Neg logit contributions
apult-1.821
cles-1.805
aeda-1.787
elaide-1.744
riots-1.744
Token<|endoftext|>
Token ID50256
Feature activation+1.11e-01

Pos logit contributions
itized+0.592
PD+0.587
olk+0.579
 reviewer+0.573
 renamed+0.565
Neg logit contributions
cles-1.456
apult-1.456
aeda-1.448
elaide-1.405
riots-1.398
TokenWH
Token ID12418
Feature activation+4.95e-01

Pos logit contributions
apult+0.098
cles+0.098
aeda+0.097
elaide+0.093
riots+0.093
Neg logit contributions
itized-0.068
PD-0.067
olk-0.066
 reviewer-0.066
agers-0.066
TokenEN
Token ID1677
Feature activation-1.88e+00

Pos logit contributions
apult+0.472
cles+0.471
aeda+0.466
riots+0.449
elaide+0.448
Neg logit contributions
itized-0.266
PD-0.261
olk-0.260
 reviewer-0.258
agers-0.256
Token Catherine
Token ID22578
Feature activation+1.13e+01

Pos logit contributions
itized+1.009
 reviewer+0.998
PD+0.998
olk+0.986
 renamed+0.984
Neg logit contributions
apult-1.796
cles-1.785
aeda-1.771
berus-1.704
elaide-1.701
Token Mull
Token ID19574
Feature activation-7.39e+00

Pos logit contributions
cles+9.662
apult+9.564
aeda+9.310
riots+9.146
nea+9.043
Neg logit contributions
itized-6.510
essor-6.185
olk-6.170
PD-6.031
 reviewer-6.009
Tokenigan
Token ID5516
Feature activation-2.23e+00

Pos logit contributions
stead+3.421
olk+3.407
ield+3.386
itized+3.373
agers+3.369
Neg logit contributions
apult-7.301
cles-7.255
aeda-7.151
berus-7.090
riots-7.019
Token,
Token ID11
Feature activation+4.85e-01

Pos logit contributions
itized+1.166
PD+1.151
 renamed+1.145
olk+1.145
 reviewer+1.144
Neg logit contributions
apult-2.150
cles-2.136
aeda-2.133
berus-2.055
riots-2.049
Token a
Token ID257
Feature activation-5.84e-01

Pos logit contributions
apult+0.465
cles+0.464
aeda+0.460
riots+0.443
elaide+0.442
Neg logit contributions
itized-0.258
PD-0.253
olk-0.252
 reviewer-0.251
 renamed-0.248
Token part
Token ID636
Feature activation-5.02e+00

Pos logit contributions
itized+0.331
 reviewer+0.330
PD+0.328
olk+0.326
 renamed+0.325
Neg logit contributions
apult-0.539
cles-0.536
aeda-0.532
riots-0.511
elaide-0.509
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
itized+1.500
olk+1.480
PD+1.457
agers+1.445
stead+1.440
Neg logit contributions
apult-2.827
aeda-2.819
cles-2.813
elaide-2.725
riots-2.702
Token<|endoftext|>
Token ID50256
Feature activation-6.12e-03

Pos logit contributions
itized+0.072
olk+0.071
PD+0.071
 reviewer+0.069
agers+0.069
Neg logit contributions
apult-0.177
cles-0.176
aeda-0.175
riots-0.170
elaide-0.169
TokenWASHINGTON
Token ID21793
Feature activation+1.92e+00

Pos logit contributions
itized+0.004
PD+0.004
olk+0.004
 reviewer+0.004
agers+0.004
Neg logit contributions
apult-0.005
cles-0.005
aeda-0.005
elaide-0.005
riots-0.005
Token
Token ID851
Feature activation+1.88e-03

Pos logit contributions
apult+1.822
cles+1.818
aeda+1.794
riots+1.729
elaide+1.726
Neg logit contributions
itized-1.043
olk-1.014
 reviewer-1.008
PD-1.008
agers-1.002
Token A
Token ID317
Feature activation+1.49e+00

Pos logit contributions
apult+0.002
cles+0.002
aeda+0.002
elaide+0.002
riots+0.002
Neg logit contributions
itized-0.001
PD-0.001
olk-0.001
 reviewer-0.001
 renamed-0.001
Token Cy
Token ID5934
Feature activation+1.12e+01

Pos logit contributions
apult+1.370
cles+1.366
aeda+1.351
riots+1.299
elaide+1.297
Neg logit contributions
itized-0.860
PD-0.843
olk-0.843
 reviewer-0.836
agers-0.830
Tokengn
Token ID4593
Feature activation-4.09e+00

Pos logit contributions
cles+8.572
apult+7.998
aeda+7.987
prus+7.884
riots+7.762
Neg logit contributions
itized-7.993
 reviewer-7.792
olk-7.750
essor-7.746
agers-7.696
Tokenus
Token ID385
Feature activation-6.70e-01

Pos logit contributions
itized+1.895
olk+1.834
PD+1.806
essor+1.793
agers+1.782
Neg logit contributions
cles-4.194
apult-4.193
aeda-4.145
elaide-4.021
riots-4.006
Token cargo
Token ID15892
Feature activation+3.24e+00

Pos logit contributions
itized+0.370
PD+0.363
olk+0.361
 reviewer+0.360
 renamed+0.358
Neg logit contributions
apult-0.630
cles-0.627
aeda-0.622
elaide-0.599
riots-0.599
Token mission
Token ID4365
Feature activation-1.14e+00

Pos logit contributions
apult+2.515
cles+2.500
aeda+2.455
riots+2.359
elaide+2.357
Neg logit contributions
itized-2.307
olk-2.247
PD-2.225
essor-2.210
 reviewer-2.208
Token to
Token ID284
Feature activation-9.67e-01

Pos logit contributions
itized+0.616
PD+0.600
olk+0.599
 renamed+0.599
 reviewer+0.599
Neg logit contributions
apult-1.088
cles-1.084
aeda-1.077
riots-1.038
elaide-1.037
Token Block
Token ID9726
Feature activation+7.32e-01

Pos logit contributions
itized+1.203
olk+1.184
PD+1.184
 reviewer+1.177
agers+1.170
Neg logit contributions
apult-1.050
cles-1.049
aeda-1.035
riots-0.983
elaide-0.977
Token did
Token ID750
Feature activation-3.94e-01

Pos logit contributions
apult+0.702
cles+0.700
aeda+0.693
riots+0.668
elaide+0.666
Neg logit contributions
itized-0.390
PD-0.382
olk-0.381
 reviewer-0.378
agers-0.375
Token you
Token ID345
Feature activation-1.63e-01

Pos logit contributions
itized+0.200
PD+0.196
olk+0.196
 reviewer+0.195
 renamed+0.193
Neg logit contributions
apult-0.387
cles-0.386
aeda-0.382
riots-0.368
elaide-0.368
Token have
Token ID423
Feature activation-6.23e-03

Pos logit contributions
itized+0.098
PD+0.096
olk+0.096
 reviewer+0.095
essor+0.094
Neg logit contributions
apult-0.146
cles-0.145
aeda-0.143
riots-0.138
elaide-0.138
Token a
Token ID257
Feature activation+1.23e+00

Pos logit contributions
itized+0.003
olk+0.003
PD+0.003
 reviewer+0.003
agers+0.003
Neg logit contributions
cles-0.006
apult-0.006
aeda-0.006
riots-0.006
elaide-0.006
Token blueprint
Token ID30881
Feature activation+1.12e+01

Pos logit contributions
cles+1.144
apult+1.141
aeda+1.126
riots+1.085
elaide+1.081
Neg logit contributions
itized-0.686
olk-0.672
PD-0.668
agers-0.662
essor-0.658
Token for
Token ID329
Feature activation+1.02e+00

Pos logit contributions
apult+9.068
cles+9.019
aeda+8.524
riots+8.323
nea+8.154
Neg logit contributions
olk-6.872
itized-6.687
agers-6.599
PD-6.542
iciency-6.493
Token the
Token ID262
Feature activation-1.36e-01

Pos logit contributions
apult+0.963
cles+0.961
aeda+0.953
riots+0.917
berus+0.909
Neg logit contributions
itized-0.555
olk-0.545
PD-0.540
 reviewer-0.533
essor-0.530
Token way
Token ID835
Feature activation-1.59e+00

Pos logit contributions
itized+0.077
PD+0.075
olk+0.075
 reviewer+0.074
agers+0.074
Neg logit contributions
apult-0.125
cles-0.125
aeda-0.124
riots-0.119
elaide-0.118
Token you
Token ID345
Feature activation-9.35e-01

Pos logit contributions
itized+0.746
PD+0.730
olk+0.727
 reviewer+0.725
agers+0.716
Neg logit contributions
apult-1.625
cles-1.619
aeda-1.602
elaide-1.551
riots-1.548
Token wanted
Token ID2227
Feature activation+5.50e-01

Pos logit contributions
itized+0.548
olk+0.536
PD+0.535
 reviewer+0.531
agers+0.527
Neg logit contributions
cles-0.846
apult-0.846
aeda-0.837
riots-0.804
elaide-0.800
Token applies
Token ID8991
Feature activation-1.14e+00

Pos logit contributions
apult+0.876
cles+0.875
aeda+0.863
riots+0.832
elaide+0.828
Neg logit contributions
itized-0.549
PD-0.539
olk-0.539
 reviewer-0.533
 renamed-0.530
Token to
Token ID284
Feature activation-2.18e+00

Pos logit contributions
itized+0.585
PD+0.575
olk+0.569
 reviewer+0.568
 renamed+0.562
Neg logit contributions
apult-1.127
cles-1.121
aeda-1.112
berus-1.076
riots-1.072
Token humans
Token ID5384
Feature activation+3.02e+00

Pos logit contributions
itized+1.085
PD+1.061
 reviewer+1.053
olk+1.053
 renamed+1.042
Neg logit contributions
apult-2.185
cles-2.174
aeda-2.155
elaide-2.079
riots-2.075
Token.
Token ID13
Feature activation-7.88e-01

Pos logit contributions
cles+2.706
apult+2.690
aeda+2.655
elaide+2.557
riots+2.553
Neg logit contributions
itized-1.773
PD-1.742
olk-1.742
 reviewer-1.729
essor-1.716
Token Mi
Token ID13756
Feature activation-3.23e+00

Pos logit contributions
itized+0.364
PD+0.354
olk+0.354
 reviewer+0.351
agers+0.347
Neg logit contributions
apult-0.813
cles-0.811
aeda-0.803
riots-0.776
elaide-0.774
Tokenikk
Token ID36073
Feature activation-1.28e+01

Pos logit contributions
itized+2.353
olk+2.348
PD+2.344
agers+2.311
stead+2.291
Neg logit contributions
apult-2.440
cles-2.413
aeda-2.389
riots-2.296
elaide-2.288
Tokenul
Token ID377
Feature activation-4.23e+00

Pos logit contributions
olk+7.728
ansky+7.633
essor+7.623
agers+7.590
ield+7.484
Neg logit contributions
apult-10.305
cles-10.169
nces-9.971
berus-9.734
aeda-9.675
Tokenain
Token ID391
Feature activation-4.60e-01

Pos logit contributions
itized+2.319
olk+2.296
PD+2.253
agers+2.251
 renamed+2.247
Neg logit contributions
apult-3.953
cles-3.932
aeda-3.907
elaide-3.772
berus-3.763
Tokenen
Token ID268
Feature activation+1.25e-01

Pos logit contributions
itized+0.154
PD+0.149
olk+0.148
 reviewer+0.146
agers+0.144
Neg logit contributions
apult-0.534
cles-0.532
aeda-0.527
riots-0.512
elaide-0.511
Token and
Token ID290
Feature activation+1.66e-01

Pos logit contributions
apult+0.117
cles+0.117
aeda+0.115
riots+0.111
elaide+0.110
Neg logit contributions
itized-0.070
PD-0.068
olk-0.068
 reviewer-0.067
agers-0.067
Token Hoffman
Token ID29010
Feature activation-3.80e+00

Pos logit contributions
apult+0.151
cles+0.150
aeda+0.149
riots+0.143
elaide+0.143
Neg logit contributions
itized-0.098
PD-0.096
olk-0.095
 reviewer-0.095
agers-0.094
Token child
Token ID1200
Feature activation-1.21e+00

Pos logit contributions
itized+0.465
olk+0.456
PD+0.455
 reviewer+0.450
agers+0.449
Neg logit contributions
apult-0.764
cles-0.764
aeda-0.753
riots-0.725
elaide-0.723
Token is
Token ID318
Feature activation+4.65e-01

Pos logit contributions
itized+0.697
PD+0.684
olk+0.684
 reviewer+0.679
agers+0.674
Neg logit contributions
apult-1.104
cles-1.099
aeda-1.089
riots-1.046
elaide-1.044
Token transgender
Token ID10637
Feature activation+8.65e-01

Pos logit contributions
cles+0.419
apult+0.417
aeda+0.412
riots+0.395
elaide+0.395
Neg logit contributions
itized-0.274
olk-0.270
PD-0.268
 reviewer-0.266
essor-0.266
Token,
Token ID11
Feature activation-1.00e+00

Pos logit contributions
apult+0.840
cles+0.837
aeda+0.830
riots+0.799
elaide+0.798
Neg logit contributions
itized-0.452
PD-0.443
olk-0.442
 reviewer-0.438
agers-0.435
Token society
Token ID3592
Feature activation-7.15e-02

Pos logit contributions
itized+0.510
PD+0.499
olk+0.496
 reviewer+0.495
agers+0.492
Neg logit contributions
apult-0.990
cles-0.983
aeda-0.980
berus-0.943
riots-0.943
Token inst
Token ID916
Feature activation-1.28e+01

Pos logit contributions
itized+0.041
olk+0.040
PD+0.040
 reviewer+0.039
essor+0.039
Neg logit contributions
cles-0.066
apult-0.066
aeda-0.065
riots-0.062
elaide-0.062
Tokenills
Token ID2171
Feature activation-2.96e+00

Pos logit contributions
itiz+8.108
agers+7.986
itized+7.966
olk+7.738
hips+7.716
Neg logit contributions
apult-9.619
berus-9.581
cles-9.503
prus-9.386
nea-9.271
Token in
Token ID287
Feature activation-9.28e-01

Pos logit contributions
itized+1.511
PD+1.477
olk+1.473
 reviewer+1.469
 renamed+1.461
Neg logit contributions
apult-2.909
cles-2.892
aeda-2.868
berus-2.776
elaide-2.766
Token them
Token ID606
Feature activation+9.79e-01

Pos logit contributions
itized+0.457
PD+0.446
olk+0.443
 reviewer+0.440
agers+0.439
Neg logit contributions
apult-0.932
cles-0.928
aeda-0.921
riots-0.889
elaide-0.888
Token rules
Token ID3173
Feature activation-1.59e+00

Pos logit contributions
cles+0.954
apult+0.953
aeda+0.940
riots+0.907
elaide+0.905
Neg logit contributions
itized-0.504
olk-0.493
PD-0.492
 reviewer-0.489
essor-0.486
Token about
Token ID546
Feature activation-1.86e+00

Pos logit contributions
itized+0.859
PD+0.845
olk+0.840
 reviewer+0.834
 renamed+0.831
Neg logit contributions
apult-1.514
cles-1.502
aeda-1.499
berus-1.441
riots-1.440
Token r
Token ID374
Feature activation-1.63e+00

Pos logit contributions
apult+1.097
cles+1.097
aeda+1.084
riots+1.044
elaide+1.042
Neg logit contributions
itized-0.623
olk-0.610
PD-0.610
 reviewer-0.604
agers-0.600
Tokenims
Token ID12078
Feature activation-3.00e+00

Pos logit contributions
itized+1.000
PD+0.981
olk+0.975
agers+0.966
 reviewer+0.965
Neg logit contributions
apult-1.442
cles-1.428
aeda-1.411
riots-1.360
elaide-1.358
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
itized+1.503
PD+1.453
 renamed+1.448
olk+1.447
stead+1.433
Neg logit contributions
apult-3.008
cles-2.954
aeda-2.944
berus-2.855
riots-2.852
Token laced
Token ID49699
Feature activation-7.05e+00

Pos logit contributions
itized+0.531
PD+0.520
olk+0.518
 reviewer+0.515
 renamed+0.514
Neg logit contributions
apult-1.016
cles-1.009
aeda-0.999
riots-0.965
elaide-0.964
Token to
Token ID284
Feature activation-3.35e+00

Pos logit contributions
itized+3.221
PD+3.138
 renamed+3.107
stead+3.104
 reviewer+3.053
Neg logit contributions
apult-7.261
aeda-6.984
cles-6.929
berus-6.846
riots-6.820
Token Suz
Token ID22691
Feature activation-1.27e+01

Pos logit contributions
itized+1.659
PD+1.625
 reviewer+1.612
olk+1.601
 renamed+1.592
Neg logit contributions
apult-3.330
cles-3.292
aeda-3.270
elaide-3.187
riots-3.166
Tokenue
Token ID518
Feature activation-4.19e-01

