TOP ACTIVATIONS
MAX = 2.300

ur E CA l ' intention de sa maj est é
esp rit origin el des Cors aires [...] En cas de
all elbows and knees , Pl ath ian with a r
ind re ment , les Cors aires l oy aux rest
loans are Vi aches lav Pl ak as ov , Vol
eng agement qu ' ils av a ient pr it en
the # deb ates # Occup y The Deb ates pic
leave . OS HA ( Occup ational Health and Safety Administration
J ' ai l ' hon ne ur d ' ê
ament que le Command ement Cors aire ser ait ill é
s neo - Ott oman an vil fall hardest
cl able cat am aran Pl ast iki , which is
De vers . Sl ov akia : Gre if
F ond ateurs pre nd ront la cision finale .
giving both the carrot and the stick To an
actually drives the sheet of ice backwards and inland .
have moved with local forces within 20 miles of the ISIS
eg ener ative collagen ous pl aques of the hand ")
pour le Command ement des Cors aires de l ' E
, Or k ney and Mill port were exploring their options

MIN ACTIVATIONS
MIN = -2.486

ed by dumping garbage and diver ting the creek water so
in the Lif eline program diver ts scarce funds from the
ney - G ambling - Super bowl Advertising - Aust rail
not easy even for the super com puters , but it
The Times of Israel 's Daily Edition by email and never
oom in land , and ad heres to the original stories
of Defense s urgent needs , says Capt .
to the islands in a super - cool ed , liquid
and bring him into this super spy political thriller made so
Technology and two 8 mm Super P ipes to enhance heat
fix the walk ways without diver ting money from what they
at winning the W BA super - middle weight title ,
destroyed by dumping garbage and diver ting the creek water .
by R yo ( Super cell ). Here
liquid state and held in super - ins ulated containers and
session after delivering the 6 th Dil ip Sard es ai
quotes Wagner : " After spe aring the poor br utes
asked MIT s Dar on Ace m oglu .
some sort of discovery about really old wards covering the whole
Subscribe via RSS or daily email Contact the editor about

INTERVAL 1.103 - 2.300
CONTAINS 0.781%

chosen based on stat istical data , prior complaints
a big part of their hockey team . It 's been
to all Priv ile ges and Immun ities of Citizens in
breaks off from the glacier front , is tall and relatively
have to be a practicing Lac anian psych oan alyst to

INTERVAL -0.093 - 1.103
CONTAINS 59.411%

sure ," said On stad , now 47 and an assistant
over it 's body as armor . It 's shoulder blades
On Kickstarter , backers ( you !) ultimately decide the validity
. It s either going to cost us now
fact , a common phrase among CAT adjust ers is ,

INTERVAL -1.290 - -0.093
CONTAINS 39.543%

, although it had been upgraded regularly over the years ,
s not going to be a champagne party or
variation for a 16 - 35 f / 4 IS lens
However , the GP was not made aware that the
H ag el had a rocky tenure from the

INTERVAL -2.486 - -1.290
CONTAINS 0.265%

umbles ( t ied for second ), grabbed an interception ,
catch on ? Would you ever use this ? Share in
do you ever find that sometimes in
$ font 1 = New - Object System . Draw ing
were acquired by companies for millions of pounds and this helped
Tokenur
Token ID333
Feature activation+3.58e-01

Pos logit contributions
auts+1.787
wikipedia+1.753
orem+1.739
д+1.718
ompl+1.698
Neg logit contributions
nces-2.036
quad-1.974
arms-1.915
bane-1.829
ldom-1.829
Token E
Token ID412
Feature activation+2.78e-01

Pos logit contributions
auts+2.112
wikipedia+2.068
orem+2.055
д+2.027
ompl+2.003
Neg logit contributions
nces-2.369
quad-2.289
arms-2.222
ldom-2.127
bane-2.119
TokenCA
Token ID8141
Feature activation-7.06e-01

Pos logit contributions
auts+1.760
wikipedia+1.727
orem+1.715
д+1.698
ompl+1.680
Neg logit contributions
nces-1.717
quad-1.662
arms-1.608
bane-1.532
ldom-1.531
Token l
Token ID300
Feature activation+8.57e-01

Pos logit contributions
nces+4.399
quad+4.341
arms+4.149
bane+3.992
ldom+3.971
Neg logit contributions
auts-4.198
wikipedia-4.107
orem-4.046
д-3.972
ompl-3.939
Token'
Token ID6
Feature activation+5.25e-01

Pos logit contributions
auts+4.193
orem+4.111
wikipedia+4.031
д+4.000
ompl+3.965
Neg logit contributions
nces-6.425
quad-6.228
arms-6.028
ldom-5.871
bane-5.828
Tokenintention
Token ID40867
Feature activation+2.30e+00

Pos logit contributions
auts+3.177
wikipedia+3.099
orem+3.081
д+3.049
ompl+3.019
Neg logit contributions
nces-3.401
quad-3.271
arms-3.147
ldom-3.053
bane-3.029
Token de
Token ID390
Feature activation+3.94e-01

Pos logit contributions
auts+12.692
wikipedia+12.518
orem+12.441
ompl+12.171
iste+12.162
Neg logit contributions
nces-12.453
quad-11.713
arms-11.642
ldom-11.385
tails-11.240
Token sa
Token ID473
Feature activation+5.33e-01

Pos logit contributions
auts+2.328
wikipedia+2.280
orem+2.259
д+2.237
ompl+2.220
Neg logit contributions
nces-2.608
quad-2.522
arms-2.447
ldom-2.344
bane-2.333
Token maj
Token ID16486
Feature activation+1.60e+00

Pos logit contributions
auts+3.212
wikipedia+3.132
orem+3.125
д+3.072
ompl+3.066
Neg logit contributions
nces-3.461
quad-3.304
arms-3.234
bane-3.093
ldom-3.087
Tokenest
Token ID395
Feature activation+9.64e-01

Pos logit contributions
orem+7.276
auts+6.949
ompl+6.692
iste+6.477
wikipedia+6.472
Neg logit contributions
nces-12.151
quad-11.408
arms-11.138
ldom-11.004
bane-10.872
Tokené
Token ID2634
Feature activation+7.50e-01

Pos logit contributions
orem+4.524
auts+4.509
wikipedia+4.412
д+4.286
ompl+4.258
Neg logit contributions
nces-7.450
quad-7.130
arms-6.945
ldom-6.740
perate-6.683
Tokenesp
Token ID9774
Feature activation+8.06e-01

Pos logit contributions
auts+4.216
wikipedia+4.078
orem+4.064
д+3.991
ompl+3.969
Neg logit contributions
nces-5.296
quad-5.091
arms-4.877
ldom-4.788
bane-4.755
Tokenrit
Token ID799
Feature activation+6.12e-01

Pos logit contributions
auts+5.454
wikipedia+5.277
orem+5.269
ompl+5.168
д+5.166
Neg logit contributions
nces-4.631
quad-4.416
arms-4.215
bane-4.072
ldom-4.066
Token origin
Token ID8159
Feature activation+1.32e+00

Pos logit contributions
auts+3.511
orem+3.419
wikipedia+3.402
д+3.342
ompl+3.320
Neg logit contributions
nces-4.092
quad-4.006
arms-3.882
ldom-3.724
bane-3.708
Tokenel
Token ID417
Feature activation+1.07e+00

Pos logit contributions
auts+8.427
orem+8.128
ompl+7.885
wikipedia+7.884
iste+7.818
Neg logit contributions
quad-7.291
nces-7.155
arms-6.653
bane-6.574
IOR-6.470
Token des
Token ID748
Feature activation+5.86e-01

Pos logit contributions
auts+6.247
orem+6.005
wikipedia+5.902
ompl+5.820
д+5.766
Neg logit contributions
nces-6.764
quad-6.697
arms-6.454
ldom-6.237
bane-6.214
Token Cors
Token ID26978
Feature activation+2.28e+00

Pos logit contributions
auts+3.636
wikipedia+3.523
orem+3.516
д+3.472
ompl+3.429
Neg logit contributions
nces-3.694
quad-3.566
arms-3.448
ldom-3.323
bane-3.313
Tokenaires
Token ID17693
Feature activation+9.33e-01

Pos logit contributions
auts+12.736
orem+12.112
wikipedia+11.665
ompl+11.297
essee+11.176
Neg logit contributions
quad-12.336
nces-12.106
ldom-11.264
IOR-11.239
bane-11.210
Token [...]
Token ID26894
Feature activation+5.17e-01

Pos logit contributions
auts+5.199
orem+5.049
wikipedia+5.026
д+4.902
ompl+4.899
Neg logit contributions
nces-6.201
quad-6.026
arms-5.857
ldom-5.678
bane-5.637
Token En
Token ID2039
Feature activation+4.95e-01

Pos logit contributions
auts+2.974
orem+2.904
wikipedia+2.903
д+2.852
ompl+2.833
Neg logit contributions
nces-3.478
quad-3.373
arms-3.281
ldom-3.147
bane-3.142
Token cas
Token ID6124
Feature activation+9.70e-01

Pos logit contributions
auts+3.133
wikipedia+3.051
orem+3.030
д+3.005
ompl+2.990
Neg logit contributions
nces-3.049
quad-2.931
arms-2.842
ldom-2.724
bane-2.719
Token de
Token ID390
Feature activation+6.40e-01

Pos logit contributions
auts+5.758
orem+5.637
wikipedia+5.571
ompl+5.470
д+5.425
Neg logit contributions
nces-6.061
quad-5.864
arms-5.722
ldom-5.509
bane-5.402
Token all
Token ID477
Feature activation+2.36e-01

Pos logit contributions
auts+0.071
wikipedia+0.070
orem+0.070
д+0.068
ompl+0.068
Neg logit contributions
nces-0.072
quad-0.069
arms-0.067
bane-0.065
ldom-0.064
Token elbows
Token ID37076
Feature activation+5.26e-02

Pos logit contributions
auts+1.326
wikipedia+1.297
orem+1.287
д+1.272
ompl+1.257
Neg logit contributions
nces-1.628
quad-1.581
arms-1.536
bane-1.473
ldom-1.471
Token and
Token ID290
Feature activation+4.33e-01

Pos logit contributions
auts+0.323
wikipedia+0.316
orem+0.314
д+0.310
ompl+0.307
Neg logit contributions
nces-0.336
quad-0.329
arms-0.317
bane-0.303
ldom-0.302
Token knees
Token ID14475
Feature activation-3.50e-01

Pos logit contributions
auts+3.416
wikipedia+3.365
orem+3.348
д+3.318
ompl+3.288
Neg logit contributions
nces-1.967
quad-1.884
arms-1.767
ldom-1.688
bane-1.668
Token,
Token ID11
Feature activation+1.94e-01

Pos logit contributions
nces+2.220
quad+2.185
arms+2.095
bane+2.010
ldom+1.991
Neg logit contributions
auts-2.154
orem-2.095
wikipedia-2.091
ompl-2.044
д-2.041
Token Pl
Token ID1345
Feature activation+2.27e+00

Pos logit contributions
auts+1.216
wikipedia+1.193
orem+1.180
д+1.172
ompl+1.160
Neg logit contributions
nces-1.206
quad-1.166
arms-1.126
ldom-1.076
bane-1.073
Tokenath
Token ID776
Feature activation+3.10e-01

Pos logit contributions
auts+12.261
orem+11.574
ompl+11.445
ocate+11.168
iste+10.952
Neg logit contributions
nces-13.840
quad-12.587
IOR-12.560
tails-11.959
ldom-11.958
Tokenian
Token ID666
Feature activation-3.71e-01

Pos logit contributions
auts+1.851
wikipedia+1.815
orem+1.801
д+1.780
ompl+1.762
Neg logit contributions
nces-2.032
quad-1.972
arms-1.912
bane-1.828
ldom-1.826
Token with
Token ID351
Feature activation-5.94e-02

Pos logit contributions
nces+2.369
quad+2.284
arms+2.234
bane+2.134
ldom+2.113
Neg logit contributions
wikipedia-2.247
auts-2.219
orem-2.190
д-2.166
ompl-2.146
Token a
Token ID257
Feature activation-1.46e-01

Pos logit contributions
nces+0.376
quad+0.364
arms+0.355
bane+0.337
ldom+0.336
Neg logit contributions
auts-0.369
wikipedia-0.363
orem-0.358
д-0.355
ompl-0.352
Token r
Token ID374
Feature activation-2.32e-01

Pos logit contributions
nces+0.909
quad+0.887
arms+0.859
bane+0.822
ldom+0.819
Neg logit contributions
auts-0.914
wikipedia-0.893
orem-0.881
д-0.874
ompl-0.866
Tokenind
Token ID521
Feature activation+1.34e+00

Pos logit contributions
auts+4.487
orem+4.283
ompl+4.244
wikipedia+4.190
д+4.122
Neg logit contributions
nces-8.028
quad-7.663
arms-7.390
bane-7.265
ldom-7.207
Tokenre
Token ID260
Feature activation+3.51e-01

Pos logit contributions
auts+8.150
ompl+7.794
orem+7.747
wikipedia+7.571
д+7.419
Neg logit contributions
quad-7.901
nces-7.801
arms-7.326
bane-7.114
ldom-7.105
Tokenment
Token ID434
Feature activation+1.46e+00

Pos logit contributions
auts+2.021
wikipedia+1.967
orem+1.959
д+1.926
ompl+1.914
Neg logit contributions
nces-2.363
quad-2.307
arms-2.234
ldom-2.142
bane-2.134
Token,
Token ID11
Feature activation+6.19e-01

Pos logit contributions
auts+8.207
orem+8.030
wikipedia+7.761
ompl+7.728
iste+7.607
Neg logit contributions
nces-8.910
quad-8.859
arms-8.501
ldom-8.285
tails-8.220
Token les
Token ID10287
Feature activation+4.52e-01

Pos logit contributions
auts+3.494
orem+3.399
wikipedia+3.381
ompl+3.331
д+3.329
Neg logit contributions
nces-4.207
quad-4.066
arms-3.965
ldom-3.818
bane-3.775
Token Cors
Token ID26978
Feature activation+2.26e+00

Pos logit contributions
auts+2.726
wikipedia+2.651
orem+2.646
д+2.606
ompl+2.582
Neg logit contributions
nces-2.936
quad-2.832
arms-2.745
ldom-2.641
bane-2.630
Tokenaires
Token ID17693
Feature activation+5.53e-01

Pos logit contributions
auts+13.059
orem+12.362
wikipedia+11.903
ompl+11.662
iste+11.543
Neg logit contributions
nces-11.971
quad-11.895
ldom-11.007
IOR-10.870
arms-10.742
Token l
Token ID300
Feature activation+1.49e+00

Pos logit contributions
auts+3.179
wikipedia+3.083
orem+3.078
д+3.028
ompl+3.012
Neg logit contributions
nces-3.708
quad-3.594
arms-3.499
ldom-3.368
bane-3.339
Tokenoy
Token ID726
Feature activation+9.91e-01

Pos logit contributions
auts+6.958
orem+6.858
ompl+6.481
ocate+6.382
д+6.335
Neg logit contributions
nces-10.915
quad-10.690
arms-10.026
ldom-10.025
bane-9.910
Tokenaux
Token ID14644
Feature activation+8.16e-01

Pos logit contributions
auts+6.149
orem+5.887
wikipedia+5.867
ompl+5.731
д+5.722
Neg logit contributions
quad-5.945
nces-5.941
arms-5.659
ldom-5.477
bane-5.447
Token rest
Token ID1334
Feature activation+1.73e+00

Pos logit contributions
auts+4.673
orem+4.516
wikipedia+4.492
ompl+4.404
д+4.384
Neg logit contributions
nces-5.423
quad-5.236
arms-5.115
ldom-4.925
bane-4.863
Token loans
Token ID10021
Feature activation+3.98e-01

Pos logit contributions
nces+2.042
quad+1.960
arms+1.903
bane+1.757
perate+1.729
Neg logit contributions
auts-3.603
wikipedia-3.561
orem-3.535
д-3.509
ompl-3.492
Token are
Token ID389
Feature activation+6.70e-01

Pos logit contributions
auts+2.282
wikipedia+2.223
orem+2.211
д+2.175
ompl+2.158
Neg logit contributions
nces-2.696
quad-2.581
arms-2.519
ldom-2.418
bane-2.410
Token Vi
Token ID16049
Feature activation+2.22e-01

Pos logit contributions
auts+4.024
wikipedia+3.968
orem+3.902
д+3.900
ompl+3.839
Neg logit contributions
nces-4.288
quad-4.145
arms-3.997
ldom-3.849
bane-3.837
Tokenaches
Token ID3694
Feature activation+1.64e-01

Pos logit contributions
auts+1.322
wikipedia+1.296
orem+1.284
д+1.274
ompl+1.257
Neg logit contributions
nces-1.459
quad-1.422
arms-1.379
ldom-1.315
bane-1.314
Tokenlav
Token ID18809
Feature activation+6.33e-01

Pos logit contributions
auts+1.062
wikipedia+1.042
orem+1.033
д+1.028
ompl+1.015
Neg logit contributions
nces-0.988
quad-0.960
arms-0.928
bane-0.881
ldom-0.879
Token Pl
Token ID1345
Feature activation+2.25e+00

Pos logit contributions
auts+4.059
wikipedia+3.984
orem+3.958
д+3.912
ompl+3.852
Neg logit contributions
nces-3.821
quad-3.682
arms-3.558
ldom-3.411
bane-3.376
Tokenak
Token ID461
Feature activation+6.20e-01

Pos logit contributions
auts+13.147
ocate+12.837
orem+12.745
ompl+12.570
wikipedia+12.388
Neg logit contributions
nces-12.430
quad-10.814
ldom-10.623
 proportions-10.352
IOR-10.295
Tokenas
Token ID292
Feature activation-1.02e-01

Pos logit contributions
auts+3.633
wikipedia+3.555
orem+3.525
ompl+3.470
д+3.459
Neg logit contributions
nces-4.100
quad-3.950
arms-3.837
ldom-3.687
bane-3.664
Tokenov
Token ID709
Feature activation+6.18e-01

Pos logit contributions
nces+0.718
quad+0.708
arms+0.682
bane+0.659
perate+0.648
Neg logit contributions
auts-0.560
wikipedia-0.549
orem-0.542
д-0.537
ompl-0.530
Token,
Token ID11
Feature activation+5.85e-01

Pos logit contributions
auts+3.621
wikipedia+3.532
orem+3.511
д+3.489
ompl+3.432
Neg logit contributions
nces-4.088
quad-3.922
arms-3.808
ldom-3.666
bane-3.633
Token Vol
Token ID4709
Feature activation+1.47e+00

Pos logit contributions
auts+3.428
wikipedia+3.378
orem+3.339
д+3.313
ompl+3.274
Neg logit contributions
nces-3.881
quad-3.725
arms-3.602
ldom-3.481
bane-3.470
Tokeneng
Token ID1516
Feature activation+6.68e-01

Pos logit contributions
auts+5.380
orem+5.199
wikipedia+5.191
ompl+5.084
д+5.065
Neg logit contributions
nces-6.539
quad-6.243
arms-5.947
ldom-5.912
bane-5.830
Tokenagement
Token ID5082
Feature activation+8.69e-01

Pos logit contributions
auts+4.049
wikipedia+3.952
orem+3.926
ompl+3.876
д+3.854
Neg logit contributions
nces-4.260
quad-4.120
arms-3.942
bane-3.846
ldom-3.799
Token qu
Token ID627
Feature activation+4.16e-01

Pos logit contributions
auts+4.843
orem+4.724
wikipedia+4.704
ompl+4.603
д+4.582
Neg logit contributions
nces-5.862
quad-5.680
arms-5.526
ldom-5.335
tails-5.275
Token'
Token ID6
Feature activation+7.26e-01

Pos logit contributions
auts+1.941
wikipedia+1.876
orem+1.872
д+1.833
ompl+1.819
Neg logit contributions
nces-3.275
quad-3.183
arms-3.096
ldom-2.992
bane-2.991
Tokenils
Token ID4487
Feature activation+9.97e-01

Pos logit contributions
auts+4.424
orem+4.284
wikipedia+4.259
ompl+4.229
д+4.205
Neg logit contributions
nces-4.623
quad-4.457
arms-4.250
ldom-4.162
bane-4.075
Token av
Token ID1196
Feature activation+2.24e+00

Pos logit contributions
auts+5.757
orem+5.511
wikipedia+5.493
ompl+5.428
д+5.418
Neg logit contributions
nces-6.485
quad-6.181
arms-6.096
ldom-5.921
tails-5.782
Tokena
Token ID64
Feature activation+3.19e-01

Pos logit contributions
auts+11.450
orem+10.805
ompl+10.768
iste+10.385
ocate+10.363
Neg logit contributions
nces-13.592
quad-12.731
ldom-12.425
bane-11.991
tails-11.949
Tokenient
Token ID1153
Feature activation+9.81e-01

Pos logit contributions
auts+1.357
wikipedia+1.324
orem+1.297
д+1.286
ompl+1.258
Neg logit contributions
nces-2.632
quad-2.579
arms-2.514
ldom-2.422
bane-2.421
Token pr
Token ID778
Feature activation+1.26e+00

Pos logit contributions
auts+5.558
orem+5.356
wikipedia+5.310
ompl+5.268
д+5.246
Neg logit contributions
nces-6.439
quad-6.264
arms-6.092
ldom-5.911
tails-5.810
Tokenit
Token ID270
Feature activation+1.47e+00

Pos logit contributions
auts+5.444
orem+5.425
ompl+5.186
wikipedia+5.115
iste+5.104
Neg logit contributions
nces-9.842
quad-9.495
arms-9.211
ldom-9.041
tails-9.002
Token en
Token ID551
Feature activation+8.01e-01

Pos logit contributions
auts+8.377
orem+8.287
ompl+7.956
wikipedia+7.844
д+7.839
Neg logit contributions
nces-8.984
quad-8.685
arms-8.595
ldom-8.074
tails-8.030
Token the
Token ID262
Feature activation-2.39e-01

Pos logit contributions
nces+1.807
quad+1.751
arms+1.688
ldom+1.601
bane+1.597
Neg logit contributions
auts-1.856
wikipedia-1.816
orem-1.811
д-1.794
ompl-1.778
Token #
Token ID1303
Feature activation-1.07e-02

Pos logit contributions
nces+1.490
quad+1.449
arms+1.396
ldom+1.329
bane+1.325
Neg logit contributions
auts-1.496
wikipedia-1.462
д-1.451
orem-1.449
ompl-1.428
Tokendeb
Token ID11275
Feature activation-6.32e-01

Pos logit contributions
nces+0.064
quad+0.062
arms+0.060
bane+0.057
ldom+0.057
Neg logit contributions
auts-0.070
orem-0.068
wikipedia-0.068
д-0.067
ompl-0.067
Tokenates
Token ID689
Feature activation-3.66e-01

Pos logit contributions
nces+3.950
quad+3.920
arms+3.827
ldom+3.677
bane+3.621
Neg logit contributions
auts-3.728
д-3.709
wikipedia-3.664
orem-3.582
ompl-3.530
Token #
Token ID1303
Feature activation+6.49e-02

Pos logit contributions
nces+2.543
quad+2.526
arms+2.398
bane+2.312
perate+2.297
Neg logit contributions
auts-2.017
orem-1.949
wikipedia-1.945
д-1.921
ompl-1.911
TokenOccup
Token ID47658
Feature activation+2.23e+00

Pos logit contributions
auts+0.409
orem+0.399
wikipedia+0.399
д+0.395
ompl+0.391
Neg logit contributions
nces-0.404
quad-0.394
arms-0.380
bane-0.361
ldom-0.360
Tokeny
Token ID88
Feature activation+5.48e-01

