TOP ACTIVATIONS
MAX = 4.793

our latest issue Subscribe now for as little as
pur ak ushi Profile Joined August 2012 United States 3
domestic violence charge Subscribe to The Hollywood Reporter Today
14 Recommend Recommend Share this comment on Facebook Share
Barack Obama , they in ­ v oke him .
the NDP and the Bl oc , if not outright opposed
heart l xp Profile Joined September 2010 United States 10
ing Jimmy Carter . Al ­ though he left the White
) cricket and more O DI tournaments ," D rav id
19 Recommend Recommend Share this comment on Facebook Share
Obama is the worst ne ­ go ­ ti ­ at
expectations and elevated the Bl oc s prestige to
visits today ) Subscribe and get email notifications whenever
should not fear the Bl oc Qué b é co is
io on Fox News Chan ­ nel after Obama nor ­
of Dal K Profile Blog Joined June 2012 Canada 16 10
name is still a polit ­ ic ­ al in ­
still a polit ­ ic ­ al in ­ s ult
­ ic ­ al in ­ s ult . When Re
onto utility ... Subscribe to C rave :

MIN ACTIVATIONS
MIN = -4.052

However , now the tide has turned again , and
D ang - Hall er equ ates food to
. <|endoftext|> Ill ust rious Illum ination : Incredible TR ON
According to the FIR , inn ocent
- o vert ime goal clin ched New Jersey
s ear or a compliment in Benjamin Netanyahu
I mean that as a compliment , Rich man
to raise awareness of an issue than through a nice Public
, previously worked as a taxi driver , according to filings
mobilization . Increases cellular fat oxidation .
Calif . Before proceeding , the team carefully studied
gathered for dinner at a piano bar and discussed the visit
eye up like a marsh mallow . It was also that
Audio evidence The FIR further quotes the contents of
delight after that deal was clin ched in October last .
to sport a rum pled suit than a hood ie ,
in a radio debate with incumbent U . S . Sen
ator from Syria carrying bin ocular s , explosives , and
. In some respects , it is tech rather
1 world was a bro thel , one would explain it

INTERVAL 2.582 - 4.793
CONTAINS 0.186%

like this : --> src / main . rs
Michael From an to John Podesta in 2008 a document
14 Recommend Recommend Share this comment on Facebook
the years . Share this : Facebook
15 , 2010 Subject : Que er magnet ?

INTERVAL 0.370 - 2.582
CONTAINS 26.901%

Prime Minister Trudeau might agree with you
characters from mythology in a way never before imagined .
13 . 3 %. But many of the 8 % calling
, including an image falsely suggesting Kurt Cob ain had predicted
." " Ste lla !" When she

INTERVAL -1.841 - 0.370
CONTAINS 71.724%

card games , the break f asts , the saying
deal with the Demons is reportedly worth $ 750 , 000
activity more accessible . Work it Y OW is
it s obvious the homeless have dug in .
, Merry , P ipp in , Ar ag orn ,

INTERVAL -4.052 - -1.841
CONTAINS 1.188%

demise of the wind power production tax credit ), and compared
for have further destabil ized eastern Ukraine . While
" We don 't ordinarily allow police officers to detain
N ( 7 R 0 N , get it ?) watch
snaps it and takes a step to the play side .
Token our
Token ID674
Feature activation+5.08e-01

Pos logit contributions
wit+0.530
horn+0.523
 Spur+0.512
utenant+0.476
bon+0.458
Neg logit contributions
 polyg-0.555
idential-0.551
 Afgh-0.546
-0.544
methyl-0.534
Token latest
Token ID3452
Feature activation+6.43e-01

Pos logit contributions
idential+0.399
 polyg+0.398
 Afgh+0.395
+0.393
methyl+0.386
Neg logit contributions
wit-0.328
 Spur-0.322
horn-0.321
utenant-0.295
bon-0.281
Token issue
Token ID2071
Feature activation-1.49e+00

Pos logit contributions
idential+0.514
 polyg+0.514
 Afgh+0.510
+0.506
methyl+0.495
Neg logit contributions
wit-0.405
horn-0.400
 Spur-0.392
utenant-0.366
bon-0.341
Token
Token ID198
Feature activation+7.14e-01

Pos logit contributions
wit+0.867
horn+0.859
 Spur+0.846
utenant+0.782
bon+0.725
Neg logit contributions
 polyg-1.275
 Afgh-1.268
idential-1.268
-1.246
methyl-1.233
Token
Token ID198
Feature activation+7.67e-01

Pos logit contributions
 polyg+0.599
idential+0.599
 Afgh+0.597
+0.587
methyl+0.575
Neg logit contributions
wit-0.427
horn-0.421
 Spur-0.410
utenant-0.380
bon-0.356
TokenSubscribe
Token ID27125
Feature activation+4.79e+00

Pos logit contributions
 polyg+0.625
idential+0.619
 Afgh+0.618
+0.605
methyl+0.590
Neg logit contributions
wit-0.478
horn-0.473
 Spur-0.458
utenant-0.431
bon-0.406
Token now
Token ID783
Feature activation+1.64e-01

Pos logit contributions
idential+4.104
 Afgh+4.040
 polyg+4.028
+4.013
methyl+3.866
Neg logit contributions
wit-2.718
horn-2.628
 Spur-2.626
utenant-2.463
lishes-2.214
Token for
Token ID329
Feature activation+6.29e-01

Pos logit contributions
 Afgh+0.123
idential+0.119
 tremend+0.118
 polyg+0.116
+0.115
Neg logit contributions
wit-0.116
horn-0.114
 Spur-0.113
utenant-0.106
bon-0.100
Token as
Token ID355
Feature activation+3.28e-01

Pos logit contributions
idential+0.421
 Afgh+0.419
+0.417
 polyg+0.416
methyl+0.405
Neg logit contributions
horn-0.479
wit-0.474
 Spur-0.466
utenant-0.439
bon-0.425
Token little
Token ID1310
Feature activation-5.85e-01

Pos logit contributions
idential+0.220
 polyg+0.220
 Afgh+0.218
+0.216
methyl+0.211
Neg logit contributions
wit-0.248
horn-0.246
 Spur-0.246
utenant-0.229
bon-0.219
Token as
Token ID355
Feature activation+6.33e-03

Pos logit contributions
wit+0.447
horn+0.442
 Spur+0.434
utenant+0.404
bon+0.390
Neg logit contributions
idential-0.397
 polyg-0.394
 Afgh-0.394
-0.387
 tremend-0.377
Token
Token ID198
Feature activation+6.49e-01

Pos logit contributions
 polyg+0.731
idential+0.730
 Afgh+0.729
+0.710
methyl+0.700
Neg logit contributions
wit-0.523
horn-0.517
 Spur-0.501
utenant-0.466
bon-0.436
Tokenpur
Token ID14225
Feature activation+4.06e-01

Pos logit contributions
idential+0.467
 polyg+0.467
 Afgh+0.463
+0.457
methyl+0.446
Neg logit contributions
wit-0.461
horn-0.455
 Spur-0.447
utenant-0.422
bon-0.395
Tokenak
Token ID461
Feature activation+1.12e+00

Pos logit contributions
 polyg+0.251
idential+0.251
 Afgh+0.249
+0.246
methyl+0.239
Neg logit contributions
wit-0.330
horn-0.326
 Spur-0.321
utenant-0.305
bon-0.289
Tokenushi
Token ID17731
Feature activation-3.14e-01

Pos logit contributions
idential+0.800
 polyg+0.798
 Afgh+0.791
+0.783
methyl+0.764
Neg logit contributions
wit-0.807
horn-0.797
 Spur-0.786
utenant-0.741
bon-0.693
Token Profile
Token ID13118
Feature activation+8.59e-01

Pos logit contributions
wit+0.228
horn+0.225
 Spur+0.221
utenant+0.209
bon+0.196
Neg logit contributions
 polyg-0.222
idential-0.222
 Afgh-0.220
-0.218
methyl-0.212
Token Joined
Token ID16709
Feature activation+4.73e+00

Pos logit contributions
idential+0.761
 polyg+0.759
 Afgh+0.755
+0.750
methyl+0.734
Neg logit contributions
wit-0.467
horn-0.457
 Spur-0.447
utenant-0.415
bon-0.375
Token August
Token ID2932
Feature activation+1.46e-01

Pos logit contributions
 polyg+3.433
idential+3.417
 Afgh+3.414
+3.361
methyl+3.288
Neg logit contributions
wit-3.302
horn-3.239
 Spur-3.173
utenant-3.023
lishes-2.801
Token 2012
Token ID2321
Feature activation+2.19e-01

Pos logit contributions
idential+0.115
 polyg+0.114
 Afgh+0.112
+0.112
methyl+0.110
Neg logit contributions
wit-0.095
horn-0.094
 Spur-0.093
utenant-0.086
bon-0.080
Token United
Token ID1578
Feature activation+1.03e+00

Pos logit contributions
idential+0.133
 polyg+0.131
 Afgh+0.129
+0.129
methyl+0.126
Neg logit contributions
wit-0.181
horn-0.179
 Spur-0.178
utenant-0.167
bon-0.159
Token States
Token ID1829
Feature activation-6.79e-01

Pos logit contributions
 polyg+0.712
 Afgh+0.710
idential+0.705
+0.695
methyl+0.680
Neg logit contributions
wit-0.763
horn-0.754
 Spur-0.739
utenant-0.704
bon-0.656
Token 3
Token ID513
Feature activation+4.63e-01

Pos logit contributions
wit+0.538
horn+0.535
 Spur+0.533
utenant+0.495
bon+0.470
Neg logit contributions
idential-0.437
 polyg-0.429
 Afgh-0.422
-0.420
methyl-0.412
Token domestic
Token ID5928
Feature activation-1.02e+00

Pos logit contributions
idential+0.004
 polyg+0.003
 Afgh+0.003
+0.003
methyl+0.003
Neg logit contributions
wit-0.003
horn-0.003
 Spur-0.003
utenant-0.003
bon-0.003
Token violence
Token ID3685
Feature activation-3.07e-01

Pos logit contributions
wit+0.628
horn+0.625
 Spur+0.611
utenant+0.567
bon+0.529
Neg logit contributions
idential-0.831
 polyg-0.818
 Afgh-0.816
-0.814
methyl-0.799
Token charge
Token ID3877
Feature activation-7.45e-01

Pos logit contributions
wit+0.250
horn+0.248
 Spur+0.246
utenant+0.232
bon+0.220
Neg logit contributions
idential-0.189
 polyg-0.186
 Afgh-0.185
-0.184
methyl-0.179
Token
Token ID198
Feature activation+8.51e-01

Pos logit contributions
wit+0.486
horn+0.480
 Spur+0.474
utenant+0.439
bon+0.411
Neg logit contributions
idential-0.580
 polyg-0.574
 Afgh-0.572
-0.570
methyl-0.558
Token
Token ID198
Feature activation+8.63e-01

Pos logit contributions
idential+0.713
 polyg+0.711
 Afgh+0.710
+0.699
methyl+0.685
Neg logit contributions
wit-0.509
horn-0.503
 Spur-0.491
utenant-0.454
bon-0.424
TokenSubscribe
Token ID27125
Feature activation+4.72e+00

Pos logit contributions
idential+0.616
 polyg+0.614
 Afgh+0.610
+0.602
methyl+0.587
Neg logit contributions
wit-0.620
horn-0.613
 Spur-0.603
utenant-0.567
bon-0.533
Token to
Token ID284
Feature activation+8.02e-01

Pos logit contributions
idential+3.245
 polyg+3.210
 Afgh+3.174
+3.151
methyl+3.070
Neg logit contributions
wit-3.482
horn-3.375
 Spur-3.349
utenant-3.215
lishes-2.962
Token The
Token ID383
Feature activation+8.11e-03

Pos logit contributions
idential+0.559
 polyg+0.558
 Afgh+0.553
+0.547
methyl+0.534
Neg logit contributions
wit-0.588
horn-0.581
 Spur-0.572
utenant-0.541
bon-0.506
Token Hollywood
Token ID8502
Feature activation-6.74e-02

Pos logit contributions
idential+0.005
 polyg+0.005
 Afgh+0.005
+0.005
methyl+0.005
Neg logit contributions
wit-0.006
horn-0.006
 Spur-0.006
utenant-0.006
bon-0.005
Token Reporter
Token ID25869
Feature activation+2.80e-01

Pos logit contributions
wit+0.066
horn+0.066
 Spur+0.065
utenant+0.062
bon+0.059
Neg logit contributions
idential-0.030
 polyg-0.030
 Afgh-0.030
-0.029
methyl-0.028
Token Today
Token ID6288
Feature activation+1.71e+00

Pos logit contributions
 Afgh+0.228
 polyg+0.228
+0.226
idential+0.225
methyl+0.220
Neg logit contributions
wit-0.172
horn-0.170
 Spur-0.168
utenant-0.154
bon-0.146
Token14
Token ID1415
Feature activation+1.45e+00

Pos logit contributions
idential+0.867
 polyg+0.866
 Afgh+0.858
+0.841
methyl+0.825
Neg logit contributions
wit-0.886
horn-0.874
 Spur-0.863
utenant-0.812
bon-0.762
Token Recommend
Token ID30361
Feature activation+3.71e+00

Pos logit contributions
 polyg+0.940
idential+0.940
 Afgh+0.933
+0.923
methyl+0.897
Neg logit contributions
wit-1.127
horn-1.114
 Spur-1.098
utenant-1.042
bon-0.979
Token
Token ID198
Feature activation+1.49e+00

Pos logit contributions
idential+3.011
 polyg+3.006
 Afgh+2.984
+2.958
methyl+2.894
Neg logit contributions
wit-2.290
horn-2.259
 Spur-2.220
utenant-2.072
bon-1.913
Token
Token ID198
Feature activation+1.43e+00

Pos logit contributions
idential+1.215
 polyg+1.212
 Afgh+1.205
+1.193
methyl+1.167
Neg logit contributions
wit-0.917
horn-0.905
 Spur-0.888
utenant-0.828
bon-0.766
TokenRecommend
Token ID41248
Feature activation+4.21e+00

Pos logit contributions
 polyg+0.797
 Afgh+0.796
idential+0.795
+0.766
methyl+0.741
Neg logit contributions
wit-1.266
horn-1.241
 Spur-1.229
utenant-1.163
bon-1.123
Token Share
Token ID8734
Feature activation+4.66e+00

Pos logit contributions
 polyg+2.794
idential+2.789
 Afgh+2.752
+2.732
methyl+2.671
Neg logit contributions
wit-3.195
horn-3.122
 Spur-3.098
utenant-2.959
bon-2.745
Token this
Token ID428
Feature activation+1.38e+00

Pos logit contributions
 polyg+2.991
 Afgh+2.979
idential+2.917
+2.880
methyl+2.795
Neg logit contributions
wit-3.606
horn-3.546
 Spur-3.523
utenant-3.304
lishes-3.147
Token comment
Token ID2912
Feature activation+5.23e-01

Pos logit contributions
idential+1.312
 Afgh+1.307
+1.298
 polyg+1.285
methyl+1.272
Neg logit contributions
wit-0.678
horn-0.673
 Spur-0.664
utenant-0.595
 waiter-0.547
Token on
Token ID319
Feature activation+5.61e-01

Pos logit contributions
 Afgh+0.405
idential+0.403
 polyg+0.401
+0.398
methyl+0.392
Neg logit contributions
wit-0.343
horn-0.342
 Spur-0.339
utenant-0.314
bon-0.295
Token Facebook
Token ID3203
Feature activation-7.49e-01

Pos logit contributions
idential+0.462
 polyg+0.456
 Afgh+0.456
+0.453
methyl+0.442
Neg logit contributions
wit-0.339
horn-0.336
 Spur-0.333
utenant-0.303
bon-0.286
Token Share
Token ID8734
Feature activation+4.19e+00

Pos logit contributions
wit+0.546
horn+0.539
 Spur+0.531
utenant+0.502
bon+0.469
Neg logit contributions
idential-0.524
 polyg-0.524
 Afgh-0.519
-0.514
methyl-0.501
Token Barack
Token ID8732
Feature activation-5.44e-01

Pos logit contributions
idential+0.095
 polyg+0.094
 Afgh+0.093
+0.092
methyl+0.090
Neg logit contributions
wit-0.099
horn-0.097
 Spur-0.097
utenant-0.091
bon-0.085
Token Obama
Token ID2486
Feature activation+8.53e-01

Pos logit contributions
wit+0.485
horn+0.481
 Spur+0.474
utenant+0.454
bon+0.430
Neg logit contributions
idential-0.292
 polyg-0.292
 Afgh-0.290
-0.285
methyl-0.275
Token,
Token ID11
Feature activation+6.82e-01

Pos logit contributions
 polyg+0.532
idential+0.531
 Afgh+0.527
+0.521
methyl+0.504
Neg logit contributions
wit-0.686
horn-0.680
 Spur-0.671
utenant-0.638
bon-0.600
Token they
Token ID484
Feature activation+1.26e-01

Pos logit contributions
idential+0.440
 polyg+0.437
 Afgh+0.433
+0.430
methyl+0.418
Neg logit contributions
wit-0.536
horn-0.529
 Spur-0.524
utenant-0.495
bon-0.466
Token in
Token ID287
Feature activation+2.56e-01

Pos logit contributions
idential+0.096
 polyg+0.095
 Afgh+0.095
+0.095
methyl+0.093
Neg logit contributions
wit-0.084
horn-0.082
 Spur-0.081
utenant-0.076
bon-0.071
Token­
Token ID3907
Feature activation+4.59e+00

Pos logit contributions
 polyg+0.124
idential+0.124
 Afgh+0.123
+0.121
methyl+0.116
Neg logit contributions
wit-0.241
horn-0.239
 Spur-0.237
utenant-0.227
bon-0.215
Tokenv
Token ID85
Feature activation+2.50e-01

Pos logit contributions
idential+2.941
 polyg+2.939
 Afgh+2.890
methyl+2.870
+2.862
Neg logit contributions
wit-3.440
horn-3.420
 Spur-3.414
utenant-3.238
 waiter-3.045
Tokenoke
Token ID2088
Feature activation-1.03e-01

Pos logit contributions
idential+0.175
 polyg+0.173
 Afgh+0.171
+0.170
methyl+0.166
Neg logit contributions
wit-0.182
horn-0.180
 Spur-0.178
utenant-0.168
bon-0.157
Token him
Token ID683
Feature activation-4.85e-01

Pos logit contributions
wit+0.075
horn+0.074
 Spur+0.073
utenant+0.068
bon+0.064
Neg logit contributions
idential-0.072
 polyg-0.072
 Afgh-0.071
-0.071
methyl-0.069
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
wit+0.356
horn+0.352
 Spur+0.346
utenant+0.324
bon+0.307
Neg logit contributions
idential-0.340
 polyg-0.334
 Afgh-0.333
-0.330
methyl-0.326
Token
Token ID564
Feature activation+2.04e+00

Pos logit contributions
idential+0.157
 polyg+0.156
 Afgh+0.152
+0.152
methyl+0.150
Neg logit contributions
wit-0.155
horn-0.153
 Spur-0.153
utenant-0.141
bon-0.133
Token the
Token ID262
Feature activation-3.36e-01

Pos logit contributions
wit+0.205
horn+0.203
 Spur+0.200
utenant+0.188
bon+0.175
Neg logit contributions
idential-0.217
 polyg-0.216
 Afgh-0.214
-0.212
methyl-0.207
Token NDP
Token ID20392
Feature activation+2.78e-01

Pos logit contributions
wit+0.207
horn+0.204
 Spur+0.202
utenant+0.186
bon+0.174
Neg logit contributions
idential-0.274
 polyg-0.271
 Afgh-0.269
-0.268
methyl-0.263
Token and
Token ID290
Feature activation-2.81e-01

Pos logit contributions
idential+0.187
 polyg+0.186
 Afgh+0.184
+0.181
methyl+0.178
Neg logit contributions
wit-0.211
horn-0.209
 Spur-0.206
utenant-0.194
bon-0.183
Token the
Token ID262
Feature activation-2.81e-01

Pos logit contributions
wit+0.199
horn+0.196
 Spur+0.194
utenant+0.181
bon+0.170
Neg logit contributions
idential-0.205
 polyg-0.202
 Afgh-0.202
-0.200
methyl-0.196
Token Bl
Token ID1086
Feature activation-1.50e+00

Pos logit contributions
wit+0.191
horn+0.189
 Spur+0.188
utenant+0.174
bon+0.164
Neg logit contributions
idential-0.212
 Afgh-0.208
 polyg-0.207
-0.207
methyl-0.203
Tokenoc
Token ID420
Feature activation+4.54e+00

Pos logit contributions
wit+1.006
horn+0.989
 Spur+0.941
utenant+0.897
bon+0.872
Neg logit contributions
 Afgh-1.166
 polyg-1.149
-1.144
idential-1.133
 tremend-1.122
Token,
Token ID11
Feature activation-1.75e-01

Pos logit contributions
 polyg+2.214
idential+2.166
 Afgh+2.145
+2.132
methyl+2.032
Neg logit contributions
wit-4.245
horn-4.215
 Spur-4.156
utenant-4.004
lishes-3.782
Token if
Token ID611
Feature activation+6.50e-01

Pos logit contributions
wit+0.126
horn+0.125
 Spur+0.123
utenant+0.115
bon+0.108
Neg logit contributions
idential-0.125
 polyg-0.122
 Afgh-0.122
-0.121
methyl-0.119
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
idential+0.445
 polyg+0.444
 Afgh+0.440
+0.436
methyl+0.425
Neg logit contributions
wit-0.484
horn-0.478
 Spur-0.472
utenant-0.446
bon-0.418
Token outright
Token ID15828
Feature activation-4.73e-02

Pos logit contributions
wit+0.720
horn+0.710
 Spur+0.708
utenant+0.658
bon+0.619
Neg logit contributions
idential-0.711
 polyg-0.701
 Afgh-0.700
-0.693
methyl-0.680
Token opposed
Token ID6886
Feature activation+1.00e-01

Pos logit contributions
wit+0.031
horn+0.031
 Spur+0.030
utenant+0.028
bon+0.026
Neg logit contributions
idential-0.037
 Afgh-0.036
 polyg-0.036
-0.036
methyl-0.035
Token
Token ID198
Feature activation+1.15e+00

Pos logit contributions
idential+1.085
 polyg+1.082
 Afgh+1.077
+1.065
methyl+1.042
Neg logit contributions
wit-0.808
horn-0.797
 Spur-0.782
utenant-0.726
bon-0.674
Tokenheart
Token ID11499
Feature activation+4.08e-01

Pos logit contributions
idential+0.821
 polyg+0.818
 Afgh+0.811
+0.807
methyl+0.790
Neg logit contributions
wit-0.815
horn-0.805
 Spur-0.798
utenant-0.751
bon-0.697
Tokenl
Token ID75
Feature activation-1.71e-01

Pos logit contributions
 polyg+0.293
idential+0.293
 Afgh+0.291
+0.287
methyl+0.280
Neg logit contributions
wit-0.292
horn-0.289
 Spur-0.282
utenant-0.268
bon-0.251
Tokenxp
Token ID42372
Feature activation-9.02e-01

Pos logit contributions
wit+0.126
horn+0.125
 Spur+0.123
utenant+0.116
bon+0.109
Neg logit contributions
 polyg-0.118
idential-0.118
 Afgh-0.117
-0.116
methyl-0.112
Token Profile
Token ID13118
Feature activation+7.23e-01

Pos logit contributions
wit+0.627
horn+0.619
 Spur+0.608
utenant+0.573
bon+0.537
Neg logit contributions
 polyg-0.664
 Afgh-0.660
idential-0.659
-0.648
methyl-0.634
Token Joined
Token ID16709
Feature activation+4.48e+00

Pos logit contributions
idential+0.628
 polyg+0.627
 Afgh+0.624
+0.619
methyl+0.606
Neg logit contributions
wit-0.406
horn-0.397
 Spur-0.387
utenant-0.361
lishes-0.327
Token September
Token ID2693
Feature activation+4.87e-01

Pos logit contributions
 polyg+3.255
 Afgh+3.243
idential+3.233
+3.186
methyl+3.113
Neg logit contributions
wit-3.123
horn-3.065
 Spur-2.997
utenant-2.859
lishes-2.645
Token 2010
Token ID3050
Feature activation+8.15e-01

