TOP ACTIVATIONS
MAX = 11.660

, Facebook C OO Sher yl Sand berg said
seen any claims yet ," Las z ewski says . "
carbon ation . In the mouth it has an incredibly soft
put them in with the bell peppers . Fry until the
its top - not ch rating in the event of a
able version <|endoftext|> Rob C estern ino hosts a jam packed
it has an incredibly soft mouth feel , very smooth ,
the baking . Chest nut Fl our This
. Now we cut the bell peppers into small - medium
critical illness - related cort ic oster oid ins uff iciency
California 's Great America in Santa Clara , California was originally
straight from the horse 's mouth ! Now , as cool
reviewed by Facebook employees in Palo Alto , Calif ., and
s tongue , lips , jaw and l aryn x .
1080 ships with 25 60 CU DA cores and 20 SM
se , M ., Sch ol te , R ., Sal
the University of California , Santa Barbara , and an organizer
ol can be a daunting mouth ful , in more ways
. <|endoftext|> B rock Les nar has been flagged by the
surgery after suffering a fractured collar bone in Foot sc ray

MIN ACTIVATIONS
MIN = -12.029

: New Insight Into How Bees See <|endoftext|> The fuss is
last one is standing against Boris ). But that
post G WAR Eternal Tour Beaut ifully Paid Hom age To
former India captain , Rahul D rav id who said there
she calls the War on Women in politics . Hide Caption
We don 't have Q d oba there ."
industry ." Jerry Dw or ak , head of
Stephen Am ell and Robert Patt inson . While
bound on East 16 th Avenue . The woman
Trophy and Way man T isd ale Award Watch Lists .[
officer , Ak iny emi Boris ade , had only been
, that will no - d oubt reach fever pitch around
in Boston by anti - street harassment organization Holl ab ack
the Supreme Court Orders on Aadhaar The Supreme Court
we will perform meta - reg ression if a sufficient number
.' s lead singer Michael St ipe , told Newsweek in
a mission manager Dr Rune Fl ober gh agen .
. At least 250 people cycle in and out of the
companies letter to Sen . Patty Murray , Chair , Democratic
to say today , about Dw y ane Wade , Chris

INTERVAL 5.738 - 11.660
CONTAINS 0.424%

rock out cro ps and upper flat areas . If you
Sullivan is finally able to enter the cabin more than an
for repairing the sidewalks . AB 12 90 money is to
court has ruled if the seizure can go ahead . Some
stars a great future for Tol ui 's eldest son and

INTERVAL -0.184 - 5.738
CONTAINS 53.755%

He 's an animated figure , so he 's
start schedules up and back ." Let ting teenagers
by WikiLeaks sent from the US embassy in Tripoli in November
battle engines as well . Talk about a theme force with
Arts , which were parties to the public interest litigation (

INTERVAL -6.106 - -0.184
CONTAINS 45.496%

situation was . Areas of skin on his face and legs
ast > dude nice [ 10 : 47 ] < sp
)); RAW _ ASS ERT ( it -> i () ==
Dun bar form the centre partnership , while Finn Russell and
or 99 % of the people we so far know to

INTERVAL -12.029 - -6.106
CONTAINS 0.324%

her der , Yuri Kh udi , and his sons found
of calling out the hyper b olic Republican allegations MM legitim
" 94 "] [ Event Date " 2016 . ?? .?
of modern architectural firms and urban planning . Yet
between sub - st ages Super Mario 64 - style ,
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
terness+1.207
thur+1.143
phia+1.088
י�+1.073
chio+1.067
Neg logit contributions
��-1.058
 Belg-1.011
uss-0.983
rol-0.962
roid-0.947
Token
Token ID447
Feature activation+1.41e+00

Pos logit contributions
terness+1.091
thur+1.042
phia+0.998
י�+0.987
chio+0.980
Neg logit contributions
��-0.695
 Belg-0.659
uss-0.639
rol-0.621
roid-0.609
Token
Token ID251
Feature activation+4.13e-01

Pos logit contributions
terness+1.022
thur+0.962
phia+0.910
י�+0.895
chio+0.886
Neg logit contributions
��-1.138
 Belg-1.100
uss-1.075
rol-1.054
roid-1.037
Token Facebook
Token ID3203
Feature activation+1.23e+00

Pos logit contributions
terness+0.347
thur+0.330
phia+0.314
י�+0.310
chio+0.308
Neg logit contributions
��-0.286
 Belg-0.273
uss-0.266
rol-0.260
roid-0.255
Token C
Token ID327
Feature activation+2.41e+00

Pos logit contributions
terness+1.039
thur+0.988
phia+0.943
י�+0.929
chio+0.923
Neg logit contributions
��-0.845
 Belg-0.808
uss-0.786
rol-0.769
roid-0.755
TokenOO
Token ID6684
Feature activation+1.17e+01

Pos logit contributions
terness+1.472
thur+1.374
phia+1.285
י�+1.258
chio+1.248
Neg logit contributions
��-2.217
 Belg-2.142
uss-2.090
rol-2.058
roid-2.034
Token Sher
Token ID6528
Feature activation+5.99e-01

Pos logit contributions
terness+8.610
thur+8.085
phia+8.069
TER+8.053
י�+7.956
Neg logit contributions
��-7.949
 Belg-7.369
uss-7.097
roid-6.966
rol-6.867
Tokenyl
Token ID2645
Feature activation+2.54e+00

Pos logit contributions
terness+0.396
thur+0.369
phia+0.348
י�+0.343
chio+0.338
Neg logit contributions
��-0.518
 Belg-0.506
uss-0.496
rol-0.490
roid-0.481
Token Sand
Token ID3837
Feature activation-4.07e+00

Pos logit contributions
terness+1.948
thur+1.839
phia+1.751
י�+1.720
chio+1.705
Neg logit contributions
��-1.939
 Belg-1.864
uss-1.823
rol-1.787
roid-1.756
Tokenberg
Token ID3900
Feature activation+4.13e+00

Pos logit contributions
uss+3.124
��+3.012
rol+3.005
 Belg+3.001
roid+2.884
Neg logit contributions
terness-3.076
thur-2.798
renheit-2.729
BLIC-2.663
phia-2.651
Token said
Token ID531
Feature activation+1.87e+00

Pos logit contributions
terness+3.411
thur+3.262
phia+3.104
chio+3.094
י�+3.087
Neg logit contributions
��-2.879
 Belg-2.695
uss-2.596
rol-2.550
roid-2.518
Token seen
Token ID1775
Feature activation-8.52e-01

Pos logit contributions
terness+2.873
thur+2.759
phia+2.636
י�+2.619
chio+2.606
Neg logit contributions
��-2.204
 Belg-2.047
uss-1.990
rol-1.943
roid-1.892
Token any
Token ID597
Feature activation-2.28e-02

Pos logit contributions
��+0.552
 Belg+0.537
uss+0.521
rol+0.510
roid+0.499
Neg logit contributions
terness-0.749
thur-0.710
phia-0.680
י�-0.669
renheit-0.666
Token claims
Token ID3667
Feature activation+1.28e+00

Pos logit contributions
��+0.015
 Belg+0.014
uss+0.014
rol+0.013
roid+0.013
Neg logit contributions
terness-0.020
thur-0.019
phia-0.018
י�-0.018
chio-0.018
Token yet
Token ID1865
Feature activation-1.35e+00

Pos logit contributions
terness+1.131
thur+1.077
phia+1.029
י�+1.015
chio+1.009
Neg logit contributions
��-0.839
 Belg-0.800
uss-0.777
rol-0.759
roid-0.743
Token,"
Token ID553
Feature activation-1.64e+00

Pos logit contributions
��+0.844
 Belg+0.831
uss+0.808
rol+0.794
roid+0.776
Neg logit contributions
terness-1.202
thur-1.149
phia-1.098
י�-1.078
renheit-1.076
Token Las
Token ID10123
Feature activation+1.06e+01

Pos logit contributions
��+0.953
 Belg+0.938
uss+0.898
rol+0.885
roid+0.856
Neg logit contributions
terness-1.538
thur-1.473
phia-1.409
renheit-1.394
י�-1.385
Tokenz
Token ID89
Feature activation+4.40e+00

Pos logit contributions
terness+6.255
thur+6.230
chio+5.949
TER+5.878
phia+5.799
Neg logit contributions
��-9.767
 Belg-8.961
 newsp-8.318
 millenn-8.165
 heartbeat-8.045
Tokenewski
Token ID46151
Feature activation+1.79e+00

Pos logit contributions
terness+2.713
thur+2.596
chio+2.445
phia+2.435
י�+2.367
Neg logit contributions
��-4.014
 Belg-3.817
uss-3.589
rol-3.582
roid-3.563
Token says
Token ID1139
Feature activation+7.10e-01

Pos logit contributions
terness+1.539
thur+1.463
phia+1.395
י�+1.384
chio+1.377
Neg logit contributions
��-1.208
 Belg-1.146
uss-1.111
rol-1.084
roid-1.066
Token.
Token ID13
Feature activation+2.42e+00

Pos logit contributions
terness+0.578
thur+0.546
phia+0.519
י�+0.514
chio+0.510
Neg logit contributions
��-0.511
 Belg-0.489
uss-0.477
rol-0.466
roid-0.459
Token "
Token ID366
Feature activation+2.19e+00

Pos logit contributions
terness+1.821
thur+1.716
phia+1.629
י�+1.607
chio+1.593
Neg logit contributions
��-1.894
 Belg-1.809
uss-1.770
rol-1.731
roid-1.709
Token carbon
Token ID6588
Feature activation+3.14e-01

Pos logit contributions
terness+0.139
thur+0.131
phia+0.125
י�+0.124
chio+0.123
Neg logit contributions
��-0.111
 Belg-0.105
uss-0.103
rol-0.101
roid-0.099
Tokenation
Token ID341
Feature activation-9.59e-01

Pos logit contributions
terness+0.226
thur+0.213
phia+0.201
י�+0.198
chio+0.196
Neg logit contributions
��-0.255
 Belg-0.246
uss-0.240
rol-0.236
roid-0.232
Token.
Token ID13
Feature activation+1.91e+00

Pos logit contributions
��+0.652
 Belg+0.632
uss+0.616
rol+0.605
roid+0.593
Neg logit contributions
terness-0.806
thur-0.774
phia-0.737
י�-0.722
renheit-0.719
Token In
Token ID554
Feature activation+1.60e+00

Pos logit contributions
terness+1.544
thur+1.462
phia+1.390
י�+1.372
chio+1.361
Neg logit contributions
��-1.386
 Belg-1.322
uss-1.293
rol-1.266
roid-1.245
Token the
Token ID262
Feature activation+1.45e+00

Pos logit contributions
terness+1.405
thur+1.325
phia+1.263
י�+1.245
chio+1.245
Neg logit contributions
��-1.065
 Belg-1.003
uss-0.977
rol-0.960
roid-0.949
Token mouth
Token ID5422
Feature activation+1.04e+01

Pos logit contributions
terness+1.265
thur+1.200
phia+1.145
י�+1.131
chio+1.126
Neg logit contributions
��-0.952
 Belg-0.903
uss-0.882
rol-0.864
roid-0.848
Token it
Token ID340
Feature activation-3.40e-01

Pos logit contributions
terness+7.926
thur+7.085
י�+6.771
renheit+6.705
TER+6.590
Neg logit contributions
��-7.960
 Belg-7.274
roid-7.039
rol-6.994
uss-6.939
Token has
Token ID468
Feature activation+2.73e+00

Pos logit contributions
��+0.221
 Belg+0.215
uss+0.210
rol+0.204
roid+0.200
Neg logit contributions
terness-0.297
thur-0.283
phia-0.271
י�-0.267
renheit-0.265
Token an
Token ID281
Feature activation+1.37e+00

Pos logit contributions
terness+2.263
thur+2.135
phia+2.014
י�+2.002
chio+1.983
Neg logit contributions
��-1.952
 Belg-1.829
uss-1.796
rol-1.756
roid-1.727
Token incredibly
Token ID8131
Feature activation-2.42e+00

Pos logit contributions
terness+1.179
thur+1.116
phia+1.054
י�+1.046
chio+1.037
Neg logit contributions
��-0.941
 Belg-0.890
uss-0.869
rol-0.849
roid-0.836
Token soft
Token ID2705
Feature activation+1.22e+00

Pos logit contributions
��+1.454
 Belg+1.430
uss+1.375
rol+1.340
roid+1.298
Neg logit contributions
terness-2.193
thur-2.116
phia-2.045
י�-1.988
renheit-1.984
Token put
Token ID1234
Feature activation-2.72e+00

Pos logit contributions
��+1.059
 Belg+1.048
uss+1.029
rol+1.003
roid+0.976
Neg logit contributions
terness-1.315
thur-1.248
phia-1.189
renheit-1.172
י�-1.164
Token them
Token ID606
Feature activation+1.13e+00

Pos logit contributions
��+1.562
 Belg+1.504
uss+1.482
rol+1.447
roid+1.401
Neg logit contributions
terness-2.542
thur-2.445
phia-2.339
י�-2.314
renheit-2.286
Token in
Token ID287
Feature activation-7.50e-01

Pos logit contributions
terness+0.997
thur+0.950
phia+0.908
י�+0.895
chio+0.890
Neg logit contributions
��-0.744
 Belg-0.710
uss-0.687
rol-0.671
roid-0.658
Token with
Token ID351
Feature activation-2.12e+00

Pos logit contributions
��+0.529
 Belg+0.510
uss+0.499
rol+0.487
roid+0.478
Neg logit contributions
terness-0.615
thur-0.587
phia-0.556
י�-0.548
renheit-0.542
Token the
Token ID262
Feature activation-2.50e-01

Pos logit contributions
��+1.439
 Belg+1.421
uss+1.376
rol+1.353
roid+1.314
Neg logit contributions
terness-1.762
thur-1.688
phia-1.602
י�-1.569
renheit-1.564
Token bell
Token ID8966
Feature activation+1.04e+01

Pos logit contributions
��+0.195
 Belg+0.191
uss+0.185
rol+0.182
roid+0.178
Neg logit contributions
terness-0.186
thur-0.176
phia-0.167
י�-0.164
renheit-0.163
Token peppers
Token ID31804
Feature activation+2.96e+00

Pos logit contributions
terness+3.953
thur+3.493
phia+3.281
chio+3.097
י�+3.093
Neg logit contributions
��-11.628
 Belg-11.108
uss-10.682
roid-10.517
rol-10.470
Token.
Token ID13
Feature activation+5.19e-01

Pos logit contributions
terness+2.355
thur+2.220
phia+2.113
י�+2.090
chio+2.071
Neg logit contributions
��-2.200
 Belg-2.096
uss-2.025
rol-1.981
roid-1.950
Token Fry
Token ID25305
Feature activation+8.46e-01

Pos logit contributions
terness+0.425
thur+0.404
phia+0.385
י�+0.378
chio+0.376
Neg logit contributions
��-0.369
 Belg-0.357
uss-0.347
rol-0.340
roid-0.333
Token until
Token ID1566
Feature activation+2.90e-01

Pos logit contributions
terness+0.733
thur+0.698
phia+0.666
י�+0.657
chio+0.653
Neg logit contributions
��-0.562
 Belg-0.539
uss-0.524
rol-0.513
roid-0.502
Token the
Token ID262
Feature activation+9.93e-01

Pos logit contributions
terness+0.246
thur+0.237
phia+0.225
י�+0.221
renheit+0.221
Neg logit contributions
��-0.195
 Belg-0.187
uss-0.183
rol-0.179
roid-0.174
Token its
Token ID663
Feature activation+5.88e-01

Pos logit contributions
terness+1.716
thur+1.631
phia+1.556
י�+1.534
chio+1.523
Neg logit contributions
��-1.372
 Belg-1.316
uss-1.280
rol-1.252
roid-1.227
Token top
Token ID1353
Feature activation+3.11e+00

Pos logit contributions
terness+0.514
thur+0.484
phia+0.463
י�+0.457
renheit+0.455
Neg logit contributions
��-0.384
 Belg-0.377
uss-0.366
rol-0.359
roid-0.347
Token-
Token ID12
Feature activation-9.59e-01

Pos logit contributions
terness+2.673
thur+2.566
phia+2.442
י�+2.416
renheit+2.387
Neg logit contributions
��-2.094
 Belg-1.955
uss-1.910
rol-1.855
roid-1.829
Tokennot
Token ID1662
Feature activation-2.67e-01

Pos logit contributions
��+0.701
 Belg+0.686
uss+0.675
rol+0.665
roid+0.652
Neg logit contributions
terness-0.756
thur-0.711
phia-0.678
י�-0.666
renheit-0.664
Tokench
Token ID354
Feature activation-8.59e-01

Pos logit contributions
��+0.207
 Belg+0.202
uss+0.200
rol+0.196
roid+0.192
Neg logit contributions
terness-0.197
thur-0.186
phia-0.178
י�-0.175
renheit-0.173
Token rating
Token ID7955
Feature activation+1.02e+01

Pos logit contributions
��+0.531
 Belg+0.516
uss+0.500
rol+0.488
roid+0.476
Neg logit contributions
terness-0.782
thur-0.743
phia-0.710
י�-0.701
renheit-0.697
Token in
Token ID287
Feature activation+2.21e+00

Pos logit contributions
terness+7.209
thur+6.914
chio+6.483
י�+6.477
phia+6.419
Neg logit contributions
��-8.106
 Belg-7.116
uss-6.984
rol-6.810
roid-6.758
Token the
Token ID262
Feature activation+2.12e+00

Pos logit contributions
terness+1.712
thur+1.633
phia+1.552
י�+1.518
chio+1.516
Neg logit contributions
��-1.683
 Belg-1.580
uss-1.540
rol-1.513
roid-1.505
Token event
Token ID1785
Feature activation+3.27e+00

Pos logit contributions
terness+1.828
thur+1.748
phia+1.673
י�+1.648
chio+1.640
Neg logit contributions
��-1.426
 Belg-1.335
uss-1.297
rol-1.274
roid-1.256
Token of
Token ID286
Feature activation+3.02e-01

Pos logit contributions
terness+2.470
thur+2.330
phia+2.188
י�+2.165
chio+2.156
Neg logit contributions
��-2.559
 Belg-2.413
uss-2.340
rol-2.308
roid-2.305
Token a
Token ID257
Feature activation+1.83e+00

Pos logit contributions
terness+0.257
thur+0.244
phia+0.233
י�+0.230
chio+0.228
Neg logit contributions
��-0.205
 Belg-0.197
uss-0.192
rol-0.188
roid-0.184
Tokenable
Token ID540
Feature activation+2.01e+00

Pos logit contributions
terness+1.304
thur+1.256
phia+1.192
chio+1.191
י�+1.175
Neg logit contributions
��-0.793
 Belg-0.725
rol-0.702
uss-0.699
roid-0.660
Token version
Token ID2196
Feature activation+1.61e+00

Pos logit contributions
terness+1.591
thur+1.535
phia+1.441
chio+1.428
י�+1.422
Neg logit contributions
��-1.496
 Belg-1.411
uss-1.369
rol-1.353
roid-1.315
Token<|endoftext|>
Token ID50256
Feature activation+1.18e+00

Pos logit contributions
terness+1.070
thur+1.015
phia+0.949
chio+0.935
י�+0.935
Neg logit contributions
��-1.400
 Belg-1.321
uss-1.300
rol-1.295
roid-1.240
TokenRob
Token ID14350
Feature activation-1.97e+00

Pos logit contributions
terness+0.854
thur+0.804
phia+0.760
י�+0.747
chio+0.741
Neg logit contributions
��-0.956
 Belg-0.923
uss-0.902
rol-0.886
roid-0.871
Token C
Token ID327
Feature activation-1.76e+00

Pos logit contributions
��+1.436
 Belg+1.398
uss+1.362
rol+1.336
roid+1.312
Neg logit contributions
terness-1.573
thur-1.497
phia-1.407
י�-1.392
renheit-1.389
Tokenestern
Token ID3330
Feature activation+1.02e+01

Pos logit contributions
��+1.663
uss+1.646
 Belg+1.642
rol+1.617
roid+1.582
Neg logit contributions
terness-1.013
thur-0.925
phia-0.869
י�-0.857
renheit-0.829
Tokenino
Token ID2879
Feature activation+4.11e+00

Pos logit contributions
terness+4.498
thur+4.369
chio+4.311
י�+3.886
phia+3.831
Neg logit contributions
��-11.095
 Belg-10.200
roid-9.559
rol-9.400
 heartbeat-9.376
Token hosts
Token ID11453
Feature activation+1.46e+00

Pos logit contributions
terness+3.337
thur+3.178
phia+3.013
chio+2.996
י�+2.987
Neg logit contributions
��-2.976
 Belg-2.781
uss-2.676
rol-2.648
roid-2.597
Token a
Token ID257
Feature activation+2.66e-01

Pos logit contributions
terness+1.203
thur+1.144
phia+1.090
י�+1.073
chio+1.067
Neg logit contributions
��-1.033
 Belg-0.988
uss-0.961
rol-0.941
roid-0.924
Token jam
Token ID16853
Feature activation+7.18e-01

Pos logit contributions
terness+0.246
thur+0.234
phia+0.224
י�+0.222
renheit+0.220
Neg logit contributions
��-0.161
 Belg-0.154
uss-0.150
rol-0.146
roid-0.143
Token packed
Token ID11856
Feature activation-2.47e-01

Pos logit contributions
terness+0.615
thur+0.584
phia+0.557
י�+0.549
renheit+0.545
Neg logit contributions
��-0.486
 Belg-0.466
uss-0.455
rol-0.444
roid-0.436
Token it
Token ID340
Feature activation-3.40e-01

Pos logit contributions
terness+7.926
thur+7.085
י�+6.771
renheit+6.705
TER+6.590
Neg logit contributions
��-7.960
 Belg-7.274
roid-7.039
rol-6.994
uss-6.939
Token has
Token ID468
Feature activation+2.73e+00

Pos logit contributions
��+0.221
 Belg+0.215
uss+0.210
rol+0.204
roid+0.200
Neg logit contributions
terness-0.297
thur-0.283
phia-0.271
י�-0.267
renheit-0.265
Token an
Token ID281
Feature activation+1.37e+00

Pos logit contributions
terness+2.263
thur+2.135
phia+2.014
י�+2.002
chio+1.983
Neg logit contributions
��-1.952
 Belg-1.829
uss-1.796
rol-1.756
roid-1.727
Token incredibly
Token ID8131
Feature activation-2.42e+00

Pos logit contributions
terness+1.179
thur+1.116
phia+1.054
י�+1.046
chio+1.037
Neg logit contributions
��-0.941
 Belg-0.890
uss-0.869
rol-0.849
roid-0.836
Token soft
Token ID2705
Feature activation+1.22e+00

Pos logit contributions
��+1.454
 Belg+1.430
uss+1.375
rol+1.340
roid+1.298
Neg logit contributions
terness-2.193
thur-2.116
phia-2.045
י�-1.988
renheit-1.984
Token mouth
Token ID5422
Feature activation+1.01e+01

Pos logit contributions
terness+1.020
thur+0.962
phia+0.917
י�+0.904
chio+0.897
Neg logit contributions
��-0.861
 Belg-0.819
uss-0.799
rol-0.781
roid-0.768
Tokenfeel
Token ID36410
Feature activation+2.12e+00

