TOP ACTIVATIONS
MAX = 11.997

intoler ant attitude had always eng endered a great deal of
switching from a three - man defence to a back four
Richard Painter , the chief White House ethics lawyer during
safe ! Shelby W add ell (@ s
from the W ob urn Superior Court offices to inform immigration
= c v 2 . Ga ussian Bl ur ( gray
investigation into the acqu ired rights of
Simon King , Albion 's Chief Commercial Officer , said :
Amir H oss ain , chief forest official of the Sund
prevent future claims from being filed . Turkey will expel Sale
opening theme of Hats une Mik u : Project Div a
. You can add a product or update inventory
impact would be muted . Add to that some probable guidance
cl osures the Finance Minister filed with the federal Ethics Commissioner
: Dw ark a , Gujarat 36 13 35 , India
Howard Archer , chief UK & European economist at
Kevin Miles , chief executive of the Football Supporters
Jamal H ame edi , chief engineer , Ford Performance .
legislation to strike down the Tory law that allowed the government
page lawsuit Gal ar za filed in November 2010 .

MIN ACTIVATIONS
MIN = -12.066

military and the Department of Homeland Security have set in motion
less beauty played by Mar iel Hem ing way , and
Superior Court offices to inform immigration officials and a det ainer
back ? Sign up for Take Action Now and get three
a bit of a fac el ift . Beyond
important and reliable bi - l ateral partner ,
our latest issue Travel With The Nation Be the
, director of the International Travel Company of the DPRK ,
psycho analysis . This is bullshit . There are
2013 Alec Baldwin 2013 Jason Bat eman
published in N . Eng l . J . Med .,
Guard { ... } pub fn pin () -> Guard ;
conversations with point guard Ben o U dri h , according
actually unacceptable , how non chal antly some say that it
not have qualified for the scholarship under the new rules because
impl Board { pub fn copy _ board ( &
people because you guys feel torn . You re
which are in a nond esc ript pre war building overlooking
In a way , Julia H ahn is the Patty
Is an Acc ompl ished Travel Writer A birth

INTERVAL 5.981 - 11.997
CONTAINS 0.702%

end of the thread . Sew on a button : One
, as you may find yourself stuck with the Token while
on the slippery Cleveland Stadium sod , the Rams ran out
talk of political polarization , Mac ri
as manager Mike Mat heny put it , has been an

INTERVAL -0.035 - 5.981
CONTAINS 49.941%

immersion it is your job to provide it for them
change over time , despite the objection of people who are
Height ), $ SR . Width , $ SR . Height
ice benefit for the team . Phil K essel
with that of The Flash , Super girl , and D

INTERVAL -6.051 - -0.035
CONTAINS 48.631%

s okay to just postpone a situation even if I
between Mid n ighter and Dick Grayson , and , in
players ' fault . And maybe , we should be incentiv
vey , 1950 .) Hitchcock 's unw avering belief in America
The other rock , though , is each other . It

INTERVAL -12.066 - -6.051
CONTAINS 0.726%

With Ghostbusters we learned that if you find a phantom ,
. I van Nep om ny ash ch ikh
- 14 dates in the range of 22 , 000 to
an Emer itus Professor of Economics at Fl inders University ,
in play . If we simply want to write
Token intoler
Token ID20619
Feature activation+1.52e+00

Pos logit contributions
======+0.905
imaru+0.792
brush+0.789
+0.778
+0.764
Neg logit contributions
obal-1.745
acter-1.702
ython-1.632
eware-1.631
 Kimmel-1.605
Tokenant
Token ID415
Feature activation+2.93e+00

Pos logit contributions
======+1.250
imaru+1.173
brush+1.157
+1.151
214+1.139
Neg logit contributions
obal-0.811
acter-0.778
ython-0.724
eware-0.722
 Kimmel-0.716
Token attitude
Token ID9408
Feature activation+5.92e-01

Pos logit contributions
======+1.877
brush+1.714
imaru+1.705
+1.671
214+1.651
Neg logit contributions
obal-2.121
acter-2.065
ython-1.940
eware-1.925
 Kimmel-1.872
Token had
Token ID550
Feature activation+9.01e-01

Pos logit contributions
======+0.373
imaru+0.342
brush+0.336
+0.333
 toget+0.331
Neg logit contributions
obal-0.434
acter-0.422
eware-0.399
ython-0.399
 Kimmel-0.393
Token always
Token ID1464
Feature activation+2.48e+00

Pos logit contributions
======+0.558
imaru+0.507
brush+0.502
+0.500
+0.493
Neg logit contributions
obal-0.672
acter-0.649
eware-0.617
ython-0.616
 Kimmel-0.603
Token eng
Token ID1786
Feature activation+1.20e+01

Pos logit contributions
======+1.542
imaru+1.412
brush+1.411
+1.391
 toget+1.390
Neg logit contributions
obal-1.819
acter-1.747
eware-1.680
ython-1.661
 Kimmel-1.619
Tokenendered
Token ID30398
Feature activation+4.09e+00

Pos logit contributions
======+5.868
rouse+5.757
brush+5.742
imaru+5.524
+5.440
Neg logit contributions
obal-8.825
acter-8.460
ython-8.419
 equivalents-8.322
 Kimmel-8.302
Token a
Token ID257
Feature activation+2.17e+00

Pos logit contributions
======+2.415
brush+2.202
 grievances+2.188
+2.148
 toget+2.111
Neg logit contributions
obal-3.123
acter-3.001
eware-2.883
ython-2.870
 Kimmel-2.784
Token great
Token ID1049
Feature activation+3.34e+00

Pos logit contributions
======+1.357
brush+1.222
imaru+1.215
+1.212
rouse+1.197
Neg logit contributions
obal-1.612
acter-1.565
ython-1.478
eware-1.476
 Kimmel-1.439
Token deal
Token ID1730
Feature activation-9.38e-01

Pos logit contributions
======+2.483
brush+2.288
+2.276
imaru+2.230
 grievances+2.224
Neg logit contributions
obal-2.058
acter-1.971
ython-1.848
eware-1.845
 Kimmel-1.804
Token of
Token ID286
Feature activation+4.53e-01

Pos logit contributions
obal+0.714
acter+0.693
eware+0.658
ython+0.658
 Kimmel+0.651
Neg logit contributions
======-0.566
imaru-0.516
brush-0.508
-0.504
-0.498
Token switching
Token ID15430
Feature activation+2.11e-01

Pos logit contributions
======+0.258
imaru+0.236
brush+0.235
+0.233
214+0.231
Neg logit contributions
obal-0.243
acter-0.234
eware-0.222
ython-0.221
 Kimmel-0.217
Token from
Token ID422
Feature activation-2.15e-01

Pos logit contributions
======+0.132
imaru+0.121
brush+0.119
+0.118
 toget+0.117
Neg logit contributions
obal-0.156
acter-0.151
ython-0.143
eware-0.143
 Kimmel-0.141
Token a
Token ID257
Feature activation+3.00e+00

Pos logit contributions
obal+0.168
acter+0.163
eware+0.155
ython+0.155
 Kimmel+0.153
Neg logit contributions
======-0.125
imaru-0.113
brush-0.112
-0.110
214-0.109
Token three
Token ID1115
Feature activation+3.53e+00

Pos logit contributions
======+1.596
brush+1.427
imaru+1.393
214+1.383
+1.380
Neg logit contributions
obal-2.479
acter-2.427
eware-2.294
ython-2.287
 Kimmel-2.247
Token-
Token ID12
Feature activation+9.58e+00

Pos logit contributions
======+1.927
brush+1.722
imaru+1.717
+1.688
+1.662
Neg logit contributions
obal-2.873
acter-2.796
eware-2.661
ython-2.657
 Kimmel-2.636
Tokenman
Token ID805
Feature activation+1.15e+01

Pos logit contributions
======+4.546
brush+4.364
214+3.959
onto+3.902
cade+3.897
Neg logit contributions
obal-7.765
acter-7.592
 Kimmel-7.289
eware-7.256
ython-7.219
Token defence
Token ID9366
Feature activation+3.21e+00

Pos logit contributions
======+6.270
brush+5.734
cade+5.496
214+5.414
▬▬+5.311
Neg logit contributions
obal-8.309
acter-8.204
ython-7.741
eware-7.635
offer-7.568
Token to
Token ID284
Feature activation+3.08e+00

Pos logit contributions
======+1.718
brush+1.527
imaru+1.522
 toget+1.498
+1.487
Neg logit contributions
obal-2.644
acter-2.572
ython-2.450
eware-2.446
 Kimmel-2.416
Token a
Token ID257
Feature activation+2.26e+00

Pos logit contributions
======+1.842
brush+1.664
imaru+1.638
+1.611
214+1.610
Neg logit contributions
obal-2.330
acter-2.264
eware-2.147
ython-2.139
 Kimmel-2.099
Token back
Token ID736
Feature activation+2.19e+00

Pos logit contributions
======+1.245
brush+1.113
imaru+1.093
+1.090
+1.083
Neg logit contributions
obal-1.831
acter-1.791
eware-1.691
ython-1.681
 Kimmel-1.659
Token four
Token ID1440
Feature activation+3.62e+00

Pos logit contributions
======+1.282
brush+1.160
imaru+1.152
+1.132
214+1.125
Neg logit contributions
obal-1.691
acter-1.645
eware-1.551
ython-1.551
 Kimmel-1.544
Token
Token ID198
Feature activation+7.97e-01

Pos logit contributions
======+0.618
imaru+0.519
brush+0.517
214+0.513
+0.501
Neg logit contributions
obal-1.496
acter-1.465
eware-1.409
ython-1.400
 Kimmel-1.377
TokenRichard
Token ID22245
Feature activation-3.16e+00

Pos logit contributions
======+0.464
imaru+0.419
brush+0.412
+0.411
214+0.404
Neg logit contributions
obal-0.626
acter-0.608
eware-0.579
ython-0.578
 Kimmel-0.572
Token Painter
Token ID49102
Feature activation-3.62e-01

Pos logit contributions
obal+2.127
acter+2.045
 Kimmel+1.933
ython+1.930
eware+1.926
Neg logit contributions
======-2.186
imaru-2.016
brush-1.978
-1.974
-1.963
Token,
Token ID11
Feature activation+4.14e-01

Pos logit contributions
obal+0.275
acter+0.267
eware+0.254
ython+0.253
 Kimmel+0.251
Neg logit contributions
======-0.219
imaru-0.200
brush-0.196
-0.194
-0.192
Token the
Token ID262
Feature activation+1.56e+00

Pos logit contributions
======+0.262
imaru+0.240
brush+0.237
+0.235
 toget+0.231
Neg logit contributions
obal-0.302
acter-0.293
eware-0.277
ython-0.277
 Kimmel-0.274
Token chief
Token ID4039
Feature activation+1.15e+01

Pos logit contributions
======+0.868
brush+0.777
+0.773
imaru+0.771
214+0.754
Neg logit contributions
obal-1.258
acter-1.216
ython-1.169
eware-1.163
 Kimmel-1.144
Token White
Token ID2635
Feature activation-6.34e-01

Pos logit contributions
======+3.830
+3.693
brush+3.624
 grievances+3.403
214+3.222
Neg logit contributions
obal-10.645
acter-10.153
ython-10.033
 Pigs-9.886
 Kimmel-9.846
Token House
Token ID2097
Feature activation-9.76e-01

Pos logit contributions
obal+0.590
acter+0.579
ython+0.553
eware+0.549
 Kimmel+0.543
Neg logit contributions
======-0.276
brush-0.241
imaru-0.241
-0.239
214-0.231
Token ethics
Token ID14458
Feature activation+1.94e+00

Pos logit contributions
obal+0.844
acter+0.825
eware+0.788
ython+0.785
 Kimmel+0.780
Neg logit contributions
======-0.487
imaru-0.438
-0.419
-0.418
brush-0.418
Token lawyer
Token ID6853
Feature activation+3.96e+00

Pos logit contributions
======+1.072
brush+0.982
imaru+0.967
+0.961
214+0.934
Neg logit contributions
obal-1.543
acter-1.492
 Kimmel-1.424
ython-1.423
eware-1.416
Token during
Token ID1141
Feature activation+1.81e+00

Pos logit contributions
======+2.192
imaru+1.987
brush+1.969
+1.940
 toget+1.916
Neg logit contributions
obal-3.170
acter-3.093
ython-2.950
eware-2.938
 Kimmel-2.893
Token safe
Token ID3338
Feature activation-3.99e-01

Pos logit contributions
obal+1.438
acter+1.383
eware+1.288
ython+1.288
 Kimmel+1.274
Neg logit contributions
======-1.933
imaru-1.803
brush-1.777
-1.768
-1.751
Token!
Token ID0
Feature activation+1.55e+00

Pos logit contributions
obal+0.305
acter+0.296
ython+0.281
eware+0.280
 Kimmel+0.278
Neg logit contributions
======-0.240
imaru-0.218
brush-0.214
-0.212
 toget-0.210
Token
Token ID851
Feature activation+2.85e+00

Pos logit contributions
======+0.968
imaru+0.883
brush+0.867
+0.861
+0.856
Neg logit contributions
obal-1.138
acter-1.117
ython-1.053
eware-1.048
 Kimmel-1.033
Token Shelby
Token ID35053
Feature activation+4.84e+00

Pos logit contributions
======+2.021
imaru+1.859
brush+1.840
+1.830
+1.815
Neg logit contributions
obal-1.853
acter-1.795
ython-1.694
eware-1.689
 Kimmel-1.635
Token W
Token ID370
Feature activation+2.73e+00

Pos logit contributions
======+3.356
imaru+3.121
brush+3.102
+3.068
214+3.026
Neg logit contributions
obal-3.158
acter-3.106
eware-2.894
ython-2.891
 Kimmel-2.773
Tokenadd
Token ID2860
Feature activation+1.15e+01

Pos logit contributions
======+1.780
imaru+1.632
brush+1.618
+1.596
214+1.581
Neg logit contributions
obal-1.910
acter-1.861
eware-1.750
ython-1.749
 Kimmel-1.733
Tokenell
Token ID695
Feature activation+3.80e+00

Pos logit contributions
======+6.371
brush+6.064
imaru+5.965
214+5.697
+5.673
Neg logit contributions
obal-8.041
acter-7.674
ython-7.500
 Kimmel-7.375
 equivalents-7.340
Token
Token ID14519
Feature activation+3.43e+00

Pos logit contributions
======+2.448
imaru+2.246
brush+2.224
+2.215
+2.193
Neg logit contributions
obal-2.705
acter-2.649
eware-2.478
ython-2.476
 Kimmel-2.422
Token
Token ID234
Feature activation+4.41e+00

Pos logit contributions
======+2.636
imaru+2.456
brush+2.417
+2.413
+2.370
Neg logit contributions
obal-2.019
acter-1.945
eware-1.822
ython-1.817
 Kimmel-1.816
Token (@
Token ID4275
Feature activation+7.57e-01

Pos logit contributions
======+2.847
imaru+2.580
+2.575
+2.553
brush+2.549
Neg logit contributions
obal-3.142
acter-3.069
eware-2.894
ython-2.876
 Kimmel-2.824
Tokens
Token ID82
Feature activation-9.69e-01

Pos logit contributions
======+0.467
imaru+0.427
brush+0.420
+0.417
+0.412
Neg logit contributions
obal-0.565
acter-0.548
eware-0.519
ython-0.519
 Kimmel-0.516
Token from
Token ID422
Feature activation-1.85e+00

Pos logit contributions
======+0.012
imaru+0.011
brush+0.011
+0.011
 toget+0.011
Neg logit contributions
obal-0.016
acter-0.016
ython-0.015
eware-0.015
 Kimmel-0.015
Token the
Token ID262
Feature activation+8.80e-01

Pos logit contributions
obal+1.296
acter+1.255
eware+1.180
ython+1.179
 Kimmel+1.179
Neg logit contributions
======-1.227
imaru-1.127
brush-1.110
-1.103
-1.093
Token W
Token ID370
Feature activation+2.67e-01

Pos logit contributions
======+0.551
imaru+0.506
brush+0.497
+0.494
214+0.489
Neg logit contributions
obal-0.642
acter-0.625
ython-0.596
eware-0.593
 Kimmel-0.579
Tokenob
Token ID672
Feature activation+1.77e+00

Pos logit contributions
======+0.174
imaru+0.160
brush+0.157
+0.156
214+0.154
Neg logit contributions
obal-0.190
acter-0.184
eware-0.174
ython-0.174
 Kimmel-0.172
Tokenurn
Token ID700
Feature activation+1.80e+00

Pos logit contributions
======+1.338
imaru+1.263
brush+1.238
+1.214
214+1.211
Neg logit contributions
obal-1.055
acter-1.004
 Kimmel-0.953
ython-0.947
eware-0.945
Token Superior
Token ID22953
Feature activation+1.13e+01

Pos logit contributions
======+1.168
imaru+1.077
brush+1.066
+1.061
214+1.047
Neg logit contributions
obal-1.265
acter-1.232
ython-1.161
eware-1.160
 Kimmel-1.139
Token Court
Token ID3078
Feature activation+3.26e+00

Pos logit contributions
======+2.656
imaru+2.212
brush+2.088
214+2.087
cade+2.041
Neg logit contributions
obal-11.767
acter-11.562
ython-11.206
eware-10.962
offer-10.889
Token offices
Token ID9730
Feature activation-1.20e+00

Pos logit contributions
======+1.922
imaru+1.748
brush+1.715
+1.703
214+1.689
Neg logit contributions
obal-2.511
acter-2.443
ython-2.327
eware-2.302
 Kimmel-2.278
Token to
Token ID284
Feature activation-4.21e-01

Pos logit contributions
obal+0.891
acter+0.864
eware+0.818
ython+0.818
 Kimmel+0.811
Neg logit contributions
======-0.741
imaru-0.678
brush-0.665
-0.661
-0.653
Token inform
Token ID4175
Feature activation-2.94e+00

Pos logit contributions
obal+0.302
acter+0.292
ython+0.277
eware+0.276
 Kimmel+0.272
Neg logit contributions
======-0.273
imaru-0.251
brush-0.247
-0.245
-0.242
Token immigration
Token ID6272
Feature activation-1.15e+01

Pos logit contributions
obal+2.004
acter+1.946
eware+1.837
 Kimmel+1.834
ython+1.822
Neg logit contributions
======-1.984
imaru-1.821
brush-1.794
-1.774
 toget-1.773
Token =
Token ID796
Feature activation+2.56e+00

Pos logit contributions
======+1.363
brush+1.278
imaru+1.273
214+1.269
+1.215
Neg logit contributions
obal-2.401
acter-2.371
eware-2.245
ython-2.217
 Kimmel-2.213
Token c
Token ID269
Feature activation+1.24e+00

Pos logit contributions
======+0.997
brush+0.863
214+0.842
imaru+0.829
cade+0.804
Neg logit contributions
obal-2.485
acter-2.423
ython-2.329
eware-2.319
 Kimmel-2.278
Tokenv
Token ID85
Feature activation+4.24e+00

Pos logit contributions
======+0.800
brush+0.734
imaru+0.722
214+0.714
+0.707
Neg logit contributions
obal-0.883
acter-0.868
eware-0.818
 Kimmel-0.811
ython-0.805
Token2
Token ID17
Feature activation+1.73e+00

Pos logit contributions
======+0.714
214+0.568
brush+0.494
imaru+0.423
+0.401
Neg logit contributions
obal-5.072
acter-5.011
eware-4.846
 Pigs-4.767
 Kimmel-4.766
Token.
Token ID764
Feature activation+3.70e+00

Pos logit contributions
======+0.826
214+0.731
brush+0.730
imaru+0.725
+0.707
Neg logit contributions
obal-1.536
acter-1.508
eware-1.442
ython-1.426
 Kimmel-1.406
Token Ga
Token ID12822
Feature activation+1.12e+01

Pos logit contributions
======+1.943
brush+1.763
imaru+1.732
214+1.702
 toget+1.689
Neg logit contributions
obal-3.041
acter-2.973
eware-2.837
ython-2.826
 Kimmel-2.797
Tokenussian
Token ID31562
Feature activation+6.52e+00

Pos logit contributions
======+3.351
brush+2.935
214+2.818
utation+2.772
iety+2.549
Neg logit contributions
 Kimmel-10.808
 Pigs-10.716
 Lilly-10.683
obal-10.476
acter-10.473
TokenBl
Token ID3629
Feature activation+4.45e+00

Pos logit contributions
======+3.402
brush+3.176
imaru+3.077
214+3.009
+2.965
Neg logit contributions
acter-5.441
obal-5.161
eware-5.128
ython-5.006
oppers-4.891
Tokenur
Token ID333
Feature activation+7.00e+00

Pos logit contributions
======+3.606
imaru+3.504
brush+3.476
214+3.374
rouse+3.307
Neg logit contributions
obal-2.227
acter-2.161
 Pigs-2.146
 Kimmel-2.083
ython-2.015
Token (
Token ID357
Feature activation+4.33e+00

Pos logit contributions
======+3.476
214+3.220
brush+3.152
imaru+3.055
+3.034
Neg logit contributions
obal-5.913
acter-5.745
eware-5.576
ython-5.485
ngth-5.390
Token gray
Token ID12768
Feature activation+5.07e+00

Pos logit contributions
======+2.752
brush+2.636
imaru+2.595
 grievances+2.477
214+2.461
Neg logit contributions
obal-2.997
acter-2.958
 Pigs-2.794
eware-2.793
ython-2.778
Token investigation
Token ID3645
Feature activation+3.31e+00

Pos logit contributions
obal+0.461
acter+0.445
ython+0.423
eware+0.421
 Kimmel+0.419
Neg logit contributions
======-0.384
imaru-0.351
brush-0.345
-0.344
214-0.338
Token into
Token ID656
Feature activation+4.40e+00

Pos logit contributions
======+1.479
imaru+1.313
brush+1.271
+1.253
214+1.237
Neg logit contributions
obal-3.008
acter-2.917
ython-2.809
eware-2.792
 Kimmel-2.749
Token the
Token ID262
Feature activation+3.51e+00

Pos logit contributions
======+2.621
imaru+2.374
brush+2.369
 grievances+2.359
+2.323
Neg logit contributions
obal-3.282
acter-3.228
ython-3.067
eware-3.035
 Kimmel-2.978
Token
Token ID564
Feature activation+2.32e-02

Pos logit contributions
======+2.144
+1.920
 grievances+1.916
imaru+1.914
brush+1.906
Neg logit contributions
obal-2.585
acter-2.529
ython-2.423
eware-2.416
 Kimmel-2.342
Token
Token ID250
Feature activation+1.34e+00

Pos logit contributions
======+0.015
imaru+0.014
brush+0.014
+0.014
+0.014
Neg logit contributions
obal-0.016
acter-0.016
eware-0.015
ython-0.015
 Kimmel-0.015
Tokenacqu
Token ID43561
Feature activation+1.12e+01

Pos logit contributions
======+0.830
brush+0.746
imaru+0.744
+0.742
214+0.732
Neg logit contributions
obal-0.994
acter-0.962
ython-0.917
eware-0.914
 Kimmel-0.912
Tokenired
Token ID1202
Feature activation-1.06e+00

