TOP ACTIVATIONS
MAX = 2.047

ence , 8 , 333 - 354 . Google
Drawing . Solid Br ush ( [ System . Draw ing
From Ar gb ($ FC 2 [ 0 ], $ FC
but doctors said she risked severe infection and scar ring if
6 { ( 6 s )} 38 . N d 4
states , Ms . Set zer said .
) $ s z 2 = [ system . windows .
Se eker wrote : Cl arity Gaming will also
millionaires , Ms . Ole ch owski said .
x . x . x . 112 10 25 151 x
Boston College on January 3 ,[ 112 ] earning his fifth
# We ve Had Enough protester in Petersburg ,
Font Name , $ FS 2 ,[ System . Draw ing
E , DP 02 _ 00 64 E , DP 02
land remain Kenyan . In June 1962 , Ken y atta
accepted its presidency . In January 1962 he was elected un
ing . Rect angle F ( 0 , ($ s z
any Mode : Man aged Access Point : Not - Associated
203 x . x . x . 112 10 25 151
[ 0 ], $ FC 2 [ 1 ], $ FC

MIN ACTIVATIONS
MIN = -1.590

x . x . x . 99 10 88 350 x
ble Prime Minister Sh ri Narendra Modi has approved the
,[ 98 ] Sporting News ,[ 99 ] SB Nation ,[
Pick J AB arry Maryland 1 hour ago This election was
, and four panel ists voting in favour of a redesign
Golden State War riors (@ war riors ) September 24
11 : 50 AM ET Fri , 28 July 2017 |
Reserve and Western Front s .[ 30 ] On 10 October
paper towel - lined plate . Serve hot ! <|endoftext|> Image
[ UPDATE , 7 : 01 p . m .: CNN
everything ? Flag Flag Reply 27 Recommend
Recommend Share this comment on Facebook Share this comment on Twitter
make a living doing something you not only like doing ,
available since 16 July 2007 .[ 19 ] $
Sven s ka Te ater .[ 26 ] In
St Lucia from £ 1 , 8 29 all - in
x . x . x . 149 110 22 26 x
, died at 2 : 20 p . m . at
broccoli for a few minutes until fork - t ender .
racist . Flag Flag Reply 19 Recommend

INTERVAL 1.138 - 2.047
CONTAINS 0.011%

x . x . x . 138 11 30 277 x
Massachusetts were the Y aw key Center at Emmanuel College in
[ 1 ], $ FC 2 [ 2 ]) ) $
to subscribe to . Sign Up You will receive emails containing
the worst ne ­ go ­ ti ­ at ­ or

INTERVAL 0.228 - 1.138
CONTAINS 16.930%

king Xer xes sent his massive army across the stra it
Gentle men tried to record live -- first of all ,
golden child right now , but I ve also
be . Mal colm Grim ston , a nuclear
you do . Lyn n Rogers , Bi ologist

INTERVAL -0.681 - 0.228
CONTAINS 82.615%

costume were everywhere , anticipating an evening of trick or treating
). Gl ü ck learned much from Pl ath about how
the charity s obligations to the public during the
States is spir alling down into a basic indec ency and
but respecting them in their choice not to talk is more

INTERVAL -1.590 - -0.681
CONTAINS 0.444%

that if all the 63 , 511 coaches under operation are
the day a man was pronounced dead after he was shot
and Producer , DA VID SL ACK
own best selling Kindle book . We ll announce
racist . Flag Flag Reply 19 Recommend
Tokenence
Token ID594
Feature activation-4.94e-01

Pos logit contributions
 disag+0.737
Sah+0.692
Saharan+0.690
 pleas+0.680
ucket+0.675
Neg logit contributions
isphere-0.409
orth-0.402
л-0.389
arthed-0.370
cliffe-0.368
Token,
Token ID11
Feature activation-3.39e-01

Pos logit contributions
 disag+4.469
Sah+4.134
Saharan+4.113
 pleas+4.048
ucket+4.008
Neg logit contributions
isphere-3.931
orth-3.821
л-3.726
arthed-3.638
cliffe-3.565
Token 8
Token ID807
Feature activation-2.63e-01

Pos logit contributions
 disag+2.848
Sah+2.694
Saharan+2.633
 pleas+2.612
uffy+2.500
Neg logit contributions
isphere-2.952
orth-2.823
arthed-2.721
л-2.703
enza-2.646
Token,
Token ID11
Feature activation-2.20e-01

Pos logit contributions
 disag+2.487
Sah+2.309
Saharan+2.288
 pleas+2.264
ucket+2.238
Neg logit contributions
isphere-2.018
orth-1.988
л-1.924
arthed-1.861
cliffe-1.840
Token 333
Token ID23460
Feature activation+4.34e-01

Pos logit contributions
 disag+2.001
Sah+1.864
 pleas+1.828
Saharan+1.822
uffy+1.765
Neg logit contributions
isphere-1.777
orth-1.720
л-1.649
arthed-1.625
cliffe-1.604
Token -
Token ID532
Feature activation+2.05e+00

Pos logit contributions
orth+2.181
isphere+2.150
л+2.097
cliffe+1.922
arthed+1.912
Neg logit contributions
 disag-5.233
Saharan-4.829
Sah-4.828
ucket-4.793
 pleas-4.778
Token 354
Token ID46752
Feature activation+2.37e-02

Pos logit contributions
л+9.257
orth+8.767
irc+8.186
 Ost+8.141
herer+8.118
Neg logit contributions
 disag-20.019
Saharan-18.889
ucket-18.328
uffy-18.248
Sah-17.738
Token.
Token ID764
Feature activation-6.14e-02

Pos logit contributions
isphere+0.179
orth+0.176
л+0.170
arthed+0.165
enza+0.163
Neg logit contributions
 disag-0.227
Sah-0.212
Saharan-0.210
 pleas-0.208
ucket-0.205
Token
Token ID198
Feature activation-1.73e-01

Pos logit contributions
 disag+0.612
Sah+0.579
Saharan+0.574
 pleas+0.569
ucket+0.556
Neg logit contributions
isphere-0.440
orth-0.425
л-0.411
arthed-0.399
enza-0.393
Token
Token ID198
Feature activation-5.70e-01

Pos logit contributions
 disag+1.630
Sah+1.563
Saharan+1.547
 pleas+1.533
uffy+1.478
Neg logit contributions
isphere-1.335
orth-1.265
л-1.229
arthed-1.212
enza-1.191
TokenGoogle
Token ID11708
Feature activation-7.42e-01

Pos logit contributions
Sah+4.119
Saharan+3.855
 disag+3.692
 pleas+3.523
ucket+3.437
Neg logit contributions
isphere-5.659
 liner-5.392
arthed-5.299
orth-5.271
enza-5.203
Token Drawing
Token ID40027
Feature activation+5.92e-03

Pos logit contributions
isphere+3.258
orth+3.257
л+3.105
arthed+2.950
cliffe+2.940
Neg logit contributions
 disag-5.893
Sah-5.520
Saharan-5.478
ucket-5.395
 pleas-5.372
Token.
Token ID13
Feature activation+3.03e-01

Pos logit contributions
isphere+0.046
orth+0.045
л+0.043
arthed+0.042
enza+0.042
Neg logit contributions
 disag-0.056
Sah-0.052
Saharan-0.052
 pleas-0.051
ucket-0.050
TokenSolid
Token ID46933
Feature activation+4.53e-01

Pos logit contributions
isphere+2.178
orth+2.171
л+2.101
arthed+2.006
cliffe+1.987
Neg logit contributions
 disag-3.012
Sah-2.768
Saharan-2.747
 pleas-2.734
ucket-2.704
TokenBr
Token ID9414
Feature activation-6.61e-01

Pos logit contributions
orth+2.942
isphere+2.869
л+2.844
cliffe+2.675
arthed+2.651
Neg logit contributions
 disag-4.847
 pleas-4.343
ucket-4.340
Sah-4.324
Saharan-4.301
Tokenush
Token ID1530
Feature activation+3.79e-01

Pos logit contributions
 disag+3.953
Saharan+3.919
Sah+3.867
uffy+3.784
ucket+3.765
Neg logit contributions
isphere-6.860
л-6.577
orth-6.485
arthed-6.407
 liner-6.373
Token (
Token ID357
Feature activation+1.66e+00

Pos logit contributions
orth+3.112
isphere+3.080
л+3.045
cliffe+2.893
arthed+2.885
Neg logit contributions
 disag-3.359
Sah-3.037
Saharan-3.017
 pleas-3.002
ucket-2.964
Token [
Token ID685
Feature activation+6.20e-01

Pos logit contributions
orth+5.684
irc+5.157
л+5.147
isphere+4.929
cliffe+4.262
Neg logit contributions
 disag-18.840
Saharan-17.911
 pleas-17.783
Sah-17.764
ucket-17.365
TokenSystem
Token ID11964
Feature activation-2.81e-02

Pos logit contributions
orth+2.567
isphere+2.468
л+2.431
cliffe+2.160
arthed+2.155
Neg logit contributions
 disag-8.014
 pleas-7.387
ucket-7.375
Saharan-7.337
Sah-7.307
Token.
Token ID13
Feature activation+3.80e-02

Pos logit contributions
 disag+0.261
Sah+0.246
Saharan+0.243
 pleas+0.241
ucket+0.236
Neg logit contributions
isphere-0.220
orth-0.214
л-0.207
arthed-0.202
enza-0.200
TokenDraw
Token ID25302
Feature activation+3.40e-01

Pos logit contributions
isphere+0.283
orth+0.276
л+0.266
arthed+0.259
enza+0.257
Neg logit contributions
 disag-0.368
Sah-0.349
Saharan-0.345
 pleas-0.339
ucket-0.333
Tokening
Token ID278
Feature activation+1.73e-01

Pos logit contributions
orth+2.099
isphere+2.077
л+1.995
cliffe+1.888
arthed+1.880
Neg logit contributions
 disag-3.741
Sah-3.455
Saharan-3.429
 pleas-3.412
ucket-3.377
TokenFrom
Token ID4863
Feature activation+9.69e-01

Pos logit contributions
orth+4.623
л+4.518
isphere+3.955
irc+3.882
arthed+3.747
Neg logit contributions
 disag-13.318
ucket-11.965
 srf-11.846
uffy-11.716
 uncons-11.640
TokenAr
Token ID3163
Feature activation+2.40e-01

Pos logit contributions
orth+3.819
л+3.481
isphere+3.255
irc+3.193
cliffe+3.113
Neg logit contributions
 disag-12.723
ucket-11.536
 pleas-11.398
uffy-11.309
 uncons-11.137
Tokengb
Token ID22296
Feature activation+6.95e-01

Pos logit contributions
isphere+1.876
orth+1.854
л+1.788
cliffe+1.723
arthed+1.714
Neg logit contributions
 disag-2.240
Sah-2.064
 pleas-2.026
Saharan-2.024
ucket-1.994
Token($
Token ID16763
Feature activation+3.64e-01

Pos logit contributions
orth+4.161
л+4.029
isphere+3.893
cliffe+3.724
enza+3.630
Neg logit contributions
 disag-7.788
Sah-7.056
 pleas-6.970
Saharan-6.947
ucket-6.917
TokenFC
Token ID4851
Feature activation+5.12e-01

Pos logit contributions
orth+3.407
isphere+3.405
л+3.296
arthed+3.192
cliffe+3.171
Neg logit contributions
 disag-2.831
Sah-2.545
 pleas-2.509
Saharan-2.508
ucket-2.455
Token2
Token ID17
Feature activation+1.62e+00

Pos logit contributions
isphere+3.666
orth+3.640
л+3.616
arthed+3.382
irc+3.352
Neg logit contributions
 disag-4.962
Sah-4.509
 pleas-4.440
Saharan-4.438
ucket-4.355
Token[
Token ID58
Feature activation+5.99e-01

Pos logit contributions
orth+4.693
irc+4.310
л+4.256
isphere+3.720
herer+3.294
Neg logit contributions
 disag-20.362
 srf-19.468
Sah-18.603
 uncons-18.588
Saharan-18.561
Token0
Token ID15
Feature activation+1.69e-01

Pos logit contributions
orth+3.870
isphere+3.747
л+3.671
arthed+3.510
cliffe+3.435
Neg logit contributions
 disag-6.340
Sah-5.833
 pleas-5.730
Saharan-5.686
 uncons-5.539
Token],
Token ID4357
Feature activation+9.51e-01

Pos logit contributions
isphere+1.237
orth+1.227
л+1.189
arthed+1.141
cliffe+1.130
Neg logit contributions
 disag-1.656
Sah-1.535
Saharan-1.519
 pleas-1.506
ucket-1.489
Token$
Token ID3
Feature activation+4.23e-01

Pos logit contributions
orth+6.603
л+6.345
isphere+6.169
cliffe+5.980
irc+5.980
Neg logit contributions
 disag-9.401
 pleas-8.372
ucket-8.330
Sah-8.196
Saharan-8.102
TokenFC
Token ID4851
Feature activation+4.69e-01

Pos logit contributions
orth+4.008
isphere+3.997
л+3.896
arthed+3.747
cliffe+3.741
Neg logit contributions
 disag-3.228
Sah-2.885
Saharan-2.842
 pleas-2.836
ucket-2.799
Token but
Token ID475
Feature activation+3.48e-01

Pos logit contributions
isphere+1.586
orth+1.572
л+1.516
arthed+1.449
cliffe+1.439
Neg logit contributions
 disag-2.396
Sah-2.239
Saharan-2.222
 pleas-2.194
ucket-2.174
Token doctors
Token ID7519
Feature activation+1.75e-01

Pos logit contributions
isphere+2.676
orth+2.676
л+2.608
cliffe+2.496
arthed+2.479
Neg logit contributions
 disag-3.242
Sah-3.026
Saharan-3.019
ucket-2.930
 pleas-2.859
Token said
Token ID531
Feature activation-4.82e-02

Pos logit contributions
isphere+1.169
orth+1.155
л+1.117
arthed+1.066
cliffe+1.054
Neg logit contributions
 disag-1.817
Sah-1.697
Saharan-1.689
 pleas-1.662
ucket-1.650
Token she
Token ID673
Feature activation-6.33e-01

Pos logit contributions
 disag+0.355
Sah+0.322
Saharan+0.318
 pleas+0.317
ucket+0.308
Neg logit contributions
isphere-0.472
orth-0.467
л-0.454
arthed-0.444
enza-0.439
Token risked
Token ID42179
Feature activation-3.46e-02

Pos logit contributions
 disag+5.021
 pleas+4.705
Sah+4.624
Saharan+4.381
uffy+4.283
Neg logit contributions
isphere-5.722
л-5.612
orth-5.574
enza-5.352
arthed-5.347
Token severe
Token ID6049
Feature activation+1.58e+00

Pos logit contributions
 disag+0.273
Sah+0.248
Saharan+0.245
 pleas+0.244
ucket+0.236
Neg logit contributions
isphere-0.322
orth-0.319
л-0.312
arthed-0.303
enza-0.299
Token infection
Token ID10280
Feature activation+1.08e-01

Pos logit contributions
л+3.237
orth+3.023
 liner+2.997
ional+2.769
enza+2.749
Neg logit contributions
 disag-20.186
Sah-19.964
ucket-19.563
Saharan-19.539
maxwell-19.307
Token and
Token ID290
Feature activation-2.12e-02

Pos logit contributions
isphere+0.832
orth+0.821
л+0.795
arthed+0.767
enza+0.758
Neg logit contributions
 disag-1.023
Sah-0.949
Saharan-0.941
 pleas-0.934
ucket-0.919
Token scar
Token ID10153
Feature activation-3.31e-02

Pos logit contributions
 disag+0.146
Sah+0.132
Saharan+0.130
 pleas+0.129
ucket+0.125
Neg logit contributions
isphere-0.218
orth-0.216
л-0.210
arthed-0.206
enza-0.203
Tokenring
Token ID1806
Feature activation-1.14e-01

Pos logit contributions
 disag+0.253
Sah+0.231
Saharan+0.229
 pleas+0.226
ucket+0.220
Neg logit contributions
isphere-0.315
orth-0.312
л-0.303
arthed-0.296
enza-0.293
Token if
Token ID611
Feature activation+1.75e-01

Pos logit contributions
 disag+0.983
Sah+0.906
 pleas+0.899
Saharan+0.893
ucket+0.882
Neg logit contributions
isphere-0.971
orth-0.951
л-0.924
arthed-0.900
enza-0.893
Token6
Token ID21
Feature activation+1.02e+00

Pos logit contributions
isphere+3.419
orth+3.413
л+3.233
cliffe+3.107
enza+3.073
Neg logit contributions
 disag-5.911
Sah-5.527
Saharan-5.475
 pleas-5.361
ucket-5.357
Token {
Token ID1391
Feature activation-1.22e-01

Pos logit contributions
isphere+6.310
orth+6.199
л+6.077
irc+5.875
cliffe+5.832
Neg logit contributions
 disag-10.435
ucket-9.639
Sah-9.419
uffy-9.386
Saharan-9.385
Token(
Token ID7
Feature activation+3.79e-01

Pos logit contributions
 disag+1.056
Sah+1.013
Saharan+0.997
 pleas+0.981
ucket+0.956
Neg logit contributions
isphere-1.016
orth-0.978
л-0.950
arthed-0.936
enza-0.927
Token6
Token ID21
Feature activation+2.08e-03

Pos logit contributions
isphere+3.137
orth+3.135
л+3.054
arthed+2.921
cliffe+2.903
Neg logit contributions
 disag-3.329
Sah-3.033
Saharan-3.026
 pleas-2.987
ucket-2.953
Tokens
Token ID82
Feature activation-1.09e-01

Pos logit contributions
isphere+0.015
orth+0.015
л+0.015
arthed+0.014
cliffe+0.014
Neg logit contributions
 disag-0.020
Sah-0.019
Saharan-0.019
 pleas-0.019
ucket-0.018
Token)}
Token ID38165
Feature activation+1.57e+00

Pos logit contributions
 disag+0.924
Sah+0.867
 pleas+0.857
Saharan+0.854
ucket+0.834
Neg logit contributions
isphere-0.928
orth-0.904
л-0.879
arthed-0.853
enza-0.849
Token 38
Token ID4353
Feature activation+5.88e-01

Pos logit contributions
isphere+5.527
л+5.377
orth+5.354
cliffe+5.185
irc+4.998
Neg logit contributions
 disag-18.255
Saharan-16.985
uffy-16.901
Sah-16.889
 pleas-16.837
Token.
Token ID13
Feature activation+7.00e-01

Pos logit contributions
orth+3.580
л+3.492
isphere+3.471
cliffe+3.251
irc+3.213
Neg logit contributions
 disag-6.432
ucket-5.782
Saharan-5.780
Sah-5.771
uffy-5.716
Token N
Token ID399
Feature activation+5.48e-01

Pos logit contributions
orth+4.874
isphere+4.866
л+4.721
cliffe+4.537
enza+4.463
Neg logit contributions
 disag-6.725
Saharan-6.358
Sah-6.288
uffy-6.204
ucket-6.152
Tokend
Token ID67
Feature activation+5.28e-01

Pos logit contributions
orth+4.240
isphere+4.236
л+4.059
cliffe+3.919
bey+3.896
Neg logit contributions
 disag-5.109
Sah-4.663
Saharan-4.644
 pleas-4.561
ucket-4.479
Token4
Token ID19
Feature activation+5.42e-01

Pos logit contributions
isphere+3.787
orth+3.748
л+3.609
cliffe+3.449
enza+3.421
Neg logit contributions
 disag-5.242
Sah-4.839
Saharan-4.785
ucket-4.707
 pleas-4.705
Token states
Token ID2585
Feature activation+2.32e-02

Pos logit contributions
isphere+2.419
orth+2.390
л+2.311
arthed+2.210
cliffe+2.200
Neg logit contributions
 disag-3.467
Sah-3.239
Saharan-3.212
 pleas-3.167
ucket-3.148
Token,
Token ID11
Feature activation-4.09e-02

Pos logit contributions
isphere+0.204
orth+0.202
л+0.197
arthed+0.192
enza+0.189
Neg logit contributions
 disag-0.195
Sah-0.177
Saharan-0.176
 pleas-0.175
ucket-0.171
Token
Token ID447
Feature activation-7.12e-02

Pos logit contributions
 disag+0.370
Sah+0.341
Saharan+0.337
 pleas+0.337
ucket+0.327
Neg logit contributions
isphere-0.333
orth-0.330
л-0.318
arthed-0.313
enza-0.309
Token
Token ID251
Feature activation+2.93e-01

Pos logit contributions
 disag+0.441
Sah+0.397
Saharan+0.392
 pleas+0.389
ucket+0.381
Neg logit contributions
isphere-0.774
orth-0.768
л-0.746
arthed-0.728
cliffe-0.725
Token Ms
Token ID6997
Feature activation+3.48e-01

Pos logit contributions
isphere+2.424
orth+2.400
л+2.333
arthed+2.244
cliffe+2.240
Neg logit contributions
 disag-2.564
Sah-2.369
Saharan-2.346
 pleas-2.311
ucket-2.298
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
orth+2.392
isphere+2.386
л+2.322
cliffe+2.187
arthed+2.184
Neg logit contributions
 disag-3.551
Sah-3.246
Saharan-3.237
 pleas-3.212
ucket-3.176
Token Set
Token ID5345
Feature activation+4.48e-01

Pos logit contributions
orth+7.546
л+7.546
isphere+7.509
 Ost+7.080
enza+6.951
Neg logit contributions
 disag-14.496
 pleas-13.214
Sah-13.180
Saharan-13.065
uffy-13.006
Tokenzer
Token ID9107
Feature activation-1.21e-01

Pos logit contributions
isphere+1.373
orth+1.357
л+1.231
cliffe+1.117
enza+1.107
Neg logit contributions
 disag-6.316
Sah-5.969
Saharan-5.910
 pleas-5.909
ucket-5.826
Token said
Token ID531
Feature activation-1.00e-01

Pos logit contributions
 disag+1.223
Sah+1.139
Saharan+1.130
 pleas+1.121
ucket+1.106
Neg logit contributions
isphere-0.852
orth-0.837
л-0.809
arthed-0.781
cliffe-0.770
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
 disag+0.970
Sah+0.901
Saharan+0.894
 pleas+0.886
ucket+0.874
Neg logit contributions
isphere-0.748
orth-0.738
л-0.714
arthed-0.689
cliffe-0.681
Token
Token ID564
Feature activation-2.93e-01

Pos logit contributions
 disag+2.184
Sah+2.053
Saharan+2.030
 pleas+2.008
ucket+1.973
Neg logit contributions
isphere-1.645
orth-1.585
л-1.515
arthed-1.490
enza-1.469
Token )
Token ID1267
Feature activation+4.08e-01

Pos logit contributions
orth+3.138
л+3.092
isphere+3.052
cliffe+2.750
arthed+2.606
Neg logit contributions
 disag-12.892
Sah-12.059
Saharan-12.038
ucket-11.873
 pleas-11.816
Token $
Token ID720
Feature activation+4.74e-01

Pos logit contributions
orth+2.933
isphere+2.903
л+2.840
cliffe+2.694
arthed+2.693
Neg logit contributions
 disag-3.957
Sah-3.724
Saharan-3.721
 pleas-3.569
ucket-3.558
Tokens
Token ID82
Feature activation+7.22e-01

Pos logit contributions
orth+3.402
isphere+3.400
л+3.251
arthed+3.113
cliffe+3.088
Neg logit contributions
 disag-4.697
Sah-4.308
Saharan-4.285
 pleas-4.259
ucket-4.192
Tokenz
Token ID89
Feature activation+5.01e-01

Pos logit contributions
isphere+2.407
orth+2.399
л+2.200
arthed+2.004
cliffe+1.987
Neg logit contributions
 disag-9.780
Sah-9.065
 pleas-9.051
Saharan-9.018
ucket-8.828
Token2
Token ID17
Feature activation+8.96e-01

Pos logit contributions
isphere+3.691
orth+3.653
л+3.561
arthed+3.365
irc+3.335
Neg logit contributions
 disag-4.832
Sah-4.379
Saharan-4.354
 pleas-4.319
uffy-4.245
Token =
Token ID796
Feature activation+1.43e+00

Pos logit contributions
orth+2.768
л+2.686
isphere+2.650
 +=+2.297
irc+2.284
Neg logit contributions
 disag-12.240
Saharan-11.144
Sah-11.092
 pleas-11.089
uffy-11.017
Token [
Token ID685
Feature activation+5.61e-01

