TOP ACTIVATIONS
MAX = 2.837

he s a sod om ite !
to sleep in a U sonian home , just 45 minutes
/ File photo TP X IMAGES OF THE DAY ) Chris
settlements south of Jerusalem to Heb ron , bis ect ing
and click on the Settings Icon in the top left corner
J . stands as the cab ler s most
Part 6 [ edit ] It was a
I military formations [ edit ] Women volunteers served
s attorney Sal Stra zz ull o said ,
Foundation : " R oc kefeller Family Fund , Inc .:
F acts [ edit ] At the California
; the other the Ne veh Shal om massacre of September
The Two Towers [ edit ] Or cs sent
: 05 35 z 1 GER ON IM O T OC
is connected to the Muslim Brotherhood , that Marco Rubio is
like you re gre asing politicians for fav ours
month have made a significant profit . Of course
Other media [ edit ] Video games [
that they will make a profit , and they will try
and has been key to helping Boston to a 14 -

MIN ACTIVATIONS
MIN = -2.624

Miami Dolphins : DE Cameron Wake Contract : A
beating alcohol or avoiding d eng ue fever .
the imminent demise of the wind power production tax credit ),
ev ic " ( m att - EE - oh -
he said . <|endoftext|> Meg ach urch founder Rev . Ted
enable Broad band Connection ( Co ax ) under the list
( tem perature - am pl ifying ) and negative (
between her and manager Michelle Po ague . At 8 :
runoff against Rep . Bill Cassidy , standing
Ste lla - san collapsed ?」 " Yes .
to ." B att iat o said The World
called absurd and fear m ong ering . The
the smoker , like k ung p ao cor ned beef
can do to combat this wave of misinformation is to talk
basement of concrete . Ma ori affairs and state housing did
eaten her mother 's d ung to acquire the gut microbes
order to synchron ize D DoS mitigation perfectly with the changing
), Has i ( M ong ol ian form of Tang
title . B ung ie 's contract with Activision
players . <|endoftext|> A D DoS Gap occurs whenever D DoS

INTERVAL 1.472 - 2.837
CONTAINS 0.388%

mainstream UK media and the diss ident Real News Network ,
because of their age and you had some very interesting things
adjacent to the Journal Square PATH station as a location for
Sub prime market getting hit hard . The
it out , causing major scar ring and deform ity ,

INTERVAL 0.106 - 1.472
CONTAINS 38.434%

the latest Jesuit institution to offer the benefits to the same
tough question , and probably not a fair one .
huge conglomerate corporations have dominated political institutions and the mass media
the rest at 1 percent interest over the next 25 years
it was seen as contributing to the success or defeat of

INTERVAL -1.259 - 0.106
CONTAINS 60.277%

a reasonable waiting period before the app lets you check into
Opt ronics TN Film @ 144 Hz ( OD = Normal
attitude meant he would not continue his flying career beyond his
are still an estimated 250 such giant freshwater crocod iles still
visit of B ourn emouth to The Hawth orns .

INTERVAL -2.624 - -1.259
CONTAINS 0.901%

that might be impacted ? Well , Shell s
, d ) C - 14 Years B . P .
freedom to live in this country and honour it , so
hole . Start by showing him how to bring the kn
How about after a year ? How about when something needs
Token he
Token ID339
Feature activation+1.20e-01

Pos logit contributions
deen+1.841
…………+1.521
……………………+1.487
 sod+1.382
sth+1.359
Neg logit contributions
rast-1.884
iar-1.509
oise-1.483
 relegation-1.459
ouver-1.436
Token
Token ID447
Feature activation-1.74e-01

Pos logit contributions
deen+0.345
…………+0.287
……………………+0.282
sth+0.264
 sod+0.263
Neg logit contributions
rast-0.285
iar-0.219
 relegation-0.215
oise-0.214
assic-0.208
Token
Token ID247
Feature activation+2.86e-01

Pos logit contributions
rast+0.582
iar+0.491
 relegation+0.485
oise+0.483
orth+0.475
Neg logit contributions
deen-0.333
…………-0.250
……………………-0.247
sth-0.215
 sod-0.209
Tokens
Token ID82
Feature activation+2.14e-01

Pos logit contributions
deen+0.683
…………+0.538
……………………+0.530
sth+0.493
hest+0.480
Neg logit contributions
rast-0.821
 relegation-0.664
iar-0.664
oise-0.654
assic-0.640
Token a
Token ID257
Feature activation+4.24e-01

Pos logit contributions
deen+0.576
…………+0.471
……………………+0.465
sth+0.429
 sod+0.429
Neg logit contributions
rast-0.554
iar-0.438
oise-0.430
 relegation-0.425
assic-0.415
Token sod
Token ID32581
Feature activation+2.84e+00

Pos logit contributions
deen+1.151
…………+0.945
……………………+0.936
 sod+0.871
sth+0.859
Neg logit contributions
rast-1.079
iar-0.854
oise-0.835
 relegation-0.822
assic-0.810
Tokenom
Token ID296
Feature activation+3.33e-01

Pos logit contributions
deen+5.883
……………………+4.743
…………+4.729
 sod+4.485
hest+4.337
Neg logit contributions
rast-7.966
 relegation-6.922
 failings-6.750
ruciating-6.700
 cohesion-6.692
Tokenite
Token ID578
Feature activation+4.14e-01

Pos logit contributions
deen+0.775
…………+0.606
……………………+0.600
 sod+0.543
sth+0.542
Neg logit contributions
rast-0.981
iar-0.796
 relegation-0.791
oise-0.785
assic-0.766
Token!
Token ID0
Feature activation+7.16e-01

Pos logit contributions
deen+1.052
…………+0.854
……………………+0.841
sth+0.767
 sod+0.763
Neg logit contributions
rast-1.125
iar-0.907
 relegation-0.883
oise-0.882
assic-0.866
Token
Token ID447
Feature activation-9.01e-02

Pos logit contributions
deen+1.579
…………+1.239
……………………+1.226
sth+1.094
 sod+1.080
Neg logit contributions
rast-2.168
iar-1.798
 relegation-1.757
oise-1.757
assic-1.734
Token
Token ID251
Feature activation+1.89e-03

Pos logit contributions
rast+0.256
iar+0.212
 relegation+0.206
oise+0.205
assic+0.201
Neg logit contributions
deen-0.216
…………-0.173
……………………-0.170
sth-0.156
 sod-0.153
Token to
Token ID284
Feature activation-3.76e-01

Pos logit contributions
rast+1.625
iar+1.267
oise+1.228
 relegation+1.223
orth+1.187
Neg logit contributions
deen-1.912
…………-1.548
……………………-1.533
sth-1.439
hest-1.426
Token sleep
Token ID3993
Feature activation+1.25e-01

Pos logit contributions
rast+1.042
iar+0.842
oise+0.821
 relegation+0.818
orth+0.797
Neg logit contributions
deen-0.940
…………-0.741
……………………-0.733
sth-0.679
hest-0.670
Token in
Token ID287
Feature activation-4.88e-01

Pos logit contributions
deen+0.328
…………+0.264
……………………+0.260
sth+0.241
hest+0.239
Neg logit contributions
rast-0.334
iar-0.266
oise-0.261
 relegation-0.259
assic-0.253
Token a
Token ID257
Feature activation-4.86e-01

Pos logit contributions
rast+1.306
iar+1.045
oise+1.021
 relegation+1.015
orth+0.988
Neg logit contributions
deen-1.268
…………-1.013
……………………-1.002
sth-0.930
hest-0.918
Token U
Token ID471
Feature activation+3.90e-01

Pos logit contributions
rast+1.220
iar+0.960
oise+0.935
 relegation+0.928
orth+0.902
Neg logit contributions
deen-1.345
…………-1.092
……………………-1.082
sth-1.008
 sod-0.997
Tokensonian
Token ID35202
Feature activation+2.82e+00

Pos logit contributions
deen+1.079
…………+0.870
……………………+0.862
sth+0.815
hest+0.799
Neg logit contributions
rast-0.976
iar-0.770
oise-0.757
 relegation-0.755
assic-0.725
Token home
Token ID1363
Feature activation+1.39e+00

Pos logit contributions
deen+7.118
…………+5.969
……………………+5.858
sth+5.431
 sod+5.286
Neg logit contributions
rast-7.075
iar-5.567
oise-5.518
 relegation-5.469
assic-5.351
Token,
Token ID11
Feature activation-9.65e-02

Pos logit contributions
deen+3.455
…………+2.832
……………………+2.780
sth+2.544
 sod+2.510
Neg logit contributions
rast-3.797
iar-3.037
 relegation-2.996
oise-2.990
assic-2.939
Token just
Token ID655
Feature activation+1.43e-01

Pos logit contributions
rast+0.259
iar+0.208
oise+0.203
 relegation+0.201
orth+0.196
Neg logit contributions
deen-0.250
…………-0.200
……………………-0.198
sth-0.183
hest-0.181
Token 45
Token ID4153
Feature activation-1.26e-01

Pos logit contributions
deen+0.371
…………+0.299
……………………+0.295
sth+0.273
 sod+0.272
Neg logit contributions
rast-0.382
iar-0.305
oise-0.299
 relegation-0.295
assic-0.288
Token minutes
Token ID2431
Feature activation+6.15e-01

Pos logit contributions
rast+0.324
iar+0.257
oise+0.251
 relegation+0.251
assic+0.243
Neg logit contributions
deen-0.337
…………-0.272
……………………-0.270
sth-0.251
hest-0.248
Token/
Token ID14
Feature activation-7.26e-01

Pos logit contributions
deen+1.784
…………+1.426
……………………+1.412
sth+1.316
hest+1.298
Neg logit contributions
rast-1.774
iar-1.415
oise-1.383
 relegation-1.377
assic-1.336
TokenFile
Token ID8979
Feature activation+7.09e-01

Pos logit contributions
rast+2.116
iar+1.727
oise+1.692
 relegation+1.685
orth+1.643
Neg logit contributions
deen-1.715
…………-1.333
……………………-1.317
sth-1.212
hest-1.194
Token photo
Token ID4590
Feature activation+5.39e-01

Pos logit contributions
deen+1.693
…………+1.296
……………………+1.291
sth+1.183
hest+1.171
Neg logit contributions
rast-2.044
iar-1.669
oise-1.646
 relegation-1.635
assic-1.592
Token TP
Token ID24525
Feature activation-4.95e-01

Pos logit contributions
deen+1.519
…………+1.237
……………………+1.224
sth+1.145
hest+1.133
Neg logit contributions
rast-1.326
iar-1.036
oise-1.009
 relegation-1.004
orth-0.974
TokenX
Token ID55
Feature activation-4.82e-01

Pos logit contributions
rast+1.549
iar+1.286
oise+1.260
 relegation+1.255
orth+1.229
Neg logit contributions
deen-1.065
…………-0.803
……………………-0.792
sth-0.720
hest-0.709
Token IMAGES
Token ID45325
Feature activation+2.75e+00

Pos logit contributions
rast+1.332
iar+1.075
oise+1.050
 relegation+1.046
orth+1.019
Neg logit contributions
deen-1.209
…………-0.956
……………………-0.945
sth-0.874
hest-0.863
Token OF
Token ID3963
Feature activation+7.15e-01

Pos logit contributions
deen+4.412
…………+3.191
……………………+3.133
sth+2.619
hest+2.570
Neg logit contributions
rast-9.797
oise-8.244
iar-8.216
 relegation-8.193
ruciating-8.161
Token THE
Token ID3336
Feature activation+4.17e-01

Pos logit contributions
deen+1.559
…………+1.198
……………………+1.178
sth+1.069
hest+1.054
Neg logit contributions
rast-2.204
iar-1.822
oise-1.799
 relegation-1.775
assic-1.748
Token DAY
Token ID24644
Feature activation+7.57e-01

Pos logit contributions
deen+1.061
…………+0.857
……………………+0.846
sth+0.769
 sod+0.765
Neg logit contributions
rast-1.125
iar-0.909
oise-0.893
 relegation-0.884
assic-0.877
Token)
Token ID8
Feature activation+4.41e-01

Pos logit contributions
deen+1.977
…………+1.586
……………………+1.571
sth+1.452
hest+1.432
Neg logit contributions
rast-1.988
iar-1.590
oise-1.570
 relegation-1.545
assic-1.511
Token Chris
Token ID5180
Feature activation-4.76e-01

Pos logit contributions
deen+1.149
…………+0.933
……………………+0.923
sth+0.842
hest+0.841
Neg logit contributions
rast-1.167
iar-0.931
oise-0.907
 relegation-0.903
orth-0.883
Token settlements
Token ID18573
Feature activation+7.14e-01

Pos logit contributions
rast+0.627
iar+0.496
oise+0.481
 relegation+0.477
assic+0.467
Neg logit contributions
deen-0.696
…………-0.565
……………………-0.560
sth-0.522
 sod-0.518
Token south
Token ID5366
Feature activation-4.20e-01

Pos logit contributions
deen+1.823
…………+1.468
……………………+1.451
sth+1.341
hest+1.325
Neg logit contributions
rast-1.921
iar-1.551
oise-1.519
 relegation-1.507
assic-1.477
Token of
Token ID286
Feature activation+2.30e-01

Pos logit contributions
rast+1.019
iar+0.795
oise+0.773
 relegation+0.769
orth+0.746
Neg logit contributions
deen-1.196
…………-0.975
……………………-0.966
sth-0.905
hest-0.895
Token Jerusalem
Token ID10843
Feature activation+2.63e-01

Pos logit contributions
deen+0.542
…………+0.420
……………………+0.416
sth+0.379
 sod+0.374
Neg logit contributions
rast-0.671
iar-0.550
oise-0.537
 relegation-0.536
orth-0.525
Token to
Token ID284
Feature activation+2.36e-01

Pos logit contributions
deen+0.693
…………+0.557
……………………+0.550
sth+0.511
hest+0.504
Neg logit contributions
rast-0.694
iar-0.555
 relegation-0.542
oise-0.542
assic-0.525
Token Heb
Token ID27030
Feature activation+2.73e+00

Pos logit contributions
deen+0.582
…………+0.457
……………………+0.451
sth+0.416
 sod+0.411
Neg logit contributions
rast-0.663
iar-0.540
oise-0.526
 relegation-0.524
orth-0.512
Tokenron
Token ID1313
Feature activation+1.13e+00

Pos logit contributions
deen+5.051
…………+3.125
……………………+3.105
hest+2.998
sth+2.923
Neg logit contributions
rast-8.685
 relegation-7.764
ーティ-7.705
 failings-7.598
 evolves-7.561
Token,
Token ID11
Feature activation+5.44e-02

Pos logit contributions
deen+2.788
…………+2.205
……………………+2.163
sth+1.985
 sod+1.959
Neg logit contributions
rast-3.139
iar-2.560
 relegation-2.519
oise-2.486
assic-2.457
Token bis
Token ID47457
Feature activation+1.95e+00

Pos logit contributions
deen+0.142
…………+0.113
……………………+0.112
sth+0.103
 sod+0.103
Neg logit contributions
rast-0.145
iar-0.117
oise-0.114
 relegation-0.113
assic-0.110
Tokenect
Token ID478
Feature activation+3.01e-01

Pos logit contributions
deen+3.983
…………+2.927
……………………+2.831
sth+2.747
hest+2.740
Neg logit contributions
rast-5.991
iar-5.066
 relegation-5.027
oise-4.979
 failings-4.812
Tokening
Token ID278
Feature activation+6.15e-01

Pos logit contributions
deen+0.888
…………+0.724
……………………+0.718
sth+0.675
 sod+0.671
Neg logit contributions
rast-0.697
iar-0.539
 relegation-0.523
oise-0.522
assic-0.510
Token and
Token ID290
Feature activation+6.93e-02

Pos logit contributions
deen+0.431
…………+0.344
……………………+0.342
sth+0.316
hest+0.312
Neg logit contributions
rast-0.433
iar-0.347
oise-0.339
 relegation-0.338
orth-0.328
Token click
Token ID3904
Feature activation+1.04e+00

Pos logit contributions
deen+0.173
…………+0.138
……………………+0.136
sth+0.125
 sod+0.124
Neg logit contributions
rast-0.192
iar-0.155
oise-0.152
 relegation-0.151
assic-0.147
Token on
Token ID319
Feature activation+2.33e-01

Pos logit contributions
deen+2.562
…………+2.072
……………………+2.042
sth+1.856
hest+1.838
Neg logit contributions
rast-2.907
iar-2.306
oise-2.271
 relegation-2.265
assic-2.240
Token the
Token ID262
Feature activation+2.13e-01

Pos logit contributions
deen+0.584
…………+0.466
……………………+0.461
sth+0.424
hest+0.419
Neg logit contributions
rast-0.644
iar-0.517
oise-0.506
 relegation-0.503
assic-0.492
Token Settings
Token ID16163
Feature activation+1.12e+00

Pos logit contributions
deen+0.556
…………+0.449
……………………+0.444
sth+0.409
 sod+0.406
Neg logit contributions
rast-0.570
iar-0.452
oise-0.442
 relegation-0.438
assic-0.429
Token Icon
Token ID26544
Feature activation+2.73e+00

Pos logit contributions
deen+2.757
…………+2.274
……………………+2.236
sth+2.003
 sod+2.003
Neg logit contributions
rast-3.052
iar-2.453
oise-2.401
 relegation-2.385
assic-2.374
Token in
Token ID287
Feature activation+2.54e-01

Pos logit contributions
deen+6.263
…………+5.178
……………………+5.076
sth+4.493
 sod+4.428
Neg logit contributions
rast-7.404
iar-6.019
assic-5.963
 relegation-5.943
oise-5.915
Token the
Token ID262
Feature activation+2.78e-01

Pos logit contributions
deen+0.616
…………+0.486
……………………+0.481
sth+0.441
hest+0.437
Neg logit contributions
rast-0.720
iar-0.584
oise-0.571
 relegation-0.569
assic-0.556
Token top
Token ID1353
Feature activation-2.79e-01

Pos logit contributions
deen+0.787
…………+0.646
……………………+0.640
sth+0.594
 sod+0.592
Neg logit contributions
rast-0.676
iar-0.529
oise-0.514
 relegation-0.507
assic-0.498
Token left
Token ID1364
Feature activation+6.44e-01

Pos logit contributions
rast+0.778
iar+0.629
oise+0.616
 relegation+0.612
orth+0.596
Neg logit contributions
deen-0.693
…………-0.549
……………………-0.543
sth-0.500
hest-0.495
Token corner
Token ID5228
Feature activation-3.81e-02

Pos logit contributions
deen+1.724
…………+1.412
……………………+1.402
sth+1.277
hest+1.275
Neg logit contributions
rast-1.648
iar-1.316
oise-1.283
 relegation-1.268
assic-1.240
TokenJ
Token ID41
Feature activation+5.84e-01

Pos logit contributions
deen+1.844
…………+1.391
……………………+1.363
sth+1.198
 sod+1.177
Neg logit contributions
rast-3.299
iar-2.808
 relegation-2.783
oise-2.768
assic-2.708
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
deen+1.487
…………+1.180
……………………+1.167
sth+1.081
hest+1.068
Neg logit contributions
rast-1.593
iar-1.282
oise-1.252
 relegation-1.247
orth-1.213
Token stands
Token ID6296
Feature activation+1.11e+00

Pos logit contributions
deen+0.370
…………+0.304
……………………+0.301
sth+0.280
 sod+0.280
Neg logit contributions
rast-0.311
iar-0.242
oise-0.237
 relegation-0.235
orth-0.227
Token as
Token ID355
Feature activation-3.17e-01

Pos logit contributions
deen+2.840
…………+2.305
……………………+2.284
 sod+2.131
hest+2.105
Neg logit contributions
rast-2.966
iar-2.328
oise-2.278
 relegation-2.237
ruciating-2.234
Token the
Token ID262
Feature activation-1.69e-01

Pos logit contributions
rast+0.843
iar+0.674
oise+0.657
 relegation+0.655
orth+0.637
Neg logit contributions
deen-0.831
…………-0.663
……………………-0.656
sth-0.610
hest-0.602
Token cab
Token ID16212
Feature activation+2.64e+00

Pos logit contributions
rast+0.408
iar+0.317
oise+0.311
 relegation+0.307
orth+0.300
Neg logit contributions
deen-0.482
…………-0.394
……………………-0.391
sth-0.365
hest-0.364
Tokenler
Token ID1754
Feature activation-3.70e-02

Pos logit contributions
deen+4.862
…………+3.647
……………………+3.593
hest+3.478
 sod+3.286
Neg logit contributions
rast-8.352
 relegation-7.046
iar-6.980
velength-6.937
assic-6.863
Token
Token ID447
Feature activation+3.23e-02

Pos logit contributions
rast+0.088
iar+0.068
oise+0.066
 relegation+0.066
assic+0.064
Neg logit contributions
deen-0.107
…………-0.087
……………………-0.087
sth-0.082
hest-0.081
Token
Token ID247
Feature activation+2.10e-01

Pos logit contributions
deen+0.068
…………+0.051
……………………+0.050
sth+0.045
hest+0.044
Neg logit contributions
rast-0.103
iar-0.086
 relegation-0.084
oise-0.084
orth-0.083
Tokens
Token ID82
Feature activation+4.44e-02

Pos logit contributions
deen+0.556
…………+0.444
……………………+0.439
sth+0.414
hest+0.409
Neg logit contributions
rast-0.553
iar-0.439
 relegation-0.429
oise-0.429
assic-0.415
Token most
Token ID749
Feature activation+2.80e-01

Pos logit contributions
deen+0.128
…………+0.105
……………………+0.104
hest+0.098
sth+0.097
Neg logit contributions
rast-0.106
iar-0.082
oise-0.080
 relegation-0.079
orth-0.077
Token
Token ID198
Feature activation+2.84e-01

Pos logit contributions
deen+0.768
…………+0.626
……………………+0.618
sth+0.566
 sod+0.558
Neg logit contributions
rast-0.824
iar-0.666
 relegation-0.659
oise-0.648
assic-0.645
TokenPart
Token ID7841
Feature activation-1.32e+00

Pos logit contributions
deen+0.682
…………+0.552
……………………+0.545
sth+0.491
hest+0.481
Neg logit contributions
rast-0.813
iar-0.663
 relegation-0.657
oise-0.648
assic-0.640
Token 6
Token ID718
Feature activation+8.58e-02

Pos logit contributions
rast+3.739
iar+3.037
oise+2.967
 relegation+2.950
orth+2.879
Neg logit contributions
deen-3.242
…………-2.542
……………………-2.513
sth-2.322
hest-2.288
Token [
Token ID685
Feature activation+3.32e-01

Pos logit contributions
deen+0.223
…………+0.180
……………………+0.177
sth+0.163
hest+0.161
Neg logit contributions
rast-0.230
iar-0.183
oise-0.179
 relegation-0.178
assic-0.174
Token edit
Token ID4370
Feature activation+6.17e-01

Pos logit contributions
deen+0.845
…………+0.685
……………………+0.674
sth+0.622
hest+0.606
Neg logit contributions
rast-0.905
iar-0.727
 relegation-0.711
oise-0.708
assic-0.695
Token ]
Token ID2361
Feature activation+2.63e+00

Pos logit contributions
deen+1.282
…………+0.974
……………………+0.953
sth+0.853
hest+0.843
Neg logit contributions
rast-1.970
iar-1.634
 relegation-1.599
oise-1.589
assic-1.576
Token
Token ID198
Feature activation+1.66e-01

Pos logit contributions
deen+5.607
…………+4.783
……………………+4.660
 sod+4.025
sth+3.983
Neg logit contributions
rast-7.597
ruciating-6.520
vertisement-6.318
assic-6.286
ouver-6.273
Token
Token ID198
Feature activation+2.08e-01