Pos logit contributions
======+4.217
imaru+4.140
brush+4.011
cade+3.999
214+3.870
Neg logit contributions
 Kimmel-9.228
obal-9.199
acter-9.104
 Pigs-9.076
 equivalents-8.851
Token rights
Token ID2489
Feature activation+2.85e+00

Pos logit contributions
obal+0.799
acter+0.776
eware+0.736
ython+0.735
 Kimmel+0.729
Neg logit contributions
======-0.641
imaru-0.587
brush-0.575
-0.570
-0.564
Token
Token ID447
Feature activation+1.08e-01

Pos logit contributions
======+1.701
imaru+1.529
brush+1.509
+1.508
 toget+1.481
Neg logit contributions
obal-2.186
acter-2.131
eware-2.016
ython-2.013
 Kimmel-1.994
Token
Token ID251
Feature activation+1.52e-02

Pos logit contributions
======+0.073
imaru+0.067
+0.066
brush+0.066
+0.065
Neg logit contributions
obal-0.074
acter-0.072
eware-0.068
ython-0.068
 Kimmel-0.067
Token of
Token ID286
Feature activation+3.08e+00

Pos logit contributions
======+0.009
imaru+0.008
brush+0.008
+0.008
+0.008
Neg logit contributions
obal-0.011
acter-0.011
eware-0.011
ython-0.011
 Kimmel-0.010
TokenSimon
Token ID35475
Feature activation-2.43e+00

Pos logit contributions
obal+0.992
acter+0.965
eware+0.924
ython+0.921
 Kimmel+0.916
Neg logit contributions
======-0.547
imaru-0.497
brush-0.477
 toget-0.476
-0.472
Token King
Token ID2677
Feature activation-1.13e+00

Pos logit contributions
obal+1.576
acter+1.512
 Kimmel+1.445
eware+1.427
ython+1.423
Neg logit contributions
======-1.729
imaru-1.592
-1.564
 toget-1.561
brush-1.556
Token,
Token ID11
Feature activation+1.16e+00

Pos logit contributions
obal+0.846
acter+0.817
eware+0.773
ython+0.772
 Kimmel+0.769
Neg logit contributions
======-0.697
imaru-0.641
-0.621
brush-0.620
 toget-0.615
Token Albion
Token ID47995
Feature activation+1.03e+00

Pos logit contributions
======+0.691
imaru+0.629
brush+0.619
+0.614
+0.606
Neg logit contributions
obal-0.890
acter-0.865
ython-0.821
eware-0.821
 Kimmel-0.812
Token's
Token ID338
Feature activation+1.75e+00

Pos logit contributions
======+0.627
imaru+0.572
brush+0.563
+0.559
+0.551
Neg logit contributions
obal-0.780
acter-0.758
eware-0.718
ython-0.718
 Kimmel-0.711
Token Chief
Token ID5953
Feature activation+1.11e+01

Pos logit contributions
======+1.087
imaru+0.988
brush+0.975
+0.971
214+0.958
Neg logit contributions
obal-1.288
acter-1.257
ython-1.194
eware-1.189
 Kimmel-1.168
Token Commercial
Token ID22724
Feature activation-1.07e+00

Pos logit contributions
======+5.899
cade+5.343
 Companion+5.333
+5.309
 Membership+5.230
Neg logit contributions
acter-8.091
obal-7.920
ython-7.765
eware-7.667
 Kimmel-7.454
Token Officer
Token ID10391
Feature activation+3.16e+00

Pos logit contributions
obal+0.873
acter+0.849
eware+0.807
ython+0.807
 Kimmel+0.802
Neg logit contributions
======-0.585
imaru-0.528
brush-0.517
-0.513
-0.507
Token,
Token ID11
Feature activation-6.88e-01

Pos logit contributions
======+1.859
imaru+1.695
brush+1.670
+1.662
214+1.635
Neg logit contributions
obal-2.422
acter-2.371
ython-2.251
eware-2.243
 Kimmel-2.185
Token said
Token ID531
Feature activation+8.21e-01

Pos logit contributions
obal+0.459
acter+0.443
eware+0.417
ython+0.417
 Kimmel+0.413
Neg logit contributions
======-0.481
imaru-0.445
brush-0.437
-0.435
-0.430
Token:
Token ID25
Feature activation+1.43e+00

Pos logit contributions
======+0.486
imaru+0.443
brush+0.433
+0.431
+0.426
Neg logit contributions
obal-0.634
acter-0.615
eware-0.585
ython-0.584
 Kimmel-0.581
Token Amir
Token ID43931
Feature activation-8.84e-02

Pos logit contributions
obal+1.351
acter+1.303
eware+1.227
ython+1.226
 Kimmel+1.225
Neg logit contributions
======-1.356
imaru-1.258
brush-1.230
-1.225
-1.218
Token H
Token ID367
Feature activation+1.71e+00

Pos logit contributions
obal+0.057
acter+0.055
eware+0.052
ython+0.051
 Kimmel+0.051
Neg logit contributions
======-0.064
imaru-0.059
brush-0.058
-0.058
214-0.057
Tokenoss
Token ID793
Feature activation+3.94e-02

Pos logit contributions
======+1.175
imaru+1.098
brush+1.072
214+1.052
+1.050
Neg logit contributions
obal-1.130
acter-1.096
eware-1.039
 Kimmel-1.034
ython-1.033
Tokenain
Token ID391
Feature activation+6.97e-01

Pos logit contributions
======+0.032
imaru+0.030
brush+0.030
+0.029
214+0.029
Neg logit contributions
obal-0.022
acter-0.021
eware-0.019
ython-0.019
 Kimmel-0.019
Token,
Token ID11
Feature activation+3.67e+00

Pos logit contributions
======+0.420
imaru+0.387
brush+0.378
+0.373
214+0.368
Neg logit contributions
obal-0.529
acter-0.514
eware-0.488
ython-0.487
 Kimmel-0.483
Token chief
Token ID4039
Feature activation+1.08e+01

Pos logit contributions
======+2.255
brush+2.050
imaru+2.045
+2.030
 toget+1.977
Neg logit contributions
obal-2.695
acter-2.632
eware-2.506
ython-2.496
 Kimmel-2.437
Token forest
Token ID8222
Feature activation-4.78e-01

Pos logit contributions
======+6.051
+5.618
brush+5.610
 grievances+5.418
214+5.336
Neg logit contributions
obal-7.666
acter-7.553
ython-7.220
 Kimmel-7.112
eware-7.016
Token official
Token ID1743
Feature activation+4.14e+00

Pos logit contributions
obal+0.361
acter+0.350
ython+0.332
eware+0.332
 Kimmel+0.330
Neg logit contributions
======-0.290
imaru-0.265
brush-0.261
-0.259
214-0.255
Token of
Token ID286
Feature activation-4.58e-01

Pos logit contributions
======+2.311
brush+2.086
imaru+2.086
+2.053
+2.028
Neg logit contributions
obal-3.294
acter-3.228
ython-3.056
eware-3.030
 Kimmel-2.998
Token the
Token ID262
Feature activation-1.60e+00

Pos logit contributions
obal+0.309
acter+0.299
eware+0.282
ython+0.281
 Kimmel+0.279
Neg logit contributions
======-0.316
imaru-0.292
brush-0.287
-0.285
-0.282
Token Sund
Token ID3309
Feature activation+3.15e+00

Pos logit contributions
obal+1.139
acter+1.103
eware+1.042
ython+1.041
 Kimmel+1.033
Neg logit contributions
======-1.042
imaru-0.959
brush-0.941
-0.935
-0.925
Token prevent
Token ID2948
Feature activation+1.45e+00

Pos logit contributions
======+1.207
imaru+1.099
+1.078
brush+1.077
 toget+1.075
Neg logit contributions
obal-1.538
acter-1.496
ython-1.435
eware-1.422
 Kimmel-1.409
Token future
Token ID2003
Feature activation-4.18e+00

Pos logit contributions
======+0.893
imaru+0.815
brush+0.800
+0.799
214+0.794
Neg logit contributions
obal-1.086
acter-1.056
ython-1.006
eware-1.000
 Kimmel-0.981
Token claims
Token ID3667
Feature activation+2.81e+00

Pos logit contributions
obal+2.942
acter+2.834
 Kimmel+2.682
eware+2.676
ython+2.661
Neg logit contributions
======-2.721
imaru-2.538
brush-2.461
-2.448
 toget-2.427
Token from
Token ID422
Feature activation-6.86e-01

Pos logit contributions
======+1.650
imaru+1.496
brush+1.466
+1.462
 toget+1.453
Neg logit contributions
obal-2.176
acter-2.121
ython-2.009
eware-2.009
 Kimmel-1.989
Token being
Token ID852
Feature activation-1.12e+00

Pos logit contributions
obal+0.466
acter+0.452
eware+0.424
ython+0.423
 Kimmel+0.423
Neg logit contributions
======-0.469
imaru-0.433
brush-0.426
-0.423
-0.420
Token filed
Token ID5717
Feature activation+1.08e+01

Pos logit contributions
obal+0.867
acter+0.843
eware+0.798
 Kimmel+0.796
ython+0.796
Neg logit contributions
======-0.661
imaru-0.601
brush-0.588
-0.581
-0.574
Token.
Token ID13
Feature activation+4.05e+00

Pos logit contributions
======+5.066
 toget+4.630
brush+4.443
214+4.427
+4.408
Neg logit contributions
obal-8.981
acter-8.686
ython-8.261
eware-8.184
 Kimmel-8.144
Token Turkey
Token ID7137
Feature activation-1.06e+00

Pos logit contributions
======+2.225
imaru+1.992
+1.981
214+1.947
brush+1.942
Neg logit contributions
obal-3.295
acter-3.212
ython-3.073
eware-3.065
 Kimmel-2.956
Token will
Token ID481
Feature activation-1.03e-01

Pos logit contributions
obal+0.775
acter+0.752
eware+0.712
ython+0.711
 Kimmel+0.704
Neg logit contributions
======-0.670
imaru-0.614
brush-0.603
-0.600
-0.592
Token expel
Token ID46466
Feature activation-2.94e-01

Pos logit contributions
obal+0.075
acter+0.073
ython+0.069
eware+0.069
 Kimmel+0.069
Neg logit contributions
======-0.065
imaru-0.060
brush-0.058
-0.058
 toget-0.058
Token Sale
Token ID16467
Feature activation-8.69e-01

Pos logit contributions
obal+0.214
acter+0.208
ython+0.197
eware+0.197
 Kimmel+0.194
Neg logit contributions
======-0.187
imaru-0.172
brush-0.169
-0.168
214-0.166
Token opening
Token ID4756
Feature activation+3.12e+00

Pos logit contributions
======+0.465
imaru+0.431
brush+0.422
+0.421
+0.416
Neg logit contributions
obal-0.495
acter-0.479
eware-0.455
ython-0.453
 Kimmel-0.447
Token theme
Token ID7505
Feature activation+1.93e+00

Pos logit contributions
======+1.632
imaru+1.460
brush+1.453
+1.448
+1.419
Neg logit contributions
obal-2.587
acter-2.505
ython-2.407
eware-2.387
 Kimmel-2.350
Token of
Token ID286
Feature activation+6.66e-01

Pos logit contributions
======+1.160
imaru+1.058
brush+1.040
+1.033
 toget+1.023
Neg logit contributions
obal-1.468
acter-1.422
ython-1.358
eware-1.353
 Kimmel-1.333
Token Hats
Token ID37934
Feature activation+1.56e+00

Pos logit contributions
======+0.448
imaru+0.414
brush+0.406
+0.404
+0.399
Neg logit contributions
obal-0.460
acter-0.445
eware-0.420
ython-0.419
 Kimmel-0.416
Tokenune
Token ID1726
Feature activation+3.60e+00

Pos logit contributions
======+0.667
imaru+0.592
brush+0.568
214+0.543
+0.539
Neg logit contributions
obal-1.471
acter-1.422
eware-1.372
 Kimmel-1.370
ython-1.365
Token Mik
Token ID17722
Feature activation+1.07e+01

Pos logit contributions
======+1.712
imaru+1.566
brush+1.509
+1.480
214+1.464
Neg logit contributions
obal-3.219
acter-3.061
eware-2.955
ython-2.950
 Kimmel-2.865
Tokenu
Token ID84
Feature activation+4.65e+00

Pos logit contributions
======+3.666
imaru+3.479
brush+3.135
azaki+3.126
cade+3.044
Neg logit contributions
obal-9.955
 Pigs-9.613
acter-9.581
 Kimmel-9.555
 equivalents-9.446
Token:
Token ID25
Feature activation+2.78e+00

Pos logit contributions
======+2.551
imaru+2.306
+2.251
brush+2.246
+2.231
Neg logit contributions
obal-3.765
acter-3.641
ython-3.471
eware-3.460
 Kimmel-3.429
Token Project
Token ID4935
Feature activation+2.54e+00

Pos logit contributions
======+1.807
imaru+1.661
brush+1.637
+1.618
 toget+1.603
Neg logit contributions
obal-1.988
acter-1.924
eware-1.817
ython-1.816
 Kimmel-1.804
Token Div
Token ID4777
Feature activation+6.63e+00

Pos logit contributions
======+1.498
imaru+1.371
brush+1.333
+1.318
214+1.308
Neg logit contributions
obal-1.981
acter-1.928
eware-1.844
ython-1.825
 Kimmel-1.793
Tokena
Token ID64
Feature activation+2.41e+00

Pos logit contributions
======+3.094
imaru+2.785
brush+2.707
214+2.661
cade+2.591
Neg logit contributions
obal-5.754
acter-5.532
 Kimmel-5.477
eware-5.440
 Pigs-5.414
Token.
Token ID13
Feature activation+6.22e-01

Pos logit contributions
======+0.722
imaru+0.653
brush+0.643
+0.634
 toget+0.634
Neg logit contributions
obal-0.991
acter-0.965
eware-0.915
ython-0.914
 Kimmel-0.907
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
======+0.346
imaru+0.309
brush+0.305
+0.303
214+0.299
Neg logit contributions
obal-0.505
acter-0.493
ython-0.468
eware-0.468
 Kimmel-0.460
Token
Token ID198
Feature activation+5.56e-01

Pos logit contributions
obal+0.130
acter+0.127
eware+0.122
ython+0.122
 Kimmel+0.120
Neg logit contributions
======-0.059
imaru-0.051
brush-0.050
-0.050
214-0.049
TokenYou
Token ID1639
Feature activation+3.77e+00

Pos logit contributions
======+0.299
imaru+0.265
brush+0.262
+0.261
214+0.257
Neg logit contributions
obal-0.463
acter-0.450
ython-0.430
eware-0.429
 Kimmel-0.427
Token can
Token ID460
Feature activation+3.02e+00

Pos logit contributions
======+2.007
imaru+1.795
+1.777
brush+1.776
+1.724
Neg logit contributions
obal-3.095
acter-3.034
ython-2.887
eware-2.879
 Kimmel-2.866
Token add
Token ID751
Feature activation+1.06e+01

Pos logit contributions
======+1.855
imaru+1.676
brush+1.653
+1.635
 toget+1.631
Neg logit contributions
obal-2.255
acter-2.176
ython-2.082
eware-2.076
 Kimmel-2.070
Token a
Token ID257
Feature activation+5.23e+00

Pos logit contributions
======+6.231
 grievances+5.525
imaru+5.505
+5.490
brush+5.425
Neg logit contributions
obal-7.286
acter-7.225
ython-7.028
eware-6.942
 Kimmel-6.888
Token product
Token ID1720
Feature activation+5.38e+00

Pos logit contributions
======+3.356
imaru+3.064
+3.029
brush+2.978
214+2.977
Neg logit contributions
obal-3.648
acter-3.598
eware-3.421
ython-3.412
 Kimmel-3.359
Token or
Token ID393
Feature activation+4.70e+00

Pos logit contributions
======+2.998
imaru+2.736
brush+2.691
+2.640
214+2.625
Neg logit contributions
obal-4.219
acter-4.107
ython-3.900
eware-3.887
 Kimmel-3.877
Token update
Token ID4296
Feature activation+5.95e+00

Pos logit contributions
======+2.922
imaru+2.634
brush+2.609
+2.596
214+2.525
Neg logit contributions
obal-3.449
acter-3.319
eware-3.179
ython-3.160
 Kimmel-3.128
Token inventory
Token ID13184
Feature activation+2.90e-03

Pos logit contributions
======+3.600
imaru+3.215
brush+3.212
+3.183
 grievances+3.174
Neg logit contributions
obal-4.385
acter-4.255
ython-4.067
eware-4.039
 Kimmel-4.003
Token impact
Token ID2928
Feature activation-9.84e-01

Pos logit contributions
======+2.047
brush+1.863
+1.842
imaru+1.842
 toget+1.804
Neg logit contributions
obal-2.877
acter-2.835
ython-2.662
 Kimmel-2.647
eware-2.644
Token would
Token ID561
Feature activation+3.00e+00

Pos logit contributions
obal+0.730
acter+0.706
eware+0.671
ython+0.670
 Kimmel+0.664
Neg logit contributions
======-0.613
imaru-0.562
brush-0.551
-0.547
-0.541
Token be
Token ID307
Feature activation+8.12e-01

Pos logit contributions
======+1.703
imaru+1.531
brush+1.513
+1.491
214+1.489
Neg logit contributions
obal-2.377
acter-2.309
ython-2.191
eware-2.191
 Kimmel-2.189
Token muted
Token ID38952
Feature activation-2.46e+00

Pos logit contributions
======+0.525
imaru+0.482
brush+0.473
+0.472
 toget+0.465
Neg logit contributions
obal-0.583
acter-0.565
ython-0.533
eware-0.533
 Kimmel-0.527
Token.
Token ID13
Feature activation+8.10e-01

Pos logit contributions
obal+1.811
acter+1.751
eware+1.671
ython+1.665
 Kimmel+1.651
Neg logit contributions
======-1.523
imaru-1.400
brush-1.373
-1.368
-1.350
Token Add
Token ID3060
Feature activation+1.05e+01

Pos logit contributions
======+0.408
imaru+0.364
+0.357
brush+0.357
214+0.349
Neg logit contributions
obal-0.699
acter-0.687
ython-0.652
eware-0.651
 Kimmel-0.637
Token to
Token ID284
Feature activation+7.64e+00

Pos logit contributions
======+5.353
imaru+4.973
+4.941
brush+4.853
 toget+4.822
Neg logit contributions
obal-8.019
acter-8.013
ython-7.731
eware-7.558
 Kimmel-7.530
Token that
Token ID326
Feature activation+9.06e+00

Pos logit contributions
======+3.746
imaru+3.364
brush+3.363
+3.336
 grievances+3.218
Neg logit contributions
obal-6.349
acter-6.333
ython-5.969
eware-5.934
 Kimmel-5.875
Token some
Token ID617
Feature activation+2.56e+00

Pos logit contributions
======+5.086
brush+4.644
imaru+4.596
 grievances+4.580
+4.573
Neg logit contributions
obal-6.889
acter-6.788
ython-6.379
eware-6.198
 Kimmel-6.096
Token probable
Token ID17939
Feature activation+3.81e-01

Pos logit contributions
======+1.628
imaru+1.485
brush+1.485
+1.481
 toget+1.447
Neg logit contributions
obal-1.849
acter-1.803
ython-1.701
eware-1.674
 Kimmel-1.668
Token guidance
Token ID11154
Feature activation-7.60e-01

Pos logit contributions
======+0.243
imaru+0.223
brush+0.219
+0.219
+0.215
Neg logit contributions
obal-0.278
acter-0.270
ython-0.254
eware-0.254
 Kimmel-0.252
Tokencl
Token ID565
Feature activation-2.15e+00

Pos logit contributions
======+1.510
imaru+1.404
brush+1.403
+1.384
214+1.369
Neg logit contributions
obal-1.235
acter-1.170
ython-1.109
eware-1.098
 Kimmel-1.095
Tokenosures
Token ID16091
Feature activation+2.48e+00

Pos logit contributions
obal+1.495
acter+1.444
eware+1.359
ython+1.356
 Kimmel+1.327
Neg logit contributions
======-1.456
imaru-1.342
-1.321
brush-1.315
-1.315
Token the
Token ID262
Feature activation-8.41e-01

Pos logit contributions
======+1.511
imaru+1.381
brush+1.361
+1.348
214+1.332
Neg logit contributions
obal-1.877
acter-1.814
eware-1.726
ython-1.724
 Kimmel-1.683
Token Finance
Token ID15007
Feature activation+1.67e+00

Pos logit contributions
obal+0.642
acter+0.623
eware+0.590
ython+0.589
 Kimmel+0.586
Neg logit contributions
======-0.507
imaru-0.463
brush-0.453
-0.449
-0.445
Token Minister
Token ID4139
Feature activation+6.02e-01

Pos logit contributions
======+1.150
imaru+1.060
brush+1.039
+1.035
+1.029
Neg logit contributions
obal-1.128
acter-1.092
eware-1.029
ython-1.024
 Kimmel-1.021
Token filed
Token ID5717
Feature activation+1.05e+01

Pos logit contributions
======+0.332
imaru+0.303
brush+0.300
+0.297
+0.292
Neg logit contributions
obal-0.484
acter-0.476
ython-0.450
eware-0.449
 Kimmel-0.442
Token with
Token ID351
Feature activation+3.14e+00

Pos logit contributions
======+4.985
brush+4.583
214+4.532
imaru+4.524
 grievances+4.440
Neg logit contributions
obal-8.639
acter-8.316
eware-7.995
ython-7.920
 Kimmel-7.663
Token the
Token ID262
Feature activation+2.61e+00

Pos logit contributions
======+1.874
imaru+1.726
+1.685
brush+1.680
214+1.649
Neg logit contributions
obal-2.370
acter-2.321
eware-2.208
ython-2.204
 Kimmel-2.175
Token federal
Token ID2717
Feature activation+1.71e+00

Pos logit contributions
======+1.441
imaru+1.321
+1.296
brush+1.285
214+1.266
Neg logit contributions
obal-2.065
acter-2.037
ython-1.945
eware-1.939
 Kimmel-1.909
Token Ethics
Token ID25092
Feature activation+3.92e-03

Pos logit contributions
======+0.930
imaru+0.839
brush+0.829
+0.819
+0.807
Neg logit contributions
obal-1.383
acter-1.363
ython-1.294
eware-1.291
 Kimmel-1.282
Token Commissioner
Token ID13270
Feature activation+2.06e+00

Pos logit contributions
======+0.002
imaru+0.002
brush+0.002
+0.002
+0.001
Neg logit contributions
obal-0.004
acter-0.003
eware-0.003
ython-0.003
 Kimmel-0.003
Token:
Token ID25
Feature activation-1.37e+00

Pos logit contributions
obal+0.810
acter+0.789
eware+0.746
ython+0.745
 Kimmel+0.733
Neg logit contributions
======-0.544
imaru-0.490
brush-0.481
-0.477
214-0.474
Token Dw
Token ID19113
Feature activation+2.91e+00

Pos logit contributions
obal+0.891
acter+0.862
eware+0.809
ython+0.807
 Kimmel+0.797
Neg logit contributions
======-0.981
imaru-0.910
brush-0.895
-0.890
-0.879
Tokenark
Token ID668
Feature activation+2.03e+00