Pos logit contributions
olk+6.929
itized+6.903
stead+6.534
agers+6.505
ield+6.481
Neg logit contributions
elaide-10.958
apult-10.911
aeda-10.656
cles-10.638
riots-10.623
Token road
Token ID2975
Feature activation-4.26e+00

Pos logit contributions
itized+0.238
PD+0.234
olk+0.232
 reviewer+0.231
 renamed+0.229
Neg logit contributions
apult-0.389
cles-0.383
aeda-0.381
elaide-0.369
riots-0.368
Token hubs
Token ID38459
Feature activation+2.79e+00

Pos logit contributions
itized+2.475
stead+2.461
PD+2.440
 reviewer+2.422
agers+2.397
Neg logit contributions
apult-3.899
aeda-3.786
cles-3.738
berus-3.678
elaide-3.655
Token with
Token ID351
Feature activation-1.46e+00

Pos logit contributions
cles+2.606
apult+2.597
aeda+2.571
riots+2.470
elaide+2.465
Neg logit contributions
itized-1.546
olk-1.519
PD-1.517
 reviewer-1.508
agers-1.503
Token an
Token ID281
Feature activation-6.24e-01

Pos logit contributions
itized+0.741
PD+0.726
 reviewer+0.721
olk+0.721
 renamed+0.715
Neg logit contributions
apult-1.437
cles-1.426
aeda-1.415
riots-1.366
elaide-1.365
Token,
Token ID11
Feature activation+9.80e-01

Pos logit contributions
itized+0.942
 renamed+0.935
PD+0.933
olk+0.925
 reviewer+0.922
Neg logit contributions
apult-1.859
cles-1.849
aeda-1.848
elaide-1.787
riots-1.775
Token P
Token ID350
Feature activation+1.37e-01

Pos logit contributions
cles+0.896
apult+0.895
aeda+0.882
riots+0.851
berus+0.846
Neg logit contributions
itized-0.568
olk-0.556
PD-0.553
 reviewer-0.545
essor-0.542
Token.
Token ID13
Feature activation-7.69e-01

Pos logit contributions
apult+0.116
cles+0.115
aeda+0.115
elaide+0.110
riots+0.110
Neg logit contributions
itized-0.088
PD-0.087
olk-0.086
 reviewer-0.085
agers-0.085
TokenA
Token ID32
Feature activation+1.69e+00

Pos logit contributions
itized+0.353
PD+0.350
olk+0.347
 reviewer+0.344
 renamed+0.342
Neg logit contributions
apult-0.789
cles-0.786
aeda-0.782
elaide-0.756
riots-0.755
Token.,
Token ID1539
Feature activation+1.01e-01

Pos logit contributions
apult+1.505
cles+1.501
aeda+1.483
riots+1.424
elaide+1.422
Neg logit contributions
itized-1.021
PD-1.001
olk-1.001
 reviewer-0.993
agers-0.986
Token inst
Token ID916
Feature activation-1.25e+01

Pos logit contributions
apult+0.094
cles+0.094
aeda+0.092
riots+0.089
elaide+0.089
Neg logit contributions
itized-0.057
olk-0.056
PD-0.056
 reviewer-0.056
agers-0.055
Tokenig
Token ID328
Feature activation-3.24e+00

Pos logit contributions
agers+8.852
itized+8.722
itiz+8.689
hips+8.440
olk+8.292
Neg logit contributions
apult-8.562
cles-8.496
prus-8.370
berus-8.367
aeda-8.267
Tokenates
Token ID689
Feature activation+1.00e+00

Pos logit contributions
itized+2.097
agers+2.023
PD+2.020
olk+2.016
hips+1.995
Neg logit contributions
apult-2.734
aeda-2.709
cles-2.652
berus-2.577
elaide-2.560
Token 13
Token ID1511
Feature activation-9.71e-01

Pos logit contributions
apult+0.976
cles+0.972
aeda+0.963
riots+0.929
berus+0.925
Neg logit contributions
itized-0.523
olk-0.511
PD-0.510
 reviewer-0.502
stead-0.500
Token lawsuits
Token ID17785
Feature activation+1.52e+00

Pos logit contributions
itized+0.582
PD+0.572
olk+0.571
 reviewer+0.569
 renamed+0.565
Neg logit contributions
apult-0.866
cles-0.866
aeda-0.855
elaide-0.821
riots-0.820
Token against
Token ID1028
Feature activation+2.73e-01

Pos logit contributions
apult+1.390
cles+1.388
aeda+1.368
riots+1.319
elaide+1.313
Neg logit contributions
itized-0.873
olk-0.854
PD-0.853
 reviewer-0.842
agers-0.838
Token,
Token ID11
Feature activation-1.66e+00

Pos logit contributions
apult+1.902
cles+1.897
aeda+1.874
riots+1.808
elaide+1.800
Neg logit contributions
itized-1.072
olk-1.052
PD-1.047
 reviewer-1.037
essor-1.028
Token too
Token ID1165
Feature activation-3.52e+00

Pos logit contributions
itized+0.879
 reviewer+0.863
PD+0.862
olk+0.862
 renamed+0.855
Neg logit contributions
cles-1.585
apult-1.585
aeda-1.566
elaide-1.512
berus-1.510
Token,
Token ID11
Feature activation-9.89e-01

Pos logit contributions
itized+1.713
PD+1.697
olk+1.694
 reviewer+1.689
 renamed+1.669
Neg logit contributions
apult-3.505
cles-3.494
aeda-3.477
riots-3.363
berus-3.359
Token with
Token ID351
Feature activation-2.71e+00

Pos logit contributions
itized+0.514
PD+0.502
olk+0.501
 reviewer+0.501
 renamed+0.499
Neg logit contributions
apult-0.962
cles-0.960
aeda-0.951
riots-0.917
elaide-0.917
Token each
Token ID1123
Feature activation+4.19e+00

Pos logit contributions
itized+1.395
 reviewer+1.373
PD+1.369
olk+1.364
 renamed+1.361
Neg logit contributions
cles-2.624
apult-2.621
aeda-2.588
elaide-2.508
riots-2.506
Token inst
Token ID916
Feature activation-1.22e+01

Pos logit contributions
apult+3.966
cles+3.910
aeda+3.859
berus+3.718
riots+3.714
Neg logit contributions
itized-2.248
olk-2.201
PD-2.197
agers-2.168
essor-2.167
Tokenal
Token ID282
Feature activation-7.88e-01

Pos logit contributions
olk+6.401
agers+6.376
itized+6.322
ield+6.310
stead+6.250
Neg logit contributions
cles-10.826
apult-10.299
berus-10.261
prus-10.251
aeda-10.154
Tokenment
Token ID434
Feature activation-4.14e+00

Pos logit contributions
itized+0.579
olk+0.570
PD+0.568
 reviewer+0.565
 renamed+0.562
Neg logit contributions
cles-0.596
apult-0.596
aeda-0.589
elaide-0.560
berus-0.559
Token representing
Token ID10200
Feature activation+6.37e-01

Pos logit contributions
itized+2.183
 renamed+2.163
 reviewer+2.157
PD+2.149
olk+2.134
Neg logit contributions
cles-3.929
apult-3.922
aeda-3.917
berus-3.798
elaide-3.790
Token a
Token ID257
Feature activation-4.97e-01

Pos logit contributions
apult+0.639
cles+0.637
aeda+0.631
riots+0.609
elaide+0.607
Neg logit contributions
itized-0.311
PD-0.304
olk-0.304
 reviewer-0.301
agers-0.298
Token sizeable
Token ID47225
Feature activation+2.24e+00

Pos logit contributions
itized+0.277
PD+0.271
olk+0.271
 reviewer+0.269
 renamed+0.267
Neg logit contributions
apult-0.465
cles-0.464
aeda-0.459
riots-0.442
elaide-0.441
Token version
Token ID2196
Feature activation-4.30e+00

Pos logit contributions
itized+0.048
olk+0.047
PD+0.047
 reviewer+0.046
agers+0.046
Neg logit contributions
apult-0.104
cles-0.104
aeda-0.103
riots-0.099
elaide-0.099
Token |
Token ID930
Feature activation-8.14e-01

Pos logit contributions
itized+2.048
PD+2.047
 reviewer+2.017
 renamed+2.010
olk+1.984
Neg logit contributions
apult-4.330
cles-4.306
aeda-4.266
riots-4.153
elaide-4.139
Token count
Token ID954
Feature activation+6.99e-01

Pos logit contributions
itized+0.424
PD+0.417
olk+0.416
 reviewer+0.414
 renamed+0.411
Neg logit contributions
apult-0.791
cles-0.789
aeda-0.781
riots-0.753
elaide-0.751
Token |
Token ID930
Feature activation-8.89e-01

Pos logit contributions
apult+0.679
cles+0.678
aeda+0.670
riots+0.646
elaide+0.645
Neg logit contributions
itized-0.365
olk-0.356
PD-0.356
 reviewer-0.353
agers-0.350
Token |
Token ID930
Feature activation-1.16e+00

Pos logit contributions
itized+0.458
PD+0.449
olk+0.448
 reviewer+0.447
 renamed+0.444
Neg logit contributions
apult-0.869
cles-0.866
aeda-0.858
riots-0.828
elaide-0.825
Token --------------------
Token ID41436
Feature activation-1.21e+01

Pos logit contributions
itized+0.578
PD+0.568
olk+0.566
 reviewer+0.563
 renamed+0.560
Neg logit contributions
apult-1.146
cles-1.143
aeda-1.132
riots-1.093
elaide-1.088
Token-+
Token ID19529
Feature activation-3.86e+00

Pos logit contributions
itized+4.650
 renamed+4.618
PD+4.581
 reviewer+4.539
essor+4.499
Neg logit contributions
apult-12.328
cles-12.118
aeda-12.070
riots-11.992
elaide-11.832
Token--------
Token ID982
Feature activation-5.83e+00

Pos logit contributions
itized+1.826
PD+1.817
 renamed+1.784
olk+1.765
 reviewer+1.762
Neg logit contributions
cles-3.895
apult-3.892
aeda-3.859
riots-3.734
elaide-3.720
Token-+
Token ID19529
Feature activation-2.12e+00

Pos logit contributions
PD+1.503
itized+1.498
olk+1.463
 renamed+1.456
 reviewer+1.405
Neg logit contributions
cles-7.059
apult-7.057
aeda-6.995
riots-6.868
berus-6.830
Token-------
Token ID26866
Feature activation-8.77e+00

Pos logit contributions
itized+1.011
PD+1.001
olk+0.982
 renamed+0.979
 reviewer+0.974
Neg logit contributions
cles-2.153
apult-2.150
aeda-2.129
riots-2.061
berus-2.055
Token|
Token ID91
Feature activation-8.95e-01

Pos logit contributions
itized+3.653
PD+3.650
olk+3.577
 renamed+3.571
 reviewer+3.472
Neg logit contributions
apult-8.974
cles-8.903
aeda-8.834
riots-8.777
berus-8.609
Token rock
Token ID3881
Feature activation-1.99e+00

Pos logit contributions
apult+0.059
cles+0.059
aeda+0.058
riots+0.056
elaide+0.056
Neg logit contributions
itized-0.033
PD-0.032
olk-0.032
 reviewer-0.032
 renamed-0.032
Token festival
Token ID10876
Feature activation-2.61e+00

Pos logit contributions
itized+1.020
stead+1.006
 reviewer+0.985
olk+0.985
PD+0.981
Neg logit contributions
aeda-1.947
cles-1.946
apult-1.930
berus-1.885
riots-1.879
Token,
Token ID11
Feature activation-1.97e-01

Pos logit contributions
itized+1.353
olk+1.313
PD+1.303
stead+1.300
 reviewer+1.299
Neg logit contributions
apult-2.542
cles-2.538
aeda-2.526
berus-2.451
elaide-2.431
Token or
Token ID393
Feature activation+5.21e-01

Pos logit contributions
itized+0.107
olk+0.104
PD+0.104
 reviewer+0.104
 renamed+0.103
Neg logit contributions
apult-0.187
cles-0.187
aeda-0.185
riots-0.178
elaide-0.178
Token a
Token ID257
Feature activation+1.56e-01

Pos logit contributions
apult+0.517
cles+0.516
aeda+0.511
riots+0.493
elaide+0.492
Neg logit contributions
itized-0.260
olk-0.254
PD-0.254
 reviewer-0.252
 renamed-0.249
Token skate
Token ID22647
Feature activation-1.16e+01

Pos logit contributions
apult+0.148
cles+0.148
aeda+0.146
riots+0.141
elaide+0.141
Neg logit contributions
itized-0.084
olk-0.082
PD-0.082
 reviewer-0.082
 renamed-0.081
Token park
Token ID3952
Feature activation-4.40e+00

Pos logit contributions
olk+5.820
stead+5.731
PD+5.708
itized+5.629
 reviewer+5.553
Neg logit contributions
aeda-10.994
cles-10.602
apult-10.562
nces-10.357
berus-10.355
Token or
Token ID393
Feature activation+9.77e-01

Pos logit contributions
itized+2.099
 renamed+2.053
stead+2.052
 reviewer+2.051
PD+2.046
Neg logit contributions
aeda-4.389
cles-4.365
apult-4.349
berus-4.251
riots-4.219
Token hanging
Token ID10938
Feature activation-5.96e+00

Pos logit contributions
apult+0.989
cles+0.986
aeda+0.976
riots+0.943
elaide+0.940
Neg logit contributions
itized-0.469
PD-0.458
olk-0.458
 reviewer-0.453
agers-0.449
Token out
Token ID503
Feature activation-2.12e+00

Pos logit contributions
itized+2.270
 reviewer+2.244
stead+2.222
 renamed+2.212
PD+2.179
Neg logit contributions
apult-6.426
cles-6.411
aeda-6.404
berus-6.255
elaide-6.203
Token in
Token ID287
Feature activation+1.69e+00

Pos logit contributions
itized+1.018
olk+0.988
PD+0.987
 renamed+0.981
 reviewer+0.977
Neg logit contributions
apult-2.131
aeda-2.117
cles-2.114
berus-2.049
elaide-2.034
Token cent
Token ID1247
Feature activation+1.43e+00

Pos logit contributions
itized+1.273
 reviewer+1.250
 renamed+1.242
olk+1.238
PD+1.236
Neg logit contributions
apult-1.885
cles-1.873
aeda-1.865
riots-1.789
berus-1.771
Token.
Token ID13
Feature activation-9.98e-01

Pos logit contributions
apult+1.299
cles+1.295
aeda+1.280
riots+1.231
elaide+1.229
Neg logit contributions
itized-0.840
PD-0.823
olk-0.822
 reviewer-0.817
agers-0.810
Token
Token ID198
Feature activation-1.71e+00

Pos logit contributions
itized+0.480
PD+0.473
olk+0.469
 reviewer+0.466
 renamed+0.463
Neg logit contributions
cles-1.007
apult-1.006
aeda-0.997
elaide-0.968
riots-0.964
Token
Token ID198
Feature activation-1.15e+00

Pos logit contributions
itized+0.709
PD+0.693
olk+0.689
 reviewer+0.680
agers+0.674
Neg logit contributions
apult-1.846
cles-1.840
aeda-1.825
elaide-1.766
riots-1.765
TokenLeg
Token ID11484
Feature activation-4.52e+00

Pos logit contributions
itized+0.705
PD+0.699
olk+0.687
agers+0.679
stead+0.676
Neg logit contributions
apult-1.022
cles-1.014
aeda-1.010
elaide-0.973
berus-0.966
Tokenisl
Token ID3044
Feature activation-1.16e+01

Pos logit contributions
itized+2.513
olk+2.408
PD+2.390
stead+2.380
agers+2.378
Neg logit contributions
apult-4.240
aeda-4.189
cles-4.182
berus-4.028
elaide-4.025
Tokenation
Token ID341
Feature activation-1.06e+00

Pos logit contributions
itized+5.916
agers+5.817
olk+5.795
PD+5.705
 reviewer+5.659
Neg logit contributions
apult-10.244
cles-10.174
aeda-10.141
elaide-9.964
berus-9.961
Token [
Token ID685
Feature activation+9.68e-01

Pos logit contributions
itized+0.552
PD+0.539
olk+0.539
 reviewer+0.537
 renamed+0.533
Neg logit contributions
apult-1.028
cles-1.023
aeda-1.016
elaide-0.979
riots-0.979
Token edit
Token ID4370
Feature activation-5.69e+00

Pos logit contributions
apult+1.107
cles+1.105
aeda+1.095
riots+1.061
elaide+1.060
Neg logit contributions
itized-0.338
PD-0.327
olk-0.327
 reviewer-0.323
agers-0.318
Token ]
Token ID2361
Feature activation-4.68e-01