Pos logit contributions
deen+0.422
…………+0.344
……………………+0.339
sth+0.312
 sod+0.308
Neg logit contributions
rast-0.446
iar-0.359
 relegation-0.354
oise-0.349
assic-0.346
TokenIt
Token ID1026
Feature activation+2.92e-01

Pos logit contributions
deen+0.505
…………+0.409
……………………+0.403
sth+0.364
hest+0.357
Neg logit contributions
rast-0.591
iar-0.479
 relegation-0.476
oise-0.468
assic-0.462
Token was
Token ID373
Feature activation-1.55e-01

Pos logit contributions
deen+0.891
…………+0.740
……………………+0.728
sth+0.685
hest+0.679
Neg logit contributions
rast-0.655
iar-0.489
 relegation-0.488
oise-0.475
assic-0.474
Token a
Token ID257
Feature activation+1.45e-01

Pos logit contributions
rast+0.396
iar+0.311
oise+0.304
 relegation+0.299
assic+0.295
Neg logit contributions
deen-0.424
…………-0.348
……………………-0.342
sth-0.315
 sod-0.313
TokenI
Token ID40
Feature activation+2.16e-01

Pos logit contributions
deen+2.315
…………+1.843
……………………+1.812
hest+1.693
sth+1.691
Neg logit contributions
rast-2.789
iar-2.228
oise-2.222
 relegation-2.188
assic-2.167
Token military
Token ID2422
Feature activation+6.68e-01

Pos logit contributions
deen+0.602
…………+0.488
……………………+0.483
sth+0.452
 sod+0.447
Neg logit contributions
rast-0.540
iar-0.423
oise-0.414
 relegation-0.408
assic-0.400
Token formations
Token ID30648
Feature activation+1.01e+00

Pos logit contributions
deen+1.832
…………+1.479
……………………+1.456
 sod+1.376
sth+1.363
Neg logit contributions
rast-1.681
iar-1.317
oise-1.294
assic-1.258
 relegation-1.247
Token [
Token ID685
Feature activation+5.19e-01

Pos logit contributions
deen+2.690
…………+2.160
……………………+2.129
 sod+1.983
sth+1.968
Neg logit contributions
rast-2.615
iar-2.077
oise-2.021
 relegation-1.988
assic-1.978
Token edit
Token ID4370
Feature activation+8.16e-01

Pos logit contributions
deen+1.301
…………+1.033
……………………+1.020
sth+0.946
 sod+0.926
Neg logit contributions
rast-1.433
iar-1.158
 relegation-1.134
oise-1.129
assic-1.109
Token ]
Token ID2361
Feature activation+2.62e+00

Pos logit contributions
deen+1.610
…………+1.214
……………………+1.199
 sod+1.057
sth+1.049
Neg logit contributions
rast-2.672
iar-2.222
 relegation-2.185
ruciating-2.181
assic-2.180
Token
Token ID198
Feature activation+2.53e-01

Pos logit contributions
deen+5.560
…………+4.635
……………………+4.551
 sod+4.008
sth+3.926
Neg logit contributions
rast-7.542
ruciating-6.509
assic-6.294
vertisement-6.289
ouver-6.270
Token
Token ID198
Feature activation+2.50e-01

Pos logit contributions
deen+0.643
…………+0.521
……………………+0.515
sth+0.473
 sod+0.469
Neg logit contributions
rast-0.683
iar-0.551
 relegation-0.542
oise-0.536
assic-0.531
TokenWomen
Token ID18495
Feature activation-5.16e-01

Pos logit contributions
deen+0.613
…………+0.487
……………………+0.480
sth+0.442
hest+0.435
Neg logit contributions
rast-0.705
iar-0.572
 relegation-0.562
oise-0.559
assic-0.545
Token volunteers
Token ID11661
Feature activation-2.18e-01

Pos logit contributions
rast+1.304
iar+1.028
oise+1.001
 relegation+0.996
orth+0.968
Neg logit contributions
deen-1.418
…………-1.147
……………………-1.134
sth-1.059
hest-1.047
Token served
Token ID4983
Feature activation+4.89e-01

Pos logit contributions
rast+0.567
iar+0.449
oise+0.438
 relegation+0.434
assic+0.424
Neg logit contributions
deen-0.588
…………-0.473
……………………-0.468
sth-0.434
hest-0.430
Token
Token ID247
Feature activation+4.11e-01

Pos logit contributions
deen+0.645
…………+0.508
……………………+0.502
sth+0.463
hest+0.455
Neg logit contributions
rast-0.763
iar-0.621
 relegation-0.608
oise-0.607
orth-0.590
Tokens
Token ID82
Feature activation+1.14e-01

Pos logit contributions
deen+1.181
…………+0.960
……………………+0.951
sth+0.900
hest+0.882
Neg logit contributions
rast-0.986
iar-0.763
 relegation-0.756
oise-0.748
assic-0.721
Token attorney
Token ID6136
Feature activation+3.18e-01

Pos logit contributions
deen+0.318
…………+0.260
……………………+0.258
sth+0.240
hest+0.238
Neg logit contributions
rast-0.281
iar-0.220
oise-0.214
 relegation-0.212
orth-0.206
Token Sal
Token ID4849
Feature activation+7.09e-01

Pos logit contributions
deen+0.874
…………+0.713
……………………+0.703
sth+0.652
 sod+0.646
Neg logit contributions
rast-0.803
iar-0.628
oise-0.622
 relegation-0.618
assic-0.598
Token Stra
Token ID15195
Feature activation-4.71e-01

Pos logit contributions
deen+1.935
…………+1.530
……………………+1.521
sth+1.430
hest+1.420
Neg logit contributions
rast-1.785
iar-1.406
 relegation-1.400
oise-1.369
assic-1.342
Tokenzz
Token ID3019
Feature activation+2.60e+00

Pos logit contributions
rast+1.265
iar+1.013
oise+0.994
 relegation+0.993
orth+0.958
Neg logit contributions
deen-1.222
…………-0.973
……………………-0.962
sth-0.899
hest-0.889
Tokenull
Token ID724
Feature activation-4.62e-01

Pos logit contributions
deen+7.759
…………+6.232
……………………+6.124
sth+5.987
hest+5.934
Neg logit contributions
rast-5.438
ruciating-4.220
 relegation-4.181
velength-4.028
oise-4.019
Tokeno
Token ID78
Feature activation+3.32e-02

Pos logit contributions
rast+1.083
iar+0.819
 relegation+0.815
oise+0.808
orth+0.781
Neg logit contributions
deen-1.359
…………-1.114
……………………-1.103
sth-1.038
hest-1.025
Token said
Token ID531
Feature activation+3.12e-01

Pos logit contributions
deen+0.100
…………+0.083
……………………+0.082
sth+0.077
hest+0.076
Neg logit contributions
rast-0.075
iar-0.057
 relegation-0.056
oise-0.056
orth-0.053
Token,
Token ID11
Feature activation+2.14e-01

Pos logit contributions
deen+0.809
…………+0.651
……………………+0.647
sth+0.599
hest+0.588
Neg logit contributions
rast-0.834
iar-0.667
oise-0.658
 relegation-0.647
orth-0.632
Token
Token ID564
Feature activation+2.23e-01

Pos logit contributions
deen+0.504
…………+0.394
……………………+0.389
sth+0.357
 sod+0.351
Neg logit contributions
rast-0.622
iar-0.509
oise-0.500
 relegation-0.497
orth-0.484
Token Foundation
Token ID5693
Feature activation+2.23e-01

Pos logit contributions
rast+2.431
iar+1.988
oise+1.953
 relegation+1.947
assic+1.905
Neg logit contributions
deen-1.833
…………-1.420
……………………-1.405
sth-1.279
hest-1.257
Token:
Token ID25
Feature activation-9.08e-02

Pos logit contributions
deen+0.579
…………+0.461
……………………+0.456
sth+0.424
hest+0.419
Neg logit contributions
rast-0.596
iar-0.477
oise-0.466
 relegation-0.464
orth-0.451
Token "
Token ID366
Feature activation+2.64e-01

Pos logit contributions
rast+0.242
iar+0.193
oise+0.189
 relegation+0.188
orth+0.183
Neg logit contributions
deen-0.238
…………-0.189
……………………-0.187
sth-0.174
hest-0.172
TokenR
Token ID49
Feature activation+6.12e-01

Pos logit contributions
deen+0.705
…………+0.577
……………………+0.569
sth+0.524
hest+0.521
Neg logit contributions
rast-0.683
iar-0.539
 relegation-0.530
oise-0.525
assic-0.510
Tokenoc
Token ID420
Feature activation+4.23e-01

Pos logit contributions
deen+1.650
…………+1.342
……………………+1.331
sth+1.231
hest+1.226
Neg logit contributions
rast-1.557
iar-1.231
 relegation-1.210
oise-1.202
orth-1.158
Tokenkefeller
Token ID31424
Feature activation+2.60e+00

Pos logit contributions
deen+0.431
…………+0.207
……………………+0.203
hest+0.156
sth+0.149
Neg logit contributions
rast-1.791
iar-1.561
 relegation-1.556
oise-1.542
orth-1.515
Token Family
Token ID7884
Feature activation+1.22e+00

Pos logit contributions
deen+4.819
…………+3.617
……………………+3.613
hest+3.144
sth+3.127
Neg logit contributions
rast-8.506
iar-7.071
oise-7.064
 relegation-6.973
assic-6.859
Token Fund
Token ID7557
Feature activation-5.62e-02

Pos logit contributions
deen+4.036
…………+3.453
……………………+3.442
hest+3.229
sth+3.220
Neg logit contributions
rast-2.352
iar-1.677
 relegation-1.617
oise-1.612
assic-1.560
Token,
Token ID11
Feature activation+4.02e-02

Pos logit contributions
rast+0.147
iar+0.117
oise+0.114
 relegation+0.114
orth+0.111
Neg logit contributions
deen-0.150
…………-0.120
……………………-0.118
sth-0.110
hest-0.109
Token Inc
Token ID3457
Feature activation-1.06e-02

Pos logit contributions
deen+0.095
…………+0.073
……………………+0.073
sth+0.067
hest+0.066
Neg logit contributions
rast-0.117
iar-0.096
oise-0.094
 relegation-0.093
orth-0.091
Token.:
Token ID11207
Feature activation+1.49e-01

Pos logit contributions
rast+0.032
iar+0.026
oise+0.026
 relegation+0.026
orth+0.025
Neg logit contributions
deen-0.024
…………-0.018
……………………-0.018
sth-0.017
hest-0.016
Token
Token ID198
Feature activation-2.75e-01

Pos logit contributions
rast+1.088
iar+0.867
oise+0.845
 relegation+0.844
assic+0.820
Neg logit contributions
deen-1.106
…………-0.891
……………………-0.882
sth-0.819
hest-0.809
TokenF
Token ID37
Feature activation+2.64e-02

Pos logit contributions
rast+0.789
iar+0.644
 relegation+0.632
oise+0.630
orth+0.611
Neg logit contributions
deen-0.659
…………-0.518
……………………-0.512
sth-0.470
hest-0.463
Tokenacts
Token ID8656
Feature activation-4.26e-02

Pos logit contributions
deen+0.072
…………+0.058
……………………+0.057
sth+0.053
hest+0.053
Neg logit contributions
rast-0.067
iar-0.053
oise-0.052
 relegation-0.052
assic-0.050
Token [
Token ID685
Feature activation+4.19e-01

Pos logit contributions
rast+0.111
iar+0.088
oise+0.086
 relegation+0.086
assic+0.083
Neg logit contributions
deen-0.114
…………-0.092
……………………-0.091
sth-0.084
 sod-0.083
Token edit
Token ID4370
Feature activation+7.86e-01

Pos logit contributions
deen+1.101
…………+0.887
……………………+0.883
sth+0.822
 sod+0.797
Neg logit contributions
rast-1.101
iar-0.878
 relegation-0.866
oise-0.862
assic-0.839
Token ]
Token ID2361
Feature activation+2.54e+00

Pos logit contributions
deen+1.544
…………+1.158
……………………+1.145
 sod+1.009
sth+1.004
Neg logit contributions
rast-2.590
iar-2.154
 relegation-2.117
ruciating-2.111
oise-2.111
Token
Token ID198
Feature activation-2.29e-01

Pos logit contributions
deen+5.271
…………+4.366
……………………+4.350
 sod+3.747
sth+3.734
Neg logit contributions
rast-7.410
ruciating-6.380
assic-6.191
 relegation-6.175
ouver-6.150
Token
Token ID198
Feature activation-1.26e-01

Pos logit contributions
rast+0.606
iar+0.484
 relegation+0.474
oise+0.472
assic+0.462
Neg logit contributions
deen-0.600
…………-0.484
……………………-0.479
sth-0.443
hest-0.438
TokenAt
Token ID2953
Feature activation+1.52e-01

Pos logit contributions
rast+0.356
iar+0.289
 relegation+0.284
oise+0.283
assic+0.274
Neg logit contributions
deen-0.308
…………-0.244
……………………-0.242
sth-0.222
hest-0.218
Token the
Token ID262
Feature activation+1.98e-01

Pos logit contributions
deen+0.405
…………+0.326
……………………+0.323
sth+0.302
 sod+0.299
Neg logit contributions
rast-0.395
iar-0.316
oise-0.309
 relegation-0.305
assic-0.302
Token California
Token ID3442
Feature activation+7.48e-01

Pos logit contributions
deen+0.557
…………+0.454
……………………+0.450
sth+0.422
 sod+0.420
Neg logit contributions
rast-0.483
iar-0.381
oise-0.369
 relegation-0.363
orth-0.355
Token;
Token ID26
Feature activation-1.13e-01

Pos logit contributions
deen+1.636
…………+1.315
……………………+1.288
 sod+1.189
sth+1.189
Neg logit contributions
rast-1.782
iar-1.437
oise-1.410
 relegation-1.396
assic-1.364
Token the
Token ID262
Feature activation-2.23e-01

Pos logit contributions
rast+0.308
iar+0.248
 relegation+0.241
oise+0.241
orth+0.235
Neg logit contributions
deen-0.286
…………-0.226
……………………-0.224
sth-0.208
hest-0.205
Token other
Token ID584
Feature activation+5.01e-01

Pos logit contributions
rast+0.548
iar+0.429
oise+0.418
 relegation+0.416
orth+0.403
Neg logit contributions
deen-0.629
…………-0.512
……………………-0.507
sth-0.474
hest-0.469
Token the
Token ID262
Feature activation-2.91e-01

Pos logit contributions
deen+1.343
…………+1.097
……………………+1.082
 sod+1.011
sth+1.009
Neg logit contributions
rast-1.282
iar-1.014
oise-1.002
 relegation-0.976
assic-0.965
Token Ne
Token ID3169
Feature activation+9.00e-01

Pos logit contributions
rast+0.738
iar+0.582
oise+0.568
 relegation+0.562
orth+0.549
Neg logit contributions
deen-0.797
…………-0.645
……………………-0.638
sth-0.596
 sod-0.589
Tokenveh
Token ID33892
Feature activation+2.54e+00

Pos logit contributions
deen+2.373
…………+1.876
……………………+1.854
hest+1.778
sth+1.770
Neg logit contributions
rast-2.297
 relegation-1.843
iar-1.832
oise-1.802
orth-1.771
Token Shal
Token ID47974
Feature activation+6.60e-01

Pos logit contributions
deen+6.824
…………+5.369
……………………+5.302
 sod+5.173
sth+5.091
Neg logit contributions
rast-6.062
velength-4.687
 relegation-4.670
iar-4.643
oise-4.608
Tokenom
Token ID296
Feature activation+2.36e-01

Pos logit contributions
deen+1.703
…………+1.340
……………………+1.330
hest+1.239
sth+1.236
Neg logit contributions
rast-1.763
 relegation-1.405
iar-1.399
oise-1.384
assic-1.337
Token massacre
Token ID19050
Feature activation+4.28e-01

Pos logit contributions
deen+0.650
…………+0.525
……………………+0.519
sth+0.485
 sod+0.485
Neg logit contributions
rast-0.597
iar-0.466
oise-0.459
 relegation-0.457
assic-0.445
Token of
Token ID286
Feature activation+1.36e-03

Pos logit contributions
deen+1.110
…………+0.897
……………………+0.882
sth+0.818
 sod+0.817
Neg logit contributions
rast-1.140
iar-0.914
oise-0.891
 relegation-0.881
assic-0.862
Token September
Token ID2693
Feature activation+2.26e-01

Pos logit contributions
deen+0.003
…………+0.003
……………………+0.003
 sod+0.002
sth+0.002
Neg logit contributions
rast-0.004
iar-0.003
oise-0.003
 relegation-0.003
orth-0.003
TokenThe
Token ID464
Feature activation+1.18e-01

Pos logit contributions
deen+0.483
…………+0.387
……………………+0.383
sth+0.346
hest+0.344
Neg logit contributions
rast-0.571
iar-0.463
 relegation-0.462
oise-0.456
assic-0.446
Token Two
Token ID4930
Feature activation+1.65e-01

Pos logit contributions
deen+0.303
…………+0.242
……………………+0.240
sth+0.222
hest+0.221
Neg logit contributions
rast-0.316
iar-0.254
oise-0.248
 relegation-0.246
assic-0.241
Token Towers
Token ID29031
Feature activation+1.06e-01

Pos logit contributions
deen+0.445
……………………+0.361
…………+0.361
hest+0.331
sth+0.330
Neg logit contributions
rast-0.416
iar-0.328
oise-0.323
 relegation-0.321
orth-0.313
Token [
Token ID685
Feature activation+2.73e-01

Pos logit contributions
deen+0.281
…………+0.226
……………………+0.223
sth+0.207
hest+0.205
Neg logit contributions
rast-0.276
iar-0.220
oise-0.214
 relegation-0.213
orth-0.208
Token edit
Token ID4370
Feature activation+4.59e-01

Pos logit contributions
deen+0.687
…………+0.551
……………………+0.546
sth+0.503
 sod+0.497
Neg logit contributions
rast-0.751
iar-0.605
 relegation-0.595
oise-0.592
assic-0.578
Token ]
Token ID2361
Feature activation+2.51e+00

Pos logit contributions
deen+0.926
…………+0.701
……………………+0.693
sth+0.610
hest+0.609
Neg logit contributions
rast-1.489
iar-1.238
 relegation-1.221
oise-1.207
assic-1.206
Token
Token ID198
Feature activation+7.26e-02

Pos logit contributions
deen+5.243
…………+4.431
……………………+4.375
 sod+3.816
sth+3.719
Neg logit contributions
rast-7.286
ruciating-6.299
vertisement-6.211
ouver-6.089
assic-6.073
Token
Token ID198
Feature activation+8.45e-02

Pos logit contributions
deen+0.186
…………+0.151
……………………+0.149
sth+0.137
 sod+0.136
Neg logit contributions
rast-0.195
iar-0.157
 relegation-0.154
oise-0.153
assic-0.151
TokenOr
Token ID5574
Feature activation-3.96e-01

Pos logit contributions
deen+0.205
…………+0.163
……………………+0.161
sth+0.147
hest+0.146
Neg logit contributions
rast-0.240
iar-0.194
 relegation-0.192
oise-0.191
assic-0.186
Tokencs
Token ID6359
Feature activation+1.19e+00

Pos logit contributions
rast+1.257
iar+1.051
oise+1.038
 relegation+1.034
assic+1.009
Neg logit contributions
deen-0.828
…………-0.614
……………………-0.604
sth-0.551
hest-0.543
Token sent
Token ID1908
Feature activation-6.48e-02

Pos logit contributions
deen+3.093
…………+2.476
……………………+2.458
sth+2.271
hest+2.258
Neg logit contributions
rast-3.104
iar-2.501
oise-2.420
 relegation-2.410
assic-2.385
Token:
Token ID25
Feature activation-2.24e-01

Pos logit contributions
rast+1.000
iar+0.816
oise+0.798
 relegation+0.795
orth+0.775
Neg logit contributions
deen-0.825
…………-0.644
……………………-0.636
sth-0.585
hest-0.576
Token 05
Token ID8870
Feature activation-2.46e-02

Pos logit contributions
rast+0.592
iar+0.472
oise+0.462
 relegation+0.459
orth+0.447
Neg logit contributions
deen-0.587
…………-0.475
……………………-0.470
sth-0.435
hest-0.428
Token35
Token ID2327
Feature activation-1.54e-01

Pos logit contributions
rast+0.066
iar+0.052
 relegation+0.052
oise+0.051
assic+0.051
Neg logit contributions
deen-0.063
…………-0.052
……………………-0.051
sth-0.047
 sod-0.046
Tokenz
Token ID89
Feature activation+6.08e-01

Pos logit contributions
rast+0.490
iar+0.408
oise+0.399
 relegation+0.397
orth+0.390
Neg logit contributions
deen-0.321
…………-0.239
……………………-0.235
sth-0.213
hest-0.210
Token 1
Token ID352
Feature activation+3.98e-01

Pos logit contributions
deen+1.528
…………+1.236
……………………+1.225
sth+1.113
 sod+1.106
Neg logit contributions
rast-1.656
iar-1.333
oise-1.314
 relegation-1.298
assic-1.276
Token GER
Token ID44186
Feature activation+2.51e+00

Pos logit contributions
deen+0.952
…………+0.751
……………………+0.745
sth+0.683
 sod+0.668
Neg logit contributions
rast-1.141
iar-0.931
oise-0.911
 relegation-0.910
assic-0.890
TokenON
Token ID1340
Feature activation+3.96e-01

Pos logit contributions
deen+4.213
…………+2.977
……………………+2.915
MEN+2.570
 sod+2.464
Neg logit contributions
rast-8.671
iar-7.412
 relegation-7.287
oise-7.198
assic-7.110
TokenIM
Token ID3955
Feature activation+9.98e-01

Pos logit contributions
deen+0.914
…………+0.722
……………………+0.719
sth+0.649
hest+0.639
Neg logit contributions
rast-1.157
iar-0.948
 relegation-0.937
oise-0.933
assic-0.911
TokenO
Token ID46
Feature activation+1.24e-01

Pos logit contributions
deen+1.773
…………+1.364
……………………+1.346
 sod+1.146
MEN+1.135
Neg logit contributions
rast-3.403
iar-2.872
 relegation-2.853
assic-2.814
ruciating-2.797
Token T
Token ID309
Feature activation+4.54e-01

Pos logit contributions
deen+0.300
…………+0.235
……………………+0.232
sth+0.213
hest+0.210
Neg logit contributions
rast-0.357
iar-0.290
oise-0.284
 relegation-0.283
orth-0.276
TokenOC
Token ID4503
Feature activation-2.35e-01

Pos logit contributions
deen+0.915
…………+0.705
……………………+0.691
sth+0.612
 sod+0.606
Neg logit contributions
rast-1.458
iar-1.213
 relegation-1.206
oise-1.195
assic-1.172
Token is
Token ID318
Feature activation+5.26e-01

Pos logit contributions
rast+0.720
iar+0.557
oise+0.543
 relegation+0.540
orth+0.522
Neg logit contributions
deen-0.875
…………-0.718
……………………-0.710
sth-0.664
 sod-0.660
Token connected
Token ID5884
Feature activation+2.77e-01

Pos logit contributions
deen+1.345
…………+1.085
……………………+1.080
 sod+0.998
hest+0.987
Neg logit contributions
rast-1.424
iar-1.133
oise-1.119
 relegation-1.096
assic-1.080
Token to
Token ID284
Feature activation+5.37e-01

