TOP ACTIVATIONS
MAX = 9.250

D DoS traffic would be mit igated , there would be
Flake ( R - Ari z .) after he was heard
D DoS Mit igation No Silver Bullet
v 2 . COL OR _ B GR 2 G RAY
trans cript s / sc aling bitcoin / h ong -
ara P 217 Gibson came fourth , ahead of the fastest
noted . <|endoftext|> T EL AV IV A clandestine Israeli
day of the year was cold and over cast , but
network D DoS Mit igation No Silver Bullet
problems . I 've Mac Gy vered mental upgrades out of
c v 2 . Ga ussian Bl ur ( gray ,
is officially supported . For now , the lens is excellent
finding a safety . For now , coaches have David Brut
two options . The first is an illegal hack to remove
Virginia . Di plom atic cables are internal documents
_ in jury _ pre vention / key _ facts /
Civil Beat C ald well also wants to enact
, with La La Land producer Jordan
ried , who also had history on the trading side ,
um acher 's Mercedes was third ahead of McLaren 's Lewis

MIN ACTIVATIONS
MIN = -10.072

downright optimistic . The original End bringer stood about forty five
that the crackdown s against Occupy protesters appear to be violating
=" phone . name "> span > < p ng -
John Murd y , Halloween Horror Nights ' Creative Director ,
not protecting the rights of Occupy demonstrators whose protests are being
phone in phones "> < span ng - bind =" phone
to the hugely popular Halloween Horror Nights , I returned for
Manufacturing Process 14 nm 28 nm 28 nm 16 nm 16
t ong ue . Th é od en must ers his
shareholders ," deputy Conservative leader Lisa Ra itt said . "
fossils , geographic regions and strat ig raphic positions make random
. For give me ! Please forgive me !
It s my fault . # atl weather #
, and Prof . Loren Cord ain comes down pretty hard
We ve seen it with [ alcohol ]
so I added a < span > around the phone name
in a table or chart format ). It may also have
> li > ul > body >
putting together an event like Horror Nights ... tanks included .
ua , New Hampshire . Hide Caption 6 of 15 Photos

INTERVAL 4.419 - 9.250
CONTAINS 0.671%

his initial pick from Lone Druid to Templar Assassin . He
capital is rep lete with memorial s to presidents and veterans
a program he thought was rational over the objections of the
those of ausp icious or ( for boys ) man ly
/ or Survival + The Prim er from your local book

INTERVAL -0.411 - 4.419
CONTAINS 59.289%

be confronted almost immediately by the staggering dimensions of my own
Writ ters Strike 2008 01 04 O & A - WOR
? She said : I I asked : What is the
SOLD IER L : VB 5 92 4 78 T :
s is a modern , multi - billion dollar campaign to

INTERVAL -5.242 - -0.411
CONTAINS 39.797%

OF EXT REM ELY EXP ENS IVE BE ER WITHOUT THE
larger ( 3 . 9 4 . 5 kg ),
located the legendary war for Helen that would become parad igmatic
The bulldo zers that are responsible for destroying land and buildings
their territory . But we should applaud them for their realism

INTERVAL -10.072 - -5.242
CONTAINS 0.242%

- cl oak to this end . It works by injecting
Mag ico and V ivid Audio -- and their lowest -
capacity to 300 , 000 barrels a day . Virt ually
her and another employee , Desire e La Feb re .
rebutt als toward cliché bo hem ian ideals that have been
Token D
Token ID360
Feature activation-1.48e+00

Pos logit contributions
 Debor+1.030
+0.904
+0.848
 MSM+0.845
 unsus+0.825
Neg logit contributions
grain-1.048
urdue-1.008
ellar-1.004
 Windsor-0.984
font-0.972
TokenDoS
Token ID46498
Feature activation-2.43e+00

Pos logit contributions
grain+0.994
urdue+0.949
ellar+0.947
 Windsor+0.927
font+0.913
Neg logit contributions
 Debor-1.230
-1.092
-1.032
 MSM-1.026
 unsus-1.006
Token traffic
Token ID4979
Feature activation+3.63e-01

Pos logit contributions
grain+2.078
urdue+1.998
ellar+1.997
 Windsor+1.978
font+1.957
Neg logit contributions
 Debor-1.562
-1.328
-1.243
 MSM-1.219
-1.207
Token would
Token ID561
Feature activation+3.22e+00

Pos logit contributions
 Debor+0.302
+0.268
+0.253
 MSM+0.253
 unsus+0.248
Neg logit contributions
grain-0.244
urdue-0.233
ellar-0.232
 Windsor-0.226
font-0.223
Token be
Token ID307
Feature activation+4.20e+00

Pos logit contributions
 Debor+2.435
+2.128
+2.021
 MSM+2.017
 unsus+1.999
Neg logit contributions
grain-2.367
urdue-2.273
ellar-2.244
 Windsor-2.208
font-2.198
Token mit
Token ID10255
Feature activation+9.25e+00

Pos logit contributions
 Debor+2.967
+2.550
 MSM+2.439
 unsus+2.399
+2.396
Neg logit contributions
grain-3.301
urdue-3.206
ellar-3.181
font-3.082
 Windsor-3.070
Tokenigated
Token ID26963
Feature activation+5.02e+00

Pos logit contributions
 Debor+6.882
+5.933
+5.751
 MSM+5.692
 Swordsman+5.548
Neg logit contributions
grain-6.183
urdue-6.141
 Windsor-6.010
ellar-5.869
afety-5.753
Token,
Token ID11
Feature activation+2.14e+00

Pos logit contributions
 Debor+3.656
+3.213
 MSM+2.980
+2.976
 unsus+2.957
Neg logit contributions
grain-3.851
ellar-3.668
urdue-3.656
 Windsor-3.593
font-3.519
Token there
Token ID612
Feature activation+6.12e-02

Pos logit contributions
 Debor+1.691
+1.495
+1.413
 MSM+1.410
 unsus+1.383
Neg logit contributions
grain-1.515
urdue-1.445
ellar-1.443
 Windsor-1.409
font-1.391
Token would
Token ID561
Feature activation+7.39e-01

Pos logit contributions
 Debor+0.050
+0.044
+0.042
 MSM+0.042
 unsus+0.041
Neg logit contributions
grain-0.042
urdue-0.040
ellar-0.040
 Windsor-0.039
font-0.039
Token be
Token ID307
Feature activation-9.22e-01

Pos logit contributions
 Debor+0.598
+0.530
+0.501
 MSM+0.498
 unsus+0.488
Neg logit contributions
grain-0.513
urdue-0.490
ellar-0.487
 Windsor-0.479
font-0.471
Token Flake
Token ID39727
Feature activation+6.37e-01

Pos logit contributions
 Debor+0.869
+0.740
+0.679
 MSM+0.672
 unsus+0.652
Neg logit contributions
grain-1.290
urdue-1.248
ellar-1.243
 Windsor-1.229
font-1.213
Token(
Token ID7
Feature activation+1.60e+00

Pos logit contributions
 Debor+0.517
+0.458
+0.432
 MSM+0.430
 unsus+0.421
Neg logit contributions
grain-0.442
urdue-0.422
ellar-0.421
 Windsor-0.412
font-0.405
TokenR
Token ID49
Feature activation-7.82e-01

Pos logit contributions
 Debor+1.072
+0.925
+0.862
 MSM+0.854
 unsus+0.828
Neg logit contributions
grain-1.337
urdue-1.288
ellar-1.285
 Windsor-1.264
font-1.247
Token-
Token ID12
Feature activation+3.90e+00

Pos logit contributions
grain+0.488
urdue+0.465
ellar+0.463
 Windsor+0.453
font+0.446
Neg logit contributions
 Debor-0.685
-0.612
-0.581
 MSM-0.579
 unsus-0.569
TokenAri
Token ID26529
Feature activation+3.33e+00

Pos logit contributions
 Debor+1.832
+1.512
+1.373
 MSM+1.330
+1.263
Neg logit contributions
grain-3.964
urdue-3.921
ellar-3.874
 Windsor-3.817
font-3.733
Tokenz
Token ID89
Feature activation+8.98e+00

Pos logit contributions
 Debor+2.759
+2.450
 MSM+2.324
+2.316
 unsus+2.297
Neg logit contributions
grain-2.106
ellar-2.087
urdue-2.078
afety-2.028
 Windsor-1.979
Token.)
Token ID2014
Feature activation-2.51e-01

Pos logit contributions
 Debor+5.587
+4.862
+4.524
 MSM+4.456
+4.347
Neg logit contributions
grain-7.362
ellar-7.176
urdue-7.001
 Windsor-6.971
font-6.937
Token after
Token ID706
Feature activation+4.19e-01

Pos logit contributions
grain+0.170
urdue+0.162
ellar+0.162
 Windsor+0.159
font+0.156
Neg logit contributions
 Debor-0.207
-0.184
-0.174
 MSM-0.173
 unsus-0.170
Token he
Token ID339
Feature activation+1.78e+00

Pos logit contributions
 Debor+0.325
+0.287
+0.271
 MSM+0.268
 unsus+0.263
Neg logit contributions
grain-0.304
urdue-0.291
ellar-0.290
 Windsor-0.286
font-0.281
Token was
Token ID373
Feature activation+7.76e-01

Pos logit contributions
 Debor+1.508
+1.327
+1.261
 MSM+1.255
 unsus+1.244
Neg logit contributions
grain-1.174
urdue-1.122
ellar-1.120
 Windsor-1.087
font-1.076
Token heard
Token ID2982
Feature activation+5.67e-01

Pos logit contributions
 Debor+0.682
+0.609
+0.579
 MSM+0.576
 unsus+0.566
Neg logit contributions
grain-0.485
urdue-0.462
ellar-0.461
 Windsor-0.449
font-0.442
Token
Token ID198
Feature activation-1.78e+00

Pos logit contributions
grain+1.468
ellar+1.406
urdue+1.397
 Windsor+1.389
font+1.363
Neg logit contributions
 Debor-1.524
-1.341
-1.264
 MSM-1.237
-1.228
Token
Token ID198
Feature activation-1.46e+00

Pos logit contributions
grain+1.314
urdue+1.259
ellar+1.256
 Windsor+1.233
font+1.217
Neg logit contributions
 Debor-1.359
-1.195
-1.123
 MSM-1.115
 unsus-1.092
TokenD
Token ID35
Feature activation-1.82e-01

Pos logit contributions
grain+1.035
ellar+0.982
urdue+0.979
 Windsor+0.960
font+0.958
Neg logit contributions
 Debor-1.170
-1.019
 MSM-0.961
-0.960
 unsus-0.949
TokenDoS
Token ID46498
Feature activation-3.12e-01

Pos logit contributions
grain+0.122
urdue+0.117
ellar+0.116
 Windsor+0.114
font+0.112
Neg logit contributions
 Debor-0.152
-0.135
-0.128
 MSM-0.127
 unsus-0.124
Token Mit
Token ID11707
Feature activation+8.10e+00

Pos logit contributions
grain+0.244
urdue+0.235
ellar+0.234
 Windsor+0.231
font+0.227
Neg logit contributions
 Debor-0.225
-0.196
-0.184
 MSM-0.182
 unsus-0.178
Tokenigation
Token ID7065
Feature activation+8.74e+00

Pos logit contributions
 Debor+6.638
+5.795
 MSM+5.539
+5.506
+5.298
Neg logit contributions
grain-5.006
urdue-4.934
 Windsor-4.705
ellar-4.693
afety-4.522
Token
Token ID784
Feature activation+2.16e+00

Pos logit contributions
 Debor+6.601
+5.735
 MSM+5.616
+5.250
 Swordsman+5.222
Neg logit contributions
grain-6.082
ellar-6.045
urdue-5.994
afety-5.650
 Windsor-5.641
Token No
Token ID1400
Feature activation+4.34e+00

Pos logit contributions
 Debor+1.732
+1.531
 MSM+1.447
+1.444
 unsus+1.405
Neg logit contributions
grain-1.504
urdue-1.445
ellar-1.439
 Windsor-1.400
font-1.385
Token Silver
Token ID7698
Feature activation+2.89e+00

Pos logit contributions
 Debor+3.521
+3.103
 MSM+3.002
+2.958
 unsus+2.894
Neg logit contributions
grain-2.902
urdue-2.819
ellar-2.772
 Windsor-2.700
font-2.674
Token Bullet
Token ID18003
Feature activation+2.58e+00

Pos logit contributions
 Debor+2.501
+2.224
 MSM+2.110
+2.085
 unsus+2.035
Neg logit contributions
grain-1.802
urdue-1.798
ellar-1.764
 Windsor-1.674
afety-1.662
Token
Token ID198
Feature activation+1.19e+00

Pos logit contributions
 Debor+1.938
+1.698
 MSM+1.600
+1.588
 unsus+1.544
Neg logit contributions
grain-1.919
urdue-1.859
ellar-1.851
 Windsor-1.798
font-1.776
Tokenv
Token ID85
Feature activation+3.10e+00

Pos logit contributions
 Debor+2.181
+1.890
+1.795
 MSM+1.759
 unsus+1.697
Neg logit contributions
grain-2.657
urdue-2.615
ellar-2.607
 Windsor-2.563
afety-2.548
Token2
Token ID17
Feature activation+2.74e+00

Pos logit contributions
 Debor+1.895
+1.649
+1.566
 MSM+1.499
KEY+1.453
Neg logit contributions
grain-2.643
urdue-2.603
ellar-2.582
afety-2.549
 Windsor-2.535
Token.
Token ID764
Feature activation+4.61e+00

Pos logit contributions
 Debor+1.712
+1.469
+1.366
 MSM+1.366
+1.285
Neg logit contributions
grain-2.342
urdue-2.291
ellar-2.274
afety-2.217
 Windsor-2.209
Token COL
Token ID20444
Feature activation+5.11e+00

Pos logit contributions
 Debor+3.551
+3.159
 MSM+3.024
+2.922
 melanch+2.863
Neg logit contributions
grain-3.265
urdue-3.151
ellar-3.151
 Windsor-3.051
afety-3.026
TokenOR
Token ID1581
Feature activation+6.26e+00

Pos logit contributions
 Debor+3.435
+3.057
+2.896
 MSM+2.848
KEY+2.842
Neg logit contributions
grain-3.953
urdue-3.922
ellar-3.834
afety-3.822
 Windsor-3.742
Token_
Token ID62
Feature activation+8.62e+00

Pos logit contributions
 Debor+3.767
+3.369
+3.184
KEY+3.144
 MSM+3.093
Neg logit contributions
grain-5.181
urdue-5.097
ellar-5.048
afety-5.014
 Windsor-4.891
TokenB
Token ID33
Feature activation+3.90e+00

Pos logit contributions
 Debor+4.122
+3.718
KEY+3.370
 MSM+3.345
+3.278
Neg logit contributions
grain-8.114
ellar-8.028
urdue-8.027
afety-7.906
 Windsor-7.767
TokenGR
Token ID10761
Feature activation+6.75e+00

Pos logit contributions
 Debor+2.029
+1.786
 MSM+1.598
+1.593
KEY+1.575
Neg logit contributions
grain-3.608
urdue-3.561
ellar-3.531
afety-3.498
 Windsor-3.479
Token2
Token ID17
Feature activation+7.46e+00

Pos logit contributions
 Debor+3.644
+3.278
+3.093
KEY+3.045
 MSM+2.953
Neg logit contributions
grain-5.914
urdue-5.911
ellar-5.881
afety-5.871
 Windsor-5.651
TokenG
Token ID38
Feature activation+3.44e+00

Pos logit contributions
 Debor+4.434
+4.101
KEY+3.909
 MSM+3.844
+3.753
Neg logit contributions
grain-5.996
ellar-5.996
urdue-5.982
afety-5.921
ossession-5.642
TokenRAY
Token ID30631
Feature activation+6.26e+00

Pos logit contributions
 Debor+2.456
+2.198
+2.025
 MSM+2.022
KEY+2.015
Neg logit contributions
grain-2.558
urdue-2.501
afety-2.470
ellar-2.464
 Windsor-2.444
Tokentrans
Token ID7645
Feature activation+2.51e+00

Pos logit contributions
grain+0.307
ellar+0.294
urdue+0.293
 Windsor+0.288
font+0.285
Neg logit contributions
 Debor-0.294
-0.256
-0.240
 MSM-0.239
 unsus-0.234
Tokencript
Token ID6519
Feature activation+4.62e+00

Pos logit contributions
 Debor+2.593
+2.354
+2.291
 MSM+2.270
 unsus+2.217
Neg logit contributions
grain-1.107
urdue-1.054
ellar-1.051
 Windsor-1.019
afety-0.959
Tokens
Token ID82
Feature activation+1.95e+00

Pos logit contributions
 Debor+3.154
+2.820
+2.643
 MSM+2.560
+2.532
Neg logit contributions
grain-3.563
urdue-3.516
ellar-3.475
 Windsor-3.441
afety-3.362
Token/
Token ID14
Feature activation+2.46e+00

Pos logit contributions
 Debor+1.522
+1.345
+1.267
 MSM+1.258
+1.222
Neg logit contributions
grain-1.406
urdue-1.347
ellar-1.342
 Windsor-1.317
font-1.291
Tokensc
Token ID1416
Feature activation+2.28e+00

Pos logit contributions
 Debor+2.281
+2.069
+1.976
 MSM+1.955
+1.912
Neg logit contributions
grain-1.372
urdue-1.331
ellar-1.307
 Windsor-1.284
afety-1.235
Tokenaling
Token ID4272
Feature activation+8.60e+00

Pos logit contributions
 Debor+1.782
+1.573
+1.499
 MSM+1.492
 unsus+1.455
Neg logit contributions
grain-1.563
urdue-1.520
 Windsor-1.487
ellar-1.483
font-1.447
Tokenbitcoin
Token ID35395
Feature activation+8.70e-01

Pos logit contributions
 Debor+3.421
+2.668
+2.491
 MSM+2.395
KEY+2.254
Neg logit contributions
urdue-8.671
grain-8.644
ellar-8.564
 Windsor-8.529
 Craft-8.294
Token/
Token ID14
Feature activation+3.02e+00

Pos logit contributions
 Debor+0.690
+0.610
+0.575
 MSM+0.572
 unsus+0.558
Neg logit contributions
grain-0.616
urdue-0.589
ellar-0.588
 Windsor-0.576
font-0.567
Tokenh
Token ID71
Feature activation+1.87e+00

Pos logit contributions
 Debor+2.392
+2.131
+2.003
 MSM+1.985
+1.944
Neg logit contributions
grain-2.094
urdue-2.039
ellar-2.026
 Windsor-1.984
font-1.920
Tokenong
Token ID506
Feature activation+3.36e+00

Pos logit contributions
 Debor+1.889
+1.725
+1.663
 MSM+1.639
 unsus+1.630
Neg logit contributions
grain-0.867
urdue-0.825
ellar-0.822
 Windsor-0.813
font-0.763
Token-
Token ID12
Feature activation+2.44e+00

Pos logit contributions
 Debor+2.629
+2.333
+2.217
 MSM+2.194
 unsus+2.116
Neg logit contributions
grain-2.336
urdue-2.268
ellar-2.250
 Windsor-2.215
afety-2.170
Tokenara
Token ID3301
Feature activation-6.30e-01

Pos logit contributions
 Debor+0.435
+0.387
+0.366
 MSM+0.364
 unsus+0.356
Neg logit contributions
grain-0.358
urdue-0.342
ellar-0.341
 Windsor-0.333
font-0.328
Token P
Token ID350
Feature activation-3.00e-01

Pos logit contributions
grain+0.429
urdue+0.410
ellar+0.409
 Windsor+0.401
font+0.394
Neg logit contributions
 Debor-0.517
-0.460
-0.434
 MSM-0.432
 unsus-0.423
Token217
Token ID24591
Feature activation+1.16e+00

Pos logit contributions
grain+0.222
urdue+0.213
ellar+0.212
 Windsor+0.208
font+0.205
Neg logit contributions
 Debor-0.229
-0.201
-0.189
 MSM-0.188
 unsus-0.184
Token Gibson
Token ID20400
Feature activation+1.37e+00

Pos logit contributions
 Debor+0.905
+0.801
+0.754
 MSM+0.750
 unsus+0.731
Neg logit contributions
grain-0.831
urdue-0.796
ellar-0.794
 Windsor-0.776
font-0.766
Token came
Token ID1625
Feature activation+1.24e+00

Pos logit contributions
 Debor+1.069
+0.945
+0.888
 MSM+0.888
 unsus+0.866
Neg logit contributions
grain-0.986
urdue-0.944
ellar-0.943
 Windsor-0.915
font-0.909
Token fourth
Token ID5544
Feature activation+8.37e+00

Pos logit contributions
 Debor+0.913
+0.799
+0.750
 MSM+0.744
 unsus+0.730
Neg logit contributions
grain-0.953
urdue-0.913
ellar-0.912
 Windsor-0.890
font-0.881
Token,
Token ID11
Feature activation+2.40e+00

Pos logit contributions
 Debor+5.347
+4.450
 unsus+4.315
 MSM+4.260
+4.158
Neg logit contributions
grain-6.918
ellar-6.724
urdue-6.670
afety-6.506
ˈ-6.400
Token ahead
Token ID4058
Feature activation+4.76e+00

Pos logit contributions
 Debor+1.805
+1.570
+1.484
 MSM+1.480
 unsus+1.451
Neg logit contributions
grain-1.801
ellar-1.729
urdue-1.722
 Windsor-1.661
afety-1.661
Token of
Token ID286
Feature activation+8.38e-01

Pos logit contributions
 Debor+3.428
+2.959
+2.810
 MSM+2.780
+2.726
Neg logit contributions
grain-3.683
urdue-3.530
ellar-3.520
font-3.412
afety-3.406
Token the
Token ID262
Feature activation+4.05e-01

Pos logit contributions
 Debor+0.658
+0.579
+0.546
 MSM+0.544
 unsus+0.531
Neg logit contributions
grain-0.604
urdue-0.578
ellar-0.576
 Windsor-0.561
font-0.556
Token fastest
Token ID14162
Feature activation+1.06e+00

Pos logit contributions
 Debor+0.319
+0.281
+0.265
 MSM+0.264
 unsus+0.258
Neg logit contributions
grain-0.290
urdue-0.278
ellar-0.277
 Windsor-0.270
font-0.267
Token noted
Token ID4367
Feature activation-7.91e-01

Pos logit contributions
 Debor+0.398
+0.363
+0.346
 MSM+0.344
 unsus+0.338
Neg logit contributions
grain-0.192
urdue-0.180
ellar-0.180
 Windsor-0.174
font-0.171
Token.
Token ID13
Feature activation+2.42e-01

Pos logit contributions
grain+0.581
urdue+0.561
ellar+0.556
 Windsor+0.548
font+0.540
Neg logit contributions
 Debor-0.602
-0.529
-0.501
 MSM-0.496
 unsus-0.486
Token<|endoftext|>
Token ID50256
Feature activation+1.14e+00

Pos logit contributions
 Debor+0.187
+0.164
+0.154
 MSM+0.154
+0.149
Neg logit contributions
grain-0.178
ellar-0.170
urdue-0.170
 Windsor-0.166
font-0.164
TokenT
Token ID51
Feature activation+8.70e-01

Pos logit contributions
 Debor+0.900
+0.802
+0.757
 MSM+0.748
+0.730
Neg logit contributions
grain-0.801
urdue-0.771
ellar-0.768
 Windsor-0.752
font-0.735
TokenEL
Token ID3698
Feature activation-4.18e+00

Pos logit contributions
 Debor+0.712
+0.632
+0.597
 MSM+0.593
 unsus+0.582
Neg logit contributions
grain-0.594
urdue-0.566
ellar-0.564
 Windsor-0.553
font-0.545
Token AV
Token ID14661
Feature activation+8.26e+00

Pos logit contributions
grain+2.852
 Windsor+2.774
urdue+2.722
font+2.710
ellar+2.658
Neg logit contributions
 Debor-3.411
-2.900
 unsus-2.749
-2.738
-2.700
TokenIV
Token ID3824
Feature activation+4.03e+00

