TOP ACTIVATIONS
MAX = 12.395

Richie Inc ogn ito (@ 68 INC OG
officer . M ilit ants based in the Moh
documents that prove they have lived in the country since before
: that the Swiss and Cay man accounts that we already
Howard Archer , chief UK & European economist at
Bills : G Richie Inc ogn ito Contract :
or even take a small nap if you can .
the great news of the OCT A receiving the welcome endorsement
guards ) Inc ogn ito s 2013
0 . 0 f ); RAW _ ASS ERT ( it
10 , 2013 Pe ak price : $ 266
, Mass . -- Boston Celtics swing man Jae Crow der
needs to be connected to Live . Has two characters of
. <|endoftext|> Long view , Wash ., police say a man
us . If that didn 't convince you , perhaps their
this approach . He ordered Cabinet secretaries not to do their
, 000 ; field 36 batt alions of Marines ; set
You will receive emails containing news content , updates and promotions
The senior Israeli official noted that the
mag azine ) <|endoftext|> C it ib ank fore closed on

MIN ACTIVATIONS
MIN = -12.341

phan Black BBC America Matthew Mc Con aug hey True Detective
2006 Charlie Sheen 2007 Ricky G erv ais 2007
. For a lot of young evangelicals , church
le 2014 Ricky G erv ais 2014
Rob oc op . Continue Reading Below Advertisement <|endoftext|> UN ITED
," " P unct ate ker at oder ma ," and
in 1946 ( Mic key Mc Bride s buzz
their coverage . Po ppy Har low , Brian Todd ,
contends he was denied a fair hearing without confronting his accuser
be equally as tight - f isted as the Conservatives when
ago I think a simple passing mention of the intervention of
is only the tip of the iceberg ," he told The
Se infeld 1995 Kel sey Gram mer 1995 John
color in a respectful and fair manner .
is an autos omal dominant ker at oder ma of late
and ling 1994 Kel sey Gram mer 1994 John
a parody of a Pit bull and Ke $ ha music
CNN s Andrew K ac zynski .
tic palm opl ant ar ker at oder ma has been
you can avoid a wild goose chase . #

INTERVAL 6.211 - 12.395
CONTAINS 0.586%

of these mushrooms particularly dist ast eful , you can always
, TX from the east coast knowing all of five people
ev / R IA Nov ost i / K remlin
Who is this young man ? said
Var ric chio , a pale ont ologist at Montana State

INTERVAL 0.027 - 6.211
CONTAINS 49.429%

. Defense Department said it condemned the crimes in Min ova
). Here s a picture to help
Pixel pipe Advertisement If you
is going down . Those who find ways to
best exploration game I ve played . It

INTERVAL -6.157 - 0.027
CONTAINS 49.244%

different and with Dick Grayson that 's just a perfect mix
App ro ved Author Notes : This could go
issues that dw elt un spoken at the heart of Lovecraft
, Patricia M . Lap eral of Behavioral Dynamics , said
the public . Ob amacare , or the Affordable

INTERVAL -12.341 - -6.157
CONTAINS 0.741%

. # 40 Sub script ions No
probably not sensible to get too worked up about the details
Other animals [ edit ] Wild nine -
and it will turn a spotlight on the pivotal role that
arm - mounted Alpha Part icle X - Ray Spect rom
Token
Token ID222
Feature activation-3.19e+00

Pos logit contributions
Appearances+3.295
interstitial+3.240
+3.152
 barn+3.065
NPR+3.002
Neg logit contributions
zos-4.849
oint-4.405
kus-4.255
ghazi-4.135
wra-4.106
Token
Token ID126
Feature activation-3.62e+00

Pos logit contributions
Appearances+2.140
interstitial+2.092
+2.083
 barn+2.018
NPR+2.003
Neg logit contributions
zos-2.873
oint-2.601
kus-2.491
wra-2.435
ghazi-2.433
Token
Token ID242
Feature activation-2.94e+00

Pos logit contributions
Appearances+2.724
interstitial+2.693
+2.635
 barn+2.567
NPR+2.536
Neg logit contributions
zos-2.972
oint-2.648
kus-2.560
ghazi-2.477
wra-2.467
Token Richie
Token ID49209
Feature activation-1.59e+00

Pos logit contributions
Appearances+2.024
interstitial+1.979
+1.970
 barn+1.906
NPR+1.886
Neg logit contributions
zos-2.600
oint-2.344
kus-2.246
ghazi-2.191
wra-2.190
Token Inc
Token ID3457
Feature activation-3.71e+00

Pos logit contributions
Appearances+1.074
interstitial+1.057
+1.040
 barn+1.012
NPR+0.995
Neg logit contributions
zos-1.439
oint-1.309
kus-1.251
wra-1.220
ghazi-1.214
Tokenogn
Token ID2360
Feature activation+1.24e+01

Pos logit contributions
Appearances+2.941
interstitial+2.901
+2.854
 barn+2.826
NPR+2.793
Neg logit contributions
zos-2.853
oint-2.548
kus-2.432
ghazi-2.359
wra-2.358
Tokenito
Token ID10094
Feature activation+4.37e+00

Pos logit contributions
zos+6.692
oint+5.551
kus+5.086
estine+4.949
ghazi+4.898
Neg logit contributions
interstitial-12.197
-12.185
Appearances-12.098
 barn-11.569
 Emmy-11.342
Token (@
Token ID4275
Feature activation+2.77e+00

Pos logit contributions
zos+3.898
oint+3.554
kus+3.392
wra+3.320
ghazi+3.287
Neg logit contributions
Appearances-2.949
interstitial-2.918
-2.816
NPR-2.721
 barn-2.717
Token68
Token ID3104
Feature activation-4.01e-01

Pos logit contributions
zos+2.356
oint+2.132
kus+2.031
wra+1.987
ghazi+1.975
Neg logit contributions
Appearances-1.999
interstitial-1.977
-1.944
 barn-1.897
 Emmy-1.853
TokenINC
Token ID30158
Feature activation+1.74e+00

Pos logit contributions
Appearances+0.293
interstitial+0.289
+0.284
 barn+0.275
NPR+0.274
Neg logit contributions
zos-0.342
oint-0.308
kus-0.293
wra-0.286
ghazi-0.285
TokenOG
Token ID7730
Feature activation+4.21e+00

Pos logit contributions
zos+1.270
oint+1.139
kus+1.064
wra+1.038
ghazi+1.028
Neg logit contributions
Appearances-1.473
interstitial-1.461
-1.433
 barn-1.401
NPR-1.377
Token officer
Token ID3818
Feature activation+1.60e+00

Pos logit contributions
zos+3.010
oint+2.765
kus+2.586
ghazi+2.535
wra+2.534
Neg logit contributions
Appearances-2.880
-2.863
interstitial-2.846
NPR-2.658
 barn-2.658
Token.
Token ID13
Feature activation+4.52e-01

Pos logit contributions
zos+1.323
oint+1.200
kus+1.135
wra+1.113
ghazi+1.109
Neg logit contributions
Appearances-1.197
interstitial-1.175
-1.160
 barn-1.114
NPR-1.110
Token
Token ID198
Feature activation+1.31e-01

Pos logit contributions
zos+0.398
oint+0.363
kus+0.345
ghazi+0.338
wra+0.338
Neg logit contributions
interstitial-0.315
Appearances-0.314
-0.306
 barn-0.298
NPR-0.292
Token
Token ID198
Feature activation-1.07e+00

Pos logit contributions
zos+0.124
oint+0.112
kus+0.108
ghazi+0.106
wra+0.106
Neg logit contributions
Appearances-0.084
interstitial-0.080
-0.079
 barn-0.078
NPR-0.078
TokenM
Token ID44
Feature activation+2.04e+00

Pos logit contributions
Appearances+0.705
interstitial+0.684
+0.671
NPR+0.651
 barn+0.645
Neg logit contributions
zos-0.994
oint-0.904
kus-0.865
wra-0.845
ghazi-0.840
Tokenilit
Token ID6392
Feature activation+1.18e+01

Pos logit contributions
zos+1.296
oint+1.135
kus+1.054
wra+1.018
ghazi+1.015
Neg logit contributions
Appearances-1.929
interstitial-1.914
-1.887
 barn-1.844
NPR-1.823
Tokenants
Token ID1187
Feature activation+3.85e-01

Pos logit contributions
zos+5.383
oint+4.740
ghazi+3.975
kus+3.900
wra+3.797
Neg logit contributions
-12.651
Appearances-12.186
interstitial-12.150
 Emmy-11.870
 barn-11.809
Token based
Token ID1912
Feature activation+1.26e+00

Pos logit contributions
zos+0.363
oint+0.332
kus+0.317
wra+0.310
ghazi+0.309
Neg logit contributions
Appearances-0.246
interstitial-0.242
-0.237
 barn-0.229
NPR-0.226
Token in
Token ID287
Feature activation+2.07e+00

Pos logit contributions
zos+1.177
oint+1.075
kus+1.027
ghazi+1.008
wra+1.008
Neg logit contributions
Appearances-0.809
interstitial-0.802
-0.782
 barn-0.748
NPR-0.743
Token the
Token ID262
Feature activation+5.61e-01

Pos logit contributions
zos+1.712
oint+1.551
kus+1.470
wra+1.442
ghazi+1.442
Neg logit contributions
Appearances-1.542
interstitial-1.521
-1.502
NPR-1.442
 barn-1.427
Token Moh
Token ID9719
Feature activation+1.68e+00

Pos logit contributions
zos+0.478
oint+0.434
kus+0.412
wra+0.403
ghazi+0.401
Neg logit contributions
Appearances-0.410
interstitial-0.404
-0.398
 barn-0.382
NPR-0.381
Token documents
Token ID4963
Feature activation+4.57e+00

Pos logit contributions
zos+1.217
oint+1.103
kus+1.047
wra+1.023
ghazi+1.018
Neg logit contributions
Appearances-1.045
interstitial-1.034
-1.015
 barn-0.983
NPR-0.973
Token that
Token ID326
Feature activation+1.73e+00

Pos logit contributions
zos+3.931
oint+3.626
kus+3.395
wra+3.362
estine+3.315
Neg logit contributions
interstitial-3.265
Appearances-3.218
-3.163
NPR-2.976
 barn-2.928
Token prove
Token ID5879
Feature activation-2.27e-01

Pos logit contributions
zos+1.660
oint+1.524
kus+1.461
wra+1.430
ghazi+1.422
Neg logit contributions
Appearances-1.061
interstitial-1.060
-1.027
 barn-0.983
NPR-0.977
Token they
Token ID484
Feature activation+3.25e+00

Pos logit contributions
Appearances+0.126
interstitial+0.122
+0.120
 barn+0.117
NPR+0.113
Neg logit contributions
zos-0.234
oint-0.215
kus-0.207
wra-0.203
ghazi-0.202
Token have
Token ID423
Feature activation+2.71e+00

Pos logit contributions
zos+3.121
oint+2.872
kus+2.741
wra+2.674
estine+2.662
Neg logit contributions
interstitial-2.022
Appearances-2.020
-1.942
NPR-1.841
 barn-1.832
Token lived
Token ID5615
Feature activation+1.16e+01

Pos logit contributions
zos+2.414
oint+2.204
kus+2.097
wra+2.047
ghazi+2.039
Neg logit contributions
Appearances-1.868
interstitial-1.852
-1.811
 barn-1.743
NPR-1.732
Token in
Token ID287
Feature activation+3.87e+00

Pos logit contributions
zos+8.880
oint+8.133
kus+7.644
estine+7.583
ghazi+7.512
Neg logit contributions
interstitial-8.732
Appearances-8.395
-8.159
NPR-7.808
 barn-7.661
Token the
Token ID262
Feature activation+4.17e+00

Pos logit contributions
zos+3.263
oint+2.972
kus+2.800
wra+2.745
ghazi+2.721
Neg logit contributions
interstitial-2.843
Appearances-2.829
-2.778
NPR-2.656
 barn-2.634
Token country
Token ID1499
Feature activation+1.46e+00

Pos logit contributions
zos+3.366
oint+3.065
kus+2.895
wra+2.812
ghazi+2.799
Neg logit contributions
Appearances-3.209
interstitial-3.196
-3.106
NPR-2.989
 barn-2.966
Token since
Token ID1201
Feature activation+4.41e+00

Pos logit contributions
zos+1.277
oint+1.157
kus+1.102
wra+1.078
ghazi+1.071
Neg logit contributions
Appearances-1.040
interstitial-1.029
-1.010
 barn-0.974
NPR-0.966
Token before
Token ID878
Feature activation+5.25e+00

Pos logit contributions
zos+3.900
oint+3.606
kus+3.395
wra+3.336
ghazi+3.329
Neg logit contributions
Appearances-2.999
interstitial-2.989
-2.949
NPR-2.769
 barn-2.739
Token:
Token ID25
Feature activation-1.98e+00

Pos logit contributions
Appearances+1.604
interstitial+1.579
+1.555
 barn+1.516
NPR+1.488
Neg logit contributions
zos-2.117
oint-1.912
kus-1.836
ghazi-1.784
wra-1.778
Token that
Token ID326
Feature activation+4.24e-01

Pos logit contributions
Appearances+1.213
interstitial+1.191
+1.164
 barn+1.135
NPR+1.112
Neg logit contributions
zos-1.922
oint-1.754
kus-1.685
wra-1.649
ghazi-1.642
Token the
Token ID262
Feature activation+1.05e+00

Pos logit contributions
zos+0.432
oint+0.398
kus+0.382
wra+0.374
ghazi+0.373
Neg logit contributions
Appearances-0.238
interstitial-0.234
-0.228
 barn-0.219
NPR-0.216
Token Swiss
Token ID14780
Feature activation-5.36e-01

Pos logit contributions
zos+0.939
oint+0.858
kus+0.816
wra+0.794
ghazi+0.792
Neg logit contributions
Appearances-0.715
interstitial-0.706
-0.691
NPR-0.659
 barn-0.659
Token and
Token ID290
Feature activation+1.96e+00

Pos logit contributions
Appearances+0.372
interstitial+0.367
+0.360
 barn+0.351
NPR+0.345
Neg logit contributions
zos-0.474
oint-0.431
kus-0.411
wra-0.402
ghazi-0.400
Token Cay
Token ID28335
Feature activation+1.15e+01

Pos logit contributions
zos+1.850
oint+1.694
kus+1.621
wra+1.582
ghazi+1.575
Neg logit contributions
Appearances-1.250
interstitial-1.226
-1.202
 barn-1.151
NPR-1.145
Tokenman
Token ID805
Feature activation+2.90e+00

Pos logit contributions
zos+8.992
oint+7.988
kus+7.651
wra+7.379
utsche+7.156
Neg logit contributions
Appearances-8.705
interstitial-8.566
-8.455
NPR-8.169
 barn-8.069
Token accounts
Token ID5504
Feature activation+6.79e+00

Pos logit contributions
zos+2.169
oint+1.933
kus+1.803
wra+1.766
ghazi+1.747
Neg logit contributions
Appearances-2.419
interstitial-2.411
-2.348
NPR-2.280
 barn-2.269
Token that
Token ID326
Feature activation+1.26e+00

Pos logit contributions
zos+5.958
oint+5.484
kus+5.136
wra+5.136
estine+5.027
Neg logit contributions
Appearances-4.561
interstitial-4.492
-4.418
NPR-4.176
 barn-4.154
Token we
Token ID356
Feature activation-4.17e+00

Pos logit contributions
zos+1.265
oint+1.164
kus+1.117
wra+1.094
ghazi+1.090
Neg logit contributions
Appearances-0.723
interstitial-0.715
-0.697
 barn-0.665
NPR-0.658
Token already
Token ID1541
Feature activation-2.94e+00

Pos logit contributions
Appearances+2.924
+2.891
interstitial+2.871
 barn+2.853
NPR+2.782
Neg logit contributions
zos-3.555
oint-3.201
kus-3.038
wra-2.997
ghazi-2.995
Token
Token ID198
Feature activation-5.14e-01

Pos logit contributions
Appearances+3.288
+3.186
interstitial+3.167
 barn+3.092
NPR+3.071
Neg logit contributions
zos-5.143
oint-4.634
kus-4.471
wra-4.378
ghazi-4.374
Token
Token ID198
Feature activation-3.80e-01

Pos logit contributions
Appearances+0.322
interstitial+0.301
+0.301
 barn+0.298
NPR+0.298
Neg logit contributions
zos-0.494
oint-0.445
kus-0.430
ghazi-0.424
wra-0.421
TokenHoward
Token ID32434
Feature activation-3.07e+00

Pos logit contributions
Appearances+0.247
interstitial+0.239
+0.235
NPR+0.229
 barn+0.226
Neg logit contributions
zos-0.358
oint-0.326
kus-0.312
wra-0.305
ghazi-0.304
Token Archer
Token ID19333
Feature activation-2.22e+00

Pos logit contributions
Appearances+2.291
interstitial+2.242
+2.222
 barn+2.193
 Emmy+2.148
Neg logit contributions
zos-2.540
oint-2.281
kus-2.167
ghazi-2.123
wra-2.113
Token,
Token ID11
Feature activation+4.11e+00

Pos logit contributions
Appearances+1.723
interstitial+1.681
+1.671
 barn+1.659
NPR+1.613
Neg logit contributions
zos-1.750
oint-1.557
ghazi-1.474
kus-1.470
wra-1.451
Token chief
Token ID4039
Feature activation+1.14e+01

Pos logit contributions
zos+3.231
oint+2.967
kus+2.773
wra+2.688
ghazi+2.646
Neg logit contributions
Appearances-3.228
interstitial-3.228
-3.152
NPR-2.980
 barn-2.979
Token UK
Token ID3482
Feature activation+3.04e+00

Pos logit contributions
zos+7.954
oint+7.884
utsche+7.172
kus+6.913
estine+6.675
Neg logit contributions
Appearances-9.031
interstitial-8.960
-8.779
NPR-8.276
 Emmy-7.976
Token &
Token ID1222
Feature activation+4.56e+00

Pos logit contributions
zos+2.090
oint+1.880
kus+1.733
wra+1.676
ghazi+1.676
Neg logit contributions
Appearances-2.689
interstitial-2.672
-2.624
NPR-2.530
 barn-2.518
Token European
Token ID3427
Feature activation+4.14e+00

Pos logit contributions
zos+3.812
oint+3.463
kus+3.295
wra+3.221
estine+3.211
Neg logit contributions
Appearances-3.313
interstitial-3.288
-3.186
 barn-3.098
NPR-3.071
Token economist
Token ID17646
Feature activation+6.29e+00

Pos logit contributions
zos+2.888
oint+2.606
kus+2.407
wra+2.311
ghazi+2.305
Neg logit contributions
Appearances-3.624
interstitial-3.619
-3.540
NPR-3.423
 barn-3.403
Token at
Token ID379
Feature activation+3.81e+00

Pos logit contributions
zos+5.190
oint+4.906
kus+4.574
estine+4.383
wra+4.363
Neg logit contributions
interstitial-4.543
Appearances-4.506
-4.412
NPR-4.169
 barn-4.155
Token Bills
Token ID20209
Feature activation+3.82e+00

Pos logit contributions
zos+2.010
oint+1.853
kus+1.772
wra+1.732
ghazi+1.727
Neg logit contributions
Appearances-1.322
interstitial-1.305
-1.280
NPR-1.225
 barn-1.224
Token:
Token ID25
Feature activation-2.04e-01

Pos logit contributions
zos+3.241
oint+3.000
kus+2.849
wra+2.781
ghazi+2.752
Neg logit contributions
Appearances-2.694
interstitial-2.667
-2.633
NPR-2.526
 barn-2.517
Token G
Token ID402
Feature activation-2.27e+00

Pos logit contributions
Appearances+0.133
interstitial+0.131
+0.129
 barn+0.125
NPR+0.122
Neg logit contributions
zos-0.190
oint-0.173
kus-0.165
wra-0.162
ghazi-0.161
Token Richie
Token ID49209
Feature activation-3.77e+00

Pos logit contributions
Appearances+1.566
interstitial+1.523
+1.515
 barn+1.486
 Emmy+1.451
Neg logit contributions
zos-2.025
oint-1.820
kus-1.741
wra-1.700
ghazi-1.684
Token Inc
Token ID3457
Feature activation-4.23e+00

Pos logit contributions
Appearances+2.506
interstitial+2.412
+2.379
 barn+2.372
 Emmy+2.314
Neg logit contributions
zos-3.473
oint-3.125
kus-3.005
ghazi-2.924
wra-2.906
Tokenogn
Token ID2360
Feature activation+1.13e+01

Pos logit contributions
Appearances+3.221
interstitial+3.083
 barn+3.079
+3.034
NPR+3.006
Neg logit contributions
zos-3.359
oint-3.024
kus-2.866
wra-2.824
ghazi-2.822
Tokenito
Token ID10094
Feature activation+3.34e+00

Pos logit contributions
zos+6.181
oint+5.073
kus+4.787
estine+4.630
ghazi+4.592
Neg logit contributions
-11.409
Appearances-11.212
interstitial-11.211
 barn-10.718
NPR-10.533
Token
Token ID198
Feature activation-6.27e-01

Pos logit contributions
zos+2.685
oint+2.433
kus+2.314
wra+2.258
ghazi+2.225
Neg logit contributions
Appearances-2.553
interstitial-2.527
-2.475
 barn-2.399
NPR-2.398
Token
Token ID198
Feature activation-3.37e+00

Pos logit contributions
Appearances+0.397
interstitial+0.374
+0.373
 barn+0.370
NPR+0.368
Neg logit contributions
zos-0.597
oint-0.539
kus-0.518
ghazi-0.510
wra-0.508
TokenContract
Token ID45845
Feature activation-4.43e+00

Pos logit contributions
Appearances+2.389
interstitial+2.235
+2.226
NPR+2.176
 barn+2.082
Neg logit contributions
zos-3.052
oint-2.722
kus-2.614
estine-2.552
utsche-2.532
Token:
Token ID25
Feature activation-2.67e+00

Pos logit contributions
Appearances+2.945
interstitial+2.862
+2.834
 barn+2.767
 Emmy+2.694
Neg logit contributions
zos-4.055
oint-3.636
kus-3.500
ghazi-3.446
estine-3.433
Token or
Token ID393
Feature activation+5.48e-01

Pos logit contributions
zos+1.455
oint+1.318
kus+1.256
wra+1.226
ghazi+1.212
Neg logit contributions
Appearances-1.197
interstitial-1.191
-1.166
 barn-1.106
NPR-1.103
Token even
Token ID772
Feature activation-1.46e+00

Pos logit contributions
zos+0.482
oint+0.437
kus+0.417
wra+0.407
ghazi+0.406
Neg logit contributions
Appearances-0.385
interstitial-0.379
-0.373
 barn-0.363
NPR-0.357
Token take
Token ID1011
Feature activation+1.82e+00

Pos logit contributions
Appearances+0.992
interstitial+0.974
 barn+0.958
+0.958
NPR+0.930
Neg logit contributions
zos-1.292
oint-1.173
kus-1.117
ghazi-1.103
wra-1.095
Token a
Token ID257
Feature activation+1.14e+00

Pos logit contributions
zos+1.493
oint+1.350
kus+1.276
wra+1.249
ghazi+1.233
Neg logit contributions
Appearances-1.387
interstitial-1.374
-1.348
 barn-1.288
NPR-1.284
Token small
Token ID1402
Feature activation-1.31e+00

Pos logit contributions
zos+1.074
oint+0.986
kus+0.944
wra+0.922
ghazi+0.916
Neg logit contributions
Appearances-0.730
interstitial-0.725
-0.705
NPR-0.668
 barn-0.667
Token nap
Token ID25422
Feature activation+1.11e+01

Pos logit contributions
Appearances+0.830
interstitial+0.815
+0.801
 barn+0.783
NPR+0.766
Neg logit contributions
zos-1.233
oint-1.122
kus-1.077
ghazi-1.053
wra-1.053
Token if
Token ID611
Feature activation+2.25e+00

Pos logit contributions
zos+9.069
oint+8.405
wra+7.749
kus+7.669
estine+7.525
Neg logit contributions
interstitial-7.903
Appearances-7.903
-7.762
NPR-7.059
 Emmy-6.883
Token you
Token ID345
Feature activation+3.33e+00