Pos logit contributions
deen+0.804
…………+0.654
……………………+0.647
sth+0.608
hest+0.601
Neg logit contributions
rast-0.660
iar-0.514
oise-0.498
 relegation-0.496
orth-0.482
Token the
Token ID262
Feature activation+2.54e-01

Pos logit contributions
deen+1.321
…………+1.050
……………………+1.035
 sod+0.951
sth+0.950
Neg logit contributions
rast-1.503
iar-1.216
oise-1.191
 relegation-1.177
assic-1.155
Token Muslim
Token ID3765
Feature activation+9.23e-01

Pos logit contributions
deen+0.652
…………+0.519
……………………+0.514
sth+0.475
hest+0.472
Neg logit contributions
rast-0.687
iar-0.551
oise-0.538
 relegation-0.534
orth-0.523
Token Brotherhood
Token ID17987
Feature activation+2.46e+00

Pos logit contributions
deen+1.465
…………+1.006
……………………+1.001
 sod+0.854
sth+0.835
Neg logit contributions
rast-3.374
iar-2.860
oise-2.829
 relegation-2.809
orth-2.781
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
deen+5.464
…………+4.430
……………………+4.379
hest+3.854
sth+3.824
Neg logit contributions
rast-7.062
iar-5.792
oise-5.728
assic-5.619
 relegation-5.589
Token that
Token ID326
Feature activation-4.05e-01

Pos logit contributions
deen+0.298
…………+0.240
……………………+0.237
sth+0.219
 sod+0.219
Neg logit contributions
rast-0.309
iar-0.247
oise-0.241
 relegation-0.239
orth-0.234
Token Marco
Token ID16556
Feature activation-2.54e-01

Pos logit contributions
rast+1.087
iar+0.871
oise+0.851
 relegation+0.847
orth+0.824
Neg logit contributions
deen-1.049
…………-0.836
……………………-0.827
sth-0.768
hest-0.758
Token Rubio
Token ID15476
Feature activation-2.76e-01

Pos logit contributions
rast+0.574
iar+0.442
oise+0.425
 relegation+0.422
assic+0.410
Neg logit contributions
deen-0.765
…………-0.640
……………………-0.635
 sod-0.588
hest-0.588
Token is
Token ID318
Feature activation+5.58e-01

Pos logit contributions
rast+0.734
iar+0.585
oise+0.571
 relegation+0.570
orth+0.553
Neg logit contributions
deen-0.723
…………-0.581
……………………-0.575
sth-0.532
 sod-0.527
Token like
Token ID588
Feature activation+2.59e-01

Pos logit contributions
deen+3.320
…………+2.729
……………………+2.691
 sod+2.474
sth+2.465
Neg logit contributions
rast-3.057
iar-2.365
oise-2.342
 relegation-2.284
assic-2.262
Token you
Token ID345
Feature activation+1.46e+00

Pos logit contributions
deen+0.680
…………+0.551
……………………+0.542
sth+0.501
 sod+0.497
Neg logit contributions
rast-0.684
iar-0.544
oise-0.533
 relegation-0.524
orth-0.516
Token
Token ID447
Feature activation+9.25e-02

Pos logit contributions
deen+3.913
…………+3.203
……………………+3.137
 sod+2.907
sth+2.902
Neg logit contributions
rast-3.730
iar-2.927
oise-2.897
 relegation-2.837
assic-2.817
Token
Token ID247
Feature activation+4.87e-01

Pos logit contributions
deen+0.196
…………+0.148
……………………+0.147
sth+0.131
hest+0.129
Neg logit contributions
rast-0.292
iar-0.244
 relegation-0.239
oise-0.238
orth-0.233
Tokenre
Token ID260
Feature activation+6.02e-01

Pos logit contributions
deen+1.207
…………+0.952
……………………+0.938
sth+0.879
hest+0.857
Neg logit contributions
rast-1.361
iar-1.099
 relegation-1.080
oise-1.071
assic-1.049
Token gre
Token ID10536
Feature activation+2.46e+00

Pos logit contributions
deen+1.680
…………+1.382
……………………+1.364
 sod+1.262
sth+1.256
Neg logit contributions
rast-1.493
iar-1.157
oise-1.142
 relegation-1.121
assic-1.099
Tokenasing
Token ID2313
Feature activation+1.14e+00

Pos logit contributions
deen+6.675
…………+5.630
……………………+5.498
hest+5.159
sth+5.068
Neg logit contributions
rast-5.751
 relegation-4.566
iar-4.297
 failings-4.283
oise-4.253
Token politicians
Token ID7602
Feature activation+4.68e-01

Pos logit contributions
deen+2.898
…………+2.344
……………………+2.302
sth+2.131
hest+2.101
Neg logit contributions
rast-3.062
iar-2.471
oise-2.401
 relegation-2.396
assic-2.358
Token for
Token ID329
Feature activation+1.08e-01

Pos logit contributions
deen+1.105
…………+0.869
……………………+0.856
sth+0.783
hest+0.768
Neg logit contributions
rast-1.359
iar-1.110
oise-1.093
 relegation-1.086
assic-1.064
Token fav
Token ID2090
Feature activation+1.40e+00

Pos logit contributions
deen+0.288
…………+0.233
……………………+0.231
sth+0.213
 sod+0.213
Neg logit contributions
rast-0.281
iar-0.224
oise-0.219
 relegation-0.214
orth-0.211
Tokenours
Token ID4662
Feature activation+8.89e-01

Pos logit contributions
deen+2.778
…………+2.103
……………………+2.059
hest+1.900
sth+1.853
Neg logit contributions
rast-4.452
 relegation-3.714
iar-3.691
oise-3.638
assic-3.590
Token month
Token ID1227
Feature activation-1.81e-01

Pos logit contributions
deen+0.712
…………+0.577
……………………+0.570
sth+0.528
 sod+0.526
Neg logit contributions
rast-0.704
iar-0.568
oise-0.547
 relegation-0.532
assic-0.531
Token have
Token ID423
Feature activation-3.69e-01

Pos logit contributions
rast+0.433
iar+0.337
oise+0.327
 relegation+0.325
orth+0.314
Neg logit contributions
deen-0.521
…………-0.427
……………………-0.422
sth-0.397
hest-0.393
Token made
Token ID925
Feature activation+7.86e-01

Pos logit contributions
rast+0.920
iar+0.723
oise+0.704
 relegation+0.696
orth+0.676
Neg logit contributions
deen-1.028
…………-0.840
……………………-0.830
sth-0.772
 sod-0.769
Token a
Token ID257
Feature activation+8.49e-01

Pos logit contributions
deen+2.046
…………+1.680
……………………+1.657
 sod+1.535
hest+1.520
Neg logit contributions
rast-2.057
iar-1.653
oise-1.599
 relegation-1.572
assic-1.553
Token significant
Token ID2383
Feature activation+9.04e-01

Pos logit contributions
deen+2.243
…………+1.833
……………………+1.817
 sod+1.680
hest+1.653
Neg logit contributions
rast-2.212
iar-1.781
oise-1.711
 relegation-1.669
assic-1.667
Token profit
Token ID7630
Feature activation+2.45e+00

Pos logit contributions
deen+2.350
…………+1.909
……………………+1.889
 sod+1.750
sth+1.727
Neg logit contributions
rast-2.388
iar-1.908
oise-1.846
 relegation-1.814
assic-1.792
Token.
Token ID13
Feature activation+2.10e-01

Pos logit contributions
deen+5.620
…………+4.659
……………………+4.532
hest+4.095
sth+4.078
Neg logit contributions
rast-6.789
iar-5.573
oise-5.416
assic-5.314
 relegation-5.302
Token
Token ID198
Feature activation+2.61e-01

Pos logit contributions
deen+0.538
…………+0.437
……………………+0.432
sth+0.397
hest+0.393
Neg logit contributions
rast-0.560
iar-0.451
 relegation-0.442
oise-0.441
assic-0.435
Token
Token ID198
Feature activation+2.18e-01

Pos logit contributions
deen+0.657
…………+0.534
……………………+0.528
sth+0.485
 sod+0.479
Neg logit contributions
rast-0.709
iar-0.573
 relegation-0.567
oise-0.557
assic-0.555
TokenOf
Token ID5189
Feature activation+3.00e-01

Pos logit contributions
deen+0.529
…………+0.425
……………………+0.420
sth+0.382
hest+0.377
Neg logit contributions
rast-0.613
iar-0.499
 relegation-0.495
oise-0.488
assic-0.479
Token course
Token ID1781
Feature activation-9.31e-02

Pos logit contributions
deen+0.745
…………+0.587
……………………+0.580
sth+0.536
hest+0.529
Neg logit contributions
rast-0.840
iar-0.679
oise-0.664
 relegation-0.661
orth-0.646
Token
Token ID198
Feature activation+1.17e-01

Pos logit contributions
deen+0.390
…………+0.317
……………………+0.314
sth+0.288
 sod+0.285
Neg logit contributions
rast-0.411
iar-0.331
 relegation-0.326
oise-0.322
assic-0.318
TokenOther
Token ID6395
Feature activation+9.48e-01

Pos logit contributions
deen+0.295
…………+0.238
……………………+0.236
sth+0.217
hest+0.213
Neg logit contributions
rast-0.321
iar-0.258
 relegation-0.254
oise-0.252
assic-0.244
Token media
Token ID2056
Feature activation-1.53e-01

Pos logit contributions
deen+2.536
…………+2.071
……………………+2.061
 sod+1.916
sth+1.882
Neg logit contributions
rast-2.412
iar-1.901
oise-1.874
ouver-1.826
 relegation-1.810
Token [
Token ID685
Feature activation+1.75e-01

Pos logit contributions
rast+0.394
iar+0.311
oise+0.305
 relegation+0.300
orth+0.293
Neg logit contributions
deen-0.412
…………-0.334
……………………-0.330
sth-0.306
 sod-0.304
Token edit
Token ID4370
Feature activation+6.59e-01

Pos logit contributions
deen+0.452
…………+0.362
……………………+0.358
sth+0.333
hest+0.327
Neg logit contributions
rast-0.470
iar-0.376
oise-0.367
 relegation-0.367
orth-0.355
Token ]
Token ID2361
Feature activation+2.43e+00

Pos logit contributions
deen+1.353
…………+1.008
……………………+0.996
sth+0.891
 sod+0.886
Neg logit contributions
rast-2.127
iar-1.767
 relegation-1.729
oise-1.725
assic-1.699
Token
Token ID198
Feature activation-1.43e-01

Pos logit contributions
deen+6.066
…………+4.870
……………………+4.828
sth+4.389
 sod+4.374
Neg logit contributions
rast-6.566
iar-5.241
oise-5.096
 relegation-5.077
ouver-4.989
Token
Token ID198
Feature activation-6.18e-02

Pos logit contributions
rast+0.379
iar+0.304
 relegation+0.297
oise+0.296
assic+0.289
Neg logit contributions
deen-0.373
…………-0.302
……………………-0.299
sth-0.276
 sod-0.273
TokenVideo
Token ID10798
Feature activation-5.02e-01

Pos logit contributions
rast+0.168
iar+0.135
 relegation+0.133
oise+0.132
assic+0.128
Neg logit contributions
deen-0.157
…………-0.126
……………………-0.125
sth-0.115
hest-0.113
Token games
Token ID1830
Feature activation+3.11e-01

Pos logit contributions
rast+1.244
iar+0.975
oise+0.948
 relegation+0.939
orth+0.914
Neg logit contributions
deen-1.407
…………-1.143
……………………-1.132
sth-1.057
 sod-1.045
Token [
Token ID685
Feature activation+1.11e-01

Pos logit contributions
deen+0.819
…………+0.662
……………………+0.654
 sod+0.604
sth+0.603
Neg logit contributions
rast-0.821
iar-0.651
oise-0.634
 relegation-0.628
ouver-0.614
Token that
Token ID326
Feature activation-8.67e-02

Pos logit contributions
deen+0.362
…………+0.296
……………………+0.292
sth+0.271
 sod+0.270
Neg logit contributions
rast-0.335
iar-0.264
oise-0.257
 relegation-0.254
assic-0.249
Token they
Token ID484
Feature activation+3.85e-01

Pos logit contributions
rast+0.232
iar+0.186
oise+0.182
 relegation+0.179
assic+0.176
Neg logit contributions
deen-0.225
…………-0.181
……………………-0.179
sth-0.166
 sod-0.164
Token will
Token ID481
Feature activation+3.30e-01

Pos logit contributions
deen+1.025
…………+0.829
……………………+0.814
sth+0.760
 sod+0.756
Neg logit contributions
rast-0.998
iar-0.790
oise-0.777
 relegation-0.770
assic-0.751
Token make
Token ID787
Feature activation+1.22e+00

Pos logit contributions
deen+0.892
…………+0.724
……………………+0.710
 sod+0.664
sth+0.661
Neg logit contributions
rast-0.847
iar-0.665
oise-0.655
 relegation-0.646
assic-0.636
Token a
Token ID257
Feature activation+1.03e+00

Pos logit contributions
deen+2.939
…………+2.331
……………………+2.306
 sod+2.131
sth+2.110
Neg logit contributions
rast-3.471
iar-2.808
oise-2.746
 relegation-2.684
assic-2.684
Token profit
Token ID7630
Feature activation+2.39e+00

Pos logit contributions
deen+2.744
…………+2.223
……………………+2.198
 sod+2.049
sth+2.023
Neg logit contributions
rast-2.673
iar-2.130
oise-2.055
assic-2.017
 relegation-2.006
Token,
Token ID11
Feature activation+3.55e-01

Pos logit contributions
deen+5.636
…………+4.592
……………………+4.480
sth+4.089
 sod+4.068
Neg logit contributions
rast-6.563
iar-5.243
oise-5.210
 relegation-5.101
ruciating-5.065
Token and
Token ID290
Feature activation+1.82e-01

Pos logit contributions
deen+0.943
…………+0.762
……………………+0.754
 sod+0.696
sth+0.696
Neg logit contributions
rast-0.927
iar-0.737
oise-0.723
 relegation-0.711
orth-0.696
Token they
Token ID484
Feature activation+3.46e-01

Pos logit contributions
deen+0.474
…………+0.384
……………………+0.379
sth+0.350
 sod+0.348
Neg logit contributions
rast-0.483
iar-0.387
oise-0.378
 relegation-0.372
orth-0.367
Token will
Token ID481
Feature activation+2.15e-01

Pos logit contributions
deen+0.950
…………+0.773
……………………+0.761
sth+0.711
hest+0.706
Neg logit contributions
rast-0.872
iar-0.687
oise-0.673
 relegation-0.668
assic-0.650
Token try
Token ID1949
Feature activation+1.15e+00

Pos logit contributions
deen+0.572
…………+0.461
……………………+0.454
sth+0.422
 sod+0.421
Neg logit contributions
rast-0.561
iar-0.444
oise-0.437
 relegation-0.431
assic-0.423
Token and
Token ID290
Feature activation-2.27e-01

Pos logit contributions
rast+2.098
iar+1.660
oise+1.620
 relegation+1.616
orth+1.567
Neg logit contributions
deen-2.216
…………-1.783
……………………-1.766
sth-1.649
hest-1.628
Token has
Token ID468
Feature activation+3.39e-01

Pos logit contributions
rast+0.536
iar+0.414
oise+0.404
 relegation+0.398
assic+0.387
Neg logit contributions
deen-0.659
…………-0.543
……………………-0.537
 sod-0.501
sth-0.499
Token been
Token ID587
Feature activation+5.76e-01

Pos logit contributions
deen+0.941
…………+0.771
……………………+0.761
 sod+0.715
hest+0.707
Neg logit contributions
rast-0.842
iar-0.660
oise-0.648
 relegation-0.633
orth-0.620
Token key
Token ID1994
Feature activation+4.24e-01

Pos logit contributions
deen+1.518
…………+1.231
……………………+1.218
 sod+1.141
hest+1.120
Neg logit contributions
rast-1.501
iar-1.199
oise-1.178
 relegation-1.138
orth-1.132
Token to
Token ID284
Feature activation+7.05e-01

Pos logit contributions
deen+1.112
…………+0.895
……………………+0.884
 sod+0.831
sth+0.825
Neg logit contributions
rast-1.099
iar-0.870
oise-0.859
 relegation-0.850
assic-0.838
Token helping
Token ID5742
Feature activation+2.36e+00

Pos logit contributions
deen+1.641
…………+1.295
……………………+1.269
 sod+1.171
hest+1.166
Neg logit contributions
rast-2.033
iar-1.676
oise-1.622
 relegation-1.596
assic-1.592
Token Boston
Token ID6182
Feature activation+2.17e-01

Pos logit contributions
deen+5.342
…………+4.305
……………………+4.150
 sod+3.896
hest+3.760
Neg logit contributions
rast-6.676
iar-5.457
assic-5.342
ouver-5.253
oise-5.248
Token to
Token ID284
Feature activation+1.60e-01

Pos logit contributions
deen+0.568
…………+0.456
……………………+0.450
sth+0.418
hest+0.415
Neg logit contributions
rast-0.572
iar-0.457
oise-0.445
 relegation-0.441
orth-0.432
Token a
Token ID257
Feature activation+5.73e-02

Pos logit contributions
deen+0.410
…………+0.328
……………………+0.324
sth+0.300
hest+0.299
Neg logit contributions
rast-0.431
iar-0.346
oise-0.337
 relegation-0.333
orth-0.327
Token 14
Token ID1478
Feature activation-4.48e-01

Pos logit contributions
deen+0.154
…………+0.124
……………………+0.123
sth+0.114
hest+0.114
Neg logit contributions
rast-0.148
iar-0.118
oise-0.114
 relegation-0.113
orth-0.111
Token-
Token ID12
Feature activation+2.96e-01

Pos logit contributions
rast+1.226
iar+0.982
oise+0.968
 relegation+0.964
orth+0.936
Neg logit contributions
deen-1.148
…………-0.900
……………………-0.891
sth-0.822
hest-0.817
TokenMiami
Token ID41191
Feature activation-9.74e-01

Pos logit contributions
rast+0.582
iar+0.472
 relegation+0.464
oise+0.463
assic+0.450
Neg logit contributions
deen-0.498
…………-0.396
……………………-0.392
sth-0.356
hest-0.354
Token Dolphins
Token ID21668
Feature activation-6.62e-01

Pos logit contributions
rast+2.000
iar+1.480
oise+1.431
 relegation+1.421
orth+1.366
Neg logit contributions
deen-3.141
…………-2.628
……………………-2.607
sth-2.464
hest-2.441
Token:
Token ID25
Feature activation-3.73e-01

Pos logit contributions
rast+1.853
iar+1.487
 relegation+1.460
oise+1.455
orth+1.426
Neg logit contributions
deen-1.629
…………-1.268
……………………-1.252
sth-1.188
 sod-1.163
Token DE
Token ID5550
Feature activation-1.98e-01

Pos logit contributions
rast+0.984
iar+0.784
oise+0.766
 relegation+0.761
assic+0.741
Neg logit contributions
deen-0.984
…………-0.792
……………………-0.783
sth-0.724
hest-0.719
Token Cameron
Token ID10821
Feature activation-1.82e-01

Pos logit contributions
rast+0.498
iar+0.392
oise+0.383
 relegation+0.382
assic+0.371
Neg logit contributions
deen-0.544
…………-0.442
……………………-0.438
sth-0.406
hest-0.403
Token Wake
Token ID20441
Feature activation-2.62e+00

Pos logit contributions
rast+0.374
iar+0.277
oise+0.265
 relegation+0.265
assic+0.256
Neg logit contributions
deen-0.586
…………-0.491
……………………-0.487
sth-0.460
 sod-0.456
Token
Token ID198
Feature activation-4.88e-01

Pos logit contributions
rast+6.346
iar+4.977
oise+4.801
orth+4.742
 relegation+4.733
Neg logit contributions
deen-7.206
…………-5.841
……………………-5.793
sth-5.470
hest-5.375
Token
Token ID198
Feature activation-3.89e-01

Pos logit contributions
rast+1.270
iar+1.010
oise+0.984
 relegation+0.982
orth+0.952
Neg logit contributions
deen-1.305
…………-1.051
……………………-1.041
sth-0.967
hest-0.956
TokenContract
Token ID45845
Feature activation-4.10e-01

Pos logit contributions
rast+1.111
iar+0.905
oise+0.883
 relegation+0.874
orth+0.861
Neg logit contributions
deen-0.944
…………-0.730
……………………-0.720
sth-0.672
 sod-0.662
Token:
Token ID25
Feature activation-3.47e-01

Pos logit contributions
rast+1.219
iar+1.002
oise+0.982
 relegation+0.979
assic+0.957
Neg logit contributions
deen-0.940
…………-0.733
……………………-0.726
sth-0.660
hest-0.651
Token A
Token ID317
Feature activation+9.70e-02

Pos logit contributions
rast+0.922
iar+0.735
oise+0.718
 relegation+0.714
orth+0.695
Neg logit contributions
deen-0.911
…………-0.730
……………………-0.722
sth-0.670
hest-0.663
Token beating
Token ID11226
Feature activation+4.01e-01

Pos logit contributions
rast+0.877
iar+0.687
oise+0.668
 relegation+0.656
assic+0.651
Neg logit contributions
deen-0.969
…………-0.796
……………………-0.788
 sod-0.738
sth-0.730
Token alcohol
Token ID5548
Feature activation-1.11e-01

Pos logit contributions
deen+1.073
…………+0.867
……………………+0.858
 sod+0.804
sth+0.802
Neg logit contributions
rast-1.036
iar-0.816
oise-0.795
 relegation-0.788
assic-0.778
Token or
Token ID393
Feature activation-7.43e-01

Pos logit contributions
rast+0.301
iar+0.239
oise+0.235
 relegation+0.234
assic+0.229
Neg logit contributions
deen-0.285
…………-0.230
……………………-0.227
sth-0.210
 sod-0.207
Token avoiding
Token ID14928
Feature activation+3.14e-01

Pos logit contributions
rast+1.856
iar+1.454
oise+1.420
 relegation+1.405
orth+1.370
Neg logit contributions
deen-2.069
…………-1.683
……………………-1.668
sth-1.551
 sod-1.548
Token d
Token ID288
Feature activation+3.14e-01

Pos logit contributions
deen+0.890
…………+0.732
……………………+0.727
 sod+0.692
sth+0.675
Neg logit contributions
rast-0.760
iar-0.589
oise-0.580
assic-0.560
orth-0.558
Tokeneng
Token ID1516
Feature activation-2.61e+00

Pos logit contributions
deen+0.841
…………+0.673
……………………+0.664
sth+0.624
hest+0.622
Neg logit contributions
rast-0.807
iar-0.639
 relegation-0.634
oise-0.630
assic-0.609
Tokenue
Token ID518
Feature activation-1.05e+00

Pos logit contributions
rast+5.066
iar+3.669
oise+3.598
 relegation+3.496
orth+3.413
Neg logit contributions
deen-8.511
…………-7.109
……………………-7.066
hest-6.677
sth-6.638
Token fever
Token ID17372
Feature activation-3.44e-01

Pos logit contributions
rast+2.966
iar+2.403
oise+2.351
 relegation+2.339
orth+2.283
Neg logit contributions
deen-2.561
…………-2.013
……………………-1.990
sth-1.835
hest-1.809
Token.
Token ID13
Feature activation-2.45e-01

Pos logit contributions
rast+0.937
iar+0.752
oise+0.737
 relegation+0.731
assic+0.715
Neg logit contributions
deen-0.878
…………-0.700
……………………-0.692
sth-0.642
hest-0.632
Token
Token ID564
Feature activation+3.22e-01