Pos logit contributions
itized+1.012
PD+0.969
 reviewer+0.942
olk+0.916
 renamed+0.911
Neg logit contributions
apult-7.455
cles-7.424
aeda-7.402
elaide-7.326
berus-7.152
Token
Token ID198
Feature activation-3.22e-01

Pos logit contributions
itized+0.199
olk+0.194
PD+0.194
 reviewer+0.192
agers+0.190
Neg logit contributions
apult-0.500
cles-0.498
aeda-0.493
riots-0.477
elaide-0.476
Token.
Token ID13
Feature activation+4.85e-01

Pos logit contributions
itized+0.497
PD+0.493
olk+0.488
stead+0.484
 reviewer+0.482
Neg logit contributions
apult-0.884
cles-0.875
aeda-0.870
berus-0.843
riots-0.841
Token This
Token ID770
Feature activation-3.73e-01

Pos logit contributions
apult+0.468
cles+0.467
aeda+0.462
riots+0.445
berus+0.443
Neg logit contributions
itized-0.257
olk-0.250
PD-0.250
 reviewer-0.249
agers-0.247
Token
Token ID564
Feature activation-5.34e+00

Pos logit contributions
itized+0.198
PD+0.194
olk+0.194
 reviewer+0.193
 renamed+0.191
Neg logit contributions
apult-0.359
cles-0.358
aeda-0.354
riots-0.341
elaide-0.340
Token
Token ID250
Feature activation-1.83e+00

Pos logit contributions
itized+3.483
olk+3.455
 reviewer+3.412
PD+3.390
 renamed+3.364
Neg logit contributions
apult-4.430
cles-4.379
aeda-4.313
berus-4.225
elaide-4.184
Token new
Token ID649
Feature activation-2.19e+00

Pos logit contributions
itized+1.178
PD+1.161
olk+1.158
 reviewer+1.143
stead+1.140
Neg logit contributions
apult-1.551
cles-1.545
aeda-1.526
elaide-1.461
riots-1.461
Token local
Token ID1957
Feature activation-1.16e+01

Pos logit contributions
itized+1.185
olk+1.155
PD+1.153
 reviewer+1.151
 renamed+1.138
Neg logit contributions
cles-2.080
apult-2.079
aeda-2.055
riots-1.992
elaide-1.980
Tokenism
Token ID1042
Feature activation-3.16e+00

Pos logit contributions
itized+6.001
PD+5.766
 reviewer+5.753
olk+5.690
 matter+5.657
Neg logit contributions
cles-10.279
apult-10.278
riots-10.272
aeda-10.225
berus-10.034
Token
Token ID447
Feature activation+1.23e-02

Pos logit contributions
itized+1.599
olk+1.572
PD+1.562
 reviewer+1.551
 renamed+1.540
Neg logit contributions
apult-3.064
cles-3.061
aeda-3.052
riots-2.961
elaide-2.955
Token
Token ID251
Feature activation-1.16e-01

Pos logit contributions
apult+0.010
cles+0.010
aeda+0.010
elaide+0.010
riots+0.010
Neg logit contributions
itized-0.008
PD-0.008
olk-0.008
 reviewer-0.008
 renamed-0.008
Token is
Token ID318
Feature activation-8.20e-01

Pos logit contributions
itized+0.064
PD+0.062
olk+0.062
 reviewer+0.062
 renamed+0.061
Neg logit contributions
apult-0.109
cles-0.109
aeda-0.108
riots-0.104
elaide-0.103
Token pragmatic
Token ID33119
Feature activation+9.62e-01

Pos logit contributions
itized+0.435
PD+0.426
olk+0.426
 reviewer+0.422
agers+0.418
Neg logit contributions
apult-0.789
cles-0.787
aeda-0.778
riots-0.750
elaide-0.748
Token that
Token ID326
Feature activation+1.10e+00

Pos logit contributions
itized+1.531
 renamed+1.509
 reviewer+1.504
PD+1.499
olk+1.497
Neg logit contributions
apult-3.087
cles-3.035
aeda-3.026
berus-2.943
riots-2.942
Token he
Token ID339
Feature activation-1.74e+00

Pos logit contributions
apult+1.053
cles+1.050
aeda+1.038
riots+1.001
elaide+0.999
Neg logit contributions
itized-0.596
PD-0.583
olk-0.583
 reviewer-0.579
 renamed-0.574
Token had
Token ID550
Feature activation-1.24e+00

Pos logit contributions
itized+0.959
olk+0.945
PD+0.945
 renamed+0.945
 reviewer+0.941
Neg logit contributions
apult-1.640
cles-1.624
aeda-1.612
riots-1.554
berus-1.550
Token been
Token ID587
Feature activation-2.04e+00

Pos logit contributions
itized+0.657
 renamed+0.643
PD+0.643
olk+0.641
 reviewer+0.640
Neg logit contributions
apult-1.199
cles-1.186
aeda-1.176
riots-1.137
berus-1.135
Token an
Token ID281
Feature activation-1.69e-01

Pos logit contributions
itized+1.053
PD+1.034
olk+1.031
 renamed+1.030
 reviewer+1.023
Neg logit contributions
apult-1.993
cles-1.977
aeda-1.958
riots-1.895
berus-1.894
Token inst
Token ID916
Feature activation-1.12e+01

Pos logit contributions
itized+0.090
PD+0.088
olk+0.088
 reviewer+0.087
agers+0.087
Neg logit contributions
apult-0.162
cles-0.162
aeda-0.160
riots-0.154
elaide-0.153
Tokenigator
Token ID23823
Feature activation+9.85e-01

Pos logit contributions
essor+4.400
itized+4.392
olk+4.306
itiz+4.180
agers+4.120
Neg logit contributions
cles-11.720
apult-11.562
aeda-11.263
nces-11.159
berus-11.141
Token of
Token ID286
Feature activation+1.89e+00

Pos logit contributions
apult+0.922
cles+0.918
aeda+0.909
riots+0.875
elaide+0.873
Neg logit contributions
itized-0.549
PD-0.539
olk-0.538
 reviewer-0.536
 renamed-0.532
Token the
Token ID262
Feature activation+3.28e-01

Pos logit contributions
apult+1.809
cles+1.806
aeda+1.790
riots+1.725
elaide+1.717
Neg logit contributions
itized-1.008
PD-0.986
olk-0.986
 reviewer-0.976
agers-0.970
Token Mau
Token ID28931
Feature activation+8.97e-01

Pos logit contributions
apult+0.298
cles+0.297
aeda+0.294
riots+0.283
elaide+0.281
Neg logit contributions
itized-0.192
PD-0.188
olk-0.188
 reviewer-0.186
agers-0.185
Token Mau
Token ID28931
Feature activation+1.07e+00

Pos logit contributions
apult+0.884
cles+0.881
aeda+0.872
riots+0.842
elaide+0.841
Neg logit contributions
itized-0.456
PD-0.447
olk-0.446
 reviewer-0.441
 renamed-0.438
Tokenam
Token ID321
Feature activation-3.36e+00

Pos logit contributions
itized+0.535
PD+0.525
olk+0.525
 reviewer+0.520
agers+0.517
Neg logit contributions
apult-0.769
cles-0.767
aeda-0.758
riots-0.728
elaide-0.726
Token,
Token ID11
Feature activation-2.05e+00

Pos logit contributions
itized+1.595
PD+1.569
olk+1.561
 renamed+1.546
 reviewer+1.538
Neg logit contributions
apult-3.419
cles-3.399
aeda-3.385
elaide-3.275
berus-3.243
Token a
Token ID257
Feature activation-2.08e+00

Pos logit contributions
itized+0.942
PD+0.931
olk+0.922
 renamed+0.919
 reviewer+0.917
Neg logit contributions
apult-2.112
cles-2.102
aeda-2.085
elaide-2.023
riots-2.012
Token benz
Token ID39601
Feature activation-6.58e+00

Pos logit contributions
itized+1.030
PD+1.029
 reviewer+1.022
 renamed+1.017
olk+1.016
Neg logit contributions
apult-2.070
cles-2.059
aeda-2.050
elaide-1.980
riots-1.975
Tokenod
Token ID375
Feature activation-4.99e+00

Pos logit contributions
olk+2.089
itized+2.027
PD+1.997
stead+1.985
essor+1.979
Neg logit contributions
cles-7.656
aeda-7.638
apult-7.524
riots-7.350
elaide-7.332
Tokeniazep
Token ID48826
Feature activation-1.12e+01

Pos logit contributions
olk+2.261
PD+2.247
itized+2.244
essor+2.172
 reviewer+2.164
Neg logit contributions
apult-5.135
cles-5.127
aeda-5.080
riots-4.932
elaide-4.924
Tokenine
Token ID500
Feature activation-1.09e+00

Pos logit contributions
olk+3.403
essor+3.171
PD+3.127
stead+3.083
ansky+3.002
Neg logit contributions
cles-12.996
aeda-12.767
apult-12.608
riots-12.458
nces-12.407
Token anx
Token ID7296
Feature activation-2.08e+00

Pos logit contributions
itized+0.534
PD+0.526
olk+0.524
 reviewer+0.521
 renamed+0.517
Neg logit contributions
apult-1.091
cles-1.088
aeda-1.080
elaide-1.042
riots-1.040
Tokenio
Token ID952
Feature activation+2.97e+00

Pos logit contributions
itized+0.972
olk+0.933
PD+0.926
 reviewer+0.914
stead+0.902
Neg logit contributions
cles-2.159
apult-2.158
aeda-2.153
elaide-2.067
riots-2.063
Tokenly
Token ID306
Feature activation-6.18e-01

Pos logit contributions
cles+1.626
apult+1.566
aeda+1.514
riots+1.462
berus+1.438
Neg logit contributions
olk-2.798
itized-2.786
 renamed-2.768
agers-2.762
PD-2.761
Tokentic
Token ID13370
Feature activation-3.69e+00

Pos logit contributions
itized+0.432
PD+0.425
olk+0.424
 reviewer+0.421
 renamed+0.419
Neg logit contributions
apult-0.493
cles-0.488
aeda-0.485
elaide-0.465
riots-0.462
Token echoes
Token ID30346
Feature activation+3.73e+00

Pos logit contributions
itized+3.250
olk+3.181
 reviewer+3.178
stead+3.141
agers+3.139
Neg logit contributions
apult-4.891
aeda-4.859
cles-4.817
berus-4.652
elaide-4.642
Token of
Token ID286
Feature activation+1.11e+00

Pos logit contributions
apult+3.403
cles+3.400
aeda+3.335
riots+3.200
elaide+3.199
Neg logit contributions
itized-2.123
PD-2.088
olk-2.083
essor-2.072
agers-2.063
Token M
Token ID337
Feature activation-7.44e-01

Pos logit contributions
apult+1.046
cles+1.043
aeda+1.030
riots+0.993
elaide+0.991
Neg logit contributions
itized-0.612
PD-0.599
olk-0.598
 reviewer-0.591
agers-0.588
Token.
Token ID13
Feature activation-3.04e-01

Pos logit contributions
itized+0.452
olk+0.445
PD+0.444
 reviewer+0.440
agers+0.437
Neg logit contributions
apult-0.659
cles-0.656
aeda-0.648
riots-0.623
elaide-0.622
Token Night
Token ID5265
Feature activation-2.89e+00

Pos logit contributions
itized+0.168
PD+0.164
olk+0.164
 reviewer+0.163
 renamed+0.161
Neg logit contributions
apult-0.287
cles-0.286
aeda-0.283
riots-0.273
elaide-0.272
Token Shy
Token ID36838
Feature activation-1.11e+01

Pos logit contributions
itized+1.475
olk+1.467
PD+1.438
 reviewer+1.429
essor+1.417
Neg logit contributions
apult-2.846
aeda-2.816
cles-2.810
berus-2.736
riots-2.717
Tokenam
Token ID321
Feature activation-3.60e+00

Pos logit contributions
olk+5.284
PD+4.882
ansky+4.871
agers+4.671
 renamed+4.663
Neg logit contributions
aeda-11.240
apult-11.108
berus-10.909
cles-10.817
elaide-10.717
Tokenalan
Token ID25786
Feature activation-3.49e-01

Pos logit contributions
itized+1.823
PD+1.782
olk+1.781
 reviewer+1.765
agers+1.750
Neg logit contributions
apult-3.550
cles-3.540
aeda-3.504
riots-3.379
elaide-3.373
Token
Token ID447
Feature activation+1.78e-01

Pos logit contributions
itized+0.195
olk+0.191
PD+0.191
 reviewer+0.190
 renamed+0.189
Neg logit contributions
apult-0.326
cles-0.325
aeda-0.322
riots-0.310
berus-0.309
Token
Token ID247
Feature activation-1.69e-01

Pos logit contributions
apult+0.112
cles+0.111
aeda+0.110
riots+0.104
elaide+0.103
Neg logit contributions
itized-0.154
PD-0.152
olk-0.152
 reviewer-0.151
agers-0.150
Tokens
Token ID82
Feature activation+1.34e+00

Pos logit contributions
itized+0.074
PD+0.072
olk+0.072
 reviewer+0.071
 renamed+0.071
Neg logit contributions
apult-0.178
cles-0.177
aeda-0.176
riots-0.170
elaide-0.169
Token orient
Token ID11367
Feature activation-1.83e+00

Pos logit contributions
itized+2.757
PD+2.652
olk+2.631
stead+2.604
 renamed+2.600
Neg logit contributions
apult-5.143
aeda-5.098
cles-5.090
berus-4.892
riots-4.870
Tokenations
Token ID602
Feature activation-2.22e-01

Pos logit contributions
itized+1.317
PD+1.285
olk+1.282
 reviewer+1.264
 renamed+1.262
Neg logit contributions
apult-1.431
cles-1.429
aeda-1.407
elaide-1.351
berus-1.349
Token.
Token ID13
Feature activation-7.51e-01

Pos logit contributions
itized+0.119
PD+0.116
olk+0.116
 reviewer+0.115
 renamed+0.114
Neg logit contributions
apult-0.214
cles-0.213
aeda-0.211
berus-0.203
riots-0.203
Token Small
Token ID10452
Feature activation-2.64e+00

Pos logit contributions
itized+0.387
PD+0.380
olk+0.378
 reviewer+0.375
 renamed+0.372
Neg logit contributions
apult-0.734
cles-0.732
aeda-0.724
elaide-0.699
riots-0.699
Tokener
Token ID263
Feature activation+2.29e-01

Pos logit contributions
itized+1.452
olk+1.406
 reviewer+1.396
PD+1.395
agers+1.392
Neg logit contributions
apult-2.499
cles-2.477
aeda-2.476
berus-2.374
elaide-2.369
Token local
Token ID1957
Feature activation-1.11e+01

Pos logit contributions
apult+0.210
cles+0.210
aeda+0.207
riots+0.200
elaide+0.199
Neg logit contributions
itized-0.131
PD-0.129
olk-0.129
 reviewer-0.128
agers-0.127
Tokenes
Token ID274
Feature activation-1.08e+00

Pos logit contributions
itized+5.177
agers+4.928
stead+4.880
itiz+4.805
hips+4.800
Neg logit contributions
apult-10.768
aeda-10.634
berus-10.352
cles-10.335
elaide-10.212
Token in
Token ID287
Feature activation-6.58e-01

Pos logit contributions
itized+0.587
olk+0.574
PD+0.574
 reviewer+0.570
 renamed+0.567
Neg logit contributions
apult-1.030
cles-1.024
aeda-1.017
elaide-0.978
riots-0.978
Token the
Token ID262
Feature activation+1.22e-01

Pos logit contributions
itized+0.353
PD+0.345
olk+0.345
 reviewer+0.343
agers+0.341
Neg logit contributions
apult-0.630
cles-0.627
aeda-0.622
riots-0.599
elaide-0.598
Token same
Token ID976
Feature activation+1.93e+00

Pos logit contributions
apult+0.113
cles+0.113
aeda+0.111
riots+0.107
elaide+0.107
Neg logit contributions
itized-0.069
PD-0.068
olk-0.068
 reviewer-0.067
agers-0.067
Token time
Token ID640
Feature activation+1.40e+00

Pos logit contributions
cles+1.785
apult+1.780
aeda+1.756
riots+1.690
elaide+1.686
Neg logit contributions
itized-1.085
PD-1.068
olk-1.066
agers-1.049
 reviewer-1.045
TokenBS
Token ID4462
Feature activation-3.80e+00

Pos logit contributions
itized+0.321
PD+0.316
olk+0.316
 reviewer+0.313
agers+0.311
Neg logit contributions
apult-0.395
cles-0.394
aeda-0.389
riots-0.372
elaide-0.371
Token,
Token ID11
Feature activation-9.15e-01

Pos logit contributions
PD+1.752
itized+1.737
 renamed+1.695
olk+1.669
 reviewer+1.667
Neg logit contributions
cles-3.899
apult-3.877
aeda-3.869
berus-3.730
riots-3.717
Token Food
Token ID7318
Feature activation-2.97e+00