Pos logit contributions
zos+1.887
oint+1.708
kus+1.609
wra+1.577
ghazi+1.564
Neg logit contributions
Appearances-1.679
interstitial-1.670
-1.638
 barn-1.559
NPR-1.557
Token can
Token ID460
Feature activation+2.16e+00

Pos logit contributions
zos+3.046
oint+2.774
kus+2.643
wra+2.584
ghazi+2.554
Neg logit contributions
Appearances-2.241
interstitial-2.226
-2.169
 barn-2.058
NPR-2.052
Token.
Token ID13
Feature activation+2.27e+00

Pos logit contributions
zos+1.689
oint+1.519
kus+1.436
wra+1.393
ghazi+1.380
Neg logit contributions
Appearances-1.740
interstitial-1.723
-1.695
 barn-1.625
NPR-1.618
Token
Token ID198
Feature activation+6.69e-01

Pos logit contributions
zos+2.069
oint+1.889
kus+1.794
wra+1.764
ghazi+1.754
Neg logit contributions
interstitial-1.511
Appearances-1.502
-1.467
 barn-1.413
NPR-1.384
Token the
Token ID262
Feature activation+2.24e+00

Pos logit contributions
Appearances+0.515
interstitial+0.508
+0.498
 barn+0.484
NPR+0.477
Neg logit contributions
zos-0.673
oint-0.611
kus-0.583
wra-0.570
ghazi-0.568
Token great
Token ID1049
Feature activation+1.22e+00

Pos logit contributions
zos+2.043
oint+1.871
kus+1.780
wra+1.740
ghazi+1.726
Neg logit contributions
Appearances-1.493
interstitial-1.487
-1.454
NPR-1.373
 barn-1.371
Token news
Token ID1705
Feature activation+8.17e-01

Pos logit contributions
zos+1.127
oint+1.029
kus+0.983
wra+0.962
ghazi+0.957
Neg logit contributions
Appearances-0.805
interstitial-0.795
-0.778
 barn-0.751
NPR-0.742
Token of
Token ID286
Feature activation+1.38e+00

Pos logit contributions
zos+0.770
oint+0.704
kus+0.672
wra+0.660
ghazi+0.656
Neg logit contributions
Appearances-0.521
interstitial-0.514
-0.504
 barn-0.485
NPR-0.478
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
zos+1.219
oint+1.108
kus+1.054
wra+1.032
ghazi+1.028
Neg logit contributions
Appearances-0.961
interstitial-0.949
-0.932
 barn-0.900
NPR-0.891
Token OCT
Token ID42256
Feature activation+1.10e+01

Pos logit contributions
Appearances+0.795
interstitial+0.778
+0.765
 barn+0.750
NPR+0.733
Neg logit contributions
zos-1.165
oint-1.059
kus-1.017
wra-0.993
ghazi-0.991
TokenA
Token ID32
Feature activation+1.63e+00

Pos logit contributions
zos+9.080
oint+8.383
wra+7.690
ghazi+7.656
estine+7.548
Neg logit contributions
interstitial-7.531
Appearances-7.524
-7.256
ozyg-6.673
 barn-6.671
Token receiving
Token ID6464
Feature activation-1.36e+00

Pos logit contributions
zos+1.485
oint+1.356
kus+1.285
wra+1.262
ghazi+1.260
Neg logit contributions
Appearances-1.082
interstitial-1.079
-1.047
 barn-1.004
NPR-0.998
Token the
Token ID262
Feature activation+1.13e+00

Pos logit contributions
Appearances+0.909
interstitial+0.896
+0.878
 barn+0.857
NPR+0.842
Neg logit contributions
zos-1.242
oint-1.129
kus-1.077
wra-1.054
ghazi-1.052
Token welcome
Token ID7062
Feature activation+2.04e+00

Pos logit contributions
zos+1.025
oint+0.935
kus+0.894
wra+0.874
ghazi+0.868
Neg logit contributions
Appearances-0.755
interstitial-0.744
-0.731
 barn-0.703
NPR-0.697
Token endorsement
Token ID17819
Feature activation-1.90e+00

Pos logit contributions
zos+1.789
oint+1.634
kus+1.560
wra+1.533
ghazi+1.503
Neg logit contributions
Appearances-1.430
interstitial-1.399
-1.391
 barn-1.312
NPR-1.310
Token guards
Token ID10942
Feature activation+1.84e+00

Pos logit contributions
zos+2.762
oint+2.429
kus+2.230
wra+2.194
ghazi+2.143
Neg logit contributions
interstitial-4.664
Appearances-4.661
-4.544
NPR-4.433
 barn-4.392
Token)
Token ID8
Feature activation-2.02e+00

Pos logit contributions
zos+1.333
oint+1.180
kus+1.113
wra+1.080
ghazi+1.076
Neg logit contributions
Appearances-1.575
interstitial-1.556
-1.534
 barn-1.499
NPR-1.483
Token
Token ID198
Feature activation+4.98e-01

Pos logit contributions
Appearances+1.349
interstitial+1.325
+1.306
 barn+1.261
NPR+1.242
Neg logit contributions
zos-1.854
oint-1.678
kus-1.609
wra-1.569
ghazi-1.566
Token
Token ID198
Feature activation-1.18e+00

Pos logit contributions
zos+0.464
oint+0.419
kus+0.403
ghazi+0.395
wra+0.394
Neg logit contributions
Appearances-0.325
interstitial-0.313
-0.309
 barn-0.303
NPR-0.302
TokenInc
Token ID25517
Feature activation-8.06e-01

Pos logit contributions
Appearances+0.821
interstitial+0.793
+0.779
NPR+0.754
 barn+0.742
Neg logit contributions
zos-1.062
oint-0.959
kus-0.916
wra-0.887
ghazi-0.887
Tokenogn
Token ID2360
Feature activation+1.09e+01

Pos logit contributions
Appearances+0.662
interstitial+0.655
+0.646
 barn+0.630
NPR+0.623
Neg logit contributions
zos-0.611
oint-0.542
kus-0.515
wra-0.499
ghazi-0.499
Tokenito
Token ID10094
Feature activation+6.75e+00

Pos logit contributions
zos+6.069
oint+5.207
estine+4.772
kus+4.706
wra+4.495
Neg logit contributions
interstitial-10.911
-10.899
Appearances-10.636
���-10.559
 barn-10.413
Token
Token ID447
Feature activation+2.18e+00

Pos logit contributions
zos+6.116
oint+5.612
kus+5.401
wra+5.342
ghazi+5.202
Neg logit contributions
Appearances-4.322
interstitial-4.320
-4.096
NPR-4.002
 barn-3.914
Token
Token ID247
Feature activation-5.14e-01

Pos logit contributions
zos+1.759
oint+1.600
kus+1.518
wra+1.480
ghazi+1.475
Neg logit contributions
Appearances-1.651
interstitial-1.634
-1.623
 barn-1.566
NPR-1.543
Tokens
Token ID82
Feature activation-7.24e-01

Pos logit contributions
Appearances+0.336
interstitial+0.332
+0.326
 barn+0.316
NPR+0.310
Neg logit contributions
zos-0.477
oint-0.433
kus-0.413
ghazi-0.405
wra-0.403
Token 2013
Token ID2211
Feature activation-3.04e+00

Pos logit contributions
Appearances+0.507
interstitial+0.501
+0.492
 barn+0.479
NPR+0.471
Neg logit contributions
zos-0.638
oint-0.576
kus-0.550
wra-0.537
ghazi-0.535
Token 0
Token ID657
Feature activation+1.48e+00

Pos logit contributions
zos+2.675
oint+2.456
kus+2.328
wra+2.292
ghazi+2.244
Neg logit contributions
Appearances-1.989
interstitial-1.956
-1.913
NPR-1.819
 barn-1.813
Token.
Token ID13
Feature activation+3.04e+00

Pos logit contributions
zos+1.180
oint+1.063
kus+1.005
wra+0.980
ghazi+0.973
Neg logit contributions
Appearances-1.159
interstitial-1.144
-1.125
 barn-1.093
NPR-1.081
Token0
Token ID15
Feature activation-9.50e-02

Pos logit contributions
zos+2.297
oint+2.041
kus+1.932
wra+1.893
ghazi+1.859
Neg logit contributions
Appearances-2.513
interstitial-2.490
-2.454
 barn-2.381
NPR-2.348
Tokenf
Token ID69
Feature activation+2.77e+00

Pos logit contributions
Appearances+0.076
interstitial+0.075
+0.074
 barn+0.072
NPR+0.071
Neg logit contributions
zos-0.075
oint-0.067
kus-0.063
wra-0.062
ghazi-0.061
Token);
Token ID1776
Feature activation-2.14e+00

Pos logit contributions
zos+2.158
oint+1.938
kus+1.813
wra+1.777
ghazi+1.758
Neg logit contributions
Appearances-2.233
interstitial-2.206
-2.161
 barn-2.099
NPR-2.074
Token RAW
Token ID33782
Feature activation+1.08e+01

Pos logit contributions
Appearances+1.345
interstitial+1.322
+1.301
 barn+1.276
NPR+1.244
Neg logit contributions
zos-2.017
oint-1.840
kus-1.770
ghazi-1.729
wra-1.722
Token_
Token ID62
Feature activation+2.27e+00

Pos logit contributions
zos+8.451
oint+7.710
kus+7.196
wra+7.076
estine+6.855
Neg logit contributions
interstitial-7.922
Appearances-7.823
-7.462
 barn-7.319
 Emmy-7.282
TokenASS
Token ID10705
Feature activation+5.26e+00

Pos logit contributions
zos+1.954
oint+1.776
kus+1.687
wra+1.657
ghazi+1.631
Neg logit contributions
Appearances-1.631
interstitial-1.609
-1.585
 barn-1.542
NPR-1.506
TokenERT
Token ID17395
Feature activation-1.23e-01

Pos logit contributions
zos+4.003
oint+3.657
kus+3.355
wra+3.275
estine+3.251
Neg logit contributions
Appearances-4.231
interstitial-4.206
-4.137
 barn-3.946
 Emmy-3.840
Token(
Token ID7
Feature activation+7.16e+00

Pos logit contributions
Appearances+0.091
interstitial+0.090
+0.089
 barn+0.086
NPR+0.085
Neg logit contributions
zos-0.103
oint-0.093
kus-0.089
wra-0.086
ghazi-0.086
Tokenit
Token ID270
Feature activation+8.20e+00

Pos logit contributions
zos+6.007
oint+5.429
kus+5.189
wra+5.152
ghazi+4.938
Neg logit contributions
Appearances-5.150
interstitial-5.032
-4.973
 barn-4.823
 Emmy-4.752
Token 10
Token ID838
Feature activation+1.45e+00

Pos logit contributions
zos+1.333
oint+1.218
kus+1.161
wra+1.140
ghazi+1.132
Neg logit contributions
Appearances-0.936
interstitial-0.927
-0.909
 barn-0.874
NPR-0.864
Token,
Token ID11
Feature activation+7.19e-01

Pos logit contributions
zos+1.262
oint+1.147
kus+1.093
wra+1.069
ghazi+1.063
Neg logit contributions
Appearances-1.029
interstitial-1.021
-1.000
 barn-0.969
NPR-0.958
Token 2013
Token ID2211
Feature activation-1.99e+00

Pos logit contributions
zos+0.663
oint+0.604
kus+0.576
wra+0.565
ghazi+0.562
Neg logit contributions
Appearances-0.474
interstitial-0.468
-0.458
 barn-0.442
NPR-0.437
Token
Token ID198
Feature activation+3.54e+00

Pos logit contributions
Appearances+1.295
interstitial+1.265
+1.248
 barn+1.210
NPR+1.187
Neg logit contributions
zos-1.852
oint-1.682
kus-1.612
wra-1.577
ghazi-1.574
Token
Token ID198
Feature activation+1.94e+00

Pos logit contributions
zos+3.079
oint+2.807
kus+2.668
wra+2.603
ghazi+2.580
Neg logit contributions
interstitial-2.500
Appearances-2.489
-2.441
 barn-2.345
NPR-2.303
TokenPe
Token ID6435
Feature activation+1.08e+01

Pos logit contributions
zos+1.732
oint+1.575
kus+1.501
wra+1.471
ghazi+1.463
Neg logit contributions
Appearances-1.320
interstitial-1.315
-1.288
 barn-1.255
NPR-1.222
Tokenak
Token ID461
Feature activation+2.72e+00

Pos logit contributions
zos+7.569
oint+6.363
kus+5.854
utsche+5.676
estine+5.573
Neg logit contributions
Appearances-9.555
interstitial-9.354
-9.167
 barn-9.067
 Emmy-8.911
Token price
Token ID2756
Feature activation+8.60e-01

Pos logit contributions
zos+2.371
oint+2.169
kus+2.051
wra+2.015
ghazi+1.991
Neg logit contributions
Appearances-1.907
interstitial-1.895
-1.866
 barn-1.786
NPR-1.770
Token:
Token ID25
Feature activation-4.27e+00

Pos logit contributions
zos+0.782
oint+0.711
kus+0.679
wra+0.664
ghazi+0.662
Neg logit contributions
Appearances-0.578
interstitial-0.571
-0.561
 barn-0.541
NPR-0.535
Token $
Token ID720
Feature activation+2.23e+00

Pos logit contributions
Appearances+2.924
interstitial+2.875
+2.841
 barn+2.774
NPR+2.724
Neg logit contributions
zos-3.754
oint-3.404
kus-3.255
ghazi-3.174
wra-3.158
Token266
Token ID25540
Feature activation-2.07e+00

Pos logit contributions
zos+2.076
oint+1.894
kus+1.810
wra+1.773
ghazi+1.766
Neg logit contributions
Appearances-1.441
interstitial-1.424
-1.393
 barn-1.349
NPR-1.327
Token,
Token ID11
Feature activation+3.53e+00

Pos logit contributions
zos+1.407
oint+1.264
kus+1.192
wra+1.146
ghazi+1.146
Neg logit contributions
Appearances-1.560
interstitial-1.555
-1.526
 barn-1.480
NPR-1.469
Token Mass
Token ID5674
Feature activation+6.80e+00

Pos logit contributions
zos+2.704
oint+2.452
kus+2.293
ghazi+2.238
wra+2.228
Neg logit contributions
Appearances-2.833
interstitial-2.829
-2.787
 barn-2.679
NPR-2.669
Token.
Token ID13
Feature activation+4.90e+00

Pos logit contributions
zos+4.726
oint+4.190
kus+3.951
wra+3.790
ghazi+3.773
Neg logit contributions
interstitial-5.846
Appearances-5.752
-5.705
 barn-5.554
NPR-5.486
Token --
Token ID1377
Feature activation+1.13e+00

Pos logit contributions
zos+3.879
oint+3.531
kus+3.366
wra+3.300
ghazi+3.297
Neg logit contributions
interstitial-3.689
Appearances-3.630
-3.555
 barn-3.446
NPR-3.378
Token Boston
Token ID6182
Feature activation+5.54e+00

Pos logit contributions
zos+1.062
oint+0.972
kus+0.930
wra+0.910
ghazi+0.908
Neg logit contributions
Appearances-0.719
interstitial-0.712
-0.695
 barn-0.671
NPR-0.661
Token Celtics
Token ID24116
Feature activation+1.07e+01

Pos logit contributions
zos+4.864
oint+4.428
kus+4.297
ghazi+4.212
wra+4.175
Neg logit contributions
interstitial-3.703
Appearances-3.699
-3.608
NPR-3.496
 barn-3.384
Token swing
Token ID9628
Feature activation+6.11e+00

Pos logit contributions
zos+7.868
oint+7.498
kus+7.010
wra+6.949
ghazi+6.902
Neg logit contributions
interstitial-7.898
Appearances-7.798
-7.589
NPR-7.112
ozyg-7.013
Tokenman
Token ID805
Feature activation+1.97e+00

Pos logit contributions
zos+4.941
oint+4.515
kus+4.370
wra+4.274
ghazi+4.198
Neg logit contributions
interstitial-4.545
Appearances-4.518
-4.463
 barn-4.216
NPR-4.204
Token Jae
Token ID34521
Feature activation+6.66e+00

Pos logit contributions
zos+1.812
oint+1.660
kus+1.581
wra+1.558
ghazi+1.551
Neg logit contributions
Appearances-1.282
interstitial-1.275
-1.247
 barn-1.188
NPR-1.187
Token Crow
Token ID15502
Feature activation-1.34e+00

Pos logit contributions
zos+6.030
oint+5.756
kus+5.376
wra+5.358
estine+5.287
Neg logit contributions
interstitial-4.331
-4.245
Appearances-4.158
 barn-3.929
NPR-3.910
Tokender
Token ID1082
Feature activation+2.77e-01

Pos logit contributions
Appearances+0.835
interstitial+0.822
+0.805
 barn+0.779
NPR+0.767
Neg logit contributions
zos-1.290
oint-1.179
kus-1.129
wra-1.107
ghazi-1.103
Token needs
Token ID2476
Feature activation+1.31e+00

Pos logit contributions
zos+1.244
oint+1.134
kus+1.083
wra+1.060
ghazi+1.052
Neg logit contributions
Appearances-0.908
interstitial-0.900
-0.879
 barn-0.850
NPR-0.843
Token to
Token ID284
Feature activation+2.32e+00

Pos logit contributions
zos+1.114
oint+1.008
kus+0.959
wra+0.936
ghazi+0.930
Neg logit contributions
Appearances-0.954
interstitial-0.942
-0.926
 barn-0.897
NPR-0.888
Token be
Token ID307
Feature activation+2.30e+00

Pos logit contributions
zos+2.006
oint+1.820
kus+1.744
wra+1.690
ghazi+1.671
Neg logit contributions
Appearances-1.663
interstitial-1.650
-1.611
NPR-1.546
 barn-1.543
Token connected
Token ID5884
Feature activation+4.44e+00

Pos logit contributions
zos+2.081
oint+1.895
kus+1.810
wra+1.773
ghazi+1.752
Neg logit contributions
Appearances-1.556
interstitial-1.542
-1.512
NPR-1.443
 barn-1.440
Token to
Token ID284
Feature activation+2.03e+00

Pos logit contributions
zos+3.626
oint+3.279
kus+3.118
wra+3.053
ghazi+2.998
Neg logit contributions
interstitial-3.363
Appearances-3.352
-3.264
 barn-3.132
NPR-3.124
Token Live
Token ID7547
Feature activation+1.06e+01

Pos logit contributions
zos+1.690
oint+1.527
kus+1.453
wra+1.414
ghazi+1.399
Neg logit contributions
Appearances-1.518
interstitial-1.508
-1.477
 barn-1.421
NPR-1.414
Token.
Token ID13
Feature activation+5.98e-01

Pos logit contributions
zos+8.674
oint+7.926
kus+7.475
wra+7.264
ghazi+7.232
Neg logit contributions
interstitial-7.760
Appearances-7.427
-7.280
 barn-6.882
NPR-6.827
Token Has
Token ID7875
Feature activation+7.02e-01

Pos logit contributions
zos+0.544
oint+0.495
kus+0.472
wra+0.462
ghazi+0.460
Neg logit contributions
Appearances-0.402
interstitial-0.397
-0.389
 barn-0.377
NPR-0.372
Token two
Token ID734
Feature activation-2.53e+00

Pos logit contributions
zos+0.612
oint+0.554
kus+0.528
wra+0.516
ghazi+0.516
Neg logit contributions
Appearances-0.498
interstitial-0.491
-0.482
 barn-0.469
NPR-0.462
Token characters
Token ID3435
Feature activation+7.95e-01

Pos logit contributions
Appearances+1.769
interstitial+1.731
+1.698
 barn+1.691
 Emmy+1.641
Neg logit contributions
zos-2.218
oint-2.008
kus-1.909
ghazi-1.883
wra-1.871
Token of
Token ID286
Feature activation-2.25e+00

Pos logit contributions
zos+0.680
oint+0.615
kus+0.585
wra+0.572
ghazi+0.568
Neg logit contributions
Appearances-0.576
interstitial-0.570
-0.560
 barn-0.543
NPR-0.537
Token.
Token ID13
Feature activation+6.38e-01

Pos logit contributions
zos+2.800
oint+2.542
kus+2.387
wra+2.356
ghazi+2.334
Neg logit contributions
Appearances-2.520
interstitial-2.514
-2.456
NPR-2.349
 barn-2.344
Token<|endoftext|>
Token ID50256
Feature activation-4.69e+00

Pos logit contributions
zos+0.608
oint+0.557
kus+0.532
wra+0.522
ghazi+0.520
Neg logit contributions
Appearances-0.399
interstitial-0.397
-0.386
 barn-0.372
NPR-0.366
TokenLong
Token ID14617
Feature activation+2.97e+00

Pos logit contributions
Appearances+3.307
interstitial+3.180
NPR+3.094
+3.065
 barn+2.944
Neg logit contributions
zos-4.136
oint-3.733
kus-3.542
estine-3.459
ghazi-3.455
Tokenview
Token ID1177
Feature activation-6.28e-01

Pos logit contributions
zos+2.555
oint+2.304
kus+2.199
wra+2.160
ghazi+2.135
Neg logit contributions
Appearances-2.132
interstitial-2.113
-2.066
NPR-1.988
 barn-1.986
Token,
Token ID11
Feature activation+3.74e+00

Pos logit contributions
Appearances+0.453
interstitial+0.447
+0.439
 barn+0.426
NPR+0.421
Neg logit contributions
zos-0.540
oint-0.489
kus-0.466
wra-0.455
ghazi-0.453
Token Wash
Token ID22892
Feature activation+1.04e+01

Pos logit contributions
zos+3.239
oint+2.968
kus+2.815
wra+2.792
estine+2.710
Neg logit contributions
Appearances-2.601
interstitial-2.601
-2.564
 barn-2.427
NPR-2.424
Token.,
Token ID1539
Feature activation+2.51e+00

Pos logit contributions
zos+6.607
oint+5.995
kus+5.687
wra+5.490
estine+5.350
Neg logit contributions
interstitial-9.161
-8.924
Appearances-8.876
 barn-8.527
NPR-8.457
Token police
Token ID1644
Feature activation+4.61e+00

Pos logit contributions
zos+2.228
oint+2.040
kus+1.945
wra+1.912
ghazi+1.881
Neg logit contributions
Appearances-1.698
interstitial-1.694
-1.666
 barn-1.576
NPR-1.569
Token say
Token ID910
Feature activation+8.96e-01

Pos logit contributions
zos+4.036
oint+3.704
kus+3.512
wra+3.424
ghazi+3.398
Neg logit contributions
interstitial-3.188
Appearances-3.184
-3.122
NPR-2.898
 barn-2.880
Token a
Token ID257
Feature activation+1.57e+00

Pos logit contributions
zos+0.797
oint+0.724
kus+0.691
wra+0.675
ghazi+0.671
Neg logit contributions
Appearances-0.620
interstitial-0.611
-0.602
 barn-0.577
NPR-0.574
Token man
Token ID582
Feature activation+2.37e+00

Pos logit contributions
zos+1.410
oint+1.287
kus+1.234
wra+1.197
ghazi+1.192
Neg logit contributions
Appearances-1.072
interstitial-1.057
-1.039
NPR-0.988
 barn-0.976
Token us
Token ID514
Feature activation-1.88e+00

Pos logit contributions
Appearances+1.282
interstitial+1.258
+1.239
 barn+1.218
NPR+1.195
Neg logit contributions
zos-1.541
oint-1.387
kus-1.322
wra-1.294
ghazi-1.290
Token.
Token ID13
Feature activation-1.23e+00

Pos logit contributions
Appearances+1.292
interstitial+1.272
+1.249
 barn+1.239
NPR+1.204
Neg logit contributions
zos-1.665
oint-1.503
kus-1.430
wra-1.410
ghazi-1.407
Token If
Token ID1002
Feature activation+3.17e-01

Pos logit contributions
Appearances+0.759
interstitial+0.744
+0.731
 barn+0.708
NPR+0.699
Neg logit contributions
zos-1.180
oint-1.078
kus-1.034
wra-1.011
ghazi-1.008
Token that
Token ID326
Feature activation+3.07e-01