Pos logit contributions
 Debor+1.411
+0.838
+0.297
 unsus+0.295
+0.268
Neg logit contributions
grain-10.760
urdue-10.418
font-10.282
afety-10.189
ellar-10.182
Token
Token ID784
Feature activation+1.90e+00

Pos logit contributions
 Debor+3.264
+2.891
 MSM+2.726
+2.699
+2.646
Neg logit contributions
grain-2.776
ellar-2.654
urdue-2.653
 Windsor-2.561
font-2.531
Token A
Token ID317
Feature activation+1.43e+00

Pos logit contributions
 Debor+1.490
+1.301
 MSM+1.232
+1.223
 unsus+1.178
Neg logit contributions
grain-1.376
ellar-1.321
urdue-1.313
 Windsor-1.264
font-1.260
Token clandestine
Token ID39903
Feature activation-5.37e-01

Pos logit contributions
 Debor+1.106
+0.973
+0.918
 MSM+0.913
 unsus+0.890
Neg logit contributions
grain-1.044
ellar-0.999
urdue-0.996
 Windsor-0.967
font-0.965
Token Israeli
Token ID6085
Feature activation-1.99e+00

Pos logit contributions
grain+0.417
urdue+0.401
ellar+0.400
 Windsor+0.396
font+0.388
Neg logit contributions
 Debor-0.386
-0.339
-0.317
 MSM-0.312
-0.307
Token day
Token ID1110
Feature activation+2.04e+00

Pos logit contributions
 Debor+1.593
+1.409
+1.332
 MSM+1.327
 unsus+1.296
Neg logit contributions
grain-1.417
urdue-1.368
ellar-1.365
 Windsor-1.322
font-1.312
Token of
Token ID286
Feature activation+7.81e-01

Pos logit contributions
 Debor+1.582
+1.390
+1.309
 MSM+1.304
 unsus+1.272
Neg logit contributions
grain-1.477
ellar-1.420
urdue-1.420
 Windsor-1.380
font-1.365
Token the
Token ID262
Feature activation-6.94e-01

Pos logit contributions
 Debor+0.605
+0.533
+0.502
 MSM+0.499
 unsus+0.488
Neg logit contributions
grain-0.568
urdue-0.544
ellar-0.543
 Windsor-0.532
font-0.525
Token year
Token ID614
Feature activation+2.65e+00

Pos logit contributions
grain+0.502
urdue+0.481
ellar+0.478
 Windsor+0.473
font+0.464
Neg logit contributions
 Debor-0.538
-0.476
-0.447
 MSM-0.443
 unsus-0.435
Token was
Token ID373
Feature activation+2.48e+00

Pos logit contributions
 Debor+2.069
+1.818
+1.718
 MSM+1.704
 unsus+1.662
Neg logit contributions
grain-1.896
ellar-1.823
urdue-1.820
 Windsor-1.760
font-1.749
Token cold
Token ID4692
Feature activation+8.21e+00

Pos logit contributions
 Debor+1.925
+1.676
+1.581
 MSM+1.575
 unsus+1.559
Neg logit contributions
grain-1.811
urdue-1.746
ellar-1.739
font-1.670
afety-1.665
Token and
Token ID290
Feature activation+2.90e+00

Pos logit contributions
 Debor+5.648
+4.763
 melanch+4.567
 unsus+4.506
 MSM+4.466
Neg logit contributions
grain-6.377
ellar-6.207
urdue-6.174
 Windsor-6.040
afety-5.939
Token over
Token ID625
Feature activation+6.82e-01

Pos logit contributions
 Debor+2.223
+1.940
+1.835
 MSM+1.824
 unsus+1.799
Neg logit contributions
grain-2.132
urdue-2.056
ellar-2.042
 Windsor-1.985
font-1.971
Tokencast
Token ID2701
Feature activation+2.27e+00

Pos logit contributions
 Debor+0.530
+0.466
 MSM+0.439
+0.439
+0.428
Neg logit contributions
grain-0.496
urdue-0.473
ellar-0.471
 Windsor-0.465
font-0.460
Token,
Token ID11
Feature activation+2.84e+00

Pos logit contributions
 Debor+1.702
+1.490
+1.397
 MSM+1.391
 unsus+1.361
Neg logit contributions
grain-1.709
urdue-1.640
ellar-1.636
 Windsor-1.601
font-1.581
Token but
Token ID475
Feature activation+1.26e+00

Pos logit contributions
 Debor+2.193
+1.915
+1.808
 MSM+1.797
 unsus+1.774
Neg logit contributions
grain-2.071
urdue-1.991
ellar-1.988
 Windsor-1.928
font-1.910
Token network
Token ID3127
Feature activation-2.00e+00

Pos logit contributions
 Debor+0.933
+0.805
+0.748
 MSM+0.741
 unsus+0.722
Neg logit contributions
grain-1.174
urdue-1.132
ellar-1.129
 Windsor-1.111
font-1.097
Token
Token ID198
Feature activation-1.78e+00

Pos logit contributions
grain+1.468
ellar+1.406
urdue+1.397
 Windsor+1.389
font+1.363
Neg logit contributions
 Debor-1.524
-1.341
-1.264
 MSM-1.237
-1.228
Token
Token ID198
Feature activation-1.46e+00

Pos logit contributions
grain+1.314
urdue+1.259
ellar+1.256
 Windsor+1.233
font+1.217
Neg logit contributions
 Debor-1.359
-1.195
-1.123
 MSM-1.115
 unsus-1.092
TokenD
Token ID35
Feature activation-1.82e-01

Pos logit contributions
grain+1.035
ellar+0.982
urdue+0.979
 Windsor+0.960
font+0.958
Neg logit contributions
 Debor-1.170
-1.019
 MSM-0.961
-0.960
 unsus-0.949
TokenDoS
Token ID46498
Feature activation-3.12e-01

Pos logit contributions
grain+0.122
urdue+0.117
ellar+0.116
 Windsor+0.114
font+0.112
Neg logit contributions
 Debor-0.152
-0.135
-0.128
 MSM-0.127
 unsus-0.124
Token Mit
Token ID11707
Feature activation+8.10e+00

Pos logit contributions
grain+0.244
urdue+0.235
ellar+0.234
 Windsor+0.231
font+0.227
Neg logit contributions
 Debor-0.225
-0.196
-0.184
 MSM-0.182
 unsus-0.178
Tokenigation
Token ID7065
Feature activation+8.74e+00

Pos logit contributions
 Debor+6.638
+5.795
 MSM+5.539
+5.506
+5.298
Neg logit contributions
grain-5.006
urdue-4.934
 Windsor-4.705
ellar-4.693
afety-4.522
Token
Token ID784
Feature activation+2.16e+00

Pos logit contributions
 Debor+6.601
+5.735
 MSM+5.616
+5.250
 Swordsman+5.222
Neg logit contributions
grain-6.082
ellar-6.045
urdue-5.994
afety-5.650
 Windsor-5.641
Token No
Token ID1400
Feature activation+4.34e+00

Pos logit contributions
 Debor+1.732
+1.531
 MSM+1.447
+1.444
 unsus+1.405
Neg logit contributions
grain-1.504
urdue-1.445
ellar-1.439
 Windsor-1.400
font-1.385
Token Silver
Token ID7698
Feature activation+2.89e+00

Pos logit contributions
 Debor+3.521
+3.103
 MSM+3.002
+2.958
 unsus+2.894
Neg logit contributions
grain-2.902
urdue-2.819
ellar-2.772
 Windsor-2.700
font-2.674
Token Bullet
Token ID18003
Feature activation+2.58e+00

Pos logit contributions
 Debor+2.501
+2.224
 MSM+2.110
+2.085
 unsus+2.035
Neg logit contributions
grain-1.802
urdue-1.798
ellar-1.764
 Windsor-1.674
afety-1.662
Token problems
Token ID2761
Feature activation-3.06e-01

Pos logit contributions
 Debor+0.436
+0.378
+0.353
 MSM+0.351
 unsus+0.343
Neg logit contributions
grain-0.504
urdue-0.485
ellar-0.484
 Windsor-0.475
font-0.469
Token.
Token ID13
Feature activation-5.64e-01

Pos logit contributions
grain+0.224
urdue+0.215
ellar+0.214
 Windsor+0.210
font+0.207
Neg logit contributions
 Debor-0.235
-0.207
-0.195
 MSM-0.193
 unsus-0.189
Token I
Token ID314
Feature activation-4.50e-01

Pos logit contributions
grain+0.410
urdue+0.392
ellar+0.391
 Windsor+0.385
font+0.379
Neg logit contributions
 Debor-0.438
-0.386
-0.364
 MSM-0.361
 unsus-0.354
Token've
Token ID1053
Feature activation+8.05e-01

Pos logit contributions
grain+0.306
urdue+0.292
ellar+0.291
 Windsor+0.286
font+0.281
Neg logit contributions
 Debor-0.371
-0.329
-0.311
 MSM-0.309
 unsus-0.303
Token Mac
Token ID4100
Feature activation-7.62e-01

Pos logit contributions
 Debor+0.669
+0.592
+0.560
 MSM+0.559
 unsus+0.551
Neg logit contributions
grain-0.542
ellar-0.518
urdue-0.518
 Windsor-0.504
font-0.497
TokenGy
Token ID44802
Feature activation+8.06e+00

Pos logit contributions
grain+0.589
urdue+0.565
ellar+0.564
 Windsor+0.554
font+0.549
Neg logit contributions
 Debor-0.554
-0.486
-0.455
 MSM-0.453
 unsus-0.441
Tokenvered
Token ID21917
Feature activation+8.81e-01

Pos logit contributions
 Debor+5.625
+4.620
+4.603
 unsus+4.455
 MSM+4.392
Neg logit contributions
urdue-5.790
 Windsor-5.649
grain-5.528
ellar-5.442
afety-5.439
Token mental
Token ID5110
Feature activation-6.02e-01

Pos logit contributions
 Debor+0.687
+0.604
+0.569
 MSM+0.567
 unsus+0.555
Neg logit contributions
grain-0.637
urdue-0.610
ellar-0.609
 Windsor-0.595
font-0.587
Token upgrades
Token ID16608
Feature activation+2.03e+00

Pos logit contributions
grain+0.445
urdue+0.427
ellar+0.426
 Windsor+0.418
font+0.412
Neg logit contributions
 Debor-0.459
-0.404
-0.379
 MSM-0.377
 unsus-0.368
Token out
Token ID503
Feature activation+3.97e-01

Pos logit contributions
 Debor+1.558
+1.372
 MSM+1.284
+1.282
 unsus+1.270
Neg logit contributions
grain-1.480
ellar-1.420
urdue-1.418
 Windsor-1.382
font-1.358
Token of
Token ID286
Feature activation-1.07e+00

Pos logit contributions
 Debor+0.309
+0.273
+0.257
 MSM+0.255
 unsus+0.249
Neg logit contributions
grain-0.287
urdue-0.274
ellar-0.274
 Windsor-0.269
font-0.265
Token c
Token ID269
Feature activation+2.20e+00

Pos logit contributions
 Debor+1.272
+1.143
 MSM+1.099
+1.093
 unsus+1.074
Neg logit contributions
grain-0.744
urdue-0.705
ellar-0.699
 Windsor-0.677
afety-0.669
Tokenv
Token ID85
Feature activation+2.86e+00

Pos logit contributions
 Debor+1.486
+1.292
+1.228
 MSM+1.199
 unsus+1.160
Neg logit contributions
grain-1.743
urdue-1.703
ellar-1.693
 Windsor-1.670
afety-1.655
Token2
Token ID17
Feature activation+2.56e+00

Pos logit contributions
 Debor+1.747
+1.509
+1.450
 MSM+1.380
KEY+1.335
Neg logit contributions
grain-2.448
urdue-2.407
ellar-2.391
afety-2.361
 Windsor-2.342
Token.
Token ID764
Feature activation+3.22e+00

Pos logit contributions
 Debor+1.614
+1.374
+1.288
 MSM+1.281
+1.203
Neg logit contributions
grain-2.199
urdue-2.146
ellar-2.134
afety-2.075
 Windsor-2.068
Token Ga
Token ID12822
Feature activation+5.15e+00

Pos logit contributions
 Debor+2.480
+2.170
 MSM+2.085
+2.047
 melanch+2.017
Neg logit contributions
grain-2.313
ellar-2.237
urdue-2.225
 Windsor-2.163
afety-2.135
Tokenussian
Token ID31562
Feature activation+8.05e+00

Pos logit contributions
 Debor+2.176
+1.836
+1.697
 MSM+1.561
 unsus+1.498
Neg logit contributions
grain-5.129
 Windsor-5.123
urdue-5.063
afety-4.976
ellar-4.949
TokenBl
Token ID3629
Feature activation+3.12e+00

Pos logit contributions
 Debor+3.364
+2.854
+2.649
BM+2.382
+2.314
Neg logit contributions
grain-8.164
ellar-8.079
urdue-8.067
afety-7.988
 Windsor-7.782
Tokenur
Token ID333
Feature activation+4.06e+00

Pos logit contributions
 Debor+2.772
+2.500
+2.473
 MSM+2.368
 unsus+2.357
Neg logit contributions
grain-1.687
urdue-1.660
ellar-1.645
 Windsor-1.639
afety-1.618
Token (
Token ID357
Feature activation+4.97e+00

Pos logit contributions
 Debor+2.844
+2.523
+2.416
 MSM+2.384
+2.271
Neg logit contributions
grain-3.071
ellar-3.029
urdue-3.022
afety-2.952
 Windsor-2.868
Token gray
Token ID12768
Feature activation+2.06e+00

Pos logit contributions
 Debor+2.738
+2.097
 MSM+2.083
 unsus+2.014
 melanch+1.998
Neg logit contributions
grain-4.533
afety-4.482
ellar-4.476
urdue-4.463
 Windsor-4.319
Token,
Token ID837
Feature activation+2.73e+00

Pos logit contributions
 Debor+1.497
+1.315
+1.246
 MSM+1.241
 unsus+1.185
Neg logit contributions
grain-1.547
ellar-1.511
urdue-1.504
afety-1.471
 Windsor-1.454
Token is
Token ID318
Feature activation+1.73e+00

Pos logit contributions
 Debor+0.733
+0.655
+0.621
 MSM+0.618
 unsus+0.606
Neg logit contributions
grain-0.542
urdue-0.516
ellar-0.514
 Windsor-0.503
font-0.495
Token officially
Token ID8720
Feature activation+4.28e+00

Pos logit contributions
 Debor+1.363
+1.204
+1.137
 MSM+1.133
 unsus+1.109
Neg logit contributions
grain-1.226
urdue-1.175
ellar-1.170
 Windsor-1.147
font-1.130
Token supported
Token ID4855
Feature activation+2.21e+00

Pos logit contributions
 Debor+2.656
+2.244
 MSM+2.133
+2.075
 unsus+2.059
Neg logit contributions
grain-3.746
urdue-3.609
ellar-3.582
 Windsor-3.525
afety-3.512
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
 Debor+1.647
+1.444
+1.349
 MSM+1.347
 unsus+1.314
Neg logit contributions
grain-1.677
ellar-1.606
urdue-1.602
 Windsor-1.573
font-1.542
Token For
Token ID1114
Feature activation+7.99e-01

Pos logit contributions
grain+0.099
urdue+0.095
ellar+0.095
 Windsor+0.093
font+0.092
Neg logit contributions
 Debor-0.109
-0.096
-0.090
 MSM-0.090
 unsus-0.088
Token now
Token ID783
Feature activation+7.91e+00

Pos logit contributions
 Debor+0.629
+0.556
+0.524
 MSM+0.523
 unsus+0.509
Neg logit contributions
grain-0.568
urdue-0.548
ellar-0.544
 Windsor-0.533
font-0.525
Token,
Token ID11
Feature activation+2.21e+00

Pos logit contributions
 Debor+5.239
+4.511
 MSM+4.320
+4.226
 melanch+4.093
Neg logit contributions
grain-6.297
urdue-6.161
ellar-6.137
 Windsor-5.945
afety-5.920
Token the
Token ID262
Feature activation+1.93e+00

Pos logit contributions
 Debor+1.646
+1.440
+1.355
 MSM+1.354
 unsus+1.313
Neg logit contributions
grain-1.672
urdue-1.615
ellar-1.609
 Windsor-1.571
font-1.550
Token lens
Token ID10317
Feature activation-6.45e-01

Pos logit contributions
 Debor+1.525
+1.346
 MSM+1.278
+1.269
 unsus+1.241
Neg logit contributions
grain-1.359
urdue-1.313
ellar-1.305
 Windsor-1.273
font-1.256
Token is
Token ID318
Feature activation+2.86e+00

Pos logit contributions
grain+0.410
urdue+0.388
ellar+0.388
 Windsor+0.379
font+0.374
Neg logit contributions
 Debor-0.559
-0.499
-0.474
 MSM-0.469
 unsus-0.463
Token excellent
Token ID6275
Feature activation+2.68e+00

Pos logit contributions
 Debor+2.190
+1.931
 MSM+1.821
+1.812
 unsus+1.766
Neg logit contributions
grain-2.080
urdue-2.010
ellar-2.002
 Windsor-1.956
font-1.927
Token finding
Token ID4917
Feature activation-1.71e+00

Pos logit contributions
grain+0.114
urdue+0.109
ellar+0.109
 Windsor+0.107
font+0.105
Neg logit contributions
 Debor-0.137
-0.122
-0.115
 MSM-0.114
 unsus-0.112
Token a
Token ID257
Feature activation-3.82e-01

Pos logit contributions
grain+1.261
urdue+1.209
ellar+1.201
 Windsor+1.196
font+1.168
Neg logit contributions
 Debor-1.296
-1.148
-1.077
 MSM-1.058
-1.045
Token safety
Token ID3747
Feature activation-1.44e+00

Pos logit contributions
grain+0.312
urdue+0.300
ellar+0.298
 Windsor+0.295
font+0.290
Neg logit contributions
 Debor-0.262
-0.227
-0.211
 MSM-0.209
 unsus-0.204
Token.
Token ID13
Feature activation-2.09e+00

Pos logit contributions
grain+1.006
urdue+0.962
ellar+0.957
 Windsor+0.948
font+0.935
Neg logit contributions
 Debor-1.154
-1.011
-0.966
 MSM-0.949
-0.936
Token For
Token ID1114
Feature activation-2.77e-02

Pos logit contributions
grain+1.414
urdue+1.352
ellar+1.339
 Windsor+1.329
font+1.303
Neg logit contributions
 Debor-1.713
-1.533
-1.445
 MSM-1.429
 unsus-1.423
Token now
Token ID783
Feature activation+7.88e+00

Pos logit contributions
grain+0.020
urdue+0.019
ellar+0.019
 Windsor+0.018
font+0.018
Neg logit contributions
 Debor-0.022
-0.019
-0.018
 MSM-0.018
 unsus-0.018
Token,
Token ID11
Feature activation+2.00e+00

Pos logit contributions
 Debor+5.354
+4.619
 MSM+4.358
+4.329
+4.165
Neg logit contributions
grain-6.258
ellar-6.065
urdue-5.939
 Windsor-5.770
afety-5.768
Token coaches
Token ID11070
Feature activation+1.39e+00

Pos logit contributions
 Debor+1.570
+1.373
 MSM+1.299
+1.298
 unsus+1.263
Neg logit contributions
grain-1.434
ellar-1.378
urdue-1.374
 Windsor-1.335
font-1.321
Token have
Token ID423
Feature activation+6.03e-01

Pos logit contributions
 Debor+1.164
+1.034
+0.977
 MSM+0.973
 unsus+0.953
Neg logit contributions
grain-0.931
urdue-0.888
ellar-0.887
 Windsor-0.867
font-0.854
Token David
Token ID3271
Feature activation-2.15e+00

Pos logit contributions
 Debor+0.488
+0.434
+0.409
 MSM+0.406
 unsus+0.398
Neg logit contributions
grain-0.417
urdue-0.399
ellar-0.397
 Windsor-0.391
font-0.384
Token Brut
Token ID30291
Feature activation-1.36e+00

Pos logit contributions
grain+1.578
urdue+1.513
ellar+1.509
 Windsor+1.482
font+1.460
Neg logit contributions
 Debor-1.644
-1.448
-1.361
 MSM-1.352
 unsus-1.322
Token two
Token ID734
Feature activation+1.56e-01

Pos logit contributions
grain+0.537
urdue+0.513
ellar+0.512
 Windsor+0.504
font+0.496
Neg logit contributions
 Debor-0.576
-0.509
-0.477
 MSM-0.475
 unsus-0.464
Token options
Token ID3689
Feature activation+3.19e+00

Pos logit contributions
 Debor+0.104
+0.090
+0.084
 MSM+0.083
 unsus+0.081
Neg logit contributions
grain-0.130
urdue-0.125
ellar-0.125
 Windsor-0.123
font-0.121
Token.
Token ID13
Feature activation+2.64e+00

Pos logit contributions
 Debor+2.268
+1.986
+1.840
 MSM+1.830
 unsus+1.781
Neg logit contributions
grain-2.508
ellar-2.412
urdue-2.404
 Windsor-2.351
font-2.300
Token The
Token ID383
Feature activation+2.67e+00

Pos logit contributions
 Debor+2.266
+2.007
+1.912
 MSM+1.895
+1.835
Neg logit contributions
grain-1.715
ellar-1.633
urdue-1.631
 Windsor-1.573
afety-1.556
Token first
Token ID717
Feature activation+2.80e+00

Pos logit contributions
 Debor+1.912
+1.658
+1.559
 MSM+1.551
 unsus+1.510
Neg logit contributions
grain-2.085
urdue-2.011
ellar-2.007
 Windsor-1.959
afety-1.925
Token is
Token ID318
Feature activation+7.79e+00

Pos logit contributions
 Debor+2.295
+2.037
+1.926
 MSM+1.921
 unsus+1.874
Neg logit contributions
grain-1.884
ellar-1.810
urdue-1.809
 Windsor-1.755
font-1.722
Token an
Token ID281
Feature activation+3.24e+00

Pos logit contributions
 Debor+5.255
+4.616
+4.354
 MSM+4.263
 unsus+4.135
Neg logit contributions
grain-6.077
urdue-5.873
ellar-5.818
 Windsor-5.687
afety-5.536
Token illegal
Token ID5293
Feature activation-2.76e-01

Pos logit contributions
 Debor+2.397
+2.104
+1.968
 MSM+1.965
 unsus+1.932
Neg logit contributions
grain-2.469
urdue-2.381
ellar-2.356
 Windsor-2.315
font-2.272
Token hack
Token ID8156
Feature activation-1.53e+00

Pos logit contributions
grain+0.202
urdue+0.194
ellar+0.194
 Windsor+0.190
font+0.188
Neg logit contributions
 Debor-0.211
-0.186
-0.174
 MSM-0.174
 unsus-0.170
Token to
Token ID284
Feature activation-8.79e-01

Pos logit contributions
grain+1.066
urdue+1.025
ellar+1.022
 Windsor+0.998
font+0.992
Neg logit contributions
 Debor-1.227
-1.084
-1.021
 MSM-1.020
 unsus-0.995
Token remove
Token ID4781
Feature activation-1.40e+00

Pos logit contributions
grain+0.596
urdue+0.569
ellar+0.567
 Windsor+0.557
font+0.548
Neg logit contributions
 Debor-0.724
-0.643
-0.607
 MSM-0.604
 unsus-0.590
Token Virginia
Token ID6025
Feature activation+1.64e+00

Pos logit contributions
 Debor+0.561
+0.492
 MSM+0.467
+0.465
 unsus+0.452
Neg logit contributions
grain-0.519
ellar-0.495
urdue-0.495
 Windsor-0.479
font-0.479
Token.
Token ID13
Feature activation+1.29e+00

Pos logit contributions
 Debor+1.274
+1.116
 MSM+1.057
+1.042
 unsus+1.034
Neg logit contributions
grain-1.204
ellar-1.148
urdue-1.140
 Windsor-1.102
font-1.091
Token
Token ID198
Feature activation+1.52e+00

