TOP ACTIVATIONS
MAX = 1.347

handling of Mam ad ou Sak ho drugs test Read more
l ' E mpire . FIN DE TRAN SM ISSION ///
point , 7 - re bound , 2 - block effort
79 23 12 . e ce / edd 75 / AUT
half of the air we breath .
35 79 23 12 . e ce / edd 75 /
3 . THE BIG SH ORT People inside Goldman
short story HOL Y O AK about a quirky witch in
Metroid series developer Yosh io Sak amoto told me in 2010
As per reports published in media ,
27 , 2012 ) A 24 - year -
f ); RAW _ ASS ERT ( it -> vec ()
ate , was unin hab ited early last week when the
re missing all those guys ; it
( t ) Let s assume u
in the short run , but also in the long term
Revis it 's just crazy . I 've settled down
inking Mathematics : Teaching Social Justice by the Numbers " guide
1 AL READ Y COMP ET ED : vs . Seattle
DS CC As king Koch s for Cash

MIN ACTIVATIONS
MIN = -1.317

Get our daily newsletter Upgrade your inbox and get
Sonia R inc ón (@ S onia R in con )
ported License . <|endoftext|> Image copyright AP Image caption Peace talks
. Facebook Twitter Pinterest Mitch Robinson shows Tyson Gold
But at the same time he realizes he
. <|endoftext|> Image copyright Deadline Police have
Get our daily newsletter Upgrade your inbox and get
, associate editor (@ Aaron L _ Power , @ P
cohort of patients ( n = 91 ) only received trans
# 1 T ric er at ops # 1
. <|endoftext|> Image copyright publicity Image caption The Greeks
million years . <|endoftext|> Image copyright AFP The Bank
Serve hot ! <|endoftext|> Image copyright ESA Image caption Go ce
. Facebook Twitter Pinterest Mick M alth ouse :
? í k , H ric ( V aj s 41
The @ T ucker Carl son opening statement about our
n oh w crypt : Disable hardware encryption . ( bool
royalty ? @ A jit P ai F CC orp Sh
Santa Clara County v . Southern Pacific Railroad Company
Wester lund (@ C ody W ester lund ) October 7

INTERVAL 0.681 - 1.347
CONTAINS 0.222%

examples of Ant ill oth rix bones to the newly discovered
" 2016 . ?? .? ?" ] [ Event Country "
ON OM ICS AND TR ADE The Wednesday -
- front s " Ent ire classrooms of Somali
_ K k BY RG v Ch 5 Z k A

INTERVAL 0.015 - 0.681
CONTAINS 46.863%

model wearing a dress created from roses to mark the connection
Ellis , Devin Harris , Raymond Fel ton ( who has
uters typically pay none of these costs , he noted .
sets without knowing the magnitude of signals in them .
Thank you , Dave . Don na 's cub

INTERVAL -0.651 - 0.015
CONTAINS 52.601%

yards with one touchdown and one interception . He 's only
revealed there was no evidence of any prior relationship or association
doctors said she risked severe infection and scar ring if she
) or maybe for clarity s sake you reduce
playing well . Now we are playing well , it shows

INTERVAL -1.317 - -0.651
CONTAINS 0.314%

brew s beer , grows fruit and vegetables , keeps honey
. P el oton Based on the
Share this comment on Facebook Share this comment on Twitter
. Advertisement Continue reading the main story
China punished almost 300 , 000 officials for graft last year
Token handling
Token ID9041
Feature activation-3.19e-01

Pos logit contributions
alsh+0.371
roller+0.323
roid+0.319
ndra+0.316
rador+0.313
Neg logit contributions
�士-0.329
ciating-0.314
iev-0.305
��極-0.300
 EDIT-0.296
Token of
Token ID286
Feature activation-6.94e-02

Pos logit contributions
alsh+1.285
roller+1.102
roid+1.088
ndra+1.074
rador+1.063
Neg logit contributions
�士-1.378
ciating-1.321
iev-1.280
��極-1.258
 EDIT-1.239
Token Mam
Token ID29926
Feature activation+3.55e-02

Pos logit contributions
alsh+0.316
roller+0.276
roid+0.274
ndra+0.271
rador+0.268
Neg logit contributions
�士-0.263
ciating-0.250
iev-0.242
��極-0.238
 EDIT-0.234
Tokenad
Token ID324
Feature activation+1.62e-01

Pos logit contributions
�士+0.171
ciating+0.165
iev+0.162
��極+0.159
 Buk+0.158
Neg logit contributions
alsh-0.124
roller-0.104
roid-0.102
ndra-0.102
rador-0.100
Tokenou
Token ID280
Feature activation+2.04e-01

Pos logit contributions
�士+0.783
ciating+0.755
iev+0.740
��極+0.728
 Buk+0.719
Neg logit contributions
alsh-0.569
roller-0.475
roid-0.467
ndra-0.463
rador-0.458
Token Sak
Token ID13231
Feature activation+1.35e+00

Pos logit contributions
�士+0.585
ciating+0.548
iev+0.527
��極+0.515
 EDIT+0.505
Neg logit contributions
alsh-1.113
roller-0.996
roid-0.987
ndra-0.980
rador-0.973
Tokenho
Token ID8873
Feature activation-5.08e-02

Pos logit contributions
iev+4.105
�士+4.081
 Amar+3.903
 Buk+3.894
 Iz+3.885
Neg logit contributions
alsh-6.542
roid-5.855
rador-5.815
ndra-5.705
roller-5.654
Token drugs
Token ID5010
Feature activation+2.68e-01

Pos logit contributions
alsh+0.217
roller+0.187
roid+0.185
ndra+0.183
rador+0.181
Neg logit contributions
�士-0.207
ciating-0.198
iev-0.192
��極-0.189
 EDIT-0.186
Token test
Token ID1332
Feature activation-2.01e-01

Pos logit contributions
�士+1.028
ciating+0.981
iev+0.978
 Iz+0.959
 Buk+0.958
Neg logit contributions
alsh-1.173
roller-1.015
roid-1.011
ndra-1.005
rador-0.998
Token Read
Token ID4149
Feature activation-3.28e-01

Pos logit contributions
alsh+0.942
roller+0.826
roid+0.818
ndra+0.810
rador+0.803
Neg logit contributions
�士-0.736
ciating-0.699
iev-0.679
��極-0.666
 EDIT-0.657
Token more
Token ID517
Feature activation-3.79e-01

Pos logit contributions
alsh+1.456
roller+1.269
roid+1.250
ndra+1.246
rador+1.220
Neg logit contributions
�士-1.303
ciating-1.223
��極-1.175
iev-1.174
 EDIT-1.137
Token l
Token ID300
Feature activation+2.22e-01

Pos logit contributions
alsh+0.117
roller+0.103
roid+0.102
ndra+0.101
rador+0.100
Neg logit contributions
�士-0.085
ciating-0.080
iev-0.078
��極-0.076
 EDIT-0.075
Token'
Token ID6
Feature activation-5.74e-03

Pos logit contributions
�士+0.648
ciating+0.612
iev+0.600
��極+0.574
 EDIT+0.566
Neg logit contributions
alsh-1.191
roller-1.062
roid-1.052
ndra-1.042
rador-1.034
TokenE
Token ID36
Feature activation+2.52e-01

Pos logit contributions
alsh+0.027
roller+0.024
roid+0.023
ndra+0.023
rador+0.023
Neg logit contributions
�士-0.021
ciating-0.020
iev-0.019
��極-0.019
 EDIT-0.019
Tokenmpire
Token ID35386
Feature activation-1.17e-01

Pos logit contributions
�士+0.953
ciating+0.924
iev+0.916
 EDIT+0.875
��極+0.874
Neg logit contributions
alsh-1.115
roller-0.965
roid-0.950
rador-0.936
ndra-0.931
Token.
Token ID13
Feature activation+1.79e-01

Pos logit contributions
alsh+0.536
roller+0.469
roid+0.463
ndra+0.459
rador+0.455
Neg logit contributions
�士-0.437
ciating-0.415
iev-0.403
��極-0.395
 EDIT-0.391
TokenFIN
Token ID20032
Feature activation+1.27e+00

Pos logit contributions
�士+0.677
ciating+0.643
iev+0.627
��極+0.615
 EDIT+0.610
Neg logit contributions
alsh-0.812
roller-0.708
roid-0.699
ndra-0.691
rador-0.688
Token DE
Token ID5550
Feature activation+1.68e-01

Pos logit contributions
�士+3.892
ciating+3.820
 EDIT+3.753
iev+3.744
 Buk+3.640
Neg logit contributions
alsh-6.245
roller-5.605
roid-5.472
rador-5.440
ndra-5.428
Token TRAN
Token ID48213
Feature activation+1.17e-01

Pos logit contributions
�士+0.566
ciating+0.535
iev+0.518
��極+0.507
 EDIT+0.502
Neg logit contributions
alsh-0.835
roller-0.738
roid-0.731
ndra-0.725
rador-0.719
TokenSM
Token ID12310
Feature activation+4.38e-01

Pos logit contributions
�士+0.490
ciating+0.468
iev+0.459
��極+0.451
 EDIT+0.449
Neg logit contributions
alsh-0.484
roller-0.417
roid-0.411
ndra-0.408
rador-0.405
TokenISSION
Token ID40373
Feature activation+3.39e-01

Pos logit contributions
�士+1.040
ciating+0.969
iev+0.928
 EDIT+0.892
��極+0.890
Neg logit contributions
alsh-2.605
roller-2.353
roid-2.333
ndra-2.314
rador-2.303
Token ///
Token ID34013
Feature activation+8.02e-02

Pos logit contributions
�士+1.276
ciating+1.208
iev+1.189
 EDIT+1.164
��極+1.156
Neg logit contributions
alsh-1.543
roller-1.348
roid-1.324
ndra-1.311
rador-1.301
Tokenpoint
Token ID4122
Feature activation+3.39e-01

Pos logit contributions
�士+1.066
ciating+1.021
iev+1.013
��極+0.968
 Iz+0.967
Neg logit contributions
alsh-1.334
roid-1.148
ndra-1.143
roller-1.143
rador-1.140
Token,
Token ID11
Feature activation+4.94e-01

Pos logit contributions
�士+1.427
ciating+1.346
iev+1.346
��極+1.315
 Iz+1.311
Neg logit contributions
alsh-1.376
roller-1.175
roid-1.163
rador-1.160
ndra-1.144
Token 7
Token ID767
Feature activation+1.60e-01

Pos logit contributions
�士+1.735
ciating+1.647
iev+1.597
��極+1.563
 EDIT+1.545
Neg logit contributions
alsh-2.375
roller-2.089
roid-2.070
ndra-2.053
rador-2.035
Token-
Token ID12
Feature activation+5.37e-01

Pos logit contributions
�士+0.666
ciating+0.640
iev+0.625
 Iz+0.613
��極+0.611
Neg logit contributions
alsh-0.661
roller-0.564
roid-0.562
ndra-0.555
rador-0.550
Tokenre
Token ID260
Feature activation+4.03e-01

Pos logit contributions
�士+2.296
ciating+2.203
iev+2.195
 Iz+2.117
 Amar+2.107
Neg logit contributions
alsh-2.129
ndra-1.784
roid-1.767
roller-1.756
rador-1.755
Tokenbound
Token ID7784
Feature activation+1.26e+00

Pos logit contributions
�士+1.167
ciating+1.063
��極+1.022
iev+0.998
 EDIT+0.970
Neg logit contributions
alsh-2.251
roller-2.016
roid-2.009
ndra-1.985
rador-1.960
Token,
Token ID11
Feature activation+6.47e-01

Pos logit contributions
�士+4.641
iev+4.382
 Iz+4.375
 Amar+4.361
 Ala+4.342
Neg logit contributions
alsh-5.444
roller-4.781
rador-4.711
roid-4.686
ndra-4.657
Token 2
Token ID362
Feature activation+3.69e-01

Pos logit contributions
�士+2.288
ciating+2.170
iev+2.125
 Iz+2.082
 Buk+2.074
Neg logit contributions
alsh-3.062
roller-2.682
roid-2.666
ndra-2.647
rador-2.627
Token-
Token ID12
Feature activation+2.49e-01

Pos logit contributions
�士+1.522
ciating+1.450
iev+1.417
 Iz+1.398
��極+1.395
Neg logit contributions
alsh-1.549
roller-1.314
roid-1.312
ndra-1.296
rador-1.287
Tokenblock
Token ID9967
Feature activation+2.26e-01

Pos logit contributions
�士+0.986
ciating+0.941
iev+0.920
��極+0.898
 Iz+0.891
Neg logit contributions
alsh-1.081
roller-0.923
roid-0.919
ndra-0.916
rador-0.905
Token effort
Token ID3626
Feature activation+3.46e-01

Pos logit contributions
�士+0.953
ciating+0.901
iev+0.889
��極+0.873
 Iz+0.863
Neg logit contributions
alsh-0.932
roller-0.799
roid-0.789
ndra-0.785
rador-0.775
Token79
Token ID3720
Feature activation+2.08e-01

Pos logit contributions
�士+0.983
ciating+0.931
iev+0.902
 EDIT+0.869
��極+0.867
Neg logit contributions
alsh-1.584
roller-1.402
roid-1.392
ndra-1.384
rador-1.377
Token23
Token ID1954
Feature activation+4.85e-01

Pos logit contributions
�士+0.706
ciating+0.669
iev+0.651
��極+0.630
 EDIT+0.628
Neg logit contributions
alsh-1.018
roller-0.897
roid-0.889
ndra-0.884
rador-0.877
Token12
Token ID1065
Feature activation+6.56e-01

Pos logit contributions
�士+1.644
ciating+1.567
iev+1.551
 EDIT+1.503
 Buk+1.492
Neg logit contributions
alsh-2.332
roller-2.049
roid-2.027
rador-2.025
ndra-2.023
Token.
Token ID13
Feature activation+6.35e-01

Pos logit contributions
iev+2.587
�士+2.565
ciating+2.533
 Buk+2.519
 Iz+2.517
Neg logit contributions
alsh-2.677
roller-2.265
rador-2.248
roid-2.239
uca-2.220
Tokene
Token ID68
Feature activation+1.21e+00

Pos logit contributions
�士+1.373
ciating+1.296
iev+1.243
��極+1.180
 Buk+1.177
Neg logit contributions
alsh-3.856
roller-3.483
roid-3.448
uca-3.405
rador-3.395
Tokence
Token ID344
Feature activation+1.25e+00

Pos logit contributions
�士+3.912
iev+3.855
ciating+3.846
��極+3.658
 EDIT+3.627
Neg logit contributions
alsh-5.880
roller-5.302
rador-5.169
roid-5.141
ndra-5.092
Token/
Token ID14
Feature activation+4.79e-01

Pos logit contributions
�士+6.247
iev+6.014
 EDIT+5.949
 Buk+5.935
 Iz+5.879
Neg logit contributions
alsh-3.957
roller-3.297
ndra-3.187
rador-3.146
roid-3.081
Tokenedd
Token ID6048
Feature activation+3.60e-01

Pos logit contributions
�士+1.680
ciating+1.611
iev+1.577
��極+1.513
 EDIT+1.512
Neg logit contributions
alsh-2.266
roller-1.992
roid-1.975
ndra-1.962
rador-1.950
Token75
Token ID2425
Feature activation+2.78e-01

Pos logit contributions
�士+1.269
ciating+1.214
iev+1.193
 EDIT+1.141
 Buk+1.139
Neg logit contributions
alsh-1.702
roller-1.496
roid-1.481
ndra-1.473
rador-1.460
Token/
Token ID14
Feature activation+3.09e-01

Pos logit contributions
�士+1.438
ciating+1.398
iev+1.384
 EDIT+1.352
 Buk+1.348
Neg logit contributions
alsh-0.848
roller-0.687
roid-0.673
ndra-0.669
rador-0.660
TokenAUT
Token ID39371
Feature activation+8.09e-01

Pos logit contributions
�士+0.660
ciating+0.601
iev+0.596
��極+0.576
 EDIT+0.564
Neg logit contributions
alsh-1.897
roid-1.690
roller-1.686
ndra-1.679
uca-1.670
Token half
Token ID2063
Feature activation+4.70e-01

Pos logit contributions
alsh+0.227
roller+0.199
roid+0.197
ndra+0.195
rador+0.194
Neg logit contributions
�士-0.172
ciating-0.163
iev-0.157
��極-0.155
 EDIT-0.151
Token of
Token ID286
Feature activation+2.56e-01

Pos logit contributions
�士+1.740
ciating+1.652
iev+1.629
��極+1.593
 Iz+1.579
Neg logit contributions
alsh-2.142
roller-1.870
roid-1.829
ndra-1.824
rador-1.805
Token the
Token ID262
Feature activation+3.91e-01

Pos logit contributions
�士+0.872
ciating+0.826
iev+0.803
��極+0.782
 Iz+0.778
Neg logit contributions
alsh-1.254
roller-1.111
roid-1.093
ndra-1.085
rador-1.075
Token air
Token ID1633
Feature activation+4.12e-01

Pos logit contributions
�士+1.371
ciating+1.306
iev+1.270
 Buk+1.241
 EDIT+1.240
Neg logit contributions
alsh-1.860
roller-1.643
roid-1.614
ndra-1.601
rador-1.591
Token we
Token ID356
Feature activation+3.55e-01

Pos logit contributions
�士+1.594
ciating+1.524
iev+1.514
 Iz+1.464
��極+1.464
Neg logit contributions
alsh-1.785
roller-1.555
roid-1.529
ndra-1.522
rador-1.499
Token breath
Token ID8033
Feature activation+1.24e+00

Pos logit contributions
�士+1.243
ciating+1.193
iev+1.162
 EDIT+1.129
��極+1.125
Neg logit contributions
alsh-1.691
roller-1.487
roid-1.470
ndra-1.453
rador-1.450
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
�士+4.558
ciating+4.531
iev+4.463
 Iz+4.433
 EDIT+4.389
Neg logit contributions
alsh-5.164
roller-4.491
roid-4.425
ndra-4.393
rador-4.353
Token
Token ID198
Feature activation+1.40e-01

Pos logit contributions
�士+0.844
ciating+0.803
iev+0.783
 EDIT+0.770
 Iz+0.766
Neg logit contributions
alsh-1.027
roller-0.897
roid-0.886
ndra-0.877
rador-0.873
Token
Token ID198
Feature activation+2.48e-01

Pos logit contributions
�士+0.567
ciating+0.541
iev+0.525
��極+0.518
 EDIT+0.509
Neg logit contributions
alsh-0.604
roller-0.523
roid-0.518
ndra-0.512
rador-0.506
Token
Token ID447
Feature activation+1.69e-01

Pos logit contributions
�士+0.957
ciating+0.918
iev+0.894
��極+0.868
 EDIT+0.865
Neg logit contributions
alsh-1.092
roller-0.947
roid-0.939
ndra-0.933
rador-0.922
Token
Token ID246
Feature activation-1.43e-01

Pos logit contributions
�士+0.512
ciating+0.475
iev+0.464
��極+0.455
 EDIT+0.447
Neg logit contributions
alsh-0.889
roller-0.795
roid-0.783
ndra-0.775
rador-0.772
Token35
Token ID2327
Feature activation+3.09e-01

Pos logit contributions
�士+0.934
ciating+0.896
iev+0.880
 Buk+0.861
 EDIT+0.855
Neg logit contributions
alsh-1.100
roller-0.974
roid-0.966
ndra-0.957
rador-0.946
Token79
Token ID3720
Feature activation+2.08e-01

Pos logit contributions
�士+0.983
ciating+0.931
iev+0.902
 EDIT+0.869
��極+0.867
Neg logit contributions
alsh-1.584
roller-1.402
roid-1.392
ndra-1.384
rador-1.377
Token23
Token ID1954
Feature activation+4.85e-01

Pos logit contributions
�士+0.706
ciating+0.669
iev+0.651
��極+0.630
 EDIT+0.628
Neg logit contributions
alsh-1.018
roller-0.897
roid-0.889
ndra-0.884
rador-0.877
Token12
Token ID1065
Feature activation+6.56e-01

Pos logit contributions
�士+1.644
ciating+1.567
iev+1.551
 EDIT+1.503
 Buk+1.492
Neg logit contributions
alsh-2.332
roller-2.049
roid-2.027
rador-2.025
ndra-2.023
Token.
Token ID13
Feature activation+6.35e-01

Pos logit contributions
iev+2.587
�士+2.565
ciating+2.533
 Buk+2.519
 Iz+2.517
Neg logit contributions
alsh-2.677
roller-2.265
rador-2.248
roid-2.239
uca-2.220
Tokene
Token ID68
Feature activation+1.21e+00

Pos logit contributions
�士+1.373
ciating+1.296
iev+1.243
��極+1.180
 Buk+1.177
Neg logit contributions
alsh-3.856
roller-3.483
roid-3.448
uca-3.405
rador-3.395
Tokence
Token ID344
Feature activation+1.25e+00

Pos logit contributions
�士+3.912
iev+3.855
ciating+3.846
��極+3.658
 EDIT+3.627
Neg logit contributions
alsh-5.880
roller-5.302
rador-5.169
roid-5.141
ndra-5.092
Token/
Token ID14
Feature activation+4.79e-01

Pos logit contributions
�士+6.247
iev+6.014
 EDIT+5.949
 Buk+5.935
 Iz+5.879
Neg logit contributions
alsh-3.957
roller-3.297
ndra-3.187
rador-3.146
roid-3.081
Tokenedd
Token ID6048
Feature activation+3.60e-01

Pos logit contributions
�士+1.680
ciating+1.611
iev+1.577
��極+1.513
 EDIT+1.512
Neg logit contributions
alsh-2.266
roller-1.992
roid-1.975
ndra-1.962
rador-1.950
Token75
Token ID2425
Feature activation+2.78e-01

Pos logit contributions
�士+1.269
ciating+1.214
iev+1.193
 EDIT+1.141
 Buk+1.139
Neg logit contributions
alsh-1.702
roller-1.496
roid-1.481
ndra-1.473
rador-1.460
Token/
Token ID14
Feature activation+3.09e-01

Pos logit contributions
�士+1.438
ciating+1.398
iev+1.384
 EDIT+1.352
 Buk+1.348
Neg logit contributions
alsh-0.848
roller-0.687
roid-0.673
ndra-0.669
rador-0.660
Token3
Token ID18
Feature activation+1.95e-01

Pos logit contributions
alsh+0.485
roller+0.421
roid+0.417
ndra+0.413
rador+0.409
Neg logit contributions
�士-0.437
ciating-0.417
iev-0.405
��極-0.398
 EDIT-0.393
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
�士+0.849
ciating+0.818
iev+0.796
��極+0.785
 EDIT+0.785
Neg logit contributions
alsh-0.771
roid-0.656
roller-0.656
rador-0.635
ndra-0.635
Token THE
Token ID3336
Feature activation+3.89e-01

Pos logit contributions
�士+0.695
ciating+0.656
iev+0.643
 EDIT+0.630
 Buk+0.629
Neg logit contributions
alsh-0.885
roller-0.770
roid-0.768
ndra-0.754
rador-0.753
Token BIG
Token ID26746
Feature activation+4.77e-01

Pos logit contributions
�士+1.295
ciating+1.215
iev+1.189
 EDIT+1.179
 Buk+1.160
Neg logit contributions
alsh-1.937
roller-1.705
roid-1.693
ndra-1.678
rador-1.671
Token SH
Token ID6006
Feature activation+4.03e-02

Pos logit contributions
�士+1.619
 EDIT+1.523
ciating+1.517
iev+1.504
 Buk+1.479
Neg logit contributions
alsh-2.309
roller-2.030
roid-2.009
rador-2.005
ndra-2.002
TokenORT
Token ID9863
Feature activation+1.18e+00

Pos logit contributions
�士+0.134
ciating+0.126
iev+0.122
��極+0.120
 EDIT+0.118
Neg logit contributions
alsh-0.202
roller-0.179
roid-0.177
ndra-0.175
rador-0.174
Token
Token ID198
Feature activation+3.52e-01

Pos logit contributions
 EDIT+3.768
�士+3.753
iev+3.592
 Buk+3.554
 Iz+3.551
Neg logit contributions
alsh-5.726
roid-5.031
ndra-4.985
rador-4.976
roller-4.965
Token
Token ID198
Feature activation+4.08e-01