Pos logit contributions
======+2.835
imaru+2.718
brush+2.683
+2.651
214+2.642
Neg logit contributions
obal-1.066
acter-1.014
 Kimmel-0.897
eware-0.894
ython-0.894
Tokena
Token ID64
Feature activation+2.26e+00

Pos logit contributions
======+1.507
imaru+1.403
brush+1.380
+1.371
+1.357
Neg logit contributions
obal-1.262
acter-1.217
eware-1.140
ython-1.139
 Kimmel-1.129
Token,
Token ID11
Feature activation+1.69e+00

Pos logit contributions
======+1.370
imaru+1.273
+1.239
brush+1.239
214+1.211
Neg logit contributions
obal-1.678
acter-1.647
eware-1.560
ython-1.542
 Kimmel-1.526
Token Gujarat
Token ID30311
Feature activation+1.05e+01

Pos logit contributions
======+1.150
imaru+1.072
+1.047
brush+1.044
214+1.028
Neg logit contributions
obal-1.149
acter-1.125
eware-1.056
ython-1.045
 Kimmel-1.024
Token 36
Token ID4570
Feature activation+4.21e+00

Pos logit contributions
======+4.550
imaru+4.375
brush+4.147
214+4.066
+3.891
Neg logit contributions
obal-9.059
acter-8.837
ython-8.232
eware-8.229
 Kimmel-8.050
Token13
Token ID1485
Feature activation+2.79e-01

Pos logit contributions
======+1.506
214+1.353
+1.239
+1.224
brush+1.209
Neg logit contributions
obal-4.259
acter-4.168
ython-3.970
eware-3.957
 Kimmel-3.948
Token35
Token ID2327
Feature activation+2.38e+00

Pos logit contributions
======+0.126
imaru+0.110
brush+0.108
214+0.108
+0.107
Neg logit contributions
obal-0.255
acter-0.250
eware-0.239
ython-0.239
 Kimmel-0.236
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
======+1.296
imaru+1.171
brush+1.145
+1.134
 toget+1.128
Neg logit contributions
obal-1.963
acter-1.901
ython-1.818
eware-1.814
 Kimmel-1.808
Token India
Token ID3794
Feature activation+2.45e+00

Pos logit contributions
obal+0.868
acter+0.834
eware+0.799
 Kimmel+0.799
ython+0.795
Neg logit contributions
======-0.752
imaru-0.688
brush-0.676
 toget-0.670
-0.669
Token
Token ID198
Feature activation-1.71e+00

Pos logit contributions
obal+0.312
acter+0.303
 Kimmel+0.290
ython+0.290
eware+0.290
Neg logit contributions
======-0.183
imaru-0.163
 toget-0.159
-0.158
brush-0.158
Token
Token ID198
Feature activation-3.22e+00

Pos logit contributions
obal+1.545
acter+1.508
eware+1.442
ython+1.442
 Kimmel+1.433
Neg logit contributions
======-0.784
imaru-0.696
brush-0.676
-0.670
 toget-0.661
TokenHoward
Token ID32434
Feature activation-3.75e+00

Pos logit contributions
obal+2.498
acter+2.423
eware+2.306
ython+2.287
 Kimmel+2.275
Neg logit contributions
======-1.832
imaru-1.714
 toget-1.676
brush-1.639
-1.622
Token Archer
Token ID19333
Feature activation-1.91e+00

Pos logit contributions
obal+2.323
acter+2.238
 Kimmel+2.136
ython+2.104
eware+2.090
Neg logit contributions
======-2.778
imaru-2.583
 toget-2.504
-2.503
-2.497
Token,
Token ID11
Feature activation+1.97e+00

Pos logit contributions
obal+1.428
acter+1.386
ython+1.313
eware+1.313
 Kimmel+1.304
Neg logit contributions
======-1.179
imaru-1.080
-1.049
brush-1.048
-1.040
Token chief
Token ID4039
Feature activation+1.05e+01

Pos logit contributions
======+1.199
imaru+1.096
brush+1.090
+1.078
 toget+1.058
Neg logit contributions
obal-1.467
acter-1.425
ython-1.360
eware-1.350
 Kimmel-1.332
Token UK
Token ID3482
Feature activation-7.89e-01

Pos logit contributions
======+4.822
+4.627
brush+4.542
cade+4.350
imaru+4.307
Neg logit contributions
obal-8.292
acter-8.094
 Kimmel-7.900
ython-7.855
 Pigs-7.645
Token &
Token ID1222
Feature activation-9.29e-01

Pos logit contributions
obal+0.578
acter+0.561
ython+0.531
eware+0.531
 Kimmel+0.526
Neg logit contributions
======-0.497
imaru-0.456
brush-0.448
-0.445
-0.439
Token European
Token ID3427
Feature activation-2.06e+00

Pos logit contributions
obal+0.660
acter+0.639
eware+0.606
ython+0.601
 Kimmel+0.597
Neg logit contributions
======-0.607
imaru-0.561
brush-0.548
-0.541
 toget-0.539
Token economist
Token ID17646
Feature activation-1.02e-01

Pos logit contributions
obal+1.470
acter+1.417
eware+1.331
ython+1.327
 Kimmel+1.322
Neg logit contributions
======-1.352
imaru-1.256
brush-1.221
-1.210
-1.204
Token at
Token ID379
Feature activation-1.82e+00

Pos logit contributions
obal+0.075
acter+0.073
eware+0.069
ython+0.069
 Kimmel+0.069
Neg logit contributions
======-0.064
imaru-0.059
brush-0.058
-0.057
-0.057
Token
Token ID198
Feature activation-7.95e-01

Pos logit contributions
======+0.626
imaru+0.561
brush+0.548
+0.543
 toget+0.537
Neg logit contributions
obal-1.132
acter-1.103
ython-1.055
eware-1.054
 Kimmel-1.053
Token
Token ID198
Feature activation-4.80e-01

Pos logit contributions
obal+0.735
acter+0.717
eware+0.687
ython+0.686
 Kimmel+0.680
Neg logit contributions
======-0.353
imaru-0.310
brush-0.303
-0.299
214-0.295
TokenKevin
Token ID23865
Feature activation+4.62e-01

Pos logit contributions
obal+0.385
acter+0.375
eware+0.356
ython+0.356
 Kimmel+0.354
Neg logit contributions
======-0.267
imaru-0.244
brush-0.238
-0.236
 toget-0.235
Token Miles
Token ID20404
Feature activation+2.35e+00

Pos logit contributions
======+0.328
imaru+0.305
brush+0.300
+0.298
214+0.294
Neg logit contributions
obal-0.301
acter-0.292
eware-0.274
ython-0.273
 Kimmel-0.269
Token,
Token ID11
Feature activation+1.40e+00

Pos logit contributions
======+1.363
imaru+1.243
brush+1.229
+1.212
214+1.190
Neg logit contributions
obal-1.839
acter-1.790
eware-1.698
ython-1.695
 Kimmel-1.677
Token chief
Token ID4039
Feature activation+1.04e+01

Pos logit contributions
======+0.871
imaru+0.796
brush+0.780
+0.776
+0.766
Neg logit contributions
obal-1.045
acter-1.013
eware-0.961
ython-0.960
 Kimmel-0.948
Token executive
Token ID4640
Feature activation+7.80e-01

Pos logit contributions
======+4.691
+4.197
cade+4.010
 grievances+3.981
214+3.960
Neg logit contributions
obal-8.666
acter-8.495
ython-8.343
eware-8.196
 Kimmel-8.125
Token of
Token ID286
Feature activation+7.42e-01

Pos logit contributions
======+0.494
imaru+0.457
brush+0.446
+0.443
 toget+0.439
Neg logit contributions
obal-0.571
acter-0.552
eware-0.523
ython-0.521
 Kimmel-0.519
Token the
Token ID262
Feature activation-1.39e+00

Pos logit contributions
======+0.483
imaru+0.444
brush+0.436
+0.434
+0.428
Neg logit contributions
obal-0.529
acter-0.513
eware-0.485
ython-0.484
 Kimmel-0.479
Token Football
Token ID9957
Feature activation-6.30e+00

Pos logit contributions
obal+0.992
acter+0.961
ython+0.907
eware+0.907
 Kimmel+0.901
Neg logit contributions
======-0.904
imaru-0.832
brush-0.819
-0.812
-0.804
Token Supporters
Token ID39995
Feature activation-4.86e+00

Pos logit contributions
obal+4.427
acter+4.236
 Kimmel+4.028
eware+4.024
ython+3.967
Neg logit contributions
======-4.036
imaru-3.769
 toget-3.682
-3.654
brush-3.651
Token Jamal
Token ID46520
Feature activation-4.86e+00

Pos logit contributions
======+0.175
imaru+0.161
brush+0.158
+0.157
+0.156
Neg logit contributions
obal-0.187
acter-0.181
eware-0.171
ython-0.171
 Kimmel-0.170
Token H
Token ID367
Feature activation+2.08e-01

Pos logit contributions
obal+3.162
acter+3.037
 Kimmel+2.932
ython+2.864
eware+2.861
Neg logit contributions
======-3.429
 toget-3.143
imaru-3.130
-3.112
-3.090
Tokename
Token ID480
Feature activation+1.95e-01

Pos logit contributions
======+0.141
imaru+0.130
brush+0.128
+0.127
+0.126
Neg logit contributions
obal-0.142
acter-0.137
eware-0.129
ython-0.129
 Kimmel-0.128
Tokenedi
Token ID13740
Feature activation+8.41e-01

Pos logit contributions
======+0.108
imaru+0.100
brush+0.097
+0.095
214+0.094
Neg logit contributions
obal-0.157
acter-0.152
ython-0.145
eware-0.145
 Kimmel-0.145
Token,
Token ID11
Feature activation+3.45e+00

Pos logit contributions
======+0.521
imaru+0.476
brush+0.465
 toget+0.465
+0.465
Neg logit contributions
obal-0.631
acter-0.611
eware-0.578
ython-0.576
 Kimmel-0.573
Token chief
Token ID4039
Feature activation+1.04e+01

Pos logit contributions
======+2.024
imaru+1.814
brush+1.809
+1.804
214+1.763
Neg logit contributions
obal-2.660
acter-2.593
ython-2.492
eware-2.483
 Kimmel-2.412
Token engineer
Token ID11949
Feature activation+1.19e+00

Pos logit contributions
======+5.681
+5.200
brush+5.095
214+4.965
cade+4.917
Neg logit contributions
obal-7.614
acter-7.424
ython-7.276
eware-7.043
 Kimmel-6.983
Token,
Token ID11
Feature activation-1.73e-01

Pos logit contributions
======+0.734
imaru+0.677
brush+0.659
+0.654
+0.649
Neg logit contributions
obal-0.891
acter-0.862
eware-0.819
ython-0.815
 Kimmel-0.813
Token Ford
Token ID8092
Feature activation+1.95e+00

Pos logit contributions
obal+0.134
acter+0.130
eware+0.123
ython+0.123
 Kimmel+0.122
Neg logit contributions
======-0.103
imaru-0.094
brush-0.092
-0.091
-0.090
Token Performance
Token ID15193
Feature activation-2.42e+00

Pos logit contributions
======+1.236
imaru+1.122
brush+1.114
+1.109
214+1.092
Neg logit contributions
obal-1.414
acter-1.382
eware-1.314
ython-1.314
 Kimmel-1.285
Token.
Token ID13
Feature activation+2.36e+00

Pos logit contributions
obal+1.717
acter+1.653
eware+1.565
 Kimmel+1.562
ython+1.557
Neg logit contributions
======-1.582
imaru-1.460
brush-1.425
-1.419
 toget-1.414
Token legislation
Token ID5520
Feature activation+3.18e+00

Pos logit contributions
======+2.243
+2.021
brush+2.012
imaru+2.007
 toget+1.985
Neg logit contributions
obal-2.797
acter-2.727
ython-2.611
eware-2.571
 Kimmel-2.513
Token to
Token ID284
Feature activation+2.51e-01

Pos logit contributions
======+1.783
imaru+1.601
+1.599
 toget+1.582
brush+1.573
Neg logit contributions
obal-2.556
acter-2.487
eware-2.378
ython-2.378
 Kimmel-2.310
Token strike
Token ID5587
Feature activation-4.33e+00

Pos logit contributions
======+0.149
imaru+0.135
+0.133
brush+0.133
 toget+0.131
Neg logit contributions
obal-0.194
acter-0.189
ython-0.181
eware-0.180
 Kimmel-0.177
Token down
Token ID866
Feature activation+7.42e-01

Pos logit contributions
obal+2.903
acter+2.797
eware+2.630
 Kimmel+2.619
ython+2.583
Neg logit contributions
======-2.945
imaru-2.740
brush-2.652
214-2.651
-2.650
Token the
Token ID262
Feature activation+3.36e+00

Pos logit contributions
======+0.467
imaru+0.426
brush+0.423
+0.421
 toget+0.412
Neg logit contributions
obal-0.543
acter-0.530
ython-0.504
eware-0.498
 Kimmel-0.492
Token Tory
Token ID19037
Feature activation+1.04e+01

Pos logit contributions
======+2.097
+1.908
imaru+1.895
brush+1.879
 grievances+1.874
Neg logit contributions
acter-2.401
obal-2.398
ython-2.311
eware-2.238
 Kimmel-2.177
Token law
Token ID1099
Feature activation+1.40e+00

Pos logit contributions
======+6.406
 grievances+5.940
+5.852
brush+5.843
 toget+5.584
Neg logit contributions
acter-7.019
obal-6.837
ython-6.665
eware-6.307
 Kimmel-6.115
Token that
Token ID326
Feature activation+8.55e-02

Pos logit contributions
======+0.837
imaru+0.760
brush+0.752
+0.749
 toget+0.734
Neg logit contributions
obal-1.077
acter-1.051
ython-1.002
eware-0.995
 Kimmel-0.978
Token allowed
Token ID3142
Feature activation-4.18e-01

Pos logit contributions
======+0.053
imaru+0.048
+0.048
brush+0.047
 toget+0.047
Neg logit contributions
obal-0.064
acter-0.062
eware-0.059
ython-0.059
 Kimmel-0.057
Token the
Token ID262
Feature activation-2.66e-01

Pos logit contributions
obal+0.305
acter+0.296
ython+0.280
eware+0.280
 Kimmel+0.277
Neg logit contributions
======-0.265
imaru-0.243
brush-0.239
-0.237
 toget-0.234
Token government
Token ID1230
Feature activation+8.37e-01

Pos logit contributions
obal+0.210
acter+0.205
ython+0.196
eware+0.194
 Kimmel+0.192
Neg logit contributions
======-0.152
imaru-0.138
-0.135
brush-0.135
 toget-0.132
Tokenpage
Token ID7700
Feature activation+2.93e+00

Pos logit contributions
======+1.254
brush+1.104
imaru+1.083
214+1.080
+1.078
Neg logit contributions
obal-2.636
acter-2.544
ython-2.470
 Kimmel-2.447
eware-2.441
Token lawsuit
Token ID8087
Feature activation+4.12e+00

Pos logit contributions
======+1.553
imaru+1.398
 grievances+1.398
+1.393
214+1.393
Neg logit contributions
obal-2.393
acter-2.334
ython-2.237
eware-2.222
 Kimmel-2.180
Token Gal
Token ID5027
Feature activation-3.15e+00

Pos logit contributions
======+2.199
imaru+2.001
brush+1.978
214+1.968
+1.950
Neg logit contributions
obal-3.386
acter-3.261
ython-3.148
eware-3.104
 Kimmel-2.975
Tokenar
Token ID283
Feature activation-3.23e+00

Pos logit contributions
obal+2.380
acter+2.307
eware+2.188
ython+2.185
 Kimmel+2.166
Neg logit contributions
======-1.926
imaru-1.760
brush-1.725
-1.717
 toget-1.707
Tokenza
Token ID4496
Feature activation+3.69e-01

Pos logit contributions
obal+3.630
acter+3.552
eware+3.428
ython+3.427
 Kimmel+3.402
Neg logit contributions
======-0.778
 toget-0.643
imaru-0.606
-0.583
brush-0.572
Token filed
Token ID5717
Feature activation+1.02e+01

Pos logit contributions
======+0.227
imaru+0.209
brush+0.207
+0.205
+0.202
Neg logit contributions
obal-0.274
acter-0.267
ython-0.252
eware-0.252
 Kimmel-0.248
Token in
Token ID287
Feature activation+3.97e+00

Pos logit contributions
======+4.688
brush+4.248
 grievances+4.210
214+4.178
imaru+4.148
Neg logit contributions
obal-8.759
acter-8.451
ython-8.206
eware-8.055
 Kimmel-7.660
Token November
Token ID3389
Feature activation-1.62e-01

Pos logit contributions
======+2.262
imaru+2.070
brush+2.058
214+2.016
 grievances+2.009
Neg logit contributions
obal-3.092
acter-2.980
ython-2.869
eware-2.855
 Kimmel-2.739
Token 2010
Token ID3050
Feature activation-1.05e+00

Pos logit contributions
obal+0.115
acter+0.111
eware+0.105
ython+0.105
 Kimmel+0.105
Neg logit contributions
======-0.106
imaru-0.097
brush-0.095
-0.095
-0.094
Token.
Token ID13
Feature activation+2.45e+00

Pos logit contributions
obal+0.800
acter+0.777
eware+0.738
 Kimmel+0.737
ython+0.737
Neg logit contributions
======-0.633
imaru-0.579
-0.564
brush-0.562
 toget-0.555
Token
Token ID198
Feature activation+5.37e-01

Pos logit contributions
======+1.249
imaru+1.140
brush+1.098
+1.092
214+1.087
Neg logit contributions
obal-2.088
acter-2.030
eware-1.942
ython-1.940
 Kimmel-1.895
Token military
Token ID2422
Feature activation-5.32e+00

Pos logit contributions
======+0.249
imaru+0.228
brush+0.224
+0.223
214+0.220
Neg logit contributions
obal-0.281
acter-0.272
ython-0.259
eware-0.257
 Kimmel-0.254
Token and
Token ID290
Feature activation-7.21e-01

Pos logit contributions
obal+3.848
acter+3.693
eware+3.521
 Kimmel+3.489
ython+3.455
Neg logit contributions
======-3.335
imaru-3.083
-3.030
-3.017
brush-2.982
Token the
Token ID262
Feature activation+2.84e-01

Pos logit contributions
obal+0.521
acter+0.505
eware+0.477
ython+0.477
 Kimmel+0.473
Neg logit contributions
======-0.462
imaru-0.425
brush-0.417
-0.414
-0.409
Token Department
Token ID2732
Feature activation+1.23e+00

Pos logit contributions
======+0.179
imaru+0.164
brush+0.161
+0.160
214+0.158
Neg logit contributions
obal-0.209
acter-0.202
ython-0.192
eware-0.191
 Kimmel-0.189
Token of
Token ID286
Feature activation-2.78e+00

Pos logit contributions
======+0.680
imaru+0.602
brush+0.600
+0.593
214+0.589
Neg logit contributions
obal-0.999
acter-0.972
ython-0.932
eware-0.922
 Kimmel-0.913
Token Homeland
Token ID17444
Feature activation-1.21e+01

Pos logit contributions
obal+1.850
acter+1.787
ython+1.680
eware+1.680
 Kimmel+1.671
Neg logit contributions
======-1.936
imaru-1.800
brush-1.760
-1.753
 toget-1.745
Token Security
Token ID4765
Feature activation-5.02e+00

Pos logit contributions
obal+5.609
acter+5.269
ython+5.043
eware+4.949
 Pigs+4.649
Neg logit contributions
 toget-9.701
imaru-9.656
======-9.651
 convol-9.487
brush-9.442
Token have
Token ID423
Feature activation-2.83e+00

Pos logit contributions
obal+3.581
acter+3.473
eware+3.306
 Kimmel+3.276
ython+3.263
Neg logit contributions
======-3.170
imaru-2.937
brush-2.862
-2.846
-2.833
Token set
Token ID900
Feature activation-3.54e+00

Pos logit contributions
obal+1.957
acter+1.903
eware+1.791
ython+1.779
 Kimmel+1.771
Neg logit contributions
======-1.884
imaru-1.746
brush-1.711
-1.696
-1.685
Token in
Token ID287
Feature activation+3.98e+00

Pos logit contributions
obal+2.480
acter+2.427
eware+2.297
ython+2.276
 Kimmel+2.268
Neg logit contributions
======-2.244
imaru-2.115
-2.048
brush-2.042
214-2.029
Token motion
Token ID6268
Feature activation-8.52e-01

Pos logit contributions
======+2.897
brush+2.656
+2.637
 toget+2.611
▬▬+2.601
Neg logit contributions
obal-2.502
acter-2.399
ython-2.279
eware-2.234
 Kimmel-2.215
Tokenless
Token ID1203
Feature activation-1.74e+00

Pos logit contributions
obal+2.975
acter+2.893
eware+2.744
ython+2.726
 Kimmel+2.708
Neg logit contributions
======-2.430
imaru-2.225
-2.149
brush-2.113
 toget-2.103
Token beauty
Token ID8737
Feature activation-2.43e+00

Pos logit contributions
obal+1.189
acter+1.156
eware+1.089
 Kimmel+1.088
ython+1.085
Neg logit contributions
======-1.183
imaru-1.097
-1.066
brush-1.066
-1.055
Token played
Token ID2826
Feature activation-6.89e+00

Pos logit contributions
obal+1.750
acter+1.695
eware+1.609
 Kimmel+1.602
ython+1.598
Neg logit contributions
======-1.554
imaru-1.433
-1.387
brush-1.383
 toget-1.364
Token by
Token ID416
Feature activation-7.21e-01

Pos logit contributions
obal+3.709
acter+3.692
 Kimmel+3.431
eware+3.395
ython+3.264
Neg logit contributions
======-5.367
imaru-5.108
-4.925
brush-4.895
214-4.889
Token Mar
Token ID1526
Feature activation-1.41e+00

Pos logit contributions
obal+0.461
acter+0.445
eware+0.418
ython+0.418
 Kimmel+0.412
Neg logit contributions
======-0.523
imaru-0.485
brush-0.478
-0.475
-0.470
Tokeniel
Token ID8207
Feature activation-1.18e+01

Pos logit contributions
obal+0.907
acter+0.878
eware+0.817
ython+0.809
 Kimmel+0.809
Neg logit contributions
======-1.030
imaru-0.944
-0.935
brush-0.932
 toget-0.931
Token Hem
Token ID15617
Feature activation-5.41e+00

Pos logit contributions
obal+6.714
acter+6.576
 Kimmel+6.445
 Lilly+6.002
 Pigs+5.799
Neg logit contributions
======-8.643
imaru-8.330
 toget-8.034
-8.023
milo-7.935
Tokening
Token ID278
Feature activation-2.53e+00

Pos logit contributions
obal+4.089
acter+3.931
eware+3.707
 Kimmel+3.651
ython+3.644
Neg logit contributions
======-3.329
 toget-3.001
-2.955
imaru-2.933
▬▬-2.927
Tokenway
Token ID1014
Feature activation-7.58e-01