Pos logit contributions
rast+0.647
iar+0.516
oise+0.504
 relegation+0.503
assic+0.492
Neg logit contributions
deen-0.642
…………-0.519
……………………-0.513
sth-0.475
hest-0.470
Token
Token ID250
Feature activation-4.02e-01

Pos logit contributions
deen+0.568
…………+0.400
……………………+0.394
sth+0.343
hest+0.336
Neg logit contributions
rast-1.130
iar-0.961
oise-0.943
 relegation-0.940
orth-0.923
Token the
Token ID262
Feature activation+3.79e-02

Pos logit contributions
deen+1.223
…………+0.973
……………………+0.958
sth+0.880
 sod+0.880
Neg logit contributions
rast-1.376
iar-1.116
oise-1.088
 relegation-1.077
assic-1.059
Token imminent
Token ID21161
Feature activation+1.49e-01

Pos logit contributions
deen+0.105
…………+0.086
……………………+0.085
 sod+0.079
sth+0.079
Neg logit contributions
rast-0.094
iar-0.075
oise-0.072
 relegation-0.071
orth-0.070
Token demise
Token ID25403
Feature activation-1.08e-01

Pos logit contributions
deen+0.413
…………+0.338
……………………+0.334
sth+0.313
 sod+0.312
Neg logit contributions
rast-0.371
iar-0.293
oise-0.283
 relegation-0.273
orth-0.273
Token of
Token ID286
Feature activation+2.44e-02

Pos logit contributions
rast+0.265
iar+0.207
oise+0.201
 relegation+0.200
orth+0.194
Neg logit contributions
deen-0.307
…………-0.249
……………………-0.247
sth-0.231
hest-0.229
Token the
Token ID262
Feature activation-1.08e-01

Pos logit contributions
deen+0.062
…………+0.050
……………………+0.049
 sod+0.046
sth+0.046
Neg logit contributions
rast-0.066
iar-0.053
oise-0.052
 relegation-0.051
assic-0.051
Token wind
Token ID2344
Feature activation-2.59e+00

Pos logit contributions
rast+0.279
iar+0.222
oise+0.217
 relegation+0.215
orth+0.210
Neg logit contributions
deen-0.291
…………-0.236
……………………-0.233
sth-0.216
 sod-0.216
Token power
Token ID1176
Feature activation-4.66e-01

Pos logit contributions
rast+6.246
iar+4.833
oise+4.742
 relegation+4.680
orth+4.598
Neg logit contributions
deen-7.330
…………-5.885
……………………-5.855
sth-5.518
hest-5.416
Token production
Token ID3227
Feature activation-8.69e-02

Pos logit contributions
rast+1.181
iar+0.941
oise+0.912
 relegation+0.900
orth+0.879
Neg logit contributions
deen-1.272
…………-1.042
……………………-1.028
sth-0.956
 sod-0.955
Token tax
Token ID1687
Feature activation+4.50e-02

Pos logit contributions
rast+0.221
iar+0.177
oise+0.171
 relegation+0.169
orth+0.165
Neg logit contributions
deen-0.236
…………-0.192
……………………-0.190
sth-0.177
 sod-0.176
Token credit
Token ID3884
Feature activation+9.55e-01

Pos logit contributions
deen+0.117
…………+0.094
……………………+0.093
sth+0.086
 sod+0.085
Neg logit contributions
rast-0.121
iar-0.097
oise-0.094
 relegation-0.094
orth-0.092
Token),
Token ID828
Feature activation+4.66e-01

Pos logit contributions
deen+2.430
…………+1.964
……………………+1.934
sth+1.813
 sod+1.775
Neg logit contributions
rast-2.554
iar-2.077
 relegation-2.002
oise-1.984
orth-1.935
Tokenev
Token ID1990
Feature activation-6.68e-01

Pos logit contributions
deen+0.909
…………+0.713
……………………+0.706
sth+0.657
hest+0.653
Neg logit contributions
rast-0.956
 relegation-0.760
iar-0.758
oise-0.743
assic-0.729
Tokenic
Token ID291
Feature activation-3.96e-02

Pos logit contributions
rast+1.903
iar+1.541
 relegation+1.508
oise+1.508
orth+1.465
Neg logit contributions
deen-1.624
…………-1.269
……………………-1.254
sth-1.156
hest-1.146
Token"
Token ID1
Feature activation-2.90e-01

Pos logit contributions
rast+0.103
iar+0.081
 relegation+0.080
oise+0.079
orth+0.077
Neg logit contributions
deen-0.106
…………-0.085
……………………-0.084
sth-0.079
hest-0.078
Token (
Token ID357
Feature activation-5.38e-01

Pos logit contributions
rast+0.796
iar+0.641
oise+0.627
 relegation+0.626
orth+0.607
Neg logit contributions
deen-0.732
…………-0.580
……………………-0.574
sth-0.530
hest-0.525
Tokenm
Token ID76
Feature activation+4.44e-03

Pos logit contributions
rast+1.477
iar+1.190
oise+1.163
 relegation+1.159
orth+1.126
Neg logit contributions
deen-1.364
…………-1.080
……………………-1.068
sth-0.990
hest-0.977
Tokenatt
Token ID1078
Feature activation-2.57e+00

Pos logit contributions
deen+0.012
…………+0.009
……………………+0.009
sth+0.009
hest+0.008
Neg logit contributions
rast-0.012
iar-0.009
 relegation-0.009
oise-0.009
orth-0.009
Token-
Token ID12
Feature activation-9.19e-01

Pos logit contributions
rast+7.431
iar+6.189
oise+5.930
orth+5.749
assic+5.747
Neg logit contributions
deen-5.884
…………-4.614
……………………-4.537
sth-4.045
 sod-3.987
TokenEE
Token ID6500
Feature activation-5.12e-01

Pos logit contributions
rast+2.692
iar+2.204
oise+2.153
 relegation+2.127
orth+2.093
Neg logit contributions
deen-2.152
…………-1.671
……………………-1.651
sth-1.513
hest-1.489
Token-
Token ID12
Feature activation-3.41e-01

Pos logit contributions
rast+1.427
iar+1.155
oise+1.129
 relegation+1.128
orth+1.093
Neg logit contributions
deen-1.276
…………-1.008
……………………-0.996
sth-0.922
hest-0.910
Tokenoh
Token ID1219
Feature activation-7.15e-01

Pos logit contributions
rast+0.966
iar+0.786
 relegation+0.772
oise+0.769
assic+0.745
Neg logit contributions
deen-0.832
…………-0.652
……………………-0.644
sth-0.597
hest-0.589
Token-
Token ID12
Feature activation-4.74e-01

Pos logit contributions
rast+1.915
iar+1.534
oise+1.498
 relegation+1.489
orth+1.450
Neg logit contributions
deen-1.855
…………-1.479
……………………-1.463
sth-1.358
hest-1.342
Token he
Token ID339
Feature activation-3.86e-01

Pos logit contributions
rast+1.141
iar+0.901
oise+0.877
 relegation+0.873
orth+0.848
Neg logit contributions
deen-1.241
…………-1.003
……………………-0.993
sth-0.927
hest-0.916
Token said
Token ID531
Feature activation-1.44e-01

Pos logit contributions
rast+0.823
iar+0.618
oise+0.597
 relegation+0.593
orth+0.572
Neg logit contributions
deen-1.214
…………-1.010
……………………-1.002
sth-0.945
hest-0.936
Token.
Token ID13
Feature activation+2.79e-01

Pos logit contributions
rast+0.383
iar+0.306
oise+0.297
 relegation+0.296
orth+0.290
Neg logit contributions
deen-0.379
…………-0.302
……………………-0.299
sth-0.278
hest-0.274
Token<|endoftext|>
Token ID50256
Feature activation-2.34e-01

Pos logit contributions
deen+0.723
…………+0.580
……………………+0.574
sth+0.531
hest+0.526
Neg logit contributions
rast-0.745
iar-0.597
oise-0.585
 relegation-0.584
assic-0.568
TokenMeg
Token ID42672
Feature activation-5.31e-01

Pos logit contributions
rast+0.652
iar+0.527
 relegation+0.517
oise+0.515
assic+0.499
Neg logit contributions
deen-0.583
…………-0.463
……………………-0.458
sth-0.422
hest-0.416
Tokenach
Token ID620
Feature activation-2.50e+00

Pos logit contributions
rast+1.367
iar+1.089
oise+1.065
 relegation+1.062
assic+1.020
Neg logit contributions
deen-1.437
…………-1.146
……………………-1.134
sth-1.068
hest-1.059
Tokenurch
Token ID2575
Feature activation-6.62e-01

Pos logit contributions
rast+6.154
iar+4.819
oise+4.687
 relegation+4.608
orth+4.551
Neg logit contributions
deen-6.971
…………-5.695
……………………-5.644
sth-5.263
 sod-5.223
Token founder
Token ID9119
Feature activation-6.12e-01

Pos logit contributions
rast+1.712
iar+1.356
oise+1.323
 relegation+1.315
orth+1.280
Neg logit contributions
deen-1.785
…………-1.437
……………………-1.422
sth-1.323
hest-1.311
Token Rev
Token ID5416
Feature activation-6.93e-01

Pos logit contributions
rast+1.566
iar+1.238
oise+1.207
 relegation+1.198
orth+1.167
Neg logit contributions
deen-1.669
…………-1.351
……………………-1.335
sth-1.243
hest-1.233
Token.
Token ID13
Feature activation+1.61e-01

Pos logit contributions
rast+1.883
iar+1.505
 relegation+1.476
oise+1.466
assic+1.432
Neg logit contributions
deen-1.785
…………-1.399
……………………-1.383
sth-1.289
hest-1.287
Token Ted
Token ID11396
Feature activation-1.01e+00

Pos logit contributions
deen+0.437
…………+0.354
……………………+0.350
sth+0.327
 sod+0.325
Neg logit contributions
rast-0.413
iar-0.326
oise-0.318
 relegation-0.317
assic-0.310
Token enable
Token ID7139
Feature activation+6.74e-01

Pos logit contributions
deen+0.251
…………+0.202
……………………+0.200
sth+0.185
 sod+0.183
Neg logit contributions
rast-0.253
iar-0.202
oise-0.197
 relegation-0.196
assic-0.192
Token Broad
Token ID9765
Feature activation+2.96e-02

Pos logit contributions
deen+1.746
…………+1.407
……………………+1.393
sth+1.298
 sod+1.280
Neg logit contributions
rast-1.784
iar-1.427
oise-1.394
 relegation-1.378
assic-1.368
Tokenband
Token ID3903
Feature activation-3.94e-01

Pos logit contributions
deen+0.084
…………+0.068
……………………+0.067
sth+0.063
hest+0.063
Neg logit contributions
rast-0.072
iar-0.057
 relegation-0.056
oise-0.055
assic-0.054
Token Connection
Token ID26923
Feature activation+6.27e-01

Pos logit contributions
rast+1.072
iar+0.862
oise+0.843
 relegation+0.840
assic+0.818
Neg logit contributions
deen-1.004
…………-0.801
……………………-0.792
sth-0.732
hest-0.722
Token (
Token ID357
Feature activation-3.60e-01

Pos logit contributions
deen+1.542
…………+1.244
……………………+1.233
sth+1.135
 sod+1.109
Neg logit contributions
rast-1.723
iar-1.405
oise-1.367
 relegation-1.365
assic-1.355
TokenCo
Token ID7222
Feature activation-2.48e+00

Pos logit contributions
rast+0.980
iar+0.788
 relegation+0.773
oise+0.772
assic+0.751
Neg logit contributions
deen-0.916
…………-0.731
……………………-0.723
sth-0.671
hest-0.660
Tokenax
Token ID897
Feature activation-8.24e-01

Pos logit contributions
rast+5.968
iar+4.649
oise+4.526
 relegation+4.432
orth+4.394
Neg logit contributions
deen-7.070
…………-5.715
……………………-5.656
sth-5.316
 sod-5.239
Token)
Token ID8
Feature activation-5.50e-02

Pos logit contributions
rast+2.011
iar+1.559
 relegation+1.540
oise+1.532
assic+1.499
Neg logit contributions
deen-2.337
…………-1.906
……………………-1.885
sth-1.774
hest-1.761
Token under
Token ID739
Feature activation+3.38e-01

Pos logit contributions
rast+0.144
iar+0.115
oise+0.112
 relegation+0.112
assic+0.110
Neg logit contributions
deen-0.145
…………-0.117
……………………-0.116
sth-0.107
 sod-0.106
Token the
Token ID262
Feature activation+1.83e-01

Pos logit contributions
deen+0.852
…………+0.679
……………………+0.671
sth+0.621
 sod+0.611
Neg logit contributions
rast-0.928
iar-0.748
oise-0.734
 relegation-0.730
assic-0.717
Token list
Token ID1351
Feature activation+3.84e-01

Pos logit contributions
deen+0.469
…………+0.376
……………………+0.372
sth+0.344
 sod+0.340
Neg logit contributions
rast-0.493
iar-0.393
oise-0.386
 relegation-0.383
assic-0.376
Token (
Token ID357
Feature activation-1.72e-01

Pos logit contributions
deen+2.701
…………+2.226
……………………+2.208
sth+2.050
 sod+2.039
Neg logit contributions
rast-2.311
iar-1.813
oise-1.746
 relegation-1.721
assic-1.690
Tokentem
Token ID11498
Feature activation-4.82e-01

Pos logit contributions
rast+0.466
iar+0.374
 relegation+0.366
oise+0.366
assic+0.355
Neg logit contributions
deen-0.443
…………-0.352
……………………-0.348
sth-0.323
hest-0.320
Tokenperature
Token ID21069
Feature activation+3.34e-01

Pos logit contributions
rast+1.029
iar+0.773
oise+0.749
 relegation+0.747
orth+0.715
Neg logit contributions
deen-1.515
…………-1.262
……………………-1.252
sth-1.179
hest-1.171
Token-
Token ID12
Feature activation-2.89e-01

Pos logit contributions
deen+0.925
…………+0.754
……………………+0.748
sth+0.691
hest+0.687
Neg logit contributions
rast-0.836
iar-0.660
oise-0.640
 relegation-0.634
assic-0.620
Tokenam
Token ID321
Feature activation-1.08e+00

Pos logit contributions
rast+0.799
iar+0.648
oise+0.632
 relegation+0.630
assic+0.613
Neg logit contributions
deen-0.725
…………-0.572
……………………-0.566
sth-0.523
hest-0.518
Tokenpl
Token ID489
Feature activation-2.45e+00

Pos logit contributions
rast+2.544
iar+1.952
oise+1.900
 relegation+1.884
orth+1.838
Neg logit contributions
deen-3.168
…………-2.599
……………………-2.577
sth-2.409
hest-2.390
Tokenifying
Token ID4035
Feature activation-8.45e-01

Pos logit contributions
rast+6.135
iar+4.996
oise+4.750
 relegation+4.614
assic+4.566
Neg logit contributions
deen-6.600
…………-5.344
……………………-5.284
sth-4.964
 sod-4.904
Token)
Token ID8
Feature activation-2.96e-01

Pos logit contributions
rast+2.032
iar+1.582
oise+1.544
 relegation+1.531
orth+1.484
Neg logit contributions
deen-2.414
…………-1.964
……………………-1.943
sth-1.831
hest-1.809
Token and
Token ID290
Feature activation-3.68e-01

Pos logit contributions
rast+0.710
iar+0.554
oise+0.536
 relegation+0.531
orth+0.516
Neg logit contributions
deen-0.855
…………-0.702
……………………-0.696
sth-0.648
 sod-0.644
Token negative
Token ID4633
Feature activation+6.46e-01

Pos logit contributions
rast+0.769
iar+0.572
oise+0.556
 relegation+0.548
orth+0.529
Neg logit contributions
deen-1.171
…………-0.979
……………………-0.970
sth-0.915
hest-0.909
Token (
Token ID357
Feature activation-4.50e-01

Pos logit contributions
deen+1.529
…………+1.201
……………………+1.184
sth+1.080
 sod+1.077
Neg logit contributions
rast-1.867
iar-1.538
oise-1.493
 relegation-1.476
orth-1.448
Token between
Token ID1022
Feature activation-4.51e-01

Pos logit contributions
deen+0.559
…………+0.450
……………………+0.445
sth+0.412
hest+0.405
Neg logit contributions
rast-0.590
iar-0.474
oise-0.464
 relegation-0.463
assic-0.449
Token her
Token ID607
Feature activation-3.47e-01

Pos logit contributions
rast+1.141
iar+0.900
oise+0.877
 relegation+0.873
orth+0.848
Neg logit contributions
deen-1.239
…………-1.002
……………………-0.991
sth-0.925
hest-0.915
Token and
Token ID290
Feature activation+3.99e-01

Pos logit contributions
rast+0.936
iar+0.750
oise+0.732
 relegation+0.728
orth+0.709
Neg logit contributions
deen-0.899
…………-0.717
……………………-0.709
sth-0.657
hest-0.649
Token manager
Token ID4706
Feature activation-2.47e-01

Pos logit contributions
deen+1.061
…………+0.864
……………………+0.851
sth+0.789
hest+0.786
Neg logit contributions
rast-1.034
iar-0.823
oise-0.799
 relegation-0.789
assic-0.786
Token Michelle
Token ID16738
Feature activation-7.40e-01

Pos logit contributions
rast+0.617
iar+0.484
oise+0.472
 relegation+0.469
assic+0.458
Neg logit contributions
deen-0.688
…………-0.559
……………………-0.552
sth-0.515
hest-0.510
Token Po
Token ID7695
Feature activation-2.43e+00

Pos logit contributions
rast+1.889
iar+1.493
oise+1.456
 relegation+1.449
orth+1.407
Neg logit contributions
deen-2.018
…………-1.628
……………………-1.612
sth-1.503
hest-1.486
Tokenague
Token ID2064
Feature activation+2.33e-01

Pos logit contributions
rast+6.663
iar+5.432
oise+5.288
orth+5.212
 relegation+5.158
Neg logit contributions
deen-5.975
…………-4.727
……………………-4.699
 sod-4.286
sth-4.285
Token.
Token ID13
Feature activation+1.50e-01

Pos logit contributions
deen+0.588
…………+0.470
……………………+0.462
sth+0.429
hest+0.422
Neg logit contributions
rast-0.641
iar-0.513
 relegation-0.504
oise-0.502
assic-0.492
Token At
Token ID1629
Feature activation+1.75e-01

Pos logit contributions
deen+0.391
…………+0.318
……………………+0.314
sth+0.287
hest+0.285
Neg logit contributions
rast-0.397
iar-0.316
 relegation-0.310
oise-0.309
assic-0.304
Token 8
Token ID807
Feature activation+7.98e-02

Pos logit contributions
deen+0.429
…………+0.344
……………………+0.339
sth+0.310
 sod+0.308
Neg logit contributions
rast-0.486
iar-0.397
oise-0.385
 relegation-0.384
assic-0.382
Token:
Token ID25
Feature activation+5.32e-02

Pos logit contributions
deen+0.178
…………+0.140
……………………+0.138
sth+0.125
 sod+0.123
Neg logit contributions
rast-0.239
iar-0.199
 relegation-0.194
oise-0.193
assic-0.190
Token runoff
Token ID37536
Feature activation-9.25e-01

Pos logit contributions
deen+1.015
…………+0.847
……………………+0.840
sth+0.789
 sod+0.785
Neg logit contributions
rast-0.726
iar-0.547
oise-0.533
 relegation-0.518
orth-0.510
Token against
Token ID1028
Feature activation-2.03e-01

Pos logit contributions
rast+2.280
iar+1.787
oise+1.741
 relegation+1.740
orth+1.680
Neg logit contributions
deen-2.600
…………-2.102
……………………-2.082
sth-1.952
hest-1.935
Token Rep
Token ID1432
Feature activation+9.17e-02

Pos logit contributions
rast+0.517
iar+0.408
oise+0.397
 relegation+0.390
orth+0.386
Neg logit contributions
deen-0.556
…………-0.452
……………………-0.446
 sod-0.413
sth-0.413
Token.
Token ID13
Feature activation-4.70e-01

Pos logit contributions
deen+0.220
…………+0.174
……………………+0.173
sth+0.157
hest+0.157
Neg logit contributions
rast-0.261
iar-0.212
oise-0.209
 relegation-0.208
assic-0.204
Token Bill
Token ID3941
Feature activation-6.10e-01

Pos logit contributions
rast+1.191
iar+0.936
oise+0.916
 relegation+0.906
assic+0.886
Neg logit contributions
deen-1.292
…………-1.050
……………………-1.041
sth-0.966
 sod-0.962
Token Cassidy
Token ID41373
Feature activation-2.43e+00

Pos logit contributions
rast+1.544
iar+1.218
oise+1.183
 relegation+1.179
orth+1.149
Neg logit contributions
deen-1.677
…………-1.346
……………………-1.338
sth-1.252
hest-1.234
Token,
Token ID11
Feature activation+6.59e-02

Pos logit contributions
rast+6.264
iar+5.035
oise+4.897
 relegation+4.873
orth+4.754
Neg logit contributions
deen-6.468
…………-5.057
……………………-5.005
sth-4.710
hest-4.660
Token
Token ID564
Feature activation+9.41e-01

Pos logit contributions
deen+0.171
…………+0.138
……………………+0.138
 sod+0.127
sth+0.127
Neg logit contributions
rast-0.174
iar-0.139
oise-0.136
 relegation-0.133
orth-0.133
Token
Token ID250
Feature activation-3.58e-02

Pos logit contributions
deen+1.980
……………………+1.497
…………+1.496
sth+1.322
hest+1.311
Neg logit contributions
rast-2.927
iar-2.462
 relegation-2.415
oise-2.410
orth-2.353
Tokenstanding
Token ID5646
Feature activation+1.00e+00

Pos logit contributions
rast+0.097
iar+0.078
 relegation+0.076
oise+0.076
assic+0.074
Neg logit contributions
deen-0.092
…………-0.073
……………………-0.073
sth-0.068
hest-0.067
Token
Token ID447
Feature activation+1.05e-01

Pos logit contributions
deen+2.630
…………+2.119
……………………+2.111
 sod+1.961
sth+1.954
Neg logit contributions
rast-2.606
iar-2.058
 relegation-1.988
oise-1.986
assic-1.976
TokenSte
Token ID7447
Feature activation-1.29e+00

Pos logit contributions
deen+0.288
…………+0.234
……………………+0.230
sth+0.209
hest+0.205
Neg logit contributions
rast-0.320
iar-0.259
 relegation-0.256
oise-0.253
assic-0.249
Tokenlla
Token ID8466
Feature activation-1.02e+00

Pos logit contributions
rast+4.285
iar+3.597
oise+3.533
 relegation+3.515
orth+3.446
Neg logit contributions
deen-2.524
…………-1.844
……………………-1.816
sth-1.627
hest-1.596
Token-
Token ID12
Feature activation-1.75e-01

Pos logit contributions
rast+2.730
iar+2.187
oise+2.135
 relegation+2.122
orth+2.067
Neg logit contributions
deen-2.656
…………-2.112
……………………-2.091
sth-1.946
hest-1.922
Tokensan
Token ID12807
Feature activation-5.99e-01

Pos logit contributions
rast+0.462
iar+0.367
 relegation+0.360
oise+0.360
orth+0.349
Neg logit contributions
deen-0.462
…………-0.371
……………………-0.366
sth-0.340
hest-0.336
Token collapsed
Token ID14707
Feature activation-3.51e-01

Pos logit contributions
rast+1.608
iar+1.285
oise+1.256
 relegation+1.254
orth+1.216
Neg logit contributions
deen-1.555
…………-1.247
……………………-1.230
sth-1.141
hest-1.126
Token?」
Token ID42943
Feature activation-2.41e+00