Pos logit contributions
 Debor+1.030
+0.906
 MSM+0.863
+0.855
+0.823
Neg logit contributions
grain-0.909
ellar-0.866
urdue-0.864
 Windsor-0.835
afety-0.829
Token
Token ID198
Feature activation+1.46e+00

Pos logit contributions
 Debor+1.039
+0.906
+0.856
 MSM+0.855
+0.808
Neg logit contributions
grain-1.214
urdue-1.179
ellar-1.178
afety-1.147
 Windsor-1.143
TokenDi
Token ID18683
Feature activation+3.02e+00

Pos logit contributions
 Debor+1.163
+1.043
+0.986
 MSM+0.977
+0.951
Neg logit contributions
grain-1.015
urdue-0.975
ellar-0.971
 Windsor-0.950
afety-0.931
Tokenplom
Token ID7302
Feature activation+7.69e+00

Pos logit contributions
 Debor+2.809
+2.545
 MSM+2.411
+2.402
 unsus+2.361
Neg logit contributions
grain-1.703
urdue-1.606
ellar-1.565
 Windsor-1.532
font-1.522
Tokenatic
Token ID1512
Feature activation+2.29e+00

Pos logit contributions
 Debor+5.443
+4.521
 MSM+4.329
+4.250
 unsus+4.178
Neg logit contributions
grain-5.852
urdue-5.605
ellar-5.530
 Windsor-5.470
font-5.390
Token cables
Token ID18018
Feature activation+3.51e-01

Pos logit contributions
 Debor+1.729
+1.498
 MSM+1.414
+1.407
 unsus+1.377
Neg logit contributions
grain-1.717
urdue-1.649
ellar-1.643
 Windsor-1.597
font-1.585
Token are
Token ID389
Feature activation-1.71e+00

Pos logit contributions
 Debor+0.285
+0.253
+0.239
 MSM+0.238
 unsus+0.233
Neg logit contributions
grain-0.242
urdue-0.232
ellar-0.231
 Windsor-0.226
font-0.223
Token internal
Token ID5387
Feature activation+1.65e+00

Pos logit contributions
grain+1.187
ellar+1.138
urdue+1.135
 Windsor+1.128
font+1.097
Neg logit contributions
 Debor-1.362
-1.226
-1.155
 MSM-1.126
-1.115
Token documents
Token ID4963
Feature activation+1.46e+00

Pos logit contributions
 Debor+1.323
+1.169
 MSM+1.104
+1.104
 unsus+1.076
Neg logit contributions
grain-1.154
urdue-1.104
ellar-1.099
 Windsor-1.074
font-1.060
Token_
Token ID62
Feature activation+3.78e+00

Pos logit contributions
 Debor+1.379
+1.219
+1.149
 MSM+1.142
 unsus+1.116
Neg logit contributions
grain-1.244
urdue-1.192
ellar-1.189
 Windsor-1.164
font-1.146
Tokenin
Token ID259
Feature activation+2.47e+00

Pos logit contributions
 Debor+2.943
+2.616
+2.468
 MSM+2.439
 unsus+2.389
Neg logit contributions
grain-2.656
urdue-2.585
ellar-2.576
 Windsor-2.521
font-2.431
Tokenjury
Token ID21871
Feature activation+3.65e+00

Pos logit contributions
 Debor+2.111
+1.887
+1.791
 MSM+1.781
 unsus+1.741
Neg logit contributions
grain-1.573
ellar-1.510
urdue-1.502
 Windsor-1.462
font-1.437
Token_
Token ID62
Feature activation+4.47e+00

Pos logit contributions
 Debor+2.743
+2.408
 MSM+2.254
+2.242
 unsus+2.176
Neg logit contributions
grain-2.720
ellar-2.613
urdue-2.608
 Windsor-2.531
font-2.494
Tokenpre
Token ID3866
Feature activation+5.06e+00

Pos logit contributions
 Debor+3.434
+3.070
+2.892
 MSM+2.853
 unsus+2.793
Neg logit contributions
grain-3.140
urdue-3.070
ellar-3.062
 Windsor-2.986
font-2.877
Tokenvention
Token ID4018
Feature activation+7.69e+00

Pos logit contributions
 Debor+3.614
+3.156
 MSM+2.963
+2.950
 unsus+2.836
Neg logit contributions
grain-3.811
ellar-3.761
urdue-3.753
 Windsor-3.599
afety-3.546
Token/
Token ID14
Feature activation+2.86e+00

Pos logit contributions
 Debor+5.364
+4.657
 MSM+4.428
+4.269
+4.149
Neg logit contributions
grain-5.876
ellar-5.696
urdue-5.655
 Windsor-5.423
font-5.336
Tokenkey
Token ID2539
Feature activation+3.54e+00

Pos logit contributions
 Debor+2.402
+2.151
+2.031
 MSM+2.025
 unsus+1.975
Neg logit contributions
grain-1.873
ellar-1.798
urdue-1.797
 Windsor-1.743
font-1.706
Token_
Token ID62
Feature activation+3.59e+00

Pos logit contributions
 Debor+2.645
+2.338
+2.190
 MSM+2.183
 unsus+2.115
Neg logit contributions
grain-2.629
urdue-2.534
ellar-2.525
 Windsor-2.466
font-2.408
Tokenfacts
Token ID37473
Feature activation+5.72e-01

Pos logit contributions
 Debor+2.985
+2.683
+2.537
 MSM+2.516
+2.455
Neg logit contributions
grain-2.332
urdue-2.268
ellar-2.246
 Windsor-2.203
afety-2.119
Token/
Token ID14
Feature activation+1.31e+00

Pos logit contributions
 Debor+0.441
+0.389
+0.366
 MSM+0.362
 unsus+0.356
Neg logit contributions
grain-0.419
urdue-0.401
ellar-0.400
 Windsor-0.394
font-0.388
TokenCivil
Token ID32610
Feature activation-2.22e+00

Pos logit contributions
grain+1.317
urdue+1.259
ellar+1.256
 Windsor+1.236
font+1.228
Neg logit contributions
 Debor-1.251
-1.077
-1.014
 MSM-1.013
 unsus-1.005
Token Beat
Token ID12568
Feature activation-1.66e+00

Pos logit contributions
grain+2.185
urdue+2.125
ellar+2.114
 Windsor+2.097
font+2.074
Neg logit contributions
 Debor-1.122
-0.937
-0.842
 MSM-0.823
 unsus-0.809
Token
Token ID198
Feature activation-2.12e+00

Pos logit contributions
grain+1.178
urdue+1.146
ellar+1.131
 Windsor+1.121
font+1.099
Neg logit contributions
 Debor-1.294
-1.148
-1.091
 MSM-1.072
 unsus-1.069
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
grain+1.555
urdue+1.489
ellar+1.486
 Windsor+1.459
font+1.442
Neg logit contributions
 Debor-1.629
-1.433
-1.346
 MSM-1.337
 unsus-1.313
TokenC
Token ID34
Feature activation+2.22e+00

Pos logit contributions
grain+0.113
urdue+0.108
ellar+0.108
 Windsor+0.106
font+0.104
Neg logit contributions
 Debor-0.138
-0.123
-0.116
 MSM-0.115
 unsus-0.113
Tokenald
Token ID1940
Feature activation+7.68e+00

Pos logit contributions
 Debor+0.934
+0.743
+0.646
 MSM+0.632
+0.611
Neg logit contributions
grain-2.374
urdue-2.272
 Windsor-2.247
ellar-2.231
font-2.223
Tokenwell
Token ID4053
Feature activation+2.40e+00

Pos logit contributions
 Debor+4.523
+3.858
+3.827
 unsus+3.637
 MSM+3.608
Neg logit contributions
grain-6.241
urdue-5.946
ˈ-5.944
 Windsor-5.778
afety-5.774
Token also
Token ID635
Feature activation-6.96e-01

Pos logit contributions
 Debor+2.068
+1.845
+1.738
 MSM+1.726
 unsus+1.701
Neg logit contributions
grain-1.549
ellar-1.470
urdue-1.461
 Windsor-1.424
font-1.406
Token wants
Token ID3382
Feature activation-1.13e+00

Pos logit contributions
grain+0.447
urdue+0.426
ellar+0.425
 Windsor+0.415
font+0.409
Neg logit contributions
 Debor-0.598
-0.534
-0.506
 MSM-0.503
 unsus-0.494
Token to
Token ID284
Feature activation-2.00e+00

Pos logit contributions
grain+0.841
urdue+0.809
ellar+0.807
 Windsor+0.797
font+0.780
Neg logit contributions
 Debor-0.850
-0.749
-0.706
 MSM-0.697
 unsus-0.686
Token enact
Token ID10865
Feature activation+1.08e+00

Pos logit contributions
grain+1.299
urdue+1.242
ellar+1.237
 Windsor+1.213
font+1.191
Neg logit contributions
 Debor-1.709
-1.522
-1.444
 MSM-1.433
 unsus-1.404
Token,
Token ID11
Feature activation+4.31e-01

Pos logit contributions
grain+0.919
urdue+0.884
ellar+0.878
 Windsor+0.867
font+0.856
Neg logit contributions
 Debor-1.018
-0.899
-0.855
 MSM-0.843
-0.824
Token with
Token ID351
Feature activation-2.02e+00

Pos logit contributions
 Debor+0.337
+0.297
+0.280
 MSM+0.278
 unsus+0.272
Neg logit contributions
grain-0.311
ellar-0.298
urdue-0.296
 Windsor-0.290
font-0.286
Token
Token ID564
Feature activation-1.03e+00

Pos logit contributions
grain+1.384
urdue+1.322
ellar+1.318
 Windsor+1.295
font+1.272
Neg logit contributions
 Debor-1.640
-1.458
-1.376
 MSM-1.367
 unsus-1.339
Token
Token ID250
Feature activation+1.70e-01

Pos logit contributions
grain+0.836
urdue+0.805
ellar+0.803
 Windsor+0.789
font+0.780
Neg logit contributions
 Debor-0.710
-0.616
-0.571
 MSM-0.570
 unsus-0.556
TokenLa
Token ID14772
Feature activation+3.17e+00

Pos logit contributions
 Debor+0.134
+0.118
+0.112
 MSM+0.111
 unsus+0.108
Neg logit contributions
grain-0.121
urdue-0.116
ellar-0.116
 Windsor-0.114
font-0.112
Token La
Token ID4689
Feature activation+7.65e+00

Pos logit contributions
 Debor+2.629
+2.336
+2.215
 MSM+2.201
 unsus+2.140
Neg logit contributions
grain-2.120
urdue-2.029
ellar-2.012
 Windsor-1.960
afety-1.952
Token Land
Token ID6379
Feature activation+4.70e+00

Pos logit contributions
 Debor+5.432
+4.766
 MSM+4.498
+4.479
+4.329
Neg logit contributions
grain-5.714
urdue-5.517
ellar-5.464
afety-5.381
 Windsor-5.283
Token
Token ID447
Feature activation+3.66e+00

Pos logit contributions
 Debor+3.497
+3.070
+2.870
 MSM+2.809
 unsus+2.808
Neg logit contributions
grain-3.541
urdue-3.398
ellar-3.371
 Windsor-3.276
afety-3.262
Token
Token ID251
Feature activation+1.60e+00

Pos logit contributions
 Debor+2.117
+1.786
+1.687
 MSM+1.636
+1.586
Neg logit contributions
grain-3.333
urdue-3.241
ellar-3.205
 Windsor-3.151
font-3.129
Token producer
Token ID9920
Feature activation-3.15e-01

Pos logit contributions
 Debor+1.269
+1.119
+1.053
 MSM+1.045
 unsus+1.025
Neg logit contributions
grain-1.140
urdue-1.094
ellar-1.088
 Windsor-1.063
font-1.049
Token Jordan
Token ID8078
Feature activation-1.11e+00

Pos logit contributions
grain+0.222
urdue+0.212
ellar+0.212
 Windsor+0.208
font+0.205
Neg logit contributions
 Debor-0.251
-0.223
-0.210
 MSM-0.208
 unsus-0.204
Tokenried
Token ID2228
Feature activation+4.89e-01

Pos logit contributions
grain+2.241
urdue+2.133
ellar+2.118
 Windsor+2.108
font+2.102
Neg logit contributions
 Debor-2.170
-1.871
-1.738
 MSM-1.734
 unsus-1.720
Token,
Token ID11
Feature activation+1.09e+00

Pos logit contributions
 Debor+0.388
+0.343
+0.324
 MSM+0.321
 unsus+0.315
Neg logit contributions
grain-0.346
urdue-0.332
ellar-0.331
 Windsor-0.324
font-0.320
Token who
Token ID508
Feature activation+2.05e+00

Pos logit contributions
 Debor+0.854
+0.754
+0.710
 MSM+0.705
 unsus+0.691
Neg logit contributions
grain-0.784
urdue-0.752
ellar-0.749
 Windsor-0.736
font-0.725
Token also
Token ID635
Feature activation+1.48e+00

Pos logit contributions
 Debor+1.578
+1.389
+1.306
 MSM+1.302
 unsus+1.272
Neg logit contributions
grain-1.498
urdue-1.432
ellar-1.429
 Windsor-1.395
font-1.378
Token had
Token ID550
Feature activation+2.45e+00

Pos logit contributions
 Debor+1.104
+0.966
+0.908
 MSM+0.903
 unsus+0.883
Neg logit contributions
grain-1.118
urdue-1.072
ellar-1.070
 Windsor-1.045
font-1.033
Token history
Token ID2106
Feature activation+7.65e+00

Pos logit contributions
 Debor+1.887
+1.652
+1.553
 MSM+1.552
 unsus+1.523
Neg logit contributions
grain-1.796
urdue-1.715
ellar-1.711
 Windsor-1.658
font-1.646
Token on
Token ID319
Feature activation-3.65e-01

Pos logit contributions
 Debor+5.270
+4.511
 MSM+4.197
+4.161
 unsus+4.109
Neg logit contributions
grain-6.075
ellar-5.845
urdue-5.774
 Windsor-5.610
afety-5.595
Token the
Token ID262
Feature activation-1.52e+00

Pos logit contributions
grain+0.237
urdue+0.227
ellar+0.226
 Windsor+0.223
font+0.219
Neg logit contributions
 Debor-0.309
-0.277
-0.261
 MSM-0.259
 unsus-0.255
Token trading
Token ID7313
Feature activation+8.88e-01

Pos logit contributions
grain+1.068
urdue+1.019
ellar+1.018
 Windsor+1.007
font+0.988
Neg logit contributions
 Debor-1.204
-1.069
-1.008
 MSM-0.992
 unsus-0.978
Token side
Token ID1735
Feature activation-1.11e+00

Pos logit contributions
 Debor+0.669
+0.587
+0.551
 MSM+0.549
 unsus+0.536
Neg logit contributions
grain-0.665
urdue-0.639
ellar-0.637
 Windsor-0.623
font-0.615
Token,
Token ID11
Feature activation+2.19e+00

Pos logit contributions
grain+0.782
urdue+0.752
ellar+0.742
 Windsor+0.739
font+0.730
Neg logit contributions
 Debor-0.877
-0.774
-0.737
 MSM-0.729
 unsus-0.714
Tokenum
Token ID388
Feature activation-3.90e+00

Pos logit contributions
 Debor+1.386
+1.239
+1.205
 MSM+1.187
 unsus+1.161
Neg logit contributions
grain-0.897
urdue-0.868
 Windsor-0.849
ellar-0.846
afety-0.815
Tokenacher
Token ID3493
Feature activation-7.86e-01

Pos logit contributions
grain+2.233
ellar+2.224
urdue+2.088
font+2.070
 Windsor+2.031
Neg logit contributions
 Debor-3.632
-3.299
-3.084
 MSM-3.069
-3.044
Token's
Token ID338
Feature activation-1.07e+00

Pos logit contributions
grain+0.540
urdue+0.517
ellar+0.515
 Windsor+0.505
font+0.497
Neg logit contributions
 Debor-0.639
-0.568
-0.536
 MSM-0.532
 unsus-0.521
Token Mercedes
Token ID21279
Feature activation-1.31e-01

Pos logit contributions
grain+0.738
urdue+0.707
ellar+0.704
 Windsor+0.694
font+0.680
Neg logit contributions
 Debor-0.871
-0.775
-0.730
 MSM-0.724
 unsus-0.708
Token was
Token ID373
Feature activation-1.06e-01

Pos logit contributions
grain+0.087
urdue+0.084
ellar+0.083
 Windsor+0.081
font+0.080
Neg logit contributions
 Debor-0.110
-0.098
-0.092
 MSM-0.092
 unsus-0.090
Token third
Token ID2368
Feature activation+7.64e+00

Pos logit contributions
grain+0.078
urdue+0.075
ellar+0.075
 Windsor+0.073
font+0.072
Neg logit contributions
 Debor-0.081
-0.072
-0.067
 MSM-0.067
 unsus-0.066
Token ahead
Token ID4058
Feature activation+4.33e+00

Pos logit contributions
 Debor+5.045
+4.240
 MSM+4.121
 unsus+4.117
+3.966
Neg logit contributions
grain-6.195
ellar-6.041
urdue-5.968
afety-5.809
ˈ-5.698
Token of
Token ID286
Feature activation+4.08e-01

Pos logit contributions
 Debor+3.107
+2.649
 MSM+2.525
+2.496
 unsus+2.478
Neg logit contributions
grain-3.391
ellar-3.291
urdue-3.248
afety-3.131
font-3.108
Token McLaren
Token ID33017
Feature activation+6.33e-01

Pos logit contributions
 Debor+0.329
+0.291
+0.275
 MSM+0.274
 unsus+0.267
Neg logit contributions
grain-0.286
urdue-0.272
ellar-0.272
 Windsor-0.264
font-0.262
Token's
Token ID338
Feature activation+1.86e-01

Pos logit contributions
 Debor+0.483
+0.425
+0.399
 MSM+0.398
 unsus+0.389
Neg logit contributions
grain-0.468
urdue-0.448
ellar-0.448
 Windsor-0.437
font-0.432
Token Lewis
Token ID10174
Feature activation+3.10e+00

Pos logit contributions
 Debor+0.148
+0.130
 MSM+0.123
+0.123
 unsus+0.120
Neg logit contributions
grain-0.132
urdue-0.126
ellar-0.126
 Windsor-0.122
font-0.121
Token downright
Token ID31464
Feature activation-1.51e+00

Pos logit contributions
grain+0.113
urdue+0.108
ellar+0.108
 Windsor+0.106
font+0.104
Neg logit contributions
 Debor-0.132
-0.117
-0.111
 MSM-0.110
 unsus-0.108
Token optimistic
Token ID16915
Feature activation+1.44e+00

Pos logit contributions
grain+0.965
urdue+0.918
ellar+0.916
 Windsor+0.902
font+0.884
Neg logit contributions
 Debor-1.296
-1.158
-1.094
 MSM-1.086
-1.067
Token.
Token ID13
Feature activation+1.22e+00

Pos logit contributions
 Debor+1.078
+0.944
+0.887
 MSM+0.882
 unsus+0.863
Neg logit contributions
grain-1.081
urdue-1.035
ellar-1.034
 Windsor-1.012
font-0.997
Token The
Token ID383
Feature activation-5.63e-02

Pos logit contributions
 Debor+0.959
+0.839
 MSM+0.795
+0.795
+0.763
Neg logit contributions
grain-0.885
urdue-0.850
ellar-0.846
 Windsor-0.819
afety-0.812
Token original
Token ID2656
Feature activation-2.21e+00

Pos logit contributions
grain+0.040
urdue+0.039
ellar+0.039
 Windsor+0.038
font+0.037
Neg logit contributions
 Debor-0.044
-0.039
-0.037
 MSM-0.036
 unsus-0.036
Token End
Token ID5268
Feature activation-1.01e+01

Pos logit contributions
grain+1.587
ellar+1.511
urdue+1.510
 Windsor+1.498
font+1.478
Neg logit contributions
 Debor-1.715
-1.530
-1.431
 MSM-1.415
-1.408
Tokenbringer
Token ID48046
Feature activation-2.19e+00

Pos logit contributions
grain+5.378
ellar+5.023
font+4.912
 Windsor+4.791
urdue+4.761
Neg logit contributions
 Debor-9.289
-8.602
-8.109
 unsus-8.104
-8.029
Token stood
Token ID6204
Feature activation-5.45e-02

Pos logit contributions
grain+1.524
urdue+1.454
ellar+1.452
 Windsor+1.441
font+1.425
Neg logit contributions
 Debor-1.750
-1.565
-1.463
-1.442
 MSM-1.440
Token about
Token ID546
Feature activation+2.57e+00

Pos logit contributions
grain+0.038
urdue+0.037
ellar+0.036
 Windsor+0.036
font+0.035
Neg logit contributions
 Debor-0.044
-0.039
-0.036
 MSM-0.036
 unsus-0.035
Token forty
Token ID16571
Feature activation+2.47e+00

Pos logit contributions
 Debor+2.111
+1.857
 MSM+1.760
+1.760
 unsus+1.733
Neg logit contributions
grain-1.753
urdue-1.679
ellar-1.667
 Windsor-1.604
font-1.604
Token five
Token ID1936
Feature activation+5.72e-01

Pos logit contributions
 Debor+1.712
+1.491
+1.379
 MSM+1.378
 unsus+1.350
Neg logit contributions
grain-1.986
urdue-1.916
ellar-1.915
 Windsor-1.859
afety-1.841
Token that
Token ID326
Feature activation-4.45e-01

Pos logit contributions
 Debor+2.228
+1.960
+1.848
 MSM+1.848
 unsus+1.814
Neg logit contributions
grain-1.842
ellar-1.754
urdue-1.748
 Windsor-1.701
font-1.687
Token the
Token ID262
Feature activation+5.68e-01

Pos logit contributions
grain+0.313
urdue+0.299
ellar+0.299
 Windsor+0.294
font+0.289
Neg logit contributions
 Debor-0.355
-0.315
-0.298
 MSM-0.294
 unsus-0.288
Token crackdown
Token ID22671
Feature activation+6.65e-01

Pos logit contributions
 Debor+0.420
+0.367
+0.344
 MSM+0.343
 unsus+0.334
Neg logit contributions
grain-0.434
urdue-0.417
ellar-0.416
 Windsor-0.407
font-0.403
Tokens
Token ID82
Feature activation-1.17e+00

Pos logit contributions
 Debor+0.517
+0.455
+0.428
 MSM+0.427
 unsus+0.418
Neg logit contributions
grain-0.483
ellar-0.462
urdue-0.462
 Windsor-0.450
font-0.445
Token against
Token ID1028
Feature activation-2.16e+00

Pos logit contributions
grain+0.836
urdue+0.800
ellar+0.798
 Windsor+0.784
font+0.771
Neg logit contributions
 Debor-0.918
-0.812
-0.766
 MSM-0.759
 unsus-0.743
Token Occupy
Token ID25551
Feature activation-9.76e+00

Pos logit contributions
grain+1.416
urdue+1.356
ellar+1.353
 Windsor+1.337
font+1.305
Neg logit contributions
 Debor-1.812
-1.614
-1.530
 MSM-1.506
-1.493
Token protesters
Token ID9584
Feature activation-6.77e+00

Pos logit contributions
 Windsor+5.933
grain+5.927
urdue+5.842
font+5.617
ellar+5.597
Neg logit contributions
 Debor-8.113
-7.193
-6.851
-6.811
 MSM-6.776
Token appear
Token ID1656
Feature activation+1.07e-02

Pos logit contributions
grain+4.349
urdue+4.249
 Windsor+4.185
ellar+4.095
font+4.076
Neg logit contributions
 Debor-5.529
-4.995
-4.753
-4.685
-4.664
Token to
Token ID284
Feature activation+2.01e+00