Pos logit contributions
obal+2.443
acter+2.371
eware+2.298
 Kimmel+2.280
ython+2.270
Neg logit contributions
======-1.006
imaru-0.870
-0.828
brush-0.826
-0.819
Token,
Token ID11
Feature activation-9.60e-01

Pos logit contributions
obal+0.578
acter+0.560
eware+0.532
ython+0.532
 Kimmel+0.530
Neg logit contributions
======-0.455
imaru-0.416
brush-0.405
-0.404
-0.397
Token and
Token ID290
Feature activation-1.92e+00

Pos logit contributions
obal+0.701
acter+0.680
eware+0.644
ython+0.642
 Kimmel+0.639
Neg logit contributions
======-0.608
imaru-0.558
brush-0.546
-0.543
-0.536
Token Superior
Token ID22953
Feature activation+1.13e+01

Pos logit contributions
======+1.168
imaru+1.077
brush+1.066
+1.061
214+1.047
Neg logit contributions
obal-1.265
acter-1.232
ython-1.161
eware-1.160
 Kimmel-1.139
Token Court
Token ID3078
Feature activation+3.26e+00

Pos logit contributions
======+2.656
imaru+2.212
brush+2.088
214+2.087
cade+2.041
Neg logit contributions
obal-11.767
acter-11.562
ython-11.206
eware-10.962
offer-10.889
Token offices
Token ID9730
Feature activation-1.20e+00

Pos logit contributions
======+1.922
imaru+1.748
brush+1.715
+1.703
214+1.689
Neg logit contributions
obal-2.511
acter-2.443
ython-2.327
eware-2.302
 Kimmel-2.278
Token to
Token ID284
Feature activation-4.21e-01

Pos logit contributions
obal+0.891
acter+0.864
eware+0.818
ython+0.818
 Kimmel+0.811
Neg logit contributions
======-0.741
imaru-0.678
brush-0.665
-0.661
-0.653
Token inform
Token ID4175
Feature activation-2.94e+00

Pos logit contributions
obal+0.302
acter+0.292
ython+0.277
eware+0.276
 Kimmel+0.272
Neg logit contributions
======-0.273
imaru-0.251
brush-0.247
-0.245
-0.242
Token immigration
Token ID6272
Feature activation-1.15e+01

Pos logit contributions
obal+2.004
acter+1.946
eware+1.837
 Kimmel+1.834
ython+1.822
Neg logit contributions
======-1.984
imaru-1.821
brush-1.794
-1.774
 toget-1.773
Token officials
Token ID2828
Feature activation-4.71e+00

Pos logit contributions
obal+6.138
acter+5.750
eware+5.561
ython+5.510
 equivalents+5.494
Neg logit contributions
======-8.661
imaru-8.231
▬▬-8.046
-8.013
-7.948
Token and
Token ID290
Feature activation-2.34e+00

Pos logit contributions
obal+3.298
acter+3.186
 Kimmel+3.028
eware+3.018
ython+3.001
Neg logit contributions
======-3.055
imaru-2.815
brush-2.764
-2.747
-2.712
Token a
Token ID257
Feature activation-8.75e-01

Pos logit contributions
obal+1.670
acter+1.619
eware+1.531
ython+1.526
 Kimmel+1.520
Neg logit contributions
======-1.513
imaru-1.392
brush-1.365
-1.355
-1.340
Token det
Token ID1062
Feature activation-3.63e+00

Pos logit contributions
obal+0.628
acter+0.610
ython+0.575
eware+0.574
 Kimmel+0.569
Neg logit contributions
======-0.567
imaru-0.521
brush-0.511
-0.510
214-0.503
Tokenainer
Token ID10613
Feature activation-2.03e+00

Pos logit contributions
obal+1.891
acter+1.856
eware+1.706
ython+1.651
 Kimmel+1.613
Neg logit contributions
======-3.035
imaru-2.845
-2.808
brush-2.803
 toget-2.797
Token back
Token ID736
Feature activation+8.94e-01

Pos logit contributions
======+1.997
imaru+1.816
brush+1.772
 toget+1.768
+1.758
Neg logit contributions
obal-2.668
acter-2.588
ython-2.472
eware-2.453
 Kimmel-2.395
Token?
Token ID30
Feature activation-4.63e-01

Pos logit contributions
======+0.461
imaru+0.414
brush+0.404
+0.401
+0.396
Neg logit contributions
obal-0.759
acter-0.740
ython-0.704
eware-0.704
 Kimmel-0.696
Token Sign
Token ID5865
Feature activation+1.50e-01

Pos logit contributions
obal+0.357
acter+0.347
eware+0.329
ython+0.329
 Kimmel+0.325
Neg logit contributions
======-0.277
imaru-0.252
brush-0.247
-0.245
214-0.242
Token up
Token ID510
Feature activation-1.77e+00

Pos logit contributions
======+0.093
imaru+0.085
brush+0.083
+0.083
+0.082
Neg logit contributions
obal-0.112
acter-0.108
eware-0.103
ython-0.102
 Kimmel-0.102
Token for
Token ID329
Feature activation+1.54e+00

Pos logit contributions
obal+1.311
acter+1.274
eware+1.209
ython+1.207
 Kimmel+1.202
Neg logit contributions
======-1.086
imaru-0.997
brush-0.978
-0.977
-0.960
Token Take
Token ID7214
Feature activation-1.12e+01

Pos logit contributions
======+1.022
imaru+0.934
brush+0.912
+0.911
 toget+0.906
Neg logit contributions
obal-1.085
acter-1.051
eware-0.998
ython-0.993
 Kimmel-0.976
Token Action
Token ID7561
Feature activation-3.24e+00

Pos logit contributions
obal+7.797
acter+7.598
 Kimmel+7.228
ython+7.147
offer+6.971
Neg logit contributions
======-6.585
 toget-6.145
rouse-6.109
-6.074
 convol-6.074
Token Now
Token ID2735
Feature activation-3.93e-01

Pos logit contributions
obal+2.349
acter+2.287
ython+2.177
eware+2.159
 Kimmel+2.158
Neg logit contributions
======-2.023
imaru-1.863
-1.836
brush-1.825
-1.811
Token and
Token ID290
Feature activation-3.67e+00

Pos logit contributions
obal+0.306
acter+0.297
eware+0.282
ython+0.282
 Kimmel+0.280
Neg logit contributions
======-0.231
imaru-0.209
brush-0.205
-0.203
214-0.201
Token get
Token ID651
Feature activation-1.35e-01

Pos logit contributions
obal+2.680
acter+2.595
eware+2.466
 Kimmel+2.463
ython+2.452
Neg logit contributions
======-2.293
imaru-2.131
brush-2.062
-2.060
-2.038
Token three
Token ID1115
Feature activation-1.08e-01

Pos logit contributions
obal+0.096
acter+0.094
eware+0.089
ython+0.088
 Kimmel+0.087
Neg logit contributions
======-0.087
imaru-0.080
brush-0.079
-0.078
 toget-0.077
Token a
Token ID257
Feature activation-3.26e+00

Pos logit contributions
obal+0.918
acter+0.888
eware+0.836
ython+0.836
 Kimmel+0.828
Neg logit contributions
======-0.921
imaru-0.850
brush-0.836
-0.831
-0.821
Token bit
Token ID1643
Feature activation-4.02e+00

Pos logit contributions
obal+2.141
acter+2.062
ython+1.949
eware+1.946
 Kimmel+1.945
Neg logit contributions
======-2.275
imaru-2.120
brush-2.062
-2.057
214-2.036
Token of
Token ID286
Feature activation-5.14e+00

Pos logit contributions
obal+2.503
acter+2.430
eware+2.278
 Kimmel+2.276
ython+2.262
Neg logit contributions
======-2.954
imaru-2.759
brush-2.670
-2.666
-2.644
Token a
Token ID257
Feature activation-6.13e+00

Pos logit contributions
obal+3.468
acter+3.365
 Kimmel+3.197
eware+3.175
ython+3.132
Neg logit contributions
======-3.441
imaru-3.243
-3.112
brush-3.089
-3.087
Token fac
Token ID1777
Feature activation-2.88e+00

Pos logit contributions
obal+4.121
acter+3.963
 Kimmel+3.832
ython+3.777
eware+3.766
Neg logit contributions
======-4.035
imaru-3.770
-3.604
214-3.600
brush-3.591
Tokenel
Token ID417
Feature activation-1.12e+01

Pos logit contributions
obal+1.287
acter+1.222
eware+1.120
ython+1.110
 Kimmel+1.089
Neg logit contributions
======-2.642
imaru-2.489
brush-2.454
-2.450
 toget-2.429
Tokenift
Token ID2135
Feature activation-3.61e+00

Pos logit contributions
obal+4.623
acter+4.329
offer+3.747
ython+3.739
eware+3.543
Neg logit contributions
-10.241
======-10.146
 convol-10.145
 toget-10.100
-10.079
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
obal+2.605
acter+2.536
eware+2.401
ython+2.394
 Kimmel+2.384
Neg logit contributions
======-2.269
imaru-2.097
-2.067
brush-2.034
214-2.025
Token
Token ID198
Feature activation-7.88e-01

Pos logit contributions
obal+1.148
acter+1.117
eware+1.066
ython+1.064
 Kimmel+1.058
Neg logit contributions
======-0.720
imaru-0.650
brush-0.634
-0.630
 toget-0.620
Token
Token ID198
Feature activation+1.30e-01

Pos logit contributions
obal+0.731
acter+0.713
eware+0.683
ython+0.682
 Kimmel+0.676
Neg logit contributions
======-0.349
imaru-0.306
brush-0.299
-0.294
214-0.291
TokenBeyond
Token ID24102
Feature activation+2.55e+00

Pos logit contributions
======+0.070
imaru+0.062
brush+0.061
+0.061
214+0.060
Neg logit contributions
obal-0.108
acter-0.105
ython-0.100
eware-0.100
 Kimmel-0.099
Token important
Token ID1593
Feature activation+1.29e+00

Pos logit contributions
======+1.235
imaru+1.128
+1.123
brush+1.120
214+1.101
Neg logit contributions
obal-1.472
acter-1.431
ython-1.368
eware-1.346
 Kimmel-1.321
Token and
Token ID290
Feature activation-7.58e-01

Pos logit contributions
======+0.841
imaru+0.779
brush+0.769
+0.768
 grievances+0.756
Neg logit contributions
obal-0.902
acter-0.882
ython-0.841
eware-0.831
 Kimmel-0.816
Token reliable
Token ID9314
Feature activation+2.48e+00

Pos logit contributions
obal+0.536
acter+0.518
ython+0.491
eware+0.490
 Kimmel+0.484
Neg logit contributions
======-0.499
imaru-0.459
brush-0.451
-0.449
-0.443
Token bi
Token ID3182
Feature activation-1.47e+00

Pos logit contributions
======+1.671
imaru+1.549
brush+1.533
+1.526
+1.487
Neg logit contributions
obal-1.672
acter-1.627
ython-1.559
eware-1.530
 Kimmel-1.504
Token-
Token ID12
Feature activation-1.02e+00

Pos logit contributions
obal+0.940
acter+0.905
eware+0.848
ython+0.843
 Kimmel+0.829
Neg logit contributions
======-1.076
imaru-1.001
brush-0.980
-0.977
 toget-0.970
Tokenl
Token ID75
Feature activation-1.12e+01

Pos logit contributions
obal+0.854
acter+0.831
eware+0.792
ython+0.792
 Kimmel+0.785
Neg logit contributions
======-0.532
imaru-0.479
brush-0.467
-0.464
-0.457
Tokenateral
Token ID10534
Feature activation-8.06e-01

Pos logit contributions
obal+6.566
acter+5.977
ython+5.228
eware+4.904
ots+4.814
Neg logit contributions
======-8.899
▬▬-8.371
-8.244
 toget-8.209
 convol-8.094
Token partner
Token ID5212
Feature activation+3.56e+00

Pos logit contributions
obal+0.614
acter+0.596
ython+0.566
eware+0.566
 Kimmel+0.561
Neg logit contributions
======-0.485
imaru-0.443
brush-0.435
-0.433
214-0.426
Token,
Token ID11
Feature activation+3.05e-02

Pos logit contributions
======+2.041
imaru+1.848
brush+1.814
+1.796
+1.780
Neg logit contributions
obal-2.795
acter-2.730
ython-2.604
eware-2.585
 Kimmel-2.550
Token
Token ID447
Feature activation+3.55e-01

Pos logit contributions
======+0.020
imaru+0.018
brush+0.018
+0.018
214+0.017
Neg logit contributions
obal-0.022
acter-0.021
eware-0.020
ython-0.020
 Kimmel-0.020
Token
Token ID251
Feature activation-2.18e-01

Pos logit contributions
======+0.222
imaru+0.204
brush+0.200
+0.199
+0.196
Neg logit contributions
obal-0.262
acter-0.254
eware-0.241
ython-0.241
 Kimmel-0.239
Token our
Token ID674
Feature activation+3.57e+00

Pos logit contributions
obal+0.161
acter+0.157
eware+0.148
ython+0.147
 Kimmel+0.145
Neg logit contributions
======-0.161
imaru-0.148
brush-0.146
-0.145
214-0.144
Token latest
Token ID3452
Feature activation+3.67e+00

Pos logit contributions
======+2.653
214+2.421
brush+2.398
imaru+2.363
 grievances+2.349
Neg logit contributions
obal-2.184
acter-2.132
eware-1.994
ython-1.986
 Kimmel-1.922
Token issue
Token ID2071
Feature activation+5.57e+00

Pos logit contributions
======+1.822
brush+1.542
214+1.533
imaru+1.531
+1.524
Neg logit contributions
obal-3.191
acter-3.149
eware-2.967
ython-2.958
 Kimmel-2.913
Token
Token ID198
Feature activation-7.66e-01

Pos logit contributions
======+1.930
214+1.588
brush+1.568
imaru+1.565
+1.523
Neg logit contributions
obal-5.682
acter-5.620
eware-5.381
ython-5.340
 equivalents-5.199
Token
Token ID198
Feature activation-5.25e-01

Pos logit contributions
obal+0.707
acter+0.690
eware+0.662
ython+0.660
 Kimmel+0.655
Neg logit contributions
======-0.341
imaru-0.299
brush-0.292
-0.288
214-0.285
TokenTravel
Token ID33074
Feature activation-1.11e+01

Pos logit contributions
obal+0.484
acter+0.474
eware+0.455
ython+0.454
 Kimmel+0.453
Neg logit contributions
======-0.232
imaru-0.201
brush-0.200
-0.198
214-0.195
Token With
Token ID2080
Feature activation-1.86e+00

Pos logit contributions
obal+7.069
eware+6.808
acter+6.638
offer+6.542
 Kimmel+6.385
Neg logit contributions
======-7.137
imaru-7.020
brush-6.786
milo-6.618
▬▬-6.558
Token The
Token ID383
Feature activation+9.18e-02

Pos logit contributions
obal+1.377
acter+1.336
eware+1.267
ython+1.264
 Kimmel+1.251
Neg logit contributions
======-1.161
imaru-1.064
brush-1.042
-1.036
-1.024
Token Nation
Token ID8741
Feature activation-2.04e-01

Pos logit contributions
======+0.039
imaru+0.034
brush+0.033
+0.033
+0.032
Neg logit contributions
obal-0.086
acter-0.084
eware-0.081
ython-0.081
 Kimmel-0.080
Token Be
Token ID1355
Feature activation-2.99e+00

Pos logit contributions
obal+0.163
acter+0.162
ython+0.156
eware+0.152
 Kimmel+0.151
Neg logit contributions
======-0.111
brush-0.101
imaru-0.099
214-0.099
-0.097
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
obal+2.122
acter+2.060
eware+1.952
ython+1.943
 Kimmel+1.924
Neg logit contributions
======-1.961
imaru-1.792
brush-1.773
-1.757
 toget-1.743
Token,
Token ID11
Feature activation+2.14e+00

Pos logit contributions
obal+0.541
acter+0.527
eware+0.499
ython+0.499
 Kimmel+0.495
Neg logit contributions
======-0.410
imaru-0.374
brush-0.367
-0.365
-0.359
Token director
Token ID3437
Feature activation+4.42e+00

Pos logit contributions
======+1.325
imaru+1.215
brush+1.196
+1.195
+1.178
Neg logit contributions
obal-1.593
acter-1.544
eware-1.458
ython-1.454
 Kimmel-1.433
Token of
Token ID286
Feature activation-3.46e-01

Pos logit contributions
======+2.660
imaru+2.424
brush+2.380
+2.365
+2.337
Neg logit contributions
obal-3.357
acter-3.263
eware-3.088
ython-3.086
 Kimmel-3.068
Token the
Token ID262
Feature activation-1.97e+00

Pos logit contributions
obal+0.249
acter+0.242
eware+0.228
ython+0.228
 Kimmel+0.226
Neg logit contributions
======-0.223
imaru-0.204
brush-0.201
-0.200
-0.197
Token International
Token ID4037
Feature activation-2.57e+00

Pos logit contributions
obal+1.374
acter+1.332
eware+1.255
ython+1.253
 Kimmel+1.241
Neg logit contributions
======-1.309
imaru-1.207
brush-1.185
-1.179
-1.164
Token Travel
Token ID13524
Feature activation-1.11e+01

Pos logit contributions
obal+1.837
acter+1.776
ython+1.682
eware+1.680
 Kimmel+1.672
Neg logit contributions
======-1.676
imaru-1.541
brush-1.510
-1.500
 toget-1.489
Token Company
Token ID5834
Feature activation-7.38e-01

Pos logit contributions
obal+7.704
acter+7.345
eware+7.072
ython+7.031
 Kimmel+7.012
Neg logit contributions
======-6.866
 toget-6.464
imaru-6.314
-6.253
▬▬-6.200
Token of
Token ID286
Feature activation-2.58e+00

Pos logit contributions
obal+0.551
acter+0.535
eware+0.507
ython+0.506
 Kimmel+0.502
Neg logit contributions
======-0.455
imaru-0.417
brush-0.409
-0.406
-0.401
Token the
Token ID262
Feature activation-3.14e+00

Pos logit contributions
obal+1.809
acter+1.747
ython+1.662
eware+1.659
 Kimmel+1.656
Neg logit contributions
======-1.692
imaru-1.550
brush-1.532
-1.510
 toget-1.509
Token DPRK
Token ID48363
Feature activation-6.36e+00

Pos logit contributions
obal+2.209
acter+2.136
ython+2.024
eware+2.022
 Kimmel+2.016
Neg logit contributions
======-2.068
imaru-1.899
brush-1.869
-1.849
-1.840
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
obal+4.315
acter+4.145
eware+4.008
ython+3.994
 Kimmel+3.962
Neg logit contributions
======-4.222
imaru-3.867
 toget-3.791
brush-3.772
▬▬-3.737
Token psycho
Token ID30731
Feature activation-2.53e+00

Pos logit contributions
======+0.870
brush+0.803
imaru+0.802
+0.798
 toget+0.790
Neg logit contributions
obal-0.555
acter-0.527
ython-0.494
eware-0.492
 Kimmel-0.487
Tokenanalysis
Token ID20930
Feature activation-2.94e+00

Pos logit contributions
obal+1.392
acter+1.342
eware+1.243
ython+1.237
 Kimmel+1.213
Neg logit contributions
======-2.051
imaru-1.934
-1.888
brush-1.885
-1.871
Token.
Token ID13
Feature activation-1.83e+00

Pos logit contributions
obal+2.210
acter+2.149
eware+2.035
ython+2.032
 Kimmel+2.020
Neg logit contributions
======-1.779
imaru-1.638
-1.598
brush-1.585
-1.568
Token This
Token ID770
Feature activation-6.16e-01

Pos logit contributions
obal+1.475
acter+1.437
eware+1.363
ython+1.363
 Kimmel+1.335
Neg logit contributions
======-1.035
imaru-0.935
brush-0.917
-0.912
214-0.900
Token is
Token ID318
Feature activation-3.63e+00

Pos logit contributions
obal+0.471
acter+0.458
eware+0.434
ython+0.433
 Kimmel+0.428
Neg logit contributions
======-0.370
imaru-0.338
brush-0.333
-0.329
214-0.324
Token bullshit
Token ID20041
Feature activation-1.09e+01

Pos logit contributions
obal+2.478
acter+2.383
 Kimmel+2.274
ython+2.267
eware+2.254
Neg logit contributions
======-2.423
imaru-2.252
-2.200
brush-2.187
 toget-2.165
Token.
Token ID13
Feature activation-5.24e+00

Pos logit contributions
obal+6.783
acter+6.545
eware+6.426
 Kimmel+6.368
ython+6.366
Neg logit contributions
======-6.928
imaru-6.632
-6.504
▬▬-6.430
-6.339
Token
Token ID198
Feature activation-2.09e+00

Pos logit contributions
obal+3.919
acter+3.813
 Kimmel+3.676
eware+3.624
ython+3.616
Neg logit contributions
======-3.099
imaru-2.850
 toget-2.828
brush-2.787
-2.760
Token
Token ID198
Feature activation-1.22e+00

Pos logit contributions
obal+1.880
acter+1.835
ython+1.754
eware+1.754
 Kimmel+1.746
Neg logit contributions
======-0.970
imaru-0.864
brush-0.839
-0.833
 toget-0.830
TokenThere
Token ID1858
Feature activation+1.02e+00

Pos logit contributions
obal+1.017
acter+0.988
ython+0.942
eware+0.942
 Kimmel+0.931
Neg logit contributions
======-0.666
imaru-0.591
brush-0.583
-0.581
214-0.574
Token are
Token ID389
Feature activation-1.21e+00

Pos logit contributions
======+0.621
imaru+0.563
brush+0.555
+0.554
+0.542
Neg logit contributions
obal-0.774
acter-0.751
eware-0.712
ython-0.712
 Kimmel-0.704
Token2013
Token ID6390
Feature activation-9.85e+00

Pos logit contributions
======+1.307
214+1.152
+1.125
brush+1.121
imaru+1.094
Neg logit contributions
obal-2.443
acter-2.378
ython-2.295
eware-2.276
 Kimmel-2.263
Token Alec
Token ID38285
Feature activation-4.63e+00

Pos logit contributions
obal+5.660
 Kimmel+5.579
acter+5.407
 Pigs+5.119
 Lilly+5.092
Neg logit contributions
======-7.170
imaru-6.859
 toget-6.831
-6.631
brush-6.530
Token Baldwin
Token ID26402
Feature activation-3.27e+00

Pos logit contributions
obal+2.221
acter+2.105
 Kimmel+1.967
ython+1.929
eware+1.925
Neg logit contributions
======-4.054
imaru-3.829
 toget-3.789
-3.780
brush-3.764
Token
Token ID198
Feature activation-1.29e+00

Pos logit contributions
obal+2.879
acter+2.799
eware+2.684
 Kimmel+2.683
ython+2.676
Neg logit contributions
======-1.571
imaru-1.404
 toget-1.367
brush-1.366
-1.363
Token
Token ID198
Feature activation+3.04e+00

Pos logit contributions
obal+1.175
acter+1.146
eware+1.097
ython+1.096
 Kimmel+1.089
Neg logit contributions
======-0.588
imaru-0.520
brush-0.506
-0.501
-0.492
Token2013
Token ID6390
Feature activation-1.09e+01