Pos logit contributions
auts+8.738
wikipedia+8.319
ompl+8.080
д+7.924
orem+7.913
Neg logit contributions
nces-16.096
quad-15.492
bane-15.008
ldom-14.970
arms-14.889
TokenThe
Token ID464
Feature activation+3.25e-01

Pos logit contributions
auts+3.436
wikipedia+3.399
orem+3.328
д+3.317
ompl+3.270
Neg logit contributions
nces-3.393
quad-3.238
arms-3.145
ldom-3.047
bane-3.017
TokenDeb
Token ID16587
Feature activation-4.14e-01

Pos logit contributions
auts+1.913
wikipedia+1.876
orem+1.865
д+1.837
ompl+1.816
Neg logit contributions
nces-2.160
quad-2.081
arms-2.021
ldom-1.948
bane-1.941
Tokenates
Token ID689
Feature activation+1.19e-01

Pos logit contributions
nces+2.617
quad+2.562
arms+2.541
ldom+2.414
bane+2.384
Neg logit contributions
д-2.442
auts-2.427
wikipedia-2.416
ompl-2.353
orem-2.349
Token pic
Token ID8301
Feature activation+4.83e-01

Pos logit contributions
auts+0.582
wikipedia+0.567
orem+0.563
д+0.554
ompl+0.548
Neg logit contributions
nces-0.911
quad-0.891
arms-0.865
bane-0.833
ldom-0.831
Token leave
Token ID2666
Feature activation+5.85e-01

Pos logit contributions
auts+0.327
wikipedia+0.320
orem+0.318
д+0.315
ompl+0.312
Neg logit contributions
nces-0.330
quad-0.320
arms-0.309
ldom-0.295
bane-0.295
Token.
Token ID13
Feature activation+2.60e-01

Pos logit contributions
auts+3.146
wikipedia+3.038
orem+3.031
д+3.025
ompl+2.969
Neg logit contributions
nces-4.058
quad-3.989
arms-3.839
bane-3.728
ldom-3.705
Token OS
Token ID7294
Feature activation+8.60e-01

Pos logit contributions
auts+1.420
wikipedia+1.391
orem+1.372
д+1.362
ompl+1.337
Neg logit contributions
nces-1.837
quad-1.783
arms-1.728
ldom-1.672
bane-1.655
TokenHA
Token ID7801
Feature activation-1.34e-01

Pos logit contributions
auts+4.921
wikipedia+4.690
orem+4.662
ompl+4.623
д+4.596
Neg logit contributions
nces-5.755
quad-5.572
arms-5.422
ldom-5.276
perate-5.190
Token (
Token ID357
Feature activation+2.17e-01

Pos logit contributions
nces+0.885
quad+0.856
arms+0.838
bane+0.796
poses+0.792
Neg logit contributions
auts-0.789
wikipedia-0.774
orem-0.769
д-0.754
ompl-0.745
TokenOccup
Token ID47658
Feature activation+2.23e+00

Pos logit contributions
auts+1.317
wikipedia+1.289
orem+1.280
д+1.266
ompl+1.252
Neg logit contributions
nces-1.398
quad-1.356
arms-1.315
bane-1.254
ldom-1.251
Tokenational
Token ID864
Feature activation+1.53e+00

Pos logit contributions
auts+8.453
essee+7.941
orem+7.911
wikipedia+7.765
ompl+7.679
Neg logit contributions
quad-16.662
nces-16.106
arms-15.375
ldom-15.226
bane-15.064
Token Health
Token ID3893
Feature activation+1.25e+00

Pos logit contributions
auts+7.158
orem+6.857
д+6.816
estern+6.792
ompl+6.787
Neg logit contributions
nces-11.063
quad-10.737
arms-10.146
ldom-9.687
bane-9.669
Token and
Token ID290
Feature activation+5.90e-01

Pos logit contributions
auts+6.498
д+6.378
orem+6.336
wikipedia+6.291
ompl+6.175
Neg logit contributions
nces-8.668
quad-8.400
arms-7.857
perate-7.744
ldom-7.741
Token Safety
Token ID11233
Feature activation+5.75e-01

Pos logit contributions
auts+3.192
д+3.154
orem+3.122
wikipedia+3.091
ompl+3.046
Neg logit contributions
quad-4.103
nces-4.077
arms-3.820
ldom-3.700
bane-3.684
Token Administration
Token ID8694
Feature activation+1.95e-01

Pos logit contributions
auts+2.526
wikipedia+2.473
д+2.440
orem+2.428
ompl+2.380
Neg logit contributions
nces-4.620
quad-4.523
arms-4.383
bane-4.254
ldom-4.251
TokenJ
Token ID41
Feature activation+7.76e-01

Pos logit contributions
auts+3.533
wikipedia+3.454
orem+3.443
д+3.416
ompl+3.342
Neg logit contributions
nces-3.769
quad-3.602
arms-3.503
ldom-3.413
perate-3.319
Token'
Token ID6
Feature activation+3.63e-01

Pos logit contributions
auts+3.493
orem+3.349
wikipedia+3.304
ompl+3.291
д+3.232
Neg logit contributions
nces-6.285
quad-6.035
arms-5.856
ldom-5.718
bane-5.685
Tokenai
Token ID1872
Feature activation+1.00e+00

Pos logit contributions
auts+1.967
wikipedia+1.922
orem+1.907
д+1.884
ompl+1.862
Neg logit contributions
nces-2.585
quad-2.513
arms-2.442
ldom-2.343
bane-2.342
Token l
Token ID300
Feature activation+1.47e+00

Pos logit contributions
auts+5.861
orem+5.650
ompl+5.627
wikipedia+5.608
д+5.485
Neg logit contributions
nces-6.468
quad-6.130
arms-6.017
ldom-5.821
tails-5.786
Token'
Token ID6
Feature activation+7.94e-01

Pos logit contributions
auts+6.617
orem+6.441
ompl+6.107
ocate+5.962
д+5.874
Neg logit contributions
nces-11.215
quad-10.798
ldom-10.278
arms-10.205
bane-10.104
Tokenhon
Token ID24130
Feature activation+2.22e+00

Pos logit contributions
auts+4.330
wikipedia+4.186
orem+4.178
д+4.092
ompl+4.091
Neg logit contributions
nces-5.592
quad-5.373
arms-5.157
ldom-5.066
bane-5.012
Tokenne
Token ID710
Feature activation+1.10e+00

Pos logit contributions
orem+12.294
auts+12.134
wikipedia+11.564
ompl+11.547
iste+11.028
Neg logit contributions
nces-12.254
arms-11.669
quad-11.615
ldom-11.613
tails-10.822
Tokenur
Token ID333
Feature activation+6.65e-01

Pos logit contributions
wikipedia+4.285
auts+4.276
orem+4.113
ompl+4.071
д+3.959
Neg logit contributions
nces-9.045
quad-8.724
arms-8.681
tails-8.273
ldom-8.260
Token d
Token ID288
Feature activation+2.96e-01

Pos logit contributions
auts+3.851
wikipedia+3.751
orem+3.734
ompl+3.659
д+3.653
Neg logit contributions
nces-4.408
quad-4.293
arms-4.178
ldom-3.998
bane-3.969
Token'
Token ID6
Feature activation+7.88e-01

Pos logit contributions
auts+1.321
wikipedia+1.289
orem+1.274
д+1.258
ompl+1.234
Neg logit contributions
nces-2.386
quad-2.329
arms-2.273
bane-2.192
ldom-2.191
Tokenê
Token ID25792
Feature activation+3.55e-01

Pos logit contributions
auts+4.295
orem+4.155
wikipedia+4.142
д+4.067
ompl+4.046
Neg logit contributions
nces-5.589
quad-5.367
arms-5.152
ldom-5.066
bane-4.994
Tokenament
Token ID3263
Feature activation+1.44e+00

Pos logit contributions
auts+3.157
orem+3.033
wikipedia+2.986
ompl+2.938
д+2.935
Neg logit contributions
nces-4.325
quad-4.173
arms-4.013
bane-3.917
ldom-3.913
Token que
Token ID8358
Feature activation+6.98e-01

Pos logit contributions
auts+8.529
orem+8.338
iste+8.018
wikipedia+8.004
ompl+7.947
Neg logit contributions
quad-8.297
nces-8.036
arms-7.821
ldom-7.619
tails-7.534
Token le
Token ID443
Feature activation+8.10e-01

Pos logit contributions
auts+3.935
wikipedia+3.822
orem+3.814
д+3.751
ompl+3.716
Neg logit contributions
nces-4.720
quad-4.580
arms-4.475
ldom-4.274
bane-4.264
Token Command
Token ID9455
Feature activation+7.97e-01

Pos logit contributions
auts+4.817
orem+4.703
wikipedia+4.637
ompl+4.549
д+4.544
Neg logit contributions
nces-5.241
quad-5.004
arms-4.857
ldom-4.657
bane-4.648
Tokenement
Token ID972
Feature activation+9.47e-01

Pos logit contributions
auts+4.504
orem+4.372
wikipedia+4.339
ompl+4.232
д+4.218
Neg logit contributions
nces-5.362
quad-5.169
arms-5.037
ldom-4.872
bane-4.823
Token Cors
Token ID26978
Feature activation+2.20e+00

Pos logit contributions
auts+5.369
orem+5.226
wikipedia+5.205
ompl+5.070
д+5.061
Neg logit contributions
nces-6.201
quad-6.026
arms-5.842
ldom-5.633
tails-5.614
Tokenaire
Token ID7626
Feature activation+3.91e-01

Pos logit contributions
auts+11.914
orem+11.686
wikipedia+10.957
iste+10.897
ompl+10.676
Neg logit contributions
nces-12.628
quad-12.460
ldom-11.526
arms-11.297
perate-11.247
Token ser
Token ID1055
Feature activation+8.28e-01

Pos logit contributions
auts+2.199
wikipedia+2.145
orem+2.138
д+2.105
ompl+2.084
Neg logit contributions
nces-2.691
quad-2.617
arms-2.541
ldom-2.436
bane-2.433
Tokenait
Token ID4548
Feature activation+1.37e+00

Pos logit contributions
auts+4.487
orem+4.333
wikipedia+4.256
д+4.225
ompl+4.220
Neg logit contributions
nces-5.833
quad-5.638
arms-5.493
ldom-5.286
bane-5.211
Token ill
Token ID2801
Feature activation+1.96e+00

Pos logit contributions
auts+7.426
orem+7.276
ompl+7.069
wikipedia+7.021
 admire+6.916
Neg logit contributions
nces-8.780
quad-8.572
arms-8.366
ldom-8.188
tails-7.992
Tokené
Token ID2634
Feature activation+5.79e-01

Pos logit contributions
auts+10.741
orem+10.472
ompl+10.278
iste+10.176
ocate+10.087
Neg logit contributions
nces-12.297
quad-11.017
arms-10.699
ldom-10.451
perate-10.325
Token
Token ID447
Feature activation+7.46e-02

Pos logit contributions
auts+1.661
wikipedia+1.626
orem+1.613
д+1.601
ompl+1.581
Neg logit contributions
nces-1.915
quad-1.854
arms-1.798
bane-1.719
ldom-1.717
Token
Token ID247
Feature activation+6.16e-02

Pos logit contributions
auts+0.619
wikipedia+0.610
orem+0.608
д+0.605
ompl+0.598
Neg logit contributions
nces-0.314
quad-0.298
arms-0.284
bane-0.264
ldom-0.263
Tokens
Token ID82
Feature activation-1.89e-02

Pos logit contributions
auts+0.300
wikipedia+0.292
orem+0.290
д+0.285
ompl+0.282
Neg logit contributions
nces-0.473
quad-0.460
arms-0.449
ldom-0.432
bane-0.431
Token neo
Token ID19102
Feature activation-2.42e-01

Pos logit contributions
nces+0.112
quad+0.108
arms+0.105
ldom+0.100
bane+0.100
Neg logit contributions
auts-0.124
wikipedia-0.121
orem-0.121
д-0.119
ompl-0.119
Token-
Token ID12
Feature activation-4.31e-01

Pos logit contributions
quad+1.345
nces+1.336
arms+1.272
perate+1.204
bane+1.201
Neg logit contributions
auts-1.635
wikipedia-1.606
orem-1.595
ompl-1.559
д-1.547
TokenOtt
Token ID49092
Feature activation+2.17e+00

Pos logit contributions
quad+2.727
nces+2.710
arms+2.633
bane+2.509
poses+2.487
Neg logit contributions
auts-2.594
orem-2.568
wikipedia-2.491
ompl-2.485
д-2.456
Tokenoman
Token ID5185
Feature activation+5.20e-01

Pos logit contributions
auts+7.100
д+6.158
wikipedia+6.125
ocate+6.090
ompl+6.073
Neg logit contributions
nces-18.675
quad-17.717
IOR-16.737
arms-16.675
ldom-16.519
Token an
Token ID281
Feature activation+1.34e-03

Pos logit contributions
auts+3.284
wikipedia+3.200
д+3.176
orem+3.167
ompl+3.119
Neg logit contributions
nces-3.228
quad-3.116
arms-2.987
bane-2.865
ldom-2.855
Tokenvil
Token ID2991
Feature activation+1.39e-01

Pos logit contributions
auts+0.009
wikipedia+0.008
orem+0.008
д+0.008
ompl+0.008
Neg logit contributions
nces-0.008
quad-0.008
arms-0.008
ldom-0.007
bane-0.007
Token fall
Token ID2121
Feature activation+5.43e-01

Pos logit contributions
auts+0.772
wikipedia+0.755
orem+0.749
д+0.740
ompl+0.731
Neg logit contributions
nces-0.971
quad-0.944
arms-0.917
bane-0.879
ldom-0.879
Token hardest
Token ID17612
Feature activation-4.08e-02

Pos logit contributions
auts+3.051
wikipedia+2.960
orem+2.948
д+2.933
ompl+2.889
Neg logit contributions
nces-3.732
quad-3.620
arms-3.484
bane-3.350
ldom-3.346
Tokencl
Token ID565
Feature activation+4.79e-02

Pos logit contributions
nces+6.333
quad+6.295
arms+6.225
bane+5.984
perate+5.818
Neg logit contributions
wikipedia-8.406
auts-8.351
orem-8.327
д-8.203
ompl-8.178
Tokenable
Token ID540
Feature activation-5.08e-01

Pos logit contributions
wikipedia+0.255
auts+0.254
д+0.249
orem+0.249
ompl+0.245
Neg logit contributions
nces-0.338
quad-0.331
arms-0.323
bane-0.308
perate-0.308
Token cat
Token ID3797
Feature activation-7.87e-01

Pos logit contributions
nces+3.076
quad+3.009
arms+2.937
bane+2.774
ldom+2.744
Neg logit contributions
auts-3.168
д-3.124
wikipedia-3.112
orem-3.106
ompl-3.066
Tokenam
Token ID321
Feature activation+1.88e-01

Pos logit contributions
nces+5.228
quad+5.215
arms+5.130
bane+4.937
tails+4.788
Neg logit contributions
auts-4.260
wikipedia-4.207
д-4.188
orem-4.164
ompl-4.028
Tokenaran
Token ID19173
Feature activation-4.81e-01

Pos logit contributions
auts+0.997
wikipedia+0.978
orem+0.971
д+0.961
ompl+0.944
Neg logit contributions
nces-1.352
quad-1.319
arms-1.283
ldom-1.230
bane-1.229
Token Pl
Token ID1345
Feature activation+2.16e+00

Pos logit contributions
nces+2.986
quad+2.910
arms+2.804
ldom+2.671
bane+2.662
Neg logit contributions
auts-2.917
wikipedia-2.904
orem-2.894
д-2.868
ompl-2.817
Tokenast
Token ID459
Feature activation+8.12e-01

Pos logit contributions
auts+12.184
ompl+11.791
orem+11.763
ocate+11.582
wikipedia+11.193
Neg logit contributions
nces-12.668
ldom-10.804
quad-10.758
IOR-10.689
 proportions-10.634
Tokeniki
Token ID5580
Feature activation-7.87e-02

Pos logit contributions
auts+4.370
orem+4.239
wikipedia+4.219
д+4.111
ompl+4.095
Neg logit contributions
nces-5.753
quad-5.541
arms-5.398
bane-5.176
ldom-5.162
Token,
Token ID11
Feature activation+1.28e-01

Pos logit contributions
nces+0.504
quad+0.493
arms+0.475
bane+0.452
ldom+0.452
Neg logit contributions
auts-0.475
wikipedia-0.471
orem-0.467
д-0.462
ompl-0.454
Token which
Token ID543
Feature activation-3.87e-02

Pos logit contributions
auts+0.784
wikipedia+0.769
orem+0.765
д+0.756
ompl+0.747
Neg logit contributions
nces-0.824
quad-0.799
arms-0.774
bane-0.739
ldom-0.738
Token is
Token ID318
Feature activation+2.27e-01

Pos logit contributions
nces+0.250
quad+0.241
arms+0.234
bane+0.223
ldom+0.222
Neg logit contributions
auts-0.234
wikipedia-0.230
orem-0.228
д-0.226
ompl-0.223
Token De
Token ID1024
Feature activation-6.19e-01

Pos logit contributions
auts+1.562
wikipedia+1.533
orem+1.522
д+1.507
ompl+1.489
Neg logit contributions
nces-1.426
quad-1.374
arms-1.329
ldom-1.267
bane-1.258
Tokenvers
Token ID690
Feature activation-1.36e-01

Pos logit contributions
nces+3.934
quad+3.815
arms+3.759
bane+3.627
perate+3.579
Neg logit contributions
auts-3.676
wikipedia-3.584
orem-3.550
д-3.547
ompl-3.532
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
nces+0.875
quad+0.859
arms+0.830
bane+0.801
perate+0.784
Neg logit contributions
auts-0.827
wikipedia-0.812
orem-0.802
д-0.797
ompl-0.786
Token
Token ID198
Feature activation+2.02e-01

Pos logit contributions
nces+0.733
quad+0.714
arms+0.690
bane+0.666
ldom+0.652
Neg logit contributions
auts-0.736
orem-0.719
wikipedia-0.716
д-0.703
ompl-0.701
Token
Token ID198
Feature activation+5.54e-01

Pos logit contributions
auts+1.114
wikipedia+1.098
д+1.070
orem+1.063
ompl+1.036
Neg logit contributions
nces-1.445
quad-1.366
arms-1.325
ldom-1.302
perate-1.274
TokenSl
Token ID11122
Feature activation+2.15e+00

Pos logit contributions
auts+4.001
wikipedia+3.968
д+3.905
orem+3.862
ompl+3.827
Neg logit contributions
nces-2.894
quad-2.711
arms-2.636
ldom-2.546
perate-2.503
Tokenov
Token ID709
Feature activation+1.76e+00

Pos logit contributions
auts+5.492
wikipedia+5.043
ompl+4.648
ocate+4.599
essee+4.522
Neg logit contributions
nces-18.870
IOR-17.585
 nodd-17.573
tails-17.568
 DISTR-17.343
Tokenakia
Token ID21897
Feature activation+4.95e-01

Pos logit contributions
auts+6.667
wikipedia+6.081
ocate+5.881
iste+5.739
anova+5.624
Neg logit contributions
quad-13.840
nces-13.830
IOR-12.970
ldom-12.955
 DISTR-12.775
Token:
Token ID25
Feature activation+1.36e-01

Pos logit contributions
auts+2.380
wikipedia+2.312
orem+2.283
д+2.280
ompl+2.245
Neg logit contributions
nces-3.809
quad-3.695
arms-3.608
ldom-3.472
bane-3.465
Token Gre
Token ID11955
Feature activation+1.05e-01

Pos logit contributions
auts+0.890
wikipedia+0.874
orem+0.868
д+0.859
ompl+0.850
Neg logit contributions
nces-0.815
quad-0.788
arms-0.761
ldom-0.724
bane-0.724
Tokenif
Token ID361
Feature activation+2.18e-02

Pos logit contributions
auts+0.628
wikipedia+0.618
orem+0.610
д+0.607
ompl+0.599
Neg logit contributions
nces-0.687
quad-0.665
arms-0.646
bane-0.618
ldom-0.617
Token F
Token ID376
Feature activation+3.12e-01

Pos logit contributions
auts+2.322
wikipedia+2.262
orem+2.255
д+2.223
ompl+2.201
Neg logit contributions
nces-2.505
quad-2.418
arms-2.346
ldom-2.251
bane-2.246
Tokenond
Token ID623
Feature activation-2.20e-01

Pos logit contributions
auts+1.960
wikipedia+1.921
orem+1.908
д+1.887
ompl+1.869
Neg logit contributions
nces-1.952
quad-1.888
arms-1.828
bane-1.743
ldom-1.742
Tokenateurs
Token ID45211
Feature activation+2.67e-01

Pos logit contributions
nces+1.457
quad+1.392
arms+1.386
bane+1.305
ldom+1.297
Neg logit contributions
wikipedia-1.286
auts-1.271
д-1.261
orem-1.257
ompl-1.240
Token pre
Token ID662
Feature activation+4.17e-01

Pos logit contributions
auts+1.558
wikipedia+1.525
orem+1.514
д+1.497
ompl+1.480
Neg logit contributions
nces-1.787
quad-1.734
arms-1.683
ldom-1.610
bane-1.609
Tokennd
Token ID358
Feature activation-8.53e-03

Pos logit contributions
auts+3.841
orem+3.767
wikipedia+3.763
д+3.717
ompl+3.712
Neg logit contributions
nces-1.332
quad-1.267
arms-1.180
ldom-1.087
bane-1.079
Tokenront
Token ID4298
Feature activation+2.14e+00

Pos logit contributions
nces+0.056
quad+0.054
arms+0.052
ldom+0.050
bane+0.050
Neg logit contributions
auts-0.051
wikipedia-0.050
orem-0.049
д-0.049
ompl-0.049
Token la
Token ID8591
Feature activation+7.34e-01

Pos logit contributions
auts+11.815
orem+11.753
iste+11.326
ompl+10.982
 admire+10.947
Neg logit contributions
nces-11.599
quad-11.554
arms-11.135
ldom-10.860
tails-10.667
Token
Token ID39073
Feature activation+1.32e-01

Pos logit contributions
auts+4.461
orem+4.366
wikipedia+4.337
ompl+4.258
д+4.252
Neg logit contributions
nces-4.702
quad-4.435
arms-4.341
bane-4.169
ldom-4.165
Tokencision
Token ID16005
Feature activation+7.73e-01

Pos logit contributions
auts+0.887
wikipedia+0.869
orem+0.866
д+0.858
ompl+0.848
Neg logit contributions
nces-0.767
quad-0.742
arms-0.715
bane-0.680
ldom-0.678
Token finale
Token ID19523
Feature activation+2.35e-01

Pos logit contributions
auts+4.358
wikipedia+4.287
orem+4.274
ompl+4.155
д+4.153
Neg logit contributions
nces-5.156
quad-4.980
arms-4.871
ldom-4.653
bane-4.646
Token.
Token ID13
Feature activation+4.70e-01

Pos logit contributions
auts+1.351
wikipedia+1.322
orem+1.313
д+1.297
ompl+1.283
Neg logit contributions
nces-1.592
quad-1.545
arms-1.500
ldom-1.435
bane-1.435
Token giving
Token ID3501
Feature activation-5.53e-01

Pos logit contributions
auts+3.218
wikipedia+3.197
orem+3.155
д+3.136
ompl+3.071
Neg logit contributions
nces-3.197
quad-3.053
arms-2.961
ldom-2.841
bane-2.797
Token both
Token ID1111
Feature activation+4.67e-02