Pos logit contributions
 Debor+0.008
+0.007
+0.007
 MSM+0.007
 unsus+0.006
Neg logit contributions
grain-0.008
urdue-0.008
ellar-0.008
 Windsor-0.008
font-0.007
Token be
Token ID307
Feature activation+1.50e+00

Pos logit contributions
 Debor+1.547
+1.363
+1.288
 MSM+1.285
 unsus+1.263
Neg logit contributions
grain-1.461
ellar-1.390
urdue-1.389
 Windsor-1.350
font-1.345
Token violating
Token ID18134
Feature activation+2.22e+00

Pos logit contributions
 Debor+1.192
+1.050
 MSM+0.998
+0.988
 unsus+0.977
Neg logit contributions
grain-1.055
urdue-1.010
ellar-1.002
 Windsor-0.974
font-0.970
Token="
Token ID2625
Feature activation-1.40e+00

Pos logit contributions
grain+1.298
ellar+1.216
urdue+1.213
 Windsor+1.187
font+1.177
Neg logit contributions
 Debor-2.499
-2.260
-2.160
 MSM-2.154
 unsus-2.119
Tokenphone
Token ID4862
Feature activation+6.17e-01

Pos logit contributions
grain+1.008
urdue+0.957
ellar+0.957
font+0.941
 Windsor+0.941
Neg logit contributions
 Debor-1.106
-0.969
 MSM-0.912
-0.912
 unsus-0.893
Token.
Token ID13
Feature activation+1.94e+00

Pos logit contributions
 Debor+0.521
+0.464
+0.440
 MSM+0.437
 unsus+0.428
Neg logit contributions
grain-0.406
urdue-0.387
ellar-0.386
 Windsor-0.378
font-0.372
Tokenname
Token ID3672
Feature activation+1.16e+00

Pos logit contributions
 Debor+1.513
+1.341
+1.267
 MSM+1.248
 unsus+1.222
Neg logit contributions
grain-1.386
urdue-1.335
ellar-1.329
 Windsor-1.302
afety-1.270
Token">
Token ID23984
Feature activation-4.29e+00

Pos logit contributions
 Debor+1.146
+1.037
+0.994
 MSM+0.987
 unsus+0.971
Neg logit contributions
grain-0.597
urdue-0.560
ellar-0.557
 Windsor-0.538
font-0.525
Tokenspan
Token ID12626
Feature activation-9.22e+00

Pos logit contributions
grain+2.886
font+2.726
urdue+2.718
ellar+2.689
 Windsor+2.654
Neg logit contributions
 Debor-3.594
-3.187
-3.014
 MSM-3.001
-2.966
Token>
Token ID29
Feature activation-3.06e+00

Pos logit contributions
grain+3.572
font+3.283
 Windsor+3.242
ellar+3.215
urdue+3.200
Neg logit contributions
 Debor-10.058
-9.179
-8.824
 MSM-8.706
 melanch-8.614
Token <
Token ID1279
Feature activation-2.32e+00

Pos logit contributions
grain+1.241
urdue+1.151
ellar+1.150
 Windsor+1.121
font+1.094
Neg logit contributions
 Debor-3.329
-3.049
-2.925
 MSM-2.906
-2.873
Tokenp
Token ID79
Feature activation-4.55e+00

Pos logit contributions
grain+1.511
urdue+1.425
ellar+1.423
font+1.406
 Windsor+1.395
Neg logit contributions
 Debor-1.983
-1.761
 MSM-1.670
-1.668
-1.639
Token ng
Token ID23370
Feature activation-4.55e+00

Pos logit contributions
grain+2.100
urdue+2.014
ellar+1.980
 Windsor+1.943
font+1.939
Neg logit contributions
 Debor-4.698
-4.267
 MSM-4.057
-4.048
-3.983
Token-
Token ID12
Feature activation-1.37e+00

Pos logit contributions
grain+2.683
ellar+2.505
font+2.491
urdue+2.484
 Windsor+2.461
Neg logit contributions
 Debor-4.147
-3.704
 MSM-3.533
-3.508
 melanch-3.466
Token John
Token ID1757
Feature activation+1.15e+00

Pos logit contributions
 Debor+0.208
+0.181
+0.170
 MSM+0.168
 unsus+0.164
Neg logit contributions
grain-0.230
urdue-0.221
ellar-0.220
 Windsor-0.217
font-0.214
Token Murd
Token ID20305
Feature activation-2.53e+00

Pos logit contributions
 Debor+0.932
+0.821
+0.775
 MSM+0.775
 unsus+0.752
Neg logit contributions
grain-0.804
urdue-0.771
ellar-0.761
 Windsor-0.741
afety-0.736
Tokeny
Token ID88
Feature activation+1.12e+00

Pos logit contributions
grain+1.280
ellar+1.208
urdue+1.202
 Windsor+1.160
font+1.142
Neg logit contributions
 Debor-2.521
-2.292
-2.188
 MSM-2.168
-2.137
Token,
Token ID11
Feature activation+1.32e+00

Pos logit contributions
 Debor+0.865
+0.764
+0.719
 MSM+0.714
 unsus+0.698
Neg logit contributions
grain-0.812
urdue-0.778
ellar-0.775
 Windsor-0.760
font-0.747
Token Halloween
Token ID16032
Feature activation-2.61e+00

Pos logit contributions
 Debor+1.090
+0.968
 MSM+0.915
+0.914
 unsus+0.892
Neg logit contributions
grain-0.889
urdue-0.848
ellar-0.842
 Windsor-0.819
font-0.810
Token Horror
Token ID22732
Feature activation-8.81e+00

Pos logit contributions
grain+1.738
ellar+1.657
urdue+1.654
 Windsor+1.632
font+1.601
Neg logit contributions
 Debor-2.168
-1.927
-1.823
 MSM-1.811
-1.778
Token Nights
Token ID27760
Feature activation-1.62e+00

Pos logit contributions
grain+4.977
ellar+4.836
 Windsor+4.833
urdue+4.790
 Citizens+4.756
Neg logit contributions
 Debor-7.543
-6.731
-6.383
 MSM-6.349
-6.326
Token'
Token ID6
Feature activation-4.27e+00

Pos logit contributions
grain+1.096
urdue+1.047
ellar+1.044
 Windsor+1.023
font+1.007
Neg logit contributions
 Debor-1.330
-1.182
-1.118
 MSM-1.110
 unsus-1.087
Token Creative
Token ID17404
Feature activation-4.10e+00

Pos logit contributions
grain+2.680
ellar+2.565
urdue+2.561
 Windsor+2.556
font+2.468
Neg logit contributions
 Debor-3.657
-3.289
-3.115
 MSM-3.065
-3.048
Token Director
Token ID5890
Feature activation-4.06e+00

Pos logit contributions
grain+1.704
ellar+1.586
urdue+1.572
 Windsor+1.569
font+1.504
Neg logit contributions
 Debor-4.404
-4.047
-3.885
 MSM-3.825
-3.818
Token,
Token ID11
Feature activation-1.10e-01

Pos logit contributions
grain+2.884
urdue+2.783
ellar+2.777
 Windsor+2.740
font+2.720
Neg logit contributions
 Debor-3.105
-2.755
-2.605
 MSM-2.580
 unsus-2.549
Token not
Token ID407
Feature activation-1.30e+00

Pos logit contributions
grain+1.284
urdue+1.226
ellar+1.222
 Windsor+1.203
font+1.181
Neg logit contributions
 Debor-1.660
-1.483
-1.405
 MSM-1.389
-1.367
Token protecting
Token ID10192
Feature activation+7.63e-01

Pos logit contributions
grain+0.869
urdue+0.829
ellar+0.827
 Windsor+0.813
font+0.799
Neg logit contributions
 Debor-1.081
-0.962
-0.912
 MSM-0.903
-0.886
Token the
Token ID262
Feature activation-4.84e-01

Pos logit contributions
 Debor+0.591
+0.521
+0.491
 MSM+0.489
 unsus+0.478
Neg logit contributions
grain-0.556
urdue-0.532
ellar-0.531
 Windsor-0.519
font-0.513
Token rights
Token ID2489
Feature activation+7.83e-01

Pos logit contributions
grain+0.358
urdue+0.343
ellar+0.342
 Windsor+0.336
font+0.331
Neg logit contributions
 Debor-0.370
-0.325
-0.306
 MSM-0.304
 unsus-0.297
Token of
Token ID286
Feature activation+5.01e-02

Pos logit contributions
 Debor+0.606
+0.534
+0.503
 MSM+0.499
 unsus+0.488
Neg logit contributions
grain-0.570
urdue-0.546
ellar-0.545
 Windsor-0.534
font-0.527
Token Occupy
Token ID25551
Feature activation-8.58e+00

Pos logit contributions
 Debor+0.038
+0.033
+0.031
 MSM+0.031
 unsus+0.030
Neg logit contributions
grain-0.037
urdue-0.036
ellar-0.036
 Windsor-0.035
font-0.035
Token demonstrators
Token ID25016
Feature activation-5.83e+00

Pos logit contributions
grain+4.955
 Windsor+4.952
urdue+4.805
font+4.670
 Citizens+4.669
Neg logit contributions
 Debor-7.547
-6.623
-6.377
-6.326
-6.263
Token whose
Token ID3025
Feature activation+4.03e-02

Pos logit contributions
grain+3.836
urdue+3.766
 Windsor+3.730
font+3.631
ellar+3.615
Neg logit contributions
 Debor-4.662
-4.183
-3.983
-3.929
 MSM-3.912
Token protests
Token ID8536
Feature activation-3.61e+00

Pos logit contributions
 Debor+0.031
+0.027
+0.025
 MSM+0.025
 unsus+0.025
Neg logit contributions
grain-0.030
urdue-0.029
ellar-0.028
 Windsor-0.028
font-0.028
Token are
Token ID389
Feature activation-6.68e-01

Pos logit contributions
grain+2.447
urdue+2.354
 Windsor+2.321
ellar+2.318
font+2.263
Neg logit contributions
 Debor-2.929
-2.615
-2.479
 MSM-2.430
-2.407
Token being
Token ID852
Feature activation+6.09e-01

Pos logit contributions
grain+0.483
urdue+0.462
ellar+0.461
 Windsor+0.451
font+0.445
Neg logit contributions
 Debor-0.521
-0.459
-0.432
 MSM-0.430
 unsus-0.422
Tokenphone
Token ID4862
Feature activation+1.07e-01

Pos logit contributions
grain+0.741
urdue+0.708
ellar+0.707
 Windsor+0.694
font+0.694
Neg logit contributions
 Debor-0.679
-0.587
-0.549
 MSM-0.548
 unsus-0.536
Token in
Token ID287
Feature activation+1.09e+00

Pos logit contributions
 Debor+0.073
+0.063
+0.058
 MSM+0.058
 unsus+0.056
Neg logit contributions
grain-0.088
urdue-0.085
ellar-0.085
 Windsor-0.083
font-0.082
Token phones
Token ID9512
Feature activation+9.14e-02

Pos logit contributions
 Debor+0.827
+0.728
+0.683
 MSM+0.680
 unsus+0.664
Neg logit contributions
grain-0.817
urdue-0.783
ellar-0.782
 Windsor-0.765
font-0.754
Token">
Token ID5320
Feature activation-2.92e+00

Pos logit contributions
 Debor+0.099
+0.090
+0.087
 MSM+0.086
 unsus+0.085
Neg logit contributions
grain-0.039
urdue-0.036
ellar-0.036
 Windsor-0.035
font-0.034
Token <
Token ID1279
Feature activation-4.21e-01

Pos logit contributions
grain+1.200
urdue+1.114
ellar+1.099
 Windsor+1.082
font+1.063
Neg logit contributions
 Debor-3.172
-2.897
 MSM-2.768
-2.761
 unsus-2.729
Tokenspan
Token ID12626
Feature activation-8.55e+00

Pos logit contributions
grain+0.258
urdue+0.244
ellar+0.243
 Windsor+0.237
font+0.236
Neg logit contributions
 Debor-0.376
-0.336
-0.320
 MSM-0.318
 unsus-0.314
Token ng
Token ID23370
Feature activation-4.84e+00

Pos logit contributions
grain+4.219
font+4.132
 Windsor+4.008
ellar+3.996
urdue+3.992
Neg logit contributions
 Debor-8.245
-7.479
-7.153
 MSM-6.996
-6.931
Token-
Token ID12
Feature activation-1.56e+00

Pos logit contributions
grain+2.748
font+2.590
ellar+2.552
 Windsor+2.510
urdue+2.504
Neg logit contributions
 Debor-4.488
-4.009
 MSM-3.837
-3.810
 unsus-3.795
Tokenbind
Token ID21653
Feature activation-2.53e+00

Pos logit contributions
grain+1.122
ellar+1.061
urdue+1.059
font+1.047
 Windsor+1.039
Neg logit contributions
 Debor-1.235
-1.084
 MSM-1.024
-1.023
 unsus-0.998
Token="
Token ID2625
Feature activation-1.40e+00

Pos logit contributions
grain+1.298
ellar+1.216
urdue+1.213
 Windsor+1.187
font+1.177
Neg logit contributions
 Debor-2.499
-2.260
-2.160
 MSM-2.154
 unsus-2.119
Tokenphone
Token ID4862
Feature activation+6.17e-01

Pos logit contributions
grain+1.008
urdue+0.957
ellar+0.957
font+0.941
 Windsor+0.941
Neg logit contributions
 Debor-1.106
-0.969
 MSM-0.912
-0.912
 unsus-0.893
Token to
Token ID284
Feature activation+1.70e+00

Pos logit contributions
 Debor+0.803
+0.704
+0.661
 MSM+0.659
 unsus+0.642
Neg logit contributions
grain-0.789
urdue-0.758
ellar-0.756
 Windsor-0.740
font-0.730
Token the
Token ID262
Feature activation-3.25e-03

Pos logit contributions
 Debor+1.183
+1.027
+0.959
 MSM+0.953
 unsus+0.928
Neg logit contributions
grain-1.365
urdue-1.314
ellar-1.311
 Windsor-1.285
font-1.271
Token hugely
Token ID22641
Feature activation+3.20e+00

Pos logit contributions
grain+0.002
urdue+0.002
ellar+0.002
 Windsor+0.002
font+0.002
Neg logit contributions
 Debor-0.002
-0.002
-0.002
 MSM-0.002
 unsus-0.002
Token popular
Token ID2968
Feature activation+1.16e+00

Pos logit contributions
 Debor+2.230
+1.944
+1.830
 MSM+1.819
 unsus+1.786
Neg logit contributions
grain-2.562
urdue-2.454
ellar-2.438
afety-2.400
 Windsor-2.374
Token Halloween
Token ID16032
Feature activation-1.53e+00

Pos logit contributions
 Debor+0.928
+0.820
+0.775
 MSM+0.770
 unsus+0.753
Neg logit contributions
grain-0.817
urdue-0.781
ellar-0.780
 Windsor-0.762
font-0.752
Token Horror
Token ID22732
Feature activation-8.24e+00

Pos logit contributions
grain+1.067
ellar+1.020
urdue+1.019
 Windsor+1.010
font+0.990
Neg logit contributions
 Debor-1.216
-1.076
 MSM-1.008
-1.007
-0.988
Token Nights
Token ID27760
Feature activation+3.10e-01

Pos logit contributions
grain+5.051
 Craft+4.904
 Windsor+4.898
 Citizens+4.802
urdue+4.794
Neg logit contributions
 Debor-6.864
-6.121
-5.787
-5.688
 MSM-5.666
Token,
Token ID11
Feature activation-3.23e-01

Pos logit contributions
 Debor+0.246
+0.218
+0.206
 MSM+0.204
 unsus+0.200
Neg logit contributions
grain-0.220
urdue-0.210
ellar-0.210
 Windsor-0.205
font-0.202
Token I
Token ID314
Feature activation+9.50e-02

Pos logit contributions
grain+0.246
urdue+0.236
ellar+0.235
 Windsor+0.231
font+0.228
Neg logit contributions
 Debor-0.239
-0.210
-0.197
 MSM-0.196
 unsus-0.191
Token returned
Token ID4504
Feature activation-1.54e+00

Pos logit contributions
 Debor+0.074
+0.065
+0.061
 MSM+0.061
 unsus+0.060
Neg logit contributions
grain-0.069
urdue-0.066
ellar-0.066
 Windsor-0.064
font-0.063
Token for
Token ID329
Feature activation-9.85e-01

Pos logit contributions
grain+1.117
urdue+1.069
ellar+1.061
 Windsor+1.061
font+1.033
Neg logit contributions
 Debor-1.180
-1.049
-0.984
 MSM-0.979
-0.960
Token Manufacturing
Token ID32760
Feature activation+2.02e+00

Pos logit contributions
 Debor+3.982
+3.457
 MSM+3.385
+3.250
 socket+3.171
Neg logit contributions
grain-4.270
urdue-4.138
ellar-4.105
afety-4.012
 Windsor-3.926
Token Process
Token ID10854
Feature activation-1.37e+00

Pos logit contributions
 Debor+1.762
+1.576
 MSM+1.511
+1.494
 unsus+1.462
Neg logit contributions
grain-1.257
urdue-1.204
ellar-1.202
 Windsor-1.157
font-1.145
Token 14
Token ID1478
Feature activation-9.89e-01

Pos logit contributions
grain+0.928
urdue+0.885
ellar+0.881
 Windsor+0.867
font+0.852
Neg logit contributions
 Debor-1.135
-1.011
-0.954
 MSM-0.941
 unsus-0.935
Tokennm
Token ID21533
Feature activation-6.35e+00

Pos logit contributions
grain+0.695
urdue+0.662
ellar+0.654
 Windsor+0.651
font+0.638
Neg logit contributions
 Debor-0.797
-0.704
-0.661
 MSM-0.654
 unsus-0.650
Token 28
Token ID2579
Feature activation-2.09e+00

Pos logit contributions
grain+3.416
 Windsor+3.244
urdue+3.200
ellar+3.126
font+3.100
Neg logit contributions
 Debor-6.036
-5.436
-5.139
 unsus-5.106
 melanch-5.049
Tokennm
Token ID21533
Feature activation-8.17e+00

Pos logit contributions
grain+1.429
urdue+1.357
ellar+1.348
 Windsor+1.336
font+1.309
Neg logit contributions
 Debor-1.719
-1.526
-1.430
 MSM-1.416
 unsus-1.409
Token 28
Token ID2579
Feature activation-4.54e+00

Pos logit contributions
grain+4.246
 Windsor+4.097
urdue+3.963
 Craft+3.913
font+3.885
Neg logit contributions
 Debor-7.598
-6.980
 unsus-6.676
-6.576
-6.564
Tokennm
Token ID21533
Feature activation-6.24e+00

Pos logit contributions
grain+3.035
ellar+2.869
urdue+2.850
font+2.798
 Windsor+2.796
Neg logit contributions
 Debor-3.831
-3.364
-3.151
 unsus-3.123
 MSM-3.123
Token 16
Token ID1467
Feature activation-1.18e+00

Pos logit contributions
grain+3.378
 Windsor+3.201
urdue+3.175
ellar+3.141
font+3.095
Neg logit contributions
 Debor-5.805
-5.295
-5.019
 unsus-5.013
-4.982
Tokennm
Token ID21533
Feature activation-5.66e+00

Pos logit contributions
grain+0.836
urdue+0.796
ellar+0.795
 Windsor+0.780
font+0.770
Neg logit contributions
 Debor-0.948
-0.837
-0.788
 MSM-0.780
 unsus-0.771
Token 16
Token ID1467
Feature activation-2.16e+00

Pos logit contributions
grain+3.024
 Windsor+2.867
urdue+2.819
ellar+2.777
font+2.739
Neg logit contributions
 Debor-5.363
-4.890
-4.641
 unsus-4.632
-4.568
Tokent
Token ID83
Feature activation-2.60e+00

Pos logit contributions
grain+2.476
ellar+2.264
font+2.230
urdue+2.216
 Windsor+2.195
Neg logit contributions
 Debor-3.685
-3.328
-3.146
-3.110
 MSM-3.081
Tokenong
Token ID506
Feature activation-2.50e+00

Pos logit contributions
grain+1.029
ellar+0.952
urdue+0.924
 Windsor+0.888
font+0.868
Neg logit contributions
 Debor-2.917
-2.687
-2.555
 MSM-2.554
-2.527
Tokenue
Token ID518
Feature activation-1.98e+00

Pos logit contributions
grain+1.834
ellar+1.737
urdue+1.731
 Windsor+1.713
font+1.684
Neg logit contributions
 Debor-1.937
-1.731
-1.619
 MSM-1.595
 unsus-1.573
Token.
Token ID13
Feature activation-5.92e-01

Pos logit contributions
grain+1.414
urdue+1.350
ellar+1.346
 Windsor+1.330
font+1.315
Neg logit contributions
 Debor-1.556
-1.376
-1.301
 MSM-1.293
-1.263
Token Th
Token ID536
Feature activation-2.19e+00

Pos logit contributions
grain+0.421
urdue+0.403
ellar+0.402
 Windsor+0.392
font+0.387
Neg logit contributions
 Debor-0.470
-0.414
-0.391
 MSM-0.389
 unsus-0.379
Tokené
Token ID2634
Feature activation-8.11e+00

Pos logit contributions
grain+1.507
ellar+1.447
urdue+1.443
 Windsor+1.408
font+1.400
Neg logit contributions
 Debor-1.780
-1.587
-1.495
 MSM-1.486
-1.458
Tokenod
Token ID375
Feature activation-5.96e+00

Pos logit contributions
grain+3.679
ellar+3.437
urdue+3.354
font+3.316
 Windsor+3.282
Neg logit contributions
 Debor-8.437
-7.684
 MSM-7.380
 unden-7.265
-7.255
Tokenen
Token ID268
Feature activation-3.16e+00

Pos logit contributions
grain+3.023
ellar+2.905
urdue+2.829
font+2.821
 Windsor+2.776
Neg logit contributions
 Debor-5.861
-5.289
 MSM-5.089
-5.036
-5.007
Token must
Token ID1276
Feature activation-2.03e+00

Pos logit contributions
grain+1.991
urdue+1.917
ellar+1.893
 Windsor+1.887
font+1.839
Neg logit contributions
 Debor-2.699
-2.425
-2.298
 MSM-2.281
-2.250
Tokeners
Token ID364
Feature activation-2.51e+00

Pos logit contributions
grain+1.331
ellar+1.271
urdue+1.270
 Windsor+1.240
font+1.222
Neg logit contributions
 Debor-1.715
-1.531
-1.446
 MSM-1.437
-1.406
Token his
Token ID465
Feature activation-3.80e-01

Pos logit contributions
grain+1.698
urdue+1.612
ellar+1.610
 Windsor+1.587
font+1.558
Neg logit contributions
 Debor-2.062
-1.833
-1.733
 MSM-1.721
-1.687
Token shareholders
Token ID19195
Feature activation-4.03e+00

Pos logit contributions
grain+0.281
urdue+0.269
ellar+0.269
font+0.259
 Windsor+0.259
Neg logit contributions
 Debor-0.299
-0.261
 MSM-0.247
-0.246
 unsus-0.241
Token,"
Token ID553
Feature activation-2.08e+00

Pos logit contributions
grain+2.730
 Windsor+2.633
urdue+2.607
ellar+2.576
font+2.527
Neg logit contributions
 Debor-3.237
-2.909
-2.779
-2.735
 MSM-2.704
Token deputy
Token ID10636
Feature activation-3.08e+00

Pos logit contributions
grain+1.388
urdue+1.326
ellar+1.323
 Windsor+1.309
font+1.273
Neg logit contributions
 Debor-1.722
-1.539
-1.456
 MSM-1.440
 unsus-1.414
Token Conservative
Token ID11132
Feature activation-6.49e+00

Pos logit contributions
grain+2.073
urdue+1.977
ellar+1.973
 Windsor+1.950
font+1.903
Neg logit contributions
 Debor-2.549
-2.268
-2.148
 MSM-2.129
 unsus-2.090
Token leader
Token ID3554
Feature activation-3.19e+00

