TOP ACTIVATIONS
MAX = 0.723

able version <|endoftext|> Rob C estern ino hosts a jam packed
ou ria : The Saga [/ b ][/ color ] -
bind =" phone . name "> span > < p ng
the whore house <|endoftext|> Steven Gerrard scored his 100 th
pointer . pub fn null () -> Atomic < T >
and Hillary Clinton Hillary Diane Rodham Clinton Sanders : ' I
of a new mood of cens orious political correctness sweeping university
B ionic Commando Rear med [/ b ][/ color ] -
][ b ] Mega Pony [/ b ][/ color ] -
tour overall focused on G WAR s search for
b ] Est imate : [/ b ] 1 : 20
and Hillary Clinton Hillary Diane Rodham Clinton Sanders : ' I
+ " \ S + "] ' ) AS library ,
make sure that the retailer orders twice as many for the
images ( args [" images "] ): # load the image
his infection . Thomas Eric Duncan succumbed to his illness 11
b ] Est imate : [/ b ] 00 : 40
The press office and Vice President Mike Pence cited the Sessions
. 18 36 pattern for the two - cent
moved closer to the be aver for a photo , it

MIN ACTIVATIONS
MIN = -0.735

vs . Hust lers TBA TBA The Complete Thirty - Six
me later . Rated 5 out of 5 by
Hide Caption 5 of 15 Photos : Carly Fiorina 's political
Territory and the Northern Territory ).[ 184 ] The House of
р у ь я м и
had it might get quite warm . Got it
+ { ( 10 s )} K b 7 { (
Hide Caption 8 of 15 Photos : Carly Fiorina 's political
on Facebook @ https :// www . facebook . com /
mates , V Ps See Gallery Donald Trump passes on '
Hide Caption 7 of 15 Photos : Carly Fiorina 's political
7 { ( 3 s )} 52 . Q xf 7
. For the Yog ventures Kickstarter backers the physical
Roman F lynn pic . twitter . com / gy d
и м и р у
7 { ( 490 s )} 51 . N d 4
Hide Caption 9 of 15 Photos : Carly Fiorina 's political
Hide Caption 6 of 15 Photos : Carly Fiorina 's political
3 { ( 1 s )} Q xf 7 { (
s tongue , lips , jaw and l aryn x .

INTERVAL 0.358 - 0.723
CONTAINS 0.149%

This little speaker is a landmark of a convention - sh
Book - M unch kins - J ill Nick all ini
, Science and Related Ag encies subcommittee of the Senate Appropriations
smaller than adequate for larger prints . This makes for easy
is done at the subt ape level . Don

INTERVAL -0.006 - 0.358
CONTAINS 52.033%

and against the capital . There must be a special mention
the Russian - Uk rain ian border , says the underlying
, he said without hesitation . I
to deliver positive messages to teammates , opponents , coaches ,
About . D ance quietly ; do

INTERVAL -0.371 - -0.006
CONTAINS 47.692%

refresh rate and fast response time TN Film panel . This
United States Basketball Writers Association ( USB WA ).[ 119 ]
few weeks before her film wraps ( I [
9 - hour Turkey - backed offensive . AFP has more
on the island of K ail o beside the old town

INTERVAL -0.735 - -0.371
CONTAINS 0.126%

turn is positioned against the UTC , even while their local
6 { ( 4 s )} 60 . e 7 {
stress even just his first warm - up pitches as a
approved the ill - con ceived hostage rescue mission that ended
said , according to the Telegraph . <|endoftext|> AN AL YS
Tokenable
Token ID540
Feature activation+3.21e-01

Pos logit contributions
osity+0.008
*,+0.008
 Converted+0.007
®,+0.007
riend+0.007
Neg logit contributions
anmar-0.010
ngth-0.009
enhagen-0.009
romeda-0.009
agra-0.008
Token version
Token ID2196
Feature activation+1.48e-01

Pos logit contributions
osity+0.704
 Converted+0.657
*,+0.652
 REPL+0.615
®,+0.609
Neg logit contributions
anmar-1.385
ngth-1.268
enhagen-1.255
romeda-1.230
agra-1.191
Token<|endoftext|>
Token ID50256
Feature activation+3.74e-02

Pos logit contributions
osity+0.379
 Converted+0.365
*,+0.363
®,+0.353
 REPL+0.344
Neg logit contributions
anmar-0.566
ngth-0.522
enhagen-0.511
romeda-0.493
kefeller-0.490
TokenRob
Token ID14350
Feature activation+3.57e-01

Pos logit contributions
osity+0.098
 Converted+0.090
*,+0.089
xa+0.086
®,+0.085
Neg logit contributions
anmar-0.146
ngth-0.134
enhagen-0.134
romeda-0.132
merce-0.126
Token C
Token ID327
Feature activation+1.21e-02

Pos logit contributions
osity+1.047
 Converted+0.942
*,+0.933
®,+0.902
xa+0.892
Neg logit contributions
anmar-1.284
ngth-1.172
romeda-1.161
enhagen-1.137
agra-1.102
Tokenestern
Token ID3330
Feature activation+7.23e-01

Pos logit contributions
osity+0.034
*,+0.031
erved+0.030
®,+0.030
 Converted+0.030
Neg logit contributions
anmar-0.046
ngth-0.041
romeda-0.040
enhagen-0.039
merce-0.039
Tokenino
Token ID2879
Feature activation+4.59e-02

Pos logit contributions
osity+1.776
 Converted+1.693
*,+1.613
®,+1.568
erved+1.558
Neg logit contributions
anmar-2.894
ngth-2.648
romeda-2.589
enhagen-2.583
agra-2.519
Token hosts
Token ID11453
Feature activation+2.82e-02

Pos logit contributions
osity+0.131
*,+0.123
 Converted+0.121
®,+0.119
 REPL+0.114
Neg logit contributions
anmar-0.172
ngth-0.154
romeda-0.150
enhagen-0.148
agra-0.146
Token a
Token ID257
Feature activation+4.53e-02

Pos logit contributions
osity+0.088
 Converted+0.084
*,+0.083
®,+0.081
 REPL+0.079
Neg logit contributions
anmar-0.096
ngth-0.085
enhagen-0.084
romeda-0.083
kefeller-0.080
Token jam
Token ID16853
Feature activation-7.35e-02

Pos logit contributions
osity+0.125
 Converted+0.119
*,+0.116
 REPL+0.113
®,+0.112
Neg logit contributions
anmar-0.169
ngth-0.152
enhagen-0.150
romeda-0.149
kefeller-0.144
Token packed
Token ID11856
Feature activation-9.28e-02

Pos logit contributions
anmar+0.304
ngth+0.280
enhagen+0.272
romeda+0.269
kefeller+0.265
Neg logit contributions
osity-0.182
*,-0.167
 Converted-0.160
®,-0.153
 REPL-0.153
Tokenou
Token ID280
Feature activation+4.75e-02

Pos logit contributions
osity+0.190
*,+0.170
 Converted+0.170
xa+0.164
®,+0.164
Neg logit contributions
anmar-0.280
ngth-0.259
enhagen-0.252
romeda-0.243
agra-0.241
Tokenria
Token ID7496
Feature activation-1.03e-01

Pos logit contributions
osity+0.129
 Converted+0.123
*,+0.120
xa+0.115
®,+0.115
Neg logit contributions
anmar-0.185
ngth-0.164
romeda-0.159
enhagen-0.159
agra-0.152
Token:
Token ID25
Feature activation-3.36e-02

Pos logit contributions
anmar+0.390
ngth+0.348
enhagen+0.348
romeda+0.340
kefeller+0.328
Neg logit contributions
osity-0.292
 Converted-0.272
*,-0.270
®,-0.258
xa-0.252
Token The
Token ID383
Feature activation+3.02e-02

Pos logit contributions
anmar+0.131
ngth+0.117
enhagen+0.116
romeda+0.115
merce+0.111
Neg logit contributions
osity-0.089
 Converted-0.084
*,-0.081
xa-0.078
®,-0.077
Token Saga
Token ID19743
Feature activation-2.11e-01

Pos logit contributions
osity+0.084
 Converted+0.082
*,+0.078
®,+0.076
 REPL+0.074
Neg logit contributions
anmar-0.112
ngth-0.101
enhagen-0.101
romeda-0.097
kefeller-0.095
Token[/
Token ID13412
Feature activation+6.58e-01

Pos logit contributions
anmar+0.783
enhagen+0.693
ngth+0.690
romeda+0.683
merce+0.653
Neg logit contributions
osity-0.611
 Converted-0.571
*,-0.559
®,-0.539
xa-0.529
Tokenb
Token ID65
Feature activation+4.30e-02

Pos logit contributions
osity+1.709
 Converted+1.572
*,+1.570
xa+1.547
erved+1.472
Neg logit contributions
anmar-2.586
ngth-2.422
enhagen-2.364
romeda-2.268
merce-2.258
Token][/
Token ID44926
Feature activation+4.22e-02

Pos logit contributions
osity+0.142
 Converted+0.133
*,+0.129
erved+0.127
xa+0.127
Neg logit contributions
anmar-0.138
enhagen-0.119
ngth-0.119
romeda-0.118
agra-0.113
Tokencolor
Token ID8043
Feature activation-9.90e-03

Pos logit contributions
osity+0.071
 Converted+0.061
*,+0.059
xa+0.056
erved+0.056
Neg logit contributions
anmar-0.204
ngth-0.190
enhagen-0.189
romeda-0.186
agra-0.181
Token]
Token ID60
Feature activation+8.55e-05

Pos logit contributions
anmar+0.034
ngth+0.030
enhagen+0.030
romeda+0.030
agra+0.028
Neg logit contributions
osity-0.030
 Converted-0.028
*,-0.028
erved-0.027
xa-0.027
Token -
Token ID532
Feature activation-8.43e-02

Pos logit contributions
osity+0.000
 Converted+0.000
*,+0.000
xa+0.000
erved+0.000
Neg logit contributions
anmar-0.000
ngth-0.000
enhagen-0.000
romeda-0.000
kefeller-0.000
Tokenbind
Token ID21653
Feature activation+1.69e-01

Pos logit contributions
anmar+0.327
enhagen+0.301
ngth+0.300
romeda+0.296
kefeller+0.287
Neg logit contributions
osity-0.199
 Converted-0.178
*,-0.176
xa-0.173
erved-0.168
Token="
Token ID2625
Feature activation-1.76e-01

Pos logit contributions
osity+0.428
 Converted+0.382
*,+0.372
xa+0.359
®,+0.357
Neg logit contributions
anmar-0.670
enhagen-0.619
ngth-0.612
romeda-0.601
agra-0.587
Tokenphone
Token ID4862
Feature activation-4.89e-02

Pos logit contributions
anmar+0.679
ngth+0.619
enhagen+0.616
romeda+0.607
agra+0.585
Neg logit contributions
osity-0.467
 Converted-0.422
*,-0.421
xa-0.403
®,-0.400
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
anmar+0.171
ngth+0.157
enhagen+0.153
romeda+0.152
agra+0.147
Neg logit contributions
osity-0.148
 Converted-0.137
*,-0.134
 REPL-0.130
xa-0.129
Tokenname
Token ID3672
Feature activation+7.27e-02

Pos logit contributions
anmar+0.399
enhagen+0.360
ngth+0.360
romeda+0.358
agra+0.344
Neg logit contributions
osity-0.269
 Converted-0.241
*,-0.240
xa-0.231
erved-0.227
Token">
Token ID23984
Feature activation+6.42e-01

Pos logit contributions
osity+0.216
 Converted+0.203
*,+0.197
erved+0.189
®,+0.188
Neg logit contributions
anmar-0.258
ngth-0.234
enhagen-0.229
romeda-0.228
agra-0.220
Tokenspan
Token ID12626
Feature activation-1.16e-01

Pos logit contributions
osity+0.970
 Converted+0.793
*,+0.787
xa+0.767
erved+0.753
Neg logit contributions
anmar-3.226
ngth-3.018
enhagen-3.003
romeda-2.956
kefeller-2.869
Token>
Token ID29
Feature activation-9.32e-02

Pos logit contributions
anmar+0.462
ngth+0.425
enhagen+0.419
romeda+0.412
agra+0.399
Neg logit contributions
osity-0.295
 Converted-0.270
*,-0.266
xa-0.255
erved-0.253
Token <
Token ID1279
Feature activation-9.66e-02

Pos logit contributions
anmar+0.329
ngth+0.299
enhagen+0.292
romeda+0.290
agra+0.279
Neg logit contributions
osity-0.279
 Converted-0.261
*,-0.251
®,-0.245
 REPL-0.244
Tokenp
Token ID79
Feature activation-2.81e-02

Pos logit contributions
anmar+0.393
ngth+0.354
enhagen+0.353
romeda+0.353
agra+0.337
Neg logit contributions
osity-0.237
 Converted-0.214
*,-0.213
erved-0.205
xa-0.204
Token ng
Token ID23370
Feature activation-1.28e-01

Pos logit contributions
anmar+0.106
ngth+0.095
enhagen+0.094
romeda+0.094
agra+0.090
Neg logit contributions
osity-0.077
 Converted-0.070
*,-0.069
erved-0.066
xa-0.066
Token the
Token ID262
Feature activation-5.14e-03

Pos logit contributions
anmar+0.089
ngth+0.082
romeda+0.080
enhagen+0.079
kefeller+0.076
Neg logit contributions
osity-0.075
*,-0.071
 Converted-0.070
®,-0.067
itor-0.067
Token whore
Token ID40107
Feature activation+3.02e-02

Pos logit contributions
anmar+0.018
ngth+0.017
romeda+0.017
enhagen+0.017
merce+0.016
Neg logit contributions
osity-0.015
 Converted-0.014
*,-0.014
xa-0.013
 REPL-0.013
Tokenhouse
Token ID4803
Feature activation-2.83e-01

Pos logit contributions
osity+0.066
*,+0.062
 Converted+0.060
xa+0.056
®,+0.055
Neg logit contributions
anmar-0.131
ngth-0.120
enhagen-0.118
romeda-0.117
kefeller-0.115
Token
Token ID1399
Feature activation-2.24e-01

Pos logit contributions
anmar+1.032
ngth+0.930
enhagen+0.923
romeda+0.914
merce+0.873
Neg logit contributions
osity-0.820
*,-0.767
 Converted-0.760
®,-0.722
xa-0.717
Token<|endoftext|>
Token ID50256
Feature activation+1.43e-02

Pos logit contributions
anmar+0.812
enhagen+0.726
ngth+0.726
romeda+0.720
kefeller+0.686
Neg logit contributions
osity-0.640
 Converted-0.596
*,-0.595
®,-0.562
xa-0.561
TokenSteven
Token ID28292
Feature activation+6.41e-01

Pos logit contributions
osity+0.038
 Converted+0.034
*,+0.034
xa+0.033
®,+0.033
Neg logit contributions
anmar-0.056
ngth-0.051
enhagen-0.051
romeda-0.050
merce-0.048
Token Gerrard
Token ID49314
Feature activation+3.87e-01

Pos logit contributions
osity+1.798
 Converted+1.675
*,+1.670
®,+1.594
erved+1.573
Neg logit contributions
anmar-2.337
ngth-2.090
romeda-2.079
enhagen-2.070
agra-2.016
Token scored
Token ID7781
Feature activation+1.19e-01

Pos logit contributions
osity+1.090
*,+1.036
 Converted+1.027
®,+0.988
 REPL+0.955
Neg logit contributions
anmar-1.451
ngth-1.296
romeda-1.269
enhagen-1.265
merce-1.222
Token his
Token ID465
Feature activation+2.17e-01

Pos logit contributions
osity+0.351
 Converted+0.328
*,+0.321
erved+0.308
®,+0.306
Neg logit contributions
anmar-0.432
ngth-0.396
enhagen-0.387
romeda-0.379
merce-0.366
Token 100
Token ID1802
Feature activation+1.95e-01

Pos logit contributions
osity+0.650
 Converted+0.608
*,+0.599
®,+0.574
erved+0.574
Neg logit contributions
anmar-0.767
ngth-0.708
enhagen-0.687
romeda-0.671
merce-0.665
Tokenth
Token ID400
Feature activation+2.85e-01

Pos logit contributions
osity+0.376
*,+0.328
 Converted+0.321
xa+0.310
erved+0.297
Neg logit contributions
anmar-0.922
ngth-0.839
enhagen-0.836
romeda-0.835
merce-0.799
Token pointer
Token ID17562
Feature activation-8.07e-02

Pos logit contributions
anmar+0.037
ngth+0.033
enhagen+0.033
romeda+0.032
merce+0.032
Neg logit contributions
osity-0.024
 Converted-0.022
*,-0.022
®,-0.020
 REPL-0.020
Token.
Token ID13
Feature activation-6.46e-02

Pos logit contributions
anmar+0.301
ngth+0.269
enhagen+0.266
romeda+0.260
merce+0.255
Neg logit contributions
osity-0.230
 Converted-0.216
*,-0.211
®,-0.202
erved-0.201
Token pub
Token ID2240
Feature activation+2.48e-01

Pos logit contributions
anmar+0.256
ngth+0.233
enhagen+0.229
romeda+0.226
merce+0.222
Neg logit contributions
osity-0.169
 Converted-0.159
*,-0.152
erved-0.145
®,-0.144
Token fn
Token ID24714
Feature activation+4.58e-01

Pos logit contributions
osity+0.419
 Converted+0.373
*,+0.360
xa+0.328
®,+0.328
Neg logit contributions
anmar-1.210
ngth-1.119
enhagen-1.109
romeda-1.092
agra-1.064
Token null
Token ID9242
Feature activation+2.60e-01

Pos logit contributions
osity+1.353
 Converted+1.290
*,+1.284
 REPL+1.206
®,+1.195
Neg logit contributions
anmar-1.636
ngth-1.506
enhagen-1.492
merce-1.408
romeda-1.404
Token ()
Token ID7499
Feature activation+6.29e-01

Pos logit contributions
osity+0.662
 Converted+0.583
*,+0.567
xa+0.566
erved+0.544
Neg logit contributions
anmar-1.052
ngth-0.958
enhagen-0.950
romeda-0.934
agra-0.913
Token ->
Token ID4613
Feature activation+8.09e-02

Pos logit contributions
osity+0.690
 Converted+0.534
*,+0.528
xa+0.468
itor+0.419
Neg logit contributions
anmar-3.440
ngth-3.243
enhagen-3.208
romeda-3.182
agra-3.110
Token Atomic
Token ID28976
Feature activation+1.79e-01

Pos logit contributions
osity+0.232
 Converted+0.221
*,+0.216
®,+0.203
xa+0.202
Neg logit contributions
anmar-0.301
ngth-0.273
enhagen-0.271
romeda-0.261
agra-0.257
Token <
Token ID1279
Feature activation+1.85e-01

Pos logit contributions
osity+0.570
 Converted+0.527
*,+0.519
xa+0.495
erved+0.492
Neg logit contributions
anmar-0.615
ngth-0.561
enhagen-0.539
romeda-0.537
agra-0.521
Token T
Token ID309
Feature activation+1.92e-01

Pos logit contributions
osity+0.634
 Converted+0.599
*,+0.599
erved+0.569
xa+0.568
Neg logit contributions
anmar-0.582
ngth-0.511
enhagen-0.509
romeda-0.502
agra-0.485
Token >
Token ID1875
Feature activation+3.14e-01

Pos logit contributions
osity+0.444
*,+0.410
 Converted+0.401
erved+0.381
xa+0.380
Neg logit contributions
anmar-0.810
ngth-0.740
enhagen-0.730
romeda-0.725
agra-0.711
Token and
Token ID290
Feature activation+2.03e-02

Pos logit contributions
anmar+0.722
ngth+0.665
romeda+0.649
enhagen+0.638
agra+0.622
Neg logit contributions
osity-0.534
*,-0.508
 Converted-0.492
®,-0.486
erved-0.455
Token Hillary
Token ID5073
Feature activation+2.39e-01

Pos logit contributions
osity+0.061
 Converted+0.056
*,+0.056
®,+0.053
xa+0.052
Neg logit contributions
anmar-0.072
ngth-0.066
enhagen-0.065
romeda-0.062
merce-0.062
Token Clinton
Token ID2605
Feature activation+7.84e-02

Pos logit contributions
osity+0.797
*,+0.750
 Converted+0.745
®,+0.722
xa+0.695
Neg logit contributions
anmar-0.755
ngth-0.685
enhagen-0.679
romeda-0.674
agra-0.636
Token Hillary
Token ID5073
Feature activation+2.06e-01

Pos logit contributions
osity+0.268
*,+0.252
 Converted+0.249
®,+0.245
 REPL+0.232
Neg logit contributions
anmar-0.246
ngth-0.226
enhagen-0.225
romeda-0.219
kefeller-0.214
Token Diane
Token ID26542
Feature activation+1.96e-01

Pos logit contributions
osity+0.539
 Converted+0.493
*,+0.479
®,+0.463
erved+0.462
Neg logit contributions
anmar-0.800
ngth-0.721
enhagen-0.717
romeda-0.708
agra-0.685
Token Rodham
Token ID41848
Feature activation+6.22e-01

Pos logit contributions
osity+0.641
 Converted+0.598
*,+0.589
®,+0.573
erved+0.566
Neg logit contributions
anmar-0.633
ngth-0.562
enhagen-0.553
romeda-0.548
agra-0.523
Token Clinton
Token ID2605
Feature activation+1.34e-01

Pos logit contributions
osity+2.115
 Converted+1.963
*,+1.959
erved+1.871
®,+1.863
Neg logit contributions
anmar-1.959
enhagen-1.765
ngth-1.751
romeda-1.728
htaking-1.593
TokenSanders
Token ID26747
Feature activation+2.69e-01

Pos logit contributions
osity+0.352
*,+0.315
 Converted+0.310
®,+0.304
 REPL+0.294
Neg logit contributions
anmar-0.537
ngth-0.494
enhagen-0.486
romeda-0.484
merce-0.460
Token:
Token ID25
Feature activation+3.95e-02

Pos logit contributions
osity+0.686
 Converted+0.619
*,+0.606
 REPL+0.589
®,+0.573
Neg logit contributions
anmar-1.079
ngth-0.985
romeda-0.969
enhagen-0.962
agra-0.928
Token '
Token ID705
Feature activation+4.25e-02

Pos logit contributions
osity+0.128
 Converted+0.120
*,+0.117
erved+0.113
®,+0.113
Neg logit contributions
anmar-0.129
ngth-0.114
enhagen-0.113
romeda-0.112
agra-0.107
TokenI
Token ID40
Feature activation+8.96e-02

Pos logit contributions
osity+0.154
 Converted+0.145
*,+0.142
erved+0.139
®,+0.138
Neg logit contributions
anmar-0.122
enhagen-0.105
ngth-0.105
romeda-0.102
agra-0.098
Token of
Token ID286
Feature activation-6.92e-02

Pos logit contributions
anmar+0.236
enhagen+0.209
ngth+0.209
romeda+0.207
agra+0.200
Neg logit contributions
osity-0.199
*,-0.187
 Converted-0.184
®,-0.177
xa-0.175
Token a
Token ID257
Feature activation-2.78e-02

Pos logit contributions
anmar+0.237
ngth+0.220
enhagen+0.213
romeda+0.209
merce+0.206
Neg logit contributions
osity-0.209
*,-0.196
 Converted-0.196
xa-0.185
®,-0.185
Token new
Token ID649
Feature activation+6.62e-02

Pos logit contributions
anmar+0.099
ngth+0.091
enhagen+0.090
romeda+0.087
merce+0.085
Neg logit contributions
osity-0.080
*,-0.075
 Converted-0.075
®,-0.071
erved-0.071
Token mood
Token ID10038
Feature activation+7.21e-02

Pos logit contributions
osity+0.176
*,+0.167
 Converted+0.162
®,+0.156
 REPL+0.154
Neg logit contributions
anmar-0.251
ngth-0.229
enhagen-0.227
romeda-0.224
merce-0.221
Token of
Token ID286
Feature activation-3.84e-02

Pos logit contributions
osity+0.215
*,+0.196
 Converted+0.195
xa+0.184
®,+0.182
Neg logit contributions
anmar-0.264
ngth-0.238
enhagen-0.234
romeda-0.225
merce-0.224
Token cens
Token ID12428
Feature activation+6.08e-01

Pos logit contributions
anmar+0.145
ngth+0.130
enhagen+0.129
romeda+0.127
merce+0.124
Neg logit contributions
osity-0.107
*,-0.097
 Converted-0.096
xa-0.093
erved-0.091
Tokenorious
Token ID9982
Feature activation-3.35e-01

