TOP ACTIVATIONS
MAX = 14.528

Manchester United [ 95 ][ 96 ] International
6 { ( 6 s )} 26 . Rd 2 {
happened to represent Patrick O ' Brian . He borrowed a
open new store at Five Corn ers in Bur ien
- wall aby ( Pet rog ale wil kins i ),
7 { ( 17 s )} 27 . R xd 8
Reviewer : Mike M anners - favorite favorite favorite
kind el . V ad im And rey uk
youtube . com / channel / UC _ K k BY
( 55 s )} Ra 8 { ( 113 s )}
networking website . V ital y Nem ov ,
part . A hot - button topic in the
] CBS Sports . com ,[ 96 ] NBC Sports .
- wall aby ( Pet rog ale br achy ot is
. Save ($ Out File , [ system . draw ing
at least 100 , 000 light - years across . We
. Count ; $ i ++) { if ($ i -
from another area of the body ,' says a source .
path )" break } } else { $ SR = [
San Francisco Board of Super visors San

MIN ACTIVATIONS
MIN = -17.161

Committee and the Commerce , Justice , Science and Related Ag
to create our own best selling Kindle book . We
to promote the accuracy , fairness , and privacy of consumer
Wall Street will continue to wre ak havoc on our economy
after dozens of people began sleeping outside the premises each week
night , but we all slept well after a long day
thy hands , thou shalt sm ite every male therein with
alert . He doesn 't sleep . He doesn 't need
written by the Icelandic writer S j ón .
icus brief calling for the Court to take the case .)
All advanced metrics courtesy of Pro Football Focus unless otherwise indicated
presided over a soft - dr ink bott ling company that
http :// www . ed wards . af . mil /
by the Icelandic writer S j ón . H
_ state : Arc :: clone ( self . prev _
did receive a last name Sur ley , a date of
ingestion ". ' Sm alls things you can do
, check : self . check , prev _ state :
government and its leader becomes Prime Minister . In cases where
We 're hoping that he sur rend ers ," the police

INTERVAL 6.605 - 14.528
CONTAINS 0.819%

through the use of the UL MB stro bed back light
player in MLS . He came out of retirement
Roll s - Roy ce says it has completed a thorough
full lineup of games that will be played at the January
for the Ring bet rays Fro do by leading him

INTERVAL -1.317 - 6.605
CONTAINS 69.729%

Chrom ecast or Fire St ick . Check out
banks and " invest ors ," all backed by Federal guarantees
LG D people , including LG D s manager
another trust , called the Mor neau McCain Family Trust .
There are two ways to approach Lac an

INTERVAL -9.239 - -1.317
CONTAINS 29.349%

, why are we doing other things - the pre -
Psychology Quarterly , 23 , 26 - 42 .
р о с ь о�
references on card n ° 1 and more details on card
're living in a global economy , and important as Europe

INTERVAL -17.161 - -9.239
CONTAINS 0.103%

E ia n ō na e , ma ke
WE ARE WITH YOU . GOD BL ESS ! Donald
? Jay C z ark owski : I would
а м н и к
Henry Pyr g os has recovered from injury .
Token
Token ID198
Feature activation+9.01e-01

Pos logit contributions
idav+0.458
zeb+0.434
ween+0.434
wave+0.428
abase+0.409
Neg logit contributions
enthal-0.578
esan-0.510
aeda-0.485
iners-0.479
ocument-0.474
TokenManchester
Token ID40744
Feature activation+1.31e+00

Pos logit contributions
enthal+0.689
esan+0.599
aeda+0.558
iners+0.556
ROR+0.544
Neg logit contributions
idav-0.705
ween-0.660
zeb-0.658
wave-0.645
abase-0.632
Token United
Token ID1578
Feature activation-1.96e-01

Pos logit contributions
enthal+1.161
esan+1.032
aeda+0.964
iners+0.961
ROR+0.941
Neg logit contributions
idav-0.871
zeb-0.803
ween-0.795
wave-0.787
abase-0.759
Token[
Token ID58
Feature activation+4.32e+00

Pos logit contributions
idav+0.139
zeb+0.130
ween+0.130
wave+0.128
abase+0.124
Neg logit contributions
enthal-0.164
esan-0.144
aeda-0.136
iners-0.135
ocument-0.133
Token95
Token ID3865
Feature activation-3.30e-02

Pos logit contributions
enthal+3.395
esan+3.047
aeda+2.865
iners+2.801
ROR+2.798
Neg logit contributions
idav-3.146
ween-2.936
zeb-2.891
wave-2.823
abase-2.797
Token][
Token ID7131
Feature activation+1.45e+01

Pos logit contributions
idav+0.019
ween+0.017
zeb+0.017
wave+0.017
abase+0.016
Neg logit contributions
enthal-0.032
esan-0.029
aeda-0.027
iners-0.027
ocument-0.027
Token96
Token ID4846
Feature activation-2.33e-01

Pos logit contributions
enthal+7.574
esan+6.452
bos+6.216
aeda+6.138
ROR+5.925
Neg logit contributions
idav-12.822
 Faul-11.579
ween-11.501
zeb-11.493
wave-11.270
Token]
Token ID60
Feature activation+3.22e-01

Pos logit contributions
idav+0.133
ween+0.123
zeb+0.123
wave+0.120
abase+0.116
Neg logit contributions
enthal-0.226
esan-0.203
aeda-0.193
iners-0.192
ocument-0.189
Token
Token ID198
Feature activation-1.56e+00

Pos logit contributions
enthal+0.264
esan+0.231
aeda+0.217
iners+0.216
ocument+0.211
Neg logit contributions
idav-0.234
ween-0.219
zeb-0.219
wave-0.215
abase-0.208
Token
Token ID198
Feature activation+1.24e-01

Pos logit contributions
idav+1.022
zeb+0.977
ween+0.976
wave+0.966
 Faul+0.915
Neg logit contributions
enthal-1.361
esan-1.203
aeda-1.153
iners-1.133
ocument-1.126
TokenInternational
Token ID24274
Feature activation+1.29e+00

Pos logit contributions
enthal+0.100
esan+0.088
aeda+0.082
iners+0.082
ROR+0.081
Neg logit contributions
idav-0.092
zeb-0.085
ween-0.085
wave-0.083
abase-0.082
Token6
Token ID21
Feature activation+1.14e+01

Pos logit contributions
enthal+0.308
esan+0.270
aeda+0.255
iners+0.254
ocument+0.248
Neg logit contributions
idav-0.270
ween-0.255
zeb-0.251
wave-0.248
abase-0.241
Token {
Token ID1391
Feature activation+5.63e-01

Pos logit contributions
enthal+5.270
esan+4.225
iners+3.715
aeda+3.531
ROR+3.373
Neg logit contributions
idav-11.808
ween-10.879
zeb-10.747
 Faul-10.520
wave-10.518
Token(
Token ID7
Feature activation-2.43e+00

Pos logit contributions
enthal+0.559
esan+0.502
aeda+0.479
iners+0.476
ocument+0.469
Neg logit contributions
idav-0.309
ween-0.285
zeb-0.284
wave-0.278
abase-0.267
Token 6
Token ID718
Feature activation+1.63e-01

Pos logit contributions
idav+1.716
zeb+1.612
ween+1.611
wave+1.587
abase+1.533
Neg logit contributions
enthal-2.020
esan-1.777
aeda-1.671
iners-1.660
ocument-1.630
Tokens
Token ID82
Feature activation+5.18e-01

Pos logit contributions
enthal+0.136
esan+0.120
aeda+0.113
iners+0.112
ocument+0.110
Neg logit contributions
idav-0.115
ween-0.108
zeb-0.108
wave-0.106
abase-0.103
Token)}
Token ID38165
Feature activation+1.39e+01

Pos logit contributions
enthal+0.355
esan+0.303
aeda+0.282
iners+0.279
ocument+0.273
Neg logit contributions
idav-0.443
ween-0.421
zeb-0.421
wave-0.415
abase-0.404
Token 26
Token ID2608
Feature activation+2.67e+00

Pos logit contributions
enthal+6.775
esan+5.049
iners+4.821
aeda+4.745
ROR+4.367
Neg logit contributions
idav-13.596
ween-12.438
zeb-12.191
wave-12.163
pell-11.668
Token.
Token ID13
Feature activation+3.08e+00

Pos logit contributions
enthal+2.296
esan+2.026
aeda+1.899
iners+1.895
ocument+1.849
Neg logit contributions
idav-1.843
ween-1.701
zeb-1.684
wave-1.651
abase-1.630
Token Rd
Token ID20769
Feature activation-1.91e+00

Pos logit contributions
enthal+2.524
esan+2.218
aeda+2.100
iners+2.070
ROR+2.022
Neg logit contributions
idav-2.238
ween-2.078
zeb-2.049
wave-2.016
abase-1.952
Token2
Token ID17
Feature activation+7.15e+00

Pos logit contributions
idav+1.107
zeb+1.028
ween+1.025
wave+1.005
abase+0.964
Neg logit contributions
enthal-1.828
esan-1.639
aeda-1.560
iners-1.547
ocument-1.528
Token {
Token ID1391
Feature activation-2.12e-01

Pos logit contributions
enthal+3.716
esan+3.057
iners+2.796
aeda+2.728
ROR+2.600
Neg logit contributions
idav-7.139
ween-6.736
zeb-6.561
wave-6.489
 Faul-6.382
Token happened
Token ID3022
Feature activation+5.44e-01

Pos logit contributions
idav+1.806
ween+1.705
zeb+1.703
wave+1.682
 Faul+1.631
Neg logit contributions
enthal-2.205
esan-1.938
aeda-1.840
iners-1.819
ocument-1.802
Token to
Token ID284
Feature activation-1.58e+00

Pos logit contributions
enthal+0.452
esan+0.397
aeda+0.374
iners+0.371
ocument+0.363
Neg logit contributions
idav-0.387
zeb-0.364
ween-0.362
wave-0.355
abase-0.346
Token represent
Token ID2380
Feature activation+1.23e+00

Pos logit contributions
idav+1.176
ween+1.108
zeb+1.107
wave+1.089
abase+1.058
Neg logit contributions
enthal-1.260
esan-1.100
aeda-1.036
iners-1.025
ocument-1.007
Token Patrick
Token ID9925
Feature activation-2.49e+00

Pos logit contributions
enthal+1.063
esan+0.939
aeda+0.889
iners+0.887
ROR+0.865
Neg logit contributions
idav-0.839
zeb-0.780
ween-0.777
wave-0.757
abase-0.743
Token O
Token ID440
Feature activation+7.35e-01

Pos logit contributions
idav+1.531
ween+1.430
zeb+1.424
wave+1.395
 Faul+1.346
Neg logit contributions
enthal-2.304
esan-2.051
aeda-1.952
iners-1.934
ocument-1.907
Token'
Token ID6
Feature activation+1.33e+01

Pos logit contributions
enthal+0.551
esan+0.477
aeda+0.447
iners+0.443
ocument+0.438
Neg logit contributions
idav-0.579
zeb-0.550
ween-0.550
wave-0.542
abase-0.525
TokenBrian
Token ID24761
Feature activation-9.11e-01

Pos logit contributions
enthal+6.341
esan+5.258
ROR+4.649
iners+4.553
aeda+4.484
Neg logit contributions
idav-12.978
zeb-12.056
ween-11.768
abase-11.731
wave-11.685
Token.
Token ID13
Feature activation+5.19e-01

Pos logit contributions
idav+0.629
zeb+0.587
ween+0.586
wave+0.576
abase+0.559
Neg logit contributions
enthal-0.781
esan-0.687
aeda-0.648
iners-0.642
ocument-0.633
Token He
Token ID679
Feature activation+6.02e-02

Pos logit contributions
enthal+0.436
esan+0.384
aeda+0.361
iners+0.360
ocument+0.354
Neg logit contributions
idav-0.365
zeb-0.342
ween-0.342
wave-0.334
abase-0.328
Token borrowed
Token ID22546
Feature activation-1.08e+00

Pos logit contributions
enthal+0.049
esan+0.043
aeda+0.040
iners+0.040
ocument+0.039
Neg logit contributions
idav-0.044
ween-0.041
zeb-0.041
wave-0.040
abase-0.039
Token a
Token ID257
Feature activation+6.42e-02

Pos logit contributions
idav+0.758
ween+0.712
zeb+0.711
wave+0.700
 Faul+0.676
Neg logit contributions
enthal-0.905
esan-0.796
aeda-0.751
iners-0.743
ocument-0.731
Token open
Token ID1280
Feature activation+4.52e-01

Pos logit contributions
enthal+2.440
esan+2.185
iners+2.075
aeda+2.032
ocument+2.024
Neg logit contributions
idav-1.801
zeb-1.693
ween-1.684
wave-1.613
abase-1.593
Token new
Token ID649
Feature activation-9.57e-02

Pos logit contributions
enthal+0.371
esan+0.325
aeda+0.308
iners+0.306
ocument+0.299
Neg logit contributions
idav-0.328
zeb-0.307
ween-0.307
wave-0.300
abase-0.291
Token store
Token ID3650
Feature activation-3.64e+00

Pos logit contributions
idav+0.065
zeb+0.060
ween+0.060
wave+0.058
abase+0.057
Neg logit contributions
enthal-0.084
esan-0.074
aeda-0.070
iners-0.070
ocument-0.068
Token at
Token ID379
Feature activation-6.85e-01

Pos logit contributions
idav+2.300
ween+2.156
zeb+2.148
wave+2.105
abase+2.043
Neg logit contributions
enthal-3.297
esan-2.928
aeda-2.785
iners-2.744
ocument-2.716
Token Five
Token ID10579
Feature activation-2.21e+00

Pos logit contributions
idav+0.527
zeb+0.496
ween+0.496
wave+0.488
abase+0.475
Neg logit contributions
enthal-0.531
esan-0.463
aeda-0.434
iners-0.430
ocument-0.422
Token Corn
Token ID11424
Feature activation+1.28e+01

Pos logit contributions
idav+1.317
ween+1.239
zeb+1.231
wave+1.211
 Faul+1.175
Neg logit contributions
enthal-2.063
esan-1.838
aeda-1.762
iners-1.747
ocument-1.738
Tokeners
Token ID364
Feature activation+2.03e+00

Pos logit contributions
enthal+6.351
esan+5.163
iners+4.938
aeda+4.031
estone+4.019
Neg logit contributions
idav-12.686
 Faul-11.840
abase-11.825
ween-11.702
zeb-11.401
Token in
Token ID287
Feature activation-7.33e-01

Pos logit contributions
enthal+1.560
esan+1.344
iners+1.263
aeda+1.261
ocument+1.215
Neg logit contributions
idav-1.567
zeb-1.473
ween-1.462
wave-1.447
abase-1.410
Token Bur
Token ID5481
Feature activation+2.21e+00

Pos logit contributions
idav+0.379
zeb+0.351
ween+0.351
wave+0.342
 Faul+0.329
Neg logit contributions
enthal-0.748
esan-0.675
aeda-0.644
iners-0.640
ocument-0.633
Tokenien
Token ID2013
Feature activation-1.35e+00

Pos logit contributions
enthal+2.030
esan+1.803
aeda+1.706
iners+1.705
ocument+1.668
Neg logit contributions
idav-1.382
zeb-1.274
ween-1.273
wave-1.253
 Faul-1.210
Token
Token ID198
Feature activation+1.99e+00

Pos logit contributions
idav+0.940
ween+0.881
zeb+0.881
wave+0.865
abase+0.838
Neg logit contributions
enthal-1.147
esan-1.010
aeda-0.955
iners-0.946
ocument-0.931
Token-
Token ID12
Feature activation-1.92e+00

Pos logit contributions
enthal+1.005
esan+0.888
aeda+0.834
iners+0.822
ocument+0.812
Neg logit contributions
idav-0.806
ween-0.750
zeb-0.748
wave-0.731
abase-0.714
Tokenwall
Token ID11930
Feature activation+8.50e-01

Pos logit contributions
idav+1.186
ween+1.105
zeb+1.104
wave+1.083
abase+1.043
Neg logit contributions
enthal-1.774
esan-1.581
aeda-1.502
iners-1.491
ocument-1.468
Tokenaby
Token ID3930
Feature activation+8.14e-01

Pos logit contributions
enthal+0.745
esan+0.660
aeda+0.625
iners+0.616
ocument+0.605
Neg logit contributions
idav-0.565
ween-0.529
zeb-0.526
wave-0.518
 Faul-0.504
Token (
Token ID357
Feature activation+1.31e+00

Pos logit contributions
enthal+0.702
esan+0.621
aeda+0.589
iners+0.577
ocument+0.572
Neg logit contributions
idav-0.556
ween-0.521
zeb-0.518
wave-0.507
abase-0.496
TokenPet
Token ID25803
Feature activation-9.64e-01

Pos logit contributions
enthal+1.166
esan+1.030
aeda+0.980
iners+0.969
ROR+0.956
Neg logit contributions
idav-0.851
ween-0.786
zeb-0.784
wave-0.762
abase-0.751
Tokenrog
Token ID3828
Feature activation+1.28e+01

Pos logit contributions
idav+0.924
zeb+0.883
ween+0.883
wave+0.872
 Faul+0.855
Neg logit contributions
enthal-0.564
esan-0.466
aeda-0.426
iners-0.418
ocument-0.406
Tokenale
Token ID1000
Feature activation+8.52e-01

Pos logit contributions
enthal+7.804
esan+7.047
aeda+6.250
iners+5.986
ocument+5.551
Neg logit contributions
idav-10.633
 Faul-10.255
ween-10.040
zeb-9.764
wave-9.733
Token wil
Token ID39716
Feature activation+4.61e+00

Pos logit contributions
enthal+0.739
esan+0.657
aeda+0.624
iners+0.612
ocument+0.607
Neg logit contributions
idav-0.567
zeb-0.528
ween-0.528
wave-0.524
abase-0.505
Tokenkins
Token ID5331
Feature activation+2.40e+00

Pos logit contributions
enthal+3.535
esan+3.075
iners+2.921
aeda+2.865
ocument+2.700
Neg logit contributions
idav-3.504
ween-3.259
zeb-3.237
 Faul-3.223
wave-3.209
Tokeni
Token ID72
Feature activation+3.37e+00

Pos logit contributions
enthal+1.972
esan+1.730
aeda+1.649
iners+1.591
ocument+1.568
Neg logit contributions
idav-1.725
zeb-1.618
ween-1.606
wave-1.591
abase-1.561
Token),
Token ID828
Feature activation+1.13e+00

Pos logit contributions
enthal+2.722
esan+2.389
aeda+2.266
iners+2.187
ocument+2.180
Neg logit contributions
idav-2.443
zeb-2.297
ween-2.275
wave-2.263
abase-2.169
Token7
Token ID22
Feature activation+4.29e+00

Pos logit contributions
idav+2.306
zeb+2.181
ween+2.150
wave+2.114
abase+2.028
Neg logit contributions
enthal-3.496
esan-3.137
aeda-2.973
iners-2.947
ocument-2.930
Token {
Token ID1391
Feature activation+6.96e-02

Pos logit contributions
enthal+2.413
esan+1.996
iners+1.805
aeda+1.766
ROR+1.708
Neg logit contributions
idav-4.219
ween-3.993
zeb-3.956
wave-3.891
abase-3.839
Token(
Token ID7
Feature activation-3.67e+00

Pos logit contributions
enthal+0.070
esan+0.063
aeda+0.060
iners+0.059
ocument+0.059
Neg logit contributions
idav-0.038
ween-0.035
zeb-0.035
wave-0.034
abase-0.033
Token17
Token ID1558
Feature activation+2.75e+00

Pos logit contributions
idav+2.558
zeb+2.403
ween+2.401
wave+2.370
abase+2.282
Neg logit contributions
enthal-3.064
esan-2.704
aeda-2.533
iners-2.522
ocument-2.473
Tokens
Token ID82
Feature activation+1.11e+00

Pos logit contributions
enthal+2.321
esan+2.016
iners+1.923
aeda+1.919
ROR+1.878
Neg logit contributions
idav-1.916
ween-1.778
zeb-1.763
wave-1.745
abase-1.707
Token)}
Token ID38165
Feature activation+1.27e+01

Pos logit contributions
enthal+0.745
esan+0.631
aeda+0.585
iners+0.580
ROR+0.563
Neg logit contributions
idav-0.965
ween-0.915
zeb-0.914
wave-0.900
abase-0.882
Token 27
Token ID2681
Feature activation+1.22e+00

Pos logit contributions
enthal+5.979
iners+4.459
esan+4.423
aeda+3.885
 fork+3.792
Neg logit contributions
idav-12.582
ween-11.961
wave-11.603
zeb-11.503
abase-11.327
Token.
Token ID13
Feature activation+3.90e+00

Pos logit contributions
enthal+1.076
esan+0.952
aeda+0.900
iners+0.895
ocument+0.877
Neg logit contributions
idav-0.812
ween-0.754
zeb-0.751
wave-0.736
abase-0.717
Token R
Token ID371
Feature activation-3.00e+00

Pos logit contributions
enthal+3.137
esan+2.754
aeda+2.602
iners+2.570
ROR+2.506
Neg logit contributions
idav-2.867
ween-2.663
zeb-2.618
wave-2.575
abase-2.496
Tokenxd
Token ID24954
Feature activation-2.38e+00

Pos logit contributions
idav+1.921
zeb+1.815
ween+1.800
wave+1.774
abase+1.718
Neg logit contributions
enthal-2.678
esan-2.378
aeda-2.252
iners-2.238
ocument-2.212
Token8
Token ID23
Feature activation+4.55e+00

Pos logit contributions
idav+1.363
zeb+1.264
ween+1.254
wave+1.233
abase+1.183
Neg logit contributions
enthal-2.307
esan-2.069
aeda-1.969
iners-1.954
ocument-1.930
Token
Token ID198
Feature activation-1.63e+00

Pos logit contributions
idav+1.800
zeb+1.693
ween+1.691
wave+1.666
abase+1.614
Neg logit contributions
enthal-2.178
esan-1.927
aeda-1.819
iners-1.803
ocument-1.771
Token
Token ID198
Feature activation-1.98e+00

Pos logit contributions
idav+1.057
zeb+1.012
ween+1.005
wave+1.001
 Faul+0.941
Neg logit contributions
enthal-1.434
esan-1.275
aeda-1.222
iners-1.195
ocument-1.193
TokenReviewer
Token ID35407
Feature activation+1.70e+00

Pos logit contributions
idav+1.513
zeb+1.442
ween+1.434
wave+1.429
abase+1.359
Neg logit contributions
enthal-1.520
esan-1.339
aeda-1.260
iners-1.235
ocument-1.221
Token:
Token ID25
Feature activation+6.22e+00

Pos logit contributions
enthal+1.557
esan+1.385
aeda+1.306
iners+1.302
ocument+1.279
Neg logit contributions
idav-1.067
ween-0.984
zeb-0.981
wave-0.956
abase-0.936
Token Mike
Token ID4995
Feature activation+4.43e+00

Pos logit contributions
enthal+5.031
esan+4.454
iners+4.139
aeda+4.109
ROR+4.049
Neg logit contributions
idav-4.296
ween-3.983
zeb-3.941
wave-3.899
abase-3.850
TokenM
Token ID44
Feature activation+1.25e+01

Pos logit contributions
enthal+3.743
esan+3.242
aeda+3.068
iners+3.040
ROR+3.023
Neg logit contributions
idav-3.013
ween-2.814
zeb-2.810
wave-2.742
abase-2.734
Tokenanners
Token ID15672
Feature activation+7.35e-01

Pos logit contributions
enthal+6.298
esan+4.820
aeda+4.750
iners+4.605
ocument+4.222
Neg logit contributions
idav-11.579
zeb-10.982
 Faul-10.820
wave-10.798
ween-10.761
Token -
Token ID532
Feature activation+2.41e+00