Pos logit contributions
zos+0.275
oint+0.249
kus+0.237
wra+0.232
ghazi+0.231
Neg logit contributions
Appearances-0.226
interstitial-0.223
-0.219
 barn-0.213
NPR-0.210
Token didn
Token ID1422
Feature activation+9.43e+00

Pos logit contributions
zos+0.277
oint+0.252
kus+0.240
wra+0.235
ghazi+0.234
Neg logit contributions
Appearances-0.209
interstitial-0.206
-0.202
 barn-0.196
NPR-0.194
Token't
Token ID470
Feature activation+1.04e+01

Pos logit contributions
zos+4.943
oint+4.386
kus+3.978
wra+3.685
estine+3.502
Neg logit contributions
interstitial-9.936
eatures-9.826
���-9.550
-9.523
Appearances-9.421
Token convince
Token ID11508
Feature activation+4.68e+00

Pos logit contributions
zos+7.864
oint+7.320
kus+7.193
estine+6.584
wra+6.475
Neg logit contributions
interstitial-8.319
-8.038
Appearances-7.973
NPR-7.182
eatures-6.920
Token you
Token ID345
Feature activation+1.96e+00

Pos logit contributions
zos+3.696
oint+3.340
kus+3.167
wra+3.067
estine+3.032
Neg logit contributions
interstitial-3.644
Appearances-3.612
-3.603
NPR-3.363
 barn-3.346
Token,
Token ID11
Feature activation+1.78e+00

Pos logit contributions
zos+1.527
oint+1.367
kus+1.291
wra+1.257
ghazi+1.250
Neg logit contributions
Appearances-1.567
interstitial-1.556
-1.532
 barn-1.480
NPR-1.469
Token perhaps
Token ID3737
Feature activation+1.57e+00

Pos logit contributions
zos+1.487
oint+1.339
kus+1.279
wra+1.239
ghazi+1.230
Neg logit contributions
Appearances-1.326
interstitial-1.317
-1.295
 barn-1.235
NPR-1.226
Token their
Token ID511
Feature activation+3.46e-01

Pos logit contributions
zos+1.364
oint+1.237
kus+1.182
wra+1.148
ghazi+1.140
Neg logit contributions
Appearances-1.126
interstitial-1.111
-1.095
 barn-1.051
NPR-1.041
Token this
Token ID428
Feature activation-1.39e+00

Pos logit contributions
zos+2.821
oint+2.595
kus+2.411
wra+2.381
ghazi+2.355
Neg logit contributions
Appearances-2.590
interstitial-2.559
-2.557
NPR-2.401
 barn-2.380
Token approach
Token ID3164
Feature activation+1.65e+00

Pos logit contributions
Appearances+0.977
interstitial+0.965
+0.941
 barn+0.931
NPR+0.911
Neg logit contributions
zos-1.222
oint-1.101
kus-1.052
wra-1.028
ghazi-1.021
Token.
Token ID13
Feature activation+1.00e+00

Pos logit contributions
zos+1.336
oint+1.207
kus+1.144
wra+1.115
ghazi+1.109
Neg logit contributions
Appearances-1.272
interstitial-1.267
-1.246
NPR-1.188
 barn-1.186
Token He
Token ID679
Feature activation+5.05e-01

Pos logit contributions
zos+0.921
oint+0.844
kus+0.803
ghazi+0.789
wra+0.787
Neg logit contributions
interstitial-0.660
Appearances-0.656
-0.638
 barn-0.615
NPR-0.602
Token ordered
Token ID6149
Feature activation+2.40e+00

Pos logit contributions
zos+0.479
oint+0.438
kus+0.419
wra+0.410
ghazi+0.409
Neg logit contributions
Appearances-0.319
interstitial-0.314
-0.308
 barn-0.299
NPR-0.294
Token Cabinet
Token ID20384
Feature activation+1.03e+01

Pos logit contributions
zos+2.103
oint+1.929
kus+1.814
wra+1.785
ghazi+1.774
Neg logit contributions
Appearances-1.698
interstitial-1.673
-1.646
 barn-1.561
NPR-1.555
Token secretaries
Token ID49431
Feature activation+4.68e+00

Pos logit contributions
zos+7.117
oint+6.605
kus+5.860
ghazi+5.818
wra+5.814
Neg logit contributions
interstitial-8.829
-8.593
Appearances-8.543
NPR-8.131
 barn-7.936
Token not
Token ID407
Feature activation+1.53e+00

Pos logit contributions
zos+3.743
oint+3.388
kus+3.158
ghazi+3.118
wra+3.108
Neg logit contributions
interstitial-3.637
Appearances-3.625
-3.527
 barn-3.346
NPR-3.340
Token to
Token ID284
Feature activation+2.12e+00

Pos logit contributions
zos+1.265
oint+1.144
kus+1.083
wra+1.057
ghazi+1.054
Neg logit contributions
Appearances-1.161
interstitial-1.156
-1.134
 barn-1.091
NPR-1.082
Token do
Token ID466
Feature activation+2.77e-01

Pos logit contributions
zos+1.843
oint+1.677
kus+1.595
wra+1.554
ghazi+1.545
Neg logit contributions
Appearances-1.513
interstitial-1.499
-1.469
 barn-1.405
NPR-1.398
Token their
Token ID511
Feature activation+3.40e+00

Pos logit contributions
zos+0.262
oint+0.240
kus+0.229
wra+0.225
ghazi+0.224
Neg logit contributions
Appearances-0.176
interstitial-0.173
-0.170
 barn-0.164
NPR-0.162
Token,
Token ID11
Feature activation+2.17e+00

Pos logit contributions
zos+0.739
oint+0.666
kus+0.631
wra+0.612
ghazi+0.605
Neg logit contributions
Appearances-0.801
interstitial-0.790
-0.785
 barn-0.759
NPR-0.752
Token000
Token ID830
Feature activation+2.09e+00

Pos logit contributions
zos+1.979
oint+1.818
kus+1.722
wra+1.702
ghazi+1.682
Neg logit contributions
Appearances-1.440
interstitial-1.407
-1.401
 barn-1.342
NPR-1.321
Token;
Token ID26
Feature activation-3.81e+00

Pos logit contributions
zos+1.733
oint+1.584
kus+1.499
wra+1.469
ghazi+1.449
Neg logit contributions
Appearances-1.552
interstitial-1.527
-1.524
 barn-1.456
NPR-1.444
Token field
Token ID2214
Feature activation-4.09e+00

Pos logit contributions
Appearances+2.463
interstitial+2.443
+2.374
 barn+2.340
NPR+2.297
Neg logit contributions
zos-3.524
oint-3.172
kus-3.065
ghazi-2.981
wra-2.969
Token 36
Token ID4570
Feature activation+1.17e+00

Pos logit contributions
Appearances+2.839
interstitial+2.779
+2.699
 barn+2.670
NPR+2.622
Neg logit contributions
zos-3.605
oint-3.216
kus-3.092
ghazi-3.029
estine-3.018
Token batt
Token ID6274
Feature activation+1.03e+01

Pos logit contributions
zos+0.912
oint+0.818
kus+0.774
wra+0.753
ghazi+0.750
Neg logit contributions
Appearances-0.935
interstitial-0.924
-0.910
 barn-0.886
NPR-0.876
Tokenalions
Token ID50022
Feature activation+9.17e-01

Pos logit contributions
zos+4.461
oint+3.856
kus+3.607
wra+3.257
estine+3.181
Neg logit contributions
-11.495
Appearances-11.167
interstitial-10.907
 Emmy-10.648
���-10.518
Token of
Token ID286
Feature activation-2.47e+00

Pos logit contributions
zos+0.788
oint+0.716
kus+0.681
wra+0.667
ghazi+0.661
Neg logit contributions
Appearances-0.661
interstitial-0.652
-0.644
 barn-0.619
NPR-0.612
Token Marines
Token ID19586
Feature activation+6.40e+00

Pos logit contributions
Appearances+1.676
interstitial+1.663
+1.607
 barn+1.584
NPR+1.553
Neg logit contributions
zos-2.230
oint-2.006
kus-1.926
wra-1.879
ghazi-1.879
Token;
Token ID26
Feature activation-1.25e+00

Pos logit contributions
zos+4.898
oint+4.492
kus+4.205
wra+4.188
ghazi+4.087
Neg logit contributions
Appearances-4.894
-4.881
interstitial-4.813
 barn-4.590
 Emmy-4.532
Token set
Token ID900
Feature activation+1.71e+00

Pos logit contributions
Appearances+0.858
interstitial+0.847
+0.831
 barn+0.810
NPR+0.796
Neg logit contributions
zos-1.124
oint-1.018
kus-0.974
wra-0.951
ghazi-0.949
Token You
Token ID921
Feature activation+1.70e+00

Pos logit contributions
zos+1.609
oint+1.466
kus+1.403
wra+1.375
ghazi+1.370
Neg logit contributions
Appearances-1.090
interstitial-1.075
-1.052
 barn-1.020
NPR-1.007
Token will
Token ID481
Feature activation+1.55e+00

Pos logit contributions
zos+1.537
oint+1.399
kus+1.335
wra+1.305
ghazi+1.299
Neg logit contributions
Appearances-1.154
interstitial-1.138
-1.119
 barn-1.082
NPR-1.068
Token receive
Token ID3328
Feature activation+1.73e+00

Pos logit contributions
zos+1.225
oint+1.096
kus+1.040
wra+1.014
ghazi+1.010
Neg logit contributions
Appearances-1.220
interstitial-1.206
-1.184
 barn-1.158
NPR-1.144
Token emails
Token ID7237
Feature activation+2.76e-01

Pos logit contributions
zos+1.470
oint+1.334
kus+1.268
wra+1.235
ghazi+1.226
Neg logit contributions
Appearances-1.259
interstitial-1.235
-1.223
 barn-1.179
NPR-1.163
Token containing
Token ID7268
Feature activation+2.25e+00

Pos logit contributions
zos+0.260
oint+0.236
kus+0.227
ghazi+0.222
wra+0.221
Neg logit contributions
Appearances-0.176
interstitial-0.175
-0.170
 barn-0.166
NPR-0.163
Token news
Token ID1705
Feature activation+1.02e+01

Pos logit contributions
zos+1.601
oint+1.415
kus+1.340
wra+1.300
ghazi+1.276
Neg logit contributions
Appearances-1.948
interstitial-1.913
-1.906
 barn-1.828
NPR-1.816
Token content
Token ID2695
Feature activation+4.75e+00

Pos logit contributions
zos+5.615
oint+4.828
kus+4.538
wra+4.349
estine+4.227
Neg logit contributions
-9.954
Appearances-9.950
interstitial-9.723
eatures-9.711
 barn-9.349
Token,
Token ID837
Feature activation+1.02e+00

Pos logit contributions
zos+4.175
oint+3.821
kus+3.601
wra+3.493
estine+3.475
Neg logit contributions
Appearances-3.312
-3.272
interstitial-3.202
 barn-3.085
eatures-3.000
Token updates
Token ID5992
Feature activation+6.62e+00

Pos logit contributions
zos+0.778
oint+0.695
kus+0.657
wra+0.637
ghazi+0.632
Neg logit contributions
Appearances-0.844
interstitial-0.829
-0.824
 barn-0.796
NPR-0.787
Token and
Token ID290
Feature activation+3.37e+00

Pos logit contributions
zos+5.087
oint+4.582
kus+4.310
wra+4.197
utsche+4.132
Neg logit contributions
-5.231
interstitial-5.218
Appearances-5.194
eatures-4.955
 barn-4.831
Token promotions
Token ID20699
Feature activation+5.31e+00

Pos logit contributions
zos+2.404
oint+2.194
kus+2.037
wra+1.979
ghazi+1.950
Neg logit contributions
Appearances-2.833
-2.813
interstitial-2.782
 barn-2.672
NPR-2.665
Token
Token ID447
Feature activation-1.26e+00

Pos logit contributions
zos+0.594
oint+0.544
kus+0.520
wra+0.510
ghazi+0.508
Neg logit contributions
Appearances-0.378
interstitial-0.374
-0.365
 barn-0.353
NPR-0.347
Token
Token ID251
Feature activation-4.46e-01

Pos logit contributions
Appearances+0.650
interstitial+0.639
+0.623
 barn+0.597
NPR+0.587
Neg logit contributions
zos-1.341
oint-1.238
kus-1.191
wra-1.169
ghazi-1.165
Token
Token ID198
Feature activation-2.00e-01

Pos logit contributions
Appearances+0.291
interstitial+0.285
+0.281
 barn+0.272
NPR+0.269
Neg logit contributions
zos-0.415
oint-0.378
kus-0.362
wra-0.354
ghazi-0.353
Token
Token ID198
Feature activation-1.70e-01

Pos logit contributions
Appearances+0.129
interstitial+0.123
+0.122
 barn+0.120
NPR+0.120
Neg logit contributions
zos-0.188
oint-0.170
kus-0.163
ghazi-0.161
wra-0.160
TokenThe
Token ID464
Feature activation+9.97e-02

Pos logit contributions
Appearances+0.112
interstitial+0.110
+0.108
 barn+0.104
NPR+0.104
Neg logit contributions
zos-0.157
oint-0.143
kus-0.137
wra-0.134
ghazi-0.133
Token senior
Token ID4664
Feature activation+1.02e+01

Pos logit contributions
zos+0.088
oint+0.079
kus+0.076
wra+0.074
ghazi+0.074
Neg logit contributions
Appearances-0.070
interstitial-0.069
-0.068
 barn-0.066
NPR-0.065
Token Israeli
Token ID6085
Feature activation+5.30e-01

Pos logit contributions
zos+7.889
oint+7.293
kus+6.789
estine+6.714
utsche+6.534
Neg logit contributions
Appearances-7.520
interstitial-7.387
-7.321
 barn-6.832
NPR-6.814
Token official
Token ID1743
Feature activation+5.08e+00

Pos logit contributions
zos+0.481
oint+0.437
kus+0.417
wra+0.408
ghazi+0.406
Neg logit contributions
Appearances-0.358
interstitial-0.353
-0.346
 barn-0.336
NPR-0.331
Token noted
Token ID4367
Feature activation+1.94e+00

Pos logit contributions
zos+4.415
oint+4.029
kus+3.849
wra+3.733
ghazi+3.713
Neg logit contributions
interstitial-3.556
Appearances-3.545
-3.379
NPR-3.287
 barn-3.226
Token that
Token ID326
Feature activation+3.07e-01

Pos logit contributions
zos+1.745
oint+1.588
kus+1.510
wra+1.479
ghazi+1.470
Neg logit contributions
Appearances-1.315
interstitial-1.306
-1.274
 barn-1.232
NPR-1.222
Token the
Token ID262
Feature activation+1.55e+00

Pos logit contributions
zos+0.271
oint+0.246
kus+0.234
wra+0.229
ghazi+0.228
Neg logit contributions
Appearances-0.214
interstitial-0.211
-0.207
 barn-0.201
NPR-0.198
Tokenmag
Token ID19726
Feature activation-2.37e+00

Pos logit contributions
Appearances+0.117
interstitial+0.115
+0.113
 barn+0.109
NPR+0.109
Neg logit contributions
zos-0.135
oint-0.122
kus-0.115
wra-0.113
ghazi-0.112
Tokenazine
Token ID4994
Feature activation-4.19e-01

Pos logit contributions
Appearances+1.758
interstitial+1.711
+1.701
NPR+1.654
 barn+1.650
Neg logit contributions
zos-1.986
oint-1.781
kus-1.691
wra-1.649
ghazi-1.647
Token)
Token ID8
Feature activation-1.26e+00

Pos logit contributions
Appearances+0.342
interstitial+0.334
+0.333
 barn+0.323
NPR+0.323
Neg logit contributions
zos-0.322
oint-0.286
kus-0.272
wra-0.264
ghazi-0.263
Token<|endoftext|>
Token ID50256
Feature activation-4.75e+00

Pos logit contributions
Appearances+0.840
interstitial+0.823
+0.812
 barn+0.788
NPR+0.777
Neg logit contributions
zos-1.155
oint-1.048
kus-1.002
wra-0.979
ghazi-0.975
TokenC
Token ID34
Feature activation-4.92e-01

Pos logit contributions
Appearances+3.348
interstitial+3.219
NPR+3.127
+3.097
 barn+2.970
Neg logit contributions
zos-4.187
oint-3.781
kus-3.584
estine-3.502
ghazi-3.495
Tokenit
Token ID270
Feature activation+1.01e+01

Pos logit contributions
Appearances+0.375
interstitial+0.371
+0.364
 barn+0.356
NPR+0.352
Neg logit contributions
zos-0.401
oint-0.360
kus-0.344
wra-0.335
ghazi-0.334
Tokenib
Token ID571
Feature activation+8.88e-01

Pos logit contributions
zos+7.413
oint+6.616
kus+6.220
estine+6.017
wra+5.986
Neg logit contributions
Appearances-8.312
-8.177
interstitial-8.058
NPR-7.713
 barn-7.684
Tokenank
Token ID962
Feature activation+9.30e+00

Pos logit contributions
zos+0.558
oint+0.486
kus+0.453
wra+0.437
ghazi+0.434
Neg logit contributions
Appearances-0.846
interstitial-0.838
-0.827
 barn-0.809
NPR-0.801
Token fore
Token ID1674
Feature activation-9.60e-01

Pos logit contributions
zos+8.046
oint+7.398
kus+7.140
wra+6.924
utsche+6.868
Neg logit contributions
interstitial-6.209
Appearances-6.082
-5.870
NPR-5.629
 barn-5.556
Tokenclosed
Token ID20225
Feature activation-1.22e+00

Pos logit contributions
Appearances+0.725
interstitial+0.715
+0.703
 barn+0.685
NPR+0.674
Neg logit contributions
zos-0.790
oint-0.712
kus-0.674
ghazi-0.658
wra-0.657
Token on
Token ID319
Feature activation+2.66e+00

Pos logit contributions
Appearances+0.755
interstitial+0.742
+0.729
 barn+0.710
NPR+0.694
Neg logit contributions
zos-1.174
oint-1.071
kus-1.027
wra-1.007
ghazi-1.003
Tokenphan
Token ID19080
Feature activation-2.11e+00

Pos logit contributions
Appearances+3.219
interstitial+3.186
+3.090
 barn+3.085
 Emmy+3.069
Neg logit contributions
zos-2.102
oint-1.821
kus-1.662
ghazi-1.628
wra-1.612
Token Black
Token ID2619
Feature activation-8.80e-02

Pos logit contributions
Appearances+1.649
interstitial+1.613
+1.583
 barn+1.579
 Emmy+1.553
Neg logit contributions
zos-1.667
oint-1.500
kus-1.419
wra-1.385
ghazi-1.380
Token BBC
Token ID7823
Feature activation-8.31e-01

Pos logit contributions
Appearances+0.055
interstitial+0.054
+0.053
 barn+0.051
NPR+0.050
Neg logit contributions
zos-0.085
oint-0.077
kus-0.074
wra-0.073
ghazi-0.072
Token America
Token ID2253
Feature activation-1.14e+00

Pos logit contributions
Appearances+0.521
interstitial+0.506
+0.501
 barn+0.488
NPR+0.480
Neg logit contributions
zos-0.792
oint-0.723
kus-0.693
wra-0.677
ghazi-0.673
Token Matthew
Token ID9308
Feature activation-2.55e+00

Pos logit contributions
Appearances+0.707
interstitial+0.689
+0.677
 barn+0.662
 Emmy+0.653
Neg logit contributions
zos-1.095
oint-0.999
kus-0.958
wra-0.937
ghazi-0.934
Token Mc
Token ID1982
Feature activation-1.23e+01

Pos logit contributions
Appearances+1.113
interstitial+1.070
+1.049
 barn+1.031
 Emmy+1.010
Neg logit contributions
zos-2.878
oint-2.667
kus-2.584
wra-2.536
ghazi-2.530
TokenCon
Token ID3103
Feature activation-4.38e+00

Pos logit contributions
Appearances+6.175
 barn+5.778
 Emmy+5.454
NPR+5.446
+5.168
Neg logit contributions
zos-12.454
kus-11.178
oint-11.001
estine-10.772
utsche-10.568
Tokenaug
Token ID7493
Feature activation-3.79e+00

Pos logit contributions
Appearances+2.165
interstitial+2.127
 barn+2.070
+2.007
NPR+1.994
Neg logit contributions
zos-4.582
oint-4.155
kus-4.032
utsche-3.934
wra-3.923
Tokenhey
Token ID20342
Feature activation-4.71e+00

Pos logit contributions
Appearances+1.847
interstitial+1.775
 barn+1.734
+1.693
NPR+1.658
Neg logit contributions
zos-4.033
oint-3.669
kus-3.553
ghazi-3.528
estine-3.504
Token True
Token ID6407
Feature activation-1.49e-01

Pos logit contributions
Appearances+3.003
 Emmy+2.943
 barn+2.863
interstitial+2.855
+2.833
Neg logit contributions
zos-4.355
oint-3.922
kus-3.784
wra-3.694
estine-3.687
Token Detective
Token ID20220
Feature activation-2.51e+00

Pos logit contributions
Appearances+0.110
interstitial+0.107
+0.105
 barn+0.104
 Emmy+0.103
Neg logit contributions
zos-0.125
oint-0.113
kus-0.107
wra-0.104
ghazi-0.104
Token2006
Token ID13330
Feature activation-2.07e+00

Pos logit contributions
Appearances+0.493
interstitial+0.479
+0.463
NPR+0.443
 barn+0.439
Neg logit contributions
zos-0.992
oint-0.915
kus-0.876
wra-0.859
ghazi-0.859
Token Charlie
Token ID11526
Feature activation-5.81e+00

Pos logit contributions
Appearances+1.250
interstitial+1.222
+1.197
 barn+1.169
 Emmy+1.151
Neg logit contributions
zos-2.016
oint-1.845
kus-1.771
wra-1.734
ghazi-1.729
Token Sheen
Token ID50189
Feature activation-4.83e-01

Pos logit contributions
Appearances+2.898
 Emmy+2.830
interstitial+2.809
 barn+2.771
+2.764
Neg logit contributions
zos-6.035
oint-5.611
kus-5.387
wra-5.325
ghazi-5.252
Token 2007
Token ID4343
Feature activation-9.34e-01

Pos logit contributions
Appearances+0.330
interstitial+0.326
+0.320
 barn+0.310
NPR+0.306
Neg logit contributions
zos-0.434
oint-0.394
kus-0.376
wra-0.368
ghazi-0.366
Token Ricky
Token ID31668
Feature activation-2.72e+00

Pos logit contributions
Appearances+0.570
interstitial+0.561
+0.550
 barn+0.531
NPR+0.523
Neg logit contributions
zos-0.906
oint-0.830
kus-0.795
wra-0.779
ghazi-0.776
Token G
Token ID402
Feature activation-1.22e+01

Pos logit contributions
Appearances+1.690
interstitial+1.675
+1.629
 barn+1.606
 Emmy+1.594
Neg logit contributions
zos-2.586
oint-2.366
kus-2.254
ghazi-2.207
wra-2.200
Tokenerv
Token ID712
Feature activation-3.81e+00

Pos logit contributions
 barn+9.622
 Emmy+9.040
Appearances+9.005
interstitial+8.978
NPR+8.674
Neg logit contributions
zos-8.524
kus-7.628
oint-7.384
ghazi-7.118
estine-7.034
Tokenais
Token ID15152
Feature activation-2.45e+00

Pos logit contributions
interstitial+3.314
Appearances+3.303
 barn+3.253
NPR+3.191
+3.176
Neg logit contributions
zos-2.516
oint-2.220
ghazi-2.069
wra-2.055
kus-2.043
Token
Token ID198
Feature activation-5.80e-01

Pos logit contributions
Appearances+1.639
interstitial+1.605
+1.577
 barn+1.535
NPR+1.510
Neg logit contributions
zos-2.238
oint-2.035
kus-1.945
wra-1.907
ghazi-1.899
Token
Token ID198
Feature activation-2.59e+00