Pos logit contributions
osity+1.785
*,+1.527
erved+1.511
itor+1.501
 Converted+1.485
Neg logit contributions
anmar-2.231
ngth-1.970
enhagen-1.964
romeda-1.944
merce-1.921
Token political
Token ID1964
Feature activation+8.35e-02

Pos logit contributions
anmar+1.289
ngth+1.179
enhagen+1.173
romeda+1.147
agra+1.111
Neg logit contributions
osity-0.905
*,-0.818
 Converted-0.802
®,-0.773
xa-0.769
Token correctness
Token ID29409
Feature activation+1.72e-01

Pos logit contributions
osity+0.158
*,+0.136
 Converted+0.131
 REPL+0.124
®,+0.123
Neg logit contributions
anmar-0.387
ngth-0.361
enhagen-0.358
romeda-0.354
kefeller-0.349
Token sweeping
Token ID18404
Feature activation+1.06e-01

Pos logit contributions
osity+0.484
*,+0.454
 Converted+0.449
®,+0.420
erved+0.413
Neg logit contributions
anmar-0.640
ngth-0.583
enhagen-0.577
romeda-0.559
kefeller-0.551
Token university
Token ID6403
Feature activation+4.88e-02

Pos logit contributions
osity+0.312
*,+0.304
 Converted+0.300
 REPL+0.282
erved+0.279
Neg logit contributions
anmar-0.368
ngth-0.343
enhagen-0.334
romeda-0.324
merce-0.320
TokenB
Token ID33
Feature activation-3.83e-03

Pos logit contributions
osity+0.508
 Converted+0.464
*,+0.461
xa+0.441
erved+0.434
Neg logit contributions
anmar-0.725
enhagen-0.650
ngth-0.648
romeda-0.643
merce-0.621
Tokenionic
Token ID26523
Feature activation-3.46e-02

Pos logit contributions
anmar+0.014
enhagen+0.013
ngth+0.013
romeda+0.012
merce+0.012
Neg logit contributions
osity-0.011
*,-0.010
 Converted-0.010
erved-0.009
xa-0.009
Token Commando
Token ID47150
Feature activation-6.21e-02

Pos logit contributions
anmar+0.095
ngth+0.084
enhagen+0.081
romeda+0.081
merce+0.077
Neg logit contributions
osity-0.132
*,-0.124
 Converted-0.121
xa-0.120
®,-0.118
Token Rear
Token ID30144
Feature activation-4.00e-02

Pos logit contributions
anmar+0.242
ngth+0.218
enhagen+0.214
romeda+0.212
merce+0.204
Neg logit contributions
osity-0.168
*,-0.154
 Converted-0.154
®,-0.147
xa-0.144
Tokenmed
Token ID1150
Feature activation+1.38e-01

Pos logit contributions
anmar+0.145
enhagen+0.129
ngth+0.125
romeda+0.124
kefeller+0.122
Neg logit contributions
osity-0.117
*,-0.112
 Converted-0.111
®,-0.107
xa-0.107
Token[/
Token ID13412
Feature activation+6.03e-01

Pos logit contributions
osity+0.377
 Converted+0.351
*,+0.347
®,+0.329
xa+0.328
Neg logit contributions
anmar-0.529
ngth-0.481
enhagen-0.469
romeda-0.462
merce-0.453
Tokenb
Token ID65
Feature activation+8.79e-02

Pos logit contributions
osity+1.551
 Converted+1.425
*,+1.424
xa+1.378
erved+1.345
Neg logit contributions
anmar-2.360
ngth-2.140
enhagen-2.107
romeda-2.101
kefeller-2.025
Token][/
Token ID44926
Feature activation-2.17e-02

Pos logit contributions
osity+0.272
 Converted+0.251
*,+0.249
xa+0.241
erved+0.239
Neg logit contributions
anmar-0.306
enhagen-0.263
ngth-0.262
romeda-0.262
kefeller-0.250
Tokencolor
Token ID8043
Feature activation+1.81e-02

Pos logit contributions
anmar+0.105
ngth+0.097
enhagen+0.096
romeda+0.096
agra+0.093
Neg logit contributions
osity-0.036
 Converted-0.032
*,-0.031
erved-0.029
xa-0.029
Token]
Token ID60
Feature activation+1.21e-01

Pos logit contributions
osity+0.053
 Converted+0.049
*,+0.048
erved+0.047
xa+0.046
Neg logit contributions
anmar-0.065
enhagen-0.057
ngth-0.057
romeda-0.057
kefeller-0.054
Token -
Token ID532
Feature activation+3.48e-02

Pos logit contributions
osity+0.361
 Converted+0.344
*,+0.339
 REPL+0.320
xa+0.318
Neg logit contributions
anmar-0.429
enhagen-0.373
ngth-0.373
romeda-0.368
merce-0.355
Token][
Token ID7131
Feature activation-1.21e-01

Pos logit contributions
anmar+0.414
ngth+0.375
enhagen+0.374
romeda+0.371
agra+0.356
Neg logit contributions
osity-0.221
 Converted-0.199
*,-0.196
erved-0.186
®,-0.186
Tokenb
Token ID65
Feature activation-2.42e-03

Pos logit contributions
anmar+0.457
ngth+0.420
enhagen+0.409
romeda+0.403
merce+0.393
Neg logit contributions
osity-0.336
 Converted-0.307
*,-0.307
xa-0.301
erved-0.294
Token]
Token ID60
Feature activation+4.83e-02

Pos logit contributions
anmar+0.009
ngth+0.008
enhagen+0.008
romeda+0.008
merce+0.008
Neg logit contributions
osity-0.007
 Converted-0.006
*,-0.006
xa-0.006
erved-0.006
TokenMega
Token ID43471
Feature activation+4.50e-02

Pos logit contributions
osity+0.129
 Converted+0.119
*,+0.117
xa+0.112
®,+0.111
Neg logit contributions
anmar-0.187
ngth-0.171
enhagen-0.171
romeda-0.166
merce-0.162
Token Pony
Token ID30377
Feature activation+8.43e-02

Pos logit contributions
osity+0.108
*,+0.095
 Converted+0.094
®,+0.090
xa+0.088
Neg logit contributions
anmar-0.188
enhagen-0.172
ngth-0.171
romeda-0.167
kefeller-0.165
Token[/
Token ID13412
Feature activation+6.00e-01

Pos logit contributions
osity+0.236
 Converted+0.215
*,+0.214
®,+0.208
itor+0.197
Neg logit contributions
anmar-0.327
ngth-0.287
romeda-0.284
enhagen-0.284
kefeller-0.269
Tokenb
Token ID65
Feature activation+6.85e-02

Pos logit contributions
osity+1.578
*,+1.448
 Converted+1.447
xa+1.425
erved+1.358
Neg logit contributions
anmar-2.345
ngth-2.187
enhagen-2.145
merce-2.047
romeda-2.044
Token][/
Token ID44926
Feature activation+2.92e-02

Pos logit contributions
osity+0.224
 Converted+0.211
*,+0.205
xa+0.202
erved+0.200
Neg logit contributions
anmar-0.226
ngth-0.198
enhagen-0.198
romeda-0.190
merce-0.187
Tokencolor
Token ID8043
Feature activation-1.62e-02

Pos logit contributions
osity+0.050
 Converted+0.043
*,+0.042
erved+0.039
xa+0.039
Neg logit contributions
anmar-0.141
ngth-0.131
enhagen-0.130
romeda-0.128
agra-0.124
Token]
Token ID60
Feature activation+5.28e-02

Pos logit contributions
anmar+0.061
ngth+0.055
enhagen+0.054
romeda+0.052
merce+0.052
Neg logit contributions
osity-0.046
 Converted-0.043
*,-0.042
xa-0.041
erved-0.041
Token -
Token ID532
Feature activation+2.11e-03

Pos logit contributions
osity+0.112
 Converted+0.101
*,+0.097
erved+0.092
xa+0.092
Neg logit contributions
anmar-0.232
ngth-0.211
enhagen-0.210
romeda-0.208
agra-0.201
Token tour
Token ID4205
Feature activation+4.71e-02

Pos logit contributions
anmar+0.039
ngth+0.035
enhagen+0.034
romeda+0.034
kefeller+0.033
Neg logit contributions
osity-0.033
 Converted-0.030
*,-0.030
®,-0.029
 REPL-0.028
Token overall
Token ID4045
Feature activation-1.62e-02

Pos logit contributions
osity+0.128
*,+0.119
 Converted+0.114
®,+0.113
xa+0.111
Neg logit contributions
anmar-0.178
ngth-0.162
enhagen-0.160
romeda-0.158
merce-0.155
Token focused
Token ID5670
Feature activation-5.37e-02

Pos logit contributions
anmar+0.062
ngth+0.056
enhagen+0.055
romeda+0.055
kefeller+0.054
Neg logit contributions
osity-0.044
*,-0.041
 Converted-0.040
®,-0.038
erved-0.038
Token on
Token ID319
Feature activation+5.00e-02

Pos logit contributions
anmar+0.186
enhagen+0.168
romeda+0.167
ngth+0.167
merce+0.159
Neg logit contributions
osity-0.161
*,-0.148
 Converted-0.148
erved-0.140
®,-0.140
Token G
Token ID402
Feature activation+3.16e-01

Pos logit contributions
osity+0.152
 Converted+0.141
*,+0.141
®,+0.135
erved+0.134
Neg logit contributions
anmar-0.171
ngth-0.154
enhagen-0.151
romeda-0.149
kefeller-0.148
TokenWAR
Token ID16279
Feature activation+5.98e-01

Pos logit contributions
osity+0.555
*,+0.467
 Converted+0.458
®,+0.445
xa+0.438
Neg logit contributions
anmar-1.483
ngth-1.371
enhagen-1.370
romeda-1.352
agra-1.309
Token
Token ID447
Feature activation+4.79e-02

Pos logit contributions
osity+1.626
*,+1.548
®,+1.487
 Converted+1.479
xa+1.393
Neg logit contributions
anmar-2.226
ngth-2.024
enhagen-1.972
romeda-1.968
agra-1.926
Token
Token ID247
Feature activation+6.72e-02

Pos logit contributions
osity+0.142
*,+0.132
 Converted+0.131
®,+0.127
erved+0.125
Neg logit contributions
anmar-0.170
enhagen-0.151
ngth-0.150
romeda-0.149
agra-0.143
Tokens
Token ID82
Feature activation-3.78e-02

Pos logit contributions
osity+0.187
*,+0.171
 Converted+0.169
®,+0.165
erved+0.162
Neg logit contributions
anmar-0.252
enhagen-0.225
romeda-0.224
ngth-0.224
kefeller-0.217
Token search
Token ID2989
Feature activation-7.35e-02

Pos logit contributions
anmar+0.136
ngth+0.123
enhagen+0.122
romeda+0.121
kefeller+0.117
Neg logit contributions
osity-0.109
*,-0.101
 Converted-0.101
®,-0.097
erved-0.095
Token for
Token ID329
Feature activation-7.69e-02

Pos logit contributions
anmar+0.255
ngth+0.231
romeda+0.230
enhagen+0.226
kefeller+0.223
Neg logit contributions
osity-0.225
*,-0.209
 Converted-0.200
®,-0.196
xa-0.194
Tokenb
Token ID65
Feature activation+1.05e-02

Pos logit contributions
anmar+0.763
romeda+0.694
ngth+0.694
enhagen+0.694
agra+0.668
Neg logit contributions
osity-0.355
 Converted-0.313
*,-0.307
xa-0.293
erved-0.289
Token]
Token ID60
Feature activation+6.97e-02

Pos logit contributions
osity+0.030
 Converted+0.027
*,+0.027
erved+0.026
xa+0.026
Neg logit contributions
anmar-0.039
enhagen-0.035
ngth-0.034
romeda-0.034
agra-0.033
TokenEst
Token ID22362
Feature activation+5.92e-02

Pos logit contributions
osity+0.182
 Converted+0.168
*,+0.166
xa+0.158
®,+0.157
Neg logit contributions
anmar-0.275
ngth-0.250
enhagen-0.248
romeda-0.241
merce-0.236
Tokenimate
Token ID1920
Feature activation-8.15e-02

Pos logit contributions
osity+0.168
 Converted+0.156
*,+0.153
erved+0.148
xa+0.147
Neg logit contributions
anmar-0.217
ngth-0.197
enhagen-0.195
romeda-0.186
kefeller-0.185
Token:
Token ID25
Feature activation+5.07e-02

Pos logit contributions
anmar+0.314
ngth+0.277
romeda+0.277
enhagen+0.274
merce+0.264
Neg logit contributions
osity-0.227
 Converted-0.210
*,-0.207
erved-0.195
®,-0.195
Token[/
Token ID13412
Feature activation+5.88e-01

Pos logit contributions
osity+0.140
 Converted+0.132
*,+0.129
erved+0.121
®,+0.121
Neg logit contributions
anmar-0.193
ngth-0.172
enhagen-0.171
romeda-0.168
merce-0.165
Tokenb
Token ID65
Feature activation+8.17e-02

Pos logit contributions
osity+1.529
 Converted+1.403
*,+1.401
xa+1.375
erved+1.317
Neg logit contributions
anmar-2.298
ngth-2.138
enhagen-2.067
romeda-2.046
kefeller-2.004
Token]
Token ID60
Feature activation+1.50e-01

Pos logit contributions
osity+0.253
 Converted+0.235
*,+0.230
xa+0.223
erved+0.223
Neg logit contributions
anmar-0.281
romeda-0.243
ngth-0.243
enhagen-0.243
agra-0.232
Token 1
Token ID352
Feature activation+1.76e-02

Pos logit contributions
osity+0.426
 Converted+0.400
*,+0.392
erved+0.366
®,+0.365
Neg logit contributions
anmar-0.562
ngth-0.494
romeda-0.489
enhagen-0.489
merce-0.477
Token:
Token ID25
Feature activation-6.50e-02

Pos logit contributions
osity+0.050
*,+0.046
 Converted+0.046
xa+0.044
erved+0.043
Neg logit contributions
anmar-0.065
ngth-0.059
enhagen-0.058
romeda-0.057
merce-0.056
Token20
Token ID1238
Feature activation-5.77e-02

Pos logit contributions
anmar+0.248
ngth+0.223
enhagen+0.222
romeda+0.215
merce+0.213
Neg logit contributions
osity-0.179
 Converted-0.170
*,-0.166
xa-0.157
erved-0.156
Token and
Token ID290
Feature activation+1.29e-01

Pos logit contributions
anmar+0.306
ngth+0.277
romeda+0.275
enhagen+0.273
agra+0.263
Neg logit contributions
osity-0.220
 Converted-0.202
*,-0.201
®,-0.193
xa-0.186
Token Hillary
Token ID5073
Feature activation+1.88e-01

Pos logit contributions
osity+0.402
*,+0.381
 Converted+0.378
®,+0.357
 REPL+0.354
Neg logit contributions
anmar-0.437
ngth-0.401
enhagen-0.395
merce-0.371
romeda-0.367
Token Clinton
Token ID2605
Feature activation-1.25e-02

Pos logit contributions
osity+0.633
 Converted+0.603
*,+0.597
®,+0.568
erved+0.560
Neg logit contributions
anmar-0.601
ngth-0.546
enhagen-0.536
romeda-0.520
agra-0.501
Token Hillary
Token ID5073
Feature activation+1.38e-01

Pos logit contributions
anmar+0.041
ngth+0.038
enhagen+0.038
kefeller+0.036
romeda+0.036
Neg logit contributions
osity-0.041
*,-0.039
 Converted-0.038
®,-0.037
 REPL-0.035
Token Diane
Token ID26542
Feature activation+1.77e-01

Pos logit contributions
osity+0.361
 Converted+0.330
*,+0.320
®,+0.310
erved+0.310
Neg logit contributions
anmar-0.537
ngth-0.484
enhagen-0.482
romeda-0.475
agra-0.460
Token Rodham
Token ID41848
Feature activation+5.86e-01

Pos logit contributions
osity+0.567
 Converted+0.530
*,+0.521
®,+0.506
erved+0.500
Neg logit contributions
anmar-0.588
ngth-0.525
enhagen-0.515
romeda-0.512
agra-0.490
Token Clinton
Token ID2605
Feature activation+4.72e-02

Pos logit contributions
osity+1.984
 Converted+1.842
*,+1.839
erved+1.764
®,+1.748
Neg logit contributions
anmar-1.846
enhagen-1.659
ngth-1.639
romeda-1.624
htaking-1.496
TokenSanders
Token ID26747
Feature activation+1.85e-01

Pos logit contributions
osity+0.124
*,+0.111
 Converted+0.109
®,+0.107
xa+0.103
Neg logit contributions
anmar-0.187
ngth-0.172
enhagen-0.170
romeda-0.169
merce-0.160
Token:
Token ID25
Feature activation+6.35e-02

Pos logit contributions
osity+0.478
 Converted+0.430
*,+0.423
 REPL+0.411
®,+0.398
Neg logit contributions
anmar-0.739
ngth-0.671
romeda-0.664
enhagen-0.659
agra-0.635
Token '
Token ID705
Feature activation+6.39e-02

Pos logit contributions
osity+0.204
 Converted+0.192
*,+0.186
erved+0.181
®,+0.181
Neg logit contributions
anmar-0.208
ngth-0.185
enhagen-0.184
romeda-0.182
agra-0.174
TokenI
Token ID40
Feature activation+1.05e-01

Pos logit contributions
osity+0.231
 Converted+0.217
*,+0.213
erved+0.208
®,+0.208
Neg logit contributions
anmar-0.184
ngth-0.158
enhagen-0.158
romeda-0.155
agra-0.148
Token+
Token ID10
Feature activation+1.22e-01

Pos logit contributions
osity+0.200
*,+0.184
 Converted+0.166
xa+0.157
®,+0.153
Neg logit contributions
anmar-0.772
enhagen-0.705
ngth-0.703
romeda-0.698
kefeller-0.681
Token"
Token ID1
Feature activation+1.80e-01

Pos logit contributions
osity+0.256
*,+0.241
 Converted+0.230
xa+0.222
®,+0.219
Neg logit contributions
anmar-0.545
ngth-0.489
enhagen-0.487
romeda-0.486
kefeller-0.472
Token\
Token ID59
Feature activation+1.94e-01

Pos logit contributions
osity+0.408
*,+0.380
 Converted+0.371
®,+0.354
xa+0.351
Neg logit contributions
anmar-0.773
enhagen-0.691
ngth-0.689
romeda-0.684
agra-0.658
TokenS
Token ID50
Feature activation+9.22e-02

Pos logit contributions
osity+0.519
*,+0.488
xa+0.470
 Converted+0.470
®,+0.457
Neg logit contributions
anmar-0.774
ngth-0.681
enhagen-0.678
romeda-0.672
kefeller-0.643
Token+
Token ID10
Feature activation+1.30e-01

Pos logit contributions
osity+0.166
*,+0.152
 Converted+0.145
xa+0.137
®,+0.136
Neg logit contributions
anmar-0.441
enhagen-0.402
ngth-0.399
romeda-0.395
merce-0.384
Token"]
Token ID8973
Feature activation+5.76e-01

Pos logit contributions
osity+0.300
*,+0.280
 Converted+0.272
xa+0.262
®,+0.259
Neg logit contributions
anmar-0.554
ngth-0.497
enhagen-0.496
romeda-0.493
kefeller-0.474
Token'
Token ID6
Feature activation+1.77e-01

Pos logit contributions
osity+1.143
*,+1.088
 Converted+1.034
®,+0.973
xa+0.971
Neg logit contributions
anmar-2.631
ngth-2.363
enhagen-2.361
romeda-2.344
merce-2.261
Token )
Token ID1267
Feature activation+4.65e-02

Pos logit contributions
osity+0.307
*,+0.263
 Converted+0.263
 REPL+0.245
®,+0.245
Neg logit contributions
anmar-0.858
ngth-0.783
enhagen-0.775
romeda-0.771
agra-0.750
Token AS
Token ID7054
Feature activation-3.40e-02

Pos logit contributions
osity+0.122
*,+0.112
 Converted+0.112
 REPL+0.107
®,+0.107
Neg logit contributions
anmar-0.184
ngth-0.165
enhagen-0.162
romeda-0.161
agra-0.155
Token library
Token ID5888
Feature activation+1.15e-01

Pos logit contributions
anmar+0.132
ngth+0.117
enhagen+0.117
romeda+0.115
agra+0.112
Neg logit contributions
osity-0.091
 Converted-0.084
*,-0.084
 REPL-0.082
®,-0.080
Token,
Token ID837
Feature activation-5.42e-02

Pos logit contributions
osity+0.316
 Converted+0.289
*,+0.288
 REPL+0.281
®,+0.277
Neg logit contributions
anmar-0.444
ngth-0.390
romeda-0.387
enhagen-0.387
agra-0.373
Token make
Token ID787
Feature activation+9.06e-02

Pos logit contributions
osity+0.093
*,+0.087
 Converted+0.086
®,+0.084
 REPL+0.084
Neg logit contributions
anmar-0.095
ngth-0.085
enhagen-0.085
romeda-0.081
agra-0.079
Token sure
Token ID1654
Feature activation+1.57e-01

Pos logit contributions
osity+0.251
 Converted+0.230
*,+0.226
®,+0.219
xa+0.216
Neg logit contributions
anmar-0.339
ngth-0.311
enhagen-0.308
romeda-0.296
kefeller-0.290
Token that
Token ID326
Feature activation+1.71e-02

Pos logit contributions
osity+0.455
*,+0.417
 Converted+0.413
®,+0.401
xa+0.394
Neg logit contributions
anmar-0.570
ngth-0.520
enhagen-0.511
romeda-0.489
kefeller-0.484
Token the
Token ID262
Feature activation-4.70e-03

Pos logit contributions
osity+0.052
*,+0.047
 Converted+0.047
®,+0.046
xa+0.045
Neg logit contributions
anmar-0.061
ngth-0.055
enhagen-0.054
romeda-0.052
kefeller-0.051
Token retailer
Token ID21538
Feature activation+8.63e-02

Pos logit contributions
anmar+0.017
ngth+0.016
enhagen+0.015
romeda+0.015
merce+0.015
Neg logit contributions
osity-0.014
 Converted-0.012
*,-0.012
®,-0.012
erved-0.012
Token orders
Token ID6266
Feature activation+5.59e-01

Pos logit contributions
osity+0.253
*,+0.235
 Converted+0.232
®,+0.225
xa+0.220
Neg logit contributions
anmar-0.315
ngth-0.285
enhagen-0.279
romeda-0.270
kefeller-0.265
Token twice
Token ID5403
Feature activation-1.24e-01

Pos logit contributions
osity+1.788
*,+1.683
 Converted+1.679
®,+1.635
xa+1.586
Neg logit contributions
anmar-1.819
ngth-1.657
enhagen-1.627
romeda-1.543
kefeller-1.530
Token as
Token ID355
Feature activation+7.45e-03

Pos logit contributions
anmar+0.478
ngth+0.432
enhagen+0.428
romeda+0.415
kefeller+0.408
Neg logit contributions
osity-0.339
*,-0.313
 Converted-0.311
®,-0.297
erved-0.295
Token many
Token ID867
Feature activation-1.43e-03

Pos logit contributions
osity+0.021
 Converted+0.019
*,+0.019
®,+0.018
erved+0.018
Neg logit contributions
anmar-0.028
ngth-0.025
enhagen-0.025
romeda-0.024
kefeller-0.024
Token for
Token ID329
Feature activation+8.49e-02

Pos logit contributions
anmar+0.007
ngth+0.006
enhagen+0.006
romeda+0.006
agra+0.006
Neg logit contributions
osity-0.003
 Converted-0.002
*,-0.002
®,-0.002
erved-0.002
Token the
Token ID262
Feature activation-2.99e-02

Pos logit contributions
osity+0.259
 Converted+0.235
*,+0.232
®,+0.226
erved+0.225
Neg logit contributions
anmar-0.298
ngth-0.271
enhagen-0.268
romeda-0.257
merce-0.250
Tokenimages
Token ID17566
Feature activation+1.48e-01

Pos logit contributions
osity+0.207
 Converted+0.182
*,+0.181
xa+0.175
erved+0.173
Neg logit contributions
anmar-0.393
ngth-0.364
enhagen-0.359
romeda-0.352
merce-0.341
Token(
Token ID7
Feature activation-4.14e-03

Pos logit contributions
osity+0.364
 Converted+0.333
*,+0.330
xa+0.313
®,+0.313
Neg logit contributions
anmar-0.614
ngth-0.561
enhagen-0.554
romeda-0.541
merce-0.533
Tokenargs
Token ID22046
Feature activation-2.85e-02