Pos logit contributions
enthal+0.591
esan+0.511
aeda+0.481
iners+0.480
ROR+0.471
Neg logit contributions
idav-0.543
zeb-0.511
ween-0.510
wave-0.502
abase-0.491
Token favorite
Token ID4004
Feature activation+3.31e+00

Pos logit contributions
enthal+1.739
esan+1.496
aeda+1.389
iners+1.378
ocument+1.341
Neg logit contributions
idav-1.988
ween-1.881
zeb-1.877
wave-1.846
abase-1.805
Token favorite
Token ID4004
Feature activation+3.82e+00

Pos logit contributions
enthal+2.275
esan+1.948
iners+1.781
aeda+1.774
ROR+1.737
Neg logit contributions
idav-2.824
ween-2.671
zeb-2.666
wave-2.603
abase-2.576
Token favorite
Token ID4004
Feature activation+5.83e+00

Pos logit contributions
enthal+2.585
esan+2.212
iners+2.017
aeda+2.003
ROR+1.968
Neg logit contributions
idav-3.286
ween-3.106
zeb-3.101
wave-3.023
abase-2.998
Tokenkind
Token ID11031
Feature activation-8.61e-01

Pos logit contributions
idav+4.574
ween+4.369
zeb+4.366
wave+4.251
abase+4.030
Neg logit contributions
enthal-5.331
esan-4.820
ROR-4.569
aeda-4.457
iners-4.448
Tokenel
Token ID417
Feature activation-3.55e+00

Pos logit contributions
idav+0.611
zeb+0.579
ween+0.576
wave+0.570
abase+0.548
Neg logit contributions
enthal-0.709
esan-0.622
aeda-0.592
iners-0.586
ocument-0.577
Token.
Token ID13
Feature activation-3.16e+00

Pos logit contributions
idav+2.279
zeb+2.149
ween+2.141
wave+2.093
abase+2.018
Neg logit contributions
enthal-3.143
esan-2.800
aeda-2.672
iners-2.640
ocument-2.600
Token
Token ID198
Feature activation+1.47e+00

Pos logit contributions
idav+2.154
zeb+2.024
ween+2.016
wave+1.978
 Faul+1.918
Neg logit contributions
enthal-2.698
esan-2.387
aeda-2.267
iners-2.237
ocument-2.203
Token
Token ID198
Feature activation+1.08e+00

Pos logit contributions
enthal+1.197
esan+1.050
aeda+0.981
iners+0.979
ROR+0.958
Neg logit contributions
idav-1.074
ween-1.001
zeb-0.998
wave-0.978
abase-0.963
TokenV
Token ID53
Feature activation+1.24e+01

Pos logit contributions
enthal+0.880
esan+0.771
iners+0.722
aeda+0.716
ROR+0.711
Neg logit contributions
idav-0.789
ween-0.740
zeb-0.736
wave-0.724
abase-0.715
Tokenad
Token ID324
Feature activation+7.50e-01

Pos logit contributions
enthal+8.187
esan+7.153
iners+6.748
aeda+6.586
ocument+6.156
Neg logit contributions
idav-9.464
 Faul-9.158
ween-9.106
zeb-8.920
wave-8.870
Tokenim
Token ID320
Feature activation+1.73e+00

Pos logit contributions
enthal+0.600
esan+0.525
iners+0.490
aeda+0.490
ocument+0.482
Neg logit contributions
idav-0.555
ween-0.527
zeb-0.520
wave-0.515
 Faul-0.501
Token And
Token ID843
Feature activation+2.48e+00

Pos logit contributions
enthal+1.340
esan+1.167
aeda+1.083
iners+1.069
ocument+1.056
Neg logit contributions
idav-1.329
ween-1.267
zeb-1.241
wave-1.228
abase-1.203
Tokenrey
Token ID4364
Feature activation+4.95e+00

Pos logit contributions
enthal+1.834
esan+1.575
aeda+1.467
iners+1.450
ocument+1.414
Neg logit contributions
idav-2.001
ween-1.885
zeb-1.884
wave-1.847
abase-1.829
Tokenuk
Token ID2724
Feature activation+4.33e-01

Pos logit contributions
enthal+3.148
esan+2.657
iners+2.392
aeda+2.373
ocument+2.282
Neg logit contributions
idav-4.463
ween-4.241
zeb-4.208
wave-4.167
abase-4.148
Tokenyoutube
Token ID11604
Feature activation-1.90e+00

Pos logit contributions
idav+1.610
ween+1.506
zeb+1.502
wave+1.479
abase+1.417
Neg logit contributions
enthal-2.255
esan-2.003
aeda-1.902
iners-1.885
ROR-1.853
Token.
Token ID13
Feature activation+5.20e+00

Pos logit contributions
idav+1.136
zeb+1.079
ween+1.073
wave+1.066
abase+1.000
Neg logit contributions
enthal-1.770
esan-1.580
aeda-1.512
iners-1.490
ocument-1.473
Tokencom
Token ID785
Feature activation+8.54e-01

Pos logit contributions
enthal+2.509
esan+1.967
iners+1.738
aeda+1.730
ocument+1.655
Neg logit contributions
idav-5.463
ween-5.196
zeb-5.153
 Faul-5.115
abase-5.089
Token/
Token ID14
Feature activation+1.44e+00

Pos logit contributions
enthal+0.726
esan+0.637
aeda+0.603
iners+0.600
ocument+0.591
Neg logit contributions
idav-0.591
zeb-0.551
ween-0.549
wave-0.540
abase-0.529
Tokenchannel
Token ID17620
Feature activation+1.83e+00

Pos logit contributions
enthal+1.058
esan+0.914
aeda+0.853
iners+0.851
ocument+0.834
Neg logit contributions
idav-1.158
ween-1.087
zeb-1.085
wave-1.061
 Faul-1.056
Token/
Token ID14
Feature activation+1.24e+01

Pos logit contributions
enthal+1.582
esan+1.397
aeda+1.319
iners+1.310
ROR+1.286
Neg logit contributions
idav-1.249
ween-1.159
zeb-1.159
wave-1.128
abase-1.108
TokenUC
Token ID9598
Feature activation+1.50e+00

Pos logit contributions
enthal+5.683
esan+5.115
ROR+4.650
ocument+4.295
aeda+4.254
Neg logit contributions
idav-11.779
abase-11.196
ween-11.110
 Faul-10.996
zeb-10.841
Token_
Token ID62
Feature activation-5.51e+00

Pos logit contributions
enthal+1.295
esan+1.141
aeda+1.083
iners+1.075
ROR+1.060
Neg logit contributions
idav-1.015
ween-0.946
zeb-0.938
wave-0.921
 Faul-0.912
TokenK
Token ID42
Feature activation-3.57e+00

Pos logit contributions
idav+3.810
zeb+3.620
ween+3.596
wave+3.548
abase+3.384
Neg logit contributions
enthal-4.570
esan-4.036
aeda-3.805
iners-3.760
ocument-3.708
Tokenk
Token ID74
Feature activation-7.97e+00

Pos logit contributions
idav+2.489
zeb+2.350
ween+2.349
wave+2.308
abase+2.219
Neg logit contributions
enthal-2.993
esan-2.635
aeda-2.486
iners-2.463
ocument-2.427
TokenBY
Token ID17513
Feature activation-7.17e-01

Pos logit contributions
idav+5.456
zeb+5.212
ween+5.187
wave+5.101
abase+4.843
Neg logit contributions
enthal-6.458
esan-5.710
aeda-5.375
iners-5.320
ocument-5.249
Token(
Token ID7
Feature activation-2.60e+00

Pos logit contributions
enthal+0.856
esan+0.768
aeda+0.732
iners+0.727
ocument+0.717
Neg logit contributions
idav-0.478
ween-0.440
zeb-0.440
wave-0.429
abase-0.413
Token55
Token ID2816
Feature activation+4.03e+00

Pos logit contributions
idav+1.762
zeb+1.655
ween+1.655
wave+1.628
abase+1.569
Neg logit contributions
enthal-2.228
esan-1.970
aeda-1.857
iners-1.845
ocument-1.815
Tokens
Token ID82
Feature activation+4.55e+00

Pos logit contributions
enthal+3.302
esan+2.892
iners+2.728
aeda+2.701
ROR+2.645
Neg logit contributions
idav-2.867
ween-2.689
zeb-2.639
wave-2.634
abase-2.577
Token)}
Token ID38165
Feature activation+5.08e+00

Pos logit contributions
enthal+2.899
esan+2.414
iners+2.226
aeda+2.224
ROR+2.142
Neg logit contributions
idav-4.103
ween-3.895
zeb-3.865
wave-3.803
abase-3.759
Token Ra
Token ID7567
Feature activation+2.75e+00

Pos logit contributions
enthal+4.027
esan+3.530
aeda+3.353
iners+3.320
ROR+3.241
Neg logit contributions
idav-3.742
ween-3.488
zeb-3.408
wave-3.339
abase-3.237
Token8
Token ID23
Feature activation+1.22e+01

Pos logit contributions
enthal+2.431
esan+2.148
aeda+2.025
iners+2.013
ROR+1.968
Neg logit contributions
idav-1.811
ween-1.689
zeb-1.665
wave-1.648
 Faul-1.618
Token {
Token ID1391
Feature activation+1.55e+00

Pos logit contributions
enthal+5.398
esan+4.325
iners+3.937
aeda+3.735
 fork+3.699
Neg logit contributions
idav-12.240
ween-11.765
zeb-11.478
 Faul-11.074
wave-11.055
Token(
Token ID7
Feature activation-1.69e+00

Pos logit contributions
enthal+1.521
esan+1.364
aeda+1.294
iners+1.289
ROR+1.271
Neg logit contributions
idav-0.880
ween-0.808
zeb-0.806
wave-0.784
abase-0.760
Token113
Token ID16616
Feature activation+9.83e+00

Pos logit contributions
idav+1.151
zeb+1.079
ween+1.079
wave+1.060
abase+1.025
Neg logit contributions
enthal-1.456
esan-1.286
aeda-1.214
iners-1.205
ocument-1.186
Tokens
Token ID82
Feature activation+3.11e+00

Pos logit contributions
enthal+7.400
esan+6.365
iners+6.116
aeda+5.881
ROR+5.839
Neg logit contributions
idav-7.347
ween-6.685
zeb-6.655
abase-6.536
 Faul-6.471
Token)}
Token ID38165
Feature activation+9.87e+00

Pos logit contributions
enthal+2.008
esan+1.684
aeda+1.555
iners+1.546
ROR+1.489
Neg logit contributions
idav-2.792
ween-2.642
zeb-2.636
wave-2.591
abase-2.563
Token networking
Token ID19140
Feature activation+2.23e+00

Pos logit contributions
enthal+0.817
esan+0.709
iners+0.671
aeda+0.659
ocument+0.646
Neg logit contributions
idav-0.796
ween-0.751
zeb-0.750
wave-0.729
abase-0.723
Token website
Token ID3052
Feature activation-6.70e-01

Pos logit contributions
enthal+1.711
esan+1.482
iners+1.406
aeda+1.383
ocument+1.336
Neg logit contributions
idav-1.738
ween-1.633
zeb-1.613
wave-1.575
abase-1.555
Token.
Token ID13
Feature activation-5.18e-01

Pos logit contributions
idav+0.450
ween+0.421
zeb+0.419
wave+0.411
abase+0.399
Neg logit contributions
enthal-0.586
esan-0.517
aeda-0.488
iners-0.485
ocument-0.477
Token
Token ID198
Feature activation+1.80e+00

Pos logit contributions
idav+0.367
ween+0.344
zeb+0.344
wave+0.338
abase+0.328
Neg logit contributions
enthal-0.432
esan-0.379
aeda-0.357
iners-0.355
ocument-0.349
Token
Token ID198
Feature activation+1.41e+00

Pos logit contributions
enthal+1.457
esan+1.277
aeda+1.190
iners+1.190
ROR+1.165
Neg logit contributions
idav-1.329
ween-1.238
zeb-1.233
wave-1.207
abase-1.192
TokenV
Token ID53
Feature activation+1.22e+01

Pos logit contributions
enthal+1.157
esan+1.015
iners+0.953
aeda+0.946
ROR+0.938
Neg logit contributions
idav-1.012
ween-0.945
zeb-0.945
wave-0.925
abase-0.913
Tokenital
Token ID1287
Feature activation+2.27e+00

Pos logit contributions
enthal+8.822
esan+7.872
iners+7.441
aeda+7.341
ocument+6.890
Neg logit contributions
idav-8.394
 Faul-8.176
ween-8.093
zeb-7.968
wave-7.843
Tokeny
Token ID88
Feature activation+1.26e+00

Pos logit contributions
enthal+1.798
esan+1.578
iners+1.465
aeda+1.464
ocument+1.432
Neg logit contributions
idav-1.692
ween-1.598
zeb-1.581
wave-1.556
abase-1.518
Token Nem
Token ID22547
Feature activation+5.69e+00

Pos logit contributions
enthal+0.829
esan+0.693
aeda+0.636
iners+0.626
ocument+0.615
Neg logit contributions
idav-1.121
ween-1.074
zeb-1.062
wave-1.054
abase-1.030
Tokenov
Token ID709
Feature activation+4.16e-01

Pos logit contributions
enthal+2.339
esan+1.770
iners+1.498
aeda+1.457
ocument+1.356
Neg logit contributions
idav-6.384
ween-6.127
zeb-6.102
 Faul-6.057
wave-6.025
Token,
Token ID11
Feature activation+3.59e+00

Pos logit contributions
enthal+0.362
esan+0.319
aeda+0.299
iners+0.298
ocument+0.293
Neg logit contributions
idav-0.283
ween-0.265
zeb-0.263
wave-0.259
abase-0.251
Tokenpart
Token ID3911
Feature activation-4.40e-01

Pos logit contributions
enthal+1.171
esan+1.027
aeda+0.965
iners+0.958
ocument+0.937
Neg logit contributions
idav-0.996
zeb-0.929
ween-0.929
wave-0.908
abase-0.890
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
idav+0.291
zeb+0.272
ween+0.272
wave+0.266
abase+0.258
Neg logit contributions
enthal-0.389
esan-0.345
aeda-0.325
iners-0.323
ocument-0.319
Token
Token ID198
Feature activation-2.97e-01

Pos logit contributions
enthal+0.826
esan+0.723
iners+0.677
aeda+0.676
ocument+0.664
Neg logit contributions
idav-0.752
zeb-0.707
ween-0.707
wave-0.690
abase-0.678
Token
Token ID198
Feature activation+1.00e+00

Pos logit contributions
idav+0.204
zeb+0.192
ween+0.192
wave+0.190
abase+0.182
Neg logit contributions
enthal-0.254
esan-0.223
aeda-0.212
iners-0.209
ocument-0.207
TokenA
Token ID32
Feature activation+3.46e+00

Pos logit contributions
enthal+0.847
esan+0.748
iners+0.707
aeda+0.700
ROR+0.692
Neg logit contributions
idav-0.701
zeb-0.652
ween-0.650
wave-0.633
abase-0.629
Token hot
Token ID3024
Feature activation+1.21e+01

Pos logit contributions
enthal+2.798
esan+2.461
iners+2.281
aeda+2.275
ocument+2.246
Neg logit contributions
idav-2.520
ween-2.360
zeb-2.343
wave-2.296
abase-2.264
Token-
Token ID12
Feature activation+2.41e+00

Pos logit contributions
enthal+8.880
esan+7.345
iners+7.146
ocument+6.976
aeda+6.884
Neg logit contributions
idav-8.628
zeb-7.898
abase-7.758
ween-7.746
 Faul-7.497
Tokenbutton
Token ID16539
Feature activation+1.49e+00

Pos logit contributions
enthal+1.991
esan+1.719
iners+1.621
aeda+1.617
ocument+1.589
Neg logit contributions
idav-1.733
zeb-1.616
ween-1.603
 Faul-1.568
abase-1.561
Token topic
Token ID7243
Feature activation+2.00e+00

Pos logit contributions
enthal+1.408
esan+1.255
iners+1.181
aeda+1.178
ocument+1.163
Neg logit contributions
idav-0.897
zeb-0.820
ween-0.810
wave-0.795
abase-0.784
Token in
Token ID287
Feature activation-4.39e-01

Pos logit contributions
enthal+1.616
esan+1.416
iners+1.318
aeda+1.317
ocument+1.293
Neg logit contributions
idav-1.482
zeb-1.379
ween-1.374
wave-1.345
abase-1.325
Token the
Token ID262
Feature activation-1.27e+00

Pos logit contributions
idav+0.323
zeb+0.303
ween+0.302
wave+0.297
abase+0.290
Neg logit contributions
enthal-0.354
esan-0.310
aeda-0.291
iners-0.290
ocument-0.284
Token]
Token ID60
Feature activation-2.54e-01

Pos logit contributions
idav+0.136
ween+0.125
zeb+0.125
wave+0.122
abase+0.118
Neg logit contributions
enthal-0.233
esan-0.209
aeda-0.198
iners-0.197
ocument-0.194
Token CBS
Token ID11133
Feature activation-2.64e+00

Pos logit contributions
idav+0.185
ween+0.173
zeb+0.173
wave+0.170
abase+0.165
Neg logit contributions
enthal-0.207
esan-0.182
aeda-0.171
iners-0.171
ocument-0.166
TokenSports
Token ID18153
Feature activation+2.76e+00

Pos logit contributions
idav+1.665
ween+1.575
zeb+1.562
wave+1.532
abase+1.476
Neg logit contributions
enthal-2.387
esan-2.125
aeda-2.019
iners-1.989
ocument-1.973
Token.
Token ID13
Feature activation+2.90e+00

Pos logit contributions
enthal+2.323
esan+2.041
iners+1.926
aeda+1.889
ROR+1.868
Neg logit contributions
idav-1.961
zeb-1.780
ween-1.765
wave-1.762
 Faul-1.697
Tokencom
Token ID785
Feature activation+1.27e+00

Pos logit contributions
enthal+1.518
esan+1.222
iners+1.085
aeda+1.077
ocument+1.041
Neg logit contributions
idav-2.979
ween-2.821
zeb-2.809
wave-2.780
abase-2.737
Token,[
Token ID17414
Feature activation+1.20e+01

Pos logit contributions
enthal+1.100
esan+0.973
iners+0.921
aeda+0.918
ocument+0.894
Neg logit contributions
idav-0.863
zeb-0.797
ween-0.789
wave-0.786
abase-0.754
Token96
Token ID4846
Feature activation+1.74e+00

Pos logit contributions
enthal+6.568
esan+5.657
aeda+5.426
ROR+5.305
bos+5.262
Neg logit contributions
idav-10.524
zeb-9.611
ween-9.591
 Faul-9.568
abase-9.411
Token]
Token ID60
Feature activation+7.81e-01

Pos logit contributions
enthal+1.658
esan+1.488
aeda+1.410
iners+1.394
ocument+1.377
Neg logit contributions
idav-1.033
ween-0.950
zeb-0.948
wave-0.926
abase-0.896
Token NBC
Token ID9716
Feature activation+6.71e-01

Pos logit contributions
enthal+0.640
esan+0.561
iners+0.526
aeda+0.525
ocument+0.514
Neg logit contributions
idav-0.568
ween-0.528
zeb-0.528
wave-0.520
abase-0.504
TokenSports
Token ID18153
Feature activation+2.54e+00

Pos logit contributions
enthal+0.598
esan+0.529
iners+0.502
aeda+0.498
ocument+0.489
Neg logit contributions
idav-0.439
zeb-0.407
ween-0.403
wave-0.398
abase-0.387
Token.
Token ID13
Feature activation+4.20e+00

Pos logit contributions
enthal+2.145
esan+1.878
iners+1.777
aeda+1.746
ROR+1.726
Neg logit contributions
idav-1.787
zeb-1.631
ween-1.630
wave-1.616
 Faul-1.558
Token-
Token ID12
Feature activation-4.50e-01

Pos logit contributions
enthal+3.770
esan+3.326
aeda+3.110
iners+3.062
ocument+2.950
Neg logit contributions
idav-3.556
ween-3.301
zeb-3.232
wave-3.225
abase-3.182
Tokenwall
Token ID11930
Feature activation+3.75e+00

Pos logit contributions
idav+0.333
ween+0.312
zeb+0.311
wave+0.306
abase+0.299
Neg logit contributions
enthal-0.362
esan-0.316
aeda-0.298
iners-0.294
ocument-0.288
Tokenaby
Token ID3930
Feature activation+2.14e+00

Pos logit contributions
enthal+3.056
esan+2.705
aeda+2.540
iners+2.536
ocument+2.432
Neg logit contributions
idav-2.686
ween-2.508
zeb-2.486
wave-2.450
abase-2.405
Token (
Token ID357
Feature activation+2.41e+00

Pos logit contributions
enthal+1.769
esan+1.553
aeda+1.474
iners+1.449
ocument+1.426
Neg logit contributions
idav-1.530
ween-1.434
zeb-1.420
wave-1.398
abase-1.368
TokenPet
Token ID25803
Feature activation+2.52e+00

Pos logit contributions
enthal+2.069
esan+1.813
aeda+1.728
iners+1.710
ROR+1.694
Neg logit contributions
idav-1.634
ween-1.519
zeb-1.506
wave-1.467
abase-1.450
Tokenrog
Token ID3828
Feature activation+1.20e+01

Pos logit contributions
enthal+2.293
esan+2.032
aeda+1.930
iners+1.895
ROR+1.850
Neg logit contributions
idav-1.580
zeb-1.464
ween-1.463
wave-1.458
 Faul-1.426
Tokenale
Token ID1000
Feature activation+5.95e+00

Pos logit contributions
enthal+9.964
esan+8.797
aeda+8.222
iners+8.021
ocument+7.556
Neg logit contributions
idav-7.521
 Faul-7.117
wave-6.868
zeb-6.798
ween-6.781
Token br
Token ID865
Feature activation+1.46e+00

Pos logit contributions
enthal+4.820
esan+4.315
aeda+4.129
iners+3.984
ocument+3.900
Neg logit contributions
idav-4.097
wave-3.834
ween-3.818
zeb-3.774
abase-3.674
Tokenachy
Token ID35586
Feature activation+9.53e-01

Pos logit contributions
enthal+1.113
esan+0.979
aeda+0.916
iners+0.901
ocument+0.880
Neg logit contributions
idav-1.130
ween-1.078
zeb-1.069
wave-1.059
 Faul-1.039
Tokenot
Token ID313
Feature activation-5.00e+00

Pos logit contributions
enthal+0.628
esan+0.525
aeda+0.492
iners+0.473
ocument+0.467
Neg logit contributions
idav-0.841
ween-0.807
zeb-0.800
wave-0.792
 Faul-0.775
Tokenis
Token ID271
Feature activation+2.24e+00

Pos logit contributions
idav+3.152
zeb+2.957
ween+2.921
wave+2.864
abase+2.752
Neg logit contributions
enthal-4.488
esan-3.997
iners-3.769
ROR-3.765
aeda-3.749
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
enthal+1.115
esan+0.980
iners+0.928
aeda+0.925
ocument+0.915
Neg logit contributions
idav-0.851
ween-0.804
zeb-0.798
wave-0.778
abase-0.761
TokenSave
Token ID16928
Feature activation+7.95e-02

Pos logit contributions
idav+0.955
ween+0.905
zeb+0.904
wave+0.890
abase+0.868
Neg logit contributions
enthal-0.843
esan-0.724
aeda-0.676
iners-0.670
ocument-0.656
Token($
Token ID16763
Feature activation+3.89e+00

Pos logit contributions
enthal+0.069
esan+0.061
aeda+0.057
iners+0.057
ocument+0.056
Neg logit contributions
idav-0.054
ween-0.051
zeb-0.050
wave-0.049
abase-0.048
TokenOut
Token ID7975
Feature activation+2.19e-01