Pos logit contributions
orth+5.081
л+4.915
isphere+4.765
irc+4.764
 liner+4.444
Neg logit contributions
 disag-16.057
Saharan-15.612
Sah-15.508
 pleas-15.260
ucket-15.022
Tokensystem
Token ID10057
Feature activation-1.84e-01

Pos logit contributions
orth+1.728
isphere+1.722
л+1.552
cliffe+1.384
arthed+1.376
Neg logit contributions
 disag-7.793
Sah-7.343
 pleas-7.316
Saharan-7.314
ucket-7.260
Token.
Token ID13
Feature activation+5.57e-01

Pos logit contributions
 disag+1.622
Sah+1.549
Saharan+1.522
 pleas+1.513
ucket+1.469
Neg logit contributions
isphere-1.515
orth-1.458
л-1.414
arthed-1.400
enza-1.382
Tokenwindows
Token ID28457
Feature activation+1.78e-01

Pos logit contributions
orth+3.033
isphere+3.018
л+2.840
cliffe+2.697
arthed+2.682
Neg logit contributions
 disag-6.391
Sah-5.961
 pleas-5.952
Saharan-5.898
ucket-5.797
Token.
Token ID13
Feature activation+3.14e-01

Pos logit contributions
isphere+1.284
orth+1.274
л+1.233
arthed+1.179
cliffe+1.171
Neg logit contributions
 disag-1.768
Sah-1.639
Saharan-1.627
 pleas-1.608
ucket-1.594
Token Se
Token ID1001
Feature activation-1.24e-01

Pos logit contributions
isphere+0.572
orth+0.565
л+0.543
arthed+0.519
cliffe+0.513
Neg logit contributions
 disag-0.965
Sah-0.903
Saharan-0.896
 pleas-0.889
ucket-0.878
Tokeneker
Token ID28233
Feature activation-1.41e-01

Pos logit contributions
 disag+1.105
Sah+1.036
Saharan+1.033
ucket+1.012
 pleas+1.008
Neg logit contributions
orth-0.980
isphere-0.980
л-0.959
arthed-0.914
cliffe-0.899
Token wrote
Token ID2630
Feature activation-3.67e-01

Pos logit contributions
 disag+1.438
Sah+1.348
 pleas+1.339
Saharan+1.333
ucket+1.303
Neg logit contributions
isphere-0.971
orth-0.959
л-0.918
arthed-0.893
enza-0.879
Token:
Token ID25
Feature activation+4.11e-01

Pos logit contributions
 disag+3.238
Sah+3.148
 pleas+3.123
Saharan+3.112
uffy+2.940
Neg logit contributions
isphere-2.931
orth-2.801
arthed-2.722
л-2.694
enza-2.659
Token
Token ID198
Feature activation+8.40e-01

Pos logit contributions
orth+2.495
isphere+2.468
л+2.409
cliffe+2.260
arthed+2.236
Neg logit contributions
 disag-4.543
Sah-4.163
Saharan-4.155
 pleas-4.120
ucket-4.112
Token
Token ID198
Feature activation+1.43e+00

Pos logit contributions
orth+4.140
л+3.942
isphere+3.746
cliffe+3.625
bey+3.508
Neg logit contributions
 disag-10.111
ucket-9.091
uffy-8.989
 srf-8.963
Saharan-8.962
TokenCl
Token ID2601
Feature activation+1.18e-01

Pos logit contributions
orth+4.907
isphere+4.486
л+4.336
cliffe+4.267
irc+3.847
Neg logit contributions
 disag-18.248
 pleas-16.445
 uncons-16.377
uffy-16.361
ucket-16.138
Tokenarity
Token ID6806
Feature activation-2.12e-01

Pos logit contributions
isphere+0.873
orth+0.860
л+0.841
arthed+0.805
cliffe+0.794
Neg logit contributions
 disag-1.146
Sah-1.069
Saharan-1.062
 pleas-1.044
ucket-1.039
Token Gaming
Token ID14426
Feature activation+5.23e-01

Pos logit contributions
 disag+1.411
Sah+1.275
Saharan+1.254
 pleas+1.252
ucket+1.203
Neg logit contributions
isphere-2.205
orth-2.194
л-2.156
arthed-2.109
enza-2.076
Token will
Token ID481
Feature activation+2.00e-01

Pos logit contributions
isphere+3.751
orth+3.739
л+3.633
cliffe+3.471
arthed+3.430
Neg logit contributions
 disag-5.081
Saharan-4.730
Sah-4.724
ucket-4.617
uffy-4.571
Token also
Token ID635
Feature activation-7.35e-02

Pos logit contributions
isphere+1.712
orth+1.695
л+1.648
arthed+1.595
cliffe+1.580
Neg logit contributions
 disag-1.706
Sah-1.569
Saharan-1.554
 pleas-1.537
ucket-1.514
Token millionaires
Token ID48675
Feature activation+1.57e-01

Pos logit contributions
 disag+1.597
 pleas+1.469
Sah+1.451
Saharan+1.443
ucket+1.422
Neg logit contributions
isphere-1.573
orth-1.547
л-1.483
arthed-1.457
enza-1.451
Token,
Token ID11
Feature activation+3.63e-01

Pos logit contributions
isphere+1.165
orth+1.155
л+1.121
arthed+1.073
cliffe+1.065
Neg logit contributions
 disag-1.511
Sah-1.405
Saharan-1.395
 pleas-1.376
ucket-1.360
Token
Token ID447
Feature activation-7.92e-02

Pos logit contributions
isphere+3.006
orth+2.997
л+2.924
arthed+2.794
cliffe+2.789
Neg logit contributions
 disag-3.152
Sah-2.910
Saharan-2.885
 pleas-2.830
ucket-2.810
Token
Token ID251
Feature activation+4.39e-01

Pos logit contributions
 disag+0.627
Sah+0.574
Saharan+0.568
 pleas+0.564
ucket+0.554
Neg logit contributions
isphere-0.727
orth-0.721
л-0.699
arthed-0.676
cliffe-0.675
Token Ms
Token ID6997
Feature activation+7.69e-01

Pos logit contributions
orth+3.784
isphere+3.764
л+3.666
arthed+3.520
cliffe+3.507
Neg logit contributions
 disag-3.669
Sah-3.353
Saharan-3.333
 pleas-3.265
ucket-3.259
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
orth+4.870
л+4.704
isphere+4.683
cliffe+4.311
irc+4.259
Neg logit contributions
 disag-8.213
Saharan-7.409
 pleas-7.382
Sah-7.372
ucket-7.153
Token Ole
Token ID30093
Feature activation+1.32e-01

Pos logit contributions
orth+7.733
л+7.453
 Ost+7.408
isphere+7.104
 liner+6.711
Neg logit contributions
 disag-14.322
Saharan-12.714
Sah-12.604
 pleas-12.442
uffy-12.317
Tokench
Token ID354
Feature activation+6.76e-01

Pos logit contributions
isphere+0.683
orth+0.667
л+0.640
arthed+0.605
enza+0.593
Neg logit contributions
 disag-1.569
Sah-1.483
Saharan-1.475
 pleas-1.459
ucket-1.449
Tokenowski
Token ID12079
Feature activation+1.29e-02

Pos logit contributions
orth+4.068
isphere+4.041
л+3.868
cliffe+3.729
arthed+3.654
Neg logit contributions
 disag-7.429
Sah-6.863
 pleas-6.813
Saharan-6.756
ucket-6.542
Token said
Token ID531
Feature activation-2.18e-01

Pos logit contributions
isphere+0.091
orth+0.089
л+0.086
arthed+0.083
cliffe+0.082
Neg logit contributions
 disag-0.130
Sah-0.121
Saharan-0.120
 pleas-0.119
ucket-0.118
Token.
Token ID13
Feature activation-3.45e-01

Pos logit contributions
 disag+2.055
Sah+1.896
Saharan+1.884
 pleas+1.876
ucket+1.844
Neg logit contributions
isphere-1.675
orth-1.645
л-1.586
arthed-1.550
cliffe-1.527
Token x
Token ID2124
Feature activation+1.63e-01

Pos logit contributions
isphere+1.144
orth+1.132
л+1.078
arthed+0.995
cliffe+0.991
Neg logit contributions
 disag-3.252
Sah-3.079
Saharan-3.062
 pleas-3.025
ucket-3.010
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
isphere+1.194
orth+1.181
л+1.143
arthed+1.098
cliffe+1.088
Neg logit contributions
 disag-1.594
Sah-1.480
Saharan-1.469
 pleas-1.454
ucket-1.437
Tokenx
Token ID87
Feature activation+5.18e-01

Pos logit contributions
orth+2.904
isphere+2.827
л+2.747
cliffe+2.625
arthed+2.556
Neg logit contributions
 disag-5.464
Sah-4.997
Saharan-4.948
 pleas-4.935
ucket-4.900
Token.
Token ID13
Feature activation+8.48e-01

Pos logit contributions
orth+3.332
isphere+3.228
л+3.189
cliffe+3.016
arthed+2.963
Neg logit contributions
 disag-5.556
Sah-5.020
Saharan-5.001
ucket-4.985
 pleas-4.949
Tokenx
Token ID87
Feature activation+1.33e+00

Pos logit contributions
orth+4.669
isphere+4.374
л+4.179
irc+4.037
cliffe+4.006
Neg logit contributions
 disag-9.870
Sah-8.881
 pleas-8.876
ucket-8.811
 uncons-8.775
Token.
Token ID13
Feature activation+1.38e+00

Pos logit contributions
orth+6.949
irc+6.389
л+6.099
isphere+6.031
ional+5.809
Neg logit contributions
 disag-14.888
 srf-14.125
ucket-13.312
 uncons-13.267
 pleas-13.203
Token112
Token ID14686
Feature activation+6.52e-01

Pos logit contributions
orth+4.737
irc+4.072
isphere+4.044
ional+3.377
л+3.327
Neg logit contributions
 disag-17.780
ucket-16.746
 pleas-16.650
uffy-16.564
Sah-16.459
Token 10
Token ID838
Feature activation+3.98e-01

Pos logit contributions
orth+4.580
isphere+4.495
л+4.427
arthed+4.247
cliffe+4.183
Neg logit contributions
 disag-6.388
Saharan-5.920
Sah-5.898
ucket-5.838
 pleas-5.826
Token25
Token ID1495
Feature activation-7.70e-02

Pos logit contributions
orth+3.263
isphere+3.232
л+3.181
arthed+3.033
cliffe+3.029
Neg logit contributions
 disag-3.538
Sah-3.208
Saharan-3.202
 pleas-3.162
ucket-3.130
Token151
Token ID24309
Feature activation+4.04e-01

Pos logit contributions
 disag+0.612
Sah+0.563
Saharan+0.555
 pleas+0.550
ucket+0.539
Neg logit contributions
isphere-0.707
orth-0.694
л-0.676
arthed-0.659
cliffe-0.653
Token x
Token ID2124
Feature activation+1.59e-01

Pos logit contributions
orth+1.635
isphere+1.627
л+1.566
cliffe+1.434
arthed+1.405
Neg logit contributions
 disag-5.187
Sah-4.917
Saharan-4.897
ucket-4.820
 pleas-4.810
Token Boston
Token ID6182
Feature activation+8.40e-02

Pos logit contributions
 disag+0.077
Sah+0.071
Saharan+0.070
 pleas+0.070
ucket+0.068
Neg logit contributions
isphere-0.078
orth-0.077
л-0.075
arthed-0.073
enza-0.072
Token College
Token ID5535
Feature activation+2.97e-01

Pos logit contributions
isphere+0.587
orth+0.573
л+0.558
arthed+0.541
enza+0.528
Neg logit contributions
 disag-0.855
Sah-0.795
Saharan-0.788
 pleas-0.784
ucket-0.775
Token on
Token ID319
Feature activation+1.71e-01

Pos logit contributions
isphere+2.249
orth+2.233
л+2.140
enza+2.060
cliffe+2.057
Neg logit contributions
 disag-2.807
Sah-2.619
Saharan-2.604
 pleas-2.576
ucket-2.527
Token January
Token ID3269
Feature activation+1.02e-01

Pos logit contributions
isphere+1.355
orth+1.340
л+1.299
arthed+1.251
cliffe+1.244
Neg logit contributions
 disag-1.569
Sah-1.453
Saharan-1.441
 pleas-1.424
ucket-1.407
Token 3
Token ID513
Feature activation-1.59e-01

Pos logit contributions
isphere+0.854
orth+0.844
л+0.820
arthed+0.793
enza+0.785
Neg logit contributions
 disag-0.890
Sah-0.822
Saharan-0.814
 pleas-0.805
ucket-0.792
Token,[
Token ID17414
Feature activation+1.38e+00

Pos logit contributions
 disag+1.484
Sah+1.366
Saharan+1.351
 pleas+1.342
ucket+1.324
Neg logit contributions
isphere-1.237
orth-1.207
л-1.182
arthed-1.145
enza-1.126
Token112
Token ID14686
Feature activation-1.27e-01

Pos logit contributions
orth+5.544
isphere+5.235
arthed+4.601
irc+4.421
л+4.344
Neg logit contributions
 disag-16.323
 pleas-15.183
Sah-15.107
Saharan-15.047
ucket-15.030
Token]
Token ID60
Feature activation+1.29e-01

Pos logit contributions
 disag+1.217
Sah+1.130
Saharan+1.121
 pleas+1.108
ucket+1.093
Neg logit contributions
isphere-0.958
orth-0.948
л-0.918
arthed-0.885
cliffe-0.873
Token earning
Token ID13748
Feature activation-7.15e-02

Pos logit contributions
isphere+1.030
orth+1.018
л+0.988
arthed+0.953
cliffe+0.944
Neg logit contributions
 disag-1.178
Sah-1.089
Saharan-1.079
 pleas-1.069
ucket-1.053
Token his
Token ID465
Feature activation-1.17e-01

Pos logit contributions
 disag+0.674
Sah+0.623
 pleas+0.620
Saharan+0.617
ucket+0.606
Neg logit contributions
isphere-0.549
orth-0.540
л-0.528
arthed-0.506
enza-0.502
Token fifth
Token ID8150
Feature activation-4.79e-01

Pos logit contributions
 disag+1.126
 pleas+1.036
Sah+1.031
Saharan+1.021
ucket+1.004
Neg logit contributions
isphere-0.882
orth-0.863
л-0.841
arthed-0.822
enza-0.801
Token #
Token ID1303
Feature activation+3.88e-01

Pos logit contributions
 disag+2.467
 pleas+2.258
Sah+2.225
Saharan+2.204
 uncons+2.133
Neg logit contributions
isphere-2.343
orth-2.304
arthed-2.199
л-2.195
cliffe-2.147
TokenWe
Token ID1135
Feature activation-1.38e-01

Pos logit contributions
isphere+3.207
orth+3.189
л+3.151
arthed+2.953
enza+2.948
Neg logit contributions
 disag-3.419
Saharan-3.090
Sah-3.089
 pleas-3.061
ucket-3.036
Token
Token ID447
Feature activation-3.84e-01

Pos logit contributions
 disag+1.259
Sah+1.187
Saharan+1.163
 pleas+1.157
ucket+1.125
Neg logit contributions
isphere-1.097
orth-1.083
л-1.030
arthed-1.016
cliffe-1.010
Token
Token ID247
Feature activation-1.42e-02

Pos logit contributions
 disag+2.945
Sah+2.748
Saharan+2.739
 pleas+2.703
ucket+2.691
Neg logit contributions
orth-3.500
isphere-3.469
л-3.310
cliffe-3.242
arthed-3.198
Tokenve
Token ID303
Feature activation+2.77e-01

Pos logit contributions
 disag+0.110
Sah+0.101
Saharan+0.100
 pleas+0.099
ucket+0.097
Neg logit contributions
isphere-0.134
orth-0.132
л-0.128
arthed-0.125
cliffe-0.124
TokenHad
Token ID25383
Feature activation+1.38e+00

Pos logit contributions
isphere+2.648
orth+2.629
л+2.592
arthed+2.504
enza+2.465
Neg logit contributions
 disag-2.099
Saharan-1.869
Sah-1.868
 pleas-1.845
ucket-1.822
TokenEnough
Token ID47323
Feature activation-3.32e-01

Pos logit contributions
л+4.847
orth+4.752
isphere+4.405
arthed+3.906
enza+3.819
Neg logit contributions
 disag-17.877
 pleas-15.853
Saharan-15.849
 DAV-15.815
Sah-15.786
Token protester
Token ID34678
Feature activation+1.14e-01

Pos logit contributions
 disag+2.757
Sah+2.531
 pleas+2.521
Saharan+2.488
uffy+2.397
Neg logit contributions
isphere-2.892
orth-2.837
arthed-2.716
л-2.714
cliffe-2.688
Token in
Token ID287
Feature activation-1.14e-01

Pos logit contributions
isphere+0.911
orth+0.902
л+0.872
arthed+0.845
enza+0.837
Neg logit contributions
 disag-1.041
Sah-0.960
Saharan-0.950
 pleas-0.948
ucket-0.929
Token Petersburg
Token ID27051
Feature activation+1.73e-02

Pos logit contributions
 disag+1.073
Sah+0.986
 pleas+0.983
Saharan+0.976
ucket+0.958
Neg logit contributions
isphere-0.894
orth-0.865
л-0.833
arthed-0.821
enza-0.808
Token,
Token ID11
Feature activation-1.73e-01

Pos logit contributions
isphere+0.141
orth+0.140
л+0.135
arthed+0.132
enza+0.130
Neg logit contributions
 disag-0.156
Sah-0.144
 pleas-0.143
Saharan-0.142
ucket-0.139
TokenFont
Token ID23252
Feature activation-1.79e-01

Pos logit contributions
isphere+0.622
orth+0.616
л+0.583
arthed+0.549
cliffe+0.542
Neg logit contributions
 disag-1.511
Sah-1.418
Saharan-1.409
 pleas-1.402
ucket-1.386
TokenName
Token ID5376
Feature activation+3.12e-01

Pos logit contributions
 disag+1.529
Sah+1.427
Saharan+1.414
 pleas+1.386
ucket+1.373
Neg logit contributions
isphere-1.523
orth-1.495
л-1.450
arthed-1.414
enza-1.401
Token,
Token ID11
Feature activation+6.53e-01

Pos logit contributions
orth+2.256
isphere+2.250
л+2.186
arthed+2.076
cliffe+2.075
Neg logit contributions
 disag-3.068
Sah-2.830
Saharan-2.809
 pleas-2.778
ucket-2.757
Token$
Token ID3
Feature activation+6.06e-01

Pos logit contributions
orth+5.081
isphere+4.993
л+4.887
cliffe+4.672
arthed+4.649
Neg logit contributions
 disag-5.974
 pleas-5.428
Sah-5.401
Saharan-5.377
ucket-5.328
TokenFS
Token ID10652
Feature activation+2.98e-01

Pos logit contributions
orth+5.433
isphere+5.356
л+5.219
arthed+4.989
cliffe+4.977
Neg logit contributions
 disag-4.916
Sah-4.363
 pleas-4.355
Saharan-4.322
ucket-4.217
Token2
Token ID17
Feature activation+1.35e+00

Pos logit contributions
isphere+2.089
orth+2.084
л+2.028
arthed+1.916
cliffe+1.898
Neg logit contributions
 disag-3.004
Sah-2.760
Saharan-2.740
 pleas-2.718
ucket-2.695
Token,[
Token ID17414
Feature activation+6.56e-01

Pos logit contributions
orth+7.066
л+6.609
irc+6.423
isphere+6.350
herer+5.797
Neg logit contributions
 disag-14.417
Sah-13.332
Saharan-13.226
uffy-13.079
ucket-12.841
TokenSystem
Token ID11964
Feature activation-1.63e-01

Pos logit contributions
orth+2.749
isphere+2.662
л+2.578
arthed+2.328
cliffe+2.326
Neg logit contributions
 disag-8.396
 pleas-7.774
Saharan-7.763
Sah-7.756
ucket-7.705
Token.
Token ID13
Feature activation+9.51e-02

Pos logit contributions
 disag+1.449
Sah+1.382
Saharan+1.360
 pleas+1.350
ucket+1.313
Neg logit contributions
isphere-1.335
orth-1.287
л-1.243
arthed-1.228
enza-1.219
TokenDraw
Token ID25302
Feature activation+3.65e-01

Pos logit contributions
isphere+0.697
orth+0.683
л+0.659
arthed+0.638
enza+0.634
Neg logit contributions
 disag-0.932
Sah-0.880
Saharan-0.871
 pleas-0.858
ucket-0.846
Tokening
Token ID278
Feature activation-5.63e-02

Pos logit contributions
orth+2.227
isphere+2.201
л+2.120
cliffe+2.004
arthed+1.992
Neg logit contributions
 disag-4.049
Sah-3.730
Saharan-3.698
 pleas-3.685
ucket-3.644
TokenE
Token ID36
Feature activation-2.61e-01

Pos logit contributions
isphere+2.631
orth+2.621
л+2.555
cliffe+2.360
arthed+2.355
Neg logit contributions
 disag-5.273
Sah-4.877
Saharan-4.864
 pleas-4.821
ucket-4.817
Token,
Token ID11
Feature activation-5.75e-02

Pos logit contributions
 disag+2.440
Sah+2.239
Saharan+2.215
 pleas+2.200
ucket+2.169
Neg logit contributions
isphere-2.045
orth-2.008
л-1.938
arthed-1.881
cliffe-1.865
TokenDP
Token ID6322
Feature activation+1.40e-01

Pos logit contributions
 disag+0.398
Sah+0.359
Saharan+0.355
 pleas+0.348
ucket+0.343
Neg logit contributions
isphere-0.588
orth-0.582
л-0.569
arthed-0.553
cliffe-0.549
Token02
Token ID2999
Feature activation+2.81e-01

Pos logit contributions
isphere+1.286
orth+1.278
л+1.250
arthed+1.217
cliffe+1.200
Neg logit contributions
 disag-1.106
Sah-1.005
Saharan-0.992
 pleas-0.982
ucket-0.959
Token_
Token ID62
Feature activation-3.05e-01

Pos logit contributions
orth+1.639
isphere+1.639
л+1.583
arthed+1.486
cliffe+1.480
Neg logit contributions
 disag-3.163
Sah-2.924
Saharan-2.907
 pleas-2.892
ucket-2.870
Token00
Token ID405
Feature activation+1.35e+00

Pos logit contributions
 disag+2.229
Sah+2.049
Saharan+2.025
 pleas+1.976
ucket+1.959
Neg logit contributions
isphere-2.989
orth-2.931
л-2.855
arthed-2.765
cliffe-2.762
Token64
Token ID2414
Feature activation+6.79e-01

Pos logit contributions
orth+6.231
л+5.955
isphere+5.662
irc+5.147
cliffe+5.049
Neg logit contributions
 disag-15.343
ucket-13.899
uffy-13.858
 pleas-13.857
 uncons-13.688
TokenE
Token ID36
Feature activation-2.47e-01

Pos logit contributions
л+3.424
orth+3.418
isphere+3.344
cliffe+3.018
enza+3.012
Neg logit contributions
 disag-8.053
ucket-7.349
Saharan-7.315
Sah-7.289
 pleas-7.271
Token,
Token ID11
Feature activation-1.00e-01

Pos logit contributions
 disag+2.324
Sah+2.139
Saharan+2.117
 pleas+2.101
ucket+2.074
Neg logit contributions
isphere-1.923
orth-1.890
л-1.825
arthed-1.766
cliffe-1.753
TokenDP
Token ID6322
Feature activation+6.21e-02

Pos logit contributions
 disag+0.688
Sah+0.620
Saharan+0.613
 pleas+0.600
ucket+0.592
Neg logit contributions
isphere-1.031
orth-1.020
л-0.997
arthed-0.969
cliffe-0.964
Token02
Token ID2999
Feature activation+2.79e-01

Pos logit contributions
isphere+0.617
orth+0.607
л+0.590
arthed+0.575
enza+0.572
Neg logit contributions
 disag-0.449
Sah-0.413
Saharan-0.407
 pleas-0.401
ucket-0.394
Token land
Token ID1956
Feature activation+4.27e-02

Pos logit contributions
 disag+3.136
 pleas+2.856
Sah+2.833
Saharan+2.777
ucket+2.686
Neg logit contributions
isphere-2.959
orth-2.874
л-2.848
arthed-2.790
enza-2.732
Token remain
Token ID3520
Feature activation-3.27e-01

Pos logit contributions
isphere+0.332
orth+0.327
л+0.318
arthed+0.308
enza+0.304
Neg logit contributions
 disag-0.401
Sah-0.371
Saharan-0.366
 pleas-0.365
ucket-0.357
Token Kenyan
Token ID47214
Feature activation-2.97e-01