Pos logit contributions
Appearances+0.365
interstitial+0.342
+0.341
 barn+0.339
NPR+0.338
Neg logit contributions
zos-0.555
oint-0.501
kus-0.483
ghazi-0.475
wra-0.473
Token2007
Token ID12726
Feature activation-2.47e+00

Pos logit contributions
Appearances+1.408
interstitial+1.324
+1.275
NPR+1.244
 barn+1.224
Neg logit contributions
zos-2.745
oint-2.517
kus-2.422
estine-2.370
ghazi-2.367
Token.
Token ID13
Feature activation-1.85e+00

Pos logit contributions
Appearances+3.346
interstitial+3.249
 barn+3.207
+3.170
NPR+3.113
Neg logit contributions
zos-4.529
oint-4.121
kus-3.958
ghazi-3.819
wra-3.768
Token
Token ID447
Feature activation-1.38e+00

Pos logit contributions
Appearances+0.947
interstitial+0.914
+0.905
 barn+0.869
NPR+0.858
Neg logit contributions
zos-1.972
oint-1.817
kus-1.754
wra-1.715
ghazi-1.711
Token
Token ID247
Feature activation-4.45e-01

Pos logit contributions
Appearances+0.656
interstitial+0.642
+0.625
 barn+0.598
NPR+0.586
Neg logit contributions
zos-1.530
oint-1.417
kus-1.366
wra-1.341
ghazi-1.337
Token For
Token ID1114
Feature activation-2.89e+00

Pos logit contributions
Appearances+0.277
interstitial+0.271
+0.266
 barn+0.258
NPR+0.254
Neg logit contributions
zos-0.428
oint-0.391
kus-0.375
wra-0.367
ghazi-0.366
Token a
Token ID257
Feature activation-4.89e+00

Pos logit contributions
Appearances+1.899
interstitial+1.853
+1.833
 barn+1.793
NPR+1.755
Neg logit contributions
zos-2.650
oint-2.421
kus-2.322
ghazi-2.264
wra-2.254
Token lot
Token ID1256
Feature activation-1.19e+01

Pos logit contributions
Appearances+3.211
interstitial+3.137
+3.116
 barn+3.081
NPR+2.980
Neg logit contributions
zos-4.452
oint-4.033
kus-3.855
ghazi-3.786
wra-3.765
Token of
Token ID286
Feature activation-6.74e+00

Pos logit contributions
Appearances+5.967
 barn+5.697
+5.614
NPR+5.450
 Emmy+5.432
Neg logit contributions
zos-11.484
oint-10.682
kus-10.340
ghazi-10.216
estine-9.916
Token young
Token ID1862
Feature activation+5.45e+00

Pos logit contributions
Appearances+4.137
 barn+4.097
+4.033
interstitial+3.982
 Emmy+3.931
Neg logit contributions
zos-6.121
oint-5.597
kus-5.458
ghazi-5.368
wra-5.291
Token evangelicals
Token ID44881
Feature activation+2.18e-01

Pos logit contributions
zos+4.514
oint+4.026
kus+3.782
wra+3.715
ghazi+3.646
Neg logit contributions
interstitial-4.136
Appearances-4.115
-4.007
NPR-3.821
 barn-3.718
Token,
Token ID11
Feature activation+1.86e+00

Pos logit contributions
zos+0.168
oint+0.150
kus+0.142
wra+0.139
ghazi+0.138
Neg logit contributions
Appearances-0.177
interstitial-0.175
-0.172
 barn-0.167
NPR-0.166
Token church
Token ID4928
Feature activation-3.15e-01

Pos logit contributions
zos+1.669
oint+1.519
kus+1.440
wra+1.417
ghazi+1.405
Neg logit contributions
interstitial-1.268
Appearances-1.267
-1.227
 barn-1.168
NPR-1.166
Tokenle
Token ID293
Feature activation+2.25e-01

Pos logit contributions
zos+1.303
oint+1.140
kus+1.065
wra+1.029
ghazi+1.027
Neg logit contributions
Appearances-1.848
interstitial-1.829
-1.801
 barn-1.764
NPR-1.749
Token
Token ID198
Feature activation+2.07e+00

Pos logit contributions
zos+0.198
oint+0.180
kus+0.172
wra+0.168
ghazi+0.167
Neg logit contributions
Appearances-0.157
interstitial-0.155
-0.152
 barn-0.147
NPR-0.146
Token
Token ID198
Feature activation-2.13e-01

Pos logit contributions
zos+1.870
oint+1.700
kus+1.623
wra+1.587
ghazi+1.582
Neg logit contributions
Appearances-1.408
interstitial-1.385
-1.360
 barn-1.320
NPR-1.304
Token2014
Token ID4967
Feature activation-8.34e-01

Pos logit contributions
Appearances+0.130
interstitial+0.126
+0.123
NPR+0.119
 barn+0.118
Neg logit contributions
zos-0.209
oint-0.191
kus-0.183
ghazi-0.179
wra-0.179
Token Ricky
Token ID31668
Feature activation-2.26e+00

Pos logit contributions
Appearances+0.516
interstitial+0.507
+0.497
 barn+0.481
NPR+0.474
Neg logit contributions
zos-0.802
oint-0.734
kus-0.703
wra-0.688
ghazi-0.686
Token G
Token ID402
Feature activation-1.18e+01

Pos logit contributions
Appearances+1.385
interstitial+1.355
+1.328
 Emmy+1.303
 barn+1.296
Neg logit contributions
zos-2.169
oint-1.989
kus-1.882
wra-1.851
ghazi-1.847
Tokenerv
Token ID712
Feature activation-3.58e+00

Pos logit contributions
 barn+8.853
Appearances+8.836
NPR+8.495
 Emmy+8.428
interstitial+8.401
Neg logit contributions
zos-8.490
kus-7.089
oint-6.973
llah-6.670
wra-6.670
Tokenais
Token ID15152
Feature activation-2.32e+00

Pos logit contributions
interstitial+3.133
Appearances+3.117
NPR+2.949
 barn+2.939
+2.921
Neg logit contributions
zos-2.408
oint-2.075
wra-1.981
ghazi-1.957
utsche-1.951
Token
Token ID198
Feature activation+2.07e+00

Pos logit contributions
Appearances+1.523
interstitial+1.498
+1.467
 barn+1.427
NPR+1.403
Neg logit contributions
zos-2.139
oint-1.947
kus-1.862
wra-1.822
ghazi-1.817
Token
Token ID198
Feature activation-1.62e-02

Pos logit contributions
zos+1.868
oint+1.698
kus+1.621
wra+1.585
ghazi+1.579
Neg logit contributions
Appearances-1.409
interstitial-1.388
-1.363
 barn-1.322
NPR-1.305
Token2014
Token ID4967
Feature activation-1.52e+00

Pos logit contributions
Appearances+0.010
interstitial+0.010
+0.009
NPR+0.009
 barn+0.009
Neg logit contributions
zos-0.016
oint-0.014
kus-0.014
ghazi-0.013
wra-0.013
Token Rob
Token ID3851
Feature activation-2.61e+00

Pos logit contributions
zos+1.543
oint+1.403
kus+1.336
wra+1.307
ghazi+1.300
Neg logit contributions
Appearances-1.221
interstitial-1.205
-1.187
 barn-1.139
NPR-1.131
Tokenoc
Token ID420
Feature activation-3.40e+00

Pos logit contributions
Appearances+1.797
interstitial+1.768
+1.746
 barn+1.695
NPR+1.672
Neg logit contributions
zos-2.306
oint-2.097
kus-2.003
wra-1.951
ghazi-1.943
Tokenop
Token ID404
Feature activation+4.23e+00

Pos logit contributions
Appearances+2.414
interstitial+2.392
+2.341
 barn+2.313
NPR+2.282
Neg logit contributions
zos-2.884
oint-2.591
kus-2.493
ghazi-2.441
wra-2.433
Token.
Token ID13
Feature activation+2.26e-01

Pos logit contributions
zos+3.460
oint+3.166
kus+2.973
wra+2.928
ghazi+2.886
Neg logit contributions
Appearances-3.192
interstitial-3.189
-3.067
NPR-2.962
 barn-2.940
Token Continue
Token ID10054
Feature activation-4.10e+00

Pos logit contributions
zos+0.210
oint+0.192
kus+0.184
wra+0.180
ghazi+0.179
Neg logit contributions
Appearances-0.146
interstitial-0.145
-0.141
 barn-0.137
NPR-0.135
Token Reading
Token ID11725
Feature activation-1.17e+01

Pos logit contributions
Appearances+1.893
interstitial+1.801
+1.766
 Emmy+1.716
 barn+1.714
Neg logit contributions
zos-4.541
oint-4.215
kus-4.047
ghazi-4.002
wra-3.975
Token Below
Token ID10383
Feature activation-4.92e+00

Pos logit contributions
Appearances+3.182
 Emmy+2.882
+2.659
NPR+2.540
 Pigs+2.441
Neg logit contributions
zos-14.302
oint-13.628
kus-13.229
ghazi-13.215
utsche-12.806
Token Advertisement
Token ID39711
Feature activation-5.74e+00

Pos logit contributions
Appearances+2.109
interstitial+1.988
+1.951
 Emmy+1.901
 barn+1.863
Neg logit contributions
zos-5.586
oint-5.247
kus-5.026
ghazi-4.973
wra-4.965
Token<|endoftext|>
Token ID50256
Feature activation-4.61e+00

Pos logit contributions
Appearances+3.519
interstitial+3.413
+3.391
 barn+3.279
NPR+3.271
Neg logit contributions
zos-5.436
oint-4.951
kus-4.775
ghazi-4.648
wra-4.627
TokenUN
Token ID4944
Feature activation+5.22e+00

Pos logit contributions
Appearances+3.249
interstitial+3.126
NPR+3.037
+3.008
 barn+2.885
Neg logit contributions
zos-4.070
oint-3.675
kus-3.487
estine-3.403
ghazi-3.399
TokenITED
Token ID22061
Feature activation+5.23e+00

Pos logit contributions
zos+4.015
oint+3.656
kus+3.398
wra+3.351
ghazi+3.339
Neg logit contributions
Appearances-4.093
interstitial-4.051
-4.008
 barn-3.888
NPR-3.807
Token,"
Token ID553
Feature activation-2.19e+00

Pos logit contributions
Appearances+1.100
interstitial+1.064
+1.021
 barn+1.017
NPR+0.992
Neg logit contributions
zos-2.169
oint-1.991
kus-1.915
wra-1.897
ghazi-1.879
Token "
Token ID366
Feature activation-6.35e-01

Pos logit contributions
Appearances+1.475
interstitial+1.421
+1.413
 barn+1.391
 Emmy+1.365
Neg logit contributions
zos-1.994
oint-1.794
kus-1.718
ghazi-1.689
wra-1.688
TokenP
Token ID47
Feature activation+4.27e-01

Pos logit contributions
Appearances+0.421
interstitial+0.403
+0.398
NPR+0.387
 barn+0.382
Neg logit contributions
zos-0.595
oint-0.539
kus-0.516
ghazi-0.504
wra-0.504
Tokenunct
Token ID16260
Feature activation-3.90e+00

Pos logit contributions
zos+0.113
oint+0.071
kus+0.060
ghazi+0.053
wra+0.052
Neg logit contributions
Appearances-0.564
interstitial-0.561
-0.549
 barn-0.546
NPR-0.544
Tokenate
Token ID378
Feature activation+7.83e-01

Pos logit contributions
Appearances+3.029
interstitial+2.964
 barn+2.879
NPR+2.816
+2.783
Neg logit contributions
zos-3.040
oint-2.559
kus-2.544
ghazi-2.469
wra-2.458
Token ker
Token ID41927
Feature activation-1.17e+01

Pos logit contributions
zos+0.852
oint+0.789
kus+0.760
wra+0.746
ghazi+0.743
Neg logit contributions
Appearances-0.386
interstitial-0.378
-0.369
 barn-0.351
NPR-0.345
Tokenat
Token ID265
Feature activation-1.47e+00

Pos logit contributions
Appearances+5.801
interstitial+5.615
 barn+5.549
NPR+5.297
ozyg+5.072
Neg logit contributions
zos-10.698
ghazi-9.406
estine-9.168
ット-9.159
wra-9.158
Tokenoder
Token ID12342
Feature activation-5.66e+00

Pos logit contributions
interstitial+0.910
Appearances+0.906
NPR+0.847
 barn+0.844
+0.840
Neg logit contributions
zos-1.376
oint-1.249
kus-1.207
wra-1.196
ghazi-1.189
Tokenma
Token ID2611
Feature activation-6.10e+00

Pos logit contributions
Appearances+3.106
interstitial+3.038
 barn+2.886
 Emmy+2.829
+2.819
Neg logit contributions
zos-5.555
oint-5.106
wra-4.867
ghazi-4.849
kus-4.816
Token,"
Token ID553
Feature activation-2.75e+00

Pos logit contributions
Appearances+2.875
 barn+2.748
interstitial+2.716
 Emmy+2.603
NPR+2.602
Neg logit contributions
zos-6.610
oint-6.032
wra-5.868
kus-5.847
ghazi-5.831
Token and
Token ID290
Feature activation-1.39e+00

Pos logit contributions
Appearances+1.700
 barn+1.613
interstitial+1.590
+1.580
 Emmy+1.576
Neg logit contributions
zos-2.641
oint-2.379
kus-2.303
ghazi-2.260
wra-2.252
Token in
Token ID287
Feature activation-2.22e+00

Pos logit contributions
Appearances+2.868
interstitial+2.837
+2.775
 barn+2.758
NPR+2.683
Neg logit contributions
zos-3.546
oint-3.224
kus-3.055
ghazi-3.014
wra-2.964
Token 1946
Token ID22717
Feature activation+3.27e-01

Pos logit contributions
Appearances+1.574
interstitial+1.535
 barn+1.506
+1.502
 Emmy+1.458
Neg logit contributions
zos-1.923
oint-1.740
kus-1.655
ghazi-1.633
wra-1.618
Token (
Token ID357
Feature activation+1.14e+00

Pos logit contributions
zos+0.249
oint+0.222
kus+0.210
wra+0.204
ghazi+0.203
Neg logit contributions
Appearances-0.268
interstitial-0.265
-0.261
 barn-0.254
NPR-0.252
TokenMic
Token ID25437
Feature activation-2.43e+00

Pos logit contributions
zos+0.924
oint+0.831
kus+0.789
wra+0.773
ghazi+0.764
Neg logit contributions
Appearances-0.881
interstitial-0.872
-0.860
 barn-0.835
NPR-0.821
Tokenkey
Token ID2539
Feature activation-2.96e+00

Pos logit contributions
Appearances+1.950
interstitial+1.921
+1.912
 barn+1.892
NPR+1.834
Neg logit contributions
zos-1.850
oint-1.637
kus-1.548
wra-1.509
ghazi-1.503
Token Mc
Token ID1982
Feature activation-1.15e+01

Pos logit contributions
Appearances+1.813
+1.767
interstitial+1.761
 barn+1.705
 Emmy+1.655
Neg logit contributions
zos-2.853
oint-2.593
kus-2.489
wra-2.441
ghazi-2.432
TokenBride
Token ID47148
Feature activation-2.63e-01

Pos logit contributions
Appearances+7.627
 barn+7.150
+7.103
interstitial+6.902
NPR+6.757
Neg logit contributions
zos-9.562
oint-8.806
kus-8.573
wra-8.045
estine-7.995
Token
Token ID447
Feature activation+3.34e+00

Pos logit contributions
Appearances+0.183
interstitial+0.181
+0.177
 barn+0.172
NPR+0.170
Neg logit contributions
zos-0.232
oint-0.211
kus-0.201
wra-0.197
ghazi-0.196
Token
Token ID247
Feature activation+1.84e-01

Pos logit contributions
zos+2.588
oint+2.363
kus+2.226
wra+2.165
ghazi+2.160
Neg logit contributions
Appearances-2.602
interstitial-2.589
-2.588
 barn-2.485
NPR-2.445
Tokens
Token ID82
Feature activation-1.88e+00

Pos logit contributions
zos+0.159
oint+0.144
kus+0.137
wra+0.134
ghazi+0.133
Neg logit contributions
Appearances-0.132
interstitial-0.131
-0.128
 barn-0.125
NPR-0.123
Token buzz
Token ID14713
Feature activation-6.12e-01

Pos logit contributions
Appearances+1.207
interstitial+1.186
+1.168
 barn+1.138
NPR+1.111
Neg logit contributions
zos-1.760
oint-1.600
kus-1.532
wra-1.503
ghazi-1.499
Token their
Token ID511
Feature activation+7.05e-01

Pos logit contributions
Appearances+0.601
interstitial+0.593
+0.582
 barn+0.565
NPR+0.558
Neg logit contributions
zos-0.782
oint-0.710
kus-0.677
wra-0.662
ghazi-0.660
Token coverage
Token ID5197
Feature activation-2.65e+00

Pos logit contributions
zos+0.622
oint+0.566
kus+0.540
wra+0.527
ghazi+0.524
Neg logit contributions
Appearances-0.493
interstitial-0.487
-0.478
 barn-0.459
NPR-0.454
Token.
Token ID13
Feature activation-5.00e-01

Pos logit contributions
Appearances+1.871
interstitial+1.837
+1.816
 barn+1.795
NPR+1.771
Neg logit contributions
zos-2.280
oint-2.057
kus-1.963
wra-1.915
ghazi-1.911
Token Po
Token ID7695
Feature activation-1.63e+00

Pos logit contributions
Appearances+0.317
interstitial+0.312
+0.306
 barn+0.296
NPR+0.292
Neg logit contributions
zos-0.474
oint-0.433
kus-0.414
wra-0.406
ghazi-0.404
Tokenppy
Token ID14097
Feature activation-3.06e+00

Pos logit contributions
Appearances+1.340
interstitial+1.324
+1.304
 barn+1.272
NPR+1.259
Neg logit contributions
zos-1.222
oint-1.093
kus-1.032
wra-1.010
ghazi-0.999
Token Har
Token ID2113
Feature activation-1.15e+01

Pos logit contributions
Appearances+1.655
interstitial+1.598
+1.584
 barn+1.528
 Emmy+1.491
Neg logit contributions
zos-3.210
oint-2.919
kus-2.816
ghazi-2.760
wra-2.756
Tokenlow
Token ID9319
Feature activation-5.13e+00

Pos logit contributions
interstitial+6.141
Appearances+6.137
NPR+5.881
 barn+5.860
 Emmy+5.553
Neg logit contributions
zos-11.012
oint-10.130
utsche-9.989
ghazi-9.819
kus-9.741
Token,
Token ID11
Feature activation+7.08e-01

Pos logit contributions
Appearances+3.248
interstitial+3.154
+3.154
 barn+3.099
NPR+3.071
Neg logit contributions
zos-4.748
oint-4.325
kus-4.101
ghazi-4.044
wra-4.034
Token Brian
Token ID8403
Feature activation-5.51e+00

Pos logit contributions
zos+0.632
oint+0.576
kus+0.549
wra+0.538
ghazi+0.536
Neg logit contributions
Appearances-0.487
interstitial-0.481
-0.472
 barn-0.452
NPR-0.446
Token Todd
Token ID14377
Feature activation-6.32e+00

Pos logit contributions
Appearances+2.364
+2.355
interstitial+2.342
 Emmy+2.282
 barn+2.268
Neg logit contributions
zos-6.091
oint-5.708
wra-5.324
kus-5.291
utsche-5.275
Token,
Token ID11
Feature activation-1.94e+00

Pos logit contributions
Appearances+4.422
+4.325
interstitial+4.288
 barn+4.242
 Emmy+4.226
Neg logit contributions
zos-5.321
oint-4.888
kus-4.581
wra-4.498
ghazi-4.490
Token contends
Token ID33799
Feature activation-1.28e+00

Pos logit contributions
Appearances+0.095
interstitial+0.093
+0.091
 barn+0.089
NPR+0.087
Neg logit contributions
zos-0.152
oint-0.139
kus-0.133
wra-0.131
ghazi-0.130
Token he
Token ID339
Feature activation+1.11e+00

Pos logit contributions
Appearances+0.830
interstitial+0.818
+0.802
 barn+0.776
NPR+0.765
Neg logit contributions
zos-1.187
oint-1.083
kus-1.036
wra-1.013
ghazi-1.009
Token was
Token ID373
Feature activation+1.65e+00

Pos logit contributions
zos+1.159
oint+1.069
kus+1.026
wra+1.007
ghazi+1.004
Neg logit contributions
Appearances-0.595
interstitial-0.587
-0.570
 barn-0.545
NPR-0.538
Token denied
Token ID6699
Feature activation+8.50e-01

Pos logit contributions
zos+1.425
oint+1.295
kus+1.230
wra+1.201
ghazi+1.198
Neg logit contributions
Appearances-1.193
interstitial-1.178
-1.151
NPR-1.103
 barn-1.101
Token a
Token ID257
Feature activation+6.53e-01

Pos logit contributions
zos+0.772
oint+0.704
kus+0.672
wra+0.656
ghazi+0.654
Neg logit contributions
Appearances-0.572
interstitial-0.564
-0.555
 barn-0.534
NPR-0.529
Token fair
Token ID3148
Feature activation-1.15e+01

Pos logit contributions
zos+0.571
oint+0.518
kus+0.494
wra+0.482
ghazi+0.480
Neg logit contributions
Appearances-0.461
interstitial-0.455
-0.447
 barn-0.433
NPR-0.428
Token hearing
Token ID4854
Feature activation-3.98e+00

Pos logit contributions
Appearances+6.359
 barn+6.233
 Emmy+6.156
interstitial+5.977
NPR+5.898
Neg logit contributions
zos-10.893
oint-9.699
kus-9.541
wra-9.389
ghazi-9.273
Token without
Token ID1231
Feature activation+2.29e+00

Pos logit contributions
Appearances+2.386
 barn+2.346
interstitial+2.327
 Emmy+2.278
+2.257
Neg logit contributions
zos-3.826
oint-3.437
kus-3.327
ghazi-3.255
wra-3.254
Token confronting
Token ID31291
Feature activation-2.79e+00

Pos logit contributions
zos+2.005
oint+1.831
kus+1.744
wra+1.693
ghazi+1.679
Neg logit contributions
Appearances-1.613
interstitial-1.597
-1.578
 barn-1.495
NPR-1.494
Token his
Token ID465
Feature activation-1.16e+00

Pos logit contributions
Appearances+1.814
interstitial+1.763
+1.723
 barn+1.715
 Emmy+1.668
Neg logit contributions
zos-2.598
oint-2.356
kus-2.250
wra-2.222
ghazi-2.216
Token accuser
Token ID43738
Feature activation-2.15e+00

Pos logit contributions
Appearances+0.673
interstitial+0.659
+0.644
 barn+0.632
NPR+0.615
Neg logit contributions
zos-1.162
oint-1.061
kus-1.016
wra-1.004
ghazi-0.998
Token be
Token ID307
Feature activation-2.67e+00

Pos logit contributions
Appearances+1.801
interstitial+1.763
 barn+1.750
+1.749
NPR+1.697
Neg logit contributions
zos-2.304
oint-2.071
kus-1.978
ghazi-1.961
wra-1.953
Token equally
Token ID8603
Feature activation-2.39e+00

Pos logit contributions
Appearances+1.639
interstitial+1.607
+1.573
 barn+1.561
 Emmy+1.515
Neg logit contributions
zos-2.557
oint-2.327
kus-2.235
wra-2.201
ghazi-2.187
Token as
Token ID355
Feature activation-2.73e+00

Pos logit contributions
Appearances+1.461
interstitial+1.419
 barn+1.405
+1.395
 Emmy+1.361
Neg logit contributions
zos-2.294
oint-2.072
kus-2.005
ghazi-1.984
wra-1.964
Token tight
Token ID5381
Feature activation-6.28e+00

Pos logit contributions
Appearances+2.424
 barn+2.384
interstitial+2.380
+2.330
 Emmy+2.319
Neg logit contributions
zos-1.858
oint-1.595
kus-1.514
ghazi-1.489
estine-1.471
Token-
Token ID12
Feature activation-3.96e+00