Pos logit contributions
enthal+3.125
esan+2.709
iners+2.546
ROR+2.509
ocument+2.505
Neg logit contributions
idav-2.845
zeb-2.637
ween-2.636
 Faul-2.579
wave-2.535
TokenFile
Token ID8979
Feature activation+1.13e-02

Pos logit contributions
enthal+0.187
esan+0.165
aeda+0.154
iners+0.154
ocument+0.151
Neg logit contributions
idav-0.152
zeb-0.143
ween-0.142
wave-0.139
abase-0.136
Token,
Token ID11
Feature activation+1.20e+01

Pos logit contributions
enthal+0.010
esan+0.009
aeda+0.008
iners+0.008
ocument+0.008
Neg logit contributions
idav-0.008
ween-0.007
zeb-0.007
wave-0.007
abase-0.007
Token [
Token ID685
Feature activation+9.12e+00

Pos logit contributions
enthal+8.564
esan+7.316
ocument+6.999
ROR+6.926
iners+6.875
Neg logit contributions
idav-8.567
zeb-8.243
ween-8.233
abase-7.876
wave-7.793
Tokensystem
Token ID10057
Feature activation+6.37e+00

Pos logit contributions
enthal+7.528
esan+6.652
iners+6.290
ROR+6.268
ocument+6.233
Neg logit contributions
idav-5.959
ween-5.457
zeb-5.444
 Faul-5.264
abase-5.195
Token.
Token ID13
Feature activation+5.11e+00

Pos logit contributions
enthal+5.076
esan+4.508
iners+4.156
ROR+4.119
ocument+4.099
Neg logit contributions
idav-4.633
zeb-4.317
ween-4.290
 Faul-4.190
wave-4.127
Tokendraw
Token ID19334
Feature activation+3.33e-01

Pos logit contributions
enthal+4.484
esan+3.936
iners+3.787
aeda+3.706
ocument+3.704
Neg logit contributions
idav-3.281
zeb-3.003
ween-2.981
 Faul-2.962
abase-2.889
Tokening
Token ID278
Feature activation+1.33e+00

Pos logit contributions
enthal+0.257
esan+0.223
aeda+0.210
iners+0.207
ocument+0.204
Neg logit contributions
idav-0.257
ween-0.243
zeb-0.243
wave-0.239
abase-0.232
Token at
Token ID379
Feature activation-8.00e-01

Pos logit contributions
idav+2.251
ween+2.140
zeb+2.139
wave+2.110
abase+2.055
Neg logit contributions
enthal-2.437
esan-2.130
aeda-2.007
iners-1.982
ocument-1.960
Token least
Token ID1551
Feature activation-1.15e-01

Pos logit contributions
idav+0.610
zeb+0.571
ween+0.570
wave+0.561
abase+0.544
Neg logit contributions
enthal-0.628
esan-0.547
aeda-0.514
iners-0.510
ocument-0.498
Token 100
Token ID1802
Feature activation-3.28e+00

Pos logit contributions
idav+0.087
zeb+0.082
ween+0.082
wave+0.080
abase+0.078
Neg logit contributions
enthal-0.090
esan-0.078
aeda-0.073
iners-0.073
ocument-0.071
Token,
Token ID11
Feature activation-1.61e+00

Pos logit contributions
idav+2.044
zeb+1.906
ween+1.906
wave+1.869
abase+1.801
Neg logit contributions
enthal-3.008
esan-2.677
aeda-2.541
iners-2.516
ocument-2.485
Token000
Token ID830
Feature activation-4.93e-01

Pos logit contributions
idav+0.714
ween+0.651
zeb+0.646
wave+0.634
abase+0.599
Neg logit contributions
enthal-1.762
esan-1.603
aeda-1.539
iners-1.528
ocument-1.510
Token light
Token ID1657
Feature activation+1.19e+01

Pos logit contributions
idav+0.329
zeb+0.306
ween+0.306
wave+0.298
abase+0.291
Neg logit contributions
enthal-0.432
esan-0.383
aeda-0.361
iners-0.361
ocument-0.353
Token-
Token ID12
Feature activation+5.61e+00

Pos logit contributions
enthal+7.861
esan+6.697
iners+6.274
bos+5.913
aeda+5.854
Neg logit contributions
idav-9.556
zeb-8.933
ween-8.592
abase-8.587
 Faul-8.324
Tokenyears
Token ID19002
Feature activation-9.43e-02

Pos logit contributions
enthal+3.636
esan+2.975
iners+2.820
aeda+2.779
bos+2.621
Neg logit contributions
idav-4.960
zeb-4.612
 Faul-4.582
abase-4.573
ween-4.519
Token across
Token ID1973
Feature activation-2.82e+00

Pos logit contributions
idav+0.076
zeb+0.071
ween+0.071
wave+0.069
abase+0.068
Neg logit contributions
enthal-0.070
esan-0.061
aeda-0.056
iners-0.056
ocument-0.055
Token.
Token ID13
Feature activation-1.79e+00

Pos logit contributions
idav+1.792
ween+1.678
zeb+1.673
wave+1.647
abase+1.588
Neg logit contributions
enthal-2.540
esan-2.255
aeda-2.143
iners-2.122
ocument-2.093
Token We
Token ID775
Feature activation+6.12e-01

Pos logit contributions
idav+1.198
zeb+1.129
ween+1.128
wave+1.111
 Faul+1.071
Neg logit contributions
enthal-1.547
esan-1.367
aeda-1.296
iners-1.282
ocument-1.265
Token.
Token ID13
Feature activation-8.40e-02

Pos logit contributions
idav+0.328
ween+0.307
zeb+0.307
wave+0.301
abase+0.292
Neg logit contributions
enthal-0.424
esan-0.375
aeda-0.354
iners-0.352
ocument-0.346
TokenCount
Token ID12332
Feature activation-6.04e+00

Pos logit contributions
idav+0.059
zeb+0.055
ween+0.055
wave+0.054
abase+0.052
Neg logit contributions
enthal-0.071
esan-0.063
aeda-0.059
iners-0.059
ocument-0.058
Token ;
Token ID2162
Feature activation+4.04e+00

Pos logit contributions
idav+4.080
wave+3.858
ween+3.809
zeb+3.789
abase+3.631
Neg logit contributions
enthal-5.061
esan-4.406
aeda-4.313
iners-4.168
ocument-4.090
Token $
Token ID720
Feature activation+1.80e+00

Pos logit contributions
enthal+2.421
esan+2.094
iners+1.853
ocument+1.822
aeda+1.800
Neg logit contributions
idav-3.696
ween-3.551
zeb-3.538
wave-3.481
abase-3.425
Tokeni
Token ID72
Feature activation+8.09e-01

Pos logit contributions
enthal+1.425
esan+1.257
iners+1.163
aeda+1.157
ocument+1.141
Neg logit contributions
idav-1.335
zeb-1.261
ween-1.261
wave-1.228
abase-1.208
Token++)
Token ID29577
Feature activation+1.19e+01

Pos logit contributions
enthal+0.566
esan+0.488
aeda+0.450
iners+0.449
ROR+0.436
Neg logit contributions
idav-0.680
ween-0.643
zeb-0.643
wave-0.632
abase-0.620
Token {
Token ID1391
Feature activation+4.55e+00

Pos logit contributions
enthal+5.478
esan+4.543
ocument+4.309
iners+4.195
ROR+4.020
Neg logit contributions
idav-11.098
zeb-10.961
ween-10.802
wave-10.399
abase-10.251
Token if
Token ID611
Feature activation+6.40e+00

Pos logit contributions
enthal+3.455
esan+3.039
iners+2.835
ocument+2.807
ROR+2.774
Neg logit contributions
idav-3.425
zeb-3.262
ween-3.250
wave-3.129
abase-3.090
Token ($
Token ID7198
Feature activation-1.48e+00

Pos logit contributions
enthal+4.495
esan+3.930
ocument+3.674
iners+3.606
aeda+3.465
Neg logit contributions
idav-5.054
zeb-4.847
ween-4.817
wave-4.643
abase-4.534
Tokeni
Token ID72
Feature activation-1.21e+00

Pos logit contributions
idav+1.054
ween+0.989
zeb+0.989
wave+0.971
abase+0.942
Neg logit contributions
enthal-1.237
esan-1.087
aeda-1.025
iners-1.017
ocument-1.000
Token -
Token ID532
Feature activation-6.15e-01

Pos logit contributions
idav+0.799
ween+0.748
zeb+0.747
wave+0.733
abase+0.709
Neg logit contributions
enthal-1.069
esan-0.946
aeda-0.897
iners-0.889
ocument-0.875
Token from
Token ID422
Feature activation+1.98e+00

Pos logit contributions
enthal+0.047
esan+0.041
aeda+0.039
iners+0.039
ocument+0.038
Neg logit contributions
idav-0.038
ween-0.036
zeb-0.036
wave-0.035
abase-0.034
Token another
Token ID1194
Feature activation+2.96e+00

Pos logit contributions
enthal+1.607
esan+1.411
aeda+1.327
iners+1.314
ocument+1.285
Neg logit contributions
idav-1.446
ween-1.354
zeb-1.353
wave-1.328
abase-1.292
Token area
Token ID1989
Feature activation+5.73e+00

Pos logit contributions
enthal+2.904
esan+2.622
aeda+2.470
iners+2.438
ROR+2.415
Neg logit contributions
idav-1.672
ween-1.525
zeb-1.517
wave-1.465
abase-1.418
Token of
Token ID286
Feature activation+6.96e-01

Pos logit contributions
enthal+4.456
esan+3.947
aeda+3.614
iners+3.564
ROR+3.498
Neg logit contributions
idav-4.314
ween-4.007
zeb-3.986
abase-3.858
wave-3.854
Token the
Token ID262
Feature activation+4.39e+00

Pos logit contributions
enthal+0.565
esan+0.495
aeda+0.467
iners+0.462
ocument+0.454
Neg logit contributions
idav-0.507
ween-0.478
zeb-0.478
wave-0.470
abase-0.456
Token body
Token ID1767
Feature activation+1.18e+01

Pos logit contributions
enthal+2.697
esan+2.265
iners+2.038
aeda+2.037
ROR+1.967
Neg logit contributions
idav-4.058
ween-3.835
zeb-3.820
wave-3.741
abase-3.686
Token,'
Token ID4032
Feature activation+3.50e+00

Pos logit contributions
enthal+8.342
esan+7.106
aeda+6.633
iners+6.323
ocument+6.184
Neg logit contributions
idav-8.821
zeb-8.452
ween-8.284
wave-8.143
abase-7.890
Token says
Token ID1139
Feature activation+2.96e+00

Pos logit contributions
enthal+2.754
esan+2.402
aeda+2.232
iners+2.231
ocument+2.173
Neg logit contributions
idav-2.600
zeb-2.469
ween-2.464
wave-2.416
abase-2.365
Token a
Token ID257
Feature activation-1.32e-01

Pos logit contributions
enthal+2.277
esan+1.968
aeda+1.842
iners+1.835
ROR+1.794
Neg logit contributions
idav-2.275
ween-2.149
zeb-2.132
wave-2.109
abase-2.056
Token source
Token ID2723
Feature activation-3.39e+00

Pos logit contributions
idav+0.101
ween+0.096
zeb+0.095
wave+0.094
abase+0.091
Neg logit contributions
enthal-0.103
esan-0.090
aeda-0.084
iners-0.083
ocument-0.081
Token.
Token ID13
Feature activation+2.12e+00

Pos logit contributions
idav+2.158
ween+2.029
zeb+2.001
wave+1.970
abase+1.903
Neg logit contributions
enthal-3.063
esan-2.696
aeda-2.589
iners-2.565
ROR-2.517
Tokenpath
Token ID6978
Feature activation-4.86e-01

Pos logit contributions
idav+0.535
ween+0.508
zeb+0.507
wave+0.501
abase+0.485
Neg logit contributions
enthal-0.523
esan-0.454
aeda-0.429
iners-0.423
ocument-0.414
Token)"
Token ID16725
Feature activation+6.04e+00

Pos logit contributions
idav+0.317
ween+0.296
zeb+0.296
wave+0.290
abase+0.281
Neg logit contributions
enthal-0.433
esan-0.384
aeda-0.363
iners-0.360
ocument-0.355
Token break
Token ID2270
Feature activation+6.67e+00

Pos logit contributions
enthal+4.419
esan+3.803
iners+3.570
ROR+3.568
ocument+3.522
Neg logit contributions
idav-4.603
ween-4.501
zeb-4.418
abase-4.241
wave-4.213
Token }
Token ID1782
Feature activation+4.62e+00

Pos logit contributions
enthal+4.490
esan+3.772
iners+3.554
ocument+3.469
ROR+3.468
Neg logit contributions
idav-5.474
ween-5.329
zeb-5.303
abase-5.094
wave-5.026
Token }
Token ID1782
Feature activation+3.76e+00

Pos logit contributions
enthal+3.207
esan+2.768
iners+2.567
ROR+2.528
ocument+2.513
Neg logit contributions
idav-3.805
ween-3.625
zeb-3.593
abase-3.494
wave-3.473
Token else
Token ID2073
Feature activation+1.18e+01

Pos logit contributions
enthal+2.767
esan+2.409
iners+2.245
ocument+2.210
ROR+2.200
Neg logit contributions
idav-2.973
ween-2.804
zeb-2.801
wave-2.705
abase-2.694
Token {
Token ID1391
Feature activation+4.02e+00

Pos logit contributions
enthal+5.404
esan+4.512
ocument+4.201
iners+4.139
ROR+4.007
Neg logit contributions
idav-11.220
zeb-10.966
ween-10.851
 Faul-10.291
wave-10.263
Token $
Token ID720
Feature activation+1.43e+00

Pos logit contributions
enthal+3.396
esan+2.999
iners+2.842
ocument+2.811
ROR+2.792
Neg logit contributions
idav-2.695
ween-2.565
zeb-2.527
wave-2.458
abase-2.437
TokenSR
Token ID12562
Feature activation+2.38e+00

Pos logit contributions
enthal+1.195
esan+1.050
iners+0.987
aeda+0.985
ocument+0.974
Neg logit contributions
idav-1.004
zeb-0.932
ween-0.932
wave-0.901
 Faul-0.898
Token =
Token ID796
Feature activation+9.02e+00

Pos logit contributions
enthal+2.048
esan+1.823
aeda+1.704
iners+1.702
ROR+1.693
Neg logit contributions
idav-1.599
ween-1.505
zeb-1.492
wave-1.454
abase-1.425
Token [
Token ID685
Feature activation+9.54e+00

Pos logit contributions
enthal+6.331
esan+5.419
iners+5.108
ROR+5.091
ocument+5.085
Neg logit contributions
idav-6.943
ween-6.662
zeb-6.577
wave-6.397
abase-6.195
Token
Token ID198
Feature activation-1.86e+00

Pos logit contributions
idav+1.339
zeb+1.256
ween+1.256
wave+1.233
abase+1.193
Neg logit contributions
enthal-1.648
esan-1.454
aeda-1.379
iners-1.364
ocument-1.341
Token
Token ID198
Feature activation-2.96e+00

Pos logit contributions
idav+1.225
ween+1.164
zeb+1.163
wave+1.150
abase+1.085
Neg logit contributions
enthal-1.611
esan-1.426
aeda-1.367
iners-1.343
ocument-1.327
TokenSan
Token ID15017
Feature activation-2.79e+00

Pos logit contributions
idav+1.997
ween+1.877
zeb+1.871
wave+1.847
abase+1.772
Neg logit contributions
enthal-2.560
esan-2.260
aeda-2.148
iners-2.121
ocument-2.083
Token Francisco
Token ID6033
Feature activation+1.50e+00

Pos logit contributions
idav+1.921
zeb+1.800
ween+1.795
wave+1.768
abase+1.708
Neg logit contributions
enthal-2.373
esan-2.096
aeda-1.983
iners-1.962
ROR-1.935
Token Board
Token ID5926
Feature activation+2.50e-01

Pos logit contributions
enthal+1.198
esan+1.044
aeda+0.977
iners+0.976
ocument+0.955
Neg logit contributions
idav-1.116
ween-1.053
zeb-1.051
wave-1.031
abase-1.009
Token of
Token ID286
Feature activation+1.18e+01

Pos logit contributions
enthal+0.212
esan+0.188
aeda+0.176
iners+0.175
ocument+0.172
Neg logit contributions
idav-0.173
ween-0.163
zeb-0.162
wave-0.159
abase-0.155
Token Super
Token ID3115
Feature activation+4.10e+00

Pos logit contributions
enthal+7.765
esan+6.281
iners+5.945
ROR+5.592
ocument+5.560
Neg logit contributions
idav-9.983
zeb-9.370
ween-9.286
abase-9.202
wave-8.952
Tokenvisors
Token ID27681
Feature activation-4.18e-01

Pos logit contributions
enthal+2.509
esan+2.031
iners+1.905
aeda+1.833
ocument+1.825
Neg logit contributions
idav-3.834
zeb-3.694
ween-3.634
abase-3.566
wave-3.563
Token
Token ID198
Feature activation+1.67e-01

Pos logit contributions
idav+0.291
zeb+0.273
ween+0.273
wave+0.268
abase+0.260
Neg logit contributions
enthal-0.355
esan-0.312
aeda-0.295
iners-0.292
ocument-0.288
Token
Token ID198
Feature activation-2.98e+00

Pos logit contributions
enthal+0.141
esan+0.124
aeda+0.117
iners+0.116
ocument+0.114
Neg logit contributions
idav-0.116
ween-0.109
zeb-0.109
wave-0.107
abase-0.104
TokenSan
Token ID15017
Feature activation-3.10e+00

Pos logit contributions
idav+2.027
ween+1.898
zeb+1.890
wave+1.873
abase+1.798
Neg logit contributions
enthal-2.563
esan-2.261
aeda-2.151
iners-2.122
ocument-2.082
Token Committee
Token ID4606
Feature activation-2.22e-01

Pos logit contributions
idav+4.096
ween+3.877
wave+3.818
zeb+3.816
 Faul+3.685
Neg logit contributions
enthal-5.572
esan-4.921
aeda-4.724
ocument-4.626
iners-4.621
Token and
Token ID290
Feature activation+1.99e+00

Pos logit contributions
idav+0.148
ween+0.139
zeb+0.139
wave+0.135
abase+0.131
Neg logit contributions
enthal-0.195
esan-0.173
aeda-0.163
iners-0.162
ocument-0.159
Token the
Token ID262
Feature activation-8.36e-01

Pos logit contributions
enthal+1.582
esan+1.378
aeda+1.284
iners+1.282
ROR+1.256
Neg logit contributions
idav-1.508
zeb-1.403
ween-1.400
wave-1.362
abase-1.328
Token Commerce
Token ID16127
Feature activation-2.84e+00

Pos logit contributions
idav+0.581
zeb+0.544
ween+0.543
wave+0.532
abase+0.517
Neg logit contributions
enthal-0.712
esan-0.627
aeda-0.591
iners-0.588
ocument-0.575
Token,
Token ID11
Feature activation-4.29e+00

Pos logit contributions
idav+1.939
ween+1.825
zeb+1.813
wave+1.789
abase+1.725
Neg logit contributions
enthal-2.435
esan-2.144
aeda-2.038
iners-2.011
ocument-1.988
Token Justice
Token ID4796
Feature activation-1.72e+01

Pos logit contributions
idav+2.829
ween+2.714
zeb+2.674
wave+2.655
 Faul+2.601
Neg logit contributions
enthal-3.726
esan-3.258
aeda-3.122
iners-3.052
ocument-3.032
Token,
Token ID11
Feature activation-5.42e+00

Pos logit contributions
idav+7.680
ween+7.297
 Faul+7.230
wave+7.132
 Frontier+6.863
Neg logit contributions
enthal-15.169
ocument-13.753
esan-13.492
aeda-13.439
iners-13.133
Token Science
Token ID5800
Feature activation-9.40e+00

Pos logit contributions
idav+3.457
ween+3.325
zeb+3.267
wave+3.238
 Faul+3.167
Neg logit contributions
enthal-4.729
esan-4.187
aeda-4.016
iners-3.935
ocument-3.917
Token and
Token ID290
Feature activation-3.09e+00

Pos logit contributions
idav+5.036
wave+4.743
zeb+4.675
ween+4.669
 Faul+4.544
Neg logit contributions
enthal-8.690
esan-7.829
ocument-7.556
aeda-7.473
iners-7.430
Token Related
Token ID19809
Feature activation-6.63e+00

Pos logit contributions
idav+2.213
ween+2.088
zeb+2.088
wave+2.060
 Faul+1.993
Neg logit contributions
enthal-2.537
esan-2.220
aeda-2.089
iners-2.070
ocument-2.044
Token Ag
Token ID2449
Feature activation+2.94e-01

Pos logit contributions
idav+3.681
ween+3.488
zeb+3.437
wave+3.432
 Faul+3.344
Neg logit contributions
enthal-6.379
esan-5.663
aeda-5.441
ocument-5.317
iners-5.256
Token to
Token ID284
Feature activation-2.89e-01

Pos logit contributions
enthal+0.455
esan+0.401
aeda+0.379
iners+0.376
ocument+0.370
Neg logit contributions
idav-0.370
ween-0.347
zeb-0.347
wave-0.341
abase-0.330
Token create
Token ID2251
Feature activation-3.83e+00

Pos logit contributions
idav+0.201
ween+0.188
zeb+0.188
wave+0.184
abase+0.179
Neg logit contributions
enthal-0.245
esan-0.216
aeda-0.204
iners-0.203
ocument-0.199
Token our
Token ID674
Feature activation+1.84e+00

Pos logit contributions
idav+2.109
zeb+2.000
ween+1.995
wave+1.967
 Faul+1.850
Neg logit contributions
enthal-3.722
esan-3.293
aeda-3.192
iners-3.149
ocument-3.134
Token own
Token ID898
Feature activation-2.25e-01

Pos logit contributions
enthal+1.509
esan+1.335
aeda+1.248
iners+1.243
ROR+1.210
Neg logit contributions
idav-1.324
ween-1.244
zeb-1.240
wave-1.217
abase-1.180
Token best
Token ID1266
Feature activation-1.00e+00

Pos logit contributions
idav+0.142
ween+0.132
zeb+0.132
wave+0.129
abase+0.125
Neg logit contributions
enthal-0.206
esan-0.183
aeda-0.174
iners-0.173
ocument-0.170
Token selling
Token ID6301
Feature activation-1.54e+01

Pos logit contributions
idav+0.777
ween+0.738
zeb+0.737
wave+0.726
abase+0.705
Neg logit contributions
enthal-0.759
esan-0.659
aeda-0.620
iners-0.613
ocument-0.605
Token Kindle
Token ID27114
Feature activation-9.35e+00

Pos logit contributions
idav+4.706
wave+4.292
zeb+4.266
 Faul+4.156
ween+3.968
Neg logit contributions
enthal-16.231
esan-15.027
iners-14.746
aeda-14.662
ROR-14.502
Token book
Token ID1492
Feature activation+1.51e+00

Pos logit contributions
idav+5.457
zeb+5.335
wave+5.329
ween+5.318
 Faul+5.025
Neg logit contributions
enthal-8.246
esan-7.314
aeda-7.191
ROR-6.985
iners-6.929
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
enthal+1.319
esan+1.166
aeda+1.097
iners+1.091
ROR+1.076
Neg logit contributions
idav-1.023
ween-0.950
zeb-0.946
wave-0.925
abase-0.906
Token We
Token ID775
Feature activation+3.78e+00

Pos logit contributions
idav+0.774
ween+0.733
zeb+0.729
wave+0.716
 Faul+0.690
Neg logit contributions
enthal-1.207
esan-1.074
aeda-1.030
iners-1.021
ocument-1.001
Token
Token ID447
Feature activation+1.30e+00