Pos logit contributions
itized+0.486
PD+0.476
olk+0.475
 reviewer+0.471
 renamed+0.468
Neg logit contributions
apult-0.880
cles-0.878
aeda-0.869
riots-0.837
elaide-0.836
Token Network
Token ID7311
Feature activation-3.61e+00

Pos logit contributions
itized+1.184
 reviewer+1.166
PD+1.166
olk+1.142
stead+1.118
Neg logit contributions
cles-3.220
aeda-3.214
apult-3.189
berus-3.117
riots-3.092
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
itized+1.648
PD+1.636
agers+1.610
 reviewer+1.601
 renamed+1.600
Neg logit contributions
aeda-3.673
apult-3.660
cles-3.659
berus-3.531
riots-3.527
Token HG
Token ID48698
Feature activation-1.10e+01

Pos logit contributions
itized+0.536
PD+0.526
olk+0.523
 reviewer+0.519
 renamed+0.517
Neg logit contributions
apult-1.004
cles-1.002
aeda-0.994
elaide-0.956
riots-0.955
TokenTV
Token ID6849
Feature activation-2.27e+00

Pos logit contributions
PD+5.517
 reviewer+4.715
hips+4.706
stead+4.653
itized+4.648
Neg logit contributions
cles-11.113
apult-10.939
aeda-10.883
elaide-10.669
berus-10.660
Token,
Token ID11
Feature activation-6.06e-01

Pos logit contributions
itized+1.098
PD+1.096
 reviewer+1.073
olk+1.067
 renamed+1.063
Neg logit contributions
apult-2.280
cles-2.279
aeda-2.267
berus-2.179
riots-2.170
Token Cartoon
Token ID46838
Feature activation-2.26e+00

Pos logit contributions
itized+0.310
PD+0.303
olk+0.302
 reviewer+0.300
 renamed+0.298
Neg logit contributions
apult-0.595
cles-0.593
aeda-0.588
riots-0.566
elaide-0.566
Token Network
Token ID7311
Feature activation-2.14e+00

Pos logit contributions
itized+0.929
PD+0.910
olk+0.896
 reviewer+0.887
 renamed+0.881
Neg logit contributions
aeda-2.437
apult-2.431
cles-2.420
elaide-2.334
berus-2.329
Token,
Token ID11
Feature activation-6.55e-01

Pos logit contributions
itized+1.023
PD+1.013
 reviewer+0.996
agers+0.991
 renamed+0.990
Neg logit contributions
apult-2.160
cles-2.151
aeda-2.151
berus-2.065
riots-2.062
Token activity
Token ID3842
Feature activation+8.43e-03

Pos logit contributions
itized+0.940
PD+0.933
olk+0.923
 reviewer+0.916
 renamed+0.912
Neg logit contributions
apult-1.672
cles-1.672
aeda-1.650
elaide-1.591
riots-1.589
Token returns
Token ID5860
Feature activation+6.70e-01

Pos logit contributions
apult+0.008
cles+0.008
aeda+0.008
riots+0.008
elaide+0.008
Neg logit contributions
itized-0.005
PD-0.005
olk-0.005
 reviewer-0.005
 renamed-0.005
Token to
Token ID284
Feature activation-1.38e+00

Pos logit contributions
apult+0.641
cles+0.639
aeda+0.633
riots+0.609
elaide+0.608
Neg logit contributions
itized-0.359
olk-0.351
PD-0.351
 reviewer-0.348
agers-0.346
Token normal
Token ID3487
Feature activation-6.56e-02

Pos logit contributions
itized+0.681
PD+0.668
olk+0.662
 reviewer+0.661
 renamed+0.656
Neg logit contributions
apult-1.383
cles-1.382
aeda-1.367
riots-1.319
elaide-1.315
Token,
Token ID11
Feature activation-1.66e+00

Pos logit contributions
itized+0.036
PD+0.036
olk+0.036
 reviewer+0.035
agers+0.035
Neg logit contributions
apult-0.062
cles-0.062
aeda-0.061
riots-0.059
elaide-0.059
Token seasonal
Token ID21819
Feature activation-1.08e+01

Pos logit contributions
itized+0.929
PD+0.920
 reviewer+0.913
olk+0.911
 renamed+0.910
Neg logit contributions
apult-1.549
cles-1.542
aeda-1.525
elaide-1.465
riots-1.464
Token flu
Token ID6562
Feature activation-4.82e+00

Pos logit contributions
itized+6.135
PD+6.076
 reviewer+6.059
 renamed+6.012
stead+6.007
Neg logit contributions
apult-9.433
aeda-9.209
cles-9.107
berus-8.849
riots-8.804
Token levels
Token ID2974
Feature activation-2.28e+00

Pos logit contributions
PD+2.579
itized+2.563
 renamed+2.529
 reviewer+2.507
stead+2.505
Neg logit contributions
apult-4.590
aeda-4.522
cles-4.518
berus-4.364
elaide-4.346
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
itized+1.246
PD+1.234
olk+1.220
 reviewer+1.217
 renamed+1.216
Neg logit contributions
apult-2.153
cles-2.139
aeda-2.123
riots-2.048
elaide-2.044
Token BACK
Token ID28767
Feature activation-2.95e+00

Pos logit contributions
itized+0.915
PD+0.909
olk+0.897
 reviewer+0.888
 renamed+0.884
Neg logit contributions
apult-1.774
cles-1.772
aeda-1.751
elaide-1.694
riots-1.689
Token {
Token ID1391
Feature activation+2.69e+00

Pos logit contributions
PD+1.599
itized+1.586
 renamed+1.535
 reviewer+1.534
olk+1.524
Neg logit contributions
cles-2.814
apult-2.807
aeda-2.788
elaide-2.709
riots-2.688
Token by
Token ID416
Feature activation+1.14e+00

Pos logit contributions
apult+0.027
cles+0.027
aeda+0.026
riots+0.025
elaide+0.025
Neg logit contributions
itized-0.016
PD-0.016
olk-0.016
 reviewer-0.015
 renamed-0.015
Token a
Token ID257
Feature activation-3.05e-01

Pos logit contributions
apult+1.089
cles+1.083
aeda+1.069
riots+1.037
elaide+1.031
Neg logit contributions
itized-0.616
olk-0.604
PD-0.601
 reviewer-0.592
agers-0.591
Token combination
Token ID6087
Feature activation+4.38e+00

Pos logit contributions
itized+0.172
olk+0.169
PD+0.169
 reviewer+0.167
agers+0.166
Neg logit contributions
apult-0.283
cles-0.282
aeda-0.279
riots-0.269
elaide-0.268
Token of
Token ID286
Feature activation+1.30e+00

Pos logit contributions
apult+3.584
cles+3.551
aeda+3.458
riots+3.362
berus+3.312
Neg logit contributions
itized-2.885
olk-2.822
agers-2.796
essor-2.774
PD-2.755
Token the
Token ID262
Feature activation-4.20e-01

Pos logit contributions
apult+1.224
cles+1.216
aeda+1.200
riots+1.162
elaide+1.156
Neg logit contributions
itized-0.719
olk-0.707
PD-0.702
agers-0.694
essor-0.692
Token Soon
Token ID15894
Feature activation-1.07e+01

Pos logit contributions
itized+0.236
olk+0.232
PD+0.231
 reviewer+0.228
agers+0.227
Neg logit contributions
apult-0.391
cles-0.389
aeda-0.384
riots-0.371
elaide-0.369
Tokeners
Token ID364
Feature activation-3.05e+00

Pos logit contributions
agers+3.230
olk+3.022
stead+2.950
 renamed+2.903
PD+2.872
Neg logit contributions
apult-12.530
aeda-12.391
elaide-12.244
cles-12.151
berus-12.140
Token'
Token ID6
Feature activation+5.06e-01

Pos logit contributions
itized+1.312
PD+1.279
olk+1.267
 reviewer+1.258
 renamed+1.255
Neg logit contributions
cles-3.245
apult-3.237
aeda-3.209
elaide-3.106
riots-3.097
Token own
Token ID898
Feature activation+8.83e-01

Pos logit contributions
apult+0.480
cles+0.478
aeda+0.473
riots+0.456
elaide+0.454
Neg logit contributions
itized-0.273
olk-0.270
PD-0.269
 reviewer-0.265
agers-0.265
Token inept
Token ID43891
Feature activation-9.82e-01

Pos logit contributions
apult+0.833
cles+0.830
aeda+0.820
riots+0.792
elaide+0.788
Neg logit contributions
itized-0.480
olk-0.475
PD-0.471
agers-0.466
 reviewer-0.465
Token offense
Token ID6907
Feature activation-1.44e+00

Pos logit contributions
itized+0.589
PD+0.577
olk+0.577
 reviewer+0.573
agers+0.569
Neg logit contributions
apult-0.878
cles-0.875
aeda-0.865
riots-0.831
elaide-0.829
Token
Token ID447
Feature activation+1.69e-01

Pos logit contributions
itized+0.355
olk+0.349
PD+0.349
 reviewer+0.345
stead+0.343
Neg logit contributions
apult-0.625
cles-0.620
aeda-0.616
elaide-0.594
riots-0.593
Token
Token ID251
Feature activation+2.23e-02

Pos logit contributions
apult+0.149
cles+0.148
aeda+0.146
riots+0.141
elaide+0.141
Neg logit contributions
itized-0.104
olk-0.102
PD-0.102
 reviewer-0.101
agers-0.100
Token books
Token ID3835
Feature activation-1.67e+00

Pos logit contributions
apult+0.020
cles+0.020
aeda+0.020
riots+0.019
elaide+0.019
Neg logit contributions
itized-0.013
PD-0.013
olk-0.013
 reviewer-0.013
agers-0.013
Token,
Token ID11
Feature activation-5.74e-01

Pos logit contributions
itized+0.875
 reviewer+0.852
PD+0.851
olk+0.846
 renamed+0.843
Neg logit contributions
apult-1.617
cles-1.616
aeda-1.610
berus-1.551
elaide-1.548
Token the
Token ID262
Feature activation-8.78e-01

Pos logit contributions
itized+0.294
PD+0.286
 reviewer+0.286
olk+0.286
 renamed+0.283
Neg logit contributions
cles-0.563
apult-0.562
aeda-0.557
riots-0.537
elaide-0.537
Token hipp
Token ID18568
Feature activation-1.07e+01

Pos logit contributions
itized+0.501
 reviewer+0.497
PD+0.487
olk+0.486
agers+0.483
Neg logit contributions
apult-0.810
cles-0.810
aeda-0.802
elaide-0.772
berus-0.770
Tokenie
Token ID494
Feature activation-5.31e+00

Pos logit contributions
itized+4.109
olk+4.055
essor+4.004
agers+3.894
 reviewer+3.888
Neg logit contributions
cles-11.191
aeda-11.176
apult-11.156
berus-10.881
elaide-10.845
Token inside
Token ID2641
Feature activation-1.80e-01

Pos logit contributions
 reviewer+2.873
itized+2.814
PD+2.751
agers+2.745
stead+2.743
Neg logit contributions
aeda-5.020
apult-5.009
cles-4.984
elaide-4.819
berus-4.811
Token me
Token ID502
Feature activation+9.04e-01

Pos logit contributions
itized+0.083
PD+0.081
 reviewer+0.080
olk+0.080
 renamed+0.079
Neg logit contributions
apult-0.186
cles-0.186
aeda-0.184
riots-0.178
elaide-0.178
Token thinks
Token ID6834
Feature activation+1.15e+00

Pos logit contributions
apult+0.836
cles+0.834
aeda+0.826
riots+0.794
elaide+0.793
Neg logit contributions
itized-0.513
PD-0.503
olk-0.502
 reviewer-0.499
 renamed-0.495
Token that
Token ID326
Feature activation+2.32e+00

Pos logit contributions
apult+1.094
cles+1.090
aeda+1.077
riots+1.039
elaide+1.035
Neg logit contributions
itized-0.616
olk-0.602
PD-0.602
 reviewer-0.595
agers-0.592
Token.
Token ID13
Feature activation+5.38e-01

Pos logit contributions
itized+0.146
PD+0.143
olk+0.143
 reviewer+0.142
stead+0.141
Neg logit contributions
apult-0.254
cles-0.253
aeda-0.251
riots-0.243
berus-0.242
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
apult+0.530
cles+0.528
aeda+0.522
riots+0.504
berus+0.502
Neg logit contributions
itized-0.273
olk-0.266
PD-0.266
 reviewer-0.264
agers-0.262
Token
Token ID198
Feature activation-1.19e-01

Pos logit contributions
itized+0.440
PD+0.429
olk+0.428
 reviewer+0.423
agers+0.419
Neg logit contributions
apult-1.119
cles-1.116
aeda-1.106
riots-1.070
elaide-1.068
TokenFor
Token ID1890
Feature activation+2.06e+00

Pos logit contributions
itized+0.072
PD+0.071
olk+0.071
 reviewer+0.070
agers+0.070
Neg logit contributions
apult-0.105
cles-0.105
aeda-0.104
riots-0.099
elaide-0.099
Token the
Token ID262
Feature activation-4.17e-01

Pos logit contributions
apult+1.968
cles+1.957
aeda+1.936
riots+1.861
elaide+1.859
Neg logit contributions
itized-1.099
olk-1.069
PD-1.068
 reviewer-1.047
 renamed-1.042
Token Yog
Token ID31604
Feature activation-1.06e+01

Pos logit contributions
itized+0.239
PD+0.234
olk+0.234
 reviewer+0.232
agers+0.230
Neg logit contributions
apult-0.384
cles-0.383
aeda-0.379
riots-0.364
elaide-0.364
Tokenventures
Token ID10065
Feature activation-4.08e+00

Pos logit contributions
olk+7.587
agers+7.529
PD+7.462
stead+7.430
itized+7.388
Neg logit contributions
aeda-7.594
cles-7.472
apult-7.406
berus-7.201
riots-7.148
Token Kickstarter
Token ID14437
Feature activation+6.24e-01

Pos logit contributions
 reviewer+2.072
itized+2.069
PD+2.041
olk+2.032
 renamed+2.024
Neg logit contributions
apult-3.978
cles-3.950
aeda-3.949
elaide-3.823
riots-3.809
Token backers
Token ID18917
Feature activation+8.75e-01

Pos logit contributions
apult+0.574
cles+0.572
aeda+0.563
riots+0.543
elaide+0.542
Neg logit contributions
itized-0.359
olk-0.351
PD-0.349
 reviewer-0.344
agers-0.343
Token the
Token ID262
Feature activation-1.95e-01

Pos logit contributions
apult+0.838
cles+0.836
aeda+0.827
riots+0.797
elaide+0.795
Neg logit contributions
itized-0.468
PD-0.458
olk-0.458
 reviewer-0.454
agers-0.450
Token physical
Token ID3518
Feature activation-3.81e-01

Pos logit contributions
itized+0.111
PD+0.109
olk+0.109
 reviewer+0.108
agers+0.107
Neg logit contributions
apult-0.179
cles-0.179
aeda-0.177
riots-0.170
elaide-0.170
Token the
Token ID262
Feature activation-5.91e-02

Pos logit contributions
itized+0.615
olk+0.606
PD+0.604
 reviewer+0.602
agers+0.597
Neg logit contributions
apult-1.021
cles-1.019
aeda-1.011
riots-0.972
elaide-0.970
Token north
Token ID5093
Feature activation-3.53e-01

Pos logit contributions
itized+0.033
olk+0.033
PD+0.033
 reviewer+0.033
agers+0.032
Neg logit contributions
apult-0.055
cles-0.055
aeda-0.054
riots-0.052
elaide-0.052
Token than
Token ID621
Feature activation-5.16e-02

Pos logit contributions
itized+0.184
olk+0.181
PD+0.181
 reviewer+0.179
 renamed+0.177
Neg logit contributions
apult-0.342
cles-0.342
aeda-0.339
riots-0.326
berus-0.326
Token the
Token ID262
Feature activation-8.50e-01

Pos logit contributions
itized+0.027
olk+0.026
PD+0.026
 reviewer+0.026
agers+0.026
Neg logit contributions
apult-0.050
cles-0.050
aeda-0.049
riots-0.048
elaide-0.048
Token tiny
Token ID7009
Feature activation-2.26e+00

Pos logit contributions
itized+0.469
olk+0.462
PD+0.459
 reviewer+0.459
 renamed+0.456
Neg logit contributions
apult-0.798
cles-0.795
aeda-0.788
riots-0.759
elaide-0.756
Token sl
Token ID1017
Feature activation-1.06e+01

Pos logit contributions
itized+1.258
olk+1.236
 reviewer+1.232
PD+1.223
 renamed+1.217
Neg logit contributions
apult-2.105
cles-2.097
aeda-2.082
riots-2.001
elaide-1.997
Tokeniver
Token ID1428
Feature activation-1.24e+00