Pos logit contributions
�士+1.341
ciating+1.289
iev+1.272
 EDIT+1.239
 Buk+1.236
Neg logit contributions
alsh-1.563
roller-1.355
roid-1.342
ndra-1.330
rador-1.325
TokenPeople
Token ID8061
Feature activation-1.30e-02

Pos logit contributions
�士+1.538
ciating+1.463
iev+1.451
 Buk+1.398
 EDIT+1.396
Neg logit contributions
alsh-1.829
roid-1.570
roller-1.559
rador-1.550
ndra-1.540
Token inside
Token ID2641
Feature activation+7.78e-02

Pos logit contributions
alsh+0.056
roller+0.048
roid+0.048
ndra+0.047
rador+0.047
Neg logit contributions
�士-0.052
ciating-0.050
iev-0.049
��極-0.048
 EDIT-0.047
Token Goldman
Token ID18740
Feature activation+6.99e-03

Pos logit contributions
�士+0.255
ciating+0.240
iev+0.233
��極+0.227
 EDIT+0.226
Neg logit contributions
alsh-0.393
roller-0.347
roid-0.346
ndra-0.341
rador-0.339
Token short
Token ID1790
Feature activation+2.99e-02

Pos logit contributions
alsh+2.488
roller+2.158
roid+2.143
ndra+2.109
rador+2.089
Neg logit contributions
�士-2.327
ciating-2.222
iev-2.149
��極-2.120
 EDIT-2.067
Token story
Token ID1621
Feature activation-4.83e-02

Pos logit contributions
�士+0.121
ciating+0.115
iev+0.113
��極+0.110
 EDIT+0.110
Neg logit contributions
alsh-0.128
roller-0.110
roid-0.109
ndra-0.108
rador-0.107
Token HOL
Token ID49707
Feature activation+3.83e-01

Pos logit contributions
alsh+0.204
roller+0.176
roid+0.174
ndra+0.172
rador+0.171
Neg logit contributions
�士-0.197
ciating-0.188
iev-0.185
 EDIT-0.181
��極-0.180
TokenY
Token ID56
Feature activation+3.29e-01

Pos logit contributions
�士+1.454
ciating+1.381
iev+1.353
 EDIT+1.326
��極+1.316
Neg logit contributions
alsh-1.723
roller-1.501
roid-1.488
ndra-1.482
rador-1.468
TokenO
Token ID46
Feature activation-5.20e-02

Pos logit contributions
�士+1.196
ciating+1.133
iev+1.106
��極+1.082
 EDIT+1.078
Neg logit contributions
alsh-1.543
roller-1.352
roid-1.340
ndra-1.329
rador-1.320
TokenAK
Token ID10206
Feature activation+1.17e+00

Pos logit contributions
alsh+0.243
roller+0.214
roid+0.212
ndra+0.210
rador+0.207
Neg logit contributions
�士-0.191
ciating-0.181
iev-0.175
��極-0.172
 Buk-0.169
Token about
Token ID546
Feature activation-1.03e-01

Pos logit contributions
�士+4.393
 EDIT+4.199
iev+4.177
ciating+4.148
 Iz+4.118
Neg logit contributions
alsh-5.034
roller-4.415
rador-4.377
ndra-4.374
roid-4.357
Token a
Token ID257
Feature activation-2.80e-01

Pos logit contributions
alsh+0.484
roller+0.425
roid+0.420
ndra+0.417
rador+0.413
Neg logit contributions
�士-0.372
ciating-0.353
iev-0.342
��極-0.336
 EDIT-0.332
Token quirky
Token ID37276
Feature activation-7.72e-02

Pos logit contributions
alsh+1.251
roller+1.090
roid+1.079
ndra+1.067
rador+1.058
Neg logit contributions
�士-1.085
ciating-1.035
iev-1.004
��極-0.987
 EDIT-0.973
Token witch
Token ID16365
Feature activation-1.51e-01

Pos logit contributions
alsh+0.338
roller+0.293
roid+0.290
ndra+0.287
rador+0.284
Neg logit contributions
�士-0.305
ciating-0.291
iev-0.283
��極-0.278
 EDIT-0.275
Token in
Token ID287
Feature activation+1.93e-03

Pos logit contributions
alsh+0.659
roller+0.571
roid+0.565
ndra+0.561
rador+0.555
Neg logit contributions
�士-0.594
ciating-0.568
iev-0.557
��極-0.543
 EDIT-0.540
Token Metroid
Token ID45430
Feature activation+1.59e-01

Pos logit contributions
�士+0.411
ciating+0.392
iev+0.385
 Buk+0.379
 Iz+0.379
Neg logit contributions
alsh-0.433
roller-0.372
roid-0.366
ndra-0.366
rador-0.365
Token series
Token ID2168
Feature activation+1.50e-01

Pos logit contributions
�士+0.608
ciating+0.575
iev+0.566
��極+0.552
 EDIT+0.550
Neg logit contributions
alsh-0.715
roller-0.620
ndra-0.613
roid-0.612
rador-0.608
Token developer
Token ID8517
Feature activation-1.98e-01

Pos logit contributions
�士+0.570
ciating+0.541
iev+0.531
 EDIT+0.517
 Buk+0.517
Neg logit contributions
alsh-0.675
roller-0.585
roid-0.579
ndra-0.574
rador-0.572
Token Yosh
Token ID28563
Feature activation+3.15e-01

Pos logit contributions
alsh+0.886
roller+0.771
roid+0.763
ndra+0.756
rador+0.751
Neg logit contributions
�士-0.763
ciating-0.726
iev-0.709
��極-0.694
 EDIT-0.689
Tokenio
Token ID952
Feature activation+1.49e-01

Pos logit contributions
�士+1.164
ciating+1.104
iev+1.097
 Iz+1.056
��極+1.056
Neg logit contributions
alsh-1.441
roller-1.266
roid-1.252
ndra-1.248
rador-1.236
Token Sak
Token ID13231
Feature activation+1.12e+00

Pos logit contributions
�士+0.451
ciating+0.423
iev+0.409
��極+0.401
 Iz+0.398
Neg logit contributions
alsh-0.790
roller-0.705
roid-0.699
ndra-0.693
rador-0.691
Tokenamoto
Token ID25384
Feature activation+4.38e-01

Pos logit contributions
�士+4.264
iev+4.233
ciating+4.102
 Iz+4.027
 Amar+4.014
Neg logit contributions
alsh-4.622
ndra-4.040
roller-4.034
roid-3.973
rador-3.931
Token told
Token ID1297
Feature activation+4.40e-01

Pos logit contributions
�士+1.640
ciating+1.556
iev+1.535
��極+1.497
 Iz+1.495
Neg logit contributions
alsh-1.986
roller-1.732
roid-1.708
rador-1.697
ndra-1.695
Token me
Token ID502
Feature activation+2.24e-01

Pos logit contributions
�士+1.539
ciating+1.497
 Iz+1.478
 EDIT+1.463
 Buk+1.458
Neg logit contributions
alsh-2.047
rador-1.783
roller-1.782
roid-1.763
ndra-1.751
Token in
Token ID287
Feature activation-2.34e-01

Pos logit contributions
�士+0.913
ciating+0.876
iev+0.862
 Iz+0.844
 EDIT+0.843
Neg logit contributions
alsh-0.936
roller-0.812
roid-0.800
ndra-0.794
rador-0.790
Token 2010
Token ID3050
Feature activation+8.90e-02

Pos logit contributions
alsh+0.971
roller+0.836
roid+0.827
ndra+0.819
rador+0.808
Neg logit contributions
�士-0.978
ciating-0.936
iev-0.909
��極-0.896
 EDIT-0.882
Token
Token ID198
Feature activation-8.78e-02

Pos logit contributions
alsh+0.094
roller+0.081
roid+0.081
ndra+0.080
rador+0.079
Neg logit contributions
�士-0.087
ciating-0.083
iev-0.081
��極-0.080
 EDIT-0.079
Token
Token ID198
Feature activation+6.07e-02

Pos logit contributions
alsh+0.366
roller+0.317
roid+0.313
ndra+0.310
rador+0.303
Neg logit contributions
�士-0.376
ciating-0.355
��極-0.343
iev-0.339
 Afric-0.330
Token
Token ID447
Feature activation+1.27e-01

Pos logit contributions
�士+0.236
ciating+0.225
iev+0.220
��極+0.214
 EDIT+0.213
Neg logit contributions
alsh-0.269
roller-0.233
roid-0.231
ndra-0.229
rador-0.227
Token
Token ID250
Feature activation+1.88e-02

Pos logit contributions
�士+0.413
ciating+0.388
iev+0.378
��極+0.369
 EDIT+0.365
Neg logit contributions
alsh-0.640
roller-0.567
roid-0.561
ndra-0.556
rador-0.552
TokenAs
Token ID1722
Feature activation+1.05e-01

Pos logit contributions
�士+0.073
ciating+0.069
iev+0.068
��極+0.066
 EDIT+0.066
Neg logit contributions
alsh-0.083
roller-0.072
roid-0.072
ndra-0.071
rador-0.070
Token per
Token ID583
Feature activation+1.11e+00

Pos logit contributions
�士+0.416
ciating+0.398
iev+0.389
��極+0.379
 Buk+0.377
Neg logit contributions
alsh-0.456
roller-0.396
roid-0.392
ndra-0.386
rador-0.383
Token reports
Token ID3136
Feature activation-1.10e-01

Pos logit contributions
�士+3.809
ciating+3.631
iev+3.622
 Buk+3.582
 Iz+3.558
Neg logit contributions
alsh-5.163
roller-4.617
roid-4.564
ndra-4.499
uca-4.467
Token published
Token ID3199
Feature activation-3.99e-01

Pos logit contributions
alsh+0.450
roller+0.387
roid+0.381
ndra+0.377
rador+0.373
Neg logit contributions
�士-0.469
ciating-0.448
iev-0.438
��極-0.430
 EDIT-0.426
Token in
Token ID287
Feature activation+5.34e-02

Pos logit contributions
alsh+1.676
roller+1.443
roid+1.431
ndra+1.414
rador+1.400
Neg logit contributions
�士-1.652
ciating-1.581
iev-1.535
��極-1.514
 EDIT-1.489
Token media
Token ID2056
Feature activation+2.16e-01

Pos logit contributions
�士+0.187
ciating+0.179
iev+0.174
 Buk+0.171
 EDIT+0.170
Neg logit contributions
alsh-0.255
roller-0.225
roid-0.223
ndra-0.221
rador-0.218
Token,
Token ID11
Feature activation+1.29e-01

Pos logit contributions
�士+0.865
ciating+0.824
iev+0.811
 Buk+0.795
 EDIT+0.793
Neg logit contributions
alsh-0.919
roller-0.793
roid-0.784
ndra-0.783
uca-0.772
Token 27
Token ID2681
Feature activation+1.92e-01

Pos logit contributions
�士+2.144
iev+2.047
 Buk+2.046
 EDIT+2.043
 Iz+2.031
Neg logit contributions
alsh-3.625
roller-3.187
rador-3.161
roid-3.156
ndra-3.153
Token,
Token ID11
Feature activation+1.47e-01

Pos logit contributions
�士+0.881
ciating+0.850
iev+0.840
 EDIT+0.822
 Buk+0.818
Neg logit contributions
alsh-0.702
roller-0.590
roid-0.582
ndra-0.575
rador-0.571
Token 2012
Token ID2321
Feature activation+1.66e-01

Pos logit contributions
�士+0.662
ciating+0.637
iev+0.618
��極+0.612
 EDIT+0.601
Neg logit contributions
alsh-0.565
roller-0.480
roid-0.475
ndra-0.468
rador-0.463
Token)
Token ID8
Feature activation+5.76e-01

Pos logit contributions
�士+0.769
ciating+0.737
��極+0.712
iev+0.708
 Buk+0.687
Neg logit contributions
alsh-0.627
roller-0.531
roid-0.524
ndra-0.516
rador-0.509
Token
Token ID198
Feature activation+9.87e-01

Pos logit contributions
�士+2.173
ciating+2.085
iev+2.063
 EDIT+2.028
 Buk+2.007
Neg logit contributions
alsh-2.566
roller-2.231
roid-2.211
ndra-2.192
rador-2.179
Token
Token ID198
Feature activation+1.11e+00

Pos logit contributions
iev+3.150
 Buk+3.130
 Iz+3.127
 EDIT+3.125
 Amar+3.080
Neg logit contributions
alsh-4.720
rador-4.110
roller-4.096
roid-4.072
ndra-4.044
TokenA
Token ID32
Feature activation+4.53e-01

Pos logit contributions
�士+3.412
iev+3.329
ciating+3.287
AMI+3.231
 EDIT+3.208
Neg logit contributions
alsh-5.413
rador-4.805
ndra-4.737
roid-4.734
roller-4.696
Token 24
Token ID1987
Feature activation+2.68e-01

Pos logit contributions
�士+1.374
ciating+1.292
iev+1.274
 Buk+1.241
 EDIT+1.230
Neg logit contributions
alsh-2.339
roller-2.096
roid-2.082
ndra-2.071
rador-2.043
Token-
Token ID12
Feature activation+4.08e-01

Pos logit contributions
�士+1.136
ciating+1.097
iev+1.075
��極+1.050
 EDIT+1.045
Neg logit contributions
alsh-1.083
roller-0.926
roid-0.919
ndra-0.906
rador-0.898
Tokenyear
Token ID1941
Feature activation+8.74e-02

Pos logit contributions
�士+1.820
ciating+1.750
iev+1.711
��極+1.681
 EDIT+1.666
Neg logit contributions
alsh-1.569
roller-1.332
roid-1.318
ndra-1.304
rador-1.288
Token-
Token ID12
Feature activation+1.24e-01

Pos logit contributions
�士+0.392
ciating+0.373
iev+0.362
��極+0.359
 EDIT+0.353
Neg logit contributions
alsh-0.341
roller-0.291
roid-0.287
ndra-0.284
rador-0.281
Tokenf
Token ID69
Feature activation+2.26e-01

Pos logit contributions
�士+2.291
ciating+2.168
iev+2.158
 EDIT+2.118
 Iz+2.103
Neg logit contributions
alsh-2.326
roller-2.011
ndra-2.002
roid-1.978
rador-1.946
Token);
Token ID1776
Feature activation-5.59e-02

Pos logit contributions
�士+0.962
ciating+0.922
iev+0.908
 EDIT+0.883
��極+0.880
Neg logit contributions
alsh-0.911
roller-0.784
roid-0.770
ndra-0.769
rador-0.762
Token RAW
Token ID33782
Feature activation+3.92e-01

Pos logit contributions
alsh+0.244
roller+0.212
roid+0.210
ndra+0.208
rador+0.206
Neg logit contributions
�士-0.222
ciating-0.212
iev-0.206
��極-0.202
 EDIT-0.200
Token_
Token ID62
Feature activation-6.80e-02

Pos logit contributions
�士+1.810
ciating+1.739
iev+1.709
��極+1.681
 EDIT+1.680
Neg logit contributions
alsh-1.431
roller-1.199
roid-1.179
ndra-1.179
rador-1.170
TokenASS
Token ID10705
Feature activation+3.61e-01

Pos logit contributions
alsh+0.327
roller+0.289
roid+0.285
ndra+0.281
rador+0.278
Neg logit contributions
�士-0.242
ciating-0.229
iev-0.220
��極-0.218
 Buk-0.213
TokenERT
Token ID17395
Feature activation+1.10e+00

Pos logit contributions
�士+1.564
ciating+1.503
iev+1.478
 EDIT+1.453
 Buk+1.441
Neg logit contributions
alsh-1.424
roller-1.211
roid-1.193
ndra-1.190
rador-1.173
Token(
Token ID7
Feature activation+2.09e-01

Pos logit contributions
�士+4.855
iev+4.691
 EDIT+4.587
ciating+4.538
 Iz+4.532
Neg logit contributions
alsh-4.134
ndra-3.428
roller-3.423
rador-3.403
roid-3.345
Tokenit
Token ID270
Feature activation-6.53e-02

Pos logit contributions
�士+0.823
ciating+0.787
iev+0.768
��極+0.751
 EDIT+0.744
Neg logit contributions
alsh-0.915
roller-0.792
roid-0.783
ndra-0.778
rador-0.773
Token->
Token ID3784
Feature activation+3.70e-01

Pos logit contributions
alsh+0.227
roller+0.189
roid+0.186
ndra+0.185
rador+0.182
Neg logit contributions
�士-0.314
ciating-0.303
iev-0.298
��極-0.291
 EDIT-0.291
Tokenvec
Token ID35138
Feature activation+5.54e-01

Pos logit contributions
�士+1.345
ciating+1.310
iev+1.279
 EDIT+1.221
 Iz+1.220
Neg logit contributions
alsh-1.692
roller-1.468
roid-1.463
ndra-1.459
rador-1.446
Token()
Token ID3419
Feature activation+1.93e-02

Pos logit contributions
�士+2.224
ciating+2.144
iev+2.121
 Buk+2.044
 Iz+2.032
Neg logit contributions
alsh-2.299
roller-1.968
roid-1.957
ndra-1.955
rador-1.952
Tokenate
Token ID378
Feature activation+2.85e-01

Pos logit contributions
�士+2.418
iev+2.366
ciating+2.341
 Iz+2.304
 EDIT+2.300
Neg logit contributions
alsh-1.320
roller-1.078
roid-1.052
ndra-1.047
rador-1.034
Token,
Token ID11
Feature activation+3.02e-01

Pos logit contributions
�士+1.229
ciating+1.174
iev+1.169
 Iz+1.148
 Buk+1.145
Neg logit contributions
alsh-1.116
roller-0.957
roid-0.936
ndra-0.934
rador-0.924
Token was
Token ID373
Feature activation-2.08e-02

Pos logit contributions
�士+1.131
ciating+1.070
iev+1.049
��極+1.023
 Buk+1.018
Neg logit contributions
alsh-1.381
roller-1.208
roid-1.195
ndra-1.183
rador-1.174
Token unin
Token ID26329
Feature activation+1.45e-01

Pos logit contributions
alsh+0.091
roller+0.079
roid+0.078
ndra+0.077
rador+0.076
Neg logit contributions
�士-0.083
ciating-0.080
iev-0.077
��極-0.076
 EDIT-0.075
Tokenhab
Token ID5976
Feature activation+4.98e-01

Pos logit contributions
�士+0.432
ciating+0.410
iev+0.400
��極+0.383
 EDIT+0.377
Neg logit contributions
alsh-0.775
roller-0.687
roid-0.687
ndra-0.679
rador-0.677
Tokenited
Token ID863
Feature activation+1.07e+00

Pos logit contributions
�士+1.325
iev+1.299
ciating+1.279
 Iz+1.187
 EDIT+1.182
Neg logit contributions
alsh-2.767
roller-2.490
ndra-2.438
roid-2.434
rador-2.411
Token early
Token ID1903
Feature activation+3.04e-02

Pos logit contributions
�士+3.957
iev+3.861
 Iz+3.844
 Ala+3.841
ciating+3.840
Neg logit contributions
alsh-4.621
roller-3.996
rador-3.933
ndra-3.931
roid-3.922
Token last
Token ID938
Feature activation-1.44e-01

Pos logit contributions
�士+0.121
ciating+0.115
iev+0.112
��極+0.110
 EDIT+0.109
Neg logit contributions
alsh-0.132
roller-0.115
roid-0.114
ndra-0.112
rador-0.111
Token week
Token ID1285
Feature activation+4.24e-02

Pos logit contributions
alsh+0.543
roller+0.459
roid+0.454
ndra+0.448
rador+0.443
Neg logit contributions
�士-0.660
ciating-0.634
iev-0.619
��極-0.609
 EDIT-0.603
Token when
Token ID618
Feature activation-1.75e-02

Pos logit contributions
�士+0.187
ciating+0.180
iev+0.176
��極+0.173
 EDIT+0.172
Neg logit contributions
alsh-0.166
roller-0.141
roid-0.139
ndra-0.137
rador-0.136
Token the
Token ID262
Feature activation+6.13e-02

Pos logit contributions
alsh+0.077
roller+0.067
roid+0.067
ndra+0.066
rador+0.065
Neg logit contributions
�士-0.068
ciating-0.065
iev-0.063
��極-0.062
 EDIT-0.061
Token
Token ID447
Feature activation+2.77e-02

Pos logit contributions
�士+0.243
ciating+0.233
iev+0.227
��極+0.222
 EDIT+0.220
Neg logit contributions
alsh-0.255
roller-0.219
roid-0.218
ndra-0.215
rador-0.213
Token
Token ID247
Feature activation+7.54e-02

Pos logit contributions
�士+0.100
ciating+0.095
iev+0.092
��極+0.091
 EDIT+0.089
Neg logit contributions
alsh-0.131
roller-0.115
roid-0.114
ndra-0.112
rador-0.112
Tokenre
Token ID260
Feature activation+7.73e-02

Pos logit contributions
�士+0.344
ciating+0.331
iev+0.324
��極+0.318
 EDIT+0.316
Neg logit contributions
alsh-0.283
roller-0.239
roid-0.236
ndra-0.233
rador-0.231
Token missing
Token ID4814
Feature activation+2.28e-01

Pos logit contributions
�士+0.314
ciating+0.301
iev+0.293
��極+0.288
 EDIT+0.285
Neg logit contributions
alsh-0.329
roller-0.284
roid-0.281
ndra-0.279
rador-0.276
Token all
Token ID477
Feature activation+6.41e-01

Pos logit contributions
�士+0.823
ciating+0.783
iev+0.759
��極+0.744
 EDIT+0.735
Neg logit contributions
alsh-1.074
roller-0.942
roid-0.933
ndra-0.925
rador-0.917
Token those
Token ID883
Feature activation+1.07e+00

Pos logit contributions
�士+2.327
ciating+2.260
iev+2.216
 Iz+2.170
 Buk+2.159
Neg logit contributions
alsh-2.954
roller-2.546
ndra-2.529
roid-2.515
rador-2.508
Token guys
Token ID3730
Feature activation+2.95e-01

Pos logit contributions
�士+4.247
ciating+4.183
iev+4.103
 Iz+4.062
 Amar+4.044
Neg logit contributions
alsh-4.426
ndra-3.706
rador-3.700
roid-3.693
roller-3.691
Token;
Token ID26
Feature activation+3.83e-01

Pos logit contributions
�士+1.256
ciating+1.214
iev+1.194
 EDIT+1.160
 Iz+1.160
Neg logit contributions
alsh-1.182
roller-1.005
roid-0.997
ndra-0.988
rador-0.982
Token it
Token ID340
Feature activation-4.44e-02

Pos logit contributions
�士+1.526
ciating+1.466
iev+1.430
 Iz+1.398
 Buk+1.396
Neg logit contributions
alsh-1.654
roller-1.424
roid-1.413
ndra-1.403
rador-1.393
Token
Token ID447
Feature activation-3.39e-01

Pos logit contributions
alsh+0.189
roller+0.163
roid+0.161
ndra+0.160
rador+0.158
Neg logit contributions
�士-0.180
ciating-0.172
iev-0.168
��極-0.165
 EDIT-0.163
Token
Token ID247
Feature activation-2.78e-01

Pos logit contributions
alsh+1.536
roller+1.330
roid+1.323
ndra+1.313
rador+1.296
Neg logit contributions
�士-1.296
ciating-1.247
iev-1.194
��極-1.166
 EDIT-1.165
Token (
Token ID357
Feature activation+1.33e-01

Pos logit contributions
alsh+1.231
roller+1.073
roid+1.062
ndra+1.052
rador+1.042
Neg logit contributions
�士-1.046
ciating-0.997
iev-0.969
��極-0.951
 EDIT-0.940
Tokent
Token ID83
Feature activation+5.04e-02

Pos logit contributions
�士+0.527
ciating+0.504
iev+0.492
��極+0.482
 EDIT+0.476
Neg logit contributions
alsh-0.578
roller-0.502
roid-0.495
ndra-0.491
rador-0.488
Token)
Token ID8
Feature activation-6.15e-02