Pos logit contributions
enthal+3.586
esan+3.226
iners+3.055
aeda+3.047
ocument+3.045
Neg logit contributions
idav-2.166
zeb-2.052
ween-2.019
wave-1.965
abase-1.904
Token to
Token ID284
Feature activation-5.29e-01

Pos logit contributions
idav+1.056
ween+0.994
zeb+0.991
wave+0.978
abase+0.944
Neg logit contributions
enthal-1.311
esan-1.157
aeda-1.094
iners-1.081
ocument-1.063
Token promote
Token ID7719
Feature activation-2.46e+00

Pos logit contributions
idav+0.420
ween+0.398
zeb+0.397
wave+0.390
abase+0.381
Neg logit contributions
enthal-0.395
esan-0.342
aeda-0.320
iners-0.317
ocument-0.310
Token the
Token ID262
Feature activation-8.14e-01

Pos logit contributions
idav+1.760
ween+1.657
zeb+1.657
wave+1.631
abase+1.577
Neg logit contributions
enthal-2.026
esan-1.782
aeda-1.680
iners-1.656
ocument-1.639
Token accuracy
Token ID9922
Feature activation-6.94e-01

Pos logit contributions
idav+0.592
ween+0.557
zeb+0.556
wave+0.546
abase+0.532
Neg logit contributions
enthal-0.665
esan-0.582
aeda-0.549
iners-0.544
ocument-0.532
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
idav+0.482
zeb+0.450
ween+0.450
wave+0.441
abase+0.429
Neg logit contributions
enthal-0.592
esan-0.522
aeda-0.492
iners-0.489
ocument-0.479
Token fairness
Token ID22692
Feature activation-1.47e+01

Pos logit contributions
idav+0.849
ween+0.799
zeb+0.799
wave+0.784
abase+0.763
Neg logit contributions
enthal-0.933
esan-0.816
aeda-0.768
iners-0.762
ocument-0.746
Token,
Token ID11
Feature activation-4.53e+00

Pos logit contributions
idav+6.355
ween+5.996
wave+5.973
zeb+5.828
 Faul+5.696
Neg logit contributions
enthal-13.809
esan-12.532
aeda-12.454
ocument-12.261
ROR-11.914
Token and
Token ID290
Feature activation-1.85e+00

Pos logit contributions
idav+3.023
zeb+2.837
ween+2.834
wave+2.795
 Faul+2.691
Neg logit contributions
enthal-3.883
esan-3.448
aeda-3.256
iners-3.221
ocument-3.203
Token privacy
Token ID6782
Feature activation-7.41e+00

Pos logit contributions
idav+1.341
ween+1.261
zeb+1.260
wave+1.239
abase+1.202
Neg logit contributions
enthal-1.505
esan-1.319
aeda-1.243
iners-1.231
ocument-1.210
Token of
Token ID286
Feature activation-3.27e+00

Pos logit contributions
idav+4.270
ween+4.109
wave+4.056
zeb+4.021
 Faul+3.817
Neg logit contributions
enthal-6.769
esan-5.999
aeda-5.846
ocument-5.706
iners-5.705
Token consumer
Token ID7172
Feature activation-5.07e+00

Pos logit contributions
idav+2.339
ween+2.198
zeb+2.198
wave+2.176
 Faul+2.113
Neg logit contributions
enthal-2.680
esan-2.341
aeda-2.239
ocument-2.171
iners-2.162
Token Wall
Token ID5007
Feature activation-2.55e+00

Pos logit contributions
idav+0.107
zeb+0.101
ween+0.101
wave+0.099
abase+0.097
Neg logit contributions
enthal-0.114
esan-0.100
aeda-0.094
iners-0.093
ocument-0.091
Token Street
Token ID3530
Feature activation+8.11e-02

Pos logit contributions
idav+2.333
zeb+2.256
ween+2.253
wave+2.226
 Faul+2.169
Neg logit contributions
enthal-1.534
esan-1.299
aeda-1.208
ocument-1.198
iners-1.173
Token will
Token ID481
Feature activation+4.21e-01

Pos logit contributions
enthal+0.068
esan+0.060
aeda+0.056
iners+0.056
ocument+0.054
Neg logit contributions
idav-0.058
ween-0.054
zeb-0.054
wave-0.053
abase-0.052
Token continue
Token ID2555
Feature activation-2.55e-01

Pos logit contributions
enthal+0.330
esan+0.290
iners+0.271
aeda+0.271
ocument+0.263
Neg logit contributions
idav-0.318
ween-0.298
zeb-0.298
wave-0.291
abase-0.287
Token to
Token ID284
Feature activation-1.39e+00

Pos logit contributions
idav+0.185
zeb+0.173
ween+0.172
wave+0.170
abase+0.166
Neg logit contributions
enthal-0.209
esan-0.183
aeda-0.174
iners-0.172
ocument-0.169
Token wre
Token ID30154
Feature activation-1.43e+01

Pos logit contributions
idav+1.001
ween+0.941
zeb+0.940
wave+0.924
abase+0.897
Neg logit contributions
enthal-1.138
esan-0.998
aeda-0.941
iners-0.932
ocument-0.916
Tokenak
Token ID461
Feature activation-7.24e+00

Pos logit contributions
zeb+6.832
wave+6.595
idav+6.350
ween+6.182
pell+5.730
Neg logit contributions
enthal-12.940
esan-11.608
ocument-11.454
ROR-11.336
iners-11.324
Token havoc
Token ID29860
Feature activation-3.91e+00

Pos logit contributions
idav+4.272
zeb+4.243
ween+4.157
wave+4.106
 Faul+4.011
Neg logit contributions
enthal-6.458
esan-5.781
aeda-5.393
ocument-5.384
iners-5.348
Token on
Token ID319
Feature activation-2.37e+00

Pos logit contributions
idav+2.672
ween+2.542
zeb+2.534
wave+2.498
 Faul+2.398
Neg logit contributions
enthal-3.293
esan-2.903
aeda-2.761
iners-2.722
ROR-2.687
Token our
Token ID674
Feature activation+3.66e-01

Pos logit contributions
idav+1.640
ween+1.546
zeb+1.540
wave+1.515
abase+1.468
Neg logit contributions
enthal-2.013
esan-1.773
aeda-1.671
iners-1.653
ocument-1.633
Token economy
Token ID3773
Feature activation-4.98e+00

Pos logit contributions
enthal+0.296
esan+0.260
aeda+0.247
iners+0.245
ROR+0.238
Neg logit contributions
idav-0.268
zeb-0.251
ween-0.249
wave-0.245
abase-0.239
Token after
Token ID706
Feature activation+5.83e-01

Pos logit contributions
enthal+4.782
esan+4.155
iners+3.850
aeda+3.740
ocument+3.685
Neg logit contributions
idav-5.369
zeb-5.127
ween-5.003
wave-4.794
abase-4.779
Token dozens
Token ID9264
Feature activation+1.13e+00

Pos logit contributions
enthal+0.452
esan+0.394
aeda+0.369
iners+0.368
ocument+0.360
Neg logit contributions
idav-0.447
zeb-0.423
ween-0.420
wave-0.410
abase-0.402
Token of
Token ID286
Feature activation+1.63e+00

Pos logit contributions
enthal+0.936
esan+0.825
iners+0.773
aeda+0.771
ocument+0.760
Neg logit contributions
idav-0.806
ween-0.758
zeb-0.750
wave-0.730
abase-0.720
Token people
Token ID661
Feature activation+7.29e-01

Pos logit contributions
enthal+1.308
esan+1.144
iners+1.074
aeda+1.068
ROR+1.043
Neg logit contributions
idav-1.199
zeb-1.135
ween-1.124
wave-1.089
abase-1.072
Token began
Token ID2540
Feature activation+1.85e+00

Pos logit contributions
enthal+0.596
esan+0.523
iners+0.491
aeda+0.490
ocument+0.478
Neg logit contributions
idav-0.529
ween-0.498
zeb-0.498
wave-0.484
abase-0.473
Token sleeping
Token ID11029
Feature activation-1.43e+01

Pos logit contributions
enthal+1.455
esan+1.274
iners+1.203
aeda+1.189
ocument+1.168
Neg logit contributions
idav-1.388
zeb-1.311
ween-1.306
wave-1.267
abase-1.246
Token outside
Token ID2354
Feature activation-3.22e+00

Pos logit contributions
idav+7.693
wave+7.654
ween+7.333
zeb+7.129
abase+6.691
Neg logit contributions
enthal-12.773
esan-11.143
aeda-10.735
ocument-10.401
ROR-10.131
Token the
Token ID262
Feature activation-5.72e+00

Pos logit contributions
idav+2.147
ween+2.031
zeb+2.017
wave+2.010
 Faul+1.943
Neg logit contributions
enthal-2.781
esan-2.453
aeda-2.323
iners-2.288
ocument-2.268
Token premises
Token ID17095
Feature activation-9.62e-01

Pos logit contributions
idav+3.815
wave+3.633
ween+3.622
zeb+3.568
 Faul+3.497
Neg logit contributions
enthal-4.847
esan-4.287
aeda-4.109
ocument-4.017
iners-3.995
Token each
Token ID1123
Feature activation-6.40e-01

Pos logit contributions
idav+0.669
zeb+0.627
ween+0.627
wave+0.614
abase+0.596
Neg logit contributions
enthal-0.815
esan-0.718
aeda-0.678
iners-0.673
ocument-0.661
Token week
Token ID1285
Feature activation+3.13e-01

Pos logit contributions
idav+0.458
ween+0.430
zeb+0.429
wave+0.419
abase+0.411
Neg logit contributions
enthal-0.531
esan-0.466
aeda-0.437
iners-0.435
ocument-0.427
Token night
Token ID1755
Feature activation-2.52e+00

Pos logit contributions
idav+3.506
ween+3.364
zeb+3.344
wave+3.280
 Faul+3.191
Neg logit contributions
enthal-4.355
esan-3.835
aeda-3.692
ocument-3.588
iners-3.586
Token,
Token ID11
Feature activation-2.84e+00

Pos logit contributions
idav+1.661
ween+1.555
zeb+1.552
wave+1.529
abase+1.471
Neg logit contributions
enthal-2.218
esan-1.965
aeda-1.863
iners-1.845
ocument-1.819
Token but
Token ID475
Feature activation-1.08e+00

Pos logit contributions
idav+1.937
ween+1.826
zeb+1.821
wave+1.805
 Faul+1.742
Neg logit contributions
enthal-2.411
esan-2.124
aeda-2.014
iners-1.992
ocument-1.972
Token we
Token ID356
Feature activation+3.55e+00

Pos logit contributions
idav+0.782
ween+0.736
zeb+0.736
wave+0.723
abase+0.702
Neg logit contributions
enthal-0.882
esan-0.773
aeda-0.729
iners-0.722
ocument-0.710
Token all
Token ID477
Feature activation+1.76e+00

Pos logit contributions
enthal+2.787
esan+2.454
iners+2.307
aeda+2.247
ROR+2.161
Neg logit contributions
idav-2.687
ween-2.508
zeb-2.447
wave-2.433
abase-2.429
Token slept
Token ID21256
Feature activation-1.39e+01

Pos logit contributions
enthal+1.425
esan+1.248
iners+1.165
aeda+1.163
ocument+1.117
Neg logit contributions
idav-1.306
ween-1.217
zeb-1.202
wave-1.185
abase-1.170
Token well
Token ID880
Feature activation-7.35e+00

Pos logit contributions
idav+7.163
zeb+7.156
wave+7.148
ween+6.722
 Faul+6.499
Neg logit contributions
enthal-12.314
esan-11.252
ocument-10.733
aeda-10.687
ROR-10.423
Token after
Token ID706
Feature activation-4.92e+00

Pos logit contributions
idav+4.428
zeb+4.195
wave+4.168
ween+4.161
 Faul+3.998
Neg logit contributions
enthal-6.587
esan-5.873
aeda-5.684
ocument-5.571
ROR-5.571
Token a
Token ID257
Feature activation-4.61e+00

Pos logit contributions
idav+3.373
zeb+3.192
ween+3.188
wave+3.170
 Faul+3.052
Neg logit contributions
enthal-4.114
esan-3.644
aeda-3.462
iners-3.382
ocument-3.372
Token long
Token ID890
Feature activation-3.56e+00

Pos logit contributions
idav+3.064
zeb+2.890
ween+2.881
wave+2.880
 Faul+2.754
Neg logit contributions
enthal-3.979
esan-3.496
aeda-3.360
iners-3.308
ocument-3.268
Token day
Token ID1110
Feature activation-4.72e+00

Pos logit contributions
idav+2.473
ween+2.322
zeb+2.322
wave+2.316
 Faul+2.220
Neg logit contributions
enthal-2.993
esan-2.631
aeda-2.504
iners-2.467
ocument-2.448
Token thy
Token ID11906
Feature activation-5.17e+00

Pos logit contributions
idav+2.495
zeb+2.366
ween+2.359
wave+2.299
 Faul+2.239
Neg logit contributions
enthal-2.902
esan-2.536
aeda-2.411
iners-2.379
ocument-2.346
Token hands
Token ID2832
Feature activation-1.53e+00

Pos logit contributions
idav+3.660
zeb+3.496
ween+3.452
wave+3.404
 Faul+3.284
Neg logit contributions
enthal-4.264
esan-3.682
aeda-3.534
iners-3.432
ocument-3.415
Token,
Token ID11
Feature activation-2.37e+00

Pos logit contributions
idav+1.002
ween+0.936
zeb+0.935
wave+0.918
abase+0.888
Neg logit contributions
enthal-1.353
esan-1.199
aeda-1.135
iners-1.126
ocument-1.109
Token thou
Token ID14210
Feature activation-7.44e+00

Pos logit contributions
idav+1.624
ween+1.525
zeb+1.521
wave+1.496
 Faul+1.444
Neg logit contributions
enthal-2.017
esan-1.777
aeda-1.688
iners-1.662
ocument-1.640
Token shalt
Token ID36258
Feature activation-2.60e+00

Pos logit contributions
idav+4.868
zeb+4.791
wave+4.652
ween+4.545
 Faul+4.404
Neg logit contributions
enthal-6.298
esan-5.475
aeda-5.283
ocument-5.196
ROR-5.140
Token sm
Token ID895
Feature activation-1.39e+01

Pos logit contributions
idav+1.859
zeb+1.748
ween+1.744
wave+1.723
 Faul+1.657
Neg logit contributions
enthal-2.149
esan-1.873
aeda-1.778
iners-1.743
ROR-1.724
Tokenite
Token ID578
Feature activation-1.98e+00

Pos logit contributions
idav+7.425
wave+6.999
zeb+6.703
ween+6.429
abase+6.067
Neg logit contributions
enthal-12.083
ROR-11.454
esan-10.883
aeda-10.399
 Nou-10.073
Token every
Token ID790
Feature activation-4.60e+00

Pos logit contributions
idav+1.452
ween+1.372
zeb+1.371
wave+1.345
abase+1.306
Neg logit contributions
enthal-1.605
esan-1.402
aeda-1.322
iners-1.307
ocument-1.287
Token male
Token ID4257
Feature activation-7.66e+00

Pos logit contributions
idav+3.386
zeb+3.246
ween+3.220
wave+3.141
 Faul+3.053
Neg logit contributions
enthal-3.657
esan-3.166
aeda-3.032
iners-2.961
ocument-2.924
Token therein
Token ID27258
Feature activation-1.24e+00

Pos logit contributions
idav+5.239
ween+5.090
zeb+5.052
wave+4.877
 Faul+4.694
Neg logit contributions
enthal-6.284
esan-5.379
aeda-5.363
iners-5.181
ocument-5.128
Token with
Token ID351
Feature activation+4.70e-02

Pos logit contributions
idav+0.856
zeb+0.801
ween+0.800
wave+0.787
abase+0.763
Neg logit contributions
enthal-1.056
esan-0.932
aeda-0.879
iners-0.873
ocument-0.859
Token alert
Token ID7995
Feature activation+2.09e+00

Pos logit contributions
enthal+1.985
esan+1.735
aeda+1.620
iners+1.606
ROR+1.577
Neg logit contributions
idav-1.985
zeb-1.874
ween-1.867
wave-1.830
abase-1.796
Token.
Token ID13
Feature activation+2.37e+00

Pos logit contributions
enthal+1.736
esan+1.517
aeda+1.443
iners+1.434
ROR+1.397
Neg logit contributions
idav-1.479
ween-1.375
zeb-1.371
wave-1.324
abase-1.317
Token He
Token ID679
Feature activation-1.25e+00

Pos logit contributions
enthal+2.003
esan+1.758
aeda+1.654
iners+1.644
ROR+1.618
Neg logit contributions
idav-1.670
ween-1.546
zeb-1.528
wave-1.492
abase-1.488
Token doesn
Token ID1595
Feature activation-2.56e+00

Pos logit contributions
idav+0.865
zeb+0.813
ween+0.812
wave+0.799
abase+0.773
Neg logit contributions
enthal-1.056
esan-0.929
aeda-0.880
iners-0.870
ocument-0.858
Token't
Token ID470
Feature activation-1.81e+00

Pos logit contributions
idav+1.502
zeb+1.449
ween+1.437
wave+1.430
 Faul+1.332
Neg logit contributions
enthal-2.382
esan-2.122
aeda-2.052
ocument-2.002
iners-2.000
Token sleep
Token ID3993
Feature activation-1.38e+01

Pos logit contributions
idav+1.256
zeb+1.179
ween+1.178
wave+1.164
abase+1.120
Neg logit contributions
enthal-1.531
esan-1.346
aeda-1.277
iners-1.257
ocument-1.241
Token.
Token ID13
Feature activation+7.61e-01

Pos logit contributions
idav+7.446
wave+7.303
ween+7.012
zeb+6.822
 Faul+6.620
Neg logit contributions
enthal-12.221
esan-11.109
ocument-10.344
aeda-10.270
iners-10.042
Token He
Token ID679
Feature activation-1.85e+00

Pos logit contributions
enthal+0.674
esan+0.596
aeda+0.562
iners+0.559
ocument+0.551
Neg logit contributions
idav-0.504
ween-0.466
zeb-0.463
wave-0.452
abase-0.447
Token doesn
Token ID1595
Feature activation+1.84e+00

Pos logit contributions
idav+1.272
zeb+1.196
ween+1.195
wave+1.179
abase+1.134
Neg logit contributions
enthal-1.581
esan-1.393
aeda-1.322
iners-1.304
ocument-1.288
Token't
Token ID470
Feature activation-1.05e+00

Pos logit contributions
enthal+1.568
esan+1.381
iners+1.293
aeda+1.291
ROR+1.265
Neg logit contributions
idav-1.288
ween-1.191
zeb-1.187
wave-1.159
abase-1.147
Token need
Token ID761
Feature activation-1.02e+00

Pos logit contributions
idav+0.733
ween+0.687
zeb+0.687
wave+0.672
abase+0.654
Neg logit contributions
enthal-0.886
esan-0.780
aeda-0.736
iners-0.732
ocument-0.718
Token written
Token ID3194
Feature activation-1.06e+00

Pos logit contributions
idav+0.658
ween+0.615
zeb+0.615
wave+0.603
abase+0.583
Neg logit contributions
enthal-0.891
esan-0.790
aeda-0.748
iners-0.742
ocument-0.730
Token by
Token ID416
Feature activation-3.65e+00

Pos logit contributions
idav+0.743
zeb+0.696
ween+0.696
wave+0.683
abase+0.662
Neg logit contributions
enthal-0.896
esan-0.789
aeda-0.745
iners-0.738
ocument-0.726
Token the
Token ID262
Feature activation-4.45e+00

Pos logit contributions
idav+2.483
ween+2.343
zeb+2.338
wave+2.306
 Faul+2.244
Neg logit contributions
enthal-3.113
esan-2.736
aeda-2.606
iners-2.576
ocument-2.532
Token Icelandic
Token ID41959
Feature activation-7.31e+00

Pos logit contributions
idav+2.993
ween+2.836
zeb+2.817
wave+2.791
 Faul+2.718
Neg logit contributions
enthal-3.814
esan-3.339
aeda-3.198
iners-3.147
ROR-3.096
Token writer
Token ID6260
Feature activation-6.38e+00

Pos logit contributions
idav+4.969
ween+4.760
wave+4.745
zeb+4.742
 Faul+4.645
Neg logit contributions
enthal-6.002
esan-5.165
aeda-5.036
iners-4.900
ocument-4.848
Token S
Token ID311
Feature activation-1.37e+01

Pos logit contributions
idav+4.252
zeb+4.048
ween+4.009
wave+3.980
 Faul+3.900
Neg logit contributions
enthal-5.397
esan-4.714
aeda-4.555
iners-4.485
ROR-4.428
Tokenj
Token ID73
Feature activation-1.30e+01

Pos logit contributions
idav+8.955
ween+8.785
zeb+8.740
wave+8.428
abase+8.153
Neg logit contributions
enthal-10.460
esan-8.949
ROR-8.819
ocument-8.775
aeda-8.705
Tokenón
Token ID18840
Feature activation-8.80e+00

Pos logit contributions
idav+9.060
zeb+8.603
ween+8.577
wave+8.342
abase+8.098
Neg logit contributions
enthal-9.570
ROR-8.521
esan-8.347
iners-7.974
ocument-7.895
Token.
Token ID13
Feature activation-2.54e+00

Pos logit contributions
idav+6.145
zeb+5.896
ween+5.825
wave+5.741
 Faul+5.646
Neg logit contributions
enthal-6.937
esan-6.044
aeda-5.858
iners-5.756
ROR-5.726
Token
Token ID198
Feature activation-2.66e+00

Pos logit contributions
idav+1.695
ween+1.590
zeb+1.589
wave+1.561
abase+1.510
Neg logit contributions
enthal-2.212
esan-1.957
aeda-1.856
iners-1.838
ocument-1.806
Token
Token ID198
Feature activation-4.82e+00

Pos logit contributions
idav+1.666
zeb+1.602
ween+1.600
wave+1.595
 Faul+1.496
Neg logit contributions
enthal-2.372
esan-2.100
aeda-2.029
iners-1.982
ocument-1.980
Tokenicus
Token ID24552
Feature activation-2.05e+00

Pos logit contributions
idav+2.264
zeb+2.091
ween+2.090
wave+2.058
abase+1.976
Neg logit contributions
enthal-2.795
esan-2.449
aeda-2.345
iners-2.311
ROR-2.280
Token brief
Token ID4506
Feature activation-1.81e+00

Pos logit contributions
idav+1.584
ween+1.482
zeb+1.482
wave+1.465
abase+1.422
Neg logit contributions
enthal-1.586
esan-1.371
aeda-1.295
iners-1.281
ROR-1.252
Token calling
Token ID4585
Feature activation-6.25e+00

Pos logit contributions
idav+1.315
ween+1.235
zeb+1.233
wave+1.214
abase+1.177
Neg logit contributions
enthal-1.483
esan-1.299
aeda-1.225
iners-1.214
ocument-1.192
Token for
Token ID329
Feature activation-4.49e+00

Pos logit contributions
idav+4.100
ween+3.794
zeb+3.784
wave+3.730
 Faul+3.678
Neg logit contributions
enthal-5.329
esan-4.807
aeda-4.541
ocument-4.490
iners-4.476
Token the
Token ID262
Feature activation-3.97e+00

Pos logit contributions
idav+3.150
ween+2.943
zeb+2.940
wave+2.907
 Faul+2.835
Neg logit contributions
enthal-3.727
esan-3.288
aeda-3.102
iners-3.058
ocument-3.051
Token Court
Token ID3078
Feature activation-1.36e+01