Pos logit contributions
agers+5.210
essor+5.126
ansky+4.994
olk+4.974
itized+4.878
Neg logit contributions
apult-10.204
aeda-9.849
cles-9.814
elaide-9.501
berus-9.448
Token of
Token ID286
Feature activation+1.96e-01

Pos logit contributions
itized+0.676
olk+0.664
PD+0.661
 renamed+0.657
 reviewer+0.654
Neg logit contributions
apult-1.178
cles-1.170
aeda-1.166
elaide-1.119
riots-1.118
Token sea
Token ID5417
Feature activation-1.65e-01

Pos logit contributions
apult+0.180
cles+0.180
aeda+0.178
riots+0.171
elaide+0.170
Neg logit contributions
itized-0.113
PD-0.111
olk-0.110
 reviewer-0.110
agers-0.109
Token that
Token ID326
Feature activation+1.13e+00

Pos logit contributions
itized+0.090
olk+0.088
PD+0.088
 reviewer+0.087
 renamed+0.087
Neg logit contributions
apult-0.156
cles-0.156
aeda-0.155
riots-0.149
elaide-0.149
Token divides
Token ID36319
Feature activation+3.22e+00

Pos logit contributions
apult+0.993
cles+0.992
aeda+0.978
riots+0.939
elaide+0.937
Neg logit contributions
itized-0.698
olk-0.684
PD-0.684
 reviewer-0.678
agers-0.674
Token radio
Token ID5243
Feature activation+3.85e+00

Pos logit contributions
apult+0.322
cles+0.322
aeda+0.318
riots+0.306
elaide+0.306
Neg logit contributions
itized-0.189
PD-0.186
olk-0.185
 reviewer-0.184
 renamed-0.183
Token in
Token ID287
Feature activation+1.96e+00

Pos logit contributions
apult+3.595
cles+3.581
aeda+3.545
riots+3.417
elaide+3.417
Neg logit contributions
itized-2.143
olk-2.102
PD-2.091
 reviewer-2.072
agers-2.060
Token FP
Token ID31459
Feature activation+1.51e+00

Pos logit contributions
apult+1.777
cles+1.776
aeda+1.751
riots+1.687
elaide+1.679
Neg logit contributions
itized-1.140
olk-1.110
PD-1.108
 reviewer-1.103
essor-1.095
Token1
Token ID16
Feature activation-6.66e-01

Pos logit contributions
apult+1.394
cles+1.389
aeda+1.373
riots+1.322
berus+1.319
Neg logit contributions
itized-0.860
PD-0.854
olk-0.853
 reviewer-0.841
 renamed-0.835
Token at
Token ID379
Feature activation+4.29e+00

Pos logit contributions
itized+0.361
PD+0.359
olk+0.355
 reviewer+0.354
 renamed+0.352
Neg logit contributions
apult-0.632
cles-0.628
aeda-0.624
berus-0.600
riots-0.599
Token Suz
Token ID22691
Feature activation-1.06e+01

Pos logit contributions
apult+3.973
cles+3.957
aeda+3.854
riots+3.758
elaide+3.737
Neg logit contributions
itized-2.395
essor-2.314
olk-2.300
PD-2.290
agers-2.279
Tokenuka
Token ID14852
Feature activation-1.91e+00

Pos logit contributions
olk+3.649
itized+3.259
stead+3.138
ansky+3.124
agers+3.025
Neg logit contributions
aeda-12.297
apult-12.075
elaide-11.839
cles-11.764
berus-11.674
Token to
Token ID284
Feature activation+1.28e+00

Pos logit contributions
itized+1.027
PD+1.026
olk+1.018
 reviewer+1.010
 renamed+1.008
Neg logit contributions
apult-1.820
cles-1.807
aeda-1.794
berus-1.734
riots-1.731
Token say
Token ID910
Feature activation-2.40e+00

Pos logit contributions
cles+1.139
apult+1.138
aeda+1.121
riots+1.078
berus+1.075
Neg logit contributions
itized-0.770
olk-0.752
PD-0.748
essor-0.741
 reviewer-0.738
Token:
Token ID25
Feature activation-3.08e-01

Pos logit contributions
itized+1.252
PD+1.245
olk+1.236
 reviewer+1.233
 renamed+1.224
Neg logit contributions
apult-2.326
cles-2.309
aeda-2.302
elaide-2.212
riots-2.203
Token "
Token ID366
Feature activation+1.96e+00

Pos logit contributions
itized+0.117
PD+0.115
olk+0.114
 reviewer+0.113
 renamed+0.111
Neg logit contributions
apult-0.342
cles-0.341
aeda-0.338
riots-0.327
elaide-0.327
Token F
Token ID376
Feature activation-5.43e-01

Pos logit contributions
apult+0.579
cles+0.578
aeda+0.573
riots+0.552
elaide+0.549
Neg logit contributions
itized-0.321
PD-0.315
olk-0.314
 reviewer-0.309
agers-0.308
Tokenender
Token ID2194
Feature activation-1.91e+00

Pos logit contributions
itized+0.325
PD+0.319
olk+0.319
 reviewer+0.315
agers+0.314
Neg logit contributions
apult-0.487
cles-0.485
aeda-0.480
riots-0.461
elaide-0.460
Token Jaguar
Token ID39288
Feature activation-5.27e-01

Pos logit contributions
itized+0.964
 reviewer+0.942
olk+0.940
PD+0.939
 renamed+0.936
Neg logit contributions
apult-1.881
cles-1.873
aeda-1.858
riots-1.793
elaide-1.790
Token
Token ID198
Feature activation+6.69e-01

Pos logit contributions
itized+0.266
PD+0.260
olk+0.260
 reviewer+0.259
 renamed+0.256
Neg logit contributions
apult-0.520
cles-0.518
aeda-0.513
riots-0.495
elaide-0.495
Token
Token ID198
Feature activation+1.26e+00

Pos logit contributions
cles+0.689
apult+0.687
aeda+0.677
riots+0.657
berus+0.655
Neg logit contributions
itized-0.308
 reviewer-0.299
olk-0.298
agers-0.294
PD-0.293
TokenC
Token ID34
Feature activation+9.94e+00

Pos logit contributions
cles+1.178
apult+1.176
aeda+1.159
riots+1.123
berus+1.112
Neg logit contributions
itized-0.696
olk-0.682
 reviewer-0.681
PD-0.673
 renamed-0.672
Tokenob
Token ID672
Feature activation+6.03e+00

Pos logit contributions
aeda+6.541
apult+6.385
cles+6.364
riots+6.003
berus+5.868
Neg logit contributions
 reviewer-7.824
 renamed-7.812
itized-7.655
essor-7.577
 Enforcement-7.539
Tokenain
Token ID391
Feature activation+3.77e+00

Pos logit contributions
cles+5.865
apult+5.836
aeda+5.765
riots+5.669
berus+5.550
Neg logit contributions
PD-2.985
 reviewer-2.965
itized-2.964
 renamed-2.897
agers-2.845
Token was
Token ID373
Feature activation+6.55e-01

Pos logit contributions
cles+3.489
apult+3.440
aeda+3.386
riots+3.272
elaide+3.251
Neg logit contributions
itized-2.091
olk-2.048
PD-2.031
essor-2.004
agers-1.988
Token affected
Token ID5676
Feature activation-1.12e+00

Pos logit contributions
cles+0.619
apult+0.619
aeda+0.609
riots+0.587
elaide+0.586
Neg logit contributions
itized-0.358
olk-0.351
PD-0.350
 reviewer-0.345
essor-0.344
Token enough
Token ID1576
Feature activation+1.18e+00

Pos logit contributions
itized+0.603
olk+0.591
PD+0.591
 reviewer+0.588
 renamed+0.583
Neg logit contributions
apult-1.066
cles-1.057
aeda-1.050
riots-1.009
berus-1.008
Token of
Token ID286
Feature activation+1.02e+00

Pos logit contributions
cles+3.481
apult+3.480
aeda+3.418
riots+3.284
elaide+3.276
Neg logit contributions
itized-2.146
olk-2.104
PD-2.099
essor-2.079
 reviewer-2.078
Token your
Token ID534
Feature activation-2.68e-01

Pos logit contributions
apult+0.956
cles+0.953
aeda+0.943
riots+0.906
elaide+0.905
Neg logit contributions
itized-0.561
olk-0.550
PD-0.549
 reviewer-0.542
agers-0.540
Token existence
Token ID6224
Feature activation+2.22e+00

Pos logit contributions
itized+0.153
PD+0.150
olk+0.149
 reviewer+0.149
 renamed+0.147
Neg logit contributions
apult-0.248
cles-0.247
aeda-0.245
riots-0.236
elaide-0.235
Token you
Token ID345
Feature activation+3.05e-01

Pos logit contributions
apult+2.137
cles+2.133
aeda+2.107
riots+2.031
elaide+2.027
Neg logit contributions
itized-1.178
olk-1.153
PD-1.151
 reviewer-1.141
agers-1.133
Token are
Token ID389
Feature activation+2.57e+00

Pos logit contributions
apult+0.273
cles+0.272
aeda+0.268
riots+0.258
elaide+0.258
Neg logit contributions
itized-0.182
olk-0.178
PD-0.178
 reviewer-0.176
agers-0.176
Token complete
Token ID1844
Feature activation+7.34e+00

Pos logit contributions
apult+2.281
cles+2.281
aeda+2.241
riots+2.155
elaide+2.136
Neg logit contributions
itized-1.533
olk-1.511
PD-1.499
 reviewer-1.481
essor-1.480
Token,
Token ID11
Feature activation-3.99e-01

Pos logit contributions
apult+6.436
cles+6.415
aeda+6.316
riots+6.148
berus+6.017
Neg logit contributions
olk-4.183
PD-4.156
agers-4.130
itized-4.128
 reviewer-4.097
Token whole
Token ID2187
Feature activation+2.86e+00

Pos logit contributions
itized+0.221
PD+0.216
olk+0.216
 reviewer+0.215
 renamed+0.213
Neg logit contributions
apult-0.375
cles-0.373
aeda-0.370
elaide-0.356
riots-0.355
Token,
Token ID11
Feature activation-1.77e+00

Pos logit contributions
apult+2.702
cles+2.693
aeda+2.662
riots+2.567
elaide+2.559
Neg logit contributions
itized-1.552
PD-1.530
olk-1.526
 reviewer-1.515
agers-1.507
Token perfect
Token ID2818
Feature activation+3.41e+00

Pos logit contributions
itized+0.944
PD+0.919
 reviewer+0.918
olk+0.917
 renamed+0.913
Neg logit contributions
apult-1.699
cles-1.689
aeda-1.676
elaide-1.614
berus-1.613
Token and
Token ID290
Feature activation-1.32e+00

Pos logit contributions
apult+3.169
cles+3.163
aeda+3.120
riots+3.017
elaide+2.999
Neg logit contributions
itized-1.883
PD-1.868
olk-1.865
 reviewer-1.844
 renamed-1.835
Token the
Token ID262
Feature activation-8.93e-01

Pos logit contributions
apult+1.249
cles+1.247
aeda+1.233
riots+1.188
elaide+1.184
Neg logit contributions
itized-0.706
olk-0.693
PD-0.693
 reviewer-0.685
agers-0.680
Token absorption
Token ID24774
Feature activation-3.50e-02

Pos logit contributions
itized+0.500
olk+0.489
PD+0.488
 reviewer+0.486
 renamed+0.482
Neg logit contributions
apult-0.837
cles-0.832
aeda-0.825
elaide-0.794
riots-0.793
Token grows
Token ID13676
Feature activation-2.39e+00

Pos logit contributions
itized+0.021
PD+0.020
olk+0.020
 reviewer+0.020
 renamed+0.020
Neg logit contributions
apult-0.032
cles-0.032
aeda-0.031
elaide-0.030
riots-0.030
Token with
Token ID351
Feature activation-2.96e+00

Pos logit contributions
itized+1.293
PD+1.260
 reviewer+1.251
stead+1.242
olk+1.242
Neg logit contributions
apult-2.294
aeda-2.258
cles-2.257
riots-2.181
elaide-2.181
Token [
Token ID685
Feature activation+2.62e+00

Pos logit contributions
itized+1.634
PD+1.593
 reviewer+1.582
agers+1.579
olk+1.578
Neg logit contributions
apult-2.793
cles-2.779
aeda-2.762
riots-2.659
elaide-2.655
TokenCO
Token ID8220
Feature activation+7.22e+00

Pos logit contributions
apult+2.138
cles+2.133
aeda+2.103
riots+2.014
elaide+2.001
Neg logit contributions
itized-1.769
olk-1.739
 reviewer-1.734
PD-1.726
 renamed-1.721
Token 2
Token ID362
Feature activation+1.57e+00

Pos logit contributions
apult+6.161
cles+6.128
aeda+6.090
berus+5.845
nea+5.809
Neg logit contributions
itized-4.308
agers-4.198
essor-4.192
 reviewer-4.179
ansky-4.159
Token ]
Token ID2361
Feature activation+2.48e+00

Pos logit contributions
apult+1.903
cles+1.897
aeda+1.883
riots+1.827
berus+1.823
Neg logit contributions
itized-0.444
olk-0.426
PD-0.426
 reviewer-0.418
agers-0.414
Token due
Token ID2233
Feature activation-3.31e+00

Pos logit contributions
apult+2.548
cles+2.548
aeda+2.519
riots+2.434
elaide+2.424
Neg logit contributions
itized-1.135
olk-1.114
PD-1.104
 reviewer-1.102
agers-1.090
Token to
Token ID284
Feature activation-2.65e+00

Pos logit contributions
itized+1.593
olk+1.543
PD+1.524
 reviewer+1.513
agers+1.499
Neg logit contributions
apult-3.345
cles-3.299
aeda-3.275
riots-3.200
berus-3.178
Token fertil
Token ID19078
Feature activation+3.32e+00

Pos logit contributions
itized+1.375
PD+1.336
olk+1.334
 reviewer+1.332
agers+1.324
Neg logit contributions
apult-2.583
cles-2.564
aeda-2.555
elaide-2.465
riots-2.455
Token speaker
Token ID10834
Feature activation-1.64e+00

Pos logit contributions
itized+0.100
PD+0.098
olk+0.098
 reviewer+0.098
 renamed+0.097
Neg logit contributions
apult-0.135
cles-0.134
aeda-0.133
elaide-0.128
riots-0.127
Token of
Token ID286
Feature activation+1.81e+00

Pos logit contributions
itized+0.852
PD+0.849
 renamed+0.834
 reviewer+0.830
olk+0.830
Neg logit contributions
apult-1.588
cles-1.577
aeda-1.574
elaide-1.534
riots-1.515
Token Catalan
Token ID31066
Feature activation+6.40e+00

Pos logit contributions
apult+1.558
cles+1.553
aeda+1.538
riots+1.473
elaide+1.472
Neg logit contributions
itized-1.143
olk-1.125
PD-1.124
 reviewer-1.115
 renamed-1.108
Token Parliament
Token ID8411
Feature activation+1.95e+00

Pos logit contributions
cles+5.017
apult+4.995
aeda+4.862
riots+4.670
nea+4.627
Neg logit contributions
itized-4.455
 reviewer-4.313
olk-4.310
agers-4.303
stead-4.303
Token,
Token ID11
Feature activation+1.21e+00

Pos logit contributions
apult+1.831
cles+1.824
aeda+1.806
riots+1.738
elaide+1.737
Neg logit contributions
itized-1.085
PD-1.065
olk-1.062
 reviewer-1.054
 renamed-1.046
Token Car
Token ID1879
Feature activation+8.29e+00

Pos logit contributions
apult+1.105
cles+1.102
aeda+1.090
riots+1.048
elaide+1.047
Neg logit contributions
itized-0.703
PD-0.690
olk-0.688
 reviewer-0.684
 renamed-0.679
Tokenme
Token ID1326
Feature activation-8.45e-01

Pos logit contributions
cles+5.846
apult+5.743
aeda+5.582
berus+5.412
nea+5.400
Neg logit contributions
itized-6.313
 reviewer-6.312
 renamed-6.243
PD-6.230
olk-6.196
Token For
Token ID1114
Feature activation+7.86e-01

Pos logit contributions
itized+0.492
PD+0.490
olk+0.489
agers+0.482
stead+0.480
Neg logit contributions
apult-0.762
cles-0.757
aeda-0.747
riots-0.725
elaide-0.724
Tokencade
Token ID46395
Feature activation+4.14e+00

Pos logit contributions
apult+0.607
cles+0.601
aeda+0.594
riots+0.569
elaide+0.568
Neg logit contributions
itized-0.569
olk-0.561
PD-0.561
agers-0.556
 reviewer-0.554
Tokenll
Token ID297
Feature activation-5.04e+00

Pos logit contributions
cles+2.080
apult+2.013
aeda+1.996
riots+1.857
berus+1.842
Neg logit contributions
itized-4.102
olk-4.065
PD-4.058
 reviewer-4.055
agers-4.054
Token,
Token ID11
Feature activation+6.31e-01

