TOP ACTIVATIONS
MAX = 4.698

targeting and abuse . No wonder the Obama IRS has had
safe ! Shelby W add ell (@ s
Charlie Cameron and Harrison W igg moving elsewhere .
, and the only w isp of political activity in her
the findings . Un w illing to challenge the data openly
the Nexus 6 . No word on if there will be
a crust y old bl oke on a stool , ask
stemming from an out - of - comp etition test conducted
: struct Board { turn : Player , //
The MLB Network squ aw ked from the television , news
pub struct Guard { ... } pub fn pin
] States and territories A map of
will o ' the w isp of a grand constitution ,
of the lab ia str add ling the clitor is .
9 . Sw amin ar ayan A ks hard
mentioned . No word if the Str and Craft
probably have an out - of - spec lens . That
wrote Ari ka Ok rent , a lingu ist and
and Way man T isd ale Award Watch Lists .[ 105
period . It made me wonder how many cub s have

MIN ACTIVATIONS
MIN = -5.209

Serve hot ! <|endoftext|> Image copyright ESA Image caption Go ce
million years . <|endoftext|> Image copyright AFP The Bank
ported License . <|endoftext|> Image copyright AP Image caption Peace talks
. <|endoftext|> Image copyright publicity Image caption The Greeks
not trust him , keep away from him , he shouldn
. <|endoftext|> Image copyright Deadline Police have
Hide Caption 7 of 15 Photos : Carly Fiorina 's political
Hide Caption 4 of 15 Photos : Carly Fiorina 's political
20 , 2015 . Hide Caption 8 of 15 Photos :
Women in politics . Hide Caption 7 of 15 Photos :
unsupported on your device Media caption Nigel Farage : " Lord
Hide Caption 14 of 15 Photos : Carly Fiorina 's political
energy goals . <|endoftext|> Media playback is unsupported on your device
Hide Caption 11 of 15 Photos : Carly Fiorina 's political
Hide Caption 8 of 15 Photos : Carly Fiorina 's political
in , Iowa . Hide Caption 5 of 15 Photos :
Irvine , California . Hide Caption 9 of 15 Photos :
Hide Caption 9 of 15 Photos : Carly Fiorina 's political
Hide Caption 13 of 15 Photos : Carly Fiorina 's political
Hide Caption 6 of 15 Photos : Carly Fiorina 's political

INTERVAL 2.221 - 4.698
CONTAINS 0.272%

mechanism . When a server sends a notification to a client
growing number of r umb lings , and the prag mat
strange feeling for Andrew L add , who will walk into
intoler ant attitude had always eng endered a great deal
+ -------------------- --+ | ... | + -------------------- --+

INTERVAL -0.255 - 2.221
CONTAINS 65.000%

, on an outcome that 's unknown , where Britain 's
who was following her upstairs , got crushed under her weight
according to court documents . The Washington State Patrol
to explain . Ad Policy Mod er ator Elaine
P ence did well enough for the cable pundits

INTERVAL -2.732 - -0.255
CONTAINS 34.649%

. And after three months of racing around the
cannot and will not , and I encourage even my friends
- one heat sinks cool the memory and power modules ,
put together a map of places that should be stocking issues
More in this series H ansen :

INTERVAL -5.209 - -2.732
CONTAINS 0.079%

deliver " big news ". According to the magazine J olla
iking , on the other hand , is as simple as
Connor ( which at some point is going to come ,
size of my thumb ). Now throw it on the pan
girls . N om inate an exceptional Peace Corps
Token targeting
Token ID10822
Feature activation+2.74e-01

Pos logit contributions
Glass+0.447
 Ped+0.437
%:+0.397
 Forever+0.389
Ped+0.382
Neg logit contributions
acas-0.519
zag-0.474
henko-0.446
arial-0.436
ibaba-0.429
Token and
Token ID290
Feature activation+3.99e-01

Pos logit contributions
acas+0.250
zag+0.229
henko+0.216
arial+0.212
ibaba+0.209
Neg logit contributions
Glass-0.199
 Ped-0.195
%:-0.175
 Forever-0.173
Ped-0.169
Token abuse
Token ID5076
Feature activation-4.78e-01

Pos logit contributions
acas+0.339
zag+0.310
henko+0.289
arial+0.286
ibaba+0.278
Neg logit contributions
Glass-0.312
 Ped-0.306
%:-0.278
 Forever-0.273
Ped-0.270
Token.
Token ID13
Feature activation+4.72e-01

Pos logit contributions
Glass+0.341
 Ped+0.335
%:+0.300
 Forever+0.296
Ped+0.290
Neg logit contributions
acas-0.439
zag-0.405
henko-0.379
arial-0.373
ibaba-0.369
Token No
Token ID1400
Feature activation-2.11e-01

Pos logit contributions
acas+0.443
zag+0.408
henko+0.385
arial+0.379
ibaba+0.371
Neg logit contributions
Glass-0.328
 Ped-0.321
%:-0.289
 Forever-0.283
Ped-0.277
Token wonder
Token ID4240
Feature activation+4.70e+00

Pos logit contributions
Glass+0.163
 Ped+0.159
%:+0.144
 Forever+0.142
Ped+0.139
Neg logit contributions
acas-0.183
zag-0.167
henko-0.156
arial-0.154
ibaba-0.151
Token the
Token ID262
Feature activation-1.63e-01

Pos logit contributions
acas+4.200
zag+3.872
arial+3.605
henko+3.574
omore+3.454
Neg logit contributions
Glass-3.343
 Ped-3.209
%:-2.895
Ped-2.866
 Forever-2.860
Token Obama
Token ID2486
Feature activation-1.15e-01

Pos logit contributions
Glass+0.121
 Ped+0.119
%:+0.107
 Forever+0.105
Ped+0.103
Neg logit contributions
acas-0.146
zag-0.134
henko-0.126
arial-0.124
ibaba-0.121
Token IRS
Token ID14440
Feature activation+3.93e-01

Pos logit contributions
Glass+0.093
 Ped+0.091
%:+0.084
 Forever+0.082
Ped+0.081
Neg logit contributions
acas-0.095
zag-0.087
henko-0.081
arial-0.080
ibaba-0.078
Token has
Token ID468
Feature activation-1.33e-01

Pos logit contributions
acas+0.356
zag+0.327
henko+0.307
arial+0.302
ibaba+0.296
Neg logit contributions
Glass-0.287
 Ped-0.280
%:-0.254
 Forever-0.249
Ped-0.244
Token had
Token ID550
Feature activation+2.63e-01

Pos logit contributions
Glass+0.097
 Ped+0.095
%:+0.086
 Forever+0.084
Ped+0.083
Neg logit contributions
acas-0.120
zag-0.110
henko-0.104
arial-0.102
ibaba-0.100
Token safe
Token ID3338
Feature activation-1.13e-01

Pos logit contributions
Glass+0.761
 Ped+0.749
%:+0.672
 Forever+0.663
Ped+0.649
Neg logit contributions
acas-1.017
zag-0.934
henko-0.881
arial-0.868
ibaba-0.853
Token!
Token ID0
Feature activation-4.91e-02

Pos logit contributions
Glass+0.081
 Ped+0.080
%:+0.072
 Forever+0.071
Ped+0.069
Neg logit contributions
acas-0.103
zag-0.095
henko-0.089
arial-0.088
ibaba-0.086
Token
Token ID851
Feature activation+2.01e-02

Pos logit contributions
Glass+0.038
 Ped+0.037
%:+0.034
 Forever+0.033
Ped+0.032
Neg logit contributions
acas-0.043
zag-0.039
henko-0.037
arial-0.036
ibaba-0.035
Token Shelby
Token ID35053
Feature activation+2.14e+00

Pos logit contributions
acas+0.020
zag+0.018
henko+0.017
arial+0.017
ibaba+0.017
Neg logit contributions
Glass-0.013
 Ped-0.013
%:-0.011
 Forever-0.011
Ped-0.011
Token W
Token ID370
Feature activation+1.79e-02

Pos logit contributions
acas+2.110
zag+1.948
henko+1.849
arial+1.818
ibaba+1.780
Neg logit contributions
Glass-1.377
 Ped-1.333
%:-1.207
 Forever-1.163
Ped-1.145
Tokenadd
Token ID2860
Feature activation+4.51e+00

Pos logit contributions
acas+0.016
zag+0.014
henko+0.013
arial+0.013
ibaba+0.013
Neg logit contributions
Glass-0.014
 Ped-0.013
%:-0.012
 Forever-0.012
Ped-0.012
Tokenell
Token ID695
Feature activation+1.62e+00

Pos logit contributions
acas+3.982
zag+3.643
henko+3.416
arial+3.351
ibaba+3.299
Neg logit contributions
Glass-3.373
 Ped-3.283
%:-2.996
 Forever-2.916
Ped-2.896
Token
Token ID14519
Feature activation-1.21e+00

Pos logit contributions
acas+1.540
zag+1.419
henko+1.343
arial+1.321
ibaba+1.292
Neg logit contributions
Glass-1.097
 Ped-1.065
%:-0.965
 Forever-0.935
Ped-0.922
Token
Token ID234
Feature activation+9.14e-01

Pos logit contributions
Glass+1.174
 Ped+1.153
%:+1.067
 Forever+1.053
Ped+1.040
Neg logit contributions
acas-0.798
zag-0.710
henko-0.646
arial-0.638
ibaba-0.613
Token (@
Token ID4275
Feature activation-1.61e+00

Pos logit contributions
acas+0.826
zag+0.758
henko+0.713
arial+0.702
ibaba+0.686
Neg logit contributions
Glass-0.664
 Ped-0.649
%:-0.590
 Forever-0.575
Ped-0.565
Tokens
Token ID82
Feature activation-1.20e-01

Pos logit contributions
Glass+1.110
 Ped+1.063
%:+0.957
 Forever+0.941
Ped+0.935
Neg logit contributions
acas-1.517
zag-1.397
henko-1.326
arial-1.299
ibaba-1.285
Token Charlie
Token ID11526
Feature activation+5.45e-01

Pos logit contributions
acas+0.349
zag+0.322
henko+0.303
arial+0.298
ibaba+0.291
Neg logit contributions
Glass-0.268
 Ped-0.260
%:-0.236
 Forever-0.230
Ped-0.227
Token Cameron
Token ID10821
Feature activation-1.13e-02

Pos logit contributions
acas+0.545
zag+0.505
henko+0.478
arial+0.471
ibaba+0.462
Neg logit contributions
Glass-0.346
 Ped-0.339
%:-0.301
 Forever-0.294
Ped-0.288
Token and
Token ID290
Feature activation+1.52e-01

Pos logit contributions
Glass+0.009
 Ped+0.009
%:+0.008
 Forever+0.008
Ped+0.008
Neg logit contributions
acas-0.010
zag-0.009
henko-0.008
arial-0.008
ibaba-0.008
Token Harrison
Token ID17281
Feature activation-4.65e-01

Pos logit contributions
acas+0.151
zag+0.140
henko+0.132
arial+0.130
ibaba+0.128
Neg logit contributions
Glass-0.097
 Ped-0.095
%:-0.085
 Forever-0.083
Ped-0.081
Token W
Token ID370
Feature activation+6.10e-01

Pos logit contributions
Glass+0.294
 Ped+0.291
%:+0.256
 Forever+0.251
Ped+0.244
Neg logit contributions
acas-0.466
zag-0.430
henko-0.408
arial-0.402
ibaba-0.395
Tokenigg
Token ID6950
Feature activation+4.25e+00

Pos logit contributions
acas+0.470
zag+0.425
henko+0.397
arial+0.389
ibaba+0.379
Neg logit contributions
Glass-0.526
 Ped-0.516
%:-0.475
 Forever-0.467
Ped-0.458
Token moving
Token ID3867
Feature activation+7.15e-01

Pos logit contributions
acas+3.240
zag+2.902
henko+2.691
arial+2.647
ibaba+2.573
Neg logit contributions
Glass-3.703
 Ped-3.584
%:-3.337
 Forever-3.272
Ped-3.235
Token elsewhere
Token ID8057
Feature activation-4.14e-01

Pos logit contributions
acas+0.642
zag+0.589
henko+0.553
arial+0.544
ibaba+0.533
Neg logit contributions
Glass-0.527
 Ped-0.517
%:-0.467
 Forever-0.458
Ped-0.450
Token.
Token ID13
Feature activation+1.08e-01

Pos logit contributions
Glass+0.283
 Ped+0.281
%:+0.250
 Forever+0.247
Ped+0.240
Neg logit contributions
acas-0.392
zag-0.360
henko-0.339
arial-0.334
ibaba-0.330
Token
Token ID198
Feature activation+7.78e-01

Pos logit contributions
acas+0.106
zag+0.098
henko+0.092
arial+0.091
ibaba+0.089
Neg logit contributions
Glass-0.070
 Ped-0.068
%:-0.061
 Forever-0.060
Ped-0.059
Token
Token ID198
Feature activation+7.17e-01

Pos logit contributions
acas+0.777
zag+0.720
henko+0.681
arial+0.673
ibaba+0.658
Neg logit contributions
Glass-0.493
 Ped-0.480
%:-0.428
 Forever-0.418
Ped-0.409
Token,
Token ID11
Feature activation-8.97e-02

Pos logit contributions
acas+0.720
zag+0.660
henko+0.621
arial+0.611
ibaba+0.598
Neg logit contributions
Glass-0.576
 Ped-0.564
%:-0.509
 Forever-0.500
Ped-0.490
Token and
Token ID290
Feature activation-6.41e-01

Pos logit contributions
Glass+0.070
 Ped+0.068
%:+0.062
 Forever+0.061
Ped+0.060
Neg logit contributions
acas-0.077
zag-0.070
henko-0.066
arial-0.064
ibaba-0.063
Token the
Token ID262
Feature activation-2.40e-01

Pos logit contributions
Glass+0.452
 Ped+0.444
%:+0.398
 Forever+0.391
Ped+0.383
Neg logit contributions
acas-0.596
zag-0.547
henko-0.514
arial-0.506
ibaba-0.498
Token only
Token ID691
Feature activation+1.32e-01

Pos logit contributions
Glass+0.177
 Ped+0.174
%:+0.157
 Forever+0.155
Ped+0.151
Neg logit contributions
acas-0.215
zag-0.197
henko-0.186
arial-0.182
ibaba-0.179
Token w
Token ID266
Feature activation-4.86e-01

Pos logit contributions
acas+0.114
zag+0.104
henko+0.098
arial+0.095
ibaba+0.094
Neg logit contributions
Glass-0.103
 Ped-0.101
%:-0.091
 Forever-0.090
Ped-0.088
Tokenisp
Token ID8802
Feature activation+4.14e+00

Pos logit contributions
Glass+0.264
 Ped+0.257
%:+0.223
 Forever+0.217
Ped+0.211
Neg logit contributions
acas-0.528
zag-0.492
henko-0.470
arial-0.464
ibaba-0.455
Token of
Token ID286
Feature activation+3.27e-01

Pos logit contributions
acas+3.209
zag+2.908
henko+2.692
arial+2.640
ibaba+2.551
Neg logit contributions
Glass-3.514
 Ped-3.431
%:-3.197
 Forever-3.117
Ped-3.073
Token political
Token ID1964
Feature activation-1.47e+00

Pos logit contributions
acas+0.283
zag+0.259
henko+0.243
arial+0.239
ibaba+0.233
Neg logit contributions
Glass-0.251
 Ped-0.246
%:-0.224
 Forever-0.219
Ped-0.216
Token activity
Token ID3842
Feature activation+6.31e-01

Pos logit contributions
Glass+1.141
 Ped+1.124
%:+1.003
 Forever+0.995
Ped+0.979
Neg logit contributions
acas-1.260
zag-1.158
henko-1.083
arial-1.050
ibaba-1.046
Token in
Token ID287
Feature activation+4.43e-01

Pos logit contributions
acas+0.496
zag+0.448
henko+0.417
arial+0.408
ibaba+0.400
Neg logit contributions
Glass-0.536
 Ped-0.528
%:-0.483
 Forever-0.476
Ped-0.468
Token her
Token ID607
Feature activation-1.11e-01

Pos logit contributions
acas+0.413
zag+0.380
henko+0.359
arial+0.353
ibaba+0.346
Neg logit contributions
Glass-0.311
 Ped-0.305
%:-0.274
 Forever-0.269
Ped-0.263
Token the
Token ID262
Feature activation-3.51e-01

Pos logit contributions
acas+0.888
zag+0.819
henko+0.772
arial+0.763
ibaba+0.745
Neg logit contributions
Glass-0.627
 Ped-0.610
%:-0.550
 Forever-0.536
Ped-0.527
Token findings
Token ID6373
Feature activation+6.19e-01

Pos logit contributions
Glass+0.268
 Ped+0.264
%:+0.239
 Forever+0.236
Ped+0.231
Neg logit contributions
acas-0.305
zag-0.279
henko-0.262
arial-0.256
ibaba-0.252
Token.
Token ID13
Feature activation-2.50e-01

Pos logit contributions
acas+0.577
zag+0.532
henko+0.500
arial+0.491
ibaba+0.486
Neg logit contributions
Glass-0.433
 Ped-0.427
%:-0.383
 Forever-0.377
Ped-0.368
Token Un
Token ID791
Feature activation-2.92e-01

Pos logit contributions
Glass+0.153
 Ped+0.150
%:+0.132
 Forever+0.130
Ped+0.127
Neg logit contributions
acas-0.256
zag-0.237
henko-0.225
arial-0.221
ibaba-0.219
Tokenw
Token ID86
Feature activation+9.06e-01

Pos logit contributions
Glass+0.206
 Ped+0.201
%:+0.182
 Forever+0.178
Ped+0.175
Neg logit contributions
acas-0.270
zag-0.249
henko-0.234
arial-0.230
ibaba-0.227
Tokenilling
Token ID4509
Feature activation+4.07e+00

Pos logit contributions
acas+0.715
zag+0.647
henko+0.602
arial+0.591
ibaba+0.576
Neg logit contributions
Glass-0.766
 Ped-0.751
%:-0.691
 Forever-0.679
Ped-0.668
Token to
Token ID284
Feature activation+9.45e-01

Pos logit contributions
acas+3.614
zag+3.337
arial+3.094
henko+3.080
omore+2.983
Neg logit contributions
Glass-2.955
 Ped-2.861
%:-2.655
 Forever-2.544
Ped-2.523
Token challenge
Token ID4427
Feature activation+5.99e-01

Pos logit contributions
acas+0.737
zag+0.668
henko+0.620
arial+0.609
ibaba+0.596
Neg logit contributions
Glass-0.806
 Ped-0.795
%:-0.729
 Forever-0.717
Ped-0.704
Token the
Token ID262
Feature activation-4.25e-01

Pos logit contributions
acas+0.573
zag+0.529
henko+0.499
arial+0.492
ibaba+0.482
Neg logit contributions
Glass-0.405
 Ped-0.396
%:-0.355
 Forever-0.348
Ped-0.341
Token data
Token ID1366
Feature activation+5.99e-02

Pos logit contributions
Glass+0.329
 Ped+0.324
%:+0.293
 Forever+0.289
Ped+0.283
Neg logit contributions
acas-0.365
zag-0.334
henko-0.314
arial-0.307
ibaba-0.303
Token openly
Token ID11764
Feature activation-4.10e-01

Pos logit contributions
acas+0.053
zag+0.049
henko+0.046
arial+0.045
ibaba+0.044
Neg logit contributions
Glass-0.044
 Ped-0.044
%:-0.039
 Forever-0.039
Ped-0.038
Token the
Token ID262
Feature activation-8.82e-02

Pos logit contributions
acas+0.782
zag+0.722
henko+0.678
arial+0.670
ibaba+0.656
Neg logit contributions
Glass-0.551
 Ped-0.536
%:-0.483
 Forever-0.469
Ped-0.464
Token Nexus
Token ID16756
Feature activation+9.83e-01

Pos logit contributions
Glass+0.058
 Ped+0.057
%:+0.051
 Forever+0.050
Ped+0.049
Neg logit contributions
acas-0.086
zag-0.079
henko-0.075
arial-0.074
ibaba-0.073
Token 6
Token ID718
Feature activation+7.29e-01

Pos logit contributions
acas+0.879
zag+0.808
henko+0.758
arial+0.742
ibaba+0.729
Neg logit contributions
Glass-0.721
 Ped-0.705
%:-0.642
 Forever-0.624
Ped-0.618
Token.
Token ID13
Feature activation+8.07e-01

Pos logit contributions
acas+0.674
zag+0.621
henko+0.584
arial+0.575
ibaba+0.563
Neg logit contributions
Glass-0.514
 Ped-0.502
%:-0.453
 Forever-0.443
Ped-0.436
Token No
Token ID1400
Feature activation+2.50e-01

Pos logit contributions
acas+0.805
zag+0.745
henko+0.704
arial+0.695
ibaba+0.681
Neg logit contributions
Glass-0.512
 Ped-0.497
%:-0.445
 Forever-0.431
Ped-0.426
Token word
Token ID1573
Feature activation+4.07e+00

Pos logit contributions
acas+0.214
zag+0.195
henko+0.183
arial+0.180
ibaba+0.175
Neg logit contributions
Glass-0.196
 Ped-0.192
%:-0.175
 Forever-0.172
Ped-0.169
Token on
Token ID319
Feature activation+5.18e-01

Pos logit contributions
acas+3.450
zag+3.160
henko+2.988
arial+2.984
omore+2.851
Neg logit contributions
Glass-3.120
 Ped-3.011
%:-2.772
 Forever-2.698
Ped-2.658
Token if
Token ID611
Feature activation+1.35e+00

Pos logit contributions
acas+0.469
zag+0.431
henko+0.405
arial+0.399
ibaba+0.391
Neg logit contributions
Glass-0.376
 Ped-0.367
%:-0.333
 Forever-0.325
Ped-0.321
Token there
Token ID612
Feature activation+5.71e-01

Pos logit contributions
acas+1.222
zag+1.121
henko+1.052
arial+1.037
ibaba+1.015
Neg logit contributions
Glass-0.979
 Ped-0.956
%:-0.870
 Forever-0.844
Ped-0.837
Token will
Token ID481
Feature activation-5.92e-01

Pos logit contributions
acas+0.557
zag+0.515
henko+0.487
arial+0.480
ibaba+0.471
Neg logit contributions
Glass-0.374
 Ped-0.364
%:-0.327
 Forever-0.318
Ped-0.313
Token be
Token ID307
Feature activation-6.34e-01

Pos logit contributions
Glass+0.404
 Ped+0.394
%:+0.355
 Forever+0.346
Ped+0.340
Neg logit contributions
acas-0.563
zag-0.520
henko-0.490
arial-0.483
ibaba-0.473
Token a
Token ID257
Feature activation+1.50e-02

Pos logit contributions
Glass+0.147
 Ped+0.144
%:+0.130
 Forever+0.127
Ped+0.125
Neg logit contributions
acas-0.183
zag-0.168
henko-0.158
arial-0.156
ibaba-0.153
Token crust
Token ID20048
Feature activation+9.04e-01

Pos logit contributions
acas+0.013
zag+0.012
henko+0.011
arial+0.011
ibaba+0.010
Neg logit contributions
Glass-0.012
 Ped-0.012
%:-0.011
 Forever-0.010
Ped-0.010
Tokeny
Token ID88
Feature activation-3.01e-01

Pos logit contributions
acas+0.740
zag+0.673
henko+0.628
arial+0.617
ibaba+0.603
Neg logit contributions
Glass-0.737
 Ped-0.723
%:-0.661
 Forever-0.649
Ped-0.639
Token old
Token ID1468
Feature activation-1.06e+00

Pos logit contributions
Glass+0.225
 Ped+0.221
%:+0.200
 Forever+0.196
Ped+0.193
Neg logit contributions
acas-0.267
zag-0.244
henko-0.229
arial-0.226
ibaba-0.221
Token bl
Token ID698
Feature activation+9.99e-01

Pos logit contributions
Glass+0.928
 Ped+0.918
%:+0.833
 Forever+0.829
Ped+0.812
Neg logit contributions
acas-0.807
zag-0.732
henko-0.679
arial-0.661
ibaba-0.650
Tokenoke
Token ID2088
Feature activation+3.87e+00

Pos logit contributions
acas+0.712
zag+0.636
henko+0.586
arial+0.575
ibaba+0.557
Neg logit contributions
Glass-0.925
 Ped-0.907
%:-0.840
 Forever-0.827
Ped-0.816
Token on
Token ID319
Feature activation-1.97e-01