Pos logit contributions
terness+6.359
thur+5.863
י�+5.395
phia+5.394
TER+5.265
Neg logit contributions
��-8.580
 Belg-8.368
roid-7.839
uss-7.742
rol-7.602
Token,
Token ID11
Feature activation+4.72e-01

Pos logit contributions
terness+1.720
thur+1.621
phia+1.540
י�+1.526
chio+1.508
Neg logit contributions
��-1.533
 Belg-1.472
uss-1.431
rol-1.400
roid-1.376
Token very
Token ID845
Feature activation-7.61e-01

Pos logit contributions
terness+0.404
thur+0.384
phia+0.367
י�+0.362
chio+0.359
Neg logit contributions
��-0.320
 Belg-0.306
uss-0.298
rol-0.291
roid-0.286
Token smooth
Token ID7209
Feature activation+9.38e-01

Pos logit contributions
��+0.459
 Belg+0.439
uss+0.425
rol+0.414
roid+0.404
Neg logit contributions
terness-0.706
thur-0.675
phia-0.647
י�-0.638
chio-0.634
Token,
Token ID11
Feature activation+2.78e+00

Pos logit contributions
terness+0.755
thur+0.712
phia+0.677
י�+0.669
chio+0.661
Neg logit contributions
��-0.685
 Belg-0.656
uss-0.638
rol-0.626
roid-0.615
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
��+0.303
 Belg+0.297
uss+0.289
rol+0.282
roid+0.275
Neg logit contributions
terness-0.371
thur-0.352
phia-0.336
י�-0.331
renheit-0.330
Token baking
Token ID16871
Feature activation+1.87e-01

Pos logit contributions
terness+1.044
thur+0.993
phia+0.948
י�+0.933
chio+0.927
Neg logit contributions
��-0.838
 Belg-0.798
uss-0.777
rol-0.760
roid-0.746
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
terness+0.164
thur+0.157
phia+0.150
י�+0.148
chio+0.146
Neg logit contributions
��-0.122
 Belg-0.118
uss-0.114
rol-0.112
roid-0.109
Token
Token ID198
Feature activation+9.79e-01

Pos logit contributions
terness+1.045
thur+0.991
phia+0.942
י�+0.926
chio+0.921
Neg logit contributions
��-0.941
 Belg-0.910
uss-0.884
rol-0.866
roid-0.850
Token
Token ID198
Feature activation-2.28e-01

Pos logit contributions
terness+0.714
thur+0.670
phia+0.634
י�+0.622
chio+0.617
Neg logit contributions
��-0.786
 Belg-0.763
uss-0.746
rol-0.733
roid-0.720
TokenChest
Token ID45170
Feature activation+1.00e+01

Pos logit contributions
��+0.182
 Belg+0.178
uss+0.176
rol+0.173
roid+0.170
Neg logit contributions
terness-0.166
thur-0.154
phia-0.146
renheit-0.143
י�-0.142
Tokennut
Token ID14930
Feature activation+5.39e+00

Pos logit contributions
terness+4.668
thur+4.586
phia+4.057
chio+4.010
י�+3.835
Neg logit contributions
��-10.051
 Belg-9.568
uss-9.330
rol-9.103
roid-9.045
Token Fl
Token ID1610
Feature activation-2.07e+00

Pos logit contributions
terness+4.815
thur+4.620
phia+4.406
chio+4.376
י�+4.322
Neg logit contributions
��-3.363
 Belg-3.118
uss-3.071
rol-2.944
roid-2.897
Tokenour
Token ID454
Feature activation+1.41e-01

Pos logit contributions
��+0.762
 Belg+0.726
uss+0.717
rol+0.678
roid+0.655
Neg logit contributions
terness-2.376
thur-2.278
phia-2.201
י�-2.190
renheit-2.169
Token
Token ID960
Feature activation-2.47e-01

Pos logit contributions
terness+0.114
thur+0.108
phia+0.103
י�+0.101
chio+0.100
Neg logit contributions
��-0.102
 Belg-0.098
uss-0.096
rol-0.094
roid-0.092
TokenThis
Token ID1212
Feature activation-2.15e+00

Pos logit contributions
��+0.193
 Belg+0.190
uss+0.186
rol+0.182
roid+0.179
Neg logit contributions
terness-0.183
thur-0.171
phia-0.162
renheit-0.159
י�-0.159
Token.
Token ID13
Feature activation+2.40e+00

Pos logit contributions
��+0.230
 Belg+0.227
uss+0.222
rol+0.218
roid+0.212
Neg logit contributions
terness-0.309
thur-0.291
phia-0.278
י�-0.271
renheit-0.271
Token Now
Token ID2735
Feature activation+2.83e+00

Pos logit contributions
terness+2.125
thur+2.012
phia+1.922
י�+1.911
chio+1.897
Neg logit contributions
��-1.558
 Belg-1.462
uss-1.426
rol-1.390
roid-1.371
Token we
Token ID356
Feature activation+1.71e+00

Pos logit contributions
terness+2.466
thur+2.339
phia+2.228
י�+2.213
chio+2.200
Neg logit contributions
��-1.888
 Belg-1.766
uss-1.704
rol-1.664
roid-1.641
Token cut
Token ID2005
Feature activation+4.15e+00

Pos logit contributions
terness+1.436
thur+1.365
phia+1.299
י�+1.285
chio+1.277
Neg logit contributions
��-1.192
 Belg-1.140
uss-1.103
rol-1.080
roid-1.063
Token the
Token ID262
Feature activation+6.14e-01

Pos logit contributions
terness+3.248
thur+3.063
phia+2.915
י�+2.882
chio+2.856
Neg logit contributions
��-3.118
 Belg-2.968
uss-2.864
rol-2.814
roid-2.773
Token bell
Token ID8966
Feature activation+1.00e+01

Pos logit contributions
terness+0.490
thur+0.463
phia+0.441
י�+0.434
renheit+0.430
Neg logit contributions
��-0.450
 Belg-0.436
uss-0.425
rol-0.416
roid-0.407
Token peppers
Token ID31804
Feature activation+3.79e+00

Pos logit contributions
terness+4.606
thur+4.263
phia+4.098
chio+3.851
י�+3.808
Neg logit contributions
��-10.702
 Belg-9.908
uss-9.581
rol-9.453
roid-9.443
Token into
Token ID656
Feature activation+2.75e+00

Pos logit contributions
terness+3.037
thur+2.877
phia+2.732
י�+2.708
chio+2.702
Neg logit contributions
��-2.770
 Belg-2.608
uss-2.524
rol-2.470
roid-2.424
Token small
Token ID1402
Feature activation+1.34e+00

Pos logit contributions
terness+2.367
thur+2.260
phia+2.165
י�+2.135
chio+2.124
Neg logit contributions
��-1.846
 Belg-1.724
uss-1.682
rol-1.643
roid-1.616
Token-
Token ID12
Feature activation+7.88e-01

Pos logit contributions
terness+1.144
thur+1.089
phia+1.041
י�+1.025
chio+1.019
Neg logit contributions
��-0.903
 Belg-0.860
uss-0.838
rol-0.819
roid-0.803
Tokenmedium
Token ID24132
Feature activation+9.93e-01

Pos logit contributions
terness+0.604
thur+0.571
phia+0.541
י�+0.533
chio+0.529
Neg logit contributions
��-0.603
 Belg-0.580
uss-0.567
rol-0.555
roid-0.546
Token critical
Token ID4688
Feature activation-4.06e-01

Pos logit contributions
terness+1.128
thur+1.077
phia+1.027
י�+1.015
chio+1.009
Neg logit contributions
��-0.854
 Belg-0.808
uss-0.787
rol-0.768
roid-0.752
Token illness
Token ID8526
Feature activation-5.59e-01

Pos logit contributions
��+0.253
 Belg+0.244
uss+0.237
rol+0.232
roid+0.227
Neg logit contributions
terness-0.367
thur-0.350
phia-0.335
י�-0.330
renheit-0.328
Token-
Token ID12
Feature activation+1.17e+00

Pos logit contributions
��+0.388
 Belg+0.375
uss+0.365
rol+0.357
roid+0.351
Neg logit contributions
terness-0.466
thur-0.444
phia-0.422
י�-0.417
renheit-0.414
Tokenrelated
Token ID5363
Feature activation-1.09e+00

Pos logit contributions
terness+1.019
thur+0.970
phia+0.926
י�+0.914
renheit+0.908
Neg logit contributions
��-0.773
 Belg-0.743
uss-0.725
rol-0.707
roid-0.693
Token cort
Token ID12794
Feature activation+2.35e+00

Pos logit contributions
��+0.713
 Belg+0.700
uss+0.677
rol+0.662
roid+0.650
Neg logit contributions
terness-0.943
thur-0.897
phia-0.858
י�-0.841
renheit-0.841
Tokenic
Token ID291
Feature activation+9.99e+00

Pos logit contributions
terness+1.366
thur+1.270
phia+1.183
י�+1.155
chio+1.148
Neg logit contributions
��-2.245
 Belg-2.170
uss-2.116
rol-2.087
roid-2.061
Tokenoster
Token ID6197
Feature activation+4.01e+00

Pos logit contributions
terness+6.072
thur+5.647
chio+5.479
phia+5.244
י�+5.229
Neg logit contributions
��-9.261
 Belg-8.583
uss-8.006
rol-7.982
roid-7.755
Tokenoid
Token ID1868
Feature activation+5.61e+00

Pos logit contributions
terness+1.462
thur+1.303
phia+1.153
י�+1.098
chio+1.097
Neg logit contributions
��-4.713
 Belg-4.556
uss-4.449
rol-4.389
roid-4.343
Token ins
Token ID1035
Feature activation+3.73e+00

Pos logit contributions
terness+4.644
thur+4.354
phia+4.220
chio+4.186
י�+4.179
Neg logit contributions
��-3.927
 Belg-3.535
uss-3.376
rol-3.326
roid-3.229
Tokenuff
Token ID1648
Feature activation-5.04e-01

Pos logit contributions
terness+3.127
thur+2.931
phia+2.831
chio+2.770
י�+2.764
Neg logit contributions
��-2.621
 Belg-2.495
uss-2.355
rol-2.316
roid-2.277
Tokeniciency
Token ID19777
Feature activation+2.58e+00

Pos logit contributions
��+0.379
 Belg+0.370
uss+0.367
rol+0.362
roid+0.354
Neg logit contributions
terness-0.387
thur-0.365
phia-0.343
י�-0.340
renheit-0.337
Token California
Token ID3442
Feature activation+7.57e-01

Pos logit contributions
��+0.358
 Belg+0.346
uss+0.336
rol+0.330
roid+0.323
Neg logit contributions
terness-0.393
thur-0.371
phia-0.353
י�-0.348
renheit-0.346
Token's
Token ID338
Feature activation-2.10e+00

Pos logit contributions
terness+0.654
thur+0.624
phia+0.595
י�+0.586
chio+0.582
Neg logit contributions
��-0.507
 Belg-0.484
uss-0.470
rol-0.459
roid-0.451
Token Great
Token ID3878
Feature activation-1.77e-01

Pos logit contributions
��+1.452
 Belg+1.417
uss+1.365
rol+1.343
roid+1.312
Neg logit contributions
terness-1.760
thur-1.661
phia-1.589
י�-1.562
renheit-1.557
Token America
Token ID2253
Feature activation+9.97e-01

Pos logit contributions
��+0.132
 Belg+0.127
uss+0.124
rol+0.122
roid+0.119
Neg logit contributions
terness-0.139
thur-0.132
phia-0.125
י�-0.123
chio-0.122
Token in
Token ID287
Feature activation-1.12e+00

Pos logit contributions
terness+0.810
thur+0.776
phia+0.738
י�+0.723
chio+0.721
Neg logit contributions
��-0.717
 Belg-0.680
uss-0.662
rol-0.649
roid-0.637
Token Santa
Token ID8909
Feature activation+9.96e+00

Pos logit contributions
��+0.765
 Belg+0.741
uss+0.718
rol+0.703
roid+0.688
Neg logit contributions
terness-0.949
thur-0.900
phia-0.858
י�-0.846
chio-0.840
Token Clara
Token ID27443
Feature activation+3.04e+00

Pos logit contributions
terness+6.160
thur+6.033
phia+5.628
renheit+5.499
chio+5.478
Neg logit contributions
��-8.634
 Belg-7.854
uss-7.791
roid-7.707
rol-7.533
Token,
Token ID11
Feature activation+1.71e+00

Pos logit contributions
terness+2.375
thur+2.284
phia+2.188
י�+2.122
chio+2.120
Neg logit contributions
��-2.259
 Belg-2.135
uss-2.080
rol-2.036
roid-2.002
Token California
Token ID3442
Feature activation+3.59e+00

Pos logit contributions
terness+1.081
thur+1.018
phia+0.948
י�+0.930
chio+0.921
Neg logit contributions
��-1.544
 Belg-1.475
uss-1.446
rol-1.427
roid-1.408
Token was
Token ID373
Feature activation-5.72e-01

Pos logit contributions
terness+2.792
thur+2.701
phia+2.561
chio+2.520
י�+2.512
Neg logit contributions
��-2.652
 Belg-2.508
uss-2.424
rol-2.377
roid-2.350
Token originally
Token ID6198
Feature activation+2.27e+00

Pos logit contributions
��+0.363
 Belg+0.350
uss+0.340
rol+0.332
roid+0.325
Neg logit contributions
terness-0.513
thur-0.488
phia-0.466
י�-0.460
renheit-0.457
Token straight
Token ID3892
Feature activation+7.65e+00

Pos logit contributions
terness+2.472
thur+2.358
phia+2.236
י�+2.214
chio+2.199
Neg logit contributions
��-2.061
 Belg-1.905
uss-1.873
rol-1.830
roid-1.813
Token from
Token ID422
Feature activation+2.75e+00

Pos logit contributions
terness+6.069
thur+5.847
י�+5.553
phia+5.493
DEN+5.443
Neg logit contributions
��-5.525
 Belg-4.873
uss-4.752
rol-4.703
roid-4.613
Token the
Token ID262
Feature activation+1.56e+00

Pos logit contributions
terness+2.312
thur+2.203
phia+2.097
י�+2.074
chio+2.053
Neg logit contributions
��-1.915
 Belg-1.793
uss-1.752
rol-1.715
roid-1.690
Token horse
Token ID8223
Feature activation+4.20e+00

Pos logit contributions
terness+1.372
thur+1.313
phia+1.252
י�+1.237
chio+1.230
Neg logit contributions
��-1.019
 Belg-0.961
uss-0.936
rol-0.914
roid-0.896
Token's
Token ID338
Feature activation+3.05e-01

Pos logit contributions
terness+3.409
thur+3.309
phia+3.096
י�+3.048
chio+3.021
Neg logit contributions
��-3.010
 Belg-2.821
uss-2.730
rol-2.666
roid-2.651
Token mouth
Token ID5422
Feature activation+9.89e+00

Pos logit contributions
terness+0.275
thur+0.262
phia+0.251
י�+0.248
chio+0.246
Neg logit contributions
��-0.193
 Belg-0.184
uss-0.179
rol-0.174
roid-0.171
Token!
Token ID0
Feature activation+4.30e+00

Pos logit contributions
terness+7.117
thur+6.707
י�+6.368
phia+6.336
TER+6.269
Neg logit contributions
��-7.696
 Belg-6.906
uss-6.654
rol-6.640
roid-6.503
Token Now
Token ID2735
Feature activation+3.46e+00

Pos logit contributions
terness+3.407
thur+3.243
י�+3.072
phia+3.054
chio+3.031
Neg logit contributions
��-3.169
 Belg-2.891
uss-2.874
rol-2.805
roid-2.786
Token,
Token ID11
Feature activation+4.17e-01

Pos logit contributions
terness+2.813
thur+2.691
phia+2.532
י�+2.525
chio+2.506
Neg logit contributions
��-2.491
 Belg-2.305
uss-2.240
rol-2.187
roid-2.162
Token as
Token ID355
Feature activation+3.26e+00

Pos logit contributions
terness+0.355
thur+0.338
phia+0.322
י�+0.317
chio+0.315
Neg logit contributions
��-0.284
 Belg-0.272
uss-0.265
rol-0.259
roid-0.254
Token cool
Token ID3608
Feature activation-3.03e+00

Pos logit contributions
terness+2.575
thur+2.453
phia+2.312
י�+2.286
chio+2.267
Neg logit contributions
��-2.435
 Belg-2.273
uss-2.218
rol-2.177
roid-2.162
Token reviewed
Token ID11765
Feature activation+3.68e+00

Pos logit contributions
terness+3.117
thur+2.992
phia+2.847
י�+2.811
chio+2.797
Neg logit contributions
��-2.621
 Belg-2.404
uss-2.360
rol-2.308
roid-2.272
Token by
Token ID416
Feature activation-7.24e-01

Pos logit contributions
terness+2.850
thur+2.721
phia+2.572
י�+2.549
chio+2.534
Neg logit contributions
��-2.755
 Belg-2.586
uss-2.537
rol-2.466
roid-2.441
Token Facebook
Token ID3203
Feature activation-2.05e-01

Pos logit contributions
��+0.499
 Belg+0.482
uss+0.467
rol+0.458
roid+0.448
Neg logit contributions
terness-0.613
thur-0.581
phia-0.553
י�-0.545
chio-0.542
Token employees
Token ID4409
Feature activation+1.77e+00

Pos logit contributions
��+0.143
 Belg+0.138
uss+0.134
rol+0.131
roid+0.129
Neg logit contributions
terness-0.172
thur-0.163
phia-0.155
י�-0.153
chio-0.152
Token in
Token ID287
Feature activation+1.22e+00

Pos logit contributions
terness+1.413
thur+1.343
phia+1.278
י�+1.262
chio+1.250
Neg logit contributions
��-1.298
 Belg-1.236
uss-1.204
rol-1.176
roid-1.157
Token Palo
Token ID44878
Feature activation+9.88e+00

Pos logit contributions
terness+1.051
thur+1.002
phia+0.958
י�+0.944
chio+0.939
Neg logit contributions
��-0.812
 Belg-0.769
uss-0.748
rol-0.733
roid-0.719
Token Alto
Token ID34317
Feature activation+6.43e+00

Pos logit contributions
terness+3.763
thur+3.528
phia+3.231
chio+3.007
renheit+2.861
Neg logit contributions
��-11.268
 Belg-10.342
uss-10.318
rol-10.199
roid-10.069
Token,
Token ID11
Feature activation+1.32e+00

Pos logit contributions
terness+4.586
thur+4.418
phia+4.265
י�+4.056
chio+4.042
Neg logit contributions
��-5.173
 Belg-4.812
uss-4.723
rol-4.579
roid-4.566
Token Calif
Token ID3192
Feature activation+5.03e+00

Pos logit contributions
terness+0.927
thur+0.873
phia+0.824
י�+0.809
chio+0.801
Neg logit contributions
��-1.097
 Belg-1.055
uss-1.032
rol-1.014
roid-0.998
Token.,
Token ID1539
Feature activation-2.81e-01

Pos logit contributions
terness+3.248
thur+3.098
phia+2.928
י�+2.855
chio+2.834
Neg logit contributions
��-4.381
 Belg-4.179
uss-4.000
roid-3.907
rol-3.899
Token and
Token ID290
Feature activation+3.17e-01

Pos logit contributions
��+0.192
 Belg+0.186
uss+0.180
rol+0.176
roid+0.173
Neg logit contributions
terness-0.238
thur-0.226
phia-0.215
י�-0.212
renheit-0.211
Tokens
Token ID82
Feature activation+2.44e-01

Pos logit contributions
terness+0.437
thur+0.416
phia+0.397
י�+0.392
chio+0.389
Neg logit contributions
��-0.330
 Belg-0.316
uss-0.307
rol-0.300
roid-0.294
Token tongue
Token ID11880
Feature activation+4.06e+00

Pos logit contributions
terness+0.206
thur+0.196
phia+0.187
י�+0.184
renheit+0.183
Neg logit contributions
��-0.168
 Belg-0.161
uss-0.157
rol-0.154
roid-0.151
Token,
Token ID11
Feature activation+1.47e+00

Pos logit contributions
terness+3.544
thur+3.345
י�+3.201
phia+3.182
chio+3.149
Neg logit contributions
��-2.671
 Belg-2.543
uss-2.428
rol-2.373
roid-2.333
Token lips
Token ID11914
Feature activation+4.58e+00

Pos logit contributions
terness+1.247
thur+1.185
phia+1.129
י�+1.118
chio+1.108
Neg logit contributions
��-1.002
 Belg-0.956
uss-0.930
rol-0.909
roid-0.894
Token,
Token ID11
Feature activation+2.47e+00

Pos logit contributions
terness+3.481
thur+3.283
phia+3.094
י�+3.087
chio+3.036
Neg logit contributions
��-3.501
 Belg-3.373
uss-3.245
rol-3.188
roid-3.140
Token jaw
Token ID19218
Feature activation+9.79e+00

Pos logit contributions
terness+1.883
thur+1.781
phia+1.693
י�+1.671
chio+1.653
Neg logit contributions
��-1.889
 Belg-1.809
uss-1.761
rol-1.727
roid-1.696
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
terness+6.998
thur+6.640
phia+6.270
י�+6.216
chio+6.146
Neg logit contributions
��-7.536
 Belg-7.173
uss-6.728
rol-6.594
roid-6.527
Token l
Token ID300
Feature activation-9.11e-01

Pos logit contributions
terness+1.150
thur+1.092
phia+1.040
י�+1.024
chio+1.015
Neg logit contributions
��-1.082
 Belg-1.034
uss-1.005
rol-0.985
roid-0.966
Tokenaryn
Token ID38621
Feature activation+8.57e+00

Pos logit contributions
��+0.842
 Belg+0.819
uss+0.813
rol+0.798
roid+0.786
Neg logit contributions
terness-0.550
thur-0.509
phia-0.474
י�-0.464
renheit-0.463
Tokenx
Token ID87
Feature activation+1.75e+00

Pos logit contributions
terness+4.227
thur+4.073
chio+3.760
phia+3.701
י�+3.513
Neg logit contributions
��-8.696
 Belg-8.395
uss-8.067
rol-7.939
roid-7.913
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
terness+1.573
thur+1.498
phia+1.431
י�+1.420
chio+1.408
Neg logit contributions
��-1.109
 Belg-1.058
uss-1.023
rol-0.998
roid-0.977
Token1080
Token ID24045
Feature activation-3.43e+00

Pos logit contributions
terness+2.447
thur+2.314
phia+2.174
י�+2.150
chio+2.125
Neg logit contributions
��-3.210
 Belg-3.071
uss-3.008
rol-2.962
roid-2.904
Token ships
Token ID7937
Feature activation-2.05e+00

Pos logit contributions
��+2.225
 Belg+2.168
uss+2.111
rol+2.060
roid+2.046
Neg logit contributions
terness-2.991
thur-2.832
phia-2.676
י�-2.651
renheit-2.638
Token with
Token ID351
Feature activation-1.07e+00

Pos logit contributions
��+1.339
 Belg+1.317
uss+1.276
rol+1.246
roid+1.222
Neg logit contributions
terness-1.781
thur-1.696
phia-1.609
י�-1.589
renheit-1.580
Token 25
Token ID1679
Feature activation-1.99e+00