Pos logit contributions
olk+2.492
PD+2.443
 renamed+2.409
itized+2.404
agers+2.400
Neg logit contributions
apult-4.912
cles-4.845
aeda-4.838
berus-4.738
elaide-4.709
TokenOWER
Token ID36048
Feature activation+1.73e+00

Pos logit contributions
apult+2.903
cles+2.891
aeda+2.868
riots+2.761
elaide+2.753
Neg logit contributions
itized-1.833
 reviewer-1.792
 renamed-1.784
olk-1.775
PD-1.767
Tokenmag
Token ID19726
Feature activation-1.18e+00

Pos logit contributions
apult+1.550
cles+1.545
aeda+1.528
riots+1.468
elaide+1.465
Neg logit contributions
itized-1.033
PD-1.014
olk-1.013
 reviewer-1.005
agers-0.997
Tokenazine
Token ID4994
Feature activation-6.16e-01

Pos logit contributions
itized+0.537
PD+0.531
olk+0.522
 reviewer+0.522
essor+0.515
Neg logit contributions
cles-1.221
apult-1.220
aeda-1.217
berus-1.166
riots-1.166
Token)
Token ID8
Feature activation+2.26e+00

Pos logit contributions
PD+0.247
itized+0.247
olk+0.242
 reviewer+0.242
agers+0.237
Neg logit contributions
cles-0.670
apult-0.669
aeda-0.664
riots-0.642
berus-0.640
Token<|endoftext|>
Token ID50256
Feature activation+4.90e-02

Pos logit contributions
apult+2.149
cles+2.135
aeda+2.113
riots+2.035
elaide+2.033
Neg logit contributions
itized-1.226
olk-1.197
PD-1.188
agers-1.180
 reviewer-1.176
TokenC
Token ID34
Feature activation+9.69e+00

Pos logit contributions
apult+0.043
cles+0.043
aeda+0.043
elaide+0.041
riots+0.041
Neg logit contributions
itized-0.030
PD-0.029
olk-0.029
 reviewer-0.029
agers-0.029
Tokenit
Token ID270
Feature activation+3.24e+00

Pos logit contributions
aeda+8.887
cles+8.840
apult+8.766
elaide+8.376
riots+8.366
Neg logit contributions
itized-5.074
 reviewer-5.053
 renamed-4.989
stead-4.848
essor-4.777
Tokenib
Token ID571
Feature activation+2.86e+00

Pos logit contributions
apult+2.363
cles+2.351
aeda+2.312
riots+2.210
elaide+2.201
Neg logit contributions
itized-2.483
PD-2.441
olk-2.438
 reviewer-2.431
 renamed-2.414
Tokenank
Token ID962
Feature activation-2.85e+00

Pos logit contributions
apult+2.654
cles+2.653
aeda+2.621
riots+2.522
elaide+2.520
Neg logit contributions
itized-1.608
PD-1.573
olk-1.566
 reviewer-1.564
agers-1.548
Token fore
Token ID1674
Feature activation+1.20e+00

Pos logit contributions
itized+1.496
PD+1.486
 reviewer+1.477
 renamed+1.475
olk+1.458
Neg logit contributions
apult-2.736
aeda-2.718
cles-2.714
berus-2.604
elaide-2.602
Tokenclosed
Token ID20225
Feature activation-2.06e+00

Pos logit contributions
apult+0.933
cles+0.928
aeda+0.920
elaide+0.873
riots+0.873
Neg logit contributions
itized-0.857
PD-0.844
olk-0.842
 reviewer-0.837
agers-0.836
Token one
Token ID530
Feature activation-2.65e+00

Pos logit contributions
itized+1.949
 reviewer+1.906
PD+1.891
olk+1.888
agers+1.875
Neg logit contributions
apult-4.284
cles-4.238
aeda-4.223
riots-4.096
berus-4.075
Token side
Token ID1735
Feature activation+2.88e-01

Pos logit contributions
itized+0.852
 reviewer+0.843
PD+0.820
olk+0.816
 renamed+0.810
Neg logit contributions
apult-3.094
cles-3.075
aeda-3.064
riots-2.979
berus-2.971
Token,
Token ID11
Feature activation-2.07e-01

Pos logit contributions
apult+0.278
cles+0.277
aeda+0.274
riots+0.264
berus+0.263
Neg logit contributions
itized-0.153
PD-0.149
olk-0.149
 reviewer-0.148
 renamed-0.147
Token and
Token ID290
Feature activation+3.89e-01

Pos logit contributions
itized+0.112
olk+0.110
PD+0.110
 reviewer+0.109
 renamed+0.108
Neg logit contributions
apult-0.197
cles-0.196
aeda-0.194
riots-0.187
elaide-0.186
Token not
Token ID407
Feature activation+2.16e-01

Pos logit contributions
apult+0.375
cles+0.375
aeda+0.370
riots+0.357
elaide+0.356
Neg logit contributions
itized-0.205
PD-0.200
olk-0.200
 reviewer-0.198
agers-0.197
Token much
Token ID881
Feature activation+1.20e+00

Pos logit contributions
apult+0.207
cles+0.207
aeda+0.205
riots+0.197
elaide+0.197
Neg logit contributions
itized-0.115
PD-0.112
olk-0.112
 reviewer-0.111
agers-0.110
Token on
Token ID319
Feature activation-4.91e+00

Pos logit contributions
apult+1.072
cles+1.071
aeda+1.055
elaide+1.014
riots+1.014
Neg logit contributions
itized-0.720
PD-0.707
olk-0.704
 reviewer-0.697
agers-0.696
Token the
Token ID262
Feature activation-1.35e+00

Pos logit contributions
itized+2.181
PD+2.165
olk+2.157
 reviewer+2.155
 renamed+2.147
Neg logit contributions
apult-5.096
aeda-5.061
cles-5.044
riots-4.862
berus-4.858
Token other
Token ID584
Feature activation+1.33e+00

Pos logit contributions
itized+0.889
 reviewer+0.880
olk+0.879
PD+0.874
 renamed+0.872
Neg logit contributions
apult-1.116
cles-1.115
aeda-1.105
berus-1.055
riots-1.054
Token.
Token ID13
Feature activation-1.93e-01

Pos logit contributions
apult+1.265
cles+1.262
aeda+1.248
riots+1.202
elaide+1.200
Neg logit contributions
itized-0.724
PD-0.709
olk-0.708
 reviewer-0.702
agers-0.697
Token But
Token ID887
Feature activation+1.61e+00

Pos logit contributions
itized+0.098
olk+0.095
PD+0.095
 reviewer+0.095
agers+0.094
Neg logit contributions
apult-0.190
cles-0.190
aeda-0.188
riots-0.181
elaide-0.180
Token.
Token ID13
Feature activation-7.99e-02

Pos logit contributions
itized+0.031
PD+0.031
 reviewer+0.031
 renamed+0.031
olk+0.031
Neg logit contributions
apult-0.055
cles-0.054
aeda-0.054
berus-0.052
riots-0.052
Token He
Token ID679
Feature activation+6.27e-01

Pos logit contributions
itized+0.038
olk+0.037
PD+0.037
 reviewer+0.037
agers+0.036
Neg logit contributions
apult-0.081
cles-0.081
aeda-0.080
riots-0.077
elaide-0.077
Token graduated
Token ID18303
Feature activation+1.48e+00

Pos logit contributions
cles+0.593
apult+0.589
aeda+0.579
riots+0.558
berus+0.558
Neg logit contributions
itized-0.346
PD-0.339
olk-0.338
 reviewer-0.334
essor-0.331
Token from
Token ID422
Feature activation-9.64e-01

Pos logit contributions
apult+1.404
cles+1.400
aeda+1.385
riots+1.334
elaide+1.331
Neg logit contributions
itized-0.799
PD-0.782
olk-0.781
 reviewer-0.774
agers-0.770
Token Dartmouth
Token ID47888
Feature activation+2.99e+00

Pos logit contributions
itized+0.519
PD+0.512
olk+0.510
 reviewer+0.506
 renamed+0.505
Neg logit contributions
apult-0.919
cles-0.917
aeda-0.908
elaide-0.873
riots-0.873
Token in
Token ID287
Feature activation+2.14e+00

Pos logit contributions
apult+2.751
cles+2.731
aeda+2.700
riots+2.604
elaide+2.593
Neg logit contributions
itized-1.716
PD-1.668
olk-1.665
 reviewer-1.660
agers-1.650
Token 1973
Token ID15674
Feature activation-8.25e-01

Pos logit contributions
cles+2.081
apult+2.078
aeda+2.050
riots+1.982
berus+1.967
Neg logit contributions
itized-1.116
PD-1.078
olk-1.071
 reviewer-1.057
essor-1.051
Token and
Token ID290
Feature activation+1.28e+00

Pos logit contributions
itized+0.409
PD+0.399
 renamed+0.399
olk+0.398
 reviewer+0.397
Neg logit contributions
apult-0.822
cles-0.819
aeda-0.816
berus-0.786
riots-0.783
Token then
Token ID788
Feature activation+3.70e-01

Pos logit contributions
cles+1.177
apult+1.168
aeda+1.152
riots+1.104
berus+1.103
Neg logit contributions
itized-0.738
olk-0.724
PD-0.723
agers-0.711
 reviewer-0.709
Token law
Token ID1099
Feature activation-5.47e+00

Pos logit contributions
cles+0.341
apult+0.340
aeda+0.335
riots+0.322
berus+0.321
Neg logit contributions
itized-0.212
olk-0.208
PD-0.208
 reviewer-0.205
agers-0.205
Token school
Token ID1524
Feature activation-3.16e+00

Pos logit contributions
 renamed+1.897
itized+1.894
PD+1.888
olk+1.872
 reviewer+1.851
Neg logit contributions
apult-6.209
aeda-6.121
cles-6.093
riots-5.951
berus-5.931
Token through
Token ID832
Feature activation+1.56e+00

Pos logit contributions
itized+0.684
PD+0.672
olk+0.671
 reviewer+0.669
 renamed+0.667
Neg logit contributions
apult-1.210
cles-1.203
aeda-1.195
riots-1.152
elaide-1.150
Token the
Token ID262
Feature activation-5.72e-01

Pos logit contributions
apult+1.536
cles+1.532
aeda+1.515
riots+1.460
berus+1.459
Neg logit contributions
itized-0.784
olk-0.765
PD-0.765
 reviewer-0.757
agers-0.751
Token Flor
Token ID4432
Feature activation-2.18e+00

Pos logit contributions
itized+0.331
PD+0.325
olk+0.324
 reviewer+0.323
 renamed+0.321
Neg logit contributions
apult-0.522
cles-0.521
aeda-0.515
riots-0.496
elaide-0.496
Tokena
Token ID64
Feature activation-1.68e-01

Pos logit contributions
itized+1.165
olk+1.151
agers+1.131
PD+1.129
essor+1.126
Neg logit contributions
cles-2.067
apult-2.064
aeda-2.039
elaide-1.972
riots-1.963
Token Family
Token ID7884
Feature activation-2.27e+00

Pos logit contributions
itized+0.129
PD+0.127
olk+0.127
 reviewer+0.126
 renamed+0.126
Neg logit contributions
apult-0.122
cles-0.122
aeda-0.120
elaide-0.114
riots-0.114
Token Foundation
Token ID5693
Feature activation+3.00e+00

Pos logit contributions
itized+1.260
PD+1.249
 renamed+1.241
olk+1.240
 reviewer+1.229
Neg logit contributions
apult-2.107
cles-2.089
aeda-2.088
elaide-2.020
riots-2.004
Token.
Token ID13
Feature activation+6.68e-01

Pos logit contributions
apult+2.809
cles+2.800
aeda+2.761
riots+2.658
berus+2.657
Neg logit contributions
itized-1.660
olk-1.621
PD-1.618
 reviewer-1.608
agers-1.595
Token
Token ID198
Feature activation-3.95e-01

Pos logit contributions
apult+0.657
cles+0.656
aeda+0.649
riots+0.626
elaide+0.626
Neg logit contributions
itized-0.341
PD-0.334
olk-0.332
 reviewer-0.330
 renamed-0.328
Token
Token ID198
Feature activation+9.13e-02

Pos logit contributions
itized+0.173
olk+0.168
 reviewer+0.167
PD+0.167
agers+0.165
Neg logit contributions
apult-0.416
cles-0.416
aeda-0.410
riots-0.397
berus-0.396
TokenOthers
Token ID25599
Feature activation+3.75e+00

Pos logit contributions
apult+0.081
cles+0.080
aeda+0.080
elaide+0.076
riots+0.076
Neg logit contributions
itized-0.056
PD-0.055
olk-0.054
 reviewer-0.054
agers-0.054
Token involved
Token ID2950
Feature activation-3.52e-01

Pos logit contributions
cles+3.536
apult+3.522
aeda+3.466
berus+3.334
riots+3.321
Neg logit contributions
itized-2.040
PD-1.995
olk-1.993
agers-1.961
essor-1.949
Token key
Token ID1994
Feature activation+4.06e+00

Pos logit contributions
apult+0.979
cles+0.977
aeda+0.965
riots+0.929
elaide+0.927
Neg logit contributions
itized-0.590
PD-0.578
olk-0.578
 reviewer-0.573
agers-0.569
Token plan
Token ID1410
Feature activation+2.20e+00

Pos logit contributions
apult+3.867
cles+3.846
aeda+3.796
riots+3.659
elaide+3.642
Neg logit contributions
itized-2.179
olk-2.149
PD-2.143
 reviewer-2.119
agers-2.106
Tokenks
Token ID591
Feature activation-3.31e+00

Pos logit contributions
cles+1.743
apult+1.742
aeda+1.712
riots+1.638
elaide+1.629
Neg logit contributions
itized-1.545
PD-1.516
olk-1.514
 reviewer-1.506
 renamed-1.499
Token of
Token ID286
Feature activation+1.53e+00

Pos logit contributions
itized+1.746
olk+1.708
PD+1.707
 renamed+1.698
 reviewer+1.688
Neg logit contributions
cles-3.146
aeda-3.139
apult-3.131
berus-3.065
elaide-3.047
Token this
Token ID428
Feature activation-2.51e+00

Pos logit contributions
apult+1.485
cles+1.476
aeda+1.463
riots+1.409
elaide+1.403
Neg logit contributions
itized-0.799
olk-0.780
PD-0.780
 reviewer-0.773
agers-0.767
Token world
Token ID995
Feature activation+3.26e+00

Pos logit contributions
itized+1.484
PD+1.457
 reviewer+1.455
 renamed+1.452
olk+1.452
Neg logit contributions
cles-2.242
aeda-2.231
apult-2.227
elaide-2.153
berus-2.143
Token beating
Token ID11226
Feature activation+5.11e-01

Pos logit contributions
apult+3.058
cles+3.046
aeda+3.009
riots+2.897
elaide+2.888
Neg logit contributions
itized-1.815
olk-1.777
PD-1.776
 reviewer-1.761
agers-1.748
Token military
Token ID2422
Feature activation-3.27e+00

Pos logit contributions
apult+0.503
cles+0.502
aeda+0.497
riots+0.479
elaide+0.479
Neg logit contributions
itized-0.260
PD-0.254
olk-0.253
 reviewer-0.252
 renamed-0.249
Token machine
Token ID4572
Feature activation+3.36e+00

Pos logit contributions
itized+1.765
PD+1.733
 reviewer+1.724
olk+1.720
 renamed+1.706
Neg logit contributions
apult-3.094
cles-3.077
aeda-3.061
riots-2.948
elaide-2.939
Token.
Token ID13
Feature activation-4.73e-01

Pos logit contributions
apult+3.118
cles+3.090
aeda+3.041
riots+2.942
elaide+2.923
Neg logit contributions
itized-1.913
olk-1.866
PD-1.852
 reviewer-1.845
essor-1.825
Token
Token ID198
Feature activation-1.75e+00

Pos logit contributions
itized+0.218
PD+0.216
olk+0.214
 reviewer+0.211
 renamed+0.210
Neg logit contributions
cles-0.486
apult-0.485
aeda-0.480
elaide-0.467
riots-0.465
Token brain
Token ID3632
Feature activation+3.52e+00

Pos logit contributions
apult+1.346
cles+1.346
aeda+1.326
elaide+1.273
riots+1.272
Neg logit contributions
itized-0.795
olk-0.781
PD-0.780
 reviewer-0.772
agers-0.769
Token was
Token ID373
Feature activation-3.46e-01

Pos logit contributions
apult+3.363
cles+3.363
aeda+3.307
riots+3.186
elaide+3.176
Neg logit contributions
itized-1.864
olk-1.834
PD-1.819
 reviewer-1.797
agers-1.797
Token not
Token ID407
Feature activation+6.25e-01

Pos logit contributions
itized+0.186
PD+0.182
olk+0.182
 reviewer+0.180
agers+0.179
Neg logit contributions
apult-0.330
cles-0.329
aeda-0.326
riots-0.314
elaide-0.313
Token necessary
Token ID3306
Feature activation+2.13e+00