Pos logit contributions
�士+0.218
ciating+0.209
iev+0.206
��極+0.202
 EDIT+0.201
Neg logit contributions
alsh-0.199
roller-0.171
roid-0.168
ndra-0.167
rador-0.165
Token
Token ID198
Feature activation-1.77e-01

Pos logit contributions
alsh+0.266
roller+0.231
roid+0.228
ndra+0.226
rador+0.224
Neg logit contributions
�士-0.246
ciating-0.235
iev-0.229
��極-0.225
 EDIT-0.222
Token
Token ID198
Feature activation-1.42e-01

Pos logit contributions
alsh+0.731
roller+0.631
roid+0.625
ndra+0.617
rador+0.604
Neg logit contributions
�士-0.774
ciating-0.728
��極-0.706
iev-0.692
 Afric-0.674
TokenLet
Token ID5756
Feature activation+1.06e+00

Pos logit contributions
alsh+0.584
roller+0.502
roid+0.496
ndra+0.491
rador+0.486
Neg logit contributions
�士-0.598
ciating-0.572
iev-0.558
��極-0.548
 EDIT-0.542
Token
Token ID447
Feature activation-1.09e-01

Pos logit contributions
�士+3.781
iev+3.560
ciating+3.550
 Buk+3.468
 EDIT+3.450
Neg logit contributions
alsh-4.870
roller-4.290
roid-4.193
ndra-4.164
rador-4.161
Token
Token ID247
Feature activation+2.64e-01

Pos logit contributions
alsh+0.510
roller+0.447
roid+0.442
ndra+0.439
rador+0.435
Neg logit contributions
�士-0.402
ciating-0.380
iev-0.369
��極-0.363
 EDIT-0.357
Tokens
Token ID82
Feature activation-4.01e-01

Pos logit contributions
�士+1.037
ciating+0.990
iev+0.969
��極+0.946
 EDIT+0.938
Neg logit contributions
alsh-1.156
roller-1.004
roid-0.989
ndra-0.983
rador-0.977
Token assume
Token ID7048
Feature activation+3.88e-02

Pos logit contributions
alsh+1.675
roller+1.439
roid+1.425
ndra+1.408
rador+1.393
Neg logit contributions
�士-1.678
ciating-1.603
iev-1.543
��極-1.537
 Buk-1.501
Token u
Token ID334
Feature activation-6.32e-02

Pos logit contributions
�士+0.151
ciating+0.143
iev+0.140
��極+0.137
 EDIT+0.136
Neg logit contributions
alsh-0.172
roller-0.150
roid-0.148
ndra-0.147
rador-0.145
Token in
Token ID287
Feature activation+3.84e-01

Pos logit contributions
�士+1.182
ciating+1.142
iev+1.119
��極+1.091
 Buk+1.089
Neg logit contributions
alsh-1.084
roller-0.931
roid-0.916
ndra-0.908
rador-0.899
Token the
Token ID262
Feature activation+2.43e-01

Pos logit contributions
�士+1.343
ciating+1.280
iev+1.246
��極+1.210
 Buk+1.203
Neg logit contributions
alsh-1.838
roller-1.622
roid-1.605
ndra-1.592
rador-1.575
Token short
Token ID1790
Feature activation+1.69e-01

Pos logit contributions
�士+0.928
ciating+0.888
iev+0.864
��極+0.845
 EDIT+0.839
Neg logit contributions
alsh-1.090
roller-0.950
roid-0.941
ndra-0.932
rador-0.924
Token run
Token ID1057
Feature activation-3.92e-01

Pos logit contributions
�士+0.723
ciating+0.693
iev+0.683
��極+0.666
 EDIT+0.662
Neg logit contributions
alsh-0.678
roller-0.581
roid-0.579
ndra-0.570
rador-0.562
Token,
Token ID11
Feature activation+3.59e-01

Pos logit contributions
alsh+1.526
roller+1.299
roid+1.287
ndra+1.270
rador+1.251
Neg logit contributions
�士-1.748
ciating-1.670
iev-1.619
��極-1.603
 EDIT-1.578
Token but
Token ID475
Feature activation+1.05e+00

Pos logit contributions
�士+1.315
ciating+1.258
iev+1.232
��極+1.199
 Buk+1.195
Neg logit contributions
alsh-1.654
roller-1.452
roid-1.437
ndra-1.423
rador-1.414
Token also
Token ID635
Feature activation+7.41e-01

Pos logit contributions
�士+3.641
ciating+3.572
 Iz+3.481
iev+3.472
 Afric+3.434
Neg logit contributions
alsh-4.846
roller-4.297
roid-4.206
rador-4.145
ndra-4.134
Token in
Token ID287
Feature activation+2.39e-01

Pos logit contributions
�士+2.743
ciating+2.679
iev+2.610
 Iz+2.579
 Buk+2.558
Neg logit contributions
alsh-3.302
roller-2.899
roid-2.837
ndra-2.812
rador-2.789
Token the
Token ID262
Feature activation+1.99e-01

Pos logit contributions
�士+0.856
ciating+0.819
iev+0.794
 Iz+0.772
��極+0.770
Neg logit contributions
alsh-1.128
roller-0.996
roid-0.984
ndra-0.976
rador-0.961
Token long
Token ID890
Feature activation+1.16e-01

Pos logit contributions
�士+0.649
ciating+0.617
iev+0.595
��極+0.581
 Buk+0.574
Neg logit contributions
alsh-1.000
roller-0.886
roid-0.879
ndra-0.871
rador-0.863
Token term
Token ID3381
Feature activation+2.59e-01

Pos logit contributions
�士+0.497
ciating+0.478
iev+0.475
 Afric+0.458
��極+0.457
Neg logit contributions
alsh-0.462
roller-0.397
roid-0.393
ndra-0.385
rador-0.379
Token Revis
Token ID46146
Feature activation+5.78e-01

Pos logit contributions
�士+0.267
ciating+0.237
iev+0.225
 EDIT+0.206
��極+0.206
Neg logit contributions
alsh-1.095
roller-0.997
roid-0.990
ndra-0.988
rador-0.982
Token
Token ID851
Feature activation+1.04e-01

Pos logit contributions
�士+2.395
ciating+2.337
iev+2.293
 EDIT+2.242
 Iz+2.224
Neg logit contributions
alsh-2.330
roller-2.001
roid-1.983
ndra-1.974
rador-1.957
Token it
Token ID340
Feature activation-5.63e-02

Pos logit contributions
�士+0.398
ciating+0.380
iev+0.370
��極+0.361
 EDIT+0.360
Neg logit contributions
alsh-0.463
roller-0.402
roid-0.400
ndra-0.396
rador-0.393
Token's
Token ID338
Feature activation+3.17e-01

Pos logit contributions
alsh+0.233
roller+0.200
roid+0.198
ndra+0.196
rador+0.194
Neg logit contributions
�士-0.236
ciating-0.226
iev-0.220
��極-0.216
 EDIT-0.214
Token just
Token ID655
Feature activation-9.85e-02

Pos logit contributions
�士+1.216
ciating+1.168
iev+1.140
 Iz+1.114
��極+1.113
Neg logit contributions
alsh-1.407
roller-1.220
roid-1.211
ndra-1.200
rador-1.191
Token crazy
Token ID7165
Feature activation+1.05e+00

Pos logit contributions
alsh+0.437
roller+0.381
roid+0.376
ndra+0.372
rador+0.368
Neg logit contributions
�士-0.385
ciating-0.366
iev-0.355
��極-0.350
 EDIT-0.344
Token.
Token ID13
Feature activation+9.32e-02

Pos logit contributions
ciating+4.118
�士+4.111
iev+3.977
 Iz+3.944
 EDIT+3.942
Neg logit contributions
alsh-4.279
roid-3.722
ndra-3.709
rador-3.667
roller-3.665
Token I
Token ID314
Feature activation+4.36e-02

Pos logit contributions
�士+0.347
ciating+0.331
iev+0.322
 EDIT+0.315
��極+0.314
Neg logit contributions
alsh-0.427
roller-0.373
roid-0.371
ndra-0.368
rador-0.365
Token've
Token ID1053
Feature activation+2.94e-01

Pos logit contributions
�士+0.180
ciating+0.172
iev+0.167
��極+0.165
 EDIT+0.163
Neg logit contributions
alsh-0.183
roller-0.158
roid-0.156
ndra-0.155
rador-0.153
Token settled
Token ID10282
Feature activation+3.68e-01

Pos logit contributions
�士+1.110
ciating+1.064
iev+1.033
��極+1.013
 Buk+1.003
Neg logit contributions
alsh-1.329
roller-1.157
roid-1.146
ndra-1.136
rador-1.125
Token down
Token ID866
Feature activation-5.83e-03

Pos logit contributions
�士+1.410
ciating+1.373
iev+1.339
 Iz+1.319
 EDIT+1.312
Neg logit contributions
alsh-1.611
roller-1.384
roid-1.379
ndra-1.376
rador-1.362
Tokeninking
Token ID8040
Feature activation+1.16e-01

Pos logit contributions
alsh+0.922
roller+0.787
roid+0.778
ndra+0.768
rador+0.756
Neg logit contributions
�士-1.053
ciating-1.008
iev-0.978
��極-0.971
 EDIT-0.957
Token Mathematics
Token ID39448
Feature activation+3.56e-01

Pos logit contributions
�士+0.405
ciating+0.385
iev+0.373
��極+0.364
 EDIT+0.360
Neg logit contributions
alsh-0.558
roller-0.490
roid-0.486
ndra-0.482
rador-0.478
Token:
Token ID25
Feature activation+1.60e-01

Pos logit contributions
�士+1.298
ciating+1.246
iev+1.228
 Iz+1.197
 Buk+1.195
Neg logit contributions
alsh-1.632
roller-1.421
roid-1.405
ndra-1.396
rador-1.394
Token Teaching
Token ID38094
Feature activation+5.98e-01

Pos logit contributions
�士+0.558
ciating+0.530
iev+0.513
��極+0.502
 EDIT+0.497
Neg logit contributions
alsh-0.773
roller-0.680
roid-0.674
ndra-0.668
rador-0.662
Token Social
Token ID5483
Feature activation+1.69e-01

Pos logit contributions
�士+2.208
ciating+2.106
iev+2.063
 Afric+2.017
 Iz+2.015
Neg logit contributions
alsh-2.753
roller-2.384
roid-2.373
ndra-2.347
rador-2.330
Token Justice
Token ID4796
Feature activation+1.04e+00

Pos logit contributions
�士+0.503
ciating+0.473
iev+0.464
 EDIT+0.445
 Iz+0.443
Neg logit contributions
alsh-0.901
roller-0.802
roid-0.794
ndra-0.787
rador-0.787
Token by
Token ID416
Feature activation+3.62e-01

Pos logit contributions
�士+3.823
iev+3.693
ciating+3.680
 Afric+3.616
 Iz+3.614
Neg logit contributions
alsh-4.607
roller-3.982
rador-3.948
roid-3.908
ndra-3.904
Token the
Token ID262
Feature activation-5.95e-02

Pos logit contributions
�士+1.346
ciating+1.293
iev+1.249
 EDIT+1.220
 Buk+1.219
Neg logit contributions
alsh-1.664
roller-1.447
roid-1.432
ndra-1.422
rador-1.413
Token Numbers
Token ID27797
Feature activation+1.63e-01

Pos logit contributions
alsh+0.268
roller+0.234
roid+0.232
ndra+0.230
rador+0.227
Neg logit contributions
�士-0.227
ciating-0.217
iev-0.210
��極-0.207
 EDIT-0.204
Token"
Token ID1
Feature activation-9.72e-02

Pos logit contributions
�士+0.598
ciating+0.573
iev+0.561
 EDIT+0.545
 Iz+0.545
Neg logit contributions
alsh-0.754
roller-0.653
roid-0.649
ndra-0.648
rador-0.645
Token guide
Token ID5698
Feature activation-1.74e-01

Pos logit contributions
alsh+0.407
roller+0.351
roid+0.347
ndra+0.343
rador+0.339
Neg logit contributions
�士-0.404
ciating-0.386
iev-0.375
��極-0.370
 EDIT-0.365
Token 1
Token ID352
Feature activation+2.77e-01

Pos logit contributions
�士+0.766
ciating+0.723
iev+0.711
 EDIT+0.700
 Ala+0.693
Neg logit contributions
alsh-0.978
roller-0.855
roid-0.848
ndra-0.841
rador-0.836
Token AL
Token ID8355
Feature activation+5.24e-01

Pos logit contributions
�士+0.899
ciating+0.848
iev+0.825
 EDIT+0.819
 Ala+0.804
Neg logit contributions
alsh-1.401
roller-1.236
roid-1.228
ndra-1.221
rador-1.211
TokenREAD
Token ID15675
Feature activation+3.04e-01

Pos logit contributions
�士+1.569
ciating+1.474
iev+1.450
 EDIT+1.397
��極+1.381
Neg logit contributions
alsh-2.774
roller-2.472
roid-2.445
ndra-2.444
rador-2.420
TokenY
Token ID56
Feature activation+1.90e-01

Pos logit contributions
�士+1.290
ciating+1.232
iev+1.188
��極+1.183
 Afric+1.153
Neg logit contributions
alsh-1.254
roller-1.080
roid-1.071
ndra-1.059
rador-1.040
Token COMP
Token ID24301
Feature activation+5.09e-01

Pos logit contributions
�士+0.541
ciating+0.505
iev+0.488
��極+0.475
 EDIT+0.470
Neg logit contributions
alsh-1.039
roller-0.929
roid-0.921
ndra-0.915
rador-0.908
TokenET
Token ID2767
Feature activation+1.04e+00

Pos logit contributions
�士+1.408
ciating+1.322
iev+1.287
��極+1.236
 EDIT+1.235
Neg logit contributions
alsh-2.814
roller-2.518
roid-2.494
ndra-2.476
rador-2.456
TokenED
Token ID1961
Feature activation+5.55e-01

Pos logit contributions
�士+3.639
ciating+3.498
iev+3.480
 EDIT+3.401
 Buk+3.370
Neg logit contributions
alsh-4.893
roller-4.275
roid-4.210
rador-4.173
ndra-4.172
Token:
Token ID25
Feature activation+5.14e-02

Pos logit contributions
�士+1.927
ciating+1.808
iev+1.784
 EDIT+1.769
 Ala+1.732
Neg logit contributions
alsh-2.651
roller-2.341
ndra-2.320
roid-2.306
rador-2.274
Token vs
Token ID3691
Feature activation+1.60e-01

Pos logit contributions
�士+0.218
ciating+0.208
iev+0.204
��極+0.199
 EDIT+0.199
Neg logit contributions
alsh-0.209
roller-0.180
roid-0.178
ndra-0.177
rador-0.174
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
�士+0.740
ciating+0.711
iev+0.693
��極+0.684
 EDIT+0.675
Neg logit contributions
alsh-0.591
roller-0.499
roid-0.493
ndra-0.487
rador-0.480
Token Seattle
Token ID7312
Feature activation-8.52e-02

Pos logit contributions
�士+0.514
ciating+0.481
iev+0.467
 EDIT+0.451
��極+0.450
Neg logit contributions
alsh-0.948
roller-0.846
roid-0.838
ndra-0.834
rador-0.827
Token
Token ID447
Feature activation-1.13e-01

Pos logit contributions
�士+0.363
ciating+0.347
iev+0.339
��極+0.330
 EDIT+0.329
Neg logit contributions
alsh-0.418
roller-0.362
roid-0.360
ndra-0.356
rador-0.354
Token
Token ID250
Feature activation+1.84e-01

Pos logit contributions
alsh+0.542
roller+0.477
roid+0.472
ndra+0.468
rador+0.463
Neg logit contributions
�士-0.404
ciating-0.381
iev-0.369
��極-0.365
 EDIT-0.358
TokenDS
Token ID5258
Feature activation+6.39e-02

Pos logit contributions
�士+0.721
ciating+0.689
iev+0.671
��極+0.657
 EDIT+0.656
Neg logit contributions
alsh-0.808
roller-0.702
roid-0.695
ndra-0.688
rador-0.683
TokenCC
Token ID4093
Feature activation-1.72e-01

Pos logit contributions
�士+0.249
ciating+0.237
iev+0.232
��極+0.226
 EDIT+0.226
Neg logit contributions
alsh-0.283
roller-0.246
roid-0.243
ndra-0.241
rador-0.239
Token As
Token ID1081
Feature activation+2.42e-01

Pos logit contributions
alsh+0.775
roller+0.676
roid+0.669
ndra+0.662
rador+0.656
Neg logit contributions
�士-0.659
ciating-0.629
iev-0.610
��極-0.600
 EDIT-0.591
Tokenking
Token ID3364
Feature activation+1.04e+00

Pos logit contributions
�士+1.108
ciating+1.071
iev+1.044
 EDIT+1.022
��極+1.020
Neg logit contributions
alsh-0.904
roller-0.762
roid-0.754
ndra-0.743
rador-0.737
Token Koch
Token ID17009
Feature activation+5.83e-01

Pos logit contributions
�士+3.905
ciating+3.798
 EDIT+3.694
iev+3.676
 Buk+3.657
Neg logit contributions
alsh-4.568
roid-3.882
roller-3.876
rador-3.853
ndra-3.824
Tokens
Token ID82
Feature activation+5.77e-01

Pos logit contributions
�士+2.199
ciating+2.083
iev+2.063
 EDIT+2.013
 Iz+2.009
Neg logit contributions
alsh-2.626
ndra-2.251
roller-2.242
roid-2.235
rador-2.221
Token for
Token ID329
Feature activation+4.29e-01

Pos logit contributions
�士+2.435
ciating+2.343
iev+2.282
 EDIT+2.257
 Buk+2.246
Neg logit contributions
alsh-2.338
roller-1.975
roid-1.967
ndra-1.958
rador-1.934
Token Cash
Token ID16210
Feature activation+2.67e-01

Pos logit contributions
�士+1.475
ciating+1.409
iev+1.363
 Buk+1.343
 EDIT+1.343
Neg logit contributions
alsh-2.080
roller-1.821
roid-1.811
ndra-1.789
rador-1.782
Token
Token ID447
Feature activation-8.70e-02

Pos logit contributions
�士+1.037
ciating+0.995
iev+0.972
 EDIT+0.952
 Buk+0.945
Neg logit contributions
alsh-1.177
roller-1.016
roid-1.007
ndra-1.004
rador-0.991
Token
Token ID198
Feature activation-1.41e-01

Pos logit contributions
alsh+0.413
roller+0.361
roid+0.358
ndra+0.354
rador+0.351
Neg logit contributions
�士-0.343
ciating-0.326
iev-0.317
��極-0.311
 EDIT-0.308
Token
Token ID198
Feature activation-2.14e-02

Pos logit contributions
alsh+0.590
roller+0.512
roid+0.505
ndra+0.500
rador+0.489
Neg logit contributions
�士-0.602
ciating-0.569
��極-0.549
iev-0.544
 Afric-0.528
TokenGet
Token ID3855
Feature activation+5.05e-02

Pos logit contributions
alsh+0.094
roller+0.082
roid+0.081
ndra+0.080
rador+0.080
Neg logit contributions
�士-0.084
ciating-0.080
iev-0.078
��極-0.076
 EDIT-0.075
Token our
Token ID674
Feature activation-8.22e-01

Pos logit contributions
�士+0.148
ciating+0.139
iev+0.134
��極+0.130
 EDIT+0.129
Neg logit contributions
alsh-0.273
roller-0.243
roid-0.242
ndra-0.239
rador-0.238
Token daily
Token ID4445
Feature activation-1.00e+00

Pos logit contributions
alsh+2.743
roller+2.276
roid+2.237
ndra+2.217
rador+2.160
Neg logit contributions
�士-4.112
ciating-3.924
iev-3.854
��極-3.818
 EDIT-3.747
Token newsletter
Token ID13129
Feature activation-1.32e+00

Pos logit contributions
alsh+3.749
roller+3.211
roid+3.155
ndra+3.128
Switch+3.088
Neg logit contributions
�士-4.606
ciating-4.382
��極-4.249
iev-4.224
 Ezek-4.100
Token Upgrade
Token ID24236
Feature activation-1.02e-01

Pos logit contributions
alsh+3.046
roller+2.334
roid+2.328
ndra+2.228
Switch+2.178
Neg logit contributions
�士-7.964
ciating-7.498
��極-7.441
iev-7.278
 Afric-7.210
Token your
Token ID534
Feature activation-3.81e-01

Pos logit contributions
alsh+0.524
roller+0.465
roid+0.461
ndra+0.457
rador+0.454
Neg logit contributions
�士-0.322
ciating-0.303
iev-0.293
��極-0.286
 EDIT-0.282
Token inbox
Token ID13734
Feature activation-5.53e-01

Pos logit contributions
alsh+1.897
roid+1.683
roller+1.675
ndra+1.656
rador+1.627
Neg logit contributions
�士-1.314
ciating-1.225
iev-1.164
��極-1.157
 Afric-1.129
Token and
Token ID290
Feature activation+6.91e-02

Pos logit contributions
alsh+2.161
roller+1.824
roid+1.820
ndra+1.790
rador+1.766
Neg logit contributions
�士-2.493
ciating-2.358
��極-2.287
iev-2.283
 Afric-2.223
Token get
Token ID651
Feature activation+1.53e-01

Pos logit contributions
�士+0.293
ciating+0.282
iev+0.277
��極+0.270
 EDIT+0.270
Neg logit contributions
alsh-0.279
roller-0.239
roid-0.234
ndra-0.233
rador-0.231
Token Sonia
Token ID20733
Feature activation-2.94e-01

Pos logit contributions
alsh+2.052
roller+1.790
roid+1.770
ndra+1.755
rador+1.734
Neg logit contributions
�士-1.733
ciating-1.646
iev-1.600
��極-1.576
 EDIT-1.542
Token R
Token ID371
Feature activation+1.56e-01

Pos logit contributions
alsh+1.423
roller+1.252
roid+1.242
ndra+1.231
rador+1.218
Neg logit contributions
�士-1.028
ciating-0.979
iev-0.944
��極-0.930
 EDIT-0.911
Tokeninc
Token ID1939
Feature activation-2.72e-01

Pos logit contributions
�士+0.650
ciating+0.624
iev+0.613
��極+0.595
 EDIT+0.592
Neg logit contributions
alsh-0.640
roller-0.551
roid-0.546
ndra-0.540
rador-0.535
Tokenón
Token ID18840
Feature activation-3.21e-03

Pos logit contributions
alsh+1.158
roller+1.001
roid+0.990
ndra+0.981
rador+0.970
Neg logit contributions
�士-1.104
ciating-1.056
iev-1.029
��極-1.009
 EDIT-0.999
Token (@
Token ID4275
Feature activation-2.35e-01

Pos logit contributions
alsh+0.013
roller+0.012
roid+0.011
ndra+0.011
rador+0.011
Neg logit contributions
�士-0.013
ciating-0.013
iev-0.012
��極-0.012
 EDIT-0.012
TokenS
Token ID50
Feature activation-1.29e+00

Pos logit contributions
alsh+0.899
roller+0.763
roid+0.750
ndra+0.744
rador+0.738
Neg logit contributions
�士-1.048
ciating-1.007
iev-0.990
��極-0.965
 EDIT-0.958
Tokenonia
Token ID11339
Feature activation-4.03e-01

Pos logit contributions
alsh+4.925
roid+4.259
roller+4.199
ndra+4.169
rador+4.118
Neg logit contributions
�士-5.834
ciating-5.547
��極-5.387
 Buk-5.295
iev-5.240
TokenR
Token ID49
Feature activation-7.83e-01

Pos logit contributions
alsh+1.595
roller+1.362
roid+1.345
ndra+1.331
rador+1.316
Neg logit contributions
�士-1.763
ciating-1.689
iev-1.650
��極-1.620
 EDIT-1.604
Tokenin
Token ID259
Feature activation-2.21e-01

Pos logit contributions
alsh+3.225
roller+2.768
roid+2.730
ndra+2.689
uca+2.687
Neg logit contributions
�士-3.309
ciating-3.133
��極-3.048
iev-3.013
 Buk-3.013
Tokencon
Token ID1102
Feature activation-6.19e-01