Pos logit contributions
 disag+2.769
Sah+2.515
 pleas+2.493
Saharan+2.480
uffy+2.391
Neg logit contributions
isphere-2.881
orth-2.794
л-2.748
arthed-2.675
enza-2.644
Token.
Token ID13
Feature activation+9.46e-02

Pos logit contributions
 disag+2.714
Sah+2.531
 pleas+2.488
Saharan+2.475
ucket+2.399
Neg logit contributions
isphere-2.359
orth-2.302
л-2.258
enza-2.204
arthed-2.198
Token In
Token ID554
Feature activation+2.25e-01

Pos logit contributions
isphere+0.705
orth+0.691
л+0.667
arthed+0.647
enza+0.638
Neg logit contributions
 disag-0.920
Sah-0.861
Saharan-0.852
 pleas-0.843
ucket-0.828
Token June
Token ID2795
Feature activation+1.34e+00

Pos logit contributions
isphere+1.800
orth+1.781
л+1.727
arthed+1.666
cliffe+1.654
Neg logit contributions
 disag-2.054
Sah-1.900
Saharan-1.883
 pleas-1.862
ucket-1.839
Token 1962
Token ID20033
Feature activation-1.41e-01

Pos logit contributions
isphere+7.617
orth+7.474
л+7.334
cliffe+7.305
 liner+6.899
Neg logit contributions
 disag-13.036
Sah-12.494
Saharan-12.418
uffy-12.210
ucket-12.025
Token,
Token ID11
Feature activation-1.27e-01

Pos logit contributions
 disag+1.291
Sah+1.188
Saharan+1.180
 pleas+1.177
ucket+1.151
Neg logit contributions
isphere-1.137
orth-1.119
л-1.088
arthed-1.053
enza-1.035
Token Ken
Token ID7148
Feature activation-2.28e-01

Pos logit contributions
 disag+1.104
Sah+1.007
 pleas+1.003
Saharan+0.999
ucket+0.970
Neg logit contributions
isphere-1.074
orth-1.061
л-1.032
arthed-1.003
enza-0.990
Tokeny
Token ID88
Feature activation-2.01e-01

Pos logit contributions
 disag+2.018
Sah+1.886
 pleas+1.882
Saharan+1.861
ucket+1.843
Neg logit contributions
isphere-1.895
л-1.782
orth-1.767
arthed-1.718
 liner-1.683
Tokenatta
Token ID25014
Feature activation+1.38e-03

Pos logit contributions
 disag+1.997
Saharan+1.877
Sah+1.871
ucket+1.860
 pleas+1.848
Neg logit contributions
isphere-1.435
orth-1.362
л-1.355
arthed-1.287
 liner-1.270
Token accepted
Token ID6292
Feature activation-7.24e-01

Pos logit contributions
isphere+0.311
orth+0.308
л+0.299
arthed+0.289
enza+0.286
Neg logit contributions
 disag-0.342
Sah-0.315
Saharan-0.311
 pleas-0.310
ucket-0.303
Token its
Token ID663
Feature activation-3.63e-01

Pos logit contributions
 disag+5.816
 pleas+5.406
Saharan+5.206
Sah+5.179
ucket+4.927
Neg logit contributions
orth-6.433
isphere-6.389
л-6.167
arthed-6.058
bey-5.827
Token presidency
Token ID12112
Feature activation-3.88e-01

Pos logit contributions
 disag+3.100
 pleas+2.873
Sah+2.824
Saharan+2.791
uffy+2.658
Neg logit contributions
orth-3.094
isphere-3.087
arthed-2.997
л-2.975
cliffe-2.860
Token.
Token ID13
Feature activation+2.94e-02

Pos logit contributions
 disag+3.439
 pleas+3.169
Sah+3.135
Saharan+3.087
ucket+2.971
Neg logit contributions
isphere-3.153
orth-3.110
л-3.007
arthed-2.999
enza-2.915
Token In
Token ID554
Feature activation+1.39e-01

Pos logit contributions
isphere+0.218
orth+0.213
л+0.204
arthed+0.199
enza+0.197
Neg logit contributions
 disag-0.286
Sah-0.270
Saharan-0.267
 pleas-0.263
ucket-0.258
Token January
Token ID3269
Feature activation+1.34e+00

Pos logit contributions
isphere+1.132
orth+1.118
л+1.087
arthed+1.052
enza+1.038
Neg logit contributions
 disag-1.252
Sah-1.155
Saharan-1.145
 pleas-1.136
ucket-1.116
Token 1962
Token ID20033
Feature activation-4.35e-02

Pos logit contributions
isphere+7.244
л+6.891
orth+6.829
cliffe+6.663
enza+6.509
Neg logit contributions
 disag-13.608
Sah-13.013
Saharan-12.849
uffy-12.841
ucket-12.704
Token he
Token ID339
Feature activation-4.26e-02

Pos logit contributions
 disag+0.409
Sah+0.379
Saharan+0.375
 pleas+0.372
ucket+0.367
Neg logit contributions
isphere-0.338
orth-0.334
л-0.323
arthed-0.312
cliffe-0.308
Token was
Token ID373
Feature activation+1.78e-01

Pos logit contributions
 disag+0.374
 pleas+0.340
Sah+0.338
Saharan+0.336
ucket+0.326
Neg logit contributions
isphere-0.360
orth-0.357
л-0.348
arthed-0.339
enza-0.334
Token elected
Token ID7018
Feature activation+3.69e-01

Pos logit contributions
isphere+1.438
orth+1.420
л+1.383
arthed+1.333
cliffe+1.319
Neg logit contributions
 disag-1.611
Sah-1.483
Saharan-1.472
 pleas-1.461
ucket-1.434
Token un
Token ID555
Feature activation+5.67e-01

Pos logit contributions
isphere+2.835
orth+2.832
л+2.720
cliffe+2.612
arthed+2.604
Neg logit contributions
 disag-3.400
Sah-3.176
Saharan-3.138
ucket-3.095
 pleas-3.092
Tokening
Token ID278
Feature activation+1.73e-01

Pos logit contributions
orth+3.159
isphere+3.049
л+2.963
cliffe+2.812
enza+2.753
Neg logit contributions
 disag-6.334
Sah-5.746
Saharan-5.713
 pleas-5.708
ucket-5.650
Token.
Token ID13
Feature activation+5.09e-01

Pos logit contributions
isphere+1.276
orth+1.260
л+1.219
arthed+1.174
cliffe+1.161
Neg logit contributions
 disag-1.680
Sah-1.562
Saharan-1.549
 pleas-1.534
ucket-1.514
TokenRect
Token ID45474
Feature activation+8.07e-02

Pos logit contributions
orth+2.935
isphere+2.898
л+2.796
arthed+2.603
cliffe+2.590
Neg logit contributions
 disag-5.759
 pleas-5.290
Sah-5.279
Saharan-5.233
ucket-5.191
Tokenangle
Token ID9248
Feature activation+1.38e-01

Pos logit contributions
isphere+0.347
orth+0.340
л+0.321
arthed+0.299
cliffe+0.293
Neg logit contributions
 disag-1.035
Sah-0.979
Saharan-0.973
 pleas-0.967
ucket-0.958
TokenF
Token ID37
Feature activation+6.95e-04

Pos logit contributions
isphere+1.040
orth+1.030
л+0.994
arthed+0.957
cliffe+0.950
Neg logit contributions
 disag-1.331
Sah-1.233
Saharan-1.222
 pleas-1.213
ucket-1.196
Token (
Token ID357
Feature activation+1.34e+00

Pos logit contributions
isphere+0.005
orth+0.005
л+0.005
arthed+0.005
cliffe+0.005
Neg logit contributions
 disag-0.006
Sah-0.006
Saharan-0.006
 pleas-0.006
ucket-0.006
Token0
Token ID15
Feature activation+3.93e-01

Pos logit contributions
orth+7.600
isphere+7.196
irc+7.141
л+6.996
cliffe+6.625
Neg logit contributions
 disag-13.311
 pleas-12.479
Sah-12.357
Saharan-12.284
ucket-12.186
Token,
Token ID11
Feature activation+7.09e-01

Pos logit contributions
orth+2.673
isphere+2.657
л+2.547
arthed+2.401
irc+2.398
Neg logit contributions
 disag-4.032
Sah-3.787
Saharan-3.744
 pleas-3.687
ucket-3.629
Token($
Token ID16763
Feature activation+8.96e-02

Pos logit contributions
orth+5.113
isphere+5.026
л+4.883
irc+4.671
arthed+4.646
Neg logit contributions
 disag-6.815
 pleas-6.249
Sah-6.232
Saharan-6.196
ucket-6.070
Tokens
Token ID82
Feature activation+1.03e+00

Pos logit contributions
isphere+0.655
orth+0.645
л+0.626
arthed+0.602
enza+0.597
Neg logit contributions
 disag-0.878
Sah-0.819
Saharan-0.812
 pleas-0.803
ucket-0.794
Tokenz
Token ID89
Feature activation+3.85e-01

Pos logit contributions
orth+2.884
isphere+2.717
л+2.608
cliffe+2.263
irc+2.262
Neg logit contributions
 disag-14.421
 pleas-13.177
Sah-13.088
Saharan-13.024
ucket-12.973
Tokenany
Token ID1092
Feature activation-3.09e-01

Pos logit contributions
isphere+0.482
orth+0.476
л+0.461
arthed+0.444
cliffe+0.440
Neg logit contributions
 disag-0.603
Sah-0.559
Saharan-0.554
 pleas-0.549
ucket-0.542
Token Mode
Token ID10363
Feature activation+5.11e-02

Pos logit contributions
 disag+2.281
Sah+2.051
 pleas+2.039
Saharan+2.013
ucket+1.972
Neg logit contributions
isphere-2.986
orth-2.946
л-2.865
arthed-2.833
cliffe-2.790
Token:
Token ID25
Feature activation+2.03e-01

Pos logit contributions
isphere+0.352
orth+0.346
л+0.333
arthed+0.323
enza+0.318
Neg logit contributions
 disag-0.522
Sah-0.490
Saharan-0.486
 pleas-0.482
ucket-0.474
TokenMan
Token ID5124
Feature activation-9.18e-02

Pos logit contributions
orth+1.380
isphere+1.379
л+1.327
arthed+1.265
enza+1.248
Neg logit contributions
 disag-2.084
Sah-1.923
Saharan-1.915
 pleas-1.902
ucket-1.886
Tokenaged
Token ID1886
Feature activation+5.76e-01

Pos logit contributions
 disag+0.646
Saharan+0.596
Sah+0.594
 pleas+0.575
ucket+0.571
Neg logit contributions
isphere-0.914
orth-0.894
л-0.889
cliffe-0.852
 liner-0.852
Token Access
Token ID8798
Feature activation+1.33e+00

Pos logit contributions
orth+2.992
isphere+2.903
л+2.836
cliffe+2.646
bey+2.595
Neg logit contributions
 disag-6.768
Sah-6.359
Saharan-6.306
ucket-6.260
uffy-6.212
Token Point
Token ID6252
Feature activation+3.86e-01

Pos logit contributions
orth+3.613
л+3.199
cliffe+2.940
herer+2.931
 Ost+2.843
Neg logit contributions
 disag-17.866
Sah-16.680
Saharan-16.670
ucket-16.261
 pleas-16.198
Token:
Token ID25
Feature activation+5.32e-01

Pos logit contributions
orth+2.315
isphere+2.287
л+2.231
cliffe+2.088
arthed+2.061
Neg logit contributions
 disag-4.280
Sah-3.938
Saharan-3.917
ucket-3.871
 pleas-3.868
Token Not
Token ID1892
Feature activation+1.92e-01

Pos logit contributions
orth+4.406
isphere+4.333
л+4.269
cliffe+4.034
enza+4.027
Neg logit contributions
 disag-4.532
Sah-4.185
Saharan-4.183
 pleas-4.072
ucket-4.040
Token-
Token ID12
Feature activation+4.90e-01

Pos logit contributions
isphere+1.420
orth+1.398
л+1.358
arthed+1.304
enza+1.290
Neg logit contributions
 disag-1.875
Sah-1.744
Saharan-1.730
 pleas-1.714
ucket-1.688
TokenAssociated
Token ID29014
Feature activation+3.27e-01

Pos logit contributions
orth+2.737
isphere+2.701
л+2.592
arthed+2.470
cliffe+2.421
Neg logit contributions
 disag-5.638
Sah-5.201
 pleas-5.196
Saharan-5.162
ucket-5.153
Token203
Token ID22416
Feature activation+2.58e-01

Pos logit contributions
 disag+0.817
Sah+0.752
Saharan+0.742
 pleas+0.736
ucket+0.722
Neg logit contributions
isphere-0.919
orth-0.903
л-0.878
arthed-0.855
cliffe-0.848
Token x
Token ID2124
Feature activation+1.63e-01

Pos logit contributions
isphere+1.144
orth+1.132
л+1.078
arthed+0.995
cliffe+0.991
Neg logit contributions
 disag-3.252
Sah-3.079
Saharan-3.062
 pleas-3.025
ucket-3.010
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
isphere+1.194
orth+1.181
л+1.143
arthed+1.098
cliffe+1.088
Neg logit contributions
 disag-1.594
Sah-1.480
Saharan-1.469
 pleas-1.454
ucket-1.437
Tokenx
Token ID87
Feature activation+5.18e-01

Pos logit contributions
orth+2.904
isphere+2.827
л+2.747
cliffe+2.625
arthed+2.556
Neg logit contributions
 disag-5.464
Sah-4.997
Saharan-4.948
 pleas-4.935
ucket-4.900
Token.
Token ID13
Feature activation+8.48e-01

Pos logit contributions
orth+3.332
isphere+3.228
л+3.189
cliffe+3.016
arthed+2.963
Neg logit contributions
 disag-5.556
Sah-5.020
Saharan-5.001
ucket-4.985
 pleas-4.949
Tokenx
Token ID87
Feature activation+1.33e+00

Pos logit contributions
orth+4.669
isphere+4.374
л+4.179
irc+4.037
cliffe+4.006
Neg logit contributions
 disag-9.870
Sah-8.881
 pleas-8.876
ucket-8.811
 uncons-8.775
Token.
Token ID13
Feature activation+1.38e+00

Pos logit contributions
orth+6.949
irc+6.389
л+6.099
isphere+6.031
ional+5.809
Neg logit contributions
 disag-14.888
 srf-14.125
ucket-13.312
 uncons-13.267
 pleas-13.203
Token112
Token ID14686
Feature activation+6.52e-01

Pos logit contributions
orth+4.737
irc+4.072
isphere+4.044
ional+3.377
л+3.327
Neg logit contributions
 disag-17.780
ucket-16.746
 pleas-16.650
uffy-16.564
Sah-16.459
Token 10
Token ID838
Feature activation+3.98e-01

Pos logit contributions
orth+4.580
isphere+4.495
л+4.427
arthed+4.247
cliffe+4.183
Neg logit contributions
 disag-6.388
Saharan-5.920
Sah-5.898
ucket-5.838
 pleas-5.826
Token25
Token ID1495
Feature activation-7.70e-02

Pos logit contributions
orth+3.263
isphere+3.232
л+3.181
arthed+3.033
cliffe+3.029
Neg logit contributions
 disag-3.538
Sah-3.208
Saharan-3.202
 pleas-3.162
ucket-3.130
Token151
Token ID24309
Feature activation+4.04e-01

Pos logit contributions
 disag+0.612
Sah+0.563
Saharan+0.555
 pleas+0.550
ucket+0.539
Neg logit contributions
isphere-0.707
orth-0.694
л-0.676
arthed-0.659
cliffe-0.653
Token[
Token ID58
Feature activation+5.99e-01

Pos logit contributions
orth+4.693
irc+4.310
л+4.256
isphere+3.720
herer+3.294
Neg logit contributions
 disag-20.362
 srf-19.468
Sah-18.603
 uncons-18.588
Saharan-18.561
Token0
Token ID15
Feature activation+1.69e-01

Pos logit contributions
orth+3.870
isphere+3.747
л+3.671
arthed+3.510
cliffe+3.435
Neg logit contributions
 disag-6.340
Sah-5.833
 pleas-5.730
Saharan-5.686
 uncons-5.539
Token],
Token ID4357
Feature activation+9.51e-01

Pos logit contributions
isphere+1.237
orth+1.227
л+1.189
arthed+1.141
cliffe+1.130
Neg logit contributions
 disag-1.656
Sah-1.535
Saharan-1.519
 pleas-1.506
ucket-1.489
Token$
Token ID3
Feature activation+4.23e-01

Pos logit contributions
orth+6.603
л+6.345
isphere+6.169
cliffe+5.980
irc+5.980
Neg logit contributions
 disag-9.401
 pleas-8.372
ucket-8.330
Sah-8.196
Saharan-8.102
TokenFC
Token ID4851
Feature activation+4.69e-01

Pos logit contributions
orth+4.008
isphere+3.997
л+3.896
arthed+3.747
cliffe+3.741
Neg logit contributions
 disag-3.228
Sah-2.885
Saharan-2.842
 pleas-2.836
ucket-2.799
Token2
Token ID17
Feature activation+1.33e+00

Pos logit contributions
orth+3.616
isphere+3.602
л+3.538
arthed+3.332
cliffe+3.311
Neg logit contributions
 disag-4.371
Sah-3.907
Saharan-3.867
 pleas-3.857
ucket-3.848
Token[
Token ID58
Feature activation+1.67e-01

Pos logit contributions
orth+3.746
л+3.400
irc+3.282
isphere+2.769
cliffe+2.551
Neg logit contributions
 disag-17.715
 srf-17.598
 uncons-16.230
ucket-16.152
uffy-16.089
Token1
Token ID16
Feature activation+2.15e-01

Pos logit contributions
isphere+1.176
orth+1.163
л+1.123
arthed+1.078
cliffe+1.066
Neg logit contributions
 disag-1.679
Sah-1.562
Saharan-1.550
 pleas-1.536
ucket-1.517
Token],
Token ID4357
Feature activation+7.68e-01

Pos logit contributions
isphere+1.543
orth+1.533
л+1.487
arthed+1.423
cliffe+1.408
Neg logit contributions
 disag-2.133
Sah-1.973
Saharan-1.954
 pleas-1.938
ucket-1.918
Token$
Token ID3
Feature activation+3.28e-01

Pos logit contributions
orth+5.598
л+5.413
isphere+5.314
cliffe+5.123
irc+5.060
Neg logit contributions
 disag-7.502
 pleas-6.645
ucket-6.633
Sah-6.555
Saharan-6.501
TokenFC
Token ID4851
Feature activation+4.43e-01

Pos logit contributions
isphere+3.178
orth+3.170
л+3.089
arthed+2.984
cliffe+2.972
Neg logit contributions
 disag-2.442
Sah-2.188
Saharan-2.159
 pleas-2.146
ucket-2.114
Token x
Token ID2124
Feature activation-9.42e-03

Pos logit contributions
isphere+0.852
orth+0.837
л+0.794
arthed+0.745
cliffe+0.733
Neg logit contributions
 disag-2.257
Sah-2.132
Saharan-2.118
 pleas-2.102
ucket-2.082
Token.
Token ID13
Feature activation+3.76e-01

Pos logit contributions
 disag+0.088
Sah+0.082
Saharan+0.081
 pleas+0.081
ucket+0.079
Neg logit contributions
isphere-0.074
orth-0.072
л-0.070
arthed-0.068
enza-0.067
Tokenx
Token ID87
Feature activation+6.16e-02

Pos logit contributions
orth+2.334
isphere+2.306
л+2.224
cliffe+2.118
arthed+2.091
Neg logit contributions
 disag-4.133
Sah-3.803
Saharan-3.768
 pleas-3.755
ucket-3.720
Token.
Token ID13
Feature activation+3.48e-02

Pos logit contributions
isphere+0.464
orth+0.456
л+0.442
arthed+0.427
enza+0.422
Neg logit contributions
 disag-0.591
Sah-0.552
Saharan-0.547
 pleas-0.542
ucket-0.533
Tokenx
Token ID87
Feature activation-3.56e-01

Pos logit contributions
isphere+0.242
orth+0.237
л+0.230
arthed+0.222
enza+0.218
Neg logit contributions
 disag-0.353
Sah-0.332
Saharan-0.330
 pleas-0.326
ucket-0.322
Token.
Token ID13
Feature activation-1.59e+00

Pos logit contributions
 disag+3.017
Sah+2.904
Saharan+2.859
 pleas+2.814
uffy+2.751
Neg logit contributions
isphere-3.002
orth-2.849
л-2.811
arthed-2.753
enza-2.737
Token99
Token ID2079
Feature activation+4.94e-01

Pos logit contributions
 disag+6.295
Sah+5.726
Saharan+5.396
uffy+5.345
 pleas+5.320
Neg logit contributions
isphere-17.938
л-17.866
cliffe-17.288
enza-16.959
arthed-16.938
Token 10
Token ID838
Feature activation-7.48e-02

Pos logit contributions
orth+3.573
isphere+3.532
л+3.464
arthed+3.306
cliffe+3.262
Neg logit contributions
 disag-4.817
Saharan-4.442
Sah-4.428
 pleas-4.379
ucket-4.371
Token88
Token ID3459
Feature activation+7.59e-02

Pos logit contributions
 disag+0.639
Sah+0.605
Saharan+0.590
 pleas+0.587
ucket+0.575
Neg logit contributions
isphere-0.643
orth-0.618
л-0.600
arthed-0.589
enza-0.583
Token350
Token ID14877
Feature activation+1.27e-01

Pos logit contributions
isphere+0.683
orth+0.676
л+0.658
arthed+0.638
cliffe+0.632
Neg logit contributions
 disag-0.618
Sah-0.566
Saharan-0.560
 pleas-0.553
ucket-0.545
Token x
Token ID2124
Feature activation-3.85e-02

Pos logit contributions
isphere+0.632
orth+0.617
л+0.583
arthed+0.555
enza+0.543
Neg logit contributions
 disag-1.551
Sah-1.463
Saharan-1.451
 pleas-1.448
ucket-1.427
Token
Token ID247
Feature activation-5.07e-01

Pos logit contributions
 disag+0.922
Sah+0.847
Saharan+0.845
 pleas+0.829
ucket+0.822
Neg logit contributions
isphere-1.024
orth-1.014
л-0.979
arthed-0.944
cliffe-0.944
Tokenble
Token ID903
Feature activation-3.00e-01

Pos logit contributions
 disag+4.248
Sah+4.082
Saharan+3.982
 pleas+3.903
uffy+3.812
Neg logit contributions
isphere-4.235
orth-4.112
л-3.962
arthed-3.936
cliffe-3.881
Token Prime
Token ID5537
Feature activation-6.31e-01

Pos logit contributions
 disag+2.456
Sah+2.275
Saharan+2.231
 pleas+2.229
ucket+2.150
Neg logit contributions
isphere-2.658
orth-2.585
л-2.497
arthed-2.487
enza-2.461
Token Minister
Token ID4139
Feature activation-4.85e-01

Pos logit contributions
 disag+4.173
Sah+3.903
 pleas+3.811
Saharan+3.729
ucket+3.668
Neg logit contributions
isphere-6.326
orth-6.099
л-5.953
arthed-5.936
enza-5.823
Token Sh
Token ID911
Feature activation-2.83e-01

Pos logit contributions
 disag+3.779
 pleas+3.465
Sah+3.425
Saharan+3.359
ucket+3.295
Neg logit contributions
isphere-4.431
orth-4.301
л-4.197
arthed-4.177
enza-4.115
Tokenri
Token ID380
Feature activation-1.48e+00

Pos logit contributions
 disag+2.765
Sah+2.588
 pleas+2.568
Saharan+2.546
ucket+2.509
Neg logit contributions
isphere-2.081
orth-1.987
л-1.928
arthed-1.907
cliffe-1.891
Token Narendra
Token ID28113
Feature activation-6.15e-01

Pos logit contributions
 disag+10.419
 pleas+10.005
Sah+9.939
Saharan+9.818
ucket+9.647
Neg logit contributions
isphere-11.985
orth-11.181
enza-10.749
cliffe-10.679
л-10.642
Token Modi
Token ID14637
Feature activation+2.42e-01

Pos logit contributions
 disag+1.957
 pleas+1.609
Sah+1.576
Saharan+1.488
uffy+1.312
Neg logit contributions
isphere-8.331
orth-8.238
л-8.053
arthed-8.007
enza-7.997
Token has
Token ID468
Feature activation-1.17e-01

Pos logit contributions
isphere+1.863
orth+1.843
л+1.783
arthed+1.701
cliffe+1.701
Neg logit contributions
 disag-2.255
Sah-2.107
Saharan-2.093
ucket-2.048
 pleas-2.041
Token approved
Token ID6325
Feature activation+1.73e-03