Pos logit contributions
idential+0.371
 polyg+0.369
 Afgh+0.364
+0.362
methyl+0.355
Neg logit contributions
wit-0.327
horn-0.324
 Spur-0.320
utenant-0.297
bon-0.277
Token United
Token ID1578
Feature activation+9.21e-01

Pos logit contributions
idential+0.480
 polyg+0.476
 Afgh+0.469
+0.467
methyl+0.453
Neg logit contributions
wit-0.687
horn-0.680
 Spur-0.674
utenant-0.638
bon-0.605
Token States
Token ID1829
Feature activation-7.03e-01

Pos logit contributions
 Afgh+0.610
 polyg+0.609
idential+0.599
+0.592
methyl+0.578
Neg logit contributions
wit-0.709
horn-0.698
 Spur-0.679
utenant-0.656
bon-0.609
Token 10
Token ID838
Feature activation+6.56e-01

Pos logit contributions
wit+0.559
horn+0.555
 Spur+0.552
utenant+0.514
bon+0.488
Neg logit contributions
idential-0.450
 polyg-0.442
 Afgh-0.436
-0.435
methyl-0.425
Tokening
Token ID278
Feature activation+6.23e-01

Pos logit contributions
idential+3.054
 polyg+3.038
+3.007
 Afgh+2.997
methyl+2.948
Neg logit contributions
wit-2.798
horn-2.750
 Spur-2.743
utenant-2.568
 waiter-2.363
Token Jimmy
Token ID12963
Feature activation-3.27e-01

Pos logit contributions
idential+0.439
 polyg+0.434
 Afgh+0.431
+0.429
methyl+0.417
Neg logit contributions
wit-0.455
horn-0.449
 Spur-0.442
utenant-0.416
bon-0.389
Token Carter
Token ID10831
Feature activation-7.11e-02

Pos logit contributions
wit+0.245
horn+0.241
 Spur+0.240
utenant+0.225
bon+0.212
Neg logit contributions
 polyg-0.223
idential-0.223
 Afgh-0.220
-0.218
methyl-0.213
Token.
Token ID13
Feature activation+1.93e-01

Pos logit contributions
wit+0.051
horn+0.051
 Spur+0.050
utenant+0.047
bon+0.044
Neg logit contributions
idential-0.051
 polyg-0.050
 Afgh-0.050
-0.049
methyl-0.048
Token Al
Token ID978
Feature activation-1.04e+00

Pos logit contributions
idential+0.142
 polyg+0.141
 Afgh+0.139
+0.138
methyl+0.135
Neg logit contributions
wit-0.136
horn-0.134
 Spur-0.133
utenant-0.123
bon-0.116
Token­
Token ID3907
Feature activation+4.47e+00

Pos logit contributions
wit+0.853
horn+0.839
 Spur+0.834
utenant+0.781
bon+0.749
Neg logit contributions
idential-0.648
 polyg-0.646
-0.634
 Afgh-0.630
methyl-0.610
Tokenthough
Token ID2016
Feature activation+5.05e-01

Pos logit contributions
idential+3.236
 polyg+3.152
+3.123
 Afgh+3.114
methyl+3.112
Neg logit contributions
wit-3.102
 Spur-3.085
horn-3.027
utenant-2.863
 waiter-2.690
Token he
Token ID339
Feature activation-3.15e-01

Pos logit contributions
idential+0.345
 polyg+0.341
 Afgh+0.338
+0.337
methyl+0.328
Neg logit contributions
wit-0.380
horn-0.374
 Spur-0.371
utenant-0.349
bon-0.328
Token left
Token ID1364
Feature activation+2.48e-01

Pos logit contributions
wit+0.229
horn+0.226
 Spur+0.223
utenant+0.210
bon+0.197
Neg logit contributions
idential-0.223
 polyg-0.220
 Afgh-0.218
-0.218
methyl-0.213
Token the
Token ID262
Feature activation-5.07e-02

Pos logit contributions
idential+0.170
 polyg+0.167
+0.166
 Afgh+0.165
methyl+0.162
Neg logit contributions
wit-0.186
horn-0.184
 Spur-0.182
utenant-0.171
bon-0.161
Token White
Token ID2635
Feature activation+9.75e-01

Pos logit contributions
wit+0.036
horn+0.036
 Spur+0.036
utenant+0.033
bon+0.031
Neg logit contributions
idential-0.036
 polyg-0.036
-0.036
 Afgh-0.035
methyl-0.035
Token)
Token ID8
Feature activation+3.33e-01

Pos logit contributions
wit+0.068
horn+0.067
 Spur+0.066
utenant+0.062
bon+0.058
Neg logit contributions
idential-0.081
 polyg-0.081
 Afgh-0.080
-0.080
methyl-0.078
Token cricket
Token ID18836
Feature activation+1.01e+00

Pos logit contributions
idential+0.251
 polyg+0.249
 Afgh+0.247
+0.246
methyl+0.242
Neg logit contributions
wit-0.225
horn-0.222
 Spur-0.218
utenant-0.205
bon-0.194
Token and
Token ID290
Feature activation-1.36e-01

Pos logit contributions
idential+0.684
 polyg+0.679
 Afgh+0.677
+0.673
methyl+0.659
Neg logit contributions
wit-0.760
horn-0.751
 Spur-0.735
utenant-0.696
bon-0.658
Token more
Token ID517
Feature activation+4.06e-02

Pos logit contributions
wit+0.093
horn+0.092
 Spur+0.091
utenant+0.085
bon+0.080
Neg logit contributions
idential-0.101
 polyg-0.100
-0.099
 Afgh-0.099
methyl-0.097
Token O
Token ID440
Feature activation-6.09e-01

Pos logit contributions
idential+0.031
 polyg+0.031
 Afgh+0.030
+0.030
methyl+0.030
Neg logit contributions
wit-0.027
horn-0.027
 Spur-0.026
utenant-0.025
bon-0.023
TokenDI
Token ID17931
Feature activation+4.47e+00

Pos logit contributions
wit+0.638
horn+0.631
 Spur+0.628
utenant+0.603
bon+0.579
Neg logit contributions
idential-0.234
 Afgh-0.231
 polyg-0.230
-0.226
methyl-0.213
Token tournaments
Token ID18130
Feature activation+1.16e+00

Pos logit contributions
 polyg+3.195
idential+3.185
 Afgh+3.159
+3.115
methyl+3.029
Neg logit contributions
wit-3.173
horn-3.136
 Spur-3.097
utenant-2.918
bon-2.695
Token,"
Token ID553
Feature activation-3.49e-01

Pos logit contributions
idential+0.781
 polyg+0.774
 Afgh+0.773
+0.766
methyl+0.749
Neg logit contributions
wit-0.888
horn-0.878
 Spur-0.862
utenant-0.815
bon-0.769
Token D
Token ID360
Feature activation-5.76e-02

Pos logit contributions
wit+0.255
horn+0.252
 Spur+0.249
utenant+0.235
bon+0.219
Neg logit contributions
idential-0.243
 polyg-0.243
 Afgh-0.241
-0.239
methyl-0.232
Tokenrav
Token ID4108
Feature activation+3.56e-01

Pos logit contributions
wit+0.033
horn+0.033
 Spur+0.031
utenant+0.029
bon+0.028
Neg logit contributions
 polyg-0.051
 Afgh-0.050
-0.049
idential-0.049
 proble-0.048
Tokenid
Token ID312
Feature activation+1.10e+00

Pos logit contributions
 polyg+0.252
 Afgh+0.249
+0.247
idential+0.245
methyl+0.236
Neg logit contributions
wit-0.264
horn-0.259
 Spur-0.252
utenant-0.240
bon-0.227
Token19
Token ID1129
Feature activation+1.11e+00

Pos logit contributions
 polyg+0.943
idential+0.942
 Afgh+0.934
+0.917
methyl+0.900
Neg logit contributions
wit-0.835
horn-0.825
 Spur-0.811
utenant-0.758
bon-0.710
Token Recommend
Token ID30361
Feature activation+3.81e+00

Pos logit contributions
idential+0.760
 polyg+0.756
 Afgh+0.748
+0.742
methyl+0.724
Neg logit contributions
wit-0.825
horn-0.820
 Spur-0.812
utenant-0.761
bon-0.717
Token
Token ID198
Feature activation+1.54e+00

Pos logit contributions
idential+3.034
 polyg+3.032
 Afgh+3.009
+2.982
methyl+2.918
Neg logit contributions
wit-2.395
horn-2.360
 Spur-2.322
utenant-2.178
bon-2.006
Token
Token ID198
Feature activation+1.48e+00

Pos logit contributions
idential+1.263
 polyg+1.261
 Afgh+1.254
+1.240
methyl+1.214
Neg logit contributions
wit-0.937
horn-0.924
 Spur-0.906
utenant-0.843
bon-0.782
TokenRecommend
Token ID41248
Feature activation+4.07e+00

Pos logit contributions
 polyg+0.833
idential+0.833
 Afgh+0.825
+0.794
methyl+0.772
Neg logit contributions
wit-1.310
horn-1.296
 Spur-1.280
utenant-1.214
bon-1.167
Token Share
Token ID8734
Feature activation+4.47e+00

Pos logit contributions
idential+2.819
 polyg+2.816
 Afgh+2.790
+2.765
methyl+2.694
Neg logit contributions
wit-2.993
horn-2.948
 Spur-2.905
utenant-2.755
bon-2.574
Token this
Token ID428
Feature activation+1.37e+00

Pos logit contributions
 polyg+3.048
idential+3.022
 Afgh+2.982
+2.972
methyl+2.883
Neg logit contributions
wit-3.286
horn-3.244
 Spur-3.204
utenant-3.017
lishes-2.844
Token comment
Token ID2912
Feature activation+2.39e-01

Pos logit contributions
idential+1.254
 Afgh+1.253
+1.232
 polyg+1.229
methyl+1.212
Neg logit contributions
wit-0.706
horn-0.697
 Spur-0.688
utenant-0.634
bon-0.583
Token on
Token ID319
Feature activation+5.51e-01

Pos logit contributions
idential+0.181
 Afgh+0.181
 polyg+0.179
+0.176
 tremend+0.174
Neg logit contributions
wit-0.162
horn-0.162
 Spur-0.159
utenant-0.148
bon-0.141
Token Facebook
Token ID3203
Feature activation-7.27e-01

Pos logit contributions
idential+0.464
 polyg+0.460
 Afgh+0.458
+0.452
methyl+0.447
Neg logit contributions
wit-0.328
horn-0.325
 Spur-0.319
utenant-0.288
bon-0.277
Token Share
Token ID8734
Feature activation+3.93e+00

Pos logit contributions
wit+0.487
 Spur+0.485
horn+0.484
utenant+0.442
bon+0.415
Neg logit contributions
idential-0.556
 polyg-0.551
 Afgh-0.547
-0.538
methyl-0.530
Token Obama
Token ID2486
Feature activation+3.87e-01

Pos logit contributions
wit+0.058
horn+0.057
 Spur+0.056
utenant+0.054
bon+0.051
Neg logit contributions
idential-0.038
 polyg-0.038
 Afgh-0.037
-0.037
methyl-0.036
Token is
Token ID318
Feature activation-1.66e-02

Pos logit contributions
idential+0.272
 polyg+0.269
 Afgh+0.266
+0.266
methyl+0.260
Neg logit contributions
wit-0.282
horn-0.279
 Spur-0.276
utenant-0.259
bon-0.244
Token the
Token ID262
Feature activation+2.26e-01

Pos logit contributions
wit+0.012
horn+0.012
 Spur+0.012
utenant+0.011
bon+0.011
Neg logit contributions
idential-0.012
 polyg-0.011
-0.011
 Afgh-0.011
methyl-0.011
Token worst
Token ID5290
Feature activation+1.47e-01

Pos logit contributions
idential+0.164
 polyg+0.161
+0.160
 Afgh+0.159
methyl+0.157
Neg logit contributions
wit-0.160
horn-0.157
 Spur-0.156
utenant-0.146
bon-0.137
Token ne
Token ID497
Feature activation-9.52e-01

Pos logit contributions
idential+0.106
 polyg+0.104
+0.104
 Afgh+0.103
methyl+0.101
Neg logit contributions
wit-0.106
horn-0.103
 Spur-0.103
utenant-0.096
bon-0.091
Token­
Token ID3907
Feature activation+4.44e+00

Pos logit contributions
wit+0.820
horn+0.808
 Spur+0.798
utenant+0.761
bon+0.725
Neg logit contributions
idential-0.546
 polyg-0.545
 Afgh-0.535
-0.533
methyl-0.517
Tokengo
Token ID2188
Feature activation+7.54e-02

Pos logit contributions
idential+3.005
 polyg+2.971
 Afgh+2.943
+2.939
methyl+2.884
Neg logit contributions
wit-3.280
horn-3.233
 Spur-3.230
utenant-3.029
 waiter-2.839
Token­
Token ID3907
Feature activation+4.26e+00

Pos logit contributions
idential+0.041
 polyg+0.040
 Afgh+0.040
+0.040
methyl+0.038
Neg logit contributions
wit-0.067
horn-0.067
 Spur-0.066
utenant-0.063
bon-0.060
Tokenti
Token ID20259
Feature activation+1.88e+00

Pos logit contributions
idential+2.272
 polyg+2.264
 Afgh+2.232
+2.205
methyl+2.142
Neg logit contributions
wit-3.797
horn-3.762
 Spur-3.729
utenant-3.557
bon-3.361
Token­
Token ID3907
Feature activation+3.93e+00

Pos logit contributions
idential+0.910
 polyg+0.908
 Afgh+0.896
+0.882
methyl+0.847
Neg logit contributions
wit-1.780
horn-1.767
 Spur-1.744
utenant-1.672
bon-1.589
Tokenat
Token ID265
Feature activation+5.96e-01

Pos logit contributions
idential+2.681
 polyg+2.669
 Afgh+2.626
+2.605
methyl+2.562
Neg logit contributions
wit-2.907
horn-2.886
 Spur-2.862
utenant-2.709
 waiter-2.511
Token expectations
Token ID9027
Feature activation+9.44e-02

Pos logit contributions
wit+0.302
horn+0.298
 Spur+0.296
utenant+0.277
bon+0.261
Neg logit contributions
idential-0.302
 polyg-0.299
 Afgh-0.297
-0.296
methyl-0.290
Token and
Token ID290
Feature activation-4.39e-01

Pos logit contributions
idential+0.062
 polyg+0.062
 Afgh+0.061
+0.061
methyl+0.060
Neg logit contributions
wit-0.073
horn-0.072
 Spur-0.071
utenant-0.067
bon-0.064
Token elevated
Token ID15321
Feature activation-1.30e+00

Pos logit contributions
wit+0.300
horn+0.296
 Spur+0.294
utenant+0.274
bon+0.256
Neg logit contributions
idential-0.328
 polyg-0.323
-0.321
 Afgh-0.321
methyl-0.314
Token the
Token ID262
Feature activation-3.56e-02

Pos logit contributions
wit+0.896
horn+0.887
 Spur+0.879
utenant+0.819
bon+0.769
Neg logit contributions
idential-0.957
 polyg-0.947
 Afgh-0.940
-0.936
methyl-0.918
Token Bl
Token ID1086
Feature activation-1.36e+00

Pos logit contributions
wit+0.023
horn+0.023
 Spur+0.022
utenant+0.021
bon+0.020
Neg logit contributions
idential-0.028
 polyg-0.028
 Afgh-0.027
-0.027
methyl-0.027
Tokenoc
Token ID420
Feature activation+4.42e+00

Pos logit contributions
wit+0.933
horn+0.917
 Spur+0.875
utenant+0.836
bon+0.808
Neg logit contributions
 Afgh-1.043
 polyg-1.029
-1.026
idential-1.016
 tremend-1.000
Token
Token ID447
Feature activation-2.07e-01

Pos logit contributions
 polyg+3.016
idential+2.967
 Afgh+2.957
+2.936
methyl+2.829
Neg logit contributions
wit-3.269
horn-3.224
 Spur-3.183
utenant-3.032
lishes-2.828
Token
Token ID247
Feature activation+3.92e-01

Pos logit contributions
wit+0.170
horn+0.168
 Spur+0.166
utenant+0.158
bon+0.149
Neg logit contributions
 polyg-0.127
idential-0.126
 Afgh-0.124
-0.123
methyl-0.120
Tokens
Token ID82
Feature activation+2.57e-01

Pos logit contributions
idential+0.244
 polyg+0.244
 Afgh+0.241
+0.239
methyl+0.232
Neg logit contributions
wit-0.316
horn-0.313
 Spur-0.309
utenant-0.294
bon-0.276
Token prestige
Token ID29063
Feature activation-1.37e+00

Pos logit contributions
idential+0.210
 polyg+0.210
 Afgh+0.209
+0.207
methyl+0.202
Neg logit contributions
wit-0.157
horn-0.155
 Spur-0.152
utenant-0.142
bon-0.131
Token to
Token ID284
Feature activation-3.18e-01

Pos logit contributions
wit+1.035
horn+1.025
 Spur+1.010
utenant+0.948
bon+0.905
Neg logit contributions
idential-0.926
 Afgh-0.911
 polyg-0.904
-0.894
methyl-0.889
Token visits
Token ID11864
Feature activation+1.13e-01

Pos logit contributions
horn+0.228
wit+0.227
 Spur+0.222
utenant+0.203
bon+0.186
Neg logit contributions
idential-0.372
 Afgh-0.368
-0.368
 polyg-0.368
methyl-0.360
Token today
Token ID1909
Feature activation+1.05e+00

Pos logit contributions
idential+0.100
 polyg+0.099
 Afgh+0.099
+0.099
methyl+0.096
Neg logit contributions
wit-0.061
horn-0.061
 Spur-0.059
utenant-0.054
bon-0.049
Token)
Token ID8
Feature activation+7.60e-01

Pos logit contributions
idential+0.846
 polyg+0.843
 Afgh+0.839
+0.829
methyl+0.813
Neg logit contributions
wit-0.660
horn-0.649
 Spur-0.639
utenant-0.594
bon-0.552
Token
Token ID198
Feature activation+2.92e-01

Pos logit contributions
idential+0.629
 polyg+0.626
 Afgh+0.625
+0.623
methyl+0.602
Neg logit contributions
wit-0.449
horn-0.448
 Spur-0.436
utenant-0.415
lishes-0.378
Token
Token ID198
Feature activation+2.69e-01

Pos logit contributions
idential+0.246
 polyg+0.245
 Afgh+0.245
+0.241
methyl+0.236
Neg logit contributions
wit-0.174
horn-0.171
 Spur-0.167
utenant-0.154
bon-0.144
TokenSubscribe
Token ID27125
Feature activation+4.39e+00

Pos logit contributions
 polyg+0.187
idential+0.187
 Afgh+0.186
+0.181
methyl+0.177
Neg logit contributions
wit-0.200
horn-0.197
 Spur-0.192
utenant-0.181
bon-0.173
Token and
Token ID290
Feature activation+5.10e-01

Pos logit contributions
idential+3.064
 polyg+3.053
 Afgh+3.021
+3.001
methyl+2.913
Neg logit contributions
wit-3.196
horn-3.130
 Spur-3.081
utenant-2.942
bon-2.731
Token get
Token ID651
Feature activation+9.94e-01

Pos logit contributions
idential+0.394
 polyg+0.392
 Afgh+0.391
+0.387
methyl+0.380
Neg logit contributions
wit-0.335
horn-0.330
 Spur-0.329
utenant-0.303
bon-0.284
Token email
Token ID3053
Feature activation+6.39e-01

Pos logit contributions
idential+0.689
 polyg+0.686
 Afgh+0.680
+0.678
methyl+0.659
Neg logit contributions
wit-0.732
horn-0.726
 Spur-0.717
utenant-0.669
bon-0.631
Token notifications
Token ID19605
Feature activation+2.07e+00

Pos logit contributions
idential+0.447
 polyg+0.447
 Afgh+0.443
+0.439
methyl+0.428
Neg logit contributions
wit-0.465
horn-0.461
 Spur-0.454
utenant-0.427
bon-0.401
Token whenever
Token ID8797
Feature activation+9.40e-01

Pos logit contributions
idential+1.516
 polyg+1.513
 Afgh+1.501
+1.487
methyl+1.451
Neg logit contributions
wit-1.448
horn-1.430
 Spur-1.409
utenant-1.326
bon-1.237
Token should
Token ID815
Feature activation-8.46e-01

Pos logit contributions
idential+0.063
 polyg+0.062
 Afgh+0.062
+0.062
methyl+0.060
Neg logit contributions
wit-0.056
horn-0.055
 Spur-0.055
utenant-0.051
bon-0.048
Token not
Token ID407
Feature activation-2.82e-01

Pos logit contributions
wit+0.534
horn+0.526
 Spur+0.520
utenant+0.486
bon+0.450
Neg logit contributions
idential-0.673
 Afgh-0.670
 polyg-0.668
-0.665
methyl-0.650
Token fear
Token ID3252
Feature activation+1.90e-01

Pos logit contributions
wit+0.179
horn+0.176
 Spur+0.174
utenant+0.163
bon+0.150
Neg logit contributions
idential-0.224
 polyg-0.223
 Afgh-0.223
-0.221
methyl-0.216
Token the
Token ID262
Feature activation-1.43e-01

Pos logit contributions
idential+0.136
 polyg+0.136
 Afgh+0.135
+0.134
methyl+0.131
Neg logit contributions
wit-0.135
horn-0.133
 Spur-0.132
utenant-0.124
bon-0.116
Token Bl
Token ID1086
Feature activation-1.46e+00

Pos logit contributions
wit+0.099
horn+0.098
 Spur+0.097
utenant+0.090
bon+0.085
Neg logit contributions
idential-0.105
 polyg-0.104
 Afgh-0.103
-0.103
methyl-0.101
Tokenoc
Token ID420
Feature activation+4.37e+00

Pos logit contributions
wit+1.020
horn+1.006
 Spur+0.957
utenant+0.906
bon+0.873
Neg logit contributions
 polyg-1.095
-1.083
 Afgh-1.083
idential-1.078
methyl-1.024
Token Qué
Token ID46345
Feature activation-7.89e-01

Pos logit contributions
 polyg+2.539
idential+2.521
 Afgh+2.496
+2.477
methyl+2.371
Neg logit contributions
wit-3.673
horn-3.638
 Spur-3.595
utenant-3.445
lishes-3.230
Tokenb
Token ID65
Feature activation+1.18e-01

Pos logit contributions
wit+0.609
horn+0.602
 Spur+0.586
utenant+0.557
bon+0.550
Neg logit contributions
idential-0.527
 Afgh-0.523
 polyg-0.515
-0.509
methyl-0.488
Tokené
Token ID2634
Feature activation+1.45e+00

Pos logit contributions
 Afgh+0.070
idential+0.070
 polyg+0.070
+0.068
methyl+0.066
Neg logit contributions
wit-0.099
horn-0.098
 Spur-0.096
utenant-0.091
bon-0.088
Tokenco
Token ID1073
Feature activation+1.67e-01

Pos logit contributions
 Afgh+1.025
idential+1.008
 polyg+1.008
+0.994
methyl+0.974
Neg logit contributions
horn-1.053
wit-1.051
 Spur-1.019
utenant-0.964
bon-0.932
Tokenis
Token ID271
Feature activation+1.90e-01

Pos logit contributions
idential+0.109
 Afgh+0.109
 polyg+0.107
+0.107
methyl+0.104
Neg logit contributions
horn-0.128
wit-0.128
 Spur-0.126
utenant-0.118
bon-0.113
Tokenio
Token ID952
Feature activation+1.09e+00

Pos logit contributions
 polyg+0.423
idential+0.421
 Afgh+0.419
+0.415
methyl+0.402
Neg logit contributions
wit-0.518
horn-0.512
 Spur-0.503
utenant-0.477
bon-0.452
Token on
Token ID319
Feature activation-3.77e-01

Pos logit contributions
idential+0.718
 polyg+0.715
 Afgh+0.708
+0.702
methyl+0.684
Neg logit contributions
wit-0.835
horn-0.825
 Spur-0.815
utenant-0.770
bon-0.725
Token Fox
Token ID5426
Feature activation-8.80e-01