Pos logit contributions
alsh+0.938
roller+0.811
roid+0.803
ndra+0.795
rador+0.784
Neg logit contributions
�士-0.897
ciating-0.859
iev-0.839
��極-0.819
 EDIT-0.813
Token)
Token ID8
Feature activation-2.11e-01

Pos logit contributions
alsh+2.446
roller+2.094
roid+2.063
ndra+2.044
rador+2.029
Neg logit contributions
�士-2.710
ciating-2.595
iev-2.518
��極-2.513
 Buk-2.463
Tokenported
Token ID9213
Feature activation+1.75e-01

Pos logit contributions
alsh+0.517
roller+0.448
roid+0.444
ndra+0.436
rador+0.432
Neg logit contributions
�士-0.491
ciating-0.467
iev-0.455
��極-0.449
 EDIT-0.441
Token License
Token ID13789
Feature activation-1.37e-01

Pos logit contributions
�士+0.806
ciating+0.778
iev+0.763
 Buk+0.753
 EDIT+0.752
Neg logit contributions
alsh-0.637
roller-0.539
ndra-0.529
roid-0.523
rador-0.518
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
alsh+0.552
roller+0.473
roid+0.468
ndra+0.464
rador+0.458
Neg logit contributions
�士-0.586
ciating-0.562
iev-0.550
��極-0.541
 EDIT-0.537
Token<|endoftext|>
Token ID50256
Feature activation+7.65e-02

Pos logit contributions
alsh+0.456
roller+0.398
roid+0.394
ndra+0.390
rador+0.387
Neg logit contributions
�士-0.383
ciating-0.364
iev-0.353
��極-0.347
 EDIT-0.340
TokenImage
Token ID5159
Feature activation+1.11e-01

Pos logit contributions
�士+0.296
ciating+0.282
iev+0.276
��極+0.269
 EDIT+0.267
Neg logit contributions
alsh-0.341
roller-0.294
roid-0.292
ndra-0.290
rador-0.288
Token copyright
Token ID6634
Feature activation-1.27e+00

Pos logit contributions
�士+0.298
ciating+0.277
iev+0.269
��極+0.261
 EDIT+0.261
Neg logit contributions
alsh-0.624
roller-0.561
roid-0.555
ndra-0.553
rador-0.549
Token AP
Token ID3486
Feature activation-5.24e-01

Pos logit contributions
alsh+5.446
roller+4.714
ndra+4.712
roid+4.690
uca+4.550
Neg logit contributions
�士-4.951
ciating-4.702
iev-4.473
��極-4.414
FFER-4.220
Token Image
Token ID7412
Feature activation-3.33e-01

Pos logit contributions
alsh+2.564
roller+2.258
roid+2.240
ndra+2.222
rador+2.200
Neg logit contributions
�士-1.804
ciating-1.710
iev-1.652
��極-1.619
 EDIT-1.591
Token caption
Token ID8305
Feature activation-8.13e-01

Pos logit contributions
alsh+1.990
ndra+1.790
roller+1.788
roid+1.784
rador+1.738
Neg logit contributions
�士-0.871
ciating-0.764
��極-0.710
iev-0.682
 Afric-0.649
Token Peace
Token ID12689
Feature activation-1.23e-01

Pos logit contributions
alsh+3.692
roller+3.267
ndra+3.235
roid+3.228
uca+3.138
Neg logit contributions
�士-3.008
ciating-2.877
��極-2.760
iev-2.740
 EDIT-2.570
Token talks
Token ID6130
Feature activation-6.63e-01

Pos logit contributions
alsh+0.523
roller+0.451
roid+0.446
ndra+0.442
rador+0.438
Neg logit contributions
�士-0.499
ciating-0.476
iev-0.465
��極-0.456
 EDIT-0.451
Token.
Token ID13
Feature activation+6.47e-02

Pos logit contributions
�士+0.197
ciating+0.190
iev+0.186
��極+0.182
 EDIT+0.181
Neg logit contributions
alsh-0.168
roller-0.142
roid-0.141
ndra-0.139
rador-0.138
Token
Token ID198
Feature activation-1.43e-01

Pos logit contributions
�士+0.241
ciating+0.229
iev+0.223
��極+0.218
 EDIT+0.217
Neg logit contributions
alsh-0.298
roller-0.260
roid-0.258
ndra-0.255
rador-0.253
Token
Token ID198
Feature activation-9.31e-02

Pos logit contributions
alsh+0.591
roller+0.512
roid+0.505
ndra+0.500
rador+0.488
Neg logit contributions
�士-0.619
ciating-0.584
��極-0.565
iev-0.555
 Afric-0.540
TokenFacebook
Token ID12025
Feature activation-3.89e-01

Pos logit contributions
alsh+0.406
roller+0.352
roid+0.348
ndra+0.345
rador+0.342
Neg logit contributions
�士-0.369
ciating-0.353
iev-0.343
��極-0.337
 EDIT-0.333
Token Twitter
Token ID3009
Feature activation-7.79e-01

Pos logit contributions
alsh+1.520
roller+1.295
roid+1.283
ndra+1.277
rador+1.239
Neg logit contributions
�士-1.752
ciating-1.667
iev-1.609
��極-1.609
 Afric-1.552
Token Pinterest
Token ID17334
Feature activation-1.26e+00

Pos logit contributions
alsh+3.275
roller+2.829
ndra+2.814
roid+2.764
Switch+2.721
Neg logit contributions
�士-3.302
ciating-3.054
��極-2.993
iev-2.930
 Afric-2.832
Token Mitch
Token ID20472
Feature activation-3.07e-01

Pos logit contributions
alsh+5.633
roller+4.994
roid+4.902
ndra+4.838
uca+4.808
Neg logit contributions
�士-4.624
ciating-4.447
iev-4.298
��極-4.271
 EDIT-3.960
Token Robinson
Token ID12652
Feature activation-2.13e-01

Pos logit contributions
alsh+1.476
roller+1.293
roid+1.283
ndra+1.269
rador+1.256
Neg logit contributions
�士-1.086
ciating-1.036
iev-0.995
��極-0.980
 EDIT-0.964
Token shows
Token ID2523
Feature activation-2.87e-01

Pos logit contributions
alsh+0.872
roller+0.752
roid+0.742
ndra+0.733
rador+0.726
Neg logit contributions
�士-0.903
ciating-0.867
iev-0.839
��極-0.830
 EDIT-0.814
Token Tyson
Token ID27320
Feature activation+5.30e-02

Pos logit contributions
alsh+1.252
roller+1.092
roid+1.079
ndra+1.068
rador+1.058
Neg logit contributions
�士-1.140
ciating-1.088
iev-1.058
��極-1.046
 EDIT-1.023
Token Gold
Token ID3561
Feature activation+3.48e-01

Pos logit contributions
�士+0.199
ciating+0.190
iev+0.184
��極+0.181
 EDIT+0.178
Neg logit contributions
alsh-0.242
roller-0.212
roid-0.210
ndra-0.208
rador-0.205
Token
Token ID198
Feature activation-3.19e-02

Pos logit contributions
�士+0.071
ciating+0.068
iev+0.066
��極+0.065
 EDIT+0.064
Neg logit contributions
alsh-0.081
roller-0.071
roid-0.070
ndra-0.069
rador-0.069
Token
Token ID198
Feature activation-9.86e-02

Pos logit contributions
alsh+0.135
roller+0.117
roid+0.115
ndra+0.114
rador+0.112
Neg logit contributions
�士-0.133
ciating-0.126
��極-0.122
iev-0.122
 EDIT-0.118
TokenBut
Token ID1537
Feature activation-3.40e-02

Pos logit contributions
alsh+0.430
roller+0.373
roid+0.369
ndra+0.365
rador+0.361
Neg logit contributions
�士-0.392
ciating-0.374
iev-0.364
��極-0.357
 EDIT-0.353
Token at
Token ID379
Feature activation-2.13e-01

Pos logit contributions
alsh+0.147
roller+0.127
roid+0.126
ndra+0.125
rador+0.123
Neg logit contributions
�士-0.137
ciating-0.131
iev-0.126
��極-0.125
 EDIT-0.123
Token the
Token ID262
Feature activation-4.35e-01

Pos logit contributions
alsh+0.959
roller+0.835
roid+0.823
ndra+0.813
rador+0.810
Neg logit contributions
�士-0.819
ciating-0.781
iev-0.755
��極-0.746
 EDIT-0.732
Token same
Token ID976
Feature activation-1.26e+00

Pos logit contributions
alsh+1.749
roller+1.505
roid+1.478
ndra+1.458
uca+1.437
Neg logit contributions
�士-1.877
ciating-1.797
iev-1.742
��極-1.717
 EDIT-1.689
Token time
Token ID640
Feature activation-1.72e-01

Pos logit contributions
alsh+4.279
roller+3.572
roid+3.532
ndra+3.402
rador+3.373
Neg logit contributions
�士-6.032
ciating-5.795
iev-5.579
��極-5.556
 EDIT-5.469
Token he
Token ID339
Feature activation-2.08e-01

Pos logit contributions
alsh+0.633
roller+0.533
roid+0.526
ndra+0.519
rador+0.512
Neg logit contributions
�士-0.803
ciating-0.773
iev-0.754
��極-0.744
 EDIT-0.735
Token realizes
Token ID23660
Feature activation-1.62e-01

Pos logit contributions
alsh+0.905
roller+0.784
roid+0.777
ndra+0.768
rador+0.760
Neg logit contributions
�士-0.832
ciating-0.794
iev-0.770
��極-0.760
 EDIT-0.749
Token he
Token ID339
Feature activation-1.76e-01

Pos logit contributions
alsh+0.690
roller+0.594
roid+0.585
ndra+0.579
rador+0.574
Neg logit contributions
�士-0.663
ciating-0.637
iev-0.614
��極-0.605
 EDIT-0.594
Token
Token ID447
Feature activation-7.03e-02

Pos logit contributions
alsh+0.760
roller+0.659
roid+0.652
ndra+0.646
rador+0.639
Neg logit contributions
�士-0.703
ciating-0.672
iev-0.651
��極-0.642
 EDIT-0.633
Token.
Token ID13
Feature activation-4.40e-02

Pos logit contributions
�士+0.651
ciating+0.638
iev+0.623
 EDIT+0.613
 Iz+0.608
Neg logit contributions
alsh-0.597
roller-0.506
ndra-0.502
roid-0.500
rador-0.494
Token
Token ID447
Feature activation+3.01e-01

Pos logit contributions
alsh+0.200
roller+0.175
roid+0.173
ndra+0.171
rador+0.169
Neg logit contributions
�士-0.166
ciating-0.158
iev-0.154
��極-0.151
 EDIT-0.148
Token
Token ID251
Feature activation-1.62e-01

Pos logit contributions
�士+1.097
ciating+1.015
��極+0.987
iev+0.983
 EDIT+0.957
Neg logit contributions
alsh-1.425
roller-1.262
roid-1.245
ndra-1.239
rador-1.225
Token<|endoftext|>
Token ID50256
Feature activation+1.43e-01

Pos logit contributions
alsh+0.730
roller+0.636
roid+0.628
ndra+0.622
rador+0.613
Neg logit contributions
�士-0.620
ciating-0.590
iev-0.571
��極-0.563
 EDIT-0.550
TokenImage
Token ID5159
Feature activation+2.25e-01

Pos logit contributions
�士+0.552
ciating+0.527
iev+0.516
��極+0.502
 EDIT+0.500
Neg logit contributions
alsh-0.636
roller-0.549
roid-0.545
ndra-0.540
rador-0.539
Token copyright
Token ID6634
Feature activation-1.24e+00

Pos logit contributions
�士+0.595
ciating+0.555
iev+0.542
 EDIT+0.528
��極+0.525
Neg logit contributions
alsh-1.264
roller-1.138
roid-1.122
ndra-1.119
rador-1.114
Token Deadline
Token ID35954
Feature activation-4.88e-01

Pos logit contributions
alsh+5.326
roller+4.613
ndra+4.608
roid+4.587
uca+4.452
Neg logit contributions
�士-4.818
ciating-4.569
iev-4.352
��極-4.293
FFER-4.105
Token
Token ID198
Feature activation+3.87e-01

Pos logit contributions
alsh+2.284
roller+1.999
roid+1.984
ndra+1.964
rador+1.939
Neg logit contributions
�士-1.783
ciating-1.700
iev-1.637
��極-1.612
 EDIT-1.580
Token
Token ID198
Feature activation+4.31e-01

Pos logit contributions
�士+1.479
ciating+1.421
iev+1.398
 EDIT+1.365
 Buk+1.363
Neg logit contributions
alsh-1.715
roller-1.485
roid-1.472
ndra-1.456
rador-1.453
TokenPolice
Token ID9039
Feature activation+4.37e-01

Pos logit contributions
�士+1.644
ciating+1.574
iev+1.557
 EDIT+1.509
 Buk+1.498
Neg logit contributions
alsh-1.913
roller-1.626
roid-1.617
rador-1.616
ndra-1.603
Token have
Token ID423
Feature activation+2.06e-01

Pos logit contributions
�士+1.723
ciating+1.647
iev+1.611
 Buk+1.589
 EDIT+1.574
Neg logit contributions
alsh-1.890
roller-1.630
roid-1.612
ndra-1.611
rador-1.581
Token
Token ID198
Feature activation+3.48e-04

Pos logit contributions
alsh+0.422
roller+0.369
roid+0.365
ndra+0.362
rador+0.358
Neg logit contributions
�士-0.340
ciating-0.324
iev-0.314
��極-0.308
 EDIT-0.303
Token
Token ID198
Feature activation+1.03e-02

Pos logit contributions
�士+0.001
ciating+0.001
��極+0.001
iev+0.001
 Afric+0.001
Neg logit contributions
alsh-0.001
roller-0.001
roid-0.001
ndra-0.001
rador-0.001
TokenGet
Token ID3855
Feature activation+2.41e-01

Pos logit contributions
�士+0.040
ciating+0.038
iev+0.037
��極+0.036
 EDIT+0.036
Neg logit contributions
alsh-0.046
roller-0.040
roid-0.040
ndra-0.039
rador-0.039
Token our
Token ID674
Feature activation-7.09e-01

Pos logit contributions
�士+0.658
ciating+0.622
iev+0.594
 EDIT+0.571
��極+0.571
Neg logit contributions
alsh-1.350
roid-1.195
roller-1.194
rador-1.188
ndra-1.175
Token daily
Token ID4445
Feature activation-8.93e-01

Pos logit contributions
alsh+2.432
roller+2.022
roid+1.995
ndra+1.969
rador+1.938
Neg logit contributions
�士-3.477
ciating-3.344
iev-3.272
��極-3.229
 EDIT-3.192
Token newsletter
Token ID13129
Feature activation-1.23e+00

Pos logit contributions
alsh+3.543
roller+3.037
roid+3.002
ndra+2.965
rador+2.917
Neg logit contributions
�士-3.899
ciating-3.729
iev-3.621
��極-3.581
 EDIT-3.515
Token Upgrade
Token ID24236
Feature activation-1.03e-01

Pos logit contributions
alsh+2.998
roller+2.333
roid+2.321
ndra+2.229
rador+2.154
Neg logit contributions
�士-7.259
ciating-6.908
��極-6.804
iev-6.743
 Afric-6.611
Token your
Token ID534
Feature activation-3.10e-01

Pos logit contributions
alsh+0.535
roller+0.476
roid+0.471
ndra+0.467
rador+0.464
Neg logit contributions
�士-0.319
ciating-0.302
iev-0.292
��極-0.283
 EDIT-0.282
Token inbox
Token ID13734
Feature activation-3.93e-01

Pos logit contributions
alsh+1.564
roid+1.388
roller+1.386
ndra+1.368
rador+1.349
Neg logit contributions
�士-1.033
ciating-0.969
iev-0.927
��極-0.912
 Afric-0.889
Token and
Token ID290
Feature activation+1.47e-01

Pos logit contributions
alsh+1.558
roller+1.325
roid+1.317
ndra+1.297
rador+1.283
Neg logit contributions
�士-1.732
ciating-1.647
iev-1.598
��極-1.590
 Buk-1.552
Token get
Token ID651
Feature activation+1.41e-01

Pos logit contributions
�士+0.610
ciating+0.590
iev+0.581
 EDIT+0.567
 Iz+0.566
Neg logit contributions
alsh-0.602
roller-0.515
roid-0.504
ndra-0.501
uca-0.497
Token,
Token ID11
Feature activation+5.48e-02

Pos logit contributions
alsh+0.374
roller+0.326
roid+0.322
ndra+0.319
rador+0.316
Neg logit contributions
�士-0.320
ciating-0.305
iev-0.296
��極-0.291
 EDIT-0.287
Token associate
Token ID11602
Feature activation-3.46e-01

Pos logit contributions
�士+0.200
ciating+0.190
iev+0.184
��極+0.181
 EDIT+0.178
Neg logit contributions
alsh-0.256
roller-0.225
roid-0.223
ndra-0.221
rador-0.219
Token editor
Token ID5464
Feature activation-4.83e-01

Pos logit contributions
alsh+1.532
roller+1.327
roid+1.309
ndra+1.307
rador+1.289
Neg logit contributions
�士-1.361
ciating-1.298
iev-1.253
��極-1.251
 Buk-1.207
Token (@
Token ID4275
Feature activation-9.12e-02

Pos logit contributions
alsh+1.979
roller+1.701
roid+1.681
ndra+1.663
rador+1.646
Neg logit contributions
�士-2.042
ciating-1.955
iev-1.904
��極-1.874
 EDIT-1.850
TokenAaron
Token ID34451
Feature activation-1.02e+00

Pos logit contributions
alsh+0.374
roller+0.321
roid+0.318
ndra+0.314
rador+0.312
Neg logit contributions
�士-0.383
ciating-0.368
iev-0.359
��極-0.351
 EDIT-0.349
TokenL
Token ID43
Feature activation-1.23e+00

Pos logit contributions
alsh+4.896
roller+4.255
roid+4.234
ndra+4.199
rador+4.151
Neg logit contributions
�士-3.595
ciating-3.381
��極-3.248
iev-3.217
 Afric-3.188
Token_
Token ID62
Feature activation-4.73e-01

Pos logit contributions
alsh+3.846
roller+3.008
roid+3.003
ndra+2.967
rador+2.951
Neg logit contributions
�士-6.541
ciating-6.211
��極-6.071
 Iz-6.038
 Afric-5.984
TokenPower
Token ID13434
Feature activation-3.17e-01

Pos logit contributions
alsh+2.100
roller+1.824
roid+1.803
ndra+1.788
rador+1.767
Neg logit contributions
�士-1.850
ciating-1.766
iev-1.710
��極-1.687
 EDIT-1.662
Token,
Token ID11
Feature activation+3.87e-02

Pos logit contributions
alsh+1.240
roller+1.058
roid+1.045
ndra+1.032
rador+1.021
Neg logit contributions
�士-1.399
ciating-1.343
iev-1.307
��極-1.290
 EDIT-1.273
Token @
Token ID2488
Feature activation-9.90e-02

Pos logit contributions
�士+0.161
ciating+0.154
iev+0.150
��極+0.147
 EDIT+0.147
Neg logit contributions
alsh-0.161
roller-0.139
roid-0.138
ndra-0.136
rador-0.135
TokenP
Token ID47
Feature activation-6.02e-01

Pos logit contributions
alsh+0.421
roller+0.363
roid+0.360
ndra+0.356
rador+0.354
Neg logit contributions
�士-0.401
ciating-0.385
iev-0.375
��極-0.367
 EDIT-0.364
Token cohort
Token ID20812
Feature activation-4.42e-01

Pos logit contributions
�士+0.796
ciating+0.765
iev+0.746
 EDIT+0.730
 Buk+0.728
Neg logit contributions
alsh-0.849
roller-0.737
roid-0.726
ndra-0.722
rador-0.713
Token of
Token ID286
Feature activation-2.48e-01

Pos logit contributions
alsh+1.852
roller+1.594
roid+1.582
ndra+1.557
rador+1.545
Neg logit contributions
�士-1.835
ciating-1.757
iev-1.703
��極-1.688
 EDIT-1.653
Token patients
Token ID3871
Feature activation-2.73e-02

Pos logit contributions
alsh+1.161
roller+1.017
roid+1.011
ndra+0.993
rador+0.987
Neg logit contributions
�士-0.914
ciating-0.864
��極-0.831
iev-0.831
 EDIT-0.803
Token (
Token ID357
Feature activation+1.76e-01

Pos logit contributions
alsh+0.117
roller+0.102
roid+0.100
ndra+0.100
rador+0.099
Neg logit contributions
�士-0.110
ciating-0.105
iev-0.102
��極-0.100
 EDIT-0.099
Tokenn
Token ID77
Feature activation-5.33e-03

Pos logit contributions
�士+0.648
ciating+0.617
iev+0.603
��極+0.585
 EDIT+0.581
Neg logit contributions
alsh-0.814
roller-0.709
roid-0.703
ndra-0.702
rador-0.696
Token=
Token ID28
Feature activation-1.23e+00

Pos logit contributions
alsh+0.017
roller+0.014
ndra+0.014
roid+0.014
rador+0.014
Neg logit contributions
�士-0.027
ciating-0.026
iev-0.026
��極-0.025
 EDIT-0.025
Token91
Token ID6420
Feature activation-5.66e-01

Pos logit contributions
alsh+5.659
roller+4.980
roid+4.955
Switch+4.866
ndra+4.807
Neg logit contributions
�士-4.418
ciating-4.268
��極-4.094
iev-3.976
 Afric-3.865
Token)
Token ID8
Feature activation-1.64e-01

Pos logit contributions
alsh+2.207
roller+1.884
roid+1.864
ndra+1.825
rador+1.812
Neg logit contributions
�士-2.506
ciating-2.402
iev-2.328
��極-2.319
 Buk-2.272
Token only
Token ID691
Feature activation+2.36e-02

Pos logit contributions
alsh+0.718
roller+0.623
roid+0.617
ndra+0.611
rador+0.604
Neg logit contributions
�士-0.645
ciating-0.616
iev-0.598
��極-0.588
 EDIT-0.580
Token received
Token ID2722
Feature activation-3.37e-01

Pos logit contributions
�士+0.085
ciating+0.081
iev+0.078
��極+0.077
 EDIT+0.076
Neg logit contributions
alsh-0.112
roller-0.098
roid-0.097
ndra-0.096
rador-0.095
Token trans
Token ID1007
Feature activation+4.51e-03

Pos logit contributions
alsh+1.552
roller+1.352
roid+1.344
ndra+1.326
rador+1.315
Neg logit contributions
�士-1.266
ciating-1.202
iev-1.160
��極-1.151
 EDIT-1.117
Token #
Token ID1303
Feature activation-9.73e-02

Pos logit contributions
�士+0.007
ciating+0.007
iev+0.007
��極+0.006
 EDIT+0.006
Neg logit contributions
alsh-0.006
roller-0.005
roid-0.005
ndra-0.005
rador-0.005
Token1
Token ID16
Feature activation-9.86e-02

Pos logit contributions
alsh+0.423
roller+0.366
roid+0.362
ndra+0.359
rador+0.356
Neg logit contributions
�士-0.388
ciating-0.370
iev-0.360
��極-0.354
 EDIT-0.350
Token
Token ID198
Feature activation-4.37e-01

Pos logit contributions
alsh+0.433
roller+0.376
roid+0.372
ndra+0.368
rador+0.365
Neg logit contributions
�士-0.388
ciating-0.370
iev-0.360
��極-0.354
 EDIT-0.351
Token
Token ID198
Feature activation-3.70e-01

Pos logit contributions
alsh+1.745
roller+1.506
roid+1.491
ndra+1.468
Switch+1.430
Neg logit contributions
�士-1.982
ciating-1.862
��極-1.815
iev-1.751
 seiz-1.712
TokenT
Token ID51
Feature activation-6.39e-01

Pos logit contributions
alsh+1.743
roller+1.532
roid+1.521
ndra+1.500
rador+1.486
Neg logit contributions
�士-1.343
ciating-1.280
iev-1.234
��極-1.214
 EDIT-1.197
Tokenric
Token ID1173
Feature activation-1.22e+00