Pos logit contributions
anmar+0.016
ngth+0.014
enhagen+0.014
romeda+0.014
merce+0.014
Neg logit contributions
osity-0.011
 Converted-0.010
*,-0.010
xa-0.010
erved-0.010
Token["
Token ID14692
Feature activation+2.69e-01

Pos logit contributions
anmar+0.140
ngth+0.130
enhagen+0.129
romeda+0.127
agra+0.124
Neg logit contributions
osity-0.045
 Converted-0.039
*,-0.038
erved-0.036
®,-0.036
Tokenimages
Token ID17566
Feature activation+1.14e-01

Pos logit contributions
osity+0.598
*,+0.523
 Converted+0.516
xa+0.503
erved+0.497
Neg logit contributions
anmar-1.161
ngth-1.075
enhagen-1.068
romeda-1.039
merce-1.012
Token"]
Token ID8973
Feature activation+5.56e-01

Pos logit contributions
osity+0.429
 Converted+0.405
*,+0.403
erved+0.394
xa+0.389
Neg logit contributions
anmar-0.316
ngth-0.279
enhagen-0.272
romeda-0.258
merce-0.252
Token):
Token ID2599
Feature activation-7.07e-03

Pos logit contributions
osity+1.333
 Converted+1.238
*,+1.228
xa+1.172
erved+1.151
Neg logit contributions
anmar-2.328
ngth-2.137
enhagen-2.118
merce-2.048
romeda-2.040
Token #
Token ID1303
Feature activation+1.06e-01

Pos logit contributions
anmar+0.020
ngth+0.018
enhagen+0.017
romeda+0.016
kefeller+0.016
Neg logit contributions
osity-0.027
 Converted-0.025
*,-0.025
 REPL-0.024
xa-0.024
Token load
Token ID3440
Feature activation+2.06e-01

Pos logit contributions
osity+0.252
*,+0.224
 Converted+0.219
 REPL+0.210
xa+0.208
Neg logit contributions
anmar-0.454
enhagen-0.415
ngth-0.409
romeda-0.404
kefeller-0.390
Token the
Token ID262
Feature activation+1.65e-01

Pos logit contributions
osity+0.722
 Converted+0.689
*,+0.685
erved+0.657
xa+0.656
Neg logit contributions
anmar-0.641
ngth-0.578
enhagen-0.556
romeda-0.534
merce-0.532
Token image
Token ID2939
Feature activation+1.21e-01

Pos logit contributions
osity+0.533
*,+0.497
 Converted+0.496
®,+0.476
xa+0.476
Neg logit contributions
anmar-0.546
ngth-0.499
enhagen-0.486
romeda-0.464
merce-0.460
Token his
Token ID465
Feature activation+1.42e-02

Pos logit contributions
osity+0.005
 Converted+0.005
*,+0.005
 REPL+0.005
®,+0.005
Neg logit contributions
anmar-0.005
ngth-0.005
enhagen-0.005
romeda-0.005
agra-0.005
Token infection
Token ID10280
Feature activation+2.83e-01

Pos logit contributions
osity+0.039
*,+0.036
 Converted+0.035
 REPL+0.034
®,+0.034
Neg logit contributions
anmar-0.053
ngth-0.050
enhagen-0.048
romeda-0.048
merce-0.047
Token.
Token ID13
Feature activation+6.18e-02

Pos logit contributions
osity+0.778
*,+0.746
 Converted+0.720
®,+0.684
xa+0.676
Neg logit contributions
anmar-1.058
ngth-0.975
enhagen-0.945
romeda-0.932
merce-0.912
Token Thomas
Token ID5658
Feature activation+1.69e-01

Pos logit contributions
osity+0.168
 Converted+0.165
*,+0.159
®,+0.152
 REPL+0.152
Neg logit contributions
anmar-0.238
ngth-0.217
enhagen-0.215
merce-0.210
romeda-0.205
Token Eric
Token ID7651
Feature activation+2.12e-01

Pos logit contributions
osity+0.498
*,+0.477
 Converted+0.467
®,+0.446
erved+0.446
Neg logit contributions
anmar-0.606
ngth-0.540
enhagen-0.537
romeda-0.520
merce-0.515
Token Duncan
Token ID18625
Feature activation+5.56e-01

Pos logit contributions
osity+0.576
 Converted+0.542
*,+0.532
xa+0.512
 REPL+0.508
Neg logit contributions
anmar-0.814
ngth-0.742
enhagen-0.732
romeda-0.712
agra-0.701
Token succumbed
Token ID47290
Feature activation+2.57e-02

Pos logit contributions
*,+1.421
osity+1.404
 Converted+1.343
®,+1.304
erved+1.243
Neg logit contributions
anmar-2.196
ngth-2.017
enhagen-1.943
romeda-1.923
agra-1.872
Token to
Token ID284
Feature activation+1.45e-02

Pos logit contributions
osity+0.077
 Converted+0.072
*,+0.072
erved+0.069
®,+0.068
Neg logit contributions
anmar-0.089
ngth-0.080
enhagen-0.079
romeda-0.079
agra-0.074
Token his
Token ID465
Feature activation+7.82e-02

Pos logit contributions
osity+0.041
 Converted+0.039
*,+0.039
 REPL+0.038
®,+0.037
Neg logit contributions
anmar-0.052
ngth-0.048
enhagen-0.047
romeda-0.046
merce-0.044
Token illness
Token ID8526
Feature activation+1.16e-01

Pos logit contributions
osity+0.221
 Converted+0.203
*,+0.203
 REPL+0.197
®,+0.193
Neg logit contributions
anmar-0.286
ngth-0.263
enhagen-0.260
romeda-0.253
merce-0.249
Token 11
Token ID1367
Feature activation+1.77e-01

Pos logit contributions
osity+0.331
*,+0.318
 Converted+0.311
®,+0.295
erved+0.292
Neg logit contributions
anmar-0.415
ngth-0.383
enhagen-0.376
romeda-0.365
merce-0.354
Tokenb
Token ID65
Feature activation-3.96e-02

Pos logit contributions
anmar+0.405
ngth+0.361
enhagen+0.358
romeda+0.355
agra+0.342
Neg logit contributions
osity-0.329
 Converted-0.303
*,-0.298
xa-0.289
erved-0.287
Token]
Token ID60
Feature activation+1.43e-02

Pos logit contributions
anmar+0.146
ngth+0.132
enhagen+0.130
romeda+0.125
merce+0.123
Neg logit contributions
osity-0.116
 Converted-0.107
*,-0.105
xa-0.103
erved-0.102
TokenEst
Token ID22362
Feature activation+2.49e-02

Pos logit contributions
osity+0.032
 Converted+0.030
*,+0.029
xa+0.027
erved+0.027
Neg logit contributions
anmar-0.061
ngth-0.056
enhagen-0.056
romeda-0.055
merce-0.054
Tokenimate
Token ID1920
Feature activation-1.02e-01

Pos logit contributions
osity+0.073
 Converted+0.067
*,+0.066
erved+0.065
xa+0.064
Neg logit contributions
anmar-0.090
ngth-0.082
enhagen-0.080
romeda-0.078
merce-0.076
Token:
Token ID25
Feature activation+1.42e-02

Pos logit contributions
anmar+0.355
ngth+0.316
enhagen+0.312
romeda+0.304
merce+0.297
Neg logit contributions
osity-0.318
 Converted-0.299
*,-0.292
xa-0.281
erved-0.280
Token[/
Token ID13412
Feature activation+5.51e-01

Pos logit contributions
osity+0.038
 Converted+0.036
*,+0.035
®,+0.033
xa+0.033
Neg logit contributions
anmar-0.056
ngth-0.050
enhagen-0.050
romeda-0.049
merce-0.048
Tokenb
Token ID65
Feature activation+2.33e-02

Pos logit contributions
osity+1.462
 Converted+1.342
*,+1.341
xa+1.316
erved+1.264
Neg logit contributions
anmar-2.139
ngth-1.991
enhagen-1.946
romeda-1.874
merce-1.861
Token]
Token ID60
Feature activation+8.30e-02

Pos logit contributions
osity+0.068
 Converted+0.063
*,+0.062
xa+0.060
erved+0.060
Neg logit contributions
anmar-0.086
ngth-0.077
enhagen-0.076
romeda-0.074
merce-0.073
Token 00
Token ID3571
Feature activation-1.30e-01

Pos logit contributions
osity+0.251
 Converted+0.245
*,+0.237
xa+0.225
 REPL+0.224
Neg logit contributions
anmar-0.293
ngth-0.263
enhagen-0.257
merce-0.251
romeda-0.247
Token:
Token ID25
Feature activation-4.31e-02

Pos logit contributions
anmar+0.464
ngth+0.418
enhagen+0.411
romeda+0.400
merce+0.393
Neg logit contributions
osity-0.396
 Converted-0.372
*,-0.366
xa-0.356
erved-0.350
Token40
Token ID1821
Feature activation-4.42e-02

Pos logit contributions
anmar+0.175
ngth+0.162
enhagen+0.159
merce+0.153
romeda+0.153
Neg logit contributions
osity-0.109
 Converted-0.102
*,-0.101
xa-0.097
erved-0.095
TokenThe
Token ID464
Feature activation+6.57e-02

Pos logit contributions
osity+0.187
*,+0.173
 Converted+0.172
xa+0.163
®,+0.161
Neg logit contributions
anmar-0.311
ngth-0.285
enhagen-0.282
romeda-0.275
merce-0.267
Token press
Token ID1803
Feature activation-2.45e-02

Pos logit contributions
osity+0.198
 Converted+0.184
*,+0.180
 REPL+0.173
xa+0.172
Neg logit contributions
anmar-0.231
ngth-0.211
enhagen-0.205
romeda-0.204
merce-0.196
Token office
Token ID2607
Feature activation+2.52e-01

Pos logit contributions
anmar+0.093
enhagen+0.082
ngth+0.081
romeda+0.080
agra+0.078
Neg logit contributions
osity-0.069
*,-0.063
 Converted-0.063
®,-0.060
 REPL-0.060
Token and
Token ID290
Feature activation+7.61e-02

Pos logit contributions
osity+0.668
*,+0.625
 Converted+0.623
 REPL+0.594
®,+0.581
Neg logit contributions
anmar-0.985
ngth-0.880
enhagen-0.870
romeda-0.857
agra-0.845
Token Vice
Token ID11079
Feature activation+4.19e-01

Pos logit contributions
osity+0.240
*,+0.227
 Converted+0.227
 REPL+0.216
erved+0.215
Neg logit contributions
anmar-0.257
ngth-0.232
enhagen-0.225
romeda-0.221
agra-0.215
Token President
Token ID1992
Feature activation+5.50e-01

Pos logit contributions
osity+1.325
 Converted+1.247
*,+1.235
®,+1.196
xa+1.178
Neg logit contributions
anmar-1.447
ngth-1.298
romeda-1.236
enhagen-1.226
agra-1.191
Token Mike
Token ID4995
Feature activation-4.66e-02

Pos logit contributions
osity+1.366
*,+1.294
 Converted+1.246
®,+1.196
 REPL+1.159
Neg logit contributions
anmar-2.272
enhagen-2.035
ngth-2.028
romeda-1.970
merce-1.926
Token Pence
Token ID17339
Feature activation+1.22e-01

Pos logit contributions
anmar+0.213
ngth+0.194
enhagen+0.193
romeda+0.192
agra+0.186
Neg logit contributions
osity-0.098
*,-0.089
 Converted-0.089
erved-0.081
 REPL-0.079
Token cited
Token ID9181
Feature activation+1.57e-01

Pos logit contributions
osity+0.313
*,+0.295
 Converted+0.291
®,+0.275
 REPL+0.274
Neg logit contributions
anmar-0.479
ngth-0.438
romeda-0.425
enhagen-0.423
agra-0.414
Token the
Token ID262
Feature activation+7.03e-02

Pos logit contributions
osity+0.499
*,+0.468
 Converted+0.467
erved+0.447
 REPL+0.439
Neg logit contributions
anmar-0.532
ngth-0.480
enhagen-0.467
romeda-0.460
agra-0.443
Token Sessions
Token ID15184
Feature activation-2.09e-02

Pos logit contributions
osity+0.204
 Converted+0.190
*,+0.186
 REPL+0.178
itor+0.177
Neg logit contributions
anmar-0.258
ngth-0.237
enhagen-0.230
romeda-0.226
merce-0.218
Token.
Token ID13
Feature activation+8.73e-02

Pos logit contributions
anmar+1.213
ngth+1.090
enhagen+1.085
romeda+1.064
agra+1.027
Neg logit contributions
osity-0.862
 Converted-0.807
*,-0.792
®,-0.755
erved-0.748
Token
Token ID198
Feature activation+1.08e-01

Pos logit contributions
osity+0.275
 Converted+0.255
*,+0.249
®,+0.243
erved+0.242
Neg logit contributions
anmar-0.292
ngth-0.257
enhagen-0.256
romeda-0.252
agra-0.243
Token
Token ID198
Feature activation+1.86e-01

Pos logit contributions
osity+0.340
 Converted+0.325
*,+0.317
xa+0.308
erved+0.302
Neg logit contributions
anmar-0.377
ngth-0.346
enhagen-0.336
romeda-0.322
merce-0.319
Token18
Token ID1507
Feature activation+1.67e-01

Pos logit contributions
osity+0.474
*,+0.432
 Converted+0.426
xa+0.417
®,+0.405
Neg logit contributions
anmar-0.747
ngth-0.696
enhagen-0.689
romeda-0.673
merce-0.644
Token36
Token ID2623
Feature activation+9.83e-02

Pos logit contributions
osity+0.450
 Converted+0.421
*,+0.407
xa+0.396
erved+0.393
Neg logit contributions
anmar-0.632
ngth-0.584
enhagen-0.578
romeda-0.566
agra-0.552
Token pattern
Token ID3912
Feature activation+5.48e-01

Pos logit contributions
osity+0.281
 Converted+0.267
*,+0.260
®,+0.249
 REPL+0.246
Neg logit contributions
anmar-0.361
ngth-0.326
enhagen-0.320
romeda-0.313
agra-0.306
Token for
Token ID329
Feature activation+3.47e-01

Pos logit contributions
osity+1.548
 Converted+1.440
*,+1.431
®,+1.374
 REPL+1.355
Neg logit contributions
anmar-2.007
ngth-1.812
enhagen-1.770
romeda-1.717
merce-1.681
Token the
Token ID262
Feature activation+1.29e-01

Pos logit contributions
osity+1.024
 Converted+0.954
*,+0.940
 REPL+0.913
erved+0.908
Neg logit contributions
anmar-1.216
ngth-1.117
enhagen-1.080
romeda-1.047
merce-1.019
Token two
Token ID734
Feature activation+1.78e-01

Pos logit contributions
osity+0.371
 Converted+0.350
*,+0.342
 REPL+0.333
®,+0.330
Neg logit contributions
anmar-0.459
ngth-0.422
enhagen-0.409
romeda-0.395
agra-0.387
Token-
Token ID12
Feature activation+3.79e-02

Pos logit contributions
osity+0.493
 Converted+0.461
*,+0.457
xa+0.435
 REPL+0.434
Neg logit contributions
anmar-0.665
ngth-0.603
enhagen-0.601
romeda-0.569
merce-0.556
Tokencent
Token ID1087
Feature activation+1.43e-01

Pos logit contributions
osity+0.106
*,+0.095
 Converted+0.094
xa+0.091
erved+0.090
Neg logit contributions
anmar-0.143
ngth-0.131
enhagen-0.129
romeda-0.127
kefeller-0.121
Token moved
Token ID3888
Feature activation+1.25e-01

Pos logit contributions
osity+0.032
*,+0.029
 Converted+0.029
®,+0.028
xa+0.028
Neg logit contributions
anmar-0.046
ngth-0.042
romeda-0.040
enhagen-0.040
agra-0.039
Token closer
Token ID5699
Feature activation+7.88e-02

Pos logit contributions
osity+0.355
*,+0.337
 Converted+0.335
®,+0.320
 REPL+0.313
Neg logit contributions
anmar-0.456
ngth-0.417
enhagen-0.400
romeda-0.400
kefeller-0.392
Token to
Token ID284
Feature activation-3.18e-02

Pos logit contributions
osity+0.224
*,+0.214
 Converted+0.204
®,+0.201
erved+0.196
Neg logit contributions
anmar-0.288
ngth-0.260
romeda-0.253
enhagen-0.249
agra-0.248
Token the
Token ID262
Feature activation+3.17e-02

Pos logit contributions
anmar+0.101
ngth+0.091
enhagen+0.088
romeda+0.087
agra+0.085
Neg logit contributions
osity-0.105
 Converted-0.100
*,-0.098
erved-0.095
®,-0.095
Token be
Token ID307
Feature activation+1.57e-01

Pos logit contributions
osity+0.094
 Converted+0.089
*,+0.087
®,+0.083
 REPL+0.083
Neg logit contributions
anmar-0.111
ngth-0.103
enhagen-0.100
romeda-0.097
merce-0.095
Tokenaver
Token ID8770
Feature activation+5.46e-01

Pos logit contributions
osity+0.346
 Converted+0.312
*,+0.301
erved+0.292
xa+0.290
Neg logit contributions
anmar-0.683
enhagen-0.622
ngth-0.619
romeda-0.610
kefeller-0.595
Token for
Token ID329
Feature activation+1.09e-01

Pos logit contributions
osity+1.508
*,+1.440
 Converted+1.381
®,+1.344
erved+1.281
Neg logit contributions
anmar-2.021
ngth-1.858
romeda-1.801
enhagen-1.758
kefeller-1.742
Token a
Token ID257
Feature activation+3.37e-02

Pos logit contributions
osity+0.335
*,+0.305
 Converted+0.301
®,+0.293
erved+0.293
Neg logit contributions
anmar-0.376
ngth-0.343
romeda-0.325
enhagen-0.324
merce-0.312
Token photo
Token ID4590
Feature activation+6.84e-03

Pos logit contributions
osity+0.094
 Converted+0.088
*,+0.088
 REPL+0.084
®,+0.083
Neg logit contributions
anmar-0.125
ngth-0.113
enhagen-0.111
romeda-0.108
agra-0.105
Token,
Token ID11
Feature activation-8.60e-02

Pos logit contributions
osity+0.020
*,+0.019
 Converted+0.018
®,+0.018
erved+0.018
Neg logit contributions
anmar-0.025
ngth-0.023
enhagen-0.022
romeda-0.021
agra-0.021
Token it
Token ID340
Feature activation+4.08e-03

Pos logit contributions
anmar+0.296
ngth+0.267
enhagen+0.260
romeda+0.256
agra+0.249
Neg logit contributions
osity-0.266
 Converted-0.248
*,-0.248
 REPL-0.234
®,-0.234
Token vs
Token ID3691
Feature activation+1.18e-01

Pos logit contributions
anmar+0.327
enhagen+0.288
ngth+0.288
romeda+0.283
agra+0.272
Neg logit contributions
osity-0.309
 Converted-0.288
*,-0.279
®,-0.273
erved-0.272
Token.
Token ID13
Feature activation-7.54e-02

Pos logit contributions
osity+0.325
 Converted+0.308
*,+0.300
 REPL+0.290
®,+0.286
Neg logit contributions
anmar-0.443
ngth-0.403
enhagen-0.399
romeda-0.389
merce-0.381
Token Hust
Token ID42941
Feature activation-8.84e-02

Pos logit contributions
anmar+0.267
ngth+0.242
enhagen+0.237
romeda+0.232
merce+0.229
Neg logit contributions
osity-0.225
 Converted-0.215
*,-0.207
 REPL-0.200
®,-0.199
Tokenlers
Token ID8116
Feature activation-5.46e-03

Pos logit contributions
anmar+0.339
ngth+0.306
romeda+0.298
enhagen+0.298
merce+0.291
Neg logit contributions
osity-0.246
 Converted-0.219
*,-0.217
xa-0.212
erved-0.211
Token TBA
Token ID48591
Feature activation-4.90e-01

Pos logit contributions
anmar+0.020
ngth+0.018
enhagen+0.018
romeda+0.017
kefeller+0.017
Neg logit contributions
osity-0.016
 Converted-0.015
*,-0.015
®,-0.014
erved-0.014
Token TBA
Token ID48591
Feature activation-6.79e-01

Pos logit contributions
anmar+1.779
ngth+1.586
enhagen+1.563
romeda+1.553
agra+1.493
Neg logit contributions
osity-1.437
 Converted-1.347
*,-1.328
®,-1.278
erved-1.261
Token The
Token ID383
Feature activation+1.43e-01

Pos logit contributions
anmar+2.422
ngth+2.156
enhagen+2.127
romeda+2.101
agra+2.022
Neg logit contributions
osity-2.026
 Converted-1.898
*,-1.857
®,-1.797
erved-1.781
Token Complete
Token ID13248
Feature activation-8.93e-02

Pos logit contributions
osity+0.417
 Converted+0.389
*,+0.374
®,+0.364
xa+0.363
Neg logit contributions
anmar-0.517
ngth-0.465
enhagen-0.454
romeda-0.454
merce-0.440
Token Thirty
Token ID29948
Feature activation+2.41e-02

Pos logit contributions
anmar+0.349
ngth+0.318
enhagen+0.311
romeda+0.307
merce+0.298
Neg logit contributions
osity-0.236
 Converted-0.224
*,-0.214
®,-0.210
 REPL-0.202
Token-
Token ID12
Feature activation-4.31e-02

Pos logit contributions
osity+0.064
 Converted+0.060
*,+0.058
®,+0.057
xa+0.056
Neg logit contributions
anmar-0.094
ngth-0.085
enhagen-0.083
romeda-0.083
merce-0.081
TokenSix
Token ID21447
Feature activation-4.44e-02

Pos logit contributions
anmar+0.190
ngth+0.175
romeda+0.171
enhagen+0.169
kefeller+0.167
Neg logit contributions
osity-0.092
 Converted-0.085
*,-0.082
®,-0.079
xa-0.077
Token me
Token ID502
Feature activation+4.79e-03

Pos logit contributions
anmar+0.572
ngth+0.509
romeda+0.499
enhagen+0.499
agra+0.483
Neg logit contributions
osity-0.417
 Converted-0.381
*,-0.371
 REPL-0.358
®,-0.358
Token later
Token ID1568
Feature activation-1.24e-01

Pos logit contributions
osity+0.013
 Converted+0.012
*,+0.012
®,+0.011
xa+0.011
Neg logit contributions
anmar-0.018
enhagen-0.016
ngth-0.016
romeda-0.016
kefeller-0.016
Token.
Token ID13
Feature activation-8.40e-02

Pos logit contributions
anmar+0.462
enhagen+0.418
ngth+0.415
romeda+0.411
kefeller+0.396
Neg logit contributions
osity-0.346
 Converted-0.314
*,-0.314
®,-0.302
xa-0.298
Token
Token ID198
Feature activation-1.78e-02

Pos logit contributions
anmar+0.312
ngth+0.276
enhagen+0.275
romeda+0.273
merce+0.262
Neg logit contributions
osity-0.239
 Converted-0.226
*,-0.220
 REPL-0.212
®,-0.209
Token
Token ID198
Feature activation-2.61e-02

Pos logit contributions
anmar+0.064
ngth+0.057
enhagen+0.056
romeda+0.055
kefeller+0.054
Neg logit contributions
osity-0.055
 Converted-0.051
*,-0.051
xa-0.049
®,-0.048
TokenRated
Token ID15322
Feature activation-6.25e-01

Pos logit contributions
anmar+0.093
enhagen+0.084
ngth+0.083
romeda+0.083
kefeller+0.079
Neg logit contributions
osity-0.079
*,-0.072
 Converted-0.071
xa-0.069
®,-0.068
Token 5
Token ID642
Feature activation+1.42e-01

Pos logit contributions
anmar+2.253
ngth+2.018
enhagen+1.998
romeda+1.950
kefeller+1.882
Neg logit contributions
osity-1.850
 Converted-1.722
*,-1.695
®,-1.636
 REPL-1.614
Token out
Token ID503
Feature activation+1.36e-01

Pos logit contributions
osity+0.427
*,+0.397
 Converted+0.397
®,+0.380
xa+0.377
Neg logit contributions
anmar-0.506
ngth-0.454
enhagen-0.444
romeda-0.431
kefeller-0.421
Token of
Token ID286
Feature activation+4.71e-02