Pos logit contributions
acas+3.268
zag+2.978
henko+2.792
arial+2.761
ibaba+2.664
Neg logit contributions
Glass-3.040
 Ped-2.935
%:-2.720
 Forever-2.630
Ped-2.609
Token a
Token ID257
Feature activation-8.34e-02

Pos logit contributions
Glass+0.128
 Ped+0.125
%:+0.111
 Forever+0.110
Ped+0.107
Neg logit contributions
acas-0.193
zag-0.179
henko-0.169
arial-0.166
ibaba-0.163
Token stool
Token ID38753
Feature activation+2.74e-01

Pos logit contributions
Glass+0.062
 Ped+0.061
%:+0.055
 Forever+0.054
Ped+0.053
Neg logit contributions
acas-0.074
zag-0.068
henko-0.064
arial-0.063
ibaba-0.061
Token,
Token ID11
Feature activation-1.65e-01

Pos logit contributions
acas+0.238
zag+0.219
henko+0.205
arial+0.201
ibaba+0.197
Neg logit contributions
Glass-0.209
 Ped-0.206
%:-0.187
 Forever-0.184
Ped-0.181
Token ask
Token ID1265
Feature activation+1.82e-01

Pos logit contributions
Glass+0.127
 Ped+0.125
%:+0.112
 Forever+0.111
Ped+0.109
Neg logit contributions
acas-0.143
zag-0.131
henko-0.122
arial-0.120
ibaba-0.118
Token stemming
Token ID34807
Feature activation-7.40e-01

Pos logit contributions
Glass+0.405
 Ped+0.403
%:+0.356
 Forever+0.354
Ped+0.345
Neg logit contributions
acas-0.525
zag-0.482
henko-0.451
arial-0.444
ibaba-0.443
Token from
Token ID422
Feature activation+2.81e-01

Pos logit contributions
Glass+0.470
 Ped+0.468
%:+0.408
 Forever+0.405
Ped+0.395
Neg logit contributions
acas-0.734
zag-0.680
henko-0.640
arial-0.633
ibaba-0.630
Token an
Token ID281
Feature activation+2.33e-01

Pos logit contributions
acas+0.265
zag+0.243
henko+0.229
arial+0.226
ibaba+0.224
Neg logit contributions
Glass-0.193
 Ped-0.192
%:-0.170
 Forever-0.168
Ped-0.164
Token out
Token ID503
Feature activation-1.58e-01

Pos logit contributions
acas+0.200
zag+0.184
henko+0.171
arial+0.169
ibaba+0.166
Neg logit contributions
Glass-0.179
 Ped-0.177
%:-0.160
 Forever-0.157
Ped-0.155
Token-
Token ID12
Feature activation+7.64e-01

Pos logit contributions
Glass+0.119
 Ped+0.117
%:+0.105
 Forever+0.103
Ped+0.102
Neg logit contributions
acas-0.138
zag-0.127
henko-0.119
arial-0.118
ibaba-0.116
Tokenof
Token ID1659
Feature activation+3.79e+00

Pos logit contributions
acas+0.667
zag+0.610
henko+0.572
arial+0.563
ibaba+0.551
Neg logit contributions
Glass-0.581
 Ped-0.569
%:-0.517
 Forever-0.507
Ped-0.499
Token-
Token ID12
Feature activation-1.24e-01

Pos logit contributions
acas+3.107
zag+2.837
henko+2.649
arial+2.599
ibaba+2.512
Neg logit contributions
Glass-3.070
 Ped-3.000
%:-2.756
 Forever-2.698
Ped-2.666
Tokencomp
Token ID5589
Feature activation+3.62e-01

Pos logit contributions
Glass+0.078
 Ped+0.076
%:+0.067
 Forever+0.066
Ped+0.065
Neg logit contributions
acas-0.124
zag-0.115
henko-0.109
arial-0.107
ibaba-0.106
Tokenetition
Token ID15620
Feature activation-1.03e+00

Pos logit contributions
acas+0.198
zag+0.172
henko+0.154
arial+0.149
ibaba+0.144
Neg logit contributions
Glass-0.394
 Ped-0.388
%:-0.364
 Forever-0.358
Ped-0.355
Token test
Token ID1332
Feature activation-9.79e-02

Pos logit contributions
 Ped+0.859
Glass+0.852
%:+0.765
 Forever+0.763
 PF+0.752
Neg logit contributions
acas-0.810
zag-0.737
henko-0.679
arial-0.670
ibaba-0.665
Token conducted
Token ID5952
Feature activation-4.45e-01

Pos logit contributions
Glass+0.073
 Ped+0.072
%:+0.064
 Forever+0.064
Ped+0.062
Neg logit contributions
acas-0.087
zag-0.080
henko-0.075
arial-0.073
ibaba-0.073
Token:
Token ID25
Feature activation+6.33e-02

Pos logit contributions
acas+1.135
zag+1.047
henko+0.988
arial+0.973
ibaba+0.954
Neg logit contributions
Glass-0.805
 Ped-0.787
%:-0.706
 Forever-0.690
Ped-0.676
Token
Token ID198
Feature activation-4.46e-03

Pos logit contributions
acas+0.063
zag+0.058
henko+0.055
arial+0.054
ibaba+0.053
Neg logit contributions
Glass-0.040
 Ped-0.039
%:-0.035
 Forever-0.034
Ped-0.034
Token
Token ID198
Feature activation+1.17e-01

Pos logit contributions
Glass+0.003
 Ped+0.003
%:+0.002
 Forever+0.002
Ped+0.002
Neg logit contributions
acas-0.005
zag-0.004
henko-0.004
arial-0.004
ibaba-0.004
Tokenstruct
Token ID7249
Feature activation+1.31e-01

Pos logit contributions
acas+0.113
zag+0.104
henko+0.098
arial+0.097
ibaba+0.095
Neg logit contributions
Glass-0.078
 Ped-0.077
%:-0.069
 Forever-0.067
Ped-0.065
Token Board
Token ID5926
Feature activation+1.03e+00

Pos logit contributions
acas+0.131
zag+0.121
henko+0.114
arial+0.113
ibaba+0.111
Neg logit contributions
Glass-0.084
 Ped-0.082
%:-0.073
 Forever-0.071
Ped-0.070
Token {
Token ID1391
Feature activation+3.78e+00

Pos logit contributions
acas+0.823
zag+0.747
henko+0.698
arial+0.685
ibaba+0.668
Neg logit contributions
Glass-0.854
 Ped-0.838
%:-0.768
 Forever-0.754
Ped-0.745
Token turn
Token ID1210
Feature activation-6.56e-02

Pos logit contributions
acas+3.424
zag+3.140
henko+2.945
arial+2.907
ibaba+2.804
Neg logit contributions
Glass-2.704
 Ped-2.587
%:-2.390
 Forever-2.305
Ped-2.304
Token :
Token ID1058
Feature activation+9.31e-01

Pos logit contributions
Glass+0.044
 Ped+0.043
%:+0.038
 Forever+0.037
Ped+0.037
Neg logit contributions
acas-0.064
zag-0.059
henko-0.056
arial-0.055
ibaba-0.054
Token Player
Token ID7853
Feature activation+2.50e+00

Pos logit contributions
acas+0.928
zag+0.859
henko+0.813
arial+0.802
ibaba+0.786
Neg logit contributions
Glass-0.592
 Ped-0.579
%:-0.515
 Forever-0.503
Ped-0.492
Token,
Token ID837
Feature activation+2.60e-01

Pos logit contributions
acas+2.337
zag+2.153
henko+2.027
arial+2.000
ibaba+1.955
Neg logit contributions
Glass-1.737
 Ped-1.697
%:-1.529
 Forever-1.496
Ped-1.467
Token //
Token ID3373
Feature activation+1.18e+00

Pos logit contributions
acas+0.215
zag+0.196
henko+0.183
arial+0.180
ibaba+0.176
Neg logit contributions
Glass-0.210
 Ped-0.207
%:-0.189
 Forever-0.185
Ped-0.182
Token The
Token ID383
Feature activation+5.90e-02

Pos logit contributions
Glass+0.092
 Ped+0.090
%:+0.079
 Forever+0.078
Ped+0.076
Neg logit contributions
acas-0.145
zag-0.135
henko-0.127
arial-0.125
ibaba-0.124
Token MLB
Token ID18532
Feature activation+5.29e-01

Pos logit contributions
acas+0.052
zag+0.047
henko+0.044
arial+0.044
ibaba+0.043
Neg logit contributions
Glass-0.045
 Ped-0.044
%:-0.040
 Forever-0.039
Ped-0.038
Token Network
Token ID7311
Feature activation-8.88e-01

Pos logit contributions
acas+0.482
zag+0.443
henko+0.416
arial+0.410
ibaba+0.401
Neg logit contributions
Glass-0.383
 Ped-0.375
%:-0.339
 Forever-0.332
Ped-0.326
Token squ
Token ID2809
Feature activation-5.58e-01

Pos logit contributions
Glass+0.662
 Ped+0.651
%:+0.585
 Forever+0.579
Ped+0.567
Neg logit contributions
acas-0.788
zag-0.726
henko-0.681
arial-0.668
ibaba-0.656
Tokenaw
Token ID707
Feature activation+1.69e+00

Pos logit contributions
Glass+0.435
 Ped+0.427
%:+0.388
 Forever+0.380
Ped+0.375
Neg logit contributions
acas-0.475
zag-0.435
henko-0.407
arial-0.401
ibaba-0.391
Tokenked
Token ID9091
Feature activation+3.77e+00

Pos logit contributions
acas+1.613
zag+1.484
henko+1.393
arial+1.378
ibaba+1.338
Neg logit contributions
Glass-1.150
 Ped-1.116
%:-1.012
 Forever-0.981
Ped-0.964
Token from
Token ID422
Feature activation+8.03e-03

Pos logit contributions
acas+3.311
zag+3.030
henko+2.850
arial+2.807
ibaba+2.717
Neg logit contributions
Glass-2.823
 Ped-2.732
%:-2.512
 Forever-2.424
Ped-2.411
Token the
Token ID262
Feature activation-4.02e-02

Pos logit contributions
acas+0.008
zag+0.007
henko+0.007
arial+0.006
ibaba+0.006
Neg logit contributions
Glass-0.006
 Ped-0.005
%:-0.005
 Forever-0.005
Ped-0.005
Token television
Token ID5581
Feature activation-4.64e-01

Pos logit contributions
Glass+0.031
 Ped+0.031
%:+0.028
 Forever+0.028
Ped+0.027
Neg logit contributions
acas-0.034
zag-0.031
henko-0.029
arial-0.029
ibaba-0.028
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
Glass+0.337
 Ped+0.331
%:+0.297
 Forever+0.292
Ped+0.287
Neg logit contributions
acas-0.420
zag-0.389
henko-0.368
arial-0.359
ibaba-0.351
Token news
Token ID1705
Feature activation-9.21e-01

Pos logit contributions
Glass+0.153
 Ped+0.151
%:+0.136
 Forever+0.135
Ped+0.132
Neg logit contributions
acas-0.168
zag-0.153
henko-0.144
arial-0.141
ibaba-0.139
Token
Token ID198
Feature activation+3.71e-01

Pos logit contributions
acas+0.142
zag+0.132
henko+0.124
arial+0.123
ibaba+0.120
Neg logit contributions
Glass-0.092
 Ped-0.089
%:-0.080
 Forever-0.078
Ped-0.076
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
acas+0.378
zag+0.350
henko+0.332
arial+0.327
ibaba+0.322
Neg logit contributions
Glass-0.229
 Ped-0.224
%:-0.198
 Forever-0.193
Ped-0.189
Tokenpub
Token ID12984
Feature activation+2.10e+00

Pos logit contributions
acas+0.320
zag+0.294
henko+0.276
arial+0.273
ibaba+0.266
Neg logit contributions
Glass-0.251
 Ped-0.246
%:-0.222
 Forever-0.217
Ped-0.213
Token struct
Token ID2878
Feature activation+3.32e-01

Pos logit contributions
acas+1.741
zag+1.585
henko+1.478
arial+1.453
ibaba+1.414
Neg logit contributions
Glass-1.699
 Ped-1.661
%:-1.519
 Forever-1.489
Ped-1.469
Token Guard
Token ID4932
Feature activation+1.68e+00

Pos logit contributions
acas+0.335
zag+0.310
henko+0.294
arial+0.290
ibaba+0.284
Neg logit contributions
Glass-0.207
 Ped-0.202
%:-0.180
 Forever-0.175
Ped-0.172
Token {
Token ID1391
Feature activation+3.75e+00

Pos logit contributions
acas+1.393
zag+1.268
henko+1.183
arial+1.166
ibaba+1.134
Neg logit contributions
Glass-1.348
 Ped-1.322
%:-1.209
 Forever-1.187
Ped-1.167
Token...
Token ID2644
Feature activation-8.60e-01

Pos logit contributions
acas+3.360
zag+3.079
henko+2.889
arial+2.849
ibaba+2.741
Neg logit contributions
Glass-2.703
 Ped-2.582
%:-2.375
Ped-2.306
 Forever-2.272
Token }
Token ID1782
Feature activation+2.33e-02

Pos logit contributions
Glass+0.617
 Ped+0.605
%:+0.546
 Forever+0.536
Ped+0.525
Neg logit contributions
acas-0.787
zag-0.723
henko-0.681
arial-0.670
ibaba-0.658
Token pub
Token ID2240
Feature activation+1.48e+00

Pos logit contributions
acas+0.022
zag+0.020
henko+0.019
arial+0.019
ibaba+0.018
Neg logit contributions
Glass-0.016
 Ped-0.016
%:-0.014
 Forever-0.014
Ped-0.014
Token fn
Token ID24714
Feature activation+1.68e-01

Pos logit contributions
acas+1.168
zag+1.059
henko+0.983
arial+0.965
ibaba+0.937
Neg logit contributions
Glass-1.254
 Ped-1.228
%:-1.129
 Forever-1.106
Ped-1.094
Token pin
Token ID6757
Feature activation+1.54e+00

Pos logit contributions
acas+0.144
zag+0.131
henko+0.123
arial+0.121
ibaba+0.118
Neg logit contributions
Glass-0.131
 Ped-0.129
%:-0.117
 Forever-0.116
Ped-0.113
Token]
Token ID60
Feature activation-3.28e-01

Pos logit contributions
acas+0.488
zag+0.453
henko+0.427
arial+0.422
ibaba+0.410
Neg logit contributions
Glass-0.331
 Ped-0.320
%:-0.287
 Forever-0.280
Ped-0.275
Token
Token ID198
Feature activation+6.36e-01

Pos logit contributions
Glass+0.201
 Ped+0.196
%:+0.173
 Forever+0.170
Ped+0.166
Neg logit contributions
acas-0.336
zag-0.311
henko-0.295
arial-0.291
ibaba-0.286
Token
Token ID198
Feature activation+4.73e-01

Pos logit contributions
acas+0.633
zag+0.586
henko+0.555
arial+0.548
ibaba+0.535
Neg logit contributions
Glass-0.404
 Ped-0.394
%:-0.351
 Forever-0.343
Ped-0.336
TokenStates
Token ID42237
Feature activation+1.02e+00

Pos logit contributions
acas+0.477
zag+0.444
henko+0.418
arial+0.415
ibaba+0.403
Neg logit contributions
Glass-0.292
 Ped-0.288
%:-0.255
 Forever-0.250
Ped-0.241
Token and
Token ID290
Feature activation+9.09e-02

Pos logit contributions
acas+0.935
zag+0.860
henko+0.809
arial+0.798
ibaba+0.780
Neg logit contributions
Glass-0.729
 Ped-0.713
%:-0.644
 Forever-0.631
Ped-0.619
Token territories
Token ID16771
Feature activation+3.73e+00

Pos logit contributions
acas+0.077
zag+0.070
henko+0.066
arial+0.065
ibaba+0.063
Neg logit contributions
Glass-0.071
 Ped-0.070
%:-0.064
 Forever-0.063
Ped-0.062
Token
Token ID198
Feature activation+9.16e-01

Pos logit contributions
acas+3.402
zag+3.132
henko+2.935
arial+2.897
ibaba+2.805
Neg logit contributions
Glass-2.680
 Ped-2.590
%:-2.350
Ped-2.289
 Forever-2.277
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
acas+0.913
zag+0.845
henko+0.799
arial+0.789
ibaba+0.771
Neg logit contributions
Glass-0.582
 Ped-0.567
%:-0.506
 Forever-0.493
Ped-0.484
TokenA
Token ID32
Feature activation+1.08e+00

Pos logit contributions
acas+1.141
zag+1.059
henko+0.996
arial+0.989
ibaba+0.961
Neg logit contributions
Glass-0.715
 Ped-0.707
%:-0.625
 Forever-0.614
Ped-0.592
Token map
Token ID3975
Feature activation+1.20e+00

Pos logit contributions
acas+0.948
zag+0.870
henko+0.815
arial+0.803
ibaba+0.784
Neg logit contributions
Glass-0.811
 Ped-0.792
%:-0.721
 Forever-0.705
Ped-0.698
Token of
Token ID286
Feature activation-3.84e-01

Pos logit contributions
acas+0.998
zag+0.908
henko+0.851
arial+0.834
ibaba+0.818
Neg logit contributions
Glass-0.965
 Ped-0.949
%:-0.863
 Forever-0.850
Ped-0.835
Token will
Token ID481
Feature activation-3.19e-02

Pos logit contributions
Glass+0.047
 Ped+0.046
%:+0.041
 Forever+0.040
Ped+0.040
Neg logit contributions
acas-0.060
zag-0.055
henko-0.052
arial-0.051
ibaba-0.050
Token o
Token ID267
Feature activation-1.96e+00

Pos logit contributions
Glass+0.023
 Ped+0.023
%:+0.021
 Forever+0.020
Ped+0.020
Neg logit contributions
acas-0.029
zag-0.026
henko-0.025
arial-0.024
ibaba-0.024
Token'
Token ID6
Feature activation+1.96e+00

Pos logit contributions
Glass+1.430
 Ped+1.402
%:+1.260
 Forever+1.240
Ped+1.217
Neg logit contributions
acas-1.769
zag-1.625
henko-1.521
arial-1.512
ibaba-1.470
Token the
Token ID262
Feature activation-1.64e-01

Pos logit contributions
acas+1.876
zag+1.738
henko+1.638
arial+1.618
ibaba+1.571
Neg logit contributions
Glass-1.308
 Ped-1.286
%:-1.157
 Forever-1.125
Ped-1.109
Token w
Token ID266
Feature activation-7.19e-01

Pos logit contributions
Glass+0.110
 Ped+0.107
%:+0.097
 Forever+0.094
Ped+0.093
Neg logit contributions
acas-0.157
zag-0.145
henko-0.137
arial-0.135
ibaba-0.132
Tokenisp
Token ID8802
Feature activation+3.73e+00

Pos logit contributions
Glass+0.580
 Ped+0.568
%:+0.518
 Forever+0.509
Ped+0.501
Neg logit contributions
acas-0.594
zag-0.541
henko-0.507
arial-0.498
ibaba-0.486
Token of
Token ID286
Feature activation-7.06e-01

Pos logit contributions
acas+3.212
zag+2.940
henko+2.753
arial+2.701
ibaba+2.630
Neg logit contributions
Glass-2.868
 Ped-2.797
%:-2.571
 Forever-2.498
Ped-2.470
Token a
Token ID257
Feature activation-3.31e-01

Pos logit contributions
Glass+0.488
 Ped+0.478
%:+0.427
 Forever+0.421
Ped+0.411
Neg logit contributions
acas-0.665
zag-0.612
henko-0.578
arial-0.569
ibaba-0.558
Token grand
Token ID4490
Feature activation-9.59e-01

Pos logit contributions
Glass+0.246
 Ped+0.241
%:+0.218
 Forever+0.215
Ped+0.211
Neg logit contributions
acas-0.295
zag-0.270
henko-0.254
arial-0.250
ibaba-0.244
Token constitution
Token ID11784
Feature activation+7.78e-01

Pos logit contributions
Glass+0.735
 Ped+0.721
%:+0.653
 Forever+0.643
Ped+0.632
Neg logit contributions
acas-0.831
zag-0.760
henko-0.712
arial-0.700
ibaba-0.686
Token,
Token ID11
Feature activation-1.40e-01

Pos logit contributions
acas+0.688
zag+0.630
henko+0.591
arial+0.582
ibaba+0.569
Neg logit contributions
Glass-0.583
 Ped-0.572
%:-0.518
 Forever-0.508
Ped-0.500
Token of
Token ID286
Feature activation+3.43e-01

Pos logit contributions
acas+0.847
zag+0.776
henko+0.729
arial+0.718
ibaba+0.704
Neg logit contributions
Glass-0.710
 Ped-0.696
%:-0.630
 Forever-0.619
Ped-0.608
Token the
Token ID262
Feature activation+2.19e-01

Pos logit contributions
acas+0.317
zag+0.292
henko+0.275
arial+0.271
ibaba+0.265
Neg logit contributions
Glass-0.243
 Ped-0.238
%:-0.214
 Forever-0.210
Ped-0.206
Token lab
Token ID2248
Feature activation+1.26e+00

Pos logit contributions
acas+0.174
zag+0.158
henko+0.148
arial+0.145
ibaba+0.141
Neg logit contributions
Glass-0.185
 Ped-0.182
%:-0.165
 Forever-0.164
Ped-0.161
Tokenia
Token ID544
Feature activation+4.08e-01

Pos logit contributions
acas+0.990
zag+0.895
henko+0.843
arial+0.818
ibaba+0.802
Neg logit contributions
Glass-1.073
 Ped-1.053
%:-0.961
 Forever-0.947
Ped-0.931
Token str
Token ID965
Feature activation+1.46e+00

Pos logit contributions
acas+0.357
zag+0.326
henko+0.304
arial+0.300
ibaba+0.290
Neg logit contributions
Glass-0.310
 Ped-0.302
%:-0.274
 Forever-0.270
Ped-0.267
Tokenadd
Token ID2860
Feature activation+3.72e+00

Pos logit contributions
acas+1.176
zag+1.067
henko+0.991
arial+0.981
ibaba+0.953
Neg logit contributions
Glass-1.205
 Ped-1.179
%:-1.080
 Forever-1.063
Ped-1.048
Tokenling
Token ID1359
Feature activation+1.16e+00

Pos logit contributions
acas+2.967
zag+2.693
henko+2.491
arial+2.451
ibaba+2.382
Neg logit contributions
Glass-3.098
 Ped-3.022
%:-2.777
 Forever-2.732
Ped-2.693
Token the
Token ID262
Feature activation+8.58e-02

Pos logit contributions
acas+1.070
zag+0.985
henko+0.928
arial+0.914
ibaba+0.894
Neg logit contributions
Glass-0.819
 Ped-0.802
%:-0.721
 Forever-0.708
Ped-0.694
Token clitor
Token ID48852
Feature activation-2.65e-01

Pos logit contributions
acas+0.068
zag+0.061
henko+0.057
arial+0.056
ibaba+0.055
Neg logit contributions
Glass-0.073
 Ped-0.072
%:-0.065
 Forever-0.065
Ped-0.063
Tokenis
Token ID271
Feature activation-5.13e-01

Pos logit contributions
Glass+0.160
 Ped+0.157
%:+0.139
 Forever+0.134
Ped+0.130
Neg logit contributions
acas-0.271
zag-0.252
henko-0.241
arial-0.235
ibaba-0.232
Token.
Token ID13
Feature activation+4.42e-01

Pos logit contributions
Glass+0.361
 Ped+0.356
%:+0.319
 Forever+0.313
Ped+0.306
Neg logit contributions
acas-0.477
zag-0.440
henko-0.417
arial-0.409
ibaba-0.400
Token
Token ID198
Feature activation+5.26e-01

Pos logit contributions
acas+1.325
zag+1.229
henko+1.164
arial+1.149
ibaba+1.126
Neg logit contributions
Glass-0.800
 Ped-0.778
%:-0.691
 Forever-0.673
Ped-0.660
Token
Token ID198
Feature activation+1.03e+00

Pos logit contributions
acas+0.531
zag+0.492
henko+0.466
arial+0.459
ibaba+0.451
Neg logit contributions
Glass-0.329
 Ped-0.321
%:-0.285
 Forever-0.278
Ped-0.273
Token9
Token ID24
Feature activation+6.58e-01

Pos logit contributions
acas+0.914
zag+0.837
henko+0.780
arial+0.774
ibaba+0.752
Neg logit contributions
Glass-0.762
 Ped-0.758
%:-0.684
 Forever-0.672
 Skull-0.650
Token.
Token ID13
Feature activation-3.57e-01