Pos logit contributions
Appearances+4.232
 barn+4.087
interstitial+4.083
+4.002
NPR+3.930
Neg logit contributions
zos-5.551
oint-4.950
kus-4.729
ghazi-4.705
estine-4.673
Tokenf
Token ID69
Feature activation-1.13e+01

Pos logit contributions
Appearances+2.926
interstitial+2.873
 barn+2.731
NPR+2.722
+2.707
Neg logit contributions
zos-3.291
oint-2.931
kus-2.758
ghazi-2.740
estine-2.722
Tokenisted
Token ID6347
Feature activation-3.89e+00

Pos logit contributions
Appearances+3.787
 barn+3.595
interstitial+3.481
NPR+3.469
 Emmy+3.235
Neg logit contributions
zos-12.598
ghazi-11.533
oint-11.136
IU-11.132
kus-11.036
Token as
Token ID355
Feature activation-7.32e+00

Pos logit contributions
Appearances+2.480
interstitial+2.415
+2.389
 barn+2.326
NPR+2.284
Neg logit contributions
zos-3.660
oint-3.327
kus-3.174
ghazi-3.124
wra-3.112
Token the
Token ID262
Feature activation-2.93e+00

Pos logit contributions
Appearances+4.128
 barn+3.937
+3.901
 Emmy+3.884
interstitial+3.824
Neg logit contributions
zos-7.006
oint-6.372
kus-6.191
ghazi-6.108
estine-6.078
Token Conservatives
Token ID17897
Feature activation-1.70e+00

Pos logit contributions
Appearances+1.342
+1.274
interstitial+1.249
 barn+1.226
NPR+1.197
Neg logit contributions
zos-3.256
oint-3.038
kus-2.931
ghazi-2.881
estine-2.871
Token when
Token ID618
Feature activation-1.55e+00

Pos logit contributions
Appearances+1.028
interstitial+1.012
+0.991
 barn+0.954
NPR+0.941
Neg logit contributions
zos-1.669
oint-1.532
kus-1.467
wra-1.437
ghazi-1.432
Token ago
Token ID2084
Feature activation-1.55e+00

Pos logit contributions
zos+0.568
oint+0.520
kus+0.502
wra+0.492
ghazi+0.492
Neg logit contributions
Appearances-0.304
interstitial-0.296
-0.290
 barn-0.281
NPR-0.276
Token I
Token ID314
Feature activation+1.65e+00

Pos logit contributions
Appearances+0.966
interstitial+0.945
+0.930
 barn+0.907
NPR+0.893
Neg logit contributions
zos-1.483
oint-1.352
kus-1.298
wra-1.271
ghazi-1.263
Token think
Token ID892
Feature activation-1.16e-01

Pos logit contributions
zos+1.450
oint+1.316
kus+1.256
wra+1.224
ghazi+1.219
Neg logit contributions
Appearances-1.157
interstitial-1.144
-1.119
 barn-1.081
NPR-1.070
Token a
Token ID257
Feature activation-6.47e-01

Pos logit contributions
Appearances+0.078
interstitial+0.077
+0.075
 barn+0.073
NPR+0.072
Neg logit contributions
zos-0.106
oint-0.096
kus-0.092
wra-0.090
ghazi-0.089
Token simple
Token ID2829
Feature activation-3.03e+00

Pos logit contributions
Appearances+0.402
interstitial+0.396
+0.389
 barn+0.379
NPR+0.371
Neg logit contributions
zos-0.620
oint-0.566
kus-0.542
wra-0.532
ghazi-0.529
Token passing
Token ID6427
Feature activation-1.12e+01

Pos logit contributions
Appearances+2.035
interstitial+1.970
 barn+1.952
+1.950
NPR+1.897
Neg logit contributions
zos-2.752
oint-2.474
kus-2.380
wra-2.333
ghazi-2.317
Token mention
Token ID3068
Feature activation-1.45e+00

Pos logit contributions
 barn+6.380
Appearances+6.233
 Emmy+6.000
interstitial+5.900
NPR+5.881
Neg logit contributions
zos-10.733
oint-9.395
kus-9.305
wra-9.103
estine-8.893
Token of
Token ID286
Feature activation-1.43e+00

Pos logit contributions
Appearances+0.935
interstitial+0.918
+0.902
 barn+0.880
NPR+0.864
Neg logit contributions
zos-1.358
oint-1.234
kus-1.185
wra-1.155
ghazi-1.151
Token the
Token ID262
Feature activation-3.71e-01

Pos logit contributions
Appearances+0.959
interstitial+0.946
+0.927
 barn+0.918
NPR+0.894
Neg logit contributions
zos-1.297
oint-1.174
kus-1.127
wra-1.100
ghazi-1.099
Token intervention
Token ID9572
Feature activation-3.19e+00

Pos logit contributions
Appearances+0.251
interstitial+0.248
+0.243
 barn+0.237
NPR+0.233
Neg logit contributions
zos-0.336
oint-0.305
kus-0.292
wra-0.285
ghazi-0.284
Token of
Token ID286
Feature activation-2.76e-01

Pos logit contributions
Appearances+2.127
interstitial+2.095
+2.065
 barn+2.026
NPR+1.993
Neg logit contributions
zos-2.882
oint-2.609
kus-2.493
wra-2.435
ghazi-2.413
Token is
Token ID318
Feature activation-6.66e-01

Pos logit contributions
Appearances+1.155
interstitial+1.120
+1.116
 barn+1.098
NPR+1.066
Neg logit contributions
zos-1.882
oint-1.715
kus-1.637
wra-1.613
ghazi-1.612
Token only
Token ID691
Feature activation+3.71e-01

Pos logit contributions
Appearances+0.450
interstitial+0.442
+0.435
 barn+0.431
NPR+0.420
Neg logit contributions
zos-0.599
oint-0.544
kus-0.518
ghazi-0.506
wra-0.505
Token the
Token ID262
Feature activation+2.20e+00

Pos logit contributions
zos+0.326
oint+0.295
kus+0.281
wra+0.276
ghazi+0.273
Neg logit contributions
Appearances-0.261
interstitial-0.258
-0.253
 barn-0.244
NPR-0.242
Token tip
Token ID8171
Feature activation+2.18e+00

Pos logit contributions
zos+1.951
oint+1.780
kus+1.696
wra+1.655
ghazi+1.642
Neg logit contributions
Appearances-1.515
interstitial-1.500
-1.469
 barn-1.411
NPR-1.405
Token of
Token ID286
Feature activation-7.80e+00

Pos logit contributions
zos+1.905
oint+1.749
kus+1.651
wra+1.635
ghazi+1.608
Neg logit contributions
Appearances-1.521
interstitial-1.505
-1.475
 barn-1.416
NPR-1.408
Token the
Token ID262
Feature activation-1.10e+01

Pos logit contributions
Appearances+4.428
interstitial+4.410
 barn+4.341
+4.315
 Emmy+4.213
Neg logit contributions
zos-7.492
oint-6.700
kus-6.569
ghazi-6.521
wra-6.281
Token iceberg
Token ID34849
Feature activation-1.67e+00

Pos logit contributions
 barn+3.002
Appearances+2.688
 Emmy+2.591
interstitial+2.431
+2.398
Neg logit contributions
zos-13.571
oint-12.379
kus-12.339
ghazi-12.180
wra-11.893
Token,"
Token ID553
Feature activation+1.24e+00

Pos logit contributions
Appearances+1.055
interstitial+1.032
+1.012
 barn+0.990
NPR+0.969
Neg logit contributions
zos-1.590
oint-1.450
kus-1.390
wra-1.356
ghazi-1.353
Token he
Token ID339
Feature activation+2.74e+00

Pos logit contributions
zos+1.126
oint+1.026
kus+0.982
wra+0.961
ghazi+0.954
Neg logit contributions
Appearances-0.834
interstitial-0.823
-0.808
 barn-0.777
NPR-0.769
Token told
Token ID1297
Feature activation-2.11e+00

Pos logit contributions
zos+2.420
oint+2.197
kus+2.109
wra+2.073
ghazi+2.038
Neg logit contributions
Appearances-1.908
interstitial-1.875
-1.822
NPR-1.744
 barn-1.734
Token The
Token ID383
Feature activation-3.05e+00

Pos logit contributions
Appearances+1.350
interstitial+1.346
+1.325
 barn+1.296
NPR+1.294
Neg logit contributions
zos-1.941
oint-1.760
ghazi-1.664
kus-1.664
wra-1.645
Token Se
Token ID1001
Feature activation-4.66e+00

Pos logit contributions
 Emmy+2.950
Appearances+2.930
 barn+2.875
NPR+2.725
interstitial+2.710
Neg logit contributions
zos-5.494
oint-5.014
ghazi-4.782
kus-4.775
wra-4.748
Tokeninfeld
Token ID47187
Feature activation-4.64e+00

Pos logit contributions
Appearances+1.686
interstitial+1.583
NPR+1.564
+1.555
 barn+1.539
Neg logit contributions
zos-5.416
oint-5.103
kus-4.940
ghazi-4.901
wra-4.868
Token 1995
Token ID8735
Feature activation+2.36e+00

Pos logit contributions
Appearances+2.951
interstitial+2.869
+2.815
 barn+2.774
NPR+2.733
Neg logit contributions
zos-4.328
oint-3.933
kus-3.775
wra-3.704
ghazi-3.691
Token Kel
Token ID15150
Feature activation-5.78e+00

Pos logit contributions
zos+2.217
oint+2.034
kus+1.945
wra+1.899
ghazi+1.886
Neg logit contributions
interstitial-1.501
Appearances-1.481
-1.457
NPR-1.372
 barn-1.371
Tokensey
Token ID4397
Feature activation-5.13e+00

Pos logit contributions
Appearances+2.931
interstitial+2.783
 barn+2.743
 Emmy+2.728
NPR+2.696
Neg logit contributions
zos-5.859
oint-5.480
wra-5.151
ghazi-5.121
kus-5.056
Token Gram
Token ID20159
Feature activation-1.09e+01

Pos logit contributions
Appearances+2.081
 Emmy+2.042
interstitial+1.978
+1.930
 barn+1.928
Neg logit contributions
zos-5.923
oint-5.468
kus-5.220
wra-5.185
ghazi-5.175
Tokenmer
Token ID647
Feature activation-4.22e+00

Pos logit contributions
NPR+4.432
Appearances+4.390
interstitial+4.371
 barn+4.197
 Emmy+3.913
Neg logit contributions
zos-11.337
ghazi-10.237
oint-10.176
estine-9.839
utsche-9.776
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
Appearances+2.571
+2.427
interstitial+2.427
 barn+2.405
NPR+2.382
Neg logit contributions
zos-4.019
oint-3.665
kus-3.511
wra-3.457
ghazi-3.451
Token
Token ID198
Feature activation-2.30e+00

Pos logit contributions
Appearances+0.687
 barn+0.638
interstitial+0.638
+0.637
NPR+0.636
Neg logit contributions
zos-1.077
oint-0.970
kus-0.938
ghazi-0.925
wra-0.918
Token1995
Token ID21908
Feature activation-1.07e+00

Pos logit contributions
Appearances+1.170
interstitial+1.135
+1.083
NPR+1.055
 barn+1.021
Neg logit contributions
zos-2.489
oint-2.285
kus-2.212
ghazi-2.157
wra-2.153
Token John
Token ID1757
Feature activation-1.62e+00

Pos logit contributions
Appearances+0.667
interstitial+0.654
+0.642
 barn+0.623
NPR+0.612
Neg logit contributions
zos-1.031
oint-0.943
kus-0.904
wra-0.885
ghazi-0.882
Token color
Token ID3124
Feature activation+2.89e+00

Pos logit contributions
zos+1.567
oint+1.446
kus+1.389
wra+1.363
ghazi+1.359
Neg logit contributions
Appearances-0.795
interstitial-0.781
-0.763
 barn-0.732
NPR-0.720
Token in
Token ID287
Feature activation+9.62e-01

Pos logit contributions
zos+2.314
oint+2.087
kus+1.958
wra+1.934
ghazi+1.930
Neg logit contributions
Appearances-2.223
interstitial-2.222
-2.165
 barn-2.081
NPR-2.053
Token a
Token ID257
Feature activation+2.23e-01

Pos logit contributions
zos+0.845
oint+0.768
kus+0.731
wra+0.715
ghazi+0.710
Neg logit contributions
Appearances-0.676
interstitial-0.666
-0.656
 barn-0.632
NPR-0.625
Token respectful
Token ID25923
Feature activation-2.44e+00

Pos logit contributions
zos+0.190
oint+0.173
kus+0.165
wra+0.160
ghazi+0.160
Neg logit contributions
Appearances-0.163
interstitial-0.162
-0.158
 barn-0.151
NPR-0.150
Token and
Token ID290
Feature activation-1.30e+00

Pos logit contributions
Appearances+1.665
interstitial+1.627
+1.595
 barn+1.578
NPR+1.545
Neg logit contributions
zos-2.192
oint-1.985
kus-1.899
wra-1.857
ghazi-1.855
Token fair
Token ID3148
Feature activation-1.08e+01

Pos logit contributions
Appearances+0.873
interstitial+0.858
+0.840
 barn+0.825
NPR+0.810
Neg logit contributions
zos-1.181
oint-1.071
kus-1.025
wra-1.003
ghazi-1.000
Token manner
Token ID5642
Feature activation-6.75e-01

Pos logit contributions
Appearances+6.219
 Emmy+6.178
 barn+6.144
NPR+6.007
interstitial+5.869
Neg logit contributions
zos-10.103
oint-9.026
kus-8.754
ghazi-8.637
wra-8.631
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
Appearances+0.524
interstitial+0.518
+0.509
 barn+0.495
NPR+0.490
Neg logit contributions
zos-0.544
oint-0.489
kus-0.464
wra-0.452
ghazi-0.450
Token
Token ID447
Feature activation-3.30e-01

Pos logit contributions
zos+0.376
oint+0.344
kus+0.329
wra+0.323
ghazi+0.322
Neg logit contributions
Appearances-0.244
interstitial-0.242
-0.235
 barn-0.228
NPR-0.223
Token
Token ID251
Feature activation+2.72e-01

Pos logit contributions
Appearances+0.189
interstitial+0.187
+0.183
 barn+0.176
NPR+0.173
Neg logit contributions
zos-0.332
oint-0.306
kus-0.292
wra-0.287
ghazi-0.286
Token
Token ID198
Feature activation-2.38e+00

Pos logit contributions
zos+0.257
oint+0.235
kus+0.224
wra+0.220
ghazi+0.219
Neg logit contributions
Appearances-0.173
interstitial-0.171
-0.167
 barn-0.162
NPR-0.159
Token is
Token ID318
Feature activation-1.74e+00

Pos logit contributions
Appearances+2.905
interstitial+2.875
+2.770
 barn+2.718
NPR+2.646
Neg logit contributions
zos-4.745
oint-4.315
kus-4.153
ghazi-4.082
wra-4.071
Token an
Token ID281
Feature activation+2.06e+00

Pos logit contributions
Appearances+1.073
interstitial+1.064
+1.037
 barn+1.011
NPR+0.987
Neg logit contributions
zos-1.677
oint-1.530
kus-1.463
wra-1.437
ghazi-1.436
Token autos
Token ID44619
Feature activation-8.76e+00

Pos logit contributions
zos+1.995
oint+1.846
kus+1.750
wra+1.714
ghazi+1.706
Neg logit contributions
Appearances-1.263
interstitial-1.227
-1.217
 barn-1.166
NPR-1.155
Tokenomal
Token ID18048
Feature activation-5.80e+00

Pos logit contributions
interstitial+5.875
Appearances+5.728
NPR+5.500
 barn+5.481
ozyg+5.469
Neg logit contributions
zos-7.221
wra-6.297
ghazi-6.134
oint-6.038
kus-5.904
Token dominant
Token ID11410
Feature activation-2.93e+00

Pos logit contributions
interstitial+2.987
Appearances+2.869
 barn+2.851
+2.787
NPR+2.748
Neg logit contributions
zos-6.022
oint-5.442
kus-5.291
ghazi-5.243
wra-5.241
Token ker
Token ID41927
Feature activation-1.08e+01

Pos logit contributions
Appearances+2.216
interstitial+2.214
+2.153
 barn+2.149
 Emmy+2.089
Neg logit contributions
zos-2.383
oint-2.116
kus-2.006
ghazi-1.983
wra-1.974
Tokenat
Token ID265
Feature activation-1.27e+00

Pos logit contributions
interstitial+6.631
Appearances+6.414
ozyg+6.299
 barn+6.248
+6.243
Neg logit contributions
zos-9.185
oint-8.135
ghazi-7.937
wra-7.835
kus-7.803
Tokenoder
Token ID12342
Feature activation-4.50e+00

Pos logit contributions
Appearances+0.878
interstitial+0.876
+0.853
 barn+0.832
NPR+0.819
Neg logit contributions
zos-1.116
oint-1.004
kus-0.967
wra-0.944
ghazi-0.943
Tokenma
Token ID2611
Feature activation-5.91e+00

Pos logit contributions
interstitial+2.790
Appearances+2.770
+2.681
 barn+2.651
 Emmy+2.582
Neg logit contributions
zos-4.233
oint-3.845
kus-3.672
wra-3.641
ghazi-3.626
Token of
Token ID286
Feature activation-2.80e+00

Pos logit contributions
interstitial+3.783
Appearances+3.746
 barn+3.672
+3.632
 Emmy+3.506
Neg logit contributions
zos-5.398
oint-4.837
kus-4.684
ghazi-4.647
wra-4.592
Token late
Token ID2739
Feature activation-4.39e-01

Pos logit contributions
interstitial+1.833
Appearances+1.827
+1.772
 barn+1.757
 Emmy+1.695
Neg logit contributions
zos-2.577
oint-2.326
kus-2.235
ghazi-2.193
wra-2.190
Tokenand
Token ID392
Feature activation+1.06e+00

Pos logit contributions
Appearances+6.273
interstitial+6.238
 barn+6.056
NPR+6.033
+5.991
Neg logit contributions
zos-6.658
oint-5.828
ghazi-5.640
wra-5.529
estine-5.456
Tokenling
Token ID1359
Feature activation-6.54e-01

Pos logit contributions
zos+1.308
oint+1.222
kus+1.179
wra+1.160
ghazi+1.151
Neg logit contributions
Appearances-0.380
interstitial-0.366
-0.360
 barn-0.330
NPR-0.319
Token 1994
Token ID9162
Feature activation+2.51e-01

Pos logit contributions
Appearances+0.447
interstitial+0.442
+0.434
 barn+0.419
NPR+0.414
Neg logit contributions
zos-0.587
oint-0.534
kus-0.509
wra-0.497
ghazi-0.496
Token Kel
Token ID15150
Feature activation-5.46e+00

Pos logit contributions
zos+0.238
oint+0.218
kus+0.208
wra+0.204
ghazi+0.202
Neg logit contributions
Appearances-0.158
interstitial-0.157
-0.154
 barn-0.147
NPR-0.146
Tokensey
Token ID4397
Feature activation-4.05e+00

Pos logit contributions
Appearances+2.805
 Emmy+2.657
 barn+2.649
interstitial+2.648
NPR+2.580
Neg logit contributions
zos-5.517
oint-5.163
wra-4.838
ghazi-4.796
kus-4.759
Token Gram
Token ID20159
Feature activation-1.08e+01

Pos logit contributions
Appearances+1.759
interstitial+1.692
 Emmy+1.673
+1.650
 barn+1.621
Neg logit contributions
zos-4.581
oint-4.239
kus-4.049
wra-4.016
ghazi-4.003
Tokenmer
Token ID647
Feature activation-4.74e+00

Pos logit contributions
Appearances+4.531
NPR+4.516
interstitial+4.494
 barn+4.247
 Emmy+3.989
Neg logit contributions
zos-11.202
ghazi-10.165
oint-10.069
utsche-9.702
estine-9.674
Token
Token ID198
Feature activation-5.37e-01

Pos logit contributions
Appearances+3.014
interstitial+2.922
+2.886
 barn+2.817
NPR+2.784
Neg logit contributions
zos-4.420
oint-4.027
kus-3.852
wra-3.781
ghazi-3.769
Token
Token ID198
Feature activation-2.12e+00

Pos logit contributions
Appearances+0.339
interstitial+0.319
+0.318
 barn+0.316
NPR+0.314
Neg logit contributions
zos-0.512
oint-0.462
kus-0.445
ghazi-0.438
wra-0.436
Token1994
Token ID22666
Feature activation-1.85e+00

Pos logit contributions
Appearances+1.056
interstitial+1.034
+0.994
NPR+0.950
 barn+0.949
Neg logit contributions
zos-2.303
oint-2.120
kus-2.046
wra-2.002
ghazi-1.998
Token John
Token ID1757
Feature activation-1.54e+00

Pos logit contributions
Appearances+1.133
interstitial+1.107
+1.088
 barn+1.060
NPR+1.039
Neg logit contributions
zos-1.788
oint-1.636
kus-1.569
wra-1.536
ghazi-1.533
Token a
Token ID257
Feature activation+1.38e+00

Pos logit contributions
zos+0.104
oint+0.094
kus+0.090
wra+0.088
ghazi+0.088
Neg logit contributions
Appearances-0.081
interstitial-0.080
-0.078
 barn-0.076
NPR-0.075
Token parody
Token ID29695
Feature activation+5.46e-01

Pos logit contributions
zos+1.275
oint+1.168
kus+1.116
wra+1.090
ghazi+1.086
Neg logit contributions
Appearances-0.902
interstitial-0.892
-0.876
NPR-0.831
 barn-0.825
Token of
Token ID286
Feature activation-2.49e+00

Pos logit contributions
zos+0.483
oint+0.441
kus+0.420
wra+0.411
ghazi+0.409
Neg logit contributions
Appearances-0.378
interstitial-0.374
-0.368
 barn-0.350
NPR-0.349
Token a
Token ID257
Feature activation-1.96e+00

Pos logit contributions
Appearances+1.556
interstitial+1.524
+1.495
 barn+1.461
NPR+1.426
Neg logit contributions
zos-2.371
oint-2.173
kus-2.082
wra-2.032
ghazi-2.028
Token Pit
Token ID16889
Feature activation+6.35e-01

Pos logit contributions
Appearances+1.209
interstitial+1.189
+1.164
 barn+1.133
NPR+1.109
Neg logit contributions
zos-1.897
oint-1.736
kus-1.662
wra-1.628
ghazi-1.622
Tokenbull
Token ID16308
Feature activation-1.08e+01

Pos logit contributions
zos+0.506
oint+0.454
kus+0.435
wra+0.422
ghazi+0.421
Neg logit contributions
Appearances-0.500
interstitial-0.500
-0.487
 barn-0.468
NPR-0.467
Token and
Token ID290
Feature activation-1.03e+00

Pos logit contributions
Appearances+6.801
 barn+6.658
interstitial+6.568
+6.412
 Emmy+6.341
Neg logit contributions
zos-9.630
oint-8.623
kus-8.131
ghazi-7.985
estine-7.900
Token Ke
Token ID3873
Feature activation-3.16e+00

Pos logit contributions
Appearances+0.710
interstitial+0.700
+0.686
 barn+0.667
NPR+0.657
Neg logit contributions
zos-0.921
oint-0.837
kus-0.798
wra-0.780
ghazi-0.777
Token$
Token ID3
Feature activation-3.97e+00

Pos logit contributions
Appearances+3.004
interstitial+2.967
+2.949
 barn+2.896
NPR+2.866
Neg logit contributions
zos-1.874
oint-1.653
kus-1.530
ghazi-1.497
wra-1.465
Tokenha
Token ID3099
Feature activation-5.52e+00

Pos logit contributions
Appearances+4.390
interstitial+4.288
 barn+4.204
+4.193
 Emmy+4.154
Neg logit contributions
zos-1.869
oint-1.549
kus-1.382
ghazi-1.326
wra-1.283
Token music
Token ID2647
Feature activation-4.03e-01

Pos logit contributions
Appearances+3.621
interstitial+3.550
 barn+3.479
+3.475
 Emmy+3.339
Neg logit contributions
zos-5.074
oint-4.571
kus-4.381
ghazi-4.285
wra-4.261
Token CNN
Token ID8100
Feature activation+7.89e-01