Pos logit contributions
osity+0.403
 Converted+0.379
*,+0.375
xa+0.359
®,+0.357
Neg logit contributions
anmar-0.497
ngth-0.446
enhagen-0.441
romeda-0.425
merce-0.421
Token 5
Token ID642
Feature activation-1.51e-02

Pos logit contributions
osity+0.142
 Converted+0.131
*,+0.129
®,+0.125
erved+0.124
Neg logit contributions
anmar-0.165
ngth-0.147
enhagen-0.146
romeda-0.144
agra-0.138
Token by
Token ID416
Feature activation+1.75e-02

Pos logit contributions
anmar+0.053
ngth+0.046
enhagen+0.046
romeda+0.044
merce+0.043
Neg logit contributions
osity-0.048
 Converted-0.045
*,-0.044
®,-0.043
xa-0.042
Token Hide
Token ID10415
Feature activation-1.46e-01

Pos logit contributions
anmar+0.110
ngth+0.099
enhagen+0.096
merce+0.094
romeda+0.093
Neg logit contributions
osity-0.129
 Converted-0.126
*,-0.121
 REPL-0.117
®,-0.117
Token Caption
Token ID11260
Feature activation-3.41e-01

Pos logit contributions
anmar+0.677
ngth+0.625
enhagen+0.618
romeda+0.608
merce+0.595
Neg logit contributions
osity-0.279
 Converted-0.252
*,-0.239
erved-0.226
xa-0.224
Token 5
Token ID642
Feature activation+6.47e-02

Pos logit contributions
anmar+1.153
ngth+1.017
enhagen+1.017
romeda+1.007
agra+0.965
Neg logit contributions
osity-1.059
 Converted-0.977
*,-0.956
erved-0.930
®,-0.929
Token of
Token ID286
Feature activation+6.70e-02

Pos logit contributions
osity+0.185
 Converted+0.172
*,+0.171
xa+0.166
®,+0.161
Neg logit contributions
anmar-0.247
ngth-0.223
enhagen-0.221
romeda-0.214
merce-0.214
Token 15
Token ID1315
Feature activation-4.22e-02

Pos logit contributions
osity+0.197
 Converted+0.185
*,+0.182
erved+0.175
®,+0.175
Neg logit contributions
anmar-0.242
ngth-0.218
enhagen-0.215
romeda-0.208
merce-0.205
Token Photos
Token ID9434
Feature activation-6.23e-01

Pos logit contributions
anmar+0.177
ngth+0.162
enhagen+0.160
romeda+0.155
merce+0.154
Neg logit contributions
osity-0.101
 Converted-0.095
*,-0.091
xa-0.088
®,-0.087
Token:
Token ID25
Feature activation-9.60e-02

Pos logit contributions
anmar+1.950
ngth+1.703
enhagen+1.698
romeda+1.676
agra+1.604
Neg logit contributions
osity-2.089
 Converted-1.948
*,-1.907
®,-1.860
erved-1.859
Token Carly
Token ID35982
Feature activation-2.34e-01

Pos logit contributions
anmar+0.306
ngth+0.272
enhagen+0.268
merce+0.257
romeda+0.256
Neg logit contributions
osity-0.324
 Converted-0.311
*,-0.301
®,-0.294
xa-0.290
Token Fiorina
Token ID49028
Feature activation-2.03e-01

Pos logit contributions
anmar+0.586
ngth+0.495
enhagen+0.489
romeda+0.480
agra+0.452
Neg logit contributions
osity-0.940
 Converted-0.888
*,-0.872
®,-0.854
erved-0.852
Token's
Token ID338
Feature activation+2.29e-02

Pos logit contributions
anmar+0.745
ngth+0.669
enhagen+0.655
romeda+0.652
merce+0.625
Neg logit contributions
osity-0.582
 Converted-0.544
*,-0.532
®,-0.513
xa-0.508
Token political
Token ID1964
Feature activation+1.66e-01

Pos logit contributions
osity+0.066
 Converted+0.062
*,+0.061
®,+0.059
erved+0.058
Neg logit contributions
anmar-0.082
ngth-0.077
enhagen-0.076
romeda-0.073
merce-0.070
Token Territory
Token ID25219
Feature activation-2.22e-02

Pos logit contributions
anmar+1.014
enhagen+0.907
ngth+0.906
romeda+0.893
agra+0.872
Neg logit contributions
osity-0.929
*,-0.870
 Converted-0.867
®,-0.835
erved-0.817
Token and
Token ID290
Feature activation-6.14e-02

Pos logit contributions
anmar+0.083
ngth+0.075
enhagen+0.074
romeda+0.073
agra+0.071
Neg logit contributions
osity-0.061
*,-0.058
 Converted-0.057
®,-0.055
xa-0.054
Token the
Token ID262
Feature activation-8.80e-02

Pos logit contributions
anmar+0.202
ngth+0.186
enhagen+0.183
romeda+0.173
kefeller+0.171
Neg logit contributions
osity-0.193
 Converted-0.188
*,-0.184
®,-0.178
 REPL-0.176
Token Northern
Token ID8342
Feature activation-1.21e-01

Pos logit contributions
anmar+0.302
ngth+0.283
enhagen+0.276
romeda+0.266
merce+0.260
Neg logit contributions
osity-0.264
 Converted-0.252
*,-0.246
®,-0.238
 REPL-0.238
Token Territory
Token ID25219
Feature activation+1.19e-01

Pos logit contributions
anmar+0.424
ngth+0.403
enhagen+0.391
romeda+0.380
kefeller+0.370
Neg logit contributions
osity-0.354
 Converted-0.336
*,-0.331
®,-0.320
xa-0.318
Token).[
Token ID42669
Feature activation-6.23e-01

Pos logit contributions
osity+0.314
*,+0.295
 Converted+0.291
®,+0.282
xa+0.274
Neg logit contributions
anmar-0.450
ngth-0.415
enhagen-0.414
romeda-0.402
agra-0.394
Token184
Token ID22883
Feature activation-1.15e-03

Pos logit contributions
anmar+2.310
ngth+2.072
enhagen+2.058
romeda+2.026
agra+1.958
Neg logit contributions
osity-1.762
 Converted-1.630
*,-1.605
xa-1.552
erved-1.546
Token]
Token ID60
Feature activation-1.79e-01

Pos logit contributions
anmar+0.004
ngth+0.004
enhagen+0.004
romeda+0.004
agra+0.003
Neg logit contributions
osity-0.003
 Converted-0.003
*,-0.003
erved-0.003
xa-0.003
Token The
Token ID383
Feature activation-4.85e-02

Pos logit contributions
anmar+0.682
ngth+0.619
enhagen+0.610
merce+0.594
romeda+0.591
Neg logit contributions
osity-0.499
 Converted-0.479
*,-0.468
®,-0.446
 REPL-0.440
Token House
Token ID2097
Feature activation-1.27e-01

Pos logit contributions
anmar+0.171
ngth+0.159
enhagen+0.154
romeda+0.151
merce+0.148
Neg logit contributions
osity-0.143
 Converted-0.132
*,-0.131
®,-0.125
 REPL-0.125
Token of
Token ID286
Feature activation+1.76e-02

Pos logit contributions
anmar+0.453
enhagen+0.400
ngth+0.399
romeda+0.393
agra+0.379
Neg logit contributions
osity-0.381
 Converted-0.354
*,-0.352
®,-0.338
xa-0.332
Token
Token ID116
Feature activation-1.48e-01

Pos logit contributions
anmar+1.759
enhagen+1.578
romeda+1.558
ngth+1.557
agra+1.501
Neg logit contributions
osity-1.430
 Converted-1.332
*,-1.301
xa-1.265
®,-1.253
Token
Token ID12466
Feature activation-5.91e-01

Pos logit contributions
anmar+0.448
ngth+0.391
enhagen+0.387
romeda+0.381
kefeller+0.368
Neg logit contributions
osity-0.527
*,-0.495
 Converted-0.494
xa-0.477
®,-0.476
Token
Token ID112
Feature activation-8.38e-02

Pos logit contributions
anmar+2.076
enhagen+1.853
ngth+1.838
romeda+1.822
agra+1.755
Neg logit contributions
osity-1.792
 Converted-1.664
*,-1.634
xa-1.588
®,-1.579
Tokenр
Token ID21169
Feature activation-5.05e-01

Pos logit contributions
anmar+0.263
enhagen+0.234
ngth+0.231
romeda+0.226
merce+0.220
Neg logit contributions
osity-0.288
*,-0.272
 Converted-0.270
xa-0.261
®,-0.260
Tokenу
Token ID35072
Feature activation-1.66e-01

Pos logit contributions
anmar+1.515
ngth+1.355
enhagen+1.346
romeda+1.309
merce+1.256
Neg logit contributions
osity-1.801
 Converted-1.682
*,-1.654
xa-1.614
erved-1.602
Token
Token ID140
Feature activation-6.17e-01

Pos logit contributions
anmar+0.494
ngth+0.426
enhagen+0.424
romeda+0.413
merce+0.396
Neg logit contributions
osity-0.592
 Converted-0.573
*,-0.566
®,-0.550
xa-0.549
Token
Token ID115
Feature activation-3.34e-01

Pos logit contributions
anmar+2.075
ngth+1.853
romeda+1.843
enhagen+1.833
kefeller+1.765
Neg logit contributions
osity-1.925
 Converted-1.821
*,-1.779
xa-1.740
®,-1.723
Tokenь
Token ID45367
Feature activation-2.10e-01

Pos logit contributions
anmar+0.969
enhagen+0.849
ngth+0.847
romeda+0.822
agra+0.783
Neg logit contributions
osity-1.221
 Converted-1.160
*,-1.157
®,-1.119
xa-1.106
Tokenя
Token ID40623
Feature activation+4.32e-02

Pos logit contributions
anmar+0.680
enhagen+0.610
ngth+0.591
romeda+0.584
kefeller+0.565
Neg logit contributions
osity-0.701
*,-0.672
 Converted-0.672
®,-0.644
xa-0.638
Tokenм
Token ID43108
Feature activation-6.30e-02

Pos logit contributions
osity+0.148
*,+0.143
 Converted+0.142
®,+0.138
xa+0.136
Neg logit contributions
anmar-0.134
enhagen-0.118
romeda-0.116
ngth-0.115
kefeller-0.111
Tokenи
Token ID18849
Feature activation-2.08e-01

Pos logit contributions
anmar+0.209
ngth+0.183
enhagen+0.182
romeda+0.179
kefeller+0.175
Neg logit contributions
osity-0.206
*,-0.195
 Converted-0.193
®,-0.188
xa-0.184
Token had
Token ID550
Feature activation+1.17e-01

Pos logit contributions
osity+0.015
 Converted+0.014
*,+0.013
 REPL+0.013
®,+0.013
Neg logit contributions
anmar-0.020
ngth-0.018
enhagen-0.018
kefeller-0.017
romeda-0.017
Token it
Token ID340
Feature activation+1.77e-02

Pos logit contributions
osity+0.331
*,+0.321
 Converted+0.318
®,+0.302
 REPL+0.295
Neg logit contributions
anmar-0.430
enhagen-0.386
ngth-0.382
kefeller-0.367
romeda-0.367
Token might
Token ID1244
Feature activation-1.37e-01

Pos logit contributions
osity+0.050
*,+0.048
 Converted+0.048
®,+0.045
 REPL+0.045
Neg logit contributions
anmar-0.065
enhagen-0.058
ngth-0.058
romeda-0.056
kefeller-0.055
Token get
Token ID651
Feature activation-3.46e-02

Pos logit contributions
anmar+0.464
ngth+0.407
enhagen+0.406
romeda+0.393
kefeller+0.379
Neg logit contributions
osity-0.440
*,-0.410
 Converted-0.407
 REPL-0.394
erved-0.390
Token quite
Token ID2407
Feature activation+3.74e-02

Pos logit contributions
anmar+0.126
enhagen+0.112
ngth+0.111
romeda+0.108
merce+0.106
Neg logit contributions
osity-0.100
 Converted-0.096
*,-0.094
 REPL-0.090
®,-0.090
Token warm
Token ID5814
Feature activation-6.06e-01

Pos logit contributions
osity+0.101
*,+0.097
 Converted+0.096
 REPL+0.091
erved+0.090
Neg logit contributions
anmar-0.144
enhagen-0.130
ngth-0.127
romeda-0.123
kefeller-0.122
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
anmar+2.242
ngth+2.022
enhagen+1.981
romeda+1.938
kefeller+1.902
Neg logit contributions
osity-1.709
*,-1.612
 Converted-1.577
®,-1.522
erved-1.509
Token
Token ID198
Feature activation-3.71e-04

Pos logit contributions
anmar+0.425
enhagen+0.382
ngth+0.380
romeda+0.367
merce+0.363
Neg logit contributions
osity-0.279
 Converted-0.269
*,-0.260
 REPL-0.247
®,-0.245
Token
Token ID198
Feature activation-3.74e-02

Pos logit contributions
anmar+0.001
ngth+0.001
enhagen+0.001
romeda+0.001
merce+0.001
Neg logit contributions
osity-0.001
 Converted-0.001
*,-0.001
xa-0.001
®,-0.001
TokenGot
Token ID30074
Feature activation+1.68e-01

Pos logit contributions
anmar+0.132
enhagen+0.118
ngth+0.117
romeda+0.113
kefeller+0.110
Neg logit contributions
osity-0.114
*,-0.108
 Converted-0.106
xa-0.101
®,-0.100
Token it
Token ID340
Feature activation-7.93e-03

Pos logit contributions
osity+0.504
 Converted+0.476
*,+0.468
 REPL+0.449
erved+0.448
Neg logit contributions
anmar-0.587
enhagen-0.521
ngth-0.509
romeda-0.503
kefeller-0.487
Token+
Token ID10
Feature activation-1.57e-01

Pos logit contributions
osity+0.183
 Converted+0.176
*,+0.172
xa+0.170
®,+0.164
Neg logit contributions
anmar-0.294
ngth-0.265
enhagen-0.264
romeda-0.255
merce-0.248
Token {
Token ID1391
Feature activation-1.19e-01

Pos logit contributions
anmar+0.603
ngth+0.540
enhagen+0.535
romeda+0.523
merce+0.502
Neg logit contributions
osity-0.429
 Converted-0.414
*,-0.402
xa-0.401
®,-0.383
Token(
Token ID7
Feature activation-3.81e-01

Pos logit contributions
anmar+0.484
ngth+0.434
enhagen+0.427
romeda+0.426
merce+0.419
Neg logit contributions
osity-0.302
 Converted-0.280
*,-0.269
xa-0.268
erved-0.256
Token10
Token ID940
Feature activation-2.03e-01

Pos logit contributions
anmar+1.280
ngth+1.142
enhagen+1.120
romeda+1.105
merce+1.071
Neg logit contributions
osity-1.215
 Converted-1.126
*,-1.115
xa-1.094
erved-1.072
Tokens
Token ID82
Feature activation-8.08e-02

Pos logit contributions
anmar+0.792
ngth+0.713
enhagen+0.711
romeda+0.693
agra+0.677
Neg logit contributions
osity-0.536
 Converted-0.495
*,-0.486
xa-0.471
®,-0.464
Token)}
Token ID38165
Feature activation-6.05e-01

Pos logit contributions
anmar+0.363
ngth+0.330
enhagen+0.329
romeda+0.325
agra+0.317
Neg logit contributions
osity-0.164
 Converted-0.146
*,-0.141
xa-0.135
erved-0.134
Token K
Token ID509
Feature activation+8.45e-02

Pos logit contributions
anmar+2.306
ngth+2.069
enhagen+2.051
romeda+2.010
merce+1.943
Neg logit contributions
osity-1.663
 Converted-1.566
*,-1.520
xa-1.477
®,-1.460
Tokenb
Token ID65
Feature activation+5.44e-02

Pos logit contributions
osity+0.217
xa+0.203
 Converted+0.198
*,+0.195
®,+0.187
Neg logit contributions
anmar-0.337
enhagen-0.308
ngth-0.307
romeda-0.298
merce-0.286
Token7
Token ID22
Feature activation+5.83e-02

Pos logit contributions
osity+0.165
xa+0.154
 Converted+0.152
*,+0.152
®,+0.146
Neg logit contributions
anmar-0.195
ngth-0.174
enhagen-0.173
romeda-0.168
merce-0.161
Token {
Token ID1391
Feature activation-2.13e-02

Pos logit contributions
osity+0.152
 Converted+0.146
*,+0.144
xa+0.138
®,+0.136
Neg logit contributions
anmar-0.231
enhagen-0.206
ngth-0.204
romeda-0.199
merce-0.194
Token(
Token ID7
Feature activation-2.96e-01

Pos logit contributions
anmar+0.086
ngth+0.078
romeda+0.077
enhagen+0.077
merce+0.074
Neg logit contributions
osity-0.053
 Converted-0.048
*,-0.047
xa-0.046
erved-0.045
Token Hide
Token ID10415
Feature activation-2.42e-01

Pos logit contributions
anmar+0.295
ngth+0.261
enhagen+0.254
merce+0.250
romeda+0.247
Neg logit contributions
osity-0.347
 Converted-0.335
*,-0.324
®,-0.313
erved-0.313
Token Caption
Token ID11260
Feature activation-2.96e-01

Pos logit contributions
anmar+1.104
ngth+1.013
enhagen+1.006
romeda+0.992
agra+0.964
Neg logit contributions
osity-0.477
 Converted-0.429
*,-0.410
erved-0.389
®,-0.388
Token 8
Token ID807
Feature activation+7.47e-02

Pos logit contributions
anmar+1.088
ngth+0.973
enhagen+0.968
romeda+0.949
agra+0.915
Neg logit contributions
osity-0.848
 Converted-0.784
*,-0.766
®,-0.740
erved-0.739
Token of
Token ID286
Feature activation-9.28e-03

Pos logit contributions
osity+0.217
 Converted+0.201
*,+0.200
xa+0.193
®,+0.189
Neg logit contributions
anmar-0.280
ngth-0.254
enhagen-0.250
romeda-0.242
merce-0.241
Token 15
Token ID1315
Feature activation-7.42e-02

Pos logit contributions
anmar+0.033
ngth+0.029
enhagen+0.029
romeda+0.028
merce+0.027
Neg logit contributions
osity-0.028
 Converted-0.026
*,-0.026
®,-0.025
erved-0.025
Token Photos
Token ID9434
Feature activation-6.05e-01

Pos logit contributions
anmar+0.299
ngth+0.272
enhagen+0.269
romeda+0.263
merce+0.257
Neg logit contributions
osity-0.188
 Converted-0.174
*,-0.169
xa-0.162
®,-0.162
Token:
Token ID25
Feature activation-7.58e-02

Pos logit contributions
anmar+1.899
ngth+1.660
enhagen+1.655
romeda+1.632
agra+1.563
Neg logit contributions
osity-2.029
 Converted-1.892
*,-1.852
®,-1.806
erved-1.805
Token Carly
Token ID35982
Feature activation-2.40e-01

Pos logit contributions
anmar+0.244
ngth+0.218
enhagen+0.214
merce+0.206
romeda+0.204
Neg logit contributions
osity-0.255
 Converted-0.243
*,-0.236
®,-0.230
xa-0.228
Token Fiorina
Token ID49028
Feature activation-1.48e-01

Pos logit contributions
anmar+0.594
ngth+0.500
enhagen+0.496
romeda+0.486
agra+0.458
Neg logit contributions
osity-0.967
 Converted-0.914
*,-0.898
®,-0.879
erved-0.879
Token's
Token ID338
Feature activation+1.10e-02

Pos logit contributions
anmar+0.548
ngth+0.491
enhagen+0.482
romeda+0.477
merce+0.460
Neg logit contributions
osity-0.425
 Converted-0.396
*,-0.388
®,-0.374
xa-0.372
Token political
Token ID1964
Feature activation+1.31e-01

Pos logit contributions
osity+0.032
 Converted+0.030
*,+0.030
®,+0.029
erved+0.029
Neg logit contributions
anmar-0.039
ngth-0.037
enhagen-0.036
romeda-0.035
merce-0.034
Token on
Token ID319
Feature activation+2.62e-01

Pos logit contributions
anmar+0.289
enhagen+0.258
ngth+0.257
romeda+0.255
kefeller+0.245
Neg logit contributions
osity-0.226
*,-0.206
 Converted-0.206
®,-0.202
xa-0.195
Token Facebook
Token ID3203
Feature activation+3.52e-02

Pos logit contributions
osity+0.741
 Converted+0.680
*,+0.669
xa+0.646
itor+0.642
Neg logit contributions
anmar-0.982
ngth-0.898
enhagen-0.882
romeda-0.861
agra-0.820
Token @
Token ID2488
Feature activation+4.95e-02

Pos logit contributions
osity+0.098
*,+0.092
®,+0.089
 Converted+0.089
 REPL+0.085
Neg logit contributions
anmar-0.134
ngth-0.120
enhagen-0.119
romeda-0.117
agra-0.114
Token https
Token ID3740
Feature activation-2.47e-01

Pos logit contributions
osity+0.135
 Converted+0.121
*,+0.120
xa+0.116
erved+0.115
Neg logit contributions
anmar-0.190
ngth-0.170
romeda-0.169
enhagen-0.169
merce-0.161
Token://
Token ID1378
Feature activation-2.66e-01

Pos logit contributions
anmar+0.942
ngth+0.849
enhagen+0.843
romeda+0.829
agra+0.800
Neg logit contributions
osity-0.668
 Converted-0.614
*,-0.600
®,-0.578
erved-0.578
Tokenwww
Token ID2503
Feature activation-6.04e-01

Pos logit contributions
anmar+0.989
ngth+0.878
romeda+0.877
enhagen+0.876
agra+0.831
Neg logit contributions
osity-0.764
 Converted-0.688
*,-0.685
xa-0.665
erved-0.655
Token.
Token ID13
Feature activation-2.29e-01

Pos logit contributions
anmar+2.081
ngth+1.843
enhagen+1.837
romeda+1.811
agra+1.740
Neg logit contributions
osity-1.848
 Converted-1.714
*,-1.674
®,-1.626
erved-1.626
Tokenfacebook
Token ID19024
Feature activation-3.58e-01

Pos logit contributions
anmar+0.893
enhagen+0.801
romeda+0.798
ngth+0.795
merce+0.756
Neg logit contributions
osity-0.611
 Converted-0.549
*,-0.545
xa-0.524
erved-0.521
Token.
Token ID13
Feature activation-1.92e-01

Pos logit contributions
anmar+1.255
ngth+1.118
enhagen+1.114
romeda+1.093
agra+1.050
Neg logit contributions
osity-1.079
 Converted-1.001
*,-0.979
erved-0.948
®,-0.947
Tokencom
Token ID785
Feature activation-1.86e-01

Pos logit contributions
anmar+0.768
ngth+0.695
enhagen+0.692
romeda+0.681
agra+0.656
Neg logit contributions
osity-0.487
 Converted-0.445
*,-0.433
erved-0.416
xa-0.415
Token/
Token ID14
Feature activation-2.45e-01

Pos logit contributions
anmar+0.709
ngth+0.640
enhagen+0.635
romeda+0.622
agra+0.602
Neg logit contributions
osity-0.504
 Converted-0.468
*,-0.456
erved-0.437
xa-0.437
Token mates
Token ID27973
Feature activation+1.43e-02

Pos logit contributions
anmar+0.217
ngth+0.201
enhagen+0.194
romeda+0.191
merce+0.182
Neg logit contributions
osity-0.178
*,-0.161
 Converted-0.159
xa-0.156
®,-0.153
Token,
Token ID11
Feature activation-7.21e-02

Pos logit contributions
osity+0.037
 Converted+0.035
*,+0.034
 REPL+0.032
®,+0.032
Neg logit contributions
anmar-0.056
ngth-0.052
enhagen-0.051
kefeller-0.049
agra-0.049
Token V
Token ID569
Feature activation-5.64e-03

Pos logit contributions
anmar+0.274
ngth+0.253
enhagen+0.248
romeda+0.239
merce+0.237
Neg logit contributions
osity-0.197
 Converted-0.185
*,-0.181
®,-0.172
 REPL-0.170
TokenPs
Token ID12016
Feature activation-2.81e-02

Pos logit contributions
anmar+0.021
ngth+0.020
enhagen+0.020
romeda+0.019
merce+0.019
Neg logit contributions
osity-0.015
*,-0.014
 Converted-0.014
itor-0.013
erved-0.013
Token See
Token ID4091
Feature activation-2.65e-02

Pos logit contributions
anmar+0.107
ngth+0.096
enhagen+0.096
romeda+0.095
agra+0.092
Neg logit contributions
osity-0.077
 Converted-0.070
*,-0.069
®,-0.067
 REPL-0.066
Token Gallery
Token ID12917
Feature activation-6.01e-01