Pos logit contributions
grain+4.249
 Windsor+4.189
ellar+4.048
urdue+4.007
 Citizens+3.894
Neg logit contributions
 Debor-5.247
-4.771
-4.507
-4.433
 MSM-4.419
Token Lisa
Token ID15378
Feature activation-8.06e+00

Pos logit contributions
grain+2.172
urdue+2.072
 Windsor+2.072
ellar+2.067
font+2.010
Neg logit contributions
 Debor-2.565
-2.319
-2.183
 MSM-2.159
-2.136
Token Ra
Token ID7567
Feature activation+1.21e+00

Pos logit contributions
grain+3.530
 Windsor+3.454
ellar+3.322
font+3.200
 Craft+3.164
Neg logit contributions
 Debor-8.397
-7.797
-7.440
 MSM-7.317
 unsus-7.311
Tokenitt
Token ID715
Feature activation-3.40e+00

Pos logit contributions
 Debor+0.862
+0.752
+0.712
 MSM+0.702
 unsus+0.682
Neg logit contributions
grain-0.938
urdue-0.905
ellar-0.904
 Windsor-0.888
afety-0.875
Token said
Token ID531
Feature activation-3.63e+00

Pos logit contributions
grain+1.789
ellar+1.684
urdue+1.681
 Windsor+1.648
font+1.598
Neg logit contributions
 Debor-3.298
-2.985
-2.854
 MSM-2.832
 unsus-2.793
Token.
Token ID13
Feature activation-2.55e+00

Pos logit contributions
grain+2.586
urdue+2.517
 Windsor+2.516
ellar+2.485
font+2.428
Neg logit contributions
 Debor-2.767
-2.493
-2.357
 MSM-2.297
-2.286
Token "
Token ID366
Feature activation-2.41e+00

Pos logit contributions
grain+1.541
urdue+1.464
ellar+1.460
 Windsor+1.432
font+1.403
Neg logit contributions
 Debor-2.284
-2.053
-1.952
 MSM-1.936
 unsus-1.909
Token fossils
Token ID34066
Feature activation-2.82e+00

Pos logit contributions
grain+1.531
ellar+1.462
urdue+1.454
 Windsor+1.430
font+1.398
Neg logit contributions
 Debor-2.018
-1.808
-1.718
 MSM-1.689
-1.667
Token,
Token ID11
Feature activation-3.12e+00

Pos logit contributions
grain+1.971
ellar+1.878
urdue+1.877
 Windsor+1.837
font+1.813
Neg logit contributions
 Debor-2.262
-2.013
-1.895
 MSM-1.871
-1.841
Token geographic
Token ID22987
Feature activation-3.78e+00

Pos logit contributions
grain+2.084
urdue+1.987
ellar+1.983
 Windsor+1.956
font+1.911
Neg logit contributions
 Debor-2.571
-2.297
-2.175
 MSM-2.138
-2.116
Token regions
Token ID7652
Feature activation-4.21e+00

Pos logit contributions
grain+2.643
ellar+2.552
urdue+2.469
 Windsor+2.463
font+2.418
Neg logit contributions
 Debor-3.005
-2.684
-2.546
-2.473
 MSM-2.464
Token and
Token ID290
Feature activation-2.32e+00

Pos logit contributions
grain+2.816
ellar+2.689
urdue+2.647
 Windsor+2.613
font+2.573
Neg logit contributions
 Debor-3.447
-3.096
-2.936
 MSM-2.854
-2.838
Token strat
Token ID25369
Feature activation-8.03e+00

Pos logit contributions
grain+1.567
ellar+1.498
urdue+1.479
 Windsor+1.465
font+1.426
Neg logit contributions
 Debor-1.920
-1.720
-1.626
 MSM-1.585
-1.572
Tokenig
Token ID328
Feature activation-1.78e+00

Pos logit contributions
grain+3.319
ellar+3.237
urdue+2.986
font+2.852
 Windsor+2.797
Neg logit contributions
 Debor-8.710
-7.982
-7.714
 MSM-7.606
-7.574
Tokenraphic
Token ID22262
Feature activation-5.76e+00

Pos logit contributions
grain+0.749
urdue+0.700
ellar+0.689
 Windsor+0.682
font+0.653
Neg logit contributions
 Debor-1.908
-1.746
 MSM-1.672
-1.668
 unsus-1.640
Token positions
Token ID6116
Feature activation-4.53e+00

Pos logit contributions
grain+4.186
ellar+4.057
 Windsor+3.918
font+3.891
urdue+3.875
Neg logit contributions
 Debor-4.346
-3.838
-3.701
-3.596
-3.533
Token make
Token ID787
Feature activation-9.86e-01

Pos logit contributions
grain+3.092
urdue+2.932
ellar+2.924
 Windsor+2.880
font+2.842
Neg logit contributions
 Debor-3.654
-3.257
-3.092
 MSM-3.027
-3.011
Token random
Token ID4738
Feature activation+2.73e-01

Pos logit contributions
grain+0.718
ellar+0.687
urdue+0.683
 Windsor+0.673
font+0.660
Neg logit contributions
 Debor-0.766
-0.678
-0.639
 MSM-0.627
-0.617
Token.
Token ID13
Feature activation+2.64e+00

Pos logit contributions
 Debor+0.860
+0.757
+0.714
 MSM+0.709
+0.690
Neg logit contributions
grain-0.812
urdue-0.780
ellar-0.775
 Windsor-0.763
font-0.753
Token
Token ID564
Feature activation-3.28e-01

Pos logit contributions
 Debor+2.145
+1.899
+1.795
 MSM+1.787
+1.732
Neg logit contributions
grain-1.820
ellar-1.741
urdue-1.737
 Windsor-1.678
afety-1.661
Token
Token ID250
Feature activation-4.28e-02

Pos logit contributions
grain+0.275
urdue+0.265
ellar+0.264
 Windsor+0.260
font+0.256
Neg logit contributions
 Debor-0.218
-0.188
-0.175
 MSM-0.173
 unsus-0.168
TokenFor
Token ID1890
Feature activation-1.29e-01

Pos logit contributions
grain+0.030
urdue+0.028
ellar+0.028
 Windsor+0.028
font+0.027
Neg logit contributions
 Debor-0.035
-0.031
-0.029
 MSM-0.029
 unsus-0.028
Tokengive
Token ID26535
Feature activation-3.45e+00

Pos logit contributions
grain+0.084
urdue+0.080
ellar+0.080
 Windsor+0.078
font+0.077
Neg logit contributions
 Debor-0.111
-0.099
-0.094
 MSM-0.093
 unsus-0.091
Token me
Token ID502
Feature activation-8.02e+00

Pos logit contributions
grain+2.592
urdue+2.477
ellar+2.469
 Windsor+2.466
font+2.417
Neg logit contributions
 Debor-2.525
-2.244
-2.069
 MSM-2.066
-2.054
Token!
Token ID0
Feature activation-2.48e+00

Pos logit contributions
grain+4.969
 Windsor+4.659
ellar+4.609
urdue+4.587
font+4.581
Neg logit contributions
 Debor-6.558
-5.942
-5.742
-5.662
 MSM-5.572
Token Please
Token ID4222
Feature activation+5.63e-01

Pos logit contributions
grain+1.747
urdue+1.664
ellar+1.653
 Windsor+1.636
font+1.613
Neg logit contributions
 Debor-1.968
-1.745
-1.648
 MSM-1.630
 unsus-1.621
Token forgive
Token ID20927
Feature activation-1.73e+00

Pos logit contributions
 Debor+0.441
+0.389
+0.367
 MSM+0.365
 unsus+0.357
Neg logit contributions
grain-0.404
urdue-0.387
ellar-0.387
 Windsor-0.378
font-0.372
Token me
Token ID502
Feature activation-5.53e+00

Pos logit contributions
grain+1.347
urdue+1.294
ellar+1.291
 Windsor+1.279
font+1.256
Neg logit contributions
 Debor-1.233
-1.085
-1.010
 MSM-0.999
-0.988
Token!
Token ID0
Feature activation-9.94e-01

Pos logit contributions
grain+3.518
urdue+3.379
ellar+3.347
 Windsor+3.313
font+3.262
Neg logit contributions
 Debor-4.566
-4.088
-3.923
 MSM-3.875
-3.843
Token It
Token ID632
Feature activation-2.26e+00

Pos logit contributions
grain+1.447
urdue+1.384
ellar+1.370
 Windsor+1.365
font+1.342
Neg logit contributions
 Debor-1.642
-1.462
-1.379
 unsus-1.358
 MSM-1.355
Token
Token ID447
Feature activation-4.28e-02

Pos logit contributions
grain+1.530
urdue+1.463
ellar+1.450
 Windsor+1.419
font+1.414
Neg logit contributions
 Debor-1.855
-1.641
 MSM-1.551
-1.548
 unsus-1.516
Token
Token ID247
Feature activation+1.10e-01

Pos logit contributions
grain+0.030
urdue+0.029
ellar+0.029
 Windsor+0.028
font+0.028
Neg logit contributions
 Debor-0.034
-0.030
-0.029
 MSM-0.028
 unsus-0.028
Tokens
Token ID82
Feature activation-1.02e+00

Pos logit contributions
 Debor+0.086
+0.076
+0.072
 MSM+0.071
 unsus+0.070
Neg logit contributions
grain-0.078
urdue-0.075
ellar-0.075
 Windsor-0.073
font-0.072
Token my
Token ID616
Feature activation-1.78e+00

Pos logit contributions
grain+0.705
urdue+0.674
ellar+0.671
 Windsor+0.660
font+0.649
Neg logit contributions
 Debor-0.826
-0.733
-0.692
 MSM-0.687
 unsus-0.673
Token fault
Token ID8046
Feature activation-7.92e+00

Pos logit contributions
grain+1.251
urdue+1.200
ellar+1.189
 Windsor+1.173
font+1.158
Neg logit contributions
 Debor-1.414
-1.251
-1.177
 MSM-1.171
-1.148
Token.
Token ID13
Feature activation-3.72e-01

Pos logit contributions
grain+4.857
ellar+4.712
urdue+4.696
font+4.637
 Windsor+4.636
Neg logit contributions
 Debor-6.509
-5.894
-5.694
-5.496
-5.466
Token #
Token ID1303
Feature activation-1.18e+00

Pos logit contributions
grain+0.272
urdue+0.260
ellar+0.259
 Windsor+0.255
font+0.252
Neg logit contributions
 Debor-0.286
-0.253
-0.238
 MSM-0.235
 unsus-0.232
Tokenatl
Token ID25864
Feature activation-3.32e+00

Pos logit contributions
grain+0.845
ellar+0.801
urdue+0.799
 Windsor+0.784
font+0.780
Neg logit contributions
 Debor-0.942
-0.828
-0.780
 MSM-0.777
 unsus-0.765
Tokenweather
Token ID23563
Feature activation+1.43e+00

Pos logit contributions
grain+2.009
urdue+1.888
ellar+1.859
font+1.818
 Windsor+1.815
Neg logit contributions
 Debor-2.998
-2.691
-2.533
 MSM-2.528
 unsus-2.488
Token #
Token ID1303
Feature activation-2.56e-01

Pos logit contributions
 Debor+1.155
+1.025
+0.967
 MSM+0.962
 unsus+0.940
Neg logit contributions
grain-0.985
urdue-0.946
ellar-0.944
 Windsor-0.925
font-0.906
Token,
Token ID11
Feature activation-2.32e+00

Pos logit contributions
grain+1.751
urdue+1.650
ellar+1.648
font+1.598
 Windsor+1.597
Neg logit contributions
 Debor-2.001
-1.776
-1.677
 MSM-1.658
-1.631
Token and
Token ID290
Feature activation-9.65e-01

Pos logit contributions
grain+1.448
urdue+1.366
ellar+1.355
 Windsor+1.327
font+1.310
Neg logit contributions
 Debor-2.044
-1.834
-1.731
 MSM-1.714
-1.694
Token Prof
Token ID4415
Feature activation-2.42e+00

Pos logit contributions
grain+0.664
urdue+0.631
ellar+0.627
 Windsor+0.617
font+0.607
Neg logit contributions
 Debor-0.789
-0.702
-0.661
 MSM-0.654
-0.643
Token.
Token ID13
Feature activation-2.36e+00

Pos logit contributions
grain+1.734
ellar+1.659
urdue+1.659
 Windsor+1.631
font+1.608
Neg logit contributions
 Debor-1.881
-1.672
-1.578
 MSM-1.557
 unsus-1.532
Token Loren
Token ID32035
Feature activation-5.84e+00

Pos logit contributions
grain+1.678
urdue+1.605
ellar+1.592
 Windsor+1.582
font+1.553
Neg logit contributions
 Debor-1.840
-1.634
-1.541
 MSM-1.529
 unsus-1.508
Token Cord
Token ID21119
Feature activation-7.91e+00

Pos logit contributions
grain+3.710
ellar+3.495
urdue+3.492
 Windsor+3.491
font+3.480
Neg logit contributions
 Debor-4.959
-4.474
-4.218
 MSM-4.133
 unsus-4.115
Tokenain
Token ID391
Feature activation-3.55e+00

Pos logit contributions
grain+2.958
ellar+2.546
urdue+2.471
font+2.436
 Windsor+2.301
Neg logit contributions
 Debor-8.816
-8.384
-7.976
 unsus-7.936
-7.922
Token comes
Token ID2058
Feature activation-1.83e+00

Pos logit contributions
grain+2.355
urdue+2.251
ellar+2.217
 Windsor+2.172
font+2.161
Neg logit contributions
 Debor-2.951
-2.626
 MSM-2.475
-2.472
 unsus-2.422
Token down
Token ID866
Feature activation+9.51e-01

Pos logit contributions
grain+1.174
urdue+1.118
ellar+1.110
 Windsor+1.096
font+1.080
Neg logit contributions
 Debor-1.573
-1.406
-1.330
 MSM-1.325
-1.298
Token pretty
Token ID2495
Feature activation+2.94e+00

Pos logit contributions
 Debor+0.725
+0.638
+0.600
 MSM+0.596
 unsus+0.582
Neg logit contributions
grain-0.704
urdue-0.675
ellar-0.674
 Windsor-0.661
font-0.651
Token hard
Token ID1327
Feature activation+4.48e-04

Pos logit contributions
 Debor+2.321
+2.058
+1.952
 MSM+1.936
 unsus+1.898
Neg logit contributions
grain-2.085
urdue-2.006
ellar-1.990
 Windsor-1.929
afety-1.918
Token
Token ID250
Feature activation-2.13e+00

Pos logit contributions
grain+1.612
urdue+1.544
ellar+1.537
 Windsor+1.520
font+1.498
Neg logit contributions
 Debor-1.508
-1.319
-1.224
 MSM-1.224
 unsus-1.206
TokenWe
Token ID1135
Feature activation-2.00e+00

Pos logit contributions
grain+1.409
ellar+1.338
urdue+1.337
 Windsor+1.317
font+1.302
Neg logit contributions
 Debor-1.788
-1.586
 MSM-1.496
-1.495
 unsus-1.488
Token
Token ID447
Feature activation-4.32e-01

Pos logit contributions
grain+1.348
ellar+1.287
urdue+1.286
 Windsor+1.260
font+1.239
Neg logit contributions
 Debor-1.637
-1.462
-1.374
 MSM-1.368
-1.340
Token
Token ID247
Feature activation-7.47e-01

Pos logit contributions
grain+0.335
urdue+0.322
ellar+0.321
 Windsor+0.315
font+0.311
Neg logit contributions
 Debor-0.314
-0.274
-0.257
 MSM-0.255
 unsus-0.249
Tokenve
Token ID303
Feature activation+1.82e-01

Pos logit contributions
grain+0.505
urdue+0.482
ellar+0.480
 Windsor+0.470
font+0.464
Neg logit contributions
 Debor-0.616
-0.549
-0.517
 MSM-0.514
 unsus-0.504
Token seen
Token ID1775
Feature activation-7.88e+00

Pos logit contributions
 Debor+0.146
+0.129
+0.122
 MSM+0.121
 unsus+0.118
Neg logit contributions
grain-0.128
urdue-0.123
ellar-0.122
 Windsor-0.120
font-0.118
Token it
Token ID340
Feature activation-1.12e+00

Pos logit contributions
grain+4.959
 Windsor+4.772
ellar+4.765
urdue+4.679
font+4.628
Neg logit contributions
 Debor-6.350
-5.742
-5.379
-5.324
 MSM-5.254
Token with
Token ID351
Feature activation-1.32e+00

Pos logit contributions
grain+0.749
urdue+0.717
ellar+0.713
 Windsor+0.701
font+0.690
Neg logit contributions
 Debor-0.933
-0.831
-0.784
 MSM-0.782
 unsus-0.764
Token [
Token ID685
Feature activation+1.26e-01

Pos logit contributions
grain+0.954
urdue+0.914
ellar+0.910
 Windsor+0.897
font+0.882
Neg logit contributions
 Debor-1.025
-0.905
-0.850
 MSM-0.844
 unsus-0.828
Tokenalcohol
Token ID42142
Feature activation-4.15e-01

Pos logit contributions
 Debor+0.096
+0.084
+0.079
 MSM+0.079
 unsus+0.077
Neg logit contributions
grain-0.094
urdue-0.090
ellar-0.089
 Windsor-0.088
font-0.087
Token]
Token ID60
Feature activation+9.46e-01

Pos logit contributions
grain+0.304
urdue+0.292
ellar+0.289
 Windsor+0.285
font+0.280
Neg logit contributions
 Debor-0.319
-0.281
-0.264
 MSM-0.262
 unsus-0.257
Token so
Token ID523
Feature activation-5.81e-01

Pos logit contributions
 Debor+1.198
+1.065
+1.002
 MSM+1.001
 unsus+0.984
Neg logit contributions
grain-1.039
urdue-0.995
ellar-0.994
 Windsor-0.967
afety-0.949
Token I
Token ID314
Feature activation+9.04e-01

Pos logit contributions
grain+0.402
urdue+0.384
ellar+0.383
 Windsor+0.376
font+0.371
Neg logit contributions
 Debor-0.471
-0.418
-0.394
 MSM-0.391
 unsus-0.383
Token added
Token ID2087
Feature activation+4.63e-01

Pos logit contributions
 Debor+0.731
+0.649
+0.614
 MSM+0.611
 unsus+0.601
Neg logit contributions
grain-0.623
urdue-0.599
ellar-0.596
 Windsor-0.582
afety-0.572
Token a
Token ID257
Feature activation-3.35e-01

Pos logit contributions
 Debor+0.365
+0.322
+0.303
 MSM+0.301
 unsus+0.295
Neg logit contributions
grain-0.332
urdue-0.318
ellar-0.317
 Windsor-0.311
font-0.306
Token <
Token ID1279
Feature activation+1.08e-01

Pos logit contributions
grain+0.237
urdue+0.227
ellar+0.226
 Windsor+0.222
font+0.218
Neg logit contributions
 Debor-0.266
-0.235
-0.222
 MSM-0.220
 unsus-0.215
Tokenspan
Token ID12626
Feature activation-7.87e+00

Pos logit contributions
 Debor+0.090
+0.080
+0.076
 MSM+0.075
 unsus+0.074
Neg logit contributions
grain-0.072
urdue-0.069
ellar-0.068
 Windsor-0.067
font-0.066
Token>
Token ID29
Feature activation-1.51e+00

Pos logit contributions
grain+3.616
font+3.463
 Windsor+3.396
urdue+3.387
ellar+3.336
Neg logit contributions
 Debor-7.892
-7.137
-6.846
 MSM-6.741
-6.689
Token around
Token ID1088
Feature activation+1.51e-01

Pos logit contributions
grain+1.214
urdue+1.160
ellar+1.157
 Windsor+1.142
font+1.139
Neg logit contributions
 Debor-1.063
-0.919
-0.861
 MSM-0.855
 unsus-0.832
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
 Debor+0.120
+0.106
+0.100
 MSM+0.100
 unsus+0.097
Neg logit contributions
grain-0.107
urdue-0.103
ellar-0.102
 Windsor-0.100
font-0.099
Token phone
Token ID3072
Feature activation+1.61e+00

Pos logit contributions
 Debor+1.156
+1.026
 MSM+0.973
+0.972
 unsus+0.952
Neg logit contributions
grain-0.921
urdue-0.880
ellar-0.877
 Windsor-0.851
afety-0.837
Token name
Token ID1438
Feature activation+6.48e-01

Pos logit contributions
 Debor+1.165
+1.020
+0.954
 MSM+0.946
 unsus+0.926
Neg logit contributions
grain-1.244
urdue-1.197
ellar-1.193
 Windsor-1.168
font-1.148
Token in
Token ID287
Feature activation-9.76e-01

Pos logit contributions
grain+0.569
urdue+0.545
ellar+0.544
 Windsor+0.534
font+0.527
Neg logit contributions
 Debor-0.562
-0.493
-0.463
 MSM-0.459
 unsus-0.448
Token a
Token ID257
Feature activation-1.96e+00

Pos logit contributions
grain+0.680
urdue+0.645
ellar+0.644
 Windsor+0.636
font+0.623
Neg logit contributions
 Debor-0.787
-0.702
-0.661
 MSM-0.649
-0.644
Token table
Token ID3084
Feature activation-4.62e-01

Pos logit contributions
grain+1.527
urdue+1.457
ellar+1.452
 Windsor+1.444
font+1.411
Neg logit contributions
 Debor-1.410
-1.238
-1.154
 MSM-1.130
-1.125
Token or
Token ID393
Feature activation-1.24e+00

Pos logit contributions
grain+0.343
urdue+0.329
ellar+0.328
 Windsor+0.322
font+0.317
Neg logit contributions
 Debor-0.351
-0.309
-0.290
 MSM-0.288
 unsus-0.282
Token chart
Token ID8262
Feature activation-1.62e+00

Pos logit contributions
grain+0.938
ellar+0.894
urdue+0.893
 Windsor+0.886
font+0.867
Neg logit contributions
 Debor-0.930
-0.820
-0.763
 MSM-0.747
-0.747
Token format
Token ID5794
Feature activation-7.86e+00

Pos logit contributions
grain+1.201
urdue+1.147
ellar+1.144
 Windsor+1.122
font+1.109
Neg logit contributions
 Debor-1.238
-1.087
-1.022
 MSM-1.015
-0.993
Token).
Token ID737
Feature activation+1.13e+00

Pos logit contributions
grain+5.241
urdue+4.946
ellar+4.932
 Windsor+4.866
font+4.837
Neg logit contributions
 Debor-6.248
-5.600
-5.278
-5.234
-5.108
Token It
Token ID632
Feature activation+1.99e-02

Pos logit contributions
 Debor+0.867
+0.759
+0.716
 MSM+0.715
 unsus+0.690
Neg logit contributions
grain-0.835
urdue-0.800
ellar-0.799
 Windsor-0.779
font-0.770
Token may
Token ID743
Feature activation+2.79e-01

Pos logit contributions
 Debor+0.016
+0.014
+0.014
 MSM+0.013
 unsus+0.013
Neg logit contributions
grain-0.014
urdue-0.013
ellar-0.013
 Windsor-0.013
font-0.013
Token also
Token ID635
Feature activation+1.07e+00

Pos logit contributions
 Debor+0.226
+0.200
+0.189
 MSM+0.188
 unsus+0.184
Neg logit contributions
grain-0.193
urdue-0.184
ellar-0.184
 Windsor-0.180
font-0.177
Token have
Token ID423
Feature activation+1.54e+00

Pos logit contributions
 Debor+0.851
+0.754
+0.714
 MSM+0.707
 unsus+0.696
Neg logit contributions
grain-0.752
urdue-0.721
ellar-0.717
 Windsor-0.704
font-0.694
Token>
Token ID29
Feature activation-1.80e+00

Pos logit contributions
grain+2.043
urdue+1.930
ellar+1.909
 Windsor+1.877
font+1.835
Neg logit contributions
 Debor-4.547
-4.114
-3.959
 MSM-3.927
-3.871
Token
Token ID7359
Feature activation-5.24e+00