Pos logit contributions
��+0.715
 Belg+0.700
uss+0.676
rol+0.662
roid+0.646
Neg logit contributions
terness-0.914
thur-0.869
phia-0.821
י�-0.812
renheit-0.805
Token60
Token ID1899
Feature activation+3.29e+00

Pos logit contributions
��+1.330
 Belg+1.285
uss+1.246
rol+1.214
roid+1.187
Neg logit contributions
terness-1.709
thur-1.637
phia-1.559
י�-1.519
chio-1.516
Token CU
Token ID29369
Feature activation+9.78e+00

Pos logit contributions
terness+2.313
thur+2.167
phia+2.064
י�+2.027
renheit+2.008
Neg logit contributions
��-2.717
 Belg-2.605
uss-2.564
rol-2.510
roid-2.470
TokenDA
Token ID5631
Feature activation-2.30e+00

Pos logit contributions
terness+2.615
thur+2.277
TER+1.985
phia+1.904
chio+1.890
Neg logit contributions
��-12.170
 Belg-11.655
uss-11.221
roid-11.128
rol-11.095
Token cores
Token ID21758
Feature activation-8.62e-01

Pos logit contributions
��+1.211
 Belg+1.153
uss+1.118
rol+1.086
roid+1.055
Neg logit contributions
terness-2.300
thur-2.205
phia-2.117
י�-2.083
chio-2.077
Token and
Token ID290
Feature activation-4.54e-01

Pos logit contributions
��+0.605
 Belg+0.584
uss+0.569
rol+0.556
roid+0.546
Neg logit contributions
terness-0.715
thur-0.679
phia-0.645
י�-0.634
chio-0.631
Token 20
Token ID1160
Feature activation+4.71e-01

Pos logit contributions
��+0.324
 Belg+0.314
uss+0.306
rol+0.298
roid+0.293
Neg logit contributions
terness-0.371
thur-0.352
phia-0.334
י�-0.329
chio-0.326
Token SM
Token ID9447
Feature activation+3.97e+00

Pos logit contributions
terness+0.367
thur+0.347
phia+0.330
י�+0.325
chio+0.322
Neg logit contributions
��-0.355
 Belg-0.341
uss-0.333
rol-0.326
roid-0.321
Tokense
Token ID325
Feature activation-1.07e+00

Pos logit contributions
��+1.165
uss+1.128
 Belg+1.118
rol+1.105
roid+1.086
Neg logit contributions
terness-1.138
thur-1.079
phia-1.023
י�-1.016
renheit-0.995
Token,
Token ID11
Feature activation+1.39e+00

Pos logit contributions
��+0.800
 Belg+0.772
uss+0.754
rol+0.739
roid+0.725
Neg logit contributions
terness-0.840
thur-0.795
phia-0.755
י�-0.745
chio-0.737
Token M
Token ID337
Feature activation-6.88e-01

Pos logit contributions
terness+1.279
thur+1.223
phia+1.172
י�+1.160
chio+1.153
Neg logit contributions
��-0.851
 Belg-0.795
uss-0.777
rol-0.756
roid-0.741
Token.,
Token ID1539
Feature activation-1.55e+00

Pos logit contributions
��+0.513
 Belg+0.493
uss+0.481
rol+0.472
roid+0.463
Neg logit contributions
terness-0.541
thur-0.513
phia-0.487
י�-0.479
chio-0.476
Token Sch
Token ID3059
Feature activation+3.08e+00

Pos logit contributions
��+1.046
 Belg+1.025
uss+0.984
rol+0.965
roid+0.940
Neg logit contributions
terness-1.331
thur-1.265
phia-1.201
י�-1.180
renheit-1.177
Tokenol
Token ID349
Feature activation+9.74e+00

Pos logit contributions
terness+2.525
thur+2.429
phia+2.288
chio+2.260
renheit+2.241
Neg logit contributions
��-2.202
 Belg-2.089
uss-1.976
rol-1.947
roid-1.917
Tokente
Token ID660
Feature activation+5.23e+00

Pos logit contributions
terness+4.724
thur+4.328
phia+4.044
chio+3.979
mie+3.867
Neg logit contributions
��-9.976
 Belg-9.415
uss-8.874
rol-8.792
 heartbeat-8.748
Token,
Token ID11
Feature activation+3.90e+00

Pos logit contributions
terness+3.607
thur+3.478
phia+3.285
chio+3.259
י�+3.236
Neg logit contributions
��-4.394
 Belg-4.072
uss-3.942
rol-3.831
roid-3.802
Token R
Token ID371
Feature activation+1.56e+00

Pos logit contributions
terness+3.299
thur+3.135
phia+2.999
י�+2.987
chio+2.967
Neg logit contributions
��-2.653
 Belg-2.500
uss-2.429
rol-2.329
roid-2.298
Token.,
Token ID1539
Feature activation-2.30e+00

Pos logit contributions
terness+1.208
thur+1.146
phia+1.089
י�+1.073
chio+1.063
Neg logit contributions
��-1.168
 Belg-1.125
uss-1.083
rol-1.066
roid-1.055
Token Sal
Token ID4849
Feature activation+7.38e+00

Pos logit contributions
��+1.529
 Belg+1.512
uss+1.446
rol+1.419
roid+1.375
Neg logit contributions
terness-1.987
thur-1.886
phia-1.792
י�-1.759
renheit-1.759
Token the
Token ID262
Feature activation+4.45e-01

Pos logit contributions
��+0.226
 Belg+0.223
uss+0.215
rol+0.211
roid+0.205
Neg logit contributions
terness-0.244
thur-0.231
phia-0.217
renheit-0.214
י�-0.214
Token University
Token ID2059
Feature activation-1.94e+00

Pos logit contributions
terness+0.340
thur+0.321
phia+0.303
י�+0.298
chio+0.296
Neg logit contributions
��-0.341
 Belg-0.332
uss-0.323
rol-0.316
roid-0.310
Token of
Token ID286
Feature activation+1.06e-01

Pos logit contributions
 Belg+1.318
��+1.291
uss+1.268
rol+1.252
roid+1.211
Neg logit contributions
terness-1.640
thur-1.525
phia-1.469
renheit-1.445
י�-1.433
Token California
Token ID3442
Feature activation-7.34e-01

Pos logit contributions
terness+0.077
thur+0.073
phia+0.068
י�+0.067
renheit+0.067
Neg logit contributions
��-0.085
 Belg-0.083
uss-0.080
rol-0.079
roid-0.078
Token,
Token ID11
Feature activation-3.70e-01

Pos logit contributions
��+0.527
 Belg+0.517
uss+0.506
rol+0.497
roid+0.483
Neg logit contributions
terness-0.592
thur-0.558
phia-0.530
י�-0.521
renheit-0.518
Token Santa
Token ID8909
Feature activation+9.73e+00

Pos logit contributions
��+0.315
 Belg+0.303
uss+0.297
rol+0.291
roid+0.288
Neg logit contributions
terness-0.253
thur-0.238
phia-0.224
י�-0.220
chio-0.218
Token Barbara
Token ID16685
Feature activation+1.81e+00

Pos logit contributions
terness+4.695
thur+4.661
phia+4.243
chio+4.073
TER+4.067
Neg logit contributions
��-9.895
roid-8.917
uss-8.914
 Belg-8.887
rol-8.677
Token,
Token ID11
Feature activation+5.64e-01

Pos logit contributions
terness+1.423
thur+1.357
phia+1.289
י�+1.271
chio+1.261
Neg logit contributions
��-1.348
 Belg-1.287
uss-1.247
rol-1.221
roid-1.205
Token and
Token ID290
Feature activation-1.33e-01

Pos logit contributions
terness+0.448
thur+0.425
phia+0.404
י�+0.398
chio+0.395
Neg logit contributions
��-0.416
 Belg-0.399
uss-0.388
rol-0.381
roid-0.374
Token an
Token ID281
Feature activation+1.35e+00

Pos logit contributions
��+0.090
 Belg+0.087
uss+0.084
rol+0.083
roid+0.081
Neg logit contributions
terness-0.113
thur-0.107
phia-0.102
י�-0.101
renheit-0.100
Token organizer
Token ID26311
Feature activation+4.25e+00

Pos logit contributions
terness+1.271
thur+1.215
phia+1.165
י�+1.151
chio+1.143
Neg logit contributions
��-0.797
 Belg-0.756
uss-0.731
rol-0.712
roid-0.697
Tokenol
Token ID349
Feature activation+6.67e+00

Pos logit contributions
terness+1.609
thur+1.526
phia+1.451
י�+1.429
chio+1.419
Neg logit contributions
��-1.465
 Belg-1.405
uss-1.368
rol-1.339
roid-1.316
Token can
Token ID460
Feature activation+3.29e+00

Pos logit contributions
terness+5.254
thur+4.970
phia+4.800
י�+4.677
chio+4.664
Neg logit contributions
��-4.971
 Belg-4.581
uss-4.386
rol-4.276
roid-4.258
Token be
Token ID307
Feature activation+1.32e+00

Pos logit contributions
terness+2.717
thur+2.589
phia+2.458
י�+2.436
chio+2.416
Neg logit contributions
��-2.323
 Belg-2.219
uss-2.141
rol-2.095
roid-2.060
Token a
Token ID257
Feature activation+2.34e+00

Pos logit contributions
terness+1.124
thur+1.069
phia+1.021
י�+1.005
chio+0.999
Neg logit contributions
��-0.890
 Belg-0.856
uss-0.833
rol-0.815
roid-0.798
Token daunting
Token ID30496
Feature activation+2.23e+00

Pos logit contributions
terness+2.017
thur+1.924
phia+1.834
י�+1.814
chio+1.801
Neg logit contributions
��-1.572
 Belg-1.494
uss-1.450
rol-1.413
roid-1.388
Token mouth
Token ID5422
Feature activation+9.65e+00

Pos logit contributions
terness+2.070
thur+1.981
phia+1.895
י�+1.875
chio+1.863
Neg logit contributions
��-1.356
 Belg-1.276
uss-1.237
rol-1.206
roid-1.180
Tokenful
Token ID913
Feature activation+6.56e+00

Pos logit contributions
terness+6.653
thur+6.383
י�+5.939
mie+5.790
TER+5.741
Neg logit contributions
��-7.753
 Belg-7.314
roid-6.748
uss-6.724
rol-6.640
Token,
Token ID11
Feature activation+1.37e+00

Pos logit contributions
terness+5.114
thur+4.811
י�+4.587
phia+4.533
chio+4.509
Neg logit contributions
��-4.883
 Belg-4.569
uss-4.371
rol-4.265
roid-4.258
Token in
Token ID287
Feature activation+1.56e+00

Pos logit contributions
terness+1.191
thur+1.133
phia+1.082
י�+1.067
chio+1.060
Neg logit contributions
��-0.913
 Belg-0.874
uss-0.850
rol-0.830
roid-0.814
Token more
Token ID517
Feature activation+1.37e+00

Pos logit contributions
terness+1.368
thur+1.304
phia+1.245
י�+1.228
chio+1.220
Neg logit contributions
��-1.017
 Belg-0.970
uss-0.942
rol-0.921
roid-0.903
Token ways
Token ID2842
Feature activation+1.75e+00

Pos logit contributions
terness+1.380
thur+1.323
phia+1.273
י�+1.257
chio+1.250
Neg logit contributions
��-0.713
 Belg-0.676
uss-0.651
rol-0.633
roid-0.615
Token.
Token ID13
Feature activation+9.77e-01

Pos logit contributions
��+1.474
 Belg+1.441
uss+1.414
rol+1.374
roid+1.346
Neg logit contributions
terness-1.941
thur-1.824
phia-1.742
י�-1.720
chio-1.712
Token<|endoftext|>
Token ID50256
Feature activation+1.48e+00

Pos logit contributions
terness+0.811
thur+0.769
phia+0.733
י�+0.720
chio+0.717
Neg logit contributions
��-0.684
 Belg-0.662
uss-0.643
rol-0.629
roid-0.617
TokenB
Token ID33
Feature activation+1.79e-01

Pos logit contributions
terness+1.068
thur+1.007
phia+0.952
י�+0.936
chio+0.928
Neg logit contributions
��-1.196
 Belg-1.153
uss-1.126
rol-1.105
roid-1.087
Tokenrock
Token ID10823
Feature activation+1.05e+00

Pos logit contributions
terness+0.146
thur+0.138
phia+0.132
י�+0.130
chio+0.129
Neg logit contributions
��-0.129
 Belg-0.123
uss-0.120
rol-0.117
roid-0.115
Token Les
Token ID11732
Feature activation+2.26e+00

Pos logit contributions
terness+0.854
thur+0.810
phia+0.770
י�+0.759
chio+0.754
Neg logit contributions
��-0.760
 Belg-0.731
uss-0.712
rol-0.698
roid-0.685
Tokennar
Token ID23955
Feature activation+9.54e+00

Pos logit contributions
terness+1.355
thur+1.260
phia+1.181
י�+1.161
renheit+1.155
Neg logit contributions
��-2.093
 Belg-2.043
uss-2.012
rol-1.982
roid-1.945
Token has
Token ID468
Feature activation+1.57e+00

Pos logit contributions
terness+7.239
thur+6.977
chio+6.618
phia+6.397
TER+6.363
Neg logit contributions
��-6.894
 Belg-6.268
rol-6.025
roid-5.936
uss-5.878
Token been
Token ID587
Feature activation-1.23e+00

Pos logit contributions
terness+1.303
thur+1.243
phia+1.179
י�+1.164
chio+1.160
Neg logit contributions
��-1.097
 Belg-1.040
uss-1.012
rol-0.992
roid-0.973
Token flagged
Token ID34060
Feature activation-1.98e+00

Pos logit contributions
��+0.753
 Belg+0.727
uss+0.707
rol+0.689
roid+0.673
Neg logit contributions
terness-1.125
thur-1.072
phia-1.028
י�-1.013
renheit-1.010
Token by
Token ID416
Feature activation-2.52e+00

Pos logit contributions
��+1.282
 Belg+1.241
uss+1.212
rol+1.189
roid+1.158
Neg logit contributions
terness-1.738
thur-1.642
phia-1.582
י�-1.555
renheit-1.543
Token the
Token ID262
Feature activation-8.10e-01

Pos logit contributions
��+1.735
 Belg+1.710
uss+1.669
rol+1.621
roid+1.569
Neg logit contributions
terness-2.118
thur-2.017
phia-1.905
renheit-1.892
י�-1.871
Token surgery
Token ID8185
Feature activation+2.61e+00

Pos logit contributions
��+0.827
 Belg+0.798
uss+0.777
rol+0.760
roid+0.744
Neg logit contributions
terness-1.021
thur-0.968
phia-0.924
י�-0.909
renheit-0.904
Token after
Token ID706
Feature activation-2.95e+00

Pos logit contributions
terness+2.184
thur+2.092
phia+1.988
י�+1.967
chio+1.949
Neg logit contributions
��-1.815
 Belg-1.707
uss-1.658
rol-1.621
roid-1.593
Token suffering
Token ID7195
Feature activation+4.55e+00

Pos logit contributions
��+1.635
 Belg+1.629
uss+1.575
rol+1.533
roid+1.496
Neg logit contributions
terness-2.828
thur-2.691
phia-2.590
renheit-2.561
י�-2.554
Token a
Token ID257
Feature activation+1.30e+00

Pos logit contributions
terness+3.445
thur+3.335
phia+3.157
י�+3.133
chio+3.080
Neg logit contributions
��-3.477
 Belg-3.236
uss-3.139
rol-3.063
roid-2.994
Token fractured
Token ID34051
Feature activation+2.52e+00

Pos logit contributions
terness+1.126
thur+1.073
phia+1.023
י�+1.011
chio+1.004
Neg logit contributions
��-0.868
 Belg-0.828
uss-0.804
rol-0.785
roid-0.770
Token collar
Token ID19908
Feature activation+9.50e+00

Pos logit contributions
terness+2.019
thur+1.922
phia+1.828
י�+1.812
chio+1.800
Neg logit contributions
��-1.830
 Belg-1.738
uss-1.690
rol-1.660
roid-1.624
Token bone
Token ID9970
Feature activation+2.67e-01

Pos logit contributions
terness+1.552
thur+1.430
phia+1.299
chio+1.275
י�+1.172
Neg logit contributions
��-12.404
 Belg-11.767
uss-11.343
rol-11.327
roid-11.069
Token in
Token ID287
Feature activation+3.85e-01

Pos logit contributions
terness+0.232
thur+0.220
phia+0.211
י�+0.208
renheit+0.207
Neg logit contributions
��-0.176
 Belg-0.169
uss-0.165
rol-0.161
roid-0.158
Token Foot
Token ID7870
Feature activation+2.52e-01

Pos logit contributions
terness+0.338
thur+0.323
phia+0.309
י�+0.304
chio+0.303
Neg logit contributions
��-0.252
 Belg-0.240
uss-0.232
rol-0.228
roid-0.223
Tokensc
Token ID1416
Feature activation-1.80e+00

Pos logit contributions
terness+0.204
thur+0.193
phia+0.184
י�+0.182
chio+0.180
Neg logit contributions
��-0.181
 Belg-0.174
uss-0.170
rol-0.166
roid-0.163
Tokenray
Token ID2433
Feature activation+4.46e+00

Pos logit contributions
��+1.087
 Belg+1.062
uss+1.046
rol+1.021
roid+0.992
Neg logit contributions
terness-1.645
thur-1.563
phia-1.495
י�-1.491
renheit-1.468
Token:
Token ID25
Feature activation-2.34e-01

Pos logit contributions
 Belg+2.051
uss+1.987
rol+1.938
��+1.917
roid+1.856
Neg logit contributions
terness-3.503
thur-3.285
phia-3.202
renheit-3.124
chio-3.061
Token New
Token ID968
Feature activation-3.51e+00

Pos logit contributions
��+0.166
 Belg+0.161
uss+0.156
rol+0.153
roid+0.150
Neg logit contributions
terness-0.192
thur-0.182
phia-0.173
י�-0.170
renheit-0.170
Token Insight
Token ID39917
Feature activation-1.22e+00

Pos logit contributions
��+2.102
 Belg+2.065
uss+1.974
rol+1.929
roid+1.901
Neg logit contributions
terness-3.240
thur-3.054
renheit-2.929
phia-2.921
י�-2.885
Token Into
Token ID20008
Feature activation-5.31e-01

Pos logit contributions
��+0.829
 Belg+0.804
uss+0.780
rol+0.762
roid+0.747
Neg logit contributions
terness-1.027
thur-0.982
phia-0.935
י�-0.921
chio-0.917
Token How
Token ID1374
Feature activation-1.58e+00

Pos logit contributions
��+0.366
 Belg+0.354
uss+0.343
rol+0.336
roid+0.330
Neg logit contributions
terness-0.446
thur-0.424
phia-0.403
י�-0.398
renheit-0.396
Token Bees
Token ID46698
Feature activation-1.20e+01

Pos logit contributions
��+1.070
 Belg+1.039
uss+1.006
rol+0.983
roid+0.965
Neg logit contributions
terness-1.347
thur-1.280
phia-1.218
renheit-1.201
י�-1.201
Token See
Token ID4091
Feature activation-4.75e+00

Pos logit contributions
 Belg+6.888
uss+6.709
��+6.566
rol+6.426
roid+6.201
Neg logit contributions
terness-10.510
thur-10.006
renheit-9.860
phia-9.496
DEN-9.252
Token<|endoftext|>
Token ID50256
Feature activation+1.38e+00

Pos logit contributions
 Belg+3.195
��+3.186
uss+3.087
rol+3.017
roid+2.921
Neg logit contributions
terness-3.972
thur-3.696
phia-3.572
renheit-3.523
י�-3.513
TokenThe
Token ID464
Feature activation-5.08e-01

Pos logit contributions
terness+1.002
thur+0.944
phia+0.893
י�+0.877
chio+0.870
Neg logit contributions
��-1.119
 Belg-1.080
uss-1.055
rol-1.036
roid-1.019
Token fuss
Token ID34297
Feature activation-3.41e+00

Pos logit contributions
��+0.344
 Belg+0.334
uss+0.323
rol+0.316
roid+0.310
Neg logit contributions
terness-0.434
thur-0.412
phia-0.393
י�-0.387
renheit-0.385
Token is
Token ID318
Feature activation+1.35e-01

Pos logit contributions
��+2.041
 Belg+1.979
uss+1.929
rol+1.897
roid+1.867
Neg logit contributions
terness-3.102
thur-2.987
phia-2.835
י�-2.827
renheit-2.802
Token last
Token ID938
Feature activation-4.30e-03

Pos logit contributions
��+0.925
 Belg+0.902
uss+0.887
rol+0.871
roid+0.848
Neg logit contributions
terness-1.087
thur-1.030
phia-0.982
י�-0.965
renheit-0.961
Token one
Token ID530
Feature activation+2.03e+00

Pos logit contributions
��+0.003
 Belg+0.003
uss+0.003
rol+0.002
roid+0.002
Neg logit contributions
terness-0.004
thur-0.004
phia-0.004
י�-0.004
renheit-0.003
Token is
Token ID318
Feature activation+7.95e-01

Pos logit contributions
terness+1.716
thur+1.632
phia+1.553
י�+1.538
chio+1.522
Neg logit contributions
��-1.410
 Belg-1.335
uss-1.299
rol-1.270
roid-1.247
Token standing
Token ID5055
Feature activation-1.76e+00

Pos logit contributions
terness+0.686
thur+0.651
phia+0.622
י�+0.612
chio+0.608
Neg logit contributions
��-0.530
 Belg-0.513
uss-0.498
rol-0.486
roid-0.476
Token against
Token ID1028
Feature activation-1.26e+00

Pos logit contributions
��+1.052
 Belg+1.049
uss+1.008
rol+0.990
roid+0.953
Neg logit contributions
terness-1.611
thur-1.521
phia-1.467
renheit-1.442
י�-1.442
Token Boris
Token ID25026
Feature activation-1.19e+01

Pos logit contributions
��+0.888
 Belg+0.871
uss+0.842
rol+0.824
roid+0.805
Neg logit contributions
terness-1.040
thur-0.979
phia-0.939
י�-0.919
chio-0.917
Token).
Token ID737
Feature activation-1.39e+00

Pos logit contributions
 Belg+5.956
uss+5.804
rol+5.717
��+5.382
 fitt+5.029
Neg logit contributions
terness-11.391
thur-10.874
renheit-10.584
phia-10.496
י�-10.281
Token
Token ID198
Feature activation+1.25e+00

Pos logit contributions
��+1.037
 Belg+1.026
uss+0.994
rol+0.976
roid+0.948
Neg logit contributions
terness-1.083
thur-1.018
phia-0.966
renheit-0.944
chio-0.944
Token
Token ID198
Feature activation+4.01e-02

Pos logit contributions
terness+0.900
thur+0.848
phia+0.801
י�+0.787
chio+0.780
Neg logit contributions
��-1.013
 Belg-0.979
uss-0.957
rol-0.940
roid-0.924
TokenBut
Token ID1537
Feature activation+3.22e+00