Pos logit contributions
rast+0.933
iar+0.741
oise+0.726
 relegation+0.721
assic+0.704
Neg logit contributions
deen-0.926
…………-0.749
……………………-0.737
sth-0.681
 sod-0.674
Token
Token ID198
Feature activation-2.87e-01

Pos logit contributions
rast+5.625
iar+4.382
oise+4.286
 relegation+4.131
orth+4.048
Neg logit contributions
deen-6.735
…………-5.380
……………………-5.347
hest-5.167
sth-5.139
Token
Token ID198
Feature activation-1.27e-01

Pos logit contributions
rast+0.755
iar+0.603
 relegation+0.589
oise+0.587
assic+0.572
Neg logit contributions
deen-0.758
…………-0.613
……………………-0.606
sth-0.562
hest-0.554
Token"
Token ID1
Feature activation+8.44e-01

Pos logit contributions
rast+0.325
iar+0.257
 relegation+0.253
oise+0.250
assic+0.244
Neg logit contributions
deen-0.345
…………-0.283
……………………-0.279
sth-0.258
hest-0.254
TokenYes
Token ID5297
Feature activation-1.51e-01

Pos logit contributions
deen+2.104
…………+1.778
……………………+1.736
sth+1.555
hest+1.521
Neg logit contributions
rast-2.317
 relegation-1.871
iar-1.863
assic-1.813
oise-1.807
Token.
Token ID13
Feature activation-5.00e-02

Pos logit contributions
rast+0.407
iar+0.325
oise+0.320
 relegation+0.319
assic+0.311
Neg logit contributions
deen-0.388
…………-0.314
……………………-0.309
sth-0.284
 sod-0.280
Token to
Token ID284
Feature activation-1.39e-01

Pos logit contributions
deen+0.031
…………+0.025
……………………+0.025
sth+0.023
 sod+0.023
Neg logit contributions
rast-0.029
iar-0.023
oise-0.023
 relegation-0.022
orth-0.022
Token."
Token ID526
Feature activation-1.97e-01

Pos logit contributions
rast+0.356
iar+0.280
oise+0.274
 relegation+0.272
assic+0.265
Neg logit contributions
deen-0.377
…………-0.306
……………………-0.302
sth-0.280
 sod-0.278
Token
Token ID198
Feature activation+4.17e-01

Pos logit contributions
rast+0.524
iar+0.420
oise+0.410
 relegation+0.408
assic+0.400
Neg logit contributions
deen-0.513
…………-0.415
……………………-0.411
sth-0.379
hest-0.374
Token
Token ID198
Feature activation+4.05e-01

Pos logit contributions
deen+1.045
…………+0.851
……………………+0.841
sth+0.770
 sod+0.760
Neg logit contributions
rast-1.135
iar-0.919
 relegation-0.908
oise-0.893
assic-0.891
TokenB
Token ID33
Feature activation+1.24e+00

Pos logit contributions
deen+0.992
…………+0.806
……………………+0.800
sth+0.726
hest+0.714
Neg logit contributions
rast-1.130
iar-0.915
 relegation-0.911
oise-0.895
assic-0.878
Tokenatt
Token ID1078
Feature activation-2.41e+00

Pos logit contributions
deen+2.578
…………+1.918
……………………+1.905
hest+1.760
sth+1.760
Neg logit contributions
rast-3.787
 relegation-3.193
iar-3.162
oise-3.095
 failings-3.037
Tokeniat
Token ID5375
Feature activation-1.36e+00

Pos logit contributions
rast+7.366
iar+6.084
oise+5.950
 relegation+5.843
orth+5.759
Neg logit contributions
deen-5.283
…………-4.006
……………………-3.916
sth-3.582
 sod-3.518
Tokeno
Token ID78
Feature activation+8.47e-02

Pos logit contributions
rast+3.407
iar+2.686
oise+2.614
 relegation+2.597
orth+2.524
Neg logit contributions
deen-3.745
…………-3.032
……………………-3.002
sth-2.802
hest-2.771
Token said
Token ID531
Feature activation+3.86e-01

Pos logit contributions
deen+0.248
…………+0.205
……………………+0.203
sth+0.190
hest+0.188
Neg logit contributions
rast-0.198
iar-0.152
 relegation-0.149
oise-0.149
assic-0.144
Token The
Token ID383
Feature activation+2.36e-01

Pos logit contributions
deen+1.009
…………+0.823
……………………+0.815
sth+0.752
 sod+0.747
Neg logit contributions
rast-1.015
iar-0.812
oise-0.797
 relegation-0.777
assic-0.773
Token World
Token ID2159
Feature activation-2.26e-01

Pos logit contributions
deen+0.622
…………+0.499
……………………+0.497
sth+0.461
hest+0.454
Neg logit contributions
rast-0.623
iar-0.495
oise-0.483
 relegation-0.481
assic-0.474
Token called
Token ID1444
Feature activation-4.54e-01

Pos logit contributions
rast+0.393
iar+0.307
oise+0.302
 relegation+0.298
orth+0.290
Neg logit contributions
deen-0.443
…………-0.362
……………………-0.358
 sod-0.335
sth-0.335
Token absurd
Token ID12986
Feature activation-6.83e-01

Pos logit contributions
rast+1.192
iar+0.946
oise+0.926
 relegation+0.921
orth+0.900
Neg logit contributions
deen-1.199
…………-0.967
……………………-0.955
sth-0.885
 sod-0.877
Token and
Token ID290
Feature activation+1.03e-02

Pos logit contributions
rast+1.845
iar+1.474
oise+1.447
 relegation+1.439
orth+1.400
Neg logit contributions
deen-1.756
…………-1.405
……………………-1.387
sth-1.286
hest-1.269
Token fear
Token ID3252
Feature activation-7.93e-01

Pos logit contributions
deen+0.030
…………+0.025
……………………+0.025
 sod+0.023
sth+0.023
Neg logit contributions
rast-0.024
iar-0.018
oise-0.018
 relegation-0.017
orth-0.017
Token m
Token ID285
Feature activation+7.21e-01

Pos logit contributions
rast+1.864
iar+1.450
oise+1.405
 relegation+1.398
orth+1.351
Neg logit contributions
deen-2.314
…………-1.893
……………………-1.876
sth-1.761
hest-1.743
Tokenong
Token ID506
Feature activation-2.39e+00

Pos logit contributions
deen+1.727
…………+1.377
……………………+1.354
sth+1.263
hest+1.244
Neg logit contributions
rast-2.025
 relegation-1.631
oise-1.619
iar-1.614
assic-1.554
Tokenering
Token ID1586
Feature activation-1.18e-01

Pos logit contributions
rast+7.165
iar+5.931
oise+5.773
 relegation+5.687
assic+5.623
Neg logit contributions
deen-5.356
…………-4.103
……………………-4.055
sth-3.629
 sod-3.588
Token.
Token ID13
Feature activation+6.33e-02

Pos logit contributions
rast+0.321
iar+0.257
oise+0.253
 relegation+0.250
orth+0.246
Neg logit contributions
deen-0.298
…………-0.241
……………………-0.237
 sod-0.218
sth-0.217
Token
Token ID198
Feature activation+7.15e-02

Pos logit contributions
deen+0.163
…………+0.133
……………………+0.131
sth+0.120
hest+0.119
Neg logit contributions
rast-0.169
iar-0.136
oise-0.133
 relegation-0.133
assic-0.130
Token
Token ID198
Feature activation-1.23e-03

Pos logit contributions
deen+0.183
…………+0.149
……………………+0.147
sth+0.135
 sod+0.133
Neg logit contributions
rast-0.192
iar-0.154
 relegation-0.152
oise-0.150
assic-0.148
TokenThe
Token ID464
Feature activation-1.24e-01

Pos logit contributions
rast+0.003
iar+0.003
 relegation+0.003
oise+0.003
assic+0.003
Neg logit contributions
deen-0.003
…………-0.002
……………………-0.002
sth-0.002
hest-0.002
Token the
Token ID262
Feature activation-7.80e-02

Pos logit contributions
rast+0.049
iar+0.039
oise+0.038
 relegation+0.038
assic+0.037
Neg logit contributions
deen-0.048
…………-0.039
……………………-0.038
sth-0.035
 sod-0.035
Token smoker
Token ID41644
Feature activation+7.13e-01

Pos logit contributions
rast+0.193
iar+0.152
oise+0.148
 relegation+0.147
orth+0.143
Neg logit contributions
deen-0.218
…………-0.177
……………………-0.175
sth-0.164
 sod-0.162
Token,
Token ID11
Feature activation-2.02e-02

Pos logit contributions
deen+1.779
…………+1.442
……………………+1.416
sth+1.293
hest+1.287
Neg logit contributions
rast-1.963
iar-1.580
 relegation-1.547
oise-1.545
assic-1.503
Token like
Token ID588
Feature activation-3.14e-01

Pos logit contributions
rast+0.053
iar+0.042
oise+0.041
 relegation+0.040
assic+0.039
Neg logit contributions
deen-0.054
…………-0.044
……………………-0.043
sth-0.040
hest-0.040
Token k
Token ID479
Feature activation-2.05e-01

Pos logit contributions
rast+0.843
iar+0.676
oise+0.660
 relegation+0.657
orth+0.639
Neg logit contributions
deen-0.815
…………-0.649
……………………-0.642
sth-0.597
hest-0.590
Tokenung
Token ID2150
Feature activation-2.38e+00

Pos logit contributions
rast+0.547
iar+0.436
 relegation+0.431
oise+0.428
assic+0.414
Neg logit contributions
deen-0.532
…………-0.423
……………………-0.418
sth-0.390
hest-0.385
Token p
Token ID279
Feature activation-4.03e-01

Pos logit contributions
rast+6.486
iar+5.250
oise+5.085
 relegation+5.006
orth+4.889
Neg logit contributions
deen-5.852
…………-4.601
……………………-4.506
hest-4.223
sth-4.194
Tokenao
Token ID5488
Feature activation-1.67e+00

Pos logit contributions
rast+0.942
 relegation+0.726
iar+0.704
oise+0.701
orth+0.675
Neg logit contributions
deen-1.187
…………-0.972
……………………-0.959
hest-0.912
sth-0.902
Token cor
Token ID1162
Feature activation-5.19e-01

Pos logit contributions
rast+4.309
iar+3.446
oise+3.365
 relegation+3.309
orth+3.235
Neg logit contributions
deen-4.431
…………-3.497
……………………-3.479
sth-3.270
hest-3.231
Tokenned
Token ID2817
Feature activation-1.05e-01

Pos logit contributions
rast+1.224
iar+0.945
oise+0.920
 relegation+0.917
orth+0.886
Neg logit contributions
deen-1.514
…………-1.241
……………………-1.229
sth-1.154
hest-1.141
Token beef
Token ID12023
Feature activation-1.46e-01

Pos logit contributions
rast+0.244
iar+0.188
 relegation+0.183
oise+0.181
assic+0.179
Neg logit contributions
deen-0.312
…………-0.255
……………………-0.254
sth-0.237
 sod-0.234
Token can
Token ID460
Feature activation+6.74e-01

Pos logit contributions
deen+2.054
…………+1.665
……………………+1.636
 sod+1.527
sth+1.526
Neg logit contributions
rast-1.960
oise-1.527
iar-1.527
 relegation-1.482
assic-1.475
Token do
Token ID466
Feature activation+8.99e-01

Pos logit contributions
deen+1.816
…………+1.466
……………………+1.439
sth+1.345
 sod+1.333
Neg logit contributions
rast-1.733
iar-1.380
oise-1.358
 relegation-1.327
assic-1.323
Token to
Token ID284
Feature activation+8.15e-01

Pos logit contributions
deen+2.514
…………+2.089
……………………+2.045
sth+1.903
 sod+1.893
Neg logit contributions
rast-2.163
iar-1.709
oise-1.679
 relegation-1.651
assic-1.629
Token combat
Token ID5249
Feature activation+4.83e-01

Pos logit contributions
deen+2.183
…………+1.775
……………………+1.743
 sod+1.631
hest+1.596
Neg logit contributions
rast-2.097
iar-1.664
oise-1.616
 relegation-1.600
assic-1.591
Token this
Token ID428
Feature activation+4.99e-01

Pos logit contributions
deen+1.190
…………+0.949
……………………+0.932
 sod+0.874
sth+0.863
Neg logit contributions
rast-1.337
iar-1.087
oise-1.063
assic-1.045
 relegation-1.039
Token wave
Token ID6769
Feature activation-2.36e+00

Pos logit contributions
deen+1.439
…………+1.200
……………………+1.184
 sod+1.125
sth+1.107
Neg logit contributions
rast-1.167
iar-0.900
oise-0.886
assic-0.855
orth-0.845
Token of
Token ID286
Feature activation-3.40e-01

Pos logit contributions
rast+5.355
iar+4.095
 relegation+4.002
oise+3.933
orth+3.838
Neg logit contributions
deen-6.901
…………-5.623
……………………-5.616
sth-5.252
hest-5.213
Token misinformation
Token ID32805
Feature activation-1.20e+00

Pos logit contributions
rast+0.777
iar+0.600
oise+0.582
 relegation+0.565
assic+0.560
Neg logit contributions
deen-1.009
…………-0.838
……………………-0.830
 sod-0.782
sth-0.780
Token is
Token ID318
Feature activation+6.59e-01

Pos logit contributions
rast+2.803
iar+2.161
oise+2.101
 relegation+2.087
orth+2.021
Neg logit contributions
deen-3.553
…………-2.923
……………………-2.894
sth-2.718
hest-2.688
Token to
Token ID284
Feature activation+2.33e-01

Pos logit contributions
deen+1.772
…………+1.453
……………………+1.432
 sod+1.328
sth+1.321
Neg logit contributions
rast-1.679
iar-1.334
oise-1.302
 relegation-1.280
assic-1.276
Token talk
Token ID1561
Feature activation-1.81e-01

Pos logit contributions
deen+0.634
…………+0.515
……………………+0.508
 sod+0.472
sth+0.470
Neg logit contributions
rast-0.596
iar-0.472
oise-0.460
 relegation-0.454
assic-0.449
Token basement
Token ID17012
Feature activation+2.00e-01

Pos logit contributions
rast+0.242
iar+0.194
oise+0.189
 relegation+0.186
assic+0.182
Neg logit contributions
deen-0.244
…………-0.196
……………………-0.194
sth-0.180
 sod-0.179
Token of
Token ID286
Feature activation+2.62e-01

Pos logit contributions
deen+0.504
…………+0.406
……………………+0.398
 sod+0.367
sth+0.366
Neg logit contributions
rast-0.550
iar-0.442
oise-0.435
 relegation-0.428
assic-0.424
Token concrete
Token ID10017
Feature activation+3.33e-01

Pos logit contributions
deen+0.697
…………+0.563
……………………+0.555
 sod+0.516
sth+0.515
Neg logit contributions
rast-0.682
iar-0.541
oise-0.530
 relegation-0.524
assic-0.512
Token.
Token ID13
Feature activation-4.35e-02

Pos logit contributions
deen+0.858
…………+0.697
……………………+0.682
 sod+0.633
sth+0.631
Neg logit contributions
rast-0.895
iar-0.717
oise-0.705
 relegation-0.695
assic-0.683
Token Ma
Token ID6669
Feature activation-1.49e+00

Pos logit contributions
rast+0.114
iar+0.091
oise+0.089
 relegation+0.089
assic+0.086
Neg logit contributions
deen-0.115
…………-0.094
……………………-0.093
sth-0.085
 sod-0.084
Tokenori
Token ID10145
Feature activation-2.35e+00

Pos logit contributions
rast+4.008
iar+3.213
oise+3.140
 relegation+3.109
orth+3.038
Neg logit contributions
deen-3.839
…………-3.039
……………………-3.009
sth-2.796
hest-2.760
Token affairs
Token ID9674
Feature activation+6.37e-02

Pos logit contributions
rast+6.027
iar+4.800
oise+4.644
 relegation+4.629
orth+4.516
Neg logit contributions
deen-6.260
…………-4.933
……………………-4.907
sth-4.598
hest-4.586
Token and
Token ID290
Feature activation+1.49e-01

Pos logit contributions
deen+0.173
…………+0.142
……………………+0.140
sth+0.130
 sod+0.128
Neg logit contributions
rast-0.162
iar-0.128
oise-0.126
 relegation-0.124
assic-0.121
Token state
Token ID1181
Feature activation-2.64e-01

Pos logit contributions
deen+0.403
…………+0.331
……………………+0.327
 sod+0.301
sth+0.301
Neg logit contributions
rast-0.381
iar-0.301
oise-0.298
 relegation-0.289
assic-0.286
Token housing
Token ID5627
Feature activation+7.41e-01

Pos logit contributions
rast+0.665
iar+0.523
oise+0.512
 relegation+0.504
assic+0.495
Neg logit contributions
deen-0.728
…………-0.596
……………………-0.590
sth-0.548
 sod-0.542
Token did
Token ID750
Feature activation+4.98e-01

Pos logit contributions
deen+2.003
…………+1.658
……………………+1.629
sth+1.495
 sod+1.482
Neg logit contributions
rast-1.861
iar-1.476
oise-1.465
 relegation-1.421
assic-1.413
Token eaten
Token ID17065
Feature activation+2.30e-01

Pos logit contributions
rast+1.078
iar+0.841
oise+0.817
 relegation+0.812
orth+0.787
Neg logit contributions
deen-1.276
…………-1.043
……………………-1.032
sth-0.965
 sod-0.959
Token her
Token ID607
Feature activation-7.74e-01

Pos logit contributions
deen+0.600
…………+0.483
……………………+0.478
 sod+0.448
sth+0.439
Neg logit contributions
rast-0.610
iar-0.487
oise-0.476
 relegation-0.469
orth-0.464
Token mother
Token ID2802
Feature activation-6.10e-01

Pos logit contributions
rast+1.940
iar+1.522
oise+1.488
 relegation+1.476
orth+1.435
Neg logit contributions
deen-2.150
…………-1.743
……………………-1.724
sth-1.607
 sod-1.593
Token's
Token ID338
Feature activation-6.81e-01

Pos logit contributions
rast+1.441
iar+1.112
oise+1.080
 relegation+1.079
orth+1.043
Neg logit contributions
deen-1.785
…………-1.463
……………………-1.449
sth-1.358
 sod-1.349
Token d
Token ID288
Feature activation+2.23e-01

Pos logit contributions
rast+1.847
iar+1.479
oise+1.447
 relegation+1.435
orth+1.402
Neg logit contributions
deen-1.757
…………-1.397
……………………-1.382
sth-1.278
 sod-1.272
Tokenung
Token ID2150
Feature activation-2.34e+00

Pos logit contributions
deen+0.686
…………+0.565
……………………+0.559
hest+0.526
sth+0.525
Neg logit contributions
rast-0.487
 relegation-0.367
iar-0.367
oise-0.358
assic-0.342
Token to
Token ID284
Feature activation-1.39e-01

Pos logit contributions
rast+5.878
iar+4.690
oise+4.538
 relegation+4.462
orth+4.383
Neg logit contributions
deen-6.238
…………-5.045
……………………-5.012
sth-4.698
hest-4.653
Token acquire
Token ID12831
Feature activation-4.08e-01

Pos logit contributions
rast+0.365
iar+0.289
oise+0.283
 relegation+0.281
orth+0.273
Neg logit contributions
deen-0.369
…………-0.296
……………………-0.292
 sod-0.271
sth-0.271
Token the
Token ID262
Feature activation+1.04e-01

Pos logit contributions
rast+1.068
iar+0.848
oise+0.830
 relegation+0.820
orth+0.802
Neg logit contributions
deen-1.087
…………-0.877
……………………-0.866
sth-0.804
 sod-0.803
Token gut
Token ID12500
Feature activation+5.59e-03

Pos logit contributions
deen+0.274
…………+0.220
……………………+0.217
 sod+0.204
sth+0.201
Neg logit contributions
rast-0.276
iar-0.221
oise-0.215
 relegation-0.212
orth-0.209
Token microbes
Token ID33712
Feature activation+1.64e-01

Pos logit contributions
deen+0.015
…………+0.012
……………………+0.012
sth+0.011
hest+0.011
Neg logit contributions
rast-0.014
iar-0.011
 relegation-0.011
oise-0.011
assic-0.011
Token order
Token ID1502
Feature activation-1.42e-01

Pos logit contributions
rast+0.547
iar+0.438
oise+0.424
 relegation+0.423
assic+0.411
Neg logit contributions
deen-0.583
…………-0.474
……………………-0.467
sth-0.437
hest-0.431
Token to
Token ID284
Feature activation+2.28e-02

Pos logit contributions
rast+0.335
iar+0.257
oise+0.251
 relegation+0.249
orth+0.241
Neg logit contributions
deen-0.417
…………-0.340
……………………-0.337
sth-0.317
hest-0.314
Token synchron
Token ID18305
Feature activation-8.02e-01

Pos logit contributions
deen+0.062
…………+0.051
……………………+0.050
sth+0.046
 sod+0.046
Neg logit contributions
rast-0.058
iar-0.046
oise-0.045
 relegation-0.044
assic-0.043
Tokenize
Token ID1096
Feature activation-5.35e-01

Pos logit contributions
rast+1.267
iar+0.833
 relegation+0.794
oise+0.785
orth+0.743
Neg logit contributions
deen-2.970
…………-2.550
……………………-2.530
sth-2.415
hest-2.394
Token D
Token ID360
Feature activation-4.49e-01

Pos logit contributions
rast+1.412
iar+1.128
oise+1.100
 relegation+1.095
orth+1.066
Neg logit contributions
deen-1.409
…………-1.130
……………………-1.117
sth-1.039
hest-1.024
TokenDoS
Token ID46498
Feature activation-2.34e+00

Pos logit contributions
rast+1.114
iar+0.879
 relegation+0.864
oise+0.856
assic+0.828
Neg logit contributions
deen-1.247
…………-1.018
……………………-1.005
sth-0.944
hest-0.927
Token mitigation
Token ID33585
Feature activation-5.65e-01

Pos logit contributions
rast+4.523
iar+3.254
oise+3.186
 relegation+3.100
orth+2.924
Neg logit contributions
deen-7.730
…………-6.451
……………………-6.429
sth-6.110
hest-6.039
Token perfectly
Token ID7138
Feature activation-2.18e-02

Pos logit contributions
rast+1.433
iar+1.139
oise+1.104
 relegation+1.103
orth+1.075
Neg logit contributions
deen-1.541
…………-1.254
……………………-1.238
sth-1.155
 sod-1.139
Token with
Token ID351
Feature activation-3.01e-01

Pos logit contributions
rast+0.059
iar+0.048
oise+0.047
 relegation+0.047
assic+0.046
Neg logit contributions
deen-0.055
…………-0.044
……………………-0.043
sth-0.040
hest-0.040
Token the
Token ID262
Feature activation-3.65e-01

Pos logit contributions
rast+0.825
iar+0.667
oise+0.651
 relegation+0.648
orth+0.633
Neg logit contributions
deen-0.758
…………-0.603
……………………-0.594
sth-0.551
hest-0.543
Token changing
Token ID5609
Feature activation-2.01e-02

Pos logit contributions
rast+0.975
iar+0.783
oise+0.762
 relegation+0.759
orth+0.743
Neg logit contributions
deen-0.949
…………-0.760
……………………-0.749
sth-0.697
hest-0.689
Token),
Token ID828
Feature activation+8.55e-02

Pos logit contributions
rast+1.706
iar+1.342
oise+1.308
 relegation+1.301
orth+1.262
Neg logit contributions
deen-1.887
…………-1.529
……………………-1.513
sth-1.414
hest-1.398
Token Has
Token ID7875
Feature activation+5.63e-01