Pos logit contributions
grain+0.676
urdue+0.624
ellar+0.623
 Windsor+0.601
font+0.586
Neg logit contributions
 Debor-2.018
-1.855
-1.784
 MSM-1.769
 unsus-1.751
Tokenli
Token ID4528
Feature activation-5.93e+00

Pos logit contributions
grain+2.269
font+2.067
urdue+2.020
ellar+2.014
 Windsor+1.933
Neg logit contributions
 Debor-5.668
-5.107
-4.929
-4.923
 MSM-4.915
Token>
Token ID29
Feature activation-2.79e-01

Pos logit contributions
grain+2.667
urdue+2.480
 Windsor+2.469
ellar+2.456
font+2.411
Neg logit contributions
 Debor-6.213
-5.571
-5.380
 MSM-5.371
 melanch-5.275
Token
Token ID7359
Feature activation-2.77e+00

Pos logit contributions
grain+0.112
urdue+0.104
ellar+0.103
 Windsor+0.099
font+0.097
Neg logit contributions
 Debor-0.307
-0.282
-0.271
 MSM-0.269
 unsus-0.265
Tokenul
Token ID377
Feature activation-7.85e+00

Pos logit contributions
grain+1.527
urdue+1.423
ellar+1.419
font+1.392
 Windsor+1.376
Neg logit contributions
 Debor-2.661
-2.380
-2.287
 MSM-2.272
-2.269
Token>
Token ID29
Feature activation+7.36e-01

Pos logit contributions
grain+3.112
urdue+2.865
font+2.862
 Windsor+2.840
ellar+2.818
Neg logit contributions
 Debor-8.534
-7.623
-7.398
 MSM-7.397
 unden-7.332
Token
Token ID7359
Feature activation-1.93e+00

Pos logit contributions
 Debor+0.767
+0.699
+0.670
 MSM+0.667
 unsus+0.656
Neg logit contributions
grain-0.339
urdue-0.317
ellar-0.315
 Windsor-0.305
font-0.297
Tokenbody
Token ID2618
Feature activation-2.27e+00

Pos logit contributions
grain+0.862
ellar+0.784
urdue+0.780
font+0.769
 Windsor+0.760
Neg logit contributions
 Debor-2.071
-1.868
-1.798
 MSM-1.795
 unsus-1.783
Token>
Token ID29
Feature activation-7.07e-01

Pos logit contributions
grain+1.173
urdue+1.102
ellar+1.098
 Windsor+1.069
font+1.049
Neg logit contributions
 Debor-2.241
-2.029
-1.939
 MSM-1.931
 unsus-1.899
Token
Token ID198
Feature activation+2.73e-01

Pos logit contributions
grain+0.355
urdue+0.334
ellar+0.333
 Windsor+0.323
font+0.317
Neg logit contributions
 Debor-0.707
-0.642
-0.614
 MSM-0.610
 unsus-0.602
Token putting
Token ID5137
Feature activation+2.29e+00

Pos logit contributions
grain+0.684
urdue+0.657
ellar+0.656
 Windsor+0.645
font+0.635
Neg logit contributions
 Debor-0.668
-0.585
-0.549
 MSM-0.545
 unsus-0.532
Token together
Token ID1978
Feature activation-1.74e+00

Pos logit contributions
 Debor+1.726
+1.509
+1.425
 MSM+1.420
 unsus+1.388
Neg logit contributions
grain-1.709
urdue-1.647
ellar-1.634
 Windsor-1.590
font-1.577
Token an
Token ID281
Feature activation-1.17e+00

Pos logit contributions
grain+1.201
ellar+1.145
urdue+1.142
 Windsor+1.127
font+1.109
Neg logit contributions
 Debor-1.411
-1.255
-1.186
 MSM-1.170
-1.153
Token event
Token ID1785
Feature activation-3.17e+00

Pos logit contributions
grain+0.780
ellar+0.749
urdue+0.743
 Windsor+0.735
font+0.721
Neg logit contributions
 Debor-0.967
-0.864
-0.814
 MSM-0.800
-0.795
Token like
Token ID588
Feature activation-7.13e-01

Pos logit contributions
grain+2.131
ellar+2.057
urdue+2.040
 Windsor+1.994
font+1.977
Neg logit contributions
 Debor-2.612
-2.323
-2.190
 MSM-2.169
-2.139
Token Horror
Token ID22732
Feature activation-7.83e+00

Pos logit contributions
grain+0.515
urdue+0.493
ellar+0.492
 Windsor+0.482
font+0.475
Neg logit contributions
 Debor-0.556
-0.491
-0.462
 MSM-0.459
 unsus-0.449
Token Nights
Token ID27760
Feature activation+8.80e-02

Pos logit contributions
grain+4.407
 Windsor+4.245
ellar+4.222
urdue+4.199
 Craft+4.195
Neg logit contributions
 Debor-6.884
-6.183
-5.896
 MSM-5.788
-5.757
Token...
Token ID986
Feature activation-2.69e-01

Pos logit contributions
 Debor+0.067
+0.059
+0.055
 MSM+0.055
 unsus+0.054
Neg logit contributions
grain-0.065
urdue-0.063
ellar-0.063
 Windsor-0.061
font-0.060
Token tanks
Token ID11657
Feature activation+2.39e+00

Pos logit contributions
grain+0.193
urdue+0.185
ellar+0.184
 Windsor+0.181
font+0.179
Neg logit contributions
 Debor-0.210
-0.185
-0.175
 MSM-0.173
 unsus-0.170
Token included
Token ID3017
Feature activation+1.05e+00

Pos logit contributions
 Debor+1.878
+1.658
+1.557
 MSM+1.550
 unsus+1.530
Neg logit contributions
grain-1.715
urdue-1.629
ellar-1.623
 Windsor-1.592
font-1.565
Token.
Token ID13
Feature activation-9.88e-01

Pos logit contributions
 Debor+0.793
+0.696
+0.653
 MSM+0.649
 unsus+0.634
Neg logit contributions
grain-0.791
urdue-0.758
ellar-0.756
 Windsor-0.741
font-0.730
Tokenua
Token ID6413
Feature activation+1.06e+00

Pos logit contributions
 Debor+1.923
+1.729
+1.657
 MSM+1.640
 unsus+1.607
Neg logit contributions
grain-1.182
ellar-1.117
urdue-1.115
 Windsor-1.081
font-1.058
Token,
Token ID11
Feature activation-2.80e+00

Pos logit contributions
 Debor+0.809
+0.711
+0.668
 MSM+0.665
 unsus+0.649
Neg logit contributions
grain-0.780
urdue-0.747
ellar-0.746
 Windsor-0.729
font-0.720
Token New
Token ID968
Feature activation-1.07e+00

Pos logit contributions
grain+2.087
 Windsor+2.021
urdue+2.006
ellar+1.961
font+1.935
Neg logit contributions
 Debor-2.081
-1.844
-1.732
-1.714
-1.712
Token Hampshire
Token ID13910
Feature activation+6.99e-01

Pos logit contributions
grain+0.695
urdue+0.662
ellar+0.659
 Windsor+0.647
font+0.636
Neg logit contributions
 Debor-0.918
-0.820
-0.776
 MSM-0.771
 unsus-0.758
Token.
Token ID13
Feature activation-3.44e+00

Pos logit contributions
 Debor+0.521
+0.457
+0.429
 MSM+0.426
 unsus+0.416
Neg logit contributions
grain-0.529
urdue-0.507
ellar-0.506
 Windsor-0.496
font-0.490
Token Hide
Token ID10415
Feature activation-7.80e+00

Pos logit contributions
grain+1.773
urdue+1.684
ellar+1.663
 Windsor+1.653
font+1.612
Neg logit contributions
 Debor-3.344
-3.054
-2.915
 unsus-2.883
 MSM-2.880
Token Caption
Token ID11260
Feature activation+3.21e-01

Pos logit contributions
grain+3.932
 Windsor+3.683
urdue+3.670
ellar+3.624
font+3.619
Neg logit contributions
 Debor-7.584
-6.959
 unden-6.665
 unsus-6.651
vertisement-6.575
Token 6
Token ID718
Feature activation-3.03e+00

Pos logit contributions
 Debor+0.288
+0.253
 MSM+0.249
+0.248
+0.238
Neg logit contributions
grain-0.191
urdue-0.185
ellar-0.185
afety-0.174
 Windsor-0.174
Token of
Token ID286
Feature activation-5.22e-01

Pos logit contributions
grain+2.137
ellar+2.031
urdue+2.030
 Windsor+1.993
font+1.978
Neg logit contributions
 Debor-2.420
-2.139
-2.007
 MSM-1.998
 unsus-1.975
Token 15
Token ID1315
Feature activation-2.45e-01

Pos logit contributions
grain+0.287
urdue+0.273
ellar+0.270
 Windsor+0.259
afety+0.257
Neg logit contributions
 Debor-0.498
-0.449
-0.431
 MSM-0.430
-0.419
Token Photos
Token ID9434
Feature activation+2.20e+00

Pos logit contributions
grain+0.132
urdue+0.126
ellar+0.125
 Windsor+0.120
afety+0.119
Neg logit contributions
 Debor-0.236
-0.214
-0.204
 MSM-0.203
-0.198
Token his
Token ID465
Feature activation-1.58e+00

Pos logit contributions
 Debor+0.189
+0.166
+0.157
 MSM+0.156
 unsus+0.152
Neg logit contributions
grain-0.183
urdue-0.176
ellar-0.175
 Windsor-0.173
font-0.170
Token initial
Token ID4238
Feature activation-1.21e+00

Pos logit contributions
grain+1.078
urdue+1.022
ellar+1.020
 Windsor+1.011
font+1.000
Neg logit contributions
 Debor-1.291
-1.139
-1.085
 MSM-1.078
 unsus-1.050
Token pick
Token ID2298
Feature activation+2.25e+00

Pos logit contributions
grain+0.929
urdue+0.889
ellar+0.885
 Windsor+0.879
font+0.868
Neg logit contributions
 Debor-0.891
-0.775
-0.730
 MSM-0.724
 unsus-0.706
Token from
Token ID422
Feature activation-1.47e+00

Pos logit contributions
 Debor+1.726
+1.528
+1.430
 MSM+1.421
 unsus+1.390
Neg logit contributions
grain-1.647
urdue-1.584
ellar-1.578
 Windsor-1.543
font-1.510
Token Lone
Token ID23405
Feature activation-1.68e+00

Pos logit contributions
grain+1.039
urdue+0.991
ellar+0.987
 Windsor+0.984
font+0.961
Neg logit contributions
 Debor-1.155
-1.024
-0.961
 MSM-0.953
 unsus-0.939
Token Druid
Token ID32685
Feature activation+4.71e+00

Pos logit contributions
grain+0.994
ellar+0.933
urdue+0.930
 Windsor+0.916
font+0.907
Neg logit contributions
 Debor-1.525
-1.373
-1.308
 MSM-1.294
-1.281
Token to
Token ID284
Feature activation-3.45e-02

Pos logit contributions
 Debor+3.301
+2.910
+2.727
 MSM+2.694
 melanch+2.617
Neg logit contributions
grain-3.682
urdue-3.570
ellar-3.561
 Windsor-3.452
afety-3.396
Token Templar
Token ID41741
Feature activation+1.37e+00

Pos logit contributions
grain+0.024
urdue+0.023
ellar+0.023
 Windsor+0.023
font+0.022
Neg logit contributions
 Debor-0.028
-0.024
-0.023
 MSM-0.023
 unsus-0.022
Token Assassin
Token ID21401
Feature activation+3.06e+00

Pos logit contributions
 Debor+1.122
+0.994
 MSM+0.940
+0.938
 unsus+0.919
Neg logit contributions
grain-0.929
urdue-0.890
ellar-0.889
 Windsor-0.863
font-0.852
Token.
Token ID13
Feature activation-4.61e-01

Pos logit contributions
 Debor+2.309
+2.038
+1.912
 MSM+1.896
 unsus+1.856
Neg logit contributions
grain-2.279
ellar-2.186
urdue-2.185
 Windsor-2.131
font-2.097
Token He
Token ID679
Feature activation+1.78e-01

Pos logit contributions
grain+0.315
urdue+0.301
ellar+0.300
 Windsor+0.295
font+0.290
Neg logit contributions
 Debor-0.377
-0.335
-0.317
 MSM-0.314
 unsus-0.309
Token capital
Token ID3139
Feature activation+1.77e-02

Pos logit contributions
grain+0.082
urdue+0.078
ellar+0.078
 Windsor+0.076
font+0.075
Neg logit contributions
 Debor-0.089
-0.079
-0.074
 MSM-0.074
 unsus-0.072
Token is
Token ID318
Feature activation+3.43e+00

Pos logit contributions
 Debor+0.015
+0.013
+0.012
 MSM+0.012
 unsus+0.012
Neg logit contributions
grain-0.012
urdue-0.011
ellar-0.011
 Windsor-0.011
font-0.011
Token rep
Token ID1128
Feature activation+3.15e+00

Pos logit contributions
 Debor+2.655
+2.333
 MSM+2.199
+2.193
 unsus+2.161
Neg logit contributions
grain-2.504
urdue-2.389
ellar-2.383
afety-2.295
font-2.287
Tokenlete
Token ID5807
Feature activation+1.99e+00

Pos logit contributions
 Debor+2.138
+1.843
+1.720
 MSM+1.700
 unsus+1.664
Neg logit contributions
grain-2.547
urdue-2.450
ellar-2.447
 Windsor-2.425
afety-2.370
Token with
Token ID351
Feature activation+2.67e-01

Pos logit contributions
 Debor+1.285
+1.100
+1.021
 MSM+1.013
 unsus+0.986
Neg logit contributions
grain-1.706
urdue-1.645
ellar-1.644
 Windsor-1.617
font-1.595
Token memorial
Token ID17357
Feature activation+5.30e+00

Pos logit contributions
 Debor+0.184
+0.159
+0.149
 MSM+0.147
 unsus+0.143
Neg logit contributions
grain-0.217
urdue-0.209
ellar-0.208
 Windsor-0.205
font-0.202
Tokens
Token ID82
Feature activation+9.26e-01

Pos logit contributions
 Debor+3.827
+3.429
+3.200
 MSM+3.148
 melanch+3.073
Neg logit contributions
grain-3.986
urdue-3.866
ellar-3.850
 Windsor-3.722
afety-3.713
Token to
Token ID284
Feature activation-5.30e-01

Pos logit contributions
 Debor+0.731
+0.646
+0.608
 MSM+0.605
 unsus+0.592
Neg logit contributions
grain-0.660
urdue-0.632
ellar-0.630
 Windsor-0.617
font-0.608
Token presidents
Token ID19033
Feature activation+8.25e-01

Pos logit contributions
grain+0.362
urdue+0.346
ellar+0.345
 Windsor+0.339
font+0.333
Neg logit contributions
 Debor-0.433
-0.385
-0.363
 MSM-0.360
 unsus-0.352
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
 Debor+0.655
+0.579
+0.546
 MSM+0.543
 unsus+0.531
Neg logit contributions
grain-0.584
urdue-0.559
ellar-0.557
 Windsor-0.546
font-0.538
Token veterans
Token ID11255
Feature activation+1.07e+00

Pos logit contributions
grain+0.903
urdue+0.867
ellar+0.861
 Windsor+0.857
font+0.836
Neg logit contributions
 Debor-1.029
-0.916
-0.865
 MSM-0.849
-0.836
Token a
Token ID257
Feature activation+2.44e+00

Pos logit contributions
 Debor+2.236
+1.928
 MSM+1.876
+1.832
 unsus+1.813
Neg logit contributions
grain-1.979
urdue-1.907
ellar-1.897
 Windsor-1.821
font-1.821
Token program
Token ID1430
Feature activation+2.30e+00

Pos logit contributions
 Debor+1.883
+1.641
 MSM+1.576
+1.562
 melanch+1.526
Neg logit contributions
grain-1.765
urdue-1.705
ellar-1.702
font-1.636
afety-1.636
Token he
Token ID339
Feature activation+1.25e+00

Pos logit contributions
 Debor+1.790
+1.567
 MSM+1.481
+1.476
 unsus+1.447
Neg logit contributions
grain-1.662
urdue-1.601
ellar-1.586
 Windsor-1.547
font-1.531
Token thought
Token ID1807
Feature activation-1.09e+00

Pos logit contributions
 Debor+1.004
+0.889
+0.841
 MSM+0.836
 unsus+0.823
Neg logit contributions
grain-0.879
ellar-0.841
urdue-0.835
 Windsor-0.820
font-0.805
Token was
Token ID373
Feature activation+2.88e+00

Pos logit contributions
grain+0.764
urdue+0.729
 Windsor+0.720
ellar+0.720
font+0.705
Neg logit contributions
 Debor-0.877
-0.778
-0.732
 MSM-0.719
-0.711
Token rational
Token ID9377
Feature activation+4.75e+00

Pos logit contributions
 Debor+2.300
+2.014
 MSM+1.934
 unsus+1.910
+1.905
Neg logit contributions
grain-2.010
ellar-1.932
urdue-1.932
afety-1.853
 Windsor-1.848
Token over
Token ID625
Feature activation-2.04e-02

Pos logit contributions
 Debor+3.478
+3.040
 MSM+2.885
+2.837
 unsus+2.765
Neg logit contributions
grain-3.587
urdue-3.432
ellar-3.419
 Windsor-3.373
font-3.315
Token the
Token ID262
Feature activation-4.49e-01

Pos logit contributions
grain+0.014
urdue+0.013
ellar+0.013
 Windsor+0.013
font+0.013
Neg logit contributions
 Debor-0.017
-0.015
-0.014
 MSM-0.014
 unsus-0.014
Token objections
Token ID21954
Feature activation-1.60e+00

Pos logit contributions
grain+0.328
urdue+0.315
ellar+0.314
 Windsor+0.306
font+0.303
Neg logit contributions
 Debor-0.346
-0.304
-0.287
 MSM-0.286
 unsus-0.279
Token of
Token ID286
Feature activation+6.50e-01

Pos logit contributions
grain+1.103
ellar+1.057
urdue+1.057
 Windsor+1.044
font+1.014
Neg logit contributions
 Debor-1.287
-1.147
-1.086
 MSM-1.063
 unsus-1.059
Token the
Token ID262
Feature activation-3.46e-01

Pos logit contributions
 Debor+0.491
+0.431
+0.405
 MSM+0.403
 unsus+0.393
Neg logit contributions
grain-0.485
urdue-0.465
ellar-0.464
 Windsor-0.455
font-0.449
Token those
Token ID883
Feature activation+2.89e+00

Pos logit contributions
 Debor+1.881
+1.664
+1.566
 MSM+1.559
 unsus+1.526
Neg logit contributions
grain-1.695
urdue-1.628
ellar-1.612
 Windsor-1.577
font-1.560
Token of
Token ID286
Feature activation+1.54e+00

Pos logit contributions
 Debor+2.226
+1.948
+1.841
 MSM+1.837
 unsus+1.809
Neg logit contributions
grain-2.113
urdue-2.033
ellar-2.018
 Windsor-1.965
afety-1.941
Token ausp
Token ID45062
Feature activation-1.71e-01

Pos logit contributions
 Debor+1.211
+1.066
+1.001
 MSM+1.000
 unsus+0.981
Neg logit contributions
grain-1.099
urdue-1.059
ellar-1.052
 Windsor-1.021
font-1.016
Tokenicious
Token ID6243
Feature activation+1.13e+00

Pos logit contributions
grain+0.126
urdue+0.122
ellar+0.121
 Windsor+0.119
font+0.117
Neg logit contributions
 Debor-0.130
-0.114
-0.108
 MSM-0.107
 unsus-0.104
Token or
Token ID393
Feature activation+1.55e+00

Pos logit contributions
 Debor+0.915
+0.811
+0.766
 MSM+0.762
 unsus+0.746
Neg logit contributions
grain-0.777
urdue-0.743
ellar-0.741
 Windsor-0.724
font-0.714
Token (
Token ID357
Feature activation+4.51e+00

Pos logit contributions
 Debor+1.200
+1.059
+0.997
 MSM+0.993
 unsus+0.974
Neg logit contributions
grain-1.122
urdue-1.077
ellar-1.072
 Windsor-1.047
font-1.035
Tokenfor
Token ID1640
Feature activation+3.97e+00

Pos logit contributions
 Debor+3.721
+3.372
+3.209
 MSM+3.115
+3.076
Neg logit contributions
grain-2.873
urdue-2.843
ellar-2.810
 Windsor-2.761
afety-2.691
Token boys
Token ID6510
Feature activation+4.47e+00

Pos logit contributions
 Debor+3.030
+2.652
+2.518
 MSM+2.508
 unsus+2.438
Neg logit contributions
grain-2.860
urdue-2.806
ellar-2.787
 Windsor-2.687
font-2.686
Token)
Token ID8
Feature activation+2.41e+00

Pos logit contributions
 Debor+3.408
+3.004
+2.848
 MSM+2.835
 unsus+2.810
Neg logit contributions
grain-3.232
urdue-3.085
ellar-3.072
 Windsor-3.016
font-2.968
Token man
Token ID582
Feature activation+3.88e+00

Pos logit contributions
 Debor+1.847
+1.632
+1.531
 MSM+1.527
 unsus+1.496
Neg logit contributions
grain-1.761
urdue-1.703
ellar-1.690
 Windsor-1.647
font-1.625
Tokenly
Token ID306
Feature activation+1.66e+00

Pos logit contributions
 Debor+3.137
+2.775
+2.632
 MSM+2.585
 melanch+2.538
Neg logit contributions
grain-2.658
urdue-2.565
ellar-2.499
 Windsor-2.489
afety-2.432
Token/
Token ID14
Feature activation+2.67e+00

Pos logit contributions
 Debor+0.527
+0.466
 MSM+0.442
+0.439
 unsus+0.431
Neg logit contributions
grain-0.419
urdue-0.401
ellar-0.400
 Windsor-0.389
font-0.384
Tokenor
Token ID273
Feature activation+1.14e+00

Pos logit contributions
 Debor+1.799
+1.574
+1.486
 MSM+1.451
 unsus+1.394
Neg logit contributions
grain-2.145
urdue-2.095
ellar-2.072
 Windsor-2.056
afety-2.016
Token Survival
Token ID20303
Feature activation+3.01e+00

Pos logit contributions
 Debor+0.958
+0.843
 MSM+0.807
+0.794
 unsus+0.784
Neg logit contributions
grain-0.749
urdue-0.721
ellar-0.717
 Windsor-0.694
font-0.689
Token+
Token ID10
Feature activation-8.73e-02

Pos logit contributions
 Debor+2.421
+2.145
 MSM+2.031
+2.023
 unsus+1.963
Neg logit contributions
grain-2.062
ellar-1.998
urdue-1.996
 Windsor-1.932
font-1.902
Token The
Token ID383
Feature activation+5.11e-01

Pos logit contributions
grain+0.064
urdue+0.061
ellar+0.061
 Windsor+0.060
font+0.059
Neg logit contributions
 Debor-0.067
-0.059
-0.056
 MSM-0.055
 unsus-0.054
Token Prim
Token ID11460
Feature activation+5.16e+00

Pos logit contributions
 Debor+0.428
+0.378
 MSM+0.359
+0.359
 unsus+0.350
Neg logit contributions
grain-0.340
urdue-0.327
ellar-0.325
 Windsor-0.317
font-0.312
Tokener
Token ID263
Feature activation+9.50e-01

Pos logit contributions
 Debor+3.700
+3.091
 MSM+3.012
+2.967
 unsus+2.910
Neg logit contributions
grain-3.966
urdue-3.864
ellar-3.787
 Windsor-3.709
afety-3.668
Token from
Token ID422
Feature activation+9.25e-01

Pos logit contributions
 Debor+0.748
+0.658
+0.620
 MSM+0.620
 unsus+0.605
Neg logit contributions
grain-0.679
urdue-0.652
ellar-0.651
 Windsor-0.635
font-0.626
Token your
Token ID534
Feature activation+1.35e+00