Pos logit contributions
======+1.405
214+1.258
+1.197
brush+1.196
imaru+1.146
Neg logit contributions
obal-2.784
acter-2.710
ython-2.617
eware-2.593
 Kimmel-2.577
Token Jason
Token ID8982
Feature activation-2.06e+00

Pos logit contributions
obal+6.130
 Kimmel+6.083
acter+5.783
 Pigs+5.506
eware+5.467
Neg logit contributions
======-8.039
 toget-7.720
imaru-7.716
-7.488
brush-7.362
Token Bat
Token ID6577
Feature activation+2.17e-01

Pos logit contributions
obal+1.291
acter+1.243
ython+1.165
eware+1.163
 Kimmel+1.160
Neg logit contributions
======-1.518
imaru-1.409
brush-1.384
-1.381
-1.369
Tokeneman
Token ID8463
Feature activation+2.35e+00

Pos logit contributions
======+0.143
imaru+0.132
brush+0.131
+0.128
214+0.128
Neg logit contributions
obal-0.152
acter-0.146
ython-0.140
eware-0.138
 Kimmel-0.138
Token
Token ID198
Feature activation+2.79e-01

Pos logit contributions
======+1.206
imaru+1.080
brush+1.056
+1.048
 toget+1.033
Neg logit contributions
obal-2.020
acter-1.964
eware-1.881
 Kimmel-1.873
ython-1.872
Token
Token ID198
Feature activation+3.27e+00

Pos logit contributions
======+0.118
imaru+0.103
brush+0.101
214+0.099
+0.099
Neg logit contributions
obal-0.265
acter-0.259
eware-0.248
ython-0.248
 Kimmel-0.244
Token published
Token ID3199
Feature activation+3.18e+00

Pos logit contributions
======+2.101
imaru+1.946
brush+1.916
+1.891
214+1.877
Neg logit contributions
obal-2.499
acter-2.412
ython-2.290
eware-2.287
 Kimmel-2.231
Token in
Token ID287
Feature activation+2.19e+00

Pos logit contributions
======+1.887
imaru+1.734
brush+1.689
+1.677
 toget+1.668
Neg logit contributions
obal-2.428
acter-2.346
eware-2.231
ython-2.223
 Kimmel-2.192
Token N
Token ID399
Feature activation+5.68e-01

Pos logit contributions
======+1.425
imaru+1.331
+1.287
brush+1.282
214+1.271
Neg logit contributions
obal-1.533
acter-1.487
eware-1.422
ython-1.412
 Kimmel-1.377
Token.
Token ID13
Feature activation-9.25e-01

Pos logit contributions
======+0.340
imaru+0.311
brush+0.306
+0.303
214+0.299
Neg logit contributions
obal-0.434
acter-0.421
ython-0.400
eware-0.400
 Kimmel-0.397
Token Eng
Token ID1985
Feature activation+1.36e+00

Pos logit contributions
obal+0.686
acter+0.664
eware+0.630
ython+0.630
 Kimmel+0.622
Neg logit contributions
======-0.575
imaru-0.528
brush-0.518
-0.515
-0.508
Tokenl
Token ID75
Feature activation-1.09e+01

Pos logit contributions
======+0.613
brush+0.552
imaru+0.551
+0.535
cade+0.525
Neg logit contributions
obal-1.220
acter-1.179
ython-1.150
 Kimmel-1.129
eware-1.124
Token.
Token ID13
Feature activation-3.41e+00

Pos logit contributions
obal+7.323
acter+6.994
eware+6.455
 Kimmel+6.218
offer+6.129
Neg logit contributions
======-7.309
 toget-6.995
imaru-6.850
brush-6.812
-6.751
Token J
Token ID449
Feature activation-2.01e+00

Pos logit contributions
obal+1.719
acter+1.657
eware+1.518
ython+1.514
 Kimmel+1.501
Neg logit contributions
======-2.931
imaru-2.753
brush-2.708
-2.691
-2.680
Token.
Token ID13
Feature activation-2.33e-01

Pos logit contributions
obal+1.620
acter+1.564
eware+1.496
ython+1.495
 Kimmel+1.487
Neg logit contributions
======-1.120
imaru-1.019
brush-0.995
-0.985
214-0.977
Token Med
Token ID2019
Feature activation+1.54e+00

Pos logit contributions
obal+0.136
acter+0.126
ython+0.120
eware+0.119
 Kimmel+0.117
Neg logit contributions
======-0.181
imaru-0.171
brush-0.170
-0.168
214-0.168
Token.,
Token ID1539
Feature activation-6.37e-01

Pos logit contributions
======+0.836
imaru+0.754
brush+0.738
+0.732
+0.723
Neg logit contributions
obal-1.263
acter-1.233
eware-1.172
ython-1.170
 Kimmel-1.163
Token Guard
Token ID4932
Feature activation+1.69e-01

Pos logit contributions
obal+3.166
acter+3.088
eware+2.937
 Kimmel+2.915
ython+2.912
Neg logit contributions
======-2.823
imaru-2.621
brush-2.580
-2.554
-2.540
Token {
Token ID1391
Feature activation-2.33e+00

Pos logit contributions
======+0.097
imaru+0.088
brush+0.087
+0.086
+0.085
Neg logit contributions
obal-0.133
acter-0.129
eware-0.123
ython-0.123
 Kimmel-0.122
Token...
Token ID2644
Feature activation-8.55e-01

Pos logit contributions
obal+1.757
acter+1.712
eware+1.623
ython+1.610
 Kimmel+1.601
Neg logit contributions
======-1.417
imaru-1.298
brush-1.271
-1.262
-1.254
Token }
Token ID1782
Feature activation-2.49e+00

Pos logit contributions
obal+0.626
acter+0.607
eware+0.574
ython+0.573
 Kimmel+0.568
Neg logit contributions
======-0.541
imaru-0.496
brush-0.487
-0.484
-0.478
Token pub
Token ID2240
Feature activation+5.71e-01

Pos logit contributions
obal+2.050
acter+2.002
eware+1.910
ython+1.894
 Kimmel+1.880
Neg logit contributions
======-1.333
imaru-1.216
brush-1.187
-1.173
-1.164
Token fn
Token ID24714
Feature activation-1.09e+01

Pos logit contributions
======+0.343
imaru+0.313
brush+0.306
+0.305
+0.301
Neg logit contributions
obal-0.436
acter-0.423
ython-0.401
eware-0.401
 Kimmel-0.398
Token pin
Token ID6757
Feature activation+4.67e+00

Pos logit contributions
obal+6.846
acter+6.677
eware+6.390
 Kimmel+6.231
ython+6.161
Neg logit contributions
======-7.039
imaru-6.755
-6.591
brush-6.557
-6.521
Token ()
Token ID7499
Feature activation-1.64e+00

Pos logit contributions
======+2.396
imaru+2.179
brush+2.141
214+2.094
 toget+2.058
Neg logit contributions
obal-3.901
acter-3.787
 Kimmel-3.660
ython-3.625
eware-3.608
Token ->
Token ID4613
Feature activation-2.51e-01

Pos logit contributions
obal+1.426
acter+1.390
eware+1.327
ython+1.325
 Kimmel+1.317
Neg logit contributions
======-0.814
imaru-0.732
brush-0.712
-0.706
-0.699
Token Guard
Token ID4932
Feature activation+2.48e+00

Pos logit contributions
obal+0.188
acter+0.182
eware+0.173
ython+0.172
 Kimmel+0.170
Neg logit contributions
======-0.156
imaru-0.142
brush-0.140
-0.139
 toget-0.137
Token ;
Token ID2162
Feature activation+1.19e+00

Pos logit contributions
======+1.331
imaru+1.200
+1.166
brush+1.159
214+1.157
Neg logit contributions
obal-2.047
acter-1.988
eware-1.899
ython-1.896
 Kimmel-1.893
Token conversations
Token ID10275
Feature activation-2.34e+00

Pos logit contributions
======+0.130
imaru+0.119
brush+0.117
+0.116
+0.115
Neg logit contributions
obal-0.143
acter-0.140
ython-0.132
eware-0.131
 Kimmel-0.130
Token with
Token ID351
Feature activation+9.85e-01

Pos logit contributions
obal+1.842
acter+1.797
 Kimmel+1.716
eware+1.709
ython+1.703
Neg logit contributions
======-1.336
imaru-1.211
brush-1.191
-1.168
-1.154
Token point
Token ID966
Feature activation-4.34e+00

Pos logit contributions
======+0.620
imaru+0.572
+0.561
brush+0.557
 toget+0.553
Neg logit contributions
obal-0.716
acter-0.697
ython-0.660
eware-0.659
 Kimmel-0.645
Token guard
Token ID4860
Feature activation-5.16e+00

Pos logit contributions
obal+1.790
acter+1.667
eware+1.551
ython+1.502
 Kimmel+1.474
Neg logit contributions
======-4.099
imaru-3.871
brush-3.803
-3.779
▬▬-3.778
Token Ben
Token ID3932
Feature activation-4.88e+00

Pos logit contributions
obal+2.934
acter+2.803
eware+2.674
 Kimmel+2.648
ython+2.621
Neg logit contributions
======-4.029
imaru-3.782
-3.704
-3.673
brush-3.672
Tokeno
Token ID78
Feature activation-1.08e+01

Pos logit contributions
obal+3.232
acter+3.050
eware+2.960
 Kimmel+2.918
ython+2.892
Neg logit contributions
======-3.475
-3.153
 toget-3.092
-3.091
▬▬-3.066
Token U
Token ID471
Feature activation-6.18e+00

Pos logit contributions
acter+5.019
obal+4.916
 Kimmel+4.709
eware+4.707
ots+4.277
Neg logit contributions
======-8.750
 convol-8.549
imaru-8.471
milo-8.440
-8.400
Tokendri
Token ID7553
Feature activation-1.39e+00

Pos logit contributions
obal+5.489
acter+5.452
eware+5.232
ython+5.175
offer+5.054
Neg logit contributions
======-2.772
imaru-2.396
-2.352
▬▬-2.351
brush-2.287
Tokenh
Token ID71
Feature activation-3.65e+00

Pos logit contributions
obal+0.916
acter+0.897
eware+0.840
 Kimmel+0.834
ython+0.833
Neg logit contributions
======-0.977
brush-0.894
imaru-0.885
-0.874
214-0.868
Token,
Token ID11
Feature activation-2.70e-01

Pos logit contributions
obal+2.625
acter+2.539
ython+2.407
eware+2.402
 Kimmel+2.388
Neg logit contributions
======-2.325
imaru-2.123
brush-2.089
-2.076
-2.057
Token according
Token ID1864
Feature activation+1.73e+00

Pos logit contributions
obal+0.199
acter+0.193
ython+0.183
eware+0.183
 Kimmel+0.181
Neg logit contributions
======-0.170
imaru-0.156
brush-0.153
-0.152
 toget-0.150
Token actually
Token ID1682
Feature activation-6.11e-01

Pos logit contributions
obal+1.107
acter+1.071
eware+1.010
ython+1.009
 Kimmel+0.999
Neg logit contributions
======-1.092
imaru-1.008
brush-0.990
-0.984
-0.973
Token unacceptable
Token ID18010
Feature activation+2.49e+00

Pos logit contributions
obal+0.439
acter+0.424
eware+0.403
ython+0.401
 Kimmel+0.396
Neg logit contributions
======-0.395
imaru-0.363
brush-0.357
-0.354
 toget-0.350
Token,
Token ID11
Feature activation-3.05e-01

Pos logit contributions
======+1.398
imaru+1.269
brush+1.237
+1.219
 toget+1.217
Neg logit contributions
obal-1.994
acter-1.936
eware-1.850
ython-1.846
 Kimmel-1.819
Token how
Token ID703
Feature activation+4.70e+00

Pos logit contributions
obal+0.236
acter+0.229
eware+0.218
ython+0.217
 Kimmel+0.216
Neg logit contributions
======-0.180
imaru-0.164
brush-0.161
-0.160
-0.158
Token non
Token ID1729
Feature activation-5.51e+00

Pos logit contributions
======+2.863
brush+2.620
imaru+2.589
 toget+2.572
+2.560
Neg logit contributions
obal-3.483
acter-3.369
ython-3.251
eware-3.195
 Kimmel-3.066
Tokenchal
Token ID38009
Feature activation-1.08e+01

Pos logit contributions
obal+3.849
acter+3.723
eware+3.512
 Kimmel+3.439
ython+3.417
Neg logit contributions
======-3.601
imaru-3.373
-3.200
-3.165
brush-3.155
Tokenantly
Token ID3875
Feature activation-1.82e+00

Pos logit contributions
obal+4.740
acter+4.243
offer+3.777
eware+3.703
ython+3.695
Neg logit contributions
======-9.569
imaru-9.145
 toget-9.122
-8.969
 convol-8.865
Token some
Token ID617
Feature activation-7.79e-01

Pos logit contributions
obal+1.231
acter+1.192
eware+1.123
ython+1.121
 Kimmel+1.115
Neg logit contributions
======-1.242
imaru-1.149
brush-1.126
-1.121
-1.109
Token say
Token ID910
Feature activation-2.95e+00

Pos logit contributions
obal+0.566
acter+0.549
ython+0.519
eware+0.519
 Kimmel+0.514
Neg logit contributions
======-0.496
imaru-0.455
brush-0.447
-0.445
-0.439
Token that
Token ID326
Feature activation-6.31e-01

Pos logit contributions
obal+2.013
acter+1.947
eware+1.842
ython+1.826
 Kimmel+1.824
Neg logit contributions
======-2.005
imaru-1.853
brush-1.807
-1.805
-1.786
Token it
Token ID340
Feature activation+3.77e-01

Pos logit contributions
obal+0.443
acter+0.429
ython+0.406
eware+0.404
 Kimmel+0.398
Neg logit contributions
======-0.419
imaru-0.385
brush-0.381
-0.377
 toget-0.375
Token not
Token ID407
Feature activation+3.17e+00

Pos logit contributions
======+1.502
imaru+1.384
brush+1.366
+1.352
214+1.343
Neg logit contributions
obal-1.819
acter-1.742
ython-1.669
 Kimmel-1.662
eware-1.659
Token have
Token ID423
Feature activation+2.87e+00

Pos logit contributions
======+1.891
imaru+1.731
brush+1.721
 toget+1.699
214+1.695
Neg logit contributions
obal-2.376
acter-2.282
ython-2.187
eware-2.180
 Kimmel-2.179
Token qualified
Token ID10617
Feature activation+3.26e+00

Pos logit contributions
======+1.511
imaru+1.370
brush+1.367
+1.345
 toget+1.336
Neg logit contributions
obal-2.375
acter-2.283
ython-2.223
eware-2.212
 Kimmel-2.153
Token for
Token ID329
Feature activation-5.25e-01

Pos logit contributions
======+1.811
imaru+1.651
brush+1.610
 toget+1.593
+1.588
Neg logit contributions
obal-2.614
acter-2.543
eware-2.437
ython-2.407
 Kimmel-2.376
Token the
Token ID262
Feature activation-6.74e-01

Pos logit contributions
obal+0.375
acter+0.364
eware+0.346
ython+0.346
 Kimmel+0.339
Neg logit contributions
======-0.339
imaru-0.311
brush-0.305
-0.303
214-0.299
Token scholarship
Token ID18652
Feature activation-1.07e+01

Pos logit contributions
obal+0.473
acter+0.459
eware+0.438
ython+0.437
 Kimmel+0.424
Neg logit contributions
======-0.443
imaru-0.407
brush-0.400
-0.398
214-0.393
Token under
Token ID739
Feature activation+2.72e-01

Pos logit contributions
obal+7.039
acter+6.629
 Kimmel+6.538
 equivalents+6.359
ython+6.308
Neg logit contributions
======-7.077
imaru-6.533
-6.452
▬▬-6.393
214-6.275
Token the
Token ID262
Feature activation-9.10e-01

Pos logit contributions
======+0.172
imaru+0.158
brush+0.156
+0.154
+0.152
Neg logit contributions
obal-0.199
acter-0.193
eware-0.182
ython-0.182
 Kimmel-0.179
Token new
Token ID649
Feature activation-4.96e+00

Pos logit contributions
obal+0.705
acter+0.688
eware+0.655
ython+0.653
 Kimmel+0.639
Neg logit contributions
======-0.534
imaru-0.486
brush-0.478
-0.477
-0.468
Token rules
Token ID3173
Feature activation-1.60e+00

Pos logit contributions
obal+3.713
acter+3.595
 Kimmel+3.430
eware+3.412
ython+3.398
Neg logit contributions
======-3.014
imaru-2.768
brush-2.694
 toget-2.661
-2.660
Token because
Token ID780
Feature activation+3.68e-01

Pos logit contributions
obal+1.192
acter+1.156
eware+1.095
ython+1.095
 Kimmel+1.088
Neg logit contributions
======-0.987
imaru-0.903
brush-0.886
-0.881
-0.868
Token
Token ID198
Feature activation+2.71e+00

Pos logit contributions
======+0.654
imaru+0.551
brush+0.546
214+0.543
+0.529
Neg logit contributions
obal-1.584
acter-1.544
eware-1.486
ython-1.478
 Kimmel-1.459
Tokenimpl
Token ID23928
Feature activation-3.76e+00

Pos logit contributions
======+1.547
imaru+1.371
brush+1.366
+1.347
214+1.341
Neg logit contributions
obal-2.171
acter-2.104
 Kimmel-2.012
ython-2.002
eware-1.992
Token Board
Token ID5926
Feature activation+2.49e+00

Pos logit contributions
obal+3.208
acter+3.108
ython+2.962
eware+2.955
 Kimmel+2.911
Neg logit contributions
======-1.878
imaru-1.732
brush-1.699
-1.689
-1.672
Token {
Token ID1391
Feature activation-3.02e+00

Pos logit contributions
======+1.360
imaru+1.207
brush+1.196
+1.183
214+1.180
Neg logit contributions
obal-2.040
acter-1.978
 Kimmel-1.882
ython-1.879
eware-1.873
Token pub
Token ID2240
Feature activation+2.68e-01

Pos logit contributions
obal+2.234
acter+2.157
eware+2.055
ython+2.033
 Kimmel+2.015
Neg logit contributions
======-1.869
imaru-1.732
-1.685
brush-1.683
-1.682
Token fn
Token ID24714
Feature activation-1.07e+01

Pos logit contributions
======+0.159
imaru+0.145
brush+0.142
+0.141
214+0.139
Neg logit contributions
obal-0.207
acter-0.200
ython-0.191
eware-0.190
 Kimmel-0.189
Token copy
Token ID4866
Feature activation-7.69e-01

Pos logit contributions
acter+6.664
obal+6.613
eware+6.042
 Kimmel+5.997
 equivalents+5.986
Neg logit contributions
======-6.902
imaru-6.787
-6.734
-6.690
cade-6.458
Token_
Token ID62
Feature activation-1.56e+00

Pos logit contributions
obal+0.583
acter+0.569
ython+0.538
eware+0.537
 Kimmel+0.529
Neg logit contributions
======-0.465
imaru-0.427
-0.415
brush-0.414
-0.411
Tokenboard
Token ID3526
Feature activation+4.30e+00

Pos logit contributions
obal+1.236
acter+1.203
eware+1.141
ython+1.140
 Kimmel+1.127
Neg logit contributions
======-0.894
imaru-0.814
-0.793
brush-0.792
-0.783
Token (
Token ID357
Feature activation+1.44e-01

Pos logit contributions
======+2.503
imaru+2.267
214+2.231
brush+2.229
+2.202
Neg logit contributions
obal-3.318
acter-3.198
ython-3.058
 Kimmel-3.056
eware-3.040
Token &
Token ID1222
Feature activation-1.61e+00

Pos logit contributions
======+0.082
imaru+0.074
brush+0.073
+0.072
 toget+0.071
Neg logit contributions
obal-0.115
acter-0.112
eware-0.106
ython-0.106
 Kimmel-0.106
Token people
Token ID661
Feature activation-6.83e-01

Pos logit contributions
======+0.126
imaru+0.116
brush+0.114
+0.114
 toget+0.113
Neg logit contributions
obal-0.123
acter-0.119
eware-0.113
ython-0.113
 Kimmel-0.111
Token because
Token ID780
Feature activation+3.15e-01

Pos logit contributions
obal+0.521
acter+0.506
eware+0.480
ython+0.480
 Kimmel+0.475
Neg logit contributions
======-0.411
imaru-0.375
brush-0.368
-0.365
-0.361
Token you
Token ID345
Feature activation+2.45e+00

Pos logit contributions
======+0.213
imaru+0.198
brush+0.196
 toget+0.193
+0.193
Neg logit contributions
obal-0.216
acter-0.209
eware-0.198
ython-0.198
 Kimmel-0.190
Token guys
Token ID3730
Feature activation+3.50e+00

Pos logit contributions
======+1.450
brush+1.317
imaru+1.304
+1.282
214+1.277
Neg logit contributions
obal-1.883
acter-1.827
eware-1.735
ython-1.732
 Kimmel-1.716
Token feel
Token ID1254
Feature activation-3.27e-02

Pos logit contributions
======+2.075
brush+1.880
imaru+1.859
214+1.819
 toget+1.817
Neg logit contributions
obal-2.670
acter-2.598
eware-2.475
ython-2.473
 Kimmel-2.405
Token torn
Token ID12445
Feature activation-1.06e+01

Pos logit contributions
obal+0.024
acter+0.023
eware+0.022
ython+0.022
 Kimmel+0.022
Neg logit contributions
======-0.021
imaru-0.019
brush-0.019
-0.018
 toget-0.018
Token.
Token ID13
Feature activation-1.41e+00

Pos logit contributions
obal+6.261
acter+6.022
eware+5.789
 Kimmel+5.753
ython+5.642
Neg logit contributions
======-7.410
imaru-6.974
-6.770
brush-6.733
rouse-6.720
Token You
Token ID921
Feature activation+1.49e+00

Pos logit contributions
obal+1.059
acter+1.030
eware+0.975
ython+0.974
 Kimmel+0.948
Neg logit contributions
======-0.881
imaru-0.804
brush-0.791
-0.787
-0.777
Token
Token ID447
Feature activation+1.36e+00

Pos logit contributions
======+0.943
brush+0.858
imaru+0.856
+0.845
+0.833
Neg logit contributions
obal-1.091
acter-1.061
eware-1.005
ython-0.996
 Kimmel-0.991
Token
Token ID247
Feature activation+1.83e+00

Pos logit contributions
======+0.902
imaru+0.822
brush+0.814
+0.812
214+0.805
Neg logit contributions
obal-0.960
acter-0.921
eware-0.884
ython-0.878
 Kimmel-0.861
Tokenre
Token ID260
Feature activation-9.68e-01

Pos logit contributions
======+1.054
imaru+0.957
brush+0.942
+0.935
214+0.918
Neg logit contributions
obal-1.433
acter-1.392
ython-1.326
eware-1.320
 Kimmel-1.314
Token which
Token ID543
Feature activation+1.62e-01

Pos logit contributions
obal+1.059
acter+1.023
ython+0.966
eware+0.965
 Kimmel+0.949
Neg logit contributions
======-1.046
imaru-0.965
brush-0.950
-0.942
 toget-0.934
Token are
Token ID389
Feature activation-1.30e+00