Pos logit contributions
deen+0.232
…………+0.187
……………………+0.185
sth+0.172
 sod+0.171
Neg logit contributions
rast-0.219
iar-0.173
oise-0.170
 relegation-0.168
assic-0.164
Tokeni
Token ID72
Feature activation+2.72e-01

Pos logit contributions
deen+1.466
…………+1.136
……………………+1.127
sth+1.076
hest+1.066
Neg logit contributions
rast-1.487
 relegation-1.197
iar-1.185
oise-1.167
assic-1.139
Token (
Token ID357
Feature activation-8.71e-02

Pos logit contributions
deen+0.697
…………+0.545
……………………+0.542
sth+0.505
hest+0.502
Neg logit contributions
rast-0.733
iar-0.590
 relegation-0.583
oise-0.579
orth-0.560
TokenM
Token ID44
Feature activation-4.73e-01

Pos logit contributions
rast+0.236
iar+0.190
 relegation+0.187
oise+0.186
assic+0.180
Neg logit contributions
deen-0.223
…………-0.176
……………………-0.174
sth-0.163
hest-0.161
Tokenong
Token ID506
Feature activation-2.33e+00

Pos logit contributions
rast+1.254
iar+0.999
 relegation+0.986
oise+0.980
assic+0.946
Neg logit contributions
deen-1.239
…………-0.987
……………………-0.978
sth-0.914
hest-0.903
Tokenol
Token ID349
Feature activation-3.20e-01

Pos logit contributions
rast+6.836
iar+5.608
oise+5.477
orth+5.345
assic+5.342
Neg logit contributions
deen-5.319
…………-4.153
……………………-4.080
sth-3.714
 sod-3.675
Tokenian
Token ID666
Feature activation+2.73e-02

Pos logit contributions
rast+0.898
iar+0.722
oise+0.709
 relegation+0.707
orth+0.687
Neg logit contributions
deen-0.793
…………-0.624
……………………-0.618
sth-0.572
hest-0.565
Token form
Token ID1296
Feature activation+3.99e-01

Pos logit contributions
deen+0.074
…………+0.060
……………………+0.060
sth+0.056
 sod+0.055
Neg logit contributions
rast-0.070
iar-0.055
oise-0.054
 relegation-0.053
assic-0.052
Token of
Token ID286
Feature activation-1.82e-01

Pos logit contributions
deen+1.080
…………+0.861
……………………+0.855
sth+0.800
hest+0.794
Neg logit contributions
rast-1.023
iar-0.815
oise-0.795
 relegation-0.789
assic-0.766
Token Tang
Token ID18816
Feature activation-1.15e+00

Pos logit contributions
rast+0.477
iar+0.379
oise+0.371
 relegation+0.368
orth+0.358
Neg logit contributions
deen-0.485
…………-0.388
……………………-0.384
sth-0.358
 sod-0.354
Token title
Token ID3670
Feature activation+2.75e-01

Pos logit contributions
rast+1.736
iar+1.361
oise+1.330
 relegation+1.315
orth+1.281
Neg logit contributions
deen-1.935
…………-1.571
……………………-1.552
sth-1.452
hest-1.443
Token.
Token ID13
Feature activation-1.52e-01

Pos logit contributions
deen+0.689
…………+0.546
……………………+0.536
sth+0.497
hest+0.496
Neg logit contributions
rast-0.760
iar-0.612
oise-0.601
 relegation-0.593
orth-0.580
Token
Token ID198
Feature activation+1.01e-03

Pos logit contributions
rast+0.401
iar+0.320
oise+0.313
 relegation+0.312
assic+0.304
Neg logit contributions
deen-0.401
…………-0.322
……………………-0.318
sth-0.295
hest-0.294
Token
Token ID198
Feature activation+2.35e-02

Pos logit contributions
deen+0.003
…………+0.002
……………………+0.002
sth+0.002
 sod+0.002
Neg logit contributions
rast-0.003
iar-0.002
 relegation-0.002
oise-0.002
assic-0.002
TokenB
Token ID33
Feature activation+9.15e-01

Pos logit contributions
deen+0.057
…………+0.046
……………………+0.045
sth+0.041
hest+0.041
Neg logit contributions
rast-0.066
iar-0.053
 relegation-0.053
oise-0.052
assic-0.051
Tokenung
Token ID2150
Feature activation-2.32e+00

Pos logit contributions
deen+2.843
…………+2.354
……………………+2.326
hest+2.228
sth+2.213
Neg logit contributions
rast-1.882
 relegation-1.447
iar-1.441
oise-1.400
 evolves-1.346
Tokenie
Token ID494
Feature activation-3.15e-01

Pos logit contributions
rast+3.676
iar+2.522
oise+2.358
orth+2.156
 relegation+2.136
Neg logit contributions
deen-8.419
…………-7.303
……………………-7.251
sth-6.848
hest-6.811
Token's
Token ID338
Feature activation+7.77e-02

Pos logit contributions
rast+0.761
iar+0.591
oise+0.575
 relegation+0.572
orth+0.555
Neg logit contributions
deen-0.903
…………-0.737
……………………-0.729
sth-0.683
hest-0.678
Token contract
Token ID2775
Feature activation-3.17e-01

Pos logit contributions
deen+0.218
…………+0.176
……………………+0.175
sth+0.163
 sod+0.163
Neg logit contributions
rast-0.192
iar-0.150
oise-0.147
 relegation-0.144
orth-0.142
Token with
Token ID351
Feature activation-5.49e-01

Pos logit contributions
rast+0.764
iar+0.596
oise+0.580
 relegation+0.573
orth+0.559
Neg logit contributions
deen-0.906
…………-0.743
……………………-0.735
sth-0.690
 sod-0.685
Token Activision
Token ID40723
Feature activation-1.27e+00

Pos logit contributions
rast+0.981
iar+0.687
oise+0.662
 relegation+0.652
orth+0.623
Neg logit contributions
deen-1.914
…………-1.628
……………………-1.613
sth-1.535
hest-1.522
Token players
Token ID1938
Feature activation-8.05e-01

Pos logit contributions
deen+1.132
…………+0.923
……………………+0.916
sth+0.853
 sod+0.850
Neg logit contributions
rast-1.020
iar-0.812
oise-0.796
 relegation-0.772
assic-0.770
Token.
Token ID13
Feature activation-4.46e-02

Pos logit contributions
rast+2.128
iar+1.700
oise+1.655
 relegation+1.652
orth+1.611
Neg logit contributions
deen-2.110
…………-1.681
……………………-1.665
sth-1.551
hest-1.533
Token<|endoftext|>
Token ID50256
Feature activation-3.01e-01

Pos logit contributions
rast+0.119
iar+0.096
oise+0.094
 relegation+0.093
assic+0.091
Neg logit contributions
deen-0.115
…………-0.093
……………………-0.092
sth-0.085
hest-0.084
TokenA
Token ID32
Feature activation-9.22e-03

Pos logit contributions
rast+0.838
iar+0.677
 relegation+0.664
oise+0.662
orth+0.641
Neg logit contributions
deen-0.750
…………-0.595
……………………-0.589
sth-0.543
hest-0.535
Token D
Token ID360
Feature activation-1.19e-01

Pos logit contributions
rast+0.024
iar+0.019
oise+0.018
 relegation+0.018
assic+0.018
Neg logit contributions
deen-0.025
…………-0.020
……………………-0.020
sth-0.019
 sod-0.018
TokenDoS
Token ID46498
Feature activation-2.31e+00

Pos logit contributions
rast+0.320
iar+0.257
oise+0.253
 relegation+0.252
orth+0.242
Neg logit contributions
deen-0.305
…………-0.243
……………………-0.240
sth-0.223
hest-0.220
Token Gap
Token ID33899
Feature activation-3.29e-01

Pos logit contributions
rast+5.393
iar+4.193
oise+4.069
 relegation+4.029
orth+3.880
Neg logit contributions
deen-6.741
…………-5.492
……………………-5.445
sth-5.137
hest-5.064
Token occurs
Token ID8833
Feature activation+6.44e-02

Pos logit contributions
rast+0.844
iar+0.669
 relegation+0.654
oise+0.652
assic+0.634
Neg logit contributions
deen-0.887
…………-0.723
……………………-0.716
sth-0.667
hest-0.658
Token whenever
Token ID8797
Feature activation+4.85e-02

Pos logit contributions
deen+0.163
…………+0.131
……………………+0.129
sth+0.118
hest+0.118
Neg logit contributions
rast-0.175
iar-0.142
oise-0.138
 relegation-0.137
assic-0.135
Token D
Token ID360
Feature activation-6.57e-02

Pos logit contributions
deen+0.127
…………+0.103
……………………+0.101
 sod+0.094
sth+0.094
Neg logit contributions
rast-0.128
iar-0.103
oise-0.100
 relegation-0.099
assic-0.098
TokenDoS
Token ID46498
Feature activation-2.30e+00

Pos logit contributions
rast+0.164
iar+0.129
 relegation+0.128
oise+0.127
assic+0.122
Neg logit contributions
deen-0.181
…………-0.147
……………………-0.145
sth-0.137
 sod-0.134
Token mainstream
Token ID8661
Feature activation+4.21e-01

Pos logit contributions
rast+0.195
iar+0.155
oise+0.150
 relegation+0.148
orth+0.145
Neg logit contributions
deen-0.209
…………-0.169
……………………-0.167
sth-0.156
 sod-0.155
Token UK
Token ID3482
Feature activation+9.97e-01

Pos logit contributions
deen+1.159
…………+0.947
……………………+0.935
sth+0.870
hest+0.867
Neg logit contributions
rast-1.057
iar-0.825
oise-0.810
 relegation-0.792
assic-0.781
Token media
Token ID2056
Feature activation-2.17e-01

Pos logit contributions
deen+2.698
…………+2.187
……………………+2.167
sth+2.007
 sod+1.999
Neg logit contributions
rast-2.534
iar-2.006
oise-1.949
 relegation-1.937
assic-1.886
Token and
Token ID290
Feature activation+1.11e-01

Pos logit contributions
rast+0.564
iar+0.447
oise+0.436
 relegation+0.433
orth+0.422
Neg logit contributions
deen-0.582
…………-0.470
……………………-0.465
sth-0.433
hest-0.427
Token the
Token ID262
Feature activation-1.52e-01

Pos logit contributions
deen+0.275
…………+0.217
……………………+0.214
sth+0.197
 sod+0.195
Neg logit contributions
rast-0.310
iar-0.251
oise-0.245
 relegation-0.243
orth-0.237
Token diss
Token ID6249
Feature activation+1.91e+00

Pos logit contributions
rast+0.397
iar+0.316
oise+0.309
 relegation+0.305
assic+0.298
Neg logit contributions
deen-0.404
…………-0.325
……………………-0.321
sth-0.298
 sod-0.296
Tokenident
Token ID738
Feature activation+1.22e+00

Pos logit contributions
deen+4.951
…………+3.995
……………………+3.912
hest+3.739
sth+3.669
Neg logit contributions
rast-4.906
iar-3.979
oise-3.921
 relegation-3.848
assic-3.737
Token Real
Token ID6416
Feature activation+6.13e-01

Pos logit contributions
deen+3.233
…………+2.599
……………………+2.578
 sod+2.375
hest+2.354
Neg logit contributions
rast-3.171
iar-2.508
oise-2.465
 relegation-2.413
assic-2.393
Token News
Token ID3000
Feature activation+7.67e-01

Pos logit contributions
deen+1.614
…………+1.280
……………………+1.276
sth+1.174
hest+1.170
Neg logit contributions
rast-1.619
iar-1.285
oise-1.265
 relegation-1.254
assic-1.231
Token Network
Token ID7311
Feature activation+7.36e-02

Pos logit contributions
deen+2.048
…………+1.651
……………………+1.636
sth+1.498
hest+1.485
Neg logit contributions
rast-2.001
iar-1.575
oise-1.550
 relegation-1.530
assic-1.507
Token,
Token ID11
Feature activation+2.71e-01

Pos logit contributions
deen+0.184
…………+0.146
……………………+0.144
sth+0.133
hest+0.131
Neg logit contributions
rast-0.204
iar-0.165
oise-0.161
 relegation-0.161
assic-0.157
Token because
Token ID780
Feature activation-4.47e-01

Pos logit contributions
deen+2.916
…………+2.429
……………………+2.382
 sod+2.202
sth+2.197
Neg logit contributions
rast-2.612
iar-2.114
oise-2.004
 relegation-1.988
orth-1.938
Token of
Token ID286
Feature activation+1.37e-01

Pos logit contributions
rast+1.160
iar+0.922
oise+0.902
 relegation+0.890
orth+0.873
Neg logit contributions
deen-1.198
…………-0.972
……………………-0.960
sth-0.886
 sod-0.881
Token their
Token ID511
Feature activation+2.00e-01

Pos logit contributions
deen+0.346
…………+0.278
……………………+0.273
sth+0.250
 sod+0.249
Neg logit contributions
rast-0.377
iar-0.304
oise-0.297
 relegation-0.294
assic-0.288
Token age
Token ID2479
Feature activation+4.42e-01

Pos logit contributions
deen+0.574
…………+0.475
……………………+0.469
 sod+0.437
sth+0.433
Neg logit contributions
rast-0.479
iar-0.374
oise-0.361
 relegation-0.355
orth-0.347
Token and
Token ID290
Feature activation-2.99e-02

Pos logit contributions
deen+1.099
…………+0.894
……………………+0.881
sth+0.798
 sod+0.791
Neg logit contributions
rast-1.215
iar-0.988
oise-0.959
 relegation-0.953
orth-0.936
Token you
Token ID345
Feature activation+1.62e+00

Pos logit contributions
rast+0.078
iar+0.062
oise+0.060
 relegation+0.059
assic+0.058
Neg logit contributions
deen-0.080
…………-0.065
……………………-0.064
 sod-0.059
sth-0.059
Token had
Token ID550
Feature activation+2.45e-01

Pos logit contributions
deen+4.262
…………+3.519
……………………+3.416
sth+3.196
 sod+3.157
Neg logit contributions
rast-4.135
iar-3.306
oise-3.242
 relegation-3.218
assic-3.151
Token some
Token ID617
Feature activation+2.63e-01

Pos logit contributions
deen+0.650
…………+0.532
……………………+0.524
 sod+0.484
sth+0.483
Neg logit contributions
rast-0.635
iar-0.504
oise-0.493
 relegation-0.486
orth-0.478
Token very
Token ID845
Feature activation+4.22e-02

Pos logit contributions
deen+0.734
…………+0.609
……………………+0.603
 sod+0.561
sth+0.554
Neg logit contributions
rast-0.644
iar-0.506
oise-0.491
 relegation-0.484
orth-0.473
Token interesting
Token ID3499
Feature activation+6.97e-01

Pos logit contributions
deen+0.118
…………+0.097
……………………+0.096
 sod+0.089
sth+0.089
Neg logit contributions
rast-0.104
iar-0.082
oise-0.080
 relegation-0.079
orth-0.077
Token things
Token ID1243
Feature activation-2.02e-01

Pos logit contributions
deen+1.988
…………+1.685
……………………+1.660
 sod+1.554
sth+1.547
Neg logit contributions
rast-1.619
iar-1.260
oise-1.235
 relegation-1.202
assic-1.170
Token adjacent
Token ID15909
Feature activation+2.50e-01

Pos logit contributions
deen+1.572
…………+1.273
……………………+1.260
 sod+1.173
sth+1.162
Neg logit contributions
rast-1.629
iar-1.302
oise-1.288
ruciating-1.245
 relegation-1.236
Token to
Token ID284
Feature activation+2.04e-02

Pos logit contributions
deen+0.715
…………+0.583
……………………+0.577
sth+0.540
hest+0.535
Neg logit contributions
rast-0.607
iar-0.474
oise-0.460
 relegation-0.458
orth-0.444
Token the
Token ID262
Feature activation-9.37e-02

Pos logit contributions
deen+0.052
…………+0.041
……………………+0.040
sth+0.038
 sod+0.037
Neg logit contributions
rast-0.056
iar-0.045
oise-0.044
 relegation-0.043
orth-0.043
Token Journal
Token ID4913
Feature activation-9.99e-01

Pos logit contributions
rast+0.241
iar+0.191
oise+0.186
 relegation+0.182
orth+0.181
Neg logit contributions
deen-0.254
…………-0.204
……………………-0.202
sth-0.189
 sod-0.188
Token Square
Token ID9276
Feature activation+5.56e-01

Pos logit contributions
rast+2.826
iar+2.287
oise+2.239
 relegation+2.229
assic+2.172
Neg logit contributions
deen-2.454
…………-1.925
……………………-1.905
sth-1.767
hest-1.746
Token PATH
Token ID46490
Feature activation+1.75e+00

Pos logit contributions
deen+1.496
…………+1.211
……………………+1.192
 sod+1.131
sth+1.125
Neg logit contributions
rast-1.426
iar-1.130
oise-1.107
 relegation-1.072
assic-1.071
Token station
Token ID4429
Feature activation-1.65e-01

Pos logit contributions
deen+4.452
…………+3.565
……………………+3.554
sth+3.413
 sod+3.340
Neg logit contributions
rast-4.516
iar-3.707
oise-3.632
ruciating-3.551
 relegation-3.515
Token as
Token ID355
Feature activation-2.08e-01

Pos logit contributions
rast+0.434
iar+0.348
oise+0.339
 relegation+0.334
assic+0.329
Neg logit contributions
deen-0.435
…………-0.351
……………………-0.346
sth-0.325
 sod-0.319
Token a
Token ID257
Feature activation+3.47e-03

Pos logit contributions
rast+0.549
iar+0.439
oise+0.430
 relegation+0.423
orth+0.416
Neg logit contributions
deen-0.544
…………-0.437
……………………-0.433
sth-0.403
 sod-0.399
Token location
Token ID4067
Feature activation+7.57e-01

Pos logit contributions
deen+0.009
…………+0.007
……………………+0.007
sth+0.007
 sod+0.007
Neg logit contributions
rast-0.009
iar-0.007
oise-0.007
 relegation-0.007
assic-0.007
Token for
Token ID329
Feature activation-4.69e-01

Pos logit contributions
deen+2.024
…………+1.665
……………………+1.652
 sod+1.540
sth+1.528
Neg logit contributions
rast-1.912
iar-1.519
oise-1.494
 relegation-1.450
assic-1.442
Token
Token ID250
Feature activation+8.88e-02

Pos logit contributions
deen+1.455
…………+1.079
……………………+1.070
sth+0.932
 sod+0.916
Neg logit contributions
rast-2.494
iar-2.119
oise-2.068
 relegation-2.067
orth-2.023
TokenSub
Token ID7004
Feature activation-1.07e+00

Pos logit contributions
deen+0.216
…………+0.170
……………………+0.168
sth+0.155
hest+0.153
Neg logit contributions
rast-0.251
iar-0.205
oise-0.200
 relegation-0.200
assic-0.194
Tokenprime
Token ID35505
Feature activation+5.55e-01

Pos logit contributions
rast+2.958
iar+2.383
oise+2.328
 relegation+2.318
orth+2.260
Neg logit contributions
deen-2.689
…………-2.127
……………………-2.103
sth-1.945
hest-1.919
Token market
Token ID1910
Feature activation-4.39e-01

Pos logit contributions
deen+1.545
…………+1.262
……………………+1.243
 sod+1.154
sth+1.149
Neg logit contributions
rast-1.376
iar-1.085
oise-1.056
 relegation-1.043
assic-1.030
Token getting
Token ID1972
Feature activation+4.34e-01

Pos logit contributions
rast+1.063
iar+0.829
oise+0.808
 relegation+0.797
assic+0.776
Neg logit contributions
deen-1.254
…………-1.028
……………………-1.017
sth-0.951
hest-0.943
Token hit
Token ID2277
Feature activation+1.59e+00

Pos logit contributions
deen+1.209
…………+1.009
……………………+1.000
hest+0.932
sth+0.931
Neg logit contributions
rast-1.060
iar-0.826
oise-0.811
 relegation-0.786
assic-0.774
Token hard
Token ID1327
Feature activation+7.87e-01

Pos logit contributions
deen+4.133
…………+3.359
……………………+3.294
hest+3.055
 sod+3.037
Neg logit contributions
rast-4.189
iar-3.357
oise-3.218
 relegation-3.205
assic-3.191
Token.
Token ID13
Feature activation+3.22e-01

Pos logit contributions
deen+1.982
…………+1.596
……………………+1.571
sth+1.438
hest+1.431
Neg logit contributions
rast-2.136
iar-1.736
 relegation-1.692
oise-1.691
assic-1.653
Token
Token ID447
Feature activation-3.15e-01

Pos logit contributions
deen+0.826
…………+0.668
……………………+0.662
sth+0.610
hest+0.601
Neg logit contributions
rast-0.862
iar-0.695
oise-0.679
 relegation-0.676
assic-0.667
Token
Token ID251
Feature activation-9.57e-02

Pos logit contributions
rast+0.958
iar+0.791
oise+0.775
 relegation+0.772
orth+0.754
Neg logit contributions
deen-0.702
…………-0.537
……………………-0.530
sth-0.483
hest-0.476
Token The
Token ID383
Feature activation+9.67e-02

Pos logit contributions
rast+0.254
iar+0.203
oise+0.199
 relegation+0.198
assic+0.193
Neg logit contributions
deen-0.250
…………-0.201
……………………-0.199
sth-0.185
hest-0.182
Token it
Token ID340
Feature activation+7.89e-02

Pos logit contributions
deen+0.439
…………+0.348
……………………+0.344
sth+0.316
 sod+0.313
Neg logit contributions
rast-0.503
iar-0.407
oise-0.397
 relegation-0.395
assic-0.387
Token out
Token ID503
Feature activation-3.96e-01

Pos logit contributions
deen+0.206
…………+0.166
……………………+0.164
sth+0.151
 sod+0.151
Neg logit contributions
rast-0.211
iar-0.167
oise-0.164
 relegation-0.163
assic-0.159
Token,
Token ID11
Feature activation+6.20e-02

Pos logit contributions
rast+1.005
iar+0.793
oise+0.774
 relegation+0.770
orth+0.747
Neg logit contributions
deen-1.086
…………-0.879
……………………-0.869
sth-0.810
hest-0.802
Token causing
Token ID6666
Feature activation+8.13e-01

Pos logit contributions
deen+0.135
…………+0.104
……………………+0.102
sth+0.092
 sod+0.091
Neg logit contributions
rast-0.192
iar-0.159
oise-0.156
 relegation-0.155
assic-0.151
Token major
Token ID1688
Feature activation+1.24e+00

Pos logit contributions
deen+2.123
…………+1.755
……………………+1.733
 sod+1.590
sth+1.590
Neg logit contributions
rast-2.108
iar-1.697
oise-1.639
assic-1.602
 relegation-1.602
Token scar
Token ID10153
Feature activation+1.71e+00

Pos logit contributions
deen+3.223
…………+2.695
……………………+2.662
 sod+2.472
sth+2.437
Neg logit contributions
rast-3.148
iar-2.518
oise-2.461
 relegation-2.381
assic-2.377
Tokenring
Token ID1806
Feature activation+1.26e+00

Pos logit contributions
deen+4.537
…………+3.784
……………………+3.718
sth+3.430
hest+3.405
Neg logit contributions
rast-4.180
iar-3.372
oise-3.287
 relegation-3.258
orth-3.211
Token and
Token ID290
Feature activation+4.79e-01