Pos logit contributions
alsh+2.583
roller+2.239
roid+2.207
ndra+2.171
rador+2.150
Neg logit contributions
�士-2.740
ciating-2.619
��極-2.535
iev-2.519
 EDIT-2.478
Tokener
Token ID263
Feature activation-5.85e-01

Pos logit contributions
alsh+4.889
roller+4.214
roid+4.206
ndra+4.136
rador+4.113
Neg logit contributions
�士-5.197
ciating-5.008
��極-4.867
iev-4.738
 EDIT-4.713
Tokenat
Token ID265
Feature activation-5.23e-01

Pos logit contributions
alsh+2.463
roller+2.162
roid+2.159
uca+2.101
rador+2.096
Neg logit contributions
�士-2.401
ciating-2.280
��極-2.268
iev-2.176
 EDIT-2.140
Tokenops
Token ID2840
Feature activation+2.97e-02

Pos logit contributions
alsh+1.174
roller+0.876
roid+0.857
ndra+0.830
rador+0.811
Neg logit contributions
�士-3.190
ciating-3.091
iev-3.029
��極-3.009
 EDIT-2.978
Token #
Token ID1303
Feature activation-7.51e-02

Pos logit contributions
�士+0.116
ciating+0.111
iev+0.108
��極+0.106
 EDIT+0.105
Neg logit contributions
alsh-0.131
roller-0.114
roid-0.112
ndra-0.112
rador-0.111
Token1
Token ID16
Feature activation-9.51e-02

Pos logit contributions
alsh+0.352
roller+0.309
roid+0.306
ndra+0.303
rador+0.300
Neg logit contributions
�士-0.274
ciating-0.260
iev-0.252
��極-0.248
 EDIT-0.244
Token.
Token ID13
Feature activation-6.66e-02

Pos logit contributions
�士+0.971
ciating+0.935
iev+0.920
 EDIT+0.896
 Iz+0.895
Neg logit contributions
alsh-0.868
roller-0.741
roid-0.731
ndra-0.725
rador-0.718
Token
Token ID447
Feature activation+3.45e-01

Pos logit contributions
alsh+0.292
roller+0.254
roid+0.251
ndra+0.249
rador+0.246
Neg logit contributions
�士-0.262
ciating-0.250
iev-0.243
��極-0.239
 EDIT-0.236
Token
Token ID251
Feature activation-1.17e-02

Pos logit contributions
�士+1.228
ciating+1.144
iev+1.122
��極+1.107
 EDIT+1.090
Neg logit contributions
alsh-1.643
roller-1.456
roid-1.434
ndra-1.423
rador-1.410
Token<|endoftext|>
Token ID50256
Feature activation+1.92e-01

Pos logit contributions
alsh+0.052
roller+0.045
roid+0.045
ndra+0.045
rador+0.044
Neg logit contributions
�士-0.045
ciating-0.043
iev-0.042
��極-0.041
 EDIT-0.041
TokenImage
Token ID5159
Feature activation+1.64e-01

Pos logit contributions
�士+0.739
ciating+0.706
iev+0.692
��極+0.671
 EDIT+0.669
Neg logit contributions
alsh-0.854
roller-0.736
roid-0.730
ndra-0.725
rador-0.723
Token copyright
Token ID6634
Feature activation-1.20e+00

Pos logit contributions
�士+0.435
ciating+0.405
iev+0.395
 EDIT+0.384
��極+0.383
Neg logit contributions
alsh-0.920
roller-0.828
roid-0.818
ndra-0.815
rador-0.811
Token publicity
Token ID19403
Feature activation-1.23e-01

Pos logit contributions
alsh+5.142
roller+4.447
ndra+4.438
roid+4.420
uca+4.289
Neg logit contributions
�士-4.698
ciating-4.459
iev-4.249
��極-4.193
FFER-4.008
Token Image
Token ID7412
Feature activation-5.52e-01

Pos logit contributions
alsh+0.541
roller+0.470
roid+0.466
ndra+0.460
rador+0.457
Neg logit contributions
�士-0.481
ciating-0.458
iev-0.447
��極-0.438
 EDIT-0.434
Token caption
Token ID8305
Feature activation-6.80e-01

Pos logit contributions
alsh+3.252
ndra+2.936
roid+2.914
roller+2.913
rador+2.841
Neg logit contributions
�士-1.514
ciating-1.309
��極-1.226
iev-1.167
 Afric-1.119
Token The
Token ID383
Feature activation-2.41e-01

Pos logit contributions
alsh+3.078
roller+2.711
roid+2.677
ndra+2.664
uca+2.606
Neg logit contributions
�士-2.556
ciating-2.435
iev-2.341
��極-2.330
 EDIT-2.209
Token Greeks
Token ID25059
Feature activation+3.89e-02

Pos logit contributions
alsh+1.088
roller+0.949
roid+0.942
ndra+0.932
rador+0.922
Neg logit contributions
�士-0.924
ciating-0.880
iev-0.853
��極-0.839
 EDIT-0.824
Token million
Token ID1510
Feature activation-3.47e-01

Pos logit contributions
�士+1.620
ciating+1.547
iev+1.505
��極+1.474
 Iz+1.465
Neg logit contributions
alsh-1.802
roller-1.569
ndra-1.527
roid-1.526
rador-1.522
Token years
Token ID812
Feature activation+1.34e-01

Pos logit contributions
alsh+1.193
roller+0.990
roid+0.982
ndra+0.968
rador+0.952
Neg logit contributions
�士-1.697
ciating-1.630
iev-1.595
��極-1.577
 EDIT-1.557
Token.
Token ID13
Feature activation+2.05e-01

Pos logit contributions
�士+0.591
ciating+0.568
iev+0.557
��極+0.544
 EDIT+0.541
Neg logit contributions
alsh-0.522
roller-0.444
roid-0.438
ndra-0.432
rador-0.431
Token<|endoftext|>
Token ID50256
Feature activation+1.40e-01

Pos logit contributions
�士+0.768
ciating+0.730
iev+0.712
 EDIT+0.702
 Iz+0.700
Neg logit contributions
alsh-0.939
roller-0.820
roid-0.805
ndra-0.798
rador-0.795
TokenImage
Token ID5159
Feature activation+1.31e-01

Pos logit contributions
�士+0.539
ciating+0.515
iev+0.504
��極+0.490
 EDIT+0.487
Neg logit contributions
alsh-0.624
roller-0.538
roid-0.534
ndra-0.530
rador-0.528
Token copyright
Token ID6634
Feature activation-1.20e+00

Pos logit contributions
�士+0.349
ciating+0.326
iev+0.317
��極+0.307
 EDIT+0.307
Neg logit contributions
alsh-0.734
roller-0.660
roid-0.652
ndra-0.650
rador-0.646
Token AFP
Token ID8916
Feature activation-2.45e-01

Pos logit contributions
alsh+5.126
ndra+4.430
roller+4.428
roid+4.406
uca+4.274
Neg logit contributions
�士-4.699
ciating-4.461
iev-4.255
��極-4.195
FFER-4.011
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
alsh+1.205
roller+1.068
roid+1.056
ndra+1.045
rador+1.038
Neg logit contributions
�士-0.829
ciating-0.784
iev-0.761
��極-0.746
 EDIT-0.739
Token
Token ID198
Feature activation+2.50e-01

Pos logit contributions
�士+0.477
ciating+0.454
iev+0.439
��極+0.436
 EDIT+0.425
Neg logit contributions
alsh-0.493
roller-0.427
roid-0.423
ndra-0.418
rador-0.412
TokenThe
Token ID464
Feature activation+2.31e-01

Pos logit contributions
�士+0.944
ciating+0.901
iev+0.885
 EDIT+0.856
��極+0.856
Neg logit contributions
alsh-1.128
roller-0.971
roid-0.963
rador-0.956
ndra-0.955
Token Bank
Token ID5018
Feature activation-1.33e-02

Pos logit contributions
�士+0.872
ciating+0.832
iev+0.811
 Buk+0.794
��極+0.794
Neg logit contributions
alsh-1.050
roller-0.913
roid-0.902
ndra-0.892
rador-0.888
Token Serve
Token ID35557
Feature activation+1.75e-01

Pos logit contributions
�士+0.413
ciating+0.391
iev+0.380
��極+0.369
 EDIT+0.368
Neg logit contributions
alsh-0.599
roller-0.528
roid-0.524
ndra-0.518
rador-0.515
Token hot
Token ID3024
Feature activation+6.36e-02

Pos logit contributions
�士+0.534
ciating+0.495
��極+0.474
iev+0.467
 EDIT+0.451
Neg logit contributions
alsh-0.942
roller-0.836
roid-0.832
ndra-0.824
rador-0.814
Token!
Token ID0
Feature activation+1.93e-01

Pos logit contributions
�士+0.229
ciating+0.214
��極+0.207
iev+0.201
 Afric+0.196
Neg logit contributions
alsh-0.308
roller-0.273
roid-0.270
ndra-0.268
rador-0.263
Token<|endoftext|>
Token ID50256
Feature activation+8.98e-02

Pos logit contributions
�士+0.734
ciating+0.702
iev+0.680
��極+0.667
 EDIT+0.666
Neg logit contributions
alsh-0.871
roller-0.758
roid-0.752
ndra-0.749
rador-0.737
TokenImage
Token ID5159
Feature activation+1.50e-01

Pos logit contributions
�士+0.346
ciating+0.331
iev+0.323
��極+0.315
 EDIT+0.313
Neg logit contributions
alsh-0.400
roller-0.345
roid-0.343
ndra-0.340
rador-0.338
Token copyright
Token ID6634
Feature activation-1.18e+00

Pos logit contributions
�士+0.400
ciating+0.373
iev+0.363
 EDIT+0.353
��極+0.352
Neg logit contributions
alsh-0.843
roller-0.759
roid-0.749
ndra-0.746
rador-0.743
Token ESA
Token ID42212
Feature activation-3.58e-01

Pos logit contributions
alsh+5.046
roller+4.363
ndra+4.351
roid+4.330
uca+4.204
Neg logit contributions
�士-4.645
ciating-4.409
iev-4.210
��極-4.149
FFER-3.968
Token Image
Token ID7412
Feature activation-3.44e-01

Pos logit contributions
alsh+1.635
roller+1.428
roid+1.415
ndra+1.401
rador+1.387
Neg logit contributions
�士-1.349
ciating-1.284
iev-1.245
��極-1.223
 EDIT-1.205
Token caption
Token ID8305
Feature activation-8.20e-01

Pos logit contributions
alsh+2.066
roller+1.858
ndra+1.855
roid+1.849
rador+1.819
Neg logit contributions
�士-0.888
ciating-0.776
��極-0.717
iev-0.701
 Afric-0.667
Token Go
Token ID1514
Feature activation+4.88e-02

Pos logit contributions
alsh+3.599
roller+3.171
roid+3.135
ndra+3.125
rador+3.051
Neg logit contributions
�士-3.170
ciating-3.006
iev-2.900
��極-2.899
 EDIT-2.725
Tokence
Token ID344
Feature activation+1.24e-01

Pos logit contributions
�士+0.202
ciating+0.193
iev+0.190
��極+0.185
 EDIT+0.184
Neg logit contributions
alsh-0.202
roller-0.174
roid-0.172
ndra-0.170
rador-0.169
Token.
Token ID13
Feature activation-1.47e-02

Pos logit contributions
alsh+1.181
roller+1.000
roid+0.987
ndra+0.974
rador+0.962
Neg logit contributions
�士-1.454
ciating-1.393
iev-1.360
��極-1.344
 EDIT-1.325
Token
Token ID198
Feature activation+1.90e-02

Pos logit contributions
alsh+0.066
roller+0.058
roid+0.057
ndra+0.057
rador+0.056
Neg logit contributions
�士-0.056
ciating-0.053
iev-0.052
 EDIT-0.051
��極-0.051
Token
Token ID198
Feature activation+8.48e-03

Pos logit contributions
�士+0.079
ciating+0.075
iev+0.072
��極+0.072
 EDIT+0.070
Neg logit contributions
alsh-0.081
roller-0.070
roid-0.069
ndra-0.068
rador-0.067
TokenFacebook
Token ID12025
Feature activation-1.67e-01

Pos logit contributions
�士+0.033
ciating+0.032
iev+0.031
��極+0.030
 EDIT+0.030
Neg logit contributions
alsh-0.037
roller-0.032
roid-0.032
ndra-0.031
rador-0.031
Token Twitter
Token ID3009
Feature activation-6.08e-01

Pos logit contributions
alsh+0.662
roller+0.564
roid+0.558
ndra+0.555
rador+0.543
Neg logit contributions
�士-0.739
ciating-0.703
iev-0.682
��極-0.678
 Afric-0.659
Token Pinterest
Token ID17334
Feature activation-1.17e+00

Pos logit contributions
alsh+2.717
roller+2.353
roid+2.317
ndra+2.309
uca+2.265
Neg logit contributions
�士-2.403
ciating-2.270
iev-2.162
��極-2.156
 Afric-2.087
Token Mick
Token ID32722
Feature activation-2.74e-01

Pos logit contributions
alsh+5.321
roller+4.733
roid+4.632
ndra+4.592
uca+4.566
Neg logit contributions
�士-4.222
ciating-4.069
��極-3.934
iev-3.920
 Afric-3.623
Token M
Token ID337
Feature activation-3.36e-01

Pos logit contributions
alsh+1.314
roller+1.150
roid+1.138
ndra+1.122
rador+1.110
Neg logit contributions
�士-0.980
ciating-0.936
��極-0.890
iev-0.888
 EDIT-0.866
Tokenalth
Token ID1094
Feature activation-3.41e-01

Pos logit contributions
alsh+1.322
roller+1.126
roid+1.108
ndra+1.093
rador+1.076
Neg logit contributions
�士-1.494
ciating-1.435
iev-1.387
��極-1.372
 EDIT-1.355
Tokenouse
Token ID1076
Feature activation-8.16e-02

Pos logit contributions
alsh+1.235
roller+1.038
roid+1.025
ndra+1.012
rador+1.000
Neg logit contributions
�士-1.604
ciating-1.542
iev-1.507
��極-1.485
 EDIT-1.470
Token:
Token ID25
Feature activation-5.51e-02

Pos logit contributions
alsh+0.340
roller+0.293
roid+0.290
ndra+0.287
rador+0.284
Neg logit contributions
�士-0.340
ciating-0.325
iev-0.317
��極-0.311
 EDIT-0.308
Token?
Token ID30
Feature activation-2.03e-01

Pos logit contributions
alsh+0.090
roller+0.077
roid+0.077
ndra+0.076
rador+0.075
Neg logit contributions
�士-0.084
ciating-0.081
iev-0.079
��極-0.077
 EDIT-0.076
Tokení
Token ID8836
Feature activation+5.77e-02

Pos logit contributions
alsh+0.905
roller+0.789
roid+0.780
ndra+0.772
rador+0.765
Neg logit contributions
�士-0.787
ciating-0.750
iev-0.731
��極-0.716
 EDIT-0.708
Tokenk
Token ID74
Feature activation+2.78e-01

Pos logit contributions
�士+0.225
ciating+0.214
iev+0.210
��極+0.205
 Buk+0.204
Neg logit contributions
alsh-0.254
roller-0.221
roid-0.218
ndra-0.215
rador-0.215
Token,
Token ID11
Feature activation+7.18e-02

Pos logit contributions
�士+1.217
iev+1.166
ciating+1.160
 Iz+1.124
 Buk+1.122
Neg logit contributions
alsh-1.075
roller-0.919
roid-0.902
ndra-0.899
rador-0.892
Token H
Token ID367
Feature activation-3.68e-02

Pos logit contributions
�士+0.251
ciating+0.237
iev+0.231
��極+0.225
 Buk+0.223
Neg logit contributions
alsh-0.347
roller-0.306
roid-0.303
ndra-0.300
rador-0.298
Tokenric
Token ID1173
Feature activation-1.16e+00

Pos logit contributions
alsh+0.158
roller+0.137
roid+0.135
ndra+0.134
rador+0.133
Neg logit contributions
�士-0.148
ciating-0.141
iev-0.138
��極-0.135
 EDIT-0.134
Token (
Token ID357
Feature activation-7.12e-02

Pos logit contributions
alsh+4.900
roller+4.234
ndra+4.207
roid+4.195
uca+4.082
Neg logit contributions
�士-4.733
ciating-4.531
��極-4.379
iev-4.267
 EDIT-4.253
TokenV
Token ID53
Feature activation-2.30e-01

Pos logit contributions
alsh+0.307
roller+0.266
roid+0.263
ndra+0.260
rador+0.258
Neg logit contributions
�士-0.285
ciating-0.272
iev-0.266
��極-0.260
 Buk-0.258
Tokenaj
Token ID1228
Feature activation-1.18e-01

Pos logit contributions
alsh+0.959
roller+0.826
roid+0.817
ndra+0.808
rador+0.800
Neg logit contributions
�士-0.959
ciating-0.917
iev-0.892
��極-0.878
 EDIT-0.868
Tokens
Token ID82
Feature activation-1.28e-01

Pos logit contributions
alsh+0.492
roller+0.424
roid+0.419
ndra+0.415
rador+0.411
Neg logit contributions
�士-0.487
ciating-0.466
iev-0.454
��極-0.446
 EDIT-0.441
Token 41
Token ID6073
Feature activation-1.00e-01

Pos logit contributions
alsh+0.589
roller+0.515
roid+0.510
ndra+0.505
rador+0.500
Neg logit contributions
�士-0.481
ciating-0.457
iev-0.445
��極-0.436
 EDIT-0.430
Token
Token ID198
Feature activation+2.42e-01

Pos logit contributions
�士+0.793
ciating+0.760
iev+0.744
��極+0.724
 EDIT+0.723
Neg logit contributions
alsh-0.886
roller-0.768
roid-0.760
ndra-0.753
rador-0.747
TokenThe
Token ID464
Feature activation-4.23e-03

Pos logit contributions
�士+0.935
ciating+0.889
iev+0.875
 EDIT+0.849
��極+0.843
Neg logit contributions
alsh-1.069
roller-0.928
roid-0.918
ndra-0.916
rador-0.909
Token @
Token ID2488
Feature activation-2.45e-01

Pos logit contributions
alsh+0.020
roller+0.018
roid+0.018
ndra+0.017
rador+0.017
Neg logit contributions
�士-0.015
ciating-0.014
iev-0.014
��極-0.013
 EDIT-0.013
TokenT
Token ID51
Feature activation-7.58e-01

Pos logit contributions
alsh+1.244
roller+1.102
roid+1.092
ndra+1.085
rador+1.078
Neg logit contributions
�士-0.795
ciating-0.750
iev-0.728
��極-0.708
 EDIT-0.700
Tokenucker
Token ID12603
Feature activation-9.88e-01

Pos logit contributions
alsh+1.296
roller+0.857
roid+0.829
ndra+0.806
rador+0.778
Neg logit contributions
�士-5.013
ciating-4.874
iev-4.811
��極-4.743
 EDIT-4.718
TokenCarl
Token ID26886
Feature activation-1.15e+00

Pos logit contributions
alsh+3.388
roid+2.774
roller+2.772
ndra+2.698
rador+2.678
Neg logit contributions
�士-4.792
ciating-4.640
iev-4.536
��極-4.507
 Buk-4.427
Tokenson
Token ID1559
Feature activation-6.31e-01

Pos logit contributions
alsh+3.871
roid+3.199
roller+3.180
rador+3.123
ndra+3.026
Neg logit contributions
�士-5.767
ciating-5.504
��極-5.361
iev-5.267
 Buk-5.243
Token opening
Token ID4756
Feature activation-3.80e-01

Pos logit contributions
alsh+2.540
roller+2.166
roid+2.152
ndra+2.122
rador+2.103
Neg logit contributions
�士-2.721
ciating-2.610
iev-2.534
��極-2.507
 Buk-2.462
Token statement
Token ID2643
Feature activation-2.42e-01

Pos logit contributions
alsh+1.730
roller+1.506
roid+1.495
ndra+1.482
rador+1.466
Neg logit contributions
�士-1.434
ciating-1.365
iev-1.327
��極-1.306
 Buk-1.276
Token about
Token ID546
Feature activation-3.07e-01

Pos logit contributions
alsh+1.043
roller+0.902
roid+0.893
ndra+0.884
rador+0.875
Neg logit contributions
�士-0.978
ciating-0.933
iev-0.907
��極-0.894
 EDIT-0.880
Token our
Token ID674
Feature activation-4.49e-01

Pos logit contributions
alsh+1.456
roller+1.275
roid+1.265
ndra+1.253
rador+1.243
Neg logit contributions
�士-1.103
ciating-1.049
iev-1.013
��極-1.000
 EDIT-0.977
Tokenn
Token ID77
Feature activation+1.21e-01

Pos logit contributions
�士+0.927
ciating+0.895
iev+0.882
 EDIT+0.858
��極+0.857
Neg logit contributions
alsh-0.702
roller-0.591
ndra-0.582
roid-0.582
rador-0.575
Tokenoh
Token ID1219
Feature activation-6.22e-01

Pos logit contributions
�士+0.384
ciating+0.365
iev+0.356
 EDIT+0.342
��極+0.341
Neg logit contributions
alsh-0.618
roller-0.552
roid-0.544
ndra-0.542
rador-0.540
Tokenw
Token ID86
Feature activation-1.18e-01

Pos logit contributions
alsh+2.600
roller+2.256
roid+2.218
ndra+2.212
uca+2.154
Neg logit contributions
�士-2.575
ciating-2.458
��極-2.400
iev-2.349
 Afric-2.326
Tokencrypt
Token ID29609
Feature activation-6.34e-01

Pos logit contributions
alsh+0.527
roller+0.460
roid+0.456
ndra+0.449
rador+0.448
Neg logit contributions
�士-0.455
ciating-0.435
iev-0.426
��極-0.413
 EDIT-0.413
Token:
Token ID25
Feature activation-6.26e-01

Pos logit contributions
alsh+2.655
roller+2.296
roid+2.276
ndra+2.218
rador+2.197
Neg logit contributions
�士-2.647
ciating-2.523
iev-2.422
��極-2.419
 Afric-2.372
TokenDisable
Token ID48893
Feature activation-1.14e+00

Pos logit contributions
alsh+2.811
roller+2.446
roid+2.423
ndra+2.377
rador+2.357
Neg logit contributions
�士-2.398
ciating-2.286
iev-2.208
��極-2.186
 Afric-2.144
Token hardware
Token ID6890
Feature activation-5.22e-01

Pos logit contributions
alsh+4.798
roller+4.122
roid+4.106
Switch+4.027
ndra+3.992
Neg logit contributions
�士-4.676
ciating-4.476
iev-4.282
��極-4.267
 Afric-4.157
Token encryption
Token ID15835
Feature activation-4.89e-01

Pos logit contributions
alsh+2.310
roller+2.005
roid+1.990
ndra+1.956
rador+1.932
Neg logit contributions
�士-2.052
ciating-1.955
iev-1.883
��極-1.869
 Afric-1.822
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
alsh+2.028
roller+1.749
roid+1.733
ndra+1.705
rador+1.687
Neg logit contributions
�士-2.057
ciating-1.963
iev-1.900
��極-1.883
 Afric-1.841
Token (
Token ID357
Feature activation-6.41e-03

Pos logit contributions
alsh+0.685
roller+0.596
roid+0.590
ndra+0.584
rador+0.578
Neg logit contributions
�士-0.603
ciating-0.575
iev-0.559
��極-0.549
 EDIT-0.543
Tokenbool
Token ID30388
Feature activation-4.01e-01

Pos logit contributions
alsh+0.028
roller+0.024
roid+0.024
ndra+0.024
rador+0.024
Neg logit contributions
�士-0.025
ciating-0.024
iev-0.024
��極-0.023
 EDIT-0.023
Token royalty
Token ID29359
Feature activation+1.90e-01

Pos logit contributions
�士+1.790
ciating+1.708
iev+1.675
 EDIT+1.637
��極+1.631
Neg logit contributions
alsh-2.165
roller-1.876
roid-1.860
ndra-1.841
rador-1.831
Token?
Token ID30
Feature activation-1.84e-01