Pos logit contributions
Appearances+0.540
interstitial+0.533
+0.523
 barn+0.506
NPR+0.499
Neg logit contributions
zos-0.756
oint-0.689
kus-0.659
wra-0.645
ghazi-0.642
Token
Token ID447
Feature activation+1.85e+00

Pos logit contributions
zos+0.681
oint+0.617
kus+0.588
wra+0.574
ghazi+0.572
Neg logit contributions
Appearances-0.565
interstitial-0.559
-0.548
 barn-0.532
NPR-0.524
Token
Token ID247
Feature activation+2.87e-01

Pos logit contributions
zos+1.520
oint+1.382
kus+1.309
wra+1.277
ghazi+1.273
Neg logit contributions
Appearances-1.389
interstitial-1.371
-1.360
 barn-1.314
NPR-1.292
Tokens
Token ID82
Feature activation-9.95e-02

Pos logit contributions
zos+0.284
oint+0.261
kus+0.251
wra+0.246
ghazi+0.244
Neg logit contributions
Appearances-0.170
interstitial-0.167
-0.164
 barn-0.158
NPR-0.155
Token Andrew
Token ID6858
Feature activation+1.29e+00

Pos logit contributions
Appearances+0.062
interstitial+0.061
+0.060
 barn+0.058
NPR+0.057
Neg logit contributions
zos-0.095
oint-0.087
kus-0.083
wra-0.082
ghazi-0.081
Token K
Token ID509
Feature activation-1.07e+01

Pos logit contributions
zos+1.211
oint+1.105
kus+1.064
wra+1.039
ghazi+1.039
Neg logit contributions
Appearances-0.826
interstitial-0.816
-0.795
 barn-0.766
NPR-0.756
Tokenac
Token ID330
Feature activation-2.11e+00

Pos logit contributions
Appearances+5.832
NPR+5.639
interstitial+5.460
 barn+5.453
+5.440
Neg logit contributions
zos-10.356
oint-9.194
kus-9.102
ghazi-8.779
wra-8.723
Tokenzynski
Token ID47143
Feature activation-1.90e+00

Pos logit contributions
Appearances+1.397
interstitial+1.378
+1.335
 barn+1.331
NPR+1.310
Neg logit contributions
zos-1.896
oint-1.712
kus-1.635
wra-1.621
ghazi-1.611
Token.
Token ID13
Feature activation+4.02e-01

Pos logit contributions
Appearances+1.280
interstitial+1.258
+1.245
 barn+1.203
NPR+1.192
Neg logit contributions
zos-1.714
oint-1.562
kus-1.488
wra-1.453
ghazi-1.452
Token
Token ID198
Feature activation-1.56e+00

Pos logit contributions
zos+0.363
oint+0.330
kus+0.314
wra+0.308
ghazi+0.308
Neg logit contributions
interstitial-0.272
Appearances-0.271
-0.263
 barn-0.256
NPR-0.249
Token
Token ID198
Feature activation-1.24e+00

Pos logit contributions
Appearances+0.957
NPR+0.891
 barn+0.887
+0.887
interstitial+0.883
Neg logit contributions
zos-1.512
oint-1.364
kus-1.315
ghazi-1.301
wra-1.290
Tokentic
Token ID13370
Feature activation+8.44e-01

Pos logit contributions
zos+0.668
oint+0.573
kus+0.530
wra+0.504
ghazi+0.496
Neg logit contributions
Appearances-1.252
interstitial-1.233
-1.223
 barn-1.194
NPR-1.189
Token palm
Token ID18057
Feature activation+3.57e+00

Pos logit contributions
zos+0.784
oint+0.716
kus+0.684
wra+0.667
ghazi+0.661
Neg logit contributions
Appearances-0.553
interstitial-0.542
-0.532
 barn-0.512
NPR-0.512
Tokenopl
Token ID20106
Feature activation+7.97e-01

Pos logit contributions
zos+3.197
oint+2.938
kus+2.781
wra+2.708
estine+2.692
Neg logit contributions
Appearances-2.465
interstitial-2.404
-2.367
NPR-2.278
 barn-2.268
Tokenant
Token ID415
Feature activation-2.51e+00

Pos logit contributions
zos+0.509
oint+0.444
kus+0.413
wra+0.398
ghazi+0.395
Neg logit contributions
Appearances-0.758
interstitial-0.745
-0.741
 barn-0.722
NPR-0.718
Tokenar
Token ID283
Feature activation-2.43e+00

Pos logit contributions
Appearances+2.229
interstitial+2.221
+2.171
 barn+2.142
NPR+2.099
Neg logit contributions
zos-1.700
oint-1.493
kus-1.410
wra-1.376
ghazi-1.371
Token ker
Token ID41927
Feature activation-1.07e+01

Pos logit contributions
Appearances+1.550
interstitial+1.534
+1.501
 barn+1.456
NPR+1.424
Neg logit contributions
zos-2.276
oint-2.075
kus-1.989
wra-1.949
ghazi-1.946
Tokenat
Token ID265
Feature activation-1.07e+00

Pos logit contributions
interstitial+6.839
Appearances+6.672
+6.478
 barn+6.475
ozyg+6.447
Neg logit contributions
zos-8.651
oint-7.802
kus-7.558
wra-7.505
ghazi-7.499
Tokenoder
Token ID12342
Feature activation-4.90e+00

Pos logit contributions
Appearances+0.831
interstitial+0.825
+0.809
 barn+0.788
NPR+0.779
Neg logit contributions
zos-0.857
oint-0.768
kus-0.733
wra-0.714
ghazi-0.712
Tokenma
Token ID2611
Feature activation-4.94e+00

Pos logit contributions
interstitial+3.012
Appearances+3.005
+2.913
 barn+2.863
NPR+2.788
Neg logit contributions
zos-4.559
oint-4.177
kus-3.995
wra-3.969
ghazi-3.952
Token has
Token ID468
Feature activation-3.48e+00

Pos logit contributions
Appearances+3.234
interstitial+3.189
+3.105
 barn+3.054
 Emmy+2.944
Neg logit contributions
zos-4.509
oint-4.101
kus-3.927
wra-3.867
ghazi-3.864
Token been
Token ID587
Feature activation-2.31e+00

Pos logit contributions
Appearances+2.276
interstitial+2.257
+2.199
 barn+2.172
NPR+2.097
Neg logit contributions
zos-3.199
oint-2.904
kus-2.784
ghazi-2.730
wra-2.727
Token you
Token ID345
Feature activation+3.36e+00

Pos logit contributions
Appearances+0.177
interstitial+0.174
+0.171
 barn+0.167
NPR+0.164
Neg logit contributions
zos-0.212
oint-0.192
kus-0.183
wra-0.179
ghazi-0.178
Token can
Token ID460
Feature activation+2.93e+00

Pos logit contributions
zos+3.033
oint+2.757
kus+2.638
wra+2.580
ghazi+2.543
Neg logit contributions
Appearances-2.265
interstitial-2.256
-2.201
 barn-2.092
NPR-2.081
Token avoid
Token ID3368
Feature activation+3.47e+00

Pos logit contributions
zos+2.471
oint+2.245
kus+2.147
wra+2.084
estine+2.054
Neg logit contributions
Appearances-2.171
interstitial-2.164
-2.102
NPR-1.998
 barn-1.975
Token a
Token ID257
Feature activation+2.32e+00

Pos logit contributions
zos+2.983
oint+2.719
kus+2.576
wra+2.526
estine+2.487
Neg logit contributions
Appearances-2.459
interstitial-2.437
-2.421
NPR-2.310
 barn-2.286
Token wild
Token ID4295
Feature activation+3.22e-01

Pos logit contributions
zos+1.992
oint+1.805
kus+1.725
wra+1.680
ghazi+1.673
Neg logit contributions
Appearances-1.667
interstitial-1.665
-1.623
NPR-1.557
 barn-1.553
Token goose
Token ID37246
Feature activation-1.07e+01

Pos logit contributions
zos+0.304
oint+0.278
kus+0.266
wra+0.260
ghazi+0.259
Neg logit contributions
Appearances-0.205
interstitial-0.202
-0.198
 barn-0.191
NPR-0.189
Token chase
Token ID15505
Feature activation-8.00e-01

Pos logit contributions
Appearances+4.588
 barn+4.494
interstitial+4.303
+4.167
 Emmy+4.107
Neg logit contributions
zos-11.902
oint-10.778
kus-10.578
estine-10.366
ghazi-10.275
Token.
Token ID13
Feature activation-5.17e-01

Pos logit contributions
Appearances+0.583
interstitial+0.574
+0.563
 barn+0.552
NPR+0.542
Neg logit contributions
zos-0.683
oint-0.615
kus-0.585
ghazi-0.571
wra-0.570
Token
Token ID198
Feature activation-8.96e-01

Pos logit contributions
Appearances+0.335
interstitial+0.329
+0.324
 barn+0.313
NPR+0.309
Neg logit contributions
zos-0.484
oint-0.441
kus-0.422
wra-0.412
ghazi-0.411
Token
Token ID198
Feature activation-1.14e+00

Pos logit contributions
Appearances+0.567
interstitial+0.533
+0.531
 barn+0.526
NPR+0.526
Neg logit contributions
zos-0.854
oint-0.772
kus-0.743
ghazi-0.733
wra-0.728
Token#
Token ID2
Feature activation-3.09e+00

Pos logit contributions
Appearances+0.782
interstitial+0.755
+0.744
NPR+0.724
 barn+0.716
Neg logit contributions
zos-1.042
oint-0.945
kus-0.900
ghazi-0.879
wra-0.876
Token of
Token ID286
Feature activation-5.17e-01

Pos logit contributions
zos+4.101
oint+3.770
kus+3.511
wra+3.452
ghazi+3.436
Neg logit contributions
interstitial-3.278
Appearances-3.275
-3.216
NPR-3.018
 barn-3.014
Token these
Token ID777
Feature activation-1.08e+00

Pos logit contributions
Appearances+0.349
interstitial+0.344
+0.337
 barn+0.330
NPR+0.323
Neg logit contributions
zos-0.468
oint-0.425
kus-0.407
wra-0.397
ghazi-0.396
Token mushrooms
Token ID23452
Feature activation+2.90e+00

Pos logit contributions
Appearances+0.993
interstitial+0.982
+0.970
 barn+0.952
NPR+0.940
Neg logit contributions
zos-0.707
oint-0.619
kus-0.580
wra-0.560
ghazi-0.560
Token particularly
Token ID3573
Feature activation-1.79e+00

Pos logit contributions
zos+2.567
oint+2.351
kus+2.210
wra+2.165
ghazi+2.153
Neg logit contributions
Appearances-2.016
interstitial-2.008
-1.984
NPR-1.862
 barn-1.858
Token dist
Token ID1233
Feature activation+3.71e+00

Pos logit contributions
Appearances+1.183
interstitial+1.161
 barn+1.146
+1.138
NPR+1.103
Neg logit contributions
zos-1.628
oint-1.468
kus-1.420
ghazi-1.394
wra-1.390
Tokenast
Token ID459
Feature activation+6.26e+00

Pos logit contributions
zos+2.268
oint+2.004
kus+1.837
wra+1.775
estine+1.744
Neg logit contributions
Appearances-3.596
interstitial-3.554
-3.525
 barn-3.412
NPR-3.393
Tokeneful
Token ID13839
Feature activation-8.76e-01

Pos logit contributions
zos+3.900
oint+3.536
kus+3.067
wra+3.042
estine+2.995
Neg logit contributions
Appearances-6.048
-5.982
interstitial-5.894
NPR-5.652
 barn-5.619
Token,
Token ID11
Feature activation+1.58e+00

Pos logit contributions
Appearances+0.690
interstitial+0.679
+0.664
 barn+0.659
NPR+0.646
Neg logit contributions
zos-0.689
oint-0.617
kus-0.587
ghazi-0.574
wra-0.571
Token you
Token ID345
Feature activation+6.72e-01

Pos logit contributions
zos+1.354
oint+1.225
kus+1.164
wra+1.138
ghazi+1.130
Neg logit contributions
Appearances-1.144
interstitial-1.131
-1.112
 barn-1.074
NPR-1.062
Token can
Token ID460
Feature activation-1.09e+00

Pos logit contributions
zos+0.646
oint+0.591
kus+0.566
wra+0.555
ghazi+0.553
Neg logit contributions
Appearances-0.416
interstitial-0.409
-0.401
 barn-0.390
NPR-0.383
Token always
Token ID1464
Feature activation-3.51e-01

Pos logit contributions
Appearances+0.722
interstitial+0.703
+0.698
 barn+0.698
NPR+0.679
Neg logit contributions
zos-0.977
oint-0.882
kus-0.848
ghazi-0.838
wra-0.829
Token,
Token ID11
Feature activation+5.83e+00

Pos logit contributions
zos+0.560
oint+0.504
kus+0.478
wra+0.465
ghazi+0.463
Neg logit contributions
Appearances-0.541
interstitial-0.535
-0.526
 barn-0.512
NPR-0.506
Token TX
Token ID15326
Feature activation+3.28e+00

Pos logit contributions
zos+4.673
oint+4.177
wra+3.977
kus+3.963
estine+3.759
Neg logit contributions
Appearances-4.476
-4.357
interstitial-4.345
NPR-4.100
 barn-4.077
Token from
Token ID422
Feature activation+4.19e+00

Pos logit contributions
zos+2.620
oint+2.352
kus+2.236
wra+2.191
ghazi+2.159
Neg logit contributions
Appearances-2.548
interstitial-2.519
-2.470
NPR-2.371
 barn-2.371
Token the
Token ID262
Feature activation+2.15e+00

Pos logit contributions
zos+3.649
oint+3.313
kus+3.191
wra+3.095
ghazi+3.065
Neg logit contributions
Appearances-2.923
interstitial-2.882
-2.828
NPR-2.700
 barn-2.678
Token east
Token ID7627
Feature activation+2.32e+00

Pos logit contributions
zos+1.868
oint+1.697
kus+1.622
wra+1.577
ghazi+1.564
Neg logit contributions
Appearances-1.534
interstitial-1.512
-1.479
NPR-1.420
 barn-1.415
Token coast
Token ID7051
Feature activation+6.25e+00

Pos logit contributions
zos+1.919
oint+1.740
kus+1.649
wra+1.613
ghazi+1.595
Neg logit contributions
Appearances-1.749
interstitial-1.725
-1.696
NPR-1.630
 barn-1.630
Token knowing
Token ID6970
Feature activation-9.08e-01

Pos logit contributions
zos+5.027
oint+4.538
kus+4.302
wra+4.209
estine+4.152
Neg logit contributions
Appearances-4.788
interstitial-4.704
-4.609
NPR-4.413
 barn-4.340
Token all
Token ID477
Feature activation-3.38e+00

Pos logit contributions
Appearances+0.613
interstitial+0.604
+0.594
 barn+0.584
 Emmy+0.568
Neg logit contributions
zos-0.816
oint-0.746
kus-0.711
ghazi-0.698
wra-0.696
Token of
Token ID286
Feature activation+3.04e-01

Pos logit contributions
Appearances+2.042
interstitial+2.004
+1.981
 barn+1.932
NPR+1.881
Neg logit contributions
zos-3.259
oint-2.993
kus-2.873
wra-2.814
ghazi-2.805
Token five
Token ID1936
Feature activation-4.33e+00

Pos logit contributions
zos+0.270
oint+0.245
kus+0.234
wra+0.229
ghazi+0.228
Neg logit contributions
Appearances-0.211
interstitial-0.208
-0.205
 barn-0.199
NPR-0.196
Token people
Token ID661
Feature activation+6.92e-01

Pos logit contributions
Appearances+2.942
+2.868
interstitial+2.865
 barn+2.842
 Emmy+2.769
Neg logit contributions
zos-3.820
oint-3.471
kus-3.319
wra-3.256
ghazi-3.217
Tokenev
Token ID1990
Feature activation-7.86e-01

Pos logit contributions
Appearances+0.884
interstitial+0.869
+0.847
 barn+0.839
NPR+0.826
Neg logit contributions
zos-0.994
oint-0.904
kus-0.845
wra-0.842
ghazi-0.841
Token/
Token ID14
Feature activation-1.26e+00

Pos logit contributions
Appearances+0.634
interstitial+0.624
+0.616
 barn+0.600
NPR+0.593
Neg logit contributions
zos-0.609
oint-0.543
kus-0.512
ghazi-0.500
wra-0.500
TokenR
Token ID49
Feature activation+4.48e+00

Pos logit contributions
Appearances+0.848
interstitial+0.832
+0.816
NPR+0.794
 barn+0.787
Neg logit contributions
zos-1.135
oint-1.032
kus-0.983
ghazi-0.973
wra-0.963
TokenIA
Token ID3539
Feature activation+2.12e+00

Pos logit contributions
zos+3.613
oint+3.253
kus+3.100
wra+3.014
ghazi+2.980
Neg logit contributions
Appearances-3.452
interstitial-3.410
-3.366
 barn-3.278
NPR-3.216
Token Nov
Token ID5267
Feature activation+2.40e+00

Pos logit contributions
zos+1.663
oint+1.492
kus+1.419
wra+1.390
ghazi+1.378
Neg logit contributions
Appearances-1.690
interstitial-1.682
-1.638
 barn-1.596
NPR-1.573
Tokenost
Token ID455
Feature activation+8.83e+00

Pos logit contributions
zos+1.941
oint+1.757
kus+1.662
wra+1.628
ghazi+1.604
Neg logit contributions
Appearances-1.850
interstitial-1.827
-1.814
 barn-1.735
NPR-1.711
Tokeni
Token ID72
Feature activation+5.18e+00

Pos logit contributions
zos+5.236
oint+4.814
kus+4.410
wra+4.391
estine+4.365
Neg logit contributions
Appearances-8.224
-8.156
interstitial-8.142
 barn-7.835
ozyg-7.493
Token/
Token ID14
Feature activation-4.07e-01

Pos logit contributions
zos+3.275
oint+2.941
kus+2.752
wra+2.634
estine+2.595
Neg logit contributions
interstitial-4.742
Appearances-4.735
-4.586
 barn-4.510
NPR-4.492
TokenK
Token ID42
Feature activation+7.42e-01

Pos logit contributions
Appearances+0.288
interstitial+0.282
+0.278
 barn+0.269
NPR+0.268
Neg logit contributions
zos-0.357
oint-0.324
kus-0.307
ghazi-0.301
wra-0.301
Tokenremlin
Token ID17244
Feature activation+2.08e+00

Pos logit contributions
zos+0.750
oint+0.686
kus+0.660
ghazi+0.649
wra+0.647
Neg logit contributions
Appearances-0.423
interstitial-0.415
-0.406
 barn-0.392
NPR-0.390
Token
Token ID198
Feature activation-4.12e-01

Pos logit contributions
zos+1.599
oint+1.439
kus+1.362
wra+1.325
ghazi+1.312
Neg logit contributions
Appearances-1.676
interstitial-1.663
-1.628
 barn-1.591
NPR-1.571
Token
Token ID447
Feature activation+1.43e-01

Pos logit contributions
zos+0.456
oint+0.416
kus+0.397
wra+0.389
ghazi+0.388
Neg logit contributions
Appearances-0.315
interstitial-0.309
-0.303
 barn-0.293
NPR-0.290
Token
Token ID250
Feature activation+2.16e+00

Pos logit contributions
zos+0.149
oint+0.137
kus+0.131
wra+0.129
ghazi+0.129
Neg logit contributions
Appearances-0.078
interstitial-0.077
-0.075
 barn-0.072
NPR-0.071
TokenWho
Token ID8241
Feature activation-6.80e-01

Pos logit contributions
zos+1.938
oint+1.763
kus+1.685
wra+1.650
ghazi+1.643
Neg logit contributions
Appearances-1.459
interstitial-1.456
-1.424
 barn-1.385
NPR-1.347
Token is
Token ID318
Feature activation+7.85e-02

Pos logit contributions
Appearances+0.423
interstitial+0.415
+0.409
 barn+0.396
NPR+0.389
Neg logit contributions
zos-0.651
oint-0.596
kus-0.569
wra-0.558
ghazi-0.556
Token this
Token ID428
Feature activation+2.67e-01

Pos logit contributions
zos+0.072
oint+0.065
kus+0.062
wra+0.061
ghazi+0.061
Neg logit contributions
Appearances-0.052
interstitial-0.052
-0.051
 barn-0.049
NPR-0.048
Token young
Token ID1862
Feature activation+6.43e+00

Pos logit contributions
zos+0.230
oint+0.208
kus+0.198
wra+0.193
ghazi+0.193
Neg logit contributions
Appearances-0.192
interstitial-0.190
-0.186
 barn-0.182
NPR-0.179
Token man
Token ID582
Feature activation+2.78e+00

Pos logit contributions
zos+5.431
oint+4.965
kus+4.758
wra+4.650
ghazi+4.552
Neg logit contributions
Appearances-4.558
interstitial-4.496
-4.488
NPR-4.206
 barn-4.097
Token?
Token ID30
Feature activation+1.02e-01

Pos logit contributions
zos+2.321
oint+2.090
kus+2.005
wra+1.955
ghazi+1.948
Neg logit contributions
Appearances-2.048
interstitial-2.023
-1.987
 barn-1.909
NPR-1.907
Token
Token ID447
Feature activation-2.07e-01

Pos logit contributions
zos+0.108
oint+0.100
kus+0.096
wra+0.094
ghazi+0.094
Neg logit contributions
Appearances-0.053
interstitial-0.052
-0.051
 barn-0.049
NPR-0.048
Token
Token ID251
Feature activation-8.52e-02

Pos logit contributions
Appearances+0.095
interstitial+0.093
+0.091
 barn+0.086
NPR+0.085
Neg logit contributions
zos-0.231
oint-0.215
kus-0.207
wra-0.203
ghazi-0.203
Token said
Token ID531
Feature activation-7.63e-02

Pos logit contributions
Appearances+0.056
interstitial+0.056
+0.054
 barn+0.053
NPR+0.052
Neg logit contributions
zos-0.078
oint-0.071
kus-0.068
wra-0.067
ghazi-0.067
Token Var
Token ID12372
Feature activation-1.46e+00

Pos logit contributions
Appearances+0.105
interstitial+0.103
+0.101
 barn+0.098
NPR+0.096
Neg logit contributions
zos-0.160
oint-0.146
kus-0.140
wra-0.137
ghazi-0.137
Tokenric
Token ID1173
Feature activation+1.34e+00

Pos logit contributions
Appearances+1.153
interstitial+1.149
+1.118
 barn+1.100
NPR+1.084
Neg logit contributions
zos-1.135
oint-1.021
kus-0.961
wra-0.945
ghazi-0.940
Tokenchio
Token ID40900
Feature activation+1.27e+00

Pos logit contributions
zos+1.032
oint+0.923
kus+0.873
wra+0.849
ghazi+0.845
Neg logit contributions
Appearances-1.084
interstitial-1.072
-1.056
 barn-1.028
NPR-1.017
Token,
Token ID11
Feature activation+5.08e+00

Pos logit contributions
zos+1.003
oint+0.899
kus+0.851
wra+0.829
ghazi+0.825
Neg logit contributions
Appearances-1.008
interstitial-0.997
-0.981
 barn-0.954
NPR-0.944
Token a
Token ID257
Feature activation+6.02e+00

Pos logit contributions
zos+3.841
oint+3.497
kus+3.283
wra+3.216
ghazi+3.130
Neg logit contributions
Appearances-4.067
interstitial-4.034
-3.923
NPR-3.722
 barn-3.657
Token pale
Token ID14005
Feature activation+6.91e+00

Pos logit contributions
zos+5.552
oint+5.168
kus+4.943
wra+4.776
estine+4.758
Neg logit contributions
Appearances-3.832
interstitial-3.743
-3.618
NPR-3.410
 Emmy-3.197
Tokenont
Token ID756
Feature activation+3.93e-01

Pos logit contributions
zos+5.713
oint+5.360
kus+4.829
wra+4.729
estine+4.686
Neg logit contributions
Appearances-5.249
interstitial-5.034
-4.986
NPR-4.737
 Emmy-4.659
Tokenologist
Token ID7451
Feature activation+4.65e+00