Pos logit contributions
 disag+1.107
 pleas+1.012
Sah+1.010
Saharan+1.003
ucket+0.976
Neg logit contributions
isphere-0.904
orth-0.897
л-0.870
arthed-0.841
enza-0.835
Token the
Token ID262
Feature activation-1.83e-02

Pos logit contributions
isphere+0.014
orth+0.014
л+0.014
arthed+0.013
cliffe+0.013
Neg logit contributions
 disag-0.015
Sah-0.014
Saharan-0.014
 pleas-0.014
ucket-0.014
Token,[
Token ID17414
Feature activation-2.06e-01

Pos logit contributions
 disag+0.184
Sah+0.171
Saharan+0.170
 pleas+0.168
ucket+0.166
Neg logit contributions
isphere-0.141
orth-0.139
л-0.135
arthed-0.130
enza-0.129
Token98
Token ID4089
Feature activation+3.05e-02

Pos logit contributions
 disag+1.565
Sah+1.438
Saharan+1.419
 pleas+1.389
uffy+1.369
Neg logit contributions
isphere-1.968
orth-1.924
л-1.896
enza-1.836
cliffe-1.823
Token]
Token ID60
Feature activation+2.88e-01

Pos logit contributions
isphere+0.220
orth+0.219
л+0.212
arthed+0.207
enza+0.201
Neg logit contributions
 disag-0.302
Sah-0.280
Saharan-0.279
 pleas-0.276
ucket-0.271
Token Sporting
Token ID31790
Feature activation-2.52e-01

Pos logit contributions
isphere+2.271
orth+2.259
л+2.182
arthed+2.105
cliffe+2.096
Neg logit contributions
 disag-2.632
Sah-2.440
Saharan-2.425
 pleas-2.392
ucket-2.365
Token News
Token ID3000
Feature activation-2.00e-01

Pos logit contributions
 disag+2.056
Sah+1.926
Saharan+1.893
 pleas+1.862
uffy+1.808
Neg logit contributions
isphere-2.197
orth-2.186
л-2.145
arthed-2.073
enza-2.059
Token,[
Token ID17414
Feature activation-1.41e+00

Pos logit contributions
 disag+1.873
Sah+1.733
Saharan+1.718
 pleas+1.694
ucket+1.679
Neg logit contributions
isphere-1.548
orth-1.510
л-1.478
arthed-1.416
enza-1.412
Token99
Token ID2079
Feature activation-1.68e-02

Pos logit contributions
 disag+6.561
Sah+6.026
uffy+5.847
 pleas+5.770
Saharan+5.763
Neg logit contributions
isphere-15.073
л-14.750
cliffe-14.374
enza-14.336
rity-14.252
Token]
Token ID60
Feature activation+3.56e-01

Pos logit contributions
 disag+0.163
Sah+0.152
Saharan+0.151
 pleas+0.149
ucket+0.147
Neg logit contributions
isphere-0.124
orth-0.123
л-0.120
arthed-0.116
enza-0.113
Token SB
Token ID18056
Feature activation-2.60e-01

Pos logit contributions
isphere+2.804
orth+2.797
л+2.695
arthed+2.598
cliffe+2.594
Neg logit contributions
 disag-3.237
Sah-3.003
Saharan-2.989
 pleas-2.943
ucket-2.912
Token Nation
Token ID8741
Feature activation-2.86e-01

Pos logit contributions
 disag+1.976
Sah+1.831
Saharan+1.811
ucket+1.758
 pleas+1.753
Neg logit contributions
isphere-2.450
orth-2.401
л-2.370
enza-2.278
arthed-2.278
Token,[
Token ID17414
Feature activation-1.03e+00

Pos logit contributions
 disag+2.626
Sah+2.425
Saharan+2.406
 pleas+2.374
ucket+2.351
Neg logit contributions
isphere-2.272
orth-2.211
л-2.170
enza-2.078
arthed-2.072
Token Pick
Token ID12346
Feature activation-3.93e-01

Pos logit contributions
 disag+5.389
Saharan+5.020
uffy+5.018
Sah+5.005
 pleas+4.958
Neg logit contributions
isphere-8.870
enza-8.701
rity-8.627
orth-8.549
arthed-8.526
Token J
Token ID449
Feature activation-5.07e-01

Pos logit contributions
 disag+3.531
Sah+3.251
 pleas+3.209
Saharan+3.207
ucket+3.157
Neg logit contributions
isphere-3.161
orth-3.067
л-2.975
arthed-2.898
enza-2.877
TokenAB
Token ID6242
Feature activation-3.54e-01

Pos logit contributions
 disag+4.762
Sah+4.560
Saharan+4.448
uffy+4.429
ucket+4.389
Neg logit contributions
isphere-3.731
orth-3.530
л-3.457
arthed-3.402
enza-3.294
Tokenarry
Token ID6532
Feature activation-6.58e-01

Pos logit contributions
 disag+3.141
Sah+2.915
 pleas+2.880
Saharan+2.874
uffy+2.862
Neg logit contributions
isphere-2.845
orth-2.758
л-2.702
arthed-2.627
enza-2.621
Token Maryland
Token ID10769
Feature activation-6.03e-01

Pos logit contributions
 disag+5.829
Sah+5.535
Saharan+5.371
ucket+5.357
 pleas+5.339
Neg logit contributions
isphere-5.080
orth-4.821
arthed-4.713
л-4.675
enza-4.570
Token 1
Token ID352
Feature activation-1.36e+00

Pos logit contributions
 disag+5.072
 pleas+4.644
Sah+4.638
Saharan+4.570
ucket+4.482
Neg logit contributions
isphere-5.083
orth-4.872
arthed-4.746
л-4.723
enza-4.621
Token hour
Token ID1711
Feature activation-3.31e-01

Pos logit contributions
 disag+10.500
Sah+10.221
 pleas+10.025
Saharan+9.961
uffy+9.386
Neg logit contributions
isphere-10.737
arthed-10.142
orth-9.653
cliffe-9.492
hetti-9.370
Token ago
Token ID2084
Feature activation-2.55e-01

Pos logit contributions
 disag+3.063
Saharan+2.828
Sah+2.825
 pleas+2.822
ucket+2.741
Neg logit contributions
isphere-2.572
orth-2.475
л-2.423
arthed-2.393
enza-2.345
Token This
Token ID770
Feature activation-2.71e-02

Pos logit contributions
 disag+2.351
Sah+2.191
 pleas+2.190
Saharan+2.163
uffy+2.098
Neg logit contributions
isphere-2.003
orth-1.931
л-1.858
arthed-1.842
enza-1.810
Token election
Token ID3071
Feature activation-2.97e-01

Pos logit contributions
 disag+0.243
Sah+0.222
 pleas+0.221
Saharan+0.220
ucket+0.214
Neg logit contributions
isphere-0.223
orth-0.221
л-0.215
arthed-0.210
cliffe-0.206
Token was
Token ID373
Feature activation-2.73e-01

Pos logit contributions
 disag+2.571
 pleas+2.325
Sah+2.306
Saharan+2.291
uffy+2.207
Neg logit contributions
orth-2.486
isphere-2.461
л-2.434
arthed-2.372
cliffe-2.340
Token,
Token ID11
Feature activation-2.78e-01

Pos logit contributions
 disag+2.298
 pleas+2.071
Sah+2.067
Saharan+2.040
uffy+2.003
Neg logit contributions
isphere-2.025
orth-2.004
л-1.961
arthed-1.916
enza-1.901
Token and
Token ID290
Feature activation-2.86e-01

Pos logit contributions
 disag+2.450
 pleas+2.209
Sah+2.196
Saharan+2.154
uffy+2.106
Neg logit contributions
isphere-2.349
orth-2.289
л-2.254
arthed-2.199
enza-2.190
Token four
Token ID1440
Feature activation-6.15e-01

Pos logit contributions
 disag+2.427
 pleas+2.201
Sah+2.186
Saharan+2.135
uffy+2.103
Neg logit contributions
isphere-2.500
orth-2.431
л-2.394
arthed-2.345
enza-2.308
Token panel
Token ID6103
Feature activation-4.00e-01

Pos logit contributions
 disag+5.065
 pleas+4.573
Sah+4.411
uffy+4.349
Saharan+4.285
Neg logit contributions
isphere-5.336
orth-5.235
arthed-5.176
л-5.114
enza-5.113
Tokenists
Token ID1023
Feature activation-1.17e+00

Pos logit contributions
 disag+3.660
 pleas+3.430
Sah+3.347
Saharan+3.304
uffy+3.289
Neg logit contributions
isphere-3.093
orth-3.027
л-2.948
enza-2.924
arthed-2.920
Token voting
Token ID6709
Feature activation-1.34e+00

Pos logit contributions
 disag+8.509
 pleas+7.613
 uncons+6.935
uffy+6.783
Sah+6.620
Neg logit contributions
arthed-10.411
orth-10.329
enza-10.289
isphere-10.260
л-10.102
Token in
Token ID287
Feature activation-1.04e+00

Pos logit contributions
 disag+9.230
 pleas+7.938
 uncons+7.618
uffy+7.444
Saharan+7.409
Neg logit contributions
arthed-11.877
orth-11.725
isphere-11.495
л-11.366
rity-11.346
Token favour
Token ID7075
Feature activation-4.05e-01

Pos logit contributions
 disag+7.567
 pleas+6.761
uffy+6.616
Sah+6.487
Saharan+6.400
Neg logit contributions
isphere-9.615
л-9.161
orth-9.142
arthed-9.032
enza-8.987
Token of
Token ID286
Feature activation+2.56e-01

Pos logit contributions
 disag+3.736
 pleas+3.401
Sah+3.393
Saharan+3.369
uffy+3.283
Neg logit contributions
isphere-3.187
orth-3.150
л-3.061
arthed-2.972
enza-2.942
Token a
Token ID257
Feature activation+5.48e-02

Pos logit contributions
isphere+2.046
orth+2.032
л+1.966
arthed+1.896
cliffe+1.881
Neg logit contributions
 disag-2.298
Sah-2.148
Saharan-2.127
 pleas-2.085
ucket-2.085
Token redesign
Token ID27135
Feature activation-3.07e-01

Pos logit contributions
isphere+0.442
orth+0.435
л+0.423
arthed+0.409
enza+0.405
Neg logit contributions
 disag-0.501
Sah-0.460
Saharan-0.456
 pleas-0.454
ucket-0.444
Token
Token ID851
Feature activation-2.78e-01

Pos logit contributions
 disag+0.725
Sah+0.669
 pleas+0.669
Saharan+0.662
uffy+0.644
Neg logit contributions
isphere-0.611
orth-0.598
л-0.576
arthed-0.563
enza-0.559
Token Golden
Token ID8407
Feature activation-8.18e-02

Pos logit contributions
 disag+2.446
Sah+2.257
 pleas+2.222
Saharan+2.202
uffy+2.128
Neg logit contributions
isphere-2.319
orth-2.281
л-2.194
arthed-2.146
enza-2.135
TokenState
Token ID9012
Feature activation-2.60e-02

Pos logit contributions
 disag+0.869
Sah+0.821
Saharan+0.807
 pleas+0.802
ucket+0.788
Neg logit contributions
isphere-0.533
orth-0.513
л-0.497
arthed-0.481
enza-0.477
TokenWar
Token ID13195
Feature activation-5.93e-01

Pos logit contributions
 disag+0.205
Sah+0.188
Saharan+0.186
 pleas+0.183
ucket+0.180
Neg logit contributions
isphere-0.240
orth-0.237
л-0.231
arthed-0.224
cliffe-0.223
Tokenriors
Token ID8657
Feature activation+1.80e-01

Pos logit contributions
 disag+4.105
Sah+3.699
 pleas+3.645
Saharan+3.584
ucket+3.554
Neg logit contributions
isphere-5.783
orth-5.647
arthed-5.534
л-5.451
enza-5.429
Token (@
Token ID4275
Feature activation-1.32e+00

Pos logit contributions
isphere+1.497
orth+1.490
л+1.449
arthed+1.398
cliffe+1.386
Neg logit contributions
 disag-1.582
Sah-1.454
Saharan-1.444
 pleas-1.431
ucket-1.411
Tokenwar
Token ID5767
Feature activation-5.98e-01

Pos logit contributions
Sah+10.305
 disag+10.028
Saharan+9.881
 pleas+9.287
uffy+9.274
Neg logit contributions
isphere-9.511
 liner-9.450
enza-9.074
 Baltic-8.837
orth-8.834
Tokenriors
Token ID8657
Feature activation+1.11e-01

Pos logit contributions
 disag+4.292
 pleas+3.845
uffy+3.812
Sah+3.809
ucket+3.757
Neg logit contributions
orth-5.444
isphere-5.441
л-5.414
arthed-5.375
enza-5.265
Token)
Token ID8
Feature activation+3.61e-01

Pos logit contributions
isphere+0.683
orth+0.675
л+0.647
arthed+0.619
cliffe+0.611
Neg logit contributions
 disag-1.211
Sah-1.134
Saharan-1.129
 pleas-1.120
ucket-1.107
Token September
Token ID2693
Feature activation+2.78e-02

Pos logit contributions
isphere+2.699
orth+2.691
л+2.622
cliffe+2.499
arthed+2.487
Neg logit contributions
 disag-3.420
Sah-3.171
Saharan-3.166
 pleas-3.107
ucket-3.097
Token 24
Token ID1987
Feature activation-4.00e-03

Pos logit contributions
isphere+0.241
orth+0.236
л+0.229
arthed+0.223
enza+0.221
Neg logit contributions
 disag-0.235
Sah-0.219
Saharan-0.216
 pleas-0.214
ucket-0.208
Token 11
Token ID1367
Feature activation-4.24e-01

Pos logit contributions
isphere+2.125
orth+2.094
л+2.034
arthed+1.959
cliffe+1.952
Neg logit contributions
 disag-2.373
Sah-2.210
Saharan-2.186
 pleas-2.136
ucket-2.134
Token:
Token ID25
Feature activation-3.58e-01

Pos logit contributions
 disag+3.980
 pleas+3.722
Sah+3.691
Saharan+3.648
ucket+3.600
Neg logit contributions
isphere-3.189
orth-3.054
arthed-2.951
л-2.943
enza-2.871
Token50
Token ID1120
Feature activation-8.92e-01

Pos logit contributions
 disag+2.671
Sah+2.603
Saharan+2.549
 pleas+2.518
ucket+2.399
Neg logit contributions
isphere-3.386
orth-3.239
arthed-3.138
л-3.121
enza-3.100
Token AM
Token ID3001
Feature activation-5.12e-01

Pos logit contributions
 disag+5.786
Sah+5.546
 pleas+5.508
Saharan+5.454
uffy+5.362
Neg logit contributions
isphere-8.800
orth-8.275
arthed-8.187
л-8.026
 liner-7.899
Token ET
Token ID12152
Feature activation-8.24e-01

Pos logit contributions
 disag+4.331
 pleas+3.945
Sah+3.864
Saharan+3.848
uffy+3.785
Neg logit contributions
isphere-4.323
orth-4.142
arthed-4.084
л-3.990
rity-3.925
Token Fri
Token ID19480
Feature activation-1.31e+00

Pos logit contributions
 disag+4.470
 pleas+4.443
Sah+4.197
Saharan+4.040
 DAV+3.780
Neg logit contributions
isphere-9.288
arthed-8.619
orth-8.564
rity-8.466
л-8.050
Token,
Token ID11
Feature activation-8.08e-01

Pos logit contributions
 disag+7.607
 pleas+7.088
Saharan+6.725
Sah+6.569
ucket+6.446
Neg logit contributions
isphere-12.423
arthed-12.321
rity-12.055
orth-11.660
 liner-11.160
Token 28
Token ID2579
Feature activation-3.98e-01

Pos logit contributions
 disag+5.330
Sah+5.308
 pleas+5.111
Saharan+5.033
 DAV+4.697
Neg logit contributions
isphere-7.956
orth-7.438
arthed-7.394
enza-7.170
rity-7.067
Token July
Token ID2901
Feature activation+1.31e-02

Pos logit contributions
 disag+3.036
 pleas+2.844
Sah+2.842
Saharan+2.808
uffy+2.608
Neg logit contributions
isphere-3.687
orth-3.552
arthed-3.483
enza-3.407
л-3.391
Token 2017
Token ID2177
Feature activation-3.86e-01

Pos logit contributions
isphere+0.124
orth+0.120
л+0.118
arthed+0.115
enza+0.114
Neg logit contributions
 disag-0.100
Sah-0.091
Saharan-0.091
 pleas-0.091
ucket-0.088
Token |
Token ID930
Feature activation-7.48e-01

Pos logit contributions
 disag+3.472
 pleas+3.391
Saharan+3.348
Sah+3.339
 DAV+3.174
Neg logit contributions
isphere-3.015
orth-2.819
arthed-2.775
л-2.665
rity-2.633
Token Reserve
Token ID12224
Feature activation+4.68e-01

Pos logit contributions
isphere+1.613
orth+1.593
л+1.543
arthed+1.489
cliffe+1.471
Neg logit contributions
 disag-2.033
Sah-1.885
Saharan-1.868
 pleas-1.854
ucket-1.825
Token and
Token ID290
Feature activation-6.59e-03

Pos logit contributions
isphere+2.986
orth+2.975
л+2.928
cliffe+2.741
arthed+2.738
Neg logit contributions
 disag-4.914
Sah-4.566
Saharan-4.560
ucket-4.500
 pleas-4.495
Token Western
Token ID4885
Feature activation-6.02e-02

Pos logit contributions
 disag+0.059
Sah+0.054
Saharan+0.054
 pleas+0.054
ucket+0.052
Neg logit contributions
isphere-0.054
orth-0.054
л-0.052
arthed-0.050
enza-0.050
Token Front
Token ID8880
Feature activation-4.14e-01

Pos logit contributions
 disag+0.585
Sah+0.545
Saharan+0.540
 pleas+0.538
ucket+0.524
Neg logit contributions
isphere-0.445
orth-0.436
л-0.422
arthed-0.411
enza-0.403
Tokens
Token ID82
Feature activation+1.08e-02

Pos logit contributions
 disag+3.718
Sah+3.404
 pleas+3.368
Saharan+3.349
uffy+3.236
Neg logit contributions
isphere-3.332
orth-3.244
л-3.156
arthed-3.121
enza-3.085
Token.[
Token ID3693
Feature activation-1.31e+00

Pos logit contributions
isphere+0.082
orth+0.081
л+0.079
arthed+0.076
enza+0.075
Neg logit contributions
 disag-0.102
Sah-0.095
Saharan-0.094
 pleas-0.093
ucket-0.091
Token30
Token ID1270
Feature activation+6.61e-02

Pos logit contributions
Sah+7.097
 disag+7.017
Saharan+6.773
 pleas+6.314
uffy+6.238
Neg logit contributions
isphere-12.635
orth-12.608
 liner-12.100
enza-12.030
л-11.965
Token]
Token ID60
Feature activation+1.65e-01

Pos logit contributions
isphere+0.516
orth+0.507
л+0.492
arthed+0.475
enza+0.471
Neg logit contributions
 disag-0.617
Sah-0.574
Saharan-0.568
 pleas-0.563
ucket-0.554
Token On
Token ID1550
Feature activation+2.96e-01

Pos logit contributions
isphere+1.179
orth+1.155
л+1.111
arthed+1.074
enza+1.063
Neg logit contributions
 disag-1.648
Sah-1.545
Saharan-1.528
 pleas-1.514
ucket-1.489
Token 10
Token ID838
Feature activation+1.77e-01

Pos logit contributions
isphere+2.404
orth+2.381
л+2.311
arthed+2.222
cliffe+2.218
Neg logit contributions
 disag-2.642
Sah-2.439
Saharan-2.420
 pleas-2.385
ucket-2.375
Token October
Token ID3267
Feature activation+5.96e-01

Pos logit contributions
isphere+1.316
orth+1.302
л+1.260
arthed+1.211
cliffe+1.200
Neg logit contributions
 disag-1.707
Sah-1.586
Saharan-1.573
 pleas-1.557
ucket-1.539
Token paper
Token ID3348
Feature activation+2.17e-01

Pos logit contributions
 disag+2.164
 pleas+1.904
Sah+1.888
Saharan+1.856
uffy+1.785
Neg logit contributions
isphere-4.216
orth-4.150
л-4.102
enza-3.978
arthed-3.963
Token towel
Token ID24808
Feature activation+4.89e-01

Pos logit contributions
isphere+1.793
orth+1.777
л+1.725
arthed+1.668
cliffe+1.655
Neg logit contributions
 disag-1.916
Sah-1.769
Saharan-1.753
 pleas-1.731
ucket-1.709
Token-
Token ID12
Feature activation+7.65e-01

Pos logit contributions
orth+3.165
isphere+3.130
л+3.008
cliffe+2.888
arthed+2.888
Neg logit contributions
 disag-5.065
Sah-4.775
Saharan-4.758
ucket-4.651
 pleas-4.627
Tokenlined
Token ID10837
Feature activation-1.48e-02

Pos logit contributions
orth+4.560
isphere+4.316
cliffe+4.158
л+4.150
arthed+4.033
Neg logit contributions
 disag-8.480
Sah-7.802
 pleas-7.706
ucket-7.675
Saharan-7.647
Token plate
Token ID7480
Feature activation+3.54e-03

Pos logit contributions
 disag+0.123
Sah+0.112
Saharan+0.111
 pleas+0.110
ucket+0.108
Neg logit contributions
isphere-0.131
orth-0.130
л-0.126
arthed-0.122
cliffe-0.121
Token.
Token ID13
Feature activation-1.31e+00

Pos logit contributions
isphere+0.027
orth+0.026
л+0.025
arthed+0.024
enza+0.024
Neg logit contributions
 disag-0.034
Sah-0.032
Saharan-0.031
 pleas-0.031
ucket-0.031
Token Serve
Token ID35557
Feature activation+1.76e-01

Pos logit contributions
 disag+3.690
Sah+3.537
 pleas+3.483
Saharan+3.063
 DAV+2.859
Neg logit contributions
isphere-16.763
orth-16.488
enza-15.797
л-15.643
arthed-15.612
Token hot
Token ID3024
Feature activation-1.69e-01

Pos logit contributions
isphere+1.351
orth+1.340
л+1.300
arthed+1.251
cliffe+1.239
Neg logit contributions
 disag-1.658
Sah-1.540
Saharan-1.529
 pleas-1.501
ucket-1.491
Token!
Token ID0
Feature activation-2.50e-01

Pos logit contributions
 disag+1.616
Sah+1.532
 pleas+1.521
Saharan+1.503
ucket+1.484
Neg logit contributions
isphere-1.253
orth-1.216
л-1.161
arthed-1.152
enza-1.134
Token<|endoftext|>
Token ID50256
Feature activation-3.27e-01

Pos logit contributions
 disag+2.500
Sah+2.327
Saharan+2.307
 pleas+2.298
ucket+2.265
Neg logit contributions
isphere-1.759
orth-1.745
л-1.672
arthed-1.608
enza-1.594
TokenImage
Token ID5159
Feature activation-2.75e-02

Pos logit contributions
 disag+2.964
Sah+2.932
Saharan+2.869
 pleas+2.767
ucket+2.738
Neg logit contributions
isphere-2.516
orth-2.425
л-2.342
arthed-2.308
 liner-2.296
Token [
Token ID685
Feature activation+1.54e-02

Pos logit contributions
isphere+0.168
orth+0.164
л+0.158
arthed+0.153
enza+0.151
Neg logit contributions
 disag-0.217
Sah-0.204
Saharan-0.201
 pleas-0.199
ucket-0.196
TokenUPDATE
Token ID16977
Feature activation-5.04e-02

Pos logit contributions
isphere+0.119
orth+0.117
л+0.114
arthed+0.110
enza+0.109
Neg logit contributions
 disag-0.145
Sah-0.137
Saharan-0.135
 pleas-0.133
ucket-0.130
Token,
Token ID11
Feature activation-4.23e-01

Pos logit contributions
 disag+0.489
Sah+0.454
Saharan+0.449
 pleas+0.448
ucket+0.436
Neg logit contributions
isphere-0.375
orth-0.368
л-0.353
arthed-0.346
cliffe-0.342
Token 7
Token ID767
Feature activation-7.32e-01

Pos logit contributions
 disag+3.451
 pleas+3.107
Sah+3.107
Saharan+3.055
uffy+2.907
Neg logit contributions
isphere-3.781
orth-3.693
arthed-3.556
л-3.537
enza-3.488
Token:
Token ID25
Feature activation-3.43e-01