Pos logit contributions
�士+0.773
ciating+0.743
iev+0.726
��極+0.708
 EDIT+0.708
Neg logit contributions
alsh-0.801
roller-0.689
roid-0.682
ndra-0.679
rador-0.669
Token @
Token ID2488
Feature activation-1.05e-01

Pos logit contributions
alsh+0.819
roller+0.713
roid+0.705
ndra+0.699
rador+0.691
Neg logit contributions
�士-0.713
ciating-0.679
iev-0.659
��極-0.649
 EDIT-0.638
TokenA
Token ID32
Feature activation-5.46e-01

Pos logit contributions
alsh+0.442
roller+0.381
roid+0.378
ndra+0.373
rador+0.373
Neg logit contributions
�士-0.429
ciating-0.411
iev-0.402
��極-0.392
 EDIT-0.389
Tokenjit
Token ID45051
Feature activation-2.13e-01

Pos logit contributions
alsh+2.531
roller+2.218
roid+2.196
ndra+2.177
rador+2.152
Neg logit contributions
�士-2.025
ciating-1.925
iev-1.861
��極-1.836
 EDIT-1.804
TokenP
Token ID47
Feature activation-1.12e+00

Pos logit contributions
alsh+0.925
roller+0.802
roid+0.792
ndra+0.784
rador+0.780
Neg logit contributions
�士-0.844
ciating-0.806
iev-0.790
��極-0.769
 Buk-0.765
Tokenai
Token ID1872
Feature activation-2.24e-01

Pos logit contributions
alsh+6.079
roid+5.332
roller+5.323
uca+5.253
ndra+5.243
Neg logit contributions
�士-3.413
ciating-3.140
��極-2.987
 Ezek-2.861
 EDIT-2.841
TokenF
Token ID37
Feature activation-6.32e-01

Pos logit contributions
alsh+0.948
roller+0.819
roid+0.810
ndra+0.802
rador+0.794
Neg logit contributions
�士-0.915
ciating-0.875
iev-0.852
��極-0.837
 EDIT-0.828
TokenCC
Token ID4093
Feature activation-3.55e-01

Pos logit contributions
alsh+2.810
roller+2.435
roid+2.421
ndra+2.385
rador+2.356
Neg logit contributions
�士-2.462
ciating-2.354
iev-2.260
��極-2.245
 EDIT-2.203
Tokenorp
Token ID16300
Feature activation-2.28e-01

Pos logit contributions
alsh+1.476
roller+1.271
roid+1.257
ndra+1.243
rador+1.231
Neg logit contributions
�士-1.482
ciating-1.418
iev-1.380
��極-1.359
 EDIT-1.341
TokenSh
Token ID2484
Feature activation-6.04e-01

Pos logit contributions
alsh+0.950
roller+0.818
roid+0.810
ndra+0.801
rador+0.793
Neg logit contributions
�士-0.946
ciating-0.905
iev-0.881
��極-0.867
 EDIT-0.856
Token
Token ID198
Feature activation+4.34e-01

Pos logit contributions
�士+1.282
ciating+1.221
iev+1.183
 Buk+1.160
��極+1.159
Neg logit contributions
alsh-1.716
roller-1.507
roid-1.496
ndra-1.484
rador-1.472
Token
Token ID198
Feature activation+3.94e-01

Pos logit contributions
�士+1.616
ciating+1.563
iev+1.549
 Buk+1.508
 EDIT+1.506
Neg logit contributions
alsh-1.945
roller-1.684
roid-1.670
ndra-1.656
rador-1.653
TokenSanta
Token ID42694
Feature activation-2.64e-01

Pos logit contributions
�士+1.510
ciating+1.448
iev+1.421
��極+1.369
 Buk+1.368
Neg logit contributions
alsh-1.750
roller-1.499
roid-1.495
ndra-1.490
rador-1.484
Token Clara
Token ID27443
Feature activation-4.41e-01

Pos logit contributions
alsh+1.055
roller+0.902
roid+0.892
ndra+0.882
rador+0.874
Neg logit contributions
�士-1.158
ciating-1.098
iev-1.069
��極-1.062
 EDIT-1.036
Token County
Token ID3418
Feature activation-7.00e-01

Pos logit contributions
alsh+2.231
roller+1.978
roid+1.961
ndra+1.944
rador+1.927
Neg logit contributions
�士-1.439
ciating-1.358
iev-1.311
��極-1.284
 EDIT-1.265
Token v
Token ID410
Feature activation-1.11e+00

Pos logit contributions
alsh+3.226
roller+2.845
roid+2.819
ndra+2.785
rador+2.735
Neg logit contributions
�士-2.587
ciating-2.437
iev-2.354
��極-2.329
 EDIT-2.289
Token.
Token ID13
Feature activation-1.93e-01

Pos logit contributions
alsh+3.332
roller+2.757
roid+2.721
ndra+2.702
Switch+2.674
Neg logit contributions
�士-6.028
ciating-5.677
��極-5.578
iev-5.382
 seiz-5.378
Token Southern
Token ID8050
Feature activation-3.19e-01

Pos logit contributions
alsh+0.994
roller+0.882
roid+0.874
ndra+0.867
rador+0.860
Neg logit contributions
�士-0.617
ciating-0.582
iev-0.562
��極-0.549
 EDIT-0.542
Token Pacific
Token ID8211
Feature activation-2.20e-01

Pos logit contributions
alsh+1.151
roller+0.969
roid+0.959
ndra+0.946
rador+0.931
Neg logit contributions
�士-1.517
ciating-1.451
iev-1.417
��極-1.404
 EDIT-1.377
Token Railroad
Token ID36289
Feature activation-3.59e-01

Pos logit contributions
alsh+0.798
roller+0.665
roid+0.659
ndra+0.654
rador+0.647
Neg logit contributions
�士-1.032
ciating-0.997
iev-0.974
��極-0.954
 Iz-0.952
Token Company
Token ID5834
Feature activation-4.07e-01

Pos logit contributions
alsh+1.385
roller+1.172
roid+1.164
ndra+1.150
rador+1.141
Neg logit contributions
�士-1.609
ciating-1.550
iev-1.507
��極-1.485
 EDIT-1.471
Token Wester
Token ID32104
Feature activation+1.66e-01

Pos logit contributions
alsh+0.044
roller+0.039
roid+0.038
ndra+0.038
rador+0.038
Neg logit contributions
�士-0.032
ciating-0.030
iev-0.029
��極-0.029
 EDIT-0.028
Tokenlund
Token ID37525
Feature activation+2.07e-01

Pos logit contributions
�士+0.655
ciating+0.625
iev+0.614
��極+0.600
 EDIT+0.599
Neg logit contributions
alsh-0.713
roid-0.622
roller-0.621
rador-0.605
ndra-0.604
Token (@
Token ID4275
Feature activation-1.20e-01

Pos logit contributions
�士+0.844
ciating+0.803
iev+0.791
��極+0.770
 EDIT+0.769
Neg logit contributions
alsh-0.871
roller-0.753
ndra-0.744
roid-0.742
rador-0.731
TokenC
Token ID34
Feature activation-5.98e-01

Pos logit contributions
alsh+0.524
roller+0.452
roid+0.450
ndra+0.447
rador+0.443
Neg logit contributions
�士-0.473
ciating-0.456
iev-0.444
��極-0.430
 EDIT-0.429
Tokenody
Token ID1118
Feature activation-2.29e-01

Pos logit contributions
alsh+2.821
roller+2.476
roid+2.453
ndra+2.429
rador+2.407
Neg logit contributions
�士-2.165
ciating-2.056
iev-1.989
��極-1.959
 EDIT-1.927
TokenW
Token ID54
Feature activation-1.11e+00

Pos logit contributions
alsh+0.937
roller+0.804
roid+0.796
ndra+0.787
rador+0.780
Neg logit contributions
�士-0.968
ciating-0.926
iev-0.906
��極-0.887
 EDIT-0.880
Tokenester
Token ID7834
Feature activation-3.44e-01

Pos logit contributions
alsh+3.711
roller+2.987
roid+2.885
ndra+2.856
rador+2.787
Neg logit contributions
�士-5.732
ciating-5.462
��極-5.415
 Afric-5.230
 Amar-5.192
Tokenlund
Token ID37525
Feature activation-5.08e-02

Pos logit contributions
alsh+1.808
roller+1.599
roid+1.576
ndra+1.571
rador+1.560
Neg logit contributions
�士-1.111
ciating-1.029
��極-0.986
iev-0.957
 Afric-0.951
Token)
Token ID8
Feature activation-7.24e-02

Pos logit contributions
alsh+0.207
roller+0.178
roid+0.176
ndra+0.175
rador+0.172
Neg logit contributions
�士-0.215
ciating-0.205
iev-0.202
��極-0.197
 EDIT-0.196
Token October
Token ID3267
Feature activation-1.75e-02

Pos logit contributions
alsh+0.289
roller+0.247
roid+0.244
ndra+0.240
rador+0.236
Neg logit contributions
�士-0.320
ciating-0.305
��極-0.296
iev-0.294
 Afric-0.283
Token 7
Token ID767
Feature activation-4.62e-01

Pos logit contributions
alsh+0.089
roller+0.079
roid+0.079
ndra+0.078
rador+0.077
Neg logit contributions
�士-0.057
ciating-0.054
iev-0.052
��極-0.051
 EDIT-0.050
Token examples
Token ID6096
Feature activation+2.75e-01

Pos logit contributions
alsh+0.332
roller+0.288
roid+0.285
ndra+0.282
rador+0.279
Neg logit contributions
�士-0.305
ciating-0.291
iev-0.283
��極-0.278
 EDIT-0.274
Token of
Token ID286
Feature activation-1.72e-01

Pos logit contributions
�士+1.117
ciating+1.081
iev+1.061
 Buk+1.039
 Iz+1.035
Neg logit contributions
alsh-1.153
roller-0.999
roid-0.974
ndra-0.970
rador-0.965
Token Ant
Token ID3738
Feature activation+2.62e-02

Pos logit contributions
alsh+0.773
roller+0.674
roid+0.670
ndra+0.662
rador+0.657
Neg logit contributions
�士-0.658
ciating-0.625
iev-0.609
��極-0.601
 EDIT-0.589
Tokenill
Token ID359
Feature activation-4.23e-01

Pos logit contributions
�士+0.123
ciating+0.120
iev+0.118
 EDIT+0.115
��極+0.114
Neg logit contributions
alsh-0.093
roller-0.078
roid-0.076
ndra-0.076
rador-0.075
Tokenoth
Token ID849
Feature activation+4.28e-01

Pos logit contributions
alsh+1.197
roller+0.951
roid+0.942
ndra+0.911
rador+0.901
Neg logit contributions
�士-2.382
ciating-2.264
��極-2.232
iev-2.196
 Buk-2.172
Tokenrix
Token ID8609
Feature activation+8.36e-01

Pos logit contributions
�士+1.781
ciating+1.728
iev+1.712
 EDIT+1.648
��極+1.639
Neg logit contributions
alsh-1.740
roller-1.485
ndra-1.457
roid-1.450
rador-1.439
Token bones
Token ID11945
Feature activation+5.08e-01

Pos logit contributions
�士+3.241
ciating+3.146
iev+3.093
 Buk+3.024
 Afric+3.001
Neg logit contributions
alsh-3.607
roller-3.149
ndra-3.055
rador-3.038
roid-3.021
Token to
Token ID284
Feature activation+2.33e-01

Pos logit contributions
�士+2.030
ciating+1.974
iev+1.948
 Iz+1.900
 Buk+1.898
Neg logit contributions
alsh-2.125
roller-1.847
ndra-1.808
roid-1.789
rador-1.781
Token the
Token ID262
Feature activation+3.12e-01

Pos logit contributions
�士+0.868
ciating+0.831
iev+0.804
��極+0.784
 Buk+0.783
Neg logit contributions
alsh-1.067
roller-0.933
roid-0.919
ndra-0.913
rador-0.903
Token newly
Token ID8308
Feature activation+6.00e-02

Pos logit contributions
�士+1.185
ciating+1.136
iev+1.099
 Buk+1.074
��極+1.074
Neg logit contributions
alsh-1.408
roller-1.228
roid-1.210
ndra-1.200
rador-1.190
Token discovered
Token ID5071
Feature activation-3.23e-01

Pos logit contributions
�士+0.234
ciating+0.222
iev+0.216
��極+0.213
 EDIT+0.210
Neg logit contributions
alsh-0.267
roller-0.232
roid-0.230
ndra-0.227
rador-0.226
Token "
Token ID366
Feature activation+1.92e-01

Pos logit contributions
�士+1.939
iev+1.916
ciating+1.897
 EDIT+1.882
 Buk+1.879
Neg logit contributions
alsh-2.015
ndra-1.728
rador-1.689
roller-1.681
roid-1.665
Token2016
Token ID5304
Feature activation+6.19e-01

Pos logit contributions
�士+0.851
ciating+0.813
iev+0.808
 EDIT+0.785
 Buk+0.783
Neg logit contributions
alsh-0.744
roller-0.623
ndra-0.621
roid-0.617
rador-0.613
Token.
Token ID13
Feature activation+2.76e-01

Pos logit contributions
�士+2.500
iev+2.470
 Buk+2.429
ciating+2.419
 Iz+2.414
Neg logit contributions
alsh-2.504
roller-2.123
roid-2.112
rador-2.104
ndra-2.095
Token??
Token ID3548
Feature activation+6.11e-01

Pos logit contributions
�士+1.154
ciating+1.115
iev+1.112
 EDIT+1.093
 Iz+1.090
Neg logit contributions
alsh-1.112
roller-0.935
ndra-0.927
roid-0.924
rador-0.920
Token.?
Token ID40791
Feature activation+1.41e-01

Pos logit contributions
�士+1.897
ciating+1.824
iev+1.783
 EDIT+1.747
��極+1.734
Neg logit contributions
alsh-3.150
roller-2.793
roid-2.753
ndra-2.750
rador-2.726
Token?"
Token ID1701
Feature activation+7.80e-01

Pos logit contributions
�士+0.473
ciating+0.446
iev+0.433
��極+0.421
 EDIT+0.419
Neg logit contributions
alsh-0.700
roller-0.617
roid-0.612
ndra-0.609
rador-0.603
Token]
Token ID60
Feature activation-6.23e-02

Pos logit contributions
�士+2.924
 EDIT+2.733
 Iz+2.719
 Buk+2.716
ciating+2.707
Neg logit contributions
alsh-3.564
ndra-3.090
roid-3.088
roller-3.066
rador-3.026
Token [
Token ID685
Feature activation+3.62e-01

Pos logit contributions
alsh+0.297
roller+0.262
roid+0.260
ndra+0.256
rador+0.254
Neg logit contributions
�士-0.221
ciating-0.211
iev-0.203
��極-0.200
 EDIT-0.195
TokenEvent
Token ID9237
Feature activation+8.36e-01

Pos logit contributions
�士+1.053
ciating+1.005
iev+0.968
 EDIT+0.942
 Buk+0.924
Neg logit contributions
alsh-1.968
ndra-1.739
roller-1.732
roid-1.725
rador-1.717
TokenCountry
Token ID33921
Feature activation-7.33e-02

Pos logit contributions
iev+2.867
�士+2.793
 Afric+2.784
ciating+2.759
 Iz+2.729
Neg logit contributions
alsh-3.922
roid-3.288
ndra-3.279
roller-3.250
rador-3.249
Token "
Token ID366
Feature activation+3.82e-02

Pos logit contributions
alsh+0.288
roller+0.243
ndra+0.241
roid+0.239
rador+0.236
Neg logit contributions
�士-0.327
ciating-0.312
iev-0.305
��極-0.298
 Buk-0.297
TokenON
Token ID1340
Feature activation+3.20e-01

Pos logit contributions
�士+1.198
ciating+1.139
 EDIT+1.131
iev+1.131
 Iz+1.111
Neg logit contributions
alsh-1.147
roid-0.984
roller-0.979
ndra-0.963
rador-0.945
TokenOM
Token ID2662
Feature activation+6.52e-03

Pos logit contributions
�士+1.264
ciating+1.202
iev+1.182
 EDIT+1.181
 Buk+1.163
Neg logit contributions
alsh-1.380
roller-1.197
roid-1.189
ndra-1.176
rador-1.161
TokenICS
Token ID19505
Feature activation+7.40e-01

Pos logit contributions
�士+0.026
ciating+0.025
iev+0.025
��極+0.024
 EDIT+0.024
Neg logit contributions
alsh-0.028
roller-0.024
roid-0.024
ndra-0.024
rador-0.023
Token AND
Token ID5357
Feature activation+3.63e-01

Pos logit contributions
�士+2.510
 EDIT+2.371
ciating+2.363
iev+2.339
 Buk+2.317
Neg logit contributions
alsh-3.575
roller-3.156
roid-3.122
ndra-3.112
rador-3.100
Token TR
Token ID7579
Feature activation+4.38e-01

Pos logit contributions
�士+1.185
ciating+1.114
iev+1.087
 EDIT+1.062
��極+1.056
Neg logit contributions
alsh-1.829
roller-1.621
roid-1.606
ndra-1.596
rador-1.583
TokenADE
Token ID19266
Feature activation+7.32e-01

Pos logit contributions
�士+1.607
iev+1.522
ciating+1.515
 EDIT+1.491
 Iz+1.467
Neg logit contributions
alsh-1.999
roller-1.747
ndra-1.733
roid-1.725
rador-1.714
Token
Token ID198
Feature activation+3.12e-01

Pos logit contributions
�士+2.616
 EDIT+2.483
iev+2.455
ciating+2.435
 Iz+2.428
Neg logit contributions
alsh-3.400
roller-2.983
ndra-2.955
roid-2.933
rador-2.928
Token
Token ID198
Feature activation+2.04e-01

Pos logit contributions
�士+1.211
ciating+1.161
iev+1.139
 EDIT+1.108
 Buk+1.105
Neg logit contributions
alsh-1.368
roller-1.186
roid-1.174
ndra-1.163
rador-1.156
TokenThe
Token ID464
Feature activation+6.95e-02

Pos logit contributions
�士+0.791
ciating+0.752
iev+0.742
 EDIT+0.717
 Iz+0.714
Neg logit contributions
alsh-0.903
roller-0.778
roid-0.776
ndra-0.766
rador-0.764
Token Wednesday
Token ID3583
Feature activation-8.15e-02

Pos logit contributions
�士+0.268
ciating+0.255
iev+0.249
��極+0.243
 EDIT+0.241
Neg logit contributions
alsh-0.311
roller-0.270
roid-0.268
ndra-0.265
rador-0.263
Token-
Token ID12
Feature activation+1.46e-01

Pos logit contributions
alsh+0.326
roller+0.279
roid+0.276
ndra+0.273
rador+0.270
Neg logit contributions
�士-0.353
ciating-0.338
iev-0.330
��極-0.325
 EDIT-0.321
Token-
Token ID12
Feature activation-1.83e-01

Pos logit contributions
�士+0.251
ciating+0.240
iev+0.236
 Buk+0.228
 EDIT+0.228
Neg logit contributions
alsh-0.287
roller-0.248
roid-0.245
ndra-0.244
rador-0.242
Tokenfront
Token ID8534
Feature activation-1.66e-01

Pos logit contributions
alsh+0.669
roller+0.558
roid+0.553
ndra+0.547
rador+0.542
Neg logit contributions
�士-0.856
ciating-0.823
iev-0.809
��極-0.793
 EDIT-0.787
Tokens
Token ID82
Feature activation-1.19e-01

Pos logit contributions
alsh+0.695
roller+0.599
roid+0.593
ndra+0.587
rador+0.581
Neg logit contributions
�士-0.688
ciating-0.658
iev-0.641
��極-0.630
 EDIT-0.623
Token"
Token ID1
Feature activation+9.75e-02

Pos logit contributions
alsh+0.522
roller+0.453
roid+0.449
ndra+0.444
rador+0.440
Neg logit contributions
�士-0.466
ciating-0.445
iev-0.433
��極-0.425
 EDIT-0.420
Token
Token ID198
Feature activation+6.96e-01

Pos logit contributions
�士+0.387
ciating+0.370
iev+0.361
��極+0.353
 EDIT+0.351
Neg logit contributions
alsh-0.423
roller-0.367
roid-0.363
ndra-0.360
rador-0.357
Token
Token ID198
Feature activation+8.17e-01

Pos logit contributions
�士+2.449
iev+2.388
ciating+2.382
 Buk+2.356
 EDIT+2.351
Neg logit contributions
alsh-3.190
roller-2.758
roid-2.741
rador-2.734
ndra-2.714
TokenEnt
Token ID14539
Feature activation-4.97e-02

Pos logit contributions
�士+2.997
iev+2.885
ciating+2.870
 EDIT+2.784
 Buk+2.781
Neg logit contributions
alsh-3.658
rador-3.094
ndra-3.075
roid-3.073
roller-3.070
Tokenire
Token ID557
Feature activation-3.33e-01

Pos logit contributions
alsh+0.189
roller+0.160
ndra+0.158
roid+0.157
rador+0.155
Neg logit contributions
�士-0.221
ciating-0.214
iev-0.211
 EDIT-0.204
 Buk-0.204
Token classrooms
Token ID32579
Feature activation+1.50e-01

Pos logit contributions
alsh+1.481
roller+1.289
roid+1.279
ndra+1.264
rador+1.252
Neg logit contributions
�士-1.300
ciating-1.235
iev-1.197
��極-1.182
 EDIT-1.165
Token of
Token ID286
Feature activation+4.63e-02

Pos logit contributions
�士+0.587
ciating+0.562
iev+0.550
 Buk+0.539
 Iz+0.538
Neg logit contributions
alsh-0.652
roller-0.562
roid-0.559
ndra-0.555
rador-0.546
Token Somali
Token ID30886
Feature activation-1.20e-01

Pos logit contributions
�士+0.173
ciating+0.165
iev+0.160
��極+0.157
 EDIT+0.155
Neg logit contributions
alsh-0.213
roller-0.186
roid-0.184
ndra-0.182
rador-0.181
Token_
Token ID62
Feature activation+2.34e-01

Pos logit contributions
�士+3.094
iev+3.025
ciating+3.001
 Buk+2.868
 Iz+2.855
Neg logit contributions
alsh-3.613
roller-3.147
rador-3.107
roid-3.084
ndra-3.073
TokenK
Token ID42
Feature activation+5.10e-01

Pos logit contributions
�士+0.883
ciating+0.844
iev+0.832
��極+0.803
 Buk+0.799
Neg logit contributions
alsh-1.049
roller-0.916
roid-0.902
ndra-0.896
rador-0.893
Tokenk
Token ID74
Feature activation+6.45e-01

Pos logit contributions
�士+1.921
iev+1.846
ciating+1.841
 Buk+1.755
��極+1.752
Neg logit contributions
alsh-2.250
roller-1.960
roid-1.922
rador-1.917
ndra-1.913
TokenBY
Token ID17513
Feature activation+7.43e-01

Pos logit contributions
�士+2.393
iev+2.317
ciating+2.297
 Buk+2.196
 Iz+2.194
Neg logit contributions
alsh-2.847
roller-2.489
rador-2.435
roid-2.435
ndra-2.429
TokenRG
Token ID48192
Feature activation+7.51e-01

Pos logit contributions
�士+2.793
iev+2.708
ciating+2.687
 Buk+2.575
 Iz+2.571
Neg logit contributions
alsh-3.228
roller-2.815
roid-2.750
ndra-2.749
rador-2.748
Tokenv
Token ID85
Feature activation+9.05e-01

Pos logit contributions
�士+2.801
iev+2.713
ciating+2.698
 Iz+2.583
 Buk+2.581
Neg logit contributions
alsh-3.279
roller-2.859
roid-2.802
rador-2.801
ndra-2.796
TokenCh
Token ID1925
Feature activation+5.86e-01

Pos logit contributions
�士+3.338
iev+3.266
ciating+3.209
 Buk+3.099
 Iz+3.096
Neg logit contributions
alsh-3.928
roller-3.435
rador-3.358
ndra-3.350
roid-3.344
Token5
Token ID20
Feature activation+5.43e-01