Pos logit contributions
acas+0.625
zag+0.576
henko+0.543
arial+0.536
ibaba+0.524
Neg logit contributions
Glass-0.450
 Ped-0.439
%:-0.395
 Forever-0.386
Ped-0.379
Token Sw
Token ID2451
Feature activation+7.63e-01

Pos logit contributions
Glass+0.221
 Ped+0.217
%:+0.190
 Forever+0.187
Ped+0.182
Neg logit contributions
acas-0.363
zag-0.337
henko-0.319
arial-0.314
ibaba-0.309
Tokenamin
Token ID5669
Feature activation+3.67e+00

Pos logit contributions
acas+0.641
zag+0.586
henko+0.550
arial+0.538
ibaba+0.525
Neg logit contributions
Glass-0.602
 Ped-0.592
%:-0.538
 Forever-0.528
Ped-0.520
Tokenar
Token ID283
Feature activation+5.85e-01

Pos logit contributions
acas+2.951
zag+2.685
henko+2.488
arial+2.467
ibaba+2.414
Neg logit contributions
Glass-3.041
 Ped-2.955
%:-2.754
 Forever-2.681
Ped-2.637
Tokenayan
Token ID22931
Feature activation+2.01e+00

Pos logit contributions
acas+0.513
zag+0.470
henko+0.441
arial+0.434
ibaba+0.423
Neg logit contributions
Glass-0.441
 Ped-0.433
%:-0.392
 Forever-0.386
Ped-0.379
Token A
Token ID317
Feature activation+9.24e-01

Pos logit contributions
acas+1.865
zag+1.717
henko+1.613
arial+1.595
ibaba+1.560
Neg logit contributions
Glass-1.411
 Ped-1.370
%:-1.247
 Forever-1.212
Ped-1.193
Tokenks
Token ID591
Feature activation+8.59e-01

Pos logit contributions
acas+0.774
zag+0.706
henko+0.659
arial+0.649
ibaba+0.633
Neg logit contributions
Glass-0.736
 Ped-0.721
%:-0.659
 Forever-0.647
Ped-0.637
Tokenhard
Token ID10424
Feature activation+2.26e+00

Pos logit contributions
acas+0.682
zag+0.618
henko+0.574
arial+0.563
ibaba+0.549
Neg logit contributions
Glass-0.719
 Ped-0.710
%:-0.647
 Forever-0.636
Ped-0.627
Token mentioned
Token ID4750
Feature activation-1.47e+00

Pos logit contributions
acas+0.311
zag+0.284
henko+0.266
arial+0.262
ibaba+0.255
Neg logit contributions
Glass-0.286
 Ped-0.280
%:-0.255
 Forever-0.251
Ped-0.247
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
Glass+1.069
 Ped+1.059
%:+0.945
 Forever+0.934
Ped+0.917
Neg logit contributions
acas-1.329
zag-1.226
henko-1.145
arial-1.133
ibaba-1.113
Token
Token ID198
Feature activation+1.90e-01

Pos logit contributions
Glass+0.202
 Ped+0.197
%:+0.174
 Forever+0.170
Ped+0.167
Neg logit contributions
acas-0.333
zag-0.309
henko-0.293
arial-0.289
ibaba-0.284
Token
Token ID198
Feature activation-2.32e-02

Pos logit contributions
acas+0.191
zag+0.177
henko+0.167
arial+0.165
ibaba+0.162
Neg logit contributions
Glass-0.120
 Ped-0.117
%:-0.104
 Forever-0.102
Ped-0.100
TokenNo
Token ID2949
Feature activation-4.21e-01

Pos logit contributions
Glass+0.015
 Ped+0.015
%:+0.013
 Forever+0.013
Ped+0.012
Neg logit contributions
acas-0.023
zag-0.021
henko-0.020
arial-0.020
ibaba-0.019
Token word
Token ID1573
Feature activation+3.67e+00

Pos logit contributions
Glass+0.321
 Ped+0.315
%:+0.286
 Forever+0.281
Ped+0.276
Neg logit contributions
acas-0.366
zag-0.335
henko-0.314
arial-0.309
ibaba-0.302
Token if
Token ID611
Feature activation+1.57e+00

Pos logit contributions
acas+3.139
zag+2.864
henko+2.712
arial+2.696
omore+2.579
Neg logit contributions
Glass-2.820
 Ped-2.716
%:-2.497
 Forever-2.440
Ped-2.400
Token the
Token ID262
Feature activation-2.86e-01

Pos logit contributions
acas+1.451
zag+1.331
henko+1.255
arial+1.236
ibaba+1.210
Neg logit contributions
Glass-1.109
 Ped-1.074
%:-0.983
 Forever-0.951
Ped-0.938
Token Str
Token ID4285
Feature activation+9.43e-01

Pos logit contributions
Glass+0.182
 Ped+0.177
%:+0.158
 Forever+0.154
Ped+0.151
Neg logit contributions
acas-0.286
zag-0.265
henko-0.251
arial-0.248
ibaba-0.243
Tokenand
Token ID392
Feature activation-2.50e-02

Pos logit contributions
acas+0.684
zag+0.614
henko+0.567
arial+0.558
ibaba+0.541
Neg logit contributions
Glass-0.858
 Ped-0.841
%:-0.777
 Forever-0.764
Ped-0.754
Token Craft
Token ID15745
Feature activation-1.56e-01

Pos logit contributions
Glass+0.018
 Ped+0.018
%:+0.016
 Forever+0.016
Ped+0.015
Neg logit contributions
acas-0.023
zag-0.021
henko-0.020
arial-0.020
ibaba-0.019
Token probably
Token ID2192
Feature activation-1.53e-01

Pos logit contributions
Glass+0.991
 Ped+0.988
%:+0.890
 Forever+0.866
Ped+0.845
Neg logit contributions
acas-1.264
zag-1.165
henko-1.088
arial-1.072
ibaba-1.063
Token have
Token ID423
Feature activation-1.16e+00

Pos logit contributions
Glass+0.108
 Ped+0.106
%:+0.096
 Forever+0.093
Ped+0.092
Neg logit contributions
acas-0.141
zag-0.130
henko-0.122
arial-0.120
ibaba-0.118
Token an
Token ID281
Feature activation-2.21e-01

Pos logit contributions
Glass+0.817
 Ped+0.805
%:+0.718
 Forever+0.706
Ped+0.692
Neg logit contributions
acas-1.075
zag-0.991
henko-0.932
arial-0.915
ibaba-0.902
Token out
Token ID503
Feature activation-2.17e-01

Pos logit contributions
Glass+0.169
 Ped+0.165
%:+0.150
 Forever+0.147
Ped+0.145
Neg logit contributions
acas-0.192
zag-0.176
henko-0.165
arial-0.162
ibaba-0.158
Token-
Token ID12
Feature activation+3.08e-01

Pos logit contributions
Glass+0.195
 Ped+0.192
%:+0.176
 Forever+0.174
Ped+0.171
Neg logit contributions
acas-0.161
zag-0.144
henko-0.134
arial-0.131
ibaba-0.128
Tokenof
Token ID1659
Feature activation+3.65e+00

Pos logit contributions
acas+0.270
zag+0.247
henko+0.232
arial+0.228
ibaba+0.223
Neg logit contributions
Glass-0.233
 Ped-0.228
%:-0.207
 Forever-0.203
Ped-0.200
Token-
Token ID12
Feature activation-5.92e-01

Pos logit contributions
acas+2.975
zag+2.717
henko+2.529
arial+2.489
ibaba+2.408
Neg logit contributions
Glass-2.947
 Ped-2.889
%:-2.649
 Forever-2.600
Ped-2.571
Tokenspec
Token ID16684
Feature activation-1.08e+00

Pos logit contributions
Glass+0.380
 Ped+0.369
%:+0.329
 Forever+0.321
Ped+0.315
Neg logit contributions
acas-0.589
zag-0.544
henko-0.515
arial-0.508
ibaba-0.499
Token lens
Token ID10317
Feature activation+8.78e-01

Pos logit contributions
Glass+0.878
 Ped+0.867
%:+0.780
 Forever+0.768
Ped+0.761
Neg logit contributions
acas-0.883
zag-0.800
henko-0.748
arial-0.724
ibaba-0.723
Token.
Token ID13
Feature activation-9.58e-02

Pos logit contributions
acas+0.774
zag+0.707
henko+0.664
arial+0.654
ibaba+0.641
Neg logit contributions
Glass-0.665
 Ped-0.653
%:-0.589
 Forever-0.578
Ped-0.570
Token That
Token ID1320
Feature activation+1.31e-01

Pos logit contributions
Glass+0.061
 Ped+0.060
%:+0.053
 Forever+0.052
Ped+0.051
Neg logit contributions
acas-0.096
zag-0.089
henko-0.084
arial-0.083
ibaba-0.082
Token
Token ID251
Feature activation+3.86e-01

Pos logit contributions
acas+0.638
zag+0.582
henko+0.544
arial+0.536
ibaba+0.522
Neg logit contributions
Glass-0.593
 Ped-0.581
%:-0.530
 Forever-0.520
Ped-0.512
Token wrote
Token ID2630
Feature activation-2.10e-01

Pos logit contributions
acas+0.350
zag+0.320
henko+0.302
arial+0.296
ibaba+0.291
Neg logit contributions
Glass-0.283
 Ped-0.280
%:-0.250
 Forever-0.247
Ped-0.242
Token Ari
Token ID6069
Feature activation-2.47e-01

Pos logit contributions
Glass+0.138
 Ped+0.136
%:+0.120
 Forever+0.119
Ped+0.115
Neg logit contributions
acas-0.206
zag-0.189
henko-0.179
arial-0.176
ibaba-0.174
Tokenka
Token ID4914
Feature activation-1.23e-01

Pos logit contributions
Glass+0.170
 Ped+0.167
%:+0.150
 Forever+0.147
Ped+0.144
Neg logit contributions
acas-0.233
zag-0.215
henko-0.202
arial-0.200
ibaba-0.196
Token Ok
Token ID6762
Feature activation-4.52e-01

Pos logit contributions
Glass+0.081
 Ped+0.079
%:+0.070
 Forever+0.069
Ped+0.067
Neg logit contributions
acas-0.120
zag-0.111
henko-0.105
arial-0.104
ibaba-0.102
Tokenrent
Token ID1156
Feature activation+3.65e+00

Pos logit contributions
Glass+0.381
 Ped+0.377
%:+0.345
 Forever+0.338
Ped+0.334
Neg logit contributions
acas-0.353
zag-0.319
henko-0.297
arial-0.292
ibaba-0.283
Token,
Token ID11
Feature activation+4.58e-01

Pos logit contributions
acas+3.289
zag+3.022
henko+2.864
arial+2.798
ibaba+2.725
Neg logit contributions
Glass-2.655
 Ped-2.574
%:-2.350
 Forever-2.290
Ped-2.261
Token a
Token ID257
Feature activation+1.20e+00

Pos logit contributions
acas+0.425
zag+0.391
henko+0.368
arial+0.363
ibaba+0.355
Neg logit contributions
Glass-0.323
 Ped-0.315
%:-0.284
 Forever-0.278
Ped-0.273
Token lingu
Token ID20280
Feature activation+2.91e-01

Pos logit contributions
acas+1.148
zag+1.059
henko+0.999
arial+0.985
ibaba+0.964
Neg logit contributions
Glass-0.820
 Ped-0.801
%:-0.719
 Forever-0.703
Ped-0.690
Tokenist
Token ID396
Feature activation-5.55e-03

Pos logit contributions
acas+0.244
zag+0.223
henko+0.209
arial+0.204
ibaba+0.200
Neg logit contributions
Glass-0.231
 Ped-0.227
%:-0.207
 Forever-0.203
Ped-0.200
Token and
Token ID290
Feature activation-4.06e-01

Pos logit contributions
Glass+0.004
 Ped+0.004
%:+0.004
 Forever+0.004
Ped+0.004
Neg logit contributions
acas-0.005
zag-0.005
henko-0.004
arial-0.004
ibaba-0.004
Token and
Token ID290
Feature activation-5.08e-01

Pos logit contributions
Glass+0.188
 Ped+0.183
%:+0.166
 Forever+0.162
Ped+0.160
Neg logit contributions
acas-0.241
zag-0.221
henko-0.208
arial-0.205
ibaba-0.201
Token Way
Token ID6378
Feature activation+1.50e-01

Pos logit contributions
Glass+0.357
 Ped+0.349
%:+0.314
 Forever+0.308
Ped+0.302
Neg logit contributions
acas-0.473
zag-0.435
henko-0.410
arial-0.404
ibaba-0.395
Tokenman
Token ID805
Feature activation-8.54e-01

Pos logit contributions
acas+0.139
zag+0.128
henko+0.120
arial+0.119
ibaba+0.116
Neg logit contributions
Glass-0.106
 Ped-0.104
%:-0.093
 Forever-0.091
Ped-0.090
Token T
Token ID309
Feature activation-4.53e-01

Pos logit contributions
Glass+0.722
 Ped+0.711
%:+0.649
 Forever+0.642
Ped+0.630
Neg logit contributions
acas-0.675
zag-0.612
henko-0.570
arial-0.561
ibaba-0.545
Tokenisd
Token ID9409
Feature activation+6.77e-01

Pos logit contributions
Glass+0.339
 Ped+0.331
%:+0.300
 Forever+0.295
Ped+0.289
Neg logit contributions
acas-0.402
zag-0.370
henko-0.346
arial-0.341
ibaba-0.333
Tokenale
Token ID1000
Feature activation+3.63e+00

Pos logit contributions
acas+0.656
zag+0.607
henko+0.574
arial+0.565
ibaba+0.555
Neg logit contributions
Glass-0.449
 Ped-0.439
%:-0.391
 Forever-0.384
Ped-0.372
Token Award
Token ID11289
Feature activation-1.34e+00

Pos logit contributions
acas+2.881
zag+2.614
henko+2.465
arial+2.389
ibaba+2.358
Neg logit contributions
Glass-2.987
 Ped-2.865
%:-2.693
Ped-2.592
 Forever-2.586
Token Watch
Token ID6305
Feature activation+1.44e-01

Pos logit contributions
Glass+0.935
 Ped+0.921
%:+0.825
 Forever+0.812
Ped+0.793
Neg logit contributions
acas-1.253
zag-1.154
henko-1.086
arial-1.071
ibaba-1.048
Token Lists
Token ID44968
Feature activation+8.87e-01

Pos logit contributions
acas+0.111
zag+0.101
henko+0.093
arial+0.092
ibaba+0.089
Neg logit contributions
Glass-0.124
 Ped-0.122
%:-0.112
 Forever-0.110
Ped-0.109
Token.[
Token ID3693
Feature activation+2.39e-01

Pos logit contributions
acas+0.855
zag+0.789
henko+0.744
arial+0.734
ibaba+0.720
Neg logit contributions
Glass-0.595
 Ped-0.581
%:-0.520
 Forever-0.510
Ped-0.499
Token105
Token ID13348
Feature activation-4.73e-01

Pos logit contributions
acas+0.219
zag+0.202
henko+0.190
arial+0.187
ibaba+0.183
Neg logit contributions
Glass-0.171
 Ped-0.168
%:-0.151
 Forever-0.148
Ped-0.145
Token period
Token ID2278
Feature activation+1.45e+00

Pos logit contributions
acas+0.315
zag+0.285
henko+0.264
arial+0.258
ibaba+0.253
Neg logit contributions
Glass-0.359
 Ped-0.354
%:-0.326
 Forever-0.320
Ped-0.315
Token.
Token ID13
Feature activation-3.06e-02

Pos logit contributions
acas+1.356
zag+1.251
henko+1.178
arial+1.160
ibaba+1.136
Neg logit contributions
Glass-1.007
 Ped-0.986
%:-0.887
 Forever-0.869
Ped-0.851
Token It
Token ID632
Feature activation+6.94e-02

Pos logit contributions
Glass+0.020
 Ped+0.020
%:+0.017
 Forever+0.017
Ped+0.017
Neg logit contributions
acas-0.030
zag-0.028
henko-0.026
arial-0.026
ibaba-0.026
Token made
Token ID925
Feature activation+1.12e-01

Pos logit contributions
acas+0.063
zag+0.058
henko+0.055
arial+0.054
ibaba+0.053
Neg logit contributions
Glass-0.050
 Ped-0.049
%:-0.044
 Forever-0.043
Ped-0.042
Token me
Token ID502
Feature activation+5.44e-01

Pos logit contributions
acas+0.104
zag+0.096
henko+0.090
arial+0.089
ibaba+0.087
Neg logit contributions
Glass-0.079
 Ped-0.077
%:-0.070
 Forever-0.068
Ped-0.067
Token wonder
Token ID4240
Feature activation+3.63e+00

Pos logit contributions
acas+0.461
zag+0.421
henko+0.393
arial+0.386
ibaba+0.379
Neg logit contributions
Glass-0.428
 Ped-0.420
%:-0.383
 Forever-0.377
Ped-0.370
Token how
Token ID703
Feature activation-7.26e-02

Pos logit contributions
acas+3.349
zag+3.088
henko+2.911
arial+2.870
omore+2.782
Neg logit contributions
Glass-2.559
 Ped-2.463
%:-2.230
 Forever-2.166
Ped-2.160
Token many
Token ID867
Feature activation+1.37e+00

Pos logit contributions
Glass+0.054
 Ped+0.054
%:+0.048
 Forever+0.048
Ped+0.047
Neg logit contributions
acas-0.064
zag-0.059
henko-0.055
arial-0.054
ibaba-0.054
Token cub
Token ID13617
Feature activation+1.47e+00

Pos logit contributions
acas+1.209
zag+1.108
henko+1.038
arial+1.023
ibaba+0.997
Neg logit contributions
Glass-1.035
 Ped-1.011
%:-0.920
 Forever-0.899
Ped-0.886
Tokens
Token ID82
Feature activation-2.11e-01

Pos logit contributions
acas+1.349
zag+1.241
henko+1.168
arial+1.151
ibaba+1.126
Neg logit contributions
Glass-1.046
 Ped-1.023
%:-0.924
 Forever-0.905
Ped-0.889
Token have
Token ID423
Feature activation+1.37e-01

Pos logit contributions
Glass+0.154
 Ped+0.152
%:+0.137
 Forever+0.135
Ped+0.132
Neg logit contributions
acas-0.190
zag-0.174
henko-0.164
arial-0.161
ibaba-0.159
Token Serve
Token ID35557
Feature activation-1.55e+00

Pos logit contributions
Glass+0.425
 Ped+0.411
%:+0.325
 Forever+0.318
Ped+0.290
Neg logit contributions
acas-1.544
zag-1.455
henko-1.394
arial-1.383
ibaba-1.367
Token hot
Token ID3024
Feature activation-1.94e-01

Pos logit contributions
Glass+1.272
 Ped+1.272
 Forever+1.151
%:+1.148
 Healthy+1.121
Neg logit contributions
acas-1.245
zag-1.134
henko-1.044
arial-1.032
ibaba-1.028
Token!
Token ID0
Feature activation-4.08e-01

Pos logit contributions
Glass+0.111
 Ped+0.109
%:+0.096
 Forever+0.094
Ped+0.090
Neg logit contributions
acas-0.207
zag-0.192
henko-0.182
arial-0.179
ibaba-0.177
Token<|endoftext|>
Token ID50256
Feature activation+3.41e-01

Pos logit contributions
Glass+0.274
 Ped+0.268
%:+0.238
 Forever+0.235
Ped+0.230
Neg logit contributions
acas-0.394
zag-0.363
henko-0.344
arial-0.340
ibaba-0.332
TokenImage
Token ID5159
Feature activation-1.27e+00

Pos logit contributions
acas+0.332
zag+0.307
henko+0.289
arial+0.286
ibaba+0.279
Neg logit contributions
Glass-0.223
 Ped-0.220
%:-0.196
 Forever-0.192
Ped-0.187
Token copyright
Token ID6634
Feature activation-5.21e+00

Pos logit contributions
Glass+1.253
 Ped+1.241
%:+1.152
 Forever+1.139
Ped+1.119
Neg logit contributions
acas-0.813
zag-0.727
henko-0.661
arial-0.646
ibaba-0.625
Token ESA
Token ID42212
Feature activation-9.89e-02

Pos logit contributions
 Ped+3.484
Glass+3.404
 Forever+3.026
%:+2.981
 PF+2.923
Neg logit contributions
acas-4.957
zag-4.609
henko-4.319
arial-4.288
ibaba-4.257
Token Image
Token ID7412
Feature activation-2.21e+00

Pos logit contributions
Glass+0.059
 Ped+0.057
%:+0.051
 Forever+0.049
Ped+0.048
Neg logit contributions
acas-0.103
zag-0.095
henko-0.091
arial-0.089
ibaba-0.088
Token caption
Token ID8305
Feature activation-3.57e+00

Pos logit contributions
Glass+1.994
 Ped+1.986
%:+1.823
 Forever+1.804
Ped+1.767
Neg logit contributions
acas-1.593
zag-1.456
henko-1.328
arial-1.296
ibaba-1.272
Token Go
Token ID1514
Feature activation+6.86e-01

Pos logit contributions
Glass+2.130
 Ped+2.125
%:+1.825
 Forever+1.820
Ped+1.754
Neg logit contributions
acas-3.689
zag-3.436
henko-3.244
arial-3.208
ibaba-3.167
Tokence
Token ID344
Feature activation+2.36e+00

Pos logit contributions
acas+0.605
zag+0.557
henko+0.520
arial+0.512
ibaba+0.501
Neg logit contributions
Glass-0.514
 Ped-0.503
%:-0.458
 Forever-0.447
Ped-0.440
Token million
Token ID1510
Feature activation+1.01e+00

Pos logit contributions
acas+0.090
zag+0.083
henko+0.079
arial+0.077
ibaba+0.076
Neg logit contributions
Glass-0.064
 Ped-0.062
%:-0.056
 Forever-0.054
Ped-0.053
Token years
Token ID812
Feature activation+3.00e-01

Pos logit contributions
acas+0.948
zag+0.874
henko+0.823
arial+0.813
ibaba+0.793
Neg logit contributions
Glass-0.708
 Ped-0.690
%:-0.623
 Forever-0.608
Ped-0.600
Token.
Token ID13
Feature activation-5.08e-01

Pos logit contributions
acas+0.284
zag+0.262
henko+0.247
arial+0.243
ibaba+0.238
Neg logit contributions
Glass-0.206
 Ped-0.201
%:-0.181
 Forever-0.177
Ped-0.174
Token<|endoftext|>
Token ID50256
Feature activation+6.95e-01

Pos logit contributions
Glass+0.317
 Ped+0.311
%:+0.273
 Forever+0.268
Ped+0.262
Neg logit contributions
acas-0.515
zag-0.478
henko-0.452
arial-0.446
ibaba-0.439
TokenImage
Token ID5159
Feature activation-9.70e-01

Pos logit contributions
acas+0.676
zag+0.626
henko+0.589
arial+0.583
ibaba+0.568
Neg logit contributions
Glass-0.454
 Ped-0.448
%:-0.400
 Forever-0.392
Ped-0.379
Token copyright
Token ID6634
Feature activation-5.09e+00

Pos logit contributions
Glass+0.958
 Ped+0.949
%:+0.881
 Forever+0.870
Ped+0.856
Neg logit contributions
acas-0.621
zag-0.555
henko-0.505
arial-0.493
ibaba-0.477
Token AFP
Token ID8916
Feature activation-8.01e-01

Pos logit contributions
 Ped+3.405
Glass+3.324
 Forever+2.954
%:+2.913
 PF+2.852
Neg logit contributions
acas-4.852
zag-4.515
henko-4.229
arial-4.197
ibaba-4.168
Token
Token ID198
Feature activation-7.86e-01

Pos logit contributions
Glass+0.461
 Ped+0.450
%:+0.394
 Forever+0.385
Ped+0.376
Neg logit contributions
acas-0.846
zag-0.787
henko-0.747
arial-0.739
ibaba-0.725
Token
Token ID198
Feature activation-5.64e-01

Pos logit contributions
Glass+0.481
 Ped+0.470
%:+0.414
 Forever+0.406
Ped+0.398
Neg logit contributions
acas-0.807
zag-0.747
henko-0.709
arial-0.697
ibaba-0.691
TokenThe
Token ID464
Feature activation+1.89e-01

Pos logit contributions
Glass+0.381
 Ped+0.371
%:+0.333
 Forever+0.325
Ped+0.321
Neg logit contributions
acas-0.542
zag-0.500
henko-0.472
arial-0.465
ibaba-0.457
Token Bank
Token ID5018
Feature activation+1.92e+00