Pos logit contributions
terness+0.029
thur+0.027
phia+0.025
renheit+0.024
י�+0.024
Neg logit contributions
��-0.033
 Belg-0.032
uss-0.032
rol-0.031
roid-0.030
Token that
Token ID326
Feature activation+4.94e-02

Pos logit contributions
terness+2.621
thur+2.497
phia+2.376
י�+2.332
chio+2.318
Neg logit contributions
��-2.327
 Belg-2.175
uss-2.123
rol-2.073
roid-2.056
Token post
Token ID1281
Feature activation-2.63e+00

Pos logit contributions
��+0.294
 Belg+0.284
uss+0.274
rol+0.268
roid+0.262
Neg logit contributions
terness-0.403
thur-0.381
phia-0.363
י�-0.360
renheit-0.359
Token G
Token ID402
Feature activation-2.43e+00

Pos logit contributions
��+1.756
 Belg+1.709
uss+1.661
rol+1.616
roid+1.590
Neg logit contributions
terness-2.262
thur-2.137
phia-2.042
י�-2.011
renheit-2.011
TokenWAR
Token ID16279
Feature activation-1.82e+00

Pos logit contributions
��+2.143
uss+2.124
 Belg+2.107
rol+2.090
roid+2.067
Neg logit contributions
terness-1.522
thur-1.380
phia-1.336
chio-1.282
renheit-1.279
Token Eternal
Token ID21475
Feature activation-2.51e+00

Pos logit contributions
��+1.130
 Belg+1.088
uss+1.052
rol+1.025
roid+1.007
Neg logit contributions
terness-1.652
thur-1.573
phia-1.505
י�-1.482
renheit-1.481
Token Tour
Token ID9852
Feature activation-3.42e+00

Pos logit contributions
��+1.032
 Belg+0.985
uss+0.942
rol+0.898
roid+0.871
Neg logit contributions
terness-2.794
thur-2.674
phia-2.589
renheit-2.569
י�-2.562
Token Beaut
Token ID13711
Feature activation-1.18e+01

Pos logit contributions
��+2.244
 Belg+2.192
uss+2.134
rol+2.063
roid+2.020
Neg logit contributions
terness-2.972
thur-2.797
phia-2.679
renheit-2.658
י�-2.642
Tokenifully
Token ID17049
Feature activation-2.55e+00

Pos logit contributions
uss+6.399
��+6.271
rol+6.089
 Belg+6.007
roid+5.910
Neg logit contributions
terness-10.338
thur-9.976
phia-9.617
renheit-9.485
י�-9.476
Token Paid
Token ID47355
Feature activation-3.32e+00

Pos logit contributions
��+1.689
 Belg+1.648
uss+1.598
rol+1.559
roid+1.521
Neg logit contributions
terness-2.198
thur-2.091
phia-1.993
renheit-1.960
י�-1.950
Token Hom
Token ID8074
Feature activation+1.86e+00

Pos logit contributions
��+1.999
 Belg+1.954
uss+1.898
rol+1.848
roid+1.807
Neg logit contributions
terness-3.052
thur-2.884
phia-2.779
renheit-2.751
chio-2.731
Tokenage
Token ID496
Feature activation-3.22e-01

Pos logit contributions
terness+1.118
thur+1.042
phia+0.971
י�+0.950
chio+0.941
Neg logit contributions
��-1.731
 Belg-1.677
uss-1.642
rol-1.617
roid-1.594
Token To
Token ID1675
Feature activation+8.20e-01

Pos logit contributions
��+0.216
 Belg+0.207
uss+0.201
rol+0.197
roid+0.193
Neg logit contributions
terness-0.278
thur-0.264
phia-0.252
י�-0.249
chio-0.247
Token former
Token ID1966
Feature activation+6.55e-01

Pos logit contributions
 Belg+2.123
��+2.101
uss+2.049
rol+2.039
roid+1.949
Neg logit contributions
terness-2.784
thur-2.618
renheit-2.506
phia-2.502
chio-2.478
Token India
Token ID3794
Feature activation-4.32e-01

Pos logit contributions
terness+0.556
thur+0.528
phia+0.504
י�+0.497
chio+0.493
Neg logit contributions
��-0.447
 Belg-0.431
uss-0.419
rol-0.410
roid-0.401
Token captain
Token ID10654
Feature activation+9.71e-01

Pos logit contributions
��+0.267
 Belg+0.257
uss+0.250
rol+0.244
roid+0.238
Neg logit contributions
terness-0.394
thur-0.375
phia-0.359
י�-0.355
renheit-0.353
Token,
Token ID11
Feature activation+8.94e-02

Pos logit contributions
terness+0.835
thur+0.795
phia+0.758
י�+0.748
chio+0.743
Neg logit contributions
��-0.652
 Belg-0.626
uss-0.608
rol-0.595
roid-0.583
Token Rahul
Token ID48543
Feature activation-1.58e+00

Pos logit contributions
terness+0.076
thur+0.072
phia+0.069
י�+0.068
chio+0.068
Neg logit contributions
��-0.061
 Belg-0.058
uss-0.057
rol-0.056
roid-0.054
Token D
Token ID360
Feature activation-1.15e+01

Pos logit contributions
��+0.937
 Belg+0.895
uss+0.868
rol+0.846
roid+0.826
Neg logit contributions
terness-1.482
thur-1.414
phia-1.357
י�-1.342
chio-1.331
Tokenrav
Token ID4108
Feature activation-5.48e+00

Pos logit contributions
uss+6.473
rol+6.016
 Belg+5.671
roid+5.467
inson+5.401
Neg logit contributions
terness-10.975
thur-9.938
י�-9.877
phia-9.877
renheit-9.858
Tokenid
Token ID312
Feature activation-1.36e+00

Pos logit contributions
��+2.821
uss+2.799
 Belg+2.687
rol+2.639
roid+2.587
Neg logit contributions
terness-5.453
thur-5.090
phia-5.008
י�-4.976
renheit-4.961
Token who
Token ID508
Feature activation-2.38e+00

Pos logit contributions
��+0.928
 Belg+0.895
uss+0.882
rol+0.868
roid+0.848
Neg logit contributions
terness-1.141
thur-1.081
phia-1.036
י�-1.016
renheit-1.013
Token said
Token ID531
Feature activation-4.48e-01

Pos logit contributions
��+1.485
 Belg+1.464
uss+1.421
rol+1.394
roid+1.361
Neg logit contributions
terness-2.117
thur-1.999
phia-1.919
י�-1.893
renheit-1.892
Token there
Token ID612
Feature activation-2.26e+00

Pos logit contributions
��+0.288
 Belg+0.278
uss+0.269
rol+0.263
roid+0.257
Neg logit contributions
terness-0.397
thur-0.378
phia-0.362
י�-0.357
renheit-0.355
Token she
Token ID673
Feature activation-3.53e+00

Pos logit contributions
terness+1.674
thur+1.591
phia+1.518
י�+1.496
chio+1.489
Neg logit contributions
��-1.454
 Belg-1.360
uss-1.330
rol-1.306
roid-1.283
Token calls
Token ID3848
Feature activation-1.45e+00

Pos logit contributions
 Belg+2.137
uss+2.085
��+2.080
rol+2.002
roid+1.973
Neg logit contributions
terness-3.202
thur-3.018
phia-2.891
renheit-2.873
י�-2.871
Token the
Token ID262
Feature activation-8.48e-01

Pos logit contributions
��+1.040
 Belg+1.007
uss+0.981
rol+0.959
roid+0.944
Neg logit contributions
terness-1.173
thur-1.112
phia-1.058
י�-1.041
renheit-1.034
Token War
Token ID1810
Feature activation+1.19e+00

Pos logit contributions
��+0.604
 Belg+0.588
uss+0.572
rol+0.558
roid+0.549
Neg logit contributions
terness-0.691
thur-0.654
phia-0.622
י�-0.612
renheit-0.609
Token on
Token ID319
Feature activation-2.52e+00

Pos logit contributions
terness+0.995
thur+0.946
phia+0.900
י�+0.886
chio+0.882
Neg logit contributions
��-0.833
 Belg-0.795
uss-0.773
rol-0.757
roid-0.742
Token Women
Token ID6926
Feature activation-1.11e+01

Pos logit contributions
 Belg+1.472
��+1.455
uss+1.411
rol+1.373
roid+1.320
Neg logit contributions
terness-2.341
thur-2.237
phia-2.153
renheit-2.107
י�-2.101
Token in
Token ID287
Feature activation-2.24e+00

Pos logit contributions
 Belg+6.146
uss+6.023
rol+5.957
��+5.817
roid+5.571
Neg logit contributions
terness-9.638
thur-9.316
renheit-8.854
phia-8.847
י�-8.753
Token politics
Token ID4819
Feature activation-4.40e+00

Pos logit contributions
��+1.585
 Belg+1.573
uss+1.521
rol+1.474
roid+1.428
Neg logit contributions
terness-1.812
thur-1.711
phia-1.629
י�-1.603
renheit-1.597
Token.
Token ID13
Feature activation-3.13e-01

Pos logit contributions
 Belg+2.745
��+2.732
uss+2.675
rol+2.583
roid+2.504
Neg logit contributions
terness-3.898
thur-3.668
phia-3.504
renheit-3.478
י�-3.453
Token Hide
Token ID10415
Feature activation+1.39e+00

Pos logit contributions
��+0.285
 Belg+0.280
uss+0.273
rol+0.268
roid+0.264
Neg logit contributions
terness-0.194
thur-0.181
phia-0.169
י�-0.165
renheit-0.163
Token Caption
Token ID11260
Feature activation-3.12e-01

Pos logit contributions
terness+0.901
thur+0.844
phia+0.793
י�+0.779
chio+0.773
Neg logit contributions
��-1.227
 Belg-1.179
uss-1.155
rol-1.136
roid-1.122
TokenWe
Token ID1135
Feature activation+7.97e-01

Pos logit contributions
terness+0.589
thur+0.545
phia+0.508
chio+0.494
י�+0.493
Neg logit contributions
��-0.892
 Belg-0.878
uss-0.861
rol-0.847
roid-0.834
Token don
Token ID836
Feature activation+3.48e-01

Pos logit contributions
terness+0.673
thur+0.638
phia+0.607
י�+0.599
renheit+0.597
Neg logit contributions
��-0.545
 Belg-0.529
uss-0.515
rol-0.503
roid-0.493
Token't
Token ID470
Feature activation+1.82e+00

Pos logit contributions
terness+0.302
thur+0.285
phia+0.273
י�+0.268
renheit+0.267
Neg logit contributions
��-0.230
 Belg-0.224
uss-0.218
rol-0.213
roid-0.209
Token have
Token ID423
Feature activation-1.31e+00

Pos logit contributions
terness+1.460
thur+1.391
phia+1.328
י�+1.307
chio+1.300
Neg logit contributions
��-1.337
 Belg-1.264
uss-1.229
rol-1.209
roid-1.185
Token Q
Token ID1195
Feature activation+1.64e+00

Pos logit contributions
��+0.859
 Belg+0.838
uss+0.810
rol+0.791
roid+0.772
Neg logit contributions
terness-1.149
thur-1.088
phia-1.040
י�-1.023
renheit-1.020
Tokend
Token ID67
Feature activation-1.06e+01

Pos logit contributions
terness+1.234
thur+1.171
phia+1.108
י�+1.090
chio+1.082
Neg logit contributions
��-1.278
 Belg-1.225
uss-1.190
rol-1.170
roid-1.151
Tokenoba
Token ID19981
Feature activation-2.30e+00

Pos logit contributions
uss+8.018
rol+7.937
 Belg+7.890
roid+7.820
��+7.442
Neg logit contributions
terness-7.628
thur-6.606
י�-6.550
renheit-6.540
chio-6.425
Token there
Token ID612
Feature activation-2.73e+00

Pos logit contributions
��+1.508
 Belg+1.495
uss+1.455
rol+1.422
roid+1.384
Neg logit contributions
terness-1.986
thur-1.874
phia-1.775
י�-1.764
renheit-1.757
Token."
Token ID526
Feature activation-1.12e-01

Pos logit contributions
 Belg+1.691
��+1.687
uss+1.641
rol+1.603
roid+1.550
Neg logit contributions
terness-2.437
thur-2.305
phia-2.190
י�-2.164
renheit-2.163
Token
Token ID198
Feature activation+8.45e-01

Pos logit contributions
��+0.089
 Belg+0.086
uss+0.084
rol+0.083
roid+0.081
Neg logit contributions
terness-0.082
thur-0.078
phia-0.074
י�-0.072
chio-0.072
Token
Token ID198
Feature activation+6.00e-03

Pos logit contributions
terness+0.626
thur+0.586
phia+0.555
י�+0.543
renheit+0.540
Neg logit contributions
��-0.667
 Belg-0.652
uss-0.638
rol-0.627
roid-0.615
Token industry
Token ID2831
Feature activation-1.78e+00

Pos logit contributions
terness+0.906
thur+0.863
phia+0.824
י�+0.812
chio+0.807
Neg logit contributions
��-0.747
 Belg-0.710
uss-0.691
rol-0.675
roid-0.664
Token."
Token ID526
Feature activation+4.72e-01

Pos logit contributions
��+1.077
 Belg+1.061
uss+1.028
rol+1.008
roid+0.983
Neg logit contributions
terness-1.622
thur-1.546
phia-1.474
י�-1.453
renheit-1.448
Token
Token ID198
Feature activation+1.59e+00

Pos logit contributions
terness+0.338
thur+0.319
phia+0.301
י�+0.296
chio+0.294
Neg logit contributions
��-0.385
 Belg-0.371
uss-0.362
rol-0.356
roid-0.350
Token
Token ID198
Feature activation+2.96e-01

Pos logit contributions
terness+1.120
thur+1.058
phia+0.999
י�+0.984
chio+0.976
Neg logit contributions
��-1.311
 Belg-1.257
uss-1.228
rol-1.204
roid-1.186
TokenJerry
Token ID43462
Feature activation+5.60e+00

Pos logit contributions
terness+0.222
thur+0.208
phia+0.196
renheit+0.192
י�+0.191
Neg logit contributions
��-0.230
 Belg-0.225
uss-0.221
rol-0.217
roid-0.213
Token Dw
Token ID19113
Feature activation-1.06e+01

Pos logit contributions
terness+4.686
thur+4.479
phia+4.328
chio+4.246
י�+4.232
Neg logit contributions
��-3.778
 Belg-3.496
uss-3.455
rol-3.369
roid-3.314
Tokenor
Token ID273
Feature activation-2.01e+00

Pos logit contributions
uss+5.980
rol+5.697
roid+5.578
inson+5.546
 Belg+5.423
Neg logit contributions
terness-9.582
thur-8.889
י�-8.851
renheit-8.604
phia-8.589
Tokenak
Token ID461
Feature activation-1.39e+00

Pos logit contributions
��+1.457
uss+1.434
 Belg+1.421
rol+1.411
roid+1.353
Neg logit contributions
terness-1.572
thur-1.460
phia-1.413
י�-1.403
renheit-1.374
Token,
Token ID11
Feature activation+1.84e+00

Pos logit contributions
��+0.982
 Belg+0.958
uss+0.952
rol+0.931
roid+0.909
Neg logit contributions
terness-1.130
thur-1.062
phia-1.018
י�-1.006
renheit-0.997
Token head
Token ID1182
Feature activation+4.54e+00

Pos logit contributions
terness+1.466
thur+1.389
phia+1.321
י�+1.303
chio+1.294
Neg logit contributions
��-1.355
 Belg-1.290
uss-1.260
rol-1.232
roid-1.215
Token of
Token ID286
Feature activation+9.44e-01

Pos logit contributions
terness+3.319
thur+3.126
phia+2.971
י�+2.959
chio+2.894
Neg logit contributions
��-3.657
 Belg-3.450
uss-3.351
rol-3.235
roid-3.229
Token Stephen
Token ID7970
Feature activation+2.67e+00

Pos logit contributions
terness+0.859
thur+0.814
phia+0.775
י�+0.763
chio+0.757
Neg logit contributions
��-0.807
 Belg-0.771
uss-0.753
rol-0.738
roid-0.726
Token Am
Token ID1703
Feature activation-5.57e+00

Pos logit contributions
terness+2.154
thur+2.040
phia+1.952
chio+1.916
י�+1.906
Neg logit contributions
��-1.930
 Belg-1.826
uss-1.764
rol-1.742
roid-1.727
Tokenell
Token ID695
Feature activation+7.65e-01

Pos logit contributions
uss+4.317
rol+4.129
��+4.121
 Belg+4.066
roid+4.049
Neg logit contributions
terness-4.258
thur-3.931
phia-3.732
renheit-3.731
DEN-3.613
Token and
Token ID290
Feature activation+4.84e-01

Pos logit contributions
terness+0.588
thur+0.556
phia+0.527
י�+0.519
chio+0.516
Neg logit contributions
��-0.584
 Belg-0.562
uss-0.548
rol-0.537
roid-0.528
Token Robert
Token ID5199
Feature activation-1.08e-01

Pos logit contributions
terness+0.388
thur+0.368
phia+0.351
י�+0.345
chio+0.343
Neg logit contributions
��-0.354
 Belg-0.339
uss-0.331
rol-0.324
roid-0.318
Token Patt
Token ID24682
Feature activation-1.04e+01

Pos logit contributions
��+0.072
 Belg+0.069
uss+0.067
rol+0.065
roid+0.064
Neg logit contributions
terness-0.093
thur-0.089
phia-0.085
י�-0.084
chio-0.083
Tokeninson
Token ID7899
Feature activation+3.90e-01

Pos logit contributions
inson+0.871
uss+0.552
rol+0.375
roid-0.022
 Belg-0.161
Neg logit contributions
terness-15.152
thur-14.331
י�-14.285
chio-14.187
phia-14.143
Token.
Token ID13
Feature activation+3.42e-01

Pos logit contributions
terness+0.324
thur+0.307
phia+0.293
י�+0.288
chio+0.286
Neg logit contributions
��-0.274
 Belg-0.263
uss-0.256
rol-0.250
roid-0.246
Token
Token ID198
Feature activation+1.97e+00

Pos logit contributions
terness+0.267
thur+0.253
phia+0.240
י�+0.235
renheit+0.234
Neg logit contributions
��-0.255
 Belg-0.249
uss-0.242
rol-0.238
roid-0.233
Token
Token ID198
Feature activation+9.14e-01

Pos logit contributions
terness+1.342
thur+1.276
phia+1.202
י�+1.193
chio+1.178
Neg logit contributions
��-1.676
 Belg-1.584
uss-1.549
rol-1.518
roid-1.497
TokenWhile
Token ID3633
Feature activation-2.81e+00

Pos logit contributions
terness+0.679
thur+0.641
phia+0.607
י�+0.597
chio+0.592
Neg logit contributions
��-0.722
 Belg-0.695
uss-0.679
rol-0.666
roid-0.655
Tokenbound
Token ID7784
Feature activation-1.98e+00

Pos logit contributions
terness+1.756
thur+1.666
phia+1.576
י�+1.554
chio+1.539
Neg logit contributions
��-1.777
 Belg-1.700
uss-1.657
rol-1.619
roid-1.601
Token on
Token ID319
Feature activation-2.81e+00

Pos logit contributions
 Belg+1.264
��+1.264
uss+1.234
rol+1.208
roid+1.152
Neg logit contributions
terness-1.737
thur-1.634
phia-1.567
י�-1.544
renheit-1.533
Token East
Token ID3687
Feature activation-2.07e+00

Pos logit contributions
��+2.506
 Belg+2.479
uss+2.419
rol+2.396
roid+2.313
Neg logit contributions
terness-1.761
thur-1.620
phia-1.513
י�-1.501
chio-1.487
Token 16
Token ID1467
Feature activation-5.71e+00

Pos logit contributions
��+1.571
 Belg+1.566
uss+1.521
rol+1.505
roid+1.448
Neg logit contributions
terness-1.566
thur-1.459
phia-1.385
י�-1.377
chio-1.370
Tokenth
Token ID400
Feature activation-7.43e+00

Pos logit contributions
 Belg+3.827
uss+3.782
��+3.748
rol+3.714
roid+3.472
Neg logit contributions
terness-4.677
thur-4.330
phia-4.285
chio-4.192
י�-4.171
Token Avenue
Token ID8878
Feature activation-1.02e+01

Pos logit contributions
 Belg+4.441
��+4.311
uss+4.274
rol+4.227
roid+3.981
Neg logit contributions
terness-6.670
thur-6.216
phia-5.991
י�-5.939
chio-5.890
Token.
Token ID13
Feature activation-5.16e-01

Pos logit contributions
 Belg+5.974
uss+5.896
rol+5.738
��+5.357
roid+5.354
Neg logit contributions
terness-9.065
thur-8.301
phia-8.175
renheit-7.968
י�-7.893
Token
Token ID198
Feature activation+6.12e-01

Pos logit contributions
��+0.370
 Belg+0.368
uss+0.356
rol+0.350
roid+0.339
Neg logit contributions
terness-0.414
thur-0.392
phia-0.373
י�-0.365
chio-0.364
Token
Token ID198
Feature activation-5.37e-01

Pos logit contributions
terness+0.450
thur+0.422
phia+0.399
י�+0.391
renheit+0.388
Neg logit contributions
��-0.486
 Belg-0.474
uss-0.464
rol-0.456
roid-0.447
TokenThe
Token ID464
Feature activation-1.54e+00

Pos logit contributions
��+0.405
 Belg+0.396
uss+0.391
rol+0.384
roid+0.375
Neg logit contributions
terness-0.414
thur-0.388
phia-0.369
renheit-0.360
chio-0.359
Token woman
Token ID2415
Feature activation-4.20e+00

Pos logit contributions
��+0.930
 Belg+0.905
uss+0.878
rol+0.859
roid+0.832
Neg logit contributions
terness-1.416
thur-1.346
phia-1.291
י�-1.269
renheit-1.267
Token Trophy
Token ID25640
Feature activation+6.05e-01

Pos logit contributions
terness+2.039
thur+1.957
phia+1.860
י�+1.823
chio+1.818
Neg logit contributions
��-1.997
 Belg-1.896
uss-1.844
rol-1.809
roid-1.784
Token and
Token ID290
Feature activation-4.38e-01

Pos logit contributions
terness+0.503
thur+0.480
phia+0.457
י�+0.451
chio+0.449
Neg logit contributions
��-0.425
 Belg-0.405
uss-0.392
rol-0.383
roid-0.379
Token Way
Token ID6378
Feature activation-1.79e+00

Pos logit contributions
��+0.298
 Belg+0.288
uss+0.280
rol+0.274
roid+0.268
Neg logit contributions
terness-0.372
thur-0.353
phia-0.336
י�-0.331
renheit-0.330
Tokenman
Token ID805
Feature activation-6.27e-01

Pos logit contributions
��+1.313
 Belg+1.289
uss+1.276
rol+1.251
roid+1.217
Neg logit contributions
terness-1.401
thur-1.301
י�-1.237
phia-1.235
renheit-1.223
Token T
Token ID309
Feature activation-7.43e-02

Pos logit contributions
��+0.400
 Belg+0.384
uss+0.373
rol+0.365
roid+0.356
Neg logit contributions
terness-0.561
thur-0.532
phia-0.508
י�-0.502
renheit-0.501
Tokenisd
Token ID9409
Feature activation-1.02e+01