Pos logit contributions
======+0.103
imaru+0.095
brush+0.093
+0.092
 toget+0.091
Neg logit contributions
obal-0.119
acter-0.115
eware-0.109
ython-0.108
 Kimmel-0.106
Token in
Token ID287
Feature activation+6.13e-01

Pos logit contributions
obal+0.901
acter+0.872
ython+0.823
eware+0.822
 Kimmel+0.813
Neg logit contributions
======-0.869
imaru-0.801
brush-0.787
-0.782
-0.774
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
======+0.404
imaru+0.369
brush+0.362
+0.361
 toget+0.356
Neg logit contributions
obal-0.435
acter-0.423
ython-0.400
eware-0.399
 Kimmel-0.389
Token nond
Token ID30745
Feature activation-8.06e-01

Pos logit contributions
obal+0.967
acter+0.936
eware+0.882
ython+0.882
 Kimmel+0.873
Neg logit contributions
======-0.960
imaru-0.886
brush-0.871
-0.866
-0.856
Tokenesc
Token ID3798
Feature activation-1.05e+01

Pos logit contributions
obal+0.304
acter+0.286
eware+0.257
ython+0.255
 Kimmel+0.249
Neg logit contributions
======-0.801
imaru-0.755
-0.746
brush-0.744
 toget-0.740
Tokenript
Token ID1968
Feature activation-4.00e+00

Pos logit contributions
obal+5.232
acter+4.786
eware+4.269
ython+4.193
offer+4.079
Neg logit contributions
======-8.991
imaru-8.520
-8.507
▬▬-8.426
-8.393
Token pre
Token ID662
Feature activation-1.75e-01

Pos logit contributions
obal+2.561
acter+2.472
 Kimmel+2.335
eware+2.332
ython+2.311
Neg logit contributions
======-2.848
imaru-2.659
-2.592
brush-2.591
-2.586
Tokenwar
Token ID5767
Feature activation-3.73e+00

Pos logit contributions
obal+0.133
acter+0.129
ython+0.123
eware+0.121
 Kimmel+0.121
Neg logit contributions
======-0.106
imaru-0.097
brush-0.096
-0.095
214-0.094
Token building
Token ID2615
Feature activation-4.42e-02

Pos logit contributions
obal+2.466
acter+2.392
eware+2.254
 Kimmel+2.253
ython+2.235
Neg logit contributions
======-2.586
imaru-2.400
-2.342
brush-2.342
-2.324
Token overlooking
Token ID34603
Feature activation-2.82e+00

Pos logit contributions
obal+0.032
acter+0.031
ython+0.029
eware+0.029
 Kimmel+0.029
Neg logit contributions
======-0.028
imaru-0.026
brush-0.026
-0.025
 toget-0.025
Token
Token ID198
Feature activation-2.80e+00

Pos logit contributions
obal+2.613
acter+2.548
ython+2.435
 Kimmel+2.430
eware+2.430
Neg logit contributions
======-1.427
imaru-1.285
 toget-1.270
brush-1.242
-1.238
TokenIn
Token ID818
Feature activation-3.28e-01

Pos logit contributions
obal+2.266
acter+2.204
eware+2.097
ython+2.095
 Kimmel+2.080
Neg logit contributions
======-1.536
imaru-1.397
brush-1.362
-1.351
 toget-1.342
Token a
Token ID257
Feature activation-4.87e-01

Pos logit contributions
obal+0.240
acter+0.233
eware+0.220
ython+0.220
 Kimmel+0.217
Neg logit contributions
======-0.209
imaru-0.192
brush-0.189
-0.187
214-0.184
Token way
Token ID835
Feature activation+2.62e-01

Pos logit contributions
obal+0.352
acter+0.341
eware+0.322
ython+0.321
 Kimmel+0.316
Neg logit contributions
======-0.314
imaru-0.289
brush-0.283
-0.281
-0.278
Token,
Token ID11
Feature activation-1.24e+00

Pos logit contributions
======+0.162
imaru+0.148
brush+0.145
+0.144
214+0.143
Neg logit contributions
obal-0.196
acter-0.189
ython-0.180
eware-0.179
 Kimmel-0.179
Token Julia
Token ID22300
Feature activation-1.05e+01

Pos logit contributions
obal+0.864
acter+0.837
eware+0.790
ython+0.788
 Kimmel+0.779
Neg logit contributions
======-0.826
imaru-0.760
brush-0.747
-0.743
-0.734
Token H
Token ID367
Feature activation-2.30e+00

Pos logit contributions
obal+4.968
 Kimmel+4.787
acter+4.586
ython+4.518
offer+4.335
Neg logit contributions
======-8.536
imaru-7.900
milo-7.724
 toget-7.711
brush-7.691
Tokenahn
Token ID15386
Feature activation+5.05e-01

Pos logit contributions
obal+1.635
acter+1.584
eware+1.496
ython+1.496
 Kimmel+1.480
Neg logit contributions
======-1.498
imaru-1.376
brush-1.350
-1.345
 toget-1.333
Token is
Token ID318
Feature activation-2.53e+00

Pos logit contributions
======+0.300
imaru+0.274
brush+0.270
+0.269
+0.263
Neg logit contributions
obal-0.387
acter-0.379
eware-0.358
ython-0.358
 Kimmel-0.352
Token the
Token ID262
Feature activation-1.98e+00

Pos logit contributions
obal+1.771
acter+1.715
eware+1.618
ython+1.615
 Kimmel+1.608
Neg logit contributions
======-1.674
imaru-1.543
brush-1.515
-1.506
-1.487
Token Patty
Token ID42417
Feature activation+5.70e-01

Pos logit contributions
obal+1.360
acter+1.316
ython+1.241
eware+1.241
 Kimmel+1.222
Neg logit contributions
======-1.344
imaru-1.233
brush-1.217
-1.211
-1.195
Token Is
Token ID1148
Feature activation-2.92e+00

Pos logit contributions
======+0.968
imaru+0.887
brush+0.881
+0.868
214+0.861
Neg logit contributions
obal-1.103
acter-1.078
ython-1.024
eware-1.012
 Kimmel-0.992
Token an
Token ID281
Feature activation+6.64e-02

Pos logit contributions
obal+2.009
acter+1.943
eware+1.835
 Kimmel+1.831
ython+1.817
Neg logit contributions
======-1.962
imaru-1.807
brush-1.774
-1.774
 toget-1.751
Token Acc
Token ID6366
Feature activation+4.86e+00

Pos logit contributions
======+0.044
imaru+0.041
brush+0.040
+0.040
214+0.039
Neg logit contributions
obal-0.046
acter-0.045
ython-0.042
eware-0.042
 Kimmel-0.042
Tokenompl
Token ID6316
Feature activation-1.50e+00

Pos logit contributions
======+3.101
imaru+2.940
brush+2.893
214+2.821
+2.806
Neg logit contributions
obal-3.358
acter-3.182
ython-3.049
 Kimmel-3.048
eware-3.022
Tokenished
Token ID1348
Feature activation-2.34e+00

Pos logit contributions
obal+0.743
acter+0.713
eware+0.645
ython+0.636
 Kimmel+0.629
Neg logit contributions
======-1.323
imaru-1.230
brush-1.223
 toget-1.215
-1.212
Token Travel
Token ID13524
Feature activation-1.03e+01

Pos logit contributions
obal+1.615
acter+1.564
eware+1.475
ython+1.473
 Kimmel+1.462
Neg logit contributions
======-1.570
imaru-1.448
brush-1.422
-1.414
-1.398
Token Writer
Token ID26606
Feature activation-2.66e+00

Pos logit contributions
obal+6.595
acter+6.390
eware+6.008
 Kimmel+5.953
offer+5.866
Neg logit contributions
======-7.133
imaru-6.747
 toget-6.561
▬▬-6.381
 convol-6.372
Token
Token ID198
Feature activation-4.04e-01

Pos logit contributions
obal+2.192
acter+2.130
eware+2.044
 Kimmel+2.036
ython+2.024
Neg logit contributions
======-1.411
imaru-1.284
-1.246
brush-1.242
-1.229
Token
Token ID198
Feature activation+5.50e-01

Pos logit contributions
obal+0.377
acter+0.367
eware+0.352
ython+0.352
 Kimmel+0.348
Neg logit contributions
======-0.177
imaru-0.154
brush-0.151
-0.149
214-0.148
TokenA
Token ID32
Feature activation+1.50e+00

Pos logit contributions
======+0.303
imaru+0.271
brush+0.266
+0.265
214+0.261
Neg logit contributions
obal-0.451
acter-0.438
ython-0.418
eware-0.417
 Kimmel-0.414
Token birth
Token ID4082
Feature activation-1.54e+00

Pos logit contributions
======+0.986
imaru+0.905
brush+0.887
+0.884
214+0.876
Neg logit contributions
obal-1.071
acter-1.032
ython-0.974
eware-0.971
 Kimmel-0.960
Token end
Token ID886
Feature activation-3.31e+00

Pos logit contributions
obal+1.905
acter+1.853
eware+1.749
ython+1.747
 Kimmel+1.733
Neg logit contributions
======-1.790
imaru-1.647
brush-1.608
-1.607
-1.586
Token of
Token ID286
Feature activation-2.27e+00

Pos logit contributions
obal+2.427
acter+2.386
eware+2.252
ython+2.247
 Kimmel+2.229
Neg logit contributions
======-2.050
imaru-1.871
-1.836
brush-1.819
-1.807
Token the
Token ID262
Feature activation-3.80e+00

Pos logit contributions
obal+1.559
acter+1.521
eware+1.435
ython+1.430
 Kimmel+1.421
Neg logit contributions
======-1.529
imaru-1.402
brush-1.378
-1.375
-1.364
Token thread
Token ID4704
Feature activation-2.24e+00

Pos logit contributions
obal+2.743
acter+2.683
eware+2.543
ython+2.532
 Kimmel+2.520
Neg logit contributions
======-2.416
imaru-2.208
-2.151
brush-2.149
214-2.136
Token.
Token ID13
Feature activation+1.49e-02

Pos logit contributions
obal+1.708
acter+1.672
eware+1.585
ython+1.580
 Kimmel+1.564
Neg logit contributions
======-1.343
imaru-1.223
-1.197
brush-1.189
-1.178
Token Sew
Token ID27347
Feature activation+6.02e+00

Pos logit contributions
======+0.009
imaru+0.008
brush+0.008
+0.008
214+0.008
Neg logit contributions
obal-0.012
acter-0.011
ython-0.011
eware-0.011
 Kimmel-0.010
Token on
Token ID319
Feature activation+3.17e+00

Pos logit contributions
======+3.604
brush+3.376
imaru+3.282
 toget+3.276
+3.176
Neg logit contributions
obal-4.450
acter-4.250
ython-4.078
eware-4.016
 Kimmel-3.985
Token a
Token ID257
Feature activation+1.56e+00

Pos logit contributions
======+2.003
brush+1.852
imaru+1.847
 toget+1.822
+1.783
Neg logit contributions
obal-2.296
acter-2.201
ython-2.103
eware-2.074
 Kimmel-2.041
Token button
Token ID4936
Feature activation+4.41e+00

Pos logit contributions
======+0.991
imaru+0.914
brush+0.911
+0.894
 toget+0.886
Neg logit contributions
obal-1.140
acter-1.102
eware-1.044
ython-1.043
 Kimmel-1.025
Token:
Token ID25
Feature activation-1.70e+00

Pos logit contributions
======+2.338
brush+2.165
imaru+2.144
 toget+2.075
214+2.047
Neg logit contributions
obal-3.641
acter-3.459
ython-3.294
eware-3.289
 Kimmel-3.261
Token One
Token ID1881
Feature activation-8.26e-01

Pos logit contributions
obal+1.287
acter+1.247
ython+1.180
eware+1.178
 Kimmel+1.162
Neg logit contributions
======-1.040
imaru-0.949
brush-0.935
-0.926
-0.914
Token,
Token ID11
Feature activation-3.48e-01

Pos logit contributions
obal+0.550
acter+0.535
eware+0.509
ython+0.507
 Kimmel+0.502
Neg logit contributions
======-0.424
imaru-0.387
brush-0.379
-0.376
-0.371
Token as
Token ID355
Feature activation-4.01e+00

Pos logit contributions
obal+0.268
acter+0.260
ython+0.247
eware+0.246
 Kimmel+0.245
Neg logit contributions
======-0.208
imaru-0.189
brush-0.186
-0.185
 toget-0.182
Token you
Token ID345
Feature activation+2.42e+00

Pos logit contributions
obal+2.599
acter+2.514
eware+2.375
ython+2.339
 Kimmel+2.323
Neg logit contributions
======-2.802
imaru-2.613
brush-2.581
-2.563
-2.538
Token may
Token ID743
Feature activation+6.18e-01

Pos logit contributions
======+1.428
imaru+1.280
+1.277
brush+1.262
214+1.238
Neg logit contributions
obal-1.880
acter-1.826
ython-1.739
eware-1.729
 Kimmel-1.727
Token find
Token ID1064
Feature activation+1.78e+00

Pos logit contributions
======+0.395
imaru+0.362
brush+0.355
+0.354
 toget+0.350
Neg logit contributions
obal-0.449
acter-0.434
ython-0.412
eware-0.412
 Kimmel-0.408
Token yourself
Token ID3511
Feature activation+6.10e+00

Pos logit contributions
======+1.119
imaru+1.017
+1.004
brush+0.992
 toget+0.983
Neg logit contributions
obal-1.321
acter-1.277
ython-1.215
eware-1.214
 Kimmel-1.201
Token stuck
Token ID7819
Feature activation+1.21e+00

Pos logit contributions
======+3.812
imaru+3.500
+3.471
 toget+3.387
brush+3.346
Neg logit contributions
obal-4.355
acter-4.223
ython-4.086
eware-4.071
 Kimmel-3.917
Token with
Token ID351
Feature activation-2.18e-01

Pos logit contributions
======+0.725
imaru+0.655
+0.645
brush+0.641
 toget+0.637
Neg logit contributions
obal-0.926
acter-0.898
ython-0.854
eware-0.852
 Kimmel-0.843
Token the
Token ID262
Feature activation-9.11e-01

Pos logit contributions
obal+0.155
acter+0.150
eware+0.142
ython+0.142
 Kimmel+0.141
Neg logit contributions
======-0.143
imaru-0.131
brush-0.129
-0.128
 toget-0.126
Token Token
Token ID29130
Feature activation+2.99e-01

Pos logit contributions
obal+0.673
acter+0.653
eware+0.618
ython+0.618
 Kimmel+0.613
Neg logit contributions
======-0.570
imaru-0.522
brush-0.512
-0.509
-0.502
Token while
Token ID981
Feature activation+1.46e+00

Pos logit contributions
======+0.185
imaru+0.169
brush+0.166
+0.166
 toget+0.163
Neg logit contributions
obal-0.223
acter-0.217
eware-0.205
ython-0.205
 Kimmel-0.203
Token on
Token ID319
Feature activation+2.39e+00

Pos logit contributions
======+1.580
imaru+1.420
brush+1.404
+1.379
214+1.374
Neg logit contributions
obal-2.207
acter-2.168
eware-2.067
ython-2.043
 Kimmel-2.005
Token the
Token ID262
Feature activation+2.01e+00

Pos logit contributions
======+1.449
imaru+1.341
brush+1.322
214+1.300
+1.294
Neg logit contributions
obal-1.759
acter-1.724
ython-1.650
eware-1.637
 Kimmel-1.582
Token slippery
Token ID32911
Feature activation-2.94e-02

Pos logit contributions
======+1.280
imaru+1.156
brush+1.150
+1.134
214+1.127
Neg logit contributions
obal-1.429
acter-1.406
ython-1.350
eware-1.324
 Kimmel-1.281
Token Cleveland
Token ID10306
Feature activation+3.02e+00

Pos logit contributions
obal+0.020
acter+0.019
ython+0.018
eware+0.018
 Kimmel+0.018
Neg logit contributions
======-0.020
imaru-0.019
brush-0.018
-0.018
214-0.018
Token Stadium
Token ID10499
Feature activation-4.24e-01

Pos logit contributions
======+1.973
brush+1.842
imaru+1.823
214+1.776
+1.775
Neg logit contributions
obal-2.080
acter-2.029
ython-1.938
eware-1.897
 Kimmel-1.871
Token sod
Token ID32581
Feature activation+7.42e+00

Pos logit contributions
obal+0.321
acter+0.312
ython+0.296
eware+0.295
 Kimmel+0.292
Neg logit contributions
======-0.257
imaru-0.235
brush-0.231
-0.229
214-0.226
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
======+3.929
imaru+3.696
brush+3.632
cade+3.422
214+3.417
Neg logit contributions
obal-5.890
acter-5.796
ython-5.498
 Kimmel-5.447
eware-5.426
Token the
Token ID262
Feature activation+2.42e-01

Pos logit contributions
======+1.137
imaru+1.043
brush+1.029
+1.012
214+0.995
Neg logit contributions
obal-1.526
acter-1.481
eware-1.415
ython-1.407
 Kimmel-1.379
Token Rams
Token ID16077
Feature activation-3.55e+00

Pos logit contributions
======+0.207
imaru+0.194
brush+0.192
+0.190
214+0.189
Neg logit contributions
obal-0.123
acter-0.118
ython-0.109
eware-0.109
 Kimmel-0.106
Token ran
Token ID4966
Feature activation+1.54e+00

Pos logit contributions
obal+2.506
acter+2.413
eware+2.290
ython+2.278
 Kimmel+2.278
Neg logit contributions
======-2.315
imaru-2.147
brush-2.090
-2.077
-2.065
Token out
Token ID503
Feature activation-8.07e-02

Pos logit contributions
======+0.889
brush+0.803
imaru+0.803
+0.795
 toget+0.786
Neg logit contributions
obal-1.199
acter-1.164
ython-1.116
eware-1.103
 Kimmel-1.079
Token talk
Token ID1561
Feature activation+6.48e-01

Pos logit contributions
======+0.150
imaru+0.137
brush+0.135
+0.134
214+0.132
Neg logit contributions
obal-0.185
acter-0.180
ython-0.170
eware-0.170
 Kimmel-0.167
Token of
Token ID286
Feature activation+1.25e+00

Pos logit contributions
======+0.411
imaru+0.377
brush+0.369
+0.366
+0.363
Neg logit contributions
obal-0.474
acter-0.459
eware-0.434
ython-0.434
 Kimmel-0.431
Token
Token ID564
Feature activation+1.29e-01

Pos logit contributions
======+0.796
imaru+0.728
brush+0.720
+0.715
 toget+0.707
Neg logit contributions
obal-0.902
acter-0.878
ython-0.833
eware-0.828
 Kimmel-0.815
Token
Token ID250
Feature activation+2.24e+00

Pos logit contributions
======+0.083
imaru+0.076
brush+0.075
+0.074
+0.073
Neg logit contributions
obal-0.093
acter-0.090
eware-0.085
ython-0.085
 Kimmel-0.084
Tokenpolitical
Token ID23149
Feature activation+3.75e+00

Pos logit contributions
======+1.459
brush+1.331
+1.318
imaru+1.313
+1.299
Neg logit contributions
obal-1.590
acter-1.543
ython-1.472
eware-1.461
 Kimmel-1.454
Token polarization
Token ID42704
Feature activation+6.42e+00

Pos logit contributions
======+2.245
+2.051
brush+2.001
imaru+1.984
 grievances+1.973
Neg logit contributions
obal-2.846
acter-2.783
ython-2.627
eware-2.623
 Kimmel-2.575
Token,
Token ID11
Feature activation+1.13e+00

Pos logit contributions
======+3.776
+3.393
brush+3.388
imaru+3.379
 toget+3.371
Neg logit contributions
obal-4.807
acter-4.729
ython-4.431
eware-4.430
 Kimmel-4.344
Token
Token ID447
Feature activation-6.62e-01

Pos logit contributions
======+0.816
imaru+0.753
brush+0.744
+0.743
 toget+0.733
Neg logit contributions
obal-0.720
acter-0.698
eware-0.655
ython-0.652
 Kimmel-0.639
Token
Token ID251
Feature activation-3.41e-01

Pos logit contributions
obal+0.456
acter+0.440
eware+0.417
ython+0.415
 Kimmel+0.409
Neg logit contributions
======-0.451
imaru-0.414
brush-0.408
-0.407
-0.401
Token Mac
Token ID4100
Feature activation-1.31e+00

Pos logit contributions
obal+0.237
acter+0.230
eware+0.217
ython+0.217
 Kimmel+0.215
Neg logit contributions
======-0.228
imaru-0.210
brush-0.206
-0.205
-0.203
Tokenri
Token ID380
Feature activation+1.71e-01

Pos logit contributions
obal+0.868
acter+0.840
eware+0.792
ython+0.788
 Kimmel+0.785
Neg logit contributions
======-0.919
imaru-0.853
brush-0.838
-0.831
214-0.821
Token as
Token ID355
Feature activation-2.71e+00

Pos logit contributions
obal+1.161
acter+1.125
ython+1.057
eware+1.056
 Kimmel+1.055
Neg logit contributions
======-1.078
imaru-0.997
brush-0.971
-0.968
-0.962
Token manager
Token ID4706
Feature activation-2.27e-01

Pos logit contributions
obal+1.874
acter+1.813
eware+1.706
 Kimmel+1.704
ython+1.697
Neg logit contributions
======-1.829
imaru-1.685
brush-1.649
-1.639
-1.631
Token Mike
Token ID4995
Feature activation+1.79e+00

Pos logit contributions
obal+0.154
acter+0.149
eware+0.140
ython+0.140
 Kimmel+0.140
Neg logit contributions
======-0.155
imaru-0.143
brush-0.141
-0.140
-0.139
Token Mat
Token ID6550
Feature activation+6.01e+00

Pos logit contributions
======+1.233
imaru+1.139
brush+1.117
+1.116
+1.104
Neg logit contributions
obal-1.214
acter-1.170
ython-1.105
eware-1.104
 Kimmel-1.099
Tokenheny
Token ID47413
Feature activation+3.24e+00

Pos logit contributions
======+1.588
imaru+1.529
brush+1.422
214+1.406
cade+1.350
Neg logit contributions
obal-6.246
acter-6.150
 Kimmel-5.963
eware-5.909
ython-5.879
Token put
Token ID1234
Feature activation+7.01e+00

Pos logit contributions
======+1.951
imaru+1.798
brush+1.785
+1.770
214+1.750
Neg logit contributions
obal-2.425
acter-2.365
ython-2.250
eware-2.234
 Kimmel-2.181
Token it
Token ID340
Feature activation+2.23e+00

Pos logit contributions
======+4.976
imaru+4.678
brush+4.642
+4.602
 toget+4.587
Neg logit contributions
obal-4.402
acter-4.185
ython-4.034
eware-3.979
 Kimmel-3.853
Token,
Token ID11
Feature activation+9.60e-01

Pos logit contributions
======+1.331
imaru+1.215
brush+1.190
+1.182
+1.167
Neg logit contributions
obal-1.715
acter-1.665
eware-1.581
ython-1.580
 Kimmel-1.565
Token has
Token ID468
Feature activation+1.19e+00