Pos logit contributions
 disag+6.405
Sah+5.957
 pleas+5.955
Saharan+5.798
uffy+5.666
Neg logit contributions
isphere-5.819
orth-5.510
arthed-5.402
enza-5.212
cliffe-5.208
Token01
Token ID486
Feature activation-1.30e+00

Pos logit contributions
 disag+2.448
Sah+2.400
Saharan+2.344
 pleas+2.305
ucket+2.180
Neg logit contributions
isphere-3.368
orth-3.214
arthed-3.125
л-3.101
enza-3.099
Token p
Token ID279
Feature activation-4.02e-01

Pos logit contributions
 disag+6.862
 pleas+6.268
Sah+6.050
Saharan+5.838
uffy+5.712
Neg logit contributions
isphere-13.354
orth-12.842
arthed-12.597
л-12.410
enza-12.280
Token.
Token ID13
Feature activation-1.62e-01

Pos logit contributions
 disag+3.269
Sah+3.184
Saharan+3.115
 pleas+3.100
uffy+2.968
Neg logit contributions
isphere-3.507
orth-3.306
arthed-3.248
л-3.221
enza-3.217
Tokenm
Token ID76
Feature activation-2.07e-01

Pos logit contributions
 disag+1.752
Sah+1.694
Saharan+1.688
 pleas+1.664
uffy+1.625
Neg logit contributions
isphere-0.986
orth-0.918
л-0.896
arthed-0.882
 liner-0.873
Token.:
Token ID11207
Feature activation+1.60e-01

Pos logit contributions
 disag+2.285
Sah+2.143
Saharan+2.127
 pleas+2.113
ucket+2.089
Neg logit contributions
isphere-1.264
orth-1.241
л-1.190
arthed-1.144
cliffe-1.127
Token CNN
Token ID8100
Feature activation-8.43e-02

Pos logit contributions
isphere+1.248
orth+1.233
л+1.196
arthed+1.153
cliffe+1.141
Neg logit contributions
 disag-1.494
Sah-1.384
Saharan-1.372
 pleas-1.358
ucket-1.340
Token everything
Token ID2279
Feature activation-1.03e-01

Pos logit contributions
isphere+0.320
orth+0.317
л+0.308
arthed+0.298
enza+0.296
Neg logit contributions
 disag-0.336
Sah-0.306
 pleas-0.305
Saharan-0.304
ucket-0.296
Token?
Token ID30
Feature activation-5.46e-01

Pos logit contributions
 disag+0.988
Sah+0.914
 pleas+0.910
Saharan+0.904
ucket+0.884
Neg logit contributions
isphere-0.768
orth-0.764
л-0.736
arthed-0.715
enza-0.704
Token Flag
Token ID19762
Feature activation-5.49e-01

Pos logit contributions
 disag+4.626
Sah+4.318
 pleas+4.287
Saharan+4.183
uffy+4.059
Neg logit contributions
isphere-4.468
orth-4.349
arthed-4.315
enza-4.173
л-4.147
Token
Token ID198
Feature activation-3.89e-01

Pos logit contributions
 disag+4.974
Sah+4.776
Saharan+4.693
 pleas+4.633
uffy+4.539
Neg logit contributions
isphere-4.166
orth-4.051
arthed-3.869
л-3.860
enza-3.823
Token
Token ID198
Feature activation-6.65e-01

Pos logit contributions
 disag+3.405
Sah+3.300
Saharan+3.263
 pleas+3.247
uffy+3.090
Neg logit contributions
isphere-3.192
orth-2.991
arthed-2.917
л-2.916
enza-2.845
TokenFlag
Token ID34227
Feature activation-1.29e+00

Pos logit contributions
Sah+3.573
Saharan+3.480
 disag+3.273
 pleas+3.034
ucket+2.998
Neg logit contributions
isphere-7.425
 liner-7.153
orth-7.118
arthed-7.095
rity-6.952
Token Reply
Token ID14883
Feature activation-2.47e-01

Pos logit contributions
 disag+4.550
 pleas+4.221
Sah+3.868
Saharan+3.808
 uncons+3.367
Neg logit contributions
isphere-15.217
orth-15.097
arthed-14.931
enza-14.639
rity-14.401
Token
Token ID198
Feature activation-3.63e-01

Pos logit contributions
 disag+2.363
Sah+2.238
Saharan+2.218
 pleas+2.215
ucket+2.142
Neg logit contributions
isphere-1.850
orth-1.781
л-1.722
arthed-1.690
enza-1.653
Token
Token ID198
Feature activation-5.68e-01

Pos logit contributions
 disag+3.229
Sah+3.132
Saharan+3.095
 pleas+3.075
uffy+2.925
Neg logit contributions
isphere-2.957
orth-2.758
arthed-2.702
л-2.692
enza-2.626
Token27
Token ID1983
Feature activation-7.75e-01

Pos logit contributions
Sah+4.325
 disag+4.219
Saharan+4.168
 pleas+4.010
ucket+3.842
Neg logit contributions
isphere-5.156
orth-4.816
arthed-4.787
 liner-4.674
rity-4.670
Token Recommend
Token ID30361
Feature activation-1.88e-01

Pos logit contributions
 disag+3.686
Sah+3.388
Saharan+3.386
 pleas+3.258
uffy+2.971
Neg logit contributions
isphere-9.238
orth-8.699
arthed-8.656
rity-8.608
enza-8.604
TokenRecommend
Token ID41248
Feature activation-8.74e-01

Pos logit contributions
Saharan+3.638
 disag+3.612
Sah+3.592
 pleas+3.121
ucket+3.104
Neg logit contributions
isphere-8.779
arthed-8.549
 liner-8.380
cliffe-8.355
л-8.351
Token Share
Token ID8734
Feature activation-5.71e-01

Pos logit contributions
 disag+3.081
Sah+2.646
ucket+2.537
Saharan+2.534
 pleas+2.495
Neg logit contributions
isphere-11.058
arthed-11.026
orth-10.911
л-10.722
cliffe-10.659
Token this
Token ID428
Feature activation-5.72e-01

Pos logit contributions
 disag+4.858
 pleas+4.492
Saharan+4.399
Sah+4.398
ucket+4.276
Neg logit contributions
isphere-4.982
orth-4.731
л-4.591
arthed-4.504
enza-4.426
Token comment
Token ID2912
Feature activation-8.58e-01

Pos logit contributions
 disag+4.031
 pleas+3.776
Saharan+3.491
Sah+3.490
 uncons+3.426
Neg logit contributions
isphere-5.761
orth-5.512
arthed-5.479
л-5.309
rity-5.217
Token on
Token ID319
Feature activation-4.58e-01

Pos logit contributions
 disag+5.584
 pleas+5.235
Saharan+5.084
Sah+5.028
ucket+4.726
Neg logit contributions
isphere-8.800
orth-8.184
arthed-8.047
rity-8.026
enza-7.976
Token Facebook
Token ID3203
Feature activation-1.27e+00

Pos logit contributions
 disag+2.870
Sah+2.681
 pleas+2.643
Saharan+2.597
ucket+2.522
Neg logit contributions
isphere-4.876
orth-4.754
arthed-4.626
enza-4.524
л-4.490
Token Share
Token ID8734
Feature activation-5.36e-01

Pos logit contributions
 disag+3.316
Sah+2.908
 pleas+2.884
Saharan+2.716
 DAV+2.124
Neg logit contributions
isphere-16.817
orth-16.657
arthed-16.470
enza-15.891
л-15.860
Token this
Token ID428
Feature activation-6.91e-01

Pos logit contributions
 disag+4.551
 pleas+4.303
Saharan+4.173
Sah+4.142
ucket+4.040
Neg logit contributions
isphere-4.580
orth-4.376
л-4.239
arthed-4.228
enza-4.130
Token comment
Token ID2912
Feature activation-9.10e-01

Pos logit contributions
 disag+4.734
 pleas+4.473
Saharan+4.112
Sah+4.060
 uncons+4.010
Neg logit contributions
isphere-6.897
orth-6.661
arthed-6.604
л-6.388
rity-6.298
Token on
Token ID319
Feature activation+1.89e-02

Pos logit contributions
 disag+5.808
 pleas+5.533
Saharan+5.322
Sah+5.229
uffy+4.922
Neg logit contributions
isphere-9.180
orth-8.654
arthed-8.564
rity-8.480
ortunately-8.474
Token Twitter
Token ID3009
Feature activation-8.13e-01

Pos logit contributions
isphere+0.180
orth+0.178
л+0.173
arthed+0.169
enza+0.167
Neg logit contributions
 disag-0.143
Sah-0.131
Saharan-0.130
 pleas-0.128
ucket-0.125
Token make
Token ID787
Feature activation-5.90e-02

Pos logit contributions
 disag+1.885
Sah+1.727
 pleas+1.717
Saharan+1.697
ucket+1.663
Neg logit contributions
isphere-1.784
orth-1.746
arthed-1.705
л-1.679
cliffe-1.648
Token a
Token ID257
Feature activation-1.92e-02

Pos logit contributions
 disag+0.522
Sah+0.482
 pleas+0.479
Saharan+0.477
ucket+0.469
Neg logit contributions
isphere-0.491
orth-0.483
л-0.466
arthed-0.459
enza-0.451
Token living
Token ID2877
Feature activation-6.64e-02

Pos logit contributions
 disag+0.165
Sah+0.152
Saharan+0.150
 pleas+0.150
ucket+0.147
Neg logit contributions
isphere-0.165
orth-0.163
л-0.158
arthed-0.154
cliffe-0.152
Token doing
Token ID1804
Feature activation-2.60e-01

Pos logit contributions
 disag+0.596
Sah+0.547
 pleas+0.545
Saharan+0.541
ucket+0.528
Neg logit contributions
isphere-0.548
orth-0.539
л-0.515
arthed-0.512
enza-0.503
Token something
Token ID1223
Feature activation-3.93e-01

Pos logit contributions
 disag+2.349
 pleas+2.188
Saharan+2.146
Sah+2.138
ucket+2.086
Neg logit contributions
isphere-2.128
orth-2.070
л-1.976
arthed-1.972
enza-1.936
Token you
Token ID345
Feature activation-1.25e+00

Pos logit contributions
 disag+4.068
 pleas+3.921
Sah+3.789
Saharan+3.738
uffy+3.672
Neg logit contributions
isphere-2.608
orth-2.525
arthed-2.460
л-2.434
enza-2.376
Token not
Token ID407
Feature activation-1.04e+00

Pos logit contributions
 disag+8.389
 pleas+8.139
Sah+7.419
Saharan+7.349
 uncons+7.230
Neg logit contributions
isphere-11.229
arthed-10.919
orth-10.504
cliffe-10.339
enza-10.121
Token only
Token ID691
Feature activation-3.26e-01

Pos logit contributions
 disag+7.697
 pleas+7.641
ucket+7.007
Sah+6.954
Saharan+6.867
Neg logit contributions
isphere-8.902
arthed-8.541
orth-8.323
cliffe-8.215
л-8.210
Token like
Token ID588
Feature activation-2.89e-01

Pos logit contributions
 disag+2.095
 pleas+1.911
Sah+1.863
Saharan+1.831
ucket+1.787
Neg logit contributions
isphere-3.478
orth-3.379
arthed-3.318
л-3.313
cliffe-3.249
Token doing
Token ID1804
Feature activation-5.29e-02

Pos logit contributions
 disag+2.614
 pleas+2.442
Sah+2.417
Saharan+2.402
ucket+2.358
Neg logit contributions
isphere-2.329
orth-2.243
arthed-2.155
л-2.151
enza-2.123
Token,
Token ID11
Feature activation+3.22e-01

Pos logit contributions
 disag+0.502
Sah+0.464
Saharan+0.462
 pleas+0.461
ucket+0.452
Neg logit contributions
isphere-0.406
orth-0.397
л-0.383
arthed-0.376
enza-0.369
Token available
Token ID1695
Feature activation+3.43e-01

Pos logit contributions
isphere+3.789
orth+3.745
л+3.615
arthed+3.504
enza+3.459
Neg logit contributions
 disag-4.225
Sah-3.970
Saharan-3.917
ucket-3.867
 pleas-3.841
Token since
Token ID1201
Feature activation-4.66e-02

Pos logit contributions
isphere+2.601
orth+2.566
л+2.491
arthed+2.384
enza+2.370
Neg logit contributions
 disag-3.218
Sah-3.027
Saharan-2.994
ucket-2.942
 pleas-2.939
Token 16
Token ID1467
Feature activation-1.63e-01

Pos logit contributions
 disag+0.405
Sah+0.369
Saharan+0.365
 pleas+0.363
ucket+0.351
Neg logit contributions
isphere-0.401
orth-0.395
л-0.382
arthed-0.371
enza-0.367
Token July
Token ID2901
Feature activation+2.55e-01

Pos logit contributions
 disag+1.418
Sah+1.313
Saharan+1.293
 pleas+1.283
ucket+1.253
Neg logit contributions
isphere-1.390
orth-1.347
arthed-1.295
л-1.294
enza-1.269
Token 2007
Token ID4343
Feature activation-2.46e-01

Pos logit contributions
isphere+2.059
orth+2.038
л+1.979
arthed+1.909
cliffe+1.892
Neg logit contributions
 disag-2.307
Sah-2.133
Saharan-2.115
 pleas-2.090
ucket-2.064
Token.[
Token ID3693
Feature activation-1.23e+00

Pos logit contributions
 disag+2.243
Sah+2.034
Saharan+2.015
 pleas+2.006
ucket+1.956
Neg logit contributions
isphere-1.969
orth-1.929
л-1.889
arthed-1.842
enza-1.819
Token19
Token ID1129
Feature activation-3.81e-01

Pos logit contributions
 disag+6.756
Sah+6.510
Saharan+6.302
 pleas+6.187
ucket+5.934
Neg logit contributions
isphere-12.018
л-11.611
 liner-11.422
arthed-11.411
orth-11.354
Token]
Token ID60
Feature activation+3.75e-02

Pos logit contributions
 disag+3.436
Sah+3.181
Saharan+3.143
 pleas+3.116
ucket+3.075
Neg logit contributions
isphere-3.054
orth-2.987
л-2.904
cliffe-2.799
arthed-2.793
Token
Token ID198
Feature activation+8.19e-02

Pos logit contributions
isphere+0.269
orth+0.264
л+0.255
arthed+0.245
enza+0.243
Neg logit contributions
 disag-0.375
Sah-0.349
Saharan-0.347
 pleas-0.342
ucket-0.337
Token
Token ID198
Feature activation-2.53e-01

Pos logit contributions
isphere+0.560
orth+0.548
л+0.529
arthed+0.509
enza+0.502
Neg logit contributions
 disag-0.846
Sah-0.793
Saharan-0.787
 pleas-0.780
ucket-0.768
Token$
Token ID3
Feature activation+4.22e-01

Pos logit contributions
 disag+2.243
Sah+2.176
Saharan+2.151
 pleas+2.038
ucket+2.020
Neg logit contributions
isphere-2.045
orth-1.959
л-1.917
arthed-1.877
cliffe-1.876
Token Sven
Token ID44611
Feature activation+4.44e-01

Pos logit contributions
isphere+2.034
orth+2.017
л+1.952
arthed+1.883
enza+1.865
Neg logit contributions
 disag-2.307
Sah-2.131
Saharan-2.115
 pleas-2.092
ucket-2.062
Tokens
Token ID82
Feature activation+3.11e-01

Pos logit contributions
isphere+3.139
orth+3.125
л+2.995
enza+2.861
arthed+2.859
Neg logit contributions
 disag-4.429
Saharan-4.112
Sah-4.111
 pleas-4.067
ucket-4.023
Tokenka
Token ID4914
Feature activation+3.46e-01

Pos logit contributions
isphere+2.385
orth+2.360
л+2.285
arthed+2.199
cliffe+2.182
Neg logit contributions
 disag-2.953
Sah-2.731
Saharan-2.713
 pleas-2.684
ucket-2.650
Token Te
Token ID1665
Feature activation+3.84e-01

Pos logit contributions
isphere+2.729
orth+2.716
л+2.625
arthed+2.520
enza+2.513
Neg logit contributions
 disag-3.174
Sah-2.940
Saharan-2.930
 pleas-2.880
ucket-2.849
Tokenater
Token ID729
Feature activation+1.76e-01

Pos logit contributions
isphere+3.113
orth+3.088
л+2.981
arthed+2.875
enza+2.851
Neg logit contributions
 disag-3.454
Sah-3.182
Saharan-3.175
 pleas-3.123
ucket-3.087
Token.[
Token ID3693
Feature activation-1.23e+00

Pos logit contributions
isphere+1.335
orth+1.318
л+1.279
arthed+1.233
cliffe+1.219
Neg logit contributions
 disag-1.677
Sah-1.557
Saharan-1.541
 pleas-1.527
ucket-1.508
Token26
Token ID2075
Feature activation-3.66e-01

Pos logit contributions
 disag+6.734
Sah+6.521
Saharan+6.248
 pleas+5.953
uffy+5.902
Neg logit contributions
isphere-12.148
orth-11.907
л-11.711
rity-11.519
enza-11.504
Token]
Token ID60
Feature activation+2.93e-02

Pos logit contributions
 disag+3.331
Sah+3.089
Saharan+3.050
 pleas+3.027
ucket+2.990
Neg logit contributions
isphere-2.908
orth-2.863
л-2.770
cliffe-2.675
arthed-2.672
Token
Token ID198
Feature activation-1.76e-01

Pos logit contributions
isphere+0.220
orth+0.217
л+0.207
enza+0.200
arthed+0.200
Neg logit contributions
 disag-0.282
Sah-0.263
Saharan-0.261
 pleas-0.258
ucket-0.254
Token
Token ID198
Feature activation-2.58e-01

Pos logit contributions
 disag+1.668
Sah+1.597
Saharan+1.583
 pleas+1.569
ucket+1.512
Neg logit contributions
isphere-1.347
orth-1.279
л-1.238
arthed-1.223
enza-1.206
TokenIn
Token ID818
Feature activation+9.24e-02

Pos logit contributions
 disag+2.227
Sah+2.182
Saharan+2.150
 pleas+2.051
ucket+2.046
Neg logit contributions
isphere-2.098
orth-2.038
л-1.960
enza-1.930
arthed-1.928
Token St
Token ID520
Feature activation-2.96e-01

Pos logit contributions
 disag+5.014
Saharan+4.677
 pleas+4.673
Sah+4.620
ucket+4.475
Neg logit contributions
isphere-4.898
л-4.642
orth-4.602
arthed-4.525
enza-4.372
Token Lucia
Token ID48158
Feature activation-2.86e-01

Pos logit contributions
 disag+2.641
Sah+2.457
Saharan+2.439
uffy+2.415
ucket+2.413
Neg logit contributions
isphere-2.341
л-2.268
orth-2.266
arthed-2.213
cliffe-2.147
Token from
Token ID422
Feature activation-2.61e-01

Pos logit contributions
 disag+2.515
 pleas+2.294
Sah+2.281
Saharan+2.276
ucket+2.232
Neg logit contributions
isphere-2.366
orth-2.310
л-2.290
arthed-2.231
enza-2.168
Token £
Token ID4248
Feature activation-2.69e-01

Pos logit contributions
 disag+2.503
Sah+2.308
Saharan+2.301
 pleas+2.290
uffy+2.218
Neg logit contributions
isphere-1.978
orth-1.908
л-1.847
arthed-1.821
enza-1.768
Token1
Token ID16
Feature activation-2.83e-01

Pos logit contributions
 disag+2.174
Sah+2.053
Saharan+2.023
 pleas+1.992
uffy+1.932
Neg logit contributions
isphere-2.394
orth-2.313
л-2.243
arthed-2.223
enza-2.190
Token,
Token ID11
Feature activation-1.22e+00

Pos logit contributions
 disag+2.631
Sah+2.434
Saharan+2.412
 pleas+2.396
ucket+2.358
Neg logit contributions
isphere-2.220
orth-2.168
л-2.097
arthed-2.057
cliffe-2.011
Token8
Token ID23
Feature activation+4.43e-01

Pos logit contributions
 disag+8.533
Sah+7.848
 pleas+7.843
Saharan+7.688
uffy+7.550
Neg logit contributions
isphere-10.660
orth-9.804
л-9.468
 liner-9.452
cliffe-9.443
Token29
Token ID1959
Feature activation-2.77e-01

Pos logit contributions
orth+3.472
isphere+3.440
л+3.374
cliffe+3.222
arthed+3.207
Neg logit contributions
 disag-4.065
Sah-3.689
Saharan-3.678
 pleas-3.647
ucket-3.630
Token all
Token ID477
Feature activation+5.06e-01

Pos logit contributions
 disag+2.382
Sah+2.180
 pleas+2.175
Saharan+2.157
ucket+2.101
Neg logit contributions
isphere-2.338
orth-2.311
л-2.216
arthed-2.188
enza-2.153
Token-
Token ID12
Feature activation+5.91e-01

Pos logit contributions
isphere+3.893
orth+3.875
л+3.741
cliffe+3.608
arthed+3.578
Neg logit contributions
 disag-4.665
Sah-4.321
Saharan-4.257
ucket-4.235
 pleas-4.203
Tokenin
Token ID259
Feature activation+3.76e-01

Pos logit contributions
orth+4.416
isphere+4.310
л+4.112
cliffe+4.028
enza+3.915
Neg logit contributions
 disag-5.641
Sah-5.133
 pleas-5.104
ucket-5.078
uffy-5.050
Token x
Token ID2124
Feature activation+1.09e-01

Pos logit contributions
orth+1.566
isphere+1.559
л+1.504
cliffe+1.374
arthed+1.347
Neg logit contributions
 disag-5.067
Sah-4.811
Saharan-4.791
 pleas-4.704
ucket-4.703
Token.
Token ID13
Feature activation+2.80e-01

Pos logit contributions
isphere+0.816
orth+0.803
л+0.777
arthed+0.751
enza+0.743
Neg logit contributions
 disag-1.045
Sah-0.975
Saharan-0.966
 pleas-0.957
ucket-0.942
Tokenx
Token ID87
Feature activation+1.92e-01

Pos logit contributions
isphere+1.792
orth+1.790
л+1.717
cliffe+1.629
arthed+1.628
Neg logit contributions
 disag-3.004
Sah-2.784
Saharan-2.759
 pleas-2.743
ucket-2.713
Token.
Token ID13
Feature activation+1.74e-01

Pos logit contributions
isphere+1.380
orth+1.372
л+1.327
arthed+1.270
cliffe+1.261
Neg logit contributions
 disag-1.910
Sah-1.766
Saharan-1.753
 pleas-1.736
ucket-1.720
Tokenx
Token ID87
Feature activation-5.52e-01

Pos logit contributions
isphere+1.167
orth+1.152
л+1.111
arthed+1.063
cliffe+1.052
Neg logit contributions
 disag-1.822
Sah-1.702
Saharan-1.688
 pleas-1.674
ucket-1.654
Token.
Token ID13
Feature activation-1.21e+00

Pos logit contributions
 disag+4.357
Sah+4.240
Saharan+4.182
 pleas+4.100
ucket+4.017
Neg logit contributions
isphere-4.838
orth-4.563
 liner-4.479
enza-4.433
л-4.429
Token149
Token ID19442
Feature activation+3.59e-01

Pos logit contributions
 disag+4.488
ucket+3.987
Saharan+3.962
Sah+3.960
 pleas+3.856
Neg logit contributions
isphere-14.596
 liner-14.330
enza-14.171
л-14.108
rity-14.104
Token 110
Token ID9796
Feature activation+8.53e-02

Pos logit contributions
orth+2.763
isphere+2.759
л+2.683
arthed+2.579
cliffe+2.551
Neg logit contributions
 disag-3.350
Sah-3.083
Saharan-3.076
 pleas-3.034
ucket-3.016
Token22
Token ID1828
Feature activation+1.12e-01

Pos logit contributions
isphere+0.717
orth+0.702
л+0.679
arthed+0.661
enza+0.655
Neg logit contributions
 disag-0.747
Sah-0.697
Saharan-0.687
 pleas-0.680
ucket-0.668
Token26
Token ID2075
Feature activation+4.87e-01

Pos logit contributions
isphere+0.923
orth+0.907
л+0.881
arthed+0.855
enza+0.846
Neg logit contributions
 disag-0.992
Sah-0.920
Saharan-0.910
 pleas-0.901
ucket-0.886
Token x
Token ID2124
Feature activation+8.17e-02