Pos logit contributions
wit+0.272
horn+0.268
 Spur+0.268
utenant+0.247
bon+0.236
Neg logit contributions
idential-0.267
 polyg-0.263
-0.262
 Afgh-0.259
methyl-0.256
Token News
Token ID3000
Feature activation+1.37e-01

Pos logit contributions
wit+0.557
horn+0.548
 Spur+0.547
utenant+0.501
bon+0.472
Neg logit contributions
idential-0.703
 polyg-0.701
-0.692
 Afgh-0.689
methyl-0.680
Token Chan
Token ID18704
Feature activation-2.25e-01

Pos logit contributions
 polyg+0.099
idential+0.099
+0.097
 Afgh+0.097
methyl+0.095
Neg logit contributions
wit-0.096
horn-0.095
 Spur-0.094
utenant-0.088
bon-0.083
Token­
Token ID3907
Feature activation+4.36e+00

Pos logit contributions
wit+0.206
horn+0.202
 Spur+0.201
utenant+0.190
bon+0.182
Neg logit contributions
 polyg-0.118
idential-0.117
 Afgh-0.115
-0.114
methyl-0.111
Tokennel
Token ID4954
Feature activation+2.30e-02

Pos logit contributions
idential+3.068
 polyg+3.009
+2.996
 Afgh+2.989
methyl+2.911
Neg logit contributions
wit-3.048
 Spur-3.045
horn-3.011
utenant-2.850
 waiter-2.623
Token after
Token ID706
Feature activation+3.43e-01

Pos logit contributions
idential+0.016
 polyg+0.016
+0.016
 Afgh+0.016
methyl+0.015
Neg logit contributions
wit-0.017
horn-0.017
 Spur-0.017
utenant-0.015
bon-0.015
Token Obama
Token ID2486
Feature activation+5.28e-01

Pos logit contributions
idential+0.235
 polyg+0.233
 Afgh+0.231
+0.230
methyl+0.224
Neg logit contributions
wit-0.257
horn-0.253
 Spur-0.251
utenant-0.235
bon-0.222
Token nor
Token ID4249
Feature activation-5.52e-01

Pos logit contributions
idential+0.387
 polyg+0.384
 Afgh+0.381
+0.379
methyl+0.370
Neg logit contributions
wit-0.369
horn-0.365
 Spur-0.361
utenant-0.338
bon-0.317
Token­
Token ID3907
Feature activation+4.16e+00

Pos logit contributions
wit+0.476
horn+0.470
 Spur+0.467
utenant+0.440
bon+0.421
Neg logit contributions
idential-0.315
 polyg-0.311
-0.305
 Afgh-0.302
methyl-0.298
Token of
Token ID286
Feature activation+9.25e-01

Pos logit contributions
wit+0.366
horn+0.363
 Spur+0.355
utenant+0.335
bon+0.314
Neg logit contributions
idential-0.374
 polyg-0.373
 Afgh-0.371
-0.366
methyl-0.357
Token Dal
Token ID12348
Feature activation-9.85e-01

Pos logit contributions
idential+0.572
 polyg+0.566
 Afgh+0.559
+0.551
methyl+0.537
Neg logit contributions
wit-0.753
horn-0.748
 Spur-0.740
utenant-0.696
bon-0.661
TokenK
Token ID42
Feature activation+1.36e+00

Pos logit contributions
horn+0.787
wit+0.781
 Spur+0.766
utenant+0.720
bon+0.701
Neg logit contributions
 Afgh-0.623
idential-0.620
 polyg-0.613
-0.612
CLUD-0.588
Token Profile
Token ID13118
Feature activation+6.69e-01

Pos logit contributions
idential+0.965
 polyg+0.963
 Afgh+0.955
+0.945
methyl+0.922
Neg logit contributions
wit-0.974
horn-0.962
 Spur-0.949
utenant-0.895
bon-0.836
Token Blog
Token ID14001
Feature activation+2.49e+00

Pos logit contributions
idential+0.564
 polyg+0.562
 Afgh+0.559
+0.556
methyl+0.542
Neg logit contributions
wit-0.394
horn-0.386
 Spur-0.376
utenant-0.353
lishes-0.321
Token Joined
Token ID16709
Feature activation+4.34e+00

Pos logit contributions
idential+2.306
 polyg+2.302
 Afgh+2.288
+2.270
methyl+2.227
Neg logit contributions
wit-1.254
horn-1.232
 Spur-1.206
utenant-1.107
bon-0.999
Token June
Token ID2795
Feature activation+9.71e-02

Pos logit contributions
 polyg+3.134
 Afgh+3.113
idential+3.098
+3.055
methyl+2.988
Neg logit contributions
wit-3.061
horn-3.011
 Spur-2.937
utenant-2.812
lishes-2.601
Token 2012
Token ID2321
Feature activation+1.79e-01

Pos logit contributions
idential+0.076
 polyg+0.075
 Afgh+0.074
+0.073
methyl+0.072
Neg logit contributions
wit-0.064
horn-0.064
 Spur-0.063
utenant-0.058
bon-0.054
Token Canada
Token ID3340
Feature activation+1.24e+00

Pos logit contributions
idential+0.107
 polyg+0.106
 Afgh+0.104
+0.104
methyl+0.101
Neg logit contributions
wit-0.149
horn-0.148
 Spur-0.147
utenant-0.139
bon-0.132
Token 16
Token ID1467
Feature activation+1.24e+00

Pos logit contributions
idential+0.785
 polyg+0.777
 Afgh+0.763
+0.762
methyl+0.747
Neg logit contributions
wit-0.992
horn-0.983
 Spur-0.978
utenant-0.914
bon-0.869
Token10
Token ID940
Feature activation+1.22e+00

Pos logit contributions
idential+0.962
 polyg+0.961
 Afgh+0.953
+0.944
methyl+0.923
Neg logit contributions
wit-0.809
horn-0.798
 Spur-0.785
utenant-0.735
bon-0.683
Token name
Token ID1438
Feature activation+3.41e-01

Pos logit contributions
idential+0.181
 polyg+0.177
+0.176
 Afgh+0.176
methyl+0.173
Neg logit contributions
wit-0.166
horn-0.163
 Spur-0.162
utenant-0.151
bon-0.141
Token is
Token ID318
Feature activation+1.80e-01

Pos logit contributions
idential+0.248
 polyg+0.247
 Afgh+0.245
+0.243
methyl+0.237
Neg logit contributions
wit-0.240
horn-0.237
 Spur-0.233
utenant-0.219
bon-0.205
Token still
Token ID991
Feature activation+9.51e-01

Pos logit contributions
idential+0.134
 polyg+0.133
 Afgh+0.132
+0.130
methyl+0.127
Neg logit contributions
wit-0.124
horn-0.123
 Spur-0.121
utenant-0.113
bon-0.106
Token a
Token ID257
Feature activation+4.79e-01

Pos logit contributions
idential+0.698
 polyg+0.690
 Afgh+0.685
+0.681
methyl+0.666
Neg logit contributions
wit-0.665
horn-0.659
 Spur-0.649
utenant-0.607
bon-0.571
Token polit
Token ID1408
Feature activation-4.71e-01

Pos logit contributions
idential+0.353
 polyg+0.350
 Afgh+0.349
+0.346
methyl+0.338
Neg logit contributions
wit-0.333
horn-0.329
 Spur-0.325
utenant-0.302
bon-0.284
Token­
Token ID3907
Feature activation+4.33e+00

Pos logit contributions
wit+0.426
horn+0.419
 Spur+0.412
utenant+0.393
bon+0.379
Neg logit contributions
 polyg-0.251
idential-0.250
 Afgh-0.245
-0.244
methyl-0.235
Tokenic
Token ID291
Feature activation+7.40e-01

Pos logit contributions
idential+3.381
 polyg+3.350
 Afgh+3.317
+3.302
methyl+3.233
Neg logit contributions
wit-2.791
horn-2.742
 Spur-2.729
utenant-2.550
bon-2.342
Token­
Token ID3907
Feature activation+4.30e+00

Pos logit contributions
idential+0.387
 polyg+0.386
 Afgh+0.381
+0.377
methyl+0.364
Neg logit contributions
wit-0.672
horn-0.666
 Spur-0.657
utenant-0.626
bon-0.597
Tokenal
Token ID282
Feature activation+3.50e-01

Pos logit contributions
idential+1.830
 polyg+1.801
 Afgh+1.768
+1.742
methyl+1.695
Neg logit contributions
wit-4.273
horn-4.246
 Spur-4.229
utenant-4.059
 waiter-3.843
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
idential+0.262
 polyg+0.260
 Afgh+0.258
+0.257
methyl+0.251
Neg logit contributions
wit-0.239
horn-0.236
 Spur-0.233
utenant-0.217
bon-0.204
Token­
Token ID3907
Feature activation+4.29e+00

Pos logit contributions
wit+0.162
horn+0.159
 Spur+0.158
utenant+0.150
bon+0.143
Neg logit contributions
idential-0.101
 polyg-0.100
-0.098
 Afgh-0.098
methyl-0.095
Token still
Token ID991
Feature activation+9.51e-01

Pos logit contributions
idential+0.134
 polyg+0.133
 Afgh+0.132
+0.130
methyl+0.127
Neg logit contributions
wit-0.124
horn-0.123
 Spur-0.121
utenant-0.113
bon-0.106
Token a
Token ID257
Feature activation+4.79e-01

Pos logit contributions
idential+0.698
 polyg+0.690
 Afgh+0.685
+0.681
methyl+0.666
Neg logit contributions
wit-0.665
horn-0.659
 Spur-0.649
utenant-0.607
bon-0.571
Token polit
Token ID1408
Feature activation-4.71e-01

Pos logit contributions
idential+0.353
 polyg+0.350
 Afgh+0.349
+0.346
methyl+0.338
Neg logit contributions
wit-0.333
horn-0.329
 Spur-0.325
utenant-0.302
bon-0.284
Token­
Token ID3907
Feature activation+4.33e+00

Pos logit contributions
wit+0.426
horn+0.419
 Spur+0.412
utenant+0.393
bon+0.379
Neg logit contributions
 polyg-0.251
idential-0.250
 Afgh-0.245
-0.244
methyl-0.235
Tokenic
Token ID291
Feature activation+7.40e-01

Pos logit contributions
idential+3.381
 polyg+3.350
 Afgh+3.317
+3.302
methyl+3.233
Neg logit contributions
wit-2.791
horn-2.742
 Spur-2.729
utenant-2.550
bon-2.342
Token­
Token ID3907
Feature activation+4.30e+00

Pos logit contributions
idential+0.387
 polyg+0.386
 Afgh+0.381
+0.377
methyl+0.364
Neg logit contributions
wit-0.672
horn-0.666
 Spur-0.657
utenant-0.626
bon-0.597
Tokenal
Token ID282
Feature activation+3.50e-01

Pos logit contributions
idential+1.830
 polyg+1.801
 Afgh+1.768
+1.742
methyl+1.695
Neg logit contributions
wit-4.273
horn-4.246
 Spur-4.229
utenant-4.059
 waiter-3.843
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
idential+0.262
 polyg+0.260
 Afgh+0.258
+0.257
methyl+0.251
Neg logit contributions
wit-0.239
horn-0.236
 Spur-0.233
utenant-0.217
bon-0.204
Token­
Token ID3907
Feature activation+4.29e+00

Pos logit contributions
wit+0.162
horn+0.159
 Spur+0.158
utenant+0.150
bon+0.143
Neg logit contributions
idential-0.101
 polyg-0.100
-0.098
 Afgh-0.098
methyl-0.095
Tokens
Token ID82
Feature activation+7.48e-01

Pos logit contributions
idential+2.943
 polyg+2.931
 Afgh+2.869
methyl+2.847
+2.835
Neg logit contributions
wit-3.048
 Spur-3.024
horn-3.008
utenant-2.838
 waiter-2.668
Tokenult
Token ID586
Feature activation+7.11e-01

Pos logit contributions
 polyg+0.499
idential+0.498
 Afgh+0.495
+0.490
methyl+0.476
Neg logit contributions
wit-0.571
horn-0.565
 Spur-0.555
utenant-0.526
bon-0.495
Token­
Token ID3907
Feature activation+4.33e+00

Pos logit contributions
wit+0.426
horn+0.419
 Spur+0.412
utenant+0.393
bon+0.379
Neg logit contributions
 polyg-0.251
idential-0.250
 Afgh-0.245
-0.244
methyl-0.235
Tokenic
Token ID291
Feature activation+7.40e-01

Pos logit contributions
idential+3.381
 polyg+3.350
 Afgh+3.317
+3.302
methyl+3.233
Neg logit contributions
wit-2.791
horn-2.742
 Spur-2.729
utenant-2.550
bon-2.342
Token­
Token ID3907
Feature activation+4.30e+00

Pos logit contributions
idential+0.387
 polyg+0.386
 Afgh+0.381
+0.377
methyl+0.364
Neg logit contributions
wit-0.672
horn-0.666
 Spur-0.657
utenant-0.626
bon-0.597
Tokenal
Token ID282
Feature activation+3.50e-01

Pos logit contributions
idential+1.830
 polyg+1.801
 Afgh+1.768
+1.742
methyl+1.695
Neg logit contributions
wit-4.273
horn-4.246
 Spur-4.229
utenant-4.059
 waiter-3.843
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
idential+0.262
 polyg+0.260
 Afgh+0.258
+0.257
methyl+0.251
Neg logit contributions
wit-0.239
horn-0.236
 Spur-0.233
utenant-0.217
bon-0.204
Token­
Token ID3907
Feature activation+4.29e+00

Pos logit contributions
wit+0.162
horn+0.159
 Spur+0.158
utenant+0.150
bon+0.143
Neg logit contributions
idential-0.101
 polyg-0.100
-0.098
 Afgh-0.098
methyl-0.095
Tokens
Token ID82
Feature activation+7.48e-01

Pos logit contributions
idential+2.943
 polyg+2.931
 Afgh+2.869
methyl+2.847
+2.835
Neg logit contributions
wit-3.048
 Spur-3.024
horn-3.008
utenant-2.838
 waiter-2.668
Tokenult
Token ID586
Feature activation+7.11e-01

Pos logit contributions
 polyg+0.499
idential+0.498
 Afgh+0.495
+0.490
methyl+0.476
Neg logit contributions
wit-0.571
horn-0.565
 Spur-0.555
utenant-0.526
bon-0.495
Token.
Token ID13
Feature activation+8.49e-02

Pos logit contributions
idential+0.502
 polyg+0.500
 Afgh+0.495
+0.491
methyl+0.479
Neg logit contributions
wit-0.515
horn-0.510
 Spur-0.502
utenant-0.472
bon-0.442
Token When
Token ID1649
Feature activation-6.44e-01

Pos logit contributions
idential+0.061
 polyg+0.060
+0.059
 Afgh+0.059
methyl+0.058
Neg logit contributions
wit-0.061
horn-0.060
 Spur-0.060
utenant-0.056
bon-0.053
Token Re
Token ID797
Feature activation-1.69e+00

Pos logit contributions
wit+0.479
horn+0.470
 Spur+0.469
utenant+0.440
bon+0.413
Neg logit contributions
idential-0.444
 polyg-0.437
-0.435
 Afgh-0.431
methyl-0.423
Token onto
Token ID4291
Feature activation-1.11e+00

Pos logit contributions
wit+1.260
horn+1.254
 Spur+1.222
utenant+1.105
bon+1.054
Neg logit contributions
idential-1.811
-1.766
 Afgh-1.758
 polyg-1.729
methyl-1.713
Token utility
Token ID10361
Feature activation-1.08e+00

Pos logit contributions
wit+0.827
horn+0.821
 Spur+0.812
utenant+0.755
bon+0.717
Neg logit contributions
idential-0.765
-0.750
 polyg-0.736
 Afgh-0.735
methyl-0.723
Token...
Token ID986
Feature activation+9.43e-01

Pos logit contributions
wit+0.908
horn+0.899
 Spur+0.893
utenant+0.831
bon+0.803
Neg logit contributions
idential-0.647
-0.629
 Afgh-0.629
 polyg-0.625
methyl-0.612
Token
Token ID198
Feature activation+3.20e-01

Pos logit contributions
idential+0.719
 polyg+0.715
 Afgh+0.710
+0.706
methyl+0.689
Neg logit contributions
wit-0.631
horn-0.623
 Spur-0.612
utenant-0.574
bon-0.536
Token
Token ID198
Feature activation+3.49e-01

Pos logit contributions
idential+0.277
 polyg+0.276
 Afgh+0.275
 tremend+0.271
+0.269
Neg logit contributions
wit-0.184
horn-0.182
 Spur-0.177
utenant-0.162
bon-0.153
TokenSubscribe
Token ID27125
Feature activation+4.28e+00

Pos logit contributions
idential+0.256
 polyg+0.255
 Afgh+0.253
+0.249
methyl+0.243
Neg logit contributions
wit-0.245
horn-0.242
 Spur-0.237
utenant-0.223
bon-0.210
Token to
Token ID284
Feature activation+5.21e-01

Pos logit contributions
idential+2.967
 polyg+2.943
 Afgh+2.923
+2.901
methyl+2.813
Neg logit contributions
wit-3.127
horn-3.049
 Spur-2.997
utenant-2.883
bon-2.671
Token C
Token ID327
Feature activation+9.80e-01

Pos logit contributions
idential+0.356
 polyg+0.354
 Afgh+0.351
+0.349
methyl+0.340
Neg logit contributions
wit-0.388
horn-0.383
 Spur-0.380
utenant-0.357
bon-0.336
Tokenrave
Token ID5758
Feature activation-1.08e+00

Pos logit contributions
idential+0.674
 polyg+0.673
 Afgh+0.668
+0.660
methyl+0.643
Neg logit contributions
wit-0.727
horn-0.718
 Spur-0.708
utenant-0.669
bon-0.628
Token:
Token ID25
Feature activation-8.32e-01

Pos logit contributions
wit+0.827
horn+0.817
 Spur+0.804
utenant+0.761
bon+0.718
Neg logit contributions
 polyg-0.722
idential-0.713
-0.709
 Afgh-0.707
methyl-0.692
Token
Token ID198
Feature activation-4.36e-02

Pos logit contributions
wit+0.580
horn+0.575
 Spur+0.566
utenant+0.525
bon+0.499
Neg logit contributions
 polyg-0.609
idential-0.607
 Afgh-0.601
-0.598
methyl-0.583
Token
Token ID198
Feature activation-4.46e-01

Pos logit contributions
wit+0.281
horn+0.279
 Spur+0.270
utenant+0.247
bon+0.232
Neg logit contributions
idential-0.429
 Afgh-0.428
 polyg-0.428
 tremend-0.422
-0.419
TokenHowever
Token ID4864
Feature activation+8.65e-01

Pos logit contributions
wit+0.323
horn+0.319
 Spur+0.313
utenant+0.296
bon+0.277
Neg logit contributions
idential-0.316
 polyg-0.316
 Afgh-0.313
-0.309
methyl-0.301
Token,
Token ID11
Feature activation+2.69e-02

Pos logit contributions
 polyg+0.511
idential+0.504
 Afgh+0.500
+0.490
methyl+0.479
Neg logit contributions
wit-0.725
horn-0.716
 Spur-0.705
utenant-0.672
bon-0.636
Token now
Token ID783
Feature activation-3.26e-01

Pos logit contributions
idential+0.018
 polyg+0.018
 Afgh+0.018
+0.018
methyl+0.018
Neg logit contributions
wit-0.020
horn-0.020
 Spur-0.019
utenant-0.018
bon-0.017
Token the
Token ID262
Feature activation-1.93e-01

Pos logit contributions
wit+0.239
horn+0.237
 Spur+0.233
utenant+0.220
bon+0.206
Neg logit contributions
idential-0.227
 polyg-0.226
 Afgh-0.224
-0.222
methyl-0.216
Token tide
Token ID20013
Feature activation-4.05e+00

Pos logit contributions
wit+0.130
horn+0.129
 Spur+0.127
utenant+0.119
bon+0.111
Neg logit contributions
idential-0.145
 polyg-0.145
 Afgh-0.143
-0.142
methyl-0.139
Token has
Token ID468
Feature activation-1.29e-01

Pos logit contributions
wit+2.636
horn+2.617
 Spur+2.528
utenant+2.378
bon+2.202
Neg logit contributions
idential-3.147
 Afgh-3.103
 polyg-3.096
-3.091
CLUD-2.987
Token turned
Token ID2900
Feature activation-1.11e+00

Pos logit contributions
wit+0.083
horn+0.082
 Spur+0.081
utenant+0.076
bon+0.070
Neg logit contributions
idential-0.101
 polyg-0.100
 Afgh-0.100
-0.099
methyl-0.096
Token again
Token ID757
Feature activation-2.13e-01

Pos logit contributions
wit+0.820
 Spur+0.807
horn+0.807
utenant+0.750
bon+0.702
Neg logit contributions
idential-0.781
 polyg-0.762
-0.761
 Afgh-0.756
methyl-0.742
Token,
Token ID11
Feature activation-6.24e-02

Pos logit contributions
wit+0.164
horn+0.161
 Spur+0.160
utenant+0.150
bon+0.142
Neg logit contributions
idential-0.142
 polyg-0.141
 Afgh-0.140
-0.139
methyl-0.135
Token and
Token ID290
Feature activation-5.99e-02

Pos logit contributions
wit+0.049
horn+0.048
 Spur+0.047
utenant+0.045
bon+0.042
Neg logit contributions
idential-0.041
 polyg-0.041
 Afgh-0.040
-0.040
methyl-0.039
Token
Token ID198
Feature activation-4.59e-01

Pos logit contributions
wit+0.317
horn+0.312
 Spur+0.308
utenant+0.287
bon+0.266
Neg logit contributions
idential-0.396
 polyg-0.395
 Afgh-0.391
-0.388
methyl-0.381
Token
Token ID198
Feature activation-4.81e-01

Pos logit contributions
wit+0.262
horn+0.259
 Spur+0.250
utenant+0.230
bon+0.217
Neg logit contributions
 Afgh-0.400
idential-0.400
 polyg-0.399
 tremend-0.395
-0.391
TokenD
Token ID35
Feature activation-2.50e-01

Pos logit contributions
wit+0.348
horn+0.344
 Spur+0.338
utenant+0.319
bon+0.299
Neg logit contributions
idential-0.341
 polyg-0.341
 Afgh-0.338
-0.332
methyl-0.325
Tokenang
Token ID648
Feature activation+1.39e+00

Pos logit contributions
wit+0.174
horn+0.171
 Spur+0.168
utenant+0.158
bon+0.148
Neg logit contributions
 polyg-0.185
idential-0.185
 Afgh-0.183
-0.181
methyl-0.176
Token-
Token ID12
Feature activation+1.36e-01

Pos logit contributions
idential+0.984
 polyg+0.982
 Afgh+0.974
+0.964
methyl+0.940
Neg logit contributions
wit-1.006
horn-0.995
 Spur-0.980
utenant-0.925
bon-0.865
TokenHall
Token ID34194
Feature activation-4.00e+00

Pos logit contributions
 polyg+0.101
idential+0.101
 Afgh+0.100
+0.099
methyl+0.096
Neg logit contributions
wit-0.095
horn-0.094
 Spur-0.092
utenant-0.086
bon-0.081
Tokener
Token ID263
Feature activation+1.72e-01

Pos logit contributions
horn+2.908
wit+2.894
 Spur+2.867
utenant+2.679
bon+2.527
Neg logit contributions
 polyg-2.783
idential-2.744
-2.726
 Afgh-2.668
methyl-2.661
Token equ
Token ID1602
Feature activation+6.76e-01

Pos logit contributions
idential+0.120
 polyg+0.120
 Afgh+0.119
+0.118
methyl+0.115
Neg logit contributions
wit-0.125
horn-0.124
 Spur-0.122
utenant-0.115
bon-0.108
Tokenates
Token ID689
Feature activation+6.04e-02

Pos logit contributions
idential+0.392
 polyg+0.391
 Afgh+0.388
+0.383
methyl+0.371
Neg logit contributions
wit-0.574
horn-0.568
 Spur-0.561
utenant-0.534
bon-0.505
Token food
Token ID2057
Feature activation-7.79e-01