Pos logit contributions
idav+2.760
ween+2.571
zeb+2.571
wave+2.525
 Faul+2.478
Neg logit contributions
enthal-3.326
esan-2.931
aeda-2.774
iners-2.751
ocument-2.725
Token to
Token ID284
Feature activation-1.36e+00

Pos logit contributions
idav+7.403
wave+6.644
zeb+6.611
 Faul+6.378
ween+6.363
Neg logit contributions
enthal-12.115
esan-10.505
ocument-10.413
aeda-10.383
ROR-10.360
Token take
Token ID1011
Feature activation-6.16e+00

Pos logit contributions
idav+1.010
ween+0.951
zeb+0.951
wave+0.935
abase+0.908
Neg logit contributions
enthal-1.081
esan-0.944
aeda-0.888
iners-0.880
ocument-0.864
Token the
Token ID262
Feature activation-4.55e+00

Pos logit contributions
idav+3.949
ween+3.667
wave+3.656
zeb+3.648
 Faul+3.574
Neg logit contributions
enthal-5.309
esan-4.708
aeda-4.538
ocument-4.487
ROR-4.464
Token case
Token ID1339
Feature activation-8.88e+00

Pos logit contributions
idav+2.924
ween+2.715
zeb+2.698
wave+2.662
 Faul+2.623
Neg logit contributions
enthal-3.985
esan-3.526
aeda-3.393
iners-3.376
ocument-3.354
Token.)
Token ID2014
Feature activation-1.47e+00

Pos logit contributions
idav+5.354
zeb+5.039
ween+5.021
wave+4.960
 Faul+4.824
Neg logit contributions
enthal-7.603
esan-6.735
ROR-6.542
ocument-6.534
aeda-6.523
TokenAll
Token ID3237
Feature activation+2.29e+00

Pos logit contributions
enthal+0.011
esan+0.010
iners+0.009
aeda+0.009
ROR+0.009
Neg logit contributions
idav-0.009
zeb-0.008
ween-0.008
wave-0.008
abase-0.008
Token advanced
Token ID6190
Feature activation+1.96e+00

Pos logit contributions
enthal+1.900
esan+1.678
iners+1.570
aeda+1.564
ocument+1.532
Neg logit contributions
idav-1.637
zeb-1.538
ween-1.530
wave-1.490
abase-1.449
Token metrics
Token ID20731
Feature activation-2.28e+00

Pos logit contributions
enthal+1.518
esan+1.309
iners+1.263
aeda+1.226
ocument+1.217
Neg logit contributions
idav-1.487
ween-1.403
zeb-1.380
wave-1.364
abase-1.342
Token courtesy
Token ID12537
Feature activation-8.02e-01

Pos logit contributions
idav+1.559
ween+1.470
zeb+1.467
wave+1.448
abase+1.405
Neg logit contributions
enthal-1.935
esan-1.711
aeda-1.618
iners-1.591
ocument-1.579
Token of
Token ID286
Feature activation-9.11e-01

Pos logit contributions
idav+0.559
ween+0.523
zeb+0.521
wave+0.512
abase+0.497
Neg logit contributions
enthal-0.679
esan-0.599
aeda-0.563
iners-0.560
ocument-0.552
Token Pro
Token ID1041
Feature activation-1.34e+01

Pos logit contributions
idav+0.672
ween+0.633
zeb+0.633
wave+0.622
abase+0.605
Neg logit contributions
enthal-0.732
esan-0.641
aeda-0.603
iners-0.597
ocument-0.587
Token Football
Token ID9957
Feature activation+5.10e+00

Pos logit contributions
zeb+6.470
wave+6.291
idav+6.200
ween+6.107
 Frontier+5.761
Neg logit contributions
enthal-12.587
esan-11.357
ROR-11.145
aeda-11.136
ocument-11.007
Token Focus
Token ID17061
Feature activation-2.95e+00

Pos logit contributions
enthal+3.256
esan+2.751
iners+2.567
aeda+2.490
ocument+2.456
Neg logit contributions
idav-4.566
zeb-4.299
ween-4.296
wave-4.193
abase-4.130
Token unless
Token ID4556
Feature activation+2.53e+00

Pos logit contributions
idav+1.900
ween+1.787
zeb+1.778
wave+1.745
abase+1.695
Neg logit contributions
enthal-2.609
esan-2.313
aeda-2.207
iners-2.170
ocument-2.153
Token otherwise
Token ID4306
Feature activation+4.52e+00

Pos logit contributions
enthal+1.814
esan+1.552
iners+1.445
aeda+1.430
ocument+1.411
Neg logit contributions
idav-2.086
zeb-1.990
ween-1.961
wave-1.930
abase-1.883
Token indicated
Token ID8203
Feature activation+1.81e+00

Pos logit contributions
enthal+2.644
esan+2.201
ocument+1.973
iners+1.963
aeda+1.930
Neg logit contributions
idav-4.249
ween-4.069
zeb-4.059
wave-3.994
abase-3.940
Token presided
Token ID45022
Feature activation-2.24e+00

Pos logit contributions
idav+1.484
ween+1.397
zeb+1.397
wave+1.371
 Faul+1.327
Neg logit contributions
enthal-1.834
esan-1.618
aeda-1.538
iners-1.523
ocument-1.498
Token over
Token ID625
Feature activation-2.31e+00

Pos logit contributions
idav+1.403
zeb+1.304
ween+1.301
wave+1.276
abase+1.236
Neg logit contributions
enthal-2.059
esan-1.832
aeda-1.735
iners-1.725
ocument-1.699
Token a
Token ID257
Feature activation-5.28e-01

Pos logit contributions
idav+1.660
ween+1.572
zeb+1.564
wave+1.541
abase+1.495
Neg logit contributions
enthal-1.893
esan-1.661
aeda-1.569
iners-1.551
ocument-1.528
Token soft
Token ID2705
Feature activation+5.37e+00

Pos logit contributions
idav+0.398
zeb+0.374
ween+0.374
wave+0.367
abase+0.357
Neg logit contributions
enthal-0.418
esan-0.365
aeda-0.342
iners-0.339
ocument-0.333
Token-
Token ID12
Feature activation-4.20e+00

Pos logit contributions
enthal+4.383
esan+3.769
iners+3.502
aeda+3.367
ocument+3.364
Neg logit contributions
idav-3.903
zeb-3.730
ween-3.609
abase-3.506
wave-3.447
Tokendr
Token ID7109
Feature activation-1.34e+01

Pos logit contributions
idav+2.805
ween+2.664
wave+2.636
zeb+2.629
abase+2.488
Neg logit contributions
enthal-3.591
esan-3.206
aeda-3.076
iners-2.982
ocument-2.970
Tokenink
Token ID676
Feature activation-2.36e+00

Pos logit contributions
ween+7.301
zeb+7.197
idav+7.094
abase+6.752
wave+6.488
Neg logit contributions
enthal-11.787
ROR-10.494
esan-10.237
aeda-9.930
ocument-9.873
Token bott
Token ID3005
Feature activation-1.16e+01

Pos logit contributions
idav+1.674
ween+1.578
zeb+1.577
wave+1.553
abase+1.502
Neg logit contributions
enthal-1.954
esan-1.716
aeda-1.623
iners-1.602
ocument-1.582
Tokenling
Token ID1359
Feature activation+8.30e-01

Pos logit contributions
idav+6.824
ween+6.734
zeb+6.660
abase+6.577
wave+6.559
Neg logit contributions
enthal-9.967
esan-8.813
aeda-8.723
ROR-8.651
ocument-8.275
Token company
Token ID1664
Feature activation-3.64e+00

Pos logit contributions
enthal+0.686
esan+0.604
aeda+0.569
iners+0.565
ocument+0.550
Neg logit contributions
idav-0.600
zeb-0.554
ween-0.553
wave-0.537
abase-0.527
Token that
Token ID326
Feature activation+4.54e-01

Pos logit contributions
idav+2.395
ween+2.272
zeb+2.259
wave+2.237
 Faul+2.156
Neg logit contributions
enthal-3.152
esan-2.783
aeda-2.676
iners-2.632
ROR-2.599
Token http
Token ID2638
Feature activation-1.03e+00

Pos logit contributions
enthal+3.490
esan+2.994
aeda+2.839
iners+2.769
ocument+2.756
Neg logit contributions
idav-3.723
zeb-3.579
ween-3.547
wave-3.518
abase-3.419
Token://
Token ID1378
Feature activation-3.52e+00

Pos logit contributions
idav+0.804
ween+0.764
zeb+0.763
wave+0.752
abase+0.729
Neg logit contributions
enthal-0.776
esan-0.671
aeda-0.631
iners-0.625
ocument-0.612
Tokenwww
Token ID2503
Feature activation-1.24e+00

Pos logit contributions
idav+2.796
ween+2.645
zeb+2.639
wave+2.598
abase+2.528
Neg logit contributions
enthal-2.628
esan-2.278
aeda-2.127
iners-2.104
ocument-2.073
Token.
Token ID13
Feature activation-5.92e+00

Pos logit contributions
idav+0.777
zeb+0.728
ween+0.728
wave+0.716
abase+0.684
Neg logit contributions
enthal-1.136
esan-1.011
aeda-0.964
iners-0.953
ocument-0.940
Tokened
Token ID276
Feature activation-1.61e+00

Pos logit contributions
idav+4.407
ween+4.147
zeb+4.109
wave+4.032
abase+3.911
Neg logit contributions
enthal-4.661
esan-4.080
ROR-3.803
aeda-3.800
iners-3.767
Tokenwards
Token ID2017
Feature activation-1.34e+01

Pos logit contributions
idav+0.828
ween+0.759
zeb+0.756
wave+0.738
abase+0.706
Neg logit contributions
enthal-1.655
esan-1.494
aeda-1.427
iners-1.415
ocument-1.397
Token.
Token ID13
Feature activation-2.06e+00

Pos logit contributions
idav+8.484
wave+7.944
zeb+7.931
ween+7.831
abase+7.726
Neg logit contributions
enthal-10.785
esan-9.562
ROR-9.255
aeda-8.779
iners-8.640
Tokenaf
Token ID1878
Feature activation-2.66e+00

Pos logit contributions
idav+1.290
ween+1.203
zeb+1.202
wave+1.176
abase+1.136
Neg logit contributions
enthal-1.884
esan-1.677
aeda-1.596
iners-1.580
ocument-1.554
Token.
Token ID13
Feature activation-4.86e-01

Pos logit contributions
idav+1.752
zeb+1.631
ween+1.626
wave+1.599
abase+1.544
Neg logit contributions
enthal-2.359
esan-2.092
aeda-1.970
iners-1.959
ROR-1.935
Tokenmil
Token ID25433
Feature activation-1.22e+00

Pos logit contributions
idav+0.240
ween+0.220
zeb+0.219
wave+0.214
 Faul+0.205
Neg logit contributions
enthal-0.506
esan-0.458
aeda-0.440
iners-0.437
ocument-0.429
Token/
Token ID14
Feature activation-2.43e+00

Pos logit contributions
idav+0.810
ween+0.758
zeb+0.758
wave+0.744
abase+0.719
Neg logit contributions
enthal-1.077
esan-0.953
aeda-0.903
iners-0.896
ocument-0.882
Token by
Token ID416
Feature activation-3.65e+00

Pos logit contributions
idav+0.743
zeb+0.696
ween+0.696
wave+0.683
abase+0.662
Neg logit contributions
enthal-0.896
esan-0.789
aeda-0.745
iners-0.738
ocument-0.726
Token the
Token ID262
Feature activation-4.45e+00

Pos logit contributions
idav+2.483
ween+2.343
zeb+2.338
wave+2.306
 Faul+2.244
Neg logit contributions
enthal-3.113
esan-2.736
aeda-2.606
iners-2.576
ocument-2.532
Token Icelandic
Token ID41959
Feature activation-7.31e+00

Pos logit contributions
idav+2.993
ween+2.836
zeb+2.817
wave+2.791
 Faul+2.718
Neg logit contributions
enthal-3.814
esan-3.339
aeda-3.198
iners-3.147
ROR-3.096
Token writer
Token ID6260
Feature activation-6.38e+00

Pos logit contributions
idav+4.969
ween+4.760
wave+4.745
zeb+4.742
 Faul+4.645
Neg logit contributions
enthal-6.002
esan-5.165
aeda-5.036
iners-4.900
ocument-4.848
Token S
Token ID311
Feature activation-1.37e+01

Pos logit contributions
idav+4.252
zeb+4.048
ween+4.009
wave+3.980
 Faul+3.900
Neg logit contributions
enthal-5.397
esan-4.714
aeda-4.555
iners-4.485
ROR-4.428
Tokenj
Token ID73
Feature activation-1.30e+01

Pos logit contributions
idav+8.955
ween+8.785
zeb+8.740
wave+8.428
abase+8.153
Neg logit contributions
enthal-10.460
esan-8.949
ROR-8.819
ocument-8.775
aeda-8.705
Tokenón
Token ID18840
Feature activation-8.80e+00

Pos logit contributions
idav+9.060
zeb+8.603
ween+8.577
wave+8.342
abase+8.098
Neg logit contributions
enthal-9.570
ROR-8.521
esan-8.347
iners-7.974
ocument-7.895
Token.
Token ID13
Feature activation-2.54e+00

Pos logit contributions
idav+6.145
zeb+5.896
ween+5.825
wave+5.741
 Faul+5.646
Neg logit contributions
enthal-6.937
esan-6.044
aeda-5.858
iners-5.756
ROR-5.726
Token
Token ID198
Feature activation-2.66e+00

Pos logit contributions
idav+1.695
ween+1.590
zeb+1.589
wave+1.561
abase+1.510
Neg logit contributions
enthal-2.212
esan-1.957
aeda-1.856
iners-1.838
ocument-1.806
Token
Token ID198
Feature activation-4.82e+00

Pos logit contributions
idav+1.666
zeb+1.602
ween+1.600
wave+1.595
 Faul+1.496
Neg logit contributions
enthal-2.372
esan-2.100
aeda-2.029
iners-1.982
ocument-1.980
TokenH
Token ID39
Feature activation+2.40e+00

Pos logit contributions
idav+3.172
ween+3.011
zeb+2.982
wave+2.977
abase+2.828
Neg logit contributions
enthal-4.201
esan-3.703
aeda-3.530
iners-3.467
ocument-3.408
Token_
Token ID62
Feature activation-1.65e+00

Pos logit contributions
idav+1.641
zeb+1.569
ween+1.568
wave+1.556
abase+1.461
Neg logit contributions
enthal-2.193
esan-1.946
aeda-1.872
iners-1.836
ocument-1.824
Tokenstate
Token ID5219
Feature activation-4.05e+00

Pos logit contributions
idav+1.242
ween+1.185
zeb+1.183
wave+1.174
abase+1.126
Neg logit contributions
enthal-1.281
esan-1.119
aeda-1.058
iners-1.043
ocument-1.026
Token :
Token ID1058
Feature activation+7.82e+00

Pos logit contributions
idav+2.228
zeb+2.160
wave+2.138
ween+2.131
 Faul+1.969
Neg logit contributions
enthal-3.852
esan-3.447
aeda-3.338
iners-3.290
ocument-3.248
Token Arc
Token ID10173
Feature activation-8.10e+00

Pos logit contributions
enthal+4.058
esan+3.264
iners+2.917
ocument+2.844
ROR+2.791
Neg logit contributions
idav-7.714
ween-7.278
wave-7.182
zeb-7.180
abase-7.026
Token ::
Token ID7904
Feature activation-2.06e-01

Pos logit contributions
idav+5.208
ween+4.893
zeb+4.882
wave+4.776
abase+4.667
Neg logit contributions
enthal-6.981
esan-6.119
aeda-5.967
iners-5.805
ROR-5.722
Token clone
Token ID17271
Feature activation-1.28e+01

Pos logit contributions
idav+0.150
ween+0.141
zeb+0.141
wave+0.138
abase+0.134
Neg logit contributions
enthal-0.167
esan-0.147
aeda-0.138
iners-0.137
ocument-0.135
Token (
Token ID357
Feature activation+5.14e+00

Pos logit contributions
idav+7.141
zeb+6.847
wave+6.816
ween+6.722
abase+6.524
Neg logit contributions
enthal-11.073
esan-9.688
aeda-9.677
iners-9.498
ocument-9.365
Token self
Token ID2116
Feature activation-4.37e+00

Pos logit contributions
enthal+3.645
esan+3.145
iners+2.889
aeda+2.857
ocument+2.813
Neg logit contributions
idav-4.211
zeb-3.932
ween-3.896
 Faul-3.860
wave-3.816
Token.
Token ID764
Feature activation+6.04e+00

Pos logit contributions
idav+2.237
zeb+2.072
ween+2.066
wave+2.014
abase+1.931
Neg logit contributions
enthal-4.444
esan-4.005
aeda-3.845
iners-3.796
ocument-3.750
Tokenprev
Token ID47050
Feature activation-3.76e+00

Pos logit contributions
enthal+4.793
esan+4.243
iners+3.975
aeda+3.872
ocument+3.837
Neg logit contributions
idav-4.370
 Faul-4.038
zeb-4.023
ween-3.974
wave-3.871
Token_
Token ID62
Feature activation-2.84e-01

Pos logit contributions
idav+2.555
ween+2.412
zeb+2.399
wave+2.372
abase+2.285
Neg logit contributions
enthal-3.200
esan-2.834
aeda-2.692
iners-2.658
ocument-2.624
Token did
Token ID750
Feature activation-1.05e+00

Pos logit contributions
idav+0.106
ween+0.099
zeb+0.099
wave+0.098
abase+0.095
Neg logit contributions
enthal-0.126
esan-0.111
aeda-0.104
iners-0.103
ocument-0.102
Token receive
Token ID3328
Feature activation-6.77e-01

Pos logit contributions
idav+0.754
ween+0.709
zeb+0.709
wave+0.696
abase+0.676
Neg logit contributions
enthal-0.860
esan-0.754
aeda-0.711
iners-0.705
ocument-0.693
Token a
Token ID257
Feature activation-1.26e+00

Pos logit contributions
idav+0.489
ween+0.460
zeb+0.459
wave+0.451
abase+0.438
Neg logit contributions
enthal-0.555
esan-0.486
aeda-0.458
iners-0.454
ocument-0.446
Token last
Token ID938
Feature activation-1.91e+00

Pos logit contributions
idav+0.883
ween+0.829
zeb+0.829
wave+0.814
abase+0.789
Neg logit contributions
enthal-1.056
esan-0.929
aeda-0.877
iners-0.869
ocument-0.855
Token name
Token ID1438
Feature activation+2.03e+00

Pos logit contributions
idav+1.197
zeb+1.116
ween+1.114
wave+1.097
abase+1.053
Neg logit contributions
enthal-1.742
esan-1.550
aeda-1.478
iners-1.461
ocument-1.440
Token Sur
Token ID4198
Feature activation-1.27e+01

Pos logit contributions
enthal+1.701
esan+1.493
aeda+1.398
iners+1.396
ocument+1.368
Neg logit contributions
idav-1.433
ween-1.358
zeb-1.347
wave-1.311
abase-1.280
Tokenley
Token ID1636
Feature activation-4.40e+00

Pos logit contributions
idav+9.480
ween+9.162
zeb+9.042
wave+8.862
abase+8.597
Neg logit contributions
enthal-8.814
esan-7.485
aeda-7.281
ROR-7.221
iners-7.142
Token,
Token ID11
Feature activation-9.11e-01

Pos logit contributions
idav+3.018
zeb+2.844
ween+2.841
wave+2.793
 Faul+2.727
Neg logit contributions
enthal-3.688
esan-3.270
aeda-3.099
iners-3.082
ocument-3.029
Token a
Token ID257
Feature activation-7.06e-01

Pos logit contributions
idav+0.645
ween+0.606
zeb+0.605
wave+0.595
abase+0.577
Neg logit contributions
enthal-0.759
esan-0.667
aeda-0.630
iners-0.624
ocument-0.614
Token date
Token ID3128
Feature activation-2.56e+00

Pos logit contributions
idav+0.528
ween+0.497
zeb+0.497
wave+0.488
abase+0.475
Neg logit contributions
enthal-0.562
esan-0.491
aeda-0.461
iners-0.456
ocument-0.448
Token of
Token ID286
Feature activation-6.04e-01

Pos logit contributions
idav+1.785
ween+1.679
zeb+1.670
wave+1.651
abase+1.596
Neg logit contributions
enthal-2.162
esan-1.899
aeda-1.808
iners-1.783
ocument-1.755
Token ingestion
Token ID38382
Feature activation+1.42e+00

Pos logit contributions
enthal+0.999
esan+0.876
iners+0.825
aeda+0.818
ocument+0.794
Neg logit contributions
idav-0.977
zeb-0.913
ween-0.905
wave-0.892
abase-0.872
Token".
Token ID1911
Feature activation+1.37e+00

Pos logit contributions
enthal+1.184
esan+1.039
aeda+0.978
iners+0.977
ocument+0.950
Neg logit contributions
idav-1.016
zeb-0.938
ween-0.937
wave-0.914
abase-0.897
Token
Token ID198
Feature activation-1.72e+00

Pos logit contributions
enthal+1.110
esan+0.970
aeda+0.913
iners+0.907
ROR+0.882
Neg logit contributions
idav-1.014
ween-0.951
zeb-0.948
wave-0.927
abase-0.908
Token
Token ID198
Feature activation-7.50e-02

Pos logit contributions
idav+1.098
zeb+1.055
ween+1.053
wave+1.046
 Faul+0.983
Neg logit contributions
enthal-1.524
esan-1.346
aeda-1.300
iners-1.270
ocument-1.269
Token'
Token ID6
Feature activation+3.30e-01

Pos logit contributions
idav+0.053
ween+0.050
zeb+0.050
wave+0.049
abase+0.048
Neg logit contributions
enthal-0.062
esan-0.055
aeda-0.052
iners-0.051
ROR-0.050
TokenSm
Token ID7556
Feature activation-1.27e+01

Pos logit contributions
enthal+0.282
esan+0.248
aeda+0.233
iners+0.233
ROR+0.229
Neg logit contributions
idav-0.228
zeb-0.213
ween-0.212
wave-0.207
abase-0.204
Tokenalls
Token ID5691
Feature activation-1.92e+00

Pos logit contributions
idav+8.069
wave+7.498
ween+7.481
zeb+7.266
abase+6.935
Neg logit contributions
enthal-10.069
esan-9.348
ROR-8.795
aeda-8.673
ocument-8.427
Token things
Token ID1243
Feature activation+1.46e+00

Pos logit contributions
idav+1.391
ween+1.312
zeb+1.310
wave+1.290
abase+1.249
Neg logit contributions
enthal-1.565
esan-1.375
aeda-1.295
iners-1.281
ocument-1.261
Token you
Token ID345
Feature activation-4.30e+00

Pos logit contributions
enthal+1.123
esan+0.969
iners+0.911
aeda+0.908
ROR+0.885
Neg logit contributions
idav-1.135
zeb-1.061
ween-1.056
wave-1.034
abase-1.017
Token can
Token ID460
Feature activation-6.52e+00

Pos logit contributions
idav+2.919
wave+2.768
zeb+2.767
ween+2.765
 Faul+2.645
Neg logit contributions
enthal-3.629
esan-3.204
aeda-3.067
ocument-2.979
ROR-2.935
Token do
Token ID466
Feature activation+4.10e+00

Pos logit contributions
idav+4.058
wave+3.863
ween+3.855
zeb+3.788
 Faul+3.590
Neg logit contributions
enthal-5.817
esan-5.171
aeda-5.036
ocument-4.804
ROR-4.746
Token,
Token ID837
Feature activation+3.32e+00

Pos logit contributions
idav+5.411
ween+5.142
zeb+5.119
wave+5.100
abase+4.772
Neg logit contributions
enthal-7.057
esan-6.313
aeda-5.995
iners-5.899
ocument-5.887
Token check
Token ID2198
Feature activation-7.37e+00