Pos logit contributions
nces+3.415
quad+3.345
arms+3.252
ldom+3.064
perate+3.054
Neg logit contributions
auts-3.363
orem-3.283
wikipedia-3.278
д-3.264
ompl-3.233
Token the
Token ID262
Feature activation+1.62e-01

Pos logit contributions
auts+0.306
wikipedia+0.300
orem+0.298
д+0.296
ompl+0.293
Neg logit contributions
nces-0.278
quad-0.270
arms-0.262
bane-0.247
ldom-0.247
Token carrot
Token ID40562
Feature activation+2.62e-01

Pos logit contributions
auts+0.930
wikipedia+0.911
orem+0.905
д+0.892
ompl+0.883
Neg logit contributions
nces-1.098
quad-1.064
arms-1.032
bane-0.990
ldom-0.990
Token and
Token ID290
Feature activation+1.63e+00

Pos logit contributions
auts+1.697
wikipedia+1.665
orem+1.653
д+1.637
ompl+1.621
Neg logit contributions
nces-1.591
quad-1.538
arms-1.490
ldom-1.418
bane-1.417
Token the
Token ID262
Feature activation+2.14e+00

Pos logit contributions
auts+7.353
orem+7.297
д+7.261
wikipedia+7.059
ocate+7.022
Neg logit contributions
nces-12.170
quad-11.393
arms-11.071
poses-10.808
ldom-10.713
Token stick
Token ID4859
Feature activation+2.09e-01

Pos logit contributions
д+9.661
orem+9.490
auts+9.318
 admire+9.186
ompl+8.897
Neg logit contributions
nces-15.513
quad-13.981
arms-13.699
poses-13.459
bane-13.185
Token
Token ID198
Feature activation-1.40e-03

Pos logit contributions
auts+1.180
wikipedia+1.154
orem+1.145
д+1.132
ompl+1.119
Neg logit contributions
nces-1.442
quad-1.401
arms-1.361
ldom-1.303
bane-1.303
Token
Token ID198
Feature activation+1.37e-01

Pos logit contributions
nces+0.010
quad+0.009
arms+0.009
ldom+0.009
bane+0.009
Neg logit contributions
auts-0.008
wikipedia-0.008
orem-0.008
д-0.008
ompl-0.008
TokenTo
Token ID2514
Feature activation+2.55e-01

Pos logit contributions
auts+0.835
wikipedia+0.817
orem+0.813
д+0.804
ompl+0.796
Neg logit contributions
nces-0.876
quad-0.850
arms-0.824
bane-0.786
ldom-0.785
Tokenan
Token ID272
Feature activation-3.09e-01

Pos logit contributions
auts+1.481
wikipedia+1.450
orem+1.439
д+1.422
ompl+1.407
Neg logit contributions
nces-1.714
quad-1.659
arms-1.611
bane-1.543
ldom-1.537
Token actually
Token ID1682
Feature activation-6.24e-01

Pos logit contributions
nces+1.273
quad+1.232
arms+1.203
bane+1.145
ldom+1.133
Neg logit contributions
auts-1.249
wikipedia-1.221
orem-1.219
д-1.201
ompl-1.196
Token drives
Token ID10182
Feature activation+6.64e-01

Pos logit contributions
nces+3.829
quad+3.688
arms+3.610
poses+3.418
bane+3.408
Neg logit contributions
auts-3.880
orem-3.816
wikipedia-3.772
ompl-3.698
д-3.690
Token the
Token ID262
Feature activation+4.32e-01

Pos logit contributions
auts+3.834
wikipedia+3.759
д+3.701
orem+3.684
ompl+3.608
Neg logit contributions
nces-4.453
quad-4.280
arms-4.141
ldom-4.044
bane-3.965
Token sheet
Token ID9629
Feature activation+1.10e+00

Pos logit contributions
auts+2.276
wikipedia+2.229
orem+2.207
д+2.184
ompl+2.152
Neg logit contributions
nces-3.139
quad-3.038
arms-2.947
ldom-2.851
bane-2.835
Token of
Token ID286
Feature activation+5.24e-01

Pos logit contributions
auts+6.080
wikipedia+5.968
д+5.868
orem+5.713
ompl+5.688
Neg logit contributions
nces-7.445
quad-6.952
arms-6.699
ldom-6.602
poses-6.524
Token ice
Token ID4771
Feature activation+2.13e+00

Pos logit contributions
auts+2.427
wikipedia+2.365
orem+2.331
д+2.312
ompl+2.270
Neg logit contributions
nces-4.146
quad-4.029
arms-3.924
ldom-3.797
bane-3.782
Token backwards
Token ID16196
Feature activation+9.21e-01

Pos logit contributions
auts+10.240
wikipedia+10.084
д+9.961
 admire+9.634
orem+9.506
Neg logit contributions
nces-13.642
quad-12.203
arms-11.923
ldom-11.856
poses-11.847
Token and
Token ID290
Feature activation-2.15e-01

Pos logit contributions
auts+4.872
wikipedia+4.786
д+4.753
orem+4.595
ompl+4.586
Neg logit contributions
nces-6.452
quad-6.155
arms-6.058
ldom-5.827
bane-5.806
Token inland
Token ID37874
Feature activation+5.01e-01

Pos logit contributions
nces+1.436
quad+1.401
arms+1.363
bane+1.295
poses+1.293
Neg logit contributions
auts-1.241
wikipedia-1.219
orem-1.216
ompl-1.196
д-1.191
Token.
Token ID13
Feature activation+7.30e-02

Pos logit contributions
auts+2.716
wikipedia+2.664
д+2.618
orem+2.611
ompl+2.577
Neg logit contributions
nces-3.548
quad-3.435
arms-3.337
ldom-3.204
bane-3.202
Token
Token ID564
Feature activation+1.12e-01

Pos logit contributions
auts+0.417
wikipedia+0.407
orem+0.405
д+0.400
ompl+0.396
Neg logit contributions
nces-0.497
quad-0.483
arms-0.469
bane-0.449
ldom-0.448
Token have
Token ID423
Feature activation+2.49e-01

Pos logit contributions
auts+0.957
wikipedia+0.937
orem+0.929
д+0.918
ompl+0.908
Neg logit contributions
nces-1.169
quad-1.136
arms-1.103
bane-1.056
ldom-1.056
Token moved
Token ID3888
Feature activation+6.35e-01

Pos logit contributions
auts+1.542
wikipedia+1.508
orem+1.496
д+1.485
ompl+1.467
Neg logit contributions
nces-1.582
quad-1.528
arms-1.479
bane-1.413
ldom-1.413
Token with
Token ID351
Feature activation+2.89e-01

Pos logit contributions
auts+3.380
wikipedia+3.297
д+3.262
orem+3.252
ompl+3.159
Neg logit contributions
nces-4.529
quad-4.365
arms-4.199
ldom-4.080
bane-4.063
Token local
Token ID1957
Feature activation+5.21e-01

Pos logit contributions
auts+1.797
wikipedia+1.762
orem+1.750
д+1.731
ompl+1.713
Neg logit contributions
nces-1.825
quad-1.768
arms-1.713
bane-1.632
ldom-1.631
Token forces
Token ID3386
Feature activation+6.39e-01

Pos logit contributions
auts+3.316
wikipedia+3.236
orem+3.218
д+3.200
ompl+3.151
Neg logit contributions
nces-3.207
quad-3.098
arms-2.933
bane-2.852
ldom-2.847
Token within
Token ID1626
Feature activation+2.12e+00

Pos logit contributions
auts+3.377
wikipedia+3.313
д+3.290
orem+3.249
ompl+3.209
Neg logit contributions
nces-4.590
quad-4.393
arms-4.285
bane-4.120
ldom-4.114
Token 20
Token ID1160
Feature activation+9.74e-01

Pos logit contributions
auts+9.917
д+9.724
wikipedia+9.627
 admire+9.461
orem+9.413
Neg logit contributions
nces-13.896
quad-13.098
bane-12.554
arms-12.257
tails-12.251
Token miles
Token ID4608
Feature activation+3.65e-02

Pos logit contributions
auts+5.508
д+5.278
wikipedia+5.275
orem+5.239
ompl+5.182
Neg logit contributions
nces-6.517
quad-6.243
arms-5.979
bane-5.900
ldom-5.866
Token of
Token ID286
Feature activation+5.28e-01

Pos logit contributions
auts+0.228
wikipedia+0.224
orem+0.223
д+0.219
ompl+0.218
Neg logit contributions
nces-0.228
quad-0.222
arms-0.214
ldom-0.204
bane-0.204
Token the
Token ID262
Feature activation+5.04e-01

Pos logit contributions
auts+2.993
wikipedia+2.905
orem+2.882
д+2.871
ompl+2.822
Neg logit contributions
nces-3.599
quad-3.513
arms-3.377
bane-3.263
ldom-3.254
Token ISIS
Token ID7768
Feature activation+8.94e-01

Pos logit contributions
auts+2.973
wikipedia+2.886
orem+2.879
д+2.842
ompl+2.806
Neg logit contributions
nces-3.352
quad-3.240
arms-3.108
ldom-3.008
bane-2.991
Tokeneg
Token ID1533
Feature activation+2.12e-01

Pos logit contributions
quad+3.537
nces+3.488
arms+3.471
bane+3.323
ldom+3.252
Neg logit contributions
auts-2.587
wikipedia-2.574
д-2.538
orem-2.448
ompl-2.435
Tokenener
Token ID877
Feature activation+7.28e-01

Pos logit contributions
auts+1.322
wikipedia+1.296
orem+1.286
д+1.274
ompl+1.260
Neg logit contributions
nces-1.331
quad-1.290
arms-1.249
bane-1.191
ldom-1.190
Tokenative
Token ID876
Feature activation-3.96e-01

Pos logit contributions
auts+3.970
orem+3.858
wikipedia+3.821
ompl+3.746
д+3.731
Neg logit contributions
nces-5.138
quad-4.941
arms-4.790
ldom-4.582
bane-4.557
Token collagen
Token ID45452
Feature activation+7.72e-01

Pos logit contributions
nces+2.612
quad+2.552
arms+2.479
bane+2.400
ldom+2.362
Neg logit contributions
auts-2.289
wikipedia-2.249
orem-2.231
д-2.223
ompl-2.202
Tokenous
Token ID516
Feature activation+3.20e-01

Pos logit contributions
auts+4.283
orem+4.166
wikipedia+4.131
д+4.049
ompl+4.035
Neg logit contributions
nces-5.366
quad-5.116
arms-4.992
ldom-4.767
bane-4.710
Token pl
Token ID458
Feature activation+2.11e+00

Pos logit contributions
auts+1.784
wikipedia+1.744
orem+1.732
д+1.709
ompl+1.689
Neg logit contributions
nces-2.227
quad-2.159
arms-2.098
ldom-2.009
bane-2.006
Tokenaques
Token ID46806
Feature activation+2.55e-01

Pos logit contributions
auts+9.190
orem+8.683
ompl+8.418
ocate+8.255
wikipedia+8.075
Neg logit contributions
nces-15.315
IOR-14.182
quad-13.970
ldom-13.497
bane-13.410
Token of
Token ID286
Feature activation+2.38e-01

Pos logit contributions
auts+1.411
wikipedia+1.379
orem+1.368
д+1.352
ompl+1.336
Neg logit contributions
nces-1.780
quad-1.727
arms-1.681
ldom-1.608
bane-1.608
Token the
Token ID262
Feature activation+1.18e-02

Pos logit contributions
auts+1.380
wikipedia+1.352
orem+1.341
д+1.327
ompl+1.311
Neg logit contributions
nces-1.605
quad-1.558
arms-1.512
bane-1.447
ldom-1.445
Token hand
Token ID1021
Feature activation+1.40e-01

Pos logit contributions
auts+0.087
wikipedia+0.085
orem+0.084
д+0.084
ompl+0.083
Neg logit contributions
nces-0.062
quad-0.060
arms-0.058
bane-0.054
ldom-0.054
Token")
Token ID4943
Feature activation-1.96e-01

Pos logit contributions
auts+0.814
wikipedia+0.795
orem+0.793
д+0.784
ompl+0.774
Neg logit contributions
nces-0.945
quad-0.921
arms-0.894
bane-0.857
ldom-0.856
Token pour
Token ID12797
Feature activation+1.36e+00

Pos logit contributions
auts+2.233
wikipedia+2.183
orem+2.173
д+2.145
ompl+2.126
Neg logit contributions
nces-2.629
quad-2.544
arms-2.470
ldom-2.377
bane-2.368
Token le
Token ID443
Feature activation+8.23e-01

Pos logit contributions
auts+7.636
wikipedia+7.414
ompl+7.344
orem+7.327
д+7.272
Neg logit contributions
nces-8.366
quad-8.164
arms-7.935
ldom-7.689
tails-7.434
Token Command
Token ID9455
Feature activation+9.55e-01

Pos logit contributions
auts+4.797
orem+4.699
wikipedia+4.649
ompl+4.585
д+4.545
Neg logit contributions
nces-5.376
quad-5.142
arms-4.993
ldom-4.775
bane-4.771
Tokenement
Token ID972
Feature activation+6.05e-01

Pos logit contributions
auts+3.966
orem+3.906
wikipedia+3.884
iste+3.719
д+3.674
Neg logit contributions
nces-7.655
quad-7.377
arms-7.288
ldom-7.034
bane-7.023
Token des
Token ID748
Feature activation+1.12e-01

Pos logit contributions
auts+3.527
wikipedia+3.449
orem+3.420
д+3.374
ompl+3.338
Neg logit contributions
nces-4.018
quad-3.915
arms-3.788
ldom-3.633
bane-3.626
Token Cors
Token ID26978
Feature activation+2.10e+00

Pos logit contributions
auts+0.678
wikipedia+0.667
orem+0.663
д+0.655
ompl+0.648
Neg logit contributions
nces-0.720
quad-0.699
arms-0.678
bane-0.645
ldom-0.644
Tokenaires
Token ID17693
Feature activation+6.17e-01

Pos logit contributions
auts+10.162
orem+9.474
wikipedia+9.242
ompl+8.643
essee+8.642
Neg logit contributions
quad-13.245
nces-13.035
ldom-12.435
IOR-12.270
bane-12.172
Token de
Token ID390
Feature activation+1.56e-01

Pos logit contributions
auts+3.463
orem+3.380
wikipedia+3.376
д+3.311
ompl+3.298
Neg logit contributions
nces-4.206
quad-4.077
arms-3.966
ldom-3.828
bane-3.796
Token l
Token ID300
Feature activation+9.86e-01

Pos logit contributions
auts+0.914
wikipedia+0.897
orem+0.889
д+0.880
ompl+0.868
Neg logit contributions
nces-1.042
quad-1.012
arms-0.982
bane-0.940
ldom-0.937
Token'
Token ID6
Feature activation+8.63e-01

Pos logit contributions
auts+3.938
orem+3.848
wikipedia+3.696
д+3.691
ompl+3.673
Neg logit contributions
nces-8.325
quad-8.065
arms-7.783
ldom-7.646
bane-7.555
TokenE
Token ID36
Feature activation+3.52e-01

Pos logit contributions
auts+5.084
wikipedia+4.903
orem+4.891
д+4.824
ompl+4.793
Neg logit contributions
nces-5.709
quad-5.429
arms-5.178
ldom-5.146
perate-5.051
Token,
Token ID11
Feature activation+1.65e-01

Pos logit contributions
auts+3.217
wikipedia+3.133
orem+3.098
д+3.085
ompl+3.038
Neg logit contributions
nces-3.460
quad-3.350
arms-3.240
ldom-3.082
bane-3.073
Token Or
Token ID1471
Feature activation+5.20e-01

Pos logit contributions
auts+1.056
wikipedia+1.036
orem+1.029
д+1.019
ompl+1.008
Neg logit contributions
nces-1.007
quad-0.975
arms-0.943
bane-0.898
ldom-0.897
Tokenk
Token ID74
Feature activation+1.56e-01

Pos logit contributions
auts+3.678
wikipedia+3.610
orem+3.529
ompl+3.493
д+3.489
Neg logit contributions
nces-2.782
quad-2.683
arms-2.567
ldom-2.445
bane-2.440
Tokenney
Token ID1681
Feature activation-9.18e-02

Pos logit contributions
auts+1.115
wikipedia+1.096
orem+1.090
д+1.080
ompl+1.070
Neg logit contributions
nces-0.836
quad-0.805
arms-0.775
bane-0.733
ldom-0.732
Token and
Token ID290
Feature activation-1.53e-01

Pos logit contributions
nces+0.557
quad+0.536
arms+0.521
bane+0.500
ldom+0.497
Neg logit contributions
auts-0.593
orem-0.586
wikipedia-0.585
д-0.575
ompl-0.573
Token Mill
Token ID9212
Feature activation+2.10e+00

Pos logit contributions
nces+0.928
quad+0.897
arms+0.871
bane+0.834
ldom+0.827
Neg logit contributions
auts-0.987
wikipedia-0.970
orem-0.966
д-0.959
ompl-0.950
Tokenport
Token ID634
Feature activation+4.50e-01

Pos logit contributions
ompl+10.553
auts+10.395
ocate+10.318
д+10.251
orem+10.233
Neg logit contributions
nces-12.864
quad-12.233
arms-11.506
ldom-11.234
IOR-11.049
Token were
Token ID547
Feature activation-5.13e-02

Pos logit contributions
auts+2.699
wikipedia+2.623
orem+2.593
д+2.586
ompl+2.552
Neg logit contributions
nces-2.937
quad-2.826
arms-2.736
ldom-2.620
bane-2.605
Token exploring
Token ID13504
Feature activation-4.40e-02

Pos logit contributions
nces+0.311
quad+0.301
arms+0.291
bane+0.278
ldom+0.275
Neg logit contributions
auts-0.333
wikipedia-0.325
orem-0.325
д-0.320
ompl-0.318
Token their
Token ID511
Feature activation-4.70e-01

Pos logit contributions
nces+0.275
quad+0.267
arms+0.258
ldom+0.246
bane+0.246
Neg logit contributions
auts-0.275
wikipedia-0.270
orem-0.269
д-0.266
ompl-0.263
Token options
Token ID3689
Feature activation+6.66e-02

Pos logit contributions
nces+2.882
quad+2.801
arms+2.714
bane+2.613
perate+2.608
Neg logit contributions
auts-2.906
wikipedia-2.885
orem-2.872
д-2.821
ompl-2.816
Tokened
Token ID276
Feature activation-4.62e-01

Pos logit contributions
auts+0.386
orem+0.372
wikipedia+0.372
д+0.363
ompl+0.354
Neg logit contributions
nces-1.008
quad-0.980
arms-0.965
ldom-0.933
bane-0.931
Token by
Token ID416
Feature activation-1.23e-01

Pos logit contributions
nces+2.857
quad+2.786
arms+2.664
ldom+2.563
bane+2.545
Neg logit contributions
auts-2.873
orem-2.845
wikipedia-2.819
ompl-2.776
д-2.762
Token dumping
Token ID30231
Feature activation-3.38e-01

Pos logit contributions
nces+0.776
quad+0.758
arms+0.732
bane+0.697
ldom+0.695
Neg logit contributions
auts-0.751
wikipedia-0.740
orem-0.737
д-0.728
ompl-0.719
Token garbage
Token ID15413
Feature activation-1.10e+00

Pos logit contributions
nces+2.020
quad+1.983
arms+1.909
bane+1.812
ldom+1.806
Neg logit contributions
auts-2.153
wikipedia-2.140
orem-2.133
ompl-2.091
д-2.090
Token and
Token ID290
Feature activation-5.20e-01

Pos logit contributions
nces+6.047
quad+6.040
arms+5.733
bane+5.566
perate+5.498
Neg logit contributions
orem-7.102
wikipedia-6.938
auts-6.922
ompl-6.887
д-6.861
Token diver
Token ID12312
Feature activation-2.49e+00

Pos logit contributions
nces+2.856
quad+2.818
arms+2.711
bane+2.587
perate+2.570
Neg logit contributions
auts-3.490
orem-3.468
wikipedia-3.454
ompl-3.384
д-3.374
Tokenting
Token ID889
Feature activation-3.41e-01

Pos logit contributions
nces+4.497
gging+4.156
tails+4.027
posing+3.884
arms+3.822
Neg logit contributions
orem-21.822
wikipedia-21.706
ompl-21.392
auts-21.348
sburgh-20.884
Token the
Token ID262
Feature activation-3.27e-01

Pos logit contributions
nces+2.120
quad+2.074
arms+2.008
bane+1.923
perate+1.909
Neg logit contributions
auts-2.082
orem-2.067
wikipedia-2.059
ompl-2.018
д-2.013
Token creek
Token ID39459
Feature activation-7.62e-01

Pos logit contributions
nces+1.911
quad+1.875
arms+1.804
bane+1.730
perate+1.718
Neg logit contributions
auts-2.120
orem-2.078
wikipedia-2.077
д-2.044
ompl-2.038
Token water
Token ID1660
Feature activation-9.91e-02

Pos logit contributions
nces+3.948
quad+3.909
arms+3.756
ldom+3.581
tails+3.576
Neg logit contributions
orem-5.221
auts-5.198
wikipedia-5.060
ompl-4.989
д-4.958
Token so
Token ID523
Feature activation-4.34e-01

Pos logit contributions
nces+0.694
quad+0.676
arms+0.656
ldom+0.629
bane+0.629
Neg logit contributions
auts-0.545
orem-0.534
wikipedia-0.533
д-0.522
ompl-0.518
Token in
Token ID287
Feature activation-2.76e-02

Pos logit contributions
auts+0.336
wikipedia+0.329
orem+0.327
д+0.324
ompl+0.320
Neg logit contributions
nces-0.329
quad-0.319
arms-0.309
bane-0.294
ldom-0.294
Token the
Token ID262
Feature activation-2.90e-01

Pos logit contributions
nces+0.172
quad+0.166
arms+0.161
ldom+0.153
bane+0.153
Neg logit contributions
auts-0.174
wikipedia-0.171
orem-0.169
д-0.167
ompl-0.165
Token Lif
Token ID21073
Feature activation+4.90e-01

Pos logit contributions
nces+1.902
quad+1.858
arms+1.799
ldom+1.718
bane+1.710
Neg logit contributions
auts-1.714
wikipedia-1.673
д-1.645
orem-1.641
ompl-1.607
Tokeneline
Token ID4470
Feature activation-2.08e-01

Pos logit contributions
auts+3.860
wikipedia+3.826
orem+3.788
д+3.745
ompl+3.721
Neg logit contributions
nces-2.242
quad-2.058
arms-1.972
tails-1.893
IOR-1.836
Token program
Token ID1430
Feature activation-3.52e-01

Pos logit contributions
nces+1.388
quad+1.354
arms+1.311
bane+1.247
ldom+1.247
Neg logit contributions
auts-1.206
wikipedia-1.187
orem-1.158
д-1.158
ompl-1.142
Token diver
Token ID12312
Feature activation-2.38e+00

Pos logit contributions
nces+2.356
quad+2.309
arms+2.234
bane+2.137
ldom+2.134
Neg logit contributions
auts-2.023
wikipedia-1.987
д-1.957
orem-1.955
ompl-1.921
Tokents
Token ID912
Feature activation+9.15e-02

Pos logit contributions
nces+8.610
tails+7.861
arms+7.418
poses+7.208
gging+6.365
Neg logit contributions
orem-17.866
wikipedia-17.745
estern-17.547
д-17.528
ompl-17.459
Token scarce
Token ID18549
Feature activation-5.72e-01

Pos logit contributions
auts+0.569
wikipedia+0.559
orem+0.555
д+0.549
ompl+0.543
Neg logit contributions
nces-0.576
quad-0.558
arms-0.541
bane-0.515
ldom-0.515
Token funds
Token ID5153
Feature activation-3.70e-01