Pos logit contributions
 Debor+0.751
+0.656
 MSM+0.622
+0.621
 unsus+0.604
Neg logit contributions
grain-0.645
urdue-0.620
ellar-0.618
 Windsor-0.598
font-0.592
Token local
Token ID1957
Feature activation+4.29e+00

Pos logit contributions
 Debor+1.061
+0.935
+0.882
 MSM+0.878
 unsus+0.858
Neg logit contributions
grain-0.966
urdue-0.926
ellar-0.923
 Windsor-0.903
font-0.890
Token book
Token ID1492
Feature activation+3.23e+00

Pos logit contributions
 Debor+3.425
+3.006
 MSM+2.921
+2.843
 unsus+2.808
Neg logit contributions
grain-2.938
urdue-2.874
ellar-2.826
 Windsor-2.705
afety-2.689
Token be
Token ID307
Feature activation-1.03e+00

Pos logit contributions
grain+0.283
urdue+0.270
ellar+0.269
 Windsor+0.264
font+0.260
Neg logit contributions
 Debor-0.338
-0.300
-0.283
 MSM-0.281
 unsus-0.275
Token confronted
Token ID16675
Feature activation-1.36e-01

Pos logit contributions
grain+0.703
urdue+0.674
ellar+0.669
 Windsor+0.660
font+0.649
Neg logit contributions
 Debor-0.833
-0.744
-0.704
 MSM-0.694
-0.684
Token almost
Token ID2048
Feature activation+3.98e-01

Pos logit contributions
grain+0.107
urdue+0.103
ellar+0.103
 Windsor+0.101
font+0.100
Neg logit contributions
 Debor-0.096
-0.084
-0.079
 MSM-0.078
 unsus-0.076
Token immediately
Token ID3393
Feature activation-9.33e-01

Pos logit contributions
 Debor+0.305
+0.269
+0.252
 MSM+0.250
+0.244
Neg logit contributions
grain-0.293
urdue-0.281
ellar-0.280
 Windsor-0.275
font-0.271
Token by
Token ID416
Feature activation+8.98e-01

Pos logit contributions
grain+0.697
urdue+0.672
ellar+0.667
 Windsor+0.656
font+0.650
Neg logit contributions
 Debor-0.699
-0.616
-0.579
 MSM-0.574
-0.560
Token the
Token ID262
Feature activation+2.73e-01

Pos logit contributions
 Debor+0.696
+0.613
+0.577
 MSM+0.575
 unsus+0.561
Neg logit contributions
grain-0.653
urdue-0.626
ellar-0.624
 Windsor-0.611
font-0.603
Token staggering
Token ID23508
Feature activation+1.92e+00

Pos logit contributions
 Debor+0.208
+0.183
+0.172
 MSM+0.171
 unsus+0.167
Neg logit contributions
grain-0.202
urdue-0.194
ellar-0.193
 Windsor-0.189
font-0.187
Token dimensions
Token ID15225
Feature activation+1.19e+00

Pos logit contributions
 Debor+1.437
+1.259
 MSM+1.188
+1.181
 unsus+1.154
Neg logit contributions
grain-1.449
urdue-1.391
ellar-1.387
 Windsor-1.353
font-1.336
Token of
Token ID286
Feature activation+2.01e+00

Pos logit contributions
 Debor+0.927
+0.819
+0.772
 MSM+0.766
 unsus+0.749
Neg logit contributions
grain-0.858
urdue-0.822
ellar-0.819
 Windsor-0.804
font-0.793
Token my
Token ID616
Feature activation+8.31e-01

Pos logit contributions
 Debor+1.488
+1.294
 MSM+1.225
+1.216
 unsus+1.189
Neg logit contributions
grain-1.525
ellar-1.464
urdue-1.463
 Windsor-1.422
font-1.412
Token own
Token ID898
Feature activation-6.30e-01

Pos logit contributions
 Debor+0.612
+0.536
+0.503
 MSM+0.500
 unsus+0.489
Neg logit contributions
grain-0.636
urdue-0.610
ellar-0.609
 Windsor-0.597
font-0.590
TokenWrit
Token ID20257
Feature activation-1.97e+00

Pos logit contributions
 Debor+0.327
+0.289
+0.272
 MSM+0.270
 unsus+0.263
Neg logit contributions
grain-0.305
urdue-0.292
ellar-0.291
 Windsor-0.285
font-0.281
Tokenters
Token ID1010
Feature activation+5.74e-01

Pos logit contributions
grain+1.440
ellar+1.377
urdue+1.373
 Windsor+1.351
font+1.332
Neg logit contributions
 Debor-1.511
-1.344
-1.263
 MSM-1.242
 unsus-1.224
Token Strike
Token ID12282
Feature activation-2.39e+00

Pos logit contributions
 Debor+0.474
+0.419
+0.397
 MSM+0.395
 unsus+0.386
Neg logit contributions
grain-0.389
urdue-0.373
ellar-0.371
 Windsor-0.362
font-0.357
Token 2008
Token ID3648
Feature activation-1.37e+00

Pos logit contributions
grain+1.540
urdue+1.464
ellar+1.462
 Windsor+1.440
font+1.415
Neg logit contributions
 Debor-2.040
-1.831
-1.733
 MSM-1.714
 unsus-1.689
Token01
Token ID486
Feature activation-4.07e-02

Pos logit contributions
grain+1.006
urdue+0.964
ellar+0.962
 Windsor+0.945
font+0.932
Neg logit contributions
 Debor-1.054
-0.929
-0.872
 MSM-0.868
 unsus-0.850
Token04
Token ID3023
Feature activation+4.90e-01

Pos logit contributions
grain+0.025
urdue+0.023
ellar+0.023
 Windsor+0.023
font+0.022
Neg logit contributions
 Debor-0.036
-0.033
-0.031
 MSM-0.031
 unsus-0.030
Token O
Token ID440
Feature activation-1.83e+00

Pos logit contributions
 Debor+0.464
+0.418
 MSM+0.399
+0.398
 unsus+0.388
Neg logit contributions
grain-0.274
ellar-0.258
urdue-0.258
 Windsor-0.248
font-0.245
Token&
Token ID5
Feature activation+5.44e-01

Pos logit contributions
grain+1.589
urdue+1.531
ellar+1.531
 Windsor+1.504
font+1.490
Neg logit contributions
 Debor-1.162
-0.988
-0.914
 MSM-0.906
 unsus-0.888
TokenA
Token ID32
Feature activation-1.92e+00

Pos logit contributions
 Debor+0.344
+0.300
 MSM+0.275
+0.274
+0.264
Neg logit contributions
grain-0.472
urdue-0.460
ellar-0.454
 Windsor-0.444
afety-0.439
Token-
Token ID12
Feature activation+4.76e-02

Pos logit contributions
grain+1.169
urdue+1.118
ellar+1.116
 Windsor+1.101
font+1.076
Neg logit contributions
 Debor-1.691
-1.524
-1.449
 MSM-1.430
 unsus-1.422
TokenWOR
Token ID45359
Feature activation-3.93e+00

Pos logit contributions
 Debor+0.037
+0.033
+0.031
 MSM+0.031
 unsus+0.030
Neg logit contributions
grain-0.034
urdue-0.033
ellar-0.033
 Windsor-0.032
font-0.032
Token?
Token ID30
Feature activation+4.44e-01

Pos logit contributions
grain+0.496
urdue+0.475
ellar+0.474
 Windsor+0.465
font+0.457
Neg logit contributions
 Debor-0.582
-0.516
-0.487
 MSM-0.484
 unsus-0.474
Token She
Token ID1375
Feature activation-2.79e-01

Pos logit contributions
 Debor+0.395
+0.353
+0.335
 MSM+0.334
 unsus+0.327
Neg logit contributions
grain-0.273
urdue-0.260
ellar-0.260
 Windsor-0.252
font-0.248
Token said
Token ID531
Feature activation-3.58e-01

Pos logit contributions
grain+0.174
urdue+0.166
ellar+0.165
 Windsor+0.162
font+0.159
Neg logit contributions
 Debor-0.245
-0.219
-0.208
 MSM-0.207
 unsus-0.203
Token:
Token ID25
Feature activation+1.23e+00

Pos logit contributions
grain+0.265
urdue+0.254
ellar+0.253
 Windsor+0.249
font+0.245
Neg logit contributions
 Debor-0.273
-0.240
-0.226
 MSM-0.224
 unsus-0.219
Token I
Token ID314
Feature activation-3.11e-01

Pos logit contributions
 Debor+1.013
+0.886
 MSM+0.847
+0.842
 unsus+0.817
Neg logit contributions
grain-0.843
urdue-0.813
ellar-0.810
 Windsor-0.776
font-0.775
Token I
Token ID314
Feature activation+1.23e-01

Pos logit contributions
grain+0.215
urdue+0.205
ellar+0.205
 Windsor+0.201
font+0.198
Neg logit contributions
 Debor-0.252
-0.224
-0.211
 MSM-0.210
 unsus-0.206
Token asked
Token ID1965
Feature activation-1.90e+00

Pos logit contributions
 Debor+0.102
+0.090
+0.085
 MSM+0.085
 unsus+0.083
Neg logit contributions
grain-0.083
urdue-0.079
ellar-0.079
 Windsor-0.077
font-0.076
Token:
Token ID25
Feature activation+9.65e-01

Pos logit contributions
grain+1.229
urdue+1.171
ellar+1.167
 Windsor+1.145
font+1.124
Neg logit contributions
 Debor-1.624
-1.452
-1.378
 MSM-1.365
 unsus-1.339
Token What
Token ID1867
Feature activation-1.44e+00

Pos logit contributions
 Debor+0.805
+0.708
 MSM+0.677
+0.669
 unsus+0.658
Neg logit contributions
grain-0.646
urdue-0.623
ellar-0.623
 Windsor-0.596
font-0.592
Token is
Token ID318
Feature activation-2.28e+00

Pos logit contributions
grain+0.946
urdue+0.900
ellar+0.897
 Windsor+0.880
font+0.866
Neg logit contributions
 Debor-1.217
-1.085
-1.028
 MSM-1.021
 unsus-1.001
Token the
Token ID262
Feature activation-3.31e+00

Pos logit contributions
grain+1.518
urdue+1.444
ellar+1.438
 Windsor+1.426
font+1.395
Neg logit contributions
 Debor-1.896
-1.696
-1.601
 MSM-1.582
-1.563
Token SOLD
Token ID48671
Feature activation-5.36e-01

Pos logit contributions
 Debor+0.995
+0.867
+0.810
 MSM+0.807
 unsus+0.785
Neg logit contributions
grain-1.098
urdue-1.055
ellar-1.052
 Windsor-1.032
font-1.019
TokenIER
Token ID38311
Feature activation+1.27e+00

Pos logit contributions
grain+0.394
urdue+0.381
ellar+0.378
 Windsor+0.374
font+0.368
Neg logit contributions
 Debor-0.408
-0.356
-0.337
 MSM-0.331
 unsus-0.329
Token L
Token ID406
Feature activation+1.83e+00

Pos logit contributions
 Debor+0.967
+0.852
+0.799
 MSM+0.798
 unsus+0.776
Neg logit contributions
grain-0.942
urdue-0.902
ellar-0.900
 Windsor-0.880
font-0.868
Token:
Token ID25
Feature activation+2.92e+00

Pos logit contributions
 Debor+1.295
+1.127
+1.054
 MSM+1.046
 unsus+1.020
Neg logit contributions
grain-1.449
urdue-1.394
ellar-1.391
 Windsor-1.366
font-1.348
TokenVB
Token ID44526
Feature activation+1.44e+00

Pos logit contributions
 Debor+2.179
+1.918
 MSM+1.801
+1.800
 unsus+1.735
Neg logit contributions
grain-2.209
ellar-2.119
urdue-2.117
 Windsor-2.056
font-2.037
Token 5
Token ID642
Feature activation+2.37e+00

Pos logit contributions
 Debor+1.055
+0.924
+0.866
 MSM+0.861
 unsus+0.839
Neg logit contributions
grain-1.107
urdue-1.062
ellar-1.060
 Windsor-1.039
font-1.025
Token92
Token ID5892
Feature activation+2.78e+00

Pos logit contributions
 Debor+1.724
+1.512
+1.414
 MSM+1.408
 unsus+1.367
Neg logit contributions
grain-1.838
urdue-1.765
ellar-1.763
 Windsor-1.726
font-1.704
Token 4
Token ID604
Feature activation+1.76e+00

Pos logit contributions
 Debor+2.120
+1.871
+1.758
 MSM+1.754
+1.696
Neg logit contributions
grain-2.044
urdue-1.961
ellar-1.960
 Windsor-1.910
font-1.885
Token78
Token ID3695
Feature activation+2.39e+00

Pos logit contributions
 Debor+1.223
+1.063
+0.992
 MSM+0.985
 unsus+0.958
Neg logit contributions
grain-1.413
urdue-1.360
ellar-1.357
 Windsor-1.332
font-1.315
Token T
Token ID309
Feature activation+2.31e+00

Pos logit contributions
 Debor+1.943
+1.724
+1.628
 MSM+1.626
 unsus+1.574
Neg logit contributions
grain-1.646
ellar-1.573
urdue-1.572
 Windsor-1.524
font-1.507
Token:
Token ID25
Feature activation+8.17e-01

Pos logit contributions
 Debor+1.638
+1.428
+1.335
 MSM+1.326
 unsus+1.291
Neg logit contributions
grain-1.833
urdue-1.761
ellar-1.756
 Windsor-1.725
font-1.702
Tokens
Token ID82
Feature activation-2.93e+00

Pos logit contributions
 Debor+0.532
+0.469
+0.441
 MSM+0.439
 unsus+0.429
Neg logit contributions
grain-0.502
urdue-0.481
ellar-0.480
 Windsor-0.470
font-0.463
Token is
Token ID318
Feature activation+8.55e-01

Pos logit contributions
grain+1.807
urdue+1.722
ellar+1.709
 Windsor+1.690
font+1.666
Neg logit contributions
 Debor-2.542
-2.289
-2.174
 MSM-2.162
-2.137
Token a
Token ID257
Feature activation-3.39e-02

Pos logit contributions
 Debor+0.682
+0.603
+0.568
 MSM+0.566
 unsus+0.553
Neg logit contributions
grain-0.603
urdue-0.577
ellar-0.576
 Windsor-0.563
font-0.555
Token modern
Token ID3660
Feature activation-9.96e-02

Pos logit contributions
grain+0.025
urdue+0.024
ellar+0.024
 Windsor+0.023
font+0.023
Neg logit contributions
 Debor-0.026
-0.023
-0.022
 MSM-0.022
 unsus-0.021
Token,
Token ID11
Feature activation-5.25e-01

Pos logit contributions
grain+0.073
urdue+0.070
ellar+0.070
 Windsor+0.068
font+0.067
Neg logit contributions
 Debor-0.077
-0.068
-0.064
 MSM-0.063
 unsus-0.062
Token multi
Token ID5021
Feature activation+1.96e+00

Pos logit contributions
grain+0.384
urdue+0.367
ellar+0.367
 Windsor+0.362
font+0.356
Neg logit contributions
 Debor-0.404
-0.356
-0.335
 MSM-0.331
-0.324
Token-
Token ID12
Feature activation-2.06e+00

Pos logit contributions
 Debor+1.655
+1.484
+1.405
 MSM+1.396
 unsus+1.366
Neg logit contributions
grain-1.270
urdue-1.217
ellar-1.211
 Windsor-1.184
font-1.158
Tokenbillion
Token ID24540
Feature activation+2.18e+00

Pos logit contributions
grain+1.388
ellar+1.298
urdue+1.291
font+1.284
 Windsor+1.272
Neg logit contributions
 Debor-1.718
-1.523
 MSM-1.433
-1.432
 unsus-1.401
Token dollar
Token ID8872
Feature activation+1.66e+00

Pos logit contributions
 Debor+1.431
+1.240
+1.153
 MSM+1.139
 unsus+1.108
Neg logit contributions
grain-1.832
urdue-1.777
ellar-1.769
 Windsor-1.737
font-1.711
Token campaign
Token ID1923
Feature activation+1.46e+00

Pos logit contributions
 Debor+1.247
+1.091
+1.026
 MSM+1.025
 unsus+0.998
Neg logit contributions
grain-1.254
urdue-1.204
ellar-1.202
 Windsor-1.174
font-1.158
Token to
Token ID284
Feature activation-8.87e-01

Pos logit contributions
 Debor+1.103
+0.967
+0.909
 MSM+0.905
 unsus+0.884
Neg logit contributions
grain-1.091
urdue-1.046
ellar-1.045
 Windsor-1.023
font-1.008
Token OF
Token ID3963
Feature activation+1.82e-01

Pos logit contributions
 Debor+0.077
+0.067
+0.063
 MSM+0.062
 unsus+0.062
Neg logit contributions
grain-0.079
urdue-0.076
ellar-0.076
 Windsor-0.075
font-0.074
Token EXT
Token ID27489
Feature activation-8.50e-01

Pos logit contributions
 Debor+0.138
+0.122
+0.115
 MSM+0.113
 unsus+0.112
Neg logit contributions
grain-0.134
urdue-0.129
ellar-0.129
 Windsor-0.127
font-0.125
TokenREM
Token ID40726
Feature activation+4.33e-02

Pos logit contributions
grain+0.525
urdue+0.500
ellar+0.499
 Windsor+0.487
font+0.478
Neg logit contributions
 Debor-0.752
-0.673
-0.640
 MSM-0.635
 unsus-0.624
TokenELY
Token ID30943
Feature activation-6.13e-01

Pos logit contributions
 Debor+0.032
+0.028
+0.027
 MSM+0.026
 unsus+0.026
Neg logit contributions
grain-0.033
urdue-0.031
ellar-0.031
 Windsor-0.031
font-0.030
Token EXP
Token ID25703
Feature activation-1.41e+00

Pos logit contributions
grain+0.472
urdue+0.453
ellar+0.452
 Windsor+0.444
font+0.438
Neg logit contributions
 Debor-0.449
-0.393
-0.368
 MSM-0.365
 unsus-0.357
TokenENS
Token ID16938
Feature activation-1.32e+00

Pos logit contributions
grain+0.992
ellar+0.951
urdue+0.951
 Windsor+0.937
font+0.924
Neg logit contributions
 Debor-1.120
-0.989
-0.935
 MSM-0.925
 unsus-0.914
TokenIVE
Token ID9306
Feature activation+3.30e-01

Pos logit contributions
grain+1.418
ellar+1.380
urdue+1.374
 Windsor+1.362
font+1.350
Neg logit contributions
 Debor-0.568
-0.436
-0.384
 MSM-0.376
 unsus-0.374
Token BE
Token ID9348
Feature activation-1.52e+00

Pos logit contributions
 Debor+0.239
+0.209
+0.196
 MSM+0.195
 unsus+0.190
Neg logit contributions
grain-0.256
urdue-0.246
ellar-0.246
 Windsor-0.241
font-0.238
TokenER
Token ID1137
Feature activation-1.85e+00

Pos logit contributions
grain+1.152
urdue+1.106
ellar+1.106
 Windsor+1.087
font+1.078
Neg logit contributions
 Debor-1.129
-0.976
-0.929
 MSM-0.912
 unsus-0.907
Token WITHOUT
Token ID42881
Feature activation+4.25e-01

Pos logit contributions
grain+1.307
urdue+1.252
ellar+1.248
 Windsor+1.233
font+1.216
Neg logit contributions
 Debor-1.470
-1.282
-1.218
 unsus-1.207
 MSM-1.189
Token THE
Token ID3336
Feature activation+3.36e-01

Pos logit contributions
 Debor+0.313
+0.273
+0.257
 MSM+0.254
 unsus+0.250
Neg logit contributions
grain-0.326
urdue-0.313
ellar-0.312
 Windsor-0.307
font-0.303
Token larger
Token ID4025
Feature activation-1.27e-01

Pos logit contributions
grain+0.969
ellar+0.922
urdue+0.921
 Windsor+0.907
font+0.891
Neg logit contributions
 Debor-1.163
-1.038
-0.979
 MSM-0.965
-0.951
Token (
Token ID357
Feature activation+8.33e-01

Pos logit contributions
grain+0.087
urdue+0.083
ellar+0.083
 Windsor+0.082
font+0.080
Neg logit contributions
 Debor-0.104
-0.092
-0.087
 MSM-0.087
 unsus-0.085
Token3
Token ID18
Feature activation-2.25e+00

Pos logit contributions
 Debor+0.619
+0.546
+0.514
 MSM+0.508
 unsus+0.497
Neg logit contributions
grain-0.624
urdue-0.604
ellar-0.602
 Windsor-0.590
afety-0.579
Token.
Token ID13
Feature activation-5.16e-01

Pos logit contributions
grain+1.621
urdue+1.550
ellar+1.544
 Windsor+1.531
font+1.510
Neg logit contributions
 Debor-1.760
-1.533
-1.457
 MSM-1.440
 unsus-1.423
Token9
Token ID24
Feature activation+1.68e-01

Pos logit contributions
grain+0.373
urdue+0.358
ellar+0.357
 Windsor+0.350
font+0.345
Neg logit contributions
 Debor-0.402
-0.354
-0.334
 MSM-0.331
 unsus-0.325
Token
Token ID784
Feature activation-2.03e+00

Pos logit contributions
 Debor+0.127
+0.112
+0.105
 MSM+0.105
 unsus+0.102
Neg logit contributions
grain-0.125
urdue-0.120
ellar-0.119
 Windsor-0.117
font-0.115
Token 4
Token ID604
Feature activation+6.06e-01

Pos logit contributions
grain+1.203
urdue+1.137
ellar+1.131
 Windsor+1.115
font+1.092
Neg logit contributions
 Debor-1.841
-1.659
-1.578
 MSM-1.563
 unsus-1.536
Token.
Token ID13
Feature activation+2.32e+00

Pos logit contributions
 Debor+0.445
+0.391
+0.365
 MSM+0.364
 unsus+0.354
Neg logit contributions
grain-0.464
urdue-0.446
ellar-0.445
 Windsor-0.436
font-0.430
Token5
Token ID20
Feature activation+1.23e+00

Pos logit contributions
 Debor+1.754
+1.541
+1.451
 MSM+1.438
 unsus+1.402
Neg logit contributions
grain-1.723
ellar-1.647
urdue-1.645
 Windsor-1.614
afety-1.584
Token kg
Token ID14211
Feature activation-1.72e+00

Pos logit contributions
 Debor+0.829
+0.724
 MSM+0.672
+0.670
+0.649
Neg logit contributions
grain-1.006
urdue-0.971
ellar-0.968
 Windsor-0.947
font-0.933
Token),
Token ID828
Feature activation-4.32e-01

Pos logit contributions
grain+1.151
urdue+1.098
ellar+1.085
 Windsor+1.073
font+1.058
Neg logit contributions
 Debor-1.432
-1.271
-1.206
 MSM-1.187
 unsus-1.170
Token located
Token ID5140
Feature activation-2.30e+00

Pos logit contributions
grain+0.438
urdue+0.420
ellar+0.417
 Windsor+0.411
font+0.405
Neg logit contributions
 Debor-0.484
-0.425
-0.400
 MSM-0.399
 unsus-0.389
Token the
Token ID262
Feature activation+3.04e-01

Pos logit contributions
grain+1.602
urdue+1.528
ellar+1.527
 Windsor+1.518
font+1.483
Neg logit contributions
 Debor-1.829
-1.619
-1.523
 MSM-1.510
-1.480
Token legendary
Token ID13273
Feature activation+1.98e-01

Pos logit contributions
 Debor+0.247
+0.219
+0.207
 MSM+0.207
 unsus+0.203
Neg logit contributions
grain-0.210
urdue-0.201
ellar-0.200
 Windsor-0.195
font-0.192
Token war
Token ID1175
Feature activation-1.26e+00

Pos logit contributions
 Debor+0.158
+0.140
+0.132
 MSM+0.131
 unsus+0.128
Neg logit contributions
grain-0.139
urdue-0.133
ellar-0.133
 Windsor-0.130
font-0.128
Token for
Token ID329
Feature activation-2.47e+00