Pos logit contributions
======+0.613
imaru+0.562
brush+0.553
+0.550
 toget+0.542
Neg logit contributions
obal-0.696
acter-0.676
eware-0.640
ython-0.639
 Kimmel-0.632
Token been
Token ID587
Feature activation+2.81e+00

Pos logit contributions
======+0.738
imaru+0.669
brush+0.662
+0.660
 toget+0.651
Neg logit contributions
obal-0.882
acter-0.855
eware-0.816
ython-0.813
 Kimmel-0.804
Token an
Token ID281
Feature activation+3.36e+00

Pos logit contributions
======+1.779
imaru+1.615
+1.598
brush+1.592
 toget+1.589
Neg logit contributions
obal-2.031
acter-1.958
ython-1.889
eware-1.864
 Kimmel-1.831
Token immersion
Token ID36375
Feature activation-4.62e-01

Pos logit contributions
obal+1.424
acter+1.383
eware+1.309
ython+1.308
 Kimmel+1.297
Neg logit contributions
======-1.212
imaru-1.115
brush-1.091
-1.084
-1.073
Token
Token ID784
Feature activation+1.68e+00

Pos logit contributions
obal+0.349
acter+0.339
eware+0.321
ython+0.321
 Kimmel+0.318
Neg logit contributions
======-0.282
imaru-0.257
brush-0.252
-0.251
-0.247
Token it
Token ID340
Feature activation+3.72e+00

Pos logit contributions
======+1.099
imaru+0.992
brush+0.980
+0.978
 toget+0.962
Neg logit contributions
obal-1.202
acter-1.161
ython-1.098
eware-1.094
 Kimmel-1.087
Token is
Token ID318
Feature activation+4.52e+00

Pos logit contributions
======+1.961
brush+1.752
imaru+1.747
+1.705
 toget+1.691
Neg logit contributions
obal-3.075
acter-2.988
ython-2.833
eware-2.828
 Kimmel-2.805
Token your
Token ID534
Feature activation+3.99e+00

Pos logit contributions
======+2.770
brush+2.428
imaru+2.420
 toget+2.408
214+2.399
Neg logit contributions
obal-3.390
acter-3.257
ython-3.127
eware-3.080
 Kimmel-3.035
Token job
Token ID1693
Feature activation+1.77e+00

Pos logit contributions
======+2.788
imaru+2.494
+2.485
brush+2.458
 toget+2.440
Neg logit contributions
obal-2.693
acter-2.564
eware-2.439
ython-2.429
 Kimmel-2.387
Token to
Token ID284
Feature activation+5.04e-01

Pos logit contributions
======+1.009
imaru+0.915
brush+0.896
+0.890
+0.878
Neg logit contributions
obal-1.409
acter-1.369
eware-1.301
ython-1.300
 Kimmel-1.291
Token provide
Token ID2148
Feature activation+2.76e+00

Pos logit contributions
======+0.305
imaru+0.276
brush+0.275
+0.270
 toget+0.270
Neg logit contributions
obal-0.384
acter-0.370
ython-0.354
eware-0.351
 Kimmel-0.350
Token it
Token ID340
Feature activation-7.60e-01

Pos logit contributions
======+1.670
brush+1.467
imaru+1.466
+1.461
 toget+1.445
Neg logit contributions
obal-2.124
acter-2.045
ython-1.949
eware-1.943
 Kimmel-1.914
Token for
Token ID329
Feature activation-1.79e-01

Pos logit contributions
obal+0.591
acter+0.575
eware+0.546
ython+0.546
 Kimmel+0.541
Neg logit contributions
======-0.444
imaru-0.406
brush-0.397
-0.394
-0.389
Token them
Token ID606
Feature activation-3.32e+00

Pos logit contributions
obal+0.136
acter+0.131
eware+0.125
ython+0.125
 Kimmel+0.124
Neg logit contributions
======-0.109
imaru-0.099
brush-0.097
-0.097
-0.095
Token change
Token ID1487
Feature activation-2.84e+00

Pos logit contributions
obal+0.041
acter+0.040
eware+0.038
ython+0.037
 Kimmel+0.037
Neg logit contributions
======-0.035
imaru-0.032
brush-0.031
-0.031
 toget-0.031
Token over
Token ID625
Feature activation+3.59e+00

Pos logit contributions
obal+2.092
acter+2.033
eware+1.922
ython+1.922
 Kimmel+1.909
Neg logit contributions
======-1.772
imaru-1.627
brush-1.590
-1.583
-1.565
Token time
Token ID640
Feature activation+4.37e+00

Pos logit contributions
======+2.081
brush+1.867
imaru+1.856
+1.814
214+1.801
Neg logit contributions
obal-2.828
acter-2.734
eware-2.600
ython-2.591
 Kimmel-2.564
Token,
Token ID11
Feature activation+6.42e-01

Pos logit contributions
======+2.350
imaru+2.086
brush+2.083
 toget+2.056
+2.041
Neg logit contributions
obal-3.591
acter-3.488
eware-3.344
ython-3.336
 Kimmel-3.286
Token despite
Token ID3805
Feature activation-2.67e-01

Pos logit contributions
======+0.426
imaru+0.389
brush+0.383
+0.382
 toget+0.377
Neg logit contributions
obal-0.452
acter-0.438
eware-0.416
ython-0.414
 Kimmel-0.408
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
obal+0.193
acter+0.187
eware+0.177
ython+0.177
 Kimmel+0.175
Neg logit contributions
======-0.172
imaru-0.158
brush-0.155
-0.154
-0.152
Token objection
Token ID19630
Feature activation-9.00e-01

Pos logit contributions
======+0.792
brush+0.706
imaru+0.704
+0.693
+0.683
Neg logit contributions
obal-1.099
acter-1.069
eware-1.018
ython-1.015
 Kimmel-0.996
Token of
Token ID286
Feature activation+5.19e-01

Pos logit contributions
obal+0.666
acter+0.646
eware+0.612
ython+0.611
 Kimmel+0.606
Neg logit contributions
======-0.561
imaru-0.514
brush-0.505
-0.501
-0.495
Token people
Token ID661
Feature activation-1.80e+00

Pos logit contributions
======+0.330
imaru+0.301
brush+0.297
+0.295
 toget+0.291
Neg logit contributions
obal-0.379
acter-0.368
ython-0.349
eware-0.349
 Kimmel-0.341
Token who
Token ID508
Feature activation+2.81e-01

Pos logit contributions
obal+1.362
acter+1.323
eware+1.254
ython+1.253
 Kimmel+1.247
Neg logit contributions
======-1.092
imaru-1.000
brush-0.977
-0.973
-0.960
Token are
Token ID389
Feature activation-2.45e+00

Pos logit contributions
======+0.195
imaru+0.179
brush+0.178
+0.176
214+0.174
Neg logit contributions
obal-0.189
acter-0.182
eware-0.172
ython-0.171
 Kimmel-0.168
TokenHeight
Token ID23106
Feature activation+1.36e+00

Pos logit contributions
======+0.733
brush+0.629
imaru+0.629
+0.612
214+0.607
Neg logit contributions
obal-1.720
acter-1.675
eware-1.614
ython-1.609
 Kimmel-1.599
Token),
Token ID828
Feature activation+7.84e-02

Pos logit contributions
======+0.806
imaru+0.735
brush+0.721
+0.714
214+0.705
Neg logit contributions
obal-1.056
acter-1.025
eware-0.973
ython-0.972
 Kimmel-0.965
Token$
Token ID3
Feature activation+1.07e+00

Pos logit contributions
======+0.049
imaru+0.045
brush+0.043
+0.043
 toget+0.043
Neg logit contributions
obal-0.058
acter-0.057
eware-0.054
ython-0.054
 Kimmel-0.053
TokenSR
Token ID12562
Feature activation+3.76e+00

Pos logit contributions
======+0.638
imaru+0.582
brush+0.573
+0.567
214+0.559
Neg logit contributions
obal-0.825
acter-0.802
eware-0.761
ython-0.760
 Kimmel-0.755
Token.
Token ID13
Feature activation+8.12e-01

Pos logit contributions
======+2.143
imaru+1.946
brush+1.901
+1.891
+1.868
Neg logit contributions
obal-2.988
acter-2.902
eware-2.759
ython-2.759
 Kimmel-2.735
TokenWidth
Token ID30916
Feature activation+2.58e+00

Pos logit contributions
======+0.295
imaru+0.251
brush+0.245
+0.241
214+0.236
Neg logit contributions
obal-0.813
acter-0.795
eware-0.765
ython-0.764
 Kimmel-0.760
Token,
Token ID11
Feature activation+2.63e-01

Pos logit contributions
======+1.461
imaru+1.329
brush+1.306
+1.289
214+1.273
Neg logit contributions
obal-2.059
acter-2.003
eware-1.899
ython-1.897
 Kimmel-1.888
Token$
Token ID3
Feature activation-1.07e+00

Pos logit contributions
======+0.173
imaru+0.160
brush+0.156
+0.155
 toget+0.155
Neg logit contributions
obal-0.184
acter-0.179
eware-0.169
ython-0.169
 Kimmel-0.167
TokenSR
Token ID12562
Feature activation+1.23e+00

Pos logit contributions
obal+0.822
acter+0.800
ython+0.757
eware+0.755
 Kimmel+0.750
Neg logit contributions
======-0.627
imaru-0.573
 toget-0.558
brush-0.555
-0.554
Token.
Token ID13
Feature activation-2.69e-02

Pos logit contributions
======+0.641
brush+0.566
imaru+0.565
214+0.562
+0.556
Neg logit contributions
obal-1.053
acter-1.025
eware-0.979
ython-0.971
 Kimmel-0.959
TokenHeight
Token ID23106
Feature activation+6.46e-01

Pos logit contributions
obal+0.026
acter+0.026
eware+0.025
ython+0.025
 Kimmel+0.024
Neg logit contributions
======-0.010
imaru-0.009
brush-0.009
-0.009
 toget-0.009
Tokenice
Token ID501
Feature activation+1.71e+00

Pos logit contributions
======+0.663
imaru+0.614
brush+0.603
+0.600
214+0.592
Neg logit contributions
obal-0.683
acter-0.659
eware-0.623
ython-0.620
 Kimmel-0.616
Token benefit
Token ID4414
Feature activation+2.51e+00

Pos logit contributions
======+0.995
imaru+0.894
brush+0.884
+0.874
 toget+0.860
Neg logit contributions
obal-1.348
acter-1.297
ython-1.240
eware-1.237
 Kimmel-1.217
Token for
Token ID329
Feature activation-4.00e-01

Pos logit contributions
======+1.460
imaru+1.322
brush+1.295
+1.283
+1.265
Neg logit contributions
obal-1.961
acter-1.899
eware-1.811
ython-1.802
 Kimmel-1.789
Token the
Token ID262
Feature activation-8.58e-01

Pos logit contributions
obal+0.291
acter+0.282
eware+0.267
ython+0.266
 Kimmel+0.263
Neg logit contributions
======-0.254
imaru-0.234
brush-0.229
-0.228
-0.225
Token team
Token ID1074
Feature activation-4.95e+00

Pos logit contributions
obal+0.642
acter+0.624
eware+0.591
ython+0.590
 Kimmel+0.585
Neg logit contributions
======-0.528
imaru-0.483
brush-0.474
-0.471
-0.465
Token.
Token ID13
Feature activation+1.57e+00

Pos logit contributions
obal+3.568
acter+3.418
 Kimmel+3.265
ython+3.261
eware+3.239
Neg logit contributions
======-3.102
imaru-2.869
brush-2.792
-2.792
-2.754
Token
Token ID198
Feature activation-2.22e-01

Pos logit contributions
======+0.808
imaru+0.730
+0.706
brush+0.705
214+0.695
Neg logit contributions
obal-1.338
acter-1.311
ython-1.241
eware-1.240
 Kimmel-1.203
Token
Token ID198
Feature activation+3.09e-01

Pos logit contributions
obal+0.208
acter+0.203
eware+0.195
ython+0.194
 Kimmel+0.192
Neg logit contributions
======-0.096
imaru-0.084
brush-0.082
-0.081
214-0.080
TokenPhil
Token ID18673
Feature activation-2.99e+00

Pos logit contributions
======+0.174
imaru+0.157
brush+0.154
+0.154
214+0.151
Neg logit contributions
obal-0.248
acter-0.242
eware-0.230
ython-0.230
 Kimmel-0.228
Token K
Token ID509
Feature activation-2.13e+00

Pos logit contributions
obal+1.846
acter+1.769
 Kimmel+1.681
ython+1.668
eware+1.652
Neg logit contributions
======-2.217
imaru-2.049
brush-2.019
-2.009
-2.004
Tokenessel
Token ID7878
Feature activation+2.02e+00

Pos logit contributions
obal+1.718
acter+1.671
eware+1.589
ython+1.588
 Kimmel+1.576
Neg logit contributions
======-1.187
imaru-1.075
brush-1.052
-1.045
-1.031
Token with
Token ID351
Feature activation+1.59e+00

Pos logit contributions
obal+0.278
acter+0.270
eware+0.257
ython+0.257
 Kimmel+0.255
Neg logit contributions
======-0.193
imaru-0.175
brush-0.172
-0.170
 toget-0.168
Token that
Token ID326
Feature activation+2.79e+00

Pos logit contributions
======+1.041
imaru+0.949
brush+0.938
+0.938
214+0.923
Neg logit contributions
obal-1.130
acter-1.088
eware-1.039
ython-1.038
 Kimmel-1.010
Token of
Token ID286
Feature activation-5.32e-01

Pos logit contributions
======+1.731
brush+1.570
+1.554
imaru+1.545
 toget+1.534
Neg logit contributions
obal-2.067
acter-1.986
ython-1.899
eware-1.898
 Kimmel-1.849
Token The
Token ID383
Feature activation-1.01e+00

Pos logit contributions
obal+0.373
acter+0.361
eware+0.341
ython+0.340
 Kimmel+0.338
Neg logit contributions
======-0.353
imaru-0.325
brush-0.319
-0.317
-0.314
Token Flash
Token ID9973
Feature activation+4.90e-01

Pos logit contributions
obal+0.867
acter+0.845
eware+0.806
ython+0.806
 Kimmel+0.800
Neg logit contributions
======-0.512
imaru-0.459
brush-0.448
-0.444
-0.437
Token,
Token ID11
Feature activation+1.05e-01

Pos logit contributions
======+0.298
imaru+0.273
brush+0.267
+0.265
+0.262
Neg logit contributions
obal-0.371
acter-0.360
eware-0.341
ython-0.341
 Kimmel-0.338
Token Super
Token ID3115
Feature activation+1.61e+00

Pos logit contributions
======+0.069
imaru+0.063
brush+0.062
+0.062
+0.061
Neg logit contributions
obal-0.075
acter-0.072
ython-0.068
eware-0.068
 Kimmel-0.067
Tokengirl
Token ID15219
Feature activation+2.82e+00

Pos logit contributions
======+0.926
imaru+0.842
brush+0.826
+0.817
214+0.806
Neg logit contributions
obal-1.274
acter-1.238
eware-1.178
ython-1.176
 Kimmel-1.167
Token,
Token ID11
Feature activation-8.33e-01

Pos logit contributions
======+1.691
imaru+1.543
brush+1.512
+1.502
+1.483
Neg logit contributions
obal-2.161
acter-2.099
eware-1.991
ython-1.989
 Kimmel-1.973
Token and
Token ID290
Feature activation-8.63e-02

Pos logit contributions
obal+0.586
acter+0.568
eware+0.535
 Kimmel+0.534
ython+0.533
Neg logit contributions
======-0.550
imaru-0.508
brush-0.498
-0.493
 toget-0.490
Token D
Token ID360
Feature activation+1.81e+00

Pos logit contributions
obal+0.061
acter+0.059
eware+0.056
ython+0.056
 Kimmel+0.056
Neg logit contributions
======-0.056
imaru-0.052
brush-0.051
-0.051
-0.050
Token
Token ID247
Feature activation-9.87e-01

Pos logit contributions
======+0.671
imaru+0.611
+0.607
brush+0.604
214+0.601
Neg logit contributions
obal-0.712
acter-0.683
eware-0.658
ython-0.654
 Kimmel-0.643
Tokens
Token ID82
Feature activation+1.67e+00

Pos logit contributions
obal+0.836
acter+0.814
eware+0.776
ython+0.776
 Kimmel+0.770
Neg logit contributions
======-0.511
imaru-0.459
brush-0.449
-0.445
-0.438
Token okay
Token ID8788
Feature activation+1.55e-01

Pos logit contributions
======+1.184
imaru+1.102
brush+1.086
 toget+1.079
+1.068
Neg logit contributions
obal-1.091
acter-1.055
ython-0.998
eware-0.996
 Kimmel-0.965
Token to
Token ID284
Feature activation+4.03e-01

Pos logit contributions
======+0.089
imaru+0.081
brush+0.079
+0.079
 toget+0.078
Neg logit contributions
obal-0.122
acter-0.119
eware-0.113
ython-0.113
 Kimmel-0.112
Token just
Token ID655
Feature activation-3.39e-01

Pos logit contributions
======+0.258
imaru+0.236
brush+0.235
 toget+0.231
+0.230
Neg logit contributions
obal-0.292
acter-0.281
ython-0.267
eware-0.266
 Kimmel-0.264
Token postpone
Token ID47328
Feature activation-2.26e-01

Pos logit contributions
obal+0.249
acter+0.240
ython+0.227
eware+0.227
 Kimmel+0.224
Neg logit contributions
======-0.214
imaru-0.196
brush-0.196
 toget-0.192
-0.191
Token a
Token ID257
Feature activation-1.44e+00

Pos logit contributions
obal+0.161
acter+0.156
ython+0.147
eware+0.147
 Kimmel+0.144
Neg logit contributions
======-0.148
imaru-0.136
brush-0.135
-0.133
 toget-0.132
Token situation
Token ID3074
Feature activation+1.85e+00

Pos logit contributions
obal+1.019
acter+0.988
eware+0.936
ython+0.932
 Kimmel+0.919
Neg logit contributions
======-0.947
imaru-0.870
brush-0.859
-0.852
 toget-0.845
Token even
Token ID772
Feature activation+1.54e+00

Pos logit contributions
======+1.065
imaru+0.961
brush+0.948
 toget+0.944
+0.929
Neg logit contributions
obal-1.467
acter-1.424
eware-1.354
ython-1.351
 Kimmel-1.336
Token if
Token ID611
Feature activation-2.19e+00

Pos logit contributions
======+1.065
imaru+1.000
brush+0.990
 toget+0.980
+0.973
Neg logit contributions
obal-1.021
acter-0.984
ython-0.931
eware-0.924
 Kimmel-0.901
Token I
Token ID314
Feature activation+4.22e-01

Pos logit contributions
obal+1.336
acter+1.288
eware+1.203
ython+1.203
 Kimmel+1.194
Neg logit contributions
======-1.648
imaru-1.533
brush-1.510
-1.501
-1.488
Token between
Token ID1022
Feature activation-3.35e-01

Pos logit contributions
======+0.154
imaru+0.141
brush+0.138
+0.137
+0.135
Neg logit contributions
obal-0.186
acter-0.181
eware-0.171
ython-0.171
 Kimmel-0.170
Token Mid
Token ID7215
Feature activation+8.28e-01

Pos logit contributions
obal+0.237
acter+0.229
eware+0.217
ython+0.217
 Kimmel+0.214
Neg logit contributions
======-0.220
imaru-0.203
brush-0.199
-0.198
-0.195
Tokenn
Token ID77
Feature activation-5.11e+00

Pos logit contributions
======+0.502
imaru+0.463
brush+0.458
+0.448
214+0.443
Neg logit contributions
obal-0.622
acter-0.606
ython-0.571
eware-0.569
 Kimmel-0.568
Tokenighter
Token ID4799
Feature activation-5.47e-01

Pos logit contributions
obal+3.080
acter+2.914
eware+2.798
ython+2.706
 Kimmel+2.690
Neg logit contributions
======-3.892
imaru-3.557
-3.529
 toget-3.526
brush-3.520
Token and
Token ID290
Feature activation-7.83e-01

Pos logit contributions
obal+0.397
acter+0.385
eware+0.364
ython+0.364
 Kimmel+0.361
Neg logit contributions
======-0.349
imaru-0.320
brush-0.315
-0.312
-0.309
Token Dick
Token ID11740
Feature activation-2.33e+00

Pos logit contributions
obal+0.548
acter+0.531
eware+0.501
ython+0.501
 Kimmel+0.497
Neg logit contributions
======-0.519
imaru-0.478
brush-0.470
-0.467
-0.462
Token Grayson
Token ID42657
Feature activation-2.93e+00

Pos logit contributions
obal+1.670
acter+1.615
ython+1.529
eware+1.527
 Kimmel+1.517
Neg logit contributions
======-1.511
imaru-1.385
brush-1.356
-1.352
-1.339
Token,
Token ID11
Feature activation+7.75e-01

Pos logit contributions
obal+2.186
acter+2.116
ython+2.010
eware+2.009
 Kimmel+1.997
Neg logit contributions
======-1.781
imaru-1.619
brush-1.582
-1.576
-1.571
Token and
Token ID290
Feature activation-1.12e-01

Pos logit contributions
======+0.490
imaru+0.450
brush+0.443
+0.438
 toget+0.434
Neg logit contributions
obal-0.567
acter-0.549
ython-0.521
eware-0.521
 Kimmel-0.511
Token,
Token ID11
Feature activation+1.01e+00

Pos logit contributions
obal+0.081
acter+0.078
eware+0.074
ython+0.074
 Kimmel+0.073
Neg logit contributions
======-0.072
imaru-0.067
brush-0.065
-0.065
 toget-0.064
Token in
Token ID287
Feature activation+1.70e+00

Pos logit contributions
======+0.619
imaru+0.571
brush+0.562
 toget+0.556
+0.554
Neg logit contributions
obal-0.758
acter-0.731
ython-0.697
eware-0.696
 Kimmel-0.681
Token players
Token ID1938
Feature activation-2.01e+00

Pos logit contributions
======+2.512
imaru+2.258
brush+2.254
+2.213
 grievances+2.212
Neg logit contributions
obal-2.795
acter-2.717
eware-2.595
ython-2.581
 Kimmel-2.519
Token'
Token ID6
Feature activation+1.57e+00

Pos logit contributions
obal+1.507
acter+1.460
eware+1.385
ython+1.383
 Kimmel+1.375
Neg logit contributions
======-1.233
imaru-1.127
brush-1.105
-1.100
-1.086
Token fault
Token ID8046
Feature activation+5.59e+00

Pos logit contributions
======+1.104
imaru+1.016
brush+0.997
+0.994
 toget+0.990
Neg logit contributions
obal-1.038
acter-1.005
ython-0.951
eware-0.949
 Kimmel-0.925
Token.
Token ID13
Feature activation+8.06e-01

Pos logit contributions
======+2.954
imaru+2.700
brush+2.605
 toget+2.536
+2.529
Neg logit contributions
obal-4.575
acter-4.510
eware-4.244
ython-4.237
 Kimmel-4.201
Token And
Token ID843
Feature activation+3.53e-01