Pos logit contributions
nces+3.076
quad+2.937
arms+2.864
bane+2.729
perate+2.708
Neg logit contributions
auts-3.952
wikipedia-3.938
д-3.895
orem-3.851
ompl-3.836
Token from
Token ID422
Feature activation-3.72e-01

Pos logit contributions
nces+2.355
quad+2.325
arms+2.234
ldom+2.136
perate+2.130
Neg logit contributions
auts-2.202
wikipedia-2.178
orem-2.176
д-2.115
ompl-2.113
Token the
Token ID262
Feature activation-1.57e-01

Pos logit contributions
nces+2.350
quad+2.269
arms+2.218
ldom+2.114
perate+2.092
Neg logit contributions
auts-2.277
wikipedia-2.261
д-2.203
orem-2.200
estern-2.150
Tokenney
Token ID1681
Feature activation-9.36e-02

Pos logit contributions
nces+1.019
quad+0.967
arms+0.942
bane+0.908
ldom+0.885
Neg logit contributions
auts-1.334
orem-1.316
wikipedia-1.313
д-1.298
ompl-1.283
Token-
Token ID12
Feature activation-5.82e-02

Pos logit contributions
nces+0.513
quad+0.492
arms+0.475
bane+0.454
ldom+0.452
Neg logit contributions
auts-0.657
orem-0.651
wikipedia-0.645
д-0.637
ompl-0.635
TokenG
Token ID38
Feature activation-3.55e-01

Pos logit contributions
nces+0.351
quad+0.344
arms+0.332
bane+0.316
ldom+0.313
Neg logit contributions
auts-0.375
orem-0.367
wikipedia-0.366
д-0.361
ompl-0.359
Tokenambling
Token ID15366
Feature activation-1.14e-01

Pos logit contributions
nces+2.321
quad+2.317
arms+2.262
bane+2.143
ldom+2.130
Neg logit contributions
wikipedia-2.040
auts-2.011
д-1.977
orem-1.952
ompl-1.916
Token-
Token ID12
Feature activation-2.22e-01

Pos logit contributions
nces+0.718
quad+0.701
arms+0.678
bane+0.647
ldom+0.643
Neg logit contributions
auts-0.709
wikipedia-0.694
orem-0.693
д-0.684
ompl-0.677
TokenSuper
Token ID12442
Feature activation-2.37e+00

Pos logit contributions
nces+1.326
quad+1.312
arms+1.268
bane+1.205
tails+1.189
Neg logit contributions
auts-1.433
orem-1.407
wikipedia-1.390
ompl-1.375
д-1.373
Tokenbowl
Token ID36859
Feature activation-6.06e-01

Pos logit contributions
quad+13.395
nces+12.986
poses+12.822
arms+12.735
posing+12.615
Neg logit contributions
orem-12.227
wikipedia-11.939
auts-11.652
д-11.465
ompl-11.178
Token Advertising
Token ID40113
Feature activation-6.33e-02

Pos logit contributions
nces+3.750
quad+3.680
arms+3.549
bane+3.386
ldom+3.355
Neg logit contributions
auts-3.676
orem-3.614
wikipedia-3.602
д-3.590
ompl-3.495
Token-
Token ID12
Feature activation-3.56e-01

Pos logit contributions
nces+0.391
quad+0.381
arms+0.366
bane+0.349
ldom+0.348
Neg logit contributions
auts-0.402
wikipedia-0.396
orem-0.392
д-0.387
ompl-0.382
TokenAust
Token ID15160
Feature activation-2.24e-02

Pos logit contributions
nces+2.091
quad+2.089
arms+2.016
bane+1.913
tails+1.892
Neg logit contributions
auts-2.301
orem-2.267
wikipedia-2.228
ompl-2.213
д-2.198
Tokenrail
Token ID30224
Feature activation-2.39e-01

Pos logit contributions
nces+0.109
quad+0.104
arms+0.101
bane+0.095
ldom+0.094
Neg logit contributions
auts-0.171
wikipedia-0.168
orem-0.168
д-0.167
ompl-0.164
Token not
Token ID407
Feature activation+3.26e-01

Pos logit contributions
auts+0.580
wikipedia+0.567
orem+0.564
д+0.557
ompl+0.551
Neg logit contributions
nces-0.671
quad-0.652
arms-0.632
bane-0.605
ldom-0.605
Token easy
Token ID2562
Feature activation+6.63e-01

Pos logit contributions
auts+1.885
wikipedia+1.858
orem+1.836
д+1.813
ompl+1.789
Neg logit contributions
nces-2.188
quad-2.122
arms-2.060
ldom-1.969
bane-1.964
Token even
Token ID772
Feature activation+7.03e-01

Pos logit contributions
auts+3.054
wikipedia+2.974
orem+2.971
д+2.932
ompl+2.885
Neg logit contributions
nces-5.180
quad-5.016
arms-4.921
ldom-4.764
bane-4.762
Token for
Token ID329
Feature activation+2.44e-01

Pos logit contributions
auts+3.683
wikipedia+3.607
orem+3.578
д+3.553
ompl+3.474
Neg logit contributions
nces-5.052
quad-4.849
arms-4.733
bane-4.592
ldom-4.579
Token the
Token ID262
Feature activation+1.87e-01

Pos logit contributions
auts+1.472
wikipedia+1.440
orem+1.427
д+1.412
ompl+1.398
Neg logit contributions
nces-1.584
quad-1.532
arms-1.487
bane-1.423
ldom-1.422
Token super
Token ID2208
Feature activation-2.24e+00

Pos logit contributions
auts+1.224
wikipedia+1.201
orem+1.193
д+1.180
ompl+1.169
Neg logit contributions
nces-1.121
quad-1.082
arms-1.047
bane-0.997
ldom-0.997
Tokencom
Token ID785
Feature activation-1.51e+00

Pos logit contributions
quad+13.463
nces+12.362
arms+12.248
IOR+11.679
poses+11.593
Neg logit contributions
orem-12.250
estern-11.574
д-11.072
wikipedia-11.035
essee-10.710
Tokenputers
Token ID41510
Feature activation-3.16e-01

Pos logit contributions
quad+3.254
nces+2.990
posing+2.770
arms+2.689
poses+2.664
Neg logit contributions
orem-14.283
wikipedia-14.005
д-13.962
estern-13.877
ompl-13.848
Token,
Token ID11
Feature activation-1.37e-01

Pos logit contributions
nces+2.028
quad+2.011
arms+1.912
bane+1.823
perate+1.816
Neg logit contributions
auts-1.881
orem-1.847
wikipedia-1.845
д-1.821
ompl-1.815
Token but
Token ID475
Feature activation-1.32e-03

Pos logit contributions
nces+0.853
quad+0.838
arms+0.806
ldom+0.763
bane+0.762
Neg logit contributions
auts-0.851
wikipedia-0.838
orem-0.837
д-0.824
ompl-0.818
Token it
Token ID340
Feature activation+2.98e-01

Pos logit contributions
nces+0.008
quad+0.008
arms+0.008
bane+0.007
ldom+0.007
Neg logit contributions
auts-0.008
wikipedia-0.008
orem-0.008
д-0.008
ompl-0.008
Token The
Token ID383
Feature activation-3.99e-01

Pos logit contributions
nces+5.928
quad+5.785
arms+5.671
ldom+5.452
perate+5.365
Neg logit contributions
orem-7.290
auts-7.255
wikipedia-7.045
ompl-6.961
essee-6.898
Token Times
Token ID3782
Feature activation-5.49e-01

Pos logit contributions
arms+3.187
quad+3.121
nces+3.117
bane+3.035
IOR+2.985
Neg logit contributions
auts-1.718
wikipedia-1.617
orem-1.577
estern-1.546
д-1.532
Token of
Token ID286
Feature activation-7.71e-01

Pos logit contributions
nces+3.084
quad+3.012
arms+2.912
bane+2.783
ldom+2.745
Neg logit contributions
auts-3.715
wikipedia-3.652
orem-3.651
д-3.594
ompl-3.570
Token Israel
Token ID2692
Feature activation-4.87e-01

Pos logit contributions
arms+3.546
quad+3.502
nces+3.481
IOR+3.180
bane+3.174
Neg logit contributions
auts-5.769
wikipedia-5.721
orem-5.621
д-5.548
ompl-5.473
Token's
Token ID338
Feature activation-1.17e+00

Pos logit contributions
nces+3.230
quad+3.143
arms+3.055
bane+2.922
ldom+2.921
Neg logit contributions
auts-2.842
wikipedia-2.789
orem-2.768
д-2.734
ompl-2.708
Token Daily
Token ID6714
Feature activation-2.22e+00

Pos logit contributions
arms+6.075
IOR+6.074
bane+5.894
tails+5.842
quad+5.695
Neg logit contributions
auts-7.607
wikipedia-7.532
orem-7.517
д-7.397
ompl-7.176
Token Edition
Token ID5061
Feature activation-8.77e-01

Pos logit contributions
arms+3.400
quad+2.716
tails+2.489
bane+1.963
perate+1.882
Neg logit contributions
wikipedia-21.796
orem-21.303
auts-20.912
estern-20.909
sburgh-20.696
Token by
Token ID416
Feature activation-1.29e+00

Pos logit contributions
arms+4.306
nces+4.136
quad+4.128
bane+4.053
tails+4.015
Neg logit contributions
wikipedia-6.269
orem-6.206
auts-6.145
д-5.977
ompl-5.936
Token email
Token ID3053
Feature activation-1.33e+00

Pos logit contributions
quad+6.001
arms+5.872
perate+5.668
nces+5.620
poses+5.495
Neg logit contributions
auts-9.048
orem-8.974
wikipedia-8.902
ompl-8.714
д-8.631
Token and
Token ID290
Feature activation-6.86e-01

Pos logit contributions
arms+4.878
quad+4.577
perate+4.491
ldom+4.440
tails+4.359
Neg logit contributions
wikipedia-10.863
auts-10.803
orem-10.424
ompl-10.354
д-10.350
Token never
Token ID1239
Feature activation-1.81e+00

Pos logit contributions
quad+3.318
arms+3.217
nces+3.178
perate+3.172
ldom+3.029
Neg logit contributions
auts-5.045
wikipedia-4.933
orem-4.879
д-4.855
ompl-4.801
Tokenoom
Token ID4207
Feature activation+1.83e-01

Pos logit contributions
auts+2.176
wikipedia+2.138
orem+2.117
д+2.092
ompl+2.069
Neg logit contributions
nces-2.572
quad-2.497
arms-2.426
ldom-2.322
bane-2.319
Tokenin
Token ID259
Feature activation+1.39e-01

Pos logit contributions
auts+1.032
wikipedia+1.014
orem+1.007
д+0.993
ompl+0.977
Neg logit contributions
nces-1.250
quad-1.220
arms-1.187
ldom-1.138
bane-1.136
Tokenland
Token ID1044
Feature activation+4.76e-01

Pos logit contributions
auts+0.872
wikipedia+0.859
orem+0.853
д+0.841
ompl+0.834
Neg logit contributions
nces-0.861
quad-0.835
arms-0.809
bane-0.772
ldom-0.772
Token,
Token ID11
Feature activation+4.86e-02

Pos logit contributions
auts+2.776
wikipedia+2.721
orem+2.688
д+2.671
ompl+2.634
Neg logit contributions
nces-3.184
quad-3.079
arms-2.985
bane-2.847
ldom-2.843
Token and
Token ID290
Feature activation-2.18e-01

Pos logit contributions
auts+0.312
wikipedia+0.306
orem+0.304
д+0.301
ompl+0.298
Neg logit contributions
nces-0.296
quad-0.287
arms-0.277
bane-0.264
ldom-0.264
Token ad
Token ID512
Feature activation-2.22e+00

Pos logit contributions
nces+1.375
quad+1.327
arms+1.291
bane+1.232
ldom+1.231
Neg logit contributions
auts-1.347
wikipedia-1.318
orem-1.314
д-1.296
ompl-1.286
Tokenheres
Token ID19079
Feature activation+3.39e-01

Pos logit contributions
arms+12.972
poses+12.852
nces+12.848
quad+12.766
tails+11.820
Neg logit contributions
wikipedia-11.018
orem-10.376
essee-10.286
д-10.161
auts-10.074
Token to
Token ID284
Feature activation-2.74e-01

Pos logit contributions
auts+1.808
wikipedia+1.758
orem+1.746
д+1.723
ompl+1.715
Neg logit contributions
nces-2.456
quad-2.384
arms-2.315
ldom-2.225
bane-2.222
Token the
Token ID262
Feature activation-2.97e-02

Pos logit contributions
nces+1.737
quad+1.670
arms+1.626
ldom+1.554
bane+1.550
Neg logit contributions
auts-1.679
orem-1.636
ompl-1.606
д-1.603
wikipedia-1.603
Token original
Token ID2656
Feature activation+4.60e-02

Pos logit contributions
nces+0.190
quad+0.184
arms+0.179
bane+0.171
ldom+0.171
Neg logit contributions
auts-0.182
wikipedia-0.177
orem-0.176
д-0.175
ompl-0.173
Token stories
Token ID3923
Feature activation+1.57e-01

Pos logit contributions
auts+0.298
wikipedia+0.292
orem+0.290
д+0.287
ompl+0.284
Neg logit contributions
nces-0.278
quad-0.269
arms-0.260
bane-0.247
ldom-0.247
Token of
Token ID286
Feature activation-7.55e-01

Pos logit contributions
nces+1.662
quad+1.624
arms+1.558
poses+1.457
ldom+1.457
Neg logit contributions
auts-2.150
orem-2.143
wikipedia-2.119
д-2.109
ompl-2.056
Token Defense
Token ID5947
Feature activation-7.63e-01

Pos logit contributions
nces+3.121
arms+3.111
quad+3.081
perate+2.706
ldom+2.674
Neg logit contributions
wikipedia-5.929
auts-5.902
orem-5.896
д-5.869
ompl-5.791
Token
Token ID447
Feature activation-5.44e-01

Pos logit contributions
nces+4.655
quad+4.599
arms+4.517
bane+4.164
ldom+4.160
Neg logit contributions
wikipedia-4.590
auts-4.561
orem-4.549
д-4.495
ompl-4.381
Token
Token ID247
Feature activation-6.32e-01

Pos logit contributions
nces+2.546
quad+2.460
arms+2.361
bane+2.195
ldom+2.173
Neg logit contributions
auts-4.238
wikipedia-4.173
orem-4.150
д-4.091
ompl-4.075
Tokens
Token ID82
Feature activation-1.10e+00

Pos logit contributions
nces+4.486
quad+4.452
arms+4.330
poses+4.094
ldom+4.067
Neg logit contributions
auts-3.220
orem-3.197
wikipedia-3.190
д-3.141
ompl-3.098
Token urgent
Token ID18039
Feature activation-2.21e+00

Pos logit contributions
nces+6.178
quad+6.178
arms+6.052
ldom+5.547
poses+5.508
Neg logit contributions
auts-6.787
wikipedia-6.746
д-6.669
orem-6.628
estern-6.560
Token needs
Token ID2476
Feature activation-1.18e+00

Pos logit contributions
arms+10.312
quad+10.289
nces+10.112
 proportions+9.290
poses+9.192
Neg logit contributions
wikipedia-13.185
estern-13.059
д-13.029
auts-12.961
orem-12.606
Token,
Token ID11
Feature activation-6.52e-01

Pos logit contributions
quad+6.927
nces+6.676
arms+6.293
poses+6.059
ldom+5.952
Neg logit contributions
wikipedia-7.059
auts-6.965
orem-6.948
д-6.750
ompl-6.719
Token says
Token ID1139
Feature activation-6.27e-01

Pos logit contributions
nces+4.005
quad+4.001
arms+3.875
poses+3.624
bane+3.612
Neg logit contributions
auts-3.889
orem-3.852
wikipedia-3.810
д-3.758
ompl-3.734
Token Capt
Token ID6790
Feature activation+6.98e-01

Pos logit contributions
nces+3.672
quad+3.564
arms+3.473
bane+3.229
poses+3.199
Neg logit contributions
auts-4.009
wikipedia-3.906
д-3.887
orem-3.881
ompl-3.878
Token.
Token ID13
Feature activation-7.83e-01

Pos logit contributions
auts+3.507
wikipedia+3.384
orem+3.373
д+3.311
ompl+3.288
Neg logit contributions
nces-5.201
quad-5.056
arms-4.928
ldom-4.757
bane-4.751
Token to
Token ID284
Feature activation-5.46e-01

Pos logit contributions
nces+4.011
quad+3.974
arms+3.865
bane+3.704
perate+3.668
Neg logit contributions
auts-3.692
wikipedia-3.663
orem-3.625
ompl-3.619
д-3.557
Token the
Token ID262
Feature activation-4.53e-01

Pos logit contributions
nces+3.111
quad+3.024
arms+2.959
perate+2.803
ldom+2.784
Neg logit contributions
auts-3.594
wikipedia-3.590
д-3.544
orem-3.537
ompl-3.506
Token islands
Token ID14807
Feature activation-1.19e+00

Pos logit contributions
nces+2.618
quad+2.552
arms+2.488
perate+2.349
bane+2.349
Neg logit contributions
auts-2.974
wikipedia-2.938
д-2.927
ompl-2.870
orem-2.867
Token in
Token ID287
Feature activation+2.65e-02

Pos logit contributions
quad+6.795
nces+6.589
arms+6.492
bane+6.266
perate+6.230
Neg logit contributions
auts-7.232
orem-7.149
wikipedia-7.134
estern-7.113
д-7.095
Token a
Token ID257
Feature activation-2.32e-01

Pos logit contributions
auts+0.163
wikipedia+0.161
orem+0.160
д+0.158
ompl+0.156
Neg logit contributions
nces-0.168
quad-0.164
arms-0.159
ldom-0.151
bane-0.151
Token super
Token ID2208
Feature activation-2.10e+00

Pos logit contributions
nces+1.327
quad+1.315
arms+1.255
perate+1.194
ldom+1.191
Neg logit contributions
auts-1.550
wikipedia-1.525
orem-1.515
д-1.501
ompl-1.489
Token-
Token ID12
Feature activation-1.26e+00

Pos logit contributions
quad+10.774
arms+9.473
perate+9.349
IOR+9.178
bane+8.725
Neg logit contributions
orem-13.395
estern-13.233
д-13.068
wikipedia-12.775
auts-12.482
Tokencool
Token ID24494
Feature activation+4.58e-01

Pos logit contributions
quad+7.712
arms+7.172
tails+6.807
nces+6.777
perate+6.767
Neg logit contributions
orem-7.726
д-7.415
estern-7.302
auts-7.273
ompl-7.261
Tokened
Token ID276
Feature activation+5.02e-02

Pos logit contributions
auts+1.911
wikipedia+1.854
orem+1.843
д+1.810
ompl+1.773
Neg logit contributions
nces-3.836
quad-3.719
arms-3.641
ldom-3.520
bane-3.513
Token,
Token ID11
Feature activation+2.05e-01

Pos logit contributions
auts+0.330
wikipedia+0.324
orem+0.322
д+0.319
ompl+0.316
Neg logit contributions
nces-0.297
quad-0.290
arms-0.279
bane-0.266
ldom-0.265
Token liquid
Token ID8122
Feature activation-1.88e-01

Pos logit contributions
auts+1.308
wikipedia+1.283
orem+1.274
д+1.261
ompl+1.247
Neg logit contributions
nces-1.261
quad-1.216
arms-1.179
bane-1.123
ldom-1.122
Token and
Token ID290
Feature activation-2.65e-01

Pos logit contributions
nces+0.643
quad+0.628
arms+0.606
bane+0.582
ldom+0.579
Neg logit contributions
auts-0.622
wikipedia-0.608
orem-0.607
д-0.600
ompl-0.594
Token bring
Token ID2222
Feature activation-8.61e-02

Pos logit contributions
nces+1.742
quad+1.704
arms+1.654
bane+1.591
ldom+1.578
Neg logit contributions
auts-1.560
wikipedia-1.526
orem-1.510
д-1.497
ompl-1.470
Token him
Token ID683
Feature activation+2.93e-01

Pos logit contributions
nces+0.525
quad+0.508
arms+0.492
bane+0.469
ldom+0.467
Neg logit contributions
auts-0.552
wikipedia-0.542
orem-0.540
д-0.534
ompl-0.529
Token into
Token ID656
Feature activation-3.39e-01

Pos logit contributions
auts+1.528
wikipedia+1.490
orem+1.469
д+1.459
ompl+1.435
Neg logit contributions
nces-2.137
quad-2.076
arms-2.019
ldom-1.941
bane-1.937
Token this
Token ID428
Feature activation-2.35e-01

Pos logit contributions
nces+2.095
quad+2.075
arms+2.017
ldom+1.917
poses+1.904
Neg logit contributions
auts-2.085
orem-2.066
wikipedia-2.045
д-2.019
ompl-1.997
Token super
Token ID2208
Feature activation-2.08e+00

Pos logit contributions
nces+1.421
quad+1.395
arms+1.349
ldom+1.286
bane+1.281
Neg logit contributions
auts-1.497
orem-1.478
wikipedia-1.472
д-1.448
ompl-1.444
Token spy
Token ID13997
Feature activation-6.02e-01

Pos logit contributions
quad+11.927
nces+11.304
arms+11.163
posing+10.902
poses+10.822
Neg logit contributions
orem-11.523
wikipedia-10.928
д-10.799
auts-10.747
estern-10.714
Token political
Token ID1964
Feature activation-2.80e-02

Pos logit contributions
quad+3.711
nces+3.678
arms+3.591
bane+3.416
ldom+3.386
Neg logit contributions
wikipedia-3.643
orem-3.638
auts-3.629
д-3.553
ompl-3.551
Token thriller
Token ID32251
Feature activation-3.90e-01

Pos logit contributions
nces+0.180
quad+0.176
arms+0.170
bane+0.162
ldom+0.162
Neg logit contributions
auts-0.170
wikipedia-0.167
orem-0.166
д-0.164
ompl-0.162
Token made
Token ID925
Feature activation-4.50e-01

Pos logit contributions
nces+2.453
quad+2.441
arms+2.352
bane+2.248
ldom+2.231
Neg logit contributions
auts-2.348
wikipedia-2.325
orem-2.314
д-2.280
ompl-2.266
Token so
Token ID523
Feature activation-5.94e-01

Pos logit contributions
nces+2.540
quad+2.504
arms+2.394
bane+2.292
ldom+2.261
Neg logit contributions
auts-3.024
orem-2.983
wikipedia-2.975
д-2.937
ompl-2.901
Token Technology
Token ID8987
Feature activation+3.15e-01

Pos logit contributions
nces+2.266
quad+2.204
arms+2.146
bane+2.048
tails+2.029
Neg logit contributions
auts-2.488
wikipedia-2.454
orem-2.420
д-2.384
ompl-2.347
Token and
Token ID290
Feature activation-4.25e-01

Pos logit contributions
auts+1.790
wikipedia+1.744
orem+1.738
д+1.721
ompl+1.703
Neg logit contributions
nces-2.150
quad-2.081
arms-2.025
ldom-1.947
bane-1.934
Token two
Token ID734
Feature activation-3.09e-01

Pos logit contributions
nces+2.691
quad+2.609
arms+2.512
bane+2.415
tails+2.381
Neg logit contributions
auts-2.605
wikipedia-2.573
orem-2.526
д-2.469
ompl-2.454
Token 8
Token ID807
Feature activation-5.73e-01

Pos logit contributions
nces+1.977
quad+1.915
arms+1.861
bane+1.779
perate+1.761
Neg logit contributions
auts-1.890
wikipedia-1.860
orem-1.840
д-1.805
ompl-1.787
Tokenmm
Token ID3020
Feature activation-8.85e-01