Pos logit contributions
deen+3.053
…………+2.471
……………………+2.422
sth+2.198
 sod+2.178
Neg logit contributions
rast-3.496
iar-2.852
oise-2.775
 relegation-2.769
assic-2.724
Token deform
Token ID47577
Feature activation+4.43e-01

Pos logit contributions
deen+1.278
…………+1.051
……………………+1.036
sth+0.955
 sod+0.954
Neg logit contributions
rast-1.232
iar-0.981
oise-0.954
 relegation-0.930
assic-0.921
Tokenity
Token ID414
Feature activation+1.18e+00

Pos logit contributions
deen+1.274
…………+1.048
……………………+1.041
sth+0.977
 sod+0.971
Neg logit contributions
rast-1.025
iar-0.790
 relegation-0.785
oise-0.772
assic-0.762
Token,
Token ID11
Feature activation+1.92e-01

Pos logit contributions
deen+2.867
…………+2.322
……………………+2.282
sth+2.052
 sod+2.043
Neg logit contributions
rast-3.289
iar-2.675
oise-2.620
 relegation-2.599
assic-2.579
Token the
Token ID262
Feature activation+8.67e-02

Pos logit contributions
rast+1.882
iar+1.531
oise+1.496
 relegation+1.488
orth+1.452
Neg logit contributions
deen-1.573
…………-1.235
……………………-1.220
sth-1.122
hest-1.110
Token latest
Token ID3452
Feature activation-4.39e-01

Pos logit contributions
deen+0.242
…………+0.200
……………………+0.198
sth+0.186
 sod+0.185
Neg logit contributions
rast-0.212
iar-0.166
oise-0.160
 relegation-0.159
orth-0.156
Token Jesuit
Token ID50190
Feature activation+1.15e+00

Pos logit contributions
rast+1.065
iar+0.829
oise+0.806
 relegation+0.795
assic+0.776
Neg logit contributions
deen-1.248
…………-1.028
……………………-1.018
 sod-0.953
sth-0.952
Token institution
Token ID9901
Feature activation+1.32e+00

Pos logit contributions
deen+3.237
…………+2.705
……………………+2.696
 sod+2.539
sth+2.522
Neg logit contributions
rast-2.711
oise-2.027
iar-2.024
 relegation-1.981
assic-1.952
Token to
Token ID284
Feature activation+1.20e-01

Pos logit contributions
deen+3.295
…………+2.673
……………………+2.629
 sod+2.495
sth+2.472
Neg logit contributions
rast-3.538
iar-2.825
oise-2.791
 relegation-2.704
assic-2.672
Token offer
Token ID2897
Feature activation+1.07e+00

Pos logit contributions
deen+0.322
…………+0.260
……………………+0.257
 sod+0.240
sth+0.239
Neg logit contributions
rast-0.312
iar-0.247
oise-0.240
 relegation-0.238
assic-0.234
Token the
Token ID262
Feature activation-2.06e-02

Pos logit contributions
deen+2.770
…………+2.304
……………………+2.283
 sod+2.155
sth+2.106
Neg logit contributions
rast-2.819
iar-2.234
oise-2.187
 relegation-2.126
assic-2.115
Token benefits
Token ID4034
Feature activation+6.05e-01

Pos logit contributions
rast+0.053
iar+0.042
oise+0.041
 relegation+0.040
orth+0.039
Neg logit contributions
deen-0.056
…………-0.045
……………………-0.045
sth-0.042
 sod-0.041
Token to
Token ID284
Feature activation+2.07e-01

Pos logit contributions
deen+1.605
…………+1.316
……………………+1.300
sth+1.206
 sod+1.205
Neg logit contributions
rast-1.565
iar-1.246
oise-1.212
 relegation-1.199
assic-1.175
Token the
Token ID262
Feature activation+1.61e-01

Pos logit contributions
deen+0.529
…………+0.426
……………………+0.421
 sod+0.391
sth+0.389
Neg logit contributions
rast-0.562
iar-0.449
oise-0.439
 relegation-0.436
assic-0.427
Token same
Token ID976
Feature activation-8.45e-01

Pos logit contributions
deen+0.419
…………+0.340
……………………+0.337
 sod+0.314
sth+0.311
Neg logit contributions
rast-0.431
iar-0.343
oise-0.334
 relegation-0.329
assic-0.326
Token tough
Token ID5802
Feature activation-2.08e-01

Pos logit contributions
deen+0.389
…………+0.322
……………………+0.320
sth+0.296
hest+0.295
Neg logit contributions
rast-0.316
iar-0.245
oise-0.240
 relegation-0.235
assic-0.228
Token question
Token ID1808
Feature activation-5.43e-01

Pos logit contributions
rast+0.413
iar+0.302
oise+0.294
 relegation+0.284
assic+0.276
Neg logit contributions
deen-0.680
…………-0.577
……………………-0.571
sth-0.540
 sod-0.537
Token,
Token ID11
Feature activation-6.14e-02

Pos logit contributions
rast+1.409
iar+1.119
oise+1.090
 relegation+1.085
orth+1.056
Neg logit contributions
deen-1.455
…………-1.167
……………………-1.156
sth-1.078
hest-1.065
Token and
Token ID290
Feature activation-8.44e-02

Pos logit contributions
rast+0.176
iar+0.143
oise+0.141
 relegation+0.139
assic+0.138
Neg logit contributions
deen-0.148
…………-0.117
……………………-0.115
sth-0.105
 sod-0.104
Token probably
Token ID2192
Feature activation+2.23e-02

Pos logit contributions
rast+0.224
iar+0.178
oise+0.175
 relegation+0.172
assic+0.170
Neg logit contributions
deen-0.222
…………-0.179
……………………-0.177
sth-0.163
hest-0.161
Token not
Token ID407
Feature activation+3.91e-01

Pos logit contributions
deen+0.062
…………+0.051
……………………+0.050
sth+0.047
hest+0.046
Neg logit contributions
rast-0.056
iar-0.043
oise-0.042
 relegation-0.042
assic-0.041
Token a
Token ID257
Feature activation-1.22e-01

Pos logit contributions
deen+1.027
…………+0.834
……………………+0.823
hest+0.760
sth+0.750
Neg logit contributions
rast-1.038
iar-0.817
oise-0.809
 relegation-0.792
assic-0.779
Token fair
Token ID3148
Feature activation-1.08e+00

Pos logit contributions
rast+0.300
iar+0.235
oise+0.230
 relegation+0.225
assic+0.220
Neg logit contributions
deen-0.345
…………-0.281
……………………-0.279
hest-0.259
sth-0.259
Token one
Token ID530
Feature activation-5.34e-01

Pos logit contributions
rast+2.827
iar+2.255
oise+2.200
 relegation+2.195
orth+2.134
Neg logit contributions
deen-2.849
…………-2.277
……………………-2.254
sth-2.100
hest-2.072
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
rast+1.432
iar+1.147
oise+1.122
 relegation+1.115
orth+1.084
Neg logit contributions
deen-1.388
…………-1.109
……………………-1.096
sth-1.016
hest-1.004
Token
Token ID198
Feature activation+6.97e-02

Pos logit contributions
deen+0.367
…………+0.298
……………………+0.295
sth+0.272
hest+0.267
Neg logit contributions
rast-0.378
iar-0.303
oise-0.298
 relegation-0.297
assic-0.294
Token huge
Token ID3236
Feature activation+3.92e-02

Pos logit contributions
deen+0.556
…………+0.452
……………………+0.448
 sod+0.420
sth+0.416
Neg logit contributions
rast-0.515
iar-0.409
oise-0.397
 relegation-0.388
orth-0.383
Token conglomerate
Token ID50240
Feature activation+6.54e-02

Pos logit contributions
deen+0.099
…………+0.079
……………………+0.078
sth+0.072
 sod+0.072
Neg logit contributions
rast-0.107
iar-0.086
oise-0.084
 relegation-0.084
assic-0.082
Token corporations
Token ID10225
Feature activation-2.15e-02

Pos logit contributions
deen+0.167
…………+0.134
……………………+0.132
sth+0.123
 sod+0.123
Neg logit contributions
rast-0.177
iar-0.142
oise-0.139
 relegation-0.137
assic-0.134
Token have
Token ID423
Feature activation-1.99e-02

Pos logit contributions
rast+0.054
iar+0.043
oise+0.042
 relegation+0.041
orth+0.040
Neg logit contributions
deen-0.059
…………-0.048
……………………-0.047
sth-0.044
 sod-0.044
Token dominated
Token ID13354
Feature activation+1.14e-01

Pos logit contributions
rast+0.049
iar+0.039
oise+0.038
 relegation+0.037
orth+0.036
Neg logit contributions
deen-0.055
…………-0.045
……………………-0.045
 sod-0.042
sth-0.042
Token political
Token ID1964
Feature activation+8.52e-01

Pos logit contributions
deen+0.290
…………+0.231
……………………+0.228
sth+0.212
 sod+0.211
Neg logit contributions
rast-0.308
iar-0.249
oise-0.242
 relegation-0.240
orth-0.235
Token institutions
Token ID6712
Feature activation+4.07e-01

Pos logit contributions
deen+2.364
…………+1.917
……………………+1.884
 sod+1.824
sth+1.804
Neg logit contributions
rast-2.089
iar-1.679
oise-1.611
ruciating-1.554
assic-1.549
Token and
Token ID290
Feature activation+1.96e-01

Pos logit contributions
deen+1.058
…………+0.855
……………………+0.843
 sod+0.778
sth+0.775
Neg logit contributions
rast-1.087
iar-0.876
oise-0.854
 relegation-0.834
assic-0.826
Token the
Token ID262
Feature activation+2.53e-01

Pos logit contributions
deen+0.539
…………+0.437
……………………+0.432
 sod+0.405
sth+0.405
Neg logit contributions
rast-0.493
iar-0.390
oise-0.379
 relegation-0.373
orth-0.366
Token mass
Token ID2347
Feature activation+6.34e-01

Pos logit contributions
deen+0.712
…………+0.581
……………………+0.575
 sod+0.541
sth+0.538
Neg logit contributions
rast-0.614
iar-0.486
oise-0.468
 relegation-0.460
orth-0.455
Token media
Token ID2056
Feature activation-2.05e-01

Pos logit contributions
deen+1.746
…………+1.436
……………………+1.421
 sod+1.348
hest+1.343
Neg logit contributions
rast-1.532
iar-1.214
oise-1.178
orth-1.169
assic-1.162
Token the
Token ID262
Feature activation+1.26e-01

Pos logit contributions
rast+0.175
iar+0.139
oise+0.136
 relegation+0.134
assic+0.132
Neg logit contributions
deen-0.175
…………-0.141
……………………-0.139
sth-0.129
 sod-0.128
Token rest
Token ID1334
Feature activation+1.06e-01

Pos logit contributions
deen+0.342
…………+0.277
……………………+0.274
 sod+0.255
sth+0.254
Neg logit contributions
rast-0.322
iar-0.255
oise-0.249
 relegation-0.243
assic-0.242
Token at
Token ID379
Feature activation+3.17e-01

Pos logit contributions
deen+0.284
…………+0.230
……………………+0.227
sth+0.209
hest+0.208
Neg logit contributions
rast-0.279
iar-0.219
oise-0.216
 relegation-0.212
assic-0.208
Token 1
Token ID352
Feature activation+3.90e-01

Pos logit contributions
deen+0.823
…………+0.662
……………………+0.650
 sod+0.604
sth+0.603
Neg logit contributions
rast-0.847
iar-0.675
oise-0.660
 relegation-0.647
assic-0.644
Token percent
Token ID1411
Feature activation+3.04e-02

Pos logit contributions
deen+1.123
…………+0.923
……………………+0.912
sth+0.858
 sod+0.844
Neg logit contributions
rast-0.930
iar-0.721
oise-0.703
 relegation-0.699
assic-0.683
Token interest
Token ID1393
Feature activation+2.36e-01

Pos logit contributions
deen+0.079
…………+0.064
……………………+0.063
sth+0.058
hest+0.058
Neg logit contributions
rast-0.081
iar-0.064
oise-0.063
 relegation-0.062
assic-0.061
Token over
Token ID625
Feature activation+1.33e-01

Pos logit contributions
deen+0.604
…………+0.483
……………………+0.476
sth+0.437
 sod+0.432
Neg logit contributions
rast-0.645
iar-0.516
oise-0.508
 relegation-0.501
assic-0.491
Token the
Token ID262
Feature activation+8.70e-02

Pos logit contributions
deen+0.339
…………+0.269
……………………+0.265
sth+0.246
 sod+0.242
Neg logit contributions
rast-0.364
iar-0.292
oise-0.286
 relegation-0.282
assic-0.277
Token next
Token ID1306
Feature activation-1.48e-01

Pos logit contributions
deen+0.241
…………+0.196
……………………+0.193
sth+0.180
 sod+0.180
Neg logit contributions
rast-0.219
iar-0.173
oise-0.168
 relegation-0.164
orth-0.162
Token 25
Token ID1679
Feature activation-1.28e-01

Pos logit contributions
rast+0.399
iar+0.320
oise+0.312
 relegation+0.307
assic+0.301
Neg logit contributions
deen-0.384
…………-0.308
……………………-0.304
sth-0.280
 sod-0.280
Token years
Token ID812
Feature activation+1.81e-01

Pos logit contributions
rast+0.302
iar+0.233
oise+0.226
 relegation+0.226
assic+0.218
Neg logit contributions
deen-0.374
…………-0.308
……………………-0.305
sth-0.286
 sod-0.283
Token it
Token ID340
Feature activation+2.85e-01

Pos logit contributions
rast+1.955
iar+1.532
 relegation+1.489
oise+1.484
orth+1.427
Neg logit contributions
deen-2.231
…………-1.802
……………………-1.777
sth-1.678
hest-1.646
Token was
Token ID373
Feature activation+3.07e-02

Pos logit contributions
deen+0.836
…………+0.692
……………………+0.686
hest+0.644
sth+0.642
Neg logit contributions
rast-0.659
iar-0.504
oise-0.489
 relegation-0.487
assic-0.476
Token seen
Token ID1775
Feature activation+3.68e-01

Pos logit contributions
deen+0.082
…………+0.067
……………………+0.067
sth+0.062
hest+0.062
Neg logit contributions
rast-0.079
iar-0.062
oise-0.061
 relegation-0.060
orth-0.059
Token as
Token ID355
Feature activation+2.35e-01

Pos logit contributions
deen+1.035
…………+0.844
……………………+0.839
sth+0.779
 sod+0.772
Neg logit contributions
rast-0.905
iar-0.711
oise-0.689
 relegation-0.680
orth-0.667
Token contributing
Token ID14329
Feature activation+2.38e-01

Pos logit contributions
deen+0.605
…………+0.491
……………………+0.491
hest+0.451
sth+0.450
Neg logit contributions
rast-0.623
iar-0.500
oise-0.489
 relegation-0.476
orth-0.470
Token to
Token ID284
Feature activation+1.66e-01

Pos logit contributions
deen+0.663
…………+0.540
……………………+0.537
sth+0.503
hest+0.497
Neg logit contributions
rast-0.586
iar-0.461
oise-0.451
 relegation-0.444
assic-0.434
Token the
Token ID262
Feature activation+1.28e-01

Pos logit contributions
deen+0.413
…………+0.328
……………………+0.325
sth+0.299
hest+0.297
Neg logit contributions
rast-0.457
iar-0.370
oise-0.362
 relegation-0.357
orth-0.352
Token success
Token ID1943
Feature activation+6.40e-01

Pos logit contributions
deen+0.348
…………+0.283
……………………+0.281
 sod+0.261
sth+0.260
Neg logit contributions
rast-0.321
iar-0.256
oise-0.247
orth-0.241
 relegation-0.241
Token or
Token ID393
Feature activation-3.03e-01

Pos logit contributions
deen+1.799
…………+1.462
……………………+1.446
sth+1.354
hest+1.337
Neg logit contributions
rast-1.580
iar-1.238
oise-1.205
 relegation-1.199
orth-1.162
Token defeat
Token ID7433
Feature activation-2.58e-01

Pos logit contributions
rast+0.583
iar+0.414
oise+0.408
 relegation+0.386
assic+0.386
Neg logit contributions
deen-1.011
…………-0.852
……………………-0.847
sth-0.802
 sod-0.798
Token of
Token ID286
Feature activation+2.00e-01

Pos logit contributions
rast+0.618
iar+0.480
oise+0.467
 relegation+0.466
orth+0.449
Neg logit contributions
deen-0.744
…………-0.608
……………………-0.601
sth-0.564
 sod-0.558
Token a
Token ID257
Feature activation+2.19e-01

Pos logit contributions
rast+0.405
iar+0.317
oise+0.309
 relegation+0.304
orth+0.296
Neg logit contributions
deen-0.472
…………-0.387
……………………-0.383
sth-0.358
hest-0.354
Token reasonable
Token ID6397
Feature activation-2.07e-02

Pos logit contributions
deen+0.595
…………+0.485
……………………+0.480
sth+0.444
 sod+0.442
Neg logit contributions
rast-0.556
iar-0.443
oise-0.429
 relegation-0.419
assic-0.415
Token waiting
Token ID4953
Feature activation-7.08e-01

Pos logit contributions
rast+0.045
iar+0.035
oise+0.033
 relegation+0.032
assic+0.032
Neg logit contributions
deen-0.064
…………-0.053
……………………-0.053
sth-0.050
 sod-0.049
Token period
Token ID2278
Feature activation+3.23e-01

Pos logit contributions
rast+1.737
iar+1.366
oise+1.321
 relegation+1.316
assic+1.275
Neg logit contributions
deen-1.997
…………-1.637
……………………-1.622
sth-1.514
hest-1.488
Token before
Token ID878
Feature activation-6.16e-01

Pos logit contributions
deen+0.831
…………+0.677
……………………+0.666
sth+0.615
 sod+0.602
Neg logit contributions
rast-0.864
iar-0.694
oise-0.677
 relegation-0.677
assic-0.660
Token the
Token ID262
Feature activation-1.95e-01

Pos logit contributions
rast+1.656
iar+1.327
oise+1.295
 relegation+1.291
orth+1.255
Neg logit contributions
deen-1.594
…………-1.269
……………………-1.255
sth-1.165
hest-1.151
Token app
Token ID598
Feature activation+4.86e-01

Pos logit contributions
rast+0.523
iar+0.419
oise+0.410
 relegation+0.405
orth+0.396
Neg logit contributions
deen-0.506
…………-0.406
……………………-0.402
sth-0.372
 sod-0.368
Token lets
Token ID8781
Feature activation+3.43e-01

Pos logit contributions
deen+1.385
…………+1.144
……………………+1.130
sth+1.065
hest+1.048
Neg logit contributions
rast-1.163
iar-0.892
oise-0.879
 relegation-0.871
assic-0.843
Token you
Token ID345
Feature activation+7.16e-01

Pos logit contributions
deen+0.843
…………+0.669
……………………+0.658
sth+0.613
hest+0.604
Neg logit contributions
rast-0.957
iar-0.777
oise-0.760
 relegation-0.752
assic-0.738
Token check
Token ID2198
Feature activation+2.39e-01

Pos logit contributions
deen+1.796
…………+1.445
……………………+1.424
sth+1.311
 sod+1.305
Neg logit contributions
rast-1.969
iar-1.573
oise-1.557
 relegation-1.530
assic-1.509
Token into
Token ID656
Feature activation-1.57e-01

Pos logit contributions
deen+0.623
…………+0.501
……………………+0.494
sth+0.460
hest+0.454
Neg logit contributions
rast-0.633
iar-0.505
oise-0.494
 relegation-0.490
orth-0.478
Token Opt
Token ID13123
Feature activation-9.13e-01

Pos logit contributions
deen+2.275
…………+1.969
……………………+1.947
 sod+1.817
sth+1.809
Neg logit contributions
rast-1.384
iar-1.039
 relegation-0.998
assic-0.992
oise-0.988
Tokenronics
Token ID20844
Feature activation+7.35e-01

Pos logit contributions
rast+2.357
iar+1.868
oise+1.821
 relegation+1.805
orth+1.761
Neg logit contributions
deen-2.463
…………-1.981
……………………-1.962
sth-1.828
hest-1.804
Token TN
Token ID29025
Feature activation+6.32e-01

Pos logit contributions
deen+2.139
…………+1.825
……………………+1.807
sth+1.673
hest+1.651
Neg logit contributions
rast-1.657
iar-1.288
oise-1.260
assic-1.253
 relegation-1.240
Token Film
Token ID13741
Feature activation-1.92e-01

Pos logit contributions
deen+1.849
…………+1.543
……………………+1.512
 sod+1.403
sth+1.401
Neg logit contributions
rast-1.455
 relegation-1.108
oise-1.105
iar-1.104
ouver-1.053
Token @
Token ID2488
Feature activation-1.04e-02

Pos logit contributions
rast+0.533
iar+0.432
 relegation+0.425
oise+0.424
assic+0.411
Neg logit contributions
deen-0.479
…………-0.381
……………………-0.375
sth-0.350
hest-0.342
Token 144
Token ID20224
Feature activation-7.98e-01

Pos logit contributions
rast+0.027
iar+0.021
 relegation+0.021
oise+0.021
assic+0.020
Neg logit contributions
deen-0.028
…………-0.023
……………………-0.022
sth-0.021
hest-0.021
TokenHz
Token ID7399
Feature activation-4.55e-01

Pos logit contributions
rast+1.797
iar+1.382
oise+1.339
 relegation+1.334
orth+1.285
Neg logit contributions
deen-2.407
…………-1.993
……………………-1.975
sth-1.860
hest-1.838
Token (
Token ID357
Feature activation-5.65e-01

Pos logit contributions
rast+1.301
iar+1.052
oise+1.029
 relegation+1.019
orth+0.999
Neg logit contributions
deen-1.109
…………-0.861
……………………-0.854
sth-0.786
hest-0.779
TokenOD
Token ID3727
Feature activation-1.10e+00

Pos logit contributions
rast+1.584
iar+1.282
 relegation+1.257
oise+1.257
assic+1.217
Neg logit contributions
deen-1.396
…………-1.099
……………………-1.086
sth-1.009
hest-0.991
Token =
Token ID796
Feature activation-2.07e-01

Pos logit contributions
rast+3.518
iar+2.903
oise+2.853
 relegation+2.814
orth+2.767
Neg logit contributions
deen-2.321
…………-1.729
……………………-1.698
sth-1.533
hest-1.522
Token Normal
Token ID14435
Feature activation+2.13e-01

Pos logit contributions
rast+0.537
iar+0.428
oise+0.418
 relegation+0.417
assic+0.407
Neg logit contributions
deen-0.553
…………-0.446
……………………-0.441
sth-0.412
hest-0.405
Token attitude
Token ID9408
Feature activation-3.37e-01

Pos logit contributions
deen+2.659
…………+2.189
……………………+2.187
 sod+2.060
hold+2.018
Neg logit contributions
rast-2.208
iar-1.755
oise-1.685
ouver-1.665
assic-1.644
Token meant
Token ID4001
Feature activation-9.00e-02

Pos logit contributions
rast+0.831
iar+0.654
oise+0.635
 relegation+0.626
assic+0.614
Neg logit contributions
deen-0.948
…………-0.775
……………………-0.765
sth-0.713
 sod-0.712
Token he
Token ID339
Feature activation-1.22e-01

Pos logit contributions
rast+0.234
iar+0.188
oise+0.185
assic+0.179
orth+0.178
Neg logit contributions
deen-0.238
…………-0.193
……………………-0.191
sth-0.177
 sod-0.176
Token would
Token ID561
Feature activation+5.99e-02