Pos logit contributions
acas+0.179
zag+0.165
henko+0.156
arial+0.153
ibaba+0.150
Neg logit contributions
Glass-0.130
 Ped-0.127
%:-0.114
 Forever-0.111
Ped-0.109
Tokenported
Token ID9213
Feature activation+7.72e-01

Pos logit contributions
acas+0.115
zag+0.106
henko+0.099
arial+0.098
ibaba+0.096
Neg logit contributions
Glass-0.094
 Ped-0.092
%:-0.083
 Forever-0.082
Ped-0.080
Token License
Token ID13789
Feature activation+1.54e+00

Pos logit contributions
acas+0.683
zag+0.626
henko+0.588
arial+0.579
ibaba+0.568
Neg logit contributions
Glass-0.578
 Ped-0.569
%:-0.517
 Forever-0.506
Ped-0.495
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
acas+1.436
zag+1.323
henko+1.247
arial+1.230
ibaba+1.204
Neg logit contributions
Glass-1.073
 Ped-1.050
%:-0.946
 Forever-0.925
Ped-0.907
Token<|endoftext|>
Token ID50256
Feature activation+6.10e-01

Pos logit contributions
acas+0.127
zag+0.117
henko+0.111
arial+0.109
ibaba+0.107
Neg logit contributions
Glass-0.084
 Ped-0.082
%:-0.073
 Forever-0.072
Ped-0.070
TokenImage
Token ID5159
Feature activation-9.60e-01

Pos logit contributions
acas+0.594
zag+0.549
henko+0.517
arial+0.512
ibaba+0.499
Neg logit contributions
Glass-0.399
 Ped-0.394
%:-0.351
 Forever-0.344
Ped-0.333
Token copyright
Token ID6634
Feature activation-4.96e+00

Pos logit contributions
Glass+0.948
 Ped+0.938
%:+0.871
 Forever+0.860
Ped+0.846
Neg logit contributions
acas-0.615
zag-0.550
henko-0.500
arial-0.489
ibaba-0.473
Token AP
Token ID3486
Feature activation-7.76e-01

Pos logit contributions
 Ped+3.322
Glass+3.252
 Forever+2.886
%:+2.853
 PF+2.787
Neg logit contributions
acas-4.713
zag-4.382
henko-4.105
arial-4.075
ibaba-4.043
Token Image
Token ID7412
Feature activation-2.54e+00

Pos logit contributions
Glass+0.448
 Ped+0.437
%:+0.383
 Forever+0.373
Ped+0.365
Neg logit contributions
acas-0.819
zag-0.762
henko-0.723
arial-0.714
ibaba-0.700
Token caption
Token ID8305
Feature activation-3.48e+00

Pos logit contributions
Glass+2.256
 Ped+2.245
%:+2.054
 Forever+2.031
Ped+1.991
Neg logit contributions
acas-1.869
zag-1.710
henko-1.558
arial-1.513
omore-1.513
Token Peace
Token ID12689
Feature activation+1.64e+00

Pos logit contributions
 Ped+2.266
Glass+2.226
 Forever+1.952
%:+1.943
Ped+1.887
Neg logit contributions
acas-3.406
zag-3.176
henko-2.969
arial-2.950
ibaba-2.906
Token talks
Token ID6130
Feature activation+7.26e-01

Pos logit contributions
acas+1.406
zag+1.282
henko+1.204
arial+1.180
ibaba+1.152
Neg logit contributions
Glass-1.280
 Ped-1.249
%:-1.141
 Forever-1.117
Ped-1.099
Token.
Token ID13
Feature activation+3.65e-01

Pos logit contributions
Glass+0.227
 Ped+0.225
%:+0.202
 Forever+0.198
Ped+0.194
Neg logit contributions
acas-0.309
zag-0.283
henko-0.266
arial-0.262
ibaba-0.259
Token
Token ID447
Feature activation-4.50e-01

Pos logit contributions
acas+0.309
zag+0.282
henko+0.263
arial+0.259
ibaba+0.253
Neg logit contributions
Glass-0.288
 Ped-0.283
%:-0.258
 Forever-0.254
Ped-0.249
Token
Token ID251
Feature activation-1.58e-01

Pos logit contributions
Glass+0.338
 Ped+0.331
%:+0.300
 Forever+0.295
Ped+0.288
Neg logit contributions
acas-0.399
zag-0.365
henko-0.342
arial-0.338
ibaba-0.329
Token<|endoftext|>
Token ID50256
Feature activation+4.91e-01

Pos logit contributions
Glass+0.105
 Ped+0.103
%:+0.092
 Forever+0.090
Ped+0.088
Neg logit contributions
acas-0.154
zag-0.143
henko-0.135
arial-0.133
ibaba-0.130
TokenImage
Token ID5159
Feature activation-7.64e-01

Pos logit contributions
acas+0.477
zag+0.441
henko+0.416
arial+0.411
ibaba+0.401
Neg logit contributions
Glass-0.322
 Ped-0.317
%:-0.283
 Forever-0.277
Ped-0.269
Token copyright
Token ID6634
Feature activation-4.87e+00

Pos logit contributions
Glass+0.756
 Ped+0.748
%:+0.695
 Forever+0.686
Ped+0.675
Neg logit contributions
acas-0.488
zag-0.435
henko-0.396
arial-0.387
ibaba-0.374
Token publicity
Token ID19403
Feature activation-9.75e-01

Pos logit contributions
 Ped+3.251
Glass+3.182
 Forever+2.822
%:+2.790
 PF+2.728
Neg logit contributions
acas-4.647
zag-4.323
henko-4.049
arial-4.021
ibaba-3.991
Token Image
Token ID7412
Feature activation-2.37e+00

Pos logit contributions
Glass+0.623
 Ped+0.608
%:+0.534
 Forever+0.529
Ped+0.519
Neg logit contributions
acas-0.967
zag-0.898
henko-0.845
arial-0.839
ibaba-0.821
Token caption
Token ID8305
Feature activation-3.13e+00

Pos logit contributions
Glass+2.092
 Ped+2.087
%:+1.914
 Forever+1.891
Ped+1.848
Neg logit contributions
acas-1.740
zag-1.598
henko-1.459
arial-1.410
ibaba-1.403
Token The
Token ID383
Feature activation+6.43e-01

Pos logit contributions
 Ped+1.976
Glass+1.958
 Forever+1.709
%:+1.700
Ped+1.641
Neg logit contributions
acas-3.123
zag-2.913
henko-2.737
arial-2.702
ibaba-2.667
Token Greeks
Token ID25059
Feature activation-7.50e-01

Pos logit contributions
acas+0.572
zag+0.525
henko+0.492
arial+0.485
ibaba+0.474
Neg logit contributions
Glass-0.479
 Ped-0.468
%:-0.425
 Forever-0.416
Ped-0.409
Token not
Token ID407
Feature activation-2.42e-01

Pos logit contributions
acas+1.363
zag+1.263
henko+1.191
arial+1.175
ibaba+1.151
Neg logit contributions
Glass-0.904
 Ped-0.880
%:-0.788
 Forever-0.767
Ped-0.754
Token trust
Token ID3774
Feature activation-1.26e+00

Pos logit contributions
Glass+0.197
 Ped+0.195
%:+0.178
 Forever+0.175
Ped+0.171
Neg logit contributions
acas-0.198
zag-0.180
henko-0.168
arial-0.165
ibaba-0.162
Token him
Token ID683
Feature activation-2.52e-01

Pos logit contributions
Glass+0.800
 Ped+0.788
%:+0.696
 Forever+0.687
Ped+0.666
Neg logit contributions
acas-1.256
zag-1.159
henko-1.098
arial-1.084
ibaba-1.065
Token,
Token ID11
Feature activation-8.48e-02

Pos logit contributions
Glass+0.174
 Ped+0.171
%:+0.153
 Forever+0.150
Ped+0.147
Neg logit contributions
acas-0.239
zag-0.220
henko-0.207
arial-0.204
ibaba-0.201
Token keep
Token ID1394
Feature activation-4.91e-02

Pos logit contributions
Glass+0.065
 Ped+0.064
%:+0.058
 Forever+0.057
Ped+0.056
Neg logit contributions
acas-0.074
zag-0.067
henko-0.063
arial-0.062
ibaba-0.061
Token away
Token ID1497
Feature activation-4.83e+00

Pos logit contributions
Glass+0.035
 Ped+0.034
%:+0.031
 Forever+0.030
Ped+0.030
Neg logit contributions
acas-0.045
zag-0.042
henko-0.039
arial-0.039
ibaba-0.038
Token from
Token ID422
Feature activation+3.21e-01

Pos logit contributions
Glass+3.068
 Ped+3.024
%:+2.654
 Forever+2.645
Ped+2.575
Neg logit contributions
acas-4.758
zag-4.404
henko-4.172
arial-4.099
ibaba-4.070
Token him
Token ID683
Feature activation-4.31e-01

Pos logit contributions
acas+0.285
zag+0.262
henko+0.246
arial+0.242
ibaba+0.237
Neg logit contributions
Glass-0.240
 Ped-0.235
%:-0.213
 Forever-0.209
Ped-0.205
Token,
Token ID11
Feature activation+1.52e-01

Pos logit contributions
Glass+0.292
 Ped+0.286
%:+0.256
 Forever+0.252
Ped+0.246
Neg logit contributions
acas-0.411
zag-0.380
henko-0.357
arial-0.353
ibaba-0.347
Token he
Token ID339
Feature activation-5.92e-01

Pos logit contributions
acas+0.132
zag+0.121
henko+0.113
arial+0.112
ibaba+0.109
Neg logit contributions
Glass-0.116
 Ped-0.114
%:-0.103
 Forever-0.102
Ped-0.100
Token shouldn
Token ID6584
Feature activation+2.83e-01

Pos logit contributions
Glass+0.408
 Ped+0.400
%:+0.358
 Forever+0.352
Ped+0.345
Neg logit contributions
acas-0.559
zag-0.514
henko-0.485
arial-0.477
ibaba-0.468
Token.
Token ID13
Feature activation+1.70e-01

Pos logit contributions
acas+0.012
zag+0.011
henko+0.010
arial+0.010
ibaba+0.010
Neg logit contributions
Glass-0.008
 Ped-0.008
%:-0.007
 Forever-0.007
Ped-0.007
Token
Token ID447
Feature activation-4.91e-03

Pos logit contributions
acas+0.161
zag+0.149
henko+0.140
arial+0.138
ibaba+0.136
Neg logit contributions
Glass-0.117
 Ped-0.115
%:-0.103
 Forever-0.102
Ped-0.099
Token
Token ID251
Feature activation+1.63e-01

Pos logit contributions
Glass+0.004
 Ped+0.004
%:+0.003
 Forever+0.003
Ped+0.003
Neg logit contributions
acas-0.004
zag-0.004
henko-0.004
arial-0.004
ibaba-0.003
Token<|endoftext|>
Token ID50256
Feature activation+5.01e-01

Pos logit contributions
acas+0.164
zag+0.151
henko+0.144
arial+0.142
ibaba+0.139
Neg logit contributions
Glass-0.102
 Ped-0.100
%:-0.089
 Forever-0.087
Ped-0.085
TokenImage
Token ID5159
Feature activation-8.04e-01

Pos logit contributions
acas+0.488
zag+0.451
henko+0.425
arial+0.420
ibaba+0.410
Neg logit contributions
Glass-0.328
 Ped-0.323
%:-0.288
 Forever-0.282
Ped-0.274
Token copyright
Token ID6634
Feature activation-4.78e+00

Pos logit contributions
Glass+0.794
 Ped+0.785
%:+0.730
 Forever+0.720
Ped+0.709
Neg logit contributions
acas-0.516
zag-0.461
henko-0.419
arial-0.410
ibaba-0.397
Token Deadline
Token ID35954
Feature activation+8.69e-01

Pos logit contributions
 Ped+3.188
Glass+3.124
 Forever+2.770
%:+2.739
 PF+2.673
Neg logit contributions
acas-4.567
zag-4.246
henko-3.980
arial-3.952
ibaba-3.922
Token
Token ID198
Feature activation-7.79e-01

Pos logit contributions
acas+0.879
zag+0.815
henko+0.771
arial+0.760
ibaba+0.746
Neg logit contributions
Glass-0.539
 Ped-0.524
%:-0.470
 Forever-0.454
Ped-0.445
Token
Token ID198
Feature activation-5.29e-01

Pos logit contributions
Glass+0.481
 Ped+0.470
%:+0.415
 Forever+0.406
Ped+0.398
Neg logit contributions
acas-0.796
zag-0.737
henko-0.699
arial-0.688
ibaba-0.680
TokenPolice
Token ID9039
Feature activation-1.75e-02

Pos logit contributions
Glass+0.351
 Ped+0.343
%:+0.307
 Forever+0.300
Ped+0.293
Neg logit contributions
acas-0.514
zag-0.475
henko-0.448
arial-0.442
ibaba-0.432
Token have
Token ID423
Feature activation-5.46e-01

Pos logit contributions
Glass+0.013
 Ped+0.013
%:+0.012
 Forever+0.012
Ped+0.011
Neg logit contributions
acas-0.015
zag-0.014
henko-0.013
arial-0.013
ibaba-0.013
Token Hide
Token ID10415
Feature activation-1.29e+00

Pos logit contributions
Glass+0.475
 Ped+0.468
%:+0.422
 Forever+0.416
Ped+0.404
Neg logit contributions
acas-0.568
zag-0.520
henko-0.488
arial-0.481
ibaba-0.472
Token Caption
Token ID11260
Feature activation-4.70e+00

Pos logit contributions
Glass+1.084
 Ped+1.080
%:+0.984
 Forever+0.971
Ped+0.950
Neg logit contributions
acas-1.040
zag-0.940
henko-0.869
arial-0.853
ibaba-0.847
Token 7
Token ID767
Feature activation+1.10e+00

Pos logit contributions
 Ped+2.967
Glass+2.945
 Forever+2.580
%:+2.548
 PF+2.506
Neg logit contributions
acas-4.701
zag-4.328
henko-4.143
ibaba-4.107
arial-4.049
Token of
Token ID286
Feature activation-1.78e-01

Pos logit contributions
acas+0.944
zag+0.865
henko+0.811
arial+0.799
ibaba+0.776
Neg logit contributions
Glass-0.841
 Ped-0.823
%:-0.751
 Forever-0.735
Ped-0.724
Token 15
Token ID1315
Feature activation-4.35e-01

Pos logit contributions
Glass+0.126
 Ped+0.123
%:+0.111
 Forever+0.109
Ped+0.106
Neg logit contributions
acas-0.166
zag-0.153
henko-0.144
arial-0.142
ibaba-0.139
Token Photos
Token ID9434
Feature activation-4.77e+00

Pos logit contributions
Glass+0.300
 Ped+0.294
%:+0.264
 Forever+0.258
Ped+0.252
Neg logit contributions
acas-0.413
zag-0.381
henko-0.358
arial-0.354
ibaba-0.348
Token:
Token ID25
Feature activation+4.88e-02

Pos logit contributions
Glass+1.778
 Ped+1.758
%:+1.515
 Forever+1.385
Ped+1.273
Neg logit contributions
acas-6.004
zag-5.601
ibaba-5.407
henko-5.366
omore-5.320
Token Carly
Token ID35982
Feature activation+1.62e+00

Pos logit contributions
acas+0.039
zag+0.035
henko+0.033
arial+0.032
ibaba+0.031
Neg logit contributions
Glass-0.041
 Ped-0.040
%:-0.037
 Forever-0.036
Ped-0.036
Token Fiorina
Token ID49028
Feature activation+1.48e-02

Pos logit contributions
acas+1.077
zag+0.955
henko+0.876
arial+0.858
ibaba+0.824
Neg logit contributions
Glass-1.569
 Ped-1.530
%:-1.424
 Forever-1.397
Ped-1.392
Token's
Token ID338
Feature activation+2.24e-01

Pos logit contributions
acas+0.013
zag+0.012
henko+0.011
arial+0.011
ibaba+0.011
Neg logit contributions
Glass-0.012
 Ped-0.011
%:-0.010
 Forever-0.010
Ped-0.010
Token political
Token ID1964
Feature activation-5.38e-01

Pos logit contributions
acas+0.211
zag+0.194
henko+0.183
arial+0.179
ibaba+0.178
Neg logit contributions
Glass-0.155
 Ped-0.153
%:-0.137
 Forever-0.134
Ped-0.132
Token Hide
Token ID10415
Feature activation+1.98e-01

Pos logit contributions
Glass+0.025
 Ped+0.024
%:+0.022
 Forever+0.021
Ped+0.021
Neg logit contributions
acas-0.039
zag-0.036
henko-0.034
arial-0.034
ibaba-0.033
Token Caption
Token ID11260
Feature activation-3.80e+00

Pos logit contributions
acas+0.147
zag+0.132
henko+0.122
arial+0.120
ibaba+0.116
Neg logit contributions
Glass-0.176
 Ped-0.173
%:-0.160
 Forever-0.157
Ped-0.155
Token 4
Token ID604
Feature activation+5.38e-01

Pos logit contributions
Glass+2.625
 Ped+2.603
 Forever+2.338
%:+2.280
 PF+2.229
Neg logit contributions
acas-3.610
zag-3.285
henko-3.137
ibaba-3.067
arial-3.048
Token of
Token ID286
Feature activation-8.38e-01

Pos logit contributions
acas+0.473
zag+0.433
henko+0.406
arial+0.400
ibaba+0.391
Neg logit contributions
Glass-0.406
 Ped-0.398
%:-0.361
 Forever-0.354
Ped-0.348
Token 15
Token ID1315
Feature activation+1.83e-02

Pos logit contributions
Glass+0.602
 Ped+0.594
%:+0.530
 Forever+0.527
Ped+0.511
Neg logit contributions
acas-0.774
zag-0.707
henko-0.669
arial-0.655
ibaba-0.651
Token Photos
Token ID9434
Feature activation-4.72e+00

Pos logit contributions
acas+0.017
zag+0.016
henko+0.015
arial+0.015
ibaba+0.014
Neg logit contributions
Glass-0.013
 Ped-0.013
%:-0.011
 Forever-0.011
Ped-0.011
Token:
Token ID25
Feature activation-2.26e-01

Pos logit contributions
Glass+1.778
 Ped+1.771
%:+1.519
 Forever+1.431
 PF+1.290
Neg logit contributions
acas-5.912
zag-5.506
ibaba-5.320
henko-5.316
arial-5.253
Token Carly
Token ID35982
Feature activation+2.21e+00

Pos logit contributions
Glass+0.153
 Ped+0.150
%:+0.134
 Forever+0.132
Ped+0.128
Neg logit contributions
acas-0.218
zag-0.201
henko-0.190
arial-0.187
ibaba-0.184
Token Fiorina
Token ID49028
Feature activation+1.31e+00

Pos logit contributions
acas+1.538
zag+1.359
henko+1.253
arial+1.221
ibaba+1.176
Neg logit contributions
Glass-2.080
 Ped-2.022
%:-1.887
 Forever-1.861
Ped-1.841
Token's
Token ID338
Feature activation-1.46e-01

Pos logit contributions
acas+1.131
zag+1.035
henko+0.967
arial+0.954
ibaba+0.930
Neg logit contributions
Glass-1.006
 Ped-0.980
%:-0.893
 Forever-0.874
Ped-0.865
Token political
Token ID1964
Feature activation-8.21e-01

Pos logit contributions
Glass+0.113
 Ped+0.111
%:+0.101
 Forever+0.099
Ped+0.097
Neg logit contributions
acas-0.126
zag-0.115
henko-0.108
arial-0.106
ibaba-0.104
Token 20
Token ID1160
Feature activation+1.30e+00

Pos logit contributions
acas+0.031
zag+0.029
henko+0.027
arial+0.026
ibaba+0.026
Neg logit contributions
Glass-0.024
 Ped-0.023
%:-0.021
 Forever-0.021
Ped-0.020
Token,
Token ID11
Feature activation-5.16e-01

Pos logit contributions
acas+1.174
zag+1.076
henko+1.011
arial+0.996
ibaba+0.979
Neg logit contributions
Glass-0.957
 Ped-0.942
%:-0.850
 Forever-0.834
Ped-0.817
Token 2015
Token ID1853
Feature activation-1.13e+00

Pos logit contributions
Glass+0.383
 Ped+0.378
%:+0.337
 Forever+0.334
Ped+0.326
Neg logit contributions
acas-0.462
zag-0.423
henko-0.397
arial-0.392
ibaba-0.384
Token.
Token ID13
Feature activation-1.25e+00

Pos logit contributions
Glass+0.786
 Ped+0.766
%:+0.691
 Forever+0.675
Ped+0.664
Neg logit contributions
acas-1.062
zag-0.979
henko-0.921
arial-0.909
ibaba-0.888
Token Hide
Token ID10415
Feature activation-1.40e+00

Pos logit contributions
Glass+0.936
 Ped+0.925
%:+0.833
 Forever+0.824
Ped+0.799
Neg logit contributions
acas-1.109
zag-1.016
henko-0.955
arial-0.938
ibaba-0.926
Token Caption
Token ID11260
Feature activation-4.70e+00

Pos logit contributions
Glass+1.170
 Ped+1.165
%:+1.061
 Forever+1.049
Ped+1.025
Neg logit contributions
acas-1.120
zag-1.012
henko-0.937
arial-0.919
ibaba-0.913
Token 8
Token ID807
Feature activation+1.11e+00

Pos logit contributions
 Ped+2.588
Glass+2.528
%:+2.195
 Forever+2.189
 Skull+2.082
Neg logit contributions
acas-5.062
zag-4.788
henko-4.525
ibaba-4.520
omore-4.444
Token of
Token ID286
Feature activation-2.80e-01

Pos logit contributions
acas+0.964
zag+0.883
henko+0.827
arial+0.815
ibaba+0.794
Neg logit contributions
Glass-0.846
 Ped-0.828
%:-0.754
 Forever-0.739
Ped-0.727
Token 15
Token ID1315
Feature activation-2.85e-01

Pos logit contributions
Glass+0.195
 Ped+0.192
%:+0.172
 Forever+0.169
Ped+0.165
Neg logit contributions
acas-0.263
zag-0.242
henko-0.228
arial-0.224
ibaba-0.221
Token Photos
Token ID9434
Feature activation-4.52e+00

Pos logit contributions
Glass+0.196
 Ped+0.192
%:+0.172
 Forever+0.169
Ped+0.165
Neg logit contributions
acas-0.271
zag-0.251
henko-0.236
arial-0.233
ibaba-0.229
Token:
Token ID25
Feature activation+2.38e-01

Pos logit contributions
Glass+1.711
 Ped+1.686
%:+1.450
 Forever+1.333
Ped+1.229
Neg logit contributions
acas-5.674
zag-5.294
ibaba-5.100
henko-5.070
omore-5.021
Token Women
Token ID6926
Feature activation+7.94e-01

Pos logit contributions
Glass+0.194
 Ped+0.187
%:+0.168
Ped+0.161
 Forever+0.160
Neg logit contributions
acas-0.327
zag-0.302
henko-0.287
arial-0.283
ibaba-0.278
Token in
Token ID287
Feature activation-1.03e+00

Pos logit contributions
acas+0.726
zag+0.665
henko+0.627
arial+0.617
ibaba+0.607
Neg logit contributions
Glass-0.571
 Ped-0.564
%:-0.507
 Forever-0.500
Ped-0.486
Token politics
Token ID4819
Feature activation-6.41e-01

Pos logit contributions
Glass+0.706
 Ped+0.702
%:+0.622
 Forever+0.617
 PF+0.594
Neg logit contributions
acas-0.960
zag-0.885
henko-0.842
arial-0.818
ibaba-0.808
Token.
Token ID13
Feature activation-6.37e-01

Pos logit contributions
Glass+0.440
 Ped+0.436
%:+0.389
 Forever+0.385
Ped+0.371
Neg logit contributions
acas-0.604
zag-0.555
henko-0.522
arial-0.515
ibaba-0.514
Token Hide
Token ID10415
Feature activation-1.29e+00

Pos logit contributions
Glass+0.475
 Ped+0.468
%:+0.422
 Forever+0.416
Ped+0.404
Neg logit contributions
acas-0.568
zag-0.520
henko-0.488
arial-0.481
ibaba-0.472
Token Caption
Token ID11260
Feature activation-4.70e+00