Pos logit contributions
nces+2.622
quad+2.563
arms+2.489
bane+2.317
perate+2.275
Neg logit contributions
auts-4.429
wikipedia-4.387
orem-4.370
д-4.272
ompl-4.240
Token Super
Token ID3115
Feature activation-2.08e+00

Pos logit contributions
nces+5.579
quad+5.348
arms+5.206
perate+5.051
bane+5.026
Neg logit contributions
auts-5.263
wikipedia-5.253
orem-5.108
д-4.982
estern-4.979
TokenP
Token ID47
Feature activation-6.48e-01

Pos logit contributions
quad+11.960
IOR+11.317
nces+11.104
arms+11.058
bane+11.001
Neg logit contributions
orem-11.652
wikipedia-11.448
auts-11.416
estern-10.938
д-10.702
Tokenipes
Token ID18636
Feature activation-6.45e-01

Pos logit contributions
nces+4.063
quad+4.023
arms+4.002
bane+3.760
poses+3.727
Neg logit contributions
wikipedia-3.829
orem-3.781
auts-3.737
д-3.698
ompl-3.504
Token to
Token ID284
Feature activation-4.56e-01

Pos logit contributions
nces+3.990
quad+3.951
arms+3.795
bane+3.651
perate+3.608
Neg logit contributions
wikipedia-3.944
auts-3.922
orem-3.844
д-3.757
estern-3.699
Token enhance
Token ID9494
Feature activation+1.49e-01

Pos logit contributions
nces+2.828
quad+2.770
arms+2.657
bane+2.558
perate+2.543
Neg logit contributions
wikipedia-2.810
auts-2.792
orem-2.729
д-2.692
estern-2.679
Token heat
Token ID4894
Feature activation+3.01e-01

Pos logit contributions
auts+0.981
wikipedia+0.964
orem+0.957
д+0.947
ompl+0.937
Neg logit contributions
nces-0.879
quad-0.851
arms-0.822
bane-0.782
ldom-0.780
Token fix
Token ID4259
Feature activation-8.93e-01

Pos logit contributions
nces+3.041
quad+2.996
arms+2.869
bane+2.800
ldom+2.787
Neg logit contributions
auts-2.965
wikipedia-2.921
д-2.877
orem-2.858
estern-2.828
Token the
Token ID262
Feature activation-3.54e-01

Pos logit contributions
nces+5.185
quad+5.046
arms+4.976
bane+4.827
ldom+4.749
Neg logit contributions
auts-5.476
wikipedia-5.390
д-5.240
orem-5.214
ompl-5.111
Token walk
Token ID2513
Feature activation+7.31e-01

Pos logit contributions
nces+2.417
quad+2.373
arms+2.311
bane+2.239
ldom+2.219
Neg logit contributions
auts-1.964
wikipedia-1.907
д-1.869
orem-1.869
ompl-1.833
Tokenways
Token ID1322
Feature activation-4.54e-01

Pos logit contributions
auts+2.974
wikipedia+2.868
д+2.828
orem+2.825
ompl+2.759
Neg logit contributions
nces-6.167
quad-5.895
arms-5.715
ldom-5.612
bane-5.515
Token without
Token ID1231
Feature activation+3.44e-01

Pos logit contributions
nces+2.689
quad+2.678
arms+2.542
bane+2.446
ldom+2.411
Neg logit contributions
auts-2.921
wikipedia-2.855
orem-2.834
д-2.809
ompl-2.787
Token diver
Token ID12312
Feature activation-2.06e+00

Pos logit contributions
auts+2.246
wikipedia+2.189
orem+2.182
д+2.167
ompl+2.147
Neg logit contributions
nces-2.055
quad-1.976
arms-1.902
ldom-1.823
bane-1.796
Tokenting
Token ID889
Feature activation-5.56e-02

Pos logit contributions
arms+2.483
nces+2.416
tails+2.384
gging+2.329
posing+2.075
Neg logit contributions
orem-20.343
auts-20.181
wikipedia-19.762
essee-19.749
estern-19.636
Token money
Token ID1637
Feature activation-7.01e-01

Pos logit contributions
nces+0.349
quad+0.337
arms+0.328
bane+0.314
ldom+0.312
Neg logit contributions
auts-0.345
wikipedia-0.342
orem-0.339
д-0.335
ompl-0.330
Token from
Token ID422
Feature activation-1.46e-01

Pos logit contributions
nces+4.220
quad+4.176
arms+3.982
perate+3.849
tails+3.807
Neg logit contributions
auts-4.250
orem-4.227
wikipedia-4.186
ompl-4.081
estern-4.077
Token what
Token ID644
Feature activation+1.62e-01

Pos logit contributions
nces+0.934
quad+0.905
arms+0.883
ldom+0.842
bane+0.842
Neg logit contributions
auts-0.884
wikipedia-0.868
orem-0.860
д-0.850
ompl-0.836
Token they
Token ID484
Feature activation+3.41e-01

Pos logit contributions
auts+0.941
wikipedia+0.922
orem+0.915
д+0.904
ompl+0.894
Neg logit contributions
nces-1.083
quad-1.051
arms-1.019
bane-0.975
ldom-0.975
Token at
Token ID379
Feature activation+6.05e-01

Pos logit contributions
nces+0.321
quad+0.308
arms+0.298
ldom+0.287
bane+0.285
Neg logit contributions
auts-0.326
wikipedia-0.320
orem-0.319
ompl-0.312
д-0.312
Token winning
Token ID5442
Feature activation+2.15e-02

Pos logit contributions
auts+3.603
wikipedia+3.529
orem+3.497
д+3.487
ompl+3.433
Neg logit contributions
nces-3.908
quad-3.789
arms-3.655
bane-3.494
ldom-3.491
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
auts+0.131
wikipedia+0.129
orem+0.127
д+0.126
ompl+0.125
Neg logit contributions
nces-0.138
quad-0.134
arms-0.130
ldom-0.124
bane-0.124
Token W
Token ID370
Feature activation+3.31e-02

Pos logit contributions
nces+1.011
quad+0.991
arms+0.965
ldom+0.916
bane+0.912
Neg logit contributions
auts-1.041
wikipedia-1.022
orem-1.008
д-1.003
ompl-0.986
TokenBA
Token ID4339
Feature activation-6.63e-01

Pos logit contributions
auts+0.243
wikipedia+0.240
orem+0.238
д+0.236
ompl+0.233
Neg logit contributions
nces-0.171
quad-0.165
arms-0.160
bane-0.150
ldom-0.150
Token super
Token ID2208
Feature activation-2.05e+00

Pos logit contributions
quad+3.914
nces+3.904
arms+3.814
ldom+3.628
bane+3.559
Neg logit contributions
auts-4.166
wikipedia-4.084
orem-4.030
д-3.951
ompl-3.883
Token-
Token ID12
Feature activation-1.15e+00

Pos logit contributions
quad+10.201
arms+9.995
IOR+9.148
ldom+9.134
posing+8.896
Neg logit contributions
auts-13.016
orem-12.807
wikipedia-12.562
estern-12.159
ocate-11.965
Tokenmiddle
Token ID27171
Feature activation-7.43e-01

Pos logit contributions
quad+5.660
arms+5.353
poses+4.950
nces+4.929
posing+4.921
Neg logit contributions
auts-8.454
orem-8.414
wikipedia-8.008
estern-7.977
д-7.960
Tokenweight
Token ID6551
Feature activation-4.69e-01

Pos logit contributions
quad+3.013
nces+2.991
arms+2.970
ldom+2.735
bane+2.634
Neg logit contributions
auts-6.109
wikipedia-6.027
orem-6.002
ompl-5.862
estern-5.760
Token title
Token ID3670
Feature activation-3.83e-01

Pos logit contributions
quad+3.194
nces+3.187
arms+3.129
ldom+2.997
bane+2.941
Neg logit contributions
auts-2.572
wikipedia-2.511
orem-2.459
д-2.413
ompl-2.390
Token,
Token ID11
Feature activation+9.85e-02

Pos logit contributions
nces+2.252
quad+2.192
arms+2.111
ldom+2.034
bane+1.994
Neg logit contributions
auts-2.517
wikipedia-2.469
orem-2.448
д-2.394
ompl-2.381
Token destroyed
Token ID6572
Feature activation-3.65e-01

Pos logit contributions
auts+1.744
wikipedia+1.719
orem+1.697
д+1.688
ompl+1.668
Neg logit contributions
nces-1.763
quad-1.705
arms-1.661
ldom-1.577
bane-1.572
Token by
Token ID416
Feature activation-1.50e-01

Pos logit contributions
nces+2.247
quad+2.190
arms+2.086
ldom+2.012
perate+1.990
Neg logit contributions
auts-2.306
orem-2.268
wikipedia-2.253
д-2.210
ompl-2.209
Token dumping
Token ID30231
Feature activation-1.23e-01

Pos logit contributions
nces+0.944
quad+0.922
arms+0.892
bane+0.850
ldom+0.846
Neg logit contributions
auts-0.925
wikipedia-0.908
orem-0.905
д-0.895
ompl-0.883
Token garbage
Token ID15413
Feature activation-1.03e+00

Pos logit contributions
nces+0.765
quad+0.743
arms+0.719
ldom+0.684
bane+0.683
Neg logit contributions
auts-0.768
wikipedia-0.756
orem-0.752
д-0.742
ompl-0.736
Token and
Token ID290
Feature activation-2.98e-01

Pos logit contributions
nces+5.656
quad+5.635
arms+5.438
bane+5.211
perate+5.132
Neg logit contributions
orem-6.541
wikipedia-6.454
д-6.416
auts-6.413
ompl-6.392
Token diver
Token ID12312
Feature activation-2.01e+00

Pos logit contributions
nces+1.747
quad+1.701
arms+1.653
bane+1.571
ldom+1.554
Neg logit contributions
auts-1.946
wikipedia-1.924
orem-1.917
д-1.885
ompl-1.875
Tokenting
Token ID889
Feature activation-3.41e-01

Pos logit contributions
nces+4.823
arms+4.659
tails+4.345
gging+4.239
quad+4.011
Neg logit contributions
orem-17.708
wikipedia-17.524
auts-17.088
ompl-17.058
essee-16.887
Token the
Token ID262
Feature activation-4.99e-02

Pos logit contributions
nces+2.067
quad+2.003
arms+1.949
bane+1.856
ldom+1.838
Neg logit contributions
auts-2.158
wikipedia-2.139
orem-2.134
д-2.093
ompl-2.085
Token creek
Token ID39459
Feature activation-4.39e-01

Pos logit contributions
nces+0.306
quad+0.296
arms+0.287
bane+0.274
ldom+0.273
Neg logit contributions
auts-0.317
wikipedia-0.312
orem-0.310
д-0.306
ompl-0.304
Token water
Token ID1660
Feature activation+8.89e-02

Pos logit contributions
nces+2.837
quad+2.770
arms+2.730
ldom+2.580
tails+2.568
Neg logit contributions
auts-2.566
orem-2.565
wikipedia-2.530
д-2.466
ompl-2.465
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
auts+0.480
wikipedia+0.469
orem+0.465
д+0.460
ompl+0.454
Neg logit contributions
nces-0.633
quad-0.616
arms-0.599
bane-0.574
ldom-0.574
Token
Token ID251
Feature activation+7.05e-01

Pos logit contributions
auts+1.751
wikipedia+1.723
orem+1.715
д+1.702
ompl+1.684
Neg logit contributions
nces-1.193
quad-1.147
arms-1.102
bane-1.037
ldom-1.036
Token by
Token ID416
Feature activation+6.20e-01

Pos logit contributions
auts+3.996
wikipedia+3.892
д+3.861
orem+3.841
ompl+3.803
Neg logit contributions
nces-4.730
quad-4.601
arms-4.492
ldom-4.269
bane-4.265
Token R
Token ID371
Feature activation-1.25e-01

Pos logit contributions
auts+3.899
wikipedia+3.836
orem+3.785
д+3.774
ompl+3.721
Neg logit contributions
nces-3.802
quad-3.680
arms-3.568
ldom-3.419
bane-3.390
Tokenyo
Token ID8226
Feature activation-4.97e-01

Pos logit contributions
nces+0.894
quad+0.862
arms+0.851
ldom+0.808
bane+0.807
Neg logit contributions
auts-0.661
wikipedia-0.659
orem-0.640
д-0.636
ompl-0.627
Token (
Token ID357
Feature activation+1.21e-01

Pos logit contributions
nces+2.931
quad+2.930
arms+2.766
bane+2.668
ldom+2.657
Neg logit contributions
auts-3.120
ompl-3.054
orem-3.047
wikipedia-3.045
д-3.004
TokenSuper
Token ID12442
Feature activation-2.01e+00

Pos logit contributions
auts+0.758
orem+0.741
wikipedia+0.740
д+0.727
ompl+0.723
Neg logit contributions
nces-0.760
quad-0.739
arms-0.714
bane-0.681
ldom-0.679
Tokencell
Token ID3846
Feature activation-3.17e-01

Pos logit contributions
quad+12.475
nces+12.356
arms+11.885
poses+11.529
posing+11.378
Neg logit contributions
orem-10.170
auts-9.322
wikipedia-9.320
ompl-9.086
estern-8.952
Token).
Token ID737
Feature activation+4.76e-01

Pos logit contributions
nces+2.049
quad+1.994
arms+1.931
ldom+1.840
bane+1.836
Neg logit contributions
auts-1.880
wikipedia-1.876
orem-1.870
д-1.807
ompl-1.799
Token Here
Token ID3423
Feature activation-3.08e-01

Pos logit contributions
auts+2.724
wikipedia+2.672
orem+2.638
д+2.633
ompl+2.582
Neg logit contributions
nces-3.225
quad-3.134
arms-3.040
ldom-2.914
bane-2.900
Token
Token ID447
Feature activation+2.06e-01

Pos logit contributions
nces+1.974
quad+1.892
arms+1.851
bane+1.764
ldom+1.756
Neg logit contributions
auts-1.861
wikipedia-1.827
orem-1.813
ompl-1.775
д-1.759
Token
Token ID247
Feature activation+1.62e-01

Pos logit contributions
auts+1.514
wikipedia+1.488
orem+1.479
д+1.465
ompl+1.453
Neg logit contributions
nces-1.074
quad-1.033
arms-0.993
bane-0.937
ldom-0.936
Token liquid
Token ID8122
Feature activation-1.88e-01

Pos logit contributions
auts+1.308
wikipedia+1.283
orem+1.274
д+1.261
ompl+1.247
Neg logit contributions
nces-1.261
quad-1.216
arms-1.179
bane-1.123
ldom-1.122
Token state
Token ID1181
Feature activation-1.48e-01

Pos logit contributions
nces+1.026
quad+1.016
arms+0.973
bane+0.928
perate+0.925
Neg logit contributions
auts-1.304
wikipedia-1.280
orem-1.275
д-1.263
ompl-1.258
Token and
Token ID290
Feature activation-4.51e-01

Pos logit contributions
nces+0.973
quad+0.951
arms+0.923
ldom+0.883
bane+0.881
Neg logit contributions
auts-0.866
wikipedia-0.850
orem-0.849
д-0.834
ompl-0.830
Token held
Token ID2714
Feature activation+7.24e-01

Pos logit contributions
nces+2.607
quad+2.568
arms+2.486
perate+2.359
ldom+2.354
Neg logit contributions
wikipedia-2.942
auts-2.929
orem-2.871
д-2.866
ompl-2.857
Token in
Token ID287
Feature activation+6.73e-01

Pos logit contributions
auts+4.170
wikipedia+4.008
orem+3.999
д+3.957
 admire+3.833
Neg logit contributions
nces-4.854
quad-4.566
arms-4.524
bane-4.356
ldom-4.321
Token super
Token ID2208
Feature activation-2.01e+00

Pos logit contributions
auts+4.074
wikipedia+3.948
orem+3.913
д+3.875
ompl+3.772
Neg logit contributions
nces-4.388
quad-4.169
arms-4.038
bane-3.922
ldom-3.865
Token-
Token ID12
Feature activation-1.13e+00

Pos logit contributions
quad+10.103
perate+9.400
arms+9.330
nces+9.114
IOR+8.954
Neg logit contributions
orem-12.533
д-12.128
wikipedia-12.002
estern-11.947
ompl-11.764
Tokenins
Token ID1040
Feature activation+4.95e-01

Pos logit contributions
quad+6.943
arms+6.636
nces+6.535
perate+6.268
tails+6.236
Neg logit contributions
orem-6.832
д-6.610
ompl-6.490
wikipedia-6.453
auts-6.446
Tokenulated
Token ID4817
Feature activation-2.02e-01

Pos logit contributions
auts+3.568
orem+3.530
wikipedia+3.506
ompl+3.451
д+3.437
Neg logit contributions
nces-2.605
quad-2.434
arms-2.375
bane-2.245
ldom-2.220
Token containers
Token ID16472
Feature activation-1.33e-01

Pos logit contributions
nces+1.077
quad+1.053
arms+1.012
perate+0.951
ldom+0.951
Neg logit contributions
auts-1.424
wikipedia-1.416
orem-1.400
ompl-1.388
д-1.387
Token and
Token ID290
Feature activation-2.74e-01

Pos logit contributions
nces+0.879
quad+0.864
arms+0.832
ldom+0.796
bane+0.796
Neg logit contributions
auts-0.781
wikipedia-0.769
orem-0.764
д-0.754
ompl-0.749
Token session
Token ID6246
Feature activation-8.19e-01

Pos logit contributions
nces+5.524
quad+5.441
arms+5.244
perate+4.958
tails+4.957
Neg logit contributions
auts-4.333
д-4.223
wikipedia-4.200
orem-4.173
ompl-4.150
Token after
Token ID706
Feature activation-1.50e-02

Pos logit contributions
nces+4.308
quad+4.223
arms+3.917
ldom+3.792
perate+3.735
Neg logit contributions
wikipedia-5.605
auts-5.597
orem-5.560
ompl-5.426
д-5.396
Token delivering
Token ID13630
Feature activation-5.53e-01

Pos logit contributions
nces+0.094
quad+0.091
arms+0.088
bane+0.084
ldom+0.084
Neg logit contributions
auts-0.094
wikipedia-0.092
orem-0.091
д-0.090
ompl-0.089
Token the
Token ID262
Feature activation-4.64e-01

Pos logit contributions
nces+3.343
quad+3.247
arms+3.136
poses+2.945
ldom+2.941
Neg logit contributions
auts-3.494
wikipedia-3.437
orem-3.396
д-3.391
ompl-3.325
Token 6
Token ID718
Feature activation-1.90e-01

Pos logit contributions
nces+3.010
quad+2.956
arms+2.856
bane+2.711
ldom+2.705
Neg logit contributions
auts-2.727
wikipedia-2.659
д-2.631
orem-2.608
ompl-2.560
Tokenth
Token ID400
Feature activation-1.99e+00

Pos logit contributions
nces+1.113
quad+1.093
arms+1.058
bane+0.996
ldom+0.990
Neg logit contributions
auts-1.247
wikipedia-1.231
orem-1.212
д-1.197
ompl-1.192
Token Dil
Token ID29328
Feature activation-6.25e-02

Pos logit contributions
quad+11.260
nces+10.779
arms+9.970
bane+9.850
ldom+9.734
Neg logit contributions
auts-10.878
wikipedia-10.671
д-10.613
orem-10.507
ompl-10.438
Tokenip
Token ID541
Feature activation-2.63e-01

Pos logit contributions
nces+0.408
quad+0.398
arms+0.385
bane+0.371
ldom+0.369
Neg logit contributions
auts-0.370
wikipedia-0.364
д-0.362
orem-0.360
ompl-0.354
Token Sard
Token ID46997
Feature activation-2.18e-01

Pos logit contributions
nces+1.552
quad+1.503
arms+1.440
ldom+1.376
bane+1.369
Neg logit contributions
auts-1.715
wikipedia-1.700
д-1.694
ompl-1.666
orem-1.658
Tokenes
Token ID274
Feature activation-7.20e-02

Pos logit contributions
nces+1.942
quad+1.879
arms+1.857
bane+1.774
ldom+1.773
Neg logit contributions
wikipedia-0.788
д-0.779
auts-0.774
orem-0.757
ompl-0.738
Tokenai
Token ID1872
Feature activation-1.54e-01

Pos logit contributions
nces+0.355
quad+0.342
arms+0.329
bane+0.310
ldom+0.307
Neg logit contributions
auts-0.546
wikipedia-0.537
orem-0.534
д-0.531
ompl-0.527
Token quotes
Token ID13386
Feature activation+7.17e-01

Pos logit contributions
nces+3.063
quad+2.982
arms+2.870
bane+2.764
poses+2.729
Neg logit contributions
auts-3.168
orem-3.112
wikipedia-3.097
д-3.044
ompl-3.029
Token Wagner
Token ID26451
Feature activation-1.58e-01

Pos logit contributions
auts+4.207
wikipedia+4.158
orem+4.051
д+4.039
ompl+3.970
Neg logit contributions
nces-4.645
quad-4.576
arms-4.395
ldom-4.234
tails-4.172
Token:
Token ID25
Feature activation-2.18e-02

Pos logit contributions
nces+1.004
quad+0.969
arms+0.932
bane+0.906
ldom+0.899
Neg logit contributions
auts-0.972
orem-0.954
wikipedia-0.953
д-0.933
ompl-0.921
Token "
Token ID366
Feature activation+4.61e-01

Pos logit contributions
nces+0.129
quad+0.124
arms+0.120
ldom+0.115
bane+0.114
Neg logit contributions
auts-0.144
wikipedia-0.141
orem-0.141
д-0.138
ompl-0.137
TokenAfter
Token ID3260
Feature activation+6.80e-01

Pos logit contributions
auts+2.703
wikipedia+2.664
orem+2.615
д+2.613
ompl+2.571
Neg logit contributions
nces-3.063
quad-2.934
arms-2.832
ldom-2.747
bane-2.721
Token spe
Token ID693
Feature activation-1.98e+00

Pos logit contributions
auts+4.060
wikipedia+4.013
д+4.001
orem+3.974
ompl+3.912
Neg logit contributions
nces-4.334
quad-4.192
arms-4.041
ldom-3.865
bane-3.838
Tokenaring
Token ID1723
Feature activation-2.07e-01

Pos logit contributions
arms+8.571
quad+7.925
gging+7.407
ldom+7.387
nces+7.385
Neg logit contributions
auts-13.295
wikipedia-13.163
 Participant-13.030
-12.884
orem-12.854
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
nces+1.297
quad+1.255
arms+1.222
bane+1.173
ldom+1.156
Neg logit contributions
auts-1.288
wikipedia-1.275
orem-1.268
д-1.240
ompl-1.236
Token poor
Token ID3595
Feature activation-2.75e-01

Pos logit contributions
auts+0.940
wikipedia+0.922
orem+0.916
д+0.907
ompl+0.898
Neg logit contributions
nces-0.840
quad-0.812
arms-0.785
bane-0.745
ldom-0.745
Token br
Token ID865
Feature activation-3.24e-01

Pos logit contributions
nces+1.641
quad+1.597
arms+1.539
bane+1.481
ldom+1.458
Neg logit contributions
auts-1.777
wikipedia-1.766
orem-1.739
д-1.707
ompl-1.705
Tokenutes
Token ID1769
Feature activation-1.13e-01

Pos logit contributions
nces+2.031
quad+1.988
arms+1.971
poses+1.831
ldom+1.829
Neg logit contributions
auts-1.946
wikipedia-1.945
д-1.912
orem-1.892
ompl-1.848
Token asked
Token ID1965
Feature activation+1.60e-01