Pos logit contributions
�士+2.210
iev+2.130
ciating+2.119
 Buk+2.029
 Iz+2.021
Neg logit contributions
alsh-2.575
roller-2.243
roid-2.201
ndra-2.191
rador-2.190
TokenZ
Token ID57
Feature activation+3.97e-01

Pos logit contributions
�士+2.089
iev+2.011
ciating+2.007
 Buk+1.917
 Iz+1.914
Neg logit contributions
alsh-2.344
roller-2.038
roid-2.001
rador-1.991
ndra-1.987
Tokenk
Token ID74
Feature activation+6.11e-01

Pos logit contributions
�士+1.516
ciating+1.449
iev+1.447
 Buk+1.382
��極+1.381
Neg logit contributions
alsh-1.746
roller-1.520
roid-1.493
ndra-1.486
rador-1.482
TokenA
Token ID32
Feature activation+3.60e-01

Pos logit contributions
�士+2.274
iev+2.196
ciating+2.180
 Buk+2.088
 Iz+2.082
Neg logit contributions
alsh-2.703
roller-2.363
roid-2.313
rador-2.309
ndra-2.305
Token model
Token ID2746
Feature activation+3.90e-01

Pos logit contributions
�士+0.200
ciating+0.191
iev+0.185
��極+0.182
 Buk+0.182
Neg logit contributions
alsh-0.232
roller-0.202
roid-0.200
ndra-0.198
rador-0.197
Token wearing
Token ID5762
Feature activation+6.93e-02

Pos logit contributions
�士+1.541
ciating+1.469
iev+1.450
 Buk+1.427
 Iz+1.423
Neg logit contributions
alsh-1.691
roller-1.453
ndra-1.430
roid-1.422
rador-1.406
Token a
Token ID257
Feature activation+1.48e-01

Pos logit contributions
�士+0.246
ciating+0.234
iev+0.227
��極+0.223
 EDIT+0.219
Neg logit contributions
alsh-0.330
roller-0.291
roid-0.288
ndra-0.285
rador-0.283
Token dress
Token ID6576
Feature activation+3.30e-01

Pos logit contributions
�士+0.547
ciating+0.518
iev+0.504
��極+0.495
 Buk+0.491
Neg logit contributions
alsh-0.683
roller-0.596
roid-0.590
ndra-0.587
rador-0.579
Token created
Token ID2727
Feature activation+1.26e-01

Pos logit contributions
�士+1.345
ciating+1.277
iev+1.263
 Buk+1.236
 Iz+1.235
Neg logit contributions
alsh-1.391
roller-1.195
ndra-1.179
roid-1.178
rador-1.160
Token from
Token ID422
Feature activation+2.88e-01

Pos logit contributions
�士+0.499
ciating+0.474
iev+0.463
��極+0.453
 Buk+0.452
Neg logit contributions
alsh-0.547
roller-0.476
ndra-0.468
roid-0.466
rador-0.457
Token roses
Token ID42152
Feature activation+2.63e-01

Pos logit contributions
�士+1.014
ciating+0.957
iev+0.932
��極+0.909
 Buk+0.908
Neg logit contributions
alsh-1.383
roller-1.214
roid-1.199
ndra-1.193
rador-1.177
Token to
Token ID284
Feature activation+1.80e-01

Pos logit contributions
�士+1.119
ciating+1.073
iev+1.053
 Buk+1.028
��極+1.028
Neg logit contributions
alsh-1.061
roller-0.908
roid-0.895
ndra-0.886
rador-0.878
Token mark
Token ID1317
Feature activation+4.69e-02

Pos logit contributions
�士+0.716
ciating+0.683
iev+0.665
��極+0.648
 Buk+0.647
Neg logit contributions
alsh-0.783
roller-0.679
roid-0.669
ndra-0.665
rador-0.659
Token the
Token ID262
Feature activation+3.24e-03

Pos logit contributions
�士+0.170
ciating+0.162
iev+0.157
��極+0.154
 Buk+0.153
Neg logit contributions
alsh-0.220
roller-0.193
roid-0.191
ndra-0.189
rador-0.187
Token connection
Token ID4637
Feature activation+1.69e-01

Pos logit contributions
�士+0.012
ciating+0.012
iev+0.012
��極+0.011
 EDIT+0.011
Neg logit contributions
alsh-0.014
roller-0.013
roid-0.013
ndra-0.012
rador-0.012
Token Ellis
Token ID21299
Feature activation+1.49e-01

Pos logit contributions
alsh+0.634
roller+0.544
roid+0.538
ndra+0.533
rador+0.527
Neg logit contributions
�士-0.653
ciating-0.625
iev-0.609
��極-0.599
 EDIT-0.592
Token,
Token ID11
Feature activation+6.38e-02

Pos logit contributions
�士+0.673
ciating+0.643
iev+0.634
��極+0.621
 Iz+0.616
Neg logit contributions
alsh-0.568
roller-0.478
roid-0.473
ndra-0.472
rador-0.466
Token Devin
Token ID37081
Feature activation+2.56e-01

Pos logit contributions
�士+0.254
ciating+0.243
iev+0.237
��極+0.232
 Buk+0.231
Neg logit contributions
alsh-0.277
roller-0.240
roid-0.237
ndra-0.235
rador-0.234
Token Harris
Token ID10026
Feature activation+2.56e-01

Pos logit contributions
�士+0.814
ciating+0.767
iev+0.740
��極+0.724
 EDIT+0.712
Neg logit contributions
alsh-1.317
roller-1.170
roid-1.160
ndra-1.150
rador-1.140
Token,
Token ID11
Feature activation+1.28e-01

Pos logit contributions
�士+1.153
ciating+1.098
iev+1.085
��極+1.060
 Buk+1.054
Neg logit contributions
alsh-0.975
roller-0.821
roid-0.812
ndra-0.811
rador-0.802
Token Raymond
Token ID24238
Feature activation+2.03e-01

Pos logit contributions
�士+0.507
ciating+0.485
iev+0.473
��極+0.464
 Buk+0.463
Neg logit contributions
alsh-0.555
roller-0.481
roid-0.475
ndra-0.471
rador-0.469
Token Fel
Token ID13937
Feature activation+4.95e-01

Pos logit contributions
�士+0.659
ciating+0.643
 Buk+0.623
 Iz+0.619
iev+0.617
Neg logit contributions
alsh-1.006
roller-0.886
roid-0.876
rador-0.873
ndra-0.867
Tokenton
Token ID1122
Feature activation-4.46e-02

Pos logit contributions
�士+1.601
iev+1.548
ciating+1.547
 EDIT+1.505
 Iz+1.486
Neg logit contributions
alsh-2.413
ndra-2.119
roid-2.106
rador-2.101
roller-2.094
Token (
Token ID357
Feature activation+1.82e-01

Pos logit contributions
alsh+0.166
roller+0.139
roid+0.138
ndra+0.137
rador+0.135
Neg logit contributions
�士-0.206
ciating-0.197
iev-0.194
��極-0.191
 Buk-0.188
Tokenwho
Token ID8727
Feature activation+2.24e-01

Pos logit contributions
�士+0.700
ciating+0.666
iev+0.657
��極+0.641
 EDIT+0.633
Neg logit contributions
alsh-0.806
roller-0.693
ndra-0.690
roid-0.689
rador-0.685
Token has
Token ID468
Feature activation-8.03e-02

Pos logit contributions
�士+0.886
ciating+0.845
iev+0.824
��極+0.807
 EDIT+0.799
Neg logit contributions
alsh-0.981
roller-0.850
roid-0.841
ndra-0.833
rador-0.827
Tokenuters
Token ID5843
Feature activation+1.30e-01

Pos logit contributions
�士+0.831
ciating+0.810
iev+0.803
 EDIT+0.782
 Ala+0.777
Neg logit contributions
alsh-0.460
roller-0.371
ndra-0.371
roid-0.363
rador-0.352
Token typically
Token ID6032
Feature activation+1.69e-01

Pos logit contributions
�士+0.534
ciating+0.512
iev+0.501
��極+0.490
 EDIT+0.489
Neg logit contributions
alsh-0.542
roller-0.467
roid-0.460
ndra-0.457
rador-0.454
Token pay
Token ID1414
Feature activation+3.90e-01

Pos logit contributions
�士+0.687
ciating+0.658
iev+0.643
��極+0.630
 EDIT+0.629
Neg logit contributions
alsh-0.712
roller-0.615
roid-0.606
ndra-0.599
rador-0.597
Token none
Token ID4844
Feature activation+8.02e-02

Pos logit contributions
�士+1.458
ciating+1.394
iev+1.369
 Iz+1.336
 EDIT+1.335
Neg logit contributions
alsh-1.765
roller-1.537
roid-1.522
ndra-1.508
rador-1.508
Token of
Token ID286
Feature activation+3.80e-01

Pos logit contributions
�士+0.330
ciating+0.320
iev+0.317
 EDIT+0.309
 Iz+0.309
Neg logit contributions
alsh-0.328
roller-0.281
roid-0.277
ndra-0.277
rador-0.275
Token these
Token ID777
Feature activation+1.44e-01

Pos logit contributions
�士+1.333
ciating+1.255
iev+1.237
 Buk+1.205
 Iz+1.203
Neg logit contributions
alsh-1.806
roller-1.598
roid-1.578
rador-1.560
ndra-1.557
Token costs
Token ID3484
Feature activation+2.37e-01

Pos logit contributions
�士+0.624
ciating+0.600
iev+0.586
��極+0.574
 EDIT+0.571
Neg logit contributions
alsh-0.573
roller-0.491
roid-0.485
ndra-0.480
rador-0.476
Token,
Token ID11
Feature activation+7.05e-02

Pos logit contributions
�士+1.002
ciating+0.968
iev+0.964
 Iz+0.944
 EDIT+0.941
Neg logit contributions
alsh-0.936
roller-0.800
roid-0.789
ndra-0.788
rador-0.785
Token he
Token ID339
Feature activation-2.56e-01

Pos logit contributions
�士+0.277
ciating+0.264
iev+0.256
��極+0.252
 EDIT+0.249
Neg logit contributions
alsh-0.311
roller-0.270
roid-0.267
ndra-0.264
rador-0.262
Token noted
Token ID4367
Feature activation-2.71e-01

Pos logit contributions
alsh+1.270
roller+1.117
roid+1.113
ndra+1.105
rador+1.088
Neg logit contributions
�士-0.866
ciating-0.824
iev-0.789
��極-0.777
 EDIT-0.761
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
alsh+1.012
roller+0.856
roid+0.845
ndra+0.836
rador+0.826
Neg logit contributions
�士-1.241
ciating-1.192
iev-1.165
��極-1.148
 EDIT-1.136
Token sets
Token ID5621
Feature activation+4.58e-01

Pos logit contributions
�士+3.081
iev+3.034
ciating+3.006
 Iz+2.965
 EDIT+2.953
Neg logit contributions
alsh-3.194
roller-2.771
ndra-2.713
roid-2.704
rador-2.669
Token
Token ID851
Feature activation+1.39e-01

Pos logit contributions
�士+1.898
ciating+1.847
iev+1.825
 Iz+1.783
 EDIT+1.783
Neg logit contributions
alsh-1.850
roller-1.586
roid-1.570
ndra-1.539
rador-1.537
Token without
Token ID1231
Feature activation+2.47e-01

Pos logit contributions
�士+0.540
ciating+0.517
iev+0.503
��極+0.491
 EDIT+0.488
Neg logit contributions
alsh-0.614
roller-0.535
roid-0.529
ndra-0.524
rador-0.519
Token knowing
Token ID6970
Feature activation+5.32e-01

Pos logit contributions
�士+0.939
ciating+0.902
iev+0.879
 Buk+0.856
 EDIT+0.854
Neg logit contributions
alsh-1.112
roller-0.974
roid-0.953
ndra-0.951
rador-0.939
Token the
Token ID262
Feature activation+3.89e-01

Pos logit contributions
�士+1.723
ciating+1.635
iev+1.618
 Buk+1.575
 EDIT+1.573
Neg logit contributions
alsh-2.667
roller-2.365
roid-2.327
ndra-2.326
rador-2.297
Token magnitude
Token ID14735
Feature activation+8.50e-02

Pos logit contributions
�士+1.513
ciating+1.444
iev+1.410
 Buk+1.371
 EDIT+1.371
Neg logit contributions
alsh-1.726
roller-1.501
roid-1.479
ndra-1.471
rador-1.454
Token of
Token ID286
Feature activation+1.27e-01

Pos logit contributions
�士+0.349
ciating+0.333
iev+0.330
 EDIT+0.320
 Buk+0.320
Neg logit contributions
alsh-0.355
roller-0.306
ndra-0.303
rador-0.300
roid-0.300
Token signals
Token ID10425
Feature activation+2.51e-01

Pos logit contributions
�士+0.462
ciating+0.440
iev+0.431
 Buk+0.418
 EDIT+0.417
Neg logit contributions
alsh-0.595
roller-0.523
roid-0.514
ndra-0.513
rador-0.507
Token in
Token ID287
Feature activation+2.28e-01

Pos logit contributions
�士+1.033
ciating+0.993
iev+0.981
 Iz+0.952
 EDIT+0.950
Neg logit contributions
alsh-1.045
roller-0.902
roid-0.886
ndra-0.882
rador-0.878
Token them
Token ID606
Feature activation+2.71e-01

Pos logit contributions
�士+0.901
ciating+0.866
iev+0.846
 EDIT+0.821
 Buk+0.821
Neg logit contributions
alsh-0.990
roller-0.860
roid-0.849
ndra-0.843
rador-0.832
Token.
Token ID13
Feature activation+1.35e-01

Pos logit contributions
�士+1.175
ciating+1.134
iev+1.119
 EDIT+1.089
 Iz+1.086
Neg logit contributions
alsh-1.059
roller-0.903
roid-0.891
ndra-0.885
rador-0.874
Token Thank
Token ID6952
Feature activation-1.52e-01

Pos logit contributions
alsh+0.434
roller+0.380
roid+0.376
ndra+0.373
rador+0.369
Neg logit contributions
�士-0.346
ciating-0.329
iev-0.319
��極-0.314
 EDIT-0.308
Token you
Token ID345
Feature activation-5.24e-01

Pos logit contributions
alsh+0.637
roller+0.549
roid+0.543
ndra+0.537
rador+0.532
Neg logit contributions
�士-0.628
ciating-0.601
iev-0.587
��極-0.573
 EDIT-0.570
Token,
Token ID11
Feature activation-2.31e-01

Pos logit contributions
alsh+2.039
roller+1.737
roid+1.723
ndra+1.707
rador+1.674
Neg logit contributions
�士-2.318
ciating-2.215
iev-2.157
��極-2.147
 Buk-2.094
Token Dave
Token ID9935
Feature activation-4.40e-01

Pos logit contributions
alsh+1.039
roller+0.905
roid+0.895
ndra+0.890
rador+0.877
Neg logit contributions
�士-0.885
ciating-0.841
iev-0.815
��極-0.807
 EDIT-0.785
Token.
Token ID13
Feature activation-2.34e-01

Pos logit contributions
alsh+1.858
roller+1.600
roid+1.589
ndra+1.567
rador+1.540
Neg logit contributions
�士-1.816
ciating-1.735
iev-1.679
��極-1.660
 EDIT-1.632
Token
Token ID198
Feature activation+1.22e-01

Pos logit contributions
alsh+1.027
roller+0.892
roid+0.880
ndra+0.874
rador+0.864
Neg logit contributions
�士-0.922
ciating-0.877
iev-0.850
��極-0.842
 Buk-0.819
Token
Token ID198
Feature activation+1.42e-01

Pos logit contributions
�士+0.495
ciating+0.472
iev+0.457
��極+0.452
 EDIT+0.444
Neg logit contributions
alsh-0.525
roller-0.455
roid-0.450
ndra-0.445
rador-0.440
TokenDon
Token ID3987
Feature activation-2.39e-01

Pos logit contributions
�士+0.566
ciating+0.543
iev+0.532
��極+0.515
 EDIT+0.515
Neg logit contributions
alsh-0.609
roller-0.526
roid-0.521
ndra-0.515
rador-0.513
Tokenna
Token ID2616
Feature activation-2.16e-01

Pos logit contributions
alsh+0.979
roller+0.841
roid+0.831
ndra+0.823
rador+0.813
Neg logit contributions
�士-1.015
ciating-0.972
iev-0.947
��極-0.933
 EDIT-0.921
Token's
Token ID338
Feature activation+5.37e-03

Pos logit contributions
alsh+1.025
roller+0.900
roid+0.893
ndra+0.883
rador+0.873
Neg logit contributions
�士-0.777
ciating-0.740
iev-0.713
��極-0.704
 EDIT-0.689
Token cub
Token ID13617
Feature activation-2.41e-01

Pos logit contributions
�士+0.020
ciating+0.019
iev+0.019
��極+0.018
 EDIT+0.018
Neg logit contributions
alsh-0.024
roller-0.021
roid-0.021
ndra-0.021
rador-0.021
Token yards
Token ID5695
Feature activation+3.79e-01

Pos logit contributions
�士+0.985
iev+0.934
ciating+0.924
 Iz+0.897
 EDIT+0.894
Neg logit contributions
alsh-1.377
roller-1.221
roid-1.208
rador-1.190
ndra-1.186
Token with
Token ID351
Feature activation+2.19e-01

Pos logit contributions
�士+1.569
iev+1.504
ciating+1.500
 Iz+1.464
 Amar+1.458
Neg logit contributions
alsh-1.535
roller-1.330
roid-1.314
rador-1.298
ndra-1.289
Token one
Token ID530
Feature activation-2.02e-01

Pos logit contributions
�士+0.761
ciating+0.721
iev+0.702
 Iz+0.683
��極+0.683
Neg logit contributions
alsh-1.057
roller-0.936
roid-0.924
ndra-0.918
rador-0.911
Token touchdown
Token ID10242
Feature activation-1.86e-01

Pos logit contributions
alsh+0.741
roller+0.625
roid+0.619
ndra+0.610
rador+0.600
Neg logit contributions
�士-0.939
ciating-0.903
iev-0.877
��極-0.869
 EDIT-0.857
Token and
Token ID290
Feature activation+1.74e-01

Pos logit contributions
alsh+0.743
roller+0.638
roid+0.629
ndra+0.621
rador+0.616
Neg logit contributions
�士-0.805
ciating-0.770
iev-0.759
��極-0.740
 EDIT-0.735
Token one
Token ID530
Feature activation-1.10e-01

Pos logit contributions
�士+0.639
ciating+0.607
iev+0.590
��極+0.578
 EDIT+0.571
Neg logit contributions
alsh-0.809
roller-0.709
roid-0.702
ndra-0.695
rador-0.689
Token interception
Token ID28759
Feature activation-3.33e-01

Pos logit contributions
alsh+0.447
roller+0.383
roid+0.379
ndra+0.374
rador+0.370
Neg logit contributions
�士-0.473
ciating-0.453
iev-0.440
��極-0.435
 EDIT-0.428
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
alsh+1.254
roller+1.062
roid+1.049
ndra+1.037
rador+1.024
Neg logit contributions
�士-1.518
ciating-1.458
iev-1.424
��極-1.402
 EDIT-1.388
Token He
Token ID679
Feature activation+1.64e-01

Pos logit contributions
alsh+0.524
roller+0.460
roid+0.455
ndra+0.451
rador+0.443
Neg logit contributions
�士-0.413
ciating-0.396
iev-0.379
��極-0.377
 Buk-0.362
Token's
Token ID338
Feature activation+2.31e-01

Pos logit contributions
�士+0.681
ciating+0.653
iev+0.629
��極+0.624
 EDIT+0.612
Neg logit contributions
alsh-0.694
roller-0.597
roid-0.594
ndra-0.588
rador-0.578
Token only
Token ID691
Feature activation+2.35e-02

Pos logit contributions
�士+0.905
ciating+0.865
iev+0.833
��極+0.823
 EDIT+0.807
Neg logit contributions
alsh-1.022
roller-0.888
roid-0.880
ndra-0.871
rador-0.860
Token revealed
Token ID4602
Feature activation-2.14e-01

Pos logit contributions
�士+0.566
ciating+0.541
iev+0.529
��極+0.514
 EDIT+0.513
Neg logit contributions
alsh-0.665
roller-0.580
roid-0.573
ndra-0.569
rador-0.562
Token there
Token ID612
Feature activation-1.42e-01

Pos logit contributions
alsh+0.926
roller+0.800
roid+0.789
ndra+0.783
rador+0.772
Neg logit contributions
�士-0.863
ciating-0.827
iev-0.802
��極-0.788
 EDIT-0.775
Token was
Token ID373
Feature activation+3.02e-01

Pos logit contributions
alsh+0.603
roller+0.521
roid+0.516
ndra+0.510
rador+0.505
Neg logit contributions
�士-0.576
ciating-0.550
iev-0.536
��極-0.527
 EDIT-0.521
Token no
Token ID645
Feature activation+2.54e-01

Pos logit contributions
�士+1.270
ciating+1.217
iev+1.193
 Iz+1.165
 EDIT+1.165
Neg logit contributions
alsh-1.231
roller-1.059
roid-1.049
ndra-1.035
rador-1.026
Token evidence
Token ID2370
Feature activation+3.67e-01

Pos logit contributions
�士+0.956
ciating+0.911
iev+0.888
 Buk+0.865
��極+0.864
Neg logit contributions
alsh-1.152
roller-1.008
roid-0.999
ndra-0.989
rador-0.981
Token of
Token ID286
Feature activation-4.36e-02

Pos logit contributions
�士+1.485
ciating+1.405
iev+1.388
 Buk+1.362
 Ala+1.361
Neg logit contributions
alsh-1.544
roller-1.344
roid-1.335
rador-1.314
ndra-1.298
Token any
Token ID597
Feature activation-3.42e-01

Pos logit contributions
alsh+0.190
roller+0.165
roid+0.164
ndra+0.162
rador+0.160
Neg logit contributions
�士-0.173
ciating-0.165
iev-0.160
��極-0.157
 EDIT-0.156
Token prior
Token ID3161
Feature activation-1.56e-01

Pos logit contributions
alsh+1.451
roller+1.249
roid+1.236
ndra+1.221
rador+1.210
Neg logit contributions
�士-1.406
ciating-1.344
iev-1.304
��極-1.291
 EDIT-1.262
Token relationship
Token ID2776
Feature activation+5.99e-03

Pos logit contributions
alsh+0.625
roller+0.535
roid+0.529
ndra+0.523
rador+0.517
Neg logit contributions
�士-0.673
ciating-0.645
iev-0.629
��極-0.619
 EDIT-0.613
Token or
Token ID393
Feature activation+5.81e-02

Pos logit contributions
�士+0.023
ciating+0.022
iev+0.022
��極+0.021
 EDIT+0.021
Neg logit contributions
alsh-0.027
roller-0.023
roid-0.023
ndra-0.023
rador-0.022
Token association
Token ID8112
Feature activation-1.13e-01

Pos logit contributions
�士+0.239
ciating+0.229
iev+0.223
��極+0.218
 EDIT+0.217
Neg logit contributions
alsh-0.244
roller-0.211
roid-0.209
ndra-0.206
rador-0.204
Token doctors
Token ID7519
Feature activation-6.78e-02

Pos logit contributions
alsh+0.571
roller+0.494
roid+0.488
ndra+0.483
rador+0.479
Neg logit contributions
�士-0.549
ciating-0.525
iev-0.512
��極-0.502
 EDIT-0.497
Token said
Token ID531
Feature activation+3.35e-03

Pos logit contributions
alsh+0.298
roller+0.259
roid+0.256
ndra+0.254
rador+0.251
Neg logit contributions
�士-0.267
ciating-0.255
iev-0.248
��極-0.243
 EDIT-0.241
Token she
Token ID673
Feature activation+4.81e-02

Pos logit contributions
�士+0.014
ciating+0.013
iev+0.013
 Iz+0.013
 Buk+0.013
Neg logit contributions
alsh-0.014
roller-0.012
roid-0.012
ndra-0.012
rador-0.012
Token risked
Token ID42179
Feature activation+1.23e-02

Pos logit contributions
�士+0.192
ciating+0.183
iev+0.177
��極+0.176
 EDIT+0.172
Neg logit contributions
alsh-0.209
roller-0.182
roid-0.180
ndra-0.178
rador-0.176
Token severe
Token ID6049
Feature activation-3.30e-01