Pos logit contributions
anmar+0.098
ngth+0.091
enhagen+0.088
romeda+0.085
merce+0.085
Neg logit contributions
osity-0.075
 Converted-0.071
*,-0.069
erved-0.066
®,-0.066
Token Donald
Token ID3759
Feature activation+4.94e-02

Pos logit contributions
anmar+1.990
ngth+1.752
enhagen+1.743
romeda+1.723
agra+1.653
Neg logit contributions
osity-1.923
 Converted-1.796
*,-1.751
®,-1.704
erved-1.701
Token Trump
Token ID1301
Feature activation+3.43e-02

Pos logit contributions
osity+0.181
 Converted+0.172
*,+0.168
®,+0.163
 REPL+0.162
Neg logit contributions
anmar-0.145
ngth-0.129
enhagen-0.124
romeda-0.122
merce-0.119
Token passes
Token ID8318
Feature activation+2.48e-01

Pos logit contributions
osity+0.094
 Converted+0.089
*,+0.086
®,+0.082
xa+0.081
Neg logit contributions
anmar-0.131
ngth-0.118
enhagen-0.115
romeda-0.114
agra-0.112
Token on
Token ID319
Feature activation-1.30e-02

Pos logit contributions
osity+0.775
*,+0.723
 Converted+0.706
 REPL+0.695
®,+0.692
Neg logit contributions
anmar-0.839
ngth-0.759
romeda-0.728
enhagen-0.719
merce-0.701
Token '
Token ID705
Feature activation+3.76e-02

Pos logit contributions
anmar+0.043
ngth+0.038
enhagen+0.037
romeda+0.037
agra+0.035
Neg logit contributions
osity-0.041
 Converted-0.038
*,-0.038
®,-0.037
xa-0.037
Token Hide
Token ID10415
Feature activation-9.97e-02

Pos logit contributions
osity+0.067
 Converted+0.065
*,+0.063
 REPL+0.061
erved+0.061
Neg logit contributions
anmar-0.061
ngth-0.054
enhagen-0.053
romeda-0.052
merce-0.052
Token Caption
Token ID11260
Feature activation-2.95e-01

Pos logit contributions
anmar+0.462
ngth+0.426
enhagen+0.421
romeda+0.415
merce+0.405
Neg logit contributions
osity-0.192
 Converted-0.173
*,-0.164
erved-0.156
xa-0.155
Token 7
Token ID767
Feature activation+9.39e-02

Pos logit contributions
anmar+0.986
ngth+0.872
enhagen+0.867
romeda+0.853
agra+0.819
Neg logit contributions
osity-0.931
 Converted-0.868
*,-0.848
®,-0.825
erved-0.824
Token of
Token ID286
Feature activation+4.23e-02

Pos logit contributions
osity+0.270
 Converted+0.251
*,+0.250
xa+0.241
®,+0.236
Neg logit contributions
anmar-0.353
ngth-0.320
enhagen-0.315
romeda-0.305
merce-0.304
Token 15
Token ID1315
Feature activation-6.48e-02

Pos logit contributions
osity+0.128
 Converted+0.119
*,+0.117
®,+0.113
erved+0.113
Neg logit contributions
anmar-0.149
ngth-0.133
enhagen-0.131
romeda-0.128
merce-0.124
Token Photos
Token ID9434
Feature activation-5.95e-01

Pos logit contributions
anmar+0.263
ngth+0.240
enhagen+0.237
romeda+0.231
merce+0.227
Neg logit contributions
osity-0.162
 Converted-0.151
*,-0.147
xa-0.141
®,-0.140
Token:
Token ID25
Feature activation-8.49e-02

Pos logit contributions
anmar+1.866
ngth+1.630
enhagen+1.626
romeda+1.604
agra+1.535
Neg logit contributions
osity-1.996
 Converted-1.861
*,-1.821
®,-1.777
erved-1.776
Token Carly
Token ID35982
Feature activation-2.41e-01

Pos logit contributions
anmar+0.273
ngth+0.243
enhagen+0.239
merce+0.230
romeda+0.228
Neg logit contributions
osity-0.286
 Converted-0.273
*,-0.265
®,-0.258
xa-0.256
Token Fiorina
Token ID49028
Feature activation-1.17e-01

Pos logit contributions
anmar+0.594
ngth+0.500
enhagen+0.497
romeda+0.487
agra+0.459
Neg logit contributions
osity-0.974
 Converted-0.921
*,-0.904
®,-0.886
erved-0.885
Token's
Token ID338
Feature activation+7.17e-03

Pos logit contributions
anmar+0.435
ngth+0.390
enhagen+0.383
romeda+0.379
merce+0.365
Neg logit contributions
osity-0.334
 Converted-0.312
*,-0.306
®,-0.295
xa-0.293
Token political
Token ID1964
Feature activation+1.39e-01

Pos logit contributions
osity+0.021
 Converted+0.020
*,+0.019
®,+0.019
erved+0.019
Neg logit contributions
anmar-0.026
ngth-0.024
enhagen-0.023
romeda-0.023
merce-0.022
Token7
Token ID22
Feature activation+5.83e-02

Pos logit contributions
osity+0.165
xa+0.154
 Converted+0.152
*,+0.152
®,+0.146
Neg logit contributions
anmar-0.195
ngth-0.174
enhagen-0.173
romeda-0.168
merce-0.161
Token {
Token ID1391
Feature activation-2.13e-02

Pos logit contributions
osity+0.152
 Converted+0.146
*,+0.144
xa+0.138
®,+0.136
Neg logit contributions
anmar-0.231
enhagen-0.206
ngth-0.204
romeda-0.199
merce-0.194
Token(
Token ID7
Feature activation-2.96e-01

Pos logit contributions
anmar+0.086
ngth+0.078
romeda+0.077
enhagen+0.077
merce+0.074
Neg logit contributions
osity-0.053
 Converted-0.048
*,-0.047
xa-0.046
erved-0.045
Token3
Token ID18
Feature activation-3.50e-01

Pos logit contributions
anmar+1.068
ngth+0.965
enhagen+0.945
romeda+0.931
merce+0.904
Neg logit contributions
osity-0.870
 Converted-0.801
*,-0.794
xa-0.778
erved-0.759
Tokens
Token ID82
Feature activation-1.00e-01

Pos logit contributions
anmar+1.304
ngth+1.171
enhagen+1.164
romeda+1.137
agra+1.102
Neg logit contributions
osity-0.983
 Converted-0.906
*,-0.890
xa-0.867
®,-0.857
Token)}
Token ID38165
Feature activation-5.93e-01

Pos logit contributions
anmar+0.447
ngth+0.407
enhagen+0.406
romeda+0.401
agra+0.391
Neg logit contributions
osity-0.205
 Converted-0.183
*,-0.177
xa-0.169
erved-0.168
Token 52
Token ID6740
Feature activation-2.25e-02

Pos logit contributions
anmar+2.129
ngth+1.897
enhagen+1.887
romeda+1.844
agra+1.778
Neg logit contributions
osity-1.751
 Converted-1.647
*,-1.606
xa-1.555
®,-1.547
Token.
Token ID13
Feature activation-6.12e-02

Pos logit contributions
anmar+0.084
ngth+0.077
enhagen+0.076
romeda+0.074
merce+0.072
Neg logit contributions
osity-0.064
 Converted-0.059
*,-0.058
xa-0.057
®,-0.055
Token Q
Token ID1195
Feature activation+4.06e-03

Pos logit contributions
anmar+0.228
ngth+0.206
enhagen+0.204
romeda+0.198
merce+0.192
Neg logit contributions
osity-0.173
 Converted-0.165
*,-0.160
xa-0.158
®,-0.153
Tokenxf
Token ID26152
Feature activation+2.98e-02

Pos logit contributions
osity+0.009
xa+0.009
 Converted+0.008
*,+0.008
erved+0.008
Neg logit contributions
anmar-0.017
ngth-0.016
enhagen-0.016
romeda-0.016
kefeller-0.015
Token7
Token ID22
Feature activation+3.84e-02

Pos logit contributions
osity+0.095
*,+0.088
 Converted+0.088
xa+0.087
®,+0.085
Neg logit contributions
anmar-0.101
ngth-0.092
enhagen-0.090
romeda-0.088
agra-0.084
Token.
Token ID13
Feature activation-6.32e-02

Pos logit contributions
osity+0.395
*,+0.365
 Converted+0.352
®,+0.346
xa+0.338
Neg logit contributions
anmar-0.528
ngth-0.476
romeda-0.470
enhagen-0.468
kefeller-0.465
Token
Token ID198
Feature activation-4.65e-02

Pos logit contributions
anmar+0.240
ngth+0.217
enhagen+0.215
romeda+0.210
merce+0.207
Neg logit contributions
osity-0.175
 Converted-0.169
*,-0.165
®,-0.158
 REPL-0.157
Token
Token ID198
Feature activation-6.13e-02

Pos logit contributions
anmar+0.158
ngth+0.143
enhagen+0.141
romeda+0.135
merce+0.132
Neg logit contributions
osity-0.151
 Converted-0.143
*,-0.140
xa-0.136
®,-0.134
TokenFor
Token ID1890
Feature activation-1.81e-01

Pos logit contributions
anmar+0.251
ngth+0.230
enhagen+0.229
romeda+0.225
merce+0.216
Neg logit contributions
osity-0.154
*,-0.140
 Converted-0.139
xa-0.133
®,-0.133
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
anmar+0.654
ngth+0.594
enhagen+0.578
romeda+0.572
kefeller+0.549
Neg logit contributions
osity-0.535
 Converted-0.488
*,-0.483
®,-0.467
erved-0.465
Token Yog
Token ID31604
Feature activation-5.93e-01

Pos logit contributions
anmar+0.450
ngth+0.407
enhagen+0.400
romeda+0.393
kefeller+0.380
Neg logit contributions
osity-0.366
 Converted-0.341
*,-0.334
®,-0.324
 REPL-0.324
Tokenventures
Token ID10065
Feature activation-2.66e-01

Pos logit contributions
anmar+2.207
ngth+1.995
enhagen+1.972
romeda+1.934
kefeller+1.868
Neg logit contributions
osity-1.675
 Converted-1.529
*,-1.505
®,-1.457
erved-1.444
Token Kickstarter
Token ID14437
Feature activation-1.79e-01

Pos logit contributions
anmar+0.988
ngth+0.898
enhagen+0.894
romeda+0.876
agra+0.844
Neg logit contributions
osity-0.754
 Converted-0.697
*,-0.695
®,-0.679
 REPL-0.658
Token backers
Token ID18917
Feature activation+1.43e-01

Pos logit contributions
anmar+0.677
ngth+0.631
enhagen+0.617
romeda+0.612
agra+0.594
Neg logit contributions
osity-0.482
*,-0.453
 Converted-0.447
®,-0.441
 REPL-0.421
Token the
Token ID262
Feature activation+9.30e-03

Pos logit contributions
osity+0.388
*,+0.381
 Converted+0.367
®,+0.364
erved+0.348
Neg logit contributions
anmar-0.529
ngth-0.486
enhagen-0.480
romeda-0.468
agra-0.467
Token physical
Token ID3518
Feature activation+6.37e-02

Pos logit contributions
osity+0.027
 Converted+0.025
*,+0.025
®,+0.024
 REPL+0.024
Neg logit contributions
anmar-0.033
ngth-0.030
enhagen-0.030
romeda-0.030
kefeller-0.028
TokenRoman
Token ID32454
Feature activation+1.06e-01

Pos logit contributions
anmar+0.694
ngth+0.619
enhagen+0.616
romeda+0.610
agra+0.588
Neg logit contributions
osity-0.496
 Converted-0.451
*,-0.450
®,-0.436
xa-0.436
TokenF
Token ID37
Feature activation+1.30e-01

Pos logit contributions
osity+0.309
 Converted+0.281
*,+0.272
®,+0.263
xa+0.261
Neg logit contributions
anmar-0.386
ngth-0.351
romeda-0.348
enhagen-0.345
merce-0.331
Tokenlynn
Token ID12935
Feature activation-1.20e-01

Pos logit contributions
osity+0.353
*,+0.325
 Converted+0.321
erved+0.314
®,+0.311
Neg logit contributions
anmar-0.483
ngth-0.439
enhagen-0.437
romeda-0.430
merce-0.423
Token pic
Token ID8301
Feature activation-3.68e-01

Pos logit contributions
anmar+0.420
ngth+0.375
enhagen+0.371
romeda+0.368
kefeller+0.353
Neg logit contributions
osity-0.368
 Converted-0.343
*,-0.336
®,-0.327
 REPL-0.324
Token.
Token ID13
Feature activation+8.13e-02

Pos logit contributions
anmar+1.283
ngth+1.140
enhagen+1.134
romeda+1.116
agra+1.072
Neg logit contributions
osity-1.115
 Converted-1.035
*,-1.012
®,-0.981
erved-0.980
Tokentwitter
Token ID6956
Feature activation-5.92e-01

Pos logit contributions
osity+0.242
 Converted+0.224
*,+0.222
xa+0.214
erved+0.212
Neg logit contributions
anmar-0.294
ngth-0.263
enhagen-0.261
romeda-0.254
merce-0.247
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
anmar+2.029
ngth+1.796
enhagen+1.789
romeda+1.766
agra+1.697
Neg logit contributions
osity-1.815
 Converted-1.683
*,-1.643
®,-1.597
erved-1.597
Tokencom
Token ID785
Feature activation-4.01e-02

Pos logit contributions
osity+0.327
 Converted+0.298
*,+0.296
xa+0.282
erved+0.278
Neg logit contributions
anmar-0.583
ngth-0.531
enhagen-0.528
romeda-0.510
merce-0.497
Token/
Token ID14
Feature activation-9.53e-02

Pos logit contributions
anmar+0.163
ngth+0.148
enhagen+0.146
romeda+0.141
merce+0.140
Neg logit contributions
osity-0.103
 Converted-0.095
*,-0.094
xa-0.091
®,-0.089
Tokengy
Token ID1360
Feature activation-1.04e-01

Pos logit contributions
anmar+0.353
ngth+0.318
enhagen+0.318
romeda+0.315
merce+0.300
Neg logit contributions
osity-0.268
 Converted-0.243
*,-0.243
xa-0.243
erved-0.236
Tokend
Token ID67
Feature activation-1.33e-01

Pos logit contributions
anmar+0.384
enhagen+0.348
ngth+0.348
romeda+0.343
merce+0.327
Neg logit contributions
osity-0.292
 Converted-0.265
xa-0.264
*,-0.264
erved-0.257
Tokenи
Token ID18849
Feature activation-2.91e-01

Pos logit contributions
anmar+0.288
enhagen+0.257
romeda+0.256
ngth+0.254
merce+0.247
Neg logit contributions
osity-0.288
*,-0.274
 Converted-0.273
®,-0.267
xa-0.261
Tokenм
Token ID43108
Feature activation-1.55e-01

Pos logit contributions
anmar+0.909
enhagen+0.804
ngth+0.789
romeda+0.782
kefeller+0.758
Neg logit contributions
osity-0.999
 Converted-0.967
*,-0.956
®,-0.927
xa-0.908
Tokenи
Token ID18849
Feature activation-3.18e-01

Pos logit contributions
anmar+0.517
ngth+0.457
enhagen+0.452
romeda+0.447
kefeller+0.438
Neg logit contributions
osity-0.505
 Converted-0.478
*,-0.478
®,-0.463
xa-0.452
Token
Token ID12466
Feature activation-4.88e-01

Pos logit contributions
anmar+1.019
enhagen+0.899
ngth+0.890
romeda+0.881
kefeller+0.857
Neg logit contributions
osity-1.067
 Converted-1.018
*,-1.012
®,-0.972
xa-0.957
Token
Token ID116
Feature activation-1.48e-01

Pos logit contributions
anmar+1.759
enhagen+1.578
romeda+1.558
ngth+1.557
agra+1.501
Neg logit contributions
osity-1.430
 Converted-1.332
*,-1.301
xa-1.265
®,-1.253
Token
Token ID12466
Feature activation-5.91e-01

Pos logit contributions
anmar+0.448
ngth+0.391
enhagen+0.387
romeda+0.381
kefeller+0.368
Neg logit contributions
osity-0.527
*,-0.495
 Converted-0.494
xa-0.477
®,-0.476
Token
Token ID112
Feature activation-8.38e-02

Pos logit contributions
anmar+2.076
enhagen+1.853
ngth+1.838
romeda+1.822
agra+1.755
Neg logit contributions
osity-1.792
 Converted-1.664
*,-1.634
xa-1.588
®,-1.579
Tokenр
Token ID21169
Feature activation-5.05e-01

Pos logit contributions
anmar+0.263
enhagen+0.234
ngth+0.231
romeda+0.226
merce+0.220
Neg logit contributions
osity-0.288
*,-0.272
 Converted-0.270
xa-0.261
®,-0.260
Tokenу
Token ID35072
Feature activation-1.66e-01

Pos logit contributions
anmar+1.515
ngth+1.355
enhagen+1.346
romeda+1.309
merce+1.256
Neg logit contributions
osity-1.801
 Converted-1.682
*,-1.654
xa-1.614
erved-1.602
Token
Token ID140
Feature activation-6.17e-01

Pos logit contributions
anmar+0.494
ngth+0.426
enhagen+0.424
romeda+0.413
merce+0.396
Neg logit contributions
osity-0.592
 Converted-0.573
*,-0.566
®,-0.550
xa-0.549
Token
Token ID115
Feature activation-3.34e-01

Pos logit contributions
anmar+2.075
ngth+1.853
romeda+1.843
enhagen+1.833
kefeller+1.765
Neg logit contributions
osity-1.925
 Converted-1.821
*,-1.779
xa-1.740
®,-1.723
Token7
Token ID22
Feature activation-2.36e-02

Pos logit contributions
anmar+0.005
ngth+0.005
enhagen+0.004
romeda+0.004
merce+0.004
Neg logit contributions
osity-0.004
*,-0.004
 Converted-0.004
xa-0.004
®,-0.004
Token {
Token ID1391
Feature activation-2.19e-02

Pos logit contributions
anmar+0.103
ngth+0.092
enhagen+0.091
romeda+0.088
htaking+0.085
Neg logit contributions
osity-0.053
 Converted-0.052
*,-0.052
xa-0.051
®,-0.049
Token(
Token ID7
Feature activation-3.33e-01

Pos logit contributions
anmar+0.088
ngth+0.080
enhagen+0.078
romeda+0.078
merce+0.076
Neg logit contributions
osity-0.057
 Converted-0.053
*,-0.052
xa-0.051
erved-0.049
Token490
Token ID31503
Feature activation-2.72e-01

Pos logit contributions
anmar+1.042
ngth+0.919
enhagen+0.906
romeda+0.887
merce+0.851
Neg logit contributions
osity-1.139
*,-1.065
 Converted-1.062
xa-1.045
erved-1.017
Tokens
Token ID82
Feature activation-1.44e-01

Pos logit contributions
anmar+1.131
enhagen+1.013
ngth+1.011
romeda+0.992
agra+0.971
Neg logit contributions
osity-0.665
 Converted-0.606
*,-0.597
xa-0.578
erved-0.565
Token)}
Token ID38165
Feature activation-5.90e-01

Pos logit contributions
anmar+0.652
ngth+0.592
enhagen+0.592
romeda+0.584
agra+0.569
Neg logit contributions
osity-0.289
 Converted-0.256
*,-0.249
xa-0.239
®,-0.234
Token 51
Token ID6885
Feature activation-1.04e-01

Pos logit contributions
anmar+2.287
ngth+2.068
enhagen+2.035
romeda+1.986
agra+1.927
Neg logit contributions
osity-1.599
 Converted-1.512
*,-1.471
xa-1.433
®,-1.411
Token.
Token ID13
Feature activation-8.79e-02

Pos logit contributions
anmar+0.403
ngth+0.359
enhagen+0.353
romeda+0.347
kefeller+0.336
Neg logit contributions
osity-0.289
 Converted-0.270
*,-0.263
xa-0.263
erved-0.252
Token N
Token ID399
Feature activation+1.30e-01

Pos logit contributions
anmar+0.330
ngth+0.297
enhagen+0.294
romeda+0.287
merce+0.280
Neg logit contributions
osity-0.245
 Converted-0.232
*,-0.225
xa-0.223
®,-0.215
Tokend
Token ID67
Feature activation-3.18e-02

Pos logit contributions
osity+0.265
xa+0.251
 Converted+0.235
*,+0.233
erved+0.226
Neg logit contributions
anmar-0.590
ngth-0.546
enhagen-0.545
romeda-0.525
merce-0.509
Token4
Token ID19
Feature activation+7.24e-02

Pos logit contributions
anmar+0.114
ngth+0.105
enhagen+0.103
romeda+0.099
merce+0.096
Neg logit contributions
osity-0.094
xa-0.089
 Converted-0.088
*,-0.087
®,-0.084
Token Hide
Token ID10415
Feature activation-1.46e-01

Pos logit contributions
anmar+0.323
ngth+0.288
enhagen+0.280
merce+0.274
romeda+0.270
Neg logit contributions
osity-0.365
 Converted-0.356
*,-0.342
®,-0.332
erved-0.332
Token Caption
Token ID11260
Feature activation-2.26e-01

Pos logit contributions
anmar+0.673
ngth+0.619
enhagen+0.613
romeda+0.604
merce+0.589
Neg logit contributions
osity-0.282
 Converted-0.255
*,-0.243
erved-0.230
®,-0.228
Token 9
Token ID860
Feature activation+9.14e-02

Pos logit contributions
anmar+0.781
ngth+0.692
enhagen+0.688
romeda+0.678
agra+0.652
Neg logit contributions
osity-0.689
 Converted-0.640
*,-0.625
®,-0.607
erved-0.606
Token of
Token ID286
Feature activation+4.18e-02

Pos logit contributions
osity+0.265
 Converted+0.245
*,+0.245
xa+0.235
®,+0.231
Neg logit contributions
anmar-0.342
ngth-0.311
enhagen-0.306
romeda-0.296
merce-0.295
Token 15
Token ID1315
Feature activation-7.26e-02

Pos logit contributions
osity+0.125
 Converted+0.117
*,+0.115
®,+0.111
erved+0.111
Neg logit contributions
anmar-0.149
ngth-0.134
enhagen-0.132
romeda-0.128
merce-0.126
Token Photos
Token ID9434
Feature activation-5.89e-01

Pos logit contributions
anmar+0.294
ngth+0.268
enhagen+0.264
romeda+0.258
merce+0.253
Neg logit contributions
osity-0.182
 Converted-0.170
*,-0.165
xa-0.158
®,-0.158
Token:
Token ID25
Feature activation-8.05e-02

Pos logit contributions
anmar+1.859
ngth+1.627
enhagen+1.621
romeda+1.597
agra+1.529
Neg logit contributions
osity-1.968
 Converted-1.836
*,-1.797
®,-1.751
erved-1.751
Token Carly
Token ID35982
Feature activation-1.92e-01

Pos logit contributions
anmar+0.260
ngth+0.233
enhagen+0.229
merce+0.220
romeda+0.217
Neg logit contributions
osity-0.269
 Converted-0.258
*,-0.250
®,-0.243
xa-0.241
Token Fiorina
Token ID49028
Feature activation-6.74e-02

Pos logit contributions
anmar+0.480
ngth+0.405
enhagen+0.401
romeda+0.393
agra+0.371
Neg logit contributions
osity-0.769
 Converted-0.727
*,-0.714
®,-0.699
erved-0.698
Token's
Token ID338
Feature activation+2.03e-03

Pos logit contributions
anmar+0.252
ngth+0.227
enhagen+0.222
romeda+0.220
merce+0.213
Neg logit contributions
osity-0.191
 Converted-0.179
*,-0.175
®,-0.168
xa-0.168
Token political
Token ID1964
Feature activation+1.20e-01

Pos logit contributions
osity+0.006
 Converted+0.006
*,+0.005
®,+0.005
erved+0.005
Neg logit contributions
anmar-0.007
ngth-0.007
enhagen-0.007
romeda-0.006
merce-0.006
Token Hide
Token ID10415
Feature activation-1.32e-01

Pos logit contributions
anmar+0.239
ngth+0.213
enhagen+0.207
merce+0.202
romeda+0.201
Neg logit contributions
osity-0.281
 Converted-0.274
*,-0.264
®,-0.255
erved-0.255
Token Caption
Token ID11260
Feature activation-3.06e-01