Pos logit contributions
======+0.443
imaru+0.399
brush+0.390
+0.385
214+0.382
Neg logit contributions
obal-0.664
acter-0.650
eware-0.616
ython-0.615
 Kimmel-0.601
Token maybe
Token ID3863
Feature activation-4.66e-01

Pos logit contributions
======+0.229
imaru+0.211
brush+0.207
+0.204
 toget+0.204
Neg logit contributions
obal-0.252
acter-0.245
eware-0.231
ython-0.231
 Kimmel-0.228
Token,
Token ID11
Feature activation-3.63e-01

Pos logit contributions
obal+0.328
acter+0.318
eware+0.300
ython+0.300
 Kimmel+0.296
Neg logit contributions
======-0.309
imaru-0.284
brush-0.279
-0.277
 toget-0.274
Token we
Token ID356
Feature activation+4.76e-01

Pos logit contributions
obal+0.257
acter+0.249
eware+0.235
ython+0.235
 Kimmel+0.232
Neg logit contributions
======-0.238
imaru-0.220
brush-0.216
-0.214
 toget-0.212
Token should
Token ID815
Feature activation+9.85e-01

Pos logit contributions
======+0.286
imaru+0.260
brush+0.259
+0.254
214+0.251
Neg logit contributions
obal-0.361
acter-0.353
ython-0.334
eware-0.334
 Kimmel-0.329
Token be
Token ID307
Feature activation-2.73e+00

Pos logit contributions
======+0.611
brush+0.560
imaru+0.559
+0.544
214+0.544
Neg logit contributions
obal-0.725
acter-0.700
ython-0.668
eware-0.664
 Kimmel-0.662
Token incentiv
Token ID39678
Feature activation+3.22e+00

Pos logit contributions
obal+1.885
acter+1.824
eware+1.720
ython+1.712
 Kimmel+1.707
Neg logit contributions
======-1.838
imaru-1.693
brush-1.664
-1.656
-1.637
Tokenvey
Token ID3304
Feature activation-9.92e-01

Pos logit contributions
======+0.250
imaru+0.232
brush+0.228
+0.225
214+0.224
Neg logit contributions
obal-0.251
acter-0.242
ython-0.230
eware-0.228
 Kimmel-0.227
Token,
Token ID11
Feature activation+9.11e-02

Pos logit contributions
obal+0.699
acter+0.676
ython+0.641
eware+0.640
 Kimmel+0.629
Neg logit contributions
======-0.653
imaru-0.601
brush-0.594
-0.587
214-0.582
Token 1950
Token ID11445
Feature activation+3.40e+00

Pos logit contributions
======+0.061
imaru+0.056
brush+0.055
+0.055
+0.054
Neg logit contributions
obal-0.064
acter-0.061
ython-0.059
eware-0.058
 Kimmel-0.057
Token.)
Token ID2014
Feature activation+2.59e-01

Pos logit contributions
======+2.040
brush+1.847
imaru+1.823
+1.819
+1.815
Neg logit contributions
obal-2.573
acter-2.498
ython-2.370
eware-2.361
 Kimmel-2.347
Token Hitchcock
Token ID49817
Feature activation-2.32e+00

Pos logit contributions
======+0.160
imaru+0.146
brush+0.144
+0.142
214+0.142
Neg logit contributions
obal-0.195
acter-0.189
ython-0.180
eware-0.179
 Kimmel-0.175
Token's
Token ID338
Feature activation-6.37e-01

Pos logit contributions
obal+1.670
acter+1.618
eware+1.530
ython+1.528
 Kimmel+1.518
Neg logit contributions
======-1.503
imaru-1.375
brush-1.346
-1.343
-1.327
Token unw
Token ID7379
Feature activation+6.03e+00

Pos logit contributions
obal+0.441
acter+0.425
ython+0.403
eware+0.401
 Kimmel+0.398
Neg logit contributions
======-0.429
imaru-0.395
brush-0.389
-0.386
214-0.381
Tokenavering
Token ID42610
Feature activation-1.23e+00

Pos logit contributions
======+3.723
imaru+3.511
brush+3.475
rouse+3.440
214+3.410
Neg logit contributions
obal-4.216
acter-4.066
 Pigs-3.871
 Kimmel-3.851
ython-3.843
Token belief
Token ID4901
Feature activation+1.43e+00

Pos logit contributions
obal+0.927
acter+0.899
ython+0.852
eware+0.852
 Kimmel+0.845
Neg logit contributions
======-0.747
imaru-0.682
brush-0.671
-0.666
-0.656
Token in
Token ID287
Feature activation-6.65e-01

Pos logit contributions
======+0.880
imaru+0.806
brush+0.790
+0.785
+0.775
Neg logit contributions
obal-1.066
acter-1.035
eware-0.980
ython-0.980
 Kimmel-0.972
Token America
Token ID2253
Feature activation+7.90e-01

Pos logit contributions
obal+0.477
acter+0.462
ython+0.437
eware+0.437
 Kimmel+0.433
Neg logit contributions
======-0.430
imaru-0.395
brush-0.389
-0.386
-0.381
TokenThe
Token ID464
Feature activation-1.93e+00

Pos logit contributions
======+0.179
imaru+0.162
brush+0.159
+0.158
214+0.156
Neg logit contributions
obal-0.240
acter-0.233
eware-0.222
ython-0.221
 Kimmel-0.219
Token other
Token ID584
Feature activation-7.32e+00

Pos logit contributions
obal+1.371
acter+1.328
eware+1.255
ython+1.254
 Kimmel+1.243
Neg logit contributions
======-1.257
imaru-1.156
brush-1.135
-1.128
-1.115
Token rock
Token ID3881
Feature activation-6.38e-02

Pos logit contributions
obal+4.533
acter+4.383
eware+4.150
 Kimmel+4.120
ython+4.048
Neg logit contributions
======-5.264
imaru-4.900
brush-4.772
-4.761
214-4.717
Token,
Token ID11
Feature activation-3.85e+00

Pos logit contributions
obal+0.048
acter+0.047
ython+0.045
eware+0.045
 Kimmel+0.044
Neg logit contributions
======-0.039
imaru-0.035
brush-0.035
-0.034
 toget-0.034
Token though
Token ID996
Feature activation+9.36e-02

Pos logit contributions
obal+2.589
acter+2.502
 Kimmel+2.363
ython+2.350
eware+2.348
Neg logit contributions
======-2.635
imaru-2.424
brush-2.378
-2.375
-2.349
Token,
Token ID11
Feature activation-2.03e+00

Pos logit contributions
======+0.058
imaru+0.054
brush+0.052
+0.052
214+0.052
Neg logit contributions
obal-0.069
acter-0.067
ython-0.063
eware-0.063
 Kimmel-0.063
Token is
Token ID318
Feature activation-2.93e+00

Pos logit contributions
obal+1.495
acter+1.449
eware+1.371
ython+1.370
 Kimmel+1.365
Neg logit contributions
======-1.267
imaru-1.158
brush-1.137
-1.129
-1.118
Token each
Token ID1123
Feature activation-9.76e-01

Pos logit contributions
obal+2.041
acter+1.979
 Kimmel+1.866
eware+1.861
ython+1.860
Neg logit contributions
======-1.927
imaru-1.771
brush-1.739
-1.731
214-1.713
Token other
Token ID584
Feature activation-3.57e+00

Pos logit contributions
obal+0.700
acter+0.679
eware+0.642
ython+0.641
 Kimmel+0.636
Neg logit contributions
======-0.630
imaru-0.580
brush-0.568
-0.565
-0.558
Token.
Token ID13
Feature activation-1.70e+00

Pos logit contributions
obal+2.626
acter+2.525
eware+2.396
ython+2.389
 Kimmel+2.388
Neg logit contributions
======-2.224
imaru-2.035
brush-1.969
-1.966
214-1.950
Token It
Token ID632
Feature activation-5.72e-01

Pos logit contributions
obal+1.293
acter+1.255
eware+1.190
ython+1.189
 Kimmel+1.177
Neg logit contributions
======-1.025
imaru-0.936
brush-0.917
-0.911
-0.900
Token With
Token ID2080
Feature activation-3.10e+00

Pos logit contributions
obal+1.417
acter+1.375
 Kimmel+1.319
eware+1.309
ython+1.304
Neg logit contributions
======-0.892
imaru-0.803
-0.786
 toget-0.782
-0.776
Token Ghostbusters
Token ID50037
Feature activation+6.34e+00

Pos logit contributions
obal+1.891
acter+1.844
 Kimmel+1.703
eware+1.689
ython+1.688
Neg logit contributions
======-2.299
imaru-2.169
brush-2.130
 toget-2.122
-2.107
Token we
Token ID356
Feature activation-3.47e-01

Pos logit contributions
======+4.291
imaru+3.866
brush+3.848
+3.847
+3.822
Neg logit contributions
obal-4.267
acter-4.053
eware-3.923
ython-3.880
 Kimmel-3.766
Token learned
Token ID4499
Feature activation-1.08e+00

Pos logit contributions
obal+0.249
acter+0.239
eware+0.228
ython+0.227
 Kimmel+0.223
Neg logit contributions
======-0.226
imaru-0.208
brush-0.207
-0.204
214-0.202
Token that
Token ID326
Feature activation-1.46e+00

Pos logit contributions
obal+0.835
acter+0.810
eware+0.772
ython+0.770
 Kimmel+0.759
Neg logit contributions
======-0.636
imaru-0.579
brush-0.569
-0.564
-0.558
Token if
Token ID611
Feature activation-6.26e+00

Pos logit contributions
obal+0.940
acter+0.900
eware+0.849
ython+0.849
 Kimmel+0.831
Neg logit contributions
======-1.070
imaru-0.990
brush-0.975
-0.970
-0.961
Token you
Token ID345
Feature activation+3.72e-01

Pos logit contributions
obal+3.364
acter+3.319
ython+3.055
 Kimmel+3.046
eware+3.040
Neg logit contributions
======-4.960
 toget-4.684
imaru-4.682
-4.586
▬▬-4.584
Token find
Token ID1064
Feature activation+1.44e+00

Pos logit contributions
======+0.222
imaru+0.200
brush+0.199
+0.195
+0.193
Neg logit contributions
obal-0.287
acter-0.278
ython-0.265
eware-0.265
 Kimmel-0.264
Token a
Token ID257
Feature activation+7.71e-01

Pos logit contributions
======+0.863
brush+0.777
imaru+0.776
+0.758
+0.752
Neg logit contributions
obal-1.110
acter-1.070
eware-1.028
ython-1.017
 Kimmel-0.988
Token phantom
Token ID36381
Feature activation+3.05e+00

Pos logit contributions
======+0.398
brush+0.354
imaru+0.350
+0.347
+0.341
Neg logit contributions
obal-0.655
acter-0.633
eware-0.608
ython-0.607
 Kimmel-0.600
Token,
Token ID11
Feature activation-7.80e-02

Pos logit contributions
======+1.522
brush+1.354
imaru+1.347
214+1.319
+1.304
Neg logit contributions
obal-2.673
acter-2.561
eware-2.473
ython-2.453
 Kimmel-2.382
Token.
Token ID13
Feature activation+5.35e-01

Pos logit contributions
======+0.389
imaru+0.354
brush+0.348
+0.345
 toget+0.341
Neg logit contributions
obal-0.515
acter-0.499
eware-0.474
ython-0.473
 Kimmel-0.469
Token
Token ID198
Feature activation-3.91e-01

Pos logit contributions
======+0.303
imaru+0.275
brush+0.271
+0.270
+0.266
Neg logit contributions
obal-0.428
acter-0.418
eware-0.395
ython-0.394
 Kimmel-0.385
Token
Token ID198
Feature activation-6.75e-01

Pos logit contributions
obal+0.367
acter+0.358
eware+0.343
ython+0.342
 Kimmel+0.339
Neg logit contributions
======-0.170
imaru-0.148
brush-0.145
-0.143
214-0.142
TokenI
Token ID40
Feature activation-6.63e-01

Pos logit contributions
obal+0.537
acter+0.522
eware+0.496
ython+0.495
 Kimmel+0.492
Neg logit contributions
======-0.386
imaru-0.349
brush-0.343
-0.341
-0.336
Tokenvan
Token ID10438
Feature activation+5.73e-02

Pos logit contributions
obal+0.467
acter+0.450
eware+0.425
ython+0.423
 Kimmel+0.423
Neg logit contributions
======-0.439
imaru-0.405
brush-0.399
-0.396
-0.391
Token Nep
Token ID15310
Feature activation-6.27e+00

Pos logit contributions
======+0.040
imaru+0.037
brush+0.036
+0.036
+0.035
Neg logit contributions
obal-0.038
acter-0.037
eware-0.035
ython-0.035
 Kimmel-0.035
Tokenom
Token ID296
Feature activation+2.66e+00

Pos logit contributions
obal+4.524
acter+4.380
ython+4.144
eware+4.133
 Kimmel+4.005
Neg logit contributions
======-4.094
▬▬-3.715
-3.710
 toget-3.672
-3.671
Tokenny
Token ID3281
Feature activation-2.24e-02

Pos logit contributions
======+1.635
imaru+1.512
brush+1.485
+1.450
214+1.435
Neg logit contributions
obal-1.960
acter-1.906
 Kimmel-1.806
eware-1.798
ython-1.797
Tokenash
Token ID1077
Feature activation-1.38e-02

Pos logit contributions
obal+0.017
acter+0.016
eware+0.016
ython+0.015
 Kimmel+0.015
Neg logit contributions
======-0.014
imaru-0.013
brush-0.012
-0.012
-0.012
Tokench
Token ID354
Feature activation-4.35e-01

Pos logit contributions
obal+0.009
acter+0.009
eware+0.009
ython+0.009
 Kimmel+0.009
Neg logit contributions
======-0.009
imaru-0.009
brush-0.008
-0.008
 toget-0.008
Tokenikh
Token ID13848
Feature activation+2.85e+00

Pos logit contributions
obal+0.292
acter+0.282
eware+0.266
ython+0.265
 Kimmel+0.263
Neg logit contributions
======-0.301
imaru-0.280
brush-0.275
-0.272
-0.269
Token-
Token ID12
Feature activation+5.35e-01

Pos logit contributions
======+0.242
imaru+0.221
brush+0.217
+0.216
+0.214
Neg logit contributions
obal-0.301
acter-0.292
ython-0.277
eware-0.277
 Kimmel-0.274
Token14
Token ID1415
Feature activation+6.46e-01

Pos logit contributions
======+0.179
imaru+0.151
brush+0.145
+0.143
+0.140
Neg logit contributions
obal-0.552
acter-0.540
eware-0.519
ython-0.519
 Kimmel-0.515
Token dates
Token ID9667
Feature activation+1.67e-01

Pos logit contributions
======+0.402
imaru+0.362
brush+0.362
+0.356
 toget+0.352
Neg logit contributions
obal-0.478
acter-0.463
ython-0.443
eware-0.442
 Kimmel-0.439
Token in
Token ID287
Feature activation+4.58e-01

Pos logit contributions
======+0.101
imaru+0.092
brush+0.091
 toget+0.090
+0.089
Neg logit contributions
obal-0.128
acter-0.123
eware-0.117
ython-0.117
 Kimmel-0.115
Token the
Token ID262
Feature activation-7.03e-01

Pos logit contributions
======+0.284
imaru+0.257
brush+0.256
+0.254
214+0.250
Neg logit contributions
obal-0.341
acter-0.331
ython-0.314
eware-0.314
 Kimmel-0.308
Token range
Token ID2837
Feature activation-6.61e+00

Pos logit contributions
obal+0.507
acter+0.490
eware+0.465
ython+0.463
 Kimmel+0.456
Neg logit contributions
======-0.454
imaru-0.416
brush-0.411
-0.407
214-0.402
Token of
Token ID286
Feature activation-2.76e+00

Pos logit contributions
obal+4.437
acter+4.294
eware+4.044
 Kimmel+4.043
ython+4.009
Neg logit contributions
======-4.465
imaru-4.100
-4.035
brush-3.980
▬▬-3.971
Token 22
Token ID2534
Feature activation-2.19e+00

Pos logit contributions
obal+2.164
acter+2.104
eware+1.997
ython+1.995
 Kimmel+1.983
Neg logit contributions
======-1.605
imaru-1.461
brush-1.429
-1.420
-1.404
Token,
Token ID11
Feature activation+1.27e-01

Pos logit contributions
obal+1.583
acter+1.556
ython+1.464
eware+1.458
 Kimmel+1.446
Neg logit contributions
======-1.386
imaru-1.289
brush-1.246
-1.238
 toget-1.218
Token000
Token ID830
Feature activation+2.78e+00

Pos logit contributions
======+0.091
imaru+0.085
brush+0.083
+0.083
+0.082
Neg logit contributions
obal-0.082
acter-0.079
eware-0.074
ython-0.074
 Kimmel-0.073
Token to
Token ID284
Feature activation-2.35e-01

Pos logit contributions
======+1.548
imaru+1.397
brush+1.371
+1.361
214+1.348
Neg logit contributions
obal-2.242
acter-2.170
eware-2.071
ython-2.067
 Kimmel-2.052
Token an
Token ID281
Feature activation+9.15e-01

Pos logit contributions
obal+1.221
acter+1.182
eware+1.115
ython+1.112
 Kimmel+1.107
Neg logit contributions
======-1.184
imaru-1.088
brush-1.068
-1.063
-1.053
Token Emer
Token ID10320
Feature activation-3.45e+00

Pos logit contributions
======+0.590
imaru+0.543
+0.532
brush+0.531
214+0.523
Neg logit contributions
obal-0.655
acter-0.633
ython-0.603
eware-0.600
 Kimmel-0.593
Tokenitus
Token ID17506
Feature activation-1.04e+00

Pos logit contributions
obal+2.134
acter+2.090
ython+1.924
eware+1.915
 Kimmel+1.896
Neg logit contributions
======-2.562
-2.340
imaru-2.333
-2.328
 toget-2.320
Token Professor
Token ID8129
Feature activation-1.58e+00

Pos logit contributions
obal+0.687
acter+0.664
eware+0.624
ython+0.624
 Kimmel+0.618
Neg logit contributions
======-0.730
imaru-0.676
brush-0.665
-0.661
-0.654
Token of
Token ID286
Feature activation-2.38e+00

Pos logit contributions
obal+1.104
acter+1.068
ython+1.009
 Kimmel+1.008
eware+1.007
Neg logit contributions
======-1.050
imaru-0.959
brush-0.942
-0.932
 toget-0.932
Token Economics
Token ID18963
Feature activation-6.78e+00

Pos logit contributions
obal+1.553
acter+1.500
eware+1.409
ython+1.408
 Kimmel+1.396
Neg logit contributions
======-1.699
imaru-1.573
brush-1.548
-1.538
-1.524
Token at
Token ID379
Feature activation-3.89e+00

Pos logit contributions
obal+4.238
acter+4.057
ython+3.889
 Kimmel+3.849
eware+3.840
Neg logit contributions
======-4.754
imaru-4.410
-4.387
 toget-4.348
▬▬-4.344
Token Fl
Token ID1610
Feature activation-4.36e+00

Pos logit contributions
obal+2.627
acter+2.543
 Kimmel+2.410
ython+2.403
eware+2.389
Neg logit contributions
======-2.664
imaru-2.441
brush-2.411
-2.410
-2.399
Tokeninders
Token ID29700
Feature activation+1.55e+00

Pos logit contributions
obal+2.789
acter+2.684
eware+2.489
ython+2.485
 Kimmel+2.428
Neg logit contributions
======-3.213
imaru-2.955
-2.925
brush-2.899
▬▬-2.895
Token University
Token ID2059
Feature activation-5.73e+00

Pos logit contributions
======+0.995
brush+0.919
imaru+0.915
+0.905
214+0.903
Neg logit contributions
obal-1.108
acter-1.075
eware-1.013
ython-1.011
 Kimmel-0.974
Token,
Token ID11
Feature activation-3.27e+00

Pos logit contributions
obal+3.881
acter+3.711
 Kimmel+3.613
ython+3.515
eware+3.509
Neg logit contributions
======-3.893
imaru-3.542
-3.483
 toget-3.457
-3.442
Token in
Token ID287
Feature activation-1.95e+00

Pos logit contributions
======+0.823
imaru+0.742
brush+0.735
+0.734
 toget+0.729
Neg logit contributions
obal-1.018
acter-0.990
eware-0.935
ython-0.935
 Kimmel-0.926
Token play
Token ID711
Feature activation-7.14e+00

Pos logit contributions
obal+1.347
acter+1.302
ython+1.236
eware+1.231
 Kimmel+1.212
Neg logit contributions
======-1.303
imaru-1.212
brush-1.189
-1.174
-1.168
Token.
Token ID13
Feature activation-2.34e+00

Pos logit contributions
obal+4.816
acter+4.721
ython+4.494
eware+4.455
 Kimmel+4.326
Neg logit contributions
======-4.562
imaru-4.335
-4.219
▬▬-4.147
brush-4.129
Token
Token ID198
Feature activation-1.98e+00

Pos logit contributions
obal+1.796
acter+1.749
eware+1.661
ython+1.661
 Kimmel+1.648
Neg logit contributions
======-1.393
imaru-1.272
brush-1.247
-1.240
-1.224
Token
Token ID198
Feature activation-7.09e-01

Pos logit contributions
obal+1.779
acter+1.736
ython+1.660
eware+1.659
 Kimmel+1.650
Neg logit contributions
======-0.915
imaru-0.814
brush-0.790
-0.785
 toget-0.779
TokenIf
Token ID1532
Feature activation-6.63e+00

Pos logit contributions
obal+0.577
acter+0.562
eware+0.535
ython+0.534
 Kimmel+0.530
Neg logit contributions
======-0.389
imaru-0.353
brush-0.345
-0.342
-0.338
Token we
Token ID356
Feature activation-8.20e-01

Pos logit contributions
obal+3.816
acter+3.762
ython+3.536
eware+3.510
 Kimmel+3.434
Neg logit contributions
======-4.900
brush-4.647
imaru-4.612
-4.560
-4.527
Token simply
Token ID2391
Feature activation+1.73e+00

Pos logit contributions
obal+0.579
acter+0.558
eware+0.527
ython+0.526
 Kimmel+0.525
Neg logit contributions
======-0.541
imaru-0.497
brush-0.489
-0.488
214-0.481
Token want
Token ID765
Feature activation+5.39e+00

Pos logit contributions
======+1.130
imaru+1.036
brush+1.018
214+1.017
 toget+1.014
Neg logit contributions
obal-1.230
acter-1.183
ython-1.111
eware-1.110
 Kimmel-1.108
Token to
Token ID284
Feature activation+1.60e+00

Pos logit contributions
======+2.891
imaru+2.564
 toget+2.524
brush+2.467
+2.449
Neg logit contributions
obal-4.391
acter-4.263
eware-4.059
ython-4.056
 Kimmel-4.029
Token write
Token ID3551
Feature activation-4.95e-02

Pos logit contributions
======+1.102
imaru+1.008
 toget+0.995
brush+0.995
214+0.984
Neg logit contributions
obal-1.083
acter-1.042
ython-0.987
 Kimmel-0.983
eware-0.980