Pos logit contributions
Glass+1.084
 Ped+1.080
%:+0.984
 Forever+0.971
Ped+0.950
Neg logit contributions
acas-1.040
zag-0.940
henko-0.869
arial-0.853
ibaba-0.847
Token 7
Token ID767
Feature activation+1.10e+00

Pos logit contributions
 Ped+2.967
Glass+2.945
 Forever+2.580
%:+2.548
 PF+2.506
Neg logit contributions
acas-4.701
zag-4.328
henko-4.143
ibaba-4.107
arial-4.049
Token of
Token ID286
Feature activation-1.78e-01

Pos logit contributions
acas+0.944
zag+0.865
henko+0.811
arial+0.799
ibaba+0.776
Neg logit contributions
Glass-0.841
 Ped-0.823
%:-0.751
 Forever-0.735
Ped-0.724
Token 15
Token ID1315
Feature activation-4.35e-01

Pos logit contributions
Glass+0.126
 Ped+0.123
%:+0.111
 Forever+0.109
Ped+0.106
Neg logit contributions
acas-0.166
zag-0.153
henko-0.144
arial-0.142
ibaba-0.139
Token Photos
Token ID9434
Feature activation-4.77e+00

Pos logit contributions
Glass+0.300
 Ped+0.294
%:+0.264
 Forever+0.258
Ped+0.252
Neg logit contributions
acas-0.413
zag-0.381
henko-0.358
arial-0.354
ibaba-0.348
Token:
Token ID25
Feature activation+4.88e-02

Pos logit contributions
Glass+1.778
 Ped+1.758
%:+1.515
 Forever+1.385
Ped+1.273
Neg logit contributions
acas-6.004
zag-5.601
ibaba-5.407
henko-5.366
omore-5.320
Token unsupported
Token ID24222
Feature activation-8.27e-01

Pos logit contributions
acas+0.197
zag+0.176
henko+0.161
arial+0.158
ibaba+0.153
Neg logit contributions
Glass-0.282
 Ped-0.277
%:-0.257
 Forever-0.253
Ped-0.250
Token on
Token ID319
Feature activation+1.19e+00

Pos logit contributions
Glass+0.593
 Ped+0.588
%:+0.525
 Forever+0.517
Ped+0.506
Neg logit contributions
acas-0.758
zag-0.698
henko-0.650
ibaba-0.646
arial-0.642
Token your
Token ID534
Feature activation+8.06e-01

Pos logit contributions
acas+1.428
zag+1.340
henko+1.282
arial+1.267
ibaba+1.246
Neg logit contributions
Glass-0.513
 Ped-0.489
%:-0.412
 Forever-0.392
Ped-0.387
Token device
Token ID3335
Feature activation+4.74e-01

Pos logit contributions
acas+0.882
zag+0.823
henko+0.782
arial+0.772
ibaba+0.761
Neg logit contributions
Glass-0.436
 Ped-0.426
%:-0.370
 Forever-0.358
Ped-0.350
Token Media
Token ID6343
Feature activation-2.98e+00

Pos logit contributions
acas+0.423
zag+0.387
henko+0.365
arial+0.358
ibaba+0.350
Neg logit contributions
Glass-0.350
 Ped-0.339
%:-0.310
 Forever-0.302
Ped-0.299
Token caption
Token ID8305
Feature activation-4.64e+00

Pos logit contributions
 Ped+2.630
Glass+2.616
%:+2.381
 Forever+2.365
Ped+2.304
Neg logit contributions
acas-2.193
zag-2.031
henko-1.838
arial-1.827
ibaba-1.794
Token Nigel
Token ID28772
Feature activation+7.22e-01

Pos logit contributions
 Ped+2.992
Glass+2.915
 Forever+2.567
%:+2.544
 PF+2.474
Neg logit contributions
acas-4.561
zag-4.276
henko-3.996
arial-3.964
ibaba-3.927
Token Farage
Token ID33904
Feature activation-2.30e-01

Pos logit contributions
acas+0.607
zag+0.554
henko+0.517
arial+0.509
ibaba+0.497
Neg logit contributions
Glass-0.572
 Ped-0.562
%:-0.512
 Forever-0.503
Ped-0.494
Token:
Token ID25
Feature activation+5.88e-01

Pos logit contributions
Glass+0.151
 Ped+0.148
%:+0.132
 Forever+0.129
Ped+0.126
Neg logit contributions
acas-0.224
zag-0.207
henko-0.195
arial-0.193
ibaba-0.190
Token "
Token ID366
Feature activation+8.03e-01

Pos logit contributions
acas+0.522
zag+0.479
henko+0.451
arial+0.443
ibaba+0.432
Neg logit contributions
Glass-0.437
 Ped-0.425
%:-0.387
 Forever-0.378
Ped-0.373
TokenLord
Token ID22438
Feature activation+3.86e-01

Pos logit contributions
acas+0.744
zag+0.688
henko+0.647
arial+0.638
ibaba+0.619
Neg logit contributions
Glass-0.555
 Ped-0.549
%:-0.496
 Forever-0.485
 Skull-0.469
Token Hide
Token ID10415
Feature activation-9.02e-01

Pos logit contributions
acas+0.024
zag+0.022
henko+0.020
arial+0.020
ibaba+0.020
Neg logit contributions
Glass-0.021
 Ped-0.021
%:-0.019
 Forever-0.018
Ped-0.018
Token Caption
Token ID11260
Feature activation-3.95e+00

Pos logit contributions
Glass+0.762
 Ped+0.760
%:+0.692
 Forever+0.684
Ped+0.668
Neg logit contributions
acas-0.718
zag-0.649
henko-0.600
arial-0.589
ibaba-0.584
Token 14
Token ID1478
Feature activation+1.18e+00

Pos logit contributions
Glass+2.651
 Ped+2.648
 Forever+2.356
%:+2.350
 Skull+2.257
Neg logit contributions
acas-3.789
zag-3.492
henko-3.286
ibaba-3.264
omore-3.198
Token of
Token ID286
Feature activation-2.03e-01

Pos logit contributions
acas+1.024
zag+0.937
henko+0.878
arial+0.865
ibaba+0.843
Neg logit contributions
Glass-0.898
 Ped-0.879
%:-0.800
 Forever-0.784
Ped-0.771
Token 15
Token ID1315
Feature activation-7.86e-01

Pos logit contributions
Glass+0.142
 Ped+0.140
%:+0.125
 Forever+0.123
Ped+0.120
Neg logit contributions
acas-0.190
zag-0.175
henko-0.165
arial-0.162
ibaba-0.160
Token Photos
Token ID9434
Feature activation-4.57e+00

Pos logit contributions
Glass+0.534
 Ped+0.526
%:+0.469
 Forever+0.460
Ped+0.448
Neg logit contributions
acas-0.754
zag-0.698
henko-0.655
arial-0.647
ibaba-0.639
Token:
Token ID25
Feature activation+1.02e-01

Pos logit contributions
Glass+1.734
 Ped+1.719
%:+1.469
 Forever+1.356
Ped+1.254
Neg logit contributions
acas-5.730
zag-5.351
ibaba-5.150
henko-5.118
omore-5.070
Token Carly
Token ID35982
Feature activation+1.67e+00

Pos logit contributions
acas+0.081
zag+0.073
henko+0.068
arial+0.067
ibaba+0.065
Neg logit contributions
Glass-0.086
 Ped-0.084
%:-0.077
 Forever-0.076
Ped-0.075
Token Fiorina
Token ID49028
Feature activation+1.58e-01

Pos logit contributions
acas+1.112
zag+0.988
henko+0.906
arial+0.888
ibaba+0.853
Neg logit contributions
Glass-1.608
 Ped-1.569
%:-1.460
 Forever-1.433
Ped-1.426
Token's
Token ID338
Feature activation+3.83e-01

Pos logit contributions
acas+0.134
zag+0.122
henko+0.114
arial+0.112
ibaba+0.110
Neg logit contributions
Glass-0.124
 Ped-0.122
%:-0.111
 Forever-0.109
Ped-0.107
Token political
Token ID1964
Feature activation-6.28e-01

Pos logit contributions
acas+0.357
zag+0.328
henko+0.309
arial+0.304
ibaba+0.300
Neg logit contributions
Glass-0.269
 Ped-0.265
%:-0.237
 Forever-0.232
Ped-0.228
Token energy
Token ID2568
Feature activation-8.59e-01

Pos logit contributions
Glass+0.012
 Ped+0.011
%:+0.010
 Forever+0.010
Ped+0.010
Neg logit contributions
acas-0.013
zag-0.012
henko-0.012
arial-0.011
ibaba-0.011
Token goals
Token ID4661
Feature activation-6.06e-01

Pos logit contributions
Glass+0.605
 Ped+0.592
%:+0.533
 Forever+0.522
Ped+0.513
Neg logit contributions
acas-0.798
zag-0.735
henko-0.692
arial-0.682
ibaba-0.668
Token.
Token ID13
Feature activation-4.15e-01

Pos logit contributions
Glass+0.404
 Ped+0.398
%:+0.353
 Forever+0.350
Ped+0.340
Neg logit contributions
acas-0.585
zag-0.539
henko-0.508
arial-0.503
ibaba-0.494
Token<|endoftext|>
Token ID50256
Feature activation+6.03e-01

Pos logit contributions
Glass+0.263
 Ped+0.256
%:+0.228
 Forever+0.222
Ped+0.218
Neg logit contributions
acas-0.416
zag-0.385
henko-0.365
arial-0.360
ibaba-0.353
TokenMedia
Token ID13152
Feature activation-1.35e+00

Pos logit contributions
acas+0.587
zag+0.543
henko+0.511
arial+0.505
ibaba+0.493
Neg logit contributions
Glass-0.394
 Ped-0.389
%:-0.347
 Forever-0.340
Ped-0.329
Token playback
Token ID16388
Feature activation-4.56e+00

Pos logit contributions
Glass+1.084
 Ped+1.066
%:+0.969
 Forever+0.955
Ped+0.939
Neg logit contributions
acas-1.121
zag-1.028
henko-0.961
arial-0.951
ibaba-0.917
Token is
Token ID318
Feature activation+2.93e-01

Pos logit contributions
 Ped+2.596
Glass+2.516
 Forever+2.177
%:+2.171
buffer+2.126
Neg logit contributions
acas-4.798
zag-4.516
henko-4.207
arial-4.201
ibaba-4.196
Token unsupported
Token ID24222
Feature activation-8.27e-01

Pos logit contributions
acas+0.197
zag+0.176
henko+0.161
arial+0.158
ibaba+0.153
Neg logit contributions
Glass-0.282
 Ped-0.277
%:-0.257
 Forever-0.253
Ped-0.250
Token on
Token ID319
Feature activation+1.19e+00

Pos logit contributions
Glass+0.593
 Ped+0.588
%:+0.525
 Forever+0.517
Ped+0.506
Neg logit contributions
acas-0.758
zag-0.698
henko-0.650
ibaba-0.646
arial-0.642
Token your
Token ID534
Feature activation+8.06e-01

Pos logit contributions
acas+1.428
zag+1.340
henko+1.282
arial+1.267
ibaba+1.246
Neg logit contributions
Glass-0.513
 Ped-0.489
%:-0.412
 Forever-0.392
Ped-0.387
Token device
Token ID3335
Feature activation+4.74e-01

Pos logit contributions
acas+0.882
zag+0.823
henko+0.782
arial+0.772
ibaba+0.761
Neg logit contributions
Glass-0.436
 Ped-0.426
%:-0.370
 Forever-0.358
Ped-0.350
Token Hide
Token ID10415
Feature activation-9.57e-01

Pos logit contributions
Glass+0.166
 Ped+0.164
%:+0.148
 Forever+0.146
Ped+0.142
Neg logit contributions
acas-0.193
zag-0.177
henko-0.166
arial-0.163
ibaba-0.160
Token Caption
Token ID11260
Feature activation-4.29e+00

Pos logit contributions
Glass+0.808
 Ped+0.805
%:+0.733
 Forever+0.724
Ped+0.709
Neg logit contributions
acas-0.763
zag-0.689
henko-0.638
arial-0.625
ibaba-0.620
Token 11
Token ID1367
Feature activation+1.28e+00

Pos logit contributions
Glass+3.076
 Ped+3.063
 Forever+2.738
%:+2.685
 PF+2.654
Neg logit contributions
acas-3.948
zag-3.592
henko-3.390
ibaba-3.343
omore-3.328
Token of
Token ID286
Feature activation-7.99e-02

Pos logit contributions
acas+1.099
zag+1.007
henko+0.944
arial+0.931
ibaba+0.902
Neg logit contributions
Glass-0.984
 Ped-0.963
%:-0.878
 Forever-0.860
Ped-0.846
Token 15
Token ID1315
Feature activation-7.84e-01

Pos logit contributions
Glass+0.056
 Ped+0.055
%:+0.050
 Forever+0.049
Ped+0.048
Neg logit contributions
acas-0.074
zag-0.068
henko-0.064
arial-0.063
ibaba-0.062
Token Photos
Token ID9434
Feature activation-4.54e+00

Pos logit contributions
Glass+0.534
 Ped+0.525
%:+0.469
 Forever+0.459
Ped+0.447
Neg logit contributions
acas-0.751
zag-0.695
henko-0.652
arial-0.644
ibaba-0.636
Token:
Token ID25
Feature activation+2.14e-01

Pos logit contributions
Glass+1.726
 Ped+1.705
%:+1.461
 Forever+1.347
Ped+1.245
Neg logit contributions
acas-5.698
zag-5.317
ibaba-5.116
henko-5.086
omore-5.039
Token Carly
Token ID35982
Feature activation+1.35e+00

Pos logit contributions
acas+0.169
zag+0.153
henko+0.142
arial+0.140
ibaba+0.136
Neg logit contributions
Glass-0.180
 Ped-0.177
%:-0.162
 Forever-0.159
Ped-0.157
Token Fiorina
Token ID49028
Feature activation-9.22e-02

Pos logit contributions
acas+0.906
zag+0.805
henko+0.739
arial+0.724
ibaba+0.696
Neg logit contributions
Glass-1.299
 Ped-1.269
%:-1.180
 Forever-1.159
Ped-1.152
Token's
Token ID338
Feature activation+7.34e-02

Pos logit contributions
Glass+0.072
 Ped+0.071
%:+0.064
 Forever+0.063
Ped+0.062
Neg logit contributions
acas-0.079
zag-0.072
henko-0.067
arial-0.066
ibaba-0.065
Token political
Token ID1964
Feature activation-6.86e-01

Pos logit contributions
acas+0.069
zag+0.064
henko+0.060
arial+0.059
ibaba+0.058
Neg logit contributions
Glass-0.051
 Ped-0.050
%:-0.045
 Forever-0.044
Ped-0.043
Token Hide
Token ID10415
Feature activation-1.40e+00

Pos logit contributions
Glass+0.936
 Ped+0.925
%:+0.833
 Forever+0.824
Ped+0.799
Neg logit contributions
acas-1.109
zag-1.016
henko-0.955
arial-0.938
ibaba-0.926
Token Caption
Token ID11260
Feature activation-4.70e+00

Pos logit contributions
Glass+1.170
 Ped+1.165
%:+1.061
 Forever+1.049
Ped+1.025
Neg logit contributions
acas-1.120
zag-1.012
henko-0.937
arial-0.919
ibaba-0.913
Token 8
Token ID807
Feature activation+1.11e+00

Pos logit contributions
 Ped+2.588
Glass+2.528
%:+2.195
 Forever+2.189
 Skull+2.082
Neg logit contributions
acas-5.062
zag-4.788
henko-4.525
ibaba-4.520
omore-4.444
Token of
Token ID286
Feature activation-2.80e-01

Pos logit contributions
acas+0.964
zag+0.883
henko+0.827
arial+0.815
ibaba+0.794
Neg logit contributions
Glass-0.846
 Ped-0.828
%:-0.754
 Forever-0.739
Ped-0.727
Token 15
Token ID1315
Feature activation-2.85e-01

Pos logit contributions
Glass+0.195
 Ped+0.192
%:+0.172
 Forever+0.169
Ped+0.165
Neg logit contributions
acas-0.263
zag-0.242
henko-0.228
arial-0.224
ibaba-0.221
Token Photos
Token ID9434
Feature activation-4.52e+00

Pos logit contributions
Glass+0.196
 Ped+0.192
%:+0.172
 Forever+0.169
Ped+0.165
Neg logit contributions
acas-0.271
zag-0.251
henko-0.236
arial-0.233
ibaba-0.229
Token:
Token ID25
Feature activation+2.38e-01

Pos logit contributions
Glass+1.711
 Ped+1.686
%:+1.450
 Forever+1.333
Ped+1.229
Neg logit contributions
acas-5.674
zag-5.294
ibaba-5.100
henko-5.070
omore-5.021
Token Carly
Token ID35982
Feature activation+1.58e+00

Pos logit contributions
acas+0.188
zag+0.170
henko+0.158
arial+0.156
ibaba+0.151
Neg logit contributions
Glass-0.201
 Ped-0.197
%:-0.181
 Forever-0.178
Ped-0.175
Token Fiorina
Token ID49028
Feature activation-8.58e-03

Pos logit contributions
acas+1.052
zag+0.933
henko+0.856
arial+0.839
ibaba+0.806
Neg logit contributions
Glass-1.529
 Ped-1.492
%:-1.389
 Forever-1.362
Ped-1.357
Token's
Token ID338
Feature activation+3.06e-01

Pos logit contributions
Glass+0.007
 Ped+0.007
%:+0.006
 Forever+0.006
Ped+0.006
Neg logit contributions
acas-0.007
zag-0.007
henko-0.006
arial-0.006
ibaba-0.006
Token political
Token ID1964
Feature activation-4.43e-01

Pos logit contributions
acas+0.287
zag+0.264
henko+0.249
arial+0.245
ibaba+0.242
Neg logit contributions
Glass-0.213
 Ped-0.210
%:-0.188
 Forever-0.184
Ped-0.181
Tokenin
Token ID259
Feature activation+3.94e-01

Pos logit contributions
Glass+0.047
 Ped+0.046
%:+0.041
 Forever+0.041
Ped+0.040
Neg logit contributions
acas-0.064
zag-0.059
henko-0.055
arial-0.054
ibaba-0.053
Token,
Token ID11
Feature activation+2.76e-01

Pos logit contributions
acas+0.357
zag+0.328
henko+0.310
arial+0.304
ibaba+0.299
Neg logit contributions
Glass-0.286
 Ped-0.281
%:-0.253
 Forever-0.249
Ped-0.243
Token Iowa
Token ID9406
Feature activation-4.64e-01

Pos logit contributions
acas+0.239
zag+0.219
henko+0.205
arial+0.201
ibaba+0.197
Neg logit contributions
Glass-0.212
 Ped-0.209
%:-0.189
 Forever-0.187
Ped-0.183
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
Glass+0.313
 Ped+0.306
%:+0.274
 Forever+0.269
Ped+0.263
Neg logit contributions
acas-0.445
zag-0.411
henko-0.388
arial-0.382
ibaba-0.375
Token Hide
Token ID10415
Feature activation-7.62e-01

Pos logit contributions
Glass+0.076
 Ped+0.075
%:+0.068
 Forever+0.067
Ped+0.065
Neg logit contributions
acas-0.089
zag-0.081
henko-0.076
arial-0.075
ibaba-0.074
Token Caption
Token ID11260
Feature activation-4.52e+00

Pos logit contributions
Glass+0.648
 Ped+0.643
%:+0.587
 Forever+0.580
Ped+0.569
Neg logit contributions
acas-0.600
zag-0.542
henko-0.503
arial-0.493
ibaba-0.486
Token 5
Token ID642
Feature activation+7.82e-01

Pos logit contributions
Glass+3.065
 Ped+3.039
 Forever+2.721
%:+2.646
 PF+2.637
Neg logit contributions
acas-4.312
zag-3.972
henko-3.806
omore-3.725
ibaba-3.711
Token of
Token ID286
Feature activation-5.08e-01

Pos logit contributions
acas+0.677
zag+0.620
henko+0.581
arial+0.573
ibaba+0.557
Neg logit contributions
Glass-0.598
 Ped-0.586
%:-0.533
 Forever-0.522
Ped-0.514
Token 15
Token ID1315
Feature activation-4.62e-01

Pos logit contributions
Glass+0.359
 Ped+0.351
%:+0.316
 Forever+0.310
Ped+0.303
Neg logit contributions
acas-0.473
zag-0.435
henko-0.410
arial-0.403
ibaba-0.396
Token Photos
Token ID9434
Feature activation-4.36e+00

Pos logit contributions
Glass+0.323
 Ped+0.316
%:+0.284
 Forever+0.278
Ped+0.273
Neg logit contributions
acas-0.433
zag-0.399
henko-0.375
arial-0.370
ibaba-0.363
Token:
Token ID25
Feature activation+2.06e-01

Pos logit contributions
Glass+1.675
 Ped+1.644
%:+1.411
 Forever+1.310
Ped+1.204
Neg logit contributions
acas-5.451
zag-5.088
ibaba-4.891
henko-4.889
omore-4.825
Token Irvine
Token ID37277
Feature activation-2.11e-01

Pos logit contributions
 Ped+0.653
Glass+0.651
 Forever+0.579
%:+0.573
 Skull+0.556
Neg logit contributions
acas-0.767
zag-0.704
henko-0.666
arial-0.654
ibaba-0.646
Token,
Token ID11
Feature activation+5.17e-01

Pos logit contributions
Glass+0.156
 Ped+0.153
%:+0.138
 Forever+0.136
Ped+0.133
Neg logit contributions
acas-0.188
zag-0.172
henko-0.162
arial-0.160
ibaba-0.156
Token California
Token ID3442
Feature activation-9.93e-01

Pos logit contributions
acas+0.487
zag+0.447
henko+0.422
arial+0.416
ibaba+0.409
Neg logit contributions
Glass-0.360
 Ped-0.353
%:-0.315
 Forever-0.312
Ped-0.304
Token.
Token ID13
Feature activation-4.34e-01

Pos logit contributions
Glass+0.683
 Ped+0.666
%:+0.600
 Forever+0.586
Ped+0.576
Neg logit contributions
acas-0.940
zag-0.866
henko-0.816
arial-0.805
ibaba-0.788
Token Hide
Token ID10415
Feature activation-1.12e+00

Pos logit contributions
Glass+0.334
 Ped+0.329
%:+0.299
 Forever+0.295
Ped+0.287
Neg logit contributions
acas-0.376
zag-0.344
henko-0.323
arial-0.317
ibaba-0.312
Token Caption
Token ID11260
Feature activation-4.51e+00

Pos logit contributions
Glass+0.937
 Ped+0.934
%:+0.851
 Forever+0.840
Ped+0.821
Neg logit contributions
acas-0.894
zag-0.808
henko-0.747
arial-0.733
ibaba-0.729
Token 9
Token ID860
Feature activation+1.45e+00

Pos logit contributions
 Ped+2.642
Glass+2.619
 Forever+2.312
%:+2.219
 PF+2.196
Neg logit contributions
acas-4.688
zag-4.379
henko-4.185
ibaba-4.113
omore-4.099
Token of
Token ID286
Feature activation-9.32e-02

Pos logit contributions
acas+1.246
zag+1.142
henko+1.070
arial+1.055
ibaba+1.020
Neg logit contributions
Glass-1.123
 Ped-1.098
%:-1.002
 Forever-0.981
Ped-0.966
Token 15
Token ID1315
Feature activation-5.69e-01

Pos logit contributions
Glass+0.065
 Ped+0.064
%:+0.058
 Forever+0.057
Ped+0.055
Neg logit contributions
acas-0.087
zag-0.080
henko-0.075
arial-0.074
ibaba-0.073
Token Photos
Token ID9434
Feature activation-4.48e+00

Pos logit contributions
Glass+0.388
 Ped+0.382
%:+0.341
 Forever+0.334
Ped+0.326
Neg logit contributions
acas-0.544
zag-0.503
henko-0.472
arial-0.466
ibaba-0.460
Token:
Token ID25
Feature activation+2.90e-01

Pos logit contributions
Glass+1.700
 Ped+1.677
%:+1.441
 Forever+1.325
Ped+1.226
Neg logit contributions
acas-5.619
zag-5.241
ibaba-5.047
henko-5.016
omore-4.968
Token Hide
Token ID10415
Feature activation-1.12e+00

Pos logit contributions
Glass+0.334
 Ped+0.329
%:+0.299
 Forever+0.295
Ped+0.287
Neg logit contributions
acas-0.376
zag-0.344
henko-0.323
arial-0.317
ibaba-0.312
Token Caption
Token ID11260
Feature activation-4.51e+00