Pos logit contributions
anmar+0.613
ngth+0.564
enhagen+0.559
romeda+0.550
merce+0.537
Neg logit contributions
osity-0.255
 Converted-0.230
*,-0.219
erved-0.208
®,-0.206
Token 6
Token ID718
Feature activation+7.05e-02

Pos logit contributions
anmar+1.040
ngth+0.919
enhagen+0.914
romeda+0.898
agra+0.862
Neg logit contributions
osity-0.962
 Converted-0.896
*,-0.877
erved-0.850
®,-0.850
Token of
Token ID286
Feature activation+5.46e-02

Pos logit contributions
osity+0.204
 Converted+0.189
*,+0.189
xa+0.182
®,+0.178
Neg logit contributions
anmar-0.264
ngth-0.239
enhagen-0.235
romeda-0.229
merce-0.227
Token 15
Token ID1315
Feature activation-4.05e-02

Pos logit contributions
osity+0.163
 Converted+0.153
*,+0.150
®,+0.145
erved+0.145
Neg logit contributions
anmar-0.194
ngth-0.174
enhagen-0.172
romeda-0.167
merce-0.163
Token Photos
Token ID9434
Feature activation-5.87e-01

Pos logit contributions
anmar+0.165
ngth+0.151
enhagen+0.149
romeda+0.145
merce+0.143
Neg logit contributions
osity-0.100
 Converted-0.094
*,-0.091
xa-0.087
®,-0.087
Token:
Token ID25
Feature activation-1.12e-01

Pos logit contributions
anmar+1.841
ngth+1.609
enhagen+1.604
romeda+1.583
agra+1.515
Neg logit contributions
osity-1.968
 Converted-1.836
*,-1.796
®,-1.752
erved-1.751
Token Carly
Token ID35982
Feature activation-2.68e-01

Pos logit contributions
anmar+0.356
ngth+0.317
enhagen+0.313
merce+0.299
romeda+0.298
Neg logit contributions
osity-0.377
 Converted-0.360
*,-0.349
®,-0.340
xa-0.337
Token Fiorina
Token ID49028
Feature activation-1.91e-01

Pos logit contributions
anmar+0.657
ngth+0.552
enhagen+0.549
romeda+0.538
agra+0.507
Neg logit contributions
osity-1.084
 Converted-1.024
*,-1.007
®,-0.986
erved-0.986
Token's
Token ID338
Feature activation+1.54e-02

Pos logit contributions
anmar+0.700
ngth+0.627
enhagen+0.617
romeda+0.610
merce+0.586
Neg logit contributions
osity-0.554
 Converted-0.517
*,-0.506
®,-0.488
xa-0.486
Token political
Token ID1964
Feature activation+1.62e-01

Pos logit contributions
osity+0.044
 Converted+0.042
*,+0.042
®,+0.040
erved+0.040
Neg logit contributions
anmar-0.055
ngth-0.051
enhagen-0.051
romeda-0.049
merce-0.047
Token3
Token ID18
Feature activation+4.71e-02

Pos logit contributions
anmar+0.668
ngth+0.604
enhagen+0.602
romeda+0.595
agra+0.578
Neg logit contributions
osity-0.402
 Converted-0.364
*,-0.353
®,-0.341
erved-0.341
Token {
Token ID1391
Feature activation-5.14e-02

Pos logit contributions
osity+0.144
 Converted+0.134
*,+0.130
erved+0.127
®,+0.127
Neg logit contributions
anmar-0.161
ngth-0.143
enhagen-0.142
romeda-0.140
agra-0.135
Token(
Token ID7
Feature activation-2.56e-01

Pos logit contributions
anmar+0.197
ngth+0.175
romeda+0.174
enhagen+0.173
agra+0.166
Neg logit contributions
osity-0.145
 Converted-0.134
*,-0.132
xa-0.128
erved-0.126
Token1
Token ID16
Feature activation-1.58e-01

Pos logit contributions
anmar+0.987
ngth+0.879
enhagen+0.878
romeda+0.858
agra+0.836
Neg logit contributions
osity-0.691
*,-0.645
 Converted-0.640
xa-0.624
erved-0.600
Tokens
Token ID82
Feature activation-1.49e-01

Pos logit contributions
anmar+0.632
ngth+0.575
enhagen+0.566
romeda+0.549
agra+0.548
Neg logit contributions
osity-0.404
*,-0.377
 Converted-0.370
xa-0.358
®,-0.354
Token)}
Token ID38165
Feature activation-5.81e-01

Pos logit contributions
anmar+0.596
enhagen+0.541
ngth+0.533
romeda+0.523
agra+0.511
Neg logit contributions
osity-0.382
 Converted-0.347
*,-0.347
xa-0.332
erved-0.331
Token Q
Token ID1195
Feature activation-3.35e-02

Pos logit contributions
anmar+2.290
ngth+2.064
enhagen+2.024
romeda+2.016
kefeller+1.959
Neg logit contributions
osity-1.539
 Converted-1.446
*,-1.421
xa-1.350
®,-1.334
Tokenxf
Token ID26152
Feature activation-1.42e-03

Pos logit contributions
anmar+0.132
ngth+0.118
enhagen+0.117
romeda+0.116
kefeller+0.114
Neg logit contributions
osity-0.089
*,-0.081
 Converted-0.081
xa-0.081
erved-0.078
Token7
Token ID22
Feature activation-2.36e-02

Pos logit contributions
anmar+0.005
ngth+0.005
enhagen+0.004
romeda+0.004
merce+0.004
Neg logit contributions
osity-0.004
*,-0.004
 Converted-0.004
xa-0.004
®,-0.004
Token {
Token ID1391
Feature activation-2.19e-02

Pos logit contributions
anmar+0.103
ngth+0.092
enhagen+0.091
romeda+0.088
htaking+0.085
Neg logit contributions
osity-0.053
 Converted-0.052
*,-0.052
xa-0.051
®,-0.049
Token(
Token ID7
Feature activation-3.33e-01

Pos logit contributions
anmar+0.088
ngth+0.080
enhagen+0.078
romeda+0.078
merce+0.076
Neg logit contributions
osity-0.057
 Converted-0.053
*,-0.052
xa-0.051
erved-0.049
Tokens
Token ID82
Feature activation+1.02e-01

Pos logit contributions
anmar+0.198
enhagen+0.180
romeda+0.179
ngth+0.177
agra+0.173
Neg logit contributions
osity-0.113
*,-0.103
 Converted-0.100
®,-0.098
erved-0.095
Token tongue
Token ID11880
Feature activation-7.13e-02

Pos logit contributions
osity+0.287
*,+0.269
 Converted+0.256
®,+0.255
erved+0.250
Neg logit contributions
anmar-0.374
enhagen-0.341
romeda-0.341
ngth-0.332
kefeller-0.331
Token,
Token ID11
Feature activation-1.02e-01

Pos logit contributions
anmar+0.306
enhagen+0.276
romeda+0.275
ngth+0.271
merce+0.264
Neg logit contributions
osity-0.166
*,-0.155
 Converted-0.147
®,-0.143
erved-0.137
Token lips
Token ID11914
Feature activation-1.65e-01

Pos logit contributions
anmar+0.400
enhagen+0.360
ngth+0.360
romeda+0.357
kefeller+0.342
Neg logit contributions
osity-0.268
*,-0.248
 Converted-0.243
®,-0.234
 REPL-0.229
Token,
Token ID11
Feature activation-4.24e-02

Pos logit contributions
anmar+0.636
romeda+0.569
enhagen+0.569
ngth+0.561
agra+0.544
Neg logit contributions
osity-0.446
*,-0.421
 Converted-0.404
®,-0.398
erved-0.386
Token jaw
Token ID19218
Feature activation-5.71e-01

Pos logit contributions
anmar+0.166
ngth+0.149
enhagen+0.148
romeda+0.148
merce+0.142
Neg logit contributions
osity-0.113
*,-0.105
 Converted-0.101
®,-0.099
xa-0.098
Token and
Token ID290
Feature activation-6.72e-02

Pos logit contributions
anmar+2.166
enhagen+1.936
romeda+1.928
ngth+1.921
agra+1.842
Neg logit contributions
osity-1.594
*,-1.463
 Converted-1.431
®,-1.398
xa-1.364
Token l
Token ID300
Feature activation-1.20e-01

Pos logit contributions
anmar+0.235
ngth+0.207
enhagen+0.207
romeda+0.201
kefeller+0.196
Neg logit contributions
osity-0.207
*,-0.197
 Converted-0.190
xa-0.185
®,-0.185
Tokenaryn
Token ID38621
Feature activation-2.35e-01

Pos logit contributions
anmar+0.273
enhagen+0.233
ngth+0.226
romeda+0.217
merce+0.217
Neg logit contributions
osity-0.520
*,-0.487
itor-0.478
xa-0.472
erved-0.471
Tokenx
Token ID87
Feature activation+3.30e-03

Pos logit contributions
anmar+1.200
enhagen+1.099
romeda+1.098
ngth+1.085
agra+1.062
Neg logit contributions
osity-0.367
xa-0.295
*,-0.292
 Converted-0.281
®,-0.268
Token.
Token ID13
Feature activation-1.61e-02

Pos logit contributions
osity+0.007
*,+0.007
 Converted+0.006
®,+0.006
erved+0.006
Neg logit contributions
anmar-0.014
romeda-0.013
enhagen-0.013
ngth-0.013
agra-0.013
Token This
Token ID770
Feature activation+1.26e-01

Pos logit contributions
osity+0.207
 Converted+0.203
*,+0.196
®,+0.189
 REPL+0.186
Neg logit contributions
anmar-0.292
enhagen-0.258
ngth-0.257
romeda-0.252
merce-0.247
Token little
Token ID1310
Feature activation-1.38e-02

Pos logit contributions
osity+0.375
*,+0.352
 Converted+0.350
®,+0.336
 REPL+0.334
Neg logit contributions
anmar-0.448
ngth-0.403
enhagen-0.394
romeda-0.389
kefeller-0.379
Token speaker
Token ID10834
Feature activation+3.34e-02

Pos logit contributions
anmar+0.053
ngth+0.048
enhagen+0.047
romeda+0.046
agra+0.045
Neg logit contributions
osity-0.038
 Converted-0.035
*,-0.034
 REPL-0.033
®,-0.033
Token is
Token ID318
Feature activation+6.21e-02

Pos logit contributions
osity+0.097
*,+0.092
 Converted+0.089
®,+0.087
 REPL+0.086
Neg logit contributions
anmar-0.124
ngth-0.108
enhagen-0.108
romeda-0.106
merce-0.102
Token a
Token ID257
Feature activation+3.05e-02

Pos logit contributions
osity+0.179
*,+0.170
 Converted+0.169
®,+0.161
erved+0.159
Neg logit contributions
anmar-0.225
ngth-0.201
enhagen-0.200
romeda-0.196
kefeller-0.190
Token landmark
Token ID20533
Feature activation+4.17e-01

Pos logit contributions
osity+0.086
 Converted+0.082
*,+0.081
®,+0.078
 REPL+0.077
Neg logit contributions
anmar-0.111
enhagen-0.100
ngth-0.099
romeda-0.097
agra-0.095
Token of
Token ID286
Feature activation-2.76e-02

Pos logit contributions
osity+1.180
*,+1.141
 Converted+1.092
®,+1.083
 REPL+1.058
Neg logit contributions
anmar-1.547
enhagen-1.401
ngth-1.343
romeda-1.337
agra-1.303
Token a
Token ID257
Feature activation+3.41e-02

Pos logit contributions
anmar+0.096
ngth+0.085
romeda+0.083
enhagen+0.083
agra+0.081
Neg logit contributions
osity-0.085
 Converted-0.079
*,-0.079
®,-0.076
erved-0.075
Token convention
Token ID9831
Feature activation+2.11e-01

Pos logit contributions
osity+0.096
 Converted+0.091
*,+0.091
®,+0.087
 REPL+0.086
Neg logit contributions
anmar-0.125
enhagen-0.111
ngth-0.109
romeda-0.108
agra-0.106
Token-
Token ID12
Feature activation-1.05e-02

Pos logit contributions
osity+0.498
*,+0.442
 Converted+0.428
®,+0.421
erved+0.413
Neg logit contributions
anmar-0.896
enhagen-0.807
ngth-0.802
romeda-0.794
agra-0.766
Tokensh
Token ID1477
Feature activation-8.09e-02

Pos logit contributions
anmar+0.039
enhagen+0.035
ngth+0.035
romeda+0.035
kefeller+0.033
Neg logit contributions
osity-0.030
*,-0.027
 Converted-0.027
xa-0.026
erved-0.026
Token Book
Token ID4897
Feature activation-6.74e-02

Pos logit contributions
anmar+0.939
ngth+0.850
enhagen+0.839
romeda+0.834
merce+0.799
Neg logit contributions
osity-0.674
 Converted-0.618
*,-0.600
®,-0.578
erved-0.575
Token-
Token ID12
Feature activation+3.56e-01

Pos logit contributions
anmar+0.260
ngth+0.235
enhagen+0.232
romeda+0.231
merce+0.222
Neg logit contributions
osity-0.182
 Converted-0.166
*,-0.161
erved-0.155
®,-0.154
TokenM
Token ID44
Feature activation+1.50e-01

Pos logit contributions
osity+0.936
 Converted+0.860
*,+0.832
xa+0.809
erved+0.794
Neg logit contributions
anmar-1.402
ngth-1.282
enhagen-1.273
romeda-1.249
merce-1.225
Tokenunch
Token ID3316
Feature activation-1.52e-01

Pos logit contributions
osity+0.424
*,+0.377
 Converted+0.370
erved+0.368
itor+0.360
Neg logit contributions
anmar-0.553
ngth-0.507
enhagen-0.501
romeda-0.490
merce-0.477
Tokenkins
Token ID5331
Feature activation-1.18e-01

Pos logit contributions
anmar+0.576
ngth+0.519
enhagen+0.518
romeda+0.508
merce+0.494
Neg logit contributions
osity-0.425
 Converted-0.389
*,-0.376
erved-0.366
®,-0.363
Token-
Token ID12
Feature activation+3.62e-01

Pos logit contributions
anmar+0.444
ngth+0.402
enhagen+0.400
romeda+0.394
merce+0.379
Neg logit contributions
osity-0.331
 Converted-0.305
*,-0.294
®,-0.285
erved-0.284
TokenJ
Token ID41
Feature activation-4.23e-04

Pos logit contributions
osity+0.954
 Converted+0.875
*,+0.849
xa+0.825
erved+0.809
Neg logit contributions
anmar-1.422
ngth-1.302
enhagen-1.293
romeda-1.270
merce-1.243
Tokenill
Token ID359
Feature activation+2.59e-01

Pos logit contributions
anmar+0.002
enhagen+0.001
ngth+0.001
romeda+0.001
merce+0.001
Neg logit contributions
osity-0.001
*,-0.001
 Converted-0.001
erved-0.001
xa-0.001
Token Nick
Token ID8047
Feature activation+4.51e-03

Pos logit contributions
osity+0.751
 Converted+0.687
*,+0.670
erved+0.646
xa+0.639
Neg logit contributions
anmar-0.942
ngth-0.852
enhagen-0.845
romeda-0.828
merce-0.813
Tokenall
Token ID439
Feature activation+7.84e-02

Pos logit contributions
osity+0.013
 Converted+0.013
*,+0.012
erved+0.012
xa+0.012
Neg logit contributions
anmar-0.016
ngth-0.014
romeda-0.014
enhagen-0.014
merce-0.014
Tokenini
Token ID5362
Feature activation+1.77e-01

Pos logit contributions
osity+0.218
 Converted+0.197
*,+0.192
xa+0.187
®,+0.184
Neg logit contributions
anmar-0.296
ngth-0.269
enhagen-0.264
romeda-0.263
merce-0.259
Token,
Token ID11
Feature activation+9.41e-02

Pos logit contributions
anmar+0.777
ngth+0.687
enhagen+0.686
romeda+0.675
agra+0.650
Neg logit contributions
osity-0.689
 Converted-0.639
*,-0.622
erved-0.606
®,-0.604
Token Science
Token ID5800
Feature activation+2.32e-01

Pos logit contributions
osity+0.254
 Converted+0.238
*,+0.232
®,+0.219
xa+0.218
Neg logit contributions
anmar-0.368
ngth-0.338
romeda-0.330
enhagen-0.321
agra-0.310
Token and
Token ID290
Feature activation+5.13e-02

Pos logit contributions
osity+0.630
*,+0.591
 Converted+0.572
®,+0.570
xa+0.544
Neg logit contributions
anmar-0.898
romeda-0.808
ngth-0.794
enhagen-0.786
agra-0.746
Token Related
Token ID19809
Feature activation+4.22e-03

Pos logit contributions
osity+0.122
 Converted+0.112
*,+0.110
erved+0.103
®,+0.100
Neg logit contributions
anmar-0.224
ngth-0.199
romeda-0.198
enhagen-0.193
merce-0.189
Token Ag
Token ID2449
Feature activation+4.08e-02

Pos logit contributions
osity+0.015
 Converted+0.014
*,+0.014
®,+0.013
itor+0.013
Neg logit contributions
anmar-0.013
enhagen-0.012
ngth-0.011
romeda-0.011
agra-0.011
Tokenencies
Token ID3976
Feature activation+4.52e-01

Pos logit contributions
osity+0.111
 Converted+0.100
*,+0.100
itor+0.096
xa+0.095
Neg logit contributions
anmar-0.155
ngth-0.140
enhagen-0.140
romeda-0.139
agra-0.133
Token subcommittee
Token ID47014
Feature activation-1.69e-01

Pos logit contributions
osity+0.915
*,+0.865
 Converted+0.851
®,+0.802
erved+0.797
Neg logit contributions
anmar-1.992
ngth-1.849
enhagen-1.814
romeda-1.802
merce-1.750
Token of
Token ID286
Feature activation-1.03e-01

Pos logit contributions
anmar+0.593
ngth+0.527
enhagen+0.524
romeda+0.522
agra+0.493
Neg logit contributions
osity-0.511
*,-0.489
 Converted-0.471
®,-0.459
xa-0.449
Token the
Token ID262
Feature activation-7.96e-02

Pos logit contributions
anmar+0.311
ngth+0.275
romeda+0.270
enhagen+0.268
merce+0.248
Neg logit contributions
osity-0.360
*,-0.336
 Converted-0.335
®,-0.327
itor-0.325
Token Senate
Token ID3845
Feature activation-1.52e-01

Pos logit contributions
anmar+0.274
ngth+0.252
enhagen+0.242
romeda+0.240
merce+0.227
Neg logit contributions
osity-0.242
 Converted-0.229
*,-0.224
®,-0.219
 REPL-0.218
Token Appropriations
Token ID37552
Feature activation-9.42e-02

Pos logit contributions
anmar+0.625
ngth+0.564
enhagen+0.557
romeda+0.554
agra+0.529
Neg logit contributions
osity-0.375
 Converted-0.346
*,-0.344
®,-0.327
erved-0.323
Token smaller
Token ID4833
Feature activation-3.84e-02

Pos logit contributions
anmar+0.559
enhagen+0.499
ngth+0.498
romeda+0.479
kefeller+0.477
Neg logit contributions
osity-0.413
 Converted-0.392
*,-0.390
xa-0.367
®,-0.367
Token than
Token ID621
Feature activation+4.88e-02

Pos logit contributions
anmar+0.147
enhagen+0.132
ngth+0.132
kefeller+0.126
agra+0.126
Neg logit contributions
osity-0.104
*,-0.098
 Converted-0.097
®,-0.092
xa-0.091
Token adequate
Token ID12872
Feature activation+1.68e-01

Pos logit contributions
osity+0.155
*,+0.150
 Converted+0.149
®,+0.144
 REPL+0.141
Neg logit contributions
anmar-0.162
ngth-0.144
enhagen-0.142
kefeller-0.138
agra-0.134
Token for
Token ID329
Feature activation+5.84e-02

Pos logit contributions
osity+0.474
*,+0.451
 Converted+0.439
®,+0.422
xa+0.416
Neg logit contributions
anmar-0.618
ngth-0.553
enhagen-0.550
kefeller-0.531
romeda-0.530
Token larger
Token ID4025
Feature activation+1.63e-03

Pos logit contributions
osity+0.172
*,+0.163
 Converted+0.162
®,+0.155
xa+0.155
Neg logit contributions
anmar-0.206
ngth-0.186
enhagen-0.183
kefeller-0.175
romeda-0.175
Token prints
Token ID20842
Feature activation+3.91e-01

Pos logit contributions
osity+0.004
*,+0.004
 Converted+0.004
®,+0.004
xa+0.004
Neg logit contributions
anmar-0.006
ngth-0.006
enhagen-0.006
romeda-0.005
agra-0.005
Token.
Token ID13
Feature activation+6.03e-02

Pos logit contributions
osity+1.039
*,+1.006
 Converted+0.953
®,+0.926
erved+0.912
Neg logit contributions
anmar-1.504
enhagen-1.330
ngth-1.327
romeda-1.323
kefeller-1.288
Token This
Token ID770
Feature activation+7.90e-02

Pos logit contributions
osity+0.155
 Converted+0.153
*,+0.147
 REPL+0.139
®,+0.139
Neg logit contributions
anmar-0.238
ngth-0.215
enhagen-0.213
kefeller-0.206
romeda-0.206
Token makes
Token ID1838
Feature activation+6.54e-02

Pos logit contributions
osity+0.243
*,+0.229
 Converted+0.226
®,+0.215
 REPL+0.214
Neg logit contributions
anmar-0.275
ngth-0.245
enhagen-0.237
romeda-0.233
merce-0.228
Token for
Token ID329
Feature activation+6.39e-02

Pos logit contributions
osity+0.199
*,+0.189
 Converted+0.188
®,+0.180
xa+0.179
Neg logit contributions
anmar-0.222
ngth-0.200
enhagen-0.195
romeda-0.190
kefeller-0.188
Token easy
Token ID2562
Feature activation+1.20e-01

Pos logit contributions
osity+0.202
*,+0.190
 Converted+0.189
xa+0.181
®,+0.180
Neg logit contributions
anmar-0.212
ngth-0.186
enhagen-0.185
romeda-0.184
kefeller-0.178
Token is
Token ID318
Feature activation-8.05e-02

Pos logit contributions
osity+0.574
*,+0.539
 Converted+0.529
®,+0.504
 REPL+0.503
Neg logit contributions
anmar-0.696
enhagen-0.613
ngth-0.610
romeda-0.601
merce-0.586
Token done
Token ID1760
Feature activation+7.67e-02

Pos logit contributions
anmar+0.306
enhagen+0.276
ngth+0.274
romeda+0.264
merce+0.259
Neg logit contributions
osity-0.222
 Converted-0.208
*,-0.205
 REPL-0.195
erved-0.193
Token at
Token ID379
Feature activation+4.31e-03

Pos logit contributions
osity+0.212
*,+0.201
 Converted+0.198
 REPL+0.188
®,+0.188
Neg logit contributions
anmar-0.288
enhagen-0.257
ngth-0.257
romeda-0.251
merce-0.243
Token the
Token ID262
Feature activation+5.90e-02

Pos logit contributions
osity+0.013
 Converted+0.012
*,+0.012
 REPL+0.012
xa+0.012
Neg logit contributions
anmar-0.015
ngth-0.013
enhagen-0.013
romeda-0.013
merce-0.013
Token subt
Token ID13284
Feature activation+3.32e-01

Pos logit contributions
osity+0.187
 Converted+0.177
*,+0.174
 REPL+0.170
®,+0.166
Neg logit contributions
anmar-0.199
ngth-0.176
enhagen-0.173
romeda-0.170
agra-0.165
Tokenape
Token ID1758
Feature activation+3.72e-01

Pos logit contributions
osity+0.781
*,+0.675
 Converted+0.673
erved+0.656
xa+0.649
Neg logit contributions
anmar-1.407
ngth-1.250
romeda-1.239
enhagen-1.232
kefeller-1.189
Token level
Token ID1241
Feature activation+5.54e-03

Pos logit contributions
osity+1.096
*,+0.985
 Converted+0.982
 REPL+0.942
®,+0.934
Neg logit contributions
anmar-1.384
enhagen-1.207
ngth-1.192
romeda-1.190
agra-1.151
Token.
Token ID13
Feature activation+6.83e-03

Pos logit contributions
osity+0.016
*,+0.014
 Converted+0.014
®,+0.014
 REPL+0.013
Neg logit contributions
anmar-0.021
ngth-0.018
enhagen-0.018
romeda-0.018
agra-0.018
Token Don
Token ID2094
Feature activation-4.85e-02