Pos logit contributions
nces+0.729
quad+0.714
arms+0.689
bane+0.658
ldom+0.656
Neg logit contributions
auts-0.655
orem-0.638
wikipedia-0.635
д-0.631
ompl-0.628
Token MIT
Token ID17168
Feature activation-3.16e-01

Pos logit contributions
auts+0.974
wikipedia+0.953
orem+0.946
д+0.939
ompl+0.928
Neg logit contributions
nces-1.027
quad-0.994
arms-0.963
bane-0.919
ldom-0.918
Token
Token ID447
Feature activation-5.54e-01

Pos logit contributions
nces+2.579
quad+2.488
arms+2.429
bane+2.356
poses+2.335
Neg logit contributions
auts-1.380
wikipedia-1.332
orem-1.311
д-1.298
ompl-1.275
Token
Token ID247
Feature activation+5.68e-02

Pos logit contributions
nces+2.243
quad+2.154
arms+2.054
bane+1.912
ldom+1.872
Neg logit contributions
auts-4.642
wikipedia-4.595
orem-4.561
д-4.491
ompl-4.480
Tokens
Token ID82
Feature activation-4.74e-02

Pos logit contributions
auts+0.282
wikipedia+0.275
orem+0.271
д+0.266
ompl+0.265
Neg logit contributions
nces-0.431
quad-0.419
arms-0.408
bane-0.392
ldom-0.389
Token Dar
Token ID7491
Feature activation-1.98e+00

Pos logit contributions
nces+0.288
quad+0.278
arms+0.269
bane+0.257
ldom+0.255
Neg logit contributions
auts-0.306
wikipedia-0.299
orem-0.296
д-0.296
ompl-0.293
Tokenon
Token ID261
Feature activation-3.43e-01

Pos logit contributions
nces+11.143
arms+10.913
quad+10.755
ldom+10.244
bane+10.210
Neg logit contributions
д-10.175
auts-9.965
estern-9.532
wikipedia-9.518
-9.498
Token Ace
Token ID17102
Feature activation-7.78e-01

Pos logit contributions
nces+2.005
quad+1.965
arms+1.933
tails+1.825
bane+1.823
Neg logit contributions
auts-2.188
ompl-2.168
wikipedia-2.150
д-2.148
orem-2.122
Tokenm
Token ID76
Feature activation-6.46e-01

Pos logit contributions
nces+3.871
quad+3.644
arms+3.628
bane+3.476
ldom+3.412
Neg logit contributions
auts-5.690
д-5.630
wikipedia-5.568
ompl-5.497
orem-5.424
Tokenoglu
Token ID49006
Feature activation-6.20e-01

Pos logit contributions
nces+3.570
quad+3.497
arms+3.456
poses+3.245
perate+3.236
Neg logit contributions
auts-4.249
wikipedia-4.218
ompl-4.181
д-4.164
orem-4.063
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
nces+3.835
quad+3.794
arms+3.588
bane+3.511
ldom+3.447
Neg logit contributions
auts-3.737
wikipedia-3.674
orem-3.627
ompl-3.605
д-3.558
Token some
Token ID617
Feature activation+3.93e-01

Pos logit contributions
nces+1.114
quad+1.074
arms+1.040
bane+0.999
ldom+0.997
Neg logit contributions
auts-0.990
orem-0.971
wikipedia-0.966
д-0.953
ompl-0.946
Token sort
Token ID3297
Feature activation+1.93e-01

Pos logit contributions
auts+2.186
wikipedia+2.148
orem+2.111
д+2.096
ompl+2.065
Neg logit contributions
nces-2.715
quad-2.649
arms-2.576
ldom-2.459
bane-2.450
Token of
Token ID286
Feature activation+3.14e-03

Pos logit contributions
auts+1.188
wikipedia+1.181
д+1.146
orem+1.139
ompl+1.121
Neg logit contributions
nces-1.230
quad-1.189
arms-1.149
ldom-1.106
bane-1.092
Token discovery
Token ID9412
Feature activation+9.96e-02

Pos logit contributions
auts+0.017
wikipedia+0.017
orem+0.017
д+0.017
ompl+0.016
Neg logit contributions
nces-0.022
quad-0.021
arms-0.021
bane-0.020
ldom-0.020
Token about
Token ID546
Feature activation-2.35e-01

Pos logit contributions
auts+0.592
wikipedia+0.580
orem+0.576
д+0.569
ompl+0.563
Neg logit contributions
nces-0.656
quad-0.636
arms-0.617
ldom-0.590
bane-0.590
Token really
Token ID1107
Feature activation-1.98e+00

Pos logit contributions
nces+1.379
quad+1.340
arms+1.307
bane+1.243
ldom+1.243
Neg logit contributions
auts-1.542
wikipedia-1.518
orem-1.511
д-1.495
ompl-1.488
Token old
Token ID1468
Feature activation-7.02e-01

Pos logit contributions
quad+10.168
nces+9.938
arms+9.623
bane+9.522
poses+9.245
Neg logit contributions
orem-11.773
auts-11.606
ompl-11.380
wikipedia-11.362
estern-10.976
Token wards
Token ID32710
Feature activation-9.05e-01

Pos logit contributions
nces+3.493
quad+3.336
arms+3.295
bane+3.131
ldom+3.037
Neg logit contributions
auts-5.086
wikipedia-4.969
ompl-4.960
orem-4.954
д-4.948
Token covering
Token ID9505
Feature activation+5.78e-02

Pos logit contributions
nces+5.311
quad+5.255
arms+5.027
bane+4.923
ldom+4.810
Neg logit contributions
orem-5.660
auts-5.645
д-5.459
ompl-5.459
wikipedia-5.456
Token the
Token ID262
Feature activation-2.72e-01

Pos logit contributions
auts+0.354
wikipedia+0.347
orem+0.345
д+0.341
ompl+0.338
Neg logit contributions
nces-0.370
quad-0.358
arms-0.348
ldom-0.332
bane-0.332
Token whole
Token ID2187
Feature activation-2.40e-01

Pos logit contributions
nces+1.677
quad+1.629
arms+1.596
bane+1.524
ldom+1.512
Neg logit contributions
auts-1.698
wikipedia-1.668
orem-1.655
д-1.642
ompl-1.635
Token
Token ID198
Feature activation-2.73e-01

Pos logit contributions
auts+0.201
wikipedia+0.198
orem+0.194
д+0.194
ompl+0.189
Neg logit contributions
nces-0.245
quad-0.234
arms-0.227
ldom-0.222
bane-0.217
TokenSubscribe
Token ID27125
Feature activation-2.66e-01

Pos logit contributions
nces+1.643
quad+1.629
arms+1.578
bane+1.485
poses+1.483
Neg logit contributions
auts-1.722
wikipedia-1.689
orem-1.685
ompl-1.668
д-1.653
Token via
Token ID2884
Feature activation-6.38e-01

Pos logit contributions
nces+1.815
quad+1.762
arms+1.729
ldom+1.640
bane+1.640
Neg logit contributions
auts-1.485
wikipedia-1.472
orem-1.435
ompl-1.404
д-1.403
Token RSS
Token ID25012
Feature activation-7.28e-01

Pos logit contributions
nces+3.345
quad+3.300
arms+3.139
perate+2.995
ldom+2.913
Neg logit contributions
orem-4.408
auts-4.408
wikipedia-4.321
ompl-4.229
д-4.199
Token or
Token ID393
Feature activation-6.12e-01

Pos logit contributions
nces+3.975
quad+3.970
arms+3.834
bane+3.712
ldom+3.626
Neg logit contributions
auts-4.798
wikipedia-4.776
orem-4.683
ompl-4.559
д-4.545
Token daily
Token ID4445
Feature activation-1.98e+00

Pos logit contributions
quad+3.625
nces+3.611
arms+3.403
perate+3.296
bane+3.258
Neg logit contributions
wikipedia-3.827
auts-3.809
orem-3.785
estern-3.676
д-3.651
Token email
Token ID3053
Feature activation-8.22e-01

Pos logit contributions
quad+10.610
arms+10.349
nces+9.807
perate+9.404
tails+9.183
Neg logit contributions
orem-11.455
wikipedia-11.448
auts-11.177
essee-10.992
estern-10.983
Token Contact
Token ID14039
Feature activation-8.20e-01

Pos logit contributions
nces+4.788
quad+4.770
arms+4.700
bane+4.374
perate+4.374
Neg logit contributions
wikipedia-5.187
orem-5.111
auts-5.077
ompl-4.860
д-4.815
Token the
Token ID262
Feature activation-5.38e-01

Pos logit contributions
nces+4.858
quad+4.744
arms+4.714
bane+4.552
tails+4.457
Neg logit contributions
auts-4.980
orem-4.877
wikipedia-4.872
д-4.705
ompl-4.676
Token editor
Token ID5464
Feature activation-2.41e-01

Pos logit contributions
nces+4.257
quad+4.240
arms+4.161
bane+4.047
tails+3.996
Neg logit contributions
auts-2.325
orem-2.245
wikipedia-2.242
д-2.201
ompl-2.126
Token about
Token ID546
Feature activation-4.99e-01

Pos logit contributions
nces+1.646
quad+1.596
arms+1.550
bane+1.490
ldom+1.482
Neg logit contributions
auts-1.348
wikipedia-1.344
orem-1.320
д-1.301
ompl-1.295
Token chosen
Token ID7147
Feature activation+2.50e-03

Pos logit contributions
nces+1.357
quad+1.317
arms+1.269
ldom+1.211
bane+1.211
Neg logit contributions
auts-1.388
orem-1.372
wikipedia-1.368
д-1.338
ompl-1.326
Token based
Token ID1912
Feature activation-6.64e-01

Pos logit contributions
auts+0.017
wikipedia+0.017
orem+0.017
д+0.017
ompl+0.017
Neg logit contributions
nces-0.014
quad-0.013
arms-0.013
bane-0.012
ldom-0.012
Token on
Token ID319
Feature activation-9.80e-02

Pos logit contributions
nces+3.820
quad+3.631
arms+3.543
bane+3.394
poses+3.380
Neg logit contributions
auts-4.275
wikipedia-4.226
ompl-4.123
д-4.106
orem-4.061
Token
Token ID564
Feature activation+1.47e-01

Pos logit contributions
nces+0.638
quad+0.611
arms+0.596
ldom+0.572
bane+0.564
Neg logit contributions
auts-0.589
wikipedia-0.581
orem-0.573
д-0.568
ompl-0.559
Token
Token ID250
Feature activation+1.10e-01

Pos logit contributions
auts+1.231
wikipedia+1.210
orem+1.204
д+1.191
ompl+1.186
Neg logit contributions
nces-0.617
quad-0.590
arms-0.560
bane-0.520
ldom-0.519
Tokenstat
Token ID14269
Feature activation+1.39e+00

Pos logit contributions
auts+0.666
orem+0.652
wikipedia+0.652
д+0.642
ompl+0.633
Neg logit contributions
nces-0.719
quad-0.697
arms-0.676
ldom-0.645
bane-0.640
Tokenistical
Token ID19929
Feature activation+7.06e-01

Pos logit contributions
auts+6.401
wikipedia+6.115
д+6.043
orem+6.015
ompl+5.886
Neg logit contributions
nces-10.080
quad-9.988
arms-9.565
perate-9.293
tails-9.288
Token data
Token ID1366
Feature activation+4.11e-01

Pos logit contributions
auts+4.237
orem+4.093
д+4.077
wikipedia+4.075
ompl+4.024
Neg logit contributions
nces-4.461
quad-4.359
arms-4.197
bane-4.062
tails-4.008
Token,
Token ID11
Feature activation+3.47e-01

Pos logit contributions
auts+2.414
wikipedia+2.347
orem+2.339
д+2.323
ompl+2.286
Neg logit contributions
nces-2.719
quad-2.629
arms-2.557
bane-2.449
ldom-2.442
Token prior
Token ID3161
Feature activation+2.01e-01

Pos logit contributions
auts+2.086
wikipedia+2.045
orem+2.028
д+2.009
ompl+1.985
Neg logit contributions
nces-2.247
quad-2.185
arms-2.114
bane-2.022
ldom-2.018
Token complaints
Token ID9687
Feature activation-2.10e-01

Pos logit contributions
auts+1.036
wikipedia+1.009
orem+1.001
д+0.983
ompl+0.971
Neg logit contributions
nces-1.486
quad-1.441
arms-1.406
ldom-1.350
bane-1.346
Token a
Token ID257
Feature activation+7.15e-01

Pos logit contributions
auts+2.971
wikipedia+2.884
д+2.843
orem+2.826
ompl+2.793
Neg logit contributions
nces-3.553
quad-3.433
arms-3.351
ldom-3.221
bane-3.185
Token big
Token ID1263
Feature activation+5.00e-01

Pos logit contributions
auts+3.996
wikipedia+3.867
orem+3.854
д+3.828
ompl+3.821
Neg logit contributions
nces-4.825
quad-4.639
arms-4.567
ldom-4.351
tails-4.305
Token part
Token ID636
Feature activation+1.01e+00

Pos logit contributions
auts+3.417
orem+3.335
wikipedia+3.324
д+3.301
ompl+3.289
Neg logit contributions
nces-2.828
quad-2.721
arms-2.611
ldom-2.508
bane-2.452
Token of
Token ID286
Feature activation+8.15e-01

Pos logit contributions
auts+5.893
д+5.741
wikipedia+5.738
orem+5.663
ompl+5.607
Neg logit contributions
nces-6.481
quad-6.225
arms-6.163
ldom-5.854
tails-5.785
Token their
Token ID511
Feature activation+7.92e-01

Pos logit contributions
auts+4.517
wikipedia+4.428
д+4.363
ompl+4.316
orem+4.274
Neg logit contributions
nces-5.531
quad-5.296
arms-5.144
ldom-4.985
perate-4.975
Token hockey
Token ID12217
Feature activation+1.27e+00

Pos logit contributions
auts+3.606
wikipedia+3.556
ompl+3.472
orem+3.467
д+3.446
Neg logit contributions
nces-6.204
quad-5.946
arms-5.851
ldom-5.671
poses-5.622
Token team
Token ID1074
Feature activation+2.37e-01

Pos logit contributions
auts+6.680
wikipedia+6.583
ompl+6.471
д+6.413
orem+6.327
Neg logit contributions
nces-8.797
quad-7.995
arms-7.982
ldom-7.789
poses-7.770
Token.
Token ID13
Feature activation+4.18e-01

Pos logit contributions
auts+1.414
wikipedia+1.386
orem+1.376
д+1.360
ompl+1.345
Neg logit contributions
nces-1.552
quad-1.506
arms-1.460
bane-1.395
ldom-1.394
Token It
Token ID632
Feature activation+6.69e-01

Pos logit contributions
auts+2.284
wikipedia+2.237
д+2.193
orem+2.183
ompl+2.150
Neg logit contributions
nces-2.957
quad-2.862
arms-2.765
ldom-2.695
perate-2.655
Token's
Token ID338
Feature activation+6.76e-01

Pos logit contributions
auts+3.536
wikipedia+3.426
д+3.357
ompl+3.338
 admire+3.319
Neg logit contributions
nces-4.661
quad-4.539
arms-4.428
ldom-4.281
bane-4.220
Token been
Token ID587
Feature activation+8.49e-01

Pos logit contributions
auts+3.821
wikipedia+3.725
д+3.656
orem+3.581
ompl+3.571
Neg logit contributions
nces-4.559
quad-4.416
arms-4.273
ldom-4.102
perate-4.090
Token to
Token ID284
Feature activation+4.30e-01

Pos logit contributions
auts+4.882
orem+4.646
д+4.597
wikipedia+4.579
ompl+4.548
Neg logit contributions
nces-7.959
quad-7.654
arms-7.471
bane-7.259
tails-7.226
Token all
Token ID477
Feature activation+3.43e-01

Pos logit contributions
auts+2.565
orem+2.507
wikipedia+2.488
д+2.460
ompl+2.440
Neg logit contributions
nces-2.809
quad-2.706
arms-2.609
bane-2.500
ldom-2.493
Token Priv
Token ID9243
Feature activation+1.29e+00

Pos logit contributions
auts+2.063
orem+2.023
wikipedia+2.007
д+1.987
ompl+1.972
Neg logit contributions
nces-2.226
quad-2.144
arms-2.067
ldom-1.988
bane-1.980
Tokenile
Token ID576
Feature activation-6.08e-02

Pos logit contributions
auts+6.804
ompl+6.590
orem+6.497
д+6.276
essee+6.248
Neg logit contributions
nces-8.639
quad-8.280
bane-8.011
arms-7.880
gging-7.860
Tokenges
Token ID3212
Feature activation+9.60e-01

Pos logit contributions
nces+0.371
quad+0.358
arms+0.349
ldom+0.331
bane+0.330
Neg logit contributions
auts-0.391
wikipedia-0.385
orem-0.382
д-0.376
ompl-0.373
Token and
Token ID290
Feature activation+1.79e+00

Pos logit contributions
auts+5.197
orem+5.091
wikipedia+5.086
д+5.014
ompl+4.970
Neg logit contributions
nces-6.520
quad-6.217
arms-6.143
tails-5.854
poses-5.815
Token Immun
Token ID25445
Feature activation+1.40e+00

Pos logit contributions
ompl+6.950
auts+6.889
д+6.698
 admire+6.590
orem+6.431
Neg logit contributions
nces-13.547
quad-12.513
bane-12.499
tails-12.057
gging-12.049
Tokenities
Token ID871
Feature activation+1.04e+00

Pos logit contributions
orem+6.034
auts+5.987
ompl+5.672
iste+5.666
album+5.302
Neg logit contributions
nces-10.495
bane-10.101
 AGA-9.784
quad-9.782
 anew-9.656
Token of
Token ID286
Feature activation+5.29e-01

Pos logit contributions
auts+5.546
orem+5.473
wikipedia+5.445
д+5.443
ompl+5.362
Neg logit contributions
nces-7.087
quad-6.718
arms-6.614
tails-6.364
bane-6.275
Token Citizens
Token ID18029
Feature activation-9.70e-02

Pos logit contributions
auts+2.985
orem+2.895
wikipedia+2.868
д+2.844
ompl+2.827
Neg logit contributions
nces-3.653
quad-3.523
arms-3.403
bane-3.284
ldom-3.261
Token in
Token ID287
Feature activation-2.55e-01

Pos logit contributions
nces+0.572
quad+0.556
arms+0.534
bane+0.515
ldom+0.510
Neg logit contributions
auts-0.641
wikipedia-0.632
orem-0.621
д-0.618
ompl-0.612
Token breaks
Token ID9457
Feature activation+2.32e-01

Pos logit contributions
nces+1.296
quad+1.254
arms+1.219
bane+1.158
ldom+1.152
Neg logit contributions
auts-1.306
wikipedia-1.284
orem-1.280
д-1.268
ompl-1.254
Token off
Token ID572
Feature activation-1.94e-02

Pos logit contributions
auts+1.396
wikipedia+1.368
orem+1.356
д+1.343
ompl+1.327
Neg logit contributions
nces-1.513
quad-1.466
arms-1.420
ldom-1.357
bane-1.357
Token from
Token ID422
Feature activation-5.90e-02

Pos logit contributions
nces+0.123
quad+0.119
arms+0.116
ldom+0.110
bane+0.110
Neg logit contributions
auts-0.120
orem-0.118
wikipedia-0.118
д-0.116
ompl-0.115
Token the
Token ID262
Feature activation+1.84e-02

Pos logit contributions
nces+0.384
quad+0.373
arms+0.364
ldom+0.347
bane+0.346
Neg logit contributions
auts-0.349
orem-0.343
wikipedia-0.342
д-0.338
ompl-0.337
Token glacier
Token ID44539
Feature activation+1.20e-01

Pos logit contributions
auts+0.113
wikipedia+0.111
orem+0.110
д+0.109
ompl+0.108
Neg logit contributions
nces-0.116
quad-0.113
arms-0.110
bane-0.105
ldom-0.104
Token front
Token ID2166
Feature activation+1.23e+00

Pos logit contributions
auts+0.739
wikipedia+0.725
orem+0.720
д+0.712
ompl+0.705
Neg logit contributions
nces-0.765
quad-0.742
arms-0.719
bane-0.686
ldom-0.686
Token,
Token ID11
Feature activation+2.11e-01

Pos logit contributions
auts+6.556
wikipedia+6.356
orem+6.250
д+6.124
ompl+6.089
Neg logit contributions
nces-8.501
quad-7.912
arms-7.579
bane-7.457
ldom-7.448
Token is
Token ID318
Feature activation+2.70e-01

Pos logit contributions
auts+1.238
wikipedia+1.211
orem+1.200
д+1.187
ompl+1.174
Neg logit contributions
nces-1.402
quad-1.359
arms-1.317
ldom-1.260
bane-1.259
Token tall
Token ID7331
Feature activation+7.17e-01

Pos logit contributions
auts+1.617
wikipedia+1.585
orem+1.572
д+1.556
ompl+1.538
Neg logit contributions
nces-1.761
quad-1.706
arms-1.655
bane-1.580
ldom-1.580
Token and
Token ID290
Feature activation+2.94e-01

Pos logit contributions
auts+4.347
wikipedia+4.212
orem+4.184
д+4.168
ompl+4.112
Neg logit contributions
nces-4.615
quad-4.419
arms-4.220
bane-4.080
ldom-4.077
Token relatively
Token ID5365
Feature activation+2.01e-01

Pos logit contributions
auts+1.898
wikipedia+1.866
orem+1.848
д+1.834
ompl+1.812
Neg logit contributions
nces-1.788
quad-1.724
arms-1.666
ldom-1.588
bane-1.585
Token have
Token ID423
Feature activation+1.24e-01

Pos logit contributions
nces+3.280
quad+3.182
arms+3.112
bane+2.991
ldom+2.990
Neg logit contributions
auts-2.671
wikipedia-2.598
orem-2.593
д-2.520
ompl-2.507
Token to
Token ID284
Feature activation-2.03e-01

Pos logit contributions
auts+0.596
wikipedia+0.586
orem+0.579
д+0.567
ompl+0.566
Neg logit contributions
nces-0.950
quad-0.925
arms-0.903
ldom-0.870
bane-0.864
Token be
Token ID307
Feature activation-9.16e-03

Pos logit contributions
nces+1.370
quad+1.326
arms+1.295
bane+1.242
ldom+1.240
Neg logit contributions
auts-1.161
wikipedia-1.140
orem-1.121
д-1.114
ompl-1.096
Token a
Token ID257
Feature activation+2.86e-01

Pos logit contributions
nces+0.061
quad+0.059
arms+0.057
bane+0.055
ldom+0.055
Neg logit contributions
auts-0.054
wikipedia-0.052
orem-0.052
д-0.051
ompl-0.051
Token practicing
Token ID18207
Feature activation+1.05e-01

Pos logit contributions
auts+1.651
wikipedia+1.616
orem+1.605
д+1.588
ompl+1.569
Neg logit contributions
nces-1.934
quad-1.874
arms-1.821
ldom-1.741
bane-1.740
Token Lac
Token ID23115
Feature activation+1.20e+00

Pos logit contributions
auts+0.555
wikipedia+0.543
orem+0.539
д+0.529
ompl+0.525
Neg logit contributions
nces-0.757
quad-0.741
arms-0.722
bane-0.692
perate-0.688
Tokenanian
Token ID38336
Feature activation+6.15e-01

Pos logit contributions
auts+3.223
ocate+3.023
wikipedia+2.993
ompl+2.946
anova+2.884
Neg logit contributions
nces-11.725
quad-11.025
arms-10.714
tails-10.630
ldom-10.598
Token psych
Token ID3795
Feature activation+9.83e-01

Pos logit contributions
auts+3.234
wikipedia+3.152
orem+3.127
д+3.119
ompl+3.066
Neg logit contributions
nces-4.468
quad-4.321
arms-4.196
ldom-4.032
bane-4.008
Tokenoan
Token ID24611
Feature activation+3.23e-01