Pos logit contributions
enthal+2.797
esan+2.483
iners+2.334
aeda+2.290
ROR+2.248
Neg logit contributions
idav-2.313
zeb-2.138
ween-2.135
wave-2.085
abase-2.031
Token :
Token ID1058
Feature activation+4.36e+00

Pos logit contributions
idav+3.880
zeb+3.741
ween+3.727
wave+3.725
 Faul+3.425
Neg logit contributions
enthal-6.995
esan-6.318
aeda-6.181
ocument-6.044
iners-6.003
Token self
Token ID2116
Feature activation-3.66e+00

Pos logit contributions
enthal+2.763
esan+2.304
iners+2.113
ocument+2.073
aeda+2.069
Neg logit contributions
idav-3.935
ween-3.699
zeb-3.676
wave-3.626
abase-3.573
Token.
Token ID764
Feature activation-1.63e+00

Pos logit contributions
idav+1.737
zeb+1.594
ween+1.583
wave+1.542
abase+1.469
Neg logit contributions
enthal-3.875
esan-3.510
aeda-3.366
iners-3.332
ocument-3.297
Tokencheck
Token ID9122
Feature activation-1.26e+01

Pos logit contributions
idav+1.089
ween+1.016
zeb+1.015
wave+0.995
abase+0.964
Neg logit contributions
enthal-1.431
esan-1.266
aeda-1.195
iners-1.189
ocument-1.169
Token,
Token ID837
Feature activation+4.32e+00

Pos logit contributions
idav+7.063
wave+6.688
zeb+6.595
ween+6.564
abase+6.237
Neg logit contributions
enthal-11.012
esan-9.894
aeda-9.636
ocument-9.413
ROR-9.314
Token prev
Token ID8654
Feature activation-2.52e+00

Pos logit contributions
enthal+3.702
esan+3.293
iners+3.099
aeda+3.018
ROR+2.974
Neg logit contributions
idav-2.934
zeb-2.710
ween-2.701
wave-2.630
abase-2.573
Token_
Token ID62
Feature activation-1.65e+00

Pos logit contributions
idav+1.641
zeb+1.569
ween+1.568
wave+1.556
abase+1.461
Neg logit contributions
enthal-2.193
esan-1.946
aeda-1.872
iners-1.836
ocument-1.824
Tokenstate
Token ID5219
Feature activation-4.05e+00

Pos logit contributions
idav+1.242
ween+1.185
zeb+1.183
wave+1.174
abase+1.126
Neg logit contributions
enthal-1.281
esan-1.119
aeda-1.058
iners-1.043
ocument-1.026
Token :
Token ID1058
Feature activation+7.82e+00

Pos logit contributions
idav+2.228
zeb+2.160
wave+2.138
ween+2.131
 Faul+1.969
Neg logit contributions
enthal-3.852
esan-3.447
aeda-3.338
iners-3.290
ocument-3.248
Token government
Token ID1230
Feature activation-2.80e+00

Pos logit contributions
idav+0.718
zeb+0.675
ween+0.674
wave+0.657
abase+0.641
Neg logit contributions
enthal-0.825
esan-0.727
aeda-0.684
iners-0.679
ocument-0.664
Token and
Token ID290
Feature activation-4.96e+00

Pos logit contributions
idav+1.893
ween+1.780
zeb+1.776
wave+1.750
abase+1.692
Neg logit contributions
enthal-2.415
esan-2.126
aeda-2.020
iners-1.998
ocument-1.966
Token its
Token ID663
Feature activation-5.28e+00

Pos logit contributions
idav+3.373
ween+3.241
wave+3.210
zeb+3.197
 Faul+3.107
Neg logit contributions
enthal-4.196
esan-3.661
aeda-3.498
ocument-3.409
iners-3.393
Token leader
Token ID3554
Feature activation+2.21e-01

Pos logit contributions
idav+3.278
ween+3.114
wave+3.091
zeb+3.074
 Faul+2.948
Neg logit contributions
enthal-4.791
esan-4.207
aeda-4.022
ocument-3.981
iners-3.957
Token becomes
Token ID4329
Feature activation-1.18e+00

Pos logit contributions
enthal+0.185
esan+0.163
iners+0.153
aeda+0.152
ocument+0.150
Neg logit contributions
idav-0.157
zeb-0.146
ween-0.146
wave-0.143
abase-0.139
Token Prime
Token ID5537
Feature activation-1.25e+01

Pos logit contributions
idav+0.796
ween+0.743
zeb+0.742
wave+0.726
abase+0.707
Neg logit contributions
enthal-1.025
esan-0.906
aeda-0.854
iners-0.851
ocument-0.837
Token Minister
Token ID4139
Feature activation-4.53e+00

Pos logit contributions
idav+2.232
wave+2.126
zeb+2.001
ween+1.983
 Abbott+1.971
Neg logit contributions
enthal-15.481
esan-14.349
aeda-14.312
ROR-14.249
iners-13.695
Token.
Token ID13
Feature activation-2.12e+00

Pos logit contributions
idav+2.920
ween+2.767
zeb+2.740
wave+2.720
abase+2.621
Neg logit contributions
enthal-3.980
esan-3.526
aeda-3.361
iners-3.318
ROR-3.268
Token In
Token ID554
Feature activation-3.42e+00

Pos logit contributions
idav+1.386
ween+1.299
zeb+1.295
wave+1.275
abase+1.228
Neg logit contributions
enthal-1.884
esan-1.668
aeda-1.583
iners-1.567
ocument-1.544
Token cases
Token ID2663
Feature activation-3.68e+00

Pos logit contributions
idav+2.410
ween+2.279
zeb+2.254
wave+2.245
abase+2.158
Neg logit contributions
enthal-2.854
esan-2.512
aeda-2.372
iners-2.339
ocument-2.315
Token where
Token ID810
Feature activation-5.50e+00

Pos logit contributions
idav+2.562
ween+2.449
zeb+2.407
wave+2.392
 Faul+2.305
Neg logit contributions
enthal-3.078
esan-2.681
aeda-2.555
iners-2.524
ocument-2.485
TokenWe
Token ID1135
Feature activation+5.07e+00

Pos logit contributions
enthal+2.157
esan+1.893
iners+1.790
aeda+1.777
ROR+1.773
Neg logit contributions
idav-1.834
zeb-1.705
ween-1.703
wave-1.671
abase-1.647
Token're
Token ID821
Feature activation+4.60e+00

Pos logit contributions
enthal+3.774
esan+3.325
iners+3.152
aeda+3.023
ocument+2.961
Neg logit contributions
idav-3.972
ween-3.739
zeb-3.663
wave-3.589
abase-3.553
Token hoping
Token ID7725
Feature activation+4.13e-01

Pos logit contributions
enthal+3.353
esan+2.911
iners+2.750
aeda+2.662
ocument+2.620
Neg logit contributions
idav-3.701
ween-3.431
zeb-3.409
wave-3.321
abase-3.249
Token that
Token ID326
Feature activation+5.43e-01

Pos logit contributions
enthal+0.337
esan+0.295
aeda+0.278
iners+0.277
ocument+0.270
Neg logit contributions
idav-0.299
zeb-0.281
ween-0.281
wave-0.276
abase-0.268
Token he
Token ID339
Feature activation-4.23e-01

Pos logit contributions
enthal+0.440
esan+0.385
aeda+0.362
iners+0.361
ocument+0.352
Neg logit contributions
idav-0.398
zeb-0.374
ween-0.373
wave-0.367
abase-0.357
Token sur
Token ID969
Feature activation-1.25e+01

Pos logit contributions
idav+0.301
ween+0.283
zeb+0.282
wave+0.277
abase+0.269
Neg logit contributions
enthal-0.351
esan-0.309
aeda-0.290
iners-0.289
ocument-0.283
Tokenrend
Token ID10920
Feature activation+1.25e+00

Pos logit contributions
idav+5.443
ween+5.285
wave+5.202
zeb+4.836
pell+4.619
Neg logit contributions
enthal-12.428
esan-10.909
ROR-10.552
aeda-10.500
iners-10.422
Tokeners
Token ID364
Feature activation-5.82e-01

Pos logit contributions
enthal+0.871
esan+0.746
aeda+0.697
iners+0.685
ocument+0.673
Neg logit contributions
idav-1.049
zeb-0.995
ween-0.993
wave-0.982
abase-0.951
Token,"
Token ID553
Feature activation-1.29e+00

Pos logit contributions
idav+0.404
ween+0.379
zeb+0.379
wave+0.371
abase+0.361
Neg logit contributions
enthal-0.493
esan-0.434
aeda-0.410
iners-0.407
ocument-0.400
Token the
Token ID262
Feature activation-4.88e+00

Pos logit contributions
idav+0.920
ween+0.865
zeb+0.864
wave+0.850
abase+0.825
Neg logit contributions
enthal-1.070
esan-0.938
aeda-0.884
iners-0.877
ocument-0.861
Token police
Token ID1644
Feature activation-5.65e+00

Pos logit contributions
idav+3.707
zeb+3.481
ween+3.468
wave+3.428
 Faul+3.355
Neg logit contributions
enthal-3.779
esan-3.303
aeda-3.131
iners-3.089
ocument-3.074
Token through
Token ID832
Feature activation-1.74e+00

Pos logit contributions
enthal+0.169
esan+0.149
aeda+0.140
iners+0.139
ocument+0.136
Neg logit contributions
idav-0.144
zeb-0.134
ween-0.134
wave-0.131
abase-0.128
Token the
Token ID262
Feature activation-6.01e-01

Pos logit contributions
idav+1.263
ween+1.193
zeb+1.188
wave+1.170
abase+1.133
Neg logit contributions
enthal-1.424
esan-1.248
aeda-1.178
iners-1.165
ocument-1.148
Token use
Token ID779
Feature activation+3.81e-01

Pos logit contributions
idav+0.444
zeb+0.417
ween+0.417
wave+0.410
abase+0.399
Neg logit contributions
enthal-0.483
esan-0.422
aeda-0.397
iners-0.394
ocument-0.386
Token of
Token ID286
Feature activation+5.36e-01

Pos logit contributions
enthal+0.326
esan+0.288
aeda+0.272
iners+0.269
ocument+0.265
Neg logit contributions
idav-0.262
ween-0.245
zeb-0.245
wave-0.240
abase-0.233
Token the
Token ID262
Feature activation+1.87e+00

Pos logit contributions
enthal+0.434
esan+0.379
aeda+0.357
iners+0.355
ocument+0.346
Neg logit contributions
idav-0.394
zeb-0.370
ween-0.367
wave-0.361
abase-0.354
Token UL
Token ID44475
Feature activation+8.47e+00

Pos logit contributions
enthal+1.519
esan+1.324
aeda+1.245
iners+1.240
ocument+1.205
Neg logit contributions
idav-1.371
zeb-1.285
ween-1.269
wave-1.249
abase-1.234
TokenMB
Token ID10744
Feature activation-5.59e-02

Pos logit contributions
enthal+6.992
iners+5.649
esan+5.645
aeda+5.543
ROR+5.520
Neg logit contributions
idav-5.843
zeb-5.424
abase-5.392
ween-5.366
wave-5.173
Token stro
Token ID9660
Feature activation+1.64e+00

Pos logit contributions
idav+0.040
zeb+0.038
ween+0.037
wave+0.037
abase+0.036
Neg logit contributions
enthal-0.046
esan-0.041
aeda-0.038
iners-0.038
ocument-0.037
Tokenbed
Token ID3077
Feature activation-9.79e-01

Pos logit contributions
enthal+1.032
esan+0.856
aeda+0.787
iners+0.782
ocument+0.763
Neg logit contributions
idav-1.497
zeb-1.418
ween-1.414
wave-1.389
abase-1.378
Token back
Token ID736
Feature activation+4.08e+00

Pos logit contributions
idav+0.722
ween+0.680
zeb+0.679
wave+0.669
abase+0.649
Neg logit contributions
enthal-0.788
esan-0.689
aeda-0.649
iners-0.643
ocument-0.632
Tokenlight
Token ID2971
Feature activation+4.65e+00

Pos logit contributions
enthal+2.773
esan+2.294
iners+2.174
aeda+2.137
ROR+2.060
Neg logit contributions
idav-3.522
zeb-3.335
ween-3.257
abase-3.251
 Faul-3.196
Token player
Token ID2137
Feature activation-3.55e+00

Pos logit contributions
idav+2.350
zeb+2.246
ween+2.243
wave+2.232
 Faul+2.160
Neg logit contributions
enthal-2.895
esan-2.534
aeda-2.427
iners-2.379
ocument-2.356
Token in
Token ID287
Feature activation+1.14e+00

Pos logit contributions
idav+2.311
ween+2.196
zeb+2.190
wave+2.160
abase+2.088
Neg logit contributions
enthal-3.109
esan-2.750
aeda-2.637
iners-2.569
ROR-2.558
Token MLS
Token ID13981
Feature activation+1.57e-01

Pos logit contributions
enthal+0.886
esan+0.770
iners+0.723
aeda+0.720
ocument+0.703
Neg logit contributions
idav-0.877
zeb-0.819
ween-0.814
wave-0.800
abase-0.778
Token.
Token ID13
Feature activation+2.47e+00

Pos logit contributions
enthal+0.132
esan+0.117
aeda+0.110
iners+0.109
ocument+0.107
Neg logit contributions
idav-0.110
zeb-0.102
ween-0.102
wave-0.100
abase-0.097
Token
Token ID198
Feature activation+4.49e+00

Pos logit contributions
enthal+2.018
esan+1.752
iners+1.638
aeda+1.638
ocument+1.601
Neg logit contributions
idav-1.836
zeb-1.691
ween-1.689
wave-1.653
abase-1.625
Token
Token ID198
Feature activation+8.01e+00

Pos logit contributions
enthal+3.334
esan+2.907
iners+2.675
ROR+2.622
aeda+2.615
Neg logit contributions
idav-3.611
ween-3.295
zeb-3.287
abase-3.254
wave-3.179
TokenHe
Token ID1544
Feature activation-8.07e-01

Pos logit contributions
enthal+5.915
esan+5.148
ROR+4.959
iners+4.916
ocument+4.685
Neg logit contributions
idav-6.085
zeb-5.557
abase-5.541
ween-5.498
 Faul-5.479
Token came
Token ID1625
Feature activation-2.71e+00

Pos logit contributions
idav+0.574
ween+0.539
zeb+0.538
wave+0.529
abase+0.513
Neg logit contributions
enthal-0.671
esan-0.590
aeda-0.556
iners-0.552
ocument-0.542
Token out
Token ID503
Feature activation+6.65e-01

Pos logit contributions
idav+1.852
zeb+1.763
ween+1.751
wave+1.729
 Faul+1.669
Neg logit contributions
enthal-2.298
esan-2.030
aeda-1.913
iners-1.889
ocument-1.861
Token of
Token ID286
Feature activation-4.46e+00

Pos logit contributions
enthal+0.548
esan+0.481
aeda+0.454
iners+0.451
ocument+0.443
Neg logit contributions
idav-0.480
zeb-0.449
ween-0.446
wave-0.434
abase-0.428
Token retirement
Token ID10737
Feature activation+2.08e+00

Pos logit contributions
idav+3.114
ween+3.036
zeb+2.988
wave+2.959
 Faul+2.906
Neg logit contributions
enthal-3.606
esan-3.184
aeda-3.042
iners-2.939
ocument-2.935
TokenRoll
Token ID26869
Feature activation+6.65e-01

Pos logit contributions
idav+0.613
zeb+0.575
ween+0.575
wave+0.564
abase+0.549
Neg logit contributions
enthal-0.740
esan-0.652
aeda-0.614
iners-0.611
ocument-0.600
Tokens
Token ID82
Feature activation-1.50e+00

Pos logit contributions
enthal+0.604
esan+0.537
aeda+0.512
iners+0.505
ocument+0.500
Neg logit contributions
idav-0.420
ween-0.392
zeb-0.391
wave-0.385
abase-0.370
Token-
Token ID12
Feature activation-6.89e+00

Pos logit contributions
idav+0.947
ween+0.885
zeb+0.882
wave+0.876
abase+0.839
Neg logit contributions
enthal-1.349
esan-1.202
aeda-1.149
iners-1.134
ocument-1.127
TokenRoy
Token ID32027
Feature activation+2.30e+00

Pos logit contributions
wave+3.818
idav+3.807
ween+3.748
zeb+3.620
abase+3.434
Neg logit contributions
enthal-6.311
esan-5.692
aeda-5.550
ocument-5.458
iners-5.392
Tokence
Token ID344
Feature activation-4.30e+00

Pos logit contributions
enthal+2.478
esan+2.249
aeda+2.141
iners+2.124
ocument+2.085
Neg logit contributions
idav-1.079
ween-0.977
zeb-0.962
wave-0.940
 Faul-0.906
Token says
Token ID1139
Feature activation+6.69e+00

Pos logit contributions
idav+2.978
zeb+2.784
wave+2.783
ween+2.783
 Faul+2.699
Neg logit contributions
enthal-3.580
esan-3.144
aeda-2.987
ocument-2.935
iners-2.918
Token it
Token ID340
Feature activation+3.19e+00

Pos logit contributions
enthal+4.745
esan+4.056
iners+3.800
aeda+3.672
ocument+3.646
Neg logit contributions
idav-5.402
zeb-5.127
ween-5.008
wave-4.936
abase-4.866
Token has
Token ID468
Feature activation+4.64e+00

Pos logit contributions
enthal+2.481
esan+2.183
iners+2.045
aeda+2.023
ocument+1.965
Neg logit contributions
idav-2.442
ween-2.263
zeb-2.252
wave-2.191
abase-2.157
Token completed
Token ID5668
Feature activation+3.36e+00

Pos logit contributions
enthal+3.455
esan+3.017
iners+2.853
aeda+2.783
ocument+2.737
Neg logit contributions
idav-3.632
ween-3.411
zeb-3.391
wave-3.300
abase-3.225
Token a
Token ID257
Feature activation+2.41e+00

Pos logit contributions
enthal+2.564
esan+2.218
iners+2.096
aeda+2.042
ocument+2.020
Neg logit contributions
idav-2.611
zeb-2.478
ween-2.442
wave-2.392
abase-2.331
Token thorough
Token ID9321
Feature activation+1.35e+00

Pos logit contributions
enthal+1.944
esan+1.691
aeda+1.576
iners+1.576
ocument+1.536
Neg logit contributions
idav-1.776
zeb-1.674
ween-1.672
wave-1.617
abase-1.593
Token full
Token ID1336
Feature activation+1.07e+00

Pos logit contributions
enthal+0.157
esan+0.137
aeda+0.129
iners+0.128
ocument+0.125
Neg logit contributions
idav-0.150
ween-0.141
zeb-0.141
wave-0.139
abase-0.135
Token lineup
Token ID12750
Feature activation+1.16e+00

Pos logit contributions
enthal+0.937
esan+0.831
aeda+0.783
iners+0.779
ocument+0.763
Neg logit contributions
idav-0.713
zeb-0.667
ween-0.665
wave-0.647
abase-0.631
Token of
Token ID286
Feature activation+2.58e-01

Pos logit contributions
enthal+0.958
esan+0.845
aeda+0.787
iners+0.785
ocument+0.762
Neg logit contributions
idav-0.845
ween-0.792
zeb-0.785
wave-0.767
abase-0.748
Token games
Token ID1830
Feature activation+1.33e+00

Pos logit contributions
enthal+0.207
esan+0.181
aeda+0.170
iners+0.169
ocument+0.165
Neg logit contributions
idav-0.192
zeb-0.180
ween-0.180
wave-0.177
abase-0.172
Token that
Token ID326
Feature activation+4.79e+00

Pos logit contributions
enthal+1.067
esan+0.932
aeda+0.872
iners+0.871
ocument+0.852
Neg logit contributions
idav-0.986
zeb-0.923
ween-0.921
wave-0.903
abase-0.881
Token will
Token ID481
Feature activation+6.63e+00

Pos logit contributions
enthal+3.638
esan+3.215
iners+3.044
aeda+2.913
ocument+2.909
Neg logit contributions
idav-3.687
zeb-3.475
ween-3.407
wave-3.326
abase-3.302
Token be
Token ID307
Feature activation+2.32e+00

Pos logit contributions
enthal+4.334
esan+3.814
iners+3.602
aeda+3.427
ocument+3.419
Neg logit contributions
idav-5.668
zeb-5.350
ween-5.234
abase-5.081
wave-5.068
Token played
Token ID2826
Feature activation-2.74e-01

Pos logit contributions
enthal+1.848
esan+1.615
aeda+1.502
iners+1.500
ocument+1.467
Neg logit contributions
idav-1.761
zeb-1.640
ween-1.620
wave-1.596
abase-1.559
Token at
Token ID379
Feature activation+3.91e-01

Pos logit contributions
idav+0.195
zeb+0.182
ween+0.182
wave+0.179
abase+0.174
Neg logit contributions
enthal-0.228
esan-0.201
aeda-0.189
iners-0.188
ocument-0.184
Token the
Token ID262
Feature activation+1.65e+00

Pos logit contributions
enthal+0.320
esan+0.281
aeda+0.263
iners+0.262
ocument+0.257
Neg logit contributions
idav-0.285
zeb-0.267
ween-0.266
wave-0.261
abase-0.254
Token January
Token ID3269
Feature activation-1.82e+00

Pos logit contributions
enthal+1.300
esan+1.138
aeda+1.059
iners+1.057
ROR+1.027
Neg logit contributions
idav-1.243
zeb-1.171
ween-1.167
wave-1.143
abase-1.118
Token for
Token ID329
Feature activation+2.57e+00

Pos logit contributions
idav+2.322
zeb+2.183
ween+2.177
wave+2.146
 Faul+2.059
Neg logit contributions
enthal-3.034
esan-2.688
aeda-2.547
iners-2.522
ocument-2.490
Token the
Token ID262
Feature activation-1.37e-01

Pos logit contributions
enthal+1.942
esan+1.677
aeda+1.560
iners+1.553
ROR+1.509
Neg logit contributions
idav-2.032
ween-1.894
wave-1.876
zeb-1.870
abase-1.833
Token Ring
Token ID12569
Feature activation-1.49e-01

Pos logit contributions
idav+0.092
ween+0.085
zeb+0.085
wave+0.084
abase+0.081
Neg logit contributions
enthal-0.121
esan-0.107
aeda-0.101
iners-0.100
ROR-0.098
Token
Token ID784
Feature activation+8.00e-01

Pos logit contributions
idav+0.102
ween+0.095
zeb+0.094
wave+0.092
abase+0.090
Neg logit contributions
enthal-0.130
esan-0.114
aeda-0.108
iners-0.107
ocument-0.105
Token bet
Token ID731
Feature activation-6.72e+00

Pos logit contributions
enthal+0.664
esan+0.585
iners+0.546
aeda+0.546
ocument+0.532
Neg logit contributions
idav-0.571
ween-0.535
zeb-0.531
wave-0.522
abase-0.512
Tokenrays
Token ID20477
Feature activation+6.91e+00

Pos logit contributions
idav+1.287
ween+1.171
zeb+1.018
wave+0.997
abase+0.823
Neg logit contributions
enthal-8.958
esan-8.181
aeda-7.903
iners-7.846
ocument-7.845
Token Fro
Token ID9734
Feature activation-2.43e+00

Pos logit contributions
enthal+5.295
esan+4.668
aeda+4.258
iners+4.256
ROR+4.210
Neg logit contributions
idav-5.229
ween-4.738
zeb-4.699
abase-4.654
wave-4.639
Tokendo
Token ID4598
Feature activation+6.66e-01