Pos logit contributions
osity+0.019
 Converted+0.018
*,+0.017
 REPL+0.017
®,+0.017
Neg logit contributions
anmar-0.026
enhagen-0.024
ngth-0.024
romeda-0.023
merce-0.023
Token
Token ID447
Feature activation+1.43e-01

Pos logit contributions
anmar+0.270
enhagen+0.251
ngth+0.251
romeda+0.247
merce+0.241
Neg logit contributions
osity-0.049
 Converted-0.039
*,-0.038
erved-0.033
®,-0.033
Token
Token ID247
Feature activation+2.21e-02

Pos logit contributions
osity+0.386
 Converted+0.354
*,+0.354
®,+0.341
erved+0.340
Neg logit contributions
anmar-0.548
ngth-0.496
enhagen-0.495
romeda-0.484
kefeller-0.466
Token and
Token ID290
Feature activation+8.28e-02

Pos logit contributions
osity+0.138
*,+0.131
 Converted+0.124
®,+0.120
xa+0.118
Neg logit contributions
anmar-0.185
ngth-0.165
enhagen-0.164
romeda-0.164
agra-0.157
Token against
Token ID1028
Feature activation+5.45e-02

Pos logit contributions
osity+0.244
*,+0.226
 Converted+0.224
xa+0.216
®,+0.215
Neg logit contributions
anmar-0.296
ngth-0.268
enhagen-0.264
romeda-0.249
agra-0.246
Token the
Token ID262
Feature activation+4.59e-02

Pos logit contributions
osity+0.158
*,+0.145
 Converted+0.144
xa+0.141
 REPL+0.139
Neg logit contributions
anmar-0.196
ngth-0.181
enhagen-0.175
romeda-0.171
agra-0.164
Token capital
Token ID3139
Feature activation-6.67e-02

Pos logit contributions
osity+0.131
 Converted+0.119
*,+0.118
xa+0.115
 REPL+0.115
Neg logit contributions
anmar-0.168
ngth-0.154
enhagen-0.149
romeda-0.147
agra-0.141
Token.
Token ID13
Feature activation-4.36e-02

Pos logit contributions
anmar+0.259
enhagen+0.229
romeda+0.227
ngth+0.225
agra+0.220
Neg logit contributions
osity-0.184
*,-0.170
 Converted-0.163
®,-0.157
itor-0.154
Token There
Token ID1318
Feature activation+2.66e-02

Pos logit contributions
anmar+0.173
ngth+0.157
enhagen+0.157
merce+0.151
romeda+0.151
Neg logit contributions
osity-0.113
 Converted-0.110
*,-0.106
xa-0.100
®,-0.100
Token must
Token ID1276
Feature activation-2.70e-02

Pos logit contributions
osity+0.084
*,+0.080
 Converted+0.078
®,+0.075
erved+0.075
Neg logit contributions
anmar-0.090
enhagen-0.079
ngth-0.078
romeda-0.077
kefeller-0.074
Token be
Token ID307
Feature activation+2.09e-02

Pos logit contributions
anmar+0.078
ngth+0.066
enhagen+0.066
romeda+0.065
agra+0.062
Neg logit contributions
osity-0.098
*,-0.092
 Converted-0.091
xa-0.089
®,-0.089
Token a
Token ID257
Feature activation-3.86e-02

Pos logit contributions
osity+0.063
*,+0.059
 Converted+0.058
xa+0.056
 REPL+0.055
Neg logit contributions
anmar-0.074
ngth-0.065
enhagen-0.065
romeda-0.064
merce-0.062
Token special
Token ID2041
Feature activation+1.75e-02

Pos logit contributions
anmar+0.144
enhagen+0.128
ngth+0.128
romeda+0.126
merce+0.121
Neg logit contributions
osity-0.107
*,-0.101
 Converted-0.100
 REPL-0.096
®,-0.095
Token mention
Token ID3068
Feature activation+1.07e-01

Pos logit contributions
osity+0.050
*,+0.046
 Converted+0.045
 REPL+0.044
xa+0.044
Neg logit contributions
anmar-0.064
ngth-0.058
romeda-0.058
enhagen-0.058
merce-0.055
Token the
Token ID262
Feature activation+8.55e-02

Pos logit contributions
osity+0.116
 Converted+0.110
*,+0.109
erved+0.104
xa+0.103
Neg logit contributions
anmar-0.128
ngth-0.119
enhagen-0.114
romeda-0.114
merce-0.109
Token Russian
Token ID3394
Feature activation+1.21e-01

Pos logit contributions
osity+0.271
*,+0.253
 Converted+0.253
 REPL+0.242
xa+0.242
Neg logit contributions
anmar-0.282
ngth-0.269
romeda-0.251
enhagen-0.250
merce-0.240
Token-
Token ID12
Feature activation+9.93e-02

Pos logit contributions
osity+0.389
*,+0.363
 Converted+0.361
xa+0.350
 REPL+0.349
Neg logit contributions
anmar-0.393
ngth-0.363
enhagen-0.351
romeda-0.346
kefeller-0.334
TokenUk
Token ID28425
Feature activation+1.36e-01

Pos logit contributions
osity+0.275
*,+0.249
 Converted+0.246
erved+0.239
xa+0.238
Neg logit contributions
anmar-0.369
ngth-0.347
romeda-0.336
enhagen-0.335
kefeller-0.330
Tokenrain
Token ID3201
Feature activation-2.20e-01

Pos logit contributions
osity+0.417
 Converted+0.380
*,+0.375
erved+0.369
itor+0.362
Neg logit contributions
anmar-0.462
enhagen-0.431
ngth-0.428
romeda-0.415
kefeller-0.407
Tokenian
Token ID666
Feature activation+1.54e-01

Pos logit contributions
anmar+0.714
ngth+0.677
enhagen+0.653
romeda+0.634
kefeller+0.625
Neg logit contributions
osity-0.707
 Converted-0.655
erved-0.642
*,-0.641
xa-0.629
Token border
Token ID4865
Feature activation+2.69e-01

Pos logit contributions
osity+0.450
 Converted+0.418
*,+0.417
erved+0.401
xa+0.400
Neg logit contributions
anmar-0.537
ngth-0.516
enhagen-0.486
romeda-0.475
kefeller-0.467
Token,
Token ID11
Feature activation-2.39e-02

Pos logit contributions
osity+0.760
*,+0.723
 Converted+0.702
®,+0.677
erved+0.665
Neg logit contributions
anmar-0.971
ngth-0.899
romeda-0.873
enhagen-0.859
agra-0.833
Token says
Token ID1139
Feature activation-3.69e-02

Pos logit contributions
anmar+0.090
ngth+0.085
romeda+0.081
enhagen+0.080
merce+0.079
Neg logit contributions
osity-0.064
*,-0.060
 Converted-0.059
 REPL-0.055
xa-0.055
Token the
Token ID262
Feature activation+3.01e-02

Pos logit contributions
anmar+0.129
ngth+0.117
enhagen+0.115
romeda+0.111
agra+0.108
Neg logit contributions
osity-0.113
*,-0.105
 Converted-0.104
 REPL-0.099
erved-0.098
Token underlying
Token ID10238
Feature activation+1.63e-01

Pos logit contributions
osity+0.087
*,+0.080
 Converted+0.080
 REPL+0.076
xa+0.075
Neg logit contributions
anmar-0.110
ngth-0.102
enhagen-0.098
romeda-0.097
merce-0.093
Token,
Token ID11
Feature activation-3.76e-03

Pos logit contributions
osity+0.451
*,+0.430
®,+0.406
 Converted+0.397
 REPL+0.388
Neg logit contributions
anmar-0.616
enhagen-0.544
romeda-0.541
ngth-0.538
kefeller-0.523
Token
Token ID447
Feature activation+5.54e-02

Pos logit contributions
anmar+0.019
enhagen+0.017
ngth+0.017
romeda+0.017
kefeller+0.017
Neg logit contributions
osity-0.006
*,-0.005
 Converted-0.005
®,-0.005
 REPL-0.004
Token
Token ID251
Feature activation+1.96e-02

Pos logit contributions
osity+0.145
*,+0.135
 Converted+0.133
xa+0.126
®,+0.126
Neg logit contributions
anmar-0.218
ngth-0.196
enhagen-0.195
romeda-0.190
agra-0.187
Token he
Token ID339
Feature activation-3.01e-02

Pos logit contributions
osity+0.055
*,+0.051
 Converted+0.050
®,+0.049
erved+0.049
Neg logit contributions
anmar-0.073
ngth-0.064
romeda-0.064
enhagen-0.064
agra-0.061
Token said
Token ID531
Feature activation+6.39e-02

Pos logit contributions
anmar+0.116
ngth+0.106
romeda+0.102
enhagen+0.101
agra+0.099
Neg logit contributions
osity-0.080
*,-0.074
 Converted-0.073
erved-0.070
xa-0.070
Token without
Token ID1231
Feature activation+1.48e-01

Pos logit contributions
osity+0.187
*,+0.173
 Converted+0.172
®,+0.165
erved+0.164
Neg logit contributions
anmar-0.230
ngth-0.205
enhagen-0.203
romeda-0.201
agra-0.194
Token hesitation
Token ID29592
Feature activation-2.77e-03

Pos logit contributions
osity+0.418
*,+0.380
 Converted+0.371
 REPL+0.363
®,+0.362
Neg logit contributions
anmar-0.555
ngth-0.504
enhagen-0.488
romeda-0.486
kefeller-0.478
Token.
Token ID13
Feature activation+4.87e-02

Pos logit contributions
anmar+0.010
ngth+0.009
enhagen+0.009
romeda+0.009
agra+0.008
Neg logit contributions
osity-0.008
*,-0.007
 Converted-0.007
®,-0.007
erved-0.007
Token
Token ID564
Feature activation+1.06e-01

Pos logit contributions
osity+0.125
 Converted+0.117
*,+0.116
®,+0.110
 REPL+0.110
Neg logit contributions
anmar-0.195
enhagen-0.173
ngth-0.172
romeda-0.171
kefeller-0.166
Token
Token ID250
Feature activation-5.80e-02

Pos logit contributions
osity+0.288
 Converted+0.269
*,+0.268
xa+0.255
®,+0.253
Neg logit contributions
anmar-0.405
ngth-0.365
enhagen-0.365
romeda-0.354
agra-0.346
TokenI
Token ID40
Feature activation-5.02e-03

Pos logit contributions
anmar+0.235
enhagen+0.211
ngth+0.211
romeda+0.210
merce+0.200
Neg logit contributions
osity-0.146
*,-0.133
 Converted-0.132
xa-0.127
®,-0.127
Token to
Token ID284
Feature activation+1.90e-01

Pos logit contributions
osity+0.094
*,+0.086
 Converted+0.085
®,+0.082
 REPL+0.081
Neg logit contributions
anmar-0.132
enhagen-0.119
ngth-0.118
romeda-0.116
kefeller-0.113
Token deliver
Token ID5203
Feature activation-1.98e-02

Pos logit contributions
osity+0.576
 Converted+0.531
*,+0.531
 REPL+0.517
®,+0.511
Neg logit contributions
anmar-0.660
enhagen-0.598
ngth-0.591
romeda-0.579
agra-0.565
Token positive
Token ID3967
Feature activation+1.94e-01

Pos logit contributions
anmar+0.073
ngth+0.066
enhagen+0.066
romeda+0.064
kefeller+0.063
Neg logit contributions
osity-0.057
*,-0.052
 Converted-0.052
®,-0.050
 REPL-0.050
Token messages
Token ID6218
Feature activation-9.91e-02

Pos logit contributions
osity+0.566
*,+0.517
®,+0.494
 Converted+0.493
 REPL+0.490
Neg logit contributions
anmar-0.708
ngth-0.670
enhagen-0.653
romeda-0.640
kefeller-0.620
Token to
Token ID284
Feature activation+3.65e-02

Pos logit contributions
anmar+0.361
ngth+0.324
enhagen+0.323
romeda+0.318
kefeller+0.310
Neg logit contributions
osity-0.289
*,-0.271
 Converted-0.268
®,-0.259
erved-0.252
Token teammates
Token ID13107
Feature activation+5.11e-02

Pos logit contributions
osity+0.111
 Converted+0.103
*,+0.101
®,+0.098
 REPL+0.097
Neg logit contributions
anmar-0.127
ngth-0.117
enhagen-0.112
romeda-0.111
kefeller-0.109
Token,
Token ID11
Feature activation+1.62e-02

Pos logit contributions
osity+0.138
*,+0.133
 Converted+0.129
®,+0.127
erved+0.122
Neg logit contributions
anmar-0.194
ngth-0.176
enhagen-0.173
romeda-0.171
kefeller-0.171
Token opponents
Token ID7691
Feature activation-6.10e-02

Pos logit contributions
osity+0.053
*,+0.049
 Converted+0.049
®,+0.048
 REPL+0.047
Neg logit contributions
anmar-0.053
ngth-0.048
enhagen-0.047
romeda-0.046
kefeller-0.045
Token,
Token ID11
Feature activation+3.45e-02

Pos logit contributions
anmar+0.233
ngth+0.208
romeda+0.206
enhagen+0.205
agra+0.199
Neg logit contributions
osity-0.166
*,-0.155
 Converted-0.151
®,-0.149
erved-0.144
Token coaches
Token ID11070
Feature activation-1.49e-01

Pos logit contributions
osity+0.105
*,+0.096
 Converted+0.095
®,+0.093
 REPL+0.091
Neg logit contributions
anmar-0.121
ngth-0.111
romeda-0.107
enhagen-0.107
agra-0.103
Token,
Token ID11
Feature activation+1.39e-02

Pos logit contributions
anmar+0.554
ngth+0.496
romeda+0.489
enhagen+0.488
agra+0.471
Neg logit contributions
osity-0.415
*,-0.390
 Converted-0.382
®,-0.374
erved-0.363
Token About
Token ID7994
Feature activation+8.71e-02

Pos logit contributions
anmar+0.024
enhagen+0.021
ngth+0.021
romeda+0.021
kefeller+0.020
Neg logit contributions
osity-0.019
*,-0.018
 Converted-0.017
®,-0.017
itor-0.016
Token.
Token ID13
Feature activation-6.25e-03

Pos logit contributions
osity+0.243
 Converted+0.231
*,+0.231
®,+0.220
erved+0.212
Neg logit contributions
anmar-0.331
enhagen-0.293
ngth-0.293
romeda-0.282
kefeller-0.276
Token
Token ID198
Feature activation-2.90e-02

Pos logit contributions
anmar+0.019
ngth+0.017
enhagen+0.017
romeda+0.016
agra+0.016
Neg logit contributions
osity-0.022
 Converted-0.020
*,-0.020
®,-0.019
erved-0.019
Token
Token ID198
Feature activation-3.36e-02

Pos logit contributions
anmar+0.099
ngth+0.089
enhagen+0.087
romeda+0.084
merce+0.082
Neg logit contributions
osity-0.094
 Converted-0.088
*,-0.088
xa-0.085
®,-0.084
Token
Token ID447
Feature activation+2.07e-02

Pos logit contributions
anmar+0.181
enhagen+0.168
ngth+0.167
romeda+0.167
kefeller+0.161
Neg logit contributions
osity-0.041
*,-0.032
 Converted-0.031
®,-0.029
xa-0.028
Token
Token ID250
Feature activation-1.71e-03

Pos logit contributions
osity+0.059
 Converted+0.054
*,+0.053
®,+0.051
xa+0.051
Neg logit contributions
anmar-0.076
enhagen-0.068
ngth-0.068
romeda-0.067
agra-0.065
TokenD
Token ID35
Feature activation+4.20e-02

Pos logit contributions
anmar+0.007
enhagen+0.006
romeda+0.006
ngth+0.006
kefeller+0.006
Neg logit contributions
osity-0.004
 Converted-0.004
*,-0.004
®,-0.004
xa-0.004
Tokenance
Token ID590
Feature activation+4.20e-02

Pos logit contributions
osity+0.100
*,+0.090
 Converted+0.089
erved+0.088
itor+0.085
Neg logit contributions
anmar-0.172
enhagen-0.160
ngth-0.159
romeda-0.154
kefeller-0.151
Token quietly
Token ID12703
Feature activation+1.47e-01

Pos logit contributions
osity+0.124
*,+0.115
 Converted+0.114
®,+0.110
erved+0.108
Neg logit contributions
anmar-0.154
romeda-0.136
enhagen-0.135
ngth-0.134
kefeller-0.129
Token;
Token ID26
Feature activation+4.97e-02

Pos logit contributions
osity+0.389
*,+0.378
 Converted+0.359
®,+0.348
erved+0.339
Neg logit contributions
anmar-0.577
ngth-0.510
romeda-0.505
enhagen-0.504
kefeller-0.487
Token do
Token ID466
Feature activation+8.62e-03

Pos logit contributions
osity+0.147
*,+0.137
 Converted+0.132
®,+0.129
xa+0.127
Neg logit contributions
anmar-0.180
enhagen-0.161
ngth-0.158
romeda-0.157
agra-0.153
Token refresh
Token ID14976
Feature activation-4.58e-02

Pos logit contributions
osity+0.018
 Converted+0.017
*,+0.016
®,+0.016
 REPL+0.016
Neg logit contributions
anmar-0.022
ngth-0.020
enhagen-0.020
romeda-0.020
agra-0.019
Token rate
Token ID2494
Feature activation-2.05e-01

Pos logit contributions
anmar+0.213
ngth+0.198
romeda+0.195
enhagen+0.195
kefeller+0.189
Neg logit contributions
osity-0.086
 Converted-0.076
*,-0.076
®,-0.069
xa-0.068
Token and
Token ID290
Feature activation-5.04e-02

Pos logit contributions
anmar+0.768
ngth+0.692
enhagen+0.681
romeda+0.672
agra+0.655
Neg logit contributions
osity-0.580
*,-0.534
 Converted-0.532
®,-0.505
xa-0.500
Token fast
Token ID3049
Feature activation-3.29e-02

Pos logit contributions
anmar+0.182
ngth+0.162
enhagen+0.160
kefeller+0.154
merce+0.154
Neg logit contributions
osity-0.149
 Converted-0.140
*,-0.137
erved-0.131
 REPL-0.131
Token response
Token ID2882
Feature activation+1.01e-01

Pos logit contributions
anmar+0.128
ngth+0.117
enhagen+0.115
romeda+0.115
agra+0.112
Neg logit contributions
osity-0.086
 Converted-0.080
*,-0.078
xa-0.074
erved-0.074
Token time
Token ID640
Feature activation-5.57e-02

Pos logit contributions
osity+0.228
*,+0.205
 Converted+0.198
®,+0.187
xa+0.186
Neg logit contributions
anmar-0.430
ngth-0.399
enhagen-0.392
romeda-0.386
merce-0.377
Token TN
Token ID29025
Feature activation+3.87e-02

Pos logit contributions
anmar+0.209
ngth+0.190
enhagen+0.186
romeda+0.184
agra+0.179
Neg logit contributions
osity-0.156
*,-0.145
 Converted-0.142
®,-0.135
xa-0.134
Token Film
Token ID13741
Feature activation+3.28e-02

Pos logit contributions
osity+0.088
 Converted+0.080
*,+0.079
®,+0.076
 REPL+0.075
Neg logit contributions
anmar-0.162
ngth-0.151
enhagen-0.149
romeda-0.147
merce-0.142
Token panel
Token ID6103
Feature activation-1.65e-01

Pos logit contributions
osity+0.091
 Converted+0.085
*,+0.083
®,+0.080
 REPL+0.079
Neg logit contributions
anmar-0.124
ngth-0.113
enhagen-0.111
romeda-0.108
kefeller-0.106
Token.
Token ID13
Feature activation+4.20e-03

Pos logit contributions
anmar+0.623
ngth+0.569
enhagen+0.557
romeda+0.547
kefeller+0.532
Neg logit contributions
osity-0.455
*,-0.420
 Converted-0.414
®,-0.392
erved-0.391
Token This
Token ID770
Feature activation+7.55e-02

Pos logit contributions
osity+0.011
 Converted+0.011
*,+0.010
 REPL+0.010
xa+0.009
Neg logit contributions
anmar-0.017
ngth-0.015
enhagen-0.015
merce-0.015
romeda-0.015
Token United
Token ID1578
Feature activation-1.36e-01

Pos logit contributions
anmar+0.251
ngth+0.224
romeda+0.219
enhagen+0.215
merce+0.213
Neg logit contributions
osity-0.229
 Converted-0.218
*,-0.212
®,-0.206
xa-0.203
Token States
Token ID1829
Feature activation-7.75e-02

Pos logit contributions
anmar+0.548
enhagen+0.491
ngth+0.491
romeda+0.486
merce+0.470
Neg logit contributions
osity-0.357
 Converted-0.328
*,-0.319
®,-0.305
erved-0.304
Token Basketball
Token ID25911
Feature activation-1.35e-01

Pos logit contributions
anmar+0.289
enhagen+0.260
ngth+0.256
romeda+0.255
merce+0.247
Neg logit contributions
osity-0.222
 Converted-0.212
*,-0.207
®,-0.198
erved-0.195
Token Writers
Token ID37732
Feature activation-1.28e-01

Pos logit contributions
anmar+0.598
ngth+0.551
enhagen+0.550
romeda+0.545
agra+0.529
Neg logit contributions
osity-0.280
 Converted-0.259
*,-0.251
®,-0.240
erved-0.234
Token Association
Token ID5396
Feature activation-1.24e-01

Pos logit contributions
anmar+0.505
ngth+0.457
enhagen+0.453
romeda+0.452
agra+0.436
Neg logit contributions
osity-0.333
 Converted-0.312
*,-0.311
®,-0.302
erved-0.287
Token (
Token ID357
Feature activation-1.40e-01

Pos logit contributions
anmar+0.479
ngth+0.429
romeda+0.427
enhagen+0.423
agra+0.412
Neg logit contributions
osity-0.329
*,-0.310
 Converted-0.305
®,-0.301
erved-0.284
TokenUSB
Token ID27155
Feature activation+3.05e-02

Pos logit contributions
anmar+0.421
romeda+0.373
ngth+0.371
enhagen+0.366
kefeller+0.345
Neg logit contributions
osity-0.493
 Converted-0.461
*,-0.457
xa-0.444
®,-0.442
TokenWA
Token ID15543
Feature activation-1.14e-02

Pos logit contributions
osity+0.063
 Converted+0.055
*,+0.055
®,+0.053
xa+0.053
Neg logit contributions
anmar-0.135
ngth-0.125
romeda-0.125
enhagen-0.124
merce-0.119
Token).[
Token ID42669
Feature activation-1.43e-01

Pos logit contributions
anmar+0.043
ngth+0.039
romeda+0.038
enhagen+0.038
agra+0.037
Neg logit contributions
osity-0.031
 Converted-0.029
*,-0.029
®,-0.028
erved-0.027
Token119
Token ID16315
Feature activation+1.44e-01

Pos logit contributions
anmar+0.494
ngth+0.438
enhagen+0.436
romeda+0.430
agra+0.417
Neg logit contributions
osity-0.439
 Converted-0.407
*,-0.400
®,-0.390
xa-0.388
Token]
Token ID60
Feature activation-3.09e-02

Pos logit contributions
osity+0.457
 Converted+0.425
*,+0.415
®,+0.405
erved+0.403
Neg logit contributions
anmar-0.478
ngth-0.422
enhagen-0.421
romeda-0.414
agra-0.397
Token few
Token ID1178
Feature activation-1.89e-01

Pos logit contributions
anmar+0.324
enhagen+0.291
ngth+0.290
romeda+0.286
kefeller+0.278
Neg logit contributions
osity-0.211
*,-0.204
 Converted-0.198
erved-0.190
®,-0.190
Token weeks
Token ID2745
Feature activation-1.24e-01

Pos logit contributions
anmar+0.851
ngth+0.789
romeda+0.778
enhagen+0.776
kefeller+0.748
Neg logit contributions
osity-0.376
*,-0.339
 Converted-0.329
xa-0.317
®,-0.313
Token before
Token ID878
Feature activation+9.61e-03

Pos logit contributions
anmar+0.496
romeda+0.448
ngth+0.446
enhagen+0.438
kefeller+0.435
Neg logit contributions
osity-0.306
*,-0.293
 Converted-0.281
®,-0.274
erved-0.272
Token her
Token ID607
Feature activation-1.22e-01

Pos logit contributions
osity+0.028
*,+0.027
 Converted+0.027
®,+0.026
 REPL+0.025
Neg logit contributions
anmar-0.034
ngth-0.031
enhagen-0.031
romeda-0.030
agra-0.029
Token film
Token ID2646
Feature activation-1.87e-01