Pos logit contributions
��+0.051
 Belg+0.050
uss+0.049
rol+0.048
roid+0.047
Neg logit contributions
terness-0.062
thur-0.059
phia-0.056
י�-0.055
renheit-0.055
Tokenale
Token ID1000
Feature activation+8.90e-01

Pos logit contributions
rol+4.738
uss+4.629
roid+4.356
��+4.304
 Belg+4.135
Neg logit contributions
terness-10.347
thur-9.994
phia-9.607
renheit-9.551
י�-9.490
Token Award
Token ID11289
Feature activation+9.18e-01

Pos logit contributions
terness+0.731
thur+0.695
phia+0.662
י�+0.651
chio+0.647
Neg logit contributions
��-0.632
 Belg-0.606
uss-0.590
rol-0.577
roid-0.567
Token Watch
Token ID6305
Feature activation-1.29e+00

Pos logit contributions
terness+0.783
thur+0.746
phia+0.712
י�+0.702
chio+0.699
Neg logit contributions
��-0.624
 Belg-0.595
uss-0.576
rol-0.562
roid-0.555
Token Lists
Token ID44968
Feature activation-2.42e+00

Pos logit contributions
��+0.621
 Belg+0.592
uss+0.579
rol+0.567
roid+0.543
Neg logit contributions
terness-1.343
thur-1.280
phia-1.238
י�-1.220
renheit-1.215
Token.[
Token ID3693
Feature activation-3.77e+00

Pos logit contributions
��+1.423
 Belg+1.367
uss+1.344
rol+1.318
roid+1.268
Neg logit contributions
terness-2.261
thur-2.153
phia-2.063
י�-2.041
renheit-2.031
Token officer
Token ID3818
Feature activation+7.38e-01

Pos logit contributions
��+0.244
 Belg+0.238
uss+0.232
rol+0.228
roid+0.224
Neg logit contributions
terness-0.214
thur-0.201
phia-0.189
י�-0.186
renheit-0.185
Token,
Token ID11
Feature activation+1.31e+00

Pos logit contributions
terness+0.616
thur+0.584
phia+0.556
י�+0.548
chio+0.544
Neg logit contributions
��-0.515
 Belg-0.496
uss-0.483
rol-0.473
roid-0.463
Token Ak
Token ID9084
Feature activation-1.39e+00

Pos logit contributions
terness+1.042
thur+0.990
phia+0.944
י�+0.927
chio+0.920
Neg logit contributions
��-0.965
 Belg-0.919
uss-0.897
rol-0.877
roid-0.866
Tokeniny
Token ID3541
Feature activation-1.41e+00

Pos logit contributions
��+1.013
 Belg+0.994
uss+0.989
rol+0.970
roid+0.940
Neg logit contributions
terness-1.079
thur-1.012
phia-0.977
י�-0.970
chio-0.952
Tokenemi
Token ID43967
Feature activation+1.82e+00

Pos logit contributions
��+1.131
 Belg+1.114
uss+1.095
rol+1.069
roid+1.059
Neg logit contributions
terness-1.003
thur-0.937
phia-0.887
י�-0.885
renheit-0.875
Token Boris
Token ID25026
Feature activation-1.02e+01

Pos logit contributions
terness+1.584
thur+1.510
phia+1.444
י�+1.424
chio+1.418
Neg logit contributions
��-1.203
 Belg-1.137
uss-1.111
rol-1.082
roid-1.063
Tokenade
Token ID671
Feature activation-4.75e+00

Pos logit contributions
uss+7.216
rol+7.057
 Belg+7.024
��+6.954
roid+6.691
Neg logit contributions
terness-7.475
thur-6.995
י�-6.779
phia-6.751
renheit-6.688
Token,
Token ID11
Feature activation+5.97e-02

Pos logit contributions
��+3.069
 Belg+3.035
uss+2.996
rol+2.959
roid+2.858
Neg logit contributions
terness-4.044
thur-3.802
phia-3.657
י�-3.637
renheit-3.587
Token had
Token ID550
Feature activation-2.19e-03

Pos logit contributions
terness+0.051
thur+0.049
phia+0.046
י�+0.046
chio+0.045
Neg logit contributions
��-0.040
 Belg-0.039
uss-0.038
rol-0.037
roid-0.036
Token only
Token ID691
Feature activation-2.02e+00

Pos logit contributions
��+0.002
 Belg+0.002
uss+0.001
rol+0.001
roid+0.001
Neg logit contributions
terness-0.002
thur-0.002
phia-0.002
י�-0.002
chio-0.002
Token been
Token ID587
Feature activation-2.46e+00

Pos logit contributions
��+1.370
 Belg+1.353
uss+1.304
rol+1.285
roid+1.254
Neg logit contributions
terness-1.705
thur-1.608
phia-1.532
י�-1.507
renheit-1.506
Token,
Token ID11
Feature activation+9.95e-01

Pos logit contributions
terness+3.451
thur+3.242
phia+3.095
י�+3.079
chio+3.014
Neg logit contributions
��-3.213
 Belg-3.019
uss-2.924
rol-2.870
roid-2.833
Token that
Token ID326
Feature activation-7.46e-02

Pos logit contributions
terness+0.885
thur+0.842
phia+0.805
י�+0.795
chio+0.789
Neg logit contributions
��-0.642
 Belg-0.609
uss-0.591
rol-0.578
roid-0.568
Token will
Token ID481
Feature activation+2.50e+00

Pos logit contributions
��+0.050
 Belg+0.048
uss+0.046
rol+0.045
roid+0.044
Neg logit contributions
terness-0.065
thur-0.062
phia-0.059
י�-0.058
chio-0.058
Token no
Token ID645
Feature activation+7.38e-01

Pos logit contributions
terness+2.137
thur+2.036
phia+1.940
י�+1.917
chio+1.902
Neg logit contributions
��-1.698
 Belg-1.611
uss-1.564
rol-1.524
roid-1.499
Token-
Token ID12
Feature activation-5.18e+00

Pos logit contributions
terness+0.691
thur+0.661
phia+0.631
י�+0.626
chio+0.621
Neg logit contributions
��-0.442
 Belg-0.417
uss-0.403
rol-0.394
roid-0.387
Tokend
Token ID67
Feature activation-1.02e+01

Pos logit contributions
��+3.601
uss+3.568
 Belg+3.563
rol+3.411
roid+3.326
Neg logit contributions
terness-4.155
thur-3.855
phia-3.744
renheit-3.718
י�-3.677
Tokenoubt
Token ID47675
Feature activation-1.89e-01

Pos logit contributions
uss+5.069
 Belg+4.719
roid+4.645
rol+4.637
��+4.386
Neg logit contributions
terness-10.141
thur-9.358
י�-9.323
phia-9.317
renheit-9.222
Token reach
Token ID3151
Feature activation+3.07e+00

Pos logit contributions
��+0.128
 Belg+0.125
uss+0.121
rol+0.118
roid+0.116
Neg logit contributions
terness-0.160
thur-0.152
phia-0.145
י�-0.143
renheit-0.142
Token fever
Token ID17372
Feature activation+2.12e+00

Pos logit contributions
terness+2.636
thur+2.517
phia+2.397
י�+2.353
renheit+2.328
Neg logit contributions
��-2.069
 Belg-1.937
uss-1.892
rol-1.857
roid-1.825
Token pitch
Token ID7078
Feature activation+1.22e+00

Pos logit contributions
terness+1.442
thur+1.355
phia+1.273
י�+1.250
chio+1.240
Neg logit contributions
��-1.807
 Belg-1.741
uss-1.704
rol-1.676
roid-1.649
Token around
Token ID1088
Feature activation+2.56e-01

Pos logit contributions
terness+1.064
thur+1.013
phia+0.967
י�+0.954
chio+0.947
Neg logit contributions
��-0.812
 Belg-0.775
uss-0.753
rol-0.736
roid-0.722
Token in
Token ID287
Feature activation-4.20e-01

Pos logit contributions
terness+0.297
thur+0.281
phia+0.267
י�+0.263
chio+0.261
Neg logit contributions
��-0.276
 Belg-0.266
uss-0.259
rol-0.254
roid-0.250
Token Boston
Token ID6182
Feature activation-2.12e+00

Pos logit contributions
��+0.303
 Belg+0.293
uss+0.284
rol+0.278
roid+0.272
Neg logit contributions
terness-0.341
thur-0.324
phia-0.307
י�-0.302
chio-0.301
Token by
Token ID416
Feature activation-3.08e+00

Pos logit contributions
��+1.325
 Belg+1.293
uss+1.245
rol+1.232
roid+1.187
Neg logit contributions
terness-1.896
thur-1.815
phia-1.727
renheit-1.705
י�-1.699
Token anti
Token ID3098
Feature activation-8.52e+00

Pos logit contributions
��+2.156
 Belg+2.121
uss+2.022
rol+1.997
roid+1.934
Neg logit contributions
terness-2.510
thur-2.410
phia-2.255
chio-2.240
renheit-2.237
Token-
Token ID12
Feature activation-5.02e+00

Pos logit contributions
 Belg+4.628
uss+4.601
rol+4.530
��+4.477
roid+4.318
Neg logit contributions
terness-7.985
thur-7.324
phia-7.210
chio-7.170
renheit-7.140
Tokenstreet
Token ID25662
Feature activation-1.01e+01

Pos logit contributions
uss+2.961
��+2.944
 Belg+2.933
rol+2.902
roid+2.873
Neg logit contributions
terness-4.502
thur-4.208
renheit-4.036
phia-4.020
chio-4.015
Token harassment
Token ID10556
Feature activation-4.54e+00

Pos logit contributions
��+4.946
 Belg+4.839
uss+4.838
rol+4.820
roid+4.586
Neg logit contributions
terness-9.432
thur-9.034
phia-8.594
renheit-8.593
chio-8.520
Token organization
Token ID4009
Feature activation-3.18e-01

Pos logit contributions
 Belg+2.838
��+2.770
uss+2.720
rol+2.686
roid+2.613
Neg logit contributions
terness-3.986
thur-3.799
phia-3.577
chio-3.548
renheit-3.541
Token Holl
Token ID11806
Feature activation-7.98e-01

Pos logit contributions
��+0.215
 Belg+0.209
uss+0.202
rol+0.198
roid+0.193
Neg logit contributions
terness-0.270
thur-0.258
phia-0.245
י�-0.241
chio-0.240
Tokenab
Token ID397
Feature activation+2.66e+00

Pos logit contributions
��+0.519
 Belg+0.501
uss+0.492
rol+0.479
roid+0.468
Neg logit contributions
terness-0.699
thur-0.663
phia-0.632
י�-0.626
chio-0.625
Tokenack
Token ID441
Feature activation+5.22e-02

Pos logit contributions
terness+1.889
thur+1.792
phia+1.694
י�+1.672
chio+1.643
Neg logit contributions
��-2.191
 Belg-2.077
uss-2.002
rol-1.982
roid-1.952
Token the
Token ID262
Feature activation-3.98e-01

Pos logit contributions
terness+0.255
thur+0.242
phia+0.230
י�+0.226
renheit+0.225
Neg logit contributions
��-0.218
 Belg-0.211
uss-0.205
rol-0.200
roid-0.196
Token Supreme
Token ID5617
Feature activation-3.16e-01

Pos logit contributions
��+0.272
 Belg+0.264
uss+0.255
rol+0.249
roid+0.244
Neg logit contributions
terness-0.337
thur-0.320
phia-0.306
י�-0.300
renheit-0.299
Token Court
Token ID3078
Feature activation-1.96e+00

Pos logit contributions
��+0.219
 Belg+0.215
uss+0.208
rol+0.204
roid+0.199
Neg logit contributions
terness-0.262
thur-0.248
phia-0.239
י�-0.234
renheit-0.233
Token Orders
Token ID30689
Feature activation-2.46e+00

Pos logit contributions
��+1.283
 Belg+1.234
uss+1.207
rol+1.171
roid+1.146
Neg logit contributions
terness-1.712
thur-1.633
phia-1.566
renheit-1.540
י�-1.537
Token on
Token ID319
Feature activation-2.32e+00

Pos logit contributions
��+1.714
 Belg+1.694
uss+1.631
rol+1.595
roid+1.555
Neg logit contributions
terness-2.007
thur-1.920
phia-1.832
renheit-1.812
י�-1.792
Token Aadhaar
Token ID47727
Feature activation-9.99e+00

Pos logit contributions
��+1.599
 Belg+1.591
uss+1.528
rol+1.502
roid+1.463
Neg logit contributions
terness-1.919
thur-1.797
phia-1.728
renheit-1.698
י�-1.687
Token
Token ID198
Feature activation-2.69e+00

Pos logit contributions
 Belg+6.192
��+5.949
uss+5.905
rol+5.886
roid+5.765
Neg logit contributions
terness-8.451
thur-7.922
renheit-7.737
phia-7.595
י�-7.565
Token
Token ID198
Feature activation-2.36e+00

Pos logit contributions
��+2.006
 Belg+1.987
uss+1.938
rol+1.909
roid+1.867
Neg logit contributions
terness-2.087
thur-1.950
phia-1.855
renheit-1.813
chio-1.813
TokenThe
Token ID464
Feature activation-1.46e+00

Pos logit contributions
��+1.805
 Belg+1.795
uss+1.783
rol+1.744
roid+1.713
Neg logit contributions
terness-1.751
thur-1.627
phia-1.551
renheit-1.522
chio-1.517
Token Supreme
Token ID5617
Feature activation-1.06e+00

Pos logit contributions
��+0.975
 Belg+0.949
uss+0.923
rol+0.901
roid+0.880
Neg logit contributions
terness-1.256
thur-1.192
phia-1.146
י�-1.123
renheit-1.121
Token Court
Token ID3078
Feature activation-3.28e+00

Pos logit contributions
��+0.721
 Belg+0.710
uss+0.691
rol+0.677
roid+0.658
Neg logit contributions
terness-0.891
thur-0.839
phia-0.814
י�-0.791
renheit-0.790
Token we
Token ID356
Feature activation+1.79e+00

Pos logit contributions
��+1.088
 Belg+1.058
uss+1.032
rol+1.010
roid+0.985
Neg logit contributions
terness-1.431
thur-1.360
phia-1.296
י�-1.281
renheit-1.275
Token will
Token ID481
Feature activation+4.77e-01

Pos logit contributions
terness+1.502
thur+1.435
phia+1.363
י�+1.346
chio+1.337
Neg logit contributions
��-1.246
 Belg-1.179
uss-1.131
rol-1.107
roid-1.091
Token perform
Token ID1620
Feature activation-7.17e-01

Pos logit contributions
terness+0.434
thur+0.414
phia+0.396
י�+0.391
chio+0.389
Neg logit contributions
��-0.298
 Belg-0.284
uss-0.274
rol-0.268
roid-0.262
Token meta
Token ID13634
Feature activation-3.94e+00

Pos logit contributions
��+0.453
 Belg+0.440
uss+0.428
rol+0.418
roid+0.408
Neg logit contributions
terness-0.641
thur-0.608
phia-0.582
י�-0.575
renheit-0.573
Token-
Token ID12
Feature activation-7.15e+00

Pos logit contributions
��+2.412
uss+2.388
 Belg+2.376
rol+2.325
roid+2.256
Neg logit contributions
terness-3.532
thur-3.317
phia-3.230
renheit-3.181
chio-3.149
Tokenreg
Token ID2301
Feature activation-9.97e+00

Pos logit contributions
uss+5.676
rol+5.573
 Belg+5.451
roid+5.444
rolling+5.331
Neg logit contributions
terness-4.970
thur-4.446
renheit-4.408
chio-4.317
phia-4.262
Tokenression
Token ID2234
Feature activation+1.30e+00

Pos logit contributions
uss+2.727
rol+2.675
rolling+2.317
istry+2.290
roid+2.166
Neg logit contributions
terness-12.066
renheit-11.366
phia-11.338
thur-11.326
chio-10.983
Token if
Token ID611
Feature activation-7.34e-01

Pos logit contributions
terness+1.104
thur+1.050
phia+1.001
י�+0.988
chio+0.980
Neg logit contributions
��-0.893
 Belg-0.851
uss-0.824
rol-0.806
roid-0.793
Token a
Token ID257
Feature activation+7.35e-01

Pos logit contributions
��+0.485
 Belg+0.470
uss+0.458
rol+0.448
roid+0.437
Neg logit contributions
terness-0.635
thur-0.604
phia-0.575
י�-0.569
renheit-0.567
Token sufficient
Token ID6751
Feature activation-2.07e+00

Pos logit contributions
terness+0.677
thur+0.647
phia+0.621
י�+0.612
chio+0.610
Neg logit contributions
��-0.450
 Belg-0.427
uss-0.412
rol-0.402
roid-0.394
Token number
Token ID1271
Feature activation-1.57e+00

Pos logit contributions
��+1.343
 Belg+1.313
uss+1.275
rol+1.245
roid+1.219
Neg logit contributions
terness-1.819
thur-1.723
phia-1.647
renheit-1.625
י�-1.621
Token.'
Token ID2637
Feature activation-3.81e-01

Pos logit contributions
��+2.166
 Belg+2.103
uss+2.071
rol+2.020
roid+1.975
Neg logit contributions
terness-2.479
thur-2.326
phia-2.216
י�-2.198
renheit-2.180
Tokens
Token ID82
Feature activation-3.95e-01

Pos logit contributions
��+0.339
 Belg+0.337
uss+0.333
rol+0.326
roid+0.321
Neg logit contributions
terness-0.238
thur-0.220
phia-0.207
renheit-0.202
י�-0.201
Token lead
Token ID1085
Feature activation-7.47e-02

Pos logit contributions
��+0.282
 Belg+0.272
uss+0.264
rol+0.259
roid+0.254
Neg logit contributions
terness-0.324
thur-0.307
phia-0.292
י�-0.288
chio-0.286
Token singer
Token ID14015
Feature activation+4.70e+00

Pos logit contributions
��+0.050
 Belg+0.047
uss+0.046
rol+0.045
roid+0.044
Neg logit contributions
terness-0.064
thur-0.061
phia-0.059
י�-0.058
chio-0.057
Token Michael
Token ID3899
Feature activation-2.49e+00

Pos logit contributions
terness+3.504
thur+3.339
phia+3.155
י�+3.112
TER+3.075
Neg logit contributions
��-3.622
 Belg-3.399
uss-3.300
rol-3.245
roid-3.222
Token St
Token ID520
Feature activation-9.79e+00

Pos logit contributions
��+1.684
 Belg+1.660
uss+1.599
rol+1.561
roid+1.518
Neg logit contributions
terness-2.123
thur-2.005
phia-1.896
renheit-1.888
י�-1.882
Tokenipe
Token ID3757
Feature activation-2.47e+00

Pos logit contributions
uss+6.569
 Belg+6.285
rol+6.207
��+6.061
roid+6.006
Neg logit contributions
terness-8.274
thur-7.690
י�-7.571
phia-7.226
DEN-7.156
Token,
Token ID11
Feature activation-5.74e-01

Pos logit contributions
��+1.758
 Belg+1.710
uss+1.673
rol+1.648
roid+1.609
Neg logit contributions
terness-2.011
thur-1.901
phia-1.814
י�-1.787
renheit-1.778
Token told
Token ID1297
Feature activation-1.43e+00

Pos logit contributions
��+0.387
 Belg+0.372
uss+0.362
rol+0.354
roid+0.346
Neg logit contributions
terness-0.492
thur-0.468
phia-0.447
י�-0.440
chio-0.437
Token Newsweek
Token ID39594
Feature activation-1.28e+00

Pos logit contributions
��+0.955
 Belg+0.937
uss+0.903
rol+0.882
roid+0.862
Neg logit contributions
terness-1.225
thur-1.160
phia-1.105
י�-1.088
renheit-1.085
Token in
Token ID287
Feature activation-6.44e-01

Pos logit contributions
��+0.875
 Belg+0.844
uss+0.820
rol+0.802
roid+0.786
Neg logit contributions
terness-1.077
thur-1.023
phia-0.974
י�-0.962
chio-0.954
Tokena
Token ID64
Feature activation-3.58e+00

Pos logit contributions
terness+2.112
thur+1.991
phia+1.896
י�+1.848
chio+1.845
Neg logit contributions
��-2.563
 Belg-2.442
uss-2.370
rol-2.325
roid-2.310
Token mission
Token ID4365
Feature activation-4.00e+00

Pos logit contributions
 Belg+2.385
��+2.344
uss+2.344
rol+2.295
roid+2.191
Neg logit contributions
terness-3.010
thur-2.845
phia-2.715
renheit-2.713
י�-2.693
Token manager
Token ID4706
Feature activation+1.02e+00

Pos logit contributions
 Belg+2.376
��+2.344
uss+2.306
rol+2.271
roid+2.171
Neg logit contributions
terness-3.663
thur-3.470
phia-3.334
י�-3.300
renheit-3.292
Token Dr
Token ID1583
Feature activation-2.79e+00

Pos logit contributions
terness+0.822
thur+0.780
phia+0.742
י�+0.730
chio+0.725
Neg logit contributions
��-0.741
 Belg-0.709
uss-0.692
rol-0.678
roid-0.666
Token Rune
Token ID28228
Feature activation-1.07e+00

Pos logit contributions
��+1.981
 Belg+1.972
uss+1.904
rol+1.872
roid+1.799
Neg logit contributions
terness-2.254
thur-2.141
phia-2.036
י�-1.998
renheit-1.995
Token Fl
Token ID1610
Feature activation-9.75e+00

Pos logit contributions
��+0.719
 Belg+0.699
uss+0.680
rol+0.663
roid+0.648
Neg logit contributions
terness-0.919
thur-0.870
phia-0.833
י�-0.823
renheit-0.816
Tokenober
Token ID2023
Feature activation+1.63e+00

Pos logit contributions
uss+7.331
rol+6.860
 Belg+6.676
roid+6.599
inson+6.497
Neg logit contributions
terness-7.124
thur-6.613
י�-6.528
renheit-6.297
DEN-6.286
Tokengh
Token ID456
Feature activation+4.68e+00

Pos logit contributions
terness+1.135
thur+1.075
phia+1.007
chio+0.985
י�+0.983
Neg logit contributions
��-1.375
 Belg-1.315
uss-1.281
rol-1.254
roid-1.238
Tokenagen
Token ID11286
Feature activation+6.28e-01

Pos logit contributions
terness+3.636
thur+3.506
chio+3.260
phia+3.249
י�+3.217
Neg logit contributions
��-3.560
 Belg-3.319
uss-3.120
rol-3.099
roid-3.085
Token.
Token ID13
Feature activation+2.30e+00

Pos logit contributions
terness+0.518
thur+0.491
phia+0.469
י�+0.461
chio+0.458
Neg logit contributions
��-0.443
 Belg-0.428
uss-0.417
rol-0.408
roid-0.399
Token
Token ID198
Feature activation+7.90e-01

Pos logit contributions
terness+1.612
thur+1.522
phia+1.432
י�+1.414
chio+1.404
Neg logit contributions
��-1.915
 Belg-1.829
uss-1.790
rol-1.753
roid-1.730
Token.
Token ID13
Feature activation-7.17e-01