Pos logit contributions
Glass+0.937
 Ped+0.934
%:+0.851
 Forever+0.840
Ped+0.821
Neg logit contributions
acas-0.894
zag-0.808
henko-0.747
arial-0.733
ibaba-0.729
Token 9
Token ID860
Feature activation+1.45e+00

Pos logit contributions
 Ped+2.642
Glass+2.619
 Forever+2.312
%:+2.219
 PF+2.196
Neg logit contributions
acas-4.688
zag-4.379
henko-4.185
ibaba-4.113
omore-4.099
Token of
Token ID286
Feature activation-9.32e-02

Pos logit contributions
acas+1.246
zag+1.142
henko+1.070
arial+1.055
ibaba+1.020
Neg logit contributions
Glass-1.123
 Ped-1.098
%:-1.002
 Forever-0.981
Ped-0.966
Token 15
Token ID1315
Feature activation-5.69e-01

Pos logit contributions
Glass+0.065
 Ped+0.064
%:+0.058
 Forever+0.057
Ped+0.055
Neg logit contributions
acas-0.087
zag-0.080
henko-0.075
arial-0.074
ibaba-0.073
Token Photos
Token ID9434
Feature activation-4.48e+00

Pos logit contributions
Glass+0.388
 Ped+0.382
%:+0.341
 Forever+0.334
Ped+0.326
Neg logit contributions
acas-0.544
zag-0.503
henko-0.472
arial-0.466
ibaba-0.460
Token:
Token ID25
Feature activation+2.90e-01

Pos logit contributions
Glass+1.700
 Ped+1.677
%:+1.441
 Forever+1.325
Ped+1.226
Neg logit contributions
acas-5.619
zag-5.241
ibaba-5.047
henko-5.016
omore-4.968
Token Carly
Token ID35982
Feature activation+1.64e+00

Pos logit contributions
acas+0.228
zag+0.207
henko+0.192
arial+0.189
ibaba+0.184
Neg logit contributions
Glass-0.245
 Ped-0.240
%:-0.221
 Forever-0.217
Ped-0.214
Token Fiorina
Token ID49028
Feature activation-2.19e-03

Pos logit contributions
acas+1.088
zag+0.965
henko+0.886
arial+0.868
ibaba+0.834
Neg logit contributions
Glass-1.580
 Ped-1.541
%:-1.434
 Forever-1.407
Ped-1.401
Token's
Token ID338
Feature activation+3.31e-01

Pos logit contributions
Glass+0.002
 Ped+0.002
%:+0.002
 Forever+0.002
Ped+0.001
Neg logit contributions
acas-0.002
zag-0.002
henko-0.002
arial-0.002
ibaba-0.002
Token political
Token ID1964
Feature activation-5.35e-01

Pos logit contributions
acas+0.308
zag+0.284
henko+0.267
arial+0.262
ibaba+0.259
Neg logit contributions
Glass-0.231
 Ped-0.228
%:-0.204
 Forever-0.200
Ped-0.197
Token Hide
Token ID10415
Feature activation-8.17e-01

Pos logit contributions
Glass+0.162
 Ped+0.160
%:+0.144
 Forever+0.142
Ped+0.138
Neg logit contributions
acas-0.193
zag-0.177
henko-0.166
arial-0.163
ibaba-0.161
Token Caption
Token ID11260
Feature activation-3.98e+00

Pos logit contributions
Glass+0.690
 Ped+0.688
%:+0.627
 Forever+0.619
Ped+0.605
Neg logit contributions
acas-0.650
zag-0.587
henko-0.543
arial-0.533
ibaba-0.529
Token 13
Token ID1511
Feature activation+8.88e-01

Pos logit contributions
Glass+2.471
 Ped+2.465
 Forever+2.169
%:+2.127
 Skull+2.056
Neg logit contributions
acas-4.044
zag-3.692
henko-3.531
ibaba-3.519
omore-3.439
Token of
Token ID286
Feature activation-2.16e-01

Pos logit contributions
acas+0.778
zag+0.712
henko+0.668
arial+0.657
ibaba+0.643
Neg logit contributions
Glass-0.674
 Ped-0.660
%:-0.599
 Forever-0.588
Ped-0.578
Token 15
Token ID1315
Feature activation-8.02e-01

Pos logit contributions
Glass+0.152
 Ped+0.149
%:+0.134
 Forever+0.131
Ped+0.128
Neg logit contributions
acas-0.202
zag-0.186
henko-0.175
arial-0.172
ibaba-0.170
Token Photos
Token ID9434
Feature activation-4.45e+00

Pos logit contributions
Glass+0.545
 Ped+0.537
%:+0.479
 Forever+0.469
Ped+0.457
Neg logit contributions
acas-0.770
zag-0.712
henko-0.669
arial-0.661
ibaba-0.653
Token:
Token ID25
Feature activation+1.60e-01

Pos logit contributions
Glass+1.701
 Ped+1.683
%:+1.438
 Forever+1.329
Ped+1.232
Neg logit contributions
acas-5.572
zag-5.202
ibaba-5.001
henko-4.974
omore-4.925
Token Carly
Token ID35982
Feature activation+1.57e+00

Pos logit contributions
acas+0.127
zag+0.115
henko+0.107
arial+0.105
ibaba+0.102
Neg logit contributions
Glass-0.135
 Ped-0.132
%:-0.121
 Forever-0.119
Ped-0.117
Token Fiorina
Token ID49028
Feature activation-1.62e-02

Pos logit contributions
acas+1.050
zag+0.933
henko+0.856
arial+0.838
ibaba+0.806
Neg logit contributions
Glass-1.515
 Ped-1.479
%:-1.376
 Forever-1.351
Ped-1.344
Token's
Token ID338
Feature activation+2.81e-01

Pos logit contributions
Glass+0.013
 Ped+0.012
%:+0.011
 Forever+0.011
Ped+0.011
Neg logit contributions
acas-0.014
zag-0.013
henko-0.012
arial-0.012
ibaba-0.011
Token political
Token ID1964
Feature activation-8.43e-01

Pos logit contributions
acas+0.263
zag+0.242
henko+0.228
arial+0.224
ibaba+0.222
Neg logit contributions
Glass-0.196
 Ped-0.193
%:-0.173
 Forever-0.169
Ped-0.166
Token Hide
Token ID10415
Feature activation-7.03e-01

Pos logit contributions
Glass+0.010
 Ped+0.010
%:+0.009
 Forever+0.009
Ped+0.009
Neg logit contributions
acas-0.011
zag-0.011
henko-0.010
arial-0.010
ibaba-0.009
Token Caption
Token ID11260
Feature activation-4.26e+00

Pos logit contributions
Glass+0.597
 Ped+0.593
%:+0.542
 Forever+0.535
Ped+0.524
Neg logit contributions
acas-0.556
zag-0.502
henko-0.465
arial-0.457
ibaba-0.450
Token 6
Token ID718
Feature activation+1.34e+00

Pos logit contributions
Glass+2.723
 Ped+2.701
 Forever+2.431
%:+2.375
 PF+2.306
Neg logit contributions
acas-4.231
zag-3.905
henko-3.684
arial-3.644
ibaba-3.628
Token of
Token ID286
Feature activation-3.78e-01

Pos logit contributions
acas+1.148
zag+1.052
henko+0.986
arial+0.972
ibaba+0.941
Neg logit contributions
Glass-1.032
 Ped-1.009
%:-0.921
 Forever-0.902
Ped-0.888
Token 15
Token ID1315
Feature activation-4.62e-01

Pos logit contributions
Glass+0.265
 Ped+0.260
%:+0.234
 Forever+0.229
Ped+0.224
Neg logit contributions
acas-0.352
zag-0.324
henko-0.305
arial-0.300
ibaba-0.296
Token Photos
Token ID9434
Feature activation-4.43e+00

Pos logit contributions
Glass+0.319
 Ped+0.312
%:+0.280
 Forever+0.274
Ped+0.268
Neg logit contributions
acas-0.437
zag-0.403
henko-0.379
arial-0.374
ibaba-0.368
Token:
Token ID25
Feature activation+1.44e-01

Pos logit contributions
Glass+1.682
 Ped+1.659
%:+1.427
 Forever+1.311
Ped+1.212
Neg logit contributions
acas-5.562
zag-5.191
ibaba-4.997
henko-4.972
omore-4.920
Token Carly
Token ID35982
Feature activation+1.91e+00

Pos logit contributions
acas+0.113
zag+0.103
henko+0.096
arial+0.094
ibaba+0.091
Neg logit contributions
Glass-0.122
 Ped-0.119
%:-0.110
 Forever-0.108
Ped-0.106
Token Fiorina
Token ID49028
Feature activation+2.81e-01

Pos logit contributions
acas+1.255
zag+1.111
henko+1.018
arial+0.998
ibaba+0.956
Neg logit contributions
Glass-1.864
 Ped-1.813
%:-1.691
 Forever-1.656
Ped-1.655
Token's
Token ID338
Feature activation+3.13e-01

Pos logit contributions
acas+0.240
zag+0.218
henko+0.205
arial+0.200
ibaba+0.198
Neg logit contributions
Glass-0.220
 Ped-0.217
%:-0.197
 Forever-0.194
Ped-0.190
Token political
Token ID1964
Feature activation-3.72e-01

Pos logit contributions
acas+0.294
zag+0.270
henko+0.255
arial+0.250
ibaba+0.248
Neg logit contributions
Glass-0.217
 Ped-0.214
%:-0.191
 Forever-0.187
Ped-0.184
Token mechanism
Token ID9030
Feature activation-3.44e-01

Pos logit contributions
Glass+0.417
 Ped+0.410
%:+0.371
 Forever+0.365
Ped+0.358
Neg logit contributions
acas-0.460
zag-0.421
henko-0.394
arial-0.386
ibaba-0.379
Token.
Token ID13
Feature activation+8.21e-01

Pos logit contributions
Glass+0.249
 Ped+0.245
%:+0.221
 Forever+0.216
Ped+0.211
Neg logit contributions
acas-0.314
zag-0.289
henko-0.272
arial-0.267
ibaba-0.263
Token When
Token ID1649
Feature activation-4.18e-01

Pos logit contributions
acas+0.849
zag+0.787
henko+0.747
arial+0.739
ibaba+0.724
Neg logit contributions
Glass-0.490
 Ped-0.473
%:-0.421
 Forever-0.408
Ped-0.402
Token a
Token ID257
Feature activation+9.38e-01

Pos logit contributions
Glass+0.283
 Ped+0.278
%:+0.249
 Forever+0.243
Ped+0.238
Neg logit contributions
acas-0.400
zag-0.370
henko-0.348
arial-0.342
ibaba-0.335
Token server
Token ID4382
Feature activation+1.90e+00

Pos logit contributions
acas+0.737
zag+0.668
henko+0.621
arial+0.609
ibaba+0.594
Neg logit contributions
Glass-0.797
 Ped-0.783
%:-0.718
 Forever-0.706
Ped-0.695
Token sends
Token ID12800
Feature activation+2.53e+00

Pos logit contributions
acas+1.674
zag+1.534
henko+1.438
arial+1.416
ibaba+1.384
Neg logit contributions
Glass-1.430
 Ped-1.400
%:-1.271
 Forever-1.246
Ped-1.225
Token a
Token ID257
Feature activation-8.30e-02

Pos logit contributions
acas+2.341
zag+2.150
henko+2.039
arial+2.004
ibaba+1.942
Neg logit contributions
Glass-1.780
 Ped-1.719
%:-1.558
 Forever-1.524
Ped-1.504
Token notification
Token ID14483
Feature activation-3.82e-02

Pos logit contributions
Glass+0.068
 Ped+0.067
%:+0.061
 Forever+0.060
Ped+0.058
Neg logit contributions
acas-0.068
zag-0.062
henko-0.058
arial-0.057
ibaba-0.056
Token to
Token ID284
Feature activation-2.01e-01

Pos logit contributions
Glass+0.027
 Ped+0.027
%:+0.024
 Forever+0.023
Ped+0.023
Neg logit contributions
acas-0.035
zag-0.032
henko-0.031
arial-0.030
ibaba-0.030
Token a
Token ID257
Feature activation+3.95e-01

Pos logit contributions
Glass+0.136
 Ped+0.133
%:+0.119
 Forever+0.116
Ped+0.114
Neg logit contributions
acas-0.194
zag-0.179
henko-0.169
arial-0.166
ibaba-0.163
Token client
Token ID5456
Feature activation+2.09e+00

Pos logit contributions
acas+0.297
zag+0.268
henko+0.248
arial+0.243
ibaba+0.237
Neg logit contributions
Glass-0.350
 Ped-0.344
%:-0.317
 Forever-0.312
Ped-0.307
Token growing
Token ID3957
Feature activation+6.70e-02

Pos logit contributions
acas+1.063
zag+0.973
henko+0.912
arial+0.898
ibaba+0.878
Neg logit contributions
Glass-0.920
 Ped-0.902
%:-0.818
 Forever-0.803
Ped-0.789
Token number
Token ID1271
Feature activation+7.48e-01

Pos logit contributions
acas+0.057
zag+0.052
henko+0.049
arial+0.048
ibaba+0.047
Neg logit contributions
Glass-0.052
 Ped-0.052
%:-0.046
 Forever-0.046
Ped-0.045
Token of
Token ID286
Feature activation-3.07e-01

Pos logit contributions
acas+0.657
zag+0.602
henko+0.564
arial+0.555
ibaba+0.543
Neg logit contributions
Glass-0.565
 Ped-0.554
%:-0.502
 Forever-0.493
Ped-0.485
Token r
Token ID374
Feature activation-4.44e-01

Pos logit contributions
Glass+0.221
 Ped+0.220
%:+0.195
 Forever+0.194
 PF+0.189
Neg logit contributions
acas-0.281
zag-0.258
henko-0.243
arial-0.238
ibaba-0.236
Tokenumb
Token ID2178
Feature activation+7.97e-01

Pos logit contributions
Glass+0.327
 Ped+0.322
%:+0.288
 Forever+0.283
Ped+0.281
Neg logit contributions
acas-0.395
zag-0.367
henko-0.340
arial-0.334
ibaba-0.328
Tokenlings
Token ID17783
Feature activation+2.95e+00

Pos logit contributions
acas+0.788
zag+0.729
henko+0.691
arial+0.679
ibaba+0.669
Neg logit contributions
Glass-0.513
 Ped-0.500
%:-0.447
 Forever-0.435
Ped-0.425
Token,
Token ID11
Feature activation+1.34e+00

Pos logit contributions
acas+2.515
zag+2.302
henko+2.158
arial+2.131
ibaba+2.060
Neg logit contributions
Glass-2.294
 Ped-2.227
%:-2.051
 Forever-1.998
Ped-1.972
Token and
Token ID290
Feature activation-1.20e-01

Pos logit contributions
acas+1.189
zag+1.090
henko+1.022
arial+1.007
ibaba+0.984
Neg logit contributions
Glass-1.001
 Ped-0.983
%:-0.887
 Forever-0.873
Ped-0.857
Token the
Token ID262
Feature activation+6.20e-01

Pos logit contributions
Glass+0.081
 Ped+0.080
%:+0.071
 Forever+0.070
Ped+0.068
Neg logit contributions
acas-0.115
zag-0.106
henko-0.100
arial-0.099
ibaba-0.097
Token prag
Token ID23864
Feature activation+4.50e-01

Pos logit contributions
acas+0.558
zag+0.512
henko+0.480
arial+0.473
ibaba+0.464
Neg logit contributions
Glass-0.456
 Ped-0.448
%:-0.404
 Forever-0.398
Ped-0.389
Tokenmat
Token ID6759
Feature activation-7.14e-01

Pos logit contributions
acas+0.395
zag+0.362
henko+0.339
arial+0.334
ibaba+0.327
Neg logit contributions
Glass-0.339
 Ped-0.333
%:-0.302
 Forever-0.296
Ped-0.291
Token strange
Token ID6283
Feature activation+8.68e-01

Pos logit contributions
acas+0.222
zag+0.202
henko+0.191
arial+0.187
ibaba+0.184
Neg logit contributions
Glass-0.179
 Ped-0.177
%:-0.158
 Forever-0.157
Ped-0.153
Token feeling
Token ID4203
Feature activation+5.33e-01

Pos logit contributions
acas+0.755
zag+0.689
henko+0.647
arial+0.636
ibaba+0.624
Neg logit contributions
Glass-0.664
 Ped-0.654
%:-0.590
 Forever-0.583
Ped-0.571
Token for
Token ID329
Feature activation-2.31e-01

Pos logit contributions
acas+0.498
zag+0.458
henko+0.431
arial+0.425
ibaba+0.416
Neg logit contributions
Glass-0.374
 Ped-0.366
%:-0.329
 Forever-0.323
Ped-0.317
Token Andrew
Token ID6858
Feature activation-9.63e-01

Pos logit contributions
Glass+0.157
 Ped+0.154
%:+0.137
 Forever+0.135
Ped+0.132
Neg logit contributions
acas-0.221
zag-0.203
henko-0.192
arial-0.189
ibaba-0.186
Token L
Token ID406
Feature activation+1.21e-01

Pos logit contributions
Glass+0.509
 Ped+0.498
%:+0.430
 Forever+0.419
Ped+0.406
Neg logit contributions
acas-1.065
zag-0.993
henko-0.942
arial-0.933
ibaba-0.920
Tokenadd
Token ID2860
Feature activation+2.41e+00

Pos logit contributions
acas+0.085
zag+0.076
henko+0.070
arial+0.068
ibaba+0.066
Neg logit contributions
Glass-0.112
 Ped-0.110
%:-0.102
 Forever-0.100
Ped-0.099
Token,
Token ID11
Feature activation+9.09e-02

Pos logit contributions
acas+2.155
zag+1.978
henko+1.862
arial+1.829
ibaba+1.788
Neg logit contributions
Glass-1.788
 Ped-1.741
%:-1.584
 Forever-1.548
Ped-1.523
Token who
Token ID508
Feature activation-2.31e-01

Pos logit contributions
acas+0.082
zag+0.075
henko+0.070
arial+0.069
ibaba+0.068
Neg logit contributions
Glass-0.067
 Ped-0.065
%:-0.059
 Forever-0.058
Ped-0.057
Token will
Token ID481
Feature activation+3.69e-02

Pos logit contributions
Glass+0.166
 Ped+0.163
%:+0.146
 Forever+0.144
Ped+0.141
Neg logit contributions
acas-0.212
zag-0.195
henko-0.183
arial-0.180
ibaba-0.177
Token walk
Token ID2513
Feature activation+9.97e-01

Pos logit contributions
acas+0.033
zag+0.030
henko+0.029
arial+0.028
ibaba+0.028
Neg logit contributions
Glass-0.027
 Ped-0.027
%:-0.024
 Forever-0.024
Ped-0.023
Token into
Token ID656
Feature activation+7.25e-01

Pos logit contributions
acas+0.905
zag+0.831
henko+0.781
arial+0.770
ibaba+0.753
Neg logit contributions
Glass-0.725
 Ped-0.709
%:-0.641
 Forever-0.628
Ped-0.617
Token
Token ID247
Feature activation+2.23e-01

Pos logit contributions
acas+0.561
zag+0.512
henko+0.479
arial+0.473
ibaba+0.461
Neg logit contributions
Glass-0.505
 Ped-0.494
%:-0.449
 Forever-0.441
Ped-0.434
Token intoler
Token ID20619
Feature activation+5.93e-01

Pos logit contributions
acas+0.205
zag+0.189
henko+0.178
arial+0.175
ibaba+0.171
Neg logit contributions
Glass-0.158
 Ped-0.155
%:-0.140
 Forever-0.137
Ped-0.135
Tokenant
Token ID415
Feature activation-4.59e-01

Pos logit contributions
acas+0.335
zag+0.293
henko+0.263
arial+0.255
ibaba+0.246
Neg logit contributions
Glass-0.632
 Ped-0.625
%:-0.584
 Forever-0.574
Ped-0.570
Token attitude
Token ID9408
Feature activation+2.38e-01

Pos logit contributions
Glass+0.359
 Ped+0.357
%:+0.322
 Forever+0.318
Ped+0.312
Neg logit contributions
acas-0.389
zag-0.356
henko-0.336
arial-0.327
ibaba-0.322
Token had
Token ID550
Feature activation+2.76e-02

Pos logit contributions
acas+0.211
zag+0.194
henko+0.182
arial+0.179
ibaba+0.176
Neg logit contributions
Glass-0.177
 Ped-0.174
%:-0.157
 Forever-0.154
Ped-0.152
Token always
Token ID1464
Feature activation+2.46e+00

Pos logit contributions
acas+0.025
zag+0.023
henko+0.022
arial+0.021
ibaba+0.021
Neg logit contributions
Glass-0.020
 Ped-0.020
%:-0.018
 Forever-0.017
Ped-0.017
Token eng
Token ID1786
Feature activation-8.67e-01

Pos logit contributions
acas+2.201
zag+2.016
henko+1.920
arial+1.903
omore+1.823
Neg logit contributions
Glass-1.800
 Ped-1.718
%:-1.600
 Forever-1.538
Ped-1.513
Tokenendered
Token ID30398
Feature activation+1.48e-01

Pos logit contributions
Glass+0.503
 Ped+0.492
%:+0.430
 Forever+0.420
Ped+0.413
Neg logit contributions
acas-0.907
zag-0.847
henko-0.806
arial-0.791
ibaba-0.781
Token a
Token ID257
Feature activation-4.97e-01

Pos logit contributions
acas+0.123
zag+0.112
henko+0.104
arial+0.103
ibaba+0.100
Neg logit contributions
Glass-0.120
 Ped-0.117
%:-0.107
 Forever-0.105
Ped-0.104
Token great
Token ID1049
Feature activation+1.71e-01

Pos logit contributions
Glass+0.403
 Ped+0.398
%:+0.360
 Forever+0.356
Ped+0.348
Neg logit contributions
acas-0.408
zag-0.373
henko-0.349
arial-0.340
ibaba-0.334
Token deal
Token ID1730
Feature activation-1.08e-01

Pos logit contributions
acas+0.113
zag+0.101
henko+0.093
arial+0.089
ibaba+0.088
Neg logit contributions
Glass-0.166
 Ped-0.164
%:-0.152
 Forever-0.150
Ped-0.148
Token
Token ID198
Feature activation+3.77e-01

Pos logit contributions
Glass+0.669
 Ped+0.652
%:+0.581
 Forever+0.567
Ped+0.556
Neg logit contributions
acas-1.054
zag-0.976
henko-0.923
arial-0.911
ibaba-0.893
Token
Token ID198
Feature activation+2.38e-01

Pos logit contributions
acas+0.380
zag+0.352
henko+0.333
arial+0.329
ibaba+0.323
Neg logit contributions
Glass-0.236
 Ped-0.230
%:-0.204
 Forever-0.199
Ped-0.195
Token+
Token ID10
Feature activation+7.91e-02

Pos logit contributions
acas+0.222
zag+0.204
henko+0.191
arial+0.189
ibaba+0.185
Neg logit contributions
Glass-0.168
 Ped-0.165
%:-0.148
 Forever-0.145
Ped-0.142
Token--------------------
Token ID19351
Feature activation+2.22e-01

Pos logit contributions
acas+0.072
zag+0.066
henko+0.062
arial+0.061
ibaba+0.060
Neg logit contributions
Glass-0.057
 Ped-0.056
%:-0.051
 Forever-0.050
Ped-0.049
Token--+
Token ID44785
Feature activation+1.94e-01

Pos logit contributions
acas+0.189
zag+0.173
henko+0.161
arial+0.158
ibaba+0.156
Neg logit contributions
Glass-0.174
 Ped-0.171
%:-0.157
 Forever-0.153
Ped-0.151
Token |
Token ID930
Feature activation+2.29e+00

Pos logit contributions
acas+0.186
zag+0.172
henko+0.162
arial+0.160
ibaba+0.156
Neg logit contributions
Glass-0.131
 Ped-0.127
%:-0.114
 Forever-0.112
Ped-0.110
Token...
Token ID2644
Feature activation-1.46e-01

Pos logit contributions
acas+1.843
zag+1.674
henko+1.558
arial+1.532
ibaba+1.486
Neg logit contributions
Glass-1.885
 Ped-1.829
%:-1.687
 Forever-1.653
Ped-1.635
Token |
Token ID930
Feature activation+2.43e+00

Pos logit contributions
Glass+0.097
 Ped+0.095
%:+0.085
 Forever+0.083
Ped+0.081
Neg logit contributions
acas-0.142
zag-0.132
henko-0.124
arial-0.122
ibaba-0.120
Token +
Token ID1343
Feature activation+7.88e-01