Pos logit contributions
apult+0.588
cles+0.587
aeda+0.580
riots+0.558
elaide+0.557
Neg logit contributions
itized-0.344
PD-0.336
olk-0.336
 reviewer-0.333
essor-0.331
Token to
Token ID284
Feature activation-1.68e+00

Pos logit contributions
apult+1.906
cles+1.902
aeda+1.881
riots+1.804
elaide+1.803
Neg logit contributions
itized-1.272
PD-1.247
olk-1.246
 reviewer-1.235
agers-1.228
Token master
Token ID4958
Feature activation+2.34e+00

Pos logit contributions
itized+0.936
PD+0.919
olk+0.917
 reviewer+0.913
agers+0.905
Neg logit contributions
apult-1.577
cles-1.574
aeda-1.555
riots-1.503
elaide-1.500
Token multiple
Token ID3294
Feature activation+3.85e+00

Pos logit contributions
apult+2.180
cles+2.177
aeda+2.147
elaide+2.059
riots+2.054
Neg logit contributions
itized-1.296
olk-1.268
PD-1.265
 reviewer-1.253
essor-1.250
Token simultaneous
Token ID29526
Feature activation+1.99e+00

Pos logit contributions
cles+3.807
apult+3.790
aeda+3.743
elaide+3.598
riots+3.583
Neg logit contributions
itized-1.894
olk-1.861
PD-1.850
essor-1.834
 reviewer-1.817
Token conceptual
Token ID23355
Feature activation-1.81e+00

Pos logit contributions
cles+1.894
apult+1.889
aeda+1.863
elaide+1.791
riots+1.785
Neg logit contributions
itized-1.067
olk-1.047
PD-1.041
essor-1.028
 reviewer-1.026
Token rule
Token ID3896
Feature activation-3.51e+00

Pos logit contributions
itized+0.951
PD+0.929
 reviewer+0.923
olk+0.922
agers+0.917
Neg logit contributions
apult-1.757
cles-1.744
aeda-1.737
riots-1.678
elaide-1.671
Token learning
Token ID4673
Feature activation-4.63e+00

Pos logit contributions
PD+1.696
olk+1.686
itized+1.685
agers+1.677
 reviewer+1.672
Neg logit contributions
apult-3.503
aeda-3.465
cles-3.446
elaide-3.342
riots-3.333
Token of
Token ID286
Feature activation+1.33e+00

Pos logit contributions
apult+0.406
cles+0.405
aeda+0.401
riots+0.386
elaide+0.385
Neg logit contributions
itized-0.228
PD-0.223
olk-0.222
 reviewer-0.222
 renamed-0.221
Token the
Token ID262
Feature activation+3.49e-01

Pos logit contributions
apult+1.254
cles+1.250
aeda+1.237
riots+1.191
elaide+1.188
Neg logit contributions
itized-0.737
PD-0.722
olk-0.722
 reviewer-0.714
agers-0.709
Token first
Token ID717
Feature activation+2.79e-01

Pos logit contributions
apult+0.328
cles+0.327
aeda+0.323
riots+0.311
berus+0.310
Neg logit contributions
itized-0.193
olk-0.189
PD-0.189
 reviewer-0.187
agers-0.185
Token water
Token ID1660
Feature activation-8.74e-01

Pos logit contributions
apult+0.266
cles+0.265
aeda+0.262
elaide+0.252
riots+0.252
Neg logit contributions
itized-0.152
PD-0.148
olk-0.148
 reviewer-0.148
 renamed-0.146
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
itized+0.492
PD+0.482
 reviewer+0.478
 renamed+0.474
olk+0.472
Neg logit contributions
apult-0.820
cles-0.812
aeda-0.806
elaide-0.779
riots-0.778
Token an
Token ID281
Feature activation-2.77e+00

Pos logit contributions
itized+0.737
olk+0.721
PD+0.721
 reviewer+0.719
 renamed+0.716
Neg logit contributions
apult-1.036
cles-1.034
aeda-1.022
riots-0.981
elaide-0.979
Token enormous
Token ID9812
Feature activation+1.90e+00

Pos logit contributions
itized+1.509
PD+1.450
olk+1.450
 renamed+1.448
 reviewer+1.447
Neg logit contributions
cles-2.611
apult-2.605
aeda-2.584
elaide-2.501
riots-2.498
Token White
Token ID2635
Feature activation-3.40e+00

Pos logit contributions
apult+1.700
cles+1.693
aeda+1.676
berus+1.607
riots+1.602
Neg logit contributions
itized-1.125
PD-1.114
olk-1.114
agers-1.093
stead-1.089
Token Elephant
Token ID42651
Feature activation-4.49e+00

Pos logit contributions
itized+2.026
PD+2.003
 reviewer+1.990
olk+1.977
 renamed+1.971
Neg logit contributions
cles-3.031
apult-3.007
aeda-2.990
elaide-2.883
berus-2.860
Token,
Token ID11
Feature activation-5.20e-01

Pos logit contributions
itized+2.337
 reviewer+2.312
 renamed+2.309
PD+2.277
olk+2.237
Neg logit contributions
cles-4.289
apult-4.269
aeda-4.237
elaide-4.141
riots-4.126
Token completely
Token ID3190
Feature activation+2.54e+00

Pos logit contributions
itized+0.275
PD+0.268
 reviewer+0.268
 renamed+0.268
olk+0.267
Neg logit contributions
cles-0.502
apult-0.502
aeda-0.496
elaide-0.478
riots-0.478
Token farm
Token ID5318
Feature activation-2.73e+00

Pos logit contributions
apult+1.955
cles+1.954
aeda+1.918
riots+1.856
berus+1.849
Neg logit contributions
itized-1.060
PD-1.029
olk-1.029
agers-1.016
 reviewer-1.012
Token nearby
Token ID6716
Feature activation+4.14e-01

Pos logit contributions
itized+1.194
 reviewer+1.175
PD+1.168
stead+1.163
olk+1.161
Neg logit contributions
apult-2.861
aeda-2.844
cles-2.837
elaide-2.748
riots-2.746
Token?
Token ID30
Feature activation+1.70e-01

Pos logit contributions
apult+0.448
cles+0.447
aeda+0.443
riots+0.429
elaide+0.428
Neg logit contributions
itized-0.169
PD-0.165
olk-0.164
 reviewer-0.163
 renamed-0.161
Token (
Token ID357
Feature activation-9.96e-01

Pos logit contributions
apult+0.157
cles+0.157
aeda+0.155
riots+0.149
elaide+0.149
Neg logit contributions
itized-0.096
PD-0.094
olk-0.094
 reviewer-0.094
agers-0.093
TokenThink
Token ID22073
Feature activation+1.19e+00

Pos logit contributions
itized+0.600
PD+0.593
olk+0.587
 reviewer+0.582
agers+0.580
Neg logit contributions
apult-0.888
cles-0.883
aeda-0.878
elaide-0.841
berus-0.839
Token of
Token ID286
Feature activation-1.71e-01

Pos logit contributions
apult+1.078
cles+1.075
aeda+1.063
riots+1.022
elaide+1.020
Neg logit contributions
itized-0.696
PD-0.682
olk-0.682
 reviewer-0.677
agers-0.672
Token The
Token ID383
Feature activation+2.04e+00

Pos logit contributions
itized+0.089
PD+0.087
olk+0.087
 reviewer+0.087
agers+0.086
Neg logit contributions
apult-0.166
cles-0.165
aeda-0.164
riots-0.158
elaide-0.158
Token Simpsons
Token ID34376
Feature activation-6.63e+00

Pos logit contributions
apult+1.855
cles+1.850
aeda+1.829
riots+1.758
elaide+1.755
Neg logit contributions
itized-1.194
PD-1.170
olk-1.170
 reviewer-1.161
agers-1.152
Token and
Token ID290
Feature activation-4.09e-02

Pos logit contributions
 renamed+3.150
PD+3.141
itized+3.132
 reviewer+3.126
agers+3.038
Neg logit contributions
apult-6.509
cles-6.496
aeda-6.449
elaide-6.288
prus-6.255
Token the
Token ID262
Feature activation+1.83e-01

Pos logit contributions
itized+0.022
PD+0.022
olk+0.022
 reviewer+0.022
agers+0.022
Neg logit contributions
apult-0.039
cles-0.038
aeda-0.038
riots-0.037
elaide-0.037
Token mon
Token ID937
Feature activation+1.30e+00

Pos logit contributions
apult+0.171
cles+0.170
aeda+0.168
riots+0.162
elaide+0.162
Neg logit contributions
itized-0.103
PD-0.101
olk-0.101
 reviewer-0.100
 renamed-0.099
Token been
Token ID587
Feature activation-2.28e+00

Pos logit contributions
itized+0.328
PD+0.321
olk+0.321
 reviewer+0.318
agers+0.316
Neg logit contributions
apult-0.567
cles-0.566
aeda-0.560
riots-0.539
elaide-0.538
Token a
Token ID257
Feature activation+8.16e-01

Pos logit contributions
itized+1.202
PD+1.179
olk+1.178
 reviewer+1.170
 renamed+1.165
Neg logit contributions
apult-2.195
cles-2.186
aeda-2.168
riots-2.089
berus-2.085
Token dedicated
Token ID7256
Feature activation+4.30e+00

Pos logit contributions
apult+0.756
cles+0.755
aeda+0.746
riots+0.718
berus+0.715
Neg logit contributions
itized-0.460
olk-0.450
PD-0.450
agers-0.446
 reviewer-0.442
Token anti
Token ID3098
Feature activation-1.00e+00

Pos logit contributions
cles+3.416
apult+3.385
aeda+3.375
riots+3.233
berus+3.178
Neg logit contributions
itized-2.929
agers-2.868
PD-2.866
olk-2.862
 renamed-2.826
Token-
Token ID12
Feature activation+1.93e-01

Pos logit contributions
itized+0.335
PD+0.327
olk+0.326
 reviewer+0.320
essor+0.315
Neg logit contributions
apult-1.158
cles-1.153
aeda-1.145
elaide-1.110
riots-1.108
Tokengun
Token ID7145
Feature activation-2.20e+00

Pos logit contributions
apult+0.145
cles+0.144
aeda+0.142
elaide+0.136
berus+0.135
Neg logit contributions
itized-0.143
PD-0.141
olk-0.141
 reviewer-0.139
agers-0.139
Token advocate
Token ID12811
Feature activation+3.64e+00

Pos logit contributions
itized+1.092
olk+1.078
 reviewer+1.073
PD+1.071
stead+1.060
Neg logit contributions
apult-2.195
cles-2.184
aeda-2.164
elaide-2.089
berus-2.087
Token in
Token ID287
Feature activation+1.11e+00

Pos logit contributions
cles+3.253
apult+3.241
aeda+3.190
elaide+3.073
riots+3.070
Neg logit contributions
itized-2.165
olk-2.114
PD-2.111
agers-2.088
 reviewer-2.081
Token her
Token ID607
Feature activation+7.38e-01

Pos logit contributions
apult+1.046
cles+1.043
aeda+1.032
riots+0.994
elaide+0.992
Neg logit contributions
itized-0.607
PD-0.595
olk-0.595
 reviewer-0.590
agers-0.585
Token private
Token ID2839
Feature activation+9.84e-01

Pos logit contributions
apult+0.659
cles+0.659
aeda+0.650
riots+0.625
elaide+0.623
Neg logit contributions
itized-0.442
PD-0.433
olk-0.432
 reviewer-0.429
agers-0.427
Token life
Token ID1204
Feature activation+7.89e-01

Pos logit contributions
apult+0.900
cles+0.899
aeda+0.889
riots+0.854
elaide+0.853
Neg logit contributions
itized-0.569
PD-0.554
olk-0.552
agers-0.548
 reviewer-0.548
Token The
Token ID383
Feature activation+1.76e+00

Pos logit contributions
itized+0.056
olk+0.055
PD+0.055
 reviewer+0.054
agers+0.054
Neg logit contributions
apult-0.093
cles-0.093
aeda-0.092
riots-0.089
elaide-0.088
Token trailers
Token ID33122
Feature activation-3.20e+00

Pos logit contributions
apult+1.627
cles+1.622
aeda+1.605
riots+1.544
elaide+1.540
Neg logit contributions
itized-0.995
PD-0.977
olk-0.975
agers-0.958
 reviewer-0.958
Token and
Token ID290
Feature activation-9.82e-01

Pos logit contributions
itized+1.758
 reviewer+1.754
PD+1.743
olk+1.733
 renamed+1.726
Neg logit contributions
apult-2.989
cles-2.973
aeda-2.961
berus-2.861
elaide-2.845
Token still
Token ID991
Feature activation-4.06e+00

Pos logit contributions
itized+0.538
PD+0.529
olk+0.527
 reviewer+0.527
 renamed+0.520
Neg logit contributions
apult-0.927
cles-0.925
aeda-0.915
riots-0.880
berus-0.880
Tokens
Token ID82
Feature activation-1.45e+00

Pos logit contributions
itized+1.975
PD+1.954
 reviewer+1.929
olk+1.928
agers+1.907
Neg logit contributions
apult-4.075
cles-4.025
aeda-3.993
berus-3.908
elaide-3.860
Token for
Token ID329
Feature activation-1.26e+00

Pos logit contributions
itized+0.801
PD+0.787
 reviewer+0.785
olk+0.785
 renamed+0.775
Neg logit contributions
apult-1.359
cles-1.354
aeda-1.344
berus-1.294
elaide-1.293
Token the
Token ID262
Feature activation-3.07e-01

Pos logit contributions
itized+0.658
PD+0.645
olk+0.642
 reviewer+0.640
agers+0.635
Neg logit contributions
apult-1.225
cles-1.221
aeda-1.209
berus-1.166
riots-1.165
Token upcoming
Token ID7865
Feature activation-1.15e+00

Pos logit contributions
itized+0.174
PD+0.171
olk+0.170
 reviewer+0.169
agers+0.168
Neg logit contributions
apult-0.284
cles-0.283
aeda-0.280
riots-0.269
elaide-0.269
Token episode
Token ID4471
Feature activation-4.75e+00

Pos logit contributions
itized+0.549
PD+0.537
olk+0.534
 reviewer+0.532
 renamed+0.527
Neg logit contributions
apult-1.165
cles-1.161
aeda-1.150
berus-1.109
elaide-1.109
Token have
Token ID423
Feature activation-1.29e+00

Pos logit contributions
itized+2.490
PD+2.471
 reviewer+2.462
 renamed+2.430
stead+2.423
Neg logit contributions
cles-4.517
apult-4.502
aeda-4.456
berus-4.346
elaide-4.306
Token already
Token ID1541
Feature activation+1.77e+00

Pos logit contributions
itized+0.673
PD+0.659
olk+0.657
 reviewer+0.655
 renamed+0.648
Neg logit contributions
apult-1.256
cles-1.251
aeda-1.239
riots-1.194
elaide-1.193
Token on
Token ID319
Feature activation-2.35e+00

Pos logit contributions
itized+0.051
PD+0.050
olk+0.050
 reviewer+0.049
agers+0.049
Neg logit contributions
apult-0.099
cles-0.099
aeda-0.098
riots-0.094
elaide-0.094
Token some
Token ID617
Feature activation-1.51e+00

Pos logit contributions
itized+1.172
PD+1.144
 reviewer+1.138
olk+1.134
 renamed+1.130
Neg logit contributions
apult-2.343
cles-2.329
aeda-2.312
riots-2.236
elaide-2.229
Token pretty
Token ID2495
Feature activation+2.27e+00

Pos logit contributions
itized+0.809
PD+0.790
 reviewer+0.786
olk+0.785
 renamed+0.781
Neg logit contributions
apult-1.448
cles-1.440
aeda-1.426
riots-1.378
elaide-1.377
Token heavy
Token ID4334
Feature activation-1.36e+00

Pos logit contributions
cles+2.164
apult+2.153
aeda+2.119
berus+2.045
riots+2.040
Neg logit contributions
itized-1.197
olk-1.181
PD-1.172
agers-1.156
essor-1.152
Token software
Token ID3788
Feature activation-5.36e+00

Pos logit contributions
itized+0.711
PD+0.695
olk+0.691
 reviewer+0.688
 renamed+0.683
Neg logit contributions
apult-1.329
cles-1.319
aeda-1.311
riots-1.264
elaide-1.261
Token correction
Token ID17137
Feature activation-1.22e+00

Pos logit contributions
itized+2.603
 reviewer+2.556
PD+2.554
 renamed+2.549
stead+2.518
Neg logit contributions
apult-5.350
aeda-5.288
cles-5.232
riots-5.167
elaide-5.093
Token,
Token ID11
Feature activation-1.29e+00

Pos logit contributions
itized+0.626
PD+0.613
olk+0.610
 reviewer+0.607
 renamed+0.605
Neg logit contributions
apult-1.196
cles-1.187
aeda-1.181
riots-1.139
elaide-1.134
Token especially
Token ID2592
Feature activation-1.02e+00