Pos logit contributions
idav+1.866
zeb+1.807
ween+1.796
wave+1.758
abase+1.668
Neg logit contributions
enthal-1.844
esan-1.608
aeda-1.534
iners-1.524
ROR-1.498
Token by
Token ID416
Feature activation+1.60e+00

Pos logit contributions
enthal+0.557
esan+0.490
aeda+0.459
iners+0.454
ocument+0.449
Neg logit contributions
idav-0.477
zeb-0.440
ween-0.440
wave-0.432
abase-0.421
Token leading
Token ID3756
Feature activation+2.99e+00

Pos logit contributions
enthal+1.256
esan+1.108
aeda+1.027
iners+1.020
ocument+0.995
Neg logit contributions
idav-1.214
ween-1.135
zeb-1.125
wave-1.111
abase-1.087
Token him
Token ID683
Feature activation+4.63e+00

Pos logit contributions
enthal+2.370
esan+2.079
aeda+1.949
iners+1.932
ocument+1.882
Neg logit contributions
idav-2.220
ween-2.079
zeb-2.066
abase-2.015
wave-2.011
Token Chrom
Token ID18255
Feature activation+1.09e+00

Pos logit contributions
enthal+1.940
esan+1.700
aeda+1.582
iners+1.577
ocument+1.544
Neg logit contributions
idav-1.788
ween-1.668
zeb-1.666
wave-1.631
abase-1.595
Tokenecast
Token ID43299
Feature activation-4.75e+00

Pos logit contributions
enthal+1.058
esan+0.949
aeda+0.902
iners+0.895
ocument+0.880
Neg logit contributions
idav-0.622
ween-0.573
zeb-0.572
wave-0.557
abase-0.537
Token or
Token ID393
Feature activation+4.39e+00

Pos logit contributions
idav+2.910
zeb+2.730
ween+2.727
wave+2.713
abase+2.571
Neg logit contributions
enthal-4.323
esan-3.829
aeda-3.670
iners-3.617
ocument-3.572
Token Fire
Token ID3764
Feature activation+1.95e+00

Pos logit contributions
enthal+3.263
esan+2.847
iners+2.639
aeda+2.620
ROR+2.547
Neg logit contributions
idav-3.477
ween-3.221
zeb-3.214
wave-3.135
abase-3.084
TokenSt
Token ID1273
Feature activation-4.05e-01

Pos logit contributions
enthal+1.666
esan+1.467
aeda+1.393
iners+1.377
ocument+1.358
Neg logit contributions
idav-1.323
zeb-1.240
ween-1.236
wave-1.185
abase-1.178
Tokenick
Token ID624
Feature activation+1.33e+00

Pos logit contributions
idav+0.209
ween+0.191
zeb+0.191
wave+0.184
abase+0.178
Neg logit contributions
enthal-0.416
esan-0.375
aeda-0.359
iners-0.355
ocument-0.351
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
enthal+1.142
esan+1.007
aeda+0.942
iners+0.939
ocument+0.922
Neg logit contributions
idav-0.908
ween-0.846
zeb-0.845
wave-0.820
abase-0.805
Token
Token ID198
Feature activation+3.65e-01

Pos logit contributions
enthal+0.936
esan+0.825
aeda+0.774
iners+0.768
ocument+0.757
Neg logit contributions
idav-0.798
ween-0.747
zeb-0.745
wave-0.730
abase-0.711
Token
Token ID198
Feature activation+1.17e-01

Pos logit contributions
enthal+0.301
esan+0.265
aeda+0.248
iners+0.247
ROR+0.243
Neg logit contributions
idav-0.263
ween-0.246
zeb-0.246
wave-0.241
abase-0.236
TokenCheck
Token ID9787
Feature activation+1.83e+00

Pos logit contributions
enthal+0.097
esan+0.086
aeda+0.081
iners+0.080
ocument+0.079
Neg logit contributions
idav-0.084
ween-0.079
zeb-0.078
wave-0.077
abase-0.075
Tokenout
Token ID448
Feature activation+5.95e-01

Pos logit contributions
enthal+1.423
esan+1.239
aeda+1.149
iners+1.147
ocument+1.133
Neg logit contributions
idav-1.400
ween-1.326
zeb-1.309
wave-1.286
abase-1.251
Token banks
Token ID6341
Feature activation-4.46e-01

Pos logit contributions
enthal+0.310
esan+0.271
aeda+0.255
iners+0.254
ocument+0.248
Neg logit contributions
idav-0.288
zeb-0.271
ween-0.269
wave-0.265
abase-0.257
Token and
Token ID290
Feature activation+4.16e+00

Pos logit contributions
idav+0.301
zeb+0.281
ween+0.281
wave+0.275
abase+0.267
Neg logit contributions
enthal-0.387
esan-0.342
aeda-0.323
iners-0.321
ocument-0.315
Token "
Token ID366
Feature activation+3.46e+00

Pos logit contributions
enthal+3.079
esan+2.660
iners+2.575
aeda+2.511
ROR+2.442
Neg logit contributions
idav-3.245
zeb-3.047
ween-3.012
wave-2.941
abase-2.897
Tokeninvest
Token ID24859
Feature activation-5.49e-01

Pos logit contributions
enthal+2.637
esan+2.292
iners+2.177
aeda+2.130
ROR+2.103
Neg logit contributions
idav-2.662
zeb-2.488
ween-2.452
 Faul-2.417
abase-2.394
Tokenors
Token ID669
Feature activation+5.74e+00

Pos logit contributions
idav+0.273
zeb+0.248
ween+0.247
wave+0.241
abase+0.232
Neg logit contributions
enthal-0.573
esan-0.517
iners-0.497
aeda-0.495
ocument-0.485
Token,"
Token ID553
Feature activation+3.25e+00

Pos logit contributions
enthal+4.220
esan+3.716
iners+3.453
aeda+3.412
ocument+3.307
Neg logit contributions
idav-4.460
zeb-4.152
ween-4.124
wave-4.025
abase-3.985
Token all
Token ID477
Feature activation+6.15e-01

Pos logit contributions
enthal+2.565
esan+2.226
iners+2.108
aeda+2.099
ocument+2.050
Neg logit contributions
idav-2.424
zeb-2.277
ween-2.249
wave-2.193
abase-2.152
Token backed
Token ID9763
Feature activation-1.48e+00

Pos logit contributions
enthal+0.497
esan+0.437
iners+0.410
aeda+0.409
ocument+0.402
Neg logit contributions
idav-0.450
zeb-0.422
ween-0.420
wave-0.411
abase-0.403
Token by
Token ID416
Feature activation-2.09e-01

Pos logit contributions
idav+1.036
ween+0.972
zeb+0.970
wave+0.954
abase+0.925
Neg logit contributions
enthal-1.240
esan-1.090
aeda-1.030
iners-1.023
ocument-1.005
Token Federal
Token ID5618
Feature activation+3.12e+00

Pos logit contributions
idav+0.156
zeb+0.147
ween+0.146
wave+0.144
abase+0.140
Neg logit contributions
enthal-0.166
esan-0.145
aeda-0.137
iners-0.136
ocument-0.133
Token guarantees
Token ID19026
Feature activation+2.23e+00

Pos logit contributions
enthal+1.987
esan+1.708
iners+1.570
aeda+1.569
ocument+1.516
Neg logit contributions
idav-2.750
zeb-2.616
ween-2.605
wave-2.571
abase-2.560
Token LG
Token ID17370
Feature activation+2.58e+00

Pos logit contributions
idav+1.629
zeb+1.537
ween+1.536
wave+1.512
abase+1.465
Neg logit contributions
enthal-1.828
esan-1.598
aeda-1.510
iners-1.493
ocument-1.474
TokenD
Token ID35
Feature activation-1.25e+00

Pos logit contributions
enthal+1.937
esan+1.673
iners+1.578
aeda+1.560
ROR+1.529
Neg logit contributions
idav-2.036
ween-1.909
zeb-1.907
wave-1.871
abase-1.834
Token people
Token ID661
Feature activation-1.13e+00

Pos logit contributions
idav+0.877
ween+0.822
zeb+0.821
wave+0.807
abase+0.783
Neg logit contributions
enthal-1.053
esan-0.926
aeda-0.874
iners-0.868
ocument-0.852
Token,
Token ID11
Feature activation-7.94e-01

Pos logit contributions
idav+0.770
ween+0.721
zeb+0.721
wave+0.707
abase+0.685
Neg logit contributions
enthal-0.976
esan-0.862
aeda-0.815
iners-0.808
ocument-0.795
Token including
Token ID1390
Feature activation-1.29e+00

Pos logit contributions
idav+0.563
ween+0.529
zeb+0.529
wave+0.519
abase+0.504
Neg logit contributions
enthal-0.661
esan-0.581
aeda-0.548
iners-0.543
ocument-0.534
Token LG
Token ID17370
Feature activation+2.72e+00

Pos logit contributions
idav+0.941
ween+0.885
zeb+0.884
wave+0.869
abase+0.844
Neg logit contributions
enthal-1.044
esan-0.914
aeda-0.861
iners-0.853
ocument-0.838
TokenD
Token ID35
Feature activation+2.18e+00

Pos logit contributions
enthal+2.002
esan+1.715
aeda+1.588
iners+1.575
ROR+1.540
Neg logit contributions
idav-2.214
ween-2.077
zeb-2.069
wave-2.036
abase-1.993
Token
Token ID447
Feature activation+7.15e-01

Pos logit contributions
enthal+1.823
esan+1.597
aeda+1.506
iners+1.496
ocument+1.466
Neg logit contributions
idav-1.551
ween-1.431
zeb-1.427
wave-1.402
abase-1.361
Token
Token ID247
Feature activation-1.26e+00

Pos logit contributions
enthal+0.543
esan+0.470
aeda+0.444
iners+0.438
ocument+0.429
Neg logit contributions
idav-0.560
ween-0.530
zeb-0.527
wave-0.519
abase-0.505
Tokens
Token ID82
Feature activation-1.59e+00

Pos logit contributions
idav+0.870
ween+0.815
zeb+0.814
wave+0.799
abase+0.775
Neg logit contributions
enthal-1.068
esan-0.941
aeda-0.889
iners-0.881
ocument-0.867
Token manager
Token ID4706
Feature activation-1.86e+00

Pos logit contributions
idav+1.166
ween+1.097
zeb+1.097
wave+1.078
abase+1.047
Neg logit contributions
enthal-1.292
esan-1.131
aeda-1.065
iners-1.055
ocument-1.037
Token another
Token ID1194
Feature activation+2.58e+00

Pos logit contributions
enthal+3.273
esan+2.822
iners+2.682
aeda+2.666
ocument+2.590
Neg logit contributions
idav-3.254
zeb-3.070
ween-3.018
wave-2.945
abase-2.900
Token trust
Token ID3774
Feature activation+8.44e-01

Pos logit contributions
enthal+2.079
esan+1.814
aeda+1.704
iners+1.691
ocument+1.660
Neg logit contributions
idav-1.889
zeb-1.778
ween-1.772
wave-1.716
abase-1.688
Token,
Token ID11
Feature activation+1.06e+00

Pos logit contributions
enthal+0.717
esan+0.633
aeda+0.594
iners+0.592
ocument+0.582
Neg logit contributions
idav-0.585
ween-0.548
zeb-0.548
wave-0.533
abase-0.521
Token called
Token ID1444
Feature activation+2.27e+00

Pos logit contributions
enthal+0.861
esan+0.755
aeda+0.710
iners+0.707
ocument+0.695
Neg logit contributions
idav-0.769
zeb-0.721
ween-0.720
wave-0.705
abase-0.686
Token the
Token ID262
Feature activation+2.93e+00

Pos logit contributions
enthal+1.801
esan+1.577
aeda+1.482
iners+1.480
ocument+1.457
Neg logit contributions
idav-1.683
zeb-1.574
ween-1.568
wave-1.534
abase-1.498
Token Mor
Token ID3461
Feature activation+3.87e+00

Pos logit contributions
enthal+2.358
esan+2.064
aeda+1.934
iners+1.926
ocument+1.893
Neg logit contributions
idav-2.136
zeb-2.017
ween-1.991
wave-1.960
abase-1.918
Tokenneau
Token ID46533
Feature activation+2.06e+00

Pos logit contributions
enthal+2.679
esan+2.267
iners+2.100
aeda+2.065
ocument+2.033
Neg logit contributions
idav-3.220
zeb-3.065
ween-3.015
wave-2.988
abase-2.941
Token McCain
Token ID14264
Feature activation+4.92e+00

Pos logit contributions
enthal+1.671
esan+1.456
aeda+1.370
iners+1.367
ocument+1.339
Neg logit contributions
idav-1.501
zeb-1.409
ween-1.379
wave-1.375
abase-1.350
Token Family
Token ID7884
Feature activation+2.21e+00

Pos logit contributions
enthal+3.955
esan+3.430
iners+3.195
aeda+3.183
ocument+3.142
Neg logit contributions
idav-3.581
zeb-3.381
ween-3.326
wave-3.268
abase-3.218
Token Trust
Token ID9870
Feature activation-7.51e-01

Pos logit contributions
enthal+1.859
esan+1.635
iners+1.516
aeda+1.513
ocument+1.497
Neg logit contributions
idav-1.551
zeb-1.467
ween-1.446
wave-1.423
abase-1.389
Token.
Token ID13
Feature activation+1.86e+00

Pos logit contributions
idav+0.489
ween+0.456
zeb+0.456
wave+0.447
abase+0.432
Neg logit contributions
enthal-0.670
esan-0.594
aeda-0.562
iners-0.558
ocument-0.550
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
enthal+2.321
esan+2.038
aeda+1.892
iners+1.885
ROR+1.867
Neg logit contributions
idav-2.100
ween-1.968
zeb-1.940
wave-1.899
abase-1.889
Token
Token ID198
Feature activation+2.25e+00

Pos logit contributions
idav+0.808
zeb+0.772
ween+0.769
wave+0.763
 Faul+0.722
Neg logit contributions
enthal-1.071
esan-0.946
aeda-0.908
iners-0.889
ocument-0.886
TokenThere
Token ID1858
Feature activation+5.64e+00

Pos logit contributions
enthal+1.847
esan+1.637
iners+1.520
ROR+1.512
aeda+1.507
Neg logit contributions
idav-1.616
ween-1.508
zeb-1.494
wave-1.456
abase-1.454
Token are
Token ID389
Feature activation+3.00e+00

Pos logit contributions
enthal+4.456
esan+3.929
iners+3.680
aeda+3.610
ocument+3.549
Neg logit contributions
idav-4.136
zeb-3.832
wave-3.781
ween-3.778
abase-3.636
Token two
Token ID734
Feature activation+7.45e+00

Pos logit contributions
enthal+2.342
esan+2.042
iners+1.909
aeda+1.901
ocument+1.846
Neg logit contributions
idav-2.273
ween-2.146
zeb-2.142
wave-2.089
abase-2.055
Token ways
Token ID2842
Feature activation-1.26e-01

Pos logit contributions
enthal+5.159
esan+4.577
iners+4.175
aeda+4.092
ROR+3.988
Neg logit contributions
idav-5.992
ween-5.637
zeb-5.593
abase-5.410
wave-5.375
Token to
Token ID284
Feature activation+5.04e+00

Pos logit contributions
idav+0.090
ween+0.085
zeb+0.084
wave+0.083
abase+0.081
Neg logit contributions
enthal-0.104
esan-0.092
aeda-0.086
iners-0.085
ocument-0.084
Token approach
Token ID3164
Feature activation+1.81e+00

Pos logit contributions
enthal+3.915
esan+3.452
iners+3.202
aeda+3.157
ocument+3.105
Neg logit contributions
idav-3.747
ween-3.563
zeb-3.483
abase-3.375
wave-3.372
Token Lac
Token ID23115
Feature activation+1.50e+00

Pos logit contributions
enthal+1.419
esan+1.237
aeda+1.152
iners+1.146
ROR+1.119
Neg logit contributions
idav-1.369
ween-1.295
zeb-1.282
wave-1.261
abase-1.234
Tokenan
Token ID272
Feature activation+1.61e+00

Pos logit contributions
enthal+0.972
esan+0.825
aeda+0.754
iners+0.746
ocument+0.723
Neg logit contributions
idav-1.340
ween-1.272
zeb-1.266
wave-1.249
abase-1.221
Token
Token ID447
Feature activation+5.48e-01

Pos logit contributions
enthal+1.422
esan+1.252
aeda+1.169
iners+1.164
ocument+1.143
Neg logit contributions
idav-1.081
ween-1.009
zeb-1.000
wave-0.989
abase-0.959
Token,
Token ID11
Feature activation-9.14e-01

Pos logit contributions
enthal+2.448
esan+2.143
iners+2.035
aeda+1.996
ocument+1.970
Neg logit contributions
idav-2.136
zeb-1.986
ween-1.967
wave-1.929
abase-1.873
Token why
Token ID1521
Feature activation+2.14e+00

Pos logit contributions
idav+0.655
ween+0.614
zeb+0.613
wave+0.601
abase+0.584
Neg logit contributions
enthal-0.757
esan-0.665
aeda-0.626
iners-0.623
ocument-0.609
Token are
Token ID389
Feature activation+1.18e-01

Pos logit contributions
enthal+1.711
esan+1.499
iners+1.419
aeda+1.385
ocument+1.344
Neg logit contributions
idav-1.597
ween-1.483
zeb-1.479
wave-1.437
abase-1.416
Token we
Token ID356
Feature activation+7.63e-01

Pos logit contributions
enthal+0.094
esan+0.082
iners+0.077
aeda+0.076
ocument+0.074
Neg logit contributions
idav-0.089
zeb-0.083
ween-0.082
wave-0.081
abase-0.080
Token doing
Token ID1804
Feature activation+3.43e+00

Pos logit contributions
enthal+0.590
esan+0.516
iners+0.481
aeda+0.480
ocument+0.466
Neg logit contributions
idav-0.589
ween-0.548
zeb-0.547
wave-0.540
abase-0.527
Token other
Token ID584
Feature activation-6.06e+00

Pos logit contributions
enthal+2.584
esan+2.247
iners+2.125
aeda+2.063
ocument+2.000
Neg logit contributions
idav-2.702
ween-2.485
zeb-2.469
wave-2.439
abase-2.416
Token things
Token ID1243
Feature activation+8.93e-01

Pos logit contributions
idav+3.807
ween+3.660
zeb+3.647
wave+3.587
 Faul+3.453
Neg logit contributions
enthal-5.288
esan-4.733
aeda-4.509
ocument-4.506
ROR-4.401
Token -
Token ID532
Feature activation-1.66e+00

Pos logit contributions
enthal+0.760
esan+0.669
iners+0.629
aeda+0.628
ocument+0.613
Neg logit contributions
idav-0.621
zeb-0.579
ween-0.576
wave-0.565
abase-0.552
Token the
Token ID262
Feature activation-2.97e+00

Pos logit contributions
idav+1.192
ween+1.122
zeb+1.121
wave+1.102
abase+1.068
Neg logit contributions
enthal-1.366
esan-1.198
aeda-1.130
iners-1.118
ocument-1.102
Token pre
Token ID662
Feature activation-1.10e+00

Pos logit contributions
idav+2.130
ween+2.007
zeb+2.005
wave+1.968
abase+1.911
Neg logit contributions
enthal-2.443
esan-2.147
aeda-2.025
iners-1.999
ocument-1.979
Token-
Token ID12
Feature activation+7.18e-01

Pos logit contributions
idav+0.797
ween+0.750
zeb+0.749
wave+0.736
abase+0.715
Neg logit contributions
enthal-0.905
esan-0.793
aeda-0.748
iners-0.741
ocument-0.728
Token Psychology
Token ID18430
Feature activation-1.33e+00

Pos logit contributions
enthal+0.362
esan+0.316
aeda+0.296
iners+0.294
ROR+0.287
Neg logit contributions
idav-0.343
zeb-0.322
ween-0.322
wave-0.317
abase-0.309
Token Quarterly
Token ID36082
Feature activation-3.43e-01

Pos logit contributions
idav+1.000
ween+0.943
zeb+0.942
wave+0.927
abase+0.900
Neg logit contributions
enthal-1.058
esan-0.923
aeda-0.868
iners-0.860
ocument-0.845
Token,
Token ID11
Feature activation-6.42e-01

Pos logit contributions
idav+0.234
ween+0.218
zeb+0.218
wave+0.213
abase+0.208
Neg logit contributions
enthal-0.296
esan-0.262
aeda-0.247
iners-0.245
ocument-0.241
Token 23
Token ID2242
Feature activation-2.32e+00

Pos logit contributions
idav+0.510
ween+0.483
zeb+0.483
wave+0.475
abase+0.462
Neg logit contributions
enthal-0.480
esan-0.415
aeda-0.389
iners-0.384
ocument-0.377
Token,
Token ID11
Feature activation-1.79e+00

Pos logit contributions
idav+1.349
ween+1.249
zeb+1.248
wave+1.220
abase+1.175
Neg logit contributions
enthal-2.236
esan-2.002
aeda-1.906
iners-1.891
ocument-1.864
Token 26
Token ID2608
Feature activation-3.85e+00

Pos logit contributions
idav+1.333
ween+1.258
zeb+1.257
wave+1.237
abase+1.199
Neg logit contributions
enthal-1.424
esan-1.242
aeda-1.169
iners-1.159
ocument-1.138
Token -
Token ID532
Feature activation+3.97e+00

Pos logit contributions
idav+2.686
zeb+2.518
ween+2.512
wave+2.491
 Faul+2.409
Neg logit contributions
enthal-3.223
esan-2.846
aeda-2.667
iners-2.656
ocument-2.630
Token 42
Token ID5433
Feature activation+3.80e+00

Pos logit contributions
enthal+2.699
esan+2.336
iners+2.129
aeda+2.123
ROR+2.095
Neg logit contributions
idav-3.397
ween-3.175
zeb-3.161
abase-3.121
wave-3.083
Token.
Token ID764
Feature activation+4.21e+00

Pos logit contributions
enthal+3.732
esan+3.356
iners+3.146
aeda+3.140
ROR+3.105
Neg logit contributions
idav-2.163
ween-1.938
zeb-1.910
abase-1.865
wave-1.857
Token
Token ID198
Feature activation+3.12e+00

Pos logit contributions
enthal+3.204
esan+2.775
aeda+2.546
iners+2.527
ROR+2.502
Neg logit contributions
idav-3.326
ween-3.056
zeb-3.049
wave-2.955
abase-2.953
Token
Token ID198
Feature activation+8.92e-01

Pos logit contributions
enthal+2.446
esan+2.132
iners+1.976
aeda+1.958
ROR+1.936
Neg logit contributions
idav-2.395
ween-2.212
zeb-2.199
abase-2.159
wave-2.151
Token
Token ID12466
Feature activation-3.63e-01

Pos logit contributions
enthal+1.996
esan+1.734
aeda+1.635
iners+1.624
ocument+1.603
Neg logit contributions
idav-1.802
zeb-1.701
ween-1.696
wave-1.651
abase-1.629
Token
Token ID123
Feature activation-1.45e+00

Pos logit contributions
idav+0.280
ween+0.264
zeb+0.264
wave+0.260
abase+0.253
Neg logit contributions
enthal-0.279
esan-0.242
aeda-0.228
iners-0.225
ocument-0.221
Tokenр
Token ID21169
Feature activation+1.13e+00

Pos logit contributions
idav+1.022
ween+0.959
zeb+0.959
wave+0.941
abase+0.914
Neg logit contributions
enthal-1.211
esan-1.064
aeda-1.005
iners-0.995
ocument-0.980
Tokenо
Token ID15166
Feature activation-2.25e+00

Pos logit contributions
enthal+0.850
esan+0.735
aeda+0.686
iners+0.683
ocument+0.671
Neg logit contributions
idav-0.887
zeb-0.842
ween-0.838
wave-0.825
abase-0.804
Tokenс
Token ID21727
Feature activation-1.60e+00