Pos logit contributions
 polyg+0.043
idential+0.043
 Afgh+0.043
+0.042
methyl+0.041
Neg logit contributions
wit-0.043
horn-0.042
 Spur-0.042
utenant-0.039
bon-0.037
Token to
Token ID284
Feature activation-7.54e-01

Pos logit contributions
wit+0.543
horn+0.539
 Spur+0.529
utenant+0.495
bon+0.465
Neg logit contributions
idential-0.569
 polyg-0.566
 Afgh-0.559
-0.555
methyl-0.547
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
wit+0.155
horn+0.153
 Spur+0.150
utenant+0.142
bon+0.134
Neg logit contributions
idential-0.131
 polyg-0.129
 Afgh-0.129
-0.127
methyl-0.125
Token<|endoftext|>
Token ID50256
Feature activation-5.88e-01

Pos logit contributions
wit+0.072
horn+0.072
 Spur+0.071
utenant+0.066
bon+0.061
Neg logit contributions
idential-0.085
 polyg-0.085
 Afgh-0.084
-0.083
methyl-0.081
TokenIll
Token ID21478
Feature activation-1.37e+00

Pos logit contributions
wit+0.417
horn+0.412
 Spur+0.401
utenant+0.378
bon+0.358
Neg logit contributions
 polyg-0.428
idential-0.427
 Afgh-0.425
-0.415
methyl-0.404
Tokenust
Token ID436
Feature activation-8.25e-02

Pos logit contributions
wit+0.812
horn+0.802
 Spur+0.786
utenant+0.736
bon+0.676
Neg logit contributions
 polyg-1.137
idential-1.132
 Afgh-1.130
-1.127
methyl-1.092
Tokenrious
Token ID32527
Feature activation-5.33e-01

Pos logit contributions
wit+0.060
horn+0.059
 Spur+0.059
utenant+0.055
bon+0.052
Neg logit contributions
 polyg-0.058
idential-0.058
 Afgh-0.057
-0.057
methyl-0.055
Token Illum
Token ID39256
Feature activation-3.99e+00

Pos logit contributions
wit+0.383
horn+0.379
 Spur+0.376
utenant+0.350
bon+0.330
Neg logit contributions
idential-0.381
 polyg-0.375
-0.373
 Afgh-0.372
methyl-0.362
Tokenination
Token ID1883
Feature activation-1.33e+00

Pos logit contributions
wit+3.214
horn+3.157
 Spur+3.066
utenant+2.946
bon+2.762
Neg logit contributions
 polyg-2.495
-2.475
 Afgh-2.457
idential-2.412
methyl-2.333
Token:
Token ID25
Feature activation-1.34e+00

Pos logit contributions
wit+0.962
horn+0.952
 Spur+0.946
utenant+0.878
bon+0.825
Neg logit contributions
idential-0.949
 polyg-0.936
-0.929
 Afgh-0.928
methyl-0.905
Token Incredible
Token ID33832
Feature activation-4.92e-01

Pos logit contributions
wit+0.976
horn+0.965
 Spur+0.958
utenant+0.893
bon+0.840
Neg logit contributions
idential-0.937
 polyg-0.927
-0.915
 Afgh-0.914
methyl-0.891
Token TR
Token ID7579
Feature activation-1.06e+00

Pos logit contributions
wit+0.368
horn+0.363
 Spur+0.361
utenant+0.335
bon+0.317
Neg logit contributions
idential-0.337
 polyg-0.332
-0.329
 Afgh-0.328
methyl-0.320
TokenON
Token ID1340
Feature activation-1.08e+00

Pos logit contributions
wit+0.763
horn+0.751
 Spur+0.743
utenant+0.695
bon+0.655
Neg logit contributions
idential-0.756
 polyg-0.753
 Afgh-0.748
-0.742
methyl-0.722
Token
Token ID198
Feature activation-6.50e-01

Pos logit contributions
wit+0.442
horn+0.437
 Spur+0.433
utenant+0.403
bon+0.376
Neg logit contributions
idential-0.499
 polyg-0.499
 Afgh-0.492
-0.489
methyl-0.479
Token
Token ID198
Feature activation-5.42e-01

Pos logit contributions
wit+0.375
horn+0.370
 Spur+0.359
utenant+0.329
bon+0.310
Neg logit contributions
idential-0.562
 polyg-0.560
 Afgh-0.560
 tremend-0.549
-0.549
TokenAccording
Token ID4821
Feature activation+2.76e-01

Pos logit contributions
wit+0.386
horn+0.381
 Spur+0.374
utenant+0.352
bon+0.331
Neg logit contributions
 polyg-0.391
idential-0.391
 Afgh-0.387
-0.381
methyl-0.373
Token to
Token ID284
Feature activation-4.73e-01

Pos logit contributions
idential+0.208
 polyg+0.206
 Afgh+0.206
+0.203
methyl+0.198
Neg logit contributions
wit-0.188
horn-0.185
 Spur-0.183
utenant-0.172
bon-0.160
Token the
Token ID262
Feature activation-3.11e-01

Pos logit contributions
wit+0.345
horn+0.341
 Spur+0.337
utenant+0.318
bon+0.297
Neg logit contributions
idential-0.330
 polyg-0.328
 Afgh-0.326
-0.324
methyl-0.317
Token FIR
Token ID23703
Feature activation-3.97e+00

Pos logit contributions
wit+0.207
horn+0.204
 Spur+0.201
utenant+0.189
bon+0.176
Neg logit contributions
idential-0.237
 polyg-0.236
 Afgh-0.234
-0.233
methyl-0.228
Token,
Token ID11
Feature activation-8.15e-01

Pos logit contributions
wit+2.982
horn+2.920
 Spur+2.887
utenant+2.747
bon+2.552
Neg logit contributions
idential-2.630
 polyg-2.622
-2.620
 Afgh-2.615
methyl-2.557
Token
Token ID564
Feature activation-7.00e-02

Pos logit contributions
wit+0.592
horn+0.585
 Spur+0.579
utenant+0.546
bon+0.510
Neg logit contributions
idential-0.570
 polyg-0.569
 Afgh-0.564
-0.561
methyl-0.549
Token
Token ID250
Feature activation-5.16e-01

Pos logit contributions
wit+0.055
horn+0.054
 Spur+0.054
utenant+0.051
bon+0.048
Neg logit contributions
idential-0.045
 Afgh-0.045
 polyg-0.045
-0.045
methyl-0.043
Tokeninn
Token ID3732
Feature activation+7.26e-01

Pos logit contributions
wit+0.366
horn+0.362
 Spur+0.356
utenant+0.336
bon+0.314
Neg logit contributions
idential-0.371
 polyg-0.371
 Afgh-0.368
-0.364
methyl-0.355
Tokenocent
Token ID29421
Feature activation-3.63e-01

Pos logit contributions
idential+0.425
 polyg+0.425
 Afgh+0.421
+0.415
methyl+0.403
Neg logit contributions
wit-0.613
horn-0.607
 Spur-0.598
utenant-0.570
bon-0.538
Token-
Token ID12
Feature activation-1.76e-01

Pos logit contributions
idential+0.456
 polyg+0.452
 Afgh+0.450
+0.447
methyl+0.434
Neg logit contributions
wit-0.374
horn-0.369
 Spur-0.365
utenant-0.340
bon-0.315
Tokeno
Token ID78
Feature activation-1.45e-01

Pos logit contributions
wit+0.124
horn+0.122
 Spur+0.120
utenant+0.113
bon+0.106
Neg logit contributions
idential-0.129
 polyg-0.128
 Afgh-0.127
-0.126
methyl-0.123
Tokenvert
Token ID1851
Feature activation+1.02e+00

Pos logit contributions
wit+0.096
horn+0.094
 Spur+0.093
utenant+0.087
bon+0.081
Neg logit contributions
idential-0.111
 polyg-0.111
 Afgh-0.110
-0.108
methyl-0.106
Tokenime
Token ID524
Feature activation+1.33e+00

Pos logit contributions
 polyg+0.689
idential+0.687
 Afgh+0.677
+0.675
methyl+0.655
Neg logit contributions
wit-0.773
horn-0.760
 Spur-0.753
utenant-0.709
bon-0.663
Token goal
Token ID3061
Feature activation+1.21e+00

Pos logit contributions
idential+1.147
 polyg+1.145
 Afgh+1.137
+1.128
methyl+1.105
Neg logit contributions
wit-0.748
horn-0.737
 Spur-0.724
utenant-0.671
bon-0.613
Token clin
Token ID5327
Feature activation-3.94e+00

Pos logit contributions
idential+0.883
 polyg+0.882
 Afgh+0.874
+0.868
methyl+0.846
Neg logit contributions
wit-0.846
horn-0.835
 Spur-0.823
utenant-0.775
bon-0.723
Tokenched
Token ID1740
Feature activation-2.74e-01

Pos logit contributions
wit+3.222
horn+3.184
 Spur+2.990
utenant+2.887
bon+2.844
Neg logit contributions
 polyg-2.520
 Afgh-2.503
-2.484
 tremend-2.421
 proble-2.357
Token New
Token ID968
Feature activation-9.59e-01

Pos logit contributions
wit+0.201
horn+0.199
 Spur+0.197
utenant+0.185
bon+0.173
Neg logit contributions
idential-0.192
 polyg-0.190
 Afgh-0.190
-0.188
methyl-0.183
Token Jersey
Token ID8221
Feature activation-1.31e+00

Pos logit contributions
wit+0.686
horn+0.675
 Spur+0.663
utenant+0.629
bon+0.586
Neg logit contributions
idential-0.687
 polyg-0.683
 Afgh-0.679
-0.670
methyl-0.655
Token
Token ID447
Feature activation-5.69e-01

Pos logit contributions
wit+0.916
horn+0.905
 Spur+0.897
utenant+0.840
bon+0.782
Neg logit contributions
idential-0.957
 polyg-0.952
 Afgh-0.948
-0.939
methyl-0.915
Token
Token ID247
Feature activation-9.98e-02

Pos logit contributions
wit+0.437
horn+0.433
 Spur+0.425
utenant+0.412
bon+0.381
Neg logit contributions
 polyg-0.377
idential-0.371
 Afgh-0.369
-0.362
methyl-0.353
Token
Token ID247
Feature activation-4.75e-01

Pos logit contributions
wit+0.495
horn+0.488
 Spur+0.479
utenant+0.459
bon+0.429
Neg logit contributions
 polyg-0.412
idential-0.407
 Afgh-0.402
-0.390
methyl-0.387
Tokens
Token ID82
Feature activation-3.31e-01

Pos logit contributions
wit+0.371
horn+0.367
 Spur+0.361
utenant+0.342
bon+0.323
Neg logit contributions
 polyg-0.309
idential-0.309
 Afgh-0.306
-0.302
methyl-0.295
Token ear
Token ID1027
Feature activation+9.48e-01

Pos logit contributions
wit+0.227
horn+0.225
 Spur+0.222
utenant+0.207
bon+0.194
Neg logit contributions
idential-0.245
 polyg-0.242
 Afgh-0.241
-0.241
methyl-0.236
Token or
Token ID393
Feature activation-3.60e-01

Pos logit contributions
idential+0.595
 polyg+0.594
 Afgh+0.589
+0.580
methyl+0.566
Neg logit contributions
wit-0.762
horn-0.755
 Spur-0.741
utenant-0.705
bon-0.666
Token a
Token ID257
Feature activation-5.39e-01

Pos logit contributions
wit+0.267
horn+0.264
 Spur+0.261
utenant+0.246
bon+0.231
Neg logit contributions
idential-0.247
 polyg-0.246
 Afgh-0.244
-0.242
methyl-0.236
Token compliment
Token ID19370
Feature activation-3.93e+00

Pos logit contributions
wit+0.363
horn+0.358
 Spur+0.353
utenant+0.330
bon+0.308
Neg logit contributions
idential-0.409
 polyg-0.405
 Afgh-0.404
-0.401
methyl-0.392
Token in
Token ID287
Feature activation-1.25e+00

Pos logit contributions
wit+2.590
horn+2.588
 Spur+2.520
utenant+2.359
 waiter+2.217
Neg logit contributions
idential-2.975
 Afgh-2.942
 polyg-2.934
-2.927
methyl-2.864
Token Benjamin
Token ID14533
Feature activation-1.01e+00

Pos logit contributions
wit+0.934
horn+0.925
 Spur+0.917
utenant+0.860
bon+0.809
Neg logit contributions
idential-0.865
 polyg-0.849
-0.841
 Afgh-0.837
methyl-0.821
Token Netanyahu
Token ID17104
Feature activation-1.58e-01

Pos logit contributions
wit+0.756
horn+0.745
 Spur+0.741
utenant+0.688
bon+0.650
Neg logit contributions
idential-0.693
 polyg-0.689
 Afgh-0.684
-0.678
methyl-0.670
Token
Token ID447
Feature activation-4.37e-01

Pos logit contributions
wit+0.113
horn+0.112
 Spur+0.110
utenant+0.104
bon+0.097
Neg logit contributions
idential-0.113
 polyg-0.112
 Afgh-0.112
-0.111
methyl-0.108
Token
Token ID247
Feature activation-3.46e-01

Pos logit contributions
wit+0.346
horn+0.342
 Spur+0.334
utenant+0.321
bon+0.300
Neg logit contributions
 polyg-0.283
idential-0.280
 Afgh-0.278
-0.270
methyl-0.267
Token I
Token ID314
Feature activation-2.83e-01

Pos logit contributions
wit+0.019
horn+0.018
 Spur+0.018
utenant+0.017
bon+0.016
Neg logit contributions
idential-0.016
 polyg-0.016
 Afgh-0.016
-0.016
methyl-0.016
Token mean
Token ID1612
Feature activation-2.00e+00

Pos logit contributions
wit+0.181
horn+0.178
 Spur+0.175
utenant+0.164
bon+0.152
Neg logit contributions
idential-0.224
 polyg-0.223
 Afgh-0.222
-0.219
methyl-0.216
Token that
Token ID326
Feature activation+1.07e-01

Pos logit contributions
wit+1.465
horn+1.415
 Spur+1.404
utenant+1.322
bon+1.233
Neg logit contributions
idential-1.407
 polyg-1.386
 Afgh-1.373
-1.360
methyl-1.351
Token as
Token ID355
Feature activation-1.90e-01

Pos logit contributions
idential+0.075
 polyg+0.075
 Afgh+0.074
+0.073
methyl+0.072
Neg logit contributions
wit-0.078
horn-0.077
 Spur-0.075
utenant-0.071
bon-0.067
Token a
Token ID257
Feature activation-3.05e-01

Pos logit contributions
wit+0.145
horn+0.142
 Spur+0.141
utenant+0.132
bon+0.124
Neg logit contributions
idential-0.127
 polyg-0.127
 Afgh-0.126
-0.124
methyl-0.122
Token compliment
Token ID19370
Feature activation-3.86e+00

Pos logit contributions
wit+0.165
horn+0.162
 Spur+0.159
utenant+0.146
bon+0.133
Neg logit contributions
idential-0.272
 polyg-0.271
 Afgh-0.271
-0.268
methyl-0.263
Token,
Token ID11
Feature activation-3.81e-01

Pos logit contributions
wit+2.857
horn+2.815
 Spur+2.776
utenant+2.630
bon+2.462
Neg logit contributions
 Afgh-2.629
idential-2.591
 polyg-2.591
methyl-2.533
-2.528
Token
Token ID447
Feature activation-7.87e-02

Pos logit contributions
wit+0.289
horn+0.284
 Spur+0.282
utenant+0.265
bon+0.249
Neg logit contributions
idential-0.256
 polyg-0.254
 Afgh-0.253
-0.249
methyl-0.245
Token
Token ID251
Feature activation-3.05e-01

Pos logit contributions
wit+0.054
horn+0.053
 Spur+0.052
utenant+0.049
bon+0.046
Neg logit contributions
idential-0.060
 polyg-0.059
 Afgh-0.058
-0.057
methyl-0.057
Token Rich
Token ID3998
Feature activation+4.33e-01

Pos logit contributions
wit+0.235
horn+0.231
 Spur+0.228
utenant+0.214
bon+0.203
Neg logit contributions
idential-0.204
 polyg-0.203
 Afgh-0.201
-0.197
methyl-0.194
Tokenman
Token ID805
Feature activation+8.32e-01

Pos logit contributions
idential+0.306
 polyg+0.305
 Afgh+0.303
+0.298
methyl+0.294
Neg logit contributions
wit-0.315
horn-0.312
 Spur-0.309
utenant-0.287
bon-0.272
Token to
Token ID284
Feature activation+1.15e-01

Pos logit contributions
 polyg+0.926
idential+0.924
 Afgh+0.916
+0.906
methyl+0.883
Neg logit contributions
wit-0.991
horn-0.979
 Spur-0.967
utenant-0.918
bon-0.857
Token raise
Token ID5298
Feature activation-3.64e-01

Pos logit contributions
idential+0.097
 polyg+0.096
 Afgh+0.096
+0.095
methyl+0.093
Neg logit contributions
wit-0.068
horn-0.066
 Spur-0.066
utenant-0.061
bon-0.056
Token awareness
Token ID9359
Feature activation-1.77e+00

Pos logit contributions
wit+0.264
horn+0.261
 Spur+0.259
utenant+0.242
bon+0.228
Neg logit contributions
idential-0.257
 polyg-0.255
-0.252
 Afgh-0.252
methyl-0.245
Token of
Token ID286
Feature activation-8.14e-01

Pos logit contributions
wit+1.311
horn+1.291
 Spur+1.273
utenant+1.195
bon+1.126
Neg logit contributions
idential-1.221
 polyg-1.216
 Afgh-1.205
-1.194
methyl-1.166
Token an
Token ID281
Feature activation-9.77e-01

Pos logit contributions
wit+0.598
horn+0.594
 Spur+0.589
utenant+0.549
bon+0.520
Neg logit contributions
idential-0.565
-0.554
 polyg-0.554
 Afgh-0.551
methyl-0.535
Token issue
Token ID2071
Feature activation-3.86e+00

Pos logit contributions
wit+0.663
horn+0.659
 Spur+0.647
utenant+0.603
bon+0.561
Neg logit contributions
idential-0.729
 polyg-0.726
-0.724
 Afgh-0.714
methyl-0.704
Token than
Token ID621
Feature activation-1.83e+00

Pos logit contributions
wit+2.950
horn+2.923
 Spur+2.902
utenant+2.667
bon+2.538
Neg logit contributions
idential-2.525
-2.472
 polyg-2.465
 Afgh-2.459
methyl-2.435
Token through
Token ID832
Feature activation-5.07e-01

Pos logit contributions
wit+1.231
horn+1.213
 Spur+1.204
utenant+1.119
bon+1.043
Neg logit contributions
idential-1.382
 polyg-1.363
 Afgh-1.359
-1.353
methyl-1.322
Token a
Token ID257
Feature activation-6.32e-01

Pos logit contributions
wit+0.369
horn+0.364
 Spur+0.360
utenant+0.338
bon+0.317
Neg logit contributions
idential-0.357
 polyg-0.354
 Afgh-0.352
-0.349
methyl-0.340
Token nice
Token ID3621
Feature activation-1.02e+00

Pos logit contributions
wit+0.434
horn+0.428
 Spur+0.424
utenant+0.393
bon+0.370
Neg logit contributions
idential-0.471
 polyg-0.465
 Afgh-0.465
-0.462
methyl-0.450
Token Public
Token ID5094
Feature activation-1.98e+00

Pos logit contributions
wit+0.719
horn+0.713
 Spur+0.704
utenant+0.652
bon+0.618
Neg logit contributions
idential-0.740
 polyg-0.730
 Afgh-0.727
-0.723
methyl-0.705
Token,
Token ID11
Feature activation-8.99e-01

Pos logit contributions
wit+0.082
horn+0.081
 Spur+0.080
utenant+0.076
bon+0.072
Neg logit contributions
idential-0.068
 polyg-0.068
 Afgh-0.067
-0.066
methyl-0.064
Token previously
Token ID4271
Feature activation+2.19e-01

Pos logit contributions
wit+0.640
horn+0.636
 Spur+0.628
utenant+0.585
bon+0.552
Neg logit contributions
idential-0.643
 polyg-0.636
-0.630
 Afgh-0.628
methyl-0.613
Token worked
Token ID3111
Feature activation+9.27e-01

Pos logit contributions
idential+0.168
 polyg+0.166
 Afgh+0.164
+0.164
methyl+0.160
Neg logit contributions
wit-0.146
horn-0.145
 Spur-0.143
utenant-0.133
bon-0.124
Token as
Token ID355
Feature activation+5.65e-02

Pos logit contributions
idential+0.654
 polyg+0.650
 Afgh+0.645
+0.643
methyl+0.625
Neg logit contributions
wit-0.670
horn-0.666
 Spur-0.656
utenant-0.619
bon-0.578
Token a
Token ID257
Feature activation-5.08e-01

Pos logit contributions
idential+0.039
 polyg+0.039
 Afgh+0.039
+0.038
methyl+0.037
Neg logit contributions
wit-0.042
horn-0.041
 Spur-0.041
utenant-0.038
bon-0.036
Token taxi
Token ID17536
Feature activation-3.83e+00

Pos logit contributions
wit+0.335
horn+0.333
 Spur+0.330
utenant+0.305
 waiter+0.287
Neg logit contributions
idential-0.391
 polyg-0.385
-0.384
 Afgh-0.383
methyl-0.374
Token driver
Token ID4639
Feature activation-1.44e+00

Pos logit contributions
horn+1.837
wit+1.833
 Spur+1.768
utenant+1.644
 waiter+1.531
Neg logit contributions
idential-3.569
 Afgh-3.535
 polyg-3.534
-3.515
methyl-3.465
Token,
Token ID11
Feature activation-9.40e-01

Pos logit contributions
wit+1.043
horn+1.043
 Spur+1.025
utenant+0.970
 waiter+0.909
Neg logit contributions
idential-1.011
 polyg-0.995
-0.992
 Afgh-0.989
methyl-0.965
Token according
Token ID1864
Feature activation+3.02e-01

Pos logit contributions
wit+0.671
horn+0.665
 Spur+0.658
utenant+0.615
 waiter+0.584
Neg logit contributions
idential-0.669
 polyg-0.663
-0.657
 Afgh-0.656
methyl-0.640
Token to
Token ID284
Feature activation-5.51e-01

Pos logit contributions
idential+0.233
 Afgh+0.229
 polyg+0.229
+0.227
methyl+0.221
Neg logit contributions
wit-0.202
horn-0.200
 Spur-0.197
utenant-0.182
bon-0.172
Token filings
Token ID28058
Feature activation-4.21e-01

Pos logit contributions
wit+0.408
horn+0.404
 Spur+0.401
utenant+0.376
bon+0.354
Neg logit contributions
idential-0.378
 polyg-0.373
 Afgh-0.372
-0.371
methyl-0.361
Token mobilization
Token ID46762
Feature activation-8.87e-01

Pos logit contributions
wit+0.361
horn+0.355
 Spur+0.352
utenant+0.327
bon+0.305
Neg logit contributions
idential-0.457
 Afgh-0.455
 polyg-0.454
-0.450
methyl-0.437
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
wit+0.697
horn+0.688
 Spur+0.679
utenant+0.638
bon+0.606
Neg logit contributions
idential-0.575
 polyg-0.569
 Afgh-0.567
-0.559
methyl-0.540
Token
Token ID198
Feature activation-4.50e-01

Pos logit contributions
 polyg+0.188
idential+0.187
 Afgh+0.187
+0.185
methyl+0.182
Neg logit contributions
wit-0.162
horn-0.161
 Spur-0.156
utenant-0.149
 waiter-0.137
Token
Token ID198
Feature activation-3.22e-01

Pos logit contributions
wit+0.257
horn+0.255
 Spur+0.246
utenant+0.225
bon+0.213
Neg logit contributions
idential-0.393
 Afgh-0.391
 polyg-0.391
 tremend-0.387
-0.383
TokenIncreases
Token ID28544
Feature activation-1.35e+00

Pos logit contributions
wit+0.218
horn+0.215
 Spur+0.212
utenant+0.197
bon+0.186
Neg logit contributions
idential-0.244
 polyg-0.244
 Afgh-0.242
-0.238
methyl-0.232
Token cellular
Token ID19824
Feature activation-3.81e+00