Pos logit contributions
anmar+0.442
ngth+0.409
enhagen+0.398
romeda+0.390
merce+0.383
Neg logit contributions
osity-0.348
 Converted-0.322
*,-0.320
®,-0.308
 REPL-0.306
Token wraps
Token ID27521
Feature activation-2.43e-01

Pos logit contributions
anmar+0.731
ngth+0.658
enhagen+0.650
romeda+0.637
kefeller+0.616
Neg logit contributions
osity-0.509
*,-0.463
 Converted-0.456
®,-0.441
 REPL-0.433
Token (
Token ID357
Feature activation-1.07e-02

Pos logit contributions
anmar+0.897
ngth+0.803
enhagen+0.787
romeda+0.780
merce+0.759
Neg logit contributions
osity-0.695
*,-0.662
®,-0.633
 Converted-0.631
xa-0.613
Token
Token ID447
Feature activation+2.11e-01

Pos logit contributions
anmar+0.041
ngth+0.038
enhagen+0.038
romeda+0.037
kefeller+0.036
Neg logit contributions
osity-0.028
*,-0.026
 Converted-0.025
®,-0.025
xa-0.024
Token
Token ID250
Feature activation-3.84e-02

Pos logit contributions
osity+0.587
*,+0.548
 Converted+0.538
®,+0.511
erved+0.511
Neg logit contributions
anmar-0.788
enhagen-0.716
ngth-0.707
romeda-0.700
kefeller-0.683
TokenI
Token ID40
Feature activation+1.17e-02

Pos logit contributions
anmar+0.147
ngth+0.136
enhagen+0.135
romeda+0.132
kefeller+0.128
Neg logit contributions
osity-0.102
*,-0.093
 Converted-0.092
xa-0.088
®,-0.088
Token [
Token ID685
Feature activation-1.80e-02

Pos logit contributions
osity+0.032
*,+0.030
 Converted+0.029
®,+0.028
erved+0.028
Neg logit contributions
anmar-0.043
enhagen-0.039
ngth-0.039
romeda-0.039
kefeller-0.038
Token 9
Token ID860
Feature activation-7.96e-02

Pos logit contributions
anmar+0.155
ngth+0.147
romeda+0.137
enhagen+0.137
merce+0.135
Neg logit contributions
osity-0.123
 Converted-0.117
*,-0.115
xa-0.110
®,-0.109
Token-
Token ID12
Feature activation-6.15e-02

Pos logit contributions
anmar+0.323
ngth+0.304
enhagen+0.296
romeda+0.290
agra+0.286
Neg logit contributions
osity-0.192
*,-0.176
 Converted-0.171
erved-0.169
®,-0.167
Tokenhour
Token ID9769
Feature activation-3.52e-02

Pos logit contributions
anmar+0.234
ngth+0.218
enhagen+0.213
romeda+0.208
agra+0.206
Neg logit contributions
osity-0.164
*,-0.149
 Converted-0.147
erved-0.145
xa-0.144
Token Turkey
Token ID7137
Feature activation+5.98e-02

Pos logit contributions
anmar+0.120
ngth+0.111
enhagen+0.108
romeda+0.107
agra+0.103
Neg logit contributions
osity-0.108
*,-0.099
 Converted-0.098
xa-0.095
®,-0.095
Token-
Token ID12
Feature activation-1.37e-02

Pos logit contributions
osity+0.162
*,+0.155
 Converted+0.152
®,+0.149
xa+0.144
Neg logit contributions
anmar-0.224
ngth-0.207
enhagen-0.201
romeda-0.195
merce-0.190
Tokenbacked
Token ID17078
Feature activation-3.16e-02

Pos logit contributions
anmar+0.052
ngth+0.050
enhagen+0.048
romeda+0.047
kefeller+0.046
Neg logit contributions
osity-0.036
*,-0.033
 Converted-0.033
erved-0.032
xa-0.031
Token offensive
Token ID5859
Feature activation-3.17e-02

Pos logit contributions
anmar+0.114
ngth+0.107
enhagen+0.103
romeda+0.100
kefeller+0.099
Neg logit contributions
osity-0.088
*,-0.083
 Converted-0.083
®,-0.079
xa-0.078
Token.
Token ID13
Feature activation-8.30e-02

Pos logit contributions
anmar+0.113
ngth+0.103
enhagen+0.102
romeda+0.100
agra+0.098
Neg logit contributions
osity-0.091
*,-0.088
 Converted-0.085
®,-0.082
erved-0.080
Token AFP
Token ID8916
Feature activation+1.77e-02

Pos logit contributions
anmar+0.311
ngth+0.280
enhagen+0.277
romeda+0.272
merce+0.269
Neg logit contributions
osity-0.230
 Converted-0.225
*,-0.219
®,-0.208
 REPL-0.205
Token has
Token ID468
Feature activation-9.35e-03

Pos logit contributions
osity+0.043
*,+0.041
 Converted+0.040
®,+0.038
xa+0.037
Neg logit contributions
anmar-0.072
ngth-0.065
enhagen-0.063
romeda-0.063
agra-0.062
Token more
Token ID517
Feature activation+1.11e-02

Pos logit contributions
anmar+0.035
ngth+0.032
enhagen+0.031
romeda+0.031
agra+0.030
Neg logit contributions
osity-0.025
 Converted-0.024
*,-0.024
erved-0.022
®,-0.022
Token on
Token ID319
Feature activation-2.53e-02

Pos logit contributions
anmar+0.297
ngth+0.266
enhagen+0.264
romeda+0.261
merce+0.253
Neg logit contributions
osity-0.259
 Converted-0.251
*,-0.249
®,-0.235
 REPL-0.232
Token the
Token ID262
Feature activation+4.55e-02

Pos logit contributions
anmar+0.080
ngth+0.070
enhagen+0.070
romeda+0.070
merce+0.067
Neg logit contributions
osity-0.083
 Converted-0.080
*,-0.077
erved-0.077
®,-0.075
Token island
Token ID7022
Feature activation+2.09e-01

Pos logit contributions
osity+0.137
 Converted+0.130
*,+0.127
®,+0.123
xa+0.122
Neg logit contributions
anmar-0.156
ngth-0.144
enhagen-0.139
romeda-0.138
merce-0.135
Token of
Token ID286
Feature activation+5.58e-02

Pos logit contributions
osity+0.592
*,+0.549
 Converted+0.546
®,+0.524
erved+0.518
Neg logit contributions
anmar-0.752
enhagen-0.679
ngth-0.671
romeda-0.671
merce-0.658
Token K
Token ID509
Feature activation-3.56e-02

Pos logit contributions
osity+0.165
 Converted+0.155
*,+0.152
erved+0.146
®,+0.146
Neg logit contributions
anmar-0.196
enhagen-0.178
ngth-0.176
romeda-0.172
merce-0.170
Tokenail
Token ID603
Feature activation-1.49e-01

Pos logit contributions
anmar+0.139
enhagen+0.125
romeda+0.124
ngth+0.123
merce+0.118
Neg logit contributions
osity-0.094
*,-0.083
 Converted-0.082
erved-0.081
xa-0.081
Tokeno
Token ID78
Feature activation+8.38e-02

Pos logit contributions
anmar+0.575
ngth+0.522
romeda+0.522
enhagen+0.516
merce+0.500
Neg logit contributions
osity-0.402
*,-0.359
 Converted-0.353
xa-0.348
®,-0.346
Token beside
Token ID13970
Feature activation+5.73e-03

Pos logit contributions
osity+0.252
*,+0.235
 Converted+0.232
®,+0.225
xa+0.220
Neg logit contributions
anmar-0.292
enhagen-0.263
ngth-0.262
romeda-0.261
merce-0.255
Token the
Token ID262
Feature activation+3.41e-04

Pos logit contributions
osity+0.018
 Converted+0.018
*,+0.017
®,+0.017
erved+0.017
Neg logit contributions
anmar-0.019
enhagen-0.016
romeda-0.016
ngth-0.016
merce-0.016
Token old
Token ID1468
Feature activation-1.85e-01

Pos logit contributions
osity+0.001
 Converted+0.001
*,+0.001
®,+0.001
 REPL+0.001
Neg logit contributions
anmar-0.001
ngth-0.001
enhagen-0.001
romeda-0.001
merce-0.001
Token town
Token ID3240
Feature activation-6.79e-02

Pos logit contributions
anmar+0.646
ngth+0.586
romeda+0.575
enhagen+0.571
merce+0.555
Neg logit contributions
osity-0.546
 Converted-0.512
*,-0.503
®,-0.487
xa-0.484
Token turn
Token ID1210
Feature activation-1.41e-01

Pos logit contributions
anmar+0.103
ngth+0.094
enhagen+0.092
romeda+0.090
merce+0.087
Neg logit contributions
osity-0.093
 Converted-0.087
*,-0.086
erved-0.083
xa-0.083
Token is
Token ID318
Feature activation-7.99e-02

Pos logit contributions
anmar+0.531
enhagen+0.467
ngth+0.464
romeda+0.460
merce+0.441
Neg logit contributions
osity-0.400
*,-0.375
 Converted-0.369
®,-0.355
xa-0.352
Token positioned
Token ID19378
Feature activation-5.67e-02

Pos logit contributions
anmar+0.333
ngth+0.305
enhagen+0.299
romeda+0.294
merce+0.286
Neg logit contributions
osity-0.190
 Converted-0.176
*,-0.172
erved-0.164
xa-0.162
Token against
Token ID1028
Feature activation-1.88e-02

Pos logit contributions
anmar+0.214
ngth+0.192
enhagen+0.190
romeda+0.186
merce+0.181
Neg logit contributions
osity-0.157
 Converted-0.147
*,-0.146
®,-0.137
erved-0.137
Token the
Token ID262
Feature activation+1.86e-02

Pos logit contributions
anmar+0.060
ngth+0.053
enhagen+0.052
romeda+0.051
merce+0.049
Neg logit contributions
osity-0.063
 Converted-0.058
*,-0.058
erved-0.056
®,-0.055
Token UTC
Token ID18119
Feature activation-4.33e-01

Pos logit contributions
osity+0.054
 Converted+0.050
*,+0.049
erved+0.047
 REPL+0.047
Neg logit contributions
anmar-0.068
ngth-0.061
enhagen-0.060
romeda-0.059
merce-0.057
Token,
Token ID11
Feature activation-4.73e-02

Pos logit contributions
anmar+1.611
ngth+1.446
enhagen+1.441
romeda+1.417
agra+1.372
Neg logit contributions
osity-1.226
*,-1.131
 Converted-1.128
®,-1.085
xa-1.054
Token even
Token ID772
Feature activation-1.18e-01

Pos logit contributions
anmar+0.185
ngth+0.168
enhagen+0.167
romeda+0.161
merce+0.157
Neg logit contributions
osity-0.124
 Converted-0.116
*,-0.114
®,-0.109
 REPL-0.107
Token while
Token ID981
Feature activation-6.95e-02

Pos logit contributions
anmar+0.470
ngth+0.427
enhagen+0.417
romeda+0.405
merce+0.398
Neg logit contributions
osity-0.306
 Converted-0.283
*,-0.279
xa-0.265
®,-0.262
Token their
Token ID511
Feature activation-1.29e-01

Pos logit contributions
anmar+0.251
ngth+0.226
enhagen+0.226
romeda+0.218
agra+0.212
Neg logit contributions
osity-0.202
 Converted-0.188
*,-0.186
 REPL-0.177
®,-0.176
Token local
Token ID1957
Feature activation-1.33e-01

Pos logit contributions
anmar+0.466
ngth+0.426
enhagen+0.421
romeda+0.413
merce+0.398
Neg logit contributions
osity-0.375
 Converted-0.347
*,-0.344
 REPL-0.329
®,-0.328
Token6
Token ID21
Feature activation+1.40e-01

Pos logit contributions
osity+0.436
xa+0.412
*,+0.404
 Converted+0.401
®,+0.385
Neg logit contributions
anmar-0.516
ngth-0.466
enhagen-0.462
romeda-0.446
merce-0.429
Token {
Token ID1391
Feature activation+1.19e-01

Pos logit contributions
osity+0.315
 Converted+0.289
*,+0.279
xa+0.269
®,+0.265
Neg logit contributions
anmar-0.604
ngth-0.549
enhagen-0.546
romeda-0.533
merce-0.521
Token(
Token ID7
Feature activation-1.04e-01

Pos logit contributions
osity+0.285
 Converted+0.260
*,+0.258
xa+0.248
®,+0.242
Neg logit contributions
anmar-0.501
ngth-0.461
enhagen-0.455
romeda-0.443
merce-0.439
Token4
Token ID19
Feature activation-1.95e-02

Pos logit contributions
anmar+0.397
ngth+0.359
enhagen+0.355
romeda+0.348
merce+0.341
Neg logit contributions
osity-0.285
 Converted-0.267
*,-0.263
xa-0.254
®,-0.249
Tokens
Token ID82
Feature activation+3.60e-02

Pos logit contributions
anmar+0.070
ngth+0.062
enhagen+0.062
romeda+0.061
agra+0.059
Neg logit contributions
osity-0.057
 Converted-0.052
*,-0.051
®,-0.049
erved-0.049
Token)}
Token ID38165
Feature activation-4.29e-01

Pos logit contributions
osity+0.074
 Converted+0.066
*,+0.064
xa+0.061
®,+0.061
Neg logit contributions
anmar-0.160
ngth-0.146
enhagen-0.146
romeda-0.143
agra-0.140
Token 60
Token ID3126
Feature activation+1.22e-01

Pos logit contributions
anmar+1.533
ngth+1.369
enhagen+1.361
romeda+1.346
agra+1.295
Neg logit contributions
osity-1.242
 Converted-1.144
*,-1.115
®,-1.085
erved-1.083
Token.
Token ID13
Feature activation+2.55e-02

Pos logit contributions
osity+0.340
 Converted+0.319
*,+0.314
xa+0.305
®,+0.297
Neg logit contributions
anmar-0.471
ngth-0.428
enhagen-0.421
romeda-0.407
merce-0.404
Token e
Token ID304
Feature activation+1.71e-01

Pos logit contributions
osity+0.072
 Converted+0.069
*,+0.067
xa+0.066
®,+0.064
Neg logit contributions
anmar-0.095
ngth-0.085
enhagen-0.085
romeda-0.082
merce-0.080
Token7
Token ID22
Feature activation-2.76e-02

Pos logit contributions
osity+0.502
xa+0.480
*,+0.463
 Converted+0.461
erved+0.442
Neg logit contributions
anmar-0.620
enhagen-0.558
ngth-0.558
romeda-0.542
merce-0.514
Token {
Token ID1391
Feature activation+4.96e-02

Pos logit contributions
anmar+0.121
ngth+0.109
enhagen+0.109
romeda+0.107
agra+0.103
Neg logit contributions
osity-0.061
 Converted-0.056
*,-0.054
xa-0.053
®,-0.051
Token stress
Token ID5503
Feature activation-1.96e-01

Pos logit contributions
osity+0.052
*,+0.048
 Converted+0.048
 REPL+0.047
®,+0.046
Neg logit contributions
anmar-0.056
enhagen-0.050
ngth-0.050
romeda-0.048
agra-0.046
Token even
Token ID772
Feature activation-3.50e-02

Pos logit contributions
anmar+0.695
ngth+0.620
enhagen+0.607
romeda+0.597
agra+0.587
Neg logit contributions
osity-0.598
 Converted-0.550
*,-0.550
®,-0.527
xa-0.523
Token just
Token ID655
Feature activation-5.53e-02

Pos logit contributions
anmar+0.126
ngth+0.113
enhagen+0.109
romeda+0.107
agra+0.104
Neg logit contributions
osity-0.105
 Converted-0.097
*,-0.097
erved-0.091
®,-0.091
Token his
Token ID465
Feature activation+3.26e-02

Pos logit contributions
anmar+0.196
ngth+0.174
enhagen+0.172
romeda+0.165
agra+0.162
Neg logit contributions
osity-0.167
*,-0.156
 Converted-0.156
erved-0.148
®,-0.147
Token first
Token ID717
Feature activation-1.13e-01

Pos logit contributions
osity+0.096
*,+0.089
 Converted+0.088
 REPL+0.085
®,+0.084
Neg logit contributions
anmar-0.116
ngth-0.105
romeda-0.103
enhagen-0.103
kefeller-0.101
Token warm
Token ID5814
Feature activation-4.75e-01

Pos logit contributions
anmar+0.406
ngth+0.363
enhagen+0.361
romeda+0.360
kefeller+0.346
Neg logit contributions
osity-0.331
*,-0.309
 Converted-0.306
®,-0.292
 REPL-0.291
Token-
Token ID12
Feature activation-5.82e-02

Pos logit contributions
anmar+1.784
ngth+1.660
enhagen+1.593
romeda+1.592
agra+1.550
Neg logit contributions
osity-1.291
*,-1.189
 Converted-1.167
®,-1.143
xa-1.131
Tokenup
Token ID929
Feature activation-5.52e-02

Pos logit contributions
anmar+0.249
ngth+0.233
merce+0.226
enhagen+0.225
romeda+0.223
Neg logit contributions
osity-0.126
*,-0.115
 Converted-0.111
®,-0.107
erved-0.106
Token pitches
Token ID22421
Feature activation-1.31e-01

Pos logit contributions
anmar+0.208
ngth+0.188
enhagen+0.186
romeda+0.185
kefeller+0.180
Neg logit contributions
osity-0.151
*,-0.145
 Converted-0.141
®,-0.136
 REPL-0.133
Token as
Token ID355
Feature activation+2.09e-03

Pos logit contributions
anmar+0.480
ngth+0.433
romeda+0.426
enhagen+0.424
kefeller+0.408
Neg logit contributions
osity-0.377
*,-0.358
 Converted-0.351
®,-0.335
erved-0.334
Token a
Token ID257
Feature activation+9.44e-02

Pos logit contributions
osity+0.007
 Converted+0.006
*,+0.006
erved+0.006
®,+0.006
Neg logit contributions
anmar-0.007
ngth-0.006
enhagen-0.006
romeda-0.006
merce-0.006
Token approved
Token ID6325
Feature activation-1.91e-01

Pos logit contributions
anmar+0.164
ngth+0.153
enhagen+0.149
romeda+0.145
agra+0.142
Neg logit contributions
osity-0.114
 Converted-0.107
*,-0.105
 REPL-0.100
erved-0.099
Token the
Token ID262
Feature activation+1.26e-02

Pos logit contributions
anmar+0.622
ngth+0.571
enhagen+0.561
romeda+0.546
kefeller+0.513
Neg logit contributions
osity-0.613
 Converted-0.569
*,-0.566
®,-0.543
 REPL-0.542
Token ill
Token ID2801
Feature activation+4.56e-02

Pos logit contributions
osity+0.036
 Converted+0.033
*,+0.032
®,+0.032
 REPL+0.031
Neg logit contributions
anmar-0.045
ngth-0.043
enhagen-0.041
romeda-0.040
merce-0.039
Token-
Token ID12
Feature activation+1.85e-02

Pos logit contributions
osity+0.133
 Converted+0.118
*,+0.116
xa+0.114
erved+0.114
Neg logit contributions
anmar-0.165
ngth-0.156
enhagen-0.146
merce-0.144
kefeller-0.143
Tokencon
Token ID1102
Feature activation+5.45e-02

Pos logit contributions
osity+0.052
 Converted+0.048
*,+0.047
erved+0.046
xa+0.045
Neg logit contributions
anmar-0.069
ngth-0.064
romeda-0.061
enhagen-0.061
kefeller-0.059
Tokenceived
Token ID6471
Feature activation-4.24e-01

Pos logit contributions
osity+0.123
erved+0.116
 Converted+0.112
xa+0.108
*,+0.107
Neg logit contributions
anmar-0.231
ngth-0.214
romeda-0.210
enhagen-0.210
merce-0.200
Token hostage
Token ID23229
Feature activation+4.94e-02

Pos logit contributions
anmar+1.512
ngth+1.401
enhagen+1.370
romeda+1.339
agra+1.282
Neg logit contributions
osity-1.243
 Converted-1.146
*,-1.126
®,-1.089
 REPL-1.078
Token rescue
Token ID9992
Feature activation-5.08e-02

Pos logit contributions
osity+0.136
 Converted+0.126
*,+0.124
®,+0.119
 REPL+0.118
Neg logit contributions
anmar-0.187
ngth-0.171
enhagen-0.167
romeda-0.164
kefeller-0.158
Token mission
Token ID4365
Feature activation-2.48e-01

Pos logit contributions
anmar+0.199
ngth+0.182
enhagen+0.181
romeda+0.176
agra+0.170
Neg logit contributions
osity-0.132
 Converted-0.122
*,-0.121
®,-0.114
xa-0.113
Token that
Token ID326
Feature activation-4.81e-02

Pos logit contributions
anmar+0.870
ngth+0.788
enhagen+0.782
romeda+0.765
agra+0.740
Neg logit contributions
osity-0.745
 Converted-0.692
*,-0.687
®,-0.652
erved-0.647
Token ended
Token ID4444
Feature activation+1.03e-02

Pos logit contributions
anmar+0.185
ngth+0.170
enhagen+0.166
romeda+0.163
agra+0.157
Neg logit contributions
osity-0.127
 Converted-0.120
*,-0.118
erved-0.113
xa-0.112
Token said
Token ID531
Feature activation+2.14e-01

Pos logit contributions
osity+0.264
*,+0.240
 Converted+0.236
erved+0.228
xa+0.228
Neg logit contributions
anmar-0.372
ngth-0.341
romeda-0.330
enhagen-0.328
agra-0.315
Token,
Token ID11
Feature activation-4.25e-02

Pos logit contributions
osity+0.596
*,+0.553
 Converted+0.540
xa+0.518
erved+0.516
Neg logit contributions
anmar-0.798
ngth-0.720
enhagen-0.710
romeda-0.706
agra-0.678
Token according
Token ID1864
Feature activation-1.74e-01

Pos logit contributions
anmar+0.171
ngth+0.156
enhagen+0.154
romeda+0.150
merce+0.146
Neg logit contributions
osity-0.107
*,-0.098
 Converted-0.097
erved-0.091
 REPL-0.090
Token to
Token ID284
Feature activation+2.49e-02

Pos logit contributions
anmar+0.589
ngth+0.525
enhagen+0.520
romeda+0.506
merce+0.490
Neg logit contributions
osity-0.546
 Converted-0.511
*,-0.500
xa-0.483
®,-0.483
Token the
Token ID262
Feature activation-7.62e-02

Pos logit contributions
osity+0.080
 Converted+0.074
*,+0.074
erved+0.071
xa+0.070
Neg logit contributions
anmar-0.081
ngth-0.073
enhagen-0.072
romeda-0.071
merce-0.069
Token Telegraph
Token ID21821
Feature activation-3.91e-01

Pos logit contributions
anmar+0.246
ngth+0.224
enhagen+0.217
romeda+0.214
merce+0.209
Neg logit contributions
osity-0.249
*,-0.229
 Converted-0.229
xa-0.221
 REPL-0.220
Token.
Token ID13
Feature activation-1.21e-02

Pos logit contributions
anmar+1.325
ngth+1.168
enhagen+1.166
romeda+1.151
agra+1.103
Neg logit contributions
osity-1.212
 Converted-1.128
*,-1.095
erved-1.070
®,-1.067
Token<|endoftext|>
Token ID50256
Feature activation+8.68e-02

Pos logit contributions
anmar+0.040
ngth+0.035
enhagen+0.035
romeda+0.034
agra+0.033
Neg logit contributions
osity-0.039
 Converted-0.036
*,-0.036
erved-0.035
xa-0.035
TokenAN
Token ID1565
Feature activation+5.60e-02

Pos logit contributions
osity+0.227
 Converted+0.207
*,+0.207
xa+0.199
®,+0.197
Neg logit contributions
anmar-0.340
ngth-0.313
enhagen-0.312
romeda-0.306
merce-0.293
TokenAL
Token ID1847
Feature activation+1.63e-01

Pos logit contributions
osity+0.142
 Converted+0.127
*,+0.124
 REPL+0.122
®,+0.121
Neg logit contributions
anmar-0.223
ngth-0.205
enhagen-0.202
romeda-0.200
kefeller-0.198
TokenYS
Token ID16309
Feature activation-1.60e-01

Pos logit contributions
osity+0.389
*,+0.354
 Converted+0.345
®,+0.345
 REPL+0.334
Neg logit contributions
anmar-0.686
ngth-0.646
romeda-0.616
enhagen-0.616
kefeller-0.601