Pos logit contributions
rast+0.288
iar+0.221
oise+0.216
 relegation+0.212
assic+0.208
Neg logit contributions
deen-0.359
…………-0.296
……………………-0.292
 sod-0.275
hest-0.273
Token not
Token ID407
Feature activation+3.34e-01

Pos logit contributions
deen+0.170
…………+0.138
……………………+0.136
 sod+0.127
sth+0.127
Neg logit contributions
rast-0.147
iar-0.114
oise-0.112
 relegation-0.110
assic-0.109
Token continue
Token ID2555
Feature activation-3.54e-01

Pos logit contributions
deen+0.898
…………+0.724
……………………+0.712
 sod+0.664
hest+0.659
Neg logit contributions
rast-0.863
iar-0.675
oise-0.672
 relegation-0.659
assic-0.654
Token his
Token ID465
Feature activation-4.07e-01

Pos logit contributions
rast+0.918
iar+0.726
oise+0.716
 relegation+0.704
assic+0.693
Neg logit contributions
deen-0.948
…………-0.765
……………………-0.758
sth-0.702
 sod-0.697
Token flying
Token ID7348
Feature activation+1.45e-01

Pos logit contributions
rast+0.971
iar+0.753
oise+0.734
 relegation+0.723
assic+0.707
Neg logit contributions
deen-1.176
…………-0.965
……………………-0.956
sth-0.894
 sod-0.889
Token career
Token ID3451
Feature activation+1.88e+00

Pos logit contributions
deen+0.447
…………+0.374
……………………+0.369
 sod+0.347
sth+0.342
Neg logit contributions
rast-0.319
iar-0.242
oise-0.237
 relegation-0.228
assic-0.227
Token beyond
Token ID3675
Feature activation+1.01e+00

Pos logit contributions
deen+4.403
…………+3.525
……………………+3.444
 sod+3.161
hest+3.075
Neg logit contributions
rast-5.282
iar-4.354
oise-4.343
assic-4.245
 relegation-4.121
Token his
Token ID465
Feature activation+1.28e-01

Pos logit contributions
deen+2.502
…………+2.043
……………………+2.012
 sod+1.867
hest+1.830
Neg logit contributions
rast-2.732
iar-2.203
oise-2.161
assic-2.127
orth-2.093
Token are
Token ID389
Feature activation-3.32e-01

Pos logit contributions
deen+0.882
…………+0.716
……………………+0.706
sth+0.664
hest+0.658
Neg logit contributions
rast-0.789
iar-0.621
 relegation-0.605
oise-0.599
ouver-0.582
Token still
Token ID991
Feature activation-5.70e-01

Pos logit contributions
rast+0.860
iar+0.688
oise+0.667
 relegation+0.655
orth+0.643
Neg logit contributions
deen-0.889
…………-0.726
……………………-0.715
 sod-0.663
sth-0.660
Token an
Token ID281
Feature activation-1.50e-02

Pos logit contributions
rast+1.415
iar+1.116
oise+1.083
 relegation+1.064
orth+1.042
Neg logit contributions
deen-1.587
…………-1.302
……………………-1.285
 sod-1.197
sth-1.196
Token estimated
Token ID6108
Feature activation-6.15e-02

Pos logit contributions
rast+0.038
iar+0.030
 relegation+0.029
oise+0.029
ouver+0.028
Neg logit contributions
deen-0.041
…………-0.034
……………………-0.033
sth-0.031
hest-0.031
Token 250
Token ID8646
Feature activation+2.92e-01

Pos logit contributions
rast+0.168
iar+0.135
oise+0.131
 relegation+0.129
orth+0.127
Neg logit contributions
deen-0.156
…………-0.126
……………………-0.124
 sod-0.115
sth-0.114
Token such
Token ID884
Feature activation-5.75e-02

Pos logit contributions
deen+0.783
…………+0.649
……………………+0.641
 sod+0.598
sth+0.596
Neg logit contributions
rast-0.736
iar-0.585
oise-0.569
 relegation-0.565
ouver-0.549
Token giant
Token ID6175
Feature activation+5.53e-01

Pos logit contributions
rast+0.122
iar+0.092
oise+0.089
 relegation+0.088
orth+0.085
Neg logit contributions
deen-0.179
…………-0.151
……………………-0.149
sth-0.142
 sod-0.141
Token freshwater
Token ID40941
Feature activation-4.20e-01

Pos logit contributions
deen+1.895
…………+1.640
……………………+1.620
 sod+1.569
sth+1.548
Neg logit contributions
rast-0.966
iar-0.686
oise-0.663
 relegation-0.642
orth-0.615
Token crocod
Token ID37565
Feature activation-5.03e-01

Pos logit contributions
rast+0.633
iar+0.412
oise+0.391
 relegation+0.382
orth+0.357
Neg logit contributions
deen-1.580
…………-1.364
……………………-1.353
sth-1.295
 sod-1.292
Tokeniles
Token ID2915
Feature activation+3.66e-01

Pos logit contributions
rast+1.140
iar+0.874
 relegation+0.866
oise+0.852
assic+0.821
Neg logit contributions
deen-1.498
…………-1.233
……………………-1.222
sth-1.151
hest-1.150
Token still
Token ID991
Feature activation-1.64e-01

Pos logit contributions
deen+0.949
…………+0.772
……………………+0.758
 sod+0.702
sth+0.698
Neg logit contributions
rast-0.981
iar-0.781
oise-0.765
 relegation-0.755
assic-0.741
Token visit
Token ID3187
Feature activation+5.06e-01

Pos logit contributions
rast+0.792
iar+0.624
oise+0.605
 relegation+0.598
orth+0.586
Neg logit contributions
deen-0.875
…………-0.709
……………………-0.702
sth-0.654
 sod-0.647
Token of
Token ID286
Feature activation+8.94e-02

Pos logit contributions
deen+1.414
…………+1.148
……………………+1.137
sth+1.062
hest+1.049
Neg logit contributions
rast-1.255
iar-0.985
oise-0.959
 relegation-0.953
orth-0.925
Token B
Token ID347
Feature activation+6.08e-01

Pos logit contributions
deen+0.250
…………+0.202
……………………+0.199
 sod+0.185
sth+0.185
Neg logit contributions
rast-0.223
iar-0.174
oise-0.171
assic-0.167
ouver-0.166
Tokenourn
Token ID1798
Feature activation-4.03e-01

Pos logit contributions
deen+1.659
……………………+1.303
…………+1.294
sth+1.232
hest+1.213
Neg logit contributions
rast-1.512
iar-1.186
oise-1.167
assic-1.159
 relegation-1.149
Tokenemouth
Token ID46880
Feature activation-9.06e-01

Pos logit contributions
rast+1.051
iar+0.824
oise+0.805
 relegation+0.804
assic+0.788
Neg logit contributions
deen-1.084
…………-0.865
……………………-0.858
sth-0.796
 sod-0.787
Token to
Token ID284
Feature activation-1.95e-01

Pos logit contributions
rast+2.366
iar+1.883
oise+1.836
 relegation+1.825
orth+1.777
Neg logit contributions
deen-2.416
…………-1.939
……………………-1.917
sth-1.784
hest-1.761
Token The
Token ID383
Feature activation-2.91e-01

Pos logit contributions
rast+0.512
iar+0.409
oise+0.399
 relegation+0.394
assic+0.386
Neg logit contributions
deen-0.516
…………-0.413
……………………-0.408
sth-0.379
 sod-0.375
Token Hawth
Token ID41457
Feature activation-9.39e-01

Pos logit contributions
rast+0.857
iar+0.702
oise+0.686
 relegation+0.679
assic+0.673
Neg logit contributions
deen-0.686
…………-0.527
……………………-0.521
sth-0.482
hest-0.471
Tokenorns
Token ID19942
Feature activation-3.48e-01

Pos logit contributions
rast+1.690
iar+1.214
 relegation+1.158
oise+1.154
assic+1.112
Neg logit contributions
deen-3.247
…………-2.730
……………………-2.711
sth-2.592
hest-2.587
Token.
Token ID13
Feature activation-2.65e-01

Pos logit contributions
rast+0.930
iar+0.745
oise+0.728
 relegation+0.720
assic+0.704
Neg logit contributions
deen-0.907
…………-0.723
……………………-0.715
sth-0.664
hest-0.654
Token
Token ID198
Feature activation-3.89e-01

Pos logit contributions
rast+0.671
iar+0.531
 relegation+0.516
oise+0.516
orth+0.499
Neg logit contributions
deen-0.729
…………-0.588
……………………-0.581
sth-0.546
hest-0.538
Token that
Token ID326
Feature activation+1.01e-01

Pos logit contributions
rast+2.565
iar+2.027
oise+1.977
 relegation+1.966
orth+1.910
Neg logit contributions
deen-2.751
…………-2.221
……………………-2.198
sth-2.051
hest-2.027
Token might
Token ID1244
Feature activation-3.26e-01

Pos logit contributions
deen+0.286
…………+0.234
……………………+0.231
sth+0.217
 sod+0.217
Neg logit contributions
rast-0.250
iar-0.193
oise-0.189
 relegation-0.187
orth-0.182
Token be
Token ID307
Feature activation-6.77e-02

Pos logit contributions
rast+0.792
iar+0.616
oise+0.600
 relegation+0.596
orth+0.578
Neg logit contributions
deen-0.933
…………-0.761
……………………-0.753
sth-0.706
hest-0.698
Token impacted
Token ID20755
Feature activation-3.42e-02

Pos logit contributions
rast+0.170
iar+0.133
oise+0.130
 relegation+0.129
assic+0.125
Neg logit contributions
deen-0.187
…………-0.153
……………………-0.151
sth-0.142
 sod-0.142
Token?
Token ID30
Feature activation-1.55e+00

Pos logit contributions
rast+0.090
iar+0.071
oise+0.070
 relegation+0.069
assic+0.067
Neg logit contributions
deen-0.091
…………-0.074
……………………-0.073
sth-0.067
hest-0.067
Token Well
Token ID3894
Feature activation-1.63e+00

Pos logit contributions
rast+3.912
iar+3.078
oise+2.996
 relegation+2.970
orth+2.902
Neg logit contributions
deen-4.269
…………-3.410
……………………-3.373
sth-3.170
hest-3.144
Token,
Token ID11
Feature activation-6.89e-01

Pos logit contributions
rast+4.054
iar+3.195
oise+3.086
 relegation+3.079
orth+3.011
Neg logit contributions
deen-4.483
…………-3.544
……………………-3.528
sth-3.314
hest-3.287
Token Shell
Token ID17537
Feature activation+2.79e-01

Pos logit contributions
rast+1.799
iar+1.432
oise+1.398
 relegation+1.389
orth+1.351
Neg logit contributions
deen-1.836
…………-1.476
……………………-1.460
sth-1.359
hest-1.342
Token
Token ID447
Feature activation+4.15e-01

Pos logit contributions
deen+0.803
…………+0.662
……………………+0.654
sth+0.613
 sod+0.606
Neg logit contributions
rast-0.664
iar-0.514
 relegation-0.506
oise-0.501
assic-0.483
Token
Token ID247
Feature activation+2.36e-01

Pos logit contributions
deen+0.832
…………+0.615
……………………+0.613
sth+0.530
hest+0.528
Neg logit contributions
rast-1.363
iar-1.141
 relegation-1.120
oise-1.116
orth-1.103
Tokens
Token ID82
Feature activation+2.68e-01

Pos logit contributions
deen+0.628
…………+0.502
……………………+0.497
sth+0.467
 sod+0.458
Neg logit contributions
rast-0.619
iar-0.489
 relegation-0.482
oise-0.477
ouver-0.464
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
rast+0.053
iar+0.042
oise+0.041
 relegation+0.041
orth+0.039
Neg logit contributions
deen-0.058
…………-0.047
……………………-0.047
sth-0.043
hest-0.043
Tokend
Token ID67
Feature activation-3.92e-01

Pos logit contributions
rast+3.616
iar+3.028
oise+2.962
 relegation+2.930
orth+2.898
Neg logit contributions
deen-2.276
…………-1.701
……………………-1.680
sth-1.518
hest-1.499
Token)
Token ID8
Feature activation-2.53e-01

Pos logit contributions
rast+0.984
iar+0.775
oise+0.755
 relegation+0.750
orth+0.729
Neg logit contributions
deen-1.084
…………-0.877
……………………-0.868
sth-0.812
hest-0.803
Token C
Token ID327
Feature activation+2.37e-01

Pos logit contributions
rast+0.664
iar+0.529
oise+0.516
 relegation+0.516
orth+0.500
Neg logit contributions
deen-0.668
…………-0.536
……………………-0.531
sth-0.493
hest-0.488
Token-
Token ID12
Feature activation-7.01e-01

Pos logit contributions
deen+0.580
…………+0.456
……………………+0.451
sth+0.416
hest+0.410
Neg logit contributions
rast-0.669
iar-0.540
 relegation-0.530
oise-0.530
orth-0.512
Token14
Token ID1415
Feature activation-1.56e+00

Pos logit contributions
rast+1.931
iar+1.555
oise+1.527
assic+1.495
orth+1.491
Neg logit contributions
deen-1.748
…………-1.393
……………………-1.375
sth-1.266
hest-1.251
Token Years
Token ID13212
Feature activation+9.16e-01

Pos logit contributions
rast+4.024
iar+3.199
oise+3.113
 relegation+3.092
assic+3.029
Neg logit contributions
deen-4.168
…………-3.335
……………………-3.296
sth-3.085
hest-3.029
Token B
Token ID347
Feature activation+8.66e-01

Pos logit contributions
deen+2.323
…………+1.868
……………………+1.858
sth+1.698
 sod+1.693
Neg logit contributions
rast-2.485
iar-1.972
 relegation-1.954
oise-1.948
ouver-1.884
Token.
Token ID13
Feature activation-6.27e-01

Pos logit contributions
deen+2.030
…………+1.565
……………………+1.557
sth+1.438
hest+1.412
Neg logit contributions
rast-2.520
 relegation-2.038
iar-2.035
oise-2.015
orth-1.932
TokenP
Token ID47
Feature activation-8.66e-01

Pos logit contributions
rast+1.717
iar+1.382
oise+1.350
 relegation+1.343
orth+1.309
Neg logit contributions
deen-1.591
…………-1.261
……………………-1.247
sth-1.155
hest-1.141
Token.
Token ID13
Feature activation-6.86e-01

Pos logit contributions
rast+2.317
iar+1.864
oise+1.820
 relegation+1.796
orth+1.768
Neg logit contributions
deen-2.240
…………-1.789
……………………-1.771
sth-1.637
hest-1.614
Token freedom
Token ID4925
Feature activation+7.96e-02

Pos logit contributions
rast+0.842
iar+0.656
oise+0.637
 relegation+0.633
orth+0.615
Neg logit contributions
deen-1.011
…………-0.827
……………………-0.820
sth-0.766
hest-0.760
Token to
Token ID284
Feature activation+3.54e-01

Pos logit contributions
deen+0.216
…………+0.175
……………………+0.173
sth+0.161
hest+0.159
Neg logit contributions
rast-0.204
iar-0.161
oise-0.157
 relegation-0.157
orth-0.152
Token live
Token ID2107
Feature activation+4.29e-02

Pos logit contributions
deen+0.929
…………+0.746
……………………+0.736
 sod+0.682
sth+0.673
Neg logit contributions
rast-0.941
iar-0.749
oise-0.733
 relegation-0.726
assic-0.722
Token in
Token ID287
Feature activation-1.90e-01

Pos logit contributions
deen+0.109
…………+0.087
……………………+0.086
sth+0.079
hest+0.078
Neg logit contributions
rast-0.117
iar-0.095
oise-0.092
 relegation-0.092
assic-0.091
Token this
Token ID428
Feature activation+1.54e-01

Pos logit contributions
rast+0.537
iar+0.436
oise+0.426
 relegation+0.422
assic+0.414
Neg logit contributions
deen-0.469
…………-0.369
……………………-0.364
sth-0.335
 sod-0.331
Token country
Token ID1499
Feature activation-1.45e+00

Pos logit contributions
deen+0.396
…………+0.315
……………………+0.311
sth+0.287
 sod+0.287
Neg logit contributions
rast-0.419
iar-0.339
oise-0.330
 relegation-0.324
assic-0.319
Token and
Token ID290
Feature activation-4.40e-01

Pos logit contributions
rast+3.879
iar+3.119
oise+3.042
 relegation+3.027
orth+2.957
Neg logit contributions
deen-3.703
…………-2.926
……………………-2.911
sth-2.740
hest-2.687
Token honour
Token ID15393
Feature activation+1.27e-01

Pos logit contributions
rast+1.122
iar+0.886
oise+0.864
 relegation+0.857
orth+0.836
Neg logit contributions
deen-1.206
…………-0.974
……………………-0.961
sth-0.894
 sod-0.889
Token it
Token ID340
Feature activation+3.82e-02

Pos logit contributions
deen+0.307
…………+0.240
……………………+0.237
sth+0.217
 sod+0.215
Neg logit contributions
rast-0.363
iar-0.296
 relegation-0.288
oise-0.288
assic-0.282
Token,
Token ID11
Feature activation-1.77e-01

Pos logit contributions
deen+0.098
…………+0.079
……………………+0.077
sth+0.070
 sod+0.070
Neg logit contributions
rast-0.105
iar-0.084
oise-0.082
 relegation-0.082
assic-0.081
Token so
Token ID523
Feature activation+1.31e-01

Pos logit contributions
rast+0.453
iar+0.359
oise+0.350
 relegation+0.348
assic+0.339
Neg logit contributions
deen-0.483
…………-0.390
……………………-0.385
sth-0.355
 sod-0.355
Token hole
Token ID7604
Feature activation+4.56e-02

Pos logit contributions
rast+3.110
iar+2.448
oise+2.389
 relegation+2.375
orth+2.305
Neg logit contributions
deen-3.422
…………-2.760
……………………-2.734
sth-2.561
hest-2.530
Token.
Token ID13
Feature activation-2.92e-01

Pos logit contributions
deen+0.116
…………+0.094
……………………+0.092
sth+0.085
 sod+0.084
Neg logit contributions
rast-0.124
iar-0.100
 relegation-0.097
oise-0.097
assic-0.095
Token Start
Token ID7253
Feature activation-4.64e-01

Pos logit contributions
rast+0.760
iar+0.606
 relegation+0.591
oise+0.590
assic+0.577
Neg logit contributions
deen-0.772
…………-0.629
……………………-0.622
sth-0.572
hest-0.567
Token by
Token ID416
Feature activation-4.62e-01

Pos logit contributions
rast+1.219
iar+0.972
oise+0.948
 relegation+0.944
orth+0.917
Neg logit contributions
deen-1.228
…………-0.984
……………………-0.974
sth-0.906
hest-0.895
Token showing
Token ID4478
Feature activation+2.25e-02

Pos logit contributions
rast+1.228
iar+0.982
oise+0.959
 relegation+0.954
orth+0.928
Neg logit contributions
deen-1.207
…………-0.966
……………………-0.955
sth-0.886
hest-0.876
Token him
Token ID683
Feature activation-1.59e+00

Pos logit contributions
deen+0.053
…………+0.041
……………………+0.041
sth+0.037
hest+0.037
Neg logit contributions
rast-0.066
iar-0.054
oise-0.053
 relegation-0.053
assic-0.051
Token how
Token ID703
Feature activation-5.61e-01

Pos logit contributions
rast+4.068
iar+3.216
oise+3.155
 relegation+3.096
orth+3.061
Neg logit contributions
deen-4.272
…………-3.350
……………………-3.326
sth-3.148
hest-3.109
Token to
Token ID284
Feature activation-4.83e-01

Pos logit contributions
rast+1.345
iar+1.049
oise+1.023
 relegation+1.010
orth+0.985
Neg logit contributions
deen-1.614
…………-1.294
……………………-1.286
sth-1.218
hest-1.208
Token bring
Token ID2222
Feature activation+1.34e-01

Pos logit contributions
rast+1.281
iar+1.023
oise+1.000
 relegation+0.994
orth+0.968
Neg logit contributions
deen-1.265
…………-1.005
……………………-0.995
sth-0.929
hest-0.918
Token the
Token ID262
Feature activation-3.73e-01

Pos logit contributions
deen+0.331
…………+0.264
……………………+0.261
sth+0.240
 sod+0.237
Neg logit contributions
rast-0.375
iar-0.303
oise-0.296
 relegation-0.295
assic-0.289
Token kn
Token ID638
Feature activation-2.49e-01

Pos logit contributions
rast+0.955
iar+0.757
oise+0.736
 relegation+0.732
orth+0.713
Neg logit contributions
deen-1.009
…………-0.821
……………………-0.812
sth-0.753
 sod-0.746
Token How
Token ID1374
Feature activation-4.69e-01

Pos logit contributions
rast+3.191
iar+2.505
oise+2.442
 relegation+2.425
orth+2.357
Neg logit contributions
deen-3.540
…………-2.847
……………………-2.820
sth-2.650
hest-2.617
Token about
Token ID546
Feature activation-3.45e-01

Pos logit contributions
rast+0.998
iar+0.749
oise+0.725
 relegation+0.721
orth+0.695
Neg logit contributions
deen-1.472
…………-1.233
……………………-1.220
sth-1.148
 sod-1.136
Token after
Token ID706
Feature activation-8.98e-01

Pos logit contributions
rast+0.870
iar+0.688
oise+0.672
 relegation+0.662
orth+0.647
Neg logit contributions
deen-0.948
…………-0.773
……………………-0.763
sth-0.708
 sod-0.702
Token a
Token ID257
Feature activation-3.44e-01

Pos logit contributions
rast+2.360
iar+1.881
oise+1.836
 relegation+1.824
orth+1.775
Neg logit contributions
deen-2.380
…………-1.909
……………………-1.889
sth-1.757
hest-1.736
Token year
Token ID614
Feature activation+3.00e-01

Pos logit contributions
rast+0.876
iar+0.698
oise+0.678
 relegation+0.669
orth+0.655
Neg logit contributions
deen-0.938
…………-0.760
……………………-0.753
sth-0.698
 sod-0.692
Token?
Token ID30
Feature activation-1.48e+00

Pos logit contributions
deen+0.788
…………+0.639
……………………+0.630
sth+0.586
 sod+0.573
Neg logit contributions
rast-0.786
iar-0.631
 relegation-0.616
oise-0.614
assic-0.595
Token How
Token ID1374
Feature activation-5.16e-01

Pos logit contributions
rast+3.624
iar+2.824
oise+2.752
 relegation+2.730
orth+2.654
Neg logit contributions
deen-4.173
…………-3.351
……………………-3.321
sth-3.142
hest-3.098
Token about
Token ID546
Feature activation-2.96e-01

Pos logit contributions
rast+1.061
iar+0.785
oise+0.759
 relegation+0.754
orth+0.725
Neg logit contributions
deen-1.661
…………-1.390
……………………-1.378
sth-1.302
hest-1.290
Token when
Token ID618
Feature activation+1.24e-01

Pos logit contributions
rast+0.747
iar+0.591
oise+0.577
 relegation+0.567
orth+0.556
Neg logit contributions
deen-0.813
…………-0.664
……………………-0.654
sth-0.607
 sod-0.602
Token something
Token ID1223
Feature activation-1.13e+00

Pos logit contributions
deen+0.314
…………+0.254
……………………+0.250
sth+0.231
 sod+0.229
Neg logit contributions
rast-0.336
iar-0.272
oise-0.265
 relegation-0.262
assic-0.257
Token needs
Token ID2476
Feature activation-8.76e-01

Pos logit contributions
rast+2.621
iar+2.022
oise+1.963
 relegation+1.951
orth+1.889
Neg logit contributions
deen-3.328
…………-2.742
……………………-2.716
sth-2.551
hest-2.522