Pos logit contributions
wit+0.949
horn+0.938
 Spur+0.927
utenant+0.868
bon+0.814
Neg logit contributions
idential-0.981
 polyg-0.972
 Afgh-0.967
-0.962
methyl-0.932
Token fat
Token ID3735
Feature activation-1.93e+00

Pos logit contributions
wit+2.452
horn+2.420
 Spur+2.418
utenant+2.201
bon+2.079
Neg logit contributions
idential-2.938
-2.901
 polyg-2.892
 Afgh-2.882
methyl-2.771
Token oxidation
Token ID37767
Feature activation-2.26e+00

Pos logit contributions
wit+1.282
horn+1.251
 Spur+1.233
utenant+1.158
bon+1.091
Neg logit contributions
 Afgh-1.476
idential-1.467
 polyg-1.461
-1.442
methyl-1.400
Token.
Token ID13
Feature activation+3.39e-01

Pos logit contributions
wit+1.739
horn+1.711
 Spur+1.687
utenant+1.586
bon+1.511
Neg logit contributions
idential-1.496
 Afgh-1.484
 polyg-1.476
-1.459
methyl-1.407
Token
Token ID198
Feature activation-3.84e-01

Pos logit contributions
 polyg+0.260
idential+0.259
 Afgh+0.259
+0.256
methyl+0.251
Neg logit contributions
wit-0.223
horn-0.222
 Spur-0.215
utenant-0.206
 waiter-0.190
Token
Token ID198
Feature activation-2.51e-01

Pos logit contributions
wit+0.220
horn+0.218
 Spur+0.211
utenant+0.193
bon+0.182
Neg logit contributions
idential-0.334
 Afgh-0.333
 polyg-0.333
 tremend-0.328
-0.326
Token Calif
Token ID3192
Feature activation+4.96e-01

Pos logit contributions
idential+0.176
 polyg+0.175
 Afgh+0.174
+0.172
methyl+0.168
Neg logit contributions
wit-0.200
horn-0.198
 Spur-0.195
utenant-0.185
bon-0.174
Token.
Token ID13
Feature activation+8.56e-02

Pos logit contributions
idential+0.259
 polyg+0.256
 Afgh+0.252
+0.249
methyl+0.242
Neg logit contributions
wit-0.451
horn-0.449
 Spur-0.444
utenant-0.424
bon-0.400
Token
Token ID198
Feature activation+2.13e-01

Pos logit contributions
idential+0.069
 polyg+0.069
 Afgh+0.068
+0.067
methyl+0.066
Neg logit contributions
wit-0.054
horn-0.053
 Spur-0.052
utenant-0.048
bon-0.045
Token
Token ID198
Feature activation+2.33e-01

Pos logit contributions
idential+0.181
 Afgh+0.181
 polyg+0.181
+0.178
methyl+0.174
Neg logit contributions
wit-0.125
horn-0.124
 Spur-0.120
utenant-0.111
bon-0.104
TokenBefore
Token ID8421
Feature activation+5.63e-01

Pos logit contributions
idential+0.170
 polyg+0.169
 Afgh+0.168
+0.166
methyl+0.162
Neg logit contributions
wit-0.164
horn-0.162
 Spur-0.159
utenant-0.150
bon-0.141
Token proceeding
Token ID18788
Feature activation-3.77e+00

Pos logit contributions
idential+0.410
 polyg+0.404
 Afgh+0.402
+0.401
methyl+0.390
Neg logit contributions
wit-0.396
horn-0.392
 Spur-0.388
utenant-0.362
bon-0.341
Token,
Token ID11
Feature activation-4.31e-01

Pos logit contributions
wit+2.496
horn+2.474
 Spur+2.466
utenant+2.262
bon+2.122
Neg logit contributions
idential-2.836
 Afgh-2.787
 polyg-2.770
-2.766
methyl-2.713
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
wit+0.315
horn+0.312
 Spur+0.308
utenant+0.291
bon+0.272
Neg logit contributions
idential-0.300
 polyg-0.298
 Afgh-0.297
-0.295
methyl-0.286
Token team
Token ID1074
Feature activation+1.59e+00

Pos logit contributions
wit+0.091
horn+0.091
 Spur+0.089
utenant+0.083
bon+0.079
Neg logit contributions
idential-0.088
 polyg-0.086
-0.086
 Afgh-0.086
methyl-0.083
Token carefully
Token ID7773
Feature activation+5.61e-01

Pos logit contributions
idential+1.148
 polyg+1.145
 Afgh+1.137
+1.126
methyl+1.098
Neg logit contributions
wit-1.127
horn-1.114
 Spur-1.097
utenant-1.034
bon-0.966
Token studied
Token ID9713
Feature activation-7.00e-01

Pos logit contributions
idential+0.411
 polyg+0.408
 Afgh+0.406
+0.403
methyl+0.392
Neg logit contributions
wit-0.392
horn-0.388
 Spur-0.382
utenant-0.360
bon-0.336
Token gathered
Token ID9272
Feature activation-2.12e+00

Pos logit contributions
wit+0.280
horn+0.277
 Spur+0.273
utenant+0.254
bon+0.237
Neg logit contributions
idential-0.340
 polyg-0.336
 Afgh-0.335
-0.333
methyl-0.325
Token for
Token ID329
Feature activation-3.86e-01

Pos logit contributions
horn+1.395
 Spur+1.388
wit+1.384
utenant+1.254
bon+1.186
Neg logit contributions
idential-1.631
 Afgh-1.595
 polyg-1.594
-1.591
methyl-1.554
Token dinner
Token ID8073
Feature activation-2.38e+00

Pos logit contributions
wit+0.261
horn+0.258
 Spur+0.256
utenant+0.237
bon+0.223
Neg logit contributions
idential-0.292
 polyg-0.288
 Afgh-0.287
-0.284
methyl-0.279
Token at
Token ID379
Feature activation-3.47e-01

Pos logit contributions
horn+1.637
wit+1.628
 Spur+1.610
utenant+1.487
 waiter+1.411
Neg logit contributions
idential-1.759
 polyg-1.718
 Afgh-1.705
-1.699
methyl-1.675
Token a
Token ID257
Feature activation-5.74e-01

Pos logit contributions
wit+0.253
horn+0.251
 Spur+0.250
utenant+0.233
bon+0.218
Neg logit contributions
idential-0.242
 polyg-0.241
 Afgh-0.239
-0.237
methyl-0.232
Token piano
Token ID19132
Feature activation-3.73e+00

Pos logit contributions
wit+0.368
horn+0.364
 Spur+0.363
utenant+0.334
bon+0.313
Neg logit contributions
idential-0.452
 polyg-0.446
 Afgh-0.444
-0.442
methyl-0.433
Token bar
Token ID2318
Feature activation-8.07e-01

Pos logit contributions
horn+2.536
wit+2.476
 Spur+2.468
utenant+2.261
 waiter+2.196
Neg logit contributions
idential-2.792
 Afgh-2.761
 polyg-2.735
-2.699
methyl-2.657
Token and
Token ID290
Feature activation-7.67e-01

Pos logit contributions
wit+0.567
horn+0.565
 Spur+0.556
utenant+0.520
bon+0.488
Neg logit contributions
idential-0.585
 polyg-0.582
 Afgh-0.581
-0.570
methyl-0.560
Token discussed
Token ID6693
Feature activation-4.41e-01

Pos logit contributions
wit+0.502
horn+0.498
 Spur+0.494
utenant+0.454
bon+0.426
Neg logit contributions
idential-0.596
 polyg-0.587
 Afgh-0.586
-0.583
methyl-0.570
Token the
Token ID262
Feature activation-2.23e-01

Pos logit contributions
wit+0.320
horn+0.317
 Spur+0.315
utenant+0.294
bon+0.276
Neg logit contributions
idential-0.310
 polyg-0.307
 Afgh-0.305
-0.304
methyl-0.297
Token visit
Token ID3187
Feature activation+6.73e-01

Pos logit contributions
wit+0.153
 Spur+0.152
horn+0.151
utenant+0.139
bon+0.132
Neg logit contributions
idential-0.165
-0.162
 polyg-0.162
 Afgh-0.162
methyl-0.158
Token eye
Token ID4151
Feature activation+1.72e+00

Pos logit contributions
idential+0.415
 polyg+0.411
 Afgh+0.409
+0.408
methyl+0.398
Neg logit contributions
wit-0.352
horn-0.347
 Spur-0.343
utenant-0.319
bon-0.299
Token up
Token ID510
Feature activation+7.92e-01

Pos logit contributions
idential+1.194
 polyg+1.190
 Afgh+1.181
+1.168
methyl+1.140
Neg logit contributions
wit-1.268
horn-1.253
 Spur-1.235
utenant-1.166
bon-1.092
Token like
Token ID588
Feature activation+6.08e-01

Pos logit contributions
idential+0.534
 polyg+0.531
 Afgh+0.527
+0.521
methyl+0.512
Neg logit contributions
wit-0.599
horn-0.595
 Spur-0.586
utenant-0.552
bon-0.520
Token a
Token ID257
Feature activation+4.80e-01

Pos logit contributions
idential+0.412
 polyg+0.405
+0.402
 Afgh+0.401
methyl+0.390
Neg logit contributions
wit-0.461
horn-0.457
 Spur-0.453
utenant-0.421
bon-0.399
Token marsh
Token ID22397
Feature activation-4.72e-01

Pos logit contributions
idential+0.361
 polyg+0.358
 Afgh+0.356
+0.355
methyl+0.345
Neg logit contributions
wit-0.326
horn-0.324
 Spur-0.318
utenant-0.296
bon-0.278
Tokenmallow
Token ID42725
Feature activation-3.72e+00

Pos logit contributions
wit+0.378
horn+0.378
 Spur+0.368
utenant+0.347
bon+0.331
Neg logit contributions
idential-0.300
 polyg-0.296
 Afgh-0.294
-0.291
methyl-0.282
Token.
Token ID13
Feature activation-2.16e-01

Pos logit contributions
horn+2.738
wit+2.733
 Spur+2.659
utenant+2.452
bon+2.381
Neg logit contributions
idential-2.582
 polyg-2.540
 Afgh-2.508
-2.497
methyl-2.464
Token It
Token ID632
Feature activation-5.98e-01

Pos logit contributions
wit+0.158
 Spur+0.156
horn+0.156
utenant+0.145
bon+0.136
Neg logit contributions
idential-0.153
 polyg-0.152
 Afgh-0.149
-0.149
methyl-0.146
Token was
Token ID373
Feature activation+7.95e-02

Pos logit contributions
wit+0.495
horn+0.491
 Spur+0.486
utenant+0.462
bon+0.435
Neg logit contributions
idential-0.361
 polyg-0.357
 Afgh-0.354
-0.350
methyl-0.340
Token also
Token ID635
Feature activation+1.05e+00

Pos logit contributions
idential+0.057
 polyg+0.057
 Afgh+0.056
+0.056
methyl+0.054
Neg logit contributions
wit-0.057
horn-0.056
 Spur-0.055
utenant-0.052
bon-0.049
Token that
Token ID326
Feature activation+6.77e-01

Pos logit contributions
 polyg+0.733
idential+0.733
 Afgh+0.727
+0.719
methyl+0.701
Neg logit contributions
wit-0.769
horn-0.760
 Spur-0.746
utenant-0.707
bon-0.661
TokenAudio
Token ID21206
Feature activation+7.22e-02

Pos logit contributions
wit+0.331
horn+0.327
 Spur+0.322
utenant+0.304
bon+0.285
Neg logit contributions
idential-0.315
 polyg-0.315
 Afgh-0.312
-0.308
methyl-0.301
Token evidence
Token ID2370
Feature activation-1.01e+00

Pos logit contributions
idential+0.050
 polyg+0.050
 Afgh+0.050
+0.049
methyl+0.048
Neg logit contributions
wit-0.053
horn-0.052
 Spur-0.051
utenant-0.048
bon-0.046
Token
Token ID198
Feature activation-7.80e-01

Pos logit contributions
wit+0.706
horn+0.696
 Spur+0.683
utenant+0.646
bon+0.604
Neg logit contributions
idential-0.739
 polyg-0.731
 Afgh-0.728
-0.724
methyl-0.710
Token
Token ID198
Feature activation-6.88e-01

Pos logit contributions
wit+0.447
horn+0.442
 Spur+0.426
utenant+0.390
bon+0.368
Neg logit contributions
idential-0.677
 Afgh-0.674
 polyg-0.673
 tremend-0.665
-0.660
TokenThe
Token ID464
Feature activation+2.18e-01

Pos logit contributions
wit+0.492
horn+0.487
 Spur+0.474
utenant+0.448
bon+0.424
Neg logit contributions
idential-0.493
 polyg-0.493
 Afgh-0.490
-0.480
methyl-0.470
Token FIR
Token ID23703
Feature activation-3.69e+00

Pos logit contributions
idential+0.161
 polyg+0.161
 Afgh+0.160
+0.158
methyl+0.155
Neg logit contributions
wit-0.151
horn-0.149
 Spur-0.147
utenant-0.138
bon-0.129
Token further
Token ID2252
Feature activation-1.68e+00

Pos logit contributions
wit+2.545
horn+2.482
 Spur+2.439
utenant+2.337
bon+2.189
Neg logit contributions
-2.668
idential-2.660
 Afgh-2.646
 polyg-2.640
methyl-2.582
Token quotes
Token ID13386
Feature activation-1.03e+00

Pos logit contributions
wit+1.040
horn+1.030
 Spur+1.005
utenant+0.949
bon+0.886
Neg logit contributions
idential-1.341
-1.335
 Afgh-1.331
 polyg-1.328
methyl-1.303
Token the
Token ID262
Feature activation+1.37e-02

Pos logit contributions
wit+0.752
horn+0.744
 Spur+0.734
utenant+0.695
bon+0.649
Neg logit contributions
idential-0.711
 polyg-0.706
-0.702
 Afgh-0.702
methyl-0.688
Token contents
Token ID10154
Feature activation-5.34e-01

Pos logit contributions
idential+0.010
 polyg+0.010
 Afgh+0.010
+0.010
methyl+0.010
Neg logit contributions
wit-0.009
horn-0.009
 Spur-0.009
utenant-0.009
bon-0.008
Token of
Token ID286
Feature activation+3.89e-02

Pos logit contributions
wit+0.384
horn+0.378
 Spur+0.375
utenant+0.351
bon+0.329
Neg logit contributions
idential-0.381
 polyg-0.380
 Afgh-0.374
-0.373
methyl-0.362
Token delight
Token ID10974
Feature activation-2.30e-01

Pos logit contributions
wit+0.192
horn+0.190
 Spur+0.188
utenant+0.172
bon+0.161
Neg logit contributions
idential-0.265
 polyg-0.262
-0.261
 Afgh-0.260
methyl-0.255
Tokenafter
Token ID8499
Feature activation+1.30e-01

Pos logit contributions
wit+0.157
horn+0.155
 Spur+0.153
utenant+0.143
bon+0.134
Neg logit contributions
idential-0.172
 polyg-0.171
 Afgh-0.170
-0.168
methyl-0.165
Token that
Token ID326
Feature activation-2.83e-01

Pos logit contributions
idential+0.091
 polyg+0.090
 Afgh+0.090
+0.089
methyl+0.087
Neg logit contributions
wit-0.095
horn-0.094
 Spur-0.093
utenant-0.087
bon-0.082
Token deal
Token ID1730
Feature activation+1.31e+00

Pos logit contributions
wit+0.217
horn+0.215
 Spur+0.212
utenant+0.200
bon+0.189
Neg logit contributions
idential-0.187
 polyg-0.186
 Afgh-0.185
-0.183
methyl-0.178
Token was
Token ID373
Feature activation-5.64e-01

Pos logit contributions
idential+0.897
 polyg+0.896
 Afgh+0.889
+0.879
methyl+0.858
Neg logit contributions
wit-0.979
horn-0.969
 Spur-0.953
utenant-0.900
bon-0.845
Token clin
Token ID5327
Feature activation-3.66e+00

Pos logit contributions
wit+0.324
horn+0.319
 Spur+0.312
utenant+0.290
bon+0.266
Neg logit contributions
idential-0.482
 polyg-0.480
 Afgh-0.478
-0.474
methyl-0.465
Tokenched
Token ID1740
Feature activation-6.25e-01

Pos logit contributions
wit+3.100
horn+3.085
 Spur+2.933
utenant+2.811
bon+2.763
Neg logit contributions
 Afgh-2.158
 polyg-2.157
-2.120
idential-2.106
 tremend-2.010
Token in
Token ID287
Feature activation-6.76e-01

Pos logit contributions
wit+0.453
horn+0.449
 Spur+0.436
utenant+0.414
bon+0.391
Neg logit contributions
 polyg-0.440
idential-0.439
 Afgh-0.438
-0.428
methyl-0.424
Token October
Token ID3267
Feature activation+3.44e-01

Pos logit contributions
wit+0.543
horn+0.535
 Spur+0.531
utenant+0.498
bon+0.474
Neg logit contributions
idential-0.426
 polyg-0.418
 Afgh-0.417
-0.414
methyl-0.405
Token last
Token ID938
Feature activation-6.80e-01

Pos logit contributions
idential+0.246
 polyg+0.246
 Afgh+0.243
+0.240
methyl+0.236
Neg logit contributions
wit-0.247
horn-0.244
 Spur-0.240
utenant-0.225
bon-0.211
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
wit+0.579
horn+0.572
 Spur+0.565
utenant+0.536
bon+0.509
Neg logit contributions
idential-0.394
 polyg-0.392
 Afgh-0.388
-0.382
methyl-0.373
Token to
Token ID284
Feature activation+2.06e-01

Pos logit contributions
wit+0.169
horn+0.168
 Spur+0.167
utenant+0.158
bon+0.149
Neg logit contributions
 polyg-0.131
idential-0.130
 Afgh-0.129
-0.128
methyl-0.124
Token sport
Token ID6332
Feature activation-1.32e+00

Pos logit contributions
idential+0.199
 polyg+0.198
 Afgh+0.197
+0.196
methyl+0.192
Neg logit contributions
wit-0.096
horn-0.094
 Spur-0.092
utenant-0.084
bon-0.075
Token a
Token ID257
Feature activation-2.71e-01

Pos logit contributions
wit+0.989
horn+0.978
 Spur+0.966
utenant+0.904
bon+0.858
Neg logit contributions
idential-0.902
 polyg-0.883
-0.883
 Afgh-0.879
methyl-0.855
Token rum
Token ID7440
Feature activation-2.39e+00

Pos logit contributions
wit+0.189
horn+0.187
 Spur+0.185
utenant+0.172
bon+0.162
Neg logit contributions
idential-0.199
-0.196
 Afgh-0.196
 polyg-0.196
methyl-0.190
Tokenpled
Token ID10137
Feature activation-7.33e-01

Pos logit contributions
wit+1.892
horn+1.873
 Spur+1.826
utenant+1.735
bon+1.670
Neg logit contributions
idential-1.525
-1.502
 polyg-1.501
 Afgh-1.499
CLUD-1.430
Token suit
Token ID6050
Feature activation-3.63e+00

Pos logit contributions
wit+0.499
horn+0.493
 Spur+0.486
utenant+0.455
bon+0.426
Neg logit contributions
idential-0.551
 polyg-0.546
 Afgh-0.542
-0.541
methyl-0.527
Token than
Token ID621
Feature activation-1.83e+00

Pos logit contributions
wit+2.838
horn+2.819
 Spur+2.747
utenant+2.586
bon+2.458
Neg logit contributions
idential-2.349
 polyg-2.315
 Afgh-2.309
-2.298
methyl-2.250
Token a
Token ID257
Feature activation-6.23e-01

Pos logit contributions
wit+1.367
horn+1.348
 Spur+1.340
utenant+1.259
 waiter+1.179
Neg logit contributions
idential-1.261
-1.235
 polyg-1.232
 Afgh-1.227
methyl-1.197
Token hood
Token ID14263
Feature activation-1.78e+00

Pos logit contributions
wit+0.433
horn+0.428
 Spur+0.423
utenant+0.395
bon+0.371
Neg logit contributions
idential-0.462
-0.453
 polyg-0.452
 Afgh-0.451
methyl-0.439
Tokenie
Token ID494
Feature activation-1.19e+00

Pos logit contributions
wit+1.153
horn+1.129
 Spur+1.103
utenant+1.032
bon+0.969
Neg logit contributions
idential-1.402
 polyg-1.389
-1.384
 Afgh-1.379
methyl-1.342
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
wit+0.898
horn+0.890
 Spur+0.874
utenant+0.826
bon+0.777
Neg logit contributions
idential-0.808
 polyg-0.799
 Afgh-0.794
-0.791
methyl-0.771
Token in
Token ID287
Feature activation-5.33e-01

Pos logit contributions
idential+0.170
 polyg+0.169
 Afgh+0.166
+0.162
methyl+0.160
Neg logit contributions
wit-0.185
horn-0.181
 Spur-0.179
utenant-0.169
lishes-0.160
Token a
Token ID257
Feature activation+2.18e-01

Pos logit contributions
wit+0.406
horn+0.401
 Spur+0.398
utenant+0.375
bon+0.353
Neg logit contributions
idential-0.356
 polyg-0.353
 Afgh-0.351
-0.349
methyl-0.339
Token radio
Token ID5243
Feature activation-1.10e+00

Pos logit contributions
idential+0.171
 polyg+0.170
 Afgh+0.169
+0.168
methyl+0.164
Neg logit contributions
wit-0.141
horn-0.139
 Spur-0.138
utenant-0.128
bon-0.119
Token debate
Token ID4384
Feature activation-1.63e+00

Pos logit contributions
wit+0.710
horn+0.701
 Spur+0.690
utenant+0.643
bon+0.600
Neg logit contributions
idential-0.863
 polyg-0.858
 Afgh-0.854
-0.849
methyl-0.829
Token with
Token ID351
Feature activation+2.06e-01

Pos logit contributions
wit+1.084
horn+1.078
 Spur+1.066
utenant+0.985
bon+0.926
Neg logit contributions
idential-1.236
-1.226
 polyg-1.224
 Afgh-1.223
methyl-1.194
Token incumbent
Token ID23526
Feature activation-3.60e+00

Pos logit contributions
idential+0.148
 polyg+0.147
 Afgh+0.146
+0.145
methyl+0.142
Neg logit contributions
wit-0.146
horn-0.144
 Spur-0.143
utenant-0.134
bon-0.125
Token U
Token ID471
Feature activation-1.23e-01

Pos logit contributions
wit+2.198
 Spur+2.180
horn+2.171
utenant+2.000
bon+1.863
Neg logit contributions
idential-2.933
-2.870
 polyg-2.848
 Afgh-2.823
methyl-2.805
Token.
Token ID13
Feature activation+5.30e-01

Pos logit contributions
wit+0.098
horn+0.097
 Spur+0.094
utenant+0.090
bon+0.086
Neg logit contributions
idential-0.080
 polyg-0.079
 Afgh-0.079
-0.078
methyl-0.075
TokenS
Token ID50
Feature activation+8.00e-01

Pos logit contributions
 polyg+0.433
idential+0.432
 Afgh+0.426
+0.420
methyl+0.413
Neg logit contributions
wit-0.333
horn-0.329
 Spur-0.321
utenant-0.297
bon-0.278
Token.
Token ID13
Feature activation-2.89e-01

Pos logit contributions
idential+0.516
 polyg+0.514
 Afgh+0.506
+0.506
methyl+0.489
Neg logit contributions
wit-0.636
horn-0.630
 Spur-0.620
utenant-0.586
bon-0.554
Token Sen
Token ID2311
Feature activation+3.38e-01

Pos logit contributions
wit+0.175
horn+0.172
 Spur+0.169
utenant+0.158
bon+0.145
Neg logit contributions
idential-0.238
 polyg-0.238
 Afgh-0.236
-0.234
methyl-0.229
Tokenator
Token ID1352
Feature activation-2.31e-01

Pos logit contributions
wit+0.761
horn+0.753
 Spur+0.744
utenant+0.709
bon+0.671
Neg logit contributions
idential-0.505
 polyg-0.504
 Afgh-0.499
-0.492
methyl-0.477
Token from
Token ID422
Feature activation-1.46e+00