Pos logit contributions
�士+0.048
ciating+0.046
iev+0.045
��極+0.044
 EDIT+0.044
Neg logit contributions
alsh-0.054
roller-0.047
roid-0.047
ndra-0.046
rador-0.046
Token infection
Token ID10280
Feature activation-3.42e-01

Pos logit contributions
alsh+1.435
roller+1.244
roid+1.237
ndra+1.220
rador+1.207
Neg logit contributions
�士-1.313
ciating-1.253
iev-1.214
��極-1.210
 EDIT-1.176
Token and
Token ID290
Feature activation-1.57e-01

Pos logit contributions
alsh+1.463
roller+1.265
roid+1.254
ndra+1.239
rador+1.226
Neg logit contributions
�士-1.390
ciating-1.326
iev-1.289
��極-1.271
 EDIT-1.252
Token scar
Token ID10153
Feature activation-2.19e-01

Pos logit contributions
alsh+0.680
roller+0.588
roid+0.583
ndra+0.577
rador+0.570
Neg logit contributions
�士-0.631
ciating-0.603
iev-0.586
��極-0.578
 EDIT-0.568
Tokenring
Token ID1806
Feature activation+4.75e-02

Pos logit contributions
alsh+0.924
roller+0.798
roid+0.791
ndra+0.781
rador+0.772
Neg logit contributions
�士-0.898
ciating-0.857
iev-0.834
��極-0.822
 EDIT-0.811
Token if
Token ID611
Feature activation+4.94e-02

Pos logit contributions
�士+0.191
ciating+0.184
iev+0.179
��極+0.175
 EDIT+0.174
Neg logit contributions
alsh-0.203
roller-0.176
roid-0.173
ndra-0.172
rador-0.171
Token she
Token ID673
Feature activation+3.88e-03

Pos logit contributions
�士+0.211
ciating+0.202
iev+0.198
 Iz+0.193
 EDIT+0.193
Neg logit contributions
alsh-0.200
roller-0.171
roid-0.169
ndra-0.167
rador-0.165
Token)
Token ID8
Feature activation+1.88e-01

Pos logit contributions
�士+2.187
ciating+2.112
iev+2.062
 EDIT+2.026
 Iz+2.019
Neg logit contributions
alsh-1.999
roller-1.706
roid-1.692
ndra-1.685
rador-1.667
Token or
Token ID393
Feature activation-3.32e-03

Pos logit contributions
�士+0.816
ciating+0.786
iev+0.772
 EDIT+0.757
 Iz+0.751
Neg logit contributions
alsh-0.736
roller-0.633
roid-0.625
ndra-0.619
rador-0.612
Token maybe
Token ID3863
Feature activation+5.70e-01

Pos logit contributions
alsh+0.014
roller+0.012
roid+0.012
ndra+0.012
rador+0.012
Neg logit contributions
�士-0.013
ciating-0.013
iev-0.012
��極-0.012
 EDIT-0.012
Token for
Token ID329
Feature activation-2.54e-01

Pos logit contributions
�士+2.162
ciating+2.062
iev+2.015
 EDIT+1.995
 Iz+1.976
Neg logit contributions
alsh-2.527
roller-2.211
roid-2.186
ndra-2.164
rador-2.130
Token clarity
Token ID16287
Feature activation-1.94e-02

Pos logit contributions
alsh+1.186
roller+1.039
roid+1.028
ndra+1.019
rador+1.009
Neg logit contributions
�士-0.927
ciating-0.881
iev-0.854
��極-0.842
 EDIT-0.824
Token
Token ID447
Feature activation-4.31e-01

Pos logit contributions
alsh+0.077
roller+0.065
roid+0.065
ndra+0.064
rador+0.064
Neg logit contributions
�士-0.084
ciating-0.081
iev-0.079
 EDIT-0.078
��極-0.077
Token
Token ID247
Feature activation-1.32e-01

Pos logit contributions
alsh+1.931
roller+1.668
roid+1.665
ndra+1.647
rador+1.632
Neg logit contributions
�士-1.641
ciating-1.596
iev-1.540
 EDIT-1.496
 Afric-1.487
Tokens
Token ID82
Feature activation-2.51e-01

Pos logit contributions
alsh+0.548
roller+0.472
roid+0.467
ndra+0.462
rador+0.457
Neg logit contributions
�士-0.553
ciating-0.529
iev-0.515
��極-0.507
 EDIT-0.501
Token sake
Token ID11060
Feature activation+1.81e-01

Pos logit contributions
alsh+1.355
roller+1.210
roid+1.200
ndra+1.190
rador+1.181
Neg logit contributions
�士-0.740
ciating-0.695
iev-0.669
��極-0.652
 EDIT-0.642
Token you
Token ID345
Feature activation-3.60e-02

Pos logit contributions
�士+0.794
ciating+0.766
iev+0.751
 EDIT+0.737
��極+0.729
Neg logit contributions
alsh-0.705
roller-0.601
roid-0.593
ndra-0.588
rador-0.581
Token reduce
Token ID4646
Feature activation-3.85e-03

Pos logit contributions
alsh+0.148
roller+0.127
roid+0.126
ndra+0.125
rador+0.123
Neg logit contributions
�士-0.151
ciating-0.145
iev-0.141
��極-0.139
 EDIT-0.138
Token playing
Token ID2712
Feature activation-4.25e-01

Pos logit contributions
�士+0.295
ciating+0.281
iev+0.273
��極+0.268
 EDIT+0.265
Neg logit contributions
alsh-0.332
roller-0.289
roid-0.286
ndra-0.283
rador-0.280
Token well
Token ID880
Feature activation+1.41e-01

Pos logit contributions
alsh+1.800
roller+1.574
roid+1.542
ndra+1.513
uca+1.497
Neg logit contributions
�士-1.754
ciating-1.655
��極-1.603
iev-1.588
 EDIT-1.540
Token.
Token ID13
Feature activation+1.47e-01

Pos logit contributions
�士+0.582
ciating+0.561
iev+0.548
��極+0.535
 EDIT+0.533
Neg logit contributions
alsh-0.587
roller-0.504
roid-0.500
ndra-0.495
rador-0.490
Token Now
Token ID2735
Feature activation+2.19e-01

Pos logit contributions
�士+0.524
ciating+0.497
iev+0.483
��極+0.471
 EDIT+0.470
Neg logit contributions
alsh-0.701
roller-0.616
roid-0.611
ndra-0.605
rador-0.601
Token we
Token ID356
Feature activation-1.54e-01

Pos logit contributions
�士+0.888
ciating+0.851
iev+0.835
 Iz+0.814
 EDIT+0.813
Neg logit contributions
alsh-0.922
roller-0.794
roid-0.790
ndra-0.784
rador-0.778
Token are
Token ID389
Feature activation-1.27e-01

Pos logit contributions
alsh+0.647
roller+0.559
roid+0.552
ndra+0.546
rador+0.539
Neg logit contributions
�士-0.635
ciating-0.607
iev-0.589
��極-0.582
 EDIT-0.573
Token playing
Token ID2712
Feature activation-2.65e-01

Pos logit contributions
alsh+0.536
roller+0.464
roid+0.458
ndra+0.453
rador+0.447
Neg logit contributions
�士-0.521
ciating-0.497
iev-0.482
��極-0.475
 EDIT-0.469
Token well
Token ID880
Feature activation+1.91e-02

Pos logit contributions
alsh+1.143
roller+0.995
roid+0.979
ndra+0.965
rador+0.954
Neg logit contributions
�士-1.073
ciating-1.020
��極-0.979
iev-0.979
 EDIT-0.952
Token,
Token ID11
Feature activation+5.70e-02

Pos logit contributions
�士+0.083
ciating+0.080
iev+0.078
��極+0.076
 EDIT+0.075
Neg logit contributions
alsh-0.076
roller-0.065
roid-0.064
ndra-0.064
rador-0.063
Token it
Token ID340
Feature activation+8.11e-03

Pos logit contributions
�士+0.236
ciating+0.226
iev+0.220
��極+0.216
 EDIT+0.214
Neg logit contributions
alsh-0.239
roller-0.206
roid-0.204
ndra-0.202
rador-0.200
Token shows
Token ID2523
Feature activation+4.63e-02

Pos logit contributions
�士+0.032
ciating+0.030
iev+0.029
��極+0.029
 EDIT+0.029
Neg logit contributions
alsh-0.036
roller-0.031
roid-0.031
ndra-0.031
rador-0.030
Token brew
Token ID9059
Feature activation+2.01e-01

Pos logit contributions
alsh+0.993
roller+0.861
roid+0.855
ndra+0.844
rador+0.833
Neg logit contributions
�士-0.904
ciating-0.866
iev-0.836
��極-0.830
 EDIT-0.808
Tokens
Token ID82
Feature activation+2.69e-02

Pos logit contributions
�士+0.913
ciating+0.872
iev+0.861
 Iz+0.844
��極+0.842
Neg logit contributions
alsh-0.749
roller-0.634
roid-0.624
ndra-0.623
rador-0.611
Token beer
Token ID6099
Feature activation-1.97e-01

Pos logit contributions
�士+0.105
ciating+0.100
iev+0.097
��極+0.096
 EDIT+0.094
Neg logit contributions
alsh-0.119
roller-0.103
roid-0.102
ndra-0.101
rador-0.100
Token,
Token ID11
Feature activation-1.17e-01

Pos logit contributions
alsh+0.729
roller+0.615
roid+0.608
ndra+0.599
rador+0.592
Neg logit contributions
�士-0.911
ciating-0.875
iev-0.854
��極-0.842
 EDIT-0.832
Token grows
Token ID13676
Feature activation-5.28e-01

Pos logit contributions
alsh+0.478
roller+0.411
roid+0.407
ndra+0.402
rador+0.397
Neg logit contributions
�士-0.494
ciating-0.473
iev-0.460
��極-0.454
 EDIT-0.446
Token fruit
Token ID8234
Feature activation-8.02e-01

Pos logit contributions
alsh+2.308
roller+2.001
roid+1.989
ndra+1.961
rador+1.945
Neg logit contributions
�士-2.100
ciating-2.000
iev-1.924
��極-1.909
 EDIT-1.865
Token and
Token ID290
Feature activation-3.32e-01

Pos logit contributions
alsh+2.949
roller+2.481
roid+2.472
ndra+2.408
rador+2.391
Neg logit contributions
�士-3.755
ciating-3.576
iev-3.476
��極-3.467
 EDIT-3.394
Token vegetables
Token ID13701
Feature activation-3.61e-01

Pos logit contributions
alsh+1.458
roller+1.264
roid+1.257
ndra+1.240
rador+1.224
Neg logit contributions
�士-1.313
ciating-1.259
iev-1.215
��極-1.203
 EDIT-1.175
Token,
Token ID11
Feature activation-2.92e-01

Pos logit contributions
alsh+1.414
roller+1.202
roid+1.192
ndra+1.172
rador+1.160
Neg logit contributions
�士-1.609
ciating-1.537
iev-1.495
��極-1.480
 EDIT-1.453
Token keeps
Token ID7622
Feature activation-3.27e-01

Pos logit contributions
alsh+1.228
roller+1.056
roid+1.050
ndra+1.036
rador+1.021
Neg logit contributions
�士-1.217
ciating-1.167
iev-1.125
��極-1.123
 EDIT-1.088
Token honey
Token ID12498
Feature activation-4.90e-01

Pos logit contributions
alsh+1.483
roller+1.296
roid+1.285
ndra+1.270
rador+1.258
Neg logit contributions
�士-1.246
ciating-1.184
iev-1.150
��極-1.135
 EDIT-1.113
Token.
Token ID13
Feature activation-2.30e-01

Pos logit contributions
�士+0.166
ciating+0.159
iev+0.156
��極+0.153
 EDIT+0.152
Neg logit contributions
alsh-0.152
roller-0.130
roid-0.128
ndra-0.127
rador-0.126
Token
Token ID198
Feature activation-6.35e-02

Pos logit contributions
alsh+1.066
roller+0.934
roid+0.924
ndra+0.915
rador+0.906
Neg logit contributions
�士-0.854
ciating-0.813
iev-0.788
��極-0.774
 EDIT-0.761
Token
Token ID198
Feature activation+1.01e-01

Pos logit contributions
alsh+0.266
roller+0.231
roid+0.228
ndra+0.226
rador+0.222
Neg logit contributions
�士-0.268
ciating-0.254
��極-0.245
iev-0.244
 Afric-0.236
TokenP
Token ID47
Feature activation-2.28e-01

Pos logit contributions
�士+0.389
ciating+0.374
iev+0.367
 EDIT+0.356
 Iz+0.354
Neg logit contributions
alsh-0.447
roller-0.383
roid-0.382
ndra-0.380
rador-0.379
Tokenel
Token ID417
Feature activation-6.29e-01

Pos logit contributions
alsh+0.926
roller+0.794
roid+0.785
ndra+0.777
rador+0.769
Neg logit contributions
�士-0.971
ciating-0.933
iev-0.910
��極-0.891
 EDIT-0.884
Tokenoton
Token ID18970
Feature activation-9.20e-01

Pos logit contributions
alsh+2.171
roller+1.814
roid+1.796
ndra+1.751
uca+1.734
Neg logit contributions
�士-3.091
ciating-2.949
iev-2.860
��極-2.858
 EDIT-2.818
Token
Token ID198
Feature activation+2.90e-01

Pos logit contributions
alsh+3.928
roller+3.418
roid+3.368
ndra+3.324
uca+3.294
Neg logit contributions
�士-3.724
ciating-3.519
��極-3.403
iev-3.391
 EDIT-3.287
Token
Token ID198
Feature activation+2.46e-01

Pos logit contributions
�士+1.117
ciating+1.073
iev+1.055
 EDIT+1.026
 Buk+1.025
Neg logit contributions
alsh-1.280
roller-1.109
roid-1.098
ndra-1.088
rador-1.082
TokenBased
Token ID15001
Feature activation+5.37e-02

Pos logit contributions
�士+0.948
ciating+0.914
iev+0.899
 EDIT+0.871
 Iz+0.867
Neg logit contributions
alsh-1.075
roid-0.919
roller-0.915
ndra-0.912
rador-0.911
Token on
Token ID319
Feature activation-1.08e-01

Pos logit contributions
�士+0.222
ciating+0.212
iev+0.207
��極+0.203
 EDIT+0.202
Neg logit contributions
alsh-0.224
roller-0.194
roid-0.192
ndra-0.190
rador-0.187
Token the
Token ID262
Feature activation+2.00e-01

Pos logit contributions
alsh+0.507
roller+0.444
roid+0.440
ndra+0.436
rador+0.432
Neg logit contributions
�士-0.394
ciating-0.374
iev-0.364
��極-0.356
 EDIT-0.354
Token Share
Token ID8734
Feature activation-5.02e-01

Pos logit contributions
�士+1.764
ciating+1.676
iev+1.629
��極+1.595
 EDIT+1.585
Neg logit contributions
alsh-2.363
roller-2.074
roid-2.058
ndra-2.037
rador-2.025
Token this
Token ID428
Feature activation-1.41e-02

Pos logit contributions
alsh+2.199
roid+1.951
ndra+1.945
roller+1.941
uca+1.869
Neg logit contributions
�士-2.013
ciating-1.936
��極-1.866
iev-1.768
 EDIT-1.741
Token comment
Token ID2912
Feature activation+5.72e-01

Pos logit contributions
alsh+0.059
roller+0.052
roid+0.052
ndra+0.050
uca+0.049
Neg logit contributions
�士-0.060
��極-0.056
ciating-0.055
iev-0.053
 EDIT-0.052
Token on
Token ID319
Feature activation-1.25e-01

Pos logit contributions
�士+2.353
ciating+2.282
iev+2.238
 EDIT+2.186
 Buk+2.176
Neg logit contributions
alsh-2.375
roller-2.031
roid-2.017
ndra-1.988
rador-1.978
Token Facebook
Token ID3203
Feature activation-2.25e-01

Pos logit contributions
alsh+0.609
roller+0.537
roid+0.532
ndra+0.527
rador+0.523
Neg logit contributions
�士-0.431
ciating-0.409
iev-0.396
��極-0.388
 EDIT-0.382
Token Share
Token ID8734
Feature activation-6.93e-01

Pos logit contributions
alsh+1.098
roller+0.962
roid+0.956
rador+0.941
ndra+0.940
Neg logit contributions
�士-0.776
ciating-0.740
iev-0.712
 Buk-0.707
 EDIT-0.706
Token this
Token ID428
Feature activation+1.18e-01

Pos logit contributions
alsh+3.051
ndra+2.748
roid+2.716
roller+2.711
uca+2.647
Neg logit contributions
�士-2.778
ciating-2.557
��極-2.556
iev-2.402
 seiz-2.401
Token comment
Token ID2912
Feature activation+6.45e-01

Pos logit contributions
�士+0.427
ciating+0.410
iev+0.402
 EDIT+0.390
 Buk+0.389
Neg logit contributions
alsh-0.550
roller-0.481
roid-0.475
ndra-0.472
rador-0.470
Token on
Token ID319
Feature activation+8.45e-02

Pos logit contributions
iev+2.425
�士+2.415
ciating+2.395
 EDIT+2.369
 Buk+2.351
Neg logit contributions
alsh-2.759
roller-2.368
roid-2.352
rador-2.339
ndra-2.319
Token Twitter
Token ID3009
Feature activation-4.67e-01

Pos logit contributions
�士+0.362
ciating+0.347
iev+0.337
��極+0.333
 EDIT+0.328
Neg logit contributions
alsh-0.342
roller-0.294
roid-0.290
ndra-0.287
rador-0.284
Token
Token ID198
Feature activation-3.22e-01

Pos logit contributions
alsh+2.004
roller+1.731
roid+1.713
ndra+1.697
rador+1.672
Neg logit contributions
�士-1.887
ciating-1.798
iev-1.745
��極-1.725
 EDIT-1.678
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
alsh+0.110
roller+0.094
roid+0.093
ndra+0.091
rador+0.090
Neg logit contributions
�士-0.123
ciating-0.118
iev-0.115
��極-0.113
 EDIT-0.112
Token
Token ID198
Feature activation+1.94e-01

Pos logit contributions
�士+0.745
ciating+0.703
iev+0.687
 EDIT+0.675
 Iz+0.672
Neg logit contributions
alsh-0.942
roller-0.825
roid-0.818
ndra-0.806
rador-0.806
Token
Token ID198
Feature activation+2.10e-01

Pos logit contributions
�士+0.773
ciating+0.738
iev+0.719
��極+0.706
 EDIT+0.698
Neg logit contributions
alsh-0.840
roller-0.728
roid-0.720
ndra-0.713
rador-0.706
TokenAdvertisement
Token ID4723
Feature activation-1.09e-01

Pos logit contributions
�士+0.851
ciating+0.816
iev+0.801
 EDIT+0.776
 Iz+0.774
Neg logit contributions
alsh-0.883
roller-0.753
roid-0.751
rador-0.746
ndra-0.745
Token Continue
Token ID10054
Feature activation-2.70e-01

Pos logit contributions
alsh+0.498
roller+0.435
roid+0.430
ndra+0.426
rador+0.420
Neg logit contributions
�士-0.417
ciating-0.395
iev-0.382
��極-0.377
 Buk-0.368
Token reading
Token ID3555
Feature activation-8.88e-01

Pos logit contributions
alsh+1.461
roller+1.316
roid+1.294
ndra+1.286
rador+1.263
Neg logit contributions
�士-0.813
ciating-0.742
��極-0.711
iev-0.700
 EDIT-0.665
Token the
Token ID262
Feature activation-4.61e-01

Pos logit contributions
alsh+3.684
roller+3.217
roid+3.189
ndra+3.175
rador+3.069
Neg logit contributions
�士-3.786
ciating-3.544
��極-3.449
iev-3.326
 Ezek-3.254
Token main
Token ID1388
Feature activation-5.83e-01

Pos logit contributions
alsh+1.730
roller+1.469
roid+1.461
ndra+1.437
rador+1.394
Neg logit contributions
�士-2.160
ciating-2.049
��極-1.984
iev-1.968
 Buk-1.919
Token story
Token ID1621
Feature activation-7.03e-01

Pos logit contributions
alsh+2.222
roller+1.894
roid+1.880
ndra+1.858
rador+1.805
Neg logit contributions
�士-2.718
ciating-2.553
��極-2.479
iev-2.444
 Afric-2.385
Token
Token ID198
Feature activation-3.86e-01

Pos logit contributions
alsh+2.718
roller+2.352
roid+2.313
ndra+2.299
Switch+2.257
Neg logit contributions
�士-3.268
ciating-3.045
��極-2.960
 seiz-2.869
iev-2.858
Token
Token ID198
Feature activation-2.97e-01

Pos logit contributions
alsh+1.516
roller+1.315
roid+1.298
ndra+1.279
Switch+1.256
Neg logit contributions
�士-1.784
ciating-1.669
��極-1.636
iev-1.563
 seiz-1.553
TokenChina
Token ID14581
Feature activation+3.07e-01

Pos logit contributions
�士+0.169
ciating+0.162
iev+0.158
��極+0.154
 EDIT+0.153
Neg logit contributions
alsh-0.195
roller-0.169
roid-0.168
ndra-0.166
rador-0.165
Token punished
Token ID16851
Feature activation-4.71e-01

Pos logit contributions
�士+1.194
ciating+1.132
iev+1.114
 Buk+1.095
 EDIT+1.091
Neg logit contributions
alsh-1.348
roller-1.166
roid-1.151
ndra-1.142
rador-1.142
Token almost
Token ID2048
Feature activation-3.53e-01

Pos logit contributions
alsh+2.217
roller+1.966
roid+1.952
ndra+1.934
rador+1.901
Neg logit contributions
�士-1.687
ciating-1.606
��極-1.541
iev-1.534
 EDIT-1.470
Token 300
Token ID5867
Feature activation-3.71e-01

Pos logit contributions
alsh+1.655
roller+1.469
roid+1.461
ndra+1.436
rador+1.422
Neg logit contributions
�士-1.275
ciating-1.200
iev-1.159
��極-1.155
 EDIT-1.123
Token,
Token ID11
Feature activation-1.41e-01

Pos logit contributions
alsh+1.645
roller+1.440
roid+1.425
ndra+1.406
rador+1.394
Neg logit contributions
�士-1.441
ciating-1.378
iev-1.332
��極-1.312
 EDIT-1.290
Token000
Token ID830
Feature activation-8.24e-01

Pos logit contributions
alsh+0.638
roller+0.561
roid+0.554
ndra+0.547
rador+0.541
Neg logit contributions
�士-0.547
ciating-0.516
��極-0.499
iev-0.493
 EDIT-0.480
Token officials
Token ID2828
Feature activation+6.57e-02

Pos logit contributions
alsh+3.688
roller+3.275
roid+3.270
ndra+3.186
rador+3.169
Neg logit contributions
�士-3.087
ciating-2.970
iev-2.803
��極-2.786
 EDIT-2.654
Token for
Token ID329
Feature activation-1.48e-01

Pos logit contributions
�士+0.276
ciating+0.264
iev+0.258
��極+0.253
 EDIT+0.251
Neg logit contributions
alsh-0.271
roller-0.233
roid-0.230
ndra-0.228
rador-0.225
Token graft
Token ID38455
Feature activation+3.32e-02

Pos logit contributions
alsh+0.658
roller+0.573
roid+0.567
ndra+0.559
rador+0.556
Neg logit contributions
�士-0.574
ciating-0.550
iev-0.532
��極-0.526
 EDIT-0.514
Token last
Token ID938
Feature activation-3.12e-02

Pos logit contributions
�士+0.133
ciating+0.129
iev+0.127
 Buk+0.124
 Iz+0.124
Neg logit contributions
alsh-0.141
roller-0.121
ndra-0.119
roid-0.119
rador-0.118
Token year
Token ID614
Feature activation+1.81e-01

Pos logit contributions
alsh+0.115
roller+0.097
roid+0.096
ndra+0.095
rador+0.094
Neg logit contributions
�士-0.144
ciating-0.139
iev-0.136
��極-0.134
 Buk-0.133