Pos logit contributions
grain+0.900
urdue+0.859
ellar+0.853
 Windsor+0.840
font+0.831
Neg logit contributions
 Debor-1.000
-0.880
-0.830
 MSM-0.823
 unsus-0.805
Token Helen
Token ID22695
Feature activation-3.37e+00

Pos logit contributions
grain+1.753
urdue+1.663
ellar+1.656
 Windsor+1.645
font+1.616
Neg logit contributions
 Debor-1.947
-1.727
-1.608
 MSM-1.606
-1.575
Token that
Token ID326
Feature activation-5.96e-01

Pos logit contributions
grain+2.389
urdue+2.242
ellar+2.233
 Windsor+2.224
font+2.216
Neg logit contributions
 Debor-2.674
-2.340
 MSM-2.227
-2.200
 unsus-2.166
Token would
Token ID561
Feature activation-1.44e+00

Pos logit contributions
grain+0.408
urdue+0.390
ellar+0.387
 Windsor+0.383
font+0.375
Neg logit contributions
 Debor-0.485
-0.431
-0.407
 MSM-0.404
 unsus-0.395
Token become
Token ID1716
Feature activation+5.15e-01

Pos logit contributions
grain+0.931
urdue+0.887
ellar+0.885
 Windsor+0.867
font+0.852
Neg logit contributions
 Debor-1.238
-1.105
-1.047
 MSM-1.040
 unsus-1.019
Token parad
Token ID11497
Feature activation-1.30e-01

Pos logit contributions
 Debor+0.423
+0.376
+0.355
 MSM+0.353
 unsus+0.346
Neg logit contributions
grain-0.351
urdue-0.335
ellar-0.334
 Windsor-0.326
font-0.322
Tokenigmatic
Token ID38860
Feature activation-8.82e-01

Pos logit contributions
grain+0.069
urdue+0.065
ellar+0.065
 Windsor+0.063
font+0.062
Neg logit contributions
 Debor-0.125
-0.113
-0.108
 MSM-0.107
 unsus-0.105
Token The
Token ID383
Feature activation+7.54e-01

Pos logit contributions
 Debor+0.676
+0.593
+0.559
 MSM+0.559
 unsus+0.538
Neg logit contributions
grain-0.627
urdue-0.600
ellar-0.599
 Windsor-0.580
font-0.576
Token bulldo
Token ID44767
Feature activation+1.86e-01

Pos logit contributions
 Debor+0.551
+0.480
 MSM+0.451
+0.449
 unsus+0.438
Neg logit contributions
grain-0.584
urdue-0.561
ellar-0.560
 Windsor-0.546
font-0.542
Tokenzers
Token ID47031
Feature activation+3.40e-01

Pos logit contributions
 Debor+0.125
+0.108
+0.100
 MSM+0.100
 unsus+0.097
Neg logit contributions
grain-0.155
urdue-0.149
ellar-0.149
 Windsor-0.147
font-0.145
Token that
Token ID326
Feature activation-1.13e+00

Pos logit contributions
 Debor+0.272
+0.240
+0.227
 MSM+0.225
 unsus+0.221
Neg logit contributions
grain-0.239
urdue-0.229
ellar-0.228
 Windsor-0.224
font-0.220
Token are
Token ID389
Feature activation+3.86e-01

Pos logit contributions
grain+0.784
urdue+0.749
ellar+0.746
 Windsor+0.736
font+0.721
Neg logit contributions
 Debor-0.908
-0.806
-0.761
 MSM-0.754
-0.740
Token responsible
Token ID4497
Feature activation-1.75e+00

Pos logit contributions
 Debor+0.305
+0.269
+0.253
 MSM+0.252
 unsus+0.247
Neg logit contributions
grain-0.275
urdue-0.263
ellar-0.263
 Windsor-0.257
font-0.253
Token for
Token ID329
Feature activation-2.99e+00

Pos logit contributions
grain+1.121
urdue+1.072
ellar+1.069
 Windsor+1.044
font+1.031
Neg logit contributions
 Debor-1.494
-1.332
-1.270
 MSM-1.258
 unsus-1.238
Token destroying
Token ID13897
Feature activation-2.46e+00

Pos logit contributions
grain+1.998
ellar+1.907
urdue+1.900
 Windsor+1.899
font+1.842
Neg logit contributions
 Debor-2.446
-2.182
-2.073
 MSM-2.029
-2.021
Token land
Token ID1956
Feature activation+9.42e-01

Pos logit contributions
grain+1.737
 Windsor+1.649
ellar+1.646
urdue+1.645
font+1.601
Neg logit contributions
 Debor-1.927
-1.724
-1.621
 MSM-1.593
-1.583
Token and
Token ID290
Feature activation-7.10e-01

Pos logit contributions
 Debor+0.706
+0.618
+0.581
 MSM+0.576
 unsus+0.567
Neg logit contributions
grain-0.706
urdue-0.682
ellar-0.682
 Windsor-0.666
font-0.655
Token buildings
Token ID6832
Feature activation-2.64e+00

Pos logit contributions
grain+0.485
urdue+0.463
ellar+0.462
 Windsor+0.453
font+0.446
Neg logit contributions
 Debor-0.581
-0.516
-0.487
 MSM-0.484
 unsus-0.474
Token their
Token ID511
Feature activation-5.42e-01

Pos logit contributions
 Debor+1.584
+1.377
+1.294
 MSM+1.290
 unsus+1.260
Neg logit contributions
grain-1.668
urdue-1.605
ellar-1.601
 Windsor-1.558
font-1.546
Token territory
Token ID7674
Feature activation-9.16e-01

Pos logit contributions
grain+0.403
urdue+0.385
ellar+0.385
 Windsor+0.381
font+0.374
Neg logit contributions
 Debor-0.407
-0.360
-0.338
 MSM-0.334
-0.327
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
grain+0.647
urdue+0.620
ellar+0.616
 Windsor+0.610
font+0.600
Neg logit contributions
 Debor-0.722
-0.640
-0.605
 MSM-0.602
 unsus-0.587
Token But
Token ID887
Feature activation+4.46e-01

Pos logit contributions
 Debor+0.900
+0.792
+0.747
 MSM+0.745
 unsus+0.721
Neg logit contributions
grain-0.809
urdue-0.773
ellar-0.772
 Windsor-0.750
font-0.742
Token we
Token ID356
Feature activation-1.37e+00

Pos logit contributions
 Debor+0.348
+0.308
+0.290
 MSM+0.287
 unsus+0.281
Neg logit contributions
grain-0.322
urdue-0.309
ellar-0.308
 Windsor-0.303
font-0.298
Token should
Token ID815
Feature activation-1.10e+00

Pos logit contributions
grain+0.904
ellar+0.862
urdue+0.861
 Windsor+0.850
font+0.832
Neg logit contributions
 Debor-1.139
-1.021
-0.969
 MSM-0.952
-0.946
Token applaud
Token ID22517
Feature activation-3.49e+00

Pos logit contributions
grain+0.727
urdue+0.696
ellar+0.691
 Windsor+0.679
font+0.670
Neg logit contributions
 Debor-0.925
-0.823
-0.780
 MSM-0.773
-0.757
Token them
Token ID606
Feature activation-3.18e+00

Pos logit contributions
grain+2.336
 Windsor+2.269
urdue+2.261
ellar+2.229
font+2.190
Neg logit contributions
 Debor-2.800
-2.529
-2.398
-2.341
-2.336
Token for
Token ID329
Feature activation-1.43e+00

Pos logit contributions
grain+2.037
urdue+1.977
ellar+1.954
 Windsor+1.939
font+1.911
Neg logit contributions
 Debor-2.652
-2.367
-2.263
 MSM-2.243
-2.205
Token their
Token ID511
Feature activation-2.16e+00

Pos logit contributions
grain+0.966
urdue+0.930
ellar+0.925
 Windsor+0.913
font+0.893
Neg logit contributions
 Debor-1.169
-1.040
-0.984
 MSM-0.973
-0.953
Token realism
Token ID30787
Feature activation+8.98e-01

Pos logit contributions
grain+1.492
urdue+1.433
ellar+1.428
 Windsor+1.411
font+1.377
Neg logit contributions
 Debor-1.741
-1.543
-1.458
 MSM-1.438
-1.415
Token-
Token ID12
Feature activation+9.30e-01

Pos logit contributions
grain+1.249
urdue+1.169
ellar+1.168
 Windsor+1.153
font+1.151
Neg logit contributions
 Debor-1.808
-1.613
 MSM-1.532
-1.529
 unsus-1.508
Tokencl
Token ID565
Feature activation-2.63e-01

Pos logit contributions
 Debor+0.706
+0.623
+0.585
 MSM+0.579
 unsus+0.567
Neg logit contributions
grain-0.688
urdue-0.664
ellar-0.661
 Windsor-0.648
font-0.634
Tokenoak
Token ID15877
Feature activation+5.27e-01

Pos logit contributions
grain+0.161
ellar+0.153
urdue+0.153
 Windsor+0.149
font+0.145
Neg logit contributions
 Debor-0.233
-0.209
-0.199
 MSM-0.197
 unsus-0.194
Token to
Token ID284
Feature activation+1.67e+00

Pos logit contributions
 Debor+0.414
+0.367
+0.345
 MSM+0.343
 unsus+0.336
Neg logit contributions
grain-0.377
urdue-0.362
ellar-0.361
 Windsor-0.353
font-0.347
Token this
Token ID428
Feature activation+1.52e+00

Pos logit contributions
 Debor+1.340
+1.193
 MSM+1.127
+1.125
 unsus+1.107
Neg logit contributions
grain-1.162
urdue-1.126
ellar-1.117
 Windsor-1.084
afety-1.073
Token end
Token ID886
Feature activation-5.63e+00

Pos logit contributions
 Debor+1.158
+1.020
 MSM+0.956
+0.955
 unsus+0.937
Neg logit contributions
grain-1.115
urdue-1.076
ellar-1.073
 Windsor-1.045
font-1.031
Token.
Token ID13
Feature activation+7.35e-02

Pos logit contributions
grain+3.882
urdue+3.628
ellar+3.604
font+3.575
 Windsor+3.518
Neg logit contributions
 Debor-4.579
-4.027
-3.857
 MSM-3.799
-3.778
Token It
Token ID632
Feature activation+4.53e-01

Pos logit contributions
 Debor+0.059
+0.052
+0.049
 MSM+0.049
 unsus+0.048
Neg logit contributions
grain-0.051
urdue-0.049
ellar-0.049
 Windsor-0.048
font-0.047
Token works
Token ID2499
Feature activation+4.02e+00

Pos logit contributions
 Debor+0.377
+0.336
+0.317
 MSM+0.316
 unsus+0.310
Neg logit contributions
grain-0.303
urdue-0.289
ellar-0.289
 Windsor-0.282
font-0.277
Token by
Token ID416
Feature activation+1.52e+00

Pos logit contributions
 Debor+3.081
+2.709
 MSM+2.558
 unsus+2.528
+2.527
Neg logit contributions
grain-2.916
urdue-2.820
ellar-2.795
 Windsor-2.696
afety-2.674
Token injecting
Token ID41750
Feature activation+1.24e+00

Pos logit contributions
 Debor+1.275
+1.134
 MSM+1.070
+1.069
 unsus+1.053
Neg logit contributions
grain-1.009
urdue-0.964
ellar-0.960
 Windsor-0.933
font-0.919
Token Mag
Token ID2944
Feature activation+1.04e+00

Pos logit contributions
 Debor+0.918
+0.808
+0.760
 MSM+0.759
 unsus+0.738
Neg logit contributions
grain-0.852
urdue-0.819
ellar-0.818
 Windsor-0.795
font-0.786
Tokenico
Token ID3713
Feature activation-1.76e+00

Pos logit contributions
 Debor+0.842
+0.746
+0.707
 MSM+0.701
 unsus+0.685
Neg logit contributions
grain-0.719
urdue-0.693
ellar-0.688
 Windsor-0.676
font-0.661
Token and
Token ID290
Feature activation-4.25e-01

Pos logit contributions
grain+1.231
urdue+1.171
ellar+1.166
 Windsor+1.151
font+1.136
Neg logit contributions
 Debor-1.412
-1.241
-1.179
 MSM-1.167
 unsus-1.151
Token V
Token ID569
Feature activation+1.52e-01

Pos logit contributions
grain+0.305
urdue+0.292
ellar+0.291
 Windsor+0.287
font+0.282
Neg logit contributions
 Debor-0.332
-0.294
-0.277
 MSM-0.274
 unsus-0.269
Tokenivid
Token ID1699
Feature activation+8.48e-01

Pos logit contributions
 Debor+0.119
+0.105
+0.098
 MSM+0.098
 unsus+0.096
Neg logit contributions
grain-0.110
urdue-0.106
ellar-0.106
 Windsor-0.103
font-0.102
Token Audio
Token ID13491
Feature activation-5.46e+00

Pos logit contributions
 Debor+0.691
+0.615
+0.580
 MSM+0.577
 unsus+0.564
Neg logit contributions
grain-0.580
urdue-0.556
ellar-0.554
 Windsor-0.542
font-0.533
Token --
Token ID1377
Feature activation-1.63e+00

Pos logit contributions
grain+3.666
urdue+3.476
 Windsor+3.440
font+3.409
ellar+3.397
Neg logit contributions
 Debor-4.439
-3.834
-3.703
 unsus-3.655
 MSM-3.631
Token and
Token ID290
Feature activation+7.57e-01

Pos logit contributions
grain+1.135
urdue+1.081
ellar+1.077
 Windsor+1.060
font+1.048
Neg logit contributions
 Debor-1.309
-1.157
-1.095
 MSM-1.081
-1.070
Token their
Token ID511
Feature activation+6.12e-02

Pos logit contributions
 Debor+0.601
+0.531
+0.501
 MSM+0.499
 unsus+0.488
Neg logit contributions
grain-0.536
urdue-0.514
ellar-0.513
 Windsor-0.502
font-0.494
Token lowest
Token ID9016
Feature activation-1.23e+00

Pos logit contributions
 Debor+0.048
+0.042
+0.040
 MSM+0.039
 unsus+0.038
Neg logit contributions
grain-0.044
urdue-0.042
ellar-0.042
 Windsor-0.042
font-0.041
Token-
Token ID12
Feature activation-1.28e+00

Pos logit contributions
grain+0.818
ellar+0.781
urdue+0.778
 Windsor+0.762
font+0.752
Neg logit contributions
 Debor-1.021
-0.905
-0.860
 MSM-0.852
 unsus-0.837
Token capacity
Token ID5339
Feature activation-3.57e+00

Pos logit contributions
grain+1.591
urdue+1.517
ellar+1.515
 Windsor+1.496
font+1.464
Neg logit contributions
 Debor-1.739
-1.540
-1.452
 MSM-1.438
 unsus-1.406
Token to
Token ID284
Feature activation-2.02e+00

Pos logit contributions
grain+2.466
urdue+2.349
 Windsor+2.331
ellar+2.316
font+2.267
Neg logit contributions
 Debor-2.830
-2.530
-2.412
 MSM-2.385
-2.329
Token 300
Token ID5867
Feature activation-1.39e+00

Pos logit contributions
grain+1.430
urdue+1.368
ellar+1.366
 Windsor+1.347
font+1.317
Neg logit contributions
 Debor-1.598
-1.417
-1.337
 MSM-1.321
 unsus-1.295
Token,
Token ID11
Feature activation-2.14e+00

Pos logit contributions
grain+1.025
urdue+0.979
ellar+0.977
 Windsor+0.964
font+0.947
Neg logit contributions
 Debor-1.071
-0.942
-0.888
 MSM-0.880
 unsus-0.863
Token000
Token ID830
Feature activation-1.12e+00

Pos logit contributions
grain+1.657
urdue+1.595
ellar+1.587
 Windsor+1.572
font+1.541
Neg logit contributions
 Debor-1.549
-1.353
-1.264
 MSM-1.258
 unsus-1.227
Token barrels
Token ID17907
Feature activation-6.75e+00

Pos logit contributions
grain+0.651
urdue+0.615
ellar+0.614
 Windsor+0.601
font+0.588
Neg logit contributions
 Debor-1.037
-0.933
-0.889
 MSM-0.884
 unsus-0.869
Token a
Token ID257
Feature activation+3.26e+00

Pos logit contributions
grain+3.860
 Windsor+3.639
urdue+3.582
font+3.537
afety+3.535
Neg logit contributions
 Debor-6.096
-5.416
-5.277
-5.177
 MSM-5.142
Token day
Token ID1110
Feature activation+4.31e-02

Pos logit contributions
 Debor+2.323
+2.058
+1.909
 MSM+1.889
 unsus+1.847
Neg logit contributions
grain-2.530
urdue-2.457
ellar-2.451
font-2.363
afety-2.353
Token.
Token ID13
Feature activation-6.26e-01

Pos logit contributions
 Debor+0.034
+0.030
+0.028
 MSM+0.028
 unsus+0.027
Neg logit contributions
grain-0.031
urdue-0.030
ellar-0.029
 Windsor-0.029
font-0.029
Token Virt
Token ID11285
Feature activation-4.25e-01

Pos logit contributions
grain+0.451
urdue+0.432
ellar+0.431
 Windsor+0.425
font+0.417
Neg logit contributions
 Debor-0.487
-0.430
-0.406
 MSM-0.402
 unsus-0.397
Tokenually
Token ID935
Feature activation-1.68e+00

Pos logit contributions
grain+0.276
urdue+0.262
ellar+0.262
 Windsor+0.257
font+0.252
Neg logit contributions
 Debor-0.364
-0.324
-0.307
 MSM-0.305
 unsus-0.299
Token her
Token ID607
Feature activation-1.68e+00

Pos logit contributions
grain+0.783
urdue+0.751
ellar+0.750
 Windsor+0.740
font+0.726
Neg logit contributions
 Debor-0.819
-0.724
-0.683
 MSM-0.675
 unsus-0.661
Token and
Token ID290
Feature activation-2.51e+00

Pos logit contributions
grain+1.184
urdue+1.137
ellar+1.135
 Windsor+1.123
font+1.097
Neg logit contributions
 Debor-1.322
-1.169
-1.112
 MSM-1.096
 unsus-1.074
Token another
Token ID1194
Feature activation-1.43e+00

Pos logit contributions
grain+1.834
urdue+1.759
ellar+1.756
 Windsor+1.749
font+1.700
Neg logit contributions
 Debor-1.901
-1.687
-1.594
 MSM-1.571
-1.543
Token employee
Token ID6538
Feature activation-1.43e+00

Pos logit contributions
grain+1.002
urdue+0.959
ellar+0.956
 Windsor+0.938
font+0.922
Neg logit contributions
 Debor-1.152
-1.021
-0.964
 MSM-0.957
 unsus-0.937
Token,
Token ID11
Feature activation+8.85e-02

Pos logit contributions
grain+1.031
urdue+0.991
ellar+0.986
 Windsor+0.972
font+0.955
Neg logit contributions
 Debor-1.113
-0.983
-0.929
 MSM-0.922
 unsus-0.900
Token Desire
Token ID41042
Feature activation-5.76e+00

Pos logit contributions
 Debor+0.071
+0.063
+0.059
 MSM+0.059
 unsus+0.057
Neg logit contributions
grain-0.062
urdue-0.060
ellar-0.059
 Windsor-0.058
font-0.057
Tokene
Token ID68
Feature activation-2.37e+00

Pos logit contributions
grain+3.116
 Windsor+3.024
ellar+2.988
urdue+2.946
font+2.869
Neg logit contributions
 Debor-5.269
-4.896
-4.644
 MSM-4.622
-4.581
Token La
Token ID4689
Feature activation+3.32e-02

Pos logit contributions
grain+1.699
ellar+1.623
urdue+1.622
 Windsor+1.619
font+1.578
Neg logit contributions
 Debor-1.829
-1.633
-1.537
 MSM-1.521
 unsus-1.503
TokenFeb
Token ID15146
Feature activation+1.70e+00

Pos logit contributions
 Debor+0.026
+0.023
+0.021
 MSM+0.021
 unsus+0.021
Neg logit contributions
grain-0.024
urdue-0.023
ellar-0.023
 Windsor-0.023
font-0.022
Tokenre
Token ID260
Feature activation+1.12e+00

Pos logit contributions
 Debor+1.451
+1.290
+1.226
 MSM+1.213
 unsus+1.192
Neg logit contributions
grain-1.096
urdue-1.044
ellar-1.029
 Windsor-1.014
font-0.996
Token.
Token ID13
Feature activation-1.12e+00

Pos logit contributions
 Debor+0.870
+0.768
+0.723
 MSM+0.718
 unsus+0.703
Neg logit contributions
grain-0.806
urdue-0.771
ellar-0.769
 Windsor-0.755
font-0.744
Token rebutt
Token ID46472
Feature activation+9.59e-01

Pos logit contributions
 Debor+0.965
+0.838
+0.785
 MSM+0.781
 unsus+0.763
Neg logit contributions
grain-1.093
urdue-1.051
ellar-1.049
 Windsor-1.027
font-1.016
Tokenals
Token ID874
Feature activation+1.90e+00

Pos logit contributions
 Debor+0.707
+0.619
+0.581
 MSM+0.577
 unsus+0.563
Neg logit contributions
grain-0.732
urdue-0.704
ellar-0.701
 Windsor-0.689
font-0.679
Token toward
Token ID3812
Feature activation-6.57e-01

Pos logit contributions
 Debor+1.448
+1.275
+1.200
 MSM+1.191
 unsus+1.171
Neg logit contributions
grain-1.405
ellar-1.343
urdue-1.343
 Windsor-1.311
font-1.288
Token cliché
Token ID43973
Feature activation+7.26e-01

Pos logit contributions
grain+0.473
urdue+0.452
ellar+0.451
 Windsor+0.446
font+0.436
Neg logit contributions
 Debor-0.511
-0.455
-0.427
 MSM-0.421
-0.416
Token bo
Token ID1489
Feature activation-2.03e-01

Pos logit contributions
 Debor+0.589
+0.522
+0.493
 MSM+0.490
 unsus+0.480
Neg logit contributions
grain-0.501
urdue-0.479
ellar-0.477
 Windsor-0.467
font-0.460
Tokenhem
Token ID4411
Feature activation-6.51e+00

Pos logit contributions
grain+0.134
urdue+0.128
ellar+0.128
 Windsor+0.125
font+0.123
Neg logit contributions
 Debor-0.170
-0.151
-0.143
 MSM-0.142
 unsus-0.140
Tokenian
Token ID666
Feature activation+1.92e+00

Pos logit contributions
grain+3.382
ellar+3.097
urdue+3.030
font+3.002
 Windsor+2.970
Neg logit contributions
 Debor-6.381
-5.709
-5.490
-5.457
-5.427
Token ideals
Token ID22247
Feature activation+1.44e+00

Pos logit contributions
 Debor+1.437
+1.257
+1.183
 MSM+1.180
 unsus+1.151
Neg logit contributions
grain-1.448
urdue-1.393
ellar-1.385
 Windsor-1.357
font-1.341
Token that
Token ID326
Feature activation+7.75e-01

Pos logit contributions
 Debor+1.116
+0.984
+0.925
 MSM+0.921
 unsus+0.905
Neg logit contributions
grain-1.037
urdue-0.993
ellar-0.991
 Windsor-0.969
font-0.954
Token have
Token ID423
Feature activation+1.49e+00

Pos logit contributions
 Debor+0.587
+0.516
+0.485
 MSM+0.482
 unsus+0.471
Neg logit contributions
grain-0.577
urdue-0.554
ellar-0.552
 Windsor-0.542
font-0.534
Token been
Token ID587
Feature activation-1.82e+00

Pos logit contributions
 Debor+1.295
+1.153
+1.095
 MSM+1.092
 unsus+1.074
Neg logit contributions
grain-0.948
urdue-0.903
ellar-0.902
 Windsor-0.879
font-0.866