Pos logit contributions
orth+1.844
isphere+1.803
л+1.767
cliffe+1.599
arthed+1.559
Neg logit contributions
 disag-6.363
Sah-6.026
Saharan-6.008
ucket-5.922
 pleas-5.878
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
 disag+1.868
 pleas+1.726
Sah+1.698
Saharan+1.690
ucket+1.657
Neg logit contributions
isphere-1.678
orth-1.662
л-1.603
arthed-1.562
enza-1.534
Token died
Token ID3724
Feature activation-4.19e-01

Pos logit contributions
 disag+1.368
 pleas+1.258
Sah+1.258
Saharan+1.238
ucket+1.211
Neg logit contributions
isphere-1.218
orth-1.201
л-1.168
arthed-1.134
enza-1.120
Token at
Token ID379
Feature activation-6.19e-01

Pos logit contributions
 disag+3.590
 pleas+3.354
Sah+3.219
Saharan+3.169
 uncons+3.088
Neg logit contributions
isphere-3.531
orth-3.477
arthed-3.362
л-3.362
enza-3.279
Token 2
Token ID362
Feature activation-1.04e+00

Pos logit contributions
 disag+4.931
 pleas+4.584
Sah+4.548
Saharan+4.508
ucket+4.376
Neg logit contributions
isphere-5.517
orth-5.207
л-5.112
arthed-5.065
enza-4.956
Token:
Token ID25
Feature activation-7.60e-01

Pos logit contributions
 disag+7.942
 pleas+7.662
Sah+7.608
Saharan+7.517
uffy+7.436
Neg logit contributions
isphere-8.353
orth-7.934
arthed-7.893
л-7.798
enza-7.589
Token20
Token ID1238
Feature activation-1.21e+00

Pos logit contributions
Sah+4.826
Saharan+4.682
 disag+4.583
 pleas+4.565
ucket+4.163
Neg logit contributions
isphere-7.719
orth-7.232
arthed-7.167
 liner-7.129
enza-7.093
Token p
Token ID279
Feature activation-6.71e-01

Pos logit contributions
 disag+6.552
 pleas+6.461
Saharan+6.050
Sah+6.042
ucket+5.903
Neg logit contributions
isphere-12.293
orth-11.681
arthed-11.516
л-11.417
rity-11.114
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
Sah+4.847
 disag+4.779
 pleas+4.692
Saharan+4.688
uffy+4.472
Neg logit contributions
isphere-6.235
arthed-5.766
 liner-5.752
orth-5.752
enza-5.724
Tokenm
Token ID76
Feature activation-6.93e-01

Pos logit contributions
 disag+4.222
Saharan+4.135
Sah+4.108
 pleas+4.077
uffy+3.977
Neg logit contributions
isphere-2.762
 liner-2.516
orth-2.509
arthed-2.479
л-2.470
Token.
Token ID13
Feature activation-5.75e-01

Pos logit contributions
 disag+5.941
 pleas+5.480
Sah+5.457
ucket+5.430
Saharan+5.409
Neg logit contributions
isphere-5.632
orth-5.416
arthed-5.262
л-5.198
enza-5.099
Token at
Token ID379
Feature activation-5.43e-01

Pos logit contributions
 disag+4.958
 pleas+4.599
Sah+4.457
Saharan+4.443
ucket+4.321
Neg logit contributions
isphere-4.770
orth-4.496
л-4.421
arthed-4.395
enza-4.301
Token broccoli
Token ID44653
Feature activation-3.93e-01

Pos logit contributions
 disag+2.611
 pleas+2.142
 uncons+1.937
Saharan+1.891
uffy+1.876
Neg logit contributions
isphere-8.869
orth-8.796
л-8.438
arthed-8.425
cliffe-8.290
Token for
Token ID329
Feature activation-5.55e-01

Pos logit contributions
 disag+3.275
 pleas+3.001
Sah+2.962
Saharan+2.889
uffy+2.848
Neg logit contributions
isphere-3.486
orth-3.359
л-3.314
arthed-3.297
enza-3.235
Token a
Token ID257
Feature activation-4.38e-01

Pos logit contributions
 disag+4.001
 pleas+3.716
Sah+3.707
Saharan+3.651
uffy+3.496
Neg logit contributions
isphere-5.503
orth-5.287
л-5.163
arthed-5.059
cliffe-5.004
Token few
Token ID1178
Feature activation-2.18e-01

Pos logit contributions
 disag+3.040
 pleas+2.842
Sah+2.771
Saharan+2.696
uffy+2.626
Neg logit contributions
isphere-4.433
orth-4.338
л-4.217
arthed-4.184
enza-4.089
Token minutes
Token ID2431
Feature activation-7.20e-01

Pos logit contributions
 disag+1.295
 pleas+1.205
Sah+1.165
Saharan+1.124
ucket+1.086
Neg logit contributions
isphere-2.436
orth-2.405
л-2.343
arthed-2.293
enza-2.274
Token until
Token ID1566
Feature activation-1.21e+00

Pos logit contributions
 disag+5.294
 pleas+4.805
Sah+4.782
Saharan+4.761
ucket+4.482
Neg logit contributions
isphere-7.010
orth-6.868
л-6.725
arthed-6.506
enza-6.405
Token fork
Token ID15563
Feature activation-5.20e-01

Pos logit contributions
 disag+5.160
 pleas+4.460
 uncons+4.121
Saharan+3.948
uffy+3.818
Neg logit contributions
isphere-14.245
arthed-13.802
л-13.690
orth-13.651
enza-13.605
Token-
Token ID12
Feature activation-3.36e-02

Pos logit contributions
 disag+4.286
 pleas+3.969
Sah+3.885
Saharan+3.872
uffy+3.755
Neg logit contributions
isphere-4.607
л-4.314
orth-4.305
arthed-4.235
enza-4.207
Tokent
Token ID83
Feature activation-5.17e-01

Pos logit contributions
 disag+0.338
Saharan+0.317
Sah+0.317
 pleas+0.312
ucket+0.308
Neg logit contributions
isphere-0.239
orth-0.228
л-0.226
arthed-0.217
enza-0.214
Tokenender
Token ID2194
Feature activation-4.30e-01

Pos logit contributions
 disag+5.104
Saharan+4.956
ucket+4.902
uffy+4.900
Sah+4.813
Neg logit contributions
isphere-3.435
л-3.342
orth-3.154
arthed-3.131
enza-3.061
Token.
Token ID13
Feature activation-4.79e-01

Pos logit contributions
 disag+3.491
Sah+3.353
 pleas+3.297
Saharan+3.295
ucket+3.129
Neg logit contributions
isphere-3.768
orth-3.562
arthed-3.488
л-3.464
enza-3.423
Token racist
Token ID9811
Feature activation-2.85e-01

Pos logit contributions
 disag+4.746
 pleas+4.375
Sah+4.266
Saharan+4.130
uffy+4.116
Neg logit contributions
isphere-4.690
orth-4.576
л-4.371
arthed-4.366
enza-4.271
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
 disag+2.630
Sah+2.414
 pleas+2.410
Saharan+2.364
uffy+2.317
Neg logit contributions
isphere-2.257
orth-2.219
arthed-2.122
л-2.121
enza-2.072
Token Flag
Token ID19762
Feature activation-4.55e-01

Pos logit contributions
 disag+2.119
Sah+1.978
 pleas+1.963
Saharan+1.944
ucket+1.874
Neg logit contributions
isphere-1.983
orth-1.933
л-1.854
arthed-1.853
enza-1.812
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
 disag+4.207
Sah+4.002
Saharan+3.949
 pleas+3.901
ucket+3.830
Neg logit contributions
isphere-3.427
orth-3.352
л-3.210
arthed-3.206
enza-3.164
Token
Token ID198
Feature activation-7.11e-01

Pos logit contributions
 disag+3.643
Sah+3.546
Saharan+3.501
 pleas+3.485
uffy+3.307
Neg logit contributions
isphere-3.497
orth-3.262
arthed-3.196
л-3.183
enza-3.112
TokenFlag
Token ID34227
Feature activation-1.21e+00

Pos logit contributions
Sah+3.681
Saharan+3.586
 disag+3.279
ucket+3.047
 pleas+3.042
Neg logit contributions
isphere-8.098
 liner-7.798
arthed-7.742
orth-7.718
rity-7.580
Token Reply
Token ID14883
Feature activation-2.80e-01

Pos logit contributions
 disag+4.334
 pleas+3.952
Sah+3.704
Saharan+3.632
 uncons+3.197
Neg logit contributions
isphere-14.469
orth-14.332
arthed-14.166
enza-13.805
rity-13.685
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
 disag+2.659
Sah+2.523
Saharan+2.499
 pleas+2.496
ucket+2.411
Neg logit contributions
isphere-2.126
orth-2.044
л-1.974
arthed-1.943
enza-1.895
Token
Token ID198
Feature activation-4.05e-01

Pos logit contributions
 disag+2.570
Sah+2.477
Saharan+2.446
 pleas+2.433
uffy+2.327
Neg logit contributions
isphere-2.231
orth-2.094
л-2.040
arthed-2.039
enza-1.982
Token19
Token ID1129
Feature activation-8.94e-01

Pos logit contributions
Sah+3.222
 disag+3.209
Saharan+3.117
 pleas+3.017
ucket+2.907
Neg logit contributions
isphere-3.585
orth-3.369
arthed-3.325
л-3.257
cliffe-3.256
Token Recommend
Token ID30361
Feature activation-1.94e-01

Pos logit contributions
 disag+4.146
Sah+3.705
Saharan+3.622
 pleas+3.580
uffy+3.258
Neg logit contributions
isphere-10.733
arthed-10.087
enza-9.983
orth-9.972
rity-9.895
Token x
Token ID2124
Feature activation+1.02e-01

Pos logit contributions
isphere+0.530
orth+0.518
л+0.491
arthed+0.464
enza+0.454
Neg logit contributions
 disag-1.368
Sah-1.292
Saharan-1.284
 pleas-1.276
ucket-1.261
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
isphere+0.771
orth+0.758
л+0.734
arthed+0.709
enza+0.702
Neg logit contributions
 disag-0.980
Sah-0.915
Saharan-0.906
 pleas-0.898
ucket-0.883
Tokenx
Token ID87
Feature activation+3.49e-01

Pos logit contributions
orth+1.849
isphere+1.848
л+1.770
cliffe+1.681
arthed+1.680
Neg logit contributions
 disag-3.119
Sah-2.888
Saharan-2.863
 pleas-2.847
ucket-2.818
Token.
Token ID13
Feature activation+6.58e-01

Pos logit contributions
orth+2.388
isphere+2.364
л+2.295
cliffe+2.174
arthed+2.169
Neg logit contributions
 disag-3.611
Sah-3.299
Saharan-3.277
 pleas-3.254
ucket-3.240
Tokenx
Token ID87
Feature activation+1.04e+00

Pos logit contributions
orth+3.984
isphere+3.880
л+3.668
cliffe+3.477
irc+3.466
Neg logit contributions
 disag-7.371
Sah-6.719
 pleas-6.672
Saharan-6.590
ucket-6.562
Token.
Token ID13
Feature activation+1.17e+00

Pos logit contributions
orth+5.920
isphere+5.490
л+5.368
irc+5.270
cliffe+4.915
Neg logit contributions
 disag-11.821
 srf-10.585
 pleas-10.469
Sah-10.467
 uncons-10.429
Token138
Token ID20107
Feature activation+4.97e-01

Pos logit contributions
orth+4.510
isphere+4.104
л+3.601
irc+3.555
arthed+3.215
Neg logit contributions
 disag-15.288
Sah-14.065
 pleas-14.033
uffy-14.005
 uncons-13.836
Token 11
Token ID1367
Feature activation+1.33e-01

Pos logit contributions
orth+3.591
isphere+3.548
л+3.470
arthed+3.344
cliffe+3.298
Neg logit contributions
 disag-4.819
Saharan-4.453
Sah-4.436
 pleas-4.384
ucket-4.380
Token30
Token ID1270
Feature activation-2.22e-01

Pos logit contributions
isphere+1.129
orth+1.112
л+1.079
arthed+1.047
enza+1.037
Neg logit contributions
 disag-1.152
Sah-1.065
Saharan-1.054
 pleas-1.043
ucket-1.026
Token277
Token ID27019
Feature activation+4.11e-01

Pos logit contributions
 disag+1.717
Sah+1.583
Saharan+1.551
 pleas+1.546
ucket+1.506
Neg logit contributions
isphere-2.071
orth-2.017
л-1.964
arthed-1.926
cliffe-1.905
Token x
Token ID2124
Feature activation+1.62e-01

Pos logit contributions
orth+1.630
isphere+1.607
л+1.559
cliffe+1.420
arthed+1.390
Neg logit contributions
 disag-5.307
Sah-5.029
Saharan-5.013
ucket-4.934
 pleas-4.921
Token Massachusetts
Token ID10140
Feature activation+2.22e-01

Pos logit contributions
 disag+0.224
Sah+0.205
Saharan+0.203
 pleas+0.200
ucket+0.197
Neg logit contributions
isphere-0.243
orth-0.241
л-0.235
arthed-0.227
cliffe-0.225
Token were
Token ID547
Feature activation+3.65e-02

Pos logit contributions
isphere+1.825
orth+1.811
л+1.752
arthed+1.698
cliffe+1.677
Neg logit contributions
 disag-1.957
Sah-1.794
Saharan-1.790
 pleas-1.755
ucket-1.741
Token the
Token ID262
Feature activation-4.62e-02

Pos logit contributions
isphere+0.312
orth+0.307
л+0.299
arthed+0.289
enza+0.287
Neg logit contributions
 disag-0.315
Sah-0.290
Saharan-0.287
 pleas-0.285
ucket-0.279
Token Y
Token ID575
Feature activation-6.67e-02

Pos logit contributions
 disag+0.420
Sah+0.388
Saharan+0.383
 pleas+0.383
ucket+0.378
Neg logit contributions
isphere-0.372
orth-0.365
л-0.356
arthed-0.345
enza-0.340
Tokenaw
Token ID707
Feature activation-1.58e-01

Pos logit contributions
 disag+0.591
Sah+0.554
Saharan+0.551
 pleas+0.539
ucket+0.535
Neg logit contributions
isphere-0.549
orth-0.532
л-0.525
arthed-0.506
enza-0.497
Tokenkey
Token ID2539
Feature activation+1.31e+00

Pos logit contributions
 disag+1.910
Saharan+1.842
Sah+1.828
ucket+1.816
 pleas+1.808
Neg logit contributions
isphere-0.737
л-0.707
orth-0.693
arthed-0.671
enza-0.642
Token Center
Token ID3337
Feature activation+3.19e-01

Pos logit contributions
orth+6.715
isphere+6.496
cliffe+6.433
irc+6.324
л+6.220
Neg logit contributions
 disag-14.011
Saharan-12.906
Sah-12.879
uffy-12.747
ucket-12.528
Token at
Token ID379
Feature activation+2.64e-02

Pos logit contributions
isphere+2.139
orth+2.136
л+2.056
cliffe+1.961
arthed+1.960
Neg logit contributions
 disag-3.305
Sah-3.073
Saharan-3.053
 pleas-3.013
ucket-2.994
Token Emmanuel
Token ID32390
Feature activation+9.97e-01

Pos logit contributions
isphere+0.241
orth+0.237
л+0.231
arthed+0.225
cliffe+0.222
Neg logit contributions
 disag-0.212
Sah-0.194
Saharan-0.192
 pleas-0.190
ucket-0.186
Token College
Token ID5535
Feature activation-2.21e-01

Pos logit contributions
orth+4.738
л+4.387
cliffe+4.305
isphere+4.244
bey+4.158
Neg logit contributions
 disag-11.913
Sah-11.137
Saharan-11.062
ucket-10.825
uffy-10.709
Token in
Token ID287
Feature activation-3.77e-01

Pos logit contributions
 disag+1.928
Sah+1.797
 pleas+1.783
Saharan+1.777
ucket+1.722
Neg logit contributions
isphere-1.848
orth-1.796
л-1.754
arthed-1.723
enza-1.683
Token[
Token ID58
Feature activation+1.67e-01

Pos logit contributions
orth+3.746
л+3.400
irc+3.282
isphere+2.769
cliffe+2.551
Neg logit contributions
 disag-17.715
 srf-17.598
 uncons-16.230
ucket-16.152
uffy-16.089
Token1
Token ID16
Feature activation+2.15e-01

Pos logit contributions
isphere+1.176
orth+1.163
л+1.123
arthed+1.078
cliffe+1.066
Neg logit contributions
 disag-1.679
Sah-1.562
Saharan-1.550
 pleas-1.536
ucket-1.517
Token],
Token ID4357
Feature activation+7.68e-01

Pos logit contributions
isphere+1.543
orth+1.533
л+1.487
arthed+1.423
cliffe+1.408
Neg logit contributions
 disag-2.133
Sah-1.973
Saharan-1.954
 pleas-1.938
ucket-1.918
Token$
Token ID3
Feature activation+3.28e-01

Pos logit contributions
orth+5.598
л+5.413
isphere+5.314
cliffe+5.123
irc+5.060
Neg logit contributions
 disag-7.502
 pleas-6.645
ucket-6.633
Sah-6.555
Saharan-6.501
TokenFC
Token ID4851
Feature activation+4.43e-01

Pos logit contributions
isphere+3.178
orth+3.170
л+3.089
arthed+2.984
cliffe+2.972
Neg logit contributions
 disag-2.442
Sah-2.188
Saharan-2.159
 pleas-2.146
ucket-2.114
Token2
Token ID17
Feature activation+1.28e+00

Pos logit contributions
orth+3.436
isphere+3.420
л+3.360
arthed+3.169
cliffe+3.147
Neg logit contributions
 disag-4.126
Sah-3.685
Saharan-3.652
 pleas-3.638
ucket-3.634
Token[
Token ID58
Feature activation+5.44e-01

Pos logit contributions
orth+3.703
л+3.436
irc+3.190
isphere+2.751
cliffe+2.594
Neg logit contributions
 disag-17.185
 srf-17.056
 uncons-15.670
ucket-15.661
uffy-15.588
Token2
Token ID17
Feature activation+3.48e-01

Pos logit contributions
orth+4.062
isphere+3.995
л+3.906
cliffe+3.729
irc+3.677
Neg logit contributions
 disag-5.244
Sah-4.628
ucket-4.605
Saharan-4.592
 pleas-4.578
Token])
Token ID12962
Feature activation+9.79e-01

Pos logit contributions
isphere+2.183
orth+2.167
л+2.114
arthed+2.023
enza+1.951
Neg logit contributions
 disag-3.772
Sah-3.499
Saharan-3.472
 pleas-3.431
uffy-3.364
Token )
Token ID1267
Feature activation+4.08e-01

Pos logit contributions
orth+3.138
л+3.092
isphere+3.052
cliffe+2.750
arthed+2.606
Neg logit contributions
 disag-12.892
Sah-12.059
Saharan-12.038
ucket-11.873
 pleas-11.816
Token $
Token ID720
Feature activation+4.74e-01

Pos logit contributions
orth+2.933
isphere+2.903
л+2.840
cliffe+2.694
arthed+2.693
Neg logit contributions
 disag-3.957
Sah-3.724
Saharan-3.721
 pleas-3.569
ucket-3.558
Token to
Token ID284
Feature activation-1.60e-01

Pos logit contributions
isphere+0.575
orth+0.569
л+0.551
arthed+0.532
cliffe+0.526
Neg logit contributions
 disag-0.693
Sah-0.642
Saharan-0.637
 pleas-0.631
ucket-0.622
Token subscribe
Token ID12383
Feature activation+2.32e-01

Pos logit contributions
 disag+1.457
Saharan+1.344
Sah+1.336
 pleas+1.329
ucket+1.306
Neg logit contributions
isphere-1.287
orth-1.260
л-1.219
arthed-1.198
cliffe-1.176
Token to
Token ID284
Feature activation-1.42e-03

Pos logit contributions
isphere+1.697
orth+1.687
л+1.647
cliffe+1.571
arthed+1.560
Neg logit contributions
 disag-2.254
Sah-2.082
Saharan-2.058
 pleas-2.036
ucket-2.030
Token.
Token ID13
Feature activation+2.38e-01

Pos logit contributions
 disag+0.013
Sah+0.013
Saharan+0.012
 pleas+0.012
ucket+0.012
Neg logit contributions
isphere-0.011
orth-0.011
л-0.010
arthed-0.010
enza-0.010
Token Sign
Token ID5865
Feature activation+6.07e-01

Pos logit contributions
isphere+1.929
orth+1.905
л+1.846
arthed+1.785
enza+1.766
Neg logit contributions
 disag-2.158
Sah-1.998
Saharan-1.980
 pleas-1.960
ucket-1.928
Token Up
Token ID3205
Feature activation+1.20e+00

Pos logit contributions
orth+4.122
isphere+4.034
л+4.023
cliffe+3.852
bey+3.773
Neg logit contributions
 disag-6.141
Sah-5.567
 pleas-5.540
ucket-5.521
Saharan-5.486
Token You
Token ID921
Feature activation+3.83e-01

Pos logit contributions
л+2.720
orth+2.293
isphere+2.194
bey+2.173
 Ost+2.150
Neg logit contributions
 disag-16.780
ucket-15.754
Sah-15.344
 pleas-15.238
 srf-15.193
Token will
Token ID481
Feature activation+2.02e-01

Pos logit contributions
orth+2.820
isphere+2.795
л+2.731
cliffe+2.602
bey+2.598
Neg logit contributions
 disag-3.702
Sah-3.432
Saharan-3.400
ucket-3.318
uffy-3.299
Token receive
Token ID3328
Feature activation+5.86e-01

Pos logit contributions
orth+0.916
isphere+0.907
л+0.859
cliffe+0.802
arthed+0.786
Neg logit contributions
 disag-2.528
Sah-2.395
Saharan-2.366
 pleas-2.341
ucket-2.324
Token emails
Token ID7237
Feature activation+2.89e-01

Pos logit contributions
isphere+3.198
orth+3.075
л+3.028
cliffe+2.890
arthed+2.829
Neg logit contributions
 disag-6.611
Sah-6.313
Saharan-6.173
ucket-6.156
uffy-6.029
Token containing
Token ID7268
Feature activation+3.38e-01

Pos logit contributions
isphere+1.991
orth+1.967
л+1.913
cliffe+1.820
arthed+1.811
Neg logit contributions
 disag-2.916
Sah-2.745
Saharan-2.706
ucket-2.660
 pleas-2.651
Token the
Token ID262
Feature activation+3.36e-01

Pos logit contributions
 disag+0.361
Sah+0.329
 pleas+0.327
Saharan+0.326
ucket+0.318
Neg logit contributions
isphere-0.363
orth-0.355
л-0.345
arthed-0.337
cliffe-0.333
Token worst
Token ID5290
Feature activation+1.69e-01

Pos logit contributions
orth+2.817
isphere+2.816
л+2.739
arthed+2.634
enza+2.614
Neg logit contributions
 disag-2.859
Sah-2.645
Saharan-2.625
 pleas-2.564
ucket-2.562
Token ne
Token ID497
Feature activation+4.31e-01

Pos logit contributions
isphere+1.358
orth+1.341
л+1.301
arthed+1.258
cliffe+1.246
Neg logit contributions
 disag-1.534
Sah-1.416
Saharan-1.404
 pleas-1.391
ucket-1.370
Token­
Token ID3907
Feature activation+7.82e-01

Pos logit contributions
isphere+3.367
orth+3.366
л+3.297
arthed+3.170
cliffe+3.133
Neg logit contributions
 disag-3.892
Sah-3.623
Saharan-3.610
 pleas-3.499
ucket-3.483
Tokengo
Token ID2188
Feature activation+3.21e-01

Pos logit contributions
isphere+5.664
orth+5.662
л+5.321
bey+5.267
arthed+5.167
Neg logit contributions
 disag-7.513
Sah-6.918
Saharan-6.791
uffy-6.693
 pleas-6.632
Token­
Token ID3907
Feature activation+1.28e+00

Pos logit contributions
isphere+2.782
orth+2.756
л+2.679
arthed+2.593
cliffe+2.569
Neg logit contributions
 disag-2.714
Sah-2.493
Saharan-2.469
 pleas-2.441
ucket-2.405
Tokenti
Token ID20259
Feature activation+1.22e-03

Pos logit contributions
orth+7.543
isphere+7.106
rity+6.425
enza+6.359
bey+6.296
Neg logit contributions
 disag-13.843
uffy-12.712
ucket-12.698
Sah-12.509
 DAV-12.209
Token­
Token ID3907
Feature activation+1.03e+00

Pos logit contributions
isphere+0.011
orth+0.011
л+0.011
arthed+0.010
cliffe+0.010
Neg logit contributions
 disag-0.010
Sah-0.009
Saharan-0.009
 pleas-0.009
ucket-0.009
Tokenat
Token ID265
Feature activation+1.75e-01