Pos logit contributions
��+1.863
 Belg+1.844
uss+1.812
rol+1.787
roid+1.705
Neg logit contributions
terness-2.583
thur-2.471
phia-2.371
chio-2.317
renheit-2.302
Token At
Token ID1629
Feature activation-2.18e+00

Pos logit contributions
��+0.539
 Belg+0.528
uss+0.513
rol+0.505
roid+0.491
Neg logit contributions
terness-0.554
thur-0.527
phia-0.499
י�-0.488
chio-0.488
Token least
Token ID1551
Feature activation-5.01e+00

Pos logit contributions
��+1.335
 Belg+1.288
uss+1.245
rol+1.219
roid+1.184
Neg logit contributions
terness-1.995
thur-1.903
phia-1.823
י�-1.799
chio-1.785
Token 250
Token ID8646
Feature activation-3.80e+00

Pos logit contributions
 Belg+2.952
��+2.832
uss+2.804
rol+2.737
roid+2.640
Neg logit contributions
terness-4.659
thur-4.395
phia-4.228
renheit-4.173
י�-4.166
Token people
Token ID661
Feature activation-3.34e+00

Pos logit contributions
 Belg+2.575
��+2.543
uss+2.491
rol+2.463
roid+2.363
Neg logit contributions
terness-3.140
thur-3.020
phia-2.848
chio-2.824
renheit-2.809
Token cycle
Token ID6772
Feature activation-9.74e+00

Pos logit contributions
 Belg+2.096
��+2.065
uss+2.034
rol+2.001
roid+1.918
Neg logit contributions
terness-2.947
thur-2.805
phia-2.649
renheit-2.611
chio-2.599
Token in
Token ID287
Feature activation-3.60e+00

Pos logit contributions
 Belg+5.711
uss+5.507
rol+5.504
��+5.167
roid+5.069
Neg logit contributions
terness-8.760
thur-8.198
chio-7.825
phia-7.803
renheit-7.779
Token and
Token ID290
Feature activation-7.52e-01

Pos logit contributions
��+2.428
 Belg+2.389
uss+2.339
rol+2.303
roid+2.226
Neg logit contributions
terness-3.036
thur-2.869
phia-2.728
chio-2.696
י�-2.683
Token out
Token ID503
Feature activation+5.22e-01

Pos logit contributions
��+0.418
 Belg+0.401
uss+0.388
rol+0.378
roid+0.366
Neg logit contributions
terness-0.732
thur-0.700
phia-0.672
י�-0.662
chio-0.660
Token of
Token ID286
Feature activation-2.57e+00

Pos logit contributions
terness+0.415
thur+0.393
phia+0.373
י�+0.368
chio+0.365
Neg logit contributions
��-0.386
 Belg-0.370
uss-0.361
rol-0.353
roid-0.348
Token the
Token ID262
Feature activation-2.66e+00

Pos logit contributions
��+1.843
 Belg+1.806
uss+1.755
rol+1.728
roid+1.682
Neg logit contributions
terness-2.071
thur-1.977
phia-1.861
chio-1.834
י�-1.832
Token companies
Token ID2706
Feature activation+7.88e-01

Pos logit contributions
terness+2.000
thur+1.900
phia+1.805
י�+1.779
chio+1.768
Neg logit contributions
��-1.799
 Belg-1.721
uss-1.676
rol-1.640
roid-1.611
Token letter
Token ID3850
Feature activation-2.28e+00

Pos logit contributions
terness+0.647
thur+0.614
phia+0.586
י�+0.577
chio+0.574
Neg logit contributions
��-0.562
 Belg-0.534
uss-0.520
rol-0.509
roid-0.500
Token to
Token ID284
Feature activation-4.43e-01

Pos logit contributions
��+1.463
 Belg+1.422
uss+1.384
rol+1.351
roid+1.322
Neg logit contributions
terness-2.003
thur-1.910
phia-1.830
י�-1.793
renheit-1.788
Token Sen
Token ID2311
Feature activation+1.14e+00

Pos logit contributions
��+0.324
 Belg+0.318
uss+0.309
rol+0.303
roid+0.296
Neg logit contributions
terness-0.353
thur-0.333
phia-0.317
renheit-0.310
י�-0.310
Token.
Token ID13
Feature activation-2.43e+00

Pos logit contributions
terness+0.922
thur+0.881
phia+0.834
י�+0.825
chio+0.821
Neg logit contributions
��-0.817
 Belg-0.782
uss-0.757
rol-0.741
roid-0.731
Token Patty
Token ID42417
Feature activation-9.73e+00

Pos logit contributions
 Belg+1.768
��+1.765
uss+1.706
rol+1.681
roid+1.636
Neg logit contributions
terness-1.943
thur-1.814
phia-1.739
renheit-1.695
י�-1.673
Token Murray
Token ID12164
Feature activation-7.94e-01

Pos logit contributions
 Belg+4.381
rol+4.217
roid+4.183
uss+4.181
��+4.021
Neg logit contributions
terness-9.947
thur-9.842
renheit-9.145
phia-9.127
י�-9.010
Token,
Token ID11
Feature activation-1.38e+00

Pos logit contributions
��+0.550
 Belg+0.533
uss+0.519
rol+0.509
roid+0.498
Neg logit contributions
terness-0.660
thur-0.628
phia-0.602
י�-0.591
renheit-0.587
Token Chair
Token ID9369
Feature activation+3.55e+00

Pos logit contributions
��+0.873
 Belg+0.849
uss+0.820
rol+0.801
roid+0.780
Neg logit contributions
terness-1.229
thur-1.170
phia-1.120
י�-1.105
renheit-1.098
Token,
Token ID11
Feature activation+3.29e-01

Pos logit contributions
terness+2.847
thur+2.698
phia+2.547
י�+2.521
chio+2.501
Neg logit contributions
��-2.590
 Belg-2.479
uss-2.402
rol-2.339
roid-2.310
Token Democratic
Token ID4390
Feature activation-1.26e+00

Pos logit contributions
terness+0.274
thur+0.260
phia+0.248
י�+0.244
renheit+0.243
Neg logit contributions
��-0.229
 Belg-0.221
uss-0.215
rol-0.210
roid-0.206
Token to
Token ID284
Feature activation-1.03e+00

Pos logit contributions
terness+0.069
thur+0.066
phia+0.063
י�+0.062
chio+0.062
Neg logit contributions
��-0.050
 Belg-0.048
uss-0.047
rol-0.046
roid-0.045
Token say
Token ID910
Feature activation-9.41e-02

Pos logit contributions
��+0.661
 Belg+0.645
uss+0.633
rol+0.615
roid+0.605
Neg logit contributions
terness-0.907
thur-0.860
phia-0.823
renheit-0.814
י�-0.805
Token today
Token ID1909
Feature activation+2.66e+00

Pos logit contributions
��+0.066
 Belg+0.064
uss+0.063
rol+0.061
roid+0.060
Neg logit contributions
terness-0.078
thur-0.074
phia-0.070
י�-0.069
chio-0.068
Token,
Token ID11
Feature activation+2.16e-01

Pos logit contributions
terness+2.158
thur+2.045
phia+1.942
י�+1.924
chio+1.907
Neg logit contributions
��-1.923
 Belg-1.837
uss-1.785
rol-1.744
roid-1.717
Token about
Token ID546
Feature activation+1.36e+00

Pos logit contributions
terness+0.197
thur+0.187
phia+0.179
י�+0.177
chio+0.176
Neg logit contributions
��-0.134
 Belg-0.128
uss-0.124
rol-0.121
roid-0.118
Token Dw
Token ID19113
Feature activation-9.71e+00

Pos logit contributions
terness+1.143
thur+1.092
phia+1.038
י�+1.028
chio+1.018
Neg logit contributions
��-0.945
 Belg-0.894
uss-0.865
rol-0.849
roid-0.838
Tokeny
Token ID88
Feature activation-4.16e+00

Pos logit contributions
uss+3.204
rol+3.136
 Belg+3.045
��+2.975
roid+2.941
Neg logit contributions
terness-11.336
phia-10.389
thur-10.233
י�-9.955
DEN-9.871
Tokenane
Token ID1531
Feature activation-5.87e+00

Pos logit contributions
uss+3.435
 Belg+3.412
rol+3.351
roid+3.276
��+3.223
Neg logit contributions
terness-2.920
thur-2.632
renheit-2.483
phia-2.463
י�-2.412
Token Wade
Token ID19136
Feature activation-7.91e+00

Pos logit contributions
��+2.621
 Belg+2.483
uss+2.332
rol+2.270
roid+2.172
Neg logit contributions
terness-6.397
thur-6.055
phia-5.922
renheit-5.817
chio-5.777
Token,
Token ID11
Feature activation-4.68e-01

Pos logit contributions
��+4.666
uss+4.588
rol+4.571
 Belg+4.473
roid+4.249
Neg logit contributions
terness-6.832
thur-6.506
phia-6.404
chio-6.178
י�-6.143
Token Chris
Token ID5180
Feature activation-3.00e+00

Pos logit contributions
��+0.337
 Belg+0.323
uss+0.315
rol+0.308
roid+0.303
Neg logit contributions
terness-0.380
thur-0.361
phia-0.343
י�-0.338
chio-0.336
Token rock
Token ID3881
Feature activation-1.69e+00

Pos logit contributions
terness+0.320
thur+0.304
phia+0.290
י�+0.286
chio+0.284
Neg logit contributions
��-0.255
 Belg-0.245
uss-0.238
rol-0.233
roid-0.229
Token out
Token ID503
Feature activation+1.24e+00

Pos logit contributions
��+1.125
 Belg+1.102
uss+1.078
rol+1.044
roid+1.034
Neg logit contributions
terness-1.446
thur-1.359
phia-1.298
renheit-1.287
י�-1.287
Tokencro
Token ID19915
Feature activation-1.21e-01

Pos logit contributions
terness+0.733
thur+0.681
phia+0.635
י�+0.620
chio+0.614
Neg logit contributions
��-1.176
 Belg-1.138
uss-1.115
rol-1.097
roid-1.083
Tokenps
Token ID862
Feature activation-1.32e+00

Pos logit contributions
��+0.116
 Belg+0.114
uss+0.112
rol+0.110
roid+0.109
Neg logit contributions
terness-0.068
thur-0.063
phia-0.058
י�-0.058
chio-0.056
Token and
Token ID290
Feature activation-8.98e-01

Pos logit contributions
��+0.878
 Belg+0.855
uss+0.835
rol+0.813
roid+0.794
Neg logit contributions
terness-1.140
thur-1.078
phia-1.034
י�-1.020
renheit-1.015
Token upper
Token ID6727
Feature activation+5.82e+00

Pos logit contributions
��+0.602
 Belg+0.588
uss+0.571
rol+0.558
roid+0.546
Neg logit contributions
terness-0.769
thur-0.725
phia-0.694
י�-0.686
renheit-0.682
Token flat
Token ID6228
Feature activation+1.60e+00

Pos logit contributions
terness+4.723
thur+4.562
phia+4.385
י�+4.254
chio+4.240
Neg logit contributions
��-4.062
 Belg-3.682
uss-3.613
rol-3.531
roid-3.449
Token areas
Token ID3006
Feature activation-1.89e+00

Pos logit contributions
terness+1.400
thur+1.333
phia+1.273
י�+1.255
chio+1.247
Neg logit contributions
��-1.060
 Belg-1.013
uss-0.984
rol-0.962
roid-0.942
Token.
Token ID13
Feature activation-8.48e-01

Pos logit contributions
��+1.250
 Belg+1.227
uss+1.200
rol+1.168
roid+1.142
Neg logit contributions
terness-1.629
thur-1.534
phia-1.475
י�-1.452
renheit-1.450
Token If
Token ID1002
Feature activation+8.70e-01

Pos logit contributions
��+0.561
 Belg+0.559
uss+0.539
rol+0.526
roid+0.512
Neg logit contributions
terness-0.727
thur-0.685
phia-0.657
renheit-0.645
י�-0.644
Token you
Token ID345
Feature activation-6.84e-01

Pos logit contributions
terness+0.678
thur+0.642
phia+0.609
י�+0.600
chio+0.595
Neg logit contributions
��-0.654
 Belg-0.630
uss-0.614
rol-0.602
roid-0.592
Token Sullivan
Token ID18501
Feature activation+4.37e+00

Pos logit contributions
terness+0.142
thur+0.135
phia+0.129
י�+0.127
chio+0.126
Neg logit contributions
��-0.106
 Belg-0.102
uss-0.099
rol-0.097
roid-0.095
Token is
Token ID318
Feature activation+1.96e+00

Pos logit contributions
terness+3.605
thur+3.448
phia+3.289
chio+3.227
י�+3.223
Neg logit contributions
��-3.082
 Belg-2.877
uss-2.784
rol-2.728
roid-2.680
Token finally
Token ID3443
Feature activation+3.04e+00

Pos logit contributions
terness+1.780
thur+1.702
phia+1.634
י�+1.609
chio+1.599
Neg logit contributions
��-1.228
 Belg-1.142
uss-1.110
rol-1.085
roid-1.062
Token able
Token ID1498
Feature activation+1.43e+00

Pos logit contributions
terness+2.841
thur+2.736
phia+2.624
י�+2.592
chio+2.579
Neg logit contributions
��-1.828
 Belg-1.672
uss-1.624
rol-1.578
roid-1.534
Token to
Token ID284
Feature activation+9.82e-01

Pos logit contributions
terness+1.249
thur+1.191
phia+1.137
י�+1.124
chio+1.116
Neg logit contributions
��-0.940
 Belg-0.896
uss-0.870
rol-0.850
roid-0.832
Token enter
Token ID3802
Feature activation+6.26e+00

Pos logit contributions
terness+0.852
thur+0.813
phia+0.777
י�+0.766
chio+0.763
Neg logit contributions
��-0.653
 Belg-0.620
uss-0.602
rol-0.590
roid-0.577
Token the
Token ID262
Feature activation+1.08e+00

Pos logit contributions
terness+4.949
thur+4.710
phia+4.535
י�+4.475
chio+4.399
Neg logit contributions
��-4.498
 Belg-4.132
uss-4.069
rol-4.033
roid-3.955
Token cabin
Token ID9351
Feature activation+3.57e+00

Pos logit contributions
terness+0.923
thur+0.877
phia+0.837
י�+0.825
chio+0.819
Neg logit contributions
��-0.731
 Belg-0.702
uss-0.682
rol-0.666
roid-0.654
Token more
Token ID517
Feature activation+1.24e+00

Pos logit contributions
terness+2.881
thur+2.747
phia+2.600
י�+2.573
chio+2.551
Neg logit contributions
��-2.585
 Belg-2.451
uss-2.370
rol-2.315
roid-2.272
Token than
Token ID621
Feature activation+1.88e+00

Pos logit contributions
terness+1.170
thur+1.121
phia+1.071
י�+1.062
chio+1.055
Neg logit contributions
��-0.727
 Belg-0.685
uss-0.665
rol-0.647
roid-0.631
Token an
Token ID281
Feature activation+6.45e-01

Pos logit contributions
terness+1.664
thur+1.593
phia+1.516
י�+1.500
chio+1.492
Neg logit contributions
��-1.218
 Belg-1.150
uss-1.122
rol-1.097
roid-1.075
Token for
Token ID329
Feature activation+1.49e+00

Pos logit contributions
��+0.916
 Belg+0.885
uss+0.864
rol+0.845
roid+0.824
Neg logit contributions
terness-1.362
thur-1.292
phia-1.236
chio-1.218
י�-1.217
Token repairing
Token ID39005
Feature activation+4.88e-01

Pos logit contributions
terness+1.331
thur+1.275
phia+1.218
י�+1.205
chio+1.194
Neg logit contributions
��-0.960
 Belg-0.894
uss-0.869
rol-0.848
roid-0.835
Token the
Token ID262
Feature activation+1.24e+00

Pos logit contributions
terness+0.405
thur+0.385
phia+0.366
י�+0.361
chio+0.358
Neg logit contributions
��-0.342
 Belg-0.329
uss-0.321
rol-0.314
roid-0.308
Token sidewalks
Token ID38282
Feature activation-4.11e+00

Pos logit contributions
terness+1.043
thur+0.990
phia+0.947
י�+0.932
chio+0.924
Neg logit contributions
��-0.863
 Belg-0.815
uss-0.794
rol-0.776
roid-0.766
Token.
Token ID13
Feature activation+3.63e-01

Pos logit contributions
 Belg+2.570
��+2.553
uss+2.523
rol+2.455
roid+2.386
Neg logit contributions
terness-3.602
thur-3.422
phia-3.273
renheit-3.218
chio-3.213
Token AB
Token ID9564
Feature activation+5.88e+00

Pos logit contributions
terness+0.317
thur+0.302
phia+0.288
י�+0.283
renheit+0.282
Neg logit contributions
��-0.237
 Belg-0.232
uss-0.224
rol-0.219
roid-0.214
Token 12
Token ID1105
Feature activation-1.08e-01

Pos logit contributions
terness+4.101
thur+3.820
chio+3.537
phia+3.529
TER+3.518
Neg logit contributions
��-4.914
 Belg-4.670
uss-4.509
rol-4.427
roid-4.380
Token90
Token ID3829
Feature activation+5.28e-01

Pos logit contributions
��+0.072
 Belg+0.070
uss+0.068
rol+0.067
roid+0.065
Neg logit contributions
terness-0.092
thur-0.087
phia-0.083
י�-0.082
chio-0.082
Token money
Token ID1637
Feature activation-8.49e-01

Pos logit contributions
terness+0.453
thur+0.431
phia+0.411
י�+0.405
chio+0.402
Neg logit contributions
��-0.356
 Belg-0.341
uss-0.332
rol-0.325
roid-0.318
Token is
Token ID318
Feature activation+1.64e+00

Pos logit contributions
��+0.562
 Belg+0.545
uss+0.531
rol+0.520
roid+0.510
Neg logit contributions
terness-0.734
thur-0.697
phia-0.663
י�-0.654
renheit-0.651
Token to
Token ID284
Feature activation+7.81e-02

Pos logit contributions
terness+1.386
thur+1.321
phia+1.262
י�+1.244
chio+1.234
Neg logit contributions
��-1.138
 Belg-1.072
uss-1.042
rol-1.023
roid-1.005
Token court
Token ID2184
Feature activation+5.73e-01

Pos logit contributions
terness+1.957
thur+1.873
phia+1.787
י�+1.764
chio+1.754
Neg logit contributions
��-1.415
 Belg-1.343
uss-1.299
rol-1.276
roid-1.249
Token has
Token ID468
Feature activation+1.28e+00

Pos logit contributions
terness+0.512
thur+0.488
phia+0.467
י�+0.460
chio+0.457
Neg logit contributions
��-0.365
 Belg-0.350
uss-0.340
rol-0.332
roid-0.325
Token ruled
Token ID8879
Feature activation+1.19e+00

Pos logit contributions
terness+1.069
thur+1.020
phia+0.971
י�+0.958
chio+0.951
Neg logit contributions
��-0.886
 Belg-0.843
uss-0.822
rol-0.803
roid-0.788
Token if
Token ID611
Feature activation-2.62e-01

Pos logit contributions
terness+0.992
thur+0.946
phia+0.900
י�+0.889
chio+0.881
Neg logit contributions
��-0.835
 Belg-0.790
uss-0.770
rol-0.755
roid-0.742
Token the
Token ID262
Feature activation+4.49e-01

Pos logit contributions
��+0.183
 Belg+0.177
uss+0.173
rol+0.168
roid+0.165
Neg logit contributions
terness-0.218
thur-0.206
phia-0.196
י�-0.194
renheit-0.193
Token seizure
Token ID22338
Feature activation+6.87e+00

Pos logit contributions
terness+0.397
thur+0.378
phia+0.361
י�+0.356
chio+0.354
Neg logit contributions
��-0.291
 Belg-0.279
uss-0.271
rol-0.264
roid-0.259
Token can
Token ID460
Feature activation+1.93e+00

Pos logit contributions
terness+5.324
thur+5.158
phia+4.850
י�+4.823
chio+4.808
Neg logit contributions
��-5.135
 Belg-4.712
uss-4.573
rol-4.484
roid-4.401
Token go
Token ID467
Feature activation-3.19e-01

Pos logit contributions
terness+1.496
thur+1.414
phia+1.343
י�+1.321
chio+1.311
Neg logit contributions
��-1.458
 Belg-1.403
uss-1.369
rol-1.342
roid-1.319
Token ahead
Token ID4058
Feature activation-2.23e-01

Pos logit contributions
��+0.145
 Belg+0.137
uss+0.131
rol+0.127
roid+0.123
Neg logit contributions
terness-0.344
thur-0.330
phia-0.318
י�-0.315
chio-0.313
Token.
Token ID13
Feature activation-3.55e-02

Pos logit contributions
��+0.147
 Belg+0.144
uss+0.141
rol+0.138
roid+0.134
Neg logit contributions
terness-0.191
thur-0.180
phia-0.174
chio-0.170
י�-0.170
Token Some
Token ID2773
Feature activation+4.04e+00

Pos logit contributions
��+0.024
 Belg+0.024
uss+0.023
rol+0.022
roid+0.022
Neg logit contributions
terness-0.030
thur-0.029
phia-0.027
chio-0.027
renheit-0.027
Token stars
Token ID5788
Feature activation+1.46e-01

Pos logit contributions
terness+0.202
thur+0.191
phia+0.183
י�+0.180
renheit+0.179
Neg logit contributions
��-0.149
 Belg-0.146
uss-0.140
rol-0.137
roid-0.134
Token a
Token ID257
Feature activation-3.26e-01

Pos logit contributions
terness+0.124
thur+0.118
phia+0.112
י�+0.110
renheit+0.110
Neg logit contributions
��-0.099
 Belg-0.096
uss-0.093
rol-0.091
roid-0.089
Token great
Token ID1049
Feature activation-5.01e-01

Pos logit contributions
��+0.214
 Belg+0.209
uss+0.202
rol+0.198
roid+0.194
Neg logit contributions
terness-0.284
thur-0.269
phia-0.256
י�-0.252
renheit-0.252
Token future
Token ID2003
Feature activation+1.56e+00

Pos logit contributions
��+0.323
 Belg+0.315
uss+0.306
rol+0.298
roid+0.292
Neg logit contributions
terness-0.443
thur-0.419
phia-0.402
renheit-0.394
י�-0.394
Token for
Token ID329
Feature activation-9.25e-01

Pos logit contributions
terness+1.320
thur+1.256
phia+1.195
י�+1.181
chio+1.173
Neg logit contributions
��-1.074
 Belg-1.024
uss-0.996
rol-0.974
roid-0.955
Token Tol
Token ID20054
Feature activation+6.09e+00

Pos logit contributions
��+0.541
 Belg+0.534
uss+0.512
rol+0.501
roid+0.485
Neg logit contributions
terness-0.864
thur-0.824
phia-0.789
renheit-0.777
י�-0.776
Tokenui
Token ID9019
Feature activation-2.15e+00

Pos logit contributions
terness+4.495
thur+4.253
phia+4.037
chio+3.990
י�+3.969
Neg logit contributions
��-4.825
 Belg-4.454
uss-4.365
rol-4.268
roid-4.183
Token's
Token ID338
Feature activation-2.04e+00