Pos logit contributions
itized+0.686
PD+0.672
olk+0.670
 reviewer+0.668
 renamed+0.664
Neg logit contributions
apult-1.244
cles-1.240
aeda-1.227
riots-1.184
elaide-1.183
Token in
Token ID287
Feature activation-1.89e+00

Pos logit contributions
itized+0.566
PD+0.556
olk+0.553
 reviewer+0.551
 renamed+0.547
Neg logit contributions
apult-0.958
cles-0.955
aeda-0.945
riots-0.911
elaide-0.910
Token the
Token ID262
Feature activation-2.42e-01

Pos logit contributions
itized+0.973
PD+0.958
 reviewer+0.951
olk+0.943
 renamed+0.938
Neg logit contributions
apult-1.851
cles-1.837
aeda-1.819
riots-1.767
elaide-1.759
Token corners
Token ID14371
Feature activation+2.10e+00

Pos logit contributions
itized+0.134
PD+0.131
olk+0.131
 reviewer+0.130
agers+0.129
Neg logit contributions
apult-0.228
cles-0.228
aeda-0.225
riots-0.217
elaide-0.217
Token film
Token ID2646
Feature activation+1.17e+00

Pos logit contributions
itized+0.657
PD+0.641
olk+0.638
 reviewer+0.636
 renamed+0.629
Neg logit contributions
apult-1.724
cles-1.717
aeda-1.704
elaide-1.650
riots-1.645
Token than
Token ID621
Feature activation+3.23e-01

Pos logit contributions
apult+1.057
cles+1.054
aeda+1.043
riots+1.002
elaide+1.001
Neg logit contributions
itized-0.688
PD-0.675
olk-0.673
 reviewer-0.669
 renamed-0.664
Token in
Token ID287
Feature activation-8.41e-01

Pos logit contributions
apult+0.305
cles+0.304
aeda+0.301
riots+0.291
elaide+0.289
Neg logit contributions
itized-0.177
olk-0.172
PD-0.172
agers-0.170
 reviewer-0.170
Token any
Token ID597
Feature activation+1.29e+00

Pos logit contributions
itized+0.464
PD+0.455
olk+0.455
 reviewer+0.451
agers+0.447
Neg logit contributions
apult-0.791
cles-0.789
aeda-0.781
riots-0.751
elaide-0.750
Token previous
Token ID2180
Feature activation-8.42e-01

Pos logit contributions
apult+1.059
cles+1.059
aeda+1.036
riots+1.005
elaide+0.991
Neg logit contributions
itized-0.855
olk-0.837
PD-0.835
agers-0.834
essor-0.829
Token live
Token ID2107
Feature activation-7.69e+00

Pos logit contributions
itized+0.406
PD+0.397
olk+0.396
 reviewer+0.393
agers+0.389
Neg logit contributions
apult-0.852
cles-0.849
aeda-0.841
riots-0.811
elaide-0.810
Token-
Token ID12
Feature activation+5.36e-01

Pos logit contributions
PD+2.449
itized+2.447
olk+2.363
stead+2.329
 reviewer+2.317
Neg logit contributions
apult-8.850
aeda-8.834
cles-8.807
berus-8.618
nea-8.518
Tokenaction
Token ID2673
Feature activation-2.07e+00

Pos logit contributions
apult+0.366
cles+0.363
aeda+0.358
riots+0.346
elaide+0.337
Neg logit contributions
itized-0.434
 reviewer-0.429
 renamed-0.426
essor-0.426
olk-0.425
Token TM
Token ID21232
Feature activation-7.42e+00

Pos logit contributions
itized+0.867
PD+0.846
olk+0.845
 reviewer+0.835
agers+0.826
Neg logit contributions
apult-2.225
cles-2.218
aeda-2.201
elaide-2.125
riots-2.124
TokenNT
Token ID11251
Feature activation-3.26e+00

Pos logit contributions
PD+3.373
olk+3.089
itized+3.072
agers+3.008
essor+3.004
Neg logit contributions
cles-7.801
aeda-7.726
apult-7.685
elaide-7.550
berus-7.503
Token movie
Token ID3807
Feature activation+7.46e-01

Pos logit contributions
itized+1.241
PD+1.222
olk+1.213
 reviewer+1.190
stead+1.180
Neg logit contributions
apult-3.615
cles-3.608
aeda-3.585
berus-3.473
elaide-3.472
Token fight
Token ID1907
Feature activation+3.42e+00

Pos logit contributions
apult+0.587
cles+0.586
aeda+0.578
riots+0.556
berus+0.554
Neg logit contributions
itized-0.384
olk-0.376
PD-0.376
 reviewer-0.372
agers-0.370
Token him
Token ID683
Feature activation+3.18e-01

Pos logit contributions
apult+3.185
cles+3.173
aeda+3.132
riots+3.021
berus+2.998
Neg logit contributions
itized-1.898
olk-1.857
PD-1.843
 reviewer-1.831
essor-1.811
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
apult+0.298
cles+0.297
aeda+0.295
riots+0.283
berus+0.283
Neg logit contributions
itized-0.177
PD-0.174
olk-0.174
 renamed-0.173
 reviewer-0.172
Token The
Token ID383
Feature activation+2.27e+00

Pos logit contributions
apult+1.123
cles+1.118
aeda+1.105
riots+1.065
berus+1.064
Neg logit contributions
itized-0.600
olk-0.585
PD-0.583
 reviewer-0.581
agers-0.575
Token Her
Token ID2332
Feature activation+6.24e-01

Pos logit contributions
apult+2.068
cles+2.056
aeda+2.031
riots+1.953
berus+1.945
Neg logit contributions
itized-1.330
PD-1.301
olk-1.301
 reviewer-1.277
agers-1.274
Tokenok
Token ID482
Feature activation-7.60e+00

Pos logit contributions
apult+0.456
cles+0.453
aeda+0.448
elaide+0.427
riots+0.425
Neg logit contributions
itized-0.476
PD-0.470
olk-0.469
agers-0.465
 reviewer-0.465
Tokeniller
Token ID4665
Feature activation-8.84e-01

Pos logit contributions
olk+4.421
 renamed+4.350
stead+4.343
itized+4.318
agers+4.292
Neg logit contributions
cles-6.648
apult-6.646
aeda-6.533
elaide-6.406
berus-6.335
Token was
Token ID373
Feature activation+6.30e-01

Pos logit contributions
itized+0.470
PD+0.463
olk+0.462
 renamed+0.457
 reviewer+0.457
Neg logit contributions
apult-0.845
cles-0.842
aeda-0.837
elaide-0.807
riots-0.804
Token big
Token ID1263
Feature activation+2.62e+00

Pos logit contributions
apult+0.578
cles+0.576
aeda+0.570
riots+0.548
elaide+0.547
Neg logit contributions
itized-0.362
PD-0.355
olk-0.355
 reviewer-0.352
 renamed-0.350
Token enough
Token ID1576
Feature activation-1.54e+00

Pos logit contributions
apult+2.489
cles+2.487
aeda+2.454
riots+2.366
elaide+2.363
Neg logit contributions
itized-1.416
PD-1.387
olk-1.386
 reviewer-1.375
agers-1.363
Token that
Token ID326
Feature activation-3.02e-01

Pos logit contributions
itized+0.766
PD+0.750
olk+0.748
 renamed+0.745
 reviewer+0.744
Neg logit contributions
apult-1.530
cles-1.514
aeda-1.513
elaide-1.455
riots-1.453
Token0
Token ID15
Feature activation-1.90e+00

Pos logit contributions
apult+1.307
cles+1.303
aeda+1.288
riots+1.238
elaide+1.235
Neg logit contributions
itized-0.862
olk-0.844
PD-0.842
 reviewer-0.840
agers-0.833
Token,
Token ID11
Feature activation-2.57e+00

Pos logit contributions
itized+0.929
PD+0.917
olk+0.914
 renamed+0.897
 reviewer+0.896
Neg logit contributions
apult-1.895
cles-1.885
aeda-1.871
riots-1.805
elaide-1.797
Token ].
Token ID20740
Feature activation+6.02e-01

Pos logit contributions
itized+1.087
PD+1.077
olk+1.054
 renamed+1.042
 reviewer+1.038
Neg logit contributions
cles-2.734
apult-2.732
aeda-2.716
riots-2.626
elaide-2.618
Token This
Token ID770
Feature activation-1.15e+00

Pos logit contributions
apult+0.578
cles+0.577
aeda+0.571
riots+0.550
elaide+0.549
Neg logit contributions
itized-0.320
PD-0.314
olk-0.313
 reviewer-0.311
agers-0.308
Token can
Token ID460
Feature activation-9.93e-01

Pos logit contributions
itized+0.610
PD+0.598
olk+0.597
 reviewer+0.596
 renamed+0.590
Neg logit contributions
apult-1.100
cles-1.094
aeda-1.086
riots-1.047
elaide-1.046
Token be
Token ID307
Feature activation-6.25e+00

Pos logit contributions
itized+0.576
olk+0.564
PD+0.563
 reviewer+0.560
 renamed+0.556
Neg logit contributions
apult-0.907
cles-0.903
aeda-0.896
riots-0.863
elaide-0.861
Token done
Token ID1760
Feature activation-2.11e+00

Pos logit contributions
 renamed+1.920
itized+1.911
PD+1.867
 reviewer+1.844
olk+1.831
Neg logit contributions
apult-7.337
aeda-7.247
cles-7.240
elaide-7.096
riots-7.078
Token with
Token ID351
Feature activation-2.69e+00

Pos logit contributions
itized+1.103
PD+1.075
olk+1.074
 reviewer+1.073
 renamed+1.069
Neg logit contributions
apult-2.044
cles-2.026
aeda-2.016
riots-1.952
elaide-1.944
Token the
Token ID262
Feature activation-8.98e-01

Pos logit contributions
itized+1.282
PD+1.259
 renamed+1.251
 reviewer+1.250
olk+1.246
Neg logit contributions
apult-2.722
cles-2.705
aeda-2.693
elaide-2.605
riots-2.604
Token following
Token ID1708
Feature activation-1.30e+00

Pos logit contributions
itized+0.563
PD+0.553
olk+0.552
 reviewer+0.550
 renamed+0.546
Neg logit contributions
apult-0.776
cles-0.774
aeda-0.765
riots-0.735
elaide-0.734
Token equation
Token ID16022
Feature activation+4.12e+00

Pos logit contributions
itized+0.601
PD+0.587
olk+0.584
 reviewer+0.581
 renamed+0.577
Neg logit contributions
apult-1.341
cles-1.335
aeda-1.325
riots-1.280
elaide-1.279
Token the
Token ID262
Feature activation-5.91e-02

Pos logit contributions
itized+0.615
olk+0.606
PD+0.604
 reviewer+0.602
agers+0.597
Neg logit contributions
apult-1.021
cles-1.019
aeda-1.011
riots-0.972
elaide-0.970
Token north
Token ID5093
Feature activation-3.53e-01

Pos logit contributions
itized+0.033
olk+0.033
PD+0.033
 reviewer+0.033
agers+0.032
Neg logit contributions
apult-0.055
cles-0.055
aeda-0.054
riots-0.052
elaide-0.052
Token than
Token ID621
Feature activation-5.16e-02

Pos logit contributions
itized+0.184
olk+0.181
PD+0.181
 reviewer+0.179
 renamed+0.177
Neg logit contributions
apult-0.342
cles-0.342
aeda-0.339
riots-0.326
berus-0.326
Token the
Token ID262
Feature activation-8.50e-01

Pos logit contributions
itized+0.027
olk+0.026
PD+0.026
 reviewer+0.026
agers+0.026
Neg logit contributions
apult-0.050
cles-0.050
aeda-0.049
riots-0.048
elaide-0.048
Token tiny
Token ID7009
Feature activation-2.26e+00

Pos logit contributions
itized+0.469
olk+0.462
PD+0.459
 reviewer+0.459
 renamed+0.456
Neg logit contributions
apult-0.798
cles-0.795
aeda-0.788
riots-0.759
elaide-0.756
Token sl
Token ID1017
Feature activation-1.06e+01

Pos logit contributions
itized+1.258
olk+1.236
 reviewer+1.232
PD+1.223
 renamed+1.217
Neg logit contributions
apult-2.105
cles-2.097
aeda-2.082
riots-2.001
elaide-1.997
Tokeniver
Token ID1428
Feature activation-1.24e+00

Pos logit contributions
agers+5.210
essor+5.126
ansky+4.994
olk+4.974
itized+4.878
Neg logit contributions
apult-10.204
aeda-9.849
cles-9.814
elaide-9.501
berus-9.448
Token of
Token ID286
Feature activation+1.96e-01

Pos logit contributions
itized+0.676
olk+0.664
PD+0.661
 renamed+0.657
 reviewer+0.654
Neg logit contributions
apult-1.178
cles-1.170
aeda-1.166
elaide-1.119
riots-1.118
Token sea
Token ID5417
Feature activation-1.65e-01

Pos logit contributions
apult+0.180
cles+0.180
aeda+0.178
riots+0.171
elaide+0.170
Neg logit contributions
itized-0.113
PD-0.111
olk-0.110
 reviewer-0.110
agers-0.109
Token that
Token ID326
Feature activation+1.13e+00

Pos logit contributions
itized+0.090
olk+0.088
PD+0.088
 reviewer+0.087
 renamed+0.087
Neg logit contributions
apult-0.156
cles-0.156
aeda-0.155
riots-0.149
elaide-0.149
Token divides
Token ID36319
Feature activation+3.22e+00

Pos logit contributions
apult+0.993
cles+0.992
aeda+0.978
riots+0.939
elaide+0.937
Neg logit contributions
itized-0.698
olk-0.684
PD-0.684
 reviewer-0.678
agers-0.674
Token Sp
Token ID1338
Feature activation-3.14e+00

Pos logit contributions
itized+0.063
olk+0.062
PD+0.062
 reviewer+0.061
 renamed+0.061
Neg logit contributions
apult-0.099
cles-0.099
aeda-0.098
elaide-0.094
riots-0.094
Tokenires
Token ID2387
Feature activation+3.40e+00

Pos logit contributions
itized+1.788
olk+1.762
agers+1.743
PD+1.739
stead+1.716
Neg logit contributions
apult-2.899
cles-2.870
aeda-2.843
riots-2.743
berus-2.741
Token vs
Token ID3691
Feature activation+3.01e+00

Pos logit contributions
apult+3.627
cles+3.623
aeda+3.574
riots+3.460
berus+3.452
Neg logit contributions
itized-1.429
PD-1.386
olk-1.385
 reviewer-1.370
agers-1.361
Token Ank
Token ID24792
Feature activation-6.49e+00

Pos logit contributions
apult+2.788
cles+2.769
aeda+2.737
riots+2.634
berus+2.631
Neg logit contributions
itized-1.693
olk-1.652
PD-1.647
 reviewer-1.636
agers-1.623
Tokenle
Token ID293
Feature activation-1.23e+00

Pos logit contributions
olk+4.264
itized+4.183
agers+4.179
essor+4.154
stead+4.135
Neg logit contributions
apult-5.170
cles-5.110
aeda-5.102
elaide-4.968
riots-4.882
Token Shank
Token ID41595
Feature activation-8.38e+00

Pos logit contributions
itized+0.737
PD+0.728
olk+0.727
stead+0.721
agers+0.720
Neg logit contributions
cles-1.088
apult-1.086
aeda-1.081
elaide-1.042
berus-1.035
Tokener
Token ID263
Feature activation+2.12e+00

Pos logit contributions
stead+4.267
olk+4.230
agers+4.219
PD+4.132
 reviewer+4.086
Neg logit contributions
aeda-7.731
cles-7.689
elaide-7.636
apult-7.628
berus-7.528
Token
Token ID198
Feature activation+1.22e+00

Pos logit contributions
apult+2.221
cles+2.214
aeda+2.188
riots+2.117
berus+2.111
Neg logit contributions
itized-0.945
PD-0.916
olk-0.914
 reviewer-0.908
 renamed-0.897
Token
Token ID198
Feature activation+1.59e+00

Pos logit contributions
cles+1.236
apult+1.228
aeda+1.209
riots+1.174
berus+1.172
Neg logit contributions
itized-0.580
 reviewer-0.565
olk-0.560
essor-0.555
agers-0.552
TokenPh
Token ID2725
Feature activation+9.83e-01

Pos logit contributions
apult+1.446
cles+1.443
aeda+1.422
riots+1.372
berus+1.364
Neg logit contributions
itized-0.930
olk-0.910
 reviewer-0.908
PD-0.904
 renamed-0.898
Tokeny
Token ID88
Feature activation-1.69e+00

Pos logit contributions
apult+0.893
cles+0.891
aeda+0.880
riots+0.847
elaide+0.845
Neg logit contributions
itized-0.573
olk-0.563
PD-0.562
 reviewer-0.557
agers-0.554