Pos logit contributions
wit+0.159
horn+0.157
 Spur+0.155
utenant+0.146
bon+0.136
Neg logit contributions
idential-0.172
 polyg-0.169
-0.168
 Afgh-0.168
methyl-0.164
Token Syria
Token ID4392
Feature activation-4.03e-02

Pos logit contributions
wit+1.067
horn+1.057
 Spur+1.050
utenant+0.983
bon+0.923
Neg logit contributions
idential-1.021
 polyg-1.004
-1.001
 Afgh-0.983
methyl-0.972
Token carrying
Token ID6872
Feature activation-1.65e+00

Pos logit contributions
wit+0.027
horn+0.027
 Spur+0.026
utenant+0.025
bon+0.023
Neg logit contributions
idential-0.031
 polyg-0.030
-0.030
 Afgh-0.030
methyl-0.029
Token bin
Token ID9874
Feature activation-1.14e+00

Pos logit contributions
wit+1.214
horn+1.211
 Spur+1.204
utenant+1.116
bon+1.056
Neg logit contributions
idential-1.124
-1.108
 polyg-1.089
 Afgh-1.074
methyl-1.062
Tokenocular
Token ID37320
Feature activation-3.58e+00

Pos logit contributions
horn+1.028
wit+1.020
 Spur+0.997
utenant+0.951
bon+0.911
Neg logit contributions
idential-0.614
-0.598
 polyg-0.598
 Afgh-0.585
methyl-0.567
Tokens
Token ID82
Feature activation-2.69e-02

Pos logit contributions
horn+2.527
wit+2.523
 Spur+2.475
utenant+2.263
bon+2.199
Neg logit contributions
idential-2.582
-2.503
 Afgh-2.404
undown-2.404
 polyg-2.403
Token,
Token ID11
Feature activation-7.80e-01

Pos logit contributions
wit+0.018
horn+0.018
 Spur+0.018
utenant+0.017
bon+0.016
Neg logit contributions
idential-0.020
-0.020
 polyg-0.020
 Afgh-0.020
methyl-0.019
Token explosives
Token ID20732
Feature activation-1.39e+00

Pos logit contributions
wit+0.584
horn+0.575
 Spur+0.571
utenant+0.536
bon+0.505
Neg logit contributions
idential-0.532
-0.521
 polyg-0.516
 Afgh-0.512
methyl-0.504
Token,
Token ID11
Feature activation-9.71e-01

Pos logit contributions
wit+1.087
horn+1.077
 Spur+1.059
utenant+0.998
bon+0.945
Neg logit contributions
idential-0.894
 polyg-0.880
 Afgh-0.878
-0.869
methyl-0.845
Token and
Token ID290
Feature activation-4.15e-01

Pos logit contributions
wit+0.732
horn+0.724
 Spur+0.719
utenant+0.669
bon+0.636
Neg logit contributions
idential-0.657
-0.644
 polyg-0.634
 Afgh-0.629
methyl-0.619
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
wit+0.044
horn+0.043
 Spur+0.043
utenant+0.041
bon+0.038
Neg logit contributions
idential-0.035
 polyg-0.035
 Afgh-0.035
-0.034
methyl-0.033
Token
Token ID198
Feature activation-5.16e-01

Pos logit contributions
idential+0.079
 polyg+0.079
 Afgh+0.078
+0.078
methyl+0.076
Neg logit contributions
wit-0.065
horn-0.064
 Spur-0.063
utenant-0.058
bon-0.055
Token
Token ID198
Feature activation-4.68e-01

Pos logit contributions
wit+0.296
horn+0.293
 Spur+0.282
utenant+0.259
bon+0.245
Neg logit contributions
idential-0.448
 Afgh-0.448
 polyg-0.448
 tremend-0.440
-0.438
TokenIn
Token ID818
Feature activation+2.87e-01

Pos logit contributions
wit+0.338
horn+0.334
 Spur+0.325
utenant+0.305
bon+0.292
Neg logit contributions
 polyg-0.337
idential-0.336
 Afgh-0.334
-0.324
methyl-0.317
Token some
Token ID617
Feature activation-2.37e-01

Pos logit contributions
idential+0.198
 polyg+0.196
 Afgh+0.195
+0.193
methyl+0.188
Neg logit contributions
wit-0.215
horn-0.212
 Spur-0.209
utenant-0.197
bon-0.186
Token respects
Token ID19410
Feature activation-3.56e+00

Pos logit contributions
wit+0.167
horn+0.165
 Spur+0.163
utenant+0.153
bon+0.143
Neg logit contributions
idential-0.171
 polyg-0.169
 Afgh-0.169
-0.168
methyl-0.164
Token,
Token ID11
Feature activation-3.09e-01

Pos logit contributions
wit+2.488
horn+2.450
 Spur+2.449
utenant+2.285
bon+2.144
Neg logit contributions
idential-2.538
 Afgh-2.518
-2.509
 polyg-2.491
methyl-2.466
Token it
Token ID340
Feature activation-3.38e-01

Pos logit contributions
wit+0.210
horn+0.206
 Spur+0.205
utenant+0.191
bon+0.179
Neg logit contributions
idential-0.231
 polyg-0.229
 Afgh-0.228
-0.228
methyl-0.222
Token is
Token ID318
Feature activation+2.36e-02

Pos logit contributions
wit+0.238
horn+0.235
 Spur+0.232
utenant+0.218
bon+0.205
Neg logit contributions
idential-0.244
 polyg-0.241
 Afgh-0.241
-0.239
methyl-0.235
Token tech
Token ID7261
Feature activation+2.09e+00

Pos logit contributions
idential+0.017
 polyg+0.016
 Afgh+0.016
+0.016
methyl+0.016
Neg logit contributions
wit-0.017
horn-0.017
 Spur-0.017
utenant-0.016
bon-0.015
Token rather
Token ID2138
Feature activation+3.81e-01

Pos logit contributions
idential+1.445
 polyg+1.443
 Afgh+1.427
+1.416
methyl+1.373
Neg logit contributions
wit-1.543
horn-1.519
 Spur-1.498
utenant-1.421
bon-1.321
Token1
Token ID16
Feature activation-8.69e-02

Pos logit contributions
wit+0.147
horn+0.145
 Spur+0.143
utenant+0.134
bon+0.126
Neg logit contributions
idential-0.155
 polyg-0.155
 Afgh-0.154
-0.152
methyl-0.148
Token world
Token ID995
Feature activation-1.62e+00

Pos logit contributions
wit+0.059
horn+0.058
 Spur+0.057
utenant+0.054
bon+0.050
Neg logit contributions
idential-0.065
 polyg-0.065
 Afgh-0.065
-0.064
methyl-0.063
Token was
Token ID373
Feature activation-1.16e+00

Pos logit contributions
wit+1.081
horn+1.067
 Spur+1.049
utenant+0.983
bon+0.917
Neg logit contributions
idential-1.230
 polyg-1.227
 Afgh-1.218
-1.208
methyl-1.179
Token a
Token ID257
Feature activation-2.22e-01

Pos logit contributions
wit+0.807
horn+0.798
 Spur+0.787
utenant+0.735
bon+0.687
Neg logit contributions
idential-0.851
-0.837
 polyg-0.835
 Afgh-0.833
methyl-0.809
Token bro
Token ID1379
Feature activation-1.13e+00

Pos logit contributions
wit+0.156
horn+0.154
 Spur+0.153
utenant+0.142
bon+0.134
Neg logit contributions
idential-0.161
 Afgh-0.160
 polyg-0.159
-0.159
methyl-0.154
Tokenthel
Token ID37274
Feature activation-3.54e+00

Pos logit contributions
wit+0.692
horn+0.687
 Spur+0.676
utenant+0.625
bon+0.583
Neg logit contributions
idential-0.921
 polyg-0.920
 Afgh-0.916
-0.907
methyl-0.888
Token,
Token ID11
Feature activation-3.47e-01

Pos logit contributions
wit+2.537
horn+2.529
 Spur+2.463
utenant+2.306
bon+2.197
Neg logit contributions
idential-2.479
 Afgh-2.462
 polyg-2.445
-2.423
methyl-2.392
Token one
Token ID530
Feature activation-7.80e-01

Pos logit contributions
wit+0.268
horn+0.265
 Spur+0.262
utenant+0.247
bon+0.233
Neg logit contributions
idential-0.228
 polyg-0.226
 Afgh-0.225
-0.224
methyl-0.217
Token would
Token ID561
Feature activation-5.80e-01

Pos logit contributions
wit+0.589
horn+0.583
 Spur+0.575
utenant+0.541
bon+0.509
Neg logit contributions
idential-0.527
 polyg-0.521
 Afgh-0.518
-0.517
methyl-0.503
Token explain
Token ID4727
Feature activation+1.14e+00

Pos logit contributions
wit+0.304
horn+0.298
 Spur+0.292
utenant+0.270
bon+0.244
Neg logit contributions
idential-0.527
 polyg-0.524
 Afgh-0.523
-0.519
methyl-0.509
Token it
Token ID340
Feature activation-4.95e-01

Pos logit contributions
 polyg+0.772
idential+0.769
 Afgh+0.765
+0.754
methyl+0.735
Neg logit contributions
wit-0.857
horn-0.845
 Spur-0.832
utenant-0.791
bon-0.741
Token like
Token ID588
Feature activation+1.52e-02

Pos logit contributions
wit+0.853
horn+0.832
 Spur+0.830
utenant+0.767
bon+0.718
Neg logit contributions
idential-1.073
 Afgh-1.068
-1.060
 polyg-1.049
methyl-1.038
Token this
Token ID428
Feature activation+2.57e-01

Pos logit contributions
idential+0.011
 Afgh+0.011
 polyg+0.011
+0.011
methyl+0.011
Neg logit contributions
wit-0.011
horn-0.010
 Spur-0.010
utenant-0.010
bon-0.009
Token:
Token ID25
Feature activation-6.41e-01

Pos logit contributions
idential+0.174
 Afgh+0.173
+0.171
 polyg+0.170
methyl+0.167
Neg logit contributions
wit-0.193
horn-0.190
 Spur-0.189
utenant-0.177
bon-0.167
Token
Token ID198
Feature activation-8.89e-01

Pos logit contributions
wit+0.419
horn+0.411
 Spur+0.409
utenant+0.380
bon+0.354
Neg logit contributions
idential-0.497
 Afgh-0.491
 polyg-0.490
-0.485
methyl-0.479
Token
Token ID198
Feature activation-7.69e-01

Pos logit contributions
wit+0.505
horn+0.498
 Spur+0.479
utenant+0.438
bon+0.417
Neg logit contributions
idential-0.778
 Afgh-0.778
 polyg-0.775
 tremend-0.770
-0.758
Token-->
Token ID46904
Feature activation+3.07e+00

Pos logit contributions
wit+0.540
horn+0.531
 Spur+0.515
utenant+0.484
bon+0.464
Neg logit contributions
 polyg-0.569
idential-0.568
 Afgh-0.566
-0.549
methyl-0.536
Token src
Token ID12351
Feature activation+5.37e-01

Pos logit contributions
 polyg+2.204
idential+2.201
 Afgh+2.184
+2.164
methyl+2.105
Neg logit contributions
wit-2.172
horn-2.146
 Spur-2.112
utenant-1.992
bon-1.859
Token/
Token ID14
Feature activation-6.29e-01

Pos logit contributions
idential+0.451
 polyg+0.450
 Afgh+0.446
+0.443
methyl+0.433
Neg logit contributions
wit-0.318
horn-0.312
 Spur-0.307
utenant-0.286
bon-0.263
Tokenmain
Token ID12417
Feature activation-1.06e+00

Pos logit contributions
wit+0.475
horn+0.468
 Spur+0.458
utenant+0.435
bon+0.411
Neg logit contributions
idential-0.431
 polyg-0.427
 Afgh-0.425
-0.418
methyl-0.407
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
wit+0.803
horn+0.794
 Spur+0.783
utenant+0.741
bon+0.694
Neg logit contributions
idential-0.712
 polyg-0.712
 Afgh-0.705
-0.696
methyl-0.678
Tokenrs
Token ID3808
Feature activation-3.57e-01

Pos logit contributions
wit+0.087
horn+0.086
 Spur+0.083
utenant+0.080
bon+0.076
Neg logit contributions
 polyg-0.061
 Afgh-0.060
idential-0.060
-0.059
methyl-0.056
Token Michael
Token ID3899
Feature activation-1.82e-01

Pos logit contributions
wit+0.310
horn+0.306
 Spur+0.304
utenant+0.284
bon+0.269
Neg logit contributions
idential-0.294
 polyg-0.290
-0.289
 Afgh-0.288
methyl-0.280
Token From
Token ID3574
Feature activation-9.24e-02

Pos logit contributions
wit+0.132
horn+0.131
 Spur+0.130
utenant+0.121
bon+0.114
Neg logit contributions
idential-0.128
 polyg-0.127
 Afgh-0.126
-0.126
methyl-0.122
Tokenan
Token ID272
Feature activation-1.08e-01

Pos logit contributions
wit+0.074
horn+0.073
 Spur+0.071
utenant+0.067
bon+0.064
Neg logit contributions
 polyg-0.059
idential-0.059
 Afgh-0.058
-0.058
methyl-0.055
Token to
Token ID284
Feature activation-2.77e-01

Pos logit contributions
wit+0.076
horn+0.075
 Spur+0.074
utenant+0.069
bon+0.065
Neg logit contributions
idential-0.079
 polyg-0.078
 Afgh-0.078
-0.077
methyl-0.075
Token John
Token ID1757
Feature activation-2.60e-01

Pos logit contributions
wit+0.202
horn+0.198
 Spur+0.198
utenant+0.184
bon+0.174
Neg logit contributions
idential-0.194
 polyg-0.192
-0.191
 Afgh-0.190
methyl-0.186
Token Podesta
Token ID27375
Feature activation+2.66e+00

Pos logit contributions
wit+0.207
horn+0.205
 Spur+0.203
utenant+0.191
bon+0.181
Neg logit contributions
idential-0.166
 polyg-0.165
 Afgh-0.162
-0.162
methyl-0.157
Token in
Token ID287
Feature activation+4.02e-02

Pos logit contributions
idential+1.865
 polyg+1.862
 Afgh+1.846
+1.826
methyl+1.781
Neg logit contributions
wit-1.943
horn-1.919
 Spur-1.892
utenant-1.786
bon-1.671
Token 2008
Token ID3648
Feature activation-4.61e-01

Pos logit contributions
idential+0.030
 polyg+0.030
+0.030
 Afgh+0.029
methyl+0.029
Neg logit contributions
wit-0.027
horn-0.027
 Spur-0.027
utenant-0.025
bon-0.023
Token
Token ID851
Feature activation+4.26e-01

Pos logit contributions
wit+0.332
horn+0.328
 Spur+0.325
utenant+0.306
bon+0.288
Neg logit contributions
idential-0.325
-0.320
 polyg-0.320
 Afgh-0.320
methyl-0.311
Token a
Token ID257
Feature activation+7.17e-01

Pos logit contributions
idential+0.295
 polyg+0.294
 Afgh+0.291
+0.290
methyl+0.283
Neg logit contributions
wit-0.313
horn-0.309
 Spur-0.305
utenant-0.288
bon-0.271
Token document
Token ID3188
Feature activation+1.49e+00

Pos logit contributions
idential+0.504
 Afgh+0.498
 polyg+0.497
+0.494
methyl+0.481
Neg logit contributions
wit-0.523
horn-0.515
 Spur-0.509
utenant-0.477
bon-0.451
Token
Token ID198
Feature activation+1.22e+00

Pos logit contributions
idential+1.026
 polyg+1.023
 Afgh+1.018
+1.005
methyl+0.985
Neg logit contributions
wit-0.756
horn-0.746
 Spur-0.731
utenant-0.679
bon-0.630
Token14
Token ID1415
Feature activation+1.45e+00

Pos logit contributions
idential+0.867
 polyg+0.866
 Afgh+0.858
+0.841
methyl+0.825
Neg logit contributions
wit-0.886
horn-0.874
 Spur-0.863
utenant-0.812
bon-0.762
Token Recommend
Token ID30361
Feature activation+3.71e+00

Pos logit contributions
 polyg+0.940
idential+0.940
 Afgh+0.933
+0.923
methyl+0.897
Neg logit contributions
wit-1.127
horn-1.114
 Spur-1.098
utenant-1.042
bon-0.979
Token
Token ID198
Feature activation+1.49e+00

Pos logit contributions
idential+3.011
 polyg+3.006
 Afgh+2.984
+2.958
methyl+2.894
Neg logit contributions
wit-2.290
horn-2.259
 Spur-2.220
utenant-2.072
bon-1.913
Token
Token ID198
Feature activation+1.43e+00

Pos logit contributions
idential+1.215
 polyg+1.212
 Afgh+1.205
+1.193
methyl+1.167
Neg logit contributions
wit-0.917
horn-0.905
 Spur-0.888
utenant-0.828
bon-0.766
TokenRecommend
Token ID41248
Feature activation+4.21e+00

Pos logit contributions
 polyg+0.797
 Afgh+0.796
idential+0.795
+0.766
methyl+0.741
Neg logit contributions
wit-1.266
horn-1.241
 Spur-1.229
utenant-1.163
bon-1.123
Token Share
Token ID8734
Feature activation+4.66e+00

Pos logit contributions
 polyg+2.794
idential+2.789
 Afgh+2.752
+2.732
methyl+2.671
Neg logit contributions
wit-3.195
horn-3.122
 Spur-3.098
utenant-2.959
bon-2.745
Token this
Token ID428
Feature activation+1.38e+00

Pos logit contributions
 polyg+2.991
 Afgh+2.979
idential+2.917
+2.880
methyl+2.795
Neg logit contributions
wit-3.606
horn-3.546
 Spur-3.523
utenant-3.304
lishes-3.147
Token comment
Token ID2912
Feature activation+5.23e-01

Pos logit contributions
idential+1.312
 Afgh+1.307
+1.298
 polyg+1.285
methyl+1.272
Neg logit contributions
wit-0.678
horn-0.673
 Spur-0.664
utenant-0.595
 waiter-0.547
Token on
Token ID319
Feature activation+5.61e-01

Pos logit contributions
 Afgh+0.405
idential+0.403
 polyg+0.401
+0.398
methyl+0.392
Neg logit contributions
wit-0.343
horn-0.342
 Spur-0.339
utenant-0.314
bon-0.295
Token Facebook
Token ID3203
Feature activation-7.49e-01

Pos logit contributions
idential+0.462
 polyg+0.456
 Afgh+0.456
+0.453
methyl+0.442
Neg logit contributions
wit-0.339
horn-0.336
 Spur-0.333
utenant-0.303
bon-0.286
Token the
Token ID262
Feature activation+4.40e-01

Pos logit contributions
idential+0.729
 polyg+0.727
 Afgh+0.721
+0.714
methyl+0.696
Neg logit contributions
wit-0.792
horn-0.782
 Spur-0.771
utenant-0.728
bon-0.684
Token years
Token ID812
Feature activation+4.59e-01

Pos logit contributions
idential+0.300
 polyg+0.297
 Afgh+0.296
+0.292
methyl+0.288
Neg logit contributions
wit-0.329
horn-0.325
 Spur-0.323
utenant-0.301
bon-0.284
Token.
Token ID13
Feature activation+5.68e-01

Pos logit contributions
idential+0.300
 polyg+0.299
 Afgh+0.298
+0.294
methyl+0.287
Neg logit contributions
wit-0.357
horn-0.354
 Spur-0.348
utenant-0.328
bon-0.309
Token
Token ID198
Feature activation-1.13e-01

Pos logit contributions
idential+0.405
 polyg+0.404
 Afgh+0.398
+0.395
methyl+0.387
Neg logit contributions
wit-0.408
horn-0.403
 Spur-0.399
utenant-0.373
bon-0.352
Token
Token ID198
Feature activation-9.64e-02

Pos logit contributions
wit+0.066
horn+0.065
 Spur+0.064
utenant+0.059
bon+0.055
Neg logit contributions
idential-0.096
 polyg-0.096
 Afgh-0.096
-0.094
methyl-0.092
TokenShare
Token ID11649
Feature activation+2.79e+00

Pos logit contributions
wit+0.071
horn+0.070
 Spur+0.069
utenant+0.065
bon+0.061
Neg logit contributions
 polyg-0.067
idential-0.067
 Afgh-0.067
-0.066
methyl-0.064
Token this
Token ID428
Feature activation+8.08e-01

Pos logit contributions
 polyg+1.963
idential+1.963
 Afgh+1.938
+1.922
methyl+1.868
Neg logit contributions
wit-2.014
horn-1.986
 Spur-1.956
utenant-1.847
bon-1.723
Token:
Token ID25
Feature activation+2.50e-01

Pos logit contributions
idential+0.451
 polyg+0.450
 Afgh+0.446
+0.441
methyl+0.427
Neg logit contributions
wit-0.703
horn-0.696
 Spur-0.689
utenant-0.655
bon-0.621
Token Facebook
Token ID3203
Feature activation-1.11e+00

Pos logit contributions
idential+0.196
 polyg+0.195
 Afgh+0.194
+0.192
methyl+0.188
Neg logit contributions
wit-0.162
horn-0.160
 Spur-0.158
utenant-0.147
bon-0.136
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
wit+0.612
horn+0.607
 Spur+0.603
utenant+0.542
bon+0.501
Neg logit contributions
 polyg-0.974
idential-0.972
 Afgh-0.968
 tremend-0.958
-0.952
Token
Token ID198
Feature activation-6.96e-02

Pos logit contributions
wit+0.075
horn+0.075
 Spur+0.073
utenant+0.067
bon+0.062
Neg logit contributions
idential-0.112
 polyg-0.112
 Afgh-0.111
-0.109
 tremend-0.108
Token 15
Token ID1315
Feature activation+1.35e+00

Pos logit contributions
idential+0.587
 polyg+0.583
 Afgh+0.575
+0.570
methyl+0.553
Neg logit contributions
wit-0.812
horn-0.807
 Spur-0.798
utenant-0.747
bon-0.714
Token,
Token ID11
Feature activation+1.54e+00

Pos logit contributions
idential+0.866
 polyg+0.865
 Afgh+0.863
+0.842
methyl+0.820
Neg logit contributions
wit-1.073
horn-1.065
 Spur-1.045
utenant-0.989
bon-0.938
Token 2010
Token ID3050
Feature activation+1.04e+00

Pos logit contributions
idential+1.088
 polyg+1.047
 Afgh+1.041
+1.023
methyl+1.008
Neg logit contributions
wit-1.129
horn-1.095
 Spur-1.092
utenant-1.066
lishes-0.989
Token
Token ID198
Feature activation+2.62e+00

Pos logit contributions
idential+0.870
 polyg+0.868
 Afgh+0.863
+0.852
methyl+0.834
Neg logit contributions
wit-0.629
horn-0.621
 Spur-0.608
utenant-0.562
bon-0.525
Token
Token ID198
Feature activation+2.34e+00

Pos logit contributions
idential+2.089
 polyg+2.087
 Afgh+2.068
+2.054
methyl+2.009
Neg logit contributions
wit-1.648
horn-1.624
 Spur-1.601
utenant-1.502
bon-1.380
TokenSubject
Token ID19776
Feature activation+3.04e+00

Pos logit contributions
idential+1.829
 polyg+1.828
 Afgh+1.816
+1.791
methyl+1.753
Neg logit contributions
wit-1.518
horn-1.500
 Spur-1.470
utenant-1.376
bon-1.283
Token:
Token ID25
Feature activation+9.39e-01

Pos logit contributions
idential+1.525
 polyg+1.522
 Afgh+1.505
+1.481
methyl+1.430
Neg logit contributions
wit-2.819
horn-2.793
 Spur-2.761
utenant-2.639
bon-2.510
Token Que
Token ID4670
Feature activation-8.75e-01

Pos logit contributions
idential+0.654
 polyg+0.650
 Afgh+0.644
+0.639
methyl+0.623
Neg logit contributions
wit-0.689
horn-0.684
 Spur-0.674
utenant-0.633
bon-0.596
Tokener
Token ID263
Feature activation+6.36e-01