Pos logit contributions
idav+1.572
ween+1.475
zeb+1.472
wave+1.453
abase+1.402
Neg logit contributions
enthal-1.896
esan-1.671
aeda-1.581
iners-1.562
ocument-1.535
Tokenь
Token ID45367
Feature activation-2.66e+00

Pos logit contributions
idav+1.180
ween+1.112
zeb+1.109
wave+1.094
abase+1.058
Neg logit contributions
enthal-1.290
esan-1.131
aeda-1.064
iners-1.053
ocument-1.035
Token
Token ID140
Feature activation-4.12e+00

Pos logit contributions
idav+1.880
ween+1.774
zeb+1.768
wave+1.745
abase+1.682
Neg logit contributions
enthal-2.211
esan-1.946
aeda-1.835
iners-1.819
ocument-1.783
Token
Token ID109
Feature activation-6.22e-01

Pos logit contributions
idav+2.526
ween+2.366
zeb+2.362
wave+2.338
abase+2.223
Neg logit contributions
enthal-3.779
esan-3.377
aeda-3.208
iners-3.175
ocument-3.136
Tokenо�
Token ID25443
Feature activation-5.14e+00

Pos logit contributions
idav+0.477
ween+0.450
zeb+0.450
wave+0.442
abase+0.431
Neg logit contributions
enthal-0.483
esan-0.420
aeda-0.394
iners-0.390
ocument-0.384
Token
Token ID117
Feature activation-1.32e+00

Pos logit contributions
idav+3.952
ween+3.762
wave+3.700
zeb+3.689
 Faul+3.567
Neg logit contributions
enthal-3.874
esan-3.383
aeda-3.193
iners-3.117
ocument-3.068
Token
Token ID12466
Feature activation-1.72e+00

Pos logit contributions
idav+0.860
ween+0.804
zeb+0.803
wave+0.787
abase+0.762
Neg logit contributions
enthal-1.173
esan-1.040
aeda-0.985
iners-0.977
ocument-0.962
Token references
Token ID10288
Feature activation+1.45e+00

Pos logit contributions
enthal+0.850
esan+0.738
iners+0.693
aeda+0.682
ocument+0.677
Neg logit contributions
idav-0.812
ween-0.772
zeb-0.769
wave-0.752
abase-0.728
Token on
Token ID319
Feature activation-1.68e+00

Pos logit contributions
enthal+1.150
esan+1.000
iners+0.944
aeda+0.936
ocument+0.923
Neg logit contributions
idav-1.075
zeb-1.019
ween-1.013
wave-0.995
abase-0.968
Token card
Token ID2657
Feature activation+2.33e+00

Pos logit contributions
idav+1.227
ween+1.156
zeb+1.155
wave+1.133
abase+1.100
Neg logit contributions
enthal-1.370
esan-1.198
aeda-1.128
iners-1.121
ocument-1.101
Token n
Token ID299
Feature activation+6.24e+00

Pos logit contributions
enthal+1.903
esan+1.673
iners+1.571
aeda+1.571
ocument+1.532
Neg logit contributions
idav-1.676
ween-1.584
zeb-1.579
wave-1.539
 Faul-1.504
Token°
Token ID7200
Feature activation-2.54e-01

Pos logit contributions
enthal+4.464
esan+3.852
iners+3.565
aeda+3.563
ocument+3.539
Neg logit contributions
idav-4.914
zeb-4.754
ween-4.696
wave-4.607
 Faul-4.540
Token1
Token ID16
Feature activation-1.70e+00

Pos logit contributions
idav+0.149
zeb+0.138
ween+0.138
wave+0.134
abase+0.130
Neg logit contributions
enthal-0.244
esan-0.218
aeda-0.208
iners-0.206
ocument-0.203
Token and
Token ID290
Feature activation+4.59e+00

Pos logit contributions
idav+1.165
ween+1.092
zeb+1.090
wave+1.072
abase+1.039
Neg logit contributions
enthal-1.459
esan-1.289
aeda-1.220
iners-1.207
ocument-1.187
Token more
Token ID517
Feature activation+1.12e+00

Pos logit contributions
enthal+3.480
esan+2.964
iners+2.819
ocument+2.737
aeda+2.734
Neg logit contributions
idav-3.500
ween-3.395
zeb-3.369
wave-3.260
 Faul-3.158
Token details
Token ID3307
Feature activation-2.28e-01

Pos logit contributions
enthal+0.917
esan+0.799
aeda+0.750
iners+0.749
ocument+0.738
Neg logit contributions
idav-0.815
zeb-0.768
ween-0.767
wave-0.753
abase-0.729
Token on
Token ID319
Feature activation-1.12e+00

Pos logit contributions
idav+0.164
zeb+0.154
ween+0.154
wave+0.151
abase+0.147
Neg logit contributions
enthal-0.188
esan-0.165
aeda-0.156
iners-0.155
ocument-0.152
Token card
Token ID2657
Feature activation+6.14e-01

Pos logit contributions
idav+0.855
ween+0.808
zeb+0.807
wave+0.792
abase+0.769
Neg logit contributions
enthal-0.880
esan-0.765
aeda-0.717
iners-0.714
ocument-0.700
Token're
Token ID821
Feature activation+7.70e-01

Pos logit contributions
idav+0.688
ween+0.646
zeb+0.646
wave+0.634
abase+0.616
Neg logit contributions
enthal-0.785
esan-0.689
aeda-0.650
iners-0.644
ocument-0.633
Token living
Token ID2877
Feature activation-4.39e+00

Pos logit contributions
enthal+0.599
esan+0.522
iners+0.491
aeda+0.491
ocument+0.477
Neg logit contributions
idav-0.594
zeb-0.552
ween-0.551
wave-0.541
abase-0.526
Token in
Token ID287
Feature activation-8.23e-01

Pos logit contributions
idav+2.937
ween+2.784
zeb+2.766
wave+2.747
 Faul+2.640
Neg logit contributions
enthal-3.779
esan-3.328
aeda-3.132
ROR-3.078
ocument-3.055
Token a
Token ID257
Feature activation+5.32e-01

Pos logit contributions
idav+0.605
ween+0.567
zeb+0.567
wave+0.556
abase+0.542
Neg logit contributions
enthal-0.666
esan-0.582
aeda-0.551
iners-0.547
ocument-0.534
Token global
Token ID3298
Feature activation-3.77e-01

Pos logit contributions
enthal+0.404
esan+0.350
aeda+0.328
iners+0.327
ocument+0.318
Neg logit contributions
idav-0.419
ween-0.392
zeb-0.390
wave-0.382
abase-0.376
Token economy
Token ID3773
Feature activation-2.86e+00

Pos logit contributions
idav+0.238
ween+0.221
zeb+0.220
wave+0.214
abase+0.210
Neg logit contributions
enthal-0.344
esan-0.306
aeda-0.290
iners-0.289
ocument-0.284
Token,
Token ID11
Feature activation+1.43e+00

Pos logit contributions
idav+1.881
ween+1.790
zeb+1.788
wave+1.771
 Faul+1.711
Neg logit contributions
enthal-2.490
esan-2.194
aeda-2.088
iners-2.058
ROR-2.043
Token and
Token ID290
Feature activation+4.58e-01

Pos logit contributions
enthal+1.158
esan+1.013
aeda+0.958
iners+0.951
ocument+0.929
Neg logit contributions
idav-1.057
zeb-0.990
ween-0.983
wave-0.961
abase-0.941
Token important
Token ID1593
Feature activation+1.43e+00

Pos logit contributions
enthal+0.368
esan+0.321
aeda+0.303
iners+0.301
ocument+0.294
Neg logit contributions
idav-0.340
zeb-0.319
ween-0.318
wave-0.313
abase-0.305
Token as
Token ID355
Feature activation-8.25e-01

Pos logit contributions
enthal+1.149
esan+1.006
iners+0.950
aeda+0.947
ocument+0.917
Neg logit contributions
idav-1.057
zeb-0.989
ween-0.986
wave-0.965
abase-0.945
Token Europe
Token ID2031
Feature activation-2.44e+00

Pos logit contributions
idav+0.606
ween+0.571
zeb+0.570
wave+0.561
abase+0.545
Neg logit contributions
enthal-0.666
esan-0.582
aeda-0.548
iners-0.543
ocument-0.534
Token E
Token ID412
Feature activation+5.83e-01

Pos logit contributions
enthal+1.350
esan+1.193
aeda+1.123
iners+1.108
ocument+1.088
Neg logit contributions
idav-1.112
ween-1.037
zeb-1.031
wave-1.014
abase-0.990
Tokenia
Token ID544
Feature activation+1.10e+00

Pos logit contributions
enthal+0.492
esan+0.435
aeda+0.409
iners+0.406
ocument+0.398
Neg logit contributions
idav-0.407
ween-0.379
zeb-0.378
wave-0.373
abase-0.362
Token n
Token ID299
Feature activation+9.26e-01

Pos logit contributions
enthal+0.933
esan+0.826
aeda+0.775
iners+0.769
ocument+0.754
Neg logit contributions
idav-0.761
ween-0.708
zeb-0.704
wave-0.694
abase-0.677
Tokenō
Token ID13090
Feature activation-4.68e+00

Pos logit contributions
enthal+0.691
esan+0.602
aeda+0.564
iners+0.556
ocument+0.541
Neg logit contributions
idav-0.733
ween-0.691
zeb-0.690
wave-0.682
 Faul-0.668
Token na
Token ID12385
Feature activation+2.54e+00

Pos logit contributions
idav+3.075
zeb+2.913
ween+2.891
wave+2.855
abase+2.730
Neg logit contributions
enthal-4.076
esan-3.595
aeda-3.423
iners-3.405
ROR-3.359
Token
Token ID134
Feature activation-9.41e+00

Pos logit contributions
enthal+2.136
esan+1.901
aeda+1.772
iners+1.760
ocument+1.724
Neg logit contributions
idav-1.749
ween-1.630
zeb-1.612
wave-1.600
abase-1.554
Token
Token ID119
Feature activation-2.80e+00

Pos logit contributions
idav+5.698
zeb+5.438
ween+5.350
wave+5.229
abase+4.989
Neg logit contributions
enthal-8.376
esan-7.277
aeda-6.993
ROR-6.987
iners-6.985
Tokene
Token ID68
Feature activation-8.82e-01

Pos logit contributions
idav+2.101
zeb+1.987
ween+1.987
wave+1.954
abase+1.896
Neg logit contributions
enthal-2.206
esan-1.918
aeda-1.806
iners-1.788
ROR-1.763
Token,
Token ID11
Feature activation-7.58e-01

Pos logit contributions
idav+0.606
ween+0.567
zeb+0.565
wave+0.556
abase+0.540
Neg logit contributions
enthal-0.754
esan-0.666
aeda-0.628
iners-0.623
ocument-0.612
Token ma
Token ID17266
Feature activation+1.01e+00

Pos logit contributions
idav+0.512
ween+0.479
zeb+0.478
wave+0.469
abase+0.455
Neg logit contributions
enthal-0.658
esan-0.581
aeda-0.550
iners-0.545
ocument-0.536
Token ke
Token ID885
Feature activation-5.13e+00

Pos logit contributions
enthal+0.862
esan+0.761
aeda+0.714
iners+0.710
ocument+0.695
Neg logit contributions
idav-0.702
ween-0.656
zeb-0.651
wave-0.644
abase-0.624
Token WE
Token ID12887
Feature activation-2.39e+00

Pos logit contributions
idav+1.599
ween+1.505
zeb+1.494
wave+1.485
 Faul+1.425
Neg logit contributions
enthal-1.905
esan-1.686
aeda-1.585
iners-1.570
ocument-1.551
Token ARE
Token ID15986
Feature activation-1.26e+00

Pos logit contributions
idav+1.621
ween+1.523
zeb+1.520
wave+1.520
 Faul+1.448
Neg logit contributions
enthal-2.020
esan-1.794
aeda-1.687
iners-1.655
ocument-1.651
Token WITH
Token ID13315
Feature activation+5.34e+00

Pos logit contributions
idav+0.891
ween+0.839
zeb+0.835
wave+0.830
 Faul+0.799
Neg logit contributions
enthal-1.054
esan-0.925
aeda-0.875
iners-0.859
ocument-0.850
Token YOU
Token ID7013
Feature activation+2.77e+00

Pos logit contributions
enthal+3.521
esan+3.075
ROR+2.838
iners+2.728
aeda+2.702
Neg logit contributions
idav-4.680
zeb-4.473
ween-4.351
abase-4.344
wave-4.293
Token.
Token ID13
Feature activation-3.93e-01

Pos logit contributions
enthal+2.244
esan+1.939
iners+1.856
aeda+1.845
ROR+1.805
Neg logit contributions
idav-2.025
zeb-1.918
ween-1.885
abase-1.854
wave-1.844
Token GOD
Token ID29562
Feature activation-1.02e+01

Pos logit contributions
idav+0.279
zeb+0.262
ween+0.262
wave+0.255
abase+0.252
Neg logit contributions
enthal-0.328
esan-0.287
aeda-0.271
iners-0.270
ROR-0.264
Token BL
Token ID9878
Feature activation-8.53e-01

Pos logit contributions
idav+5.430
wave+5.401
ween+5.375
zeb+5.305
 Faul+5.054
Neg logit contributions
enthal-9.409
esan-8.357
aeda-8.115
ocument-8.042
iners-7.907
TokenESS
Token ID7597
Feature activation-5.77e-02

Pos logit contributions
idav+1.071
ween+1.036
zeb+1.032
wave+1.031
 Faul+1.005
Neg logit contributions
enthal-0.239
esan-0.158
aeda-0.123
iners-0.110
ocument-0.100
Token!
Token ID0
Feature activation+2.75e-01

Pos logit contributions
idav+0.044
zeb+0.041
ween+0.041
wave+0.040
abase+0.040
Neg logit contributions
enthal-0.045
esan-0.040
aeda-0.037
iners-0.037
ROR-0.036
Token
Token ID851
Feature activation-2.52e+00

Pos logit contributions
enthal+0.222
esan+0.192
aeda+0.182
iners+0.181
ROR+0.177
Neg logit contributions
idav-0.204
zeb-0.192
ween-0.192
wave-0.186
abase-0.185
Token Donald
Token ID3759
Feature activation-6.51e-01

Pos logit contributions
idav+1.764
zeb+1.651
ween+1.650
wave+1.627
 Faul+1.568
Neg logit contributions
enthal-2.120
esan-1.870
aeda-1.767
iners-1.742
ocument-1.723
Token?
Token ID30
Feature activation+1.13e+00

Pos logit contributions
idav+0.986
ween+0.923
zeb+0.923
wave+0.904
abase+0.878
Neg logit contributions
enthal-1.192
esan-1.048
aeda-0.989
iners-0.981
ocument-0.963
Token
Token ID198
Feature activation+5.98e-01

Pos logit contributions
enthal+0.898
esan+0.783
aeda+0.733
iners+0.729
ocument+0.716
Neg logit contributions
idav-0.853
ween-0.796
zeb-0.792
wave-0.772
abase-0.756
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
enthal+0.499
esan+0.438
aeda+0.413
iners+0.410
ocument+0.402
Neg logit contributions
idav-0.425
ween-0.398
zeb-0.398
wave-0.390
abase-0.380
TokenJay
Token ID30568
Feature activation-1.05e+01

Pos logit contributions
enthal+0.879
esan+0.752
aeda+0.688
iners+0.687
ROR+0.682
Neg logit contributions
idav-1.119
ween-1.060
zeb-1.048
 Faul-1.035
wave-1.033
Token C
Token ID327
Feature activation-7.66e-01

Pos logit contributions
zeb+3.680
idav+3.672
wave+3.666
 Faul+3.663
ween+3.536
Neg logit contributions
enthal-11.218
iners-10.018
esan-9.988
aeda-9.956
ocument-9.953
Tokenz
Token ID89
Feature activation-1.10e+01

Pos logit contributions
idav+0.204
zeb+0.173
ween+0.171
wave+0.163
abase+0.147
Neg logit contributions
enthal-0.976
esan-0.899
aeda-0.868
iners-0.863
ocument-0.855
Tokenark
Token ID668
Feature activation+1.49e+00

Pos logit contributions
idav+5.549
zeb+5.313
wave+5.193
ween+4.931
abase+4.813
Neg logit contributions
enthal-10.167
esan-9.472
 tremend-9.120
ROR-9.009
ocument-8.975
Tokenowski
Token ID12079
Feature activation-2.21e+00

Pos logit contributions
enthal+0.983
esan+0.830
aeda+0.760
iners+0.756
ocument+0.735
Neg logit contributions
idav-1.318
ween-1.251
zeb-1.243
wave-1.229
 Faul-1.210
Token:
Token ID25
Feature activation+1.26e-01

Pos logit contributions
idav+1.195
zeb+1.139
ween+1.135
wave+1.124
 Faul+1.056
Neg logit contributions
enthal-2.162
esan-1.934
aeda-1.876
iners-1.849
ocument-1.827
Token I
Token ID314
Feature activation+2.19e+00

Pos logit contributions
enthal+0.107
esan+0.094
aeda+0.089
iners+0.088
ocument+0.086
Neg logit contributions
idav-0.089
zeb-0.083
ween-0.082
wave-0.081
abase-0.079
Token would
Token ID561
Feature activation-7.91e-01

Pos logit contributions
enthal+1.819
esan+1.607
iners+1.512
aeda+1.499
ocument+1.468
Neg logit contributions
idav-1.558
zeb-1.452
ween-1.446
wave-1.399
abase-1.375
Token
Token ID141
Feature activation-7.22e+00

Pos logit contributions
enthal+3.065
esan+2.646
aeda+2.462
iners+2.430
ocument+2.402
Neg logit contributions
idav-3.216
zeb-3.032
ween-3.012
abase-2.932
wave-2.912
Token
Token ID227
Feature activation-5.77e-01

Pos logit contributions
idav+4.264
zeb+3.946
wave+3.916
ween+3.901
 Faul+3.765
Neg logit contributions
enthal-6.568
esan-5.907
aeda-5.653
iners-5.602
ROR-5.583
Token
Token ID12466
Feature activation-2.73e-01

Pos logit contributions
idav+0.340
zeb+0.315
ween+0.315
wave+0.307
abase+0.297
Neg logit contributions
enthal-0.550
esan-0.492
aeda-0.467
iners-0.463
ocument-0.458
Token
Token ID121
Feature activation+6.91e-01

Pos logit contributions
idav+0.212
ween+0.200
zeb+0.200
wave+0.196
abase+0.191
Neg logit contributions
enthal-0.210
esan-0.182
aeda-0.171
iners-0.169
ocument-0.166
Tokenа
Token ID16142
Feature activation+2.82e-01

Pos logit contributions
enthal+0.497
esan+0.427
aeda+0.398
iners+0.393
ocument+0.388
Neg logit contributions
idav-0.570
zeb-0.538
ween-0.538
wave-0.530
abase-0.518
Token
Token ID141
Feature activation-1.09e+01

Pos logit contributions
enthal+0.248
esan+0.219
aeda+0.208
iners+0.206
ocument+0.204
Neg logit contributions
idav-0.187
ween-0.175
zeb-0.175
wave-0.170
abase-0.166
Token
Token ID239
Feature activation-2.28e-01

Pos logit contributions
idav+6.438
zeb+5.952
ween+5.912
wave+5.889
abase+5.675
Neg logit contributions
enthal-9.413
esan-8.291
aeda-7.942
ROR-7.841
ocument-7.818
Tokenм
Token ID43108
Feature activation-8.66e-01

Pos logit contributions
idav+0.167
ween+0.157
zeb+0.157
wave+0.154
abase+0.150
Neg logit contributions
enthal-0.184
esan-0.161
aeda-0.152
iners-0.150
ocument-0.148
Tokenн
Token ID22177
Feature activation-2.31e+00

Pos logit contributions
idav+0.678
ween+0.640
zeb+0.640
wave+0.628
abase+0.613
Neg logit contributions
enthal-0.660
esan-0.571
aeda-0.535
iners-0.530
ocument-0.521
Tokenи
Token ID18849
Feature activation-1.90e+00

Pos logit contributions
idav+1.912
zeb+1.816
ween+1.815
wave+1.793
abase+1.744
Neg logit contributions
enthal-1.636
esan-1.407
aeda-1.318
iners-1.295
ocument-1.266
Tokenк
Token ID31583
Feature activation-2.21e-02

Pos logit contributions
idav+1.555
zeb+1.474
ween+1.473
wave+1.454
abase+1.414
Neg logit contributions
enthal-1.378
esan-1.185
aeda-1.111
iners-1.096
ocument-1.075
Token Henry
Token ID8616
Feature activation-4.61e+00

Pos logit contributions
enthal+0.234
esan+0.205
aeda+0.193
iners+0.192
ocument+0.187
Neg logit contributions
idav-0.205
zeb-0.192
ween-0.191
wave-0.187
abase-0.183
Token Pyr
Token ID27958
Feature activation-3.69e+00

Pos logit contributions
idav+3.270
ween+3.131
zeb+3.100
wave+3.089
 Faul+3.042
Neg logit contributions
enthal-3.711
esan-3.247
aeda-3.130
ocument-3.058
iners-3.047
Tokeng
Token ID70
Feature activation-2.92e-01

Pos logit contributions
idav+2.804
zeb+2.667
ween+2.650
wave+2.614
abase+2.528
Neg logit contributions
enthal-2.869
esan-2.490
aeda-2.371
iners-2.321
ocument-2.300
Tokenos
Token ID418
Feature activation-9.75e-01

Pos logit contributions
idav+0.260
zeb+0.247
ween+0.246
wave+0.242
abase+0.238
Neg logit contributions
enthal-0.191
esan-0.162
iners-0.148
aeda-0.148
ocument-0.144
Token has
Token ID468
Feature activation-3.45e-01

Pos logit contributions
idav+0.684
ween+0.641
zeb+0.640
wave+0.629
abase+0.611
Neg logit contributions
enthal-0.822
esan-0.723
aeda-0.680
iners-0.677
ocument-0.664
Token recovered
Token ID11911
Feature activation-1.05e+01

Pos logit contributions
idav+0.253
ween+0.239
zeb+0.238
wave+0.232
abase+0.227
Neg logit contributions
enthal-0.280
esan-0.244
iners-0.229
aeda-0.229
ocument-0.223
Token from
Token ID422
Feature activation-5.05e+00

Pos logit contributions
idav+5.902
zeb+5.692
wave+5.630
 Faul+5.575
ween+5.491
Neg logit contributions
enthal-9.494
esan-8.685
aeda-8.211
ocument-8.110
ROR-7.986
Token injury
Token ID5095
Feature activation-2.89e+00

Pos logit contributions
idav+3.382
ween+3.171
zeb+3.166
wave+3.160
 Faul+3.094
Neg logit contributions
enthal-4.294
esan-3.825
aeda-3.626
iners-3.564
ocument-3.556
Token.
Token ID13
Feature activation+9.50e-02

Pos logit contributions
idav+1.870
ween+1.752
zeb+1.750
wave+1.729
 Faul+1.662
Neg logit contributions
enthal-2.568
esan-2.272
aeda-2.169
iners-2.140
ROR-2.109
Token
Token ID198
Feature activation-3.02e-01

Pos logit contributions
enthal+0.077
esan+0.067
aeda+0.063
iners+0.062
ROR+0.061
Neg logit contributions
idav-0.070
zeb-0.066
ween-0.066
wave-0.064
abase-0.063
Token
Token ID198
Feature activation+3.80e-01

Pos logit contributions
idav+0.209
ween+0.197
zeb+0.197
wave+0.194
abase+0.187
Neg logit contributions
enthal-0.256
esan-0.225
aeda-0.213
iners-0.211
ocument-0.208