Pos logit contributions
acas+2.262
zag+2.082
henko+1.958
arial+1.930
ibaba+1.887
Neg logit contributions
Glass-1.702
 Ped-1.645
%:-1.491
 Forever-1.457
Ped-1.439
Token--------------------
Token ID19351
Feature activation-8.72e-02

Pos logit contributions
acas+0.717
zag+0.660
henko+0.617
arial+0.608
ibaba+0.599
Neg logit contributions
Glass-0.573
 Ped-0.559
%:-0.510
 Forever-0.496
Ped-0.488
Token--+
Token ID44785
Feature activation+8.15e-02

Pos logit contributions
Glass+0.069
 Ped+0.068
%:+0.062
 Forever+0.060
Ped+0.060
Neg logit contributions
acas-0.074
zag-0.067
henko-0.063
arial-0.062
ibaba-0.061
Token,
Token ID11
Feature activation-4.64e-01

Pos logit contributions
acas+0.139
zag+0.127
henko+0.120
arial+0.118
ibaba+0.115
Neg logit contributions
Glass-0.116
 Ped-0.113
%:-0.103
 Forever-0.100
Ped-0.099
Token on
Token ID319
Feature activation+7.97e-02

Pos logit contributions
Glass+0.294
 Ped+0.287
%:+0.255
 Forever+0.249
Ped+0.244
Neg logit contributions
acas-0.464
zag-0.430
henko-0.407
arial-0.401
ibaba-0.394
Token an
Token ID281
Feature activation+5.84e-01

Pos logit contributions
acas+0.075
zag+0.069
henko+0.065
arial+0.065
ibaba+0.063
Neg logit contributions
Glass-0.055
 Ped-0.054
%:-0.048
 Forever-0.047
Ped-0.046
Token outcome
Token ID8055
Feature activation+2.98e-01

Pos logit contributions
acas+0.510
zag+0.465
henko+0.437
arial+0.435
ibaba+0.420
Neg logit contributions
Glass-0.446
 Ped-0.433
%:-0.395
 Forever-0.385
Ped-0.381
Token that
Token ID326
Feature activation+1.82e-01

Pos logit contributions
acas+0.244
zag+0.222
henko+0.207
arial+0.204
ibaba+0.198
Neg logit contributions
Glass-0.243
 Ped-0.238
%:-0.218
 Forever-0.214
Ped-0.210
Token's
Token ID338
Feature activation+4.77e-01

Pos logit contributions
acas+0.165
zag+0.152
henko+0.143
arial+0.141
ibaba+0.137
Neg logit contributions
Glass-0.132
 Ped-0.128
%:-0.117
 Forever-0.113
Ped-0.112
Token unknown
Token ID6439
Feature activation-7.33e-02

Pos logit contributions
acas+0.434
zag+0.399
henko+0.375
arial+0.371
ibaba+0.360
Neg logit contributions
Glass-0.345
 Ped-0.336
%:-0.306
 Forever-0.297
Ped-0.293
Token,
Token ID11
Feature activation-3.83e-01

Pos logit contributions
Glass+0.053
 Ped+0.052
%:+0.047
 Forever+0.046
Ped+0.045
Neg logit contributions
acas-0.067
zag-0.061
henko-0.057
arial-0.057
ibaba-0.055
Token where
Token ID810
Feature activation-1.33e+00

Pos logit contributions
Glass+0.268
 Ped+0.262
%:+0.236
 Forever+0.231
Ped+0.227
Neg logit contributions
acas-0.357
zag-0.329
henko-0.309
arial-0.305
ibaba-0.299
Token Britain
Token ID5491
Feature activation+2.42e-01

Pos logit contributions
Glass+0.914
 Ped+0.895
%:+0.798
 Forever+0.786
Ped+0.768
Neg logit contributions
acas-1.265
zag-1.167
henko-1.101
arial-1.081
ibaba-1.063
Token's
Token ID338
Feature activation-7.25e-01

Pos logit contributions
acas+0.223
zag+0.205
henko+0.193
arial+0.190
ibaba+0.185
Neg logit contributions
Glass-0.173
 Ped-0.169
%:-0.153
 Forever-0.149
Ped-0.147
Token who
Token ID508
Feature activation+6.09e-01

Pos logit contributions
acas+0.836
zag+0.763
henko+0.714
arial+0.703
ibaba+0.688
Neg logit contributions
Glass-0.747
 Ped-0.733
%:-0.665
 Forever-0.654
Ped-0.643
Token was
Token ID373
Feature activation+2.05e-02

Pos logit contributions
acas+0.593
zag+0.548
henko+0.516
arial+0.508
ibaba+0.501
Neg logit contributions
Glass-0.402
 Ped-0.396
%:-0.350
 Forever-0.345
Ped-0.338
Token following
Token ID1708
Feature activation-2.23e+00

Pos logit contributions
acas+0.018
zag+0.017
henko+0.016
arial+0.016
ibaba+0.015
Neg logit contributions
Glass-0.015
 Ped-0.015
%:-0.013
 Forever-0.013
Ped-0.013
Token her
Token ID607
Feature activation+7.85e-02

Pos logit contributions
 Ped+1.623
Glass+1.610
 Forever+1.417
%:+1.386
Ped+1.384
Neg logit contributions
acas-2.021
zag-1.834
henko-1.738
ibaba-1.700
arial-1.689
Token upstairs
Token ID26148
Feature activation-2.84e-01

Pos logit contributions
acas+0.071
zag+0.065
henko+0.061
arial+0.060
ibaba+0.059
Neg logit contributions
Glass-0.057
 Ped-0.057
%:-0.051
 Forever-0.050
Ped-0.049
Token,
Token ID11
Feature activation+8.91e-02

Pos logit contributions
Glass+0.202
 Ped+0.202
 Forever+0.176
%:+0.175
Ped+0.173
Neg logit contributions
acas-0.261
zag-0.240
henko-0.226
arial-0.221
ibaba-0.220
Token got
Token ID1392
Feature activation+1.03e+00

Pos logit contributions
acas+0.079
zag+0.072
henko+0.067
arial+0.066
ibaba+0.065
Neg logit contributions
Glass-0.067
 Ped-0.067
%:-0.059
 Forever-0.059
Ped-0.058
Token crushed
Token ID18577
Feature activation+1.65e-01

Pos logit contributions
acas+0.929
zag+0.852
henko+0.801
arial+0.790
ibaba+0.771
Neg logit contributions
Glass-0.753
 Ped-0.735
%:-0.668
 Forever-0.653
Ped-0.642
Token under
Token ID739
Feature activation+3.97e-01

Pos logit contributions
acas+0.154
zag+0.142
henko+0.132
arial+0.131
ibaba+0.129
Neg logit contributions
Glass-0.116
 Ped-0.114
%:-0.101
 Forever-0.100
Ped-0.098
Token her
Token ID607
Feature activation+2.82e-01

Pos logit contributions
acas+0.398
zag+0.369
henko+0.349
arial+0.344
ibaba+0.337
Neg logit contributions
Glass-0.251
 Ped-0.245
%:-0.217
 Forever-0.212
Ped-0.208
Token weight
Token ID3463
Feature activation+5.90e-01

Pos logit contributions
acas+0.240
zag+0.219
henko+0.205
arial+0.201
ibaba+0.197
Neg logit contributions
Glass-0.221
 Ped-0.217
%:-0.197
 Forever-0.194
Ped-0.191
Token according
Token ID1864
Feature activation-8.03e-01

Pos logit contributions
acas+0.207
zag+0.190
henko+0.179
arial+0.176
ibaba+0.172
Neg logit contributions
Glass-0.173
 Ped-0.169
%:-0.154
 Forever-0.150
Ped-0.148
Token to
Token ID284
Feature activation+4.19e-01

Pos logit contributions
Glass+0.533
 Ped+0.525
%:+0.463
 Forever+0.456
Ped+0.447
Neg logit contributions
acas-0.784
zag-0.722
henko-0.680
arial-0.671
ibaba-0.663
Token court
Token ID2184
Feature activation-6.80e-02

Pos logit contributions
acas+0.397
zag+0.365
henko+0.346
arial+0.340
ibaba+0.333
Neg logit contributions
Glass-0.286
 Ped-0.276
%:-0.252
 Forever-0.244
Ped-0.241
Token documents
Token ID4963
Feature activation-5.03e-01

Pos logit contributions
Glass+0.049
 Ped+0.048
%:+0.043
 Forever+0.042
Ped+0.042
Neg logit contributions
acas-0.062
zag-0.057
henko-0.054
arial-0.053
ibaba-0.052
Token.
Token ID13
Feature activation-3.31e-01

Pos logit contributions
Glass+0.346
 Ped+0.339
%:+0.303
 Forever+0.298
Ped+0.292
Neg logit contributions
acas-0.476
zag-0.438
henko-0.412
arial-0.407
ibaba-0.399
Token
Token ID198
Feature activation+1.62e-02

Pos logit contributions
Glass+0.208
 Ped+0.204
%:+0.181
 Forever+0.177
Ped+0.173
Neg logit contributions
acas-0.332
zag-0.308
henko-0.291
arial-0.287
ibaba-0.282
Token
Token ID198
Feature activation-1.27e-01

Pos logit contributions
acas+0.017
zag+0.015
henko+0.014
arial+0.014
ibaba+0.014
Neg logit contributions
Glass-0.010
 Ped-0.010
%:-0.009
 Forever-0.009
Ped-0.008
TokenThe
Token ID464
Feature activation-1.33e-01

Pos logit contributions
Glass+0.083
 Ped+0.081
%:+0.073
 Forever+0.071
Ped+0.069
Neg logit contributions
acas-0.124
zag-0.114
henko-0.108
arial-0.107
ibaba-0.104
Token Washington
Token ID2669
Feature activation+1.47e+00

Pos logit contributions
Glass+0.100
 Ped+0.097
%:+0.089
 Forever+0.087
Ped+0.085
Neg logit contributions
acas-0.118
zag-0.108
henko-0.101
arial-0.100
ibaba-0.097
Token State
Token ID1812
Feature activation+2.57e+00

Pos logit contributions
acas+1.403
zag+1.294
henko+1.213
arial+1.195
ibaba+1.176
Neg logit contributions
Glass-0.990
 Ped-0.954
%:-0.873
 Forever-0.840
Ped-0.829
Token Patrol
Token ID20989
Feature activation+1.47e+00

Pos logit contributions
acas+2.705
zag+2.513
henko+2.376
arial+2.335
ibaba+2.295
Neg logit contributions
Glass-1.465
 Ped-1.371
%:-1.274
 Forever-1.188
Ped-1.184
Token to
Token ID284
Feature activation+2.66e-01

Pos logit contributions
Glass+0.322
 Ped+0.319
%:+0.288
 Forever+0.279
Ped+0.272
Neg logit contributions
acas-0.435
zag-0.401
henko-0.377
arial-0.373
ibaba-0.368
Token explain
Token ID4727
Feature activation+8.57e-01

Pos logit contributions
acas+0.221
zag+0.201
henko+0.188
arial+0.184
ibaba+0.181
Neg logit contributions
Glass-0.214
 Ped-0.210
%:-0.192
 Forever-0.188
Ped-0.185
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
acas+0.804
zag+0.739
henko+0.697
arial+0.687
ibaba+0.675
Neg logit contributions
Glass-0.597
 Ped-0.586
%:-0.528
 Forever-0.516
Ped-0.506
Token Ad
Token ID1215
Feature activation-1.25e-01

Pos logit contributions
acas+0.117
zag+0.109
henko+0.103
arial+0.101
ibaba+0.100
Neg logit contributions
Glass-0.075
 Ped-0.073
%:-0.065
 Forever-0.064
Ped-0.062
Token Policy
Token ID7820
Feature activation-1.83e+00

Pos logit contributions
Glass+0.092
 Ped+0.090
%:+0.081
 Forever+0.080
Ped+0.078
Neg logit contributions
acas-0.113
zag-0.104
henko-0.098
arial-0.096
ibaba-0.094
Token
Token ID198
Feature activation-1.43e-01

Pos logit contributions
Glass+1.121
 Ped+1.117
%:+0.977
 Forever+0.963
Ped+0.935
Neg logit contributions
acas-1.853
zag-1.725
henko-1.636
arial-1.607
ibaba-1.589
Token
Token ID198
Feature activation+4.28e-02

Pos logit contributions
Glass+0.089
 Ped+0.087
%:+0.077
 Forever+0.075
Ped+0.074
Neg logit contributions
acas-0.145
zag-0.135
henko-0.127
arial-0.126
ibaba-0.124
TokenMod
Token ID5841
Feature activation+1.08e-01

Pos logit contributions
acas+0.041
zag+0.038
henko+0.036
arial+0.035
ibaba+0.035
Neg logit contributions
Glass-0.029
 Ped-0.028
%:-0.025
 Forever-0.025
Ped-0.024
Tokener
Token ID263
Feature activation-5.79e-01

Pos logit contributions
acas+0.111
zag+0.103
henko+0.097
arial+0.096
ibaba+0.094
Neg logit contributions
Glass-0.067
 Ped-0.065
%:-0.058
 Forever-0.056
Ped-0.055
Tokenator
Token ID1352
Feature activation-5.46e-01

Pos logit contributions
Glass+0.473
 Ped+0.465
%:+0.427
 Forever+0.417
Ped+0.412
Neg logit contributions
acas-0.471
zag-0.428
henko-0.401
arial-0.392
ibaba-0.386
Token Elaine
Token ID41463
Feature activation+8.44e-01

Pos logit contributions
Glass+0.321
 Ped+0.312
%:+0.275
 Forever+0.268
Ped+0.262
Neg logit contributions
acas-0.571
zag-0.531
henko-0.504
arial-0.497
ibaba-0.488
Token
Token ID198
Feature activation-3.46e-01

Pos logit contributions
acas+0.019
zag+0.018
henko+0.017
arial+0.016
ibaba+0.016
Neg logit contributions
Glass-0.011
 Ped-0.011
%:-0.010
 Forever-0.010
Ped-0.009
Token
Token ID198
Feature activation-1.10e-01

Pos logit contributions
Glass+0.212
 Ped+0.207
%:+0.183
 Forever+0.179
Ped+0.175
Neg logit contributions
acas-0.354
zag-0.328
henko-0.311
arial-0.306
ibaba-0.303
TokenP
Token ID47
Feature activation+3.98e-01

Pos logit contributions
Glass+0.073
 Ped+0.071
%:+0.064
 Forever+0.062
Ped+0.061
Neg logit contributions
acas-0.107
zag-0.099
henko-0.094
arial-0.092
ibaba-0.091
Tokenence
Token ID594
Feature activation+1.14e+00

Pos logit contributions
acas+0.409
zag+0.380
henko+0.360
arial+0.357
ibaba+0.349
Neg logit contributions
Glass-0.241
 Ped-0.234
%:-0.207
 Forever-0.202
Ped-0.198
Token did
Token ID750
Feature activation-4.10e-01

Pos logit contributions
acas+1.012
zag+0.928
henko+0.871
arial+0.858
ibaba+0.838
Neg logit contributions
Glass-0.845
 Ped-0.826
%:-0.749
 Forever-0.734
Ped-0.722
Token well
Token ID880
Feature activation+5.47e-01

Pos logit contributions
Glass+0.294
 Ped+0.291
%:+0.263
 Forever+0.257
Ped+0.252
Neg logit contributions
acas-0.374
zag-0.342
henko-0.323
arial-0.319
ibaba-0.312
Token enough
Token ID1576
Feature activation+4.29e-01

Pos logit contributions
acas+0.514
zag+0.472
henko+0.444
arial+0.437
ibaba+0.429
Neg logit contributions
Glass-0.381
 Ped-0.375
%:-0.337
 Forever-0.330
Ped-0.322
Token for
Token ID329
Feature activation-3.66e-01

Pos logit contributions
acas+0.403
zag+0.370
henko+0.349
arial+0.343
ibaba+0.337
Neg logit contributions
Glass-0.298
 Ped-0.294
%:-0.264
 Forever-0.259
Ped-0.252
Token the
Token ID262
Feature activation+2.78e-02

Pos logit contributions
Glass+0.269
 Ped+0.266
%:+0.238
 Forever+0.236
Ped+0.229
Neg logit contributions
acas-0.330
zag-0.302
henko-0.284
arial-0.279
ibaba-0.275
Token cable
Token ID7862
Feature activation+8.89e-02

Pos logit contributions
acas+0.024
zag+0.022
henko+0.021
arial+0.021
ibaba+0.020
Neg logit contributions
Glass-0.021
 Ped-0.021
%:-0.019
 Forever-0.019
Ped-0.018
Token pundits
Token ID30855
Feature activation+7.77e-01

Pos logit contributions
acas+0.079
zag+0.072
henko+0.068
arial+0.067
ibaba+0.065
Neg logit contributions
Glass-0.066
 Ped-0.065
%:-0.059
 Forever-0.058
Ped-0.057
Token.
Token ID13
Feature activation+5.80e-01

Pos logit contributions
acas+1.133
zag+1.044
henko+0.980
arial+0.968
ibaba+0.952
Neg logit contributions
Glass-0.857
 Ped-0.844
%:-0.757
 Forever-0.745
Ped-0.728
Token
Token ID198
Feature activation-4.34e-02

Pos logit contributions
acas+0.589
zag+0.547
henko+0.517
arial+0.510
ibaba+0.502
Neg logit contributions
Glass-0.359
 Ped-0.352
%:-0.311
 Forever-0.305
Ped-0.297
Token
Token ID198
Feature activation-8.07e-02

Pos logit contributions
Glass+0.027
 Ped+0.026
%:+0.023
 Forever+0.023
Ped+0.022
Neg logit contributions
acas-0.044
zag-0.041
henko-0.039
arial-0.038
ibaba-0.038
TokenAnd
Token ID1870
Feature activation+2.58e-01

Pos logit contributions
Glass+0.054
 Ped+0.053
%:+0.047
 Forever+0.046
Ped+0.046
Neg logit contributions
acas-0.078
zag-0.072
henko-0.068
arial-0.067
ibaba-0.066
Token after
Token ID706
Feature activation+1.12e-01

Pos logit contributions
acas+0.236
zag+0.217
henko+0.204
arial+0.201
ibaba+0.197
Neg logit contributions
Glass-0.185
 Ped-0.183
%:-0.164
 Forever-0.161
Ped-0.158
Token three
Token ID1115
Feature activation-5.14e-01

Pos logit contributions
acas+0.102
zag+0.094
henko+0.088
arial+0.087
ibaba+0.086
Neg logit contributions
Glass-0.081
 Ped-0.080
%:-0.071
 Forever-0.070
Ped-0.069
Token months
Token ID1933
Feature activation-7.36e-02

Pos logit contributions
Glass+0.352
 Ped+0.346
%:+0.308
 Forever+0.304
Ped+0.296
Neg logit contributions
acas-0.489
zag-0.449
henko-0.424
arial-0.420
ibaba-0.412
Token of
Token ID286
Feature activation+1.94e+00

Pos logit contributions
Glass+0.053
 Ped+0.052
%:+0.047
 Forever+0.046
Ped+0.045
Neg logit contributions
acas-0.067
zag-0.061
henko-0.057
arial-0.057
ibaba-0.056
Token racing
Token ID11717
Feature activation-1.37e+00

Pos logit contributions
acas+1.653
zag+1.509
henko+1.412
arial+1.389
ibaba+1.355
Neg logit contributions
Glass-1.524
 Ped-1.491
%:-1.361
 Forever-1.334
Ped-1.314
Token around
Token ID1088
Feature activation-3.56e-01

Pos logit contributions
Glass+0.950
 Ped+0.942
%:+0.823
 Forever+0.822
Ped+0.807
Neg logit contributions
acas-1.273
zag-1.173
henko-1.107
arial-1.098
ibaba-1.074
Token the
Token ID262
Feature activation+2.38e-01

Pos logit contributions
Glass+0.243
 Ped+0.239
%:+0.212
 Forever+0.210
Ped+0.204
Neg logit contributions
acas-0.338
zag-0.311
henko-0.295
arial-0.290
ibaba-0.284
Token cannot
Token ID2314
Feature activation+1.69e-01

Pos logit contributions
Glass+0.040
 Ped+0.039
%:+0.035
 Forever+0.035
Ped+0.034
Neg logit contributions
acas-0.048
zag-0.044
henko-0.042
arial-0.041
ibaba-0.040
Token and
Token ID290
Feature activation+9.09e-01

Pos logit contributions
acas+0.143
zag+0.130
henko+0.122
arial+0.119
ibaba+0.118
Neg logit contributions
Glass-0.134
 Ped-0.132
%:-0.121
 Forever-0.118
Ped-0.115
Token will
Token ID481
Feature activation+4.89e-01

Pos logit contributions
acas+0.886
zag+0.819
henko+0.773
arial+0.762
ibaba+0.748
Neg logit contributions
Glass-0.600
 Ped-0.588
%:-0.525
 Forever-0.514
Ped-0.503
Token not
Token ID407
Feature activation+2.99e-01

Pos logit contributions
acas+0.492
zag+0.456
henko+0.432
arial+0.426
ibaba+0.419
Neg logit contributions
Glass-0.307
 Ped-0.300
%:-0.267
 Forever-0.261
Ped-0.255
Token,
Token ID11
Feature activation-1.98e-01

Pos logit contributions
acas+0.240
zag+0.218
henko+0.203
arial+0.198
ibaba+0.196
Neg logit contributions
Glass-0.249
 Ped-0.246
%:-0.226
 Forever-0.221
Ped-0.217
Token and
Token ID290
Feature activation-3.84e-01

Pos logit contributions
Glass+0.166
 Ped+0.164
%:+0.149
 Forever+0.148
Ped+0.145
Neg logit contributions
acas-0.159
zag-0.144
henko-0.134
arial-0.131
ibaba-0.129
Token I
Token ID314
Feature activation+4.03e-01

Pos logit contributions
Glass+0.288
 Ped+0.285
%:+0.258
 Forever+0.254
Ped+0.247
Neg logit contributions
acas-0.340
zag-0.311
henko-0.292
arial-0.287
ibaba-0.281
Token encourage
Token ID7898
Feature activation-1.37e+00

Pos logit contributions
acas+0.375
zag+0.345
henko+0.325
arial+0.320
ibaba+0.314
Neg logit contributions
Glass-0.283
 Ped-0.277
%:-0.250
 Forever-0.245
Ped-0.239
Token even
Token ID772
Feature activation+3.34e-01

Pos logit contributions
Glass+0.865
 Ped+0.852
%:+0.749
 Forever+0.737
Ped+0.719
Neg logit contributions
acas-1.379
zag-1.271
henko-1.209
arial-1.188
ibaba-1.172
Token my
Token ID616
Feature activation-5.14e-01

Pos logit contributions
acas+0.301
zag+0.277
henko+0.260
arial+0.256
ibaba+0.250
Neg logit contributions
Glass-0.244
 Ped-0.238
%:-0.216
 Forever-0.211
Ped-0.208
Token friends
Token ID2460
Feature activation-5.05e-01

Pos logit contributions
Glass+0.380
 Ped+0.373
%:+0.337
 Forever+0.331
Ped+0.325
Neg logit contributions
acas-0.461
zag-0.422
henko-0.397
arial-0.390
ibaba-0.383
Token-
Token ID12
Feature activation-8.43e-01

Pos logit contributions
acas+1.018
zag+0.928
henko+0.867
arial+0.851
ibaba+0.830
Neg logit contributions
Glass-0.974
 Ped-0.955
%:-0.874
 Forever-0.856
Ped-0.844
Tokenone
Token ID505
Feature activation-2.36e-01

Pos logit contributions
Glass+0.756
 Ped+0.739
%:+0.682
 Forever+0.670
Ped+0.664
Neg logit contributions
acas-0.621
zag-0.559
henko-0.518
arial-0.509
ibaba-0.494
Token heat
Token ID4894
Feature activation+4.78e-01

Pos logit contributions
Glass+0.189
 Ped+0.187
%:+0.169
 Forever+0.168
Ped+0.164
Neg logit contributions
acas-0.196
zag-0.180
henko-0.168
arial-0.166
ibaba-0.162
Token sinks
Token ID38614
Feature activation+3.53e-02

Pos logit contributions
acas+0.498
zag+0.462
henko+0.438
arial+0.433
ibaba+0.425
Neg logit contributions
Glass-0.283
 Ped-0.275
%:-0.243
 Forever-0.237
Ped-0.232
Token cool
Token ID3608
Feature activation+1.22e-01