Pos logit contributions
wit+0.585
horn+0.578
 Spur+0.570
utenant+0.535
bon+0.502
Neg logit contributions
 polyg-0.665
 Afgh-0.663
idential-0.662
-0.656
methyl-0.639
Token magnet
Token ID19972
Feature activation+1.30e+00

Pos logit contributions
idential+0.441
 polyg+0.439
 Afgh+0.435
+0.433
methyl+0.421
Neg logit contributions
wit-0.468
horn-0.465
 Spur-0.457
utenant-0.429
bon-0.406
Token?
Token ID30
Feature activation+1.51e+00

Pos logit contributions
idential+0.889
 polyg+0.886
 Afgh+0.880
+0.869
methyl+0.848
Neg logit contributions
wit-0.970
horn-0.959
 Spur-0.946
utenant-0.891
bon-0.838
Token
Token ID251
Feature activation-4.55e-01

Pos logit contributions
idential+0.144
 polyg+0.144
 Afgh+0.143
+0.142
methyl+0.138
Neg logit contributions
wit-0.171
horn-0.169
 Spur-0.167
utenant-0.158
bon-0.149
Token
Token ID198
Feature activation-5.94e-02

Pos logit contributions
wit+0.320
horn+0.316
 Spur+0.312
utenant+0.291
bon+0.275
Neg logit contributions
idential-0.332
 polyg-0.331
 Afgh-0.326
-0.322
methyl-0.319
Token
Token ID198
Feature activation-6.32e-02

Pos logit contributions
wit+0.034
horn+0.034
 Spur+0.033
utenant+0.030
bon+0.028
Neg logit contributions
idential-0.051
 polyg-0.051
 Afgh-0.051
 tremend-0.050
-0.050
TokenPrime
Token ID26405
Feature activation+9.06e-01

Pos logit contributions
wit+0.046
horn+0.045
 Spur+0.044
utenant+0.042
bon+0.040
Neg logit contributions
idential-0.045
 polyg-0.045
 Afgh-0.044
-0.043
methyl-0.043
Token Minister
Token ID4139
Feature activation+4.96e-01

Pos logit contributions
 polyg+0.688
idential+0.684
 Afgh+0.678
+0.673
methyl+0.654
Neg logit contributions
wit-0.611
horn-0.593
 Spur-0.592
utenant-0.553
lishes-0.514
Token Trudeau
Token ID17524
Feature activation+1.12e+00

Pos logit contributions
idential+0.357
 polyg+0.356
 Afgh+0.354
+0.350
methyl+0.342
Neg logit contributions
wit-0.352
horn-0.348
 Spur-0.343
utenant-0.323
bon-0.302
Token might
Token ID1244
Feature activation+1.14e+00

Pos logit contributions
idential+0.828
 polyg+0.822
 Afgh+0.819
+0.810
methyl+0.796
Neg logit contributions
wit-0.769
horn-0.763
 Spur-0.750
utenant-0.702
bon-0.657
Token agree
Token ID4236
Feature activation-2.78e-01

Pos logit contributions
 polyg+0.870
idential+0.869
 Afgh+0.860
+0.853
methyl+0.832
Neg logit contributions
wit-0.760
horn-0.750
 Spur-0.739
utenant-0.693
bon-0.644
Token with
Token ID351
Feature activation+9.91e-02

Pos logit contributions
wit+0.206
horn+0.202
 Spur+0.200
utenant+0.188
bon+0.176
Neg logit contributions
idential-0.192
 Afgh-0.190
 polyg-0.190
-0.187
methyl-0.185
Token you
Token ID345
Feature activation+1.28e-01

Pos logit contributions
idential+0.070
 polyg+0.069
 Afgh+0.069
+0.068
methyl+0.067
Neg logit contributions
wit-0.072
horn-0.071
 Spur-0.071
utenant-0.066
bon-0.062
Token
Token ID851
Feature activation-6.13e-01

Pos logit contributions
idential+0.086
 polyg+0.085
 Afgh+0.085
+0.084
methyl+0.083
Neg logit contributions
wit-0.097
horn-0.096
 Spur-0.095
utenant-0.090
bon-0.084
Token characters
Token ID3435
Feature activation-2.74e-01

Pos logit contributions
wit+0.420
horn+0.416
 Spur+0.413
utenant+0.381
bon+0.362
Neg logit contributions
idential-0.372
 polyg-0.367
-0.366
 Afgh-0.364
methyl-0.359
Token from
Token ID422
Feature activation-6.18e-01

Pos logit contributions
wit+0.195
horn+0.192
 Spur+0.190
utenant+0.177
bon+0.166
Neg logit contributions
idential-0.199
 polyg-0.197
 Afgh-0.195
-0.194
methyl-0.191
Token mythology
Token ID25871
Feature activation-6.03e-01

Pos logit contributions
wit+0.440
 Spur+0.439
horn+0.438
utenant+0.400
bon+0.381
Neg logit contributions
idential-0.438
-0.434
 polyg-0.430
 Afgh-0.429
methyl-0.424
Token in
Token ID287
Feature activation-1.91e-01

Pos logit contributions
wit+0.468
horn+0.463
 Spur+0.457
utenant+0.430
bon+0.405
Neg logit contributions
idential-0.395
 polyg-0.391
 Afgh-0.389
-0.384
methyl-0.377
Token a
Token ID257
Feature activation+2.15e-01

Pos logit contributions
wit+0.143
horn+0.142
 Spur+0.139
utenant+0.129
bon+0.123
Neg logit contributions
idential-0.131
 polyg-0.129
-0.129
 Afgh-0.128
methyl-0.125
Token way
Token ID835
Feature activation+8.43e-01

Pos logit contributions
idential+0.139
 polyg+0.137
 Afgh+0.137
+0.136
methyl+0.133
Neg logit contributions
wit-0.169
horn-0.167
 Spur-0.166
utenant-0.154
bon-0.148
Token never
Token ID1239
Feature activation-1.46e+00

Pos logit contributions
idential+0.605
 polyg+0.598
 Afgh+0.597
+0.592
methyl+0.581
Neg logit contributions
wit-0.600
horn-0.594
 Spur-0.589
utenant-0.543
bon-0.515
Token before
Token ID878
Feature activation-2.03e-02

Pos logit contributions
wit+0.899
horn+0.894
 Spur+0.877
utenant+0.810
bon+0.758
Neg logit contributions
idential-1.194
 polyg-1.176
 Afgh-1.170
-1.167
methyl-1.141
Token imagined
Token ID15758
Feature activation-6.74e-01

Pos logit contributions
wit+0.011
horn+0.011
 Spur+0.011
utenant+0.010
bon+0.009
Neg logit contributions
idential-0.018
 polyg-0.018
 Afgh-0.018
-0.018
methyl-0.017
Token.
Token ID13
Feature activation+7.22e-02

Pos logit contributions
wit+0.501
horn+0.497
 Spur+0.488
utenant+0.455
bon+0.430
Neg logit contributions
idential-0.461
 polyg-0.459
 Afgh-0.457
-0.447
methyl-0.445
Token
Token ID447
Feature activation-2.54e-01

Pos logit contributions
idential+0.050
 polyg+0.050
 Afgh+0.049
+0.049
methyl+0.048
Neg logit contributions
wit-0.053
horn-0.053
 Spur-0.053
utenant-0.048
bon-0.046
Token 13
Token ID1511
Feature activation-6.34e-01

Pos logit contributions
wit+0.127
horn+0.126
 Spur+0.125
utenant+0.117
bon+0.111
Neg logit contributions
idential-0.104
-0.102
 polyg-0.101
 Afgh-0.100
methyl-0.099
Token.
Token ID13
Feature activation-6.75e-01

Pos logit contributions
wit+0.496
horn+0.491
 Spur+0.485
utenant+0.459
bon+0.431
Neg logit contributions
idential-0.410
 polyg-0.409
 Afgh-0.405
-0.400
methyl-0.390
Token3
Token ID18
Feature activation-2.23e-01

Pos logit contributions
wit+0.502
horn+0.496
 Spur+0.489
utenant+0.462
bon+0.433
Neg logit contributions
idential-0.463
 polyg-0.462
 Afgh-0.458
-0.453
methyl-0.442
Token%.
Token ID7225
Feature activation-1.07e+00

Pos logit contributions
wit+0.142
horn+0.140
 Spur+0.138
utenant+0.129
bon+0.119
Neg logit contributions
idential-0.177
 polyg-0.177
 Afgh-0.176
-0.174
methyl-0.170
Token But
Token ID887
Feature activation-8.10e-01

Pos logit contributions
wit+0.767
horn+0.763
 Spur+0.762
utenant+0.697
bon+0.663
Neg logit contributions
idential-0.764
 polyg-0.760
-0.749
 Afgh-0.749
methyl-0.737
Token many
Token ID867
Feature activation+1.23e+00

Pos logit contributions
wit+0.590
horn+0.585
 Spur+0.585
utenant+0.538
bon+0.513
Neg logit contributions
idential-0.566
-0.558
 Afgh-0.556
 polyg-0.552
methyl-0.545
Token of
Token ID286
Feature activation+1.71e-01

Pos logit contributions
idential+0.897
 polyg+0.897
 Afgh+0.889
+0.879
methyl+0.858
Neg logit contributions
wit-0.865
horn-0.854
 Spur-0.841
utenant-0.793
bon-0.739
Token the
Token ID262
Feature activation-1.30e-01

Pos logit contributions
idential+0.110
 polyg+0.110
 Afgh+0.109
+0.108
methyl+0.105
Neg logit contributions
wit-0.135
horn-0.133
 Spur-0.132
utenant-0.125
bon-0.117
Token 8
Token ID807
Feature activation-7.94e-01

Pos logit contributions
wit+0.093
horn+0.092
 Spur+0.091
utenant+0.084
bon+0.080
Neg logit contributions
idential-0.094
 Afgh-0.092
-0.091
 polyg-0.091
methyl-0.090
Token%
Token ID4
Feature activation-4.10e-01

Pos logit contributions
wit+0.584
horn+0.578
 Spur+0.568
utenant+0.535
bon+0.504
Neg logit contributions
idential-0.552
 polyg-0.546
 Afgh-0.544
-0.541
methyl-0.523
Token calling
Token ID4585
Feature activation-2.64e-01

Pos logit contributions
wit+0.277
horn+0.274
 Spur+0.270
utenant+0.252
bon+0.236
Neg logit contributions
idential-0.310
 polyg-0.307
 Afgh-0.306
-0.303
methyl-0.297
Token,
Token ID11
Feature activation+3.10e-01

Pos logit contributions
wit+0.040
horn+0.040
 Spur+0.040
utenant+0.037
bon+0.035
Neg logit contributions
idential-0.041
 Afgh-0.040
 polyg-0.040
-0.040
methyl-0.039
Token including
Token ID1390
Feature activation+8.60e-01

Pos logit contributions
idential+0.204
 polyg+0.199
 Afgh+0.198
+0.198
methyl+0.193
Neg logit contributions
wit-0.242
horn-0.239
 Spur-0.237
utenant-0.222
bon-0.210
Token an
Token ID281
Feature activation-4.46e-01

Pos logit contributions
idential+0.593
 polyg+0.588
 Afgh+0.584
+0.580
methyl+0.565
Neg logit contributions
wit-0.639
horn-0.630
 Spur-0.624
utenant-0.587
bon-0.552
Token image
Token ID2939
Feature activation-9.72e-01

Pos logit contributions
wit+0.293
horn+0.288
 Spur+0.285
utenant+0.265
bon+0.247
Neg logit contributions
idential-0.346
 polyg-0.341
-0.341
 Afgh-0.338
methyl-0.332
Token falsely
Token ID24566
Feature activation-1.46e-01

Pos logit contributions
wit+0.653
horn+0.645
 Spur+0.635
utenant+0.590
bon+0.555
Neg logit contributions
idential-0.744
 polyg-0.731
 Afgh-0.728
-0.722
methyl-0.708
Token suggesting
Token ID9524
Feature activation+1.13e+00

Pos logit contributions
wit+0.089
horn+0.088
 Spur+0.086
utenant+0.080
bon+0.075
Neg logit contributions
idential-0.121
 polyg-0.120
 Afgh-0.119
-0.119
methyl-0.116
Token Kurt
Token ID20642
Feature activation+5.47e-01

Pos logit contributions
idential+0.784
 polyg+0.779
 Afgh+0.773
+0.768
methyl+0.748
Neg logit contributions
wit-0.828
horn-0.819
 Spur-0.809
utenant-0.762
bon-0.715
Token Cob
Token ID14828
Feature activation+6.44e-01

Pos logit contributions
 polyg+0.368
idential+0.367
+0.366
 Afgh+0.364
methyl+0.353
Neg logit contributions
wit-0.418
horn-0.410
 Spur-0.408
utenant-0.382
bon-0.359
Tokenain
Token ID391
Feature activation+2.56e+00

Pos logit contributions
 Afgh+0.518
 polyg+0.515
idential+0.515
+0.511
CLUD+0.493
Neg logit contributions
wit-0.409
horn-0.406
 Spur-0.391
utenant-0.364
bon-0.354
Token had
Token ID550
Feature activation-5.51e-02

Pos logit contributions
idential+1.709
 polyg+1.696
 Afgh+1.682
+1.670
methyl+1.623
Neg logit contributions
wit-1.956
horn-1.945
 Spur-1.912
utenant-1.809
bon-1.704
Token predicted
Token ID11001
Feature activation-4.32e-01

Pos logit contributions
wit+0.037
horn+0.036
 Spur+0.036
utenant+0.033
bon+0.031
Neg logit contributions
idential-0.042
-0.042
 polyg-0.041
 Afgh-0.041
methyl-0.040
Token."
Token ID526
Feature activation-1.07e+00

Pos logit contributions
wit+1.380
horn+1.366
 Spur+1.316
utenant+1.265
bon+1.186
Neg logit contributions
idential-1.244
 polyg-1.242
 Afgh-1.238
-1.225
methyl-1.189
Token
Token ID198
Feature activation-8.99e-01

Pos logit contributions
wit+0.698
horn+0.688
 Spur+0.673
utenant+0.639
bon+0.592
Neg logit contributions
idential-0.834
 polyg-0.832
 Afgh-0.827
-0.824
methyl-0.799
Token
Token ID198
Feature activation-8.73e-01

Pos logit contributions
wit+0.517
horn+0.509
 Spur+0.494
utenant+0.450
bon+0.426
Neg logit contributions
idential-0.782
 polyg-0.780
 Afgh-0.780
 tremend-0.769
-0.761
Token"
Token ID1
Feature activation-3.20e-02

Pos logit contributions
wit+0.584
horn+0.577
 Spur+0.565
utenant+0.528
bon+0.495
Neg logit contributions
idential-0.670
 polyg-0.669
 Afgh-0.665
-0.650
methyl-0.639
TokenSte
Token ID7447
Feature activation-2.67e+00

Pos logit contributions
wit+0.023
horn+0.023
 Spur+0.022
utenant+0.021
bon+0.020
Neg logit contributions
idential-0.023
 polyg-0.023
 Afgh-0.023
-0.022
methyl-0.022
Tokenlla
Token ID8466
Feature activation+7.00e-01

Pos logit contributions
horn+2.114
wit+2.113
 Spur+2.012
utenant+1.938
bon+1.879
Neg logit contributions
 Afgh-1.753
 polyg-1.749
idential-1.703
-1.694
 tremend-1.683
Token!"
Token ID2474
Feature activation-6.56e-01

Pos logit contributions
idential+0.473
 polyg+0.472
 Afgh+0.468
+0.463
methyl+0.451
Neg logit contributions
wit-0.527
horn-0.521
 Spur-0.514
utenant-0.486
bon-0.456
Token
Token ID198
Feature activation-6.26e-01

Pos logit contributions
wit+0.432
horn+0.426
 Spur+0.416
utenant+0.394
bon+0.368
Neg logit contributions
idential-0.504
 polyg-0.502
 Afgh-0.498
-0.496
methyl-0.481
Token
Token ID198
Feature activation-5.89e-01

Pos logit contributions
wit+0.361
horn+0.355
 Spur+0.345
utenant+0.315
bon+0.298
Neg logit contributions
idential-0.542
 Afgh-0.541
 polyg-0.540
 tremend-0.531
-0.528
TokenWhen
Token ID2215
Feature activation-6.93e-05

Pos logit contributions
wit+0.397
horn+0.392
 Spur+0.384
utenant+0.360
bon+0.337
Neg logit contributions
idential-0.447
 polyg-0.447
 Afgh-0.444
-0.436
methyl-0.427
Token she
Token ID673
Feature activation-5.31e-01

Pos logit contributions
wit+0.000
horn+0.000
 Spur+0.000
utenant+0.000
bon+0.000
Neg logit contributions
idential-0.000
 polyg-0.000
 Afgh-0.000
-0.000
methyl-0.000
Token card
Token ID2657
Feature activation-7.04e-01

Pos logit contributions
wit+0.604
horn+0.597
 Spur+0.590
utenant+0.549
bon+0.512
Neg logit contributions
idential-0.710
 polyg-0.702
 Afgh-0.697
-0.696
methyl-0.679
Token games
Token ID1830
Feature activation+2.49e-01

Pos logit contributions
wit+0.456
horn+0.452
 Spur+0.442
utenant+0.414
bon+0.387
Neg logit contributions
idential-0.551
 polyg-0.548
 Afgh-0.547
-0.540
methyl-0.530
Token,
Token ID11
Feature activation-5.39e-01

Pos logit contributions
idential+0.187
 polyg+0.186
 Afgh+0.185
+0.183
methyl+0.179
Neg logit contributions
wit-0.169
horn-0.167
 Spur-0.165
utenant-0.154
bon-0.144
Token the
Token ID262
Feature activation-3.04e-01

Pos logit contributions
wit+0.392
horn+0.387
 Spur+0.385
utenant+0.361
bon+0.337
Neg logit contributions
idential-0.378
 polyg-0.373
 Afgh-0.371
-0.370
methyl-0.360
Token break
Token ID2270
Feature activation+2.07e-01

Pos logit contributions
wit+0.210
horn+0.207
 Spur+0.205
utenant+0.191
bon+0.179
Neg logit contributions
idential-0.226
 polyg-0.223
 Afgh-0.221
-0.221
methyl-0.215
Tokenf
Token ID69
Feature activation-4.13e-01

Pos logit contributions
idential+0.155
 polyg+0.153
 Afgh+0.153
+0.152
methyl+0.149
Neg logit contributions
wit-0.142
horn-0.140
 Spur-0.137
utenant-0.129
bon-0.122
Tokenasts
Token ID5773
Feature activation-1.52e+00

Pos logit contributions
wit+0.366
horn+0.361
 Spur+0.357
utenant+0.340
bon+0.323
Neg logit contributions
idential-0.225
 polyg-0.224
 Afgh-0.222
-0.219
methyl-0.212
Token,
Token ID11
Feature activation-7.09e-01

Pos logit contributions
wit+1.162
horn+1.152
 Spur+1.141
utenant+1.074
bon+1.010
Neg logit contributions
idential-1.002
 polyg-0.993
 Afgh-0.993
-0.976
methyl-0.960
Token the
Token ID262
Feature activation-2.87e-01

Pos logit contributions
wit+0.520
horn+0.514
 Spur+0.508
utenant+0.479
bon+0.448
Neg logit contributions
idential-0.492
 polyg-0.490
 Afgh-0.486
-0.481
methyl-0.469
Token saying
Token ID2282
Feature activation+1.45e-01

Pos logit contributions
wit+0.199
horn+0.196
 Spur+0.194
utenant+0.181
bon+0.170
Neg logit contributions
idential-0.212
 polyg-0.210
 Afgh-0.208
-0.207
methyl-0.203
Token
Token ID564
Feature activation+6.31e-02

Pos logit contributions
idential+0.101
 polyg+0.101
 Afgh+0.100
+0.099
methyl+0.097
Neg logit contributions
wit-0.106
horn-0.105
 Spur-0.104
utenant-0.098
bon-0.092
Token deal
Token ID1730
Feature activation+7.66e-01

Pos logit contributions
wit+0.580
horn+0.573
 Spur+0.560
utenant+0.509
bon+0.464
Neg logit contributions
idential-1.116
 polyg-1.115
 Afgh-1.111
-1.099
methyl-1.081
Token with
Token ID351
Feature activation-5.11e-01

Pos logit contributions
idential+0.523
 polyg+0.520
 Afgh+0.517
+0.512
methyl+0.499
Neg logit contributions
wit-0.574
horn-0.566
 Spur-0.560
utenant-0.527
bon-0.496
Token the
Token ID262
Feature activation-4.23e-01

Pos logit contributions
wit+0.372
horn+0.369
 Spur+0.368
utenant+0.343
bon+0.323
Neg logit contributions
idential-0.357
 polyg-0.355
 Afgh-0.352
-0.350
methyl-0.342
Token Demons
Token ID38539
Feature activation+3.16e-01

Pos logit contributions
wit+0.324
horn+0.321
 Spur+0.320
utenant+0.298
bon+0.284
Neg logit contributions
idential-0.281
 polyg-0.277
 Afgh-0.275
-0.274
methyl-0.270
Token is
Token ID318
Feature activation-4.09e-01

Pos logit contributions
idential+0.220
 polyg+0.219
 Afgh+0.217
+0.215
methyl+0.210
Neg logit contributions
wit-0.232
horn-0.229
 Spur-0.226
utenant-0.213
bon-0.200
Token reportedly
Token ID7478
Feature activation-1.79e+00

Pos logit contributions
wit+0.279
horn+0.275
 Spur+0.272
utenant+0.255
bon+0.239
Neg logit contributions
idential-0.305
 polyg-0.303
 Afgh-0.302
-0.300
methyl-0.293
Token worth
Token ID2861
Feature activation+8.07e-01

Pos logit contributions
wit+1.158
horn+1.135
 Spur+1.133
utenant+1.053
bon+0.989
Neg logit contributions
idential-1.397
 Afgh-1.382
 polyg-1.380
-1.376
methyl-1.345
Token $
Token ID720
Feature activation-6.35e-01

Pos logit contributions
idential+0.569
 polyg+0.567
 Afgh+0.563
+0.558
methyl+0.545
Neg logit contributions
wit-0.584
horn-0.578
 Spur-0.571
utenant-0.538
bon-0.504
Token750
Token ID15426
Feature activation-9.91e-01

Pos logit contributions
wit+0.436
horn+0.433
 Spur+0.420
utenant+0.391
bon+0.375
Neg logit contributions
 polyg-0.481
 Afgh-0.479
idential-0.476
-0.461
methyl-0.453
Token,
Token ID11
Feature activation-4.06e-01

Pos logit contributions
wit+0.777
horn+0.769
 Spur+0.759
utenant+0.720
bon+0.681
Neg logit contributions
idential-0.637
 polyg-0.635
 Afgh-0.629
-0.622
methyl-0.602
Token000
Token ID830
Feature activation-8.80e-01

Pos logit contributions
horn+0.282
wit+0.279
 Spur+0.272
utenant+0.256
bon+0.242
Neg logit contributions
 Afgh-0.302
 polyg-0.301
idential-0.297
-0.294
 proble-0.288
Token activity
Token ID3842
Feature activation-6.12e-01

Pos logit contributions
idential+0.314
 polyg+0.307
+0.304
 Afgh+0.301
methyl+0.295
Neg logit contributions
wit-0.355
horn-0.352
 Spur-0.346
utenant-0.325
bon-0.313
Token more
Token ID517
Feature activation+1.07e-01

Pos logit contributions
wit+0.447
horn+0.444
 Spur+0.440
utenant+0.411
bon+0.393
Neg logit contributions
idential-0.424
-0.418
 Afgh-0.417
 polyg-0.414
methyl-0.405
Token accessible
Token ID9857
Feature activation+1.69e+00

Pos logit contributions
idential+0.074
+0.073
 polyg+0.072
 Afgh+0.072
methyl+0.071
Neg logit contributions
wit-0.079
horn-0.079
 Spur-0.078
utenant-0.073
bon-0.069
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
idential+1.163
 polyg+1.158
 Afgh+1.152
+1.141
methyl+1.113
Neg logit contributions
wit-1.255
horn-1.243
 Spur-1.229
utenant-1.153
bon-1.086
Token
Token ID198
Feature activation+2.57e-01