Pos logit contributions
zos+0.383
oint+0.353
kus+0.336
wra+0.329
ghazi+0.328
Neg logit contributions
Appearances-0.239
interstitial-0.236
-0.230
 barn-0.221
NPR-0.219
Token at
Token ID379
Feature activation+9.52e-01

Pos logit contributions
zos+3.956
oint+3.649
kus+3.410
wra+3.350
ghazi+3.279
Neg logit contributions
Appearances-3.318
interstitial-3.317
-3.213
NPR-3.027
 barn-3.006
Token Montana
Token ID18311
Feature activation-4.59e+00

Pos logit contributions
zos+0.838
oint+0.763
kus+0.726
wra+0.709
ghazi+0.704
Neg logit contributions
Appearances-0.669
interstitial-0.659
-0.646
 barn-0.621
NPR-0.618
Token State
Token ID1812
Feature activation-1.64e+00

Pos logit contributions
Appearances+4.030
interstitial+3.924
+3.915
 barn+3.857
NPR+3.787
Neg logit contributions
zos-3.214
oint-2.824
kus-2.643
wra-2.590
ghazi-2.589
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
zos+0.260
oint+0.233
kus+0.220
wra+0.215
ghazi+0.214
Neg logit contributions
Appearances-0.266
interstitial-0.263
-0.259
 barn-0.252
NPR-0.250
Token Defense
Token ID5947
Feature activation+1.25e+00

Pos logit contributions
zos+0.992
oint+0.906
kus+0.862
wra+0.841
ghazi+0.841
Neg logit contributions
Appearances-0.775
interstitial-0.763
-0.754
 barn-0.723
NPR-0.717
Token Department
Token ID2732
Feature activation+3.32e+00

Pos logit contributions
zos+1.088
oint+1.003
kus+0.949
wra+0.928
ghazi+0.926
Neg logit contributions
Appearances-0.871
interstitial-0.868
-0.864
NPR-0.827
 barn-0.825
Token said
Token ID531
Feature activation+1.09e+00

Pos logit contributions
zos+3.093
oint+2.860
kus+2.720
wra+2.657
ghazi+2.641
Neg logit contributions
Appearances-2.142
interstitial-2.115
-2.057
NPR-1.965
 barn-1.951
Token it
Token ID340
Feature activation+2.73e+00

Pos logit contributions
zos+0.982
oint+0.897
kus+0.860
wra+0.839
ghazi+0.835
Neg logit contributions
Appearances-0.732
interstitial-0.722
-0.709
 barn-0.679
NPR-0.677
Token condemned
Token ID15006
Feature activation+5.28e+00

Pos logit contributions
zos+2.714
oint+2.517
kus+2.408
wra+2.366
ghazi+2.343
Neg logit contributions
Appearances-1.604
interstitial-1.585
-1.530
NPR-1.445
 barn-1.438
Token the
Token ID262
Feature activation+1.93e+00

Pos logit contributions
zos+4.144
oint+3.778
kus+3.591
wra+3.513
ghazi+3.488
Neg logit contributions
Appearances-4.016
interstitial-3.958
-3.934
NPR-3.837
 barn-3.722
Token crimes
Token ID6741
Feature activation-4.20e-01

Pos logit contributions
zos+1.648
oint+1.502
kus+1.427
wra+1.388
ghazi+1.379
Neg logit contributions
Appearances-1.404
interstitial-1.376
-1.368
NPR-1.305
 barn-1.298
Token in
Token ID287
Feature activation+3.75e-01

Pos logit contributions
Appearances+0.304
interstitial+0.299
+0.295
 barn+0.287
NPR+0.283
Neg logit contributions
zos-0.360
oint-0.325
kus-0.309
wra-0.302
ghazi-0.301
Token Min
Token ID1855
Feature activation+3.68e+00

Pos logit contributions
zos+0.321
oint+0.291
kus+0.277
wra+0.270
ghazi+0.269
Neg logit contributions
Appearances-0.273
interstitial-0.269
-0.265
 barn-0.256
NPR-0.254
Tokenova
Token ID10071
Feature activation+2.17e+00

Pos logit contributions
zos+2.849
oint+2.551
kus+2.416
wra+2.348
ghazi+2.338
Neg logit contributions
Appearances-2.973
interstitial-2.940
-2.904
 barn-2.811
NPR-2.778
Token).
Token ID737
Feature activation-4.33e-01

Pos logit contributions
zos+0.482
oint+0.434
kus+0.410
wra+0.401
ghazi+0.398
Neg logit contributions
Appearances-0.479
interstitial-0.474
-0.465
 barn-0.451
NPR-0.447
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
Appearances+0.270
interstitial+0.266
+0.261
 barn+0.252
NPR+0.248
Neg logit contributions
zos-0.415
oint-0.379
kus-0.363
wra-0.356
ghazi-0.354
Token
Token ID198
Feature activation-5.10e-01

Pos logit contributions
Appearances+0.107
interstitial+0.102
+0.101
 barn+0.100
NPR+0.100
Neg logit contributions
zos-0.158
oint-0.143
kus-0.137
ghazi-0.135
wra-0.134
TokenHere
Token ID4342
Feature activation-4.22e-01

Pos logit contributions
Appearances+0.337
interstitial+0.330
+0.323
 barn+0.313
NPR+0.312
Neg logit contributions
zos-0.472
oint-0.429
kus-0.411
wra-0.400
ghazi-0.400
Token
Token ID447
Feature activation+1.39e+00

Pos logit contributions
Appearances+0.283
interstitial+0.279
+0.274
 barn+0.265
NPR+0.261
Neg logit contributions
zos-0.384
oint-0.350
kus-0.334
wra-0.327
ghazi-0.325
Token
Token ID247
Feature activation+1.06e+00

Pos logit contributions
zos+1.100
oint+0.996
kus+0.942
wra+0.920
ghazi+0.916
Neg logit contributions
Appearances-1.087
interstitial-1.073
-1.067
 barn-1.032
NPR-1.017
Tokens
Token ID82
Feature activation-7.54e-01

Pos logit contributions
zos+1.026
oint+0.941
kus+0.901
wra+0.885
ghazi+0.880
Neg logit contributions
Appearances-0.645
interstitial-0.636
-0.622
 barn-0.599
NPR-0.592
Token a
Token ID257
Feature activation+6.92e-01

Pos logit contributions
Appearances+0.535
interstitial+0.528
+0.520
 barn+0.506
NPR+0.498
Neg logit contributions
zos-0.655
oint-0.594
kus-0.566
wra-0.552
ghazi-0.551
Token picture
Token ID4286
Feature activation-5.63e-01

Pos logit contributions
zos+0.619
oint+0.563
kus+0.538
wra+0.526
ghazi+0.523
Neg logit contributions
Appearances-0.476
interstitial-0.471
-0.461
 barn-0.443
NPR-0.440
Token to
Token ID284
Feature activation-4.41e+00

Pos logit contributions
Appearances+0.370
interstitial+0.364
+0.357
 barn+0.348
NPR+0.343
Neg logit contributions
zos-0.520
oint-0.472
kus-0.453
ghazi-0.441
wra-0.441
Token help
Token ID1037
Feature activation-3.25e+00

Pos logit contributions
Appearances+2.381
 barn+2.326
+2.301
interstitial+2.269
NPR+2.251
Neg logit contributions
zos-4.464
oint-4.094
ghazi-3.910
estine-3.873
kus-3.871
Token
Token ID198
Feature activation+4.04e-02

Pos logit contributions
Appearances+0.726
interstitial+0.713
+0.702
 barn+0.679
NPR+0.669
Neg logit contributions
zos-1.028
oint-0.936
kus-0.896
wra-0.876
ghazi-0.873
Token
Token ID198
Feature activation-9.49e-01

Pos logit contributions
zos+0.038
oint+0.034
kus+0.033
ghazi+0.032
wra+0.032
Neg logit contributions
Appearances-0.026
interstitial-0.025
-0.025
 barn-0.024
NPR-0.024
TokenPixel
Token ID40809
Feature activation+2.94e+00

Pos logit contributions
Appearances+0.677
interstitial+0.660
+0.647
NPR+0.633
 barn+0.623
Neg logit contributions
zos-0.827
oint-0.750
kus-0.715
ghazi-0.696
wra-0.696
Tokenpipe
Token ID34360
Feature activation+1.62e+00

Pos logit contributions
zos+2.589
oint+2.355
kus+2.247
wra+2.202
ghazi+2.185
Neg logit contributions
Appearances-2.062
interstitial-2.037
-1.993
 barn-1.931
NPR-1.901
Token
Token ID198
Feature activation+2.51e+00

Pos logit contributions
zos+1.432
oint+1.302
kus+1.241
wra+1.213
ghazi+1.205
Neg logit contributions
Appearances-1.122
interstitial-1.113
-1.085
 barn-1.053
NPR-1.040
Token
Token ID198
Feature activation+8.53e-01

Pos logit contributions
zos+2.249
oint+2.045
kus+1.951
wra+1.908
ghazi+1.899
Neg logit contributions
Appearances-1.714
interstitial-1.692
-1.660
 barn-1.609
NPR-1.587
TokenAdvertisement
Token ID4723
Feature activation-5.86e+00

Pos logit contributions
zos+0.740
oint+0.670
kus+0.638
wra+0.623
ghazi+0.621
Neg logit contributions
Appearances-0.610
interstitial-0.601
-0.590
 barn-0.572
NPR-0.567
Token
Token ID198
Feature activation+1.83e+00

Pos logit contributions
Appearances+3.096
NPR+2.861
 Emmy+2.778
 barn+2.773
+2.702
Neg logit contributions
zos-6.009
oint-5.420
ghazi-5.260
kus-5.252
utsche-5.249
Token
Token ID198
Feature activation+1.45e+00

Pos logit contributions
zos+1.649
oint+1.499
kus+1.431
wra+1.399
ghazi+1.394
Neg logit contributions
Appearances-1.242
interstitial-1.222
-1.200
 barn-1.165
NPR-1.151
TokenIf
Token ID1532
Feature activation+1.15e+00

Pos logit contributions
zos+1.211
oint+1.092
kus+1.038
wra+1.013
ghazi+1.008
Neg logit contributions
Appearances-1.086
interstitial-1.072
-1.054
 barn-1.024
NPR-1.012
Token you
Token ID345
Feature activation+2.09e+00

Pos logit contributions
zos+0.985
oint+0.890
kus+0.847
wra+0.827
ghazi+0.824
Neg logit contributions
Appearances-0.840
interstitial-0.830
-0.815
 barn-0.792
NPR-0.782
Token is
Token ID318
Feature activation-1.28e+00

Pos logit contributions
Appearances+0.026
interstitial+0.025
+0.025
 barn+0.024
NPR+0.023
Neg logit contributions
zos-0.041
oint-0.038
kus-0.036
wra-0.035
ghazi-0.035
Token going
Token ID1016
Feature activation-2.79e+00

Pos logit contributions
Appearances+0.804
interstitial+0.794
+0.776
 barn+0.759
NPR+0.744
Neg logit contributions
zos-1.219
oint-1.112
kus-1.064
ghazi-1.042
wra-1.039
Token down
Token ID866
Feature activation+1.44e+00

Pos logit contributions
Appearances+1.861
interstitial+1.836
+1.784
 barn+1.776
NPR+1.719
Neg logit contributions
zos-2.536
oint-2.305
kus-2.210
ghazi-2.158
wra-2.139
Token.
Token ID13
Feature activation+6.84e-01

Pos logit contributions
zos+1.261
oint+1.147
kus+1.093
wra+1.072
ghazi+1.060
Neg logit contributions
Appearances-1.023
interstitial-1.007
-0.993
 barn-0.950
NPR-0.944
Token
Token ID198
Feature activation+1.85e-01

Pos logit contributions
zos+0.633
oint+0.578
kus+0.551
wra+0.540
ghazi+0.538
Neg logit contributions
Appearances-0.448
interstitial-0.444
-0.434
 barn-0.419
NPR-0.412
Token
Token ID198
Feature activation+4.95e-01

Pos logit contributions
zos+0.173
oint+0.157
kus+0.151
ghazi+0.148
wra+0.148
Neg logit contributions
Appearances-0.120
interstitial-0.115
-0.114
 barn-0.112
NPR-0.111
TokenThose
Token ID9627
Feature activation+6.44e-01

Pos logit contributions
zos+0.452
oint+0.411
kus+0.393
wra+0.384
ghazi+0.383
Neg logit contributions
Appearances-0.332
interstitial-0.326
-0.320
 barn-0.310
NPR-0.307
Token who
Token ID508
Feature activation+2.76e+00

Pos logit contributions
zos+0.558
oint+0.506
kus+0.482
wra+0.470
ghazi+0.469
Neg logit contributions
Appearances-0.460
interstitial-0.454
-0.446
 barn-0.434
NPR-0.428
Token find
Token ID1064
Feature activation+1.04e+00

Pos logit contributions
zos+2.503
oint+2.276
kus+2.176
wra+2.126
ghazi+2.105
Neg logit contributions
Appearances-1.865
interstitial-1.855
-1.799
 barn-1.724
NPR-1.717
Token ways
Token ID2842
Feature activation-1.37e+00

Pos logit contributions
zos+0.956
oint+0.871
kus+0.830
wra+0.814
ghazi+0.809
Neg logit contributions
Appearances-0.684
interstitial-0.675
-0.661
 barn-0.637
NPR-0.631
Token to
Token ID284
Feature activation+1.68e+00

Pos logit contributions
Appearances+0.974
interstitial+0.955
+0.941
 barn+0.921
NPR+0.907
Neg logit contributions
zos-1.184
oint-1.072
kus-1.024
ghazi-0.997
wra-0.996
Token best
Token ID1266
Feature activation+2.33e+00

Pos logit contributions
zos+0.497
oint+0.452
kus+0.431
wra+0.422
ghazi+0.420
Neg logit contributions
Appearances-0.382
interstitial-0.377
-0.370
 barn-0.358
NPR-0.354
Token exploration
Token ID13936
Feature activation+5.10e-01

Pos logit contributions
zos+2.050
oint+1.855
kus+1.771
wra+1.739
ghazi+1.718
Neg logit contributions
Appearances-1.636
interstitial-1.612
-1.589
 barn-1.522
NPR-1.516
Token game
Token ID983
Feature activation+3.02e+00

Pos logit contributions
zos+0.444
oint+0.402
kus+0.383
wra+0.374
ghazi+0.373
Neg logit contributions
Appearances-0.362
interstitial-0.358
-0.351
 barn-0.341
NPR-0.337
Token I
Token ID314
Feature activation-2.07e-01

Pos logit contributions
zos+2.398
oint+2.148
kus+2.040
wra+1.994
ghazi+1.967
Neg logit contributions
Appearances-2.361
interstitial-2.353
-2.315
 barn-2.217
NPR-2.210
Token
Token ID447
Feature activation-6.87e-01

Pos logit contributions
Appearances+0.127
interstitial+0.125
+0.122
 barn+0.119
NPR+0.116
Neg logit contributions
zos-0.200
oint-0.184
kus-0.175
wra-0.172
ghazi-0.172
Token
Token ID247
Feature activation+3.10e-01

Pos logit contributions
Appearances+0.479
interstitial+0.474
+0.460
 barn+0.450
NPR+0.444
Neg logit contributions
zos-0.610
oint-0.550
kus-0.525
wra-0.513
ghazi-0.512
Tokenve
Token ID303
Feature activation-7.22e-01

Pos logit contributions
zos+0.282
oint+0.256
kus+0.245
wra+0.240
ghazi+0.238
Neg logit contributions
Appearances-0.208
interstitial-0.205
-0.201
 barn-0.195
NPR-0.193
Token played
Token ID2826
Feature activation+1.37e+00

Pos logit contributions
Appearances+0.518
interstitial+0.507
+0.502
 barn+0.493
NPR+0.481
Neg logit contributions
zos-0.620
oint-0.562
kus-0.532
ghazi-0.522
wra-0.521
Token.
Token ID13
Feature activation+7.12e-01

Pos logit contributions
zos+1.203
oint+1.091
kus+1.040
wra+1.017
ghazi+1.012
Neg logit contributions
Appearances-0.958
interstitial-0.948
-0.929
 barn-0.898
NPR-0.890
Token It
Token ID632
Feature activation+1.38e+00

Pos logit contributions
zos+0.659
oint+0.601
kus+0.574
wra+0.562
ghazi+0.559
Neg logit contributions
Appearances-0.467
interstitial-0.462
-0.452
 barn-0.438
NPR-0.432
Token
Token ID447
Feature activation+1.65e+00

Pos logit contributions
zos+1.347
oint+1.236
kus+1.186
wra+1.164
ghazi+1.155
Neg logit contributions
Appearances-0.836
interstitial-0.825
-0.805
 barn-0.775
NPR-0.766
Token different
Token ID1180
Feature activation-3.44e-01

Pos logit contributions
zos+2.847
oint+2.577
kus+2.489
wra+2.406
ghazi+2.370
Neg logit contributions
interstitial-2.311
Appearances-2.310
-2.276
NPR-2.165
 barn-2.157
Token and
Token ID290
Feature activation+9.66e-01

Pos logit contributions
Appearances+0.252
interstitial+0.249
+0.244
 barn+0.239
NPR+0.235
Neg logit contributions
zos-0.292
oint-0.263
kus-0.250
wra-0.244
ghazi-0.244
Token with
Token ID351
Feature activation+1.62e+00

Pos logit contributions
zos+0.873
oint+0.795
kus+0.760
wra+0.741
ghazi+0.737
Neg logit contributions
Appearances-0.654
interstitial-0.646
-0.636
 barn-0.611
NPR-0.605
Token Dick
Token ID11740
Feature activation-2.03e+00

Pos logit contributions
zos+1.425
oint+1.293
kus+1.232
wra+1.204
ghazi+1.196
Neg logit contributions
Appearances-1.140
interstitial-1.128
-1.109
 barn-1.066
NPR-1.060
Token Grayson
Token ID42657
Feature activation-4.76e+00

Pos logit contributions
Appearances+1.254
interstitial+1.237
+1.212
 barn+1.183
NPR+1.158
Neg logit contributions
zos-1.936
oint-1.773
kus-1.693
wra-1.657
ghazi-1.655
Token that
Token ID326
Feature activation-2.31e+00

Pos logit contributions
Appearances+3.304
interstitial+3.250
 barn+3.199
+3.185
 Emmy+3.120
Neg logit contributions
zos-4.095
oint-3.720
kus-3.521
ghazi-3.443
wra-3.442
Token's
Token ID338
Feature activation-5.07e-02

Pos logit contributions
Appearances+1.496
interstitial+1.469
+1.438
 barn+1.423
 Emmy+1.385
Neg logit contributions
zos-2.140
oint-1.937
kus-1.855
ghazi-1.820
wra-1.817
Token just
Token ID655
Feature activation+2.19e+00

Pos logit contributions
Appearances+0.034
interstitial+0.033
+0.033
 barn+0.032
NPR+0.031
Neg logit contributions
zos-0.046
oint-0.042
kus-0.040
wra-0.039
ghazi-0.039
Token a
Token ID257
Feature activation+2.70e+00

Pos logit contributions
zos+1.948
oint+1.777
kus+1.696
wra+1.656
ghazi+1.637
Neg logit contributions
Appearances-1.502
interstitial-1.491
-1.469
NPR-1.394
 barn-1.387
Token perfect
Token ID2818
Feature activation-7.91e-01

Pos logit contributions
zos+2.347
oint+2.150
kus+2.059
wra+1.994
ghazi+1.978
Neg logit contributions
Appearances-1.903
interstitial-1.896
-1.852
NPR-1.771
 barn-1.707
Token mix
Token ID5022
Feature activation+2.21e+00

Pos logit contributions
Appearances+0.512
interstitial+0.505
+0.495
 barn+0.479
NPR+0.473
Neg logit contributions
zos-0.739
oint-0.674
kus-0.645
wra-0.631
ghazi-0.628
TokenApp
Token ID4677
Feature activation+4.20e+00

Pos logit contributions
zos+2.276
oint+2.077
kus+1.972
wra+1.947
ghazi+1.918
Neg logit contributions
Appearances-1.776
interstitial-1.762
-1.734
 barn-1.671
NPR-1.641
Tokenro
Token ID305
Feature activation+9.33e-01

Pos logit contributions
zos+2.974
oint+2.731
kus+2.472
wra+2.453
ghazi+2.404
Neg logit contributions
interstitial-3.642
Appearances-3.625
-3.558
 barn-3.445
NPR-3.417
Tokenved
Token ID1079
Feature activation+7.37e-01

Pos logit contributions
zos+0.763
oint+0.687
kus+0.653
wra+0.637
ghazi+0.632
Neg logit contributions
Appearances-0.713
interstitial-0.705
-0.694
 barn-0.674
NPR-0.667
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
zos+0.664
oint+0.605
kus+0.577
wra+0.566
ghazi+0.562
Neg logit contributions
Appearances-0.501
interstitial-0.495
-0.484
 barn-0.468
NPR-0.463
Token
Token ID198
Feature activation-1.96e+00

Pos logit contributions
Appearances+0.088
interstitial+0.083
+0.083
 barn+0.081
NPR+0.081
Neg logit contributions
zos-0.127
oint-0.115
kus-0.111
ghazi-0.109
wra-0.108
TokenAuthor
Token ID13838
Feature activation-3.80e+00

Pos logit contributions
Appearances+1.312
interstitial+1.273
+1.248
NPR+1.218
 barn+1.197
Neg logit contributions
zos-1.804
oint-1.632
kus-1.564
ghazi-1.521
wra-1.516
Token Notes
Token ID11822
Feature activation-5.39e-01

Pos logit contributions
Appearances+2.499
+2.406
interstitial+2.379
 barn+2.358
 Emmy+2.315
Neg logit contributions
zos-3.513
oint-3.164
kus-3.041
ghazi-2.972
wra-2.952
Token:
Token ID25
Feature activation-2.41e+00

Pos logit contributions
Appearances+0.354
interstitial+0.348
+0.342
 barn+0.332
NPR+0.327
Neg logit contributions
zos-0.499
oint-0.454
kus-0.434
wra-0.424
ghazi-0.423
Token This
Token ID770
Feature activation-1.67e+00

Pos logit contributions
Appearances+1.596
interstitial+1.558
+1.543
 barn+1.507
NPR+1.485
Neg logit contributions
zos-2.210
oint-2.003
kus-1.913
ghazi-1.869
wra-1.860
Token could
Token ID714
Feature activation+2.31e+00

Pos logit contributions
Appearances+1.141
interstitial+1.123
+1.107
 barn+1.081
NPR+1.061
Neg logit contributions
zos-1.507
oint-1.364
kus-1.301
wra-1.269
ghazi-1.269
Token go
Token ID467
Feature activation+4.20e-01

Pos logit contributions
zos+1.965
oint+1.788
kus+1.710
wra+1.657
ghazi+1.646
Neg logit contributions
Appearances-1.686
interstitial-1.674
-1.638
 barn-1.562
NPR-1.555
Token issues
Token ID2428
Feature activation-2.45e+00

Pos logit contributions
Appearances+0.566
interstitial+0.558
+0.547
 barn+0.537
NPR+0.526
Neg logit contributions
zos-0.683
oint-0.616
kus-0.587
wra-0.573
ghazi-0.573
Token that
Token ID326
Feature activation-2.27e-01

Pos logit contributions
Appearances+1.577
interstitial+1.542
+1.514
 barn+1.476
NPR+1.456
Neg logit contributions
zos-2.305
oint-2.102
kus-2.011
ghazi-1.965
wra-1.964
Token dw
Token ID43756
Feature activation+4.53e+00

Pos logit contributions
Appearances+0.145
interstitial+0.143
+0.140
 barn+0.135
NPR+0.134
Neg logit contributions
zos-0.214
oint-0.196
kus-0.187
wra-0.183
ghazi-0.182
Tokenelt
Token ID2120
Feature activation+4.28e+00

Pos logit contributions
zos+3.423
oint+3.103
kus+2.932
wra+2.833
estine+2.812
Neg logit contributions
Appearances-3.705
interstitial-3.664
-3.611
 barn-3.478
NPR-3.462
Token un
Token ID555
Feature activation+3.29e+00