Pos logit contributions
acas+0.031
zag+0.029
henko+0.027
arial+0.026
ibaba+0.026
Neg logit contributions
Glass-0.026
 Ped-0.026
%:-0.024
 Forever-0.023
Ped-0.023
Token the
Token ID262
Feature activation-4.93e-01

Pos logit contributions
acas+0.118
zag+0.109
henko+0.103
arial+0.102
ibaba+0.099
Neg logit contributions
Glass-0.081
 Ped-0.080
%:-0.071
 Forever-0.070
Ped-0.068
Token memory
Token ID4088
Feature activation-4.41e-02

Pos logit contributions
Glass+0.392
 Ped+0.387
%:+0.350
 Forever+0.347
Ped+0.340
Neg logit contributions
acas-0.412
zag-0.378
henko-0.351
arial-0.346
ibaba-0.339
Token and
Token ID290
Feature activation+7.84e-03

Pos logit contributions
Glass+0.034
 Ped+0.034
%:+0.031
 Forever+0.030
Ped+0.030
Neg logit contributions
acas-0.038
zag-0.035
henko-0.032
arial-0.032
ibaba-0.031
Token power
Token ID1176
Feature activation+3.26e-01

Pos logit contributions
acas+0.007
zag+0.006
henko+0.006
arial+0.006
ibaba+0.006
Neg logit contributions
Glass-0.006
 Ped-0.006
%:-0.005
 Forever-0.005
Ped-0.005
Token modules
Token ID13103
Feature activation+1.88e-02

Pos logit contributions
acas+0.253
zag+0.229
henko+0.213
arial+0.209
ibaba+0.203
Neg logit contributions
Glass-0.279
 Ped-0.274
%:-0.252
 Forever-0.247
Ped-0.244
Token,
Token ID11
Feature activation-7.79e-02

Pos logit contributions
acas+0.017
zag+0.016
henko+0.015
arial+0.015
ibaba+0.014
Neg logit contributions
Glass-0.014
 Ped-0.013
%:-0.012
 Forever-0.012
Ped-0.012
Token put
Token ID1234
Feature activation-3.32e-01

Pos logit contributions
acas+0.041
zag+0.037
henko+0.035
arial+0.034
ibaba+0.034
Neg logit contributions
Glass-0.039
 Ped-0.039
%:-0.035
 Forever-0.034
Ped-0.034
Token together
Token ID1978
Feature activation+7.14e-01

Pos logit contributions
Glass+0.327
 Ped+0.323
%:+0.300
 Forever+0.297
Ped+0.291
Neg logit contributions
acas-0.215
zag-0.191
henko-0.174
arial-0.169
ibaba-0.165
Token a
Token ID257
Feature activation+1.18e-01

Pos logit contributions
acas+0.681
zag+0.628
henko+0.593
arial+0.584
ibaba+0.572
Neg logit contributions
Glass-0.485
 Ped-0.475
%:-0.426
 Forever-0.417
Ped-0.408
Token map
Token ID3975
Feature activation+7.62e-01

Pos logit contributions
acas+0.095
zag+0.087
henko+0.081
arial+0.079
ibaba+0.077
Neg logit contributions
Glass-0.098
 Ped-0.096
%:-0.088
 Forever-0.087
Ped-0.085
Token of
Token ID286
Feature activation-1.49e-01

Pos logit contributions
acas+0.658
zag+0.601
henko+0.567
arial+0.556
ibaba+0.545
Neg logit contributions
Glass-0.586
 Ped-0.578
%:-0.523
 Forever-0.514
Ped-0.504
Token places
Token ID4113
Feature activation-5.85e-01

Pos logit contributions
Glass+0.102
 Ped+0.100
%:+0.090
 Forever+0.088
Ped+0.086
Neg logit contributions
acas-0.141
zag-0.130
henko-0.123
arial-0.121
ibaba-0.118
Token that
Token ID326
Feature activation-1.87e-01

Pos logit contributions
Glass+0.437
 Ped+0.434
%:+0.388
 Forever+0.387
Ped+0.376
Neg logit contributions
acas-0.516
zag-0.474
henko-0.446
arial-0.438
ibaba-0.430
Token should
Token ID815
Feature activation-1.02e+00

Pos logit contributions
Glass+0.136
 Ped+0.133
%:+0.121
 Forever+0.118
Ped+0.116
Neg logit contributions
acas-0.170
zag-0.156
henko-0.147
arial-0.144
ibaba-0.141
Token be
Token ID307
Feature activation-1.17e+00

Pos logit contributions
Glass+0.723
 Ped+0.714
%:+0.645
 Forever+0.629
Ped+0.617
Neg logit contributions
acas-0.940
zag-0.866
henko-0.817
arial-0.803
ibaba-0.788
Token stocking
Token ID49774
Feature activation-1.45e+00

Pos logit contributions
Glass+0.884
 Ped+0.878
%:+0.789
 Forever+0.780
Ped+0.763
Neg logit contributions
acas-1.028
zag-0.940
henko-0.885
arial-0.866
ibaba-0.853
Token issues
Token ID2428
Feature activation-4.87e-01

Pos logit contributions
Glass+1.087
 Ped+1.077
%:+0.969
 Forever+0.957
Ped+0.937
Neg logit contributions
acas-1.272
zag-1.174
henko-1.102
arial-1.082
ibaba-1.056
Token
Token ID198
Feature activation-3.09e-01

Pos logit contributions
Glass+0.588
 Ped+0.580
%:+0.516
 Forever+0.510
Ped+0.498
Neg logit contributions
acas-0.768
zag-0.708
henko-0.666
arial-0.655
ibaba-0.645
Token
Token ID198
Feature activation+2.22e-01

Pos logit contributions
Glass+0.187
 Ped+0.183
%:+0.162
 Forever+0.158
Ped+0.155
Neg logit contributions
acas-0.318
zag-0.295
henko-0.280
arial-0.275
ibaba-0.273
TokenMore
Token ID5167
Feature activation-6.73e-01

Pos logit contributions
acas+0.218
zag+0.201
henko+0.190
arial+0.188
ibaba+0.184
Neg logit contributions
Glass-0.145
 Ped-0.141
%:-0.126
 Forever-0.123
Ped-0.121
Token in
Token ID287
Feature activation+3.08e-01

Pos logit contributions
Glass+0.481
 Ped+0.473
%:+0.426
 Forever+0.417
Ped+0.408
Neg logit contributions
acas-0.620
zag-0.571
henko-0.537
arial-0.527
ibaba-0.517
Token this
Token ID428
Feature activation-1.86e+00

Pos logit contributions
acas+0.290
zag+0.268
henko+0.253
arial+0.249
ibaba+0.245
Neg logit contributions
Glass-0.213
 Ped-0.209
%:-0.187
 Forever-0.184
Ped-0.179
Token series
Token ID2168
Feature activation-1.01e+00

Pos logit contributions
Glass+1.382
 Ped+1.374
%:+1.224
 Forever+1.224
Ped+1.178
Neg logit contributions
acas-1.642
zag-1.518
henko-1.440
arial-1.416
ibaba-1.373
Token
Token ID198
Feature activation-8.84e-01

Pos logit contributions
Glass+0.569
 Ped+0.557
%:+0.486
 Forever+0.474
Ped+0.460
Neg logit contributions
acas-1.085
zag-1.014
henko-0.963
arial-0.950
ibaba-0.932
Token
Token ID198
Feature activation-1.46e-01

Pos logit contributions
Glass+0.524
 Ped+0.513
%:+0.450
 Forever+0.440
Ped+0.432
Neg logit contributions
acas-0.926
zag-0.858
henko-0.815
arial-0.799
ibaba-0.798
TokenH
Token ID39
Feature activation+4.84e-01

Pos logit contributions
Glass+0.095
 Ped+0.093
%:+0.083
 Forever+0.081
Ped+0.080
Neg logit contributions
acas-0.143
zag-0.133
henko-0.125
arial-0.124
ibaba-0.121
Tokenansen
Token ID33807
Feature activation+1.66e-01

Pos logit contributions
acas+0.409
zag+0.373
henko+0.349
arial+0.344
ibaba+0.336
Neg logit contributions
Glass-0.381
 Ped-0.373
%:-0.340
 Forever-0.334
Ped-0.329
Token:
Token ID25
Feature activation+9.51e-01

Pos logit contributions
acas+0.148
zag+0.136
henko+0.128
arial+0.126
ibaba+0.123
Neg logit contributions
Glass-0.123
 Ped-0.121
%:-0.109
 Forever-0.107
Ped-0.105
Token deliver
Token ID5203
Feature activation-5.39e-02

Pos logit contributions
acas+0.587
zag+0.535
henko+0.500
arial+0.492
ibaba+0.480
Neg logit contributions
Glass-0.559
 Ped-0.548
%:-0.500
 Forever-0.491
Ped-0.484
Token "
Token ID366
Feature activation+1.09e-01

Pos logit contributions
Glass+0.038
 Ped+0.038
%:+0.034
 Forever+0.033
Ped+0.033
Neg logit contributions
acas-0.049
zag-0.045
henko-0.043
arial-0.042
ibaba-0.041
Tokenbig
Token ID14261
Feature activation-6.72e-01

Pos logit contributions
acas+0.097
zag+0.089
henko+0.084
arial+0.082
ibaba+0.080
Neg logit contributions
Glass-0.080
 Ped-0.079
%:-0.071
 Forever-0.070
Ped-0.069
Token news
Token ID1705
Feature activation-8.50e-01

Pos logit contributions
Glass+0.487
 Ped+0.476
%:+0.431
 Forever+0.422
Ped+0.415
Neg logit contributions
acas-0.610
zag-0.561
henko-0.527
arial-0.519
ibaba-0.508
Token".
Token ID1911
Feature activation-4.14e-01

Pos logit contributions
Glass+0.550
 Ped+0.537
%:+0.479
 Forever+0.469
Ped+0.457
Neg logit contributions
acas-0.839
zag-0.776
henko-0.733
arial-0.723
ibaba-0.713
TokenAccording
Token ID4821
Feature activation-3.52e+00

Pos logit contributions
Glass+0.269
 Ped+0.262
%:+0.234
 Forever+0.228
Ped+0.224
Neg logit contributions
acas-0.408
zag-0.378
henko-0.356
arial-0.352
ibaba-0.346
Token to
Token ID284
Feature activation+2.81e-01

Pos logit contributions
Glass+2.327
 Ped+2.273
%:+2.024
 Forever+1.982
Ped+1.943
Neg logit contributions
acas-3.408
zag-3.144
henko-2.974
arial-2.937
ibaba-2.872
Token the
Token ID262
Feature activation+1.90e-01

Pos logit contributions
acas+0.266
zag+0.245
henko+0.231
arial+0.228
ibaba+0.223
Neg logit contributions
Glass-0.193
 Ped-0.188
%:-0.169
 Forever-0.166
Ped-0.163
Token magazine
Token ID7093
Feature activation+3.54e-01

Pos logit contributions
acas+0.159
zag+0.145
henko+0.135
arial+0.133
ibaba+0.130
Neg logit contributions
Glass-0.152
 Ped-0.149
%:-0.136
 Forever-0.133
Ped-0.131
Token J
Token ID449
Feature activation-2.45e-01

Pos logit contributions
acas+0.317
zag+0.291
henko+0.273
arial+0.269
ibaba+0.263
Neg logit contributions
Glass-0.262
 Ped-0.256
%:-0.232
 Forever-0.227
Ped-0.223
Tokenolla
Token ID33011
Feature activation-5.86e-01

Pos logit contributions
Glass+0.220
 Ped+0.215
%:+0.199
 Forever+0.195
Ped+0.193
Neg logit contributions
acas-0.180
zag-0.162
henko-0.150
arial-0.147
ibaba-0.143
Tokeniking
Token ID14132
Feature activation-7.64e-01

Pos logit contributions
acas+0.664
zag+0.600
henko+0.556
arial+0.547
ibaba+0.533
Neg logit contributions
Glass-0.729
 Ped-0.715
%:-0.657
 Forever-0.647
Ped-0.637
Token,
Token ID11
Feature activation-9.53e-01

Pos logit contributions
Glass+0.555
 Ped+0.547
%:+0.492
 Forever+0.485
Ped+0.474
Neg logit contributions
acas-0.694
zag-0.636
henko-0.599
arial-0.592
ibaba-0.579
Token on
Token ID319
Feature activation-1.34e+00

Pos logit contributions
Glass+0.696
 Ped+0.686
%:+0.614
 Forever+0.607
Ped+0.595
Neg logit contributions
acas-0.863
zag-0.791
henko-0.743
arial-0.734
ibaba-0.717
Token the
Token ID262
Feature activation-3.00e-01

Pos logit contributions
Glass+0.804
 Ped+0.789
%:+0.690
 Forever+0.677
Ped+0.660
Neg logit contributions
acas-1.389
zag-1.287
henko-1.223
arial-1.212
ibaba-1.178
Token other
Token ID584
Feature activation-1.13e+00

Pos logit contributions
Glass+0.218
 Ped+0.215
%:+0.193
 Forever+0.190
Ped+0.186
Neg logit contributions
acas-0.272
zag-0.249
henko-0.235
arial-0.231
ibaba-0.227
Token hand
Token ID1021
Feature activation-3.29e+00

Pos logit contributions
Glass+0.972
 Ped+0.968
%:+0.881
 Forever+0.871
Ped+0.852
Neg logit contributions
acas-0.868
zag-0.784
henko-0.723
arial-0.710
ibaba-0.702
Token,
Token ID11
Feature activation-8.65e-01

Pos logit contributions
 Ped+2.171
Glass+2.161
%:+1.954
 Forever+1.891
Ped+1.838
Neg logit contributions
acas-3.160
zag-2.922
henko-2.725
ibaba-2.708
arial-2.690
Token is
Token ID318
Feature activation-3.82e-01

Pos logit contributions
Glass+0.612
 Ped+0.605
%:+0.542
 Forever+0.533
Ped+0.523
Neg logit contributions
acas-0.799
zag-0.734
henko-0.690
arial-0.681
ibaba-0.667
Token as
Token ID355
Feature activation-9.29e-01

Pos logit contributions
Glass+0.277
 Ped+0.272
%:+0.245
 Forever+0.241
Ped+0.237
Neg logit contributions
acas-0.347
zag-0.318
henko-0.299
arial-0.295
ibaba-0.288
Token simple
Token ID2829
Feature activation-2.25e+00

Pos logit contributions
Glass+0.689
 Ped+0.678
%:+0.611
 Forever+0.599
Ped+0.590
Neg logit contributions
acas-0.830
zag-0.757
henko-0.712
arial-0.701
ibaba-0.688
Token as
Token ID355
Feature activation+1.19e+00

Pos logit contributions
Glass+1.578
 Ped+1.560
%:+1.404
 Forever+1.378
Ped+1.346
Neg logit contributions
acas-2.082
zag-1.902
henko-1.799
arial-1.768
ibaba-1.735
Token Connor
Token ID27599
Feature activation-8.35e-01

Pos logit contributions
acas+0.632
zag+0.583
henko+0.550
arial+0.543
ibaba+0.532
Neg logit contributions
Glass-0.437
 Ped-0.427
%:-0.383
 Forever-0.374
Ped-0.367
Token (
Token ID357
Feature activation-9.84e-01

Pos logit contributions
Glass+0.592
 Ped+0.585
%:+0.523
 Forever+0.514
Ped+0.506
Neg logit contributions
acas-0.769
zag-0.708
henko-0.665
arial-0.658
ibaba-0.644
Tokenwhich
Token ID4758
Feature activation+4.63e-01

Pos logit contributions
Glass+0.780
 Ped+0.760
%:+0.694
 Forever+0.679
Ped+0.676
Neg logit contributions
acas-0.830
zag-0.754
henko-0.707
arial-0.697
ibaba-0.684
Token at
Token ID379
Feature activation-1.52e+00

Pos logit contributions
acas+0.424
zag+0.390
henko+0.367
arial+0.361
ibaba+0.353
Neg logit contributions
Glass-0.332
 Ped-0.322
%:-0.293
 Forever-0.286
Ped-0.281
Token some
Token ID617
Feature activation-6.92e-01

Pos logit contributions
Glass+1.111
 Ped+1.107
%:+0.998
 Forever+0.977
Ped+0.952
Neg logit contributions
acas-1.357
zag-1.240
henko-1.171
arial-1.153
ibaba-1.129
Token point
Token ID966
Feature activation-3.58e+00

Pos logit contributions
Glass+0.630
 Ped+0.622
%:+0.573
 Forever+0.563
Ped+0.555
Neg logit contributions
acas-0.500
zag-0.448
henko-0.414
arial-0.404
ibaba-0.397
Token is
Token ID318
Feature activation-1.29e+00

Pos logit contributions
 Ped+2.399
Glass+2.398
%:+2.099
 Forever+2.089
Ped+2.047
Neg logit contributions
acas-3.401
zag-3.160
henko-2.946
arial-2.922
ibaba-2.892
Token going
Token ID1016
Feature activation-2.41e-01

Pos logit contributions
Glass+0.916
 Ped+0.902
%:+0.806
 Forever+0.795
Ped+0.780
Neg logit contributions
acas-1.198
zag-1.101
henko-1.036
arial-1.020
ibaba-0.998
Token to
Token ID284
Feature activation-6.70e-02

Pos logit contributions
Glass+0.165
 Ped+0.161
%:+0.144
 Forever+0.142
Ped+0.139
Neg logit contributions
acas-0.229
zag-0.211
henko-0.199
arial-0.196
ibaba-0.192
Token come
Token ID1282
Feature activation-2.26e-01

Pos logit contributions
Glass+0.052
 Ped+0.052
%:+0.047
 Forever+0.046
Ped+0.045
Neg logit contributions
acas-0.057
zag-0.052
henko-0.049
arial-0.048
ibaba-0.047
Token,
Token ID11
Feature activation+4.07e-02

Pos logit contributions
Glass+0.156
 Ped+0.153
%:+0.137
 Forever+0.135
Ped+0.132
Neg logit contributions
acas-0.213
zag-0.196
henko-0.185
arial-0.182
ibaba-0.178
Token size
Token ID2546
Feature activation-4.66e-01

Pos logit contributions
Glass+0.500
 Ped+0.490
%:+0.444
 Forever+0.436
Ped+0.428
Neg logit contributions
acas-0.581
zag-0.531
henko-0.499
arial-0.492
ibaba-0.481
Token of
Token ID286
Feature activation-2.16e-01

Pos logit contributions
Glass+0.347
 Ped+0.340
%:+0.306
 Forever+0.302
Ped+0.297
Neg logit contributions
acas-0.415
zag-0.380
henko-0.357
arial-0.353
ibaba-0.344
Token my
Token ID616
Feature activation+2.54e-01

Pos logit contributions
Glass+0.156
 Ped+0.153
%:+0.137
 Forever+0.135
Ped+0.133
Neg logit contributions
acas-0.197
zag-0.180
henko-0.170
arial-0.168
ibaba-0.164
Token thumb
Token ID15683
Feature activation-3.58e-01

Pos logit contributions
acas+0.214
zag+0.195
henko+0.182
arial+0.180
ibaba+0.176
Neg logit contributions
Glass-0.202
 Ped-0.199
%:-0.180
 Forever-0.178
Ped-0.174
Token).
Token ID737
Feature activation-2.67e-01

Pos logit contributions
Glass+0.230
 Ped+0.224
%:+0.198
 Forever+0.195
Ped+0.191
Neg logit contributions
acas-0.356
zag-0.328
henko-0.312
arial-0.306
ibaba-0.302
Token Now
Token ID2735
Feature activation-3.67e+00

Pos logit contributions
Glass+0.173
 Ped+0.169
%:+0.151
 Forever+0.147
Ped+0.145
Neg logit contributions
acas-0.262
zag-0.243
henko-0.229
arial-0.226
ibaba-0.222
Token throw
Token ID3714
Feature activation-7.25e-01

Pos logit contributions
Glass+2.913
 Ped+2.882
%:+2.601
 Forever+2.571
 PF+2.502
Neg logit contributions
acas-2.993
zag-2.759
henko-2.591
arial-2.550
omore-2.489
Token it
Token ID340
Feature activation-1.50e+00

Pos logit contributions
Glass+0.472
 Ped+0.462
%:+0.408
 Forever+0.405
Ped+0.392
Neg logit contributions
acas-0.713
zag-0.657
henko-0.623
arial-0.617
ibaba-0.601
Token on
Token ID319
Feature activation-2.98e-01

Pos logit contributions
Glass+1.073
 Ped+1.055
%:+0.943
 Forever+0.936
Ped+0.904
Neg logit contributions
acas-1.372
zag-1.257
henko-1.180
arial-1.170
ibaba-1.146
Token the
Token ID262
Feature activation-1.09e+00

Pos logit contributions
Glass+0.202
 Ped+0.197
%:+0.177
 Forever+0.173
Ped+0.170
Neg logit contributions
acas-0.284
zag-0.262
henko-0.247
arial-0.244
ibaba-0.239
Token pan
Token ID3425
Feature activation-1.12e+00

Pos logit contributions
Glass+0.972
 Ped+0.955
%:+0.876
 Forever+0.867
Ped+0.852
Neg logit contributions
acas-0.811
zag-0.729
henko-0.673
arial-0.661
ibaba-0.644
Token girls
Token ID4813
Feature activation-1.40e-01

Pos logit contributions
Glass+0.209
 Ped+0.208
%:+0.186
 Forever+0.183
Ped+0.181
Neg logit contributions
acas-0.252
zag-0.230
henko-0.217
arial-0.215
ibaba-0.210
Token.
Token ID13
Feature activation-3.62e-02

Pos logit contributions
Glass+0.097
 Ped+0.096
%:+0.086
 Forever+0.085
Ped+0.082
Neg logit contributions
acas-0.131
zag-0.120
henko-0.113
arial-0.112
ibaba-0.110
Token
Token ID198
Feature activation+6.25e-01

Pos logit contributions
Glass+0.022
 Ped+0.021
%:+0.019
 Forever+0.018
Ped+0.018
Neg logit contributions
acas-0.038
zag-0.035
henko-0.033
arial-0.033
ibaba-0.032
Token
Token ID198
Feature activation+4.48e-01

Pos logit contributions
acas+0.626
zag+0.580
henko+0.549
arial+0.542
ibaba+0.530
Neg logit contributions
Glass-0.395
 Ped-0.385
%:-0.343
 Forever-0.335
Ped-0.328
TokenN
Token ID45
Feature activation+4.76e-01

Pos logit contributions
acas+0.488
zag+0.456
henko+0.432
arial+0.429
ibaba+0.419
Neg logit contributions
Glass-0.239
 Ped-0.235
%:-0.205
 Forever-0.199
Ped-0.191
Tokenom
Token ID296
Feature activation-3.68e+00

Pos logit contributions
acas+0.436
zag+0.402
henko+0.377
arial+0.373
ibaba+0.364
Neg logit contributions
Glass-0.340
 Ped-0.333
%:-0.301
 Forever-0.294
Ped-0.289
Tokeninate
Token ID4559
Feature activation-2.30e-01

Pos logit contributions
Glass+2.754
 Ped+2.688
%:+2.422
 Forever+2.373
Ped+2.319
Neg logit contributions
acas-3.240
zag-2.967
henko-2.790
arial-2.722
ibaba-2.689
Token an
Token ID281
Feature activation+1.43e-02

Pos logit contributions
Glass+0.157
 Ped+0.154
%:+0.138
 Forever+0.135
Ped+0.132
Neg logit contributions
acas-0.218
zag-0.201
henko-0.190
arial-0.187
ibaba-0.183
Token exceptional
Token ID15313
Feature activation-6.59e-01

Pos logit contributions
acas+0.012
zag+0.011
henko+0.010
arial+0.010
ibaba+0.010
Neg logit contributions
Glass-0.012
 Ped-0.011
%:-0.010
 Forever-0.010
Ped-0.010
Token Peace
Token ID12689
Feature activation+9.53e-01

Pos logit contributions
Glass+0.517
 Ped+0.517
%:+0.468
 Forever+0.464
Ped+0.449
Neg logit contributions
acas-0.555
zag-0.509
henko-0.473
arial-0.463
ibaba-0.458
Token Corps
Token ID12778
Feature activation+1.41e+00

Pos logit contributions
acas+1.049
zag+0.979
henko+0.932
arial+0.921
ibaba+0.904
Neg logit contributions
Glass-0.508
 Ped-0.492
%:-0.428
 Forever-0.415
Ped-0.405