Pos logit contributions
��+1.457
 Belg+1.449
uss+1.414
rol+1.395
roid+1.343
Neg logit contributions
terness-1.796
thur-1.696
phia-1.615
renheit-1.596
י�-1.588
Token eldest
Token ID34331
Feature activation+1.99e+00

Pos logit contributions
 Belg+1.568
��+1.553
uss+1.512
rol+1.487
roid+1.461
Neg logit contributions
terness-1.539
thur-1.425
phia-1.357
renheit-1.335
י�-1.327
Token son
Token ID3367
Feature activation+1.87e+00

Pos logit contributions
terness+1.482
thur+1.402
phia+1.327
י�+1.305
chio+1.296
Neg logit contributions
��-1.561
 Belg-1.497
uss-1.463
rol-1.437
roid-1.412
Token and
Token ID290
Feature activation+8.36e-02

Pos logit contributions
terness+1.527
thur+1.448
phia+1.379
י�+1.359
chio+1.349
Neg logit contributions
��-1.332
 Belg-1.276
uss-1.244
rol-1.218
roid-1.196
Token
Token ID564
Feature activation+1.88e+00

Pos logit contributions
terness+0.807
thur+0.766
phia+0.728
י�+0.728
chio+0.717
Neg logit contributions
��-0.618
 Belg-0.591
uss-0.574
rol-0.562
roid-0.554
Token
Token ID250
Feature activation+9.43e-01

Pos logit contributions
terness+1.375
thur+1.297
phia+1.226
י�+1.208
chio+1.196
Neg logit contributions
��-1.502
 Belg-1.456
uss-1.418
rol-1.388
roid-1.366
TokenHe
Token ID1544
Feature activation-2.45e+00

Pos logit contributions
terness+0.670
thur+0.631
phia+0.595
י�+0.586
chio+0.580
Neg logit contributions
��-0.776
 Belg-0.747
uss-0.730
rol-0.716
roid-0.705
Token's
Token ID338
Feature activation+1.27e-01

Pos logit contributions
��+1.497
uss+1.478
 Belg+1.476
rol+1.436
roid+1.396
Neg logit contributions
terness-2.203
thur-2.065
phia-2.004
י�-1.963
renheit-1.950
Token an
Token ID281
Feature activation+9.79e-01

Pos logit contributions
terness+0.113
thur+0.108
phia+0.103
י�+0.102
chio+0.101
Neg logit contributions
��-0.081
 Belg-0.077
uss-0.075
rol-0.073
roid-0.071
Token animated
Token ID15108
Feature activation+1.33e+00

Pos logit contributions
terness+0.858
thur+0.819
phia+0.781
י�+0.771
chio+0.766
Neg logit contributions
��-0.642
 Belg-0.611
uss-0.594
rol-0.580
roid-0.568
Token figure
Token ID3785
Feature activation+3.71e+00

Pos logit contributions
terness+1.166
thur+1.111
phia+1.060
י�+1.045
chio+1.038
Neg logit contributions
��-0.866
 Belg-0.831
uss-0.807
rol-0.788
roid-0.773
Token,
Token ID11
Feature activation-1.37e-01

Pos logit contributions
terness+3.035
thur+2.879
phia+2.741
י�+2.718
chio+2.699
Neg logit contributions
��-2.626
 Belg-2.484
uss-2.400
rol-2.357
roid-2.308
Token so
Token ID523
Feature activation+1.09e+00

Pos logit contributions
��+0.094
 Belg+0.091
uss+0.088
rol+0.086
roid+0.085
Neg logit contributions
terness-0.115
thur-0.109
phia-0.104
י�-0.103
chio-0.102
Token he
Token ID339
Feature activation-9.89e-01

Pos logit contributions
terness+0.924
thur+0.878
phia+0.836
י�+0.825
chio+0.819
Neg logit contributions
��-0.754
 Belg-0.717
uss-0.698
rol-0.682
roid-0.670
Token's
Token ID338
Feature activation+1.21e+00

Pos logit contributions
��+0.609
 Belg+0.589
uss+0.580
rol+0.567
roid+0.551
Neg logit contributions
terness-0.898
thur-0.852
phia-0.819
י�-0.803
renheit-0.801
Token start
Token ID923
Feature activation+2.16e-03

Pos logit contributions
terness+0.693
thur+0.657
phia+0.621
י�+0.610
chio+0.606
Neg logit contributions
��-0.739
 Belg-0.708
uss-0.693
rol-0.679
roid-0.669
Token schedules
Token ID24025
Feature activation-1.78e+00

Pos logit contributions
terness+0.002
thur+0.002
phia+0.002
י�+0.002
chio+0.002
Neg logit contributions
��-0.001
 Belg-0.001
uss-0.001
rol-0.001
roid-0.001
Token up
Token ID510
Feature activation+3.69e-01

Pos logit contributions
��+1.106
 Belg+1.098
uss+1.057
rol+1.038
roid+1.011
Neg logit contributions
terness-1.603
thur-1.514
phia-1.453
י�-1.429
renheit-1.426
Token and
Token ID290
Feature activation-5.37e-01

Pos logit contributions
terness+0.318
thur+0.301
phia+0.288
י�+0.284
chio+0.282
Neg logit contributions
��-0.247
 Belg-0.239
uss-0.232
rol-0.228
roid-0.221
Token back
Token ID736
Feature activation+1.31e+00

Pos logit contributions
��+0.354
 Belg+0.342
uss+0.332
rol+0.325
roid+0.318
Neg logit contributions
terness-0.467
thur-0.444
phia-0.424
י�-0.418
chio-0.415
Token."
Token ID526
Feature activation+7.46e-01

Pos logit contributions
terness+1.133
thur+1.079
phia+1.030
י�+1.015
chio+1.009
Neg logit contributions
��-0.870
 Belg-0.832
uss-0.809
rol-0.790
roid-0.774
Token
Token ID198
Feature activation+1.81e+00

Pos logit contributions
terness+0.536
thur+0.504
phia+0.478
י�+0.470
chio+0.465
Neg logit contributions
��-0.606
 Belg-0.584
uss-0.571
rol-0.560
roid-0.552
Token
Token ID198
Feature activation+7.27e-01

Pos logit contributions
terness+1.274
thur+1.204
phia+1.137
י�+1.121
chio+1.110
Neg logit contributions
��-1.500
 Belg-1.436
uss-1.403
rol-1.376
roid-1.356
TokenLet
Token ID5756
Feature activation+2.23e+00

Pos logit contributions
terness+0.532
thur+0.500
phia+0.472
י�+0.462
chio+0.460
Neg logit contributions
��-0.580
 Belg-0.563
uss-0.551
rol-0.542
roid-0.532
Tokenting
Token ID889
Feature activation+3.69e+00

Pos logit contributions
terness+1.744
thur+1.639
phia+1.561
י�+1.532
chio+1.530
Neg logit contributions
��-1.687
 Belg-1.613
uss-1.570
rol-1.531
roid-1.515
Token teenagers
Token ID17366
Feature activation-6.79e+00

Pos logit contributions
terness+2.627
thur+2.469
phia+2.349
chio+2.296
י�+2.287
Neg logit contributions
��-3.072
 Belg-2.854
uss-2.811
rol-2.746
roid-2.738
Token by
Token ID416
Feature activation+1.93e-01

Pos logit contributions
terness+1.524
thur+1.443
phia+1.364
י�+1.347
chio+1.336
Neg logit contributions
��-1.525
 Belg-1.460
uss-1.428
rol-1.399
roid-1.375
Token WikiLeaks
Token ID19766
Feature activation-4.13e+00

Pos logit contributions
terness+0.172
thur+0.164
phia+0.157
י�+0.154
chio+0.154
Neg logit contributions
��-0.123
 Belg-0.119
uss-0.115
rol-0.112
roid-0.110
Token sent
Token ID1908
Feature activation-5.58e-01

Pos logit contributions
 Belg+2.421
��+2.417
uss+2.307
rol+2.247
roid+2.178
Neg logit contributions
terness-3.788
thur-3.619
phia-3.499
י�-3.400
renheit-3.398
Token from
Token ID422
Feature activation+2.26e+00

Pos logit contributions
��+0.372
 Belg+0.359
uss+0.348
rol+0.341
roid+0.334
Neg logit contributions
terness-0.483
thur-0.459
phia-0.439
י�-0.430
chio-0.428
Token the
Token ID262
Feature activation+4.03e-01

Pos logit contributions
terness+1.793
thur+1.703
phia+1.619
י�+1.594
chio+1.581
Neg logit contributions
��-1.668
 Belg-1.595
uss-1.558
rol-1.528
roid-1.501
Token US
Token ID1294
Feature activation+3.17e+00

Pos logit contributions
terness+0.331
thur+0.312
phia+0.298
י�+0.293
chio+0.291
Neg logit contributions
��-0.286
 Belg-0.279
uss-0.270
rol-0.264
roid-0.259
Token embassy
Token ID18613
Feature activation-5.92e+00

Pos logit contributions
terness+2.693
thur+2.583
phia+2.446
י�+2.418
chio+2.388
Neg logit contributions
��-2.164
 Belg-2.035
uss-1.981
rol-1.940
roid-1.903
Token in
Token ID287
Feature activation+5.47e-01

Pos logit contributions
��+3.206
 Belg+3.206
uss+3.093
rol+2.957
roid+2.830
Neg logit contributions
terness-5.680
thur-5.363
phia-5.168
י�-5.086
renheit-5.066
Token Tripoli
Token ID47318
Feature activation-7.30e-01

Pos logit contributions
terness+0.383
thur+0.361
phia+0.341
י�+0.335
chio+0.332
Neg logit contributions
��-0.454
 Belg-0.436
uss-0.427
rol-0.420
roid-0.414
Token in
Token ID287
Feature activation+4.12e-01

Pos logit contributions
��+0.482
 Belg+0.466
uss+0.452
rol+0.441
roid+0.431
Neg logit contributions
terness-0.635
thur-0.604
phia-0.578
י�-0.568
renheit-0.564
Token November
Token ID3389
Feature activation+4.88e+00

Pos logit contributions
terness+0.340
thur+0.323
phia+0.308
י�+0.303
chio+0.301
Neg logit contributions
��-0.291
 Belg-0.279
uss-0.272
rol-0.266
roid-0.261
Token battle
Token ID3344
Feature activation-1.52e-01

Pos logit contributions
��+2.088
 Belg+2.061
uss+2.008
rol+1.954
roid+1.902
Neg logit contributions
terness-3.346
thur-3.143
phia-3.059
renheit-3.022
י�-2.993
Token engines
Token ID11874
Feature activation-7.36e-02

Pos logit contributions
��+0.109
 Belg+0.105
uss+0.103
rol+0.101
roid+0.099
Neg logit contributions
terness-0.124
thur-0.117
phia-0.112
י�-0.110
chio-0.109
Token as
Token ID355
Feature activation+1.57e+00

Pos logit contributions
��+0.050
 Belg+0.048
uss+0.047
rol+0.046
roid+0.045
Neg logit contributions
terness-0.063
thur-0.060
phia-0.057
י�-0.056
chio-0.056
Token well
Token ID880
Feature activation-6.22e+00

Pos logit contributions
terness+1.229
thur+1.169
phia+1.107
י�+1.090
chio+1.082
Neg logit contributions
��-1.179
 Belg-1.128
uss-1.099
rol-1.080
roid-1.062
Token.
Token ID13
Feature activation-7.91e-01

Pos logit contributions
��+3.892
 Belg+3.814
uss+3.712
rol+3.649
roid+3.511
Neg logit contributions
terness-5.476
thur-5.181
phia-5.022
chio-4.892
renheit-4.848
Token Talk
Token ID12167
Feature activation+1.13e+00

Pos logit contributions
��+0.559
 Belg+0.554
uss+0.533
rol+0.523
roid+0.510
Neg logit contributions
terness-0.648
thur-0.609
phia-0.582
renheit-0.571
י�-0.568
Token about
Token ID546
Feature activation-3.65e-01

Pos logit contributions
terness+0.884
thur+0.837
phia+0.795
י�+0.781
chio+0.776
Neg logit contributions
��-0.847
 Belg-0.812
uss-0.791
rol-0.776
roid-0.764
Token a
Token ID257
Feature activation-3.94e-01

Pos logit contributions
��+0.233
 Belg+0.224
uss+0.217
rol+0.212
roid+0.208
Neg logit contributions
terness-0.326
thur-0.310
phia-0.297
י�-0.293
renheit-0.291
Token theme
Token ID7505
Feature activation-4.22e+00

Pos logit contributions
��+0.250
 Belg+0.240
uss+0.233
rol+0.228
roid+0.223
Neg logit contributions
terness-0.354
thur-0.337
phia-0.322
י�-0.318
chio-0.316
Token force
Token ID2700
Feature activation-5.38e+00

Pos logit contributions
��+2.416
 Belg+2.325
uss+2.292
rol+2.189
roid+2.185
Neg logit contributions
terness-3.996
thur-3.798
phia-3.623
renheit-3.617
י�-3.611
Token with
Token ID351
Feature activation-3.68e+00

Pos logit contributions
��+3.234
 Belg+3.197
uss+3.167
rol+3.053
roid+3.026
Neg logit contributions
terness-4.768
thur-4.549
renheit-4.347
phia-4.343
י�-4.305
Token Arts
Token ID11536
Feature activation-1.89e+00

Pos logit contributions
��+0.202
 Belg+0.196
uss+0.191
rol+0.187
roid+0.183
Neg logit contributions
terness-0.237
thur-0.225
phia-0.215
י�-0.212
renheit-0.211
Token,
Token ID11
Feature activation+2.59e-01

Pos logit contributions
��+1.332
 Belg+1.303
uss+1.272
rol+1.255
roid+1.224
Neg logit contributions
terness-1.535
thur-1.444
phia-1.386
renheit-1.367
י�-1.361
Token which
Token ID543
Feature activation-1.11e+00

Pos logit contributions
terness+0.225
thur+0.215
phia+0.205
י�+0.202
chio+0.201
Neg logit contributions
��-0.171
 Belg-0.163
uss-0.159
rol-0.155
roid-0.152
Token were
Token ID547
Feature activation-1.37e+00

Pos logit contributions
��+0.754
 Belg+0.726
uss+0.706
rol+0.690
roid+0.676
Neg logit contributions
terness-0.945
thur-0.897
phia-0.856
י�-0.844
renheit-0.839
Token parties
Token ID4671
Feature activation-5.24e-01

Pos logit contributions
��+0.887
 Belg+0.857
uss+0.832
rol+0.813
roid+0.794
Neg logit contributions
terness-1.209
thur-1.150
phia-1.101
י�-1.083
renheit-1.080
Token to
Token ID284
Feature activation+4.44e-01

Pos logit contributions
��+0.336
 Belg+0.321
uss+0.312
rol+0.305
roid+0.298
Neg logit contributions
terness-0.466
thur-0.444
phia-0.425
י�-0.419
chio-0.417
Token the
Token ID262
Feature activation-9.07e-02

Pos logit contributions
terness+0.344
thur+0.325
phia+0.308
י�+0.304
chio+0.301
Neg logit contributions
��-0.336
 Belg-0.325
uss-0.315
rol-0.309
roid-0.305
Token public
Token ID1171
Feature activation-7.29e-01

Pos logit contributions
��+0.055
 Belg+0.053
uss+0.051
rol+0.050
roid+0.049
Neg logit contributions
terness-0.084
thur-0.080
phia-0.076
י�-0.075
chio-0.075
Token interest
Token ID1393
Feature activation-1.34e+00

Pos logit contributions
��+0.469
 Belg+0.449
uss+0.437
rol+0.427
roid+0.418
Neg logit contributions
terness-0.647
thur-0.616
phia-0.589
י�-0.580
chio-0.577
Token litigation
Token ID19284
Feature activation+1.66e-01

Pos logit contributions
��+0.807
 Belg+0.772
uss+0.750
rol+0.731
roid+0.714
Neg logit contributions
terness-1.248
thur-1.191
phia-1.143
י�-1.127
renheit-1.122
Token (
Token ID357
Feature activation+1.00e-01

Pos logit contributions
terness+0.144
thur+0.137
phia+0.131
י�+0.129
chio+0.128
Neg logit contributions
��-0.111
 Belg-0.106
uss-0.103
rol-0.100
roid-0.099
Token situation
Token ID3074
Feature activation+1.67e+00

Pos logit contributions
��+0.062
 Belg+0.060
uss+0.058
rol+0.057
roid+0.056
Neg logit contributions
terness-0.088
thur-0.084
phia-0.080
renheit-0.079
י�-0.079
Token was
Token ID373
Feature activation-5.22e-01

Pos logit contributions
terness+1.469
thur+1.399
phia+1.338
י�+1.320
chio+1.309
Neg logit contributions
��-1.094
 Belg-1.045
uss-1.013
rol-0.991
roid-0.971
Token.
Token ID13
Feature activation+2.06e-01

Pos logit contributions
��+0.348
 Belg+0.336
uss+0.329
rol+0.323
roid+0.316
Neg logit contributions
terness-0.447
thur-0.426
phia-0.406
י�-0.398
chio-0.397
Token Areas
Token ID38662
Feature activation-2.54e+00

Pos logit contributions
terness+0.177
thur+0.168
phia+0.160
chio+0.157
renheit+0.157
Neg logit contributions
��-0.136
 Belg-0.136
uss-0.130
rol-0.128
roid-0.124
Token of
Token ID286
Feature activation-7.04e-01

Pos logit contributions
��+1.621
 Belg+1.606
uss+1.559
rol+1.520
roid+1.490
Neg logit contributions
terness-2.222
thur-2.111
phia-2.038
renheit-2.006
chio-1.986
Token skin
Token ID4168
Feature activation-2.23e+00

Pos logit contributions
��+0.470
 Belg+0.462
uss+0.447
rol+0.438
roid+0.428
Neg logit contributions
terness-0.600
thur-0.572
phia-0.543
renheit-0.535
י�-0.535
Token on
Token ID319
Feature activation-2.62e+00

Pos logit contributions
��+1.389
 Belg+1.365
uss+1.326
rol+1.302
roid+1.276
Neg logit contributions
terness-1.983
thur-1.899
phia-1.821
renheit-1.805
chio-1.786
Token his
Token ID465
Feature activation-1.66e+00

Pos logit contributions
 Belg+1.622
��+1.621
uss+1.582
rol+1.542
roid+1.483
Neg logit contributions
terness-2.349
thur-2.223
phia-2.119
renheit-2.080
chio-2.078
Token face
Token ID1986
Feature activation+1.26e+00

Pos logit contributions
��+1.134
 Belg+1.119
uss+1.097
rol+1.071
roid+1.051
Neg logit contributions
terness-1.389
thur-1.307
phia-1.247
renheit-1.230
chio-1.222
Token and
Token ID290
Feature activation+3.03e-01

Pos logit contributions
terness+1.050
thur+0.997
phia+0.951
י�+0.936
chio+0.931
Neg logit contributions
��-0.872
 Belg-0.839
uss-0.817
rol-0.800
roid-0.785
Token legs
Token ID7405
Feature activation+9.24e-02

Pos logit contributions
terness+0.245
thur+0.233
phia+0.221
י�+0.218
chio+0.217
Neg logit contributions
��-0.220
 Belg-0.211
uss-0.205
rol-0.201
roid-0.197
Tokenast
Token ID459
Feature activation-4.01e+00

Pos logit contributions
��+1.032
 Belg+0.994
uss+0.988
rol+0.966
roid+0.952
Neg logit contributions
terness-1.083
thur-1.016
phia-0.971
י�-0.959
renheit-0.951
Token>
Token ID29
Feature activation+2.66e-02

Pos logit contributions
��+2.911
uss+2.861
rol+2.815
 Belg+2.813
roid+2.771
Neg logit contributions
terness-3.130
thur-2.910
phia-2.804
י�-2.777
renheit-2.747
Token dude
Token ID18396
Feature activation-1.63e+00

Pos logit contributions
terness+0.022
thur+0.021
phia+0.020
י�+0.019
chio+0.019
Neg logit contributions
��-0.019
 Belg-0.018
uss-0.018
rol-0.017
roid-0.017
Token nice
Token ID3621
Feature activation-3.48e+00

Pos logit contributions
��+1.061
 Belg+1.031
uss+1.001
rol+0.977
roid+0.956
Neg logit contributions
terness-1.424
thur-1.348
phia-1.300
י�-1.276
renheit-1.267
Token [
Token ID685
Feature activation-8.39e-01

Pos logit contributions
��+2.279
 Belg+2.217
uss+2.171
rol+2.112
roid+2.069
Neg logit contributions
terness-3.005
thur-2.842
phia-2.731
י�-2.683
renheit-2.676
Token10
Token ID940
Feature activation-3.01e+00

Pos logit contributions
��+0.501
 Belg+0.493
uss+0.485
rol+0.477
roid+0.467
Neg logit contributions
terness-0.776
thur-0.731
phia-0.704
renheit-0.688
י�-0.685
Token:
Token ID25
Feature activation+1.06e+00

Pos logit contributions
 Belg+1.731
uss+1.670
rol+1.649
��+1.636
roid+1.603
Neg logit contributions
terness-2.894
thur-2.685
phia-2.582
renheit-2.527
chio-2.499
Token47
Token ID2857
Feature activation-1.73e+00

Pos logit contributions
terness+0.792
thur+0.748
phia+0.709
י�+0.698
chio+0.692
Neg logit contributions
��-0.832
 Belg-0.801
uss-0.782
rol-0.767
roid-0.754
Token]
Token ID60
Feature activation+5.96e-01

Pos logit contributions
��+0.674
 Belg+0.671
uss+0.646
rol+0.630
roid+0.601
Neg logit contributions
terness-1.959
thur-1.861
phia-1.803
renheit-1.768
י�-1.761
Token <
Token ID1279
Feature activation+3.46e+00

Pos logit contributions
terness+0.436
thur+0.412
phia+0.387
י�+0.383
chio+0.379
Neg logit contributions
��-0.476
 Belg-0.460
uss-0.449
rol-0.440
roid-0.433
Tokensp
Token ID2777
Feature activation-5.26e+00

Pos logit contributions
terness+2.670
thur+2.566
phia+2.424
י�+2.371
chio+2.371
Neg logit contributions
��-2.613
 Belg-2.507
uss-2.402
rol-2.347
roid-2.305
Token));
Token ID18125
Feature activation-2.60e+00

Pos logit contributions
��+1.329
 Belg+1.282
uss+1.266
rol+1.253
roid+1.233
Neg logit contributions
terness-1.465
thur-1.397
phia-1.320
י�-1.306
renheit-1.282
Token RAW
Token ID33782
Feature activation+5.36e-01

Pos logit contributions
��+1.824
 Belg+1.757
uss+1.719
rol+1.678
roid+1.642
Neg logit contributions
terness-2.141
thur-2.046
phia-1.956
י�-1.913
renheit-1.898
Token_
Token ID62
Feature activation-1.26e+00

Pos logit contributions
terness+0.433
thur+0.410
phia+0.390
י�+0.383
chio+0.380
Neg logit contributions
��-0.388
 Belg-0.374
uss-0.365
rol-0.358
roid-0.351
TokenASS
Token ID10705
Feature activation-6.66e+00