Pos logit contributions
orth+7.884
isphere+7.359
rity+7.259
enza+7.208
bey+7.025
Neg logit contributions
 disag-9.330
Sah-8.493
 pleas-8.310
ucket-8.302
Saharan-8.143
Token­
Token ID3907
Feature activation+4.16e-01

Pos logit contributions
isphere+1.426
orth+1.410
л+1.368
arthed+1.322
cliffe+1.309
Neg logit contributions
 disag-1.581
Sah-1.460
Saharan-1.447
 pleas-1.432
ucket-1.412
Tokenor
Token ID273
Feature activation+2.08e-01

Pos logit contributions
isphere+2.595
orth+2.584
л+2.440
enza+2.322
arthed+2.319
Neg logit contributions
 disag-4.524
Sah-4.267
Saharan-4.206
 pleas-4.168
ucket-4.098
Token king
Token ID5822
Feature activation+4.06e-01

Pos logit contributions
isphere+0.747
orth+0.737
л+0.715
arthed+0.690
cliffe+0.683
Neg logit contributions
 disag-0.908
Sah-0.840
Saharan-0.828
 pleas-0.827
ucket-0.810
Token Xer
Token ID44264
Feature activation+1.26e-01

Pos logit contributions
isphere+3.176
orth+3.156
л+3.062
arthed+2.959
cliffe+2.925
Neg logit contributions
 disag-3.722
Sah-3.441
Saharan-3.437
 pleas-3.359
ucket-3.354
Tokenxes
Token ID48169
Feature activation+4.79e-01

Pos logit contributions
isphere+1.203
orth+1.187
л+1.162
arthed+1.126
enza+1.118
Neg logit contributions
 disag-0.960
Sah-0.874
Saharan-0.864
 pleas-0.857
ucket-0.839
Token sent
Token ID1908
Feature activation+3.85e-01

Pos logit contributions
isphere+3.764
orth+3.737
л+3.626
arthed+3.488
cliffe+3.467
Neg logit contributions
 disag-4.344
Sah-4.059
Saharan-4.022
ucket-3.942
 pleas-3.923
Token his
Token ID465
Feature activation+3.84e-01

Pos logit contributions
isphere+3.023
orth+3.008
л+2.936
arthed+2.823
enza+2.799
Neg logit contributions
 disag-3.498
Sah-3.234
Saharan-3.207
ucket-3.150
 pleas-3.143
Token massive
Token ID4858
Feature activation+4.07e-01

Pos logit contributions
isphere+2.958
orth+2.935
л+2.865
arthed+2.739
cliffe+2.725
Neg logit contributions
 disag-3.536
Sah-3.283
Saharan-3.263
ucket-3.221
 pleas-3.197
Token army
Token ID5428
Feature activation+3.47e-01

Pos logit contributions
isphere+2.723
orth+2.694
л+2.620
arthed+2.485
cliffe+2.459
Neg logit contributions
 disag-4.176
Sah-3.911
Saharan-3.889
ucket-3.832
 pleas-3.827
Token across
Token ID1973
Feature activation+3.66e-02

Pos logit contributions
isphere+2.667
orth+2.629
л+2.551
arthed+2.452
enza+2.429
Neg logit contributions
 disag-3.238
Sah-3.022
Saharan-2.998
ucket-2.947
 pleas-2.942
Token the
Token ID262
Feature activation-1.52e-01

Pos logit contributions
isphere+0.305
orth+0.301
л+0.292
arthed+0.283
enza+0.280
Neg logit contributions
 disag-0.323
Sah-0.299
Saharan-0.297
 pleas-0.293
ucket-0.287
Token stra
Token ID3534
Feature activation-4.24e-01

Pos logit contributions
 disag+1.280
Sah+1.189
Saharan+1.167
 pleas+1.154
ucket+1.104
Neg logit contributions
isphere-1.333
orth-1.314
л-1.285
arthed-1.249
enza-1.234
Tokenit
Token ID270
Feature activation+1.19e-01

Pos logit contributions
 disag+2.411
Saharan+2.282
Sah+2.234
uffy+2.172
 pleas+2.058
Neg logit contributions
л-4.559
isphere-4.524
arthed-4.512
orth-4.499
 liner-4.453
Token Gentle
Token ID25066
Feature activation+2.94e-01

Pos logit contributions
 disag+0.533
Sah+0.476
Saharan+0.470
 pleas+0.462
ucket+0.453
Neg logit contributions
isphere-0.891
orth-0.884
л-0.864
arthed-0.842
cliffe-0.836
Tokenmen
Token ID3653
Feature activation-3.64e-01

Pos logit contributions
isphere+1.299
orth+1.295
л+1.202
arthed+1.118
cliffe+1.116
Neg logit contributions
 disag-3.737
Sah-3.521
Saharan-3.502
 pleas-3.445
ucket-3.444
Token tried
Token ID3088
Feature activation-2.11e-01

Pos logit contributions
 disag+2.970
 pleas+2.700
Sah+2.623
Saharan+2.600
ucket+2.546
Neg logit contributions
orth-3.199
isphere-3.183
л-3.155
arthed-3.089
cliffe-3.010
Token to
Token ID284
Feature activation+1.79e-02

Pos logit contributions
 disag+1.892
 pleas+1.733
Sah+1.723
Saharan+1.705
ucket+1.669
Neg logit contributions
isphere-1.722
orth-1.710
л-1.658
arthed-1.615
enza-1.596
Token record
Token ID1700
Feature activation-1.55e-01

Pos logit contributions
isphere+0.173
orth+0.171
л+0.168
arthed+0.164
cliffe+0.161
Neg logit contributions
 disag-0.136
Sah-0.122
 pleas-0.121
Saharan-0.121
ucket-0.117
Token live
Token ID2107
Feature activation+2.81e-01

Pos logit contributions
 disag+1.392
 pleas+1.275
Sah+1.266
Saharan+1.261
ucket+1.225
Neg logit contributions
orth-1.266
isphere-1.263
л-1.226
arthed-1.192
enza-1.174
Token --
Token ID1377
Feature activation-1.31e-02

Pos logit contributions
isphere+2.106
orth+2.075
л+2.010
arthed+1.929
enza+1.913
Neg logit contributions
 disag-2.694
Sah-2.506
Saharan-2.484
 pleas-2.447
ucket-2.433
Token first
Token ID717
Feature activation+1.06e-01

Pos logit contributions
 disag+0.126
Sah+0.116
 pleas+0.115
Saharan+0.115
ucket+0.112
Neg logit contributions
isphere-0.100
orth-0.098
л-0.095
arthed-0.093
enza-0.091
Token of
Token ID286
Feature activation+1.51e-01

Pos logit contributions
isphere+0.832
orth+0.825
л+0.802
arthed+0.772
cliffe+0.764
Neg logit contributions
 disag-0.981
Sah-0.907
Saharan-0.896
 pleas-0.894
ucket-0.875
Token all
Token ID477
Feature activation+1.87e-01

Pos logit contributions
isphere+1.278
orth+1.258
л+1.226
arthed+1.186
enza+1.172
Neg logit contributions
 disag-1.331
Sah-1.219
Saharan-1.209
 pleas-1.206
ucket-1.177
Token,
Token ID11
Feature activation+1.02e-01

Pos logit contributions
isphere+1.393
orth+1.376
л+1.334
arthed+1.275
cliffe+1.267
Neg logit contributions
 disag-1.806
Sah-1.682
Saharan-1.669
 pleas-1.640
ucket-1.629
Token golden
Token ID10861
Feature activation-3.82e-01

Pos logit contributions
 disag+1.403
Sah+1.277
 pleas+1.262
Saharan+1.262
ucket+1.227
Neg logit contributions
isphere-1.510
orth-1.485
л-1.445
arthed-1.421
cliffe-1.400
Token child
Token ID1200
Feature activation+1.13e-01

Pos logit contributions
 disag+3.455
Sah+3.219
Saharan+3.144
 pleas+3.126
ucket+3.037
Neg logit contributions
isphere-3.090
orth-2.952
л-2.913
arthed-2.899
cliffe-2.851
Token right
Token ID826
Feature activation-5.05e-01

Pos logit contributions
isphere+0.833
orth+0.821
л+0.800
arthed+0.760
enza+0.754
Neg logit contributions
 disag-1.109
Sah-1.031
Saharan-1.025
 pleas-1.007
ucket-0.998
Token now
Token ID783
Feature activation+3.95e-01

Pos logit contributions
 disag+4.100
 pleas+3.779
Sah+3.739
Saharan+3.673
ucket+3.566
Neg logit contributions
isphere-4.395
orth-4.250
arthed-4.116
л-4.034
enza-3.960
Token,
Token ID11
Feature activation-6.93e-02

Pos logit contributions
isphere+2.864
orth+2.844
л+2.767
enza+2.584
cliffe+2.583
Neg logit contributions
 disag-3.855
Sah-3.617
Saharan-3.598
 pleas-3.504
ucket-3.482
Token but
Token ID475
Feature activation+3.95e-01

Pos logit contributions
 disag+0.644
Sah+0.593
 pleas+0.587
Saharan+0.587
ucket+0.574
Neg logit contributions
isphere-0.548
orth-0.537
л-0.521
arthed-0.509
enza-0.502
Token I
Token ID314
Feature activation-2.00e-01

Pos logit contributions
isphere+3.094
orth+3.065
л+2.960
enza+2.834
cliffe+2.830
Neg logit contributions
 disag-3.595
Sah-3.353
Saharan-3.306
 pleas-3.253
ucket-3.250
Token
Token ID447
Feature activation+6.15e-02

Pos logit contributions
 disag+1.763
Sah+1.621
 pleas+1.592
Saharan+1.583
uffy+1.532
Neg logit contributions
isphere-1.690
orth-1.635
arthed-1.580
л-1.576
cliffe-1.538
Token
Token ID247
Feature activation+8.60e-02

Pos logit contributions
isphere+0.524
orth+0.522
л+0.501
arthed+0.484
cliffe+0.484
Neg logit contributions
 disag-0.528
Sah-0.489
Saharan-0.485
 pleas-0.480
ucket-0.474
Tokenve
Token ID303
Feature activation-9.45e-02

Pos logit contributions
isphere+0.525
orth+0.507
л+0.487
arthed+0.466
cliffe+0.462
Neg logit contributions
 disag-0.951
Sah-0.892
Saharan-0.885
 pleas-0.880
uffy-0.866
Token also
Token ID635
Feature activation-7.85e-02

Pos logit contributions
 disag+0.808
Sah+0.737
 pleas+0.731
Saharan+0.724
ucket+0.699
Neg logit contributions
isphere-0.821
orth-0.807
л-0.781
arthed-0.764
cliffe-0.760
Token be
Token ID307
Feature activation-2.46e-01

Pos logit contributions
 disag+1.507
Sah+1.378
Saharan+1.372
 pleas+1.367
ucket+1.328
Neg logit contributions
isphere-1.578
orth-1.545
л-1.505
arthed-1.482
cliffe-1.454
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
 disag+2.240
 pleas+2.051
Sah+2.049
Saharan+2.031
ucket+1.982
Neg logit contributions
isphere-1.949
orth-1.907
л-1.849
arthed-1.840
cliffe-1.799
Token
Token ID198
Feature activation-3.46e-02

Pos logit contributions
 disag+1.775
Sah+1.673
Saharan+1.647
 pleas+1.631
ucket+1.608
Neg logit contributions
isphere-1.337
orth-1.289
л-1.229
arthed-1.213
enza-1.186
Token
Token ID198
Feature activation-1.36e-01

Pos logit contributions
 disag+0.344
Sah+0.326
Saharan+0.323
 pleas+0.320
ucket+0.312
Neg logit contributions
isphere-0.250
orth-0.241
л-0.232
arthed-0.227
enza-0.223
TokenMal
Token ID15029
Feature activation+2.88e-02

Pos logit contributions
 disag+1.237
Sah+1.188
Saharan+1.163
 pleas+1.136
ucket+1.129
Neg logit contributions
isphere-1.075
orth-1.040
л-1.000
arthed-0.992
cliffe-0.974
Tokencolm
Token ID18414
Feature activation+4.89e-01

Pos logit contributions
isphere+0.241
orth+0.238
л+0.232
arthed+0.224
enza+0.222
Neg logit contributions
 disag-0.252
Sah-0.232
Saharan-0.229
 pleas-0.227
ucket-0.225
Token Grim
Token ID17525
Feature activation+4.22e-01

Pos logit contributions
isphere+3.913
orth+3.911
л+3.782
cliffe+3.647
arthed+3.626
Neg logit contributions
 disag-4.297
Sah-4.009
Saharan-4.000
 pleas-3.906
ucket-3.854
Tokenston
Token ID3743
Feature activation+3.64e-01

Pos logit contributions
isphere+3.215
orth+3.207
л+3.077
cliffe+2.962
arthed+2.955
Neg logit contributions
 disag-3.992
Sah-3.711
Saharan-3.688
 pleas-3.628
ucket-3.577
Token,
Token ID11
Feature activation-1.05e-01

Pos logit contributions
isphere+2.709
orth+2.685
л+2.594
cliffe+2.474
arthed+2.473
Neg logit contributions
 disag-3.518
Sah-3.271
Saharan-3.245
 pleas-3.203
ucket-3.161
Token a
Token ID257
Feature activation-3.39e-01

Pos logit contributions
 disag+0.945
Sah+0.871
Saharan+0.866
 pleas+0.860
ucket+0.844
Neg logit contributions
isphere-0.853
orth-0.837
л-0.813
arthed-0.791
cliffe-0.779
Token nuclear
Token ID4523
Feature activation-2.64e-01

Pos logit contributions
 disag+2.943
 pleas+2.697
Saharan+2.663
Sah+2.659
ucket+2.594
Neg logit contributions
isphere-2.850
orth-2.773
л-2.699
arthed-2.678
enza-2.604
Token you
Token ID345
Feature activation+3.61e-03

Pos logit contributions
 disag+0.096
Sah+0.089
 pleas+0.088
Saharan+0.087
ucket+0.085
Neg logit contributions
isphere-0.080
orth-0.080
л-0.077
arthed-0.074
cliffe-0.074
Token do
Token ID466
Feature activation-3.67e-02

Pos logit contributions
isphere+0.032
orth+0.031
л+0.030
arthed+0.030
cliffe+0.029
Neg logit contributions
 disag-0.030
Sah-0.028
Saharan-0.028
 pleas-0.027
ucket-0.027
Token.
Token ID13
Feature activation-8.84e-02

Pos logit contributions
 disag+0.342
Sah+0.316
Saharan+0.313
 pleas+0.312
ucket+0.307
Neg logit contributions
isphere-0.287
orth-0.281
л-0.271
arthed-0.267
enza-0.263
Token
Token ID198
Feature activation-9.01e-02

Pos logit contributions
 disag+0.845
Sah+0.799
 pleas+0.785
Saharan+0.783
ucket+0.762
Neg logit contributions
isphere-0.667
orth-0.651
л-0.622
arthed-0.613
enza-0.605
Token
Token ID198
Feature activation-2.84e-01

Pos logit contributions
 disag+0.882
Sah+0.838
Saharan+0.829
 pleas+0.825
ucket+0.800
Neg logit contributions
isphere-0.664
orth-0.637
л-0.616
arthed-0.603
enza-0.592
TokenLyn
Token ID37207
Feature activation+3.80e-01

Pos logit contributions
 disag+2.563
Sah+2.523
Saharan+2.441
 pleas+2.381
uffy+2.342
Neg logit contributions
isphere-2.216
orth-2.134
л-2.075
arthed-2.051
enza-2.024
Tokenn
Token ID77
Feature activation+4.41e-01

Pos logit contributions
isphere+2.915
orth+2.900
л+2.788
arthed+2.681
cliffe+2.676
Neg logit contributions
 disag-3.565
Sah-3.298
Saharan-3.290
 pleas-3.233
ucket-3.196
Token Rogers
Token ID15372
Feature activation+1.26e-01

Pos logit contributions
orth+3.423
isphere+3.420
л+3.305
cliffe+3.173
arthed+3.152
Neg logit contributions
 disag-4.072
Saharan-3.746
Sah-3.738
 pleas-3.651
ucket-3.628
Token,
Token ID11
Feature activation-4.00e-01

Pos logit contributions
isphere+0.947
orth+0.933
л+0.903
arthed+0.871
enza+0.861
Neg logit contributions
 disag-1.212
Sah-1.126
Saharan-1.115
 pleas-1.107
ucket-1.090
Token Bi
Token ID8436
Feature activation-2.44e-01

Pos logit contributions
 disag+3.502
Sah+3.231
 pleas+3.209
Saharan+3.181
ucket+3.085
Neg logit contributions
isphere-3.302
orth-3.203
л-3.108
arthed-3.045
enza-2.997
Tokenologist
Token ID7451
Feature activation+1.78e-02

Pos logit contributions
 disag+2.007
Sah+1.866
Saharan+1.846
 pleas+1.829
ucket+1.803
Neg logit contributions
isphere-2.137
orth-2.072
л-2.063
enza-1.978
arthed-1.978
Token costume
Token ID16569
Feature activation+1.02e-01

Pos logit contributions
 disag+0.869
Sah+0.792
Saharan+0.786
 pleas+0.782
ucket+0.761
Neg logit contributions
isphere-0.880
orth-0.860
л-0.839
arthed-0.819
enza-0.806
Token were
Token ID547
Feature activation-2.87e-01

Pos logit contributions
isphere+0.829
orth+0.820
л+0.795
arthed+0.769
cliffe+0.761
Neg logit contributions
 disag-0.921
Sah-0.850
Saharan-0.842
 pleas-0.835
ucket-0.822
Token everywhere
Token ID8347
Feature activation-1.59e-01

Pos logit contributions
 disag+2.530
 pleas+2.356
Sah+2.255
Saharan+2.207
uffy+2.179
Neg logit contributions
isphere-2.379
orth-2.365
л-2.311
enza-2.242
arthed-2.227
Token,
Token ID11
Feature activation-5.75e-01

Pos logit contributions
 disag+1.454
 pleas+1.352
Sah+1.327
Saharan+1.292
ucket+1.288
Neg logit contributions
isphere-1.270
orth-1.243
л-1.201
arthed-1.186
enza-1.173
Token anticipating
Token ID40807
Feature activation-9.66e-02

Pos logit contributions
 disag+4.794
 pleas+4.475
Sah+4.232
 uncons+4.110
Saharan+4.057
Neg logit contributions
isphere-5.006
orth-4.834
enza-4.695
л-4.694
arthed-4.680
Token an
Token ID281
Feature activation+1.36e-01

Pos logit contributions
 disag+0.840
 pleas+0.775
Sah+0.764
Saharan+0.752
ucket+0.740
Neg logit contributions
isphere-0.812
orth-0.805
л-0.789
arthed-0.767
enza-0.758
Token evening
Token ID6180
Feature activation-3.08e-01

Pos logit contributions
isphere+1.040
orth+1.024
л+1.004
arthed+0.964
cliffe+0.952
Neg logit contributions
 disag-1.299
Sah-1.193
 pleas-1.187
Saharan-1.183
ucket-1.159
Token of
Token ID286
Feature activation-2.88e-02

Pos logit contributions
 disag+2.698
 pleas+2.513
Sah+2.411
Saharan+2.385
uffy+2.372
Neg logit contributions
isphere-2.523
orth-2.513
л-2.491
arthed-2.404
cliffe-2.386
Token trick
Token ID6908
Feature activation-9.84e-02

Pos logit contributions
 disag+0.240
 pleas+0.218
Sah+0.217
Saharan+0.214
ucket+0.209
Neg logit contributions
isphere-0.256
orth-0.254
л-0.248
arthed-0.240
enza-0.238
Token or
Token ID393
Feature activation+3.92e-01

Pos logit contributions
 disag+0.920
 pleas+0.858
Sah+0.849
Saharan+0.838
uffy+0.826
Neg logit contributions
isphere-0.762
orth-0.746
л-0.732
arthed-0.706
enza-0.700
Token treating
Token ID13622
Feature activation-1.40e-01

Pos logit contributions
isphere+2.511
orth+2.481
л+2.373
cliffe+2.260
arthed+2.241
Neg logit contributions
 disag-4.110
Sah-3.929
Saharan-3.887
ucket-3.811
 pleas-3.716
Token).
Token ID737
Feature activation+6.76e-02

Pos logit contributions
isphere+0.047
orth+0.046
л+0.045
arthed+0.043
enza+0.042
Neg logit contributions
 disag-0.065
Sah-0.061
Saharan-0.060
 pleas-0.060
ucket-0.059
Token Gl
Token ID2671
Feature activation-2.35e-01

Pos logit contributions
isphere+0.512
orth+0.498
л+0.478
arthed+0.468
enza+0.461
Neg logit contributions
 disag-0.651
Sah-0.610
Saharan-0.602
 pleas-0.598
ucket-0.586
Tokenü
Token ID9116
Feature activation+3.33e-01

Pos logit contributions
 disag+1.489
Sah+1.347
ucket+1.333
Saharan+1.330
uffy+1.329
Neg logit contributions
isphere-2.516
л-2.416
orth-2.408
arthed-2.361
cliffe-2.314
Tokenck
Token ID694
Feature activation-5.25e-01

Pos logit contributions
isphere+1.986
orth+1.972
л+1.908
arthed+1.795
cliffe+1.786
Neg logit contributions
 disag-3.720
Sah-3.479
Saharan-3.455
 pleas-3.421
ucket-3.372
Token learned
Token ID4499
Feature activation-1.03e-01

Pos logit contributions
 disag+4.598
 pleas+4.229
Saharan+4.105
Sah+4.082
ucket+4.047
Neg logit contributions
isphere-4.328
orth-4.163
arthed-4.088
л-4.075
enza-3.947
Token much
Token ID881
Feature activation+8.00e-02

Pos logit contributions
 disag+0.914
 pleas+0.837
Sah+0.835
Saharan+0.833
ucket+0.810
Neg logit contributions
isphere-0.849
orth-0.837
л-0.807
arthed-0.796
enza-0.781
Token from
Token ID422
Feature activation+1.86e-01

Pos logit contributions
isphere+0.665
orth+0.656
л+0.636
arthed+0.619
enza+0.611
Neg logit contributions
 disag-0.711
Sah-0.652
Saharan-0.647
 pleas-0.646
ucket-0.631
Token Pl
Token ID1345
Feature activation+5.48e-01

Pos logit contributions
isphere+1.578
orth+1.562
л+1.518
arthed+1.468
cliffe+1.455
Neg logit contributions
 disag-1.615
Sah-1.487
Saharan-1.473
 pleas-1.456
ucket-1.435
Tokenath
Token ID776
Feature activation+3.36e-01

Pos logit contributions
orth+2.844
isphere+2.769
л+2.588
enza+2.453
cliffe+2.441
Neg logit contributions
 disag-6.605
Sah-6.162
 pleas-6.137
Saharan-6.103
ucket-5.933
Token about
Token ID546
Feature activation+1.96e-01

Pos logit contributions
isphere+1.752
orth+1.724
л+1.646
arthed+1.535
cliffe+1.534
Neg logit contributions
 disag-3.984
Sah-3.747
Saharan-3.701
 pleas-3.677
uffy-3.632
Token how
Token ID703
Feature activation+8.83e-02

Pos logit contributions
isphere+1.633
orth+1.615
л+1.570
arthed+1.516
cliffe+1.503
Neg logit contributions
 disag-1.716
Sah-1.582
Saharan-1.567
 pleas-1.549
ucket-1.528
Token the
Token ID262
Feature activation+2.55e-01

Pos logit contributions
isphere+2.933
orth+2.918
л+2.833
arthed+2.717
cliffe+2.706
Neg logit contributions
 disag-3.380
Sah-3.145
Saharan-3.121
 pleas-3.053
ucket-3.028
Token charity
Token ID11016
Feature activation+4.34e-02

Pos logit contributions
isphere+2.104
orth+2.081
л+2.022
arthed+1.953
cliffe+1.935
Neg logit contributions
 disag-2.267
Sah-2.091
Saharan-2.072
 pleas-2.051
ucket-2.021
Token
Token ID447
Feature activation+9.45e-02

Pos logit contributions
isphere+0.343
orth+0.337
л+0.328
arthed+0.319
enza+0.315
Neg logit contributions
 disag-0.401
Sah-0.371
Saharan-0.367
 pleas-0.367
ucket-0.359
Token
Token ID247
Feature activation+1.29e-01