Pos logit contributions
auts+3.557
orem+3.368
д+3.341
ompl+3.326
wikipedia+3.302
Neg logit contributions
nces-8.726
quad-8.310
arms-8.174
ldom-7.973
tails-7.972
Tokenalyst
Token ID21470
Feature activation+8.14e-01

Pos logit contributions
auts+0.999
wikipedia+0.964
orem+0.951
д+0.930
ompl+0.904
Neg logit contributions
nces-3.038
quad-2.988
arms-2.923
ldom-2.832
bane-2.831
Token to
Token ID284
Feature activation+3.02e-01

Pos logit contributions
auts+4.082
д+3.927
wikipedia+3.924
orem+3.916
ompl+3.832
Neg logit contributions
nces-6.018
quad-5.819
arms-5.658
ldom-5.441
bane-5.434
Token sure
Token ID1654
Feature activation+3.93e-01

Pos logit contributions
nces+2.511
quad+2.413
arms+2.331
ldom+2.221
bane+2.186
Neg logit contributions
auts-3.889
wikipedia-3.858
orem-3.834
д-3.787
ompl-3.733
Token,"
Token ID553
Feature activation+8.91e-01

Pos logit contributions
auts+1.905
wikipedia+1.858
orem+1.837
д+1.818
ompl+1.791
Neg logit contributions
nces-3.014
quad-2.935
arms-2.861
bane-2.751
ldom-2.750
Token said
Token ID531
Feature activation+4.83e-01

Pos logit contributions
auts+4.962
wikipedia+4.778
orem+4.731
д+4.679
ompl+4.661
Neg logit contributions
nces-6.151
quad-5.859
arms-5.714
ldom-5.526
bane-5.453
Token On
Token ID1550
Feature activation+4.63e-01

Pos logit contributions
auts+2.658
wikipedia+2.592
orem+2.574
д+2.541
ompl+2.516
Neg logit contributions
nces-3.394
quad-3.291
arms-3.199
ldom-3.068
bane-3.064
Tokenstad
Token ID24107
Feature activation-1.24e-01

Pos logit contributions
auts+2.251
wikipedia+2.193
orem+2.067
ompl+2.049
д+2.032
Neg logit contributions
nces-3.613
quad-3.370
arms-3.364
ldom-3.248
tails-3.197
Token,
Token ID11
Feature activation-7.94e-02

Pos logit contributions
nces+0.758
quad+0.748
arms+0.712
ldom+0.687
bane+0.685
Neg logit contributions
auts-0.788
wikipedia-0.777
orem-0.770
д-0.756
ompl-0.753
Token now
Token ID783
Feature activation+2.72e-01

Pos logit contributions
nces+0.526
quad+0.514
arms+0.498
ldom+0.475
bane+0.475
Neg logit contributions
auts-0.465
wikipedia-0.455
orem-0.453
д-0.448
ompl-0.443
Token 47
Token ID6298
Feature activation+7.06e-02

Pos logit contributions
auts+1.572
wikipedia+1.528
orem+1.513
д+1.495
ompl+1.486
Neg logit contributions
nces-1.846
quad-1.771
arms-1.723
bane-1.655
ldom-1.653
Token and
Token ID290
Feature activation+3.65e-02

Pos logit contributions
auts+0.412
wikipedia+0.407
orem+0.403
д+0.397
ompl+0.393
Neg logit contributions
nces-0.470
quad-0.457
arms-0.444
ldom-0.424
bane-0.423
Token an
Token ID281
Feature activation+9.01e-01

Pos logit contributions
auts+0.232
wikipedia+0.228
orem+0.226
д+0.224
ompl+0.222
Neg logit contributions
nces-0.224
quad-0.218
arms-0.211
bane-0.201
ldom-0.201
Token assistant
Token ID8796
Feature activation-5.92e-01

Pos logit contributions
auts+4.911
orem+4.820
wikipedia+4.687
ompl+4.670
 admire+4.626
Neg logit contributions
nces-6.304
quad-6.074
arms-5.768
ldom-5.735
tails-5.671
Token over
Token ID625
Feature activation+3.43e-01

Pos logit contributions
nces+0.792
quad+0.774
arms+0.746
bane+0.713
perate+0.702
Neg logit contributions
auts-0.827
wikipedia-0.806
orem-0.801
ompl-0.790
д-0.785
Token it
Token ID340
Feature activation+2.08e-01

Pos logit contributions
auts+2.066
wikipedia+2.024
orem+2.009
д+1.996
ompl+1.961
Neg logit contributions
nces-2.217
quad-2.140
arms-2.068
ldom-1.983
bane-1.980
Token's
Token ID338
Feature activation+2.28e-01

Pos logit contributions
auts+1.209
wikipedia+1.183
orem+1.173
д+1.163
ompl+1.148
Neg logit contributions
nces-1.394
quad-1.352
arms-1.312
ldom-1.255
bane-1.254
Token body
Token ID1767
Feature activation-2.45e-02

Pos logit contributions
auts+1.515
wikipedia+1.487
orem+1.477
д+1.464
ompl+1.449
Neg logit contributions
nces-1.337
quad-1.291
arms-1.245
ldom-1.185
bane-1.184
Token as
Token ID355
Feature activation-5.85e-01

Pos logit contributions
nces+0.160
quad+0.156
arms+0.152
bane+0.145
ldom+0.145
Neg logit contributions
auts-0.147
wikipedia-0.144
orem-0.143
д-0.140
ompl-0.139
Token armor
Token ID8328
Feature activation+3.54e-01

Pos logit contributions
quad+3.214
nces+3.190
arms+3.120
bane+2.902
tails+2.861
Neg logit contributions
auts-3.967
wikipedia-3.901
ompl-3.836
orem-3.832
д-3.826
Token.
Token ID13
Feature activation-2.39e-01

Pos logit contributions
auts+2.028
wikipedia+1.991
orem+1.967
д+1.946
ompl+1.925
Neg logit contributions
nces-2.396
quad-2.282
arms-2.220
ldom-2.140
poses-2.123
Token It
Token ID632
Feature activation-1.62e-01

Pos logit contributions
nces+1.554
quad+1.526
arms+1.488
bane+1.421
ldom+1.392
Neg logit contributions
auts-1.419
wikipedia-1.389
orem-1.385
д-1.367
ompl-1.363
Token's
Token ID338
Feature activation+1.44e-02

Pos logit contributions
nces+0.975
quad+0.949
arms+0.917
bane+0.874
ldom+0.870
Neg logit contributions
auts-1.051
wikipedia-1.030
orem-1.025
д-1.013
ompl-1.005
Token shoulder
Token ID8163
Feature activation-5.45e-02

Pos logit contributions
auts+0.096
wikipedia+0.094
orem+0.093
д+0.093
ompl+0.092
Neg logit contributions
nces-0.084
quad-0.082
arms-0.079
bane-0.075
ldom-0.075
Token blades
Token ID20784
Feature activation-1.64e-01

Pos logit contributions
nces+0.318
quad+0.311
arms+0.303
bane+0.286
ldom+0.285
Neg logit contributions
auts-0.361
wikipedia-0.355
orem-0.354
д-0.350
ompl-0.347
Token On
Token ID1550
Feature activation-8.38e-02

Pos logit contributions
auts+3.023
wikipedia+2.937
orem+2.894
д+2.869
ompl+2.839
Neg logit contributions
nces-4.097
quad-3.933
arms-3.831
ldom-3.718
bane-3.659
Token Kickstarter
Token ID14437
Feature activation-2.68e-01

Pos logit contributions
nces+0.535
quad+0.522
arms+0.505
bane+0.483
ldom+0.482
Neg logit contributions
auts-0.502
wikipedia-0.500
orem-0.498
д-0.493
ompl-0.482
Token,
Token ID11
Feature activation+5.76e-01

Pos logit contributions
nces+1.592
quad+1.559
arms+1.506
bane+1.428
ldom+1.425
Neg logit contributions
auts-1.722
wikipedia-1.712
orem-1.705
д-1.671
ompl-1.651
Token backers
Token ID18917
Feature activation+4.30e-01

Pos logit contributions
auts+3.386
wikipedia+3.270
orem+3.246
ompl+3.219
д+3.197
Neg logit contributions
nces-3.837
quad-3.698
arms-3.590
bane-3.439
ldom-3.437
Token (
Token ID357
Feature activation-7.37e-02

Pos logit contributions
auts+2.261
orem+2.175
wikipedia+2.172
д+2.128
ompl+2.118
Neg logit contributions
nces-3.133
quad-3.000
arms-2.942
ldom-2.832
poses-2.811
Tokenyou
Token ID5832
Feature activation+8.81e-03

Pos logit contributions
nces+0.511
quad+0.508
arms+0.491
bane+0.467
ldom+0.464
Neg logit contributions
auts-0.402
orem-0.396
wikipedia-0.394
д-0.390
ompl-0.383
Token!)
Token ID8133
Feature activation+4.98e-01

Pos logit contributions
wikipedia+0.055
auts+0.055
orem+0.054
д+0.053
ompl+0.053
Neg logit contributions
nces-0.055
quad-0.053
arms-0.051
bane-0.050
ldom-0.049
Token ultimately
Token ID6165
Feature activation+5.50e-01

Pos logit contributions
auts+2.561
orem+2.490
wikipedia+2.469
ompl+2.411
д+2.403
Neg logit contributions
nces-3.677
quad-3.532
arms-3.451
ldom-3.323
tails-3.301
Token decide
Token ID5409
Feature activation+1.31e-01

Pos logit contributions
auts+2.982
orem+2.936
wikipedia+2.881
ompl+2.831
д+2.805
Neg logit contributions
nces-3.894
quad-3.709
arms-3.617
ldom-3.500
bane-3.454
Token the
Token ID262
Feature activation+2.56e-01

Pos logit contributions
auts+0.803
wikipedia+0.792
orem+0.783
д+0.780
ompl+0.768
Neg logit contributions
nces-0.828
quad-0.804
arms-0.780
bane-0.745
ldom-0.745
Token validity
Token ID19648
Feature activation-4.40e-01

Pos logit contributions
auts+1.482
wikipedia+1.450
orem+1.440
д+1.423
ompl+1.408
Neg logit contributions
nces-1.726
quad-1.674
arms-1.625
bane-1.554
ldom-1.554
Token.
Token ID13
Feature activation+2.98e-02

Pos logit contributions
nces+4.225
quad+4.157
arms+3.984
bane+3.733
ldom+3.725
Neg logit contributions
auts-5.085
wikipedia-5.025
orem-4.993
ompl-4.953
estern-4.829
Token It
Token ID632
Feature activation-1.90e-01

Pos logit contributions
auts+0.163
wikipedia+0.159
orem+0.159
д+0.155
ompl+0.155
Neg logit contributions
nces-0.209
quad-0.204
arms-0.199
bane-0.190
ldom-0.190
Token
Token ID447
Feature activation-2.33e-01

Pos logit contributions
nces+1.255
quad+1.215
arms+1.183
bane+1.129
poses+1.128
Neg logit contributions
auts-1.115
wikipedia-1.090
orem-1.086
д-1.059
ompl-1.050
Token
Token ID247
Feature activation-4.40e-01

Pos logit contributions
nces+0.971
quad+0.925
arms+0.882
bane+0.816
ldom+0.815
Neg logit contributions
auts-1.943
wikipedia-1.914
orem-1.904
д-1.887
ompl-1.874
Tokens
Token ID82
Feature activation+8.29e-03

Pos logit contributions
nces+3.248
quad+3.093
arms+3.053
poses+2.936
ldom+2.911
Neg logit contributions
auts-2.266
wikipedia-2.194
orem-2.183
д-2.174
ompl-2.127
Token either
Token ID2035
Feature activation+8.74e-01

Pos logit contributions
auts+0.055
wikipedia+0.054
orem+0.054
д+0.053
ompl+0.053
Neg logit contributions
nces-0.048
quad-0.047
arms-0.045
bane-0.043
ldom-0.043
Token going
Token ID1016
Feature activation+2.16e-01

Pos logit contributions
auts+5.123
wikipedia+5.068
д+4.992
orem+4.963
ompl+4.897
Neg logit contributions
nces-5.671
quad-5.380
arms-5.194
ldom-4.990
bane-4.978
Token to
Token ID284
Feature activation-1.13e-01

Pos logit contributions
auts+1.025
wikipedia+0.999
orem+0.993
д+0.968
ompl+0.959
Neg logit contributions
nces-1.683
quad-1.648
arms-1.601
bane-1.541
ldom-1.534
Token cost
Token ID1575
Feature activation+5.41e-01

Pos logit contributions
nces+0.735
quad+0.716
arms+0.692
bane+0.663
ldom+0.660
Neg logit contributions
auts-0.674
wikipedia-0.663
orem-0.656
д-0.649
ompl-0.641
Token us
Token ID514
Feature activation+5.15e-01

Pos logit contributions
auts+2.941
wikipedia+2.865
orem+2.826
д+2.816
ompl+2.775
Neg logit contributions
nces-3.838
quad-3.687
arms-3.588
ldom-3.445
bane-3.438
Token now
Token ID783
Feature activation-1.17e-01

Pos logit contributions
auts+3.189
wikipedia+3.119
д+3.087
orem+3.067
ompl+3.011
Neg logit contributions
nces-3.260
quad-3.154
arms-3.028
ldom-2.897
bane-2.890
Token fact
Token ID1109
Feature activation+4.60e-01

Pos logit contributions
auts+1.137
wikipedia+1.114
orem+1.107
д+1.095
ompl+1.083
Neg logit contributions
nces-1.179
quad-1.143
arms-1.107
bane-1.056
ldom-1.056
Token,
Token ID11
Feature activation+3.48e-01

Pos logit contributions
auts+2.748
wikipedia+2.687
orem+2.678
д+2.643
ompl+2.616
Neg logit contributions
nces-2.988
quad-2.906
arms-2.819
bane-2.698
ldom-2.689
Token a
Token ID257
Feature activation+3.17e-01

Pos logit contributions
auts+2.216
wikipedia+2.175
orem+2.162
д+2.131
ompl+2.115
Neg logit contributions
nces-2.123
quad-2.058
arms-1.997
bane-1.901
ldom-1.897
Token common
Token ID2219
Feature activation-2.88e-01

Pos logit contributions
auts+2.275
wikipedia+2.238
orem+2.229
д+2.205
ompl+2.188
Neg logit contributions
nces-1.686
quad-1.621
arms-1.566
bane-1.477
ldom-1.473
Token phrase
Token ID9546
Feature activation+6.73e-01

Pos logit contributions
nces+1.917
quad+1.862
arms+1.808
perate+1.734
bane+1.727
Neg logit contributions
auts-1.674
wikipedia-1.624
д-1.600
orem-1.582
ompl-1.576
Token among
Token ID1871
Feature activation+8.97e-01

Pos logit contributions
auts+4.040
wikipedia+3.951
orem+3.925
д+3.876
ompl+3.846
Neg logit contributions
nces-4.318
quad-4.168
arms-4.042
ldom-3.875
bane-3.866
Token CAT
Token ID38348
Feature activation+8.35e-02

Pos logit contributions
auts+5.932
orem+5.864
wikipedia+5.852
ompl+5.707
д+5.689
Neg logit contributions
nces-5.108
quad-4.905
arms-4.773
ldom-4.507
bane-4.476
Token adjust
Token ID4532
Feature activation+7.40e-02

Pos logit contributions
auts+0.432
wikipedia+0.426
orem+0.418
д+0.412
ompl+0.409
Neg logit contributions
nces-0.613
quad-0.593
arms-0.581
bane-0.557
perate-0.556
Tokeners
Token ID364
Feature activation+3.68e-01

Pos logit contributions
auts+0.367
wikipedia+0.361
orem+0.356
д+0.352
ompl+0.347
Neg logit contributions
nces-0.558
quad-0.543
arms-0.530
bane-0.508
ldom-0.508
Token is
Token ID318
Feature activation+4.89e-01

Pos logit contributions
auts+1.981
wikipedia+1.931
orem+1.916
д+1.892
ompl+1.867
Neg logit contributions
nces-2.628
quad-2.553
arms-2.484
ldom-2.385
bane-2.380
Token,
Token ID11
Feature activation-2.41e-01

Pos logit contributions
auts+2.961
wikipedia+2.901
orem+2.890
д+2.855
ompl+2.829
Neg logit contributions
nces-3.145
quad-3.047
arms-2.956
bane-2.824
ldom-2.812
Token,
Token ID11
Feature activation-6.68e-01

Pos logit contributions
nces+2.702
quad+2.688
arms+2.573
bane+2.412
poses+2.389
Neg logit contributions
auts-3.373
wikipedia-3.330
orem-3.287
д-3.266
ompl-3.237
Token although
Token ID3584
Feature activation+3.70e-01

Pos logit contributions
quad+3.846
nces+3.846
arms+3.668
bane+3.506
perate+3.468
Neg logit contributions
auts-4.282
orem-4.140
wikipedia-4.133
д-4.124
ompl-4.019
Token it
Token ID340
Feature activation+4.05e-01

Pos logit contributions
auts+2.271
wikipedia+2.254
orem+2.217
д+2.201
ompl+2.175
Neg logit contributions
nces-2.351
quad-2.253
arms-2.195
ldom-2.098
bane-2.087
Token had
Token ID550
Feature activation+1.55e-01

Pos logit contributions
auts+2.337
wikipedia+2.305
orem+2.271
д+2.252
ompl+2.227
Neg logit contributions
nces-2.714
quad-2.618
arms-2.555
ldom-2.445
bane-2.434
Token been
Token ID587
Feature activation+1.87e-01

Pos logit contributions
auts+0.923
wikipedia+0.904
orem+0.898
д+0.888
ompl+0.878
Neg logit contributions
nces-1.014
quad-0.983
arms-0.953
bane-0.910
ldom-0.910
Token upgraded
Token ID17955
Feature activation-3.76e-01

Pos logit contributions
auts+1.204
wikipedia+1.187
orem+1.175
д+1.166
ompl+1.151
Neg logit contributions
nces-1.139
quad-1.098
arms-1.067
ldom-1.015
bane-1.012
Token regularly
Token ID7987
Feature activation-4.44e-01

Pos logit contributions
nces+2.434
quad+2.365
arms+2.279
bane+2.186
ldom+2.182
Neg logit contributions
auts-2.235
wikipedia-2.180
orem-2.169
д-2.124
ompl-2.119
Token over
Token ID625
Feature activation+4.73e-01

Pos logit contributions
nces+2.645
quad+2.581
arms+2.446
ldom+2.339
bane+2.334
Neg logit contributions
auts-2.866
wikipedia-2.808
orem-2.791
ompl-2.728
д-2.703
Token the
Token ID262
Feature activation+5.29e-01

Pos logit contributions
auts+2.617
wikipedia+2.559
orem+2.520
д+2.514
ompl+2.478
Neg logit contributions
nces-3.298
quad-3.187
arms-3.090
bane-2.970
ldom-2.961
Token years
Token ID812
Feature activation+1.60e-01

Pos logit contributions
auts+3.407
wikipedia+3.323
orem+3.321
д+3.286
ompl+3.259
Neg logit contributions
nces-3.217
quad-3.069
arms-2.946
bane-2.835
ldom-2.824
Token,
Token ID11
Feature activation-5.77e-01

Pos logit contributions
auts+0.972
wikipedia+0.952
orem+0.947
д+0.932
ompl+0.925
Neg logit contributions
nces-1.027
quad-0.999
arms-0.965
bane-0.922
ldom-0.921
Token
Token ID447
Feature activation-8.63e-02

Pos logit contributions
nces+2.550
quad+2.475
arms+2.432
ldom+2.294
poses+2.290
Neg logit contributions
auts-2.545
wikipedia-2.506
orem-2.486
д-2.412
estern-2.382
Token
Token ID247
Feature activation+2.64e-01

Pos logit contributions
nces+0.411
quad+0.394
arms+0.378
bane+0.354
ldom+0.354
Neg logit contributions
auts-0.669
wikipedia-0.659
orem-0.655
д-0.650
ompl-0.644
Tokens
Token ID82
Feature activation-2.00e-01

Pos logit contributions
auts+1.326
wikipedia+1.295
orem+1.282
д+1.265
ompl+1.249
Neg logit contributions
nces-1.986
quad-1.930
arms-1.881
ldom-1.808
bane-1.807
Token not
Token ID407
Feature activation-4.57e-01

Pos logit contributions
nces+1.285
quad+1.237
arms+1.207
ldom+1.154
bane+1.139
Neg logit contributions
wikipedia-1.198
auts-1.196
orem-1.174
д-1.148
ompl-1.143
Token going
Token ID1016
Feature activation-1.04e-01

Pos logit contributions
nces+2.678
quad+2.601
arms+2.500
ldom+2.440
bane+2.366
Neg logit contributions
auts-2.902
orem-2.857
wikipedia-2.853
д-2.781
ompl-2.779
Token to
Token ID284
Feature activation-1.15e-01

Pos logit contributions
nces+0.792
quad+0.773
arms+0.747
bane+0.723
ldom+0.720
Neg logit contributions
auts-0.499
orem-0.487
wikipedia-0.486
д-0.466
ompl-0.461
Token be
Token ID307
Feature activation-1.34e-01

Pos logit contributions
nces+0.766
quad+0.747
arms+0.718
ldom+0.691
bane+0.690
Neg logit contributions
auts-0.661
wikipedia-0.654
orem-0.646
д-0.636
ompl-0.626
Token a
Token ID257
Feature activation-7.83e-01

Pos logit contributions
nces+0.789
quad+0.759
arms+0.728
ldom+0.702
bane+0.693
Neg logit contributions
auts-0.884
orem-0.878
wikipedia-0.873
д-0.857
ompl-0.847
Token champagne
Token ID37392
Feature activation+9.25e-03

Pos logit contributions
nces+4.919
quad+4.846
arms+4.547
perate+4.493
ldom+4.492
Neg logit contributions
auts-4.496
wikipedia-4.455
orem-4.392
д-4.353
ompl-4.287
Token party
Token ID2151
Feature activation-8.66e-01

Pos logit contributions
auts+0.053
wikipedia+0.052
orem+0.052
д+0.051
ompl+0.051
Neg logit contributions
nces-0.062
quad-0.061
arms-0.059
bane-0.056
ldom-0.056
Token or
Token ID393
Feature activation-7.29e-02

Pos logit contributions
nces+4.888
quad+4.787
arms+4.545
ldom+4.390
bane+4.382
Neg logit contributions
auts-5.554
orem-5.498
wikipedia-5.481
д-5.437
ompl-5.321
Token variation
Token ID12291
Feature activation-4.16e-01

Pos logit contributions
auts+2.560
wikipedia+2.526
orem+2.510
д+2.479
ompl+2.435
Neg logit contributions
nces-3.484
quad-3.359
arms-3.294
ldom-3.160
bane-3.153
Token for
Token ID329
Feature activation-4.56e-01

Pos logit contributions
nces+2.484
quad+2.410
arms+2.304
ldom+2.178
perate+2.176
Neg logit contributions
auts-2.703
wikipedia-2.666
orem-2.624
ompl-2.562
д-2.556
Token a
Token ID257
Feature activation-4.71e-01

Pos logit contributions
nces+2.908
quad+2.838
arms+2.722
perate+2.588
ldom+2.578
Neg logit contributions
auts-2.800
wikipedia-2.705
orem-2.692
д-2.652
ompl-2.636
Token 16
Token ID1467
Feature activation-4.79e-01