Pos logit contributions
zos+3.879
oint+3.527
kus+3.380
wra+3.329
ghazi+3.279
Neg logit contributions
interstitial-2.861
Appearances-2.823
-2.718
 barn-2.627
NPR-2.604
Tokenspoken
Token ID19842
Feature activation-7.95e-01

Pos logit contributions
zos+2.831
oint+2.561
wra+2.465
kus+2.446
ghazi+2.370
Neg logit contributions
Appearances-2.350
-2.318
interstitial-2.308
 barn-2.202
NPR-2.155
Token at
Token ID379
Feature activation-2.03e+00

Pos logit contributions
Appearances+0.496
interstitial+0.488
+0.478
 barn+0.464
NPR+0.457
Neg logit contributions
zos-0.761
oint-0.696
kus-0.667
wra-0.651
ghazi-0.650
Token the
Token ID262
Feature activation-4.31e-01

Pos logit contributions
Appearances+1.367
interstitial+1.337
+1.314
 barn+1.287
NPR+1.262
Neg logit contributions
zos-1.846
oint-1.681
kus-1.603
wra-1.571
ghazi-1.566
Token heart
Token ID2612
Feature activation+6.39e-01

Pos logit contributions
Appearances+0.303
interstitial+0.299
+0.294
 barn+0.285
NPR+0.281
Neg logit contributions
zos-0.379
oint-0.344
kus-0.328
wra-0.320
ghazi-0.319
Token of
Token ID286
Feature activation+4.01e-02

Pos logit contributions
zos+0.581
oint+0.529
kus+0.505
wra+0.495
ghazi+0.492
Neg logit contributions
Appearances-0.428
interstitial-0.423
-0.415
 barn-0.401
NPR-0.396
Token Lovecraft
Token ID37655
Feature activation+1.93e+00

Pos logit contributions
zos+0.036
oint+0.033
kus+0.032
wra+0.031
ghazi+0.031
Neg logit contributions
Appearances-0.027
interstitial-0.027
-0.026
 barn-0.025
NPR-0.025
Token,
Token ID11
Feature activation+1.01e+00

Pos logit contributions
zos+2.588
oint+2.367
kus+2.254
wra+2.203
ghazi+2.175
Neg logit contributions
Appearances-2.012
interstitial-2.006
-1.939
NPR-1.847
 barn-1.836
Token Patricia
Token ID30223
Feature activation+3.34e+00

Pos logit contributions
zos+0.890
oint+0.811
kus+0.771
wra+0.756
ghazi+0.750
Neg logit contributions
Appearances-0.697
interstitial-0.692
-0.678
 barn-0.650
NPR-0.647
Token M
Token ID337
Feature activation-2.45e+00

Pos logit contributions
zos+3.119
oint+2.851
kus+2.721
wra+2.665
ghazi+2.649
Neg logit contributions
Appearances-2.158
interstitial-2.151
-2.091
 barn-2.004
NPR-1.997
Token.
Token ID13
Feature activation-7.03e-01

Pos logit contributions
Appearances+1.938
interstitial+1.925
+1.885
 barn+1.863
NPR+1.830
Neg logit contributions
zos-1.889
oint-1.670
kus-1.595
wra-1.555
ghazi-1.547
Token Lap
Token ID26944
Feature activation+2.86e+00

Pos logit contributions
Appearances+0.449
interstitial+0.441
+0.434
 barn+0.420
NPR+0.414
Neg logit contributions
zos-0.661
oint-0.604
kus-0.577
wra-0.565
ghazi-0.563
Tokeneral
Token ID1691
Feature activation-9.21e-01

Pos logit contributions
zos+2.058
oint+1.858
kus+1.745
wra+1.670
ghazi+1.654
Neg logit contributions
Appearances-2.481
interstitial-2.439
-2.419
 barn-2.339
NPR-2.322
Token of
Token ID286
Feature activation+2.87e+00

Pos logit contributions
Appearances+0.732
interstitial+0.722
+0.712
 barn+0.697
NPR+0.687
Neg logit contributions
zos-0.713
oint-0.642
kus-0.604
wra-0.591
ghazi-0.591
Token Behavioral
Token ID38483
Feature activation+4.04e+00

Pos logit contributions
zos+2.544
oint+2.325
kus+2.211
wra+2.159
ghazi+2.133
Neg logit contributions
Appearances-1.979
interstitial-1.950
-1.918
NPR-1.834
 barn-1.833
Token Dynamics
Token ID33806
Feature activation+1.47e-01

Pos logit contributions
zos+3.414
oint+3.087
kus+2.945
wra+2.859
ghazi+2.857
Neg logit contributions
Appearances-2.961
interstitial-2.953
-2.876
 barn-2.766
NPR-2.755
Token,
Token ID11
Feature activation+3.76e+00

Pos logit contributions
zos+0.123
oint+0.110
kus+0.104
wra+0.103
ghazi+0.103
Neg logit contributions
Appearances-0.109
interstitial-0.107
-0.106
 barn-0.104
NPR-0.102
Token said
Token ID531
Feature activation-1.73e+00

Pos logit contributions
zos+3.437
oint+3.151
kus+3.009
wra+2.955
ghazi+2.888
Neg logit contributions
interstitial-2.477
Appearances-2.471
-2.390
NPR-2.280
 barn-2.268
Token the
Token ID262
Feature activation+3.03e-01

Pos logit contributions
Appearances+0.232
interstitial+0.229
+0.224
 barn+0.217
NPR+0.214
Neg logit contributions
zos-0.363
oint-0.332
kus-0.318
wra-0.311
ghazi-0.310
Token public
Token ID1171
Feature activation-3.97e+00

Pos logit contributions
zos+0.266
oint+0.242
kus+0.230
wra+0.225
ghazi+0.224
Neg logit contributions
Appearances-0.213
interstitial-0.210
-0.207
 barn-0.200
NPR-0.197
Token.
Token ID13
Feature activation+9.34e-04

Pos logit contributions
Appearances+2.884
interstitial+2.823
+2.791
 barn+2.785
NPR+2.710
Neg logit contributions
zos-3.352
oint-2.978
kus-2.857
wra-2.778
ghazi-2.769
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
zos+0.001
oint+0.001
kus+0.001
wra+0.001
ghazi+0.001
Neg logit contributions
Appearances-0.001
interstitial-0.001
-0.001
 barn-0.001
NPR-0.001
Token
Token ID198
Feature activation-5.76e-01

Pos logit contributions
Appearances+0.207
interstitial+0.197
+0.196
NPR+0.193
 barn+0.192
Neg logit contributions
zos-0.299
oint-0.271
kus-0.260
wra-0.255
ghazi-0.255
TokenOb
Token ID5944
Feature activation-3.86e-01

Pos logit contributions
Appearances+0.391
interstitial+0.376
+0.372
NPR+0.364
 barn+0.358
Neg logit contributions
zos-0.526
oint-0.479
kus-0.458
wra-0.446
ghazi-0.444
Tokenamacare
Token ID11724
Feature activation-1.38e+00

Pos logit contributions
Appearances+0.345
interstitial+0.342
+0.337
 barn+0.330
NPR+0.327
Neg logit contributions
zos-0.262
oint-0.230
kus-0.215
wra-0.209
ghazi-0.207
Token,
Token ID11
Feature activation+2.74e+00

Pos logit contributions
Appearances+0.839
interstitial+0.821
+0.806
 barn+0.785
NPR+0.769
Neg logit contributions
zos-1.352
oint-1.235
kus-1.184
wra-1.159
ghazi-1.154
Token or
Token ID393
Feature activation+5.19e-02

Pos logit contributions
zos+2.402
oint+2.186
kus+2.073
wra+2.047
ghazi+2.035
Neg logit contributions
interstitial-1.914
Appearances-1.908
-1.863
NPR-1.754
 barn-1.750
Token the
Token ID262
Feature activation+1.45e+00

Pos logit contributions
zos+0.047
oint+0.043
kus+0.041
wra+0.040
ghazi+0.040
Neg logit contributions
Appearances-0.035
interstitial-0.035
-0.034
 barn-0.033
NPR-0.033
Token Affordable
Token ID19258
Feature activation+2.08e+00

Pos logit contributions
zos+1.339
oint+1.223
kus+1.166
wra+1.141
ghazi+1.138
Neg logit contributions
Appearances-0.953
interstitial-0.942
-0.925
NPR-0.876
 barn-0.872
Token.
Token ID13
Feature activation-5.17e-01

Pos logit contributions
Appearances+0.583
interstitial+0.574
+0.563
 barn+0.552
NPR+0.542
Neg logit contributions
zos-0.683
oint-0.615
kus-0.585
ghazi-0.571
wra-0.570
Token
Token ID198
Feature activation-8.96e-01

Pos logit contributions
Appearances+0.335
interstitial+0.329
+0.324
 barn+0.313
NPR+0.309
Neg logit contributions
zos-0.484
oint-0.441
kus-0.422
wra-0.412
ghazi-0.411
Token
Token ID198
Feature activation-1.14e+00

Pos logit contributions
Appearances+0.567
interstitial+0.533
+0.531
 barn+0.526
NPR+0.526
Neg logit contributions
zos-0.854
oint-0.772
kus-0.743
ghazi-0.733
wra-0.728
Token#
Token ID2
Feature activation-3.09e+00

Pos logit contributions
Appearances+0.782
interstitial+0.755
+0.744
NPR+0.724
 barn+0.716
Neg logit contributions
zos-1.042
oint-0.945
kus-0.900
ghazi-0.879
wra-0.876
Token40
Token ID1821
Feature activation-1.64e+00

Pos logit contributions
Appearances+2.148
interstitial+2.096
+2.066
 barn+2.012
NPR+2.004
Neg logit contributions
zos-2.729
oint-2.469
kus-2.370
ghazi-2.306
wra-2.293
Token Sub
Token ID3834
Feature activation-7.10e+00

Pos logit contributions
Appearances+1.074
interstitial+1.052
+1.040
 barn+1.005
NPR+0.991
Neg logit contributions
zos-1.519
oint-1.382
kus-1.319
wra-1.289
ghazi-1.287
Tokenscript
Token ID12048
Feature activation-8.52e+00

Pos logit contributions
Appearances+5.117
interstitial+4.986
+4.970
 barn+4.889
NPR+4.714
Neg logit contributions
zos-5.831
oint-5.220
kus-4.981
ghazi-4.917
wra-4.735
Tokenions
Token ID507
Feature activation-1.27e+00

Pos logit contributions
Appearances+4.915
+4.666
interstitial+4.652
 barn+4.587
 Emmy+4.477
Neg logit contributions
zos-8.275
oint-7.451
kus-7.296
ghazi-7.209
utsche-6.993
Token
Token ID198
Feature activation+5.21e-01

Pos logit contributions
Appearances+0.851
interstitial+0.838
+0.823
 barn+0.798
NPR+0.787
Neg logit contributions
zos-1.161
oint-1.056
kus-1.009
wra-0.985
ghazi-0.984
Token
Token ID198
Feature activation-1.03e+00

Pos logit contributions
zos+0.484
oint+0.438
kus+0.421
ghazi+0.412
wra+0.411
Neg logit contributions
Appearances-0.343
interstitial-0.330
-0.326
 barn-0.320
NPR-0.317
TokenNo
Token ID2949
Feature activation+2.38e+00

Pos logit contributions
Appearances+0.689
interstitial+0.671
+0.659
NPR+0.638
 barn+0.633
Neg logit contributions
zos-0.950
oint-0.863
kus-0.824
ghazi-0.804
wra-0.803
Token probably
Token ID2192
Feature activation-6.85e-01

Pos logit contributions
zos+0.352
oint+0.319
kus+0.304
wra+0.297
ghazi+0.295
Neg logit contributions
Appearances-0.293
interstitial-0.290
-0.285
 barn-0.275
NPR-0.272
Token not
Token ID407
Feature activation+1.96e+00

Pos logit contributions
Appearances+0.472
interstitial+0.466
+0.457
 barn+0.445
NPR+0.439
Neg logit contributions
zos-0.610
oint-0.554
kus-0.528
wra-0.516
ghazi-0.515
Token sensible
Token ID20586
Feature activation-5.55e-01

Pos logit contributions
zos+1.709
oint+1.560
kus+1.486
wra+1.446
ghazi+1.439
Neg logit contributions
Appearances-1.385
interstitial-1.373
-1.348
 barn-1.277
NPR-1.277
Token to
Token ID284
Feature activation+1.79e-01

Pos logit contributions
Appearances+0.394
interstitial+0.388
+0.381
 barn+0.372
NPR+0.367
Neg logit contributions
zos-0.484
oint-0.438
kus-0.418
wra-0.408
ghazi-0.406
Token get
Token ID651
Feature activation-3.92e+00

Pos logit contributions
zos+0.160
oint+0.145
kus+0.139
wra+0.136
ghazi+0.135
Neg logit contributions
Appearances-0.123
interstitial-0.121
-0.119
 barn-0.116
NPR-0.114
Token too
Token ID1165
Feature activation-6.94e+00

Pos logit contributions
Appearances+2.452
interstitial+2.434
+2.368
 barn+2.355
NPR+2.301
Neg logit contributions
zos-3.674
oint-3.348
kus-3.234
ghazi-3.165
wra-3.152
Token worked
Token ID3111
Feature activation-2.63e+00

Pos logit contributions
Appearances+4.149
 barn+4.094
interstitial+4.068
+4.028
 Emmy+3.966
Neg logit contributions
zos-6.511
oint-5.959
kus-5.751
ghazi-5.662
wra-5.609
Token up
Token ID510
Feature activation+1.84e+00

Pos logit contributions
Appearances+1.703
interstitial+1.673
+1.643
 barn+1.605
NPR+1.571
Neg logit contributions
zos-2.452
oint-2.235
kus-2.130
wra-2.084
ghazi-2.082
Token about
Token ID546
Feature activation+1.70e+00

Pos logit contributions
zos+1.728
oint+1.585
kus+1.509
wra+1.485
ghazi+1.477
Neg logit contributions
Appearances-1.177
interstitial-1.167
-1.142
 barn-1.085
NPR-1.078
Token the
Token ID262
Feature activation+2.56e+00

Pos logit contributions
zos+1.561
oint+1.428
kus+1.357
wra+1.328
ghazi+1.323
Neg logit contributions
Appearances-1.125
interstitial-1.110
-1.091
 barn-1.041
NPR-1.034
Token details
Token ID3307
Feature activation+6.14e-01

Pos logit contributions
zos+2.287
oint+2.093
kus+1.989
wra+1.937
ghazi+1.929
Neg logit contributions
Appearances-1.754
interstitial-1.738
-1.698
NPR-1.607
 barn-1.600
Token
Token ID198
Feature activation-3.19e+00

Pos logit contributions
Appearances+1.753
NPR+1.624
 barn+1.605
+1.579
 Emmy+1.577
Neg logit contributions
zos-2.970
oint-2.668
kus-2.589
ghazi-2.571
wra-2.541
TokenOther
Token ID6395
Feature activation+3.53e+00

Pos logit contributions
Appearances+2.165
interstitial+2.066
+2.006
NPR+1.982
 barn+1.912
Neg logit contributions
zos-2.937
oint-2.653
kus-2.544
ghazi-2.479
wra-2.467
Token animals
Token ID4695
Feature activation-5.86e+00

Pos logit contributions
zos+3.008
oint+2.750
kus+2.604
wra+2.536
ghazi+2.513
Neg logit contributions
Appearances-2.516
interstitial-2.514
-2.455
 barn-2.355
NPR-2.350
Token [
Token ID685
Feature activation-4.36e+00

Pos logit contributions
Appearances+3.579
interstitial+3.475
 barn+3.435
+3.360
 Emmy+3.312
Neg logit contributions
zos-5.557
oint-5.019
kus-4.865
wra-4.784
ghazi-4.745
Token edit
Token ID4370
Feature activation-2.31e+00

Pos logit contributions
Appearances+2.270
 barn+2.045
NPR+2.037
interstitial+2.022
+1.954
Neg logit contributions
zos-4.552
oint-4.171
kus-4.008
ghazi-3.983
utsche-3.950
Token ]
Token ID2361
Feature activation-7.44e+00

Pos logit contributions
Appearances+1.154
+1.063
 barn+1.056
interstitial+1.056
NPR+1.042
Neg logit contributions
zos-2.484
oint-2.295
kus-2.206
wra-2.171
ghazi-2.171
Token
Token ID198
Feature activation-5.20e+00

Pos logit contributions
Appearances+4.474
interstitial+4.177
+4.130
 barn+4.106
 Emmy+3.983
Neg logit contributions
zos-7.110
oint-6.476
kus-6.270
ghazi-6.077
wra-6.057
Token
Token ID198
Feature activation-4.90e+00

Pos logit contributions
Appearances+2.809
NPR+2.583
 barn+2.565
 Emmy+2.524
+2.409
Neg logit contributions
zos-5.323
oint-4.770
ghazi-4.650
kus-4.633
utsche-4.613
TokenWild
Token ID25946
Feature activation-1.09e+00

Pos logit contributions
Appearances+3.326
interstitial+3.142
NPR+3.021
+3.006
 barn+2.908
Neg logit contributions
zos-4.495
oint-4.067
kus-3.880
ghazi-3.795
wra-3.781
Token nine
Token ID5193
Feature activation-3.17e+00

Pos logit contributions
Appearances+0.685
interstitial+0.672
+0.658
 barn+0.644
NPR+0.628
Neg logit contributions
zos-1.040
oint-0.951
kus-0.908
wra-0.891
ghazi-0.886
Token-
Token ID12
Feature activation-3.93e+00

Pos logit contributions
Appearances+2.307
interstitial+2.283
+2.231
 barn+2.202
NPR+2.152
Neg logit contributions
zos-2.694
oint-2.426
kus-2.307
ghazi-2.250
wra-2.249
Token and
Token ID290
Feature activation+1.70e-01

Pos logit contributions
Appearances+1.206
interstitial+1.189
+1.167
 barn+1.129
NPR+1.114
Neg logit contributions
zos-1.625
oint-1.480
kus-1.412
wra-1.382
ghazi-1.375
Token it
Token ID340
Feature activation-1.07e+00

Pos logit contributions
zos+0.155
oint+0.141
kus+0.135
wra+0.132
ghazi+0.131
Neg logit contributions
Appearances-0.114
interstitial-0.112
-0.110
 barn-0.106
NPR-0.105
Token will
Token ID481
Feature activation-2.02e-01

Pos logit contributions
Appearances+0.695
interstitial+0.684
+0.674
 barn+0.655
NPR+0.643
Neg logit contributions
zos-0.991
oint-0.902
kus-0.863
wra-0.843
ghazi-0.842
Token turn
Token ID1210
Feature activation-2.70e+00

Pos logit contributions
Appearances+0.137
interstitial+0.135
+0.133
 barn+0.128
NPR+0.127
Neg logit contributions
zos-0.182
oint-0.166
kus-0.158
wra-0.155
ghazi-0.154
Token a
Token ID257
Feature activation-2.69e+00

Pos logit contributions
Appearances+1.655
interstitial+1.628
 barn+1.587
+1.585
NPR+1.526
Neg logit contributions
zos-2.610
oint-2.370
kus-2.280
ghazi-2.230
wra-2.215
Token spotlight
Token ID17838
Feature activation-7.80e+00

Pos logit contributions
Appearances+1.705
interstitial+1.672
 barn+1.657
+1.642
 Emmy+1.581
Neg logit contributions
zos-2.536
oint-2.286
kus-2.192
wra-2.146
ghazi-2.144
Token on
Token ID319
Feature activation-1.03e+00

Pos logit contributions
Appearances+4.121
 barn+4.030
+3.935
interstitial+3.897
NPR+3.885
Neg logit contributions
zos-7.857
oint-7.184
kus-6.928
ghazi-6.786
estine-6.722
Token the
Token ID262
Feature activation+3.50e-02

Pos logit contributions
Appearances+0.702
interstitial+0.694
+0.677
 barn+0.667
NPR+0.651
Neg logit contributions
zos-0.933
oint-0.846
kus-0.811
ghazi-0.790
wra-0.788
Token pivotal
Token ID28992
Feature activation-8.99e-01

Pos logit contributions
zos+0.031
oint+0.028
kus+0.027
wra+0.026
ghazi+0.026
Neg logit contributions
Appearances-0.025
interstitial-0.024
-0.024
 barn-0.023
NPR-0.023
Token role
Token ID2597
Feature activation-2.20e+00

Pos logit contributions
Appearances+0.666
interstitial+0.656
+0.643
 barn+0.630
NPR+0.620
Neg logit contributions
zos-0.758
oint-0.683
kus-0.651
wra-0.634
ghazi-0.633
Token that
Token ID326
Feature activation-3.90e+00

Pos logit contributions
Appearances+1.518
interstitial+1.499
+1.469
 barn+1.437
NPR+1.409
Neg logit contributions
zos-1.957
oint-1.779
kus-1.696
wra-1.655
ghazi-1.651
Token arm
Token ID3211
Feature activation+1.69e+00

Pos logit contributions
Appearances+1.993
interstitial+1.985
+1.925
 barn+1.916
NPR+1.863
Neg logit contributions
zos-2.761
oint-2.499
kus-2.399
ghazi-2.361
wra-2.340
Token-
Token ID12
Feature activation+6.18e-01

Pos logit contributions
zos+1.395
oint+1.255
kus+1.191
wra+1.165
ghazi+1.155
Neg logit contributions
Appearances-1.282
interstitial-1.266
-1.246
 barn-1.208
NPR-1.194
Tokenmounted
Token ID29728
Feature activation-8.63e-01

Pos logit contributions
zos+0.457
oint+0.407
kus+0.382
wra+0.376
ghazi+0.369
Neg logit contributions
Appearances-0.521
interstitial-0.514
-0.511
 barn-0.496
NPR-0.488
Token Alpha
Token ID12995
Feature activation-2.08e+00

Pos logit contributions
Appearances+0.570
interstitial+0.561
+0.545
 barn+0.541
NPR+0.529
Neg logit contributions
zos-0.791
oint-0.718
kus-0.691
ghazi-0.677
wra-0.673
Token Part
Token ID2142
Feature activation-3.33e+00

Pos logit contributions
Appearances+1.319
interstitial+1.308
+1.258
 barn+1.256
NPR+1.242
Neg logit contributions
zos-1.950
oint-1.784
kus-1.708
wra-1.675
ghazi-1.666
Tokenicle
Token ID1548
Feature activation-6.89e+00

Pos logit contributions
Appearances+2.026
interstitial+1.943
+1.898
 barn+1.879
 Emmy+1.830
Neg logit contributions
zos-3.238
oint-2.926
kus-2.804
wra-2.755
ghazi-2.754
Token X
Token ID1395
Feature activation-5.55e+00

Pos logit contributions
interstitial+3.077
Appearances+3.064
 Emmy+2.909
+2.902
 barn+2.875
Neg logit contributions
zos-7.438
oint-6.867
kus-6.783
ghazi-6.710
estine-6.670
Token-
Token ID12
Feature activation-4.86e+00

Pos logit contributions
Appearances+3.666
interstitial+3.663
 barn+3.494
+3.466
NPR+3.442
Neg logit contributions
zos-4.921
oint-4.452
ghazi-4.318
kus-4.259
estine-4.165
TokenRay
Token ID19591
Feature activation-3.84e+00

Pos logit contributions
Appearances+3.278
interstitial+3.242
NPR+3.063
+3.039
 barn+3.035
Neg logit contributions
zos-4.373
oint-3.952
kus-3.795
ghazi-3.763
estine-3.719
Token Spect
Token ID13058
Feature activation-2.84e+00

Pos logit contributions
Appearances+1.634
interstitial+1.620
+1.551
 barn+1.510
NPR+1.463
Neg logit contributions
zos-4.374
oint-4.059
kus-3.927
ghazi-3.872
wra-3.861
Tokenrom
Token ID398
Feature activation-3.15e-01

Pos logit contributions
Appearances+1.831
interstitial+1.823
+1.763
 barn+1.758
NPR+1.751
Neg logit contributions
zos-2.524
oint-2.283
kus-2.215
ghazi-2.190
wra-2.159