Pos logit contributions
isphere+0.773
orth+0.767
л+0.741
arthed+0.715
cliffe+0.711
Neg logit contributions
 disag-0.844
Sah-0.784
Saharan-0.778
 pleas-0.769
ucket-0.759
Tokens
Token ID82
Feature activation+4.96e-02

Pos logit contributions
isphere+0.984
orth+0.968
л+0.940
arthed+0.907
cliffe+0.897
Neg logit contributions
 disag-1.227
Sah-1.141
Saharan-1.132
 pleas-1.121
ucket-1.103
Token obligations
Token ID13675
Feature activation+6.93e-02

Pos logit contributions
isphere+0.416
orth+0.409
л+0.398
arthed+0.388
cliffe+0.383
Neg logit contributions
 disag-0.438
Sah-0.401
 pleas-0.398
Saharan-0.398
ucket-0.386
Token to
Token ID284
Feature activation+3.14e-01

Pos logit contributions
isphere+0.531
orth+0.524
л+0.508
arthed+0.492
enza+0.485
Neg logit contributions
 disag-0.658
Sah-0.608
Saharan-0.603
 pleas-0.601
ucket-0.590
Token the
Token ID262
Feature activation+4.46e-01

Pos logit contributions
isphere+2.535
orth+2.529
л+2.446
arthed+2.353
cliffe+2.341
Neg logit contributions
 disag-2.771
Sah-2.590
Saharan-2.566
 pleas-2.516
ucket-2.501
Token public
Token ID1171
Feature activation-1.23e-01

Pos logit contributions
isphere+3.213
orth+3.201
л+3.086
arthed+2.941
enza+2.935
Neg logit contributions
 disag-4.336
Sah-4.059
Saharan-4.025
 pleas-3.936
ucket-3.914
Token during
Token ID1141
Feature activation+2.86e-01

Pos logit contributions
 disag+1.140
 pleas+1.051
Sah+1.040
Saharan+1.020
ucket+1.008
Neg logit contributions
isphere-0.969
orth-0.944
л-0.920
arthed-0.903
enza-0.892
Token the
Token ID262
Feature activation+3.83e-01

Pos logit contributions
isphere+2.388
orth+2.369
л+2.300
arthed+2.222
cliffe+2.205
Neg logit contributions
 disag-2.502
Sah-2.312
Saharan-2.289
 pleas-2.253
ucket-2.230
Token States
Token ID1829
Feature activation-1.34e-01

Pos logit contributions
isphere+0.114
orth+0.112
л+0.109
arthed+0.105
cliffe+0.103
Neg logit contributions
 disag-0.144
Sah-0.134
Saharan-0.132
 pleas-0.131
ucket-0.129
Token is
Token ID318
Feature activation-6.97e-02

Pos logit contributions
 disag+1.206
Sah+1.104
 pleas+1.098
Saharan+1.098
ucket+1.072
Neg logit contributions
isphere-1.099
orth-1.086
л-1.047
arthed-1.021
enza-1.009
Token spir
Token ID9158
Feature activation+2.90e-01

Pos logit contributions
 disag+0.600
Sah+0.546
 pleas+0.546
Saharan+0.544
ucket+0.526
Neg logit contributions
isphere-0.600
orth-0.590
л-0.576
arthed-0.560
cliffe-0.554
Tokenalling
Token ID9221
Feature activation+8.77e-02

Pos logit contributions
isphere+1.582
orth+1.549
л+1.457
enza+1.367
arthed+1.358
Neg logit contributions
 disag-3.403
Sah-3.200
Saharan-3.170
 pleas-3.156
ucket-3.108
Token down
Token ID866
Feature activation+5.82e-03

Pos logit contributions
isphere+0.763
orth+0.755
л+0.734
arthed+0.712
cliffe+0.705
Neg logit contributions
 disag-0.743
Sah-0.681
Saharan-0.675
 pleas-0.669
ucket-0.656
Token into
Token ID656
Feature activation-9.00e-02

Pos logit contributions
isphere+0.049
orth+0.049
л+0.047
arthed+0.046
cliffe+0.045
Neg logit contributions
 disag-0.051
Sah-0.047
Saharan-0.046
 pleas-0.046
ucket-0.045
Token a
Token ID257
Feature activation-4.76e-02

Pos logit contributions
 disag+0.763
Sah+0.694
 pleas+0.687
Saharan+0.686
ucket+0.666
Neg logit contributions
isphere-0.785
orth-0.777
л-0.758
arthed-0.735
cliffe-0.729
Token basic
Token ID4096
Feature activation-6.81e-02

Pos logit contributions
 disag+0.419
Sah+0.383
 pleas+0.379
Saharan+0.378
ucket+0.367
Neg logit contributions
isphere-0.401
orth-0.396
л-0.386
arthed-0.377
cliffe-0.372
Token indec
Token ID29077
Feature activation-8.66e-02

Pos logit contributions
 disag+0.617
Sah+0.560
Saharan+0.555
 pleas+0.555
ucket+0.541
Neg logit contributions
isphere-0.556
orth-0.544
л-0.532
arthed-0.529
cliffe-0.514
Tokenency
Token ID1387
Feature activation+3.48e-01

Pos logit contributions
 disag+0.668
Sah+0.603
Saharan+0.600
 pleas+0.591
ucket+0.584
Neg logit contributions
isphere-0.812
orth-0.802
л-0.786
arthed-0.767
cliffe-0.756
Token and
Token ID290
Feature activation+1.51e-01

Pos logit contributions
isphere+2.764
orth+2.731
л+2.641
enza+2.528
arthed+2.520
Neg logit contributions
 disag-3.159
Sah-2.950
Saharan-2.923
 pleas-2.861
ucket-2.856
Token but
Token ID475
Feature activation+2.47e-01

Pos logit contributions
isphere+1.201
orth+1.184
л+1.146
arthed+1.108
enza+1.094
Neg logit contributions
 disag-1.565
Sah-1.451
Saharan-1.438
 pleas-1.433
ucket-1.406
Token respecting
Token ID30796
Feature activation-2.79e-01

Pos logit contributions
isphere+1.964
orth+1.943
л+1.886
arthed+1.813
cliffe+1.804
Neg logit contributions
 disag-2.256
Sah-2.089
Saharan-2.075
 pleas-2.041
ucket-2.024
Token them
Token ID606
Feature activation-1.09e-01

Pos logit contributions
 disag+2.337
 pleas+2.187
Sah+2.150
Saharan+2.084
uffy+2.063
Neg logit contributions
isphere-2.416
orth-2.377
arthed-2.317
л-2.305
enza-2.270
Token in
Token ID287
Feature activation-6.49e-03

Pos logit contributions
 disag+0.970
 pleas+0.894
Sah+0.889
Saharan+0.875
uffy+0.856
Neg logit contributions
isphere-0.892
orth-0.876
arthed-0.853
л-0.852
enza-0.824
Token their
Token ID511
Feature activation+1.81e-01

Pos logit contributions
 disag+0.057
Sah+0.052
 pleas+0.052
Saharan+0.052
ucket+0.051
Neg logit contributions
isphere-0.055
orth-0.054
л-0.052
arthed-0.051
enza-0.051
Token choice
Token ID3572
Feature activation+6.50e-02

Pos logit contributions
isphere+1.455
orth+1.437
л+1.397
arthed+1.358
enza+1.342
Neg logit contributions
 disag-1.652
Sah-1.520
 pleas-1.510
Saharan-1.503
ucket-1.467
Token not
Token ID407
Feature activation-3.25e-01

Pos logit contributions
isphere+0.512
orth+0.507
л+0.491
arthed+0.480
cliffe+0.471
Neg logit contributions
 disag-0.601
Sah-0.556
 pleas-0.550
Saharan-0.550
ucket-0.539
Token to
Token ID284
Feature activation+1.61e-01

Pos logit contributions
 disag+2.899
 pleas+2.670
Sah+2.654
Saharan+2.632
ucket+2.585
Neg logit contributions
isphere-2.649
orth-2.614
л-2.554
arthed-2.477
cliffe-2.441
Token talk
Token ID1561
Feature activation-2.53e-01

Pos logit contributions
isphere+1.452
orth+1.436
л+1.402
arthed+1.362
cliffe+1.344
Neg logit contributions
 disag-1.318
Sah-1.197
Saharan-1.182
 pleas-1.181
ucket-1.151
Token is
Token ID318
Feature activation-3.23e-01

Pos logit contributions
 disag+2.225
 pleas+2.037
Sah+1.992
Saharan+1.970
ucket+1.941
Neg logit contributions
isphere-2.111
orth-2.067
л-2.035
arthed-2.006
enza-1.959
Token more
Token ID517
Feature activation-4.60e-01

Pos logit contributions
 disag+2.807
 pleas+2.623
Sah+2.535
Saharan+2.494
 uncons+2.464
Neg logit contributions
isphere-2.740
orth-2.640
arthed-2.607
л-2.597
enza-2.507
Token that
Token ID326
Feature activation-1.78e-01

Pos logit contributions
 disag+1.921
Sah+1.752
Saharan+1.735
 pleas+1.714
ucket+1.679
Neg logit contributions
isphere-2.054
orth-2.011
л-1.967
arthed-1.916
enza-1.904
Token if
Token ID611
Feature activation+5.66e-02

Pos logit contributions
 disag+1.556
Sah+1.420
Saharan+1.406
 pleas+1.391
ucket+1.347
Neg logit contributions
isphere-1.520
orth-1.488
л-1.465
arthed-1.417
enza-1.405
Token all
Token ID477
Feature activation+1.79e-01

Pos logit contributions
isphere+0.476
orth+0.470
л+0.458
arthed+0.442
cliffe+0.438
Neg logit contributions
 disag-0.495
Sah-0.456
Saharan-0.452
 pleas-0.447
ucket-0.439
Token the
Token ID262
Feature activation-2.30e-01

Pos logit contributions
isphere+1.493
orth+1.477
л+1.435
arthed+1.387
cliffe+1.375
Neg logit contributions
 disag-1.569
Sah-1.446
Saharan-1.432
 pleas-1.417
ucket-1.396
Token 63
Token ID8093
Feature activation-4.42e-01

Pos logit contributions
 disag+1.962
Sah+1.772
 pleas+1.750
Saharan+1.732
uffy+1.664
Neg logit contributions
isphere-2.020
orth-1.994
л-1.956
enza-1.896
arthed-1.887
Token,
Token ID11
Feature activation-6.89e-01

Pos logit contributions
 disag+3.711
Sah+3.405
Saharan+3.349
 pleas+3.315
ucket+3.210
Neg logit contributions
isphere-3.802
orth-3.736
л-3.668
arthed-3.606
enza-3.591
Token511
Token ID41647
Feature activation-4.11e-01

Pos logit contributions
 disag+5.143
Sah+4.707
 pleas+4.652
Saharan+4.617
uffy+4.529
Neg logit contributions
isphere-6.314
orth-6.093
л-5.947
cliffe-5.778
arthed-5.773
Token coaches
Token ID11070
Feature activation-4.12e-01

Pos logit contributions
 disag+3.444
Sah+3.166
 pleas+3.117
Saharan+3.105
ucket+2.996
Neg logit contributions
isphere-3.514
orth-3.480
л-3.385
arthed-3.345
enza-3.325
Token under
Token ID739
Feature activation-2.27e-01

Pos logit contributions
 disag+3.474
Sah+3.116
 pleas+3.107
Saharan+3.095
ucket+3.025
Neg logit contributions
isphere-3.505
orth-3.490
л-3.463
arthed-3.351
enza-3.272
Token operation
Token ID4905
Feature activation-2.24e-01

Pos logit contributions
 disag+1.908
Sah+1.740
Saharan+1.729
 pleas+1.689
uffy+1.639
Neg logit contributions
isphere-2.023
orth-1.982
л-1.940
enza-1.879
arthed-1.850
Token are
Token ID389
Feature activation+9.91e-02

Pos logit contributions
 disag+1.933
Sah+1.754
Saharan+1.741
 pleas+1.737
ucket+1.693
Neg logit contributions
isphere-1.901
orth-1.882
л-1.851
arthed-1.782
cliffe-1.755
Token the
Token ID262
Feature activation-2.28e-01

Pos logit contributions
 disag+2.734
Sah+2.495
Saharan+2.474
 pleas+2.473
ucket+2.389
Neg logit contributions
isphere-2.927
orth-2.844
л-2.780
arthed-2.701
enza-2.678
Token day
Token ID1110
Feature activation+9.28e-02

Pos logit contributions
 disag+2.052
Sah+1.869
 pleas+1.868
Saharan+1.853
ucket+1.787
Neg logit contributions
isphere-1.882
orth-1.838
л-1.784
arthed-1.737
cliffe-1.722
Token a
Token ID257
Feature activation-5.04e-01

Pos logit contributions
isphere+0.688
orth+0.683
л+0.660
arthed+0.632
cliffe+0.629
Neg logit contributions
 disag-0.898
Sah-0.836
Saharan-0.829
 pleas-0.814
ucket-0.809
Token man
Token ID582
Feature activation-1.66e-01

Pos logit contributions
 disag+4.259
 pleas+3.930
Sah+3.847
Saharan+3.809
ucket+3.656
Neg logit contributions
isphere-4.390
orth-4.215
л-4.160
arthed-4.089
enza-3.975
Token was
Token ID373
Feature activation-9.83e-03

Pos logit contributions
 disag+1.477
 pleas+1.361
Sah+1.349
Saharan+1.331
ucket+1.304
Neg logit contributions
isphere-1.366
orth-1.345
л-1.320
arthed-1.286
enza-1.257
Token pronounced
Token ID16293
Feature activation-8.60e-01

Pos logit contributions
 disag+0.099
Sah+0.092
 pleas+0.091
Saharan+0.091
ucket+0.089
Neg logit contributions
isphere-0.070
orth-0.069
л-0.067
arthed-0.064
enza-0.063
Token dead
Token ID2636
Feature activation-2.75e-01

Pos logit contributions
 disag+5.100
 pleas+4.907
 uncons+4.511
Sah+4.424
Saharan+4.319
Neg logit contributions
isphere-8.964
arthed-8.627
л-8.563
orth-8.556
rity-8.369
Token after
Token ID706
Feature activation+1.23e-01

Pos logit contributions
 disag+2.467
 pleas+2.280
Sah+2.251
Saharan+2.220
uffy+2.167
Neg logit contributions
isphere-2.237
orth-2.175
arthed-2.105
л-2.104
enza-2.039
Token he
Token ID339
Feature activation+2.93e-01

Pos logit contributions
isphere+0.926
orth+0.914
л+0.886
arthed+0.853
cliffe+0.843
Neg logit contributions
 disag-1.183
Sah-1.098
Saharan-1.088
 pleas-1.080
ucket-1.063
Token was
Token ID373
Feature activation+2.39e-01

Pos logit contributions
isphere+2.279
orth+2.260
л+2.187
arthed+2.098
cliffe+2.094
Neg logit contributions
 disag-2.725
Sah-2.528
Saharan-2.510
 pleas-2.467
ucket-2.455
Token shot
Token ID2823
Feature activation+4.17e-02

Pos logit contributions
isphere+1.583
orth+1.567
л+1.507
arthed+1.441
cliffe+1.429
Neg logit contributions
 disag-2.508
Sah-2.346
Saharan-2.329
 pleas-2.301
ucket-2.281
Token and
Token ID290
Feature activation-4.65e-01

Pos logit contributions
 disag+4.454
Sah+4.194
 pleas+4.176
Saharan+4.110
uffy+4.034
Neg logit contributions
isphere-3.849
orth-3.753
л-3.638
arthed-3.569
enza-3.531
Token Producer
Token ID30436
Feature activation-3.93e-01

Pos logit contributions
 disag+3.781
Sah+3.555
 pleas+3.507
Saharan+3.487
uffy+3.393
Neg logit contributions
isphere-4.117
orth-3.967
л-3.845
enza-3.745
arthed-3.698
Token,
Token ID11
Feature activation-2.58e-01

Pos logit contributions
 disag+3.302
 pleas+3.057
Sah+3.046
Saharan+2.997
uffy+2.921
Neg logit contributions
isphere-3.330
orth-3.304
л-3.177
arthed-3.112
enza-3.109
Token
Token ID198
Feature activation-2.24e-02

Pos logit contributions
 disag+1.821
Sah+1.666
 pleas+1.637
Saharan+1.633
uffy+1.570
Neg logit contributions
isphere-2.584
orth-2.551
л-2.461
enza-2.420
arthed-2.409
Token
Token ID198
Feature activation-4.31e-01

Pos logit contributions
 disag+0.222
Sah+0.211
Saharan+0.209
 pleas+0.207
ucket+0.202
Neg logit contributions
isphere-0.161
orth-0.156
л-0.151
arthed-0.146
enza-0.145
TokenDA
Token ID5631
Feature activation-7.55e-01

Pos logit contributions
Sah+3.197
 disag+3.155
Saharan+3.082
 pleas+2.944
uffy+2.892
Neg logit contributions
isphere-3.972
orth-3.856
л-3.726
enza-3.718
 liner-3.701
TokenVID
Token ID11008
Feature activation+4.45e-01

Pos logit contributions
Sah+3.632
 DAV+3.498
 disag+3.462
 pleas+3.459
Saharan+3.370
Neg logit contributions
isphere-8.888
orth-8.505
enza-8.283
cliffe-8.239
rity-8.142
Token SL
Token ID12419
Feature activation-2.61e-02

Pos logit contributions
orth+3.436
isphere+3.403
л+3.400
cliffe+3.146
arthed+3.135
Neg logit contributions
 disag-4.131
Sah-3.808
Saharan-3.801
ucket-3.747
 pleas-3.678
TokenACK
Token ID8120
Feature activation-1.04e-01

Pos logit contributions
 disag+0.235
Sah+0.222
Saharan+0.220
 pleas+0.216
ucket+0.214
Neg logit contributions
isphere-0.211
orth-0.204
л-0.195
arthed-0.193
enza-0.193
Token
Token ID198
Feature activation+2.98e-02

Pos logit contributions
 disag+1.026
Sah+0.956
 pleas+0.945
Saharan+0.944
ucket+0.925
Neg logit contributions
isphere-0.763
orth-0.744
л-0.712
arthed-0.692
enza-0.692
Token
Token ID198
Feature activation+1.02e-01

Pos logit contributions
isphere+0.207
orth+0.202
л+0.195
arthed+0.188
enza+0.186
Neg logit contributions
 disag-0.304
Sah-0.286
Saharan-0.283
 pleas-0.281
ucket-0.276
Token own
Token ID898
Feature activation-9.04e-01

Pos logit contributions
 disag+6.611
 pleas+6.391
Sah+6.190
Saharan+6.119
ucket+5.800
Neg logit contributions
isphere-8.196
enza-7.815
orth-7.733
arthed-7.710
л-7.652
Token best
Token ID1266
Feature activation-6.55e-01

Pos logit contributions
 disag+4.650
 pleas+4.566
Sah+3.973
 uncons+3.780
uffy+3.719
Neg logit contributions
isphere-10.573
arthed-9.850
orth-9.828
enza-9.690
cliffe-9.665
Token selling
Token ID6301
Feature activation-8.06e-01

Pos logit contributions
 disag+3.125
 pleas+2.870
Sah+2.672
uffy+2.585
Saharan+2.570
Neg logit contributions
isphere-7.934
orth-7.668
л-7.604
enza-7.520
irc-7.479
Token Kindle
Token ID27114
Feature activation-8.06e-01

Pos logit contributions
 disag+3.037
 pleas+2.837
Sah+2.699
Saharan+2.610
uffy+2.471
Neg logit contributions
isphere-10.113
orth-9.841
rity-9.790
arthed-9.684
л-9.446
Token book
Token ID1492
Feature activation-5.34e-01

Pos logit contributions
 disag+2.867
 pleas+2.470
Sah+2.215
Saharan+2.020
uffy+1.943
Neg logit contributions
isphere-10.910
orth-10.384
arthed-10.304
rity-10.303
л-10.271
Token.
Token ID13
Feature activation-7.85e-01

Pos logit contributions
 disag+4.188
Sah+4.158
 pleas+3.985
Saharan+3.971
ucket+3.783
Neg logit contributions
isphere-4.735
orth-4.529
enza-4.380
arthed-4.368
rity-4.283
Token We
Token ID775
Feature activation+1.79e-01

Pos logit contributions
 disag+4.482
Sah+4.450
 pleas+4.358
Saharan+4.110
ucket+3.890
Neg logit contributions
isphere-8.368
orth-8.088
enza-7.804
arthed-7.801
bey-7.692
Token
Token ID447
Feature activation-3.50e-01

Pos logit contributions
isphere+1.357
orth+1.343
л+1.303
arthed+1.254
cliffe+1.242
Neg logit contributions
 disag-1.710
Sah-1.582
Saharan-1.575
 pleas-1.555
ucket-1.535
Token
Token ID247
Feature activation-1.79e-01

Pos logit contributions
 disag+2.671
Sah+2.548
Saharan+2.514
ucket+2.508
 pleas+2.481
Neg logit contributions
orth-3.205
isphere-3.177
л-3.014
cliffe-2.940
bey-2.899
Tokenll
Token ID297
Feature activation-1.07e+00

Pos logit contributions
 disag+1.599
Sah+1.484
 pleas+1.479
ucket+1.460
Saharan+1.451
Neg logit contributions
isphere-1.439
orth-1.394
л-1.344
arthed-1.310
enza-1.290
Token announce
Token ID5453
Feature activation-2.58e-01

Pos logit contributions
 disag+6.122
Sah+5.254
 pleas+5.065
Saharan+5.001
uffy+4.859
Neg logit contributions
isphere-11.599
orth-11.301
cliffe-10.741
enza-10.738
л-10.725
Token racist
Token ID9811
Feature activation-2.85e-01

Pos logit contributions
 disag+4.746
 pleas+4.375
Sah+4.266
Saharan+4.130
uffy+4.116
Neg logit contributions
isphere-4.690
orth-4.576
л-4.371
arthed-4.366
enza-4.271
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
 disag+2.630
Sah+2.414
 pleas+2.410
Saharan+2.364
uffy+2.317
Neg logit contributions
isphere-2.257
orth-2.219
arthed-2.122
л-2.121
enza-2.072
Token Flag
Token ID19762
Feature activation-4.55e-01

Pos logit contributions
 disag+2.119
Sah+1.978
 pleas+1.963
Saharan+1.944
ucket+1.874
Neg logit contributions
isphere-1.983
orth-1.933
л-1.854
arthed-1.853
enza-1.812
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
 disag+4.207
Sah+4.002
Saharan+3.949
 pleas+3.901
ucket+3.830
Neg logit contributions
isphere-3.427
orth-3.352
л-3.210
arthed-3.206
enza-3.164
Token
Token ID198
Feature activation-7.11e-01

Pos logit contributions
 disag+3.643
Sah+3.546
Saharan+3.501
 pleas+3.485
uffy+3.307
Neg logit contributions
isphere-3.497
orth-3.262
arthed-3.196
л-3.183
enza-3.112
TokenFlag
Token ID34227
Feature activation-1.21e+00

Pos logit contributions
Sah+3.681
Saharan+3.586
 disag+3.279
ucket+3.047
 pleas+3.042
Neg logit contributions
isphere-8.098
 liner-7.798
arthed-7.742
orth-7.718
rity-7.580
Token Reply
Token ID14883
Feature activation-2.80e-01

Pos logit contributions
 disag+4.334
 pleas+3.952
Sah+3.704
Saharan+3.632
 uncons+3.197
Neg logit contributions
isphere-14.469
orth-14.332
arthed-14.166
enza-13.805
rity-13.685
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
 disag+2.659
Sah+2.523
Saharan+2.499
 pleas+2.496
ucket+2.411
Neg logit contributions
isphere-2.126
orth-2.044
л-1.974
arthed-1.943
enza-1.895
Token
Token ID198
Feature activation-4.05e-01

Pos logit contributions
 disag+2.570
Sah+2.477
Saharan+2.446
 pleas+2.433
uffy+2.327
Neg logit contributions
isphere-2.231
orth-2.094
л-2.040
arthed-2.039
enza-1.982
Token19
Token ID1129
Feature activation-8.94e-01

Pos logit contributions
Sah+3.222
 disag+3.209
Saharan+3.117
 pleas+3.017
ucket+2.907
Neg logit contributions
isphere-3.585
orth-3.369
arthed-3.325
л-3.257
cliffe-3.256
Token Recommend
Token ID30361
Feature activation-1.94e-01

Pos logit contributions
 disag+4.146
Sah+3.705
Saharan+3.622
 pleas+3.580
uffy+3.258
Neg logit contributions
isphere-10.733
arthed-10.087
enza-9.983
orth-9.972
rity-9.895