Pos logit contributions
quad+2.769
nces+2.757
arms+2.560
perate+2.498
ldom+2.480
Neg logit contributions
auts-3.091
wikipedia-2.969
orem-2.962
д-2.916
ompl-2.894
Token-
Token ID12
Feature activation-6.55e-01

Pos logit contributions
quad+2.550
nces+2.518
arms+2.412
ldom+2.278
bane+2.261
Neg logit contributions
auts-3.395
wikipedia-3.302
orem-3.279
д-3.195
ompl-3.177
Token35
Token ID2327
Feature activation-4.15e-01

Pos logit contributions
quad+3.248
nces+3.112
arms+3.082
ldom+2.756
perate+2.756
Neg logit contributions
auts-4.904
orem-4.786
wikipedia-4.748
д-4.633
sburgh-4.581
Token f
Token ID277
Feature activation-1.11e+00

Pos logit contributions
nces+2.583
quad+2.559
arms+2.408
bane+2.331
ldom+2.328
Neg logit contributions
auts-2.594
wikipedia-2.513
orem-2.489
д-2.444
ompl-2.432
Token/
Token ID14
Feature activation+1.13e-02

Pos logit contributions
quad+4.834
nces+4.744
arms+4.624
bane+4.245
perate+4.179
Neg logit contributions
auts-8.464
orem-8.408
ompl-8.315
wikipedia-8.256
д-8.211
Token4
Token ID19
Feature activation-1.32e-02

Pos logit contributions
auts+0.074
wikipedia+0.073
orem+0.072
д+0.072
ompl+0.071
Neg logit contributions
nces-0.068
quad-0.066
arms-0.063
bane-0.060
ldom-0.060
Token IS
Token ID3180
Feature activation-3.32e-01

Pos logit contributions
nces+0.071
quad+0.069
arms+0.066
ldom+0.063
bane+0.063
Neg logit contributions
auts-0.094
wikipedia-0.092
orem-0.091
д-0.091
ompl-0.090
Token lens
Token ID10317
Feature activation+2.15e-01

Pos logit contributions
nces+1.761
quad+1.756
arms+1.639
bane+1.568
perate+1.554
Neg logit contributions
auts-2.381
wikipedia-2.323
orem-2.309
д-2.283
ompl-2.256
Token
Token ID198
Feature activation+1.55e-01

Pos logit contributions
auts+0.164
wikipedia+0.161
orem+0.158
д+0.157
ompl+0.154
Neg logit contributions
nces-0.196
quad-0.188
arms-0.182
ldom-0.177
bane-0.174
TokenHowever
Token ID4864
Feature activation-1.62e-02

Pos logit contributions
auts+0.897
wikipedia+0.877
orem+0.873
д+0.861
ompl+0.853
Neg logit contributions
nces-1.038
quad-1.009
arms-0.979
bane-0.936
ldom-0.934
Token,
Token ID11
Feature activation-3.26e-01

Pos logit contributions
nces+0.101
quad+0.097
arms+0.094
bane+0.090
ldom+0.090
Neg logit contributions
auts-0.102
wikipedia-0.100
orem-0.100
д-0.098
ompl-0.098
Token the
Token ID262
Feature activation-1.26e-01

Pos logit contributions
nces+1.975
quad+1.904
arms+1.850
bane+1.767
ldom+1.754
Neg logit contributions
auts-2.079
wikipedia-2.045
orem-2.044
д-2.012
ompl-2.009
Token GP
Token ID14714
Feature activation-8.47e-01

Pos logit contributions
nces+0.875
quad+0.849
arms+0.826
bane+0.793
ldom+0.787
Neg logit contributions
auts-0.704
wikipedia-0.691
orem-0.682
д-0.675
ompl-0.670
Token was
Token ID373
Feature activation-5.52e-01

Pos logit contributions
nces+5.203
quad+5.140
arms+4.906
bane+4.782
poses+4.736
Neg logit contributions
auts-5.075
wikipedia-5.010
orem-4.919
ompl-4.877
д-4.813
Token not
Token ID407
Feature activation+1.84e-01

Pos logit contributions
nces+3.219
quad+3.171
arms+3.010
bane+2.946
ldom+2.882
Neg logit contributions
auts-3.655
wikipedia-3.563
orem-3.537
ompl-3.492
д-3.477
Token made
Token ID925
Feature activation+2.55e-01

Pos logit contributions
auts+1.085
wikipedia+1.063
orem+1.055
д+1.045
ompl+1.031
Neg logit contributions
nces-1.224
quad-1.186
arms-1.151
ldom-1.100
bane-1.099
Token aware
Token ID3910
Feature activation+5.69e-01

Pos logit contributions
auts+1.110
wikipedia+1.079
orem+1.068
д+1.052
ompl+1.036
Neg logit contributions
nces-2.081
quad-2.031
arms-1.982
bane-1.913
ldom-1.911
Token that
Token ID326
Feature activation+1.18e-01

Pos logit contributions
auts+3.407
wikipedia+3.357
д+3.319
orem+3.279
ompl+3.214
Neg logit contributions
nces-3.679
quad-3.571
arms-3.462
ldom-3.301
bane-3.277
Token the
Token ID262
Feature activation-2.31e-02

Pos logit contributions
auts+0.735
wikipedia+0.719
orem+0.713
д+0.708
ompl+0.698
Neg logit contributions
nces-0.748
quad-0.726
arms-0.701
ldom-0.670
bane-0.669
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
auts+0.685
wikipedia+0.673
orem+0.668
д+0.660
ompl+0.651
Neg logit contributions
nces-0.714
quad-0.693
arms-0.670
bane-0.640
ldom-0.638
Token
Token ID198
Feature activation+4.87e-01

Pos logit contributions
auts+0.814
wikipedia+0.804
orem+0.781
д+0.779
ompl+0.761
Neg logit contributions
nces-1.026
quad-0.977
arms-0.949
ldom-0.932
bane-0.911
TokenH
Token ID39
Feature activation-2.27e-01

Pos logit contributions
auts+2.945
wikipedia+2.914
orem+2.849
д+2.826
ompl+2.787
Neg logit contributions
nces-3.143
quad-2.997
arms-2.906
ldom-2.828
bane-2.797
Tokenag
Token ID363
Feature activation-3.13e-01

Pos logit contributions
nces+1.513
quad+1.502
arms+1.483
ldom+1.396
bane+1.392
Neg logit contributions
auts-1.281
wikipedia-1.270
orem-1.246
д-1.241
ompl-1.211
Tokenel
Token ID417
Feature activation+2.33e-01

Pos logit contributions
nces+2.024
quad+1.968
arms+1.916
ldom+1.830
bane+1.826
Neg logit contributions
auts-1.880
wikipedia-1.843
orem-1.830
д-1.813
ompl-1.789
Token had
Token ID550
Feature activation-2.02e-01

Pos logit contributions
auts+1.344
wikipedia+1.315
orem+1.305
д+1.289
ompl+1.276
Neg logit contributions
nces-1.581
quad-1.534
arms-1.489
bane-1.425
ldom-1.424
Token a
Token ID257
Feature activation-1.16e-02

Pos logit contributions
nces+1.270
quad+1.230
arms+1.193
ldom+1.143
bane+1.135
Neg logit contributions
auts-1.244
wikipedia-1.221
orem-1.218
д-1.206
ompl-1.190
Token rocky
Token ID26898
Feature activation-1.00e-01

Pos logit contributions
nces+0.077
quad+0.075
arms+0.073
ldom+0.070
bane+0.069
Neg logit contributions
auts-0.069
wikipedia-0.067
orem-0.067
д-0.066
ompl-0.065
Token tenure
Token ID17081
Feature activation+3.73e-01

Pos logit contributions
nces+0.634
quad+0.621
arms+0.601
ldom+0.576
bane+0.572
Neg logit contributions
auts-0.615
wikipedia-0.604
orem-0.598
д-0.593
ompl-0.582
Token from
Token ID422
Feature activation+9.89e-02

Pos logit contributions
auts+2.314
wikipedia+2.251
д+2.220
orem+2.217
ompl+2.209
Neg logit contributions
nces-2.343
quad-2.261
arms-2.211
bane-2.099
ldom-2.092
Token the
Token ID262
Feature activation-1.20e-01

Pos logit contributions
auts+0.585
wikipedia+0.573
orem+0.570
д+0.563
ompl+0.556
Neg logit contributions
nces-0.654
quad-0.635
arms-0.616
ldom-0.589
bane-0.588
Tokenumbles
Token ID25329
Feature activation-8.48e-01

Pos logit contributions
nces+5.097
quad+4.990
bane+4.878
arms+4.858
perate+4.646
Neg logit contributions
wikipedia-5.149
estern-5.069
 Participant-4.914
orem-4.910
д-4.909
Token (
Token ID357
Feature activation-2.30e-01

Pos logit contributions
quad+4.441
nces+4.392
arms+3.997
bane+3.972
perate+3.888
Neg logit contributions
auts-5.906
wikipedia-5.900
orem-5.848
ompl-5.649
д-5.565
Tokent
Token ID83
Feature activation-7.06e-01

Pos logit contributions
nces+1.336
quad+1.318
arms+1.263
bane+1.188
tails+1.176
Neg logit contributions
auts-1.546
orem-1.517
wikipedia-1.499
д-1.484
ompl-1.475
Tokenied
Token ID798
Feature activation-3.07e-01

Pos logit contributions
quad+6.247
nces+6.206
arms+6.129
bane+5.906
ldom+5.888
Neg logit contributions
wikipedia-2.272
auts-2.264
д-2.253
orem-2.167
ompl-2.096
Token for
Token ID329
Feature activation-6.95e-01

Pos logit contributions
nces+1.975
quad+1.924
arms+1.858
bane+1.777
ldom+1.770
Neg logit contributions
auts-1.857
wikipedia-1.824
orem-1.814
д-1.787
ompl-1.773
Token second
Token ID1218
Feature activation-1.63e+00

Pos logit contributions
nces+3.859
quad+3.814
arms+3.652
bane+3.470
ldom+3.406
Neg logit contributions
auts-4.651
wikipedia-4.558
orem-4.540
д-4.500
ompl-4.416
Token),
Token ID828
Feature activation+1.43e-01

Pos logit contributions
quad+7.675
nces+7.501
arms+7.019
perate+6.647
bane+6.586
Neg logit contributions
wikipedia-11.457
orem-11.190
auts-11.073
ompl-10.981
д-10.612
Token grabbed
Token ID13176
Feature activation-3.69e-01

Pos logit contributions
auts+0.887
wikipedia+0.869
orem+0.862
д+0.855
ompl+0.844
Neg logit contributions
nces-0.907
quad-0.876
arms-0.851
ldom-0.812
bane-0.810
Token an
Token ID281
Feature activation+2.98e-01

Pos logit contributions
nces+2.249
quad+2.190
arms+2.102
ldom+2.003
bane+2.000
Neg logit contributions
auts-2.342
wikipedia-2.316
orem-2.297
д-2.270
ompl-2.246
Token interception
Token ID28759
Feature activation-5.13e-01

Pos logit contributions
auts+1.703
wikipedia+1.677
orem+1.652
д+1.637
ompl+1.616
Neg logit contributions
nces-2.019
quad-1.979
arms-1.918
bane-1.832
ldom-1.828
Token,
Token ID11
Feature activation-1.48e-01

Pos logit contributions
quad+2.897
nces+2.879
arms+2.719
bane+2.625
perate+2.597
Neg logit contributions
auts-3.425
wikipedia-3.413
orem-3.345
д-3.261
ompl-3.235
Token catch
Token ID4929
Feature activation-1.30e+00

Pos logit contributions
nces+1.268
quad+1.234
arms+1.191
bane+1.145
ldom+1.137
Neg logit contributions
auts-1.135
wikipedia-1.117
orem-1.106
д-1.094
ompl-1.077
Token on
Token ID319
Feature activation-3.42e-01

Pos logit contributions
nces+6.854
arms+6.629
quad+6.349
tails+6.157
bane+5.781
Neg logit contributions
wikipedia-8.106
orem-8.061
д-8.049
sburgh-7.977
auts-7.932
Token?
Token ID30
Feature activation-2.52e-02

Pos logit contributions
nces+2.145
quad+2.077
arms+2.013
bane+1.925
ldom+1.911
Neg logit contributions
auts-2.069
orem-2.058
wikipedia-2.046
ompl-1.998
д-1.998
Token Would
Token ID10928
Feature activation-6.46e-02

Pos logit contributions
nces+0.173
quad+0.168
arms+0.164
bane+0.157
ldom+0.156
Neg logit contributions
auts-0.142
wikipedia-0.138
orem-0.138
д-0.135
ompl-0.135
Token you
Token ID345
Feature activation-6.96e-01

Pos logit contributions
nces+0.435
quad+0.423
arms+0.410
bane+0.394
ldom+0.392
Neg logit contributions
auts-0.370
wikipedia-0.364
orem-0.362
д-0.356
ompl-0.352
Token ever
Token ID1683
Feature activation-1.31e+00

Pos logit contributions
nces+4.311
quad+4.196
arms+4.091
bane+3.953
ldom+3.895
Neg logit contributions
auts-4.198
wikipedia-4.158
orem-4.088
д-4.036
ompl-3.973
Token use
Token ID779
Feature activation-5.40e-01

Pos logit contributions
nces+7.553
quad+7.438
arms+7.361
bane+7.073
perate+6.933
Neg logit contributions
auts-7.672
wikipedia-7.496
д-7.366
estern-7.330
orem-7.296
Token this
Token ID428
Feature activation-2.33e-01

Pos logit contributions
nces+3.190
quad+3.102
arms+3.030
bane+2.847
perate+2.844
Neg logit contributions
auts-3.411
orem-3.336
wikipedia-3.317
д-3.284
ompl-3.219
Token?
Token ID30
Feature activation-1.78e-01

Pos logit contributions
nces+1.461
quad+1.418
arms+1.368
bane+1.307
ldom+1.295
Neg logit contributions
auts-1.442
wikipedia-1.418
orem-1.408
д-1.382
ompl-1.375
Token Share
Token ID8734
Feature activation-1.37e-01

Pos logit contributions
nces+1.191
quad+1.156
arms+1.125
bane+1.083
ldom+1.069
Neg logit contributions
auts-1.024
wikipedia-0.991
orem-0.987
ompl-0.972
д-0.967
Token in
Token ID287
Feature activation-4.38e-03

Pos logit contributions
nces+0.924
quad+0.893
arms+0.872
bane+0.838
ldom+0.834
Neg logit contributions
auts-0.790
wikipedia-0.770
orem-0.762
ompl-0.755
д-0.749
Token
Token ID198
Feature activation-4.81e-02

Pos logit contributions
auts+0.360
wikipedia+0.351
orem+0.349
д+0.345
ompl+0.341
Neg logit contributions
nces-0.442
quad-0.430
arms-0.418
bane-0.400
ldom-0.399
Token
Token ID198
Feature activation-1.57e-01

Pos logit contributions
nces+0.322
quad+0.310
arms+0.300
ldom+0.290
bane+0.287
Neg logit contributions
auts-0.282
wikipedia-0.277
orem-0.274
д-0.272
ompl-0.267
Token
Token ID1399
Feature activation+4.87e-02

Pos logit contributions
nces+1.010
quad+0.998
arms+0.968
bane+0.919
poses+0.912
Neg logit contributions
auts-0.939
orem-0.919
wikipedia-0.904
ompl-0.899
д-0.896
Token do
Token ID466
Feature activation-5.13e-01

Pos logit contributions
auts+0.283
wikipedia+0.277
orem+0.275
д+0.272
ompl+0.269
Neg logit contributions
nces-0.326
quad-0.317
arms-0.308
bane-0.294
ldom-0.294
Token you
Token ID345
Feature activation-1.13e+00

Pos logit contributions
nces+3.061
quad+2.991
arms+2.916
perate+2.736
ldom+2.732
Neg logit contributions
auts-3.243
orem-3.180
wikipedia-3.176
д-3.135
estern-3.103
Token ever
Token ID1683
Feature activation-1.63e+00

Pos logit contributions
nces+6.603
quad+6.425
arms+6.224
bane+6.185
ldom+6.086
Neg logit contributions
auts-6.758
wikipedia-6.734
estern-6.537
orem-6.507
д-6.477
Token find
Token ID1064
Feature activation-1.24e+00

Pos logit contributions
nces+9.644
arms+9.260
quad+9.043
ldom+8.813
bane+8.745
Neg logit contributions
auts-9.078
estern-8.829
д-8.667
wikipedia-8.665
orem-8.524
Token that
Token ID326
Feature activation-5.29e-01

Pos logit contributions
nces+7.143
quad+6.641
arms+6.545
poses+6.253
ldom+6.239
Neg logit contributions
orem-7.567
auts-7.471
wikipedia-7.320
ompl-7.282
д-7.197
Token sometimes
Token ID3360
Feature activation-3.75e-01

Pos logit contributions
nces+3.282
quad+3.139
arms+3.052
bane+2.913
ldom+2.912
Neg logit contributions
auts-3.292
orem-3.232
wikipedia-3.179
д-3.159
ompl-3.149
Token
Token ID851
Feature activation+3.01e-01

Pos logit contributions
nces+2.345
quad+2.261
arms+2.198
ldom+2.093
bane+2.093
Neg logit contributions
auts-2.325
orem-2.284
wikipedia-2.261
д-2.225
ompl-2.224
Token in
Token ID287
Feature activation-1.99e-01

Pos logit contributions
auts+1.845
wikipedia+1.812
orem+1.791
д+1.776
ompl+1.757
Neg logit contributions
nces-1.919
quad-1.855
arms-1.792
bane-1.716
ldom-1.711
Token $
Token ID720
Feature activation+6.82e-02

Pos logit contributions
nces+2.287
quad+2.247
arms+2.164
bane+2.081
perate+2.068
Neg logit contributions
auts-2.030
wikipedia-1.982
orem-1.939
д-1.934
ompl-1.913
Tokenfont
Token ID10331
Feature activation+1.52e+00

Pos logit contributions
auts+0.343
wikipedia+0.332
orem+0.330
д+0.326
ompl+0.323
Neg logit contributions
nces-0.512
quad-0.501
arms-0.488
bane-0.467
ldom-0.465
Token1
Token ID16
Feature activation+7.19e-02

Pos logit contributions
auts+8.582
д+8.472
orem+8.432
wikipedia+8.331
ompl+8.156
Neg logit contributions
nces-9.475
quad-8.802
arms-8.569
ldom-8.531
bane-8.276
Token =
Token ID796
Feature activation-4.00e-01

Pos logit contributions
auts+0.398
wikipedia+0.389
orem+0.385
д+0.380
ompl+0.377
Neg logit contributions
nces-0.504
quad-0.491
arms-0.475
bane-0.456
ldom-0.454
Token New
Token ID968
Feature activation-8.33e-01

Pos logit contributions
nces+2.508
quad+2.472
arms+2.355
bane+2.258
perate+2.248
Neg logit contributions
auts-2.469
wikipedia-2.395
д-2.366
orem-2.366
ompl-2.352
Token-
Token ID12
Feature activation-1.45e+00

Pos logit contributions
nces+4.474
quad+4.398
arms+4.195
bane+4.017
IOR+3.962
Neg logit contributions
auts-5.724
orem-5.590
wikipedia-5.576
ompl-5.495
д-5.474
TokenObject
Token ID10267
Feature activation-3.41e-01

Pos logit contributions
quad+9.044
IOR+8.777
nces+8.721
arms+8.454
poses+8.224
Neg logit contributions
estern-8.023
orem-7.902
auts-7.884
essee-7.545
ompl-7.513
Token System
Token ID4482
Feature activation+7.08e-02

Pos logit contributions
nces+1.701
quad+1.671
arms+1.566
bane+1.529
perate+1.492
Neg logit contributions
auts-2.535
wikipedia-2.456
д-2.445
orem-2.432
ompl-2.423
Token.
Token ID13
Feature activation-3.61e-01

Pos logit contributions
auts+0.356
wikipedia+0.349
orem+0.344
д+0.341
ompl+0.335
Neg logit contributions
nces-0.531
quad-0.516
arms-0.502
ldom-0.484
bane-0.482
TokenDraw
Token ID25302
Feature activation+1.18e-03

Pos logit contributions
nces+2.609
quad+2.589
arms+2.507
IOR+2.426
bane+2.405
Neg logit contributions
auts-1.849
orem-1.821
ompl-1.771
wikipedia-1.756
estern-1.731
Tokening
Token ID278
Feature activation+3.50e-01

Pos logit contributions
auts+0.007
wikipedia+0.006
orem+0.006
д+0.006
ompl+0.006
Neg logit contributions
nces-0.008
quad-0.008
arms-0.008
ldom-0.008
bane-0.007
Token were
Token ID547
Feature activation-2.78e-01

Pos logit contributions
auts+1.758
wikipedia+1.722
orem+1.709
д+1.688
ompl+1.665
Neg logit contributions
nces-2.068
quad-2.003
arms-1.944
bane-1.865
ldom-1.861
Token acquired
Token ID9477
Feature activation-8.42e-01

Pos logit contributions
nces+1.688
quad+1.633
arms+1.577
ldom+1.513
bane+1.510
Neg logit contributions
auts-1.781
orem-1.733
wikipedia-1.728
д-1.712
ompl-1.712
Token by
Token ID416
Feature activation-1.74e-01

Pos logit contributions
nces+4.653
quad+4.427
arms+4.346
bane+4.185
ldom+4.178
Neg logit contributions
auts-5.591
orem-5.493
wikipedia-5.442
ompl-5.432
д-5.399
Token companies
Token ID2706
Feature activation-4.70e-02

Pos logit contributions
nces+1.129
quad+1.100
arms+1.076
bane+1.025
ldom+1.020
Neg logit contributions
auts-1.036
wikipedia-1.010
orem-1.007
д-1.000
ompl-0.981
Token for
Token ID329
Feature activation-6.51e-01

Pos logit contributions
nces+0.286
quad+0.279
arms+0.269
bane+0.256
ldom+0.256
Neg logit contributions
auts-0.302
wikipedia-0.296
orem-0.294
д-0.291
ompl-0.288
Token millions
Token ID5242
Feature activation-1.41e+00

Pos logit contributions
nces+3.891
quad+3.800
arms+3.775
perate+3.588
bane+3.547
Neg logit contributions
auts-4.000
wikipedia-3.921
orem-3.887
д-3.875
ompl-3.815
Token of
Token ID286
Feature activation-1.28e+00

Pos logit contributions
nces+6.347
quad+6.337
perate+5.636
arms+5.595
ldom+5.576
Neg logit contributions
auts-10.022
orem-9.814
estern-9.641
wikipedia-9.636
д-9.603
Token pounds
Token ID8059
Feature activation-1.44e+00

Pos logit contributions
nces+4.478
quad+4.437
perate+4.077
arms+4.016
ldom+3.901
Neg logit contributions
orem-10.354
wikipedia-10.301
auts-10.207
д-9.951
ompl-9.856
Token and
Token ID290
Feature activation-5.08e-01

Pos logit contributions
quad+7.468
nces+7.369
arms+6.976
perate+6.839
ldom+6.776
Neg logit contributions
auts-9.267
orem-8.969
estern-8.892
д-8.846
wikipedia-8.826
Token this
Token ID428
Feature activation+3.10e-01

Pos logit contributions
nces+3.082
quad+3.035
arms+2.953
ldom+2.813
bane+2.813
Neg logit contributions
auts-3.151
wikipedia-3.082
orem-3.071
д-3.055
ompl-3.017
Token helped
Token ID4193
Feature activation+1.74e-01

Pos logit contributions
auts+1.780
wikipedia+1.747
orem+1.732
д+1.709
ompl+1.690
Neg logit contributions
nces-2.103
quad-2.037
arms-1.975
ldom-1.893
bane-1.891