Pos logit contributions
��+0.848
 Belg+0.812
uss+0.790
rol+0.772
roid+0.757
Neg logit contributions
terness-1.079
thur-1.026
phia-0.980
י�-0.966
chio-0.959
TokenERT
Token ID17395
Feature activation-2.50e+00

Pos logit contributions
uss+5.194
 Belg+5.119
rol+5.098
roid+4.951
��+4.944
Neg logit contributions
terness-4.737
thur-4.396
phia-4.171
renheit-4.013
chio-3.955
Token(
Token ID7
Feature activation-8.78e-01

Pos logit contributions
��+1.906
 Belg+1.835
uss+1.793
rol+1.764
roid+1.731
Neg logit contributions
terness-1.915
thur-1.812
phia-1.721
י�-1.681
chio-1.674
Tokenit
Token ID270
Feature activation+1.47e-01

Pos logit contributions
��+0.717
 Belg+0.692
uss+0.676
rol+0.664
roid+0.653
Neg logit contributions
terness-0.629
thur-0.592
phia-0.559
י�-0.550
chio-0.546
Token->
Token ID3784
Feature activation-9.30e-01

Pos logit contributions
terness+0.151
thur+0.145
phia+0.140
י�+0.138
chio+0.137
Neg logit contributions
��-0.074
 Belg-0.070
uss-0.068
rol-0.066
roid-0.064
Tokeni
Token ID72
Feature activation-1.68e+00

Pos logit contributions
��+0.680
 Belg+0.654
uss+0.642
rol+0.628
roid+0.617
Neg logit contributions
terness-0.743
thur-0.704
phia-0.669
י�-0.660
chio-0.652
Token()
Token ID3419
Feature activation-1.15e+00

Pos logit contributions
��+1.334
 Belg+1.286
uss+1.257
rol+1.233
roid+1.213
Neg logit contributions
terness-1.237
thur-1.167
phia-1.104
י�-1.085
chio-1.077
Token ==
Token ID6624
Feature activation+1.94e+00

Pos logit contributions
��+0.960
 Belg+0.927
uss+0.907
rol+0.891
roid+0.876
Neg logit contributions
terness-0.807
thur-0.759
phia-0.715
י�-0.702
chio-0.696
Token Dun
Token ID5648
Feature activation-7.66e+00

Pos logit contributions
��+1.346
 Belg+1.328
uss+1.279
rol+1.252
roid+1.216
Neg logit contributions
terness-1.732
thur-1.641
phia-1.565
י�-1.558
renheit-1.550
Tokenbar
Token ID5657
Feature activation-2.79e+00

Pos logit contributions
uss+5.779
 Belg+5.642
rol+5.638
��+5.327
roid+5.304
Neg logit contributions
terness-5.504
thur-5.055
י�-4.999
BLIC-4.801
phia-4.783
Token form
Token ID1296
Feature activation-1.02e+00

Pos logit contributions
��+1.822
 Belg+1.796
uss+1.779
rol+1.737
roid+1.694
Neg logit contributions
terness-2.393
thur-2.249
renheit-2.158
phia-2.155
י�-2.124
Token the
Token ID262
Feature activation-1.68e-01

Pos logit contributions
��+0.747
 Belg+0.721
uss+0.702
rol+0.687
roid+0.673
Neg logit contributions
terness-0.814
thur-0.769
phia-0.730
י�-0.719
renheit-0.716
Token centre
Token ID7372
Feature activation+1.80e-02

Pos logit contributions
��+0.101
 Belg+0.096
uss+0.093
rol+0.090
roid+0.089
Neg logit contributions
terness-0.157
thur-0.150
phia-0.144
י�-0.142
chio-0.141
Token partnership
Token ID10413
Feature activation-3.45e+00

Pos logit contributions
terness+0.015
thur+0.015
phia+0.014
י�+0.014
chio+0.014
Neg logit contributions
��-0.012
 Belg-0.012
uss-0.011
rol-0.011
roid-0.011
Token,
Token ID11
Feature activation-2.64e+00

Pos logit contributions
��+2.146
 Belg+2.146
uss+2.090
rol+2.044
roid+1.965
Neg logit contributions
terness-3.054
thur-2.889
phia-2.776
renheit-2.744
י�-2.727
Token while
Token ID981
Feature activation-4.56e+00

Pos logit contributions
��+1.610
 Belg+1.572
uss+1.522
rol+1.481
roid+1.420
Neg logit contributions
terness-2.426
thur-2.305
phia-2.213
renheit-2.186
י�-2.170
Token Finn
Token ID15368
Feature activation+4.14e+00

Pos logit contributions
��+3.188
 Belg+3.185
uss+3.069
rol+2.990
roid+2.880
Neg logit contributions
terness-3.732
thur-3.519
renheit-3.336
phia-3.331
י�-3.281
Token Russell
Token ID11563
Feature activation-8.70e-01

Pos logit contributions
terness+3.444
thur+3.278
phia+3.129
chio+3.076
י�+3.065
Neg logit contributions
��-2.854
 Belg-2.676
uss-2.593
rol-2.559
roid-2.513
Token and
Token ID290
Feature activation-8.69e-01

Pos logit contributions
��+0.596
 Belg+0.580
uss+0.567
rol+0.553
roid+0.542
Neg logit contributions
terness-0.731
thur-0.692
phia-0.662
י�-0.652
renheit-0.650
Token or
Token ID393
Feature activation+1.43e+00

Pos logit contributions
��+0.335
 Belg+0.324
uss+0.315
rol+0.309
roid+0.303
Neg logit contributions
terness-0.388
thur-0.368
phia-0.350
י�-0.345
chio-0.343
Token 99
Token ID7388
Feature activation-7.86e-02

Pos logit contributions
terness+1.148
thur+1.091
phia+1.037
י�+1.020
chio+1.015
Neg logit contributions
��-1.046
 Belg-0.999
uss-0.972
rol-0.955
roid-0.938
Token%
Token ID4
Feature activation-1.44e+00

Pos logit contributions
��+0.055
 Belg+0.053
uss+0.052
rol+0.050
roid+0.049
Neg logit contributions
terness-0.065
thur-0.062
phia-0.059
י�-0.058
chio-0.058
Token of
Token ID286
Feature activation+3.53e-02

Pos logit contributions
��+1.000
 Belg+0.978
uss+0.953
rol+0.929
roid+0.913
Neg logit contributions
terness-1.187
thur-1.125
phia-1.073
י�-1.059
chio-1.046
Token the
Token ID262
Feature activation+1.81e-01

Pos logit contributions
terness+0.028
thur+0.027
phia+0.026
י�+0.025
chio+0.025
Neg logit contributions
��-0.026
 Belg-0.025
uss-0.024
rol-0.024
roid-0.023
Token people
Token ID661
Feature activation-1.72e+00

Pos logit contributions
terness+0.151
thur+0.143
phia+0.136
י�+0.134
chio+0.134
Neg logit contributions
��-0.127
 Belg-0.121
uss-0.118
rol-0.116
roid-0.114
Token we
Token ID356
Feature activation+1.45e+00

Pos logit contributions
��+1.135
 Belg+1.106
uss+1.076
rol+1.051
roid+1.029
Neg logit contributions
terness-1.493
thur-1.418
phia-1.349
י�-1.336
renheit-1.324
Token so
Token ID523
Feature activation-7.20e-01

Pos logit contributions
terness+1.198
thur+1.141
phia+1.088
chio+1.070
י�+1.070
Neg logit contributions
��-1.035
 Belg-0.976
uss-0.947
rol-0.930
roid-0.913
Token far
Token ID1290
Feature activation-1.48e+00

Pos logit contributions
��+0.457
 Belg+0.444
uss+0.433
rol+0.424
roid+0.412
Neg logit contributions
terness-0.641
thur-0.610
phia-0.584
י�-0.577
renheit-0.573
Token know
Token ID760
Feature activation+2.26e+00

Pos logit contributions
��+1.022
 Belg+1.006
uss+0.978
rol+0.958
roid+0.940
Neg logit contributions
terness-1.232
thur-1.164
phia-1.107
י�-1.093
renheit-1.088
Token to
Token ID284
Feature activation-6.42e-01

Pos logit contributions
terness+1.763
thur+1.674
phia+1.606
י�+1.568
chio+1.563
Neg logit contributions
��-1.714
 Belg-1.596
uss-1.555
rol-1.523
roid-1.493
Token her
Token ID607
Feature activation+1.62e+00

Pos logit contributions
terness+0.210
thur+0.200
phia+0.191
י�+0.189
chio+0.187
Neg logit contributions
��-0.145
 Belg-0.139
uss-0.135
rol-0.131
roid-0.128
Tokender
Token ID1082
Feature activation+5.33e+00

Pos logit contributions
terness+0.712
thur+0.642
phia+0.583
י�+0.566
chio+0.555
Neg logit contributions
��-1.763
 Belg-1.719
uss-1.693
rol-1.671
roid-1.650
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
terness+4.175
thur+4.023
chio+3.784
phia+3.778
י�+3.772
Neg logit contributions
��-3.904
 Belg-3.590
uss-3.495
rol-3.454
roid-3.400
Token Yuri
Token ID38450
Feature activation+1.81e-01

Pos logit contributions
terness+1.627
thur+1.547
phia+1.471
י�+1.457
chio+1.448
Neg logit contributions
��-1.369
 Belg-1.298
uss-1.268
rol-1.240
roid-1.222
Token Kh
Token ID5311
Feature activation-6.33e+00

Pos logit contributions
terness+0.156
thur+0.148
phia+0.142
י�+0.140
chio+0.138
Neg logit contributions
��-0.121
 Belg-0.116
uss-0.113
rol-0.110
roid-0.108
Tokenudi
Token ID47928
Feature activation-6.51e+00

Pos logit contributions
uss+4.506
rol+4.322
��+4.298
roid+4.177
 Belg+4.167
Neg logit contributions
terness-5.016
thur-4.587
י�-4.525
phia-4.483
DEN-4.391
Token,
Token ID11
Feature activation+1.64e+00

Pos logit contributions
��+4.371
uss+4.305
 Belg+4.269
rol+4.233
roid+4.061
Neg logit contributions
terness-5.321
thur-5.008
phia-4.841
renheit-4.735
י�-4.708
Token and
Token ID290
Feature activation+3.67e-02

Pos logit contributions
terness+1.375
thur+1.312
phia+1.246
י�+1.233
chio+1.226
Neg logit contributions
��-1.136
 Belg-1.078
uss-1.050
rol-1.028
roid-1.012
Token his
Token ID465
Feature activation+6.87e-01

Pos logit contributions
terness+0.036
thur+0.035
phia+0.033
י�+0.033
chio+0.033
Neg logit contributions
��-0.020
 Belg-0.019
uss-0.018
rol-0.018
roid-0.017
Token sons
Token ID11989
Feature activation+3.28e+00

Pos logit contributions
terness+0.405
thur+0.376
phia+0.351
י�+0.343
chio+0.339
Neg logit contributions
��-0.648
 Belg-0.629
uss-0.617
rol-0.607
roid-0.598
Token found
Token ID1043
Feature activation-2.29e+00

Pos logit contributions
terness+2.676
thur+2.556
phia+2.429
י�+2.406
chio+2.403
Neg logit contributions
��-2.329
 Belg-2.198
uss-2.141
rol-2.092
roid-2.073
Token of
Token ID286
Feature activation-4.48e+00

Pos logit contributions
��+1.234
 Belg+1.200
uss+1.166
rol+1.138
roid+1.118
Neg logit contributions
terness-1.395
thur-1.338
phia-1.268
י�-1.241
chio-1.240
Token calling
Token ID4585
Feature activation-2.22e+00

Pos logit contributions
 Belg+2.270
��+2.246
uss+2.183
rol+2.088
roid+2.044
Neg logit contributions
terness-4.467
thur-4.261
phia-4.103
renheit-4.072
י�-4.040
Token out
Token ID503
Feature activation-2.76e+00

Pos logit contributions
��+1.370
 Belg+1.362
uss+1.333
rol+1.286
roid+1.258
Neg logit contributions
terness-1.984
thur-1.885
phia-1.802
י�-1.778
renheit-1.768
Token the
Token ID262
Feature activation-2.66e+00

Pos logit contributions
 Belg+1.896
��+1.881
uss+1.836
rol+1.787
roid+1.756
Neg logit contributions
terness-2.271
thur-2.142
phia-2.048
י�-2.008
renheit-1.996
Token hyper
Token ID8718
Feature activation+2.61e-01

Pos logit contributions
��+1.709
 Belg+1.706
uss+1.641
rol+1.591
roid+1.570
Neg logit contributions
terness-2.314
thur-2.195
phia-2.099
י�-2.064
renheit-2.053
Tokenb
Token ID65
Feature activation-7.87e+00

Pos logit contributions
terness+0.203
thur+0.192
phia+0.182
י�+0.180
chio+0.178
Neg logit contributions
��-0.198
 Belg-0.189
uss-0.184
rol-0.180
roid-0.177
Tokenolic
Token ID4160
Feature activation+1.28e+00

Pos logit contributions
uss+5.962
rol+5.827
 Belg+5.694
roid+5.611
��+5.608
Neg logit contributions
terness-5.686
thur-5.267
י�-5.197
phia-5.043
chio-5.032
Token Republican
Token ID3415
Feature activation+3.14e+00

Pos logit contributions
terness+1.115
thur+1.062
phia+1.015
י�+1.003
chio+1.000
Neg logit contributions
��-0.856
 Belg-0.806
uss-0.784
rol-0.770
roid-0.751
Token allegations
Token ID7636
Feature activation-1.09e+00

Pos logit contributions
terness+2.725
thur+2.598
phia+2.490
י�+2.449
chio+2.449
Neg logit contributions
��-2.111
 Belg-1.949
uss-1.889
rol-1.871
roid-1.815
Token MM
Token ID20806
Feature activation+3.88e+00

Pos logit contributions
��+0.766
 Belg+0.744
uss+0.724
rol+0.707
roid+0.693
Neg logit contributions
terness-0.898
thur-0.858
phia-0.821
י�-0.803
chio-0.797
Token legitim
Token ID18262
Feature activation-4.59e-01

Pos logit contributions
terness+3.117
thur+2.969
phia+2.821
י�+2.771
chio+2.766
Neg logit contributions
��-2.847
 Belg-2.691
uss-2.579
rol-2.560
roid-2.498
Token "
Token ID366
Feature activation+6.92e-01

Pos logit contributions
 Belg+2.488
��+2.449
uss+2.420
rol+2.417
roid+2.365
Neg logit contributions
terness-3.350
thur-3.136
phia-2.960
י�-2.907
renheit-2.889
Token94
Token ID5824
Feature activation-2.28e+00

Pos logit contributions
terness+0.522
thur+0.491
phia+0.465
י�+0.456
chio+0.454
Neg logit contributions
��-0.537
 Belg-0.521
uss-0.509
rol-0.499
roid-0.490
Token"]
Token ID8973
Feature activation+9.02e-01

Pos logit contributions
��+1.172
 Belg+1.113
uss+1.076
rol+1.049
roid+1.012
Neg logit contributions
terness-2.325
thur-2.230
phia-2.141
י�-2.108
chio-2.104
Token [
Token ID685
Feature activation-7.18e-01

Pos logit contributions
terness+0.751
thur+0.713
phia+0.679
י�+0.669
chio+0.664
Neg logit contributions
��-0.631
 Belg-0.606
uss-0.590
rol-0.577
roid-0.566
TokenEvent
Token ID9237
Feature activation-4.07e-01

Pos logit contributions
��+0.541
 Belg+0.521
uss+0.509
rol+0.499
roid+0.490
Neg logit contributions
terness-0.559
thur-0.528
phia-0.502
י�-0.493
chio-0.490
TokenDate
Token ID10430
Feature activation-6.30e+00

Pos logit contributions
��+0.364
 Belg+0.353
uss+0.346
rol+0.340
roid+0.335
Neg logit contributions
terness-0.260
thur-0.243
phia-0.228
י�-0.223
chio-0.221
Token "
Token ID366
Feature activation+7.20e-01

Pos logit contributions
uss+3.893
 Belg+3.855
rol+3.828
roid+3.756
��+3.680
Neg logit contributions
terness-5.606
thur-5.156
renheit-4.903
phia-4.892
chio-4.737
Token2016
Token ID5304
Feature activation-2.69e+00

Pos logit contributions
terness+0.489
thur+0.461
phia+0.436
י�+0.430
chio+0.423
Neg logit contributions
��-0.614
 Belg-0.591
uss-0.576
rol-0.567
roid-0.558
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
 Belg+1.650
uss+1.625
��+1.622
rol+1.590
roid+1.526
Neg logit contributions
terness-2.453
thur-2.283
phia-2.195
renheit-2.148
chio-2.117
Token??
Token ID3548
Feature activation-2.19e+00

Pos logit contributions
��+0.936
 Belg+0.915
uss+0.894
rol+0.868
roid+0.855
Neg logit contributions
terness-1.240
thur-1.167
phia-1.127
renheit-1.100
chio-1.094
Token.?
Token ID40791
Feature activation-2.70e+00

Pos logit contributions
��+1.232
 Belg+1.200
uss+1.165
rol+1.126
roid+1.092
Neg logit contributions
terness-2.121
thur-2.011
phia-1.921
chio-1.905
י�-1.888
Token of
Token ID286
Feature activation+9.43e-01

Pos logit contributions
terness+1.147
thur+1.080
י�+1.019
phia+1.016
renheit+1.005
Neg logit contributions
��-1.197
 Belg-1.151
uss-1.125
rol-1.102
roid-1.084
Token modern
Token ID3660
Feature activation-5.63e+00

Pos logit contributions
terness+0.803
thur+0.765
phia+0.730
י�+0.721
chio+0.715
Neg logit contributions
��-0.640
 Belg-0.607
uss-0.594
rol-0.581
roid-0.570
Token architectural
Token ID27070
Feature activation-3.66e+00

Pos logit contributions
 Belg+3.131
��+3.055
uss+2.937
rol+2.836
roid+2.703
Neg logit contributions
terness-5.462
thur-5.122
phia-4.964
chio-4.868
renheit-4.859
Token firms
Token ID9611
Feature activation-6.41e-01

Pos logit contributions
 Belg+2.302
��+2.298
uss+2.206
rol+2.143
roid+2.084
Neg logit contributions
terness-3.258
thur-3.063
phia-2.945
renheit-2.902
י�-2.902
Token and
Token ID290
Feature activation-9.48e-01

Pos logit contributions
��+0.425
 Belg+0.408
uss+0.397
rol+0.388
roid+0.380
Neg logit contributions
terness-0.555
thur-0.530
phia-0.505
י�-0.496
chio-0.496
Token urban
Token ID7876
Feature activation-6.16e+00

Pos logit contributions
��+0.644
 Belg+0.619
uss+0.601
rol+0.588
roid+0.576
Neg logit contributions
terness-0.808
thur-0.768
phia-0.733
י�-0.722
chio-0.717
Token planning
Token ID5410
Feature activation-3.17e+00

Pos logit contributions
 Belg+3.693
��+3.612
uss+3.505
rol+3.355
roid+3.320
Neg logit contributions
terness-5.629
thur-5.312
phia-5.062
chio-5.054
renheit-5.025
Token.
Token ID13
Feature activation-6.76e-01

Pos logit contributions
��+2.066
 Belg+2.032
uss+1.971
rol+1.929
roid+1.877
Neg logit contributions
terness-2.763
thur-2.612
phia-2.488
chio-2.466
י�-2.450
Token
Token ID198
Feature activation+2.24e+00

Pos logit contributions
��+0.459
 Belg+0.455
uss+0.437
rol+0.428
roid+0.416
Neg logit contributions
terness-0.573
thur-0.543
phia-0.515
renheit-0.506
chio-0.505
Token
Token ID198
Feature activation+6.16e-01

Pos logit contributions
terness+1.530
thur+1.456
phia+1.371
י�+1.359
chio+1.342
Neg logit contributions
��-1.900
 Belg-1.801
uss-1.759
rol-1.724
roid-1.701
TokenYet
Token ID11486
Feature activation-1.21e+00

Pos logit contributions
terness+0.464
thur+0.438
phia+0.414
י�+0.407
chio+0.404
Neg logit contributions
��-0.480
 Belg-0.464
uss-0.453
rol-0.445
roid-0.437
Token between
Token ID1022
Feature activation-3.42e+00

Pos logit contributions
��+1.140
 Belg+1.110
uss+1.067
rol+1.043
roid+1.017
Neg logit contributions
terness-1.937
thur-1.841
phia-1.772
י�-1.748
renheit-1.738
Token sub
Token ID850
Feature activation-1.64e+00

Pos logit contributions
��+2.090
 Belg+2.065
uss+1.970
rol+1.941
roid+1.896
Neg logit contributions
terness-3.093
thur-2.928
phia-2.831
renheit-2.777
י�-2.776
Token-
Token ID12
Feature activation-4.11e+00

Pos logit contributions
��+1.114
 Belg+1.072
uss+1.049
rol+1.028
roid+1.007
Neg logit contributions
terness-1.390
thur-1.315
phia-1.260
י�-1.237
chio-1.228
Tokenst
Token ID301
Feature activation-7.79e+00

Pos logit contributions
��+2.871
 Belg+2.842
uss+2.837
rol+2.787
roid+2.755
Neg logit contributions
terness-3.307
thur-3.047
phia-2.953
י�-2.885
renheit-2.885
Tokenages
Token ID1095
Feature activation-2.42e+00

Pos logit contributions
uss+5.722
rol+5.720
roid+5.549
 Belg+5.511
��+5.289
Neg logit contributions
terness-5.907
thur-5.447
phia-5.208
י�-5.025
DEN-4.965
Token Super
Token ID3115
Feature activation-6.40e+00

Pos logit contributions
��+1.640
 Belg+1.599
uss+1.563
rol+1.521
roid+1.490
Neg logit contributions
terness-2.041
thur-1.940
phia-1.865
renheit-1.826
י�-1.814
Token Mario
Token ID10682
Feature activation-8.92e+00

Pos logit contributions
��+4.266
 Belg+4.263
uss+4.118
rol+4.100
roid+4.022
Neg logit contributions
terness-5.324
thur-4.952
phia-4.790
י�-4.757
renheit-4.603
Token 64
Token ID5598
Feature activation-2.69e+00

Pos logit contributions
 Belg+5.127
��+5.093
uss+5.004
roid+4.852
rol+4.825
Neg logit contributions
terness-8.106
thur-7.537
phia-7.328
י�-7.270
renheit-7.128
Token-
Token ID12
Feature activation+4.16e-01

Pos logit contributions
��+1.868
 Belg+1.820
uss+1.779
rol+1.744
roid+1.720
Neg logit contributions
terness-2.213
thur-2.093
phia-2.002
י�-1.971
renheit-1.952
Tokenstyle
Token ID7635
Feature activation-2.34e+00

Pos logit contributions
terness+0.330
thur+0.312
phia+0.297
י�+0.292
chio+0.290
Neg logit contributions
��-0.309
 Belg-0.297
uss-0.289
rol-0.283
roid-0.278
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
��+1.609
 Belg+1.557
uss+1.515
rol+1.483
roid+1.456
Neg logit contributions
terness-1.961
thur-1.862
phia-1.779
י�-1.747
renheit-1.738