Pos logit contributions
idential+0.199
 polyg+0.199
 Afgh+0.197
+0.196
methyl+0.191
Neg logit contributions
wit-0.158
horn-0.156
 Spur-0.153
utenant-0.144
bon-0.133
Token
Token ID198
Feature activation+3.03e-01

Pos logit contributions
idential+0.219
 polyg+0.219
 Afgh+0.218
+0.214
methyl+0.210
Neg logit contributions
wit-0.152
horn-0.150
 Spur-0.146
utenant-0.135
bon-0.126
TokenWork
Token ID12468
Feature activation+1.02e+00

Pos logit contributions
idential+0.216
 polyg+0.216
 Afgh+0.214
+0.212
methyl+0.207
Neg logit contributions
wit-0.217
horn-0.215
 Spur-0.211
utenant-0.199
bon-0.186
Token it
Token ID340
Feature activation+3.60e-01

Pos logit contributions
idential+0.668
 polyg+0.666
 Afgh+0.664
+0.659
methyl+0.635
Neg logit contributions
wit-0.791
horn-0.785
 Spur-0.767
utenant-0.727
bon-0.689
Token Y
Token ID575
Feature activation-7.96e-02

Pos logit contributions
idential+0.244
 polyg+0.243
 Afgh+0.241
+0.241
methyl+0.234
Neg logit contributions
wit-0.272
horn-0.269
 Spur-0.263
utenant-0.248
bon-0.235
TokenOW
Token ID3913
Feature activation+9.77e-01

Pos logit contributions
wit+0.061
horn+0.060
 Spur+0.059
utenant+0.056
bon+0.053
Neg logit contributions
idential-0.053
 polyg-0.053
 Afgh-0.053
-0.052
methyl-0.050
Token is
Token ID318
Feature activation+4.70e-01

Pos logit contributions
idential+0.666
 polyg+0.663
 Afgh+0.659
+0.652
methyl+0.635
Neg logit contributions
wit-0.732
horn-0.723
 Spur-0.714
utenant-0.670
bon-0.634
Token it
Token ID340
Feature activation-7.42e-03

Pos logit contributions
wit+0.254
horn+0.251
 Spur+0.249
utenant+0.233
bon+0.219
Neg logit contributions
idential-0.232
 polyg-0.230
 Afgh-0.229
-0.228
methyl-0.223
Token
Token ID447
Feature activation+3.62e-01

Pos logit contributions
wit+0.005
horn+0.005
 Spur+0.005
utenant+0.005
bon+0.005
Neg logit contributions
idential-0.005
 polyg-0.005
 Afgh-0.005
-0.005
methyl-0.005
Token
Token ID247
Feature activation+4.42e-01

Pos logit contributions
 polyg+0.235
idential+0.233
 Afgh+0.229
+0.224
methyl+0.220
Neg logit contributions
wit-0.285
horn-0.282
 Spur-0.275
utenant-0.264
bon-0.248
Tokens
Token ID82
Feature activation+4.13e-01

Pos logit contributions
 polyg+0.295
 Afgh+0.294
idential+0.292
+0.282
methyl+0.276
Neg logit contributions
horn-0.341
wit-0.341
 Spur-0.332
utenant-0.313
bon-0.297
Token obvious
Token ID3489
Feature activation+2.66e-01

Pos logit contributions
idential+0.289
 polyg+0.286
 Afgh+0.284
+0.283
methyl+0.276
Neg logit contributions
wit-0.302
horn-0.299
 Spur-0.296
utenant-0.277
bon-0.261
Token the
Token ID262
Feature activation+3.67e-01

Pos logit contributions
idential+0.186
 polyg+0.185
 Afgh+0.183
+0.182
methyl+0.179
Neg logit contributions
wit-0.193
horn-0.191
 Spur-0.190
utenant-0.177
bon-0.166
Token homeless
Token ID10463
Feature activation+1.56e+00

Pos logit contributions
idential+0.246
 polyg+0.243
+0.242
 Afgh+0.241
methyl+0.236
Neg logit contributions
wit-0.277
horn-0.274
 Spur-0.273
utenant-0.255
bon-0.241
Token have
Token ID423
Feature activation+4.31e-01

Pos logit contributions
idential+1.161
 polyg+1.157
 Afgh+1.149
+1.139
methyl+1.113
Neg logit contributions
wit-1.065
horn-1.051
 Spur-1.036
utenant-0.971
bon-0.906
Token dug
Token ID18735
Feature activation+7.51e-01

Pos logit contributions
idential+0.332
 polyg+0.329
 Afgh+0.327
+0.325
methyl+0.318
Neg logit contributions
wit-0.284
horn-0.280
 Spur-0.276
utenant-0.257
bon-0.241
Token in
Token ID287
Feature activation+1.66e-01

Pos logit contributions
idential+0.557
 polyg+0.549
 Afgh+0.546
+0.543
methyl+0.534
Neg logit contributions
wit-0.521
horn-0.515
 Spur-0.508
utenant-0.471
bon-0.445
Token.
Token ID13
Feature activation+9.22e-02

Pos logit contributions
idential+0.115
 polyg+0.113
 Afgh+0.113
+0.111
methyl+0.109
Neg logit contributions
wit-0.124
horn-0.123
 Spur-0.121
utenant-0.113
bon-0.107
Token,
Token ID11
Feature activation-2.82e-01

Pos logit contributions
 polyg+0.561
idential+0.558
 Afgh+0.556
+0.544
methyl+0.534
Neg logit contributions
wit-0.769
horn-0.756
 Spur-0.751
utenant-0.726
lishes-0.674
Token Merry
Token ID39001
Feature activation-1.69e+00

Pos logit contributions
wit+0.199
horn+0.197
 Spur+0.194
utenant+0.182
bon+0.170
Neg logit contributions
idential-0.205
 polyg-0.204
 Afgh-0.202
-0.202
methyl-0.196
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
horn+1.300
wit+1.297
 Spur+1.239
utenant+1.158
bon+1.117
Neg logit contributions
idential-1.169
 polyg-1.143
 Afgh-1.132
-1.121
methyl-1.088
Token P
Token ID350
Feature activation+3.19e-01

Pos logit contributions
wit+0.114
horn+0.112
 Spur+0.111
utenant+0.103
bon+0.097
Neg logit contributions
idential-0.116
 polyg-0.115
 Afgh-0.114
-0.114
methyl-0.111
Tokenipp
Token ID3974
Feature activation-1.03e+00

Pos logit contributions
idential+0.133
 polyg+0.133
 Afgh+0.131
+0.129
methyl+0.123
Neg logit contributions
wit-0.324
horn-0.321
 Spur-0.317
utenant-0.304
bon-0.291
Tokenin
Token ID259
Feature activation-1.90e-01

Pos logit contributions
wit+0.692
horn+0.683
 Spur+0.671
utenant+0.630
bon+0.585
Neg logit contributions
idential-0.788
 polyg-0.787
 Afgh-0.782
-0.775
methyl-0.756
Token,
Token ID11
Feature activation-4.28e-01

Pos logit contributions
wit+0.154
horn+0.152
 Spur+0.151
utenant+0.143
bon+0.135
Neg logit contributions
idential-0.117
 polyg-0.117
 Afgh-0.116
-0.114
methyl-0.111
Token Ar
Token ID943
Feature activation-8.96e-01

Pos logit contributions
wit+0.306
horn+0.302
 Spur+0.298
utenant+0.279
bon+0.262
Neg logit contributions
idential-0.308
 polyg-0.306
 Afgh-0.303
-0.302
methyl-0.294
Tokenag
Token ID363
Feature activation-5.38e-01

Pos logit contributions
wit+0.675
horn+0.667
 Spur+0.655
utenant+0.619
bon+0.584
Neg logit contributions
 polyg-0.608
idential-0.608
 Afgh-0.602
-0.598
methyl-0.580
Tokenorn
Token ID1211
Feature activation-1.27e-01

Pos logit contributions
wit+0.353
horn+0.349
 Spur+0.341
utenant+0.320
bon+0.300
Neg logit contributions
idential-0.419
 polyg-0.418
 Afgh-0.415
-0.411
methyl-0.401
Token,
Token ID11
Feature activation-5.23e-01

Pos logit contributions
wit+0.104
horn+0.102
 Spur+0.101
utenant+0.096
bon+0.091
Neg logit contributions
idential-0.078
 polyg-0.078
 Afgh-0.077
-0.076
methyl-0.074
Token demise
Token ID25403
Feature activation-1.91e-01

Pos logit contributions
wit+0.235
horn+0.231
 Spur+0.229
utenant+0.212
bon+0.198
Neg logit contributions
idential-0.284
 polyg-0.282
 Afgh-0.280
-0.280
methyl-0.273
Token of
Token ID286
Feature activation+2.66e-01

Pos logit contributions
wit+0.139
horn+0.138
 Spur+0.136
utenant+0.128
bon+0.120
Neg logit contributions
idential-0.134
 polyg-0.134
 Afgh-0.132
-0.131
methyl-0.127
Token the
Token ID262
Feature activation+1.65e-01

Pos logit contributions
idential+0.189
 polyg+0.187
 Afgh+0.186
+0.185
methyl+0.180
Neg logit contributions
wit-0.192
horn-0.188
 Spur-0.187
utenant-0.176
bon-0.165
Token wind
Token ID2344
Feature activation+1.42e-01

Pos logit contributions
idential+0.118
 polyg+0.117
 Afgh+0.116
+0.116
methyl+0.113
Neg logit contributions
wit-0.117
horn-0.115
 Spur-0.115
utenant-0.107
bon-0.101
Token power
Token ID1176
Feature activation-1.26e+00

Pos logit contributions
idential+0.120
 polyg+0.120
 Afgh+0.119
+0.118
methyl+0.116
Neg logit contributions
wit-0.083
horn-0.082
 Spur-0.080
utenant-0.074
bon-0.069
Token production
Token ID3227
Feature activation-2.12e+00

Pos logit contributions
wit+0.858
horn+0.846
 Spur+0.837
utenant+0.773
bon+0.734
Neg logit contributions
idential-0.948
 Afgh-0.935
 polyg-0.934
-0.925
methyl-0.911
Token tax
Token ID1687
Feature activation+3.50e-01

Pos logit contributions
wit+1.441
horn+1.428
 Spur+1.419
utenant+1.306
bon+1.246
Neg logit contributions
idential-1.586
 Afgh-1.563
 polyg-1.559
-1.545
methyl-1.523
Token credit
Token ID3884
Feature activation+1.08e+00

Pos logit contributions
idential+0.258
 polyg+0.258
 Afgh+0.256
+0.253
methyl+0.247
Neg logit contributions
wit-0.242
horn-0.239
 Spur-0.235
utenant-0.221
bon-0.206
Token),
Token ID828
Feature activation+2.91e-01

Pos logit contributions
 polyg+0.776
idential+0.775
 Afgh+0.767
+0.760
methyl+0.741
Neg logit contributions
wit-0.762
horn-0.753
 Spur-0.741
utenant-0.701
bon-0.651
Token and
Token ID290
Feature activation+2.93e-01

Pos logit contributions
idential+0.200
 polyg+0.198
 Afgh+0.198
+0.196
methyl+0.191
Neg logit contributions
wit-0.215
horn-0.212
 Spur-0.211
utenant-0.198
bon-0.186
Token compared
Token ID3688
Feature activation+4.20e-01

Pos logit contributions
idential+0.207
 polyg+0.205
 Afgh+0.205
+0.204
methyl+0.199
Neg logit contributions
wit-0.210
horn-0.208
 Spur-0.206
utenant-0.193
bon-0.182
Token for
Token ID329
Feature activation-6.93e-02

Pos logit contributions
idential+0.118
 polyg+0.118
 Afgh+0.117
+0.116
methyl+0.113
Neg logit contributions
wit-0.121
horn-0.119
 Spur-0.118
utenant-0.111
bon-0.104
Token have
Token ID423
Feature activation-4.30e-01

Pos logit contributions
wit+0.049
horn+0.049
 Spur+0.048
utenant+0.045
bon+0.042
Neg logit contributions
idential-0.050
 polyg-0.050
 Afgh-0.049
-0.049
methyl-0.048
Token further
Token ID2252
Feature activation-2.27e+00

Pos logit contributions
wit+0.298
horn+0.294
 Spur+0.289
utenant+0.273
bon+0.256
Neg logit contributions
idential-0.317
 polyg-0.316
 Afgh-0.314
-0.310
methyl-0.303
Token destabil
Token ID27397
Feature activation-2.99e-01

Pos logit contributions
wit+1.474
horn+1.460
 Spur+1.455
utenant+1.308
bon+1.261
Neg logit contributions
idential-1.744
-1.710
 polyg-1.706
 Afgh-1.703
methyl-1.667
Tokenized
Token ID1143
Feature activation+6.08e-01

Pos logit contributions
wit+0.230
horn+0.227
 Spur+0.224
utenant+0.213
bon+0.200
Neg logit contributions
idential-0.197
 polyg-0.196
 Afgh-0.195
-0.193
methyl-0.188
Token eastern
Token ID10183
Feature activation-2.36e+00

Pos logit contributions
 polyg+0.404
 Afgh+0.401
idential+0.396
+0.389
methyl+0.380
Neg logit contributions
wit-0.465
horn-0.463
 Spur-0.455
utenant-0.436
bon-0.404
Token Ukraine
Token ID7049
Feature activation+2.60e-01

Pos logit contributions
wit+1.803
horn+1.788
 Spur+1.761
utenant+1.654
bon+1.567
Neg logit contributions
idential-1.576
 polyg-1.558
 Afgh-1.545
-1.541
methyl-1.497
Token.
Token ID13
Feature activation+2.03e-02

Pos logit contributions
idential+0.158
 polyg+0.158
 Afgh+0.157
+0.155
methyl+0.150
Neg logit contributions
wit-0.213
horn-0.211
 Spur-0.208
utenant-0.198
bon-0.187
Token
Token ID198
Feature activation-2.33e-01

Pos logit contributions
idential+0.015
 Afgh+0.015
 polyg+0.015
+0.015
methyl+0.015
Neg logit contributions
wit-0.014
horn-0.014
 Spur-0.013
utenant-0.013
 waiter-0.012
Token
Token ID198
Feature activation-2.66e-01

Pos logit contributions
wit+0.137
horn+0.135
 Spur+0.131
utenant+0.121
bon+0.113
Neg logit contributions
idential-0.198
 polyg-0.198
 Afgh-0.197
-0.194
methyl-0.190
TokenWhile
Token ID3633
Feature activation+4.43e-01

Pos logit contributions
wit+0.197
horn+0.195
 Spur+0.192
utenant+0.182
bon+0.170
Neg logit contributions
idential-0.183
 polyg-0.182
 Afgh-0.181
-0.179
methyl-0.175
Token
Token ID198
Feature activation-9.38e-02

Pos logit contributions
wit+0.122
horn+0.121
 Spur+0.117
utenant+0.108
bon+0.101
Neg logit contributions
idential-0.180
 polyg-0.180
 Afgh-0.180
-0.176
 tremend-0.175
Token"
Token ID1
Feature activation+1.31e+00

Pos logit contributions
wit+0.065
horn+0.064
 Spur+0.063
utenant+0.059
bon+0.056
Neg logit contributions
idential-0.069
 polyg-0.069
 Afgh-0.069
-0.068
methyl-0.066
TokenWe
Token ID1135
Feature activation+5.79e-01

Pos logit contributions
idential+0.916
 polyg+0.914
 Afgh+0.907
+0.897
methyl+0.875
Neg logit contributions
wit-0.950
horn-0.938
 Spur-0.925
utenant-0.873
bon-0.817
Token don
Token ID836
Feature activation-1.22e+00

Pos logit contributions
idential+0.473
 polyg+0.471
 Afgh+0.469
+0.467
methyl+0.457
Neg logit contributions
wit-0.353
horn-0.347
 Spur-0.343
utenant-0.319
bon-0.296
Token't
Token ID470
Feature activation+5.59e-01

Pos logit contributions
wit+0.631
horn+0.622
 Spur+0.602
utenant+0.551
bon+0.517
Neg logit contributions
 tremend-1.122
 Afgh-1.121
idential-1.117
 polyg-1.117
 proble-1.092
Token ordinarily
Token ID43605
Feature activation-2.17e+00

Pos logit contributions
idential+0.464
 Afgh+0.461
 polyg+0.461
+0.458
methyl+0.448
Neg logit contributions
wit-0.336
horn-0.330
 Spur-0.325
utenant-0.302
bon-0.279
Token allow
Token ID1249
Feature activation+9.47e-01

Pos logit contributions
wit+1.316
 Spur+1.289
horn+1.283
utenant+1.182
bon+1.103
Neg logit contributions
 Afgh-1.756
-1.750
idential-1.746
methyl-1.723
CLUD-1.712
Token police
Token ID1644
Feature activation-1.88e-01

Pos logit contributions
idential+0.640
 polyg+0.631
+0.629
 Afgh+0.629
methyl+0.613
Neg logit contributions
wit-0.712
horn-0.703
 Spur-0.697
utenant-0.657
bon-0.617
Token officers
Token ID3790
Feature activation-1.10e+00

Pos logit contributions
wit+0.142
horn+0.140
 Spur+0.139
utenant+0.131
bon+0.123
Neg logit contributions
idential-0.127
 Afgh-0.126
 polyg-0.125
-0.124
methyl-0.121
Token to
Token ID284
Feature activation-5.15e-01

Pos logit contributions
wit+0.763
horn+0.752
 Spur+0.741
utenant+0.700
bon+0.650
Neg logit contributions
idential-0.803
 Afgh-0.796
 polyg-0.795
-0.785
methyl-0.769
Token detain
Token ID17017
Feature activation-3.20e-01

Pos logit contributions
wit+0.330
horn+0.322
 Spur+0.320
utenant+0.299
bon+0.276
Neg logit contributions
idential-0.407
 Afgh-0.405
-0.402
 polyg-0.401
methyl-0.394
TokenN
Token ID45
Feature activation-1.47e+00

Pos logit contributions
wit+0.496
horn+0.491
 Spur+0.478
utenant+0.447
bon+0.424
Neg logit contributions
 polyg-0.522
idential-0.522
 Afgh-0.517
-0.512
methyl-0.494
Token (
Token ID357
Feature activation-3.54e-01

Pos logit contributions
wit+1.090
horn+1.088
 Spur+1.063
utenant+0.997
bon+0.940
Neg logit contributions
 polyg-1.006
idential-1.005
 Afgh-1.004
-0.986
methyl-0.952
Token7
Token ID22
Feature activation-9.14e-01

Pos logit contributions
wit+0.252
horn+0.249
 Spur+0.245
utenant+0.230
bon+0.216
Neg logit contributions
idential-0.254
 polyg-0.254
 Afgh-0.252
-0.249
methyl-0.242
TokenR
Token ID49
Feature activation-1.18e+00

Pos logit contributions
wit+0.639
horn+0.632
 Spur+0.622
utenant+0.584
bon+0.546
Neg logit contributions
idential-0.670
 polyg-0.665
 Afgh-0.663
-0.654
methyl-0.638
Token0
Token ID15
Feature activation-7.16e-01

Pos logit contributions
wit+0.779
horn+0.771
 Spur+0.760
utenant+0.709
bon+0.661
Neg logit contributions
idential-0.905
 polyg-0.902
 Afgh-0.899
-0.884
methyl-0.866
TokenN
Token ID45
Feature activation-1.91e+00

Pos logit contributions
wit+0.456
horn+0.451
 Spur+0.442
utenant+0.412
bon+0.383
Neg logit contributions
idential-0.567
 polyg-0.565
 Afgh-0.562
-0.555
methyl-0.544
Token,
Token ID11
Feature activation-3.60e-01

Pos logit contributions
wit+1.238
horn+1.223
 Spur+1.204
utenant+1.111
bon+1.040
Neg logit contributions
idential-1.491
 polyg-1.478
 Afgh-1.477
-1.450
methyl-1.423
Token get
Token ID651
Feature activation-3.02e-01

Pos logit contributions
wit+0.256
horn+0.254
 Spur+0.251
utenant+0.234
bon+0.220
Neg logit contributions
idential-0.258
 polyg-0.256
 Afgh-0.254
-0.253
methyl-0.247
Token it
Token ID340
Feature activation-5.40e-01

Pos logit contributions
wit+0.215
horn+0.213
 Spur+0.209
utenant+0.196
bon+0.184
Neg logit contributions
idential-0.218
 Afgh-0.215
 polyg-0.215
-0.211
methyl-0.207
Token?)
Token ID10091
Feature activation+6.35e-01

Pos logit contributions
wit+0.304
horn+0.299
 Spur+0.294
utenant+0.272
bon+0.249
Neg logit contributions
idential-0.467
 polyg-0.466
 Afgh-0.463
-0.459
methyl-0.450
Token watch
Token ID2342
Feature activation+1.53e+00

Pos logit contributions
idential+0.445
 polyg+0.442
 Afgh+0.440
+0.436
methyl+0.424
Neg logit contributions
wit-0.465
horn-0.460
 Spur-0.452
utenant-0.426
bon-0.400
Token snaps
Token ID23429
Feature activation-1.92e-01

Pos logit contributions
idential+0.139
 polyg+0.139
 Afgh+0.137
+0.136
methyl+0.133
Neg logit contributions
wit-0.142
horn-0.141
 Spur-0.139
utenant-0.131
bon-0.123
Token it
Token ID340
Feature activation-2.96e-01

Pos logit contributions
wit+0.138
horn+0.136
 Spur+0.136
utenant+0.127
bon+0.119
Neg logit contributions
idential-0.137
 polyg-0.136
 Afgh-0.135
-0.134
methyl-0.131
Token and
Token ID290
Feature activation-1.14e-02

Pos logit contributions
wit+0.218
horn+0.216
 Spur+0.214
utenant+0.201
bon+0.189
Neg logit contributions
idential-0.205
 polyg-0.201
 Afgh-0.201
-0.200
methyl-0.196
Token takes
Token ID2753
Feature activation+1.42e+00

Pos logit contributions
wit+0.008
horn+0.008
 Spur+0.008
utenant+0.007
bon+0.007
Neg logit contributions
idential-0.008
 polyg-0.008
 Afgh-0.008
-0.008
methyl-0.008
Token a
Token ID257
Feature activation-1.16e-01

Pos logit contributions
idential+0.977
 polyg+0.972
 Afgh+0.965
+0.956
methyl+0.932
Neg logit contributions
wit-1.048
horn-1.037
 Spur-1.024
utenant-0.964
bon-0.905
Token step
Token ID2239
Feature activation-2.20e+00

Pos logit contributions
wit+0.077
horn+0.076
 Spur+0.076
utenant+0.070
bon+0.066
Neg logit contributions
idential-0.089
 Afgh-0.088
 polyg-0.087
-0.087
methyl-0.085
Token to
Token ID284
Feature activation-3.16e-01

Pos logit contributions
wit+1.458
horn+1.456
 Spur+1.424
utenant+1.322
bon+1.245
Neg logit contributions
idential-1.689
 polyg-1.664
 Afgh-1.662
-1.646
CLUD-1.609
Token the
Token ID262
Feature activation-5.04e-01

Pos logit contributions
wit+0.230
horn+0.227
 Spur+0.224
utenant+0.212
bon+0.198
Neg logit contributions
idential-0.222
 polyg-0.221
 Afgh-0.219
-0.217
methyl-0.212
Token play
Token ID711
Feature activation-6.33e-01

Pos logit contributions
wit+0.365
horn+0.361
 Spur+0.357
utenant+0.335
bon+0.314
Neg logit contributions
idential-0.355
 polyg-0.352
 Afgh-0.350
-0.348
methyl-0.339
Token side
Token ID1735
Feature activation+8.01e-01

Pos logit contributions
wit+0.489
horn+0.486
 Spur+0.477
utenant+0.451
bon+0.425
Neg logit contributions
idential-0.418
 polyg-0.416
 Afgh-0.412
-0.408
methyl-0.398
Token.
Token ID13
Feature activation-2.08e-01

Pos logit contributions
idential+0.531
 polyg+0.529
 Afgh+0.525
+0.519
methyl+0.506
Neg logit contributions
wit-0.615
horn-0.608
 Spur-0.600
utenant-0.567
bon-0.533